Commit
•
0005076
1
Parent(s):
fa4c3de
Cheers 🎉
Browse files- README.md +4 -3
- all_results.json +11 -11
- eval_results.json +6 -6
- runs/Dec10_22-36-13_8460a124220f/events.out.tfevents.1733873345.8460a124220f.23.2 +3 -0
- test_results.json +6 -6
- train_results.json +6 -6
- trainer_state.json +983 -767
README.md
CHANGED
|
@@ -3,6 +3,7 @@ library_name: transformers
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: Sohaibsoussi/ViT-NIH-Chest-X-ray-dataset-small
|
| 5 |
tags:
|
|
|
|
| 6 |
- generated_from_trainer
|
| 7 |
metrics:
|
| 8 |
- accuracy
|
|
@@ -16,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# ViT-NIH-Chest-X-ray-dataset-small
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [Sohaibsoussi/ViT-NIH-Chest-X-ray-dataset-small](https://huggingface.co/Sohaibsoussi/ViT-NIH-Chest-X-ray-dataset-small) on
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Accuracy:
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 3 |
license: apache-2.0
|
| 4 |
base_model: Sohaibsoussi/ViT-NIH-Chest-X-ray-dataset-small
|
| 5 |
tags:
|
| 6 |
+
- image-classification
|
| 7 |
- generated_from_trainer
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 17 |
|
| 18 |
# ViT-NIH-Chest-X-ray-dataset-small
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [Sohaibsoussi/ViT-NIH-Chest-X-ray-dataset-small](https://huggingface.co/Sohaibsoussi/ViT-NIH-Chest-X-ray-dataset-small) on the Sohaibsoussi/NIH-Chest-X-ray-dataset-small dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.6731
|
| 23 |
+
- Accuracy: 0.2189
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
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": 32.
|
| 7 |
-
"eval_steps_per_second": 4.
|
| 8 |
-
"total_flos":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.0,
|
| 3 |
+
"eval_accuracy": 0.21892103205629398,
|
| 4 |
+
"eval_loss": 0.6731089949607849,
|
| 5 |
+
"eval_runtime": 38.919,
|
| 6 |
+
"eval_samples_per_second": 32.863,
|
| 7 |
+
"eval_steps_per_second": 4.111,
|
| 8 |
+
"total_flos": 3.017424657591816e+18,
|
| 9 |
+
"train_loss": 0.01402124272053813,
|
| 10 |
+
"train_runtime": 3085.6034,
|
| 11 |
+
"train_samples_per_second": 12.618,
|
| 12 |
+
"train_steps_per_second": 0.79
|
| 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": 9.0,
|
| 3 |
+
"eval_accuracy": 1.0,
|
| 4 |
+
"eval_loss": 0.0013051489368081093,
|
| 5 |
+
"eval_runtime": 52.636,
|
| 6 |
+
"eval_samples_per_second": 32.867,
|
| 7 |
+
"eval_steps_per_second": 4.123
|
| 8 |
}
|
runs/Dec10_22-36-13_8460a124220f/events.out.tfevents.1733873345.8460a124220f.23.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3695a757d37a115086bc0b4e94cdaecbd9fec29bc0d54c78565487a120ff673
|
| 3 |
+
size 734
|
test_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": 32.
|
| 7 |
-
"eval_steps_per_second": 4.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.0,
|
| 3 |
+
"eval_accuracy": 0.21892103205629398,
|
| 4 |
+
"eval_loss": 0.6731089949607849,
|
| 5 |
+
"eval_runtime": 38.919,
|
| 6 |
+
"eval_samples_per_second": 32.863,
|
| 7 |
+
"eval_steps_per_second": 4.111
|
| 8 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"total_flos":
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 9.0,
|
| 3 |
+
"total_flos": 3.017424657591816e+18,
|
| 4 |
+
"train_loss": 0.01402124272053813,
|
| 5 |
+
"train_runtime": 3085.6034,
|
| 6 |
+
"train_samples_per_second": 12.618,
|
| 7 |
+
"train_steps_per_second": 0.79
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,1728 +1,1944 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "./ViT-NIH-Chest-X-ray-dataset-small/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": 0.03690036900369004,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate": 0.
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.07380073800738007,
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
-
"learning_rate": 0.
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.11070110701107011,
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
-
"learning_rate": 0.
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.14760147601476015,
|
| 34 |
-
"grad_norm": 0.
|
| 35 |
-
"learning_rate": 0.
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.18450184501845018,
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
-
"learning_rate": 0.
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.22140221402214022,
|
| 48 |
-
"grad_norm": 0.
|
| 49 |
-
"learning_rate": 0.
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.25830258302583026,
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
-
"learning_rate": 0.
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.2952029520295203,
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate": 0.
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.33210332103321033,
|
| 69 |
-
"grad_norm": 0.
|
| 70 |
-
"learning_rate": 0.
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.36900369003690037,
|
| 76 |
-
"grad_norm": 0.
|
| 77 |
-
"learning_rate": 0.
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.36900369003690037,
|
| 83 |
-
"eval_accuracy": 0.
|
| 84 |
-
"eval_loss": 0.
|
| 85 |
-
"eval_runtime":
|
| 86 |
-
"eval_samples_per_second":
|
| 87 |
-
"eval_steps_per_second": 4.
|
| 88 |
"step": 100
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 0.4059040590405904,
|
| 92 |
-
"grad_norm": 0.
|
| 93 |
-
"learning_rate": 0.
|
| 94 |
-
"loss": 0.
|
| 95 |
"step": 110
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 0.44280442804428044,
|
| 99 |
-
"grad_norm": 0.
|
| 100 |
-
"learning_rate": 0.
|
| 101 |
-
"loss": 0.
|
| 102 |
"step": 120
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.4797047970479705,
|
| 106 |
-
"grad_norm": 0.
|
| 107 |
-
"learning_rate": 0.
|
| 108 |
-
"loss": 0.
|
| 109 |
"step": 130
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 0.5166051660516605,
|
| 113 |
-
"grad_norm": 0.
|
| 114 |
-
"learning_rate": 0.
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 140
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.5535055350553506,
|
| 120 |
-
"grad_norm": 0.
|
| 121 |
-
"learning_rate": 0.
|
| 122 |
-
"loss": 0.
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.5904059040590406,
|
| 127 |
-
"grad_norm": 0.
|
| 128 |
-
"learning_rate": 0.
|
| 129 |
-
"loss": 0.
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 0.6273062730627307,
|
| 134 |
-
"grad_norm":
|
| 135 |
-
"learning_rate": 0.
|
| 136 |
-
"loss": 0.
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 0.6642066420664207,
|
| 141 |
-
"grad_norm": 0.
|
| 142 |
-
"learning_rate": 0.
|
| 143 |
-
"loss": 0.
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 0.7011070110701108,
|
| 148 |
-
"grad_norm": 0.
|
| 149 |
-
"learning_rate": 0.
|
| 150 |
-
"loss": 0.
|
| 151 |
"step": 190
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 0.7380073800738007,
|
| 155 |
-
"grad_norm": 0.
|
| 156 |
-
"learning_rate": 0.
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 200
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 0.7380073800738007,
|
| 162 |
-
"eval_accuracy": 0.
|
| 163 |
-
"eval_loss": 0.
|
| 164 |
-
"eval_runtime":
|
| 165 |
-
"eval_samples_per_second":
|
| 166 |
-
"eval_steps_per_second": 4.
|
| 167 |
"step": 200
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 0.7749077490774908,
|
| 171 |
-
"grad_norm": 0.
|
| 172 |
-
"learning_rate": 0.
|
| 173 |
-
"loss": 0.
|
| 174 |
"step": 210
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 0.8118081180811808,
|
| 178 |
-
"grad_norm":
|
| 179 |
-
"learning_rate": 0.
|
| 180 |
-
"loss": 0.
|
| 181 |
"step": 220
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 0.8487084870848709,
|
| 185 |
-
"grad_norm": 0.
|
| 186 |
-
"learning_rate": 0.
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 230
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.8856088560885609,
|
| 192 |
-
"grad_norm": 0.
|
| 193 |
-
"learning_rate": 0.
|
| 194 |
-
"loss": 0.
|
| 195 |
"step": 240
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.922509225092251,
|
| 199 |
-
"grad_norm": 0.
|
| 200 |
-
"learning_rate": 0.
|
| 201 |
-
"loss": 0.
|
| 202 |
"step": 250
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 0.959409594095941,
|
| 206 |
-
"grad_norm": 0.
|
| 207 |
-
"learning_rate": 0.
|
| 208 |
-
"loss": 0.
|
| 209 |
"step": 260
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 0.996309963099631,
|
| 213 |
-
"grad_norm": 0.
|
| 214 |
-
"learning_rate": 0.
|
| 215 |
-
"loss": 0.
|
| 216 |
"step": 270
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 1.033210332103321,
|
| 220 |
-
"grad_norm": 0.
|
| 221 |
-
"learning_rate": 0.
|
| 222 |
-
"loss": 0.
|
| 223 |
"step": 280
|
| 224 |
},
|
| 225 |
{
|
| 226 |
"epoch": 1.070110701107011,
|
| 227 |
-
"grad_norm": 0.
|
| 228 |
-
"learning_rate": 0.
|
| 229 |
-
"loss": 0.
|
| 230 |
"step": 290
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 1.1070110701107012,
|
| 234 |
-
"grad_norm": 0.
|
| 235 |
-
"learning_rate": 0.
|
| 236 |
-
"loss": 0.
|
| 237 |
"step": 300
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 1.1070110701107012,
|
| 241 |
-
"eval_accuracy": 0.
|
| 242 |
-
"eval_loss": 0.
|
| 243 |
-
"eval_runtime":
|
| 244 |
-
"eval_samples_per_second":
|
| 245 |
-
"eval_steps_per_second": 4.
|
| 246 |
"step": 300
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 1.1439114391143912,
|
| 250 |
-
"grad_norm": 0.
|
| 251 |
-
"learning_rate": 0.
|
| 252 |
-
"loss": 0.
|
| 253 |
"step": 310
|
| 254 |
},
|
| 255 |
{
|
| 256 |
"epoch": 1.1808118081180812,
|
| 257 |
-
"grad_norm": 0.
|
| 258 |
-
"learning_rate": 0.
|
| 259 |
-
"loss": 0.
|
| 260 |
"step": 320
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 1.2177121771217712,
|
| 264 |
-
"grad_norm": 0.
|
| 265 |
-
"learning_rate": 0.
|
| 266 |
-
"loss": 0.
|
| 267 |
"step": 330
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 1.2546125461254611,
|
| 271 |
-
"grad_norm": 0.
|
| 272 |
-
"learning_rate": 0.
|
| 273 |
-
"loss": 0.
|
| 274 |
"step": 340
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 1.2915129151291513,
|
| 278 |
-
"grad_norm": 0.
|
| 279 |
-
"learning_rate": 0.
|
| 280 |
-
"loss": 0.
|
| 281 |
"step": 350
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 1.3284132841328413,
|
| 285 |
-
"grad_norm": 0.
|
| 286 |
-
"learning_rate": 0.
|
| 287 |
-
"loss": 0.
|
| 288 |
"step": 360
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 1.3653136531365313,
|
| 292 |
-
"grad_norm": 0.
|
| 293 |
-
"learning_rate": 0.
|
| 294 |
-
"loss": 0.
|
| 295 |
"step": 370
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 1.4022140221402215,
|
| 299 |
-
"grad_norm": 0.
|
| 300 |
-
"learning_rate": 0.
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 380
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 1.4391143911439115,
|
| 306 |
-
"grad_norm": 0.
|
| 307 |
-
"learning_rate": 0.
|
| 308 |
-
"loss": 0.
|
| 309 |
"step": 390
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 1.4760147601476015,
|
| 313 |
-
"grad_norm": 0.
|
| 314 |
-
"learning_rate": 0.
|
| 315 |
-
"loss": 0.
|
| 316 |
"step": 400
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 1.4760147601476015,
|
| 320 |
-
"eval_accuracy": 0.
|
| 321 |
-
"eval_loss": 0.
|
| 322 |
-
"eval_runtime":
|
| 323 |
-
"eval_samples_per_second":
|
| 324 |
-
"eval_steps_per_second": 4.
|
| 325 |
"step": 400
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 1.5129151291512914,
|
| 329 |
-
"grad_norm": 0.
|
| 330 |
-
"learning_rate": 0.
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 410
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 1.5498154981549814,
|
| 336 |
-
"grad_norm": 0.
|
| 337 |
-
"learning_rate": 0.
|
| 338 |
-
"loss": 0.
|
| 339 |
"step": 420
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 1.5867158671586716,
|
| 343 |
-
"grad_norm": 0.
|
| 344 |
-
"learning_rate": 0.
|
| 345 |
-
"loss": 0.
|
| 346 |
"step": 430
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.6236162361623616,
|
| 350 |
-
"grad_norm": 0.
|
| 351 |
-
"learning_rate": 0.
|
| 352 |
-
"loss": 0.
|
| 353 |
"step": 440
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 1.6605166051660518,
|
| 357 |
-
"grad_norm": 0.
|
| 358 |
-
"learning_rate": 0.
|
| 359 |
-
"loss": 0.
|
| 360 |
"step": 450
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 1.6974169741697418,
|
| 364 |
-
"grad_norm": 0.
|
| 365 |
-
"learning_rate": 0.
|
| 366 |
-
"loss": 0.
|
| 367 |
"step": 460
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 1.7343173431734318,
|
| 371 |
-
"grad_norm": 0.
|
| 372 |
-
"learning_rate": 0.
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 470
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 1.7712177121771218,
|
| 378 |
-
"grad_norm": 0.
|
| 379 |
-
"learning_rate": 0.
|
| 380 |
-
"loss": 0.
|
| 381 |
"step": 480
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 1.8081180811808117,
|
| 385 |
-
"grad_norm": 0.
|
| 386 |
-
"learning_rate": 0.
|
| 387 |
-
"loss": 0.
|
| 388 |
"step": 490
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.8450184501845017,
|
| 392 |
-
"grad_norm": 0.
|
| 393 |
-
"learning_rate": 0.
|
| 394 |
-
"loss": 0.
|
| 395 |
"step": 500
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.8450184501845017,
|
| 399 |
-
"eval_accuracy": 0.
|
| 400 |
-
"eval_loss": 0.
|
| 401 |
-
"eval_runtime":
|
| 402 |
-
"eval_samples_per_second":
|
| 403 |
-
"eval_steps_per_second": 4.
|
| 404 |
"step": 500
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 1.881918819188192,
|
| 408 |
-
"grad_norm": 0.
|
| 409 |
-
"learning_rate": 0.
|
| 410 |
-
"loss": 0.
|
| 411 |
"step": 510
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 1.918819188191882,
|
| 415 |
-
"grad_norm": 0.
|
| 416 |
-
"learning_rate": 0.
|
| 417 |
-
"loss": 0.
|
| 418 |
"step": 520
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"epoch": 1.9557195571955721,
|
| 422 |
-
"grad_norm": 0.
|
| 423 |
-
"learning_rate": 0.
|
| 424 |
-
"loss": 0.
|
| 425 |
"step": 530
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 1.992619926199262,
|
| 429 |
-
"grad_norm": 0.
|
| 430 |
-
"learning_rate": 0.
|
| 431 |
-
"loss": 0.
|
| 432 |
"step": 540
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 2.029520295202952,
|
| 436 |
-
"grad_norm": 0.
|
| 437 |
-
"learning_rate": 0.
|
| 438 |
-
"loss": 0.
|
| 439 |
"step": 550
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 2.066420664206642,
|
| 443 |
-
"grad_norm": 0.
|
| 444 |
-
"learning_rate": 0.
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 560
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 2.103321033210332,
|
| 450 |
-
"grad_norm": 0.
|
| 451 |
-
"learning_rate": 0.
|
| 452 |
-
"loss": 0.
|
| 453 |
"step": 570
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 2.140221402214022,
|
| 457 |
-
"grad_norm": 0.
|
| 458 |
-
"learning_rate": 0.
|
| 459 |
-
"loss": 0.
|
| 460 |
"step": 580
|
| 461 |
},
|
| 462 |
{
|
| 463 |
"epoch": 2.177121771217712,
|
| 464 |
-
"grad_norm": 0.
|
| 465 |
-
"learning_rate": 0.
|
| 466 |
-
"loss": 0.
|
| 467 |
"step": 590
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 2.2140221402214024,
|
| 471 |
-
"grad_norm": 0.
|
| 472 |
-
"learning_rate": 0.
|
| 473 |
-
"loss": 0.
|
| 474 |
"step": 600
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 2.2140221402214024,
|
| 478 |
-
"eval_accuracy": 0.
|
| 479 |
-
"eval_loss": 0.
|
| 480 |
-
"eval_runtime":
|
| 481 |
-
"eval_samples_per_second":
|
| 482 |
-
"eval_steps_per_second": 4.
|
| 483 |
"step": 600
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 2.2509225092250924,
|
| 487 |
-
"grad_norm": 0.
|
| 488 |
-
"learning_rate": 0.
|
| 489 |
-
"loss": 0.
|
| 490 |
"step": 610
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 2.2878228782287824,
|
| 494 |
-
"grad_norm": 0.
|
| 495 |
-
"learning_rate": 0.
|
| 496 |
-
"loss": 0.
|
| 497 |
"step": 620
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 2.3247232472324724,
|
| 501 |
-
"grad_norm": 0.
|
| 502 |
-
"learning_rate": 0.
|
| 503 |
-
"loss": 0.
|
| 504 |
"step": 630
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 2.3616236162361623,
|
| 508 |
-
"grad_norm": 0.
|
| 509 |
-
"learning_rate": 0.
|
| 510 |
-
"loss": 0.
|
| 511 |
"step": 640
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 2.3985239852398523,
|
| 515 |
-
"grad_norm": 0.
|
| 516 |
-
"learning_rate": 0.
|
| 517 |
-
"loss": 0.
|
| 518 |
"step": 650
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 2.4354243542435423,
|
| 522 |
-
"grad_norm": 0.
|
| 523 |
-
"learning_rate": 0.
|
| 524 |
-
"loss": 0.
|
| 525 |
"step": 660
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 2.4723247232472323,
|
| 529 |
-
"grad_norm": 0.
|
| 530 |
-
"learning_rate": 0.
|
| 531 |
-
"loss": 0.
|
| 532 |
"step": 670
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 2.5092250922509223,
|
| 536 |
-
"grad_norm": 0.
|
| 537 |
-
"learning_rate": 0.
|
| 538 |
-
"loss": 0.
|
| 539 |
"step": 680
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 2.5461254612546127,
|
| 543 |
-
"grad_norm":
|
| 544 |
-
"learning_rate": 0.
