🍻 cheers
Browse files- README.md +4 -3
- all_results.json +9 -9
- data/events.out.tfevents.1730711565.0894b137f84e.248.1 +3 -0
- eval_results.json +5 -5
- train_results.json +4 -4
- trainer_state.json +390 -390
README.md
CHANGED
|
@@ -3,6 +3,7 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
- imagefolder
|
|
@@ -23,7 +24,7 @@ model-index:
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
-
value: 0.
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -33,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
|
| 34 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
-
- Loss: 0.
|
| 37 |
-
- Accuracy: 0.
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: google/vit-base-patch16-224-in21k
|
| 5 |
tags:
|
| 6 |
+
- image-classification
|
| 7 |
- generated_from_trainer
|
| 8 |
datasets:
|
| 9 |
- imagefolder
|
|
|
|
| 24 |
metrics:
|
| 25 |
- name: Accuracy
|
| 26 |
type: accuracy
|
| 27 |
+
value: 0.920863309352518
|
| 28 |
---
|
| 29 |
|
| 30 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 34 |
|
| 35 |
This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the imagefolder dataset.
|
| 36 |
It achieves the following results on the evaluation set:
|
| 37 |
+
- Loss: 0.3301
|
| 38 |
+
- Accuracy: 0.9209
|
| 39 |
|
| 40 |
## Model description
|
| 41 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 2.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
"total_flos": 1.9334597982400512e+18,
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 2.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.920863309352518,
|
| 4 |
+
"eval_loss": 0.330095499753952,
|
| 5 |
+
"eval_runtime": 2.7656,
|
| 6 |
+
"eval_samples_per_second": 100.521,
|
| 7 |
+
"eval_steps_per_second": 12.656,
|
| 8 |
"total_flos": 1.9334597982400512e+18,
|
| 9 |
+
"train_loss": 0.20911514231314263,
|
| 10 |
+
"train_runtime": 603.1201,
|
| 11 |
+
"train_samples_per_second": 41.368,
|
| 12 |
+
"train_steps_per_second": 2.587
|
| 13 |
}
|
data/events.out.tfevents.1730711565.0894b137f84e.248.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b818a1630ed93ed7a3d1ba8b06671df4b96179958951f73df53dfb2c07f694c
|
| 3 |
+
size 411
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime": 2.
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
+
"eval_accuracy": 0.920863309352518,
|
| 4 |
+
"eval_loss": 0.330095499753952,
|
| 5 |
+
"eval_runtime": 2.7656,
|
| 6 |
+
"eval_samples_per_second": 100.521,
|
| 7 |
+
"eval_steps_per_second": 12.656
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
"total_flos": 1.9334597982400512e+18,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 2.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
"total_flos": 1.9334597982400512e+18,
|
| 4 |
+
"train_loss": 0.20911514231314263,
|
| 5 |
+
"train_runtime": 603.1201,
|
| 6 |
+
"train_samples_per_second": 41.368,
|
| 7 |
+
"train_steps_per_second": 2.587
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "vit-weldclassifyv4/checkpoint-
|
| 4 |
"epoch": 10.0,
|
| 5 |
"eval_steps": 100,
|
| 6 |
"global_step": 1560,
|
|
@@ -10,1239 +10,1239 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0641025641025641,
|
| 13 |
-
"grad_norm": 1.
|
| 14 |
"learning_rate": 0.00019871794871794874,
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.1282051282051282,
|
| 20 |
-
"grad_norm": 1.
|
| 21 |
"learning_rate": 0.00019743589743589744,
|
| 22 |
-
"loss": 1.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.19230769230769232,
|
| 27 |
-
"grad_norm": 1.
|
| 28 |
"learning_rate": 0.00019615384615384615,
|
| 29 |
-
"loss": 1.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.2564102564102564,
|
| 34 |
-
"grad_norm":
|
| 35 |
"learning_rate": 0.00019487179487179487,
|
| 36 |
-
"loss":
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.32051282051282054,
|
| 41 |
-
"grad_norm":
|
| 42 |
"learning_rate": 0.0001935897435897436,
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.38461538461538464,
|
| 48 |
-
"grad_norm":
|
| 49 |
"learning_rate": 0.00019230769230769233,
|
| 50 |
-
"loss":
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.44871794871794873,
|
| 55 |
-
"grad_norm": 2.
|
| 56 |
"learning_rate": 0.00019102564102564104,
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.5128205128205128,
|
| 62 |
-
"grad_norm":
|
| 63 |
"learning_rate": 0.00018974358974358974,
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.5769230769230769,
|
| 69 |
-
"grad_norm": 2.
|
| 70 |
"learning_rate": 0.00018846153846153847,
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.6410256410256411,
|
| 76 |
-
"grad_norm": 2.
|
| 77 |
"learning_rate": 0.0001871794871794872,
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.6410256410256411,
|
| 83 |
-
"eval_accuracy": 0.
|
| 84 |
-
"eval_loss":
|
| 85 |
-
"eval_runtime":
|
| 86 |
-
"eval_samples_per_second":
|
| 87 |
-
"eval_steps_per_second":
|
| 88 |
"step": 100
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 0.7051282051282052,
|
| 92 |
-
"grad_norm":
|
| 93 |
"learning_rate": 0.0001858974358974359,
|
| 94 |
-
"loss": 0.
|
| 95 |
"step": 110
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 0.7692307692307693,
|
| 99 |
-
"grad_norm":
|
| 100 |
"learning_rate": 0.00018461538461538463,
|
| 101 |
-
"loss": 0.
|
| 102 |
"step": 120
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.8333333333333334,
|
| 106 |
-
"grad_norm":
|
| 107 |
"learning_rate": 0.00018333333333333334,
|
| 108 |
-
"loss": 0.
|
| 109 |
"step": 130
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 0.8974358974358975,
|
| 113 |
-
"grad_norm": 2.
|
| 114 |
"learning_rate": 0.00018205128205128207,
|
| 115 |
-
"loss":
|
| 116 |
"step": 140
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.9615384615384616,
|
| 120 |
-
"grad_norm": 2.
|
| 121 |
"learning_rate": 0.00018076923076923077,
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 1.0256410256410255,
|
| 127 |
-
"grad_norm":
|
| 128 |
"learning_rate": 0.0001794871794871795,
|
| 129 |
-
"loss": 0.
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 1.0897435897435896,
|
| 134 |
-
"grad_norm": 2.
|
| 135 |
"learning_rate": 0.00017820512820512823,
|
| 136 |
-
"loss": 0.
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 1.1538461538461537,
|
| 141 |
-
"grad_norm":
|
| 142 |
"learning_rate": 0.00017692307692307693,
|
| 143 |
-
"loss": 0.
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 1.217948717948718,
|
| 148 |
-
"grad_norm":
|
| 149 |
"learning_rate": 0.00017564102564102566,
|
| 150 |
-
"loss": 0.
|
| 151 |
"step": 190
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 1.282051282051282,
|
| 155 |
-
"grad_norm":
|
| 156 |
"learning_rate": 0.00017435897435897436,
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 200
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 1.282051282051282,
|
| 162 |
-
"eval_accuracy": 0.
|
| 163 |
-
"eval_loss":
|
| 164 |
-
"eval_runtime":
|
| 165 |
-
"eval_samples_per_second":
|
| 166 |
-
"eval_steps_per_second":
|
| 167 |
"step": 200
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 1.3461538461538463,
|
| 171 |
-
"grad_norm":
|
| 172 |
"learning_rate": 0.0001730769230769231,
|
| 173 |
-
"loss": 0.
|
| 174 |
"step": 210
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 1.4102564102564101,
|
| 178 |
-
"grad_norm": 2.
|
| 179 |
"learning_rate": 0.0001717948717948718,
|
| 180 |
-
"loss": 0.
|
| 181 |
"step": 220
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 1.4743589743589745,
|
| 185 |
-
"grad_norm":
|
| 186 |
"learning_rate": 0.00017051282051282053,
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 230
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 1.5384615384615383,
|
| 192 |
-
"grad_norm":
|
| 193 |
"learning_rate": 0.00016923076923076923,
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 240
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 1.6025641025641026,
|
| 199 |
-
"grad_norm":
|
| 200 |
"learning_rate": 0.00016794871794871796,
|
| 201 |
-
"loss": 0.
|
| 202 |
"step": 250
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 1.6666666666666665,
|
| 206 |
-
"grad_norm": 3.
|
| 207 |
"learning_rate": 0.0001666666666666667,
|
| 208 |
-
"loss": 0.
|
| 209 |
"step": 260
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 1.7307692307692308,
|
| 213 |
-
"grad_norm":
|
| 214 |
"learning_rate": 0.0001653846153846154,
|
| 215 |
-
"loss": 0.
|
| 216 |
"step": 270
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 1.7948717948717947,
|
| 220 |
-
"grad_norm":
|
| 221 |
"learning_rate": 0.0001641025641025641,
|
| 222 |
-
"loss": 0.
|
| 223 |
"step": 280
|
| 224 |
},
|
| 225 |
{
|
| 226 |
"epoch": 1.858974358974359,
|
| 227 |
-
"grad_norm":
|
| 228 |
"learning_rate": 0.00016282051282051282,
|
| 229 |
-
"loss": 0.
|
| 230 |
"step": 290
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 1.9230769230769231,
|
| 234 |
-
"grad_norm":
|
| 235 |
"learning_rate": 0.00016153846153846155,
|
| 236 |
-
"loss": 0.
|
| 237 |
"step": 300
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 1.9230769230769231,
|
| 241 |
-
"eval_accuracy": 0.
|
| 242 |
-
"eval_loss": 0.
|
| 243 |
-
"eval_runtime":
|
| 244 |
-
"eval_samples_per_second":
|
| 245 |
-
"eval_steps_per_second":
|
| 246 |
"step": 300
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 1.9871794871794872,
|
| 250 |
-
"grad_norm":
|
| 251 |
"learning_rate": 0.00016025641025641028,
|
| 252 |
-
"loss": 0.
|
| 253 |
"step": 310
|
| 254 |
},
|
| 255 |
{
|
| 256 |
"epoch": 2.051282051282051,
|
| 257 |
-
"grad_norm":
|
| 258 |
"learning_rate": 0.00015897435897435896,
|
| 259 |
-
"loss": 0.
|
| 260 |
"step": 320
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 2.1153846153846154,
|
| 264 |
-
"grad_norm": 2.
|
| 265 |
"learning_rate": 0.0001576923076923077,
|
| 266 |
-
"loss": 0.
|
| 267 |
"step": 330
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 2.1794871794871793,
|
| 271 |
-
"grad_norm":
|
| 272 |
"learning_rate": 0.00015641025641025642,
|
| 273 |
-
"loss": 0.
|
| 274 |
"step": 340
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 2.2435897435897436,
|
| 278 |
-
"grad_norm": 1.
|
| 279 |
"learning_rate": 0.00015512820512820515,
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 350
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 2.3076923076923075,
|
| 285 |
-
"grad_norm":
|
| 286 |
"learning_rate": 0.00015384615384615385,
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 360
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 2.371794871794872,
|
| 292 |
-
"grad_norm":
|
| 293 |
"learning_rate": 0.00015256410256410255,
|
| 294 |
-
"loss": 0.
|
| 295 |
"step": 370
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 2.435897435897436,
|
| 299 |
-
"grad_norm":
|
| 300 |
"learning_rate": 0.00015128205128205128,
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 380
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 2.5,
|
| 306 |
-
"grad_norm":
|
| 307 |
"learning_rate": 0.00015000000000000001,
|
| 308 |
-
"loss": 0.
