🍻 cheers
Browse files- README.md +4 -3
- all_results.json +11 -11
- data/events.out.tfevents.1730620135.cf96de2eb818.233.1 +3 -0
- eval_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +1352 -720
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: 0.
|
| 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: 0.9244604316546763
|
| 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: 0.3162
|
| 38 |
+
- Accuracy: 0.9245
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 2.
|
| 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":
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.9244604316546763,
|
| 4 |
+
"eval_loss": 0.3162367641925812,
|
| 5 |
+
"eval_runtime": 2.9069,
|
| 6 |
+
"eval_samples_per_second": 95.635,
|
| 7 |
+
"eval_steps_per_second": 12.04,
|
| 8 |
+
"total_flos": 2.900189697360077e+18,
|
| 9 |
+
"train_loss": 0.14551133991808146,
|
| 10 |
+
"train_runtime": 927.2479,
|
| 11 |
+
"train_samples_per_second": 40.361,
|
| 12 |
+
"train_steps_per_second": 2.524
|
| 13 |
}
|
data/events.out.tfevents.1730620135.cf96de2eb818.233.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1fc0570e9865f3a2fd0a3427472d0e425fbe34f012b012daf49ebe5ecf21398
|
| 3 |
+
size 411
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 2.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.9244604316546763,
|
| 4 |
+
"eval_loss": 0.3162367641925812,
|
| 5 |
+
"eval_runtime": 2.9069,
|
| 6 |
+
"eval_samples_per_second": 95.635,
|
| 7 |
+
"eval_steps_per_second": 12.04
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 2.900189697360077e+18,
|
| 4 |
+
"train_loss": 0.14551133991808146,
|
| 5 |
+
"train_runtime": 927.2479,
|
| 6 |
+
"train_samples_per_second": 40.361,
|
| 7 |
+
"train_steps_per_second": 2.524
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1240 +1,1872 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "vit-weldclassifyv4/checkpoint-
|
| 4 |
-
"epoch":
|
| 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": 1.
|
| 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":
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate": 0.
|
| 57 |
-
"loss":
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss":
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss":
|
| 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":
|
| 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":
|
| 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":
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
-
"epoch": 1.
|
| 127 |
-
"grad_norm":
|
| 128 |
-
"learning_rate": 0.
|
| 129 |
-
"loss":
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
-
"epoch": 1.
|
| 134 |
-
"grad_norm":
|
| 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": 2.
|
| 165 |
-
"eval_samples_per_second":
|
| 166 |
-
"eval_steps_per_second": 12.
|
| 167 |
"step": 200
|
| 168 |
},
|
| 169 |
{
|
| 170 |
-
"epoch": 1.
|
| 171 |
-
"grad_norm":
|
| 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":
|
| 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": 2.
|
| 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":
|
| 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": 2.
|
| 279 |
-
"learning_rate": 0.
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 350
|
| 282 |
},
|
| 283 |
{
|
| 284 |
-
"epoch":
|
| 285 |
-
"grad_norm":
|
| 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":
|
| 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": 2.
|
| 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": 2.
|
| 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": 4.
|
| 365 |
-
"learning_rate": 0.
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 460
|
| 368 |
},
|
| 369 |
{
|
| 370 |
-
"epoch": 3.
|
| 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": 2.
|
| 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":
|
| 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":
|
| 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": 2.
|
| 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":
|
| 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":
|
| 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": 0.
|
| 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":
|
| 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": 0.
|
| 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": 0.
|
| 609 |
-
"learning_rate": 0.
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 770
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch":
|
| 615 |
-
"grad_norm": 0.
|
| 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":
|
| 639 |
-
"eval_samples_per_second":
|
| 640 |
-
"eval_steps_per_second":
|
| 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":
|
| 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": 5.
|
| 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": 0.
|
| 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": 0.
|
| 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":
|
| 717 |
-
"eval_runtime": 2.
|
| 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":
|
| 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": 0.
|
| 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": 0.
|
| 781 |
-
"learning_rate":
|
| 782 |
-
"loss": 0.
|
| 783 |
"step": 990
|
| 784 |
},
|
| 785 |
{
|
| 786 |
-
"epoch":
|
| 787 |
-
"grad_norm": 0.
|
| 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": 0.
|
| 832 |
-
"learning_rate":
|
| 833 |
-
"loss": 0.
|
| 834 |
"step": 1050
|
| 835 |
},
|
| 836 |
{
|
| 837 |
-
"epoch":
|
| 838 |
-
"grad_norm":
|
| 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":
|
| 876 |
-
"eval_samples_per_second":
|
| 877 |
-
"eval_steps_per_second":
|
| 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": 0.
|
| 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":
|
| 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":
|
| 957 |
"step": 1200
|
| 958 |
},
|
| 959 |
{
|
| 960 |
-
"epoch":
|
| 961 |
-
"grad_norm":
|
| 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":
|
| 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":
|
| 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":
|
| 1033 |
-
"eval_runtime":
|
| 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": 0.
|
| 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":
|
| 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": 7.
|
| 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":
|
| 1191 |
-
"eval_runtime": 2.
|
| 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":
|
| 1226 |
-
"
|
| 1227 |
-
"
|
| 1228 |
-
"
|
| 1229 |
-
"
|
| 1230 |
-
|
| 1231 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1232 |
}
|
| 1233 |
],
|
| 1234 |
"logging_steps": 10,
|
| 1235 |
-
"max_steps":
|
| 1236 |
"num_input_tokens_seen": 0,
|
| 1237 |
-
"num_train_epochs":
|
| 1238 |
"save_steps": 100,
|
| 1239 |
"stateful_callbacks": {
|
| 1240 |
"TrainerControl": {
|
|
@@ -1248,7 +1880,7 @@
|
|
| 1248 |
"attributes": {}
|
| 1249 |
}
|
| 1250 |
},
|
| 1251 |
-
"total_flos":
|
| 1252 |
"train_batch_size": 16,
|
| 1253 |
"trial_name": null,
|
| 1254 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.3162367641925812,
|
| 3 |
+
"best_model_checkpoint": "vit-weldclassifyv4/checkpoint-1000",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 2340,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.0641025641025641,
|
| 13 |
+
"grad_norm": 1.9132781028747559,
|
| 14 |
+
"learning_rate": 0.00019914529914529915,
|
| 15 |
+
"loss": 1.2054,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.1282051282051282,
|
| 20 |
+
"grad_norm": 1.633124589920044,
|
| 21 |
+
"learning_rate": 0.0001982905982905983,
|
| 22 |
+
"loss": 1.0748,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
+
"epoch": 0.19230769230769232,
|
| 27 |
+
"grad_norm": 2.4126267433166504,
|
| 28 |
+
"learning_rate": 0.00019743589743589744,
|
| 29 |
+
"loss": 1.0973,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.2564102564102564,
|
| 34 |
+
"grad_norm": 3.881457567214966,
|
| 35 |
+
"learning_rate": 0.00019658119658119659,
|
| 36 |
+
"loss": 1.0609,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.32051282051282054,
|
| 41 |
+
"grad_norm": 3.1995434761047363,
|
| 42 |
+
"learning_rate": 0.00019572649572649573,
|
| 43 |
+
"loss": 1.0024,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.38461538461538464,
|
| 48 |
+
"grad_norm": 2.410505533218384,
|
| 49 |
+
"learning_rate": 0.00019487179487179487,
