Model save
Browse files
README.md
CHANGED
|
@@ -2,13 +2,10 @@
|
|
| 2 |
license: llama2
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
| 5 |
-
- alignment-handbook
|
| 6 |
- trl
|
| 7 |
- sft
|
| 8 |
- generated_from_trainer
|
| 9 |
base_model: meta-llama/Llama-2-7b-hf
|
| 10 |
-
datasets:
|
| 11 |
-
- HuggingFaceH4/ultrachat_200k
|
| 12 |
model-index:
|
| 13 |
- name: llama2-20p-POE
|
| 14 |
results: []
|
|
@@ -19,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
# llama2-20p-POE
|
| 21 |
|
| 22 |
-
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the
|
| 23 |
It achieves the following results on the evaluation set:
|
| 24 |
- Loss: nan
|
| 25 |
|
|
@@ -58,7 +55,7 @@ The following hyperparameters were used during training:
|
|
| 58 |
|
| 59 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 60 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 61 |
-
| 0.
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
|
|
|
| 2 |
license: llama2
|
| 3 |
library_name: peft
|
| 4 |
tags:
|
|
|
|
| 5 |
- trl
|
| 6 |
- sft
|
| 7 |
- generated_from_trainer
|
| 8 |
base_model: meta-llama/Llama-2-7b-hf
|
|
|
|
|
|
|
| 9 |
model-index:
|
| 10 |
- name: llama2-20p-POE
|
| 11 |
results: []
|
|
|
|
| 16 |
|
| 17 |
# llama2-20p-POE
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: nan
|
| 22 |
|
|
|
|
| 55 |
|
| 56 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 58 |
+
| 0.7327 | 1.0 | 1039 | nan |
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 60089544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af8b59a0f339223195ffda22e2cc190e5b99e802340991131a98cce499515eaf
|
| 3 |
size 60089544
|
all_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.7603742487735766,
|
| 4 |
+
"train_runtime": 32307.7024,
|
| 5 |
+
"train_samples": 33257,
|
| 6 |
+
"train_samples_per_second": 1.029,
|
| 7 |
+
"train_steps_per_second": 0.032
|
| 8 |
}
|
runs/May03_06-09-37_ip-172-31-69-60.ec2.internal/events.out.tfevents.1714716718.ip-172-31-69-60.ec2.internal.2066.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38dcc78b365fe2e878562c93604823a359f8f1c3842b73d7ec15f47d7c201acf
|
| 3 |
+
size 49121
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 0.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 0.7603742487735766,
|
| 4 |
+
"train_runtime": 32307.7024,
|
| 5 |
+
"train_samples": 33257,
|
| 6 |
+
"train_samples_per_second": 1.029,
|
| 7 |
+
"train_steps_per_second": 0.032
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,989 +1,1493 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 5
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.01,
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm": 0.
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss": 0.
|
| 37 |
"step": 15
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm": 0.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 25
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm": 0.
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 0.
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm": 0.
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 0.
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm": 0.
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 0.
|
| 72 |
"step": 40
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm": 0.
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 0.
|
| 79 |
"step": 45
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"grad_norm": 0.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 50
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"grad_norm": 0.
|
| 91 |
-
"learning_rate": 0.
|
| 92 |
-
"loss": 0.
|
| 93 |
"step": 55
|
| 94 |
},
|
| 95 |
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"grad_norm": 0.
|
| 98 |
-
"learning_rate": 0.
|
| 99 |
-
"loss": 0.
|
| 100 |
"step": 60
|
| 101 |
},
|
| 102 |
{
|
| 103 |
-
"epoch": 0.
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
-
"learning_rate": 0.
|
| 106 |
-
"loss": 0.
|
| 107 |
"step": 65
|
| 108 |
},
|
| 109 |
{
|
| 110 |
-
"epoch": 0.
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
-
"learning_rate": 0.
|
| 113 |
-
"loss": 0.
|
| 114 |
"step": 70
|
| 115 |
},
|
| 116 |
{
|
| 117 |
-
"epoch": 0.
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
-
"learning_rate": 0.
|
| 120 |
-
"loss": 0.
|
| 121 |
"step": 75
|
| 122 |
},
|
| 123 |
{
|
| 124 |
-
"epoch": 0.
|
| 125 |
-
"grad_norm": 0.
|
| 126 |
-
"learning_rate": 0.
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 80
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"grad_norm": 0.
|
| 133 |
-
"learning_rate": 0.
|
| 134 |
-
"loss": 0.
|
| 135 |
"step": 85
|
| 136 |
},
|
| 137 |
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
-
"learning_rate": 0.
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 90
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch": 0.
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
-
"learning_rate": 0.
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 95
|
| 150 |
},
|
| 151 |
{
|
| 152 |
-
"epoch": 0.
|
| 153 |
-
"grad_norm": 0.
|
| 154 |
-
"learning_rate": 0.
|
| 155 |
-
"loss": 0.
|
| 156 |
"step": 100
|
| 157 |
},
|
| 158 |
{
|
| 159 |
-
"epoch": 0.
|
| 160 |
-
"grad_norm": 0.
|
| 161 |
-
"learning_rate": 0.
|
| 162 |
-
"loss": 0.
|
| 163 |
"step": 105
|
| 164 |
},
|
| 165 |
{
|
| 166 |
-
"epoch": 0.
|
| 167 |
-
"grad_norm": 0.
|
| 168 |
-
"learning_rate": 0.
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 110
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch": 0.
|
| 174 |
-
"grad_norm": 0.
|
| 175 |
-
"learning_rate": 0.
|
| 176 |
-
"loss": 0.
|
| 177 |
"step": 115
|
| 178 |
},
|
| 179 |
{
|
| 180 |
-
"epoch": 0.
|
| 181 |
-
"grad_norm": 0.
|
| 182 |
-
"learning_rate": 0.
|
| 183 |
-
"loss": 0.
|
| 184 |
"step": 120
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch": 0.
|
| 188 |
-
"grad_norm": 0.
|
| 189 |
-
"learning_rate": 0.
|
| 190 |
-
"loss": 0.
|
| 191 |
"step": 125
|
| 192 |
},
|
| 193 |
{
|
| 194 |
-
"epoch": 0.
|
| 195 |
-
"grad_norm": 0.
|
| 196 |
-
"learning_rate": 0.
|
| 197 |
-
"loss": 0.
|
| 198 |
"step": 130
|
| 199 |
},
|
| 200 |
{
|
| 201 |
-
"epoch": 0.
|
| 202 |
-
"grad_norm": 0.
|
| 203 |
-
"learning_rate": 0.
|
| 204 |
-
"loss": 0.
|
| 205 |
"step": 135
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch": 0.
|
| 209 |
-
"grad_norm": 0.
|
| 210 |
-
"learning_rate": 0.
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 140
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch": 0.
|
| 216 |
-
"grad_norm": 0.
|
| 217 |
-
"learning_rate": 0.
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 145
|
| 220 |
},
|
| 221 |
{
|
| 222 |
-
"epoch": 0.
|
| 223 |
-
"grad_norm": 0.
|
| 224 |
-
"learning_rate": 0.
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 150
|
| 227 |
},
|
| 228 |
{
|
| 229 |
-
"epoch": 0.
|
| 230 |
-
"grad_norm": 0.
|
| 231 |
-
"learning_rate": 0.
|
| 232 |
-
"loss": 0.
|
| 233 |
"step": 155
|
| 234 |
},
|
| 235 |
{
|
| 236 |
-
"epoch": 0.
|
| 237 |
-
"grad_norm": 0.
|
| 238 |
-
"learning_rate": 0.
|
| 239 |
-
"loss": 0.
|
| 240 |
"step": 160
|
| 241 |
},
|
| 242 |
{
|
| 243 |
-
"epoch": 0.
|
| 244 |
-
"grad_norm": 0.
|
| 245 |
-
"learning_rate": 0.
|
| 246 |
-
"loss": 0.
|
| 247 |
"step": 165
|
| 248 |
},
|
| 249 |
{
|
| 250 |
-
"epoch": 0.
|
| 251 |
-
"grad_norm": 0.
|
| 252 |
-
"learning_rate": 0.
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 170
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch": 0.
|
| 258 |
-
"grad_norm": 0.
|
| 259 |
-
"learning_rate": 0.
|
| 260 |
-
"loss": 0.
|
| 261 |
"step": 175
|
| 262 |
},
|
| 263 |
{
|
| 264 |
-
"epoch": 0.
|
| 265 |
-
"grad_norm": 0.
|
| 266 |
-
"learning_rate": 0.
|
| 267 |
-
"loss": 0.
|
| 268 |
"step": 180
|
| 269 |
},
|
| 270 |
{
|
| 271 |
-
"epoch": 0.
|
| 272 |
-
"grad_norm": 0.
|
| 273 |
-
"learning_rate": 0.
|
| 274 |
-
"loss": 0.
|
| 275 |
"step": 185
|
| 276 |
},
|
| 277 |
{
|
| 278 |
-
"epoch": 0.
|
| 279 |
-
"grad_norm": 0.
|
| 280 |
-
"learning_rate": 0.
|
| 281 |
-
"loss": 0.
|
| 282 |
"step": 190
|
| 283 |
},
|
| 284 |
{
|
| 285 |
-
"epoch": 0.
|
| 286 |
-
"grad_norm": 0.
|
| 287 |
-
"learning_rate": 0.
|
| 288 |
-
"loss": 0.
|
| 289 |
"step": 195
|
| 290 |
},
|
| 291 |
{
|
| 292 |
-
"epoch": 0.
|
| 293 |
-
"grad_norm": 0.
|
| 294 |
-
"learning_rate": 0.
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 200
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch": 0.
|
| 300 |
-
"grad_norm": 0.
|
| 301 |
-
"learning_rate": 0.
|
| 302 |
-
"loss": 0.
|
| 303 |
"step": 205
|
| 304 |
},
|
| 305 |
{
|
| 306 |
-
"epoch": 0.
|
| 307 |
-
"grad_norm": 0.
|
| 308 |
-
"learning_rate": 0.
|
| 309 |
-
"loss": 0.
|
| 310 |
"step": 210
|
| 311 |
},
|
| 312 |
{
|
| 313 |
-
"epoch": 0.
|
| 314 |
-
"grad_norm": 0.
|
| 315 |
-
"learning_rate": 0.
|
| 316 |
-
"loss": 0.
|
| 317 |
"step": 215
|
| 318 |
},
|
| 319 |
{
|
| 320 |
-
"epoch": 0.
|
| 321 |
-
"grad_norm": 0.
|
| 322 |
-
"learning_rate": 0.
|
| 323 |
-
"loss": 0.
|
| 324 |
"step": 220
|
| 325 |
},
|
| 326 |
{
|
| 327 |
-
"epoch": 0.
|
| 328 |
-
"grad_norm": 0.
|
| 329 |
-
"learning_rate": 0.
|
| 330 |
-
"loss": 0.
|
| 331 |
"step": 225
|
| 332 |
},
|
| 333 |
{
|
| 334 |
-
"epoch": 0.
|
| 335 |
-
"grad_norm": 0.
|
| 336 |
-
"learning_rate": 0.
