🍻 cheers
Browse files- README.md +6 -5
- all_results.json +11 -11
- eval_results.json +6 -6
- runs/Nov19_07-31-43_09d27efa0afa/events.out.tfevents.1700384480.09d27efa0afa.1367.1 +3 -0
- train_results.json +6 -6
- trainer_state.json +2041 -322
README.md
CHANGED
|
@@ -2,6 +2,7 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
datasets:
|
| 7 |
- imagefolder
|
|
@@ -14,7 +15,7 @@ model-index:
|
|
| 14 |
name: Image Classification
|
| 15 |
type: image-classification
|
| 16 |
dataset:
|
| 17 |
-
name:
|
| 18 |
type: imagefolder
|
| 19 |
config: default
|
| 20 |
split: train
|
|
@@ -22,7 +23,7 @@ model-index:
|
|
| 22 |
metrics:
|
| 23 |
- name: Accuracy
|
| 24 |
type: accuracy
|
| 25 |
-
value: 0.
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -30,10 +31,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 30 |
|
| 31 |
# Action_all_10_class
|
| 32 |
|
| 33 |
-
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
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
-
- Loss: 0.
|
| 36 |
-
- Accuracy: 0.
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: google/vit-base-patch16-224-in21k
|
| 4 |
tags:
|
| 5 |
+
- image-classification
|
| 6 |
- generated_from_trainer
|
| 7 |
datasets:
|
| 8 |
- imagefolder
|
|
|
|
| 15 |
name: Image Classification
|
| 16 |
type: image-classification
|
| 17 |
dataset:
|
| 18 |
+
name: Action_small_dataset
|
| 19 |
type: imagefolder
|
| 20 |
config: default
|
| 21 |
split: train
|
|
|
|
| 23 |
metrics:
|
| 24 |
- name: Accuracy
|
| 25 |
type: accuracy
|
| 26 |
+
value: 0.8646723646723646
|
| 27 |
---
|
| 28 |
|
| 29 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 31 |
|
| 32 |
# Action_all_10_class
|
| 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 Action_small_dataset dataset.
|
| 35 |
It achieves the following results on the evaluation set:
|
| 36 |
+
- Loss: 0.5056
|
| 37 |
+
- Accuracy: 0.8647
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second":
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.8646723646723646,
|
| 4 |
+
"eval_loss": 0.5055693984031677,
|
| 5 |
+
"eval_runtime": 16.1252,
|
| 6 |
+
"eval_samples_per_second": 43.534,
|
| 7 |
+
"eval_steps_per_second": 5.457,
|
| 8 |
+
"total_flos": 4.617303784967946e+18,
|
| 9 |
+
"train_loss": 0.43795731744293864,
|
| 10 |
+
"train_runtime": 5300.4754,
|
| 11 |
+
"train_samples_per_second": 11.241,
|
| 12 |
+
"train_steps_per_second": 0.705
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_runtime":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"eval_accuracy": 0.8646723646723646,
|
| 4 |
+
"eval_loss": 0.5055693984031677,
|
| 5 |
+
"eval_runtime": 16.1252,
|
| 6 |
+
"eval_samples_per_second": 43.534,
|
| 7 |
+
"eval_steps_per_second": 5.457
|
| 8 |
}
|
runs/Nov19_07-31-43_09d27efa0afa/events.out.tfevents.1700384480.09d27efa0afa.1367.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b338b4882b66ba3ec59776afe6226a5809d426dd2460d3ca89313edf32cd7e0
|
| 3 |
+
size 411
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 15.0,
|
| 3 |
+
"total_flos": 4.617303784967946e+18,
|
| 4 |
+
"train_loss": 0.43795731744293864,
|
| 5 |
+
"train_runtime": 5300.4754,
|
| 6 |
+
"train_samples_per_second": 11.241,
|
| 7 |
+
"train_steps_per_second": 0.705
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,880 +1,2599 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "Action_all_10_class/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.04,
|
| 13 |
-
"learning_rate": 0.
|
| 14 |
-
"loss": 2.
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.08,
|
| 19 |
-
"learning_rate": 0.
|
| 20 |
-
"loss": 2.
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.12,
|
| 25 |
-
"learning_rate": 0.
|
| 26 |
-
"loss": 1.
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.16,
|
| 31 |
-
"learning_rate": 0.
|
| 32 |
-
"loss": 1.
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.2,
|
| 37 |
-
"learning_rate": 0.
|
| 38 |
-
"loss": 1.
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.24,
|
| 43 |
-
"learning_rate": 0.
|
| 44 |
-
"loss": 1.
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.28,
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.32,
|
| 55 |
-
"learning_rate": 0.
|
| 56 |
-
"loss": 1.
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.36,
|
| 61 |
-
"learning_rate": 0.
|
| 62 |
-
"loss": 1.
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.4,
|
| 67 |
-
"learning_rate": 0.
|
| 68 |
-
"loss": 1.
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.4,
|
| 73 |
-
"eval_accuracy": 0.
|
| 74 |
-
"eval_loss":
|
| 75 |
-
"eval_runtime":
|
| 76 |
-
"eval_samples_per_second":
|
| 77 |
-
"eval_steps_per_second":
|
| 78 |
"step": 100
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 0.44,
|
| 82 |
-
"learning_rate": 0.
|
| 83 |
-
"loss": 1.
|
| 84 |
"step": 110
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 0.48,
|
| 88 |
-
"learning_rate": 0.
|
| 89 |
-
"loss":
|
| 90 |
"step": 120
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 0.52,
|
| 94 |
-
"learning_rate": 0.
|
| 95 |
-
"loss":
|
| 96 |
"step": 130
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 0.56,
|
| 100 |
-
"learning_rate": 0.
|
| 101 |
-
"loss": 1.
|
| 102 |
"step": 140
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.6,
|
| 106 |
-
"learning_rate": 0.
|
| 107 |
-
"loss": 1.
|
| 108 |
"step": 150
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.64,
|
| 112 |
-
"learning_rate": 0.
|
| 113 |
-
"loss":
|
| 114 |
"step": 160
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.68,
|
| 118 |
-
"learning_rate": 0.
|
| 119 |
-
"loss":
|
| 120 |
"step": 170
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 0.72,
|
| 124 |
-
"learning_rate": 0.
|
| 125 |
-
"loss":
|
| 126 |
"step": 180
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 0.76,
|
| 130 |
-
"learning_rate": 0.
|
| 131 |
-
"loss":
|
| 132 |
"step": 190
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 0.8,
|
| 136 |
-
"learning_rate": 0.
|
| 137 |
-
"loss": 0.
|
| 138 |
"step": 200
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 0.8,
|
| 142 |
-
"eval_accuracy": 0.
|
| 143 |
-
"eval_loss": 0.
|
| 144 |
-
"eval_runtime":
|
| 145 |
-
"eval_samples_per_second":
|
| 146 |
-
"eval_steps_per_second":
|
| 147 |
"step": 200
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.84,
|
| 151 |
-
"learning_rate": 0.
|
| 152 |
-
"loss":
|
| 153 |
"step": 210
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.88,
|
| 157 |
-
"learning_rate": 0.
|
| 158 |
-
"loss": 0.
|
| 159 |
"step": 220
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.92,
|
| 163 |
-
"learning_rate": 0.
|
| 164 |
-
"loss": 0.
|
| 165 |
"step": 230
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.96,
|
| 169 |
-
"learning_rate": 0.
|
| 170 |
-
"loss": 0.
|
| 171 |
"step": 240
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 1.0,
|
| 175 |
-
"learning_rate": 0.
|
| 176 |
-
"loss":
|
| 177 |
"step": 250
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 1.04,
|
| 181 |
-
"learning_rate": 0.
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 260
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 1.08,
|
| 187 |
-
"learning_rate": 0.
|
| 188 |
-
"loss": 0.
|
| 189 |
"step": 270
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 1.12,
|
| 193 |
-
"learning_rate": 0.
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 280
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 1.16,
|
| 199 |
-
"learning_rate": 0.
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 290
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 1.2,
|
| 205 |
-
"learning_rate": 0.
|
| 206 |
-
"loss": 0.
|
| 207 |
"step": 300
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 1.2,
|
| 211 |
-
"eval_accuracy": 0.
|
| 212 |
-
"eval_loss": 0.
|
| 213 |
-
"eval_runtime":
|
| 214 |
-
"eval_samples_per_second":
|
| 215 |
-
"eval_steps_per_second":
|
| 216 |
"step": 300
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 1.24,
|
| 220 |
-
"learning_rate": 0.
|
| 221 |
-
"loss": 0.
|
| 222 |
"step": 310
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 1.29,
|
| 226 |
-
"learning_rate": 0.
|
| 227 |
-
"loss": 0.
|
| 228 |
"step": 320
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 1.33,
|
| 232 |
-
"learning_rate": 0.
|
| 233 |
-
"loss": 0.
|
| 234 |
"step": 330
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 1.37,
|
| 238 |
-
"learning_rate": 0.
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 340
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 1.41,
|
| 244 |
-
"learning_rate": 0.
|
| 245 |
-
"loss": 0.
|
| 246 |
"step": 350
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 1.45,
|
| 250 |
-
"learning_rate": 0.
|
| 251 |
-
"loss": 0.
|
| 252 |
"step": 360
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 1.49,
|
| 256 |
-
"learning_rate": 0.
|
| 257 |
-
"loss": 0.
|
| 258 |
"step": 370
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 1.53,
|
| 262 |
-
"learning_rate": 0.
|
| 263 |
-
"loss": 0.
|
| 264 |
"step": 380
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 1.57,
|
| 268 |
-
"learning_rate": 0.
|
| 269 |
-
"loss": 0.
|
| 270 |
"step": 390
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 1.61,
|
| 274 |
-
"learning_rate": 0.
|
| 275 |
-
"loss": 0.
|
| 276 |
"step": 400
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 1.61,
|
| 280 |
-
"eval_accuracy": 0.
|
| 281 |
-
"eval_loss": 0.
|
| 282 |
-
"eval_runtime":
|
| 283 |
-
"eval_samples_per_second":
|
| 284 |
-
"eval_steps_per_second":
|
| 285 |
"step": 400
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 1.65,
|
| 289 |
-
"learning_rate": 0.
|
| 290 |
-
"loss": 0.
|
| 291 |
"step": 410
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 1.69,
|
| 295 |
-
"learning_rate": 0.
|
| 296 |
-
"loss": 0.
|
| 297 |
"step": 420
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 1.73,
|
| 301 |
-
"learning_rate": 0.
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 430
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 1.77,
|
| 307 |
-
"learning_rate": 0.
|
| 308 |
-
"loss": 0.
|
| 309 |
"step": 440
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 1.81,
|
| 313 |
-
"learning_rate": 0.
|
| 314 |
-
"loss": 0.
|
| 315 |
"step": 450
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 1.85,
|
| 319 |
-
"learning_rate": 0.
|
| 320 |
-
"loss": 0.
|
| 321 |
"step": 460
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 1.89,
|
| 325 |
-
"learning_rate": 0.
|
| 326 |
-
"loss": 0.
|
| 327 |
"step": 470
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 1.93,
|
| 331 |
-
"learning_rate": 0.
|
| 332 |
-
"loss": 0.
|
| 333 |
"step": 480
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 1.97,
|
| 337 |
-
"learning_rate": 0.
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 490
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 2.01,
|
| 343 |
-
"learning_rate": 0.
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 500
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 2.01,
|
| 349 |
-
"eval_accuracy": 0.
|
| 350 |
-
"eval_loss": 0.
|
| 351 |
-
"eval_runtime":
|
| 352 |
-
"eval_samples_per_second":
|
| 353 |
-
"eval_steps_per_second":
|
| 354 |
"step": 500
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 2.05,
|
| 358 |
-
"learning_rate": 0.
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 510
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 2.09,
|
| 364 |
-
"learning_rate": 0.
|
| 365 |
-
"loss": 0.
|
| 366 |
"step": 520
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 2.13,
|
| 370 |
-
"learning_rate": 0.
|
| 371 |
-
"loss": 0.
|
| 372 |
"step": 530
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 2.17,
|
| 376 |
-
"learning_rate": 0.
|
| 377 |
-
"loss": 0.
|
| 378 |
"step": 540
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 2.21,
|
| 382 |
-
"learning_rate": 0.
|
| 383 |
-
"loss": 0.
|
| 384 |
"step": 550
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 2.25,
|
| 388 |
-
"learning_rate": 0.
|
| 389 |
-
"loss": 0.
|
| 390 |
"step": 560
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 2.29,
|
| 394 |
-
"learning_rate": 0.
|
| 395 |
-
"loss": 0.
|
| 396 |
"step": 570
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 2.33,
|
| 400 |
-
"learning_rate": 0.
|
| 401 |
-
"loss": 0.
|
| 402 |
"step": 580
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 2.37,
|
| 406 |
-
"learning_rate": 0.
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 590
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 2.41,
|
| 412 |
-
"learning_rate": 0.
|
| 413 |
-
"loss": 0.
|
| 414 |
"step": 600
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 2.41,
|
| 418 |
-
"eval_accuracy": 0.
|
| 419 |
-
"eval_loss": 0.
|
| 420 |
-
"eval_runtime":
|
| 421 |
-
"eval_samples_per_second":
|
| 422 |
-
"eval_steps_per_second":
|
| 423 |
"step": 600
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 2.45,
|
| 427 |
-
"learning_rate": 0.
