Upload folder using huggingface_hub
Browse files- README.md +12 -10
- decider/infer.py +13 -9
- decider/prompt.py +11 -2
- decider_config.json +1 -1
- eval_results.json +842 -828
- model.safetensors +1 -1
- tokenizer_config.json +1 -1
README.md
CHANGED
|
@@ -88,8 +88,9 @@ SHP, HH-RLHF) and tool selection (Glaive, ToolACE).
|
|
| 88 |
v4 adds next-action choice from agent trajectories (AgentGym AgentTraj-L), web element
|
| 89 |
choice (Mind2Web), 1.5k synthetic situations written by Qwen3.5-27B, and teacher-labelled
|
| 90 |
states from Pong, Breakout, CliffWalking, MiniGrid and Super Mario Bros.
|
| 91 |
-
Abstention augmentation: in 10% of questions with three or more options
|
| 92 |
-
|
|
|
|
| 93 |
|
| 94 |
## Evaluation
|
| 95 |
|
|
@@ -99,8 +100,8 @@ gold option is removed and "none of the above" becomes the answer.
|
|
| 99 |
| Qwen3.5-2B-Base, zero-shot | held-out (23) | 0.642 | 0.853 | 0.460 | 0.105 | 0.242 | 0.685 |
|
| 100 |
| Qwen3.5-4B-Base, zero-shot | in-task (64) | 0.695 | 0.768 | 0.405 | 0.090 | 0.206 | 0.742 |
|
| 101 |
| Qwen3.5-4B-Base, zero-shot | held-out (23) | 0.711 | 0.734 | 0.390 | 0.089 | 0.169 | 0.761 |
|
| 102 |
-
| **this model (
|
| 103 |
-
| **this model (
|
| 104 |
|
| 105 |
|
| 106 |
Per-task accuracy / ECE on the held-out datasets:
|
|
@@ -196,7 +197,7 @@ Per-task accuracy / ECE on the held-out datasets:
|
|
| 196 |
| tweet_irony | 0.511 / 0.158 | 0.676 / 0.073 | 0.769 / 0.048 |
|
| 197 |
|
| 198 |
|
| 199 |
-
Probabilities use a temperature of 1.
|
| 200 |
*In-task* = test splits of the training datasets (in-task rows for the zero-shot baselines cover the original 64). *Held-out* = 23 datasets never
|
| 201 |
seen in training: TREC, BBC news, PAWS, SciQ, Social IQa, StrategyQA, PubMedQA,
|
| 202 |
TruthfulQA, tweet irony, financial sentiment, ADE, MASSIVE scenario, student
|
|
@@ -240,11 +241,12 @@ less than the evaluation noise (18-task check: accuracy 0.833 vs 0.835, ECE equa
|
|
| 240 |
raised held-out accuracy but lowered two held-out tasks: Hermes tool selection
|
| 241 |
(0.80 to 0.74) and TruthfulQA (0.54 to 0.50).
|
| 242 |
* Scale fields are the least trained type; expect wider distributions there.
|
| 243 |
-
*
|
| 244 |
-
|
| 245 |
-
|
| 246 |
-
|
| 247 |
-
|
|
|
|
| 248 |
* One in-task dataset, `tweet_hate` (SemEval-2019 HatEval), stays near chance on its
|
| 249 |
test split. That split is known to differ from its training split in collection
|
| 250 |
and label definition; the number is reported as measured.
|
|
|
|
| 88 |
v4 adds next-action choice from agent trajectories (AgentGym AgentTraj-L), web element
|
| 89 |
choice (Mind2Web), 1.5k synthetic situations written by Qwen3.5-27B, and teacher-labelled
|
| 90 |
states from Pong, Breakout, CliffWalking, MiniGrid and Super Mario Bros.
|
| 91 |
+
Abstention augmentation: in 10% of questions with three or more options an abstain
|
| 92 |
+
option with one of twelve wordings is added; in a quarter of those the whole option list is
|
| 93 |
+
replaced by labels from an unrelated task, making the abstain option correct.
|
| 94 |
|
| 95 |
## Evaluation
|
| 96 |
|
|
|
|
| 100 |
| Qwen3.5-2B-Base, zero-shot | held-out (23) | 0.642 | 0.853 | 0.460 | 0.105 | 0.242 | 0.685 |
|
| 101 |
| Qwen3.5-4B-Base, zero-shot | in-task (64) | 0.695 | 0.768 | 0.405 | 0.090 | 0.206 | 0.742 |
|
| 102 |
| Qwen3.5-4B-Base, zero-shot | held-out (23) | 0.711 | 0.734 | 0.390 | 0.089 | 0.169 | 0.761 |
|
| 103 |
+
| **this model (v5)** | in-task (69) | 0.815 | 0.445 | 0.248 | 0.028 | 0.093 | 0.866 |
|
| 104 |
+
| **this model (v5)** | held-out (24) | 0.738 | 0.678 | 0.360 | 0.084 | 0.145 | 0.793 |
|
| 105 |
|
| 106 |
|
| 107 |
Per-task accuracy / ECE on the held-out datasets:
|
|
|
|
| 197 |
| tweet_irony | 0.511 / 0.158 | 0.676 / 0.073 | 0.769 / 0.048 |
|
| 198 |
|
| 199 |
|
| 200 |
+
Probabilities use a temperature of 1.05 fitted on in-task data (stored in `decider_config.json`, applied by the helper).
|
| 201 |
*In-task* = test splits of the training datasets (in-task rows for the zero-shot baselines cover the original 64). *Held-out* = 23 datasets never
|
| 202 |
seen in training: TREC, BBC news, PAWS, SciQ, Social IQa, StrategyQA, PubMedQA,
|
| 203 |
TruthfulQA, tweet irony, financial sentiment, ADE, MASSIVE scenario, student
|
|
|
|
| 241 |
raised held-out accuracy but lowered two held-out tasks: Hermes tool selection
|
| 242 |
(0.80 to 0.74) and TruthfulQA (0.54 to 0.50).
|
| 243 |
* Scale fields are the least trained type; expect wider distributions there.
|
| 244 |
+
* Abstention (v5): an option such as "none of the above", "other" or "unsure" is chosen when
|
| 245 |
+
nothing on offer fits the situation, not when the exact fine-grained label is merely absent
|
| 246 |
+
(it then takes the best available option). Trained with twelve abstain wordings and
|
| 247 |
+
off-topic option lists; on a held-out probe with off-topic option lists it scores 0.83
|
| 248 |
+
(v4: 0.68). Earlier versions (v4 and before) had learned the literal phrase as an abstain
|
| 249 |
+
signal; the bundled helper's rewrite for that is disabled for v5 via `decider_config.json`.
|
| 250 |
* One in-task dataset, `tweet_hate` (SemEval-2019 HatEval), stays near chance on its
|
| 251 |
test split. That split is known to differ from its training split in collection
|
| 252 |
and label definition; the number is reported as measured.
|
decider/infer.py
CHANGED
|
@@ -44,14 +44,17 @@ class Decider:
|
|
| 44 |
"""use_graphs=True (default on CUDA) routes scoring through decider.engine.Engine: shape-bucketed
|
| 45 |
CUDA graphs, ~7x lower single-request latency than eager. Set False for CPU or debugging."""
|
| 46 |
def __init__(self, path, device="cuda", dtype=torch.bfloat16, temperature=None, abstain_below=0.0, use_graphs=None):
|
| 47 |
-
|
| 48 |
-
|
| 49 |
-
|
| 50 |
-
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
|
| 54 |
-
|
|
|
|
|
|
|
|
|
|
| 55 |
if use_graphs is None:
|
| 56 |
use_graphs = str(device).startswith("cuda")
|
| 57 |
if use_graphs:
|
|
@@ -65,7 +68,8 @@ class Decider:
|
|
| 65 |
def decide_batch(self, requests, max_ctx_tokens=1536):
|
| 66 |
"""requests: list of (context:str, questions:list[dict(question, options)]). One forward pass for everything."""
|
| 67 |
exs, meta = [], []
|
| 68 |
-
|
|
|
|
| 69 |
for context, qs in requests:
|
| 70 |
for q in qs:
|
| 71 |
assert 2 <= len(q["options"]) <= MAX_OPTIONS, f"2..{MAX_OPTIONS} options required"
|
|
|
|
| 44 |
"""use_graphs=True (default on CUDA) routes scoring through decider.engine.Engine: shape-bucketed
|
| 45 |
CUDA graphs, ~7x lower single-request latency than eager. Set False for CPU or debugging."""
|
| 46 |
def __init__(self, path, device="cuda", dtype=torch.bfloat16, temperature=None, abstain_below=0.0, use_graphs=None):
|
| 47 |
+
import json, os
|
| 48 |
+
cfg = {}
|
| 49 |
+
try: # model folder may carry decider_config.json (temperature, flags)
|
| 50 |
+
from huggingface_hub import hf_hub_download
|
| 51 |
+
cfg_path = os.path.join(path, "decider_config.json") if os.path.isdir(path) else hf_hub_download(path, "decider_config.json")
|
| 52 |
+
cfg = json.load(open(cfg_path))
|
| 53 |
+
except Exception:
|
| 54 |
+
pass
|
| 55 |
+
if temperature is None:
|
| 56 |
+
temperature = float(cfg.get("temperature", 1.0))
|
| 57 |
+
self.neutralize_none = bool(cfg.get("neutralize_none", True)) # v4 and earlier learned the literal string as an abstain signal
|
| 58 |
if use_graphs is None:
|
| 59 |
use_graphs = str(device).startswith("cuda")
|
| 60 |
if use_graphs:
|
|
|
|
| 68 |
def decide_batch(self, requests, max_ctx_tokens=1536):
|
| 69 |
"""requests: list of (context:str, questions:list[dict(question, options)]). One forward pass for everything."""
|
| 70 |
exs, meta = [], []
|
| 71 |
+
if self.neutralize_none:
|
| 72 |
+
requests = [(context, [dict(q, options=neutralize_options(q["options"])[0], _back=neutralize_options(q["options"])[1]) for q in qs]) for context, qs in requests]
|
| 73 |
for context, qs in requests:
|
| 74 |
for q in qs:
|
| 75 |
assert 2 <= len(q["options"]) <= MAX_OPTIONS, f"2..{MAX_OPTIONS} options required"
|
decider/prompt.py
CHANGED
|
@@ -9,6 +9,13 @@ import random
|
|
| 9 |
|
| 10 |
LETTERS = "ABCDEFGHIJ"
|
| 11 |
MAX_OPTIONS = len(LETTERS)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
|
| 14 |
def build(example, tok, rng=None, max_options=MAX_OPTIONS, max_ctx_tokens=1536):
|
|
@@ -21,8 +28,10 @@ def build(example, tok, rng=None, max_options=MAX_OPTIONS, max_ctx_tokens=1536):
|
|
| 21 |
for k, q in enumerate(example.qs):
|
| 22 |
opts = list(range(len(q.options)))
|
| 23 |
if len(opts) > max_options:
|
| 24 |
-
|
| 25 |
-
|
|
|
|
|
|
|
| 26 |
opts = keep
|
| 27 |
rng.shuffle(opts)
|
| 28 |
lines = [f"\n\nQuestion{' ' + str(k + 1) if multi else ''}: {q.text}\nOptions:"]
|
|
|
|
| 9 |
|
| 10 |
LETTERS = "ABCDEFGHIJ"
|
| 11 |
MAX_OPTIONS = len(LETTERS)
|
| 12 |
+
ABSTAIN_PREFIXES = ("none of the above", "none of these", "not listed", "no suitable", "does not apply", "cannot tell")
|
| 13 |
+
ABSTAIN_EXACT = ("other", "unsure", "something else", "neither of these", "other / not covered")
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
def is_abstain_option(o):
|
| 17 |
+
o = o.strip().lower()
|
| 18 |
+
return o.startswith(ABSTAIN_PREFIXES) or o in ABSTAIN_EXACT
|
| 19 |
|
| 20 |
|
| 21 |
def build(example, tok, rng=None, max_options=MAX_OPTIONS, max_ctx_tokens=1536):
|
|
|
|
| 28 |
for k, q in enumerate(example.qs):
|
| 29 |
opts = list(range(len(q.options)))
|
| 30 |
if len(opts) > max_options:
|
| 31 |
+
# always keep the gold and any abstain-style option (its mere presence must not carry information)
|
| 32 |
+
forced = {q.gold} | {i for i, o in enumerate(q.options) if is_abstain_option(o)}
|
| 33 |
+
others = [i for i in opts if i not in forced]
|
| 34 |
+
keep = rng.sample(others, max_options - len(forced)) + list(forced)
|
| 35 |
opts = keep
|
| 36 |
rng.shuffle(opts)
|
| 37 |
lines = [f"\n\nQuestion{' ' + str(k + 1) if multi else ''}: {q.text}\nOptions:"]
|
decider_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"temperature": 1.
|
|
|
|
| 1 |
+
{"temperature": 1.05, "neutralize_none": false, "version": "v5", "base": "Qwen/Qwen3.5-2B-Base"}
|
eval_results.json
CHANGED
|
@@ -2,1361 +2,1375 @@
|
|
| 2 |
"results": {
|
| 3 |
"clinc_oos": {
|
| 4 |
"n": 1500,
|
| 5 |
-
"acc": 0.
|
| 6 |
-
"nll": 0.
|
| 7 |
-
"brier": 0.
|
| 8 |
-
"ece": 0.
|
| 9 |
-
"aurc": 0.
|
| 10 |
-
"acc_at_80": 0.
|
| 11 |
-
"acc_at_50":
|
| 12 |
"chance": 0.1,
|
| 13 |
-
"mean_conf": 0.
|
| 14 |
-
"sec":
|
| 15 |
"heldout": false
|
| 16 |
},
|
| 17 |
"massive_intent": {
|
| 18 |
"n": 1500,
|
| 19 |
-
"acc": 0.
|
| 20 |
-
"nll": 0.
|
| 21 |
-
"brier": 0.
|
| 22 |
-
"ece": 0.
|
| 23 |
-
"aurc": 0.
|
| 24 |
-
"acc_at_80": 0.
|
| 25 |
-
"acc_at_50": 0.
|
| 26 |
"chance": 0.1,
|
| 27 |
-
"mean_conf": 0.
|
| 28 |
-
"sec":
|
| 29 |
"heldout": false
|
| 30 |
},
|
| 31 |
"massive_scenario": {
|
| 32 |
"n": 1500,
|
| 33 |
-
"acc": 0.
|
| 34 |
-
"nll": 0.
|
| 35 |
-
"brier": 0.
|
| 36 |
-
"ece": 0.
|
| 37 |
-
"aurc": 0.
|
| 38 |
-
"acc_at_80": 0.
|
| 39 |
-
"acc_at_50": 0.
|
| 40 |
"chance": 0.1,
|
| 41 |
-
"mean_conf": 0.
|
| 42 |
"sec": 1.5,
|
| 43 |
"heldout": true
|
| 44 |
},
|
| 45 |
"bitext_support": {
|
| 46 |
"n": 3000,
|
| 47 |
-
"acc": 0.
|
| 48 |
-
"nll": 0.
|
| 49 |
-
"brier": 0.
|
| 50 |
-
"ece": 0.
|
| 51 |
-
"aurc":
|
| 52 |
-
"acc_at_80":
|
| 53 |
"acc_at_50": 1.0,
|
| 54 |
"chance": 0.09999999999999998,
|
| 55 |
-
"mean_conf": 0.
|
| 56 |
"sec": 2.1,
|
| 57 |
"heldout": false,
|
| 58 |
"per_q": [
|
| 59 |
0.9986666666666667,
|
| 60 |
-
0.
|
| 61 |
]
|
| 62 |
},
|
| 63 |
"support_tickets": {
|
| 64 |
"n": 4500,
|
| 65 |
-
"acc": 0.
|
| 66 |
-
"nll": 0.
|
| 67 |
-
"brier": 0.
|
| 68 |
-
"ece": 0.
|
| 69 |
-
"aurc": 0.
|
| 70 |
-
"acc_at_80": 0.
|
| 71 |
-
"acc_at_50": 0.
|
| 72 |
"chance": 0.22777777777777777,
|
| 73 |
-
"mean_conf": 0.
|
| 74 |
-
"sec": 10.
|
| 75 |
"heldout": false,
|
| 76 |
"per_q": [
|
| 77 |
-
0.
|
| 78 |
-
0.
|
| 79 |
-
0.
|
| 80 |
]
|
| 81 |
},
|
| 82 |
"ag_news": {
|
| 83 |
"n": 1500,
|
| 84 |
-
"acc": 0.
|
| 85 |
-
"nll": 0.
|
| 86 |
-
"brier": 0.
|
| 87 |
-
"ece": 0.
|
| 88 |
-
"aurc": 0.
|
| 89 |
-
"acc_at_80": 0.
|
| 90 |
-
"acc_at_50": 0.
|
| 91 |
"chance": 0.25,
|
| 92 |
-
"mean_conf": 0.
|
| 93 |
"sec": 1.5,
|
| 94 |
"heldout": false
|
| 95 |
},
|
| 96 |
"dbpedia": {
|
| 97 |
"n": 1500,
|
| 98 |
-
"acc": 0.
|
| 99 |
-
"nll": 0.
|
| 100 |
-
"brier": 0.
|
| 101 |
-
"ece": 0.
|
| 102 |
-
"aurc": 0.
|
| 103 |
"acc_at_80": 1.0,
|
| 104 |
"acc_at_50": 1.0,
|
| 105 |
"chance": 0.1,
|
| 106 |
-
"mean_conf": 0.
|
| 107 |
"sec": 2.0,
|
| 108 |
"heldout": false
|
| 109 |
},
|
| 110 |
"yahoo_topics": {
|
| 111 |
"n": 1500,
|
| 112 |
-
"acc": 0.
|
| 113 |
-
"nll": 0.
|
| 114 |
-
"brier": 0.
|
| 115 |
-
"ece": 0.
|
| 116 |
-
"aurc": 0.
|
| 117 |
-
"acc_at_80": 0.
|
| 118 |
-
"acc_at_50": 0.
|
| 119 |
"chance": 0.1,
|
| 120 |
-
"mean_conf": 0.