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 690
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 2.5830258302583027,
|
| 550 |
-
"grad_norm": 0.
|
| 551 |
-
"learning_rate": 0.
|
| 552 |
-
"loss": 0.
|
| 553 |
"step": 700
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 2.5830258302583027,
|
| 557 |
-
"eval_accuracy": 0.
|
| 558 |
-
"eval_loss": 0.
|
| 559 |
-
"eval_runtime":
|
| 560 |
-
"eval_samples_per_second":
|
| 561 |
-
"eval_steps_per_second": 4.
|
| 562 |
"step": 700
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"epoch": 2.6199261992619927,
|
| 566 |
-
"grad_norm": 0.
|
| 567 |
-
"learning_rate": 0.
|
| 568 |
-
"loss": 0.
|
| 569 |
"step": 710
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 2.6568265682656826,
|
| 573 |
-
"grad_norm": 0.
|
| 574 |
-
"learning_rate": 0.
|
| 575 |
-
"loss": 0.
|
| 576 |
"step": 720
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 2.6937269372693726,
|
| 580 |
-
"grad_norm":
|
| 581 |
-
"learning_rate": 0.
|
| 582 |
-
"loss": 0.
|
| 583 |
"step": 730
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 2.7306273062730626,
|
| 587 |
-
"grad_norm": 0.
|
| 588 |
-
"learning_rate": 0.
|
| 589 |
-
"loss": 0.
|
| 590 |
"step": 740
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 2.767527675276753,
|
| 594 |
-
"grad_norm": 0.
|
| 595 |
-
"learning_rate": 0.
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 750
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 2.804428044280443,
|
| 601 |
-
"grad_norm": 0.
|
| 602 |
-
"learning_rate": 0.
|
| 603 |
-
"loss": 0.
|
| 604 |
"step": 760
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 2.841328413284133,
|
| 608 |
-
"grad_norm": 0.
|
| 609 |
-
"learning_rate": 0.
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 770
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 2.878228782287823,
|
| 615 |
-
"grad_norm": 0.
|
| 616 |
-
"learning_rate": 0.
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 780
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 2.915129151291513,
|
| 622 |
-
"grad_norm": 0.
|
| 623 |
-
"learning_rate": 0.
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 790
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 2.952029520295203,
|
| 629 |
-
"grad_norm": 0.
|
| 630 |
-
"learning_rate": 0.
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 800
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 2.952029520295203,
|
| 636 |
-
"eval_accuracy": 0.
|
| 637 |
-
"eval_loss": 0.
|
| 638 |
-
"eval_runtime":
|
| 639 |
-
"eval_samples_per_second":
|
| 640 |
-
"eval_steps_per_second": 4.
|
| 641 |
"step": 800
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 2.988929889298893,
|
| 645 |
-
"grad_norm": 0.
|
| 646 |
-
"learning_rate": 0.
|
| 647 |
-
"loss": 0.
|
| 648 |
"step": 810
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 3.025830258302583,
|
| 652 |
-
"grad_norm": 0.
|
| 653 |
-
"learning_rate": 0.
|
| 654 |
-
"loss": 0.
|
| 655 |
"step": 820
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 3.062730627306273,
|
| 659 |
-
"grad_norm": 0.
|
| 660 |
-
"learning_rate": 0.
|
| 661 |
-
"loss": 0.
|
| 662 |
"step": 830
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 3.0996309963099633,
|
| 666 |
-
"grad_norm": 0.
|
| 667 |
-
"learning_rate": 0.
|
| 668 |
-
"loss": 0.
|
| 669 |
"step": 840
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 3.1365313653136533,
|
| 673 |
-
"grad_norm": 0.
|
| 674 |
-
"learning_rate": 0.
|
| 675 |
-
"loss": 0.
|
| 676 |
"step": 850
|
| 677 |
},
|
| 678 |
{
|
| 679 |
"epoch": 3.1734317343173433,
|
| 680 |
-
"grad_norm": 0.
|
| 681 |
-
"learning_rate": 0.
|
| 682 |
-
"loss": 0.
|
| 683 |
"step": 860
|
| 684 |
},
|
| 685 |
{
|
| 686 |
"epoch": 3.2103321033210332,
|
| 687 |
-
"grad_norm": 0.
|
| 688 |
-
"learning_rate": 0.
|
| 689 |
-
"loss": 0.
|
| 690 |
"step": 870
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 3.2472324723247232,
|
| 694 |
-
"grad_norm": 0.
|
| 695 |
-
"learning_rate": 0.
|
| 696 |
-
"loss": 0.
|
| 697 |
"step": 880
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 3.284132841328413,
|
| 701 |
-
"grad_norm": 0.
|
| 702 |
-
"learning_rate": 0.
|
| 703 |
-
"loss": 0.
|
| 704 |
"step": 890
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 3.321033210332103,
|
| 708 |
-
"grad_norm": 0.
|
| 709 |
-
"learning_rate": 0.
|
| 710 |
-
"loss": 0.
|
| 711 |
"step": 900
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 3.321033210332103,
|
| 715 |
-
"eval_accuracy": 0.
|
| 716 |
-
"eval_loss": 0.
|
| 717 |
-
"eval_runtime":
|
| 718 |
-
"eval_samples_per_second":
|
| 719 |
-
"eval_steps_per_second": 4.
|
| 720 |
"step": 900
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 3.357933579335793,
|
| 724 |
-
"grad_norm": 0.
|
| 725 |
-
"learning_rate": 0.
|
| 726 |
-
"loss": 0.
|
| 727 |
"step": 910
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 3.3948339483394836,
|
| 731 |
-
"grad_norm": 0.
|
| 732 |
-
"learning_rate": 0.
|
| 733 |
-
"loss": 0.
|
| 734 |
"step": 920
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 3.4317343173431736,
|
| 738 |
-
"grad_norm": 0.
|
| 739 |
-
"learning_rate": 0.
|
| 740 |
-
"loss": 0.
|
| 741 |
"step": 930
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 3.4686346863468636,
|
| 745 |
-
"grad_norm": 0.
|
| 746 |
-
"learning_rate": 0.
|
| 747 |
-
"loss": 0.
|
| 748 |
"step": 940
|
| 749 |
},
|
| 750 |
{
|
| 751 |
"epoch": 3.5055350553505535,
|
| 752 |
-
"grad_norm": 0.
|
| 753 |
-
"learning_rate": 0.
|
| 754 |
-
"loss": 0.
|
| 755 |
"step": 950
|
| 756 |
},
|
| 757 |
{
|
| 758 |
"epoch": 3.5424354243542435,
|
| 759 |
-
"grad_norm": 0.
|
| 760 |
-
"learning_rate": 0.
|
| 761 |
-
"loss": 0.
|
| 762 |
"step": 960
|
| 763 |
},
|
| 764 |
{
|
| 765 |
"epoch": 3.5793357933579335,
|
| 766 |
-
"grad_norm": 0.
|
| 767 |
-
"learning_rate": 0.
|
| 768 |
-
"loss": 0.
|
| 769 |
"step": 970
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 3.6162361623616235,
|
| 773 |
-
"grad_norm":
|
| 774 |
-
"learning_rate": 0.
|
| 775 |
-
"loss": 0.
|
| 776 |
"step": 980
|
| 777 |
},
|
| 778 |
{
|
| 779 |
"epoch": 3.6531365313653135,
|
| 780 |
-
"grad_norm": 0.
|
| 781 |
-
"learning_rate": 0.
|
| 782 |
-
"loss": 0.
|
| 783 |
"step": 990
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 3.6900369003690034,
|
| 787 |
-
"grad_norm": 0.
|
| 788 |
-
"learning_rate": 0.
|
| 789 |
-
"loss": 0.
|
| 790 |
"step": 1000
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 3.6900369003690034,
|
| 794 |
-
"eval_accuracy": 0.
|
| 795 |
-
"eval_loss": 0.
|
| 796 |
-
"eval_runtime":
|
| 797 |
-
"eval_samples_per_second":
|
| 798 |
-
"eval_steps_per_second": 4.
|
| 799 |
"step": 1000
|
| 800 |
},
|
| 801 |
{
|
| 802 |
"epoch": 3.726937269372694,
|
| 803 |
-
"grad_norm": 0.
|
| 804 |
-
"learning_rate": 0.
|
| 805 |
-
"loss": 0.
|
| 806 |
"step": 1010
|
| 807 |
},
|
| 808 |
{
|
| 809 |
"epoch": 3.763837638376384,
|
| 810 |
-
"grad_norm": 0.
|
| 811 |
-
"learning_rate": 0.
|
| 812 |
-
"loss": 0.
|
| 813 |
"step": 1020
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 3.800738007380074,
|
| 817 |
-
"grad_norm": 0.
|
| 818 |
-
"learning_rate": 0.
|
| 819 |
-
"loss": 0.
|
| 820 |
"step": 1030
|
| 821 |
},
|
| 822 |
{
|
| 823 |
"epoch": 3.837638376383764,
|
| 824 |
-
"grad_norm": 0.
|
| 825 |
-
"learning_rate": 0.
|
| 826 |
-
"loss": 0.
|
| 827 |
"step": 1040
|
| 828 |
},
|
| 829 |
{
|
| 830 |
"epoch": 3.874538745387454,
|
| 831 |
-
"grad_norm": 0.
|
| 832 |
-
"learning_rate": 0.
|
| 833 |
-
"loss": 0.
|
| 834 |
"step": 1050
|
| 835 |
},
|
| 836 |
{
|
| 837 |
"epoch": 3.911439114391144,
|
| 838 |
-
"grad_norm": 0.
|
| 839 |
-
"learning_rate": 0.
|
| 840 |
-
"loss": 0.
|
| 841 |
"step": 1060
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"epoch": 3.948339483394834,
|
| 845 |
-
"grad_norm": 0.
|
| 846 |
-
"learning_rate": 0.
|
| 847 |
-
"loss": 0.
|
| 848 |
"step": 1070
|
| 849 |
},
|
| 850 |
{
|
| 851 |
"epoch": 3.985239852398524,
|
| 852 |
-
"grad_norm": 0.
|
| 853 |
-
"learning_rate": 0.
|
| 854 |
-
"loss": 0.
|
| 855 |
"step": 1080
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 4.022140221402214,
|
| 859 |
-
"grad_norm": 0.
|
| 860 |
-
"learning_rate":
|
| 861 |
-
"loss": 0.
|
| 862 |
"step": 1090
|
| 863 |
},
|
| 864 |
{
|
| 865 |
"epoch": 4.059040590405904,
|
| 866 |
-
"grad_norm": 0.
|
| 867 |
-
"learning_rate":
|
| 868 |
-
"loss": 0.
|
| 869 |
"step": 1100
|
| 870 |
},
|
| 871 |
{
|
| 872 |
"epoch": 4.059040590405904,
|
| 873 |
-
"eval_accuracy": 0.
|
| 874 |
-
"eval_loss": 0.
|
| 875 |
-
"eval_runtime":
|
| 876 |
-
"eval_samples_per_second":
|
| 877 |
-
"eval_steps_per_second": 4.
|
| 878 |
"step": 1100
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 4.095940959409594,
|
| 882 |
-
"grad_norm": 0.
|
| 883 |
-
"learning_rate":
|
| 884 |
-
"loss": 0.
|
| 885 |
"step": 1110
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 4.132841328413284,
|
| 889 |
-
"grad_norm": 0.
|
| 890 |
-
"learning_rate":
|
| 891 |
-
"loss": 0.
|
| 892 |
"step": 1120
|
| 893 |
},
|
| 894 |
{
|
| 895 |
"epoch": 4.169741697416974,
|
| 896 |
-
"grad_norm": 0.
|
| 897 |
-
"learning_rate":
|
| 898 |
-
"loss": 0.
|
| 899 |
"step": 1130
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 4.206642066420664,
|
| 903 |
-
"grad_norm": 0.
|
| 904 |
-
"learning_rate":
|
| 905 |
-
"loss": 0.
|
| 906 |
"step": 1140
|
| 907 |
},
|
| 908 |
{
|
| 909 |
"epoch": 4.243542435424354,
|
| 910 |
-
"grad_norm": 0.
|
| 911 |
-
"learning_rate":
|
| 912 |
-
"loss": 0.
|
| 913 |
"step": 1150
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"epoch": 4.280442804428044,
|
| 917 |
-
"grad_norm": 0.
|
| 918 |
-
"learning_rate":
|
| 919 |
-
"loss": 0.
|
| 920 |
"step": 1160
|
| 921 |
},
|
| 922 |
{
|
| 923 |
"epoch": 4.317343173431734,
|
| 924 |
-
"grad_norm": 0.
|
| 925 |
-
"learning_rate":
|
| 926 |
-
"loss": 0.
|
| 927 |
"step": 1170
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 4.354243542435424,
|
| 931 |
-
"grad_norm": 0.
|
| 932 |
-
"learning_rate":
|
| 933 |
-
"loss": 0.
|
| 934 |
"step": 1180
|
| 935 |
},
|
| 936 |
{
|
| 937 |
"epoch": 4.391143911439114,
|
| 938 |
-
"grad_norm": 0.
|
| 939 |
-
"learning_rate":
|
| 940 |
-
"loss": 0.
|
| 941 |
"step": 1190
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 4.428044280442805,
|
| 945 |
-
"grad_norm": 0.
|
| 946 |
-
"learning_rate":
|
| 947 |
-
"loss": 0.
|
| 948 |
"step": 1200
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 4.428044280442805,
|
| 952 |
-
"eval_accuracy": 0.
|
| 953 |
-
"eval_loss": 0.
|
| 954 |
-
"eval_runtime":
|
| 955 |
-
"eval_samples_per_second":
|
| 956 |
-
"eval_steps_per_second": 4.
|
| 957 |
"step": 1200
|
| 958 |
},
|
| 959 |
{
|
| 960 |
"epoch": 4.464944649446495,
|
| 961 |
-
"grad_norm": 0.
|
| 962 |
-
"learning_rate":
|
| 963 |
-
"loss": 0.
|
| 964 |
"step": 1210
|
| 965 |
},
|
| 966 |
{
|
| 967 |
"epoch": 4.501845018450185,
|
| 968 |
-
"grad_norm": 0.
|
| 969 |
-
"learning_rate":
|
| 970 |
-
"loss": 0.
|
| 971 |
"step": 1220
|
| 972 |
},
|
| 973 |
{
|
| 974 |
"epoch": 4.538745387453875,
|
| 975 |
-
"grad_norm": 0.
|
| 976 |
-
"learning_rate":
|
| 977 |
-
"loss": 0.
|
| 978 |
"step": 1230
|
| 979 |
},
|
| 980 |
{
|
| 981 |
"epoch": 4.575645756457565,
|
| 982 |
-
"grad_norm": 0.
|
| 983 |
-
"learning_rate":
|
| 984 |
-
"loss": 0.
|
| 985 |
"step": 1240
|
| 986 |
},
|
| 987 |
{
|
| 988 |
"epoch": 4.612546125461255,
|
| 989 |
-
"grad_norm": 0.
|
| 990 |
-
"learning_rate":
|
| 991 |
-
"loss": 0.
|
| 992 |
"step": 1250
|
| 993 |
},
|
| 994 |
{
|
| 995 |
"epoch": 4.649446494464945,
|
| 996 |
-
"grad_norm": 0.
|
| 997 |
-
"learning_rate":
|
| 998 |
-
"loss": 0.
|
| 999 |
"step": 1260
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 4.686346863468635,
|
| 1003 |
-
"grad_norm": 0.
|
| 1004 |
-
"learning_rate":
|
| 1005 |
-
"loss": 0.
|
| 1006 |
"step": 1270
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
"epoch": 4.723247232472325,
|
| 1010 |
-
"grad_norm": 0.
|
| 1011 |
-
"learning_rate":
|
| 1012 |
-
"loss": 0.
|
| 1013 |
"step": 1280
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
"epoch": 4.760147601476015,
|
| 1017 |
-
"grad_norm": 0.
|
| 1018 |
-
"learning_rate":
|
| 1019 |
-
"loss": 0.
|
| 1020 |
"step": 1290
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
"epoch": 4.797047970479705,
|
| 1024 |
-
"grad_norm": 0.
|
| 1025 |
-
"learning_rate":
|
| 1026 |
-
"loss": 0.
|
| 1027 |
"step": 1300
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
"epoch": 4.797047970479705,
|
| 1031 |
-
"eval_accuracy": 0.
|
| 1032 |
-
"eval_loss": 0.
|
| 1033 |
-
"eval_runtime":
|
| 1034 |
-
"eval_samples_per_second":
|
| 1035 |
-
"eval_steps_per_second": 4.
|
| 1036 |
"step": 1300
|
| 1037 |
},
|
| 1038 |
{
|
| 1039 |
"epoch": 4.833948339483395,
|
| 1040 |
-
"grad_norm": 0.
|
| 1041 |
-
"learning_rate":
|
| 1042 |
-
"loss": 0.
|
| 1043 |
"step": 1310
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
"epoch": 4.870848708487085,
|
| 1047 |
-
"grad_norm": 0.
|
| 1048 |
-
"learning_rate":
|
| 1049 |
-
"loss": 0.
|
| 1050 |
"step": 1320
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
"epoch": 4.907749077490775,
|
| 1054 |
-
"grad_norm": 0.
|
| 1055 |
-
"learning_rate":
|
| 1056 |
-
"loss": 0.
|
| 1057 |
"step": 1330
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
"epoch": 4.944649446494465,
|
| 1061 |
-
"grad_norm": 0.
|
| 1062 |
-
"learning_rate":
|
| 1063 |
-
"loss": 0.
|
| 1064 |
"step": 1340
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
"epoch": 4.9815498154981555,
|
| 1068 |
-
"grad_norm": 0.
|
| 1069 |
-
"learning_rate":
|
| 1070 |
-
"loss": 0.
|
| 1071 |
"step": 1350
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 5.018450184501845,
|
| 1075 |
-
"grad_norm": 0.
|
| 1076 |
-
"learning_rate":
|
| 1077 |
-
"loss": 0.
|
| 1078 |
"step": 1360
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
"epoch": 5.055350553505535,
|
| 1082 |
-
"grad_norm": 0.
|
| 1083 |
-
"learning_rate":
|
| 1084 |
-
"loss": 0.
|
| 1085 |
"step": 1370
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 5.092250922509225,
|
| 1089 |
-
"grad_norm": 0.
|
| 1090 |
-
"learning_rate":
|
| 1091 |
-
"loss": 0.
|
| 1092 |
"step": 1380
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 5.129151291512915,
|
| 1096 |
-
"grad_norm": 0.
|
| 1097 |
-
"learning_rate":
|
| 1098 |
-
"loss": 0.