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 610
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 2.49,
|
| 433 |
-
"learning_rate": 0.
|
| 434 |
-
"loss": 0.
|
| 435 |
"step": 620
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 2.53,
|
| 439 |
-
"learning_rate":
|
| 440 |
-
"loss": 0.
|
| 441 |
"step": 630
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 2.57,
|
| 445 |
-
"learning_rate":
|
| 446 |
-
"loss": 0.
|
| 447 |
"step": 640
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 2.61,
|
| 451 |
-
"learning_rate":
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 650
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 2.65,
|
| 457 |
-
"learning_rate":
|
| 458 |
-
"loss": 0.
|
| 459 |
"step": 660
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 2.69,
|
| 463 |
-
"learning_rate":
|
| 464 |
-
"loss": 0.
|
| 465 |
"step": 670
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 2.73,
|
| 469 |
-
"learning_rate":
|
| 470 |
-
"loss": 0.
|
| 471 |
"step": 680
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 2.77,
|
| 475 |
-
"learning_rate":
|
| 476 |
-
"loss": 0.
|
| 477 |
"step": 690
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 2.81,
|
| 481 |
-
"learning_rate":
|
| 482 |
-
"loss": 0.
|
| 483 |
"step": 700
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 2.81,
|
| 487 |
-
"eval_accuracy": 0.
|
| 488 |
-
"eval_loss": 0.
|
| 489 |
-
"eval_runtime":
|
| 490 |
-
"eval_samples_per_second":
|
| 491 |
-
"eval_steps_per_second":
|
| 492 |
"step": 700
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 2.85,
|
| 496 |
-
"learning_rate":
|
| 497 |
-
"loss": 0.
|
| 498 |
"step": 710
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 2.89,
|
| 502 |
-
"learning_rate":
|
| 503 |
-
"loss": 0.
|
| 504 |
"step": 720
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 2.93,
|
| 508 |
-
"learning_rate":
|
| 509 |
-
"loss": 0.
|
| 510 |
"step": 730
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 2.97,
|
| 514 |
-
"learning_rate":
|
| 515 |
-
"loss": 0.
|
| 516 |
"step": 740
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 3.01,
|
| 520 |
-
"learning_rate":
|
| 521 |
-
"loss": 0.
|
| 522 |
"step": 750
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 3.05,
|
| 526 |
-
"learning_rate":
|
| 527 |
-
"loss": 0.
|
| 528 |
"step": 760
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 3.09,
|
| 532 |
-
"learning_rate":
|
| 533 |
-
"loss": 0.
|
| 534 |
"step": 770
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 3.13,
|
| 538 |
-
"learning_rate":
|
| 539 |
-
"loss": 0.
|
| 540 |
"step": 780
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 3.17,
|
| 544 |
-
"learning_rate":
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 790
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 3.21,
|
| 550 |
-
"learning_rate":
|
| 551 |
-
"loss": 0.
|
| 552 |
"step": 800
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 3.21,
|
| 556 |
-
"eval_accuracy": 0.
|
| 557 |
-
"eval_loss": 0.
|
| 558 |
-
"eval_runtime":
|
| 559 |
-
"eval_samples_per_second":
|
| 560 |
-
"eval_steps_per_second":
|
| 561 |
"step": 800
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 3.25,
|
| 565 |
-
"learning_rate":
|
| 566 |
-
"loss": 0.
|
| 567 |
"step": 810
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 3.29,
|
| 571 |
-
"learning_rate":
|
| 572 |
-
"loss": 0.
|
| 573 |
"step": 820
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 3.33,
|
| 577 |
-
"learning_rate":
|
| 578 |
-
"loss": 0.
|
| 579 |
"step": 830
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 3.37,
|
| 583 |
-
"learning_rate":
|
| 584 |
-
"loss": 0.
|
| 585 |
"step": 840
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 3.41,
|
| 589 |
-
"learning_rate":
|
| 590 |
-
"loss": 0.
|
| 591 |
"step": 850
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 3.45,
|
| 595 |
-
"learning_rate":
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 860
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 3.49,
|
| 601 |
-
"learning_rate":
|
| 602 |
-
"loss": 0.
|
| 603 |
"step": 870
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 3.53,
|
| 607 |
-
"learning_rate":
|
| 608 |
-
"loss": 0.
|
| 609 |
"step": 880
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 3.57,
|
| 613 |
-
"learning_rate":
|
| 614 |
-
"loss": 0.
|
| 615 |
"step": 890
|
| 616 |
},
|
| 617 |
{
|
| 618 |
"epoch": 3.61,
|
| 619 |
-
"learning_rate":
|
| 620 |
-
"loss": 0.
|
| 621 |
"step": 900
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 3.61,
|
| 625 |
-
"eval_accuracy": 0.
|
| 626 |
-
"eval_loss": 0.
|
| 627 |
-
"eval_runtime":
|
| 628 |
-
"eval_samples_per_second":
|
| 629 |
-
"eval_steps_per_second":
|
| 630 |
"step": 900
|
| 631 |
},
|
| 632 |
{
|
| 633 |
"epoch": 3.65,
|
| 634 |
-
"learning_rate":
|
| 635 |
-
"loss": 0.
|
| 636 |
"step": 910
|
| 637 |
},
|
| 638 |
{
|
| 639 |
"epoch": 3.69,
|
| 640 |
-
"learning_rate":
|
| 641 |
-
"loss": 0.
|
| 642 |
"step": 920
|
| 643 |
},
|
| 644 |
{
|
| 645 |
"epoch": 3.73,
|
| 646 |
-
"learning_rate":
|
| 647 |
-
"loss": 0.
|
| 648 |
"step": 930
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 3.78,
|
| 652 |
-
"learning_rate":
|
| 653 |
-
"loss": 0.
|
| 654 |
"step": 940
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 3.82,
|
| 658 |
-
"learning_rate":
|
| 659 |
-
"loss": 0.
|
| 660 |
"step": 950
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 3.86,
|
| 664 |
-
"learning_rate":
|
| 665 |
-
"loss": 0.
|
| 666 |
"step": 960
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 3.9,
|
| 670 |
-
"learning_rate":
|
| 671 |
-
"loss": 0.
|
| 672 |
"step": 970
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 3.94,
|
| 676 |
-
"learning_rate":
|
| 677 |
-
"loss": 0.
|
| 678 |
"step": 980
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 3.98,
|
| 682 |
-
"learning_rate":
|
| 683 |
-
"loss": 0.
|
| 684 |
"step": 990
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 4.02,
|
| 688 |
-
"learning_rate":
|
| 689 |
-
"loss": 0.
|
| 690 |
"step": 1000
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 4.02,
|
| 694 |
-
"eval_accuracy": 0.
|
| 695 |
-
"eval_loss": 0.
|
| 696 |
-
"eval_runtime":
|
| 697 |
-
"eval_samples_per_second":
|
| 698 |
-
"eval_steps_per_second":
|
| 699 |
"step": 1000
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 4.06,
|
| 703 |
-
"learning_rate":
|
| 704 |
-
"loss": 0.
|
| 705 |
"step": 1010
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 4.1,
|
| 709 |
-
"learning_rate":
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 1020
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 4.14,
|
| 715 |
-
"learning_rate":
|
| 716 |
-
"loss": 0.
|
| 717 |
"step": 1030
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 4.18,
|
| 721 |
-
"learning_rate":
|
| 722 |
-
"loss": 0.
|
| 723 |
"step": 1040
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 4.22,
|
| 727 |
-
"learning_rate":
|
| 728 |
-
"loss": 0.
|
| 729 |
"step": 1050
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 4.26,
|
| 733 |
-
"learning_rate":
|
| 734 |
-
"loss": 0.
|
| 735 |
"step": 1060
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 4.3,
|
| 739 |
-
"learning_rate":
|
| 740 |
-
"loss": 0.
|
| 741 |
"step": 1070
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 4.34,
|
| 745 |
-
"learning_rate":
|
| 746 |
-
"loss": 0.
|
| 747 |
"step": 1080
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 4.38,
|
| 751 |
-
"learning_rate":
|
| 752 |
-
"loss": 0.
|
| 753 |
"step": 1090
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 4.42,
|
| 757 |
-
"learning_rate":
|
| 758 |
-
"loss": 0.
|
| 759 |
"step": 1100
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 4.42,
|
| 763 |
-
"eval_accuracy": 0.
|
| 764 |
-
"eval_loss": 0.
|
| 765 |
-
"eval_runtime":
|
| 766 |
-
"eval_samples_per_second":
|
| 767 |
-
"eval_steps_per_second":
|
| 768 |
"step": 1100
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 4.46,
|
| 772 |
-
"learning_rate":
|
| 773 |
-
"loss": 0.
|
| 774 |
"step": 1110
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 4.5,
|
| 778 |
-
"learning_rate":
|
| 779 |
-
"loss": 0.
|
| 780 |
"step": 1120
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 4.54,
|
| 784 |
-
"learning_rate":
|
| 785 |
-
"loss": 0.
|
| 786 |
"step": 1130
|
| 787 |
},
|
| 788 |
{
|
| 789 |
"epoch": 4.58,
|
| 790 |
-
"learning_rate":
|
| 791 |
-
"loss": 0.
|
| 792 |
"step": 1140
|
| 793 |
},
|
| 794 |
{
|
| 795 |
"epoch": 4.62,
|
| 796 |
-
"learning_rate":
|
| 797 |
-
"loss": 0.
|
| 798 |
"step": 1150
|
| 799 |
},
|
| 800 |
{
|
| 801 |
"epoch": 4.66,
|
| 802 |
-
"learning_rate":
|
| 803 |
-
"loss": 0.
|
| 804 |
"step": 1160
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 4.7,
|
| 808 |
-
"learning_rate":
|
| 809 |
-
"loss": 0.
|
| 810 |
"step": 1170
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 4.74,
|
| 814 |
-
"learning_rate":
|
| 815 |
-
"loss": 0.
|
| 816 |
"step": 1180
|
| 817 |
},
|
| 818 |
{
|
| 819 |
"epoch": 4.78,
|
| 820 |
-
"learning_rate":
|
| 821 |
-
"loss": 0.
|
| 822 |
"step": 1190
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 4.82,
|
| 826 |
-
"learning_rate":
|
| 827 |
-
"loss": 0.
|
| 828 |
"step": 1200
|
| 829 |
},
|
| 830 |
{
|
| 831 |
"epoch": 4.82,
|
| 832 |
-
"eval_accuracy": 0.
|
| 833 |
-
"eval_loss": 0.
|
| 834 |
-
"eval_runtime":
|
| 835 |
-
"eval_samples_per_second":
|
| 836 |
-
"eval_steps_per_second":
|
| 837 |
"step": 1200
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 4.86,
|
| 841 |
-
"learning_rate":
|
| 842 |
-
"loss": 0.
|
| 843 |
"step": 1210
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 4.9,
|
| 847 |
-
"learning_rate":
|
| 848 |
-
"loss": 0.
|
| 849 |
"step": 1220
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 4.94,
|
| 853 |
-
"learning_rate":
|
| 854 |
-
"loss": 0.
|
| 855 |
"step": 1230
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 4.98,
|
| 859 |
-
"learning_rate":
|
| 860 |
-
"loss": 0.
|
| 861 |
"step": 1240
|
| 862 |
},
|
| 863 |
{
|
| 864 |
-
"epoch": 5.
|
| 865 |
-
"
|
| 866 |
-
"
|
| 867 |
-
"
|
| 868 |
-
|
| 869 |
-
|
| 870 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 871 |
}
|
| 872 |
],
|
| 873 |
"logging_steps": 10,
|
| 874 |
-
"max_steps":
|
| 875 |
-
"num_train_epochs":
|
| 876 |
"save_steps": 100,
|
| 877 |
-
"total_flos":
|
| 878 |
"trial_name": null,
|
| 879 |
"trial_params": null
|
| 880 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.5055693984031677,
|
| 3 |
+
"best_model_checkpoint": "Action_all_10_class/checkpoint-2700",
|
| 4 |
+
"epoch": 15.0,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 3735,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.04,
|
| 13 |
+
"learning_rate": 0.0001994645247657296,
|
| 14 |
+
"loss": 2.2354,
|
| 15 |
"step": 10
|
| 16 |
},
|
| 17 |
{
|
| 18 |
"epoch": 0.08,
|
| 19 |
+
"learning_rate": 0.00019892904953145918,
|
| 20 |
+
"loss": 2.071,
|
| 21 |
"step": 20
|
| 22 |
},
|
| 23 |
{
|
| 24 |
"epoch": 0.12,
|
| 25 |
+
"learning_rate": 0.00019839357429718877,
|
| 26 |
+
"loss": 1.8632,
|
| 27 |
"step": 30
|
| 28 |
},
|
| 29 |
{
|
| 30 |
"epoch": 0.16,
|
| 31 |
+
"learning_rate": 0.00019785809906291835,
|
| 32 |
+
"loss": 1.6341,
|
| 33 |
"step": 40
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 0.2,
|
| 37 |
+
"learning_rate": 0.0001973226238286479,
|
| 38 |
+
"loss": 1.5563,
|
| 39 |
"step": 50
|
| 40 |
},
|
| 41 |
{
|
| 42 |
"epoch": 0.24,
|
| 43 |
+
"learning_rate": 0.00019678714859437752,
|
| 44 |
+
"loss": 1.3715,
|
| 45 |
"step": 60
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 0.28,
|
| 49 |
+
"learning_rate": 0.0001962516733601071,
|
| 50 |
+
"loss": 1.3253,
|
| 51 |
"step": 70
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.32,
|
| 55 |
+
"learning_rate": 0.00019571619812583667,
|
| 56 |
+
"loss": 1.2745,
|
| 57 |
"step": 80
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 0.36,
|
| 61 |
+
"learning_rate": 0.00019518072289156628,
|
| 62 |
+
"loss": 1.2778,
|
| 63 |
"step": 90
