Commit
•
4a39723
1
Parent(s):
ad9a638
huggingartists
Browse files- README.md +3 -3
- 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
- tokenizer.json +6 -3
- trainer_state.json +214 -222
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
| 45 |
dataset = load_dataset("huggingartists/eminem")
|
| 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 Eminem'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/eminem")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1b0rnnbf/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 Eminem's lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/qx8rcy66) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/qx8rcy66/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 0.
|
|
|
|
| 1 |
+
{"eval_loss": 0.2455403357744217, "eval_runtime": 13.8298, "eval_samples_per_second": 43.674, "eval_steps_per_second": 5.495, "epoch": 2.0}
|
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 sha256:91f6459b49fddf722d9f858151797155a47bc8c1ea85a7b38322bbab947c2cca
|
| 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 sha256:5ee96f8a6e48147487cfb22ba654c29712017fab3f311ef29e0b92b111b5dcc9
|
| 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 510404393
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47644ff40a294931cd31f96b23b17629d42b2e26ea5369f56afd9709f6fe557e
|
| 3 |
size 510404393
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14567
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8620a678022e3508118c53e7b72967ce161e332ca8a4bec3c57043c8d0ab815e
|
| 3 |
size 14567
|
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:f05fbfb2124177f9afcf7ea2075c976a78e42036cfed8db1b7e37fe10af01dde
|
| 3 |
size 623
|
tokenizer.json
CHANGED
|
@@ -17,17 +17,20 @@
|
|
| 17 |
"pre_tokenizer": {
|
| 18 |
"type": "ByteLevel",
|
| 19 |
"add_prefix_space": false,
|
| 20 |
-
"trim_offsets": true
|
|
|
|
| 21 |
},
|
| 22 |
"post_processor": {
|
| 23 |
"type": "ByteLevel",
|
| 24 |
"add_prefix_space": true,
|
| 25 |
-
"trim_offsets": false
|
|
|
|
| 26 |
},
|
| 27 |
"decoder": {
|
| 28 |
"type": "ByteLevel",
|
| 29 |
"add_prefix_space": true,
|
| 30 |
-
"trim_offsets": true
|
|
|
|
| 31 |
},
|
| 32 |
"model": {
|
| 33 |
"type": "BPE",
|
|
|
|
| 17 |
"pre_tokenizer": {
|
| 18 |
"type": "ByteLevel",
|
| 19 |
"add_prefix_space": false,
|
| 20 |
+
"trim_offsets": true,
|
| 21 |
+
"use_regex": true
|
| 22 |
},
|
| 23 |
"post_processor": {
|
| 24 |
"type": "ByteLevel",
|
| 25 |
"add_prefix_space": true,
|
| 26 |
+
"trim_offsets": false,
|
| 27 |
+
"use_regex": true
|
| 28 |
},
|
| 29 |
"decoder": {
|
| 30 |
"type": "ByteLevel",
|
| 31 |
"add_prefix_space": true,
|
| 32 |
+
"trim_offsets": true,
|
| 33 |
+
"use_regex": true
|
| 34 |
},
|
| 35 |
"model": {
|
| 36 |
"type": "BPE",
|
trainer_state.json
CHANGED
|
@@ -1,584 +1,576 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "output/eminem/checkpoint-
|
| 4 |
"epoch": 1.0,
|
| 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": 0.01,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 5
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.02,
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.03,
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 15
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.04,
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 20
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.05,
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 25
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.07,
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.08,
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss": 0.
|
| 50 |
"step": 35
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.09,
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 40
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.1,
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 45
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.11,
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 50
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.12,
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 55
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.13,
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 60
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.14,
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 65
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.15,
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 70
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.16,
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 75
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.17,
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 80
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch": 0.
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 85
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.2,
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 90
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.21,
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 95
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.22,
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
"step": 100
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.23,
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss": 0.
|
| 134 |
"step": 105
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 0.24,
|
| 138 |
-
"learning_rate":
|
| 139 |
-
"loss": 0.
|
| 140 |
"step": 110
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 0.25,
|
| 144 |
-
"learning_rate":
|
| 145 |
-
"loss": 0.
|
| 146 |
"step": 115
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.26,
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 120
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 0.27,
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 125
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 0.28,
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 130
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 0.29,
|
| 168 |
-
"learning_rate":
|
| 169 |
-
"loss": 0.
|
| 170 |
"step": 135
|
| 171 |
},
|
| 172 |
{
|
| 173 |
-
"epoch": 0.
|
| 174 |
-
"learning_rate":
|
| 175 |
-
"loss": 0.
|
| 176 |
"step": 140
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 0.32,
|
| 180 |
-
"learning_rate": 3.
