🍻 cheers
Browse files- README.md +4 -3
- all_results.json +10 -10
- data/events.out.tfevents.1730611272.07f6fc948a6b.436.3 +3 -0
- eval_results.json +5 -5
- train_results.json +5 -5
- trainer_state.json +717 -1119
README.md
CHANGED
|
@@ -3,6 +3,7 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
- imagefolder
|
|
@@ -23,7 +24,7 @@ model-index:
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
-
value: 0.
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -33,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss:
|
| 37 |
-
- Accuracy: 0.
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
| 6 |
+
- image-classification
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- imagefolder
|
|
|
|
| 24 |
metrics:
|
| 25 |
- name: Accuracy
|
| 26 |
type: accuracy
|
| 27 |
+
value: 0.6745283018867925
|
| 28 |
---
|
| 29 |
|
| 30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 34 |
|
| 35 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 36 |
It achieves the following results on the evaluation set:
|
| 37 |
+
- Loss: 0.7452
|
| 38 |
+
- Accuracy: 0.6745
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 13.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 1.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 13.0,
|
| 3 |
+
"eval_accuracy": 0.6745283018867925,
|
| 4 |
+
"eval_loss": 0.7452366948127747,
|
| 5 |
+
"eval_runtime": 2.5059,
|
| 6 |
+
"eval_samples_per_second": 84.599,
|
| 7 |
+
"eval_steps_per_second": 10.774,
|
| 8 |
+
"total_flos": 1.9140864535683072e+18,
|
| 9 |
+
"train_loss": 0.35688263059153663,
|
| 10 |
+
"train_runtime": 955.328,
|
| 11 |
+
"train_samples_per_second": 25.855,
|
| 12 |
+
"train_steps_per_second": 1.619
|
| 13 |
}
|
data/events.out.tfevents.1730611272.07f6fc948a6b.436.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b63372cd34724660f122424e445f8909de85a62b82dc5b17c298bf39f592829d
|
| 3 |
+
size 411
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 13.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 13.0,
|
| 3 |
+
"eval_accuracy": 0.6745283018867925,
|
| 4 |
+
"eval_loss": 0.7452366948127747,
|
| 5 |
+
"eval_runtime": 2.5059,
|
| 6 |
+
"eval_samples_per_second": 84.599,
|
| 7 |
+
"eval_steps_per_second": 10.774
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 13.0,
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 1.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 13.0,
|
| 3 |
+
"total_flos": 1.9140864535683072e+18,
|
| 4 |
+
"train_loss": 0.35688263059153663,
|
| 5 |
+
"train_runtime": 955.328,
|
| 6 |
+
"train_samples_per_second": 25.855,
|
| 7 |
+
"train_steps_per_second": 1.619
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1640 +1,1238 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "vit-weldclassifyv4/checkpoint-
|
| 4 |
"epoch": 13.0,
|
| 5 |
"eval_steps": 100,
|
| 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": 1.
|
| 14 |
-
"learning_rate": 0.
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate": 0.
|
| 22 |
-
"loss": 1.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm":
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
-
"loss": 1.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate": 0.
|
| 36 |
-
"loss": 1.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm":
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm":
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate": 0.
|
| 57 |
-
"loss": 1.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm": 1.
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss": 1.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss": 1.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate": 0.
|
| 78 |
-
"loss":
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"eval_accuracy": 0.
|
| 84 |
-
"eval_loss":
|
| 85 |
-
"eval_runtime": 2.
|
| 86 |
-
"eval_samples_per_second":
|
| 87 |
-
"eval_steps_per_second":
|
| 88 |
"step": 100
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"epoch": 0.
|
| 92 |
-
"grad_norm": 1.
|
| 93 |
-
"learning_rate": 0.
|
| 94 |
-
"loss":
|
| 95 |
"step": 110
|
| 96 |
},
|
| 97 |
{
|
| 98 |
-
"epoch":
|
| 99 |
-
"grad_norm":
|
| 100 |
-
"learning_rate": 0.
|
| 101 |
-
"loss":
|
| 102 |
"step": 120
|
| 103 |
},
|
| 104 |
{
|
| 105 |
-
"epoch":
|
| 106 |
-
"grad_norm": 1.
|
| 107 |
-
"learning_rate": 0.
|
| 108 |
-
"loss":
|
| 109 |
"step": 130
|
| 110 |
},
|
| 111 |
{
|
| 112 |
-
"epoch":
|
| 113 |
-
"grad_norm":
|
| 114 |
-
"learning_rate": 0.
|
| 115 |
-
"loss":
|
| 116 |
"step": 140
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch":
|
| 120 |
-
"grad_norm":
|
| 121 |
-
"learning_rate": 0.
|
| 122 |
-
"loss": 1.
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 1.
|
| 127 |
-
"grad_norm":
|
| 128 |
-
"learning_rate": 0.
|
| 129 |
-
"loss": 1.
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
-
"epoch": 1.
|
| 134 |
-
"grad_norm": 1.
|
| 135 |
-
"learning_rate": 0.
|
| 136 |
-
"loss":
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
-
"epoch": 1.
|
| 141 |
-
"grad_norm":
|
| 142 |
-
"learning_rate": 0.
|
| 143 |
-
"loss":
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
-
"epoch": 1.
|
| 148 |
-
"grad_norm":
|
| 149 |
-
"learning_rate": 0.
|
| 150 |
-
"loss":
|
| 151 |
"step": 190
|
| 152 |
},
|
| 153 |
{
|
| 154 |
-
"epoch": 1.
|
| 155 |
-
"grad_norm":
|
| 156 |
-
"learning_rate": 0.
|
| 157 |
-
"loss":
|
| 158 |
"step": 200
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch": 1.
|
| 162 |
-
"eval_accuracy": 0.
|
| 163 |
-
"eval_loss":
|
| 164 |
-
"eval_runtime":
|
| 165 |
-
"eval_samples_per_second":
|
| 166 |
-
"eval_steps_per_second":
|
| 167 |
"step": 200
|
| 168 |
},
|
| 169 |
{
|
| 170 |
-
"epoch": 1.
|
| 171 |
-
"grad_norm": 1.
|
| 172 |
-
"learning_rate": 0.
|
| 173 |
-
"loss":
|
| 174 |
"step": 210
|
| 175 |
},
|
| 176 |
{
|
| 177 |
-
"epoch": 1.
|
| 178 |
-
"grad_norm":
|
| 179 |
-
"learning_rate": 0.
|
| 180 |
-
"loss":
|
| 181 |
"step": 220
|
| 182 |
},
|
| 183 |
{
|
| 184 |
-
"epoch": 1.
|
| 185 |
-
"grad_norm": 1.
|
| 186 |
-
"learning_rate": 0.
|
| 187 |
-
"loss":
|
| 188 |
"step": 230
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch":
|
| 192 |
-
"grad_norm":
|
| 193 |
-
"learning_rate": 0.
|
| 194 |
-
"loss":
|
| 195 |
"step": 240
|
| 196 |
},
|
| 197 |
{
|
| 198 |
-
"epoch":
|
| 199 |
-
"grad_norm":
|
| 200 |
-
"learning_rate": 0.
|
| 201 |
-
"loss": 0.
|
| 202 |
"step": 250
|
| 203 |
},
|
| 204 |
{
|
| 205 |
-
"epoch":
|
| 206 |
-
"grad_norm":
|
| 207 |
-
"learning_rate": 0.
|
| 208 |
-
"loss":
|
| 209 |
"step": 260
|
| 210 |
},
|
| 211 |
{
|
| 212 |
-
"epoch":
|
| 213 |
-
"grad_norm":
|
| 214 |
-
"learning_rate": 0.
|
| 215 |
-
"loss": 0.
|
| 216 |
"step": 270
|
| 217 |
},
|
| 218 |
{
|
| 219 |
-
"epoch":
|
| 220 |
-
"grad_norm":
|
| 221 |
-
"learning_rate": 0.
|
| 222 |
-
"loss": 0.
|
| 223 |
"step": 280
|
| 224 |
},
|
| 225 |
{
|
| 226 |
-
"epoch":
|
| 227 |
-
"grad_norm":
|
| 228 |
-
"learning_rate": 0.
|
| 229 |
-
"loss": 0.
|
| 230 |
"step": 290
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"epoch":
|
| 234 |
-
"grad_norm":
|
| 235 |
-
"learning_rate": 0.
|
| 236 |
-
"loss":
|
| 237 |
"step": 300
|
| 238 |
},
|
| 239 |
{
|
| 240 |
-
"epoch":
|
| 241 |
-
"eval_accuracy": 0.
|
| 242 |
-
"eval_loss": 0.
|
| 243 |
-
"eval_runtime": 2.
|
| 244 |
-
"eval_samples_per_second":
|
| 245 |
-
"eval_steps_per_second":
|
| 246 |
"step": 300
|
| 247 |
},
|
| 248 |
{
|
| 249 |
-
"epoch":
|
| 250 |
-
"grad_norm": 2.
|
| 251 |
-
"learning_rate": 0.
|
| 252 |
-
"loss": 0.
|
| 253 |
"step": 310
|
| 254 |
},
|
| 255 |
{
|
| 256 |
-
"epoch": 2.
|
| 257 |
-
"grad_norm":
|
| 258 |
-
"learning_rate": 0.
|
| 259 |
-
"loss": 0.
|
| 260 |
"step": 320
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"epoch": 2.
|
| 264 |
-
"grad_norm":
|
| 265 |
-
"learning_rate": 0.
|
| 266 |
-
"loss": 0.
|
| 267 |
"step": 330
|
| 268 |
},
|
| 269 |
{
|
| 270 |
-
"epoch": 2.
|
| 271 |
-
"grad_norm":
|
| 272 |
-
"learning_rate": 0.
|
| 273 |
-
"loss": 0.
|
| 274 |
"step": 340
|
| 275 |
},
|
| 276 |
{
|
| 277 |
-
"epoch": 2.
|
| 278 |
-
"grad_norm":
|
| 279 |
-
"learning_rate": 0.
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 350
|
| 282 |
},
|
| 283 |
{
|
| 284 |
-
"epoch":
|
| 285 |
-
"grad_norm": 2.
|
| 286 |
-
"learning_rate": 0.
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 360
|
| 289 |
},
|
| 290 |
{
|
| 291 |
-
"epoch":
|
| 292 |
-
"grad_norm":
|
| 293 |
-
"learning_rate": 0.
|
| 294 |
-
"loss": 0.
|
| 295 |
"step": 370
|
| 296 |
},
|
| 297 |
{
|
| 298 |
-
"epoch":
|
| 299 |
-
"grad_norm": 1.
|
| 300 |
-
"learning_rate": 0.
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 380
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"epoch":
|
| 306 |
-
"grad_norm":
|
| 307 |
-
"learning_rate": 0.
|
| 308 |
-
"loss": 0.
|
| 309 |
"step": 390
|
| 310 |
},
|
| 311 |
{
|
| 312 |
-
"epoch":
|
| 313 |
-
"grad_norm":
|
| 314 |
-
"learning_rate": 0.
|
| 315 |
-
"loss": 0.
|
| 316 |
"step": 400
|
| 317 |
},
|
| 318 |
{
|
| 319 |
-
"epoch":
|
| 320 |
-
"eval_accuracy": 0.
|
| 321 |
-
"eval_loss": 0.
|
| 322 |
-
"eval_runtime":
|
| 323 |
-
"eval_samples_per_second":
|
| 324 |
-
"eval_steps_per_second":
|
| 325 |
"step": 400
|
| 326 |
},
|
| 327 |
{
|
| 328 |
-
"epoch":
|
| 329 |
-
"grad_norm":
|
| 330 |
-
"learning_rate": 0.
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 410
|
| 333 |
},
|
| 334 |
{
|
| 335 |
-
"epoch":
|
| 336 |
-
"grad_norm":
|
| 337 |
-
"learning_rate": 0.
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 420
|
| 340 |
},
|
| 341 |
{
|
| 342 |
-
"epoch":
|
| 343 |
-
"grad_norm":
|
| 344 |
-
"learning_rate": 0.
|
| 345 |
-
"loss": 0.
|
| 346 |
"step": 430
|
| 347 |
},
|
| 348 |
{
|
| 349 |
-
"epoch":
|
| 350 |
-
"grad_norm":
|
| 351 |
-
"learning_rate": 0.
|
| 352 |
-
"loss": 0.
|
| 353 |
"step": 440
|
| 354 |
},
|
| 355 |
{
|
| 356 |
-
"epoch":
|
| 357 |
-
"grad_norm":
|
| 358 |
-
"learning_rate": 0.
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 450
|
| 361 |
},
|
| 362 |
{
|
| 363 |
-
"epoch":
|
| 364 |
-
"grad_norm":
|
| 365 |
-
"learning_rate": 0.
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 460
|
| 368 |
},
|
| 369 |
{
|
| 370 |
-
"epoch":
|
| 371 |
-
"grad_norm": 2.
|
| 372 |
-
"learning_rate": 0.
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 470
|
| 375 |
},
|
| 376 |
{
|
| 377 |
-
"epoch":
|
| 378 |
-
"grad_norm":
|
| 379 |
-
"learning_rate": 0.
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 480
|
| 382 |
},
|
| 383 |
{
|
| 384 |
-
"epoch":
|
| 385 |
-
"grad_norm":
|
| 386 |
-
"learning_rate": 0.
|
| 387 |
-
"loss": 0.
|
| 388 |
"step": 490
|
| 389 |
},
|
| 390 |
{
|
| 391 |
-
"epoch":
|
| 392 |
-
"grad_norm": 2.
|
| 393 |
-
"learning_rate": 0.
|
| 394 |
-
"loss": 0.
|
| 395 |
"step": 500
|
| 396 |
},
|
| 397 |
{
|
| 398 |
-
"epoch":
|
| 399 |
-
"eval_accuracy": 0.
|
| 400 |
-
"eval_loss": 0.
|
| 401 |
-
"eval_runtime":
|
| 402 |
-
"eval_samples_per_second":
|
| 403 |
-
"eval_steps_per_second":
|
| 404 |
"step": 500
|
| 405 |
},
|
| 406 |
{
|
| 407 |
-
"epoch":
|
| 408 |
-
"grad_norm":
|
| 409 |
-
"learning_rate": 0.
|
| 410 |
-
"loss": 0.
|
| 411 |
"step": 510
|
| 412 |
},
|
| 413 |
{
|
| 414 |
-
"epoch":
|
| 415 |
-
"grad_norm":
|
| 416 |
-
"learning_rate": 0.
|
| 417 |
-
"loss": 0.
|
| 418 |
"step": 520
|
| 419 |
},
|
| 420 |
{
|
| 421 |
-
"epoch":
|
| 422 |
-
"grad_norm": 1.
|
| 423 |
-
"learning_rate": 0.
|
| 424 |
-
"loss": 0.
|
| 425 |
"step": 530
|
| 426 |
},
|
| 427 |
{
|
| 428 |
-
"epoch":
|
| 429 |
-
"grad_norm": 0.
|
| 430 |
-
"learning_rate": 0.
|
| 431 |
-
"loss": 0.
|
| 432 |
"step": 540
|
| 433 |
},
|
| 434 |
{
|
| 435 |
-
"epoch":
|
| 436 |
-
"grad_norm":
|
| 437 |
-
"learning_rate": 0.
|
| 438 |
-
"loss": 0.
|
| 439 |
"step": 550
|
| 440 |
},
|
| 441 |
{
|
| 442 |
-
"epoch":
|
| 443 |
-
"grad_norm":
|
| 444 |
-
"learning_rate": 0.