|
| 1099 |
"step": 1390
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
"epoch": 5.166051660516605,
|
| 1103 |
-
"grad_norm": 0.
|
| 1104 |
-
"learning_rate":
|
| 1105 |
-
"loss": 0.
|
| 1106 |
"step": 1400
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 5.166051660516605,
|
| 1110 |
-
"eval_accuracy": 0.
|
| 1111 |
-
"eval_loss": 0.
|
| 1112 |
-
"eval_runtime":
|
| 1113 |
-
"eval_samples_per_second":
|
| 1114 |
-
"eval_steps_per_second": 4.
|
| 1115 |
"step": 1400
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
"epoch": 5.202952029520295,
|
| 1119 |
-
"grad_norm": 0.
|
| 1120 |
-
"learning_rate":
|
| 1121 |
-
"loss": 0.
|
| 1122 |
"step": 1410
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 5.239852398523985,
|
| 1126 |
-
"grad_norm": 0.
|
| 1127 |
-
"learning_rate":
|
| 1128 |
-
"loss": 0.
|
| 1129 |
"step": 1420
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 5.276752767527675,
|
| 1133 |
-
"grad_norm": 0.
|
| 1134 |
-
"learning_rate":
|
| 1135 |
-
"loss": 0.
|
| 1136 |
"step": 1430
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 5.313653136531365,
|
| 1140 |
-
"grad_norm": 0.
|
| 1141 |
-
"learning_rate":
|
| 1142 |
-
"loss": 0.
|
| 1143 |
"step": 1440
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 5.350553505535055,
|
| 1147 |
-
"grad_norm": 0.
|
| 1148 |
-
"learning_rate":
|
| 1149 |
-
"loss": 0.
|
| 1150 |
"step": 1450
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 5.387453874538745,
|
| 1154 |
-
"grad_norm": 0.
|
| 1155 |
-
"learning_rate":
|
| 1156 |
-
"loss": 0.
|
| 1157 |
"step": 1460
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 5.424354243542435,
|
| 1161 |
-
"grad_norm": 0.
|
| 1162 |
-
"learning_rate":
|
| 1163 |
-
"loss": 0.
|
| 1164 |
"step": 1470
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 5.461254612546125,
|
| 1168 |
-
"grad_norm": 0.
|
| 1169 |
-
"learning_rate":
|
| 1170 |
-
"loss": 0.
|
| 1171 |
"step": 1480
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 5.498154981549815,
|
| 1175 |
-
"grad_norm": 0.
|
| 1176 |
-
"learning_rate":
|
| 1177 |
-
"loss": 0.
|
| 1178 |
"step": 1490
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
"epoch": 5.535055350553505,
|
| 1182 |
-
"grad_norm": 0.
|
| 1183 |
-
"learning_rate":
|
| 1184 |
-
"loss": 0.
|
| 1185 |
"step": 1500
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 5.535055350553505,
|
| 1189 |
-
"eval_accuracy": 0.
|
| 1190 |
-
"eval_loss": 0.
|
| 1191 |
-
"eval_runtime":
|
| 1192 |
-
"eval_samples_per_second":
|
| 1193 |
-
"eval_steps_per_second": 4.
|
| 1194 |
"step": 1500
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
"epoch": 5.571955719557195,
|
| 1198 |
-
"grad_norm": 0.
|
| 1199 |
-
"learning_rate":
|
| 1200 |
-
"loss": 0.
|
| 1201 |
"step": 1510
|
| 1202 |
},
|
| 1203 |
{
|
| 1204 |
"epoch": 5.608856088560886,
|
| 1205 |
-
"grad_norm": 0.
|
| 1206 |
-
"learning_rate":
|
| 1207 |
-
"loss": 0.
|
| 1208 |
"step": 1520
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
"epoch": 5.645756457564576,
|
| 1212 |
-
"grad_norm": 0.
|
| 1213 |
-
"learning_rate":
|
| 1214 |
-
"loss": 0.
|
| 1215 |
"step": 1530
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
"epoch": 5.682656826568266,
|
| 1219 |
-
"grad_norm": 0.
|
| 1220 |
-
"learning_rate":
|
| 1221 |
-
"loss": 0.
|
| 1222 |
"step": 1540
|
| 1223 |
},
|
| 1224 |
{
|
| 1225 |
"epoch": 5.719557195571956,
|
| 1226 |
-
"grad_norm": 0.
|
| 1227 |
-
"learning_rate":
|
| 1228 |
-
"loss": 0.
|
| 1229 |
"step": 1550
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
"epoch": 5.756457564575646,
|
| 1233 |
-
"grad_norm": 0.
|
| 1234 |
-
"learning_rate":
|
| 1235 |
-
"loss": 0.
|
| 1236 |
"step": 1560
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
"epoch": 5.793357933579336,
|
| 1240 |
-
"grad_norm": 0.
|
| 1241 |
-
"learning_rate":
|
| 1242 |
-
"loss": 0.
|
| 1243 |
"step": 1570
|
| 1244 |
},
|
| 1245 |
{
|
| 1246 |
"epoch": 5.830258302583026,
|
| 1247 |
-
"grad_norm": 0.
|
| 1248 |
-
"learning_rate":
|
| 1249 |
-
"loss": 0.
|
| 1250 |
"step": 1580
|
| 1251 |
},
|
| 1252 |
{
|
| 1253 |
"epoch": 5.867158671586716,
|
| 1254 |
-
"grad_norm": 0.
|
| 1255 |
-
"learning_rate":
|
| 1256 |
-
"loss": 0.
|
| 1257 |
"step": 1590
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 5.904059040590406,
|
| 1261 |
-
"grad_norm": 0.
|
| 1262 |
-
"learning_rate":
|
| 1263 |
-
"loss": 0.
|
| 1264 |
"step": 1600
|
| 1265 |
},
|
| 1266 |
{
|
| 1267 |
"epoch": 5.904059040590406,
|
| 1268 |
-
"eval_accuracy": 0.
|
| 1269 |
-
"eval_loss": 0.
|
| 1270 |
-
"eval_runtime":
|
| 1271 |
-
"eval_samples_per_second":
|
| 1272 |
-
"eval_steps_per_second": 4.
|
| 1273 |
"step": 1600
|
| 1274 |
},
|
| 1275 |
{
|
| 1276 |
"epoch": 5.940959409594096,
|
| 1277 |
-
"grad_norm": 0.
|
| 1278 |
-
"learning_rate":
|
| 1279 |
-
"loss": 0.
|
| 1280 |
"step": 1610
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
"epoch": 5.977859778597786,
|
| 1284 |
-
"grad_norm": 0.
|
| 1285 |
-
"learning_rate":
|
| 1286 |
-
"loss": 0.
|
| 1287 |
"step": 1620
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
"epoch": 6.014760147601476,
|
| 1291 |
-
"grad_norm": 0.
|
| 1292 |
-
"learning_rate":
|
| 1293 |
-
"loss": 0.
|
| 1294 |
"step": 1630
|
| 1295 |
},
|
| 1296 |
{
|
| 1297 |
"epoch": 6.051660516605166,
|
| 1298 |
-
"grad_norm": 0.
|
| 1299 |
-
"learning_rate":
|
| 1300 |
-
"loss": 0.
|
| 1301 |
"step": 1640
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
"epoch": 6.088560885608856,
|
| 1305 |
-
"grad_norm": 0.
|
| 1306 |
-
"learning_rate":
|
| 1307 |
-
"loss": 0.
|
| 1308 |
"step": 1650
|
| 1309 |
},
|
| 1310 |
{
|
| 1311 |
"epoch": 6.125461254612546,
|
| 1312 |
-
"grad_norm": 0.
|
| 1313 |
-
"learning_rate":
|
| 1314 |
-
"loss": 0.
|
| 1315 |
"step": 1660
|
| 1316 |
},
|
| 1317 |
{
|
| 1318 |
"epoch": 6.162361623616236,
|
| 1319 |
-
"grad_norm": 0.
|
| 1320 |
-
"learning_rate":
|
| 1321 |
-
"loss": 0.
|
| 1322 |
"step": 1670
|
| 1323 |
},
|
| 1324 |
{
|
| 1325 |
"epoch": 6.199261992619927,
|
| 1326 |
-
"grad_norm": 0.
|
| 1327 |
-
"learning_rate":
|
| 1328 |
-
"loss": 0.
|
| 1329 |
"step": 1680
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 6.236162361623617,
|
| 1333 |
-
"grad_norm": 0.
|
| 1334 |
-
"learning_rate":
|
| 1335 |
-
"loss": 0.
|
| 1336 |
"step": 1690
|
| 1337 |
},
|
| 1338 |
{
|
| 1339 |
"epoch": 6.273062730627307,
|
| 1340 |
-
"grad_norm": 0.
|
| 1341 |
-
"learning_rate":
|
| 1342 |
-
"loss": 0.
|
| 1343 |
"step": 1700
|
| 1344 |
},
|
| 1345 |
{
|
| 1346 |
"epoch": 6.273062730627307,
|
| 1347 |
-
"eval_accuracy": 0.
|
| 1348 |
-
"eval_loss": 0.
|
| 1349 |
-
"eval_runtime":
|
| 1350 |
-
"eval_samples_per_second":
|
| 1351 |
-
"eval_steps_per_second": 4.
|
| 1352 |
"step": 1700
|
| 1353 |
},
|
| 1354 |
{
|
| 1355 |
"epoch": 6.3099630996309966,
|
| 1356 |
-
"grad_norm": 0.
|
| 1357 |
-
"learning_rate":
|
| 1358 |
-
"loss": 0.
|
| 1359 |
"step": 1710
|
| 1360 |
},
|
| 1361 |
{
|
| 1362 |
"epoch": 6.3468634686346865,
|
| 1363 |
-
"grad_norm": 0.
|
| 1364 |
-
"learning_rate":
|
| 1365 |
-
"loss": 0.
|
| 1366 |
"step": 1720
|
| 1367 |
},
|
| 1368 |
{
|
| 1369 |
"epoch": 6.3837638376383765,
|
| 1370 |
-
"grad_norm": 0.
|
| 1371 |
-
"learning_rate":
|
| 1372 |
-
"loss": 0.
|
| 1373 |
"step": 1730
|
| 1374 |
},
|
| 1375 |
{
|
| 1376 |
"epoch": 6.4206642066420665,
|
| 1377 |
-
"grad_norm": 0.
|
| 1378 |
-
"learning_rate":
|
| 1379 |
-
"loss": 0.
|
| 1380 |
"step": 1740
|
| 1381 |
},
|
| 1382 |
{
|
| 1383 |
"epoch": 6.4575645756457565,
|
| 1384 |
-
"grad_norm": 0.
|
| 1385 |
-
"learning_rate":
|
| 1386 |
-
"loss": 0.
|
| 1387 |
"step": 1750
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
"epoch": 6.4944649446494465,
|
| 1391 |
-
"grad_norm": 0.
|
| 1392 |
-
"learning_rate":
|
| 1393 |
-
"loss": 0.
|
| 1394 |
"step": 1760
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 6.531365313653136,
|
| 1398 |
-
"grad_norm": 0.
|
| 1399 |
-
"learning_rate":
|
| 1400 |
-
"loss": 0.
|
| 1401 |
"step": 1770
|
| 1402 |
},
|
| 1403 |
{
|
| 1404 |
"epoch": 6.568265682656826,
|
| 1405 |
-
"grad_norm": 0.
|
| 1406 |
-
"learning_rate":
|
| 1407 |
-
"loss": 0.
|
| 1408 |
"step": 1780
|
| 1409 |
},
|
| 1410 |
{
|
| 1411 |
"epoch": 6.605166051660516,
|
| 1412 |
-
"grad_norm": 0.
|
| 1413 |
-
"learning_rate":
|
| 1414 |
-
"loss": 0.
|
| 1415 |
"step": 1790
|
| 1416 |
},
|
| 1417 |
{
|
| 1418 |
"epoch": 6.642066420664206,
|
| 1419 |
-
"grad_norm": 0.
|
| 1420 |
-
"learning_rate":
|
| 1421 |
-
"loss": 0.
|
| 1422 |
"step": 1800
|
| 1423 |
},
|
| 1424 |
{
|
| 1425 |
"epoch": 6.642066420664206,
|
| 1426 |
-
"eval_accuracy": 0.
|
| 1427 |
-
"eval_loss": 0.
|
| 1428 |
-
"eval_runtime":
|
| 1429 |
-
"eval_samples_per_second":
|
| 1430 |
-
"eval_steps_per_second": 4.
|
| 1431 |
"step": 1800
|
| 1432 |
},
|
| 1433 |
{
|
| 1434 |
"epoch": 6.678966789667896,
|
| 1435 |
-
"grad_norm": 0.
|
| 1436 |
-
"learning_rate":
|
| 1437 |
-
"loss": 0.
|
| 1438 |
"step": 1810
|
| 1439 |
},
|
| 1440 |
{
|
| 1441 |
"epoch": 6.715867158671586,
|
| 1442 |
-
"grad_norm": 0.
|
| 1443 |
-
"learning_rate":
|
| 1444 |
-
"loss": 0.
|
| 1445 |
"step": 1820
|
| 1446 |
},
|
| 1447 |
{
|
| 1448 |
"epoch": 6.752767527675276,
|
| 1449 |
-
"grad_norm": 0.
|
| 1450 |
-
"learning_rate":
|
| 1451 |
-
"loss": 0.
|
| 1452 |
"step": 1830
|
| 1453 |
},
|
| 1454 |
{
|
| 1455 |
"epoch": 6.789667896678967,
|
| 1456 |
-
"grad_norm": 0.
|
| 1457 |
-
"learning_rate":
|
| 1458 |
-
"loss": 0.
|
| 1459 |
"step": 1840
|
| 1460 |
},
|
| 1461 |
{
|
| 1462 |
"epoch": 6.826568265682657,
|
| 1463 |
-
"grad_norm": 0.
|
| 1464 |
-
"learning_rate":
|
| 1465 |
-
"loss": 0.
|
| 1466 |
"step": 1850
|
| 1467 |
},
|
| 1468 |
{
|
| 1469 |
"epoch": 6.863468634686347,
|
| 1470 |
-
"grad_norm": 0.
|
| 1471 |
-
"learning_rate":
|
| 1472 |
-
"loss": 0.
|
| 1473 |
"step": 1860
|
| 1474 |
},
|
| 1475 |
{
|
| 1476 |
"epoch": 6.900369003690037,
|
| 1477 |
-
"grad_norm": 0.
|
| 1478 |
-
"learning_rate":
|
| 1479 |
-
"loss": 0.
|
| 1480 |
"step": 1870
|
| 1481 |
},
|
| 1482 |
{
|
| 1483 |
"epoch": 6.937269372693727,
|
| 1484 |
-
"grad_norm": 0.
|
| 1485 |
-
"learning_rate":
|
| 1486 |
-
"loss": 0.
|
| 1487 |
"step": 1880
|
| 1488 |
},
|
| 1489 |
{
|
| 1490 |
"epoch": 6.974169741697417,
|
| 1491 |
-
"grad_norm": 0.
|
| 1492 |
-
"learning_rate":
|
| 1493 |
-
"loss": 0.
|
| 1494 |
"step": 1890
|
| 1495 |
},
|
| 1496 |
{
|
| 1497 |
"epoch": 7.011070110701107,
|
| 1498 |
-
"grad_norm": 0.
|
| 1499 |
-
"learning_rate":
|
| 1500 |
-
"loss": 0.
|
| 1501 |
"step": 1900
|
| 1502 |
},
|
| 1503 |
{
|
| 1504 |
"epoch": 7.011070110701107,
|
| 1505 |
-
"eval_accuracy": 0
|
| 1506 |
-
"eval_loss": 0.
|
| 1507 |
-
"eval_runtime":
|
| 1508 |
-
"eval_samples_per_second":
|
| 1509 |
-
"eval_steps_per_second": 4.
|
| 1510 |
"step": 1900
|
| 1511 |
},
|
| 1512 |
{
|
| 1513 |
"epoch": 7.047970479704797,
|
| 1514 |
-
"grad_norm": 0.
|
| 1515 |
-
"learning_rate":
|
| 1516 |
-
"loss": 0.
|
| 1517 |
"step": 1910
|
| 1518 |
},
|
| 1519 |
{
|
| 1520 |
"epoch": 7.084870848708487,
|
| 1521 |
-
"grad_norm": 0.
|
| 1522 |
-
"learning_rate":
|
| 1523 |
-
"loss": 0.
|
| 1524 |
"step": 1920
|
| 1525 |
},
|
| 1526 |
{
|
| 1527 |
"epoch": 7.121771217712177,
|
| 1528 |
-
"grad_norm": 0.
|
| 1529 |
-
"learning_rate":
|
| 1530 |
-
"loss": 0.
|
| 1531 |
"step": 1930
|
| 1532 |
},
|
| 1533 |
{
|
| 1534 |
"epoch": 7.158671586715867,
|
| 1535 |
-
"grad_norm": 0.
|
| 1536 |
-
"learning_rate":
|
| 1537 |
-
"loss": 0.
|
| 1538 |
"step": 1940
|
| 1539 |
},
|
| 1540 |
{
|
| 1541 |
"epoch": 7.195571955719557,
|
| 1542 |
-
"grad_norm": 0.
|
| 1543 |
-
"learning_rate":
|
| 1544 |
-
"loss": 0.
|
| 1545 |
"step": 1950
|
| 1546 |
},
|
| 1547 |
{
|
| 1548 |
"epoch": 7.232472324723247,
|
| 1549 |
-
"grad_norm": 0.
|
| 1550 |
-
"learning_rate":
|
| 1551 |
-
"loss": 0.
|
| 1552 |
"step": 1960
|
| 1553 |
},
|
| 1554 |
{
|
| 1555 |
"epoch": 7.269372693726937,
|
| 1556 |
-
"grad_norm": 0.
|
| 1557 |
-
"learning_rate":
|
| 1558 |
-
"loss": 0.
|
| 1559 |
"step": 1970
|
| 1560 |
},
|
| 1561 |
{
|
| 1562 |
"epoch": 7.306273062730627,
|
| 1563 |
-
"grad_norm": 0.
|
| 1564 |
-
"learning_rate":
|
| 1565 |
-
"loss": 0.
|
| 1566 |
"step": 1980
|
| 1567 |
},
|
| 1568 |
{
|
| 1569 |
"epoch": 7.343173431734318,
|
| 1570 |
-
"grad_norm": 0.
|
| 1571 |
-
"learning_rate":
|
| 1572 |
-
"loss": 0.
|
| 1573 |
"step": 1990
|
| 1574 |
},
|
| 1575 |
{
|
| 1576 |
"epoch": 7.380073800738008,
|
| 1577 |
-
"grad_norm": 0.
