Kev-0.8B: Qwen3.5-0.8B-Base, decision-v7 recipe (locked test 0.827 / 0.668)
Browse files- .gitattributes +1 -0
- README.md +99 -0
- adapter_config.json +56 -0
- adapter_model.safetensors +3 -0
- head.pt +3 -0
- provenance.json +58 -0
- result.json +2693 -0
- tokenizer.json +3 -0
- tokenizer_config.json +32 -0
- train.log +319 -0
- training_config.json +42 -0
- training_metrics.json +14 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: en
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
library_name: peft
|
| 5 |
+
base_model: Qwen/Qwen3.5-0.8B-Base
|
| 6 |
+
base_model_relation: adapter
|
| 7 |
+
pipeline_tag: text-classification
|
| 8 |
+
tags:
|
| 9 |
+
- decision-model
|
| 10 |
+
- calibration
|
| 11 |
+
- lora
|
| 12 |
+
- multiple-choice
|
| 13 |
+
- typesafe
|
| 14 |
+
- qwen3.5
|
| 15 |
+
datasets:
|
| 16 |
+
- legacy-datasets/banking77
|
| 17 |
+
- google/boolq
|
| 18 |
+
- fancyzhx/ag_news
|
| 19 |
+
- nyu-mll/multi_nli
|
| 20 |
+
- SetFit/sst5
|
| 21 |
+
- Yelp/yelp_review_full
|
| 22 |
+
- CogComp/trec
|
| 23 |
+
- fancyzhx/dbpedia_14
|
| 24 |
+
- SetFit/amazon_reviews_multi_en
|
| 25 |
+
- stanfordnlp/imdb
|
| 26 |
+
metrics:
|
| 27 |
+
- accuracy
|
| 28 |
+
- brier_score
|
| 29 |
+
- expected_calibration_error
|
| 30 |
+
model-index:
|
| 31 |
+
- name: Kev-0.8B
|
| 32 |
+
results:
|
| 33 |
+
- task: { type: text-classification, name: typed decision (choice / noul / score) }
|
| 34 |
+
dataset: { type: mixed, name: "decision-v7 development (1,204 records; ten trained public sources + programmatic policy data)" }
|
| 35 |
+
metrics:
|
| 36 |
+
- { type: accuracy, value: 0.829 }
|
| 37 |
+
- { type: expected_calibration_error, value: 0.095, name: "ECE, raw probabilities" }
|
| 38 |
+
- task: { type: text-classification, name: typed decision, out-of-domain }
|
| 39 |
+
dataset: { type: mixed, name: "transfer-v4 development (764 records; six never-trained sources + held-out policy structures)" }
|
| 40 |
+
metrics:
|
| 41 |
+
- { type: accuracy, value: 0.643 }
|
| 42 |
+
- { type: brier_score, value: 0.513 }
|
| 43 |
+
---
|
| 44 |
+
|
| 45 |
+
# Kev-0.8B
|
| 46 |
+
|
| 47 |
+
Kev-0.8B is a **decision model**: one document (the *state*) and a set of typed questions in, a probability distribution per question out, in one forward pass. No text generation. It is a LoRA adapter (r=16, 11.3M trainable parameters) plus a pointer head on `Qwen/Qwen3.5-0.8B-Base` (revision `dc7cdfe2`), serving TypeSafe's public `/v1/systemone` contract.
|
| 48 |
+
|
| 49 |
+
**The small member of the Kev family.** Same data and recipe as the 0.6B it replaces, on the Qwen3.5 base: in-distribution 0.829 (Kev-0.6B 0.801), out of domain 0.643 (0.620), and it is the first small Kev that learns any rule composition (held-out pairs 0.38 vs 0.08). Three seeds: transfer 0.622 / 0.634 / **0.643**; this checkpoint is seed 2, selected on the development partition (highest development accuracy). Out of domain it is still a sub-1B model: use Kev-4B for accuracy; use this one where memory rules the 4B out, and measure on your own data.
|
| 50 |
+
|
| 51 |
+
- Hub: `jaredpalmer/kev-0.8b` (this repo; trial `q35-08b/02-trial-2`)
|
| 52 |
+
- Code, suites, results, and the full research log: [github.com/jaredpalmer/kev](https://github.com/jaredpalmer/kev) — `PLAN_Qwen35.md`, `PLAN.md`, `runs/leaderboard.md`
|
| 53 |
+
|
| 54 |
+
## Results (same frozen items for every row)
|
| 55 |
+
|
| 56 |
+
| | Kev-0.6B (Qwen3) | **Kev-0.8B** | Kev-4B | Kev-9B | Jev |
|
| 57 |
+
|---|---|---|---|---|---|
|
| 58 |
+
| in-distribution accuracy (decision-v7 dev, 1,204 records) | 0.801 | **0.829** | 0.877 | 0.876 | 0.845 |
|
| 59 |
+
| out-of-domain accuracy (transfer-v4 dev, 764 records) | 0.620 | **0.643** | 0.794 | 0.812 | 0.857 |
|
| 60 |
+
| out-of-domain Brier | 0.536 | **0.513** | 0.316 | 0.291 | 0.211 |
|
| 61 |
+
| confident errors out of domain (p ≥ 0.9 and wrong) | 10.8% | 9.6% | 8.2% | 7.5% | 3.7% |
|
| 62 |
+
| coverage at ≤ 5% error (share of decisions automatable) | – | 0.17 | 0.54 | 0.53 | 0.70 |
|
| 63 |
+
| held-out policy structures, both siblings correct | 0.08 | **0.38** | 0.78 | 0.80 | 0.86 |
|
| 64 |
+
| option-order flip rate | 0.07 | 0.06 | 0.08 | 0.03 | 0.00 |
|
| 65 |
+
| none-option present, accuracy | 0.80 | 0.83 | 0.93 | 0.90 | – |
|
| 66 |
+
|
| 67 |
+
Per-source out-of-domain accuracy (Kev-0.8B / Jev): QNLI 0.82 / 0.93, SciQ 0.90 / 0.99, TweetEval-offensive 0.62 / 0.81, PAWS 0.59 / 0.79, MMLU 0.41 / 0.90, Emotion 0.54 / 0.59, authorization 0.90 / 1.00, deadline (3-level date arithmetic) 0.28 / 0.93, (A or B) and C 0.66 / 0.91, (A and B) or not C 0.62 / 0.97, if A then not B else C 0.72 / 0.78.
|
| 68 |
+
|
| 69 |
+
Paired against Kev-0.6B on the same items (record-clustered bootstrap): +5.7 pp [+1.2, +10.0] out of domain.
|
| 70 |
+
|
| 71 |
+
**Locked test, read once** (`runs/locked/kev-08b-q35-ungated/`): in-distribution **0.827** (Brier 0.258, ECE 0.096), out-of-domain **0.668** (Brier 0.473, ECE 0.164, confident errors 9.6%, held-out pairs 0.36). Kev-0.6B on the same test items: 0.808 / 0.642. This partition will not be read again for this checkpoint.
|
| 72 |
+
|
| 73 |
+
## Known limits
|
| 74 |
+
|
| 75 |
+
- **Out of domain it is a sub-1B model.** Knowledge (MMLU 0.41) and paraphrase (PAWS 0.59) are near the untrained base; the same recipe reaches 0.79 at 4B and 0.81 at 9B on these items.
|
| 76 |
+
- **Slow on a Mac for its size.** The DeltaNet kernels have no MPS implementation; a five-question request takes ~0.33 s in bf16 on an M5 (Kev-0.6B: 0.12 s). On CUDA with `flash-linear-attention` it is fast.
|
| 77 |
+
- Requires `transformers >= 5.17` and `peft >= 0.21`.
|
| 78 |
+
- Ordinal hedging on date arithmetic (`deadline` 0.28): collapses to the middle level.
|
| 79 |
+
- Confident-error rate out of domain is 9.6%; raw ECE 0.095 in-domain, 0.184 out of domain. Probabilities are usable in-domain; treat them as advisory elsewhere.
|
| 80 |
+
|
| 81 |
+
## Training
|
| 82 |
+
|
| 83 |
+
Frozen suite `evals/v7/decision-v7`: 10,000 public records (1,000 per source), 896 policy minimal-pair records over nine template families, 1,680 records from 60 randomly generated rule structures in four rendering styles. Two epochs, LoRA r=16 α=32 on attention, MLP and DeltaNet projections; pointer head from scratch; cross-entropy on the option distribution; lr 1e-4 (OneCycle), batch 8, bf16 autocast with fp32 master weights; option permutation, none-of-the-above insertion, distractors, none minimal pairs on 25% of Choice records; ~20 min on one H100. No Jev outputs were used for training.
|
| 84 |
+
|
| 85 |
+
## Evaluation protocol
|
| 86 |
+
|
| 87 |
+
Development partitions select models; the locked test partition is read at most once per candidate. Every number carries suite hash, code hashes and git commit in `result.json`.
|
| 88 |
+
|
| 89 |
+
## Use
|
| 90 |
+
|
| 91 |
+
```bash
|
| 92 |
+
uv run --extra serve python -m kev.serve --run jaredpalmer/kev-0.8b --port 8008
|
| 93 |
+
```
|
| 94 |
+
|
| 95 |
+
Any TypeSafe-compatible client works: `TypeSafeClient(api_key="local", base_url="http://127.0.0.1:8008", model="kev-latest")`.
|
| 96 |
+
|
| 97 |
+
## License
|
| 98 |
+
|
| 99 |
+
Apache-2.0 for the adapter and head; the Qwen3.5 base is Apache-2.0; datasets carry their own licenses.
|
adapter_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3.5-0.8B-Base",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"kasa_config": null,
|
| 16 |
+
"layer_replication": null,
|
| 17 |
+
"layers_pattern": null,
|
| 18 |
+
"layers_to_transform": null,
|
| 19 |
+
"loftq_config": {},
|
| 20 |
+
"lora_alpha": 32,
|
| 21 |
+
"lora_bias": false,
|
| 22 |
+
"lora_dropout": 0.05,
|
| 23 |
+
"lora_ga_config": null,
|
| 24 |
+
"megatron_config": null,
|
| 25 |
+
"megatron_core": "megatron.core",
|
| 26 |
+
"modules_to_save": null,
|
| 27 |
+
"monteclora_config": null,
|
| 28 |
+
"peft_type": "LORA",
|
| 29 |
+
"peft_version": "0.21.0",
|
| 30 |
+
"qalora_group_size": 16,
|
| 31 |
+
"r": 16,
|
| 32 |
+
"rank_pattern": {},
|
| 33 |
+
"revision": null,
|
| 34 |
+
"target_modules": [
|
| 35 |
+
"in_proj_b",
|
| 36 |
+
"in_proj_qkv",
|
| 37 |
+
"gate_proj",
|
| 38 |
+
"v_proj",
|
| 39 |
+
"o_proj",
|
| 40 |
+
"k_proj",
|
| 41 |
+
"up_proj",
|
| 42 |
+
"in_proj_z",
|
| 43 |
+
"in_proj_a",
|
| 44 |
+
"out_proj",
|
| 45 |
+
"down_proj",
|
| 46 |
+
"q_proj"
|
| 47 |
+
],
|
| 48 |
+
"target_parameters": null,
|
| 49 |
+
"task_type": "FEATURE_EXTRACTION",
|
| 50 |
+
"trainable_token_indices": null,
|
| 51 |
+
"use_bdlora": null,
|
| 52 |
+
"use_dora": false,
|
| 53 |
+
"use_qalora": false,
|
| 54 |
+
"use_rslora": false,
|
| 55 |
+
"velora_config": null
|
| 56 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9fa619fd3b0490122454c386bfa1b53c23850189d1b5c4346962162e2e39a64
|
| 3 |
+
size 43338624
|
head.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8610dac1c30a64bbcea7715f20a258f4d084d7b862c10f96a1625c732049a32a
|
| 3 |
+
size 2102399
|
provenance.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"config": {
|
| 3 |
+
"epochs": 2,
|
| 4 |
+
"seed": 2,
|
| 5 |
+
"lr": 0.0001,
|
| 6 |
+
"lora": 16,
|
| 7 |
+
"accum": 1,
|
| 8 |
+
"batch": 8,
|
| 9 |
+
"perm_kl": 0.0,
|
| 10 |
+
"perm_frac": 0.3,
|
| 11 |
+
"ord_w": 0.0,
|
| 12 |
+
"p_none": 0.1,
|
| 13 |
+
"p_none_distract": 0.12,
|
| 14 |
+
"p_distract": 0.15,
|
| 15 |
+
"p_none_pair": 0.25,
|
| 16 |
+
"synthetic_repeat": 1,
|
| 17 |
+
"public_frac": 1.0,
|
| 18 |
+
"head_lr": 0.0,
|
| 19 |
+
"weight_decay": 0.01,
|
| 20 |
+
"anchor_w": 0.0,
|
| 21 |
+
"base": "Qwen/Qwen3.5-0.8B-Base",
|
| 22 |
+
"base_revision": "dc7cdfe2ee4154fa7e30f5b51ca41bfa40174e68",
|
| 23 |
+
"dtype": "bf16"
|
| 24 |
+
},
|
| 25 |
+
"config_sha256": "1f902b8d0af3e9c1384f56f9f248c92d27f7029156a1a640389fb2acf5ea6b0a",
|
| 26 |
+
"suite_sha256": "a8f50e481b7d90b97da049e0ff6a01cee2f1ed204aed61a8265af0edbb5514d2",
|
| 27 |
+
"source_hashes": {
|
| 28 |
+
"kev/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
| 29 |
+
"kev/anchors.py": "089d8a5493502bb26f540eb1c5e681780ca0bb01276073d4e1733211f15d0e10",
|
| 30 |
+
"kev/api.py": "cdb0602684d798ccd3fc2c86be622f2a8e7bcdeee64d07f95604c7d3fd4701ec",
|
| 31 |
+
"kev/autoresearch.py": "0a8aa6b57c1c9ba93d25b2cf631b03aed2e686e374c1148002eec48765b7b1fc",
|
| 32 |
+
"kev/benchmark.py": "5be816b27bc69c7244fd1b0ad619d4783b85a21b928212f306e731312f5146b2",
|
| 33 |
+
"kev/compare.py": "bd0445f021de59e35c7bff9304e39dd2e1211e3877a453575594ae7b81b0ada4",
|
| 34 |
+
"kev/composition.py": "f335ed17e18e0a544893db5e22b9a059e6ce1b2e14dbb863ac7d7bbf8f3e0536",
|
| 35 |
+
"kev/contrastive.py": "cbb979aa5d40265ad0e64695f94b281d91751fa405811ddfa8212fede111edcf",
|
| 36 |
+
"kev/data.py": "9729f8f497b02aca542915d6f1bea3ff55956629d7d9610370aea91ee66efd23",
|
| 37 |
+
"kev/evaluate.py": "6f95c52f757ecffc887710e1b354f06c69c35336421d3e75eae84d251ddd120c",
|
| 38 |
+
"kev/experiment.py": "c635394fe56c9aa11765f8bbf8f133dcf3e57cbe8f2bce4ebdc7b4e85fa536ff",
|
| 39 |
+
"kev/jev.py": "e0213782359ba2f95adbf045ddaf0a008b08b4162bf6a9b66d4ce55fc91a51cb",
|
| 40 |
+
"kev/model.py": "46d72ec55c9c35d28e8c43d820733e21bc5f3f261ff72a939fe029b88c4fcb1c",
|
| 41 |
+
"kev/plot.py": "d689c7dd18cde7f9ea77cb4f55c50ff7da1880b21cb2ecf244348e45842a1382",
|
| 42 |
+
"kev/publish.py": "c0b3efac3cfe93990d1846cfd306cf762a9d03e9e58380d13c2961a5ddae4619",
|
| 43 |
+
"kev/serve.py": "570e995aa98b51dbbf867694276d29fc9b9f3f1e62f22bea0116ae51d6497003",
|
| 44 |
+
"kev/study_v3.py": "9fc44d44dad09a4f1ee29a7bcb2eb3c7aa373d09186d0e9533666b69ec95c401",
|
| 45 |
+
"kev/suite.py": "44858f9a99df086a47d1ae36141631fab6fb6a8293a9e1d0c6ad397ddcfaf94a",
|
| 46 |
+
"kev/train.py": "e405978b6e1e7444e682a8869d1bd6c88c90bd9890836fcd84b2ab2aa0543817",
|
| 47 |
+
"kev/transfer_v9.py": "588aa2ff3ec0823c2e31733bef9a3748b263849c966ef6a80ebd686539c605e9",
|
| 48 |
+
"modal_app.py": "12c1b6c1d7f264da8644819bfd11b4baab9c541b1277fee120467514d4628591",
|
| 49 |
+
"pyproject.toml": "52da5eea3efc6f2b1c0589acebad62e56a214294bb02c1a4218c93efd4af3182",
|
| 50 |
+
"uv.lock": "18b3e5ea0f25d2e8546fab81f16cb965ae05c3289fffaaa1ce27d114adee47f3"
|
| 51 |
+
},
|
| 52 |
+
"git_commit": "5f78968927069eaacc3b2bdb688586989b3933ac",
|
| 53 |
+
"platform": "Linux-4.19.0-gvisor-x86_64-with-glibc2.36",
|
| 54 |
+
"torch": "2.8.0+cu128",
|
| 55 |
+
"device": "cuda",
|
| 56 |
+
"gpu": "NVIDIA H100 80GB HBM3",
|
| 57 |
+
"legacy_checkpoint": false
|
| 58 |
+
}
|
result.json
ADDED
|
@@ -0,0 +1,2693 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"objective": -0.5104393802981871,
|
| 3 |
+
"paired_flip": {
|
| 4 |
+
"pairs": 80,
|
| 5 |
+
"flip_rate": 0.8,
|
| 6 |
+
"both_correct_rate": 0.775,
|
| 7 |
+
"invariant_pairs": 32,
|
| 8 |
+
"invariance_rate": 1.0,
|
| 9 |
+
"invariant_both_correct_rate": 0.8125
|
| 10 |
+
},
|
| 11 |
+
"unknowable": null,
|
| 12 |
+
"clean": {
|
| 13 |
+
"n": 1264,
|
| 14 |
+
"nll": 0.6044957065419644,
|
| 15 |
+
"acc": 0.8291139240506329,
|
| 16 |
+
"ece": 0.09460930817547933,
|
| 17 |
+
"brier": 0.26350001968671594,
|
| 18 |
+
"mean_conf": 0.9216668428711666,
|
| 19 |
+
"confident_error_rate": 0.0625,
|
| 20 |
+
"coverage_at_0_9": 0.7579113924050633,
|
| 21 |
+
"accuracy_at_0_9": 0.9175365344467641,
|
| 22 |
+
"coverage_at_5pct_error": 0.5759493670886076,
|
| 23 |
+
"coverage_at_1pct_error": 0.20174050632911392,
|
| 24 |
+
"confidence_bias": 0.09255291882053374,
|
| 25 |
+
"top_bins": {
|
| 26 |
+
"0.9": {
|
| 27 |
+
"n": 958,
|
| 28 |
+
"errors": 79,
|
| 29 |
+
"error_rate": 0.0824634655532359
|
| 30 |
+
},
|
| 31 |
+
"0.95": {
|
| 32 |
+
"n": 877,
|
| 33 |
+
"errors": 58,
|
| 34 |
+
"error_rate": 0.0661345496009122
|
| 35 |
+
},
|
| 36 |
+
"0.99": {
|
| 37 |
+
"n": 731,
|
| 38 |
+
"errors": 37,
|
| 39 |
+
"error_rate": 0.0506155950752394
|
| 40 |
+
}
|
| 41 |
+
},
|
| 42 |
+
"selective": {
|
| 43 |
+
"0.5": {
|
| 44 |
+
"coverage": 0.5,
|
| 45 |
+
"accuracy": 0.9636075949367089,
|
| 46 |
+
"confidence_cutoff": 0.9966887232973961
|
| 47 |
+
},
|
| 48 |
+
"0.8": {
|
| 49 |
+
"coverage": 0.8006329113924051,
|
| 50 |
+
"accuracy": 0.9110671936758893,
|
| 51 |
+
"confidence_cutoff": 0.8535004294293571
|
| 52 |
+
}
|
| 53 |
+
},
|
| 54 |
+
"score_mae": 0.500978878525793,
|
| 55 |
+
"ranked_probability_score": 0.08832172033138225
|
| 56 |
+
},
|
| 57 |
+
"tasks": {
|
| 58 |
+
"agnews": {
|
| 59 |
+
"n": 80,
|
| 60 |
+
"nll": 0.8609991041276182,
|
| 61 |
+
"acc": 0.85,
|
| 62 |
+
"ece": 0.1317994269543806,
|
| 63 |
+
"brier": 0.26184053769385046,
|
| 64 |
+
"mean_conf": 0.958729752607385,
|
| 65 |
+
"confident_error_rate": 0.1,
|
| 66 |
+
"coverage_at_0_9": 0.85,
|
| 67 |
+
"accuracy_at_0_9": 0.8823529411764706,
|
| 68 |
+
"coverage_at_5pct_error": 0.65,
|
| 69 |
+
"coverage_at_1pct_error": 0.375,
|
| 70 |
+
"confidence_bias": 0.10872975260738504,
|
| 71 |
+
"top_bins": {
|
| 72 |
+
"0.9": {
|
| 73 |
+
"n": 68,
|
| 74 |
+
"errors": 8,
|
| 75 |
+
"error_rate": 0.11764705882352941
|
| 76 |
+
},
|
| 77 |
+
"0.95": {
|
| 78 |
+
"n": 67,
|
| 79 |
+
"errors": 7,
|
| 80 |
+
"error_rate": 0.1044776119402985
|
| 81 |
+
},
|
| 82 |
+
"0.99": {
|
| 83 |
+
"n": 64,
|
| 84 |
+
"errors": 7,
|
| 85 |
+
"error_rate": 0.109375
|
| 86 |
+
}
|
| 87 |
+
},
|
| 88 |
+
"selective": {
|
| 89 |
+
"0.5": {
|
| 90 |
+
"coverage": 0.5,
|
| 91 |
+
"accuracy": 0.975,
|
| 92 |
+
"confidence_cutoff": 0.9998993535118608
|
| 93 |
+
},
|
| 94 |
+
"0.8": {
|
| 95 |
+
"coverage": 0.8,
|
| 96 |
+
"accuracy": 0.890625,
|
| 97 |
+
"confidence_cutoff": 0.9916554582405294
|
| 98 |
+
}
|
| 99 |
+
}
|
| 100 |
+
},
|
| 101 |
+
"agnews_yn": {
|
| 102 |
+
"n": 160,
|
| 103 |
+
"nll": 0.2599717840406628,
|
| 104 |
+
"acc": 0.91875,
|
| 105 |
+
"ece": 0.05876332042250172,
|
| 106 |
+
"brier": 0.12890913705724624,
|
| 107 |
+
"mean_conf": 0.9775133204225017,
|
| 108 |
+
"confident_error_rate": 0.05,
|
| 109 |
+
"coverage_at_0_9": 0.925,
|
| 110 |
+
"accuracy_at_0_9": 0.9459459459459459,
|
| 111 |
+
"coverage_at_5pct_error": 0.91875,
|
| 112 |
+
"coverage_at_1pct_error": 0.5125,
|
| 113 |
+
"confidence_bias": 0.058763320422501764,
|
| 114 |
+
"top_bins": {
|
| 115 |
+
"0.9": {
|
| 116 |
+
"n": 148,
|
| 117 |
+
"errors": 8,
|
| 118 |
+
"error_rate": 0.05405405405405406
|
| 119 |
