End of training
Browse files- README.md +5 -5
- all_results.json +14 -14
- eval_results.json +9 -9
- runs/Sep05_08-10-30_43d6627a09b0/events.out.tfevents.1725526395.43d6627a09b0.309.1 +3 -0
- train_results.json +6 -6
- trainer_state.json +561 -477
README.md
CHANGED
|
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 21 |
|
| 22 |
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.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
-
- Loss: 0.
|
| 25 |
-
- Accuracy: 0.
|
| 26 |
-
- F1: 0.
|
| 27 |
-
- Precision: 0.
|
| 28 |
-
- Recall: 0.
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
|
|
|
| 21 |
|
| 22 |
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.
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
+
- Loss: 0.9120
|
| 25 |
+
- Accuracy: 0.6138
|
| 26 |
+
- F1: 0.5996
|
| 27 |
+
- Precision: 0.5969
|
| 28 |
+
- Recall: 0.6138
|
| 29 |
|
| 30 |
## Model description
|
| 31 |
|
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":
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second": 6.
|
| 11 |
-
"total_flos": 4.
|
| 12 |
-
"train_loss": 1.
|
| 13 |
-
"train_runtime":
|
| 14 |
-
"train_samples_per_second":
|
| 15 |
-
"train_steps_per_second": 0.
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 11.961661341853034,
|
| 3 |
+
"eval_accuracy": 0.6137931034482759,
|
| 4 |
+
"eval_f1": 0.5996477650763593,
|
| 5 |
+
"eval_loss": 0.9119637608528137,
|
| 6 |
+
"eval_precision": 0.596855024118962,
|
| 7 |
+
"eval_recall": 0.6137931034482759,
|
| 8 |
+
"eval_runtime": 4.1197,
|
| 9 |
+
"eval_samples_per_second": 105.59,
|
| 10 |
+
"eval_steps_per_second": 6.797,
|
| 11 |
+
"total_flos": 4.743827088137626e+18,
|
| 12 |
+
"train_loss": 1.079931161342523,
|
| 13 |
+
"train_runtime": 2308.5403,
|
| 14 |
+
"train_samples_per_second": 26.027,
|
| 15 |
+
"train_steps_per_second": 0.405
|
| 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":
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second": 6.
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 11.961661341853034,
|
| 3 |
+
"eval_accuracy": 0.6137931034482759,
|
| 4 |
+
"eval_f1": 0.5996477650763593,
|
| 5 |
+
"eval_loss": 0.9119637608528137,
|
| 6 |
+
"eval_precision": 0.596855024118962,
|
| 7 |
+
"eval_recall": 0.6137931034482759,
|
| 8 |
+
"eval_runtime": 4.1197,
|
| 9 |
+
"eval_samples_per_second": 105.59,
|
| 10 |
+
"eval_steps_per_second": 6.797
|
| 11 |
}
|
runs/Sep05_08-10-30_43d6627a09b0/events.out.tfevents.1725526395.43d6627a09b0.309.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2221cf45441b9f89a927e8c90687a0e0bf1fabcc59dccee723f36556679457e
|
| 3 |
+
size 560
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch": 11.
|
| 3 |
-
"total_flos": 4.
|
| 4 |
-
"train_loss": 1.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 11.961661341853034,
|
| 3 |
+
"total_flos": 4.743827088137626e+18,
|
| 4 |
+
"train_loss": 1.079931161342523,
|
| 5 |
+
"train_runtime": 2308.5403,
|
| 6 |
+
"train_samples_per_second": 26.027,
|
| 7 |
+
"train_steps_per_second": 0.405
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,736 +1,820 @@
|
|
| 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": 1.
|
| 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": 2.
|
| 36 |
-
"loss": 1.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate": 2.
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate": 3.
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"
|
| 56 |
-
"
|
| 57 |
-
"
|
| 58 |
-
"
|
| 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":
|
| 67 |
-
"
|
| 68 |
-
"
|
| 69 |
-
"
|
| 70 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
},
|
| 72 |
{
|
| 73 |
-
"epoch": 1.
|
| 74 |
-
"grad_norm":
|
| 75 |
-
"learning_rate": 4.
|
| 76 |
-
"loss": 1.
|
| 77 |
"step": 80
|
| 78 |
},
|
| 79 |
{
|
| 80 |
-
"epoch": 1.
|
| 81 |
-
"grad_norm":
|
| 82 |
-
"learning_rate": 4.
|
| 83 |
-
"loss": 1.
|
| 84 |
"step": 90
|
| 85 |
},
|
| 86 |
{
|
| 87 |
-
"epoch": 1.
|
| 88 |
-
"grad_norm":
|
| 89 |
-
"learning_rate": 4.
|
| 90 |
-
"loss": 1.
|
| 91 |
"step": 100
|
| 92 |
},
|
| 93 |
{
|
| 94 |
-
"epoch": 1.
|
| 95 |
-
"grad_norm":
|
| 96 |
-
"learning_rate": 4.
|
| 97 |
-
"loss": 1.
|
| 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 |
-
"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":
|
| 135 |
-
"grad_norm":
|
| 136 |
-
"learning_rate": 4.
|
| 137 |
-
"loss": 1.
|
| 138 |
"step": 150
|
| 139 |
},
|
| 140 |
{
|
| 141 |
-
"epoch":
|
| 142 |
-
"
|
| 143 |
-
"
|
| 144 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 145 |
"step": 160
|
| 146 |
},
|
| 147 |
{
|
| 148 |
-
"epoch": 2.
|
| 149 |
-
"grad_norm":
|
| 150 |
-
"learning_rate": 4.
|
| 151 |
-
"loss": 1.
|
| 152 |
"step": 170
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch": 2.
|
| 156 |
-
"grad_norm":
|
| 157 |
-
"learning_rate": 4.
|
| 158 |
-
"loss": 1.
|
| 159 |
"step": 180
|
| 160 |
},
|
| 161 |
{
|
| 162 |
-
"epoch": 2.
|
| 163 |
-
"grad_norm":
|
| 164 |
-
"learning_rate": 4.
|
| 165 |
-
"loss": 1.
|
| 166 |
"step": 190
|
| 167 |
},
|
| 168 |
{
|
| 169 |
-
"epoch": 2.
|
| 170 |
-
"grad_norm":
|
| 171 |
-
"learning_rate": 4.
|
| 172 |
-
"loss": 1.
|
| 173 |
"step": 200
|
| 174 |
},
|
| 175 |
{
|
| 176 |
-
"epoch": 2.
|
| 177 |
-
"
|
| 178 |
-
"
|
| 179 |
-
"
|
| 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":
|
| 196 |
-
"grad_norm":
|
| 197 |
-
"learning_rate": 4.
|
| 198 |
-
"loss": 1.
|
| 199 |
"step": 220
|
| 200 |
},
|
| 201 |
{
|
| 202 |
-
"epoch":
|
| 203 |
-
"grad_norm":
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss": 1.
|
| 206 |
"step": 230
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch":
|
| 210 |
-
"
|
| 211 |
-
"
|
| 212 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 213 |
"step": 240
|
| 214 |
},
|
| 215 |
{
|
| 216 |
-
"epoch": 3.
|
| 217 |
-
"grad_norm": 8.
|
| 218 |
-
"learning_rate":
|
| 219 |
-
"loss": 1.
|
| 220 |
"step": 250
|
| 221 |
},
|
| 222 |
{
|
| 223 |
-
"epoch": 3.
|
| 224 |
-
"grad_norm":
|
| 225 |
-
"learning_rate":
|
| 226 |
-
"loss": 1.
