Commit ·
60643e2
1
Parent(s): ead4f2b
huggingartists
Browse files- README.md +4 -4
- 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 +1230 -556
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -14,7 +14,7 @@ widget:
|
|
| 14 |
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
| 15 |
<div class="flex">
|
| 16 |
<div
|
| 17 |
-
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://images.genius.com/
|
| 18 |
</div>
|
| 19 |
</div>
|
| 20 |
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
|
|
@@ -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 |
|
|
|
|
| 14 |
<div class="inline-flex flex-col" style="line-height: 1.5;">
|
| 15 |
<div class="flex">
|
| 16 |
<div
|
| 17 |
+
style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url('https://images.genius.com/76c536a17ca35f7edd1f78e129609fe0.573x573x1.jpg')">
|
| 18 |
</div>
|
| 19 |
</div>
|
| 20 |
<div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
|
|
|
|
| 45 |
dataset = load_dataset("huggingartists/eminem")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1cw72fwg/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/1s9gn4n3) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1s9gn4n3/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
config.json
CHANGED
|
@@ -36,7 +36,7 @@
|
|
| 36 |
}
|
| 37 |
},
|
| 38 |
"torch_dtype": "float32",
|
| 39 |
-
"transformers_version": "4.
|
| 40 |
"use_cache": true,
|
| 41 |
"vocab_size": 50257
|
| 42 |
}
|
|
|
|
| 36 |
}
|
| 37 |
},
|
| 38 |
"torch_dtype": "float32",
|
| 39 |
+
"transformers_version": "4.21.1",
|
| 40 |
"use_cache": true,
|
| 41 |
"vocab_size": 50257
|
| 42 |
}
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 0.
|
|
|
|
| 1 |
+
{"eval_loss": 0.7975038886070251, "eval_runtime": 7.9777, "eval_samples_per_second": 81.352, "eval_steps_per_second": 10.279, "epoch": 3.0}
|
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 sha256:195352921c9768b8f7722a7c6dadd24e0bb41f9c5b687a015dad8577e2e19d1e
|
| 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 sha256:3d220c780eb71062e07399c346abb83a3d8d5d253a988aae163afad0591fdd04
|
| 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 510396521
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1ea0a731add3655e830275a1f48125cb7f3420e6c2aa5a5112f441a84aaadeb
|
| 3 |
size 510396521
|
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 sha256:85a94ba790ee5732238750868c0fa5cd84aca898f6e3c21a553f5290ecb0fd85
|
| 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 sha256:1b357301156ff71969e9f7ff0267a328310fe92287f1483cfbf7826710ed8a0b
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,1112 +1,1786 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "output/eminem/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": 0.01,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 5
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.02,
|
| 18 |
-
"learning_rate": 7.
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.03,
|
| 24 |
-
"learning_rate": 7.
|
| 25 |
-
"loss":
|
| 26 |
"step": 15
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.04,
|
| 30 |
-
"learning_rate": 7.
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 20
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate": 7.
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 25
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 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":
|
| 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":
|
| 80 |
"step": 60
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch": 0.
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
| 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": 0.
|
| 98 |
"step": 75
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch": 0.
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss":
|
| 104 |
"step": 80
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch": 0.
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss":
|
| 110 |
"step": 85
|
| 111 |
},
|
| 112 |
{
|
| 113 |
-
"epoch": 0.
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 0.
|
| 116 |
"step": 90
|
| 117 |
},
|
| 118 |
{
|
| 119 |
-
"epoch": 0.
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 0.
|
| 122 |
"step": 95
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch": 0.
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss":
|
| 128 |
"step": 100
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss": 0.
|
| 134 |
"step": 105
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch": 0.
|
| 138 |
-
"learning_rate":
|
| 139 |
-
"loss": 0.
|
| 140 |
"step": 110
|
| 141 |
},
|
| 142 |
{
|
| 143 |
-
"epoch": 0.
|
| 144 |
-
"learning_rate":
|
| 145 |
-
"loss": 0.
|
| 146 |
"step": 115
|
| 147 |
},
|
| 148 |
{
|
| 149 |
-
"epoch": 0.
|
| 150 |
-
"learning_rate":
|
| 151 |
-
"loss": 0.
|
| 152 |
"step": 120
|
| 153 |
},
|
| 154 |
{
|
| 155 |
-
"epoch": 0.
|
| 156 |
-
"learning_rate":
|
| 157 |
-
"loss": 0.
|
| 158 |
"step": 125
|
| 159 |
},
|
| 160 |
{
|
| 161 |
-
"epoch": 0.
|
| 162 |
-
"learning_rate":
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 130
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch": 0.
|
| 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.
|
| 180 |
-
"learning_rate":
|
| 181 |
-
"loss": 0.
|
| 182 |
"step": 145
|
| 183 |
},
|
| 184 |
{
|
| 185 |
-
"epoch": 0.
|
| 186 |
-
"learning_rate":
|
| 187 |
-
"loss": 0.
|
| 188 |
"step": 150
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch": 0.
|
| 192 |
-
"learning_rate":
|
| 193 |
-
"loss": 0.
|
| 194 |
"step": 155
|
| 195 |
},
|
| 196 |
{
|
| 197 |
-
"epoch": 0.
|
| 198 |
-
"learning_rate":
|
| 199 |
-
"loss": 0.
|
| 200 |
"step": 160
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch": 0.
|
| 204 |
-
"learning_rate":
|
| 205 |
-
"loss": 0.
|
| 206 |
"step": 165
|
| 207 |
},
|
| 208 |
{
|
| 209 |
-
"epoch": 0.
|
| 210 |
-
"learning_rate":
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 170
|
| 213 |
},
|
| 214 |
{
|
| 215 |
-
"epoch": 0.
|
| 216 |
-
"learning_rate":
|
| 217 |
-
"loss": 0.
|
| 218 |
"step": 175
|
| 219 |
},
|
| 220 |
{
|
| 221 |
-
"epoch": 0.
|
| 222 |
-
"learning_rate":
|
| 223 |
-
"loss": 0.
|
| 224 |
"step": 180
|
| 225 |
},
|
| 226 |
{
|
| 227 |
-
"epoch": 0.
|
| 228 |
-
"learning_rate":
|
| 229 |
-
"loss": 0.
|
| 230 |
"step": 185
|
| 231 |
},
|
| 232 |
{
|
| 233 |
-
"epoch": 0.
|
| 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.
|
| 252 |
-
"learning_rate":
|
| 253 |
-
"loss": 0.
|
| 254 |
"step": 205
|
| 255 |
},
|
| 256 |
{
|
| 257 |
-
"epoch": 0.
|
| 258 |
-
"learning_rate":
|
| 259 |
-
"loss":
|
| 260 |
"step": 210
|
| 261 |
},
|
| 262 |
{
|
| 263 |
-
"epoch": 0.
|
| 264 |
-
"learning_rate":
|
| 265 |
-
"loss":
|
| 266 |
"step": 215
|
| 267 |
},
|
| 268 |
{
|
| 269 |
-
"epoch": 0.
|
| 270 |
-
"learning_rate":
|
| 271 |
-
"loss":
|
| 272 |
"step": 220
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"epoch": 0.
|
| 276 |
-
"learning_rate":
|
| 277 |
-
"loss": 0.
|
| 278 |
"step": 225
|
| 279 |
},
|
| 280 |
{
|
| 281 |
-
"epoch": 0.
|
| 282 |
-
"learning_rate":
|
| 283 |
-
"loss":
|
| 284 |
"step": 230
|
| 285 |
},
|
| 286 |
{
|
| 287 |
-
"epoch": 0.
|
| 288 |
-
"learning_rate":
|
| 289 |
-
"loss": 0.
|
| 290 |
"step": 235
|
| 291 |
},
|
| 292 |
{
|
| 293 |
-
"epoch": 0.
|
| 294 |
-
"learning_rate":
|
| 295 |
-
"loss": 0.
|
| 296 |
"step": 240
|
| 297 |
},
|
| 298 |
{
|
| 299 |
-
"epoch": 0.
|
| 300 |
-
"learning_rate":
|
| 301 |
-
"loss": 0.
