frostsolutions/frost-vision-v2-google_vit-base-patch16-224-v2024-11-14
Browse files- README.md +9 -9
- all_results.json +12 -12
- eval_results.json +8 -8
- runs/Nov14_23-23-05_ba4b501b14a9/events.out.tfevents.1731627314.ba4b501b14a9.833.3 +3 -0
- train_results.json +4 -4
- trainer_state.json +923 -923
README.md
CHANGED
|
@@ -26,16 +26,16 @@ model-index:
|
|
| 26 |
metrics:
|
| 27 |
- name: Accuracy
|
| 28 |
type: accuracy
|
| 29 |
-
value: 0.
|
| 30 |
- name: F1
|
| 31 |
type: f1
|
| 32 |
-
value: 0.
|
| 33 |
- name: Precision
|
| 34 |
type: precision
|
| 35 |
-
value: 0.
|
| 36 |
- name: Recall
|
| 37 |
type: recall
|
| 38 |
-
value: 0.
|
| 39 |
---
|
| 40 |
|
| 41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -45,11 +45,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 45 |
|
| 46 |
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the webdataset dataset.
|
| 47 |
It achieves the following results on the evaluation set:
|
| 48 |
-
- Loss: 0.
|
| 49 |
-
- Accuracy: 0.
|
| 50 |
-
- F1: 0.
|
| 51 |
-
- Precision: 0.
|
| 52 |
-
- Recall: 0.
|
| 53 |
|
| 54 |
## Model description
|
| 55 |
|
|
|
|
| 26 |
metrics:
|
| 27 |
- name: Accuracy
|
| 28 |
type: accuracy
|
| 29 |
+
value: 0.9388888888888889
|
| 30 |
- name: F1
|
| 31 |
type: f1
|
| 32 |
+
value: 0.8436018957345972
|
| 33 |
- name: Precision
|
| 34 |
type: precision
|
| 35 |
+
value: 0.8654781199351702
|
| 36 |
- name: Recall
|
| 37 |
type: recall
|
| 38 |
+
value: 0.8228043143297381
|
| 39 |
---
|
| 40 |
|
| 41 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 45 |
|
| 46 |
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the webdataset dataset.
|
| 47 |
It achieves the following results on the evaluation set:
|
| 48 |
+
- Loss: 0.1577
|
| 49 |
+
- Accuracy: 0.9389
|
| 50 |
+
- F1: 0.8436
|
| 51 |
+
- Precision: 0.8655
|
| 52 |
+
- Recall: 0.8228
|
| 53 |
|
| 54 |
## Model description
|
| 55 |
|
all_results.json
CHANGED
|
@@ -1,16 +1,16 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 30.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime":
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second":
|
| 11 |
"total_flos": 3.008454731998249e+18,
|
| 12 |
-
"train_loss": 0.
|
| 13 |
-
"train_runtime":
|
| 14 |
-
"train_samples_per_second":
|
| 15 |
-
"train_steps_per_second": 3.
|
| 16 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.9388888888888889,
|
| 4 |
+
"eval_f1": 0.8436018957345972,
|
| 5 |
+
"eval_loss": 0.15773314237594604,
|
| 6 |
+
"eval_precision": 0.8654781199351702,
|
| 7 |
+
"eval_recall": 0.8228043143297381,
|
| 8 |
+
"eval_runtime": 2.635,
|
| 9 |
+
"eval_samples_per_second": 122.962,
|
| 10 |
+
"eval_steps_per_second": 15.56,
|
| 11 |
"total_flos": 3.008454731998249e+18,
|
| 12 |
+
"train_loss": 0.09584075045070531,
|
| 13 |
+
"train_runtime": 684.1699,
|
| 14 |
+
"train_samples_per_second": 56.74,
|
| 15 |
+
"train_steps_per_second": 3.552
|
| 16 |
}
|
eval_results.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 30.0,
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"eval_f1": 0.
|
| 5 |
-
"eval_loss": 0.
|
| 6 |
-
"eval_precision": 0.
|
| 7 |
-
"eval_recall": 0.
|
| 8 |
-
"eval_runtime":
|
| 9 |
-
"eval_samples_per_second":
|
| 10 |
-
"eval_steps_per_second":
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 30.0,
|
| 3 |
+
"eval_accuracy": 0.9388888888888889,
|
| 4 |
+
"eval_f1": 0.8436018957345972,
|
| 5 |
+
"eval_loss": 0.15773314237594604,
|
| 6 |
+
"eval_precision": 0.8654781199351702,
|
| 7 |
+
"eval_recall": 0.8228043143297381,
|
| 8 |
+
"eval_runtime": 2.635,
|
| 9 |
+
"eval_samples_per_second": 122.962,
|
| 10 |
+
"eval_steps_per_second": 15.56
|
| 11 |
}
|
runs/Nov14_23-23-05_ba4b501b14a9/events.out.tfevents.1731627314.ba4b501b14a9.833.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06c4a31a750ad5b1bfddbbed253fc1582e33e701c2089178daa31f1a37ba4142
|
| 3 |
+
size 560
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 30.0,
|
| 3 |
"total_flos": 3.008454731998249e+18,
|
| 4 |
-
"train_loss": 0.
|
| 5 |
-
"train_runtime":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 3.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 30.0,
|
| 3 |
"total_flos": 3.008454731998249e+18,
|
| 4 |
+
"train_loss": 0.09584075045070531,
|
| 5 |
+
"train_runtime": 684.1699,
|
| 6 |
+
"train_samples_per_second": 56.74,
|
| 7 |
+
"train_steps_per_second": 3.552
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "frostsolutions/frost-vision-v2-google_vit-base-patch16-224-v2024-11-14/checkpoint-
|
| 4 |
"epoch": 30.0,
|
| 5 |
"eval_steps": 100,
|
| 6 |
"global_step": 2430,
|
|
@@ -10,2001 +10,2001 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.12345679012345678,
|
| 13 |
-
"grad_norm":
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.24691358024691357,
|
| 20 |
-
"grad_norm": 1.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.37037037037037035,
|
| 27 |
-
"grad_norm": 1.
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.49382716049382713,
|
| 34 |
-
"grad_norm": 1.
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.6172839506172839,
|
| 41 |
-
"grad_norm": 1.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.7407407407407407,
|
| 48 |
-
"grad_norm": 1.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.8641975308641975,
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.9876543209876543,
|
| 62 |
-
"grad_norm": 1.
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 1.1111111111111112,
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 1.2345679012345678,
|
| 76 |
-
"grad_norm": 0.
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.2345679012345678,
|
| 83 |
-
"eval_accuracy": 0.
|
| 84 |
-
"eval_f1": 0.
|
| 85 |
-
"eval_loss": 0.
|
| 86 |
-
"eval_precision": 0.
|
| 87 |
-
"eval_recall": 0.
|
| 88 |
-
"eval_runtime":
|
| 89 |
-
"eval_samples_per_second":
|
| 90 |
-
"eval_steps_per_second":
|
| 91 |
"step": 100
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 1.3580246913580247,
|
| 95 |
-
"grad_norm": 0.
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 110
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 1.4814814814814814,
|
| 102 |
-
"grad_norm": 0.
|
| 103 |
-
"learning_rate":
|
| 104 |
-
"loss": 0.
|
| 105 |
"step": 120
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 1.6049382716049383,
|
| 109 |
-
"grad_norm": 0.
|
| 110 |
-
"learning_rate":
|
| 111 |
-
"loss": 0.
|
| 112 |
"step": 130
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"epoch": 1.7283950617283952,
|
| 116 |
-
"grad_norm":
|
| 117 |
-
"learning_rate":
|
| 118 |
-
"loss": 0.
|
| 119 |
"step": 140
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 1.8518518518518519,
|
| 123 |
-
"grad_norm": 0.
|
| 124 |
-
"learning_rate":
|
| 125 |
-
"loss": 0.
|
| 126 |
"step": 150
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 1.9753086419753085,
|
| 130 |
-
"grad_norm":
|
| 131 |
-
"learning_rate":
|
| 132 |
-
"loss": 0.
|
| 133 |
"step": 160
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"epoch": 2.0987654320987654,
|
| 137 |
-
"grad_norm": 0.
|
| 138 |
-
"learning_rate":
|
| 139 |
-
"loss": 0.
|
| 140 |
"step": 170
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 2.2222222222222223,
|
| 144 |
-
"grad_norm":
|
| 145 |
-
"learning_rate":
|
| 146 |
-
"loss": 0.
|
| 147 |
"step": 180
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 2.3456790123456788,
|
| 151 |
-
"grad_norm": 0.
|
| 152 |
-
"learning_rate":
|
| 153 |
-
"loss": 0.
|
| 154 |
"step": 190
|
| 155 |
},
|
| 156 |
{
|
| 157 |
"epoch": 2.4691358024691357,
|
| 158 |
-
"grad_norm":
|
| 159 |
-
"learning_rate":
|
| 160 |
-
"loss": 0.
|
| 161 |
"step": 200
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 2.4691358024691357,
|
| 165 |
-
"eval_accuracy": 0.
|
| 166 |
-
"eval_f1": 0.
|
| 167 |
-
"eval_loss": 0.
|
| 168 |
-
"eval_precision": 0.
|
| 169 |
-
"eval_recall": 0.
|
| 170 |
-
"eval_runtime": 2.
|
| 171 |
-
"eval_samples_per_second":
|
| 172 |
-
"eval_steps_per_second": 15.
|
| 173 |
"step": 200
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 2.5925925925925926,
|
| 177 |
-
"grad_norm":
|
| 178 |
-
"learning_rate":
|
| 179 |
-
"loss": 0.
|
| 180 |
"step": 210
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 2.7160493827160495,
|
| 184 |
-
"grad_norm":
|
| 185 |
-
"learning_rate":
|
| 186 |
-
"loss": 0.
|
| 187 |
"step": 220
|
| 188 |
},
|
| 189 |
{
|
| 190 |
"epoch": 2.8395061728395063,
|
| 191 |
-
"grad_norm":
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss": 0.
|
| 194 |
"step": 230
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 2.962962962962963,
|
| 198 |
-
"grad_norm": 1.
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 0.
|
| 201 |
"step": 240
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 3.0864197530864197,
|
| 205 |
-
"grad_norm":
|
| 206 |
-
"learning_rate":
|
| 207 |
-
"loss": 0.
|
| 208 |
"step": 250
|
| 209 |
},
|
| 210 |
{
|
| 211 |
"epoch": 3.2098765432098766,
|
| 212 |
-
"grad_norm":
|
| 213 |
-
"learning_rate":
|
| 214 |
-
"loss": 0.
|
| 215 |
"step": 260
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 3.3333333333333335,
|
| 219 |
-
"grad_norm": 0.
|
| 220 |
-
"learning_rate":
|
| 221 |
-
"loss": 0.
|
| 222 |
"step": 270
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 3.45679012345679,
|
| 226 |
-
"grad_norm":
|
| 227 |
-
"learning_rate":
|
| 228 |
-
"loss": 0.
|
| 229 |
"step": 280
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"epoch": 3.580246913580247,
|
| 233 |
-
"grad_norm":
|
| 234 |
-
"learning_rate":
|
| 235 |
-
"loss": 0.
|
| 236 |
"step": 290
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 3.7037037037037037,
|
| 240 |
-
"grad_norm": 0.
|
| 241 |
-
"learning_rate":
|
| 242 |
-
"loss": 0.
|
| 243 |
"step": 300
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 3.7037037037037037,
|
| 247 |
-
"eval_accuracy": 0.
|
| 248 |
-
"eval_f1": 0.
|
| 249 |
-
"eval_loss": 0.
|
| 250 |
-
"eval_precision": 0.
|
| 251 |
-
"eval_recall": 0.
|
| 252 |
-
"eval_runtime":
|
| 253 |
-
"eval_samples_per_second":
|
| 254 |
-
"eval_steps_per_second":
|
| 255 |
"step": 300
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 3.8271604938271606,
|
| 259 |
-
"grad_norm": 0.
|
| 260 |
-
"learning_rate":
|
| 261 |
-
"loss": 0.
|
| 262 |
"step": 310
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 3.950617283950617,
|
| 266 |
-
"grad_norm": 0.
|
| 267 |
-
"learning_rate":
|
| 268 |
-
"loss": 0.
|
| 269 |
"step": 320
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 4.074074074074074,
|
| 273 |
-
"grad_norm": 0.
|
| 274 |
-
"learning_rate":
|
| 275 |
-
"loss": 0.
|
| 276 |
"step": 330
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 4.197530864197531,
|
| 280 |
-
"grad_norm": 0.
|
| 281 |
-
"learning_rate":
|
| 282 |
-
"loss": 0.
|
| 283 |
"step": 340
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 4.320987654320987,
|
| 287 |
-
"grad_norm": 1.
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss": 0.
|
| 290 |
"step": 350
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 4.444444444444445,
|
| 294 |
-
"grad_norm":
|
| 295 |
-
"learning_rate":
|
| 296 |
-
"loss": 0.
|
| 297 |
"step": 360
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 4.567901234567901,
|
| 301 |
-
"grad_norm":
|
| 302 |
-
"learning_rate":
|
| 303 |
-
"loss": 0.
|
| 304 |
"step": 370
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 4.6913580246913575,
|
| 308 |
-
"grad_norm":
|
| 309 |
-
"learning_rate":
|
| 310 |
-
"loss": 0.
|
| 311 |
"step": 380
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 4.814814814814815,
|
| 315 |
-
"grad_norm": 0.
|
| 316 |
-
"learning_rate":
|
| 317 |
-
"loss": 0.
|
| 318 |
"step": 390
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 4.938271604938271,
|
| 322 |
-
"grad_norm": 0.
|
| 323 |
-
"learning_rate":
|
| 324 |
-
"loss": 0.
|
| 325 |
"step": 400
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 4.938271604938271,
|
| 329 |
-
"eval_accuracy": 0.
|
| 330 |
-
"eval_f1": 0.
|
| 331 |
-
"eval_loss": 0.
|
| 332 |
-
"eval_precision": 0.
|
| 333 |
-
"eval_recall": 0.
|
| 334 |
-
"eval_runtime": 2.
|
| 335 |
-
"eval_samples_per_second":
|
| 336 |
-
"eval_steps_per_second": 16.
|
| 337 |
"step": 400
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 5.061728395061729,
|
| 341 |
-
"grad_norm": 0.
|
| 342 |
-
"learning_rate":
|
| 343 |
-
"loss": 0.
|
| 344 |
"step": 410
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 5.185185185185185,
|
| 348 |
-
"grad_norm": 0.
|
| 349 |
-
"learning_rate":
|
| 350 |
-
"loss": 0.
|
| 351 |
"step": 420
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 5.308641975308642,
|
| 355 |
-
"grad_norm":
|
| 356 |
-
"learning_rate":
|
| 357 |
-
"loss": 0.
|
| 358 |
"step": 430
|
| 359 |
},
|
| 360 |
{
|
| 361 |
"epoch": 5.432098765432099,
|
| 362 |
-
"grad_norm":
|
| 363 |
-
"learning_rate":
|
| 364 |
-
"loss": 0.
|
| 365 |
"step": 440
|
| 366 |
},
|
| 367 |
{
|
| 368 |
"epoch": 5.555555555555555,
|
| 369 |
-
"grad_norm": 0.
|
| 370 |
-
"learning_rate":
|
| 371 |
-
"loss": 0.
|
| 372 |
"step": 450
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 5.679012345679013,
|
| 376 |
-
"grad_norm": 0.
|
| 377 |
-
"learning_rate":
|
| 378 |
-
"loss": 0.
|
| 379 |
"step": 460
|
| 380 |
},
|
| 381 |
{
|
| 382 |
"epoch": 5.802469135802469,
|
| 383 |
-
"grad_norm": 1.
|
| 384 |
-
"learning_rate":
|
| 385 |
-
"loss": 0.
|
| 386 |
"step": 470
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 5.925925925925926,
|
| 390 |
-
"grad_norm": 0.
|
| 391 |
-
"learning_rate":
|
| 392 |
-
"loss": 0.
|
| 393 |
"step": 480
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 6.049382716049383,
|
| 397 |
-
"grad_norm": 0.
|
| 398 |
-
"learning_rate":
|
| 399 |
-
"loss": 0.
|
| 400 |
"step": 490
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"epoch": 6.172839506172839,
|
| 404 |
-
"grad_norm":
|
| 405 |
-
"learning_rate":
|
| 406 |
-
"loss": 0.
|
| 407 |
"step": 500
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 6.172839506172839,
|
| 411 |
-
"eval_accuracy": 0.
|
| 412 |
-
"eval_f1": 0.
|
| 413 |
-
"eval_loss": 0.
|
| 414 |
-
"eval_precision": 0.
|
| 415 |
-
"eval_recall": 0.
|
| 416 |
-
"eval_runtime":
|
| 417 |
-
"eval_samples_per_second":
|
| 418 |
-
"eval_steps_per_second":
|
| 419 |
"step": 500
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 6.296296296296296,
|
| 423 |
-
"grad_norm": 0.
|
| 424 |
-
"learning_rate":
|
| 425 |
-
"loss": 0.
|
| 426 |
"step": 510
|
| 427 |
},
|
| 428 |
{
|
| 429 |
"epoch": 6.419753086419753,
|
| 430 |
-
"grad_norm": 0.
|
| 431 |
-
"learning_rate":
|
| 432 |
-
"loss": 0.
|
| 433 |
"step": 520
|
| 434 |
},
|
| 435 |
{
|
| 436 |
"epoch": 6.54320987654321,
|
| 437 |
-
"grad_norm": 1.
|
| 438 |
-
"learning_rate":
|
| 439 |
-
"loss": 0.
|
| 440 |
"step": 530
|
| 441 |
},
|
| 442 |
{
|
| 443 |
"epoch": 6.666666666666667,
|
| 444 |
-
"grad_norm":
|
| 445 |
-
"learning_rate":
|
| 446 |
-
"loss": 0.
|
| 447 |
"step": 540
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 6.790123456790123,
|
| 451 |
-
"grad_norm": 0.
|
| 452 |
-
"learning_rate":
|
| 453 |
-
"loss": 0.
|
| 454 |
"step": 550
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"epoch": 6.91358024691358,
|
| 458 |
-
"grad_norm": 0.
|
| 459 |
-
"learning_rate":
|
| 460 |
-
"loss": 0.
|
| 461 |
"step": 560
|
| 462 |
},
|
| 463 |
{
|
| 464 |
"epoch": 7.037037037037037,
|
| 465 |
-
"grad_norm": 0.
|
| 466 |
-
"learning_rate":
|
| 467 |
-
"loss": 0.
|
| 468 |
"step": 570
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 7.160493827160494,
|
| 472 |
-
"grad_norm":
|
| 473 |
-
"learning_rate":
|
| 474 |
-
"loss": 0.
|
| 475 |
"step": 580
|
| 476 |
},
|
| 477 |
{
|
| 478 |
"epoch": 7.283950617283951,
|
| 479 |
-
"grad_norm": 0.
|
| 480 |
-
"learning_rate":
|
| 481 |
-
"loss": 0.
|
| 482 |
"step": 590
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 7.407407407407407,
|
| 486 |
-
"grad_norm":
|
| 487 |
-
"learning_rate":
|
| 488 |
-
"loss": 0.
|
| 489 |
"step": 600
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 7.407407407407407,
|
| 493 |
-
"eval_accuracy": 0.
|
| 494 |
-
"eval_f1": 0.
|
| 495 |
-
"eval_loss": 0.
|
| 496 |
-
"eval_precision": 0.
|
| 497 |
-
"eval_recall": 0.
|
| 498 |
-
"eval_runtime": 2.
|
| 499 |
-
"eval_samples_per_second":
|
| 500 |
-
"eval_steps_per_second": 17.
|
| 501 |
"step": 600
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 7.530864197530864,
|
| 505 |
-
"grad_norm": 0.
|
| 506 |
-
"learning_rate":
|
| 507 |
-
"loss": 0.
|
| 508 |
"step": 610
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 7.654320987654321,
|
| 512 |
-
"grad_norm": 0.
|
| 513 |
-
"learning_rate":
|
| 514 |
-
"loss": 0.
|
| 515 |
"step": 620
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 7.777777777777778,
|
| 519 |
-
"grad_norm": 0.
|
| 520 |
-
"learning_rate":
|
| 521 |
-
"loss": 0.
|
| 522 |
"step": 630
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 7.901234567901234,
|
| 526 |
-
"grad_norm":
|
| 527 |
-
"learning_rate":
|
| 528 |
-
"loss": 0.
|
| 529 |
"step": 640
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 8.024691358024691,
|
| 533 |
-
"grad_norm":
|
| 534 |
-
"learning_rate":
|
| 535 |
-
"loss": 0.
|
| 536 |
"step": 650
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 8.148148148148149,
|
| 540 |
-
"grad_norm":
|
| 541 |
-
"learning_rate":
|
| 542 |
-
"loss": 0.
|
| 543 |
"step": 660
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 8.271604938271604,
|
| 547 |
-
"grad_norm": 0.
|
| 548 |
-
"learning_rate":
|
| 549 |
-
"loss": 0.
|
| 550 |
"step": 670
|
| 551 |
},
|
| 552 |
{
|
| 553 |
"epoch": 8.395061728395062,
|
| 554 |
-
"grad_norm": 0.
|
| 555 |
-
"learning_rate":
|
| 556 |
-
"loss": 0.
|
| 557 |
"step": 680
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 8.518518518518519,
|
| 561 |
-
"grad_norm": 0.
|
| 562 |
-
"learning_rate":
|
| 563 |
-
"loss": 0.
|
| 564 |
"step": 690
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 8.641975308641975,
|
| 568 |
-
"grad_norm": 0.
|
| 569 |
-
"learning_rate":
|
| 570 |
-
"loss": 0.
|
| 571 |
"step": 700
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 8.641975308641975,
|
| 575 |
-
"eval_accuracy": 0.
|
| 576 |
-
"eval_f1": 0.
|
| 577 |
-
"eval_loss": 0.
|
| 578 |
-
"eval_precision": 0.
|
| 579 |
-
"eval_recall": 0.
|
| 580 |
-
"eval_runtime":
|
| 581 |
-
"eval_samples_per_second":
|
| 582 |
-
"eval_steps_per_second":
|
| 583 |
"step": 700
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 8.765432098765432,
|
| 587 |
-
"grad_norm": 0.
|
| 588 |
-
"learning_rate":
|
| 589 |
-
"loss": 0.
|
| 590 |
"step": 710
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 8.88888888888889,
|
| 594 |
-
"grad_norm":
|
| 595 |
-
"learning_rate":
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 720
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 9.012345679012345,
|
| 601 |
-
"grad_norm": 0.
|
| 602 |
-
"learning_rate":
|
| 603 |
-
"loss": 0.
|
| 604 |
"step": 730
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 9.135802469135802,
|
| 608 |
-
"grad_norm": 0.
|
| 609 |
-
"learning_rate":
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 740
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 9.25925925925926,
|
| 615 |
-
"grad_norm": 0.