|
| 121 |
"sec": 1.8,
|
| 122 |
"heldout": false
|
| 123 |
},
|
| 124 |
"newsgroups": {
|
| 125 |
"n": 1462,
|
| 126 |
-
"acc": 0.
|
| 127 |
-
"nll": 0.
|
| 128 |
-
"brier": 0.
|
| 129 |
-
"ece": 0.
|
| 130 |
-
"aurc": 0.
|
| 131 |
-
"acc_at_80": 0.
|
| 132 |
-
"acc_at_50": 0.
|
| 133 |
"chance": 0.09999999999999999,
|
| 134 |
-
"mean_conf": 0.
|
| 135 |
-
"sec": 14.
|
| 136 |
"heldout": false
|
| 137 |
},
|
| 138 |
"bbc_news": {
|
| 139 |
"n": 1000,
|
| 140 |
-
"acc": 0.
|
| 141 |
-
"nll": 0.
|
| 142 |
-
"brier": 0.
|
| 143 |
-
"ece": 0.
|
| 144 |
-
"aurc": 0.
|
| 145 |
-
"acc_at_80": 0.
|
| 146 |
"acc_at_50": 1.0,
|
| 147 |
"chance": 0.20000000000000004,
|
| 148 |
-
"mean_conf": 0.
|
| 149 |
"sec": 5.8,
|
| 150 |
"heldout": true
|
| 151 |
},
|
| 152 |
"trec": {
|
| 153 |
"n": 500,
|
| 154 |
-
"acc": 0.
|
| 155 |
-
"nll": 0.
|
| 156 |
-
"brier": 0.
|
| 157 |
-
"ece": 0.
|
| 158 |
-
"aurc": 0.
|
| 159 |
-
"acc_at_80": 0.
|
| 160 |
-
"acc_at_50": 0.
|
| 161 |
"chance": 0.16666666666666663,
|
| 162 |
-
"mean_conf": 0.
|
| 163 |
-
"sec":
|
| 164 |
"heldout": true
|
| 165 |
},
|
| 166 |
"student_questions": {
|
| 167 |
"n": 1500,
|
| 168 |
-
"acc": 0.
|
| 169 |
-
"nll": 0.
|
| 170 |
-
"brier": 0.
|
| 171 |
-
"ece": 0.
|
| 172 |
-
"aurc": 0.
|
| 173 |
-
"acc_at_80": 0.
|
| 174 |
-
"acc_at_50": 0.
|
| 175 |
"chance": 0.25,
|
| 176 |
-
"mean_conf": 0.
|
| 177 |
-
"sec":
|
| 178 |
"heldout": true
|
| 179 |
},
|
| 180 |
"dolly_category": {
|
| 181 |
"n": 1500,
|
| 182 |
-
"acc": 0.
|
| 183 |
-
"nll": 2.
|
| 184 |
-
"brier": 0.
|
| 185 |
-
"ece": 0.
|
| 186 |
-
"aurc": 0.
|
| 187 |
-
"acc_at_80": 0.
|
| 188 |
-
"acc_at_50": 0.
|
| 189 |
"chance": 0.125,
|
| 190 |
-
"mean_conf": 0.
|
| 191 |
-
"sec":
|
| 192 |
"heldout": true
|
| 193 |
},
|
| 194 |
"imdb": {
|
| 195 |
"n": 1500,
|
| 196 |
"acc": 0.9613333333333334,
|
| 197 |
-
"nll": 0.
|
| 198 |
-
"brier": 0.
|
| 199 |
-
"ece": 0.
|
| 200 |
-
"aurc": 0.
|
| 201 |
-
"acc_at_80": 0.
|
| 202 |
"acc_at_50": 1.0,
|
| 203 |
"chance": 0.5,
|
| 204 |
-
"mean_conf": 0.
|
| 205 |
-
"sec":
|
| 206 |
"heldout": false
|
| 207 |
},
|
| 208 |
"sst2": {
|
| 209 |
"n": 872,
|
| 210 |
-
"acc": 0.
|
| 211 |
-
"nll": 0.
|
| 212 |
-
"brier": 0.
|
| 213 |
-
"ece": 0.
|
| 214 |
-
"aurc": 0.
|
| 215 |
-
"acc_at_80": 0.
|
| 216 |
"acc_at_50": 0.9931192660550459,
|
| 217 |
"chance": 0.5,
|
| 218 |
-
"mean_conf": 0.
|
| 219 |
-
"sec": 3.
|
| 220 |
"heldout": false
|
| 221 |
},
|
| 222 |
"sst5": {
|
| 223 |
"n": 1500,
|
| 224 |
-
"acc": 0.
|
| 225 |
-
"nll": 0.
|
| 226 |
-
"brier": 0.
|
| 227 |
-
"ece": 0.
|
| 228 |
-
"aurc": 0.
|
| 229 |
-
"acc_at_80": 0.
|
| 230 |
-
"acc_at_50": 0.
|
| 231 |
"chance": 0.2,
|
| 232 |
-
"mean_conf": 0.
|
| 233 |
-
"sec":
|
| 234 |
"heldout": false
|
| 235 |
},
|
| 236 |
"yelp": {
|
| 237 |
"n": 1500,
|
| 238 |
-
"acc": 0.
|
| 239 |
-
"nll": 0.
|
| 240 |
-
"brier": 0.
|
| 241 |
-
"ece": 0.
|
| 242 |
-
"aurc": 0.
|
| 243 |
-
"acc_at_80": 0.
|
| 244 |
-
"acc_at_50": 0.
|
| 245 |
"chance": 0.2,
|
| 246 |
-
"mean_conf": 0.
|
| 247 |
-
"sec":
|
| 248 |
"heldout": false
|
| 249 |
},
|
| 250 |
"amazon_stars": {
|
| 251 |
"n": 1500,
|
| 252 |
-
"acc": 0.
|
| 253 |
-
"nll": 0.
|
| 254 |
-
"brier": 0.
|
| 255 |
-
"ece": 0.
|
| 256 |
-
"aurc": 0.
|
| 257 |
-
"acc_at_80": 0.
|
| 258 |
-
"acc_at_50": 0.
|
| 259 |
"chance": 0.2,
|
| 260 |
-
"mean_conf": 0.
|
| 261 |
-
"sec":
|
| 262 |
"heldout": false
|
| 263 |
},
|
| 264 |
"emotion": {
|
| 265 |
"n": 1500,
|
| 266 |
-
"acc": 0.
|
| 267 |
-
"nll": 0.
|
| 268 |
-
"brier": 0.
|
| 269 |
-
"ece": 0.
|
| 270 |
-
"aurc": 0.
|
| 271 |
-
"acc_at_80": 0.
|
| 272 |
-
"acc_at_50": 0.
|
| 273 |
"chance": 0.16666666666666666,
|
| 274 |
-
"mean_conf": 0.
|
| 275 |
-
"sec":
|
| 276 |
"heldout": false
|
| 277 |
},
|
| 278 |
"go_emotions": {
|
| 279 |
"n": 1500,
|
| 280 |
-
"acc": 0.
|
| 281 |
-
"nll": 0.
|
| 282 |
-
"brier": 0.
|
| 283 |
-
"ece": 0.
|
| 284 |
-
"aurc": 0.
|
| 285 |
-
"acc_at_80": 0.
|
| 286 |
-
"acc_at_50": 0.
|
| 287 |
"chance": 0.1,
|
| 288 |
-
"mean_conf": 0.
|
| 289 |
-
"sec":
|
| 290 |
"heldout": false
|
| 291 |
},
|
| 292 |
"tweet_sentiment": {
|
| 293 |
"n": 1500,
|
| 294 |
-
"acc": 0.
|
| 295 |
-
"nll": 0.
|
| 296 |
-
"brier": 0.
|
| 297 |
-
"ece": 0.
|
| 298 |
-
"aurc": 0.
|
| 299 |
-
"acc_at_80": 0.
|
| 300 |
-
"acc_at_50": 0.
|
| 301 |
"chance": 0.3333333333333333,
|
| 302 |
-
"mean_conf": 0.
|
| 303 |
-
"sec":
|
| 304 |
"heldout": false
|
| 305 |
},
|
| 306 |
"tweet_emotion": {
|
| 307 |
"n": 1421,
|
| 308 |
-
"acc": 0.
|
| 309 |
-
"nll": 0.
|
| 310 |
-
"brier": 0.
|
| 311 |
-
"ece": 0.
|
| 312 |
-
"aurc": 0.
|
| 313 |
-
"acc_at_80": 0.
|
| 314 |
-
"acc_at_50": 0.
|
| 315 |
"chance": 0.25,
|
| 316 |
-
"mean_conf": 0.
|
| 317 |
-
"sec":
|
| 318 |
"heldout": false
|
| 319 |
},
|
| 320 |
"tweet_irony": {
|
| 321 |
"n": 784,
|
| 322 |
-
"acc": 0.
|
| 323 |
-
"nll": 0.
|
| 324 |
-
"brier": 0.
|
| 325 |
-
"ece": 0.
|
| 326 |
-
"aurc": 0.
|
| 327 |
-
"acc_at_80": 0.
|
| 328 |
-
"acc_at_50": 0.
|
| 329 |
"chance": 0.5,
|
| 330 |
-
"mean_conf": 0.
|
| 331 |
-
"sec":
|
| 332 |
"heldout": true
|
| 333 |
},
|
| 334 |
"fin_sentiment": {
|
| 335 |
"n": 1500,
|
| 336 |
-
"acc": 0.
|
| 337 |
-
"nll": 0.
|
| 338 |
-
"brier": 0.
|
| 339 |
-
"ece": 0.
|
| 340 |
-
"aurc": 0.
|
| 341 |
-
"acc_at_80": 0.
|
| 342 |
-
"acc_at_50": 0.
|
| 343 |
"chance": 0.3333333333333333,
|
| 344 |
-
"mean_conf": 0.
|
| 345 |
-
"sec":
|
| 346 |
"heldout": true
|
| 347 |
},
|
| 348 |
"cr_reviews": {
|
| 349 |
"n": 753,
|
| 350 |
-
"acc": 0.
|
| 351 |
-
"nll": 0.
|
| 352 |
-
"brier": 0.
|
| 353 |
-
"ece": 0.
|
| 354 |
-
"aurc": 0.
|
| 355 |
-
"acc_at_80": 0.
|
| 356 |
-
"acc_at_50": 0.
|
| 357 |
"chance": 0.5,
|
| 358 |
-
"mean_conf": 0.
|
| 359 |
-
"sec":
|
| 360 |
"heldout": true
|
| 361 |
},
|
| 362 |
"counterfactual": {
|
| 363 |
"n": 1500,
|
| 364 |
-
"acc": 0.
|
| 365 |
-
"nll": 0.
|
| 366 |
-
"brier": 0.
|
| 367 |
-
"ece": 0.
|
| 368 |
-
"aurc": 0.
|
| 369 |
"acc_at_80": 0.99,
|
| 370 |
"acc_at_50": 0.9973333333333333,
|
| 371 |
"chance": 0.5,
|
| 372 |
-
"mean_conf": 0.
|
| 373 |
-
"sec":
|
| 374 |
"heldout": false
|
| 375 |
},
|
| 376 |
"subjectivity": {
|
| 377 |
"n": 1500,
|
| 378 |
-
"acc": 0.
|
| 379 |
-
"nll": 0.
|
| 380 |
-
"brier": 0.
|
| 381 |
-
"ece": 0.
|
| 382 |
-
"aurc": 0.
|
| 383 |
-
"acc_at_80": 0.
|
| 384 |
"acc_at_50": 0.9973333333333333,
|
| 385 |
"chance": 0.5,
|
| 386 |
-
"mean_conf": 0.
|
| 387 |
-
"sec":
|
| 388 |
"heldout": false
|
| 389 |
},
|
| 390 |
"tweet_offensive": {
|
| 391 |
"n": 860,
|
| 392 |
-
"acc": 0.
|
| 393 |
-
"nll": 0.
|
| 394 |
-
"brier": 0.
|
| 395 |
-
"ece": 0.
|
| 396 |
-
"aurc": 0.
|
| 397 |
-
"acc_at_80": 0.
|
| 398 |
-
"acc_at_50": 0.
|
| 399 |
"chance": 0.5,
|
| 400 |
-
"mean_conf": 0.
|
| 401 |
-
"sec":
|
| 402 |
"heldout": false
|
| 403 |
},
|
| 404 |
"tweet_hate": {
|
| 405 |
"n": 1500,
|
| 406 |
-
"acc": 0.
|
| 407 |
-
"nll": 0.
|
| 408 |
-
"brier": 0.
|
| 409 |
-
"ece": 0.
|
| 410 |
-
"aurc": 0.
|
| 411 |
-
"acc_at_80": 0.
|
| 412 |
-
"acc_at_50": 0.
|
| 413 |
"chance": 0.5,
|
| 414 |
-
"mean_conf": 0.
|
| 415 |
-
"sec":
|
| 416 |
"heldout": false
|
| 417 |
},
|
| 418 |
"hate_offensive": {
|
| 419 |
"n": 1500,
|
| 420 |
-
"acc": 0.
|
| 421 |
-
"nll": 0.
|
| 422 |
-
"brier": 0.
|
| 423 |
-
"ece": 0.
|
| 424 |
-
"aurc": 0.
|
| 425 |
-
"acc_at_80": 0.
|
| 426 |
-
"acc_at_50": 0.
|
| 427 |
"chance": 0.3333333333333333,
|
| 428 |
-
"mean_conf": 0.
|
| 429 |
-
"sec":
|
| 430 |
"heldout": false
|
| 431 |
},
|
| 432 |
"civil_comments": {
|
| 433 |
"n": 7500,
|
| 434 |
-
"acc": 0.
|
| 435 |
-
"nll": 0.
|
| 436 |
-
"brier": 0.
|
| 437 |
-
"ece": 0.
|
| 438 |
-
"aurc": 0.
|
| 439 |
-
"acc_at_80": 0.
|
| 440 |
-
"acc_at_50":
|
| 441 |
"chance": 0.5,
|
| 442 |
-
"mean_conf": 0.
|
| 443 |
-
"sec":
|
| 444 |
"heldout": false,
|
| 445 |
"per_q": [
|
| 446 |
-
0.
|
| 447 |
-
0.
|
| 448 |
-
0.
|
| 449 |
-
0.
|
| 450 |
-
0.
|
| 451 |
]
|
| 452 |
},
|
| 453 |
"toxic_chat": {
|
| 454 |
"n": 3000,
|
| 455 |
-
"acc": 0.
|
| 456 |
-
"nll": 0.
|
| 457 |
-
"brier": 0.
|
| 458 |
-
"ece": 0.
|
| 459 |
-
"aurc": 0.
|
| 460 |
"acc_at_80": 0.9991666666666666,
|
| 461 |
-
"acc_at_50":
|
| 462 |
"chance": 0.5,
|
| 463 |
-
"mean_conf": 0.
|
| 464 |
-
"sec":
|
| 465 |
"heldout": false,
|
| 466 |
"per_q": [
|
| 467 |
-
0.
|
| 468 |
-
0.
|
| 469 |
]
|
| 470 |
},
|
| 471 |
"sms_spam": {
|
| 472 |
"n": 1000,
|
| 473 |
-
"acc": 0.
|
| 474 |
-
"nll": 0.
|
| 475 |
-
"brier": 0.
|
| 476 |
-
"ece": 0.
|
| 477 |
-
"aurc": 0.
|
| 478 |
-
"acc_at_80": 0.
|
| 479 |
"acc_at_50": 0.998,
|
| 480 |
"chance": 0.5,
|
| 481 |
-
"mean_conf": 0.
|
| 482 |
-
"sec":
|
| 483 |
"heldout": false
|
| 484 |
},
|
| 485 |
"enron_spam": {
|
| 486 |
"n": 1500,
|
| 487 |
-
"acc": 0.
|
| 488 |
-
"nll": 0.
|
| 489 |
-
"brier": 0.
|
| 490 |
-
"ece": 0.
|
| 491 |
-
"aurc": 0.
|
| 492 |
"acc_at_80": 1.0,
|
| 493 |
"acc_at_50": 1.0,
|
| 494 |
"chance": 0.5,
|
| 495 |
-
"mean_conf": 0.
|
| 496 |
-
"sec":
|
| 497 |
"heldout": false
|
| 498 |
},
|
| 499 |
"insincere_questions": {
|
| 500 |
"n": 1500,
|
| 501 |
-
"acc": 0.
|
| 502 |
-
"nll": 0.
|
| 503 |
-
"brier": 0.
|
| 504 |
-
"ece": 0.
|
| 505 |
-
"aurc": 0.
|
| 506 |
"acc_at_80": 0.9975,
|
| 507 |
-
"acc_at_50": 0.
|
| 508 |
"chance": 0.5,
|
| 509 |
-
"mean_conf": 0.
|
| 510 |
-
"sec":
|
| 511 |
"heldout": false
|
| 512 |
},
|
| 513 |
"ade": {
|
| 514 |
"n": 1500,
|
| 515 |
-
"acc": 0.
|
| 516 |
-
"nll": 0.
|
| 517 |
-
"brier": 0.
|
| 518 |
-
"ece": 0.
|
| 519 |
-
"aurc": 0.
|
| 520 |
-
"acc_at_80": 0.
|
| 521 |
-
"acc_at_50": 0.
|
| 522 |
"chance": 0.5,
|
| 523 |
-
"mean_conf": 0.
|
| 524 |
-
"sec":
|
| 525 |
"heldout": true
|
| 526 |
},
|
| 527 |
"snli": {
|
| 528 |
"n": 1476,
|
| 529 |
-
"acc": 0.
|
| 530 |
-
"nll": 0.
|
| 531 |
-
"brier": 0.
|
| 532 |
-
"ece": 0.
|
| 533 |
-
"aurc": 0.
|
| 534 |
-
"acc_at_80": 0.
|
| 535 |
-
"acc_at_50": 0.
|
| 536 |
"chance": 0.3333333333333333,
|
| 537 |
-
"mean_conf": 0.
|
| 538 |
-
"sec":
|
| 539 |
"heldout": false
|
| 540 |
},
|
| 541 |
"mnli": {
|
| 542 |
"n": 1500,
|
| 543 |
-
"acc": 0.
|
| 544 |
-
"nll": 0.
|
| 545 |
-
"brier": 0.