|
| 302 |
"step": 245
|
| 303 |
},
|
| 304 |
{
|
| 305 |
-
"epoch": 0.
|
| 306 |
-
"learning_rate":
|
| 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.
|
| 318 |
-
"learning_rate":
|
| 319 |
-
"loss":
|
| 320 |
"step": 260
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"epoch": 0.
|
| 324 |
-
"learning_rate":
|
| 325 |
-
"loss":
|
| 326 |
"step": 265
|
| 327 |
},
|
| 328 |
{
|
| 329 |
-
"epoch": 0.
|
| 330 |
-
"learning_rate":
|
| 331 |
-
"loss":
|
| 332 |
"step": 270
|
| 333 |
},
|
| 334 |
{
|
| 335 |
-
"epoch": 0.
|
| 336 |
-
"learning_rate":
|
| 337 |
-
"loss": 0.
|
| 338 |
"step": 275
|
| 339 |
},
|
| 340 |
{
|
| 341 |
-
"epoch": 0.
|
| 342 |
-
"learning_rate":
|
| 343 |
-
"loss": 0.
|
| 344 |
"step": 280
|
| 345 |
},
|
| 346 |
{
|
| 347 |
-
"epoch": 0.
|
| 348 |
-
"learning_rate":
|
| 349 |
-
"loss": 0.
|
| 350 |
"step": 285
|
| 351 |
},
|
| 352 |
{
|
| 353 |
-
"epoch": 0.
|
| 354 |
-
"learning_rate":
|
| 355 |
-
"loss": 0.
|
| 356 |
"step": 290
|
| 357 |
},
|
| 358 |
{
|
| 359 |
-
"epoch": 0.
|
| 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.
|
| 390 |
-
"learning_rate":
|
| 391 |
-
"loss": 0.
|
| 392 |
"step": 320
|
| 393 |
},
|
| 394 |
{
|
| 395 |
-
"epoch": 0.
|
| 396 |
-
"learning_rate":
|
| 397 |
-
"loss":
|
| 398 |
"step": 325
|
| 399 |
},
|
| 400 |
{
|
| 401 |
-
"epoch": 0.
|
| 402 |
-
"learning_rate":
|
| 403 |
-
"loss":
|
| 404 |
"step": 330
|
| 405 |
},
|
| 406 |
{
|
| 407 |
-
"epoch": 0.
|
| 408 |
-
"learning_rate":
|
| 409 |
-
"loss": 0.
|
| 410 |
"step": 335
|
| 411 |
},
|
| 412 |
{
|
| 413 |
-
"epoch": 0.
|
| 414 |
-
"learning_rate":
|
| 415 |
-
"loss": 0.
|
| 416 |
"step": 340
|
| 417 |
},
|
| 418 |
{
|
| 419 |
-
"epoch": 0.
|
| 420 |
-
"learning_rate":
|
| 421 |
-
"loss": 0.
|
| 422 |
"step": 345
|
| 423 |
},
|
| 424 |
{
|
| 425 |
-
"epoch": 0.
|
| 426 |
-
"learning_rate":
|
| 427 |
-
"loss": 0.
|
| 428 |
"step": 350
|
| 429 |
},
|
| 430 |
{
|
| 431 |
-
"epoch": 0.
|
| 432 |
-
"learning_rate":
|
| 433 |
-
"loss":
|
| 434 |
"step": 355
|
| 435 |
},
|
| 436 |
{
|
| 437 |
-
"epoch": 0.
|
| 438 |
-
"learning_rate":
|
| 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.
|
| 456 |
-
"learning_rate":
|
| 457 |
-
"loss": 0.
|
| 458 |
"step": 375
|
| 459 |
},
|
| 460 |
{
|
| 461 |
-
"epoch": 0.
|
| 462 |
-
"learning_rate":
|
| 463 |
-
"loss":
|
| 464 |
"step": 380
|
| 465 |
},
|
| 466 |
{
|
| 467 |
-
"epoch": 0.
|
| 468 |
-
"learning_rate":
|
| 469 |
-
"loss": 0.
|
| 470 |
"step": 385
|
| 471 |
},
|
| 472 |
{
|
| 473 |
-
"epoch": 0.
|
| 474 |
-
"learning_rate":
|
| 475 |
-
"loss": 0.
|
| 476 |
"step": 390
|
| 477 |
},
|
| 478 |
{
|
| 479 |
-
"epoch": 0.
|
| 480 |
-
"learning_rate":
|
| 481 |
-
"loss": 0.
|
| 482 |
"step": 395
|
| 483 |
},
|
| 484 |
{
|
| 485 |
-
"epoch": 0.
|
| 486 |
-
"learning_rate":
|
| 487 |
-
"loss": 0.
|
| 488 |
"step": 400
|
| 489 |
},
|
| 490 |
{
|
| 491 |
-
"epoch": 0.
|
| 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":
|
| 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.
|
| 528 |
-
"learning_rate":
|
| 529 |
-
"loss": 0.
|
| 530 |
"step": 435
|
| 531 |
},
|
| 532 |
{
|
| 533 |
-
"epoch": 0.
|
| 534 |
-
"learning_rate":
|
| 535 |
-
"loss": 0.
|
| 536 |
"step": 440
|
| 537 |
},
|
| 538 |
{
|
| 539 |
-
"epoch": 0.
|
| 540 |
-
"learning_rate":
|
| 541 |
-
"loss": 0.
|
| 542 |
"step": 445
|
| 543 |
},
|
| 544 |
{
|
| 545 |
-
"epoch":
|
| 546 |
-
"learning_rate":
|
| 547 |
-
"loss": 0.
|
| 548 |
"step": 450
|
| 549 |
},
|
| 550 |
{
|
| 551 |
-
"epoch":
|
| 552 |
-
"
|
| 553 |
-
"
|
| 554 |
-
"eval_samples_per_second": 41.79,
|
| 555 |
-
"eval_steps_per_second": 5.271,
|
| 556 |
-
"step": 452
|
| 557 |
-
},
|
| 558 |
-
{
|
| 559 |
-
"epoch": 1.01,
|
| 560 |
-
"learning_rate": 5.486625907525938e-05,
|
| 561 |
-
"loss": 0.3706,
|
| 562 |
"step": 455
|
| 563 |
},
|
| 564 |
{
|
| 565 |
-
"epoch":
|
| 566 |
-
"learning_rate":
|
| 567 |
-
"loss": 0.
|
| 568 |
"step": 460
|
| 569 |
},
|
| 570 |
{
|
| 571 |
-
"epoch":
|
| 572 |
-
"learning_rate":
|
| 573 |
-
"loss": 0.
|
| 574 |
"step": 465
|
| 575 |
},
|
| 576 |
{
|
| 577 |
-
"epoch":
|
| 578 |
-
"learning_rate":
|
| 579 |
-
"loss": 0.
|
| 580 |
"step": 470
|
| 581 |
},
|
| 582 |
{
|
| 583 |
-
"epoch":
|
| 584 |
-
"learning_rate":
|
| 585 |
-
"loss": 0.
|
| 586 |
"step": 475
|
| 587 |
},
|
| 588 |
{
|
| 589 |
-
"epoch":
|
| 590 |
-
"learning_rate":
|
| 591 |
-
"loss": 0.
|
| 592 |
"step": 480
|
| 593 |
},
|
| 594 |
{
|
| 595 |
-
"epoch": 1.
|
| 596 |
-
"learning_rate": 6.
|
| 597 |
-
"loss": 0.
|
| 598 |
"step": 485
|
| 599 |
},
|
| 600 |
{
|
| 601 |
-
"epoch": 1.
|
| 602 |
-
"
|
| 603 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 604 |
"step": 490
|
| 605 |
},
|
| 606 |
{
|
| 607 |
-
"epoch": 1.
|
| 608 |
-
"learning_rate":
|
| 609 |
-
"loss": 0.
|
| 610 |
"step": 495
|
| 611 |
},
|
| 612 |
{
|
| 613 |
-
"epoch": 1.
|
| 614 |
-
"learning_rate":
|
| 615 |
-
"loss": 0.
|
| 616 |
"step": 500
|
| 617 |
},
|
| 618 |
{
|
| 619 |
-
"epoch": 1.
|
| 620 |
-
"learning_rate":
|
| 621 |
-
"loss": 0.