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 750
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 9.382716049382717,
|
| 622 |
-
"grad_norm": 0.
|
| 623 |
-
"learning_rate":
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 760
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 9.506172839506172,
|
| 629 |
-
"grad_norm": 0.
|
| 630 |
-
"learning_rate":
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 770
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 9.62962962962963,
|
| 636 |
-
"grad_norm": 0.
|
| 637 |
-
"learning_rate":
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 780
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 9.753086419753087,
|
| 643 |
-
"grad_norm": 0.
|
| 644 |
-
"learning_rate":
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 790
|
| 647 |
},
|
| 648 |
{
|
| 649 |
"epoch": 9.876543209876543,
|
| 650 |
-
"grad_norm": 0.
|
| 651 |
-
"learning_rate":
|
| 652 |
-
"loss": 0.
|
| 653 |
"step": 800
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 9.876543209876543,
|
| 657 |
-
"eval_accuracy": 0.
|
| 658 |
-
"eval_f1": 0.
|
| 659 |
-
"eval_loss": 0.
|
| 660 |
-
"eval_precision": 0.
|
| 661 |
-
"eval_recall": 0.
|
| 662 |
-
"eval_runtime": 2.
|
| 663 |
-
"eval_samples_per_second":
|
| 664 |
-
"eval_steps_per_second":
|
| 665 |
"step": 800
|
| 666 |
},
|
| 667 |
{
|
| 668 |
"epoch": 10.0,
|
| 669 |
-
"grad_norm":
|
| 670 |
-
"learning_rate":
|
| 671 |
-
"loss": 0.
|
| 672 |
"step": 810
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 10.123456790123457,
|
| 676 |
-
"grad_norm": 0.
|
| 677 |
-
"learning_rate":
|
| 678 |
-
"loss": 0.
|
| 679 |
"step": 820
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"epoch": 10.246913580246913,
|
| 683 |
-
"grad_norm": 0.
|
| 684 |
-
"learning_rate":
|
| 685 |
-
"loss": 0.
|
| 686 |
"step": 830
|
| 687 |
},
|
| 688 |
{
|
| 689 |
"epoch": 10.37037037037037,
|
| 690 |
-
"grad_norm": 0.
|
| 691 |
-
"learning_rate":
|
| 692 |
-
"loss": 0.
|
| 693 |
"step": 840
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 10.493827160493828,
|
| 697 |
-
"grad_norm": 0.
|
| 698 |
-
"learning_rate":
|
| 699 |
-
"loss": 0.
|
| 700 |
"step": 850
|
| 701 |
},
|
| 702 |
{
|
| 703 |
"epoch": 10.617283950617283,
|
| 704 |
-
"grad_norm":
|
| 705 |
-
"learning_rate":
|
| 706 |
-
"loss": 0.
|
| 707 |
"step": 860
|
| 708 |
},
|
| 709 |
{
|
| 710 |
"epoch": 10.74074074074074,
|
| 711 |
-
"grad_norm": 0.
|
| 712 |
-
"learning_rate":
|
| 713 |
-
"loss": 0.
|
| 714 |
"step": 870
|
| 715 |
},
|
| 716 |
{
|
| 717 |
"epoch": 10.864197530864198,
|
| 718 |
-
"grad_norm": 1.
|
| 719 |
-
"learning_rate":
|
| 720 |
-
"loss": 0.
|
| 721 |
"step": 880
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 10.987654320987655,
|
| 725 |
-
"grad_norm":
|
| 726 |
-
"learning_rate":
|
| 727 |
-
"loss": 0.
|
| 728 |
"step": 890
|
| 729 |
},
|
| 730 |
{
|
| 731 |
"epoch": 11.11111111111111,
|
| 732 |
-
"grad_norm":
|
| 733 |
-
"learning_rate":
|
| 734 |
-
"loss": 0.
|
| 735 |
"step": 900
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 11.11111111111111,
|
| 739 |
-
"eval_accuracy": 0.
|
| 740 |
-
"eval_f1": 0.
|
| 741 |
-
"eval_loss": 0.
|
| 742 |
-
"eval_precision": 0.
|
| 743 |
-
"eval_recall": 0.
|
| 744 |
-
"eval_runtime": 2.
|
| 745 |
-
"eval_samples_per_second":
|
| 746 |
-
"eval_steps_per_second":
|
| 747 |
"step": 900
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 11.234567901234568,
|
| 751 |
-
"grad_norm": 0.
|
| 752 |
-
"learning_rate":
|
| 753 |
"loss": 0.0758,
|
| 754 |
"step": 910
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 11.358024691358025,
|
| 758 |
-
"grad_norm": 0.
|
| 759 |
-
"learning_rate":
|
| 760 |
-
"loss": 0.
|
| 761 |
"step": 920
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 11.481481481481481,
|
| 765 |
-
"grad_norm": 0.
|
| 766 |
-
"learning_rate":
|
| 767 |
-
"loss": 0.
|
| 768 |
"step": 930
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 11.604938271604938,
|
| 772 |
-
"grad_norm": 0.
|
| 773 |
-
"learning_rate":
|
| 774 |
-
"loss": 0.
|
| 775 |
"step": 940
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 11.728395061728396,
|
| 779 |
-
"grad_norm":
|
| 780 |
-
"learning_rate":
|
| 781 |
-
"loss": 0.
|
| 782 |
"step": 950
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 11.851851851851851,
|
| 786 |
-
"grad_norm": 0.
|
| 787 |
-
"learning_rate":
|
| 788 |
-
"loss": 0.
|
| 789 |
"step": 960
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 11.975308641975309,
|
| 793 |
-
"grad_norm": 0.
|
| 794 |
-
"learning_rate":
|
| 795 |
-
"loss": 0.
|
| 796 |
"step": 970
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"epoch": 12.098765432098766,
|
| 800 |
-
"grad_norm": 0.
|
| 801 |
-
"learning_rate":
|
| 802 |
-
"loss": 0.
|
| 803 |
"step": 980
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 12.222222222222221,
|
| 807 |
-
"grad_norm": 0.
|
| 808 |
-
"learning_rate":
|
| 809 |
-
"loss": 0.
|
| 810 |
"step": 990
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 12.345679012345679,
|
| 814 |
-
"grad_norm": 0.
|
| 815 |
-
"learning_rate":
|
| 816 |
-
"loss": 0.
|
| 817 |
"step": 1000
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 12.345679012345679,
|
| 821 |
-
"eval_accuracy": 0.
|
| 822 |
-
"eval_f1": 0.
|
| 823 |
-
"eval_loss": 0.
|
| 824 |
-
"eval_precision": 0.
|
| 825 |
-
"eval_recall": 0.
|
| 826 |
-
"eval_runtime":
|
| 827 |
-
"eval_samples_per_second":
|
| 828 |
-
"eval_steps_per_second":
|
| 829 |
"step": 1000
|
| 830 |
},
|
| 831 |
{
|
| 832 |
"epoch": 12.469135802469136,
|
| 833 |
-
"grad_norm": 0.
|
| 834 |
-
"learning_rate":
|
| 835 |
-
"loss": 0.
|
| 836 |
"step": 1010
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 12.592592592592592,
|
| 840 |
-
"grad_norm": 1.
|
| 841 |
-
"learning_rate":
|
| 842 |
-
"loss": 0.
|
| 843 |
"step": 1020
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 12.716049382716049,
|
| 847 |
-
"grad_norm": 0.
|
| 848 |
-
"learning_rate":
|
| 849 |
-
"loss": 0.
|
| 850 |
"step": 1030
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"epoch": 12.839506172839506,
|
| 854 |
-
"grad_norm": 0.
|
| 855 |
-
"learning_rate":
|
| 856 |
-
"loss": 0.
|
| 857 |
"step": 1040
|
| 858 |
},
|
| 859 |
{
|
| 860 |
"epoch": 12.962962962962964,
|
| 861 |
-
"grad_norm":
|
| 862 |
-
"learning_rate":
|
| 863 |
-
"loss": 0.
|
| 864 |
"step": 1050
|
| 865 |
},
|
| 866 |
{
|
| 867 |
"epoch": 13.08641975308642,
|
| 868 |
-
"grad_norm": 0.
|
| 869 |
-
"learning_rate":
|
| 870 |
-
"loss": 0.
|
| 871 |
"step": 1060
|
| 872 |
},
|
| 873 |
{
|
| 874 |
"epoch": 13.209876543209877,
|
| 875 |
-
"grad_norm": 0.
|
| 876 |
-
"learning_rate":
|
| 877 |
-
"loss": 0.
|
| 878 |
"step": 1070
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 13.333333333333334,
|
| 882 |
-
"grad_norm":
|
| 883 |
-
"learning_rate":
|
| 884 |
-
"loss": 0.
|
| 885 |
"step": 1080
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 13.45679012345679,
|
| 889 |
-
"grad_norm": 0.
|
| 890 |
-
"learning_rate":
|
| 891 |
-
"loss": 0.
|
| 892 |
"step": 1090
|
| 893 |
},
|
| 894 |
{
|
| 895 |
"epoch": 13.580246913580247,
|
| 896 |
-
"grad_norm": 1.
|
| 897 |
-
"learning_rate":
|
| 898 |
-
"loss": 0.
|
| 899 |
"step": 1100
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 13.580246913580247,
|
| 903 |
-
"eval_accuracy": 0.
|
| 904 |
-
"eval_f1": 0.
|
| 905 |
-
"eval_loss": 0.
|
| 906 |
-
"eval_precision": 0.
|
| 907 |
-
"eval_recall": 0.
|
| 908 |
-
"eval_runtime": 2.
|
| 909 |
-
"eval_samples_per_second":
|
| 910 |
-
"eval_steps_per_second":
|
| 911 |
"step": 1100
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 13.703703703703704,
|
| 915 |
-
"grad_norm": 0.
|
| 916 |
-
"learning_rate":
|
| 917 |
-
"loss": 0.
|
| 918 |
"step": 1110
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 13.82716049382716,
|
| 922 |
-
"grad_norm": 0.
|
| 923 |
-
"learning_rate":
|
| 924 |
-
"loss": 0.
|
| 925 |
"step": 1120
|
| 926 |
},
|
| 927 |
{
|
| 928 |
"epoch": 13.950617283950617,
|
| 929 |
-
"grad_norm": 0.
|
| 930 |
-
"learning_rate":
|
| 931 |
-
"loss": 0.
|
| 932 |
"step": 1130
|
| 933 |
},
|
| 934 |
{
|
| 935 |
"epoch": 14.074074074074074,
|
| 936 |
-
"grad_norm": 0.
|
| 937 |
-
"learning_rate":
|
| 938 |
-
"loss": 0.
|
| 939 |
"step": 1140
|
| 940 |
},
|
| 941 |
{
|
| 942 |
"epoch": 14.197530864197532,
|
| 943 |
-
"grad_norm": 0.
|
| 944 |
-
"learning_rate":
|
| 945 |
-
"loss": 0.
|
| 946 |
"step": 1150
|
| 947 |
},
|
| 948 |
{
|
| 949 |
"epoch": 14.320987654320987,
|
| 950 |
-
"grad_norm": 0.
|
| 951 |
-
"learning_rate":
|
| 952 |
-
"loss": 0.
|
| 953 |
"step": 1160
|
| 954 |
},
|
| 955 |
{
|
| 956 |
"epoch": 14.444444444444445,
|
| 957 |
-
"grad_norm": 0.
|
| 958 |
-
"learning_rate":
|
| 959 |
-
"loss": 0.
|
| 960 |
"step": 1170
|
| 961 |
},
|
| 962 |
{
|
| 963 |
"epoch": 14.567901234567902,
|
| 964 |
-
"grad_norm": 0.
|
| 965 |
-
"learning_rate":
|
| 966 |
-
"loss": 0.
|
| 967 |
"step": 1180
|
| 968 |
},
|
| 969 |
{
|
| 970 |
"epoch": 14.691358024691358,
|
| 971 |
-
"grad_norm": 0.
|
| 972 |
-
"learning_rate":
|
| 973 |
-
"loss": 0.
|
| 974 |
"step": 1190
|
| 975 |
},
|
| 976 |
{
|
| 977 |
"epoch": 14.814814814814815,
|
| 978 |
-
"grad_norm":
|
| 979 |
-
"learning_rate":
|
| 980 |
-
"loss": 0.
|
| 981 |
"step": 1200
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 14.814814814814815,
|
| 985 |
-
"eval_accuracy": 0.
|
| 986 |
-
"eval_f1": 0.
|
| 987 |
-
"eval_loss": 0.
|
| 988 |
-
"eval_precision": 0.
|
| 989 |
-
"eval_recall": 0.
|
| 990 |
-
"eval_runtime":
|
| 991 |
-
"eval_samples_per_second":
|
| 992 |
-
"eval_steps_per_second":
|
| 993 |
"step": 1200
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 14.938271604938272,
|
| 997 |
-
"grad_norm": 0.
|
| 998 |
-
"learning_rate":
|
| 999 |
-
"loss": 0.
|
| 1000 |
"step": 1210
|
| 1001 |
},
|
| 1002 |
{
|
| 1003 |
"epoch": 15.061728395061728,
|
| 1004 |
-
"grad_norm":
|
| 1005 |
-
"learning_rate":
|
| 1006 |
-
"loss": 0.
|
| 1007 |
"step": 1220
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
"epoch": 15.185185185185185,
|
| 1011 |
-
"grad_norm": 0.
|
| 1012 |
-
"learning_rate":
|
| 1013 |
-
"loss": 0.
|
| 1014 |
"step": 1230
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
"epoch": 15.308641975308642,
|
| 1018 |
-
"grad_norm":
|
| 1019 |
-
"learning_rate":
|
| 1020 |
-
"loss": 0.
|
| 1021 |
"step": 1240
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
"epoch": 15.432098765432098,
|
| 1025 |
-
"grad_norm": 0.
|
| 1026 |
-
"learning_rate":
|
| 1027 |
-
"loss": 0.
|
| 1028 |
"step": 1250
|
| 1029 |
},
|
| 1030 |
{
|
| 1031 |
"epoch": 15.555555555555555,
|
| 1032 |
-
"grad_norm": 0.
|
| 1033 |
-
"learning_rate":
|
| 1034 |
-
"loss": 0.
|
| 1035 |
"step": 1260
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 15.679012345679013,
|
| 1039 |
-
"grad_norm":
|
| 1040 |
-
"learning_rate":
|
| 1041 |
-
"loss": 0.
|
| 1042 |
"step": 1270
|
| 1043 |
},
|
| 1044 |
{
|
| 1045 |
"epoch": 15.802469135802468,
|
| 1046 |
-
"grad_norm": 0.
|
| 1047 |
-
"learning_rate":
|
| 1048 |
-
"loss": 0.
|
| 1049 |
"step": 1280
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 15.925925925925926,
|
| 1053 |
-
"grad_norm": 0.
|
| 1054 |
-
"learning_rate":
|
| 1055 |
-
"loss": 0.
|
| 1056 |
"step": 1290
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 16.049382716049383,
|
| 1060 |
-
"grad_norm":
|
| 1061 |
-
"learning_rate":
|
| 1062 |
-
"loss": 0.
|
| 1063 |
"step": 1300
|
| 1064 |
},
|
| 1065 |
{
|
| 1066 |
"epoch": 16.049382716049383,
|
| 1067 |
-
"eval_accuracy": 0.
|
| 1068 |
-
"eval_f1": 0.
|
| 1069 |
-
"eval_loss": 0.
|
| 1070 |
-
"eval_precision": 0.
|
| 1071 |
-
"eval_recall": 0.
|
| 1072 |
-
"eval_runtime":
|
| 1073 |
-
"eval_samples_per_second":
|
| 1074 |
-
"eval_steps_per_second":
|
| 1075 |
"step": 1300
|
| 1076 |
},
|
| 1077 |
{
|
| 1078 |
"epoch": 16.17283950617284,
|
| 1079 |
-
"grad_norm":
|
| 1080 |
-
"learning_rate":
|
| 1081 |
-
"loss": 0.
|
| 1082 |
"step": 1310
|
| 1083 |
},
|
| 1084 |
{
|
| 1085 |
"epoch": 16.296296296296298,
|
| 1086 |
-
"grad_norm": 0.
|
| 1087 |
-
"learning_rate":
|
| 1088 |
-
"loss": 0.
|
| 1089 |
"step": 1320
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
"epoch": 16.419753086419753,
|
| 1093 |
-
"grad_norm": 0.
|
| 1094 |
-
"learning_rate":
|
| 1095 |
"loss": 0.0534,
|
| 1096 |
"step": 1330
|
| 1097 |
},
|
| 1098 |
{
|
| 1099 |
"epoch": 16.54320987654321,
|
| 1100 |
-
"grad_norm": 0.
|
| 1101 |
-
"learning_rate":
|
| 1102 |
-
"loss": 0.
|
| 1103 |
"step": 1340
|
| 1104 |
},
|
| 1105 |
{
|
| 1106 |
"epoch": 16.666666666666668,
|
| 1107 |
-
"grad_norm": 0.
|
| 1108 |
-
"learning_rate":
|
| 1109 |
-
"loss": 0.
|
| 1110 |
"step": 1350
|
| 1111 |
},
|
| 1112 |
{
|
| 1113 |
"epoch": 16.790123456790123,
|
| 1114 |
-
"grad_norm": 0.
|
| 1115 |
-
"learning_rate":
|
| 1116 |
-
"loss": 0.
|
| 1117 |
"step": 1360
|
| 1118 |
},
|
| 1119 |
{
|
| 1120 |
"epoch": 16.91358024691358,
|
| 1121 |
-
"grad_norm":
|
| 1122 |
-
"learning_rate":
|
| 1123 |
-
"loss": 0.
|
| 1124 |
"step": 1370
|
| 1125 |
},
|
| 1126 |
{
|
| 1127 |
"epoch": 17.037037037037038,
|
| 1128 |
-
"grad_norm": 0.
|
| 1129 |
-
"learning_rate":
|
| 1130 |
-
"loss": 0.
|
| 1131 |
"step": 1380
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 17.160493827160494,
|
| 1135 |
-
"grad_norm": 0.
|
| 1136 |
-
"learning_rate":
|
| 1137 |
-
"loss": 0.
|
| 1138 |
"step": 1390
|
| 1139 |
},
|
| 1140 |
{
|
| 1141 |
"epoch": 17.28395061728395,
|
| 1142 |
-
"grad_norm": 0.
|
| 1143 |
-
"learning_rate":
|
| 1144 |
-
"loss": 0.
|
| 1145 |
"step": 1400
|
| 1146 |
},
|
| 1147 |
{
|
| 1148 |
"epoch": 17.28395061728395,
|
| 1149 |
-
"eval_accuracy": 0.
|
| 1150 |
-
"eval_f1": 0.
|
| 1151 |
-
"eval_loss": 0.
|
| 1152 |
-
"eval_precision": 0.
|
| 1153 |
-
"eval_recall": 0.
|
| 1154 |
-
"eval_runtime": 2.
|
| 1155 |
-
"eval_samples_per_second":
|
| 1156 |
-
"eval_steps_per_second":
|
| 1157 |
"step": 1400
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 17.40740740740741,
|
| 1161 |
-
"grad_norm":
|
| 1162 |
-
"learning_rate":
|
| 1163 |
-
"loss": 0.
|
| 1164 |
"step": 1410
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 17.530864197530864,
|
| 1168 |
-
"grad_norm": 0.
|
| 1169 |
-
"learning_rate":
|
| 1170 |
-
"loss": 0.
|
| 1171 |
"step": 1420
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 17.65432098765432,
|
| 1175 |
-
"grad_norm": 0.
|
| 1176 |
-
"learning_rate":
|
| 1177 |
-
"loss": 0.
|
| 1178 |
"step": 1430
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
"epoch": 17.77777777777778,
|
| 1182 |
-
"grad_norm": 0.
|
| 1183 |
-
"learning_rate":
|
| 1184 |
-
"loss": 0.
|
| 1185 |
"step": 1440
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 17.901234567901234,
|
| 1189 |
-
"grad_norm":
|
| 1190 |
-
"learning_rate":
|
| 1191 |
-
"loss": 0.