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 230
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch": 0.
|
| 342 |
-
"grad_norm": 0.
|
| 343 |
-
"learning_rate": 0.
|
| 344 |
-
"loss": 0.
|
| 345 |
"step": 235
|
| 346 |
},
|
| 347 |
{
|
| 348 |
-
"epoch": 0.
|
| 349 |
-
"grad_norm": 0.
|
| 350 |
-
"learning_rate": 0.
|
| 351 |
-
"loss": 0.
|
| 352 |
"step": 240
|
| 353 |
},
|
| 354 |
{
|
| 355 |
-
"epoch": 0.
|
| 356 |
-
"grad_norm": 0.
|
| 357 |
-
"learning_rate": 0.
|
| 358 |
-
"loss": 0.
|
| 359 |
"step": 245
|
| 360 |
},
|
| 361 |
{
|
| 362 |
-
"epoch": 0.
|
| 363 |
-
"grad_norm": 0.
|
| 364 |
-
"learning_rate": 0.
|
| 365 |
-
"loss": 0.
|
| 366 |
"step": 250
|
| 367 |
},
|
| 368 |
{
|
| 369 |
-
"epoch": 0.
|
| 370 |
-
"grad_norm": 0.
|
| 371 |
-
"learning_rate": 0.
|
| 372 |
-
"loss": 0.
|
| 373 |
"step": 255
|
| 374 |
},
|
| 375 |
{
|
| 376 |
-
"epoch": 0.
|
| 377 |
-
"grad_norm": 0.
|
| 378 |
-
"learning_rate": 0.
|
| 379 |
-
"loss": 0.
|
| 380 |
"step": 260
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"epoch": 0.
|
| 384 |
-
"grad_norm": 0.
|
| 385 |
-
"learning_rate": 0.
|
| 386 |
-
"loss": 0.
|
| 387 |
"step": 265
|
| 388 |
},
|
| 389 |
{
|
| 390 |
-
"epoch": 0.
|
| 391 |
-
"grad_norm": 0.
|
| 392 |
-
"learning_rate": 0.
|
| 393 |
-
"loss": 0.
|
| 394 |
"step": 270
|
| 395 |
},
|
| 396 |
{
|
| 397 |
-
"epoch": 0.
|
| 398 |
-
"grad_norm": 0.
|
| 399 |
-
"learning_rate": 0.
|
| 400 |
-
"loss": 0.
|
| 401 |
"step": 275
|
| 402 |
},
|
| 403 |
{
|
| 404 |
-
"epoch": 0.
|
| 405 |
-
"grad_norm": 0.
|
| 406 |
-
"learning_rate": 0.
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 280
|
| 409 |
},
|
| 410 |
{
|
| 411 |
-
"epoch": 0.
|
| 412 |
-
"grad_norm": 0.
|
| 413 |
-
"learning_rate": 0.
|
| 414 |
-
"loss": 0.
|
| 415 |
"step": 285
|
| 416 |
},
|
| 417 |
{
|
| 418 |
-
"epoch": 0.
|
| 419 |
-
"grad_norm": 0.
|
| 420 |
-
"learning_rate": 0.
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 290
|
| 423 |
},
|
| 424 |
{
|
| 425 |
-
"epoch": 0.
|
| 426 |
-
"grad_norm": 0.
|
| 427 |
-
"learning_rate": 0.
|
| 428 |
-
"loss": 0.
|
| 429 |
"step": 295
|
| 430 |
},
|
| 431 |
{
|
| 432 |
-
"epoch": 0.
|
| 433 |
-
"grad_norm": 0.
|
| 434 |
-
"learning_rate": 0.
|
| 435 |
-
"loss": 0.
|
| 436 |
"step": 300
|
| 437 |
},
|
| 438 |
{
|
| 439 |
-
"epoch": 0.
|
| 440 |
-
"grad_norm": 0.
|
| 441 |
-
"learning_rate": 0.
|
| 442 |
-
"loss": 0.
|
| 443 |
"step": 305
|
| 444 |
},
|
| 445 |
{
|
| 446 |
-
"epoch": 0.
|
| 447 |
-
"grad_norm": 0.
|
| 448 |
-
"learning_rate": 0.
|
| 449 |
-
"loss": 0.
|
| 450 |
"step": 310
|
| 451 |
},
|
| 452 |
{
|
| 453 |
-
"epoch": 0.
|
| 454 |
-
"grad_norm": 0.
|
| 455 |
-
"learning_rate": 0.
|
| 456 |
-
"loss": 0.
|
| 457 |
"step": 315
|
| 458 |
},
|
| 459 |
{
|
| 460 |
-
"epoch": 0.
|
| 461 |
-
"grad_norm": 0.
|
| 462 |
-
"learning_rate": 0.
|
| 463 |
-
"loss": 0.
|
| 464 |
"step": 320
|
| 465 |
},
|
| 466 |
{
|
| 467 |
-
"epoch": 0.
|
| 468 |
-
"grad_norm": 0.
|
| 469 |
-
"learning_rate": 0.
|
| 470 |
-
"loss": 0.
|
| 471 |
"step": 325
|
| 472 |
},
|
| 473 |
{
|
| 474 |
-
"epoch": 0.
|
| 475 |
-
"grad_norm": 0.
|
| 476 |
-
"learning_rate": 0.
|
| 477 |
-
"loss": 0.
|
| 478 |
"step": 330
|
| 479 |
},
|
| 480 |
{
|
| 481 |
-
"epoch": 0.
|
| 482 |
-
"grad_norm": 0.
|
| 483 |
-
"learning_rate": 0.
|
| 484 |
-
"loss": 0.
|
| 485 |
"step": 335
|
| 486 |
},
|
| 487 |
{
|
| 488 |
-
"epoch": 0.
|
| 489 |
-
"grad_norm": 0.
|
| 490 |
-
"learning_rate": 0.
|
| 491 |
-
"loss": 0.
|
| 492 |
"step": 340
|
| 493 |
},
|
| 494 |
{
|
| 495 |
-
"epoch": 0.
|
| 496 |
-
"grad_norm": 0.
|
| 497 |
-
"learning_rate": 0.
|
| 498 |
-
"loss": 0.
|
| 499 |
"step": 345
|
| 500 |
},
|
| 501 |
{
|
| 502 |
-
"epoch": 0.
|
| 503 |
-
"grad_norm": 0.
|
| 504 |
-
"learning_rate": 0.
|
| 505 |
-
"loss": 0.
|
| 506 |
"step": 350
|
| 507 |
},
|
| 508 |
{
|
| 509 |
-
"epoch": 0.
|
| 510 |
-
"grad_norm": 0.
|
| 511 |
-
"learning_rate": 0.
|
| 512 |
-
"loss": 0.
|
| 513 |
"step": 355
|
| 514 |
},
|
| 515 |
{
|
| 516 |
-
"epoch": 0.
|
| 517 |
-
"grad_norm": 0.
|
| 518 |
-
"learning_rate": 0.
|
| 519 |
-
"loss": 0.
|
| 520 |
"step": 360
|
| 521 |
},
|
| 522 |
{
|
| 523 |
-
"epoch": 0.
|
| 524 |
-
"grad_norm": 0.
|
| 525 |
-
"learning_rate": 0.
|
| 526 |
-
"loss": 0.
|
| 527 |
"step": 365
|
| 528 |
},
|
| 529 |
{
|
| 530 |
-
"epoch": 0.
|
| 531 |
-
"grad_norm": 0.
|
| 532 |
-
"learning_rate": 0.
|
| 533 |
-
"loss": 0.
|
| 534 |
"step": 370
|
| 535 |
},
|
| 536 |
{
|
| 537 |
-
"epoch": 0.
|
| 538 |
-
"grad_norm": 0.
|
| 539 |
-
"learning_rate":
|
| 540 |
-
"loss": 0.
|
| 541 |
"step": 375
|
| 542 |
},
|
| 543 |
{
|
| 544 |
-
"epoch": 0.
|
| 545 |
-
"grad_norm": 0.
|
| 546 |
-
"learning_rate":
|
| 547 |
-
"loss": 0.
|
| 548 |
"step": 380
|
| 549 |
},
|
| 550 |
{
|
| 551 |
-
"epoch": 0.
|
| 552 |
-
"grad_norm": 0.
|
| 553 |
-
"learning_rate":
|
| 554 |
-
"loss": 0.
|
| 555 |
"step": 385
|
| 556 |
},
|
| 557 |
{
|
| 558 |
-
"epoch": 0.
|
| 559 |
-
"grad_norm": 0.
|
| 560 |
-
"learning_rate":
|
| 561 |
-
"loss": 0.
|
| 562 |
"step": 390
|
| 563 |
},
|
| 564 |
{
|
| 565 |
-
"epoch": 0.
|
| 566 |
-
"grad_norm": 0.
|
| 567 |
-
"learning_rate":
|
| 568 |
-
"loss": 0.
|
| 569 |
"step": 395
|
| 570 |
},
|
| 571 |
{
|
| 572 |
-
"epoch": 0.
|
| 573 |
-
"grad_norm": 0.
|
| 574 |
-
"learning_rate":
|
| 575 |
-
"loss": 0.
|
| 576 |
"step": 400
|
| 577 |
},
|
| 578 |
{
|
| 579 |
-
"epoch": 0.
|
| 580 |
-
"grad_norm": 0.
|
| 581 |
-
"learning_rate":
|
| 582 |
-
"loss": 0.
|
| 583 |
"step": 405
|
| 584 |
},
|
| 585 |
{
|
| 586 |
-
"epoch": 0.
|
| 587 |
-
"grad_norm": 0.
|
| 588 |
-
"learning_rate":
|
| 589 |
-
"loss": 0.
|
| 590 |
"step": 410
|
| 591 |
},
|
| 592 |
{
|
| 593 |
-
"epoch": 0.
|
| 594 |
-
"grad_norm": 0.
|
| 595 |
-
"learning_rate":
|
| 596 |
-
"loss": 0.
|
| 597 |
"step": 415
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch": 0.
|
| 601 |
-
"grad_norm": 0.
|
| 602 |
-
"learning_rate":
|
| 603 |
-
"loss": 0.
|
| 604 |
"step": 420
|
| 605 |
},
|
| 606 |
{
|
| 607 |
-
"epoch": 0.
|
| 608 |
-
"grad_norm": 0.
|
| 609 |
-
"learning_rate":
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 425
|
| 612 |
},
|
| 613 |
{
|
| 614 |
-
"epoch": 0.
|
| 615 |
-
"grad_norm": 0.
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 0.
|
| 618 |
"step": 430
|
| 619 |
},
|
| 620 |
{
|
| 621 |
-
"epoch": 0.
|
| 622 |
-
"grad_norm": 0.
|
| 623 |
-
"learning_rate":
|
| 624 |
-
"loss": 0.
|
| 625 |
"step": 435
|
| 626 |
},
|
| 627 |
{
|
| 628 |
-
"epoch": 0.
|
| 629 |
-
"grad_norm": 0.
|
| 630 |
-
"learning_rate":
|
| 631 |
-
"loss": 0.
|
| 632 |
"step": 440
|
| 633 |
},
|
| 634 |
{
|
| 635 |
-
"epoch": 0.
|
| 636 |
-
"grad_norm": 0.
|
| 637 |
-
"learning_rate":
|
| 638 |
-
"loss": 0.
|
| 639 |
"step": 445
|
| 640 |
},
|
| 641 |
{
|
| 642 |
-
"epoch": 0.
|
| 643 |
-
"grad_norm": 0.
|
| 644 |
-
"learning_rate":
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 450
|
| 647 |
},
|
| 648 |
{
|
| 649 |
-
"epoch": 0.
|
| 650 |
-
"grad_norm": 0.
|
| 651 |
-
"learning_rate":
|
| 652 |
-
"loss": 0.
|
| 653 |
"step": 455
|
| 654 |
},
|
| 655 |
{
|
| 656 |
-
"epoch": 0.
|
| 657 |
-
"grad_norm": 0.
|
| 658 |
-
"learning_rate":
|
| 659 |
-
"loss": 0.
|
| 660 |
"step": 460
|
| 661 |
},
|
| 662 |
{
|
| 663 |
-
"epoch": 0.
|
| 664 |
-
"grad_norm": 0.
|
| 665 |
-
"learning_rate":
|
| 666 |
-
"loss": 0.
|
| 667 |
"step": 465
|
| 668 |
},
|
| 669 |
{
|
| 670 |
-
"epoch": 0.
|
| 671 |
-
"grad_norm": 0.
|
| 672 |
-
"learning_rate":
|
| 673 |
-
"loss": 0.
|
| 674 |
"step": 470
|
| 675 |
},
|
| 676 |
{
|
| 677 |
-
"epoch": 0.
|
| 678 |
-
"grad_norm": 0.
|
| 679 |
-
"learning_rate":
|
| 680 |
-
"loss": 0.
|
| 681 |
"step": 475
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch": 0.
|
| 685 |
-
"grad_norm": 0.
|
| 686 |
-
"learning_rate":
|
| 687 |
-
"loss": 0.
|
| 688 |
"step": 480
|
| 689 |
},
|
| 690 |
{
|
| 691 |
-
"epoch": 0.
|
| 692 |
-
"grad_norm": 0.