|
| 50 |
+
"loss": 0.8658,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.44871794871794873,
|
| 55 |
+
"grad_norm": 2.05910325050354,
|
| 56 |
+
"learning_rate": 0.00019401709401709402,
|
| 57 |
+
"loss": 0.9616,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.5128205128205128,
|
| 62 |
+
"grad_norm": 4.032101154327393,
|
| 63 |
+
"learning_rate": 0.00019316239316239316,
|
| 64 |
+
"loss": 0.9391,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.5769230769230769,
|
| 69 |
+
"grad_norm": 2.779008150100708,
|
| 70 |
+
"learning_rate": 0.00019230769230769233,
|
| 71 |
+
"loss": 0.9206,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.6410256410256411,
|
| 76 |
+
"grad_norm": 2.771672010421753,
|
| 77 |
+
"learning_rate": 0.00019145299145299148,
|
| 78 |
+
"loss": 0.8146,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.6410256410256411,
|
| 83 |
+
"eval_accuracy": 0.6834532374100719,
|
| 84 |
+
"eval_loss": 0.7348725199699402,
|
| 85 |
+
"eval_runtime": 2.6163,
|
| 86 |
+
"eval_samples_per_second": 106.259,
|
| 87 |
+
"eval_steps_per_second": 13.378,
|
| 88 |
"step": 100
|
| 89 |
},
|
| 90 |
{
|
| 91 |
+
"epoch": 0.7051282051282052,
|
| 92 |
+
"grad_norm": 2.4781739711761475,
|
| 93 |
+
"learning_rate": 0.0001905982905982906,
|
| 94 |
+
"loss": 0.7542,
|
| 95 |
"step": 110
|
| 96 |
},
|
| 97 |
{
|
| 98 |
+
"epoch": 0.7692307692307693,
|
| 99 |
+
"grad_norm": 2.8731400966644287,
|
| 100 |
+
"learning_rate": 0.00018974358974358974,
|
| 101 |
+
"loss": 0.7726,
|
| 102 |
"step": 120
|
| 103 |
},
|
| 104 |
{
|
| 105 |
+
"epoch": 0.8333333333333334,
|
| 106 |
+
"grad_norm": 2.480015277862549,
|
| 107 |
+
"learning_rate": 0.00018888888888888888,
|
| 108 |
+
"loss": 0.6705,
|
| 109 |
"step": 130
|
| 110 |
},
|
| 111 |
{
|
| 112 |
+
"epoch": 0.8974358974358975,
|
| 113 |
+
"grad_norm": 3.7568867206573486,
|
| 114 |
+
"learning_rate": 0.00018803418803418803,
|
| 115 |
+
"loss": 0.6004,
|
| 116 |
"step": 140
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 0.9615384615384616,
|
| 120 |
+
"grad_norm": 2.720820903778076,
|
| 121 |
+
"learning_rate": 0.0001871794871794872,
|
| 122 |
+
"loss": 0.8144,
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 1.0256410256410255,
|
| 127 |
+
"grad_norm": 1.9295154809951782,
|
| 128 |
+
"learning_rate": 0.00018632478632478634,
|
| 129 |
+
"loss": 0.6479,
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
+
"epoch": 1.0897435897435896,
|
| 134 |
+
"grad_norm": 3.0400049686431885,
|
| 135 |
+
"learning_rate": 0.0001854700854700855,
|
| 136 |
+
"loss": 0.522,
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
+
"epoch": 1.1538461538461537,
|
| 141 |
+
"grad_norm": 3.7371773719787598,
|
| 142 |
+
"learning_rate": 0.00018461538461538463,
|
| 143 |
+
"loss": 0.5998,
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 1.217948717948718,
|
| 148 |
+
"grad_norm": 2.992065668106079,
|
| 149 |
+
"learning_rate": 0.00018376068376068375,
|
| 150 |
+
"loss": 0.6268,
|
| 151 |
"step": 190
|
| 152 |
},
|
| 153 |
{
|
| 154 |
+
"epoch": 1.282051282051282,
|
| 155 |
+
"grad_norm": 2.213074207305908,
|
| 156 |
+
"learning_rate": 0.00018290598290598292,
|
| 157 |
+
"loss": 0.6048,
|
| 158 |
"step": 200
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 1.282051282051282,
|
| 162 |
+
"eval_accuracy": 0.697841726618705,
|
| 163 |
+
"eval_loss": 0.6820898056030273,
|
| 164 |
+
"eval_runtime": 2.7768,
|
| 165 |
+
"eval_samples_per_second": 100.114,
|
| 166 |
+
"eval_steps_per_second": 12.604,
|
| 167 |
"step": 200
|
| 168 |
},
|
| 169 |
{
|
| 170 |
+
"epoch": 1.3461538461538463,
|
| 171 |
+
"grad_norm": 3.2302353382110596,
|
| 172 |
+
"learning_rate": 0.00018205128205128207,
|
| 173 |
+
"loss": 0.6054,
|
| 174 |
"step": 210
|
| 175 |
},
|
| 176 |
{
|
| 177 |
+
"epoch": 1.4102564102564101,
|
| 178 |
+
"grad_norm": 3.9419608116149902,
|
| 179 |
+
"learning_rate": 0.0001811965811965812,
|
| 180 |
+
"loss": 0.5863,
|
| 181 |
"step": 220
|
| 182 |
},
|
| 183 |
{
|
| 184 |
+
"epoch": 1.4743589743589745,
|
| 185 |
+
"grad_norm": 2.5351428985595703,
|
| 186 |
+
"learning_rate": 0.00018034188034188035,
|
| 187 |
+
"loss": 0.4328,
|
| 188 |
"step": 230
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 1.5384615384615383,
|
| 192 |
+
"grad_norm": 2.677548885345459,
|
| 193 |
+
"learning_rate": 0.0001794871794871795,
|
| 194 |
+
"loss": 0.4744,
|
| 195 |
"step": 240
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 1.6025641025641026,
|
| 199 |
+
"grad_norm": 2.3627212047576904,
|
| 200 |
+
"learning_rate": 0.00017863247863247864,
|
| 201 |
+
"loss": 0.3523,
|
| 202 |
"step": 250
|
| 203 |
},
|
| 204 |
{
|
| 205 |
+
"epoch": 1.6666666666666665,
|
| 206 |
+
"grad_norm": 6.175805568695068,
|
| 207 |
+
"learning_rate": 0.00017777777777777779,
|
| 208 |
+
"loss": 0.5934,
|
| 209 |
"step": 260
|
| 210 |
},
|
| 211 |
{
|
| 212 |
+
"epoch": 1.7307692307692308,
|
| 213 |
+
"grad_norm": 2.920872211456299,
|
| 214 |
+
"learning_rate": 0.00017692307692307693,
|
| 215 |
+
"loss": 0.5758,
|
| 216 |
"step": 270
|
| 217 |
},
|
| 218 |
{
|
| 219 |
+
"epoch": 1.7948717948717947,
|
| 220 |
+
"grad_norm": 2.1116819381713867,
|
| 221 |
+
"learning_rate": 0.00017606837606837607,
|
| 222 |
+
"loss": 0.5086,
|
| 223 |
"step": 280
|
| 224 |
},
|
| 225 |
{
|
| 226 |
+
"epoch": 1.858974358974359,
|
| 227 |
+
"grad_norm": 3.4553894996643066,
|
| 228 |
+
"learning_rate": 0.00017521367521367522,
|
| 229 |
+
"loss": 0.4474,
|
| 230 |
"step": 290
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 1.9230769230769231,
|
| 234 |
+
"grad_norm": 2.4064671993255615,
|
| 235 |
+
"learning_rate": 0.00017435897435897436,
|
| 236 |
+
"loss": 0.4796,
|
| 237 |
"step": 300
|
| 238 |
},
|
| 239 |
{
|
| 240 |
+
"epoch": 1.9230769230769231,
|
| 241 |
+
"eval_accuracy": 0.8129496402877698,
|
| 242 |
+
"eval_loss": 0.48327746987342834,
|
| 243 |
+
"eval_runtime": 2.565,
|
| 244 |
+
"eval_samples_per_second": 108.383,
|
| 245 |
+
"eval_steps_per_second": 13.645,
|
| 246 |
"step": 300
|
| 247 |
},
|
| 248 |
{
|
| 249 |
+
"epoch": 1.9871794871794872,
|
| 250 |
+
"grad_norm": 3.8495571613311768,
|
| 251 |
+
"learning_rate": 0.0001735042735042735,
|
| 252 |
+
"loss": 0.4925,
|
| 253 |
"step": 310
|
| 254 |
},
|
| 255 |
{
|
| 256 |
+
"epoch": 2.051282051282051,
|
| 257 |
+
"grad_norm": 2.036381244659424,
|
| 258 |
+
"learning_rate": 0.00017264957264957268,
|
| 259 |
+
"loss": 0.3936,
|
| 260 |
"step": 320
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 2.1153846153846154,
|
| 264 |
+
"grad_norm": 3.381953001022339,
|
| 265 |
+
"learning_rate": 0.0001717948717948718,
|
| 266 |
+
"loss": 0.3416,
|
| 267 |
"step": 330
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 2.1794871794871793,
|
| 271 |
+
"grad_norm": 5.715399265289307,
|
| 272 |
+
"learning_rate": 0.00017094017094017094,
|
| 273 |
+
"loss": 0.4081,
|
| 274 |
"step": 340
|
| 275 |
},
|
| 276 |
{
|
| 277 |
+
"epoch": 2.2435897435897436,
|
| 278 |
+
"grad_norm": 2.237466335296631,
|
| 279 |
+
"learning_rate": 0.00017008547008547008,
|
| 280 |
+
"loss": 0.3313,
|
| 281 |
"step": 350
|
| 282 |
},
|
| 283 |
{
|
| 284 |
+
"epoch": 2.3076923076923075,
|
| 285 |
+
"grad_norm": 5.658877372741699,
|
| 286 |
+
"learning_rate": 0.00016923076923076923,
|
| 287 |
+
"loss": 0.3926,
|
| 288 |
"step": 360
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 2.371794871794872,
|
| 292 |
+
"grad_norm": 3.633448362350464,
|
| 293 |
+
"learning_rate": 0.00016837606837606837,
|
| 294 |
+
"loss": 0.4664,
|
| 295 |
"step": 370
|
| 296 |
},
|
| 297 |
{
|
| 298 |
+
"epoch": 2.435897435897436,
|
| 299 |
+
"grad_norm": 4.460226058959961,
|
| 300 |
+
"learning_rate": 0.00016752136752136754,
|
| 301 |
+
"loss": 0.4206,
|
| 302 |
"step": 380
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 2.5,
|
| 306 |
+
"grad_norm": 1.1033204793930054,
|
| 307 |
+
"learning_rate": 0.0001666666666666667,
|
| 308 |
+
"loss": 0.2678,
|
| 309 |
"step": 390
|
| 310 |
},
|
| 311 |
{
|
| 312 |
+
"epoch": 2.564102564102564,
|
| 313 |
+
"grad_norm": 6.69362735748291,
|
| 314 |
+
"learning_rate": 0.00016581196581196583,
|
| 315 |
+
"loss": 0.4532,
|
| 316 |
"step": 400
|
| 317 |
},
|
| 318 |
{
|
| 319 |
+
"epoch": 2.564102564102564,
|
| 320 |
+
"eval_accuracy": 0.802158273381295,
|
| 321 |
+
"eval_loss": 0.5380275249481201,
|
| 322 |
+
"eval_runtime": 3.354,
|
| 323 |
+
"eval_samples_per_second": 82.885,
|
| 324 |
+