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 0.4,
|
| 67 |
+
"learning_rate": 0.00019464524765729587,
|
| 68 |
+
"loss": 1.1504,
|
| 69 |
"step": 100
|
| 70 |
},
|
| 71 |
{
|
| 72 |
"epoch": 0.4,
|
| 73 |
+
"eval_accuracy": 0.7777777777777778,
|
| 74 |
+
"eval_loss": 0.8748393058776855,
|
| 75 |
+
"eval_runtime": 418.086,
|
| 76 |
+
"eval_samples_per_second": 1.679,
|
| 77 |
+
"eval_steps_per_second": 0.21,
|
| 78 |
"step": 100
|
| 79 |
},
|
| 80 |
{
|
| 81 |
"epoch": 0.44,
|
| 82 |
+
"learning_rate": 0.00019410977242302542,
|
| 83 |
+
"loss": 1.0145,
|
| 84 |
"step": 110
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 0.48,
|
| 88 |
+
"learning_rate": 0.00019357429718875504,
|
| 89 |
+
"loss": 1.1444,
|
| 90 |
"step": 120
|
| 91 |
},
|
| 92 |
{
|
| 93 |
"epoch": 0.52,
|
| 94 |
+
"learning_rate": 0.00019303882195448462,
|
| 95 |
+
"loss": 0.9792,
|
| 96 |
"step": 130
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 0.56,
|
| 100 |
+
"learning_rate": 0.0001925033467202142,
|
| 101 |
+
"loss": 1.1636,
|
| 102 |
"step": 140
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.6,
|
| 106 |
+
"learning_rate": 0.00019196787148594377,
|
| 107 |
+
"loss": 1.0842,
|
| 108 |
"step": 150
|
| 109 |
},
|
| 110 |
{
|
| 111 |
"epoch": 0.64,
|
| 112 |
+
"learning_rate": 0.00019143239625167338,
|
| 113 |
+
"loss": 0.9826,
|
| 114 |
"step": 160
|
| 115 |
},
|
| 116 |
{
|
| 117 |
"epoch": 0.68,
|
| 118 |
+
"learning_rate": 0.00019089692101740297,
|
| 119 |
+
"loss": 0.8372,
|
| 120 |
"step": 170
|
| 121 |
},
|
| 122 |
{
|
| 123 |
"epoch": 0.72,
|
| 124 |
+
"learning_rate": 0.00019036144578313252,
|
| 125 |
+
"loss": 0.8697,
|
| 126 |
"step": 180
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 0.76,
|
| 130 |
+
"learning_rate": 0.00018982597054886214,
|
| 131 |
+
"loss": 0.9655,
|
| 132 |
"step": 190
|
| 133 |
},
|
| 134 |
{
|
| 135 |
"epoch": 0.8,
|
| 136 |
+
"learning_rate": 0.00018929049531459172,
|
| 137 |
+
"loss": 0.944,
|
| 138 |
"step": 200
|
| 139 |
},
|
| 140 |
{
|
| 141 |
"epoch": 0.8,
|
| 142 |
+
"eval_accuracy": 0.7549857549857549,
|
| 143 |
+
"eval_loss": 0.8146545886993408,
|
| 144 |
+
"eval_runtime": 15.9187,
|
| 145 |
+
"eval_samples_per_second": 44.099,
|
| 146 |
+
"eval_steps_per_second": 5.528,
|
| 147 |
"step": 200
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.84,
|
| 151 |
+
"learning_rate": 0.00018875502008032128,
|
| 152 |
+
"loss": 0.9529,
|
| 153 |
"step": 210
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.88,
|
| 157 |
+
"learning_rate": 0.0001882195448460509,
|
| 158 |
+
"loss": 0.9535,
|
| 159 |
"step": 220
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.92,
|
| 163 |
+
"learning_rate": 0.00018768406961178048,
|
| 164 |
+
"loss": 0.8665,
|
| 165 |
"step": 230
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.96,
|
| 169 |
+
"learning_rate": 0.00018714859437751004,
|
| 170 |
+
"loss": 0.8345,
|
| 171 |
"step": 240
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 1.0,
|
| 175 |
+
"learning_rate": 0.00018661311914323962,
|
| 176 |
+
"loss": 1.0123,
|
| 177 |
"step": 250
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 1.04,
|
| 181 |
+
"learning_rate": 0.00018607764390896924,
|
| 182 |
+
"loss": 0.8241,
|
| 183 |
"step": 260
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 1.08,
|
| 187 |
+
"learning_rate": 0.0001855421686746988,
|
| 188 |
+
"loss": 0.8182,
|
| 189 |
"step": 270
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 1.12,
|
| 193 |
+
"learning_rate": 0.00018500669344042838,
|
| 194 |
+
"loss": 0.8616,
|
| 195 |
"step": 280
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 1.16,
|
| 199 |
+
"learning_rate": 0.000184471218206158,
|
| 200 |
+
"loss": 0.7276,
|
| 201 |
"step": 290
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 1.2,
|
| 205 |
+
"learning_rate": 0.00018393574297188755,
|
| 206 |
+
"loss": 0.9096,
|
| 207 |
"step": 300
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 1.2,
|
| 211 |
+
"eval_accuracy": 0.7507122507122507,
|
| 212 |
+
"eval_loss": 0.7890926003456116,
|
| 213 |
+
"eval_runtime": 16.3956,
|
| 214 |
+
"eval_samples_per_second": 42.816,
|
| 215 |
+
"eval_steps_per_second": 5.367,
|
| 216 |
"step": 300
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 1.24,
|
| 220 |
+
"learning_rate": 0.00018340026773761714,
|
| 221 |
+
"loss": 0.8907,
|
| 222 |
"step": 310
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 1.29,
|
| 226 |
+
"learning_rate": 0.00018286479250334675,
|
| 227 |
+
"loss": 0.8123,
|
| 228 |
"step": 320
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 1.33,
|
| 232 |
+
"learning_rate": 0.0001823293172690763,
|
| 233 |
+
"loss": 0.7859,
|
| 234 |
"step": 330
|
| 235 |
},
|
| 236 |
{
|
| 237 |
"epoch": 1.37,
|
| 238 |
+
"learning_rate": 0.0001817938420348059,
|
| 239 |
+
"loss": 0.8536,
|
| 240 |
"step": 340
|
| 241 |
},
|
| 242 |
{
|
| 243 |
"epoch": 1.41,
|
| 244 |
+
"learning_rate": 0.00018125836680053548,
|
| 245 |
+
"loss": 0.7297,
|
| 246 |
"step": 350
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 1.45,
|
| 250 |
+
"learning_rate": 0.00018072289156626507,
|
| 251 |
+
"loss": 0.9101,
|
| 252 |
"step": 360
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 1.49,
|
| 256 |
+
"learning_rate": 0.00018018741633199465,
|
| 257 |
+
"loss": 0.8368,
|
| 258 |
"step": 370
|
| 259 |
},
|
| 260 |
{
|
| 261 |
"epoch": 1.53,
|
| 262 |
+
"learning_rate": 0.00017965194109772424,
|
| 263 |
+
"loss": 0.7023,
|
| 264 |
"step": 380
|
| 265 |
},
|
| 266 |
{
|
| 267 |
"epoch": 1.57,
|
| 268 |
+
"learning_rate": 0.00017911646586345382,
|
| 269 |
+
"loss": 0.7859,
|
| 270 |
"step": 390
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 1.61,
|
| 274 |
+
"learning_rate": 0.0001785809906291834,
|
| 275 |
+
"loss": 0.7847,
|
| 276 |
"step": 400
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 1.61,
|
| 280 |
+
"eval_accuracy": 0.7749287749287749,
|
| 281 |
+
"eval_loss": 0.749781608581543,
|
| 282 |
+
"eval_runtime": 16.0514,
|
| 283 |
+
"eval_samples_per_second": 43.735,
|
| 284 |
+
"eval_steps_per_second": 5.482,
|
| 285 |
"step": 400
|
| 286 |
},
|
| 287 |
{
|
| 288 |
"epoch": 1.65,
|
| 289 |
+
"learning_rate": 0.000178045515394913,
|
| 290 |
+
"loss": 0.7916,
|
| 291 |
"step": 410
|
| 292 |
},
|
| 293 |
{
|
| 294 |
"epoch": 1.69,
|
| 295 |
+
"learning_rate": 0.00017751004016064258,
|
| 296 |
+
"loss": 0.832,
|
| 297 |
"step": 420
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 1.73,
|
| 301 |
+
"learning_rate": 0.00017697456492637216,
|
| 302 |
+
"loss": 0.8133,
|
| 303 |
"step": 430
|
| 304 |
},
|
| 305 |
{
|
| 306 |
"epoch": 1.77,
|
| 307 |
+
"learning_rate": 0.00017643908969210175,
|
| 308 |
+
"loss": 0.9792,
|
| 309 |
"step": 440
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 1.81,
|
| 313 |
+
"learning_rate": 0.00017590361445783134,
|
| 314 |
+
"loss": 0.8379,
|
| 315 |
"step": 450
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 1.85,
|
| 319 |
+
"learning_rate": 0.00017536813922356092,
|
| 320 |
+
"loss": 0.6937,
|
| 321 |
"step": 460
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 1.89,
|
| 325 |
+
"learning_rate": 0.0001748326639892905,
|
| 326 |
+
"loss": 0.6223,
|
| 327 |
"step": 470
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 1.93,
|
| 331 |
+
"learning_rate": 0.0001742971887550201,
|
| 332 |
+
"loss": 0.7433,
|
| 333 |
"step": 480
|
| 334 |
},
|
| 335 |
{
|
| 336 |
"epoch": 1.97,
|
| 337 |
+
"learning_rate": 0.00017376171352074968,
|
| 338 |
+
"loss": 0.8604,
|
| 339 |
"step": 490
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 2.01,
|
| 343 |
+
"learning_rate": 0.00017322623828647926,
|
| 344 |
+
"loss": 0.7296,
|
| 345 |
"step": 500
|
| 346 |
},
|
| 347 |
{
|
| 348 |
"epoch": 2.01,
|
| 349 |
+
"eval_accuracy": 0.8034188034188035,
|
| 350 |
+
"eval_loss": 0.6464697122573853,
|
| 351 |
+
"eval_runtime": 15.9168,
|
| 352 |
+
"eval_samples_per_second": 44.104,
|
| 353 |
+
"eval_steps_per_second": 5.529,
|
| 354 |
"step": 500
|
| 355 |
},
|
| 356 |
{
|
| 357 |
"epoch": 2.05,
|
| 358 |
+
"learning_rate": 0.00017269076305220885,
|
| 359 |
+
"loss": 0.6047,
|
| 360 |
"step": 510
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 2.09,
|
| 364 |
+
"learning_rate": 0.00017215528781793844,
|
| 365 |
+
"loss": 0.7931,
|
| 366 |
"step": 520
|
| 367 |
},
|
| 368 |
{
|
| 369 |
"epoch": 2.13,
|
| 370 |
+
"learning_rate": 0.00017161981258366802,
|
| 371 |
+
"loss": 0.6484,
|
| 372 |
"step": 530
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 2.17,
|
| 376 |
+
"learning_rate": 0.0001710843373493976,
|
| 377 |
+
"loss": 0.6168,
|
| 378 |
"step": 540
|
| 379 |
},
|
| 380 |
{
|
| 381 |
"epoch": 2.21,
|
| 382 |
+
"learning_rate": 0.00017054886211512717,
|
| 383 |
+
"loss": 0.6084,
|
| 384 |
"step": 550
|
| 385 |
},
|
| 386 |
{
|
| 387 |
"epoch": 2.25,
|
| 388 |
+
"learning_rate": 0.00017001338688085678,
|
| 389 |
+
"loss": 0.5808,
|
| 390 |
"step": 560
|
| 391 |
},
|
| 392 |
{
|
| 393 |
"epoch": 2.29,
|
| 394 |
+
"learning_rate": 0.00016947791164658636,
|
| 395 |
+
"loss": 0.6777,
|
| 396 |
"step": 570
|
| 397 |
},
|
| 398 |
{
|
| 399 |
"epoch": 2.33,
|
| 400 |
+
"learning_rate": 0.00016894243641231592,
|
| 401 |
+
"loss": 0.6263,
|
| 402 |
"step": 580
|
| 403 |
},
|
| 404 |
{
|
| 405 |
"epoch": 2.37,
|
| 406 |
+
"learning_rate": 0.00016840696117804553,
|
| 407 |
+
"loss": 0.6697,
|
| 408 |
"step": 590
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 2.41,
|
| 412 |
+
"learning_rate": 0.00016787148594377512,
|
| 413 |
+
"loss": 0.7107,
|
| 414 |
"step": 600
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 2.41,
|
| 418 |
+
"eval_accuracy": 0.7549857549857549,
|
| 419 |
+
"eval_loss": 0.7201387882232666,
|
| 420 |
+
"eval_runtime": 16.1564,
|
| 421 |
+
"eval_samples_per_second": 43.45,
|
| 422 |
+
"eval_steps_per_second": 5.447,
|
| 423 |
"step": 600
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 2.45,
|
| 427 |
+
"learning_rate": 0.00016733601070950468,
|
| 428 |
+
"loss": 0.6248,
|
| 429 |
"step": 610
|
| 430 |
},
|
| 431 |
{
|
| 432 |
"epoch": 2.49,
|
| 433 |
+
"learning_rate": 0.0001668005354752343,
|
| 434 |
+
"loss": 0.6299,
|
| 435 |
"step": 620
|
| 436 |
},
|
| 437 |
{
|
| 438 |
"epoch": 2.53,
|
| 439 |
+
"learning_rate": 0.00016631860776439089,
|
| 440 |
+
"loss": 0.7085,
|
| 441 |
"step": 630
|
| 442 |
},
|
| 443 |
{
|
| 444 |
"epoch": 2.57,
|
| 445 |
+
"learning_rate": 0.0001657831325301205,
|
| 446 |
+
"loss": 0.6907,
|
| 447 |
"step": 640
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 2.61,
|
| 451 |
+
"learning_rate": 0.00016524765729585008,
|
| 452 |
+
"loss": 0.7222,
|
| 453 |
"step": 650
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 2.65,
|
| 457 |
+
"learning_rate": 0.00016471218206157964,
|
| 458 |
+
"loss": 0.5053,
|
| 459 |
"step": 660
|
| 460 |
},
|
| 461 |
{
|
| 462 |
"epoch": 2.69,
|
| 463 |
+
"learning_rate": 0.00016417670682730923,
|
| 464 |
+
"loss": 0.5526,
|
| 465 |
"step": 670
|
| 466 |
},
|
| 467 |
{
|
| 468 |
"epoch": 2.73,
|
| 469 |
+
"learning_rate": 0.00016364123159303884,
|
| 470 |
+
"loss": 0.7261,
|
| 471 |
"step": 680
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 2.77,
|
| 475 |
+
"learning_rate": 0.0001631057563587684,
|
| 476 |
+
"loss": 0.7419,
|
| 477 |
"step": 690
|
| 478 |
},
|
| 479 |
{
|
| 480 |
"epoch": 2.81,
|
| 481 |
+
"learning_rate": 0.00016257028112449799,
|
| 482 |
+
"loss": 0.5229,
|
| 483 |
"step": 700
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 2.81,
|
| 487 |
+
"eval_accuracy": 0.7521367521367521,
|
| 488 |
+
"eval_loss": 0.7578324675559998,
|
| 489 |
+
"eval_runtime": 15.6021,
|
| 490 |
+
"eval_samples_per_second": 44.994,
|
| 491 |
+
"eval_steps_per_second": 5.64,
|
| 492 |
"step": 700
|
| 493 |
},
|
| 494 |
{
|
| 495 |
"epoch": 2.85,
|
| 496 |
+
"learning_rate": 0.0001620348058902276,
|
| 497 |
+
"loss": 0.5829,
|
| 498 |
"step": 710
|
| 499 |
},
|
| 500 |
{
|
| 501 |
"epoch": 2.89,
|
| 502 |
+
"learning_rate": 0.00016149933065595716,
|
| 503 |
+
"loss": 0.7214,
|
| 504 |
"step": 720