|
| 181 |
-
"loss": 0.
|
| 182 |
"step": 145
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 0.33,
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 150
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.34,
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss": 0.
|
| 194 |
"step": 155
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 0.35,
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss": 0.
|
| 200 |
"step": 160
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 0.36,
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 165
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 0.37,
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 170
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.38,
|
| 216 |
-
"learning_rate":
|
| 217 |
-
"loss": 0.
|
| 218 |
"step": 175
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 0.39,
|
| 222 |
-
"learning_rate": 2.
|
| 223 |
-
"loss": 0.
|
| 224 |
"step": 180
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 0.4,
|
| 228 |
-
"learning_rate":
|
| 229 |
-
"loss": 0.
|
| 230 |
"step": 185
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 0.41,
|
| 234 |
-
"learning_rate":
|
| 235 |
-
"loss": 0.
|
| 236 |
"step": 190
|
| 237 |
},
|
| 238 |
{
|
| 239 |
-
"epoch": 0.
|
| 240 |
-
"learning_rate":
|
| 241 |
-
"loss": 0.
|
| 242 |
"step": 195
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch": 0.
|
| 246 |
-
"learning_rate":
|
| 247 |
-
"loss": 0.
|
| 248 |
"step": 200
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 0.45,
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 205
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 0.46,
|
| 258 |
-
"learning_rate":
|
| 259 |
-
"loss": 0.
|
| 260 |
"step": 210
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 0.47,
|
| 264 |
-
"learning_rate":
|
| 265 |
-
"loss": 0.
|
| 266 |
"step": 215
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 0.48,
|
| 270 |
-
"learning_rate": 1.
|
| 271 |
-
"loss": 0.
|
| 272 |
"step": 220
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 0.49,
|
| 276 |
-
"learning_rate": 1.
|
| 277 |
-
"loss": 0.
|
| 278 |
"step": 225
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 0.5,
|
| 282 |
-
"learning_rate":
|
| 283 |
-
"loss": 0.
|
| 284 |
"step": 230
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 0.51,
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss": 0.
|
| 290 |
"step": 235
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 0.52,
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 240
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 0.53,
|
| 300 |
-
"learning_rate":
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 245
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"epoch": 0.
|
| 306 |
-
"learning_rate": 5.
|
| 307 |
-
"loss": 0.
|
| 308 |
"step": 250
|
| 309 |
},
|
| 310 |
{
|
| 311 |
-
"epoch": 0.
|
| 312 |
-
"learning_rate":
|
| 313 |
-
"loss": 0.
|
| 314 |
"step": 255
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 0.57,
|
| 318 |
-
"learning_rate":
|
| 319 |
-
"loss": 0.
|
| 320 |
"step": 260
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 0.58,
|
| 324 |
-
"learning_rate":
|
| 325 |
-
"loss": 0.
|
| 326 |
"step": 265
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 0.59,
|
| 330 |
-
"learning_rate":
|
| 331 |
-
"loss": 0.
|
| 332 |
"step": 270
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 0.6,
|
| 336 |
-
"learning_rate": 1.
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 275
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.61,
|
| 342 |
-
"learning_rate": 1.
|
| 343 |
-
"loss": 0.
|
| 344 |
"step": 280
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 0.62,
|
| 348 |
-
"learning_rate":
|
| 349 |
-
"loss": 0.
|
| 350 |
"step": 285
|
| 351 |
},
|
| 352 |
{
|
| 353 |
"epoch": 0.63,
|
| 354 |
-
"learning_rate":
|
| 355 |
-
"loss": 0.
|
| 356 |
"step": 290
|
| 357 |
},
|
| 358 |
{
|
| 359 |
"epoch": 0.64,
|
| 360 |
-
"learning_rate":
|
| 361 |
-
"loss": 0.
|
| 362 |
"step": 295
|
| 363 |
},
|
| 364 |
{
|
| 365 |
-
"epoch": 0.
|
| 366 |
-
"learning_rate":
|
| 367 |
-
"loss": 0.
|
| 368 |
"step": 300
|
| 369 |
},
|
| 370 |
{
|
| 371 |
-
"epoch": 0.
|
| 372 |
-
"learning_rate":
|
| 373 |
-
"loss": 0.
|
| 374 |
"step": 305
|
| 375 |
},
|
| 376 |
{
|
| 377 |
-
"epoch": 0.
|
| 378 |
-
"learning_rate":
|
| 379 |
-
"loss": 0.
|
| 380 |
"step": 310
|
| 381 |
},
|
| 382 |
{
|
| 383 |
-
"epoch": 0.
|
| 384 |
-
"learning_rate":
|
| 385 |
-
"loss": 0.