|
| 622 |
"step": 505
|
| 623 |
},
|
| 624 |
{
|
| 625 |
-
"epoch": 1.
|
| 626 |
-
"learning_rate":
|
| 627 |
-
"loss": 0.
|
| 628 |
"step": 510
|
| 629 |
},
|
| 630 |
{
|
| 631 |
-
"epoch": 1.
|
| 632 |
-
"learning_rate":
|
| 633 |
-
"loss": 0.
|
| 634 |
"step": 515
|
| 635 |
},
|
| 636 |
{
|
| 637 |
-
"epoch": 1.
|
| 638 |
-
"learning_rate":
|
| 639 |
-
"loss": 0.
|
| 640 |
"step": 520
|
| 641 |
},
|
| 642 |
{
|
| 643 |
-
"epoch": 1.
|
| 644 |
-
"learning_rate":
|
| 645 |
-
"loss": 0.
|
| 646 |
"step": 525
|
| 647 |
},
|
| 648 |
{
|
| 649 |
-
"epoch": 1.
|
| 650 |
-
"learning_rate":
|
| 651 |
-
"loss": 0.
|
| 652 |
"step": 530
|
| 653 |
},
|
| 654 |
{
|
| 655 |
-
"epoch": 1.
|
| 656 |
-
"learning_rate":
|
| 657 |
-
"loss": 0.
|
| 658 |
"step": 535
|
| 659 |
},
|
| 660 |
{
|
| 661 |
-
"epoch": 1.
|
| 662 |
-
"learning_rate":
|
| 663 |
-
"loss": 0.
|
| 664 |
"step": 540
|
| 665 |
},
|
| 666 |
{
|
| 667 |
-
"epoch": 1.
|
| 668 |
-
"learning_rate":
|
| 669 |
-
"loss": 0.
|
| 670 |
"step": 545
|
| 671 |
},
|
| 672 |
{
|
| 673 |
-
"epoch": 1.
|
| 674 |
-
"learning_rate":
|
| 675 |
-
"loss": 0.
|
| 676 |
"step": 550
|
| 677 |
},
|
| 678 |
{
|
| 679 |
-
"epoch": 1.
|
| 680 |
-
"learning_rate":
|
| 681 |
-
"loss": 0.
|
| 682 |
"step": 555
|
| 683 |
},
|
| 684 |
{
|
| 685 |
-
"epoch": 1.
|
| 686 |
-
"learning_rate":
|
| 687 |
-
"loss": 0.
|
| 688 |
"step": 560
|
| 689 |
},
|
| 690 |
{
|
| 691 |
-
"epoch": 1.
|
| 692 |
-
"learning_rate":
|
| 693 |
-
"loss": 0.
|
| 694 |
"step": 565
|
| 695 |
},
|
| 696 |
{
|
| 697 |
-
"epoch": 1.
|
| 698 |
-
"learning_rate":
|
| 699 |
-
"loss": 0.
|
| 700 |
"step": 570
|
| 701 |
},
|
| 702 |
{
|
| 703 |
-
"epoch": 1.
|
| 704 |
-
"learning_rate":
|
| 705 |
-
"loss": 0.
|
| 706 |
"step": 575
|
| 707 |
},
|
| 708 |
{
|
| 709 |
-
"epoch": 1.
|
| 710 |
-
"learning_rate":
|
| 711 |
-
"loss": 0.
|
| 712 |
"step": 580
|
| 713 |
},
|
| 714 |
{
|
| 715 |
-
"epoch": 1.
|
| 716 |
-
"learning_rate":
|
| 717 |
-
"loss": 0.
|
| 718 |
"step": 585
|
| 719 |
},
|
| 720 |
{
|
| 721 |
-
"epoch": 1.
|
| 722 |
-
"learning_rate":
|
| 723 |
-
"loss": 0.
|
| 724 |
"step": 590
|
| 725 |
},
|
| 726 |
{
|
| 727 |
-
"epoch": 1.
|
| 728 |
-
"learning_rate":
|
| 729 |
-
"loss": 0.
|
| 730 |
"step": 595
|
| 731 |
},
|
| 732 |
{
|
| 733 |
-
"epoch": 1.
|
| 734 |
-
"learning_rate":
|
| 735 |
-
"loss": 0.
|
| 736 |
"step": 600
|
| 737 |
},
|
| 738 |
{
|
| 739 |
-
"epoch": 1.
|
| 740 |
-
"learning_rate":
|
| 741 |
-
"loss": 0.
|
| 742 |
"step": 605
|
| 743 |
},
|
| 744 |
{
|
| 745 |
-
"epoch": 1.
|
| 746 |
-
"learning_rate":
|
| 747 |
-
"loss": 0.
|
| 748 |
"step": 610
|
| 749 |
},
|
| 750 |
{
|
| 751 |
-
"epoch": 1.
|
| 752 |
-
"learning_rate":
|
| 753 |
-
"loss":
|
| 754 |
"step": 615
|
| 755 |
},
|
| 756 |
{
|
| 757 |
-
"epoch": 1.
|
| 758 |
-
"learning_rate":
|
| 759 |
-
"loss": 0.
|
| 760 |
"step": 620
|
| 761 |
},
|
| 762 |
{
|
| 763 |
-
"epoch": 1.
|
| 764 |
-
"learning_rate":
|
| 765 |
-
"loss": 0.
|
| 766 |
"step": 625
|
| 767 |
},
|
| 768 |
{
|
| 769 |
-
"epoch": 1.
|
| 770 |
-
"learning_rate":
|
| 771 |
-
"loss": 0.
|
| 772 |
"step": 630
|
| 773 |
},
|
| 774 |
{
|
| 775 |
-
"epoch": 1.
|
| 776 |
-
"learning_rate":
|
| 777 |
-
"loss": 0.
|
| 778 |
"step": 635
|
| 779 |
},
|
| 780 |
{
|
| 781 |
-
"epoch": 1.
|
| 782 |
-
"learning_rate":
|
| 783 |
-
"loss": 0.
|
| 784 |
"step": 640
|
| 785 |
},
|
| 786 |
{
|
| 787 |
-
"epoch": 1.
|
| 788 |
-
"learning_rate":
|
| 789 |
-
"loss": 0.
|
| 790 |
"step": 645
|
| 791 |
},
|
| 792 |
{
|
| 793 |
-
"epoch": 1.
|
| 794 |
-
"learning_rate":
|
| 795 |
-
"loss":
|
| 796 |
"step": 650
|
| 797 |
},
|
| 798 |
{
|
| 799 |
-
"epoch": 1.
|
| 800 |
-
"learning_rate":
|
| 801 |
-
"loss": 0.
|
| 802 |
"step": 655
|
| 803 |
},
|
| 804 |
{
|
| 805 |
-
"epoch": 1.
|
| 806 |
-
"learning_rate":
|
| 807 |
-
"loss": 0.
|
| 808 |
"step": 660
|
| 809 |
},
|
| 810 |
{
|
| 811 |
-
"epoch": 1.
|
| 812 |
-
"learning_rate":
|
| 813 |
-
"loss": 0.
|
| 814 |
"step": 665
|
| 815 |
},
|
| 816 |
{
|
| 817 |
-
"epoch": 1.
|
| 818 |
-
"learning_rate":
|
| 819 |
-
"loss": 0.
|
| 820 |
"step": 670
|
| 821 |
},
|
| 822 |
{
|
| 823 |
-
"epoch": 1.
|
| 824 |
-
"learning_rate":
|
| 825 |
-
"loss": 0.
|
| 826 |
"step": 675
|
| 827 |
},
|
| 828 |
{
|
| 829 |
-
"epoch": 1.
|
| 830 |
-
"learning_rate":
|
| 831 |
-
"loss": 0.
|
| 832 |
"step": 680
|
| 833 |
},
|
| 834 |
{
|
| 835 |
-
"epoch": 1.
|
| 836 |
-
"learning_rate":
|
| 837 |
-
"loss": 0.
|
| 838 |
"step": 685
|
| 839 |
},
|
| 840 |
{
|
| 841 |
-
"epoch": 1.
|
| 842 |
-
"learning_rate":
|
| 843 |
-
"loss": 0.
