🍻 cheers
Browse files- README.md +5 -4
- all_results.json +12 -12
- eval_results.json +7 -7
- runs/Aug10_02-56-03_instance-camaras/events.out.tfevents.1754795221.instance-camaras +3 -0
- train_results.json +6 -6
- trainer_state.json +789 -1109
README.md
CHANGED
|
@@ -3,6 +3,7 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: facebook/deit-base-distilled-patch16-224
|
| 5 |
tags:
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
@@ -17,11 +18,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
# deit-CEMEDE
|
| 19 |
|
| 20 |
-
This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 0.
|
| 23 |
-
- Accuracy: 0.
|
| 24 |
-
- F1: 0.
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: facebook/deit-base-distilled-patch16-224
|
| 5 |
tags:
|
| 6 |
+
- image-classification
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 18 |
|
| 19 |
# deit-CEMEDE
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [facebook/deit-base-distilled-patch16-224](https://huggingface.co/facebook/deit-base-distilled-patch16-224) on the cemede dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.8585
|
| 24 |
+
- Accuracy: 0.7884
|
| 25 |
+
- F1: 0.7973
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
all_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_runtime": 12.
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
-
"total_flos": 1.
|
| 10 |
-
"train_loss": 0.
|
| 11 |
-
"train_runtime":
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second":
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.6923076923076923,
|
| 3 |
+
"eval_accuracy": 0.7883975273418925,
|
| 4 |
+
"eval_f1": 0.7973086083953446,
|
| 5 |
+
"eval_loss": 0.8585250973701477,
|
| 6 |
+
"eval_runtime": 12.5738,
|
| 7 |
+
"eval_samples_per_second": 167.252,
|
| 8 |
+
"eval_steps_per_second": 20.916,
|
| 9 |
+
"total_flos": 1.3637892549580186e+18,
|
| 10 |
+
"train_loss": 0.3320726641470736,
|
| 11 |
+
"train_runtime": 627.5337,
|
| 12 |
+
"train_samples_per_second": 82.824,
|
| 13 |
+
"train_steps_per_second": 10.358
|
| 14 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_runtime": 12.
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.6923076923076923,
|
| 3 |
+
"eval_accuracy": 0.7883975273418925,
|
| 4 |
+
"eval_f1": 0.7973086083953446,
|
| 5 |
+
"eval_loss": 0.8585250973701477,
|
| 6 |
+
"eval_runtime": 12.5738,
|
| 7 |
+
"eval_samples_per_second": 167.252,
|
| 8 |
+
"eval_steps_per_second": 20.916
|
| 9 |
}
|
runs/Aug10_02-56-03_instance-camaras/events.out.tfevents.1754795221.instance-camaras
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b42c9ea95e051e5bc8d73a868483da7b840faf76679b42cce2f3e9cbfbe3051
|
| 3 |
+
size 40
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos": 1.
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1.6923076923076923,
|
| 3 |
+
"total_flos": 1.3637892549580186e+18,
|
| 4 |
+
"train_loss": 0.3320726641470736,
|
| 5 |
+
"train_runtime": 627.5337,
|
| 6 |
+
"train_samples_per_second": 82.824,
|
| 7 |
+
"train_steps_per_second": 10.358
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,2102 +1,1782 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "./deit-CEMEDE/checkpoint-
|
| 5 |
-
"epoch":
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.007692307692307693,
|
| 14 |
-
"grad_norm":
|
| 15 |
-
"learning_rate": 0.
|
| 16 |
-
"loss": 2.
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.015384615384615385,
|
| 21 |
-
"grad_norm":
|
| 22 |
-
"learning_rate": 0.
|
| 23 |
-
"loss": 1.
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.023076923076923078,
|
| 28 |
-
"grad_norm":
|
| 29 |
-
"learning_rate": 0.
|
| 30 |
-
"loss": 1.
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.03076923076923077,
|
| 35 |
-
"grad_norm":
|
| 36 |
-
"learning_rate": 0.
|
| 37 |
-
"loss": 1.
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.038461538461538464,
|
| 42 |
-
"grad_norm":
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss": 0.
|
| 45 |
"step": 50
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.046153846153846156,
|
| 49 |
-
"grad_norm":
|
| 50 |
-
"learning_rate": 0.
|
| 51 |
-
"loss": 0.
|
| 52 |
"step": 60
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.05384615384615385,
|
| 56 |
-
"grad_norm":
|
| 57 |
-
"learning_rate": 0.
|
| 58 |
-
"loss":
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.06153846153846154,
|
| 63 |
-
"grad_norm":
|
| 64 |
-
"learning_rate": 0.
|
| 65 |
-
"loss": 1.
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.06923076923076923,
|
| 70 |
-
"grad_norm":
|
| 71 |
-
"learning_rate": 0.
|
| 72 |
-
"loss": 0.
|
| 73 |
"step": 90
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.07692307692307693,
|
| 77 |
-
"grad_norm":
|
| 78 |
-
"learning_rate": 0.
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 100
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.07692307692307693,
|
| 84 |
-
"eval_accuracy": 0.
|
| 85 |
-
"eval_f1": 0.
|
| 86 |
-
"eval_loss": 1.
|
| 87 |
-
"eval_runtime": 12.
|
| 88 |
-
"eval_samples_per_second":
|
| 89 |
-
"eval_steps_per_second": 20.
|
| 90 |
"step": 100
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 0.08461538461538462,
|
| 94 |
-
"grad_norm":
|
| 95 |
-
"learning_rate": 0.
|
| 96 |
-
"loss": 0.
|
| 97 |
"step": 110
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"epoch": 0.09230769230769231,
|
| 101 |
-
"grad_norm":
|
| 102 |
-
"learning_rate": 0.
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 120
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.1,
|
| 108 |
-
"grad_norm":
|
| 109 |
-
"learning_rate": 0.
|
| 110 |
-
"loss": 0.
|
| 111 |
"step": 130
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.1076923076923077,
|
| 115 |
-
"grad_norm":
|
| 116 |
-
"learning_rate": 0.
|
| 117 |
-
"loss": 0.
|
| 118 |
"step": 140
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 0.11538461538461539,
|
| 122 |
-
"grad_norm":
|
| 123 |
-
"learning_rate": 0.
|
| 124 |
-
"loss": 0.
|
| 125 |
"step": 150
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"epoch": 0.12307692307692308,
|
| 129 |
-
"grad_norm":
|
| 130 |
-
"learning_rate": 0.
|
| 131 |
-
"loss": 0.
|
| 132 |
"step": 160
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 0.13076923076923078,
|
| 136 |
-
"grad_norm":
|
| 137 |
-
"learning_rate": 0.
|
| 138 |
-
"loss": 0.
|
| 139 |
"step": 170
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 0.13846153846153847,
|
| 143 |
-
"grad_norm": 9.
|
| 144 |
-
"learning_rate": 0.
|
| 145 |
-
"loss": 0.
|
| 146 |
"step": 180
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.14615384615384616,
|
| 150 |
-
"grad_norm":
|
| 151 |
-
"learning_rate": 0.
|
| 152 |
-
"loss": 0.
|
| 153 |
"step": 190
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.15384615384615385,
|
| 157 |
-
"grad_norm":
|
| 158 |
-
"learning_rate": 0.
|
| 159 |
-
"loss": 0.
|
| 160 |
"step": 200
|
| 161 |
},
|
| 162 |
{
|
| 163 |
"epoch": 0.15384615384615385,
|
| 164 |
-
"eval_accuracy": 0.
|
| 165 |
-
"eval_f1": 0.
|
| 166 |
-
"eval_loss": 1.
|
| 167 |
-
"eval_runtime": 12.
|
| 168 |
-
"eval_samples_per_second":
|
| 169 |
-
"eval_steps_per_second": 20.
|
| 170 |
"step": 200
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.16153846153846155,
|
| 174 |
-
"grad_norm":
|
| 175 |
-
"learning_rate": 0.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 210
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.16923076923076924,
|
| 181 |
-
"grad_norm":
|
| 182 |
-
"learning_rate": 0.
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 220
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.17692307692307693,
|
| 188 |
-
"grad_norm":
|
| 189 |
-
"learning_rate": 0.
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 230
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.18461538461538463,
|
| 195 |
-
"grad_norm":
|
| 196 |
-
"learning_rate": 0.
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 240
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.19230769230769232,
|
| 202 |
-
"grad_norm": 3.
|
| 203 |
-
"learning_rate": 0.
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 250
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.2,
|
| 209 |
-
"grad_norm":
|
| 210 |
-
"learning_rate": 0.
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 260
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.2076923076923077,
|
| 216 |
-
"grad_norm":
|
| 217 |
-
"learning_rate": 0.
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 270
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.2153846153846154,
|
| 223 |
-
"grad_norm":
|
| 224 |
-
"learning_rate": 0.
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 280
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.2230769230769231,
|
| 230 |
-
"grad_norm":
|
| 231 |
-
"learning_rate": 0.
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 290
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.23076923076923078,
|
| 237 |
-
"grad_norm":
|
| 238 |
-
"learning_rate": 0.
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 300
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.23076923076923078,
|
| 244 |
-
"eval_accuracy": 0.
|
| 245 |
-
"eval_f1": 0.
|
| 246 |
-
"eval_loss":
|
| 247 |
-
"eval_runtime": 12.
|
| 248 |
-
"eval_samples_per_second":
|
| 249 |
-
"eval_steps_per_second":
|
| 250 |
"step": 300
|
| 251 |
},
|
| 252 |
{
|
| 253 |
"epoch": 0.23846153846153847,
|
| 254 |
-
"grad_norm":
|
| 255 |
-
"learning_rate": 0.
|
| 256 |
-
"loss": 0.
|
| 257 |
"step": 310
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 0.24615384615384617,
|
| 261 |
-
"grad_norm":
|
| 262 |
-
"learning_rate": 0.
|
| 263 |
-
"loss": 0.
|
| 264 |
"step": 320
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 0.25384615384615383,
|
| 268 |
-
"grad_norm":
|
| 269 |
-
"learning_rate": 0.
|
| 270 |
-
"loss": 0.
|
| 271 |
"step": 330
|
| 272 |
},
|
| 273 |
{
|
| 274 |
"epoch": 0.26153846153846155,
|
| 275 |
-
"grad_norm": 6.
|
| 276 |
-
"learning_rate": 0.
|
| 277 |
-
"loss": 0.
|
| 278 |
"step": 340
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 0.2692307692307692,
|
| 282 |
-
"grad_norm":
|
| 283 |
-
"learning_rate": 0.
|
| 284 |
-
"loss": 0.
|
| 285 |
"step": 350
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 0.27692307692307694,
|
| 289 |
-
"grad_norm":
|
| 290 |
-
"learning_rate": 0.
|
| 291 |
-
"loss": 0.
|
| 292 |
"step": 360
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 0.2846153846153846,
|
| 296 |
-
"grad_norm":
|
| 297 |
-
"learning_rate": 0.
|
| 298 |
-
"loss": 0.
|
| 299 |
"step": 370
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 0.2923076923076923,
|
| 303 |
-
"grad_norm":
|
| 304 |
-
"learning_rate": 0.
|
| 305 |
-
"loss": 0.
|
| 306 |
"step": 380
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 0.3,
|
| 310 |
-
"grad_norm": 4.
|
| 311 |
-
"learning_rate": 0.
|
| 312 |
-
"loss": 0.
|
| 313 |
"step": 390
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 0.3076923076923077,
|
| 317 |
-
"grad_norm":
|
| 318 |
-
"learning_rate": 0.
|
| 319 |
-
"loss": 0.
|
| 320 |
"step": 400
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 0.3076923076923077,
|
| 324 |
-
"eval_accuracy": 0.
|
| 325 |
-
"eval_f1": 0.
|
| 326 |
-
"eval_loss": 1.
|
| 327 |
-
"eval_runtime": 12.
|
| 328 |
-
"eval_samples_per_second":
|
| 329 |
-
"eval_steps_per_second": 20.
|
| 330 |
"step": 400
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 0.3153846153846154,
|
| 334 |
-
"grad_norm":
|
| 335 |
-
"learning_rate": 0.
|
| 336 |
-
"loss": 0.
|
| 337 |
"step": 410
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 0.3230769230769231,
|
| 341 |
-
"grad_norm":
|
| 342 |
-
"learning_rate": 0.
|
| 343 |
-
"loss": 0.
|
| 344 |
"step": 420
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 0.33076923076923076,
|
| 348 |
-
"grad_norm":
|
| 349 |
-
"learning_rate": 0.
|
| 350 |
-
"loss": 0.
|
| 351 |
"step": 430
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 0.3384615384615385,
|
| 355 |
-
"grad_norm":
|
| 356 |
-
"learning_rate": 0.
|
| 357 |
-
"loss": 0.
|
| 358 |
"step": 440
|
| 359 |
},
|
| 360 |
{
|
| 361 |
"epoch": 0.34615384615384615,
|
| 362 |
-
"grad_norm":
|
| 363 |
-
"learning_rate": 0.
|
| 364 |
-
"loss": 0.
|
| 365 |
"step": 450
|
| 366 |
},
|
| 367 |
{
|
| 368 |
"epoch": 0.35384615384615387,
|
| 369 |
-
"grad_norm":
|
| 370 |
-
"learning_rate": 0.
|
| 371 |
-
"loss": 0.
|
| 372 |
"step": 460
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 0.36153846153846153,
|
| 376 |
-
"grad_norm":
|
| 377 |
-
"learning_rate": 0.
|
| 378 |
-
"loss": 0.
|
| 379 |
"step": 470
|
| 380 |
},
|
| 381 |
{
|
| 382 |
"epoch": 0.36923076923076925,
|
| 383 |
-
"grad_norm":
|
| 384 |
-
"learning_rate": 0.
|
| 385 |
-
"loss": 0.
|
| 386 |
"step": 480
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 0.3769230769230769,
|
| 390 |
-
"grad_norm":
|
| 391 |
-
"learning_rate": 0.
|
| 392 |
-
"loss": 0.
|
| 393 |
"step": 490
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 0.38461538461538464,
|
| 397 |
-
"grad_norm":
|
| 398 |
-
"learning_rate": 0.
|
| 399 |
-
"loss": 0.
|
| 400 |
"step": 500
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"epoch": 0.38461538461538464,
|
| 404 |
-
"eval_accuracy": 0.
|
| 405 |
-
"eval_f1": 0.
|
| 406 |
-
"eval_loss": 1.
|
| 407 |
-
"eval_runtime": 12.
|
| 408 |
-
"eval_samples_per_second":
|
| 409 |
-
"eval_steps_per_second": 20.
|
| 410 |
"step": 500
|
| 411 |
},
|
| 412 |
{
|
| 413 |
"epoch": 0.3923076923076923,
|
| 414 |
-
"grad_norm":
|
| 415 |
-
"learning_rate": 0.
|
| 416 |
-
"loss": 0.
|
| 417 |
"step": 510
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 0.4,
|
| 421 |
-
"grad_norm":
|
| 422 |
-
"learning_rate": 0.
|
| 423 |
-
"loss": 0.
|
| 424 |
"step": 520
|
| 425 |
},
|
| 426 |
{
|
| 427 |
"epoch": 0.4076923076923077,
|
| 428 |
-
"grad_norm":
|
| 429 |
-
"learning_rate": 0.
|
| 430 |
-
"loss": 0.
|
| 431 |
"step": 530
|
| 432 |
},
|
| 433 |
{
|
| 434 |
"epoch": 0.4153846153846154,
|
| 435 |
-
"grad_norm": 6.
|
| 436 |
-
"learning_rate": 0.
|
| 437 |
-
"loss": 0.
|
| 438 |
"step": 540
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 0.4230769230769231,
|
| 442 |
-
"grad_norm":
|
| 443 |
-
"learning_rate": 0.
|
| 444 |
-
"loss": 0.
|
| 445 |
"step": 550
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"epoch": 0.4307692307692308,
|
| 449 |
-
"grad_norm": 0.
|
| 450 |
-
"learning_rate": 0.
|
| 451 |
-
"loss": 0.
|
| 452 |
"step": 560
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 0.43846153846153846,
|
| 456 |
-
"grad_norm": 0.
|
| 457 |
-
"learning_rate": 0.
|
| 458 |
-
"loss": 0.
|
| 459 |
"step": 570
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 0.4461538461538462,
|
| 463 |
-
"grad_norm":
|
| 464 |
-
"learning_rate": 0.
|
| 465 |
-
"loss": 0.
|
| 466 |
"step": 580
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 0.45384615384615384,
|
| 470 |
-
"grad_norm":
|
| 471 |
-
"learning_rate": 0.
|
| 472 |
-
"loss": 0.
|
| 473 |
"step": 590
|
| 474 |
},
|
| 475 |
{
|
| 476 |
"epoch": 0.46153846153846156,
|
| 477 |
-
"grad_norm":
|
| 478 |
-
"learning_rate": 0.
|
| 479 |
-
"loss": 0.
|
| 480 |
"step": 600
|
| 481 |
},
|
| 482 |
{
|
| 483 |
"epoch": 0.46153846153846156,
|
| 484 |
-
"eval_accuracy": 0.
|
| 485 |
-
"eval_f1": 0.
|
| 486 |
-
"eval_loss": 1.
|
| 487 |
-
"eval_runtime": 12.
|
| 488 |
-
"eval_samples_per_second":
|
| 489 |
-
"eval_steps_per_second": 20.
|
| 490 |
"step": 600
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 0.46923076923076923,
|
| 494 |
-
"grad_norm": 1.
|
| 495 |
-
"learning_rate": 0.
|
| 496 |
-
"loss": 0.
|
| 497 |
"step": 610
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 0.47692307692307695,
|
| 501 |
-
"grad_norm":
|
| 502 |
-
"learning_rate": 0.
|
| 503 |
-
"loss": 0.
|
| 504 |
"step": 620
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 0.4846153846153846,
|
| 508 |
-
"grad_norm":
|
| 509 |
-
"learning_rate": 0.
|
| 510 |
-
"loss": 0.
|
| 511 |
"step": 630
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 0.49230769230769234,
|
| 515 |
-
"grad_norm":
|
| 516 |
-
"learning_rate": 0.
|
| 517 |
-
"loss": 0.
|
| 518 |
"step": 640
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 0.5,
|
| 522 |
-
"grad_norm":
|
| 523 |
-
"learning_rate": 0.
|
| 524 |
-
"loss": 0.
|
| 525 |
"step": 650
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 0.5076923076923077,
|
| 529 |
-
"grad_norm":
|
| 530 |
-
"learning_rate": 0.
|
| 531 |
-
"loss": 0.
|
| 532 |
"step": 660
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 0.5153846153846153,
|
| 536 |
-
"grad_norm":
|
| 537 |
-
"learning_rate": 0.
|
| 538 |
-
"loss": 0.
|
| 539 |
"step": 670
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 0.5230769230769231,
|
| 543 |
-
"grad_norm":
|
| 544 |
-
"learning_rate": 0.