"eval_steps_per_second": 10.435,
|
| 325 |
"step": 400
|
| 326 |
},
|
| 327 |
{
|
| 328 |
+
"epoch": 2.628205128205128,
|
| 329 |
+
"grad_norm": 2.1671810150146484,
|
| 330 |
+
"learning_rate": 0.00016495726495726495,
|
| 331 |
+
"loss": 0.2966,
|
| 332 |
"step": 410
|
| 333 |
},
|
| 334 |
{
|
| 335 |
+
"epoch": 2.6923076923076925,
|
| 336 |
+
"grad_norm": 4.671816825866699,
|
| 337 |
+
"learning_rate": 0.0001641025641025641,
|
| 338 |
+
"loss": 0.3559,
|
| 339 |
"step": 420
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 2.7564102564102564,
|
| 343 |
+
"grad_norm": 2.6795239448547363,
|
| 344 |
+
"learning_rate": 0.00016324786324786327,
|
| 345 |
+
"loss": 0.2111,
|
| 346 |
"step": 430
|
| 347 |
},
|
| 348 |
{
|
| 349 |
+
"epoch": 2.8205128205128203,
|
| 350 |
+
"grad_norm": 1.8368570804595947,
|
| 351 |
+
"learning_rate": 0.0001623931623931624,
|
| 352 |
+
"loss": 0.2227,
|
| 353 |
"step": 440
|
| 354 |
},
|
| 355 |
{
|
| 356 |
+
"epoch": 2.8846153846153846,
|
| 357 |
+
"grad_norm": 0.7519993185997009,
|
| 358 |
+
"learning_rate": 0.00016153846153846155,
|
| 359 |
+
"loss": 0.2185,
|
| 360 |
"step": 450
|
| 361 |
},
|
| 362 |
{
|
| 363 |
+
"epoch": 2.948717948717949,
|
| 364 |
+
"grad_norm": 4.014621734619141,
|
| 365 |
+
"learning_rate": 0.0001606837606837607,
|
| 366 |
+
"loss": 0.2038,
|
| 367 |
"step": 460
|
| 368 |
},
|
| 369 |
{
|
| 370 |
+
"epoch": 3.0128205128205128,
|
| 371 |
+
"grad_norm": 2.412414073944092,
|
| 372 |
+
"learning_rate": 0.00015982905982905984,
|
| 373 |
+
"loss": 0.1874,
|
| 374 |
"step": 470
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 3.076923076923077,
|
| 378 |
+
"grad_norm": 3.7715134620666504,
|
| 379 |
+
"learning_rate": 0.00015897435897435896,
|
| 380 |
+
"loss": 0.1546,
|
| 381 |
"step": 480
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 3.141025641025641,
|
| 385 |
+
"grad_norm": 1.5307694673538208,
|
| 386 |
+
"learning_rate": 0.00015811965811965813,
|
| 387 |
+
"loss": 0.1115,
|
| 388 |
"step": 490
|
| 389 |
},
|
| 390 |
{
|
| 391 |
+
"epoch": 3.2051282051282053,
|
| 392 |
+
"grad_norm": 2.7572405338287354,
|
| 393 |
+
"learning_rate": 0.00015726495726495727,
|
| 394 |
+
"loss": 0.1242,
|
| 395 |
"step": 500
|
| 396 |
},
|
| 397 |
{
|
| 398 |
+
"epoch": 3.2051282051282053,
|
| 399 |
+
"eval_accuracy": 0.8741007194244604,
|
| 400 |
+
"eval_loss": 0.3899326026439667,
|
| 401 |
+
"eval_runtime": 2.8072,
|
| 402 |
+
"eval_samples_per_second": 99.033,
|
| 403 |
+
"eval_steps_per_second": 12.468,
|
| 404 |
"step": 500
|
| 405 |
},
|
| 406 |
{
|
| 407 |
+
"epoch": 3.269230769230769,
|
| 408 |
+
"grad_norm": 4.4104390144348145,
|
| 409 |
+
"learning_rate": 0.00015641025641025642,
|
| 410 |
+
"loss": 0.1986,
|
| 411 |
"step": 510
|
| 412 |
},
|
| 413 |
{
|
| 414 |
+
"epoch": 3.3333333333333335,
|
| 415 |
+
"grad_norm": 0.8930767774581909,
|
| 416 |
+
"learning_rate": 0.00015555555555555556,
|
| 417 |
+
"loss": 0.0582,
|
| 418 |
"step": 520
|
| 419 |
},
|
| 420 |
{
|
| 421 |
+
"epoch": 3.3974358974358974,
|
| 422 |
+
"grad_norm": 8.353619575500488,
|
| 423 |
+
"learning_rate": 0.0001547008547008547,
|
| 424 |
+
"loss": 0.2485,
|
| 425 |
"step": 530
|
| 426 |
},
|
| 427 |
{
|
| 428 |
+
"epoch": 3.4615384615384617,
|
| 429 |
+
"grad_norm": 0.09837932884693146,
|
| 430 |
+
"learning_rate": 0.00015384615384615385,
|
| 431 |
+
"loss": 0.1007,
|
| 432 |
"step": 540
|
| 433 |
},
|
| 434 |
{
|
| 435 |
+
"epoch": 3.5256410256410255,
|
| 436 |
+
"grad_norm": 3.90265154838562,
|
| 437 |
+
"learning_rate": 0.000152991452991453,
|
| 438 |
+
"loss": 0.2279,
|
| 439 |
"step": 550
|
| 440 |
},
|
| 441 |
{
|
| 442 |
+
"epoch": 3.58974358974359,
|
| 443 |
+
"grad_norm": 6.65275764465332,
|
| 444 |
+
"learning_rate": 0.00015213675213675214,
|
| 445 |
+
"loss": 0.1781,
|
| 446 |
"step": 560
|
| 447 |
},
|
| 448 |
{
|
| 449 |
+
"epoch": 3.6538461538461537,
|
| 450 |
+
"grad_norm": 3.493739604949951,
|
| 451 |
+
"learning_rate": 0.00015128205128205128,
|
| 452 |
+
"loss": 0.2098,
|
| 453 |
"step": 570
|
| 454 |
},
|
| 455 |
{
|
| 456 |
+
"epoch": 3.717948717948718,
|
| 457 |
+
"grad_norm": 4.4887614250183105,
|
| 458 |
+
"learning_rate": 0.00015042735042735043,
|
| 459 |
+
"loss": 0.1899,
|
| 460 |
"step": 580
|
| 461 |
},
|
| 462 |
{
|
| 463 |
+
"epoch": 3.782051282051282,
|
| 464 |
+
"grad_norm": 1.8387681245803833,
|
| 465 |
+
"learning_rate": 0.00014957264957264957,
|
| 466 |
+
"loss": 0.1831,
|
| 467 |
"step": 590
|
| 468 |
},
|
| 469 |
{
|
| 470 |
+
"epoch": 3.8461538461538463,
|
| 471 |
+
"grad_norm": 5.91892671585083,
|
| 472 |
+
"learning_rate": 0.00014871794871794872,
|
| 473 |
+
"loss": 0.124,
|
| 474 |
"step": 600
|
| 475 |
},
|
| 476 |
{
|
| 477 |
+
"epoch": 3.8461538461538463,
|
| 478 |
+
"eval_accuracy": 0.8273381294964028,
|
| 479 |
+
"eval_loss": 0.523663341999054,
|
| 480 |
+
"eval_runtime": 2.6143,
|
| 481 |
+
"eval_samples_per_second": 106.339,
|
| 482 |
+
"eval_steps_per_second": 13.388,
|
| 483 |
"step": 600
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 3.91025641025641,
|
| 487 |
+
"grad_norm": 0.5099517703056335,
|
| 488 |
+
"learning_rate": 0.0001478632478632479,
|
| 489 |
+
"loss": 0.1566,
|
| 490 |
"step": 610
|
| 491 |
},
|
| 492 |
{
|
| 493 |
+
"epoch": 3.9743589743589745,
|
| 494 |
+
"grad_norm": 0.4991530179977417,
|
| 495 |
+
"learning_rate": 0.00014700854700854703,
|
| 496 |
+
"loss": 0.1168,
|
| 497 |
"step": 620
|
| 498 |
},
|
| 499 |
{
|
| 500 |
+
"epoch": 4.038461538461538,
|
| 501 |
+
"grad_norm": 4.448193550109863,
|
| 502 |
+
"learning_rate": 0.00014615384615384615,
|
| 503 |
+
"loss": 0.1044,
|
| 504 |
"step": 630
|
| 505 |
},
|
| 506 |
{
|
| 507 |
+
"epoch": 4.102564102564102,
|
| 508 |
+
"grad_norm": 0.5183725357055664,
|
| 509 |
+
"learning_rate": 0.0001452991452991453,
|
| 510 |
+
"loss": 0.1078,
|
| 511 |
"step": 640
|
| 512 |
},
|
| 513 |
{
|
| 514 |
+
"epoch": 4.166666666666667,
|
| 515 |
+
"grad_norm": 0.9525802135467529,
|
| 516 |
+
"learning_rate": 0.00014444444444444444,
|
| 517 |
+
"loss": 0.0967,
|
| 518 |
"step": 650
|
| 519 |
},
|
| 520 |
{
|
| 521 |
+
"epoch": 4.230769230769231,
|
| 522 |
+
"grad_norm": 0.5207259058952332,
|
| 523 |
+
"learning_rate": 0.0001435897435897436,
|
| 524 |
+
"loss": 0.0973,
|
| 525 |
"step": 660
|
| 526 |
},
|
| 527 |
{
|
| 528 |
+
"epoch": 4.294871794871795,
|
| 529 |
+
"grad_norm": 1.3160842657089233,
|
| 530 |
+
"learning_rate": 0.00014273504273504275,
|
| 531 |
+
"loss": 0.1256,
|
| 532 |
"step": 670
|
| 533 |
},
|
| 534 |
{
|
| 535 |
+
"epoch": 4.358974358974359,
|
| 536 |
+
"grad_norm": 2.892195463180542,
|
| 537 |
+
"learning_rate": 0.0001418803418803419,
|
| 538 |
+
"loss": 0.1178,
|
| 539 |
"step": 680
|
| 540 |
},
|
| 541 |
{
|
| 542 |
+
"epoch": 4.423076923076923,
|
| 543 |
+
"grad_norm": 3.8142576217651367,
|
| 544 |
+
"learning_rate": 0.00014102564102564104,
|
| 545 |
+
"loss": 0.0594,
|
| 546 |
"step": 690
|
| 547 |
},
|
| 548 |
{
|
| 549 |
+
"epoch": 4.487179487179487,
|
| 550 |
+
"grad_norm": 0.11079952865839005,
|
| 551 |
+
"learning_rate": 0.00014017094017094016,
|
| 552 |
+
"loss": 0.1239,
|
| 553 |
"step": 700
|
| 554 |
},
|
| 555 |
{
|
| 556 |
+
"epoch": 4.487179487179487,
|
| 557 |
+
"eval_accuracy": 0.8848920863309353,
|
| 558 |
+
"eval_loss": 0.4221162796020508,
|
| 559 |
+
"eval_runtime": 2.7273,
|
| 560 |
+
"eval_samples_per_second": 101.932,
|
| 561 |
+
"eval_steps_per_second": 12.833,
|
| 562 |
"step": 700
|
| 563 |
},
|
| 564 |
{
|
| 565 |
+
"epoch": 4.551282051282051,
|
| 566 |
+
"grad_norm": 9.544878959655762,
|
| 567 |
+
"learning_rate": 0.0001393162393162393,
|
| 568 |
+
"loss": 0.1185,
|
| 569 |
"step": 710
|
| 570 |
},
|
| 571 |
{
|
| 572 |
+
"epoch": 4.615384615384615,
|
| 573 |
+
"grad_norm": 0.06085001304745674,
|
| 574 |
+
"learning_rate": 0.00013846153846153847,
|
| 575 |
+
"loss": 0.0499,
|
| 576 |
"step": 720
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"epoch": 4.67948717948718,
|
| 580 |
+
"grad_norm": 12.285767555236816,
|
| 581 |
+
"learning_rate": 0.00013760683760683762,
|
| 582 |
+
"loss": 0.1623,
|
| 583 |
"step": 730
|
| 584 |
},
|
| 585 |
{
|
| 586 |
+
"epoch": 4.743589743589744,
|
| 587 |
+
"grad_norm": 1.4333381652832031,
|
| 588 |
+
"learning_rate": 0.00013675213675213676,
|
| 589 |
+
"loss": 0.0903,
|
| 590 |
"step": 740
|
| 591 |
},
|
| 592 |
{
|
| 593 |
+
"epoch": 4.8076923076923075,
|
| 594 |
+
"grad_norm": 0.37026920914649963,
|