|
| 546 |
-
"ece": 0.
|
| 547 |
-
"aurc": 0.
|
| 548 |
-
"acc_at_80": 0.
|
| 549 |
-
"acc_at_50": 0.
|
| 550 |
"chance": 0.3333333333333333,
|
| 551 |
-
"mean_conf": 0.
|
| 552 |
-
"sec":
|
| 553 |
"heldout": false
|
| 554 |
},
|
| 555 |
"rte": {
|
| 556 |
"n": 277,
|
| 557 |
-
"acc": 0.
|
| 558 |
-
"nll": 0.
|
| 559 |
-
"brier": 0.
|
| 560 |
-
"ece": 0.
|
| 561 |
-
"aurc": 0.
|
| 562 |
-
"acc_at_80": 0.
|
| 563 |
-
"acc_at_50": 0.
|
| 564 |
"chance": 0.5,
|
| 565 |
-
"mean_conf": 0.
|
| 566 |
-
"sec": 0.
|
| 567 |
"heldout": false
|
| 568 |
},
|
| 569 |
"qnli": {
|
| 570 |
"n": 1500,
|
| 571 |
-
"acc": 0.
|
| 572 |
-
"nll": 0.
|
| 573 |
-
"brier": 0.
|
| 574 |
-
"ece": 0.
|
| 575 |
-
"aurc": 0.
|
| 576 |
-
"acc_at_80": 0.
|
| 577 |
-
"acc_at_50": 0.
|
| 578 |
"chance": 0.5,
|
| 579 |
-
"mean_conf": 0.
|
| 580 |
-
"sec":
|
| 581 |
"heldout": false
|
| 582 |
},
|
| 583 |
"qqp": {
|
| 584 |
"n": 1500,
|
| 585 |
-
"acc": 0.
|
| 586 |
-
"nll": 0.
|
| 587 |
-
"brier": 0.
|
| 588 |
-
"ece": 0.
|
| 589 |
-
"aurc": 0.
|
| 590 |
-
"acc_at_80": 0.
|
| 591 |
-
"acc_at_50": 0.
|
| 592 |
"chance": 0.5,
|
| 593 |
-
"mean_conf": 0.
|
| 594 |
-
"sec":
|
| 595 |
"heldout": false
|
| 596 |
},
|
| 597 |
"mrpc": {
|
| 598 |
"n": 408,
|
| 599 |
-
"acc": 0.
|
| 600 |
-
"nll": 0.
|
| 601 |
-
"brier": 0.
|
| 602 |
-
"ece": 0.
|
| 603 |
-
"aurc": 0.
|
| 604 |
-
"acc_at_80": 0.
|
| 605 |
-
"acc_at_50": 0.
|
| 606 |
"chance": 0.5,
|
| 607 |
-
"mean_conf": 0.
|
| 608 |
-
"sec": 0.
|
| 609 |
"heldout": false
|
| 610 |
},
|
| 611 |
"paws": {
|
| 612 |
"n": 1500,
|
| 613 |
-
"acc": 0.
|
| 614 |
-
"nll": 0.
|
| 615 |
-
"brier": 0.
|
| 616 |
-
"ece": 0.
|
| 617 |
-
"aurc": 0.
|
| 618 |
-
"acc_at_80": 0.
|
| 619 |
-
"acc_at_50": 0.
|
| 620 |
"chance": 0.5,
|
| 621 |
-
"mean_conf": 0.
|
| 622 |
-
"sec":
|
| 623 |
"heldout": true
|
| 624 |
},
|
| 625 |
"cola": {
|
| 626 |
"n": 1043,
|
| 627 |
-
"acc": 0.
|
| 628 |
-
"nll": 0.
|
| 629 |
-
"brier": 0.
|
| 630 |
-
"ece": 0.
|
| 631 |
-
"aurc": 0.
|
| 632 |
-
"acc_at_80": 0.
|
| 633 |
-
"acc_at_50": 0.
|
| 634 |
"chance": 0.5,
|
| 635 |
-
"mean_conf": 0.
|
| 636 |
-
"sec":
|
| 637 |
"heldout": false
|
| 638 |
},
|
| 639 |
"boolq": {
|
| 640 |
"n": 1500,
|
| 641 |
-
"acc": 0.
|
| 642 |
-
"nll": 0.
|
| 643 |
-
"brier": 0.
|
| 644 |
-
"ece": 0.
|
| 645 |
-
"aurc": 0.
|
| 646 |
-
"acc_at_80": 0.
|
| 647 |
-
"acc_at_50": 0.
|
| 648 |
"chance": 0.5,
|
| 649 |
-
"mean_conf": 0.
|
| 650 |
-
"sec":
|
| 651 |
"heldout": false
|
| 652 |
},
|
| 653 |
"strategyqa": {
|
| 654 |
"n": 687,
|
| 655 |
-
"acc": 0.
|
| 656 |
-
"nll": 0.
|
| 657 |
-
"brier": 0.
|
| 658 |
-
"ece": 0.
|
| 659 |
-
"aurc": 0.
|
| 660 |
-
"acc_at_80": 0.
|
| 661 |
-
"acc_at_50": 0.
|
| 662 |
"chance": 0.5,
|
| 663 |
-
"mean_conf": 0.
|
| 664 |
-
"sec":
|
| 665 |
"heldout": true
|
| 666 |
},
|
| 667 |
"pubmedqa": {
|
| 668 |
"n": 500,
|
| 669 |
-
"acc": 0.
|
| 670 |
-
"nll": 0.
|
| 671 |
-
"brier": 0.
|
| 672 |
-
"ece": 0.
|
| 673 |
-
"aurc": 0.
|
| 674 |
-
"acc_at_80": 0.
|
| 675 |
-
"acc_at_50": 0.
|
| 676 |
"chance": 0.33333333333333326,
|
| 677 |
-
"mean_conf": 0.
|
| 678 |
-
"sec":
|
| 679 |
"heldout": true
|
| 680 |
},
|
| 681 |
"arc": {
|
| 682 |
"n": 1172,
|
| 683 |
-
"acc": 0.
|
| 684 |
-
"nll": 0.
|
| 685 |
-
"brier": 0.
|
| 686 |
-
"ece": 0.
|
| 687 |
-
"aurc": 0.
|
| 688 |
-
"acc_at_80": 0.
|
| 689 |
-
"acc_at_50": 0.
|
| 690 |
"chance": 0.25015642775881686,
|
| 691 |
-
"mean_conf": 0.
|
| 692 |
-
"sec":
|
| 693 |
"heldout": false
|
| 694 |
},
|
| 695 |
"commonsense_qa": {
|
| 696 |
"n": 1221,
|
| 697 |
-
"acc": 0.
|
| 698 |
-
"nll": 0.
|
| 699 |
-
"brier": 0.
|
| 700 |
-
"ece": 0.
|
| 701 |
-
"aurc": 0.
|
| 702 |
-
"acc_at_80": 0.
|
| 703 |
-
"acc_at_50": 0.
|
| 704 |
"chance": 0.19999999999999998,
|
| 705 |
-
"mean_conf": 0.
|
| 706 |
-
"sec":
|
| 707 |
"heldout": false
|
| 708 |
},
|
| 709 |
"qasc": {
|
| 710 |
"n": 926,
|
| 711 |
-
"acc": 0.
|
| 712 |
-
"nll": 0.
|
| 713 |
-
"brier": 0.
|
| 714 |
-
"ece": 0.
|
| 715 |
-
"aurc": 0.
|
| 716 |
-
"acc_at_80": 0.
|
| 717 |
-
"acc_at_50": 0.
|
| 718 |
"chance": 0.125,
|
| 719 |
-
"mean_conf": 0.
|
| 720 |
-
"sec":
|
| 721 |
"heldout": false
|
| 722 |
},
|
| 723 |
"openbookqa": {
|
| 724 |
"n": 500,
|
| 725 |
-
"acc": 0.
|
| 726 |
-
"nll": 0.
|
| 727 |
-
"brier": 0.
|
| 728 |
-
"ece": 0.
|
| 729 |
-
"aurc": 0.
|
| 730 |
-
"acc_at_80": 0.
|
| 731 |
-
"acc_at_50": 0.
|
| 732 |
"chance": 0.25,
|
| 733 |
-
"mean_conf": 0.
|
| 734 |
-
"sec": 0.
|
| 735 |
"heldout": false
|
| 736 |
},
|
| 737 |
"sciq": {
|
| 738 |
"n": 1000,
|
| 739 |
-
"acc": 0.
|
| 740 |
-
"nll": 0.
|
| 741 |
-
"brier": 0.
|
| 742 |
-
"ece": 0.
|
| 743 |
-
"aurc": 0.
|
| 744 |
"acc_at_80": 1.0,
|
| 745 |
"acc_at_50": 1.0,
|
| 746 |
"chance": 0.25,
|
| 747 |
-
"mean_conf": 0.
|
| 748 |
-
"sec":
|
| 749 |
"heldout": true
|
| 750 |
},
|
| 751 |
"hellaswag": {
|
| 752 |
"n": 1500,
|
| 753 |
-
"acc": 0.
|
| 754 |
-
"nll": 0.
|
| 755 |
-
"brier": 0.
|
| 756 |
-
"ece": 0.
|
| 757 |
-
"aurc": 0.
|
| 758 |
-
"acc_at_80": 0.
|
| 759 |
-
"acc_at_50": 0.
|
| 760 |
"chance": 0.25,
|
| 761 |
-
"mean_conf": 0.
|
| 762 |
-
"sec":
|
| 763 |
"heldout": false
|
| 764 |
},
|
| 765 |
"piqa": {
|
| 766 |
"n": 1500,
|
| 767 |
-
"acc": 0.
|
| 768 |
-
"nll": 0.
|
| 769 |
-
"brier": 0.
|
| 770 |
-
"ece": 0.
|
| 771 |
-
"aurc": 0.
|
| 772 |
-
"acc_at_80": 0.
|
| 773 |
"acc_at_50": 0.9506666666666667,
|
| 774 |
"chance": 0.5,
|
| 775 |
-
"mean_conf": 0.
|
| 776 |
-
"sec":
|
| 777 |
"heldout": false
|
| 778 |
},
|
| 779 |
"social_iqa": {
|
| 780 |
"n": 1500,
|
| 781 |
-
"acc": 0.
|
| 782 |
-
"nll": 0.
|
| 783 |
-
"brier": 0.
|
| 784 |
-
"ece": 0.
|
| 785 |
-
"aurc": 0.
|
| 786 |
-
"acc_at_80": 0.
|
| 787 |
-
"acc_at_50": 0.
|
| 788 |
"chance": 0.3333333333333333,
|
| 789 |
-
"mean_conf": 0.
|
| 790 |
-
"sec":
|
| 791 |
"heldout": true
|
| 792 |
},
|
| 793 |
"winogrande": {
|
| 794 |
"n": 1267,
|
| 795 |
-
"acc": 0.
|
| 796 |
-
"nll": 0.
|
| 797 |
-
"brier": 0.
|
| 798 |
-
"ece": 0.
|
| 799 |
-
"aurc": 0.
|
| 800 |
-
"acc_at_80": 0.
|
| 801 |
-
"acc_at_50": 0.
|
| 802 |
"chance": 0.5,
|
| 803 |
-
"mean_conf": 0.
|
| 804 |
-
"sec":
|
| 805 |
"heldout": false
|
| 806 |
},
|
| 807 |
"race": {
|
| 808 |
"n": 1500,
|
| 809 |
-
"acc": 0.
|
| 810 |
-
"nll": 0.
|
| 811 |
-
"brier": 0.
|
| 812 |
-
"ece": 0.
|
| 813 |
-
"aurc": 0.
|
| 814 |
-
"acc_at_80": 0.
|
| 815 |
-
"acc_at_50": 0.
|
| 816 |
"chance": 0.25,
|
| 817 |
-
"mean_conf": 0.
|
| 818 |
-
"sec":
|
| 819 |
"heldout": false
|
| 820 |
},
|
| 821 |
"mmlu": {
|
| 822 |
"n": 1500,
|
| 823 |
-
"acc": 0.
|
| 824 |
-
"nll": 0.
|
| 825 |
-
"brier": 0.
|
| 826 |
-
"ece": 0.
|
| 827 |
-
"aurc": 0.
|
| 828 |
-
"acc_at_80": 0.
|
| 829 |
-
"acc_at_50": 0.
|
| 830 |
"chance": 0.25,
|
| 831 |
-
"mean_conf": 0.
|
| 832 |
-
"sec":
|
| 833 |
"heldout": false
|
| 834 |
},
|
| 835 |
"medqa": {
|
| 836 |
"n": 1273,
|
| 837 |
-
"acc": 0.
|
| 838 |
-
"nll": 1.
|
| 839 |
-
"brier": 0.
|
| 840 |
-
"ece": 0.
|
| 841 |
-
"aurc": 0.
|
| 842 |
-
"acc_at_80": 0.
|
| 843 |
-
"acc_at_50": 0.
|
| 844 |
"chance": 0.25,
|
| 845 |
-
"mean_conf": 0.
|
| 846 |
-
"sec":
|
| 847 |
"heldout": false
|
| 848 |
},
|
| 849 |
"truthfulqa": {
|
| 850 |
"n": 817,
|
| 851 |
-
"acc": 0.
|
| 852 |
-
"nll": 1.
|
| 853 |
-
"brier": 0.
|
| 854 |
-
"ece": 0.
|
| 855 |
-
"aurc": 0.
|
| 856 |
-
"acc_at_80": 0.
|
| 857 |
-
"acc_at_50": 0.
|
| 858 |
"chance": 0.22622350449767833,
|
| 859 |
-
"mean_conf": 0.
|
| 860 |
-
"sec":
|
| 861 |
"heldout": true
|
| 862 |
},
|
| 863 |
"fin_phrasebank": {
|
| 864 |
"n": 970,
|
| 865 |
-
"acc": 0.
|
| 866 |
-
"nll": 0.
|
| 867 |
-
"brier": 0.
|
| 868 |
-
"ece": 0.
|
| 869 |
-
"aurc": 0.
|
| 870 |
-
"acc_at_80": 0.
|
| 871 |
-
"acc_at_50": 0.
|
| 872 |
"chance": 0.33333333333333326,
|
| 873 |
-
"mean_conf": 0.
|
| 874 |
-
"sec":
|
| 875 |
"heldout": true
|
| 876 |
},
|
| 877 |
"banking77": {
|
| 878 |
"n": 1500,
|
| 879 |
-
"acc": 0.
|
| 880 |
-
"nll": 0.
|
| 881 |
-
"brier": 0.
|
| 882 |
-
"ece": 0.
|
| 883 |
-
"aurc": 0.
|
| 884 |
-
"acc_at_80": 0.
|
| 885 |
"acc_at_50": 1.0,
|
| 886 |
"chance": 0.1,
|
| 887 |
-
"mean_conf": 0.
|
| 888 |
-
"sec":
|
| 889 |
"heldout": false
|
| 890 |
},
|
| 891 |
"bias_in_bios": {
|
| 892 |
"n": 3000,
|
| 893 |
-
"acc": 0.
|
| 894 |
-
"nll": 0.
|
| 895 |
-
"brier": 0.
|
| 896 |
-
"ece": 0.
|
| 897 |
-
"aurc": 0.
|
| 898 |
-
"acc_at_80": 0.
|
| 899 |
"acc_at_50": 1.0,
|
| 900 |
"chance": 0.30000000000000004,
|
| 901 |
-
"mean_conf": 0.
|
| 902 |
-
"sec":
|
| 903 |
"heldout": false,
|
| 904 |
"per_q": [
|
| 905 |
-
0.
|
| 906 |
0.9973333333333333
|
| 907 |
]
|
| 908 |
},
|
| 909 |
"helpsteer2": {
|
| 910 |
"n": 5190,
|
| 911 |
-
"acc": 0.
|
| 912 |
-
"nll": 0.
|
| 913 |
-
"brier": 0.
|
| 914 |
-
"ece": 0.
|
| 915 |
-
"aurc": 0.
|
| 916 |
-
"acc_at_80": 0.
|
| 917 |
-
"acc_at_50": 0.
|
| 918 |
"chance": 0.2,
|
| 919 |
-
"mean_conf": 0.
|
| 920 |
-
"sec":
|
| 921 |
"heldout": false,
|
| 922 |
"per_q": [
|
| 923 |
-
0.
|
| 924 |
-
0.
|
| 925 |
-
0.
|
| 926 |
-
0.
|
| 927 |
-
0.
|
| 928 |
]
|
| 929 |
},
|
| 930 |
"helpsteer3_pref": {
|
| 931 |
"n": 1176,
|
| 932 |
-
"acc": 0.
|
| 933 |
-
"nll": 1.
|
| 934 |
-
"brier": 0.
|
| 935 |
-
"ece": 0.
|
| 936 |
-
"aurc": 0.
|
| 937 |
-
"acc_at_80": 0.
|
| 938 |
-
"acc_at_50": 0.
|
| 939 |
"chance": 0.14285714285714282,
|
| 940 |
-
"mean_conf": 0.
|
| 941 |
-
"sec":
|
| 942 |
"heldout": false
|
| 943 |
},
|
| 944 |
"hate_speech_scales": {
|
| 945 |
"n": 7500,
|
| 946 |
-
"acc": 0.
|
| 947 |
-
"nll": 0.
|
| 948 |
-
"brier": 0.
|
| 949 |
-
"ece": 0.
|
| 950 |
-
"aurc": 0.
|
| 951 |
-
"acc_at_80": 0.
|
| 952 |
-
"acc_at_50": 0.
|
| 953 |
"chance": 0.22666666666666674,
|
| 954 |
-
"mean_conf": 0.
|
| 955 |
-
"sec":
|
| 956 |
"heldout": false,
|
| 957 |
"per_q": [
|
| 958 |
-
0.
|
| 959 |
-
0.
|
| 960 |
-
0.
|
| 961 |
0.578,
|
| 962 |
-
0.
|
| 963 |
]
|
| 964 |
},
|
| 965 |
"liar2": {
|
| 966 |
"n": 1500,
|
| 967 |
-
"acc": 0.
|
| 968 |
-
"nll": 1.
|
| 969 |
-
"brier": 0.
|
| 970 |
-
"ece": 0.
