End of training
Browse files- README.md +5 -5
- all_results.json +14 -14
- eval_results.json +9 -9
- runs/Sep04_13-14-39_5bdf525bf655/events.out.tfevents.1725458001.5bdf525bf655.4076.3 +3 -0
- train_results.json +6 -6
- trainer_state.json +475 -762
README.md
CHANGED
|
@@ -20,11 +20,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-224](https://huggingface.co/facebook/convnextv2-base-22k-224) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Accuracy: 0.
|
| 25 |
-
- F1: 0.
|
| 26 |
-
- Precision: 0.
|
| 27 |
-
- Recall: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [facebook/convnextv2-base-22k-224](https://huggingface.co/facebook/convnextv2-base-22k-224) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.9468
|
| 24 |
+
- Accuracy: 0.5932
|
| 25 |
+
- F1: 0.5674
|
| 26 |
+
- Precision: 0.5709
|
| 27 |
+
- Recall: 0.5932
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
all_results.json
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 11.
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime": 10.
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second": 6.
|
| 11 |
-
"total_flos":
|
| 12 |
-
"train_loss": 1.
|
| 13 |
-
"train_runtime":
|
| 14 |
-
"train_samples_per_second":
|
| 15 |
-
"train_steps_per_second": 0.
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 11.956043956043956,
|
| 3 |
+
"eval_accuracy": 0.5932047750229569,
|
| 4 |
+
"eval_f1": 0.5674291939014156,
|
| 5 |
+
"eval_loss": 0.9468401074409485,
|
| 6 |
+
"eval_precision": 0.5709384462011384,
|
| 7 |
+
"eval_recall": 0.5932047750229569,
|
| 8 |
+
"eval_runtime": 10.108,
|
| 9 |
+
"eval_samples_per_second": 107.737,
|
| 10 |
+
"eval_steps_per_second": 6.826,
|
| 11 |
+
"total_flos": 4.123334853511373e+18,
|
| 12 |
+
"train_loss": 1.090085435147379,
|
| 13 |
+
"train_runtime": 2115.1144,
|
| 14 |
+
"train_samples_per_second": 24.697,
|
| 15 |
+
"train_steps_per_second": 0.386
|
| 16 |
}
|
eval_results.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 11.
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime": 10.
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second": 6.
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 11.956043956043956,
|
| 3 |
+
"eval_accuracy": 0.5932047750229569,
|
| 4 |
+
"eval_f1": 0.5674291939014156,
|
| 5 |
+
"eval_loss": 0.9468401074409485,
|
| 6 |
+
"eval_precision": 0.5709384462011384,
|
| 7 |
+
"eval_recall": 0.5932047750229569,
|
| 8 |
+
"eval_runtime": 10.108,
|
| 9 |
+
"eval_samples_per_second": 107.737,
|
| 10 |
+
"eval_steps_per_second": 6.826
|
| 11 |
}
|
runs/Sep04_13-14-39_5bdf525bf655/events.out.tfevents.1725458001.5bdf525bf655.4076.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d628f1953adcbffb811c23a083711fdbc320a593f1e5f0c11b8471c81024a13b
|
| 3 |
+
size 560
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 11.
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 1.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 11.956043956043956,
|
| 3 |
+
"total_flos": 4.123334853511373e+18,
|
| 4 |
+
"train_loss": 1.090085435147379,
|
| 5 |
+
"train_runtime": 2115.1144,
|
| 6 |
+
"train_samples_per_second": 24.697,
|
| 7 |
+
"train_steps_per_second": 0.386
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1023 +1,736 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "convnextv2-base-22k-224-finetuned-tekno24/checkpoint-
|
| 4 |
-
"epoch": 11.
|
| 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.
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 1.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate": 1.
|
| 29 |
-
"loss": 1.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss": 1.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"
|
| 56 |
-
"
|
| 57 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch":
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 1.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch":
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 1.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch":
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 1.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch":
|
| 83 |
-
"
|
| 84 |
-
"
|
| 85 |
-
"
|
| 86 |
-
"eval_precision": 0.4782877718762662,
|
| 87 |
-
"eval_recall": 0.5206611570247934,
|
| 88 |
-
"eval_runtime": 10.5321,
|
| 89 |
-
"eval_samples_per_second": 103.399,
|
| 90 |
-
"eval_steps_per_second": 6.551,
|
| 91 |
-
"step": 102
|
| 92 |
-
},
|
| 93 |
-
{
|
| 94 |
-
"epoch": 1.0731707317073171,
|
| 95 |
-
"grad_norm": 11.261804580688477,
|
| 96 |
-
"learning_rate": 4.390243902439025e-05,
|
| 97 |
-
"loss": 1.2688,
|
| 98 |
"step": 110
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch": 1.
|
| 102 |
-
"grad_norm":
|
| 103 |
-
"learning_rate": 4.
|
| 104 |
-
"loss": 1.
|
| 105 |
"step": 120
|
| 106 |
},
|
| 107 |
{
|
| 108 |
-
"epoch": 1.
|
| 109 |
-
"grad_norm":
|
| 110 |
-
"learning_rate": 4.
|
| 111 |
-
"loss": 1.
|
| 112 |
"step": 130
|
| 113 |
},
|
| 114 |
{
|
| 115 |
-
"epoch": 1.
|
| 116 |
-
"
|
| 117 |
-
"
|
| 118 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
"step": 140
|
| 120 |
},
|
| 121 |
{
|
| 122 |
-
"epoch":
|
| 123 |
-
"grad_norm":
|
| 124 |
-
"learning_rate": 4.
|
| 125 |
-
"loss": 1.
|
| 126 |
"step": 150
|
| 127 |
},
|
| 128 |
{
|
| 129 |
-
"epoch":
|
| 130 |
-
"grad_norm":
|
| 131 |
-
"learning_rate": 4.
|
| 132 |
-
"loss": 1.
|
| 133 |
"step": 160
|
| 134 |
},
|
| 135 |
{
|
| 136 |
-
"epoch":
|
| 137 |
-
"grad_norm": 7.
|
| 138 |
-
"learning_rate": 4.
|
| 139 |
-
"loss": 1.
|
| 140 |
"step": 170
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch":
|
| 144 |
-
"grad_norm":
|
| 145 |
-
"learning_rate": 4.
|
| 146 |
-
"loss": 1.
|
| 147 |
"step": 180
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch":
|
| 151 |
-
"grad_norm":
|
| 152 |
-
"learning_rate": 4.
|
| 153 |
-
"loss": 1.
|
| 154 |
"step": 190
|
| 155 |
},
|
| 156 |
{
|
| 157 |
-
"epoch":
|
| 158 |
-
"grad_norm":
|
| 159 |
-
"learning_rate": 4.
|
| 160 |
-
"loss": 1.
|
| 161 |
"step": 200
|
| 162 |
},
|
| 163 |
{
|
| 164 |
-
"epoch": 2.
|
| 165 |
-
"eval_accuracy": 0.
|
| 166 |
-
"eval_f1": 0.
|
| 167 |
-
"eval_loss": 1.
|
| 168 |
-
"eval_precision": 0.
|
| 169 |
-
"eval_recall": 0.
|
| 170 |
-
"eval_runtime": 10.
|
| 171 |
-
"eval_samples_per_second": 103.
|
| 172 |
-
"eval_steps_per_second": 6.
|
| 173 |
-
"step":
|
| 174 |
},
|
| 175 |
{
|
| 176 |
-
"epoch":
|
| 177 |
-
"grad_norm":
|
| 178 |
-
"learning_rate": 4.
|
| 179 |
-
"loss": 1.
|
| 180 |
"step": 210
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"epoch":
|
| 184 |
-
"grad_norm":
|
| 185 |
-
"learning_rate": 4.
|
| 186 |
-
"loss": 1.
|
| 187 |
"step": 220
|
| 188 |
},
|
| 189 |
{
|
| 190 |
-
"epoch":
|
| 191 |
-
"grad_norm":
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss": 1.
|
| 194 |
"step": 230
|
| 195 |
},
|
| 196 |
{
|
| 197 |
-
"epoch":
|
| 198 |
-
"grad_norm":
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 1.
|
| 201 |
"step": 240
|
| 202 |
},
|
| 203 |
{
|
| 204 |
-
"epoch":
|
| 205 |
-
"grad_norm":
|
| 206 |
-
"learning_rate":
|
| 207 |
-
"loss": 1.
|
| 208 |
"step": 250
|
| 209 |
},
|
| 210 |
{
|
| 211 |
-
"epoch":
|
| 212 |
-
"grad_norm":
|
| 213 |
-
"learning_rate":
|
| 214 |
-
"loss": 1.
|
| 215 |
"step": 260
|
| 216 |
},
|
| 217 |
{
|
| 218 |
-
"epoch":
|
| 219 |
-
"grad_norm":
|
| 220 |
-
"learning_rate":
|
| 221 |
-
"loss": 1.
|
| 222 |
"step": 270
|
| 223 |
},
|
| 224 |
{
|
| 225 |
-
"epoch":
|
| 226 |
-
"
|
| 227 |
-
"
|
| 228 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 229 |
"step": 280
|
| 230 |
},
|
| 231 |
{
|
| 232 |
-
"epoch":
|
| 233 |
-
"grad_norm":
|
| 234 |
-
"learning_rate":
|
| 235 |
-
"loss": 1.
|
| 236 |
"step": 290
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch":
|
| 240 |
-
"grad_norm": 7.
|
| 241 |
-
"learning_rate":
|
| 242 |
-
"loss": 1.