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 560
|
| 447 |
},
|
| 448 |
{
|
| 449 |
-
"epoch":
|
| 450 |
-
"grad_norm":
|
| 451 |
-
"learning_rate": 0.
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 570
|
| 454 |
},
|
| 455 |
{
|
| 456 |
-
"epoch":
|
| 457 |
-
"grad_norm": 2.
|
| 458 |
-
"learning_rate": 0.
|
| 459 |
-
"loss": 0.
|
| 460 |
"step": 580
|
| 461 |
},
|
| 462 |
{
|
| 463 |
-
"epoch":
|
| 464 |
-
"grad_norm":
|
| 465 |
-
"learning_rate": 0.
|
| 466 |
-
"loss": 0.
|
| 467 |
"step": 590
|
| 468 |
},
|
| 469 |
{
|
| 470 |
-
"epoch":
|
| 471 |
-
"grad_norm":
|
| 472 |
-
"learning_rate": 0.
|
| 473 |
-
"loss": 0.
|
| 474 |
"step": 600
|
| 475 |
},
|
| 476 |
{
|
| 477 |
-
"epoch":
|
| 478 |
-
"eval_accuracy": 0.
|
| 479 |
-
"eval_loss":
|
| 480 |
-
"eval_runtime":
|
| 481 |
-
"eval_samples_per_second":
|
| 482 |
-
"eval_steps_per_second":
|
| 483 |
"step": 600
|
| 484 |
},
|
| 485 |
{
|
| 486 |
-
"epoch":
|
| 487 |
-
"grad_norm":
|
| 488 |
-
"learning_rate": 0.
|
| 489 |
-
"loss": 0.
|
| 490 |
"step": 610
|
| 491 |
},
|
| 492 |
{
|
| 493 |
-
"epoch":
|
| 494 |
-
"grad_norm":
|
| 495 |
-
"learning_rate": 0.
|
| 496 |
-
"loss": 0.
|
| 497 |
"step": 620
|
| 498 |
},
|
| 499 |
{
|
| 500 |
-
"epoch":
|
| 501 |
-
"grad_norm": 5.
|
| 502 |
-
"learning_rate": 0.
|
| 503 |
-
"loss": 0.
|
| 504 |
"step": 630
|
| 505 |
},
|
| 506 |
{
|
| 507 |
-
"epoch":
|
| 508 |
-
"grad_norm":
|
| 509 |
-
"learning_rate": 0.
|
| 510 |
-
"loss": 0.
|
| 511 |
"step": 640
|
| 512 |
},
|
| 513 |
{
|
| 514 |
-
"epoch":
|
| 515 |
-
"grad_norm":
|
| 516 |
-
"learning_rate": 0.
|
| 517 |
-
"loss": 0.
|
| 518 |
"step": 650
|
| 519 |
},
|
| 520 |
{
|
| 521 |
-
"epoch":
|
| 522 |
-
"grad_norm":
|
| 523 |
-
"learning_rate": 0.
|
| 524 |
-
"loss": 0.
|
| 525 |
"step": 660
|
| 526 |
},
|
| 527 |
{
|
| 528 |
-
"epoch":
|
| 529 |
-
"grad_norm": 2.
|
| 530 |
-
"learning_rate": 0.
|
| 531 |
-
"loss": 0.
|
| 532 |
"step": 670
|
| 533 |
},
|
| 534 |
{
|
| 535 |
-
"epoch":
|
| 536 |
-
"grad_norm":
|
| 537 |
-
"learning_rate": 0.
|
| 538 |
-
"loss": 0.
|
| 539 |
"step": 680
|
| 540 |
},
|
| 541 |
{
|
| 542 |
-
"epoch":
|
| 543 |
-
"grad_norm":
|
| 544 |
-
"learning_rate": 0.
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 690
|
| 547 |
},
|
| 548 |
{
|
| 549 |
-
"epoch":
|
| 550 |
-
"grad_norm":
|
| 551 |
-
"learning_rate": 0.
|
| 552 |
-
"loss": 0.
|
| 553 |
"step": 700
|
| 554 |
},
|
| 555 |
{
|
| 556 |
-
"epoch":
|
| 557 |
-
"eval_accuracy": 0.
|
| 558 |
-
"eval_loss": 0.
|
| 559 |
-
"eval_runtime": 2.
|
| 560 |
-
"eval_samples_per_second":
|
| 561 |
-
"eval_steps_per_second":
|
| 562 |
"step": 700
|
| 563 |
},
|
| 564 |
{
|
| 565 |
-
"epoch":
|
| 566 |
-
"grad_norm":
|
| 567 |
-
"learning_rate": 0.
|
| 568 |
-
"loss": 0.
|
| 569 |
"step": 710
|
| 570 |
},
|
| 571 |
{
|
| 572 |
-
"epoch":
|
| 573 |
-
"grad_norm": 0.
|
| 574 |
-
"learning_rate": 0.
|
| 575 |
-
"loss": 0.
|
| 576 |
"step": 720
|
| 577 |
},
|
| 578 |
{
|
| 579 |
-
"epoch":
|
| 580 |
-
"grad_norm": 4.
|
| 581 |
-
"learning_rate": 0.
|
| 582 |
-
"loss": 0.
|
| 583 |
"step": 730
|
| 584 |
},
|
| 585 |
{
|
| 586 |
-
"epoch":
|
| 587 |
-
"grad_norm":
|
| 588 |
-
"learning_rate": 0.
|
| 589 |
-
"loss": 0.
|
| 590 |
"step": 740
|
| 591 |
},
|
| 592 |
{
|
| 593 |
-
"epoch":
|
| 594 |
-
"grad_norm":
|
| 595 |
-
"learning_rate": 0.
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 750
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch":
|
| 601 |
-
"grad_norm":
|
| 602 |
-
"learning_rate": 0.
|
| 603 |
-
"loss": 0.
|
| 604 |
"step": 760
|
| 605 |
},
|
| 606 |
{
|
| 607 |
-
"epoch":
|
| 608 |
-
"grad_norm":
|
| 609 |
-
"learning_rate": 0.
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 770
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch":
|
| 615 |
-
"grad_norm":
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 780
|
| 619 |
},
|
| 620 |
{
|
| 621 |
-
"epoch":
|
| 622 |
-
"grad_norm":
|
| 623 |
-
"learning_rate":
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 790
|
| 626 |
},
|
| 627 |
{
|
| 628 |
-
"epoch":
|
| 629 |
-
"grad_norm":
|
| 630 |
-
"learning_rate":
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 800
|
| 633 |
},
|
| 634 |
{
|
| 635 |
-
"epoch":
|
| 636 |
-
"eval_accuracy": 0.
|
| 637 |
-
"eval_loss": 0.
|
| 638 |
-
"eval_runtime": 2.
|
| 639 |
-
"eval_samples_per_second":
|
| 640 |
-
"eval_steps_per_second": 12.
|
| 641 |
"step": 800
|
| 642 |
},
|
| 643 |
{
|
| 644 |
-
"epoch":
|
| 645 |
-
"grad_norm": 0.
|
| 646 |
-
"learning_rate":
|
| 647 |
-
"loss": 0.
|
| 648 |
"step": 810
|
| 649 |
},
|
| 650 |
{
|
| 651 |
-
"epoch":
|
| 652 |
-
"grad_norm": 0.
|
| 653 |
-
"learning_rate":
|
| 654 |
-
"loss": 0.
|
| 655 |
"step": 820
|
| 656 |
},
|
| 657 |
{
|
| 658 |
-
"epoch":
|
| 659 |
-
"grad_norm": 0.
|
| 660 |
-
"learning_rate":
|
| 661 |
-
"loss": 0.
|
| 662 |
"step": 830
|
| 663 |
},
|
| 664 |
{
|
| 665 |
-
"epoch":
|
| 666 |
-
"grad_norm": 0.
|
| 667 |
-
"learning_rate":
|
| 668 |
-
"loss": 0.
|
| 669 |
"step": 840
|
| 670 |
},
|
| 671 |
{
|
| 672 |
-
"epoch":
|
| 673 |
-
"grad_norm":
|
| 674 |
-
"learning_rate":
|
| 675 |
-
"loss": 0.
|
| 676 |
"step": 850
|
| 677 |
},
|
| 678 |
{
|
| 679 |
-
"epoch":
|
| 680 |
-
"grad_norm":
|
| 681 |
-
"learning_rate":
|
| 682 |
-
"loss": 0.
|
| 683 |
"step": 860
|
| 684 |
},
|
| 685 |
{
|
| 686 |
-
"epoch":
|
| 687 |
-
"grad_norm":
|
| 688 |
-
"learning_rate":
|
| 689 |
-
"loss": 0.
|
| 690 |
"step": 870
|
| 691 |
},
|
| 692 |
{
|
| 693 |
-
"epoch":
|
| 694 |
-
"grad_norm":
|
| 695 |
-
"learning_rate":
|
| 696 |
-
"loss": 0.
|
| 697 |
"step": 880
|
| 698 |
},
|
| 699 |
{
|
| 700 |
-
"epoch":
|
| 701 |
-
"grad_norm":
|
| 702 |
-
"learning_rate":
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 890
|
| 705 |
},
|
| 706 |
{
|
| 707 |
-
"epoch":
|
| 708 |
-
"grad_norm":
|
| 709 |
-
"learning_rate":
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 900
|
| 712 |
},
|
| 713 |
{
|
| 714 |
-
"epoch":
|
| 715 |
-
"eval_accuracy": 0.
|
| 716 |
-
"eval_loss": 1.
|
| 717 |
-
"eval_runtime":
|
| 718 |
-
"eval_samples_per_second":
|
| 719 |
-
"eval_steps_per_second":
|
| 720 |
"step": 900
|
| 721 |
},
|
| 722 |
{
|
| 723 |
-
"epoch":
|
| 724 |
-
"grad_norm":
|
| 725 |
-
"learning_rate":
|
| 726 |
-
"loss": 0.
|
| 727 |
"step": 910
|
| 728 |
},
|
| 729 |
{
|
| 730 |
-
"epoch":
|
| 731 |
-
"grad_norm": 0.
|
| 732 |
-
"learning_rate":
|
| 733 |
-
"loss": 0.
|
| 734 |
"step": 920
|
| 735 |
},
|
| 736 |
{
|
| 737 |
-
"epoch":
|
| 738 |
-
"grad_norm":
|
| 739 |
-
"learning_rate":
|
| 740 |
-
"loss": 0.
|
| 741 |
"step": 930
|
| 742 |
},
|
| 743 |
{
|
| 744 |
-
"epoch":
|
| 745 |
-
"grad_norm":
|
| 746 |
-
"learning_rate":
|
| 747 |
-
"loss": 0.
|
| 748 |
"step": 940
|
| 749 |
},
|
| 750 |
{
|
| 751 |
-
"epoch":
|
| 752 |
-
"grad_norm": 0.
|
| 753 |
-
"learning_rate":
|
| 754 |
-
"loss": 0.
|
| 755 |
"step": 950
|
| 756 |
},
|
| 757 |
{
|
| 758 |
-
"epoch":
|
| 759 |
-
"grad_norm": 0.
|
| 760 |
-
"learning_rate":
|
| 761 |
-
"loss": 0.
|
| 762 |
"step": 960
|
| 763 |
},
|
| 764 |
{
|
| 765 |
-
"epoch":
|
| 766 |
-
"grad_norm":
|
| 767 |
-
"learning_rate":
|
| 768 |
-
"loss": 0.
|
| 769 |
"step": 970
|
| 770 |
},
|
| 771 |
{
|
| 772 |
-
"epoch":
|
| 773 |
-
"grad_norm":
|
| 774 |
-
"learning_rate":
|
| 775 |
-
"loss": 0.
|
| 776 |
"step": 980
|
| 777 |
},
|
| 778 |
{
|
| 779 |
-
"epoch":
|
| 780 |
-
"grad_norm":
|
| 781 |
-
"learning_rate":
|
| 782 |
-
"loss": 0.
|
| 783 |
"step": 990
|
| 784 |
},
|
| 785 |
{
|
| 786 |
-
"epoch":
|
| 787 |
-
"grad_norm":
|
| 788 |
-
"learning_rate":
|
| 789 |
-
"loss": 0.
|
| 790 |
"step": 1000
|
| 791 |
},
|
| 792 |
{
|
| 793 |
-
"epoch":
|
| 794 |
-
"eval_accuracy": 0.
|
| 795 |
-
"eval_loss":
|
| 796 |
-
"eval_runtime":
|
| 797 |
-
"eval_samples_per_second":
|
| 798 |
-
"eval_steps_per_second":
|
| 799 |
"step": 1000
|
| 800 |
},
|
| 801 |
{
|
| 802 |
-
"epoch":
|
| 803 |
-
"grad_norm": 0.
|
| 804 |
-
"learning_rate":
|
| 805 |
-
"loss": 0.
|
| 806 |
"step": 1010
|
| 807 |
},
|
| 808 |
{
|
| 809 |
-
"epoch":
|
| 810 |
-
"grad_norm":
|
| 811 |
-
"learning_rate":
|
| 812 |
-
"loss": 0.
|
| 813 |
"step": 1020
|
| 814 |
},
|
| 815 |
{
|
| 816 |
-
"epoch":
|
| 817 |
-
"grad_norm": 0.
|
| 818 |
-
"learning_rate":
|
| 819 |
-
"loss": 0.
|
| 820 |
"step": 1030
|
| 821 |
},
|
| 822 |
{
|
| 823 |
-
"epoch":
|
| 824 |
-
"grad_norm":
|
| 825 |
-
"learning_rate":
|
| 826 |
-
"loss": 0.
|
| 827 |
"step": 1040
|
| 828 |
},
|
| 829 |
{
|
| 830 |
-
"epoch":
|
| 831 |
-
"grad_norm":
|
| 832 |
-
"learning_rate":
|
| 833 |
-
"loss": 0.
|
| 834 |
"step": 1050
|
| 835 |
},
|
| 836 |
{
|
| 837 |
-
"epoch":
|
| 838 |
-
"grad_norm": 0.
|
| 839 |
-
"learning_rate":
|
| 840 |
-
"loss": 0.
|
| 841 |
"step": 1060
|
| 842 |
},
|
| 843 |
{
|
| 844 |
-
"epoch":
|
| 845 |
-
"grad_norm":
|
| 846 |
-
"learning_rate":
|
| 847 |
-
"loss": 0.
|
| 848 |
"step": 1070
|
| 849 |
},
|
| 850 |
{
|
| 851 |
-
"epoch":
|
| 852 |
-
"grad_norm":
|
| 853 |
-
"learning_rate":
|
| 854 |
-
"loss": 0.