|
| 844 |
"step": 690
|
| 845 |
},
|
| 846 |
{
|
| 847 |
-
"epoch": 1.
|
| 848 |
-
"learning_rate":
|
| 849 |
-
"loss": 0.
|
| 850 |
"step": 695
|
| 851 |
},
|
| 852 |
{
|
| 853 |
-
"epoch": 1.
|
| 854 |
-
"learning_rate":
|
| 855 |
-
"loss": 0.
|
| 856 |
"step": 700
|
| 857 |
},
|
| 858 |
{
|
| 859 |
-
"epoch": 1.
|
| 860 |
-
"learning_rate":
|
| 861 |
-
"loss": 0.
|
| 862 |
"step": 705
|
| 863 |
},
|
| 864 |
{
|
| 865 |
-
"epoch": 1.
|
| 866 |
-
"learning_rate":
|
| 867 |
-
"loss": 0.
|
| 868 |
"step": 710
|
| 869 |
},
|
| 870 |
{
|
| 871 |
-
"epoch": 1.
|
| 872 |
-
"learning_rate":
|
| 873 |
-
"loss": 0.
|
| 874 |
"step": 715
|
| 875 |
},
|
| 876 |
{
|
| 877 |
-
"epoch": 1.
|
| 878 |
-
"learning_rate":
|
| 879 |
-
"loss": 0.
|
| 880 |
"step": 720
|
| 881 |
},
|
| 882 |
{
|
| 883 |
-
"epoch": 1.
|
| 884 |
-
"learning_rate":
|
| 885 |
-
"loss": 0.
|
| 886 |
"step": 725
|
| 887 |
},
|
| 888 |
{
|
| 889 |
-
"epoch": 1.
|
| 890 |
-
"learning_rate":
|
| 891 |
-
"loss": 0.
|
| 892 |
"step": 730
|
| 893 |
},
|
| 894 |
{
|
| 895 |
-
"epoch": 1.
|
| 896 |
-
"learning_rate":
|
| 897 |
-
"loss": 0.
|
| 898 |
"step": 735
|
| 899 |
},
|
| 900 |
{
|
| 901 |
-
"epoch": 1.
|
| 902 |
-
"learning_rate":
|
| 903 |
-
"loss": 0.
|
| 904 |
"step": 740
|
| 905 |
},
|
| 906 |
{
|
| 907 |
-
"epoch": 1.
|
| 908 |
-
"learning_rate":
|
| 909 |
-
"loss": 0.
|
| 910 |
"step": 745
|
| 911 |
},
|
| 912 |
{
|
| 913 |
-
"epoch": 1.
|
| 914 |
-
"learning_rate":
|
| 915 |
-
"loss": 0.
|
| 916 |
"step": 750
|
| 917 |
},
|
| 918 |
{
|
| 919 |
-
"epoch": 1.
|
| 920 |
-
"learning_rate":
|
| 921 |
-
"loss": 0.
|
| 922 |
"step": 755
|
| 923 |
},
|
| 924 |
{
|
| 925 |
-
"epoch": 1.
|
| 926 |
-
"learning_rate":
|
| 927 |
-
"loss": 0.
|
| 928 |
"step": 760
|
| 929 |
},
|
| 930 |
{
|
| 931 |
-
"epoch": 1.
|
| 932 |
-
"learning_rate":
|
| 933 |
-
"loss": 0.
|
| 934 |
"step": 765
|
| 935 |
},
|
| 936 |
{
|
| 937 |
-
"epoch": 1.
|
| 938 |
-
"learning_rate":
|
| 939 |
-
"loss": 0.
|
| 940 |
"step": 770
|
| 941 |
},
|
| 942 |
{
|
| 943 |
-
"epoch": 1.
|
| 944 |
-
"learning_rate":
|
| 945 |
-
"loss": 0.
|
| 946 |
"step": 775
|
| 947 |
},
|
| 948 |
{
|
| 949 |
-
"epoch": 1.
|
| 950 |
-
"learning_rate":
|
| 951 |
-
"loss": 0.
|
| 952 |
"step": 780
|
| 953 |
},
|
| 954 |
{
|
| 955 |
-
"epoch": 1.
|
| 956 |
-
"learning_rate":
|
| 957 |
-
"loss": 0.
|
| 958 |
"step": 785
|
| 959 |
},
|
| 960 |
{
|
| 961 |
-
"epoch": 1.
|
| 962 |
-
"learning_rate":
|
| 963 |
-
"loss": 0.
|
| 964 |
"step": 790
|
| 965 |
},
|
| 966 |
{
|
| 967 |
-
"epoch": 1.
|
| 968 |
-
"learning_rate":
|
| 969 |
-
"loss": 0.
|
| 970 |
"step": 795
|
| 971 |
},
|
| 972 |
{
|
| 973 |
-
"epoch": 1.
|
| 974 |
-
"learning_rate":
|
| 975 |
-
"loss": 0.
|
| 976 |
"step": 800
|
| 977 |
},
|
| 978 |
{
|
| 979 |
-
"epoch": 1.
|
| 980 |
-
"learning_rate":
|
| 981 |
-
"loss": 0.
|
| 982 |
"step": 805
|
| 983 |
},
|
| 984 |
{
|
| 985 |
-
"epoch": 1.
|
| 986 |
-
"learning_rate":
|
| 987 |
-
"loss": 0.
|
| 988 |
"step": 810
|
| 989 |
},
|
| 990 |
{
|
| 991 |
-
"epoch": 1.
|
| 992 |
-
"learning_rate":
|
| 993 |
-
"loss": 0.
|
| 994 |
"step": 815
|
| 995 |
},
|
| 996 |
{
|
| 997 |
-
"epoch": 1.
|
| 998 |
-
"learning_rate":
|
| 999 |
-
"loss": 0.
|
| 1000 |
"step": 820
|
| 1001 |
},
|
| 1002 |
{
|
| 1003 |
-
"epoch": 1.
|
| 1004 |
-
"learning_rate":
|
| 1005 |
-
"loss": 0.
|
| 1006 |
"step": 825
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
-
"epoch": 1.
|
| 1010 |
-
"learning_rate":
|
| 1011 |
-
"loss": 0.
|
| 1012 |
"step": 830
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
-
"epoch": 1.
|
| 1016 |
-
"learning_rate":
|
| 1017 |
-
"loss": 0.
|
| 1018 |
"step": 835
|
| 1019 |
},
|
| 1020 |
{
|
| 1021 |
-
"epoch": 1.
|
| 1022 |
-
"learning_rate":
|
| 1023 |
-
"loss": 0.
|
| 1024 |
"step": 840
|
| 1025 |
},
|
| 1026 |
{
|
| 1027 |
-
"epoch": 1.
|
| 1028 |
-
"learning_rate":
|
| 1029 |
-
"loss": 0.
|
| 1030 |
"step": 845
|
| 1031 |
},
|
| 1032 |
{
|
| 1033 |
-
"epoch": 1.
|
| 1034 |
-
"learning_rate":
|
| 1035 |
-
"loss": 0.
|
| 1036 |
"step": 850
|
| 1037 |
},
|
| 1038 |
{
|
| 1039 |
-
"epoch": 1.
|
| 1040 |
-
"learning_rate":
|
| 1041 |
-
"loss": 0.
|
| 1042 |
"step": 855
|
| 1043 |
},
|
| 1044 |
{
|
| 1045 |
-
"epoch": 1.
|
| 1046 |
-
"learning_rate":
|
| 1047 |
-
"loss": 0.
|
| 1048 |
"step": 860
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
-
"epoch": 1.
|
| 1052 |
-
"learning_rate":
|
| 1053 |
-
"loss": 0.
|
| 1054 |
"step": 865
|
| 1055 |
},
|
| 1056 |
{
|
| 1057 |
-
"epoch": 1.
|
| 1058 |
-
"learning_rate":
|
| 1059 |
-
"loss": 0.
|
| 1060 |
"step": 870
|
| 1061 |
},
|
| 1062 |
{
|
| 1063 |
-
"epoch": 1.
|
| 1064 |
-
"learning_rate":
|
| 1065 |
-
"loss": 0.
|
| 1066 |
"step": 875
|
| 1067 |
},
|
| 1068 |
{
|
| 1069 |
-
"epoch": 1.