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 2.93,
|
| 508 |
+
"learning_rate": 0.00016096385542168674,
|
| 509 |
+
"loss": 0.5506,
|
| 510 |
"step": 730
|
| 511 |
},
|
| 512 |
{
|
| 513 |
"epoch": 2.97,
|
| 514 |
+
"learning_rate": 0.00016042838018741636,
|
| 515 |
+
"loss": 0.6699,
|
| 516 |
"step": 740
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 3.01,
|
| 520 |
+
"learning_rate": 0.00015989290495314594,
|
| 521 |
+
"loss": 0.6616,
|
| 522 |
"step": 750
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 3.05,
|
| 526 |
+
"learning_rate": 0.0001593574297188755,
|
| 527 |
+
"loss": 0.6225,
|
| 528 |
"step": 760
|
| 529 |
},
|
| 530 |
{
|
| 531 |
"epoch": 3.09,
|
| 532 |
+
"learning_rate": 0.00015882195448460509,
|
| 533 |
+
"loss": 0.4438,
|
| 534 |
"step": 770
|
| 535 |
},
|
| 536 |
{
|
| 537 |
"epoch": 3.13,
|
| 538 |
+
"learning_rate": 0.0001582864792503347,
|
| 539 |
+
"loss": 0.5325,
|
| 540 |
"step": 780
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 3.17,
|
| 544 |
+
"learning_rate": 0.00015775100401606426,
|
| 545 |
+
"loss": 0.4131,
|
| 546 |
"step": 790
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 3.21,
|
| 550 |
+
"learning_rate": 0.00015721552878179384,
|
| 551 |
+
"loss": 0.4698,
|
| 552 |
"step": 800
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 3.21,
|
| 556 |
+
"eval_accuracy": 0.811965811965812,
|
| 557 |
+
"eval_loss": 0.6026700735092163,
|
| 558 |
+
"eval_runtime": 16.0444,
|
| 559 |
+
"eval_samples_per_second": 43.754,
|
| 560 |
+
"eval_steps_per_second": 5.485,
|
| 561 |
"step": 800
|
| 562 |
},
|
| 563 |
{
|
| 564 |
"epoch": 3.25,
|
| 565 |
+
"learning_rate": 0.00015668005354752345,
|
| 566 |
+
"loss": 0.6905,
|
| 567 |
"step": 810
|
| 568 |
},
|
| 569 |
{
|
| 570 |
"epoch": 3.29,
|
| 571 |
+
"learning_rate": 0.000156144578313253,
|
| 572 |
+
"loss": 0.5132,
|
| 573 |
"step": 820
|
| 574 |
},
|
| 575 |
{
|
| 576 |
"epoch": 3.33,
|
| 577 |
+
"learning_rate": 0.0001556091030789826,
|
| 578 |
+
"loss": 0.474,
|
| 579 |
"step": 830
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 3.37,
|
| 583 |
+
"learning_rate": 0.0001550736278447122,
|
| 584 |
+
"loss": 0.5092,
|
| 585 |
"step": 840
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 3.41,
|
| 589 |
+
"learning_rate": 0.00015453815261044177,
|
| 590 |
+
"loss": 0.538,
|
| 591 |
"step": 850
|
| 592 |
},
|
| 593 |
{
|
| 594 |
"epoch": 3.45,
|
| 595 |
+
"learning_rate": 0.00015400267737617136,
|
| 596 |
+
"loss": 0.5138,
|
| 597 |
"step": 860
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 3.49,
|
| 601 |
+
"learning_rate": 0.00015346720214190094,
|
| 602 |
+
"loss": 0.5828,
|
| 603 |
"step": 870
|
| 604 |
},
|
| 605 |
{
|
| 606 |
"epoch": 3.53,
|
| 607 |
+
"learning_rate": 0.00015293172690763053,
|
| 608 |
+
"loss": 0.562,
|
| 609 |
"step": 880
|
| 610 |
},
|
| 611 |
{
|
| 612 |
"epoch": 3.57,
|
| 613 |
+
"learning_rate": 0.0001523962516733601,
|
| 614 |
+
"loss": 0.6672,
|
| 615 |
"step": 890
|
| 616 |
},
|
| 617 |
{
|
| 618 |
"epoch": 3.61,
|
| 619 |
+
"learning_rate": 0.0001518607764390897,
|
| 620 |
+
"loss": 0.4846,
|
| 621 |
"step": 900
|
| 622 |
},
|
| 623 |
{
|
| 624 |
"epoch": 3.61,
|
| 625 |
+
"eval_accuracy": 0.7877492877492878,
|
| 626 |
+
"eval_loss": 0.7316339612007141,
|
| 627 |
+
"eval_runtime": 16.5159,
|
| 628 |
+
"eval_samples_per_second": 42.505,
|
| 629 |
+
"eval_steps_per_second": 5.328,
|
| 630 |
"step": 900
|
| 631 |
},
|
| 632 |
{
|
| 633 |
"epoch": 3.65,
|
| 634 |
+
"learning_rate": 0.00015132530120481928,
|
| 635 |
+
"loss": 0.5271,
|
| 636 |
"step": 910
|
| 637 |
},
|
| 638 |
{
|
| 639 |
"epoch": 3.69,
|
| 640 |
+
"learning_rate": 0.00015078982597054887,
|
| 641 |
+
"loss": 0.5956,
|
| 642 |
"step": 920
|
| 643 |
},
|
| 644 |
{
|
| 645 |
"epoch": 3.73,
|
| 646 |
+
"learning_rate": 0.00015025435073627846,
|
| 647 |
+
"loss": 0.5846,
|
| 648 |
"step": 930
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 3.78,
|
| 652 |
+
"learning_rate": 0.00014971887550200804,
|
| 653 |
+
"loss": 0.6677,
|
| 654 |
"step": 940
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 3.82,
|
| 658 |
+
"learning_rate": 0.00014918340026773763,
|
| 659 |
+
"loss": 0.5125,
|
| 660 |
"step": 950
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 3.86,
|
| 664 |
+
"learning_rate": 0.0001486479250334672,
|
| 665 |
+
"loss": 0.5183,
|
| 666 |
"step": 960
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 3.9,
|
| 670 |
+
"learning_rate": 0.00014811244979919677,
|
| 671 |
+
"loss": 0.654,
|
| 672 |
"step": 970
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 3.94,
|
| 676 |
+
"learning_rate": 0.00014757697456492638,
|
| 677 |
+
"loss": 0.5701,
|
| 678 |
"step": 980
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 3.98,
|
| 682 |
+
"learning_rate": 0.00014704149933065597,
|
| 683 |
+
"loss": 0.508,
|
| 684 |
"step": 990
|
| 685 |
},
|
| 686 |
{
|
| 687 |
"epoch": 4.02,
|
| 688 |
+
"learning_rate": 0.00014650602409638555,
|
| 689 |
+
"loss": 0.5676,
|
| 690 |
"step": 1000
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 4.02,
|
| 694 |
+
"eval_accuracy": 0.7948717948717948,
|
| 695 |
+
"eval_loss": 0.6542341113090515,
|
| 696 |
+
"eval_runtime": 15.7886,
|
| 697 |
+
"eval_samples_per_second": 44.462,
|
| 698 |
+
"eval_steps_per_second": 5.574,
|
| 699 |
"step": 1000
|
| 700 |
},
|
| 701 |
{
|
| 702 |
"epoch": 4.06,
|
| 703 |
+
"learning_rate": 0.00014597054886211514,
|
| 704 |
+
"loss": 0.5009,
|
| 705 |
"step": 1010
|
| 706 |
},
|
| 707 |
{
|
| 708 |
"epoch": 4.1,
|
| 709 |
+
"learning_rate": 0.00014543507362784473,
|
| 710 |
+
"loss": 0.5297,
|
| 711 |
"step": 1020
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 4.14,
|
| 715 |
+
"learning_rate": 0.0001448995983935743,
|
| 716 |
+
"loss": 0.4541,
|
| 717 |
"step": 1030
|
| 718 |
},
|
| 719 |
{
|
| 720 |
"epoch": 4.18,
|
| 721 |
+
"learning_rate": 0.0001443641231593039,
|
| 722 |
+
"loss": 0.5364,
|
| 723 |
"step": 1040
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 4.22,
|
| 727 |
+
"learning_rate": 0.00014382864792503348,
|
| 728 |
+
"loss": 0.5752,
|
| 729 |
"step": 1050
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 4.26,
|
| 733 |
+
"learning_rate": 0.00014329317269076307,
|
| 734 |
+
"loss": 0.4823,
|
| 735 |
"step": 1060
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 4.3,
|
| 739 |
+
"learning_rate": 0.00014275769745649263,
|
| 740 |
+
"loss": 0.3711,
|
| 741 |
"step": 1070
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 4.34,
|
| 745 |
+
"learning_rate": 0.00014222222222222224,
|
| 746 |
+
"loss": 0.546,
|
| 747 |
"step": 1080
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 4.38,
|
| 751 |
+
"learning_rate": 0.00014168674698795183,
|
| 752 |
+
"loss": 0.5474,
|
| 753 |
"step": 1090
|
| 754 |
},
|
| 755 |
{
|
| 756 |
"epoch": 4.42,
|
| 757 |
+
"learning_rate": 0.00014115127175368138,
|
| 758 |
+
"loss": 0.4784,
|
| 759 |
"step": 1100
|
| 760 |
},
|
| 761 |
{
|
| 762 |
"epoch": 4.42,
|
| 763 |
+
"eval_accuracy": 0.7991452991452992,
|
| 764 |
+
"eval_loss": 0.6610600352287292,
|
| 765 |
+
"eval_runtime": 16.6911,
|
| 766 |
+
"eval_samples_per_second": 42.058,
|
| 767 |
+
"eval_steps_per_second": 5.272,
|
| 768 |
"step": 1100
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 4.46,
|
| 772 |
+
"learning_rate": 0.000140615796519411,
|
| 773 |
+
"loss": 0.3035,
|
| 774 |
"step": 1110
|
| 775 |
},
|
| 776 |
{
|
| 777 |
"epoch": 4.5,
|
| 778 |
+
"learning_rate": 0.00014008032128514058,
|
| 779 |
+
"loss": 0.5735,
|
| 780 |
"step": 1120
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 4.54,
|
| 784 |
+
"learning_rate": 0.00013954484605087014,
|
| 785 |
+
"loss": 0.4467,
|
| 786 |
"step": 1130
|
| 787 |
},
|
| 788 |
{
|
| 789 |
"epoch": 4.58,
|
| 790 |
+
"learning_rate": 0.00013900937081659975,
|
| 791 |
+
"loss": 0.5254,
|
| 792 |
"step": 1140
|
| 793 |
},
|
| 794 |
{
|
| 795 |
"epoch": 4.62,
|
| 796 |
+
"learning_rate": 0.00013847389558232934,
|
| 797 |
+
"loss": 0.5678,
|
| 798 |
"step": 1150
|
| 799 |
},
|
| 800 |
{
|
| 801 |
"epoch": 4.66,
|
| 802 |
+
"learning_rate": 0.0001379384203480589,
|
| 803 |
+
"loss": 0.5742,
|
| 804 |
"step": 1160
|
| 805 |
},
|
| 806 |
{
|
| 807 |
"epoch": 4.7,
|
| 808 |
+
"learning_rate": 0.00013740294511378848,
|
| 809 |
+
"loss": 0.53,
|
| 810 |
"step": 1170
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 4.74,
|
| 814 |
+
"learning_rate": 0.0001368674698795181,
|
| 815 |
+
"loss": 0.4964,
|
| 816 |
"step": 1180
|
| 817 |
},
|
| 818 |
{
|
| 819 |
"epoch": 4.78,
|
| 820 |
+
"learning_rate": 0.00013633199464524765,
|
| 821 |
+
"loss": 0.6265,
|
| 822 |
"step": 1190
|
| 823 |
},
|
| 824 |
{
|
| 825 |
"epoch": 4.82,
|
| 826 |
+
"learning_rate": 0.00013579651941097724,
|
| 827 |
+
"loss": 0.411,
|
| 828 |
"step": 1200
|
| 829 |
},
|
| 830 |
{
|
| 831 |
"epoch": 4.82,
|
| 832 |
+
"eval_accuracy": 0.8076923076923077,
|
| 833 |
+
"eval_loss": 0.5829504728317261,
|
| 834 |
+
"eval_runtime": 15.3709,
|
| 835 |
+
"eval_samples_per_second": 45.671,
|
| 836 |
+
"eval_steps_per_second": 5.725,
|
| 837 |
"step": 1200
|
| 838 |
},
|
| 839 |
{
|
| 840 |
"epoch": 4.86,
|
| 841 |
+
"learning_rate": 0.00013526104417670685,
|
| 842 |
+
"loss": 0.5112,
|
| 843 |
"step": 1210
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 4.9,
|
| 847 |
+
"learning_rate": 0.0001347255689424364,
|
| 848 |
+
"loss": 0.4058,
|
| 849 |
"step": 1220
|
| 850 |
},
|
| 851 |
{
|
| 852 |
"epoch": 4.94,
|
| 853 |
+
"learning_rate": 0.000134190093708166,
|
| 854 |
+
"loss": 0.4561,
|
| 855 |
"step": 1230
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 4.98,
|
| 859 |
+
"learning_rate": 0.0001336546184738956,
|
| 860 |
+
"loss": 0.5612,
|
| 861 |
"step": 1240
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 5.02,
|
| 865 |
+
"learning_rate": 0.00013311914323962517,
|
| 866 |
+
"loss": 0.5281,
|
| 867 |
+
"step": 1250
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 5.06,
|
| 871 |
+
"learning_rate": 0.00013258366800535475,
|
| 872 |
+
"loss": 0.4303,
|
| 873 |
+
"step": 1260
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 5.1,
|
| 877 |
+
"learning_rate": 0.00013204819277108434,
|
| 878 |
+
"loss": 0.5335,
|
| 879 |
+
"step": 1270
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 5.14,
|
| 883 |
+
"learning_rate": 0.00013151271753681393,
|
| 884 |
+
"loss": 0.516,
|
| 885 |
+
"step": 1280
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 5.18,
|
| 889 |
+
"learning_rate": 0.0001309772423025435,
|
| 890 |
+
"loss": 0.3724,
|
| 891 |
+
"step": 1290
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 5.22,
|
| 895 |
+
"learning_rate": 0.0001304417670682731,
|
| 896 |
+
"loss": 0.4021,
|
| 897 |
+
"step": 1300
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 5.22,
|
| 901 |
+
"eval_accuracy": 0.8447293447293447,
|
| 902 |
+
"eval_loss": 0.5220329165458679,
|
| 903 |
+
"eval_runtime": 16.7754,
|
| 904 |
+
"eval_samples_per_second": 41.847,
|
| 905 |
+
"eval_steps_per_second": 5.246,
|
| 906 |
+
"step": 1300
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 5.26,
|
| 910 |
+
"learning_rate": 0.00012990629183400268,
|
| 911 |
+
"loss": 0.3457,
|
| 912 |
+
"step": 1310
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 5.3,
|
| 916 |
+
"learning_rate": 0.00012937081659973227,
|
| 917 |
+
"loss": 0.5637,
|
| 918 |
+
"step": 1320
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 5.34,
|
| 922 |
+
"learning_rate": 0.00012883534136546185,
|
| 923 |
+
"loss": 0.5554,
|
| 924 |
+
"step": 1330
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 5.38,
|
| 928 |
+
"learning_rate": 0.00012829986613119144,
|
| 929 |
+
"loss": 0.4353,
|
| 930 |
+
"step": 1340
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 5.42,
|
| 934 |
+
"learning_rate": 0.00012776439089692102,
|
| 935 |
+
"loss": 0.4007,
|
| 936 |
+
"step": 1350
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 5.46,
|
| 940 |
+
"learning_rate": 0.0001272289156626506,
|
| 941 |
+
"loss": 0.5503,
|
| 942 |
+
"step": 1360
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 5.5,