|
| 693 |
-
"learning_rate":
|
| 694 |
-
"loss": 0.
|
| 695 |
"step": 485
|
| 696 |
},
|
| 697 |
{
|
| 698 |
-
"epoch": 0.
|
| 699 |
-
"grad_norm": 0.
|
| 700 |
-
"learning_rate":
|
| 701 |
-
"loss": 0.
|
| 702 |
"step": 490
|
| 703 |
},
|
| 704 |
{
|
| 705 |
-
"epoch": 0.
|
| 706 |
-
"grad_norm": 0.
|
| 707 |
-
"learning_rate":
|
| 708 |
-
"loss": 0.
|
| 709 |
"step": 495
|
| 710 |
},
|
| 711 |
{
|
| 712 |
-
"epoch": 0.
|
| 713 |
-
"grad_norm": 0.
|
| 714 |
-
"learning_rate":
|
| 715 |
-
"loss": 0.
|
| 716 |
"step": 500
|
| 717 |
},
|
| 718 |
{
|
| 719 |
-
"epoch": 0.
|
| 720 |
-
"grad_norm": 0.
|
| 721 |
-
"learning_rate":
|
| 722 |
-
"loss": 0.
|
| 723 |
"step": 505
|
| 724 |
},
|
| 725 |
{
|
| 726 |
-
"epoch": 0.
|
| 727 |
-
"grad_norm": 0.
|
| 728 |
-
"learning_rate":
|
| 729 |
-
"loss": 0.
|
| 730 |
"step": 510
|
| 731 |
},
|
| 732 |
{
|
| 733 |
-
"epoch": 0.
|
| 734 |
-
"grad_norm": 0.
|
| 735 |
-
"learning_rate":
|
| 736 |
-
"loss": 0.
|
| 737 |
"step": 515
|
| 738 |
},
|
| 739 |
{
|
| 740 |
-
"epoch": 0.
|
| 741 |
-
"grad_norm": 0.
|
| 742 |
-
"learning_rate":
|
| 743 |
-
"loss": 0.
|
| 744 |
"step": 520
|
| 745 |
},
|
| 746 |
{
|
| 747 |
-
"epoch": 0.
|
| 748 |
-
"grad_norm": 0.
|
| 749 |
-
"learning_rate":
|
| 750 |
-
"loss": 0.
|
| 751 |
"step": 525
|
| 752 |
},
|
| 753 |
{
|
| 754 |
-
"epoch": 0.
|
| 755 |
-
"grad_norm": 0.
|
| 756 |
-
"learning_rate":
|
| 757 |
-
"loss": 0.
|
| 758 |
"step": 530
|
| 759 |
},
|
| 760 |
{
|
| 761 |
-
"epoch": 0.
|
| 762 |
-
"grad_norm": 0.
|
| 763 |
-
"learning_rate":
|
| 764 |
-
"loss": 0.
|
| 765 |
"step": 535
|
| 766 |
},
|
| 767 |
{
|
| 768 |
-
"epoch": 0.
|
| 769 |
-
"grad_norm": 0.
|
| 770 |
-
"learning_rate":
|
| 771 |
-
"loss": 0.
|
| 772 |
"step": 540
|
| 773 |
},
|
| 774 |
{
|
| 775 |
-
"epoch": 0.
|
| 776 |
-
"grad_norm": 0.
|
| 777 |
-
"learning_rate":
|
| 778 |
-
"loss": 0.
|
| 779 |
"step": 545
|
| 780 |
},
|
| 781 |
{
|
| 782 |
-
"epoch": 0.
|
| 783 |
-
"grad_norm": 0.
|
| 784 |
-
"learning_rate":
|
| 785 |
-
"loss": 0.
|
| 786 |
"step": 550
|
| 787 |
},
|
| 788 |
{
|
| 789 |
-
"epoch": 0.
|
| 790 |
-
"grad_norm": 0.
|
| 791 |
-
"learning_rate":
|
| 792 |
-
"loss": 0.
|
| 793 |
"step": 555
|
| 794 |
},
|
| 795 |
{
|
| 796 |
-
"epoch": 0.
|
| 797 |
-
"grad_norm": 0.
|
| 798 |
-
"learning_rate":
|
| 799 |
-
"loss": 0.
|
| 800 |
"step": 560
|
| 801 |
},
|
| 802 |
{
|
| 803 |
-
"epoch": 0.
|
| 804 |
-
"grad_norm": 0.
|
| 805 |
-
"learning_rate":
|
| 806 |
-
"loss": 0.
|
| 807 |
"step": 565
|
| 808 |
},
|
| 809 |
{
|
| 810 |
-
"epoch": 0.
|
| 811 |
-
"grad_norm": 0.
|
| 812 |
-
"learning_rate":
|
| 813 |
-
"loss": 0.
|
| 814 |
"step": 570
|
| 815 |
},
|
| 816 |
{
|
| 817 |
-
"epoch": 0.
|
| 818 |
-
"grad_norm": 0.
|
| 819 |
-
"learning_rate":
|
| 820 |
-
"loss": 0.
|
| 821 |
"step": 575
|
| 822 |
},
|
| 823 |
{
|
| 824 |
-
"epoch": 0.
|
| 825 |
-
"grad_norm": 0.
|
| 826 |
-
"learning_rate":
|
| 827 |
-
"loss": 0.
|
| 828 |
"step": 580
|
| 829 |
},
|
| 830 |
{
|
| 831 |
-
"epoch": 0.
|
| 832 |
-
"grad_norm": 0.
|
| 833 |
-
"learning_rate":
|
| 834 |
-
"loss": 0.
|
| 835 |
"step": 585
|
| 836 |
},
|
| 837 |
{
|
| 838 |
-
"epoch": 0.
|
| 839 |
-
"grad_norm": 0.
|
| 840 |
-
"learning_rate": 9.
|
| 841 |
-
"loss": 0.
|
| 842 |
"step": 590
|
| 843 |
},
|
| 844 |
{
|
| 845 |
-
"epoch": 0.
|
| 846 |
-
"grad_norm": 0.
|
| 847 |
-
"learning_rate":
|
| 848 |
-
"loss": 0.
|
| 849 |
"step": 595
|
| 850 |
},
|
| 851 |
{
|
| 852 |
-
"epoch": 0.
|
| 853 |
-
"grad_norm": 0.
|
| 854 |
-
"learning_rate":
|
| 855 |
-
"loss": 0.
|
| 856 |
"step": 600
|
| 857 |
},
|
| 858 |
{
|
| 859 |
-
"epoch": 0.
|
| 860 |
-
"grad_norm": 0.
|
| 861 |
-
"learning_rate":
|
| 862 |
-
"loss": 0.
|
| 863 |
"step": 605
|
| 864 |
},
|
| 865 |
{
|
| 866 |
-
"epoch": 0.
|
| 867 |
-
"grad_norm": 0.
|
| 868 |
-
"learning_rate":
|
| 869 |
-
"loss": 0.
|
| 870 |
"step": 610
|
| 871 |
},
|
| 872 |
{
|
| 873 |
-
"epoch": 0.
|
| 874 |
-
"grad_norm": 0.
|
| 875 |
-
"learning_rate":
|
| 876 |
-
"loss": 0.
|
| 877 |
"step": 615
|
| 878 |
},
|
| 879 |
{
|
| 880 |
-
"epoch": 0.
|
| 881 |
-
"grad_norm": 0.
|
| 882 |
-
"learning_rate":
|
| 883 |
-
"loss": 0.
|
| 884 |
"step": 620
|
| 885 |
},
|
| 886 |
{
|
| 887 |
-
"epoch": 0.
|
| 888 |
-
"grad_norm": 0.
|
| 889 |
-
"learning_rate":
|
| 890 |
-
"loss": 0.
|
| 891 |
"step": 625
|
| 892 |
},
|
| 893 |
{
|
| 894 |
-
"epoch": 0.
|
| 895 |
-
"grad_norm": 0.
|
| 896 |
-
"learning_rate":
|
| 897 |
-
"loss": 0.
|
| 898 |
"step": 630
|
| 899 |
},
|
| 900 |
{
|
| 901 |
-
"epoch": 0.
|
| 902 |
-
"grad_norm": 0.
|
| 903 |
-
"learning_rate":
|
| 904 |
-
"loss": 0.
|
| 905 |
"step": 635
|
| 906 |
},
|
| 907 |
{
|
| 908 |
-
"epoch": 0.
|
| 909 |
-
"grad_norm": 0.
|
| 910 |
-
"learning_rate":
|
| 911 |
-
"loss": 0.
|
| 912 |
"step": 640
|
| 913 |
},
|
| 914 |
{
|
| 915 |
-
"epoch": 0.
|
| 916 |
-
"grad_norm": 0.
|
| 917 |
-
"learning_rate":
|
| 918 |
-
"loss": 0.
|
| 919 |
"step": 645
|
| 920 |
},
|
| 921 |
{
|
| 922 |
-
"epoch": 0.
|
| 923 |
-
"grad_norm": 0.
|
| 924 |
-
"learning_rate":
|
| 925 |
-
"loss": 0.
|
| 926 |
"step": 650
|
| 927 |
},
|
| 928 |
{
|
| 929 |
-
"epoch": 0.
|
| 930 |
-
"grad_norm": 0.
|
| 931 |
-
"learning_rate":
|
| 932 |
-
"loss": 0.
|
| 933 |
"step": 655
|
| 934 |
},
|
| 935 |
{
|
| 936 |
-
"epoch": 0.
|
| 937 |
-
"grad_norm": 0.
|
| 938 |
-
"learning_rate":
|
| 939 |
-
"loss": 0.
|
| 940 |
"step": 660
|
| 941 |
},
|
| 942 |
{
|
| 943 |
-
"epoch": 0.
|
| 944 |
-
"grad_norm": 0.
|
| 945 |
-
"learning_rate":
|
| 946 |
-
"loss": 0.
|
| 947 |
"step": 665
|
| 948 |
},
|
| 949 |
{
|
| 950 |
-
"epoch": 0.
|
| 951 |
-
"grad_norm": 0.
|
| 952 |
-
"learning_rate":
|
| 953 |
-
"loss": 0.
|
| 954 |
"step": 670
|
| 955 |
},
|
| 956 |
{
|
| 957 |
-
"epoch":
|
| 958 |
-
"grad_norm": 0.
|
| 959 |
-
"learning_rate":
|
| 960 |
-
"loss": 0.
|
| 961 |
"step": 675
|
| 962 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 963 |
{
|
| 964 |
"epoch": 1.0,
|
| 965 |
"eval_loss": NaN,
|
| 966 |
-
"eval_runtime":
|
| 967 |
-
"eval_samples_per_second": 0.
|
| 968 |
-
"eval_steps_per_second": 0.
|
| 969 |
-
"step":
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 1.0,
|
| 973 |
-
"step":
|
| 974 |
-
"total_flos":
|
| 975 |
-
"train_loss": 0.
|
| 976 |
-
"train_runtime":
|
| 977 |
-
"train_samples_per_second":
|
| 978 |
-
"train_steps_per_second": 0.