|
| 1578 |
-
"learning_rate":
|
| 1579 |
-
"loss": 0.
|
| 1580 |
"step": 2000
|
| 1581 |
},
|
| 1582 |
{
|
| 1583 |
"epoch": 7.380073800738008,
|
| 1584 |
-
"eval_accuracy": 0
|
| 1585 |
-
"eval_loss": 0.
|
| 1586 |
-
"eval_runtime":
|
| 1587 |
-
"eval_samples_per_second":
|
| 1588 |
-
"eval_steps_per_second": 4.
|
| 1589 |
"step": 2000
|
| 1590 |
},
|
| 1591 |
{
|
| 1592 |
"epoch": 7.416974169741698,
|
| 1593 |
-
"grad_norm": 0.
|
| 1594 |
-
"learning_rate":
|
| 1595 |
-
"loss": 0.
|
| 1596 |
"step": 2010
|
| 1597 |
},
|
| 1598 |
{
|
| 1599 |
"epoch": 7.453874538745388,
|
| 1600 |
-
"grad_norm": 0.
|
| 1601 |
-
"learning_rate":
|
| 1602 |
-
"loss": 0.
|
| 1603 |
"step": 2020
|
| 1604 |
},
|
| 1605 |
{
|
| 1606 |
"epoch": 7.490774907749078,
|
| 1607 |
-
"grad_norm": 0.
|
| 1608 |
-
"learning_rate":
|
| 1609 |
-
"loss": 0.
|
| 1610 |
"step": 2030
|
| 1611 |
},
|
| 1612 |
{
|
| 1613 |
"epoch": 7.527675276752768,
|
| 1614 |
-
"grad_norm": 0.
|
| 1615 |
-
"learning_rate":
|
| 1616 |
-
"loss": 0.
|
| 1617 |
"step": 2040
|
| 1618 |
},
|
| 1619 |
{
|
| 1620 |
"epoch": 7.564575645756458,
|
| 1621 |
-
"grad_norm": 0.
|
| 1622 |
-
"learning_rate":
|
| 1623 |
-
"loss": 0.
|
| 1624 |
"step": 2050
|
| 1625 |
},
|
| 1626 |
{
|
| 1627 |
"epoch": 7.601476014760148,
|
| 1628 |
-
"grad_norm": 0.
|
| 1629 |
-
"learning_rate":
|
| 1630 |
-
"loss": 0.
|
| 1631 |
"step": 2060
|
| 1632 |
},
|
| 1633 |
{
|
| 1634 |
"epoch": 7.638376383763838,
|
| 1635 |
-
"grad_norm": 0.
|
| 1636 |
-
"learning_rate":
|
| 1637 |
-
"loss": 0.
|
| 1638 |
"step": 2070
|
| 1639 |
},
|
| 1640 |
{
|
| 1641 |
"epoch": 7.675276752767528,
|
| 1642 |
-
"grad_norm": 0.
|
| 1643 |
-
"learning_rate":
|
| 1644 |
-
"loss": 0.
|
| 1645 |
"step": 2080
|
| 1646 |
},
|
| 1647 |
{
|
| 1648 |
"epoch": 7.712177121771218,
|
| 1649 |
-
"grad_norm": 0.
|
| 1650 |
-
"learning_rate":
|
| 1651 |
-
"loss": 0.
|
| 1652 |
"step": 2090
|
| 1653 |
},
|
| 1654 |
{
|
| 1655 |
"epoch": 7.749077490774908,
|
| 1656 |
-
"grad_norm": 0.
|
| 1657 |
-
"learning_rate":
|
| 1658 |
-
"loss": 0.
|
| 1659 |
"step": 2100
|
| 1660 |
},
|
| 1661 |
{
|
| 1662 |
"epoch": 7.749077490774908,
|
| 1663 |
-
"eval_accuracy": 0
|
| 1664 |
-
"eval_loss": 0.
|
| 1665 |
-
"eval_runtime":
|
| 1666 |
-
"eval_samples_per_second":
|
| 1667 |
-
"eval_steps_per_second": 4.
|
| 1668 |
"step": 2100
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
"epoch": 7.785977859778598,
|
| 1672 |
-
"grad_norm": 0.
|
| 1673 |
-
"learning_rate":
|
| 1674 |
-
"loss": 0.
|
| 1675 |
"step": 2110
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
"epoch": 7.822878228782288,
|
| 1679 |
-
"grad_norm": 0.
|
| 1680 |
-
"learning_rate":
|
| 1681 |
-
"loss": 0.
|
| 1682 |
"step": 2120
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 7.8597785977859775,
|
| 1686 |
-
"grad_norm": 0.
|
| 1687 |
-
"learning_rate":
|
| 1688 |
-
"loss": 0.
|
| 1689 |
"step": 2130
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
"epoch": 7.8966789667896675,
|
| 1693 |
-
"grad_norm": 0.
|
| 1694 |
-
"learning_rate": 2.
|
| 1695 |
-
"loss": 0.
|
| 1696 |
"step": 2140
|
| 1697 |
},
|
| 1698 |
{
|
| 1699 |
"epoch": 7.9335793357933575,
|
| 1700 |
-
"grad_norm": 0.
|
| 1701 |
-
"learning_rate":
|
| 1702 |
-
"loss": 0.
|
| 1703 |
"step": 2150
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
"epoch": 7.970479704797048,
|
| 1707 |
-
"grad_norm": 0.
|
| 1708 |
-
"learning_rate":
|
| 1709 |
-
"loss": 0.
|
| 1710 |
"step": 2160
|
| 1711 |
},
|
| 1712 |
{
|
| 1713 |
-
"epoch": 8.
|
| 1714 |
-
"
|
| 1715 |
-
"
|
| 1716 |
-
"
|
| 1717 |
-
"
|
| 1718 |
-
|
| 1719 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1720 |
}
|
| 1721 |
],
|
| 1722 |
"logging_steps": 10,
|
| 1723 |
-
"max_steps":
|
| 1724 |
"num_input_tokens_seen": 0,
|
| 1725 |
-
"num_train_epochs":
|
| 1726 |
"save_steps": 100,
|
| 1727 |
"stateful_callbacks": {
|
| 1728 |
"TrainerControl": {
|
|
@@ -1736,7 +1952,7 @@
|
|
| 1736 |
"attributes": {}
|
| 1737 |
}
|
| 1738 |
},
|
| 1739 |
-
"total_flos":
|
| 1740 |
"train_batch_size": 16,
|
| 1741 |
"trial_name": null,
|
| 1742 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.0013051489368081093,
|
| 3 |
+
"best_model_checkpoint": "./ViT-NIH-Chest-X-ray-dataset-small/checkpoint-2400",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 2439,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.03690036900369004,
|
| 13 |
+
"grad_norm": 1.528047800064087,
|
| 14 |
+
"learning_rate": 0.000199179991799918,
|
| 15 |
+
"loss": 0.0667,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.07380073800738007,
|
| 20 |
+
"grad_norm": 0.4356657862663269,
|
| 21 |
+
"learning_rate": 0.000198359983599836,
|
| 22 |
+
"loss": 0.0497,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.11070110701107011,
|
| 27 |
+
"grad_norm": 0.7035173177719116,
|
| 28 |
+
"learning_rate": 0.000197539975399754,
|
| 29 |
+
"loss": 0.0452,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.14760147601476015,
|
| 34 |
+
"grad_norm": 0.6605591773986816,
|
| 35 |
+
"learning_rate": 0.000196719967199672,
|
| 36 |
+
"loss": 0.0513,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.18450184501845018,
|
| 41 |
+
"grad_norm": 0.3567582964897156,
|
| 42 |
+
"learning_rate": 0.00019589995899959,
|
| 43 |
+
"loss": 0.0582,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.22140221402214022,
|
| 48 |
+
"grad_norm": 0.8019290566444397,
|
| 49 |
+
"learning_rate": 0.000195079950799508,
|
| 50 |
+
"loss": 0.066,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.25830258302583026,
|
| 55 |
+
"grad_norm": 0.3395977020263672,
|
| 56 |
+
"learning_rate": 0.000194259942599426,
|
| 57 |
+
"loss": 0.0461,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.2952029520295203,
|
| 62 |
+
"grad_norm": 1.1884530782699585,
|
| 63 |
+
"learning_rate": 0.000193439934399344,
|
| 64 |
+
"loss": 0.055,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 0.33210332103321033,
|
| 69 |
+
"grad_norm": 0.3934822082519531,
|
| 70 |
+
"learning_rate": 0.000192619926199262,
|
| 71 |
+
"loss": 0.0341,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 0.36900369003690037,
|
| 76 |
+
"grad_norm": 0.19823391735553741,
|
| 77 |
+
"learning_rate": 0.00019179991799918,
|
| 78 |
+
"loss": 0.0271,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 0.36900369003690037,
|
| 83 |
+
"eval_accuracy": 0.8583815028901735,
|
| 84 |
+
"eval_loss": 0.03472097963094711,
|
| 85 |
+
"eval_runtime": 53.2441,
|
| 86 |
+
"eval_samples_per_second": 32.492,
|
| 87 |
+
"eval_steps_per_second": 4.076,
|
| 88 |
"step": 100
|
| 89 |
},
|
| 90 |
{
|
| 91 |
"epoch": 0.4059040590405904,
|
| 92 |
+
"grad_norm": 0.6334025859832764,
|
| 93 |
+
"learning_rate": 0.00019097990979909799,
|
| 94 |
+
"loss": 0.0347,
|
| 95 |
"step": 110
|
| 96 |
},
|
| 97 |
{
|
| 98 |
"epoch": 0.44280442804428044,
|
| 99 |
+
"grad_norm": 0.4480656683444977,
|
| 100 |
+
"learning_rate": 0.000190159901599016,
|
| 101 |
+
"loss": 0.038,
|
| 102 |
"step": 120
|
| 103 |
},
|
| 104 |
{
|
| 105 |
"epoch": 0.4797047970479705,
|
| 106 |
+
"grad_norm": 0.35815778374671936,
|
| 107 |
+
"learning_rate": 0.000189339893398934,
|
| 108 |
+
"loss": 0.0308,
|
| 109 |
"step": 130
|
| 110 |
},
|
| 111 |
{
|
| 112 |
"epoch": 0.5166051660516605,
|
| 113 |
+
"grad_norm": 0.5924233794212341,
|
| 114 |
+
"learning_rate": 0.000188519885198852,
|
| 115 |
+
"loss": 0.0329,
|
| 116 |
"step": 140
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.5535055350553506,
|
| 120 |
+
"grad_norm": 0.8932539224624634,
|
| 121 |
+
"learning_rate": 0.00018769987699876998,
|
| 122 |
+
"loss": 0.0447,
|
| 123 |
"step": 150
|
| 124 |
},
|
| 125 |
{
|
| 126 |
"epoch": 0.5904059040590406,
|
| 127 |
+
"grad_norm": 0.4765835702419281,
|
| 128 |
+
"learning_rate": 0.000186879868798688,
|
| 129 |
+
"loss": 0.0335,
|
| 130 |
"step": 160
|
| 131 |
},
|
| 132 |
{
|
| 133 |
"epoch": 0.6273062730627307,
|
| 134 |
+
"grad_norm": 1.848928451538086,
|
| 135 |
+
"learning_rate": 0.00018605986059860597,
|
| 136 |
+
"loss": 0.0353,
|
| 137 |
"step": 170
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 0.6642066420664207,
|
| 141 |
+
"grad_norm": 0.5017064809799194,
|
| 142 |
+
"learning_rate": 0.000185239852398524,
|
| 143 |
+
"loss": 0.0365,
|
| 144 |
"step": 180
|
| 145 |
},
|
| 146 |
{
|
| 147 |
"epoch": 0.7011070110701108,
|
| 148 |
+
"grad_norm": 0.4620348811149597,
|
| 149 |
+
"learning_rate": 0.00018441984419844198,
|
| 150 |
+
"loss": 0.0284,
|
| 151 |
"step": 190
|
| 152 |
},
|
| 153 |
{
|
| 154 |
"epoch": 0.7380073800738007,
|
| 155 |
+
"grad_norm": 0.716968834400177,
|
| 156 |
+
"learning_rate": 0.00018359983599836,
|
| 157 |
+
"loss": 0.0334,
|
| 158 |
"step": 200
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 0.7380073800738007,
|
| 162 |
+
"eval_accuracy": 0.8624277456647399,
|
| 163 |
+
"eval_loss": 0.02910423092544079,
|
| 164 |
+
"eval_runtime": 53.0242,
|
| 165 |
+
"eval_samples_per_second": 32.627,
|
| 166 |
+
"eval_steps_per_second": 4.092,
|
| 167 |
"step": 200
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 0.7749077490774908,
|
| 171 |
+
"grad_norm": 0.6060870289802551,
|
| 172 |
+
"learning_rate": 0.00018277982779827797,
|
| 173 |
+
"loss": 0.0383,
|
| 174 |
"step": 210
|
| 175 |
},
|
| 176 |
{
|
| 177 |
"epoch": 0.8118081180811808,
|
| 178 |
+
"grad_norm": 1.053126335144043,
|
| 179 |
+
"learning_rate": 0.000181959819598196,
|
| 180 |
+
"loss": 0.0521,
|
| 181 |
"step": 220
|
| 182 |
},
|
| 183 |
{
|
| 184 |
"epoch": 0.8487084870848709,
|
| 185 |
+
"grad_norm": 0.48799070715904236,
|
| 186 |
+
"learning_rate": 0.00018113981139811398,
|
| 187 |
+
"loss": 0.0529,
|
| 188 |
"step": 230
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.8856088560885609,
|
| 192 |
+
"grad_norm": 0.8857760429382324,
|
| 193 |
+
"learning_rate": 0.00018031980319803198,
|
| 194 |
+
"loss": 0.0359,
|
| 195 |
"step": 240
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.922509225092251,
|
| 199 |
+
"grad_norm": 0.2952769696712494,
|
| 200 |
+
"learning_rate": 0.00017949979499794997,
|
| 201 |
+
"loss": 0.0457,
|
| 202 |
"step": 250
|
| 203 |
},
|
| 204 |
{
|
| 205 |
"epoch": 0.959409594095941,
|
| 206 |
+
"grad_norm": 0.39872637391090393,
|
| 207 |
+
"learning_rate": 0.000178679786797868,
|
| 208 |
+
"loss": 0.0573,
|
| 209 |
"step": 260
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 0.996309963099631,
|
| 213 |
+
"grad_norm": 0.5376998782157898,
|
| 214 |
+
"learning_rate": 0.00017785977859778598,
|
| 215 |
+
"loss": 0.0352,
|
| 216 |
"step": 270
|
| 217 |
},
|
| 218 |
{
|
| 219 |
"epoch": 1.033210332103321,
|
| 220 |
+
"grad_norm": 0.32833996415138245,
|
| 221 |
+
"learning_rate": 0.00017703977039770397,
|
| 222 |
+
"loss": 0.0444,
|
| 223 |
"step": 280
|
| 224 |
},
|
| 225 |
{
|
| 226 |
"epoch": 1.070110701107011,
|
| 227 |
+
"grad_norm": 0.6235490441322327,
|
| 228 |
+
"learning_rate": 0.00017621976219762197,
|
| 229 |
+
"loss": 0.0347,
|
| 230 |
"step": 290
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 1.1070110701107012,
|
| 234 |
+
"grad_norm": 0.612684428691864,
|
| 235 |
+
"learning_rate": 0.00017539975399754,
|
| 236 |
+
"loss": 0.0438,
|
| 237 |
"step": 300
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 1.1070110701107012,
|
| 241 |
+
"eval_accuracy": 0.8606936416184972,
|
| 242 |
+
"eval_loss": 0.03517782315611839,
|
| 243 |
+
"eval_runtime": 53.0738,
|
| 244 |
+
"eval_samples_per_second": 32.596,
|
| 245 |
+
"eval_steps_per_second": 4.089,
|
| 246 |
"step": 300
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 1.1439114391143912,
|
| 250 |
+
"grad_norm": 0.29079392552375793,
|
| 251 |
+
"learning_rate": 0.00017457974579745798,
|
| 252 |
+
"loss": 0.0546,
|
| 253 |
"step": 310
|
| 254 |
},
|
| 255 |
{
|
| 256 |
"epoch": 1.1808118081180812,
|
| 257 |
+
"grad_norm": 0.3669208884239197,
|
| 258 |
+
"learning_rate": 0.00017375973759737597,
|
| 259 |
+
"loss": 0.03,
|
| 260 |
"step": 320
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 1.2177121771217712,
|
| 264 |
+
"grad_norm": 0.27689820528030396,
|
| 265 |
+
"learning_rate": 0.00017293972939729397,
|
| 266 |
+
"loss": 0.0287,
|
| 267 |
"step": 330
|
| 268 |
},
|
| 269 |
{
|
| 270 |
"epoch": 1.2546125461254611,
|
| 271 |
+
"grad_norm": 0.2193935513496399,
|
| 272 |
+
"learning_rate": 0.00017211972119721199,
|
| 273 |
+
"loss": 0.0336,
|
| 274 |
"step": 340
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 1.2915129151291513,
|
| 278 |
+
"grad_norm": 0.1442354917526245,
|
| 279 |
+
"learning_rate": 0.00017129971299712998,
|
| 280 |
+
"loss": 0.0301,
|
| 281 |
"step": 350
|
| 282 |
},
|
| 283 |
{
|
| 284 |
"epoch": 1.3284132841328413,
|
| 285 |
+
"grad_norm": 0.49084681272506714,
|
| 286 |
+
"learning_rate": 0.00017047970479704797,
|
| 287 |
+
"loss": 0.0383,
|
| 288 |
"step": 360
|
| 289 |
},
|
| 290 |
{
|
| 291 |
"epoch": 1.3653136531365313,
|
| 292 |
+
"grad_norm": 0.6412920951843262,
|
| 293 |
+
"learning_rate": 0.00016965969659696597,
|
| 294 |
+
"loss": 0.0338,
|
| 295 |
"step": 370
|
| 296 |
},
|
| 297 |
{
|
| 298 |
"epoch": 1.4022140221402215,
|
| 299 |
+
"grad_norm": 0.5825220942497253,
|
| 300 |
+
"learning_rate": 0.00016883968839688399,
|
| 301 |
+
"loss": 0.0344,
|
| 302 |