|
| 386 |
"step": 315
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 0.7,
|
| 390 |
-
"learning_rate": 2.
|
| 391 |
-
"loss": 0.
|
| 392 |
"step": 320
|
| 393 |
},
|
| 394 |
{
|
| 395 |
"epoch": 0.71,
|
| 396 |
-
"learning_rate":
|
| 397 |
-
"loss": 0.
|
| 398 |
"step": 325
|
| 399 |
},
|
| 400 |
{
|
| 401 |
"epoch": 0.72,
|
| 402 |
-
"learning_rate":
|
| 403 |
-
"loss": 0.
|
| 404 |
"step": 330
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 0.73,
|
| 408 |
-
"learning_rate":
|
| 409 |
-
"loss": 0.
|
| 410 |
"step": 335
|
| 411 |
},
|
| 412 |
{
|
| 413 |
"epoch": 0.74,
|
| 414 |
-
"learning_rate":
|
| 415 |
-
"loss": 0.
|
| 416 |
"step": 340
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 0.75,
|
| 420 |
-
"learning_rate":
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 345
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 0.76,
|
| 426 |
-
"learning_rate":
|
| 427 |
-
"loss": 0.
|
| 428 |
"step": 350
|
| 429 |
},
|
| 430 |
{
|
| 431 |
-
"epoch": 0.
|
| 432 |
-
"learning_rate": 3.
|
| 433 |
-
"loss": 0.
|
| 434 |
"step": 355
|
| 435 |
},
|
| 436 |
{
|
| 437 |
-
"epoch": 0.
|
| 438 |
-
"learning_rate": 4.
|
| 439 |
-
"loss": 0.
|
| 440 |
"step": 360
|
| 441 |
},
|
| 442 |
{
|
| 443 |
-
"epoch": 0.
|
| 444 |
-
"learning_rate":
|
| 445 |
-
"loss": 0.
|
| 446 |
"step": 365
|
| 447 |
},
|
| 448 |
{
|
| 449 |
-
"epoch": 0.
|
| 450 |
-
"learning_rate":
|
| 451 |
-
"loss": 0.
|
| 452 |
"step": 370
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 0.82,
|
| 456 |
-
"learning_rate":
|
| 457 |
-
"loss": 0.
|
| 458 |
"step": 375
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 0.83,
|
| 462 |
-
"learning_rate":
|
| 463 |
-
"loss": 0.
|
| 464 |
"step": 380
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 0.84,
|
| 468 |
-
"learning_rate":
|
| 469 |
-
"loss": 0.
|
| 470 |
"step": 385
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 0.85,
|
| 474 |
-
"learning_rate":
|
| 475 |
-
"loss": 0.
|
| 476 |
"step": 390
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 0.86,
|
| 480 |
-
"learning_rate":
|
| 481 |
-
"loss": 0.
|
| 482 |
"step": 395
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 0.87,
|
| 486 |
-
"learning_rate":
|
| 487 |
-
"loss": 0.
|
| 488 |
"step": 400
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"epoch": 0.88,
|
| 492 |
-
"learning_rate":
|
| 493 |
-
"loss": 0.
|
| 494 |
"step": 405
|
| 495 |
},
|
| 496 |
{
|
| 497 |
-
"epoch": 0.
|
| 498 |
-
"learning_rate":
|
| 499 |
-
"loss": 0.
|
| 500 |
"step": 410
|
| 501 |
},
|
| 502 |
{
|
| 503 |
-
"epoch": 0.
|
| 504 |
-
"learning_rate":
|
| 505 |
-
"loss": 0.
|
| 506 |
"step": 415
|
| 507 |
},
|
| 508 |
{
|
| 509 |
-
"epoch": 0.
|
| 510 |
-
"learning_rate":
|
| 511 |
-
"loss": 0.
|
| 512 |
"step": 420
|
| 513 |
},
|
| 514 |
{
|
| 515 |
-
"epoch": 0.
|
| 516 |
-
"learning_rate":
|
| 517 |
-
"loss": 0.
|
| 518 |
"step": 425
|
| 519 |
},
|
| 520 |
{
|
| 521 |
-
"epoch": 0.
|
| 522 |
-
"learning_rate":
|
| 523 |
-
"loss": 0.
|
| 524 |
"step": 430
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 0.95,
|
| 528 |
-
"learning_rate":
|
| 529 |
-
"loss": 0.
|
| 530 |
"step": 435
|
| 531 |
},
|
| 532 |
{
|
| 533 |
"epoch": 0.96,
|
| 534 |
-
"learning_rate":
|
| 535 |
-
"loss": 0.
|
| 536 |
"step": 440
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 0.97,
|
| 540 |
-
"learning_rate":
|
| 541 |
-
"loss": 0.