+
},
|
| 120 |
+
"0.95": {
|
| 121 |
+
"n": 143,
|
| 122 |
+
"errors": 6,
|
| 123 |
+
"error_rate": 0.04195804195804196
|
| 124 |
+
},
|
| 125 |
+
"0.99": {
|
| 126 |
+
"n": 128,
|
| 127 |
+
"errors": 2,
|
| 128 |
+
"error_rate": 0.015625
|
| 129 |
+
}
|
| 130 |
+
},
|
| 131 |
+
"selective": {
|
| 132 |
+
"0.5": {
|
| 133 |
+
"coverage": 0.5,
|
| 134 |
+
"accuracy": 1.0,
|
| 135 |
+
"confidence_cutoff": 0.9985212658104174
|
| 136 |
+
},
|
| 137 |
+
"0.8": {
|
| 138 |
+
"coverage": 0.8,
|
| 139 |
+
"accuracy": 0.984375,
|
| 140 |
+
"confidence_cutoff": 0.9901837014930531
|
| 141 |
+
}
|
| 142 |
+
}
|
| 143 |
+
},
|
| 144 |
+
"amazon": {
|
| 145 |
+
"n": 80,
|
| 146 |
+
"nll": 1.170116278586447,
|
| 147 |
+
"acc": 0.5625,
|
| 148 |
+
"ece": 0.18087971737724876,
|
| 149 |
+
"brier": 0.5849052885438153,
|
| 150 |
+
"mean_conf": 0.7433797173772487,
|
| 151 |
+
"confident_error_rate": 0.0375,
|
| 152 |
+
"coverage_at_0_9": 0.3,
|
| 153 |
+
"accuracy_at_0_9": 0.875,
|
| 154 |
+
"coverage_at_5pct_error": 0.25,
|
| 155 |
+
"coverage_at_1pct_error": 0.175,
|
| 156 |
+
"confidence_bias": 0.18087971737724873,
|
| 157 |
+
"top_bins": {
|
| 158 |
+
"0.9": {
|
| 159 |
+
"n": 24,
|
| 160 |
+
"errors": 3,
|
| 161 |
+
"error_rate": 0.125
|
| 162 |
+
},
|
| 163 |
+
"0.95": {
|
| 164 |
+
"n": 13,
|
| 165 |
+
"errors": 0,
|
| 166 |
+
"error_rate": 0.0
|
| 167 |
+
},
|
| 168 |
+
"0.99": {
|
| 169 |
+
"n": 0,
|
| 170 |
+
"errors": 0,
|
| 171 |
+
"error_rate": null
|
| 172 |
+
}
|
| 173 |
+
},
|
| 174 |
+
"selective": {
|
| 175 |
+
"0.5": {
|
| 176 |
+
"coverage": 0.5,
|
| 177 |
+
"accuracy": 0.75,
|
| 178 |
+
"confidence_cutoff": 0.7599378911561145
|
| 179 |
+
},
|
| 180 |
+
"0.8": {
|
| 181 |
+
"coverage": 0.8,
|
| 182 |
+
"accuracy": 0.625,
|
| 183 |
+
"confidence_cutoff": 0.5403370771689989
|
| 184 |
+
}
|
| 185 |
+
},
|
| 186 |
+
"score_mae": 0.5431386528142971,
|
| 187 |
+
"ranked_probability_score": 0.09511597624818423
|
| 188 |
+
},
|
| 189 |
+
"banking77": {
|
| 190 |
+
"n": 80,
|
| 191 |
+
"nll": 0.4723768284029803,
|
| 192 |
+
"acc": 0.875,
|
| 193 |
+
"ece": 0.0974698382522244,
|
| 194 |
+
"brier": 0.2091235964319555,
|
| 195 |
+
"mean_conf": 0.9078220355897264,
|
| 196 |
+
"confident_error_rate": 0.0375,
|
| 197 |
+
"coverage_at_0_9": 0.775,
|
| 198 |
+
"accuracy_at_0_9": 0.9516129032258065,
|
| 199 |
+
"coverage_at_5pct_error": 0.7875,
|
| 200 |
+
"coverage_at_1pct_error": 0.6875,
|
| 201 |
+
"confidence_bias": 0.032822035589726406,
|
| 202 |
+
"top_bins": {
|
| 203 |
+
"0.9": {
|
| 204 |
+
"n": 62,
|
| 205 |
+
"errors": 3,
|
| 206 |
+
"error_rate": 0.04838709677419355
|
| 207 |
+
},
|
| 208 |
+
"0.95": {
|
| 209 |
+
"n": 61,
|
| 210 |
+
"errors": 2,
|
| 211 |
+
"error_rate": 0.03278688524590164
|
| 212 |
+
},
|
| 213 |
+
"0.99": {
|
| 214 |
+
"n": 47,
|
| 215 |
+
"errors": 0,
|
| 216 |
+
"error_rate": 0.0
|
| 217 |
+
}
|
| 218 |
+
},
|
| 219 |
+
"selective": {
|
| 220 |
+
"0.5": {
|
| 221 |
+
"coverage": 0.5,
|
| 222 |
+
"accuracy": 1.0,
|
| 223 |
+
"confidence_cutoff": 0.9987889549104316
|
| 224 |
+
},
|
| 225 |
+
"0.8": {
|
| 226 |
+
"coverage": 0.8,
|
| 227 |
+
"accuracy": 0.9375,
|
| 228 |
+
"confidence_cutoff": 0.8436485197484916
|
| 229 |
+
}
|
| 230 |
+
}
|
| 231 |
+
},
|
| 232 |
+
"boolq": {
|
| 233 |
+
"n": 80,
|
| 234 |
+
"nll": 0.9705687316652412,
|
| 235 |
+
"acc": 0.7875,
|
| 236 |
+
"ece": 0.18175883020018918,
|
| 237 |
+
"brier": 0.4024207111040451,
|
| 238 |
+
"mean_conf": 0.929455381826455,
|
| 239 |
+
"confident_error_rate": 0.1625,
|
| 240 |
+
"coverage_at_0_9": 0.775,
|
| 241 |
+
"accuracy_at_0_9": 0.7903225806451613,
|
| 242 |
+
"coverage_at_5pct_error": 0.0,
|
| 243 |
+
"coverage_at_1pct_error": 0.0,
|
| 244 |
+
"confidence_bias": 0.14195538182645506,
|
| 245 |
+
"top_bins": {
|
| 246 |
+
"0.9": {
|
| 247 |
+
"n": 62,
|
| 248 |
+
"errors": 13,
|
| 249 |
+
"error_rate": 0.20967741935483872
|
| 250 |
+
},
|
| 251 |
+
"0.95": {
|
| 252 |
+
"n": 58,
|
| 253 |
+
"errors": 11,
|
| 254 |
+
"error_rate": 0.1896551724137931
|
| 255 |
+
},
|
| 256 |
+
"0.99": {
|
| 257 |
+
"n": 42,
|
| 258 |
+
"errors": 7,
|
| 259 |
+
"error_rate": 0.16666666666666666
|
| 260 |
+
}
|
| 261 |
+
},
|
| 262 |
+
"selective": {
|
| 263 |
+
"0.5": {
|
| 264 |
+
"coverage": 0.5,
|
| 265 |
+
"accuracy": 0.825,
|
| 266 |
+
"confidence_cutoff": 0.9917437720522815
|
| 267 |
+
},
|
| 268 |
+
"0.8": {
|
| 269 |
+
"coverage": 0.8,
|
| 270 |
+
"accuracy": 0.796875,
|
| 271 |
+
"confidence_cutoff": 0.8723555207252502
|
| 272 |
+
}
|
| 273 |
+
}
|
| 274 |
+
},
|
| 275 |
+
"composition_atom": {
|
| 276 |
+
"n": 16,
|
| 277 |
+
"nll": 0.002336659423961029,
|
| 278 |
+
"acc": 1.0,
|
| 279 |
+
"ece": 0.0023327422832846167,
|
| 280 |
+
"brier": 1.562782372380122e-05,
|
| 281 |
+
"mean_conf": 0.9976672577167154,
|
| 282 |
+
"confident_error_rate": 0.0,
|
| 283 |
+
"coverage_at_0_9": 1.0,
|
| 284 |
+
"accuracy_at_0_9": 1.0,
|
| 285 |
+
"coverage_at_5pct_error": 1.0,
|
| 286 |
+
"coverage_at_1pct_error": 1.0,
|
| 287 |
+
"confidence_bias": -0.0023327422832846167,
|
| 288 |
+
"top_bins": {
|
| 289 |
+
"0.9": {
|
| 290 |
+
"n": 16,
|
| 291 |
+
"errors": 0,
|
| 292 |
+
"error_rate": 0.0
|
| 293 |
+
},
|
| 294 |
+
"0.95": {
|
| 295 |
+
"n": 16,
|
| 296 |
+
"errors": 0,
|
| 297 |
+
"error_rate": 0.0
|
| 298 |
+
},
|
| 299 |
+
"0.99": {
|
| 300 |
+
"n": 16,
|
| 301 |
+
"errors": 0,
|
| 302 |
+
"error_rate": 0.0
|
| 303 |
+
}
|
| 304 |
+
},
|
| 305 |
+
"selective": {
|
| 306 |
+
"0.5": {
|
| 307 |
+
"coverage": 0.5625,
|
| 308 |
+
"accuracy": 1.0,
|
| 309 |
+
"confidence_cutoff": 0.9979198800395774
|
| 310 |
+
},
|
| 311 |
+
"0.8": {
|
| 312 |
+
"coverage": 0.875,
|
| 313 |
+
"accuracy": 1.0,
|
| 314 |
+
"confidence_cutoff": 0.9958037284235649
|
| 315 |
+
}
|
| 316 |
+
}
|
| 317 |
+
},
|
| 318 |
+
"composition_conditional": {
|
| 319 |
+
"n": 16,
|
| 320 |
+
"nll": 1.4225334499010278,
|
| 321 |
+
"acc": 0.5625,
|
| 322 |
+
"ece": 0.3561453377965225,
|
| 323 |
+
"brier": 0.6340869179597339,
|
| 324 |
+
"mean_conf": 0.8921818043809806,
|
| 325 |
+
"confident_error_rate": 0.25,
|
| 326 |
+
"coverage_at_0_9": 0.6875,
|
| 327 |
+
"accuracy_at_0_9": 0.6363636363636364,
|
| 328 |
+
"coverage_at_5pct_error": 0.0625,
|
| 329 |
+
"coverage_at_1pct_error": 0.0625,
|
| 330 |
+
"confidence_bias": 0.3296818043809806,
|
| 331 |
+
"top_bins": {
|
| 332 |
+
"0.9": {
|
| 333 |
+
"n": 11,
|
| 334 |
+
"errors": 4,
|
| 335 |
+
"error_rate": 0.36363636363636365
|
| 336 |
+
},
|
| 337 |
+
"0.95": {
|
| 338 |
+
"n": 9,
|
| 339 |
+
"errors": 4,
|
| 340 |
+
"error_rate": 0.4444444444444444
|
| 341 |
+
},
|
| 342 |
+
"0.99": {
|
| 343 |
+
"n": 4,
|
| 344 |
+
"errors": 3,
|
| 345 |
+
"error_rate": 0.75
|
| 346 |
+
}
|
| 347 |
+
},
|
| 348 |
+
"selective": {
|
| 349 |
+
"0.5": {
|
| 350 |
+
"coverage": 0.5,
|
| 351 |
+
"accuracy": 0.5,
|
| 352 |
+
"confidence_cutoff": 0.9723861597852955
|
| 353 |
+
},
|
| 354 |
+
"0.8": {
|
| 355 |
+
"coverage": 0.8125,
|
| 356 |
+
"accuracy": 0.6923076923076923,
|
| 357 |
+
"confidence_cutoff": 0.8931548332108122
|
| 358 |
+
}
|
| 359 |
+
}
|
| 360 |
+
},
|
| 361 |
+
"composition_conjunction": {
|
| 362 |
+
"n": 16,
|
| 363 |
+
"nll": 0.3156768963675495,
|
| 364 |
+
"acc": 0.9375,
|
| 365 |
+
"ece": 0.10559007956915385,
|
| 366 |
+
"brier": 0.15326710044593198,
|
| 367 |
+
"mean_conf": 0.9322922268681412,
|
| 368 |
+
"confident_error_rate": 0.0625,
|
| 369 |
+
"coverage_at_0_9": 0.8125,
|
| 370 |
+
"accuracy_at_0_9": 0.9230769230769231,
|
| 371 |
+
"coverage_at_5pct_error": 0.5625,
|
| 372 |
+
"coverage_at_1pct_error": 0.5625,
|
| 373 |
+
"confidence_bias": -0.005207773131858828,
|
| 374 |
+
"top_bins": {
|
| 375 |
+
"0.9": {
|
| 376 |
+
"n": 13,
|
| 377 |
+
"errors": 1,
|
| 378 |
+
"error_rate": 0.07692307692307693
|
| 379 |
+
},
|
| 380 |
+
"0.95": {
|
| 381 |
+
"n": 12,
|
| 382 |
+
"errors": 1,
|
| 383 |
+
"error_rate": 0.08333333333333333
|
| 384 |
+
},
|
| 385 |
+
"0.99": {
|
| 386 |
+
"n": 8,
|
| 387 |
+
"errors": 0,
|
| 388 |
+
"error_rate": 0.0
|
| 389 |
+
}
|
| 390 |
+
},
|
| 391 |
+
"selective": {
|
| 392 |
+
"0.5": {
|
| 393 |
+
"coverage": 0.5,
|
| 394 |
+
"accuracy": 1.0,
|
| 395 |
+
"confidence_cutoff": 0.9966887232973961
|
| 396 |
+
},
|
| 397 |
+
"0.8": {
|
| 398 |
+
"coverage": 0.8125,
|
| 399 |
+
"accuracy": 0.9230769230769231,
|
| 400 |
+
"confidence_cutoff": 0.9301781515750565
|
| 401 |
+
}
|
| 402 |
+
}
|
| 403 |
+
},
|
| 404 |
+
"composition_disjunction": {
|
| 405 |
+
"n": 16,
|
| 406 |
+
"nll": 0.6430687794856909,
|
| 407 |
+
"acc": 0.5625,
|
| 408 |
+
"ece": 0.33948876901792646,
|
| 409 |
+
"brier": 0.4972525771345605,
|
| 410 |
+
"mean_conf": 0.8780158775336332,
|
| 411 |
+
"confident_error_rate": 0.0,
|
| 412 |
+
"coverage_at_0_9": 0.5625,
|
| 413 |
+
"accuracy_at_0_9": 1.0,
|
| 414 |
+
"coverage_at_5pct_error": 0.5625,
|
| 415 |
+
"coverage_at_1pct_error": 0.5625,
|
| 416 |
+
"confidence_bias": 0.3155158775336332,
|
| 417 |
+
"top_bins": {
|
| 418 |
+
"0.9": {
|
| 419 |
+
"n": 9,
|
| 420 |
+
"errors": 0,
|
| 421 |
+
"error_rate": 0.0
|
| 422 |
+
},
|
| 423 |
+
"0.95": {
|
| 424 |
+
"n": 9,
|
| 425 |
+
"errors": 0,
|
| 426 |
+
"error_rate": 0.0
|
| 427 |
+
},
|
| 428 |
+
"0.99": {
|
| 429 |
+
"n": 4,
|
| 430 |
+
"errors": 0,
|
| 431 |
+
"error_rate": 0.0
|
| 432 |
+
}
|
| 433 |
+
},
|
| 434 |
+
"selective": {
|
| 435 |
+
"0.5": {
|
| 436 |
+
"coverage": 0.5625,
|
| 437 |
+
"accuracy": 1.0,
|
| 438 |
+
"confidence_cutoff": 0.9591541457554335
|
| 439 |
+
},
|
| 440 |
+
"0.8": {
|
| 441 |
+
"coverage": 0.8125,
|
| 442 |
+
"accuracy": 0.6923076923076923,
|
| 443 |
+
"confidence_cutoff": 0.7260039828418499
|
| 444 |
+
}
|
| 445 |
+
}
|
| 446 |
+
},
|
| 447 |
+
"composition_exception": {
|
| 448 |
+
"n": 16,
|
| 449 |
+
"nll": 0.36859663892334393,
|
| 450 |
+
"acc": 0.75,
|
| 451 |
+
"ece": 0.18654958725067453,
|
| 452 |
+
"brier": 0.2816199812470343,
|
| 453 |
+
"mean_conf": 0.9078310510531081,
|
| 454 |
+
"confident_error_rate": 0.0,
|
| 455 |
+
"coverage_at_0_9": 0.6875,
|
| 456 |
+
"accuracy_at_0_9": 1.0,
|
| 457 |
+
"coverage_at_5pct_error": 0.75,
|
| 458 |
+
"coverage_at_1pct_error": 0.75,
|
| 459 |
+
"confidence_bias": 0.15783105105310813,
|
| 460 |
+
"top_bins": {
|
| 461 |
+
"0.9": {
|
| 462 |
+
"n": 11,
|
| 463 |
+
"errors": 0,
|
| 464 |
+
"error_rate": 0.0
|
| 465 |
+
},
|
| 466 |
+
"0.95": {
|
| 467 |
+
"n": 11,
|
| 468 |
+
"errors": 0,
|
| 469 |
+
"error_rate": 0.0
|
| 470 |
+
},
|
| 471 |
+
"0.99": {
|
| 472 |
+
"n": 4,
|
| 473 |
+
"errors": 0,
|
| 474 |
+
"error_rate": 0.0
|
| 475 |
+
}
|
| 476 |
+
},
|
| 477 |
+
"selective": {
|
| 478 |
+
"0.5": {
|
| 479 |
+
"coverage": 0.5,
|
| 480 |
+
"accuracy": 1.0,
|
| 481 |
+
"confidence_cutoff": 0.9660640703050476
|
| 482 |
+
},
|
| 483 |
+
"0.8": {
|
| 484 |
+
"coverage": 0.8125,
|
| 485 |
+
"accuracy": 0.9230769230769231,
|
| 486 |
+
"confidence_cutoff": 0.7701466679573059
|
| 487 |
+
}
|
| 488 |
+
}
|
| 489 |
+
},
|
| 490 |
+
"composition_negation": {
|
| 491 |
+
"n": 16,
|
| 492 |
+
"nll": 0.07593880407395798,
|
| 493 |
+
"acc": 1.0,
|
| 494 |
+
"ece": 0.07113335999517942,
|
| 495 |
+
"brier": 0.017031400418089433,
|
| 496 |
+
"mean_conf": 0.9288666400048207,
|
| 497 |
+
"confident_error_rate": 0.0,
|
| 498 |
+
"coverage_at_0_9": 0.8125,
|
| 499 |
+
"accuracy_at_0_9": 1.0,
|
| 500 |
+
"coverage_at_5pct_error": 1.0,
|
| 501 |
+
"coverage_at_1pct_error": 1.0,
|
| 502 |
+
"confidence_bias": -0.07113335999517933,
|
| 503 |
+
"top_bins": {
|
| 504 |
+
"0.9": {
|
| 505 |
+
"n": 13,
|
| 506 |
+
"errors": 0,
|
| 507 |
+
"error_rate": 0.0
|
| 508 |
+
},
|
| 509 |
+
"0.95": {
|
| 510 |
+
"n": 8,
|
| 511 |
+
"errors": 0,
|
| 512 |
+
"error_rate": 0.0
|
| 513 |
+
},
|
| 514 |
+
"0.99": {
|
| 515 |
+
"n": 0,
|
| 516 |
+
"errors": 0,
|
| 517 |
+
"error_rate": null
|
| 518 |
+
}
|
| 519 |
+
},
|
| 520 |
+
"selective": {
|
| 521 |
+
"0.5": {
|
| 522 |
+
"coverage": 0.5,
|
| 523 |
+
"accuracy": 1.0,
|
| 524 |
+
"confidence_cutoff": 0.958652863572761
|
| 525 |
+
},
|
| 526 |
+
"0.8": {
|
| 527 |
+
"coverage": 0.8125,
|
| 528 |
+
"accuracy": 1.0,
|
| 529 |
+
"confidence_cutoff": 0.9182740723572395
|
| 530 |
+
}
|
| 531 |
+
}
|
| 532 |
+
},
|
| 533 |
+
"composition_nested_and": {
|
| 534 |
+
"n": 16,
|
| 535 |
+
"nll": 0.32012543654556636,
|
| 536 |
+
"acc": 0.8125,
|
| 537 |
+
"ece": 0.14208900580264555,
|
| 538 |
+
"brier": 0.22063650770328963,
|
| 539 |
+
"mean_conf": 0.8788967302403223,
|
| 540 |
+
"confident_error_rate": 0.0,
|
| 541 |
+
"coverage_at_0_9": 0.6875,
|
| 542 |
+
"accuracy_at_0_9": 1.0,
|
| 543 |
+
"coverage_at_5pct_error": 0.6875,
|
| 544 |
+
"coverage_at_1pct_error": 0.6875,
|
| 545 |
+
"confidence_bias": 0.06639673024032233,
|
| 546 |
+
"top_bins": {
|
| 547 |
+
"0.9": {
|
| 548 |
+
"n": 11,
|
| 549 |
+
"errors": 0,
|
| 550 |
+
"error_rate": 0.0
|
| 551 |
+
},
|
| 552 |
+
"0.95": {
|
| 553 |
+
"n": 5,
|
| 554 |
+
"errors": 0,
|
| 555 |
+
"error_rate": 0.0
|
| 556 |
+
},
|
| 557 |
+
"0.99": {
|
| 558 |
+
"n": 3,
|
| 559 |
+
"errors": 0,
|
| 560 |
+
"error_rate": 0.0
|
| 561 |
+
}
|
| 562 |
+
},
|
| 563 |
+
"selective": {
|
| 564 |
+
"0.5": {
|
| 565 |
+
"coverage": 0.5,
|
| 566 |
+
"accuracy": 1.0,
|
| 567 |
+
"confidence_cutoff": 0.918865857498402
|
| 568 |
+
},
|
| 569 |
+
"0.8": {
|
| 570 |
+
"coverage": 0.8125,
|
| 571 |
+
"accuracy": 0.9230769230769231,
|
| 572 |
+
"confidence_cutoff": 0.7476357817649841
|
| 573 |
+
}
|
| 574 |
+
}
|
| 575 |
+
},
|
| 576 |
+
"composition_nested_or": {
|
| 577 |
+
"n": 16,
|
| 578 |
+
"nll": 0.05815837656428905,
|
| 579 |
+
"acc": 1.0,
|
| 580 |
+
"ece": 0.05446642839922426,
|
| 581 |
+
"brier": 0.012884220016133213,
|
| 582 |
+
"mean_conf": 0.9455335716007759,
|
| 583 |
+
"confident_error_rate": 0.0,
|
| 584 |
+
"coverage_at_0_9": 0.9375,
|
| 585 |
+
"accuracy_at_0_9": 1.0,
|
| 586 |
+
"coverage_at_5pct_error": 1.0,
|
| 587 |
+
"coverage_at_1pct_error": 1.0,
|
| 588 |
+
"confidence_bias": -0.05446642839922411,
|
| 589 |
+
"top_bins": {
|
| 590 |
+
"0.9": {
|
| 591 |
+
"n": 15,
|
| 592 |
+
"errors": 0,
|
| 593 |
+
"error_rate": 0.0
|
| 594 |
+
},
|
| 595 |
+
"0.95": {
|
| 596 |
+
"n": 9,
|
| 597 |
+
"errors": 0,
|
| 598 |
+
"error_rate": 0.0
|
| 599 |
+
},
|
| 600 |
+
"0.99": {
|
| 601 |
+
"n": 2,
|
| 602 |
+
"errors": 0,
|
| 603 |
+
"error_rate": 0.0
|
| 604 |
+
}
|
| 605 |
+
},
|
| 606 |
+
"selective": {
|
| 607 |
+
"0.5": {
|
| 608 |
+
"coverage": 0.5,
|
| 609 |
+
"accuracy": 1.0,
|
| 610 |
+
"confidence_cutoff": 0.9776142689941187
|
| 611 |
+
},
|
| 612 |
+
"0.8": {
|
| 613 |
+
"coverage": 0.875,
|
| 614 |
+
"accuracy": 1.0,
|
| 615 |
+
"confidence_cutoff": 0.9137027876326821
|
| 616 |
+
}
|
| 617 |
+
}
|
| 618 |
+
},
|
| 619 |
+
"contrastive_age_eligibility": {
|
| 620 |
+
"n": 24,
|
| 621 |
+
"nll": 1.681130539758744e-05,
|
| 622 |
+
"acc": 1.0,
|
| 623 |
+
"ece": 1.6811118455417606e-05,
|
| 624 |
+
"brier": 7.477550776629168e-10,
|
| 625 |
+
"mean_conf": 0.9999831888815446,
|
| 626 |
+
"confident_error_rate": 0.0,
|
| 627 |
+
"coverage_at_0_9": 1.0,
|
| 628 |
+
"accuracy_at_0_9": 1.0,
|
| 629 |
+
"coverage_at_5pct_error": 1.0,
|
| 630 |
+
"coverage_at_1pct_error": 1.0,
|
| 631 |
+
"confidence_bias": -1.6811118455417606e-05,
|
| 632 |
+
"top_bins": {
|
| 633 |
+
"0.9": {
|
| 634 |
+
"n": 24,
|
| 635 |
+
"errors": 0,
|
| 636 |
+
"error_rate": 0.0
|
| 637 |
+
},
|
| 638 |
+
"0.95": {
|
| 639 |
+
"n": 24,
|
| 640 |
+
"errors": 0,
|
| 641 |
+
"error_rate": 0.0
|
| 642 |
+
},
|
| 643 |
+
"0.99": {
|
| 644 |
+
"n": 24,
|
| 645 |
+
"errors": 0,
|
| 646 |
+
"error_rate": 0.0
|
| 647 |
+
}
|
| 648 |
+
},
|
| 649 |
+
"selective": {
|
| 650 |
+
"0.5": {
|
| 651 |
+
"coverage": 0.5,
|
| 652 |
+
"accuracy": 1.0,
|
| 653 |
+
"confidence_cutoff": 0.9999868565068394
|
| 654 |
+
},
|
| 655 |
+
"0.8": {
|
| 656 |
+
"coverage": 0.8333333333333334,
|
| 657 |
+
"accuracy": 1.0,
|
| 658 |
+
"confidence_cutoff": 0.9999709051282931
|
| 659 |
+
}
|
| 660 |
+
}
|
| 661 |
+
},
|
| 662 |
+
"contrastive_quantity_limit": {
|
| 663 |
+
"n": 24,
|
| 664 |
+
"nll": 0.08175941775734163,
|
| 665 |
+
"acc": 0.9166666666666666,
|
| 666 |
+
"ece": 0.05333587327209555,
|
| 667 |
+
"brier": 0.06325493754398145,
|
| 668 |
+
"mean_conf": 0.9658229555498962,
|
| 669 |
+
"confident_error_rate": 0.0,
|
| 670 |
+
"coverage_at_0_9": 0.9166666666666666,