|
| 227 |
"step": 260
|
| 228 |
},
|
| 229 |
{
|
| 230 |
-
"epoch": 3.
|
| 231 |
-
"grad_norm":
|
| 232 |
-
"learning_rate": 3.
|
| 233 |
-
"loss": 1.
|
| 234 |
"step": 270
|
| 235 |
},
|
| 236 |
{
|
| 237 |
-
"epoch":
|
| 238 |
-
"
|
| 239 |
-
"
|
| 240 |
-
"
|
| 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":
|
| 257 |
-
"grad_norm":
|
| 258 |
-
"learning_rate": 3.
|
| 259 |
-
"loss": 1.
|
| 260 |
"step": 290
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"epoch":
|
| 264 |
-
"grad_norm":
|
| 265 |
-
"learning_rate": 3.
|
| 266 |
-
"loss": 1.
|
| 267 |
"step": 300
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch":
|
| 271 |
-
"grad_norm":
|
| 272 |
-
"learning_rate": 3.
|
| 273 |
-
"loss": 1.
|
| 274 |
"step": 310
|
| 275 |
},
|
| 276 |
{
|
| 277 |
-
"epoch": 4.
|
| 278 |
-
"
|
| 279 |
-
"
|
| 280 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 281 |
"step": 320
|
| 282 |
},
|
| 283 |
{
|
| 284 |
-
"epoch": 4.
|
| 285 |
-
"grad_norm":
|
| 286 |
-
"learning_rate": 3.
|
| 287 |
-
"loss": 1.
|
| 288 |
"step": 330
|
| 289 |
},
|
| 290 |
{
|
| 291 |
-
"epoch": 4.
|
| 292 |
-
"grad_norm":
|
| 293 |
-
"learning_rate": 3.
|
| 294 |
"loss": 1.096,
|
| 295 |
"step": 340
|
| 296 |
},
|
| 297 |
{
|
| 298 |
-
"epoch": 4.
|
| 299 |
-
"
|
| 300 |
-
"
|
| 301 |
-
"
|
| 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":
|
| 318 |
-
"grad_norm": 7.
|
| 319 |
-
"learning_rate": 3.
|
| 320 |
-
"loss": 1.
|
| 321 |
"step": 360
|
| 322 |
},
|
| 323 |
{
|
| 324 |
-
"epoch":
|
| 325 |
-
"grad_norm":
|
| 326 |
-
"learning_rate": 3.
|
| 327 |
-
"loss": 1.
|
| 328 |
"step": 370
|
| 329 |
},
|
| 330 |
{
|
| 331 |
-
"epoch":
|
| 332 |
-
"grad_norm":
|
| 333 |
-
"learning_rate":
|
| 334 |
-
"loss": 1.
|
| 335 |
"step": 380
|
| 336 |
},
|
| 337 |
{
|
| 338 |
-
"epoch":
|
| 339 |
-
"grad_norm":
|
| 340 |
-
"learning_rate":
|
| 341 |
-
"loss": 1.
|
| 342 |
"step": 390
|
| 343 |
},
|
| 344 |
{
|
| 345 |
-
"epoch":
|
| 346 |
-
"
|
| 347 |
-
"
|
| 348 |
-
"
|
| 349 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 350 |
},
|
| 351 |
{
|
| 352 |
-
"epoch": 5.
|
| 353 |
-
"
|
| 354 |
-
"
|
| 355 |
-
"
|
| 356 |
-
"
|
| 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":
|
| 365 |
-
"grad_norm": 9.
|
| 366 |
-
"learning_rate":
|
| 367 |
-
"loss": 1.
|
| 368 |
"step": 410
|
| 369 |
},
|
| 370 |
{
|
| 371 |
-
"epoch":
|
| 372 |
-
"grad_norm":
|
| 373 |
-
"learning_rate":
|
| 374 |
-
"loss": 1.
|
| 375 |
"step": 420
|
| 376 |
},
|
| 377 |
{
|
| 378 |
-
"epoch":
|
| 379 |
-
"grad_norm":
|
| 380 |
-
"learning_rate":
|
| 381 |
-
"loss": 1.
|
| 382 |
"step": 430
|
| 383 |
},
|
| 384 |
{
|
| 385 |
-
"epoch":
|
| 386 |
-
"grad_norm":
|
| 387 |
-
"learning_rate": 2.
|
| 388 |
-
"loss": 1.
|
| 389 |
"step": 440
|
| 390 |
},
|
| 391 |
{
|
| 392 |
-
"epoch":
|
| 393 |
-
"grad_norm":
|
| 394 |
-
"learning_rate": 2.
|
| 395 |
-
"loss": 1.
|
| 396 |
"step": 450
|
| 397 |
},
|
| 398 |
{
|
| 399 |
-
"epoch":
|
| 400 |
-
"grad_norm":
|
| 401 |
-
"learning_rate": 2.
|
| 402 |
-
"loss": 1.
|
| 403 |
"step": 460
|
| 404 |
},
|
| 405 |
{
|
| 406 |
-
"epoch":
|
| 407 |
-
"
|
| 408 |
-
"
|
| 409 |
-
"
|
| 410 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 411 |
},
|
| 412 |
{
|
| 413 |
-
"epoch": 6.
|
| 414 |
-
"
|
| 415 |
-
"
|
| 416 |
-
"
|
| 417 |
-
"
|
| 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":
|
| 426 |
-
"grad_norm":
|
| 427 |
-
"learning_rate": 2.
|
| 428 |
-
"loss": 1.
|
| 429 |
"step": 480
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch":
|
| 433 |
-
"grad_norm":
|
| 434 |
-
"learning_rate": 2.
|
| 435 |
-
"loss": 1.
|
| 436 |
"step": 490
|
| 437 |
},
|
| 438 |
{
|
| 439 |
-
"epoch":
|
| 440 |
-
"grad_norm": 8.
|
| 441 |
-
"learning_rate": 2.
|
| 442 |
-
"loss": 1.
|
| 443 |
"step": 500
|
| 444 |
},
|
| 445 |
{
|
| 446 |
-
"epoch":
|
| 447 |
-
"grad_norm":
|
| 448 |
-
"learning_rate": 2.
|
| 449 |
-
"loss":
|
| 450 |
"step": 510
|
| 451 |
},
|
| 452 |
{
|
| 453 |
-
"epoch":
|
| 454 |
-
"grad_norm": 8.
|
| 455 |
-
"learning_rate": 2.
|
| 456 |
-
"loss": 1.
|
| 457 |
"step": 520
|
| 458 |
},
|
| 459 |
{
|
| 460 |
-
"epoch":
|
| 461 |
-
"grad_norm":
|
| 462 |
-
"learning_rate":
|
| 463 |
-
"loss": 1.
|
| 464 |
"step": 530
|
| 465 |
},
|
| 466 |
{
|
| 467 |
-
"epoch":
|
| 468 |
-
"grad_norm":
|
| 469 |
-
"learning_rate":
|
| 470 |
-
"loss": 1.
|
| 471 |
"step": 540
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch":
|
| 475 |
-
"eval_accuracy": 0.
|
| 476 |
-
"eval_f1": 0.
|
| 477 |
-
"eval_loss": 0.
|
| 478 |
-
"eval_precision": 0.
|
| 479 |
-
"eval_recall": 0.
|
| 480 |
-
"eval_runtime":
|
| 481 |
-
"eval_samples_per_second": 103.
|
| 482 |
-
"eval_steps_per_second": 6.
|
| 483 |
-
"step":
|
| 484 |
-
},
|
| 485 |
-
{
|
| 486 |
-
"epoch":
|
| 487 |
-
"grad_norm": 9.