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 680
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 0.5307692307692308,
|
| 550 |
-
"grad_norm":
|
| 551 |
-
"learning_rate": 0.
|
| 552 |
-
"loss": 0.
|
| 553 |
"step": 690
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 0.5384615384615384,
|
| 557 |
-
"grad_norm":
|
| 558 |
-
"learning_rate": 0.
|
| 559 |
-
"loss": 0.
|
| 560 |
"step": 700
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 0.5384615384615384,
|
| 564 |
-
"eval_accuracy": 0.
|
| 565 |
-
"eval_f1": 0.
|
| 566 |
-
"eval_loss": 1.
|
| 567 |
-
"eval_runtime":
|
| 568 |
-
"eval_samples_per_second":
|
| 569 |
-
"eval_steps_per_second":
|
| 570 |
"step": 700
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 0.5461538461538461,
|
| 574 |
-
"grad_norm":
|
| 575 |
-
"learning_rate": 0.
|
| 576 |
-
"loss": 0.
|
| 577 |
"step": 710
|
| 578 |
},
|
| 579 |
{
|
| 580 |
"epoch": 0.5538461538461539,
|
| 581 |
-
"grad_norm": 10.
|
| 582 |
-
"learning_rate": 0.
|
| 583 |
-
"loss": 0.
|
| 584 |
"step": 720
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 0.5615384615384615,
|
| 588 |
-
"grad_norm":
|
| 589 |
-
"learning_rate": 0.
|
| 590 |
-
"loss": 0.
|
| 591 |
"step": 730
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 0.5692307692307692,
|
| 595 |
-
"grad_norm":
|
| 596 |
-
"learning_rate": 0.
|
| 597 |
-
"loss": 0.
|
| 598 |
"step": 740
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 0.5769230769230769,
|
| 602 |
-
"grad_norm": 5.
|
| 603 |
-
"learning_rate": 0.
|
| 604 |
-
"loss": 0.
|
| 605 |
"step": 750
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 0.5846153846153846,
|
| 609 |
-
"grad_norm": 3.
|
| 610 |
-
"learning_rate": 0.
|
| 611 |
-
"loss": 0.
|
| 612 |
"step": 760
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 0.5923076923076923,
|
| 616 |
-
"grad_norm":
|
| 617 |
-
"learning_rate": 0.
|
| 618 |
-
"loss": 0.
|
| 619 |
"step": 770
|
| 620 |
},
|
| 621 |
{
|
| 622 |
"epoch": 0.6,
|
| 623 |
-
"grad_norm":
|
| 624 |
-
"learning_rate": 0.
|
| 625 |
-
"loss": 0.
|
| 626 |
"step": 780
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 0.6076923076923076,
|
| 630 |
-
"grad_norm":
|
| 631 |
-
"learning_rate": 0.
|
| 632 |
-
"loss": 0.
|
| 633 |
"step": 790
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 0.6153846153846154,
|
| 637 |
-
"grad_norm":
|
| 638 |
-
"learning_rate": 0.
|
| 639 |
-
"loss": 0.
|
| 640 |
"step": 800
|
| 641 |
},
|
| 642 |
{
|
| 643 |
"epoch": 0.6153846153846154,
|
| 644 |
-
"eval_accuracy": 0.
|
| 645 |
-
"eval_f1": 0.
|
| 646 |
-
"eval_loss": 1.
|
| 647 |
-
"eval_runtime":
|
| 648 |
-
"eval_samples_per_second":
|
| 649 |
-
"eval_steps_per_second":
|
| 650 |
"step": 800
|
| 651 |
},
|
| 652 |
{
|
| 653 |
"epoch": 0.6230769230769231,
|
| 654 |
-
"grad_norm":
|
| 655 |
-
"learning_rate": 0.
|
| 656 |
-
"loss": 0.
|
| 657 |
"step": 810
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 0.6307692307692307,
|
| 661 |
-
"grad_norm":
|
| 662 |
-
"learning_rate": 0.
|
| 663 |
-
"loss": 0.
|
| 664 |
"step": 820
|
| 665 |
},
|
| 666 |
{
|
| 667 |
"epoch": 0.6384615384615384,
|
| 668 |
-
"grad_norm": 8.
|
| 669 |
-
"learning_rate": 0.
|
| 670 |
-
"loss": 0.
|
| 671 |
"step": 830
|
| 672 |
},
|
| 673 |
{
|
| 674 |
"epoch": 0.6461538461538462,
|
| 675 |
-
"grad_norm":
|
| 676 |
-
"learning_rate": 0.
|
| 677 |
-
"loss": 0.
|
| 678 |
"step": 840
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 0.6538461538461539,
|
| 682 |
-
"grad_norm":
|
| 683 |
-
"learning_rate": 0.
|
| 684 |
-
"loss": 0.
|
| 685 |
"step": 850
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 0.6615384615384615,
|
| 689 |
-
"grad_norm":
|
| 690 |
-
"learning_rate": 0.
|
| 691 |
-
"loss": 0.
|
| 692 |
"step": 860
|
| 693 |
},
|
| 694 |
{
|
| 695 |
"epoch": 0.6692307692307692,
|
| 696 |
-
"grad_norm":
|
| 697 |
-
"learning_rate": 0.
|
| 698 |
-
"loss": 0.
|
| 699 |
"step": 870
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 0.676923076923077,
|
| 703 |
-
"grad_norm":
|
| 704 |
-
"learning_rate": 0.
|
| 705 |
-
"loss": 0.
|
| 706 |
"step": 880
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"epoch": 0.6846153846153846,
|
| 710 |
-
"grad_norm":
|
| 711 |
-
"learning_rate": 0.
|
| 712 |
-
"loss": 0.
|
| 713 |
"step": 890
|
| 714 |
},
|
| 715 |
{
|
| 716 |
"epoch": 0.6923076923076923,
|
| 717 |
-
"grad_norm":
|
| 718 |
-
"learning_rate": 0.
|
| 719 |
-
"loss": 0.
|
| 720 |
"step": 900
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 0.6923076923076923,
|
| 724 |
-
"eval_accuracy": 0.
|
| 725 |
-
"eval_f1": 0.
|
| 726 |
-
"eval_loss": 1.
|
| 727 |
-
"eval_runtime":
|
| 728 |
-
"eval_samples_per_second":
|
| 729 |
-
"eval_steps_per_second":
|
| 730 |
"step": 900
|
| 731 |
},
|
| 732 |
{
|
| 733 |
"epoch": 0.7,
|
| 734 |
-
"grad_norm": 0.
|
| 735 |
-
"learning_rate": 0.
|
| 736 |
-
"loss": 0.
|
| 737 |
"step": 910
|
| 738 |
},
|
| 739 |
{
|
| 740 |
"epoch": 0.7076923076923077,
|
| 741 |
-
"grad_norm":
|
| 742 |
-
"learning_rate": 0.
|
| 743 |
-
"loss": 0.
|
| 744 |
"step": 920
|
| 745 |
},
|
| 746 |
{
|
| 747 |
"epoch": 0.7153846153846154,
|
| 748 |
-
"grad_norm": 9.
|
| 749 |
-
"learning_rate": 0.
|
| 750 |
-
"loss": 0.
|
| 751 |
"step": 930
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"epoch": 0.7230769230769231,
|
| 755 |
-
"grad_norm":
|
| 756 |
-
"learning_rate": 0.
|
| 757 |
-
"loss": 0.
|
| 758 |
"step": 940
|
| 759 |
},
|
| 760 |
{
|
| 761 |
"epoch": 0.7307692307692307,
|
| 762 |
-
"grad_norm":
|
| 763 |
-
"learning_rate": 0.
|
| 764 |
-
"loss": 0.
|
| 765 |
"step": 950
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 0.7384615384615385,
|
| 769 |
-
"grad_norm":
|
| 770 |
-
"learning_rate": 0.
|
| 771 |
-
"loss": 0.
|
| 772 |
"step": 960
|
| 773 |
},
|
| 774 |
{
|
| 775 |
"epoch": 0.7461538461538462,
|
| 776 |
-
"grad_norm": 0.
|
| 777 |
-
"learning_rate": 0.
|
| 778 |
-
"loss": 0.
|
| 779 |
"step": 970
|
| 780 |
},
|
| 781 |
{
|
| 782 |
"epoch": 0.7538461538461538,
|
| 783 |
-
"grad_norm":
|
| 784 |
-
"learning_rate": 0.
|
| 785 |
-
"loss": 0.
|
| 786 |
"step": 980
|
| 787 |
},
|
| 788 |
{
|
| 789 |
"epoch": 0.7615384615384615,
|
| 790 |
-
"grad_norm": 0.
|
| 791 |
-
"learning_rate": 0.
|
| 792 |
-
"loss": 0.
|
| 793 |
"step": 990
|
| 794 |
},
|
| 795 |
{
|
| 796 |
"epoch": 0.7692307692307693,
|
| 797 |
-
"grad_norm":
|
| 798 |
-
"learning_rate": 0.
|
| 799 |
-
"loss": 0.
|
| 800 |
"step": 1000
|
| 801 |
},
|
| 802 |
{
|
| 803 |
"epoch": 0.7692307692307693,
|
| 804 |
-
"eval_accuracy": 0.
|
| 805 |
-
"eval_f1": 0.
|
| 806 |
-
"eval_loss":
|
| 807 |
-
"eval_runtime": 13.
|
| 808 |
-
"eval_samples_per_second":
|
| 809 |
-
"eval_steps_per_second":
|
| 810 |
"step": 1000
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 0.7769230769230769,
|
| 814 |
-
"grad_norm":
|
| 815 |
-
"learning_rate": 0.
|
| 816 |
-
"loss": 0.
|
| 817 |
"step": 1010
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 0.7846153846153846,
|
| 821 |
-
"grad_norm":
|
| 822 |
-
"learning_rate": 0.
|
| 823 |
-
"loss": 0.
|
| 824 |
"step": 1020
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 0.7923076923076923,
|
| 828 |
-
"grad_norm":
|
| 829 |
-
"learning_rate": 0.
|
| 830 |
-
"loss": 0.
|
| 831 |
"step": 1030
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 0.8,
|
| 835 |
-
"grad_norm":
|
| 836 |
-
"learning_rate": 0.
|
| 837 |
-
"loss": 0.
|
| 838 |
"step": 1040
|
| 839 |
},
|
| 840 |
{
|
| 841 |
"epoch": 0.8076923076923077,
|
| 842 |
-
"grad_norm":
|
| 843 |
-
"learning_rate": 0.
|
| 844 |
-
"loss": 0.
|
| 845 |
"step": 1050
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 0.8153846153846154,
|
| 849 |
-
"grad_norm":
|
| 850 |
-
"learning_rate": 0.
|
| 851 |
-
"loss": 0.
|
| 852 |
"step": 1060
|
| 853 |
},
|
| 854 |
{
|
| 855 |
"epoch": 0.823076923076923,
|
| 856 |
-
"grad_norm":
|
| 857 |
-
"learning_rate": 0.
|
| 858 |
-
"loss": 0.
|
| 859 |
"step": 1070
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"epoch": 0.8307692307692308,
|
| 863 |
-
"grad_norm":
|
| 864 |
-
"learning_rate": 0.
|
| 865 |
-
"loss": 0.
|
| 866 |
"step": 1080
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"epoch": 0.8384615384615385,
|
| 870 |
-
"grad_norm":
|
| 871 |
-
"learning_rate": 0.
|
| 872 |
-
"loss": 0.
|
| 873 |
"step": 1090
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 0.8461538461538461,
|
| 877 |
-
"grad_norm":
|
| 878 |
-
"learning_rate": 0.
|
| 879 |
-
"loss": 0.
|
| 880 |
"step": 1100
|
| 881 |
},
|
| 882 |
{
|
| 883 |
"epoch": 0.8461538461538461,
|
| 884 |
-
"eval_accuracy": 0.
|
| 885 |
-
"eval_f1": 0.
|
| 886 |
-
"eval_loss": 0.
|
| 887 |
-
"eval_runtime": 12.
|
| 888 |
-
"eval_samples_per_second":
|
| 889 |
-
"eval_steps_per_second": 20.
|
| 890 |
"step": 1100
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 0.8538461538461538,
|
| 894 |
-
"grad_norm":
|
| 895 |
-
"learning_rate": 0.
|
| 896 |
-
"loss": 0.
|
| 897 |
"step": 1110
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 0.8615384615384616,
|
| 901 |
-
"grad_norm":
|
| 902 |
-
"learning_rate": 0.
|
| 903 |
-
"loss": 0.
|
| 904 |
"step": 1120
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"epoch": 0.8692307692307693,
|
| 908 |
-
"grad_norm":
|
| 909 |
-
"learning_rate": 0.
|
| 910 |
-
"loss": 0.
|
| 911 |
"step": 1130
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 0.8769230769230769,
|
| 915 |
-
"grad_norm": 0.
|
| 916 |
-
"learning_rate": 0.
|
| 917 |
-
"loss": 0.
|
| 918 |
"step": 1140
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 0.8846153846153846,
|
| 922 |
-
"grad_norm":
|
| 923 |
-
"learning_rate": 0.
|
| 924 |
-
"loss": 0.
|
| 925 |
"step": 1150
|
| 926 |
},
|
| 927 |
{
|
| 928 |
"epoch": 0.8923076923076924,
|
| 929 |
-
"grad_norm":
|
| 930 |
-
"learning_rate": 0.
|
| 931 |
-
"loss": 0.
|
| 932 |
"step": 1160
|
| 933 |
},
|
| 934 |
{
|
| 935 |
"epoch": 0.9,
|
| 936 |
-
"grad_norm":
|
| 937 |
-
"learning_rate": 0.
|
| 938 |
-
"loss": 0.
|
| 939 |
"step": 1170
|
| 940 |
},
|
| 941 |
{
|
| 942 |
"epoch": 0.9076923076923077,
|
| 943 |
-
"grad_norm":
|
| 944 |
-
"learning_rate": 0.
|
| 945 |
-
"loss": 0.
|
| 946 |
"step": 1180
|
| 947 |
},
|
| 948 |
{
|
| 949 |
"epoch": 0.9153846153846154,
|
| 950 |
-
"grad_norm":
|
| 951 |
-
"learning_rate": 0.
|
| 952 |
-
"loss": 0.
|
| 953 |
"step": 1190
|
| 954 |
},
|
| 955 |
{
|
| 956 |
"epoch": 0.9230769230769231,
|
| 957 |
-
"grad_norm":
|
| 958 |
-
"learning_rate": 0.
|
| 959 |
-
"loss": 0.
|
| 960 |
"step": 1200
|
| 961 |
},
|
| 962 |
{
|
| 963 |
"epoch": 0.9230769230769231,
|
| 964 |
-
"eval_accuracy": 0.
|
| 965 |
-
"eval_f1": 0.
|
| 966 |
-
"eval_loss":
|
| 967 |
-
"eval_runtime": 12.
|
| 968 |
-
"eval_samples_per_second":
|
| 969 |
-
"eval_steps_per_second": 20.
|
| 970 |
"step": 1200
|
| 971 |
},
|
| 972 |
{
|
| 973 |
"epoch": 0.9307692307692308,
|
| 974 |
-
"grad_norm": 0.
|
| 975 |
-
"learning_rate": 0.
|
| 976 |
-
"loss": 0.
|
| 977 |
"step": 1210
|
| 978 |
},
|
| 979 |
{
|
| 980 |
"epoch": 0.9384615384615385,
|
| 981 |
-
"grad_norm":
|
| 982 |
-
"learning_rate": 0.
|
| 983 |
-
"loss": 0.
|
| 984 |
"step": 1220
|
| 985 |
},
|
| 986 |
{
|
| 987 |
"epoch": 0.9461538461538461,
|
| 988 |
-
"grad_norm":
|
| 989 |
-
"learning_rate": 0.
|
| 990 |
-
"loss": 0.
|
| 991 |
"step": 1230
|
| 992 |
},
|
| 993 |
{
|
| 994 |
"epoch": 0.9538461538461539,
|
| 995 |
-
"grad_norm":
|
| 996 |
-
"learning_rate": 0.
|
| 997 |
-
"loss": 0.
|
| 998 |
"step": 1240
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 0.9615384615384616,
|
| 1002 |
-
"grad_norm":
|
| 1003 |
-
"learning_rate": 0.
|
| 1004 |
-
"loss": 0.
|
| 1005 |
"step": 1250
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 0.9692307692307692,
|
| 1009 |
-
"grad_norm":
|
| 1010 |
-
"learning_rate": 0.
|
| 1011 |
-
"loss": 0.
|
| 1012 |
"step": 1260
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
"epoch": 0.9769230769230769,
|
| 1016 |
-
"grad_norm":
|
| 1017 |
-
"learning_rate": 0.
|
| 1018 |
-
"loss": 0.
|
| 1019 |
"step": 1270
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
"epoch": 0.9846153846153847,
|
| 1023 |
-
"grad_norm":
|
| 1024 |
-
"learning_rate": 0.
|
| 1025 |
-
"loss": 0.
|
| 1026 |
"step": 1280
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
"epoch": 0.9923076923076923,
|
| 1030 |
-
"grad_norm":
|
| 1031 |
-
"learning_rate": 0.
|
| 1032 |
-
"loss": 0.
|
| 1033 |
"step": 1290
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
"epoch": 1.0,
|
| 1037 |
-
"grad_norm": 0.
|
| 1038 |
-
"learning_rate": 0.
|
| 1039 |
-
"loss": 0.
|
| 1040 |
"step": 1300
|
| 1041 |
},
|
| 1042 |
{
|
| 1043 |
"epoch": 1.0,
|
| 1044 |
-
"eval_accuracy": 0.
|
| 1045 |
-
"eval_f1": 0.
|
| 1046 |
-
"eval_loss": 1.
|
| 1047 |
-
"eval_runtime": 12.
|
| 1048 |
-
"eval_samples_per_second":
|
| 1049 |
-
"eval_steps_per_second":
|
| 1050 |
"step": 1300
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
"epoch": 1.0076923076923077,
|
| 1054 |
-
"grad_norm":
|
| 1055 |
-
"learning_rate": 0.
|
| 1056 |
-
"loss": 0.
|
| 1057 |
"step": 1310
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
"epoch": 1.0153846153846153,
|
| 1061 |
-
"grad_norm":
|
| 1062 |
-
"learning_rate": 0.
|
| 1063 |
-
"loss": 0.
|
| 1064 |
"step": 1320
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
"epoch": 1.023076923076923,
|
| 1068 |
-
"grad_norm":
|
| 1069 |
-
"learning_rate": 0.
|
| 1070 |
-
"loss": 0.
|
| 1071 |
"step": 1330
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 1.0307692307692307,
|
| 1075 |
-
"grad_norm":
|
| 1076 |
-
"learning_rate": 0.
|
| 1077 |
-
"loss": 0.
|
| 1078 |
"step": 1340
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
"epoch": 1.0384615384615385,
|
| 1082 |
-
"grad_norm":
|
| 1083 |
-
"learning_rate": 0.
|
| 1084 |
-
"loss": 0.
|
| 1085 |
"step": 1350
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 1.0461538461538462,
|
| 1089 |
-
"grad_norm": 0.
|
| 1090 |
-
"learning_rate": 0.
|
| 1091 |
-
"loss": 0.
|
| 1092 |
"step": 1360
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 1.0538461538461539,
|
| 1096 |
-
"grad_norm":
|
| 1097 |
-
"learning_rate": 0.
|
| 1098 |
-
"loss": 0.
|
| 1099 |
"step": 1370
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
"epoch": 1.0615384615384615,
|
| 1103 |
-
"grad_norm":
|
| 1104 |
-
"learning_rate": 0.
|
| 1105 |
-
"loss": 0.
|
| 1106 |
"step": 1380
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 1.0692307692307692,
|
| 1110 |
-
"grad_norm":
|
| 1111 |
-
"learning_rate": 0.
|
| 1112 |
-
"loss": 0.
|
| 1113 |
"step": 1390
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 1.0769230769230769,
|
| 1117 |
-
"grad_norm":
|
| 1118 |
-
"learning_rate": 0.
|
| 1119 |
-
"loss": 0.
|
| 1120 |
"step": 1400
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 1.0769230769230769,
|
| 1124 |
-
"eval_accuracy": 0.
|
| 1125 |
-
"eval_f1": 0.
|
| 1126 |
-
"eval_loss": 1.
|
| 1127 |
-
"eval_runtime": 12.
|
| 1128 |
-
"eval_samples_per_second": 166.
|
| 1129 |
-
"eval_steps_per_second": 20.
|
| 1130 |
"step": 1400
|
| 1131 |
},
|
| 1132 |
{
|
| 1133 |
"epoch": 1.0846153846153845,
|
| 1134 |
-
"grad_norm":
|
| 1135 |
-
"learning_rate": 0.
|
| 1136 |
-
"loss": 0.
|
| 1137 |
"step": 1410
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"epoch": 1.0923076923076924,
|
| 1141 |
-
"grad_norm": 6.
|
| 1142 |
-
"learning_rate": 0.
|
| 1143 |
-
"loss": 0.
|
| 1144 |
"step": 1420
|
| 1145 |
},
|
| 1146 |
{
|
| 1147 |
"epoch": 1.1,
|
| 1148 |
-
"grad_norm":
|
| 1149 |
-
"learning_rate": 0.
|
| 1150 |
-
"loss": 0.
|
| 1151 |
"step": 1430
|
| 1152 |
},
|
| 1153 |
{
|
| 1154 |
"epoch": 1.1076923076923078,
|
| 1155 |
-
"grad_norm": 0.
|
| 1156 |
-
"learning_rate": 0.
|
| 1157 |
-
"loss": 0.
|
| 1158 |
"step": 1440
|
| 1159 |
},
|
| 1160 |
{
|
| 1161 |
"epoch": 1.1153846153846154,
|
| 1162 |
-
"grad_norm":
|
| 1163 |
-
"learning_rate": 0.
|
| 1164 |
-
"loss": 0.
|
| 1165 |
"step": 1450
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
"epoch": 1.123076923076923,
|
| 1169 |
-
"grad_norm":
|
| 1170 |
-
"learning_rate": 0.
|
| 1171 |
-
"loss": 0.
|
| 1172 |
"step": 1460
|
| 1173 |
},
|
| 1174 |
{
|
| 1175 |
"epoch": 1.1307692307692307,
|
| 1176 |
-
"grad_norm":
|
| 1177 |
-
"learning_rate": 0.