|
| 1192 |
"step": 1450
|
| 1193 |
},
|
| 1194 |
{
|
| 1195 |
"epoch": 18.02469135802469,
|
| 1196 |
-
"grad_norm": 0.
|
| 1197 |
-
"learning_rate":
|
| 1198 |
-
"loss": 0.
|
| 1199 |
"step": 1460
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
"epoch": 18.14814814814815,
|
| 1203 |
-
"grad_norm": 0.
|
| 1204 |
-
"learning_rate":
|
| 1205 |
-
"loss": 0.
|
| 1206 |
"step": 1470
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
"epoch": 18.271604938271604,
|
| 1210 |
-
"grad_norm": 0.
|
| 1211 |
-
"learning_rate":
|
| 1212 |
-
"loss": 0.
|
| 1213 |
"step": 1480
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
"epoch": 18.395061728395063,
|
| 1217 |
-
"grad_norm": 0.
|
| 1218 |
-
"learning_rate":
|
| 1219 |
-
"loss": 0.
|
| 1220 |
"step": 1490
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 18.51851851851852,
|
| 1224 |
-
"grad_norm": 0.
|
| 1225 |
-
"learning_rate":
|
| 1226 |
-
"loss": 0.
|
| 1227 |
"step": 1500
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 18.51851851851852,
|
| 1231 |
-
"eval_accuracy": 0.
|
| 1232 |
-
"eval_f1": 0.
|
| 1233 |
-
"eval_loss": 0.
|
| 1234 |
-
"eval_precision": 0.
|
| 1235 |
-
"eval_recall": 0.
|
| 1236 |
-
"eval_runtime": 2.
|
| 1237 |
-
"eval_samples_per_second":
|
| 1238 |
-
"eval_steps_per_second":
|
| 1239 |
"step": 1500
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 18.641975308641975,
|
| 1243 |
-
"grad_norm":
|
| 1244 |
-
"learning_rate":
|
| 1245 |
-
"loss": 0.
|
| 1246 |
"step": 1510
|
| 1247 |
},
|
| 1248 |
{
|
| 1249 |
"epoch": 18.765432098765434,
|
| 1250 |
-
"grad_norm":
|
| 1251 |
-
"learning_rate":
|
| 1252 |
-
"loss": 0.
|
| 1253 |
"step": 1520
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 18.88888888888889,
|
| 1257 |
-
"grad_norm": 0.
|
| 1258 |
-
"learning_rate":
|
| 1259 |
-
"loss": 0.
|
| 1260 |
"step": 1530
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 19.012345679012345,
|
| 1264 |
-
"grad_norm": 0.
|
| 1265 |
-
"learning_rate":
|
| 1266 |
-
"loss": 0.
|
| 1267 |
"step": 1540
|
| 1268 |
},
|
| 1269 |
{
|
| 1270 |
"epoch": 19.135802469135804,
|
| 1271 |
-
"grad_norm": 0.
|
| 1272 |
-
"learning_rate":
|
| 1273 |
"loss": 0.0404,
|
| 1274 |
"step": 1550
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 19.25925925925926,
|
| 1278 |
-
"grad_norm": 0.
|
| 1279 |
-
"learning_rate":
|
| 1280 |
-
"loss": 0.
|
| 1281 |
"step": 1560
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 19.382716049382715,
|
| 1285 |
-
"grad_norm": 0.
|
| 1286 |
-
"learning_rate":
|
| 1287 |
-
"loss": 0.
|
| 1288 |
"step": 1570
|
| 1289 |
},
|
| 1290 |
{
|
| 1291 |
"epoch": 19.506172839506174,
|
| 1292 |
-
"grad_norm": 0.
|
| 1293 |
-
"learning_rate":
|
| 1294 |
-
"loss": 0.
|
| 1295 |
"step": 1580
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
"epoch": 19.62962962962963,
|
| 1299 |
-
"grad_norm": 0.
|
| 1300 |
-
"learning_rate":
|
| 1301 |
-
"loss": 0.
|
| 1302 |
"step": 1590
|
| 1303 |
},
|
| 1304 |
{
|
| 1305 |
"epoch": 19.753086419753085,
|
| 1306 |
-
"grad_norm": 0.
|
| 1307 |
-
"learning_rate":
|
| 1308 |
-
"loss": 0.
|
| 1309 |
"step": 1600
|
| 1310 |
},
|
| 1311 |
{
|
| 1312 |
"epoch": 19.753086419753085,
|
| 1313 |
-
"eval_accuracy": 0.
|
| 1314 |
-
"eval_f1": 0.
|
| 1315 |
-
"eval_loss": 0.
|
| 1316 |
-
"eval_precision": 0.
|
| 1317 |
-
"eval_recall": 0.
|
| 1318 |
-
"eval_runtime":
|
| 1319 |
-
"eval_samples_per_second":
|
| 1320 |
-
"eval_steps_per_second":
|
| 1321 |
"step": 1600
|
| 1322 |
},
|
| 1323 |
{
|
| 1324 |
"epoch": 19.876543209876544,
|
| 1325 |
-
"grad_norm": 0.
|
| 1326 |
-
"learning_rate":
|
| 1327 |
-
"loss": 0.
|
| 1328 |
"step": 1610
|
| 1329 |
},
|
| 1330 |
{
|
| 1331 |
"epoch": 20.0,
|
| 1332 |
-
"grad_norm": 0.
|
| 1333 |
-
"learning_rate":
|
| 1334 |
-
"loss": 0.
|
| 1335 |
"step": 1620
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
"epoch": 20.123456790123456,
|
| 1339 |
-
"grad_norm": 0.
|
| 1340 |
-
"learning_rate":
|
| 1341 |
-
"loss": 0.
|
| 1342 |
"step": 1630
|
| 1343 |
},
|
| 1344 |
{
|
| 1345 |
"epoch": 20.246913580246915,
|
| 1346 |
-
"grad_norm": 0.
|
| 1347 |
-
"learning_rate":
|
| 1348 |
-
"loss": 0.
|
| 1349 |
"step": 1640
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 20.37037037037037,
|
| 1353 |
-
"grad_norm": 0.
|
| 1354 |
-
"learning_rate":
|
| 1355 |
-
"loss": 0.
|
| 1356 |
"step": 1650
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 20.493827160493826,
|
| 1360 |
-
"grad_norm": 0.
|
| 1361 |
-
"learning_rate":
|
| 1362 |
-
"loss": 0.
|
| 1363 |
"step": 1660
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
"epoch": 20.617283950617285,
|
| 1367 |
-
"grad_norm": 0.
|
| 1368 |
-
"learning_rate":
|
| 1369 |
-
"loss": 0.
|
| 1370 |
"step": 1670
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 20.74074074074074,
|
| 1374 |
-
"grad_norm": 0.
|
| 1375 |
-
"learning_rate":
|
| 1376 |
-
"loss": 0.
|
| 1377 |
"step": 1680
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 20.864197530864196,
|
| 1381 |
-
"grad_norm": 0.
|
| 1382 |
-
"learning_rate":
|
| 1383 |
-
"loss": 0.
|
| 1384 |
"step": 1690
|
| 1385 |
},
|
| 1386 |
{
|
| 1387 |
"epoch": 20.987654320987655,
|
| 1388 |
-
"grad_norm": 0.
|
| 1389 |
-
"learning_rate":
|
| 1390 |
-
"loss": 0.
|
| 1391 |
"step": 1700
|
| 1392 |
},
|
| 1393 |
{
|
| 1394 |
"epoch": 20.987654320987655,
|
| 1395 |
-
"eval_accuracy": 0.
|
| 1396 |
-
"eval_f1": 0.
|
| 1397 |
-
"eval_loss": 0.
|
| 1398 |
-
"eval_precision": 0.
|
| 1399 |
-
"eval_recall": 0.
|
| 1400 |
-
"eval_runtime": 2.
|
| 1401 |
-
"eval_samples_per_second":
|
| 1402 |
-
"eval_steps_per_second":
|
| 1403 |
"step": 1700
|
| 1404 |
},
|
| 1405 |
{
|
| 1406 |
"epoch": 21.11111111111111,
|
| 1407 |
-
"grad_norm": 0.
|
| 1408 |
-
"learning_rate":
|
| 1409 |
-
"loss": 0.
|
| 1410 |
"step": 1710
|
| 1411 |
},
|
| 1412 |
{
|
| 1413 |
"epoch": 21.234567901234566,
|
| 1414 |
-
"grad_norm": 0.
|
| 1415 |
-
"learning_rate":
|
| 1416 |
-
"loss": 0.
|
| 1417 |
"step": 1720
|
| 1418 |
},
|
| 1419 |
{
|
| 1420 |
"epoch": 21.358024691358025,
|
| 1421 |
-
"grad_norm": 0.
|
| 1422 |
-
"learning_rate":
|
| 1423 |
-
"loss": 0.
|
| 1424 |
"step": 1730
|
| 1425 |
},
|
| 1426 |
{
|
| 1427 |
"epoch": 21.48148148148148,
|
| 1428 |
-
"grad_norm": 0.
|
| 1429 |
-
"learning_rate":
|
| 1430 |
-
"loss": 0.
|
| 1431 |
"step": 1740
|
| 1432 |
},
|
| 1433 |
{
|
| 1434 |
"epoch": 21.604938271604937,
|
| 1435 |
-
"grad_norm": 0.
|
| 1436 |
-
"learning_rate":
|
| 1437 |
-
"loss": 0.
|
| 1438 |
"step": 1750
|
| 1439 |
},
|
| 1440 |
{
|
| 1441 |
"epoch": 21.728395061728396,
|
| 1442 |
-
"grad_norm": 0.
|
| 1443 |
-
"learning_rate":
|
| 1444 |
-
"loss": 0.
|
| 1445 |
"step": 1760
|
| 1446 |
},
|
| 1447 |
{
|
| 1448 |
"epoch": 21.85185185185185,
|
| 1449 |
-
"grad_norm": 0.
|
| 1450 |
-
"learning_rate":
|
| 1451 |
-
"loss": 0.
|
| 1452 |
"step": 1770
|
| 1453 |
},
|
| 1454 |
{
|
| 1455 |
"epoch": 21.97530864197531,
|
| 1456 |
-
"grad_norm": 0.
|
| 1457 |
-
"learning_rate":
|
| 1458 |
-
"loss": 0.
|
| 1459 |
"step": 1780
|
| 1460 |
},
|
| 1461 |
{
|
| 1462 |
"epoch": 22.098765432098766,
|
| 1463 |
-
"grad_norm": 0.
|
| 1464 |
-
"learning_rate":
|
| 1465 |
-
"loss": 0.
|
| 1466 |
"step": 1790
|
| 1467 |
},
|
| 1468 |
{
|
| 1469 |
"epoch": 22.22222222222222,
|
| 1470 |
-
"grad_norm": 0.
|
| 1471 |
-
"learning_rate":
|
| 1472 |
-
"loss": 0.
|
| 1473 |
"step": 1800
|
| 1474 |
},
|
| 1475 |
{
|
| 1476 |
"epoch": 22.22222222222222,
|
| 1477 |
-
"eval_accuracy": 0.
|
| 1478 |
-
"eval_f1": 0.
|
| 1479 |
-
"eval_loss": 0.
|
| 1480 |
-
"eval_precision": 0.
|
| 1481 |
-
"eval_recall": 0.
|
| 1482 |
-
"eval_runtime": 2.
|
| 1483 |
-
"eval_samples_per_second":
|
| 1484 |
-
"eval_steps_per_second": 17.
|
| 1485 |
"step": 1800
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
"epoch": 22.34567901234568,
|
| 1489 |
-
"grad_norm": 0.
|
| 1490 |
-
"learning_rate":
|
| 1491 |
-
"loss": 0.
|
| 1492 |
"step": 1810
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
"epoch": 22.469135802469136,
|
| 1496 |
-
"grad_norm": 0.
|
| 1497 |
-
"learning_rate":
|
| 1498 |
-
"loss": 0.
|
| 1499 |
"step": 1820
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
"epoch": 22.59259259259259,
|
| 1503 |
-
"grad_norm": 0.
|
| 1504 |
-
"learning_rate":
|
| 1505 |
-
"loss": 0.
|
| 1506 |
"step": 1830
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
"epoch": 22.71604938271605,
|
| 1510 |
-
"grad_norm": 0.
|
| 1511 |
-
"learning_rate":
|
| 1512 |
-
"loss": 0.
|
| 1513 |
"step": 1840
|
| 1514 |
},
|
| 1515 |
{
|
| 1516 |
"epoch": 22.839506172839506,
|
| 1517 |
-
"grad_norm":
|
| 1518 |
-
"learning_rate":
|
| 1519 |
-
"loss": 0.
|
| 1520 |
"step": 1850
|
| 1521 |
},
|
| 1522 |
{
|
| 1523 |
"epoch": 22.962962962962962,
|
| 1524 |
-
"grad_norm": 0.
|
| 1525 |
-
"learning_rate":
|
| 1526 |
-
"loss": 0.
|
| 1527 |
"step": 1860
|
| 1528 |
},
|
| 1529 |
{
|
| 1530 |
"epoch": 23.08641975308642,
|
| 1531 |
-
"grad_norm": 0.
|
| 1532 |
-
"learning_rate":
|
| 1533 |
-
"loss": 0.
|
| 1534 |
"step": 1870
|
| 1535 |
},
|
| 1536 |
{
|
| 1537 |
"epoch": 23.209876543209877,
|
| 1538 |
-
"grad_norm": 0.
|
| 1539 |
-
"learning_rate":
|
| 1540 |
-
"loss": 0.
|
| 1541 |
"step": 1880
|
| 1542 |
},
|
| 1543 |
{
|
| 1544 |
"epoch": 23.333333333333332,
|
| 1545 |
-
"grad_norm": 0.
|
| 1546 |
-
"learning_rate":
|
| 1547 |
-
"loss": 0.
|
| 1548 |
"step": 1890
|
| 1549 |
},
|
| 1550 |
{
|
| 1551 |
"epoch": 23.45679012345679,
|
| 1552 |
-
"grad_norm": 0.
|
| 1553 |
-
"learning_rate":
|
| 1554 |
-
"loss": 0.
|
| 1555 |
"step": 1900
|
| 1556 |
},
|
| 1557 |
{
|
| 1558 |
"epoch": 23.45679012345679,
|
| 1559 |
-
"eval_accuracy": 0.
|
| 1560 |
-
"eval_f1": 0.
|
| 1561 |
-
"eval_loss": 0.
|
| 1562 |
-
"eval_precision": 0.
|
| 1563 |
-
"eval_recall": 0.
|
| 1564 |
-
"eval_runtime":
|
| 1565 |
-
"eval_samples_per_second":
|
| 1566 |
-
"eval_steps_per_second":
|
| 1567 |
"step": 1900
|
| 1568 |
},
|
| 1569 |
{
|
| 1570 |
"epoch": 23.580246913580247,
|
| 1571 |
-
"grad_norm": 0.
|
| 1572 |
-
"learning_rate":
|
| 1573 |
-
"loss": 0.
|
| 1574 |
"step": 1910
|
| 1575 |
},
|
| 1576 |
{
|
| 1577 |
"epoch": 23.703703703703702,
|
| 1578 |
-
"grad_norm": 0.
|
| 1579 |
-
"learning_rate":
|
| 1580 |
-
"loss": 0.
|
| 1581 |
"step": 1920
|
| 1582 |
},
|
| 1583 |
{
|
| 1584 |
"epoch": 23.82716049382716,
|
| 1585 |
-
"grad_norm": 0.
|
| 1586 |
-
"learning_rate":
|
| 1587 |
-
"loss": 0.
|
| 1588 |
"step": 1930
|
| 1589 |
},
|
| 1590 |
{
|
| 1591 |
"epoch": 23.950617283950617,
|
| 1592 |
-
"grad_norm": 0.
|
| 1593 |
-
"learning_rate":
|
| 1594 |
-
"loss": 0.
|
| 1595 |
"step": 1940
|
| 1596 |
},
|
| 1597 |
{
|
| 1598 |
"epoch": 24.074074074074073,
|
| 1599 |
-
"grad_norm": 0.
|
| 1600 |
-
"learning_rate":
|
| 1601 |
-
"loss": 0.
|
| 1602 |
"step": 1950
|
| 1603 |
},
|
| 1604 |
{
|
| 1605 |
"epoch": 24.19753086419753,
|
| 1606 |
-
"grad_norm":
|
| 1607 |
-
"learning_rate":
|
| 1608 |
-
"loss": 0.
|
| 1609 |
"step": 1960
|
| 1610 |
},
|
| 1611 |
{
|
| 1612 |
"epoch": 24.320987654320987,
|
| 1613 |
-
"grad_norm": 0.
|
| 1614 |
-
"learning_rate":
|
| 1615 |
-
"loss": 0.
|
| 1616 |
"step": 1970
|
| 1617 |
},
|
| 1618 |
{
|
| 1619 |
"epoch": 24.444444444444443,
|
| 1620 |
-
"grad_norm": 0.
|
| 1621 |
-
"learning_rate":
|
| 1622 |
-
"loss": 0.
|
| 1623 |
"step": 1980
|
| 1624 |
},
|
| 1625 |
{
|
| 1626 |
"epoch": 24.567901234567902,
|
| 1627 |
-
"grad_norm": 0.
|
| 1628 |
-
"learning_rate":
|
| 1629 |
-
"loss": 0.
|
| 1630 |
"step": 1990
|
| 1631 |
},
|
| 1632 |
{
|
| 1633 |
"epoch": 24.691358024691358,
|
| 1634 |
-
"grad_norm": 0.
|
| 1635 |
-
"learning_rate":
|
| 1636 |
-
"loss": 0.
|
| 1637 |
"step": 2000
|
| 1638 |
},
|
| 1639 |
{
|
| 1640 |
"epoch": 24.691358024691358,
|
| 1641 |
-
"eval_accuracy": 0.
|
| 1642 |
-
"eval_f1": 0.
|
| 1643 |
-
"eval_loss": 0.
|
| 1644 |
-
"eval_precision": 0.
|
| 1645 |
-
"eval_recall": 0.
|
| 1646 |
-
"eval_runtime":
|
| 1647 |
-
"eval_samples_per_second":
|
| 1648 |
-
"eval_steps_per_second":
|
| 1649 |
"step": 2000
|
| 1650 |
},
|
| 1651 |
{
|
| 1652 |
"epoch": 24.814814814814813,
|
| 1653 |
-
"grad_norm": 0.
|
| 1654 |
-
"learning_rate":
|
| 1655 |
-
"loss": 0.
|
| 1656 |
"step": 2010
|
| 1657 |
},
|
| 1658 |
{
|
| 1659 |
"epoch": 24.938271604938272,
|
| 1660 |
-
"grad_norm": 0.
|
| 1661 |
-
"learning_rate":
|
| 1662 |
-
"loss": 0.
|
| 1663 |
"step": 2020
|
| 1664 |
},
|
| 1665 |
{
|
| 1666 |
"epoch": 25.061728395061728,
|
| 1667 |
-
"grad_norm": 0.
|
| 1668 |
-
"learning_rate":
|
| 1669 |
-
"loss": 0.
|
| 1670 |
"step": 2030
|
| 1671 |
},
|
| 1672 |
{
|
| 1673 |
"epoch": 25.185185185185187,
|
| 1674 |
-
"grad_norm": 0.
|
| 1675 |
-
"learning_rate":
|
| 1676 |
-
"loss": 0.
|
| 1677 |
"step": 2040
|
| 1678 |
},
|
| 1679 |
{
|
| 1680 |
"epoch": 25.308641975308642,
|
| 1681 |
-
"grad_norm": 0.
|
| 1682 |
-
"learning_rate":
|
| 1683 |
-
"loss": 0.
|
| 1684 |
"step": 2050
|
| 1685 |
},
|
| 1686 |
{
|
| 1687 |
"epoch": 25.432098765432098,
|
| 1688 |
-
"grad_norm": 0.
|
| 1689 |
-
"learning_rate":
|
| 1690 |
-
"loss": 0.
|
| 1691 |
"step": 2060
|
| 1692 |
},
|
| 1693 |
{
|
| 1694 |
"epoch": 25.555555555555557,
|
| 1695 |
-
"grad_norm":
|
| 1696 |
-
"learning_rate":
|
| 1697 |
-
"loss": 0.
|
| 1698 |
"step": 2070
|
| 1699 |
},
|
| 1700 |
{
|
| 1701 |
"epoch": 25.679012345679013,
|
| 1702 |
-
"grad_norm": 0.
|
| 1703 |
-
"learning_rate":
|
| 1704 |
-
"loss": 0.
|
| 1705 |
"step": 2080
|
| 1706 |
},
|
| 1707 |
{
|
| 1708 |
"epoch": 25.80246913580247,
|
| 1709 |
-
"grad_norm": 0.
|
| 1710 |
-
"learning_rate":
|
| 1711 |
-
"loss": 0.
|
| 1712 |
"step": 2090
|
| 1713 |
},
|
| 1714 |
{
|
| 1715 |
"epoch": 25.925925925925927,
|
| 1716 |
-
"grad_norm": 0.
|
| 1717 |
-
"learning_rate":
|
| 1718 |
-
"loss": 0.
|
| 1719 |
"step": 2100
|
| 1720 |
},
|
| 1721 |
{
|
| 1722 |
"epoch": 25.925925925925927,
|
| 1723 |
-
"eval_accuracy": 0.
|
| 1724 |
-
"eval_f1": 0.
|
| 1725 |
-
"eval_loss": 0.
|
| 1726 |
-
"eval_precision": 0.
|
| 1727 |
-
"eval_recall": 0.