|
| 855 |
"step": 1080
|
| 856 |
},
|
| 857 |
{
|
| 858 |
-
"epoch":
|
| 859 |
-
"grad_norm": 0.
|
| 860 |
-
"learning_rate":
|
| 861 |
-
"loss": 0.
|
| 862 |
"step": 1090
|
| 863 |
},
|
| 864 |
{
|
| 865 |
-
"epoch":
|
| 866 |
-
"grad_norm": 0.
|
| 867 |
-
"learning_rate":
|
| 868 |
-
"loss": 0.
|
| 869 |
"step": 1100
|
| 870 |
},
|
| 871 |
{
|
| 872 |
-
"epoch":
|
| 873 |
-
"eval_accuracy": 0.
|
| 874 |
-
"eval_loss":
|
| 875 |
-
"eval_runtime": 2.
|
| 876 |
-
"eval_samples_per_second":
|
| 877 |
-
"eval_steps_per_second": 12.
|
| 878 |
"step": 1100
|
| 879 |
},
|
| 880 |
{
|
| 881 |
-
"epoch":
|
| 882 |
-
"grad_norm": 0.
|
| 883 |
-
"learning_rate":
|
| 884 |
-
"loss": 0.
|
| 885 |
"step": 1110
|
| 886 |
},
|
| 887 |
{
|
| 888 |
-
"epoch":
|
| 889 |
-
"grad_norm":
|
| 890 |
-
"learning_rate":
|
| 891 |
-
"loss": 0.
|
| 892 |
"step": 1120
|
| 893 |
},
|
| 894 |
{
|
| 895 |
-
"epoch":
|
| 896 |
-
"grad_norm": 0.
|
| 897 |
-
"learning_rate":
|
| 898 |
-
"loss": 0.
|
| 899 |
"step": 1130
|
| 900 |
},
|
| 901 |
{
|
| 902 |
-
"epoch":
|
| 903 |
-
"grad_norm": 0.
|
| 904 |
-
"learning_rate":
|
| 905 |
-
"loss": 0.
|
| 906 |
"step": 1140
|
| 907 |
},
|
| 908 |
{
|
| 909 |
-
"epoch":
|
| 910 |
-
"grad_norm": 0.
|
| 911 |
-
"learning_rate":
|
| 912 |
-
"loss": 0.
|
| 913 |
"step": 1150
|
| 914 |
},
|
| 915 |
{
|
| 916 |
-
"epoch":
|
| 917 |
-
"grad_norm": 0.
|
| 918 |
-
"learning_rate":
|
| 919 |
-
"loss": 0.
|
| 920 |
"step": 1160
|
| 921 |
},
|
| 922 |
{
|
| 923 |
-
"epoch":
|
| 924 |
-
"grad_norm": 0.
|
| 925 |
-
"learning_rate":
|
| 926 |
-
"loss": 0.
|
| 927 |
"step": 1170
|
| 928 |
},
|
| 929 |
{
|
| 930 |
-
"epoch":
|
| 931 |
-
"grad_norm": 0.
|
| 932 |
-
"learning_rate":
|
| 933 |
-
"loss": 0.
|
| 934 |
"step": 1180
|
| 935 |
},
|
| 936 |
{
|
| 937 |
-
"epoch":
|
| 938 |
-
"grad_norm": 0.
|
| 939 |
-
"learning_rate":
|
| 940 |
-
"loss": 0.
|
| 941 |
"step": 1190
|
| 942 |
},
|
| 943 |
{
|
| 944 |
-
"epoch":
|
| 945 |
-
"grad_norm":
|
| 946 |
-
"learning_rate":
|
| 947 |
-
"loss": 0.
|
| 948 |
"step": 1200
|
| 949 |
},
|
| 950 |
{
|
| 951 |
-
"epoch":
|
| 952 |
-
"eval_accuracy": 0.
|
| 953 |
-
"eval_loss":
|
| 954 |
-
"eval_runtime": 2.
|
| 955 |
-
"eval_samples_per_second":
|
| 956 |
-
"eval_steps_per_second": 12.
|
| 957 |
"step": 1200
|
| 958 |
},
|
| 959 |
{
|
| 960 |
-
"epoch":
|
| 961 |
-
"grad_norm": 0.
|
| 962 |
-
"learning_rate":
|
| 963 |
-
"loss": 0.
|
| 964 |
"step": 1210
|
| 965 |
},
|
| 966 |
{
|
| 967 |
-
"epoch":
|
| 968 |
-
"grad_norm":
|
| 969 |
-
"learning_rate":
|
| 970 |
-
"loss": 0.
|
| 971 |
"step": 1220
|
| 972 |
},
|
| 973 |
{
|
| 974 |
-
"epoch":
|
| 975 |
-
"grad_norm": 0.
|
| 976 |
-
"learning_rate":
|
| 977 |
-
"loss": 0.
|
| 978 |
"step": 1230
|
| 979 |
},
|
| 980 |
{
|
| 981 |
-
"epoch":
|
| 982 |
-
"grad_norm": 0.
|
| 983 |
-
"learning_rate":
|
| 984 |
-
"loss": 0.
|
| 985 |
"step": 1240
|
| 986 |
},
|
| 987 |
{
|
| 988 |
-
"epoch":
|
| 989 |
-
"grad_norm": 0.
|
| 990 |
-
"learning_rate":
|
| 991 |
-
"loss": 0.
|
| 992 |
"step": 1250
|
| 993 |
},
|
| 994 |
{
|
| 995 |
-
"epoch":
|
| 996 |
-
"grad_norm": 0.
|
| 997 |
-
"learning_rate":
|
| 998 |
-
"loss": 0.
|
| 999 |
"step": 1260
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
-
"epoch":
|
| 1003 |
-
"grad_norm": 0.
|
| 1004 |
-
"learning_rate":
|
| 1005 |
-
"loss": 0.
|
| 1006 |
"step": 1270
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
-
"epoch":
|
| 1010 |
-
"grad_norm": 0.
|
| 1011 |
-
"learning_rate":
|
| 1012 |
-
"loss": 0.
|
| 1013 |
"step": 1280
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
-
"epoch":
|
| 1017 |
-
"grad_norm": 0.
|
| 1018 |
-
"learning_rate":
|
| 1019 |
-
"loss": 0.
|
| 1020 |
"step": 1290
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
-
"epoch":
|
| 1024 |
-
"grad_norm": 0.
|
| 1025 |
-
"learning_rate":
|
| 1026 |
-
"loss": 0.
|
| 1027 |
"step": 1300
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
-
"epoch":
|
| 1031 |
-
"eval_accuracy": 0.
|
| 1032 |
-
"eval_loss": 1.
|
| 1033 |
-
"eval_runtime": 2.
|
| 1034 |
-
"eval_samples_per_second":
|
| 1035 |
-
"eval_steps_per_second":
|
| 1036 |
"step": 1300
|
| 1037 |
},
|
| 1038 |
{
|
| 1039 |
-
"epoch":
|
| 1040 |
-
"grad_norm": 0.
|
| 1041 |
-
"learning_rate":
|
| 1042 |
-
"loss": 0.
|
| 1043 |
"step": 1310
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
-
"epoch":
|
| 1047 |
-
"grad_norm":
|
| 1048 |
-
"learning_rate":
|
| 1049 |
-
"loss": 0.
|
| 1050 |
"step": 1320
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
-
"epoch":
|
| 1054 |
-
"grad_norm": 0.
|
| 1055 |
-
"learning_rate":
|
| 1056 |
-
"loss": 0.
|
| 1057 |
"step": 1330
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
-
"epoch":
|
| 1061 |
-
"grad_norm": 0.
|
| 1062 |
-
"learning_rate":
|
| 1063 |
-
"loss": 0.
|
| 1064 |
"step": 1340
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
-
"epoch":
|
| 1068 |
-
"grad_norm": 0.
|
| 1069 |
-
"learning_rate":
|
| 1070 |
-
"loss": 0.
|
| 1071 |
"step": 1350
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
-
"epoch":
|
| 1075 |
-
"grad_norm": 0.
|
| 1076 |
-
"learning_rate":
|
| 1077 |
-
"loss": 0.
|
| 1078 |
"step": 1360
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
-
"epoch":
|
| 1082 |
-
"grad_norm": 0.
|
| 1083 |
-
"learning_rate":
|
| 1084 |
-
"loss": 0.
|
| 1085 |
"step": 1370
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
-
"epoch":
|
| 1089 |
-
"grad_norm": 0.
|
| 1090 |
-
"learning_rate":
|
| 1091 |
-
"loss": 0.
|
| 1092 |
"step": 1380
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
-
"epoch":
|
| 1096 |
-
"grad_norm": 0.
|
| 1097 |
-
"learning_rate":
|
| 1098 |
-
"loss": 0.
|
| 1099 |
"step": 1390
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
-
"epoch":
|
| 1103 |
-
"grad_norm": 0.
|
| 1104 |
-
"learning_rate":
|
| 1105 |
-
"loss": 0.
|
| 1106 |
"step": 1400
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
-
"epoch":
|
| 1110 |
-
"eval_accuracy": 0.
|
| 1111 |
-
"eval_loss":
|
| 1112 |
-
"eval_runtime": 2.
|
| 1113 |
-
"eval_samples_per_second":
|
| 1114 |
-
"eval_steps_per_second": 12.
|
| 1115 |
"step": 1400
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
-
"epoch":
|
| 1119 |
-
"grad_norm": 0.
|
| 1120 |
-
"learning_rate":
|
| 1121 |
-
"loss": 0.
|
| 1122 |
"step": 1410
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
-
"epoch":
|
| 1126 |
-
"grad_norm": 0.
|
| 1127 |
-
"learning_rate":
|
| 1128 |
-
"loss": 0.
|
| 1129 |
"step": 1420
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
-
"epoch":
|
| 1133 |
-
"grad_norm": 0.
|
| 1134 |
-
"learning_rate":
|
| 1135 |
-
"loss": 0.
|
| 1136 |
"step": 1430
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
-
"epoch":
|
| 1140 |
-
"grad_norm": 0.
|
| 1141 |
-
"learning_rate":
|
| 1142 |
-
"loss": 0.
|
| 1143 |
"step": 1440
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
-
"epoch":
|
| 1147 |
-
"grad_norm": 0.
|
| 1148 |
-
"learning_rate":
|
| 1149 |
-
"loss": 0.
|
| 1150 |
"step": 1450
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
-
"epoch":
|
| 1154 |
-
"grad_norm": 0.
|
| 1155 |
-
"learning_rate":
|
| 1156 |
-
"loss": 0.
|
| 1157 |
"step": 1460
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
-
"epoch":
|
| 1161 |
-
"grad_norm": 0.
|
| 1162 |
-
"learning_rate":
|
| 1163 |
-
"loss": 0.
|
| 1164 |
"step": 1470
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
-
"epoch":
|
| 1168 |
-
"grad_norm": 0.
|
| 1169 |
-
"learning_rate":
|
| 1170 |
-
"loss": 0.
|
| 1171 |
"step": 1480
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
-
"epoch":
|
| 1175 |
-
"grad_norm": 0.
|
| 1176 |
-
"learning_rate":
|
| 1177 |
-
"loss": 0.
|
| 1178 |
"step": 1490
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
-
"epoch":
|
| 1182 |
-
"grad_norm": 0.
|
| 1183 |
-
"learning_rate":
|
| 1184 |
-
"loss": 0.
|
| 1185 |
"step": 1500
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
-
"epoch":
|
| 1189 |
-
"eval_accuracy": 0.
|
| 1190 |
-
"eval_loss": 1.
|
| 1191 |
-
"eval_runtime":
|
| 1192 |
-
"eval_samples_per_second":
|
| 1193 |
-
"eval_steps_per_second":
|
| 1194 |
"step": 1500
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
-
"epoch":
|
| 1198 |
-
"grad_norm": 0.
|
| 1199 |
-
"learning_rate":
|
| 1200 |
-
"loss": 0.
|
| 1201 |
"step": 1510
|
| 1202 |
},
|
| 1203 |
{
|
| 1204 |
-
"epoch":
|
| 1205 |
-
"grad_norm": 0.
|
| 1206 |
-
"learning_rate":
|
| 1207 |
-
"loss": 0.
|
| 1208 |
"step": 1520
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
-
"epoch":
|
| 1212 |
-
"grad_norm": 0.
|
| 1213 |
-
"learning_rate":
|
| 1214 |
-
"loss": 0.
|
| 1215 |
"step": 1530
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
-
"epoch":
|
| 1219 |
-
"grad_norm": 0.
|
| 1220 |
-
"learning_rate":
|
| 1221 |
-
"loss": 0.