|
| 1178 |
-
"loss": 0.
|
| 1179 |
"step": 1470
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
"epoch": 1.1384615384615384,
|
| 1183 |
-
"grad_norm":
|
| 1184 |
-
"learning_rate": 0.
|
| 1185 |
-
"loss": 0.
|
| 1186 |
"step": 1480
|
| 1187 |
},
|
| 1188 |
{
|
| 1189 |
"epoch": 1.146153846153846,
|
| 1190 |
-
"grad_norm":
|
| 1191 |
-
"learning_rate": 0.
|
| 1192 |
-
"loss": 0.
|
| 1193 |
"step": 1490
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
"epoch": 1.1538461538461537,
|
| 1197 |
-
"grad_norm": 0.
|
| 1198 |
-
"learning_rate": 0.
|
| 1199 |
-
"loss": 0.
|
| 1200 |
"step": 1500
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 1.1538461538461537,
|
| 1204 |
-
"eval_accuracy": 0.
|
| 1205 |
-
"eval_f1": 0.
|
| 1206 |
-
"eval_loss": 1.
|
| 1207 |
-
"eval_runtime": 12.
|
| 1208 |
-
"eval_samples_per_second":
|
| 1209 |
-
"eval_steps_per_second": 20.
|
| 1210 |
"step": 1500
|
| 1211 |
},
|
| 1212 |
{
|
| 1213 |
"epoch": 1.1615384615384616,
|
| 1214 |
-
"grad_norm": 0.
|
| 1215 |
-
"learning_rate": 0.
|
| 1216 |
-
"loss": 0.
|
| 1217 |
"step": 1510
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
"epoch": 1.1692307692307693,
|
| 1221 |
-
"grad_norm":
|
| 1222 |
-
"learning_rate": 0.
|
| 1223 |
-
"loss": 0.
|
| 1224 |
"step": 1520
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
"epoch": 1.176923076923077,
|
| 1228 |
-
"grad_norm":
|
| 1229 |
-
"learning_rate": 0.
|
| 1230 |
-
"loss": 0.
|
| 1231 |
"step": 1530
|
| 1232 |
},
|
| 1233 |
{
|
| 1234 |
"epoch": 1.1846153846153846,
|
| 1235 |
-
"grad_norm":
|
| 1236 |
-
"learning_rate": 0.
|
| 1237 |
-
"loss": 0.
|
| 1238 |
"step": 1540
|
| 1239 |
},
|
| 1240 |
{
|
| 1241 |
"epoch": 1.1923076923076923,
|
| 1242 |
-
"grad_norm":
|
| 1243 |
-
"learning_rate": 0.
|
| 1244 |
-
"loss": 0.
|
| 1245 |
"step": 1550
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
"epoch": 1.2,
|
| 1249 |
-
"grad_norm": 0.
|
| 1250 |
-
"learning_rate": 0.
|
| 1251 |
-
"loss": 0.
|
| 1252 |
"step": 1560
|
| 1253 |
},
|
| 1254 |
{
|
| 1255 |
"epoch": 1.2076923076923076,
|
| 1256 |
-
"grad_norm":
|
| 1257 |
-
"learning_rate": 0.
|
| 1258 |
-
"loss": 0.
|
| 1259 |
"step": 1570
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 1.2153846153846155,
|
| 1263 |
-
"grad_norm":
|
| 1264 |
-
"learning_rate": 0.
|
| 1265 |
-
"loss": 0.
|
| 1266 |
"step": 1580
|
| 1267 |
},
|
| 1268 |
{
|
| 1269 |
"epoch": 1.2230769230769232,
|
| 1270 |
-
"grad_norm": 0.
|
| 1271 |
-
"learning_rate": 0.
|
| 1272 |
-
"loss": 0.
|
| 1273 |
"step": 1590
|
| 1274 |
},
|
| 1275 |
{
|
| 1276 |
"epoch": 1.2307692307692308,
|
| 1277 |
-
"grad_norm":
|
| 1278 |
-
"learning_rate": 0.
|
| 1279 |
-
"loss": 0.
|
| 1280 |
"step": 1600
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
"epoch": 1.2307692307692308,
|
| 1284 |
-
"eval_accuracy": 0.
|
| 1285 |
-
"eval_f1": 0.
|
| 1286 |
-
"eval_loss":
|
| 1287 |
-
"eval_runtime": 12.
|
| 1288 |
-
"eval_samples_per_second":
|
| 1289 |
-
"eval_steps_per_second":
|
| 1290 |
"step": 1600
|
| 1291 |
},
|
| 1292 |
{
|
| 1293 |
"epoch": 1.2384615384615385,
|
| 1294 |
-
"grad_norm": 0.
|
| 1295 |
-
"learning_rate": 0.
|
| 1296 |
-
"loss": 0.
|
| 1297 |
"step": 1610
|
| 1298 |
},
|
| 1299 |
{
|
| 1300 |
"epoch": 1.2461538461538462,
|
| 1301 |
-
"grad_norm": 0.
|
| 1302 |
-
"learning_rate": 0.
|
| 1303 |
-
"loss": 0.
|
| 1304 |
"step": 1620
|
| 1305 |
},
|
| 1306 |
{
|
| 1307 |
"epoch": 1.2538461538461538,
|
| 1308 |
-
"grad_norm": 0.
|
| 1309 |
-
"learning_rate": 0.
|
| 1310 |
-
"loss": 0.
|
| 1311 |
"step": 1630
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
"epoch": 1.2615384615384615,
|
| 1315 |
-
"grad_norm": 0.
|
| 1316 |
-
"learning_rate": 0.
|
| 1317 |
-
"loss": 0.
|
| 1318 |
"step": 1640
|
| 1319 |
},
|
| 1320 |
{
|
| 1321 |
"epoch": 1.2692307692307692,
|
| 1322 |
-
"grad_norm":
|
| 1323 |
-
"learning_rate": 0.
|
| 1324 |
-
"loss": 0.
|
| 1325 |
"step": 1650
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
"epoch": 1.2769230769230768,
|
| 1329 |
-
"grad_norm": 11.
|
| 1330 |
-
"learning_rate": 0.
|
| 1331 |
-
"loss": 0.
|
| 1332 |
"step": 1660
|
| 1333 |
},
|
| 1334 |
{
|
| 1335 |
"epoch": 1.2846153846153845,
|
| 1336 |
-
"grad_norm": 0.
|
| 1337 |
-
"learning_rate": 0.
|
| 1338 |
-
"loss": 0.
|
| 1339 |
"step": 1670
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
"epoch": 1.2923076923076924,
|
| 1343 |
-
"grad_norm":
|
| 1344 |
-
"learning_rate": 0.
|
| 1345 |
-
"loss": 0.
|
| 1346 |
"step": 1680
|
| 1347 |
},
|
| 1348 |
{
|
| 1349 |
"epoch": 1.3,
|
| 1350 |
-
"grad_norm":
|
| 1351 |
-
"learning_rate": 0.
|
| 1352 |
-
"loss": 0.
|
| 1353 |
"step": 1690
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 1.3076923076923077,
|
| 1357 |
-
"grad_norm": 0.
|
| 1358 |
-
"learning_rate": 0.
|
| 1359 |
-
"loss": 0.
|
| 1360 |
"step": 1700
|
| 1361 |
},
|
| 1362 |
{
|
| 1363 |
"epoch": 1.3076923076923077,
|
| 1364 |
-
"eval_accuracy": 0.
|
| 1365 |
-
"eval_f1": 0.
|
| 1366 |
-
"eval_loss": 0.
|
| 1367 |
-
"eval_runtime":
|
| 1368 |
-
"eval_samples_per_second":
|
| 1369 |
-
"eval_steps_per_second":
|
| 1370 |
"step": 1700
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 1.3153846153846154,
|
| 1374 |
-
"grad_norm": 2.
|
| 1375 |
-
"learning_rate": 0.
|
| 1376 |
-
"loss": 0.
|
| 1377 |
"step": 1710
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 1.323076923076923,
|
| 1381 |
-
"grad_norm": 0.
|
| 1382 |
-
"learning_rate": 0.
|
| 1383 |
-
"loss": 0.
|
| 1384 |
"step": 1720
|
| 1385 |
},
|
| 1386 |
{
|
| 1387 |
"epoch": 1.3307692307692307,
|
| 1388 |
-
"grad_norm":
|
| 1389 |
-
"learning_rate": 0.
|
| 1390 |
-
"loss": 0.
|
| 1391 |
"step": 1730
|
| 1392 |
},
|
| 1393 |
{
|
| 1394 |
"epoch": 1.3384615384615386,
|
| 1395 |
-
"grad_norm":
|
| 1396 |
-
"learning_rate": 0.
|
| 1397 |
-
"loss": 0.
|
| 1398 |
"step": 1740
|
| 1399 |
},
|
| 1400 |
{
|
| 1401 |
"epoch": 1.3461538461538463,
|
| 1402 |
-
"grad_norm":
|
| 1403 |
-
"learning_rate": 0.
|
| 1404 |
-
"loss": 0.
|
| 1405 |
"step": 1750
|
| 1406 |
},
|
| 1407 |
{
|
| 1408 |
"epoch": 1.353846153846154,
|
| 1409 |
-
"grad_norm":
|
| 1410 |
-
"learning_rate": 0.
|
| 1411 |
-
"loss": 0.
|
| 1412 |
"step": 1760
|
| 1413 |
},
|
| 1414 |
{
|
| 1415 |
"epoch": 1.3615384615384616,
|
| 1416 |
-
"grad_norm":
|
| 1417 |
-
"learning_rate": 0.
|
| 1418 |
-
"loss": 0.
|
| 1419 |
"step": 1770
|
| 1420 |
},
|
| 1421 |
{
|
| 1422 |
"epoch": 1.3692307692307693,
|
| 1423 |
-
"grad_norm": 0.
|
| 1424 |
-
"learning_rate": 0.
|
| 1425 |
-
"loss": 0.
|
| 1426 |
"step": 1780
|
| 1427 |
},
|
| 1428 |
{
|
| 1429 |
"epoch": 1.376923076923077,
|
| 1430 |
-
"grad_norm":
|
| 1431 |
-
"learning_rate": 0.
|
| 1432 |
-
"loss": 0.
|
| 1433 |
"step": 1790
|
| 1434 |
},
|
| 1435 |
{
|
| 1436 |
"epoch": 1.3846153846153846,
|
| 1437 |
-
"grad_norm": 1.
|
| 1438 |
-
"learning_rate": 0.
|
| 1439 |
-
"loss": 0.
|
| 1440 |
"step": 1800
|
| 1441 |
},
|
| 1442 |
{
|
| 1443 |
"epoch": 1.3846153846153846,
|
| 1444 |
-
"eval_accuracy": 0.
|
| 1445 |
-
"eval_f1": 0.
|
| 1446 |
-
"eval_loss": 1.
|
| 1447 |
-
"eval_runtime":
|
| 1448 |
-
"eval_samples_per_second":
|
| 1449 |
-
"eval_steps_per_second": 20.
|
| 1450 |
"step": 1800
|
| 1451 |
},
|
| 1452 |
{
|
| 1453 |
"epoch": 1.3923076923076922,
|
| 1454 |
-
"grad_norm":
|
| 1455 |
-
"learning_rate": 0.
|
| 1456 |
-
"loss": 0.
|
| 1457 |
"step": 1810
|
| 1458 |
},
|
| 1459 |
{
|
| 1460 |
"epoch": 1.4,
|
| 1461 |
-
"grad_norm": 0.
|
| 1462 |
-
"learning_rate": 0.
|
| 1463 |
-
"loss": 0.
|
| 1464 |
"step": 1820
|
| 1465 |
},
|
| 1466 |
{
|
| 1467 |
"epoch": 1.4076923076923076,
|
| 1468 |
-
"grad_norm":
|
| 1469 |
-
"learning_rate": 0.
|
| 1470 |
-
"loss": 0.
|
| 1471 |
"step": 1830
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 1.4153846153846155,
|
| 1475 |
-
"grad_norm":
|
| 1476 |
-
"learning_rate": 0.
|
| 1477 |
-
"loss": 0.
|
| 1478 |
"step": 1840
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
"epoch": 1.4230769230769231,
|
| 1482 |
-
"grad_norm":
|
| 1483 |
-
"learning_rate": 0.
|
| 1484 |
-
"loss": 0.
|
| 1485 |
"step": 1850
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
"epoch": 1.4307692307692308,
|
| 1489 |
-
"grad_norm": 0.
|
| 1490 |
-
"learning_rate": 0.
|
| 1491 |
-
"loss": 0.
|
| 1492 |
"step": 1860
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
"epoch": 1.4384615384615385,
|
| 1496 |
-
"grad_norm": 0.
|
| 1497 |
-
"learning_rate": 0.
|
| 1498 |
-
"loss": 0.
|
| 1499 |
"step": 1870
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
"epoch": 1.4461538461538461,
|
| 1503 |
-
"grad_norm":
|
| 1504 |
-
"learning_rate": 0.
|
| 1505 |
-
"loss": 0.
|
| 1506 |
"step": 1880
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
"epoch": 1.4538461538461538,
|
| 1510 |
-
"grad_norm": 14.
|
| 1511 |
-
"learning_rate": 0.
|
| 1512 |
-
"loss": 0.
|
| 1513 |
"step": 1890
|
| 1514 |
},
|
| 1515 |
{
|
| 1516 |
"epoch": 1.4615384615384617,
|
| 1517 |
-
"grad_norm": 0.
|
| 1518 |
-
"learning_rate": 0.
|
| 1519 |
-
"loss": 0.
|
| 1520 |
"step": 1900
|
| 1521 |
},
|
| 1522 |
{
|
| 1523 |
"epoch": 1.4615384615384617,
|
| 1524 |
-
"eval_accuracy": 0.
|
| 1525 |
-
"eval_f1": 0.
|
| 1526 |
-
"eval_loss": 1.
|
| 1527 |
-
"eval_runtime":
|
| 1528 |
-
"eval_samples_per_second":
|
| 1529 |
-
"eval_steps_per_second":
|
| 1530 |
"step": 1900
|
| 1531 |
},
|
| 1532 |
{
|
| 1533 |
"epoch": 1.4692307692307693,
|
| 1534 |
-
"grad_norm": 0.
|
| 1535 |
-
"learning_rate": 0.
|
| 1536 |
-
"loss": 0.
|
| 1537 |
"step": 1910
|
| 1538 |
},
|
| 1539 |
{
|
| 1540 |
"epoch": 1.476923076923077,
|
| 1541 |
-
"grad_norm": 0.
|
| 1542 |
-
"learning_rate": 0.
|
| 1543 |
-
"loss": 0.
|
| 1544 |
"step": 1920
|
| 1545 |
},
|
| 1546 |
{
|
| 1547 |
"epoch": 1.4846153846153847,
|
| 1548 |
-
"grad_norm":
|
| 1549 |
-
"learning_rate": 0.
|
| 1550 |
-
"loss": 0.
|
| 1551 |
"step": 1930
|
| 1552 |
},
|
| 1553 |
{
|
| 1554 |
"epoch": 1.4923076923076923,
|
| 1555 |
-
"grad_norm": 6.
|
| 1556 |
-
"learning_rate": 0.
|
| 1557 |
-
"loss": 0.
|
| 1558 |
"step": 1940
|
| 1559 |
},
|
| 1560 |
{
|
| 1561 |
"epoch": 1.5,
|
| 1562 |
-
"grad_norm":
|
| 1563 |
-
"learning_rate": 0.
|
| 1564 |
-
"loss": 0.
|
| 1565 |
"step": 1950
|
| 1566 |
},
|
| 1567 |
{
|
| 1568 |
"epoch": 1.5076923076923077,
|
| 1569 |
-
"grad_norm":
|
| 1570 |
-
"learning_rate": 0.
|
| 1571 |
-
"loss": 0.
|
| 1572 |
"step": 1960
|
| 1573 |
},
|
| 1574 |
{
|
| 1575 |
"epoch": 1.5153846153846153,
|
| 1576 |
-
"grad_norm":
|
| 1577 |
-
"learning_rate": 0.
|
| 1578 |
-
"loss": 0.
|
| 1579 |
"step": 1970
|
| 1580 |
},
|
| 1581 |
{
|
| 1582 |
"epoch": 1.523076923076923,
|
| 1583 |
-
"grad_norm": 13.
|
| 1584 |
-
"learning_rate": 0.
|
| 1585 |
-
"loss": 0.
|
| 1586 |
"step": 1980
|
| 1587 |
},
|
| 1588 |
{
|
| 1589 |
"epoch": 1.5307692307692307,
|
| 1590 |
-
"grad_norm": 0.
|
| 1591 |
-
"learning_rate": 0.
|
| 1592 |
-
"loss": 0.
|
| 1593 |
"step": 1990
|
| 1594 |
},
|
| 1595 |
{
|
| 1596 |
"epoch": 1.5384615384615383,
|
| 1597 |
-
"grad_norm": 0.
|
| 1598 |
-
"learning_rate": 0.
|
| 1599 |
-
"loss": 0.
|
| 1600 |
"step": 2000
|
| 1601 |
},
|
| 1602 |
{
|
| 1603 |
"epoch": 1.5384615384615383,
|
| 1604 |
-
"eval_accuracy": 0.
|
| 1605 |
-
"eval_f1": 0.
|
| 1606 |
-
"eval_loss": 1.
|
| 1607 |
-
"eval_runtime": 12.
|
| 1608 |
-
"eval_samples_per_second":
|
| 1609 |
-
"eval_steps_per_second": 20.
|
| 1610 |
"step": 2000
|
| 1611 |
},
|
| 1612 |
{
|
| 1613 |
"epoch": 1.546153846153846,
|
| 1614 |
-
"grad_norm": 0.
|
| 1615 |
-
"learning_rate": 0.
|
| 1616 |
-
"loss": 0.
|
| 1617 |
"step": 2010
|
| 1618 |
},
|
| 1619 |
{
|
| 1620 |
"epoch": 1.5538461538461539,
|
| 1621 |
-
"grad_norm": 0.
|
| 1622 |
-
"learning_rate": 0.
|
| 1623 |
-
"loss": 0.
|
| 1624 |
"step": 2020
|
| 1625 |
},
|
| 1626 |
{
|
| 1627 |
"epoch": 1.5615384615384615,
|
| 1628 |
-
"grad_norm": 0.
|
| 1629 |
-
"learning_rate": 0.
|
| 1630 |
-
"loss": 0.
|
| 1631 |
"step": 2030
|
| 1632 |
},
|
| 1633 |
{
|
| 1634 |
"epoch": 1.5692307692307692,
|
| 1635 |
-
"grad_norm": 0.
|
| 1636 |
"learning_rate": 0.00013732307692307694,
|
| 1637 |
-
"loss": 0.
|
| 1638 |
"step": 2040
|
| 1639 |
},
|
| 1640 |
{
|
| 1641 |
"epoch": 1.5769230769230769,
|
| 1642 |
-
"grad_norm": 0.
|
| 1643 |
"learning_rate": 0.00013701538461538461,
|
| 1644 |
-
"loss": 0.
|
| 1645 |
"step": 2050
|
| 1646 |
},
|
| 1647 |
{
|
| 1648 |
"epoch": 1.5846153846153848,
|
| 1649 |
-
"grad_norm": 0.
|
| 1650 |
"learning_rate": 0.0001367076923076923,
|
| 1651 |
-
"loss": 0.
|
| 1652 |
"step": 2060
|
| 1653 |
},
|
| 1654 |
{
|
| 1655 |
"epoch": 1.5923076923076924,
|
| 1656 |
-
"grad_norm": 0.
|
| 1657 |
"learning_rate": 0.0001364,
|
| 1658 |
-
"loss": 0.
|
| 1659 |
"step": 2070
|
| 1660 |
},
|
| 1661 |
{
|
| 1662 |
"epoch": 1.6,
|
| 1663 |
-
"grad_norm": 0.
|
| 1664 |
"learning_rate": 0.0001360923076923077,
|
| 1665 |
-
"loss": 0.
|
| 1666 |
"step": 2080
|
| 1667 |
},
|
| 1668 |
{
|
| 1669 |
"epoch": 1.6076923076923078,
|
| 1670 |
-
"grad_norm":
|
| 1671 |
"learning_rate": 0.0001357846153846154,
|
| 1672 |
-
"loss": 0.
|
| 1673 |
"step": 2090
|
| 1674 |
},
|
| 1675 |
{
|
| 1676 |
"epoch": 1.6153846153846154,
|
| 1677 |
-
"grad_norm":
|
| 1678 |
"learning_rate": 0.00013547692307692307,
|
| 1679 |
-
"loss": 0.
