Commit
•
e118768
1
Parent(s):
0c9afed
huggingartists
Browse files- README.md +3 -3
- config.json +1 -1
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +136 -252
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
| 45 |
dataset = load_dataset("huggingartists/morgenshtern")
|
| 46 |
```
|
| 47 |
|
| 48 |
-
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on MORGENSHTERN's lyrics.
|
| 53 |
|
| 54 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 55 |
|
| 56 |
-
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
|
|
|
| 45 |
dataset = load_dataset("huggingartists/morgenshtern")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1qveqjla/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on MORGENSHTERN's lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/21tohu9l) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/21tohu9l/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
config.json
CHANGED
|
@@ -35,7 +35,7 @@
|
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
-
"transformers_version": "4.11.
|
| 39 |
"use_cache": true,
|
| 40 |
"vocab_size": 50257
|
| 41 |
}
|
|
|
|
| 35 |
}
|
| 36 |
},
|
| 37 |
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.11.3",
|
| 39 |
"use_cache": true,
|
| 40 |
"vocab_size": 50257
|
| 41 |
}
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 0.
|
|
|
|
| 1 |
+
{"eval_loss": 0.8691701889038086, "eval_runtime": 5.5874, "eval_samples_per_second": 22.014, "eval_steps_per_second": 2.864, "epoch": 4.0}
|
flax_model.msgpack
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497764120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dcb9fd0c95e49a7c5c6a915f2d7adaa973be6d1ae19ff9baad7139b0524ce2b
|
| 3 |
size 497764120
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 995604017
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b9057c2e701481d1224ab71cb3e30e9a63129f8298087d242e9dbef4d013a3c
|
| 3 |
size 995604017
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510403817
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fff17a1d5c7cb31c35913396acbea4856780b0256c64b1a8d4aaee9270629fc7
|
| 3 |
size 510403817
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9ebc7a18dd93d6b68e430a5a307587231b2cf1f61199f2bfb8080060d317195
|
| 3 |
size 14503
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b46773a8e0da9899f0332e86140882baf8db0e4d332cd8d2b17d122dbb838867
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,388 +1,272 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "output/morgenshtern/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.05,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 5
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.1,
|
| 18 |
-
"learning_rate": 5.
|
| 19 |
-
"loss":
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.15,
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 15
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.2,
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss":
|
| 32 |
"step": 20
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss":
|
| 38 |
"step": 25
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss":
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss": 0.
|
| 50 |
"step": 35
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch": 0.
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 40
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch": 0.
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 45
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch": 0.
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 50
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch": 0.
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 55
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch": 0.
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 60
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 1.
|
| 86 |
"step": 65
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 70
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch": 0.
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss":
|
| 98 |
"step": 75
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch": 0.
|
| 102 |
-
"learning_rate": 0.
|
| 103 |
-
"loss": 1.
|
| 104 |
"step": 80
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch": 0.
|
| 108 |
-
"learning_rate": 0.
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 85
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch": 0.
|
| 114 |
-
"learning_rate": 0.
|
| 115 |
-
"loss":
|
| 116 |
"step": 90
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 0.
|
| 120 |
-
"learning_rate": 0.
|
| 121 |
-
"loss": 1.
|
| 122 |
"step": 95
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch":
|
| 126 |
-
"
|
| 127 |
-
"
|
| 128 |
-
"
|
| 129 |
-
"eval_steps_per_second": 2.697,
|
| 130 |
-
"step": 98
|
| 131 |
},
|
| 132 |
{
|
| 133 |
-
"epoch": 1.
|
| 134 |
-
"
|
| 135 |
-
"
|
| 136 |
-
"
|
|
|
|
|
|
|
| 137 |
},
|
| 138 |
{
|
| 139 |
-
"epoch": 1.