|
| 1222 |
"step": 1540
|
| 1223 |
},
|
| 1224 |
-
{
|
| 1225 |
-
"epoch": 9.810126582278482,
|
| 1226 |
-
"grad_norm": 0.013694948516786098,
|
| 1227 |
-
"learning_rate": 4.907497565725414e-05,
|
| 1228 |
-
"loss": 0.0061,
|
| 1229 |
-
"step": 1550
|
| 1230 |
-
},
|
| 1231 |
-
{
|
| 1232 |
-
"epoch": 9.873417721518987,
|
| 1233 |
-
"grad_norm": 0.013068972155451775,
|
| 1234 |
-
"learning_rate": 4.810126582278481e-05,
|
| 1235 |
-
"loss": 0.0028,
|
| 1236 |
-
"step": 1560
|
| 1237 |
-
},
|
| 1238 |
-
{
|
| 1239 |
-
"epoch": 9.936708860759493,
|
| 1240 |
-
"grad_norm": 0.013739065267145634,
|
| 1241 |
-
"learning_rate": 4.7127555988315484e-05,
|
| 1242 |
-
"loss": 0.0027,
|
| 1243 |
-
"step": 1570
|
| 1244 |
-
},
|
| 1245 |
-
{
|
| 1246 |
-
"epoch": 10.0,
|
| 1247 |
-
"grad_norm": 0.014148131012916565,
|
| 1248 |
-
"learning_rate": 4.615384615384616e-05,
|
| 1249 |
-
"loss": 0.0027,
|
| 1250 |
-
"step": 1580
|
| 1251 |
-
},
|
| 1252 |
-
{
|
| 1253 |
-
"epoch": 10.063291139240507,
|
| 1254 |
-
"grad_norm": 0.014314244501292706,
|
| 1255 |
-
"learning_rate": 4.5180136319376825e-05,
|
| 1256 |
-
"loss": 0.0026,
|
| 1257 |
-
"step": 1590
|
| 1258 |
-
},
|
| 1259 |
-
{
|
| 1260 |
-
"epoch": 10.126582278481013,
|
| 1261 |
-
"grad_norm": 0.012181580066680908,
|
| 1262 |
-
"learning_rate": 4.42064264849075e-05,
|
| 1263 |
-
"loss": 0.0026,
|
| 1264 |
-
"step": 1600
|
| 1265 |
-
},
|
| 1266 |
-
{
|
| 1267 |
-
"epoch": 10.126582278481013,
|
| 1268 |
-
"eval_accuracy": 0.8220640569395018,
|
| 1269 |
-
"eval_loss": 1.00938880443573,
|
| 1270 |
-
"eval_runtime": 3.7407,
|
| 1271 |
-
"eval_samples_per_second": 75.12,
|
| 1272 |
-
"eval_steps_per_second": 9.624,
|
| 1273 |
-
"step": 1600
|
| 1274 |
-
},
|
| 1275 |
-
{
|
| 1276 |
-
"epoch": 10.189873417721518,
|
| 1277 |
-
"grad_norm": 0.014514009468257427,
|
| 1278 |
-
"learning_rate": 4.323271665043817e-05,
|
| 1279 |
-
"loss": 0.0025,
|
| 1280 |
-
"step": 1610
|
| 1281 |
-
},
|
| 1282 |
-
{
|
| 1283 |
-
"epoch": 10.253164556962025,
|
| 1284 |
-
"grad_norm": 0.013074631802737713,
|
| 1285 |
-
"learning_rate": 4.225900681596884e-05,
|
| 1286 |
-
"loss": 0.0026,
|
| 1287 |
-
"step": 1620
|
| 1288 |
-
},
|
| 1289 |
-
{
|
| 1290 |
-
"epoch": 10.316455696202532,
|
| 1291 |
-
"grad_norm": 0.012750120833516121,
|
| 1292 |
-
"learning_rate": 4.1285296981499514e-05,
|
| 1293 |
-
"loss": 0.0026,
|
| 1294 |
-
"step": 1630
|
| 1295 |
-
},
|
| 1296 |
-
{
|
| 1297 |
-
"epoch": 10.379746835443038,
|
| 1298 |
-
"grad_norm": 0.011241636238992214,
|
| 1299 |
-
"learning_rate": 4.031158714703019e-05,
|
| 1300 |
-
"loss": 0.0023,
|
| 1301 |
-
"step": 1640
|
| 1302 |
-
},
|
| 1303 |
-
{
|
| 1304 |
-
"epoch": 10.443037974683545,
|
| 1305 |
-
"grad_norm": 0.011269092559814453,
|
| 1306 |
-
"learning_rate": 3.933787731256086e-05,
|
| 1307 |
-
"loss": 0.0023,
|
| 1308 |
-
"step": 1650
|
| 1309 |
-
},
|
| 1310 |
-
{
|
| 1311 |
-
"epoch": 10.50632911392405,
|
| 1312 |
-
"grad_norm": 0.011306311935186386,
|
| 1313 |
-
"learning_rate": 3.836416747809153e-05,
|
| 1314 |
-
"loss": 0.0026,
|
| 1315 |
-
"step": 1660
|
| 1316 |
-
},
|
| 1317 |
-
{
|
| 1318 |
-
"epoch": 10.569620253164556,
|
| 1319 |
-
"grad_norm": 0.012098881416022778,
|
| 1320 |
-
"learning_rate": 3.73904576436222e-05,
|
| 1321 |
-
"loss": 0.0025,
|
| 1322 |
-
"step": 1670
|
| 1323 |
-
},
|
| 1324 |
-
{
|
| 1325 |
-
"epoch": 10.632911392405063,
|
| 1326 |
-
"grad_norm": 0.013847197405993938,
|
| 1327 |
-
"learning_rate": 3.641674780915288e-05,
|
| 1328 |
-
"loss": 0.0025,
|
| 1329 |
-
"step": 1680
|
| 1330 |
-
},
|
| 1331 |
-
{
|
| 1332 |
-
"epoch": 10.69620253164557,
|
| 1333 |
-
"grad_norm": 0.011289476417005062,
|
| 1334 |
-
"learning_rate": 3.5443037974683544e-05,
|
| 1335 |
-
"loss": 0.0024,
|
| 1336 |
-
"step": 1690
|
| 1337 |
-
},
|
| 1338 |
-
{
|
| 1339 |
-
"epoch": 10.759493670886076,
|
| 1340 |
-
"grad_norm": 0.012470747344195843,
|
| 1341 |
-
"learning_rate": 3.446932814021422e-05,
|
| 1342 |
-
"loss": 0.0024,
|
| 1343 |
-
"step": 1700
|
| 1344 |
-
},
|
| 1345 |
-
{
|
| 1346 |
-
"epoch": 10.759493670886076,
|
| 1347 |
-
"eval_accuracy": 0.8291814946619217,
|
| 1348 |
-
"eval_loss": 1.0214886665344238,
|
| 1349 |
-
"eval_runtime": 4.4027,
|
| 1350 |
-
"eval_samples_per_second": 63.824,
|
| 1351 |
-
"eval_steps_per_second": 8.177,
|
| 1352 |
-
"step": 1700
|
| 1353 |
-
},
|
| 1354 |
-
{
|
| 1355 |
-
"epoch": 10.822784810126583,
|
| 1356 |
-
"grad_norm": 0.011075363494455814,
|
| 1357 |
-
"learning_rate": 3.349561830574489e-05,
|
| 1358 |
-
"loss": 0.0023,
|
| 1359 |
-
"step": 1710
|
| 1360 |
-
},
|
| 1361 |
-
{
|
| 1362 |
-
"epoch": 10.886075949367088,
|
| 1363 |
-
"grad_norm": 0.0110908392816782,
|
| 1364 |
-
"learning_rate": 3.2521908471275565e-05,
|
| 1365 |
-
"loss": 0.0024,
|
| 1366 |
-
"step": 1720
|
| 1367 |
-
},
|
| 1368 |
-
{
|
| 1369 |
-
"epoch": 10.949367088607595,
|
| 1370 |
-
"grad_norm": 0.01047087088227272,
|
| 1371 |
-
"learning_rate": 3.154819863680623e-05,
|
| 1372 |
-
"loss": 0.0024,
|
| 1373 |
-
"step": 1730
|
| 1374 |
-
},
|
| 1375 |
-
{
|
| 1376 |
-
"epoch": 11.012658227848101,
|
| 1377 |
-
"grad_norm": 0.010718494653701782,
|
| 1378 |
-
"learning_rate": 3.0574488802336906e-05,
|
| 1379 |
-
"loss": 0.0021,
|
| 1380 |
-
"step": 1740
|
| 1381 |
-
},
|
| 1382 |
-
{
|
| 1383 |
-
"epoch": 11.075949367088608,
|
| 1384 |
-
"grad_norm": 0.011001325212419033,
|
| 1385 |
-
"learning_rate": 2.9600778967867577e-05,
|
| 1386 |
-
"loss": 0.0024,
|
| 1387 |
-
"step": 1750
|
| 1388 |
-
},
|
| 1389 |
-
{
|
| 1390 |
-
"epoch": 11.139240506329115,
|
| 1391 |
-
"grad_norm": 0.012532955966889858,
|
| 1392 |
-
"learning_rate": 2.8627069133398247e-05,
|
| 1393 |
-
"loss": 0.0024,
|
| 1394 |
-
"step": 1760
|
| 1395 |
-
},
|
| 1396 |
-
{
|
| 1397 |
-
"epoch": 11.20253164556962,
|
| 1398 |
-
"grad_norm": 0.011483966372907162,
|
| 1399 |
-
"learning_rate": 2.765335929892892e-05,
|
| 1400 |
-
"loss": 0.0022,
|
| 1401 |
-
"step": 1770
|
| 1402 |
-
},
|
| 1403 |
-
{
|
| 1404 |
-
"epoch": 11.265822784810126,
|
| 1405 |
-
"grad_norm": 0.01143474318087101,
|
| 1406 |
-
"learning_rate": 2.6679649464459595e-05,
|
| 1407 |
-
"loss": 0.0022,
|
| 1408 |
-
"step": 1780
|
| 1409 |
-
},
|
| 1410 |
-
{
|
| 1411 |
-
"epoch": 11.329113924050633,
|
| 1412 |
-
"grad_norm": 0.01154111884534359,
|
| 1413 |
-
"learning_rate": 2.5705939629990266e-05,
|
| 1414 |
-
"loss": 0.0023,
|
| 1415 |
-
"step": 1790
|
| 1416 |
-
},
|
| 1417 |
-
{
|
| 1418 |
-
"epoch": 11.39240506329114,
|
| 1419 |
-
"grad_norm": 0.011763243936002254,
|
| 1420 |
-
"learning_rate": 2.4732229795520936e-05,
|
| 1421 |
-
"loss": 0.0024,
|
| 1422 |
-
"step": 1800
|
| 1423 |
-
},
|
| 1424 |
-
{
|
| 1425 |
-
"epoch": 11.39240506329114,
|
| 1426 |
-
"eval_accuracy": 0.8291814946619217,
|
| 1427 |
-
"eval_loss": 1.0316418409347534,
|
| 1428 |
-
"eval_runtime": 4.1371,
|
| 1429 |
-
"eval_samples_per_second": 67.921,
|
| 1430 |
-
"eval_steps_per_second": 8.702,
|
| 1431 |
-
"step": 1800
|
| 1432 |
-
},
|
| 1433 |
-
{
|
| 1434 |
-
"epoch": 11.455696202531646,
|
| 1435 |
-
"grad_norm": 0.010971922427415848,
|
| 1436 |
-
"learning_rate": 2.375851996105161e-05,
|
| 1437 |
-
"loss": 0.0021,
|
| 1438 |
-
"step": 1810
|
| 1439 |
-
},
|
| 1440 |
-
{
|
| 1441 |
-
"epoch": 11.518987341772151,
|
| 1442 |
-
"grad_norm": 0.011685609817504883,
|
| 1443 |
-
"learning_rate": 2.278481012658228e-05,
|
| 1444 |
-
"loss": 0.0021,
|
| 1445 |
-
"step": 1820
|
| 1446 |
-
},
|
| 1447 |
-
{
|
| 1448 |
-
"epoch": 11.582278481012658,
|
| 1449 |
-
"grad_norm": 0.010025019757449627,
|
| 1450 |
-
"learning_rate": 2.181110029211295e-05,
|
| 1451 |
-
"loss": 0.0021,
|
| 1452 |
-
"step": 1830
|
| 1453 |
-
},
|
| 1454 |
-
{
|
| 1455 |
-
"epoch": 11.645569620253164,
|
| 1456 |
-
"grad_norm": 0.011038082651793957,
|
| 1457 |
-
"learning_rate": 2.0837390457643625e-05,
|
| 1458 |
-
"loss": 0.0022,
|
| 1459 |
-
"step": 1840
|
| 1460 |
-
},
|
| 1461 |
-
{
|
| 1462 |
-
"epoch": 11.708860759493671,
|
| 1463 |
-
"grad_norm": 0.011144652031362057,
|
| 1464 |
-
"learning_rate": 1.9863680623174295e-05,
|
| 1465 |
-
"loss": 0.0023,
|
| 1466 |
-
"step": 1850
|
| 1467 |
-
},
|
| 1468 |
-
{
|
| 1469 |
-
"epoch": 11.772151898734178,
|
| 1470 |
-
"grad_norm": 0.010572181083261967,
|
| 1471 |
-
"learning_rate": 1.8889970788704966e-05,
|
| 1472 |
-
"loss": 0.002,
|
| 1473 |
-
"step": 1860
|
| 1474 |
-
},
|
| 1475 |
-
{
|
| 1476 |
-
"epoch": 11.835443037974684,
|
| 1477 |
-
"grad_norm": 0.012614467181265354,
|
| 1478 |
-
"learning_rate": 1.791626095423564e-05,
|
| 1479 |
-
"loss": 0.0021,
|
| 1480 |
-
"step": 1870
|
| 1481 |
-
},
|
| 1482 |
-
{
|
| 1483 |
-
"epoch": 11.89873417721519,
|
| 1484 |
-
"grad_norm": 0.011049304157495499,
|
| 1485 |
-
"learning_rate": 1.694255111976631e-05,
|
| 1486 |
-
"loss": 0.002,
|
| 1487 |
-
"step": 1880
|
| 1488 |
-
},
|
| 1489 |
-
{
|
| 1490 |
-
"epoch": 11.962025316455696,
|
| 1491 |
-
"grad_norm": 0.011247304268181324,
|
| 1492 |
-
"learning_rate": 1.596884128529698e-05,
|
| 1493 |
-
"loss": 0.0021,
|
| 1494 |
-
"step": 1890
|
| 1495 |
-
},
|
| 1496 |
-
{
|
| 1497 |
-
"epoch": 12.025316455696203,
|
| 1498 |
-
"grad_norm": 0.009822424501180649,
|
| 1499 |
-
"learning_rate": 1.4995131450827655e-05,
|
| 1500 |
-
"loss": 0.002,
|
| 1501 |
-
"step": 1900
|
| 1502 |
-
},
|
| 1503 |
-
{
|
| 1504 |
-
"epoch": 12.025316455696203,
|
| 1505 |
-
"eval_accuracy": 0.8291814946619217,
|
| 1506 |
-
"eval_loss": 1.0391350984573364,
|
| 1507 |
-
"eval_runtime": 4.3594,
|
| 1508 |
-
"eval_samples_per_second": 64.458,
|
| 1509 |
-
"eval_steps_per_second": 8.258,
|
| 1510 |
-
"step": 1900
|
| 1511 |
-
},
|
| 1512 |
-
{
|
| 1513 |
-
"epoch": 12.08860759493671,
|
| 1514 |
-
"grad_norm": 0.009912836365401745,
|
| 1515 |
-
"learning_rate": 1.4021421616358327e-05,
|
| 1516 |
-
"loss": 0.0021,
|
| 1517 |
-
"step": 1910
|
| 1518 |
-
},
|
| 1519 |
-
{
|
| 1520 |
-
"epoch": 12.151898734177216,
|
| 1521 |
-
"grad_norm": 0.014617972075939178,
|
| 1522 |
-
"learning_rate": 1.3047711781888997e-05,
|
| 1523 |
-
"loss": 0.002,
|
| 1524 |
-
"step": 1920
|
| 1525 |
-
},
|
| 1526 |
-
{
|
| 1527 |
-
"epoch": 12.215189873417721,
|
| 1528 |
-
"grad_norm": 0.0097211804240942,
|
| 1529 |
-
"learning_rate": 1.207400194741967e-05,
|
| 1530 |
-
"loss": 0.0021,
|
| 1531 |
-
"step": 1930
|
| 1532 |
-
},
|
| 1533 |
-
{
|
| 1534 |
-
"epoch": 12.278481012658228,
|
| 1535 |
-
"grad_norm": 0.012906952761113644,
|
| 1536 |
-
"learning_rate": 1.1100292112950342e-05,
|
| 1537 |
-
"loss": 0.0023,
|
| 1538 |
-
"step": 1940
|
| 1539 |
-
},
|
| 1540 |
-
{
|
| 1541 |
-
"epoch": 12.341772151898734,
|
| 1542 |
-
"grad_norm": 0.010059771127998829,
|
| 1543 |
-
"learning_rate": 1.0126582278481012e-05,
|
| 1544 |
-
"loss": 0.002,
|
| 1545 |
-
"step": 1950
|
| 1546 |
-
},
|
| 1547 |
-
{
|
| 1548 |
-
"epoch": 12.405063291139241,
|
| 1549 |
-
"grad_norm": 0.010056668892502785,
|
| 1550 |
-
"learning_rate": 9.152872444011686e-06,
|
| 1551 |
-
"loss": 0.0022,
|
| 1552 |
-
"step": 1960
|
| 1553 |
-
},
|
| 1554 |
-
{
|
| 1555 |
-
"epoch": 12.468354430379748,
|
| 1556 |
-
"grad_norm": 0.012864183634519577,
|
| 1557 |
-
"learning_rate": 8.179162609542357e-06,
|
| 1558 |
-
"loss": 0.0021,
|
| 1559 |
-
"step": 1970
|
| 1560 |
-
},
|
| 1561 |
-
{
|
| 1562 |
-
"epoch": 12.531645569620252,
|
| 1563 |
-
"grad_norm": 0.011309951543807983,
|
| 1564 |
-
"learning_rate": 7.205452775073028e-06,
|
| 1565 |
-
"loss": 0.0021,
|
| 1566 |
-
"step": 1980
|
| 1567 |
-
},
|
| 1568 |
-
{
|
| 1569 |
-
"epoch": 12.594936708860759,
|
| 1570 |
-
"grad_norm": 0.009780649095773697,
|
| 1571 |
-
"learning_rate": 6.231742940603701e-06,
|
| 1572 |
-
"loss": 0.002,
|
| 1573 |
-
"step": 1990
|
| 1574 |
-
},
|
| 1575 |
-
{
|
| 1576 |
-
"epoch": 12.658227848101266,
|
| 1577 |
-
"grad_norm": 0.011779570952057838,
|
| 1578 |
-
"learning_rate": 5.258033106134372e-06,
|
| 1579 |
-
"loss": 0.0021,
|
| 1580 |
-
"step": 2000
|
| 1581 |
-
},
|
| 1582 |
-
{
|
| 1583 |
-
"epoch": 12.658227848101266,
|
| 1584 |
-
"eval_accuracy": 0.8291814946619217,
|
| 1585 |
-
"eval_loss": 1.0429939031600952,
|
| 1586 |
-
"eval_runtime": 2.9477,
|
| 1587 |
-
"eval_samples_per_second": 95.327,
|
| 1588 |
-
"eval_steps_per_second": 12.213,
|
| 1589 |
-
"step": 2000
|
| 1590 |
-
},
|
| 1591 |
-
{
|
| 1592 |
-
"epoch": 12.721518987341772,
|
| 1593 |
-
"grad_norm": 0.010478339157998562,
|
| 1594 |
-
"learning_rate": 4.284323271665044e-06,
|
| 1595 |
-
"loss": 0.0019,
|
| 1596 |
-
"step": 2010
|
| 1597 |
-
},
|
| 1598 |
-
{
|
| 1599 |
-
"epoch": 12.784810126582279,
|
| 1600 |
-
"grad_norm": 0.009612773545086384,
|
| 1601 |
-
"learning_rate": 3.3106134371957155e-06,
|
| 1602 |
-
"loss": 0.0021,
|
| 1603 |
-
"step": 2020
|
| 1604 |
-
},
|
| 1605 |
-
{
|
| 1606 |
-
"epoch": 12.848101265822784,
|
| 1607 |
-
"grad_norm": 0.010172748006880283,
|
| 1608 |
-
"learning_rate": 2.3369036027263877e-06,
|
| 1609 |
-
"loss": 0.0021,
|
| 1610 |
-
"step": 2030
|
| 1611 |
-
},
|
| 1612 |
-
{
|
| 1613 |
-
"epoch": 12.91139240506329,
|
| 1614 |
-
"grad_norm": 0.009747604839503765,
|
| 1615 |
-
"learning_rate": 1.3631937682570594e-06,
|
| 1616 |
-
"loss": 0.0019,
|
| 1617 |
-
"step": 2040
|
| 1618 |
-
},
|
| 1619 |
-
{
|
| 1620 |
-
"epoch": 12.974683544303797,
|
| 1621 |
-
"grad_norm": 0.010267944075167179,
|
| 1622 |
-
"learning_rate": 3.894839337877313e-07,
|
| 1623 |
-
"loss": 0.0021,
|
| 1624 |
-
"step": 2050
|
| 1625 |
-
},
|
| 1626 |
{
|
| 1627 |
"epoch": 13.0,
|
| 1628 |
-
"step":
|
| 1629 |
-
"total_flos":
|
| 1630 |
-
"train_loss": 0.