|
| 1680 |
"step": 2100
|
| 1681 |
},
|
| 1682 |
{
|
| 1683 |
"epoch": 1.6153846153846154,
|
| 1684 |
-
"eval_accuracy": 0.
|
| 1685 |
-
"eval_f1": 0.
|
| 1686 |
-
"eval_loss": 1.
|
| 1687 |
-
"eval_runtime": 12.
|
| 1688 |
-
"eval_samples_per_second":
|
| 1689 |
-
"eval_steps_per_second": 20.
|
| 1690 |
"step": 2100
|
| 1691 |
},
|
| 1692 |
{
|
| 1693 |
"epoch": 1.623076923076923,
|
| 1694 |
-
"grad_norm": 0.
|
| 1695 |
"learning_rate": 0.00013516923076923077,
|
| 1696 |
-
"loss": 0.
|
| 1697 |
"step": 2110
|
| 1698 |
},
|
| 1699 |
{
|
| 1700 |
"epoch": 1.6307692307692307,
|
| 1701 |
-
"grad_norm": 0.
|
| 1702 |
"learning_rate": 0.00013486153846153847,
|
| 1703 |
-
"loss": 0.
|
| 1704 |
"step": 2120
|
| 1705 |
},
|
| 1706 |
{
|
| 1707 |
"epoch": 1.6384615384615384,
|
| 1708 |
-
"grad_norm": 0.
|
| 1709 |
"learning_rate": 0.00013455384615384617,
|
| 1710 |
-
"loss": 0.
|
| 1711 |
"step": 2130
|
| 1712 |
},
|
| 1713 |
{
|
| 1714 |
"epoch": 1.646153846153846,
|
| 1715 |
-
"grad_norm": 0.
|
| 1716 |
"learning_rate": 0.00013424615384615384,
|
| 1717 |
-
"loss": 0.
|
| 1718 |
"step": 2140
|
| 1719 |
},
|
| 1720 |
{
|
| 1721 |
"epoch": 1.6538461538461537,
|
| 1722 |
-
"grad_norm":
|
| 1723 |
"learning_rate": 0.00013393846153846153,
|
| 1724 |
-
"loss": 0.
|
| 1725 |
"step": 2150
|
| 1726 |
},
|
| 1727 |
{
|
| 1728 |
"epoch": 1.6615384615384614,
|
| 1729 |
-
"grad_norm":
|
| 1730 |
"learning_rate": 0.00013363076923076926,
|
| 1731 |
-
"loss": 0.
|
| 1732 |
"step": 2160
|
| 1733 |
},
|
| 1734 |
{
|
| 1735 |
"epoch": 1.669230769230769,
|
| 1736 |
-
"grad_norm":
|
| 1737 |
"learning_rate": 0.00013332307692307693,
|
| 1738 |
-
"loss": 0.
|
| 1739 |
"step": 2170
|
| 1740 |
},
|
| 1741 |
{
|
| 1742 |
"epoch": 1.676923076923077,
|
| 1743 |
-
"grad_norm":
|
| 1744 |
"learning_rate": 0.00013301538461538463,
|
| 1745 |
-
"loss": 0.
|
| 1746 |
"step": 2180
|
| 1747 |
},
|
| 1748 |
{
|
| 1749 |
"epoch": 1.6846153846153846,
|
| 1750 |
-
"grad_norm": 0.
|
| 1751 |
"learning_rate": 0.00013270769230769232,
|
| 1752 |
-
"loss": 0.
|
| 1753 |
"step": 2190
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
"epoch": 1.6923076923076923,
|
| 1757 |
-
"grad_norm":
|
| 1758 |
"learning_rate": 0.00013240000000000002,
|
| 1759 |
-
"loss": 0.
|
| 1760 |
"step": 2200
|
| 1761 |
},
|
| 1762 |
{
|
| 1763 |
"epoch": 1.6923076923076923,
|
| 1764 |
-
"eval_accuracy": 0.
|
| 1765 |
-
"eval_f1": 0.
|
| 1766 |
-
"eval_loss":
|
| 1767 |
-
"eval_runtime": 12.
|
| 1768 |
-
"eval_samples_per_second":
|
| 1769 |
-
"eval_steps_per_second":
|
| 1770 |
"step": 2200
|
| 1771 |
},
|
| 1772 |
{
|
| 1773 |
-
"epoch": 1.
|
| 1774 |
-
"
|
| 1775 |
-
"
|
| 1776 |
-
"
|
| 1777 |
-
"
|
| 1778 |
-
|
| 1779 |
-
|
| 1780 |
-
"epoch": 1.7076923076923078,
|
| 1781 |
-
"grad_norm": 0.1556902378797531,
|
| 1782 |
-
"learning_rate": 0.0001317846153846154,
|
| 1783 |
-
"loss": 0.0158,
|
| 1784 |
-
"step": 2220
|
| 1785 |
-
},
|
| 1786 |
-
{
|
| 1787 |
-
"epoch": 1.7153846153846155,
|
| 1788 |
-
"grad_norm": 7.362657070159912,
|
| 1789 |
-
"learning_rate": 0.00013147692307692308,
|
| 1790 |
-
"loss": 0.294,
|
| 1791 |
-
"step": 2230
|
| 1792 |
-
},
|
| 1793 |
-
{
|
| 1794 |
-
"epoch": 1.7230769230769232,
|
| 1795 |
-
"grad_norm": 0.4276955723762512,
|
| 1796 |
-
"learning_rate": 0.00013116923076923078,
|
| 1797 |
-
"loss": 0.1368,
|
| 1798 |
-
"step": 2240
|
| 1799 |
-
},
|
| 1800 |
-
{
|
| 1801 |
-
"epoch": 1.7307692307692308,
|
| 1802 |
-
"grad_norm": 7.7706427574157715,
|
| 1803 |
-
"learning_rate": 0.00013086153846153845,
|
| 1804 |
-
"loss": 0.0855,
|
| 1805 |
-
"step": 2250
|
| 1806 |
-
},
|
| 1807 |
-
{
|
| 1808 |
-
"epoch": 1.7384615384615385,
|
| 1809 |
-
"grad_norm": 0.010043763555586338,
|
| 1810 |
-
"learning_rate": 0.00013055384615384615,
|
| 1811 |
-
"loss": 0.1108,
|
| 1812 |
-
"step": 2260
|
| 1813 |
-
},
|
| 1814 |
-
{
|
| 1815 |
-
"epoch": 1.7461538461538462,
|
| 1816 |
-
"grad_norm": 0.09377148002386093,
|
| 1817 |
-
"learning_rate": 0.00013024615384615387,
|
| 1818 |
-
"loss": 0.3113,
|
| 1819 |
-
"step": 2270
|
| 1820 |
-
},
|
| 1821 |
-
{
|
| 1822 |
-
"epoch": 1.7538461538461538,
|
| 1823 |
-
"grad_norm": 3.6055455207824707,
|
| 1824 |
-
"learning_rate": 0.00012993846153846154,
|
| 1825 |
-
"loss": 0.128,
|
| 1826 |
-
"step": 2280
|
| 1827 |
-
},
|
| 1828 |
-
{
|
| 1829 |
-
"epoch": 1.7615384615384615,
|
| 1830 |
-
"grad_norm": 2.1152894496917725,
|
| 1831 |
-
"learning_rate": 0.00012963076923076924,
|
| 1832 |
-
"loss": 0.1954,
|
| 1833 |
-
"step": 2290
|
| 1834 |
-
},
|
| 1835 |
-
{
|
| 1836 |
-
"epoch": 1.7692307692307692,
|
| 1837 |
-
"grad_norm": 0.0025315466336905956,
|
| 1838 |
-
"learning_rate": 0.0001293230769230769,
|
| 1839 |
-
"loss": 0.1457,
|
| 1840 |
-
"step": 2300
|
| 1841 |
-
},
|
| 1842 |
-
{
|
| 1843 |
-
"epoch": 1.7692307692307692,
|
| 1844 |
-
"eval_accuracy": 0.7841179267712791,
|
| 1845 |
-
"eval_f1": 0.8178538109762332,
|
| 1846 |
-
"eval_loss": 1.0606149435043335,
|
| 1847 |
-
"eval_runtime": 12.6141,
|
| 1848 |
-
"eval_samples_per_second": 166.718,
|
| 1849 |
-
"eval_steps_per_second": 20.85,
|
| 1850 |
-
"step": 2300
|
| 1851 |
-
},
|
| 1852 |
-
{
|
| 1853 |
-
"epoch": 1.7769230769230768,
|
| 1854 |
-
"grad_norm": 0.02707645110785961,
|
| 1855 |
-
"learning_rate": 0.00012901538461538464,
|
| 1856 |
-
"loss": 0.0758,
|
| 1857 |
-
"step": 2310
|
| 1858 |
-
},
|
| 1859 |
-
{
|
| 1860 |
-
"epoch": 1.7846153846153845,
|
| 1861 |
-
"grad_norm": 0.06029946357011795,
|
| 1862 |
-
"learning_rate": 0.0001287076923076923,
|
| 1863 |
-
"loss": 0.1275,
|
| 1864 |
-
"step": 2320
|
| 1865 |
-
},
|
| 1866 |
-
{
|
| 1867 |
-
"epoch": 1.7923076923076922,
|
| 1868 |
-
"grad_norm": 0.21329770982265472,
|
| 1869 |
-
"learning_rate": 0.0001284,
|
| 1870 |
-
"loss": 0.0112,
|
| 1871 |
-
"step": 2330
|
| 1872 |
-
},
|
| 1873 |
-
{
|
| 1874 |
-
"epoch": 1.8,
|
| 1875 |
-
"grad_norm": 0.9335693120956421,
|
| 1876 |
-
"learning_rate": 0.0001280923076923077,
|
| 1877 |
-
"loss": 0.2588,
|
| 1878 |
-
"step": 2340
|
| 1879 |
-
},
|
| 1880 |
-
{
|
| 1881 |
-
"epoch": 1.8076923076923077,
|
| 1882 |
-
"grad_norm": 6.8204474449157715,
|
| 1883 |
-
"learning_rate": 0.0001277846153846154,
|
| 1884 |
-
"loss": 0.1611,
|
| 1885 |
-
"step": 2350
|
| 1886 |
-
},
|
| 1887 |
-
{
|
| 1888 |
-
"epoch": 1.8153846153846154,
|
| 1889 |
-
"grad_norm": 0.023739751428365707,
|
| 1890 |
-
"learning_rate": 0.0001274769230769231,
|
| 1891 |
-
"loss": 0.0495,
|
| 1892 |
-
"step": 2360
|
| 1893 |
-
},
|
| 1894 |
-
{
|
| 1895 |
-
"epoch": 1.823076923076923,
|
| 1896 |
-
"grad_norm": 15.699667930603027,
|
| 1897 |
-
"learning_rate": 0.00012716923076923077,
|
| 1898 |
-
"loss": 0.1245,
|
| 1899 |
-
"step": 2370
|
| 1900 |
-
},
|
| 1901 |
-
{
|
| 1902 |
-
"epoch": 1.830769230769231,
|
| 1903 |
-
"grad_norm": 0.019991083070635796,
|
| 1904 |
-
"learning_rate": 0.00012686153846153846,
|
| 1905 |
-
"loss": 0.0221,
|
| 1906 |
-
"step": 2380
|
| 1907 |
-
},
|
| 1908 |
-
{
|
| 1909 |
-
"epoch": 1.8384615384615386,
|
| 1910 |
-
"grad_norm": 0.24979303777217865,
|
| 1911 |
-
"learning_rate": 0.00012655384615384616,
|
| 1912 |
-
"loss": 0.1426,
|
| 1913 |
-
"step": 2390
|
| 1914 |
-
},
|
| 1915 |
-
{
|
| 1916 |
-
"epoch": 1.8461538461538463,
|
| 1917 |
-
"grad_norm": 0.05418672040104866,
|
| 1918 |
-
"learning_rate": 0.00012624615384615386,
|
| 1919 |
-
"loss": 0.1211,
|
| 1920 |
-
"step": 2400
|
| 1921 |
-
},
|
| 1922 |
-
{
|
| 1923 |
-
"epoch": 1.8461538461538463,
|
| 1924 |
-
"eval_accuracy": 0.8145506419400856,
|
| 1925 |
-
"eval_f1": 0.8214275708995336,
|
| 1926 |
-
"eval_loss": 0.933445394039154,
|
| 1927 |
-
"eval_runtime": 12.5308,
|
| 1928 |
-
"eval_samples_per_second": 167.826,
|
| 1929 |
-
"eval_steps_per_second": 20.988,
|
| 1930 |
-
"step": 2400
|
| 1931 |
-
},
|
| 1932 |
-
{
|
| 1933 |
-
"epoch": 1.853846153846154,
|
| 1934 |
-
"grad_norm": 0.018888354301452637,
|
| 1935 |
-
"learning_rate": 0.00012593846153846153,
|
| 1936 |
-
"loss": 0.0065,
|
| 1937 |
-
"step": 2410
|
| 1938 |
-
},
|
| 1939 |
-
{
|
| 1940 |
-
"epoch": 1.8615384615384616,
|
| 1941 |
-
"grad_norm": 0.14981931447982788,
|
| 1942 |
-
"learning_rate": 0.00012563076923076925,
|
| 1943 |
-
"loss": 0.0036,
|
| 1944 |
-
"step": 2420
|
| 1945 |
-
},
|
| 1946 |
-
{
|
| 1947 |
-
"epoch": 1.8692307692307693,
|
| 1948 |
-
"grad_norm": 0.1521558165550232,
|
| 1949 |
-
"learning_rate": 0.00012532307692307692,
|
| 1950 |
-
"loss": 0.0123,
|
| 1951 |
-
"step": 2430
|
| 1952 |
-
},
|
| 1953 |
-
{
|
| 1954 |
-
"epoch": 1.876923076923077,
|
| 1955 |
-
"grad_norm": 0.6288071870803833,
|
| 1956 |
-
"learning_rate": 0.00012501538461538462,
|
| 1957 |
-
"loss": 0.0052,
|
| 1958 |
-
"step": 2440
|
| 1959 |
-
},
|
| 1960 |
-
{
|
| 1961 |
-
"epoch": 1.8846153846153846,
|
| 1962 |
-
"grad_norm": 8.094133377075195,
|
| 1963 |
-
"learning_rate": 0.0001247076923076923,
|
| 1964 |
-
"loss": 0.2472,
|
| 1965 |
-
"step": 2450
|
| 1966 |
-
},
|
| 1967 |
-
{
|
| 1968 |
-
"epoch": 1.8923076923076922,
|
| 1969 |
-
"grad_norm": 0.015556249767541885,
|
| 1970 |
-
"learning_rate": 0.00012440000000000002,
|
| 1971 |
-
"loss": 0.0531,
|
| 1972 |
-
"step": 2460
|
| 1973 |
-
},
|
| 1974 |
-
{
|
| 1975 |
-
"epoch": 1.9,
|
| 1976 |
-
"grad_norm": 0.05205320566892624,
|
| 1977 |
-
"learning_rate": 0.0001240923076923077,
|
| 1978 |
-
"loss": 0.1907,
|
| 1979 |
-
"step": 2470
|
| 1980 |
-
},
|
| 1981 |
-
{
|
| 1982 |
-
"epoch": 1.9076923076923076,
|
| 1983 |
-
"grad_norm": 6.338665962219238,
|
| 1984 |
-
"learning_rate": 0.00012378461538461538,
|
| 1985 |
-
"loss": 0.1587,
|
| 1986 |
-
"step": 2480
|
| 1987 |
-
},
|
| 1988 |
-
{
|
| 1989 |
-
"epoch": 1.9153846153846152,
|
| 1990 |
-
"grad_norm": 0.4923330545425415,
|
| 1991 |
-
"learning_rate": 0.00012347692307692308,
|
| 1992 |
-
"loss": 0.0978,
|
| 1993 |
-
"step": 2490
|
| 1994 |
-
},
|
| 1995 |
-
{
|
| 1996 |
-
"epoch": 1.9230769230769231,
|
| 1997 |
-
"grad_norm": 2.8340303897857666,
|
| 1998 |
-
"learning_rate": 0.00012316923076923078,
|
| 1999 |
-
"loss": 0.0175,
|
| 2000 |
-
"step": 2500
|
| 2001 |
-
},
|
| 2002 |
-
{
|
| 2003 |
-
"epoch": 1.9230769230769231,
|
| 2004 |
-
"eval_accuracy": 0.734189253447456,
|
| 2005 |
-
"eval_f1": 0.77245031199361,
|
| 2006 |
-
"eval_loss": 1.9268134832382202,
|
| 2007 |
-
"eval_runtime": 12.5739,
|
| 2008 |
-
"eval_samples_per_second": 167.251,
|
| 2009 |
-
"eval_steps_per_second": 20.916,
|
| 2010 |
-
"step": 2500
|
| 2011 |
-
},
|
| 2012 |
-
{
|
| 2013 |
-
"epoch": 1.9307692307692308,
|
| 2014 |
-
"grad_norm": 7.629446029663086,
|
| 2015 |
-
"learning_rate": 0.00012286153846153847,
|
| 2016 |
-
"loss": 0.2534,
|
| 2017 |
-
"step": 2510
|
| 2018 |
-
},
|
| 2019 |
-
{
|
| 2020 |
-
"epoch": 1.9384615384615385,
|
| 2021 |
-
"grad_norm": 0.5628572702407837,
|
| 2022 |
-
"learning_rate": 0.00012255384615384614,
|
| 2023 |
-
"loss": 0.1828,
|
| 2024 |
-
"step": 2520
|
| 2025 |
-
},
|
| 2026 |
-
{
|
| 2027 |
-
"epoch": 1.9461538461538461,
|
| 2028 |
-
"grad_norm": 0.007969832979142666,
|
| 2029 |
-
"learning_rate": 0.00012224615384615384,
|
| 2030 |
-
"loss": 0.1046,
|
| 2031 |
-
"step": 2530
|
| 2032 |
-
},
|
| 2033 |
-
{
|
| 2034 |
-
"epoch": 1.953846153846154,
|
| 2035 |
-
"grad_norm": 4.393219947814941,
|
| 2036 |
-
"learning_rate": 0.00012193846153846154,
|
| 2037 |
-
"loss": 0.221,
|
| 2038 |
-
"step": 2540
|
| 2039 |
-
},
|
| 2040 |
-
{
|
| 2041 |
-
"epoch": 1.9615384615384617,
|
| 2042 |
-
"grad_norm": 2.58774995803833,
|
| 2043 |
-
"learning_rate": 0.00012163076923076924,
|
| 2044 |
-
"loss": 0.0651,
|
| 2045 |
-
"step": 2550
|
| 2046 |
-
},
|
| 2047 |
-
{
|
| 2048 |
-
"epoch": 1.9692307692307693,
|
| 2049 |
-
"grad_norm": 0.01533615030348301,
|
| 2050 |
-
"learning_rate": 0.00012132307692307693,
|
| 2051 |
-
"loss": 0.3142,
|
| 2052 |
-
"step": 2560
|
| 2053 |
-
},
|
| 2054 |
-
{
|
| 2055 |
-
"epoch": 1.976923076923077,
|
| 2056 |
-
"grad_norm": 0.04511953145265579,
|
| 2057 |
-
"learning_rate": 0.00012101538461538462,
|
| 2058 |
-
"loss": 0.0437,
|
| 2059 |
-
"step": 2570
|
| 2060 |
-
},
|
| 2061 |
-
{
|
| 2062 |
-
"epoch": 1.9846153846153847,
|
| 2063 |
-
"grad_norm": 4.066844940185547,
|
| 2064 |
-
"learning_rate": 0.00012070769230769232,
|
| 2065 |
-
"loss": 0.1857,
|
| 2066 |
-
"step": 2580
|
| 2067 |
-
},
|
| 2068 |
-
{
|
| 2069 |
-
"epoch": 1.9923076923076923,
|
| 2070 |
-
"grad_norm": 0.030109547078609467,
|
| 2071 |
-
"learning_rate": 0.0001204,
|
| 2072 |
-
"loss": 0.2628,
|
| 2073 |
-
"step": 2590
|
| 2074 |
-
},
|
| 2075 |
-
{
|
| 2076 |
-
"epoch": 2.0,
|
| 2077 |
-
"grad_norm": 13.797858238220215,
|
| 2078 |
-
"learning_rate": 0.00012009230769230771,
|
| 2079 |
-
"loss": 0.0539,
|
| 2080 |
-
"step": 2600
|
| 2081 |
-
},
|
| 2082 |
-
{
|
| 2083 |
-
"epoch": 2.0,
|
| 2084 |
-
"eval_accuracy": 0.81169757489301,
|
| 2085 |
-
"eval_f1": 0.7984725776961168,
|
| 2086 |
-
"eval_loss": 0.9400935769081116,
|
| 2087 |
-
"eval_runtime": 12.4311,
|
| 2088 |
-
"eval_samples_per_second": 169.173,
|
| 2089 |
-
"eval_steps_per_second": 21.157,
|
| 2090 |
-
"step": 2600
|
| 2091 |
-
},
|
| 2092 |
-
{
|
| 2093 |
-
"epoch": 2.0,
|
| 2094 |
-
"step": 2600,
|
| 2095 |
-
"total_flos": 1.611433851126866e+18,
|
| 2096 |
-
"train_loss": 0.3103342184309776,
|
| 2097 |
-
"train_runtime": 732.7839,
|
| 2098 |
-
"train_samples_per_second": 70.928,
|
| 2099 |
-
"train_steps_per_second": 8.87
|
| 2100 |
}
|
| 2101 |
],
|
| 2102 |
"logging_steps": 10,
|
|
@@ -2108,7 +1788,7 @@
|
|
| 2108 |
"EarlyStoppingCallback": {
|
| 2109 |
"args": {
|
| 2110 |
"early_stopping_patience": 10,
|
| 2111 |
-
"early_stopping_threshold": 0.