|
| 243 |
"step": 300
|
| 244 |
},
|
| 245 |
{
|
| 246 |
-
"epoch":
|
| 247 |
-
"
|
| 248 |
-
"
|
| 249 |
-
"
|
| 250 |
-
"eval_precision": 0.5588554246566038,
|
| 251 |
-
"eval_recall": 0.4830119375573921,
|
| 252 |
-
"eval_runtime": 10.5448,
|
| 253 |
-
"eval_samples_per_second": 103.274,
|
| 254 |
-
"eval_steps_per_second": 6.544,
|
| 255 |
-
"step": 307
|
| 256 |
-
},
|
| 257 |
-
{
|
| 258 |
-
"epoch": 3.024390243902439,
|
| 259 |
-
"grad_norm": 7.887587547302246,
|
| 260 |
-
"learning_rate": 4.159854677565849e-05,
|
| 261 |
-
"loss": 1.1419,
|
| 262 |
"step": 310
|
| 263 |
},
|
| 264 |
{
|
| 265 |
-
"epoch":
|
| 266 |
-
"grad_norm":
|
| 267 |
-
"learning_rate":
|
| 268 |
-
"loss": 1.
|
| 269 |
"step": 320
|
| 270 |
},
|
| 271 |
{
|
| 272 |
-
"epoch":
|
| 273 |
-
"grad_norm":
|
| 274 |
-
"learning_rate":
|
| 275 |
-
"loss": 1.
|
| 276 |
"step": 330
|
| 277 |
},
|
| 278 |
{
|
| 279 |
-
"epoch":
|
| 280 |
-
"grad_norm":
|
| 281 |
-
"learning_rate":
|
| 282 |
-
"loss": 1.
|
| 283 |
"step": 340
|
| 284 |
},
|
| 285 |
{
|
| 286 |
-
"epoch":
|
| 287 |
-
"
|
| 288 |
-
"
|
| 289 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 290 |
"step": 350
|
| 291 |
},
|
| 292 |
{
|
| 293 |
-
"epoch":
|
| 294 |
-
"grad_norm":
|
| 295 |
-
"learning_rate": 3.
|
| 296 |
-
"loss": 1.
|
| 297 |
"step": 360
|
| 298 |
},
|
| 299 |
{
|
| 300 |
-
"epoch":
|
| 301 |
-
"grad_norm": 7.
|
| 302 |
-
"learning_rate": 3.
|
| 303 |
-
"loss": 1.
|
| 304 |
"step": 370
|
| 305 |
},
|
| 306 |
{
|
| 307 |
-
"epoch":
|
| 308 |
-
"grad_norm":
|
| 309 |
-
"learning_rate":
|
| 310 |
-
"loss": 1.
|
| 311 |
"step": 380
|
| 312 |
},
|
| 313 |
{
|
| 314 |
-
"epoch":
|
| 315 |
-
"grad_norm": 8.
|
| 316 |
-
"learning_rate":
|
| 317 |
-
"loss": 1.
|
| 318 |
"step": 390
|
| 319 |
},
|
| 320 |
{
|
| 321 |
-
"epoch":
|
| 322 |
-
"grad_norm":
|
| 323 |
-
"learning_rate":
|
| 324 |
-
"loss": 1.
|
| 325 |
"step": 400
|
| 326 |
},
|
| 327 |
{
|
| 328 |
-
"epoch":
|
| 329 |
-
"
|
| 330 |
-
"
|
| 331 |
-
"
|
| 332 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 333 |
},
|
| 334 |
{
|
| 335 |
-
"epoch":
|
| 336 |
-
"
|
| 337 |
-
"
|
| 338 |
-
"
|
| 339 |
-
"eval_precision": 0.5357616363900534,
|
| 340 |
-
"eval_recall": 0.5619834710743802,
|
| 341 |
-
"eval_runtime": 10.5649,
|
| 342 |
-
"eval_samples_per_second": 103.077,
|
| 343 |
-
"eval_steps_per_second": 6.531,
|
| 344 |
"step": 410
|
| 345 |
},
|
| 346 |
{
|
| 347 |
-
"epoch":
|
| 348 |
-
"grad_norm":
|
| 349 |
-
"learning_rate":
|
| 350 |
-
"loss": 1.
|
| 351 |
"step": 420
|
| 352 |
},
|
| 353 |
{
|
| 354 |
-
"epoch":
|
| 355 |
-
"grad_norm":
|
| 356 |
-
"learning_rate":
|
| 357 |
-
"loss": 1.
|
| 358 |
"step": 430
|
| 359 |
},
|
| 360 |
{
|
| 361 |
-
"epoch":
|
| 362 |
-
"grad_norm":
|
| 363 |
-
"learning_rate":
|
| 364 |
-
"loss": 1.
|
| 365 |
"step": 440
|
| 366 |
},
|
| 367 |
{
|
| 368 |
-
"epoch":
|
| 369 |
-
"grad_norm":
|
| 370 |
-
"learning_rate":
|
| 371 |
-
"loss": 1.
|
| 372 |
"step": 450
|
| 373 |
},
|
| 374 |
{
|
| 375 |
-
"epoch":
|
| 376 |
-
"grad_norm":
|
| 377 |
-
"learning_rate":
|
| 378 |
-
"loss": 1.
|
| 379 |
"step": 460
|
| 380 |
},
|
| 381 |
{
|
| 382 |
-
"epoch":
|
| 383 |
-
"grad_norm":
|
| 384 |
-
"learning_rate":
|
| 385 |
-
"loss": 1.
|
| 386 |
"step": 470
|
| 387 |
},
|
| 388 |
{
|
| 389 |
-
"epoch":
|
| 390 |
-
"
|
| 391 |
-
"
|
| 392 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 393 |
"step": 480
|
| 394 |
},
|
| 395 |
{
|
| 396 |
-
"epoch":
|
| 397 |
-
"grad_norm":
|
| 398 |
-
"learning_rate":
|
| 399 |
-
"loss": 1.
|
| 400 |
"step": 490
|
| 401 |
},
|
| 402 |
{
|
| 403 |
-
"epoch":
|
| 404 |
-
"grad_norm": 8.
|
| 405 |
-
"learning_rate":
|
| 406 |
-
"loss": 1.
|
| 407 |
"step": 500
|
| 408 |
},
|
| 409 |
{
|
| 410 |
-
"epoch":
|
| 411 |
-
"grad_norm":
|
| 412 |
-
"learning_rate":
|
| 413 |
-
"loss":
|
| 414 |
"step": 510
|
| 415 |
},
|
| 416 |
{
|
| 417 |
-
"epoch":
|
| 418 |
-
"
|
| 419 |
-
"
|
| 420 |
-
"
|
| 421 |
-
"eval_precision": 0.5719778943634586,
|
| 422 |
-
"eval_recall": 0.5344352617079889,
|
| 423 |
-
"eval_runtime": 10.4912,
|
| 424 |
-
"eval_samples_per_second": 103.801,
|
| 425 |
-
"eval_steps_per_second": 6.577,
|
| 426 |
-
"step": 512
|
| 427 |
-
},
|
| 428 |
-
{
|
| 429 |
-
"epoch": 5.073170731707317,
|
| 430 |
-
"grad_norm": 6.753456115722656,
|
| 431 |
-
"learning_rate": 3.206176203451408e-05,
|
| 432 |
-
"loss": 1.0425,
|
| 433 |
"step": 520
|
| 434 |
},
|
| 435 |
{
|
| 436 |
-
"epoch":
|
| 437 |
-
"grad_norm":
|
| 438 |
-
"learning_rate":
|
| 439 |
-
"loss": 1.
|
| 440 |
"step": 530
|
| 441 |
},
|
| 442 |
{
|
| 443 |
-
"epoch":
|
| 444 |
-
"grad_norm":
|
| 445 |
-
"learning_rate":
|
| 446 |
-
"loss": 1.
|
| 447 |
"step": 540
|
| 448 |
},
|
| 449 |
{
|
| 450 |
-
"epoch":
|
| 451 |
-
"
|
| 452 |
-
"
|
| 453 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 454 |
"step": 550
|
| 455 |
},
|
| 456 |
{
|
| 457 |
-
"epoch":
|
| 458 |
-
"grad_norm":
|
| 459 |
-
"learning_rate":
|
| 460 |
-
"loss": 1.
|
| 461 |
"step": 560
|
| 462 |
},
|
| 463 |
{
|
| 464 |
-
"epoch":
|
| 465 |
-
"grad_norm":
|
| 466 |
-
"learning_rate":
|
| 467 |
-
"loss":
|
| 468 |
"step": 570
|
| 469 |
},
|
| 470 |
{
|
| 471 |
-
"epoch":
|
| 472 |
-
"grad_norm": 10.
|
| 473 |
-
"learning_rate":
|
| 474 |
-
"loss":
|
| 475 |
"step": 580
|
| 476 |
},
|
| 477 |
{
|
| 478 |
-
"epoch":
|
| 479 |
-
"grad_norm":
|
| 480 |
-
"learning_rate":
|
| 481 |
-
"loss": 1.
|
| 482 |
"step": 590
|
| 483 |
},
|
| 484 |
{
|
| 485 |
-
"epoch":
|
| 486 |
-
"grad_norm":
|
| 487 |
-
"learning_rate":
|
| 488 |
-
"loss": 1.
|
| 489 |
"step": 600
|
| 490 |
},
|
| 491 |
{
|
| 492 |
-
"epoch":
|
| 493 |
-
"grad_norm":
|
| 494 |
-
"learning_rate":
|
| 495 |
-
"loss": 1.
|
| 496 |
"step": 610
|
| 497 |
},
|
| 498 |
{
|
| 499 |
-
"epoch":
|
| 500 |
-
"eval_accuracy": 0.
|
| 501 |
-
"eval_f1": 0.
|
| 502 |
-
"eval_loss": 0.
|
| 503 |
-
"eval_precision": 0.
|
| 504 |
-
"eval_recall": 0.