|
| 1070 |
-
"learning_rate":
|
| 1071 |
-
"loss": 0.
|
| 1072 |
"step": 880
|
| 1073 |
},
|
| 1074 |
{
|
| 1075 |
-
"epoch": 1.
|
| 1076 |
-
"learning_rate":
|
| 1077 |
-
"loss": 0.
|
| 1078 |
"step": 885
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
-
"epoch": 1.
|
| 1082 |
-
"learning_rate":
|
| 1083 |
-
"loss": 0.
|
| 1084 |
"step": 890
|
| 1085 |
},
|
| 1086 |
{
|
| 1087 |
-
"epoch": 1.
|
| 1088 |
-
"learning_rate":
|
| 1089 |
-
"loss": 0.
|
| 1090 |
"step": 895
|
| 1091 |
},
|
| 1092 |
{
|
| 1093 |
-
"epoch": 1.
|
| 1094 |
-
"learning_rate":
|
| 1095 |
-
"loss": 0.
|
| 1096 |
"step": 900
|
| 1097 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1098 |
{
|
| 1099 |
"epoch": 2.0,
|
| 1100 |
-
"eval_loss": 0.
|
| 1101 |
-
"eval_runtime":
|
| 1102 |
-
"eval_samples_per_second":
|
| 1103 |
-
"eval_steps_per_second":
|
| 1104 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1105 |
}
|
| 1106 |
],
|
| 1107 |
-
"max_steps":
|
| 1108 |
-
"num_train_epochs":
|
| 1109 |
-
"total_flos":
|
| 1110 |
"trial_name": null,
|
| 1111 |
"trial_params": null
|
| 1112 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.7975038886070251,
|
| 3 |
+
"best_model_checkpoint": "output/eminem/checkpoint-1455",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 1455,
|
| 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": 7.104344779818036e-05,
|
| 13 |
+
"loss": 0.7686,
|
| 14 |
"step": 5
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 7.326215453099495e-05,
|
| 19 |
+
"loss": 0.6054,
|
| 20 |
"step": 10
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.03,
|
| 24 |
+
"learning_rate": 7.54759713075063e-05,
|
| 25 |
+
"loss": 1.0539,
|
| 26 |
"step": 15
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.04,
|
| 30 |
+
"learning_rate": 7.768257613962603e-05,
|
| 31 |
+
"loss": 0.7369,
|
| 32 |
"step": 20
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.05,
|
| 36 |
+
"learning_rate": 7.987965460359759e-05,
|
| 37 |
+
"loss": 0.7577,
|
| 38 |
"step": 25
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.06,
|
| 42 |
+
"learning_rate": 8.206490226751101e-05,
|
| 43 |
+
"loss": 0.5693,
|
| 44 |
"step": 30
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 0.07,
|
| 48 |
+
"learning_rate": 8.423602710832802e-05,
|
| 49 |
+
"loss": 0.5772,
|
| 50 |
"step": 35
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 0.08,
|
| 54 |
+
"learning_rate": 8.63907519158997e-05,
|
| 55 |
+
"loss": 1.6227,
|
| 56 |
"step": 40
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 0.09,
|
| 60 |
+
"learning_rate": 8.852681668145864e-05,
|
| 61 |
+
"loss": 0.7695,
|
| 62 |
"step": 45
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 0.1,
|
| 66 |
+
"learning_rate": 9.064198096803333e-05,
|
| 67 |
+
"loss": 0.6463,
|
| 68 |
"step": 50
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 0.11,
|
| 72 |
+
"learning_rate": 9.27340262603724e-05,
|
| 73 |
+
"loss": 0.7689,
|
| 74 |
"step": 55
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 0.12,
|
| 78 |
+
"learning_rate": 9.480075829185323e-05,
|
| 79 |
+
"loss": 1.0531,
|
| 80 |
"step": 60
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 0.13,
|
| 84 |
+
"learning_rate": 9.684000934597923e-05,
|
| 85 |
+
"loss": 0.6097,
|
| 86 |
"step": 65
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 0.14,
|
| 90 |
+
"learning_rate": 9.884964052999149e-05,
|
| 91 |
+
"loss": 0.7093,
|
| 92 |
"step": 70
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 0.15,
|
| 96 |
+
"learning_rate": 0.00010082754401829355,
|
| 97 |
+
"loss": 0.5035,
|
| 98 |
"step": 75
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 0.16,
|
| 102 |
+
"learning_rate": 0.00010277164526325172,
|
| 103 |
+
"loss": 1.0989,
|
| 104 |
"step": 80
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 0.18,
|
| 108 |
+
"learning_rate": 0.00010467990517112986,
|
| 109 |
+
"loss": 1.0782,
|
| 110 |
"step": 85
|
| 111 |
},
|
| 112 |
{
|
| 113 |
+
"epoch": 0.19,
|
| 114 |
+
"learning_rate": 0.00010655032224079468,
|
| 115 |
+
"loss": 0.8885,
|
| 116 |
"step": 90
|
| 117 |
},
|
| 118 |
{
|
| 119 |
+
"epoch": 0.2,
|
| 120 |
+
"learning_rate": 0.00010838093466302798,
|
| 121 |
+
"loss": 0.9381,
|
| 122 |
"step": 95
|
| 123 |
},
|
| 124 |
{
|
| 125 |
+
"epoch": 0.21,
|
| 126 |
+
"learning_rate": 0.00011016982237818681,
|
| 127 |
+
"loss": 1.0053,
|
| 128 |
"step": 100
|
| 129 |
},
|
| 130 |
{
|
| 131 |
+
"epoch": 0.22,
|
| 132 |
+
"learning_rate": 0.00011191510909009365,
|
| 133 |
+
"loss": 0.6927,
|
| 134 |
"step": 105
|
| 135 |
},
|
| 136 |
{
|
| 137 |
+
"epoch": 0.23,
|
| 138 |
+
"learning_rate": 0.00011361496423399298,
|
| 139 |
+
"loss": 0.9509,
|
| 140 |
"step": 110
|
| 141 |
},
|
| 142 |
{
|
| 143 |
+
"epoch": 0.24,
|
| 144 |
+
"learning_rate": 0.0001152676048965721,
|
| 145 |
+
"loss": 0.6696,
|
| 146 |
"step": 115
|
| 147 |
},
|
| 148 |
{
|
| 149 |
+
"epoch": 0.25,
|
| 150 |
+
"learning_rate": 0.0001168712976859924,
|
| 151 |
+
"loss": 0.9941,
|
| 152 |
"step": 120
|
| 153 |
},
|
| 154 |
{
|
| 155 |
+
"epoch": 0.26,
|
| 156 |
+
"learning_rate": 0.00011842436054997332,
|
| 157 |
+
"loss": 0.5395,
|
| 158 |
"step": 125
|
| 159 |
},