|
| 2112 |
},
|
| 2113 |
"attributes": {
|
| 2114 |
"early_stopping_patience_counter": 10
|
|
@@ -2125,7 +1805,7 @@
|
|
| 2125 |
"attributes": {}
|
| 2126 |
}
|
| 2127 |
},
|
| 2128 |
-
"total_flos": 1.
|
| 2129 |
"train_batch_size": 8,
|
| 2130 |
"trial_name": null,
|
| 2131 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 1200,
|
| 3 |
+
"best_metric": 0.8585250973701477,
|
| 4 |
+
"best_model_checkpoint": "./deit-CEMEDE/checkpoint-1200",
|
| 5 |
+
"epoch": 1.6923076923076923,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 2200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
{
|
| 13 |
"epoch": 0.007692307692307693,
|
| 14 |
+
"grad_norm": 18.197193145751953,
|
| 15 |
+
"learning_rate": 0.00019975384615384615,
|
| 16 |
+
"loss": 2.5816,
|
| 17 |
"step": 10
|
| 18 |
},
|
| 19 |
{
|
| 20 |
"epoch": 0.015384615384615385,
|
| 21 |
+
"grad_norm": 8.680727005004883,
|
| 22 |
+
"learning_rate": 0.00019944615384615385,
|
| 23 |
+
"loss": 1.8162,
|
| 24 |
"step": 20
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 0.023076923076923078,
|
| 28 |
+
"grad_norm": 12.35321044921875,
|
| 29 |
+
"learning_rate": 0.00019913846153846155,
|
| 30 |
+
"loss": 1.3586,
|
| 31 |
"step": 30
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 0.03076923076923077,
|
| 35 |
+
"grad_norm": 16.556589126586914,
|
| 36 |
+
"learning_rate": 0.00019883076923076924,
|
| 37 |
+
"loss": 1.3773,
|
| 38 |
"step": 40
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.038461538461538464,
|
| 42 |
+
"grad_norm": 7.4731059074401855,
|
| 43 |
+
"learning_rate": 0.0001985230769230769,
|
| 44 |
+
"loss": 0.833,
|
| 45 |
"step": 50
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.046153846153846156,
|
| 49 |
+
"grad_norm": 16.327470779418945,
|
| 50 |
+
"learning_rate": 0.00019821538461538464,
|
| 51 |
+
"loss": 0.861,
|
| 52 |
"step": 60
|
| 53 |
},
|
| 54 |
{
|
| 55 |
"epoch": 0.05384615384615385,
|
| 56 |
+
"grad_norm": 6.821540832519531,
|
| 57 |
+
"learning_rate": 0.00019790769230769234,
|
| 58 |
+
"loss": 1.0562,
|
| 59 |
"step": 70
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.06153846153846154,
|
| 63 |
+
"grad_norm": 11.482409477233887,
|
| 64 |
+
"learning_rate": 0.0001976,
|
| 65 |
+
"loss": 1.0553,
|
| 66 |
"step": 80
|
| 67 |
},
|
| 68 |
{
|
| 69 |
"epoch": 0.06923076923076923,
|
| 70 |
+
"grad_norm": 7.535261154174805,
|
| 71 |
+
"learning_rate": 0.0001972923076923077,
|
| 72 |
+
"loss": 0.5367,
|
| 73 |
"step": 90
|
| 74 |
},
|
| 75 |
{
|
| 76 |
"epoch": 0.07692307692307693,
|
| 77 |
+
"grad_norm": 8.011478424072266,
|
| 78 |
+
"learning_rate": 0.0001969846153846154,
|
| 79 |
+
"loss": 0.5433,
|
| 80 |
"step": 100
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.07692307692307693,
|
| 84 |
+
"eval_accuracy": 0.6338563956252972,
|
| 85 |
+
"eval_f1": 0.43161314039771254,
|
| 86 |
+
"eval_loss": 1.4162613153457642,
|
| 87 |
+
"eval_runtime": 12.991,
|
| 88 |
+
"eval_samples_per_second": 161.882,
|
| 89 |
+
"eval_steps_per_second": 20.245,
|
| 90 |
"step": 100
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 0.08461538461538462,
|
| 94 |
+
"grad_norm": 6.010300159454346,
|
| 95 |
+
"learning_rate": 0.0001966769230769231,
|
| 96 |
+
"loss": 0.9265,
|
| 97 |
"step": 110
|
| 98 |
},
|
| 99 |
{
|
| 100 |
"epoch": 0.09230769230769231,
|
| 101 |
+
"grad_norm": 11.949559211730957,
|
| 102 |
+
"learning_rate": 0.00019636923076923077,
|
| 103 |
+
"loss": 0.4836,
|
| 104 |
"step": 120
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.1,
|
| 108 |
+
"grad_norm": 12.648119926452637,
|
| 109 |
+
"learning_rate": 0.00019606153846153847,
|
| 110 |
+
"loss": 0.7105,
|
| 111 |
"step": 130
|
| 112 |
},
|
| 113 |
{
|
| 114 |
"epoch": 0.1076923076923077,
|
| 115 |
+
"grad_norm": 11.041376113891602,
|
| 116 |
+
"learning_rate": 0.00019575384615384616,
|
| 117 |
+
"loss": 0.7821,
|
| 118 |
"step": 140
|
| 119 |
},
|
| 120 |
{
|
| 121 |
"epoch": 0.11538461538461539,
|
| 122 |
+
"grad_norm": 21.592378616333008,
|
| 123 |
+
"learning_rate": 0.00019544615384615386,
|
| 124 |
+
"loss": 0.5134,
|
| 125 |
"step": 150
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"epoch": 0.12307692307692308,
|
| 129 |
+
"grad_norm": 9.74736499786377,
|
| 130 |
+
"learning_rate": 0.00019513846153846156,
|
| 131 |
+
"loss": 0.5469,
|
| 132 |
"step": 160
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 0.13076923076923078,
|
| 136 |
+
"grad_norm": 12.262529373168945,
|
| 137 |
+
"learning_rate": 0.00019483076923076923,
|
| 138 |
+
"loss": 0.392,
|
| 139 |
"step": 170
|
| 140 |
},
|
| 141 |
{
|
| 142 |
"epoch": 0.13846153846153847,
|
| 143 |
+
"grad_norm": 9.946588516235352,
|
| 144 |
+
"learning_rate": 0.00019452307692307695,
|
| 145 |
+
"loss": 0.5524,
|
| 146 |
"step": 180
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.14615384615384616,
|
| 150 |
+
"grad_norm": 18.688274383544922,
|
| 151 |
+
"learning_rate": 0.00019421538461538462,
|
| 152 |
+
"loss": 0.6801,
|
| 153 |
"step": 190
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.15384615384615385,
|
| 157 |
+
"grad_norm": 3.1866862773895264,
|
| 158 |
+
"learning_rate": 0.00019390769230769232,
|
| 159 |
+
"loss": 0.8153,
|
| 160 |
"step": 200
|
| 161 |
},
|
| 162 |
{
|
| 163 |
"epoch": 0.15384615384615385,
|
| 164 |
+
"eval_accuracy": 0.7013789824060865,
|
| 165 |
+
"eval_f1": 0.6079592746324705,
|
| 166 |
+
"eval_loss": 1.2107399702072144,
|
| 167 |
+
"eval_runtime": 12.8177,
|
| 168 |
+
"eval_samples_per_second": 164.07,
|
| 169 |
+
"eval_steps_per_second": 20.518,
|
| 170 |
"step": 200
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 0.16153846153846155,
|
| 174 |
+
"grad_norm": 10.409411430358887,
|
| 175 |
+
"learning_rate": 0.00019360000000000002,
|
| 176 |
+
"loss": 0.3139,
|
| 177 |
"step": 210
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.16923076923076924,
|
| 181 |
+
"grad_norm": 10.94472599029541,
|
| 182 |
+
"learning_rate": 0.00019329230769230771,
|
| 183 |
+
"loss": 0.7899,
|
| 184 |
"step": 220
|
| 185 |
},
|
| 186 |
{
|
| 187 |
"epoch": 0.17692307692307693,
|
| 188 |
+
"grad_norm": 13.132795333862305,
|
| 189 |
+
"learning_rate": 0.00019298461538461538,
|
| 190 |
+
"loss": 0.6232,
|
| 191 |
"step": 230
|
| 192 |
},
|
| 193 |
{
|
| 194 |
"epoch": 0.18461538461538463,
|
| 195 |
+
"grad_norm": 5.178615093231201,
|
| 196 |
+
"learning_rate": 0.00019267692307692308,
|
| 197 |
+
"loss": 0.6606,
|
| 198 |
"step": 240
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 0.19230769230769232,
|
| 202 |
+
"grad_norm": 3.8530232906341553,
|
| 203 |
+
"learning_rate": 0.00019236923076923078,
|
| 204 |
+
"loss": 0.648,
|
| 205 |
"step": 250
|
| 206 |
},
|
| 207 |
{
|
| 208 |
"epoch": 0.2,
|
| 209 |
+
"grad_norm": 9.361835479736328,
|
| 210 |
+
"learning_rate": 0.00019206153846153848,
|
| 211 |
+
"loss": 0.3533,
|
| 212 |
"step": 260
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.2076923076923077,
|
| 216 |
+
"grad_norm": 7.445398330688477,
|
| 217 |
+
"learning_rate": 0.00019175384615384617,
|
| 218 |
+
"loss": 0.5113,
|
| 219 |
"step": 270
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.2153846153846154,
|
| 223 |
+
"grad_norm": 10.053826332092285,
|
| 224 |
+
"learning_rate": 0.00019144615384615384,
|
| 225 |
+
"loss": 0.6366,
|
| 226 |
"step": 280
|
| 227 |
},
|
| 228 |
{
|
| 229 |
"epoch": 0.2230769230769231,
|
| 230 |
+
"grad_norm": 9.240071296691895,
|
| 231 |
+
"learning_rate": 0.00019113846153846157,
|
| 232 |
+
"loss": 0.7002,
|
| 233 |
"step": 290
|
| 234 |
},
|
| 235 |
{
|
| 236 |
"epoch": 0.23076923076923078,
|
| 237 |
+
"grad_norm": 2.5356545448303223,
|
| 238 |
+
"learning_rate": 0.00019083076923076924,
|
| 239 |
+
"loss": 0.4572,
|
| 240 |
"step": 300
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 0.23076923076923078,
|
| 244 |
+
"eval_accuracy": 0.7513076557299097,
|
| 245 |
+
"eval_f1": 0.675000963253108,
|
| 246 |
+
"eval_loss": 0.9055613279342651,
|
| 247 |
+
"eval_runtime": 12.7209,
|
| 248 |
+
"eval_samples_per_second": 165.319,
|
| 249 |
+
"eval_steps_per_second": 20.675,
|
| 250 |
"step": 300
|
| 251 |
},
|
| 252 |
{
|
| 253 |
"epoch": 0.23846153846153847,
|
| 254 |
+
"grad_norm": 5.946889400482178,
|
| 255 |
+
"learning_rate": 0.00019052307692307694,
|
| 256 |
+
"loss": 0.1694,
|
| 257 |
"step": 310
|
| 258 |
},
|
| 259 |
{
|
| 260 |
"epoch": 0.24615384615384617,
|
| 261 |
+
"grad_norm": 3.9482967853546143,
|
| 262 |
+
"learning_rate": 0.0001902153846153846,
|
| 263 |
+
"loss": 0.1883,
|
| 264 |
"step": 320
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 0.25384615384615383,
|
| 268 |
+
"grad_norm": 10.08955192565918,
|
| 269 |
+
"learning_rate": 0.00018990769230769233,
|
| 270 |
+
"loss": 0.2619,
|
| 271 |
"step": 330
|
| 272 |
},
|
| 273 |
{
|
| 274 |
"epoch": 0.26153846153846155,
|
| 275 |
+
"grad_norm": 6.082069396972656,
|
| 276 |
+
"learning_rate": 0.0001896,
|
| 277 |
+
"loss": 0.3425,
|
| 278 |
"step": 340
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 0.2692307692307692,
|
| 282 |
+
"grad_norm": 21.109539031982422,
|
| 283 |
+
"learning_rate": 0.0001892923076923077,
|
| 284 |
+
"loss": 0.4289,
|
| 285 |
"step": 350
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 0.27692307692307694,
|
| 289 |
+
"grad_norm": 12.561626434326172,
|
| 290 |
+
"learning_rate": 0.0001889846153846154,
|
| 291 |
+
"loss": 0.4526,
|
| 292 |
"step": 360
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 0.2846153846153846,
|
| 296 |
+
"grad_norm": 18.23844337463379,
|
| 297 |
+
"learning_rate": 0.0001886769230769231,
|
| 298 |
+
"loss": 0.6775,
|
| 299 |
"step": 370
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 0.2923076923076923,
|
| 303 |
+
"grad_norm": 14.852152824401855,
|
| 304 |
+
"learning_rate": 0.0001883692307692308,
|
| 305 |
+
"loss": 0.6215,
|
| 306 |
"step": 380
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 0.3,
|
| 310 |
+
"grad_norm": 4.879684925079346,
|
| 311 |
+
"learning_rate": 0.00018806153846153846,
|
| 312 |
+
"loss": 0.5646,
|
| 313 |
"step": 390
|
| 314 |
},
|
| 315 |
{
|
| 316 |
"epoch": 0.3076923076923077,
|
| 317 |
+
"grad_norm": 11.373760223388672,
|
| 318 |
+
"learning_rate": 0.00018775384615384616,
|
| 319 |
+
"loss": 0.5055,
|
| 320 |
"step": 400
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 0.3076923076923077,
|
| 324 |
+
"eval_accuracy": 0.6571564431764146,
|
| 325 |
+
"eval_f1": 0.5795112999251144,
|
| 326 |
+
"eval_loss": 1.2328877449035645,
|
| 327 |
+
"eval_runtime": 12.9793,
|
| 328 |
+
"eval_samples_per_second": 162.027,
|
| 329 |
+
"eval_steps_per_second": 20.263,
|
| 330 |
"step": 400
|
| 331 |
},
|
| 332 |
{
|
| 333 |
"epoch": 0.3153846153846154,
|
| 334 |
+
"grad_norm": 17.832473754882812,
|
| 335 |
+
"learning_rate": 0.00018744615384615386,
|
| 336 |
+
"loss": 0.5483,
|
| 337 |
"step": 410
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 0.3230769230769231,
|
| 341 |
+
"grad_norm": 7.938933372497559,
|
| 342 |
+
"learning_rate": 0.00018713846153846155,
|
| 343 |
+
"loss": 0.4665,
|
| 344 |
"step": 420
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 0.33076923076923076,
|
| 348 |
+
"grad_norm": 0.892392098903656,
|
| 349 |
+
"learning_rate": 0.00018683076923076922,
|
| 350 |
+
"loss": 0.4319,
|
| 351 |
"step": 430
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 0.3384615384615385,
|
| 355 |
+
"grad_norm": 12.021994590759277,
|
| 356 |
+
"learning_rate": 0.00018652307692307695,
|
| 357 |
+
"loss": 0.2883,
|
| 358 |
"step": 440
|
| 359 |
},
|
| 360 |
{
|
| 361 |
"epoch": 0.34615384615384615,
|
| 362 |
+
"grad_norm": 8.725289344787598,
|
| 363 |
+
"learning_rate": 0.00018621538461538462,
|
| 364 |
+
"loss": 0.3389,
|
| 365 |
"step": 450
|
| 366 |
},
|
| 367 |
{
|
| 368 |
"epoch": 0.35384615384615387,
|
| 369 |
+
"grad_norm": 13.443779945373535,
|
| 370 |
+
"learning_rate": 0.00018590769230769231,
|
| 371 |
+
"loss": 0.5416,
|
| 372 |
"step": 460
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 0.36153846153846153,
|
| 376 |
+
"grad_norm": 5.893988132476807,
|
| 377 |
+
"learning_rate": 0.0001856,
|
| 378 |
+
"loss": 0.3084,
|
| 379 |
"step": 470
|
| 380 |
},
|
| 381 |
{
|
| 382 |
"epoch": 0.36923076923076925,
|
| 383 |
+
"grad_norm": 2.6127381324768066,
|
| 384 |
+
"learning_rate": 0.0001852923076923077,
|
| 385 |
+
"loss": 0.3881,
|
| 386 |
"step": 480
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 0.3769230769230769,
|
| 390 |
+
"grad_norm": 4.684244155883789,
|
| 391 |
+
"learning_rate": 0.0001849846153846154,
|
| 392 |
+
"loss": 0.2972,
|
| 393 |
"step": 490
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 0.38461538461538464,
|
| 397 |
+
"grad_norm": 3.0813324451446533,
|
| 398 |
+
"learning_rate": 0.00018467692307692308,
|
| 399 |
+
"loss": 0.5404,
|
| 400 |
"step": 500
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"epoch": 0.38461538461538464,
|
| 404 |
+
"eval_accuracy": 0.7156443176414645,
|
| 405 |
+
"eval_f1": 0.656711194356937,
|
| 406 |
+
"eval_loss": 1.1346296072006226,
|
| 407 |
+
"eval_runtime": 12.7812,
|
| 408 |
+
"eval_samples_per_second": 164.538,
|
| 409 |
+
"eval_steps_per_second": 20.577,
|
| 410 |
"step": 500
|
| 411 |
},
|
| 412 |
{
|
| 413 |
"epoch": 0.3923076923076923,
|
| 414 |
+
"grad_norm": 7.389800548553467,
|
| 415 |
+
"learning_rate": 0.00018436923076923077,
|
| 416 |
+
"loss": 0.3531,
|
| 417 |
"step": 510
|
| 418 |
},
|
| 419 |
{
|
| 420 |
"epoch": 0.4,
|
| 421 |
+
"grad_norm": 6.2316060066223145,
|
| 422 |
+
"learning_rate": 0.00018406153846153847,
|
| 423 |
+
"loss": 0.4253,
|
| 424 |
"step": 520
|
| 425 |
},
|
| 426 |
{
|
| 427 |
"epoch": 0.4076923076923077,
|
| 428 |
+
"grad_norm": 13.33460807800293,
|
| 429 |
+
"learning_rate": 0.00018375384615384617,
|
| 430 |
+
"loss": 0.23,
|
| 431 |
"step": 530
|
| 432 |
},
|
| 433 |
{
|
| 434 |
"epoch": 0.4153846153846154,
|
| 435 |
+
"grad_norm": 6.275513172149658,
|
| 436 |
+
"learning_rate": 0.00018344615384615384,
|
| 437 |
+
"loss": 0.6893,
|
| 438 |
"step": 540
|
| 439 |
},
|
| 440 |
{
|
| 441 |
"epoch": 0.4230769230769231,
|
| 442 |
+
"grad_norm": 7.9323649406433105,
|
| 443 |
+
"learning_rate": 0.00018313846153846154,
|
| 444 |
+
"loss": 0.5152,
|
| 445 |
"step": 550
|
| 446 |
},
|
| 447 |
{
|
| 448 |
"epoch": 0.4307692307692308,
|
| 449 |
+
"grad_norm": 0.08034035563468933,
|
| 450 |
+
"learning_rate": 0.00018283076923076926,