|
| 971 |
-
"aurc": 0.
|
| 972 |
-
"acc_at_80": 0.
|
| 973 |
"acc_at_50": 0.48933333333333334,
|
| 974 |
"chance": 0.16666666666666666,
|
| 975 |
-
"mean_conf": 0.
|
| 976 |
-
"sec":
|
| 977 |
"heldout": false
|
| 978 |
},
|
| 979 |
"prosocial_safety": {
|
| 980 |
"n": 1500,
|
| 981 |
-
"acc": 0.
|
| 982 |
-
"nll": 1.
|
| 983 |
-
"brier": 0.
|
| 984 |
-
"ece": 0.
|
| 985 |
-
"aurc": 0.
|
| 986 |
-
"acc_at_80": 0.
|
| 987 |
-
"acc_at_50": 0.
|
| 988 |
"chance": 0.2,
|
| 989 |
-
"mean_conf": 0.
|
| 990 |
-
"sec":
|
| 991 |
"heldout": false
|
| 992 |
},
|
| 993 |
"ultrafeedback_pref": {
|
| 994 |
"n": 1500,
|
| 995 |
-
"acc": 0.
|
| 996 |
-
"nll": 0.
|
| 997 |
-
"brier": 0.
|
| 998 |
-
"ece": 0.
|
| 999 |
-
"aurc": 0.
|
| 1000 |
-
"acc_at_80": 0.
|
| 1001 |
-
"acc_at_50": 0.
|
| 1002 |
"chance": 0.5,
|
| 1003 |
-
"mean_conf": 0.
|
| 1004 |
-
"sec":
|
| 1005 |
"heldout": false
|
| 1006 |
},
|
| 1007 |
"shp": {
|
| 1008 |
"n": 1500,
|
| 1009 |
-
"acc": 0.
|
| 1010 |
-
"nll": 0.
|
| 1011 |
-
"brier": 0.
|
| 1012 |
-
"ece": 0.
|
| 1013 |
-
"aurc": 0.
|
| 1014 |
-
"acc_at_80": 0.
|
| 1015 |
-
"acc_at_50": 0.
|
| 1016 |
"chance": 0.5,
|
| 1017 |
-
"mean_conf": 0.
|
| 1018 |
-
"sec":
|
| 1019 |
"heldout": false
|
| 1020 |
},
|
| 1021 |
"hh_rlhf": {
|
| 1022 |
"n": 1488,
|
| 1023 |
-
"acc": 0.
|
| 1024 |
-
"nll": 0.
|
| 1025 |
-
"brier": 0.
|
| 1026 |
-
"ece": 0.
|
| 1027 |
-
"aurc": 0.
|
| 1028 |
-
"acc_at_80": 0.
|
| 1029 |
-
"acc_at_50": 0.
|
| 1030 |
"chance": 0.5,
|
| 1031 |
-
"mean_conf": 0.
|
| 1032 |
-
"sec":
|
| 1033 |
"heldout": false
|
| 1034 |
},
|
| 1035 |
"arena_pref": {
|
| 1036 |
"n": 1500,
|
| 1037 |
-
"acc": 0.
|
| 1038 |
-
"nll": 1.
|
| 1039 |
-
"brier": 0.
|
| 1040 |
-
"ece": 0.
|
| 1041 |
-
"aurc": 0.
|
| 1042 |
-
"acc_at_80": 0.
|
| 1043 |
-
"acc_at_50": 0.
|
| 1044 |
"chance": 0.3333333333333333,
|
| 1045 |
-
"mean_conf": 0.
|
| 1046 |
-
"sec":
|
| 1047 |
"heldout": true
|
| 1048 |
},
|
| 1049 |
"reward_bench": {
|
| 1050 |
"n": 1500,
|
| 1051 |
-
"acc": 0.
|
| 1052 |
-
"nll": 0.
|
| 1053 |
-
"brier": 0.
|
| 1054 |
-
"ece": 0.
|
| 1055 |
-
"aurc": 0.
|
| 1056 |
-
"acc_at_80": 0.
|
| 1057 |
-
"acc_at_50": 0.
|
| 1058 |
"chance": 0.5,
|
| 1059 |
-
"mean_conf": 0.
|
| 1060 |
-
"sec":
|
| 1061 |
"heldout": true
|
| 1062 |
},
|
| 1063 |
"glaive_tools": {
|
| 1064 |
"n": 1348,
|
| 1065 |
"acc": 0.9473293768545994,
|
| 1066 |
-
"nll": 0.
|
| 1067 |
-
"brier": 0.
|
| 1068 |
-
"ece": 0.
|
| 1069 |
-
"aurc": 0.
|
| 1070 |
-
"acc_at_80": 0.
|
| 1071 |
-
"acc_at_50": 0.
|
| 1072 |
"chance": 0.16666666666666666,
|
| 1073 |
-
"mean_conf": 0.
|
| 1074 |
-
"sec":
|
| 1075 |
"heldout": false
|
| 1076 |
},
|
| 1077 |
"hermes_tools": {
|
| 1078 |
"n": 1500,
|
| 1079 |
-
"acc": 0.
|
| 1080 |
-
"nll": 0.
|
| 1081 |
-
"brier": 0.
|
| 1082 |
-
"ece": 0.
|
| 1083 |
-
"aurc": 0.
|
| 1084 |
-
"acc_at_80": 0.
|
| 1085 |
-
"acc_at_50": 0.
|
| 1086 |
"chance": 0.125,
|
| 1087 |
-
"mean_conf": 0.
|
| 1088 |
-
"sec":
|
| 1089 |
"heldout": true
|
| 1090 |
},
|
| 1091 |
"copa": {
|
| 1092 |
"n": 100,
|
| 1093 |
-
"acc": 0.
|
| 1094 |
-
"nll": 0.
|
| 1095 |
-
"brier": 0.
|
| 1096 |
-
"ece": 0.
|
| 1097 |
-
"aurc": 0.
|
| 1098 |
-
"acc_at_80": 0.
|
| 1099 |
"acc_at_50": 0.98,
|
| 1100 |
"chance": 0.5,
|
| 1101 |
-
"mean_conf": 0.
|
| 1102 |
-
"sec":
|
| 1103 |
"heldout": false
|
| 1104 |
},
|
| 1105 |
"wic": {
|
| 1106 |
"n": 638,
|
| 1107 |
-
"acc": 0.
|
| 1108 |
-
"nll": 0.
|
| 1109 |
-
"brier": 0.
|
| 1110 |
-
"ece": 0.
|
| 1111 |
-
"aurc": 0.
|
| 1112 |
-
"acc_at_80": 0.
|
| 1113 |
-
"acc_at_50": 0.
|
| 1114 |
"chance": 0.5,
|
| 1115 |
-
"mean_conf": 0.
|
| 1116 |
-
"sec":
|
| 1117 |
"heldout": false
|
| 1118 |
},
|
| 1119 |
"multirc": {
|
| 1120 |
"n": 1500,
|
| 1121 |
-
"acc": 0.
|
| 1122 |
-
"nll": 0.
|
| 1123 |
-
"brier": 0.
|
| 1124 |
-
"ece": 0.
|
| 1125 |
-
"aurc": 0.
|
| 1126 |
-
"acc_at_80": 0.
|
| 1127 |
-
"acc_at_50": 0.
|
| 1128 |
"chance": 0.5,
|
| 1129 |
-
"mean_conf": 0.
|
| 1130 |
-
"sec":
|
| 1131 |
"heldout": false
|
| 1132 |
},
|
| 1133 |
"cb": {
|
| 1134 |
"n": 56,
|
| 1135 |
"acc": 0.8928571428571429,
|
| 1136 |
-
"nll": 0.
|
| 1137 |
-
"brier": 0.
|
| 1138 |
-
"ece": 0.
|
| 1139 |
-
"aurc": 0.
|
| 1140 |
"acc_at_80": 0.9555555555555556,
|
| 1141 |
"acc_at_50": 0.9642857142857143,
|
| 1142 |
"chance": 0.3333333333333333,
|
| 1143 |
-
"mean_conf": 0.
|
| 1144 |
-
"sec": 0.
|
| 1145 |
"heldout": true
|
| 1146 |
},
|
| 1147 |
"fever": {
|
| 1148 |
"n": 1500,
|
| 1149 |
-
"acc": 0.
|
| 1150 |
-
"nll": 0.
|
| 1151 |
-
"brier": 0.
|
| 1152 |
-
"ece": 0.
|
| 1153 |
-
"aurc": 0.
|
| 1154 |
-
"acc_at_80": 0.
|
| 1155 |
"acc_at_50": 0.972,
|
| 1156 |
"chance": 0.3333333333333333,
|
| 1157 |
-
"mean_conf": 0.
|
| 1158 |
-
"sec":
|
| 1159 |
"heldout": false
|
| 1160 |
},
|
| 1161 |
"wiki_qa": {
|
| 1162 |
"n": 879,
|
| 1163 |
-
"acc": 0.
|
| 1164 |
-
"nll": 0.
|
| 1165 |
-
"brier": 0.
|
| 1166 |
-
"ece": 0.
|
| 1167 |
-
"aurc": 0.
|
| 1168 |
-
"acc_at_80": 0.
|
| 1169 |
-
"acc_at_50": 0.
|
| 1170 |
"chance": 0.5,
|
| 1171 |
-
"mean_conf": 0.
|
| 1172 |
-
"sec":
|
| 1173 |
"heldout": false
|
| 1174 |
},
|
| 1175 |
"msmarco_rel": {
|
| 1176 |
"n": 1446,
|
| 1177 |
-
"acc": 0.
|
| 1178 |
-
"nll": 0.
|
| 1179 |
-
"brier": 0.
|
| 1180 |
-
"ece": 0.
|
| 1181 |
-
"aurc": 0.
|
| 1182 |
-
"acc_at_80": 0.
|
| 1183 |
-
"acc_at_50": 0.
|
| 1184 |
"chance": 0.5,
|
| 1185 |
-
"mean_conf": 0.
|
| 1186 |
-
"sec":
|
| 1187 |
"heldout": false
|
| 1188 |
},
|
| 1189 |
"medmcqa": {
|
| 1190 |
"n": 1500,
|
| 1191 |
-
"acc": 0.
|
| 1192 |
-
"nll": 1.
|
| 1193 |
-
"brier": 0.
|
| 1194 |
-
"ece": 0.
|
| 1195 |
-
"aurc": 0.
|
| 1196 |
-
"acc_at_80": 0.
|
| 1197 |
-
"acc_at_50": 0.
|
| 1198 |
"chance": 0.25,
|
| 1199 |
-
"mean_conf": 0.
|
| 1200 |
-
"sec":
|
| 1201 |
"heldout": false
|
| 1202 |
},
|
| 1203 |
"quality": {
|
| 1204 |
"n": 1500,
|
| 1205 |
-
"acc": 0.
|
| 1206 |
-
"nll": 1.
|
| 1207 |
-
"brier": 0.
|
| 1208 |
-
"ece": 0.
|
| 1209 |
-
"aurc": 0.
|
| 1210 |
-
"acc_at_80": 0.
|
| 1211 |
-
"acc_at_50": 0.
|
| 1212 |
"chance": 0.25,
|
| 1213 |
-
"mean_conf": 0.
|
| 1214 |
-
"sec":
|
| 1215 |
"heldout": true
|
| 1216 |
},
|
| 1217 |
"xstory_cloze": {
|
| 1218 |
"n": 1500,
|
| 1219 |
-
"acc": 0.
|
| 1220 |
-
"nll": 0.
|
| 1221 |
-
"brier": 0.
|
| 1222 |
-
"ece": 0.
|
| 1223 |
-
"aurc": 0.
|
| 1224 |
"acc_at_80": 0.9966666666666667,
|
| 1225 |
-
"acc_at_50": 0.
|
| 1226 |
"chance": 0.5,
|
| 1227 |
-
"mean_conf": 0.
|
| 1228 |
-
"sec":
|
| 1229 |
"heldout": true
|
| 1230 |
},
|
| 1231 |
"abstain_probe": {
|
| 1232 |
"n": 1500,
|
| 1233 |
-
"acc": 0.
|
| 1234 |
-
"nll":
|
| 1235 |
-
"brier": 0.
|
| 1236 |
-
"ece": 0.
|
| 1237 |
-
"aurc": 0.
|
| 1238 |
-
"acc_at_80": 0.
|
| 1239 |
-
"acc_at_50": 0.
|
| 1240 |
"chance": 0.17950317460317464,
|
| 1241 |
-
"mean_conf": 0.
|
| 1242 |
-
"sec":
|
| 1243 |
"heldout": true
|
| 1244 |
},
|
| 1245 |
"toolace": {
|
| 1246 |
"n": 1000,
|
| 1247 |
-
"acc": 0.
|
| 1248 |
-
"nll": 0.
|
| 1249 |
-
"brier": 0.
|
| 1250 |
-
"ece": 0.
|
| 1251 |
-
"aurc": 0.
|
| 1252 |
-
"acc_at_80": 0.
|
| 1253 |
-
"acc_at_50": 0.
|
| 1254 |
"chance": 0.12470555555555554,
|
| 1255 |
-
"mean_conf": 0.
|
| 1256 |
-
"sec":
|
| 1257 |
"heldout": false
|
| 1258 |
},
|
| 1259 |
"agenttraj": {
|
| 1260 |
"n": 1500,
|
| 1261 |
-
"acc": 0.
|
| 1262 |
-
"nll": 0.
|
| 1263 |
-
"brier": 0.
|
| 1264 |
-
"ece": 0.
|
| 1265 |
-
"aurc": 0.
|
| 1266 |
"acc_at_80": 0.9891666666666666,
|
| 1267 |
-
"acc_at_50":
|
| 1268 |
"chance": 0.2,
|
| 1269 |
-
"mean_conf": 0.
|
| 1270 |
-
"sec":
|
| 1271 |
"heldout": false
|
| 1272 |
},
|
| 1273 |
"mind2web": {
|
| 1274 |
"n": 1500,
|
| 1275 |
-
"acc": 0.
|
| 1276 |
-
"nll": 0.
|
| 1277 |
-
"brier": 0.
|
| 1278 |
-
"ece": 0.
|
| 1279 |
-
"aurc": 0.
|
| 1280 |
-
"acc_at_80": 0.
|
| 1281 |
-
"acc_at_50": 0.
|
| 1282 |
"chance": 0.16666666666666666,
|
| 1283 |
-
"mean_conf": 0.
|
| 1284 |
-
"sec":
|
| 1285 |
"heldout": false
|
| 1286 |
},
|
| 1287 |
"synth": {
|
| 1288 |
"n": 300,
|
| 1289 |
-
"acc": 0.
|
| 1290 |
-
"nll": 0.
|
| 1291 |
-
"brier": 0.
|
| 1292 |
-
"ece": 0.
|
| 1293 |
-
"aurc": 0.
|
| 1294 |
-
"acc_at_80": 0.
|
| 1295 |
-
"acc_at_50": 0.
|
| 1296 |
"chance": 0.37149999999999994,
|
| 1297 |
-
"mean_conf": 0.
|
| 1298 |
-
"sec": 0.
|
| 1299 |
"heldout": false,
|
| 1300 |
"per_q": [
|
| 1301 |
-
0.
|
| 1302 |
-
0.
|
| 1303 |
]
|
| 1304 |
},
|
| 1305 |
"games": {
|
| 1306 |
"n": 500,
|
| 1307 |
-
"acc":
|
| 1308 |
-
"nll": 0.
|
| 1309 |
-
"brier": 0.
|
| 1310 |
-
"ece": 0.
|
| 1311 |
-
"aurc":
|
| 1312 |
"acc_at_80": 1.0,
|
| 1313 |
"acc_at_50": 1.0,
|
| 1314 |
"chance": 0.2885,
|
| 1315 |
-
"mean_conf": 0.
|
| 1316 |
-
"sec":
|
| 1317 |
"heldout": false
|
| 1318 |
},
|
| 1319 |
"mario": {
|
| 1320 |
"n": 276,
|
| 1321 |
-
"acc":
|
| 1322 |
-
"nll": 0.
|
| 1323 |
-
"brier": 0.
|
| 1324 |
-
"ece": 0.
|
| 1325 |
-
"aurc":
|
| 1326 |
"acc_at_80": 1.0,
|
| 1327 |
"acc_at_50": 1.0,
|
| 1328 |
"chance": 0.3333333333333333,
|
| 1329 |
-
"mean_conf": 0.
|
| 1330 |
-
"sec":
|
| 1331 |
"heldout": false,
|
| 1332 |
"per_q": [
|
| 1333 |
-
|
| 1334 |
1.0
|
| 1335 |
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1336 |
}
|
| 1337 |
},
|
| 1338 |
"agg": {
|
| 1339 |
"in_task": {
|
| 1340 |
-
"acc": 0.
|
| 1341 |
-
"nll": 0.
|
| 1342 |
-
"brier": 0.
|
| 1343 |
-
"ece": 0.
|
| 1344 |
-
"aurc": 0.
|
| 1345 |
-
"acc_at_80": 0.
|
| 1346 |
"chance": 0.32498304691713953
|
| 1347 |
},
|
| 1348 |
"heldout": {
|
| 1349 |
-
"acc": 0.
|
| 1350 |
-
"nll": 0.
|
| 1351 |
-
"brier": 0.
|
| 1352 |
-
"ece": 0.
|
| 1353 |
-
"aurc": 0.
|
| 1354 |
-
"acc_at_80": 0.
|
| 1355 |
-
"chance": 0.