"step": 380
|
| 303 |
},
|
| 304 |
{
|
| 305 |
"epoch": 1.4391143911439115,
|
| 306 |
+
"grad_norm": 0.5842616558074951,
|
| 307 |
+
"learning_rate": 0.00016801968019680198,
|
| 308 |
+
"loss": 0.0358,
|
| 309 |
"step": 390
|
| 310 |
},
|
| 311 |
{
|
| 312 |
"epoch": 1.4760147601476015,
|
| 313 |
+
"grad_norm": 0.17261776328086853,
|
| 314 |
+
"learning_rate": 0.00016719967199671997,
|
| 315 |
+
"loss": 0.0215,
|
| 316 |
"step": 400
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 1.4760147601476015,
|
| 320 |
+
"eval_accuracy": 0.8745664739884393,
|
| 321 |
+
"eval_loss": 0.03190147876739502,
|
| 322 |
+
"eval_runtime": 53.163,
|
| 323 |
+
"eval_samples_per_second": 32.541,
|
| 324 |
+
"eval_steps_per_second": 4.082,
|
| 325 |
"step": 400
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 1.5129151291512914,
|
| 329 |
+
"grad_norm": 0.42338722944259644,
|
| 330 |
+
"learning_rate": 0.00016637966379663796,
|
| 331 |
+
"loss": 0.0343,
|
| 332 |
"step": 410
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 1.5498154981549814,
|
| 336 |
+
"grad_norm": 0.6431716680526733,
|
| 337 |
+
"learning_rate": 0.00016555965559655598,
|
| 338 |
+
"loss": 0.0308,
|
| 339 |
"step": 420
|
| 340 |
},
|
| 341 |
{
|
| 342 |
"epoch": 1.5867158671586716,
|
| 343 |
+
"grad_norm": 0.9911162257194519,
|
| 344 |
+
"learning_rate": 0.00016473964739647395,
|
| 345 |
+
"loss": 0.0357,
|
| 346 |
"step": 430
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.6236162361623616,
|
| 350 |
+
"grad_norm": 0.7283934354782104,
|
| 351 |
+
"learning_rate": 0.00016391963919639197,
|
| 352 |
+
"loss": 0.0548,
|
| 353 |
"step": 440
|
| 354 |
},
|
| 355 |
{
|
| 356 |
"epoch": 1.6605166051660518,
|
| 357 |
+
"grad_norm": 0.3784200847148895,
|
| 358 |
+
"learning_rate": 0.00016309963099630996,
|
| 359 |
+
"loss": 0.0411,
|
| 360 |
"step": 450
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 1.6974169741697418,
|
| 364 |
+
"grad_norm": 0.4938986599445343,
|
| 365 |
+
"learning_rate": 0.00016227962279622798,
|
| 366 |
+
"loss": 0.0384,
|
| 367 |
"step": 460
|
| 368 |
},
|
| 369 |
{
|
| 370 |
"epoch": 1.7343173431734318,
|
| 371 |
+
"grad_norm": 0.7969509363174438,
|
| 372 |
+
"learning_rate": 0.00016145961459614595,
|
| 373 |
+
"loss": 0.0282,
|
| 374 |
"step": 470
|
| 375 |
},
|
| 376 |
{
|
| 377 |
"epoch": 1.7712177121771218,
|
| 378 |
+
"grad_norm": 0.7997636198997498,
|
| 379 |
+
"learning_rate": 0.00016063960639606397,
|
| 380 |
+
"loss": 0.0299,
|
| 381 |
"step": 480
|
| 382 |
},
|
| 383 |
{
|
| 384 |
"epoch": 1.8081180811808117,
|
| 385 |
+
"grad_norm": 0.13115979731082916,
|
| 386 |
+
"learning_rate": 0.00015981959819598196,
|
| 387 |
+
"loss": 0.0361,
|
| 388 |
"step": 490
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.8450184501845017,
|
| 392 |
+
"grad_norm": 0.9753024578094482,
|
| 393 |
+
"learning_rate": 0.00015899958999589995,
|
| 394 |
+
"loss": 0.0267,
|
| 395 |
"step": 500
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 1.8450184501845017,
|
| 399 |
+
"eval_accuracy": 0.8797687861271676,
|
| 400 |
+
"eval_loss": 0.02772846817970276,
|
| 401 |
+
"eval_runtime": 52.9913,
|
| 402 |
+
"eval_samples_per_second": 32.647,
|
| 403 |
+
"eval_steps_per_second": 4.095,
|
| 404 |
"step": 500
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 1.881918819188192,
|
| 408 |
+
"grad_norm": 0.5084354877471924,
|
| 409 |
+
"learning_rate": 0.00015817958179581795,
|
| 410 |
+
"loss": 0.0432,
|
| 411 |
"step": 510
|
| 412 |
},
|
| 413 |
{
|
| 414 |
"epoch": 1.918819188191882,
|
| 415 |
+
"grad_norm": 0.2513779103755951,
|
| 416 |
+
"learning_rate": 0.00015735957359573597,
|
| 417 |
+
"loss": 0.034,
|
| 418 |
"step": 520
|
| 419 |
},
|
| 420 |
{
|
| 421 |
"epoch": 1.9557195571955721,
|
| 422 |
+
"grad_norm": 0.284483402967453,
|
| 423 |
+
"learning_rate": 0.00015653956539565396,
|
| 424 |
+
"loss": 0.0492,
|
| 425 |
"step": 530
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 1.992619926199262,
|
| 429 |
+
"grad_norm": 0.3686124086380005,
|
| 430 |
+
"learning_rate": 0.00015571955719557195,
|
| 431 |
+
"loss": 0.0313,
|
| 432 |
"step": 540
|
| 433 |
},
|
| 434 |
{
|
| 435 |
"epoch": 2.029520295202952,
|
| 436 |
+
"grad_norm": 0.49193885922431946,
|
| 437 |
+
"learning_rate": 0.00015489954899548995,
|
| 438 |
+
"loss": 0.0346,
|
| 439 |
"step": 550
|
| 440 |
},
|
| 441 |
{
|
| 442 |
"epoch": 2.066420664206642,
|
| 443 |
+
"grad_norm": 0.48066815733909607,
|
| 444 |
+
"learning_rate": 0.00015407954079540797,
|
| 445 |
+
"loss": 0.0204,
|
| 446 |
"step": 560
|
| 447 |
},
|
| 448 |
{
|
| 449 |
"epoch": 2.103321033210332,
|
| 450 |
+
"grad_norm": 0.4960450530052185,
|
| 451 |
+
"learning_rate": 0.00015325953259532596,
|
| 452 |
+
"loss": 0.0208,
|
| 453 |
"step": 570
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 2.140221402214022,
|
| 457 |
+
"grad_norm": 0.3585696220397949,
|
| 458 |
+
"learning_rate": 0.00015243952439524395,
|
| 459 |
+
"loss": 0.0226,
|
| 460 |
"step": 580
|
| 461 |
},
|
| 462 |
{
|
| 463 |
"epoch": 2.177121771217712,
|
| 464 |
+
"grad_norm": 0.383513480424881,
|
| 465 |
+
"learning_rate": 0.00015161951619516195,
|
| 466 |
+
"loss": 0.024,
|
| 467 |
"step": 590
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 2.2140221402214024,
|
| 471 |
+
"grad_norm": 0.45566025376319885,
|
| 472 |
+
"learning_rate": 0.00015079950799507997,
|
| 473 |
+
"loss": 0.0266,
|
| 474 |
"step": 600
|
| 475 |
},
|
| 476 |
{
|
| 477 |
"epoch": 2.2140221402214024,
|
| 478 |
+
"eval_accuracy": 0.9115606936416185,
|
| 479 |
+
"eval_loss": 0.017673172056674957,
|
| 480 |
+
"eval_runtime": 53.2922,
|
| 481 |
+
"eval_samples_per_second": 32.463,
|
| 482 |
+
"eval_steps_per_second": 4.072,
|
| 483 |
"step": 600
|
| 484 |
},
|
| 485 |
{
|
| 486 |
"epoch": 2.2509225092250924,
|
| 487 |
+
"grad_norm": 0.09787905216217041,
|
| 488 |
+
"learning_rate": 0.00014997949979499796,
|
| 489 |
+
"loss": 0.0173,
|
| 490 |
"step": 610
|
| 491 |
},
|
| 492 |
{
|
| 493 |
"epoch": 2.2878228782287824,
|
| 494 |
+
"grad_norm": 0.4203137159347534,
|
| 495 |
+
"learning_rate": 0.00014915949159491595,
|
| 496 |
+
"loss": 0.0208,
|
| 497 |
"step": 620
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 2.3247232472324724,
|
| 501 |
+
"grad_norm": 0.27736109495162964,
|
| 502 |
+
"learning_rate": 0.00014833948339483394,
|
| 503 |
+
"loss": 0.019,
|
| 504 |
"step": 630
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 2.3616236162361623,
|
| 508 |
+
"grad_norm": 0.1169864758849144,
|
| 509 |
+
"learning_rate": 0.00014751947519475196,
|
| 510 |
+
"loss": 0.0144,
|
| 511 |
"step": 640
|
| 512 |
},
|
| 513 |
{
|
| 514 |
"epoch": 2.3985239852398523,
|
| 515 |
+
"grad_norm": 0.4632050096988678,
|
| 516 |
+
"learning_rate": 0.00014669946699466993,
|
| 517 |
+
"loss": 0.022,
|
| 518 |
"step": 650
|
| 519 |
},
|
| 520 |
{
|
| 521 |
"epoch": 2.4354243542435423,
|
| 522 |
+
"grad_norm": 0.25868573784828186,
|
| 523 |
+
"learning_rate": 0.00014587945879458795,
|
| 524 |
+
"loss": 0.0225,
|
| 525 |
"step": 660
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 2.4723247232472323,
|
| 529 |
+
"grad_norm": 0.7463150024414062,
|
| 530 |
+
"learning_rate": 0.00014505945059450594,
|
| 531 |
+
"loss": 0.0218,
|
| 532 |
"step": 670
|
| 533 |
},
|
| 534 |
{
|
| 535 |
"epoch": 2.5092250922509223,
|
| 536 |
+
"grad_norm": 0.4195776581764221,
|
| 537 |
+
"learning_rate": 0.00014423944239442396,
|
| 538 |
+
"loss": 0.022,
|
| 539 |
"step": 680
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 2.5461254612546127,
|
| 543 |
+
"grad_norm": 1.2269337177276611,
|
| 544 |
+
"learning_rate": 0.00014341943419434193,
|
| 545 |
+
"loss": 0.0216,
|
| 546 |
"step": 690
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 2.5830258302583027,
|
| 550 |
+
"grad_norm": 0.44495096802711487,
|
| 551 |
+
"learning_rate": 0.00014259942599425995,
|
| 552 |
+
"loss": 0.014,
|
| 553 |
"step": 700
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 2.5830258302583027,
|
| 557 |
+
"eval_accuracy": 0.9497109826589596,
|
| 558 |
+
"eval_loss": 0.01273352187126875,
|
| 559 |
+
"eval_runtime": 53.0795,
|
| 560 |
+
"eval_samples_per_second": 32.593,
|
| 561 |
+
"eval_steps_per_second": 4.088,
|
| 562 |
"step": 700
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"epoch": 2.6199261992619927,
|
| 566 |
+
"grad_norm": 0.16129033267498016,
|
| 567 |
+
"learning_rate": 0.00014177941779417794,
|
| 568 |
+
"loss": 0.0211,
|
| 569 |
"step": 710
|
| 570 |
},
|
| 571 |
{
|
| 572 |
"epoch": 2.6568265682656826,
|
| 573 |
+
"grad_norm": 0.639427900314331,
|
| 574 |
+
"learning_rate": 0.00014095940959409593,
|
| 575 |
+
"loss": 0.0245,
|
| 576 |
"step": 720
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 2.6937269372693726,
|
| 580 |
+
"grad_norm": 1.1732105016708374,
|
| 581 |
+
"learning_rate": 0.00014013940139401393,
|
| 582 |
+
"loss": 0.0188,
|
| 583 |
"step": 730
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 2.7306273062730626,
|
| 587 |
+
"grad_norm": 0.15935984253883362,
|
| 588 |
+
"learning_rate": 0.00013931939319393195,
|
| 589 |
+
"loss": 0.0225,
|
| 590 |
"step": 740
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 2.767527675276753,
|
| 594 |
+
"grad_norm": 0.44544655084609985,
|
| 595 |
+
"learning_rate": 0.00013849938499384994,
|
| 596 |
+
"loss": 0.0181,
|
| 597 |
"step": 750
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 2.804428044280443,
|
| 601 |
+
"grad_norm": 0.04136790707707405,
|
| 602 |
+
"learning_rate": 0.00013767937679376793,
|
| 603 |
+
"loss": 0.0193,
|
| 604 |
"step": 760
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 2.841328413284133,
|
| 608 |
+
"grad_norm": 0.3928181231021881,
|
| 609 |
+
"learning_rate": 0.00013685936859368593,
|
| 610 |
+
"loss": 0.0314,
|
| 611 |
"step": 770
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 2.878228782287823,
|
| 615 |
+
"grad_norm": 0.4807884097099304,
|
| 616 |
+
"learning_rate": 0.00013603936039360395,
|
| 617 |
+
"loss": 0.0204,
|
| 618 |
"step": 780
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 2.915129151291513,
|
| 622 |
+
"grad_norm": 0.11494464427232742,
|
| 623 |
+
"learning_rate": 0.00013521935219352194,
|
| 624 |
+
"loss": 0.0163,
|
| 625 |
"step": 790
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 2.952029520295203,
|
| 629 |
+
"grad_norm": 0.4516555964946747,
|
| 630 |
+
"learning_rate": 0.00013439934399343993,
|
| 631 |
+
"loss": 0.0207,
|
| 632 |
"step": 800
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 2.952029520295203,
|
| 636 |
+
"eval_accuracy": 0.9410404624277456,
|
| 637 |
+
"eval_loss": 0.014368296600878239,
|
| 638 |
+
"eval_runtime": 53.187,
|
| 639 |
+
"eval_samples_per_second": 32.527,
|
| 640 |
+
"eval_steps_per_second": 4.08,
|
| 641 |
"step": 800
|
| 642 |
},
|
| 643 |
{
|
| 644 |
"epoch": 2.988929889298893,
|
| 645 |
+
"grad_norm": 0.25021785497665405,
|
| 646 |
+
"learning_rate": 0.00013357933579335793,
|
| 647 |
+
"loss": 0.018,
|
| 648 |
"step": 810
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 3.025830258302583,
|
| 652 |
+
"grad_norm": 0.6319343447685242,
|
| 653 |
+
"learning_rate": 0.00013275932759327595,
|
| 654 |
+
"loss": 0.0212,
|
| 655 |
"step": 820
|
| 656 |
},
|
| 657 |
{
|
| 658 |
"epoch": 3.062730627306273,
|
| 659 |
+
"grad_norm": 0.16027286648750305,
|
| 660 |
+
"learning_rate": 0.00013193931939319394,
|
| 661 |
+
"loss": 0.0119,
|
| 662 |
"step": 830
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 3.0996309963099633,
|
| 666 |
+
"grad_norm": 0.27029338479042053,
|
| 667 |
+
"learning_rate": 0.00013111931119311193,
|
| 668 |
+
"loss": 0.011,
|
| 669 |
"step": 840
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 3.1365313653136533,
|
| 673 |
+
"grad_norm": 0.3908526301383972,
|
| 674 |
+
"learning_rate": 0.00013029930299302992,
|
| 675 |
+
"loss": 0.0113,
|
| 676 |
"step": 850
|
| 677 |
},
|
| 678 |
{
|
| 679 |
"epoch": 3.1734317343173433,
|
| 680 |
+
"grad_norm": 0.08731468766927719,
|
| 681 |
+
"learning_rate": 0.00012947929479294794,
|
| 682 |
+
"loss": 0.0088,
|
| 683 |
"step": 860
|
| 684 |
},
|
| 685 |
{
|
| 686 |
"epoch": 3.2103321033210332,
|
| 687 |
+
"grad_norm": 0.19361713528633118,
|
| 688 |
+
"learning_rate": 0.00012865928659286594,
|
| 689 |
+
"loss": 0.0138,
|
| 690 |
"step": 870
|
| 691 |
},
|
| 692 |
{
|
| 693 |
"epoch": 3.2472324723247232,
|
| 694 |
+
"grad_norm": 0.11760518699884415,
|
| 695 |
+
"learning_rate": 0.00012783927839278393,
|
| 696 |
+
"loss": 0.0128,
|
| 697 |
"step": 880
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 3.284132841328413,
|
| 701 |
+
"grad_norm": 0.5687548518180847,
|
| 702 |
+
"learning_rate": 0.00012701927019270192,
|
| 703 |
+
"loss": 0.0114,
|
| 704 |
"step": 890
|
| 705 |
},
|
| 706 |
{
|
| 707 |
"epoch": 3.321033210332103,
|
| 708 |
+
"grad_norm": 0.35156571865081787,
|
| 709 |
+
"learning_rate": 0.00012619926199261994,
|
| 710 |
+
"loss": 0.0115,
|
| 711 |
"step": 900
|
| 712 |
},
|
| 713 |
{
|
| 714 |
"epoch": 3.321033210332103,
|
| 715 |
+
"eval_accuracy": 0.9653179190751445,
|
| 716 |
+
"eval_loss": 0.009723745286464691,
|
| 717 |
+
"eval_runtime": 53.0303,
|
| 718 |
+
"eval_samples_per_second": 32.623,
|
| 719 |
+
