diff --git a/.env.example b/.env.example index 58acac1..61109d7 100644 --- a/.env.example +++ b/.env.example @@ -33,6 +33,7 @@ MODEL_NAME=google/gemini-2.5-flash # LAYA_DEVICE=cpu # cuda when available # LAYA_MAX_LEN=1024 # LAYA_HEAD_MAX_LEN=512 # raise for choice questions with many options +# LAYA_MPS_AMP_MIN_ROWS=5 # on MPS, fp16 from this many questions (laya's default); unset keeps fp32 # ---- Cua-S1 Nano (the in-process option scorer behind --model cua; needs `uv sync --extra cua`) ---- # CUA_S1_CHECKPOINT=cua-ai/cua-s1-nano-0.1 # a Hugging Face id, or a local directory holding / diff --git a/CHANGELOG.md b/CHANGELOG.md index 7b1eca6..7a21f6a 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -20,8 +20,11 @@ The format follows [Keep a Changelog](https://keepachangelog.com/en/1.1.0/); ver ### Changed -- `--model laya` loads in about 3 s instead of about 35 s: the encoder is built with transformers' weight init - off, since the checkpoint replaces every weight. Weights and answers are unchanged. +- `--model laya` no longer draws the encoder's random weights before the checkpoint replaces them, which took most + of a load of about 40 s on CPU. The `laya` extra now needs laya 0.3.9 or later, which skips the draw itself, + and the lock moves from 0.3.5 to 0.3.20. Weights and answers are unchanged: laya 0.3.10 and later run a request + of five or more questions in fp16 on MPS, which moves the answers, so `--model laya` keeps such requests in fp32 + unless `LAYA_MPS_AMP_MIN_ROWS` is set. - `--model` picks the model on every agent, on `decide` and on `probe`: `jev`, `laya`, `cua`, `llm`, `random` or `rule`. The results table's column, the replay page's badge data and a browser run's `answer.json` name it `model` as well; the replay still reads the `slot` key of records written by 0.1.0. diff --git a/docs/configuration.md b/docs/configuration.md index 7c71622..ff265fd 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -32,6 +32,7 @@ Variables can be exported in your shell or placed in a `.env` file at the root o | `LAYA_DEVICE` | `laya` model | `(library default)` | PyTorch device for Laya model evaluation; passes None so the library selects CUDA, MPS, or CPU. | | `LAYA_MAX_LEN` | `laya` model | `(checkpoint default)` | Maximum token sequence length for Laya state representation; overrides checkpoint window only when set. | | `LAYA_HEAD_MAX_LEN` | `laya` model | `(checkpoint default)` | Maximum token sequence length for Laya decision head options; overrides checkpoint window only when set. | +| `LAYA_MPS_AMP_MIN_ROWS` | `laya` model | *(unset: fp32)* | Laya's own variable: on MPS, requests with at least this many questions run in fp16. Unset, `--model laya` keeps every request in fp32, as on CPU; `5` is Laya's default. fp16 moves the probabilities and can flip a close decision. A value that is not a whole number is a configuration error. | | `CUA_S1_CHECKPOINT` | `cua` model | `cua-ai/cua-s1-nano-0.1` | Hugging Face checkpoint ID or local directory for Cua-S1 Nano option scorer. | | `CUA_S1_SUBFOLDER` | `cua` model | `text` | Subfolder within checkpoint directory containing text option scoring weights. | | `CUA_S1_DEVICE` | `cua` model | `auto` | PyTorch device used for Cua-S1 Nano evaluation (`auto`, `cpu`, `cuda`, or `mps`). | diff --git a/docs/results/laya-upgrade/README.md b/docs/results/laya-upgrade/README.md new file mode 100644 index 0000000..03d8c7c --- /dev/null +++ b/docs/results/laya-upgrade/README.md @@ -0,0 +1,84 @@ +# laya 0.3.5 → 0.3.20: same answers from `--model laya` + +Reproduces the evidence for #37: `--model laya` gives the same answers on main and on that branch, on CPU and +on MPS, and the answers move only when Laya's MPS fp16 is turned back on. + +| file | does | +|---|---| +| `run.sh` | checks out both commits, installs each one's lock, runs every case below, prints the tables | +| `laya_ab.py` | one fresh process: load through `LayaModel.from_env()`, answer the 30 ticket-router tickets, write a JSON | +| `compare.py` | the tables from those JSONs | +| `records/` | the 28 JSONs of the recorded run below | + +## Steps + +1. Use a Mac with Apple silicon for the MPS cases (on other machines, step 4 with `DEVICES=cpu`), with + `git` and `uv` installed and this repository cloned. +2. Fetch both checkpoints once, about 1.4 GB (`english` 804 MB, `multilingual` 614 MB): + + ```sh + uv run --extra laya python -c "import laya; laya.load('convaiinnovations/laya', device='cpu'); laya.load('convaiinnovations/laya', device='cpu', subfolder='multilingual')" + ``` + +3. Fetch the head commit. It is on #37's branch only, which a clone of ThinkFlowLab/system1-agents does not + fetch (with `origin` pointing there): + + ```sh + git fetch origin pull/37/head + ``` + +4. From the repository root, with the baseline and head commits: + + ```sh + HF_HUB_OFFLINE=1 docs/results/laya-upgrade/run.sh . 222e656 c197fe6 + ``` + + About 30 minutes on an M1 Pro. It writes to `evals/results/laya-upgrade` (ignored by git), or to the + folder given as a fourth argument, which must be empty or new. `RUNS` (default 3), `DEVICES` (`cpu mps`) + and `CHECKPOINTS` (`english multilingual`) narrow it. The checkouts go to a temporary folder and are removed + at the end. Each run's output is in `logs/`; a failing run stops `run.sh` and prints the end of its log. +5. To compare with the recorded run, `python docs/results/laya-upgrade/compare.py docs/results/laya-upgrade/records`. + +## What it runs + +Each run is one process. It loads the model, then for each of the 30 tickets in +`s1a/agents/_data/ticket_router_eval.jsonl` asks one choice question, one noul question, and one request of +six questions (the choice and five nouls). Six questions is the case that changed: from 0.3.10 Laya answers a +request of five or more questions in fp16 on MPS, and #37 keeps it in fp32. + +| case | runs | +|---|---| +| baseline and head, each checkpoint, each device | `RUNS` each, alternating baseline and head | +| head with `LAYA_MPS_AMP_MIN_ROWS=5` (Laya's default turned back on), MPS | 1 per checkpoint | +| baseline without its weight-init skip, CPU | 1 per checkpoint | + +Every JSON records the commit, the laya, torch and transformers versions, the checkpoint revision, the +device and the Laya variables that were set. + +## Reading the output + +``` +| checkpoint | device | load s, baseline | load s, head | ... | answers | +| convaiinnovations/laya | mps | 9.8 / 7.4 / 7.8 | 9.6 / 7.7 / 7.9 | ... | identical (3 + 3 runs) | +``` + +- `answers` is `identical` when every choice, probability, confidence and noul value of every run equals the + first baseline run's. That is the claim; a `DIFFERENT` row disproves it. +- The `LAYA_MPS_AMP_MIN_ROWS=5` lines show what the fp32 default prevents: the largest probability change + and each decision that changed, by ticket id. On an M1 Pro, `multilingual` changed two. +- The no-skip lines show the load the weight-init skip saves, now done by laya itself. +- Load and latency columns are for comparing the two sides of one row, run alternately on the same machine. + The first load after the checkout can include reading the model files from disk. + +## Recorded run + +`records/` is the output of step 4 on 2026-10-05: Apple M1 Pro (16 GB), macOS 26.1, Python 3.14, torch 2.14.0, +transformers 5.17.0, checkpoint revision `7b928d8`, baseline `222e656` (laya 0.3.5), head `c197fe6` (laya 0.3.20). +The machine had other work running (1-min load average about 6 to 10). All four rows are `identical`; with +`LAYA_MPS_AMP_MIN_ROWS=5`, `multilingual` changed `t_6cb98186dde0` (pick, logistics to returns) and +`t_f5251390fb88` (cancel, 0.4959 to 0.5074); without the skip the baseline loaded in 36.8 s (`english`) and +42.5 s (`multilingual`) against 6 to 10 s with it. The first `english` CPU load of each side (26.2 and 24.8 s) +read the model files from disk. + +Not covered: the `typed-decisions` checkpoint, a local checkpoint path, transformers 4.x, CUDA, and Apple chips +other than the M1 Pro. diff --git a/docs/results/laya-upgrade/compare.py b/docs/results/laya-upgrade/compare.py new file mode 100644 index 0000000..be7a29e --- /dev/null +++ b/docs/results/laya-upgrade/compare.py @@ -0,0 +1,83 @@ +# coding: utf-8 +"""Tables from the outputs of laya_ab.py: python compare.py records/ + +For each checkpoint and device: load time and latency per run for baseline and head, and whether every +answer of every run equals the first baseline run's. Then every run with LAYA_MPS_AMP_MIN_ROWS set, against +the baseline on the same device: the largest change in any probability and each decision that changed. +""" + +import json +import sys +from collections import defaultdict +from pathlib import Path + +ANSWERS = ("one_question", "one_noul", "six_questions") + + +def answers(record: dict) -> list: + return [{key: ticket[key] for key in ANSWERS} for ticket in record["tickets"]] + + +def changes(reference: dict, record: dict) -> tuple[float, list[str]]: + largest, changed = 0.0, [] + for a, b in zip(reference["tickets"], record["tickets"], strict=True): + for part in ANSWERS: + for name, value in a[part].items(): + other = b[part][name] + if name == "probabilities": + largest = max([largest] + [abs(p - other[option]) for option, p in value.items()]) + elif name == "pick": + if value != other: + changed.append(f"{a['id']} {part} pick: {value} -> {other}") + elif name != "confidence": + largest = max(largest, abs(value - other)) + if (value >= 0.5) != (other >= 0.5): + changed.append(f"{a['id']} {part} {name}: {value} -> {other}") + return round(largest, 4), changed + + +def main(folder: str) -> None: + records = [json.loads(path.read_text(encoding="utf-8")) for path in sorted(Path(folder).glob("*.json"))] + cells: dict[tuple[str, str], dict[str, list[dict]]] = defaultdict(lambda: defaultdict(list)) + for record in records: + kind = ( + "no-skip" + if record["no_skip"] + else "override" + if "LAYA_MPS_AMP_MIN_ROWS" in record["environment"] + else record["label"] + ) + cells[(record["checkpoint"], record["device"])][kind].append(record) + for record in records[:1]: + print(f"{record['chip']}, {record['os']}, torch {record['torch']}, transformers {record['transformers']}") + for label in ("baseline", "head"): + seen = {(r["s1a_commit"][:7], r["laya"], r["checkpoint_revision"][:7]) for r in records if r["label"] == label} + print(f"{label}: " + "; ".join(f"s1a {c}, laya {v}, checkpoint revision {rev}" for c, v, rev in sorted(seen))) + print() + print( + "| checkpoint | device | load s, baseline | load s, head | one question p50 ms, baseline | head | six questions p50 ms, baseline | head | answers |" + ) + print("|---|---|---|---|---|---|---|---|---|") + for (checkpoint, device), kinds in sorted(cells.items()): + base, head = kinds["baseline"], kinds["head"] + same = all(answers(r) == answers(base[0]) for r in base + head) + column = lambda rows, key: " / ".join(str(r[key]) for r in rows) # noqa: E731 + print( + f"| {checkpoint} | {device} | {column(base, 'load_s')} | {column(head, 'load_s')} | " + f"{column(base, 'one_question_p50_ms')} | {column(head, 'one_question_p50_ms')} | " + f"{column(base, 'six_questions_p50_ms')} | {column(head, 'six_questions_p50_ms')} | " + f"{'identical' if same else 'DIFFERENT'} ({len(base)} + {len(head)} runs) |" + ) + for (checkpoint, device), kinds in sorted(cells.items()): + for record in kinds["override"]: + largest, changed = changes(kinds["baseline"][0], record) + setting = record["environment"]["LAYA_MPS_AMP_MIN_ROWS"] + print(f"\n{checkpoint} on {device}, head with LAYA_MPS_AMP_MIN_ROWS={setting}, against baseline:") + print(f" largest probability change {largest}; decisions changed: {len(changed)}") + for line in changed: + print(" " + line) + for record in kinds["no-skip"]: + print(f"\n{checkpoint} on {device}, baseline without its weight-init skip: load {record['load_s']} s") + + +main(sys.argv[1]) diff --git a/docs/results/laya-upgrade/laya_ab.py b/docs/results/laya-upgrade/laya_ab.py new file mode 100644 index 0000000..420476d --- /dev/null +++ b/docs/results/laya-upgrade/laya_ab.py @@ -0,0 +1,132 @@ +# coding: utf-8 +"""One run of `--model laya`'s backend in a fresh process; run.sh calls it from each checkout's root. + +It loads the model through `LayaModel.from_env()`, then for each of the 30 tickets in the repository's +ticket-router file asks one choice question, one noul question, and one request of six questions. The JSON +it writes holds every answer, the timings, and what ran: commit, library versions, checkpoint revision, +device and the Laya variables that were set. `--no-skip` loads without main's weight-init skip. +""" + +import argparse +import asyncio +import json +import os +import platform +import statistics +import subprocess +import time +from importlib import metadata +from pathlib import Path + +T0 = time.perf_counter() +NOULS = { + "refund": "Does the customer ask for a refund?", + "angry": "Is the customer angry?", + "cancel": "Does the customer want to cancel the order?", + "human": "Does the customer ask for a human?", + "late": "Is a delivery late?", +} +LAYA_VARIABLES = ( + "LAYA_MODEL", + "LAYA_SUBFOLDER", + "LAYA_DEVICE", + "LAYA_MAX_LEN", + "LAYA_HEAD_MAX_LEN", + "LAYA_MPS_AMP_MIN_ROWS", +) + + +def run(*command: str) -> str: + try: + return subprocess.run(command, capture_output=True, text=True, timeout=10, check=True).stdout.strip() + except (OSError, subprocess.SubprocessError): + return "" + + +def checkpoint_revision(repo: str) -> str: + """The commit the local Hugging Face cache has for the repository's main.""" + from huggingface_hub.constants import HF_HUB_CACHE + + ref = Path(HF_HUB_CACHE) / f"models--{repo.replace('/', '--')}" / "refs" / "main" + return ref.read_text().strip() if ref.exists() else "" + + +async def main() -> None: + parser = argparse.ArgumentParser(description=__doc__.splitlines()[0]) + parser.add_argument("--label", required=True, help="baseline or head") + parser.add_argument("--out", required=True) + parser.add_argument("--no-skip", action="store_true", help="baseline only: load without its weight-init skip") + args = parser.parse_args() + + from s1a.agents.ticket_router import DEFAULT_DATASET, PUBLIC_FIELDS, QUEUES, RULES, load_tickets + from s1a.decision_models import ChoiceQuestion, NoulQuestion, Observation + from s1a.decision_models import laya as laya_module + + if args.no_skip: + import contextlib + + laya_module.without_weight_init = contextlib.nullcontext + model = laya_module.LayaModel.from_env() + load_s = time.perf_counter() - T0 + + pick = ChoiceQuestion(dict(QUEUES), rules=RULES) + tickets, one_ms, six_ms = [], [], [] + for row in load_tickets(DEFAULT_DATASET): + observation = Observation({key: row[key] for key in PUBLIC_FIELDS if key in row}) + started = time.perf_counter() + one = await model.decide_many(observation, {"pick": pick}) + one_ms.append((time.perf_counter() - started) * 1000) + noul = await model.decide_many(observation, {"refund": NoulQuestion(NOULS["refund"])}) + started = time.perf_counter() + six = await model.decide_many(observation, {"pick": pick, **{k: NoulQuestion(v) for k, v in NOULS.items()}}) + six_ms.append((time.perf_counter() - started) * 1000) + choice, six_choice = one.choice("pick"), six.choice("pick") + tickets.append( + { + "id": row["id"], + "one_question": { + "pick": choice.key, + "probabilities": choice.probabilities, + "confidence": choice.confidence, + }, + "one_noul": {"refund": noul.noul("refund").p}, + "six_questions": { + "pick": six_choice.key, + "probabilities": six_choice.probabilities, + "confidence": six_choice.confidence, + **{k: six.noul(k).p for k in NOULS}, + }, + } + ) + agent = model._agent + repo = os.getenv("LAYA_MODEL") or laya_module.LAYA_DEFAULT_MODEL + record = { + "label": args.label, + "no_skip": args.no_skip, + "s1a_commit": run("git", "rev-parse", "HEAD"), + "laya": metadata.version("laya"), + "torch": metadata.version("torch"), + "transformers": metadata.version("transformers"), + "python": platform.python_version(), + "chip": run("sysctl", "-n", "machdep.cpu.brand_string"), + "os": "macOS " + platform.mac_ver()[0], + "checkpoint": model.model, + "checkpoint_revision": checkpoint_revision(repo), + "device": str(agent.device), + "mps_amp_min_rows": getattr(agent, "mps_amp_min_rows", None), + "environment": {name: os.environ[name] for name in LAYA_VARIABLES if os.getenv(name)}, + "load_average_1m": round(os.getloadavg()[0], 1), + "load_s": round(load_s, 1), + "one_question_p50_ms": round(statistics.median(one_ms[1:])), + "six_questions_p50_ms": round(statistics.median(six_ms[1:])), + "tickets": tickets, + } + head = {key: value for key, value in record.items() if key != "tickets"} + lines = [json.dumps(head)[:-1] + ', "tickets": ['] + [ + " " + json.dumps(ticket) + ("," if n < len(tickets) - 1 else "") for n, ticket in enumerate(tickets) + ] + Path(args.out).write_text("\n".join(lines) + "\n]}\n", encoding="utf-8") # one ticket per line + print(args.out, record["laya"], record["device"], "load", record["load_s"], "s") + + +asyncio.run(main()) diff --git a/docs/results/laya-upgrade/records/baseline-english-cpu-1.json b/docs/results/laya-upgrade/records/baseline-english-cpu-1.json new file mode 100644 index 0000000..2a1b9e5 --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-english-cpu-1.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": false, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": null, "environment": {"LAYA_DEVICE": "cpu"}, "load_average_1m": 11.6, "load_s": 26.2, "one_question_p50_ms": 295, "six_questions_p50_ms": 1111, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-english-cpu-2.json b/docs/results/laya-upgrade/records/baseline-english-cpu-2.json new file mode 100644 index 0000000..134d5ac --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-english-cpu-2.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": false, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": null, "environment": {"LAYA_DEVICE": "cpu"}, "load_average_1m": 9.0, "load_s": 7.4, "one_question_p50_ms": 255, "six_questions_p50_ms": 917, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-english-cpu-3.json b/docs/results/laya-upgrade/records/baseline-english-cpu-3.json new file mode 100644 index 0000000..d95e217 --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-english-cpu-3.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": false, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": null, "environment": {"LAYA_DEVICE": "cpu"}, "load_average_1m": 6.6, "load_s": 6.6, "one_question_p50_ms": 249, "six_questions_p50_ms": 908, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-english-cpu-noskip.json b/docs/results/laya-upgrade/records/baseline-english-cpu-noskip.json new file mode 100644 index 0000000..0346391 --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-english-cpu-noskip.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": true, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": null, "environment": {"LAYA_DEVICE": "cpu"}, "load_average_1m": 11.5, "load_s": 36.8, "one_question_p50_ms": 292, "six_questions_p50_ms": 1080, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-english-mps-1.json b/docs/results/laya-upgrade/records/baseline-english-mps-1.json new file mode 100644 index 0000000..60455c6 --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-english-mps-1.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": false, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": null, "environment": {"LAYA_DEVICE": "mps"}, "load_average_1m": 9.9, "load_s": 9.8, "one_question_p50_ms": 91, "six_questions_p50_ms": 410, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-english-mps-2.json b/docs/results/laya-upgrade/records/baseline-english-mps-2.json new file mode 100644 index 0000000..e5a2d3e --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-english-mps-2.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": false, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": null, "environment": {"LAYA_DEVICE": "mps"}, "load_average_1m": 8.5, "load_s": 7.4, "one_question_p50_ms": 85, "six_questions_p50_ms": 386, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-english-mps-3.json b/docs/results/laya-upgrade/records/baseline-english-mps-3.json new file mode 100644 index 0000000..3f02563 --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-english-mps-3.