🔄 Incremental label | Acc: 1.000, F1: 1.000
Browse files- README.md +8 -8
- {checkpoint-674 → checkpoint-337}/config.json +0 -0
- {checkpoint-674 → checkpoint-337}/model.safetensors +1 -1
- {checkpoint-674 → checkpoint-337}/special_tokens_map.json +0 -0
- {checkpoint-674 → checkpoint-337}/tokenizer.json +0 -0
- {checkpoint-674 → checkpoint-337}/tokenizer_config.json +0 -0
- {checkpoint-674 → checkpoint-337}/trainer_state.json +80 -333
- {checkpoint-674 → checkpoint-337}/vocab.txt +0 -0
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -21,19 +21,19 @@ Fine-tuned FinBERT model for financial sentiment analysis in TradePulse.
|
|
| 21 |
|
| 22 |
## Performance
|
| 23 |
|
| 24 |
-
*Last training: 2025-
|
| 25 |
*Dataset: `base_reference.csv` (1797 samples)*
|
| 26 |
|
| 27 |
| Metric | Value |
|
| 28 |
|--------|-------|
|
| 29 |
-
| Loss | 0.
|
| 30 |
-
| Accuracy |
|
| 31 |
-
| F1 Score |
|
| 32 |
|
| 33 |
-
| F1 Macro |
|
| 34 |
|
| 35 |
-
| Precision |
|
| 36 |
-
| Recall |
|
| 37 |
|
| 38 |
## Training Details
|
| 39 |
|
|
@@ -65,4 +65,4 @@ predictions = outputs.logits.softmax(dim=-1)
|
|
| 65 |
## Model Card Authors
|
| 66 |
|
| 67 |
- TradePulse ML Team
|
| 68 |
-
- Auto-generated on 2025-
|
|
|
|
| 21 |
|
| 22 |
## Performance
|
| 23 |
|
| 24 |
+
*Last training: 2025-09-09 11:52*
|
| 25 |
*Dataset: `base_reference.csv` (1797 samples)*
|
| 26 |
|
| 27 |
| Metric | Value |
|
| 28 |
|--------|-------|
|
| 29 |
+
| Loss | 0.0003 |
|
| 30 |
+
| Accuracy | 1.0000 |
|
| 31 |
+
| F1 Score | 1.0000 |
|
| 32 |
|
| 33 |
+
| F1 Macro | 1.0000 |
|
| 34 |
|
| 35 |
+
| Precision | 1.0000 |
|
| 36 |
+
| Recall | 1.0000 |
|
| 37 |
|
| 38 |
## Training Details
|
| 39 |
|
|
|
|
| 65 |
## Model Card Authors
|
| 66 |
|
| 67 |
- TradePulse ML Team
|
| 68 |
+
- Auto-generated on 2025-09-09 11:52:04
|
{checkpoint-674 → checkpoint-337}/config.json
RENAMED
|
File without changes
|
{checkpoint-674 → checkpoint-337}/model.safetensors
RENAMED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 439039996
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cc7fcb353e9884463270bfe3d032441a20f429ca5000067bf3adb2299fbec16
|
| 3 |
size 439039996
|
{checkpoint-674 → checkpoint-337}/special_tokens_map.json
RENAMED
|
File without changes
|
{checkpoint-674 → checkpoint-337}/tokenizer.json
RENAMED
|
File without changes
|
{checkpoint-674 → checkpoint-337}/tokenizer_config.json
RENAMED
|
File without changes
|
{checkpoint-674 → checkpoint-337}/trainer_state.json
RENAMED
|
@@ -1,511 +1,258 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0
|
| 3 |
-
"best_model_checkpoint": "hf-sentiment-production/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.02967359050445104,
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
"learning_rate": 2.9761904761904765e-07,
|
| 15 |
-
"loss":
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.05934718100890208,
|
| 20 |
-
"grad_norm":
|
| 21 |
"learning_rate": 5.952380952380953e-07,
|
| 22 |
-
"loss":
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.08902077151335312,
|
| 27 |
-
"grad_norm":
|
| 28 |
"learning_rate": 8.928571428571429e-07,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.11869436201780416,
|
| 34 |
-
"grad_norm":
|
| 35 |
"learning_rate": 1.1904761904761906e-06,
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.14836795252225518,
|
| 41 |
-
"grad_norm":
|
| 42 |
"learning_rate": 1.4880952380952381e-06,
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.17804154302670624,
|
| 48 |
-
"grad_norm":
|
| 49 |
"learning_rate": 1.7857142857142859e-06,
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.20771513353115728,
|
| 55 |
-
"grad_norm":
|
| 56 |
"learning_rate": 2.0833333333333334e-06,
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.23738872403560832,
|
| 62 |
-
"grad_norm":
|
| 63 |
"learning_rate": 2.380952380952381e-06,
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.26706231454005935,
|
| 69 |
-
"grad_norm": 0.