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 0.
|
| 142 |
"step": 105
|
| 143 |
},
|
| 144 |
{
|
| 145 |
-
"epoch": 1.
|
| 146 |
-
"learning_rate":
|
| 147 |
-
"loss":
|
| 148 |
"step": 110
|
| 149 |
},
|
| 150 |
{
|
| 151 |
-
"epoch": 1.
|
| 152 |
-
"learning_rate":
|
| 153 |
-
"loss":
|
| 154 |
"step": 115
|
| 155 |
},
|
| 156 |
{
|
| 157 |
-
"epoch": 1.
|
| 158 |
-
"learning_rate":
|
| 159 |
-
"loss": 0.
|
| 160 |
"step": 120
|
| 161 |
},
|
| 162 |
{
|
| 163 |
-
"epoch": 1.
|
| 164 |
-
"learning_rate":
|
| 165 |
-
"loss":
|
| 166 |
"step": 125
|
| 167 |
},
|
| 168 |
{
|
| 169 |
-
"epoch": 1.
|
| 170 |
-
"learning_rate":
|
| 171 |
-
"loss": 0.
|
| 172 |
"step": 130
|
| 173 |
},
|
| 174 |
{
|
| 175 |
-
"epoch": 1.
|
| 176 |
-
"learning_rate":
|
| 177 |
-
"loss": 0.
|
| 178 |
"step": 135
|
| 179 |
},
|
| 180 |
{
|
| 181 |
-
"epoch": 1.
|
| 182 |
-
"learning_rate":
|
| 183 |
-
"loss":
|
| 184 |
"step": 140
|
| 185 |
},
|
| 186 |
{
|
| 187 |
-
"epoch": 1.
|
| 188 |
-
"learning_rate":
|
| 189 |
-
"loss": 0.
|
| 190 |
"step": 145
|
| 191 |
},
|
| 192 |
{
|
| 193 |
-
"epoch": 1.
|
| 194 |
-
"learning_rate":
|
| 195 |
-
"loss":
|
| 196 |
"step": 150
|
| 197 |
},
|
| 198 |
{
|
| 199 |
-
"epoch": 1.
|
| 200 |
-
"learning_rate":
|
| 201 |
-
"loss": 0.
|
| 202 |
"step": 155
|
| 203 |
},
|
| 204 |
{
|
| 205 |
-
"epoch": 1.
|
| 206 |
-
"learning_rate":
|
| 207 |
-
"loss": 0.
|
| 208 |
"step": 160
|
| 209 |
},
|
| 210 |
{
|
| 211 |
-
"epoch": 1.
|
| 212 |
-
"learning_rate":
|
| 213 |
-
"loss":
|
| 214 |
"step": 165
|
| 215 |
},
|
| 216 |
{
|
| 217 |
-
"epoch": 1.
|
| 218 |
-
"learning_rate":
|
| 219 |
-
"loss": 0.
|
| 220 |
"step": 170
|
| 221 |
},
|
| 222 |
{
|
| 223 |
-
"epoch": 1.
|
| 224 |
-
"learning_rate":
|
| 225 |
-
"loss": 0.
|
| 226 |
"step": 175
|
| 227 |
},
|
| 228 |
{
|
| 229 |
-
"epoch": 1.
|
| 230 |
-
"learning_rate":
|
| 231 |
-
"loss":
|
| 232 |
"step": 180
|
| 233 |
},
|
| 234 |
{
|
| 235 |
-
"epoch": 1.
|
| 236 |
-
"learning_rate":
|
| 237 |
-
"loss": 0.
|
| 238 |
"step": 185
|
| 239 |
},
|
| 240 |
{
|
| 241 |
-
"epoch": 1.
|
| 242 |
-
"learning_rate": 1.
|
| 243 |
-
"loss":
|
| 244 |
"step": 190
|
| 245 |
},
|
| 246 |
{
|
| 247 |
-
"epoch": 1.
|
| 248 |
-
"learning_rate":
|
| 249 |
-
"loss": 0.