| 595 |
+
"learning_rate": 0.0001358974358974359,
|
| 596 |
+
"loss": 0.082,
|
| 597 |
"step": 750
|
| 598 |
},
|
| 599 |
{
|
| 600 |
+
"epoch": 4.871794871794872,
|
| 601 |
+
"grad_norm": 7.013845443725586,
|
| 602 |
+
"learning_rate": 0.00013504273504273505,
|
| 603 |
+
"loss": 0.0443,
|
| 604 |
"step": 760
|
| 605 |
},
|
| 606 |
{
|
| 607 |
+
"epoch": 4.935897435897436,
|
| 608 |
+
"grad_norm": 0.3148520588874817,
|
| 609 |
+
"learning_rate": 0.0001341880341880342,
|
| 610 |
+
"loss": 0.1237,
|
| 611 |
"step": 770
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 5.0,
|
| 615 |
+
"grad_norm": 0.5136359930038452,
|
| 616 |
+
"learning_rate": 0.00013333333333333334,
|
| 617 |
+
"loss": 0.0592,
|
| 618 |
"step": 780
|
| 619 |
},
|
| 620 |
{
|
| 621 |
+
"epoch": 5.064102564102564,
|
| 622 |
+
"grad_norm": 7.698183536529541,
|
| 623 |
+
"learning_rate": 0.00013247863247863248,
|
| 624 |
+
"loss": 0.0742,
|
| 625 |
"step": 790
|
| 626 |
},
|
| 627 |
{
|
| 628 |
+
"epoch": 5.128205128205128,
|
| 629 |
+
"grad_norm": 0.05358889326453209,
|
| 630 |
+
"learning_rate": 0.00013162393162393163,
|
| 631 |
+
"loss": 0.0785,
|
| 632 |
"step": 800
|
| 633 |
},
|
| 634 |
{
|
| 635 |
+
"epoch": 5.128205128205128,
|
| 636 |
+
"eval_accuracy": 0.9136690647482014,
|
| 637 |
+
"eval_loss": 0.36830753087997437,
|
| 638 |
+
"eval_runtime": 3.1493,
|
| 639 |
+
"eval_samples_per_second": 88.273,
|
| 640 |
+
"eval_steps_per_second": 11.114,
|
| 641 |
"step": 800
|
| 642 |
},
|
| 643 |
{
|
| 644 |
+
"epoch": 5.1923076923076925,
|
| 645 |
+
"grad_norm": 0.045300308614969254,
|
| 646 |
+
"learning_rate": 0.00013076923076923077,
|
| 647 |
+
"loss": 0.1987,
|
| 648 |
"step": 810
|
| 649 |
},
|
| 650 |
{
|
| 651 |
+
"epoch": 5.256410256410256,
|
| 652 |
+
"grad_norm": 6.118052959442139,
|
| 653 |
+
"learning_rate": 0.00012991452991452992,
|
| 654 |
+
"loss": 0.0708,
|
| 655 |
"step": 820
|
| 656 |
},
|
| 657 |
{
|
| 658 |
+
"epoch": 5.32051282051282,
|
| 659 |
+
"grad_norm": 0.36830875277519226,
|
| 660 |
+
"learning_rate": 0.00012905982905982906,
|
| 661 |
+
"loss": 0.0329,
|
| 662 |
"step": 830
|
| 663 |
},
|
| 664 |
{
|
| 665 |
+
"epoch": 5.384615384615385,
|
| 666 |
+
"grad_norm": 0.5043929219245911,
|
| 667 |
+
"learning_rate": 0.00012820512820512823,
|
| 668 |
+
"loss": 0.0546,
|
| 669 |
"step": 840
|
| 670 |
},
|
| 671 |
{
|
| 672 |
+
"epoch": 5.448717948717949,
|
| 673 |
+
"grad_norm": 5.8541035652160645,
|
| 674 |
+
"learning_rate": 0.00012735042735042735,
|
| 675 |
+
"loss": 0.0589,
|
| 676 |
"step": 850
|
| 677 |
},
|
| 678 |
{
|
| 679 |
+
"epoch": 5.512820512820513,
|
| 680 |
+
"grad_norm": 0.09965494275093079,
|
| 681 |
+
"learning_rate": 0.0001264957264957265,
|
| 682 |
+
"loss": 0.0257,
|
| 683 |
"step": 860
|
| 684 |
},
|
| 685 |
{
|
| 686 |
+
"epoch": 5.576923076923077,
|
| 687 |
+
"grad_norm": 0.03202090039849281,
|
| 688 |
+
"learning_rate": 0.00012564102564102564,
|
| 689 |
+
"loss": 0.0349,
|
| 690 |
"step": 870
|
| 691 |
},
|
| 692 |
{
|
| 693 |
+
"epoch": 5.641025641025641,
|
| 694 |
+
"grad_norm": 7.21024751663208,
|
| 695 |
+
"learning_rate": 0.00012478632478632478,
|
| 696 |
+
"loss": 0.081,
|
| 697 |
"step": 880
|
| 698 |
},
|
| 699 |
{
|
| 700 |
+
"epoch": 5.705128205128205,
|
| 701 |
+
"grad_norm": 0.03198171406984329,
|
| 702 |
+
"learning_rate": 0.00012393162393162395,
|
| 703 |
+
"loss": 0.037,
|
| 704 |
"step": 890
|
| 705 |
},
|
| 706 |
{
|
| 707 |
+
"epoch": 5.769230769230769,
|
| 708 |
+
"grad_norm": 1.1413763761520386,
|
| 709 |
+
"learning_rate": 0.0001230769230769231,
|
| 710 |
+
"loss": 0.093,
|
| 711 |
"step": 900
|
| 712 |
},
|
| 713 |
{
|
| 714 |
+
"epoch": 5.769230769230769,
|
| 715 |
+
"eval_accuracy": 0.8597122302158273,
|
| 716 |
+
"eval_loss": 0.6375630497932434,
|
| 717 |
+
"eval_runtime": 2.5134,
|
| 718 |
+
"eval_samples_per_second": 110.607,
|
| 719 |
+
"eval_steps_per_second": 13.925,
|
| 720 |
"step": 900
|
| 721 |
},
|
| 722 |
{
|
| 723 |
+
"epoch": 5.833333333333333,
|
| 724 |
+
"grad_norm": 0.030478307977318764,
|
| 725 |
+
"learning_rate": 0.00012222222222222224,
|
| 726 |
+
"loss": 0.1015,
|
| 727 |
"step": 910
|
| 728 |
},
|
| 729 |
{
|
| 730 |
+
"epoch": 5.897435897435898,
|
| 731 |
+
"grad_norm": 7.971870422363281,
|
| 732 |
+
"learning_rate": 0.00012136752136752136,
|
| 733 |
+
"loss": 0.0421,
|
| 734 |
"step": 920
|
| 735 |
},
|
| 736 |
{
|
| 737 |
+
"epoch": 5.961538461538462,
|
| 738 |
+
"grad_norm": 0.7655214667320251,
|
| 739 |
+
"learning_rate": 0.00012051282051282052,
|
| 740 |
+
"loss": 0.0315,
|
| 741 |
"step": 930
|
| 742 |
},
|
| 743 |
{
|
| 744 |
+
"epoch": 6.0256410256410255,
|
| 745 |
+
"grad_norm": 0.10178599506616592,
|
| 746 |
+
"learning_rate": 0.00011965811965811966,
|
| 747 |
+
"loss": 0.008,
|
| 748 |
"step": 940
|
| 749 |
},
|
| 750 |
{
|
| 751 |
+
"epoch": 6.089743589743589,
|
| 752 |
+
"grad_norm": 0.024569841101765633,
|
| 753 |
+
"learning_rate": 0.0001188034188034188,
|
| 754 |
+
"loss": 0.0054,
|
| 755 |
"step": 950
|
| 756 |
},
|
| 757 |
{
|
| 758 |
+
"epoch": 6.153846153846154,
|
| 759 |
+
"grad_norm": 0.36783352494239807,
|
| 760 |
+
"learning_rate": 0.00011794871794871796,
|
| 761 |
+
"loss": 0.0752,
|
| 762 |
"step": 960
|
| 763 |
},
|
| 764 |
{
|
| 765 |
+
"epoch": 6.217948717948718,
|
| 766 |
+
"grad_norm": 0.04280726611614227,
|
| 767 |
+
"learning_rate": 0.00011709401709401711,
|
| 768 |
+
"loss": 0.0286,
|
| 769 |
"step": 970
|
| 770 |
},
|
| 771 |
{
|
| 772 |
+
"epoch": 6.282051282051282,
|
| 773 |
+
"grad_norm": 14.323381423950195,
|
| 774 |
+
"learning_rate": 0.00011623931623931625,
|
| 775 |
+
"loss": 0.0559,
|
| 776 |
"step": 980
|
| 777 |
},
|
| 778 |
{
|
| 779 |
+
"epoch": 6.346153846153846,
|
| 780 |
+
"grad_norm": 0.025405921041965485,
|
| 781 |
+
"learning_rate": 0.00011538461538461538,
|
| 782 |
+
"loss": 0.0238,
|
| 783 |
"step": 990
|
| 784 |
},
|
| 785 |
{
|
| 786 |
+
"epoch": 6.410256410256411,
|
| 787 |
+
"grad_norm": 0.02457793429493904,
|
| 788 |
+
"learning_rate": 0.00011452991452991453,
|
| 789 |
+
"loss": 0.0056,
|
| 790 |
"step": 1000
|
| 791 |
},
|
| 792 |
{
|
| 793 |
+
"epoch": 6.410256410256411,
|
| 794 |
+
"eval_accuracy": 0.9244604316546763,
|
| 795 |
+
"eval_loss": 0.3162367641925812,
|
| 796 |
+
"eval_runtime": 3.2283,
|
| 797 |
+
"eval_samples_per_second": 86.114,
|
| 798 |
+
"eval_steps_per_second": 10.842,
|
| 799 |
"step": 1000
|
| 800 |
},
|
| 801 |
{
|
| 802 |
+
"epoch": 6.4743589743589745,
|
| 803 |
+
"grad_norm": 0.020618008449673653,
|
| 804 |
+
"learning_rate": 0.00011367521367521367,
|
| 805 |
+
"loss": 0.0113,
|
| 806 |
"step": 1010
|
| 807 |
},
|
| 808 |
{
|
| 809 |
+
"epoch": 6.538461538461538,
|
| 810 |
+
"grad_norm": 0.021217485889792442,
|
| 811 |
+
"learning_rate": 0.00011282051282051283,
|
| 812 |
+
"loss": 0.0115,
|
| 813 |
"step": 1020
|
| 814 |
},
|
| 815 |
{
|
| 816 |
+
"epoch": 6.602564102564102,
|
| 817 |
+
"grad_norm": 0.028808822855353355,
|
| 818 |
+
"learning_rate": 0.00011196581196581197,
|
| 819 |
+
"loss": 0.022,
|
| 820 |
"step": 1030
|
| 821 |
},
|
| 822 |
{
|
| 823 |
+
"epoch": 6.666666666666667,
|
| 824 |
+
"grad_norm": 3.5672314167022705,
|
| 825 |
+
"learning_rate": 0.00011111111111111112,
|
| 826 |
+
"loss": 0.0706,
|
| 827 |
"step": 1040
|
| 828 |
},
|
| 829 |
{
|
| 830 |
+
"epoch": 6.730769230769231,
|
| 831 |
+
"grad_norm": 0.25913771986961365,
|
| 832 |
+
"learning_rate": 0.00011025641025641027,
|
| 833 |
+
"loss": 0.021,
|
| 834 |
"step": 1050
|
| 835 |
},
|
| 836 |
{
|
| 837 |
+
"epoch": 6.794871794871795,
|
| 838 |
+
"grad_norm": 12.088153839111328,
|
| 839 |
+
"learning_rate": 0.00010940170940170942,
|
| 840 |
+
"loss": 0.0914,
|
| 841 |
"step": 1060
|
| 842 |
},
|
| 843 |
{
|
| 844 |
+
"epoch": 6.858974358974359,
|
| 845 |
+
"grad_norm": 0.7027952671051025,
|
| 846 |
+
"learning_rate": 0.00010854700854700855,
|
| 847 |
+
"loss": 0.0766,
|
| 848 |
"step": 1070
|
| 849 |
},
|
| 850 |
{
|
| 851 |
+
"epoch": 6.923076923076923,
|
| 852 |
+
"grad_norm": 6.911967754364014,
|
| 853 |
+
"learning_rate": 0.0001076923076923077,
|
| 854 |
+
"loss": 0.0881,
|
| 855 |
"step": 1080
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 6.987179487179487,
|
| 859 |
+
"grad_norm": 0.03289846330881119,
|
| 860 |
+
"learning_rate": 0.00010683760683760684,
|
| 861 |
+
"loss": 0.0125,
|
| 862 |
"step": 1090
|
| 863 |
},
|
| 864 |
{
|
| 865 |
+
"epoch": 7.051282051282051,
|
| 866 |
+