|
| 979 |
}
|
| 980 |
],
|
| 981 |
"logging_steps": 5,
|
| 982 |
-
"max_steps":
|
| 983 |
"num_input_tokens_seen": 0,
|
| 984 |
"num_train_epochs": 1,
|
| 985 |
"save_steps": 100,
|
| 986 |
-
"total_flos":
|
| 987 |
"train_batch_size": 4,
|
| 988 |
"trial_name": null,
|
| 989 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9995189995189995,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 1039,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 0.026559076829896673,
|
| 14 |
+
"learning_rate": 1.9230769230769234e-06,
|
| 15 |
+
"loss": 0.8553,
|
| 16 |
"step": 1
|
| 17 |
},
|
| 18 |
{
|
| 19 |
+
"epoch": 0.0,
|
| 20 |
+
"grad_norm": 0.024109469955629563,
|
| 21 |
+
"learning_rate": 9.615384615384616e-06,
|
| 22 |
+
"loss": 0.8949,
|
| 23 |
"step": 5
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 0.035843143099576466,
|
| 28 |
+
"learning_rate": 1.923076923076923e-05,
|
| 29 |
+
"loss": 0.8487,
|
| 30 |
"step": 10
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 0.01,
|
| 34 |
+
"grad_norm": 0.02927511973728809,
|
| 35 |
+
"learning_rate": 2.8846153846153845e-05,
|
| 36 |
+
"loss": 0.8298,
|
| 37 |
"step": 15
|
| 38 |
},
|
| 39 |
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 0.0482470347406101,
|
| 42 |
+
"learning_rate": 3.846153846153846e-05,
|
| 43 |
+
"loss": 0.8369,
|
| 44 |
"step": 20
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"grad_norm": 0.04787111054382548,
|
| 49 |
+
"learning_rate": 4.8076923076923084e-05,
|
| 50 |
+
"loss": 0.8625,
|
| 51 |
"step": 25
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"grad_norm": 0.09068040679248557,
|
| 56 |
+
"learning_rate": 5.769230769230769e-05,
|
| 57 |
+
"loss": 0.8133,
|
| 58 |
"step": 30
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 0.03,
|
| 62 |
+
"grad_norm": 0.07412802798136442,
|
| 63 |
+
"learning_rate": 6.730769230769232e-05,
|
| 64 |
+
"loss": 0.8543,
|
| 65 |
"step": 35
|
| 66 |
},
|
| 67 |
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"grad_norm": 0.0699997088327299,
|
| 70 |
+
"learning_rate": 7.692307692307693e-05,
|
| 71 |
+
"loss": 0.763,
|
| 72 |
"step": 40
|
| 73 |
},
|
| 74 |
{
|
| 75 |
+
"epoch": 0.04,
|
| 76 |
+
"grad_norm": 0.05170267487139005,
|
| 77 |
+
"learning_rate": 8.653846153846155e-05,
|
| 78 |
+
"loss": 0.7827,
|
| 79 |
"step": 45
|
| 80 |
},
|
| 81 |
{
|
| 82 |
+
"epoch": 0.05,
|
| 83 |
+
"grad_norm": 0.07357073672675946,
|
| 84 |
+
"learning_rate": 9.615384615384617e-05,
|
| 85 |
+
"loss": 0.8022,
|
| 86 |
"step": 50
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.05,
|
| 90 |
+
"grad_norm": 0.05641137867224088,
|
| 91 |
+
"learning_rate": 0.00010576923076923077,
|
| 92 |
+
"loss": 0.7397,
|
| 93 |
"step": 55
|
| 94 |
},
|
| 95 |
{
|
| 96 |
+
"epoch": 0.06,
|
| 97 |
+
"grad_norm": 0.057002882272420445,
|
| 98 |
+
"learning_rate": 0.00011538461538461538,
|
| 99 |
+
"loss": 0.777,
|
| 100 |
"step": 60
|
| 101 |
},
|
| 102 |
{
|
| 103 |
+
"epoch": 0.06,
|
| 104 |
+
"grad_norm": 0.050844397685080686,
|
| 105 |
+
"learning_rate": 0.000125,
|
| 106 |
+
"loss": 0.7664,
|
| 107 |
"step": 65
|
| 108 |
},
|
| 109 |
{
|
| 110 |
+
"epoch": 0.07,
|
| 111 |
+
"grad_norm": 0.05336016241159068,
|
| 112 |
+
"learning_rate": 0.00013461538461538464,
|
| 113 |
+
"loss": 0.7956,
|
| 114 |
"step": 70
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 0.07,
|
| 118 |
+
"grad_norm": 0.05359842093910465,
|
| 119 |
+
"learning_rate": 0.00014423076923076924,
|
| 120 |
+
"loss": 0.751,
|
| 121 |
"step": 75
|
| 122 |
},
|
| 123 |
{
|
| 124 |
+
"epoch": 0.08,
|
| 125 |
+
"grad_norm": 0.043971570409194735,
|
| 126 |
+
"learning_rate": 0.00015384615384615385,
|
| 127 |
+
"loss": 0.7823,
|
| 128 |
"step": 80
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.08,
|
| 132 |
+
"grad_norm": 0.044563802592992065,
|
| 133 |
+
"learning_rate": 0.00016346153846153846,
|
| 134 |
+
"loss": 0.7908,
|
| 135 |
"step": 85
|
| 136 |
},
|
| 137 |
{
|
| 138 |
+
"epoch": 0.09,
|
| 139 |
+
"grad_norm": 0.04801183812641932,
|
| 140 |
+
"learning_rate": 0.0001730769230769231,
|
| 141 |
+
"loss": 0.827,
|
| 142 |
"step": 90
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 0.09,
|
| 146 |
+
"grad_norm": 0.0522380719803802,
|
| 147 |
+
"learning_rate": 0.0001826923076923077,
|
| 148 |
+
"loss": 0.8225,
|
| 149 |
"step": 95
|
| 150 |
},
|
| 151 |
{
|
| 152 |
+
"epoch": 0.1,
|
| 153 |
+
"grad_norm": 0.048043288977650755,
|
| 154 |
+
"learning_rate": 0.00019230769230769233,
|
| 155 |
+
"loss": 0.7715,
|
| 156 |
"step": 100
|
| 157 |
},
|
| 158 |
{
|
| 159 |
+
"epoch": 0.1,
|
| 160 |
+
"grad_norm": 0.04594631744893944,
|
| 161 |
+
"learning_rate": 0.00019999943552317104,
|
| 162 |
+
"loss": 0.7789,
|
| 163 |
"step": 105
|
| 164 |
},
|
| 165 |
{
|
| 166 |
+
"epoch": 0.11,
|
| 167 |
+
"grad_norm": 0.050805778293244806,
|
| 168 |
+
"learning_rate": 0.00019997967950328128,
|
| 169 |
+
"loss": 0.8401,
|
| 170 |
"step": 110
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.11,
|
| 174 |
+
"grad_norm": 0.04435482092479941,
|
| 175 |
+
"learning_rate": 0.0001999317060143023,
|
| 176 |
+
"loss": 0.7773,
|
| 177 |
"step": 115
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 0.12,
|
| 181 |
+
"grad_norm": 0.05022795262704976,
|
| 182 |
+
"learning_rate": 0.0001998555285958899,
|
| 183 |
+
"loss": 0.7271,
|
| 184 |
"step": 120
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"epoch": 0.12,
|
| 188 |
+
"grad_norm": 0.05316130307831719,
|
| 189 |
+
"learning_rate": 0.00019975116874775242,
|
| 190 |
+
"loss": 0.8088,
|
| 191 |
"step": 125
|
| 192 |
},
|
| 193 |
{
|
| 194 |
+
"epoch": 0.13,
|
| 195 |
+
"grad_norm": 0.04630310630357938,
|
| 196 |
+
"learning_rate": 0.00019961865592358288,
|
| 197 |
+
"loss": 0.7752,
|
| 198 |
"step": 130
|
| 199 |
},
|
| 200 |
{
|
| 201 |
+
"epoch": 0.13,
|
| 202 |
+
"grad_norm": 0.05955477676937173,
|
| 203 |
+
"learning_rate": 0.0001994580275227462,
|
| 204 |
+
"loss": 0.7639,
|
| 205 |
"step": 135
|
| 206 |
},
|
| 207 |
{
|
| 208 |
+
"epoch": 0.13,
|
| 209 |
+
"grad_norm": 0.04911523657827075,
|
| 210 |
+
"learning_rate": 0.00019926932887972393,
|
| 211 |
+
"loss": 0.7476,
|
| 212 |
"step": 140
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 0.14,
|
| 216 |
+
"grad_norm": 0.04365854699386244,
|
| 217 |
+
"learning_rate": 0.0001990526132513194,
|
| 218 |
+
"loss": 0.7671,
|
| 219 |
"step": 145
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 0.14,
|
| 223 |
+
"grad_norm": 0.0479590041051757,
|
| 224 |
+
"learning_rate": 0.00019880794180162693,
|
| 225 |
+
"loss": 0.8015,
|
| 226 |
"step": 150
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"epoch": 0.15,
|
| 230 |
+
"grad_norm": 0.053032592897760425,
|
| 231 |
+
"learning_rate": 0.00019853538358476932,
|
| 232 |
+
"loss": 0.8114,
|
| 233 |
"step": 155
|
| 234 |
},
|
| 235 |
{
|
| 236 |
+
"epoch": 0.15,
|
| 237 |
+
"grad_norm": 0.04823282437342225,
|
| 238 |
+
"learning_rate": 0.00019823501552540865,
|
| 239 |
+
"loss": 0.7843,
|
| 240 |
"step": 160
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 0.16,
|
| 244 |
+
"grad_norm": 0.13942036529350957,
|
| 245 |
+
"learning_rate": 0.00019790692239703557,
|
| 246 |
+
"loss": 0.7066,
|
| 247 |
"step": 165
|
| 248 |
},
|
| 249 |
{
|
| 250 |
+
"epoch": 0.16,
|
| 251 |
+
"grad_norm": 0.05813669118246924,
|
| 252 |
+
"learning_rate": 0.00019755119679804367,
|
| 253 |
+
"loss": 0.7782,
|
| 254 |
"step": 170
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 0.17,
|
| 258 |
+
"grad_norm": 0.045133845682998344,
|
| 259 |
+
"learning_rate": 0.00019716793912559507,
|
| 260 |
+
"loss": 0.8228,
|
| 261 |
"step": 175
|
| 262 |
},
|
| 263 |
{
|
| 264 |
+
"epoch": 0.17,
|
| 265 |
+
"grad_norm": 0.04767176858103638,
|
| 266 |
+
"learning_rate": 0.00019675725754728527,
|
| 267 |
+
"loss": 0.8016,
|
| 268 |
"step": 180
|
| 269 |
},
|
| 270 |
{
|
| 271 |
+
"epoch": 0.18,
|
| 272 |
+
"grad_norm": 0.05800072730359953,
|
| 273 |
+
"learning_rate": 0.00019631926797061456,
|
| 274 |
+
"loss": 0.7576,
|
| 275 |
"step": 185
|
| 276 |
},
|
| 277 |
{
|
| 278 |
+
"epoch": 0.18,
|
| 279 |
+
"grad_norm": 0.044752361745923355,
|
| 280 |
+
"learning_rate": 0.00019585409401027556,
|
| 281 |
+
"loss": 0.7311,
|
| 282 |
"step": 190
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 0.19,
|
| 286 |
+
"grad_norm": 0.0436163176892526,
|
| 287 |
+
"learning_rate": 0.00019536186695326486,
|
| 288 |
+
"loss": 0.7584,
|
| 289 |
"step": 195
|
| 290 |
},
|
| 291 |
{
|
| 292 |
+
"epoch": 0.19,
|
| 293 |
+
"grad_norm": 0.07116796220713574,
|
| 294 |
+
"learning_rate": 0.00019484272572182986,
|
| 295 |
+
"loss": 0.7525,
|
| 296 |
"step": 200
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 0.2,
|
| 300 |
+
"grad_norm": 0.051057018027582515,
|
| 301 |
+
"learning_rate": 0.00019429681683426022,
|