|
| 70 |
"learning_rate": 2.6785714285714285e-06,
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.29673590504451036,
|
| 76 |
-
"grad_norm":
|
| 77 |
"learning_rate": 2.9761904761904763e-06,
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.3264094955489614,
|
| 83 |
-
"grad_norm":
|
| 84 |
"learning_rate": 3.273809523809524e-06,
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.3560830860534125,
|
| 90 |
-
"grad_norm":
|
| 91 |
"learning_rate": 3.5714285714285718e-06,
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.3857566765578635,
|
| 97 |
-
"grad_norm":
|
| 98 |
"learning_rate": 3.869047619047619e-06,
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.41543026706231456,
|
| 104 |
-
"grad_norm":
|
| 105 |
"learning_rate": 4.166666666666667e-06,
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.44510385756676557,
|
| 111 |
-
"grad_norm":
|
| 112 |
"learning_rate": 4.464285714285715e-06,
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.47477744807121663,
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
"learning_rate": 4.761904761904762e-06,
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.5044510385756676,
|
| 125 |
-
"grad_norm":
|
| 126 |
"learning_rate": 5.05952380952381e-06,
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.5341246290801187,
|
| 132 |
-
"grad_norm":
|
| 133 |
"learning_rate": 5.357142857142857e-06,
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.5637982195845698,
|
| 139 |
-
"grad_norm":
|
| 140 |
"learning_rate": 5.654761904761905e-06,
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.5934718100890207,
|
| 146 |
-
"grad_norm":
|
| 147 |
"learning_rate": 5.9523809523809525e-06,
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.6231454005934718,
|
| 153 |
-
"grad_norm":
|
| 154 |
"learning_rate": 6.25e-06,
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 210
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.6528189910979229,
|
| 160 |
-
"grad_norm":
|
| 161 |
"learning_rate": 6.547619047619048e-06,
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 220
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.6824925816023739,
|
| 167 |
-
"grad_norm":
|
| 168 |
"learning_rate": 6.845238095238096e-06,
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 230
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.712166172106825,
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
"learning_rate": 7.1428571428571436e-06,
|
| 176 |
"loss": 0.0,
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.7418397626112759,
|
| 181 |
-
"grad_norm":
|
| 182 |
"learning_rate": 7.440476190476191e-06,
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.771513353115727,
|
| 188 |
-
"grad_norm":
|
| 189 |
"learning_rate": 7.738095238095238e-06,
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 260
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.8011869436201781,
|
| 195 |
-
"grad_norm":
|
| 196 |
"learning_rate": 8.035714285714286e-06,
|
| 197 |
"loss": 0.0,
|
| 198 |
"step": 270
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.8308605341246291,
|
| 202 |
-
"grad_norm":
|
| 203 |
"learning_rate": 8.333333333333334e-06,
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 280
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.8605341246290801,
|
| 209 |
-
"grad_norm":
|
| 210 |
"learning_rate": 8.630952380952381e-06,
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 290
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.8902077151335311,
|
| 216 |
-
"grad_norm":
|
| 217 |
"learning_rate": 8.92857142857143e-06,
|
| 218 |
"loss": 0.0,
|
| 219 |
"step": 300
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.9198813056379822,
|
| 223 |
-
"grad_norm":
|
| 224 |
"learning_rate": 9.226190476190477e-06,
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 310
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.9495548961424333,
|
| 230 |
-
"grad_norm":
|
| 231 |
"learning_rate": 9.523809523809525e-06,
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 320
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.9792284866468842,
|
| 237 |
-
"grad_norm":
|
| 238 |
"learning_rate": 9.821428571428573e-06,
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 330
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 1.0,
|
| 244 |
-
"eval_accuracy": 0
|
| 245 |
-
"eval_f1": 0
|
| 246 |
-
"eval_f1_macro": 0
|
| 247 |
-
"eval_loss": 0.