"grad_norm": 0.025492513552308083,
|
| 867 |
+
"learning_rate": 0.000105982905982906,
|
| 868 |
+
"loss": 0.0472,
|
| 869 |
"step": 1100
|
| 870 |
},
|
| 871 |
{
|
| 872 |
+
"epoch": 7.051282051282051,
|
| 873 |
+
"eval_accuracy": 0.8884892086330936,
|
| 874 |
+
"eval_loss": 0.5225415825843811,
|
| 875 |
+
"eval_runtime": 3.7495,
|
| 876 |
+
"eval_samples_per_second": 74.144,
|
| 877 |
+
"eval_steps_per_second": 9.335,
|
| 878 |
"step": 1100
|
| 879 |
},
|
| 880 |
{
|
| 881 |
+
"epoch": 7.115384615384615,
|
| 882 |
+
"grad_norm": 0.022507918998599052,
|
| 883 |
+
"learning_rate": 0.00010512820512820514,
|
| 884 |
+
"loss": 0.0386,
|
| 885 |
"step": 1110
|
| 886 |
},
|
| 887 |
{
|
| 888 |
+
"epoch": 7.17948717948718,
|
| 889 |
+
"grad_norm": 0.020967524498701096,
|
| 890 |
+
"learning_rate": 0.00010427350427350428,
|
| 891 |
+
"loss": 0.0289,
|
| 892 |
"step": 1120
|
| 893 |
},
|
| 894 |
{
|
| 895 |
+
"epoch": 7.243589743589744,
|
| 896 |
+
"grad_norm": 0.5489076972007751,
|
| 897 |
+
"learning_rate": 0.00010341880341880343,
|
| 898 |
+
"loss": 0.0041,
|
| 899 |
"step": 1130
|
| 900 |
},
|
| 901 |
{
|
| 902 |
+
"epoch": 7.3076923076923075,
|
| 903 |
+
"grad_norm": 0.12584710121154785,
|
| 904 |
+
"learning_rate": 0.00010256410256410256,
|
| 905 |
+
"loss": 0.0697,
|
| 906 |
"step": 1140
|
| 907 |
},
|
| 908 |
{
|
| 909 |
+
"epoch": 7.371794871794872,
|
| 910 |
+
"grad_norm": 0.022198162972927094,
|
| 911 |
+
"learning_rate": 0.0001017094017094017,
|
| 912 |
+
"loss": 0.0039,
|
| 913 |
"step": 1150
|
| 914 |
},
|
| 915 |
{
|
| 916 |
+
"epoch": 7.435897435897436,
|
| 917 |
+
"grad_norm": 11.968843460083008,
|
| 918 |
+
"learning_rate": 0.00010085470085470086,
|
| 919 |
+
"loss": 0.0855,
|
| 920 |
"step": 1160
|
| 921 |
},
|
| 922 |
{
|
| 923 |
+
"epoch": 7.5,
|
| 924 |
+
"grad_norm": 0.779564380645752,
|
| 925 |
+
"learning_rate": 0.0001,
|
| 926 |
+
"loss": 0.0585,
|
| 927 |
"step": 1170
|
| 928 |
},
|
| 929 |
{
|
| 930 |
+
"epoch": 7.564102564102564,
|
| 931 |
+
"grad_norm": 0.23576153814792633,
|
| 932 |
+
"learning_rate": 9.914529914529915e-05,
|
| 933 |
+
"loss": 0.0559,
|
| 934 |
"step": 1180
|
| 935 |
},
|
| 936 |
{
|
| 937 |
+
"epoch": 7.628205128205128,
|
| 938 |
+
"grad_norm": 0.020965000614523888,
|
| 939 |
+
"learning_rate": 9.829059829059829e-05,
|
| 940 |
+
"loss": 0.0785,
|
| 941 |
"step": 1190
|
| 942 |
},
|
| 943 |
{
|
| 944 |
+
"epoch": 7.6923076923076925,
|
| 945 |
+
"grad_norm": 6.914454936981201,
|
| 946 |
+
"learning_rate": 9.743589743589744e-05,
|
| 947 |
+
"loss": 0.0234,
|
| 948 |
"step": 1200
|
| 949 |
},
|
| 950 |
{
|
| 951 |
+
"epoch": 7.6923076923076925,
|
| 952 |
+
"eval_accuracy": 0.8597122302158273,
|
| 953 |
+
"eval_loss": 0.6095559000968933,
|
| 954 |
+
"eval_runtime": 2.5288,
|
| 955 |
+
"eval_samples_per_second": 109.933,
|
| 956 |
+
"eval_steps_per_second": 13.84,
|
| 957 |
"step": 1200
|
| 958 |
},
|
| 959 |
{
|
| 960 |
+
"epoch": 7.756410256410256,
|
| 961 |
+
"grad_norm": 1.3177701234817505,
|
| 962 |
+
"learning_rate": 9.658119658119658e-05,
|
| 963 |
+
"loss": 0.0768,
|
| 964 |
"step": 1210
|
| 965 |
},
|
| 966 |
{
|
| 967 |
+
"epoch": 7.82051282051282,
|
| 968 |
+
"grad_norm": 4.212278842926025,
|
| 969 |
+
"learning_rate": 9.572649572649574e-05,
|
| 970 |
+
"loss": 0.0914,
|
| 971 |
"step": 1220
|
| 972 |
},
|
| 973 |
{
|
| 974 |
+
"epoch": 7.884615384615385,
|
| 975 |
+
"grad_norm": 0.02418905310332775,
|
| 976 |
+
"learning_rate": 9.487179487179487e-05,
|
| 977 |
+
"loss": 0.0348,
|
| 978 |
"step": 1230
|
| 979 |
},
|
| 980 |
{
|
| 981 |
+
"epoch": 7.948717948717949,
|
| 982 |
+
"grad_norm": 3.008629322052002,
|
| 983 |
+
"learning_rate": 9.401709401709401e-05,
|
| 984 |
+
"loss": 0.0624,
|
| 985 |
"step": 1240
|
| 986 |
},
|
| 987 |
{
|
| 988 |
+
"epoch": 8.012820512820513,
|
| 989 |
+
"grad_norm": 0.052931949496269226,
|
| 990 |
+
"learning_rate": 9.316239316239317e-05,
|
| 991 |
+
"loss": 0.0076,
|
| 992 |
"step": 1250
|
| 993 |
},
|
| 994 |
{
|
| 995 |
+
"epoch": 8.076923076923077,
|
| 996 |
+
"grad_norm": 7.994688034057617,
|
| 997 |
+
"learning_rate": 9.230769230769232e-05,
|
| 998 |
+
"loss": 0.0326,
|
| 999 |
"step": 1260
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
+
"epoch": 8.14102564102564,
|
| 1003 |
+
"grad_norm": 0.026721293106675148,
|
| 1004 |
+
"learning_rate": 9.145299145299146e-05,
|
| 1005 |
+
"loss": 0.0324,
|
| 1006 |
"step": 1270
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
+
"epoch": 8.205128205128204,
|
| 1010 |
+
"grad_norm": 0.049855004996061325,
|
| 1011 |
+
"learning_rate": 9.05982905982906e-05,
|
| 1012 |
+
"loss": 0.0057,
|
| 1013 |
"step": 1280
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
+
"epoch": 8.26923076923077,
|
| 1017 |
+
"grad_norm": 0.014473488554358482,
|
| 1018 |
+
"learning_rate": 8.974358974358975e-05,
|
| 1019 |
+
"loss": 0.0237,
|
| 1020 |
"step": 1290
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
+
"epoch": 8.333333333333334,
|
| 1024 |
+
"grad_norm": 0.03150290250778198,
|
| 1025 |
+
"learning_rate": 8.888888888888889e-05,
|
| 1026 |
+
"loss": 0.0354,
|
| 1027 |
"step": 1300
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
+
"epoch": 8.333333333333334,
|
| 1031 |
+
"eval_accuracy": 0.8776978417266187,
|
| 1032 |
+
"eval_loss": 0.5520122647285461,
|
| 1033 |
+
"eval_runtime": 3.3151,
|
| 1034 |
+
"eval_samples_per_second": 83.858,
|
| 1035 |
+
"eval_steps_per_second": 10.558,
|
| 1036 |
"step": 1300
|
| 1037 |
},
|
| 1038 |
{
|
| 1039 |
+
"epoch": 8.397435897435898,
|
| 1040 |
+
"grad_norm": 0.013332781381905079,
|
| 1041 |
+
"learning_rate": 8.803418803418804e-05,
|
| 1042 |
+
"loss": 0.0049,
|
| 1043 |
"step": 1310
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
+
"epoch": 8.461538461538462,
|
| 1047 |
+
"grad_norm": 0.013341937214136124,
|
| 1048 |
+
"learning_rate": 8.717948717948718e-05,
|
| 1049 |
+
"loss": 0.0026,
|
| 1050 |
"step": 1320
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
+
"epoch": 8.525641025641026,
|
| 1054 |
+
"grad_norm": 0.012689488008618355,
|
| 1055 |
+
"learning_rate": 8.632478632478634e-05,
|
| 1056 |
+
"loss": 0.0051,
|
| 1057 |
"step": 1330
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
+
"epoch": 8.58974358974359,
|
| 1061 |
+
"grad_norm": 0.014231017790734768,
|
| 1062 |
+
"learning_rate": 8.547008547008547e-05,
|
| 1063 |
+
"loss": 0.0027,
|
| 1064 |
"step": 1340
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
+
"epoch": 8.653846153846153,
|
| 1068 |
+
"grad_norm": 0.052165694534778595,
|
| 1069 |
+
"learning_rate": 8.461538461538461e-05,
|
| 1070 |
+
"loss": 0.0036,
|
| 1071 |
"step": 1350
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
+
"epoch": 8.717948717948717,
|
| 1075 |
+
"grad_norm": 0.11598876118659973,
|
| 1076 |
+
"learning_rate": 8.376068376068377e-05,
|
| 1077 |
+
"loss": 0.0281,
|
| 1078 |
"step": 1360
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
+
"epoch": 8.782051282051283,
|
| 1082 |
+
"grad_norm": 0.01339508593082428,
|
| 1083 |
+
"learning_rate": 8.290598290598292e-05,
|
| 1084 |
+
"loss": 0.0026,
|
| 1085 |
"step": 1370
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
+
"epoch": 8.846153846153847,
|
| 1089 |
+
"grad_norm": 0.011919701471924782,
|
| 1090 |
+
"learning_rate": 8.205128205128205e-05,
|
| 1091 |
+
"loss": 0.0025,
|
| 1092 |
"step": 1380
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
+
"epoch": 8.91025641025641,
|
| 1096 |
+
"grad_norm": 3.217728614807129,
|
| 1097 |
+
"learning_rate": 8.11965811965812e-05,
|
| 1098 |
+
"loss": 0.0379,
|
| 1099 |
"step": 1390
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
+
"epoch": 8.974358974358974,
|
| 1103 |
+
"grad_norm": 0.01331857219338417,
|
| 1104 |
+
"learning_rate": 8.034188034188035e-05,
|
| 1105 |
+
"loss": 0.026,
|
| 1106 |
"step": 1400
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
+
"epoch": 8.974358974358974,
|
| 1110 |
+
"eval_accuracy": 0.8992805755395683,
|
| 1111 |
+
"eval_loss": 0.49377354979515076,
|
| 1112 |
+
"eval_runtime": 2.8453,
|
| 1113 |
+
"eval_samples_per_second": 97.704,
|
| 1114 |
+
"eval_steps_per_second": 12.301,
|
| 1115 |
"step": 1400
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
+
"epoch": 9.038461538461538,
|
| 1119 |
+
"grad_norm": 0.1426580250263214,
|
| 1120 |
+
"learning_rate": 7.948717948717948e-05,
|
| 1121 |
+
"loss": 0.0072,
|
| 1122 |
"step": 1410
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