|
| 542 |
"step": 445
|
| 543 |
},
|
| 544 |
{
|
| 545 |
"epoch": 0.98,
|
| 546 |
-
"learning_rate":
|
| 547 |
-
"loss": 0.
|
| 548 |
"step": 450
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 0.99,
|
| 552 |
-
"learning_rate":
|
| 553 |
-
"loss": 0.
|
| 554 |
"step": 455
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"epoch": 1.0,
|
| 558 |
-
"
|
| 559 |
-
"
|
| 560 |
-
"eval_samples_per_second": 21.243,
|
| 561 |
-
"eval_steps_per_second": 2.66,
|
| 562 |
-
"step": 458
|
| 563 |
-
},
|
| 564 |
-
{
|
| 565 |
-
"epoch": 0.99,
|
| 566 |
-
"learning_rate": 8.656213912947592e-06,
|
| 567 |
-
"loss": 0.6179,
|
| 568 |
"step": 460
|
| 569 |
},
|
| 570 |
{
|
| 571 |
"epoch": 1.0,
|
| 572 |
-
"eval_loss": 0.
|
| 573 |
-
"eval_runtime":
|
| 574 |
-
"eval_samples_per_second":
|
| 575 |
-
"eval_steps_per_second":
|
| 576 |
-
"step":
|
| 577 |
}
|
| 578 |
],
|
| 579 |
-
"max_steps":
|
| 580 |
-
"num_train_epochs":
|
| 581 |
-
"total_flos":
|
| 582 |
"trial_name": null,
|
| 583 |
"trial_params": null
|
| 584 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.2455403357744217,
|
| 3 |
+
"best_model_checkpoint": "output/eminem/checkpoint-460",
|
| 4 |
"epoch": 1.0,
|
| 5 |
+
"global_step": 460,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 0.00010098945265056683,
|
| 13 |
+
"loss": 0.4239,
|
| 14 |
"step": 5
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 9.890598330141942e-05,
|
| 19 |
+
"loss": 0.484,
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.03,
|
| 24 |
+
"learning_rate": 9.678717853140213e-05,
|
| 25 |
+
"loss": 0.4876,
|
| 26 |
"step": 15
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.04,
|
| 30 |
+
"learning_rate": 9.46355087720941e-05,
|
| 31 |
+
"loss": 0.4738,
|
| 32 |
"step": 20
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.05,
|
| 36 |
+
"learning_rate": 9.245348277418726e-05,
|
| 37 |
+
"loss": 0.4579,
|
| 38 |
"step": 25
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.07,
|
| 42 |
+
"learning_rate": 9.024364468238985e-05,
|
| 43 |
+
"loss": 0.4577,
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.08,
|
| 48 |
+
"learning_rate": 8.800857106906198e-05,
|
| 49 |
+
"loss": 0.4851,
|
| 50 |
"step": 35
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.09,
|
| 54 |
+
"learning_rate": 8.575086793006042e-05,
|
| 55 |
+
"loss": 0.4626,
|
| 56 |
"step": 40
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.1,
|
| 60 |
+
"learning_rate": 8.34731676462491e-05,
|
| 61 |
+
"loss": 0.4782,
|
| 62 |
"step": 45
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.11,
|
| 66 |
+
"learning_rate": 8.117812591427207e-05,
|
| 67 |
+
"loss": 0.5103,
|
| 68 |
"step": 50
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.12,
|
| 72 |
+
"learning_rate": 7.886841865013191e-05,
|
| 73 |
+
"loss": 0.5388,
|
| 74 |
"step": 55
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.13,
|
| 78 |
+
"learning_rate": 7.654673886917425e-05,
|
| 79 |
+
"loss": 0.4255,
|
| 80 |
"step": 60
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.14,
|
| 84 |
+
"learning_rate": 7.421579354617336e-05,
|
| 85 |
+
"loss": 0.4845,
|
| 86 |
"step": 65
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.15,
|
| 90 |
+