|
| 451 |
+
"loss": 0.3934,
|
| 452 |
"step": 560
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 0.43846153846153846,
|
| 456 |
+
"grad_norm": 0.45259109139442444,
|
| 457 |
+
"learning_rate": 0.00018252307692307693,
|
| 458 |
+
"loss": 0.332,
|
| 459 |
"step": 570
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 0.4461538461538462,
|
| 463 |
+
"grad_norm": 8.854157447814941,
|
| 464 |
+
"learning_rate": 0.00018221538461538463,
|
| 465 |
+
"loss": 0.321,
|
| 466 |
"step": 580
|
| 467 |
},
|
| 468 |
{
|
| 469 |
"epoch": 0.45384615384615384,
|
| 470 |
+
"grad_norm": 6.054807662963867,
|
| 471 |
+
"learning_rate": 0.00018190769230769233,
|
| 472 |
+
"loss": 0.2757,
|
| 473 |
"step": 590
|
| 474 |
},
|
| 475 |
{
|
| 476 |
"epoch": 0.46153846153846156,
|
| 477 |
+
"grad_norm": 0.04787035658955574,
|
| 478 |
+
"learning_rate": 0.00018160000000000002,
|
| 479 |
+
"loss": 0.3872,
|
| 480 |
"step": 600
|
| 481 |
},
|
| 482 |
{
|
| 483 |
"epoch": 0.46153846153846156,
|
| 484 |
+
"eval_accuracy": 0.7689015691868759,
|
| 485 |
+
"eval_f1": 0.6869204779737752,
|
| 486 |
+
"eval_loss": 1.0171802043914795,
|
| 487 |
+
"eval_runtime": 12.8764,
|
| 488 |
+
"eval_samples_per_second": 163.322,
|
| 489 |
+
"eval_steps_per_second": 20.425,
|
| 490 |
"step": 600
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 0.46923076923076923,
|
| 494 |
+
"grad_norm": 1.1864789724349976,
|
| 495 |
+
"learning_rate": 0.0001812923076923077,
|
| 496 |
+
"loss": 0.0565,
|
| 497 |
"step": 610
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 0.47692307692307695,
|
| 501 |
+
"grad_norm": 0.6733745336532593,
|
| 502 |
+
"learning_rate": 0.0001809846153846154,
|
| 503 |
+
"loss": 0.2029,
|
| 504 |
"step": 620
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 0.4846153846153846,
|
| 508 |
+
"grad_norm": 5.898662090301514,
|
| 509 |
+
"learning_rate": 0.0001806769230769231,
|
| 510 |
+
"loss": 0.3849,
|
| 511 |
"step": 630
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 0.49230769230769234,
|
| 515 |
+
"grad_norm": 11.095335006713867,
|
| 516 |
+
"learning_rate": 0.00018036923076923079,
|
| 517 |
+
"loss": 0.3647,
|
| 518 |
"step": 640
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 0.5,
|
| 522 |
+
"grad_norm": 1.633670687675476,
|
| 523 |
+
"learning_rate": 0.00018006153846153846,
|
| 524 |
+
"loss": 0.3256,
|
| 525 |
"step": 650
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 0.5076923076923077,
|
| 529 |
+
"grad_norm": 0.15434664487838745,
|
| 530 |
+
"learning_rate": 0.00017975384615384615,
|
| 531 |
+
"loss": 0.1804,
|
| 532 |
"step": 660
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 0.5153846153846153,
|
| 536 |
+
"grad_norm": 21.246501922607422,
|
| 537 |
+
"learning_rate": 0.00017944615384615385,
|
| 538 |
+
"loss": 0.5879,
|
| 539 |
"step": 670
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 0.5230769230769231,
|
| 543 |
+
"grad_norm": 4.079148769378662,
|
| 544 |
+
"learning_rate": 0.00017913846153846155,
|
| 545 |
+
"loss": 0.406,
|
| 546 |
"step": 680
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 0.5307692307692308,
|
| 550 |
+
"grad_norm": 14.820666313171387,
|
| 551 |
+
"learning_rate": 0.00017883076923076924,
|
| 552 |
+
"loss": 0.3732,
|
| 553 |
"step": 690
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 0.5384615384615384,
|
| 557 |
+
"grad_norm": 2.049006223678589,
|
| 558 |
+
"learning_rate": 0.00017852307692307692,
|
| 559 |
+
"loss": 0.2404,
|
| 560 |
"step": 700
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 0.5384615384615384,
|
| 564 |
+
"eval_accuracy": 0.7299096528768426,
|
| 565 |
+
"eval_f1": 0.7135465992080591,
|
| 566 |
+
"eval_loss": 1.1938942670822144,
|
| 567 |
+
"eval_runtime": 13.2482,
|
| 568 |
+
"eval_samples_per_second": 158.739,
|
| 569 |
+
"eval_steps_per_second": 19.852,
|
| 570 |
"step": 700
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 0.5461538461538461,
|
| 574 |
+
"grad_norm": 0.3764440715312958,
|
| 575 |
+
"learning_rate": 0.00017821538461538464,
|
| 576 |
+
"loss": 0.4883,
|
| 577 |
"step": 710
|
| 578 |
},
|
| 579 |
{
|
| 580 |
"epoch": 0.5538461538461539,
|
| 581 |
+
"grad_norm": 10.493640899658203,
|
| 582 |
+
"learning_rate": 0.0001779076923076923,
|
| 583 |
+
"loss": 0.3606,
|
| 584 |
"step": 720
|
| 585 |
},
|
| 586 |
{
|
| 587 |
"epoch": 0.5615384615384615,
|
| 588 |
+
"grad_norm": 5.019975662231445,
|
| 589 |
+
"learning_rate": 0.0001776,
|
| 590 |
+
"loss": 0.5277,
|
| 591 |
"step": 730
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 0.5692307692307692,
|
| 595 |
+
"grad_norm": 1.2601099014282227,
|
| 596 |
+
"learning_rate": 0.00017729230769230768,
|
| 597 |
+
"loss": 0.2193,
|
| 598 |
"step": 740
|
| 599 |
},
|
| 600 |
{
|
| 601 |
"epoch": 0.5769230769230769,
|
| 602 |
+
"grad_norm": 5.463764667510986,
|
| 603 |
+
"learning_rate": 0.0001769846153846154,
|
| 604 |
+
"loss": 0.3176,
|
| 605 |
"step": 750
|
| 606 |
},
|
| 607 |
{
|
| 608 |
"epoch": 0.5846153846153846,
|
| 609 |
+
"grad_norm": 3.235102653503418,
|
| 610 |
+
"learning_rate": 0.0001766769230769231,
|
| 611 |
+
"loss": 0.413,
|
| 612 |
"step": 760
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 0.5923076923076923,
|
| 616 |
+
"grad_norm": 2.2732224464416504,
|
| 617 |
+
"learning_rate": 0.00017636923076923077,
|
| 618 |
+
"loss": 0.2794,
|
| 619 |
"step": 770
|
| 620 |
},
|
| 621 |
{
|
| 622 |
"epoch": 0.6,
|
| 623 |
+
"grad_norm": 13.89130973815918,
|
| 624 |
+
"learning_rate": 0.00017606153846153847,
|
| 625 |
+
"loss": 0.7099,
|
| 626 |
"step": 780
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 0.6076923076923076,
|
| 630 |
+
"grad_norm": 11.57028865814209,
|
| 631 |
+
"learning_rate": 0.00017575384615384616,
|
| 632 |
+
"loss": 0.2651,
|
| 633 |
"step": 790
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 0.6153846153846154,
|
| 637 |
+
"grad_norm": 8.592397689819336,
|
| 638 |
+
"learning_rate": 0.00017544615384615386,
|
| 639 |
+
"loss": 0.3426,
|
| 640 |
"step": 800
|
| 641 |
},
|
| 642 |
{
|
| 643 |
"epoch": 0.6153846153846154,
|
| 644 |
+
"eval_accuracy": 0.7123157394198764,
|
| 645 |
+
"eval_f1": 0.7012828617998541,
|
| 646 |
+
"eval_loss": 1.3790241479873657,
|
| 647 |
+
"eval_runtime": 13.256,
|
| 648 |
+
"eval_samples_per_second": 158.645,
|
| 649 |
+
"eval_steps_per_second": 19.84,
|
| 650 |
"step": 800
|
| 651 |
},
|
| 652 |
{
|
| 653 |
"epoch": 0.6230769230769231,
|
| 654 |
+
"grad_norm": 3.83967924118042,
|
| 655 |
+
"learning_rate": 0.00017513846153846153,
|
| 656 |
+
"loss": 0.2772,
|
| 657 |
"step": 810
|
| 658 |
},
|
| 659 |
{
|
| 660 |
"epoch": 0.6307692307692307,
|
| 661 |
+
"grad_norm": 7.842036247253418,
|
| 662 |
+
"learning_rate": 0.00017483076923076923,
|
| 663 |
+
"loss": 0.0811,
|
| 664 |
"step": 820
|
| 665 |
},
|
| 666 |
{
|
| 667 |
"epoch": 0.6384615384615384,
|
| 668 |
+
"grad_norm": 8.102109909057617,
|
| 669 |
+
"learning_rate": 0.00017452307692307693,
|
| 670 |
+
"loss": 0.284,
|
| 671 |
"step": 830
|
| 672 |
},
|
| 673 |
{
|
| 674 |
"epoch": 0.6461538461538462,
|
| 675 |
+
"grad_norm": 3.7149875164031982,
|
| 676 |
+
"learning_rate": 0.00017421538461538462,
|
| 677 |
+
"loss": 0.2836,
|
| 678 |
"step": 840
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 0.6538461538461539,
|
| 682 |
+
"grad_norm": 1.5214999914169312,
|
| 683 |
+
"learning_rate": 0.00017390769230769232,
|
| 684 |
+
"loss": 0.5645,
|
| 685 |
"step": 850
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 0.6615384615384615,
|
| 689 |
+
"grad_norm": 2.1466846466064453,
|
| 690 |
+
"learning_rate": 0.00017360000000000002,
|
| 691 |
+
"loss": 0.2513,
|
| 692 |
"step": 860
|
| 693 |
},
|
| 694 |
{
|
| 695 |
"epoch": 0.6692307692307692,
|
| 696 |
+
"grad_norm": 3.5235519409179688,
|
| 697 |
+
"learning_rate": 0.00017329230769230772,
|
| 698 |
+
"loss": 0.2663,
|
| 699 |
"step": 870
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 0.676923076923077,
|
| 703 |
+
"grad_norm": 14.82608699798584,
|
| 704 |
+
"learning_rate": 0.00017298461538461539,
|
| 705 |
+
"loss": 0.6103,
|
| 706 |
"step": 880
|
| 707 |
},
|
| 708 |
{
|
| 709 |
"epoch": 0.6846153846153846,
|
| 710 |
+
"grad_norm": 6.010519504547119,
|
| 711 |
+
"learning_rate": 0.00017267692307692308,
|
| 712 |
+
"loss": 0.3315,
|
| 713 |
"step": 890
|
| 714 |
},
|
| 715 |
{
|
| 716 |
"epoch": 0.6923076923076923,
|
| 717 |
+
"grad_norm": 4.174232006072998,
|
| 718 |
+
"learning_rate": 0.00017236923076923078,
|
| 719 |
+
"loss": 0.3455,
|
| 720 |
"step": 900
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 0.6923076923076923,
|
| 724 |
+
"eval_accuracy": 0.722301474084641,
|
| 725 |
+
"eval_f1": 0.6945099209124845,
|
| 726 |
+
"eval_loss": 1.2071079015731812,
|
| 727 |
+
"eval_runtime": 13.1782,
|
| 728 |
+
"eval_samples_per_second": 159.582,
|
| 729 |
+
"eval_steps_per_second": 19.957,
|
| 730 |
"step": 900
|
| 731 |
},
|
| 732 |
{
|
| 733 |
"epoch": 0.7,
|
| 734 |
+
"grad_norm": 0.17157310247421265,
|
| 735 |
+
"learning_rate": 0.00017206153846153848,
|
| 736 |
+
"loss": 0.5492,
|
| 737 |
"step": 910
|
| 738 |
},
|
| 739 |
{
|
| 740 |
"epoch": 0.7076923076923077,
|
| 741 |
+
"grad_norm": 1.049086570739746,
|
| 742 |
+
"learning_rate": 0.00017175384615384615,
|
| 743 |
+
"loss": 0.1558,
|
| 744 |
"step": 920
|
| 745 |
},
|
| 746 |
{
|
| 747 |
"epoch": 0.7153846153846154,
|
| 748 |
+
"grad_norm": 9.643935203552246,
|
| 749 |
+
"learning_rate": 0.00017144615384615385,
|
| 750 |
+
"loss": 0.2683,
|
| 751 |
"step": 930
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"epoch": 0.7230769230769231,
|
| 755 |
+
"grad_norm": 4.239430904388428,
|
| 756 |
+
"learning_rate": 0.00017113846153846154,
|
| 757 |
+
"loss": 0.0683,
|
| 758 |
"step": 940
|
| 759 |
},
|
| 760 |
{
|
| 761 |
"epoch": 0.7307692307692307,
|
| 762 |
+
"grad_norm": 12.830389976501465,
|
| 763 |
+
"learning_rate": 0.00017083076923076924,
|
| 764 |
+
"loss": 0.3568,
|
| 765 |
"step": 950
|
| 766 |
},
|
| 767 |
{
|
| 768 |
"epoch": 0.7384615384615385,
|
| 769 |
+
"grad_norm": 11.543557167053223,
|
| 770 |
+
"learning_rate": 0.00017052307692307694,
|
| 771 |
+
"loss": 0.37,
|
| 772 |
"step": 960
|
| 773 |
},
|
| 774 |
{
|
| 775 |
"epoch": 0.7461538461538462,
|
| 776 |
+
"grad_norm": 0.12294139713048935,
|
| 777 |
+
"learning_rate": 0.0001702153846153846,
|
| 778 |
+
"loss": 0.2944,
|
| 779 |
"step": 970
|
| 780 |
},
|
| 781 |
{
|
| 782 |
"epoch": 0.7538461538461538,
|
| 783 |
+
"grad_norm": 3.925886631011963,
|
| 784 |
+
"learning_rate": 0.00016990769230769233,
|
| 785 |
+
"loss": 0.1135,
|
| 786 |
"step": 980
|
| 787 |
},
|
| 788 |
{
|
| 789 |
"epoch": 0.7615384615384615,
|
| 790 |
+
"grad_norm": 0.4756164848804474,
|
| 791 |
+
"learning_rate": 0.0001696,
|
| 792 |
+
"loss": 0.3048,
|
| 793 |
"step": 990
|
| 794 |
},
|
| 795 |
{
|
| 796 |
"epoch": 0.7692307692307693,
|
| 797 |
+
"grad_norm": 9.28410816192627,
|
| 798 |
+
"learning_rate": 0.0001692923076923077,
|
| 799 |
+
"loss": 0.3843,
|
| 800 |
"step": 1000
|
| 801 |
},
|
| 802 |
{
|
| 803 |
"epoch": 0.7692307692307693,
|
| 804 |
+
"eval_accuracy": 0.5981930575368521,
|
| 805 |
+
"eval_f1": 0.6507281627404139,
|
| 806 |
+
"eval_loss": 2.4214253425598145,
|
| 807 |
+
"eval_runtime": 13.0632,
|
| 808 |
+
"eval_samples_per_second": 160.986,
|
| 809 |
+
"eval_steps_per_second": 20.133,
|
| 810 |
"step": 1000
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 0.7769230769230769,
|
| 814 |
+
"grad_norm": 2.1016364097595215,
|
| 815 |
+
"learning_rate": 0.0001689846153846154,
|
| 816 |
+
"loss": 0.5929,
|
| 817 |
"step": 1010
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 0.7846153846153846,
|
| 821 |
+
"grad_norm": 13.423405647277832,
|
| 822 |
+
"learning_rate": 0.0001686769230769231,
|
| 823 |
+
"loss": 0.2179,
|
| 824 |
"step": 1020
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 0.7923076923076923,
|
| 828 |
+
"grad_norm": 15.832393646240234,
|
| 829 |
+
"learning_rate": 0.00016836923076923076,
|
| 830 |
+
"loss": 0.3779,
|
| 831 |
"step": 1030
|
| 832 |
},
|
| 833 |
{
|
| 834 |
"epoch": 0.8,
|
| 835 |
+
"grad_norm": 4.272373199462891,
|
| 836 |
+
"learning_rate": 0.00016806153846153846,
|
| 837 |
+
"loss": 0.2062,
|
| 838 |
"step": 1040
|
| 839 |
},
|
| 840 |
{
|
| 841 |
"epoch": 0.8076923076923077,
|
| 842 |
+
"grad_norm": 19.82012939453125,
|
| 843 |
+
"learning_rate": 0.00016775384615384616,
|
| 844 |
+
"loss": 0.3419,
|
| 845 |
"step": 1050
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 0.8153846153846154,
|
| 849 |
+
"grad_norm": 1.0584157705307007,
|
| 850 |
+
"learning_rate": 0.00016744615384615386,
|
| 851 |
+
"loss": 0.2643,
|
| 852 |
"step": 1060
|
| 853 |
},
|
| 854 |
{
|
| 855 |
"epoch": 0.823076923076923,
|
| 856 |
+
"grad_norm": 8.123514175415039,
|
| 857 |
+
"learning_rate": 0.00016713846153846155,
|
| 858 |
+
"loss": 0.3832,
|
| 859 |
"step": 1070
|
| 860 |
},
|
| 861 |
{
|
| 862 |
"epoch": 0.8307692307692308,
|
| 863 |
+
"grad_norm": 0.30591386556625366,
|
| 864 |
+
"learning_rate": 0.00016683076923076922,
|
| 865 |
+
"loss": 0.3147,
|
| 866 |
"step": 1080
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"epoch": 0.8384615384615385,
|
| 870 |
+
"grad_norm": 11.121192932128906,
|
| 871 |
+
"learning_rate": 0.00016652307692307695,
|
| 872 |
+
"loss": 0.2886,
|
| 873 |
"step": 1090
|
| 874 |
},
|
| 875 |
{
|
| 876 |
"epoch": 0.8461538461538461,
|
| 877 |
+
"grad_norm": 2.2156481742858887,
|
| 878 |
+
"learning_rate": 0.00016621538461538462,
|
| 879 |
+
"loss": 0.1851,
|
| 880 |
"step": 1100
|
| 881 |
},
|
| 882 |
{
|
| 883 |
"epoch": 0.8461538461538461,
|
| 884 |
+
"eval_accuracy": 0.7617689015691869,
|
| 885 |
+
"eval_f1": 0.7712739901548827,
|
| 886 |
+
"eval_loss": 0.9814907312393188,
|
| 887 |
+
"eval_runtime": 12.9429,
|
| 888 |
+
"eval_samples_per_second": 162.483,
|
| 889 |
+
"eval_steps_per_second": 20.32,
|
| 890 |
"step": 1100
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 0.8538461538461538,
|
| 894 |
+
"grad_norm": 4.73284912109375,
|
| 895 |
+
"learning_rate": 0.00016590769230769232,
|
| 896 |
+
"loss": 0.4132,
|
| 897 |
"step": 1110
|
| 898 |
},
|
| 899 |
{
|
| 900 |
"epoch": 0.8615384615384616,
|
| 901 |
+
"grad_norm": 8.023744583129883,
|
| 902 |
+
"learning_rate": 0.0001656,
|
| 903 |
+
"loss": 0.2097,
|
| 904 |
"step": 1120
|
| 905 |
},
|
| 906 |
{
|
| 907 |
"epoch": 0.8692307692307693,
|
| 908 |