|
| 488 |
-
"learning_rate":
|
| 489 |
-
"loss": 1.
|
| 490 |
"step": 550
|
| 491 |
},
|
| 492 |
{
|
| 493 |
-
"epoch":
|
| 494 |
-
"grad_norm":
|
| 495 |
-
"learning_rate":
|
| 496 |
-
"loss": 1.
|
| 497 |
"step": 560
|
| 498 |
},
|
| 499 |
{
|
| 500 |
-
"epoch":
|
| 501 |
-
"grad_norm":
|
| 502 |
-
"learning_rate":
|
| 503 |
-
"loss":
|
| 504 |
"step": 570
|
| 505 |
},
|
| 506 |
{
|
| 507 |
-
"epoch":
|
| 508 |
-
"grad_norm":
|
| 509 |
-
"learning_rate":
|
| 510 |
-
"loss":
|
| 511 |
"step": 580
|
| 512 |
},
|
| 513 |
{
|
| 514 |
-
"epoch":
|
| 515 |
-
"grad_norm":
|
| 516 |
-
"learning_rate":
|
| 517 |
-
"loss":
|
| 518 |
"step": 590
|
| 519 |
},
|
| 520 |
{
|
| 521 |
-
"epoch":
|
| 522 |
-
"grad_norm":
|
| 523 |
-
"learning_rate":
|
| 524 |
-
"loss": 1.
|
| 525 |
"step": 600
|
| 526 |
},
|
| 527 |
{
|
| 528 |
-
"epoch":
|
| 529 |
-
"grad_norm":
|
| 530 |
-
"learning_rate": 1.
|
| 531 |
-
"loss": 1.
|
| 532 |
"step": 610
|
| 533 |
},
|
| 534 |
{
|
| 535 |
-
"epoch":
|
| 536 |
-
"
|
| 537 |
-
"
|
| 538 |
-
"
|
| 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":
|
| 555 |
-
"
|
| 556 |
-
"
|
| 557 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 558 |
"step": 630
|
| 559 |
},
|
| 560 |
{
|
| 561 |
-
"epoch":
|
| 562 |
-
"grad_norm": 7.
|
| 563 |
-
"learning_rate": 1.
|
| 564 |
-
"loss":
|
| 565 |
"step": 640
|
| 566 |
},
|
| 567 |
{
|
| 568 |
-
"epoch":
|
| 569 |
-
"grad_norm":
|
| 570 |
-
"learning_rate": 1.
|
| 571 |
-
"loss": 0.
|
| 572 |
"step": 650
|
| 573 |
},
|
| 574 |
{
|
| 575 |
-
"epoch":
|
| 576 |
-
"grad_norm":
|
| 577 |
-
"learning_rate": 1.
|
| 578 |
-
"loss":
|
| 579 |
"step": 660
|
| 580 |
},
|
| 581 |
{
|
| 582 |
-
"epoch":
|
| 583 |
-
"grad_norm":
|
| 584 |
-
"learning_rate": 1.
|
| 585 |
-
"loss": 0.
|
| 586 |
"step": 670
|
| 587 |
},
|
| 588 |
{
|
| 589 |
-
"epoch":
|
| 590 |
-
"grad_norm":
|
| 591 |
-
"learning_rate":
|
| 592 |
-
"loss":
|
| 593 |
"step": 680
|
| 594 |
},
|
| 595 |
{
|
| 596 |
-
"epoch":
|
| 597 |
-
"
|
| 598 |
-
"
|
| 599 |
-
"
|
| 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":
|
| 616 |
-
"grad_norm":
|
| 617 |
-
"learning_rate":
|
| 618 |
-
"loss": 0.
|
| 619 |
"step": 700
|
| 620 |
},
|
| 621 |
{
|
| 622 |
-
"epoch":
|
| 623 |
-
"
|
| 624 |
-
"
|
| 625 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 626 |
"step": 710
|
| 627 |
},
|
| 628 |
{
|
| 629 |
-
"epoch":
|
| 630 |
-
"grad_norm":
|
| 631 |
-
"learning_rate":
|
| 632 |
-
"loss": 0.
|
| 633 |
"step": 720
|
| 634 |
},
|
| 635 |
{
|
| 636 |
-
"epoch":
|
| 637 |
-
"grad_norm":
|
| 638 |
-
"learning_rate":
|
| 639 |
-
"loss": 0.
|
| 640 |
"step": 730
|
| 641 |
},
|
| 642 |
{
|
| 643 |
-
"epoch":
|
| 644 |
-
"grad_norm":
|
| 645 |
-
"learning_rate":
|
| 646 |
-
"loss": 0.
|
| 647 |
"step": 740
|
| 648 |
},
|
| 649 |
{
|
| 650 |
-
"epoch":
|
| 651 |
-
"grad_norm": 9.
|
| 652 |
-
"learning_rate":
|
| 653 |
-
"loss": 0.
|
| 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":
|
| 670 |
-
"grad_norm":
|
| 671 |
-
"learning_rate":
|
| 672 |
-
"loss":
|
| 673 |
"step": 760
|
| 674 |
},
|
| 675 |
{
|
| 676 |
-
"epoch":
|
| 677 |
-
"grad_norm":
|
| 678 |
-
"learning_rate":
|
| 679 |
-
"loss": 0.
|
| 680 |
"step": 770
|
| 681 |
},
|
| 682 |
{
|
| 683 |
-
"epoch":
|
| 684 |
-
"grad_norm":
|
| 685 |
-
"learning_rate":
|
| 686 |
-
"loss": 0.
|
| 687 |
"step": 780
|
| 688 |
},
|
| 689 |
{
|
| 690 |
-
"epoch":
|
| 691 |
-
"
|
| 692 |
-
"
|
| 693 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 694 |
"step": 790
|
| 695 |
},
|
| 696 |
{
|
| 697 |
-
"epoch":
|
| 698 |
-
"grad_norm": 8.
|
| 699 |
-
"learning_rate":
|
| 700 |
-
"loss": 0.
|
| 701 |
"step": 800
|
| 702 |
},
|
| 703 |
{
|
| 704 |
-
"epoch":
|
| 705 |
-
"grad_norm":
|
| 706 |
-
"learning_rate":
|
| 707 |
-
"loss": 0.
|
| 708 |
"step": 810
|
| 709 |
},
|
| 710 |
{
|
| 711 |
-
"epoch":
|
| 712 |
-
"
|
| 713 |
-
"
|
| 714 |
-
"
|
| 715 |
-
"
|
| 716 |
-
|
| 717 |
-
|
| 718 |
-
"
|
| 719 |
-
"
|
| 720 |
-
"
|
| 721 |
-
|
| 722 |
-
|
| 723 |
-
|
| 724 |
-
|
| 725 |
-
"
|
| 726 |
-
"
|
| 727 |
-
"
|
| 728 |
-
"
|
| 729 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 730 |
}
|
| 731 |
],
|
| 732 |
"logging_steps": 10,
|
| 733 |
-
"max_steps":
|
| 734 |
"num_input_tokens_seen": 0,
|
| 735 |
"num_train_epochs": 12,
|
| 736 |
"save_steps": 500,
|
|
@@ -746,7 +830,7 @@
|
|
| 746 |
"attributes": {}
|
| 747 |
}
|
| 748 |
},
|
| 749 |
-
"total_flos": 4.