|
| 671 |
+
"accuracy_at_0_9": 1.0,
|
| 672 |
+
"coverage_at_5pct_error": 0.9583333333333334,
|
| 673 |
+
"coverage_at_1pct_error": 0.9166666666666666,
|
| 674 |
+
"confidence_bias": 0.04915628888322954,
|
| 675 |
+
"top_bins": {
|
| 676 |
+
"0.9": {
|
| 677 |
+
"n": 22,
|
| 678 |
+
"errors": 0,
|
| 679 |
+
"error_rate": 0.0
|
| 680 |
+
},
|
| 681 |
+
"0.95": {
|
| 682 |
+
"n": 22,
|
| 683 |
+
"errors": 0,
|
| 684 |
+
"error_rate": 0.0
|
| 685 |
+
},
|
| 686 |
+
"0.99": {
|
| 687 |
+
"n": 21,
|
| 688 |
+
"errors": 0,
|
| 689 |
+
"error_rate": 0.0
|
| 690 |
+
}
|
| 691 |
+
},
|
| 692 |
+
"selective": {
|
| 693 |
+
"0.5": {
|
| 694 |
+
"coverage": 0.5,
|
| 695 |
+
"accuracy": 1.0,
|
| 696 |
+
"confidence_cutoff": 0.9999971142285179
|
| 697 |
+
},
|
| 698 |
+
"0.8": {
|
| 699 |
+
"coverage": 0.8333333333333334,
|
| 700 |
+
"accuracy": 1.0,
|
| 701 |
+
"confidence_cutoff": 0.9986034079872341
|
| 702 |
+
}
|
| 703 |
+
}
|
| 704 |
+
},
|
| 705 |
+
"contrastive_return_window": {
|
| 706 |
+
"n": 24,
|
| 707 |
+
"nll": 0.48156158317006703,
|
| 708 |
+
"acc": 0.75,
|
| 709 |
+
"ece": 0.13661278940887145,
|
| 710 |
+
"brier": 0.3170947362505653,
|
| 711 |
+
"mean_conf": 0.7999831677265027,
|
| 712 |
+
"confident_error_rate": 0.041666666666666664,
|
| 713 |
+
"coverage_at_0_9": 0.3333333333333333,
|
| 714 |
+
"accuracy_at_0_9": 0.875,
|
| 715 |
+
"coverage_at_5pct_error": 0.2916666666666667,
|
| 716 |
+
"coverage_at_1pct_error": 0.2916666666666667,
|
| 717 |
+
"confidence_bias": 0.049983167726502686,
|
| 718 |
+
"top_bins": {
|
| 719 |
+
"0.9": {
|
| 720 |
+
"n": 8,
|
| 721 |
+
"errors": 1,
|
| 722 |
+
"error_rate": 0.125
|
| 723 |
+
},
|
| 724 |
+
"0.95": {
|
| 725 |
+
"n": 0,
|
| 726 |
+
"errors": 0,
|
| 727 |
+
"error_rate": null
|
| 728 |
+
},
|
| 729 |
+
"0.99": {
|
| 730 |
+
"n": 0,
|
| 731 |
+
"errors": 0,
|
| 732 |
+
"error_rate": null
|
| 733 |
+
}
|
| 734 |
+
},
|
| 735 |
+
"selective": {
|
| 736 |
+
"0.5": {
|
| 737 |
+
"coverage": 0.5,
|
| 738 |
+
"accuracy": 0.9166666666666666,
|
| 739 |
+
"confidence_cutoff": 0.8706863599606538
|
| 740 |
+
},
|
| 741 |
+
"0.8": {
|
| 742 |
+
"coverage": 0.8333333333333334,
|
| 743 |
+
"accuracy": 0.8,
|
| 744 |
+
"confidence_cutoff": 0.6540448665618896
|
| 745 |
+
}
|
| 746 |
+
}
|
| 747 |
+
},
|
| 748 |
+
"contrastive_spend_threshold": {
|
| 749 |
+
"n": 24,
|
| 750 |
+
"nll": 3.517754884122615e-07,
|
| 751 |
+
"acc": 1.0,
|
| 752 |
+
"ece": 3.5177539137176694e-07,
|
| 753 |
+
"brier": 3.4943220618119857e-13,
|
| 754 |
+
"mean_conf": 0.9999996482246086,
|
| 755 |
+
"confident_error_rate": 0.0,
|
| 756 |
+
"coverage_at_0_9": 1.0,
|
| 757 |
+
"accuracy_at_0_9": 1.0,
|
| 758 |
+
"coverage_at_5pct_error": 1.0,
|
| 759 |
+
"coverage_at_1pct_error": 1.0,
|
| 760 |
+
"confidence_bias": -3.5177539137176694e-07,
|
| 761 |
+
"top_bins": {
|
| 762 |
+
"0.9": {
|
| 763 |
+
"n": 24,
|
| 764 |
+
"errors": 0,
|
| 765 |
+
"error_rate": 0.0
|
| 766 |
+
},
|
| 767 |
+
"0.95": {
|
| 768 |
+
"n": 24,
|
| 769 |
+
"errors": 0,
|
| 770 |
+
"error_rate": 0.0
|
| 771 |
+
},
|
| 772 |
+
"0.99": {
|
| 773 |
+
"n": 24,
|
| 774 |
+
"errors": 0,
|
| 775 |
+
"error_rate": 0.0
|
| 776 |
+
}
|
| 777 |
+
},
|
| 778 |
+
"selective": {
|
| 779 |
+
"0.5": {
|
| 780 |
+
"coverage": 0.5,
|
| 781 |
+
"accuracy": 1.0,
|
| 782 |
+
"confidence_cutoff": 0.9999997129533111
|
| 783 |
+
},
|
| 784 |
+
"0.8": {
|
| 785 |
+
"coverage": 0.8333333333333334,
|
| 786 |
+
"accuracy": 1.0,
|
| 787 |
+
"confidence_cutoff": 0.9999994566494121
|
| 788 |
+
}
|
| 789 |
+
}
|
| 790 |
+
},
|
| 791 |
+
"dbpedia14": {
|
| 792 |
+
"n": 80,
|
| 793 |
+
"nll": 0.40762107591188207,
|
| 794 |
+
"acc": 0.9625,
|
| 795 |
+
"ece": 0.03977300891143117,
|
| 796 |
+
"brier": 0.07395293569128794,
|
| 797 |
+
"mean_conf": 0.9961688342822287,
|
| 798 |
+
"confident_error_rate": 0.0375,
|
| 799 |
+
"coverage_at_0_9": 0.9875,
|
| 800 |
+
"accuracy_at_0_9": 0.9620253164556962,
|
| 801 |
+
"coverage_at_5pct_error": 1.0,
|
| 802 |
+
"coverage_at_1pct_error": 0.4,
|
| 803 |
+
"confidence_bias": 0.033668834282228666,
|
| 804 |
+
"top_bins": {
|
| 805 |
+
"0.9": {
|
| 806 |
+
"n": 79,
|
| 807 |
+
"errors": 3,
|
| 808 |
+
"error_rate": 0.0379746835443038
|
| 809 |
+
},
|
| 810 |
+
"0.95": {
|
| 811 |
+
"n": 78,
|
| 812 |
+
"errors": 2,
|
| 813 |
+
"error_rate": 0.02564102564102564
|
| 814 |
+
},
|
| 815 |
+
"0.99": {
|
| 816 |
+
"n": 78,
|
| 817 |
+
"errors": 2,
|
| 818 |
+
"error_rate": 0.02564102564102564
|
| 819 |
+
}
|
| 820 |
+
},
|
| 821 |
+
"selective": {
|
| 822 |
+
"0.5": {
|
| 823 |
+
"coverage": 0.5,
|
| 824 |
+
"accuracy": 0.975,
|
| 825 |
+
"confidence_cutoff": 0.999999842718273
|
| 826 |
+
},
|
| 827 |
+
"0.8": {
|
| 828 |
+
"coverage": 0.8,
|
| 829 |
+
"accuracy": 0.984375,
|
| 830 |
+
"confidence_cutoff": 0.9999994500241649
|
| 831 |
+
}
|
| 832 |
+
}
|
| 833 |
+
},
|
| 834 |
+
"imdb": {
|
| 835 |
+
"n": 80,
|
| 836 |
+
"nll": 0.4707825073471218,
|
| 837 |
+
"acc": 0.8875,
|
| 838 |
+
"ece": 0.0963437974395494,
|
| 839 |
+
"brier": 0.1859917202833728,
|
| 840 |
+
"mean_conf": 0.9742087478769477,
|
| 841 |
+
"confident_error_rate": 0.0625,
|
| 842 |
+
"coverage_at_0_9": 0.925,
|
| 843 |
+
"accuracy_at_0_9": 0.9324324324324325,
|
| 844 |
+
"coverage_at_5pct_error": 0.8625,
|
| 845 |
+
"coverage_at_1pct_error": 0.275,
|
| 846 |
+
"confidence_bias": 0.08670874787694771,
|
| 847 |
+
"top_bins": {
|
| 848 |
+
"0.9": {
|
| 849 |
+
"n": 74,
|
| 850 |
+
"errors": 5,
|
| 851 |
+
"error_rate": 0.06756756756756757
|
| 852 |
+
},
|
| 853 |
+
"0.95": {
|
| 854 |
+
"n": 70,
|
| 855 |
+
"errors": 4,
|
| 856 |
+
"error_rate": 0.05714285714285714
|
| 857 |
+
},
|
| 858 |
+
"0.99": {
|
| 859 |
+
"n": 64,
|
| 860 |
+
"errors": 3,
|
| 861 |
+
"error_rate": 0.046875
|
| 862 |
+
}
|
| 863 |
+
},
|
| 864 |
+
"selective": {
|
| 865 |
+
"0.5": {
|
| 866 |
+
"coverage": 0.5,
|
| 867 |
+
"accuracy": 0.975,
|
| 868 |
+
"confidence_cutoff": 0.9998666398849814
|
| 869 |
+
},
|
| 870 |
+
"0.8": {
|
| 871 |
+
"coverage": 0.8,
|
| 872 |
+
"accuracy": 0.953125,
|
| 873 |
+
"confidence_cutoff": 0.992725736876431
|
| 874 |
+
}
|
| 875 |
+
}
|
| 876 |
+
},
|
| 877 |
+
"mnli": {
|
| 878 |
+
"n": 80,
|
| 879 |
+
"nll": 1.052123542511008,
|
| 880 |
+
"acc": 0.8,
|
| 881 |
+
"ece": 0.17167671527270884,
|
| 882 |
+
"brier": 0.3473046080955827,
|
| 883 |
+
"mean_conf": 0.9680617952808579,
|
| 884 |
+
"confident_error_rate": 0.15,
|
| 885 |
+
"coverage_at_0_9": 0.9125,
|
| 886 |
+
"accuracy_at_0_9": 0.8356164383561644,
|
| 887 |
+
"coverage_at_5pct_error": 0.5,
|
| 888 |
+
"coverage_at_1pct_error": 0.2875,
|
| 889 |
+
"confidence_bias": 0.16806179528085785,
|
| 890 |
+
"top_bins": {
|
| 891 |
+
"0.9": {
|
| 892 |
+
"n": 73,
|
| 893 |
+
"errors": 12,
|
| 894 |
+
"error_rate": 0.1643835616438356
|
| 895 |
+
},
|
| 896 |
+
"0.95": {
|
| 897 |
+
"n": 70,
|
| 898 |
+
"errors": 12,
|
| 899 |
+
"error_rate": 0.17142857142857143
|
| 900 |
+
},
|
| 901 |
+
"0.99": {
|
| 902 |
+
"n": 60,
|
| 903 |
+
"errors": 9,
|
| 904 |
+
"error_rate": 0.15
|
| 905 |
+
}
|
| 906 |
+
},
|
| 907 |
+
"selective": {
|
| 908 |
+
"0.5": {
|
| 909 |
+
"coverage": 0.5,
|
| 910 |
+
"accuracy": 0.95,
|
| 911 |
+
"confidence_cutoff": 0.9986011104993117
|
| 912 |
+
},
|
| 913 |
+
"0.8": {
|
| 914 |
+
"coverage": 0.8,
|
| 915 |
+
"accuracy": 0.828125,
|
| 916 |
+
"confidence_cutoff": 0.9844243539180612
|
| 917 |
+
}
|
| 918 |
+
}
|
| 919 |
+
},
|
| 920 |
+
"sst5": {
|
| 921 |
+
"n": 80,
|
| 922 |
+
"nll": 1.3649759833053072,
|
| 923 |
+
"acc": 0.55,
|
| 924 |
+
"ece": 0.2214878206642504,
|
| 925 |
+
"brier": 0.6649634858322637,
|
| 926 |
+
"mean_conf": 0.7714878206642504,
|
| 927 |
+
"confident_error_rate": 0.075,
|
| 928 |
+
"coverage_at_0_9": 0.1875,
|
| 929 |
+
"accuracy_at_0_9": 0.6,
|
| 930 |
+
"coverage_at_5pct_error": 0.025,
|
| 931 |
+
"coverage_at_1pct_error": 0.025,
|
| 932 |
+
"confidence_bias": 0.22148782066425032,
|
| 933 |
+
"top_bins": {
|
| 934 |
+
"0.9": {
|
| 935 |
+
"n": 15,
|
| 936 |
+
"errors": 6,
|
| 937 |
+
"error_rate": 0.4
|
| 938 |
+
},
|
| 939 |
+
"0.95": {
|
| 940 |
+
"n": 6,
|
| 941 |
+
"errors": 2,
|
| 942 |
+
"error_rate": 0.3333333333333333
|
| 943 |
+
},
|
| 944 |
+
"0.99": {
|
| 945 |
+
"n": 0,
|
| 946 |
+
"errors": 0,
|
| 947 |
+
"error_rate": null
|
| 948 |
+
}
|
| 949 |
+
},
|
| 950 |
+
"selective": {
|
| 951 |
+
"0.5": {
|
| 952 |
+
"coverage": 0.5,
|
| 953 |
+
"accuracy": 0.625,
|
| 954 |
+
"confidence_cutoff": 0.7860612453157669
|
| 955 |
+
},
|
| 956 |
+
"0.8": {
|
| 957 |
+
"coverage": 0.8,
|
| 958 |
+
"accuracy": 0.578125,
|
| 959 |
+
"confidence_cutoff": 0.6293674590905433
|
| 960 |
+
}
|
| 961 |
+
},
|
| 962 |
+
"score_mae": 0.5703703601933559,
|
| 963 |
+
"ranked_probability_score": 0.10447893113587625
|
| 964 |
+
},
|
| 965 |
+
"trec": {
|
| 966 |
+
"n": 80,
|
| 967 |
+
"nll": 0.323195049906628,
|
| 968 |
+
"acc": 0.9625,
|
| 969 |
+
"ece": 0.039977654464988265,
|
| 970 |
+
"brier": 0.07744763392768336,
|
| 971 |
+
"mean_conf": 0.9936264905626302,
|
| 972 |
+
"confident_error_rate": 0.0375,
|
| 973 |
+
"coverage_at_0_9": 0.9875,
|
| 974 |
+
"accuracy_at_0_9": 0.9620253164556962,
|
| 975 |
+
"coverage_at_5pct_error": 1.0,
|
| 976 |
+
"coverage_at_1pct_error": 0.4625,
|
| 977 |
+
"confidence_bias": 0.03112649056263017,
|
| 978 |
+
"top_bins": {
|
| 979 |
+
"0.9": {
|
| 980 |
+
"n": 79,
|
| 981 |
+
"errors": 3,
|
| 982 |
+
"error_rate": 0.0379746835443038
|
| 983 |
+
},
|
| 984 |
+
"0.95": {
|
| 985 |
+
"n": 78,
|
| 986 |
+
"errors": 3,
|
| 987 |
+
"error_rate": 0.038461538461538464
|
| 988 |
+
},
|
| 989 |
+
"0.99": {
|
| 990 |
+
"n": 74,
|
| 991 |
+
"errors": 2,
|
| 992 |
+
"error_rate": 0.02702702702702703
|
| 993 |
+
}
|
| 994 |
+
},
|
| 995 |
+
"selective": {
|
| 996 |
+
"0.5": {
|
| 997 |
+
"coverage": 0.5,
|
| 998 |
+
"accuracy": 0.975,
|
| 999 |
+
"confidence_cutoff": 0.999997448185817
|
| 1000 |
+
},
|
| 1001 |
+
"0.8": {
|
| 1002 |
+
"coverage": 0.8,
|
| 1003 |
+
"accuracy": 0.984375,
|
| 1004 |
+
"confidence_cutoff": 0.9999833915718569
|
| 1005 |
+
}
|
| 1006 |
+
}
|
| 1007 |
+
},
|
| 1008 |
+
"yelp": {
|
| 1009 |
+
"n": 80,
|
| 1010 |
+
"nll": 0.8304499833943442,
|
| 1011 |
+
"acc": 0.7,
|
| 1012 |
+
"ece": 0.11416545194337306,
|
| 1013 |
+
"brier": 0.4696372702127844,
|
| 1014 |
+
"mean_conf": 0.7976821800264776,
|
| 1015 |
+
"confident_error_rate": 0.075,
|
| 1016 |
+
"coverage_at_0_9": 0.3375,
|
| 1017 |
+
"accuracy_at_0_9": 0.7777777777777778,
|
| 1018 |
+
"coverage_at_5pct_error": 0.1625,
|
| 1019 |
+
"coverage_at_1pct_error": 0.1625,
|
| 1020 |
+
"confidence_bias": 0.09768218002647766,
|
| 1021 |
+
"top_bins": {
|
| 1022 |
+
"0.9": {
|
| 1023 |
+
"n": 27,
|
| 1024 |
+
"errors": 6,
|
| 1025 |
+
"error_rate": 0.2222222222222222
|
| 1026 |
+
},
|
| 1027 |
+
"0.95": {
|
| 1028 |
+
"n": 15,
|
| 1029 |
+
"errors": 1,
|
| 1030 |
+
"error_rate": 0.06666666666666667
|
| 1031 |
+
},
|
| 1032 |
+
"0.99": {
|
| 1033 |
+
"n": 4,
|
| 1034 |
+
"errors": 0,
|
| 1035 |
+
"error_rate": 0.0
|
| 1036 |
+
}
|
| 1037 |
+
},
|
| 1038 |
+
"selective": {
|
| 1039 |
+
"0.5": {
|
| 1040 |
+
"coverage": 0.5,
|
| 1041 |
+
"accuracy": 0.75,
|
| 1042 |
+
"confidence_cutoff": 0.844931699592529
|
| 1043 |
+
},
|
| 1044 |
+
"0.8": {
|
| 1045 |
+
"coverage": 0.8,
|
| 1046 |
+
"accuracy": 0.71875,
|
| 1047 |
+
"confidence_cutoff": 0.6484297513182268
|
| 1048 |
+
}
|
| 1049 |
+
},
|
| 1050 |
+
"score_mae": 0.38942762256972624,
|
| 1051 |
+
"ranked_probability_score": 0.06537025361008628
|
| 1052 |
+
},
|
| 1053 |
+
"yelp_yn": {
|
| 1054 |
+
"n": 80,
|
| 1055 |
+
"nll": 0.29759105266356817,
|
| 1056 |
+
"acc": 0.9,
|
| 1057 |
+
"ece": 0.07443223145874,
|
| 1058 |
+
"brier": 0.15043048020648295,
|
| 1059 |
+
"mean_conf": 0.9646930004307563,
|
| 1060 |
+
"confident_error_rate": 0.0375,
|
| 1061 |
+
"coverage_at_0_9": 0.875,
|
| 1062 |
+
"accuracy_at_0_9": 0.9571428571428572,
|
| 1063 |
+
"coverage_at_5pct_error": 0.9,
|
| 1064 |
+
"coverage_at_1pct_error": 0.625,
|
| 1065 |
+
"confidence_bias": 0.06469300043075632,
|
| 1066 |
+
"top_bins": {
|
| 1067 |
+
"0.9": {
|
| 1068 |
+
"n": 70,
|
| 1069 |
+
"errors": 3,
|
| 1070 |
+
"error_rate": 0.04285714285714286
|
| 1071 |
+
},
|
| 1072 |
+
"0.95": {
|
| 1073 |
+
"n": 69,
|
| 1074 |
+
"errors": 3,
|
| 1075 |
+
"error_rate": 0.043478260869565216
|
| 1076 |
+
},
|
| 1077 |
+
"0.99": {
|
| 1078 |
+
"n": 60,
|
| 1079 |
+
"errors": 2,
|
| 1080 |
+
"error_rate": 0.03333333333333333
|
| 1081 |
+
}
|
| 1082 |
+
},
|
| 1083 |
+
"selective": {
|
| 1084 |
+
"0.5": {
|
| 1085 |
+
"coverage": 0.5,
|
| 1086 |
+
"accuracy": 1.0,
|
| 1087 |
+
"confidence_cutoff": 0.9995460689181557
|
| 1088 |
+
},
|
| 1089 |
+
"0.8": {
|
| 1090 |
+
"coverage": 0.8,
|
| 1091 |
+
"accuracy": 0.953125,
|
| 1092 |
+
"confidence_cutoff": 0.9837811818800426
|
| 1093 |
+
}
|
| 1094 |
+
}
|
| 1095 |
+
}
|
| 1096 |
+
},
|
| 1097 |
+
"variants": {
|
| 1098 |
+
"clean": {
|
| 1099 |
+
"n": 1264,
|
| 1100 |
+
"nll": 0.6044957065419644,
|
| 1101 |
+
"acc": 0.8291139240506329,
|
| 1102 |
+
"ece": 0.09460930817547933,
|
| 1103 |
+
"brier": 0.26350001968671594,
|
| 1104 |
+
"mean_conf": 0.9216668428711666,
|
| 1105 |
+
"confident_error_rate": 0.0625,
|
| 1106 |
+
"coverage_at_0_9": 0.7579113924050633,
|
| 1107 |
+
"accuracy_at_0_9": 0.9175365344467641,
|
| 1108 |
+
"coverage_at_5pct_error": 0.5759493670886076,
|
| 1109 |
+
"coverage_at_1pct_error": 0.20174050632911392,
|
| 1110 |
+
"confidence_bias": 0.09255291882053374,
|
| 1111 |
+
"top_bins": {
|
| 1112 |
+
"0.9": {
|
| 1113 |
+
"n": 958,
|
| 1114 |
+
"errors": 79,
|
| 1115 |
+
"error_rate": 0.0824634655532359
|
| 1116 |
+
},
|
| 1117 |
+
"0.95": {
|
| 1118 |
+
"n": 877,
|
| 1119 |
+
"errors": 58,
|
| 1120 |
+
"error_rate": 0.0661345496009122
|
| 1121 |
+
},
|
| 1122 |
+
"0.99": {
|
| 1123 |
+
"n": 731,
|
| 1124 |
+
"errors": 37,
|
| 1125 |
+
"error_rate": 0.0506155950752394
|
| 1126 |
+
}
|
| 1127 |
+
},
|
| 1128 |
+
"selective": {
|
| 1129 |
+
"0.5": {
|
| 1130 |
+
"coverage": 0.5,
|
| 1131 |
+
"accuracy": 0.9636075949367089,
|
| 1132 |
+
"confidence_cutoff": 0.9966887232973961
|
| 1133 |
+
},
|
| 1134 |
+
"0.8": {
|
| 1135 |
+
"coverage": 0.8006329113924051,
|
| 1136 |
+
"accuracy": 0.9110671936758893,
|
| 1137 |
+
"confidence_cutoff": 0.8535004294293571
|
| 1138 |
+
}
|
| 1139 |
+
},
|
| 1140 |
+
"score_mae": 0.500978878525793,
|
| 1141 |
+
"ranked_probability_score": 0.08832172033138225
|
| 1142 |
+
},
|
| 1143 |
+
"none_absent": {
|
| 1144 |
+
"n": 60,
|
| 1145 |
+
"nll": 0.46842980464110273,
|
| 1146 |
+
"acc": 0.8666666666666667,
|
| 1147 |
+
"ece": 0.10731346782879556,
|
| 1148 |
+
"brier": 0.21873090677461612,
|
| 1149 |
+
"mean_conf": 0.9591599892690883,
|
| 1150 |
+
"confident_error_rate": 0.08333333333333333,
|
| 1151 |
+
"coverage_at_0_9": 0.8833333333333333,
|
| 1152 |
+
"accuracy_at_0_9": 0.9056603773584906,
|
| 1153 |
+
"coverage_at_5pct_error": 0.7333333333333333,
|
| 1154 |
+
"coverage_at_1pct_error": 0.23333333333333334,
|
| 1155 |
+
"confidence_bias": 0.0924933226024216,
|
| 1156 |
+
"top_bins": {
|
| 1157 |
+
"0.9": {
|
| 1158 |
+
"n": 53,
|
| 1159 |
+
"errors": 5,
|
| 1160 |
+
"error_rate": 0.09433962264150944
|
| 1161 |
+
},
|
| 1162 |
+
"0.95": {
|
| 1163 |
+
"n": 48,
|
| 1164 |
+
"errors": 5,
|
| 1165 |
+
"error_rate": 0.10416666666666667
|
| 1166 |
+
},
|
| 1167 |
+
"0.99": {
|
| 1168 |
+
"n": 33,
|
| 1169 |
+
"errors": 1,
|
| 1170 |
+
"error_rate": 0.030303030303030304
|
| 1171 |
+
}
|
| 1172 |
+
},
|
| 1173 |
+
"selective": {
|
| 1174 |
+
"0.5": {
|
| 1175 |
+
"coverage": 0.5,
|
| 1176 |
+
"accuracy": 0.9666666666666667,
|
| 1177 |
+
"confidence_cutoff": 0.9937243334013325
|
| 1178 |
+
},
|
| 1179 |
+
"0.8": {
|
| 1180 |
+
"coverage": 0.8,
|
| 1181 |
+
"accuracy": 0.8958333333333334,
|
| 1182 |
+
"confidence_cutoff": 0.9541765484061251
|
| 1183 |
+
}
|
| 1184 |
+
}
|
| 1185 |
+
},
|
| 1186 |
+
"none_present": {
|
| 1187 |
+
"n": 60,
|
| 1188 |
+
"nll": 0.8719402596994842,
|
| 1189 |
+
"acc": 0.8333333333333334,
|
| 1190 |
+
"ece": 0.1291757249761845,
|
| 1191 |
+
"brier": 0.2787725996108818,
|
| 1192 |
+
"mean_conf": 0.9450414799367672,
|
| 1193 |
+
"confident_error_rate": 0.06666666666666667,
|
| 1194 |
+
"coverage_at_0_9": 0.8,
|
| 1195 |
+
"accuracy_at_0_9": 0.9166666666666666,
|
| 1196 |