|
| 248 |
-
"eval_precision": 0
|
| 249 |
-
"eval_precision_macro": 0
|
| 250 |
-
"eval_recall": 0
|
| 251 |
-
"eval_recall_macro": 0
|
| 252 |
-
"eval_runtime":
|
| 253 |
-
"eval_samples_per_second": 1.
|
| 254 |
-
"eval_steps_per_second": 0.
|
| 255 |
"step": 337
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 1.0089020771513353,
|
| 259 |
-
"grad_norm": 0.00010033950820798054,
|
| 260 |
-
"learning_rate": 9.88165680473373e-06,
|
| 261 |
-
"loss": 0.1403,
|
| 262 |
-
"step": 340
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 1.0385756676557865,
|
| 266 |
-
"grad_norm": 0.013481284491717815,
|
| 267 |
-
"learning_rate": 9.585798816568049e-06,
|
| 268 |
-
"loss": 0.0,
|
| 269 |
-
"step": 350
|
| 270 |
-
},
|
| 271 |
-
{
|
| 272 |
-
"epoch": 1.0682492581602374,
|
| 273 |
-
"grad_norm": 0.0009898018324747682,
|
| 274 |
-
"learning_rate": 9.289940828402368e-06,
|
| 275 |
-
"loss": 0.0,
|
| 276 |
-
"step": 360
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 1.0979228486646884,
|
| 280 |
-
"grad_norm": 0.00012659125786740333,
|
| 281 |
-
"learning_rate": 8.994082840236687e-06,
|
| 282 |
-
"loss": 0.0,
|
| 283 |
-
"step": 370
|
| 284 |
-
},
|
| 285 |
-
{
|
| 286 |
-
"epoch": 1.1275964391691395,
|
| 287 |
-
"grad_norm": 0.00047182640992105007,
|
| 288 |
-
"learning_rate": 8.698224852071006e-06,
|
| 289 |
-
"loss": 0.0,
|
| 290 |
-
"step": 380
|
| 291 |
-
},
|
| 292 |
-
{
|
| 293 |
-
"epoch": 1.1572700296735905,
|
| 294 |
-
"grad_norm": 0.0001335637061856687,
|
| 295 |
-
"learning_rate": 8.402366863905327e-06,
|
| 296 |
-
"loss": 0.0,
|
| 297 |
-
"step": 390
|
| 298 |
-
},
|
| 299 |
-
{
|
| 300 |
-
"epoch": 1.1869436201780414,
|
| 301 |
-
"grad_norm": 0.0002707823005039245,
|
| 302 |
-
"learning_rate": 8.106508875739646e-06,
|
| 303 |
-
"loss": 0.0,
|
| 304 |
-
"step": 400
|
| 305 |
-
},
|
| 306 |
-
{
|
| 307 |
-
"epoch": 1.2166172106824926,
|
| 308 |
-
"grad_norm": 0.00016450774273835123,
|
| 309 |
-
"learning_rate": 7.810650887573965e-06,
|
| 310 |
-
"loss": 0.0,
|
| 311 |
-
"step": 410
|
| 312 |
-
},
|
| 313 |
-
{
|
| 314 |
-
"epoch": 1.2462908011869436,
|
| 315 |
-
"grad_norm": 0.0005354972090572119,
|
| 316 |
-
"learning_rate": 7.5147928994082845e-06,
|
| 317 |
-
"loss": 0.0,
|
| 318 |
-
"step": 420
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 1.2759643916913945,
|
| 322 |
-
"grad_norm": 0.00011406593694118783,
|
| 323 |
-
"learning_rate": 7.218934911242604e-06,
|
| 324 |
-
"loss": 0.0,
|
| 325 |
-
"step": 430
|
| 326 |
-
},
|
| 327 |
-
{
|
| 328 |
-
"epoch": 1.3056379821958457,
|
| 329 |
-
"grad_norm": 0.16808006167411804,
|
| 330 |
-
"learning_rate": 6.923076923076923e-06,
|
| 331 |
-
"loss": 0.0001,
|
| 332 |
-
"step": 440
|
| 333 |
-
},
|
| 334 |
-
{
|
| 335 |
-
"epoch": 1.3353115727002967,
|
| 336 |
-
"grad_norm": 8.87056376086548e-05,
|
| 337 |