|
| 1356 |
},
|
| 1357 |
"n_in": 69,
|
| 1358 |
-
"n_heldout":
|
| 1359 |
},
|
| 1360 |
-
"model": "runs/
|
| 1361 |
"engine": "compile"
|
| 1362 |
}
|
|
|
|
| 2 |
"results": {
|
| 3 |
"clinc_oos": {
|
| 4 |
"n": 1500,
|
| 5 |
+
"acc": 0.9613333333333334,
|
| 6 |
+
"nll": 0.1350308209657669,
|
| 7 |
+
"brier": 0.05826561525464058,
|
| 8 |
+
"ece": 0.01548567197720209,
|
| 9 |
+
"aurc": 0.0036533645736265955,
|
| 10 |
+
"acc_at_80": 0.9958333333333333,
|
| 11 |
+
"acc_at_50": 0.9986666666666667,
|
| 12 |
"chance": 0.1,
|
| 13 |
+
"mean_conf": 0.971788763999939,
|
| 14 |
+
"sec": 14.3,
|
| 15 |
"heldout": false
|
| 16 |
},
|
| 17 |
"massive_intent": {
|
| 18 |
"n": 1500,
|
| 19 |
+
"acc": 0.9506666666666667,
|
| 20 |
+
"nll": 0.14456188678741455,
|
| 21 |
+
"brier": 0.07078584283590317,
|
| 22 |
+
"ece": 0.0097324760754903,
|
| 23 |
+
"aurc": 0.004686208748570398,
|
| 24 |
+
"acc_at_80": 0.9941666666666666,
|
| 25 |
+
"acc_at_50": 0.9986666666666667,
|
| 26 |
"chance": 0.1,
|
| 27 |
+
"mean_conf": 0.9509131908416748,
|
| 28 |
+
"sec": 3.9,
|
| 29 |
"heldout": false
|
| 30 |
},
|
| 31 |
"massive_scenario": {
|
| 32 |
"n": 1500,
|
| 33 |
+
"acc": 0.7866666666666666,
|
| 34 |
+
"nll": 0.6393386125564575,
|
| 35 |
+
"brier": 0.29952406883239746,
|
| 36 |
+
"ece": 0.04220357580979665,
|
| 37 |
+
"aurc": 0.062301248078291196,
|
| 38 |
+
"acc_at_80": 0.8675,
|
| 39 |
+
"acc_at_50": 0.9706666666666667,
|
| 40 |
"chance": 0.1,
|
| 41 |
+
"mean_conf": 0.8156749606132507,
|
| 42 |
"sec": 1.5,
|
| 43 |
"heldout": true
|
| 44 |
},
|
| 45 |
"bitext_support": {
|
| 46 |
"n": 3000,
|
| 47 |
+
"acc": 0.9976666666666667,
|
| 48 |
+
"nll": 0.010479671880602837,
|
| 49 |
+
"brier": 0.0043285866267979145,
|
| 50 |
+
"ece": 0.0017144261995951603,
|
| 51 |
+
"aurc": 0.0001253647229479039,
|
| 52 |
+
"acc_at_80": 0.9995833333333334,
|
| 53 |
"acc_at_50": 1.0,
|
| 54 |
"chance": 0.09999999999999998,
|
| 55 |
+
"mean_conf": 0.9976046681404114,
|
| 56 |
"sec": 2.1,
|
| 57 |
"heldout": false,
|
| 58 |
"per_q": [
|
| 59 |
0.9986666666666667,
|
| 60 |
+
0.9966666666666667
|
| 61 |
]
|
| 62 |
},
|
| 63 |
"support_tickets": {
|
| 64 |
"n": 4500,
|
| 65 |
+
"acc": 0.5755555555555556,
|
| 66 |
+
"nll": 0.9841309785842896,
|
| 67 |
+
"brier": 0.5168883204460144,
|
| 68 |
+
"ece": 0.014961424820952942,
|
| 69 |
+
"aurc": 0.21558989155560015,
|
| 70 |
+
"acc_at_80": 0.6402777777777777,
|
| 71 |
+
"acc_at_50": 0.7546666666666667,
|
| 72 |
"chance": 0.22777777777777777,
|
| 73 |
+
"mean_conf": 0.5705822706222534,
|
| 74 |
+
"sec": 10.1,
|
| 75 |
"heldout": false,
|
| 76 |
"per_q": [
|
| 77 |
+
0.812,
|
| 78 |
+
0.424,
|
| 79 |
+
0.49066666666666664
|
| 80 |
]
|
| 81 |
},
|
| 82 |
"ag_news": {
|
| 83 |
"n": 1500,
|
| 84 |
+
"acc": 0.9186666666666666,
|
| 85 |
+
"nll": 0.2343619018793106,
|
| 86 |
+
"brier": 0.12385667860507965,
|
| 87 |
+
"ece": 0.011591263870398227,
|
| 88 |
+
"aurc": 0.017780534818882282,
|
| 89 |
+
"acc_at_80": 0.9691666666666666,
|
| 90 |
+
"acc_at_50": 0.9906666666666667,
|
| 91 |
"chance": 0.25,
|
| 92 |
+
"mean_conf": 0.9164977073669434,
|
| 93 |
"sec": 1.5,
|
| 94 |
"heldout": false
|
| 95 |
},
|
| 96 |
"dbpedia": {
|
| 97 |
"n": 1500,
|
| 98 |
+
"acc": 0.992,
|
| 99 |
+
"nll": 0.024847088381648064,
|
| 100 |
+
"brier": 0.012629971839487553,
|
| 101 |
+
"ece": 0.004867519597212441,
|
| 102 |
+
"aurc": 0.00010065472533696882,
|
| 103 |
"acc_at_80": 1.0,
|
| 104 |
"acc_at_50": 1.0,
|
| 105 |
"chance": 0.1,
|
| 106 |
+
"mean_conf": 0.9911227822303772,
|
| 107 |
"sec": 2.0,
|
| 108 |
"heldout": false
|
| 109 |
},
|
| 110 |
"yahoo_topics": {
|
| 111 |
"n": 1500,
|
| 112 |
+
"acc": 0.766,
|
| 113 |
+
"nll": 0.7322157621383667,
|
| 114 |
+
"brier": 0.3357123136520386,
|
| 115 |
+
"ece": 0.02381875579555828,
|
| 116 |
+
"aurc": 0.08019171930336874,
|
| 117 |
+
"acc_at_80": 0.8508333333333333,
|
| 118 |
+
"acc_at_50": 0.9413333333333334,
|
| 119 |
"chance": 0.1,
|
| 120 |
+
"mean_conf": 0.7529987096786499,
|
| 121 |
"sec": 1.8,
|
| 122 |
"heldout": false
|
| 123 |
},
|
| 124 |
"newsgroups": {
|
| 125 |
"n": 1462,
|
| 126 |
+
"acc": 0.79890560875513,
|
| 127 |
+
"nll": 0.5369898676872253,
|
| 128 |
+
"brier": 0.2600807249546051,
|
| 129 |
+
"ece": 0.040705675404473,
|
| 130 |
+
"aurc": 0.042875743065342066,
|
| 131 |
+
"acc_at_80": 0.9128205128205128,
|
| 132 |
+
"acc_at_50": 0.987688098495212,
|
| 133 |
"chance": 0.09999999999999999,
|
| 134 |
+
"mean_conf": 0.8376736044883728,
|
| 135 |
+
"sec": 14.0,
|
| 136 |
"heldout": false
|
| 137 |
},
|
| 138 |
"bbc_news": {
|
| 139 |
"n": 1000,
|
| 140 |
+
"acc": 0.937,
|
| 141 |
+
"nll": 0.15569916367530823,
|
| 142 |
+
"brier": 0.09091777354478836,
|
| 143 |
+
"ece": 0.015425997406244282,
|
| 144 |
+
"aurc": 0.007425713401158614,
|
| 145 |
+
"acc_at_80": 0.98625,
|
| 146 |
"acc_at_50": 1.0,
|
| 147 |
"chance": 0.20000000000000004,
|
| 148 |
+
"mean_conf": 0.9392964839935303,
|
| 149 |
"sec": 5.8,
|
| 150 |
"heldout": true
|
| 151 |
},
|
| 152 |
"trec": {
|
| 153 |
"n": 500,
|
| 154 |
+
"acc": 0.8,
|
| 155 |
+
"nll": 0.6379921436309814,
|
| 156 |
+
"brier": 0.3222799003124237,
|
| 157 |
+
"ece": 0.06791729182004927,
|
| 158 |
+
"aurc": 0.10405531504977719,
|
| 159 |
+
"acc_at_80": 0.8425,
|
| 160 |
+
"acc_at_50": 0.892,
|
| 161 |
"chance": 0.16666666666666663,
|
| 162 |
+
"mean_conf": 0.8069738745689392,
|
| 163 |
+
"sec": 2.8,
|
| 164 |
"heldout": true
|
| 165 |
},
|
| 166 |
"student_questions": {
|
| 167 |
"n": 1500,
|
| 168 |
+
"acc": 0.93,
|
| 169 |
+
"nll": 0.21689555048942566,
|
| 170 |
+
"brier": 0.11190912872552872,
|
| 171 |
+
"ece": 0.020858444054921495,
|
| 172 |
+
"aurc": 0.015722714843614413,
|
| 173 |
+
"acc_at_80": 0.9758333333333333,
|
| 174 |
+
"acc_at_50": 0.9893333333333333,
|
| 175 |
"chance": 0.25,
|
| 176 |
+
"mean_conf": 0.9092566967010498,
|
| 177 |
+
"sec": 1.8,
|
| 178 |
"heldout": true
|
| 179 |
},
|
| 180 |
"dolly_category": {
|
| 181 |
"n": 1500,
|
| 182 |
+
"acc": 0.322,
|
| 183 |
+
"nll": 2.024930238723755,
|
| 184 |
+
"brier": 0.8547297120094299,
|
| 185 |
+
"ece": 0.242468265692393,
|
| 186 |
+
"aurc": 0.5258592960293854,
|
| 187 |
+
"acc_at_80": 0.3491666666666667,
|
| 188 |
+
"acc_at_50": 0.428,
|
| 189 |
"chance": 0.125,
|
| 190 |
+
"mean_conf": 0.564468264579773,
|
| 191 |
+
"sec": 2.2,
|
| 192 |
"heldout": true
|
| 193 |
},
|
| 194 |
"imdb": {
|
| 195 |
"n": 1500,
|
| 196 |
"acc": 0.9613333333333334,
|
| 197 |
+
"nll": 0.09483654797077179,
|
| 198 |
+
"brier": 0.05605172738432884,
|
| 199 |
+
"ece": 0.01115041021505996,
|
| 200 |
+
"aurc": 0.0028939979083350527,
|
| 201 |
+
"acc_at_80": 0.9975,
|
| 202 |
"acc_at_50": 1.0,
|
| 203 |
"chance": 0.5,
|
| 204 |
+
"mean_conf": 0.9652077555656433,
|
| 205 |
+
"sec": 3.6,
|
| 206 |
"heldout": false
|
| 207 |
},
|
| 208 |
"sst2": {
|
| 209 |
"n": 872,
|
| 210 |
+
"acc": 0.9438073394495413,
|
| 211 |
+
"nll": 0.15489669144153595,
|
| 212 |
+
"brier": 0.08650284260511398,
|
| 213 |
+
"ece": 0.022252202990951892,
|
| 214 |
+
"aurc": 0.01050770504038895,
|
| 215 |
+
"acc_at_80": 0.9813753581661891,
|
| 216 |
"acc_at_50": 0.9931192660550459,
|
| 217 |
"chance": 0.5,
|
| 218 |
+
"mean_conf": 0.9430466294288635,
|
| 219 |
+
"sec": 3.0,
|
| 220 |
"heldout": false
|
| 221 |
},
|
| 222 |
"sst5": {
|
| 223 |
"n": 1500,
|
| 224 |
+
"acc": 0.6013333333333334,
|
| 225 |
+
"nll": 0.9259645342826843,
|
| 226 |
+
"brier": 0.5310559868812561,
|
| 227 |
+
"ece": 0.02794535907109577,
|
| 228 |
+
"aurc": 0.3189110639202516,
|
| 229 |
+
"acc_at_80": 0.63,
|
| 230 |
+
"acc_at_50": 0.6746666666666666,
|
| 231 |
"chance": 0.2,
|
| 232 |
+
"mean_conf": 0.5887239575386047,
|
| 233 |
+
"sec": 1.2,
|
| 234 |
"heldout": false
|
| 235 |
},
|
| 236 |
"yelp": {
|
| 237 |
"n": 1500,
|
| 238 |
+
"acc": 0.6973333333333334,
|
| 239 |
+
"nll": 0.6948801279067993,
|
| 240 |
+
"brier": 0.4055171310901642,
|
| 241 |
+
"ece": 0.023447723527749403,
|
| 242 |
+
"aurc": 0.1553584409152187,
|
| 243 |
+
"acc_at_80": 0.7533333333333333,
|
| 244 |
+
"acc_at_50": 0.8333333333333334,
|
| 245 |
"chance": 0.2,
|
| 246 |
+
"mean_conf": 0.6991026997566223,
|
| 247 |
+
"sec": 2.9,
|
| 248 |
"heldout": false
|
| 249 |
},
|
| 250 |
"amazon_stars": {
|
| 251 |
"n": 1500,
|
| 252 |
+
"acc": 0.61,
|
| 253 |
+
"nll": 0.903746485710144,
|
| 254 |
+
"brier": 0.501812756061554,
|
| 255 |
+
"ece": 0.02551889550685881,
|
| 256 |
+
"aurc": 0.22928301992632438,
|
| 257 |
+
"acc_at_80": 0.6608333333333334,
|
| 258 |
+
"acc_at_50": 0.756,
|
| 259 |
"chance": 0.2,
|
| 260 |
+
"mean_conf": 0.6187715530395508,
|
| 261 |
+
"sec": 1.6,
|
| 262 |
"heldout": false
|
| 263 |
},
|
| 264 |
"emotion": {
|
| 265 |
"n": 1500,
|
| 266 |
+
"acc": 0.8546666666666667,
|
| 267 |
+
"nll": 0.3901277184486389,
|
| 268 |
+
"brier": 0.20813561975955963,
|
| 269 |
+
"ece": 0.012389385322729728,
|
| 270 |
+
"aurc": 0.035741524192542756,
|
| 271 |
+
"acc_at_80": 0.9275,
|
| 272 |
+
"acc_at_50": 0.98,
|
| 273 |
"chance": 0.16666666666666666,
|
| 274 |
+
"mean_conf": 0.8557289838790894,
|
| 275 |
+
"sec": 1.2,
|
| 276 |
"heldout": false
|
| 277 |
},
|
| 278 |
"go_emotions": {
|
| 279 |
"n": 1500,
|
| 280 |
+
"acc": 0.7866666666666666,
|
| 281 |
+
"nll": 0.633638322353363,
|
| 282 |
+
"brier": 0.30786433815956116,
|
| 283 |
+
"ece": 0.023466816226641336,
|
| 284 |
+
"aurc": 0.07477865198611486,
|
| 285 |
+
"acc_at_80": 0.8633333333333333,
|
| 286 |
+
"acc_at_50": 0.94,
|
| 287 |
"chance": 0.1,
|
| 288 |
+
"mean_conf": 0.7958080172538757,
|
| 289 |
+
"sec": 1.5,
|
| 290 |
"heldout": false
|
| 291 |
},
|
| 292 |
"tweet_sentiment": {
|
| 293 |
"n": 1500,
|
| 294 |
+
"acc": 0.7306666666666667,
|
| 295 |
+
"nll": 0.589668869972229,
|
| 296 |
+
"brier": 0.36195889115333557,
|
| 297 |
+
"ece": 0.03478943075736365,
|
| 298 |
+
"aurc": 0.13245546777874462,
|
| 299 |
+
"acc_at_80": 0.7883333333333333,
|
| 300 |
+
"acc_at_50": 0.8653333333333333,
|
| 301 |
"chance": 0.3333333333333333,
|
| 302 |
+
"mean_conf": 0.7084402441978455,
|
| 303 |
+
"sec": 1.0,
|
| 304 |
"heldout": false
|
| 305 |
},
|
| 306 |
"tweet_emotion": {
|
| 307 |
"n": 1421,
|
| 308 |
+
"acc": 0.8465869106263195,
|
| 309 |
+
"nll": 0.4326176941394806,
|
| 310 |
+
"brier": 0.2285701334476471,
|
| 311 |
+
"ece": 0.0309200050501988,
|
| 312 |
+
"aurc": 0.04118810674643607,
|
| 313 |
+
"acc_at_80": 0.9226033421284081,
|
| 314 |
+
"acc_at_50": 0.9816901408450704,
|
| 315 |
"chance": 0.25,
|
| 316 |
+
"mean_conf": 0.819736659526825,
|
| 317 |
+
"sec": 3.5,
|
| 318 |
"heldout": false
|
| 319 |
},
|
| 320 |
"tweet_irony": {
|
| 321 |
"n": 784,
|
| 322 |
+
"acc": 0.7882653061224489,
|
| 323 |
+
"nll": 0.49027082324028015,
|
| 324 |
+
"brier": 0.32242321968078613,
|
| 325 |
+
"ece": 0.08050694453472992,
|
| 326 |
+
"aurc": 0.11250390021122361,
|
| 327 |
+
"acc_at_80": 0.8373205741626795,
|
| 328 |
+
"acc_at_50": 0.875,
|
| 329 |
"chance": 0.5,
|
| 330 |
+
"mean_conf": 0.707758367061615,
|
| 331 |
+
"sec": 0.5,
|
| 332 |
"heldout": true
|
| 333 |
},
|
| 334 |
"fin_sentiment": {
|
| 335 |
"n": 1500,
|
| 336 |
+
"acc": 0.764,
|
| 337 |
+
"nll": 0.5191769003868103,
|
| 338 |
+
"brier": 0.3192051649093628,
|
| 339 |
+
"ece": 0.038631361166636145,
|
| 340 |
+
"aurc": 0.10554895981253572,
|
| 341 |
+
"acc_at_80": 0.82,
|
| 342 |
+
"acc_at_50": 0.92,
|
| 343 |
"chance": 0.3333333333333333,
|
| 344 |
+
"mean_conf": 0.7789527773857117,
|
| 345 |
+
"sec": 1.1,
|
| 346 |
"heldout": true
|
| 347 |
},
|
| 348 |
"cr_reviews": {
|
| 349 |
"n": 753,
|
| 350 |
+
"acc": 0.8937583001328021,
|
| 351 |
+
"nll": 0.24244317412376404,