+
"coverage_at_5pct_error": 0.6166666666666667,
|
| 1197 |
+
"coverage_at_1pct_error": 0.0,
|
| 1198 |
+
"confidence_bias": 0.11170814660343387,
|
| 1199 |
+
"top_bins": {
|
| 1200 |
+
"0.9": {
|
| 1201 |
+
"n": 48,
|
| 1202 |
+
"errors": 4,
|
| 1203 |
+
"error_rate": 0.08333333333333333
|
| 1204 |
+
},
|
| 1205 |
+
"0.95": {
|
| 1206 |
+
"n": 41,
|
| 1207 |
+
"errors": 3,
|
| 1208 |
+
"error_rate": 0.07317073170731707
|
| 1209 |
+
},
|
| 1210 |
+
"0.99": {
|
| 1211 |
+
"n": 29,
|
| 1212 |
+
"errors": 1,
|
| 1213 |
+
"error_rate": 0.034482758620689655
|
| 1214 |
+
}
|
| 1215 |
+
},
|
| 1216 |
+
"selective": {
|
| 1217 |
+
"0.5": {
|
| 1218 |
+
"coverage": 0.5,
|
| 1219 |
+
"accuracy": 0.9666666666666667,
|
| 1220 |
+
"confidence_cutoff": 0.9895670129845321
|
| 1221 |
+
},
|
| 1222 |
+
"0.8": {
|
| 1223 |
+
"coverage": 0.8,
|
| 1224 |
+
"accuracy": 0.9166666666666666,
|
| 1225 |
+
"confidence_cutoff": 0.9049199074136486
|
| 1226 |
+
}
|
| 1227 |
+
}
|
| 1228 |
+
},
|
| 1229 |
+
"permuted": {
|
| 1230 |
+
"n": 84,
|
| 1231 |
+
"nll": 0.49155584391017276,
|
| 1232 |
+
"acc": 0.9166666666666666,
|
| 1233 |
+
"ece": 0.08669851605730695,
|
| 1234 |
+
"brier": 0.1495505098643444,
|
| 1235 |
+
"mean_conf": 0.9700030560455571,
|
| 1236 |
+
"confident_error_rate": 0.047619047619047616,
|
| 1237 |
+
"coverage_at_0_9": 0.9166666666666666,
|
| 1238 |
+
"accuracy_at_0_9": 0.948051948051948,
|
| 1239 |
+
"coverage_at_5pct_error": 0.8452380952380952,
|
| 1240 |
+
"coverage_at_1pct_error": 0.09523809523809523,
|
| 1241 |
+
"confidence_bias": 0.053336389378890514,
|
| 1242 |
+
"top_bins": {
|
| 1243 |
+
"0.9": {
|
| 1244 |
+
"n": 77,
|
| 1245 |
+
"errors": 4,
|
| 1246 |
+
"error_rate": 0.05194805194805195
|
| 1247 |
+
},
|
| 1248 |
+
"0.95": {
|
| 1249 |
+
"n": 76,
|
| 1250 |
+
"errors": 4,
|
| 1251 |
+
"error_rate": 0.05263157894736842
|
| 1252 |
+
},
|
| 1253 |
+
"0.99": {
|
| 1254 |
+
"n": 72,
|
| 1255 |
+
"errors": 4,
|
| 1256 |
+
"error_rate": 0.05555555555555555
|
| 1257 |
+
}
|
| 1258 |
+
},
|
| 1259 |
+
"selective": {
|
| 1260 |
+
"0.5": {
|
| 1261 |
+
"coverage": 0.5,
|
| 1262 |
+
"accuracy": 0.9761904761904762,
|
| 1263 |
+
"confidence_cutoff": 0.9995629797519826
|
| 1264 |
+
},
|
| 1265 |
+
"0.8": {
|
| 1266 |
+
"coverage": 0.8095238095238095,
|
| 1267 |
+
"accuracy": 0.9558823529411765,
|
| 1268 |
+
"confidence_cutoff": 0.9925867406723362
|
| 1269 |
+
}
|
| 1270 |
+
}
|
| 1271 |
+
}
|
| 1272 |
+
},
|
| 1273 |
+
"heldout_tasks": {},
|
| 1274 |
+
"permutation": {
|
| 1275 |
+
"n": 60,
|
| 1276 |
+
"mean_max_delta": 0.022957842014552834,
|
| 1277 |
+
"flip_rate": 0.016666666666666666
|
| 1278 |
+
},
|
| 1279 |
+
"temperature": 2.1435469250725863,
|
| 1280 |
+
"calibrated_clean": {
|
| 1281 |
+
"n": 1264,
|
| 1282 |
+
"nll": 0.44868414696957154,
|
| 1283 |
+
"acc": 0.8291139240506329,
|
| 1284 |
+
"ece": 0.033731521167180686,
|
| 1285 |
+
"brier": 0.24321761776260586,
|
| 1286 |
+
"mean_conf": 0.836360127481958,
|
| 1287 |
+
"confident_error_rate": 0.02531645569620253,
|
| 1288 |
+
"coverage_at_0_9": 0.5569620253164557,
|
| 1289 |
+
"accuracy_at_0_9": 0.9545454545454546,
|
| 1290 |
+
"coverage_at_5pct_error": 0.5886075949367089,
|
| 1291 |
+
"coverage_at_1pct_error": 0.18037974683544303,
|
| 1292 |
+
"confidence_bias": 0.007246203431325093,
|
| 1293 |
+
"top_bins": {
|
| 1294 |
+
"0.9": {
|
| 1295 |
+
"n": 704,
|
| 1296 |
+
"errors": 32,
|
| 1297 |
+
"error_rate": 0.045454545454545456
|
| 1298 |
+
},
|
| 1299 |
+
"0.95": {
|
| 1300 |
+
"n": 552,
|
| 1301 |
+
"errors": 12,
|
| 1302 |
+
"error_rate": 0.021739130434782608
|
| 1303 |
+
},
|
| 1304 |
+
"0.99": {
|
| 1305 |
+
"n": 266,
|
| 1306 |
+
"errors": 3,
|
| 1307 |
+
"error_rate": 0.011278195488721804
|
| 1308 |
+
}
|
| 1309 |
+
},
|
| 1310 |
+
"selective": {
|
| 1311 |
+
"0.5": {
|
| 1312 |
+
"coverage": 0.5,
|
| 1313 |
+
"accuracy": 0.9683544303797469,
|
| 1314 |
+
"confidence_cutoff": 0.9276771569469373
|
| 1315 |
+
},
|
| 1316 |
+
"0.8": {
|
| 1317 |
+
"coverage": 0.8006329113924051,
|
| 1318 |
+
"accuracy": 0.9071146245059288,
|
| 1319 |
+
"confidence_cutoff": 0.6464511143215232
|
| 1320 |
+
}
|
| 1321 |
+
},
|
| 1322 |
+
"score_mae": 0.5358162354852758,
|
| 1323 |
+
"ranked_probability_score": 0.0820044994751479
|
| 1324 |
+
},
|
| 1325 |
+
"metric_policy": {
|
| 1326 |
+
"nll_floor": 1e-09,
|
| 1327 |
+
"renormalize_returned_probabilities": true,
|
| 1328 |
+
"raw_sums_outside_1e_5": 0,
|
| 1329 |
+
"returned_zeros": 0
|
| 1330 |
+
},
|
| 1331 |
+
"coverage": {
|
| 1332 |
+
"requested_records": 1204,
|
| 1333 |
+
"requested_questions": 1468,
|
| 1334 |
+
"evaluated_records": 1204,
|
| 1335 |
+
"evaluated_questions": 1468,
|
| 1336 |
+
"rejected_records": 0,
|
| 1337 |
+
"truncated_records": 0
|
| 1338 |
+
},
|
| 1339 |
+
"latency_ms": {
|
| 1340 |
+
"median": 44.00106950004101,
|
| 1341 |
+
"p95": 53.79865120008844
|
| 1342 |
+
},
|
| 1343 |
+
"transfer": {
|
| 1344 |
+
"objective": -0.9744465608543084,
|
| 1345 |
+
"paired_flip": {
|
| 1346 |
+
"pairs": 64,
|
| 1347 |
+
"flip_rate": 0.375,
|
| 1348 |
+
"both_correct_rate": 0.375,
|
| 1349 |
+
"invariant_pairs": 24,
|
| 1350 |
+
"invariance_rate": 1.0,
|
| 1351 |
+
"invariant_both_correct_rate": 0.6666666666666666
|
| 1352 |
+
},
|
| 1353 |
+
"unknowable": null,
|
| 1354 |
+
"clean": {
|
| 1355 |
+
"n": 656,
|
| 1356 |
+
"nll": 0.9570682750687798,
|
| 1357 |
+
"acc": 0.6432926829268293,
|
| 1358 |
+
"ece": 0.18401217986343424,
|
| 1359 |
+
"brier": 0.5125584983305406,
|
| 1360 |
+
"mean_conf": 0.8237780936358884,
|
| 1361 |
+
"confident_error_rate": 0.09603658536585366,
|
| 1362 |
+
"coverage_at_0_9": 0.46189024390243905,
|
| 1363 |
+
"accuracy_at_0_9": 0.7920792079207921,
|
| 1364 |
+
"coverage_at_5pct_error": 0.16615853658536586,
|
| 1365 |
+
"coverage_at_1pct_error": 0.08841463414634146,
|
| 1366 |
+
"confidence_bias": 0.1804854107090591,
|
| 1367 |
+
"top_bins": {
|
| 1368 |
+
"0.9": {
|
| 1369 |
+
"n": 303,
|
| 1370 |
+
"errors": 63,
|
| 1371 |
+
"error_rate": 0.2079207920792079
|
| 1372 |
+
},
|
| 1373 |
+
"0.95": {
|
| 1374 |
+
"n": 235,
|
| 1375 |
+
"errors": 31,
|
| 1376 |
+
"error_rate": 0.13191489361702127
|
| 1377 |
+
},
|
| 1378 |
+
"0.99": {
|
| 1379 |
+
"n": 145,
|
| 1380 |
+
"errors": 14,
|
| 1381 |
+
"error_rate": 0.09655172413793103
|
| 1382 |
+
}
|
| 1383 |
+
},
|
| 1384 |
+
"selective": {
|
| 1385 |
+
"0.5": {
|
| 1386 |
+
"coverage": 0.5,
|
| 1387 |
+
"accuracy": 0.7835365853658537,
|
| 1388 |
+
"confidence_cutoff": 0.8847859831447148
|
| 1389 |
+
},
|
| 1390 |
+
"0.8": {
|
| 1391 |
+
"coverage": 0.8003048780487805,
|
| 1392 |
+
"accuracy": 0.700952380952381,
|
| 1393 |
+
"confidence_cutoff": 0.6439839389314616
|
| 1394 |
+
}
|
| 1395 |
+
},
|
| 1396 |
+
"score_mae": 0.7107663444740075,
|
| 1397 |
+
"ranked_probability_score": 0.33044152610202326
|
| 1398 |
+
},
|
| 1399 |
+
"tasks": {
|
| 1400 |
+
"composition_held_and_or": {
|
| 1401 |
+
"n": 32,
|
| 1402 |
+
"nll": 0.9136906300332568,
|
| 1403 |
+
"acc": 0.65625,
|
| 1404 |
+
"ece": 0.24657832195009244,
|
| 1405 |
+
"brier": 0.5361075837376617,
|
| 1406 |
+
"mean_conf": 0.9028283219500923,
|
| 1407 |
+
"confident_error_rate": 0.21875,
|
| 1408 |
+
"coverage_at_0_9": 0.8125,
|
| 1409 |
+
"accuracy_at_0_9": 0.7307692307692307,
|
| 1410 |
+
"coverage_at_5pct_error": 0.125,
|
| 1411 |
+
"coverage_at_1pct_error": 0.125,
|
| 1412 |
+
"confidence_bias": 0.24657832195009233,
|
| 1413 |
+
"top_bins": {
|
| 1414 |
+
"0.9": {
|
| 1415 |
+
"n": 26,
|
| 1416 |
+
"errors": 7,
|
| 1417 |
+
"error_rate": 0.2692307692307692
|
| 1418 |
+
},
|
| 1419 |
+
"0.95": {
|
| 1420 |
+
"n": 19,
|
| 1421 |
+
"errors": 3,
|
| 1422 |
+
"error_rate": 0.15789473684210525
|
| 1423 |
+
},
|
| 1424 |
+
"0.99": {
|
| 1425 |
+
"n": 3,
|
| 1426 |
+
"errors": 0,
|
| 1427 |
+
"error_rate": 0.0
|
| 1428 |
+
}
|
| 1429 |
+
},
|
| 1430 |
+
"selective": {
|
| 1431 |
+
"0.5": {
|
| 1432 |
+
"coverage": 0.5,
|
| 1433 |
+
"accuracy": 0.8125,
|
| 1434 |
+
"confidence_cutoff": 0.9686380624771118
|
| 1435 |
+
},
|
| 1436 |
+
"0.8": {
|
| 1437 |
+
"coverage": 0.8125,
|
| 1438 |
+
"accuracy": 0.7307692307692307,
|
| 1439 |
+
"confidence_cutoff": 0.9060071774274645
|
| 1440 |
+
}
|
| 1441 |
+
}
|
| 1442 |
+
},
|
| 1443 |
+
"composition_held_conditional": {
|
| 1444 |
+
"n": 32,
|
| 1445 |
+
"nll": 0.6448629311463261,
|
| 1446 |
+
"acc": 0.71875,
|
| 1447 |
+
"ece": 0.10729094246902517,
|
| 1448 |
+
"brier": 0.4221857657236401,
|
| 1449 |
+
"mean_conf": 0.8045070165534562,
|
| 1450 |
+
"confident_error_rate": 0.03125,
|
| 1451 |
+
"coverage_at_0_9": 0.125,
|
| 1452 |
+
"accuracy_at_0_9": 0.75,
|
| 1453 |
+
"coverage_at_5pct_error": 0.03125,
|
| 1454 |
+
"coverage_at_1pct_error": 0.03125,
|
| 1455 |
+
"confidence_bias": 0.08575701655345624,
|
| 1456 |
+
"top_bins": {
|
| 1457 |
+
"0.9": {
|
| 1458 |
+
"n": 4,
|
| 1459 |
+
"errors": 1,
|
| 1460 |
+
"error_rate": 0.25
|
| 1461 |
+
},
|
| 1462 |
+
"0.95": {
|
| 1463 |
+
"n": 2,
|
| 1464 |
+
"errors": 1,
|
| 1465 |
+
"error_rate": 0.5
|
| 1466 |
+
},
|
| 1467 |
+
"0.99": {
|
| 1468 |
+
"n": 0,
|
| 1469 |
+
"errors": 0,
|
| 1470 |
+
"error_rate": null
|
| 1471 |
+
}
|
| 1472 |
+
},
|
| 1473 |
+
"selective": {
|
| 1474 |
+
"0.5": {
|
| 1475 |
+
"coverage": 0.5,
|
| 1476 |
+
"accuracy": 0.8125,
|
| 1477 |
+
"confidence_cutoff": 0.855546150936301
|
| 1478 |
+
},
|
| 1479 |
+
"0.8": {
|
| 1480 |
+
"coverage": 0.8125,
|
| 1481 |
+
"accuracy": 0.7692307692307693,
|
| 1482 |
+
"confidence_cutoff": 0.654670575539504
|
| 1483 |
+
}
|
| 1484 |
+
}
|
| 1485 |
+
},
|
| 1486 |
+
"composition_held_or_not": {
|
| 1487 |
+
"n": 32,
|
| 1488 |
+
"nll": 0.7429562768560309,
|
| 1489 |
+
"acc": 0.625,
|
| 1490 |
+
"ece": 0.2541212013040856,
|
| 1491 |
+
"brier": 0.5184103008702212,
|
| 1492 |
+
"mean_conf": 0.7345879801936439,
|
| 1493 |
+
"confident_error_rate": 0.03125,
|
| 1494 |
+
"coverage_at_0_9": 0.21875,
|
| 1495 |
+
"accuracy_at_0_9": 0.8571428571428571,
|
| 1496 |
+
"coverage_at_5pct_error": 0.0,
|
| 1497 |
+
"coverage_at_1pct_error": 0.0,
|
| 1498 |
+
"confidence_bias": 0.10958798019364391,
|
| 1499 |
+
"top_bins": {
|
| 1500 |
+
"0.9": {
|
| 1501 |
+
"n": 7,
|
| 1502 |
+
"errors": 1,
|
| 1503 |
+
"error_rate": 0.14285714285714285
|
| 1504 |
+
},
|
| 1505 |
+
"0.95": {
|
| 1506 |
+
"n": 4,
|
| 1507 |
+
"errors": 1,
|
| 1508 |
+
"error_rate": 0.25
|
| 1509 |
+
},
|
| 1510 |
+
"0.99": {
|
| 1511 |
+
"n": 0,
|
| 1512 |
+
"errors": 0,
|
| 1513 |
+
"error_rate": null
|
| 1514 |
+
}
|
| 1515 |
+
},
|
| 1516 |
+
"selective": {
|
| 1517 |
+
"0.5": {
|
| 1518 |
+
"coverage": 0.53125,
|
| 1519 |
+
"accuracy": 0.6470588235294118,
|
| 1520 |
+
"confidence_cutoff": 0.7171741937748848
|
| 1521 |
+
},
|
| 1522 |
+
"0.8": {
|
| 1523 |
+
"coverage": 0.84375,
|
| 1524 |
+
"accuracy": 0.5925925925925926,
|
| 1525 |
+
"confidence_cutoff": 0.5604099631309509
|
| 1526 |
+
}
|
| 1527 |
+
}
|
| 1528 |
+
},
|
| 1529 |
+
"contrastive_authorization": {
|
| 1530 |
+
"n": 40,
|
| 1531 |
+
"nll": 0.19467410615873026,
|
| 1532 |
+
"acc": 0.9,
|
| 1533 |
+
"ece": 0.03820846875417625,
|
| 1534 |
+
"brier": 0.12726178130600177,
|
| 1535 |
+
"mean_conf": 0.9201264847929028,
|
| 1536 |
+
"confident_error_rate": 0.025,
|
| 1537 |
+
"coverage_at_0_9": 0.75,
|
| 1538 |
+
"accuracy_at_0_9": 0.9666666666666667,
|
| 1539 |
+
"coverage_at_5pct_error": 0.85,
|
| 1540 |
+
"coverage_at_1pct_error": 0.725,
|
| 1541 |
+
"confidence_bias": 0.0201264847929028,
|
| 1542 |
+
"top_bins": {
|
| 1543 |
+
"0.9": {
|
| 1544 |
+
"n": 30,
|
| 1545 |
+
"errors": 1,
|
| 1546 |
+
"error_rate": 0.03333333333333333
|
| 1547 |
+
},
|
| 1548 |
+
"0.95": {
|
| 1549 |
+
"n": 29,
|
| 1550 |
+
"errors": 0,
|
| 1551 |
+
"error_rate": 0.0
|
| 1552 |
+
},
|
| 1553 |
+
"0.99": {
|
| 1554 |
+
"n": 20,
|
| 1555 |
+
"errors": 0,
|
| 1556 |
+
"error_rate": 0.0
|
| 1557 |
+
}
|
| 1558 |
+
},
|
| 1559 |
+
"selective": {
|
| 1560 |
+
"0.5": {
|
| 1561 |
+
"coverage": 0.5,
|
| 1562 |
+
"accuracy": 1.0,
|
| 1563 |
+
"confidence_cutoff": 0.9971347548104887
|
| 1564 |
+
},
|
| 1565 |
+
"0.8": {
|
| 1566 |
+
"coverage": 0.8,
|
| 1567 |
+
"accuracy": 0.96875,
|
| 1568 |
+
"confidence_cutoff": 0.8816031611682398
|
| 1569 |
+
}
|
| 1570 |
+
}
|
| 1571 |
+
},
|
| 1572 |
+
"contrastive_deadline": {
|
| 1573 |
+
"n": 40,
|
| 1574 |
+
"nll": 2.785418715865327,
|
| 1575 |
+
"acc": 0.275,
|
| 1576 |
+
"ece": 0.6633694597358357,
|
| 1577 |
+
"brier": 1.2868469074566389,
|
| 1578 |
+
"mean_conf": 0.9383694597358356,
|
| 1579 |
+
"confident_error_rate": 0.6,
|
| 1580 |
+
"coverage_at_0_9": 0.85,
|
| 1581 |
+
"accuracy_at_0_9": 0.29411764705882354,
|
| 1582 |
+
"coverage_at_5pct_error": 0.025,
|
| 1583 |
+
"coverage_at_1pct_error": 0.025,
|
| 1584 |
+
"confidence_bias": 0.6633694597358356,
|
| 1585 |
+
"top_bins": {
|
| 1586 |
+
"0.9": {
|
| 1587 |
+
"n": 34,
|
| 1588 |
+
"errors": 24,
|
| 1589 |
+
"error_rate": 0.7058823529411765
|
| 1590 |
+
},
|
| 1591 |
+
"0.95": {
|
| 1592 |
+
"n": 17,
|
| 1593 |
+
"errors": 9,
|
| 1594 |
+
"error_rate": 0.5294117647058824
|
| 1595 |
+
},
|
| 1596 |
+
"0.99": {
|
| 1597 |
+
"n": 13,
|
| 1598 |
+
"errors": 7,
|
| 1599 |
+
"error_rate": 0.5384615384615384
|
| 1600 |
+
}
|
| 1601 |
+
},
|
| 1602 |
+
"selective": {
|
| 1603 |
+
"0.5": {
|
| 1604 |
+
"coverage": 0.5,
|
| 1605 |
+
"accuracy": 0.45,
|
| 1606 |
+
"confidence_cutoff": 0.9361307481507846
|
| 1607 |
+
},
|
| 1608 |
+
"0.8": {
|
| 1609 |
+
"coverage": 0.8,
|
| 1610 |
+
"accuracy": 0.3125,
|
| 1611 |
+
"confidence_cutoff": 0.9177724490540244
|
| 1612 |
+
}
|
| 1613 |
+
},
|
| 1614 |
+
"score_mae": 0.7107663444740075,
|
| 1615 |
+
"ranked_probability_score": 0.33044152610202326
|
| 1616 |
+
},
|
| 1617 |
+
"emotion": {
|
| 1618 |
+
"n": 80,
|
| 1619 |
+
"nll": 1.653093556050728,
|
| 1620 |
+
"acc": 0.5375,
|
| 1621 |
+
"ece": 0.22901336770397754,
|
| 1622 |
+
"brier": 0.6605442054462966,
|
| 1623 |
+
"mean_conf": 0.7296495068187532,
|
| 1624 |
+
"confident_error_rate": 0.0625,
|
| 1625 |
+
"coverage_at_0_9": 0.2625,
|
| 1626 |
+
"accuracy_at_0_9": 0.7619047619047619,
|
| 1627 |
+
"coverage_at_5pct_error": 0.0,
|
| 1628 |
+
"coverage_at_1pct_error": 0.0,
|
| 1629 |
+
"confidence_bias": 0.1921495068187532,
|
| 1630 |
+
"top_bins": {
|
| 1631 |
+
"0.9": {
|
| 1632 |
+
"n": 21,
|
| 1633 |
+
"errors": 5,
|
| 1634 |
+
"error_rate": 0.23809523809523808
|
| 1635 |
+
},
|
| 1636 |
+
"0.95": {
|
| 1637 |
+
"n": 16,
|
| 1638 |
+
"errors": 4,
|
| 1639 |
+
"error_rate": 0.25
|
| 1640 |
+
},
|
| 1641 |
+
"0.99": {
|
| 1642 |
+
"n": 7,
|
| 1643 |
+
"errors": 3,
|
| 1644 |
+
"error_rate": 0.42857142857142855
|
| 1645 |
+
}
|
| 1646 |
+
},
|
| 1647 |
+
"selective": {
|
| 1648 |
+
"0.5": {
|
| 1649 |
+
"coverage": 0.5,
|
| 1650 |
+
"accuracy": 0.65,
|
| 1651 |
+
"confidence_cutoff": 0.766856165763948
|
| 1652 |
+
},
|
| 1653 |
+
"0.8": {
|
| 1654 |
+
"coverage": 0.8,
|
| 1655 |
+
"accuracy": 0.5625,
|
| 1656 |
+
"confidence_cutoff": 0.5523026767607064
|
| 1657 |
+
}
|
| 1658 |
+
}
|
| 1659 |
+
},
|
| 1660 |
+
"mmlu": {
|
| 1661 |
+
"n": 80,
|
| 1662 |
+
"nll": 1.4114379018186007,
|
| 1663 |
+
"acc": 0.4125,
|
| 1664 |
+
"ece": 0.24866880218243045,
|
| 1665 |
+
"brier": 0.7462173145072892,
|
| 1666 |
+
"mean_conf": 0.6611688021824303,
|
| 1667 |
+
"confident_error_rate": 0.0625,
|
| 1668 |
+
"coverage_at_0_9": 0.25,
|
| 1669 |
+
"accuracy_at_0_9": 0.75,
|
| 1670 |
+
"coverage_at_5pct_error": 0.125,
|
| 1671 |
+
"coverage_at_1pct_error": 0.125,
|
| 1672 |
+
"confidence_bias": 0.24866880218243037,
|
| 1673 |
+
"top_bins": {
|
| 1674 |
+
"0.9": {
|
| 1675 |
+
"n": 20,
|
| 1676 |
+
"errors": 5,
|
| 1677 |
+
"error_rate": 0.25
|
| 1678 |
+
},
|
| 1679 |
+
"0.95": {
|
| 1680 |
+
"n": 15,
|
| 1681 |
+
"errors": 2,
|
| 1682 |
+
"error_rate": 0.13333333333333333
|
| 1683 |
+
},
|
| 1684 |
+
"0.99": {
|
| 1685 |
+
"n": 11,
|
| 1686 |
+
"errors": 1,
|
| 1687 |
+
"error_rate": 0.09090909090909091
|
| 1688 |
+
}
|
| 1689 |
+
},
|
| 1690 |
+
"selective": {
|
| 1691 |
+
"0.5": {
|
| 1692 |
+
"coverage": 0.5,
|
| 1693 |
+
"accuracy": 0.525,
|
| 1694 |
+
"confidence_cutoff": 0.6131941239996213
|
| 1695 |
+
},
|
| 1696 |
+
"0.8": {
|
| 1697 |
+
"coverage": 0.8,
|
| 1698 |
+
"accuracy": 0.421875,
|
| 1699 |
+
"confidence_cutoff": 0.4523720938182154
|
| 1700 |
+
}
|
| 1701 |
+