|
| 1631 |
-
"train_runtime":
|
| 1632 |
-
"train_samples_per_second":
|
| 1633 |
-
"train_steps_per_second": 1.
|
| 1634 |
}
|
| 1635 |
],
|
| 1636 |
"logging_steps": 10,
|
| 1637 |
-
"max_steps":
|
| 1638 |
"num_input_tokens_seen": 0,
|
| 1639 |
"num_train_epochs": 13,
|
| 1640 |
"save_steps": 100,
|
|
@@ -1650,7 +1248,7 @@
|
|
| 1650 |
"attributes": {}
|
| 1651 |
}
|
| 1652 |
},
|
| 1653 |
-
"total_flos":
|
| 1654 |
"train_batch_size": 16,
|
| 1655 |
"trial_name": null,
|
| 1656 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7452366948127747,
|
| 3 |
+
"best_model_checkpoint": "vit-weldclassifyv4/checkpoint-400",
|
| 4 |
"epoch": 13.0,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 1547,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.08403361344537816,
|
| 13 |
+
"grad_norm": 1.7778676748275757,
|
| 14 |
+
"learning_rate": 0.00019870717517776342,
|
| 15 |
+
"loss": 1.2807,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.16806722689075632,
|
| 20 |
+
"grad_norm": 1.3721851110458374,
|
| 21 |
+
"learning_rate": 0.00019741435035552685,
|
| 22 |
+
"loss": 1.187,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.25210084033613445,
|
| 27 |
+
"grad_norm": 0.4043492376804352,
|
| 28 |
+
"learning_rate": 0.00019612152553329023,
|
| 29 |
+
"loss": 1.2471,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.33613445378151263,
|
| 34 |
+
"grad_norm": 1.9244325160980225,
|
| 35 |
+
"learning_rate": 0.00019482870071105366,
|
| 36 |
+
"loss": 1.2329,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.42016806722689076,
|
| 41 |
+
"grad_norm": 0.6638385653495789,
|
| 42 |
+
"learning_rate": 0.00019353587588881707,
|
| 43 |
+
"loss": 1.1524,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.5042016806722689,
|
| 48 |
+
"grad_norm": 0.3663930594921112,
|
| 49 |
+
"learning_rate": 0.0001922430510665805,
|
| 50 |
+
"loss": 1.1548,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.5882352941176471,
|
| 55 |
+
"grad_norm": 0.6382243633270264,
|
| 56 |
+
"learning_rate": 0.0001909502262443439,
|
| 57 |
+
"loss": 1.1993,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.6722689075630253,
|
| 62 |
+
"grad_norm": 1.2848349809646606,
|
| 63 |
+
"learning_rate": 0.0001896574014221073,
|
| 64 |
+
"loss": 1.1822,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.7563025210084033,
|
| 69 |
+
"grad_norm": 1.2714462280273438,
|
| 70 |
+
"learning_rate": 0.00018836457659987072,
|
| 71 |
+
"loss": 1.1902,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.8403361344537815,
|
| 76 |
+
"grad_norm": 1.4769024848937988,
|
| 77 |
+
"learning_rate": 0.00018707175177763415,
|
| 78 |
+
"loss": 1.2099,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.8403361344537815,
|
| 83 |
+
"eval_accuracy": 0.5047169811320755,
|
| 84 |
+
"eval_loss": 1.1625308990478516,
|
| 85 |
+
"eval_runtime": 2.2575,
|
| 86 |
+
"eval_samples_per_second": 93.909,
|
| 87 |
+
"eval_steps_per_second": 11.96,
|
| 88 |
"step": 100
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"epoch": 0.9243697478991597,
|
| 92 |
+
"grad_norm": 1.2741708755493164,
|
| 93 |
+
"learning_rate": 0.00018577892695539755,
|
| 94 |
+
"loss": 1.2203,
|
| 95 |
"step": 110
|
| 96 |
},
|
| 97 |
{
|
| 98 |
+
"epoch": 1.0084033613445378,
|
| 99 |
+
"grad_norm": 1.2036206722259521,
|
| 100 |
+
"learning_rate": 0.000184486102133161,
|
| 101 |
+
"loss": 1.1936,
|
| 102 |
"step": 120
|
| 103 |
},
|
| 104 |
{
|
| 105 |
+
"epoch": 1.092436974789916,
|
| 106 |
+
"grad_norm": 1.2514188289642334,
|
| 107 |
+
"learning_rate": 0.00018319327731092437,
|
| 108 |
+
"loss": 1.1515,
|
| 109 |
"step": 130
|
| 110 |
},
|
| 111 |
{
|
| 112 |
+
"epoch": 1.1764705882352942,
|
| 113 |
+
"grad_norm": 0.7073956727981567,
|
| 114 |
+
"learning_rate": 0.0001819004524886878,
|
| 115 |
+
"loss": 1.1483,
|
| 116 |
"step": 140
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 1.2605042016806722,
|
| 120 |
+
"grad_norm": 0.7465972900390625,
|
| 121 |
+
"learning_rate": 0.0001806076276664512,
|
| 122 |
+
"loss": 1.1962,
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 1.3445378151260505,
|
| 127 |
+
"grad_norm": 0.6339373588562012,
|
| 128 |
+
"learning_rate": 0.00017931480284421464,
|
| 129 |
+
"loss": 1.1156,
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"epoch": 1.4285714285714286,
|
| 134 |
+
"grad_norm": 1.036371111869812,
|
| 135 |
+
"learning_rate": 0.00017802197802197802,
|
| 136 |
+
"loss": 1.1304,
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 1.5126050420168067,
|
| 141 |
+
"grad_norm": 1.3491630554199219,
|
| 142 |
+
"learning_rate": 0.00017672915319974145,
|
| 143 |
+
"loss": 1.1783,
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 1.596638655462185,
|
| 148 |
+
"grad_norm": 1.3167691230773926,
|
| 149 |
+
"learning_rate": 0.00017543632837750485,
|
| 150 |
+
"loss": 1.1617,
|
| 151 |
"step": 190
|
| 152 |
},
|
| 153 |
{
|
| 154 |
+
"epoch": 1.680672268907563,
|
| 155 |
+
"grad_norm": 1.0561383962631226,
|
| 156 |
+
"learning_rate": 0.00017414350355526826,
|
| 157 |
+
"loss": 1.1066,
|
| 158 |
"step": 200
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 1.680672268907563,
|
| 162 |
+
"eval_accuracy": 0.49528301886792453,
|
| 163 |
+
"eval_loss": 1.0892218351364136,
|
| 164 |
+
"eval_runtime": 2.1715,
|
| 165 |
+
"eval_samples_per_second": 97.628,
|
| 166 |
+
"eval_steps_per_second": 12.434,
|
| 167 |
"step": 200
|
| 168 |
},
|
| 169 |
{
|
| 170 |
+
"epoch": 1.7647058823529411,
|
| 171 |
+
"grad_norm": 1.2338758707046509,
|
| 172 |
+
"learning_rate": 0.0001728506787330317,
|
| 173 |
+
"loss": 1.0634,
|
| 174 |
"step": 210
|
| 175 |
},
|
| 176 |
{
|
| 177 |
+
"epoch": 1.8487394957983194,
|
| 178 |
+
"grad_norm": 1.416668176651001,
|
| 179 |
+
"learning_rate": 0.0001715578539107951,
|
| 180 |
+
"loss": 1.1408,
|
| 181 |
"step": 220
|
| 182 |
},
|
| 183 |
{
|
| 184 |
+
"epoch": 1.9327731092436975,
|
| 185 |
+
"grad_norm": 1.9194142818450928,
|
| 186 |
+
"learning_rate": 0.0001702650290885585,
|
| 187 |
+
"loss": 1.2019,
|
| 188 |
"step": 230
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 2.0168067226890756,
|
| 192 |
+
"grad_norm": 1.1238566637039185,
|
| 193 |
+
"learning_rate": 0.0001689722042663219,
|
| 194 |
+
"loss": 1.0287,
|
| 195 |
"step": 240
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 2.100840336134454,
|
| 199 |
+
"grad_norm": 3.9827613830566406,
|
| 200 |
+
"learning_rate": 0.00016767937944408534,
|
| 201 |
+
"loss": 0.9904,
|
| 202 |
"step": 250
|
| 203 |
},
|
| 204 |
{
|
| 205 |
+
"epoch": 2.184873949579832,
|
| 206 |
+
"grad_norm": 1.7081505060195923,
|
| 207 |
+
"learning_rate": 0.00016638655462184875,
|
| 208 |
+
"loss": 1.0905,
|
| 209 |
"step": 260
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 2.26890756302521,
|
| 213 |
+
"grad_norm": 2.686239719390869,
|
| 214 |
+
"learning_rate": 0.00016509372979961215,
|
| 215 |
+
"loss": 0.9177,
|
| 216 |
"step": 270
|
| 217 |
},
|
| 218 |
{
|
| 219 |
+
"epoch": 2.3529411764705883,
|
| 220 |
+
"grad_norm": 1.3638893365859985,
|
| 221 |
+
"learning_rate": 0.00016380090497737556,
|
| 222 |
+
"loss": 0.9348,
|
| 223 |
"step": 280
|
| 224 |
},
|
| 225 |
{
|
| 226 |
+
"epoch": 2.4369747899159666,
|
| 227 |
+
"grad_norm": 2.050823450088501,
|
| 228 |
+
"learning_rate": 0.000162508080155139,
|
| 229 |
+
"loss": 0.8364,
|
| 230 |
"step": 290
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 2.5210084033613445,
|
| 234 |
+
"grad_norm": 1.718785047531128,
|
| 235 |
+
"learning_rate": 0.0001612152553329024,
|
| 236 |
+
"loss": 1.0298,
|
| 237 |
"step": 300
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 2.5210084033613445,
|
| 241 |
+
"eval_accuracy": 0.589622641509434,
|
| 242 |
+
"eval_loss": 0.893924355506897,
|
| 243 |
+
"eval_runtime": 2.9715,
|
| 244 |
+
"eval_samples_per_second": 71.345,
|
| 245 |
+
"eval_steps_per_second": 9.086,
|
| 246 |
"step": 300
|
| 247 |
},
|
| 248 |
{
|
| 249 |
+
"epoch": 2.6050420168067228,
|
| 250 |
+
"grad_norm": 2.593571424484253,
|
| 251 |
+
"learning_rate": 0.00015992243051066583,
|
| 252 |
+
"loss": 0.9351,
|
| 253 |
"step": 310
|
| 254 |
},
|
| 255 |
{
|
| 256 |
+
"epoch": 2.689075630252101,
|
| 257 |
+
"grad_norm": 1.2314530611038208,
|
| 258 |
+
"learning_rate": 0.0001586296056884292,
|
| 259 |
+
"loss": 0.841,
|
| 260 |
"step": 320
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 2.773109243697479,
|
| 264 |
+
"grad_norm": 2.589643716812134,
|
| 265 |
+
"learning_rate": 0.00015733678086619264,
|
| 266 |
+
"loss": 0.7806,
|
| 267 |
"step": 330
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 2.857142857142857,
|
| 271 |
+
"grad_norm": 1.8523632287979126,
|
| 272 |
+
"learning_rate": 0.00015604395604395605,
|
| 273 |
+
"loss": 0.8915,
|
| 274 |
"step": 340
|
| 275 |
},
|
| 276 |
{
|
| 277 |
+
"epoch": 2.9411764705882355,
|
| 278 |
+
"grad_norm": 2.1867382526397705,
|
| 279 |
+
"learning_rate": 0.00015475113122171948,
|
| 280 |
+
"loss": 0.8422,
|
| 281 |
"step": 350
|
| 282 |
},
|
| 283 |
{
|
| 284 |
+
"epoch": 3.0252100840336134,
|
| 285 |
+
"grad_norm": 2.2038803100585938,
|
| 286 |
+
"learning_rate": 0.0001534583063994829,
|
| 287 |
+
"loss": 0.7271,
|
| 288 |
"step": 360
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 3.1092436974789917,
|
| 292 |
+
"grad_norm": 2.8037712574005127,
|
| 293 |
+
"learning_rate": 0.0001521654815772463,
|
| 294 |
+
"loss": 0.6003,
|
| 295 |
"step": 370
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 3.19327731092437,
|
| 299 |
+
"grad_norm": 1.8391917943954468,
|
| 300 |
+
"learning_rate": 0.0001508726567550097,
|
| 301 |
+
"loss": 0.6642,
|
| 302 |
"step": 380
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 3.277310924369748,
|
| 306 |
+
"grad_norm": 4.166950225830078,
|
| 307 |
+
"learning_rate": 0.00014957983193277313,
|
| 308 |
+
"loss": 0.6483,
|
| 309 |
"step": 390
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 3.361344537815126,
|
| 313 |
+