"eval_steps_per_second": 4.092,
|
| 720 |
"step": 900
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 3.357933579335793,
|
| 724 |
+
"grad_norm": 0.22674980759620667,
|
| 725 |
+
"learning_rate": 0.0001253792537925379,
|
| 726 |
+
"loss": 0.0126,
|
| 727 |
"step": 910
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 3.3948339483394836,
|
| 731 |
+
"grad_norm": 0.23142710328102112,
|
| 732 |
+
"learning_rate": 0.00012455924559245593,
|
| 733 |
+
"loss": 0.007,
|
| 734 |
"step": 920
|
| 735 |
},
|
| 736 |
{
|
| 737 |
"epoch": 3.4317343173431736,
|
| 738 |
+
"grad_norm": 0.11926586925983429,
|
| 739 |
+
"learning_rate": 0.00012373923739237392,
|
| 740 |
+
"loss": 0.0111,
|
| 741 |
"step": 930
|
| 742 |
},
|
| 743 |
{
|
| 744 |
"epoch": 3.4686346863468636,
|
| 745 |
+
"grad_norm": 0.12741585075855255,
|
| 746 |
+
"learning_rate": 0.00012291922919229194,
|
| 747 |
+
"loss": 0.0149,
|
| 748 |
"step": 940
|
| 749 |
},
|
| 750 |
{
|
| 751 |
"epoch": 3.5055350553505535,
|
| 752 |
+
"grad_norm": 0.8535834550857544,
|
| 753 |
+
"learning_rate": 0.0001220992209922099,
|
| 754 |
+
"loss": 0.0098,
|
| 755 |
"step": 950
|
| 756 |
},
|
| 757 |
{
|
| 758 |
"epoch": 3.5424354243542435,
|
| 759 |
+
"grad_norm": 0.2683662474155426,
|
| 760 |
+
"learning_rate": 0.00012127921279212793,
|
| 761 |
+
"loss": 0.0107,
|
| 762 |
"step": 960
|
| 763 |
},
|
| 764 |
{
|
| 765 |
"epoch": 3.5793357933579335,
|
| 766 |
+
"grad_norm": 0.2808018624782562,
|
| 767 |
+
"learning_rate": 0.00012045920459204592,
|
| 768 |
+
"loss": 0.0129,
|
| 769 |
"step": 970
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 3.6162361623616235,
|
| 773 |
+
"grad_norm": 1.0000771284103394,
|
| 774 |
+
"learning_rate": 0.00011963919639196393,
|
| 775 |
+
"loss": 0.0148,
|
| 776 |
"step": 980
|
| 777 |
},
|
| 778 |
{
|
| 779 |
"epoch": 3.6531365313653135,
|
| 780 |
+
"grad_norm": 0.16155269742012024,
|
| 781 |
+
"learning_rate": 0.00011881918819188192,
|
| 782 |
+
"loss": 0.0118,
|
| 783 |
"step": 990
|
| 784 |
},
|
| 785 |
{
|
| 786 |
"epoch": 3.6900369003690034,
|
| 787 |
+
"grad_norm": 0.053899142891168594,
|
| 788 |
+
"learning_rate": 0.00011799917999179993,
|
| 789 |
+
"loss": 0.0113,
|
| 790 |
"step": 1000
|
| 791 |
},
|
| 792 |
{
|
| 793 |
"epoch": 3.6900369003690034,
|
| 794 |
+
"eval_accuracy": 0.9710982658959537,
|
| 795 |
+
"eval_loss": 0.007686651311814785,
|
| 796 |
+
"eval_runtime": 52.7853,
|
| 797 |
+
"eval_samples_per_second": 32.774,
|
| 798 |
+
"eval_steps_per_second": 4.111,
|
| 799 |
"step": 1000
|
| 800 |
},
|
| 801 |
{
|
| 802 |
"epoch": 3.726937269372694,
|
| 803 |
+
"grad_norm": 0.23413535952568054,
|
| 804 |
+
"learning_rate": 0.0001171791717917179,
|
| 805 |
+
"loss": 0.0118,
|
| 806 |
"step": 1010
|
| 807 |
},
|
| 808 |
{
|
| 809 |
"epoch": 3.763837638376384,
|
| 810 |
+
"grad_norm": 0.19596587121486664,
|
| 811 |
+
"learning_rate": 0.00011635916359163593,
|
| 812 |
+
"loss": 0.0069,
|
| 813 |
"step": 1020
|
| 814 |
},
|
| 815 |
{
|
| 816 |
"epoch": 3.800738007380074,
|
| 817 |
+
"grad_norm": 0.28500398993492126,
|
| 818 |
+
"learning_rate": 0.0001155391553915539,
|
| 819 |
+
"loss": 0.009,
|
| 820 |
"step": 1030
|
| 821 |
},
|
| 822 |
{
|
| 823 |
"epoch": 3.837638376383764,
|
| 824 |
+
"grad_norm": 0.3002331554889679,
|
| 825 |
+
"learning_rate": 0.00011471914719147193,
|
| 826 |
+
"loss": 0.0096,
|
| 827 |
"step": 1040
|
| 828 |
},
|
| 829 |
{
|
| 830 |
"epoch": 3.874538745387454,
|
| 831 |
+
"grad_norm": 0.21130523085594177,
|
| 832 |
+
"learning_rate": 0.0001138991389913899,
|
| 833 |
+
"loss": 0.0122,
|
| 834 |
"step": 1050
|
| 835 |
},
|
| 836 |
{
|
| 837 |
"epoch": 3.911439114391144,
|
| 838 |
+
"grad_norm": 0.14506787061691284,
|
| 839 |
+
"learning_rate": 0.00011307913079130793,
|
| 840 |
+
"loss": 0.0095,
|
| 841 |
"step": 1060
|
| 842 |
},
|
| 843 |
{
|
| 844 |
"epoch": 3.948339483394834,
|
| 845 |
+
"grad_norm": 0.3295513987541199,
|
| 846 |
+
"learning_rate": 0.0001122591225912259,
|
| 847 |
+
"loss": 0.0122,
|
| 848 |
"step": 1070
|
| 849 |
},
|
| 850 |
{
|
| 851 |
"epoch": 3.985239852398524,
|
| 852 |
+
"grad_norm": 0.07300284504890442,
|
| 853 |
+
"learning_rate": 0.00011143911439114391,
|
| 854 |
+
"loss": 0.0067,
|
| 855 |
"step": 1080
|
| 856 |
},
|
| 857 |
{
|
| 858 |
"epoch": 4.022140221402214,
|
| 859 |
+
"grad_norm": 0.03413034602999687,
|
| 860 |
+
"learning_rate": 0.0001106191061910619,
|
| 861 |
+
"loss": 0.0119,
|
| 862 |
"step": 1090
|
| 863 |
},
|
| 864 |
{
|
| 865 |
"epoch": 4.059040590405904,
|
| 866 |
+
"grad_norm": 0.06467791646718979,
|
| 867 |
+
"learning_rate": 0.00010979909799097991,
|
| 868 |
+
"loss": 0.0054,
|
| 869 |
"step": 1100
|
| 870 |
},
|
| 871 |
{
|
| 872 |
"epoch": 4.059040590405904,
|
| 873 |
+
"eval_accuracy": 0.9843930635838151,
|
| 874 |
+
"eval_loss": 0.00683161336928606,
|
| 875 |
+
"eval_runtime": 52.9373,
|
| 876 |
+
"eval_samples_per_second": 32.68,
|
| 877 |
+
"eval_steps_per_second": 4.099,
|
| 878 |
"step": 1100
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 4.095940959409594,
|
| 882 |
+
"grad_norm": 0.09930551052093506,
|
| 883 |
+
"learning_rate": 0.0001089790897908979,
|
| 884 |
+
"loss": 0.0057,
|
| 885 |
"step": 1110
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 4.132841328413284,
|
| 889 |
+
"grad_norm": 0.11587420105934143,
|
| 890 |
+
"learning_rate": 0.00010815908159081591,
|
| 891 |
+
"loss": 0.0065,
|
| 892 |
"step": 1120
|
| 893 |
},
|
| 894 |
{
|
| 895 |
"epoch": 4.169741697416974,
|
| 896 |
+
"grad_norm": 0.042286355048418045,
|
| 897 |
+
"learning_rate": 0.0001073390733907339,
|
| 898 |
+
"loss": 0.0067,
|
| 899 |
"step": 1130
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 4.206642066420664,
|
| 903 |
+
"grad_norm": 0.16917578876018524,
|
| 904 |
+
"learning_rate": 0.00010651906519065191,
|
| 905 |
+
"loss": 0.0039,
|
| 906 |
"step": 1140
|
| 907 |
},
|
| 908 |
{
|
| 909 |
"epoch": 4.243542435424354,
|
| 910 |
+
"grad_norm": 0.16002944111824036,
|
| 911 |
+
"learning_rate": 0.0001056990569905699,
|
| 912 |
+
"loss": 0.0066,
|
| 913 |
"step": 1150
|
| 914 |
},
|
| 915 |
{
|
| 916 |
"epoch": 4.280442804428044,
|
| 917 |
+
"grad_norm": 0.049849651753902435,
|
| 918 |
+
"learning_rate": 0.00010487904879048791,
|
| 919 |
+
"loss": 0.0049,
|
| 920 |
"step": 1160
|
| 921 |
},
|
| 922 |
{
|
| 923 |
"epoch": 4.317343173431734,
|
| 924 |
+
"grad_norm": 0.5795335173606873,
|
| 925 |
+
"learning_rate": 0.0001040590405904059,
|
| 926 |
+
"loss": 0.007,
|
| 927 |
"step": 1170
|
| 928 |
},
|
| 929 |
{
|
| 930 |
"epoch": 4.354243542435424,
|
| 931 |
+
"grad_norm": 0.01594790630042553,
|
| 932 |
+
"learning_rate": 0.00010323903239032391,
|
| 933 |
+
"loss": 0.0062,
|
| 934 |
"step": 1180
|
| 935 |
},
|
| 936 |
{
|
| 937 |
"epoch": 4.391143911439114,
|
| 938 |
+
"grad_norm": 0.12844012677669525,
|
| 939 |
+
"learning_rate": 0.0001024190241902419,
|
| 940 |
+
"loss": 0.0045,
|
| 941 |
"step": 1190
|
| 942 |
},
|
| 943 |
{
|
| 944 |
"epoch": 4.428044280442805,
|
| 945 |
+
"grad_norm": 0.053635355085134506,
|
| 946 |
+
"learning_rate": 0.00010159901599015991,
|
| 947 |
+
"loss": 0.0047,
|
| 948 |
"step": 1200
|
| 949 |
},
|
| 950 |
{
|
| 951 |
"epoch": 4.428044280442805,
|
| 952 |
+
"eval_accuracy": 0.9849710982658959,
|
| 953 |
+
"eval_loss": 0.004636078607290983,
|
| 954 |
+
"eval_runtime": 52.7596,
|
| 955 |
+
"eval_samples_per_second": 32.79,
|
| 956 |
+
"eval_steps_per_second": 4.113,
|
| 957 |
"step": 1200
|
| 958 |
},
|
| 959 |
{
|
| 960 |
"epoch": 4.464944649446495,
|
| 961 |
+
"grad_norm": 0.048139333724975586,
|
| 962 |
+
"learning_rate": 0.0001007790077900779,
|
| 963 |
+
"loss": 0.0051,
|
| 964 |
"step": 1210
|
| 965 |
},
|
| 966 |
{
|
| 967 |
"epoch": 4.501845018450185,
|
| 968 |
+
"grad_norm": 0.05954507365822792,
|
| 969 |
+
"learning_rate": 9.995899958999591e-05,
|
| 970 |
+
"loss": 0.0076,
|
| 971 |
"step": 1220
|
| 972 |
},
|
| 973 |
{
|
| 974 |
"epoch": 4.538745387453875,
|
| 975 |
+
"grad_norm": 0.07452525943517685,
|
| 976 |
+
"learning_rate": 9.91389913899139e-05,
|
| 977 |
+
"loss": 0.0041,
|
| 978 |
"step": 1230
|
| 979 |
},
|
| 980 |
{
|
| 981 |
"epoch": 4.575645756457565,
|
| 982 |
+
"grad_norm": 0.008173154667019844,
|
| 983 |
+
"learning_rate": 9.83189831898319e-05,
|
| 984 |
+
"loss": 0.0047,
|
| 985 |
"step": 1240
|
| 986 |
},
|
| 987 |
{
|
| 988 |
"epoch": 4.612546125461255,
|
| 989 |
+
"grad_norm": 0.062416139990091324,
|
| 990 |
+
"learning_rate": 9.74989749897499e-05,
|
| 991 |
+
"loss": 0.0058,
|
| 992 |
"step": 1250
|
| 993 |
},
|
| 994 |
{
|
| 995 |
"epoch": 4.649446494464945,
|
| 996 |
+
"grad_norm": 0.3318597972393036,
|
| 997 |
+
"learning_rate": 9.66789667896679e-05,
|
| 998 |
+
"loss": 0.0052,
|
| 999 |
"step": 1260
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 4.686346863468635,
|
| 1003 |
+
"grad_norm": 0.1266857534646988,
|
| 1004 |
+
"learning_rate": 9.58589585895859e-05,
|
| 1005 |
+
"loss": 0.0079,
|
| 1006 |
"step": 1270
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
"epoch": 4.723247232472325,
|
| 1010 |
+
"grad_norm": 0.061126936227083206,
|
| 1011 |
+
"learning_rate": 9.50389503895039e-05,
|
| 1012 |
+
"loss": 0.0051,
|
| 1013 |
"step": 1280
|
| 1014 |
},
|
| 1015 |
{
|
| 1016 |
"epoch": 4.760147601476015,
|
| 1017 |
+
"grad_norm": 0.09749143570661545,
|
| 1018 |
+
"learning_rate": 9.42189421894219e-05,
|
| 1019 |
+
"loss": 0.0078,
|
| 1020 |
"step": 1290
|
| 1021 |
},
|
| 1022 |
{
|
| 1023 |
"epoch": 4.797047970479705,
|
| 1024 |
+
"grad_norm": 0.34020960330963135,
|
| 1025 |
+
"learning_rate": 9.33989339893399e-05,
|
| 1026 |
+
"loss": 0.0056,
|
| 1027 |
"step": 1300
|
| 1028 |
},
|
| 1029 |
{
|
| 1030 |
"epoch": 4.797047970479705,
|
| 1031 |
+
"eval_accuracy": 0.9901734104046243,
|
| 1032 |
+
"eval_loss": 0.0040424894541502,
|
| 1033 |
+
"eval_runtime": 52.7044,
|
| 1034 |
+
"eval_samples_per_second": 32.825,
|
| 1035 |
+
"eval_steps_per_second": 4.117,
|
| 1036 |
"step": 1300
|
| 1037 |
},
|
| 1038 |
{
|
| 1039 |
"epoch": 4.833948339483395,
|
| 1040 |
+
"grad_norm": 0.19669051468372345,
|
| 1041 |
+
"learning_rate": 9.25789257892579e-05,
|
| 1042 |
+
"loss": 0.0075,
|
| 1043 |
"step": 1310
|
| 1044 |
},
|
| 1045 |
{
|
| 1046 |
"epoch": 4.870848708487085,
|
| 1047 |
+
"grad_norm": 0.09900686144828796,
|
| 1048 |
+
"learning_rate": 9.175891758917589e-05,
|
| 1049 |
+
"loss": 0.0077,
|
| 1050 |
"step": 1320
|
| 1051 |
},
|
| 1052 |
{
|
| 1053 |
"epoch": 4.907749077490775,
|
| 1054 |
+
"grad_norm": 0.1532040238380432,
|
| 1055 |
+
"learning_rate": 9.09389093890939e-05,
|
| 1056 |
+
"loss": 0.0067,
|
| 1057 |
"step": 1330
|
| 1058 |
},
|
| 1059 |
{
|
| 1060 |
"epoch": 4.944649446494465,
|
| 1061 |
+
"grad_norm": 0.051097236573696136,
|
| 1062 |
+
"learning_rate": 9.011890118901189e-05,
|
| 1063 |
+
"loss": 0.0039,
|
| 1064 |
"step": 1340
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
"epoch": 4.9815498154981555,
|
| 1068 |
+
"grad_norm": 0.05327645316720009,
|
| 1069 |
+
"learning_rate": 8.92988929889299e-05,
|
| 1070 |
+
"loss": 0.0055,
|
| 1071 |
"step": 1350
|
| 1072 |
},
|
| 1073 |
{
|
| 1074 |
"epoch": 5.018450184501845,
|
| 1075 |
+
"grad_norm": 0.026003248989582062,
|
| 1076 |
+
"learning_rate": 8.847888478884789e-05,
|
| 1077 |
+
"loss": 0.0055,
|
| 1078 |
"step": 1360
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
"epoch": 5.055350553505535,
|
| 1082 |
+
"grad_norm": 0.11153847724199295,
|
| 1083 |
+
"learning_rate": 8.76588765887659e-05,
|
| 1084 |
+
"loss": 0.0044,
|
| 1085 |
"step": 1370
|
| 1086 |
},
|
| 1087 |
{
|
| 1088 |
"epoch": 5.092250922509225,
|
| 1089 |
+
"grad_norm": 0.02700236812233925,
|
| 1090 |
+
"learning_rate": 8.683886838868389e-05,
|
| 1091 |
+
"loss": 0.0028,
|
| 1092 |
"step": 1380
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 5.129151291512915,
|
| 1096 |
+
"grad_norm": 0.07289482653141022,
|
| 1097 |
+
"learning_rate": 8.60188601886019e-05,
|
| 1098 |
+
"loss": 0.0029,
|
| 1099 |
"step": 1390
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
"epoch": 5.166051660516605,
|
| 1103 |
+
"grad_norm": 0.0497610978782177,
|
| 1104 |
+
"learning_rate": 8.519885198851989e-05,
|
| 1105 |
+
"loss": 0.0026,
|
| 1106 |
"step": 1400
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 5.166051660516605,
|
| 1110 |
+
"eval_accuracy": 0.992485549132948,
|
| 1111 |
+
"eval_loss": 0.003214773256331682,
|
| 1112 |
+
"eval_runtime": 52.8552,
|
| 1113 |
+
"eval_samples_per_second": 32.731,
|
| 1114 |
+
"eval_steps_per_second": 4.106,
|
| 1115 |
"step": 1400
|
| 1116 |
},
|
| 1117 |
{
|
| 1118 |
"epoch": 5.202952029520295,
|
| 1119 |
+
"grad_norm": 0.15320487320423126,
|
| 1120 |
+
"learning_rate": 8.43788437884379e-05,
|
| 1121 |
+
"loss": 0.0041,
|
| 1122 |
"step": 1410
|
| 1123 |
},
|
| 1124 |
{
|
| 1125 |
"epoch": 5.239852398523985,
|
| 1126 |
+
"grad_norm": 0.018703853711485863,
|
| 1127 |
+
"learning_rate": 8.355883558835589e-05,
|
| 1128 |
+
"loss": 0.0041,
|
| 1129 |
"step": 1420
|
| 1130 |
},
|
| 1131 |
{
|
| 1132 |
"epoch": 5.276752767527675,
|
| 1133 |
+
"grad_norm": 0.007155160885304213,
|
| 1134 |
+
"learning_rate": 8.273882738827388e-05,
|
| 1135 |
+
"loss": 0.0028,
|
| 1136 |
"step": 1430
|
| 1137 |
},
|
| 1138 |
{
|
| 1139 |