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": false, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": null, "environment": {"LAYA_DEVICE": "mps"}, "load_average_1m": 5.6, "load_s": 7.8, "one_question_p50_ms": 86, "six_questions_p50_ms": 384, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-multilingual-cpu-1.json b/docs/results/laya-upgrade/records/baseline-multilingual-cpu-1.json new file mode 100644 index 0000000..7519ac9 --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-multilingual-cpu-1.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": false, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": null, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "cpu"}, "load_average_1m": 10.2, "load_s": 9.0, "one_question_p50_ms": 105, "six_questions_p50_ms": 378, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-multilingual-cpu-2.json b/docs/results/laya-upgrade/records/baseline-multilingual-cpu-2.json new file mode 100644 index 0000000..1af9fd0 --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-multilingual-cpu-2.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": false, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": null, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "cpu"}, "load_average_1m": 7.1, "load_s": 8.2, "one_question_p50_ms": 112, "six_questions_p50_ms": 388, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-multilingual-cpu-3.json b/docs/results/laya-upgrade/records/baseline-multilingual-cpu-3.json new file mode 100644 index 0000000..6a609e2 --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-multilingual-cpu-3.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": false, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": null, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "cpu"}, "load_average_1m": 6.1, "load_s": 9.9, "one_question_p50_ms": 111, "six_questions_p50_ms": 382, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-multilingual-cpu-noskip.json b/docs/results/laya-upgrade/records/baseline-multilingual-cpu-noskip.json new file mode 100644 index 0000000..6b51066 --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-multilingual-cpu-noskip.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": true, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": null, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "cpu"}, "load_average_1m": 10.6, "load_s": 42.5, "one_question_p50_ms": 129, "six_questions_p50_ms": 449, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-multilingual-mps-1.json b/docs/results/laya-upgrade/records/baseline-multilingual-mps-1.json new file mode 100644 index 0000000..021a09f --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-multilingual-mps-1.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": false, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": null, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "mps"}, "load_average_1m": 9.0, "load_s": 8.6, "one_question_p50_ms": 46, "six_questions_p50_ms": 183, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-multilingual-mps-2.json b/docs/results/laya-upgrade/records/baseline-multilingual-mps-2.json new file mode 100644 index 0000000..7e504b9 --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-multilingual-mps-2.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": false, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": null, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "mps"}, "load_average_1m": 6.1, "load_s": 8.2, "one_question_p50_ms": 41, "six_questions_p50_ms": 162, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/baseline-multilingual-mps-3.json b/docs/results/laya-upgrade/records/baseline-multilingual-mps-3.json new file mode 100644 index 0000000..81757ef --- /dev/null +++ b/docs/results/laya-upgrade/records/baseline-multilingual-mps-3.json @@ -0,0 +1,32 @@ +{"label": "baseline", "no_skip": false, "s1a_commit": "222e656a1a53d7d19c815d8ac66defaad557b1c5", "laya": "0.3.5", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": null, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "mps"}, "load_average_1m": 5.3, "load_s": 10.7, "one_question_p50_ms": 42, "six_questions_p50_ms": 173, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/head-english-cpu-1.json b/docs/results/laya-upgrade/records/head-english-cpu-1.json new file mode 100644 index 0000000..70587e7 --- /dev/null +++ b/docs/results/laya-upgrade/records/head-english-cpu-1.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": 1000000000, "environment": {"LAYA_DEVICE": "cpu"}, "load_average_1m": 10.8, "load_s": 24.8, "one_question_p50_ms": 271, "six_questions_p50_ms": 1028, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/head-english-cpu-2.json b/docs/results/laya-upgrade/records/head-english-cpu-2.json new file mode 100644 index 0000000..13356f4 --- /dev/null +++ b/docs/results/laya-upgrade/records/head-english-cpu-2.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": 1000000000, "environment": {"LAYA_DEVICE": "cpu"}, "load_average_1m": 9.4, "load_s": 7.2, "one_question_p50_ms": 246, "six_questions_p50_ms": 878, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/head-english-cpu-3.json b/docs/results/laya-upgrade/records/head-english-cpu-3.json new file mode 100644 index 0000000..94b74a9 --- /dev/null +++ b/docs/results/laya-upgrade/records/head-english-cpu-3.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": 1000000000, "environment": {"LAYA_DEVICE": "cpu"}, "load_average_1m": 6.0, "load_s": 6.0, "one_question_p50_ms": 238, "six_questions_p50_ms": 864, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/head-english-mps-1.json b/docs/results/laya-upgrade/records/head-english-mps-1.json new file mode 100644 index 0000000..37bd03d --- /dev/null +++ b/docs/results/laya-upgrade/records/head-english-mps-1.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": 1000000000, "environment": {"LAYA_DEVICE": "mps"}, "load_average_1m": 9.1, "load_s": 9.6, "one_question_p50_ms": 105, "six_questions_p50_ms": 483, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/head-english-mps-2.json b/docs/results/laya-upgrade/records/head-english-mps-2.json new file mode 100644 index 0000000..f575c90 --- /dev/null +++ b/docs/results/laya-upgrade/records/head-english-mps-2.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": 1000000000, "environment": {"LAYA_DEVICE": "mps"}, "load_average_1m": 6.9, "load_s": 7.7, "one_question_p50_ms": 85, "six_questions_p50_ms": 384, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/head-english-mps-3.json b/docs/results/laya-upgrade/records/head-english-mps-3.json new file mode 100644 index 0000000..384a8b9 --- /dev/null +++ b/docs/results/laya-upgrade/records/head-english-mps-3.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": 1000000000, "environment": {"LAYA_DEVICE": "mps"}, "load_average_1m": 5.0, "load_s": 7.9, "one_question_p50_ms": 86, "six_questions_p50_ms": 384, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637, "refund": 0.0857, "angry": 0.1446, "cancel": 0.2958, "human": 0.1046, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604, "refund": 0.0726, "angry": 0.0202, "cancel": 0.315, "human": 0.1674, "late": 0.1803}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679, "refund": 0.113, "angry": 0.0045, "cancel": 0.0649, "human": 0.6697, "late": 0.2328}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752, "refund": 0.0941, "angry": 0.0435, "cancel": 0.1157, "human": 0.1737, "late": 0.2383}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332, "refund": 0.4204, "angry": 0.1585, "cancel": 0.2098, "human": 0.0891, "late": 0.2145}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815, "refund": 0.3421, "angry": 0.1003, "cancel": 0.2162, "human": 0.2848, "late": 0.4191}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692, "refund": 0.2646, "angry": 0.3365, "cancel": 0.7061, "human": 0.0678, "late": 0.3143}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518, "refund": 0.3176, "angry": 0.139, "cancel": 0.1557, "human": 0.0539, "late": 0.6951}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682, "refund": 0.1989, "angry": 0.1317, "cancel": 0.281, "human": 0.1721, "late": 0.4639}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715, "refund": 0.4985, "angry": 0.1378, "cancel": 0.2035, "human": 0.1417, "late": 0.5237}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544, "refund": 0.0592, "angry": 0.0003, "cancel": 0.0767, "human": 0.299, "late": 0.813}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993, "refund": 0.1832, "angry": 0.1662, "cancel": 0.4928, "human": 0.1182, "late": 0.3808}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023, "refund": 0.3032, "angry": 0.0873, "cancel": 0.0886, "human": 0.1253, "late": 0.299}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068, "refund": 0.6541, "angry": 0.7001, "cancel": 0.8855, "human": 0.0654, "late": 0.1647}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857, "refund": 0.8692, "angry": 0.1723, "cancel": 0.4689, "human": 0.219, "late": 0.3584}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1232, "cancel": 0.1504, "human": 0.1451, "late": 0.2638}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645, "refund": 0.9584, "angry": 0.4322, "cancel": 0.3724, "human": 0.0794, "late": 0.4707}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734, "refund": 0.7691, "angry": 0.343, "cancel": 0.7119, "human": 0.1036, "late": 0.2436}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512, "refund": 0.0516, "angry": 0.0627, "cancel": 0.0, "human": 0.0743, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284, "refund": 0.0896, "angry": 0.1878, "cancel": 0.3868, "human": 0.0324, "late": 0.7858}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135, "refund": 0.2098, "angry": 0.4014, "cancel": 0.2939, "human": 0.1266, "late": 0.0477}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445, "refund": 0.3907, "angry": 0.0428, "cancel": 0.3042, "human": 0.1102, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212, "refund": 0.0973, "angry": 0.0624, "cancel": 0.0857, "human": 0.0929, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712, "refund": 0.0003, "angry": 0.0863, "cancel": 0.1, "human": 0.0953, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963, "refund": 0.7914, "angry": 0.1492, "cancel": 0.1032, "human": 0.0893, "late": 0.4479}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573, "refund": 0.1338, "angry": 0.0597, "cancel": 0.0406, "human": 0.1272, "late": 0.1093}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538, "refund": 0.0874, "angry": 0.0001, "cancel": 0.0235, "human": 0.0022, "late": 0.1732}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618, "refund": 0.0917, "angry": 0.227, "cancel": 0.2136, "human": 0.1924, "late": 0.2801}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753, "refund": 0.2141, "angry": 0.1262, "cancel": 0.1931, "human": 0.9542, "late": 0.4719}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003, "refund": 0.1271, "angry": 0.3146, "cancel": 0.728, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/head-english-mps-override5.json b/docs/results/laya-upgrade/records/head-english-mps-override5.json new file mode 100644 index 0000000..2dc1974 --- /dev/null +++ b/docs/results/laya-upgrade/records/head-english-mps-override5.