"grad_norm": 2.6970036029815674,
|
| 314 |
+
"learning_rate": 0.00014828700711053654,
|
| 315 |
+
"loss": 0.5798,
|
| 316 |
"step": 400
|
| 317 |
},
|
| 318 |
{
|
| 319 |
+
"epoch": 3.361344537815126,
|
| 320 |
+
"eval_accuracy": 0.6745283018867925,
|
| 321 |
+
"eval_loss": 0.7452366948127747,
|
| 322 |
+
"eval_runtime": 2.3359,
|
| 323 |
+
"eval_samples_per_second": 90.759,
|
| 324 |
+
"eval_steps_per_second": 11.559,
|
| 325 |
"step": 400
|
| 326 |
},
|
| 327 |
{
|
| 328 |
+
"epoch": 3.4453781512605044,
|
| 329 |
+
"grad_norm": 2.7985074520111084,
|
| 330 |
+
"learning_rate": 0.00014699418228829994,
|
| 331 |
+
"loss": 0.5447,
|
| 332 |
"step": 410
|
| 333 |
},
|
| 334 |
{
|
| 335 |
+
"epoch": 3.5294117647058822,
|
| 336 |
+
"grad_norm": 5.049683094024658,
|
| 337 |
+
"learning_rate": 0.00014570135746606335,
|
| 338 |
+
"loss": 0.6424,
|
| 339 |
"step": 420
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 3.6134453781512605,
|
| 343 |
+
"grad_norm": 2.288046360015869,
|
| 344 |
+
"learning_rate": 0.00014440853264382675,
|
| 345 |
+
"loss": 0.5786,
|
| 346 |
"step": 430
|
| 347 |
},
|
| 348 |
{
|
| 349 |
+
"epoch": 3.697478991596639,
|
| 350 |
+
"grad_norm": 2.6284878253936768,
|
| 351 |
+
"learning_rate": 0.0001431157078215902,
|
| 352 |
+
"loss": 0.4704,
|
| 353 |
"step": 440
|
| 354 |
},
|
| 355 |
{
|
| 356 |
+
"epoch": 3.7815126050420167,
|
| 357 |
+
"grad_norm": 3.1169135570526123,
|
| 358 |
+
"learning_rate": 0.0001418228829993536,
|
| 359 |
+
"loss": 0.5602,
|
| 360 |
"step": 450
|
| 361 |
},
|
| 362 |
{
|
| 363 |
+
"epoch": 3.865546218487395,
|
| 364 |
+
"grad_norm": 4.109696388244629,
|
| 365 |
+
"learning_rate": 0.000140530058177117,
|
| 366 |
+
"loss": 0.5028,
|
| 367 |
"step": 460
|
| 368 |
},
|
| 369 |
{
|
| 370 |
+
"epoch": 3.9495798319327733,
|
| 371 |
+
"grad_norm": 2.4809916019439697,
|
| 372 |
+
"learning_rate": 0.0001392372333548804,
|
| 373 |
+
"loss": 0.5331,
|
| 374 |
"step": 470
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 4.033613445378151,
|
| 378 |
+
"grad_norm": 5.215726375579834,
|
| 379 |
+
"learning_rate": 0.00013794440853264384,
|
| 380 |
+
"loss": 0.6104,
|
| 381 |
"step": 480
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 4.117647058823529,
|
| 385 |
+
"grad_norm": 2.3470144271850586,
|
| 386 |
+
"learning_rate": 0.00013665158371040724,
|
| 387 |
+
"loss": 0.3547,
|
| 388 |
"step": 490
|
| 389 |
},
|
| 390 |
{
|
| 391 |
+
"epoch": 4.201680672268908,
|
| 392 |
+
"grad_norm": 2.578737258911133,
|
| 393 |
+
"learning_rate": 0.00013535875888817068,
|
| 394 |
+
"loss": 0.4879,
|
| 395 |
"step": 500
|
| 396 |
},
|
| 397 |
{
|
| 398 |
+
"epoch": 4.201680672268908,
|
| 399 |
+
"eval_accuracy": 0.6556603773584906,
|
| 400 |
+
"eval_loss": 0.8673213720321655,
|
| 401 |
+
"eval_runtime": 2.9615,
|
| 402 |
+
"eval_samples_per_second": 71.585,
|
| 403 |
+
"eval_steps_per_second": 9.117,
|
| 404 |
"step": 500
|
| 405 |
},
|
| 406 |
{
|
| 407 |
+
"epoch": 4.285714285714286,
|
| 408 |
+
"grad_norm": 8.1809663772583,
|
| 409 |
+
"learning_rate": 0.00013406593406593405,
|
| 410 |
+
"loss": 0.3164,
|
| 411 |
"step": 510
|
| 412 |
},
|
| 413 |
{
|
| 414 |
+
"epoch": 4.369747899159664,
|
| 415 |
+
"grad_norm": 5.916128158569336,
|
| 416 |
+
"learning_rate": 0.0001327731092436975,
|
| 417 |
+
"loss": 0.3425,
|
| 418 |
"step": 520
|
| 419 |
},
|
| 420 |
{
|
| 421 |
+
"epoch": 4.453781512605042,
|
| 422 |
+
"grad_norm": 1.5418981313705444,
|
| 423 |
+
"learning_rate": 0.0001314802844214609,
|
| 424 |
+
"loss": 0.3219,
|
| 425 |
"step": 530
|
| 426 |
},
|
| 427 |
{
|
| 428 |
+
"epoch": 4.53781512605042,
|
| 429 |
+
"grad_norm": 0.39303484559059143,
|
| 430 |
+
"learning_rate": 0.00013018745959922433,
|
| 431 |
+
"loss": 0.372,
|
| 432 |
"step": 540
|
| 433 |
},
|
| 434 |
{
|
| 435 |
+
"epoch": 4.621848739495798,
|
| 436 |
+
"grad_norm": 2.0171704292297363,
|
| 437 |
+
"learning_rate": 0.00012889463477698773,
|
| 438 |
+
"loss": 0.3941,
|
| 439 |
"step": 550
|
| 440 |
},
|
| 441 |
{
|
| 442 |
+
"epoch": 4.705882352941177,
|
| 443 |
+
"grad_norm": 5.667063236236572,
|
| 444 |
+
"learning_rate": 0.00012760180995475114,
|
| 445 |
+
"loss": 0.3784,
|
| 446 |
"step": 560
|
| 447 |
},
|
| 448 |
{
|
| 449 |
+
"epoch": 4.7899159663865545,
|
| 450 |
+
"grad_norm": 2.0401604175567627,
|
| 451 |
+
"learning_rate": 0.00012630898513251454,
|
| 452 |
+
"loss": 0.3231,
|
| 453 |
"step": 570
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 4.873949579831933,
|
| 457 |
+
"grad_norm": 2.5163936614990234,
|
| 458 |
+
"learning_rate": 0.00012501616031027798,
|
| 459 |
+
"loss": 0.3287,
|
| 460 |
"step": 580
|
| 461 |
},
|
| 462 |
{
|
| 463 |
+
"epoch": 4.957983193277311,
|
| 464 |
+
"grad_norm": 2.357574939727783,
|
| 465 |
+
"learning_rate": 0.00012372333548804138,
|
| 466 |
+
"loss": 0.2309,
|
| 467 |
"step": 590
|
| 468 |
},
|
| 469 |
{
|
| 470 |
+
"epoch": 5.042016806722689,
|
| 471 |
+
"grad_norm": 2.399186611175537,
|
| 472 |
+
"learning_rate": 0.0001224305106658048,
|
| 473 |
+
"loss": 0.197,
|
| 474 |
"step": 600
|
| 475 |
},
|
| 476 |
{
|
| 477 |
+
"epoch": 5.042016806722689,
|
| 478 |
+
"eval_accuracy": 0.6556603773584906,
|
| 479 |
+
"eval_loss": 1.0144904851913452,
|
| 480 |
+
"eval_runtime": 2.2097,
|
| 481 |
+
"eval_samples_per_second": 95.94,
|
| 482 |
+
"eval_steps_per_second": 12.219,
|
| 483 |
"step": 600
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 5.126050420168067,
|
| 487 |
+
"grad_norm": 4.648927688598633,
|
| 488 |
+
"learning_rate": 0.00012113768584356819,
|
| 489 |
+
"loss": 0.2243,
|
| 490 |
"step": 610
|
| 491 |
},
|
| 492 |
{
|
| 493 |
+
"epoch": 5.2100840336134455,
|
| 494 |
+
"grad_norm": 5.755702972412109,
|
| 495 |
+
"learning_rate": 0.00011984486102133161,
|
| 496 |
+
"loss": 0.1775,
|
| 497 |
"step": 620
|
| 498 |
},
|
| 499 |
{
|
| 500 |
+
"epoch": 5.294117647058823,
|
| 501 |
+
"grad_norm": 5.102352619171143,
|
| 502 |
+
"learning_rate": 0.00011855203619909503,
|
| 503 |
+
"loss": 0.1982,
|
| 504 |
"step": 630
|
| 505 |
},
|
| 506 |
{
|
| 507 |
+
"epoch": 5.378151260504202,
|
| 508 |
+
"grad_norm": 2.311920404434204,
|
| 509 |
+
"learning_rate": 0.00011725921137685845,
|
| 510 |
+
"loss": 0.2125,
|
| 511 |
"step": 640
|
| 512 |
},
|
| 513 |
{
|
| 514 |
+
"epoch": 5.46218487394958,
|
| 515 |
+
"grad_norm": 5.563356876373291,
|
| 516 |
+
"learning_rate": 0.00011596638655462187,
|
| 517 |
+
"loss": 0.2259,
|
| 518 |
"step": 650
|
| 519 |
},
|
| 520 |
{
|
| 521 |
+
"epoch": 5.546218487394958,
|
| 522 |
+
"grad_norm": 5.233443260192871,
|
| 523 |
+
"learning_rate": 0.00011467356173238526,
|
| 524 |
+
"loss": 0.263,
|
| 525 |
"step": 660
|
| 526 |
},
|
| 527 |
{
|
| 528 |
+
"epoch": 5.630252100840336,
|
| 529 |
+
"grad_norm": 2.19209361076355,
|
| 530 |
+
"learning_rate": 0.00011338073691014868,
|
| 531 |
+
"loss": 0.2627,
|
| 532 |
"step": 670
|
| 533 |
},
|
| 534 |
{
|
| 535 |
+
"epoch": 5.714285714285714,
|
| 536 |
+
"grad_norm": 5.696531772613525,
|
| 537 |
+
"learning_rate": 0.0001120879120879121,
|
| 538 |
+
"loss": 0.2588,
|
| 539 |
"step": 680
|
| 540 |
},
|
| 541 |
{
|
| 542 |
+
"epoch": 5.798319327731092,
|
| 543 |
+
"grad_norm": 4.516761302947998,
|
| 544 |
+
"learning_rate": 0.0001107950872656755,
|
| 545 |
+
"loss": 0.2148,
|
| 546 |
"step": 690
|
| 547 |
},
|
| 548 |
{
|
| 549 |
+
"epoch": 5.882352941176471,
|
| 550 |
+
"grad_norm": 0.21505996584892273,
|
| 551 |
+
"learning_rate": 0.00010950226244343893,
|
| 552 |
+
"loss": 0.1368,
|
| 553 |
"step": 700
|
| 554 |
},
|
| 555 |
{
|
| 556 |
+
"epoch": 5.882352941176471,
|
| 557 |
+
"eval_accuracy": 0.7311320754716981,
|
| 558 |
+
"eval_loss": 0.8305109739303589,
|
| 559 |
+
"eval_runtime": 2.2559,
|
| 560 |
+
"eval_samples_per_second": 93.974,
|
| 561 |
+
"eval_steps_per_second": 11.968,
|
| 562 |
"step": 700
|
| 563 |
},
|
| 564 |
{
|
| 565 |
+
"epoch": 5.966386554621849,
|
| 566 |
+
"grad_norm": 4.3951263427734375,
|
| 567 |
+
"learning_rate": 0.00010820943762120233,
|
| 568 |
+
"loss": 0.2699,
|
| 569 |
"step": 710
|
| 570 |
},
|
| 571 |
{
|
| 572 |
+
"epoch": 6.050420168067227,
|
| 573 |
+
"grad_norm": 0.8779445290565491,
|
| 574 |
+
"learning_rate": 0.00010691661279896574,
|
| 575 |
+
"loss": 0.1172,
|
| 576 |
"step": 720
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"epoch": 6.1344537815126055,
|
| 580 |
+
"grad_norm": 4.695611476898193,
|
| 581 |
+
"learning_rate": 0.00010562378797672916,
|
| 582 |
+
"loss": 0.13,
|
| 583 |
"step": 730
|
| 584 |
},
|
| 585 |
{
|
| 586 |
+
"epoch": 6.218487394957983,
|
| 587 |
+
"grad_norm": 7.564522743225098,
|
| 588 |
+
"learning_rate": 0.00010433096315449258,
|
| 589 |
+
"loss": 0.1392,
|
| 590 |
"step": 740
|
| 591 |
},
|
| 592 |
{
|
| 593 |
+
"epoch": 6.302521008403361,
|
| 594 |
+
"grad_norm": 0.17681638896465302,
|
| 595 |
+
"learning_rate": 0.00010303813833225597,
|
| 596 |
+
"loss": 0.0828,
|
| 597 |
"step": 750
|
| 598 |
},
|
| 599 |
{
|
| 600 |
+
"epoch": 6.38655462184874,
|
| 601 |
+
"grad_norm": 2.515813112258911,
|
| 602 |
+
"learning_rate": 0.00010174531351001939,
|
| 603 |
+
"loss": 0.1119,
|
| 604 |
"step": 760
|
| 605 |
},
|
| 606 |
{
|
| 607 |
+
"epoch": 6.470588235294118,
|
| 608 |
+
"grad_norm": 0.3115313649177551,
|
| 609 |
+
"learning_rate": 0.0001004524886877828,
|
| 610 |
+
"loss": 0.0667,
|
| 611 |
"step": 770
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 6.554621848739496,
|
| 615 |
+
"grad_norm": 0.9338003396987915,
|
| 616 |
+
"learning_rate": 9.915966386554623e-05,
|
| 617 |
+
"loss": 0.0779,
|
| 618 |
"step": 780
|
| 619 |
},
|
| 620 |
{
|
| 621 |
+
"epoch": 6.6386554621848735,
|
| 622 |
+
"grad_norm": 5.663729190826416,
|
| 623 |
+
"learning_rate": 9.786683904330963e-05,
|
| 624 |
+
"loss": 0.0949,
|
| 625 |
"step": 790
|
| 626 |
},
|
| 627 |
{
|
| 628 |
+
"epoch": 6.722689075630252,
|
| 629 |
+
"grad_norm": 1.159752368927002,
|
| 630 |
+
"learning_rate": 9.657401422107305e-05,
|
| 631 |
+
"loss": 0.0841,
|