|
| 1728 |
-
"eval_runtime":
|
| 1729 |
-
"eval_samples_per_second":
|
| 1730 |
-
"eval_steps_per_second":
|
| 1731 |
"step": 2100
|
| 1732 |
},
|
| 1733 |
{
|
| 1734 |
"epoch": 26.049382716049383,
|
| 1735 |
-
"grad_norm": 0.
|
| 1736 |
-
"learning_rate":
|
| 1737 |
-
"loss": 0.
|
| 1738 |
"step": 2110
|
| 1739 |
},
|
| 1740 |
{
|
| 1741 |
"epoch": 26.17283950617284,
|
| 1742 |
-
"grad_norm":
|
| 1743 |
-
"learning_rate":
|
| 1744 |
-
"loss": 0.
|
| 1745 |
"step": 2120
|
| 1746 |
},
|
| 1747 |
{
|
| 1748 |
"epoch": 26.296296296296298,
|
| 1749 |
-
"grad_norm": 0.
|
| 1750 |
-
"learning_rate":
|
| 1751 |
-
"loss": 0.
|
| 1752 |
"step": 2130
|
| 1753 |
},
|
| 1754 |
{
|
| 1755 |
"epoch": 26.419753086419753,
|
| 1756 |
-
"grad_norm": 0.
|
| 1757 |
-
"learning_rate":
|
| 1758 |
-
"loss": 0.
|
| 1759 |
"step": 2140
|
| 1760 |
},
|
| 1761 |
{
|
| 1762 |
"epoch": 26.54320987654321,
|
| 1763 |
-
"grad_norm":
|
| 1764 |
-
"learning_rate":
|
| 1765 |
-
"loss": 0.
|
| 1766 |
"step": 2150
|
| 1767 |
},
|
| 1768 |
{
|
| 1769 |
"epoch": 26.666666666666668,
|
| 1770 |
-
"grad_norm": 0.
|
| 1771 |
-
"learning_rate":
|
| 1772 |
-
"loss": 0.
|
| 1773 |
"step": 2160
|
| 1774 |
},
|
| 1775 |
{
|
| 1776 |
"epoch": 26.790123456790123,
|
| 1777 |
-
"grad_norm": 0.
|
| 1778 |
-
"learning_rate":
|
| 1779 |
-
"loss": 0.
|
| 1780 |
"step": 2170
|
| 1781 |
},
|
| 1782 |
{
|
| 1783 |
"epoch": 26.91358024691358,
|
| 1784 |
-
"grad_norm": 0.
|
| 1785 |
-
"learning_rate":
|
| 1786 |
-
"loss": 0.
|
| 1787 |
"step": 2180
|
| 1788 |
},
|
| 1789 |
{
|
| 1790 |
"epoch": 27.037037037037038,
|
| 1791 |
-
"grad_norm": 0.
|
| 1792 |
-
"learning_rate":
|
| 1793 |
-
"loss": 0.
|
| 1794 |
"step": 2190
|
| 1795 |
},
|
| 1796 |
{
|
| 1797 |
"epoch": 27.160493827160494,
|
| 1798 |
-
"grad_norm": 0.
|
| 1799 |
-
"learning_rate":
|
| 1800 |
-
"loss": 0.
|
| 1801 |
"step": 2200
|
| 1802 |
},
|
| 1803 |
{
|
| 1804 |
"epoch": 27.160493827160494,
|
| 1805 |
-
"eval_accuracy": 0.
|
| 1806 |
-
"eval_f1": 0.
|
| 1807 |
-
"eval_loss": 0.
|
| 1808 |
-
"eval_precision": 0.
|
| 1809 |
-
"eval_recall": 0.
|
| 1810 |
-
"eval_runtime": 3.
|
| 1811 |
-
"eval_samples_per_second":
|
| 1812 |
-
"eval_steps_per_second":
|
| 1813 |
"step": 2200
|
| 1814 |
},
|
| 1815 |
{
|
| 1816 |
"epoch": 27.28395061728395,
|
| 1817 |
-
"grad_norm": 0.
|
| 1818 |
-
"learning_rate":
|
| 1819 |
-
"loss": 0.
|
| 1820 |
"step": 2210
|
| 1821 |
},
|
| 1822 |
{
|
| 1823 |
"epoch": 27.40740740740741,
|
| 1824 |
-
"grad_norm": 0.
|
| 1825 |
-
"learning_rate":
|
| 1826 |
-
"loss": 0.
|
| 1827 |
"step": 2220
|
| 1828 |
},
|
| 1829 |
{
|
| 1830 |
"epoch": 27.530864197530864,
|
| 1831 |
-
"grad_norm": 0.
|
| 1832 |
-
"learning_rate":
|
| 1833 |
-
"loss": 0.
|
| 1834 |
"step": 2230
|
| 1835 |
},
|
| 1836 |
{
|
| 1837 |
"epoch": 27.65432098765432,
|
| 1838 |
-
"grad_norm": 0.
|
| 1839 |
-
"learning_rate":
|
| 1840 |
-
"loss": 0.
|
| 1841 |
"step": 2240
|
| 1842 |
},
|
| 1843 |
{
|
| 1844 |
"epoch": 27.77777777777778,
|
| 1845 |
-
"grad_norm": 0.
|
| 1846 |
-
"learning_rate":
|
| 1847 |
-
"loss": 0.
|
| 1848 |
"step": 2250
|
| 1849 |
},
|
| 1850 |
{
|
| 1851 |
"epoch": 27.901234567901234,
|
| 1852 |
-
"grad_norm": 0.
|
| 1853 |
-
"learning_rate":
|
| 1854 |
-
"loss": 0.
|
| 1855 |
"step": 2260
|
| 1856 |
},
|
| 1857 |
{
|
| 1858 |
"epoch": 28.02469135802469,
|
| 1859 |
-
"grad_norm": 0.
|
| 1860 |
-
"learning_rate":
|
| 1861 |
-
"loss": 0.
|
| 1862 |
"step": 2270
|
| 1863 |
},
|
| 1864 |
{
|
| 1865 |
"epoch": 28.14814814814815,
|
| 1866 |
-
"grad_norm":
|
| 1867 |
-
"learning_rate":
|
| 1868 |
-
"loss": 0.
|
| 1869 |
"step": 2280
|
| 1870 |
},
|
| 1871 |
{
|
| 1872 |
"epoch": 28.271604938271604,
|
| 1873 |
-
"grad_norm": 0.
|
| 1874 |
-
"learning_rate":
|
| 1875 |
-
"loss": 0.
|
| 1876 |
"step": 2290
|
| 1877 |
},
|
| 1878 |
{
|
| 1879 |
"epoch": 28.395061728395063,
|
| 1880 |
-
"grad_norm": 0.
|
| 1881 |
-
"learning_rate":
|
| 1882 |
-
"loss": 0.
|
| 1883 |
"step": 2300
|
| 1884 |
},
|
| 1885 |
{
|
| 1886 |
"epoch": 28.395061728395063,
|
| 1887 |
-
"eval_accuracy": 0.
|
| 1888 |
-
"eval_f1": 0.
|
| 1889 |
-
"eval_loss": 0.
|
| 1890 |
-
"eval_precision": 0.
|
| 1891 |
-
"eval_recall": 0.
|
| 1892 |
-
"eval_runtime": 2.
|
| 1893 |
-
"eval_samples_per_second":
|
| 1894 |
-
"eval_steps_per_second":
|
| 1895 |
"step": 2300
|
| 1896 |
},
|
| 1897 |
{
|
| 1898 |
"epoch": 28.51851851851852,
|
| 1899 |
-
"grad_norm": 0.
|
| 1900 |
-
"learning_rate":
|
| 1901 |
-
"loss": 0.
|
| 1902 |
"step": 2310
|
| 1903 |
},
|
| 1904 |
{
|
| 1905 |
"epoch": 28.641975308641975,
|
| 1906 |
-
"grad_norm": 0.
|
| 1907 |
-
"learning_rate":
|
| 1908 |
-
"loss": 0.
|
| 1909 |
"step": 2320
|
| 1910 |
},
|
| 1911 |
{
|
| 1912 |
"epoch": 28.765432098765434,
|
| 1913 |
-
"grad_norm": 0.
|
| 1914 |
-
"learning_rate":
|
| 1915 |
-
"loss": 0.
|
| 1916 |
"step": 2330
|
| 1917 |
},
|
| 1918 |
{
|
| 1919 |
"epoch": 28.88888888888889,
|
| 1920 |
-
"grad_norm": 0.
|
| 1921 |
-
"learning_rate":
|
| 1922 |
-
"loss": 0.
|
| 1923 |
"step": 2340
|
| 1924 |
},
|
| 1925 |
{
|
| 1926 |
"epoch": 29.012345679012345,
|
| 1927 |
-
"grad_norm": 0.
|
| 1928 |
-
"learning_rate":
|
| 1929 |
-
"loss": 0.
|
| 1930 |
"step": 2350
|
| 1931 |
},
|
| 1932 |
{
|
| 1933 |
"epoch": 29.135802469135804,
|
| 1934 |
-
"grad_norm": 0.
|
| 1935 |
-
"learning_rate":
|
| 1936 |
-
"loss": 0.
|
| 1937 |
"step": 2360
|
| 1938 |
},
|
| 1939 |
{
|
| 1940 |
"epoch": 29.25925925925926,
|
| 1941 |
-
"grad_norm": 0.
|
| 1942 |
-
"learning_rate":
|
| 1943 |
-
"loss": 0.
|
| 1944 |
"step": 2370
|
| 1945 |
},
|
| 1946 |
{
|
| 1947 |
"epoch": 29.382716049382715,
|
| 1948 |
-
"grad_norm": 0.
|
| 1949 |
-
"learning_rate":
|
| 1950 |
-
"loss": 0.
|
| 1951 |
"step": 2380
|
| 1952 |
},
|
| 1953 |
{
|
| 1954 |
"epoch": 29.506172839506174,
|
| 1955 |
-
"grad_norm": 0.
|
| 1956 |
-
"learning_rate":
|
| 1957 |
-
"loss": 0.
|
| 1958 |
"step": 2390
|
| 1959 |
},
|
| 1960 |
{
|
| 1961 |
"epoch": 29.62962962962963,
|
| 1962 |
-
"grad_norm": 0.
|
| 1963 |
-
"learning_rate":
|
| 1964 |
-
"loss": 0.
|
| 1965 |
"step": 2400
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
"epoch": 29.62962962962963,
|
| 1969 |
-
"eval_accuracy": 0.
|
| 1970 |
-
"eval_f1": 0.
|
| 1971 |
-
"eval_loss": 0.
|
| 1972 |
-
"eval_precision": 0.
|
| 1973 |
-
"eval_recall": 0.
|
| 1974 |
-
"eval_runtime": 2.
|
| 1975 |
-
"eval_samples_per_second":
|
| 1976 |
-
"eval_steps_per_second": 16.
|
| 1977 |
"step": 2400
|
| 1978 |
},
|
| 1979 |
{
|
| 1980 |
"epoch": 29.753086419753085,
|
| 1981 |
-
"grad_norm": 0.
|
| 1982 |
-
"learning_rate":
|
| 1983 |
-
"loss": 0.
|
| 1984 |
"step": 2410
|
| 1985 |
},
|
| 1986 |
{
|
| 1987 |
"epoch": 29.876543209876544,
|
| 1988 |
-
"grad_norm": 0.
|
| 1989 |
-
"learning_rate":
|
| 1990 |
-
"loss": 0.
|
| 1991 |
"step": 2420
|
| 1992 |
},
|
| 1993 |
{
|
| 1994 |
"epoch": 30.0,
|
| 1995 |
-
"grad_norm": 0.
|
| 1996 |
"learning_rate": 0.0,
|
| 1997 |
-
"loss": 0.
|
| 1998 |
"step": 2430
|
| 1999 |
},
|
| 2000 |
{
|
| 2001 |
"epoch": 30.0,
|
| 2002 |
"step": 2430,
|
| 2003 |
"total_flos": 3.008454731998249e+18,
|
| 2004 |
-
"train_loss": 0.
|
| 2005 |
-
"train_runtime":
|
| 2006 |
-
"train_samples_per_second":
|
| 2007 |
-
"train_steps_per_second": 3.
|
| 2008 |
}
|
| 2009 |
],
|
| 2010 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.15773314237594604,
|
| 3 |
+
"best_model_checkpoint": "frostsolutions/frost-vision-v2-google_vit-base-patch16-224-v2024-11-14/checkpoint-1000",
|
| 4 |
"epoch": 30.0,
|
| 5 |
"eval_steps": 100,
|
| 6 |
"global_step": 2430,
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.12345679012345678,
|
| 13 |
+
"grad_norm": 2.0258209705352783,
|
| 14 |
+
"learning_rate": 2.05761316872428e-06,
|
| 15 |
+
"loss": 0.7157,
|
| 16 |
"step": 10
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 0.24691358024691357,
|
| 20 |
+
"grad_norm": 1.8047471046447754,
|
| 21 |
+
"learning_rate": 4.11522633744856e-06,
|
| 22 |
+
"loss": 0.6777,
|
| 23 |
"step": 20
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.37037037037037035,
|
| 27 |
+
"grad_norm": 1.81009840965271,
|
| 28 |
+
"learning_rate": 6.172839506172839e-06,
|
| 29 |
+
"loss": 0.6489,
|
| 30 |
"step": 30
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 0.49382716049382713,
|
| 34 |
+
"grad_norm": 1.4138026237487793,
|
| 35 |
+
"learning_rate": 8.23045267489712e-06,
|
| 36 |
+
"loss": 0.5874,
|
| 37 |
"step": 40
|
| 38 |
},
|
| 39 |
{
|
| 40 |
"epoch": 0.6172839506172839,
|
| 41 |
+
"grad_norm": 1.4049081802368164,
|
| 42 |
+
"learning_rate": 1.02880658436214e-05,
|
| 43 |
+
"loss": 0.5259,
|
| 44 |
"step": 50
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.7407407407407407,
|
| 48 |
+
"grad_norm": 1.0964142084121704,
|
| 49 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 50 |
+
"loss": 0.4743,
|
| 51 |
"step": 60
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 0.8641975308641975,
|
| 55 |
+
"grad_norm": 0.8998202681541443,
|
| 56 |
+
"learning_rate": 1.440329218106996e-05,
|
| 57 |
+
"loss": 0.4258,
|
| 58 |
"step": 70
|
| 59 |
},
|
| 60 |
{
|
| 61 |
"epoch": 0.9876543209876543,
|
| 62 |
+
"grad_norm": 1.0498803853988647,
|
| 63 |
+
"learning_rate": 1.646090534979424e-05,
|
| 64 |
+
"loss": 0.4061,
|
| 65 |
"step": 80
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 1.1111111111111112,
|
| 69 |
+
"grad_norm": 0.8372374773025513,
|
| 70 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 71 |
+
"loss": 0.3647,
|
| 72 |
"step": 90
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 1.2345679012345678,
|
| 76 |
+
"grad_norm": 0.9855860471725464,
|
| 77 |
+
"learning_rate": 2.05761316872428e-05,
|
| 78 |
+
"loss": 0.3381,
|
| 79 |
"step": 100
|
| 80 |
},
|
| 81 |
{
|
| 82 |
"epoch": 1.2345679012345678,
|
| 83 |
+
"eval_accuracy": 0.8660493827160494,
|
| 84 |
+
"eval_f1": 0.5668662674650699,
|
| 85 |
+
"eval_loss": 0.3270835876464844,
|
| 86 |
+
"eval_precision": 0.8045325779036827,
|
| 87 |
+
"eval_recall": 0.43759630200308164,
|
| 88 |
+
"eval_runtime": 2.3341,
|
| 89 |
+
"eval_samples_per_second": 138.812,
|
| 90 |
+
"eval_steps_per_second": 17.566,
|
| 91 |
"step": 100
|
| 92 |
},
|
| 93 |
{
|
| 94 |
"epoch": 1.3580246913580247,
|
| 95 |
+
"grad_norm": 0.8622191548347473,
|
| 96 |
+
"learning_rate": 2.2633744855967078e-05,
|
| 97 |
+
"loss": 0.3148,
|
| 98 |
"step": 110
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 1.4814814814814814,
|
| 102 |
+
"grad_norm": 0.9625290036201477,
|
| 103 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 104 |
+
"loss": 0.3021,
|
| 105 |
"step": 120
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 1.6049382716049383,
|
| 109 |
+
"grad_norm": 0.9755824208259583,
|
| 110 |
+
"learning_rate": 2.6748971193415638e-05,
|
| 111 |
+
"loss": 0.2781,
|
| 112 |
"step": 130
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"epoch": 1.7283950617283952,
|
| 116 |
+
"grad_norm": 0.7279321551322937,
|
| 117 |
+
"learning_rate": 2.880658436213992e-05,
|
| 118 |
+
"loss": 0.245,
|
| 119 |
"step": 140
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 1.8518518518518519,
|
| 123 |
+
"grad_norm": 0.8370109796524048,
|
| 124 |
+
"learning_rate": 3.08641975308642e-05,
|
| 125 |
+
"loss": 0.2747,
|
| 126 |
"step": 150
|
| 127 |
},
|
| 128 |
{
|
| 129 |
"epoch": 1.9753086419753085,
|
| 130 |
+
"grad_norm": 0.9776009917259216,
|
| 131 |
+
"learning_rate": 3.292181069958848e-05,
|
| 132 |
+
"loss": 0.2741,
|
| 133 |
"step": 160
|
| 134 |
},
|
| 135 |
{
|
| 136 |
"epoch": 2.0987654320987654,
|
| 137 |
+
"grad_norm": 0.7717245221138,
|
| 138 |
+
"learning_rate": 3.497942386831276e-05,
|
| 139 |
+
"loss": 0.2285,
|
| 140 |
"step": 170
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 2.2222222222222223,
|
| 144 |
+
"grad_norm": 0.9406857490539551,
|
| 145 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 146 |
+
"loss": 0.2179,
|
| 147 |
"step": 180
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 2.3456790123456788,
|
| 151 |
+
"grad_norm": 0.9723733067512512,
|
| 152 |
+
"learning_rate": 3.909465020576132e-05,
|
| 153 |
+
"loss": 0.2213,
|
| 154 |
"step": 190
|
| 155 |
},
|
| 156 |
{
|
| 157 |
"epoch": 2.4691358024691357,
|
| 158 |
+
"grad_norm": 1.2755147218704224,
|
| 159 |
+
"learning_rate": 4.11522633744856e-05,
|
| 160 |
+
"loss": 0.2067,
|
| 161 |
"step": 200
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 2.4691358024691357,
|
| 165 |
+
"eval_accuracy": 0.9194444444444444,
|
| 166 |
+
"eval_f1": 0.7826810990840966,
|
| 167 |
+
"eval_loss": 0.20802636444568634,
|
| 168 |
+
"eval_precision": 0.8514492753623188,
|
| 169 |
+
"eval_recall": 0.724191063174114,
|
| 170 |
+
"eval_runtime": 2.6756,
|
| 171 |
+
"eval_samples_per_second": 121.096,
|
| 172 |
+
"eval_steps_per_second": 15.324,
|
| 173 |
"step": 200
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 2.5925925925925926,
|
| 177 |
+
"grad_norm": 0.6742503643035889,
|
| 178 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 179 |
+
"loss": 0.1916,
|
| 180 |
"step": 210
|
| 181 |
},
|
| 182 |
{
|
| 183 |
"epoch": 2.7160493827160495,
|
| 184 |
+
"grad_norm": 0.9410703182220459,
|
| 185 |
+
"learning_rate": 4.5267489711934157e-05,
|
| 186 |
+
"loss": 0.1932,
|
| 187 |
"step": 220
|
| 188 |
},
|
| 189 |
{
|
| 190 |
"epoch": 2.8395061728395063,
|
| 191 |
+
"grad_norm": 1.5295264720916748,
|
| 192 |
+
"learning_rate": 4.732510288065844e-05,
|
| 193 |
+
"loss": 0.1991,
|
| 194 |
"step": 230
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 2.962962962962963,
|
| 198 |
+
"grad_norm": 1.7802011966705322,
|
| 199 |
+
"learning_rate": 4.938271604938271e-05,
|
| 200 |
+
"loss": 0.2272,
|
| 201 |
"step": 240
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 3.0864197530864197,
|
| 205 |
+
"grad_norm": 1.6310603618621826,
|
| 206 |
+
"learning_rate": 4.983996342021033e-05,
|
| 207 |
+
"loss": 0.1905,
|
| 208 |
"step": 250
|
| 209 |
},
|
| 210 |
{
|
| 211 |
"epoch": 3.2098765432098766,
|
| 212 |
+
"grad_norm": 0.588090181350708,
|
| 213 |
+
"learning_rate": 4.9611339734796525e-05,
|
| 214 |
+
"loss": 0.1577,
|
| 215 |
"step": 260
|
| 216 |
},
|
| 217 |
{
|
| 218 |
"epoch": 3.3333333333333335,
|
| 219 |
+
"grad_norm": 0.7364725470542908,
|
| 220 |
+
"learning_rate": 4.938271604938271e-05,
|
| 221 |
+
"loss": 0.1972,
|
| 222 |
"step": 270
|
| 223 |
},
|
| 224 |
{
|
| 225 |
"epoch": 3.45679012345679,
|
| 226 |
+