"epoch": 5.313653136531365,
|
| 1140 |
+
"grad_norm": 0.026553437113761902,
|
| 1141 |
+
"learning_rate": 8.191881918819189e-05,
|
| 1142 |
+
"loss": 0.0046,
|
| 1143 |
"step": 1440
|
| 1144 |
},
|
| 1145 |
{
|
| 1146 |
"epoch": 5.350553505535055,
|
| 1147 |
+
"grad_norm": 0.031090274453163147,
|
| 1148 |
+
"learning_rate": 8.109881098810988e-05,
|
| 1149 |
+
"loss": 0.0044,
|
| 1150 |
"step": 1450
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 5.387453874538745,
|
| 1154 |
+
"grad_norm": 0.1262507289648056,
|
| 1155 |
+
"learning_rate": 8.027880278802789e-05,
|
| 1156 |
+
"loss": 0.0033,
|
| 1157 |
"step": 1460
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 5.424354243542435,
|
| 1161 |
+
"grad_norm": 0.17291103303432465,
|
| 1162 |
+
"learning_rate": 7.945879458794588e-05,
|
| 1163 |
+
"loss": 0.0043,
|
| 1164 |
"step": 1470
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 5.461254612546125,
|
| 1168 |
+
"grad_norm": 0.036809444427490234,
|
| 1169 |
+
"learning_rate": 7.863878638786389e-05,
|
| 1170 |
+
"loss": 0.0038,
|
| 1171 |
"step": 1480
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 5.498154981549815,
|
| 1175 |
+
"grad_norm": 0.027763400226831436,
|
| 1176 |
+
"learning_rate": 7.781877818778188e-05,
|
| 1177 |
+
"loss": 0.002,
|
| 1178 |
"step": 1490
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
"epoch": 5.535055350553505,
|
| 1182 |
+
"grad_norm": 0.10087448358535767,
|
| 1183 |
+
"learning_rate": 7.699876998769989e-05,
|
| 1184 |
+
"loss": 0.0037,
|
| 1185 |
"step": 1500
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 5.535055350553505,
|
| 1189 |
+
"eval_accuracy": 0.9936416184971099,
|
| 1190 |
+
"eval_loss": 0.002714467002078891,
|
| 1191 |
+
"eval_runtime": 52.8635,
|
| 1192 |
+
"eval_samples_per_second": 32.726,
|
| 1193 |
+
"eval_steps_per_second": 4.105,
|
| 1194 |
"step": 1500
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
"epoch": 5.571955719557195,
|
| 1198 |
+
"grad_norm": 0.04997282847762108,
|
| 1199 |
+
"learning_rate": 7.617876178761788e-05,
|
| 1200 |
+
"loss": 0.0024,
|
| 1201 |
"step": 1510
|
| 1202 |
},
|
| 1203 |
{
|
| 1204 |
"epoch": 5.608856088560886,
|
| 1205 |
+
"grad_norm": 0.015307437628507614,
|
| 1206 |
+
"learning_rate": 7.535875358753589e-05,
|
| 1207 |
+
"loss": 0.0038,
|
| 1208 |
"step": 1520
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
"epoch": 5.645756457564576,
|
| 1212 |
+
"grad_norm": 0.0023889692965894938,
|
| 1213 |
+
"learning_rate": 7.453874538745388e-05,
|
| 1214 |
+
"loss": 0.0038,
|
| 1215 |
"step": 1530
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
"epoch": 5.682656826568266,
|
| 1219 |
+
"grad_norm": 0.040821630507707596,
|
| 1220 |
+
"learning_rate": 7.371873718737188e-05,
|
| 1221 |
+
"loss": 0.0041,
|
| 1222 |
"step": 1540
|
| 1223 |
},
|
| 1224 |
{
|
| 1225 |
"epoch": 5.719557195571956,
|
| 1226 |
+
"grad_norm": 0.09734688699245453,
|
| 1227 |
+
"learning_rate": 7.289872898728988e-05,
|
| 1228 |
+
"loss": 0.0038,
|
| 1229 |
"step": 1550
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
"epoch": 5.756457564575646,
|
| 1233 |
+
"grad_norm": 0.016573524102568626,
|
| 1234 |
+
"learning_rate": 7.207872078720787e-05,
|
| 1235 |
+
"loss": 0.0025,
|
| 1236 |
"step": 1560
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
"epoch": 5.793357933579336,
|
| 1240 |
+
"grad_norm": 0.009829455986618996,
|
| 1241 |
+
"learning_rate": 7.125871258712588e-05,
|
| 1242 |
+
"loss": 0.0041,
|
| 1243 |
"step": 1570
|
| 1244 |
},
|
| 1245 |
{
|
| 1246 |
"epoch": 5.830258302583026,
|
| 1247 |
+
"grad_norm": 0.07733350247144699,
|
| 1248 |
+
"learning_rate": 7.043870438704387e-05,
|
| 1249 |
+
"loss": 0.0024,
|
| 1250 |
"step": 1580
|
| 1251 |
},
|
| 1252 |
{
|
| 1253 |
"epoch": 5.867158671586716,
|
| 1254 |
+
"grad_norm": 0.04763353243470192,
|
| 1255 |
+
"learning_rate": 6.961869618696188e-05,
|
| 1256 |
+
"loss": 0.0025,
|
| 1257 |
"step": 1590
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
"epoch": 5.904059040590406,
|
| 1261 |
+
"grad_norm": 0.009967833757400513,
|
| 1262 |
+
"learning_rate": 6.879868798687987e-05,
|
| 1263 |
+
"loss": 0.0039,
|
| 1264 |
"step": 1600
|
| 1265 |
},
|
| 1266 |
{
|
| 1267 |
"epoch": 5.904059040590406,
|
| 1268 |
+
"eval_accuracy": 0.9976878612716763,
|
| 1269 |
+
"eval_loss": 0.0022707099560648203,
|
| 1270 |
+
"eval_runtime": 53.0061,
|
| 1271 |
+
"eval_samples_per_second": 32.638,
|
| 1272 |
+
"eval_steps_per_second": 4.094,
|
| 1273 |
"step": 1600
|
| 1274 |
},
|
| 1275 |
{
|
| 1276 |
"epoch": 5.940959409594096,
|
| 1277 |
+
"grad_norm": 0.020813655108213425,
|
| 1278 |
+
"learning_rate": 6.797867978679788e-05,
|
| 1279 |
+
"loss": 0.0029,
|
| 1280 |
"step": 1610
|
| 1281 |
},
|
| 1282 |
{
|
| 1283 |
"epoch": 5.977859778597786,
|
| 1284 |
+
"grad_norm": 0.062338754534721375,
|
| 1285 |
+
"learning_rate": 6.715867158671587e-05,
|
| 1286 |
+
"loss": 0.0023,
|
| 1287 |
"step": 1620
|
| 1288 |
},
|
| 1289 |
{
|
| 1290 |
"epoch": 6.014760147601476,
|
| 1291 |
+
"grad_norm": 0.018345272168517113,
|
| 1292 |
+
"learning_rate": 6.633866338663388e-05,
|
| 1293 |
+
"loss": 0.0029,
|
| 1294 |
"step": 1630
|
| 1295 |
},
|
| 1296 |
{
|
| 1297 |
"epoch": 6.051660516605166,
|
| 1298 |
+
"grad_norm": 0.023753851652145386,
|
| 1299 |
+
"learning_rate": 6.551865518655187e-05,
|
| 1300 |
+
"loss": 0.0018,
|
| 1301 |
"step": 1640
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
"epoch": 6.088560885608856,
|
| 1305 |
+
"grad_norm": 0.016533376649022102,
|
| 1306 |
+
"learning_rate": 6.469864698646987e-05,
|
| 1307 |
+
"loss": 0.0025,
|
| 1308 |
"step": 1650
|
| 1309 |
},
|
| 1310 |
{
|
| 1311 |
"epoch": 6.125461254612546,
|
| 1312 |
+
"grad_norm": 0.008262280374765396,
|
| 1313 |
+
"learning_rate": 6.387863878638787e-05,
|
| 1314 |
+
"loss": 0.0025,
|
| 1315 |
"step": 1660
|
| 1316 |
},
|
| 1317 |
{
|
| 1318 |
"epoch": 6.162361623616236,
|
| 1319 |
+
"grad_norm": 0.010828894563019276,
|
| 1320 |
+
"learning_rate": 6.305863058630586e-05,
|
| 1321 |
+
"loss": 0.0018,
|
| 1322 |
"step": 1670
|
| 1323 |
},
|
| 1324 |
{
|
| 1325 |
"epoch": 6.199261992619927,
|
| 1326 |
+
"grad_norm": 0.01505562849342823,
|
| 1327 |
+
"learning_rate": 6.223862238622387e-05,
|
| 1328 |
+
"loss": 0.0017,
|
| 1329 |
"step": 1680
|
| 1330 |
},
|
| 1331 |
{
|
| 1332 |
"epoch": 6.236162361623617,
|
| 1333 |
+
"grad_norm": 0.0033724599052220583,
|
| 1334 |
+
"learning_rate": 6.141861418614186e-05,
|
| 1335 |
+
"loss": 0.0018,
|
| 1336 |
"step": 1690
|
| 1337 |
},
|
| 1338 |
{
|
| 1339 |
"epoch": 6.273062730627307,
|
| 1340 |
+
"grad_norm": 0.026863617822527885,
|
| 1341 |
+
"learning_rate": 6.0598605986059866e-05,
|
| 1342 |
+
"loss": 0.0019,
|
| 1343 |
"step": 1700
|
| 1344 |
},
|
| 1345 |
{
|
| 1346 |
"epoch": 6.273062730627307,
|
| 1347 |
+
"eval_accuracy": 0.9971098265895953,
|
| 1348 |
+
"eval_loss": 0.0018508523935452104,
|
| 1349 |
+
"eval_runtime": 53.4671,
|
| 1350 |
+
"eval_samples_per_second": 32.356,
|
| 1351 |
+
"eval_steps_per_second": 4.059,
|
| 1352 |
"step": 1700
|
| 1353 |
},
|
| 1354 |
{
|
| 1355 |
"epoch": 6.3099630996309966,
|
| 1356 |
+
"grad_norm": 0.011449555866420269,
|
| 1357 |
+
"learning_rate": 5.9778597785977866e-05,
|
| 1358 |
+
"loss": 0.0019,
|
| 1359 |
"step": 1710
|
| 1360 |
},
|
| 1361 |
{
|
| 1362 |
"epoch": 6.3468634686346865,
|
| 1363 |
+
"grad_norm": 0.04869832843542099,
|
| 1364 |
+
"learning_rate": 5.8958589585895866e-05,
|
| 1365 |
+
"loss": 0.0022,
|
| 1366 |
"step": 1720
|
| 1367 |
},
|
| 1368 |
{
|
| 1369 |
"epoch": 6.3837638376383765,
|
| 1370 |
+
"grad_norm": 0.2211851179599762,
|
| 1371 |
+
"learning_rate": 5.813858138581386e-05,
|
| 1372 |
+
"loss": 0.0021,
|
| 1373 |
"step": 1730
|
| 1374 |
},
|
| 1375 |
{
|
| 1376 |
"epoch": 6.4206642066420665,
|
| 1377 |
+
"grad_norm": 0.021321425214409828,
|
| 1378 |
+
"learning_rate": 5.731857318573186e-05,
|
| 1379 |
+
"loss": 0.0017,
|
| 1380 |
"step": 1740
|
| 1381 |
},
|
| 1382 |
{
|
| 1383 |
"epoch": 6.4575645756457565,
|
| 1384 |
+
"grad_norm": 0.014219704084098339,
|
| 1385 |
+
"learning_rate": 5.649856498564986e-05,
|
| 1386 |
+
"loss": 0.0026,
|
| 1387 |
"step": 1750
|
| 1388 |
},
|
| 1389 |
{
|
| 1390 |
"epoch": 6.4944649446494465,
|
| 1391 |
+
"grad_norm": 0.011448672972619534,
|
| 1392 |
+
"learning_rate": 5.567855678556786e-05,
|
| 1393 |
+
"loss": 0.0026,
|
| 1394 |
"step": 1760
|
| 1395 |
},
|
| 1396 |
{
|
| 1397 |
"epoch": 6.531365313653136,
|
| 1398 |
+
"grad_norm": 0.008601737208664417,
|
| 1399 |
+
"learning_rate": 5.485854858548586e-05,
|
| 1400 |
+
"loss": 0.0016,
|
| 1401 |
"step": 1770
|
| 1402 |
},
|
| 1403 |
{
|
| 1404 |
"epoch": 6.568265682656826,
|
| 1405 |
+
"grad_norm": 0.013017091900110245,
|
| 1406 |
+
"learning_rate": 5.403854038540386e-05,
|
| 1407 |
+
"loss": 0.0023,
|
| 1408 |
"step": 1780
|
| 1409 |
},
|
| 1410 |
{
|
| 1411 |
"epoch": 6.605166051660516,
|
| 1412 |
+
"grad_norm": 0.008623339235782623,
|
| 1413 |
+
"learning_rate": 5.321853218532186e-05,
|
| 1414 |
+
"loss": 0.0019,
|
| 1415 |
"step": 1790
|
| 1416 |
},
|
| 1417 |
{
|
| 1418 |
"epoch": 6.642066420664206,
|
| 1419 |
+
"grad_norm": 0.027804844081401825,
|
| 1420 |
+
"learning_rate": 5.239852398523986e-05,
|
| 1421 |
+
"loss": 0.0019,
|
| 1422 |
"step": 1800
|
| 1423 |
},
|
| 1424 |
{
|
| 1425 |
"epoch": 6.642066420664206,
|
| 1426 |
+
"eval_accuracy": 0.9988439306358381,
|
| 1427 |
+
"eval_loss": 0.0016573916655033827,
|
| 1428 |
+
"eval_runtime": 53.3851,
|
| 1429 |
+
"eval_samples_per_second": 32.406,
|
| 1430 |
+
"eval_steps_per_second": 4.065,
|
| 1431 |
"step": 1800
|
| 1432 |
},
|
| 1433 |
{
|
| 1434 |
"epoch": 6.678966789667896,
|
| 1435 |
+
"grad_norm": 0.027201993390917778,
|
| 1436 |
+
"learning_rate": 5.1578515785157857e-05,
|
| 1437 |
+
"loss": 0.0021,
|
| 1438 |
"step": 1810
|
| 1439 |
},
|
| 1440 |
{
|
| 1441 |
"epoch": 6.715867158671586,
|
| 1442 |
+
"grad_norm": 0.07681945711374283,
|
| 1443 |
+
"learning_rate": 5.0758507585075856e-05,
|
| 1444 |
+
"loss": 0.0022,
|
| 1445 |
"step": 1820
|
| 1446 |
},
|
| 1447 |
{
|
| 1448 |
"epoch": 6.752767527675276,
|
| 1449 |
+
"grad_norm": 0.010648882016539574,
|
| 1450 |
+
"learning_rate": 4.9938499384993856e-05,
|
| 1451 |
+
"loss": 0.0017,
|
| 1452 |
"step": 1830
|
| 1453 |
},
|
| 1454 |
{
|
| 1455 |
"epoch": 6.789667896678967,
|
| 1456 |
+
"grad_norm": 0.01609162986278534,
|
| 1457 |
+
"learning_rate": 4.9118491184911856e-05,
|
| 1458 |
+
"loss": 0.0016,
|
| 1459 |
"step": 1840
|
| 1460 |
},
|
| 1461 |
{
|
| 1462 |
"epoch": 6.826568265682657,
|
| 1463 |
+
"grad_norm": 0.013306355103850365,
|
| 1464 |
+
"learning_rate": 4.829848298482985e-05,
|
| 1465 |
+
"loss": 0.0016,
|
| 1466 |
"step": 1850
|
| 1467 |
},
|
| 1468 |
{
|
| 1469 |
"epoch": 6.863468634686347,
|
| 1470 |
+
"grad_norm": 0.015135644935071468,
|
| 1471 |
+
"learning_rate": 4.747847478474785e-05,
|
| 1472 |
+
"loss": 0.002,
|
| 1473 |
"step": 1860
|
| 1474 |
},
|
| 1475 |
{
|
| 1476 |
"epoch": 6.900369003690037,
|
| 1477 |
+
"grad_norm": 0.019170399755239487,
|
| 1478 |
+
"learning_rate": 4.665846658466585e-05,
|
| 1479 |
+
"loss": 0.0015,
|
| 1480 |
"step": 1870
|
| 1481 |
},
|
| 1482 |
{
|
| 1483 |
"epoch": 6.937269372693727,
|
| 1484 |
+
"grad_norm": 0.02915087901055813,
|
| 1485 |
+
"learning_rate": 4.583845838458385e-05,
|
| 1486 |
+
"loss": 0.0012,
|
| 1487 |
"step": 1880
|
| 1488 |
},
|
| 1489 |
{
|
| 1490 |
"epoch": 6.974169741697417,
|
| 1491 |
+
"grad_norm": 0.023285195231437683,
|
| 1492 |
+
"learning_rate": 4.501845018450185e-05,
|
| 1493 |
+
"loss": 0.0019,
|
| 1494 |
"step": 1890
|
| 1495 |
},
|
| 1496 |
{
|
| 1497 |
"epoch": 7.011070110701107,
|
| 1498 |
+
"grad_norm": 0.013183875940740108,
|
| 1499 |
+
"learning_rate": 4.419844198441985e-05,
|
| 1500 |
+
"loss": 0.0016,
|
| 1501 |
"step": 1900
|
| 1502 |
},
|
| 1503 |
{
|
| 1504 |
"epoch": 7.011070110701107,
|
| 1505 |
+
"eval_accuracy": 1.0,
|
| 1506 |
+
"eval_loss": 0.0015279006911441684,
|
| 1507 |
+
"eval_runtime": 53.4443,
|
| 1508 |
+
"eval_samples_per_second": 32.37,
|
| 1509 |
+
"eval_steps_per_second": 4.06,
|
| 1510 |
"step": 1900
|
| 1511 |
},
|
| 1512 |
{
|
| 1513 |
"epoch": 7.047970479704797,
|
| 1514 |
+
"grad_norm": 0.008983751758933067,
|
| 1515 |
+
"learning_rate": 4.337843378433785e-05,
|
| 1516 |
+
"loss": 0.0015,
|
| 1517 |
"step": 1910
|
| 1518 |
},
|
| 1519 |
{
|
| 1520 |
"epoch": 7.084870848708487,
|
| 1521 |
+
"grad_norm": 0.003578983247280121,
|
| 1522 |
+
"learning_rate": 4.2558425584255847e-05,
|
| 1523 |
+
"loss": 0.0013,
|
| 1524 |
"step": 1920
|
| 1525 |
},
|
| 1526 |
{
|
| 1527 |
"epoch": 7.121771217712177,
|
| 1528 |
+
"grad_norm": 0.009858568198978901,
|
| 1529 |
+
"learning_rate": 4.1738417384173846e-05,
|
| 1530 |
+
"loss": 0.0017,
|
| 1531 |
"step": 1930
|
| 1532 |
},
|
| 1533 |
{
|
| 1534 |
"epoch": 7.158671586715867,
|
| 1535 |
+
"grad_norm": 0.01723896525800228,
|
| 1536 |
+
"learning_rate": 4.0918409184091846e-05,
|
| 1537 |
+
"loss": 0.0011,
|
| 1538 |
"step": 1940
|
| 1539 |
},
|
| 1540 |
{
|
| 1541 |
"epoch": 7.195571955719557,
|
| 1542 |
+
"grad_norm": 0.007069133687764406,
|
| 1543 |
+
"learning_rate": 4.0098400984009846e-05,
|
| 1544 |
+
"loss": 0.0012,
|
| 1545 |
"step": 1950
|
| 1546 |