"learning_rate": 7.187830045910335e-05,
|
| 91 |
+
"loss": 0.4882,
|
| 92 |
"step": 70
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.16,
|
| 96 |
+
"learning_rate": 6.953698502034407e-05,
|
| 97 |
+
"loss": 0.4911,
|
| 98 |
"step": 75
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.17,
|
| 102 |
+
"learning_rate": 6.719457709896656e-05,
|
| 103 |
+
"loss": 0.445,
|
| 104 |
"step": 80
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 0.18,
|
| 108 |
+
"learning_rate": 6.485380783782185e-05,
|
| 109 |
+
"loss": 0.4824,
|
| 110 |
"step": 85
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.2,
|
| 114 |
+
"learning_rate": 6.251740646916227e-05,
|
| 115 |
+
"loss": 0.478,
|
| 116 |
"step": 90
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.21,
|
| 120 |
+
"learning_rate": 6.0188097132472896e-05,
|
| 121 |
+
"loss": 0.5299,
|
| 122 |
"step": 95
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.22,
|
| 126 |
+
"learning_rate": 5.786859569824095e-05,
|
| 127 |
+
"loss": 0.5087,
|
| 128 |
"step": 100
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.23,
|
| 132 |
+
"learning_rate": 5.556160660138586e-05,
|
| 133 |
+
"loss": 0.4854,
|
| 134 |
"step": 105
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 0.24,
|
| 138 |
+
"learning_rate": 5.326981968799179e-05,
|
| 139 |
+
"loss": 0.5017,
|
| 140 |
"step": 110
|
| 141 |
},
|
| 142 |
{
|
| 143 |
"epoch": 0.25,
|
| 144 |
+
"learning_rate": 5.099590707908848e-05,
|
| 145 |
+
"loss": 0.4689,
|
| 146 |
"step": 115
|
| 147 |
},
|
| 148 |
{
|
| 149 |
"epoch": 0.26,
|
| 150 |
+
"learning_rate": 4.874252005506042e-05,
|
| 151 |
+
"loss": 0.4921,
|
| 152 |
"step": 120
|
| 153 |
},
|
| 154 |
{
|
| 155 |
"epoch": 0.27,
|
| 156 |
+
"learning_rate": 4.651228596437459e-05,
|
| 157 |
+
"loss": 0.4873,
|
| 158 |
"step": 125
|
| 159 |
},
|
| 160 |
{
|
| 161 |
"epoch": 0.28,
|
| 162 |
+
"learning_rate": 4.4307805160220805e-05,
|
| 163 |
+
"loss": 0.4682,
|
| 164 |
"step": 130
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 0.29,
|
| 168 |
+
"learning_rate": 4.2131647968601464e-05,
|
| 169 |
+
"loss": 0.5228,
|
| 170 |
"step": 135
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.3,
|
| 174 |
+
"learning_rate": 3.998635169145922e-05,
|
| 175 |
+
"loss": 0.4468,
|
| 176 |
"step": 140
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 0.32,
|
| 180 |
+
"learning_rate": 3.7874417648290806e-05,
|
| 181 |
+
"loss": 0.452,
|
| 182 |
"step": 145
|
| 183 |
},
|
| 184 |
{
|
| 185 |
"epoch": 0.33,
|
| 186 |
+
"learning_rate": 3.57983082597153e-05,
|
| 187 |
+
"loss": 0.4363,
|
| 188 |
"step": 150
|
| 189 |
},
|
| 190 |
{
|
| 191 |
"epoch": 0.34,
|
| 192 |
+
"learning_rate": 3.376044417641229e-05,
|
| 193 |
+
"loss": 0.4868,
|
| 194 |
"step": 155
|
| 195 |
},
|
| 196 |
{
|
| 197 |
"epoch": 0.35,
|
| 198 |
+
"learning_rate": 3.176320145674611e-05,
|
| 199 |
+
"loss": 0.4906,
|
| 200 |
"step": 160
|
| 201 |
},
|
| 202 |
{
|
| 203 |
"epoch": 0.36,
|
| 204 |
+
"learning_rate": 2.98089087963816e-05,
|
| 205 |
+
"loss": 0.5023,
|
| 206 |
"step": 165
|
| 207 |
},
|
| 208 |
{
|
| 209 |
"epoch": 0.37,
|
| 210 |
+
"learning_rate": 2.7899844813147157e-05,
|
| 211 |
+
"loss": 0.4712,
|
| 212 |
"step": 170