| 302 |
+
"loss": 0.798,
|
| 303 |
"step": 205
|
| 304 |
},
|
| 305 |
{
|
| 306 |
+
"epoch": 0.2,
|
| 307 |
+
"grad_norm": 0.06621856781536847,
|
| 308 |
+
"learning_rate": 0.00019372429436353606,
|
| 309 |
+
"loss": 0.7242,
|
| 310 |
"step": 210
|
| 311 |
},
|
| 312 |
{
|
| 313 |
+
"epoch": 0.21,
|
| 314 |
+
"grad_norm": 0.05280223873501623,
|
| 315 |
+
"learning_rate": 0.0001931253198938432,
|
| 316 |
+
"loss": 0.8013,
|
| 317 |
"step": 215
|
| 318 |
},
|
| 319 |
{
|
| 320 |
+
"epoch": 0.21,
|
| 321 |
+
"grad_norm": 0.049913511617762696,
|
| 322 |
+
"learning_rate": 0.00019250006247496928,
|
| 323 |
+
"loss": 0.7282,
|
| 324 |
"step": 220
|
| 325 |
},
|
| 326 |
{
|
| 327 |
+
"epoch": 0.22,
|
| 328 |
+
"grad_norm": 0.057224419119031235,
|
| 329 |
+
"learning_rate": 0.00019184869857459232,
|
| 330 |
+
"loss": 0.7986,
|
| 331 |
"step": 225
|
| 332 |
},
|
| 333 |
{
|
| 334 |
+
"epoch": 0.22,
|
| 335 |
+
"grad_norm": 0.062107090513119266,
|
| 336 |
+
"learning_rate": 0.00019117141202847586,
|
| 337 |
+
"loss": 0.7305,
|
| 338 |
"step": 230
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 0.23,
|
| 342 |
+
"grad_norm": 0.06236876490128247,
|
| 343 |
+
"learning_rate": 0.00019046839398858474,
|
| 344 |
+
"loss": 0.7961,
|
| 345 |
"step": 235
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 0.23,
|
| 349 |
+
"grad_norm": 0.04936400763486868,
|
| 350 |
+
"learning_rate": 0.00018973984286913584,
|
| 351 |
+
"loss": 0.735,
|
| 352 |
"step": 240
|
| 353 |
},
|
| 354 |
{
|
| 355 |
+
"epoch": 0.24,
|
| 356 |
+
"grad_norm": 0.053408247386716914,
|
| 357 |
+
"learning_rate": 0.0001889859642905992,
|
| 358 |
+
"loss": 0.7857,
|
| 359 |
"step": 245
|
| 360 |
},
|
| 361 |
{
|
| 362 |
+
"epoch": 0.24,
|
| 363 |
+
"grad_norm": 0.05781811933339179,
|
| 364 |
+
"learning_rate": 0.00018820697102166526,
|
| 365 |
+
"loss": 0.7627,
|
| 366 |
"step": 250
|
| 367 |
},
|
| 368 |
{
|
| 369 |
+
"epoch": 0.25,
|
| 370 |
+
"grad_norm": 0.05674627874967702,
|
| 371 |
+
"learning_rate": 0.00018740308291919497,
|
| 372 |
+
"loss": 0.7492,
|
| 373 |
"step": 255
|
| 374 |
},
|
| 375 |
{
|
| 376 |
+
"epoch": 0.25,
|
| 377 |
+
"grad_norm": 0.05113375946042358,
|
| 378 |
+
"learning_rate": 0.0001865745268661689,
|
| 379 |
+
"loss": 0.8117,
|
| 380 |
"step": 260
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"epoch": 0.25,
|
| 384 |
+
"grad_norm": 0.06186000436202041,
|
| 385 |
+
"learning_rate": 0.00018572153670765365,
|
| 386 |
+
"loss": 0.801,
|
| 387 |
"step": 265
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 0.26,
|
| 391 |
+
"grad_norm": 0.07562426320620609,
|
| 392 |
+
"learning_rate": 0.00018484435318480332,
|
| 393 |
+
"loss": 0.8071,
|
| 394 |
"step": 270
|
| 395 |
},
|
| 396 |
{
|
| 397 |
+
"epoch": 0.26,
|
| 398 |
+
"grad_norm": 0.06311677584919179,
|
| 399 |
+
"learning_rate": 0.0001839432238669147,
|
| 400 |
+
"loss": 0.7843,
|
| 401 |
"step": 275
|
| 402 |
},
|
| 403 |
{
|
| 404 |
+
"epoch": 0.27,
|
| 405 |
+
"grad_norm": 0.06630091865014885,
|
| 406 |
+
"learning_rate": 0.00018301840308155507,
|
| 407 |
+
"loss": 0.7493,
|
| 408 |
"step": 280
|
| 409 |
},
|
| 410 |
{
|
| 411 |
+
"epoch": 0.27,
|
| 412 |
+
"grad_norm": 0.06544583135680962,
|
| 413 |
+
"learning_rate": 0.00018207015184278305,
|
| 414 |
+
"loss": 0.782,
|
| 415 |
"step": 285
|
| 416 |
},
|
| 417 |
{
|
| 418 |
+
"epoch": 0.28,
|
| 419 |
+
"grad_norm": 0.06541978841910906,
|
| 420 |
+
"learning_rate": 0.000181098737777482,
|
| 421 |
+
"loss": 0.766,
|
| 422 |
"step": 290
|
| 423 |
},
|
| 424 |
{
|
| 425 |
+
"epoch": 0.28,
|
| 426 |
+
"grad_norm": 0.05791188755333043,
|
| 427 |
+
"learning_rate": 0.00018010443504982694,
|
| 428 |
+
"loss": 0.7499,
|
| 429 |
"step": 295
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 0.29,
|
| 433 |
+
"grad_norm": 0.06550833011506903,
|
| 434 |
+
"learning_rate": 0.000179087524283907,
|
| 435 |
+
"loss": 0.8137,
|
| 436 |
"step": 300
|
| 437 |
},
|
| 438 |
{
|
| 439 |
+
"epoch": 0.29,
|
| 440 |
+
"grad_norm": 0.058622811505104906,
|
| 441 |
+
"learning_rate": 0.00017804829248452395,
|
| 442 |
+
"loss": 0.7512,
|
| 443 |
"step": 305
|
| 444 |
},
|
| 445 |
{
|
| 446 |
+
"epoch": 0.3,
|
| 447 |
+
"grad_norm": 0.0646444641030475,
|
| 448 |
+
"learning_rate": 0.00017698703295619052,
|
| 449 |
+
"loss": 0.7908,
|
| 450 |
"step": 310
|
| 451 |
},
|
| 452 |
{
|
| 453 |
+
"epoch": 0.3,
|
| 454 |
+
"grad_norm": 0.06559061358782307,
|
| 455 |
+
"learning_rate": 0.00017590404522035028,
|
| 456 |
+
"loss": 0.7308,
|
| 457 |
"step": 315
|
| 458 |
},
|
| 459 |
{
|
| 460 |
+
"epoch": 0.31,
|
| 461 |
+
"grad_norm": 0.06308845309249086,
|
| 462 |
+
"learning_rate": 0.00017479963493084329,
|
| 463 |
+
"loss": 0.7643,
|
| 464 |
"step": 320
|
| 465 |
},
|
| 466 |
{
|
| 467 |
+
"epoch": 0.31,
|
| 468 |
+
"grad_norm": 0.06406066039467145,
|
| 469 |
+
"learning_rate": 0.0001736741137876405,
|
| 470 |
+
"loss": 0.7775,
|
| 471 |
"step": 325
|
| 472 |
},
|
| 473 |
{
|
| 474 |
+
"epoch": 0.32,
|
| 475 |
+
"grad_norm": 0.06444860497739553,
|
| 476 |
+
"learning_rate": 0.00017252779944887235,
|
| 477 |
+
"loss": 0.7774,
|
| 478 |
"step": 330
|
| 479 |
},
|
| 480 |
{
|
| 481 |
+
"epoch": 0.32,
|
| 482 |
+
"grad_norm": 0.06604642339408012,
|
| 483 |
+
"learning_rate": 0.00017136101544117525,
|
| 484 |
+
"loss": 0.7362,
|
| 485 |
"step": 335
|
| 486 |
},
|
| 487 |
{
|
| 488 |
+
"epoch": 0.33,
|
| 489 |
+
"grad_norm": 0.06850287335544007,
|
| 490 |
+
"learning_rate": 0.00017017409106838207,
|
| 491 |
+
"loss": 0.7501,
|
| 492 |
"step": 340
|
| 493 |
},
|
| 494 |
{
|
| 495 |
+
"epoch": 0.33,
|
| 496 |
+
"grad_norm": 0.06459535279086648,
|
| 497 |
+
"learning_rate": 0.00016896736131858208,
|
| 498 |
+
"loss": 0.7606,
|
| 499 |
"step": 345
|
| 500 |
},
|
| 501 |
{
|
| 502 |
+
"epoch": 0.34,
|
| 503 |
+
"grad_norm": 0.06245922169687922,
|
| 504 |
+
"learning_rate": 0.0001677411667695765,
|
| 505 |
+
"loss": 0.7459,
|
| 506 |
"step": 350
|
| 507 |
},
|
| 508 |
{
|
| 509 |
+
"epoch": 0.34,
|
| 510 |
+
"grad_norm": 0.0618217626323294,
|
| 511 |
+
"learning_rate": 0.00016649585349275662,
|
| 512 |
+
"loss": 0.7608,
|
| 513 |
"step": 355
|
| 514 |
},
|
| 515 |
{
|
| 516 |
+
"epoch": 0.35,
|
| 517 |
+
"grad_norm": 0.06529458738837608,
|
| 518 |
+
"learning_rate": 0.0001652317729554313,
|
| 519 |
+
"loss": 0.7793,
|
| 520 |
"step": 360
|
| 521 |
},
|
| 522 |
{
|
| 523 |
+
"epoch": 0.35,
|
| 524 |
+
"grad_norm": 0.07281345190056655,
|
| 525 |
+
"learning_rate": 0.0001639492819216316,
|
| 526 |
+
"loss": 0.7769,
|
| 527 |
"step": 365
|
| 528 |
},
|
| 529 |
{
|
| 530 |
+
"epoch": 0.36,
|
| 531 |
+
"grad_norm": 0.07253822403948054,
|
| 532 |
+
"learning_rate": 0.0001626487423514207,
|
| 533 |
+
"loss": 0.7699,
|
| 534 |
"step": 370
|
| 535 |
},
|
| 536 |
{
|
| 537 |
+
"epoch": 0.36,
|
| 538 |
+
"grad_norm": 0.059915171172645505,
|
| 539 |
+
"learning_rate": 0.00016133052129873693,
|
| 540 |
+
"loss": 0.7426,
|
| 541 |
"step": 375
|
| 542 |
},
|
| 543 |
{
|
| 544 |
+
"epoch": 0.37,
|
| 545 |
+
"grad_norm": 0.06063815927279327,
|
| 546 |
+
"learning_rate": 0.0001599949908077996,
|
| 547 |
+
"loss": 0.7859,
|
| 548 |
"step": 380
|
| 549 |
},
|
| 550 |
{
|
| 551 |
+
"epoch": 0.37,
|
| 552 |
+
"grad_norm": 0.07982151033712452,
|
| 553 |
+
"learning_rate": 0.00015864252780810616,
|
| 554 |
+
"loss": 0.7484,
|
| 555 |
"step": 385
|
| 556 |
},
|
| 557 |
{
|
| 558 |
+
"epoch": 0.38,
|
| 559 |
+
"grad_norm": 0.07807371830206032,
|
| 560 |
+
"learning_rate": 0.00015727351400805052,
|
| 561 |
+
"loss": 0.7318,
|
| 562 |
"step": 390
|
| 563 |
},
|
| 564 |
{
|
| 565 |
+
"epoch": 0.38,
|
| 566 |
+
"grad_norm": 0.06359423217230728,
|
| 567 |
+
"learning_rate": 0.0001558883357871928,
|
| 568 |
+
"loss": 0.7707,
|
| 569 |
"step": 395
|
| 570 |
},
|
| 571 |
{
|
| 572 |
+
"epoch": 0.38,
|
| 573 |
+
"grad_norm": 0.09384048396706658,
|
| 574 |
+
"learning_rate": 0.00015448738408721052,
|
| 575 |
+
"loss": 0.7869,
|
| 576 |
"step": 400
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"epoch": 0.39,
|
| 580 |
+
"grad_norm": 0.07059181179022768,
|
| 581 |
+
"learning_rate": 0.00015307105430156255,
|
| 582 |
+
"loss": 0.7139,
|
| 583 |
"step": 405
|
| 584 |
},
|
| 585 |
{
|
| 586 |
+
"epoch": 0.39,
|
| 587 |
+
"grad_norm": 0.07407320984033573,
|
| 588 |
+
"learning_rate": 0.0001516397461638962,
|
| 589 |
+
"loss": 0.7476,
|
| 590 |
"step": 410
|
| 591 |
},
|
| 592 |
{
|
| 593 |
+
"epoch": 0.4,
|
| 594 |
+
"grad_norm": 0.07240911601504253,
|
| 595 |
+
"learning_rate": 0.0001501938636352297,
|
| 596 |
+
"loss": 0.7655,
|
| 597 |
"step": 415
|
| 598 |
},
|
| 599 |
{
|
| 600 |
+
"epoch": 0.4,
|
| 601 |
+
"grad_norm": 0.07068099666527985,
|
| 602 |
+
"learning_rate": 0.00014873381478994134,
|
| 603 |
+
"loss": 0.7893,
|
| 604 |
"step": 420
|
| 605 |
},
|
| 606 |
{
|
| 607 |
+
"epoch": 0.41,