|
| 309 |
"step": 390
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 2.564102564102564,
|
| 313 |
-
"grad_norm":
|
| 314 |
"learning_rate": 0.00014871794871794872,
|
| 315 |
-
"loss": 0.
|
| 316 |
"step": 400
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 2.564102564102564,
|
| 320 |
-
"eval_accuracy": 0.
|
| 321 |
-
"eval_loss": 0.
|
| 322 |
-
"eval_runtime":
|
| 323 |
-
"eval_samples_per_second":
|
| 324 |
-
"eval_steps_per_second":
|
| 325 |
"step": 400
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 2.628205128205128,
|
| 329 |
-
"grad_norm":
|
| 330 |
"learning_rate": 0.00014743589743589745,
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 410
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 2.6923076923076925,
|
| 336 |
-
"grad_norm":
|
| 337 |
"learning_rate": 0.00014615384615384615,
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 420
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 2.7564102564102564,
|
| 343 |
-
"grad_norm":
|
| 344 |
"learning_rate": 0.00014487179487179488,
|
| 345 |
-
"loss": 0.
|
| 346 |
"step": 430
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 2.8205128205128203,
|
| 350 |
-
"grad_norm":
|
| 351 |
"learning_rate": 0.0001435897435897436,
|
| 352 |
-
"loss": 0.
|
| 353 |
"step": 440
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 2.8846153846153846,
|
| 357 |
-
"grad_norm":
|
| 358 |
"learning_rate": 0.0001423076923076923,
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 450
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 2.948717948717949,
|
| 364 |
-
"grad_norm":
|
| 365 |
"learning_rate": 0.00014102564102564104,
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 460
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 3.0128205128205128,
|
| 371 |
-
"grad_norm":
|
| 372 |
"learning_rate": 0.00013974358974358974,
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 470
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 3.076923076923077,
|
| 378 |
-
"grad_norm":
|
| 379 |
"learning_rate": 0.00013846153846153847,
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 480
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 3.141025641025641,
|
| 385 |
-
"grad_norm":
|
| 386 |
"learning_rate": 0.00013717948717948718,
|
| 387 |
-
"loss": 0.
|
| 388 |
"step": 490
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 3.2051282051282053,
|
| 392 |
-
"grad_norm":
|
| 393 |
"learning_rate": 0.0001358974358974359,
|
| 394 |
-
"loss": 0.
|
| 395 |
"step": 500
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 3.2051282051282053,
|
| 399 |
-
"eval_accuracy": 0.
|
| 400 |
-
"eval_loss": 0.
|
| 401 |
-
"eval_runtime":
|
| 402 |
-
"eval_samples_per_second":
|
| 403 |
-
"eval_steps_per_second":
|
| 404 |
"step": 500
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 3.269230769230769,
|
| 408 |
-
"grad_norm":
|
| 409 |
"learning_rate": 0.00013461538461538464,
|
| 410 |
-
"loss": 0.
|
| 411 |
"step": 510
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 3.3333333333333335,
|
| 415 |
-
"grad_norm": 0.
|
| 416 |
"learning_rate": 0.00013333333333333334,
|
| 417 |
-
"loss": 0.
|
| 418 |
"step": 520
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"epoch": 3.3974358974358974,
|
| 422 |
-
"grad_norm":
|
| 423 |
"learning_rate": 0.00013205128205128204,
|
| 424 |
-
"loss": 0.
|
| 425 |
"step": 530
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 3.4615384615384617,
|
| 429 |
-
"grad_norm":
|
| 430 |
"learning_rate": 0.00013076923076923077,
|
| 431 |
-
"loss": 0.
|
| 432 |
"step": 540
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 3.5256410256410255,
|
| 436 |
-
"grad_norm":
|
| 437 |
"learning_rate": 0.0001294871794871795,
|
| 438 |
-
"loss": 0.
|
| 439 |
"step": 550
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 3.58974358974359,
|
| 443 |
-
"grad_norm":
|
| 444 |
"learning_rate": 0.00012820512820512823,
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 560
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 3.6538461538461537,
|
| 450 |
-
"grad_norm":
|
| 451 |
"learning_rate": 0.00012692307692307693,
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 570
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 3.717948717948718,
|
| 457 |
-
"grad_norm":
|
| 458 |
"learning_rate": 0.00012564102564102564,
|
| 459 |
-
"loss": 0.
|
| 460 |
"step": 580
|
| 461 |
},
|
| 462 |
{
|
| 463 |
"epoch": 3.782051282051282,
|
| 464 |
-
"grad_norm":
|
| 465 |
"learning_rate": 0.00012435897435897437,
|
| 466 |
-
"loss": 0.
|
| 467 |
"step": 590
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 3.8461538461538463,
|
| 471 |
-
"grad_norm":
|
| 472 |
"learning_rate": 0.0001230769230769231,
|
| 473 |
-
"loss": 0.
|
| 474 |
"step": 600
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 3.8461538461538463,
|
| 478 |
-
"eval_accuracy": 0.
|
| 479 |
-
"eval_loss": 0.
|
| 480 |
-
"eval_runtime": 3.
|
| 481 |
-
"eval_samples_per_second":
|
| 482 |
-
"eval_steps_per_second":
|
| 483 |
"step": 600
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 3.91025641025641,
|
| 487 |
-
"grad_norm":
|
| 488 |
"learning_rate": 0.00012179487179487179,
|
| 489 |
-
"loss": 0.
|
| 490 |
"step": 610
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 3.9743589743589745,
|
| 494 |
-
"grad_norm":
|
| 495 |
"learning_rate": 0.00012051282051282052,
|
| 496 |
-
"loss": 0.
|
| 497 |
"step": 620
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 4.038461538461538,
|
| 501 |
-
"grad_norm":
|
| 502 |
"learning_rate": 0.00011923076923076923,
|
| 503 |
-
"loss": 0.
|
| 504 |
"step": 630
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 4.102564102564102,
|
| 508 |
-
"grad_norm":
|
| 509 |
"learning_rate": 0.00011794871794871796,
|
| 510 |
-
"loss": 0.
|
| 511 |
"step": 640
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 4.166666666666667,
|
| 515 |
-
"grad_norm":
|
| 516 |
"learning_rate": 0.00011666666666666668,
|
| 517 |
-
"loss": 0.
|
| 518 |
"step": 650
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 4.230769230769231,
|
| 522 |
-
"grad_norm":
|
| 523 |
"learning_rate": 0.00011538461538461538,
|
| 524 |
-
"loss": 0.
|
| 525 |
"step": 660
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 4.294871794871795,
|
| 529 |
-
"grad_norm":
|
| 530 |
"learning_rate": 0.0001141025641025641,
|
| 531 |
-
"loss": 0.
|
| 532 |
"step": 670
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 4.358974358974359,
|
| 536 |
-
"grad_norm": 0.
|
| 537 |
"learning_rate": 0.00011282051282051283,
|
| 538 |
-
"loss": 0.
|
| 539 |
"step": 680
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 4.423076923076923,
|
| 543 |
-
"grad_norm":
|
| 544 |
"learning_rate": 0.00011153846153846154,
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 690
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 4.487179487179487,
|
| 550 |
-
"grad_norm":
|
| 551 |
"learning_rate": 0.00011025641025641027,
|
| 552 |
-
"loss": 0.
|
| 553 |
"step": 700
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 4.487179487179487,
|
| 557 |
-
"eval_accuracy": 0.
|
| 558 |
-
"eval_loss": 0.
|
| 559 |
-
"eval_runtime":
|
| 560 |
-
"eval_samples_per_second":
|
| 561 |
-
"eval_steps_per_second":
|
| 562 |
"step": 700
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"epoch": 4.551282051282051,
|
| 566 |
-
"grad_norm":
|
| 567 |
"learning_rate": 0.00010897435897435896,
|
| 568 |
-
"loss": 0.
|
| 569 |
"step": 710
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 4.615384615384615,
|
| 573 |
-
"grad_norm":
|
| 574 |
"learning_rate": 0.0001076923076923077,
|
| 575 |
-
"loss": 0.
|
| 576 |
"step": 720
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 4.67948717948718,
|
| 580 |
-
"grad_norm":
|
| 581 |
"learning_rate": 0.00010641025641025641,
|
| 582 |
-
"loss": 0.
|
| 583 |
"step": 730
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 4.743589743589744,
|
| 587 |
-
"grad_norm":
|
| 588 |
"learning_rate": 0.00010512820512820514,
|
| 589 |
-
"loss": 0.
|
| 590 |
"step": 740
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 4.8076923076923075,
|
| 594 |
-
"grad_norm":
|
| 595 |
"learning_rate": 0.00010384615384615386,
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 750
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 4.871794871794872,
|
| 601 |
-
"grad_norm": 0.
|
| 602 |
"learning_rate": 0.00010256410256410256,
|
| 603 |
-
"loss": 0.
|
| 604 |
"step": 760
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 4.935897435897436,
|
| 608 |
-
"grad_norm": 0.
|
| 609 |
"learning_rate": 0.00010128205128205129,
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 770
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 5.0,
|
| 615 |
-
"grad_norm": 0.
|
| 616 |
"learning_rate": 0.0001,
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 780
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 5.064102564102564,
|
| 622 |
-
"grad_norm":
|
| 623 |
"learning_rate": 9.871794871794872e-05,
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 790
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 5.128205128205128,
|
| 629 |
-
"grad_norm":
|
| 630 |
"learning_rate": 9.743589743589744e-05,
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 800
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 5.128205128205128,
|
| 636 |
-
"eval_accuracy": 0.
|
| 637 |
-
"eval_loss": 0.
|
| 638 |
-
"eval_runtime": 2.
|
| 639 |
-
"eval_samples_per_second":
|
| 640 |
-
"eval_steps_per_second":
|
| 641 |
"step": 800
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 5.1923076923076925,
|
| 645 |
-
"grad_norm":
|
| 646 |
"learning_rate": 9.615384615384617e-05,
|
| 647 |
-
"loss": 0.
|
| 648 |
"step": 810
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 5.256410256410256,
|
| 652 |
-
"grad_norm": 0.
|
| 653 |
"learning_rate": 9.487179487179487e-05,
|
| 654 |
-
"loss": 0.
|
| 655 |
"step": 820
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 5.32051282051282,
|
| 659 |
-
"grad_norm": 0.
|
| 660 |
"learning_rate": 9.35897435897436e-05,
|
| 661 |
-
"loss": 0.
|
| 662 |
"step": 830
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 5.384615384615385,
|
| 666 |
-
"grad_norm": 0.
|
| 667 |
"learning_rate": 9.230769230769232e-05,
|
| 668 |
-
"loss": 0.
|
| 669 |
"step": 840
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 5.448717948717949,
|
| 673 |
-
"grad_norm":
|
| 674 |
"learning_rate": 9.102564102564103e-05,
|
| 675 |
-
"loss": 0.
|
| 676 |
"step": 850
|
| 677 |
},
|
| 678 |
{
|
| 679 |
"epoch": 5.512820512820513,
|
| 680 |
-
"grad_norm":
|
| 681 |
"learning_rate": 8.974358974358975e-05,
|
| 682 |
-
"loss": 0.
|
| 683 |
"step": 860
|
| 684 |
},
|
| 685 |
{
|
| 686 |
"epoch": 5.576923076923077,
|
| 687 |
-
"grad_norm":
|
| 688 |
"learning_rate": 8.846153846153847e-05,
|
| 689 |
-
"loss": 0.