|
| 160 |
{
|
| 161 |
+
"epoch": 0.27,
|
| 162 |
+
"learning_rate": 0.00011992516454003592,
|
| 163 |
+
"loss": 0.4659,
|
| 164 |
"step": 130
|
| 165 |
},
|
| 166 |
{
|
| 167 |
+
"epoch": 0.28,
|
| 168 |
+
"learning_rate": 0.00012137213552004078,
|
| 169 |
+
"loss": 0.8814,
|
| 170 |
"step": 135
|
| 171 |
},
|
| 172 |
{
|
| 173 |
+
"epoch": 0.29,
|
| 174 |
+
"learning_rate": 0.00012276375581724122,
|
| 175 |
+
"loss": 0.7903,
|
| 176 |
"step": 140
|
| 177 |
},
|
| 178 |
{
|
| 179 |
+
"epoch": 0.3,
|
| 180 |
+
"learning_rate": 0.00012409856581412063,
|
| 181 |
+
"loss": 0.8096,
|
| 182 |
"step": 145
|
| 183 |
},
|
| 184 |
{
|
| 185 |
+
"epoch": 0.31,
|
| 186 |
+
"learning_rate": 0.00012537516547931506,
|
| 187 |
+
"loss": 0.7711,
|
| 188 |
"step": 150
|
| 189 |
},
|
| 190 |
{
|
| 191 |
+
"epoch": 0.32,
|
| 192 |
+
"learning_rate": 0.0001265922158360627,
|
| 193 |
+
"loss": 0.7044,
|
| 194 |
"step": 155
|
| 195 |
},
|
| 196 |
{
|
| 197 |
+
"epoch": 0.33,
|
| 198 |
+
"learning_rate": 0.00012774844036660105,
|
| 199 |
+
"loss": 0.9893,
|
| 200 |
"step": 160
|
| 201 |
},
|
| 202 |
{
|
| 203 |
+
"epoch": 0.34,
|
| 204 |
+
"learning_rate": 0.00012884262635106593,
|
| 205 |
+
"loss": 0.9534,
|
| 206 |
"step": 165
|
| 207 |
},
|
| 208 |
{
|
| 209 |
+
"epoch": 0.35,
|
| 210 |
+
"learning_rate": 0.00012987362613945392,
|
| 211 |
+
"loss": 0.9657,
|
| 212 |
"step": 170
|
| 213 |
},
|
| 214 |
{
|
| 215 |
+
"epoch": 0.36,
|
| 216 |
+
"learning_rate": 0.0001308403583553606,
|
| 217 |
+
"loss": 0.8557,
|
| 218 |
"step": 175
|
| 219 |
},
|
| 220 |
{
|
| 221 |
+
"epoch": 0.37,
|
| 222 |
+
"learning_rate": 0.00013174180903018608,
|
| 223 |
+
"loss": 0.8623,
|
| 224 |
"step": 180
|
| 225 |
},
|
| 226 |
{
|
| 227 |
+
"epoch": 0.38,
|
| 228 |
+
"learning_rate": 0.00013257703266665794,
|
| 229 |
+
"loss": 0.9682,
|
| 230 |
"step": 185
|
| 231 |
},
|
| 232 |
{
|
| 233 |
+
"epoch": 0.39,
|
| 234 |
+
"learning_rate": 0.0001333451532305167,
|
| 235 |
+
"loss": 0.8295,
|
| 236 |
"step": 190
|
| 237 |
},
|
| 238 |
{
|
| 239 |
+
"epoch": 0.4,
|
| 240 |
+
"learning_rate": 0.00013404536506936147,
|
| 241 |
+
"loss": 0.6588,
|
| 242 |
"step": 195
|
| 243 |
},
|
| 244 |
{
|
| 245 |
+
"epoch": 0.41,
|
| 246 |
+
"learning_rate": 0.0001346769337576652,
|
| 247 |
+
"loss": 0.7481,
|
| 248 |
"step": 200
|
| 249 |
},
|
| 250 |
{
|
| 251 |
+
"epoch": 0.42,
|
| 252 |
+
"learning_rate": 0.0001352391968670901,
|
| 253 |
+
"loss": 0.8978,
|
| 254 |
"step": 205
|
| 255 |
},
|
| 256 |
{
|
| 257 |
+
"epoch": 0.43,
|
| 258 |
+
"learning_rate": 0.00013573156466127666,
|
| 259 |
+
"loss": 1.1897,
|
| 260 |
"step": 210
|
| 261 |
},
|
| 262 |
{
|
| 263 |
+
"epoch": 0.44,
|
| 264 |
+
"learning_rate": 0.0001361535207144,
|
| 265 |
+
"loss": 1.238,
|
| 266 |
"step": 215
|
| 267 |
},
|
| 268 |
{
|
| 269 |
+
"epoch": 0.45,
|
| 270 |
+
"learning_rate": 0.00013650462245282926,
|
| 271 |
+
"loss": 1.1457,
|
| 272 |
"step": 220
|
| 273 |
},
|
| 274 |
{
|
| 275 |
+
"epoch": 0.46,
|
| 276 |
+
"learning_rate": 0.00013678450161932478,
|
| 277 |
+
"loss": 0.8702,
|
| 278 |
"step": 225
|
| 279 |
},
|
| 280 |
{
|
| 281 |
+
"epoch": 0.47,
|
| 282 |
+
"learning_rate": 0.00013699286465928987,
|
| 283 |
+
"loss": 1.071,
|
| 284 |
"step": 230
|
| 285 |
},
|
| 286 |
{
|
| 287 |
+
"epoch": 0.48,
|
| 288 |
+
"learning_rate": 0.00013712949302866842,
|
| 289 |
+
"loss": 0.8298,
|
| 290 |
"step": 235
|
| 291 |
},
|
| 292 |
{
|
| 293 |
+
"epoch": 0.49,
|
| 294 |
+
"learning_rate": 0.00013719424342316803,
|
| 295 |
+
"loss": 0.9333,
|
| 296 |
"step": 240
|
| 297 |
},
|
| 298 |
{
|
| 299 |
+
"epoch": 0.51,
|
| 300 |
+
"learning_rate": 0.00013718704792856656,
|
| 301 |
+
"loss": 0.6711,
|
| 302 |
"step": 245
|
| 303 |
},
|
| 304 |
{
|
| 305 |
+
"epoch": 0.52,
|
| 306 |
+
"learning_rate": 0.000137107914091944,
|
| 307 |
+
"loss": 0.786,
|
| 308 |
"step": 250
|
| 309 |
},
|
| 310 |
{
|
| 311 |
+
"epoch": 0.53,
|
| 312 |
+
"learning_rate": 0.00013695692491376736,
|
| 313 |
+
"loss": 0.7021,
|
| 314 |
"step": 255
|
| 315 |
},
|
| 316 |
{
|
| 317 |
+
"epoch": 0.54,
|
| 318 |
+
"learning_rate": 0.00013673423876083446,
|
| 319 |
+
"loss": 1.0258,
|
| 320 |
"step": 260
|
| 321 |
},
|
| 322 |
{
|
| 323 |
+
"epoch": 0.55,
|
| 324 |
+
"learning_rate": 0.0001364400892001687,
|
| 325 |
+
"loss": 1.2098,
|
| 326 |
"step": 265
|
| 327 |
},
|
| 328 |
{
|
| 329 |
+
"epoch": 0.56,
|
| 330 |
+
"learning_rate": 0.00013607478475403945,
|
| 331 |
+
"loss": 1.0657,
|
| 332 |
"step": 270
|
| 333 |
},
|
| 334 |
{
|
| 335 |
+
"epoch": 0.57,
|
| 336 |
+
"learning_rate": 0.00013563870857636603,
|
| 337 |
+
"loss": 0.664,
|
| 338 |
"step": 275
|
| 339 |
},
|
| 340 |
{
|
| 341 |
+
"epoch": 0.58,
|
| 342 |
+
"learning_rate": 0.00013513231805083994,
|
| 343 |
+
"loss": 0.8538,
|
| 344 |
"step": 280
|
| 345 |
},
|
| 346 |
{
|
| 347 |
+
"epoch": 0.59,
|
| 348 |
+
"learning_rate": 0.00013455614431119578,
|
| 349 |
+
"loss": 0.8278,
|
| 350 |
"step": 285
|
| 351 |
},
|
| 352 |
{
|
| 353 |
+
"epoch": 0.6,
|
| 354 |
+
"learning_rate": 0.00013391079168412009,
|
| 355 |
+
"loss": 0.6271,
|
| 356 |
"step": 290
|
| 357 |
},
|
| 358 |
{
|
| 359 |
+
"epoch": 0.61,
|
| 360 |
+