},
|
| 1547 |
{
|
| 1548 |
"epoch": 7.232472324723247,
|
| 1549 |
+
"grad_norm": 0.006838188972324133,
|
| 1550 |
+
"learning_rate": 3.927839278392784e-05,
|
| 1551 |
+
"loss": 0.0021,
|
| 1552 |
"step": 1960
|
| 1553 |
},
|
| 1554 |
{
|
| 1555 |
"epoch": 7.269372693726937,
|
| 1556 |
+
"grad_norm": 0.011245744302868843,
|
| 1557 |
+
"learning_rate": 3.845838458384584e-05,
|
| 1558 |
+
"loss": 0.0018,
|
| 1559 |
"step": 1970
|
| 1560 |
},
|
| 1561 |
{
|
| 1562 |
"epoch": 7.306273062730627,
|
| 1563 |
+
"grad_norm": 0.002784464741125703,
|
| 1564 |
+
"learning_rate": 3.763837638376384e-05,
|
| 1565 |
+
"loss": 0.0013,
|
| 1566 |
"step": 1980
|
| 1567 |
},
|
| 1568 |
{
|
| 1569 |
"epoch": 7.343173431734318,
|
| 1570 |
+
"grad_norm": 0.007723368238657713,
|
| 1571 |
+
"learning_rate": 3.681836818368184e-05,
|
| 1572 |
+
"loss": 0.0017,
|
| 1573 |
"step": 1990
|
| 1574 |
},
|
| 1575 |
{
|
| 1576 |
"epoch": 7.380073800738008,
|
| 1577 |
+
"grad_norm": 0.016839824616909027,
|
| 1578 |
+
"learning_rate": 3.599835998359984e-05,
|
| 1579 |
+
"loss": 0.002,
|
| 1580 |
"step": 2000
|
| 1581 |
},
|
| 1582 |
{
|
| 1583 |
"epoch": 7.380073800738008,
|
| 1584 |
+
"eval_accuracy": 1.0,
|
| 1585 |
+
"eval_loss": 0.0014427828136831522,
|
| 1586 |
+
"eval_runtime": 53.204,
|
| 1587 |
+
"eval_samples_per_second": 32.516,
|
| 1588 |
+
"eval_steps_per_second": 4.079,
|
| 1589 |
"step": 2000
|
| 1590 |
},
|
| 1591 |
{
|
| 1592 |
"epoch": 7.416974169741698,
|
| 1593 |
+
"grad_norm": 0.015248976647853851,
|
| 1594 |
+
"learning_rate": 3.517835178351784e-05,
|
| 1595 |
+
"loss": 0.0018,
|
| 1596 |
"step": 2010
|
| 1597 |
},
|
| 1598 |
{
|
| 1599 |
"epoch": 7.453874538745388,
|
| 1600 |
+
"grad_norm": 0.013244880363345146,
|
| 1601 |
+
"learning_rate": 3.435834358343584e-05,
|
| 1602 |
+
"loss": 0.0022,
|
| 1603 |
"step": 2020
|
| 1604 |
},
|
| 1605 |
{
|
| 1606 |
"epoch": 7.490774907749078,
|
| 1607 |
+
"grad_norm": 0.009770199656486511,
|
| 1608 |
+
"learning_rate": 3.353833538335384e-05,
|
| 1609 |
+
"loss": 0.0017,
|
| 1610 |
"step": 2030
|
| 1611 |
},
|
| 1612 |
{
|
| 1613 |
"epoch": 7.527675276752768,
|
| 1614 |
+
"grad_norm": 0.010310194455087185,
|
| 1615 |
+
"learning_rate": 3.2718327183271836e-05,
|
| 1616 |
+
"loss": 0.0018,
|
| 1617 |
"step": 2040
|
| 1618 |
},
|
| 1619 |
{
|
| 1620 |
"epoch": 7.564575645756458,
|
| 1621 |
+
"grad_norm": 0.0034243548288941383,
|
| 1622 |
+
"learning_rate": 3.1898318983189836e-05,
|
| 1623 |
+
"loss": 0.0014,
|
| 1624 |
"step": 2050
|
| 1625 |
},
|
| 1626 |
{
|
| 1627 |
"epoch": 7.601476014760148,
|
| 1628 |
+
"grad_norm": 0.005529376212507486,
|
| 1629 |
+
"learning_rate": 3.1078310783107836e-05,
|
| 1630 |
+
"loss": 0.0013,
|
| 1631 |
"step": 2060
|
| 1632 |
},
|
| 1633 |
{
|
| 1634 |
"epoch": 7.638376383763838,
|
| 1635 |
+
"grad_norm": 0.005842520389705896,
|
| 1636 |
+
"learning_rate": 3.0258302583025832e-05,
|
| 1637 |
+
"loss": 0.0017,
|
| 1638 |
"step": 2070
|
| 1639 |
},
|
| 1640 |
{
|
| 1641 |
"epoch": 7.675276752767528,
|
| 1642 |
+
"grad_norm": 0.00041994985076598823,
|
| 1643 |
+
"learning_rate": 2.9438294382943832e-05,
|
| 1644 |
+
"loss": 0.0016,
|
| 1645 |
"step": 2080
|
| 1646 |
},
|
| 1647 |
{
|
| 1648 |
"epoch": 7.712177121771218,
|
| 1649 |
+
"grad_norm": 0.005925205536186695,
|
| 1650 |
+
"learning_rate": 2.861828618286183e-05,
|
| 1651 |
+
"loss": 0.0013,
|
| 1652 |
"step": 2090
|
| 1653 |
},
|
| 1654 |
{
|
| 1655 |
"epoch": 7.749077490774908,
|
| 1656 |
+
"grad_norm": 0.00783997867256403,
|
| 1657 |
+
"learning_rate": 2.779827798277983e-05,
|
| 1658 |
+
"loss": 0.0013,
|
| 1659 |
"step": 2100
|
| 1660 |
},
|
| 1661 |
{
|
| 1662 |
"epoch": 7.749077490774908,
|
| 1663 |
+
"eval_accuracy": 1.0,
|
| 1664 |
+
"eval_loss": 0.0013818982988595963,
|
| 1665 |
+
"eval_runtime": 53.3908,
|
| 1666 |
+
"eval_samples_per_second": 32.403,
|
| 1667 |
+
"eval_steps_per_second": 4.064,
|
| 1668 |
"step": 2100
|
| 1669 |
},
|
| 1670 |
{
|
| 1671 |
"epoch": 7.785977859778598,
|
| 1672 |
+
"grad_norm": 0.0075693195685744286,
|
| 1673 |
+
"learning_rate": 2.6978269782697828e-05,
|
| 1674 |
+
"loss": 0.0018,
|
| 1675 |
"step": 2110
|
| 1676 |
},
|
| 1677 |
{
|
| 1678 |
"epoch": 7.822878228782288,
|
| 1679 |
+
"grad_norm": 0.00795042049139738,
|
| 1680 |
+
"learning_rate": 2.6158261582615827e-05,
|
| 1681 |
+
"loss": 0.0011,
|
| 1682 |
"step": 2120
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 7.8597785977859775,
|
| 1686 |
+
"grad_norm": 0.00859429594129324,
|
| 1687 |
+
"learning_rate": 2.5338253382533827e-05,
|
| 1688 |
+
"loss": 0.0015,
|
| 1689 |
"step": 2130
|
| 1690 |
},
|
| 1691 |
{
|
| 1692 |
"epoch": 7.8966789667896675,
|
| 1693 |
+
"grad_norm": 0.005215910263359547,
|
| 1694 |
+
"learning_rate": 2.4518245182451827e-05,
|
| 1695 |
+
"loss": 0.0016,
|
| 1696 |
"step": 2140
|
| 1697 |
},
|
| 1698 |
{
|
| 1699 |
"epoch": 7.9335793357933575,
|
| 1700 |
+
"grad_norm": 0.0038353356067091227,
|
| 1701 |
+
"learning_rate": 2.3698236982369827e-05,
|
| 1702 |
+
"loss": 0.0015,
|
| 1703 |
"step": 2150
|
| 1704 |
},
|
| 1705 |
{
|
| 1706 |
"epoch": 7.970479704797048,
|
| 1707 |
+
"grad_norm": 0.00975708942860365,
|
| 1708 |
+
"learning_rate": 2.2878228782287826e-05,
|
| 1709 |
+
"loss": 0.0015,
|
| 1710 |
"step": 2160
|
| 1711 |
},
|
| 1712 |
{
|
| 1713 |
+
"epoch": 8.007380073800737,
|
| 1714 |
+
"grad_norm": 0.006485125049948692,
|
| 1715 |
+
"learning_rate": 2.2058220582205823e-05,
|
| 1716 |
+
"loss": 0.0012,
|
| 1717 |
+
"step": 2170
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 8.044280442804428,
|
| 1721 |
+
"grad_norm": 0.013848377391695976,
|
| 1722 |
+
"learning_rate": 2.1238212382123822e-05,
|
| 1723 |
+
"loss": 0.0014,
|
| 1724 |
+
"step": 2180
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 8.081180811808117,
|
| 1728 |
+
"grad_norm": 0.012979693710803986,
|
| 1729 |
+
"learning_rate": 2.0418204182041822e-05,
|
| 1730 |
+
"loss": 0.0015,
|
| 1731 |
+
"step": 2190
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 8.118081180811808,
|
| 1735 |
+
"grad_norm": 0.005968283861875534,
|
| 1736 |
+
"learning_rate": 1.9598195981959822e-05,
|
| 1737 |
+
"loss": 0.0015,
|
| 1738 |
+
"step": 2200
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 8.118081180811808,
|
| 1742 |
+
"eval_accuracy": 1.0,
|
| 1743 |
+
"eval_loss": 0.0013393920380622149,
|
| 1744 |
+
"eval_runtime": 53.2752,
|
| 1745 |
+
"eval_samples_per_second": 32.473,
|
| 1746 |
+
"eval_steps_per_second": 4.073,
|
| 1747 |
+
"step": 2200
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 8.154981549815497,
|
| 1751 |
+
"grad_norm": 0.010278232395648956,
|
| 1752 |
+
"learning_rate": 1.877818778187782e-05,
|
| 1753 |
+
"loss": 0.0009,
|
| 1754 |
+
"step": 2210
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 8.191881918819188,
|
| 1758 |
+
"grad_norm": 0.007073582150042057,
|
| 1759 |
+
"learning_rate": 1.795817958179582e-05,
|
| 1760 |
+
"loss": 0.0016,
|
| 1761 |
+
"step": 2220
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 8.228782287822877,
|
| 1765 |
+
"grad_norm": 0.0020103720016777515,
|
| 1766 |
+
"learning_rate": 1.7138171381713817e-05,
|
| 1767 |
+
"loss": 0.0014,
|
| 1768 |
+
"step": 2230
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 8.265682656826568,
|
| 1772 |
+
"grad_norm": 0.006469924468547106,
|
| 1773 |
+
"learning_rate": 1.6318163181631817e-05,
|
| 1774 |
+
"loss": 0.0014,
|
| 1775 |
+
"step": 2240
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 8.302583025830259,
|
| 1779 |
+
"grad_norm": 0.006924558896571398,
|
| 1780 |
+
"learning_rate": 1.5498154981549817e-05,
|
| 1781 |
+
"loss": 0.0013,
|
| 1782 |
+
"step": 2250
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 8.339483394833948,
|
| 1786 |
+
"grad_norm": 0.010701497085392475,
|
| 1787 |
+
"learning_rate": 1.4678146781467817e-05,
|
| 1788 |
+
"loss": 0.0013,
|
| 1789 |
+
"step": 2260
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 8.376383763837639,
|
| 1793 |
+
"grad_norm": 0.012286316603422165,
|
| 1794 |
+
"learning_rate": 1.3858138581385816e-05,
|
| 1795 |
+
"loss": 0.0016,
|
| 1796 |
+
"step": 2270
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 8.413284132841328,
|
| 1800 |
+
"grad_norm": 0.010458541102707386,
|
| 1801 |
+
"learning_rate": 1.3038130381303814e-05,
|
| 1802 |
+
"loss": 0.0018,
|
| 1803 |
+
"step": 2280
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 8.450184501845019,
|
| 1807 |
+
"grad_norm": 0.010043789632618427,
|
| 1808 |
+
"learning_rate": 1.2218122181221812e-05,
|
| 1809 |
+
"loss": 0.0012,
|
| 1810 |
+
"step": 2290
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 8.487084870848708,
|
| 1814 |
+
"grad_norm": 0.00660703144967556,
|
| 1815 |
+
"learning_rate": 1.1398113981139812e-05,
|
| 1816 |
+
"loss": 0.0011,
|
| 1817 |
+
"step": 2300
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 8.487084870848708,
|
| 1821 |
+
"eval_accuracy": 1.0,
|
| 1822 |
+
"eval_loss": 0.0013166143326088786,
|
| 1823 |
+
"eval_runtime": 53.3458,
|
| 1824 |
+
"eval_samples_per_second": 32.43,
|
| 1825 |
+
"eval_steps_per_second": 4.068,
|
| 1826 |
+
"step": 2300
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 8.523985239852399,
|
| 1830 |
+
"grad_norm": 0.006171096581965685,
|
| 1831 |
+
"learning_rate": 1.057810578105781e-05,
|
| 1832 |
+
"loss": 0.0014,
|
| 1833 |
+
"step": 2310
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 8.560885608856088,
|
| 1837 |
+
"grad_norm": 0.005463199689984322,
|
| 1838 |
+
"learning_rate": 9.75809758097581e-06,
|
| 1839 |
+
"loss": 0.0013,
|
| 1840 |
+
"step": 2320
|
| 1841 |
+
},
|
| 1842 |
+
{
|
| 1843 |
+
"epoch": 8.597785977859779,
|
| 1844 |
+
"grad_norm": 0.008069201372563839,
|
| 1845 |
+
"learning_rate": 8.93808938089381e-06,
|
| 1846 |
+
"loss": 0.0015,
|
| 1847 |
+
"step": 2330
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 8.634686346863468,
|
| 1851 |
+
"grad_norm": 0.007250032387673855,
|
| 1852 |
+
"learning_rate": 8.118081180811808e-06,
|
| 1853 |
+
"loss": 0.0017,
|
| 1854 |
+
"step": 2340
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 8.671586715867159,
|
| 1858 |
+
"grad_norm": 0.011325874365866184,
|
| 1859 |
+
"learning_rate": 7.298072980729807e-06,
|
| 1860 |
+
"loss": 0.0014,
|
| 1861 |
+
"step": 2350
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 8.708487084870848,
|
| 1865 |
+
"grad_norm": 0.019912155345082283,
|
| 1866 |
+
"learning_rate": 6.478064780647806e-06,
|
| 1867 |
+
"loss": 0.0018,
|
| 1868 |
+
"step": 2360
|
| 1869 |
+
},
|
| 1870 |
+
{
|
| 1871 |
+
"epoch": 8.745387453874539,
|
| 1872 |
+
"grad_norm": 0.0008021511603146791,
|
| 1873 |
+
"learning_rate": 5.658056580565806e-06,
|
| 1874 |
+
"loss": 0.0012,
|
| 1875 |
+
"step": 2370
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 8.782287822878228,
|
| 1879 |
+
"grad_norm": 0.01182828564196825,
|
| 1880 |
+
"learning_rate": 4.838048380483805e-06,
|
| 1881 |
+
"loss": 0.0016,
|
| 1882 |
+
"step": 2380
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 8.819188191881919,
|
| 1886 |
+
"grad_norm": 0.004345746710896492,
|
| 1887 |
+
"learning_rate": 4.018040180401804e-06,
|
| 1888 |
+
"loss": 0.001,
|
| 1889 |
+
"step": 2390
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 8.85608856088561,
|
| 1893 |
+
"grad_norm": 0.0077620395459234715,
|
| 1894 |
+
"learning_rate": 3.198031980319803e-06,
|
| 1895 |
+
"loss": 0.0013,
|
| 1896 |
+
"step": 2400
|
| 1897 |
+
},
|
| 1898 |
+
{
|
| 1899 |
+
"epoch": 8.85608856088561,
|
| 1900 |
+
"eval_accuracy": 1.0,
|
| 1901 |
+
"eval_loss": 0.0013051489368081093,
|
| 1902 |
+
"eval_runtime": 52.9588,
|
| 1903 |
+
"eval_samples_per_second": 32.667,
|
| 1904 |
+
"eval_steps_per_second": 4.098,
|
| 1905 |
+
"step": 2400
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 8.892988929889299,
|
| 1909 |
+
"grad_norm": 0.01009498443454504,
|
| 1910 |
+
"learning_rate": 2.3780237802378026e-06,
|
| 1911 |
+
"loss": 0.0015,
|
| 1912 |
+
"step": 2410
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 8.92988929889299,
|
| 1916 |
+
"grad_norm": 0.00728220259770751,
|
| 1917 |
+
"learning_rate": 1.5580155801558017e-06,
|
| 1918 |
+
"loss": 0.0015,
|
| 1919 |
+
"step": 2420
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 8.966789667896679,
|
| 1923 |
+
"grad_norm": 0.014378752559423447,
|
| 1924 |
+
"learning_rate": 7.380073800738008e-07,
|
| 1925 |
+
"loss": 0.0014,
|
| 1926 |
+
"step": 2430
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 9.0,
|
| 1930 |
+
"step": 2439,
|
| 1931 |
+
"total_flos": 3.017424657591816e+18,
|
| 1932 |
+
"train_loss": 0.01402124272053813,
|
| 1933 |
+
"train_runtime": 3085.6034,
|
| 1934 |
+
"train_samples_per_second": 12.618,
|
| 1935 |
+
"train_steps_per_second": 0.79
|
| 1936 |
}
|
| 1937 |
],
|
| 1938 |
"logging_steps": 10,
|
| 1939 |
+
"max_steps": 2439,
|
| 1940 |
"num_input_tokens_seen": 0,
|
| 1941 |
+
"num_train_epochs": 9,
|
| 1942 |
"save_steps": 100,
|
| 1943 |
"stateful_callbacks": {
|
| 1944 |
"TrainerControl": {
|
|
|
|
| 1952 |
"attributes": {}
|
| 1953 |
}
|
| 1954 |
},
|
| 1955 |
+
"total_flos": 3.017424657591816e+18,
|
| 1956 |
"train_batch_size": 16,
|
| 1957 |
"trial_name": null,
|
| 1958 |
"trial_params": null
|