|
| 250 |
"step": 195
|
| 251 |
},
|
| 252 |
{
|
| 253 |
-
"epoch":
|
| 254 |
-
"
|
| 255 |
-
"
|
| 256 |
-
"eval_samples_per_second": 20.696,
|
| 257 |
-
"eval_steps_per_second": 2.693,
|
| 258 |
-
"step": 196
|
| 259 |
-
},
|
| 260 |
-
{
|
| 261 |
-
"epoch": 2.06,
|
| 262 |
-
"learning_rate": 2.8937315607040204e-06,
|
| 263 |
-
"loss": 1.0557,
|
| 264 |
"step": 200
|
| 265 |
},
|
| 266 |
{
|
| 267 |
-
"epoch": 2.
|
| 268 |
-
"
|
| 269 |
-
"
|
| 270 |
-
"
|
| 271 |
-
|
| 272 |
-
|
| 273 |
-
"epoch": 2.16,
|
| 274 |
-
"learning_rate": 1.2583732714275138e-05,
|
| 275 |
-
"loss": 0.9577,
|
| 276 |
-
"step": 210
|
| 277 |
-
},
|
| 278 |
-
{
|
| 279 |
-
"epoch": 2.22,
|
| 280 |
-
"learning_rate": 1.9701309148087243e-05,
|
| 281 |
-
"loss": 1.0242,
|
| 282 |
-
"step": 215
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 2.27,
|
| 286 |
-
"learning_rate": 2.8098397211793345e-05,
|
| 287 |
-
"loss": 0.9276,
|
| 288 |
-
"step": 220
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 2.32,
|
| 292 |
-
"learning_rate": 3.755527380754418e-05,
|
| 293 |
-
"loss": 0.815,
|
| 294 |
-
"step": 225
|
| 295 |
-
},
|
| 296 |
-
{
|
| 297 |
-
"epoch": 2.37,
|
| 298 |
-
"learning_rate": 4.782448479340004e-05,
|
| 299 |
-
"loss": 0.9471,
|
| 300 |
-
"step": 230
|
| 301 |
-
},
|
| 302 |
-
{
|
| 303 |
-
"epoch": 2.42,
|
| 304 |
-
"learning_rate": 5.863732001255875e-05,
|
| 305 |
-
"loss": 0.937,
|
| 306 |
-
"step": 235
|
| 307 |
-
},
|
| 308 |
-
{
|
| 309 |
-
"epoch": 2.47,
|
| 310 |
-
"learning_rate": 6.97108445198519e-05,
|
| 311 |
-
"loss": 0.9469,
|
| 312 |
-
"step": 240
|
| 313 |
-
},
|
| 314 |
-
{
|
| 315 |
-
"epoch": 2.53,
|
| 316 |
-
"learning_rate": 8.075530202233491e-05,
|
| 317 |
-
"loss": 0.9792,
|
| 318 |
-
"step": 245
|
| 319 |
-
},
|
| 320 |
-
{
|
| 321 |
-
"epoch": 2.58,
|
| 322 |
-
"learning_rate": 9.148169681124647e-05,
|
| 323 |
-
"loss": 0.9752,
|
| 324 |
-
"step": 250
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 2.63,
|
| 328 |
-
"learning_rate": 0.00010160935579206932,
|
| 329 |
-
"loss": 1.0419,
|
| 330 |
-
"step": 255
|
| 331 |
-
},
|
| 332 |
-
{
|
| 333 |
-
"epoch": 2.68,
|
| 334 |
-
"learning_rate": 0.00011087327274022367,
|
| 335 |
-
"loss": 1.0001,
|
| 336 |
-
"step": 260
|
| 337 |
-
},
|
| 338 |
-
{
|
| 339 |
-
"epoch": 2.73,
|
| 340 |
-
"learning_rate": 0.00011903104260831395,
|
| 341 |
-
"loss": 0.9188,
|
| 342 |
-
"step": 265
|
| 343 |
-
},
|
| 344 |
-
{
|
| 345 |
-
"epoch": 2.78,
|
| 346 |
-
"learning_rate": 0.00012586920443780796,
|
| 347 |
-
"loss": 1.0406,
|
| 348 |
-
"step": 270
|
| 349 |
-
},
|
| 350 |
-
{
|
| 351 |
-
"epoch": 2.84,
|
| 352 |
-
"learning_rate": 0.0001312088269028256,
|
| 353 |
-
"loss": 0.9707,
|
| 354 |
-
"step": 275
|
| 355 |
-
},
|
| 356 |
-
{
|
| 357 |