|
| 608 |
+
"grad_norm": 0.08305359605908401,
|
| 609 |
+
"learning_rate": 0.00014726001170059792,
|
| 610 |
+
"loss": 0.7111,
|
| 611 |
"step": 425
|
| 612 |
},
|
| 613 |
{
|
| 614 |
+
"epoch": 0.41,
|
| 615 |
+
"grad_norm": 0.0670085750282625,
|
| 616 |
+
"learning_rate": 0.00014577287032165468,
|
| 617 |
+
"loss": 0.7527,
|
| 618 |
"step": 430
|
| 619 |
},
|
| 620 |
{
|
| 621 |
+
"epoch": 0.42,
|
| 622 |
+
"grad_norm": 0.06789518226534799,
|
| 623 |
+
"learning_rate": 0.00014427281037205945,
|
| 624 |
+
"loss": 0.7751,
|
| 625 |
"step": 435
|
| 626 |
},
|
| 627 |
{
|
| 628 |
+
"epoch": 0.42,
|
| 629 |
+
"grad_norm": 0.09136108168814464,
|
| 630 |
+
"learning_rate": 0.00014276025521679471,
|
| 631 |
+
"loss": 0.726,
|
| 632 |
"step": 440
|
| 633 |
},
|
| 634 |
{
|
| 635 |
+
"epoch": 0.43,
|
| 636 |
+
"grad_norm": 0.06956344474331025,
|
| 637 |
+
"learning_rate": 0.00014123563174739037,
|
| 638 |
+
"loss": 0.8187,
|
| 639 |
"step": 445
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 0.43,
|
| 643 |
+
"grad_norm": 0.07271098739476833,
|
| 644 |
+
"learning_rate": 0.00013969937026144118,
|
| 645 |
+
"loss": 0.7787,
|
| 646 |
"step": 450
|
| 647 |
},
|
| 648 |
{
|
| 649 |
+
"epoch": 0.44,
|
| 650 |
+
"grad_norm": 0.06984149301611005,
|
| 651 |
+
"learning_rate": 0.00013815190434116317,
|
| 652 |
+
"loss": 0.7873,
|
| 653 |
"step": 455
|
| 654 |
},
|
| 655 |
{
|
| 656 |
+
"epoch": 0.44,
|
| 657 |
+
"grad_norm": 0.07335035453389814,
|
| 658 |
+
"learning_rate": 0.00013659367073102268,
|
| 659 |
+
"loss": 0.7609,
|
| 660 |
"step": 460
|
| 661 |
},
|
| 662 |
{
|
| 663 |
+
"epoch": 0.45,
|
| 664 |
+
"grad_norm": 0.0744105188121296,
|
| 665 |
+
"learning_rate": 0.00013502510921447323,
|
| 666 |
+
"loss": 0.7169,
|
| 667 |
"step": 465
|
| 668 |
},
|
| 669 |
{
|
| 670 |
+
"epoch": 0.45,
|
| 671 |
+
"grad_norm": 0.06947572989302908,
|
| 672 |
+
"learning_rate": 0.00013344666248983432,
|
| 673 |
+
"loss": 0.7837,
|
| 674 |
"step": 470
|
| 675 |
},
|
| 676 |
{
|
| 677 |
+
"epoch": 0.46,
|
| 678 |
+
"grad_norm": 0.07999096873197906,
|
| 679 |
+
"learning_rate": 0.000131858776045348,
|
| 680 |
+
"loss": 0.7727,
|
| 681 |
"step": 475
|
| 682 |
},
|
| 683 |
{
|
| 684 |
+
"epoch": 0.46,
|
| 685 |
+
"grad_norm": 0.07774452098436961,
|
| 686 |
+
"learning_rate": 0.00013026189803344774,
|
| 687 |
+
"loss": 0.8242,
|
| 688 |
"step": 480
|
| 689 |
},
|
| 690 |
{
|
| 691 |
+
"epoch": 0.47,
|
| 692 |
+
"grad_norm": 0.07801636818427328,
|
| 693 |
+
"learning_rate": 0.00012865647914427544,
|
| 694 |
+
"loss": 0.7269,
|
| 695 |
"step": 485
|
| 696 |
},
|
| 697 |
{
|
| 698 |
+
"epoch": 0.47,
|
| 699 |
+
"grad_norm": 0.11086472292549841,
|
| 700 |
+
"learning_rate": 0.00012704297247848216,
|
| 701 |
+
"loss": 0.7503,
|
| 702 |
"step": 490
|
| 703 |
},
|
| 704 |
{
|
| 705 |
+
"epoch": 0.48,
|
| 706 |
+
"grad_norm": 0.0724703886664607,
|
| 707 |
+
"learning_rate": 0.00012542183341934872,
|
| 708 |
+
"loss": 0.81,
|
| 709 |
"step": 495
|
| 710 |
},
|
| 711 |
{
|
| 712 |
+
"epoch": 0.48,
|
| 713 |
+
"grad_norm": 0.08424198871373768,
|
| 714 |
+
"learning_rate": 0.00012379351950426187,
|
| 715 |
+
"loss": 0.7102,
|
| 716 |
"step": 500
|
| 717 |
},
|
| 718 |
{
|
| 719 |
+
"epoch": 0.49,
|
| 720 |
+
"grad_norm": 0.07399506224237913,
|
| 721 |
+
"learning_rate": 0.0001221584902955827,
|
| 722 |
+
"loss": 0.811,
|
| 723 |
"step": 505
|
| 724 |
},
|
| 725 |
{
|
| 726 |
+
"epoch": 0.49,
|
| 727 |
+
"grad_norm": 0.07513530266538687,
|
| 728 |
+
"learning_rate": 0.00012051720725094324,
|
| 729 |
+
"loss": 0.7328,
|
| 730 |
"step": 510
|
| 731 |
},
|
| 732 |
{
|
| 733 |
+
"epoch": 0.5,
|
| 734 |
+
"grad_norm": 0.08300665590930759,
|
| 735 |
+
"learning_rate": 0.00011887013359300837,
|
| 736 |
+
"loss": 0.7728,
|
| 737 |
"step": 515
|
| 738 |
},
|
| 739 |
{
|
| 740 |
+
"epoch": 0.5,
|
| 741 |
+
"grad_norm": 0.08603160091015216,
|
| 742 |
+
"learning_rate": 0.00011721773417873965,
|
| 743 |
+
"loss": 0.8092,
|
| 744 |
"step": 520
|
| 745 |
},
|
| 746 |
{
|
| 747 |
+
"epoch": 0.51,
|
| 748 |
+
"grad_norm": 0.06828684892985817,
|
| 749 |
+
"learning_rate": 0.00011556047536819777,
|
| 750 |
+
"loss": 0.7905,
|
| 751 |
"step": 525
|
| 752 |
},
|
| 753 |
{
|
| 754 |
+
"epoch": 0.51,
|
| 755 |
+
"grad_norm": 0.0888375409363043,
|
| 756 |
+
"learning_rate": 0.00011389882489292061,
|
| 757 |
+
"loss": 0.7616,
|
| 758 |
"step": 530
|
| 759 |
},
|
| 760 |
{
|
| 761 |
+
"epoch": 0.51,
|
| 762 |
+
"grad_norm": 0.07153992771335722,
|
| 763 |
+
"learning_rate": 0.0001122332517239147,
|
| 764 |
+
"loss": 0.7231,
|
| 765 |
"step": 535
|
| 766 |
},
|
| 767 |
{
|
| 768 |
+
"epoch": 0.52,
|
| 769 |
+
"grad_norm": 0.07078385208785225,
|
| 770 |
+
"learning_rate": 0.00011056422593929635,
|
| 771 |
+
"loss": 0.7744,
|
| 772 |
"step": 540
|
| 773 |
},
|
| 774 |
{
|
| 775 |
+
"epoch": 0.52,
|
| 776 |
+
"grad_norm": 0.06724179763601197,
|
| 777 |
+
"learning_rate": 0.00010889221859162062,
|
| 778 |
+
"loss": 0.7385,
|
| 779 |
"step": 545
|
| 780 |
},
|
| 781 |
{
|
| 782 |
+
"epoch": 0.53,
|
| 783 |
+
"grad_norm": 0.08127731002438206,
|
| 784 |
+
"learning_rate": 0.00010721770157493527,
|
| 785 |
+
"loss": 0.737,
|
| 786 |
"step": 550
|
| 787 |
},
|
| 788 |
{
|
| 789 |
+
"epoch": 0.53,
|
| 790 |
+
"grad_norm": 0.07971841929977522,
|
| 791 |
+
"learning_rate": 0.000105541147491597,
|
| 792 |
+
"loss": 0.7129,
|
| 793 |
"step": 555
|
| 794 |
},
|
| 795 |
{
|
| 796 |
+
"epoch": 0.54,
|
| 797 |
+
"grad_norm": 0.09905140750790473,
|
| 798 |
+
"learning_rate": 0.00010386302951888804,
|
| 799 |
+
"loss": 0.7682,
|
| 800 |
"step": 560
|
| 801 |
},
|
| 802 |
{
|
| 803 |
+
"epoch": 0.54,
|
| 804 |
+
"grad_norm": 0.07787324370915785,
|
| 805 |
+
"learning_rate": 0.00010218382127547022,
|
| 806 |
+
"loss": 0.7988,
|
| 807 |
"step": 565
|
| 808 |
},
|
| 809 |
{
|
| 810 |
+
"epoch": 0.55,
|
| 811 |
+
"grad_norm": 0.06979898484314451,
|
| 812 |
+
"learning_rate": 0.00010050399668771479,
|
| 813 |
+
"loss": 0.7505,
|
| 814 |
"step": 570
|
| 815 |
},
|
| 816 |
{
|
| 817 |
+
"epoch": 0.55,
|
| 818 |
+
"grad_norm": 0.08294483662862129,
|
| 819 |
+
"learning_rate": 9.882402985594515e-05,
|
| 820 |
+
"loss": 0.7254,
|
| 821 |
"step": 575
|
| 822 |
},
|
| 823 |
{
|
| 824 |
+
"epoch": 0.56,
|
| 825 |
+
"grad_norm": 0.09404505448514887,
|
| 826 |
+
"learning_rate": 9.71443949206304e-05,
|
| 827 |
+
"loss": 0.7744,
|
| 828 |
"step": 580
|
| 829 |
},
|
| 830 |
{
|
| 831 |
+
"epoch": 0.56,
|
| 832 |
+
"grad_norm": 0.08296480696219607,
|
| 833 |
+
"learning_rate": 9.546556592856789e-05,
|
| 834 |
+
"loss": 0.7255,
|
| 835 |
"step": 585
|
| 836 |
},
|
| 837 |
{
|
| 838 |
+
"epoch": 0.57,
|
| 839 |
+
"grad_norm": 0.08380203772972816,
|
| 840 |
+
"learning_rate": 9.378801669909197e-05,
|
| 841 |
+
"loss": 0.6704,
|
| 842 |
"step": 590
|
| 843 |
},
|
| 844 |
{
|
| 845 |
+
"epoch": 0.57,
|
| 846 |
+
"grad_norm": 0.09814150545542286,
|
| 847 |
+
"learning_rate": 9.211222069034695e-05,
|
| 848 |
+
"loss": 0.7107,
|
| 849 |
"step": 595
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 0.58,
|
| 853 |
+
"grad_norm": 0.0951778654867295,
|
| 854 |
+
"learning_rate": 9.043865086566214e-05,
|
| 855 |
+
"loss": 0.7158,
|
| 856 |
"step": 600
|
| 857 |
},
|
| 858 |
{
|
| 859 |
+
"epoch": 0.58,
|
| 860 |
+
"grad_norm": 0.08511949253631121,
|
| 861 |
+
"learning_rate": 8.87677795600663e-05,
|
| 862 |
+
"loss": 0.7572,
|
| 863 |
"step": 605
|
| 864 |
},
|
| 865 |
{
|
| 866 |
+
"epoch": 0.59,
|
| 867 |
+
"grad_norm": 0.1143213911299264,
|
| 868 |
+
"learning_rate": 8.710007834697969e-05,
|
| 869 |
+
"loss": 0.7785,
|
| 870 |
"step": 610
|
| 871 |
},
|
| 872 |
{
|
| 873 |
+
"epoch": 0.59,
|
| 874 |
+
"grad_norm": 0.08008142575287244,
|
| 875 |
+
"learning_rate": 8.543601790512083e-05,
|
| 876 |
+
"loss": 0.7327,
|
| 877 |
"step": 615
|
| 878 |
},
|
| 879 |
{
|
| 880 |
+
"epoch": 0.6,
|
| 881 |
+
"grad_norm": 0.09526058947958355,
|
| 882 |
+
"learning_rate": 8.377606788566597e-05,
|
| 883 |
+
"loss": 0.703,
|
| 884 |
"step": 620
|
| 885 |
},
|
| 886 |
{
|
| 887 |
+
"epoch": 0.6,
|
| 888 |
+
"grad_norm": 0.08273005979279956,
|
| 889 |
+
"learning_rate": 8.212069677969851e-05,
|
| 890 |
+
"loss": 0.7497,
|
| 891 |
"step": 625
|
| 892 |
},
|
| 893 |
{
|
| 894 |
+
"epoch": 0.61,
|
| 895 |
+
"grad_norm": 0.08864939979402765,
|
| 896 |
+
"learning_rate": 8.047037178598567e-05,
|
| 897 |
+
"loss": 0.7573,
|
| 898 |
"step": 630
|
| 899 |
},
|
| 900 |
{
|
| 901 |
+
"epoch": 0.61,
|
| 902 |
+
"grad_norm": 0.08394557070047488,
|
| 903 |
+
"learning_rate": 7.882555867912017e-05,
|
| 904 |
+
"loss": 0.7827,
|
| 905 |
"step": 635
|
| 906 |
},
|
| 907 |
{
|
| 908 |
+
"epoch": 0.62,
|
| 909 |
+
"grad_norm": 0.09978852942456092,
|
| 910 |
+
"learning_rate": 7.718672167806354e-05,
|
| 911 |
+
"loss": 0.7201,
|
| 912 |
"step": 640