|
| 690 |
"step": 870
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 5.641025641025641,
|
| 694 |
-
"grad_norm":
|
| 695 |
"learning_rate": 8.717948717948718e-05,
|
| 696 |
-
"loss": 0.
|
| 697 |
"step": 880
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 5.705128205128205,
|
| 701 |
-
"grad_norm": 0.
|
| 702 |
"learning_rate": 8.58974358974359e-05,
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 890
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 5.769230769230769,
|
| 708 |
-
"grad_norm": 0.
|
| 709 |
"learning_rate": 8.461538461538461e-05,
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 900
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 5.769230769230769,
|
| 715 |
-
"eval_accuracy": 0.
|
| 716 |
-
"eval_loss": 0.
|
| 717 |
-
"eval_runtime": 2.
|
| 718 |
-
"eval_samples_per_second":
|
| 719 |
-
"eval_steps_per_second": 14.
|
| 720 |
"step": 900
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 5.833333333333333,
|
| 724 |
-
"grad_norm": 0.
|
| 725 |
"learning_rate": 8.333333333333334e-05,
|
| 726 |
-
"loss": 0.
|
| 727 |
"step": 910
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 5.897435897435898,
|
| 731 |
-
"grad_norm": 0.
|
| 732 |
"learning_rate": 8.205128205128205e-05,
|
| 733 |
-
"loss": 0.
|
| 734 |
"step": 920
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 5.961538461538462,
|
| 738 |
-
"grad_norm":
|
| 739 |
"learning_rate": 8.076923076923078e-05,
|
| 740 |
-
"loss": 0.
|
| 741 |
"step": 930
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 6.0256410256410255,
|
| 745 |
-
"grad_norm": 0.
|
| 746 |
"learning_rate": 7.948717948717948e-05,
|
| 747 |
-
"loss": 0.
|
| 748 |
"step": 940
|
| 749 |
},
|
| 750 |
{
|
| 751 |
"epoch": 6.089743589743589,
|
| 752 |
-
"grad_norm": 0.
|
| 753 |
"learning_rate": 7.820512820512821e-05,
|
| 754 |
-
"loss": 0.
|
| 755 |
"step": 950
|
| 756 |
},
|
| 757 |
{
|
| 758 |
"epoch": 6.153846153846154,
|
| 759 |
-
"grad_norm":
|
| 760 |
"learning_rate": 7.692307692307693e-05,
|
| 761 |
-
"loss": 0.
|
| 762 |
"step": 960
|
| 763 |
},
|
| 764 |
{
|
| 765 |
"epoch": 6.217948717948718,
|
| 766 |
-
"grad_norm": 0.
|
| 767 |
"learning_rate": 7.564102564102564e-05,
|
| 768 |
-
"loss": 0.
|
| 769 |
"step": 970
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 6.282051282051282,
|
| 773 |
-
"grad_norm": 0.
|
| 774 |
"learning_rate": 7.435897435897436e-05,
|
| 775 |
-
"loss": 0.
|
| 776 |
"step": 980
|
| 777 |
},
|
| 778 |
{
|
| 779 |
"epoch": 6.346153846153846,
|
| 780 |
-
"grad_norm": 0.
|
| 781 |
"learning_rate": 7.307692307692307e-05,
|
| 782 |
-
"loss": 0.
|
| 783 |
"step": 990
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 6.410256410256411,
|
| 787 |
-
"grad_norm": 0.
|
| 788 |
"learning_rate": 7.17948717948718e-05,
|
| 789 |
-
"loss": 0.
|
| 790 |
"step": 1000
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 6.410256410256411,
|
| 794 |
-
"eval_accuracy": 0.
|
| 795 |
-
"eval_loss": 0.
|
| 796 |
-
"eval_runtime":
|
| 797 |
-
"eval_samples_per_second":
|
| 798 |
-
"eval_steps_per_second":
|
| 799 |
"step": 1000
|
| 800 |
},
|
| 801 |
{
|
| 802 |
"epoch": 6.4743589743589745,
|
| 803 |
-
"grad_norm": 0.
|
| 804 |
"learning_rate": 7.051282051282052e-05,
|
| 805 |
-
"loss": 0.
|
| 806 |
"step": 1010
|
| 807 |
},
|
| 808 |
{
|
| 809 |
"epoch": 6.538461538461538,
|
| 810 |
-
"grad_norm": 0.
|
| 811 |
"learning_rate": 6.923076923076924e-05,
|
| 812 |
-
"loss": 0.
|
| 813 |
"step": 1020
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 6.602564102564102,
|
| 817 |
-
"grad_norm": 0.
|
| 818 |
"learning_rate": 6.794871794871795e-05,
|
| 819 |
-
"loss": 0.
|
| 820 |
"step": 1030
|
| 821 |
},
|
| 822 |
{
|
| 823 |
"epoch": 6.666666666666667,
|
| 824 |
-
"grad_norm": 0.
|
| 825 |
"learning_rate": 6.666666666666667e-05,
|
| 826 |
-
"loss": 0.
|
| 827 |
"step": 1040
|
| 828 |
},
|
| 829 |
{
|
| 830 |
"epoch": 6.730769230769231,
|
| 831 |
-
"grad_norm": 0.
|
| 832 |
"learning_rate": 6.538461538461539e-05,
|
| 833 |
-
"loss": 0.
|
| 834 |
"step": 1050
|
| 835 |
},
|
| 836 |
{
|
| 837 |
"epoch": 6.794871794871795,
|
| 838 |
-
"grad_norm": 0.
|
| 839 |
"learning_rate": 6.410256410256412e-05,
|
| 840 |
-
"loss": 0.
|
| 841 |
"step": 1060
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"epoch": 6.858974358974359,
|
| 845 |
-
"grad_norm": 0.
|
| 846 |
"learning_rate": 6.282051282051282e-05,
|
| 847 |
-
"loss": 0.
|
| 848 |
"step": 1070
|
| 849 |
},
|
| 850 |
{
|
| 851 |
"epoch": 6.923076923076923,
|
| 852 |
-
"grad_norm":
|
| 853 |
"learning_rate": 6.153846153846155e-05,
|
| 854 |
-
"loss": 0.
|
| 855 |
"step": 1080
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 6.987179487179487,
|
| 859 |
-
"grad_norm": 0.
|
| 860 |
"learning_rate": 6.025641025641026e-05,
|
| 861 |
-
"loss": 0.
|
| 862 |
"step": 1090
|
| 863 |
},
|
| 864 |
{
|
| 865 |
"epoch": 7.051282051282051,
|
| 866 |
-
"grad_norm": 0.
|
| 867 |
"learning_rate": 5.897435897435898e-05,
|
| 868 |
-
"loss": 0.
|
| 869 |
"step": 1100
|
| 870 |
},
|
| 871 |
{
|
| 872 |
"epoch": 7.051282051282051,
|
| 873 |
-
"eval_accuracy": 0.
|
| 874 |
-
"eval_loss": 0.
|
| 875 |
-
"eval_runtime":
|
| 876 |
-
"eval_samples_per_second":
|
| 877 |
-
"eval_steps_per_second":
|
| 878 |
"step": 1100
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 7.115384615384615,
|
| 882 |
-
"grad_norm": 0.
|
| 883 |
"learning_rate": 5.769230769230769e-05,
|
| 884 |
-
"loss": 0.
|
| 885 |
"step": 1110
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 7.17948717948718,
|
| 889 |
-
"grad_norm": 0.
|
| 890 |
"learning_rate": 5.6410256410256414e-05,
|
| 891 |
-
"loss": 0.
|
| 892 |
"step": 1120
|
| 893 |
},
|
| 894 |
{
|
| 895 |
"epoch": 7.243589743589744,
|
| 896 |
-
"grad_norm": 0.
|
| 897 |
"learning_rate": 5.512820512820514e-05,
|
| 898 |
-
"loss": 0.
|
| 899 |
"step": 1130
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 7.3076923076923075,
|
| 903 |
-
"grad_norm": 0.
|
| 904 |
"learning_rate": 5.384615384615385e-05,
|
| 905 |
-
"loss": 0.
|
| 906 |
"step": 1140
|
| 907 |
},
|
| 908 |
{
|
| 909 |
"epoch": 7.371794871794872,
|
| 910 |
-
"grad_norm": 0.
|
| 911 |
"learning_rate": 5.256410256410257e-05,
|
| 912 |
-
"loss": 0.
|
| 913 |
"step": 1150
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"epoch": 7.435897435897436,
|
| 917 |
-
"grad_norm": 0.
|
| 918 |
"learning_rate": 5.128205128205128e-05,
|
| 919 |
-
"loss": 0.
|
| 920 |
"step": 1160
|
| 921 |
},
|
| 922 |
{
|
| 923 |
"epoch": 7.5,
|
| 924 |
-
"grad_norm": 0.
|
| 925 |
"learning_rate": 5e-05,
|
| 926 |
-
"loss": 0.
|
| 927 |
"step": 1170
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 7.564102564102564,
|
| 931 |
-
"grad_norm": 0.
|
| 932 |
"learning_rate": 4.871794871794872e-05,
|
| 933 |
-
"loss": 0.
|
| 934 |
"step": 1180
|
| 935 |
},
|
| 936 |
{
|
| 937 |
"epoch": 7.628205128205128,
|
| 938 |
-
"grad_norm": 0.
|
| 939 |
"learning_rate": 4.7435897435897435e-05,
|
| 940 |
"loss": 0.0037,
|
| 941 |
"step": 1190
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 7.6923076923076925,
|
| 945 |
-
"grad_norm": 0.
|
| 946 |
"learning_rate": 4.615384615384616e-05,
|
| 947 |
-
"loss": 0.
|
| 948 |
"step": 1200
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 7.6923076923076925,
|
| 952 |
-
"eval_accuracy": 0.
|
| 953 |
-
"eval_loss": 0.
|
| 954 |
-
"eval_runtime":
|
| 955 |
-
"eval_samples_per_second":
|
| 956 |
-
"eval_steps_per_second":
|
| 957 |
"step": 1200
|
| 958 |
},
|
| 959 |
{
|
| 960 |
"epoch": 7.756410256410256,
|
| 961 |
-
"grad_norm": 0.
|
| 962 |
"learning_rate": 4.4871794871794874e-05,
|
| 963 |
-
"loss": 0.
|
| 964 |
"step": 1210
|
| 965 |
},
|
| 966 |
{
|
| 967 |
"epoch": 7.82051282051282,
|
| 968 |
-
"grad_norm": 0.
|
| 969 |
"learning_rate": 4.358974358974359e-05,
|
| 970 |
-
"loss": 0.
|
| 971 |
"step": 1220
|
| 972 |
},
|
| 973 |
{
|
| 974 |
"epoch": 7.884615384615385,
|
| 975 |
-
"grad_norm": 0.
|
| 976 |
"learning_rate": 4.230769230769231e-05,
|
| 977 |
-
"loss": 0.
|
| 978 |
"step": 1230
|
| 979 |
},
|
| 980 |
{
|
| 981 |
"epoch": 7.948717948717949,
|
| 982 |
-
"grad_norm": 0.
|
| 983 |
"learning_rate": 4.1025641025641023e-05,
|
| 984 |
-
"loss": 0.
|
| 985 |
"step": 1240
|
| 986 |
},
|
| 987 |
{
|
| 988 |
"epoch": 8.012820512820513,
|
| 989 |
-
"grad_norm": 0.
|
| 990 |
"learning_rate": 3.974358974358974e-05,
|
| 991 |
-
"loss": 0.