"grad_norm": 0.9553163647651672,
|
| 227 |
+
"learning_rate": 4.9154092363968915e-05,
|
| 228 |
+
"loss": 0.1468,
|
| 229 |
"step": 280
|
| 230 |
},
|
| 231 |
{
|
| 232 |
"epoch": 3.580246913580247,
|
| 233 |
+
"grad_norm": 0.9130911827087402,
|
| 234 |
+
"learning_rate": 4.89254686785551e-05,
|
| 235 |
+
"loss": 0.1894,
|
| 236 |
"step": 290
|
| 237 |
},
|
| 238 |
{
|
| 239 |
"epoch": 3.7037037037037037,
|
| 240 |
+
"grad_norm": 0.895966649055481,
|
| 241 |
+
"learning_rate": 4.86968449931413e-05,
|
| 242 |
+
"loss": 0.1745,
|
| 243 |
"step": 300
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 3.7037037037037037,
|
| 247 |
+
"eval_accuracy": 0.9228395061728395,
|
| 248 |
+
"eval_f1": 0.8003194888178914,
|
| 249 |
+
"eval_loss": 0.18639631569385529,
|
| 250 |
+
"eval_precision": 0.8308457711442786,
|
| 251 |
+
"eval_recall": 0.7719568567026194,
|
| 252 |
+
"eval_runtime": 3.3226,
|
| 253 |
+
"eval_samples_per_second": 97.513,
|
| 254 |
+
"eval_steps_per_second": 12.34,
|
| 255 |
"step": 300
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 3.8271604938271606,
|
| 259 |
+
"grad_norm": 0.9509402513504028,
|
| 260 |
+
"learning_rate": 4.8468221307727485e-05,
|
| 261 |
+
"loss": 0.1948,
|
| 262 |
"step": 310
|
| 263 |
},
|
| 264 |
{
|
| 265 |
"epoch": 3.950617283950617,
|
| 266 |
+
"grad_norm": 0.959931492805481,
|
| 267 |
+
"learning_rate": 4.823959762231367e-05,
|
| 268 |
+
"loss": 0.1824,
|
| 269 |
"step": 320
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 4.074074074074074,
|
| 273 |
+
"grad_norm": 0.6884809732437134,
|
| 274 |
+
"learning_rate": 4.801097393689987e-05,
|
| 275 |
+
"loss": 0.156,
|
| 276 |
"step": 330
|
| 277 |
},
|
| 278 |
{
|
| 279 |
"epoch": 4.197530864197531,
|
| 280 |
+
"grad_norm": 0.9225603342056274,
|
| 281 |
+
"learning_rate": 4.7782350251486056e-05,
|
| 282 |
+
"loss": 0.1333,
|
| 283 |
"step": 340
|
| 284 |
},
|
| 285 |
{
|
| 286 |
"epoch": 4.320987654320987,
|
| 287 |
+
"grad_norm": 1.0396263599395752,
|
| 288 |
+
"learning_rate": 4.755372656607225e-05,
|
| 289 |
+
"loss": 0.1715,
|
| 290 |
"step": 350
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 4.444444444444445,
|
| 294 |
+
"grad_norm": 0.6264840364456177,
|
| 295 |
+
"learning_rate": 4.732510288065844e-05,
|
| 296 |
+
"loss": 0.1491,
|
| 297 |
"step": 360
|
| 298 |
},
|
| 299 |
{
|
| 300 |
"epoch": 4.567901234567901,
|
| 301 |
+
"grad_norm": 0.756226658821106,
|
| 302 |
+
"learning_rate": 4.709647919524463e-05,
|
| 303 |
+
"loss": 0.1563,
|
| 304 |
"step": 370
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 4.6913580246913575,
|
| 308 |
+
"grad_norm": 0.9274685382843018,
|
| 309 |
+
"learning_rate": 4.686785550983082e-05,
|
| 310 |
+
"loss": 0.1746,
|
| 311 |
"step": 380
|
| 312 |
},
|
| 313 |
{
|
| 314 |
"epoch": 4.814814814814815,
|
| 315 |
+
"grad_norm": 0.8389601111412048,
|
| 316 |
+
"learning_rate": 4.6639231824417016e-05,
|
| 317 |
+
"loss": 0.14,
|
| 318 |
"step": 390
|
| 319 |
},
|
| 320 |
{
|
| 321 |
"epoch": 4.938271604938271,
|
| 322 |
+
"grad_norm": 0.7658799290657043,
|
| 323 |
+
"learning_rate": 4.6410608139003203e-05,
|
| 324 |
+
"loss": 0.1724,
|
| 325 |
"step": 400
|
| 326 |
},
|
| 327 |
{
|
| 328 |
"epoch": 4.938271604938271,
|
| 329 |
+
"eval_accuracy": 0.9299382716049382,
|
| 330 |
+
"eval_f1": 0.8188347964884277,
|
| 331 |
+
"eval_loss": 0.17921936511993408,
|
| 332 |
+
"eval_precision": 0.8493377483443708,
|
| 333 |
+
"eval_recall": 0.7904468412942989,
|
| 334 |
+
"eval_runtime": 2.4889,
|
| 335 |
+
"eval_samples_per_second": 130.176,
|
| 336 |
+
"eval_steps_per_second": 16.473,
|
| 337 |
"step": 400
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 5.061728395061729,
|
| 341 |
+
"grad_norm": 0.47751790285110474,
|
| 342 |
+
"learning_rate": 4.618198445358939e-05,
|
| 343 |
+
"loss": 0.1397,
|
| 344 |
"step": 410
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 5.185185185185185,
|
| 348 |
+
"grad_norm": 0.8206377625465393,
|
| 349 |
+
"learning_rate": 4.5953360768175586e-05,
|
| 350 |
+
"loss": 0.1332,
|
| 351 |
"step": 420
|
| 352 |
},
|
| 353 |
{
|
| 354 |
"epoch": 5.308641975308642,
|
| 355 |
+
"grad_norm": 1.053655743598938,
|
| 356 |
+
"learning_rate": 4.5724737082761774e-05,
|
| 357 |
+
"loss": 0.1524,
|
| 358 |
"step": 430
|
| 359 |
},
|
| 360 |
{
|
| 361 |
"epoch": 5.432098765432099,
|
| 362 |
+
"grad_norm": 0.8656085729598999,
|
| 363 |
+
"learning_rate": 4.549611339734797e-05,
|
| 364 |
+
"loss": 0.1215,
|
| 365 |
"step": 440
|
| 366 |
},
|
| 367 |
{
|
| 368 |
"epoch": 5.555555555555555,
|
| 369 |
+
"grad_norm": 0.7634124755859375,
|
| 370 |
+
"learning_rate": 4.5267489711934157e-05,
|
| 371 |
+
"loss": 0.1291,
|
| 372 |
"step": 450
|
| 373 |
},
|
| 374 |
{
|
| 375 |
"epoch": 5.679012345679013,
|
| 376 |
+
"grad_norm": 0.6214159727096558,
|
| 377 |
+
"learning_rate": 4.503886602652035e-05,
|
| 378 |
+
"loss": 0.1314,
|
| 379 |
"step": 460
|
| 380 |
},
|
| 381 |
{
|
| 382 |
"epoch": 5.802469135802469,
|
| 383 |
+
"grad_norm": 1.1487807035446167,
|
| 384 |
+
"learning_rate": 4.481024234110654e-05,
|
| 385 |
+
"loss": 0.1372,
|
| 386 |
"step": 470
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 5.925925925925926,
|
| 390 |
+
"grad_norm": 0.7788066864013672,
|
| 391 |
+
"learning_rate": 4.4581618655692734e-05,
|
| 392 |
+
"loss": 0.1399,
|
| 393 |
"step": 480
|
| 394 |
},
|
| 395 |
{
|
| 396 |
"epoch": 6.049382716049383,
|
| 397 |
+
"grad_norm": 0.6658753156661987,
|
| 398 |
+
"learning_rate": 4.435299497027892e-05,
|
| 399 |
+
"loss": 0.1463,
|
| 400 |
"step": 490
|
| 401 |
},
|
| 402 |
{
|
| 403 |
"epoch": 6.172839506172839,
|
| 404 |
+
"grad_norm": 1.125616192817688,
|
| 405 |
+
"learning_rate": 4.412437128486511e-05,
|
| 406 |
+
"loss": 0.128,
|
| 407 |
"step": 500
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 6.172839506172839,
|
| 411 |
+
"eval_accuracy": 0.932716049382716,
|
| 412 |
+
"eval_f1": 0.829153605015674,
|
| 413 |
+
"eval_loss": 0.17359426617622375,
|
| 414 |
+
"eval_precision": 0.8437001594896332,
|
| 415 |
+
"eval_recall": 0.8151001540832049,
|
| 416 |
+
"eval_runtime": 2.3597,
|
| 417 |
+
"eval_samples_per_second": 137.303,
|
| 418 |
+
"eval_steps_per_second": 17.375,
|
| 419 |
"step": 500
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 6.296296296296296,
|
| 423 |
+
"grad_norm": 0.8468999862670898,
|
| 424 |
+
"learning_rate": 4.3895747599451304e-05,
|
| 425 |
+
"loss": 0.1085,
|
| 426 |
"step": 510
|
| 427 |
},
|
| 428 |
{
|
| 429 |
"epoch": 6.419753086419753,
|
| 430 |
+
"grad_norm": 0.8319602012634277,
|
| 431 |
+
"learning_rate": 4.366712391403749e-05,
|
| 432 |
+
"loss": 0.1436,
|
| 433 |
"step": 520
|
| 434 |
},
|
| 435 |
{
|
| 436 |
"epoch": 6.54320987654321,
|
| 437 |
+
"grad_norm": 1.0661511421203613,
|
| 438 |
+
"learning_rate": 4.343850022862369e-05,
|
| 439 |
+
"loss": 0.1258,
|
| 440 |
"step": 530
|
| 441 |
},
|
| 442 |
{
|
| 443 |
"epoch": 6.666666666666667,
|
| 444 |
+
"grad_norm": 1.0158193111419678,
|
| 445 |
+
"learning_rate": 4.3209876543209875e-05,
|
| 446 |
+
"loss": 0.1173,
|
| 447 |
"step": 540
|
| 448 |
},
|
| 449 |
{
|
| 450 |
"epoch": 6.790123456790123,
|
| 451 |
+
"grad_norm": 0.996032178401947,
|
| 452 |
+
"learning_rate": 4.298125285779607e-05,
|
| 453 |
+
"loss": 0.123,
|
| 454 |
"step": 550
|
| 455 |
},
|
| 456 |
{
|
| 457 |
"epoch": 6.91358024691358,
|
| 458 |
+
"grad_norm": 0.8598793148994446,
|
| 459 |
+
"learning_rate": 4.2752629172382264e-05,
|
| 460 |
+
"loss": 0.0955,
|
| 461 |
"step": 560
|
| 462 |
},
|
| 463 |
{
|
| 464 |
"epoch": 7.037037037037037,
|
| 465 |
+
"grad_norm": 0.7240075469017029,
|
| 466 |
+
"learning_rate": 4.252400548696845e-05,
|
| 467 |
+
"loss": 0.1133,
|
| 468 |
"step": 570
|
| 469 |
},
|
| 470 |
{
|
| 471 |
"epoch": 7.160493827160494,
|
| 472 |
+
"grad_norm": 1.5954258441925049,
|
| 473 |
+
"learning_rate": 4.229538180155465e-05,
|
| 474 |
+
"loss": 0.1092,
|
| 475 |
"step": 580
|
| 476 |
},
|
| 477 |
{
|
| 478 |
"epoch": 7.283950617283951,
|
| 479 |
+
"grad_norm": 0.41076725721359253,
|
| 480 |
+
"learning_rate": 4.2066758116140835e-05,
|
| 481 |
+
"loss": 0.1059,
|
| 482 |
"step": 590
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 7.407407407407407,
|
| 486 |
+
"grad_norm": 1.1242218017578125,
|
| 487 |
+
"learning_rate": 4.183813443072703e-05,
|
| 488 |
+
"loss": 0.1034,
|
| 489 |
"step": 600
|
| 490 |
},
|
| 491 |
{
|
| 492 |
"epoch": 7.407407407407407,
|
| 493 |
+
"eval_accuracy": 0.9354938271604938,
|
| 494 |
+
"eval_f1": 0.8347826086956521,
|
| 495 |
+
"eval_loss": 0.16716818511486053,
|
| 496 |
+
"eval_precision": 0.8571428571428571,
|
| 497 |
+
"eval_recall": 0.8135593220338984,
|
| 498 |
+
"eval_runtime": 2.3423,
|
| 499 |
+
"eval_samples_per_second": 138.328,
|
| 500 |
+
"eval_steps_per_second": 17.504,
|
| 501 |
"step": 600
|
| 502 |
},
|
| 503 |
{
|
| 504 |
"epoch": 7.530864197530864,
|
| 505 |
+
"grad_norm": 0.97056645154953,
|
| 506 |
+
"learning_rate": 4.160951074531322e-05,
|
| 507 |
+
"loss": 0.1239,
|
| 508 |
"step": 610
|
| 509 |
},
|
| 510 |
{
|
| 511 |
"epoch": 7.654320987654321,
|
| 512 |
+
"grad_norm": 0.8477165102958679,
|
| 513 |
+
"learning_rate": 4.138088705989941e-05,
|
| 514 |
+
"loss": 0.1164,
|
| 515 |
"step": 620
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 7.777777777777778,
|
| 519 |
+
"grad_norm": 0.7572548389434814,
|
| 520 |
+
"learning_rate": 4.11522633744856e-05,
|
| 521 |
+
"loss": 0.1156,
|
| 522 |
"step": 630
|
| 523 |
},
|
| 524 |
{
|
| 525 |
"epoch": 7.901234567901234,
|
| 526 |
+
"grad_norm": 1.5163884162902832,
|
| 527 |
+
"learning_rate": 4.092363968907179e-05,
|
| 528 |
+
"loss": 0.1195,
|
| 529 |
"step": 640
|
| 530 |
},
|
| 531 |
{
|
| 532 |
"epoch": 8.024691358024691,
|
| 533 |
+
"grad_norm": 0.7944018840789795,
|
| 534 |
+
"learning_rate": 4.069501600365798e-05,
|
| 535 |
+
"loss": 0.1086,
|
| 536 |
"step": 650
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 8.148148148148149,
|
| 540 |
+
"grad_norm": 1.1152986288070679,
|
| 541 |
+
"learning_rate": 4.046639231824417e-05,
|
| 542 |
+
"loss": 0.1101,
|
| 543 |
"step": 660
|
| 544 |
},
|
| 545 |
{
|
| 546 |
"epoch": 8.271604938271604,
|
| 547 |
+
"grad_norm": 0.7614450454711914,
|
| 548 |
+
"learning_rate": 4.0237768632830365e-05,
|
| 549 |
+
"loss": 0.1004,
|
| 550 |
"step": 670
|
| 551 |
},
|
| 552 |
{
|
| 553 |
"epoch": 8.395061728395062,
|
| 554 |
+
"grad_norm": 0.6931539177894592,
|
| 555 |
+
"learning_rate": 4.000914494741655e-05,
|
| 556 |
+
"loss": 0.1047,
|
| 557 |
"step": 680
|
| 558 |
},
|
| 559 |
{
|
| 560 |
"epoch": 8.518518518518519,
|
| 561 |
+
"grad_norm": 0.6190685629844666,
|
| 562 |
+
"learning_rate": 3.978052126200275e-05,
|
| 563 |
+
"loss": 0.0811,
|
| 564 |
"step": 690
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 8.641975308641975,
|
| 568 |
+
"grad_norm": 0.814577579498291,
|
| 569 |
+
"learning_rate": 3.9551897576588936e-05,
|
| 570 |
+
"loss": 0.0944,
|
| 571 |
"step": 700
|
| 572 |
},
|
| 573 |
{
|
| 574 |
"epoch": 8.641975308641975,
|
| 575 |
+
"eval_accuracy": 0.9391975308641975,
|
| 576 |
+
"eval_f1": 0.845247446975648,
|
| 577 |
+
"eval_loss": 0.15788604319095612,
|
| 578 |
+
"eval_precision": 0.8621794871794872,
|
| 579 |
+
"eval_recall": 0.8289676425269645,
|
| 580 |
+
"eval_runtime": 2.3023,
|
| 581 |
+
"eval_samples_per_second": 140.727,
|
| 582 |
+
"eval_steps_per_second": 17.808,
|
| 583 |
"step": 700
|
| 584 |
},
|
| 585 |
{
|
| 586 |
"epoch": 8.765432098765432,
|
| 587 |
+
"grad_norm": 0.6677612066268921,
|
| 588 |
+
"learning_rate": 3.932327389117513e-05,
|
| 589 |
+
"loss": 0.0907,
|
| 590 |
"step": 710
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 8.88888888888889,
|
| 594 |
+
"grad_norm": 1.435887098312378,
|
| 595 |
+
"learning_rate": 3.909465020576132e-05,
|
| 596 |
+
"loss": 0.0941,
|
| 597 |
"step": 720
|
| 598 |
},
|
| 599 |
{
|
| 600 |
"epoch": 9.012345679012345,
|
| 601 |
+
"grad_norm": 0.8256314992904663,
|
| 602 |
+
"learning_rate": 3.8866026520347506e-05,
|
| 603 |
+
"loss": 0.1155,
|
| 604 |
"step": 730
|
| 605 |
},
|
| 606 |
{
|
| 607 |
"epoch": 9.135802469135802,
|
| 608 |
+
"grad_norm": 0.7372011542320251,
|
| 609 |
+
"learning_rate": 3.86374028349337e-05,
|
| 610 |
+
"loss": 0.0868,
|
| 611 |
"step": 740
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 9.25925925925926,
|
| 615 |
+
"grad_norm": 0.6247950196266174,
|
| 616 |
+
"learning_rate": 3.840877914951989e-05,
|
| 617 |
+
"loss": 0.0791,
|
| 618 |
"step": 750
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 9.382716049382717,
|
| 622 |
+
"grad_norm": 0.7330453395843506,
|
| 623 |
+
"learning_rate": 3.8180155464106083e-05,
|
| 624 |
+
"loss": 0.0766,
|
| 625 |
"step": 760
|
| 626 |
},
|
| 627 |
{
|
| 628 |
"epoch": 9.506172839506172,
|
| 629 |
+
"grad_norm": 0.946180522441864,
|
| 630 |
+
"learning_rate": 3.795153177869227e-05,
|
| 631 |
+
"loss": 0.092,
|
| 632 |
"step": 770
|
| 633 |
},
|
| 634 |
{
|
| 635 |
"epoch": 9.62962962962963,
|
| 636 |
+
"grad_norm": 0.6986804008483887,
|
| 637 |
+
"learning_rate": 3.7722908093278466e-05,
|
| 638 |
+
"loss": 0.0695,
|
| 639 |
"step": 780
|
| 640 |
},
|
| 641 |
{
|
| 642 |
"epoch": 9.753086419753087,
|
| 643 |
+
"grad_norm": 0.4678453505039215,
|
| 644 |
+
"learning_rate": 3.7494284407864654e-05,
|
| 645 |
+
"loss": 0.0896,
|
| 646 |
"step": 790
|
| 647 |
},
|
| 648 |
{
|
| 649 |
"epoch": 9.876543209876543,
|
| 650 |
+
"grad_norm": 0.8175441026687622,
|
| 651 |
+
"learning_rate": 3.726566072245085e-05,
|
| 652 |
+
"loss": 0.0919,
|
| 653 |
"step": 800
|
| 654 |
},
|
| 655 |
{
|
| 656 |
"epoch": 9.876543209876543,
|
| 657 |
+
"eval_accuracy": 0.9364197530864198,
|
| 658 |
+
"eval_f1": 0.8346709470304976,
|
| 659 |
+
"eval_loss": 0.16307669878005981,
|
| 660 |
+
"eval_precision": 0.8710217755443886,
|
| 661 |
+
"eval_recall": 0.8012326656394453,
|
| 662 |
+
"eval_runtime": 2.5754,
|
| 663 |
+
"eval_samples_per_second": 125.805,
|
| 664 |
+
"eval_steps_per_second": 15.92,
|
| 665 |
"step": 800
|
| 666 |
},
|
| 667 |
{
|
| 668 |
"epoch": 10.0,
|
| 669 |
+
"grad_norm": 0.7374185919761658,
|
| 670 |
+
"learning_rate": 3.7037037037037037e-05,
|
| 671 |
+
"loss": 0.1001,
|
| 672 |
"step": 810
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 10.123456790123457,
|
| 676 |
+
"grad_norm": 0.5478447079658508,
|
| 677 |
+
"learning_rate": 3.6808413351623224e-05,
|
| 678 |
+
"loss": 0.0939,
|