|
| 750 |
"train_batch_size": 16,
|
| 751 |
"trial_name": null,
|
| 752 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.6137931034482759,
|
| 3 |
+
"best_model_checkpoint": "convnextv2-base-22k-224-finetuned-tekno24/checkpoint-860",
|
| 4 |
+
"epoch": 11.961661341853034,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 936,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.12779552715654952,
|
| 13 |
+
"grad_norm": 11.641097068786621,
|
| 14 |
+
"learning_rate": 5.319148936170213e-06,
|
| 15 |
+
"loss": 1.4077,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.25559105431309903,
|
| 20 |
+
"grad_norm": 10.328614234924316,
|
| 21 |
+
"learning_rate": 1.0638297872340426e-05,
|
| 22 |
+
"loss": 1.3907,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.38338658146964855,
|
| 27 |
+
"grad_norm": 11.496760368347168,
|
| 28 |
+
"learning_rate": 1.595744680851064e-05,
|
| 29 |
+
"loss": 1.3597,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.5111821086261981,
|
| 34 |
+
"grad_norm": 9.975175857543945,
|
| 35 |
+
"learning_rate": 2.1276595744680852e-05,
|
| 36 |
+
"loss": 1.354,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.6389776357827476,
|
| 41 |
+
"grad_norm": 11.381126403808594,
|
| 42 |
+
"learning_rate": 2.6595744680851064e-05,
|
| 43 |
+
"loss": 1.3266,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.7667731629392971,
|
| 48 |
+
"grad_norm": 9.771955490112305,
|
| 49 |
+
"learning_rate": 3.191489361702128e-05,
|
| 50 |
+
"loss": 1.291,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.8945686900958466,
|
| 55 |
+
"grad_norm": 21.0851993560791,
|
| 56 |
+
"learning_rate": 3.617021276595745e-05,
|
| 57 |
+
"loss": 1.3179,
|
| 58 |
+
"step": 70
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.9968051118210862,
|
| 62 |
+
"eval_accuracy": 0.4206896551724138,
|
| 63 |
+
"eval_f1": 0.39792953648489043,
|
| 64 |
+
"eval_loss": 1.2415151596069336,
|
| 65 |
+
"eval_precision": 0.4642161976696202,
|
| 66 |
+
"eval_recall": 0.4206896551724138,
|
| 67 |
+
"eval_runtime": 4.2118,
|
| 68 |
+
"eval_samples_per_second": 103.281,
|
| 69 |
+
"eval_steps_per_second": 6.648,
|
| 70 |
+
"step": 78
|
| 71 |
},
|
| 72 |
{
|
| 73 |
+
"epoch": 1.0223642172523961,
|
| 74 |
+
"grad_norm": 19.948223114013672,
|
| 75 |
+
"learning_rate": 4.148936170212766e-05,
|
| 76 |
+
"loss": 1.2668,
|
| 77 |
"step": 80
|
| 78 |
},
|
| 79 |
{
|
| 80 |
+
"epoch": 1.1501597444089458,
|
| 81 |
+
"grad_norm": 11.563603401184082,
|
| 82 |
+
"learning_rate": 4.680851063829788e-05,
|
| 83 |
+
"loss": 1.2202,
|
| 84 |
"step": 90
|
| 85 |
},
|
| 86 |
{
|
| 87 |
+
"epoch": 1.2779552715654952,
|
| 88 |
+
"grad_norm": 9.605425834655762,
|
| 89 |
+
"learning_rate": 4.97624703087886e-05,
|
| 90 |
+
"loss": 1.2626,
|
| 91 |
"step": 100
|
| 92 |
},
|
| 93 |
{
|
| 94 |
+
"epoch": 1.4057507987220448,
|
| 95 |
+
"grad_norm": 10.846478462219238,
|
| 96 |
+
"learning_rate": 4.9168646080760093e-05,
|
| 97 |
+
"loss": 1.251,
|
| 98 |
"step": 110
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 1.5335463258785942,
|
| 102 |
+
"grad_norm": 10.546998023986816,
|
| 103 |
+
"learning_rate": 4.8574821852731594e-05,
|
| 104 |
+
"loss": 1.2136,
|
| 105 |
"step": 120
|
| 106 |
},
|
| 107 |
{
|
| 108 |
+
"epoch": 1.6613418530351438,
|
| 109 |
+
"grad_norm": 10.678705215454102,
|
| 110 |
+
"learning_rate": 4.798099762470309e-05,
|
| 111 |
+
"loss": 1.1764,
|
| 112 |
"step": 130
|
| 113 |
},
|
| 114 |
{
|
| 115 |
+
"epoch": 1.7891373801916934,
|
| 116 |
+
"grad_norm": 10.283668518066406,
|
| 117 |
+
"learning_rate": 4.738717339667459e-05,
|
| 118 |
+
"loss": 1.2624,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 119 |
"step": 140
|
| 120 |
},
|
| 121 |
{
|
| 122 |
+
"epoch": 1.9169329073482428,
|
| 123 |
+
"grad_norm": 10.07646656036377,
|
| 124 |
+
"learning_rate": 4.679334916864608e-05,
|
| 125 |
+
"loss": 1.1998,
|
| 126 |
"step": 150
|
| 127 |
},
|
| 128 |
{
|
| 129 |
+
"epoch": 1.9936102236421727,
|
| 130 |
+
"eval_accuracy": 0.5103448275862069,
|
| 131 |
+
"eval_f1": 0.4525112700085999,
|
| 132 |
+
"eval_loss": 1.0768730640411377,
|
| 133 |
+
"eval_precision": 0.5309344450319118,
|
| 134 |
+
"eval_recall": 0.5103448275862069,
|
| 135 |
+
"eval_runtime": 4.2293,
|
| 136 |
+
"eval_samples_per_second": 102.853,
|
| 137 |
+
"eval_steps_per_second": 6.62,
|
| 138 |
+
"step": 156
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.0447284345047922,
|
| 142 |
+
"grad_norm": 10.981221199035645,
|
| 143 |
+
"learning_rate": 4.6199524940617575e-05,
|
| 144 |
+
"loss": 1.1287,
|
| 145 |
"step": 160
|
| 146 |
},
|
| 147 |
{
|
| 148 |
+
"epoch": 2.1725239616613417,
|
| 149 |
+
"grad_norm": 6.460533142089844,
|
| 150 |
+
"learning_rate": 4.5605700712589075e-05,
|
| 151 |
+
"loss": 1.1806,
|
| 152 |
"step": 170
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 2.3003194888178915,
|
| 156 |
+
"grad_norm": 7.450798511505127,
|
| 157 |
+
"learning_rate": 4.501187648456057e-05,
|
| 158 |
+
"loss": 1.1834,
|
| 159 |
"step": 180
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 2.428115015974441,
|
| 163 |
+
"grad_norm": 5.972067832946777,
|
| 164 |
+
"learning_rate": 4.441805225653207e-05,
|
| 165 |
+
"loss": 1.1639,
|
| 166 |
"step": 190
|
| 167 |
},
|
| 168 |
{
|
| 169 |
+
"epoch": 2.5559105431309903,
|
| 170 |
+
"grad_norm": 10.565897941589355,
|
| 171 |
+