-
"learning_rate": 6.627218934911244e-06,
|
| 338 |
-
"loss": 0.0,
|
| 339 |
-
"step": 450
|
| 340 |
-
},
|
| 341 |
-
{
|
| 342 |
-
"epoch": 1.3649851632047478,
|
| 343 |
-
"grad_norm": 0.0005222823820076883,
|
| 344 |
-
"learning_rate": 6.331360946745563e-06,
|
| 345 |
-
"loss": 0.0,
|
| 346 |
-
"step": 460
|
| 347 |
-
},
|
| 348 |
-
{
|
| 349 |
-
"epoch": 1.3946587537091988,
|
| 350 |
-
"grad_norm": 1.3695029338123277e-05,
|
| 351 |
-
"learning_rate": 6.035502958579882e-06,
|
| 352 |
-
"loss": 0.0,
|
| 353 |
-
"step": 470
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 1.4243323442136497,
|
| 357 |
-
"grad_norm": 5.737605533795431e-05,
|
| 358 |
-
"learning_rate": 5.739644970414202e-06,
|
| 359 |
-
"loss": 0.0,
|
| 360 |
-
"step": 480
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 1.454005934718101,
|
| 364 |
-
"grad_norm": 0.005723549518734217,
|
| 365 |
-
"learning_rate": 5.443786982248521e-06,
|
| 366 |
-
"loss": 0.0,
|
| 367 |
-
"step": 490
|
| 368 |
-
},
|
| 369 |
-
{
|
| 370 |
-
"epoch": 1.4836795252225519,
|
| 371 |
-
"grad_norm": 1.2021506336168386e-05,
|
| 372 |
-
"learning_rate": 5.14792899408284e-06,
|
| 373 |
-
"loss": 0.0,
|
| 374 |
-
"step": 500
|
| 375 |
-
},
|
| 376 |
-
{
|
| 377 |
-
"epoch": 1.513353115727003,
|
| 378 |
-
"grad_norm": 4.697950862464495e-05,
|
| 379 |
-
"learning_rate": 4.85207100591716e-06,
|
| 380 |
-
"loss": 0.0,
|
| 381 |
-
"step": 510
|
| 382 |
-
},
|
| 383 |
-
{
|
| 384 |
-
"epoch": 1.543026706231454,
|
| 385 |
-
"grad_norm": 0.000708841485902667,
|
| 386 |
-
"learning_rate": 4.55621301775148e-06,
|
| 387 |
-
"loss": 0.0,
|
| 388 |
-
"step": 520
|
| 389 |
-
},
|
| 390 |
-
{
|
| 391 |
-
"epoch": 1.572700296735905,
|
| 392 |
-
"grad_norm": 1.7618485799175687e-05,
|
| 393 |
-
"learning_rate": 4.2603550295858e-06,
|
| 394 |
-
"loss": 0.0,
|
| 395 |
-
"step": 530
|
| 396 |
-
},
|
| 397 |
-
{
|
| 398 |
-
"epoch": 1.6023738872403561,
|
| 399 |
-
"grad_norm": 0.00013081534416414797,
|
| 400 |
-
"learning_rate": 3.964497041420119e-06,
|
| 401 |
-
"loss": 0.0,
|
| 402 |
-
"step": 540
|
| 403 |
-
},
|
| 404 |
-
{
|
| 405 |
-
"epoch": 1.632047477744807,
|
| 406 |
-
"grad_norm": 0.00028243096312507987,
|
| 407 |
-
"learning_rate": 3.668639053254438e-06,
|
| 408 |
-
"loss": 0.0,
|
| 409 |
-
"step": 550
|
| 410 |
-
},
|
| 411 |
-
{
|
| 412 |
-
"epoch": 1.6617210682492582,
|
| 413 |
-
"grad_norm": 0.0002703359059523791,
|
| 414 |
-
"learning_rate": 3.3727810650887576e-06,
|
| 415 |
-
"loss": 0.0,
|
| 416 |
-
"step": 560
|
| 417 |
-
},
|
| 418 |
-
{
|
| 419 |
-
"epoch": 1.6913946587537092,
|
| 420 |
-
"grad_norm": 2.5464911232120357e-05,
|
| 421 |
-
"learning_rate": 3.0769230769230774e-06,
|
| 422 |
-
"loss": 0.0,
|
| 423 |
-
"step": 570
|
| 424 |
-
},
|
| 425 |
-
{
|
| 426 |
-
"epoch": 1.7210682492581602,
|
| 427 |
-
"grad_norm": 2.6416844775667414e-05,