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": 5, "environment": {"LAYA_DEVICE": "mps", "LAYA_MPS_AMP_MIN_ROWS": "5"}, "load_average_1m": 6.0, "load_s": 7.2, "one_question_p50_ms": 92, "six_questions_p50_ms": 433, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9212, "payment": 0.0132, "returns": 0.0226, "account": 0.0131, "human": 0.0298}, "confidence": 0.7637}, "one_noul": {"refund": 0.0857}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9187, "payment": 0.0136, "returns": 0.0232, "account": 0.0137, "human": 0.0309}, "confidence": 0.7579, "refund": 0.0858, "angry": 0.1443, "cancel": 0.296, "human": 0.1045, "late": 0.6946}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8191, "payment": 0.0279, "returns": 0.0556, "account": 0.0261, "human": 0.0713}, "confidence": 0.5604}, "one_noul": {"refund": 0.0726}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.821, "payment": 0.0276, "returns": 0.0548, "account": 0.0259, "human": 0.0707}, "confidence": 0.5637, "refund": 0.0723, "angry": 0.0205, "cancel": 0.3151, "human": 0.1675, "late": 0.1801}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9224, "payment": 0.0116, "returns": 0.028, "account": 0.0113, "human": 0.0266}, "confidence": 0.7679}, "one_noul": {"refund": 0.113}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.921, "payment": 0.0118, "returns": 0.0286, "account": 0.0116, "human": 0.027}, "confidence": 0.7646, "refund": 0.1129, "angry": 0.0047, "cancel": 0.0649, "human": 0.6701, "late": 0.2327}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.6979, "payment": 0.1177, "returns": 0.0832, "account": 0.0331, "human": 0.0681}, "confidence": 0.3752}, "one_noul": {"refund": 0.0941}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.6954, "payment": 0.1182, "returns": 0.0843, "account": 0.0334, "human": 0.0686}, "confidence": 0.3718, "refund": 0.0943, "angry": 0.0433, "cancel": 0.115, "human": 0.1735, "late": 0.2381}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8558, "payment": 0.019, "returns": 0.069, "account": 0.0183, "human": 0.0379}, "confidence": 0.6332}, "one_noul": {"refund": 0.4204}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8569, "payment": 0.019, "returns": 0.0679, "account": 0.0183, "human": 0.0379}, "confidence": 0.635, "refund": 0.4199, "angry": 0.1585, "cancel": 0.2113, "human": 0.0889, "late": 0.2156}}, + {"id": "t_97415027853c", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.7695, "payment": 0.0331, "returns": 0.0945, "account": 0.0311, "human": 0.0719}, "confidence": 0.4815}, "one_noul": {"refund": 0.3421}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.7712, "payment": 0.0329, "returns": 0.0937, "account": 0.031, "human": 0.0712}, "confidence": 0.4842, "refund": 0.341, "angry": 0.1003, "cancel": 0.2152, "human": 0.2832, "late": 0.4184}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0131, "payment": 0.9201, "returns": 0.0446, "account": 0.0092, "human": 0.0129}, "confidence": 0.7692}, "one_noul": {"refund": 0.2646}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0132, "payment": 0.9201, "returns": 0.0445, "account": 0.0093, "human": 0.013}, "confidence": 0.769, "refund": 0.2643, "angry": 0.3348, "cancel": 0.7069, "human": 0.0675, "late": 0.3131}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0462, "payment": 0.8187, "returns": 0.0595, "account": 0.0367, "human": 0.0388}, "confidence": 0.5518}, "one_noul": {"refund": 0.3176}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0458, "payment": 0.8193, "returns": 0.0593, "account": 0.0368, "human": 0.0388}, "confidence": 0.5529, "refund": 0.3174, "angry": 0.1387, "cancel": 0.1555, "human": 0.0537, "late": 0.6949}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.052, "payment": 0.758, "returns": 0.1141, "account": 0.0261, "human": 0.0498}, "confidence": 0.4682}, "one_noul": {"refund": 0.1989}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0523, "payment": 0.7566, "returns": 0.1148, "account": 0.0264, "human": 0.0499}, "confidence": 0.466, "refund": 0.1985, "angry": 0.131, "cancel": 0.2807, "human": 0.1727, "late": 0.4653}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.8786, "returns": 0.0519, "account": 0.0252, "human": 0.0228}, "confidence": 0.6715}, "one_noul": {"refund": 0.4985}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0214, "payment": 0.878, "returns": 0.0523, "account": 0.0254, "human": 0.0228}, "confidence": 0.6704, "refund": 0.4969, "angry": 0.1381, "cancel": 0.2037, "human": 0.1418, "late": 0.5245}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.1038, "payment": 0.6096, "returns": 0.1312, "account": 0.0721, "human": 0.0833}, "confidence": 0.2544}, "one_noul": {"refund": 0.0592}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.1042, "payment": 0.6085, "returns": 0.1312, "account": 0.0725, "human": 0.0835}, "confidence": 0.2531, "refund": 0.059, "angry": 0.0003, "cancel": 0.0772, "human": 0.2958, "late": 0.8124}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4421, "payment": 0.3435, "returns": 0.0814, "account": 0.0504, "human": 0.0826}, "confidence": 0.1993}, "one_noul": {"refund": 0.1832}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4378, "payment": 0.3468, "returns": 0.0817, "account": 0.0511, "human": 0.0826}, "confidence": 0.1975, "refund": 0.183, "angry": 0.1657, "cancel": 0.4935, "human": 0.1181, "late": 0.3811}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.4664, "payment": 0.0361, "returns": 0.4048, "account": 0.0335, "human": 0.0593}, "confidence": 0.3023}, "one_noul": {"refund": 0.3032}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.4626, "payment": 0.0362, "returns": 0.4079, "account": 0.0337, "human": 0.0596}, "confidence": 0.3011, "refund": 0.3039, "angry": 0.0874, "cancel": 0.0885, "human": 0.1259, "late": 0.2993}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1089, "payment": 0.2839, "returns": 0.4909, "account": 0.0464, "human": 0.0699}, "confidence": 0.2068}, "one_noul": {"refund": 0.6541}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1095, "payment": 0.2865, "returns": 0.4877, "account": 0.0463, "human": 0.0701}, "confidence": 0.2053, "refund": 0.6525, "angry": 0.7001, "cancel": 0.8859, "human": 0.0654, "late": 0.1643}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2016, "payment": 0.0325, "returns": 0.6698, "account": 0.0317, "human": 0.0644}, "confidence": 0.3857}, "one_noul": {"refund": 0.8692}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.2002, "payment": 0.0326, "returns": 0.6708, "account": 0.0318, "human": 0.0645}, "confidence": 0.3861, "refund": 0.8682, "angry": 0.1724, "cancel": 0.47, "human": 0.219, "late": 0.358}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.2709, "payment": 0.1105, "returns": 0.521, "account": 0.0466, "human": 0.051}, "confidence": 0.2348}, "one_noul": {"refund": 0.695}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.27, "payment": 0.1107, "returns": 0.5216, "account": 0.0467, "human": 0.0511}, "confidence": 0.2348, "refund": 0.695, "angry": 0.1233, "cancel": 0.1502, "human": 0.1449, "late": 0.2633}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0166, "payment": 0.8635, "returns": 0.0884, "account": 0.0146, "human": 0.0169}, "confidence": 0.6645}, "one_noul": {"refund": 0.9584}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0167, "payment": 0.8632, "returns": 0.0885, "account": 0.0147, "human": 0.017}, "confidence": 0.6639, "refund": 0.9587, "angry": 0.4316, "cancel": 0.3732, "human": 0.0798, "late": 0.4708}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5598, "payment": 0.0247, "returns": 0.3476, "account": 0.0215, "human": 0.0464}, "confidence": 0.3734}, "one_noul": {"refund": 0.7691}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5684, "payment": 0.0252, "returns": 0.3376, "account": 0.022, "human": 0.0468}, "confidence": 0.3739, "refund": 0.7689, "angry": 0.3433, "cancel": 0.7116, "human": 0.1034, "late": 0.2425}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.007, "payment": 0.007, "returns": 0.0216, "account": 0.9551, "human": 0.0092}, "confidence": 0.8512}, "one_noul": {"refund": 0.0516}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0069, "payment": 0.0069, "returns": 0.0212, "account": 0.956, "human": 0.0091}, "confidence": 0.8534, "refund": 0.0515, "angry": 0.0632, "cancel": 0.0, "human": 0.0746, "late": 0.0}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0149, "payment": 0.0105, "returns": 0.0164, "account": 0.9478, "human": 0.0104}, "confidence": 0.8284}, "one_noul": {"refund": 0.0896}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0148, "payment": 0.0105, "returns": 0.0163, "account": 0.9481, "human": 0.0103}, "confidence": 0.829, "refund": 0.0897, "angry": 0.1878, "cancel": 0.3917, "human": 0.0324, "late": 0.786}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0083, "payment": 0.0167, "returns": 0.0183, "account": 0.9419, "human": 0.0148}, "confidence": 0.8135}, "one_noul": {"refund": 0.2098}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0085, "payment": 0.0173, "returns": 0.0186, "account": 0.9406, "human": 0.015}, "confidence": 0.8103, "refund": 