|
| 505 |
-
"eval_runtime": 10.
|
| 506 |
-
"eval_samples_per_second": 103.
|
| 507 |
-
"eval_steps_per_second": 6.
|
| 508 |
-
"step":
|
| 509 |
},
|
| 510 |
{
|
| 511 |
-
"epoch":
|
| 512 |
-
"grad_norm":
|
| 513 |
-
"learning_rate":
|
| 514 |
-
"loss": 0.
|
| 515 |
"step": 620
|
| 516 |
},
|
| 517 |
{
|
| 518 |
-
"epoch":
|
| 519 |
-
"grad_norm":
|
| 520 |
-
"learning_rate":
|
| 521 |
-
"loss": 1.
|
| 522 |
"step": 630
|
| 523 |
},
|
| 524 |
{
|
| 525 |
-
"epoch":
|
| 526 |
-
"grad_norm":
|
| 527 |
-
"learning_rate":
|
| 528 |
-
"loss":
|
| 529 |
"step": 640
|
| 530 |
},
|
| 531 |
{
|
| 532 |
-
"epoch":
|
| 533 |
-
"grad_norm":
|
| 534 |
-
"learning_rate":
|
| 535 |
-
"loss":
|
| 536 |
"step": 650
|
| 537 |
},
|
| 538 |
{
|
| 539 |
-
"epoch":
|
| 540 |
-
"grad_norm":
|
| 541 |
-
"learning_rate":
|
| 542 |
-
"loss":
|
| 543 |
"step": 660
|
| 544 |
},
|
| 545 |
{
|
| 546 |
-
"epoch":
|
| 547 |
-
"grad_norm":
|
| 548 |
-
"learning_rate":
|
| 549 |
-
"loss":
|
| 550 |
"step": 670
|
| 551 |
},
|
| 552 |
{
|
| 553 |
-
"epoch":
|
| 554 |
-
"grad_norm": 10.
|
| 555 |
-
"learning_rate":
|
| 556 |
-
"loss": 0.
|
| 557 |
"step": 680
|
| 558 |
},
|
| 559 |
{
|
| 560 |
-
"epoch":
|
| 561 |
-
"
|
| 562 |
-
"
|
| 563 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 564 |
"step": 690
|
| 565 |
},
|
| 566 |
{
|
| 567 |
-
"epoch":
|
| 568 |
-
"grad_norm":
|
| 569 |
-
"learning_rate":
|
| 570 |
-
"loss":
|
| 571 |
"step": 700
|
| 572 |
},
|
| 573 |
{
|
| 574 |
-
"epoch":
|
| 575 |
-
"grad_norm": 11.
|
| 576 |
-
"learning_rate":
|
| 577 |
-
"loss":
|
| 578 |
"step": 710
|
| 579 |
},
|
| 580 |
{
|
| 581 |
-
"epoch":
|
| 582 |
-
"
|
| 583 |
-
"
|
| 584 |
-
"
|
| 585 |
-
"eval_precision": 0.5624792636698613,
|
| 586 |
-
"eval_recall": 0.559228650137741,
|
| 587 |
-
"eval_runtime": 10.478,
|
| 588 |
-
"eval_samples_per_second": 103.932,
|
| 589 |
-
"eval_steps_per_second": 6.585,
|
| 590 |
-
"step": 717
|
| 591 |
-
},
|
| 592 |
-
{
|
| 593 |
-
"epoch": 7.024390243902439,
|
| 594 |
-
"grad_norm": 7.640585899353027,
|
| 595 |
-
"learning_rate": 2.297910990009083e-05,
|
| 596 |
-
"loss": 1.0333,
|
| 597 |
"step": 720
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch":
|
| 601 |
-
"grad_norm": 10.
|
| 602 |
-
"learning_rate":
|
| 603 |
-
"loss": 0.
|
| 604 |
"step": 730
|
| 605 |
},
|
| 606 |
{
|
| 607 |
-
"epoch":
|
| 608 |
-
"grad_norm":
|
| 609 |
-
"learning_rate":
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 740
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch":
|
| 615 |
-
"grad_norm":
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 618 |
"step": 750
|
| 619 |
},
|
| 620 |
{
|
| 621 |
-
"epoch":
|
| 622 |
-
"grad_norm":
|
| 623 |
-
"learning_rate":
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 760
|
| 626 |
},
|
| 627 |
{
|
| 628 |
-
"epoch":
|
| 629 |
-
"grad_norm":
|
| 630 |
-
"learning_rate":
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 770
|
| 633 |
},
|
| 634 |
{
|
| 635 |
-
"epoch":
|
| 636 |
-
"grad_norm":
|
| 637 |
-
"learning_rate": 2.
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 780
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch":
|
| 643 |
-
"grad_norm":
|
| 644 |
-
"learning_rate": 1.
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 790
|
| 647 |
},
|
| 648 |
{
|
| 649 |
-
"epoch":
|
| 650 |
-
"grad_norm":
|
| 651 |
-
"learning_rate": 1.
|
| 652 |
-
"loss": 0.
|
| 653 |
"step": 800
|
| 654 |
},
|
| 655 |
{
|
| 656 |
-
"epoch":
|
| 657 |
-
"grad_norm": 8.
|
| 658 |
-
"learning_rate":
|
| 659 |
-
"loss": 0.
|
| 660 |
"step": 810
|
| 661 |
},
|
| 662 |
{
|
| 663 |
-
"epoch":
|
| 664 |
-
"
|
| 665 |
-
"
|
| 666 |
-
"
|
| 667 |
-
"
|
| 668 |
-
|
| 669 |
-
|
| 670 |
-
"
|
| 671 |
-
"
|
| 672 |
-
"
|
| 673 |
-
|
| 674 |
-
|
| 675 |
-
"
|
| 676 |
-
"
|
| 677 |
-
"
|
| 678 |
-
"
|
| 679 |
-
"
|
| 680 |
-
|
| 681 |
-
|
| 682 |
-
"epoch": 8.097560975609756,
|
| 683 |
-
"grad_norm": 8.30269718170166,
|
| 684 |
-
"learning_rate": 1.798365122615804e-05,
|
| 685 |
-
"loss": 0.9005,
|
| 686 |
-
"step": 830
|
| 687 |
-
},
|
| 688 |
-
{
|
| 689 |
-
"epoch": 8.195121951219512,
|
| 690 |
-
"grad_norm": 10.962409973144531,
|
| 691 |
-
"learning_rate": 1.7529518619436876e-05,
|
| 692 |
-
"loss": 0.9167,
|
| 693 |
-
"step": 840
|
| 694 |
-
},
|
| 695 |
-
{
|
| 696 |
-
"epoch": 8.292682926829269,
|
| 697 |
-
"grad_norm": 8.846582412719727,
|
| 698 |
-
"learning_rate": 1.7075386012715714e-05,
|
| 699 |
-
"loss": 0.9393,
|
| 700 |
-
"step": 850
|
| 701 |
-
},
|
| 702 |
-
{
|
| 703 |
-
"epoch": 8.390243902439025,
|
| 704 |
-
"grad_norm": 10.282524108886719,
|
| 705 |
-
"learning_rate": 1.662125340599455e-05,
|
| 706 |
-
"loss": 0.9473,
|
| 707 |
-
"step": 860
|
| 708 |
-
},
|
| 709 |
-
{
|
| 710 |
-
"epoch": 8.487804878048781,
|
| 711 |
-
"grad_norm": 11.323814392089844,
|
| 712 |
-
"learning_rate": 1.616712079927339e-05,
|
| 713 |
-
"loss": 0.8695,
|
| 714 |
-
"step": 870
|
| 715 |
-
},
|
| 716 |
-
{
|
| 717 |
-
"epoch": 8.585365853658537,
|
| 718 |
-
"grad_norm": 10.95213794708252,
|
| 719 |
-
"learning_rate": 1.5712988192552226e-05,
|
| 720 |
-
"loss": 0.9257,
|
| 721 |
-
"step": 880
|
| 722 |
-
},
|
| 723 |
-
{
|
| 724 |
-
"epoch": 8.682926829268293,
|
| 725 |
-
"grad_norm": 11.248684883117676,
|
| 726 |
-
"learning_rate": 1.5258855585831064e-05,
|
| 727 |
-
"loss": 0.8916,
|
| 728 |
-
"step": 890
|
| 729 |
-
},
|
| 730 |
-
{
|
| 731 |
-
"epoch": 8.78048780487805,
|
| 732 |
-
"grad_norm": 10.221022605895996,
|
| 733 |
-
"learning_rate": 1.48047229791099e-05,
|
| 734 |
-
"loss": 0.8961,
|
| 735 |
-
"step": 900
|
| 736 |
-
},
|
| 737 |
-
{
|
| 738 |
-
"epoch": 8.878048780487806,
|
| 739 |
-
"grad_norm": 8.226391792297363,
|
| 740 |
-
"learning_rate": 1.4350590372388739e-05,
|
| 741 |
-
"loss": 0.8783,
|
| 742 |
-
"step": 910
|
| 743 |
-
},
|
| 744 |
-
{
|
| 745 |
-
"epoch": 8.975609756097562,
|
| 746 |
-
"grad_norm": 9.135197639465332,
|
| 747 |
-
"learning_rate": 1.3896457765667576e-05,
|
| 748 |
-
"loss": 0.8856,
|
| 749 |
-
"step": 920
|
| 750 |
-
},
|
| 751 |
-
{
|
| 752 |
-
"epoch": 8.995121951219513,
|
| 753 |
-
"eval_accuracy": 0.5564738292011019,
|
| 754 |
-
"eval_f1": 0.556882933826955,
|
| 755 |
-
"eval_loss": 1.0059682130813599,
|
| 756 |
-
"eval_precision": 0.5592586252036796,
|
| 757 |
-
"eval_recall": 0.5564738292011019,
|
| 758 |
-
"eval_runtime": 10.5466,
|
| 759 |
-
"eval_samples_per_second": 103.256,
|
| 760 |
-
"eval_steps_per_second": 6.542,
|
| 761 |
-
"step": 922
|
| 762 |
-
},
|
| 763 |
-
{
|