}
|
| 1702 |
+
},
|
| 1703 |
+
"paws": {
|
| 1704 |
+
"n": 80,
|
| 1705 |
+
"nll": 0.8953421021329806,
|
| 1706 |
+
"acc": 0.5875,
|
| 1707 |
+
"ece": 0.2541297593433282,
|
| 1708 |
+
"brier": 0.6186855308160963,
|
| 1709 |
+
"mean_conf": 0.7995476792756492,
|
| 1710 |
+
"confident_error_rate": 0.0625,
|
| 1711 |
+
"coverage_at_0_9": 0.1375,
|
| 1712 |
+
"accuracy_at_0_9": 0.5454545454545454,
|
| 1713 |
+
"coverage_at_5pct_error": 0.0,
|
| 1714 |
+
"coverage_at_1pct_error": 0.0,
|
| 1715 |
+
"confidence_bias": 0.21204767927564916,
|
| 1716 |
+
"top_bins": {
|
| 1717 |
+
"0.9": {
|
| 1718 |
+
"n": 11,
|
| 1719 |
+
"errors": 5,
|
| 1720 |
+
"error_rate": 0.45454545454545453
|
| 1721 |
+
},
|
| 1722 |
+
"0.95": {
|
| 1723 |
+
"n": 3,
|
| 1724 |
+
"errors": 1,
|
| 1725 |
+
"error_rate": 0.3333333333333333
|
| 1726 |
+
},
|
| 1727 |
+
"0.99": {
|
| 1728 |
+
"n": 0,
|
| 1729 |
+
"errors": 0,
|
| 1730 |
+
"error_rate": null
|
| 1731 |
+
}
|
| 1732 |
+
},
|
| 1733 |
+
"selective": {
|
| 1734 |
+
"0.5": {
|
| 1735 |
+
"coverage": 0.5,
|
| 1736 |
+
"accuracy": 0.55,
|
| 1737 |
+
"confidence_cutoff": 0.8083969234168988
|
| 1738 |
+
},
|
| 1739 |
+
"0.8": {
|
| 1740 |
+
"coverage": 0.8,
|
| 1741 |
+
"accuracy": 0.578125,
|
| 1742 |
+
"confidence_cutoff": 0.7218610644340515
|
| 1743 |
+
}
|
| 1744 |
+
}
|
| 1745 |
+
},
|
| 1746 |
+
"qnli": {
|
| 1747 |
+
"n": 80,
|
| 1748 |
+
"nll": 0.4378801907288863,
|
| 1749 |
+
"acc": 0.825,
|
| 1750 |
+
"ece": 0.07249396310174361,
|
| 1751 |
+
"brier": 0.27092479198021,
|
| 1752 |
+
"mean_conf": 0.8974939631017437,
|
| 1753 |
+
"confident_error_rate": 0.05,
|
| 1754 |
+
"coverage_at_0_9": 0.675,
|
| 1755 |
+
"accuracy_at_0_9": 0.9259259259259259,
|
| 1756 |
+
"coverage_at_5pct_error": 0.55,
|
| 1757 |
+
"coverage_at_1pct_error": 0.2875,
|
| 1758 |
+
"confidence_bias": 0.07249396310174372,
|
| 1759 |
+
"top_bins": {
|
| 1760 |
+
"0.9": {
|
| 1761 |
+
"n": 54,
|
| 1762 |
+
"errors": 4,
|
| 1763 |
+
"error_rate": 0.07407407407407407
|
| 1764 |
+
},
|
| 1765 |
+
"0.95": {
|
| 1766 |
+
"n": 40,
|
| 1767 |
+
"errors": 2,
|
| 1768 |
+
"error_rate": 0.05
|
| 1769 |
+
},
|
| 1770 |
+
"0.99": {
|
| 1771 |
+
"n": 24,
|
| 1772 |
+
"errors": 1,
|
| 1773 |
+
"error_rate": 0.041666666666666664
|
| 1774 |
+
}
|
| 1775 |
+
},
|
| 1776 |
+
"selective": {
|
| 1777 |
+
"0.5": {
|
| 1778 |
+
"coverage": 0.5,
|
| 1779 |
+
"accuracy": 0.95,
|
| 1780 |
+
"confidence_cutoff": 0.9568438066580538
|
| 1781 |
+
},
|
| 1782 |
+
"0.8": {
|
| 1783 |
+
"coverage": 0.8,
|
| 1784 |
+
"accuracy": 0.875,
|
| 1785 |
+
"confidence_cutoff": 0.7845341797034198
|
| 1786 |
+
}
|
| 1787 |
+
}
|
| 1788 |
+
},
|
| 1789 |
+
"sciq": {
|
| 1790 |
+
"n": 80,
|
| 1791 |
+
"nll": 0.23243275250012832,
|
| 1792 |
+
"acc": 0.9,
|
| 1793 |
+
"ece": 0.06455731140104856,
|
| 1794 |
+
"brier": 0.12618100275031707,
|
| 1795 |
+
"mean_conf": 0.937110593339877,
|
| 1796 |
+
"confident_error_rate": 0.025,
|
| 1797 |
+
"coverage_at_0_9": 0.825,
|
| 1798 |
+
"accuracy_at_0_9": 0.9696969696969697,
|
| 1799 |
+
"coverage_at_5pct_error": 0.925,
|
| 1800 |
+
"coverage_at_1pct_error": 0.7375,
|
| 1801 |
+
"confidence_bias": 0.037110593339876985,
|
| 1802 |
+
"top_bins": {
|
| 1803 |
+
"0.9": {
|
| 1804 |
+
"n": 66,
|
| 1805 |
+
"errors": 2,
|
| 1806 |
+
"error_rate": 0.030303030303030304
|
| 1807 |
+
},
|
| 1808 |
+
"0.95": {
|
| 1809 |
+
"n": 64,
|
| 1810 |
+
"errors": 2,
|
| 1811 |
+
"error_rate": 0.03125
|
| 1812 |
+
},
|
| 1813 |
+
"0.99": {
|
| 1814 |
+
"n": 57,
|
| 1815 |
+
"errors": 0,
|
| 1816 |
+
"error_rate": 0.0
|
| 1817 |
+
}
|
| 1818 |
+
},
|
| 1819 |
+
"selective": {
|
| 1820 |
+
"0.5": {
|
| 1821 |
+
"coverage": 0.5,
|
| 1822 |
+
"accuracy": 1.0,
|
| 1823 |
+
"confidence_cutoff": 0.9997778769905008
|
| 1824 |
+
},
|
| 1825 |
+
"0.8": {
|
| 1826 |
+
"coverage": 0.8,
|
| 1827 |
+
"accuracy": 0.96875,
|
| 1828 |
+
"confidence_cutoff": 0.962388575525204
|
| 1829 |
+
}
|
| 1830 |
+
}
|
| 1831 |
+
},
|
| 1832 |
+
"tweet_offensive": {
|
| 1833 |
+
"n": 80,
|
| 1834 |
+
"nll": 0.8071230061063959,
|
| 1835 |
+
"acc": 0.625,
|
| 1836 |
+
"ece": 0.1989925233525855,
|
| 1837 |
+
"brier": 0.48269103629629406,
|
| 1838 |
+
"mean_conf": 0.8239925233525855,
|
| 1839 |
+
"confident_error_rate": 0.1,
|
| 1840 |
+
"coverage_at_0_9": 0.375,
|
| 1841 |
+
"accuracy_at_0_9": 0.7333333333333333,
|
| 1842 |
+
"coverage_at_5pct_error": 0.0375,
|
| 1843 |
+
"coverage_at_1pct_error": 0.0375,
|
| 1844 |
+
"confidence_bias": 0.19899252335258555,
|
| 1845 |
+
"top_bins": {
|
| 1846 |
+
"0.9": {
|
| 1847 |
+
"n": 30,
|
| 1848 |
+
"errors": 8,
|
| 1849 |
+
"error_rate": 0.26666666666666666
|
| 1850 |
+
},
|
| 1851 |
+
"0.95": {
|
| 1852 |
+
"n": 26,
|
| 1853 |
+
"errors": 6,
|
| 1854 |
+
"error_rate": 0.23076923076923078
|
| 1855 |
+
},
|
| 1856 |
+
"0.99": {
|
| 1857 |
+
"n": 10,
|
| 1858 |
+
"errors": 2,
|
| 1859 |
+
"error_rate": 0.2
|
| 1860 |
+
}
|
| 1861 |
+
},
|
| 1862 |
+
"selective": {
|
| 1863 |
+
"0.5": {
|
| 1864 |
+
"coverage": 0.5,
|
| 1865 |
+
"accuracy": 0.75,
|
| 1866 |
+
"confidence_cutoff": 0.8628702374009682
|
| 1867 |
+
},
|
| 1868 |
+
"0.8": {
|
| 1869 |
+
"coverage": 0.8,
|
| 1870 |
+
"accuracy": 0.734375,
|
| 1871 |
+
"confidence_cutoff": 0.6955991387367249
|
| 1872 |
+
}
|
| 1873 |
+
}
|
| 1874 |
+
}
|
| 1875 |
+
},
|
| 1876 |
+
"variants": {
|
| 1877 |
+
"clean": {
|
| 1878 |
+
"n": 656,
|
| 1879 |
+
"nll": 0.9570682750687798,
|
| 1880 |
+
"acc": 0.6432926829268293,
|
| 1881 |
+
"ece": 0.18401217986343424,
|
| 1882 |
+
"brier": 0.5125584983305406,
|
| 1883 |
+
"mean_conf": 0.8237780936358884,
|
| 1884 |
+
"confident_error_rate": 0.09603658536585366,
|
| 1885 |
+
"coverage_at_0_9": 0.46189024390243905,
|
| 1886 |
+
"accuracy_at_0_9": 0.7920792079207921,
|
| 1887 |
+
"coverage_at_5pct_error": 0.16615853658536586,
|
| 1888 |
+
"coverage_at_1pct_error": 0.08841463414634146,
|
| 1889 |
+
"confidence_bias": 0.1804854107090591,
|
| 1890 |
+
"top_bins": {
|
| 1891 |
+
"0.9": {
|
| 1892 |
+
"n": 303,
|
| 1893 |
+
"errors": 63,
|
| 1894 |
+
"error_rate": 0.2079207920792079
|
| 1895 |
+
},
|
| 1896 |
+
"0.95": {
|
| 1897 |
+
"n": 235,
|
| 1898 |
+
"errors": 31,
|
| 1899 |
+
"error_rate": 0.13191489361702127
|
| 1900 |
+
},
|
| 1901 |
+
"0.99": {
|
| 1902 |
+
"n": 145,
|
| 1903 |
+
"errors": 14,
|
| 1904 |
+
"error_rate": 0.09655172413793103
|
| 1905 |
+
}
|
| 1906 |
+
},
|
| 1907 |
+
"selective": {
|
| 1908 |
+
"0.5": {
|
| 1909 |
+
"coverage": 0.5,
|
| 1910 |
+
"accuracy": 0.7835365853658537,
|
| 1911 |
+
"confidence_cutoff": 0.8847859831447148
|
| 1912 |
+
},
|
| 1913 |
+
"0.8": {
|
| 1914 |
+
"coverage": 0.8003048780487805,
|
| 1915 |
+
"accuracy": 0.700952380952381,
|
| 1916 |
+
"confidence_cutoff": 0.6439839389314616
|
| 1917 |
+
}
|
| 1918 |
+
},
|
| 1919 |
+
"score_mae": 0.7107663444740075,
|
| 1920 |
+
"ranked_probability_score": 0.33044152610202326
|
| 1921 |
+
},
|
| 1922 |
+
"none_absent": {
|
| 1923 |
+
"n": 36,
|
| 1924 |
+
"nll": 0.31319671897204826,
|
| 1925 |
+
"acc": 0.9166666666666666,
|
| 1926 |
+
"ece": 0.09895040916410316,
|
| 1927 |
+
"brier": 0.17446194758126574,
|
| 1928 |
+
"mean_conf": 0.8228531419244747,
|
| 1929 |
+
"confident_error_rate": 0.0,
|
| 1930 |
+
"coverage_at_0_9": 0.4444444444444444,
|
| 1931 |
+
"accuracy_at_0_9": 1.0,
|
| 1932 |
+
"coverage_at_5pct_error": 0.8055555555555556,
|
| 1933 |
+
"coverage_at_1pct_error": 0.4722222222222222,
|
| 1934 |
+
"confidence_bias": -0.09381352474219196,
|
| 1935 |
+
"top_bins": {
|
| 1936 |
+
"0.9": {
|
| 1937 |
+
"n": 16,
|
| 1938 |
+
"errors": 0,
|
| 1939 |
+
"error_rate": 0.0
|
| 1940 |
+
},
|
| 1941 |
+
"0.95": {
|
| 1942 |
+
"n": 15,
|
| 1943 |
+
"errors": 0,
|
| 1944 |
+
"error_rate": 0.0
|
| 1945 |
+
},
|
| 1946 |
+
"0.99": {
|
| 1947 |
+
"n": 8,
|
| 1948 |
+
"errors": 0,
|
| 1949 |
+
"error_rate": 0.0
|
| 1950 |
+
}
|
| 1951 |
+
},
|
| 1952 |
+
"selective": {
|
| 1953 |
+
"0.5": {
|
| 1954 |
+
"coverage": 0.5,
|
| 1955 |
+
"accuracy": 0.9444444444444444,
|
| 1956 |
+
"confidence_cutoff": 0.8805488017736323
|
| 1957 |
+
},
|
| 1958 |
+
"0.8": {
|
| 1959 |
+
"coverage": 0.8055555555555556,
|
| 1960 |
+
"accuracy": 0.9655172413793104,
|
| 1961 |
+
"confidence_cutoff": 0.6501325456321856
|
| 1962 |
+
}
|
| 1963 |
+
}
|
| 1964 |
+
},
|
| 1965 |
+
"none_present": {
|
| 1966 |
+
"n": 36,
|
| 1967 |
+
"nll": 1.5006623637089826,
|
| 1968 |
+
"acc": 0.5277777777777778,
|
| 1969 |
+
"ece": 0.2627245301256418,
|
| 1970 |
+
"brier": 0.6897864093208933,
|
| 1971 |
+
"mean_conf": 0.7905023079034196,
|
| 1972 |
+
"confident_error_rate": 0.1111111111111111,
|
| 1973 |
+
"coverage_at_0_9": 0.4444444444444444,
|
| 1974 |
+
"accuracy_at_0_9": 0.75,
|
| 1975 |
+
"coverage_at_5pct_error": 0.16666666666666666,
|
| 1976 |
+
"coverage_at_1pct_error": 0.16666666666666666,
|
| 1977 |
+
"confidence_bias": 0.2627245301256418,
|
| 1978 |
+
"top_bins": {
|
| 1979 |
+
"0.9": {
|
| 1980 |
+
"n": 16,
|
| 1981 |
+
"errors": 4,
|
| 1982 |
+
"error_rate": 0.25
|
| 1983 |
+
},
|
| 1984 |
+
"0.95": {
|
| 1985 |
+
"n": 13,
|
| 1986 |
+
"errors": 2,
|
| 1987 |
+
"error_rate": 0.15384615384615385
|
| 1988 |
+
},
|
| 1989 |
+
"0.99": {
|
| 1990 |
+
"n": 5,
|
| 1991 |
+
"errors": 0,
|
| 1992 |
+
"error_rate": 0.0
|
| 1993 |
+
}
|
| 1994 |
+
},
|
| 1995 |
+
"selective": {
|
| 1996 |
+
"0.5": {
|
| 1997 |
+
"coverage": 0.5,
|
| 1998 |
+
"accuracy": 0.7777777777777778,
|
| 1999 |
+
"confidence_cutoff": 0.8260558825221007
|
| 2000 |
+
},
|
| 2001 |
+
"0.8": {
|
| 2002 |
+
"coverage": 0.8055555555555556,
|
| 2003 |
+
"accuracy": 0.6206896551724138,
|
| 2004 |
+
"confidence_cutoff": 0.5945354569592187
|
| 2005 |
+
}
|
| 2006 |
+
}
|
| 2007 |
+
},
|
| 2008 |
+
"permuted": {
|
| 2009 |
+
"n": 36,
|
| 2010 |
+
"nll": 0.685816309604459,
|
| 2011 |
+
"acc": 0.6666666666666666,
|
| 2012 |
+
"ece": 0.1556636851178309,
|
| 2013 |
+
"brier": 0.38401682117681707,
|
| 2014 |
+
"mean_conf": 0.8003654357284707,
|
| 2015 |
+
"confident_error_rate": 0.0,
|
| 2016 |
+
"coverage_at_0_9": 0.5277777777777778,
|
| 2017 |
+
"accuracy_at_0_9": 1.0,
|
| 2018 |
+
"coverage_at_5pct_error": 0.6111111111111112,
|
| 2019 |
+
"coverage_at_1pct_error": 0.5833333333333334,
|
| 2020 |
+
"confidence_bias": 0.1336987690618041,
|
| 2021 |
+
"top_bins": {
|
| 2022 |
+
"0.9": {
|
| 2023 |
+
"n": 19,
|
| 2024 |
+
"errors": 0,
|
| 2025 |
+
"error_rate": 0.0
|
| 2026 |
+
},
|
| 2027 |
+
"0.95": {
|
| 2028 |
+
"n": 18,
|
| 2029 |
+
"errors": 0,
|
| 2030 |
+
"error_rate": 0.0
|
| 2031 |
+
},
|
| 2032 |
+
"0.99": {
|
| 2033 |
+
"n": 13,
|
| 2034 |
+
"errors": 0,
|
| 2035 |
+
"error_rate": 0.0
|
| 2036 |
+
}
|
| 2037 |
+
},
|
| 2038 |
+
"selective": {
|
| 2039 |
+
"0.5": {
|
| 2040 |
+
"coverage": 0.5,
|
| 2041 |
+
"accuracy": 1.0,
|
| 2042 |
+
"confidence_cutoff": 0.9693646160685808
|
| 2043 |
+
},
|
| 2044 |
+
"0.8": {
|
| 2045 |
+
"coverage": 0.8055555555555556,
|
| 2046 |
+
"accuracy": 0.7931034482758621,
|
| 2047 |
+
"confidence_cutoff": 0.5474200218128784
|
| 2048 |
+
}
|
| 2049 |
+
}
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"heldout_tasks": {
|
| 2053 |
+
"composition_held_and_or": {
|
| 2054 |
+
"n": 32,
|
| 2055 |
+
"nll": 0.9136906300332568,
|
| 2056 |
+
"acc": 0.65625,
|
| 2057 |
+
"ece": 0.24657832195009244,
|
| 2058 |
+
"brier": 0.5361075837376617,
|
| 2059 |
+
"mean_conf": 0.9028283219500923,
|
| 2060 |
+
"confident_error_rate": 0.21875,
|
| 2061 |
+
"coverage_at_0_9": 0.8125,
|
| 2062 |
+
"accuracy_at_0_9": 0.7307692307692307,
|
| 2063 |
+
"coverage_at_5pct_error": 0.125,
|
| 2064 |
+
"coverage_at_1pct_error": 0.125,
|
| 2065 |
+
"confidence_bias": 0.24657832195009233,
|
| 2066 |
+
"top_bins": {
|
| 2067 |
+
"0.9": {
|
| 2068 |
+
"n": 26,
|
| 2069 |
+
"errors": 7,
|
| 2070 |
+
"error_rate": 0.2692307692307692
|
| 2071 |
+
},
|
| 2072 |
+
"0.95": {
|
| 2073 |
+
"n": 19,
|
| 2074 |
+
"errors": 3,
|
| 2075 |
+
"error_rate": 0.15789473684210525
|
| 2076 |
+
},
|
| 2077 |
+
"0.99": {
|
| 2078 |
+
"n": 3,
|
| 2079 |
+
"errors": 0,
|
| 2080 |
+
"error_rate": 0.0
|
| 2081 |
+
}
|
| 2082 |
+
},
|
| 2083 |
+
"selective": {
|
| 2084 |
+
"0.5": {
|
| 2085 |
+
"coverage": 0.5,
|
| 2086 |
+
"accuracy": 0.8125,
|
| 2087 |
+
"confidence_cutoff": 0.9686380624771118
|
| 2088 |
+
},
|
| 2089 |
+
"0.8": {
|
| 2090 |
+
"coverage": 0.8125,
|
| 2091 |
+
"accuracy": 0.7307692307692307,
|
| 2092 |
+
"confidence_cutoff": 0.9060071774274645
|
| 2093 |
+
}
|
| 2094 |
+
}
|
| 2095 |
+
},
|
| 2096 |
+
"composition_held_conditional": {
|
| 2097 |
+
"n": 32,
|
| 2098 |
+
"nll": 0.6448629311463261,
|
| 2099 |
+
"acc": 0.71875,
|
| 2100 |
+
"ece": 0.10729094246902517,
|
| 2101 |
+
"brier": 0.4221857657236401,
|
| 2102 |
+
"mean_conf": 0.8045070165534562,
|
| 2103 |
+
"confident_error_rate": 0.03125,
|
| 2104 |
+
"coverage_at_0_9": 0.125,
|
| 2105 |
+
"accuracy_at_0_9": 0.75,
|
| 2106 |
+
"coverage_at_5pct_error": 0.03125,
|
| 2107 |
+
"coverage_at_1pct_error": 0.03125,
|
| 2108 |
+
"confidence_bias": 0.08575701655345624,
|
| 2109 |
+
"top_bins": {
|
| 2110 |
+
"0.9": {
|
| 2111 |
+
"n": 4,
|
| 2112 |
+
"errors": 1,
|
| 2113 |
+
"error_rate": 0.25
|
| 2114 |
+
},
|
| 2115 |
+
"0.95": {
|
| 2116 |
+
"n": 2,
|
| 2117 |
+
"errors": 1,
|
| 2118 |
+
"error_rate": 0.5
|
| 2119 |
+
},
|
| 2120 |
+
"0.99": {
|
| 2121 |
+
"n": 0,
|
| 2122 |
+
"errors": 0,
|
| 2123 |
+
"error_rate": null
|
| 2124 |
+
}
|
| 2125 |
+
},
|
| 2126 |
+
"selective": {
|
| 2127 |
+
"0.5": {
|
| 2128 |
+
"coverage": 0.5,
|
| 2129 |
+
"accuracy": 0.8125,
|
| 2130 |
+
"confidence_cutoff": 0.855546150936301
|
| 2131 |
+
},
|
| 2132 |
+
"0.8": {
|
| 2133 |
+
"coverage": 0.8125,
|
| 2134 |
+
"accuracy": 0.7692307692307693,
|
| 2135 |
+
"confidence_cutoff": 0.654670575539504
|
| 2136 |
+
}
|
| 2137 |
+
}
|
| 2138 |
+
},
|
| 2139 |
+
"composition_held_or_not": {
|
| 2140 |
+
"n": 32,
|
| 2141 |
+
"nll": 0.7429562768560309,
|
| 2142 |
+
"acc": 0.625,
|
| 2143 |
+
"ece": 0.2541212013040856,
|
| 2144 |
+
"brier": 0.5184103008702212,
|
| 2145 |
+
"mean_conf": 0.7345879801936439,
|
| 2146 |
+
"confident_error_rate": 0.03125,
|
| 2147 |
+
"coverage_at_0_9": 0.21875,
|
| 2148 |
+
"accuracy_at_0_9": 0.8571428571428571,
|
| 2149 |
+
"coverage_at_5pct_error": 0.0,
|
| 2150 |
+
"coverage_at_1pct_error": 0.0,
|
| 2151 |
+
"confidence_bias": 0.10958798019364391,
|
| 2152 |
+
"top_bins": {
|
| 2153 |
+
"0.9": {
|
| 2154 |
+
"n": 7,
|
| 2155 |
+
"errors": 1,
|
| 2156 |
+
"error_rate": 0.14285714285714285
|
| 2157 |
+
},
|
| 2158 |
+
"0.95": {
|
| 2159 |
+
"n": 4,
|
| 2160 |
+
"errors": 1,
|
| 2161 |
+
"error_rate": 0.25
|
| 2162 |
+
},
|
| 2163 |
+
"0.99": {
|
| 2164 |
+
"n": 0,
|
| 2165 |
+
"errors": 0,
|
| 2166 |
+
"error_rate": null
|
| 2167 |
+
}
|
| 2168 |
+
},
|
| 2169 |
+
"selective": {
|
| 2170 |
+
"0.5": {
|
| 2171 |
+
"coverage": 0.53125,
|
| 2172 |
+
"accuracy": 0.6470588235294118,
|
| 2173 |
+
"confidence_cutoff": 0.7171741937748848
|
| 2174 |
+
},
|
| 2175 |
+
"0.8": {
|
| 2176 |
+
"coverage": 0.84375,
|
| 2177 |
+
"accuracy": 0.5925925925925926,
|
| 2178 |
+
"confidence_cutoff": 0.5604099631309509
|
| 2179 |
+
}
|
| 2180 |
+
}
|
| 2181 |
+
},
|
| 2182 |
+
"contrastive_authorization": {
|
| 2183 |
+
"n": 40,
|
| 2184 |
+
"nll": 0.19467410615873026,
|
| 2185 |
+
"acc": 0.9,
|
| 2186 |
+
"ece": 0.03820846875417625,
|
| 2187 |
+
"brier": 0.12726178130600177,
|
| 2188 |
+
"mean_conf": 0.9201264847929028,
|
| 2189 |
+
"confident_error_rate": 0.025,
|
| 2190 |
+
"coverage_at_0_9": 0.75,
|
| 2191 |
+
"accuracy_at_0_9": 0.9666666666666667,
|
| 2192 |
+
"coverage_at_5pct_error": 0.85,
|
| 2193 |
+
"coverage_at_1pct_error": 0.725,
|
| 2194 |
+
"confidence_bias": 0.0201264847929028,
|
| 2195 |
+
"top_bins": {
|
| 2196 |
+
"0.9": {
|
| 2197 |
+
"n": 30,
|
| 2198 |
+
"errors": 1,
|
| 2199 |
+
"error_rate": 0.03333333333333333
|
| 2200 |
+
},
|
| 2201 |
+
"0.95": {
|
| 2202 |
+
"n": 29,
|
| 2203 |
+
"errors": 0,
|
| 2204 |
+
"error_rate": 0.0
|
| 2205 |
+
},
|
| 2206 |
+
"0.99": {
|
| 2207 |
+
"n": 20,
|
| 2208 |
+
"errors": 0,
|
| 2209 |
+
"error_rate": 0.0
|
| 2210 |
+
}
|
| 2211 |
+
},
|
| 2212 |
+
"selective": {
|
| 2213 |
+
"0.5": {
|
| 2214 |
+
"coverage": 0.5,
|
| 2215 |
+
"accuracy": 1.0,
|
| 2216 |
+
"confidence_cutoff": 0.9971347548104887
|
| 2217 |
+
},
|
| 2218 |
+
"0.8": {
|
| 2219 |
+