0.2109, "angry": 0.4007, "cancel": 0.2936, "human": 0.1265, "late": 0.048}}, + {"id": "t_46f559df489a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0246, "returns": 0.2282, "account": 0.6881, "human": 0.0265}, "confidence": 0.445}, "one_noul": {"refund": 0.3907}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0326, "payment": 0.0248, "returns": 0.2224, "account": 0.6935, "human": 0.0268}, "confidence": 0.4481, "refund": 0.3922, "angry": 0.0426, "cancel": 0.3041, "human": 0.1105, "late": 0.0691}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0159, "payment": 0.0196, "returns": 0.0414, "account": 0.9021, "human": 0.021}, "confidence": 0.7212}, "one_noul": {"refund": 0.0973}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0158, "payment": 0.0195, "returns": 0.0412, "account": 0.9027, "human": 0.0209}, "confidence": 0.7224, "refund": 0.097, "angry": 0.0628, "cancel": 0.0856, "human": 0.093, "late": 0.0825}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0242, "payment": 0.0207, "returns": 0.0388, "account": 0.8987, "human": 0.0176}, "confidence": 0.712}, "one_noul": {"refund": 0.0003}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0243, "payment": 0.0209, "returns": 0.039, "account": 0.8981, "human": 0.0177}, "confidence": 0.7107, "refund": 0.0003, "angry": 0.0865, "cancel": 0.0997, "human": 0.0956, "late": 0.0}}, + {"id": "t_892cab266e67", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.8305, "payment": 0.0202, "returns": 0.0939, "account": 0.0172, "human": 0.0382}, "confidence": 0.5963}, "one_noul": {"refund": 0.7914}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.8311, "payment": 0.0204, "returns": 0.0931, "account": 0.0173, "human": 0.0381}, "confidence": 0.5969, "refund": 0.791, "angry": 0.1485, "cancel": 0.103, "human": 0.0893, "late": 0.4485}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0392, "payment": 0.1537, "returns": 0.0406, "account": 0.7371, "human": 0.0295}, "confidence": 0.4573}, "one_noul": {"refund": 0.1338}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0405, "payment": 0.1584, "returns": 0.0413, "account": 0.7298, "human": 0.03}, "confidence": 0.448, "refund": 0.1336, "angry": 0.0589, "cancel": 0.0403, "human": 0.1277, "late": 0.1099}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "human", "probabilities": {"logistics": 0.2513, "payment": 0.068, "returns": 0.198, "account": 0.0496, "human": 0.4331}, "confidence": 0.1538}, "one_noul": {"refund": 0.0874}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.2519, "payment": 0.0679, "returns": 0.1978, "account": 0.0497, "human": 0.4328}, "confidence": 0.1537, "refund": 0.0869, "angry": 0.0001, "cancel": 0.024, "human": 0.0023, "late": 0.1731}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1923, "payment": 0.0893, "returns": 0.1535, "account": 0.0671, "human": 0.4978}, "confidence": 0.1618}, "one_noul": {"refund": 0.0917}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1948, "payment": 0.0898, "returns": 0.153, "account": 0.0678, "human": 0.4946}, "confidence": 0.1594, "refund": 0.0918, "angry": 0.2269, "cancel": 0.2116, "human": 0.1932, "late": 0.2812}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0272, "payment": 0.826, "returns": 0.0559, "account": 0.0204, "human": 0.0706}, "confidence": 0.5753}, "one_noul": {"refund": 0.2141}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0273, "payment": 0.8265, "returns": 0.0552, "account": 0.0203, "human": 0.0707}, "confidence": 0.5762, "refund": 0.2134, "angry": 0.1257, "cancel": 0.1949, "human": 0.9543, "late": 0.4715}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0203, "payment": 0.0223, "returns": 0.0599, "account": 0.7656, "human": 0.1319}, "confidence": 0.5003}, "one_noul": {"refund": 0.1271}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0202, "payment": 0.0223, "returns": 0.0597, "account": 0.7677, "human": 0.1301}, "confidence": 0.5028, "refund": 0.1273, "angry": 0.3179, "cancel": 0.7278, "human": 1.0, "late": 0.0}} +]} diff --git a/docs/results/laya-upgrade/records/head-multilingual-cpu-1.json b/docs/results/laya-upgrade/records/head-multilingual-cpu-1.json new file mode 100644 index 0000000..b5c8338 --- /dev/null +++ b/docs/results/laya-upgrade/records/head-multilingual-cpu-1.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": 1000000000, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "cpu"}, "load_average_1m": 9.4, "load_s": 8.1, "one_question_p50_ms": 113, "six_questions_p50_ms": 397, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/head-multilingual-cpu-2.json b/docs/results/laya-upgrade/records/head-multilingual-cpu-2.json new file mode 100644 index 0000000..d620e96 --- /dev/null +++ b/docs/results/laya-upgrade/records/head-multilingual-cpu-2.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": 1000000000, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "cpu"}, "load_average_1m": 6.5, "load_s": 7.8, "one_question_p50_ms": 106, "six_questions_p50_ms": 360, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/head-multilingual-cpu-3.json b/docs/results/laya-upgrade/records/head-multilingual-cpu-3.json new file mode 100644 index 0000000..5807359 --- /dev/null +++ b/docs/results/laya-upgrade/records/head-multilingual-cpu-3.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "cpu", "mps_amp_min_rows": 1000000000, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "cpu"}, "load_average_1m": 6.3, "load_s": 10.4, "one_question_p50_ms": 109, "six_questions_p50_ms": 390, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/head-multilingual-mps-1.json b/docs/results/laya-upgrade/records/head-multilingual-mps-1.json new file mode 100644 index 0000000..ac796aa --- /dev/null +++ b/docs/results/laya-upgrade/records/head-multilingual-mps-1.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": 1000000000, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "mps"}, "load_average_1m": 8.1, "load_s": 8.7, "one_question_p50_ms": 40, "six_questions_p50_ms": 162, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/head-multilingual-mps-2.json b/docs/results/laya-upgrade/records/head-multilingual-mps-2.json new file mode 100644 index 0000000..2128164 --- /dev/null +++ b/docs/results/laya-upgrade/records/head-multilingual-mps-2.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": 1000000000, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "mps"}, "load_average_1m": 6.8, "load_s": 7.8, "one_question_p50_ms": 38, "six_questions_p50_ms": 162, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/head-multilingual-mps-3.json b/docs/results/laya-upgrade/records/head-multilingual-mps-3.json new file mode 100644 index 0000000..310b8ed --- /dev/null +++ b/docs/results/laya-upgrade/records/head-multilingual-mps-3.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": 1000000000, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "mps"}, "load_average_1m": 5.5, "load_s": 8.8, "one_question_p50_ms": 42, "six_questions_p50_ms": 165, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161, "refund": 0.0, "angry": 0.0146, "cancel": 0.0013, "human": 0.0065, "late": 0.5449}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532, "refund": 0.0084, "angry": 0.0048, "cancel": 0.1721, "human": 0.0769, "late": 0.1104}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357, "refund": 0.309, "angry": 0.0018, "cancel": 0.1117, "human": 0.0089, "late": 0.1958}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0787, "late": 0.1483}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608, "refund": 0.0622, "angry": 0.0067, "cancel": 0.0789, "human": 0.0113, "late": 0.0605}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964, "refund": 0.429, "angry": 0.0194, "cancel": 0.224, "human": 0.0934, "late": 0.5605}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0475, "angry": 0.0114, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947, "refund": 0.0, "angry": 0.0069, "cancel": 0.6855, "human": 0.0211, "late": 0.0114}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811, "refund": 0.9034, "angry": 0.0162, "cancel": 0.91, "human": 0.0122, "late": 0.041}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966, "refund": 0.0006, "angry": 0.0343, "cancel": 0.0303, "human": 0.0224, "late": 0.0395}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184, "refund": 0.0038, "angry": 0.0467, "cancel": 0.0153, "human": 0.0296, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058, "refund": 0.0055, "angry": 0.0067, "cancel": 0.0027, "human": 0.075, "late": 0.0462}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6878, "angry": 0.0049, "cancel": 0.2196, "human": 0.0646, "late": 0.0379}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976, "refund": 0.9921, "angry": 0.0464, "cancel": 0.997, "human": 0.0203, "late": 0.0596}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879, "refund": 0.9958, "angry": 0.0729, "cancel": 0.5784, "human": 0.0241, "late": 0.5388}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9781, "angry": 0.0146, "cancel": 0.7454, "human": 0.0331, "late": 0.452}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0115, "cancel": 0.0259, "human": 0.5212, "late": 0.0151}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711, "refund": 0.9593, "angry": 0.0197, "cancel": 0.3083, "human": 0.1038, "late": 0.1944}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941, "refund": 0.0701, "angry": 0.0059, "cancel": 0.0159, "human": 0.0082, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834, "refund": 0.0, "angry": 0.0023, "cancel": 0.4959, "human": 0.0259, "late": 0.1376}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155, "refund": 0.9908, "angry": 0.0606, "cancel": 0.9922, "human": 0.2759, "late": 0.0068}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.987, "angry": 0.0159, "cancel": 0.988, "human": 0.3731, "late": 0.0381}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0201, "cancel": 0.0138, "human": 0.0482, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268, "refund": 0.0008, "angry": 0.0681, "cancel": 0.1331, "human": 0.0337, "late": 0.0118}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7122, "human": 0.0254, "late": 0.0978}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0158, "angry": 