| 764 |
-
"epoch": 9.073170731707316,
|
| 765 |
-
"grad_norm": 11.500414848327637,
|
| 766 |
-
"learning_rate": 1.3442325158946412e-05,
|
| 767 |
-
"loss": 0.8476,
|
| 768 |
-
"step": 930
|
| 769 |
-
},
|
| 770 |
-
{
|
| 771 |
-
"epoch": 9.170731707317072,
|
| 772 |
-
"grad_norm": 11.68885612487793,
|
| 773 |
-
"learning_rate": 1.2988192552225251e-05,
|
| 774 |
-
"loss": 0.869,
|
| 775 |
-
"step": 940
|
| 776 |
-
},
|
| 777 |
-
{
|
| 778 |
-
"epoch": 9.268292682926829,
|
| 779 |
-
"grad_norm": 9.877538681030273,
|
| 780 |
-
"learning_rate": 1.2534059945504087e-05,
|
| 781 |
-
"loss": 0.8572,
|
| 782 |
-
"step": 950
|
| 783 |
-
},
|
| 784 |
-
{
|
| 785 |
-
"epoch": 9.365853658536585,
|
| 786 |
-
"grad_norm": 11.605177879333496,
|
| 787 |
-
"learning_rate": 1.2079927338782924e-05,
|
| 788 |
-
"loss": 0.8434,
|
| 789 |
-
"step": 960
|
| 790 |
-
},
|
| 791 |
-
{
|
| 792 |
-
"epoch": 9.463414634146341,
|
| 793 |
-
"grad_norm": 10.330570220947266,
|
| 794 |
-
"learning_rate": 1.1625794732061762e-05,
|
| 795 |
-
"loss": 0.894,
|
| 796 |
-
"step": 970
|
| 797 |
-
},
|
| 798 |
-
{
|
| 799 |
-
"epoch": 9.560975609756097,
|
| 800 |
-
"grad_norm": 9.849478721618652,
|
| 801 |
-
"learning_rate": 1.11716621253406e-05,
|
| 802 |
-
"loss": 0.894,
|
| 803 |
-
"step": 980
|
| 804 |
-
},
|
| 805 |
-
{
|
| 806 |
-
"epoch": 9.658536585365853,
|
| 807 |
-
"grad_norm": 9.98214340209961,
|
| 808 |
-
"learning_rate": 1.0717529518619437e-05,
|
| 809 |
-
"loss": 0.8652,
|
| 810 |
-
"step": 990
|
| 811 |
-
},
|
| 812 |
-
{
|
| 813 |
-
"epoch": 9.75609756097561,
|
| 814 |
-
"grad_norm": 9.999092102050781,
|
| 815 |
-
"learning_rate": 1.0263396911898274e-05,
|
| 816 |
-
"loss": 0.8855,
|
| 817 |
-
"step": 1000
|
| 818 |
-
},
|
| 819 |
-
{
|
| 820 |
-
"epoch": 9.853658536585366,
|
| 821 |
-
"grad_norm": 10.021332740783691,
|
| 822 |
-
"learning_rate": 9.809264305177112e-06,
|
| 823 |
-
"loss": 0.8754,
|
| 824 |
-
"step": 1010
|
| 825 |
-
},
|
| 826 |
-
{
|
| 827 |
-
"epoch": 9.951219512195122,
|
| 828 |
-
"grad_norm": 10.624610900878906,
|
| 829 |
-
"learning_rate": 9.35513169845595e-06,
|
| 830 |
-
"loss": 0.8306,
|
| 831 |
-
"step": 1020
|
| 832 |
-
},
|
| 833 |
-
{
|
| 834 |
-
"epoch": 10.0,
|
| 835 |
-
"eval_accuracy": 0.566574839302112,
|
| 836 |
-
"eval_f1": 0.5574087205222212,
|
| 837 |
-
"eval_loss": 0.9907031655311584,
|
| 838 |
-
"eval_precision": 0.5531200477134914,
|
| 839 |
-
"eval_recall": 0.566574839302112,
|
| 840 |
-
"eval_runtime": 10.5011,
|
| 841 |
-
"eval_samples_per_second": 103.703,
|
| 842 |
-
"eval_steps_per_second": 6.571,
|
| 843 |
-
"step": 1025
|
| 844 |
-
},
|
| 845 |
-
{
|
| 846 |
-
"epoch": 10.048780487804878,
|
| 847 |
-
"grad_norm": 9.162467956542969,
|
| 848 |
-
"learning_rate": 8.900999091734787e-06,
|
| 849 |
-
"loss": 0.8177,
|
| 850 |
-
"step": 1030
|
| 851 |
-
},
|
| 852 |
-
{
|
| 853 |
-
"epoch": 10.146341463414634,
|
| 854 |
-
"grad_norm": 9.493200302124023,
|
| 855 |
-
"learning_rate": 8.446866485013624e-06,
|
| 856 |
-
"loss": 0.7632,
|
| 857 |
-
"step": 1040
|
| 858 |
-
},
|
| 859 |
-
{
|
| 860 |
-
"epoch": 10.24390243902439,
|
| 861 |
-
"grad_norm": 9.642596244812012,
|
| 862 |
-
"learning_rate": 7.992733878292462e-06,
|
| 863 |
-
"loss": 0.7732,
|
| 864 |
-
"step": 1050
|
| 865 |
-
},
|
| 866 |
-
{
|
| 867 |
-
"epoch": 10.341463414634147,
|
| 868 |
-
"grad_norm": 11.928635597229004,
|
| 869 |
-
"learning_rate": 7.538601271571299e-06,
|
| 870 |
-
"loss": 0.7979,
|
| 871 |
-
"step": 1060
|
| 872 |
-
},
|
| 873 |
-
{
|
| 874 |
-
"epoch": 10.439024390243903,
|
| 875 |
-
"grad_norm": 9.884861946105957,
|
| 876 |
-
"learning_rate": 7.084468664850137e-06,
|
| 877 |
-
"loss": 0.834,
|
| 878 |
-
"step": 1070
|
| 879 |
-
},
|
| 880 |
-
{
|
| 881 |
-
"epoch": 10.536585365853659,
|
| 882 |
-
"grad_norm": 10.674219131469727,
|
| 883 |
-
"learning_rate": 6.6303360581289735e-06,
|
| 884 |
-
"loss": 0.83,
|
| 885 |
-
"step": 1080
|
| 886 |
-
},
|
| 887 |
-
{
|
| 888 |
-
"epoch": 10.634146341463415,
|
| 889 |
-
"grad_norm": 11.04780387878418,
|
| 890 |
-
"learning_rate": 6.176203451407812e-06,
|
| 891 |
-
"loss": 0.8157,
|
| 892 |
-
"step": 1090
|
| 893 |
-
},
|
| 894 |
-
{
|
| 895 |
-
"epoch": 10.731707317073171,
|
| 896 |
-
"grad_norm": 11.664216995239258,
|
| 897 |
-
"learning_rate": 5.7220708446866485e-06,
|
| 898 |
-
"loss": 0.8041,
|
| 899 |
-
"step": 1100
|
| 900 |
-
},
|
| 901 |
-
{
|
| 902 |
-
"epoch": 10.829268292682928,
|
| 903 |
-
"grad_norm": 11.164298057556152,
|
| 904 |
-
"learning_rate": 5.267938237965486e-06,
|
| 905 |
-
"loss": 0.7685,
|
| 906 |
-
"step": 1110
|
| 907 |
-
},
|
| 908 |
-
{
|
| 909 |
-
"epoch": 10.926829268292684,
|
| 910 |
-
"grad_norm": 11.851963996887207,
|
| 911 |
-
"learning_rate": 4.813805631244324e-06,
|
| 912 |
-
"loss": 0.8458,
|
| 913 |
-
"step": 1120
|
| 914 |
-
},
|
| 915 |
-
{
|
| 916 |
-
"epoch": 10.995121951219513,
|
| 917 |
-
"eval_accuracy": 0.5500459136822773,
|
| 918 |
-
"eval_f1": 0.5489227474870219,
|
| 919 |
-
"eval_loss": 1.0134857892990112,
|
| 920 |
-
"eval_precision": 0.5505838083040273,
|
| 921 |
-
"eval_recall": 0.5500459136822773,
|
| 922 |
-
"eval_runtime": 10.4709,
|
| 923 |
-
"eval_samples_per_second": 104.003,
|
| 924 |
-
"eval_steps_per_second": 6.59,
|
| 925 |
-
"step": 1127
|
| 926 |
-
},
|
| 927 |
-
{
|
| 928 |
-
"epoch": 11.024390243902438,
|
| 929 |
-
"grad_norm": 9.90632438659668,
|
| 930 |
-
"learning_rate": 4.359673024523161e-06,
|
| 931 |
-
"loss": 0.7881,
|
| 932 |
-
"step": 1130
|
| 933 |
-
},
|
| 934 |
-
{
|
| 935 |
-
"epoch": 11.121951219512194,
|
| 936 |
-
"grad_norm": 11.564204216003418,
|
| 937 |
-
"learning_rate": 3.9055404178019984e-06,
|
| 938 |
-
"loss": 0.7449,
|
| 939 |
-
"step": 1140
|
| 940 |
-
},
|
| 941 |
-
{
|
| 942 |
-
"epoch": 11.21951219512195,
|
| 943 |
-
"grad_norm": 10.323161125183105,
|
| 944 |
-
"learning_rate": 3.451407811080836e-06,
|
| 945 |
-
"loss": 0.7865,
|
| 946 |
-
"step": 1150
|
| 947 |
-
},
|
| 948 |
-
{
|
| 949 |
-
"epoch": 11.317073170731707,
|
| 950 |
-
"grad_norm": 11.201330184936523,
|
| 951 |
-
"learning_rate": 2.997275204359673e-06,
|
| 952 |
-
"loss": 0.781,
|
| 953 |
-
"step": 1160
|
| 954 |
-
},
|
| 955 |
-
{
|
| 956 |
-
"epoch": 11.414634146341463,
|
| 957 |
-
"grad_norm": 9.596723556518555,
|
| 958 |
-
"learning_rate": 2.5431425976385105e-06,
|
| 959 |
-
"loss": 0.7847,
|
| 960 |
-
"step": 1170
|
| 961 |
-
},
|
| 962 |
-
{
|
| 963 |
-
"epoch": 11.512195121951219,
|
| 964 |
-
"grad_norm": 10.385799407958984,
|
| 965 |
-