| 679 |
"step": 820
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"epoch": 10.246913580246913,
|
| 683 |
+
"grad_norm": 0.8081673979759216,
|
| 684 |
+
"learning_rate": 3.657978966620942e-05,
|
| 685 |
+
"loss": 0.0704,
|
| 686 |
"step": 830
|
| 687 |
},
|
| 688 |
{
|
| 689 |
"epoch": 10.37037037037037,
|
| 690 |
+
"grad_norm": 0.7327490448951721,
|
| 691 |
+
"learning_rate": 3.635116598079561e-05,
|
| 692 |
+
"loss": 0.0742,
|
| 693 |
"step": 840
|
| 694 |
},
|
| 695 |
{
|
| 696 |
"epoch": 10.493827160493828,
|
| 697 |
+
"grad_norm": 0.6625596284866333,
|
| 698 |
+
"learning_rate": 3.612254229538181e-05,
|
| 699 |
+
"loss": 0.0784,
|
| 700 |
"step": 850
|
| 701 |
},
|
| 702 |
{
|
| 703 |
"epoch": 10.617283950617283,
|
| 704 |
+
"grad_norm": 1.724616289138794,
|
| 705 |
+
"learning_rate": 3.5893918609967996e-05,
|
| 706 |
+
"loss": 0.0848,
|
| 707 |
"step": 860
|
| 708 |
},
|
| 709 |
{
|
| 710 |
"epoch": 10.74074074074074,
|
| 711 |
+
"grad_norm": 0.6218889951705933,
|
| 712 |
+
"learning_rate": 3.566529492455419e-05,
|
| 713 |
+
"loss": 0.0752,
|
| 714 |
"step": 870
|
| 715 |
},
|
| 716 |
{
|
| 717 |
"epoch": 10.864197530864198,
|
| 718 |
+
"grad_norm": 1.1755985021591187,
|
| 719 |
+
"learning_rate": 3.543667123914038e-05,
|
| 720 |
+
"loss": 0.0751,
|
| 721 |
"step": 880
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 10.987654320987655,
|
| 725 |
+
"grad_norm": 1.2024366855621338,
|
| 726 |
+
"learning_rate": 3.520804755372657e-05,
|
| 727 |
+
"loss": 0.0827,
|
| 728 |
"step": 890
|
| 729 |
},
|
| 730 |
{
|
| 731 |
"epoch": 11.11111111111111,
|
| 732 |
+
"grad_norm": 1.065391182899475,
|
| 733 |
+
"learning_rate": 3.497942386831276e-05,
|
| 734 |
+
"loss": 0.0791,
|
| 735 |
"step": 900
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 11.11111111111111,
|
| 739 |
+
"eval_accuracy": 0.937962962962963,
|
| 740 |
+
"eval_f1": 0.8382944489139179,
|
| 741 |
+
"eval_loss": 0.15917660295963287,
|
| 742 |
+
"eval_precision": 0.877104377104377,
|
| 743 |
+
"eval_recall": 0.802773497688752,
|
| 744 |
+
"eval_runtime": 2.965,
|
| 745 |
+
"eval_samples_per_second": 109.275,
|
| 746 |
+
"eval_steps_per_second": 13.828,
|
| 747 |
"step": 900
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 11.234567901234568,
|
| 751 |
+
"grad_norm": 0.6627580523490906,
|
| 752 |
+
"learning_rate": 3.475080018289895e-05,
|
| 753 |
"loss": 0.0758,
|
| 754 |
"step": 910
|
| 755 |
},
|
| 756 |
{
|
| 757 |
"epoch": 11.358024691358025,
|
| 758 |
+
"grad_norm": 0.5924692749977112,
|
| 759 |
+
"learning_rate": 3.4522176497485144e-05,
|
| 760 |
+
"loss": 0.0672,
|
| 761 |
"step": 920
|
| 762 |
},
|
| 763 |
{
|
| 764 |
"epoch": 11.481481481481481,
|
| 765 |
+
"grad_norm": 0.5990743637084961,
|
| 766 |
+
"learning_rate": 3.429355281207133e-05,
|
| 767 |
+
"loss": 0.0822,
|
| 768 |
"step": 930
|
| 769 |
},
|
| 770 |
{
|
| 771 |
"epoch": 11.604938271604938,
|
| 772 |
+
"grad_norm": 0.9133488535881042,
|
| 773 |
+
"learning_rate": 3.406492912665753e-05,
|
| 774 |
+
"loss": 0.0883,
|
| 775 |
"step": 940
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 11.728395061728396,
|
| 779 |
+
"grad_norm": 1.091486930847168,
|
| 780 |
+
"learning_rate": 3.3836305441243715e-05,
|
| 781 |
+
"loss": 0.0639,
|
| 782 |
"step": 950
|
| 783 |
},
|
| 784 |
{
|
| 785 |
"epoch": 11.851851851851851,
|
| 786 |
+
"grad_norm": 0.3895137310028076,
|
| 787 |
+
"learning_rate": 3.360768175582991e-05,
|
| 788 |
+
"loss": 0.0687,
|
| 789 |
"step": 960
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 11.975308641975309,
|
| 793 |
+
"grad_norm": 0.5844981074333191,
|
| 794 |
+
"learning_rate": 3.33790580704161e-05,
|
| 795 |
+
"loss": 0.0576,
|
| 796 |
"step": 970
|
| 797 |
},
|
| 798 |
{
|
| 799 |
"epoch": 12.098765432098766,
|
| 800 |
+
"grad_norm": 0.3059285879135132,
|
| 801 |
+
"learning_rate": 3.3150434385002285e-05,
|
| 802 |
+
"loss": 0.0689,
|
| 803 |
"step": 980
|
| 804 |
},
|
| 805 |
{
|
| 806 |
"epoch": 12.222222222222221,
|
| 807 |
+
"grad_norm": 0.6075615286827087,
|
| 808 |
+
"learning_rate": 3.292181069958848e-05,
|
| 809 |
+
"loss": 0.0525,
|
| 810 |
"step": 990
|
| 811 |
},
|
| 812 |
{
|
| 813 |
"epoch": 12.345679012345679,
|
| 814 |
+
"grad_norm": 0.8529097437858582,
|
| 815 |
+
"learning_rate": 3.269318701417467e-05,
|
| 816 |
+
"loss": 0.0684,
|
| 817 |
"step": 1000
|
| 818 |
},
|
| 819 |
{
|
| 820 |
"epoch": 12.345679012345679,
|
| 821 |
+
"eval_accuracy": 0.9388888888888889,
|
| 822 |
+
"eval_f1": 0.8436018957345972,
|
| 823 |
+
"eval_loss": 0.15773314237594604,
|
| 824 |
+
"eval_precision": 0.8654781199351702,
|
| 825 |
+
"eval_recall": 0.8228043143297381,
|
| 826 |
+
"eval_runtime": 3.556,
|
| 827 |
+
"eval_samples_per_second": 91.114,
|
| 828 |
+
"eval_steps_per_second": 11.53,
|
| 829 |
"step": 1000
|
| 830 |
},
|
| 831 |
{
|
| 832 |
"epoch": 12.469135802469136,
|
| 833 |
+
"grad_norm": 0.2871643602848053,
|
| 834 |
+
"learning_rate": 3.246456332876086e-05,
|
| 835 |
+
"loss": 0.0721,
|
| 836 |
"step": 1010
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 12.592592592592592,
|
| 840 |
+
"grad_norm": 1.031972050666809,
|
| 841 |
+
"learning_rate": 3.223593964334705e-05,
|
| 842 |
+
"loss": 0.0762,
|
| 843 |
"step": 1020
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 12.716049382716049,
|
| 847 |
+
"grad_norm": 0.8951663374900818,
|
| 848 |
+
"learning_rate": 3.2007315957933245e-05,
|
| 849 |
+
"loss": 0.078,
|
| 850 |
"step": 1030
|
| 851 |
},
|
| 852 |
{
|
| 853 |
"epoch": 12.839506172839506,
|
| 854 |
+
"grad_norm": 0.38367488980293274,
|
| 855 |
+
"learning_rate": 3.177869227251943e-05,
|
| 856 |
+
"loss": 0.0629,
|
| 857 |
"step": 1040
|
| 858 |
},
|
| 859 |
{
|
| 860 |
"epoch": 12.962962962962964,
|
| 861 |
+
"grad_norm": 1.0400196313858032,
|
| 862 |
+
"learning_rate": 3.155006858710563e-05,
|
| 863 |
+
"loss": 0.0755,
|
| 864 |
"step": 1050
|
| 865 |
},
|
| 866 |
{
|
| 867 |
"epoch": 13.08641975308642,
|
| 868 |
+
"grad_norm": 0.9411855340003967,
|
| 869 |
+
"learning_rate": 3.1321444901691816e-05,
|
| 870 |
+
"loss": 0.0624,
|
| 871 |
"step": 1060
|
| 872 |
},
|
| 873 |
{
|
| 874 |
"epoch": 13.209876543209877,
|
| 875 |
+
"grad_norm": 0.9051506519317627,
|
| 876 |
+
"learning_rate": 3.1092821216278004e-05,
|
| 877 |
+
"loss": 0.0573,
|
| 878 |
"step": 1070
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 13.333333333333334,
|
| 882 |
+
"grad_norm": 1.214126706123352,
|
| 883 |
+
"learning_rate": 3.08641975308642e-05,
|
| 884 |
+
"loss": 0.0658,
|
| 885 |
"step": 1080
|
| 886 |
},
|
| 887 |
{
|
| 888 |
"epoch": 13.45679012345679,
|
| 889 |
+
"grad_norm": 0.8709390163421631,
|
| 890 |
+
"learning_rate": 3.0635573845450386e-05,
|
| 891 |
+
"loss": 0.0626,
|
| 892 |
"step": 1090
|
| 893 |
},
|
| 894 |
{
|
| 895 |
"epoch": 13.580246913580247,
|
| 896 |
+
"grad_norm": 1.0249199867248535,
|
| 897 |
+
"learning_rate": 3.0406950160036577e-05,
|
| 898 |
+
"loss": 0.0737,
|
| 899 |
"step": 1100
|
| 900 |
},
|
| 901 |
{
|
| 902 |
"epoch": 13.580246913580247,
|
| 903 |
+
"eval_accuracy": 0.937962962962963,
|
| 904 |
+
"eval_f1": 0.8416075650118203,
|
| 905 |
+
"eval_loss": 0.16777929663658142,
|
| 906 |
+
"eval_precision": 0.8612903225806452,
|
| 907 |
+
"eval_recall": 0.8228043143297381,
|
| 908 |
+
"eval_runtime": 2.5879,
|
| 909 |
+
"eval_samples_per_second": 125.2,
|
| 910 |
+
"eval_steps_per_second": 15.843,
|
| 911 |
"step": 1100
|
| 912 |
},
|
| 913 |
{
|
| 914 |
"epoch": 13.703703703703704,
|
| 915 |
+
"grad_norm": 0.6229693293571472,
|
| 916 |
+
"learning_rate": 3.017832647462277e-05,
|
| 917 |
+
"loss": 0.0611,
|
| 918 |
"step": 1110
|
| 919 |
},
|
| 920 |
{
|
| 921 |
"epoch": 13.82716049382716,
|
| 922 |
+
"grad_norm": 0.29374879598617554,
|
| 923 |
+
"learning_rate": 2.994970278920896e-05,
|
| 924 |
+
"loss": 0.0616,
|
| 925 |
"step": 1120
|
| 926 |
},
|
| 927 |
{
|
| 928 |
"epoch": 13.950617283950617,
|
| 929 |
+
"grad_norm": 0.5640215277671814,
|
| 930 |
+
"learning_rate": 2.972107910379515e-05,
|
| 931 |
+
"loss": 0.0703,
|
| 932 |
"step": 1130
|
| 933 |
},
|
| 934 |
{
|
| 935 |
"epoch": 14.074074074074074,
|
| 936 |
+
"grad_norm": 0.44930121302604675,
|
| 937 |
+
"learning_rate": 2.949245541838135e-05,
|
| 938 |
+
"loss": 0.0523,
|
| 939 |
"step": 1140
|
| 940 |
},
|
| 941 |
{
|
| 942 |
"epoch": 14.197530864197532,
|
| 943 |
+
"grad_norm": 0.3680154085159302,
|
| 944 |
+
"learning_rate": 2.926383173296754e-05,
|
| 945 |
+
"loss": 0.0608,
|
| 946 |
"step": 1150
|
| 947 |
},
|
| 948 |
{
|
| 949 |
"epoch": 14.320987654320987,
|
| 950 |
+
"grad_norm": 0.5697309374809265,
|
| 951 |
+
"learning_rate": 2.903520804755373e-05,
|
| 952 |
+
"loss": 0.0581,
|
| 953 |
"step": 1160
|
| 954 |
},
|
| 955 |
{
|
| 956 |
"epoch": 14.444444444444445,
|
| 957 |
+
"grad_norm": 0.6320594549179077,
|
| 958 |
+
"learning_rate": 2.880658436213992e-05,
|
| 959 |
+
"loss": 0.0557,
|
| 960 |
"step": 1170
|
| 961 |
},
|
| 962 |
{
|
| 963 |
"epoch": 14.567901234567902,
|
| 964 |
+
"grad_norm": 0.8799903988838196,
|
| 965 |
+
"learning_rate": 2.857796067672611e-05,
|
| 966 |
+
"loss": 0.0556,
|
| 967 |
"step": 1180
|
| 968 |
},
|
| 969 |
{
|
| 970 |
"epoch": 14.691358024691358,
|
| 971 |
+
"grad_norm": 0.7066503167152405,
|
| 972 |
+
"learning_rate": 2.8349336991312303e-05,
|
| 973 |
+
"loss": 0.0574,
|
| 974 |
"step": 1190
|
| 975 |
},
|
| 976 |
{
|
| 977 |
"epoch": 14.814814814814815,
|
| 978 |
+
"grad_norm": 1.6003211736679077,
|
| 979 |
+
"learning_rate": 2.8120713305898494e-05,
|
| 980 |
+
"loss": 0.0625,
|
| 981 |
"step": 1200
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 14.814814814814815,
|
| 985 |
+
"eval_accuracy": 0.9425925925925925,
|
| 986 |
+
"eval_f1": 0.85423197492163,
|
| 987 |
+
"eval_loss": 0.16456876695156097,
|
| 988 |
+
"eval_precision": 0.8692185007974481,
|
| 989 |
+
"eval_recall": 0.8397534668721109,
|
| 990 |
+
"eval_runtime": 3.5694,
|
| 991 |
+
"eval_samples_per_second": 90.771,
|
| 992 |
+
"eval_steps_per_second": 11.486,
|
| 993 |
"step": 1200
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 14.938271604938272,
|
| 997 |
+
"grad_norm": 0.6639634966850281,
|
| 998 |
+
"learning_rate": 2.7892089620484685e-05,
|
| 999 |
+
"loss": 0.0612,
|
| 1000 |
"step": 1210
|
| 1001 |
},
|
| 1002 |
{
|
| 1003 |
"epoch": 15.061728395061728,
|
| 1004 |
+
"grad_norm": 1.4719339609146118,
|
| 1005 |
+
"learning_rate": 2.7663465935070876e-05,
|
| 1006 |
+
"loss": 0.0537,
|
| 1007 |
"step": 1220
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
"epoch": 15.185185185185185,
|
| 1011 |
+
"grad_norm": 0.6944316625595093,
|
| 1012 |
+
"learning_rate": 2.7434842249657068e-05,
|
| 1013 |
+
"loss": 0.0669,
|
| 1014 |
"step": 1230
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
"epoch": 15.308641975308642,
|
| 1018 |
+
"grad_norm": 0.43684977293014526,
|
| 1019 |
+
"learning_rate": 2.720621856424326e-05,
|
| 1020 |
+
"loss": 0.0475,
|
| 1021 |
"step": 1240
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
"epoch": 15.432098765432098,
|
| 1025 |
+
"grad_norm": 0.3456471264362335,
|
| 1026 |
+
"learning_rate": 2.6977594878829447e-05,
|
| 1027 |
+
"loss": 0.0391,
|
| 1028 |
"step": 1250
|
| 1029 |
},
|
| 1030 |
{
|
| 1031 |
"epoch": 15.555555555555555,
|
| 1032 |
+
"grad_norm": 0.9245675206184387,
|
| 1033 |
+
"learning_rate": 2.6748971193415638e-05,
|
| 1034 |
+
"loss": 0.0564,
|
| 1035 |
"step": 1260
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 15.679012345679013,
|
| 1039 |
+
"grad_norm": 1.1026465892791748,
|
| 1040 |
+
"learning_rate": 2.652034750800183e-05,
|
| 1041 |
+
"loss": 0.0628,
|
| 1042 |
"step": 1270
|
| 1043 |
},
|
| 1044 |
{
|
| 1045 |
"epoch": 15.802469135802468,
|
| 1046 |
+
"grad_norm": 0.5103587508201599,
|
| 1047 |
+
"learning_rate": 2.629172382258802e-05,
|
| 1048 |
+
"loss": 0.0554,
|
| 1049 |
"step": 1280
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
"epoch": 15.925925925925926,
|
| 1053 |
+
"grad_norm": 0.6337056159973145,
|
| 1054 |
+
"learning_rate": 2.6063100137174212e-05,
|
| 1055 |
+
"loss": 0.0569,
|
| 1056 |
"step": 1290
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
"epoch": 16.049382716049383,
|
| 1060 |
+
"grad_norm": 1.0704419612884521,
|
| 1061 |
+
"learning_rate": 2.5834476451760403e-05,
|
| 1062 |
+
"loss": 0.0591,
|
| 1063 |
"step": 1300
|
| 1064 |
},
|
| 1065 |
{
|
| 1066 |
"epoch": 16.049382716049383,
|
| 1067 |
+
"eval_accuracy": 0.9432098765432099,
|
| 1068 |
+
"eval_f1": 0.8548895899053628,
|
| 1069 |
+
"eval_loss": 0.16249051690101624,
|
| 1070 |
+
"eval_precision": 0.875605815831987,
|
| 1071 |
+
"eval_recall": 0.8351309707241911,
|
| 1072 |
+
"eval_runtime": 2.3147,
|
| 1073 |
+
"eval_samples_per_second": 139.976,
|
| 1074 |
+
"eval_steps_per_second": 17.713,
|
| 1075 |
"step": 1300
|
| 1076 |
},
|
| 1077 |
{
|
| 1078 |
"epoch": 16.17283950617284,
|
| 1079 |
+
"grad_norm": 1.0367881059646606,
|
| 1080 |
+
"learning_rate": 2.5605852766346595e-05,
|
| 1081 |
+
"loss": 0.0414,
|
| 1082 |
"step": 1310
|
| 1083 |
},
|
| 1084 |
{
|
| 1085 |
"epoch": 16.296296296296298,
|
| 1086 |
+
"grad_norm": 0.8111926317214966,
|
| 1087 |
+
"learning_rate": 2.5377229080932786e-05,
|
| 1088 |
+
"loss": 0.0649,
|
| 1089 |
"step": 1320
|
| 1090 |
},
|
| 1091 |
{
|
| 1092 |
"epoch": 16.419753086419753,
|
| 1093 |
+
"grad_norm": 0.42399314045906067,
|
| 1094 |
+
"learning_rate": 2.5148605395518977e-05,
|
| 1095 |
"loss": 0.0534,
|
| 1096 |
"step": 1330
|
| 1097 |
},
|
| 1098 |
{
|
| 1099 |
"epoch": 16.54320987654321,
|
| 1100 |
+
"grad_norm": 0.4055217206478119,
|
| 1101 |
+
"learning_rate": 2.4919981710105165e-05,
|
| 1102 |
+
"loss": 0.0451,
|
| 1103 |
"step": 1340
|
| 1104 |
},
|
| 1105 |
{
|
| 1106 |
"epoch": 16.666666666666668,
|
| 1107 |
+
"grad_norm": 0.33903083205223083,
|
| 1108 |
+
"learning_rate": 2.4691358024691357e-05,
|
| 1109 |
+
"loss": 0.0599,
|
| 1110 |
"step": 1350
|
| 1111 |
},
|
| 1112 |
{
|
| 1113 |
"epoch": 16.790123456790123,
|
| 1114 |
+
"grad_norm": 0.4832461476325989,
|
| 1115 |
+
"learning_rate": 2.446273433927755e-05,
|
| 1116 |
+
"loss": 0.0388,
|
| 1117 |
"step": 1360
|
| 1118 |
},
|
| 1119 |
{
|
| 1120 |
"epoch": 16.91358024691358,
|
| 1121 |
+
"grad_norm": 1.0101662874221802,
|
| 1122 |
+
"learning_rate": 2.4234110653863743e-05,
|
| 1123 |
+
"loss": 0.0523,
|
| 1124 |
"step": 1370
|
| 1125 |
},
|
| 1126 |
{
|
| 1127 |
"epoch": 17.037037037037038,
|