+
"grad_norm": 0.5264157652854919,
|
| 909 |
+
"learning_rate": 0.0001652923076923077,
|
| 910 |
+
"loss": 0.2644,
|
| 911 |
"step": 1130
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 0.8769230769230769,
|
| 915 |
+
"grad_norm": 0.09222064912319183,
|
| 916 |
+
"learning_rate": 0.00016498461538461538,
|
| 917 |
+
"loss": 0.3584,
|
| 918 |
"step": 1140
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 0.8846153846153846,
|
| 922 |
+
"grad_norm": 5.8107757568359375,
|
| 923 |
+
"learning_rate": 0.00016467692307692308,
|
| 924 |
+
"loss": 0.1727,
|
| 925 |
"step": 1150
|
| 926 |
},
|
| 927 |
{
|
| 928 |
"epoch": 0.8923076923076924,
|
| 929 |
+
"grad_norm": 0.7490300536155701,
|
| 930 |
+
"learning_rate": 0.00016436923076923078,
|
| 931 |
+
"loss": 0.3538,
|
| 932 |
"step": 1160
|
| 933 |
},
|
| 934 |
{
|
| 935 |
"epoch": 0.9,
|
| 936 |
+
"grad_norm": 12.119208335876465,
|
| 937 |
+
"learning_rate": 0.00016406153846153847,
|
| 938 |
+
"loss": 0.1684,
|
| 939 |
"step": 1170
|
| 940 |
},
|
| 941 |
{
|
| 942 |
"epoch": 0.9076923076923077,
|
| 943 |
+
"grad_norm": 6.949498176574707,
|
| 944 |
+
"learning_rate": 0.00016375384615384617,
|
| 945 |
+
"loss": 0.2705,
|
| 946 |
"step": 1180
|
| 947 |
},
|
| 948 |
{
|
| 949 |
"epoch": 0.9153846153846154,
|
| 950 |
+
"grad_norm": 7.305801868438721,
|
| 951 |
+
"learning_rate": 0.00016344615384615384,
|
| 952 |
+
"loss": 0.226,
|
| 953 |
"step": 1190
|
| 954 |
},
|
| 955 |
{
|
| 956 |
"epoch": 0.9230769230769231,
|
| 957 |
+
"grad_norm": 5.5069684982299805,
|
| 958 |
+
"learning_rate": 0.00016313846153846154,
|
| 959 |
+
"loss": 0.1783,
|
| 960 |
"step": 1200
|
| 961 |
},
|
| 962 |
{
|
| 963 |
"epoch": 0.9230769230769231,
|
| 964 |
+
"eval_accuracy": 0.7883975273418925,
|
| 965 |
+
"eval_f1": 0.7973086083953446,
|
| 966 |
+
"eval_loss": 0.8585250973701477,
|
| 967 |
+
"eval_runtime": 12.7217,
|
| 968 |
+
"eval_samples_per_second": 165.309,
|
| 969 |
+
"eval_steps_per_second": 20.673,
|
| 970 |
"step": 1200
|
| 971 |
},
|
| 972 |
{
|
| 973 |
"epoch": 0.9307692307692308,
|
| 974 |
+
"grad_norm": 0.19160787761211395,
|
| 975 |
+
"learning_rate": 0.00016283076923076924,
|
| 976 |
+
"loss": 0.2238,
|
| 977 |
"step": 1210
|
| 978 |
},
|
| 979 |
{
|
| 980 |
"epoch": 0.9384615384615385,
|
| 981 |
+
"grad_norm": 8.888996124267578,
|
| 982 |
+
"learning_rate": 0.00016252307692307693,
|
| 983 |
+
"loss": 0.3376,
|
| 984 |
"step": 1220
|
| 985 |
},
|
| 986 |
{
|
| 987 |
"epoch": 0.9461538461538461,
|
| 988 |
+
"grad_norm": 0.8629558086395264,
|
| 989 |
+
"learning_rate": 0.0001622153846153846,
|
| 990 |
+
"loss": 0.1931,
|
| 991 |
"step": 1230
|
| 992 |
},
|
| 993 |
{
|
| 994 |
"epoch": 0.9538461538461539,
|
| 995 |
+
"grad_norm": 9.519225120544434,
|
| 996 |
+
"learning_rate": 0.00016190769230769233,
|
| 997 |
+
"loss": 0.4684,
|
| 998 |
"step": 1240
|
| 999 |
},
|
| 1000 |
{
|
| 1001 |
"epoch": 0.9615384615384616,
|
| 1002 |
+
"grad_norm": 14.200179100036621,
|
| 1003 |
+
"learning_rate": 0.00016160000000000002,
|
| 1004 |
+
"loss": 0.4139,
|
| 1005 |
"step": 1250
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 0.9692307692307692,
|
| 1009 |
+
"grad_norm": 7.553689479827881,
|
| 1010 |
+
"learning_rate": 0.0001612923076923077,
|
| 1011 |
+
"loss": 0.0796,
|
| 1012 |
"step": 1260
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
"epoch": 0.9769230769230769,
|
| 1016 |
+
"grad_norm": 0.355137437582016,
|
| 1017 |
+
"learning_rate": 0.0001609846153846154,
|
| 1018 |
+
"loss": 0.2785,
|
| 1019 |
"step": 1270
|
| 1020 |
},
|
| 1021 |
{
|
| 1022 |
"epoch": 0.9846153846153847,
|
| 1023 |
+
"grad_norm": 10.454266548156738,
|
| 1024 |
+
"learning_rate": 0.0001606769230769231,
|
| 1025 |
+
"loss": 0.2214,
|
| 1026 |
"step": 1280
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
"epoch": 0.9923076923076923,
|
| 1030 |
+
"grad_norm": 4.790037631988525,
|
| 1031 |
+
"learning_rate": 0.0001603692307692308,
|
| 1032 |
+
"loss": 0.2865,
|
| 1033 |
"step": 1290
|
| 1034 |
},
|
| 1035 |
{
|
| 1036 |
"epoch": 1.0,
|
| 1037 |
+
"grad_norm": 0.6874844431877136,
|
| 1038 |
+
"learning_rate": 0.00016006153846153846,
|
| 1039 |
+
"loss": 0.2812,
|
| 1040 |
"step": 1300
|
| 1041 |
},
|
| 1042 |
{
|
| 1043 |
"epoch": 1.0,
|
| 1044 |
+
"eval_accuracy": 0.7394198763670946,
|
| 1045 |
+
"eval_f1": 0.7475294511131121,
|
| 1046 |
+
"eval_loss": 1.416084885597229,
|
| 1047 |
+
"eval_runtime": 12.6074,
|
| 1048 |
+
"eval_samples_per_second": 166.807,
|
| 1049 |
+
"eval_steps_per_second": 20.861,
|
| 1050 |
"step": 1300
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
"epoch": 1.0076923076923077,
|
| 1054 |
+
"grad_norm": 27.64440155029297,
|
| 1055 |
+
"learning_rate": 0.00015975384615384615,
|
| 1056 |
+
"loss": 0.3337,
|
| 1057 |
"step": 1310
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
"epoch": 1.0153846153846153,
|
| 1061 |
+
"grad_norm": 6.039366722106934,
|
| 1062 |
+
"learning_rate": 0.00015944615384615385,
|
| 1063 |
+
"loss": 0.1274,
|
| 1064 |
"step": 1320
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
"epoch": 1.023076923076923,
|
| 1068 |
+
"grad_norm": 2.63989520072937,
|
| 1069 |
+
"learning_rate": 0.00015913846153846155,
|
| 1070 |
+
"loss": 0.1286,
|
| 1071 |
"step": 1330
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 1.0307692307692307,
|
| 1075 |
+
"grad_norm": 0.025664901360869408,
|
| 1076 |
+
"learning_rate": 0.00015883076923076922,
|
| 1077 |
+
"loss": 0.0268,
|
| 1078 |
"step": 1340
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
"epoch": 1.0384615384615385,
|
| 1082 |
+
"grad_norm": 0.7110622525215149,
|
| 1083 |
+
"learning_rate": 0.00015852307692307692,
|
| 1084 |
+
"loss": 0.2141,
|
| 1085 |
"step": 1350
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 1.0461538461538462,
|
| 1089 |
+
"grad_norm": 0.16841351985931396,
|
| 1090 |
+
"learning_rate": 0.00015821538461538464,
|
| 1091 |
+
"loss": 0.1706,
|
| 1092 |
"step": 1360
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 1.0538461538461539,
|
| 1096 |
+
"grad_norm": 2.8135828971862793,
|
| 1097 |
+
"learning_rate": 0.0001579076923076923,
|
| 1098 |
+
"loss": 0.213,
|
| 1099 |
"step": 1370
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
"epoch": 1.0615384615384615,
|
| 1103 |
+
"grad_norm": 6.7190937995910645,
|
| 1104 |
+
"learning_rate": 0.0001576,
|
| 1105 |
+
"loss": 0.1559,
|
| 1106 |
"step": 1380
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 1.0692307692307692,
|
| 1110 |
+
"grad_norm": 1.2817728519439697,
|
| 1111 |
+
"learning_rate": 0.0001572923076923077,
|
| 1112 |
+
"loss": 0.1296,
|
| 1113 |
"step": 1390
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
"epoch": 1.0769230769230769,
|
| 1117 |
+
"grad_norm": 8.388606071472168,
|
| 1118 |
+
"learning_rate": 0.0001569846153846154,
|
| 1119 |
+
"loss": 0.0788,
|
| 1120 |
"step": 1400
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 1.0769230769230769,
|
| 1124 |
+
"eval_accuracy": 0.7769852591535901,
|
| 1125 |
+
"eval_f1": 0.7855219452383467,
|
| 1126 |
+
"eval_loss": 1.0477243661880493,
|
| 1127 |
+
"eval_runtime": 12.6229,
|
| 1128 |
+
"eval_samples_per_second": 166.602,
|
| 1129 |
+
"eval_steps_per_second": 20.835,
|
| 1130 |
"step": 1400
|
| 1131 |
},
|
| 1132 |
{
|
| 1133 |
"epoch": 1.0846153846153845,
|
| 1134 |
+
"grad_norm": 9.62314510345459,
|
| 1135 |
+
"learning_rate": 0.00015667692307692307,
|
| 1136 |
+
"loss": 0.421,
|
| 1137 |
"step": 1410
|
| 1138 |
},
|
| 1139 |
{
|
| 1140 |
"epoch": 1.0923076923076924,
|
| 1141 |
+
"grad_norm": 6.402166366577148,
|
| 1142 |
+
"learning_rate": 0.00015636923076923077,
|
| 1143 |
+
"loss": 0.1328,
|
| 1144 |
"step": 1420
|
| 1145 |
},
|
| 1146 |
{
|
| 1147 |
"epoch": 1.1,
|
| 1148 |
+
"grad_norm": 3.701634168624878,
|
| 1149 |
+
"learning_rate": 0.00015606153846153847,
|
| 1150 |
+
"loss": 0.0716,
|
| 1151 |
"step": 1430
|
| 1152 |
},
|
| 1153 |
{
|
| 1154 |
"epoch": 1.1076923076923078,
|
| 1155 |
+
"grad_norm": 0.01674058847129345,
|
| 1156 |
+
"learning_rate": 0.00015575384615384617,
|
| 1157 |
+
"loss": 0.0287,
|
| 1158 |
"step": 1440
|
| 1159 |
},
|
| 1160 |
{
|
| 1161 |
"epoch": 1.1153846153846154,
|
| 1162 |
+
"grad_norm": 1.9546364545822144,
|
| 1163 |
+
"learning_rate": 0.00015544615384615386,
|
| 1164 |
+
"loss": 0.2283,
|
| 1165 |
"step": 1450
|
| 1166 |
},
|
| 1167 |
{
|
| 1168 |
"epoch": 1.123076923076923,
|
| 1169 |
+
"grad_norm": 14.071533203125,
|
| 1170 |
+
"learning_rate": 0.00015513846153846153,
|
| 1171 |
+
"loss": 0.3448,
|
| 1172 |
"step": 1460
|
| 1173 |
},
|
| 1174 |
{
|
| 1175 |
"epoch": 1.1307692307692307,
|
| 1176 |
+
"grad_norm": 4.5133585929870605,
|
| 1177 |
+
"learning_rate": 0.00015483076923076926,
|
| 1178 |
+
"loss": 0.0917,
|
| 1179 |
"step": 1470
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
"epoch": 1.1384615384615384,
|
| 1183 |
+
"grad_norm": 1.5091907978057861,
|
| 1184 |
+
"learning_rate": 0.00015452307692307693,
|
| 1185 |
+
"loss": 0.2924,
|
| 1186 |
"step": 1480
|
| 1187 |
},
|
| 1188 |
{
|
| 1189 |
"epoch": 1.146153846153846,
|
| 1190 |
+
"grad_norm": 0.01831883378326893,
|
| 1191 |
+
"learning_rate": 0.00015421538461538463,
|
| 1192 |
+
"loss": 0.167,
|
| 1193 |
"step": 1490
|
| 1194 |
},
|
| 1195 |
{
|
| 1196 |
"epoch": 1.1538461538461537,
|
| 1197 |
+
"grad_norm": 0.15469826757907867,
|
| 1198 |
+
"learning_rate": 0.0001539076923076923,
|
| 1199 |
+
"loss": 0.1853,
|
| 1200 |
"step": 1500
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 1.1538461538461537,
|
| 1204 |
+
"eval_accuracy": 0.7788873038516405,
|
| 1205 |
+
"eval_f1": 0.7907369196346151,
|
| 1206 |
+
"eval_loss": 1.0843039751052856,
|
| 1207 |
+
"eval_runtime": 12.9085,
|
| 1208 |
+
"eval_samples_per_second": 162.916,
|
| 1209 |
+
"eval_steps_per_second": 20.374,
|
| 1210 |
"step": 1500
|
| 1211 |
},
|
| 1212 |
{
|
| 1213 |
"epoch": 1.1615384615384616,
|
| 1214 |
+
"grad_norm": 0.009273377247154713,
|
| 1215 |
+
"learning_rate": 0.00015360000000000002,
|
| 1216 |
+
"loss": 0.133,
|
| 1217 |
"step": 1510
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
"epoch": 1.1692307692307693,
|
| 1221 |
+
"grad_norm": 19.926687240600586,
|
| 1222 |
+
"learning_rate": 0.0001532923076923077,
|
| 1223 |
+
"loss": 0.1644,
|
| 1224 |
"step": 1520
|
| 1225 |
},
|
| 1226 |
{
|
| 1227 |
"epoch": 1.176923076923077,
|
| 1228 |
+
"grad_norm": 2.141300678253174,
|
| 1229 |
+
"learning_rate": 0.0001529846153846154,
|
| 1230 |
+
"loss": 0.2778,
|
| 1231 |
"step": 1530
|
| 1232 |
},
|
| 1233 |
{
|
| 1234 |
"epoch": 1.1846153846153846,
|
| 1235 |
+
"grad_norm": 9.439351081848145,
|
| 1236 |
+
"learning_rate": 0.00015267692307692309,
|
| 1237 |
+
"loss": 0.1928,
|
| 1238 |
"step": 1540
|
| 1239 |
},
|
| 1240 |
{
|
| 1241 |
"epoch": 1.1923076923076923,
|
| 1242 |
+
"grad_norm": 2.3497989177703857,
|
| 1243 |
+
"learning_rate": 0.00015236923076923078,
|
| 1244 |
+
"loss": 0.0872,
|
| 1245 |
"step": 1550
|
| 1246 |
},
|
| 1247 |
{
|
| 1248 |
"epoch": 1.2,
|
| 1249 |
+
"grad_norm": 0.3300742506980896,
|
| 1250 |
+
"learning_rate": 0.00015206153846153848,
|
| 1251 |
+
"loss": 0.0773,
|
| 1252 |
"step": 1560
|
| 1253 |
},
|
| 1254 |
{
|
| 1255 |
"epoch": 1.2076923076923076,
|
| 1256 |
+
"grad_norm": 4.574916839599609,
|
| 1257 |
+
"learning_rate": 0.00015175384615384615,
|
| 1258 |
+
"loss": 0.1768,
|
| 1259 |
"step": 1570
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 1.2153846153846155,
|
| 1263 |
+
"grad_norm": 2.860717535018921,
|
| 1264 |
+
"learning_rate": 0.00015144615384615385,
|
| 1265 |
+
"loss": 0.1335,
|
| 1266 |
"step": 1580
|
| 1267 |
},
|
| 1268 |
{
|
| 1269 |
"epoch": 1.2230769230769232,
|
| 1270 |
+
"grad_norm": 0.060734041035175323,
|
| 1271 |
+
"learning_rate": 0.00015113846153846154,
|
| 1272 |
+
"loss": 0.1425,
|
| 1273 |
"step": 1590
|
| 1274 |
},
|
| 1275 |
{
|
| 1276 |
"epoch": 1.2307692307692308,
|
| 1277 |
+
"grad_norm": 2.519880533218384,
|
| 1278 |
+
"learning_rate": 0.00015083076923076924,
|
| 1279 |
+
"loss": 0.0463,
|
| 1280 |
"step": 1600
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
"epoch": 1.2307692307692308,
|
| 1284 |
+
"eval_accuracy": 0.785544460294817,
|
| 1285 |
+
"eval_f1": 0.7421672482958516,
|
| 1286 |
+
"eval_loss": 1.1819196939468384,
|
| 1287 |
+
"eval_runtime": 12.7239,
|
| 1288 |
+
"eval_samples_per_second": 165.279,
|
| 1289 |
+
"eval_steps_per_second": 20.67,
|
| 1290 |
"step": 1600
|
| 1291 |
},
|
| 1292 |
{
|
| 1293 |
"epoch": 1.2384615384615385,
|
| 1294 |
+
"grad_norm": 0.014092416502535343,
|
| 1295 |
+
"learning_rate": 0.0001505230769230769,
|
| 1296 |
+
"loss": 0.347,
|
| 1297 |
"step": 1610
|
| 1298 |
},
|
| 1299 |
{
|
| 1300 |
"epoch": 1.2461538461538462,
|
| 1301 |
+
"grad_norm": 0.021726811304688454,
|
| 1302 |
+
"learning_rate": 0.00015021538461538464,
|
| 1303 |
+
"loss": 0.1134,
|
| 1304 |
"step": 1620
|
| 1305 |
},
|
| 1306 |
{
|
| 1307 |
"epoch": 1.2538461538461538,
|
| 1308 |
+
"grad_norm": 0.019754081964492798,
|
| 1309 |
+
"learning_rate": 0.0001499076923076923,
|
| 1310 |
+
"loss": 0.1126,
|
| 1311 |
"step": 1630
|
| 1312 |
},
|
| 1313 |
{
|
| 1314 |
"epoch": 1.2615384615384615,
|
| 1315 |
+
"grad_norm": 0.018249794840812683,
|
| 1316 |
+
"learning_rate": 0.0001496,
|
| 1317 |
+
"loss": 0.0706,
|
| 1318 |
"step": 1640
|
| 1319 |
},
|
| 1320 |
{
|
| 1321 |
"epoch": 1.2692307692307692,
|
| 1322 |
+
"grad_norm": 0.013677536509931087,
|
| 1323 |
+
"learning_rate": 0.0001492923076923077,
|
| 1324 |
+
"loss": 0.0554,
|
| 1325 |
"step": 1650
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
"epoch": 1.2769230769230768,
|
| 1329 |
+
"grad_norm": 11.756999969482422,
|
| 1330 |
+
"learning_rate": 0.0001489846153846154,
|
| 1331 |
+
"loss": 0.3888,
|
| 1332 |
"step": 1660
|
| 1333 |
},
|
| 1334 |
{
|
| 1335 |
"epoch": 1.2846153846153845,
|
| 1336 |
+
"grad_norm": 0.5001311898231506,
|
| 1337 |
+
"learning_rate": 0.0001486769230769231,
|
| 1338 |
+
"loss": 0.3604,
|
| 1339 |
"step": 1670
|
| 1340 |
},
|
| 1341 |
{
|
| 1342 |
"epoch": 1.2923076923076924,
|
| 1343 |
+
"grad_norm": 4.095685005187988,
|
| 1344 |
+
"learning_rate": 0.00014836923076923077,
|
| 1345 |
+
"loss": 0.0589,
|
| 1346 |
"step": 1680
|
| 1347 |
},
|
| 1348 |
{
|
| 1349 |
"epoch": 1.3,
|
| 1350 |
+
"grad_norm": 0.42667385935783386,
|
| 1351 |
+
"learning_rate": 0.00014806153846153846,
|
| 1352 |
+
"loss": 0.1972,
|
| 1353 |