"learning_rate": 2.089009990917348e-06,
|
| 966 |
-
"loss": 0.8139,
|
| 967 |
-
"step": 1180
|
| 968 |
-
},
|
| 969 |
-
{
|
| 970 |
-
"epoch": 11.609756097560975,
|
| 971 |
-
"grad_norm": 12.413230895996094,
|
| 972 |
-
"learning_rate": 1.6348773841961852e-06,
|
| 973 |
-
"loss": 0.7824,
|
| 974 |
-
"step": 1190
|
| 975 |
-
},
|
| 976 |
-
{
|
| 977 |
-
"epoch": 11.707317073170731,
|
| 978 |
-
"grad_norm": 10.438215255737305,
|
| 979 |
-
"learning_rate": 1.1807447774750227e-06,
|
| 980 |
-
"loss": 0.7464,
|
| 981 |
-
"step": 1200
|
| 982 |
-
},
|
| 983 |
-
{
|
| 984 |
-
"epoch": 11.804878048780488,
|
| 985 |
-
"grad_norm": 10.087923049926758,
|
| 986 |
-
"learning_rate": 7.266121707538601e-07,
|
| 987 |
-
"loss": 0.8032,
|
| 988 |
-
"step": 1210
|
| 989 |
-
},
|
| 990 |
-
{
|
| 991 |
-
"epoch": 11.902439024390244,
|
| 992 |
-
"grad_norm": 10.667466163635254,
|
| 993 |
-
"learning_rate": 2.7247956403269756e-07,
|
| 994 |
-
"loss": 0.815,
|
| 995 |
-
"step": 1220
|
| 996 |
-
},
|
| 997 |
-
{
|
| 998 |
-
"epoch": 11.941463414634146,
|
| 999 |
-
"eval_accuracy": 0.549127640036731,
|
| 1000 |
-
"eval_f1": 0.5520258447427934,
|
| 1001 |
-
"eval_loss": 1.0185083150863647,
|
| 1002 |
-
"eval_precision": 0.5558049078671707,
|
| 1003 |
-
"eval_recall": 0.549127640036731,
|
| 1004 |
-
"eval_runtime": 10.5534,
|
| 1005 |
-
"eval_samples_per_second": 103.19,
|
| 1006 |
-
"eval_steps_per_second": 6.538,
|
| 1007 |
-
"step": 1224
|
| 1008 |
-
},
|
| 1009 |
-
{
|
| 1010 |
-
"epoch": 11.941463414634146,
|
| 1011 |
-
"step": 1224,
|
| 1012 |
-
"total_flos": 6.197635483154842e+18,
|
| 1013 |
-
"train_loss": 1.0363535090209612,
|
| 1014 |
-
"train_runtime": 3088.0708,
|
| 1015 |
-
"train_samples_per_second": 25.461,
|
| 1016 |
-
"train_steps_per_second": 0.396
|
| 1017 |
}
|
| 1018 |
],
|
| 1019 |
"logging_steps": 10,
|
| 1020 |
-
"max_steps":
|
| 1021 |
"num_input_tokens_seen": 0,
|
| 1022 |
"num_train_epochs": 12,
|
| 1023 |
"save_steps": 500,
|
|
@@ -1033,7 +746,7 @@
|
|
| 1033 |
"attributes": {}
|
| 1034 |
}
|
| 1035 |
},
|
| 1036 |
-
"total_flos":
|
| 1037 |
"train_batch_size": 16,
|
| 1038 |
"trial_name": null,
|
| 1039 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.5932047750229569,
|
| 3 |
+
"best_model_checkpoint": "convnextv2-base-22k-224-finetuned-tekno24/checkpoint-614",
|
| 4 |
+
"epoch": 11.956043956043956,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 816,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.14652014652014653,
|
| 13 |
+
"grad_norm": 16.747648239135742,
|
| 14 |
+
"learning_rate": 6.0975609756097564e-06,
|
| 15 |
+
"loss": 1.4185,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.29304029304029305,
|
| 20 |
+
"grad_norm": 14.544577598571777,
|
| 21 |
+
"learning_rate": 1.2195121951219513e-05,
|
| 22 |
+
"loss": 1.4153,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.43956043956043955,
|
| 27 |
+
"grad_norm": 12.55716323852539,
|
| 28 |
+
"learning_rate": 1.8292682926829268e-05,
|
| 29 |
+
"loss": 1.3581,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.5860805860805861,
|
| 34 |
+
"grad_norm": 16.329694747924805,
|
| 35 |
+
"learning_rate": 2.378048780487805e-05,
|
| 36 |
+
"loss": 1.3421,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.7326007326007326,
|
| 41 |
+
"grad_norm": 9.924437522888184,
|
| 42 |
+
"learning_rate": 2.9878048780487805e-05,
|
| 43 |
+
"loss": 1.3174,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.8791208791208791,
|
| 48 |
+
"grad_norm": 8.243997573852539,
|
| 49 |
+
"learning_rate": 3.597560975609756e-05,
|
| 50 |
+
"loss": 1.2755,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.9963369963369964,
|
| 55 |
+
"eval_accuracy": 0.4903581267217631,
|
| 56 |
+
"eval_f1": 0.39101576597192117,
|
| 57 |
+
"eval_loss": 1.2008219957351685,
|
| 58 |
+
"eval_precision": 0.45771669331368264,
|
| 59 |
+
"eval_recall": 0.4903581267217631,
|
| 60 |
+
"eval_runtime": 10.5546,
|
| 61 |
+
"eval_samples_per_second": 103.178,
|
| 62 |
+
"eval_steps_per_second": 6.537,
|
| 63 |
+
"step": 68
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.0256410256410255,
|
| 67 |
+
"grad_norm": 13.558063507080078,
|
| 68 |
+
"learning_rate": 4.207317073170732e-05,
|
| 69 |
+
"loss": 1.2711,
|
| 70 |
"step": 70
|
| 71 |
},
|
| 72 |
{
|
| 73 |
+
"epoch": 1.1721611721611722,
|
| 74 |
+
"grad_norm": 27.544034957885742,
|
| 75 |
+
"learning_rate": 4.817073170731707e-05,
|
| 76 |
+
"loss": 1.2731,
|
| 77 |
"step": 80
|
| 78 |
},
|
| 79 |
{
|
| 80 |
+
"epoch": 1.3186813186813187,
|
| 81 |
+
"grad_norm": 12.061452865600586,
|
| 82 |
+
"learning_rate": 4.952316076294278e-05,
|
| 83 |
+
"loss": 1.2582,
|
| 84 |
"step": 90
|
| 85 |
},
|
| 86 |
{
|
| 87 |
+
"epoch": 1.4652014652014653,
|
| 88 |
+
"grad_norm": 13.313647270202637,
|
| 89 |
+
"learning_rate": 4.884196185286104e-05,
|
| 90 |
+
"loss": 1.2729,
|
| 91 |
"step": 100
|
| 92 |
},
|
| 93 |
{
|
| 94 |
+
"epoch": 1.6117216117216118,
|
| 95 |
+
"grad_norm": 8.85893440246582,
|
| 96 |
+
"learning_rate": 4.816076294277929e-05,
|
| 97 |
+
"loss": 1.2093,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
"step": 110
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 1.7582417582417582,
|
| 102 |
+
"grad_norm": 7.619632244110107,
|
| 103 |
+
"learning_rate": 4.747956403269755e-05,
|
| 104 |
+
"loss": 1.2445,
|
| 105 |
"step": 120
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 1.9047619047619047,
|
| 109 |
+
"grad_norm": 9.313189506530762,
|
| 110 |
+
"learning_rate": 4.6798365122615805e-05,
|
| 111 |
+
"loss": 1.1711,
|
| 112 |
"step": 130
|
| 113 |
},
|
| 114 |
{
|
| 115 |
+
"epoch": 1.9926739926739927,
|
| 116 |
+
"eval_accuracy": 0.5353535353535354,
|
| 117 |
+
"eval_f1": 0.47656758341858724,
|
| 118 |
+
"eval_loss": 1.0650511980056763,
|
| 119 |
+
"eval_precision": 0.48653241546321574,
|
| 120 |
+
"eval_recall": 0.5353535353535354,
|
| 121 |
+
"eval_runtime": 10.5232,
|
| 122 |
+
"eval_samples_per_second": 103.486,
|
| 123 |
+
"eval_steps_per_second": 6.557,
|
| 124 |
+
"step": 136
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.051282051282051,
|
| 128 |
+
"grad_norm": 9.400361061096191,
|
| 129 |
+
"learning_rate": 4.6117166212534065e-05,
|
| 130 |
+
"loss": 1.1145,
|
| 131 |
"step": 140
|
| 132 |
},
|
| 133 |
{
|
| 134 |
+
"epoch": 2.197802197802198,
|
| 135 |
+
"grad_norm": 5.284915924072266,
|
| 136 |
+
"learning_rate": 4.543596730245232e-05,
|
| 137 |
+
"loss": 1.1809,
|
| 138 |
"step": 150
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 2.3443223443223444,
|