+
"epoch": 9.102564102564102,
|
| 1126 |
+
"grad_norm": 0.021561838686466217,
|
| 1127 |
+
"learning_rate": 7.863247863247864e-05,
|
| 1128 |
+
"loss": 0.0025,
|
| 1129 |
"step": 1420
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
+
"epoch": 9.166666666666666,
|
| 1133 |
+
"grad_norm": 0.010494213551282883,
|
| 1134 |
+
"learning_rate": 7.777777777777778e-05,
|
| 1135 |
+
"loss": 0.0025,
|
| 1136 |
"step": 1430
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
+
"epoch": 9.23076923076923,
|
| 1140 |
+
"grad_norm": 0.015301249921321869,
|
| 1141 |
+
"learning_rate": 7.692307692307693e-05,
|
| 1142 |
+
"loss": 0.0051,
|
| 1143 |
"step": 1440
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
+
"epoch": 9.294871794871796,
|
| 1147 |
+
"grad_norm": 0.013643044047057629,
|
| 1148 |
+
"learning_rate": 7.606837606837607e-05,
|
| 1149 |
+
"loss": 0.0136,
|
| 1150 |
"step": 1450
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
+
"epoch": 9.35897435897436,
|
| 1154 |
+
"grad_norm": 0.02054368518292904,
|
| 1155 |
+
"learning_rate": 7.521367521367521e-05,
|
| 1156 |
+
"loss": 0.0025,
|
| 1157 |
"step": 1460
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
+
"epoch": 9.423076923076923,
|
| 1161 |
+
"grad_norm": 0.011097296141088009,
|
| 1162 |
+
"learning_rate": 7.435897435897436e-05,
|
| 1163 |
+
"loss": 0.0025,
|
| 1164 |
"step": 1470
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
+
"epoch": 9.487179487179487,
|
| 1168 |
+
"grad_norm": 0.5705698132514954,
|
| 1169 |
+
"learning_rate": 7.350427350427352e-05,
|
| 1170 |
+
"loss": 0.0048,
|
| 1171 |
"step": 1480
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
+
"epoch": 9.551282051282051,
|
| 1175 |
+
"grad_norm": 0.009772556833922863,
|
| 1176 |
+
"learning_rate": 7.264957264957265e-05,
|
| 1177 |
+
"loss": 0.002,
|
| 1178 |
"step": 1490
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
+
"epoch": 9.615384615384615,
|
| 1182 |
+
"grad_norm": 0.011127009056508541,
|
| 1183 |
+
"learning_rate": 7.17948717948718e-05,
|
| 1184 |
+
"loss": 0.002,
|
| 1185 |
"step": 1500
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
+
"epoch": 9.615384615384615,
|
| 1189 |
+
"eval_accuracy": 0.9172661870503597,
|
| 1190 |
+
"eval_loss": 0.43497270345687866,
|
| 1191 |
+
"eval_runtime": 2.5545,
|
| 1192 |
+
"eval_samples_per_second": 108.826,
|
| 1193 |
+
"eval_steps_per_second": 13.701,
|
| 1194 |
"step": 1500
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
+
"epoch": 9.679487179487179,
|
| 1198 |
+
"grad_norm": 0.013090673834085464,
|
| 1199 |
+
"learning_rate": 7.094017094017095e-05,
|
| 1200 |
+
"loss": 0.002,
|
| 1201 |
"step": 1510
|
| 1202 |
},
|
| 1203 |
{
|
| 1204 |
+
"epoch": 9.743589743589745,
|
| 1205 |
+
"grad_norm": 0.00843009538948536,
|
| 1206 |
+
"learning_rate": 7.008547008547008e-05,
|
| 1207 |
+
"loss": 0.0021,
|
| 1208 |
"step": 1520
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
+
"epoch": 9.807692307692308,
|
| 1212 |
+
"grad_norm": 0.00981289241462946,
|
| 1213 |
+
"learning_rate": 6.923076923076924e-05,
|
| 1214 |
+
"loss": 0.0018,
|
| 1215 |
"step": 1530
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
+
"epoch": 9.871794871794872,
|
| 1219 |
+
"grad_norm": 0.01045091450214386,
|
| 1220 |
+
"learning_rate": 6.837606837606838e-05,
|
| 1221 |
+
"loss": 0.0047,
|
| 1222 |
"step": 1540
|
| 1223 |
},
|
| 1224 |
{
|
| 1225 |
+
"epoch": 9.935897435897436,
|
| 1226 |
+
"grad_norm": 0.07456047832965851,
|
| 1227 |
+
"learning_rate": 6.752136752136753e-05,
|
| 1228 |
+
"loss": 0.0021,
|
| 1229 |
+
"step": 1550
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 10.0,
|
| 1233 |
+
"grad_norm": 0.010238745249807835,
|
| 1234 |
+
"learning_rate": 6.666666666666667e-05,
|
| 1235 |
+
"loss": 0.0268,
|
| 1236 |
+
"step": 1560
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 10.064102564102564,
|
| 1240 |
+
"grad_norm": 0.009372313506901264,
|
| 1241 |
+
"learning_rate": 6.581196581196581e-05,
|
| 1242 |
+
"loss": 0.0018,
|
| 1243 |
+
"step": 1570
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 10.128205128205128,
|
| 1247 |
+
"grad_norm": 0.009544081054627895,
|
| 1248 |
+
"learning_rate": 6.495726495726496e-05,
|
| 1249 |
+
"loss": 0.0017,
|
| 1250 |
+
"step": 1580
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 10.192307692307692,
|
| 1254 |
+
"grad_norm": 0.014180944301187992,
|
| 1255 |
+
"learning_rate": 6.410256410256412e-05,
|
| 1256 |
+
"loss": 0.0055,
|
| 1257 |
+
"step": 1590
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 10.256410256410255,
|
| 1261 |
+
"grad_norm": 0.19402286410331726,
|
| 1262 |
+
"learning_rate": 6.324786324786325e-05,
|
| 1263 |
+
"loss": 0.0021,
|
| 1264 |
+
"step": 1600
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 10.256410256410255,
|
| 1268 |
+
"eval_accuracy": 0.9172661870503597,
|
| 1269 |
+
"eval_loss": 0.4223933219909668,
|
| 1270 |
+
"eval_runtime": 3.538,
|
| 1271 |
+
"eval_samples_per_second": 78.575,
|
| 1272 |
+
"eval_steps_per_second": 9.893,
|
| 1273 |
+
"step": 1600
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 10.320512820512821,
|
| 1277 |
+
"grad_norm": 0.008879870176315308,
|
| 1278 |
+
"learning_rate": 6.239316239316239e-05,
|
| 1279 |
+
"loss": 0.0018,
|
| 1280 |
+
"step": 1610
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 10.384615384615385,
|
| 1284 |
+
"grad_norm": 0.008063827641308308,
|
| 1285 |
+
"learning_rate": 6.153846153846155e-05,
|
| 1286 |
+
"loss": 0.002,
|
| 1287 |
+
"step": 1620
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 10.448717948717949,
|
| 1291 |
+
"grad_norm": 0.008835590444505215,
|
| 1292 |
+
"learning_rate": 6.068376068376068e-05,
|
| 1293 |
+
"loss": 0.0018,
|
| 1294 |
+
"step": 1630
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 10.512820512820513,
|
| 1298 |
+
"grad_norm": 0.008632234297692776,
|
| 1299 |
+
"learning_rate": 5.982905982905983e-05,
|
| 1300 |
+
"loss": 0.0017,
|
| 1301 |
+
"step": 1640
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 10.576923076923077,
|
| 1305 |
+
"grad_norm": 0.00828844029456377,
|
| 1306 |
+
"learning_rate": 5.897435897435898e-05,
|
| 1307 |
+
"loss": 0.0016,
|
| 1308 |
+
"step": 1650
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 10.64102564102564,
|
| 1312 |
+
"grad_norm": 0.0323554202914238,
|
| 1313 |
+
"learning_rate": 5.8119658119658126e-05,
|
| 1314 |
+
"loss": 0.0016,
|
| 1315 |
+
"step": 1660
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 10.705128205128204,
|
| 1319 |
+
"grad_norm": 0.008372778072953224,
|
| 1320 |
+
"learning_rate": 5.726495726495726e-05,
|
| 1321 |
+
"loss": 0.0016,
|
| 1322 |
+
"step": 1670
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 10.76923076923077,
|
| 1326 |
+
"grad_norm": 0.007286165375262499,
|
| 1327 |
+
"learning_rate": 5.6410256410256414e-05,
|
| 1328 |
+
"loss": 0.0016,
|
| 1329 |
+
"step": 1680
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 10.833333333333334,
|
| 1333 |
+
"grad_norm": 0.012557004578411579,
|
| 1334 |
+
"learning_rate": 5.555555555555556e-05,
|
| 1335 |
+
"loss": 0.0017,
|
| 1336 |
+
"step": 1690
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 10.897435897435898,
|
| 1340 |
+
"grad_norm": 0.007122470065951347,
|
| 1341 |
+
"learning_rate": 5.470085470085471e-05,
|
| 1342 |
+
"loss": 0.0016,
|
| 1343 |
+
"step": 1700
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 10.897435897435898,
|
| 1347 |
+
"eval_accuracy": 0.9280575539568345,
|
| 1348 |
+
"eval_loss": 0.38381046056747437,
|
| 1349 |
+
"eval_runtime": 2.8652,
|
| 1350 |
+
"eval_samples_per_second": 97.028,
|
| 1351 |
+
"eval_steps_per_second": 12.216,
|
| 1352 |
+
"step": 1700
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 10.961538461538462,
|
| 1356 |
+
"grad_norm": 0.013124003075063229,
|
| 1357 |
+
"learning_rate": 5.384615384615385e-05,
|
| 1358 |
+
"loss": 0.0015,
|
| 1359 |
+
"step": 1710
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 11.025641025641026,
|
| 1363 |
+
"grad_norm": 0.007307114545255899,
|
| 1364 |
+
"learning_rate": 5.2991452991453e-05,
|
| 1365 |
+
"loss": 0.0015,
|
| 1366 |
+
"step": 1720
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 11.08974358974359,
|
| 1370 |
+
"grad_norm": 0.007222812157124281,
|
| 1371 |
+
"learning_rate": 5.213675213675214e-05,
|
| 1372 |
+
"loss": 0.0014,
|
| 1373 |
+
"step": 1730