0.0166, "cancel": 0.4276, "human": 0.033, "late": 0.0435}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849, "refund": 0.0, "angry": 0.0054, "cancel": 0.0134, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258, "refund": 0.0021, "angry": 0.0771, "cancel": 0.0084, "human": 0.0036, "late": 0.0201}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0358, "angry": 0.0114, "cancel": 0.8751, "human": 0.674, "late": 0.0632}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636, "refund": 0.6441, "angry": 0.0182, "cancel": 0.918, "human": 0.8235, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/records/head-multilingual-mps-override5.json b/docs/results/laya-upgrade/records/head-multilingual-mps-override5.json new file mode 100644 index 0000000..b8bd041 --- /dev/null +++ b/docs/results/laya-upgrade/records/head-multilingual-mps-override5.json @@ -0,0 +1,32 @@ +{"label": "head", "no_skip": false, "s1a_commit": "c197fe6d72b527defe0db847d195fc6cba96667d", "laya": "0.3.20", "torch": "2.14.0", "transformers": "5.17.0", "python": "3.14.3", "chip": "Apple M1 Pro", "os": "macOS 26.1", "checkpoint": "convaiinnovations/laya/multilingual", "checkpoint_revision": "7b928d828b7b0e022f929d9bd2e44165aa270148", "device": "mps", "mps_amp_min_rows": 5, "environment": {"LAYA_SUBFOLDER": "multilingual", "LAYA_DEVICE": "mps", "LAYA_MPS_AMP_MIN_ROWS": "5"}, "load_average_1m": 9.6, "load_s": 10.4, "one_question_p50_ms": 45, "six_questions_p50_ms": 181, "tickets": [ + {"id": "t_52586863f51e", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9778, "payment": 0.0034, "returns": 0.0097, "account": 0.0033, "human": 0.0058}, "confidence": 0.9161}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9784, "payment": 0.0034, "returns": 0.0094, "account": 0.0032, "human": 0.0055}, "confidence": 0.9181, "refund": 0.0, "angry": 0.0145, "cancel": 0.0013, "human": 0.0066, "late": 0.5436}}, + {"id": "t_6cb98186dde0", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.5161, "payment": 0.0005, "returns": 0.4798, "account": 0.0005, "human": 0.003}, "confidence": 0.5532}, "one_noul": {"refund": 0.0084}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.4651, "payment": 0.0005, "returns": 0.5311, "account": 0.0005, "human": 0.0028}, "confidence": 0.5551, "refund": 0.0082, "angry": 0.0048, "cancel": 0.1724, "human": 0.0768, "late": 0.1105}}, + {"id": "t_8f0ec563a91a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0193, "payment": 0.0001, "returns": 0.9798, "account": 0.0001, "human": 0.0007}, "confidence": 0.9357}, "one_noul": {"refund": 0.309}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.019, "payment": 0.0001, "returns": 0.98, "account": 0.0001, "human": 0.0007}, "confidence": 0.9363, "refund": 0.3106, "angry": 0.0018, "cancel": 0.1123, "human": 0.0089, "late": 0.1956}}, + {"id": "t_a5a229edd810", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.1834, "payment": 0.109, "returns": 0.688, "account": 0.0027, "human": 0.0169}, "confidence": 0.4438}, "one_noul": {"refund": 0.003}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.1791, "payment": 0.0978, "returns": 0.705, "account": 0.0027, "human": 0.0155}, "confidence": 0.4642, "refund": 0.003, "angry": 0.0055, "cancel": 0.0109, "human": 0.0788, "late": 0.1473}}, + {"id": "t_e4351833c8c8", "one_question": {"pick": "logistics", "probabilities": {"logistics": 0.9433, "payment": 0.0001, "returns": 0.0556, "account": 0.0001, "human": 0.0009}, "confidence": 0.8608}, "one_noul": {"refund": 0.0622}, "six_questions": {"pick": "logistics", "probabilities": {"logistics": 0.9483, "payment": 0.0001, "returns": 0.0507, "account": 0.0001, "human": 0.0008}, "confidence": 0.8699, "refund": 0.0629, "angry": 0.0067, "cancel": 0.0791, "human": 0.0115, "late": 0.0611}}, + {"id": "t_97415027853c", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0007, "payment": 0.0, "returns": 0.9993, "account": 0.0, "human": 0.0}, "confidence": 0.9964}, "one_noul": {"refund": 0.429}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0004, "payment": 0.0, "returns": 0.9995, "account": 0.0, "human": 0.0}, "confidence": 0.9975, "refund": 0.428, "angry": 0.0191, "cancel": 0.224, "human": 0.0931, "late": 0.5616}}, + {"id": "t_07772aa5f822", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993}, "one_noul": {"refund": 0.0475}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9999, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9993, "refund": 0.0478, "angry": 0.0115, "cancel": 0.0004, "human": 0.0127, "late": 0.0018}}, + {"id": "t_1a6847ba8b66", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.9692, "returns": 0.0174, "account": 0.0086, "human": 0.004}, "confidence": 0.8947}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0008, "payment": 0.967, "returns": 0.0193, "account": 0.0087, "human": 0.0042}, "confidence": 0.8889, "refund": 0.0, "angry": 0.0069, "cancel": 0.685, "human": 0.0214, "late": 0.0112}}, + {"id": "t_609c2a02ab84", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.996, "returns": 0.0019, "account": 0.0004, "human": 0.0014}, "confidence": 0.9811}, "one_noul": {"refund": 0.9034}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0003, "payment": 0.9957, "returns": 0.0021, "account": 0.0004, "human": 0.0015}, "confidence": 0.9797, "refund": 0.9031, "angry": 0.016, "cancel": 0.9086, "human": 0.0122, "late": 0.0412}}, + {"id": "t_c8fd45b69015", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9994, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9966}, "one_noul": {"refund": 0.0006}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 0.9993, "returns": 0.0, "account": 0.0006, "human": 0.0}, "confidence": 0.9963, "refund": 0.0006, "angry": 0.0345, "cancel": 0.0307, "human": 0.0223, "late": 0.0397}}, + {"id": "t_c85ca34669b1", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0062, "payment": 0.5737, "returns": 0.3482, "account": 0.0101, "human": 0.0618}, "confidence": 0.4184}, "one_noul": {"refund": 0.0038}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0057, "payment": 0.5921, "returns": 0.3346, "account": 0.0093, "human": 0.0583}, "confidence": 0.4313, "refund": 0.0038, "angry": 0.0465, "cancel": 0.0152, "human": 0.0295, "late": 0.0085}}, + {"id": "t_ace2461b953a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0153, "payment": 0.0609, "returns": 0.9233, "account": 0.0002, "human": 0.0004}, "confidence": 0.8058}, "one_noul": {"refund": 0.0055}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0147, "payment": 0.0536, "returns": 0.9311, "account": 0.0002, "human": 0.0004}, "confidence": 0.8198, "refund": 0.0054, "angry": 0.0068, "cancel": 0.0026, "human": 0.0753, "late": 0.0465}}, + {"id": "t_afe6633569aa", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996}, "one_noul": {"refund": 0.6878}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.9999, "account": 0.0, "human": 0.0}, "confidence": 0.9996, "refund": 0.6917, "angry": 0.0049, "cancel": 0.223, "human": 0.0652, "late": 0.0381}}, + {"id": "t_273060d164f5", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0001}, "confidence": 0.9976}, "one_noul": {"refund": 0.9921}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0001, "payment": 0.0002, "returns": 0.9996, "account": 0.0, "human": 0.0}, "confidence": 0.9978, "refund": 0.9921, "angry": 0.0466, "cancel": 0.997, "human": 0.0204, "late": 0.0592}}, + {"id": "t_f21a8be4a071", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9973, "account": 0.0, "human": 0.0}, "confidence": 0.9879}, "one_noul": {"refund": 0.9958}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0027, "payment": 0.0, "returns": 0.9972, "account": 0.0, "human": 0.0}, "confidence": 0.9877, "refund": 0.9958, "angry": 0.0726, "cancel": 0.5783, "human": 0.0242, "late": 0.5348}}, + {"id": "t_2ff652a83e3b", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9781}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9782, "angry": 0.0146, "cancel": 0.7453, "human": 0.0331, "late": 0.4511}}, + {"id": "t_ec027c12e4da", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999}, "one_noul": {"refund": 0.9935}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 0.9999, "refund": 0.9935, "angry": 0.0116, "cancel": 0.026, "human": 0.5243, "late": 0.0149}}, + {"id": "t_6892a5546a24", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0073, "payment": 0.0001, "returns": 0.9924, "account": 0.0001, "human": 0.0002}, "confidence": 0.9711}, "one_noul": {"refund": 0.9593}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0083, "payment": 0.0001, "returns": 0.9914, "account": 0.0001, "human": 0.0002}, "confidence": 0.9681, "refund": 0.959, "angry": 0.0196, "cancel": 0.3123, "human": 0.1022, "late": 0.1941}}, + {"id": "t_55ac1dd8d045", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.999, "human": 0.0005}, "confidence": 0.9941}, "one_noul": {"refund": 0.0701}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0002, "account": 0.9989, "human": 0.0005}, "confidence": 0.994, "refund": 0.0708, "angry": 0.006, "cancel": 0.0159, "human": 0.0081, "late": 0.0042}}, + {"id": "t_f5251390fb88", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0006, "payment": 0.0004, "returns": 0.001, "account": 0.9967, "human": 0.0012}, "confidence": 0.9834}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0007, "payment": 0.0004, "returns": 0.0011, "account": 0.9964, "human": 0.0013}, "confidence": 0.9824, "refund": 0.0, "angry": 0.0023, "cancel": 0.5074, "human": 0.0253, "late": 0.1388}}, + {"id": "t_507d761b520a", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0056, "payment": 0.0139, "returns": 0.3412, "account": 0.6323, "human": 0.007}, "confidence": 0.5155}, "one_noul": {"refund": 0.9908}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0055, "payment": 0.0146, "returns": 0.3157, "account": 0.6572, "human": 0.007}, "confidence": 0.5249, "refund": 0.9909, "angry": 0.0605, "cancel": 0.9922, "human": 0.2751, "late": 0.0067}}, + {"id": "t_46f559df489a", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.987}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 1.