| 142 |
+
"grad_norm": 10.18017292022705,
|
| 143 |
+
"learning_rate": 4.475476839237057e-05,
|
| 144 |
+
"loss": 1.1668,
|
| 145 |
"step": 160
|
| 146 |
},
|
| 147 |
{
|
| 148 |
+
"epoch": 2.490842490842491,
|
| 149 |
+
"grad_norm": 7.79976224899292,
|
| 150 |
+
"learning_rate": 4.407356948228883e-05,
|
| 151 |
+
"loss": 1.1582,
|
| 152 |
"step": 170
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 2.6373626373626373,
|
| 156 |
+
"grad_norm": 8.457806587219238,
|
| 157 |
+
"learning_rate": 4.339237057220708e-05,
|
| 158 |
+
"loss": 1.1628,
|
| 159 |
"step": 180
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 2.7838827838827838,
|
| 163 |
+
"grad_norm": 6.220970630645752,
|
| 164 |
+
"learning_rate": 4.271117166212534e-05,
|
| 165 |
+
"loss": 1.2035,
|
| 166 |
"step": 190
|
| 167 |
},
|
| 168 |
{
|
| 169 |
+
"epoch": 2.9304029304029307,
|
| 170 |
+
"grad_norm": 7.159059524536133,
|
| 171 |
+
"learning_rate": 4.20299727520436e-05,
|
| 172 |
+
"loss": 1.1599,
|
| 173 |
"step": 200
|
| 174 |
},
|
| 175 |
{
|
| 176 |
+
"epoch": 2.989010989010989,
|
| 177 |
+
"eval_accuracy": 0.54178145087236,
|
| 178 |
+
"eval_f1": 0.5077316365087595,
|
| 179 |
+
"eval_loss": 1.0533095598220825,
|
| 180 |
+
"eval_precision": 0.5274645952658832,
|
| 181 |
+
"eval_recall": 0.54178145087236,
|
| 182 |
+
"eval_runtime": 10.5408,
|
| 183 |
+
"eval_samples_per_second": 103.313,
|
| 184 |
+
"eval_steps_per_second": 6.546,
|
| 185 |
+
"step": 204
|
| 186 |
},
|
| 187 |
{
|
| 188 |
+
"epoch": 3.076923076923077,
|
| 189 |
+
"grad_norm": 5.542409896850586,
|
| 190 |
+
"learning_rate": 4.1348773841961855e-05,
|
| 191 |
+
"loss": 1.1692,
|
| 192 |
"step": 210
|
| 193 |
},
|
| 194 |
{
|
| 195 |
+
"epoch": 3.2234432234432235,
|
| 196 |
+
"grad_norm": 7.356290340423584,
|
| 197 |
+
"learning_rate": 4.066757493188011e-05,
|
| 198 |
+
"loss": 1.1176,
|
| 199 |
"step": 220
|
| 200 |
},
|
| 201 |
{
|
| 202 |
+
"epoch": 3.36996336996337,
|
| 203 |
+
"grad_norm": 6.849288463592529,
|
| 204 |
+
"learning_rate": 3.998637602179837e-05,
|
| 205 |
+
"loss": 1.1335,
|
| 206 |
"step": 230
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 3.5164835164835164,
|
| 210 |
+
"grad_norm": 11.968345642089844,
|
| 211 |
+
"learning_rate": 3.930517711171662e-05,
|
| 212 |
+
"loss": 1.14,
|
| 213 |
"step": 240
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 3.663003663003663,
|
| 217 |
+
"grad_norm": 8.681733131408691,
|
| 218 |
+
"learning_rate": 3.862397820163488e-05,
|
| 219 |
+
"loss": 1.1195,
|
| 220 |
"step": 250
|
| 221 |
},
|
| 222 |
{
|
| 223 |
+
"epoch": 3.8095238095238093,
|
| 224 |
+
"grad_norm": 8.258611679077148,
|
| 225 |
+
"learning_rate": 3.794277929155314e-05,
|
| 226 |
+
"loss": 1.1578,
|
| 227 |
"step": 260
|
| 228 |
},
|
| 229 |
{
|
| 230 |
+
"epoch": 3.956043956043956,
|
| 231 |
+
"grad_norm": 9.197736740112305,
|
| 232 |
+
"learning_rate": 3.726158038147139e-05,
|
| 233 |
+
"loss": 1.1595,
|
| 234 |
"step": 270
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"epoch": 4.0,
|
| 238 |
+
"eval_accuracy": 0.5454545454545454,
|
| 239 |
+
"eval_f1": 0.5413509466694156,
|
| 240 |
+
"eval_loss": 1.0423349142074585,
|
| 241 |
+
"eval_precision": 0.5690587889084956,
|
| 242 |
+
"eval_recall": 0.5454545454545454,
|
| 243 |
+
"eval_runtime": 10.5435,
|
| 244 |
+
"eval_samples_per_second": 103.286,
|
| 245 |
+
"eval_steps_per_second": 6.544,
|
| 246 |
+
"step": 273
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 4.102564102564102,
|
| 250 |
+
"grad_norm": 7.987867832183838,
|
| 251 |
+
"learning_rate": 3.6580381471389645e-05,
|
| 252 |
+
"loss": 1.0988,
|
| 253 |
"step": 280
|
| 254 |
},
|
| 255 |
{
|
| 256 |
+
"epoch": 4.249084249084249,
|
| 257 |
+
"grad_norm": 6.383251667022705,
|
| 258 |
+
"learning_rate": 3.5899182561307905e-05,
|
| 259 |
+
"loss": 1.1338,
|
| 260 |
"step": 290
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 4.395604395604396,
|
| 264 |
+
"grad_norm": 7.749887943267822,
|
| 265 |
+
"learning_rate": 3.521798365122616e-05,
|
| 266 |
+
"loss": 1.1635,
|
| 267 |
"step": 300
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 4.542124542124542,
|
| 271 |
+
"grad_norm": 9.830282211303711,
|
| 272 |
+
"learning_rate": 3.453678474114442e-05,
|
| 273 |
+
"loss": 1.0912,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 274 |
"step": 310
|
| 275 |
},
|
| 276 |
{
|
| 277 |
+
"epoch": 4.688644688644689,
|
| 278 |
+
"grad_norm": 9.785733222961426,
|
| 279 |
+
"learning_rate": 3.385558583106267e-05,
|
| 280 |
+
"loss": 1.1293,
|
| 281 |
"step": 320
|
| 282 |
},
|
| 283 |
{
|
| 284 |
+
"epoch": 4.835164835164835,
|
| 285 |
+
"grad_norm": 9.794586181640625,
|
| 286 |
+
"learning_rate": 3.317438692098093e-05,
|
| 287 |
+
"loss": 1.0867,
|
| 288 |
"step": 330
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 4.981684981684982,
|
| 292 |
+
"grad_norm": 5.60059928894043,
|
| 293 |
+
"learning_rate": 3.249318801089918e-05,
|
| 294 |
+
"loss": 1.096,
|
| 295 |
"step": 340
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 4.996336996336996,
|
| 299 |
+
"eval_accuracy": 0.5610651974288338,
|
| 300 |
+
"eval_f1": 0.5462709659715219,
|
| 301 |
+
"eval_loss": 1.0159707069396973,
|
| 302 |
+
"eval_precision": 0.5419035604614381,
|
| 303 |
+
"eval_recall": 0.5610651974288338,
|
| 304 |
+
"eval_runtime": 10.5161,
|
| 305 |
+
"eval_samples_per_second": 103.556,
|
| 306 |
+
"eval_steps_per_second": 6.561,
|
| 307 |
+
"step": 341
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 5.128205128205128,
|
| 311 |
+
"grad_norm": 6.809742450714111,
|
| 312 |
+
"learning_rate": 3.181198910081744e-05,
|
| 313 |
+
"loss": 1.071,
|
| 314 |
"step": 350
|
| 315 |
},
|
| 316 |
{
|
| 317 |
+
"epoch": 5.274725274725275,
|
| 318 |
+
"grad_norm": 7.61679744720459,
|
| 319 |
+
"learning_rate": 3.1130790190735695e-05,
|
| 320 |
+
"loss": 1.1031,
|
| 321 |
"step": 360
|
| 322 |
},
|
| 323 |
{
|
| 324 |
+
"epoch": 5.4212454212454215,
|
| 325 |
+
"grad_norm": 7.127725601196289,
|
| 326 |
+
"learning_rate": 3.0449591280653955e-05,
|
| 327 |
+
"loss": 1.0971,
|
| 328 |
"step": 370
|
| 329 |
},
|
| 330 |
{
|
| 331 |
+
"epoch": 5.5677655677655675,
|
| 332 |
+
"grad_norm": 6.362829685211182,
|
| 333 |
+
"learning_rate": 2.9768392370572208e-05,
|
| 334 |
+
"loss": 1.1078,
|
| 335 |
"step": 380
|
| 336 |
},
|
| 337 |
{
|
| 338 |
+
"epoch": 5.714285714285714,
|
| 339 |
+
"grad_norm": 8.149834632873535,
|
| 340 |
+
"learning_rate": 2.9087193460490464e-05,
|
| 341 |
+
"loss": 1.0871,
|
| 342 |