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 11.153846153846153,
|
| 1377 |
+
"grad_norm": 0.007087068632245064,
|
| 1378 |
+
"learning_rate": 5.128205128205128e-05,
|
| 1379 |
+
"loss": 0.0015,
|
| 1380 |
+
"step": 1740
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 11.217948717948717,
|
| 1384 |
+
"grad_norm": 0.010747412219643593,
|
| 1385 |
+
"learning_rate": 5.042735042735043e-05,
|
| 1386 |
+
"loss": 0.0016,
|
| 1387 |
+
"step": 1750
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 11.282051282051283,
|
| 1391 |
+
"grad_norm": 0.007549288682639599,
|
| 1392 |
+
"learning_rate": 4.9572649572649575e-05,
|
| 1393 |
+
"loss": 0.0014,
|
| 1394 |
+
"step": 1760
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 11.346153846153847,
|
| 1398 |
+
"grad_norm": 0.007861124351620674,
|
| 1399 |
+
"learning_rate": 4.871794871794872e-05,
|
| 1400 |
+
"loss": 0.0015,
|
| 1401 |
+
"step": 1770
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 11.41025641025641,
|
| 1405 |
+
"grad_norm": 0.008711726404726505,
|
| 1406 |
+
"learning_rate": 4.786324786324787e-05,
|
| 1407 |
+
"loss": 0.0014,
|
| 1408 |
+
"step": 1780
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 11.474358974358974,
|
| 1412 |
+
"grad_norm": 0.006650915369391441,
|
| 1413 |
+
"learning_rate": 4.700854700854701e-05,
|
| 1414 |
+
"loss": 0.0014,
|
| 1415 |
+
"step": 1790
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 11.538461538461538,
|
| 1419 |
+
"grad_norm": 0.009336930699646473,
|
| 1420 |
+
"learning_rate": 4.615384615384616e-05,
|
| 1421 |
+
"loss": 0.0014,
|
| 1422 |
+
"step": 1800
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 11.538461538461538,
|
| 1426 |
+
"eval_accuracy": 0.9280575539568345,
|
| 1427 |
+
"eval_loss": 0.3943016529083252,
|
| 1428 |
+
"eval_runtime": 2.5492,
|
| 1429 |
+
"eval_samples_per_second": 109.052,
|
| 1430 |
+
"eval_steps_per_second": 13.73,
|
| 1431 |
+
"step": 1800
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 11.602564102564102,
|
| 1435 |
+
"grad_norm": 0.0071232253685593605,
|
| 1436 |
+
"learning_rate": 4.52991452991453e-05,
|
| 1437 |
+
"loss": 0.0015,
|
| 1438 |
+
"step": 1810
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 11.666666666666666,
|
| 1442 |
+
"grad_norm": 0.0070044491440057755,
|
| 1443 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 1444 |
+
"loss": 0.0014,
|
| 1445 |
+
"step": 1820
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 11.73076923076923,
|
| 1449 |
+
"grad_norm": 0.00735941668972373,
|
| 1450 |
+
"learning_rate": 4.358974358974359e-05,
|
| 1451 |
+
"loss": 0.0014,
|
| 1452 |
+
"step": 1830
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 11.794871794871796,
|
| 1456 |
+
"grad_norm": 0.006876462604850531,
|
| 1457 |
+
"learning_rate": 4.2735042735042735e-05,
|
| 1458 |
+
"loss": 0.0013,
|
| 1459 |
+
"step": 1840
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 11.85897435897436,
|
| 1463 |
+
"grad_norm": 0.008532642386853695,
|
| 1464 |
+
"learning_rate": 4.1880341880341886e-05,
|
| 1465 |
+
"loss": 0.0014,
|
| 1466 |
+
"step": 1850
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 11.923076923076923,
|
| 1470 |
+
"grad_norm": 0.007169618736952543,
|
| 1471 |
+
"learning_rate": 4.1025641025641023e-05,
|
| 1472 |
+
"loss": 0.0013,
|
| 1473 |
+
"step": 1860
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 11.987179487179487,
|
| 1477 |
+
"grad_norm": 0.006206741090863943,
|
| 1478 |
+
"learning_rate": 4.0170940170940174e-05,
|
| 1479 |
+
"loss": 0.0012,
|
| 1480 |
+
"step": 1870
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 12.051282051282051,
|
| 1484 |
+
"grad_norm": 0.006877180654555559,
|
| 1485 |
+
"learning_rate": 3.931623931623932e-05,
|
| 1486 |
+
"loss": 0.0013,
|
| 1487 |
+
"step": 1880
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 12.115384615384615,
|
| 1491 |
+
"grad_norm": 0.006645900197327137,
|
| 1492 |
+
"learning_rate": 3.846153846153846e-05,
|
| 1493 |
+
"loss": 0.0013,
|
| 1494 |
+
"step": 1890
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 12.179487179487179,
|
| 1498 |
+
"grad_norm": 0.007376631256192923,
|
| 1499 |
+
"learning_rate": 3.760683760683761e-05,
|
| 1500 |
+
"loss": 0.0013,
|
| 1501 |
+
"step": 1900
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 12.179487179487179,
|
| 1505 |
+
"eval_accuracy": 0.9280575539568345,
|
| 1506 |
+
"eval_loss": 0.40119558572769165,
|
| 1507 |
+
"eval_runtime": 2.73,
|
| 1508 |
+
"eval_samples_per_second": 101.833,
|
| 1509 |
+
"eval_steps_per_second": 12.821,
|
| 1510 |
+
"step": 1900
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 12.243589743589743,
|
| 1514 |
+
"grad_norm": 0.007013231050223112,
|
| 1515 |
+
"learning_rate": 3.675213675213676e-05,
|
| 1516 |
+
"loss": 0.0013,
|
| 1517 |
+
"step": 1910
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 12.307692307692308,
|
| 1521 |
+
"grad_norm": 0.006970913149416447,
|
| 1522 |
+
"learning_rate": 3.58974358974359e-05,
|
| 1523 |
+
"loss": 0.0013,
|
| 1524 |
+
"step": 1920
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 12.371794871794872,
|
| 1528 |
+
"grad_norm": 0.006338655948638916,
|
| 1529 |
+
"learning_rate": 3.504273504273504e-05,
|
| 1530 |
+
"loss": 0.0013,
|
| 1531 |
+
"step": 1930
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 12.435897435897436,
|
| 1535 |
+
"grad_norm": 0.007881653495132923,
|
| 1536 |
+
"learning_rate": 3.418803418803419e-05,
|
| 1537 |
+
"loss": 0.0013,
|
| 1538 |
+
"step": 1940
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 12.5,
|
| 1542 |
+
"grad_norm": 0.005947918631136417,
|
| 1543 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 1544 |
+
"loss": 0.0012,
|
| 1545 |
+
"step": 1950
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 12.564102564102564,
|
| 1549 |
+
"grad_norm": 0.005899305455386639,
|
| 1550 |
+
"learning_rate": 3.247863247863248e-05,
|
| 1551 |
+
"loss": 0.0012,
|
| 1552 |
+
"step": 1960
|
| 1553 |
+
},
|
| 1554 |
+
{
|
| 1555 |
+
"epoch": 12.628205128205128,
|
| 1556 |
+
"grad_norm": 0.0061206454411149025,
|
| 1557 |
+
"learning_rate": 3.162393162393162e-05,
|
| 1558 |
+
"loss": 0.0013,
|
| 1559 |
+
"step": 1970
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 12.692307692307692,
|
| 1563 |
+
"grad_norm": 0.00656491843983531,
|
| 1564 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 1565 |
+
"loss": 0.0012,
|
| 1566 |
+
"step": 1980
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 12.756410256410255,
|
| 1570 |
+
"grad_norm": 0.006318471394479275,
|
| 1571 |
+
"learning_rate": 2.9914529914529915e-05,
|
| 1572 |
+
"loss": 0.0012,
|
| 1573 |
+
"step": 1990
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 12.820512820512821,
|
| 1577 |
+
"grad_norm": 0.00670122355222702,
|
| 1578 |
+
"learning_rate": 2.9059829059829063e-05,
|
| 1579 |
+
"loss": 0.0012,
|
| 1580 |
+
"step": 2000
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 12.820512820512821,
|
| 1584 |
+
"eval_accuracy": 0.9280575539568345,
|
| 1585 |
+
"eval_loss": 0.4066712558269501,
|
| 1586 |
+
"eval_runtime": 3.6428,
|
| 1587 |
+
"eval_samples_per_second": 76.315,
|
| 1588 |
+
"eval_steps_per_second": 9.608,
|
| 1589 |
+
"step": 2000
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 12.884615384615385,
|
| 1593 |
+
"grad_norm": 0.005691882688552141,
|
| 1594 |
+
"learning_rate": 2.8205128205128207e-05,
|
| 1595 |
+
"loss": 0.0012,
|
| 1596 |
+
"step": 2010
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 12.948717948717949,
|
| 1600 |
+
"grad_norm": 0.005753946490585804,
|
| 1601 |
+
"learning_rate": 2.7350427350427355e-05,
|
| 1602 |
+
"loss": 0.0012,
|
| 1603 |
+
"step": 2020
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 13.012820512820513,
|
| 1607 |
+
"grad_norm": 0.006568002514541149,
|
| 1608 |
+
"learning_rate": 2.64957264957265e-05,
|
| 1609 |
+
"loss": 0.0013,
|
| 1610 |
+
"step": 2030
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 13.076923076923077,
|
| 1614 |
+
"grad_norm": 0.005731898359954357,
|
| 1615 |
+
"learning_rate": 2.564102564102564e-05,
|
| 1616 |
+
"loss": 0.0012,
|
| 1617 |
+
"step": 2040
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 13.14102564102564,
|
| 1621 |
+
"grad_norm": 0.005868157371878624,
|
| 1622 |
+
"learning_rate": 2.4786324786324787e-05,
|
| 1623 |
+
"loss": 0.0011,
|
| 1624 |
+
"step": 2050
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 13.205128205128204,