|
| 352 |
+
"brier": 0.1483953297138214,
|
| 353 |
+
"ece": 0.023112064576243988,
|
| 354 |
+
"aurc": 0.02109664626036971,
|
| 355 |
+
"acc_at_80": 0.9551495016611296,
|
| 356 |
+
"acc_at_50": 0.9946808510638298,
|
| 357 |
"chance": 0.5,
|
| 358 |
+
"mean_conf": 0.9141256213188171,
|
| 359 |
+
"sec": 0.5,
|
| 360 |
"heldout": true
|
| 361 |
},
|
| 362 |
"counterfactual": {
|
| 363 |
"n": 1500,
|
| 364 |
+
"acc": 0.9526666666666667,
|
| 365 |
+
"nll": 0.13047298789024353,
|
| 366 |
+
"brier": 0.07368191331624985,
|
| 367 |
+
"ece": 0.007460888942082723,
|
| 368 |
+
"aurc": 0.006147812477564298,
|
| 369 |
"acc_at_80": 0.99,
|
| 370 |
"acc_at_50": 0.9973333333333333,
|
| 371 |
"chance": 0.5,
|
| 372 |
+
"mean_conf": 0.9580413699150085,
|
| 373 |
+
"sec": 1.1,
|
| 374 |
"heldout": false
|
| 375 |
},
|
| 376 |
"subjectivity": {
|
| 377 |
"n": 1500,
|
| 378 |
+
"acc": 0.9586666666666667,
|
| 379 |
+
"nll": 0.1124299094080925,
|
| 380 |
+
"brier": 0.06167744845151901,
|
| 381 |
+
"ece": 0.010298379937807677,
|
| 382 |
+
"aurc": 0.004914430563202389,
|
| 383 |
+
"acc_at_80": 0.9925,
|
| 384 |
"acc_at_50": 0.9973333333333333,
|
| 385 |
"chance": 0.5,
|
| 386 |
+
"mean_conf": 0.9552116990089417,
|
| 387 |
+
"sec": 1.1,
|
| 388 |
"heldout": false
|
| 389 |
},
|
| 390 |
"tweet_offensive": {
|
| 391 |
"n": 860,
|
| 392 |
+
"acc": 0.858139534883721,
|
| 393 |
+
"nll": 0.3267144560813904,
|
| 394 |
+
"brier": 0.20206692814826965,
|
| 395 |
+
"ece": 0.03781627153241357,
|
| 396 |
+
"aurc": 0.04183193769642952,
|
| 397 |
+
"acc_at_80": 0.9229651162790697,
|
| 398 |
+
"acc_at_50": 0.9744186046511628,
|
| 399 |
"chance": 0.5,
|
| 400 |
+
"mean_conf": 0.8322479128837585,
|
| 401 |
+
"sec": 0.7,
|
| 402 |
"heldout": false
|
| 403 |
},
|
| 404 |
"tweet_hate": {
|
| 405 |
"n": 1500,
|
| 406 |
+
"acc": 0.5226666666666666,
|
| 407 |
+
"nll": 0.9635146260261536,
|
| 408 |
+
"brier": 0.6607663035392761,
|
| 409 |
+
"ece": 0.26240865075588227,
|
| 410 |
+
"aurc": 0.4248328286104504,
|
| 411 |
+
"acc_at_80": 0.53,
|
| 412 |
+
"acc_at_50": 0.5386666666666666,
|
| 413 |
"chance": 0.5,
|
| 414 |
+
"mean_conf": 0.7850753664970398,
|
| 415 |
+
"sec": 1.2,
|
| 416 |
"heldout": false
|
| 417 |
},
|
| 418 |
"hate_offensive": {
|
| 419 |
"n": 1500,
|
| 420 |
+
"acc": 0.918,
|
| 421 |
+
"nll": 0.23910340666770935,
|
| 422 |
+
"brier": 0.1262882500886917,
|
| 423 |
+
"ece": 0.01397482017676035,
|
| 424 |
+
"aurc": 0.020077507534176645,
|
| 425 |
+
"acc_at_80": 0.9691666666666666,
|
| 426 |
+
"acc_at_50": 0.9866666666666667,
|
| 427 |
"chance": 0.3333333333333333,
|
| 428 |
+
"mean_conf": 0.9220314025878906,
|
| 429 |
+
"sec": 1.2,
|
| 430 |
"heldout": false
|
| 431 |
},
|
| 432 |
"civil_comments": {
|
| 433 |
"n": 7500,
|
| 434 |
+
"acc": 0.9346666666666666,
|
| 435 |
+
"nll": 0.14896972477436066,
|
| 436 |
+
"brier": 0.09157063812017441,
|
| 437 |
+
"ece": 0.005636482063929209,
|
| 438 |
+
"aurc": 0.007494801475142145,
|
| 439 |
+
"acc_at_80": 0.9886666666666667,
|
| 440 |
+
"acc_at_50": 1.0,
|
| 441 |
"chance": 0.5,
|
| 442 |
+
"mean_conf": 0.9398742914199829,
|
| 443 |
+
"sec": 2.6,
|
| 444 |
"heldout": false,
|
| 445 |
"per_q": [
|
| 446 |
+
0.87,
|
| 447 |
+
0.9773333333333334,
|
| 448 |
+
0.992,
|
| 449 |
+
0.8593333333333333,
|
| 450 |
+
0.9746666666666667
|
| 451 |
]
|
| 452 |
},
|
| 453 |
"toxic_chat": {
|
| 454 |
"n": 3000,
|
| 455 |
+
"acc": 0.9796666666666667,
|
| 456 |
+
"nll": 0.05411078408360481,
|
| 457 |
+
"brier": 0.030054867267608643,
|
| 458 |
+
"ece": 0.004126144587993601,
|
| 459 |
+
"aurc": 0.0010637207148584903,
|
| 460 |
"acc_at_80": 0.9991666666666666,
|
| 461 |
+
"acc_at_50": 1.0,
|
| 462 |
"chance": 0.5,
|
| 463 |
+
"mean_conf": 0.980755627155304,
|
| 464 |
+
"sec": 1.8,
|
| 465 |
"heldout": false,
|
| 466 |
"per_q": [
|
| 467 |
+
0.9666666666666667,
|
| 468 |
+
0.9926666666666667
|
| 469 |
]
|
| 470 |
},
|
| 471 |
"sms_spam": {
|
| 472 |
"n": 1000,
|
| 473 |
+
"acc": 0.981,
|
| 474 |
+
"nll": 0.05420927703380585,
|
| 475 |
+
"brier": 0.02655675821006298,
|
| 476 |
+
"ece": 0.010960762321948961,
|
| 477 |
+
"aurc": 0.0016593188515115816,
|
| 478 |
+
"acc_at_80": 0.9975,
|
| 479 |
"acc_at_50": 0.998,
|
| 480 |
"chance": 0.5,
|
| 481 |
+
"mean_conf": 0.989021360874176,
|
| 482 |
+
"sec": 3.2,
|
| 483 |
"heldout": false
|
| 484 |
},
|
| 485 |
"enron_spam": {
|
| 486 |
"n": 1500,
|
| 487 |
+
"acc": 0.9893333333333333,
|
| 488 |
+
"nll": 0.0317784920334816,
|
| 489 |
+
"brier": 0.01731153391301632,
|
| 490 |
+
"ece": 0.005647406299908973,
|
| 491 |
+
"aurc": 0.00032969116371446284,
|
| 492 |
"acc_at_80": 1.0,
|
| 493 |
"acc_at_50": 1.0,
|
| 494 |
"chance": 0.5,
|
| 495 |
+
"mean_conf": 0.9897382855415344,
|
| 496 |
+
"sec": 7.0,
|
| 497 |
"heldout": false
|
| 498 |
},
|
| 499 |
"insincere_questions": {
|
| 500 |
"n": 1500,
|
| 501 |
+
"acc": 0.9533333333333334,
|
| 502 |
+
"nll": 0.108225516974926,
|
| 503 |
+
"brier": 0.06507585942745209,
|
| 504 |
+
"ece": 0.010330648342768334,
|
| 505 |
+
"aurc": 0.004540149557653359,
|
| 506 |
"acc_at_80": 0.9975,
|
| 507 |
+
"acc_at_50": 0.9973333333333333,
|
| 508 |
"chance": 0.5,
|
| 509 |
+
"mean_conf": 0.956480860710144,
|
| 510 |
+
"sec": 1.0,
|
| 511 |
"heldout": false
|
| 512 |
},
|
| 513 |
"ade": {
|
| 514 |
"n": 1500,
|
| 515 |
+
"acc": 0.8013333333333333,
|
| 516 |
+
"nll": 0.4438433349132538,
|
| 517 |
+
"brier": 0.28561800718307495,
|
| 518 |
+
"ece": 0.030588836590449038,
|
| 519 |
+
"aurc": 0.08975771135749887,
|
| 520 |
+
"acc_at_80": 0.855,
|
| 521 |
+
"acc_at_50": 0.9026666666666666,
|
| 522 |
"chance": 0.5,
|
| 523 |
+
"mean_conf": 0.8299436569213867,
|
| 524 |
+
"sec": 1.1,
|
| 525 |
"heldout": true
|
| 526 |
},
|
| 527 |
"snli": {
|
| 528 |
"n": 1476,
|
| 529 |
+
"acc": 0.9281842818428184,
|
| 530 |
+
"nll": 0.22167986631393433,
|
| 531 |
+
"brier": 0.11423322558403015,
|
| 532 |
+
"ece": 0.015901014794340612,
|
| 533 |
+
"aurc": 0.016313831745876334,
|
| 534 |
+
"acc_at_80": 0.9720575783234547,
|
| 535 |
+
"acc_at_50": 0.986449864498645,
|
| 536 |
"chance": 0.3333333333333333,
|
| 537 |
+
"mean_conf": 0.9138893485069275,
|
| 538 |
+
"sec": 3.9,
|
| 539 |
"heldout": false
|
| 540 |
},
|
| 541 |
"mnli": {
|
| 542 |
"n": 1500,
|
| 543 |
+
"acc": 0.8906666666666667,
|
| 544 |
+
"nll": 0.2871558368206024,
|
| 545 |
+
"brier": 0.16026780009269714,
|
| 546 |
+
"ece": 0.019413771212100986,
|
| 547 |
+
"aurc": 0.023009362411430274,
|
| 548 |
+
"acc_at_80": 0.955,
|
| 549 |
+
"acc_at_50": 0.992,
|
| 550 |
"chance": 0.3333333333333333,
|
| 551 |
+
"mean_conf": 0.8811207413673401,
|
| 552 |
+
"sec": 1.6,
|
| 553 |
"heldout": false
|
| 554 |
},
|
| 555 |
"rte": {
|
| 556 |
"n": 277,
|
| 557 |
+
"acc": 0.8664259927797834,
|
| 558 |
+
"nll": 0.34656208753585815,
|
| 559 |
+
"brier": 0.21244081854820251,
|
| 560 |
+
"ece": 0.05030047463165724,
|
| 561 |
+
"aurc": 0.04784538059954504,
|
| 562 |
+
"acc_at_80": 0.918918918918919,
|
| 563 |
+
"acc_at_50": 0.9710144927536232,
|
| 564 |
"chance": 0.5,
|
| 565 |
+
"mean_conf": 0.8952643275260925,
|
| 566 |
+
"sec": 0.4,
|
| 567 |
"heldout": false
|
| 568 |
},
|
| 569 |
"qnli": {
|
| 570 |
"n": 1500,
|
| 571 |
+
"acc": 0.9433333333333334,
|
| 572 |
+
"nll": 0.15965798497200012,
|
| 573 |
+
"brier": 0.08883056789636612,
|
| 574 |
+
"ece": 0.019613722920417815,
|
| 575 |
+
"aurc": 0.009650867829334674,
|
| 576 |
+
"acc_at_80": 0.985,
|
| 577 |
+
"acc_at_50": 0.9973333333333333,
|
| 578 |
"chance": 0.5,
|
| 579 |
+
"mean_conf": 0.9275038242340088,
|
| 580 |
+
"sec": 1.5,
|
| 581 |
"heldout": false
|
| 582 |
},
|
| 583 |
"qqp": {
|
| 584 |
"n": 1500,
|
| 585 |
+
"acc": 0.856,
|
| 586 |
+
"nll": 0.3196488618850708,
|
| 587 |
+
"brier": 0.2046487182378769,
|
| 588 |
+
"ece": 0.01062200272083283,
|
| 589 |
+
"aurc": 0.040487616797730115,
|
| 590 |
+
"acc_at_80": 0.9166666666666666,
|
| 591 |
+
"acc_at_50": 0.9733333333333334,
|
| 592 |
"chance": 0.5,
|
| 593 |
+
"mean_conf": 0.8592682480812073,
|
| 594 |
+
"sec": 1.2,
|
| 595 |
"heldout": false
|
| 596 |
},
|
| 597 |
"mrpc": {
|
| 598 |
"n": 408,
|
| 599 |
+
"acc": 0.8480392156862745,
|
| 600 |
+
"nll": 0.3168051540851593,
|
| 601 |
+
"brier": 0.20282277464866638,
|
| 602 |
+
"ece": 0.03800497072584488,
|
| 603 |
+
"aurc": 0.03737257985377352,
|
| 604 |
+
"acc_at_80": 0.9171779141104295,
|
| 605 |
+
"acc_at_50": 0.9754901960784313,
|
| 606 |
"chance": 0.5,
|
| 607 |
+
"mean_conf": 0.8617921471595764,
|
| 608 |
+
"sec": 0.4,
|
| 609 |
"heldout": false
|
| 610 |
},
|
| 611 |
"paws": {
|
| 612 |
"n": 1500,
|
| 613 |
+
"acc": 0.7086666666666667,
|
| 614 |
+
"nll": 0.747458815574646,
|
| 615 |
+
"brier": 0.44605201482772827,
|
| 616 |
+
"ece": 0.19753822358449297,
|
| 617 |
+
"aurc": 0.13740906017361146,
|
| 618 |
+
"acc_at_80": 0.7716666666666666,
|
| 619 |
+
"acc_at_50": 0.884,
|
| 620 |
"chance": 0.5,
|
| 621 |
+
"mean_conf": 0.9062049388885498,
|
| 622 |
+
"sec": 1.6,
|
| 623 |
"heldout": true
|
| 624 |
},
|
| 625 |
"cola": {
|
| 626 |
"n": 1043,
|
| 627 |
+
"acc": 0.8053691275167785,
|
| 628 |
+
"nll": 0.4110952615737915,
|
| 629 |
+
"brier": 0.263612300157547,
|
| 630 |
+
"ece": 0.026030545552419217,
|
| 631 |
+
"aurc": 0.0753830017250337,
|
| 632 |
+
"acc_at_80": 0.86810551558753,
|
| 633 |
+
"acc_at_50": 0.9310344827586207,
|
| 634 |
"chance": 0.5,
|
| 635 |
+
"mean_conf": 0.8122093081474304,
|
| 636 |
+
"sec": 0.6,
|
| 637 |
"heldout": false
|
| 638 |
},
|
| 639 |
"boolq": {
|
| 640 |
"n": 1500,
|
| 641 |
+
"acc": 0.89,
|
| 642 |
+
"nll": 0.2775375545024872,
|
| 643 |
+
"brier": 0.16621354222297668,
|
| 644 |
+
"ece": 0.015124458909034735,
|
| 645 |
+
"aurc": 0.03136212917899602,
|
| 646 |
+
"acc_at_80": 0.9408333333333333,
|
| 647 |
+
"acc_at_50": 0.9813333333333333,
|
| 648 |
"chance": 0.5,
|
| 649 |
+
"mean_conf": 0.8884056210517883,
|
| 650 |
+
"sec": 2.3,
|
| 651 |
"heldout": false
|
| 652 |
},
|
| 653 |
"strategyqa": {
|
| 654 |
"n": 687,
|
| 655 |
+
"acc": 0.6055312954876274,
|
| 656 |
+
"nll": 0.6860260963439941,
|
| 657 |
+
"brier": 0.4836777150630951,
|
| 658 |
+
"ece": 0.07135456410037377,
|
| 659 |
+
"aurc": 0.33034478489678043,
|
| 660 |
+
"acc_at_80": 0.6145454545454545,
|
| 661 |
+
"acc_at_50": 0.6686046511627907,
|
| 662 |
"chance": 0.5,
|
| 663 |
+
"mean_conf": 0.6736506819725037,
|
| 664 |
+
"sec": 2.8,
|
| 665 |
"heldout": true
|
| 666 |
},
|
| 667 |
"pubmedqa": {
|
| 668 |
"n": 500,
|
| 669 |
+
"acc": 0.78,
|
| 670 |
+
"nll": 0.604637086391449,
|
| 671 |
+
"brier": 0.3268354535102844,
|
| 672 |
+
"ece": 0.04217318385839462,
|
| 673 |
+
"aurc": 0.1023213883692996,
|
| 674 |
+
"acc_at_80": 0.8525,
|
| 675 |
+
"acc_at_50": 0.912,
|
| 676 |
"chance": 0.33333333333333326,
|
| 677 |
+
"mean_conf": 0.8035740852355957,
|
| 678 |
+
"sec": 1.6,
|
| 679 |
"heldout": true
|
| 680 |
},
|
| 681 |
"arc": {
|
| 682 |
"n": 1172,
|
| 683 |
+
"acc": 0.8617747440273038,
|
| 684 |
+
"nll": 0.3778131902217865,
|
| 685 |
+
"brier": 0.19557851552963257,
|
| 686 |
+
"ece": 0.025041668768018607,
|
| 687 |
+
"aurc": 0.027995019899211025,
|
| 688 |
+
"acc_at_80": 0.9477611940298507,
|
| 689 |
+
"acc_at_50": 0.9880546075085325,
|
| 690 |
"chance": 0.25015642775881686,
|
| 691 |
+
"mean_conf": 0.8545714616775513,
|
| 692 |
+
"sec": 1.2,
|
| 693 |
"heldout": false
|
| 694 |
},
|
| 695 |
"commonsense_qa": {
|
| 696 |
"n": 1221,
|
| 697 |
+
"acc": 0.7682227682227682,
|
| 698 |
+
"nll": 0.596526026725769,
|
| 699 |
+
"brier": 0.3169134259223938,
|
| 700 |
+
"ece": 0.024408742675617233,
|
| 701 |
+
"aurc": 0.07639980329813019,