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 0.38,
|
| 216 |
+
"learning_rate": 2.603823539024549e-05,
|
| 217 |
+
"loss": 0.4571,
|
| 218 |
"step": 175
|
| 219 |
},
|
| 220 |
{
|
| 221 |
"epoch": 0.39,
|
| 222 |
+
"learning_rate": 2.422625108099115e-05,
|
| 223 |
+
"loss": 0.4262,
|
| 224 |
"step": 180
|
| 225 |
},
|
| 226 |
{
|
| 227 |
"epoch": 0.4,
|
| 228 |
+
"learning_rate": 2.2466004578035872e-05,
|
| 229 |
+
"loss": 0.455,
|
| 230 |
"step": 185
|
| 231 |
},
|
| 232 |
{
|
| 233 |
"epoch": 0.41,
|
| 234 |
+
"learning_rate": 2.0759548250059194e-05,
|
| 235 |
+
"loss": 0.4506,
|
| 236 |
"step": 190
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 0.42,
|
| 240 |
+
"learning_rate": 1.910887174880859e-05,
|
| 241 |
+
"loss": 0.4219,
|
| 242 |
"step": 195
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 0.43,
|
| 246 |
+
"learning_rate": 1.7515899689243134e-05,
|
| 247 |
+
"loss": 0.4164,
|
| 248 |
"step": 200
|
| 249 |
},
|
| 250 |
{
|
| 251 |
"epoch": 0.45,
|
| 252 |
+
"learning_rate": 1.5982489405528287e-05,
|
| 253 |
+
"loss": 0.4133,
|
| 254 |
"step": 205
|
| 255 |
},
|
| 256 |
{
|
| 257 |
"epoch": 0.46,
|
| 258 |
+
"learning_rate": 1.4510428785463036e-05,
|
| 259 |
+
"loss": 0.4375,
|
| 260 |
"step": 210
|
| 261 |
},
|
| 262 |
{
|
| 263 |
"epoch": 0.47,
|
| 264 |
+
"learning_rate": 1.3101434185879184e-05,
|
| 265 |
+
"loss": 0.4882,
|
| 266 |
"step": 215
|
| 267 |
},
|
| 268 |
{
|
| 269 |
"epoch": 0.48,
|
| 270 |
+
"learning_rate": 1.175714843145347e-05,
|
| 271 |
+
"loss": 0.445,
|
| 272 |
"step": 220
|
| 273 |
},
|
| 274 |
{
|
| 275 |
"epoch": 0.49,
|
| 276 |
+
"learning_rate": 1.0479138899242488e-05,
|
| 277 |
+
"loss": 0.46,
|
| 278 |
"step": 225
|
| 279 |
},
|
| 280 |
{
|
| 281 |
"epoch": 0.5,
|
| 282 |
+
"learning_rate": 9.268895691192436e-06,
|
| 283 |
+
"loss": 0.5074,
|
| 284 |
"step": 230
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 0.51,
|
| 288 |
+
"learning_rate": 8.127829896747804e-06,
|
| 289 |
+
"loss": 0.4527,
|
| 290 |
"step": 235
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 0.52,
|
| 294 |
+
"learning_rate": 7.057271947580458e-06,
|
| 295 |
+
"loss": 0.4939,
|
| 296 |
"step": 240
|
| 297 |
},
|
| 298 |
{
|
| 299 |
"epoch": 0.53,
|
| 300 |
+
"learning_rate": 6.058470066371539e-06,
|
| 301 |
+
"loss": 0.5338,
|
| 302 |
"step": 245
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 0.54,
|
| 306 |
+
"learning_rate": 5.132588811436518e-06,
|
| 307 |
+
"loss": 0.4298,
|
| 308 |
"step": 250
|
| 309 |
},
|
| 310 |
{
|
| 311 |
+
"epoch": 0.55,
|
| 312 |
+
"learning_rate": 4.280707718900271e-06,
|
| 313 |
+
"loss": 0.4572,
|
| 314 |
"step": 255
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 0.57,
|
| 318 |
+
"learning_rate": 3.5038200440114727e-06,
|
| 319 |
+
"loss": 0.4096,
|
| 320 |
"step": 260
|
| 321 |
},
|
| 322 |
{
|
| 323 |
"epoch": 0.58,
|
| 324 |
+
"learning_rate": 2.802831603045737e-06,
|
| 325 |
+
"loss": 0.5071,
|
| 326 |
"step": 265
|
| 327 |
},
|
| 328 |
{
|
| 329 |
"epoch": 0.59,
|
| 330 |
+
"learning_rate": 2.178559717169051e-06,
|
| 331 |
+
"loss": 0.444,
|
| 332 |
"step": 270
|
| 333 |
},
|
| 334 |
{
|
| 335 |
"epoch": 0.6,
|
| 336 |
+
"learning_rate": 1.6317322594756245e-06,
|
| 337 |
+
"loss": 0.4421,
|
| 338 |