"learning_rate": 4.382422802850357e-05,
|
| 172 |
+
"loss": 1.143,
|
| 173 |
"step": 200
|
| 174 |
},
|
| 175 |
{
|
| 176 |
+
"epoch": 2.68370607028754,
|
| 177 |
+
"grad_norm": 11.751137733459473,
|
| 178 |
+
"learning_rate": 4.323040380047506e-05,
|
| 179 |
+
"loss": 1.1911,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 180 |
"step": 210
|
| 181 |
},
|
| 182 |
{
|
| 183 |
+
"epoch": 2.8115015974440896,
|
| 184 |
+
"grad_norm": 8.518805503845215,
|
| 185 |
+
"learning_rate": 4.263657957244656e-05,
|
| 186 |
+
"loss": 1.169,
|
| 187 |
"step": 220
|
| 188 |
},
|
| 189 |
{
|
| 190 |
+
"epoch": 2.939297124600639,
|
| 191 |
+
"grad_norm": 7.631802558898926,
|
| 192 |
+
"learning_rate": 4.204275534441806e-05,
|
| 193 |
+
"loss": 1.168,
|
| 194 |
"step": 230
|
| 195 |
},
|
| 196 |
{
|
| 197 |
+
"epoch": 2.9904153354632586,
|
| 198 |
+
"eval_accuracy": 0.5494252873563218,
|
| 199 |
+
"eval_f1": 0.5033023418313557,
|
| 200 |
+
"eval_loss": 1.0573328733444214,
|
| 201 |
+
"eval_precision": 0.5604674717576669,
|
| 202 |
+
"eval_recall": 0.5494252873563218,
|
| 203 |
+
"eval_runtime": 4.2015,
|
| 204 |
+
"eval_samples_per_second": 103.535,
|
| 205 |
+
"eval_steps_per_second": 6.664,
|
| 206 |
+
"step": 234
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.0670926517571884,
|
| 210 |
+
"grad_norm": 7.9839911460876465,
|
| 211 |
+
"learning_rate": 4.144893111638955e-05,
|
| 212 |
+
"loss": 1.1172,
|
| 213 |
"step": 240
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 3.194888178913738,
|
| 217 |
+
"grad_norm": 8.082262992858887,
|
| 218 |
+
"learning_rate": 4.0855106888361044e-05,
|
| 219 |
+
"loss": 1.1659,
|
| 220 |
"step": 250
|
| 221 |
},
|
| 222 |
{
|
| 223 |
+
"epoch": 3.3226837060702876,
|
| 224 |
+
"grad_norm": 5.319189548492432,
|
| 225 |
+
"learning_rate": 4.0261282660332545e-05,
|
| 226 |
+
"loss": 1.1493,
|
| 227 |
"step": 260
|
| 228 |
},
|
| 229 |
{
|
| 230 |
+
"epoch": 3.450479233226837,
|
| 231 |
+
"grad_norm": 8.54591178894043,
|
| 232 |
+
"learning_rate": 3.966745843230404e-05,
|
| 233 |
+
"loss": 1.1158,
|
| 234 |
"step": 270
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"epoch": 3.5782747603833864,
|
| 238 |
+
"grad_norm": 9.336274147033691,
|
| 239 |
+
"learning_rate": 3.907363420427554e-05,
|
| 240 |
+
"loss": 1.1638,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 241 |
"step": 280
|
| 242 |
},
|
| 243 |
{
|
| 244 |
+
"epoch": 3.7060702875399363,
|
| 245 |
+
"grad_norm": 8.625086784362793,
|
| 246 |
+
"learning_rate": 3.847980997624703e-05,
|
| 247 |
+
"loss": 1.0932,
|
| 248 |
"step": 290
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 3.8338658146964857,
|
| 252 |
+
"grad_norm": 9.026288032531738,
|
| 253 |
+
"learning_rate": 3.7885985748218526e-05,
|
| 254 |
+
"loss": 1.1056,
|
| 255 |
"step": 300
|
| 256 |
},
|
| 257 |
{
|
| 258 |
+
"epoch": 3.961661341853035,
|
| 259 |
+
"grad_norm": 10.40346622467041,
|
| 260 |
+
"learning_rate": 3.7292161520190026e-05,
|
| 261 |
+
"loss": 1.1107,
|
| 262 |
"step": 310
|
| 263 |
},
|
| 264 |
{
|
| 265 |
+
"epoch": 4.0,
|
| 266 |
+
"eval_accuracy": 0.5540229885057472,
|
| 267 |
+
"eval_f1": 0.5163004360032211,
|
| 268 |
+
"eval_loss": 0.9923611879348755,
|
| 269 |
+
"eval_precision": 0.525717492734745,
|
| 270 |
+
"eval_recall": 0.5540229885057472,
|
| 271 |
+
"eval_runtime": 4.1795,
|
| 272 |
+
"eval_samples_per_second": 104.079,
|
| 273 |
+
"eval_steps_per_second": 6.699,
|
| 274 |
+
"step": 313
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 4.0894568690095845,
|
| 278 |
+
"grad_norm": 6.684942722320557,
|
| 279 |
+
"learning_rate": 3.669833729216152e-05,
|
| 280 |
+
"loss": 1.1252,
|
| 281 |
"step": 320
|
| 282 |
},
|
| 283 |
{
|
| 284 |
+
"epoch": 4.217252396166134,
|
| 285 |
+
"grad_norm": 10.904282569885254,
|
| 286 |
+
"learning_rate": 3.6104513064133013e-05,
|
| 287 |
+
"loss": 1.1098,
|
| 288 |
"step": 330
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 4.345047923322683,
|
| 292 |
+
"grad_norm": 9.764264106750488,
|
| 293 |
+
"learning_rate": 3.5510688836104514e-05,
|
| 294 |
"loss": 1.096,
|
| 295 |
"step": 340
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 4.472843450479234,
|
| 299 |
+
"grad_norm": 8.857853889465332,
|
| 300 |
+
"learning_rate": 3.4916864608076014e-05,
|
| 301 |
+
"loss": 1.0528,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 302 |
"step": 350
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 4.600638977635783,
|
| 306 |
+
"grad_norm": 7.500421524047852,
|
| 307 |
+
"learning_rate": 3.432304038004751e-05,
|
| 308 |
+
"loss": 1.1455,
|
| 309 |
"step": 360
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 4.728434504792332,
|
| 313 |
+
"grad_norm": 9.362208366394043,
|
| 314 |
+
"learning_rate": 3.372921615201901e-05,
|
| 315 |
+
"loss": 1.0993,
|
| 316 |
"step": 370
|
| 317 |
},
|
| 318 |
{
|
| 319 |
+
"epoch": 4.856230031948882,
|
| 320 |
+
"grad_norm": 9.38844108581543,
|
| 321 |
+
"learning_rate": 3.31353919239905e-05,
|
| 322 |
+
"loss": 1.0855,
|
| 323 |
"step": 380
|
| 324 |
},
|
| 325 |
{
|
| 326 |
+
"epoch": 4.984025559105431,
|
| 327 |
+
"grad_norm": 6.451258659362793,
|
| 328 |
+
"learning_rate": 3.2541567695961995e-05,
|
| 329 |
+
"loss": 1.1062,
|
| 330 |
"step": 390
|
| 331 |
},
|
| 332 |
{
|
| 333 |
+
"epoch": 4.996805111821086,
|
| 334 |
+
"eval_accuracy": 0.5747126436781609,
|
| 335 |