"step": 1690
|
| 1354 |
},
|
| 1355 |
{
|
| 1356 |
"epoch": 1.3076923076923077,
|
| 1357 |
+
"grad_norm": 0.4370737075805664,
|
| 1358 |
+
"learning_rate": 0.00014775384615384616,
|
| 1359 |
+
"loss": 0.1846,
|
| 1360 |
"step": 1700
|
| 1361 |
},
|
| 1362 |
{
|
| 1363 |
"epoch": 1.3076923076923077,
|
| 1364 |
+
"eval_accuracy": 0.7936281502615311,
|
| 1365 |
+
"eval_f1": 0.7834925540357461,
|
| 1366 |
+
"eval_loss": 0.9226651191711426,
|
| 1367 |
+
"eval_runtime": 13.0044,
|
| 1368 |
+
"eval_samples_per_second": 161.714,
|
| 1369 |
+
"eval_steps_per_second": 20.224,
|
| 1370 |
"step": 1700
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 1.3153846153846154,
|
| 1374 |
+
"grad_norm": 2.9129936695098877,
|
| 1375 |
+
"learning_rate": 0.00014744615384615386,
|
| 1376 |
+
"loss": 0.0855,
|
| 1377 |
"step": 1710
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 1.323076923076923,
|
| 1381 |
+
"grad_norm": 0.003025891724973917,
|
| 1382 |
+
"learning_rate": 0.00014713846153846153,
|
| 1383 |
+
"loss": 0.1383,
|
| 1384 |
"step": 1720
|
| 1385 |
},
|
| 1386 |
{
|
| 1387 |
"epoch": 1.3307692307692307,
|
| 1388 |
+
"grad_norm": 20.243345260620117,
|
| 1389 |
+
"learning_rate": 0.00014683076923076923,
|
| 1390 |
+
"loss": 0.3327,
|
| 1391 |
"step": 1730
|
| 1392 |
},
|
| 1393 |
{
|
| 1394 |
"epoch": 1.3384615384615386,
|
| 1395 |
+
"grad_norm": 0.08103461563587189,
|
| 1396 |
+
"learning_rate": 0.00014652307692307695,
|
| 1397 |
+
"loss": 0.0665,
|
| 1398 |
"step": 1740
|
| 1399 |
},
|
| 1400 |
{
|
| 1401 |
"epoch": 1.3461538461538463,
|
| 1402 |
+
"grad_norm": 7.912471771240234,
|
| 1403 |
+
"learning_rate": 0.00014621538461538462,
|
| 1404 |
+
"loss": 0.2611,
|
| 1405 |
"step": 1750
|
| 1406 |
},
|
| 1407 |
{
|
| 1408 |
"epoch": 1.353846153846154,
|
| 1409 |
+
"grad_norm": 3.1439859867095947,
|
| 1410 |
+
"learning_rate": 0.00014590769230769232,
|
| 1411 |
+
"loss": 0.148,
|
| 1412 |
"step": 1760
|
| 1413 |
},
|
| 1414 |
{
|
| 1415 |
"epoch": 1.3615384615384616,
|
| 1416 |
+
"grad_norm": 0.005958245135843754,
|
| 1417 |
+
"learning_rate": 0.00014560000000000002,
|
| 1418 |
+
"loss": 0.2973,
|
| 1419 |
"step": 1770
|
| 1420 |
},
|
| 1421 |
{
|
| 1422 |
"epoch": 1.3692307692307693,
|
| 1423 |
+
"grad_norm": 0.0040934206917881966,
|
| 1424 |
+
"learning_rate": 0.0001452923076923077,
|
| 1425 |
+
"loss": 0.0725,
|
| 1426 |
"step": 1780
|
| 1427 |
},
|
| 1428 |
{
|
| 1429 |
"epoch": 1.376923076923077,
|
| 1430 |
+
"grad_norm": 0.35973867774009705,
|
| 1431 |
+
"learning_rate": 0.00014498461538461538,
|
| 1432 |
+
"loss": 0.2344,
|
| 1433 |
"step": 1790
|
| 1434 |
},
|
| 1435 |
{
|
| 1436 |
"epoch": 1.3846153846153846,
|
| 1437 |
+
"grad_norm": 1.3999979496002197,
|
| 1438 |
+
"learning_rate": 0.00014467692307692308,
|
| 1439 |
+
"loss": 0.0886,
|
| 1440 |
"step": 1800
|
| 1441 |
},
|
| 1442 |
{
|
| 1443 |
"epoch": 1.3846153846153846,
|
| 1444 |
+
"eval_accuracy": 0.755587256300523,
|
| 1445 |
+
"eval_f1": 0.760332968619484,
|
| 1446 |
+
"eval_loss": 1.336824655532837,
|
| 1447 |
+
"eval_runtime": 13.0885,
|
| 1448 |
+
"eval_samples_per_second": 160.676,
|
| 1449 |
+
"eval_steps_per_second": 20.094,
|
| 1450 |
"step": 1800
|
| 1451 |
},
|
| 1452 |
{
|
| 1453 |
"epoch": 1.3923076923076922,
|
| 1454 |
+
"grad_norm": 12.196135520935059,
|
| 1455 |
+
"learning_rate": 0.00014436923076923078,
|
| 1456 |
+
"loss": 0.1538,
|
| 1457 |
"step": 1810
|
| 1458 |
},
|
| 1459 |
{
|
| 1460 |
"epoch": 1.4,
|
| 1461 |
+
"grad_norm": 0.052580125629901886,
|
| 1462 |
+
"learning_rate": 0.00014406153846153848,
|
| 1463 |
+
"loss": 0.287,
|
| 1464 |
"step": 1820
|
| 1465 |
},
|
| 1466 |
{
|
| 1467 |
"epoch": 1.4076923076923076,
|
| 1468 |
+
"grad_norm": 15.731462478637695,
|
| 1469 |
+
"learning_rate": 0.00014375384615384615,
|
| 1470 |
+
"loss": 0.2438,
|
| 1471 |
"step": 1830
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 1.4153846153846155,
|
| 1475 |
+
"grad_norm": 1.4881103038787842,
|
| 1476 |
+
"learning_rate": 0.00014344615384615384,
|
| 1477 |
+
"loss": 0.0786,
|
| 1478 |
"step": 1840
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
"epoch": 1.4230769230769231,
|
| 1482 |
+
"grad_norm": 0.061750538647174835,
|
| 1483 |
+
"learning_rate": 0.00014313846153846157,
|
| 1484 |
+
"loss": 0.1427,
|
| 1485 |
"step": 1850
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
"epoch": 1.4307692307692308,
|
| 1489 |
+
"grad_norm": 0.21189741790294647,
|
| 1490 |
+
"learning_rate": 0.00014283076923076924,
|
| 1491 |
+
"loss": 0.1164,
|
| 1492 |
"step": 1860
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
"epoch": 1.4384615384615385,
|
| 1496 |
+
"grad_norm": 0.04826455935835838,
|
| 1497 |
+
"learning_rate": 0.00014252307692307693,
|
| 1498 |
+
"loss": 0.0384,
|
| 1499 |
"step": 1870
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
"epoch": 1.4461538461538461,
|
| 1503 |
+
"grad_norm": 1.3123809099197388,
|
| 1504 |
+
"learning_rate": 0.0001422153846153846,
|
| 1505 |
+
"loss": 0.4418,
|
| 1506 |
"step": 1880
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
"epoch": 1.4538461538461538,
|
| 1510 |
+
"grad_norm": 14.41169548034668,
|
| 1511 |
+
"learning_rate": 0.00014190769230769233,
|
| 1512 |
+
"loss": 0.0724,
|
| 1513 |
"step": 1890
|
| 1514 |
},
|
| 1515 |
{
|
| 1516 |
"epoch": 1.4615384615384617,
|
| 1517 |
+
"grad_norm": 0.010243662633001804,
|
| 1518 |
+
"learning_rate": 0.0001416,
|
| 1519 |
+
"loss": 0.1971,
|
| 1520 |
"step": 1900
|
| 1521 |
},
|
| 1522 |
{
|
| 1523 |
"epoch": 1.4615384615384617,
|
| 1524 |
+
"eval_accuracy": 0.7527341892534475,
|
| 1525 |
+
"eval_f1": 0.7412732500492302,
|
| 1526 |
+
"eval_loss": 1.3275840282440186,
|
| 1527 |
+
"eval_runtime": 13.034,
|
| 1528 |
+
"eval_samples_per_second": 161.348,
|
| 1529 |
+
"eval_steps_per_second": 20.178,
|
| 1530 |
"step": 1900
|
| 1531 |
},
|
| 1532 |
{
|
| 1533 |
"epoch": 1.4692307692307693,
|
| 1534 |
+
"grad_norm": 0.004571467638015747,
|
| 1535 |
+
"learning_rate": 0.0001412923076923077,
|
| 1536 |
+
"loss": 0.2237,
|
| 1537 |
"step": 1910
|
| 1538 |
},
|
| 1539 |
{
|
| 1540 |
"epoch": 1.476923076923077,
|
| 1541 |
+
"grad_norm": 0.652137279510498,
|
| 1542 |
+
"learning_rate": 0.0001409846153846154,
|
| 1543 |
+
"loss": 0.1416,
|
| 1544 |
"step": 1920
|
| 1545 |
},
|
| 1546 |
{
|
| 1547 |
"epoch": 1.4846153846153847,
|
| 1548 |
+
"grad_norm": 1.6183210611343384,
|
| 1549 |
+
"learning_rate": 0.0001406769230769231,
|
| 1550 |
+
"loss": 0.1199,
|
| 1551 |
"step": 1930
|
| 1552 |
},
|
| 1553 |
{
|
| 1554 |
"epoch": 1.4923076923076923,
|
| 1555 |
+
"grad_norm": 6.971846103668213,
|
| 1556 |
+
"learning_rate": 0.0001403692307692308,
|
| 1557 |
+
"loss": 0.1777,
|
| 1558 |
"step": 1940
|
| 1559 |
},
|
| 1560 |
{
|
| 1561 |
"epoch": 1.5,
|
| 1562 |
+
"grad_norm": 1.2869207859039307,
|
| 1563 |
+
"learning_rate": 0.00014006153846153846,
|
| 1564 |
+
"loss": 0.1312,
|
| 1565 |
"step": 1950
|
| 1566 |
},
|
| 1567 |
{
|
| 1568 |
"epoch": 1.5076923076923077,
|
| 1569 |
+
"grad_norm": 11.167072296142578,
|
| 1570 |
+
"learning_rate": 0.00013975384615384616,
|
| 1571 |
+
"loss": 0.1798,
|
| 1572 |
"step": 1960
|
| 1573 |
},
|
| 1574 |
{
|
| 1575 |
"epoch": 1.5153846153846153,
|
| 1576 |
+
"grad_norm": 3.460939407348633,
|
| 1577 |
+
"learning_rate": 0.00013944615384615385,
|
| 1578 |
+
"loss": 0.0561,
|
| 1579 |
"step": 1970
|
| 1580 |
},
|
| 1581 |
{
|
| 1582 |
"epoch": 1.523076923076923,
|
| 1583 |
+
"grad_norm": 13.122215270996094,
|
| 1584 |
+
"learning_rate": 0.00013913846153846155,
|
| 1585 |
+
"loss": 0.3705,
|
| 1586 |
"step": 1980
|
| 1587 |
},
|
| 1588 |
{
|
| 1589 |
"epoch": 1.5307692307692307,
|
| 1590 |
+
"grad_norm": 0.06862486898899078,
|
| 1591 |
+
"learning_rate": 0.00013883076923076922,
|
| 1592 |
+
"loss": 0.0927,
|
| 1593 |
"step": 1990
|
| 1594 |
},
|
| 1595 |
{
|
| 1596 |
"epoch": 1.5384615384615383,
|
| 1597 |
+
"grad_norm": 0.11031440645456314,
|
| 1598 |
+
"learning_rate": 0.00013852307692307695,
|
| 1599 |
+
"loss": 0.2069,
|
| 1600 |
"step": 2000
|
| 1601 |
},
|
| 1602 |
{
|
| 1603 |
"epoch": 1.5384615384615383,
|
| 1604 |
+
"eval_accuracy": 0.7727056585829767,
|
| 1605 |
+
"eval_f1": 0.7804628247388471,
|
| 1606 |
+
"eval_loss": 1.3338302373886108,
|
| 1607 |
+
"eval_runtime": 12.9099,
|
| 1608 |
+
"eval_samples_per_second": 162.898,
|
| 1609 |
+
"eval_steps_per_second": 20.372,
|
| 1610 |
"step": 2000
|
| 1611 |
},
|
| 1612 |
{
|
| 1613 |
"epoch": 1.546153846153846,
|
| 1614 |
+
"grad_norm": 0.09383740276098251,
|
| 1615 |
+
"learning_rate": 0.00013821538461538462,
|
| 1616 |
+
"loss": 0.1164,
|
| 1617 |
"step": 2010
|
| 1618 |
},
|
| 1619 |
{
|
| 1620 |
"epoch": 1.5538461538461539,
|
| 1621 |
+
"grad_norm": 0.005354443099349737,
|
| 1622 |
+
"learning_rate": 0.0001379076923076923,
|
| 1623 |
+
"loss": 0.1628,
|
| 1624 |
"step": 2020
|
| 1625 |
},
|
| 1626 |
{
|
| 1627 |
"epoch": 1.5615384615384615,
|
| 1628 |
+
"grad_norm": 0.48392564058303833,
|
| 1629 |
+
"learning_rate": 0.00013759999999999998,
|
| 1630 |
+
"loss": 0.107,
|
| 1631 |
"step": 2030
|
| 1632 |
},
|
| 1633 |
{
|
| 1634 |
"epoch": 1.5692307692307692,
|
| 1635 |
+
"grad_norm": 0.013797705993056297,
|
| 1636 |
"learning_rate": 0.00013732307692307694,
|
| 1637 |
+
"loss": 0.1443,
|
| 1638 |
"step": 2040
|
| 1639 |
},
|
| 1640 |
{
|
| 1641 |
"epoch": 1.5769230769230769,
|
| 1642 |
+
"grad_norm": 0.0021225737873464823,
|
| 1643 |
"learning_rate": 0.00013701538461538461,
|
| 1644 |
+
"loss": 0.0892,
|
| 1645 |
"step": 2050
|
| 1646 |
},
|
| 1647 |
{
|
| 1648 |
"epoch": 1.5846153846153848,
|
| 1649 |
+
"grad_norm": 0.409858763217926,
|
| 1650 |
"learning_rate": 0.0001367076923076923,
|
| 1651 |
+
"loss": 0.1198,
|
| 1652 |
"step": 2060
|
| 1653 |
},
|
| 1654 |
{
|
| 1655 |
"epoch": 1.5923076923076924,
|
| 1656 |
+
"grad_norm": 0.07346770912408829,
|
| 1657 |
"learning_rate": 0.0001364,
|
| 1658 |
+
"loss": 0.1431,
|
| 1659 |
"step": 2070
|
| 1660 |
},
|
| 1661 |
{
|
| 1662 |
"epoch": 1.6,
|
| 1663 |
+
"grad_norm": 0.07542140781879425,
|
| 1664 |
"learning_rate": 0.0001360923076923077,
|
| 1665 |
+
"loss": 0.0692,
|
| 1666 |
"step": 2080
|
| 1667 |
},
|
| 1668 |
{
|
| 1669 |
"epoch": 1.6076923076923078,
|
| 1670 |
+
"grad_norm": 12.474515914916992,
|
| 1671 |
"learning_rate": 0.0001357846153846154,
|
| 1672 |
+
"loss": 0.2697,
|
| 1673 |
"step": 2090
|
| 1674 |
},
|
| 1675 |
{
|
| 1676 |
"epoch": 1.6153846153846154,
|
| 1677 |
+
"grad_norm": 1.3258837461471558,
|
| 1678 |
"learning_rate": 0.00013547692307692307,
|
| 1679 |
+
"loss": 0.1479,
|
| 1680 |
"step": 2100
|
| 1681 |
},
|
| 1682 |
{
|
| 1683 |
"epoch": 1.6153846153846154,
|
| 1684 |
+
"eval_accuracy": 0.7717546362339515,
|
| 1685 |
+
"eval_f1": 0.8021104948644624,
|
| 1686 |
+
"eval_loss": 1.2605870962142944,
|
| 1687 |
+
"eval_runtime": 12.6589,
|
| 1688 |
+
"eval_samples_per_second": 166.128,
|
| 1689 |
+
"eval_steps_per_second": 20.776,
|
| 1690 |
"step": 2100
|
| 1691 |
},
|
| 1692 |
{
|
| 1693 |
"epoch": 1.623076923076923,
|
| 1694 |
+
"grad_norm": 0.09133293479681015,
|
| 1695 |
"learning_rate": 0.00013516923076923077,
|
| 1696 |
+
"loss": 0.0579,
|
| 1697 |
"step": 2110
|
| 1698 |
},
|
| 1699 |
{
|
| 1700 |
"epoch": 1.6307692307692307,
|
| 1701 |
+
"grad_norm": 0.13408294320106506,
|
| 1702 |
"learning_rate": 0.00013486153846153847,
|
| 1703 |
+
"loss": 0.1774,
|
| 1704 |
"step": 2120
|
| 1705 |
},
|
| 1706 |
{
|
| 1707 |
"epoch": 1.6384615384615384,
|
| 1708 |
+
"grad_norm": 0.02371808886528015,
|
| 1709 |
"learning_rate": 0.00013455384615384617,
|
| 1710 |
+
"loss": 0.1071,
|
| 1711 |
"step": 2130
|
| 1712 |
},
|
| 1713 |
{
|
| 1714 |
"epoch": 1.646153846153846,
|
| 1715 |
+
"grad_norm": 0.03445754200220108,
|
| 1716 |
"learning_rate": 0.00013424615384615384,
|
| 1717 |
+
"loss": 0.063,
|
| 1718 |
"step": 2140
|
| 1719 |
},
|
| 1720 |
{
|
| 1721 |
"epoch": 1.6538461538461537,
|
| 1722 |
+
"grad_norm": 11.491479873657227,
|
| 1723 |
"learning_rate": 0.00013393846153846153,
|
| 1724 |
+
"loss": 0.1706,
|
| 1725 |
"step": 2150
|
| 1726 |
},
|
| 1727 |
{
|
| 1728 |
"epoch": 1.6615384615384614,
|
| 1729 |
+
"grad_norm": 5.018512725830078,
|
| 1730 |
"learning_rate": 0.00013363076923076926,
|
| 1731 |
+
"loss": 0.126,
|
| 1732 |
"step": 2160
|
| 1733 |
},
|
| 1734 |
{
|
| 1735 |
"epoch": 1.669230769230769,
|
| 1736 |
+
"grad_norm": 0.008263733237981796,
|
| 1737 |
"learning_rate": 0.00013332307692307693,
|
| 1738 |
+
"loss": 0.1425,
|
| 1739 |
"step": 2170
|
| 1740 |
},
|
| 1741 |
{
|
| 1742 |
"epoch": 1.676923076923077,
|
| 1743 |
+
"grad_norm": 1.61963951587677,
|
| 1744 |
"learning_rate": 0.00013301538461538463,
|
| 1745 |
+
"loss": 0.2236,
|
| 1746 |
"step": 2180
|
| 1747 |
},
|
| 1748 |
{
|
| 1749 |
"epoch": 1.6846153846153846,
|
| 1750 |
+
"grad_norm": 0.2399456948041916,
|
| 1751 |
"learning_rate": 0.00013270769230769232,
|
| 1752 |
+
"loss": 0.2712,
|
| 1753 |
"step": 2190
|
| 1754 |
},
|
| 1755 |
{
|
| 1756 |
"epoch": 1.6923076923076923,
|
| 1757 |
+
"grad_norm": 16.2120418548584,
|
| 1758 |
"learning_rate": 0.00013240000000000002,
|
| 1759 |
+
"loss": 0.1076,
|
| 1760 |
"step": 2200
|
| 1761 |
},
|
| 1762 |
{
|
| 1763 |
"epoch": 1.6923076923076923,
|
| 1764 |
+
"eval_accuracy": 0.8007608178792202,
|
| 1765 |
+
"eval_f1": 0.8183142194677944,
|
| 1766 |
+
"eval_loss": 0.9954975247383118,
|
| 1767 |
+
"eval_runtime": 12.719,
|
| 1768 |
+
"eval_samples_per_second": 165.344,
|
| 1769 |
+
"eval_steps_per_second": 20.678,
|
| 1770 |
"step": 2200
|
| 1771 |
},
|
| 1772 |
{
|
| 1773 |
+
"epoch": 1.6923076923076923,
|
| 1774 |
+
"step": 2200,
|
| 1775 |
+
"total_flos": 1.3637892549580186e+18,
|
| 1776 |
+
"train_loss": 0.3320726641470736,
|
| 1777 |
+
"train_runtime": 627.5337,
|
| 1778 |
+
"train_samples_per_second": 82.824,
|
| 1779 |
+
"train_steps_per_second": 10.358
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1780 |
}
|
| 1781 |
],
|
| 1782 |
"logging_steps": 10,
|
|
|
|
| 1788 |
"EarlyStoppingCallback": {
|
| 1789 |
"args": {
|
| 1790 |
"early_stopping_patience": 10,
|
| 1791 |
+
"early_stopping_threshold": 0.0001
|
| 1792 |
},
|
| 1793 |
"attributes": {
|
| 1794 |
"early_stopping_patience_counter": 10
|
|
|
|
| 1805 |
"attributes": {}
|
| 1806 |
}
|
| 1807 |
},
|
| 1808 |
+
"total_flos": 1.3637892549580186e+18,
|
| 1809 |
"train_batch_size": 8,
|
| 1810 |
"trial_name": null,
|
| 1811 |
"trial_params": null
|