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.9869, "angry": 0.0159, "cancel": 0.9881, "human": 0.3749, "late": 0.0378}}, + {"id": "t_9f4c2e9e9fc4", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992}, "one_noul": {"refund": 0.0007}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0, "payment": 0.0, "returns": 0.0, "account": 0.9999, "human": 0.0}, "confidence": 0.9992, "refund": 0.0007, "angry": 0.0202, "cancel": 0.0139, "human": 0.0488, "late": 0.0022}}, + {"id": "t_5b12b66a4428", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0007, "returns": 0.019, "account": 0.978, "human": 0.001}, "confidence": 0.9268}, "one_noul": {"refund": 0.0008}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0013, "payment": 0.0006, "returns": 0.0178, "account": 0.9793, "human": 0.001}, "confidence": 0.9304, "refund": 0.0008, "angry": 0.0685, "cancel": 0.1338, "human": 0.0337, "late": 0.0119}}, + {"id": "t_892cab266e67", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9929}, "one_noul": {"refund": 0.9951}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0015, "payment": 0.0, "returns": 0.9985, "account": 0.0, "human": 0.0}, "confidence": 0.9931, "refund": 0.9951, "angry": 0.0054, "cancel": 0.7116, "human": 0.0257, "late": 0.0981}}, + {"id": "t_d6e0fd840d60", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0158}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.0152, "angry": 0.0167, "cancel": 0.4179, "human": 0.0325, "late": 0.0431}}, + {"id": "t_fac102ef66cc", "one_question": {"pick": "returns", "probabilities": {"logistics": 0.01, "payment": 0.0062, "returns": 0.968, "account": 0.0072, "human": 0.0086}, "confidence": 0.8849}, "one_noul": {"refund": 0.0}, "six_questions": {"pick": "returns", "probabilities": {"logistics": 0.0096, "payment": 0.0058, "returns": 0.9699, "account": 0.0067, "human": 0.008}, "confidence": 0.8905, "refund": 0.0, "angry": 0.0054, "cancel": 0.0136, "human": 0.0014, "late": 0.0018}}, + {"id": "t_c5314933eb53", "one_question": {"pick": "human", "probabilities": {"logistics": 0.1671, "payment": 0.0261, "returns": 0.3012, "account": 0.0424, "human": 0.4632}, "confidence": 0.2258}, "one_noul": {"refund": 0.0021}, "six_questions": {"pick": "human", "probabilities": {"logistics": 0.1713, "payment": 0.0267, "returns": 0.305, "account": 0.0422, "human": 0.4548}, "confidence": 0.2214, "refund": 0.0021, "angry": 0.0773, "cancel": 0.0085, "human": 0.0036, "late": 0.0203}}, + {"id": "t_c72f978e4f83", "one_question": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0}, "one_noul": {"refund": 0.0358}, "six_questions": {"pick": "payment", "probabilities": {"logistics": 0.0, "payment": 1.0, "returns": 0.0, "account": 0.0, "human": 0.0}, "confidence": 1.0, "refund": 0.036, "angry": 0.0114, "cancel": 0.8745, "human": 0.6731, "late": 0.0629}}, + {"id": "t_30a6dedb9828", "one_question": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.003, "account": 0.9911, "human": 0.0055}, "confidence": 0.9636}, "one_noul": {"refund": 0.6441}, "six_questions": {"pick": "account", "probabilities": {"logistics": 0.0002, "payment": 0.0002, "returns": 0.0027, "account": 0.9924, "human": 0.0046}, "confidence": 0.9682, "refund": 0.645, "angry": 0.0183, "cancel": 0.9173, "human": 0.8232, "late": 0.0089}} +]} diff --git a/docs/results/laya-upgrade/run.sh b/docs/results/laya-upgrade/run.sh new file mode 100755 index 0000000..23ca213 --- /dev/null +++ b/docs/results/laya-upgrade/run.sh @@ -0,0 +1,73 @@ +#!/usr/bin/env bash +# Every run behind the README: baseline and head, both checkpoints, each device, RUNS times, then the controls. +# Usage: run.sh [out dir, default evals/results/laya-upgrade] +set -euo pipefail + +repo=$(cd "$1" && pwd) +base=$2 +head=$3 +out=${4:-evals/results/laya-upgrade} +if [ -n "$(ls -A "$out" 2>/dev/null)" ]; then + echo "run.sh: $out is not empty; compare.py reads every JSON there, so give an empty or new folder" >&2 + exit 1 +fi +out=$(mkdir -p "$out/logs" && cd "$out" && pwd) +here=$(cd "$(dirname "$0")" && pwd) +runs=${RUNS:-3} +devices=${DEVICES:-"cpu mps"} +checkpoints=${CHECKPOINTS:-"english multilingual"} + +work=$(mktemp -d) +cleanup() { + git -C "$repo" worktree remove --force "$work/baseline" 2>/dev/null || true + git -C "$repo" worktree remove --force "$work/head" 2>/dev/null || true + rm -rf "$work" +} +trap cleanup EXIT + +for side in baseline head; do + commit=$base + [ "$side" = head ] && commit=$head + git -C "$repo" worktree add --quiet --detach "$work/$side" "$commit" + echo "$side: $commit" + (cd "$work/$side" && uv sync --quiet --compile-bytecode --extra dev --extra laya) + "$work/$side/.venv/bin/python" -c "import torch, transformers, laya" >/dev/null 2>&1 # first imports off the clock +done + +# one [VAR=value ...] [-- laya_ab.py flags] +one() { + local side=$1 checkpoint=$2 device=$3 name=$4 + shift 4 + local subfolder="" + [ "$checkpoint" = multilingual ] && subfolder=multilingual + local vars=() flags=() + while [ $# -gt 0 ]; do + if [ "$1" = -- ]; then shift; flags=("$@"); break; fi + vars+=("$1"); shift + done + echo " $name" + if ! (cd "$work/$side" && env LAYA_MODEL= LAYA_MAX_LEN= LAYA_HEAD_MAX_LEN= LAYA_MPS_AMP_MIN_ROWS= \ + LAYA_SUBFOLDER="$subfolder" LAYA_DEVICE="$device" ${vars[@]+"${vars[@]}"} \ + .venv/bin/python "$here/laya_ab.py" --label "$side" --out "$out/$name.json" ${flags[@]+"${flags[@]}"}) >"$out/logs/$name.log" 2>&1; then + echo "run.sh: $name failed; the end of $out/logs/$name.log:" >&2 + tail -n 20 "$out/logs/$name.log" >&2 + exit 1 + fi +} + +for i in $(seq "$runs"); do + for checkpoint in $checkpoints; do + for device in $devices; do + one baseline "$checkpoint" "$device" "baseline-$checkpoint-$device-$i" + one head "$checkpoint" "$device" "head-$checkpoint-$device-$i" + done + done +done +for checkpoint in $checkpoints; do + case " $devices " in *" mps "*) + one head "$checkpoint" mps "head-$checkpoint-mps-override5" LAYA_MPS_AMP_MIN_ROWS=5 ;; + esac + one baseline "$checkpoint" cpu "baseline-$checkpoint-cpu-noskip" -- --no-skip +done + +"$work/head/.venv/bin/python" "$here/compare.py" "$out" diff --git a/pyproject.toml b/pyproject.toml index 682ddda..89e0e3c 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -40,7 +40,7 @@ alfworld-visual = [ "torchvision>=0.15", ] report = ["pillow>=10", "playwright>=1.45"] # evals.replay: pages, GIFs; never imported by a runner -laya = ["laya>=0.3.4"] # the in-process decision model behind --model laya; pulls torch and transformers +laya = ["laya>=0.3.9"] # the in-process decision model behind --model laya; pulls torch and transformers cua = [ # Cua-S1 Nano behind --model cua; pinned to the Cua PR that ships the checkpoints (trycua/cua#4023), pulls torch "cua-s1 @ git+https://github.com/trycua/cua.git@aea61b6eb97e2d8c0f6f71eb804e5769fe910af4#subdirectory=libs/cua-s1/python", "huggingface-hub>=0.24", diff --git a/s1a/decision_models/laya.py b/s1a/decision_models/laya.py index b4178a2..fb31280 100644 --- a/s1a/decision_models/laya.py +++ b/s1a/decision_models/laya.py @@ -7,10 +7,8 @@ from __future__ import annotations import asyncio -import importlib import os import time -from contextlib import AbstractContextManager, nullcontext from importlib import metadata from typing import Any @@ -23,6 +21,7 @@ LAYA_DEFAULT_MODEL = "convaiinnovations/laya" LAYA_DEFAULT_MAX_LEN = 512 # the window Laya assumes when a checkpoint config names none +LAYA_MPS_FP32_ROWS = 10**9 # no request has this many questions, so Laya never switches to fp16 on MPS def laya_question(question: Question) -> Json: @@ -34,19 +33,6 @@ def laya_question(question: Question) -> Json: return {"type": "noul", "instructions": question.question, **criteria} -def without_weight_init() -> AbstractContextManager[Any]: - """transformers' ``no_init_weights``. ``laya.load`` builds the encoder from its config, which draws every weight - at random (about 30 s of the load on CPU), then loads the checkpoint over all of them with ``strict=True``, so - the draw is thrown away. The helper sits in ``transformers.initialization`` from 5.0 and in - ``transformers.modeling_utils`` before; without either the load runs as it is.""" - for module in ("transformers.initialization", "transformers.modeling_utils"): - try: - return importlib.import_module(module).no_init_weights() - except (ImportError, AttributeError): - continue - return nullcontext() - - class LayaModel(DecisionModel): """Laya's ``Agent`` (or anything with ``system_one(state, questions)`` and a ``cfg``) behind the interface.""" @@ -103,7 +89,8 @@ def _check_the_window(self, usage: Usage, questions: int) -> None: @classmethod def from_env(cls) -> "LayaModel": """``LAYA_MODEL`` (a hub id or a path), ``LAYA_SUBFOLDER``, ``LAYA_DEVICE``; ``LAYA_MAX_LEN`` and - ``LAYA_HEAD_MAX_LEN`` override the checkpoint's window.""" + ``LAYA_HEAD_MAX_LEN`` override the checkpoint's window. On MPS the model answers in fp32 whatever the + number of questions, unless ``LAYA_MPS_AMP_MIN_ROWS`` (Laya's own variable) is set.""" try: import laya except ImportError as exc: @@ -111,10 +98,19 @@ def from_env(cls) -> "LayaModel": StatusCode.MODEL_SERVICE_CONFIG_ERROR, error_msg="--model laya needs the laya extra: uv sync --extra laya", ) from exc + mps_rows = os.getenv("LAYA_MPS_AMP_MIN_ROWS") + if mps_rows: + try: + int(mps_rows) + except ValueError as exc: # Laya would fall back to its default of 5 and run those requests in fp16 + raise build_error( + StatusCode.MODEL_SERVICE_CONFIG_ERROR, + cause=exc, + error_msg=f"LAYA_MPS_AMP_MIN_ROWS must be a whole number, not {mps_rows!r}; unset it to keep fp32", + ) from exc model = os.getenv("LAYA_MODEL") or LAYA_DEFAULT_MODEL subfolder = os.getenv("LAYA_SUBFOLDER") or None - with without_weight_init(): - agent = laya.load(model, device=os.getenv("LAYA_DEVICE") or None, subfolder=subfolder) + agent = laya.load(model, device=os.getenv("LAYA_DEVICE") or None, subfolder=subfolder) if not callable(getattr(agent, "system_one", None)): try: version = metadata.version("laya") @@ -127,6 +123,10 @@ def from_env(cls) -> "LayaModel": "the s1a laya model needs that method" ), ) + # From 0.3.10 Laya runs a request of five or more questions in fp16 on MPS. That moves the answers, enough + # to flip a close decision, so one browser episode would mix both precisions. + if not mps_rows and hasattr(agent, "mps_amp_min_rows"): + agent.mps_amp_min_rows = LAYA_MPS_FP32_ROWS for key, variable in (("max_len", "LAYA_MAX_LEN"), ("head_max_len", "LAYA_HEAD_MAX_LEN")): value = os.getenv(variable) if value: diff --git a/tests/test_decision_models_factory.py b/tests/test_decision_models_factory.py index 3c85f6d..d38866e 100644 --- a/tests/test_decision_models_factory.py +++ b/tests/test_decision_models_factory.py @@ -5,7 +5,6 @@ import os import sys -from contextlib import nullcontext from types import SimpleNamespace from unittest import TestCase from unittest.mock import patch @@ -32,9 +31,7 @@ def test_every_name_builds_its_class(self) -> None: fake_laya = SimpleNamespace( load=lambda *a, **k: SimpleNamespace(cfg={}, system_one=lambda state, questions: {}) ) - # transformers' helper stubbed so torch is not imported inside patch.dict: see TestFromEnv in the laya tests. - modules = {"laya": fake_laya, "transformers.initialization": SimpleNamespace(no_init_weights=nullcontext)} - with patch.dict(sys.modules, modules), patch.dict(os.environ, {"LAYA_SUBFOLDER": ""}): + with patch.dict(sys.modules, {"laya": fake_laya}), patch.dict(os.environ, {"LAYA_SUBFOLDER": ""}): self.assertIsInstance(build_model("laya"), LayaModel) self.assertIsInstance(build_model("random", seed=3), RandomModel) rule = build_model("rule", rule=("always-inc", lambda state, options: "inc")) diff --git a/tests/test_decision_models_laya.py b/tests/test_decision_models_laya.py index 992924d..bcdabdd 100644 --- a/tests/test_decision_models_laya.py +++ b/tests/test_decision_models_laya.py @@ -1,14 +1,12 @@ # coding: utf-8 """``LayaModel`` over a fake ``laya.Agent`` (no torch): the contract, the question mapping, the error wrap, -the filled-window error, and ``from_env`` with and without the extra and with the weight init off.""" +the filled-window error, and ``from_env`` with and without the extra.""" from __future__ import annotations import os import sys import time -from collections.abc import Iterator -from contextlib import contextmanager, nullcontext from types import SimpleNamespace from typing import Any from unittest import IsolatedAsyncioTestCase, TestCase @@ -163,14 +161,6 @@ async def test_the_window_scales_with_the_number_of_questions(self) -> None: class TestFromEnv(TestCase): - def setUp(self) -> None: - # A stand-in for transformers' helper, so no test imports torch: patch.dict drops a torch imported inside it - # from sys.modules, and importing torch a second time in one process crashes it. - helper = {"transformers.initialization": SimpleNamespace(no_init_weights=nullcontext)} - stub = patch.dict(sys.modules, helper) - stub.start() - self.addCleanup(stub.stop) - def test_without_the_extra_it_is_a_config_error_naming_the_extra(self) -> None: with patch.dict(sys.modules, {"laya": None}): with self.assertRaises(BaseError) as caught: @@ -180,13 +170,59 @@ def test_without_the_extra_it_is_a_config_error_naming_the_extra(self) -> None: def test_an_agent_without_system_one_is_a_config_error_naming_the_method(self) -> None: fake_laya = SimpleNamespace(load=lambda *a, **k: SimpleNamespace(cfg={})) - with patch.dict(sys.modules, {"laya": fake_laya}), patch.dict(os.environ, {"LAYA_SUBFOLDER": ""}): + # The installed version is pinned so the message reads the same with and without the extra. + with ( + patch.dict(sys.modules, {"laya": fake_laya}), + patch.dict(os.environ, {"LAYA_SUBFOLDER": ""}), + patch.object(laya_module.metadata, "version", return_value="0.3.0"), + ): with self.assertRaises(BaseError) as caught: LayaModel.from_env() self.assertEqual(caught.exception.status, StatusCode.MODEL_SERVICE_CONFIG_ERROR) self.assertIn("system_one", str(caught.exception)) + self.assertIn("laya 0.3.0", str(caught.exception)) + + def test_a_laya_without_package_metadata_is_named_unknown(self) -> None: + fake_laya = SimpleNamespace(load=lambda *a, **k: SimpleNamespace(cfg={})) + with ( + patch.dict(sys.modules, {"laya": fake_laya}), + patch.dict(os.environ, {"LAYA_SUBFOLDER": ""}), + patch.object(laya_module.metadata, "version", side_effect=laya_module.metadata.PackageNotFoundError), + ): + with self.assertRaises(BaseError) as caught: + LayaModel.from_env() self.assertIn("laya unknown", str(caught.exception)) + def test_mps_stays_in_fp32_unless_the_laya_variable_is_set(self) -> None: + def from_env(env: dict[str, str]) -> Any: + agent = FakeLayaAgent() + agent.mps_amp_min_rows = 5 # what laya sets from 0.3.10: fp16 from five questions on MPS + fake_laya = SimpleNamespace(load=lambda *a, **k: agent) + env = {"LAYA_SUBFOLDER": "", "LAYA_MPS_AMP_MIN_ROWS": "", **env} + with patch.dict(sys.modules, {"laya": fake_laya}), patch.dict(os.environ, env): + return LayaModel.from_env()._agent + + self.assertEqual(from_env({}).mps_amp_min_rows, laya_module.LAYA_MPS_FP32_ROWS) + self.assertEqual(from_env({"LAYA_MPS_AMP_MIN_ROWS": "5"}).mps_amp_min_rows, 5) + + def test_a_laya_variable_that_is_not_a_number_is_a_config_error(self) -> None: + loads: list[int] = [] + fake_laya = SimpleNamespace(load=lambda *a, **k: loads.append(1)) + env = {"LAYA_SUBFOLDER": "", "LAYA_MPS_AMP_MIN_ROWS": "off"} # laya would read this as its default, fp16 + with patch.dict(sys.modules, {"laya": fake_laya}), patch.dict(os.environ, env): + with self.assertRaises(BaseError) as caught: + LayaModel.from_env() + self.assertEqual(caught.exception.status, StatusCode.MODEL_SERVICE_CONFIG_ERROR) + self.assertIn("LAYA_MPS_AMP_MIN_ROWS", str(caught.exception)) + self.assertEqual(loads, []) # before the checkpoint loads + + def test_a_laya_before_the_mps_gate_gets_no_such_attribute(self) -> None: + agent = FakeLayaAgent() # laya 0.3.9 has no mps_amp_min_rows + with patch.dict(sys.modules, {"laya": SimpleNamespace(load=lambda *a, **k: agent)}): + with patch.dict(os.environ, {"LAYA_SUBFOLDER": "", "LAYA_MPS_AMP_MIN_ROWS": ""}): + LayaModel.from_env() + self.assertFalse(hasattr(agent, "mps_amp_min_rows")) + def test_the_env_names_the_checkpoint_and_overrides_the_window(self) -> None: loads: list[tuple[Any, ...]] = [] @@ -207,49 +243,6 @@ def load(model: str, device: Any = None, token: Any = None, subfolder: Any = Non self.assertEqual(decision_model.model, "convaiinnovations/laya/multilingual") self.assertEqual(decision_model._agent.cfg, {"max_len": 1024, "head_max_len": 512}) - def test_the_checkpoint_loads_with_the_weight_init_off(self) -> None: - events: list[str] = [] - - @contextmanager - def no_init_weights() -> Iterator[None]: - events.append("off") - yield - events.append("on") - - def load(*args: Any, **kwargs: Any) -> FakeLayaAgent: - events.append("load") - return FakeLayaAgent() - - modules = { - "laya": SimpleNamespace(load=load), - "transformers.initialization": SimpleNamespace(no_init_weights=no_init_weights), - } - with patch.dict(sys.modules, modules), patch.dict(os.environ, {"LAYA_SUBFOLDER": ""}): - LayaModel.from_env() - self.assertEqual(events, ["off", "load", "on"]) - - def test_the_4x_location_of_the_helper_is_used_when_the_5x_one_is_missing(self) -> None: - @contextmanager - def no_init_weights() -> Iterator[str]: - yield "4.x" - - modules = { - "transformers.initialization": None, - "transformers.modeling_utils": SimpleNamespace(no_init_weights=no_init_weights), - } - with patch.dict(sys.modules, modules), laya_module.without_weight_init() as entered: - self.assertEqual(entered, "4.x") - - def test_without_the_helper_the_checkpoint_still_loads(self) -> None: - modules = { - "laya": SimpleNamespace(load=lambda *a, **k: FakeLayaAgent()), - "transformers.initialization": None, - "transformers.modeling_utils": SimpleNamespace(), - } - with patch.dict(sys.modules, modules), patch.dict(os.environ, {"LAYA_SUBFOLDER": ""}): - decision_model = LayaModel.from_env() - self.assertIsInstance(decision_model._agent, FakeLayaAgent) - def test_the_defaults_when_the_env_is_empty(self) -> None: env = {"LAYA_MODEL": "", "LAYA_SUBFOLDER": "", "LAYA_DEVICE": "", "LAYA_MAX_LEN": "", "LAYA_HEAD_MAX_LEN": ""} with patch.dict(sys.modules, {"laya": SimpleNamespace(load=lambda *a, **k: FakeLayaAgent())}): diff --git a/uv.lock b/uv.lock index 52ec63f..066838c 100644 --- a/uv.lock +++ b/uv.lock @@ -2287,7 +2287,7 @@ wheels = [ [[package]] name = "laya" -version = "0.3.5" +version = "0.3.20" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "huggingface-hub" }, @@ -2297,9 +2297,9 @@ dependencies = [ { name = "torch" }, { name = "transformers" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/f7/f1/12459ecda42123f93da36f9f1e0c9b7b9191648fa68e7e0b09d292cc6dce/laya-0.3.5.tar.gz", hash = "sha256:5e8a4c2b38dbddc0febe7443f26f74fd9d7571fb172648b1481830c667d59219", size = 69616, upload-time = "2026-09-21T18:20:10.029Z" } +sdist = { url = "https://files.pythonhosted.org/packages/31/82/0964e13e1a67ae4ac2824c3115470d31cd149a065d971a5dec6e4049ca23/laya-0.3.20.tar.gz", hash = "sha256:692de1346cf0239bb7bbcffdf0cfbd538c24834f8bc61e9b60f4106465c033c9", size = 275028, upload-time = "2026-09-24T05:41:07.653Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/ec/1c/a9903d5c3c51579f45f9656f733c8a2d985b16a3cb7594edf45369d1f995/laya-0.3.5-py3-none-any.whl", hash = "sha256:4c57f64cbaf893bb5c7b4affddc2bf21a819f55df51941689f11868583be2903", size = 41658, upload-time = "2026-09-21T18:20:08.641Z" }, + { url = "https://files.pythonhosted.org/packages/34/0c/80982f9ad6f52ca9cb146cfc00fac79e7b7f4388f00f4197575a3170be48/laya-0.3.20-py3-none-any.whl", hash = "sha256:6039e802fa5effb8dd492061cd7ad39a43087beadc4a4fa4a649614e77eb83d4", size = 118520, upload-time = "2026-09-24T05:41:06.273Z" }, ] [[package]] @@ -5200,7 +5200,7 @@ requires-dist = [ { name = "cua-s1", marker = "extra == 'cua'", git = "https://github.com/trycua/cua.git?subdirectory=libs%2Fcua-s1%2Fpython&rev=aea61b6eb97e2d8c0f6f71eb804e5769fe910af4" }, { name = "httpx", specifier = ">=0.28" }, { name = "huggingface-hub", marker = "extra == 'cua'", specifier = ">=0.24" }, - { name = "laya", marker = "extra == 'laya'", specifier = ">=0.3.4" }, + { name = "laya", marker = "extra == 'laya'", specifier = ">=0.3.9" }, { name = "mcp", specifier = ">=1.26" }, { name = "opencv-python-headless", marker = "extra == 'alfworld-visual'", specifier = ">=4.10" }, { name = "openjiuwen", git = "https://github.com/ThinkFlowLab/agent-core?rev=jj-0.1.0" },