|
| 946 |
+
"learning_rate": 0.0001266934404283802,
|
| 947 |
+
"loss": 0.4853,
|
| 948 |
+
"step": 1370
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 5.54,
|
| 952 |
+
"learning_rate": 0.00012615796519410978,
|
| 953 |
+
"loss": 0.472,
|
| 954 |
+
"step": 1380
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 5.58,
|
| 958 |
+
"learning_rate": 0.00012562248995983937,
|
| 959 |
+
"loss": 0.3708,
|
| 960 |
+
"step": 1390
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 5.62,
|
| 964 |
+
"learning_rate": 0.00012508701472556895,
|
| 965 |
+
"loss": 0.6442,
|
| 966 |
+
"step": 1400
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 5.62,
|
| 970 |
+
"eval_accuracy": 0.7849002849002849,
|
| 971 |
+
"eval_loss": 0.7221683859825134,
|
| 972 |
+
"eval_runtime": 16.0745,
|
| 973 |
+
"eval_samples_per_second": 43.672,
|
| 974 |
+
"eval_steps_per_second": 5.475,
|
| 975 |
+
"step": 1400
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 5.66,
|
| 979 |
+
"learning_rate": 0.00012455153949129854,
|
| 980 |
+
"loss": 0.5429,
|
| 981 |
+
"step": 1410
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 5.7,
|
| 985 |
+
"learning_rate": 0.00012401606425702812,
|
| 986 |
+
"loss": 0.3282,
|
| 987 |
+
"step": 1420
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 5.74,
|
| 991 |
+
"learning_rate": 0.0001234805890227577,
|
| 992 |
+
"loss": 0.3511,
|
| 993 |
+
"step": 1430
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 5.78,
|
| 997 |
+
"learning_rate": 0.0001229451137884873,
|
| 998 |
+
"loss": 0.4462,
|
| 999 |
+
"step": 1440
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 5.82,
|
| 1003 |
+
"learning_rate": 0.00012240963855421688,
|
| 1004 |
+
"loss": 0.3959,
|
| 1005 |
+
"step": 1450
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 5.86,
|
| 1009 |
+
"learning_rate": 0.00012187416331994645,
|
| 1010 |
+
"loss": 0.4424,
|
| 1011 |
+
"step": 1460
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 5.9,
|
| 1015 |
+
"learning_rate": 0.00012133868808567604,
|
| 1016 |
+
"loss": 0.4374,
|
| 1017 |
+
"step": 1470
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 5.94,
|
| 1021 |
+
"learning_rate": 0.00012080321285140564,
|
| 1022 |
+
"loss": 0.5365,
|
| 1023 |
+
"step": 1480
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 5.98,
|
| 1027 |
+
"learning_rate": 0.00012026773761713521,
|
| 1028 |
+
"loss": 0.4206,
|
| 1029 |
+
"step": 1490
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 6.02,
|
| 1033 |
+
"learning_rate": 0.0001197322623828648,
|
| 1034 |
+
"loss": 0.4539,
|
| 1035 |
+
"step": 1500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 6.02,
|
| 1039 |
+
"eval_accuracy": 0.8347578347578347,
|
| 1040 |
+
"eval_loss": 0.5616238117218018,
|
| 1041 |
+
"eval_runtime": 15.9222,
|
| 1042 |
+
"eval_samples_per_second": 44.089,
|
| 1043 |
+
"eval_steps_per_second": 5.527,
|
| 1044 |
+
"step": 1500
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 6.06,
|
| 1048 |
+
"learning_rate": 0.0001191967871485944,
|
| 1049 |
+
"loss": 0.3495,
|
| 1050 |
+
"step": 1510
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 6.1,
|
| 1054 |
+
"learning_rate": 0.00011866131191432397,
|
| 1055 |
+
"loss": 0.4073,
|
| 1056 |
+
"step": 1520
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 6.14,
|
| 1060 |
+
"learning_rate": 0.00011812583668005355,
|
| 1061 |
+
"loss": 0.4443,
|
| 1062 |
+
"step": 1530
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 6.18,
|
| 1066 |
+
"learning_rate": 0.00011759036144578315,
|
| 1067 |
+
"loss": 0.4943,
|
| 1068 |
+
"step": 1540
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 6.22,
|
| 1072 |
+
"learning_rate": 0.00011705488621151272,
|
| 1073 |
+
"loss": 0.3544,
|
| 1074 |
+
"step": 1550
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 6.27,
|
| 1078 |
+
"learning_rate": 0.00011651941097724231,
|
| 1079 |
+
"loss": 0.3664,
|
| 1080 |
+
"step": 1560
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 6.31,
|
| 1084 |
+
"learning_rate": 0.00011598393574297188,
|
| 1085 |
+
"loss": 0.3431,
|
| 1086 |
+
"step": 1570
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 6.35,
|
| 1090 |
+
"learning_rate": 0.00011544846050870148,
|
| 1091 |
+
"loss": 0.4448,
|
| 1092 |
+
"step": 1580
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 6.39,
|
| 1096 |
+
"learning_rate": 0.00011491298527443107,
|
| 1097 |
+
"loss": 0.3958,
|
| 1098 |
+
"step": 1590
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 6.43,
|
| 1102 |
+
"learning_rate": 0.00011437751004016064,
|
| 1103 |
+
"loss": 0.4256,
|
| 1104 |
+
"step": 1600
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 6.43,
|
| 1108 |
+
"eval_accuracy": 0.801994301994302,
|
| 1109 |
+
"eval_loss": 0.6621670722961426,
|
| 1110 |
+
"eval_runtime": 16.4993,
|
| 1111 |
+
"eval_samples_per_second": 42.547,
|
| 1112 |
+
"eval_steps_per_second": 5.334,
|
| 1113 |
+
"step": 1600
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 6.47,
|
| 1117 |
+
"learning_rate": 0.00011384203480589024,
|
| 1118 |
+
"loss": 0.4149,
|
| 1119 |
+
"step": 1610
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 6.51,
|
| 1123 |
+
"learning_rate": 0.00011330655957161982,
|
| 1124 |
+
"loss": 0.3562,
|
| 1125 |
+
"step": 1620
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 6.55,
|
| 1129 |
+
"learning_rate": 0.0001127710843373494,
|
| 1130 |
+
"loss": 0.4423,
|
| 1131 |
+
"step": 1630
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 6.59,
|
| 1135 |
+
"learning_rate": 0.000112235609103079,
|
| 1136 |
+
"loss": 0.5026,
|
| 1137 |
+
"step": 1640
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 6.63,
|
| 1141 |
+
"learning_rate": 0.00011170013386880858,
|
| 1142 |
+
"loss": 0.4306,
|
| 1143 |
+
"step": 1650
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 6.67,
|
| 1147 |
+
"learning_rate": 0.00011116465863453815,
|
| 1148 |
+
"loss": 0.3413,
|
| 1149 |
+
"step": 1660
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 6.71,
|
| 1153 |
+
"learning_rate": 0.00011062918340026774,
|
| 1154 |
+
"loss": 0.3856,
|
| 1155 |
+
"step": 1670
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 6.75,
|
| 1159 |
+
"learning_rate": 0.00011009370816599734,
|
| 1160 |
+
"loss": 0.441,
|
| 1161 |
+
"step": 1680
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 6.79,
|
| 1165 |
+
"learning_rate": 0.00010955823293172691,
|
| 1166 |
+
"loss": 0.3613,
|
| 1167 |
+
"step": 1690
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 6.83,
|
| 1171 |
+
"learning_rate": 0.0001090227576974565,
|
| 1172 |
+
"loss": 0.2839,
|
| 1173 |
+
"step": 1700
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 6.83,
|
| 1177 |
+
"eval_accuracy": 0.8262108262108262,
|
| 1178 |
+
"eval_loss": 0.6048392057418823,
|
| 1179 |
+
"eval_runtime": 16.0148,
|
| 1180 |
+
"eval_samples_per_second": 43.835,
|
| 1181 |
+
"eval_steps_per_second": 5.495,
|
| 1182 |
+
"step": 1700
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 6.87,
|
| 1186 |
+
"learning_rate": 0.0001084872824631861,
|
| 1187 |
+
"loss": 0.4067,
|
| 1188 |
+
"step": 1710
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 6.91,
|
| 1192 |
+
"learning_rate": 0.00010795180722891567,
|
| 1193 |
+
"loss": 0.4729,
|
| 1194 |
+
"step": 1720
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 6.95,
|
| 1198 |
+
"learning_rate": 0.00010741633199464525,
|
| 1199 |
+
"loss": 0.414,
|
| 1200 |
+
"step": 1730
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 6.99,
|
| 1204 |
+
"learning_rate": 0.00010688085676037485,
|
| 1205 |
+
"loss": 0.3331,
|
| 1206 |
+
"step": 1740
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 7.03,
|
| 1210 |
+
"learning_rate": 0.00010634538152610442,
|
| 1211 |
+
"loss": 0.3609,
|
| 1212 |
+
"step": 1750
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 7.07,
|
| 1216 |
+
"learning_rate": 0.00010580990629183401,
|
| 1217 |
+
"loss": 0.344,
|
| 1218 |
+
"step": 1760
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 7.11,
|
| 1222 |
+
"learning_rate": 0.00010527443105756358,
|
| 1223 |
+
"loss": 0.2764,
|
| 1224 |
+
"step": 1770
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 7.15,
|
| 1228 |
+
"learning_rate": 0.00010473895582329318,
|
| 1229 |
+
"loss": 0.3016,
|
| 1230 |
+
"step": 1780
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 7.19,
|
| 1234 |
+
"learning_rate": 0.00010420348058902277,
|
| 1235 |
+
"loss": 0.3246,
|
| 1236 |
+
"step": 1790
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 7.23,
|
| 1240 |
+
"learning_rate": 0.00010366800535475234,
|
| 1241 |
+
"loss": 0.4236,
|
| 1242 |
+
"step": 1800
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 7.23,
|
| 1246 |
+
"eval_accuracy": 0.8262108262108262,
|
| 1247 |
+
"eval_loss": 0.5745150446891785,
|
| 1248 |
+
"eval_runtime": 16.5747,
|
| 1249 |
+
"eval_samples_per_second": 42.354,
|
| 1250 |
+
"eval_steps_per_second": 5.309,
|
| 1251 |
+
"step": 1800
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 7.27,
|
| 1255 |
+
"learning_rate": 0.00010313253012048194,
|
| 1256 |
+
"loss": 0.2888,
|
| 1257 |
+
"step": 1810
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 7.31,
|
| 1261 |
+
"learning_rate": 0.00010259705488621152,
|
| 1262 |
+
"loss": 0.3958,
|
| 1263 |
+
"step": 1820
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 7.35,
|
| 1267 |
+
"learning_rate": 0.0001020615796519411,
|
| 1268 |
+
"loss": 0.4288,
|
| 1269 |
+
"step": 1830
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 7.39,
|
| 1273 |
+
"learning_rate": 0.0001015261044176707,
|
| 1274 |
+
"loss": 0.3465,
|
| 1275 |
+
"step": 1840
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 7.43,
|
| 1279 |
+
"learning_rate": 0.00010099062918340028,
|
| 1280 |
+
"loss": 0.4222,
|
| 1281 |
+
"step": 1850
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 7.47,
|
| 1285 |
+
"learning_rate": 0.00010045515394912985,
|
| 1286 |
+
"loss": 0.2903,
|
| 1287 |
+
"step": 1860
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 7.51,
|
| 1291 |
+
"learning_rate": 9.991967871485944e-05,
|
| 1292 |
+
"loss": 0.4449,
|
| 1293 |
+
"step": 1870
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 7.55,
|
| 1297 |
+
"learning_rate": 9.938420348058902e-05,
|
| 1298 |
+
"loss": 0.2636,
|
| 1299 |
+
"step": 1880
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 7.59,
|
| 1303 |
+
"learning_rate": 9.884872824631861e-05,
|
| 1304 |
+
"loss": 0.2312,
|
| 1305 |
+
"step": 1890
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 7.63,
|
| 1309 |
+
"learning_rate": 9.831325301204821e-05,
|
| 1310 |
+
"loss": 0.3371,
|
| 1311 |
+
"step": 1900
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 7.63,
|
| 1315 |
+
"eval_accuracy": 0.8447293447293447,
|
| 1316 |
+
"eval_loss": 0.5557853579521179,
|
| 1317 |
+
"eval_runtime": 15.8613,
|
| 1318 |
+
"eval_samples_per_second": 44.259,
|
| 1319 |
+
"eval_steps_per_second": 5.548,
|
| 1320 |
+
"step": 1900
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 7.67,
|
| 1324 |
+
"learning_rate": 9.777777777777778e-05,
|
| 1325 |
+
"loss": 0.3054,
|
| 1326 |
+
"step": 1910
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 7.71,
|
| 1330 |
+
"learning_rate": 9.724230254350737e-05,
|
| 1331 |
+
"loss": 0.2751,
|
| 1332 |
+
"step": 1920
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 7.75,
|
| 1336 |
+
"learning_rate": 9.670682730923695e-05,
|
| 1337 |
+
"loss": 0.292,
|
| 1338 |
+
"step": 1930
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 7.79,
|
| 1342 |
+
"learning_rate": 9.617135207496654e-05,
|
| 1343 |
+
"loss": 0.3959,
|
| 1344 |
+
"step": 1940
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 7.83,
|
| 1348 |
+
"learning_rate": 9.563587684069612e-05,
|
| 1349 |
+
"loss": 0.3317,
|
| 1350 |
+
"step": 1950
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 7.87,
|
| 1354 |
+
"learning_rate": 9.510040160642571e-05,
|
| 1355 |
+
"loss": 0.3576,
|
| 1356 |
+
"step": 1960
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 7.91,
|
| 1360 |
+