|
| 428 |
-
"learning_rate": 2.7810650887573965e-06,
|
| 429 |
-
"loss": 0.0,
|
| 430 |
-
"step": 580
|
| 431 |
-
},
|
| 432 |
-
{
|
| 433 |
-
"epoch": 1.7507418397626113,
|
| 434 |
-
"grad_norm": 0.012607904151082039,
|
| 435 |
-
"learning_rate": 2.485207100591716e-06,
|
| 436 |
-
"loss": 0.051,
|
| 437 |
-
"step": 590
|
| 438 |
-
},
|
| 439 |
-
{
|
| 440 |
-
"epoch": 1.7804154302670623,
|
| 441 |
-
"grad_norm": 0.0064520263113081455,
|
| 442 |
-
"learning_rate": 2.1893491124260358e-06,
|
| 443 |
-
"loss": 0.0001,
|
| 444 |
-
"step": 600
|
| 445 |
-
},
|
| 446 |
-
{
|
| 447 |
-
"epoch": 1.8100890207715135,
|
| 448 |
-
"grad_norm": 0.00013779209984932095,
|
| 449 |
-
"learning_rate": 1.8934911242603552e-06,
|
| 450 |
-
"loss": 0.0,
|
| 451 |
-
"step": 610
|
| 452 |
-
},
|
| 453 |
-
{
|
| 454 |
-
"epoch": 1.8397626112759644,
|
| 455 |
-
"grad_norm": 0.00019228862947784364,
|
| 456 |
-
"learning_rate": 1.5976331360946749e-06,
|
| 457 |
-
"loss": 0.0,
|
| 458 |
-
"step": 620
|
| 459 |
-
},
|
| 460 |
-
{
|
| 461 |
-
"epoch": 1.8694362017804154,
|
| 462 |
-
"grad_norm": 3.4337310353294015e-05,
|
| 463 |
-
"learning_rate": 1.301775147928994e-06,
|
| 464 |
-
"loss": 0.0,
|
| 465 |
-
"step": 630
|
| 466 |
-
},
|
| 467 |
-
{
|
| 468 |
-
"epoch": 1.8991097922848663,
|
| 469 |
-
"grad_norm": 0.000257375038927421,
|
| 470 |
-
"learning_rate": 1.0059171597633138e-06,
|
| 471 |
-
"loss": 0.0,
|
| 472 |
-
"step": 640
|
| 473 |
-
},
|
| 474 |
-
{
|
| 475 |
-
"epoch": 1.9287833827893175,
|
| 476 |
-
"grad_norm": 0.0015161657938733697,
|
| 477 |
-
"learning_rate": 7.100591715976332e-07,
|
| 478 |
-
"loss": 0.001,
|
| 479 |
-
"step": 650
|
| 480 |
-
},
|
| 481 |
-
{
|
| 482 |
-
"epoch": 1.9584569732937687,
|
| 483 |
-
"grad_norm": 0.0051199602894485,
|
| 484 |
-
"learning_rate": 4.1420118343195276e-07,
|
| 485 |
-
"loss": 0.0,
|
| 486 |
-
"step": 660
|
| 487 |
-
},
|
| 488 |
-
{
|
| 489 |
-
"epoch": 1.9881305637982196,
|
| 490 |
-
"grad_norm": 0.0002789547143038362,
|
| 491 |
-
"learning_rate": 1.183431952662722e-07,
|
| 492 |
-
"loss": 0.0,
|
| 493 |
-
"step": 670
|
| 494 |
-
},
|
| 495 |
-
{
|
| 496 |
-
"epoch": 2.0,
|
| 497 |
-
"eval_accuracy": 0.9977777777777778,
|
| 498 |
-
"eval_f1": 0.9977731894655975,
|
| 499 |
-
"eval_f1_macro": 0.9971836215366922,
|
| 500 |
-
"eval_loss": 0.01406792365014553,
|
| 501 |
-
"eval_precision": 0.997787356321839,
|
| 502 |
-
"eval_precision_macro": 0.9985632183908045,
|
| 503 |
-
"eval_recall": 0.9977777777777778,
|
| 504 |
-
"eval_recall_macro": 0.9958333333333332,
|
| 505 |
-
"eval_runtime": 251.8116,
|
| 506 |
-
"eval_samples_per_second": 1.787,
|
| 507 |
-
"eval_steps_per_second": 0.449,
|
| 508 |
-
"step": 674
|
| 509 |
}
|
| 510 |
],
|
| 511 |
"logging_steps": 10,
|
|
@@ -529,12 +276,12 @@
|
|
| 529 |
"should_evaluate": false,
|
| 530 |