+
"eval_f1": 0.5507051314754062,
|
| 336 |
+
"eval_loss": 1.0018237829208374,
|
| 337 |
+
"eval_precision": 0.5659922189344513,
|
| 338 |
+
"eval_recall": 0.5747126436781609,
|
| 339 |
+
"eval_runtime": 4.1822,
|
| 340 |
+
"eval_samples_per_second": 104.012,
|
| 341 |
+
"eval_steps_per_second": 6.695,
|
| 342 |
+
"step": 391
|
| 343 |
},
|
| 344 |
{
|
| 345 |
+
"epoch": 5.111821086261981,
|
| 346 |
+
"grad_norm": 8.044933319091797,
|
| 347 |
+
"learning_rate": 3.1947743467933496e-05,
|
| 348 |
+
"loss": 1.0556,
|
| 349 |
+
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 350 |
},
|
| 351 |
{
|
| 352 |
+
"epoch": 5.23961661341853,
|
| 353 |
+
"grad_norm": 9.200007438659668,
|
| 354 |
+
"learning_rate": 3.135391923990499e-05,
|
| 355 |
+
"loss": 1.056,
|
| 356 |
"step": 410
|
| 357 |
},
|
| 358 |
{
|
| 359 |
+
"epoch": 5.36741214057508,
|
| 360 |
+
"grad_norm": 9.929868698120117,
|
| 361 |
+
"learning_rate": 3.076009501187649e-05,
|
| 362 |
+
"loss": 1.0098,
|
| 363 |
"step": 420
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"epoch": 5.49520766773163,
|
| 367 |
+
"grad_norm": 7.43991231918335,
|
| 368 |
+
"learning_rate": 3.0166270783847983e-05,
|
| 369 |
+
"loss": 1.1396,
|
| 370 |
"step": 430
|
| 371 |
},
|
| 372 |
{
|
| 373 |
+
"epoch": 5.623003194888179,
|
| 374 |
+
"grad_norm": 7.019424915313721,
|
| 375 |
+
"learning_rate": 2.9572446555819477e-05,
|
| 376 |
+
"loss": 1.0659,
|
| 377 |
"step": 440
|
| 378 |
},
|
| 379 |
{
|
| 380 |
+
"epoch": 5.7507987220447285,
|
| 381 |
+
"grad_norm": 7.227243900299072,
|
| 382 |
+
"learning_rate": 2.8978622327790977e-05,
|
| 383 |
+
"loss": 1.0453,
|
| 384 |
"step": 450
|
| 385 |
},
|
| 386 |
{
|
| 387 |
+
"epoch": 5.878594249201278,
|
| 388 |
+
"grad_norm": 9.71042537689209,
|
| 389 |
+
"learning_rate": 2.838479809976247e-05,
|
| 390 |
+
"loss": 1.0331,
|
| 391 |
"step": 460
|
| 392 |
},
|
| 393 |
{
|
| 394 |
+
"epoch": 5.993610223642173,
|
| 395 |
+
"eval_accuracy": 0.593103448275862,
|
| 396 |
+
"eval_f1": 0.5768496494171164,
|
| 397 |
+
"eval_loss": 0.9901189208030701,
|
| 398 |
+
"eval_precision": 0.6202225107325855,
|
| 399 |
+
"eval_recall": 0.593103448275862,
|
| 400 |
+
"eval_runtime": 4.1789,
|
| 401 |
+
"eval_samples_per_second": 104.095,
|
| 402 |
+
"eval_steps_per_second": 6.7,
|
| 403 |
+
"step": 469
|
| 404 |
},
|
| 405 |
{
|
| 406 |
+
"epoch": 6.006389776357827,
|
| 407 |
+
"grad_norm": 6.03436279296875,
|
| 408 |
+
"learning_rate": 2.7790973871733968e-05,
|
| 409 |
+
"loss": 1.135,
|
| 410 |
+
"step": 470
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 411 |
},
|
| 412 |
{
|
| 413 |
+
"epoch": 6.134185303514377,
|
| 414 |
+
"grad_norm": 7.317747592926025,
|
| 415 |
+
"learning_rate": 2.7197149643705465e-05,
|
| 416 |
+
"loss": 1.0316,
|
| 417 |
"step": 480
|
| 418 |
},
|
| 419 |
{
|
| 420 |
+
"epoch": 6.261980830670926,
|
| 421 |
+
"grad_norm": 7.093214511871338,
|
| 422 |
+
"learning_rate": 2.6603325415676962e-05,
|
| 423 |
+
"loss": 1.0445,
|
| 424 |
"step": 490
|
| 425 |
},
|
| 426 |
{
|
| 427 |
+
"epoch": 6.389776357827476,
|
| 428 |
+
"grad_norm": 8.44990348815918,
|
| 429 |
+
"learning_rate": 2.6009501187648455e-05,
|
| 430 |
+
"loss": 1.064,
|
| 431 |
"step": 500
|
| 432 |
},
|
| 433 |
{
|
| 434 |
+
"epoch": 6.517571884984026,
|
| 435 |
+
"grad_norm": 8.586387634277344,
|
| 436 |
+
"learning_rate": 2.5415676959619956e-05,
|
| 437 |
+
"loss": 1.0428,
|
| 438 |
"step": 510
|
| 439 |
},
|
| 440 |
{
|
| 441 |
+
"epoch": 6.645367412140575,
|
| 442 |
+
"grad_norm": 8.286543846130371,
|
| 443 |
+
"learning_rate": 2.482185273159145e-05,
|
| 444 |
+
"loss": 1.0424,
|
| 445 |
"step": 520
|
| 446 |
},
|
| 447 |
{
|
| 448 |
+
"epoch": 6.773162939297125,
|
| 449 |
+
"grad_norm": 11.05722427368164,
|
| 450 |
+
"learning_rate": 2.4228028503562946e-05,
|
| 451 |
+
"loss": 1.0486,
|
| 452 |
"step": 530
|
| 453 |
},
|
| 454 |
{
|
| 455 |
+
"epoch": 6.900958466453674,
|
| 456 |
+
"grad_norm": 11.715845108032227,
|
| 457 |
+
"learning_rate": 2.3634204275534443e-05,
|
| 458 |
+
"loss": 1.0409,
|
| 459 |
"step": 540
|
| 460 |
},
|
| 461 |
{
|
| 462 |
+
"epoch": 6.9904153354632586,
|
| 463 |
+
"eval_accuracy": 0.5747126436781609,
|
| 464 |
+
"eval_f1": 0.5723268617274374,
|
| 465 |
+
"eval_loss": 0.9633908867835999,
|
| 466 |
+
"eval_precision": 0.5722167544506434,
|
| 467 |
+
"eval_recall": 0.5747126436781609,
|
| 468 |
+
"eval_runtime": 4.2036,
|
| 469 |
+
"eval_samples_per_second": 103.482,
|
| 470 |
+
"eval_steps_per_second": 6.661,
|
| 471 |
+
"step": 547
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 7.0287539936102235,
|
| 475 |
+
"grad_norm": 9.900256156921387,
|
| 476 |
+
"learning_rate": 2.3040380047505937e-05,
|
| 477 |
+
"loss": 1.021,
|
| 478 |
"step": 550
|
| 479 |
},
|
| 480 |
{
|
| 481 |
+
"epoch": 7.156549520766773,
|
| 482 |
+
"grad_norm": 11.22358226776123,
|
| 483 |
+
"learning_rate": 2.2446555819477437e-05,
|
| 484 |
+
"loss": 1.0387,
|
| 485 |
"step": 560
|
| 486 |
},
|
| 487 |
{
|
| 488 |
+
"epoch": 7.284345047923322,
|
| 489 |
+
"grad_norm": 6.466274738311768,
|
| 490 |
+
"learning_rate": 2.1852731591448934e-05,
|
| 491 |
+
"loss": 1.0166,
|
| 492 |
"step": 570
|
| 493 |
},
|
| 494 |
{
|
| 495 |
+
"epoch": 7.412140575079873,
|
| 496 |
+
"grad_norm": 9.685991287231445,
|
| 497 |
+
"learning_rate": 2.1258907363420428e-05,
|
| 498 |
+
"loss": 1.0459,
|