|
| 992 |
"step": 1250
|
| 993 |
},
|
| 994 |
{
|
| 995 |
"epoch": 8.076923076923077,
|
| 996 |
-
"grad_norm": 0.
|
| 997 |
"learning_rate": 3.846153846153846e-05,
|
| 998 |
-
"loss": 0.
|
| 999 |
"step": 1260
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 8.14102564102564,
|
| 1003 |
-
"grad_norm": 0.
|
| 1004 |
"learning_rate": 3.717948717948718e-05,
|
| 1005 |
-
"loss": 0.
|
| 1006 |
"step": 1270
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
"epoch": 8.205128205128204,
|
| 1010 |
-
"grad_norm": 0.
|
| 1011 |
"learning_rate": 3.58974358974359e-05,
|
| 1012 |
-
"loss": 0.
|
| 1013 |
"step": 1280
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
"epoch": 8.26923076923077,
|
| 1017 |
-
"grad_norm": 0.
|
| 1018 |
"learning_rate": 3.461538461538462e-05,
|
| 1019 |
-
"loss": 0.
|
| 1020 |
"step": 1290
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
"epoch": 8.333333333333334,
|
| 1024 |
-
"grad_norm": 0.
|
| 1025 |
"learning_rate": 3.3333333333333335e-05,
|
| 1026 |
-
"loss": 0.
|
| 1027 |
"step": 1300
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
"epoch": 8.333333333333334,
|
| 1031 |
-
"eval_accuracy": 0.
|
| 1032 |
-
"eval_loss": 0.
|
| 1033 |
-
"eval_runtime": 2.
|
| 1034 |
-
"eval_samples_per_second":
|
| 1035 |
-
"eval_steps_per_second": 14.
|
| 1036 |
"step": 1300
|
| 1037 |
},
|
| 1038 |
{
|
| 1039 |
"epoch": 8.397435897435898,
|
| 1040 |
-
"grad_norm": 0.
|
| 1041 |
"learning_rate": 3.205128205128206e-05,
|
| 1042 |
-
"loss": 0.
|
| 1043 |
"step": 1310
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
"epoch": 8.461538461538462,
|
| 1047 |
-
"grad_norm": 0.
|
| 1048 |
"learning_rate": 3.0769230769230774e-05,
|
| 1049 |
-
"loss": 0.
|
| 1050 |
"step": 1320
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
"epoch": 8.525641025641026,
|
| 1054 |
-
"grad_norm": 0.
|
| 1055 |
"learning_rate": 2.948717948717949e-05,
|
| 1056 |
-
"loss": 0.
|
| 1057 |
"step": 1330
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
"epoch": 8.58974358974359,
|
| 1061 |
-
"grad_norm": 0.
|
| 1062 |
"learning_rate": 2.8205128205128207e-05,
|
| 1063 |
-
"loss": 0.
|
| 1064 |
"step": 1340
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
"epoch": 8.653846153846153,
|
| 1068 |
-
"grad_norm": 0.
|
| 1069 |
"learning_rate": 2.6923076923076923e-05,
|
| 1070 |
-
"loss": 0.
|
| 1071 |
"step": 1350
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 8.717948717948717,
|
| 1075 |
-
"grad_norm": 0.
|
| 1076 |
"learning_rate": 2.564102564102564e-05,
|
| 1077 |
-
"loss": 0.
|
| 1078 |
"step": 1360
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
"epoch": 8.782051282051283,
|
| 1082 |
-
"grad_norm": 0.
|
| 1083 |
"learning_rate": 2.435897435897436e-05,
|
| 1084 |
-
"loss": 0.
|
| 1085 |
"step": 1370
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 8.846153846153847,
|
| 1089 |
-
"grad_norm": 0.
|
| 1090 |
"learning_rate": 2.307692307692308e-05,
|
| 1091 |
-
"loss": 0.
|
| 1092 |
"step": 1380
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 8.91025641025641,
|
| 1096 |
-
"grad_norm": 0.
|
| 1097 |
"learning_rate": 2.1794871794871795e-05,
|
| 1098 |
-
"loss": 0.
|
| 1099 |
"step": 1390
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
"epoch": 8.974358974358974,
|
| 1103 |
-
"grad_norm": 0.
|
| 1104 |
"learning_rate": 2.0512820512820512e-05,
|
| 1105 |
"loss": 0.003,
|
| 1106 |
"step": 1400
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 8.974358974358974,
|
| 1110 |
-
"eval_accuracy": 0.
|
| 1111 |
-
"eval_loss": 0.
|
| 1112 |
-
"eval_runtime": 2.
|
| 1113 |
-
"eval_samples_per_second":
|
| 1114 |
-
"eval_steps_per_second":
|
| 1115 |
"step": 1400
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
"epoch": 9.038461538461538,
|
| 1119 |
-
"grad_norm": 0.
|
| 1120 |
"learning_rate": 1.923076923076923e-05,
|
| 1121 |
-
"loss": 0.
|
| 1122 |
"step": 1410
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 9.102564102564102,
|
| 1126 |
-
"grad_norm": 0.
|
| 1127 |
"learning_rate": 1.794871794871795e-05,
|
| 1128 |
-
"loss": 0.
|
| 1129 |
"step": 1420
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 9.166666666666666,
|
| 1133 |
-
"grad_norm": 0.
|
| 1134 |
"learning_rate": 1.6666666666666667e-05,
|
| 1135 |
-
"loss": 0.
|
| 1136 |
"step": 1430
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 9.23076923076923,
|
| 1140 |
-
"grad_norm": 0.
|
| 1141 |
"learning_rate": 1.5384615384615387e-05,
|
| 1142 |
-
"loss": 0.
|
| 1143 |
"step": 1440
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 9.294871794871796,
|
| 1147 |
-
"grad_norm": 0.
|
| 1148 |
"learning_rate": 1.4102564102564104e-05,
|
| 1149 |
-
"loss": 0.
|
| 1150 |
"step": 1450
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 9.35897435897436,
|
| 1154 |
-
"grad_norm": 0.
|
| 1155 |
"learning_rate": 1.282051282051282e-05,
|
| 1156 |
-
"loss": 0.
|
| 1157 |
"step": 1460
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 9.423076923076923,
|
| 1161 |
-
"grad_norm": 0.
|
| 1162 |
"learning_rate": 1.153846153846154e-05,
|
| 1163 |
-
"loss": 0.
|
| 1164 |
"step": 1470
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 9.487179487179487,
|
| 1168 |
-
"grad_norm": 0.
|
| 1169 |
"learning_rate": 1.0256410256410256e-05,
|
| 1170 |
-
"loss": 0.
|
| 1171 |
"step": 1480
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 9.551282051282051,
|
| 1175 |
-
"grad_norm": 0.
|
| 1176 |
"learning_rate": 8.974358974358976e-06,
|
| 1177 |
-
"loss": 0.
|
| 1178 |
"step": 1490
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
"epoch": 9.615384615384615,
|
| 1182 |
-
"grad_norm": 0.
|
| 1183 |
"learning_rate": 7.692307692307694e-06,
|
| 1184 |
-
"loss": 0.
|
| 1185 |
"step": 1500
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 9.615384615384615,
|
| 1189 |
-
"eval_accuracy": 0.
|
| 1190 |
-
"eval_loss": 0.
|
| 1191 |
-
"eval_runtime": 2.
|
| 1192 |
-
"eval_samples_per_second":
|
| 1193 |
-
"eval_steps_per_second":
|
| 1194 |
"step": 1500
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
"epoch": 9.679487179487179,
|
| 1198 |
-
"grad_norm": 0.
|
| 1199 |
"learning_rate": 6.41025641025641e-06,
|
| 1200 |
-
"loss": 0.
|
| 1201 |
"step": 1510
|
| 1202 |
},
|
| 1203 |
{
|
| 1204 |
"epoch": 9.743589743589745,
|
| 1205 |
-
"grad_norm": 0.
|
| 1206 |
"learning_rate": 5.128205128205128e-06,
|
| 1207 |
-
"loss": 0.
|
| 1208 |
"step": 1520
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
"epoch": 9.807692307692308,
|
| 1212 |
-
"grad_norm": 0.
|
| 1213 |
"learning_rate": 3.846153846153847e-06,
|
| 1214 |
"loss": 0.0029,
|
| 1215 |
"step": 1530
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
"epoch": 9.871794871794872,
|
| 1219 |
-
"grad_norm": 0.
|
| 1220 |
"learning_rate": 2.564102564102564e-06,
|
| 1221 |
-
"loss": 0.
|
| 1222 |
"step": 1540
|
| 1223 |
},
|
| 1224 |
{
|
| 1225 |
"epoch": 9.935897435897436,
|
| 1226 |
-
"grad_norm": 0.
|
| 1227 |
"learning_rate": 1.282051282051282e-06,
|
| 1228 |
-
"loss": 0.
|
| 1229 |
"step": 1550
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
"epoch": 10.0,
|
| 1233 |
-
"grad_norm": 0.
|
| 1234 |
"learning_rate": 0.0,
|
| 1235 |
-
"loss": 0.
|
| 1236 |
"step": 1560
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
"epoch": 10.0,
|
| 1240 |
"step": 1560,
|
| 1241 |
"total_flos": 1.9334597982400512e+18,
|
| 1242 |
-
"train_loss": 0.
|
| 1243 |
-
"train_runtime":
|
| 1244 |
-
"train_samples_per_second":
|
| 1245 |
-
"train_steps_per_second": 2.