"coverage": 0.8,
|
| 2220 |
+
"accuracy": 0.96875,
|
| 2221 |
+
"confidence_cutoff": 0.8816031611682398
|
| 2222 |
+
}
|
| 2223 |
+
}
|
| 2224 |
+
},
|
| 2225 |
+
"contrastive_deadline": {
|
| 2226 |
+
"n": 40,
|
| 2227 |
+
"nll": 2.785418715865327,
|
| 2228 |
+
"acc": 0.275,
|
| 2229 |
+
"ece": 0.6633694597358357,
|
| 2230 |
+
"brier": 1.2868469074566389,
|
| 2231 |
+
"mean_conf": 0.9383694597358356,
|
| 2232 |
+
"confident_error_rate": 0.6,
|
| 2233 |
+
"coverage_at_0_9": 0.85,
|
| 2234 |
+
"accuracy_at_0_9": 0.29411764705882354,
|
| 2235 |
+
"coverage_at_5pct_error": 0.025,
|
| 2236 |
+
"coverage_at_1pct_error": 0.025,
|
| 2237 |
+
"confidence_bias": 0.6633694597358356,
|
| 2238 |
+
"top_bins": {
|
| 2239 |
+
"0.9": {
|
| 2240 |
+
"n": 34,
|
| 2241 |
+
"errors": 24,
|
| 2242 |
+
"error_rate": 0.7058823529411765
|
| 2243 |
+
},
|
| 2244 |
+
"0.95": {
|
| 2245 |
+
"n": 17,
|
| 2246 |
+
"errors": 9,
|
| 2247 |
+
"error_rate": 0.5294117647058824
|
| 2248 |
+
},
|
| 2249 |
+
"0.99": {
|
| 2250 |
+
"n": 13,
|
| 2251 |
+
"errors": 7,
|
| 2252 |
+
"error_rate": 0.5384615384615384
|
| 2253 |
+
}
|
| 2254 |
+
},
|
| 2255 |
+
"selective": {
|
| 2256 |
+
"0.5": {
|
| 2257 |
+
"coverage": 0.5,
|
| 2258 |
+
"accuracy": 0.45,
|
| 2259 |
+
"confidence_cutoff": 0.9361307481507846
|
| 2260 |
+
},
|
| 2261 |
+
"0.8": {
|
| 2262 |
+
"coverage": 0.8,
|
| 2263 |
+
"accuracy": 0.3125,
|
| 2264 |
+
"confidence_cutoff": 0.9177724490540244
|
| 2265 |
+
}
|
| 2266 |
+
},
|
| 2267 |
+
"score_mae": 0.7107663444740075,
|
| 2268 |
+
"ranked_probability_score": 0.33044152610202326
|
| 2269 |
+
},
|
| 2270 |
+
"emotion": {
|
| 2271 |
+
"n": 80,
|
| 2272 |
+
"nll": 1.653093556050728,
|
| 2273 |
+
"acc": 0.5375,
|
| 2274 |
+
"ece": 0.22901336770397754,
|
| 2275 |
+
"brier": 0.6605442054462966,
|
| 2276 |
+
"mean_conf": 0.7296495068187532,
|
| 2277 |
+
"confident_error_rate": 0.0625,
|
| 2278 |
+
"coverage_at_0_9": 0.2625,
|
| 2279 |
+
"accuracy_at_0_9": 0.7619047619047619,
|
| 2280 |
+
"coverage_at_5pct_error": 0.0,
|
| 2281 |
+
"coverage_at_1pct_error": 0.0,
|
| 2282 |
+
"confidence_bias": 0.1921495068187532,
|
| 2283 |
+
"top_bins": {
|
| 2284 |
+
"0.9": {
|
| 2285 |
+
"n": 21,
|
| 2286 |
+
"errors": 5,
|
| 2287 |
+
"error_rate": 0.23809523809523808
|
| 2288 |
+
},
|
| 2289 |
+
"0.95": {
|
| 2290 |
+
"n": 16,
|
| 2291 |
+
"errors": 4,
|
| 2292 |
+
"error_rate": 0.25
|
| 2293 |
+
},
|
| 2294 |
+
"0.99": {
|
| 2295 |
+
"n": 7,
|
| 2296 |
+
"errors": 3,
|
| 2297 |
+
"error_rate": 0.42857142857142855
|
| 2298 |
+
}
|
| 2299 |
+
},
|
| 2300 |
+
"selective": {
|
| 2301 |
+
"0.5": {
|
| 2302 |
+
"coverage": 0.5,
|
| 2303 |
+
"accuracy": 0.65,
|
| 2304 |
+
"confidence_cutoff": 0.766856165763948
|
| 2305 |
+
},
|
| 2306 |
+
"0.8": {
|
| 2307 |
+
"coverage": 0.8,
|
| 2308 |
+
"accuracy": 0.5625,
|
| 2309 |
+
"confidence_cutoff": 0.5523026767607064
|
| 2310 |
+
}
|
| 2311 |
+
}
|
| 2312 |
+
},
|
| 2313 |
+
"mmlu": {
|
| 2314 |
+
"n": 80,
|
| 2315 |
+
"nll": 1.4114379018186007,
|
| 2316 |
+
"acc": 0.4125,
|
| 2317 |
+
"ece": 0.24866880218243045,
|
| 2318 |
+
"brier": 0.7462173145072892,
|
| 2319 |
+
"mean_conf": 0.6611688021824303,
|
| 2320 |
+
"confident_error_rate": 0.0625,
|
| 2321 |
+
"coverage_at_0_9": 0.25,
|
| 2322 |
+
"accuracy_at_0_9": 0.75,
|
| 2323 |
+
"coverage_at_5pct_error": 0.125,
|
| 2324 |
+
"coverage_at_1pct_error": 0.125,
|
| 2325 |
+
"confidence_bias": 0.24866880218243037,
|
| 2326 |
+
"top_bins": {
|
| 2327 |
+
"0.9": {
|
| 2328 |
+
"n": 20,
|
| 2329 |
+
"errors": 5,
|
| 2330 |
+
"error_rate": 0.25
|
| 2331 |
+
},
|
| 2332 |
+
"0.95": {
|
| 2333 |
+
"n": 15,
|
| 2334 |
+
"errors": 2,
|
| 2335 |
+
"error_rate": 0.13333333333333333
|
| 2336 |
+
},
|
| 2337 |
+
"0.99": {
|
| 2338 |
+
"n": 11,
|
| 2339 |
+
"errors": 1,
|
| 2340 |
+
"error_rate": 0.09090909090909091
|
| 2341 |
+
}
|
| 2342 |
+
},
|
| 2343 |
+
"selective": {
|
| 2344 |
+
"0.5": {
|
| 2345 |
+
"coverage": 0.5,
|
| 2346 |
+
"accuracy": 0.525,
|
| 2347 |
+
"confidence_cutoff": 0.6131941239996213
|
| 2348 |
+
},
|
| 2349 |
+
"0.8": {
|
| 2350 |
+
"coverage": 0.8,
|
| 2351 |
+
"accuracy": 0.421875,
|
| 2352 |
+
"confidence_cutoff": 0.4523720938182154
|
| 2353 |
+
}
|
| 2354 |
+
}
|
| 2355 |
+
},
|
| 2356 |
+
"paws": {
|
| 2357 |
+
"n": 80,
|
| 2358 |
+
"nll": 0.8953421021329806,
|
| 2359 |
+
"acc": 0.5875,
|
| 2360 |
+
"ece": 0.2541297593433282,
|
| 2361 |
+
"brier": 0.6186855308160963,
|
| 2362 |
+
"mean_conf": 0.7995476792756492,
|
| 2363 |
+
"confident_error_rate": 0.0625,
|
| 2364 |
+
"coverage_at_0_9": 0.1375,
|
| 2365 |
+
"accuracy_at_0_9": 0.5454545454545454,
|
| 2366 |
+
"coverage_at_5pct_error": 0.0,
|
| 2367 |
+
"coverage_at_1pct_error": 0.0,
|
| 2368 |
+
"confidence_bias": 0.21204767927564916,
|
| 2369 |
+
"top_bins": {
|
| 2370 |
+
"0.9": {
|
| 2371 |
+
"n": 11,
|
| 2372 |
+
"errors": 5,
|
| 2373 |
+
"error_rate": 0.45454545454545453
|
| 2374 |
+
},
|
| 2375 |
+
"0.95": {
|
| 2376 |
+
"n": 3,
|
| 2377 |
+
"errors": 1,
|
| 2378 |
+
"error_rate": 0.3333333333333333
|
| 2379 |
+
},
|
| 2380 |
+
"0.99": {
|
| 2381 |
+
"n": 0,
|
| 2382 |
+
"errors": 0,
|
| 2383 |
+
"error_rate": null
|
| 2384 |
+
}
|
| 2385 |
+
},
|
| 2386 |
+
"selective": {
|
| 2387 |
+
"0.5": {
|
| 2388 |
+
"coverage": 0.5,
|
| 2389 |
+
"accuracy": 0.55,
|
| 2390 |
+
"confidence_cutoff": 0.8083969234168988
|
| 2391 |
+
},
|
| 2392 |
+
"0.8": {
|
| 2393 |
+
"coverage": 0.8,
|
| 2394 |
+
"accuracy": 0.578125,
|
| 2395 |
+
"confidence_cutoff": 0.7218610644340515
|
| 2396 |
+
}
|
| 2397 |
+
}
|
| 2398 |
+
},
|
| 2399 |
+
"qnli": {
|
| 2400 |
+
"n": 80,
|
| 2401 |
+
"nll": 0.4378801907288863,
|
| 2402 |
+
"acc": 0.825,
|
| 2403 |
+
"ece": 0.07249396310174361,
|
| 2404 |
+
"brier": 0.27092479198021,
|
| 2405 |
+
"mean_conf": 0.8974939631017437,
|
| 2406 |
+
"confident_error_rate": 0.05,
|
| 2407 |
+
"coverage_at_0_9": 0.675,
|
| 2408 |
+
"accuracy_at_0_9": 0.9259259259259259,
|
| 2409 |
+
"coverage_at_5pct_error": 0.55,
|
| 2410 |
+
"coverage_at_1pct_error": 0.2875,
|
| 2411 |
+
"confidence_bias": 0.07249396310174372,
|
| 2412 |
+
"top_bins": {
|
| 2413 |
+
"0.9": {
|
| 2414 |
+
"n": 54,
|
| 2415 |
+
"errors": 4,
|
| 2416 |
+
"error_rate": 0.07407407407407407
|
| 2417 |
+
},
|
| 2418 |
+
"0.95": {
|
| 2419 |
+
"n": 40,
|
| 2420 |
+
"errors": 2,
|
| 2421 |
+
"error_rate": 0.05
|
| 2422 |
+
},
|
| 2423 |
+
"0.99": {
|
| 2424 |
+
"n": 24,
|
| 2425 |
+
"errors": 1,
|
| 2426 |
+
"error_rate": 0.041666666666666664
|
| 2427 |
+
}
|
| 2428 |
+
},
|
| 2429 |
+
"selective": {
|
| 2430 |
+
"0.5": {
|
| 2431 |
+
"coverage": 0.5,
|
| 2432 |
+
"accuracy": 0.95,
|
| 2433 |
+
"confidence_cutoff": 0.9568438066580538
|
| 2434 |
+
},
|
| 2435 |
+
"0.8": {
|
| 2436 |
+
"coverage": 0.8,
|
| 2437 |
+
"accuracy": 0.875,
|
| 2438 |
+
"confidence_cutoff": 0.7845341797034198
|
| 2439 |
+
}
|
| 2440 |
+
}
|
| 2441 |
+
},
|
| 2442 |
+
"sciq": {
|
| 2443 |
+
"n": 80,
|
| 2444 |
+
"nll": 0.23243275250012832,
|
| 2445 |
+
"acc": 0.9,
|
| 2446 |
+
"ece": 0.06455731140104856,
|
| 2447 |
+
"brier": 0.12618100275031707,
|
| 2448 |
+
"mean_conf": 0.937110593339877,
|
| 2449 |
+
"confident_error_rate": 0.025,
|
| 2450 |
+
"coverage_at_0_9": 0.825,
|
| 2451 |
+
"accuracy_at_0_9": 0.9696969696969697,
|
| 2452 |
+
"coverage_at_5pct_error": 0.925,
|
| 2453 |
+
"coverage_at_1pct_error": 0.7375,
|
| 2454 |
+
"confidence_bias": 0.037110593339876985,
|
| 2455 |
+
"top_bins": {
|
| 2456 |
+
"0.9": {
|
| 2457 |
+
"n": 66,
|
| 2458 |
+
"errors": 2,
|
| 2459 |
+
"error_rate": 0.030303030303030304
|
| 2460 |
+
},
|
| 2461 |
+
"0.95": {
|
| 2462 |
+
"n": 64,
|
| 2463 |
+
"errors": 2,
|
| 2464 |
+
"error_rate": 0.03125
|
| 2465 |
+
},
|
| 2466 |
+
"0.99": {
|
| 2467 |
+
"n": 57,
|
| 2468 |
+
"errors": 0,
|
| 2469 |
+
"error_rate": 0.0
|
| 2470 |
+
}
|
| 2471 |
+
},
|
| 2472 |
+
"selective": {
|
| 2473 |
+
"0.5": {
|
| 2474 |
+
"coverage": 0.5,
|
| 2475 |
+
"accuracy": 1.0,
|
| 2476 |
+
"confidence_cutoff": 0.9997778769905008
|
| 2477 |
+
},
|
| 2478 |
+
"0.8": {
|
| 2479 |
+
"coverage": 0.8,
|
| 2480 |
+
"accuracy": 0.96875,
|
| 2481 |
+
"confidence_cutoff": 0.962388575525204
|
| 2482 |
+
}
|
| 2483 |
+
}
|
| 2484 |
+
},
|
| 2485 |
+
"tweet_offensive": {
|
| 2486 |
+
"n": 80,
|
| 2487 |
+
"nll": 0.8071230061063959,
|
| 2488 |
+
"acc": 0.625,
|
| 2489 |
+
"ece": 0.1989925233525855,
|
| 2490 |
+
"brier": 0.48269103629629406,
|
| 2491 |
+
"mean_conf": 0.8239925233525855,
|
| 2492 |
+
"confident_error_rate": 0.1,
|
| 2493 |
+
"coverage_at_0_9": 0.375,
|
| 2494 |
+
"accuracy_at_0_9": 0.7333333333333333,
|
| 2495 |
+
"coverage_at_5pct_error": 0.0375,
|
| 2496 |
+
"coverage_at_1pct_error": 0.0375,
|
| 2497 |
+
"confidence_bias": 0.19899252335258555,
|
| 2498 |
+
"top_bins": {
|
| 2499 |
+
"0.9": {
|
| 2500 |
+
"n": 30,
|
| 2501 |
+
"errors": 8,
|
| 2502 |
+
"error_rate": 0.26666666666666666
|
| 2503 |
+
},
|
| 2504 |
+
"0.95": {
|
| 2505 |
+
"n": 26,
|
| 2506 |
+
"errors": 6,
|
| 2507 |
+
"error_rate": 0.23076923076923078
|
| 2508 |
+
},
|
| 2509 |
+
"0.99": {
|
| 2510 |
+
"n": 10,
|
| 2511 |
+
"errors": 2,
|
| 2512 |
+
"error_rate": 0.2
|
| 2513 |
+
}
|
| 2514 |
+
},
|
| 2515 |
+
"selective": {
|
| 2516 |
+
"0.5": {
|
| 2517 |
+
"coverage": 0.5,
|
| 2518 |
+
"accuracy": 0.75,
|
| 2519 |
+
"confidence_cutoff": 0.8628702374009682
|
| 2520 |
+
},
|
| 2521 |
+
"0.8": {
|
| 2522 |
+
"coverage": 0.8,
|
| 2523 |
+
"accuracy": 0.734375,
|
| 2524 |
+
"confidence_cutoff": 0.6955991387367249
|
| 2525 |
+
}
|
| 2526 |
+
}
|
| 2527 |
+
}
|
| 2528 |
+
},
|
| 2529 |
+
"permutation": {
|
| 2530 |
+
"n": 36,
|
| 2531 |
+
"mean_max_delta": 0.06061120075565571,
|
| 2532 |
+
"flip_rate": 0.05555555555555555
|
| 2533 |
+
},
|
| 2534 |
+
"temperature": 2.1435469250725863,
|
| 2535 |
+
"calibrated_clean": {
|
| 2536 |
+
"n": 656,
|
| 2537 |
+
"nll": 0.7411897603541017,
|
| 2538 |
+
"acc": 0.6432926829268293,
|
| 2539 |
+
"ece": 0.059138082355748585,
|
| 2540 |
+
"brier": 0.4467323923140525,
|
| 2541 |
+
"mean_conf": 0.699976445273826,
|
| 2542 |
+
"confident_error_rate": 0.009146341463414634,
|
| 2543 |
+
"coverage_at_0_9": 0.18902439024390244,
|
| 2544 |
+
"accuracy_at_0_9": 0.9516129032258065,
|
| 2545 |
+
"coverage_at_5pct_error": 0.19054878048780488,
|
| 2546 |
+
"coverage_at_1pct_error": 0.13871951219512196,
|
| 2547 |
+
"confidence_bias": 0.05668376234699668,
|
| 2548 |
+
"top_bins": {
|
| 2549 |
+
"0.9": {
|
| 2550 |
+
"n": 124,
|
| 2551 |
+
"errors": 6,
|
| 2552 |
+
"error_rate": 0.04838709677419355
|
| 2553 |
+
},
|
| 2554 |
+
"0.95": {
|
| 2555 |
+
"n": 70,
|
| 2556 |
+
"errors": 0,
|
| 2557 |
+
"error_rate": 0.0
|
| 2558 |
+
},
|
| 2559 |
+
"0.99": {
|
| 2560 |
+
"n": 22,
|
| 2561 |
+
"errors": 0,
|
| 2562 |
+
"error_rate": 0.0
|
| 2563 |
+
}
|
| 2564 |
+
},
|
| 2565 |
+
"selective": {
|
| 2566 |
+
"0.5": {
|
| 2567 |
+
"coverage": 0.5,
|
| 2568 |
+
"accuracy": 0.8140243902439024,
|
| 2569 |
+
"confidence_cutoff": 0.7036366773870764
|
| 2570 |
+
},
|
| 2571 |
+
"0.8": {
|
| 2572 |
+
"coverage": 0.8003048780487805,
|
| 2573 |
+
"accuracy": 0.7028571428571428,
|
| 2574 |
+
"confidence_cutoff": 0.5319164258766103
|
| 2575 |
+
}
|
| 2576 |
+
},
|
| 2577 |
+
"score_mae": 0.7068636886582151,
|
| 2578 |
+
"ranked_probability_score": 0.2719657679685927
|
| 2579 |
+
},
|
| 2580 |
+
"metric_policy": {
|
| 2581 |
+
"nll_floor": 1e-09,
|
| 2582 |
+
"renormalize_returned_probabilities": true,
|
| 2583 |
+
"raw_sums_outside_1e_5": 0,
|
| 2584 |
+
"returned_zeros": 0
|
| 2585 |
+
},
|
| 2586 |
+
"coverage": {
|
| 2587 |
+
"requested_records": 764,
|
| 2588 |
+
"requested_questions": 764,
|
| 2589 |
+
"evaluated_records": 764,
|
| 2590 |
+
"evaluated_questions": 764,
|
| 2591 |
+
"rejected_records": 0,
|
| 2592 |
+
"truncated_records": 0
|
| 2593 |
+
},
|
| 2594 |
+
"latency_ms": {
|
| 2595 |
+
"median": 43.41722700007722,
|
| 2596 |
+
"p95": 50.79413265002586
|
| 2597 |
+
},
|
| 2598 |
+
"suite_sha256": "31677c2256b406222e7d94ffdc0a02a70ce05746b9efe307876024c4e77291d1"
|
| 2599 |
+
},
|
| 2600 |
+
"provenance": {
|
| 2601 |
+
"config": {
|
| 2602 |
+
"epochs": 2,
|
| 2603 |
+
"seed": 2,
|
| 2604 |
+
"lr": 0.0001,
|
| 2605 |
+
"lora": 16,
|
| 2606 |
+
"accum": 1,
|
| 2607 |
+
"batch": 8,
|
| 2608 |
+
"perm_kl": 0.0,
|
| 2609 |
+
"perm_frac": 0.3,
|
| 2610 |
+
"ord_w": 0.0,
|
| 2611 |
+
"p_none": 0.1,
|
| 2612 |
+
"p_none_distract": 0.12,
|
| 2613 |
+
"p_distract": 0.15,
|
| 2614 |
+
"p_none_pair": 0.25,
|
| 2615 |
+
"synthetic_repeat": 1,
|
| 2616 |
+
"public_frac": 1.0,
|
| 2617 |
+
"head_lr": 0.0,
|
| 2618 |
+
"weight_decay": 0.01,
|
| 2619 |
+
"anchor_w": 0.0,
|
| 2620 |
+
"base": "Qwen/Qwen3.5-0.8B-Base",
|
| 2621 |
+
"base_revision": "dc7cdfe2ee4154fa7e30f5b51ca41bfa40174e68",
|
| 2622 |
+
"dtype": "bf16"
|
| 2623 |
+
},
|
| 2624 |
+
"config_sha256": "1f902b8d0af3e9c1384f56f9f248c92d27f7029156a1a640389fb2acf5ea6b0a",
|
| 2625 |
+
"suite_sha256": "a8f50e481b7d90b97da049e0ff6a01cee2f1ed204aed61a8265af0edbb5514d2",
|
| 2626 |
+
"source_hashes": {
|
| 2627 |
+
"kev/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
|
| 2628 |
+
"kev/anchors.py": "089d8a5493502bb26f540eb1c5e681780ca0bb01276073d4e1733211f15d0e10",
|
| 2629 |
+
"kev/api.py": "cdb0602684d798ccd3fc2c86be622f2a8e7bcdeee64d07f95604c7d3fd4701ec",
|
| 2630 |
+
"kev/autoresearch.py": "0a8aa6b57c1c9ba93d25b2cf631b03aed2e686e374c1148002eec48765b7b1fc",
|
| 2631 |
+
"kev/benchmark.py": "5be816b27bc69c7244fd1b0ad619d4783b85a21b928212f306e731312f5146b2",
|
| 2632 |
+
"kev/compare.py": "bd0445f021de59e35c7bff9304e39dd2e1211e3877a453575594ae7b81b0ada4",
|
| 2633 |
+
"kev/composition.py": "f335ed17e18e0a544893db5e22b9a059e6ce1b2e14dbb863ac7d7bbf8f3e0536",
|
| 2634 |
+
"kev/contrastive.py": "cbb979aa5d40265ad0e64695f94b281d91751fa405811ddfa8212fede111edcf",
|
| 2635 |
+
"kev/data.py": "9729f8f497b02aca542915d6f1bea3ff55956629d7d9610370aea91ee66efd23",
|
| 2636 |
+
"kev/evaluate.py": "6f95c52f757ecffc887710e1b354f06c69c35336421d3e75eae84d251ddd120c",
|
| 2637 |
+
"kev/experiment.py": "c635394fe56c9aa11765f8bbf8f133dcf3e57cbe8f2bce4ebdc7b4e85fa536ff",
|
| 2638 |
+
"kev/jev.py": "e0213782359ba2f95adbf045ddaf0a008b08b4162bf6a9b66d4ce55fc91a51cb",
|
| 2639 |
+
"kev/model.py": "46d72ec55c9c35d28e8c43d820733e21bc5f3f261ff72a939fe029b88c4fcb1c",
|
| 2640 |
+
"kev/plot.py": "d689c7dd18cde7f9ea77cb4f55c50ff7da1880b21cb2ecf244348e45842a1382",
|
| 2641 |
+
"kev/publish.py": "c0b3efac3cfe93990d1846cfd306cf762a9d03e9e58380d13c2961a5ddae4619",
|
| 2642 |
+
"kev/serve.py": "570e995aa98b51dbbf867694276d29fc9b9f3f1e62f22bea0116ae51d6497003",
|
| 2643 |
+
"kev/study_v3.py": "9fc44d44dad09a4f1ee29a7bcb2eb3c7aa373d09186d0e9533666b69ec95c401",
|
| 2644 |
+
"kev/suite.py": "44858f9a99df086a47d1ae36141631fab6fb6a8293a9e1d0c6ad397ddcfaf94a",
|
| 2645 |
+
"kev/train.py": "e405978b6e1e7444e682a8869d1bd6c88c90bd9890836fcd84b2ab2aa0543817",
|
| 2646 |
+
"kev/transfer_v9.py": "588aa2ff3ec0823c2e31733bef9a3748b263849c966ef6a80ebd686539c605e9",
|
| 2647 |
+
"modal_app.py": "12c1b6c1d7f264da8644819bfd11b4baab9c541b1277fee120467514d4628591",
|
| 2648 |
+
"pyproject.toml": "52da5eea3efc6f2b1c0589acebad62e56a214294bb02c1a4218c93efd4af3182",
|
| 2649 |
+
"uv.lock": "18b3e5ea0f25d2e8546fab81f16cb965ae05c3289fffaaa1ce27d114adee47f3"
|
| 2650 |
+
},
|
| 2651 |
+
"git_commit": "5f78968927069eaacc3b2bdb688586989b3933ac",
|
| 2652 |
+
"platform": "Linux-4.19.0-gvisor-x86_64-with-glibc2.36",
|
| 2653 |
+
"torch": "2.8.0+cu128",
|
| 2654 |
+
"device": "cuda",
|
| 2655 |
+
"gpu": "NVIDIA H100 80GB HBM3",
|
| 2656 |
+
"legacy_checkpoint": false
|
| 2657 |
+
},
|
| 2658 |
+
"mechanism_checks": {
|
| 2659 |
+
"n": 8,
|
| 2660 |
+
"packed_max_delta": 0.0,
|
| 2661 |
+
"sibling_max_delta": 0.0007432699203491211,
|
| 2662 |
+
"tolerance": 0.001,
|
| 2663 |
+
"passed": true
|
| 2664 |
+
},
|
| 2665 |
+
"gates": {
|
| 2666 |
+
"passed": false,
|
| 2667 |
+
"checks": {
|
| 2668 |
+
"complete_coverage": true,
|
| 2669 |
+
"isolation_and_packing": true,
|
| 2670 |
+
"transfer_complete": true,
|
| 2671 |
+
"heldout_pairs_at_least_70pct": false,
|
| 2672 |
+
"transfer_confident_errors_below_10pct": true
|
| 2673 |
+
},
|
| 2674 |
+
"policy": "Research screening only: 1e-3 isolation; 5pp task regression; 70% heldout pair correctness; <=10% confident errors; no automatic release."