|
| 702 |
+
"acc_at_80": 0.8505629477993859,
|
| 703 |
+
"acc_at_50": 0.9442622950819672,
|
| 704 |
"chance": 0.19999999999999998,
|
| 705 |
+
"mean_conf": 0.7619057297706604,
|
| 706 |
+
"sec": 0.8,
|
| 707 |
"heldout": false
|
| 708 |
},
|
| 709 |
"qasc": {
|
| 710 |
"n": 926,
|
| 711 |
+
"acc": 0.8088552915766739,
|
| 712 |
+
"nll": 0.5853570699691772,
|
| 713 |
+
"brier": 0.2697433531284332,
|
| 714 |
+
"ece": 0.06495514207923903,
|
| 715 |
+
"aurc": 0.046915675887241735,
|
| 716 |
+
"acc_at_80": 0.9041835357624831,
|
| 717 |
+
"acc_at_50": 0.978401727861771,
|
| 718 |
"chance": 0.125,
|
| 719 |
+
"mean_conf": 0.7473546862602234,
|
| 720 |
+
"sec": 0.9,
|
| 721 |
"heldout": false
|
| 722 |
},
|
| 723 |
"openbookqa": {
|
| 724 |
"n": 500,
|
| 725 |
+
"acc": 0.834,
|
| 726 |
+
"nll": 0.4812253713607788,
|
| 727 |
+
"brier": 0.24745029211044312,
|
| 728 |
+
"ece": 0.04192176961898805,
|
| 729 |
+
"aurc": 0.05150388916107792,
|
| 730 |
+
"acc_at_80": 0.9075,
|
| 731 |
+
"acc_at_50": 0.972,
|
| 732 |
"chance": 0.25,
|
| 733 |
+
"mean_conf": 0.8025239109992981,
|
| 734 |
+
"sec": 0.4,
|
| 735 |
"heldout": false
|
| 736 |
},
|
| 737 |
"sciq": {
|
| 738 |
"n": 1000,
|
| 739 |
+
"acc": 0.987,
|
| 740 |
+
"nll": 0.051316503435373306,
|
| 741 |
+
"brier": 0.02284967713057995,
|
| 742 |
+
"ece": 0.018773878514766716,
|
| 743 |
+
"aurc": 0.0003853215476759977,
|
| 744 |
"acc_at_80": 1.0,
|
| 745 |
"acc_at_50": 1.0,
|
| 746 |
"chance": 0.25,
|
| 747 |
+
"mean_conf": 0.9696812629699707,
|
| 748 |
+
"sec": 3.8,
|
| 749 |
"heldout": true
|
| 750 |
},
|
| 751 |
"hellaswag": {
|
| 752 |
"n": 1500,
|
| 753 |
+
"acc": 0.892,
|
| 754 |
+
"nll": 0.29868125915527344,
|
| 755 |
+
"brier": 0.16158466041088104,
|
| 756 |
+
"ece": 0.01794782030582424,
|
| 757 |
+
"aurc": 0.019411743923739497,
|
| 758 |
+
"acc_at_80": 0.9608333333333333,
|
| 759 |
+
"acc_at_50": 0.9973333333333333,
|
| 760 |
"chance": 0.25,
|
| 761 |
+
"mean_conf": 0.89520263671875,
|
| 762 |
+
"sec": 2.7,
|
| 763 |
"heldout": false
|
| 764 |
},
|
| 765 |
"piqa": {
|
| 766 |
"n": 1500,
|
| 767 |
+
"acc": 0.842,
|
| 768 |
+
"nll": 0.35798120498657227,
|
| 769 |
+
"brier": 0.22625073790550232,
|
| 770 |
+
"ece": 0.02936798457304638,
|
| 771 |
+
"aurc": 0.05338353492667896,
|
| 772 |
+
"acc_at_80": 0.9008333333333334,
|
| 773 |
"acc_at_50": 0.9506666666666667,
|
| 774 |
"chance": 0.5,
|
| 775 |
+
"mean_conf": 0.837594747543335,
|
| 776 |
+
"sec": 1.5,
|
| 777 |
"heldout": false
|
| 778 |
},
|
| 779 |
"social_iqa": {
|
| 780 |
"n": 1500,
|
| 781 |
+
"acc": 0.71,
|
| 782 |
+
"nll": 0.695899486541748,
|
| 783 |
+
"brier": 0.3991619348526001,
|
| 784 |
+
"ece": 0.060694456895192456,
|
| 785 |
+
"aurc": 0.14411079894615622,
|
| 786 |
+
"acc_at_80": 0.7683333333333333,
|
| 787 |
+
"acc_at_50": 0.8613333333333333,
|
| 788 |
"chance": 0.3333333333333333,
|
| 789 |
+
"mean_conf": 0.7695742845535278,
|
| 790 |
+
"sec": 1.2,
|
| 791 |
"heldout": true
|
| 792 |
},
|
| 793 |
"winogrande": {
|
| 794 |
"n": 1267,
|
| 795 |
+
"acc": 0.6803472770323599,
|
| 796 |
+
"nll": 0.6707175374031067,
|
| 797 |
+
"brier": 0.43641534447669983,
|
| 798 |
+
"ece": 0.13178394578438438,
|
| 799 |
+
"aurc": 0.19499483213034147,
|
| 800 |
+
"acc_at_80": 0.7248520710059172,
|
| 801 |
+
"acc_at_50": 0.7902208201892744,
|
| 802 |
"chance": 0.5,
|
| 803 |
+
"mean_conf": 0.8093914985656738,
|
| 804 |
+
"sec": 0.8,
|
| 805 |
"heldout": false
|
| 806 |
},
|
| 807 |
"race": {
|
| 808 |
"n": 1500,
|
| 809 |
+
"acc": 0.8426666666666667,
|
| 810 |
+
"nll": 0.4418315887451172,
|
| 811 |
+
"brier": 0.22411726415157318,
|
| 812 |
+
"ece": 0.024219590028127014,
|
| 813 |
+
"aurc": 0.0420007716587064,
|
| 814 |
+
"acc_at_80": 0.9241666666666667,
|
| 815 |
+
"acc_at_50": 0.9746666666666667,
|
| 816 |
"chance": 0.25,
|
| 817 |
+
"mean_conf": 0.8613157272338867,
|
| 818 |
+
"sec": 5.1,
|
| 819 |
"heldout": false
|
| 820 |
},
|
| 821 |
"mmlu": {
|
| 822 |
"n": 1500,
|
| 823 |
+
"acc": 0.6313333333333333,
|
| 824 |
+
"nll": 0.890999436378479,
|
| 825 |
+
"brier": 0.46188458800315857,
|
| 826 |
+
"ece": 0.0515740847190221,
|
| 827 |
+
"aurc": 0.15556783894771342,
|
| 828 |
+
"acc_at_80": 0.7191666666666666,
|
| 829 |
+
"acc_at_50": 0.8613333333333333,
|
| 830 |
"chance": 0.25,
|
| 831 |
+
"mean_conf": 0.6770187020301819,
|
| 832 |
+
"sec": 1.8,
|
| 833 |
"heldout": false
|
| 834 |
},
|
| 835 |
"medqa": {
|
| 836 |
"n": 1273,
|
| 837 |
+
"acc": 0.5577376276512176,
|
| 838 |
+
"nll": 1.0580443143844604,
|
| 839 |
+
"brier": 0.5702889561653137,
|
| 840 |
+
"ece": 0.029768652458970035,
|
| 841 |
+
"aurc": 0.2773348347125782,
|
| 842 |
+
"acc_at_80": 0.611984282907662,
|
| 843 |
+
"acc_at_50": 0.6981132075471698,
|
| 844 |
"chance": 0.25,
|
| 845 |
+
"mean_conf": 0.5789350271224976,
|
| 846 |
+
"sec": 2.5,
|
| 847 |
"heldout": false
|
| 848 |
},
|
| 849 |
"truthfulqa": {
|
| 850 |
"n": 817,
|
| 851 |
+
"acc": 0.5128518971848225,
|
| 852 |
+
"nll": 1.4920024871826172,
|
| 853 |
+
"brier": 0.6377546191215515,
|
| 854 |
+
"ece": 0.08506929861652954,
|
| 855 |
+
"aurc": 0.2737489336879717,
|
| 856 |
+
"acc_at_80": 0.581039755351682,
|
| 857 |
+
"acc_at_50": 0.7181372549019608,
|
| 858 |
"chance": 0.22622350449767833,
|
| 859 |
+
"mean_conf": 0.5959253907203674,
|
| 860 |
+
"sec": 0.9,
|
| 861 |
"heldout": true
|
| 862 |
},
|
| 863 |
"fin_phrasebank": {
|
| 864 |
"n": 970,
|
| 865 |
+
"acc": 0.634020618556701,
|
| 866 |
+
"nll": 0.708746612071991,
|
| 867 |
+
"brier": 0.4601970314979553,
|
| 868 |
+
"ece": 0.11248690885366852,
|
| 869 |
+
"aurc": 0.22041065209169486,
|
| 870 |
+
"acc_at_80": 0.6868556701030928,
|
| 871 |
+
"acc_at_50": 0.7731958762886598,
|
| 872 |
"chance": 0.33333333333333326,
|
| 873 |
+
"mean_conf": 0.7462515234947205,
|
| 874 |
+
"sec": 5.1,
|
| 875 |
"heldout": true
|
| 876 |
},
|
| 877 |
"banking77": {
|
| 878 |
"n": 1500,
|
| 879 |
+
"acc": 0.962,
|
| 880 |
+
"nll": 0.1172320544719696,
|
| 881 |
+
"brier": 0.056729208678007126,
|
| 882 |
+
"ece": 0.00940998808542892,
|
| 883 |
+
"aurc": 0.002673441928791999,
|
| 884 |
+
"acc_at_80": 0.9983333333333333,
|
| 885 |
"acc_at_50": 1.0,
|
| 886 |
"chance": 0.1,
|
| 887 |
+
"mean_conf": 0.960239589214325,
|
| 888 |
+
"sec": 1.5,
|
| 889 |
"heldout": false
|
| 890 |
},
|
| 891 |
"bias_in_bios": {
|
| 892 |
"n": 3000,
|
| 893 |
+
"acc": 0.9513333333333334,
|
| 894 |
+
"nll": 0.1394692361354828,
|
| 895 |
+
"brier": 0.06979931145906448,
|
| 896 |
+
"ece": 0.007795257161060937,
|
| 897 |
+
"aurc": 0.0035514571665865736,
|
| 898 |
+
"acc_at_80": 0.9970833333333333,
|
| 899 |
"acc_at_50": 1.0,
|
| 900 |
"chance": 0.30000000000000004,
|
| 901 |
+
"mean_conf": 0.9533326625823975,
|
| 902 |
+
"sec": 2.5,
|
| 903 |
"heldout": false,
|
| 904 |
"per_q": [
|
| 905 |
+
0.9053333333333333,
|
| 906 |
0.9973333333333333
|
| 907 |
]
|
| 908 |
},
|
| 909 |
"helpsteer2": {
|
| 910 |
"n": 5190,
|
| 911 |
+
"acc": 0.6013487475915221,
|
| 912 |
+
"nll": 0.934554398059845,
|
| 913 |
+
"brier": 0.5175615549087524,
|
| 914 |
+
"ece": 0.010821180559536854,
|
| 915 |
+
"aurc": 0.2635892747983117,
|
| 916 |
+
"acc_at_80": 0.6592003853564548,
|
| 917 |
+
"acc_at_50": 0.7391136801541426,
|
| 918 |
"chance": 0.2,
|
| 919 |
+
"mean_conf": 0.5985665917396545,
|
| 920 |
+
"sec": 12.5,
|
| 921 |
"heldout": false,
|
| 922 |
"per_q": [
|
| 923 |
+
0.45472061657032753,
|
| 924 |
+
0.5086705202312138,
|
| 925 |
+
0.7273603082851637,
|
| 926 |
+
0.6213872832369942,
|
| 927 |
+
0.6946050096339114
|
| 928 |
]
|
| 929 |
},
|
| 930 |
"helpsteer3_pref": {
|
| 931 |
"n": 1176,
|
| 932 |
+
"acc": 0.40561224489795916,
|
| 933 |
+
"nll": 1.4524648189544678,
|
| 934 |
+
"brier": 0.710177481174469,
|
| 935 |
+
"ece": 0.03173913492434691,
|
| 936 |
+
"aurc": 0.49141414112121073,
|
| 937 |
+
"acc_at_80": 0.4410201912858661,
|
| 938 |
+
"acc_at_50": 0.5017006802721088,
|
| 939 |
"chance": 0.14285714285714282,
|
| 940 |
+
"mean_conf": 0.4128914773464203,
|
| 941 |
+
"sec": 12.8,
|
| 942 |
"heldout": false
|
| 943 |
},
|
| 944 |
"hate_speech_scales": {
|
| 945 |
"n": 7500,
|
| 946 |
+
"acc": 0.5636,
|
| 947 |
+
"nll": 0.9782006740570068,
|
| 948 |
+
"brier": 0.5410642027854919,
|
| 949 |
+
"ece": 0.011817029543717711,
|
| 950 |
+
"aurc": 0.2650615424796364,
|
| 951 |
+
"acc_at_80": 0.6103333333333333,
|
| 952 |
+
"acc_at_50": 0.7074666666666667,
|
| 953 |
"chance": 0.22666666666666674,
|
| 954 |
+
"mean_conf": 0.5654744505882263,
|
| 955 |
+
"sec": 3.7,
|
| 956 |
"heldout": false,
|
| 957 |
"per_q": [
|
| 958 |
+
0.7046666666666667,
|
| 959 |
+
0.4866666666666667,
|
| 960 |
+
0.4493333333333333,
|
| 961 |
0.578,
|
| 962 |
+
0.5993333333333334
|
| 963 |
]
|
| 964 |
},
|
| 965 |
"liar2": {
|
| 966 |
"n": 1500,
|
| 967 |
+
"acc": 0.37066666666666664,
|
| 968 |
+
"nll": 1.4561086893081665,
|
| 969 |
+
"brier": 0.7133269906044006,
|
| 970 |
+
"ece": 0.02327027595043182,
|
| 971 |
+
"aurc": 0.4659199761493187,
|
| 972 |
+
"acc_at_80": 0.41083333333333333,
|
| 973 |
"acc_at_50": 0.48933333333333334,
|
| 974 |
"chance": 0.16666666666666666,
|
| 975 |
+
"mean_conf": 0.3748621940612793,
|
| 976 |
+
"sec": 2.4,
|
| 977 |
"heldout": false
|
| 978 |
},
|
| 979 |
"prosocial_safety": {
|
| 980 |
"n": 1500,
|
| 981 |
+
"acc": 0.532,
|
| 982 |
+
"nll": 1.1633950471878052,
|
| 983 |
+
"brier": 0.5889540314674377,
|
| 984 |
+
"ece": 0.03297985295454661,
|
| 985 |
+
"aurc": 0.2684920476580785,
|
| 986 |
+
"acc_at_80": 0.5925,
|
| 987 |
+
"acc_at_50": 0.7053333333333334,
|
| 988 |
"chance": 0.2,
|
| 989 |
+
"mean_conf": 0.5102941989898682,
|
| 990 |
+
"sec": 1.5,
|
| 991 |
"heldout": false
|
| 992 |
},
|
| 993 |
"ultrafeedback_pref": {
|
| 994 |
"n": 1500,
|
| 995 |
+
"acc": 0.7573333333333333,
|
| 996 |
+
"nll": 0.48778781294822693,
|
| 997 |
+
"brier": 0.32244637608528137,
|
| 998 |
+
"ece": 0.038332425316174826,
|
| 999 |
+
"aurc": 0.11649624186832548,
|
| 1000 |
+
"acc_at_80": 0.815,
|
| 1001 |
+
"acc_at_50": 0.884,
|
| 1002 |
"chance": 0.5,
|
| 1003 |
+
"mean_conf": 0.7588924169540405,
|
| 1004 |
+
"sec": 7.1,
|
| 1005 |
"heldout": false
|
| 1006 |
},
|
| 1007 |
"shp": {
|
| 1008 |
"n": 1500,
|
| 1009 |
+
"acc": 0.728,
|
| 1010 |
+
"nll": 0.5200306177139282,
|
| 1011 |
+
"brier": 0.34814339876174927,
|
| 1012 |
+
"ece": 0.039244854211807255,
|
| 1013 |
+
"aurc": 0.13985241632778875,
|
| 1014 |
+
"acc_at_80": 0.7916666666666666,
|
| 1015 |
+
"acc_at_50": 0.8546666666666667,
|
| 1016 |
"chance": 0.5,
|
| 1017 |
+
"mean_conf": 0.7454078197479248,
|
| 1018 |
+
"sec": 5.0,
|
| 1019 |
"heldout": false
|
| 1020 |
},
|
| 1021 |
"hh_rlhf": {
|
| 1022 |
"n": 1488,
|
| 1023 |
+
"acc": 0.6384408602150538,
|
| 1024 |
+
"nll": 0.6243960857391357,
|
| 1025 |
+
"brier": 0.43749359250068665,
|
| 1026 |
+
"ece": 0.025252133768091923,
|
| 1027 |
+
"aurc": 0.254013929940744,
|
| 1028 |
+
"acc_at_80": 0.6638655462184874,
|
| 1029 |
+
"acc_at_50": 0.7190860215053764,
|
| 1030 |
"chance": 0.5,
|
| 1031 |
+
"mean_conf": 0.6413496136665344,
|
| 1032 |
+
"sec": 6.6,
|
| 1033 |
"heldout": false
|
| 1034 |
},
|
| 1035 |
"arena_pref": {
|
| 1036 |
"n": 1500,
|
| 1037 |
+
"acc": 0.4786666666666667,
|
| 1038 |
+
"nll": 1.2097605466842651,
|
| 1039 |
+
"brier": 0.6734665632247925,
|
| 1040 |
+
"ece": 0.1468491670290629,
|
| 1041 |
+
"aurc": 0.41109683289171867,
|
| 1042 |
+
"acc_at_80": 0.5108333333333334,
|
| 1043 |
+
"acc_at_50": 0.5733333333333334,
|
| 1044 |
"chance": 0.3333333333333333,
|
| 1045 |
+
"mean_conf": 0.6255158185958862,
|
| 1046 |
+
"sec": 6.7,
|
| 1047 |
"heldout": true
|
| 1048 |
},
|