| 1128 |
+
"grad_norm": 0.7684808969497681,
|
| 1129 |
+
"learning_rate": 2.4005486968449934e-05,
|
| 1130 |
+
"loss": 0.0569,
|
| 1131 |
"step": 1380
|
| 1132 |
},
|
| 1133 |
{
|
| 1134 |
"epoch": 17.160493827160494,
|
| 1135 |
+
"grad_norm": 0.5816587209701538,
|
| 1136 |
+
"learning_rate": 2.3776863283036125e-05,
|
| 1137 |
+
"loss": 0.0471,
|
| 1138 |
"step": 1390
|
| 1139 |
},
|
| 1140 |
{
|
| 1141 |
"epoch": 17.28395061728395,
|
| 1142 |
+
"grad_norm": 0.5327761769294739,
|
| 1143 |
+
"learning_rate": 2.3548239597622316e-05,
|
| 1144 |
+
"loss": 0.0464,
|
| 1145 |
"step": 1400
|
| 1146 |
},
|
| 1147 |
{
|
| 1148 |
"epoch": 17.28395061728395,
|
| 1149 |
+
"eval_accuracy": 0.9385802469135802,
|
| 1150 |
+
"eval_f1": 0.8421887390959556,
|
| 1151 |
+
"eval_loss": 0.1721687614917755,
|
| 1152 |
+
"eval_precision": 0.8676470588235294,
|
| 1153 |
+
"eval_recall": 0.8181818181818182,
|
| 1154 |
+
"eval_runtime": 2.3252,
|
| 1155 |
+
"eval_samples_per_second": 139.345,
|
| 1156 |
+
"eval_steps_per_second": 17.633,
|
| 1157 |
"step": 1400
|
| 1158 |
},
|
| 1159 |
{
|
| 1160 |
"epoch": 17.40740740740741,
|
| 1161 |
+
"grad_norm": 1.4246679544448853,
|
| 1162 |
+
"learning_rate": 2.3319615912208508e-05,
|
| 1163 |
+
"loss": 0.0593,
|
| 1164 |
"step": 1410
|
| 1165 |
},
|
| 1166 |
{
|
| 1167 |
"epoch": 17.530864197530864,
|
| 1168 |
+
"grad_norm": 0.6948336958885193,
|
| 1169 |
+
"learning_rate": 2.3090992226794696e-05,
|
| 1170 |
+
"loss": 0.0368,
|
| 1171 |
"step": 1420
|
| 1172 |
},
|
| 1173 |
{
|
| 1174 |
"epoch": 17.65432098765432,
|
| 1175 |
+
"grad_norm": 0.7839669585227966,
|
| 1176 |
+
"learning_rate": 2.2862368541380887e-05,
|
| 1177 |
+
"loss": 0.0662,
|
| 1178 |
"step": 1430
|
| 1179 |
},
|
| 1180 |
{
|
| 1181 |
"epoch": 17.77777777777778,
|
| 1182 |
+
"grad_norm": 0.6608372330665588,
|
| 1183 |
+
"learning_rate": 2.2633744855967078e-05,
|
| 1184 |
+
"loss": 0.0457,
|
| 1185 |
"step": 1440
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
"epoch": 17.901234567901234,
|
| 1189 |
+
"grad_norm": 1.2672737836837769,
|
| 1190 |
+
"learning_rate": 2.240512117055327e-05,
|
| 1191 |
+
"loss": 0.0517,
|
| 1192 |
"step": 1450
|
| 1193 |
},
|
| 1194 |
{
|
| 1195 |
"epoch": 18.02469135802469,
|
| 1196 |
+
"grad_norm": 0.8855928778648376,
|
| 1197 |
+
"learning_rate": 2.217649748513946e-05,
|
| 1198 |
+
"loss": 0.0524,
|
| 1199 |
"step": 1460
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
"epoch": 18.14814814814815,
|
| 1203 |
+
"grad_norm": 0.7090869545936584,
|
| 1204 |
+
"learning_rate": 2.1947873799725652e-05,
|
| 1205 |
+
"loss": 0.0449,
|
| 1206 |
"step": 1470
|
| 1207 |
},
|
| 1208 |
{
|
| 1209 |
"epoch": 18.271604938271604,
|
| 1210 |
+
"grad_norm": 0.5972793698310852,
|
| 1211 |
+
"learning_rate": 2.1719250114311843e-05,
|
| 1212 |
+
"loss": 0.0358,
|
| 1213 |
"step": 1480
|
| 1214 |
},
|
| 1215 |
{
|
| 1216 |
"epoch": 18.395061728395063,
|
| 1217 |
+
"grad_norm": 0.2597953677177429,
|
| 1218 |
+
"learning_rate": 2.1490626428898035e-05,
|
| 1219 |
+
"loss": 0.0599,
|
| 1220 |
"step": 1490
|
| 1221 |
},
|
| 1222 |
{
|
| 1223 |
"epoch": 18.51851851851852,
|
| 1224 |
+
"grad_norm": 0.5771777629852295,
|
| 1225 |
+
"learning_rate": 2.1262002743484226e-05,
|
| 1226 |
+
"loss": 0.048,
|
| 1227 |
"step": 1500
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
"epoch": 18.51851851851852,
|
| 1231 |
+
"eval_accuracy": 0.9401234567901234,
|
| 1232 |
+
"eval_f1": 0.8472440944881889,
|
| 1233 |
+
"eval_loss": 0.16935202479362488,
|
| 1234 |
+
"eval_precision": 0.8663446054750402,
|
| 1235 |
+
"eval_recall": 0.8289676425269645,
|
| 1236 |
+
"eval_runtime": 2.5549,
|
| 1237 |
+
"eval_samples_per_second": 126.816,
|
| 1238 |
+
"eval_steps_per_second": 16.048,
|
| 1239 |
"step": 1500
|
| 1240 |
},
|
| 1241 |
{
|
| 1242 |
"epoch": 18.641975308641975,
|
| 1243 |
+
"grad_norm": 1.0612865686416626,
|
| 1244 |
+
"learning_rate": 2.1033379058070417e-05,
|
| 1245 |
+
"loss": 0.0458,
|
| 1246 |
"step": 1510
|
| 1247 |
},
|
| 1248 |
{
|
| 1249 |
"epoch": 18.765432098765434,
|
| 1250 |
+
"grad_norm": 1.0192160606384277,
|
| 1251 |
+
"learning_rate": 2.080475537265661e-05,
|
| 1252 |
+
"loss": 0.045,
|
| 1253 |
"step": 1520
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 18.88888888888889,
|
| 1257 |
+
"grad_norm": 0.8331177830696106,
|
| 1258 |
+
"learning_rate": 2.05761316872428e-05,
|
| 1259 |
+
"loss": 0.0458,
|
| 1260 |
"step": 1530
|
| 1261 |
},
|
| 1262 |
{
|
| 1263 |
"epoch": 19.012345679012345,
|
| 1264 |
+
"grad_norm": 0.5867314338684082,
|
| 1265 |
+
"learning_rate": 2.034750800182899e-05,
|
| 1266 |
+
"loss": 0.0462,
|
| 1267 |
"step": 1540
|
| 1268 |
},
|
| 1269 |
{
|
| 1270 |
"epoch": 19.135802469135804,
|
| 1271 |
+
"grad_norm": 0.2448338121175766,
|
| 1272 |
+
"learning_rate": 2.0118884316415183e-05,
|
| 1273 |
"loss": 0.0404,
|
| 1274 |
"step": 1550
|
| 1275 |
},
|
| 1276 |
{
|
| 1277 |
"epoch": 19.25925925925926,
|
| 1278 |
+
"grad_norm": 0.7374415397644043,
|
| 1279 |
+
"learning_rate": 1.9890260631001374e-05,
|
| 1280 |
+
"loss": 0.0442,
|
| 1281 |
"step": 1560
|
| 1282 |
},
|
| 1283 |
{
|
| 1284 |
"epoch": 19.382716049382715,
|
| 1285 |
+
"grad_norm": 0.6374390125274658,
|
| 1286 |
+
"learning_rate": 1.9661636945587565e-05,
|
| 1287 |
+
"loss": 0.0435,
|
| 1288 |
"step": 1570
|
| 1289 |
},
|
| 1290 |
{
|
| 1291 |
"epoch": 19.506172839506174,
|
| 1292 |
+
"grad_norm": 0.6881589889526367,
|
| 1293 |
+
"learning_rate": 1.9433013260173753e-05,
|
| 1294 |
+
"loss": 0.0498,
|
| 1295 |
"step": 1580
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
"epoch": 19.62962962962963,
|
| 1299 |
+
"grad_norm": 0.26705750823020935,
|
| 1300 |
+
"learning_rate": 1.9204389574759944e-05,
|
| 1301 |
+
"loss": 0.0415,
|
| 1302 |
"step": 1590
|
| 1303 |
},
|
| 1304 |
{
|
| 1305 |
"epoch": 19.753086419753085,
|
| 1306 |
+
"grad_norm": 0.7690613269805908,
|
| 1307 |
+
"learning_rate": 1.8975765889346136e-05,
|
| 1308 |
+
"loss": 0.0353,
|
| 1309 |
"step": 1600
|
| 1310 |
},
|
| 1311 |
{
|
| 1312 |
"epoch": 19.753086419753085,
|
| 1313 |
+
"eval_accuracy": 0.9391975308641975,
|
| 1314 |
+
"eval_f1": 0.8462138953942233,
|
| 1315 |
+
"eval_loss": 0.17146864533424377,
|
| 1316 |
+
"eval_precision": 0.8575949367088608,
|
| 1317 |
+
"eval_recall": 0.8351309707241911,
|
| 1318 |
+
"eval_runtime": 2.9802,
|
| 1319 |
+
"eval_samples_per_second": 108.717,
|
| 1320 |
+
"eval_steps_per_second": 13.757,
|
| 1321 |
"step": 1600
|
| 1322 |
},
|
| 1323 |
{
|
| 1324 |
"epoch": 19.876543209876544,
|
| 1325 |
+
"grad_norm": 0.630096971988678,
|
| 1326 |
+
"learning_rate": 1.8747142203932327e-05,
|
| 1327 |
+
"loss": 0.0385,
|
| 1328 |
"step": 1610
|
| 1329 |
},
|
| 1330 |
{
|
| 1331 |
"epoch": 20.0,
|
| 1332 |
+
"grad_norm": 0.6776329874992371,
|
| 1333 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 1334 |
+
"loss": 0.0465,
|
| 1335 |
"step": 1620
|
| 1336 |
},
|
| 1337 |
{
|
| 1338 |
"epoch": 20.123456790123456,
|
| 1339 |
+
"grad_norm": 0.8204653859138489,
|
| 1340 |
+
"learning_rate": 1.828989483310471e-05,
|
| 1341 |
+
"loss": 0.037,
|
| 1342 |
"step": 1630
|
| 1343 |
},
|
| 1344 |
{
|
| 1345 |
"epoch": 20.246913580246915,
|
| 1346 |
+
"grad_norm": 0.11897799372673035,
|
| 1347 |
+
"learning_rate": 1.8061271147690904e-05,
|
| 1348 |
+
"loss": 0.0308,
|
| 1349 |
"step": 1640
|
| 1350 |
},
|
| 1351 |
{
|
| 1352 |
"epoch": 20.37037037037037,
|
| 1353 |
+
"grad_norm": 0.6061619520187378,
|
| 1354 |
+
"learning_rate": 1.7832647462277096e-05,
|
| 1355 |
+
"loss": 0.0456,
|
| 1356 |
"step": 1650
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 20.493827160493826,
|
| 1360 |
+
"grad_norm": 0.24529418349266052,
|
| 1361 |
+
"learning_rate": 1.7604023776863283e-05,
|
| 1362 |
+
"loss": 0.0374,
|
| 1363 |
"step": 1660
|
| 1364 |
},
|
| 1365 |
{
|
| 1366 |
"epoch": 20.617283950617285,
|
| 1367 |
+
"grad_norm": 0.9412081241607666,
|
| 1368 |
+
"learning_rate": 1.7375400091449475e-05,
|
| 1369 |
+
"loss": 0.0455,
|
| 1370 |
"step": 1670
|
| 1371 |
},
|
| 1372 |
{
|
| 1373 |
"epoch": 20.74074074074074,
|
| 1374 |
+
"grad_norm": 0.39813077449798584,
|
| 1375 |
+
"learning_rate": 1.7146776406035666e-05,
|
| 1376 |
+
"loss": 0.0395,
|
| 1377 |
"step": 1680
|
| 1378 |
},
|
| 1379 |
{
|
| 1380 |
"epoch": 20.864197530864196,
|
| 1381 |
+
"grad_norm": 0.36594846844673157,
|
| 1382 |
+
"learning_rate": 1.6918152720621857e-05,
|
| 1383 |
+
"loss": 0.0376,
|
| 1384 |
"step": 1690
|
| 1385 |
},
|
| 1386 |
{
|
| 1387 |
"epoch": 20.987654320987655,
|
| 1388 |
+
"grad_norm": 0.7182625532150269,
|
| 1389 |
+
"learning_rate": 1.668952903520805e-05,
|
| 1390 |
+
"loss": 0.0434,
|
| 1391 |
"step": 1700
|
| 1392 |
},
|
| 1393 |
{
|
| 1394 |
"epoch": 20.987654320987655,
|
| 1395 |
+
"eval_accuracy": 0.937037037037037,
|
| 1396 |
+
"eval_f1": 0.8386075949367089,
|
| 1397 |
+
"eval_loss": 0.18171226978302002,
|
| 1398 |
+
"eval_precision": 0.8617886178861789,
|
| 1399 |
+
"eval_recall": 0.8166409861325116,
|
| 1400 |
+
"eval_runtime": 2.6381,
|
| 1401 |
+
"eval_samples_per_second": 122.816,
|
| 1402 |
+
"eval_steps_per_second": 15.541,
|
| 1403 |
"step": 1700
|
| 1404 |
},
|
| 1405 |
{
|
| 1406 |
"epoch": 21.11111111111111,
|
| 1407 |
+
"grad_norm": 0.6655898094177246,
|
| 1408 |
+
"learning_rate": 1.646090534979424e-05,
|
| 1409 |
+
"loss": 0.0327,
|
| 1410 |
"step": 1710
|
| 1411 |
},
|
| 1412 |
{
|
| 1413 |
"epoch": 21.234567901234566,
|
| 1414 |
+
"grad_norm": 0.5218392610549927,
|
| 1415 |
+
"learning_rate": 1.623228166438043e-05,
|
| 1416 |
+
"loss": 0.0452,
|
| 1417 |
"step": 1720
|
| 1418 |
},
|
| 1419 |
{
|
| 1420 |
"epoch": 21.358024691358025,
|
| 1421 |
+
"grad_norm": 0.6255172491073608,
|
| 1422 |
+
"learning_rate": 1.6003657978966623e-05,
|
| 1423 |
+
"loss": 0.033,
|
| 1424 |
"step": 1730
|
| 1425 |
},
|
| 1426 |
{
|
| 1427 |
"epoch": 21.48148148148148,
|
| 1428 |
+
"grad_norm": 0.6865390539169312,
|
| 1429 |
+
"learning_rate": 1.5775034293552814e-05,
|
| 1430 |
+
"loss": 0.046,
|
| 1431 |
"step": 1740
|
| 1432 |
},
|
| 1433 |
{
|
| 1434 |
"epoch": 21.604938271604937,
|
| 1435 |
+
"grad_norm": 0.577601432800293,
|
| 1436 |
+
"learning_rate": 1.5546410608139002e-05,
|
| 1437 |
+
"loss": 0.0367,
|
| 1438 |
"step": 1750
|
| 1439 |
},
|
| 1440 |
{
|
| 1441 |
"epoch": 21.728395061728396,
|
| 1442 |
+
"grad_norm": 0.5450471639633179,
|
| 1443 |
+
"learning_rate": 1.5317786922725193e-05,
|
| 1444 |
+
"loss": 0.038,
|
| 1445 |
"step": 1760
|
| 1446 |
},
|
| 1447 |
{
|
| 1448 |
"epoch": 21.85185185185185,
|
| 1449 |
+
"grad_norm": 0.8480527997016907,
|
| 1450 |
+
"learning_rate": 1.5089163237311384e-05,
|
| 1451 |
+
"loss": 0.0399,
|
| 1452 |
"step": 1770
|
| 1453 |
},
|
| 1454 |
{
|
| 1455 |
"epoch": 21.97530864197531,
|
| 1456 |
+
"grad_norm": 0.3345847427845001,
|
| 1457 |
+
"learning_rate": 1.4860539551897576e-05,
|
| 1458 |
+
"loss": 0.0333,
|
| 1459 |
"step": 1780
|
| 1460 |
},
|
| 1461 |
{
|
| 1462 |
"epoch": 22.098765432098766,
|
| 1463 |
+
"grad_norm": 0.47660622000694275,
|
| 1464 |
+
"learning_rate": 1.463191586648377e-05,
|
| 1465 |
+
"loss": 0.0404,
|
| 1466 |
"step": 1790
|
| 1467 |
},
|
| 1468 |
{
|
| 1469 |
"epoch": 22.22222222222222,
|
| 1470 |
+
"grad_norm": 0.42594680190086365,
|
| 1471 |
+
"learning_rate": 1.440329218106996e-05,
|
| 1472 |
+
"loss": 0.0332,
|
| 1473 |
"step": 1800
|
| 1474 |
},
|
| 1475 |
{
|
| 1476 |
"epoch": 22.22222222222222,
|
| 1477 |
+
"eval_accuracy": 0.9382716049382716,
|
| 1478 |
+
"eval_f1": 0.8422712933753943,
|
| 1479 |
+
"eval_loss": 0.17968803644180298,
|
| 1480 |
+
"eval_precision": 0.8626817447495961,
|
| 1481 |
+
"eval_recall": 0.8228043143297381,
|
| 1482 |
+
"eval_runtime": 2.3118,
|
| 1483 |
+
"eval_samples_per_second": 140.152,
|
| 1484 |
+
"eval_steps_per_second": 17.735,
|
| 1485 |
"step": 1800
|
| 1486 |
},
|
| 1487 |
{
|
| 1488 |
"epoch": 22.34567901234568,
|
| 1489 |
+
"grad_norm": 0.23526711761951447,
|
| 1490 |
+
"learning_rate": 1.4174668495656151e-05,
|
| 1491 |
+
"loss": 0.0336,
|
| 1492 |
"step": 1810
|
| 1493 |
},
|
| 1494 |
{
|
| 1495 |
"epoch": 22.469135802469136,
|
| 1496 |
+
"grad_norm": 0.30145469307899475,
|
| 1497 |
+
"learning_rate": 1.3946044810242343e-05,
|
| 1498 |
+
"loss": 0.033,
|
| 1499 |
"step": 1820
|
| 1500 |
},
|
| 1501 |
{
|
| 1502 |
"epoch": 22.59259259259259,
|
| 1503 |
+
"grad_norm": 0.4943447709083557,
|
| 1504 |
+
"learning_rate": 1.3717421124828534e-05,
|
| 1505 |
+
"loss": 0.0336,
|
| 1506 |
"step": 1830
|
| 1507 |
},
|
| 1508 |
{
|
| 1509 |
"epoch": 22.71604938271605,
|
| 1510 |
+
"grad_norm": 0.5769455432891846,
|
| 1511 |
+
"learning_rate": 1.3488797439414723e-05,
|
| 1512 |
+
"loss": 0.0328,
|
| 1513 |
"step": 1840
|
| 1514 |
},
|
| 1515 |
{
|
| 1516 |
"epoch": 22.839506172839506,
|
| 1517 |
+
"grad_norm": 1.038840651512146,
|
| 1518 |
+
"learning_rate": 1.3260173754000915e-05,
|
| 1519 |
+
"loss": 0.0382,
|
| 1520 |
"step": 1850
|
| 1521 |
},
|
| 1522 |
{
|
| 1523 |
"epoch": 22.962962962962962,
|
| 1524 |
+
"grad_norm": 0.4028635323047638,
|
| 1525 |
+
"learning_rate": 1.3031550068587106e-05,
|
| 1526 |
+
"loss": 0.0315,
|
| 1527 |
"step": 1860
|
| 1528 |
},
|
| 1529 |
{
|
| 1530 |
"epoch": 23.08641975308642,
|
| 1531 |
+
"grad_norm": 0.10601099580526352,
|
| 1532 |
+
"learning_rate": 1.2802926383173297e-05,
|
| 1533 |
+
"loss": 0.0282,
|
| 1534 |
"step": 1870
|
| 1535 |
},
|
| 1536 |
{
|
| 1537 |
"epoch": 23.209876543209877,
|
| 1538 |
+
"grad_norm": 0.5546613931655884,
|
| 1539 |
+
"learning_rate": 1.2574302697759489e-05,
|
| 1540 |
+
"loss": 0.0506,
|
| 1541 |
"step": 1880
|
| 1542 |
},
|
| 1543 |
{
|
| 1544 |
"epoch": 23.333333333333332,
|
| 1545 |
+
"grad_norm": 0.3614629805088043,
|
| 1546 |
+
"learning_rate": 1.2345679012345678e-05,
|
| 1547 |
+
"loss": 0.0248,
|
| 1548 |
"step": 1890
|
| 1549 |
},
|
| 1550 |
{
|
| 1551 |
"epoch": 23.45679012345679,
|
| 1552 |
+
"grad_norm": 0.47462597489356995,
|
| 1553 |
+
"learning_rate": 1.2117055326931871e-05,
|
| 1554 |
+
"loss": 0.0283,
|
| 1555 |
"step": 1900
|
| 1556 |
},
|
| 1557 |
{
|
| 1558 |
"epoch": 23.45679012345679,
|
| 1559 |
+
"eval_accuracy": 0.9401234567901234,
|
| 1560 |
+
"eval_f1": 0.8482003129890454,
|
| 1561 |
+
"eval_loss": 0.18097253143787384,
|
| 1562 |
+
"eval_precision": 0.8616852146263911,
|
| 1563 |
+
"eval_recall": 0.8351309707241911,
|
| 1564 |
+
"eval_runtime": 3.0694,
|
| 1565 |
+
"eval_samples_per_second": 105.557,