-
"epoch": 2.89,
|
| 358 |
-
"learning_rate": 0.0001349101903314451,
|
| 359 |
-
"loss": 1.0249,
|
| 360 |
-
"step": 280
|
| 361 |
-
},
|
| 362 |
-
{
|
| 363 |
-
"epoch": 2.94,
|
| 364 |
-
"learning_rate": 0.0001368764426920297,
|
| 365 |
-
"loss": 1.0981,
|
| 366 |
-
"step": 285
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 2.99,
|
| 370 |
-
"learning_rate": 0.00013705613387990704,
|
| 371 |
-
"loss": 1.0821,
|
| 372 |
-
"step": 290
|
| 373 |
-
},
|
| 374 |
-
{
|
| 375 |
-
"epoch": 3.0,
|
| 376 |
-
"eval_loss": 0.8179315328598022,
|
| 377 |
-
"eval_runtime": 7.3188,
|
| 378 |
-
"eval_samples_per_second": 21.178,
|
| 379 |
-
"eval_steps_per_second": 2.733,
|
| 380 |
-
"step": 291
|
| 381 |
}
|
| 382 |
],
|
| 383 |
-
"max_steps":
|
| 384 |
-
"num_train_epochs":
|
| 385 |
-
"total_flos":
|
| 386 |
"trial_name": null,
|
| 387 |
"trial_params": null
|
| 388 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.8691701889038086,
|
| 3 |
+
"best_model_checkpoint": "output/morgenshtern/checkpoint-202",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 202,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 4.8622670741210196e-05,
|
| 13 |
+
"loss": 0.9101,
|
| 14 |
"step": 5
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.1,
|
| 18 |
+
"learning_rate": 5.902924774844624e-05,
|
| 19 |
+
"loss": 0.8731,
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.15,
|
| 24 |
+
"learning_rate": 6.96668542977361e-05,
|
| 25 |
+
"loss": 0.9581,
|
| 26 |
"step": 15
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.2,
|
| 30 |
+
"learning_rate": 8.027870792255626e-05,
|
| 31 |
+
"loss": 0.8474,
|
| 32 |
"step": 20
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.25,
|
| 36 |
+
"learning_rate": 9.060864780933411e-05,
|
| 37 |
+
"loss": 0.9838,
|
| 38 |
"step": 25
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.3,
|
| 42 |
+
"learning_rate": 0.00010040731829419309,
|
| 43 |
+
"loss": 1.012,
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.35,
|
| 48 |
+
"learning_rate": 0.00010943818808937948,
|
| 49 |
+
"loss": 0.8702,
|
| 50 |
"step": 35
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.4,
|
| 54 |
+
"learning_rate": 0.00011748325994051893,
|
| 55 |
+
"loss": 0.9656,
|
| 56 |
"step": 40
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 0.45,
|
| 60 |
+
"learning_rate": 0.00012434833288861775,
|
| 61 |
+
"loss": 0.9745,
|
| 62 |
"step": 45
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 0.5,
|
| 66 |
+
"learning_rate": 0.0001298676901104138,
|
| 67 |
+
"loss": 0.8875,
|
| 68 |
"step": 50
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 0.54,
|
| 72 |
+
"learning_rate": 0.00013390809917674526,
|
| 73 |
+
"loss": 0.9281,
|
| 74 |
"step": 55