|
| 2675 |
+
},
|
| 2676 |
+
"wall_seconds": 1435.155213149,
|
| 2677 |
+
"promotable": false,
|
| 2678 |
+
"test_evaluated": false,
|
| 2679 |
+
"training_resources": {
|
| 2680 |
+
"wall_seconds": 1195.3522906303406,
|
| 2681 |
+
"records_seen": 30370,
|
| 2682 |
+
"requested_records": 25152,
|
| 2683 |
+
"truncated_records": 0,
|
| 2684 |
+
"rejected_records": 0,
|
| 2685 |
+
"optimizer_steps": 3144,
|
| 2686 |
+
"forward_tokens": 5832366,
|
| 2687 |
+
"peak_device_bytes": 56761799680,
|
| 2688 |
+
"device": "cuda",
|
| 2689 |
+
"dtype": "bf16",
|
| 2690 |
+
"batch": 8,
|
| 2691 |
+
"peak_rss_bytes": 10316271616
|
| 2692 |
+
}
|
| 2693 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
|
| 3 |
+
size 19989325
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|endoftext|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"local_files_only": false,
|
| 14 |
+
"model_max_length": 262144,
|
| 15 |
+
"model_specific_special_tokens": {
|
| 16 |
+
"audio_bos_token": "<|audio_start|>",
|
| 17 |
+
"audio_eos_token": "<|audio_end|>",
|
| 18 |
+
"audio_token": "<|audio_pad|>",
|
| 19 |
+
"image_token": "<|image_pad|>",
|
| 20 |
+
"video_token": "<|video_pad|>",
|
| 21 |
+
"vision_bos_token": "<|vision_start|>",
|
| 22 |
+
"vision_eos_token": "<|vision_end|>"
|
| 23 |
+
},
|
| 24 |
+
"pad_token": "<|endoftext|>",
|
| 25 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null,
|
| 29 |
+
"video_token": "<|video_pad|>",
|
| 30 |
+
"vision_bos_token": "<|vision_start|>",
|
| 31 |
+
"vision_eos_token": "<|vision_end|>"
|
| 32 |
+
}
|
train.log
ADDED
|
@@ -0,0 +1,319 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
device=cuda trainable params=11.3M
|
| 2 |
+
12576 training requests (holdout=[]), questions by type {'score': 3448, 'noul': 5224, 'choice': 6904}
|
| 3 |
+
[transformers] `causal_conv1d_fn` is falling back to its reference PyTorch implementation because `causal_conv1d` is not installed. This is correct but much slower; install `causal_conv1d` for the optimized kernel.
|
| 4 |
+
ep0 step 10/3144 loss 1.960 kl 0.000 anchor 0.000 1.843s/rec
|
| 5 |
+
ep0 step 20/3144 loss 1.867 kl 0.000 anchor 0.000 0.987s/rec
|
| 6 |
+
ep0 step 30/3144 loss 1.803 kl 0.000 anchor 0.000 0.660s/rec
|
| 7 |
+
ep0 step 40/3144 loss 1.955 kl 0.000 anchor 0.000 0.499s/rec
|
| 8 |
+
ep0 step 50/3144 loss 1.721 kl 0.000 anchor 0.000 0.409s/rec
|
| 9 |
+
ep0 step 60/3144 loss 1.448 kl 0.000 anchor 0.000 0.348s/rec
|
| 10 |
+
ep0 step 70/3144 loss 2.027 kl 0.000 anchor 0.000 0.304s/rec
|
| 11 |
+
ep0 step 80/3144 loss 1.461 kl 0.000 anchor 0.000 0.301s/rec
|
| 12 |
+
ep0 step 90/3144 loss 1.482 kl 0.000 anchor 0.000 0.268s/rec
|
| 13 |
+
ep0 step 100/3144 loss 1.319 kl 0.000 anchor 0.000 0.245s/rec
|
| 14 |
+
ep0 step 110/3144 loss 1.504 kl 0.000 anchor 0.000 0.224s/rec
|
| 15 |
+
ep0 step 120/3144 loss 1.287 kl 0.000 anchor 0.000 0.210s/rec
|
| 16 |
+
ep0 step 130/3144 loss 1.264 kl 0.000 anchor 0.000 0.197s/rec
|
| 17 |
+
ep0 step 140/3144 loss 1.123 kl 0.000 anchor 0.000 0.184s/rec
|
| 18 |
+
ep0 step 150/3144 loss 1.177 kl 0.000 anchor 0.000 0.173s/rec
|
| 19 |
+
ep0 step 160/3144 loss 1.214 kl 0.000 anchor 0.000 0.166s/rec
|
| 20 |
+
ep0 step 170/3144 loss 1.112 kl 0.000 anchor 0.000 0.158s/rec
|
| 21 |
+
ep0 step 180/3144 loss 0.867 kl 0.000 anchor 0.000 0.153s/rec
|
| 22 |
+
ep0 step 190/3144 loss 1.256 kl 0.000 anchor 0.000 0.148s/rec
|
| 23 |
+
ep0 step 200/3144 loss 1.032 kl 0.000 anchor 0.000 0.142s/rec
|
| 24 |
+
ep0 step 210/3144 loss 1.038 kl 0.000 anchor 0.000 0.137s/rec
|
| 25 |
+
ep0 step 220/3144 loss 1.062 kl 0.000 anchor 0.000 0.133s/rec
|
| 26 |
+
ep0 step 230/3144 loss 0.815 kl 0.000 anchor 0.000 0.128s/rec
|
| 27 |
+
ep0 step 240/3144 loss 0.844 kl 0.000 anchor 0.000 0.124s/rec
|
| 28 |
+
ep0 step 250/3144 loss 0.886 kl 0.000 anchor 0.000 0.121s/rec
|
| 29 |
+
ep0 step 260/3144 loss 0.806 kl 0.000 anchor 0.000 0.117s/rec
|
| 30 |
+
ep0 step 270/3144 loss 0.755 kl 0.000 anchor 0.000 0.114s/rec
|
| 31 |
+
ep0 step 280/3144 loss 0.961 kl 0.000 anchor 0.000 0.118s/rec
|
| 32 |
+
ep0 step 290/3144 loss 1.129 kl 0.000 anchor 0.000 0.115s/rec
|
| 33 |
+
ep0 step 300/3144 loss 0.962 kl 0.000 anchor 0.000 0.113s/rec
|
| 34 |
+
ep0 step 310/3144 loss 0.899 kl 0.000 anchor 0.000 0.110s/rec
|
| 35 |
+
ep0 step 320/3144 loss 0.744 kl 0.000 anchor 0.000 0.108s/rec
|
| 36 |
+
ep0 step 330/3144 loss 0.824 kl 0.000 anchor 0.000 0.105s/rec
|
| 37 |
+
ep0 step 340/3144 loss 0.752 kl 0.000 anchor 0.000 0.103s/rec
|
| 38 |
+
ep0 step 350/3144 loss 0.817 kl 0.000 anchor 0.000 0.101s/rec
|
| 39 |
+
ep0 step 360/3144 loss 0.547 kl 0.000 anchor 0.000 0.099s/rec
|
| 40 |
+
ep0 step 370/3144 loss 0.776 kl 0.000 anchor 0.000 0.097s/rec
|
| 41 |
+
ep0 step 380/3144 loss 0.734 kl 0.000 anchor 0.000 0.095s/rec
|
| 42 |
+
ep0 step 390/3144 loss 0.920 kl 0.000 anchor 0.000 0.094s/rec
|
| 43 |
+
ep0 step 400/3144 loss 1.078 kl 0.000 anchor 0.000 0.092s/rec
|
| 44 |
+
ep0 step 410/3144 loss 0.803 kl 0.000 anchor 0.000 0.091s/rec
|
| 45 |
+
ep0 step 420/3144 loss 0.653 kl 0.000 anchor 0.000 0.089s/rec
|
| 46 |
+
ep0 step 430/3144 loss 0.845 kl 0.000 anchor 0.000 0.088s/rec
|
| 47 |
+
ep0 step 440/3144 loss 0.781 kl 0.000 anchor 0.000 0.087s/rec
|
| 48 |
+
ep0 step 450/3144 loss 0.757 kl 0.000 anchor 0.000 0.085s/rec
|
| 49 |
+
ep0 step 460/3144 loss 0.768 kl 0.000 anchor 0.000 0.084s/rec
|
| 50 |
+
ep0 step 470/3144 loss 0.727 kl 0.000 anchor 0.000 0.083s/rec
|
| 51 |
+
ep0 step 480/3144 loss 0.734 kl 0.000 anchor 0.000 0.082s/rec
|
| 52 |
+
ep0 step 490/3144 loss 0.642 kl 0.000 anchor 0.000 0.081s/rec
|
| 53 |
+
ep0 step 500/3144 loss 0.758 kl 0.000 anchor 0.000 0.080s/rec
|
| 54 |
+
ep0 step 510/3144 loss 0.840 kl 0.000 anchor 0.000 0.079s/rec
|
| 55 |
+
ep0 step 520/3144 loss 0.651 kl 0.000 anchor 0.000 0.078s/rec
|
| 56 |
+
ep0 step 530/3144 loss 1.135 kl 0.000 anchor 0.000 0.077s/rec
|
| 57 |
+
ep0 step 540/3144 loss 0.673 kl 0.000 anchor 0.000 0.076s/rec
|
| 58 |
+
ep0 step 550/3144 loss 0.567 kl 0.000 anchor 0.000 0.075s/rec
|
| 59 |
+
ep0 step 560/3144 loss 1.174 kl 0.000 anchor 0.000 0.075s/rec
|
| 60 |
+
ep0 step 570/3144 loss 0.739 kl 0.000 anchor 0.000 0.074s/rec
|
| 61 |
+
ep0 step 580/3144 loss 0.647 kl 0.000 anchor 0.000 0.073s/rec
|
| 62 |
+
ep0 step 590/3144 loss 0.707 kl 0.000 anchor 0.000 0.073s/rec
|
| 63 |
+
ep0 step 600/3144 loss 0.629 kl 0.000 anchor 0.000 0.072s/rec
|
| 64 |
+
ep0 step 610/3144 loss 0.530 kl 0.000 anchor 0.000 0.072s/rec
|
| 65 |
+
ep0 step 620/3144 loss 0.579 kl 0.000 anchor 0.000 0.071s/rec
|
| 66 |
+
ep0 step 630/3144 loss 0.710 kl 0.000 anchor 0.000 0.071s/rec
|
| 67 |
+
ep0 step 640/3144 loss 0.795 kl 0.000 anchor 0.000 0.070s/rec
|
| 68 |
+
ep0 step 650/3144 loss 0.729 kl 0.000 anchor 0.000 0.070s/rec
|
| 69 |
+
ep0 step 660/3144 loss 0.806 kl 0.000 anchor 0.000 0.069s/rec
|
| 70 |
+
ep0 step 670/3144 loss 0.847 kl 0.000 anchor 0.000 0.068s/rec
|
| 71 |
+
ep0 step 680/3144 loss 0.735 kl 0.000 anchor 0.000 0.068s/rec
|
| 72 |
+
ep0 step 690/3144 loss 0.663 kl 0.000 anchor 0.000 0.067s/rec
|
| 73 |
+
ep0 step 700/3144 loss 0.755 kl 0.000 anchor 0.000 0.067s/rec
|
| 74 |
+
ep0 step 710/3144 loss 0.572 kl 0.000 anchor 0.000 0.066s/rec
|
| 75 |
+
ep0 step 720/3144 loss 0.413 kl 0.000 anchor 0.000 0.066s/rec
|
| 76 |
+
ep0 step 730/3144 loss 0.668 kl 0.000 anchor 0.000 0.065s/rec
|
| 77 |
+
ep0 step 740/3144 loss 0.540 kl 0.000 anchor 0.000 0.065s/rec
|
| 78 |
+
ep0 step 750/3144 loss 0.683 kl 0.000 anchor 0.000 0.064s/rec
|
| 79 |
+
ep0 step 760/3144 loss 0.517 kl 0.000 anchor 0.000 0.064s/rec
|
| 80 |
+
ep0 step 770/3144 loss 0.762 kl 0.000 anchor 0.000 0.064s/rec
|
| 81 |
+
ep0 step 780/3144 loss 0.634 kl 0.000 anchor 0.000 0.063s/rec
|
| 82 |
+
ep0 step 790/3144 loss 0.612 kl 0.000 anchor 0.000 0.063s/rec
|
| 83 |
+
ep0 step 800/3144 loss 0.746 kl 0.000 anchor 0.000 0.062s/rec
|
| 84 |
+
ep0 step 810/3144 loss 0.471 kl 0.000 anchor 0.000 0.062s/rec
|
| 85 |
+
ep0 step 820/3144 loss 0.620 kl 0.000 anchor 0.000 0.061s/rec
|
| 86 |
+
ep0 step 830/3144 loss 0.470 kl 0.000 anchor 0.000 0.061s/rec
|
| 87 |
+
ep0 step 840/3144 loss 0.836 kl 0.000 anchor 0.000 0.061s/rec
|
| 88 |
+
ep0 step 850/3144 loss 0.670 kl 0.000 anchor 0.000 0.060s/rec
|
| 89 |
+
ep0 step 860/3144 loss 0.489 kl 0.000 anchor 0.000 0.060s/rec
|
| 90 |
+
ep0 step 870/3144 loss 0.845 kl 0.000 anchor 0.000 0.060s/rec
|
| 91 |
+
ep0 step 880/3144 loss 0.760 kl 0.000 anchor 0.000 0.059s/rec
|
| 92 |
+
ep0 step 890/3144 loss 0.577 kl 0.000 anchor 0.000 0.059s/rec
|
| 93 |
+
ep0 step 900/3144 loss 0.841 kl 0.000 anchor 0.000 0.059s/rec
|
| 94 |
+
ep0 step 910/3144 loss 0.743 kl 0.000 anchor 0.000 0.058s/rec
|
| 95 |
+
ep0 step 920/3144 loss 0.477 kl 0.000 anchor 0.000 0.058s/rec
|
| 96 |
+
ep0 step 930/3144 loss 0.438 kl 0.000 anchor 0.000 0.058s/rec
|
| 97 |
+
ep0 step 940/3144 loss 1.025 kl 0.000 anchor 0.000 0.058s/rec
|
| 98 |
+
ep0 step 950/3144 loss 0.442 kl 0.000 anchor 0.000 0.057s/rec
|
| 99 |
+
ep0 step 960/3144 loss 1.030 kl 0.000 anchor 0.000 0.057s/rec
|
| 100 |
+
ep0 step 970/3144 loss 0.694 kl 0.000 anchor 0.000 0.057s/rec
|
| 101 |
+
ep0 step 980/3144 loss 0.540 kl 0.000 anchor 0.000 0.057s/rec
|
| 102 |
+
ep0 step 990/3144 loss 0.481 kl 0.000 anchor 0.000 0.056s/rec
|
| 103 |
+
ep0 step 1000/3144 loss 0.904 kl 0.000 anchor 0.000 0.056s/rec
|
| 104 |
+
ep0 step 1010/3144 loss 0.575 kl 0.000 anchor 0.000 0.056s/rec
|
| 105 |
+
ep0 step 1020/3144 loss 0.900 kl 0.000 anchor 0.000 0.056s/rec
|
| 106 |
+
ep0 step 1030/3144 loss 0.500 kl 0.000 anchor 0.000 0.055s/rec
|
| 107 |
+
ep0 step 1040/3144 loss 0.616 kl 0.000 anchor 0.000 0.055s/rec
|
| 108 |
+
ep0 step 1050/3144 loss 0.475 kl 0.000 anchor 0.000 0.055s/rec
|
| 109 |
+
ep0 step 1060/3144 loss 0.551 kl 0.000 anchor 0.000 0.055s/rec
|
| 110 |
+
ep0 step 1070/3144 loss 0.524 kl 0.000 anchor 0.000 0.055s/rec
|
| 111 |
+
ep0 step 1080/3144 loss 0.647 kl 0.000 anchor 0.000 0.054s/rec
|
| 112 |
+
ep0 step 1090/3144 loss 0.662 kl 0.000 anchor 0.000 0.054s/rec
|
| 113 |
+
ep0 step 1100/3144 loss 0.659 kl 0.000 anchor 0.000 0.054s/rec
|
| 114 |
+
ep0 step 1110/3144 loss 0.671 kl 0.000 anchor 0.000 0.054s/rec
|
| 115 |
+
ep0 step 1120/3144 loss 0.542 kl 0.000 anchor 0.000 0.053s/rec
|
| 116 |
+
ep0 step 1130/3144 loss 0.498 kl 0.000 anchor 0.000 0.053s/rec
|
| 117 |
+
ep0 step 1140/3144 loss 0.415 kl 0.000 anchor 0.000 0.053s/rec
|
| 118 |
+
ep0 step 1150/3144 loss 0.540 kl 0.000 anchor 0.000 0.053s/rec
|
| 119 |
+
ep0 step 1160/3144 loss 0.790 kl 0.000 anchor 0.000 0.053s/rec
|
| 120 |
+
ep0 step 1170/3144 loss 0.597 kl 0.000 anchor 0.000 0.052s/rec
|
| 121 |
+
ep0 step 1180/3144 loss 0.521 kl 0.000 anchor 0.000 0.052s/rec
|
| 122 |
+
ep0 step 1190/3144 loss 0.559 kl 0.000 anchor 0.000 0.052s/rec
|
| 123 |
+
ep0 step 1200/3144 loss 0.601 kl 0.000 anchor 0.000 0.052s/rec
|
| 124 |
+
ep0 step 1210/3144 loss 0.420 kl 0.000 anchor 0.000 0.052s/rec
|
| 125 |
+
ep0 step 1220/3144 loss 0.577 kl 0.000 anchor 0.000 0.052s/rec
|
| 126 |
+
ep0 step 1230/3144 loss 0.510 kl 0.000 anchor 0.000 0.051s/rec
|
| 127 |
+
ep0 step 1240/3144 loss 0.596 kl 0.000 anchor 0.000 0.051s/rec
|
| 128 |
+
ep0 step 1250/3144 loss 0.649 kl 0.000 anchor 0.000 0.051s/rec
|
| 129 |
+
ep0 step 1260/3144 loss 0.590 kl 0.000 anchor 0.000 0.051s/rec
|
| 130 |
+
ep0 step 1270/3144 loss 0.610 kl 0.000 anchor 0.000 0.051s/rec
|
| 131 |
+
ep0 step 1280/3144 loss 0.623 kl 0.000 anchor 0.000 0.051s/rec
|
| 132 |
+
ep0 step 1290/3144 loss 0.706 kl 0.000 anchor 0.000 0.051s/rec
|
| 133 |
+
ep0 step 1300/3144 loss 0.876 kl 0.000 anchor 0.000 0.050s/rec
|
| 134 |
+
ep0 step 1310/3144 loss 0.552 kl 0.000 anchor 0.000 0.050s/rec
|
| 135 |
+
ep0 step 1320/3144 loss 0.539 kl 0.000 anchor 0.000 0.050s/rec
|
| 136 |
+
ep0 step 1330/3144 loss 0.888 kl 0.000 anchor 0.000 0.050s/rec
|
| 137 |
+
ep0 step 1340/3144 loss 0.550 kl 0.000 anchor 0.000 0.050s/rec
|
| 138 |
+
ep0 step 1350/3144 loss 0.407 kl 0.000 anchor 0.000 0.050s/rec
|
| 139 |
+
ep0 step 1360/3144 loss 0.783 kl 0.000 anchor 0.000 0.050s/rec
|
| 140 |
+
ep0 step 1370/3144 loss 0.627 kl 0.000 anchor 0.000 0.049s/rec
|
| 141 |
+
ep0 step 1380/3144 loss 0.720 kl 0.000 anchor 0.000 0.049s/rec
|
| 142 |
+
ep0 step 1390/3144 loss 0.507 kl 0.000 anchor 0.000 0.049s/rec
|
| 143 |
+
ep0 step 1400/3144 loss 0.719 kl 0.000 anchor 0.000 0.049s/rec
|
| 144 |
+
ep0 step 1410/3144 loss 0.376 kl 0.000 anchor 0.000 0.049s/rec
|
| 145 |
+
ep0 step 1420/3144 loss 0.633 kl 0.000 anchor 0.000 0.049s/rec
|
| 146 |
+
ep0 step 1430/3144 loss 0.462 kl 0.000 anchor 0.000 0.049s/rec
|
| 147 |
+
ep0 step 1440/3144 loss 0.511 kl 0.000 anchor 0.000 0.048s/rec
|
| 148 |
+
ep0 step 1450/3144 loss 0.807 kl 0.000 anchor 0.000 0.048s/rec
|
| 149 |
+
ep0 step 1460/3144 loss 0.682 kl 0.000 anchor 0.000 0.048s/rec
|
| 150 |
+
ep0 step 1470/3144 loss 0.530 kl 0.000 anchor 0.000 0.048s/rec
|
| 151 |
+
ep0 step 1480/3144 loss 0.480 kl 0.000 anchor 0.000 0.048s/rec
|
| 152 |
+
ep0 step 1490/3144 loss 0.479 kl 0.000 anchor 0.000 0.048s/rec
|
| 153 |
+
ep0 step 1500/3144 loss 0.635 kl 0.000 anchor 0.000 0.048s/rec
|
| 154 |
+
ep0 step 1510/3144 loss 0.489 kl 0.000 anchor 0.000 0.048s/rec
|
| 155 |
+
ep0 step 1520/3144 loss 0.695 kl 0.000 anchor 0.000 0.048s/rec
|
| 156 |
+
ep0 step 1530/3144 loss 0.482 kl 0.000 anchor 0.000 0.047s/rec
|
| 157 |
+
ep0 step 1540/3144 loss 0.534 kl 0.000 anchor 0.000 0.047s/rec
|
| 158 |
+
ep0 step 1550/3144 loss 0.459 kl 0.000 anchor 0.000 0.047s/rec
|
| 159 |
+
ep0 step 1560/3144 loss 0.750 kl 0.000 anchor 0.000 0.047s/rec
|
| 160 |
+
ep0 step 1570/3144 loss 0.667 kl 0.000 anchor 0.000 0.047s/rec
|
| 161 |
+
ep1 step 1580/3144 loss 0.536 kl 0.000 anchor 0.000 0.047s/rec
|
| 162 |
+
ep1 step 1590/3144 loss 0.318 kl 0.000 anchor 0.000 0.047s/rec