"step": 275
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 0.61,
|
| 342 |
+
"learning_rate": 1.162986806318977e-06,
|
| 343 |
+
"loss": 0.4878,
|
| 344 |
"step": 280
|
| 345 |
},
|
| 346 |
{
|
| 347 |
"epoch": 0.62,
|
| 348 |
+
"learning_rate": 7.72869893930971e-07,
|
| 349 |
+
"loss": 0.4151,
|
| 350 |
"step": 285
|
| 351 |
},
|
| 352 |
{
|
| 353 |
"epoch": 0.63,
|
| 354 |
+
"learning_rate": 4.6183638117953145e-07,
|
| 355 |
+
"loss": 0.4066,
|
| 356 |
"step": 290
|
| 357 |
},
|
| 358 |
{
|
| 359 |
"epoch": 0.64,
|
| 360 |
+
"learning_rate": 2.3024891922762553e-07,
|
| 361 |
+
"loss": 0.4453,
|
| 362 |
"step": 295
|
| 363 |
},
|
| 364 |
{
|
| 365 |
+
"epoch": 0.65,
|
| 366 |
+
"learning_rate": 7.837752869653465e-08,
|
| 367 |
+
"loss": 0.5799,
|
| 368 |
"step": 300
|
| 369 |
},
|
| 370 |
{
|
| 371 |
+
"epoch": 0.66,
|
| 372 |
+
"learning_rate": 6.399284833793284e-09,
|
| 373 |
+
"loss": 0.4665,
|
| 374 |
"step": 305
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 0.67,
|
| 378 |
+
"learning_rate": 1.4398111052152874e-08,
|
| 379 |
+
"loss": 0.4856,
|
| 380 |
"step": 310
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"epoch": 0.68,
|
| 384 |
+
"learning_rate": 1.0236468107794785e-07,
|
| 385 |
+
"loss": 0.4853,
|
| 386 |
"step": 315
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 0.7,
|
| 390 |
+
"learning_rate": 2.7019642982561925e-07,
|
| 391 |
+
"loss": 0.5332,
|
| 392 |
"step": 320
|
| 393 |
},
|
| 394 |
{
|
| 395 |
"epoch": 0.71,
|
| 396 |
+
"learning_rate": 5.176976729833616e-07,
|
| 397 |
+
"loss": 0.4575,
|
| 398 |
"step": 325
|
| 399 |
},
|
| 400 |
{
|
| 401 |
"epoch": 0.72,
|
| 402 |
+
"learning_rate": 8.445798351733662e-07,
|
| 403 |
+
"loss": 0.4864,
|
| 404 |
"step": 330
|
| 405 |
},
|
| 406 |
{
|
| 407 |
"epoch": 0.73,
|
| 408 |
+
"learning_rate": 1.2504617864165704e-06,
|
| 409 |
+
"loss": 0.442,
|
| 410 |
"step": 335
|
| 411 |
},
|
| 412 |
{
|
| 413 |
"epoch": 0.74,
|
| 414 |
+
"learning_rate": 1.7348702865138632e-06,
|
| 415 |
+
"loss": 0.4695,
|
| 416 |
"step": 340
|
| 417 |
},
|
| 418 |
{
|
| 419 |
"epoch": 0.75,
|
| 420 |
+
"learning_rate": 2.297240536822864e-06,
|
| 421 |
+
"loss": 0.5056,
|
| 422 |
"step": 345
|
| 423 |
},
|
| 424 |
{
|
| 425 |
"epoch": 0.76,
|
| 426 |
+
"learning_rate": 2.936916838787285e-06,
|
| 427 |
+
"loss": 0.4522,
|
| 428 |
"step": 350
|
| 429 |
},
|
| 430 |
{
|
| 431 |
+
"epoch": 0.77,
|
| 432 |
+
"learning_rate": 3.6531533584543354e-06,
|
| 433 |
+
"loss": 0.4949,
|
| 434 |
"step": 355
|
| 435 |
},
|
| 436 |
{
|
| 437 |
+
"epoch": 0.78,
|
| 438 |
+
"learning_rate": 4.445114996080512e-06,
|
| 439 |
+
"loss": 0.4966,
|
| 440 |
"step": 360
|
| 441 |
},
|
| 442 |
{
|
| 443 |
+
"epoch": 0.79,
|
| 444 |
+
"learning_rate": 5.3118783598219064e-06,
|
| 445 |
+
"loss": 0.493,
|
| 446 |
"step": 365
|
| 447 |
},
|
| 448 |
{
|
| 449 |
+
"epoch": 0.8,
|
| 450 |
+
"learning_rate": 6.252432842370185e-06,
|
| 451 |
+
"loss": 0.4831,
|
| 452 |
"step": 370
|
| 453 |
},
|
| 454 |
{
|
| 455 |
"epoch": 0.82,
|
| 456 |
+
"learning_rate": 7.265681799270346e-06,
|
| 457 |
+
"loss": 0.4715,
|
| 458 |
"step": 375
|
| 459 |
},
|
| 460 |
{
|
| 461 |
"epoch": 0.83,
|
| 462 |
+
"learning_rate": 8.350443827565338e-06,
|