|
| 913 |
},
|
| 914 |
{
|
| 915 |
+
"epoch": 0.62,
|
| 916 |
+
"grad_norm": 0.07987549874350373,
|
| 917 |
+
"learning_rate": 7.55543233151289e-05,
|
| 918 |
+
"loss": 0.7129,
|
| 919 |
"step": 645
|
| 920 |
},
|
| 921 |
{
|
| 922 |
+
"epoch": 0.63,
|
| 923 |
+
"grad_norm": 0.09662339979538469,
|
| 924 |
+
"learning_rate": 7.392882430543928e-05,
|
| 925 |
+
"loss": 0.7593,
|
| 926 |
"step": 650
|
| 927 |
},
|
| 928 |
{
|
| 929 |
+
"epoch": 0.63,
|
| 930 |
+
"grad_norm": 0.0966150953702372,
|
| 931 |
+
"learning_rate": 7.231068341689923e-05,
|
| 932 |
+
"loss": 0.6704,
|
| 933 |
"step": 655
|
| 934 |
},
|
| 935 |
{
|
| 936 |
+
"epoch": 0.63,
|
| 937 |
+
"grad_norm": 0.08961534426031717,
|
| 938 |
+
"learning_rate": 7.070035734071574e-05,
|
| 939 |
+
"loss": 0.781,
|
| 940 |
"step": 660
|
| 941 |
},
|
| 942 |
{
|
| 943 |
+
"epoch": 0.64,
|
| 944 |
+
"grad_norm": 0.09684345543910731,
|
| 945 |
+
"learning_rate": 6.909830056250527e-05,
|
| 946 |
+
"loss": 0.7787,
|
| 947 |
"step": 665
|
| 948 |
},
|
| 949 |
{
|
| 950 |
+
"epoch": 0.64,
|
| 951 |
+
"grad_norm": 0.10518057650982461,
|
| 952 |
+
"learning_rate": 6.750496523402352e-05,
|
| 953 |
+
"loss": 0.7658,
|
| 954 |
"step": 670
|
| 955 |
},
|
| 956 |
{
|
| 957 |
+
"epoch": 0.65,
|
| 958 |
+
"grad_norm": 0.08726496496105966,
|
| 959 |
+
"learning_rate": 6.592080104555357e-05,
|
| 960 |
+
"loss": 0.7515,
|
| 961 |
"step": 675
|
| 962 |
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.65,
|
| 965 |
+
"grad_norm": 0.0933748204446253,
|
| 966 |
+
"learning_rate": 6.434625509898897e-05,
|
| 967 |
+
"loss": 0.7474,
|
| 968 |
+
"step": 680
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.66,
|
| 972 |
+
"grad_norm": 0.09987049741300834,
|
| 973 |
+
"learning_rate": 6.278177178164721e-05,
|
| 974 |
+
"loss": 0.7458,
|
| 975 |
+
"step": 685
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.66,
|
| 979 |
+
"grad_norm": 0.10265280285088377,
|
| 980 |
+
"learning_rate": 6.122779264084932e-05,
|
| 981 |
+
"loss": 0.7194,
|
| 982 |
+
"step": 690
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.67,
|
| 986 |
+
"grad_norm": 0.09519605624873385,
|
| 987 |
+
"learning_rate": 5.968475625930124e-05,
|
| 988 |
+
"loss": 0.7788,
|
| 989 |
+
"step": 695
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.67,
|
| 993 |
+
"grad_norm": 0.10432725726790697,
|
| 994 |
+
"learning_rate": 5.815309813131153e-05,
|
| 995 |
+
"loss": 0.6987,
|
| 996 |
+
"step": 700
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.68,
|
| 1000 |
+
"grad_norm": 0.0895838664526722,
|
| 1001 |
+
"learning_rate": 5.663325053988112e-05,
|
| 1002 |
+
"loss": 0.7438,
|
| 1003 |
+
"step": 705
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.68,
|
| 1007 |
+
"grad_norm": 0.1020683075125265,
|
| 1008 |
+
"learning_rate": 5.5125642434699044e-05,
|
| 1009 |
+
"loss": 0.7329,
|
| 1010 |
+
"step": 710
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.69,
|
| 1014 |
+
"grad_norm": 0.1254242358800245,
|
| 1015 |
+
"learning_rate": 5.363069931107902e-05,
|
| 1016 |
+
"loss": 0.7701,
|
| 1017 |
+
"step": 715
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.69,
|
| 1021 |
+
"grad_norm": 0.09171973242978361,
|
| 1022 |
+
"learning_rate": 5.214884308987136e-05,
|
| 1023 |
+
"loss": 0.7614,
|
| 1024 |
+
"step": 720
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.7,
|
| 1028 |
+
"grad_norm": 0.0973938129022939,
|
| 1029 |
+
"learning_rate": 5.068049199838307e-05,
|
| 1030 |
+
"loss": 0.7654,
|
| 1031 |
+
"step": 725
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.7,
|
| 1035 |
+
"grad_norm": 0.10651861956923717,
|
| 1036 |
+
"learning_rate": 4.9226060452340825e-05,
|
| 1037 |
+
"loss": 0.7459,
|
| 1038 |
+
"step": 730
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.71,
|
| 1042 |
+
"grad_norm": 0.10089952208386434,
|
| 1043 |
+
"learning_rate": 4.7785958938929644e-05,
|
| 1044 |
+
"loss": 0.7259,
|
| 1045 |
+
"step": 735
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.71,
|
| 1049 |
+
"grad_norm": 0.1210514333134373,
|
| 1050 |
+
"learning_rate": 4.6360593900940074e-05,
|
| 1051 |
+
"loss": 0.7434,
|
| 1052 |
+
"step": 740
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.72,
|
| 1056 |
+
"grad_norm": 0.09318485524858554,
|
| 1057 |
+
"learning_rate": 4.4950367622057173e-05,
|
| 1058 |
+
"loss": 0.7452,
|
| 1059 |
+
"step": 745
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.72,
|
| 1063 |
+
"grad_norm": 0.0982653281602369,
|
| 1064 |
+
"learning_rate": 4.355567811332311e-05,
|
| 1065 |
+
"loss": 0.7647,
|
| 1066 |
+
"step": 750
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.73,
|
| 1070 |
+
"grad_norm": 0.10433832624807006,
|
| 1071 |
+
"learning_rate": 4.21769190008056e-05,
|
| 1072 |
+
"loss": 0.7786,
|
| 1073 |
+
"step": 755
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.73,
|
| 1077 |
+
"grad_norm": 0.10945535727159489,
|
| 1078 |
+
"learning_rate": 4.081447941450428e-05,
|
| 1079 |
+
"loss": 0.7534,
|
| 1080 |
+
"step": 760
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.74,
|
| 1084 |
+
"grad_norm": 0.08979908942148239,
|
| 1085 |
+
"learning_rate": 3.946874387852545e-05,
|
| 1086 |
+
"loss": 0.7684,
|
| 1087 |
+
"step": 765
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.74,
|
| 1091 |
+
"grad_norm": 0.10406027811162083,
|
| 1092 |
+
"learning_rate": 3.8140092202557185e-05,
|
| 1093 |
+
"loss": 0.722,
|
| 1094 |
+
"step": 770
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.75,
|
| 1098 |
+
"grad_norm": 0.1035268479061034,
|
| 1099 |
+
"learning_rate": 3.682889937467493e-05,
|
| 1100 |
+
"loss": 0.7553,
|
| 1101 |
+
"step": 775
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.75,
|
| 1105 |
+
"grad_norm": 0.10887919806436043,
|
| 1106 |
+
"learning_rate": 3.553553545550768e-05,
|
| 1107 |
+
"loss": 0.7246,
|
| 1108 |
+
"step": 780
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.76,
|
| 1112 |
+
"grad_norm": 0.09604076773803726,
|
| 1113 |
+
"learning_rate": 3.426036547379528e-05,
|
| 1114 |
+
"loss": 0.7608,
|
| 1115 |
+
"step": 785
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.76,
|
| 1119 |
+
"grad_norm": 0.10956385216460547,
|
| 1120 |
+
"learning_rate": 3.300374932336533e-05,
|
| 1121 |
+
"loss": 0.7338,
|
| 1122 |
+
"step": 790
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.76,
|
| 1126 |
+
"grad_norm": 0.10172528555623694,
|
| 1127 |
+
"learning_rate": 3.176604166155976e-05,
|
| 1128 |
+
"loss": 0.7495,
|
| 1129 |
+
"step": 795
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.77,
|
| 1133 |
+
"grad_norm": 0.10744826094269415,
|
| 1134 |
+
"learning_rate": 3.054759180913921e-05,
|
| 1135 |
+
"loss": 0.8015,
|
| 1136 |
+
"step": 800
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.77,
|
| 1140 |
+
"grad_norm": 0.09531428953628962,
|
| 1141 |
+
"learning_rate": 2.9348743651693357e-05,
|
| 1142 |
+
"loss": 0.7432,
|
| 1143 |
+
"step": 805
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.78,
|
| 1147 |
+
"grad_norm": 0.09578814140538712,
|
| 1148 |
+
"learning_rate": 2.8169835542585587e-05,
|
| 1149 |
+
"loss": 0.6876,
|
| 1150 |
+
"step": 810
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.78,
|
| 1154 |
+
"grad_norm": 0.10906430952489729,
|
| 1155 |
+
"learning_rate": 2.7011200207458677e-05,
|
| 1156 |
+
"loss": 0.7461,
|
| 1157 |
+
"step": 815
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.79,
|
| 1161 |
+
"grad_norm": 0.09924057812689555,
|
| 1162 |
+
"learning_rate": 2.5873164650328996e-05,
|
| 1163 |
+
"loss": 0.7403,
|
| 1164 |
+
"step": 820
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.79,
|
| 1168 |
+
"grad_norm": 0.102534066373728,
|
| 1169 |
+
"learning_rate": 2.4756050061295534e-05,
|
| 1170 |
+
"loss": 0.7771,
|
| 1171 |
+
"step": 825
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.8,
|
| 1175 |
+
"grad_norm": 0.11379854278214475,
|
| 1176 |
+
"learning_rate": 2.36601717258897e-05,
|
| 1177 |
+
"loss": 0.7494,
|
| 1178 |
+
"step": 830
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.8,
|
| 1182 |
+
"grad_norm": 0.09555943569834097,
|
| 1183 |
+
"learning_rate": 2.2585838936091754e-05,
|
| 1184 |
+
"loss": 0.7062,
|
| 1185 |
+
"step": 835
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.81,
|
| 1189 |
+
"grad_norm": 0.08701341120074446,
|
| 1190 |
+
"learning_rate": 2.153335490303856e-05,
|
| 1191 |
+
"loss": 0.7029,
|
| 1192 |
+
"step": 840
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.81,
|
| 1196 |
+
"grad_norm": 0.10955955931583401,
|
| 1197 |
+
"learning_rate": 2.0503016671447785e-05,
|
| 1198 |
+
"loss": 0.7119,
|
| 1199 |
+
"step": 845
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.82,
|
| 1203 |
+
"grad_norm": 0.09961678142736638,
|
| 1204 |
+
"learning_rate": 1.9495115035782307e-05,
|
| 1205 |
+
"loss": 0.7181,