|
| 1566 |
+
"eval_steps_per_second": 13.358,
|
| 1567 |
"step": 1900
|
| 1568 |
},
|
| 1569 |
{
|
| 1570 |
"epoch": 23.580246913580247,
|
| 1571 |
+
"grad_norm": 0.18128247559070587,
|
| 1572 |
+
"learning_rate": 1.1888431641518063e-05,
|
| 1573 |
+
"loss": 0.0338,
|
| 1574 |
"step": 1910
|
| 1575 |
},
|
| 1576 |
{
|
| 1577 |
"epoch": 23.703703703703702,
|
| 1578 |
+
"grad_norm": 0.23011884093284607,
|
| 1579 |
+
"learning_rate": 1.1659807956104254e-05,
|
| 1580 |
+
"loss": 0.0453,
|
| 1581 |
"step": 1920
|
| 1582 |
},
|
| 1583 |
{
|
| 1584 |
"epoch": 23.82716049382716,
|
| 1585 |
+
"grad_norm": 0.3289709985256195,
|
| 1586 |
+
"learning_rate": 1.1431184270690443e-05,
|
| 1587 |
+
"loss": 0.0279,
|
| 1588 |
"step": 1930
|
| 1589 |
},
|
| 1590 |
{
|
| 1591 |
"epoch": 23.950617283950617,
|
| 1592 |
+
"grad_norm": 0.13935135304927826,
|
| 1593 |
+
"learning_rate": 1.1202560585276635e-05,
|
| 1594 |
+
"loss": 0.0307,
|
| 1595 |
"step": 1940
|
| 1596 |
},
|
| 1597 |
{
|
| 1598 |
"epoch": 24.074074074074073,
|
| 1599 |
+
"grad_norm": 0.6951057314872742,
|
| 1600 |
+
"learning_rate": 1.0973936899862826e-05,
|
| 1601 |
+
"loss": 0.0382,
|
| 1602 |
"step": 1950
|
| 1603 |
},
|
| 1604 |
{
|
| 1605 |
"epoch": 24.19753086419753,
|
| 1606 |
+
"grad_norm": 1.6290189027786255,
|
| 1607 |
+
"learning_rate": 1.0745313214449017e-05,
|
| 1608 |
+
"loss": 0.0388,
|
| 1609 |
"step": 1960
|
| 1610 |
},
|
| 1611 |
{
|
| 1612 |
"epoch": 24.320987654320987,
|
| 1613 |
+
"grad_norm": 0.18432094156742096,
|
| 1614 |
+
"learning_rate": 1.0516689529035209e-05,
|
| 1615 |
+
"loss": 0.0303,
|
| 1616 |
"step": 1970
|
| 1617 |
},
|
| 1618 |
{
|
| 1619 |
"epoch": 24.444444444444443,
|
| 1620 |
+
"grad_norm": 0.47055086493492126,
|
| 1621 |
+
"learning_rate": 1.02880658436214e-05,
|
| 1622 |
+
"loss": 0.0308,
|
| 1623 |
"step": 1980
|
| 1624 |
},
|
| 1625 |
{
|
| 1626 |
"epoch": 24.567901234567902,
|
| 1627 |
+
"grad_norm": 0.41197624802589417,
|
| 1628 |
+
"learning_rate": 1.0059442158207591e-05,
|
| 1629 |
+
"loss": 0.0338,
|
| 1630 |
"step": 1990
|
| 1631 |
},
|
| 1632 |
{
|
| 1633 |
"epoch": 24.691358024691358,
|
| 1634 |
+
"grad_norm": 0.4777185916900635,
|
| 1635 |
+
"learning_rate": 9.830818472793783e-06,
|
| 1636 |
+
"loss": 0.0474,
|
| 1637 |
"step": 2000
|
| 1638 |
},
|
| 1639 |
{
|
| 1640 |
"epoch": 24.691358024691358,
|
| 1641 |
+
"eval_accuracy": 0.9398148148148148,
|
| 1642 |
+
"eval_f1": 0.845360824742268,
|
| 1643 |
+
"eval_loss": 0.17648009955883026,
|
| 1644 |
+
"eval_precision": 0.8709150326797386,
|
| 1645 |
+
"eval_recall": 0.8212634822804314,
|
| 1646 |
+
"eval_runtime": 2.9138,
|
| 1647 |
+
"eval_samples_per_second": 111.195,
|
| 1648 |
+
"eval_steps_per_second": 14.071,
|
| 1649 |
"step": 2000
|
| 1650 |
},
|
| 1651 |
{
|
| 1652 |
"epoch": 24.814814814814813,
|
| 1653 |
+
"grad_norm": 0.45768871903419495,
|
| 1654 |
+
"learning_rate": 9.602194787379972e-06,
|
| 1655 |
+
"loss": 0.0269,
|
| 1656 |
"step": 2010
|
| 1657 |
},
|
| 1658 |
{
|
| 1659 |
"epoch": 24.938271604938272,
|
| 1660 |
+
"grad_norm": 0.9567142128944397,
|
| 1661 |
+
"learning_rate": 9.373571101966163e-06,
|
| 1662 |
+
"loss": 0.0335,
|
| 1663 |
"step": 2020
|
| 1664 |
},
|
| 1665 |
{
|
| 1666 |
"epoch": 25.061728395061728,
|
| 1667 |
+
"grad_norm": 0.5306533575057983,
|
| 1668 |
+
"learning_rate": 9.144947416552355e-06,
|
| 1669 |
+
"loss": 0.0229,
|
| 1670 |
"step": 2030
|
| 1671 |
},
|
| 1672 |
{
|
| 1673 |
"epoch": 25.185185185185187,
|
| 1674 |
+
"grad_norm": 0.5475009083747864,
|
| 1675 |
+
"learning_rate": 8.916323731138548e-06,
|
| 1676 |
+
"loss": 0.0245,
|
| 1677 |
"step": 2040
|
| 1678 |
},
|
| 1679 |
{
|
| 1680 |
"epoch": 25.308641975308642,
|
| 1681 |
+
"grad_norm": 0.611080527305603,
|
| 1682 |
+
"learning_rate": 8.687700045724737e-06,
|
| 1683 |
+
"loss": 0.029,
|
| 1684 |
"step": 2050
|
| 1685 |
},
|
| 1686 |
{
|
| 1687 |
"epoch": 25.432098765432098,
|
| 1688 |
+
"grad_norm": 0.4131525158882141,
|
| 1689 |
+
"learning_rate": 8.459076360310929e-06,
|
| 1690 |
+
"loss": 0.034,
|
| 1691 |
"step": 2060
|
| 1692 |
},
|
| 1693 |
{
|
| 1694 |
"epoch": 25.555555555555557,
|
| 1695 |
+
"grad_norm": 1.0216596126556396,
|
| 1696 |
+
"learning_rate": 8.23045267489712e-06,
|
| 1697 |
+
"loss": 0.0345,
|
| 1698 |
"step": 2070
|
| 1699 |
},
|
| 1700 |
{
|
| 1701 |
"epoch": 25.679012345679013,
|
| 1702 |
+
"grad_norm": 0.6425824165344238,
|
| 1703 |
+
"learning_rate": 8.001828989483311e-06,
|
| 1704 |
+
"loss": 0.0416,
|
| 1705 |
"step": 2080
|
| 1706 |
},
|
| 1707 |
{
|
| 1708 |
"epoch": 25.80246913580247,
|
| 1709 |
+
"grad_norm": 0.9126815795898438,
|
| 1710 |
+
"learning_rate": 7.773205304069501e-06,
|
| 1711 |
+
"loss": 0.0402,
|
| 1712 |
"step": 2090
|
| 1713 |
},
|
| 1714 |
{
|
| 1715 |
"epoch": 25.925925925925927,
|
| 1716 |
+
"grad_norm": 0.35245445370674133,
|
| 1717 |
+
"learning_rate": 7.544581618655692e-06,
|
| 1718 |
+
"loss": 0.0365,
|
| 1719 |
"step": 2100
|
| 1720 |
},
|
| 1721 |
{
|
| 1722 |
"epoch": 25.925925925925927,
|
| 1723 |
+
"eval_accuracy": 0.941358024691358,
|
| 1724 |
+
"eval_f1": 0.8515625,
|
| 1725 |
+
"eval_loss": 0.18350541591644287,
|
| 1726 |
+
"eval_precision": 0.8637083993660856,
|
| 1727 |
+
"eval_recall": 0.8397534668721109,
|
| 1728 |
+
"eval_runtime": 3.2348,
|
| 1729 |
+
"eval_samples_per_second": 100.161,
|
| 1730 |
+
"eval_steps_per_second": 12.675,
|
| 1731 |
"step": 2100
|
| 1732 |
},
|
| 1733 |
{
|
| 1734 |
"epoch": 26.049382716049383,
|
| 1735 |
+
"grad_norm": 0.654412031173706,
|
| 1736 |
+
"learning_rate": 7.315957933241885e-06,
|
| 1737 |
+
"loss": 0.0312,
|
| 1738 |
"step": 2110
|
| 1739 |
},
|
| 1740 |
{
|
| 1741 |
"epoch": 26.17283950617284,
|
| 1742 |
+
"grad_norm": 1.0009406805038452,
|
| 1743 |
+
"learning_rate": 7.087334247828076e-06,
|
| 1744 |
+
"loss": 0.0336,
|
| 1745 |
"step": 2120
|
| 1746 |
},
|
| 1747 |
{
|
| 1748 |
"epoch": 26.296296296296298,
|
| 1749 |
+
"grad_norm": 0.28231924772262573,
|
| 1750 |
+
"learning_rate": 6.858710562414267e-06,
|
| 1751 |
+
"loss": 0.0408,
|
| 1752 |
"step": 2130
|
| 1753 |
},
|
| 1754 |
{
|
| 1755 |
"epoch": 26.419753086419753,
|
| 1756 |
+
"grad_norm": 0.6254132390022278,
|
| 1757 |
+
"learning_rate": 6.630086877000457e-06,
|
| 1758 |
+
"loss": 0.0298,
|
| 1759 |
"step": 2140
|
| 1760 |
},
|
| 1761 |
{
|
| 1762 |
"epoch": 26.54320987654321,
|
| 1763 |
+
"grad_norm": 1.2474095821380615,
|
| 1764 |
+
"learning_rate": 6.401463191586649e-06,
|
| 1765 |
+
"loss": 0.0382,
|
| 1766 |
"step": 2150
|
| 1767 |
},
|
| 1768 |
{
|
| 1769 |
"epoch": 26.666666666666668,
|
| 1770 |
+
"grad_norm": 0.5490561723709106,
|
| 1771 |
+
"learning_rate": 6.172839506172839e-06,
|
| 1772 |
+
"loss": 0.0283,
|
| 1773 |
"step": 2160
|
| 1774 |
},
|
| 1775 |
{
|
| 1776 |
"epoch": 26.790123456790123,
|
| 1777 |
+
"grad_norm": 0.9913358688354492,
|
| 1778 |
+
"learning_rate": 5.944215820759031e-06,
|
| 1779 |
+
"loss": 0.0339,
|
| 1780 |
"step": 2170
|
| 1781 |
},
|
| 1782 |
{
|
| 1783 |
"epoch": 26.91358024691358,
|
| 1784 |
+
"grad_norm": 0.9252423644065857,
|
| 1785 |
+
"learning_rate": 5.715592135345222e-06,
|
| 1786 |
+
"loss": 0.0286,
|
| 1787 |
"step": 2180
|
| 1788 |
},
|
| 1789 |
{
|
| 1790 |
"epoch": 27.037037037037038,
|
| 1791 |
+
"grad_norm": 0.5318057537078857,
|
| 1792 |
+
"learning_rate": 5.486968449931413e-06,
|
| 1793 |
+
"loss": 0.0316,
|
| 1794 |
"step": 2190
|
| 1795 |
},
|
| 1796 |
{
|
| 1797 |
"epoch": 27.160493827160494,
|
| 1798 |
+
"grad_norm": 0.3603754937648773,
|
| 1799 |
+
"learning_rate": 5.258344764517604e-06,
|
| 1800 |
+
"loss": 0.0244,
|
| 1801 |
"step": 2200
|
| 1802 |
},
|
| 1803 |
{
|
| 1804 |
"epoch": 27.160493827160494,
|
| 1805 |
+
"eval_accuracy": 0.9404320987654321,
|
| 1806 |
+
"eval_f1": 0.8479117415287628,
|
| 1807 |
+
"eval_loss": 0.18215233087539673,
|
| 1808 |
+
"eval_precision": 0.867741935483871,
|
| 1809 |
+
"eval_recall": 0.8289676425269645,
|
| 1810 |
+
"eval_runtime": 3.1643,
|
| 1811 |
+
"eval_samples_per_second": 102.391,
|
| 1812 |
+
"eval_steps_per_second": 12.957,
|
| 1813 |
"step": 2200
|
| 1814 |
},
|
| 1815 |
{
|
| 1816 |
"epoch": 27.28395061728395,
|
| 1817 |
+
"grad_norm": 0.6729068756103516,
|
| 1818 |
+
"learning_rate": 5.029721079103796e-06,
|
| 1819 |
+
"loss": 0.0396,
|
| 1820 |
"step": 2210
|
| 1821 |
},
|
| 1822 |
{
|
| 1823 |
"epoch": 27.40740740740741,
|
| 1824 |
+
"grad_norm": 0.8200917840003967,
|
| 1825 |
+
"learning_rate": 4.801097393689986e-06,
|
| 1826 |
+
"loss": 0.0297,
|
| 1827 |
"step": 2220
|
| 1828 |
},
|
| 1829 |
{
|
| 1830 |
"epoch": 27.530864197530864,
|
| 1831 |
+
"grad_norm": 0.9590497612953186,
|
| 1832 |
+
"learning_rate": 4.572473708276177e-06,
|
| 1833 |
+
"loss": 0.0371,
|
| 1834 |
"step": 2230
|
| 1835 |
},
|
| 1836 |
{
|
| 1837 |
"epoch": 27.65432098765432,
|
| 1838 |
+
"grad_norm": 0.23443204164505005,
|
| 1839 |
+
"learning_rate": 4.343850022862369e-06,
|
| 1840 |
+
"loss": 0.0305,
|
| 1841 |
"step": 2240
|
| 1842 |
},
|
| 1843 |
{
|
| 1844 |
"epoch": 27.77777777777778,
|
| 1845 |
+
"grad_norm": 0.18787816166877747,
|
| 1846 |
+
"learning_rate": 4.11522633744856e-06,
|
| 1847 |
+
"loss": 0.0298,
|
| 1848 |
"step": 2250
|
| 1849 |
},
|
| 1850 |
{
|
| 1851 |
"epoch": 27.901234567901234,
|
| 1852 |
+
"grad_norm": 0.32972452044487,
|
| 1853 |
+
"learning_rate": 3.8866026520347504e-06,
|
| 1854 |
+
"loss": 0.023,
|
| 1855 |
"step": 2260
|
| 1856 |
},
|
| 1857 |
{
|
| 1858 |
"epoch": 28.02469135802469,
|
| 1859 |
+
"grad_norm": 0.16079440712928772,
|
| 1860 |
+
"learning_rate": 3.6579789666209426e-06,
|
| 1861 |
+
"loss": 0.0225,
|
| 1862 |
"step": 2270
|
| 1863 |
},
|
| 1864 |
{
|
| 1865 |
"epoch": 28.14814814814815,
|
| 1866 |
+
"grad_norm": 1.2685606479644775,
|
| 1867 |
+
"learning_rate": 3.4293552812071335e-06,
|
| 1868 |
+
"loss": 0.0329,
|
| 1869 |
"step": 2280
|
| 1870 |
},
|
| 1871 |
{
|
| 1872 |
"epoch": 28.271604938271604,
|
| 1873 |
+
"grad_norm": 0.6398904323577881,
|
| 1874 |
+
"learning_rate": 3.2007315957933243e-06,
|
| 1875 |
+
"loss": 0.0307,
|
| 1876 |
"step": 2290
|
| 1877 |
},
|
| 1878 |
{
|
| 1879 |
"epoch": 28.395061728395063,
|
| 1880 |
+
"grad_norm": 0.6520938873291016,
|
| 1881 |
+
"learning_rate": 2.9721079103795156e-06,
|
| 1882 |
+
"loss": 0.0242,
|
| 1883 |
"step": 2300
|
| 1884 |
},
|
| 1885 |
{
|
| 1886 |
"epoch": 28.395061728395063,
|
| 1887 |
+
"eval_accuracy": 0.9407407407407408,
|
| 1888 |
+
"eval_f1": 0.8483412322274881,
|
| 1889 |
+
"eval_loss": 0.18079863488674164,
|
| 1890 |
+
"eval_precision": 0.8703403565640194,
|
| 1891 |
+
"eval_recall": 0.827426810477658,
|
| 1892 |
+
"eval_runtime": 2.3949,
|
| 1893 |
+
"eval_samples_per_second": 135.29,
|
| 1894 |
+
"eval_steps_per_second": 17.12,
|
| 1895 |
"step": 2300
|
| 1896 |
},
|
| 1897 |
{
|
| 1898 |
"epoch": 28.51851851851852,
|
| 1899 |
+
"grad_norm": 0.20304135978221893,
|
| 1900 |
+
"learning_rate": 2.7434842249657065e-06,
|
| 1901 |
+
"loss": 0.0225,
|
| 1902 |
"step": 2310
|
| 1903 |
},
|
| 1904 |
{
|
| 1905 |
"epoch": 28.641975308641975,
|
| 1906 |
+
"grad_norm": 0.9393714070320129,
|
| 1907 |
+
"learning_rate": 2.514860539551898e-06,
|
| 1908 |
+
"loss": 0.0294,
|
| 1909 |
"step": 2320
|
| 1910 |
},
|
| 1911 |
{
|
| 1912 |
"epoch": 28.765432098765434,
|
| 1913 |
+
"grad_norm": 0.3730199933052063,
|
| 1914 |
+
"learning_rate": 2.2862368541380887e-06,
|
| 1915 |
+
"loss": 0.0339,
|
| 1916 |
"step": 2330
|
| 1917 |
},
|
| 1918 |
{
|
| 1919 |
"epoch": 28.88888888888889,
|
| 1920 |
+
"grad_norm": 0.6354162096977234,
|
| 1921 |
+
"learning_rate": 2.05761316872428e-06,
|
| 1922 |
+
"loss": 0.028,
|
| 1923 |
"step": 2340
|
| 1924 |
},
|
| 1925 |
{
|
| 1926 |
"epoch": 29.012345679012345,
|
| 1927 |
+
"grad_norm": 0.3703112006187439,
|
| 1928 |
+
"learning_rate": 1.8289894833104713e-06,
|
| 1929 |
+
"loss": 0.0314,
|
| 1930 |
"step": 2350
|
| 1931 |
},
|
| 1932 |
{
|
| 1933 |
"epoch": 29.135802469135804,
|
| 1934 |
+
"grad_norm": 0.5848723649978638,
|
| 1935 |
+
"learning_rate": 1.6003657978966622e-06,
|
| 1936 |
+
"loss": 0.0361,
|
| 1937 |
"step": 2360
|
| 1938 |
},
|
| 1939 |
{
|
| 1940 |
"epoch": 29.25925925925926,
|
| 1941 |
+
"grad_norm": 0.5978838205337524,
|
| 1942 |
+
"learning_rate": 1.3717421124828533e-06,
|
| 1943 |
+
"loss": 0.0406,
|
| 1944 |
"step": 2370
|
| 1945 |
},
|
| 1946 |
{
|
| 1947 |
"epoch": 29.382716049382715,
|
| 1948 |
+
"grad_norm": 0.280225545167923,
|
| 1949 |
+
"learning_rate": 1.1431184270690443e-06,
|
| 1950 |
+
"loss": 0.0319,
|
| 1951 |
"step": 2380
|
| 1952 |
},
|
| 1953 |
{
|
| 1954 |
"epoch": 29.506172839506174,
|
| 1955 |
+
"grad_norm": 0.39151689410209656,
|
| 1956 |
+
"learning_rate": 9.144947416552356e-07,
|
| 1957 |
+
"loss": 0.0263,
|
| 1958 |
"step": 2390
|
| 1959 |
},
|
| 1960 |
{
|
| 1961 |
"epoch": 29.62962962962963,
|
| 1962 |
+
"grad_norm": 0.5079048871994019,
|
| 1963 |
+
"learning_rate": 6.858710562414266e-07,
|
| 1964 |
+
"loss": 0.0296,
|
| 1965 |
"step": 2400
|
| 1966 |
},
|
| 1967 |
{
|
| 1968 |
"epoch": 29.62962962962963,
|
| 1969 |
+
"eval_accuracy": 0.9401234567901234,
|
| 1970 |
+
"eval_f1": 0.847723704866562,
|
| 1971 |
+
"eval_loss": 0.18171092867851257,
|
| 1972 |
+
"eval_precision": 0.864,
|
| 1973 |
+
"eval_recall": 0.8320493066255779,
|
| 1974 |
+
"eval_runtime": 2.4278,
|
| 1975 |
+
"eval_samples_per_second": 133.453,
|
| 1976 |
+
"eval_steps_per_second": 16.888,
|
| 1977 |
"step": 2400
|
| 1978 |
},
|
| 1979 |
{
|
| 1980 |
"epoch": 29.753086419753085,
|
| 1981 |
+
"grad_norm": 0.5158771276473999,
|
| 1982 |
+
"learning_rate": 4.572473708276178e-07,
|
| 1983 |
+
"loss": 0.026,
|
| 1984 |
"step": 2410
|
| 1985 |
},
|
| 1986 |
{
|
| 1987 |
"epoch": 29.876543209876544,
|
| 1988 |
+
"grad_norm": 0.7846933603286743,
|
| 1989 |
+
"learning_rate": 2.286236854138089e-07,
|
| 1990 |
+
"loss": 0.0275,
|
| 1991 |
"step": 2420
|
| 1992 |
},
|
| 1993 |
{
|
| 1994 |
"epoch": 30.0,
|
| 1995 |
+
"grad_norm": 0.403104305267334,
|
| 1996 |
"learning_rate": 0.0,
|
| 1997 |
+
"loss": 0.0277,
|
| 1998 |
"step": 2430
|
| 1999 |
},
|
| 2000 |
{
|
| 2001 |
"epoch": 30.0,
|
| 2002 |
"step": 2430,
|
| 2003 |
"total_flos": 3.008454731998249e+18,
|
| 2004 |
+
"train_loss": 0.09584075045070531,
|
| 2005 |
+
"train_runtime": 684.1699,
|
| 2006 |
+
"train_samples_per_second": 56.74,
|
| 2007 |
+
"train_steps_per_second": 3.552
|
| 2008 |
}
|
| 2009 |
],
|
| 2010 |
"logging_steps": 10,
|