| 632 |
"step": 800
|
| 633 |
},
|
| 634 |
{
|
| 635 |
+
"epoch": 6.722689075630252,
|
| 636 |
+
"eval_accuracy": 0.7735849056603774,
|
| 637 |
+
"eval_loss": 0.8974043130874634,
|
| 638 |
+
"eval_runtime": 2.2126,
|
| 639 |
+
"eval_samples_per_second": 95.816,
|
| 640 |
+
"eval_steps_per_second": 12.203,
|
| 641 |
"step": 800
|
| 642 |
},
|
| 643 |
{
|
| 644 |
+
"epoch": 6.80672268907563,
|
| 645 |
+
"grad_norm": 0.8134496808052063,
|
| 646 |
+
"learning_rate": 9.528118939883646e-05,
|
| 647 |
+
"loss": 0.1272,
|
| 648 |
"step": 810
|
| 649 |
},
|
| 650 |
{
|
| 651 |
+
"epoch": 6.890756302521009,
|
| 652 |
+
"grad_norm": 0.09464468061923981,
|
| 653 |
+
"learning_rate": 9.398836457659988e-05,
|
| 654 |
+
"loss": 0.1339,
|
| 655 |
"step": 820
|
| 656 |
},
|
| 657 |
{
|
| 658 |
+
"epoch": 6.974789915966387,
|
| 659 |
+
"grad_norm": 0.08403979986906052,
|
| 660 |
+
"learning_rate": 9.26955397543633e-05,
|
| 661 |
+
"loss": 0.0779,
|
| 662 |
"step": 830
|
| 663 |
},
|
| 664 |
{
|
| 665 |
+
"epoch": 7.0588235294117645,
|
| 666 |
+
"grad_norm": 0.11395015567541122,
|
| 667 |
+
"learning_rate": 9.14027149321267e-05,
|
| 668 |
+
"loss": 0.0495,
|
| 669 |
"step": 840
|
| 670 |
},
|
| 671 |
{
|
| 672 |
+
"epoch": 7.142857142857143,
|
| 673 |
+
"grad_norm": 5.00321102142334,
|
| 674 |
+
"learning_rate": 9.010989010989012e-05,
|
| 675 |
+
"loss": 0.2217,
|
| 676 |
"step": 850
|
| 677 |
},
|
| 678 |
{
|
| 679 |
+
"epoch": 7.226890756302521,
|
| 680 |
+
"grad_norm": 5.354154109954834,
|
| 681 |
+
"learning_rate": 8.881706528765353e-05,
|
| 682 |
+
"loss": 0.0713,
|
| 683 |
"step": 860
|
| 684 |
},
|
| 685 |
{
|
| 686 |
+
"epoch": 7.310924369747899,
|
| 687 |
+
"grad_norm": 0.07731425017118454,
|
| 688 |
+
"learning_rate": 8.752424046541694e-05,
|
| 689 |
+
"loss": 0.0482,
|
| 690 |
"step": 870
|
| 691 |
},
|
| 692 |
{
|
| 693 |
+
"epoch": 7.394957983193278,
|
| 694 |
+
"grad_norm": 1.70600163936615,
|
| 695 |
+
"learning_rate": 8.623141564318036e-05,
|
| 696 |
+
"loss": 0.0368,
|
| 697 |
"step": 880
|
| 698 |
},
|
| 699 |
{
|
| 700 |
+
"epoch": 7.4789915966386555,
|
| 701 |
+
"grad_norm": 0.09904234856367111,
|
| 702 |
+
"learning_rate": 8.493859082094377e-05,
|
| 703 |
+
"loss": 0.0389,
|
| 704 |
"step": 890
|
| 705 |
},
|
| 706 |
{
|
| 707 |
+
"epoch": 7.563025210084033,
|
| 708 |
+
"grad_norm": 5.335230350494385,
|
| 709 |
+
"learning_rate": 8.364576599870718e-05,
|
| 710 |
+
"loss": 0.0942,
|
| 711 |
"step": 900
|
| 712 |
},
|
| 713 |
{
|
| 714 |
+
"epoch": 7.563025210084033,
|
| 715 |
+
"eval_accuracy": 0.7216981132075472,
|
| 716 |
+
"eval_loss": 1.1261749267578125,
|
| 717 |
+
"eval_runtime": 2.2006,
|
| 718 |
+
"eval_samples_per_second": 96.335,
|
| 719 |
+
"eval_steps_per_second": 12.269,
|
| 720 |
"step": 900
|
| 721 |
},
|
| 722 |
{
|
| 723 |
+
"epoch": 7.647058823529412,
|
| 724 |
+
"grad_norm": 5.030584812164307,
|
| 725 |
+
"learning_rate": 8.23529411764706e-05,
|
| 726 |
+
"loss": 0.0278,
|
| 727 |
"step": 910
|
| 728 |
},
|
| 729 |
{
|
| 730 |
+
"epoch": 7.73109243697479,
|
| 731 |
+
"grad_norm": 0.12369989603757858,
|
| 732 |
+
"learning_rate": 8.1060116354234e-05,
|
| 733 |
+
"loss": 0.1137,
|
| 734 |
"step": 920
|
| 735 |
},
|
| 736 |
{
|
| 737 |
+
"epoch": 7.815126050420168,
|
| 738 |
+
"grad_norm": 7.5863189697265625,
|
| 739 |
+
"learning_rate": 7.976729153199742e-05,
|
| 740 |
+
"loss": 0.0904,
|
| 741 |
"step": 930
|
| 742 |
},
|
| 743 |
{
|
| 744 |
+
"epoch": 7.899159663865547,
|
| 745 |
+
"grad_norm": 0.2067825049161911,
|
| 746 |
+
"learning_rate": 7.847446670976083e-05,
|
| 747 |
+
"loss": 0.0397,
|
| 748 |
"step": 940
|
| 749 |
},
|
| 750 |
{
|
| 751 |
+
"epoch": 7.983193277310924,
|
| 752 |
+
"grad_norm": 0.056721098721027374,
|
| 753 |
+
"learning_rate": 7.718164188752424e-05,
|
| 754 |
+
"loss": 0.0679,
|
| 755 |
"step": 950
|
| 756 |
},
|
| 757 |
{
|
| 758 |
+
"epoch": 8.067226890756302,
|
| 759 |
+
"grad_norm": 0.05310463905334473,
|
| 760 |
+
"learning_rate": 7.588881706528765e-05,
|
| 761 |
+
"loss": 0.0329,
|
| 762 |
"step": 960
|
| 763 |
},
|
| 764 |
{
|
| 765 |
+
"epoch": 8.15126050420168,
|
| 766 |
+
"grad_norm": 7.898382663726807,
|
| 767 |
+
"learning_rate": 7.459599224305107e-05,
|
| 768 |
+
"loss": 0.0183,
|
| 769 |
"step": 970
|
| 770 |
},
|
| 771 |
{
|
| 772 |
+
"epoch": 8.235294117647058,
|
| 773 |
+
"grad_norm": 2.061277151107788,
|
| 774 |
+
"learning_rate": 7.330316742081448e-05,
|
| 775 |
+
"loss": 0.0311,
|
| 776 |
"step": 980
|
| 777 |
},
|
| 778 |
{
|
| 779 |
+
"epoch": 8.319327731092438,
|
| 780 |
+
"grad_norm": 0.06646686792373657,
|
| 781 |
+
"learning_rate": 7.20103425985779e-05,
|
| 782 |
+
"loss": 0.0334,
|
| 783 |
"step": 990
|
| 784 |
},
|
| 785 |
{
|
| 786 |
+
"epoch": 8.403361344537815,
|
| 787 |
+
"grad_norm": 0.07112545520067215,
|
| 788 |
+
"learning_rate": 7.071751777634131e-05,
|
| 789 |
+
"loss": 0.0296,
|
| 790 |
"step": 1000
|
| 791 |
},
|
| 792 |
{
|
| 793 |
+
"epoch": 8.403361344537815,
|
| 794 |
+
"eval_accuracy": 0.7122641509433962,
|
| 795 |
+
"eval_loss": 1.2889635562896729,
|
| 796 |
+
"eval_runtime": 2.2011,
|
| 797 |
+
"eval_samples_per_second": 96.314,
|
| 798 |
+
"eval_steps_per_second": 12.266,
|
| 799 |
"step": 1000
|
| 800 |
},
|
| 801 |
{
|
| 802 |
+
"epoch": 8.487394957983193,
|
| 803 |
+
"grad_norm": 0.07936228811740875,
|
| 804 |
+
"learning_rate": 6.942469295410472e-05,
|
| 805 |
+
"loss": 0.0256,
|
| 806 |
"step": 1010
|
| 807 |
},
|
| 808 |
{
|
| 809 |
+
"epoch": 8.571428571428571,
|
| 810 |
+
"grad_norm": 5.849864959716797,
|
| 811 |
+
"learning_rate": 6.813186813186814e-05,
|
| 812 |
+
"loss": 0.0346,
|
| 813 |
"step": 1020
|
| 814 |
},
|
| 815 |
{
|
| 816 |
+
"epoch": 8.655462184873949,
|
| 817 |
+
"grad_norm": 0.05158023163676262,
|
| 818 |
+
"learning_rate": 6.683904330963154e-05,
|
| 819 |
+
"loss": 0.0109,
|
| 820 |
"step": 1030
|
| 821 |
},
|
| 822 |
{
|
| 823 |
+
"epoch": 8.739495798319329,
|
| 824 |
+
"grad_norm": 0.05596969276666641,
|
| 825 |
+
"learning_rate": 6.554621848739496e-05,
|
| 826 |
+
"loss": 0.0129,
|
| 827 |
"step": 1040
|
| 828 |
},
|
| 829 |
{
|
| 830 |
+
"epoch": 8.823529411764707,
|
| 831 |
+
"grad_norm": 0.05292417109012604,
|
| 832 |
+
"learning_rate": 6.425339366515838e-05,
|
| 833 |
+
"loss": 0.033,
|
| 834 |
"step": 1050
|
| 835 |
},
|
| 836 |
{
|
| 837 |
+
"epoch": 8.907563025210084,
|
| 838 |
+
"grad_norm": 0.8892333507537842,
|
| 839 |
+
"learning_rate": 6.296056884292179e-05,
|
| 840 |
+
"loss": 0.0199,
|
| 841 |
"step": 1060
|
| 842 |
},
|
| 843 |
{
|
| 844 |
+
"epoch": 8.991596638655462,
|
| 845 |
+
"grad_norm": 1.8524911403656006,
|
| 846 |
+
"learning_rate": 6.166774402068521e-05,
|
| 847 |
+
"loss": 0.0324,
|
| 848 |
"step": 1070
|
| 849 |
},
|
| 850 |
{
|
| 851 |
+
"epoch": 9.07563025210084,
|
| 852 |
+
"grad_norm": 0.040928326547145844,
|
| 853 |
+
"learning_rate": 6.037491919844861e-05,
|
| 854 |
+
"loss": 0.0352,
|
| 855 |
"step": 1080
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 9.159663865546218,
|
| 859 |
+
"grad_norm": 0.043698906898498535,
|
| 860 |
+
"learning_rate": 5.9082094376212026e-05,
|
| 861 |
+
"loss": 0.009,
|
| 862 |
"step": 1090
|
| 863 |
},
|
| 864 |
{
|
| 865 |
+
"epoch": 9.243697478991596,
|
| 866 |
+
"grad_norm": 0.04034803435206413,
|
| 867 |
+
"learning_rate": 5.778926955397543e-05,
|
| 868 |
+
"loss": 0.0432,
|
| 869 |
"step": 1100
|
| 870 |
},
|
| 871 |
{
|
| 872 |
+
"epoch": 9.243697478991596,
|
| 873 |
+
"eval_accuracy": 0.7405660377358491,
|
| 874 |
+
"eval_loss": 1.2427575588226318,
|
| 875 |
+
"eval_runtime": 2.1879,
|
| 876 |
+
"eval_samples_per_second": 96.895,
|
| 877 |
+
"eval_steps_per_second": 12.34,
|
| 878 |
"step": 1100
|
| 879 |
},
|
| 880 |
{
|
| 881 |
+
"epoch": 9.327731092436975,
|
| 882 |
+
"grad_norm": 0.042758312076330185,
|
| 883 |
+
"learning_rate": 5.649644473173885e-05,
|
| 884 |
+
"loss": 0.0086,
|
| 885 |
"step": 1110
|
| 886 |
},
|
| 887 |
{
|
| 888 |
+
"epoch": 9.411764705882353,
|
| 889 |
+
"grad_norm": 0.05348571389913559,
|
| 890 |
+
"learning_rate": 5.520361990950227e-05,
|
| 891 |
+
"loss": 0.0113,
|
| 892 |
"step": 1120
|
| 893 |
},
|
| 894 |
{
|
| 895 |
+
"epoch": 9.495798319327731,
|
| 896 |
+
"grad_norm": 0.04173032566905022,
|
| 897 |
+
"learning_rate": 5.3910795087265676e-05,
|
| 898 |
+
"loss": 0.0083,
|
| 899 |
"step": 1130
|
| 900 |
},
|
| 901 |
{
|
| 902 |
+
"epoch": 9.579831932773109,
|
| 903 |
+
"grad_norm": 0.03784575313329697,
|
| 904 |
+
"learning_rate": 5.2617970265029096e-05,
|
| 905 |
+
"loss": 0.0086,
|
| 906 |
"step": 1140
|
| 907 |
},
|
| 908 |
{
|
| 909 |
+
"epoch": 9.663865546218487,
|
| 910 |
+
"grad_norm": 0.05332985520362854,
|
| 911 |
+
"learning_rate": 5.13251454427925e-05,
|
| 912 |
+
"loss": 0.0086,
|
| 913 |
"step": 1150
|
| 914 |
},
|
| 915 |
{
|
| 916 |
+
"epoch": 9.747899159663866,
|
| 917 |
+
"grad_norm": 0.03503885120153427,
|
| 918 |
+
"learning_rate": 5.0032320620555914e-05,
|
| 919 |
+
"loss": 0.0078,
|
| 920 |
"step": 1160
|
| 921 |
},
|
| 922 |
{
|
| 923 |
+
"epoch": 9.831932773109244,
|
| 924 |
+
"grad_norm": 0.033440928906202316,
|
| 925 |
+
"learning_rate": 4.8739495798319326e-05,
|
| 926 |
+
"loss": 0.0095,
|
| 927 |
"step": 1170
|
| 928 |
},
|
| 929 |
{
|
| 930 |
+
"epoch": 9.915966386554622,
|
| 931 |
+
"grad_norm": 0.03903155028820038,
|
| 932 |
+
"learning_rate": 4.744667097608274e-05,
|
| 933 |
+
"loss": 0.0071,
|
| 934 |
"step": 1180
|
| 935 |
},
|
| 936 |
{
|
| 937 |
+
"epoch": 10.0,
|
| 938 |
+
"grad_norm": 0.034581057727336884,
|
| 939 |
+
"learning_rate": 4.615384615384616e-05,
|
| 940 |
+
"loss": 0.0347,
|
| 941 |
"step": 1190
|
| 942 |
},
|
| 943 |
{
|
| 944 |
+
"epoch": 10.084033613445378,
|
| 945 |
+
"grad_norm": 4.804828643798828,
|
| 946 |
+
"learning_rate": 4.486102133160957e-05,
|
| 947 |
+
"loss": 0.0353,
|
| 948 |
"step": 1200
|
| 949 |
},
|
| 950 |
{
|
| 951 |
+
"epoch": 10.084033613445378,
|
| 952 |
+
"eval_accuracy": 0.7452830188679245,
|
| 953 |