|
| 1246 |
}
|
| 1247 |
],
|
| 1248 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.330095499753952,
|
| 3 |
+
"best_model_checkpoint": "vit-weldclassifyv4/checkpoint-1000",
|
| 4 |
"epoch": 10.0,
|
| 5 |
"eval_steps": 100,
|
| 6 |
"global_step": 1560,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0641025641025641,
|
| 13 |
+
"grad_norm": 1.5280327796936035,
|
| 14 |
"learning_rate": 0.00019871794871794874,
|
| 15 |
+
"loss": 1.263,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.1282051282051282,
|
| 20 |
+
"grad_norm": 1.8514498472213745,
|
| 21 |
"learning_rate": 0.00019743589743589744,
|
| 22 |
+
"loss": 1.1159,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.19230769230769232,
|
| 27 |
+
"grad_norm": 1.2513030767440796,
|
| 28 |
"learning_rate": 0.00019615384615384615,
|
| 29 |
+
"loss": 1.164,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.2564102564102564,
|
| 34 |
+
"grad_norm": 2.280437707901001,
|
| 35 |
"learning_rate": 0.00019487179487179487,
|
| 36 |
+
"loss": 0.9528,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.32051282051282054,
|
| 41 |
+
"grad_norm": 1.246656060218811,
|
| 42 |
"learning_rate": 0.0001935897435897436,
|
| 43 |
+
"loss": 1.0313,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.38461538461538464,
|
| 48 |
+
"grad_norm": 1.9358172416687012,
|
| 49 |
"learning_rate": 0.00019230769230769233,
|
| 50 |
+
"loss": 1.038,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.44871794871794873,
|
| 55 |
+
"grad_norm": 2.415847063064575,
|
| 56 |
"learning_rate": 0.00019102564102564104,
|
| 57 |
+
"loss": 0.9088,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.5128205128205128,
|
| 62 |
+
"grad_norm": 2.1359400749206543,
|
| 63 |
"learning_rate": 0.00018974358974358974,
|
| 64 |
+
"loss": 0.8265,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.5769230769230769,
|
| 69 |
+
"grad_norm": 2.2672863006591797,
|
| 70 |
"learning_rate": 0.00018846153846153847,
|
| 71 |
+
"loss": 0.8904,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.6410256410256411,
|
| 76 |
+
"grad_norm": 2.525250196456909,
|
| 77 |
"learning_rate": 0.0001871794871794872,
|
| 78 |
+
"loss": 0.8207,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.6410256410256411,
|
| 83 |
+
"eval_accuracy": 0.564748201438849,
|
| 84 |
+
"eval_loss": 1.0335605144500732,
|
| 85 |
+
"eval_runtime": 2.4754,
|
| 86 |
+
"eval_samples_per_second": 112.303,
|
| 87 |
+
"eval_steps_per_second": 14.139,
|
| 88 |
"step": 100
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 0.7051282051282052,
|
| 92 |
+
"grad_norm": 1.6615636348724365,
|
| 93 |
"learning_rate": 0.0001858974358974359,
|
| 94 |
+
"loss": 0.9254,
|
| 95 |
"step": 110
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 0.7692307692307693,
|
| 99 |
+
"grad_norm": 3.1376407146453857,
|
| 100 |
"learning_rate": 0.00018461538461538463,
|
| 101 |
+
"loss": 0.8125,
|
| 102 |
"step": 120
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.8333333333333334,
|
| 106 |
+
"grad_norm": 1.8494981527328491,
|
| 107 |
"learning_rate": 0.00018333333333333334,
|
| 108 |
+
"loss": 0.6967,
|
| 109 |
"step": 130
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 0.8974358974358975,
|
| 113 |
+
"grad_norm": 2.7374682426452637,
|
| 114 |
"learning_rate": 0.00018205128205128207,
|
| 115 |
+
"loss": 0.7031,
|
| 116 |
"step": 140
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.9615384615384616,
|
| 120 |
+
"grad_norm": 2.8239476680755615,
|
| 121 |
"learning_rate": 0.00018076923076923077,
|
| 122 |
+
"loss": 0.7871,
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 1.0256410256410255,
|
| 127 |
+
"grad_norm": 2.239936590194702,
|
| 128 |
"learning_rate": 0.0001794871794871795,
|
| 129 |
+
"loss": 0.8064,
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 1.0897435897435896,
|
| 134 |
+
"grad_norm": 2.60086727142334,
|
| 135 |
"learning_rate": 0.00017820512820512823,
|
| 136 |
+
"loss": 0.5349,
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 1.1538461538461537,
|
| 141 |
+
"grad_norm": 3.485903024673462,
|
| 142 |
"learning_rate": 0.00017692307692307693,
|
| 143 |
+
"loss": 0.5896,
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 1.217948717948718,
|
| 148 |
+
"grad_norm": 3.2817769050598145,
|
| 149 |
"learning_rate": 0.00017564102564102566,
|
| 150 |
+
"loss": 0.729,
|
| 151 |
"step": 190
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 1.282051282051282,
|
| 155 |
+
"grad_norm": 4.110422611236572,
|
| 156 |
"learning_rate": 0.00017435897435897436,
|
| 157 |
+
"loss": 0.6506,
|
| 158 |
"step": 200
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 1.282051282051282,
|
| 162 |
+
"eval_accuracy": 0.579136690647482,
|
| 163 |
+
"eval_loss": 1.1981723308563232,
|
| 164 |
+
"eval_runtime": 2.8799,
|
| 165 |
+
"eval_samples_per_second": 96.532,
|
| 166 |
+
"eval_steps_per_second": 12.153,
|
| 167 |
"step": 200
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 1.3461538461538463,
|
| 171 |
+
"grad_norm": 2.515904664993286,
|
| 172 |
"learning_rate": 0.0001730769230769231,
|
| 173 |
+
"loss": 0.8231,
|
| 174 |
"step": 210
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 1.4102564102564101,
|
| 178 |
+
"grad_norm": 2.2017431259155273,
|
| 179 |
"learning_rate": 0.0001717948717948718,
|
| 180 |
+
"loss": 0.6216,
|
| 181 |
"step": 220
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 1.4743589743589745,
|
| 185 |
+
"grad_norm": 2.253706693649292,
|
| 186 |
"learning_rate": 0.00017051282051282053,
|
| 187 |
+
"loss": 0.5126,
|
| 188 |
"step": 230
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 1.5384615384615383,
|
| 192 |
+
"grad_norm": 3.4106080532073975,
|
| 193 |
"learning_rate": 0.00016923076923076923,
|
| 194 |
+
"loss": 0.471,
|
| 195 |
"step": 240
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 1.6025641025641026,
|
| 199 |
+
"grad_norm": 1.884901523590088,
|
| 200 |
"learning_rate": 0.00016794871794871796,
|
| 201 |
+
"loss": 0.4521,
|
| 202 |
"step": 250
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 1.6666666666666665,
|
| 206 |
+
"grad_norm": 3.056332588195801,
|
| 207 |
"learning_rate": 0.0001666666666666667,
|
| 208 |
+
"loss": 0.3808,
|
| 209 |
"step": 260
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 1.7307692307692308,
|
| 213 |
+
"grad_norm": 3.2792108058929443,
|
| 214 |
"learning_rate": 0.0001653846153846154,
|
| 215 |
+
"loss": 0.3568,
|
| 216 |
"step": 270
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 1.7948717948717947,
|
| 220 |
+
"grad_norm": 3.657397985458374,
|
| 221 |
"learning_rate": 0.0001641025641025641,
|
| 222 |
+
"loss": 0.4942,
|
| 223 |
"step": 280
|
| 224 |
},
|
| 225 |
{
|
| 226 |
"epoch": 1.858974358974359,
|
| 227 |
+
"grad_norm": 3.565870523452759,
|
| 228 |
"learning_rate": 0.00016282051282051282,
|
| 229 |
+
"loss": 0.5117,
|
| 230 |
"step": 290
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 1.9230769230769231,
|
| 234 |
+
"grad_norm": 1.8648629188537598,
|
| 235 |
"learning_rate": 0.00016153846153846155,
|
| 236 |
+
"loss": 0.5324,
|
| 237 |
"step": 300
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 1.9230769230769231,
|
| 241 |
+
"eval_accuracy": 0.7769784172661871,
|
| 242 |
+
"eval_loss": 0.605965256690979,
|
| 243 |
+
"eval_runtime": 2.4146,
|
| 244 |
+
"eval_samples_per_second": 115.134,
|
| 245 |
+
"eval_steps_per_second": 14.495,
|
| 246 |
"step": 300
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 1.9871794871794872,
|
| 250 |
+
"grad_norm": 5.665286540985107,
|
| 251 |
"learning_rate": 0.00016025641025641028,
|
| 252 |
+
"loss": 0.5566,
|
| 253 |
"step": 310
|
| 254 |
},
|
| 255 |
{
|
| 256 |
"epoch": 2.051282051282051,
|
| 257 |
+
"grad_norm": 0.6339452266693115,
|
| 258 |
"learning_rate": 0.00015897435897435896,
|
| 259 |
+
"loss": 0.3058,
|
| 260 |
"step": 320
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 2.1153846153846154,
|
| 264 |
+
"grad_norm": 2.2966978549957275,
|
| 265 |
"learning_rate": 0.0001576923076923077,
|
| 266 |
+
"loss": 0.2831,
|
| 267 |
"step": 330
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 2.1794871794871793,
|
| 271 |
+
"grad_norm": 2.510307550430298,
|
| 272 |
"learning_rate": 0.00015641025641025642,
|
| 273 |
+
"loss": 0.2055,
|
| 274 |
"step": 340
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 2.2435897435897436,
|
| 278 |
+
"grad_norm": 1.1059399843215942,
|
| 279 |
"learning_rate": 0.00015512820512820515,
|
| 280 |
+
"loss": 0.2886,
|
| 281 |
"step": 350
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 2.3076923076923075,
|
| 285 |
+
"grad_norm": 6.055357933044434,
|
| 286 |
"learning_rate": 0.00015384615384615385,
|
| 287 |
+
"loss": 0.3756,
|
| 288 |
"step": 360
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 2.371794871794872,
|
| 292 |
+
"grad_norm": 0.5536957383155823,
|
| 293 |
"learning_rate": 0.00015256410256410255,
|
| 294 |
+
"loss": 0.412,
|
| 295 |
"step": 370
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 2.435897435897436,
|
| 299 |
+
"grad_norm": 5.276978969573975,
|
| 300 |
"learning_rate": 0.00015128205128205128,
|
| 301 |
+
"loss": 0.1798,
|
| 302 |
"step": 380
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 2.5,
|
| 306 |
+
"grad_norm": 2.25166916847229,
|
| 307 |
"learning_rate": 0.00015000000000000001,
|
| 308 |
+
"loss": 0.1813,
|
| 309 |
"step": 390
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 2.564102564102564,
|
| 313 |
+
"grad_norm": 4.955526351928711,
|
| 314 |
"learning_rate": 0.00014871794871794872,
|
| 315 |
+
"loss": 0.2486,
|
| 316 |
"step": 400
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 2.564102564102564,
|
| 320 |
+
"eval_accuracy": 0.7517985611510791,
|
| 321 |
+
"eval_loss": 0.729444682598114,
|
| 322 |
+
"eval_runtime": 4.0175,
|
| 323 |
+
"eval_samples_per_second": 69.198,