"step": 390
|
| 343 |
},
|
| 344 |
{
|
| 345 |
+
"epoch": 5.860805860805861,
|
| 346 |
+
"grad_norm": 8.003039360046387,
|
| 347 |
+
"learning_rate": 2.840599455040872e-05,
|
| 348 |
+
"loss": 1.0592,
|
| 349 |
"step": 400
|
| 350 |
},
|
| 351 |
{
|
| 352 |
+
"epoch": 5.992673992673993,
|
| 353 |
+
"eval_accuracy": 0.5766758494031221,
|
| 354 |
+
"eval_f1": 0.5414852771503386,
|
| 355 |
+
"eval_loss": 0.9847236275672913,
|
| 356 |
+
"eval_precision": 0.5484837093262834,
|
| 357 |
+
"eval_recall": 0.5766758494031221,
|
| 358 |
+
"eval_runtime": 10.5345,
|
| 359 |
+
"eval_samples_per_second": 103.374,
|
| 360 |
+
"eval_steps_per_second": 6.55,
|
| 361 |
+
"step": 409
|
| 362 |
},
|
| 363 |
{
|
| 364 |
+
"epoch": 6.007326007326007,
|
| 365 |
+
"grad_norm": 9.939899444580078,
|
| 366 |
+
"learning_rate": 2.772479564032698e-05,
|
| 367 |
+
"loss": 1.0573,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 368 |
"step": 410
|
| 369 |
},
|
| 370 |
{
|
| 371 |
+
"epoch": 6.153846153846154,
|
| 372 |
+
"grad_norm": 8.810173988342285,
|
| 373 |
+
"learning_rate": 2.7043596730245236e-05,
|
| 374 |
+
"loss": 1.038,
|
| 375 |
"step": 420
|
| 376 |
},
|
| 377 |
{
|
| 378 |
+
"epoch": 6.3003663003663,
|
| 379 |
+
"grad_norm": 9.228567123413086,
|
| 380 |
+
"learning_rate": 2.6362397820163485e-05,
|
| 381 |
+
"loss": 1.0441,
|
| 382 |
"step": 430
|
| 383 |
},
|
| 384 |
{
|
| 385 |
+
"epoch": 6.446886446886447,
|
| 386 |
+
"grad_norm": 10.357806205749512,
|
| 387 |
+
"learning_rate": 2.5681198910081745e-05,
|
| 388 |
+
"loss": 1.0313,
|
| 389 |
"step": 440
|
| 390 |
},
|
| 391 |
{
|
| 392 |
+
"epoch": 6.593406593406593,
|
| 393 |
+
"grad_norm": 6.874061584472656,
|
| 394 |
+
"learning_rate": 2.5e-05,
|
| 395 |
+
"loss": 1.0667,
|
| 396 |
"step": 450
|
| 397 |
},
|
| 398 |
{
|
| 399 |
+
"epoch": 6.73992673992674,
|
| 400 |
+
"grad_norm": 10.741703987121582,
|
| 401 |
+
"learning_rate": 2.4318801089918257e-05,
|
| 402 |
+
"loss": 1.0353,
|
| 403 |
"step": 460
|
| 404 |
},
|
| 405 |
{
|
| 406 |
+
"epoch": 6.886446886446887,
|
| 407 |
+
"grad_norm": 7.215301513671875,
|
| 408 |
+
"learning_rate": 2.3637602179836514e-05,
|
| 409 |
+
"loss": 1.0706,
|
| 410 |
"step": 470
|
| 411 |
},
|
| 412 |
{
|
| 413 |
+
"epoch": 6.989010989010989,
|
| 414 |
+
"eval_accuracy": 0.588613406795225,
|
| 415 |
+
"eval_f1": 0.5835655659113839,
|
| 416 |
+
"eval_loss": 0.9867706894874573,
|
| 417 |
+
"eval_precision": 0.5861531495568983,
|
| 418 |
+
"eval_recall": 0.588613406795225,
|
| 419 |
+
"eval_runtime": 10.5429,
|
| 420 |
+
"eval_samples_per_second": 103.292,
|
| 421 |
+
"eval_steps_per_second": 6.545,
|
| 422 |
+
"step": 477
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 7.032967032967033,
|
| 426 |
+
"grad_norm": 9.452975273132324,
|
| 427 |
+
"learning_rate": 2.295640326975477e-05,
|
| 428 |
+
"loss": 1.1093,
|
| 429 |
"step": 480
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 7.17948717948718,
|
| 433 |
+
"grad_norm": 5.909883499145508,
|
| 434 |
+
"learning_rate": 2.2275204359673023e-05,
|
| 435 |
+
"loss": 1.0628,
|
| 436 |
"step": 490
|
| 437 |
},
|
| 438 |
{
|
| 439 |
+
"epoch": 7.326007326007326,
|
| 440 |
+
"grad_norm": 8.430510520935059,
|
| 441 |
+
"learning_rate": 2.1594005449591282e-05,
|
| 442 |
+
"loss": 1.0175,
|
| 443 |
"step": 500
|
| 444 |
},
|
| 445 |
{
|
| 446 |
+
"epoch": 7.472527472527473,
|
| 447 |
+
"grad_norm": 11.566703796386719,
|
| 448 |
+
"learning_rate": 2.091280653950954e-05,
|
| 449 |
+
"loss": 0.9975,
|
| 450 |
"step": 510
|
| 451 |
},
|
| 452 |
{
|
| 453 |
+
"epoch": 7.619047619047619,
|
| 454 |
+
"grad_norm": 8.561046600341797,
|
| 455 |
+
"learning_rate": 2.023160762942779e-05,
|
| 456 |
+
"loss": 1.057,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 457 |
"step": 520
|
| 458 |
},
|
| 459 |
{
|
| 460 |
+
"epoch": 7.7655677655677655,
|
| 461 |
+
"grad_norm": 9.214874267578125,
|
| 462 |
+
"learning_rate": 1.955040871934605e-05,
|
| 463 |
+
"loss": 1.0085,
|
| 464 |
"step": 530
|
| 465 |
},
|
| 466 |
{
|
| 467 |
+
"epoch": 7.912087912087912,
|
| 468 |
+
"grad_norm": 7.050257682800293,
|
| 469 |
+
"learning_rate": 1.8869209809264307e-05,
|
| 470 |
+
"loss": 1.0404,
|
| 471 |
"step": 540
|
| 472 |
},
|
| 473 |
{
|
| 474 |
+
"epoch": 8.0,
|
| 475 |
+
"eval_accuracy": 0.5867768595041323,
|
| 476 |
+
"eval_f1": 0.5736657074074295,
|
| 477 |
+
"eval_loss": 0.9758484363555908,
|
| 478 |
+
"eval_precision": 0.5694509571644558,
|
| 479 |
+
"eval_recall": 0.5867768595041323,
|
| 480 |
+
"eval_runtime": 10.5054,
|
| 481 |
+
"eval_samples_per_second": 103.661,
|
| 482 |
+
"eval_steps_per_second": 6.568,
|
| 483 |
+
"step": 546
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 8.058608058608058,
|
| 487 |
+
"grad_norm": 9.406164169311523,
|
| 488 |
+
"learning_rate": 1.818801089918256e-05,
|
| 489 |
+
"loss": 1.0564,
|
| 490 |
"step": 550
|
| 491 |
},
|
| 492 |
{
|
| 493 |
+
"epoch": 8.205128205128204,
|
| 494 |
+
"grad_norm": 8.063167572021484,
|
| 495 |
+
"learning_rate": 1.750681198910082e-05,
|
| 496 |
+
"loss": 1.0381,
|
| 497 |
"step": 560
|
| 498 |
},
|
| 499 |
{
|
| 500 |
+
"epoch": 8.351648351648352,
|
| 501 |
+
"grad_norm": 7.877150535583496,
|
| 502 |
+
"learning_rate": 1.6825613079019073e-05,
|
| 503 |
+
"loss": 0.9996,
|
| 504 |
"step": 570
|
| 505 |
},
|
| 506 |
{
|
| 507 |
+
"epoch": 8.498168498168498,
|
| 508 |
+
"grad_norm": 10.49506664276123,
|
| 509 |
+
"learning_rate": 1.614441416893733e-05,
|
| 510 |
+
"loss": 0.9723,
|
| 511 |
"step": 580
|
| 512 |
},
|
| 513 |
{
|
| 514 |
+
"epoch": 8.644688644688644,
|
| 515 |
+
"grad_norm": 8.74528694152832,
|
| 516 |
+
"learning_rate": 1.546321525885559e-05,
|
| 517 |
+
"loss": 1.0267,
|
| 518 |
"step": 590
|
| 519 |
},
|
| 520 |
{
|
| 521 |
+
"epoch": 8.791208791208792,
|
| 522 |
+
"grad_norm": 7.0554962158203125,
|
| 523 |
+
"learning_rate": 1.4782016348773841e-05,
|
| 524 |
+
"loss": 1.0251,
|
| 525 |
"step": 600
|
| 526 |
},
|
| 527 |
{
|
| 528 |
+
"epoch": 8.937728937728938,
|
| 529 |
+
"grad_norm": 7.974668502807617,
|
| 530 |
+
"learning_rate": 1.41008174386921e-05,
|
| 531 |
+
"loss": 1.0059,
|
| 532 |
"step": 610
|
| 533 |
},
|
| 534 |
{
|
| 535 |
+
"epoch": 8.996336996336996,
|
| 536 |
+
"eval_accuracy": 0.5932047750229569,
|
| 537 |
+
"eval_f1": 0.5674291939014156,
|
| 538 |
+
"eval_loss": 0.9468401074409485,
|
| 539 |
+
"eval_precision": 0.5709384462011384,
|
| 540 |
+
"eval_recall": 0.5932047750229569,
|
| 541 |
+
"eval_runtime": 10.4878,
|
| 542 |
+
"eval_samples_per_second": 103.835,