"should_log": false,
|
| 531 |
"should_save": true,
|
| 532 |
-
"should_training_stop":
|
| 533 |
},
|
| 534 |
"attributes": {}
|
| 535 |
}
|
| 536 |
},
|
| 537 |
-
"total_flos":
|
| 538 |
"train_batch_size": 4,
|
| 539 |
"trial_name": null,
|
| 540 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "hf-sentiment-production/checkpoint-337",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 337,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.02967359050445104,
|
| 13 |
+
"grad_norm": 0.00024139029846992344,
|
| 14 |
"learning_rate": 2.9761904761904765e-07,
|
| 15 |
+
"loss": 0.0,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.05934718100890208,
|
| 20 |
+
"grad_norm": 0.0006298513617366552,
|
| 21 |
"learning_rate": 5.952380952380953e-07,
|
| 22 |
+
"loss": 0.0,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.08902077151335312,
|
| 27 |
+
"grad_norm": 5.432798570836894e-05,
|
| 28 |
"learning_rate": 8.928571428571429e-07,
|
| 29 |
+
"loss": 0.0,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.11869436201780416,
|
| 34 |
+
"grad_norm": 0.00013781266170553863,
|
| 35 |
"learning_rate": 1.1904761904761906e-06,
|
| 36 |
+
"loss": 0.0,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.14836795252225518,
|
| 41 |
+
"grad_norm": 3.0851035262458026e-05,
|
| 42 |
"learning_rate": 1.4880952380952381e-06,
|
| 43 |
+
"loss": 0.0,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.17804154302670624,
|
| 48 |
+
"grad_norm": 4.912382792099379e-05,
|
| 49 |
"learning_rate": 1.7857142857142859e-06,
|
| 50 |
+
"loss": 0.0,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.20771513353115728,
|
| 55 |
+
"grad_norm": 0.00010233318607788533,
|
| 56 |
"learning_rate": 2.0833333333333334e-06,
|
| 57 |
+
"loss": 0.0,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.23738872403560832,
|
| 62 |
+
"grad_norm": 8.538426300219726e-06,
|
| 63 |
"learning_rate": 2.380952380952381e-06,
|
| 64 |
+
"loss": 0.0,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.26706231454005935,
|
| 69 |
+
"grad_norm": 0.0010961185907945037,
|
| 70 |
"learning_rate": 2.6785714285714285e-06,
|
| 71 |
+
"loss": 0.0,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.29673590504451036,
|
| 76 |
+
"grad_norm": 0.00015762148541398346,
|
| 77 |
"learning_rate": 2.9761904761904763e-06,
|
| 78 |
+
"loss": 0.0,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.3264094955489614,
|
| 83 |
+
"grad_norm": 9.907303137879353e-06,
|
| 84 |
"learning_rate": 3.273809523809524e-06,
|
| 85 |
+
"loss": 0.0,
|
| 86 |
"step": 110
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.3560830860534125,
|
| 90 |
+
"grad_norm": 1.993760270124767e-05,
|
| 91 |
"learning_rate": 3.5714285714285718e-06,
|
| 92 |
+
"loss": 0.0,
|
| 93 |
"step": 120
|
| 94 |
},
|
| 95 |
{
|
| 96 |
"epoch": 0.3857566765578635,
|