|
| 1206 |
+
"step": 850
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.82,
|
| 1210 |
+
"grad_norm": 0.10875433120436596,
|
| 1211 |
+
"learning_rate": 1.8509934458178712e-05,
|
| 1212 |
+
"loss": 0.7221,
|
| 1213 |
+
"step": 855
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.83,
|
| 1217 |
+
"grad_norm": 0.10419310033343766,
|
| 1218 |
+
"learning_rate": 1.754775298816307e-05,
|
| 1219 |
+
"loss": 0.7627,
|
| 1220 |
+
"step": 860
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.83,
|
| 1224 |
+
"grad_norm": 0.11125643674385945,
|
| 1225 |
+
"learning_rate": 1.6608842184176243e-05,
|
| 1226 |
+
"loss": 0.783,
|
| 1227 |
+
"step": 865
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.84,
|
| 1231 |
+
"grad_norm": 0.09805407303806633,
|
| 1232 |
+
"learning_rate": 1.5693467036931576e-05,
|
| 1233 |
+
"loss": 0.7754,
|
| 1234 |
+
"step": 870
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.84,
|
| 1238 |
+
"grad_norm": 0.09382093887295272,
|
| 1239 |
+
"learning_rate": 1.48018858946259e-05,
|
| 1240 |
+
"loss": 0.7306,
|
| 1241 |
+
"step": 875
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.85,
|
| 1245 |
+
"grad_norm": 0.08828049016039903,
|
| 1246 |
+
"learning_rate": 1.3934350390025463e-05,
|
| 1247 |
+
"loss": 0.7277,
|
| 1248 |
+
"step": 880
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.85,
|
| 1252 |
+
"grad_norm": 0.10111049793555948,
|
| 1253 |
+
"learning_rate": 1.3091105369447165e-05,
|
| 1254 |
+
"loss": 0.7433,
|
| 1255 |
+
"step": 885
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.86,
|
| 1259 |
+
"grad_norm": 0.09959284476126003,
|
| 1260 |
+
"learning_rate": 1.22723888236549e-05,
|
| 1261 |
+
"loss": 0.7608,
|
| 1262 |
+
"step": 890
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.86,
|
| 1266 |
+
"grad_norm": 0.12000298215227106,
|
| 1267 |
+
"learning_rate": 1.1478431820691083e-05,
|
| 1268 |
+
"loss": 0.7249,
|
| 1269 |
+
"step": 895
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.87,
|
| 1273 |
+
"grad_norm": 0.09846825711770221,
|
| 1274 |
+
"learning_rate": 1.0709458440661801e-05,
|
| 1275 |
+
"loss": 0.7474,
|
| 1276 |
+
"step": 900
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.87,
|
| 1280 |
+
"grad_norm": 0.08826572755281627,
|
| 1281 |
+
"learning_rate": 9.965685712494199e-06,
|
| 1282 |
+
"loss": 0.7125,
|
| 1283 |
+
"step": 905
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.88,
|
| 1287 |
+
"grad_norm": 0.12402329261776916,
|
| 1288 |
+
"learning_rate": 9.247323552684051e-06,
|
| 1289 |
+
"loss": 0.7685,
|
| 1290 |
+
"step": 910
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.88,
|
| 1294 |
+
"grad_norm": 0.10462400264867344,
|
| 1295 |
+
"learning_rate": 8.554574706050488e-06,
|
| 1296 |
+
"loss": 0.7884,
|
| 1297 |
+
"step": 915
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.89,
|
| 1301 |
+
"grad_norm": 0.11275389812311376,
|
| 1302 |
+
"learning_rate": 7.887634688515e-06,
|
| 1303 |
+
"loss": 0.7487,
|
| 1304 |
+
"step": 920
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.89,
|
| 1308 |
+
"grad_norm": 0.11871268386808256,
|
| 1309 |
+
"learning_rate": 7.246691731920485e-06,
|
| 1310 |
+
"loss": 0.7607,
|
| 1311 |
+
"step": 925
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.89,
|
| 1315 |
+
"grad_norm": 0.12345475324952107,
|
| 1316 |
+
"learning_rate": 6.631926730906324e-06,
|
| 1317 |
+
"loss": 0.7716,
|
| 1318 |
+
"step": 930
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.9,
|
| 1322 |
+
"grad_norm": 0.10653833929745236,
|
| 1323 |
+
"learning_rate": 6.043513191853978e-06,
|
| 1324 |
+
"loss": 0.7465,
|
| 1325 |
+
"step": 935
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.9,
|
| 1329 |
+
"grad_norm": 0.09013425987778603,
|
| 1330 |
+
"learning_rate": 5.481617183918053e-06,
|
| 1331 |
+
"loss": 0.7543,
|
| 1332 |
+
"step": 940
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.91,
|
| 1336 |
+
"grad_norm": 0.09465293194517142,
|
| 1337 |
+
"learning_rate": 4.946397292156158e-06,
|
| 1338 |
+
"loss": 0.736,
|
| 1339 |
+
"step": 945
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.91,
|
| 1343 |
+
"grad_norm": 0.10787353868301028,
|
| 1344 |
+
"learning_rate": 4.438004572771182e-06,
|
| 1345 |
+
"loss": 0.7284,
|
| 1346 |
+
"step": 950
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.92,
|
| 1350 |
+
"grad_norm": 0.1429868308987827,
|
| 1351 |
+
"learning_rate": 3.9565825104783685e-06,
|
| 1352 |
+
"loss": 0.7907,
|
| 1353 |
+
"step": 955
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.92,
|
| 1357 |
+
"grad_norm": 0.10249198050493027,
|
| 1358 |
+
"learning_rate": 3.5022669780093497e-06,
|
| 1359 |
+
"loss": 0.7203,
|
| 1360 |
+
"step": 960
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.93,
|
| 1364 |
+
"grad_norm": 0.1028361192764587,
|
| 1365 |
+
"learning_rate": 3.0751861977645125e-06,
|
| 1366 |
+
"loss": 0.7284,
|
| 1367 |
+
"step": 965
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.93,
|
| 1371 |
+
"grad_norm": 0.1278500182671187,
|
| 1372 |
+
"learning_rate": 2.6754607056244883e-06,
|
| 1373 |
+
"loss": 0.7447,
|
| 1374 |
+
"step": 970
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.94,
|
| 1378 |
+
"grad_norm": 0.09199143538365835,
|
| 1379 |
+
"learning_rate": 2.303203316931102e-06,
|
| 1380 |
+
"loss": 0.7173,
|
| 1381 |
+
"step": 975
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.94,
|
| 1385 |
+
"grad_norm": 0.10797760289216082,
|
| 1386 |
+
"learning_rate": 1.9585190946472488e-06,
|
| 1387 |
+
"loss": 0.7163,
|
| 1388 |
+
"step": 980
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.95,
|
| 1392 |
+
"grad_norm": 0.09281102451549036,
|
| 1393 |
+
"learning_rate": 1.6415053197047725e-06,
|
| 1394 |
+
"loss": 0.7284,
|
| 1395 |
+
"step": 985
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.95,
|
| 1399 |
+
"grad_norm": 0.11431066643386725,
|
| 1400 |
+
"learning_rate": 1.3522514635486816e-06,
|
| 1401 |
+
"loss": 0.7723,
|
| 1402 |
+
"step": 990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.96,
|
| 1406 |
+
"grad_norm": 0.09277614207193054,
|
| 1407 |
+
"learning_rate": 1.0908391628854041e-06,
|
| 1408 |
+
"loss": 0.7623,
|
| 1409 |
+
"step": 995
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.96,
|
| 1413 |
+
"grad_norm": 0.0970512860952287,
|
| 1414 |
+
"learning_rate": 8.57342196642319e-07,
|
| 1415 |
+
"loss": 0.6736,
|
| 1416 |
+
"step": 1000
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.97,
|
| 1420 |
+
"grad_norm": 0.10404789525698893,
|
| 1421 |
+
"learning_rate": 6.518264651449779e-07,
|
| 1422 |
+
"loss": 0.7771,
|
| 1423 |
+
"step": 1005
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.97,
|
| 1427 |
+
"grad_norm": 0.09905350029610553,
|
| 1428 |
+
"learning_rate": 4.743499715179067e-07,
|
| 1429 |
+
"loss": 0.7495,
|
| 1430 |
+
"step": 1010
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.98,
|
| 1434 |
+
"grad_norm": 0.08940324837180028,
|
| 1435 |
+
"learning_rate": 3.249628053142884e-07,
|
| 1436 |
+
"loss": 0.7587,
|
| 1437 |
+
"step": 1015
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.98,
|
| 1441 |
+
"grad_norm": 0.10668411274319571,
|
| 1442 |
+
"learning_rate": 2.0370712837906037e-07,
|
| 1443 |
+
"loss": 0.7657,
|
| 1444 |
+
"step": 1020
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.99,
|
| 1448 |
+
"grad_norm": 0.0933938060668371,
|
| 1449 |
+
"learning_rate": 1.1061716294951118e-07,
|
| 1450 |
+
"loss": 0.7493,
|
| 1451 |
+
"step": 1025
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.99,
|
| 1455 |
+
"grad_norm": 0.09579015452060988,
|
| 1456 |
+
"learning_rate": 4.5719181996650705e-08,
|
| 1457 |
+
"loss": 0.7677,
|
| 1458 |
+
"step": 1030
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.0,
|
| 1462 |
+
"grad_norm": 0.1038186774195005,
|
| 1463 |
+
"learning_rate": 9.031501810174981e-09,
|
| 1464 |
+
"loss": 0.7327,
|
| 1465 |
+
"step": 1035
|
| 1466 |
+
},
|
| 1467 |
{
|
| 1468 |
"epoch": 1.0,
|
| 1469 |
"eval_loss": NaN,
|
| 1470 |
+
"eval_runtime": 3002.6712,
|
| 1471 |
+
"eval_samples_per_second": 0.769,
|
| 1472 |
+
"eval_steps_per_second": 0.192,
|
| 1473 |
+
"step": 1039
|
| 1474 |
},
|
| 1475 |
{
|
| 1476 |
"epoch": 1.0,
|
| 1477 |
+
"step": 1039,
|
| 1478 |
+
"total_flos": 3.479777588753203e+16,
|
| 1479 |
+
"train_loss": 0.7603742487735766,
|
| 1480 |
+
"train_runtime": 32307.7024,
|
| 1481 |
+
"train_samples_per_second": 1.029,
|
| 1482 |
+
"train_steps_per_second": 0.032
|
| 1483 |
}
|
| 1484 |
],
|
| 1485 |
"logging_steps": 5,
|
| 1486 |
+
"max_steps": 1039,
|
| 1487 |
"num_input_tokens_seen": 0,
|
| 1488 |
"num_train_epochs": 1,
|
| 1489 |
"save_steps": 100,
|
| 1490 |
+
"total_flos": 3.479777588753203e+16,
|
| 1491 |
"train_batch_size": 4,
|
| 1492 |
"trial_name": null,
|
| 1493 |
"trial_params": null
|