| 463 |
+
"loss": 0.4506,
|
| 464 |
"step": 380
|
| 465 |
},
|
| 466 |
{
|
| 467 |
"epoch": 0.84,
|
| 468 |
+
"learning_rate": 9.505454143253312e-06,
|
| 469 |
+
"loss": 0.4343,
|
| 470 |
"step": 385
|
| 471 |
},
|
| 472 |
{
|
| 473 |
"epoch": 0.85,
|
| 474 |
+
"learning_rate": 1.072936605597144e-05,
|
| 475 |
+
"loss": 0.4487,
|
| 476 |
"step": 390
|
| 477 |
},
|
| 478 |
{
|
| 479 |
"epoch": 0.86,
|
| 480 |
+
"learning_rate": 1.2020752539181091e-05,
|
| 481 |
+
"loss": 0.5072,
|
| 482 |
"step": 395
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 0.87,
|
| 486 |
+
"learning_rate": 1.3378107894005304e-05,
|
| 487 |
+
"loss": 0.447,
|
| 488 |
"step": 400
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"epoch": 0.88,
|
| 492 |
+
"learning_rate": 1.479984950482134e-05,
|
| 493 |
+
"loss": 0.4754,
|
| 494 |
"step": 405
|
| 495 |
},
|
| 496 |
{
|
| 497 |
+
"epoch": 0.89,
|
| 498 |
+
"learning_rate": 1.6284319684507726e-05,
|
| 499 |
+
"loss": 0.4414,
|
| 500 |
"step": 410
|
| 501 |
},
|
| 502 |
{
|
| 503 |
+
"epoch": 0.9,
|
| 504 |
+
"learning_rate": 1.782978760723747e-05,
|
| 505 |
+
"loss": 0.4684,
|
| 506 |
"step": 415
|
| 507 |
},
|
| 508 |
{
|
| 509 |
+
"epoch": 0.91,
|
| 510 |
+
"learning_rate": 1.9434451326547662e-05,
|
| 511 |
+
"loss": 0.5108,
|
| 512 |
"step": 420
|
| 513 |
},
|
| 514 |
{
|
| 515 |
+
"epoch": 0.92,
|
| 516 |
+
"learning_rate": 2.109643987632069e-05,
|
| 517 |
+
"loss": 0.4894,
|
| 518 |
"step": 425
|
| 519 |
},
|
| 520 |
{
|
| 521 |
+
"epoch": 0.93,
|
| 522 |
+
"learning_rate": 2.2813815452250717e-05,
|
| 523 |
+
"loss": 0.5156,
|
| 524 |
"step": 430
|
| 525 |
},
|
| 526 |
{
|
| 527 |
"epoch": 0.95,
|
| 528 |
+
"learning_rate": 2.4584575671241315e-05,
|
| 529 |
+
"loss": 0.4643,
|
| 530 |
"step": 435
|
| 531 |
},
|
| 532 |
{
|
| 533 |
"epoch": 0.96,
|
| 534 |
+
"learning_rate": 2.640665590608444e-05,
|
| 535 |
+
"loss": 0.457,
|
| 536 |
"step": 440
|
| 537 |
},
|
| 538 |
{
|
| 539 |
"epoch": 0.97,
|
| 540 |
+
"learning_rate": 2.8277931692735254e-05,
|
| 541 |
+
"loss": 0.4539,
|
| 542 |
"step": 445
|
| 543 |
},
|
| 544 |
{
|
| 545 |
"epoch": 0.98,
|
| 546 |
+
"learning_rate": 3.0196221207331556e-05,
|
| 547 |
+
"loss": 0.4085,
|
| 548 |
"step": 450
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 0.99,
|
| 552 |
+
"learning_rate": 3.215928781010894e-05,
|
| 553 |
+
"loss": 0.4488,
|
| 554 |
"step": 455
|
| 555 |
},
|
| 556 |
{
|
| 557 |
"epoch": 1.0,
|
| 558 |
+
"learning_rate": 3.416484265322113e-05,
|
| 559 |
+
"loss": 0.4469,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 560 |
"step": 460
|
| 561 |
},
|
| 562 |
{
|
| 563 |
"epoch": 1.0,
|
| 564 |
+
"eval_loss": 0.2455403357744217,
|
| 565 |
+
"eval_runtime": 13.8337,
|
| 566 |
+
"eval_samples_per_second": 43.661,
|
| 567 |
+
"eval_steps_per_second": 5.494,
|
| 568 |
+
"step": 460
|
| 569 |
}
|
| 570 |
],
|
| 571 |
+
"max_steps": 920,
|
| 572 |
+
"num_train_epochs": 2,
|
| 573 |
+
"total_flos": 479993462784000.0,
|
| 574 |
"trial_name": null,
|
| 575 |
"trial_params": null
|
| 576 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3055
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8dba39e4831d67bb968da088ccd9c21edb2b352696e51f4a43088020c61c6578
|
| 3 |
size 3055
|