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 0.59,
|
| 78 |
+
"learning_rate": 0.00013637202816621594,
|
| 79 |
+
"loss": 0.932,
|
| 80 |
"step": 60
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.64,
|
| 84 |
+
"learning_rate": 0.0001372,
|
| 85 |
+
"loss": 1.071,
|
| 86 |
"step": 65
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.69,
|
| 90 |
+
"learning_rate": 0.000136372028166216,
|
| 91 |
+
"loss": 0.8787,
|
| 92 |
"step": 70
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 0.74,
|
| 96 |
+
"learning_rate": 0.00013390809917674537,
|
| 97 |
+
"loss": 0.9074,
|
| 98 |
"step": 75
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 0.79,
|
| 102 |
+
"learning_rate": 0.00012986769011041397,
|
| 103 |
+
"loss": 1.0496,
|
| 104 |
"step": 80
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 0.84,
|
| 108 |
+
"learning_rate": 0.00012434833288861794,
|
| 109 |
+
"loss": 0.9943,
|
| 110 |
"step": 85
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 0.89,
|
| 114 |
+
"learning_rate": 0.00011748325994051916,
|
| 115 |
+
"loss": 1.0026,
|
| 116 |
"step": 90
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 0.94,
|
| 120 |
+
"learning_rate": 0.00010943818808937974,
|
| 121 |
+
"loss": 1.0201,
|
| 122 |
"step": 95
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 0.99,
|
| 126 |
+
"learning_rate": 0.00010040731829419337,
|
| 127 |
+
"loss": 0.9215,
|
| 128 |
+
"step": 100
|
|
|
|
|
|
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 1.0,
|
| 132 |
+
"eval_loss": 0.8902494311332703,
|
| 133 |
+
"eval_runtime": 5.4222,
|
| 134 |
+
"eval_samples_per_second": 22.684,
|
| 135 |
+
"eval_steps_per_second": 2.951,
|
| 136 |
+
"step": 101
|
| 137 |
},
|
| 138 |
{
|
| 139 |
+
"epoch": 1.04,
|
| 140 |
+
"learning_rate": 9.060864780933398e-05,
|
| 141 |
+
"loss": 0.9922,
|
| 142 |
"step": 105
|
| 143 |
},
|
| 144 |
{
|
| 145 |
+
"epoch": 1.09,
|
| 146 |
+
"learning_rate": 8.027870792255707e-05,
|
| 147 |
+
"loss": 0.8911,
|
| 148 |
"step": 110
|
| 149 |
},
|
| 150 |
{
|
| 151 |
+
"epoch": 1.14,
|
| 152 |
+
"learning_rate": 6.966685429773643e-05,
|
| 153 |
+
"loss": 0.9184,
|
| 154 |
"step": 115
|
| 155 |
},
|
| 156 |
{
|
| 157 |
+
"epoch": 1.19,
|
| 158 |
+
"learning_rate": 5.902924774844707e-05,
|
| 159 |
+
"loss": 0.8339,
|
| 160 |
"step": 120
|
| 161 |
},
|
| 162 |
{
|
| 163 |
+
"epoch": 1.24,
|
| 164 |
+
"learning_rate": 4.862267074121052e-05,
|
| 165 |
+
"loss": 0.791,
|
| 166 |
"step": 125
|
| 167 |
},
|
| 168 |
{
|
| 169 |
+
"epoch": 1.29,
|
| 170 |
+
"learning_rate": 3.869832889258939e-05,
|
| 171 |
+
"loss": 0.8984,
|
| 172 |
"step": 130
|
| 173 |
},
|
| 174 |
{
|
| 175 |
+
"epoch": 1.34,
|
| 176 |
+
"learning_rate": 2.9495787086535028e-05,
|
| 177 |
+
"loss": 0.7645,
|
| 178 |
"step": 135