| 499 |
"step": 580
|
| 500 |
},
|
| 501 |
{
|
| 502 |
+
"epoch": 7.539936102236422,
|
| 503 |
+
"grad_norm": 9.211965560913086,
|
| 504 |
+
"learning_rate": 2.0665083135391925e-05,
|
| 505 |
+
"loss": 0.9852,
|
| 506 |
"step": 590
|
| 507 |
},
|
| 508 |
{
|
| 509 |
+
"epoch": 7.667731629392971,
|
| 510 |
+
"grad_norm": 9.930057525634766,
|
| 511 |
+
"learning_rate": 2.0071258907363422e-05,
|
| 512 |
+
"loss": 1.0176,
|
| 513 |
"step": 600
|
| 514 |
},
|
| 515 |
{
|
| 516 |
+
"epoch": 7.795527156549521,
|
| 517 |
+
"grad_norm": 12.529800415039062,
|
| 518 |
+
"learning_rate": 1.947743467933492e-05,
|
| 519 |
+
"loss": 1.0465,
|
| 520 |
"step": 610
|
| 521 |
},
|
| 522 |
{
|
| 523 |
+
"epoch": 7.92332268370607,
|
| 524 |
+
"grad_norm": 9.018549919128418,
|
| 525 |
+
"learning_rate": 1.8883610451306412e-05,
|
| 526 |
+
"loss": 1.0176,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 527 |
"step": 620
|
| 528 |
},
|
| 529 |
{
|
| 530 |
+
"epoch": 8.0,
|
| 531 |
+
"eval_accuracy": 0.593103448275862,
|
| 532 |
+
"eval_f1": 0.5833555266825051,
|
| 533 |
+
"eval_loss": 0.9504066705703735,
|
| 534 |
+
"eval_precision": 0.5813528993323179,
|
| 535 |
+
"eval_recall": 0.593103448275862,
|
| 536 |
+
"eval_runtime": 4.1774,
|
| 537 |
+
"eval_samples_per_second": 104.131,
|
| 538 |
+
"eval_steps_per_second": 6.703,
|
| 539 |
+
"step": 626
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 8.05111821086262,
|
| 543 |
+
"grad_norm": 8.328828811645508,
|
| 544 |
+
"learning_rate": 1.828978622327791e-05,
|
| 545 |
+
"loss": 0.9516,
|
| 546 |
"step": 630
|
| 547 |
},
|
| 548 |
{
|
| 549 |
+
"epoch": 8.178913738019169,
|
| 550 |
+
"grad_norm": 7.750000476837158,
|
| 551 |
+
"learning_rate": 1.7695961995249406e-05,
|
| 552 |
+
"loss": 0.972,
|
| 553 |
"step": 640
|
| 554 |
},
|
| 555 |
{
|
| 556 |
+
"epoch": 8.30670926517572,
|
| 557 |
+
"grad_norm": 6.95557165145874,
|
| 558 |
+
"learning_rate": 1.7102137767220903e-05,
|
| 559 |
+
"loss": 0.9842,
|
| 560 |
"step": 650
|
| 561 |
},
|
| 562 |
{
|
| 563 |
+
"epoch": 8.434504792332268,
|
| 564 |
+
"grad_norm": 8.893524169921875,
|
| 565 |
+
"learning_rate": 1.65083135391924e-05,
|
| 566 |
+
"loss": 1.02,
|
| 567 |
"step": 660
|
| 568 |
},
|
| 569 |
{
|
| 570 |
+
"epoch": 8.562300319488818,
|
| 571 |
+
"grad_norm": 9.984440803527832,
|
| 572 |
+
"learning_rate": 1.5914489311163897e-05,
|
| 573 |
+
"loss": 0.97,
|
| 574 |
"step": 670
|
| 575 |
},
|
| 576 |
{
|
| 577 |
+
"epoch": 8.690095846645367,
|
| 578 |
+
"grad_norm": 8.314949989318848,
|
| 579 |
+
"learning_rate": 1.5320665083135394e-05,
|
| 580 |
+
"loss": 1.0366,
|
| 581 |
"step": 680
|
| 582 |
},
|
| 583 |
{
|
| 584 |
+
"epoch": 8.817891373801917,
|
| 585 |
+
"grad_norm": 9.685540199279785,
|
| 586 |
+
"learning_rate": 1.4726840855106888e-05,
|
| 587 |
+
"loss": 1.0284,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 588 |
"step": 690
|
| 589 |
},
|
| 590 |
{
|
| 591 |
+
"epoch": 8.945686900958467,
|
| 592 |
+
"grad_norm": 10.43076229095459,
|
| 593 |
+
"learning_rate": 1.4133016627078385e-05,
|
| 594 |
+
"loss": 0.995,
|
| 595 |
"step": 700
|
| 596 |
},
|
| 597 |
{
|
| 598 |
+
"epoch": 8.996805111821086,
|
| 599 |
+
"eval_accuracy": 0.5908045977011495,
|
| 600 |
+
"eval_f1": 0.5853582114263199,
|
| 601 |
+
"eval_loss": 0.9584209322929382,
|
| 602 |
+
"eval_precision": 0.5853113777126823,
|
| 603 |
+
"eval_recall": 0.5908045977011495,
|
| 604 |
+
"eval_runtime": 4.2105,
|
| 605 |
+
"eval_samples_per_second": 103.314,
|
| 606 |
+
"eval_steps_per_second": 6.65,
|
| 607 |
+
"step": 704
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 9.073482428115016,
|
| 611 |
+
"grad_norm": 8.847938537597656,
|
| 612 |
+
"learning_rate": 1.3539192399049882e-05,
|
| 613 |
+
"loss": 0.9524,
|
| 614 |
"step": 710
|
| 615 |
},
|
| 616 |
{
|
| 617 |
+
"epoch": 9.201277955271566,
|
| 618 |
+
"grad_norm": 8.750248908996582,
|
| 619 |
+
"learning_rate": 1.2945368171021377e-05,
|
| 620 |
+
"loss": 0.9846,
|
| 621 |
"step": 720
|
| 622 |
},
|
| 623 |
{
|
| 624 |
+
"epoch": 9.329073482428115,
|
| 625 |
+
"grad_norm": 9.161256790161133,
|
| 626 |
+
"learning_rate": 1.2351543942992874e-05,
|
| 627 |
+
"loss": 0.9751,
|
| 628 |
"step": 730
|
| 629 |
},
|
| 630 |
{
|
| 631 |
+
"epoch": 9.456869009584665,
|
| 632 |
+
"grad_norm": 9.544412612915039,
|
| 633 |
+
"learning_rate": 1.1757719714964371e-05,
|
| 634 |
+
"loss": 0.9417,
|
| 635 |
"step": 740
|
| 636 |
},
|
| 637 |
{
|
| 638 |
+
"epoch": 9.584664536741213,
|
| 639 |
+
"grad_norm": 9.703606605529785,
|
| 640 |
+
"learning_rate": 1.1163895486935868e-05,
|
| 641 |
+
"loss": 0.9707,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 642 |
"step": 750
|
| 643 |
},
|
| 644 |
{
|
| 645 |
+
"epoch": 9.712460063897764,
|
| 646 |
+
"grad_norm": 9.677326202392578,
|
| 647 |
+
"learning_rate": 1.0570071258907365e-05,
|
| 648 |
+
"loss": 1.0009,
|
| 649 |
"step": 760
|
| 650 |
},
|
| 651 |
{
|
| 652 |
+
"epoch": 9.840255591054314,
|
| 653 |
+
"grad_norm": 8.860432624816895,
|
| 654 |
+
"learning_rate": 9.97624703087886e-06,
|
| 655 |
+
"loss": 0.9817,
|
| 656 |
"step": 770
|
| 657 |
},
|
| 658 |
{
|
| 659 |
+
"epoch": 9.968051118210862,
|
| 660 |
+
"grad_norm": 8.743229866027832,
|
| 661 |
+
"learning_rate": 9.382422802850356e-06,
|
| 662 |
+
"loss": 0.9937,
|
| 663 |
"step": 780
|
| 664 |
},
|
| 665 |
{
|
| 666 |
+