|
| 324 |
+
"eval_steps_per_second": 8.712,
|
| 325 |
"step": 400
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 2.628205128205128,
|
| 329 |
+
"grad_norm": 5.6987690925598145,
|
| 330 |
"learning_rate": 0.00014743589743589745,
|
| 331 |
+
"loss": 0.5142,
|
| 332 |
"step": 410
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 2.6923076923076925,
|
| 336 |
+
"grad_norm": 0.589967668056488,
|
| 337 |
"learning_rate": 0.00014615384615384615,
|
| 338 |
+
"loss": 0.2685,
|
| 339 |
"step": 420
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 2.7564102564102564,
|
| 343 |
+
"grad_norm": 2.2702548503875732,
|
| 344 |
"learning_rate": 0.00014487179487179488,
|
| 345 |
+
"loss": 0.3104,
|
| 346 |
"step": 430
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 2.8205128205128203,
|
| 350 |
+
"grad_norm": 4.440503120422363,
|
| 351 |
"learning_rate": 0.0001435897435897436,
|
| 352 |
+
"loss": 0.2192,
|
| 353 |
"step": 440
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 2.8846153846153846,
|
| 357 |
+
"grad_norm": 1.690927267074585,
|
| 358 |
"learning_rate": 0.0001423076923076923,
|
| 359 |
+
"loss": 0.2557,
|
| 360 |
"step": 450
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 2.948717948717949,
|
| 364 |
+
"grad_norm": 9.020477294921875,
|
| 365 |
"learning_rate": 0.00014102564102564104,
|
| 366 |
+
"loss": 0.3725,
|
| 367 |
"step": 460
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 3.0128205128205128,
|
| 371 |
+
"grad_norm": 1.131715178489685,
|
| 372 |
"learning_rate": 0.00013974358974358974,
|
| 373 |
+
"loss": 0.3586,
|
| 374 |
"step": 470
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 3.076923076923077,
|
| 378 |
+
"grad_norm": 2.3979876041412354,
|
| 379 |
"learning_rate": 0.00013846153846153847,
|
| 380 |
+
"loss": 0.1712,
|
| 381 |
"step": 480
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 3.141025641025641,
|
| 385 |
+
"grad_norm": 1.2889968156814575,
|
| 386 |
"learning_rate": 0.00013717948717948718,
|
| 387 |
+
"loss": 0.1988,
|
| 388 |
"step": 490
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 3.2051282051282053,
|
| 392 |
+
"grad_norm": 2.893319606781006,
|
| 393 |
"learning_rate": 0.0001358974358974359,
|
| 394 |
+
"loss": 0.1366,
|
| 395 |
"step": 500
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 3.2051282051282053,
|
| 399 |
+
"eval_accuracy": 0.841726618705036,
|
| 400 |
+
"eval_loss": 0.4832339882850647,
|
| 401 |
+
"eval_runtime": 2.588,
|
| 402 |
+
"eval_samples_per_second": 107.42,
|
| 403 |
+
"eval_steps_per_second": 13.524,
|
| 404 |
"step": 500
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 3.269230769230769,
|
| 408 |
+
"grad_norm": 3.6555581092834473,
|
| 409 |
"learning_rate": 0.00013461538461538464,
|
| 410 |
+
"loss": 0.1222,
|
| 411 |
"step": 510
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 3.3333333333333335,
|
| 415 |
+
"grad_norm": 0.1904444396495819,
|
| 416 |
"learning_rate": 0.00013333333333333334,
|
| 417 |
+
"loss": 0.1654,
|
| 418 |
"step": 520
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"epoch": 3.3974358974358974,
|
| 422 |
+
"grad_norm": 4.902673244476318,
|
| 423 |
"learning_rate": 0.00013205128205128204,
|
| 424 |
+
"loss": 0.198,
|
| 425 |
"step": 530
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 3.4615384615384617,
|
| 429 |
+
"grad_norm": 0.30183860659599304,
|
| 430 |
"learning_rate": 0.00013076923076923077,
|
| 431 |
+
"loss": 0.2074,
|
| 432 |
"step": 540
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 3.5256410256410255,
|
| 436 |
+
"grad_norm": 4.17673397064209,
|
| 437 |
"learning_rate": 0.0001294871794871795,
|
| 438 |
+
"loss": 0.1021,
|
| 439 |
"step": 550
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 3.58974358974359,
|
| 443 |
+
"grad_norm": 1.6145508289337158,
|
| 444 |
"learning_rate": 0.00012820512820512823,
|
| 445 |
+
"loss": 0.1074,
|
| 446 |
"step": 560
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 3.6538461538461537,
|
| 450 |
+
"grad_norm": 4.717573165893555,
|
| 451 |
"learning_rate": 0.00012692307692307693,
|
| 452 |
+
"loss": 0.1201,
|
| 453 |
"step": 570
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 3.717948717948718,
|
| 457 |
+
"grad_norm": 1.2709864377975464,
|
| 458 |
"learning_rate": 0.00012564102564102564,
|
| 459 |
+
"loss": 0.0544,
|
| 460 |
"step": 580
|
| 461 |
},
|
| 462 |
{
|
| 463 |
"epoch": 3.782051282051282,
|
| 464 |
+
"grad_norm": 3.7621912956237793,
|
| 465 |
"learning_rate": 0.00012435897435897437,
|
| 466 |
+
"loss": 0.2016,
|
| 467 |
"step": 590
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 3.8461538461538463,
|
| 471 |
+
"grad_norm": 12.426462173461914,
|
| 472 |
"learning_rate": 0.0001230769230769231,
|
| 473 |
+
"loss": 0.3124,
|
| 474 |
"step": 600
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 3.8461538461538463,
|
| 478 |
+
"eval_accuracy": 0.762589928057554,
|
| 479 |
+
"eval_loss": 0.8676345348358154,
|
| 480 |
+
"eval_runtime": 3.0816,
|
| 481 |
+
"eval_samples_per_second": 90.213,
|
| 482 |
+
"eval_steps_per_second": 11.358,
|
| 483 |
"step": 600
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 3.91025641025641,
|
| 487 |
+
"grad_norm": 10.93652057647705,
|
| 488 |
"learning_rate": 0.00012179487179487179,
|
| 489 |
+
"loss": 0.2992,
|
| 490 |
"step": 610
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 3.9743589743589745,
|
| 494 |
+
"grad_norm": 0.6971213221549988,
|
| 495 |
"learning_rate": 0.00012051282051282052,
|
| 496 |
+
"loss": 0.1864,
|
| 497 |
"step": 620
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 4.038461538461538,
|
| 501 |
+
"grad_norm": 6.531364917755127,
|
| 502 |
"learning_rate": 0.00011923076923076923,
|
| 503 |
+
"loss": 0.1929,
|
| 504 |
"step": 630
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 4.102564102564102,
|
| 508 |
+
"grad_norm": 0.8437137007713318,
|
| 509 |
"learning_rate": 0.00011794871794871796,
|
| 510 |
+
"loss": 0.0816,
|
| 511 |
"step": 640
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 4.166666666666667,
|
| 515 |
+
"grad_norm": 9.23108196258545,
|
| 516 |
"learning_rate": 0.00011666666666666668,
|
| 517 |
+
"loss": 0.0654,
|
| 518 |
"step": 650
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 4.230769230769231,
|
| 522 |
+
"grad_norm": 1.1913517713546753,
|
| 523 |
"learning_rate": 0.00011538461538461538,
|
| 524 |
+
"loss": 0.0974,
|
| 525 |
"step": 660
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 4.294871794871795,
|
| 529 |
+
"grad_norm": 8.05540657043457,
|
| 530 |
"learning_rate": 0.0001141025641025641,
|
| 531 |
+
"loss": 0.0466,
|
| 532 |
"step": 670
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 4.358974358974359,
|
| 536 |
+
"grad_norm": 0.1012343019247055,
|
| 537 |
"learning_rate": 0.00011282051282051283,
|
| 538 |
+
"loss": 0.0641,
|
| 539 |
"step": 680
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 4.423076923076923,
|
| 543 |
+
"grad_norm": 7.817044734954834,
|
| 544 |
"learning_rate": 0.00011153846153846154,
|
| 545 |
+
"loss": 0.1442,
|
| 546 |
"step": 690
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 4.487179487179487,
|
| 550 |
+
"grad_norm": 6.788941860198975,
|
| 551 |
"learning_rate": 0.00011025641025641027,
|
| 552 |
+
"loss": 0.0296,
|
| 553 |
"step": 700
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 4.487179487179487,
|
| 557 |
+
"eval_accuracy": 0.8884892086330936,
|
| 558 |
+
"eval_loss": 0.4233308434486389,
|
| 559 |
+
"eval_runtime": 2.523,
|
| 560 |
+
"eval_samples_per_second": 110.184,
|
| 561 |
+
"eval_steps_per_second": 13.872,
|
| 562 |
"step": 700
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"epoch": 4.551282051282051,
|
| 566 |
+
"grad_norm": 4.860511302947998,
|
| 567 |
"learning_rate": 0.00010897435897435896,
|
| 568 |
+
"loss": 0.0231,
|
| 569 |
"step": 710
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 4.615384615384615,
|
| 573 |
+
"grad_norm": 0.9598804116249084,
|
| 574 |
"learning_rate": 0.0001076923076923077,
|
| 575 |
+
"loss": 0.0207,
|
| 576 |
"step": 720
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 4.67948717948718,
|
| 580 |
+
"grad_norm": 12.745481491088867,
|
| 581 |
"learning_rate": 0.00010641025641025641,
|
| 582 |
+
"loss": 0.1516,
|
| 583 |
"step": 730
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 4.743589743589744,
|
| 587 |
+
"grad_norm": 7.983795166015625,
|
| 588 |
"learning_rate": 0.00010512820512820514,
|
| 589 |
+
"loss": 0.1638,
|
| 590 |
"step": 740
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 4.8076923076923075,
|
| 594 |
+
"grad_norm": 3.051384449005127,
|
| 595 |
"learning_rate": 0.00010384615384615386,
|
| 596 |
+
"loss": 0.0477,
|
| 597 |
"step": 750
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 4.871794871794872,
|
| 601 |
+
"grad_norm": 0.10625698417425156,
|
| 602 |
"learning_rate": 0.00010256410256410256,
|
| 603 |
+
"loss": 0.0719,
|
| 604 |
"step": 760
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 4.935897435897436,
|
| 608 |
+
"grad_norm": 0.04624614119529724,
|
| 609 |
"learning_rate": 0.00010128205128205129,
|
| 610 |
+
"loss": 0.1069,
|
| 611 |
"step": 770
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 5.0,
|
| 615 |
+
"grad_norm": 0.08277003467082977,
|
| 616 |
"learning_rate": 0.0001,
|
| 617 |
+
"loss": 0.0152,
|
| 618 |
"step": 780
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 5.064102564102564,
|
| 622 |
+
"grad_norm": 0.09980784356594086,
|
| 623 |
"learning_rate": 9.871794871794872e-05,
|
| 624 |
+
"loss": 0.0719,
|
| 625 |
"step": 790
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 5.128205128205128,
|
| 629 |
+
"grad_norm": 0.09162779897451401,
|
| 630 |
"learning_rate": 9.743589743589744e-05,
|
| 631 |
+
"loss": 0.0723,
|
| 632 |
"step": 800
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 5.128205128205128,