|
| 179 |
},
|
| 180 |
{
|
| 181 |
+
"epoch": 1.39,
|
| 182 |
+
"learning_rate": 2.1237186588777798e-05,
|
| 183 |
+
"loss": 0.8448,
|
| 184 |
"step": 140
|
| 185 |
},
|
| 186 |
{
|
| 187 |
+
"epoch": 1.44,
|
| 188 |
+
"learning_rate": 1.4121882752050083e-05,
|
| 189 |
+
"loss": 0.8783,
|
| 190 |
"step": 145
|
| 191 |
},
|
| 192 |
{
|
| 193 |
+
"epoch": 1.49,
|
| 194 |
+
"learning_rate": 8.321632753190209e-06,
|
| 195 |
+
"loss": 0.8214,
|
| 196 |
"step": 150
|
| 197 |
},
|
| 198 |
{
|
| 199 |
+
"epoch": 1.53,
|
| 200 |
+
"learning_rate": 3.976449525958718e-06,
|
| 201 |
+
"loss": 0.7646,
|
| 202 |
"step": 155
|
| 203 |
},
|
| 204 |
{
|
| 205 |
+
"epoch": 1.58,
|
| 206 |
+
"learning_rate": 1.1912219719526667e-06,
|
| 207 |
+
"loss": 0.8915,
|
| 208 |
"step": 160
|
| 209 |
},
|
| 210 |
{
|
| 211 |
+
"epoch": 1.63,
|
| 212 |
+
"learning_rate": 3.318303476960258e-08,
|
| 213 |
+
"loss": 0.7759,
|
| 214 |
"step": 165
|
| 215 |
},
|
| 216 |
{
|
| 217 |
+
"epoch": 1.68,
|
| 218 |
+
"learning_rate": 5.302867558791814e-07,
|
| 219 |
+
"loss": 0.9129,
|
| 220 |
"step": 170
|
| 221 |
},
|
| 222 |
{
|
| 223 |
+
"epoch": 1.73,
|
| 224 |
+
"learning_rate": 2.670533488647443e-06,
|
| 225 |
+
"loss": 0.8839,
|
| 226 |
"step": 175
|
| 227 |
},
|
| 228 |
{
|
| 229 |
+
"epoch": 1.78,
|
| 230 |
+
"learning_rate": 6.402259559252401e-06,
|
| 231 |
+
"loss": 0.9542,
|
| 232 |
"step": 180
|
| 233 |
},
|
| 234 |
{
|
| 235 |
+
"epoch": 1.83,
|
| 236 |
+
"learning_rate": 1.1635384382334973e-05,
|
| 237 |
+
"loss": 0.891,
|
| 238 |
"step": 185
|
| 239 |
},
|
| 240 |
{
|
| 241 |
+
"epoch": 1.88,
|
| 242 |
+
"learning_rate": 1.824358492710126e-05,
|
| 243 |
+
"loss": 0.7246,
|
| 244 |
"step": 190
|
| 245 |
},
|
| 246 |
{
|
| 247 |
+
"epoch": 1.93,
|
| 248 |
+
"learning_rate": 2.6067345044190458e-05,
|
| 249 |
+
"loss": 0.7276,
|
| 250 |
"step": 195
|
| 251 |
},
|
| 252 |
{
|
| 253 |
+
"epoch": 1.98,
|
| 254 |
+
"learning_rate": 3.491780604522984e-05,
|
| 255 |
+
"loss": 0.8327,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 256 |
"step": 200
|
| 257 |
},
|
| 258 |
{
|
| 259 |
+
"epoch": 2.0,
|
| 260 |
+
"eval_loss": 0.8691701889038086,
|
| 261 |
+
"eval_runtime": 5.4146,
|
| 262 |
+
"eval_samples_per_second": 22.717,
|
| 263 |
+
"eval_steps_per_second": 2.955,
|
| 264 |
+
"step": 202
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 265 |
}
|
| 266 |
],
|
| 267 |
+
"max_steps": 404,
|
| 268 |
+
"num_train_epochs": 4,
|
| 269 |
+
"total_flos": 209817501696000.0,
|
| 270 |
"trial_name": null,
|
| 271 |
"trial_params": null
|
| 272 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2863
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd3bfc9cf6ae7969e054c62bceff3f5cf23d65ecf03aee4de9a1c7b331576fd6
|
| 3 |
size 2863
|