|
| 1628 |
+
"grad_norm": 0.006337730213999748,
|
| 1629 |
+
"learning_rate": 2.3931623931623935e-05,
|
| 1630 |
+
"loss": 0.0012,
|
| 1631 |
+
"step": 2060
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 13.26923076923077,
|
| 1635 |
+
"grad_norm": 0.006973997224122286,
|
| 1636 |
+
"learning_rate": 2.307692307692308e-05,
|
| 1637 |
+
"loss": 0.0011,
|
| 1638 |
+
"step": 2070
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 13.333333333333334,
|
| 1642 |
+
"grad_norm": 0.00554188247770071,
|
| 1643 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 1644 |
+
"loss": 0.0011,
|
| 1645 |
+
"step": 2080
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 13.397435897435898,
|
| 1649 |
+
"grad_norm": 0.006806936115026474,
|
| 1650 |
+
"learning_rate": 2.1367521367521368e-05,
|
| 1651 |
+
"loss": 0.0011,
|
| 1652 |
+
"step": 2090
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 13.461538461538462,
|
| 1656 |
+
"grad_norm": 0.005874712951481342,
|
| 1657 |
+
"learning_rate": 2.0512820512820512e-05,
|
| 1658 |
+
"loss": 0.0011,
|
| 1659 |
+
"step": 2100
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 13.461538461538462,
|
| 1663 |
+
"eval_accuracy": 0.9280575539568345,
|
| 1664 |
+
"eval_loss": 0.41012829542160034,
|
| 1665 |
+
"eval_runtime": 2.5393,
|
| 1666 |
+
"eval_samples_per_second": 109.477,
|
| 1667 |
+
"eval_steps_per_second": 13.783,
|
| 1668 |
+
"step": 2100
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 13.525641025641026,
|
| 1672 |
+
"grad_norm": 0.006118403282016516,
|
| 1673 |
+
"learning_rate": 1.965811965811966e-05,
|
| 1674 |
+
"loss": 0.0012,
|
| 1675 |
+
"step": 2110
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 13.58974358974359,
|
| 1679 |
+
"grad_norm": 0.005724759306758642,
|
| 1680 |
+
"learning_rate": 1.8803418803418804e-05,
|
| 1681 |
+
"loss": 0.0012,
|
| 1682 |
+
"step": 2120
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 13.653846153846153,
|
| 1686 |
+
"grad_norm": 0.005641784518957138,
|
| 1687 |
+
"learning_rate": 1.794871794871795e-05,
|
| 1688 |
+
"loss": 0.0011,
|
| 1689 |
+
"step": 2130
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 13.717948717948717,
|
| 1693 |
+
"grad_norm": 0.006412914022803307,
|
| 1694 |
+
"learning_rate": 1.7094017094017095e-05,
|
| 1695 |
+
"loss": 0.0012,
|
| 1696 |
+
"step": 2140
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 13.782051282051283,
|
| 1700 |
+
"grad_norm": 0.0061592236161231995,
|
| 1701 |
+
"learning_rate": 1.623931623931624e-05,
|
| 1702 |
+
"loss": 0.0012,
|
| 1703 |
+
"step": 2150
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 13.846153846153847,
|
| 1707 |
+
"grad_norm": 0.006390335038304329,
|
| 1708 |
+
"learning_rate": 1.5384615384615387e-05,
|
| 1709 |
+
"loss": 0.0012,
|
| 1710 |
+
"step": 2160
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 13.91025641025641,
|
| 1714 |
+
"grad_norm": 0.006186114624142647,
|
| 1715 |
+
"learning_rate": 1.4529914529914531e-05,
|
| 1716 |
+
"loss": 0.0012,
|
| 1717 |
+
"step": 2170
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 13.974358974358974,
|
| 1721 |
+
"grad_norm": 0.006987506989389658,
|
| 1722 |
+
"learning_rate": 1.3675213675213677e-05,
|
| 1723 |
+
"loss": 0.0013,
|
| 1724 |
+
"step": 2180
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 14.038461538461538,
|
| 1728 |
+
"grad_norm": 0.0060087586753070354,
|
| 1729 |
+
"learning_rate": 1.282051282051282e-05,
|
| 1730 |
+
"loss": 0.0011,
|
| 1731 |
+
"step": 2190
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 14.102564102564102,
|
| 1735 |
+
"grad_norm": 0.005536227021366358,
|
| 1736 |
+
"learning_rate": 1.1965811965811967e-05,
|
| 1737 |
+
"loss": 0.0011,
|
| 1738 |
+
"step": 2200
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 14.102564102564102,
|
| 1742 |
+
"eval_accuracy": 0.9280575539568345,
|
| 1743 |
+
"eval_loss": 0.41235998272895813,
|
| 1744 |
+
"eval_runtime": 3.6965,
|
| 1745 |
+
"eval_samples_per_second": 75.206,
|
| 1746 |
+
"eval_steps_per_second": 9.468,
|
| 1747 |
+
"step": 2200
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 14.166666666666666,
|
| 1751 |
+
"grad_norm": 0.00747127179056406,
|
| 1752 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 1753 |
+
"loss": 0.0011,
|
| 1754 |
+
"step": 2210
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 14.23076923076923,
|
| 1758 |
+
"grad_norm": 0.006075258832424879,
|
| 1759 |
+
"learning_rate": 1.0256410256410256e-05,
|
| 1760 |
+
"loss": 0.0012,
|
| 1761 |
+
"step": 2220
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 14.294871794871796,
|
| 1765 |
+
"grad_norm": 0.005355818197131157,
|
| 1766 |
+
"learning_rate": 9.401709401709402e-06,
|
| 1767 |
+
"loss": 0.0011,
|
| 1768 |
+
"step": 2230
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 14.35897435897436,
|
| 1772 |
+
"grad_norm": 0.006171481683850288,
|
| 1773 |
+
"learning_rate": 8.547008547008548e-06,
|
| 1774 |
+
"loss": 0.0012,
|
| 1775 |
+
"step": 2240
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 14.423076923076923,
|
| 1779 |
+
"grad_norm": 0.006203506141901016,
|
| 1780 |
+
"learning_rate": 7.692307692307694e-06,
|
| 1781 |
+
"loss": 0.0011,
|
| 1782 |
+
"step": 2250
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 14.487179487179487,
|
| 1786 |
+
"grad_norm": 0.0053332289680838585,
|
| 1787 |
+
"learning_rate": 6.837606837606839e-06,
|
| 1788 |
+
"loss": 0.0011,
|
| 1789 |
+
"step": 2260
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 14.551282051282051,
|
| 1793 |
+
"grad_norm": 0.006036951672285795,
|
| 1794 |
+
"learning_rate": 5.982905982905984e-06,
|
| 1795 |
+
"loss": 0.0012,
|
| 1796 |
+
"step": 2270
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 14.615384615384615,
|
| 1800 |
+
"grad_norm": 0.006114748306572437,
|
| 1801 |
+
"learning_rate": 5.128205128205128e-06,
|
| 1802 |
+
"loss": 0.0012,
|
| 1803 |
+
"step": 2280
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 14.679487179487179,
|
| 1807 |
+
"grad_norm": 0.0059860167093575,
|
| 1808 |
+
"learning_rate": 4.273504273504274e-06,
|
| 1809 |
+
"loss": 0.0011,
|
| 1810 |
+
"step": 2290
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 14.743589743589745,
|
| 1814 |
+
"grad_norm": 0.005834794137626886,
|
| 1815 |
+
"learning_rate": 3.4188034188034193e-06,
|
| 1816 |
+
"loss": 0.0012,
|
| 1817 |
+
"step": 2300
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 14.743589743589745,
|
| 1821 |
+
"eval_accuracy": 0.9280575539568345,
|
| 1822 |
+
"eval_loss": 0.4135644733905792,
|
| 1823 |
+
"eval_runtime": 2.5193,
|
| 1824 |
+
"eval_samples_per_second": 110.348,
|
| 1825 |
+
"eval_steps_per_second": 13.893,
|
| 1826 |
+
"step": 2300
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 14.807692307692308,
|
| 1830 |
+
"grad_norm": 0.005964505951851606,
|
| 1831 |
+
"learning_rate": 2.564102564102564e-06,
|
| 1832 |
+
"loss": 0.0012,
|
| 1833 |
+
"step": 2310
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 14.871794871794872,
|
| 1837 |
+
"grad_norm": 0.005720064975321293,
|
| 1838 |
+
"learning_rate": 1.7094017094017097e-06,
|
| 1839 |
+
"loss": 0.0011,
|
| 1840 |
+
"step": 2320
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 14.935897435897436,
|
| 1844 |
+
"grad_norm": 0.005913382861763239,
|
| 1845 |
+
"learning_rate": 8.547008547008548e-07,
|
| 1846 |
+
"loss": 0.0011,
|
| 1847 |
+
"step": 2330
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 15.0,
|
| 1851 |
+
"grad_norm": 0.005278407130390406,
|
| 1852 |
+
"learning_rate": 0.0,
|
| 1853 |
+
"loss": 0.0011,
|
| 1854 |
+
"step": 2340
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 15.0,
|
| 1858 |
+
"step": 2340,
|
| 1859 |
+
"total_flos": 2.900189697360077e+18,
|
| 1860 |
+
"train_loss": 0.14551133991808146,
|
| 1861 |
+
"train_runtime": 927.2479,
|
| 1862 |
+
"train_samples_per_second": 40.361,
|
| 1863 |
+
"train_steps_per_second": 2.524
|
| 1864 |
}
|
| 1865 |
],
|
| 1866 |
"logging_steps": 10,
|
| 1867 |
+
"max_steps": 2340,
|
| 1868 |
"num_input_tokens_seen": 0,
|
| 1869 |
+
"num_train_epochs": 15,
|
| 1870 |
"save_steps": 100,
|
| 1871 |
"stateful_callbacks": {
|
| 1872 |
"TrainerControl": {
|
|
|
|
| 1880 |
"attributes": {}
|
| 1881 |
}
|
| 1882 |
},
|
| 1883 |
+
"total_flos": 2.900189697360077e+18,
|
| 1884 |
"train_batch_size": 16,
|
| 1885 |
"trial_name": null,
|
| 1886 |
"trial_params": null
|