|
| 636 |
+
"eval_accuracy": 0.8848920863309353,
|
| 637 |
+
"eval_loss": 0.4469863176345825,
|
| 638 |
+
"eval_runtime": 2.7699,
|
| 639 |
+
"eval_samples_per_second": 100.363,
|
| 640 |
+
"eval_steps_per_second": 12.636,
|
| 641 |
"step": 800
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 5.1923076923076925,
|
| 645 |
+
"grad_norm": 0.05171818658709526,
|
| 646 |
"learning_rate": 9.615384615384617e-05,
|
| 647 |
+
"loss": 0.0192,
|
| 648 |
"step": 810
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 5.256410256410256,
|
| 652 |
+
"grad_norm": 0.05209165811538696,
|
| 653 |
"learning_rate": 9.487179487179487e-05,
|
| 654 |
+
"loss": 0.0394,
|
| 655 |
"step": 820
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 5.32051282051282,
|
| 659 |
+
"grad_norm": 0.960054874420166,
|
| 660 |
"learning_rate": 9.35897435897436e-05,
|
| 661 |
+
"loss": 0.0129,
|
| 662 |
"step": 830
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 5.384615384615385,
|
| 666 |
+
"grad_norm": 0.09233374148607254,
|
| 667 |
"learning_rate": 9.230769230769232e-05,
|
| 668 |
+
"loss": 0.0138,
|
| 669 |
"step": 840
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 5.448717948717949,
|
| 673 |
+
"grad_norm": 0.09635169804096222,
|
| 674 |
"learning_rate": 9.102564102564103e-05,
|
| 675 |
+
"loss": 0.0096,
|
| 676 |
"step": 850
|
| 677 |
},
|
| 678 |
{
|
| 679 |
"epoch": 5.512820512820513,
|
| 680 |
+
"grad_norm": 1.3777004480361938,
|
| 681 |
"learning_rate": 8.974358974358975e-05,
|
| 682 |
+
"loss": 0.0412,
|
| 683 |
"step": 860
|
| 684 |
},
|
| 685 |
{
|
| 686 |
"epoch": 5.576923076923077,
|
| 687 |
+
"grad_norm": 0.03339802846312523,
|
| 688 |
"learning_rate": 8.846153846153847e-05,
|
| 689 |
+
"loss": 0.0424,
|
| 690 |
"step": 870
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 5.641025641025641,
|
| 694 |
+
"grad_norm": 0.032307617366313934,
|
| 695 |
"learning_rate": 8.717948717948718e-05,
|
| 696 |
+
"loss": 0.0161,
|
| 697 |
"step": 880
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 5.705128205128205,
|
| 701 |
+
"grad_norm": 0.03049471788108349,
|
| 702 |
"learning_rate": 8.58974358974359e-05,
|
| 703 |
+
"loss": 0.0388,
|
| 704 |
"step": 890
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 5.769230769230769,
|
| 708 |
+
"grad_norm": 0.05182625725865364,
|
| 709 |
"learning_rate": 8.461538461538461e-05,
|
| 710 |
+
"loss": 0.0342,
|
| 711 |
"step": 900
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 5.769230769230769,
|
| 715 |
+
"eval_accuracy": 0.9172661870503597,
|
| 716 |
+
"eval_loss": 0.3406282067298889,
|
| 717 |
+
"eval_runtime": 2.3863,
|
| 718 |
+
"eval_samples_per_second": 116.5,
|
| 719 |
+
"eval_steps_per_second": 14.667,
|
| 720 |
"step": 900
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 5.833333333333333,
|
| 724 |
+
"grad_norm": 0.2365674525499344,
|
| 725 |
"learning_rate": 8.333333333333334e-05,
|
| 726 |
+
"loss": 0.0837,
|
| 727 |
"step": 910
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 5.897435897435898,
|
| 731 |
+
"grad_norm": 0.031284429132938385,
|
| 732 |
"learning_rate": 8.205128205128205e-05,
|
| 733 |
+
"loss": 0.0691,
|
| 734 |
"step": 920
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 5.961538461538462,
|
| 738 |
+
"grad_norm": 10.787687301635742,
|
| 739 |
"learning_rate": 8.076923076923078e-05,
|
| 740 |
+
"loss": 0.0524,
|
| 741 |
"step": 930
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 6.0256410256410255,
|
| 745 |
+
"grad_norm": 0.027590090408921242,
|
| 746 |
"learning_rate": 7.948717948717948e-05,
|
| 747 |
+
"loss": 0.0086,
|
| 748 |
"step": 940
|
| 749 |
},
|
| 750 |
{
|
| 751 |
"epoch": 6.089743589743589,
|
| 752 |
+
"grad_norm": 0.04675084725022316,
|
| 753 |
"learning_rate": 7.820512820512821e-05,
|
| 754 |
+
"loss": 0.0066,
|
| 755 |
"step": 950
|
| 756 |
},
|
| 757 |
{
|
| 758 |
"epoch": 6.153846153846154,
|
| 759 |
+
"grad_norm": 0.032889507710933685,
|
| 760 |
"learning_rate": 7.692307692307693e-05,
|
| 761 |
+
"loss": 0.0432,
|
| 762 |
"step": 960
|
| 763 |
},
|
| 764 |
{
|
| 765 |
"epoch": 6.217948717948718,
|
| 766 |
+
"grad_norm": 0.1580750048160553,
|
| 767 |
"learning_rate": 7.564102564102564e-05,
|
| 768 |
+
"loss": 0.006,
|
| 769 |
"step": 970
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 6.282051282051282,
|
| 773 |
+
"grad_norm": 0.024286190047860146,
|
| 774 |
"learning_rate": 7.435897435897436e-05,
|
| 775 |
+
"loss": 0.0123,
|
| 776 |
"step": 980
|
| 777 |
},
|
| 778 |
{
|
| 779 |
"epoch": 6.346153846153846,
|
| 780 |
+
"grad_norm": 0.02685542032122612,
|
| 781 |
"learning_rate": 7.307692307692307e-05,
|
| 782 |
+
"loss": 0.0059,
|
| 783 |
"step": 990
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 6.410256410256411,
|
| 787 |
+
"grad_norm": 0.9080101251602173,
|
| 788 |
"learning_rate": 7.17948717948718e-05,
|
| 789 |
+
"loss": 0.0055,
|
| 790 |
"step": 1000
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 6.410256410256411,
|
| 794 |
+
"eval_accuracy": 0.920863309352518,
|
| 795 |
+
"eval_loss": 0.330095499753952,
|
| 796 |
+
"eval_runtime": 3.1626,
|
| 797 |
+
"eval_samples_per_second": 87.904,
|
| 798 |
+
"eval_steps_per_second": 11.067,
|
| 799 |
"step": 1000
|
| 800 |
},
|
| 801 |
{
|
| 802 |
"epoch": 6.4743589743589745,
|
| 803 |
+
"grad_norm": 0.156268909573555,
|
| 804 |
"learning_rate": 7.051282051282052e-05,
|
| 805 |
+
"loss": 0.0051,
|
| 806 |
"step": 1010
|
| 807 |
},
|
| 808 |
{
|
| 809 |
"epoch": 6.538461538461538,
|
| 810 |
+
"grad_norm": 0.025522593408823013,
|
| 811 |
"learning_rate": 6.923076923076924e-05,
|
| 812 |
+
"loss": 0.0175,
|
| 813 |
"step": 1020
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 6.602564102564102,
|
| 817 |
+
"grad_norm": 0.025892965495586395,
|
| 818 |
"learning_rate": 6.794871794871795e-05,
|
| 819 |
+
"loss": 0.0133,
|
| 820 |
"step": 1030
|
| 821 |
},
|
| 822 |
{
|
| 823 |
"epoch": 6.666666666666667,
|
| 824 |
+
"grad_norm": 0.02324897050857544,
|
| 825 |
"learning_rate": 6.666666666666667e-05,
|
| 826 |
+
"loss": 0.0051,
|
| 827 |
"step": 1040
|
| 828 |
},
|
| 829 |
{
|
| 830 |
"epoch": 6.730769230769231,
|
| 831 |
+
"grad_norm": 0.20136423408985138,
|
| 832 |
"learning_rate": 6.538461538461539e-05,
|
| 833 |
+
"loss": 0.0318,
|
| 834 |
"step": 1050
|
| 835 |
},
|
| 836 |
{
|
| 837 |
"epoch": 6.794871794871795,
|
| 838 |
+
"grad_norm": 0.11247438937425613,
|
| 839 |
"learning_rate": 6.410256410256412e-05,
|
| 840 |
+
"loss": 0.0331,
|
| 841 |
"step": 1060
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"epoch": 6.858974358974359,
|
| 845 |
+
"grad_norm": 0.10950164496898651,
|
| 846 |
"learning_rate": 6.282051282051282e-05,
|
| 847 |
+
"loss": 0.0055,
|
| 848 |
"step": 1070
|
| 849 |
},
|
| 850 |
{
|
| 851 |
"epoch": 6.923076923076923,
|
| 852 |
+
"grad_norm": 1.537802815437317,
|
| 853 |
"learning_rate": 6.153846153846155e-05,
|
| 854 |
+
"loss": 0.0055,
|
| 855 |
"step": 1080
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 6.987179487179487,
|
| 859 |
+
"grad_norm": 0.023923929780721664,
|
| 860 |
"learning_rate": 6.025641025641026e-05,
|
| 861 |
+
"loss": 0.0044,
|
| 862 |
"step": 1090
|
| 863 |
},
|
| 864 |
{
|
| 865 |
"epoch": 7.051282051282051,
|
| 866 |
+
"grad_norm": 0.02083686552941799,
|
| 867 |
"learning_rate": 5.897435897435898e-05,
|
| 868 |
+
"loss": 0.0048,
|
| 869 |
"step": 1100
|
| 870 |
},
|
| 871 |
{
|
| 872 |
"epoch": 7.051282051282051,
|
| 873 |
+
"eval_accuracy": 0.9172661870503597,
|
| 874 |
+
"eval_loss": 0.3471122980117798,
|
| 875 |
+
"eval_runtime": 2.4758,
|
| 876 |
+
"eval_samples_per_second": 112.287,
|
| 877 |
+
"eval_steps_per_second": 14.137,
|
| 878 |
"step": 1100
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 7.115384615384615,
|
| 882 |
+
"grad_norm": 0.020538046956062317,
|
| 883 |
"learning_rate": 5.769230769230769e-05,
|
| 884 |
+
"loss": 0.0042,
|
| 885 |
"step": 1110
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 7.17948717948718,
|
| 889 |
+
"grad_norm": 0.01733437366783619,
|
| 890 |
"learning_rate": 5.6410256410256414e-05,
|
| 891 |
+
"loss": 0.0039,
|
| 892 |
"step": 1120
|
| 893 |
},
|
| 894 |
{
|
| 895 |
"epoch": 7.243589743589744,
|
| 896 |
+
"grad_norm": 0.01968984678387642,
|
| 897 |
"learning_rate": 5.512820512820514e-05,
|
| 898 |
+
"loss": 0.0038,
|
| 899 |
"step": 1130
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 7.3076923076923075,
|
| 903 |
+
"grad_norm": 0.019213447347283363,
|
| 904 |
"learning_rate": 5.384615384615385e-05,
|
| 905 |
+
"loss": 0.0036,
|
| 906 |
"step": 1140
|
| 907 |
},
|
| 908 |
{
|
| 909 |
"epoch": 7.371794871794872,
|
| 910 |
+
"grad_norm": 0.017935629934072495,
|
| 911 |
"learning_rate": 5.256410256410257e-05,
|
| 912 |
+
"loss": 0.004,
|
| 913 |
"step": 1150
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"epoch": 7.435897435897436,
|
| 917 |
+
"grad_norm": 0.01726532354950905,
|
| 918 |
"learning_rate": 5.128205128205128e-05,
|
| 919 |
+
"loss": 0.0038,
|
| 920 |
"step": 1160
|
| 921 |
},
|
| 922 |
{
|
| 923 |
"epoch": 7.5,
|
| 924 |
+
"grad_norm": 0.01753012090921402,
|
| 925 |
"learning_rate": 5e-05,
|
| 926 |
+
"loss": 0.0038,
|
| 927 |
"step": 1170
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 7.564102564102564,
|
| 931 |
+
"grad_norm": 0.018105851486325264,
|
| 932 |
"learning_rate": 4.871794871794872e-05,
|
| 933 |
+
"loss": 0.0036,
|
| 934 |
"step": 1180
|
| 935 |
},
|
| 936 |
{
|
| 937 |
"epoch": 7.628205128205128,
|
| 938 |
+
"grad_norm": 0.019911447539925575,
|
| 939 |
"learning_rate": 4.7435897435897435e-05,
|
| 940 |
"loss": 0.0037,
|
| 941 |
"step": 1190
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 7.6923076923076925,
|
| 945 |
+
"grad_norm": 0.023634430021047592,
|
| 946 |
"learning_rate": 4.615384615384616e-05,
|
| 947 |
+
"loss": 0.0036,
|