"epoch": 9.993610223642172,
|
| 667 |
+
"eval_accuracy": 0.6022988505747127,
|
| 668 |
+
"eval_f1": 0.5934331301305344,
|
| 669 |
+
"eval_loss": 0.9338871240615845,
|
| 670 |
+
"eval_precision": 0.5893665058889589,
|
| 671 |
+
"eval_recall": 0.6022988505747127,
|
| 672 |
+
"eval_runtime": 4.2268,
|
| 673 |
+
"eval_samples_per_second": 102.915,
|
| 674 |
+
"eval_steps_per_second": 6.624,
|
| 675 |
+
"step": 782
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 10.095846645367413,
|
| 679 |
+
"grad_norm": 7.1755900382995605,
|
| 680 |
+
"learning_rate": 8.788598574821852e-06,
|
| 681 |
+
"loss": 0.9908,
|
| 682 |
"step": 790
|
| 683 |
},
|
| 684 |
{
|
| 685 |
+
"epoch": 10.223642172523961,
|
| 686 |
+
"grad_norm": 8.917673110961914,
|
| 687 |
+
"learning_rate": 8.19477434679335e-06,
|
| 688 |
+
"loss": 0.9361,
|
| 689 |
"step": 800
|
| 690 |
},
|
| 691 |
{
|
| 692 |
+
"epoch": 10.351437699680512,
|
| 693 |
+
"grad_norm": 15.518793106079102,
|
| 694 |
+
"learning_rate": 7.6009501187648464e-06,
|
| 695 |
+
"loss": 0.9495,
|
| 696 |
"step": 810
|
| 697 |
},
|
| 698 |
{
|
| 699 |
+
"epoch": 10.47923322683706,
|
| 700 |
+
"grad_norm": 12.074665069580078,
|
| 701 |
+
"learning_rate": 7.007125890736342e-06,
|
| 702 |
+
"loss": 0.9689,
|
| 703 |
+
"step": 820
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 10.60702875399361,
|
| 707 |
+
"grad_norm": 9.314558982849121,
|
| 708 |
+
"learning_rate": 6.4133016627078396e-06,
|
| 709 |
+
"loss": 0.983,
|
| 710 |
+
"step": 830
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 10.73482428115016,
|
| 714 |
+
"grad_norm": 9.714004516601562,
|
| 715 |
+
"learning_rate": 5.819477434679335e-06,
|
| 716 |
+
"loss": 1.0,
|
| 717 |
+
"step": 840
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 10.86261980830671,
|
| 721 |
+
"grad_norm": 9.66527271270752,
|
| 722 |
+
"learning_rate": 5.225653206650832e-06,
|
| 723 |
+
"loss": 0.9036,
|
| 724 |
+
"step": 850
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 10.99041533546326,
|
| 728 |
+
"grad_norm": 11.544416427612305,
|
| 729 |
+
"learning_rate": 4.631828978622328e-06,
|
| 730 |
+
"loss": 0.9387,
|
| 731 |
+
"step": 860
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 10.99041533546326,
|
| 735 |
+
"eval_accuracy": 0.6137931034482759,
|
| 736 |
+
"eval_f1": 0.5996477650763593,
|
| 737 |
+
"eval_loss": 0.9119637608528137,
|
| 738 |
+
"eval_precision": 0.596855024118962,
|
| 739 |
+
"eval_recall": 0.6137931034482759,
|
| 740 |
+
"eval_runtime": 4.2091,
|
| 741 |
+
"eval_samples_per_second": 103.347,
|
| 742 |
+
"eval_steps_per_second": 6.652,
|
| 743 |
+
"step": 860
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 11.118210862619808,
|
| 747 |
+
"grad_norm": 9.786779403686523,
|
| 748 |
+
"learning_rate": 4.038004750593825e-06,
|
| 749 |
+
"loss": 0.911,
|
| 750 |
+
"step": 870
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 11.246006389776358,
|
| 754 |
+
"grad_norm": 10.40623664855957,
|
| 755 |
+
"learning_rate": 3.4441805225653207e-06,
|
| 756 |
+
"loss": 0.9683,
|
| 757 |
+
"step": 880
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 11.373801916932907,
|
| 761 |
+
"grad_norm": 10.116272926330566,
|
| 762 |
+
"learning_rate": 2.850356294536817e-06,
|
| 763 |
+
"loss": 0.9074,
|
| 764 |
+
"step": 890
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 11.501597444089457,
|
| 768 |
+
"grad_norm": 9.423429489135742,
|
| 769 |
+
"learning_rate": 2.2565320665083133e-06,
|
| 770 |
+
"loss": 0.908,
|
| 771 |
+
"step": 900
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 11.629392971246006,
|
| 775 |
+
"grad_norm": 11.146402359008789,
|
| 776 |
+
"learning_rate": 1.6627078384798101e-06,
|
| 777 |
+
"loss": 0.9744,
|
| 778 |
+
"step": 910
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 11.757188498402556,
|
| 782 |
+
"grad_norm": 11.125927925109863,
|
| 783 |
+
"learning_rate": 1.0688836104513065e-06,
|
| 784 |
+
"loss": 0.9541,
|
| 785 |
+
"step": 920
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 11.884984025559106,
|
| 789 |
+
"grad_norm": 10.135693550109863,
|
| 790 |
+
"learning_rate": 4.750593824228029e-07,
|
| 791 |
+
"loss": 0.9324,
|
| 792 |
+
"step": 930
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 11.961661341853034,
|
| 796 |
+
"eval_accuracy": 0.5954022988505747,
|
| 797 |
+
"eval_f1": 0.5878627034099811,
|
| 798 |
+
"eval_loss": 0.9134895205497742,
|
| 799 |
+
"eval_precision": 0.5865253155328708,
|
| 800 |
+
"eval_recall": 0.5954022988505747,
|
| 801 |
+
"eval_runtime": 4.3073,
|
| 802 |
+
"eval_samples_per_second": 100.992,
|
| 803 |
+
"eval_steps_per_second": 6.501,
|
| 804 |
+
"step": 936
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 11.961661341853034,
|
| 808 |
+
"step": 936,
|
| 809 |
+
"total_flos": 4.743827088137626e+18,
|
| 810 |
+
"train_loss": 1.079931161342523,
|
| 811 |
+
"train_runtime": 2308.5403,
|
| 812 |
+
"train_samples_per_second": 26.027,
|
| 813 |
+
"train_steps_per_second": 0.405
|
| 814 |
}
|
| 815 |
],
|
| 816 |
"logging_steps": 10,
|
| 817 |
+
"max_steps": 936,
|
| 818 |
"num_input_tokens_seen": 0,
|
| 819 |
"num_train_epochs": 12,
|
| 820 |
"save_steps": 500,
|
|
|
|
| 830 |
"attributes": {}
|
| 831 |
}
|
| 832 |
},
|
| 833 |
+
"total_flos": 4.743827088137626e+18,
|
| 834 |
"train_batch_size": 16,
|
| 835 |
"trial_name": null,
|
| 836 |
"trial_params": null
|