| 1049 |
"reward_bench": {
|
| 1050 |
"n": 1500,
|
| 1051 |
+
"acc": 0.8046666666666666,
|
| 1052 |
+
"nll": 0.4391920268535614,
|
| 1053 |
+
"brier": 0.2816815972328186,
|
| 1054 |
+
"ece": 0.030526579976081835,
|
| 1055 |
+
"aurc": 0.09005779253848542,
|
| 1056 |
+
"acc_at_80": 0.8616666666666667,
|
| 1057 |
+
"acc_at_50": 0.92,
|
| 1058 |
"chance": 0.5,
|
| 1059 |
+
"mean_conf": 0.7789213061332703,
|
| 1060 |
+
"sec": 5.3,
|
| 1061 |
"heldout": true
|
| 1062 |
},
|
| 1063 |
"glaive_tools": {
|
| 1064 |
"n": 1348,
|
| 1065 |
"acc": 0.9473293768545994,
|
| 1066 |
+
"nll": 0.16986463963985443,
|
| 1067 |
+
"brier": 0.09119585901498795,
|
| 1068 |
+
"ece": 0.01463318938936606,
|
| 1069 |
+
"aurc": 0.012421285819056932,
|
| 1070 |
+
"acc_at_80": 0.9786641929499073,
|
| 1071 |
+
"acc_at_50": 0.9896142433234422,
|
| 1072 |
"chance": 0.16666666666666666,
|
| 1073 |
+
"mean_conf": 0.950721263885498,
|
| 1074 |
+
"sec": 4.4,
|
| 1075 |
"heldout": false
|
| 1076 |
},
|
| 1077 |
"hermes_tools": {
|
| 1078 |
"n": 1500,
|
| 1079 |
+
"acc": 0.7113333333333334,
|
| 1080 |
+
"nll": 0.6692715883255005,
|
| 1081 |
+
"brier": 0.43301042914390564,
|
| 1082 |
+
"ece": 0.21088105460007986,
|
| 1083 |
+
"aurc": 0.08194760887819506,
|
| 1084 |
+
"acc_at_80": 0.8108333333333333,
|
| 1085 |
+
"acc_at_50": 0.98,
|
| 1086 |
"chance": 0.125,
|
| 1087 |
+
"mean_conf": 0.9190990328788757,
|
| 1088 |
+
"sec": 6.3,
|
| 1089 |
"heldout": true
|
| 1090 |
},
|
| 1091 |
"copa": {
|
| 1092 |
"n": 100,
|
| 1093 |
+
"acc": 0.93,
|
| 1094 |
+
"nll": 0.21066521108150482,
|
| 1095 |
+
"brier": 0.11394889652729034,
|
| 1096 |
+
"ece": 0.040256121754646275,
|
| 1097 |
+
"aurc": 0.021342808523311715,
|
| 1098 |
+
"acc_at_80": 0.9625,
|
| 1099 |
"acc_at_50": 0.98,
|
| 1100 |
"chance": 0.5,
|
| 1101 |
+
"mean_conf": 0.904087245464325,
|
| 1102 |
+
"sec": 2.6,
|
| 1103 |
"heldout": false
|
| 1104 |
},
|
| 1105 |
"wic": {
|
| 1106 |
"n": 638,
|
| 1107 |
+
"acc": 0.6990595611285266,
|
| 1108 |
+
"nll": 0.6114251017570496,
|
| 1109 |
+
"brier": 0.40890803933143616,
|
| 1110 |
+
"ece": 0.057320481370608994,
|
| 1111 |
+
"aurc": 0.22488178917696844,
|
| 1112 |
+
"acc_at_80": 0.7392156862745098,
|
| 1113 |
+
"acc_at_50": 0.7836990595611285,
|
| 1114 |
"chance": 0.5,
|
| 1115 |
+
"mean_conf": 0.753724217414856,
|
| 1116 |
+
"sec": 0.5,
|
| 1117 |
"heldout": false
|
| 1118 |
},
|
| 1119 |
"multirc": {
|
| 1120 |
"n": 1500,
|
| 1121 |
+
"acc": 0.8953333333333333,
|
| 1122 |
+
"nll": 0.2838270962238312,
|
| 1123 |
+
"brier": 0.1647527664899826,
|
| 1124 |
+
"ece": 0.015789239207903517,
|
| 1125 |
+
"aurc": 0.03669604113839991,
|
| 1126 |
+
"acc_at_80": 0.9425,
|
| 1127 |
+
"acc_at_50": 0.9706666666666667,
|
| 1128 |
"chance": 0.5,
|
| 1129 |
+
"mean_conf": 0.8994993567466736,
|
| 1130 |
+
"sec": 4.6,
|
| 1131 |
"heldout": false
|
| 1132 |
},
|
| 1133 |
"cb": {
|
| 1134 |
"n": 56,
|
| 1135 |
"acc": 0.8928571428571429,
|
| 1136 |
+
"nll": 0.36988380551338196,
|
| 1137 |
+
"brier": 0.17701731622219086,
|
| 1138 |
+
"ece": 0.10170899544443401,
|
| 1139 |
+
"aurc": 0.022862006902143423,
|
| 1140 |
"acc_at_80": 0.9555555555555556,
|
| 1141 |
"acc_at_50": 0.9642857142857143,
|
| 1142 |
"chance": 0.3333333333333333,
|
| 1143 |
+
"mean_conf": 0.8231589198112488,
|
| 1144 |
+
"sec": 0.1,
|
| 1145 |
"heldout": true
|
| 1146 |
},
|
| 1147 |
"fever": {
|
| 1148 |
"n": 1500,
|
| 1149 |
+
"acc": 0.894,
|
| 1150 |
+
"nll": 0.3236566185951233,
|
| 1151 |
+
"brier": 0.17617946863174438,
|
| 1152 |
+
"ece": 0.0255238478779793,
|
| 1153 |
+
"aurc": 0.034462965066177104,
|
| 1154 |
+
"acc_at_80": 0.9391666666666667,
|
| 1155 |
"acc_at_50": 0.972,
|
| 1156 |
"chance": 0.3333333333333333,
|
| 1157 |
+
"mean_conf": 0.8865981698036194,
|
| 1158 |
+
"sec": 1.7,
|
| 1159 |
"heldout": false
|
| 1160 |
},
|
| 1161 |
"wiki_qa": {
|
| 1162 |
"n": 879,
|
| 1163 |
+
"acc": 0.9078498293515358,
|
| 1164 |
+
"nll": 0.25518864393234253,
|
| 1165 |
+
"brier": 0.15072549879550934,
|
| 1166 |
+
"ece": 0.01926714921024741,
|
| 1167 |
+
"aurc": 0.025838258571267432,
|
| 1168 |
+
"acc_at_80": 0.9516358463726885,
|
| 1169 |
+
"acc_at_50": 0.9840909090909091,
|
| 1170 |
"chance": 0.5,
|
| 1171 |
+
"mean_conf": 0.8916476964950562,
|
| 1172 |
+
"sec": 3.4,
|
| 1173 |
"heldout": false
|
| 1174 |
},
|
| 1175 |
"msmarco_rel": {
|
| 1176 |
"n": 1446,
|
| 1177 |
+
"acc": 0.686030428769018,
|
| 1178 |
+
"nll": 0.5892097353935242,
|
| 1179 |
+
"brier": 0.4052460789680481,
|
| 1180 |
+
"ece": 0.017308449885327464,
|
| 1181 |
+
"aurc": 0.2062339594393076,
|
| 1182 |
+
"acc_at_80": 0.7208297320656871,
|
| 1183 |
+
"acc_at_50": 0.7786998616874136,
|
| 1184 |
"chance": 0.5,
|
| 1185 |
+
"mean_conf": 0.6871178150177002,
|
| 1186 |
+
"sec": 1.9,
|
| 1187 |
"heldout": false
|
| 1188 |
},
|
| 1189 |
"medmcqa": {
|
| 1190 |
"n": 1500,
|
| 1191 |
+
"acc": 0.516,
|
| 1192 |
+
"nll": 1.0883218050003052,
|
| 1193 |
+
"brier": 0.5872463583946228,
|
| 1194 |
+
"ece": 0.036159954885641735,
|
| 1195 |
+
"aurc": 0.28812445893217514,
|
| 1196 |
+
"acc_at_80": 0.5775,
|
| 1197 |
+
"acc_at_50": 0.692,
|
| 1198 |
"chance": 0.25,
|
| 1199 |
+
"mean_conf": 0.5479114055633545,
|
| 1200 |
+
"sec": 1.3,
|
| 1201 |
"heldout": false
|
| 1202 |
},
|
| 1203 |
"quality": {
|
| 1204 |
"n": 1500,
|
| 1205 |
+
"acc": 0.51,
|
| 1206 |
+
"nll": 1.2439022064208984,
|
| 1207 |
+
"brier": 0.6477080583572388,
|
| 1208 |
+
"ece": 0.15170047092437744,
|
| 1209 |
+
"aurc": 0.329958192571683,
|
| 1210 |
+
"acc_at_80": 0.5591666666666667,
|
| 1211 |
+
"acc_at_50": 0.6386666666666667,
|
| 1212 |
"chance": 0.25,
|
| 1213 |
+
"mean_conf": 0.6539396047592163,
|
| 1214 |
+
"sec": 14.5,
|
| 1215 |
"heldout": true
|
| 1216 |
},
|
| 1217 |
"xstory_cloze": {
|
| 1218 |
"n": 1500,
|
| 1219 |
+
"acc": 0.966,
|
| 1220 |
+
"nll": 0.10946577042341232,
|
| 1221 |
+
"brier": 0.057800862938165665,
|
| 1222 |
+
"ece": 0.031253365834554,
|
| 1223 |
+
"aurc": 0.0037750691801176164,
|
| 1224 |
"acc_at_80": 0.9966666666666667,
|
| 1225 |
+
"acc_at_50": 0.9973333333333333,
|
| 1226 |
"chance": 0.5,
|
| 1227 |
+
"mean_conf": 0.9347465634346008,
|
| 1228 |
+
"sec": 1.5,
|
| 1229 |
"heldout": true
|
| 1230 |
},
|
| 1231 |
"abstain_probe": {
|
| 1232 |
"n": 1500,
|
| 1233 |
+
"acc": 0.57,
|
| 1234 |
+
"nll": 1.453281283378601,
|
| 1235 |
+
"brier": 0.6186018586158752,
|
| 1236 |
+
"ece": 0.20962640981872876,
|
| 1237 |
+
"aurc": 0.2494339184298514,
|
| 1238 |
+
"acc_at_80": 0.6541666666666667,
|
| 1239 |
+
"acc_at_50": 0.756,
|
| 1240 |
"chance": 0.17950317460317464,
|
| 1241 |
+
"mean_conf": 0.7796264886856079,
|
| 1242 |
+
"sec": 2.2,
|
| 1243 |
"heldout": true
|
| 1244 |
},
|
| 1245 |
"toolace": {
|
| 1246 |
"n": 1000,
|
| 1247 |
+
"acc": 0.93,
|
| 1248 |
+
"nll": 0.2150496393442154,
|
| 1249 |
+
"brier": 0.10874852538108826,
|
| 1250 |
+
"ece": 0.010460366845130945,
|
| 1251 |
+
"aurc": 0.01925174173374489,
|
| 1252 |
+
"acc_at_80": 0.97875,
|
| 1253 |
+
"acc_at_50": 0.986,
|
| 1254 |
"chance": 0.12470555555555554,
|
| 1255 |
+
"mean_conf": 0.9300835132598877,
|
| 1256 |
+
"sec": 4.9,
|
| 1257 |
"heldout": false
|
| 1258 |
},
|
| 1259 |
"agenttraj": {
|
| 1260 |
"n": 1500,
|
| 1261 |
+
"acc": 0.9133333333333333,
|
| 1262 |
+
"nll": 0.20159707963466644,
|
| 1263 |
+
"brier": 0.11264414340257645,
|
| 1264 |
+
"ece": 0.012760755966107066,
|
| 1265 |
+
"aurc": 0.008911506957123411,
|
| 1266 |
"acc_at_80": 0.9891666666666666,
|
| 1267 |
+
"acc_at_50": 1.0,
|
| 1268 |
"chance": 0.2,
|
| 1269 |
+
"mean_conf": 0.9171887040138245,
|
| 1270 |
+
"sec": 4.4,
|
| 1271 |
"heldout": false
|
| 1272 |
},
|
| 1273 |
"mind2web": {
|
| 1274 |
"n": 1500,
|
| 1275 |
+
"acc": 0.8273333333333334,
|
| 1276 |
+
"nll": 0.48024988174438477,
|
| 1277 |
+
"brier": 0.24723227322101593,
|
| 1278 |
+
"ece": 0.02287068088849383,
|
| 1279 |
+
"aurc": 0.04421884694063308,
|
| 1280 |
+
"acc_at_80": 0.9066666666666666,
|
| 1281 |
+
"acc_at_50": 0.9813333333333333,
|
| 1282 |
"chance": 0.16666666666666666,
|
| 1283 |
+
"mean_conf": 0.8286987543106079,
|
| 1284 |
+
"sec": 2.5,
|
| 1285 |
"heldout": false
|
| 1286 |
},
|
| 1287 |
"synth": {
|
| 1288 |
"n": 300,
|
| 1289 |
+
"acc": 0.7866666666666666,
|
| 1290 |
+
"nll": 0.5258040428161621,
|
| 1291 |
+
"brier": 0.3138435482978821,
|
| 1292 |
+
"ece": 0.050415676832199115,
|
| 1293 |
+
"aurc": 0.08665319404930355,
|
| 1294 |
+
"acc_at_80": 0.8416666666666667,
|
| 1295 |
+
"acc_at_50": 0.9,
|
| 1296 |
"chance": 0.37149999999999994,
|
| 1297 |
+
"mean_conf": 0.7729342579841614,
|
| 1298 |
+
"sec": 0.3,
|
| 1299 |
"heldout": false,
|
| 1300 |
"per_q": [
|
| 1301 |
+
0.76,
|
| 1302 |
+
0.8133333333333334
|
| 1303 |
]
|
| 1304 |
},
|
| 1305 |
"games": {
|
| 1306 |
"n": 500,
|
| 1307 |
+
"acc": 1.0,
|
| 1308 |
+
"nll": 0.0030352056492120028,
|
| 1309 |
+
"brier": 0.001155107282102108,
|
| 1310 |
+
"ece": 0.002569102644920349,
|
| 1311 |
+
"aurc": 0.0,
|
| 1312 |
"acc_at_80": 1.0,
|
| 1313 |
"acc_at_50": 1.0,
|
| 1314 |
"chance": 0.2885,
|
| 1315 |
+
"mean_conf": 0.9974308609962463,
|
| 1316 |
+
"sec": 0.6,
|
| 1317 |
"heldout": false
|
| 1318 |
},
|
| 1319 |
"mario": {
|
| 1320 |
"n": 276,
|
| 1321 |
+
"acc": 1.0,
|
| 1322 |
+
"nll": 0.009527844376862049,
|
| 1323 |
+
"brier": 0.004120680037885904,
|
| 1324 |
+
"ece": 0.00811098947905112,
|
| 1325 |
+
"aurc": 0.0,
|
| 1326 |
"acc_at_80": 1.0,
|
| 1327 |
"acc_at_50": 1.0,
|
| 1328 |
"chance": 0.3333333333333333,
|
| 1329 |
+
"mean_conf": 0.9918889403343201,
|
| 1330 |
+
"sec": 2.8,
|
| 1331 |
"heldout": false,
|
| 1332 |
"per_q": [
|
| 1333 |
+
1.0,
|
| 1334 |
1.0
|
| 1335 |
]
|
| 1336 |
+
},
|
| 1337 |
+
"offtopic_probe": {
|
| 1338 |
+
"n": 1600,
|
| 1339 |
+
"acc": 0.82875,
|
| 1340 |
+
"nll": 0.6285893321037292,
|
| 1341 |
+
"brier": 0.25918903946876526,
|
| 1342 |
+
"ece": 0.07270433625206353,
|
| 1343 |
+
"aurc": 0.04255102774957042,
|
| 1344 |
+
"acc_at_80": 0.91171875,
|
| 1345 |
+
"acc_at_50": 0.975,
|
| 1346 |
+
"chance": 0.18774627976190478,
|
| 1347 |
+
"mean_conf": 0.9010530114173889,
|
| 1348 |
+
"sec": 2.3,
|
| 1349 |
+
"heldout": true
|
| 1350 |
}
|
| 1351 |
},
|
| 1352 |
"agg": {
|
| 1353 |
"in_task": {
|
| 1354 |
+
"acc": 0.8149500819963449,
|
| 1355 |
+
"nll": 0.44540443098968896,
|
| 1356 |
+
"brier": 0.2484059167917872,
|
| 1357 |
+
"ece": 0.027587339109589562,
|
| 1358 |
+
"aurc": 0.09255141592820487,
|
| 1359 |
+
"acc_at_80": 0.8653429127460076,
|
| 1360 |
"chance": 0.32498304691713953
|
| 1361 |
},
|
| 1362 |
"heldout": {
|
| 1363 |
+
"acc": 0.7384736622364532,
|
| 1364 |
+
"nll": 0.6866676495410502,
|
| 1365 |
+
"brier": 0.361666936504965,
|
| 1366 |
+
"ece": 0.0877105698314277,
|
| 1367 |
+
"aurc": 0.14519520391245042,
|
| 1368 |
+
"acc_at_80": 0.7926778581130387,
|
| 1369 |
+
"chance": 0.31500581773039266
|
| 1370 |
},
|
| 1371 |
"n_in": 69,
|
| 1372 |
+
"n_heldout": 24
|
| 1373 |
},
|
| 1374 |
+
"model": "runs/r10_v5/model",
|
| 1375 |
"engine": "compile"
|
| 1376 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3763692048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d8271b508f71697fd0a55e15fc98e1e894b93c0c37d97cbe5cc1111f81b2dca
|
| 3 |
size 3763692048
|
tokenizer_config.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"eos_token": "<|endoftext|>",
|
| 10 |
"errors": "replace",
|
| 11 |
"image_token": "<|image_pad|>",
|
| 12 |
-
"is_local":
|
| 13 |
"local_files_only": false,
|
| 14 |
"model_max_length": 262144,
|
| 15 |
"model_specific_special_tokens": {
|
|
|
|
| 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": {
|