"learning_rate": 9.45649263721553e-05,
|
| 1361 |
+
"loss": 0.2761,
|
| 1362 |
+
"step": 1970
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 7.95,
|
| 1366 |
+
"learning_rate": 9.402945113788487e-05,
|
| 1367 |
+
"loss": 0.3616,
|
| 1368 |
+
"step": 1980
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 7.99,
|
| 1372 |
+
"learning_rate": 9.349397590361446e-05,
|
| 1373 |
+
"loss": 0.3875,
|
| 1374 |
+
"step": 1990
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 8.03,
|
| 1378 |
+
"learning_rate": 9.295850066934405e-05,
|
| 1379 |
+
"loss": 0.2564,
|
| 1380 |
+
"step": 2000
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 8.03,
|
| 1384 |
+
"eval_accuracy": 0.8376068376068376,
|
| 1385 |
+
"eval_loss": 0.5993377566337585,
|
| 1386 |
+
"eval_runtime": 15.9305,
|
| 1387 |
+
"eval_samples_per_second": 44.066,
|
| 1388 |
+
"eval_steps_per_second": 5.524,
|
| 1389 |
+
"step": 2000
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 8.07,
|
| 1393 |
+
"learning_rate": 9.242302543507362e-05,
|
| 1394 |
+
"loss": 0.264,
|
| 1395 |
+
"step": 2010
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 8.11,
|
| 1399 |
+
"learning_rate": 9.188755020080322e-05,
|
| 1400 |
+
"loss": 0.2075,
|
| 1401 |
+
"step": 2020
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 8.15,
|
| 1405 |
+
"learning_rate": 9.13520749665328e-05,
|
| 1406 |
+
"loss": 0.1795,
|
| 1407 |
+
"step": 2030
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 8.19,
|
| 1411 |
+
"learning_rate": 9.081659973226239e-05,
|
| 1412 |
+
"loss": 0.3475,
|
| 1413 |
+
"step": 2040
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 8.23,
|
| 1417 |
+
"learning_rate": 9.028112449799198e-05,
|
| 1418 |
+
"loss": 0.386,
|
| 1419 |
+
"step": 2050
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 8.27,
|
| 1423 |
+
"learning_rate": 8.974564926372155e-05,
|
| 1424 |
+
"loss": 0.4569,
|
| 1425 |
+
"step": 2060
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 8.31,
|
| 1429 |
+
"learning_rate": 8.921017402945115e-05,
|
| 1430 |
+
"loss": 0.2956,
|
| 1431 |
+
"step": 2070
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 8.35,
|
| 1435 |
+
"learning_rate": 8.867469879518072e-05,
|
| 1436 |
+
"loss": 0.2071,
|
| 1437 |
+
"step": 2080
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 8.39,
|
| 1441 |
+
"learning_rate": 8.813922356091031e-05,
|
| 1442 |
+
"loss": 0.2673,
|
| 1443 |
+
"step": 2090
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 8.43,
|
| 1447 |
+
"learning_rate": 8.760374832663991e-05,
|
| 1448 |
+
"loss": 0.2802,
|
| 1449 |
+
"step": 2100
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 8.43,
|
| 1453 |
+
"eval_accuracy": 0.8589743589743589,
|
| 1454 |
+
"eval_loss": 0.5201694965362549,
|
| 1455 |
+
"eval_runtime": 16.9693,
|
| 1456 |
+
"eval_samples_per_second": 41.369,
|
| 1457 |
+
"eval_steps_per_second": 5.186,
|
| 1458 |
+
"step": 2100
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 8.47,
|
| 1462 |
+
"learning_rate": 8.706827309236948e-05,
|
| 1463 |
+
"loss": 0.4448,
|
| 1464 |
+
"step": 2110
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 8.51,
|
| 1468 |
+
"learning_rate": 8.653279785809906e-05,
|
| 1469 |
+
"loss": 0.3018,
|
| 1470 |
+
"step": 2120
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 8.55,
|
| 1474 |
+
"learning_rate": 8.599732262382865e-05,
|
| 1475 |
+
"loss": 0.4112,
|
| 1476 |
+
"step": 2130
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 8.59,
|
| 1480 |
+
"learning_rate": 8.546184738955824e-05,
|
| 1481 |
+
"loss": 0.3,
|
| 1482 |
+
"step": 2140
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 8.63,
|
| 1486 |
+
"learning_rate": 8.492637215528782e-05,
|
| 1487 |
+
"loss": 0.2328,
|
| 1488 |
+
"step": 2150
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 8.67,
|
| 1492 |
+
"learning_rate": 8.439089692101741e-05,
|
| 1493 |
+
"loss": 0.3432,
|
| 1494 |
+
"step": 2160
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 8.71,
|
| 1498 |
+
"learning_rate": 8.385542168674699e-05,
|
| 1499 |
+
"loss": 0.2498,
|
| 1500 |
+
"step": 2170
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 8.76,
|
| 1504 |
+
"learning_rate": 8.331994645247658e-05,
|
| 1505 |
+
"loss": 0.3595,
|
| 1506 |
+
"step": 2180
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 8.8,
|
| 1510 |
+
"learning_rate": 8.278447121820616e-05,
|
| 1511 |
+
"loss": 0.3939,
|
| 1512 |
+
"step": 2190
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 8.84,
|
| 1516 |
+
"learning_rate": 8.224899598393575e-05,
|
| 1517 |
+
"loss": 0.2938,
|
| 1518 |
+
"step": 2200
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 8.84,
|
| 1522 |
+
"eval_accuracy": 0.8176638176638177,
|
| 1523 |
+
"eval_loss": 0.619129478931427,
|
| 1524 |
+
"eval_runtime": 17.7657,
|
| 1525 |
+
"eval_samples_per_second": 39.514,
|
| 1526 |
+
"eval_steps_per_second": 4.953,
|
| 1527 |
+
"step": 2200
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 8.88,
|
| 1531 |
+
"learning_rate": 8.171352074966534e-05,
|
| 1532 |
+
"loss": 0.3719,
|
| 1533 |
+
"step": 2210
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 8.92,
|
| 1537 |
+
"learning_rate": 8.117804551539492e-05,
|
| 1538 |
+
"loss": 0.3056,
|
| 1539 |
+
"step": 2220
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 8.96,
|
| 1543 |
+
"learning_rate": 8.064257028112449e-05,
|
| 1544 |
+
"loss": 0.4149,
|
| 1545 |
+
"step": 2230
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 9.0,
|
| 1549 |
+
"learning_rate": 8.010709504685409e-05,
|
| 1550 |
+
"loss": 0.3413,
|
| 1551 |
+
"step": 2240
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 9.04,
|
| 1555 |
+
"learning_rate": 7.957161981258368e-05,
|
| 1556 |
+
"loss": 0.2569,
|
| 1557 |
+
"step": 2250
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 9.08,
|
| 1561 |
+
"learning_rate": 7.903614457831325e-05,
|
| 1562 |
+
"loss": 0.3128,
|
| 1563 |
+
"step": 2260
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 9.12,
|
| 1567 |
+
"learning_rate": 7.850066934404285e-05,
|
| 1568 |
+
"loss": 0.2906,
|
| 1569 |
+
"step": 2270
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 9.16,
|
| 1573 |
+
"learning_rate": 7.796519410977242e-05,
|
| 1574 |
+
"loss": 0.233,
|
| 1575 |
+
"step": 2280
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 9.2,
|
| 1579 |
+
"learning_rate": 7.7429718875502e-05,
|
| 1580 |
+
"loss": 0.3216,
|
| 1581 |
+
"step": 2290
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 9.24,
|
| 1585 |
+
"learning_rate": 7.68942436412316e-05,
|
| 1586 |
+
"loss": 0.2777,
|
| 1587 |
+
"step": 2300
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 9.24,
|
| 1591 |
+
"eval_accuracy": 0.8504273504273504,
|
| 1592 |
+
"eval_loss": 0.5119191408157349,
|
| 1593 |
+
"eval_runtime": 16.0458,
|
| 1594 |
+
"eval_samples_per_second": 43.75,
|
| 1595 |
+
"eval_steps_per_second": 5.484,
|
| 1596 |
+
"step": 2300
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 9.28,
|
| 1600 |
+
"learning_rate": 7.635876840696118e-05,
|
| 1601 |
+
"loss": 0.1969,
|
| 1602 |
+
"step": 2310
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 9.32,
|
| 1606 |
+
"learning_rate": 7.582329317269076e-05,
|
| 1607 |
+
"loss": 0.185,
|
| 1608 |
+
"step": 2320
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 9.36,
|
| 1612 |
+
"learning_rate": 7.528781793842035e-05,
|
| 1613 |
+
"loss": 0.1591,
|
| 1614 |
+
"step": 2330
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 9.4,
|
| 1618 |
+
"learning_rate": 7.475234270414993e-05,
|
| 1619 |
+
"loss": 0.2421,
|
| 1620 |
+
"step": 2340
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 9.44,
|
| 1624 |
+
"learning_rate": 7.421686746987952e-05,
|
| 1625 |
+
"loss": 0.1847,
|
| 1626 |
+
"step": 2350
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 9.48,
|
| 1630 |
+
"learning_rate": 7.36813922356091e-05,
|
| 1631 |
+
"loss": 0.2552,
|
| 1632 |
+
"step": 2360
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 9.52,
|
| 1636 |
+
"learning_rate": 7.314591700133869e-05,
|
| 1637 |
+
"loss": 0.2998,
|
| 1638 |
+
"step": 2370
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 9.56,
|
| 1642 |
+
"learning_rate": 7.261044176706828e-05,
|
| 1643 |
+
"loss": 0.1865,
|
| 1644 |
+
"step": 2380
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 9.6,
|
| 1648 |
+
"learning_rate": 7.207496653279786e-05,
|
| 1649 |
+
"loss": 0.2479,
|
| 1650 |
+
"step": 2390
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 9.64,
|
| 1654 |
+
"learning_rate": 7.153949129852745e-05,
|
| 1655 |
+
"loss": 0.1851,
|
| 1656 |
+
"step": 2400
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 9.64,
|
| 1660 |
+
"eval_accuracy": 0.8547008547008547,
|
| 1661 |
+
"eval_loss": 0.5540783405303955,
|
| 1662 |
+
"eval_runtime": 16.572,
|
| 1663 |
+
"eval_samples_per_second": 42.361,
|
| 1664 |
+
"eval_steps_per_second": 5.31,
|
| 1665 |
+
"step": 2400
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 9.68,
|
| 1669 |
+
"learning_rate": 7.100401606425703e-05,
|
| 1670 |
+
"loss": 0.2578,
|
| 1671 |
+
"step": 2410
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 9.72,
|
| 1675 |
+
"learning_rate": 7.046854082998662e-05,
|
| 1676 |
+
"loss": 0.365,
|
| 1677 |
+
"step": 2420
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 9.76,
|
| 1681 |
+
"learning_rate": 6.993306559571619e-05,
|
| 1682 |
+
"loss": 0.3247,
|
| 1683 |
+
"step": 2430
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 9.8,
|
| 1687 |
+
"learning_rate": 6.939759036144579e-05,
|
| 1688 |
+
"loss": 0.3411,
|
| 1689 |
+
"step": 2440
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 9.84,
|
| 1693 |
+
"learning_rate": 6.886211512717538e-05,
|
| 1694 |
+
"loss": 0.3435,
|
| 1695 |
+
"step": 2450
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 9.88,
|
| 1699 |
+
"learning_rate": 6.832663989290495e-05,
|
| 1700 |
+
"loss": 0.2834,
|
| 1701 |
+
"step": 2460
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 9.92,
|
| 1705 |
+
"learning_rate": 6.779116465863455e-05,
|
| 1706 |
+
"loss": 0.2982,
|
| 1707 |
+
"step": 2470
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 9.96,
|
| 1711 |
+
"learning_rate": 6.725568942436412e-05,
|
| 1712 |
+
"loss": 0.4454,
|
| 1713 |
+
"step": 2480
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 10.0,
|
| 1717 |
+
"learning_rate": 6.67202141900937e-05,
|
| 1718 |
+
"loss": 0.3108,
|
| 1719 |
+
"step": 2490
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 10.04,
|
| 1723 |
+
"learning_rate": 6.61847389558233e-05,
|
| 1724 |
+
"loss": 0.2274,
|
| 1725 |
+
"step": 2500
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 10.04,
|
| 1729 |
+
"eval_accuracy": 0.8433048433048433,
|
| 1730 |
+
"eval_loss": 0.5599452257156372,
|
| 1731 |
+
"eval_runtime": 15.5521,
|
| 1732 |
+
"eval_samples_per_second": 45.138,
|
| 1733 |
+
"eval_steps_per_second": 5.658,
|
| 1734 |
+
"step": 2500
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 10.08,
|
| 1738 |
+
"learning_rate": 6.564926372155288e-05,
|
| 1739 |
+
"loss": 0.2869,
|
| 1740 |
+
"step": 2510
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 10.12,
|
| 1744 |
+
"learning_rate": 6.511378848728246e-05,
|
| 1745 |
+
"loss": 0.2677,
|
| 1746 |
+
"step": 2520
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 10.16,
|
| 1750 |
+
"learning_rate": 6.457831325301205e-05,
|
| 1751 |
+
"loss": 0.3096,
|
| 1752 |
+
"step": 2530
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 10.2,
|
| 1756 |
+
"learning_rate": 6.404283801874163e-05,
|
| 1757 |
+
"loss": 0.3939,
|
| 1758 |
+
"step": 2540
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 10.24,
|
| 1762 |
+
"learning_rate": 6.350736278447122e-05,
|
| 1763 |
+
"loss": 0.3081,
|
| 1764 |
+
"step": 2550
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 10.28,
|
| 1768 |
+
"learning_rate": 6.29718875502008e-05,
|
| 1769 |
+
"loss": 0.2795,
|
| 1770 |
+
"step": 2560
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 10.32,
|
| 1774 |
+
"learning_rate": 6.243641231593039e-05,
|
| 1775 |
+