| 948 |
"step": 1200
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 7.6923076923076925,
|
| 952 |
+
"eval_accuracy": 0.9136690647482014,
|
| 953 |
+
"eval_loss": 0.33460894227027893,
|
| 954 |
+
"eval_runtime": 2.4621,
|
| 955 |
+
"eval_samples_per_second": 112.91,
|
| 956 |
+
"eval_steps_per_second": 14.215,
|
| 957 |
"step": 1200
|
| 958 |
},
|
| 959 |
{
|
| 960 |
"epoch": 7.756410256410256,
|
| 961 |
+
"grad_norm": 0.017936883494257927,
|
| 962 |
"learning_rate": 4.4871794871794874e-05,
|
| 963 |
+
"loss": 0.0034,
|
| 964 |
"step": 1210
|
| 965 |
},
|
| 966 |
{
|
| 967 |
"epoch": 7.82051282051282,
|
| 968 |
+
"grad_norm": 0.01885095238685608,
|
| 969 |
"learning_rate": 4.358974358974359e-05,
|
| 970 |
+
"loss": 0.0034,
|
| 971 |
"step": 1220
|
| 972 |
},
|
| 973 |
{
|
| 974 |
"epoch": 7.884615384615385,
|
| 975 |
+
"grad_norm": 0.017711780965328217,
|
| 976 |
"learning_rate": 4.230769230769231e-05,
|
| 977 |
+
"loss": 0.0033,
|
| 978 |
"step": 1230
|
| 979 |
},
|
| 980 |
{
|
| 981 |
"epoch": 7.948717948717949,
|
| 982 |
+
"grad_norm": 0.014750463888049126,
|
| 983 |
"learning_rate": 4.1025641025641023e-05,
|
| 984 |
+
"loss": 0.0034,
|
| 985 |
"step": 1240
|
| 986 |
},
|
| 987 |
{
|
| 988 |
"epoch": 8.012820512820513,
|
| 989 |
+
"grad_norm": 0.014598443172872066,
|
| 990 |
"learning_rate": 3.974358974358974e-05,
|
| 991 |
+
"loss": 0.0031,
|
| 992 |
"step": 1250
|
| 993 |
},
|
| 994 |
{
|
| 995 |
"epoch": 8.076923076923077,
|
| 996 |
+
"grad_norm": 0.01595359854400158,
|
| 997 |
"learning_rate": 3.846153846153846e-05,
|
| 998 |
+
"loss": 0.0032,
|
| 999 |
"step": 1260
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 8.14102564102564,
|
| 1003 |
+
"grad_norm": 0.01710698939859867,
|
| 1004 |
"learning_rate": 3.717948717948718e-05,
|
| 1005 |
+
"loss": 0.0032,
|
| 1006 |
"step": 1270
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
"epoch": 8.205128205128204,
|
| 1010 |
+
"grad_norm": 0.015550950542092323,
|
| 1011 |
"learning_rate": 3.58974358974359e-05,
|
| 1012 |
+
"loss": 0.0031,
|
| 1013 |
"step": 1280
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
"epoch": 8.26923076923077,
|
| 1017 |
+
"grad_norm": 0.015512553043663502,
|
| 1018 |
"learning_rate": 3.461538461538462e-05,
|
| 1019 |
+
"loss": 0.0031,
|
| 1020 |
"step": 1290
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
"epoch": 8.333333333333334,
|
| 1024 |
+
"grad_norm": 0.01687728427350521,
|
| 1025 |
"learning_rate": 3.3333333333333335e-05,
|
| 1026 |
+
"loss": 0.003,
|
| 1027 |
"step": 1300
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
"epoch": 8.333333333333334,
|
| 1031 |
+
"eval_accuracy": 0.9136690647482014,
|
| 1032 |
+
"eval_loss": 0.34976544976234436,
|
| 1033 |
+
"eval_runtime": 2.3973,
|
| 1034 |
+
"eval_samples_per_second": 115.962,
|
| 1035 |
+
"eval_steps_per_second": 14.599,
|
| 1036 |
"step": 1300
|
| 1037 |
},
|
| 1038 |
{
|
| 1039 |
"epoch": 8.397435897435898,
|
| 1040 |
+
"grad_norm": 0.017616627737879753,
|
| 1041 |
"learning_rate": 3.205128205128206e-05,
|
| 1042 |
+
"loss": 0.0031,
|
| 1043 |
"step": 1310
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
"epoch": 8.461538461538462,
|
| 1047 |
+
"grad_norm": 0.017452212050557137,
|
| 1048 |
"learning_rate": 3.0769230769230774e-05,
|
| 1049 |
+
"loss": 0.0031,
|
| 1050 |
"step": 1320
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
"epoch": 8.525641025641026,
|
| 1054 |
+
"grad_norm": 0.017976053059101105,
|
| 1055 |
"learning_rate": 2.948717948717949e-05,
|
| 1056 |
+
"loss": 0.0032,
|
| 1057 |
"step": 1330
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
"epoch": 8.58974358974359,
|
| 1061 |
+
"grad_norm": 0.014091568998992443,
|
| 1062 |
"learning_rate": 2.8205128205128207e-05,
|
| 1063 |
+
"loss": 0.0032,
|
| 1064 |
"step": 1340
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
"epoch": 8.653846153846153,
|
| 1068 |
+
"grad_norm": 0.015703728422522545,
|
| 1069 |
"learning_rate": 2.6923076923076923e-05,
|
| 1070 |
+
"loss": 0.003,
|
| 1071 |
"step": 1350
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 8.717948717948717,
|
| 1075 |
+
"grad_norm": 0.01781061850488186,
|
| 1076 |
"learning_rate": 2.564102564102564e-05,
|
| 1077 |
+
"loss": 0.003,
|
| 1078 |
"step": 1360
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
"epoch": 8.782051282051283,
|
| 1082 |
+
"grad_norm": 0.01647392474114895,
|
| 1083 |
"learning_rate": 2.435897435897436e-05,
|
| 1084 |
+
"loss": 0.0031,
|
| 1085 |
"step": 1370
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 8.846153846153847,
|
| 1089 |
+
"grad_norm": 0.013498615473508835,
|
| 1090 |
"learning_rate": 2.307692307692308e-05,
|
| 1091 |
+
"loss": 0.0028,
|
| 1092 |
"step": 1380
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 8.91025641025641,
|
| 1096 |
+
"grad_norm": 0.016175739467144012,
|
| 1097 |
"learning_rate": 2.1794871794871795e-05,
|
| 1098 |
+
"loss": 0.003,
|
| 1099 |
"step": 1390
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
"epoch": 8.974358974358974,
|
| 1103 |
+
"grad_norm": 0.015950603410601616,
|
| 1104 |
"learning_rate": 2.0512820512820512e-05,
|
| 1105 |
"loss": 0.003,
|
| 1106 |
"step": 1400
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 8.974358974358974,
|
| 1110 |
+
"eval_accuracy": 0.9100719424460432,
|
| 1111 |
+
"eval_loss": 0.354926198720932,
|
| 1112 |
+
"eval_runtime": 2.4324,
|
| 1113 |
+
"eval_samples_per_second": 114.29,
|
| 1114 |
+
"eval_steps_per_second": 14.389,
|
| 1115 |
"step": 1400
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
"epoch": 9.038461538461538,
|
| 1119 |
+
"grad_norm": 0.014547958970069885,
|
| 1120 |
"learning_rate": 1.923076923076923e-05,
|
| 1121 |
+
"loss": 0.0029,
|
| 1122 |
"step": 1410
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 9.102564102564102,
|
| 1126 |
+
"grad_norm": 0.012941875495016575,
|
| 1127 |
"learning_rate": 1.794871794871795e-05,
|
| 1128 |
+
"loss": 0.0028,
|
| 1129 |
"step": 1420
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 9.166666666666666,
|
| 1133 |
+
"grad_norm": 0.016635097563266754,
|
| 1134 |
"learning_rate": 1.6666666666666667e-05,
|
| 1135 |
+
"loss": 0.003,
|
| 1136 |
"step": 1430
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 9.23076923076923,
|
| 1140 |
+
"grad_norm": 0.018657604232430458,
|
| 1141 |
"learning_rate": 1.5384615384615387e-05,
|
| 1142 |
+
"loss": 0.0029,
|
| 1143 |
"step": 1440
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 9.294871794871796,
|
| 1147 |
+
"grad_norm": 0.015006115660071373,
|
| 1148 |
"learning_rate": 1.4102564102564104e-05,
|
| 1149 |
+
"loss": 0.0031,
|
| 1150 |
"step": 1450
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 9.35897435897436,
|
| 1154 |
+
"grad_norm": 0.01575641520321369,
|
| 1155 |
"learning_rate": 1.282051282051282e-05,
|
| 1156 |
+
"loss": 0.0027,
|
| 1157 |
"step": 1460
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 9.423076923076923,
|
| 1161 |
+
"grad_norm": 0.013228046707808971,
|
| 1162 |
"learning_rate": 1.153846153846154e-05,
|
| 1163 |
+
"loss": 0.0027,
|
| 1164 |
"step": 1470
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 9.487179487179487,
|
| 1168 |
+
"grad_norm": 0.013002932071685791,
|
| 1169 |
"learning_rate": 1.0256410256410256e-05,
|
| 1170 |
+
"loss": 0.0027,
|
| 1171 |
"step": 1480
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 9.551282051282051,
|
| 1175 |
+
"grad_norm": 0.014644928276538849,
|
| 1176 |
"learning_rate": 8.974358974358976e-06,
|
| 1177 |
+
"loss": 0.0029,
|
| 1178 |
"step": 1490
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
"epoch": 9.615384615384615,
|
| 1182 |
+
"grad_norm": 0.01448275987058878,
|
| 1183 |
"learning_rate": 7.692307692307694e-06,
|
| 1184 |
+
"loss": 0.0027,
|
| 1185 |
"step": 1500
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 9.615384615384615,
|
| 1189 |
+
"eval_accuracy": 0.9136690647482014,
|
| 1190 |
+
"eval_loss": 0.3569168150424957,
|
| 1191 |
+
"eval_runtime": 2.7846,
|
| 1192 |
+
"eval_samples_per_second": 99.835,
|
| 1193 |
+
"eval_steps_per_second": 12.569,
|
| 1194 |
"step": 1500
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
"epoch": 9.679487179487179,
|
| 1198 |
+
"grad_norm": 0.012788016349077225,
|
| 1199 |
"learning_rate": 6.41025641025641e-06,
|
| 1200 |
+
"loss": 0.0028,
|
| 1201 |
"step": 1510
|
| 1202 |
},
|
| 1203 |
{
|
| 1204 |
"epoch": 9.743589743589745,
|
| 1205 |
+
"grad_norm": 0.014576306566596031,
|
| 1206 |
"learning_rate": 5.128205128205128e-06,
|
| 1207 |
+
"loss": 0.0026,
|
| 1208 |
"step": 1520
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
"epoch": 9.807692307692308,
|
| 1212 |
+
"grad_norm": 0.014699741266667843,
|
| 1213 |
"learning_rate": 3.846153846153847e-06,
|
| 1214 |
"loss": 0.0029,
|
| 1215 |
"step": 1530
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
"epoch": 9.871794871794872,
|
| 1219 |
+
"grad_norm": 0.015379097312688828,
|
| 1220 |
"learning_rate": 2.564102564102564e-06,
|
| 1221 |
+
"loss": 0.0026,
|
| 1222 |
"step": 1540
|
| 1223 |
},
|
| 1224 |
{
|
| 1225 |
"epoch": 9.935897435897436,
|
| 1226 |
+
"grad_norm": 0.012021095491945744,
|
| 1227 |
"learning_rate": 1.282051282051282e-06,
|
| 1228 |
+
"loss": 0.0027,
|
| 1229 |
"step": 1550
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
"epoch": 10.0,
|
| 1233 |
+
"grad_norm": 0.014515766873955727,
|
| 1234 |
"learning_rate": 0.0,
|
| 1235 |
+
"loss": 0.0028,
|
| 1236 |
"step": 1560
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
"epoch": 10.0,
|
| 1240 |
"step": 1560,
|
| 1241 |
"total_flos": 1.9334597982400512e+18,
|
| 1242 |
+
"train_loss": 0.20911514231314263,
|
| 1243 |
+
"train_runtime": 603.1201,
|
| 1244 |
+
"train_samples_per_second": 41.368,
|
| 1245 |
+
"train_steps_per_second": 2.587
|
| 1246 |
}
|
| 1247 |
],
|
| 1248 |
"logging_steps": 10,
|