"learning_rate": 0.00013319693705540213,
|
| 361 |
+
"loss": 0.9119,
|
| 362 |
"step": 295
|
| 363 |
},
|
| 364 |
{
|
| 365 |
+
"epoch": 0.62,
|
| 366 |
+
"learning_rate": 0.00013241532915997056,
|
| 367 |
+
"loss": 0.5942,
|
| 368 |
"step": 300
|
| 369 |
},
|
| 370 |
{
|
| 371 |
+
"epoch": 0.63,
|
| 372 |
+
"learning_rate": 0.0001315667877965762,
|
| 373 |
+
"loss": 0.8013,
|
| 374 |
"step": 305
|
| 375 |
},
|
| 376 |
{
|
| 377 |
+
"epoch": 0.64,
|
| 378 |
+
"learning_rate": 0.00013065220296793026,
|
| 379 |
+
"loss": 0.6856,
|
| 380 |
"step": 310
|
| 381 |
},
|
| 382 |
{
|
| 383 |
+
"epoch": 0.65,
|
| 384 |
+
"learning_rate": 0.00012967253394722351,
|
| 385 |
+
"loss": 0.8229,
|
| 386 |
"step": 315
|
| 387 |
},
|
| 388 |
{
|
| 389 |
+
"epoch": 0.66,
|
| 390 |
+
"learning_rate": 0.0001286288082719761,
|
| 391 |
+
"loss": 0.9531,
|
| 392 |
"step": 320
|
| 393 |
},
|
| 394 |
{
|
| 395 |
+
"epoch": 0.67,
|
| 396 |
+
"learning_rate": 0.00012752212066629144,
|
| 397 |
+
"loss": 1.3199,
|
| 398 |
"step": 325
|
| 399 |
},
|
| 400 |
{
|
| 401 |
+
"epoch": 0.68,
|
| 402 |
+
"learning_rate": 0.00012635363189264417,
|
| 403 |
+
"loss": 1.1022,
|
| 404 |
"step": 330
|
| 405 |
},
|
| 406 |
{
|
| 407 |
+
"epoch": 0.69,
|
| 408 |
+
"learning_rate": 0.00012512456753439896,
|
| 409 |
+
"loss": 0.9544,
|
| 410 |
"step": 335
|
| 411 |
},
|
| 412 |
{
|
| 413 |
+
"epoch": 0.7,
|
| 414 |
+
"learning_rate": 0.00012383621671034582,
|
| 415 |
+
"loss": 0.9981,
|
| 416 |
"step": 340
|
| 417 |
},
|
| 418 |
{
|
| 419 |
+
"epoch": 0.71,
|
| 420 |
+
"learning_rate": 0.00012248993072259197,
|
| 421 |
+
"loss": 0.8137,
|
| 422 |
"step": 345
|
| 423 |
},
|
| 424 |
{
|
| 425 |
+
"epoch": 0.72,
|
| 426 |
+
"learning_rate": 0.00012108712163922375,
|
| 427 |
+
"loss": 0.9984,
|
| 428 |
"step": 350
|
| 429 |
},
|
| 430 |
{
|
| 431 |
+
"epoch": 0.73,
|
| 432 |
+
"learning_rate": 0.00011962926081325661,
|
| 433 |
+
"loss": 1.0316,
|
| 434 |
"step": 355
|
| 435 |
},
|
| 436 |
{
|
| 437 |
+
"epoch": 0.74,
|
| 438 |
+
"learning_rate": 0.0001181178773393795,
|
| 439 |
+
"loss": 0.8207,
|
| 440 |
"step": 360
|
| 441 |
},
|
| 442 |
{
|
| 443 |
+
"epoch": 0.75,
|
| 444 |
+
"learning_rate": 0.00011655455645015076,
|
| 445 |
+
"loss": 0.6663,
|
| 446 |
"step": 365
|
| 447 |
},
|
| 448 |
{
|
| 449 |
+
"epoch": 0.76,
|
| 450 |
+
"learning_rate": 0.00011494093785329717,
|
| 451 |
+
"loss": 0.8862,
|
| 452 |
"step": 370
|
| 453 |
},
|
| 454 |
{
|
| 455 |
+
"epoch": 0.77,
|
| 456 |
+
"learning_rate": 0.00011327871401190472,
|
| 457 |
+
"loss": 0.7749,
|
| 458 |
"step": 375
|
| 459 |
},
|
| 460 |
{
|
| 461 |
+
"epoch": 0.78,
|
| 462 |
+
"learning_rate": 0.00011156962836924195,
|
| 463 |
+
"loss": 1.0212,
|
| 464 |
"step": 380
|
| 465 |
},
|
| 466 |
{
|
| 467 |
+
"epoch": 0.79,
|
| 468 |
+
"learning_rate": 0.0001098154735201431,
|
| 469 |
+
"loss": 0.9901,
|
| 470 |
"step": 385
|
| 471 |
},
|
| 472 |
{
|
| 473 |
+
"epoch": 0.8,
|
| 474 |
+
"learning_rate": 0.00010801808933080577,
|
| 475 |
+
"loss": 0.6503,
|
| 476 |
"step": 390
|
| 477 |
},
|
| 478 |
{
|
| 479 |
+
"epoch": 0.81,
|
| 480 |
+
"learning_rate": 0.0001061793610090449,
|
| 481 |
+
"loss": 0.9526,
|
| 482 |
"step": 395
|
| 483 |
},
|
| 484 |
{
|
| 485 |
+
"epoch": 0.82,
|
| 486 |
+
"learning_rate": 0.00010430121712695815,
|
| 487 |
+
"loss": 0.9911,
|
| 488 |
"step": 400
|
| 489 |
},
|
| 490 |
{
|
| 491 |
+
"epoch": 0.84,
|
| 492 |
+
"learning_rate": 0.00010238562759812645,
|
| 493 |
+
"loss": 0.8466,
|
| 494 |
"step": 405
|
| 495 |
},
|
| 496 |
{
|
| 497 |
+
"epoch": 0.85,
|
| 498 |
+
"learning_rate": 0.00010043460161143304,
|
| 499 |
+
"loss": 0.8538,
|
| 500 |
"step": 410
|
| 501 |
},
|
| 502 |
{
|
| 503 |
+
"epoch": 0.86,
|
| 504 |
+
"learning_rate": 9.845018552372211e-05,
|
| 505 |
+
"loss": 1.0898,
|
| 506 |
"step": 415
|
| 507 |
},
|
| 508 |
{
|
| 509 |
+
"epoch": 0.87,
|
| 510 |
+
"learning_rate": 9.643446071344141e-05,
|
| 511 |
+
"loss": 0.6029,
|
| 512 |
"step": 420
|
| 513 |
},
|
| 514 |
{
|
| 515 |
+
"epoch": 0.88,
|
| 516 |
+
"learning_rate": 9.438954139756169e-05,
|
| 517 |
+
"loss": 0.6565,
|
| 518 |
"step": 425
|
| 519 |
},
|
| 520 |
{
|
| 521 |
+
"epoch": 0.89,
|
| 522 |
+
"learning_rate": 9.231757241406026e-05,
|
| 523 |
+
"loss": 0.9035,
|
| 524 |
"step": 430
|
| 525 |
},
|
| 526 |
{
|
| 527 |
+
"epoch": 0.9,
|
| 528 |
+
"learning_rate": 9.022072697227865e-05,
|
| 529 |
+
"loss": 0.6143,
|
| 530 |
"step": 435
|
| 531 |
},
|
| 532 |
{
|
| 533 |
+
"epoch": 0.91,
|
| 534 |
+
"learning_rate": 8.810120437353156e-05,
|
| 535 |
+
"loss": 0.7718,
|
| 536 |
"step": 440
|
| 537 |
},
|
| 538 |
{
|
| 539 |
+
"epoch": 0.92,
|
| 540 |
+
"learning_rate": 8.596122770434176e-05,
|
| 541 |
+
"loss": 0.9339,
|
| 542 |
"step": 445
|
| 543 |
},
|
| 544 |
{
|
| 545 |
+
"epoch": 0.93,
|
| 546 |
+
"learning_rate": 8.380304150471618e-05,
|
| 547 |
+
"loss": 0.6168,
|
| 548 |
"step": 450
|
| 549 |
},
|
| 550 |
{
|
| 551 |
+
"epoch": 0.94,
|
| 552 |
+
"learning_rate": 8.162890941395579e-05,
|
| 553 |
+
"loss": 0.917,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 554 |
"step": 455
|
| 555 |
},
|
| 556 |
{
|
| 557 |
+
"epoch": 0.95,
|
| 558 |
+