"loss": 0.2558,
|
| 1776 |
+
"step": 2570
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 10.36,
|
| 1780 |
+
"learning_rate": 6.190093708165998e-05,
|
| 1781 |
+
"loss": 0.3104,
|
| 1782 |
+
"step": 2580
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 10.4,
|
| 1786 |
+
"learning_rate": 6.136546184738956e-05,
|
| 1787 |
+
"loss": 0.3196,
|
| 1788 |
+
"step": 2590
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 10.44,
|
| 1792 |
+
"learning_rate": 6.082998661311915e-05,
|
| 1793 |
+
"loss": 0.3051,
|
| 1794 |
+
"step": 2600
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 10.44,
|
| 1798 |
+
"eval_accuracy": 0.8504273504273504,
|
| 1799 |
+
"eval_loss": 0.5281407237052917,
|
| 1800 |
+
"eval_runtime": 15.978,
|
| 1801 |
+
"eval_samples_per_second": 43.935,
|
| 1802 |
+
"eval_steps_per_second": 5.508,
|
| 1803 |
+
"step": 2600
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 10.48,
|
| 1807 |
+
"learning_rate": 6.029451137884873e-05,
|
| 1808 |
+
"loss": 0.2053,
|
| 1809 |
+
"step": 2610
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 10.52,
|
| 1813 |
+
"learning_rate": 5.975903614457832e-05,
|
| 1814 |
+
"loss": 0.2982,
|
| 1815 |
+
"step": 2620
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 10.56,
|
| 1819 |
+
"learning_rate": 5.92235609103079e-05,
|
| 1820 |
+
"loss": 0.2457,
|
| 1821 |
+
"step": 2630
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 10.6,
|
| 1825 |
+
"learning_rate": 5.8741633199464526e-05,
|
| 1826 |
+
"loss": 0.1915,
|
| 1827 |
+
"step": 2640
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 10.64,
|
| 1831 |
+
"learning_rate": 5.8206157965194105e-05,
|
| 1832 |
+
"loss": 0.2598,
|
| 1833 |
+
"step": 2650
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 10.68,
|
| 1837 |
+
"learning_rate": 5.76706827309237e-05,
|
| 1838 |
+
"loss": 0.2896,
|
| 1839 |
+
"step": 2660
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 10.72,
|
| 1843 |
+
"learning_rate": 5.713520749665329e-05,
|
| 1844 |
+
"loss": 0.1819,
|
| 1845 |
+
"step": 2670
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 10.76,
|
| 1849 |
+
"learning_rate": 5.659973226238286e-05,
|
| 1850 |
+
"loss": 0.353,
|
| 1851 |
+
"step": 2680
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 10.8,
|
| 1855 |
+
"learning_rate": 5.6064257028112455e-05,
|
| 1856 |
+
"loss": 0.307,
|
| 1857 |
+
"step": 2690
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 10.84,
|
| 1861 |
+
"learning_rate": 5.5528781793842033e-05,
|
| 1862 |
+
"loss": 0.2368,
|
| 1863 |
+
"step": 2700
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 10.84,
|
| 1867 |
+
"eval_accuracy": 0.8646723646723646,
|
| 1868 |
+
"eval_loss": 0.5055693984031677,
|
| 1869 |
+
"eval_runtime": 16.6514,
|
| 1870 |
+
"eval_samples_per_second": 42.159,
|
| 1871 |
+
"eval_steps_per_second": 5.285,
|
| 1872 |
+
"step": 2700
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 10.88,
|
| 1876 |
+
"learning_rate": 5.499330655957162e-05,
|
| 1877 |
+
"loss": 0.2823,
|
| 1878 |
+
"step": 2710
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 10.92,
|
| 1882 |
+
"learning_rate": 5.445783132530121e-05,
|
| 1883 |
+
"loss": 0.1548,
|
| 1884 |
+
"step": 2720
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 10.96,
|
| 1888 |
+
"learning_rate": 5.392235609103079e-05,
|
| 1889 |
+
"loss": 0.2435,
|
| 1890 |
+
"step": 2730
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 11.0,
|
| 1894 |
+
"learning_rate": 5.338688085676038e-05,
|
| 1895 |
+
"loss": 0.2424,
|
| 1896 |
+
"step": 2740
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 11.04,
|
| 1900 |
+
"learning_rate": 5.2851405622489955e-05,
|
| 1901 |
+
"loss": 0.2384,
|
| 1902 |
+
"step": 2750
|
| 1903 |
+
},
|
| 1904 |
+
{
|
| 1905 |
+
"epoch": 11.08,
|
| 1906 |
+
"learning_rate": 5.231593038821955e-05,
|
| 1907 |
+
"loss": 0.278,
|
| 1908 |
+
"step": 2760
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 11.12,
|
| 1912 |
+
"learning_rate": 5.178045515394914e-05,
|
| 1913 |
+
"loss": 0.2402,
|
| 1914 |
+
"step": 2770
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 11.16,
|
| 1918 |
+
"learning_rate": 5.124497991967871e-05,
|
| 1919 |
+
"loss": 0.1498,
|
| 1920 |
+
"step": 2780
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 11.2,
|
| 1924 |
+
"learning_rate": 5.0709504685408304e-05,
|
| 1925 |
+
"loss": 0.217,
|
| 1926 |
+
"step": 2790
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 11.24,
|
| 1930 |
+
"learning_rate": 5.017402945113788e-05,
|
| 1931 |
+
"loss": 0.2029,
|
| 1932 |
+
"step": 2800
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 11.24,
|
| 1936 |
+
"eval_accuracy": 0.8390313390313391,
|
| 1937 |
+
"eval_loss": 0.5582476854324341,
|
| 1938 |
+
"eval_runtime": 17.4878,
|
| 1939 |
+
"eval_samples_per_second": 40.142,
|
| 1940 |
+
"eval_steps_per_second": 5.032,
|
| 1941 |
+
"step": 2800
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 11.29,
|
| 1945 |
+
"learning_rate": 4.9638554216867475e-05,
|
| 1946 |
+
"loss": 0.2471,
|
| 1947 |
+
"step": 2810
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 11.33,
|
| 1951 |
+
"learning_rate": 4.9103078982597054e-05,
|
| 1952 |
+
"loss": 0.2972,
|
| 1953 |
+
"step": 2820
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 11.37,
|
| 1957 |
+
"learning_rate": 4.856760374832664e-05,
|
| 1958 |
+
"loss": 0.2014,
|
| 1959 |
+
"step": 2830
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 11.41,
|
| 1963 |
+
"learning_rate": 4.803212851405623e-05,
|
| 1964 |
+
"loss": 0.142,
|
| 1965 |
+
"step": 2840
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 11.45,
|
| 1969 |
+
"learning_rate": 4.749665327978581e-05,
|
| 1970 |
+
"loss": 0.3213,
|
| 1971 |
+
"step": 2850
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 11.49,
|
| 1975 |
+
"learning_rate": 4.69611780455154e-05,
|
| 1976 |
+
"loss": 0.2315,
|
| 1977 |
+
"step": 2860
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 11.53,
|
| 1981 |
+
"learning_rate": 4.642570281124498e-05,
|
| 1982 |
+
"loss": 0.2014,
|
| 1983 |
+
"step": 2870
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 11.57,
|
| 1987 |
+
"learning_rate": 4.589022757697457e-05,
|
| 1988 |
+
"loss": 0.3035,
|
| 1989 |
+
"step": 2880
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 11.61,
|
| 1993 |
+
"learning_rate": 4.5354752342704154e-05,
|
| 1994 |
+
"loss": 0.1635,
|
| 1995 |
+
"step": 2890
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 11.65,
|
| 1999 |
+
"learning_rate": 4.481927710843374e-05,
|
| 2000 |
+
"loss": 0.1971,
|
| 2001 |
+
"step": 2900
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 11.65,
|
| 2005 |
+
"eval_accuracy": 0.8433048433048433,
|
| 2006 |
+
"eval_loss": 0.5440123677253723,
|
| 2007 |
+
"eval_runtime": 16.1487,
|
| 2008 |
+
"eval_samples_per_second": 43.471,
|
| 2009 |
+
"eval_steps_per_second": 5.449,
|
| 2010 |
+
"step": 2900
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 11.69,
|
| 2014 |
+
"learning_rate": 4.4283801874163325e-05,
|
| 2015 |
+
"loss": 0.2525,
|
| 2016 |
+
"step": 2910
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 11.73,
|
| 2020 |
+
"learning_rate": 4.3748326639892904e-05,
|
| 2021 |
+
"loss": 0.2254,
|
| 2022 |
+
"step": 2920
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 11.77,
|
| 2026 |
+
"learning_rate": 4.321285140562249e-05,
|
| 2027 |
+
"loss": 0.1619,
|
| 2028 |
+
"step": 2930
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 11.81,
|
| 2032 |
+
"learning_rate": 4.267737617135208e-05,
|
| 2033 |
+
"loss": 0.2398,
|
| 2034 |
+
"step": 2940
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 11.85,
|
| 2038 |
+
"learning_rate": 4.214190093708166e-05,
|
| 2039 |
+
"loss": 0.2213,
|
| 2040 |
+
"step": 2950
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 11.89,
|
| 2044 |
+
"learning_rate": 4.1606425702811246e-05,
|
| 2045 |
+
"loss": 0.1775,
|
| 2046 |
+
"step": 2960
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 11.93,
|
| 2050 |
+
"learning_rate": 4.107095046854083e-05,
|
| 2051 |
+
"loss": 0.2309,
|
| 2052 |
+
"step": 2970
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 11.97,
|
| 2056 |
+
"learning_rate": 4.053547523427042e-05,
|
| 2057 |
+
"loss": 0.1681,
|
| 2058 |
+
"step": 2980
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 12.01,
|
| 2062 |
+
"learning_rate": 4e-05,
|
| 2063 |
+
"loss": 0.3173,
|
| 2064 |
+
"step": 2990
|
| 2065 |
+
},
|
| 2066 |
+
{
|
| 2067 |
+
"epoch": 12.05,
|
| 2068 |
+
"learning_rate": 3.946452476572959e-05,
|
| 2069 |
+
"loss": 0.2014,
|
| 2070 |
+
"step": 3000
|
| 2071 |
+
},
|
| 2072 |
+
{
|
| 2073 |
+
"epoch": 12.05,
|
| 2074 |
+
"eval_accuracy": 0.8618233618233618,
|
| 2075 |
+
"eval_loss": 0.5087952017784119,
|
| 2076 |
+
"eval_runtime": 15.8505,
|
| 2077 |
+
"eval_samples_per_second": 44.289,
|
| 2078 |
+
"eval_steps_per_second": 5.552,
|
| 2079 |
+
"step": 3000
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 12.09,
|
| 2083 |
+
"learning_rate": 3.8929049531459175e-05,
|
| 2084 |
+
"loss": 0.1908,
|
| 2085 |
+
"step": 3010
|
| 2086 |
+
},
|
| 2087 |
+
{
|
| 2088 |
+
"epoch": 12.13,
|
| 2089 |
+
"learning_rate": 3.8393574297188753e-05,
|
| 2090 |
+
"loss": 0.1207,
|
| 2091 |
+
"step": 3020
|
| 2092 |
+
},
|
| 2093 |
+
{
|
| 2094 |
+
"epoch": 12.17,
|
| 2095 |
+
"learning_rate": 3.785809906291834e-05,
|
| 2096 |
+
"loss": 0.2251,
|
| 2097 |
+
"step": 3030
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 12.21,
|
| 2101 |
+
"learning_rate": 3.732262382864793e-05,
|
| 2102 |
+
"loss": 0.1701,
|
| 2103 |
+
"step": 3040
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 12.25,
|
| 2107 |
+
"learning_rate": 3.678714859437751e-05,
|
| 2108 |
+
"loss": 0.1692,
|
| 2109 |
+
"step": 3050
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 12.29,
|
| 2113 |
+
"learning_rate": 3.6251673360107096e-05,
|
| 2114 |
+
"loss": 0.1648,
|
| 2115 |
+
"step": 3060
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 12.33,
|
| 2119 |
+
"learning_rate": 3.571619812583668e-05,
|
| 2120 |
+
"loss": 0.1305,
|
| 2121 |
+
"step": 3070
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 12.37,
|
| 2125 |
+
"learning_rate": 3.518072289156627e-05,
|
| 2126 |
+
"loss": 0.2228,
|
| 2127 |
+
"step": 3080
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 12.41,
|
| 2131 |
+
"learning_rate": 3.464524765729585e-05,
|
| 2132 |
+
"loss": 0.1924,
|
| 2133 |
+
"step": 3090
|
| 2134 |
+
},
|
| 2135 |
+
{
|
| 2136 |
+
"epoch": 12.45,
|
| 2137 |
+
"learning_rate": 3.410977242302544e-05,
|
| 2138 |
+
"loss": 0.1458,
|
| 2139 |
+
"step": 3100
|
| 2140 |
+
},
|
| 2141 |
+
{
|
| 2142 |
+
"epoch": 12.45,
|
| 2143 |
+
"eval_accuracy": 0.8618233618233618,
|
| 2144 |
+
"eval_loss": 0.5538750290870667,
|
| 2145 |
+
"eval_runtime": 15.995,
|
| 2146 |
+
"eval_samples_per_second": 43.889,
|
| 2147 |
+
"eval_steps_per_second": 5.502,
|
| 2148 |
+
"step": 3100
|
| 2149 |
+
},
|
| 2150 |
+
{
|
| 2151 |
+
"epoch": 12.49,
|
| 2152 |
+
"learning_rate": 3.3574297188755024e-05,
|
| 2153 |
+
"loss": 0.2216,
|
| 2154 |
+
"step": 3110
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 12.53,
|
| 2158 |
+
"learning_rate": 3.30388219544846e-05,
|
| 2159 |
+
"loss": 0.2085,
|
| 2160 |
+
"step": 3120
|
| 2161 |
+
},
|
| 2162 |
+
{
|
| 2163 |
+
"epoch": 12.57,
|
| 2164 |
+
"learning_rate": 3.250334672021419e-05,
|
| 2165 |
+
"loss": 0.2727,
|
| 2166 |
+
"step": 3130
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 12.61,
|
| 2170 |
+
"learning_rate": 3.196787148594378e-05,
|
| 2171 |
+
"loss": 0.1823,
|
| 2172 |
+
"step": 3140
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 12.65,
|
| 2176 |
+
"learning_rate": 3.143239625167336e-05,
|
| 2177 |
+
"loss": 0.3328,
|
| 2178 |
+
"step": 3150
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 12.69,
|
| 2182 |
+
"learning_rate": 3.0896921017402946e-05,
|
| 2183 |
+
"loss": 0.1052,
|
| 2184 |
+
"step": 3160
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 12.73,
|
| 2188 |
+
"learning_rate": 3.036144578313253e-05,
|
| 2189 |
+