| 97 |
+
"grad_norm": 5.402106762630865e-05,
|
| 98 |
"learning_rate": 3.869047619047619e-06,
|
| 99 |
+
"loss": 0.0,
|
| 100 |
"step": 130
|
| 101 |
},
|
| 102 |
{
|
| 103 |
"epoch": 0.41543026706231456,
|
| 104 |
+
"grad_norm": 3.3530592190800235e-05,
|
| 105 |
"learning_rate": 4.166666666666667e-06,
|
| 106 |
+
"loss": 0.0,
|
| 107 |
"step": 140
|
| 108 |
},
|
| 109 |
{
|
| 110 |
"epoch": 0.44510385756676557,
|
| 111 |
+
"grad_norm": 2.3308602976612747e-06,
|
| 112 |
"learning_rate": 4.464285714285715e-06,
|
| 113 |
+
"loss": 0.0,
|
| 114 |
"step": 150
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.47477744807121663,
|
| 118 |
+
"grad_norm": 0.00014736008597537875,
|
| 119 |
"learning_rate": 4.761904761904762e-06,
|
| 120 |
+
"loss": 0.0,
|
| 121 |
"step": 160
|
| 122 |
},
|
| 123 |
{
|
| 124 |
"epoch": 0.5044510385756676,
|
| 125 |
+
"grad_norm": 1.862984208855778e-05,
|
| 126 |
"learning_rate": 5.05952380952381e-06,
|
| 127 |
+
"loss": 0.0,
|
| 128 |
"step": 170
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.5341246290801187,
|
| 132 |
+
"grad_norm": 7.657575770281255e-05,
|
| 133 |
"learning_rate": 5.357142857142857e-06,
|
| 134 |
+
"loss": 0.0,
|
| 135 |
"step": 180
|
| 136 |
},
|
| 137 |
{
|
| 138 |
"epoch": 0.5637982195845698,
|
| 139 |
+
"grad_norm": 3.495160490274429e-05,
|
| 140 |
"learning_rate": 5.654761904761905e-06,
|
| 141 |
+
"loss": 0.0,
|
| 142 |
"step": 190
|
| 143 |
},
|
| 144 |
{
|
| 145 |
"epoch": 0.5934718100890207,
|
| 146 |
+
"grad_norm": 7.668938633287326e-05,
|
| 147 |
"learning_rate": 5.9523809523809525e-06,
|
| 148 |
+
"loss": 0.0,
|
| 149 |
"step": 200
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.6231454005934718,
|
| 153 |
+
"grad_norm": 3.3768927096389234e-05,
|
| 154 |
"learning_rate": 6.25e-06,
|
| 155 |
+
"loss": 0.0001,
|
| 156 |
"step": 210
|
| 157 |
},
|
| 158 |
{
|
| 159 |
"epoch": 0.6528189910979229,
|
| 160 |
+
"grad_norm": 0.028401218354701996,
|
| 161 |
"learning_rate": 6.547619047619048e-06,
|
| 162 |
+
"loss": 0.0,
|
| 163 |
"step": 220
|
| 164 |
},
|
| 165 |
{
|
| 166 |
"epoch": 0.6824925816023739,
|
| 167 |
+
"grad_norm": 3.132776328129694e-05,
|
| 168 |
"learning_rate": 6.845238095238096e-06,
|
| 169 |
+
"loss": 0.0,
|
| 170 |
"step": 230
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.712166172106825,
|
| 174 |
+
"grad_norm": 0.0001778039732016623,
|
| 175 |
"learning_rate": 7.1428571428571436e-06,
|
| 176 |
"loss": 0.0,
|
| 177 |
"step": 240
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.7418397626112759,
|
| 181 |
+
"grad_norm": 2.132856025127694e-06,
|
| 182 |
"learning_rate": 7.440476190476191e-06,
|
| 183 |
+
"loss": 0.0,
|
| 184 |
"step": 250
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.771513353115727,
|
| 188 |
+
"grad_norm": 1.4033699699211866e-05,
|
| 189 |