+
"eval_loss": 1.250637173652649,
|
| 954 |
+
"eval_runtime": 2.1411,
|
| 955 |
+
"eval_samples_per_second": 99.016,
|
| 956 |
+
"eval_steps_per_second": 12.61,
|
| 957 |
"step": 1200
|
| 958 |
},
|
| 959 |
{
|
| 960 |
+
"epoch": 10.168067226890756,
|
| 961 |
+
"grad_norm": 0.03247935697436333,
|
| 962 |
+
"learning_rate": 4.356819650937298e-05,
|
| 963 |
+
"loss": 0.0071,
|
| 964 |
"step": 1210
|
| 965 |
},
|
| 966 |
{
|
| 967 |
+
"epoch": 10.252100840336134,
|
| 968 |
+
"grad_norm": 0.03735749423503876,
|
| 969 |
+
"learning_rate": 4.2275371687136396e-05,
|
| 970 |
+
"loss": 0.007,
|
| 971 |
"step": 1220
|
| 972 |
},
|
| 973 |
{
|
| 974 |
+
"epoch": 10.336134453781513,
|
| 975 |
+
"grad_norm": 0.03190077841281891,
|
| 976 |
+
"learning_rate": 4.098254686489981e-05,
|
| 977 |
+
"loss": 0.0068,
|
| 978 |
"step": 1230
|
| 979 |
},
|
| 980 |
{
|
| 981 |
+
"epoch": 10.420168067226891,
|
| 982 |
+
"grad_norm": 0.03304820880293846,
|
| 983 |
+
"learning_rate": 3.968972204266322e-05,
|
| 984 |
+
"loss": 0.0063,
|
| 985 |
"step": 1240
|
| 986 |
},
|
| 987 |
{
|
| 988 |
+
"epoch": 10.504201680672269,
|
| 989 |
+
"grad_norm": 0.038498662412166595,
|
| 990 |
+
"learning_rate": 3.839689722042663e-05,
|
| 991 |
+
"loss": 0.0069,
|
| 992 |
"step": 1250
|
| 993 |
},
|
| 994 |
{
|
| 995 |
+
"epoch": 10.588235294117647,
|
| 996 |
+
"grad_norm": 0.03530021384358406,
|
| 997 |
+
"learning_rate": 3.7104072398190046e-05,
|
| 998 |
+
"loss": 0.0067,
|
| 999 |
"step": 1260
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
+
"epoch": 10.672268907563025,
|
| 1003 |
+
"grad_norm": 0.041745755821466446,
|
| 1004 |
+
"learning_rate": 3.581124757595346e-05,
|
| 1005 |
+
"loss": 0.0063,
|
| 1006 |
"step": 1270
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
+
"epoch": 10.756302521008404,
|
| 1010 |
+
"grad_norm": 0.03443057835102081,
|
| 1011 |
+
"learning_rate": 3.451842275371687e-05,
|
| 1012 |
+
"loss": 0.0062,
|
| 1013 |
"step": 1280
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
+
"epoch": 10.840336134453782,
|
| 1017 |
+
"grad_norm": 0.029045993462204933,
|
| 1018 |
+
"learning_rate": 3.322559793148028e-05,
|
| 1019 |
+
"loss": 0.0063,
|
| 1020 |
"step": 1290
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
+
"epoch": 10.92436974789916,
|
| 1024 |
+
"grad_norm": 0.04033966362476349,
|
| 1025 |
+
"learning_rate": 3.1932773109243696e-05,
|
| 1026 |
+
"loss": 0.0065,
|
| 1027 |
"step": 1300
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
+
"epoch": 10.92436974789916,
|
| 1031 |
+
"eval_accuracy": 0.7783018867924528,
|
| 1032 |
+
"eval_loss": 1.1232017278671265,
|
| 1033 |
+
"eval_runtime": 2.9539,
|
| 1034 |
+
"eval_samples_per_second": 71.77,
|
| 1035 |
+
"eval_steps_per_second": 9.141,
|
| 1036 |
"step": 1300
|
| 1037 |
},
|
| 1038 |
{
|
| 1039 |
+
"epoch": 11.008403361344538,
|
| 1040 |
+
"grad_norm": 0.029126280918717384,
|
| 1041 |
+
"learning_rate": 3.0639948287007115e-05,
|
| 1042 |
+
"loss": 0.0063,
|
| 1043 |
"step": 1310
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
+
"epoch": 11.092436974789916,
|
| 1047 |
+
"grad_norm": 0.02833595871925354,
|
| 1048 |
+
"learning_rate": 2.9347123464770527e-05,
|
| 1049 |
+
"loss": 0.0063,
|
| 1050 |
"step": 1320
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
+
"epoch": 11.176470588235293,
|
| 1054 |
+
"grad_norm": 0.032052479684352875,
|
| 1055 |
+
"learning_rate": 2.805429864253394e-05,
|
| 1056 |
+
"loss": 0.0063,
|
| 1057 |
"step": 1330
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
+
"epoch": 11.260504201680673,
|
| 1061 |
+
"grad_norm": 0.030251996591687202,
|
| 1062 |
+
"learning_rate": 2.676147382029735e-05,
|
| 1063 |
+
"loss": 0.006,
|
| 1064 |
"step": 1340
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
+
"epoch": 11.344537815126051,
|
| 1068 |
+
"grad_norm": 0.030112557113170624,
|
| 1069 |
+
"learning_rate": 2.546864899806076e-05,
|
| 1070 |
+
"loss": 0.0059,
|
| 1071 |
"step": 1350
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
+
"epoch": 11.428571428571429,
|
| 1075 |
+
"grad_norm": 0.027209602296352386,
|
| 1076 |
+
"learning_rate": 2.4175824175824177e-05,
|
| 1077 |
+
"loss": 0.0059,
|
| 1078 |
"step": 1360
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
+
"epoch": 11.512605042016807,
|
| 1082 |
+
"grad_norm": 0.027164172381162643,
|
| 1083 |
+
"learning_rate": 2.288299935358759e-05,
|
| 1084 |
+
"loss": 0.0057,
|
| 1085 |
"step": 1370
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
+
"epoch": 11.596638655462185,
|
| 1089 |
+
"grad_norm": 0.02858646586537361,
|
| 1090 |
+
"learning_rate": 2.1590174531351002e-05,
|
| 1091 |
+
"loss": 0.0058,
|
| 1092 |
"step": 1380
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
+
"epoch": 11.680672268907562,
|
| 1096 |
+
"grad_norm": 0.02894781529903412,
|
| 1097 |
+
"learning_rate": 2.0297349709114415e-05,
|
| 1098 |
+
"loss": 0.0055,
|
| 1099 |
"step": 1390
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
+
"epoch": 11.764705882352942,
|
| 1103 |
+
"grad_norm": 0.025563258677721024,
|
| 1104 |
+
"learning_rate": 1.9004524886877827e-05,
|
| 1105 |
+
"loss": 0.0056,
|
| 1106 |
"step": 1400
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
+
"epoch": 11.764705882352942,
|
| 1110 |
+
"eval_accuracy": 0.7830188679245284,
|
| 1111 |
+
"eval_loss": 1.1348851919174194,
|
| 1112 |
+
"eval_runtime": 2.1553,
|
| 1113 |
+
"eval_samples_per_second": 98.362,
|
| 1114 |
+
"eval_steps_per_second": 12.527,
|
| 1115 |
"step": 1400
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
+
"epoch": 11.84873949579832,
|
| 1119 |
+
"grad_norm": 0.027119316160678864,
|
| 1120 |
+
"learning_rate": 1.7711700064641243e-05,
|
| 1121 |
+
"loss": 0.0056,
|
| 1122 |
"step": 1410
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
+
"epoch": 11.932773109243698,
|
| 1126 |
+
"grad_norm": 0.02663271874189377,
|
| 1127 |
+
"learning_rate": 1.6418875242404656e-05,
|
| 1128 |
+
"loss": 0.0055,
|
| 1129 |
"step": 1420
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
+
"epoch": 12.016806722689076,
|
| 1133 |
+
"grad_norm": 0.027364488691091537,
|
| 1134 |
+
"learning_rate": 1.5126050420168067e-05,
|
| 1135 |
+
"loss": 0.0054,
|
| 1136 |
"step": 1430
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
+
"epoch": 12.100840336134453,
|
| 1140 |
+
"grad_norm": 0.02702498808503151,
|
| 1141 |
+
"learning_rate": 1.3833225597931483e-05,
|
| 1142 |
+
"loss": 0.0057,
|
| 1143 |
"step": 1440
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
+
"epoch": 12.184873949579831,
|
| 1147 |
+
"grad_norm": 0.02570091001689434,
|
| 1148 |
+
"learning_rate": 1.2540400775694893e-05,
|
| 1149 |
+
"loss": 0.0054,
|
| 1150 |
"step": 1450
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
+
"epoch": 12.268907563025211,
|
| 1154 |
+
"grad_norm": 0.02761007659137249,
|
| 1155 |
+
"learning_rate": 1.1247575953458308e-05,
|
| 1156 |
+
"loss": 0.0055,
|
| 1157 |
"step": 1460
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
+
"epoch": 12.352941176470589,
|
| 1161 |
+
"grad_norm": 0.02617548778653145,
|
| 1162 |
+
"learning_rate": 9.95475113122172e-06,
|
| 1163 |
+
"loss": 0.0055,
|
| 1164 |
"step": 1470
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
+
"epoch": 12.436974789915967,
|
| 1168 |
+
"grad_norm": 0.02675885520875454,
|
| 1169 |
+
"learning_rate": 8.661926308985133e-06,
|
| 1170 |
+
"loss": 0.0056,
|
| 1171 |
"step": 1480
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
+
"epoch": 12.521008403361344,
|
| 1175 |
+
"grad_norm": 0.029071761295199394,
|
| 1176 |
+
"learning_rate": 7.369101486748546e-06,
|
| 1177 |
+
"loss": 0.0052,
|
| 1178 |
"step": 1490
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
+
"epoch": 12.605042016806722,
|
| 1182 |
+
"grad_norm": 0.02562028169631958,
|
| 1183 |
+
"learning_rate": 6.076276664511959e-06,
|
| 1184 |
+
"loss": 0.0054,
|
| 1185 |
"step": 1500
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
+
"epoch": 12.605042016806722,
|
| 1189 |
+
"eval_accuracy": 0.7830188679245284,
|
| 1190 |
+
"eval_loss": 1.1463406085968018,
|
| 1191 |
+
"eval_runtime": 2.157,
|
| 1192 |
+
"eval_samples_per_second": 98.284,
|
| 1193 |
+
"eval_steps_per_second": 12.517,
|
| 1194 |
"step": 1500
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
+
"epoch": 12.6890756302521,
|
| 1198 |
+
"grad_norm": 0.024869520217180252,
|
| 1199 |
+
"learning_rate": 4.783451842275372e-06,
|
| 1200 |
+
"loss": 0.0055,
|
| 1201 |
"step": 1510
|
| 1202 |
},
|
| 1203 |
{
|
| 1204 |
+
"epoch": 12.77310924369748,
|
| 1205 |
+
"grad_norm": 0.02748894691467285,
|
| 1206 |
+
"learning_rate": 3.490627020038785e-06,
|
| 1207 |
+
"loss": 0.0056,
|
| 1208 |
"step": 1520
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
+
"epoch": 12.857142857142858,
|
| 1212 |
+
"grad_norm": 0.026005534455180168,
|
| 1213 |
+
"learning_rate": 2.197802197802198e-06,
|
| 1214 |
+
"loss": 0.0056,
|
| 1215 |
"step": 1530
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
+
"epoch": 12.941176470588236,
|
| 1219 |
+
"grad_norm": 0.028039414435625076,
|
| 1220 |
+
"learning_rate": 9.04977375565611e-07,
|
| 1221 |
+
"loss": 0.0054,
|
| 1222 |
"step": 1540
|
| 1223 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1224 |
{
|
| 1225 |
"epoch": 13.0,
|
| 1226 |
+
"step": 1547,
|
| 1227 |
+
"total_flos": 1.9140864535683072e+18,
|
| 1228 |
+
"train_loss": 0.35688263059153663,
|
| 1229 |
+
"train_runtime": 955.328,
|
| 1230 |
+
"train_samples_per_second": 25.855,
|
| 1231 |
+
"train_steps_per_second": 1.619
|
| 1232 |
}
|
| 1233 |
],
|
| 1234 |
"logging_steps": 10,
|
| 1235 |
+
"max_steps": 1547,
|
| 1236 |
"num_input_tokens_seen": 0,
|
| 1237 |
"num_train_epochs": 13,
|
| 1238 |
"save_steps": 100,
|
|
|
|
| 1248 |
"attributes": {}
|
| 1249 |
}
|
| 1250 |
},
|
| 1251 |
+
"total_flos": 1.9140864535683072e+18,
|
| 1252 |
"train_batch_size": 16,
|
| 1253 |
"trial_name": null,
|
| 1254 |
"trial_params": null
|