"loss": 0.1101,
|
| 2190 |
+
"step": 3170
|
| 2191 |
+
},
|
| 2192 |
+
{
|
| 2193 |
+
"epoch": 12.77,
|
| 2194 |
+
"learning_rate": 2.9825970548862113e-05,
|
| 2195 |
+
"loss": 0.1827,
|
| 2196 |
+
"step": 3180
|
| 2197 |
+
},
|
| 2198 |
+
{
|
| 2199 |
+
"epoch": 12.81,
|
| 2200 |
+
"learning_rate": 2.9290495314591702e-05,
|
| 2201 |
+
"loss": 0.0858,
|
| 2202 |
+
"step": 3190
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 12.85,
|
| 2206 |
+
"learning_rate": 2.8755020080321288e-05,
|
| 2207 |
+
"loss": 0.139,
|
| 2208 |
+
"step": 3200
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 12.85,
|
| 2212 |
+
"eval_accuracy": 0.8433048433048433,
|
| 2213 |
+
"eval_loss": 0.5865837335586548,
|
| 2214 |
+
"eval_runtime": 16.0651,
|
| 2215 |
+
"eval_samples_per_second": 43.697,
|
| 2216 |
+
"eval_steps_per_second": 5.478,
|
| 2217 |
+
"step": 3200
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 12.89,
|
| 2221 |
+
"learning_rate": 2.821954484605087e-05,
|
| 2222 |
+
"loss": 0.2402,
|
| 2223 |
+
"step": 3210
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 12.93,
|
| 2227 |
+
"learning_rate": 2.7684069611780456e-05,
|
| 2228 |
+
"loss": 0.1964,
|
| 2229 |
+
"step": 3220
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 12.97,
|
| 2233 |
+
"learning_rate": 2.7148594377510038e-05,
|
| 2234 |
+
"loss": 0.2707,
|
| 2235 |
+
"step": 3230
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 13.01,
|
| 2239 |
+
"learning_rate": 2.6613119143239627e-05,
|
| 2240 |
+
"loss": 0.2498,
|
| 2241 |
+
"step": 3240
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 13.05,
|
| 2245 |
+
"learning_rate": 2.6077643908969213e-05,
|
| 2246 |
+
"loss": 0.0964,
|
| 2247 |
+
"step": 3250
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 13.09,
|
| 2251 |
+
"learning_rate": 2.5542168674698795e-05,
|
| 2252 |
+
"loss": 0.2616,
|
| 2253 |
+
"step": 3260
|
| 2254 |
+
},
|
| 2255 |
+
{
|
| 2256 |
+
"epoch": 13.13,
|
| 2257 |
+
"learning_rate": 2.500669344042838e-05,
|
| 2258 |
+
"loss": 0.1971,
|
| 2259 |
+
"step": 3270
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 13.17,
|
| 2263 |
+
"learning_rate": 2.4471218206157966e-05,
|
| 2264 |
+
"loss": 0.1651,
|
| 2265 |
+
"step": 3280
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 13.21,
|
| 2269 |
+
"learning_rate": 2.3935742971887552e-05,
|
| 2270 |
+
"loss": 0.0599,
|
| 2271 |
+
"step": 3290
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 13.25,
|
| 2275 |
+
"learning_rate": 2.3400267737617138e-05,
|
| 2276 |
+
"loss": 0.2202,
|
| 2277 |
+
"step": 3300
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 13.25,
|
| 2281 |
+
"eval_accuracy": 0.8589743589743589,
|
| 2282 |
+
"eval_loss": 0.5248175859451294,
|
| 2283 |
+
"eval_runtime": 17.4004,
|
| 2284 |
+
"eval_samples_per_second": 40.344,
|
| 2285 |
+
"eval_steps_per_second": 5.057,
|
| 2286 |
+
"step": 3300
|
| 2287 |
+
},
|
| 2288 |
+
{
|
| 2289 |
+
"epoch": 13.29,
|
| 2290 |
+
"learning_rate": 2.286479250334672e-05,
|
| 2291 |
+
"loss": 0.2497,
|
| 2292 |
+
"step": 3310
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 13.33,
|
| 2296 |
+
"learning_rate": 2.2329317269076305e-05,
|
| 2297 |
+
"loss": 0.1713,
|
| 2298 |
+
"step": 3320
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 13.37,
|
| 2302 |
+
"learning_rate": 2.179384203480589e-05,
|
| 2303 |
+
"loss": 0.2707,
|
| 2304 |
+
"step": 3330
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 13.41,
|
| 2308 |
+
"learning_rate": 2.1258366800535477e-05,
|
| 2309 |
+
"loss": 0.2123,
|
| 2310 |
+
"step": 3340
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 13.45,
|
| 2314 |
+
"learning_rate": 2.0722891566265062e-05,
|
| 2315 |
+
"loss": 0.2833,
|
| 2316 |
+
"step": 3350
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 13.49,
|
| 2320 |
+
"learning_rate": 2.0187416331994645e-05,
|
| 2321 |
+
"loss": 0.2003,
|
| 2322 |
+
"step": 3360
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 13.53,
|
| 2326 |
+
"learning_rate": 1.965194109772423e-05,
|
| 2327 |
+
"loss": 0.2538,
|
| 2328 |
+
"step": 3370
|
| 2329 |
+
},
|
| 2330 |
+
{
|
| 2331 |
+
"epoch": 13.57,
|
| 2332 |
+
"learning_rate": 1.9116465863453816e-05,
|
| 2333 |
+
"loss": 0.112,
|
| 2334 |
+
"step": 3380
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 13.61,
|
| 2338 |
+
"learning_rate": 1.85809906291834e-05,
|
| 2339 |
+
"loss": 0.213,
|
| 2340 |
+
"step": 3390
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 13.65,
|
| 2344 |
+
"learning_rate": 1.8045515394912987e-05,
|
| 2345 |
+
"loss": 0.1421,
|
| 2346 |
+
"step": 3400
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 13.65,
|
| 2350 |
+
"eval_accuracy": 0.8475783475783476,
|
| 2351 |
+
"eval_loss": 0.5547856688499451,
|
| 2352 |
+
"eval_runtime": 16.1927,
|
| 2353 |
+
"eval_samples_per_second": 43.353,
|
| 2354 |
+
"eval_steps_per_second": 5.435,
|
| 2355 |
+
"step": 3400
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 13.69,
|
| 2359 |
+
"learning_rate": 1.7510040160642573e-05,
|
| 2360 |
+
"loss": 0.1792,
|
| 2361 |
+
"step": 3410
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 13.73,
|
| 2365 |
+
"learning_rate": 1.6974564926372155e-05,
|
| 2366 |
+
"loss": 0.1797,
|
| 2367 |
+
"step": 3420
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 13.78,
|
| 2371 |
+
"learning_rate": 1.643908969210174e-05,
|
| 2372 |
+
"loss": 0.1612,
|
| 2373 |
+
"step": 3430
|
| 2374 |
+
},
|
| 2375 |
+
{
|
| 2376 |
+
"epoch": 13.82,
|
| 2377 |
+
"learning_rate": 1.5903614457831326e-05,
|
| 2378 |
+
"loss": 0.1175,
|
| 2379 |
+
"step": 3440
|
| 2380 |
+
},
|
| 2381 |
+
{
|
| 2382 |
+
"epoch": 13.86,
|
| 2383 |
+
"learning_rate": 1.5368139223560912e-05,
|
| 2384 |
+
"loss": 0.2389,
|
| 2385 |
+
"step": 3450
|
| 2386 |
+
},
|
| 2387 |
+
{
|
| 2388 |
+
"epoch": 13.9,
|
| 2389 |
+
"learning_rate": 1.4832663989290496e-05,
|
| 2390 |
+
"loss": 0.1918,
|
| 2391 |
+
"step": 3460
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 13.94,
|
| 2395 |
+
"learning_rate": 1.429718875502008e-05,
|
| 2396 |
+
"loss": 0.1623,
|
| 2397 |
+
"step": 3470
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 13.98,
|
| 2401 |
+
"learning_rate": 1.3761713520749667e-05,
|
| 2402 |
+
"loss": 0.1686,
|
| 2403 |
+
"step": 3480
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 14.02,
|
| 2407 |
+
"learning_rate": 1.3226238286479251e-05,
|
| 2408 |
+
"loss": 0.2198,
|
| 2409 |
+
"step": 3490
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 14.06,
|
| 2413 |
+
"learning_rate": 1.2690763052208837e-05,
|
| 2414 |
+
"loss": 0.211,
|
| 2415 |
+
"step": 3500
|
| 2416 |
+
},
|
| 2417 |
+
{
|
| 2418 |
+
"epoch": 14.06,
|
| 2419 |
+
"eval_accuracy": 0.8490028490028491,
|
| 2420 |
+
"eval_loss": 0.5502182841300964,
|
| 2421 |
+
"eval_runtime": 15.5914,
|
| 2422 |
+
"eval_samples_per_second": 45.025,
|
| 2423 |
+
"eval_steps_per_second": 5.644,
|
| 2424 |
+
"step": 3500
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 14.1,
|
| 2428 |
+
"learning_rate": 1.215528781793842e-05,
|
| 2429 |
+
"loss": 0.2969,
|
| 2430 |
+
"step": 3510
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 14.14,
|
| 2434 |
+
"learning_rate": 1.1619812583668006e-05,
|
| 2435 |
+
"loss": 0.2386,
|
| 2436 |
+
"step": 3520
|
| 2437 |
+
},
|
| 2438 |
+
{
|
| 2439 |
+
"epoch": 14.18,
|
| 2440 |
+
"learning_rate": 1.108433734939759e-05,
|
| 2441 |
+
"loss": 0.218,
|
| 2442 |
+
"step": 3530
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 14.22,
|
| 2446 |
+
"learning_rate": 1.0548862115127176e-05,
|
| 2447 |
+
"loss": 0.2143,
|
| 2448 |
+
"step": 3540
|
| 2449 |
+
},
|
| 2450 |
+
{
|
| 2451 |
+
"epoch": 14.26,
|
| 2452 |
+
"learning_rate": 1.0013386880856762e-05,
|
| 2453 |
+
"loss": 0.1939,
|
| 2454 |
+
"step": 3550
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 14.3,
|
| 2458 |
+
"learning_rate": 9.477911646586345e-06,
|
| 2459 |
+
"loss": 0.1032,
|
| 2460 |
+
"step": 3560
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 14.34,
|
| 2464 |
+
"learning_rate": 8.942436412315931e-06,
|
| 2465 |
+
"loss": 0.0938,
|
| 2466 |
+
"step": 3570
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 14.38,
|
| 2470 |
+
"learning_rate": 8.406961178045515e-06,
|
| 2471 |
+
"loss": 0.2132,
|
| 2472 |
+
"step": 3580
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 14.42,
|
| 2476 |
+
"learning_rate": 7.8714859437751e-06,
|
| 2477 |
+
"loss": 0.0733,
|
| 2478 |
+
"step": 3590
|
| 2479 |
+
},
|
| 2480 |
+
{
|
| 2481 |
+
"epoch": 14.46,
|
| 2482 |
+
"learning_rate": 7.3360107095046855e-06,
|
| 2483 |
+
"loss": 0.2106,
|
| 2484 |
+
"step": 3600
|
| 2485 |
+
},
|
| 2486 |
+
{
|
| 2487 |
+
"epoch": 14.46,
|
| 2488 |
+
"eval_accuracy": 0.8504273504273504,
|
| 2489 |
+
"eval_loss": 0.5413134694099426,
|
| 2490 |
+
"eval_runtime": 16.0305,
|
| 2491 |
+
"eval_samples_per_second": 43.792,
|
| 2492 |
+
"eval_steps_per_second": 5.49,
|
| 2493 |
+
"step": 3600
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 14.5,
|
| 2497 |
+
"learning_rate": 6.800535475234271e-06,
|
| 2498 |
+
"loss": 0.1462,
|
| 2499 |
+
"step": 3610
|
| 2500 |
+
},
|
| 2501 |
+
{
|
| 2502 |
+
"epoch": 14.54,
|
| 2503 |
+
"learning_rate": 6.265060240963856e-06,
|
| 2504 |
+
"loss": 0.0978,
|
| 2505 |
+
"step": 3620
|
| 2506 |
+
},
|
| 2507 |
+
{
|
| 2508 |
+
"epoch": 14.58,
|
| 2509 |
+
"learning_rate": 5.729585006693441e-06,
|
| 2510 |
+
"loss": 0.2382,
|
| 2511 |
+
"step": 3630
|
| 2512 |
+
},
|
| 2513 |
+
{
|
| 2514 |
+
"epoch": 14.62,
|
| 2515 |
+
"learning_rate": 5.194109772423026e-06,
|
| 2516 |
+
"loss": 0.2068,
|
| 2517 |
+
"step": 3640
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 14.66,
|
| 2521 |
+
"learning_rate": 4.65863453815261e-06,
|
| 2522 |
+
"loss": 0.1502,
|
| 2523 |
+
"step": 3650
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 14.7,
|
| 2527 |
+
"learning_rate": 4.123159303882196e-06,
|
| 2528 |
+
"loss": 0.1871,
|
| 2529 |
+
"step": 3660
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 14.74,
|
| 2533 |
+
"learning_rate": 3.5876840696117802e-06,
|
| 2534 |
+
"loss": 0.1998,
|
| 2535 |
+
"step": 3670
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 14.78,
|
| 2539 |
+
"learning_rate": 3.052208835341366e-06,
|
| 2540 |
+
"loss": 0.1783,
|
| 2541 |
+
"step": 3680
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"epoch": 14.82,
|
| 2545 |
+
"learning_rate": 2.5167336010709507e-06,
|
| 2546 |
+
"loss": 0.1364,
|
| 2547 |
+
"step": 3690
|
| 2548 |
+
},
|
| 2549 |
+
{
|
| 2550 |
+
"epoch": 14.86,
|
| 2551 |
+
"learning_rate": 1.9812583668005354e-06,
|
| 2552 |
+
"loss": 0.1716,
|
| 2553 |
+
"step": 3700
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 14.86,
|
| 2557 |
+
"eval_accuracy": 0.8461538461538461,
|
| 2558 |
+
"eval_loss": 0.5398270487785339,
|
| 2559 |
+
"eval_runtime": 16.7227,
|
| 2560 |
+
"eval_samples_per_second": 41.979,
|
| 2561 |
+
"eval_steps_per_second": 5.262,
|
| 2562 |
+
"step": 3700
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 14.9,
|
| 2566 |
+
"learning_rate": 1.4457831325301207e-06,
|
| 2567 |
+
"loss": 0.2021,
|
| 2568 |
+
"step": 3710
|
| 2569 |
+
},
|
| 2570 |
+
{
|
| 2571 |
+
"epoch": 14.94,
|
| 2572 |
+
"learning_rate": 9.103078982597055e-07,
|
| 2573 |
+
"loss": 0.2808,
|
| 2574 |
+
"step": 3720
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 14.98,
|
| 2578 |
+
"learning_rate": 3.748326639892905e-07,
|
| 2579 |
+
"loss": 0.1892,
|
| 2580 |
+
"step": 3730
|
| 2581 |
+
},
|
| 2582 |
+
{
|
| 2583 |
+
"epoch": 15.0,
|
| 2584 |
+
"step": 3735,
|
| 2585 |
+
"total_flos": 4.617303784967946e+18,
|
| 2586 |
+
"train_loss": 0.43795731744293864,
|
| 2587 |
+
"train_runtime": 5300.4754,
|
| 2588 |
+
"train_samples_per_second": 11.241,
|
| 2589 |
+
"train_steps_per_second": 0.705
|
| 2590 |
}
|
| 2591 |
],
|
| 2592 |
"logging_steps": 10,
|
| 2593 |
+
"max_steps": 3735,
|
| 2594 |
+
"num_train_epochs": 15,
|
| 2595 |
"save_steps": 100,
|
| 2596 |
+
"total_flos": 4.617303784967946e+18,
|
| 2597 |
"trial_name": null,
|
| 2598 |
"trial_params": null
|
| 2599 |
}
|