"learning_rate": 7.738095238095238e-06,
|
| 190 |
+
"loss": 0.0,
|
| 191 |
"step": 260
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.8011869436201781,
|
| 195 |
+
"grad_norm": 9.22418348636711e-06,
|
| 196 |
"learning_rate": 8.035714285714286e-06,
|
| 197 |
"loss": 0.0,
|
| 198 |
"step": 270
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.8308605341246291,
|
| 202 |
+
"grad_norm": 8.610751137894113e-06,
|
| 203 |
"learning_rate": 8.333333333333334e-06,
|
| 204 |
+
"loss": 0.0,
|
| 205 |
"step": 280
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.8605341246290801,
|
| 209 |
+
"grad_norm": 1.3859172440788825e-06,
|
| 210 |
"learning_rate": 8.630952380952381e-06,
|
| 211 |
+
"loss": 0.0,
|
| 212 |
"step": 290
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.8902077151335311,
|
| 216 |
+
"grad_norm": 3.807801704169833e-06,
|
| 217 |
"learning_rate": 8.92857142857143e-06,
|
| 218 |
"loss": 0.0,
|
| 219 |
"step": 300
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.9198813056379822,
|
| 223 |
+
"grad_norm": 7.167540024966002e-05,
|
| 224 |
"learning_rate": 9.226190476190477e-06,
|
| 225 |
+
"loss": 0.0,
|
| 226 |
"step": 310
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.9495548961424333,
|
| 230 |
+
"grad_norm": 1.2782682460965589e-05,
|
| 231 |
"learning_rate": 9.523809523809525e-06,
|
| 232 |
+
"loss": 0.0,
|
| 233 |
"step": 320
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.9792284866468842,
|
| 237 |
+
"grad_norm": 7.706138603680301e-06,
|
| 238 |
"learning_rate": 9.821428571428573e-06,
|
| 239 |
+
"loss": 0.0,
|
| 240 |
"step": 330
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 1.0,
|
| 244 |
+
"eval_accuracy": 1.0,
|
| 245 |
+
"eval_f1": 1.0,
|
| 246 |
+
"eval_f1_macro": 1.0,
|
| 247 |
+
"eval_loss": 0.00034992388100363314,
|
| 248 |
+
"eval_precision": 1.0,
|
| 249 |
+
"eval_precision_macro": 1.0,
|
| 250 |
+
"eval_recall": 1.0,
|
| 251 |
+
"eval_recall_macro": 1.0,
|
| 252 |
+
"eval_runtime": 251.3627,
|
| 253 |
+
"eval_samples_per_second": 1.79,
|
| 254 |
+
"eval_steps_per_second": 0.45,
|
| 255 |
"step": 337
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 256 |
}
|
| 257 |
],
|
| 258 |
"logging_steps": 10,
|
|
|
|
| 276 |
"should_evaluate": false,
|
| 277 |
"should_log": false,
|
| 278 |
"should_save": true,
|
| 279 |
+
"should_training_stop": false
|
| 280 |
},
|
| 281 |
"attributes": {}
|
| 282 |
}
|
| 283 |
},
|
| 284 |
+
"total_flos": 354413773679616.0,
|
| 285 |
"train_batch_size": 4,
|
| 286 |
"trial_name": null,
|
| 287 |
"trial_params": null
|
{checkpoint-674 → checkpoint-337}/vocab.txt
RENAMED
|
File without changes
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 439039996
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7cc7fcb353e9884463270bfe3d032441a20f429ca5000067bf3adb2299fbec16
|
| 3 |
size 439039996
|