|
| 543 |
+
"eval_steps_per_second": 6.579,
|
| 544 |
+
"step": 614
|
| 545 |
},
|
| 546 |
{
|
| 547 |
+
"epoch": 9.084249084249084,
|
| 548 |
+
"grad_norm": 8.571954727172852,
|
| 549 |
+
"learning_rate": 1.3419618528610356e-05,
|
| 550 |
+
"loss": 0.9878,
|
| 551 |
"step": 620
|
| 552 |
},
|
| 553 |
{
|
| 554 |
+
"epoch": 9.23076923076923,
|
| 555 |
+
"grad_norm": 8.298359870910645,
|
| 556 |
+
"learning_rate": 1.273841961852861e-05,
|
| 557 |
+
"loss": 1.0056,
|
| 558 |
"step": 630
|
| 559 |
},
|
| 560 |
{
|
| 561 |
+
"epoch": 9.377289377289378,
|
| 562 |
+
"grad_norm": 7.087368965148926,
|
| 563 |
+
"learning_rate": 1.2057220708446868e-05,
|
| 564 |
+
"loss": 1.037,
|
| 565 |
"step": 640
|
| 566 |
},
|
| 567 |
{
|
| 568 |
+
"epoch": 9.523809523809524,
|
| 569 |
+
"grad_norm": 7.409104347229004,
|
| 570 |
+
"learning_rate": 1.1376021798365123e-05,
|
| 571 |
+
"loss": 0.9326,
|
| 572 |
"step": 650
|
| 573 |
},
|
| 574 |
{
|
| 575 |
+
"epoch": 9.67032967032967,
|
| 576 |
+
"grad_norm": 7.1452531814575195,
|
| 577 |
+
"learning_rate": 1.0694822888283379e-05,
|
| 578 |
+
"loss": 0.9723,
|
| 579 |
"step": 660
|
| 580 |
},
|
| 581 |
{
|
| 582 |
+
"epoch": 9.816849816849818,
|
| 583 |
+
"grad_norm": 8.340729713439941,
|
| 584 |
+
"learning_rate": 1.0013623978201635e-05,
|
| 585 |
+
"loss": 0.9914,
|
| 586 |
"step": 670
|
| 587 |
},
|
| 588 |
{
|
| 589 |
+
"epoch": 9.963369963369964,
|
| 590 |
+
"grad_norm": 10.698880195617676,
|
| 591 |
+
"learning_rate": 9.332425068119891e-06,
|
| 592 |
+
"loss": 0.965,
|
| 593 |
"step": 680
|
| 594 |
},
|
| 595 |
{
|
| 596 |
+
"epoch": 9.992673992673993,
|
| 597 |
+
"eval_accuracy": 0.5932047750229569,
|
| 598 |
+
"eval_f1": 0.5804462637419235,
|
| 599 |
+
"eval_loss": 0.9565483331680298,
|
| 600 |
+
"eval_precision": 0.5857538351608745,
|
| 601 |
+
"eval_recall": 0.5932047750229569,
|
| 602 |
+
"eval_runtime": 10.4791,
|
| 603 |
+
"eval_samples_per_second": 103.921,
|
| 604 |
+
"eval_steps_per_second": 6.585,
|
| 605 |
+
"step": 682
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 10.10989010989011,
|
| 609 |
+
"grad_norm": 10.67618465423584,
|
| 610 |
+
"learning_rate": 8.651226158038147e-06,
|
| 611 |
+
"loss": 0.9732,
|
| 612 |
"step": 690
|
| 613 |
},
|
| 614 |
{
|
| 615 |
+
"epoch": 10.256410256410255,
|
| 616 |
+
"grad_norm": 9.102426528930664,
|
| 617 |
+
"learning_rate": 7.970027247956404e-06,
|
| 618 |
+
"loss": 0.9804,
|
| 619 |
"step": 700
|
| 620 |
},
|
| 621 |
{
|
| 622 |
+
"epoch": 10.402930402930403,
|
| 623 |
+
"grad_norm": 11.115556716918945,
|
| 624 |
+
"learning_rate": 7.288828337874659e-06,
|
| 625 |
+
"loss": 0.9855,
|
| 626 |
"step": 710
|
| 627 |
},
|
| 628 |
{
|
| 629 |
+
"epoch": 10.54945054945055,
|
| 630 |
+
"grad_norm": 11.00426197052002,
|
| 631 |
+
"learning_rate": 6.607629427792916e-06,
|
| 632 |
+
"loss": 0.9691,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 633 |
"step": 720
|
| 634 |
},
|
| 635 |
{
|
| 636 |
+
"epoch": 10.695970695970695,
|
| 637 |
+
"grad_norm": 10.043339729309082,
|
| 638 |
+
"learning_rate": 5.9264305177111724e-06,
|
| 639 |
+
"loss": 0.9365,
|
| 640 |
"step": 730
|
| 641 |
},
|
| 642 |
{
|
| 643 |
+
"epoch": 10.842490842490843,
|
| 644 |
+
"grad_norm": 11.518232345581055,
|
| 645 |
+
"learning_rate": 5.245231607629428e-06,
|
| 646 |
+
"loss": 0.9659,
|
| 647 |
"step": 740
|
| 648 |
},
|
| 649 |
{
|
| 650 |
+
"epoch": 10.989010989010989,
|
| 651 |
+
"grad_norm": 9.314995765686035,
|
| 652 |
+
"learning_rate": 4.564032697547684e-06,
|
| 653 |
+
"loss": 0.9362,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 10.989010989010989,
|
| 658 |
+
"eval_accuracy": 0.588613406795225,
|
| 659 |
+
"eval_f1": 0.5778239696801104,
|
| 660 |
+
"eval_loss": 0.9466218948364258,
|
| 661 |
+
"eval_precision": 0.5767647827506791,
|
| 662 |
+
"eval_recall": 0.588613406795225,
|
| 663 |
+
"eval_runtime": 10.5258,
|
| 664 |
+
"eval_samples_per_second": 103.46,
|
| 665 |
+
"eval_steps_per_second": 6.555,
|
| 666 |
"step": 750
|
| 667 |
},
|
| 668 |
{
|
| 669 |
+
"epoch": 11.135531135531135,
|
| 670 |
+
"grad_norm": 10.667020797729492,
|
| 671 |
+
"learning_rate": 3.88283378746594e-06,
|
| 672 |
+
"loss": 0.9564,
|
| 673 |
"step": 760
|
| 674 |
},
|
| 675 |
{
|
| 676 |
+
"epoch": 11.282051282051283,
|
| 677 |
+
"grad_norm": 10.923125267028809,
|
| 678 |
+
"learning_rate": 3.2016348773841965e-06,
|
| 679 |
+
"loss": 0.9177,
|
| 680 |
"step": 770
|
| 681 |
},
|
| 682 |
{
|
| 683 |
+
"epoch": 11.428571428571429,
|
| 684 |
+
"grad_norm": 9.893692016601562,
|
| 685 |
+
"learning_rate": 2.5204359673024523e-06,
|
| 686 |
+
"loss": 0.9732,
|
| 687 |
"step": 780
|
| 688 |
},
|
| 689 |
{
|
| 690 |
+
"epoch": 11.575091575091575,
|
| 691 |
+
"grad_norm": 8.784825325012207,
|
| 692 |
+
"learning_rate": 1.8392370572207086e-06,
|
| 693 |
+
"loss": 0.9558,
|
| 694 |
"step": 790
|
| 695 |
},
|
| 696 |
{
|
| 697 |
+
"epoch": 11.72161172161172,
|
| 698 |
+
"grad_norm": 8.990778923034668,
|
| 699 |
+
"learning_rate": 1.1580381471389646e-06,
|
| 700 |
+
"loss": 0.9656,
|
| 701 |
"step": 800
|
| 702 |
},
|
| 703 |
{
|
| 704 |
+
"epoch": 11.868131868131869,
|
| 705 |
+
"grad_norm": 8.444221496582031,
|
| 706 |
+
"learning_rate": 4.768392370572207e-07,
|
| 707 |
+
"loss": 0.9334,
|
| 708 |
"step": 810
|
| 709 |
},
|
| 710 |
{
|
| 711 |
+
"epoch": 11.956043956043956,
|
| 712 |
+
"eval_accuracy": 0.5858585858585859,
|
| 713 |
+
"eval_f1": 0.5699572730591373,
|
| 714 |
+
"eval_loss": 0.9441593885421753,
|
| 715 |
+
"eval_precision": 0.5692451226403554,
|
| 716 |
+
"eval_recall": 0.5858585858585859,
|
| 717 |
+
"eval_runtime": 10.5926,
|
| 718 |
+
"eval_samples_per_second": 102.808,
|
| 719 |
+
"eval_steps_per_second": 6.514,
|
| 720 |
+
"step": 816
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 11.956043956043956,
|
| 724 |
+
"step": 816,
|
| 725 |
+
"total_flos": 4.123334853511373e+18,
|
| 726 |
+
"train_loss": 1.090085435147379,
|
| 727 |
+
"train_runtime": 2115.1144,
|
| 728 |
+
"train_samples_per_second": 24.697,
|
| 729 |
+
"train_steps_per_second": 0.386
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 730 |
}
|
| 731 |
],
|
| 732 |
"logging_steps": 10,
|
| 733 |
+
"max_steps": 816,
|
| 734 |
"num_input_tokens_seen": 0,
|
| 735 |
"num_train_epochs": 12,
|
| 736 |
"save_steps": 500,
|
|
|
|
| 746 |
"attributes": {}
|
| 747 |
}
|
| 748 |
},
|
| 749 |
+
"total_flos": 4.123334853511373e+18,
|
| 750 |
"train_batch_size": 16,
|
| 751 |
"trial_name": null,
|
| 752 |
"trial_params": null
|