|
| 163 |
+
ep1 step 1600/3144 loss 0.469 kl 0.000 anchor 0.000 0.047s/rec
|
| 164 |
+
ep1 step 1610/3144 loss 0.257 kl 0.000 anchor 0.000 0.047s/rec
|
| 165 |
+
ep1 step 1620/3144 loss 0.456 kl 0.000 anchor 0.000 0.046s/rec
|
| 166 |
+
ep1 step 1630/3144 loss 0.237 kl 0.000 anchor 0.000 0.046s/rec
|
| 167 |
+
ep1 step 1640/3144 loss 0.305 kl 0.000 anchor 0.000 0.046s/rec
|
| 168 |
+
ep1 step 1650/3144 loss 0.581 kl 0.000 anchor 0.000 0.046s/rec
|
| 169 |
+
ep1 step 1660/3144 loss 0.370 kl 0.000 anchor 0.000 0.046s/rec
|
| 170 |
+
ep1 step 1670/3144 loss 0.515 kl 0.000 anchor 0.000 0.046s/rec
|
| 171 |
+
ep1 step 1680/3144 loss 0.491 kl 0.000 anchor 0.000 0.046s/rec
|
| 172 |
+
ep1 step 1690/3144 loss 0.393 kl 0.000 anchor 0.000 0.046s/rec
|
| 173 |
+
ep1 step 1700/3144 loss 0.534 kl 0.000 anchor 0.000 0.046s/rec
|
| 174 |
+
ep1 step 1710/3144 loss 0.379 kl 0.000 anchor 0.000 0.046s/rec
|
| 175 |
+
ep1 step 1720/3144 loss 0.960 kl 0.000 anchor 0.000 0.046s/rec
|
| 176 |
+
ep1 step 1730/3144 loss 0.450 kl 0.000 anchor 0.000 0.046s/rec
|
| 177 |
+
ep1 step 1740/3144 loss 0.288 kl 0.000 anchor 0.000 0.045s/rec
|
| 178 |
+
ep1 step 1750/3144 loss 0.359 kl 0.000 anchor 0.000 0.045s/rec
|
| 179 |
+
ep1 step 1760/3144 loss 0.368 kl 0.000 anchor 0.000 0.045s/rec
|
| 180 |
+
ep1 step 1770/3144 loss 0.423 kl 0.000 anchor 0.000 0.045s/rec
|
| 181 |
+
ep1 step 1780/3144 loss 0.353 kl 0.000 anchor 0.000 0.045s/rec
|
| 182 |
+
ep1 step 1790/3144 loss 0.357 kl 0.000 anchor 0.000 0.045s/rec
|
| 183 |
+
ep1 step 1800/3144 loss 0.367 kl 0.000 anchor 0.000 0.045s/rec
|
| 184 |
+
ep1 step 1810/3144 loss 0.412 kl 0.000 anchor 0.000 0.045s/rec
|
| 185 |
+
ep1 step 1820/3144 loss 0.309 kl 0.000 anchor 0.000 0.045s/rec
|
| 186 |
+
ep1 step 1830/3144 loss 0.460 kl 0.000 anchor 0.000 0.045s/rec
|
| 187 |
+
ep1 step 1840/3144 loss 0.411 kl 0.000 anchor 0.000 0.045s/rec
|
| 188 |
+
ep1 step 1850/3144 loss 0.449 kl 0.000 anchor 0.000 0.045s/rec
|
| 189 |
+
ep1 step 1860/3144 loss 0.650 kl 0.000 anchor 0.000 0.044s/rec
|
| 190 |
+
ep1 step 1870/3144 loss 0.326 kl 0.000 anchor 0.000 0.044s/rec
|
| 191 |
+
ep1 step 1880/3144 loss 0.416 kl 0.000 anchor 0.000 0.044s/rec
|
| 192 |
+
ep1 step 1890/3144 loss 0.279 kl 0.000 anchor 0.000 0.044s/rec
|
| 193 |
+
ep1 step 1900/3144 loss 0.542 kl 0.000 anchor 0.000 0.044s/rec
|
| 194 |
+
ep1 step 1910/3144 loss 0.401 kl 0.000 anchor 0.000 0.044s/rec
|
| 195 |
+
ep1 step 1920/3144 loss 0.470 kl 0.000 anchor 0.000 0.044s/rec
|
| 196 |
+
ep1 step 1930/3144 loss 0.438 kl 0.000 anchor 0.000 0.044s/rec
|
| 197 |
+
ep1 step 1940/3144 loss 0.431 kl 0.000 anchor 0.000 0.044s/rec
|
| 198 |
+
ep1 step 1950/3144 loss 0.819 kl 0.000 anchor 0.000 0.044s/rec
|
| 199 |
+
ep1 step 1960/3144 loss 0.525 kl 0.000 anchor 0.000 0.044s/rec
|
| 200 |
+
ep1 step 1970/3144 loss 0.360 kl 0.000 anchor 0.000 0.044s/rec
|
| 201 |
+
ep1 step 1980/3144 loss 0.377 kl 0.000 anchor 0.000 0.044s/rec
|
| 202 |
+
ep1 step 1990/3144 loss 0.380 kl 0.000 anchor 0.000 0.044s/rec
|
| 203 |
+
ep1 step 2000/3144 loss 0.269 kl 0.000 anchor 0.000 0.044s/rec
|
| 204 |
+
ep1 step 2010/3144 loss 0.759 kl 0.000 anchor 0.000 0.043s/rec
|
| 205 |
+
ep1 step 2020/3144 loss 0.640 kl 0.000 anchor 0.000 0.043s/rec
|
| 206 |
+
ep1 step 2030/3144 loss 0.539 kl 0.000 anchor 0.000 0.043s/rec
|
| 207 |
+
ep1 step 2040/3144 loss 0.324 kl 0.000 anchor 0.000 0.043s/rec
|
| 208 |
+
ep1 step 2050/3144 loss 0.239 kl 0.000 anchor 0.000 0.043s/rec
|
| 209 |
+
ep1 step 2060/3144 loss 0.484 kl 0.000 anchor 0.000 0.043s/rec
|
| 210 |
+
ep1 step 2070/3144 loss 0.231 kl 0.000 anchor 0.000 0.043s/rec
|
| 211 |
+
ep1 step 2080/3144 loss 0.365 kl 0.000 anchor 0.000 0.043s/rec
|
| 212 |
+
ep1 step 2090/3144 loss 0.206 kl 0.000 anchor 0.000 0.043s/rec
|
| 213 |
+
ep1 step 2100/3144 loss 0.512 kl 0.000 anchor 0.000 0.043s/rec
|
| 214 |
+
ep1 step 2110/3144 loss 0.314 kl 0.000 anchor 0.000 0.043s/rec
|
| 215 |
+
ep1 step 2120/3144 loss 0.365 kl 0.000 anchor 0.000 0.043s/rec
|
| 216 |
+
ep1 step 2130/3144 loss 0.279 kl 0.000 anchor 0.000 0.043s/rec
|
| 217 |
+
ep1 step 2140/3144 loss 0.364 kl 0.000 anchor 0.000 0.043s/rec
|
| 218 |
+
ep1 step 2150/3144 loss 0.480 kl 0.000 anchor 0.000 0.043s/rec
|
| 219 |
+
ep1 step 2160/3144 loss 0.417 kl 0.000 anchor 0.000 0.043s/rec
|
| 220 |
+
ep1 step 2170/3144 loss 0.198 kl 0.000 anchor 0.000 0.043s/rec
|
| 221 |
+
ep1 step 2180/3144 loss 0.258 kl 0.000 anchor 0.000 0.043s/rec
|
| 222 |
+
ep1 step 2190/3144 loss 0.406 kl 0.000 anchor 0.000 0.043s/rec
|
| 223 |
+
ep1 step 2200/3144 loss 0.400 kl 0.000 anchor 0.000 0.043s/rec
|
| 224 |
+
ep1 step 2210/3144 loss 0.270 kl 0.000 anchor 0.000 0.042s/rec
|
| 225 |
+
ep1 step 2220/3144 loss 0.315 kl 0.000 anchor 0.000 0.042s/rec
|
| 226 |
+
ep1 step 2230/3144 loss 0.312 kl 0.000 anchor 0.000 0.042s/rec
|
| 227 |
+
ep1 step 2240/3144 loss 0.564 kl 0.000 anchor 0.000 0.042s/rec
|
| 228 |
+
ep1 step 2250/3144 loss 0.321 kl 0.000 anchor 0.000 0.042s/rec
|
| 229 |
+
ep1 step 2260/3144 loss 0.364 kl 0.000 anchor 0.000 0.042s/rec
|
| 230 |
+
ep1 step 2270/3144 loss 0.433 kl 0.000 anchor 0.000 0.042s/rec
|
| 231 |
+
ep1 step 2280/3144 loss 0.484 kl 0.000 anchor 0.000 0.042s/rec
|
| 232 |
+
ep1 step 2290/3144 loss 0.236 kl 0.000 anchor 0.000 0.042s/rec
|
| 233 |
+
ep1 step 2300/3144 loss 0.289 kl 0.000 anchor 0.000 0.042s/rec
|
| 234 |
+
ep1 step 2310/3144 loss 0.336 kl 0.000 anchor 0.000 0.042s/rec
|
| 235 |
+
ep1 step 2320/3144 loss 0.286 kl 0.000 anchor 0.000 0.042s/rec
|
| 236 |
+
ep1 step 2330/3144 loss 0.384 kl 0.000 anchor 0.000 0.042s/rec
|
| 237 |
+
ep1 step 2340/3144 loss 0.308 kl 0.000 anchor 0.000 0.042s/rec
|
| 238 |
+
ep1 step 2350/3144 loss 0.423 kl 0.000 anchor 0.000 0.042s/rec
|
| 239 |
+
ep1 step 2360/3144 loss 0.442 kl 0.000 anchor 0.000 0.042s/rec
|
| 240 |
+
ep1 step 2370/3144 loss 0.455 kl 0.000 anchor 0.000 0.042s/rec
|
| 241 |
+
ep1 step 2380/3144 loss 0.432 kl 0.000 anchor 0.000 0.042s/rec
|
| 242 |
+
ep1 step 2390/3144 loss 0.226 kl 0.000 anchor 0.000 0.042s/rec
|
| 243 |
+
ep1 step 2400/3144 loss 0.236 kl 0.000 anchor 0.000 0.042s/rec
|
| 244 |
+
ep1 step 2410/3144 loss 0.330 kl 0.000 anchor 0.000 0.042s/rec
|
| 245 |
+
ep1 step 2420/3144 loss 0.444 kl 0.000 anchor 0.000 0.042s/rec
|
| 246 |
+
ep1 step 2430/3144 loss 0.421 kl 0.000 anchor 0.000 0.041s/rec
|
| 247 |
+
ep1 step 2440/3144 loss 0.304 kl 0.000 anchor 0.000 0.041s/rec
|
| 248 |
+
ep1 step 2450/3144 loss 0.342 kl 0.000 anchor 0.000 0.041s/rec
|
| 249 |
+
ep1 step 2460/3144 loss 0.307 kl 0.000 anchor 0.000 0.041s/rec
|
| 250 |
+
ep1 step 2470/3144 loss 0.424 kl 0.000 anchor 0.000 0.041s/rec
|
| 251 |
+
ep1 step 2480/3144 loss 0.297 kl 0.000 anchor 0.000 0.041s/rec
|
| 252 |
+
ep1 step 2490/3144 loss 0.490 kl 0.000 anchor 0.000 0.041s/rec
|
| 253 |
+
ep1 step 2500/3144 loss 0.440 kl 0.000 anchor 0.000 0.041s/rec
|
| 254 |
+
ep1 step 2510/3144 loss 0.437 kl 0.000 anchor 0.000 0.041s/rec
|
| 255 |
+
ep1 step 2520/3144 loss 0.300 kl 0.000 anchor 0.000 0.041s/rec
|
| 256 |
+
ep1 step 2530/3144 loss 0.344 kl 0.000 anchor 0.000 0.041s/rec
|
| 257 |
+
ep1 step 2540/3144 loss 0.255 kl 0.000 anchor 0.000 0.041s/rec
|
| 258 |
+
ep1 step 2550/3144 loss 0.391 kl 0.000 anchor 0.000 0.041s/rec
|
| 259 |
+
ep1 step 2560/3144 loss 0.351 kl 0.000 anchor 0.000 0.041s/rec
|
| 260 |
+
ep1 step 2570/3144 loss 0.435 kl 0.000 anchor 0.000 0.041s/rec
|
| 261 |
+
ep1 step 2580/3144 loss 0.225 kl 0.000 anchor 0.000 0.041s/rec
|
| 262 |
+
ep1 step 2590/3144 loss 0.497 kl 0.000 anchor 0.000 0.041s/rec
|
| 263 |
+
ep1 step 2600/3144 loss 0.273 kl 0.000 anchor 0.000 0.041s/rec
|
| 264 |
+
ep1 step 2610/3144 loss 0.688 kl 0.000 anchor 0.000 0.041s/rec
|
| 265 |
+
ep1 step 2620/3144 loss 0.203 kl 0.000 anchor 0.000 0.041s/rec
|
| 266 |
+
ep1 step 2630/3144 loss 0.493 kl 0.000 anchor 0.000 0.041s/rec
|
| 267 |
+
ep1 step 2640/3144 loss 0.472 kl 0.000 anchor 0.000 0.041s/rec
|
| 268 |
+
ep1 step 2650/3144 loss 0.477 kl 0.000 anchor 0.000 0.041s/rec
|
| 269 |
+
ep1 step 2660/3144 loss 0.281 kl 0.000 anchor 0.000 0.041s/rec
|
| 270 |
+
ep1 step 2670/3144 loss 0.409 kl 0.000 anchor 0.000 0.041s/rec
|
| 271 |
+
ep1 step 2680/3144 loss 0.498 kl 0.000 anchor 0.000 0.041s/rec
|
| 272 |
+
ep1 step 2690/3144 loss 0.341 kl 0.000 anchor 0.000 0.040s/rec
|
| 273 |
+
ep1 step 2700/3144 loss 0.399 kl 0.000 anchor 0.000 0.040s/rec
|
| 274 |
+
ep1 step 2710/3144 loss 0.279 kl 0.000 anchor 0.000 0.040s/rec
|
| 275 |
+
ep1 step 2720/3144 loss 0.324 kl 0.000 anchor 0.000 0.040s/rec
|
| 276 |
+
ep1 step 2730/3144 loss 0.220 kl 0.000 anchor 0.000 0.040s/rec
|
| 277 |
+
ep1 step 2740/3144 loss 0.427 kl 0.000 anchor 0.000 0.040s/rec
|
| 278 |
+
ep1 step 2750/3144 loss 0.173 kl 0.000 anchor 0.000 0.040s/rec
|
| 279 |
+
ep1 step 2760/3144 loss 0.498 kl 0.000 anchor 0.000 0.040s/rec
|
| 280 |
+
ep1 step 2770/3144 loss 0.262 kl 0.000 anchor 0.000 0.040s/rec
|
| 281 |
+
ep1 step 2780/3144 loss 0.220 kl 0.000 anchor 0.000 0.040s/rec
|
| 282 |
+
ep1 step 2790/3144 loss 0.169 kl 0.000 anchor 0.000 0.040s/rec
|
| 283 |
+
ep1 step 2800/3144 loss 0.300 kl 0.000 anchor 0.000 0.040s/rec
|
| 284 |
+
ep1 step 2810/3144 loss 0.259 kl 0.000 anchor 0.000 0.040s/rec
|
| 285 |
+
ep1 step 2820/3144 loss 0.334 kl 0.000 anchor 0.000 0.040s/rec
|
| 286 |
+
ep1 step 2830/3144 loss 0.379 kl 0.000 anchor 0.000 0.040s/rec
|
| 287 |
+
ep1 step 2840/3144 loss 0.328 kl 0.000 anchor 0.000 0.040s/rec
|
| 288 |
+
ep1 step 2850/3144 loss 0.320 kl 0.000 anchor 0.000 0.040s/rec
|
| 289 |
+
ep1 step 2860/3144 loss 0.357 kl 0.000 anchor 0.000 0.040s/rec
|
| 290 |
+
ep1 step 2870/3144 loss 0.481 kl 0.000 anchor 0.000 0.040s/rec
|
| 291 |
+
ep1 step 2880/3144 loss 0.496 kl 0.000 anchor 0.000 0.040s/rec
|
| 292 |
+
ep1 step 2890/3144 loss 0.596 kl 0.000 anchor 0.000 0.040s/rec
|
| 293 |
+
ep1 step 2900/3144 loss 0.521 kl 0.000 anchor 0.000 0.040s/rec
|
| 294 |
+
ep1 step 2910/3144 loss 0.150 kl 0.000 anchor 0.000 0.040s/rec
|
| 295 |
+
ep1 step 2920/3144 loss 0.139 kl 0.000 anchor 0.000 0.040s/rec
|
| 296 |
+
ep1 step 2930/3144 loss 0.261 kl 0.000 anchor 0.000 0.040s/rec
|
| 297 |
+
ep1 step 2940/3144 loss 0.564 kl 0.000 anchor 0.000 0.040s/rec
|
| 298 |
+
ep1 step 2950/3144 loss 0.383 kl 0.000 anchor 0.000 0.040s/rec
|
| 299 |
+
ep1 step 2960/3144 loss 0.354 kl 0.000 anchor 0.000 0.040s/rec
|
| 300 |
+
ep1 step 2970/3144 loss 0.373 kl 0.000 anchor 0.000 0.040s/rec
|
| 301 |
+
ep1 step 2980/3144 loss 0.119 kl 0.000 anchor 0.000 0.040s/rec
|
| 302 |
+
ep1 step 2990/3144 loss 0.469 kl 0.000 anchor 0.000 0.040s/rec
|
| 303 |
+
ep1 step 3000/3144 loss 0.416 kl 0.000 anchor 0.000 0.040s/rec
|
| 304 |
+
ep1 step 3010/3144 loss 0.341 kl 0.000 anchor 0.000 0.040s/rec
|
| 305 |
+
ep1 step 3020/3144 loss 0.405 kl 0.000 anchor 0.000 0.040s/rec
|
| 306 |
+
ep1 step 3030/3144 loss 0.549 kl 0.000 anchor 0.000 0.040s/rec
|
| 307 |
+
ep1 step 3040/3144 loss 0.288 kl 0.000 anchor 0.000 0.040s/rec
|
| 308 |
+
ep1 step 3050/3144 loss 0.255 kl 0.000 anchor 0.000 0.039s/rec
|
| 309 |
+
ep1 step 3060/3144 loss 0.327 kl 0.000 anchor 0.000 0.039s/rec
|
| 310 |
+
ep1 step 3070/3144 loss 0.322 kl 0.000 anchor 0.000 0.039s/rec
|
| 311 |
+
ep1 step 3080/3144 loss 0.485 kl 0.000 anchor 0.000 0.040s/rec
|
| 312 |
+
ep1 step 3090/3144 loss 0.222 kl 0.000 anchor 0.000 0.039s/rec
|
| 313 |
+
ep1 step 3100/3144 loss 0.311 kl 0.000 anchor 0.000 0.039s/rec
|
| 314 |
+
ep1 step 3110/3144 loss 0.452 kl 0.000 anchor 0.000 0.039s/rec
|
| 315 |
+
ep1 step 3120/3144 loss 0.485 kl 0.000 anchor 0.000 0.039s/rec
|
| 316 |
+
ep1 step 3130/3144 loss 0.277 kl 0.000 anchor 0.000 0.039s/rec
|
| 317 |
+
ep1 step 3140/3144 loss 0.230 kl 0.000 anchor 0.000 0.039s/rec
|
| 318 |
+
Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads.
|
| 319 |
+
saved /runs/q35-08b/02-trial-2/checkpoint
|
training_config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"args": {
|
| 3 |
+
"base": "Qwen/Qwen3.5-0.8B-Base",
|
| 4 |
+
"n_per_source": 1000,
|
| 5 |
+
"epochs": 2,
|
| 6 |
+
"lr": 0.0001,
|
| 7 |
+
"head_lr": 0.0,
|
| 8 |
+
"weight_decay": 0.01,
|
| 9 |
+
"lora": 16,
|
| 10 |
+
"accum": 1,
|
| 11 |
+
"holdout": "",
|
| 12 |
+
"perm_kl": 0.0,
|
| 13 |
+
"perm_frac": 0.3,
|
| 14 |
+
"ord_w": 0.0,
|
| 15 |
+
"suite": "/root/evals/v7/decision-v7",
|
| 16 |
+
"train_sources": "",
|
| 17 |
+
"device": "cuda",
|
| 18 |
+
"batch": 8,
|
| 19 |
+
"dtype": "bf16",
|
| 20 |
+
"checkpointing": 0,
|
| 21 |
+
"option_isolation": 0,
|
| 22 |
+
"special_embeddings": 0,
|
| 23 |
+
"head_dim": 256,
|
| 24 |
+
"lora_targets": "all",
|
| 25 |
+
"base_revision": "dc7cdfe2ee4154fa7e30f5b51ca41bfa40174e68",
|
| 26 |
+
"p_none": 0.1,
|
| 27 |
+
"p_none_distract": 0.12,
|
| 28 |
+
"p_distract": 0.15,
|
| 29 |
+
"p_none_pair": 0.25,
|
| 30 |
+
"synthetic_repeat": 1,
|
| 31 |
+
"public_frac": 1.0,
|
| 32 |
+
"anchor": "",
|
| 33 |
+
"anchor_w": 0.0,
|
| 34 |
+
"anchor_sources": "",
|
| 35 |
+
"out": "/runs/q35-08b/02-trial-2/checkpoint",
|
| 36 |
+
"seed": 2
|
| 37 |
+
},
|
| 38 |
+
"suite_sha256": "a8f50e481b7d90b97da049e0ff6a01cee2f1ed204aed61a8265af0edbb5514d2",
|
| 39 |
+
"base_revision": "dc7cdfe2ee4154fa7e30f5b51ca41bfa40174e68",
|
| 40 |
+
"ordinal_objective": "ranked_probability_score",
|
| 41 |
+
"holdout": []
|
| 42 |
+
}
|
training_metrics.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"wall_seconds": 1195.3522906303406,
|
| 3 |
+
"records_seen": 30370,
|
| 4 |
+
"requested_records": 25152,
|
| 5 |
+
"truncated_records": 0,
|
| 6 |
+
"rejected_records": 0,
|
| 7 |
+
"optimizer_steps": 3144,
|
| 8 |
+
"forward_tokens": 5832366,
|
| 9 |
+
"peak_device_bytes": 56761799680,
|
| 10 |
+
"device": "cuda",
|
| 11 |
+
"dtype": "bf16",
|
| 12 |
+
"batch": 8,
|
| 13 |
+
"peak_rss_bytes": 10316271616
|
| 14 |
+
}
|