"learning_rate": 7.944111179639565e-05,
|
| 559 |
+
"loss": 0.9396,
|
| 560 |
"step": 460
|
| 561 |
},
|
| 562 |
{
|
| 563 |
+
"epoch": 0.96,
|
| 564 |
+
"learning_rate": 7.724194334962525e-05,
|
| 565 |
+
"loss": 0.8879,
|
| 566 |
"step": 465
|
| 567 |
},
|
| 568 |
{
|
| 569 |
+
"epoch": 0.97,
|
| 570 |
+
"learning_rate": 7.50337106976521e-05,
|
| 571 |
+
"loss": 0.7428,
|
| 572 |
"step": 470
|
| 573 |
},
|
| 574 |
{
|
| 575 |
+
"epoch": 0.98,
|
| 576 |
+
"learning_rate": 7.281872997159678e-05,
|
| 577 |
+
"loss": 0.8685,
|
| 578 |
"step": 475
|
| 579 |
},
|
| 580 |
{
|
| 581 |
+
"epoch": 0.99,
|
| 582 |
+
"learning_rate": 7.059932438036807e-05,
|
| 583 |
+
"loss": 0.6925,
|
| 584 |
"step": 480
|
| 585 |
},
|
| 586 |
{
|
| 587 |
+
"epoch": 1.0,
|
| 588 |
+
"learning_rate": 6.837782177395701e-05,
|
| 589 |
+
"loss": 0.7737,
|
| 590 |
"step": 485
|
| 591 |
},
|
| 592 |
{
|
| 593 |
+
"epoch": 1.0,
|
| 594 |
+
"eval_loss": 0.8009498715400696,
|
| 595 |
+
"eval_runtime": 7.9645,
|
| 596 |
+
"eval_samples_per_second": 81.487,
|
| 597 |
+
"eval_steps_per_second": 10.296,
|
| 598 |
+
"step": 485
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.01,
|
| 602 |
+
"learning_rate": 6.615655220182037e-05,
|
| 603 |
+
"loss": 0.9648,
|
| 604 |
"step": 490
|
| 605 |
},
|
| 606 |
{
|
| 607 |
+
"epoch": 1.02,
|
| 608 |
+
"learning_rate": 6.393784546900578e-05,
|
| 609 |
+
"loss": 0.7027,
|
| 610 |
"step": 495
|
| 611 |
},
|
| 612 |
{
|
| 613 |
+
"epoch": 1.03,
|
| 614 |
+
"learning_rate": 6.172402869249251e-05,
|
| 615 |
+
"loss": 0.6923,
|
| 616 |
"step": 500
|
| 617 |
},
|
| 618 |
{
|
| 619 |
+
"epoch": 1.04,
|
| 620 |
+
"learning_rate": 5.9517423860374716e-05,
|
| 621 |
+
"loss": 0.6036,
|
| 622 |
"step": 505
|
| 623 |
},
|
| 624 |
{
|
| 625 |
+
"epoch": 1.05,
|
| 626 |
+
"learning_rate": 5.7320345396401225e-05,
|
| 627 |
+
"loss": 0.5738,
|
| 628 |
"step": 510
|
| 629 |
},
|
| 630 |
{
|
| 631 |
+
"epoch": 1.06,
|
| 632 |
+
"learning_rate": 5.5135097732487806e-05,
|
| 633 |
+
"loss": 0.522,
|
| 634 |
"step": 515
|
| 635 |
},
|
| 636 |
{
|
| 637 |
+
"epoch": 1.07,
|
| 638 |
+
"learning_rate": 5.2963972891672695e-05,
|
| 639 |
+
"loss": 0.6331,
|
| 640 |
"step": 520
|
| 641 |
},
|
| 642 |
{
|
| 643 |
+
"epoch": 1.08,
|
| 644 |
+
"learning_rate": 5.080924808409912e-05,
|
| 645 |
+
"loss": 0.8264,
|
| 646 |
"step": 525
|
| 647 |
},
|
| 648 |
{
|
| 649 |
+
"epoch": 1.09,
|
| 650 |
+
"learning_rate": 4.867318331854207e-05,
|
| 651 |
+
"loss": 0.5139,
|
| 652 |
"step": 530
|
| 653 |
},
|
| 654 |
{
|
| 655 |
+
"epoch": 1.1,
|
| 656 |
+
"learning_rate": 4.655801903196737e-05,
|
| 657 |
+
"loss": 0.4191,
|
| 658 |
"step": 535
|
| 659 |
},
|
| 660 |
{
|
| 661 |
+
"epoch": 1.11,
|
| 662 |
+
"learning_rate": 4.4465973739628306e-05,
|
| 663 |
+
"loss": 0.7371,
|
| 664 |
"step": 540
|
| 665 |
},
|
| 666 |
{
|
| 667 |
+
"epoch": 1.12,
|
| 668 |
+
"learning_rate": 4.239924170814745e-05,
|
| 669 |
+
"loss": 0.7683,
|
| 670 |
"step": 545
|
| 671 |
},
|
| 672 |
{
|
| 673 |
+
"epoch": 1.13,
|
| 674 |
+
"learning_rate": 4.0359990654021446e-05,
|
| 675 |
+
"loss": 0.6885,
|
| 676 |
"step": 550
|
| 677 |
},
|
| 678 |
{
|
| 679 |
+
"epoch": 1.14,
|
| 680 |
+
"learning_rate": 3.835035947000743e-05,
|
| 681 |
+
"loss": 0.573,
|
| 682 |
"step": 555
|
| 683 |
},
|
| 684 |
{
|
| 685 |
+
"epoch": 1.15,
|
| 686 |
+
"learning_rate": 3.6372455981705394e-05,
|
| 687 |
+
"loss": 0.5655,
|
| 688 |
"step": 560
|
| 689 |
},
|
| 690 |
{
|
| 691 |
+
"epoch": 1.16,
|
| 692 |
+
"learning_rate": 3.442835473674722e-05,
|
| 693 |
+
"loss": 0.6614,
|
| 694 |
"step": 565
|
| 695 |
},
|
| 696 |
{
|
| 697 |
+
"epoch": 1.18,
|
| 698 |
+
"learning_rate": 3.2520094828869116e-05,
|
| 699 |
+
"loss": 0.553,
|
| 700 |
"step": 570
|
| 701 |
},
|
| 702 |
{
|
| 703 |
+
"epoch": 1.19,
|
| 704 |
+
"learning_rate": 3.064967775920593e-05,
|
| 705 |
+
"loss": 0.9856,
|
| 706 |
"step": 575
|
| 707 |
},
|
| 708 |
{
|
| 709 |
+
"epoch": 1.2,
|
| 710 |
+
"learning_rate": 2.881906533697264e-05,
|
| 711 |
+
"loss": 0.7987,
|
| 712 |
"step": 580
|
| 713 |
},
|
| 714 |
{
|
| 715 |
+
"epoch": 1.21,
|
| 716 |
+
"learning_rate": 2.7030177621813776e-05,
|
| 717 |
+
"loss": 0.4053,
|
| 718 |
"step": 585
|
| 719 |
},
|
| 720 |
{
|
| 721 |
+
"epoch": 1.22,
|
| 722 |
+
"learning_rate": 2.5284890909906917e-05,
|
| 723 |
+
"loss": 0.5987,
|
| 724 |
"step": 590
|
| 725 |
},
|
| 726 |
{
|
| 727 |
+
"epoch": 1.23,
|
| 728 |
+
"learning_rate": 2.3585035766007593e-05,
|
| 729 |
+
"loss": 0.9376,
|
| 730 |
"step": 595
|
| 731 |
},
|
| 732 |
{
|
| 733 |
+
"epoch": 1.24,
|
| 734 |
+
"learning_rate": 2.1932395103427002e-05,
|
| 735 |
+
"loss": 0.6322,
|
| 736 |
"step": 600
|
| 737 |
},
|
| 738 |
{
|
| 739 |
+
"epoch": 1.25,
|
| 740 |
+
"learning_rate": 2.032870231400813e-05,
|
| 741 |
+
"loss": 0.6378,
|
| 742 |
"step": 605
|
| 743 |
},
|
| 744 |
{
|
| 745 |
+
"epoch": 1.26,
|
| 746 |
+
"learning_rate": 1.8775639450025844e-05,
|
| 747 |
+
"loss": 0.5735,
|
| 748 |
"step": 610
|
| 749 |
},
|
| 750 |
{
|
| 751 |
+
"epoch": 1.27,
|
| 752 |
+
"learning_rate": 1.7274835459963273e-05,
|
| 753 |
+
"loss": 1.0382,
|
| 754 |
"step": 615
|
| 755 |
},
|
| 756 |
{
|
| 757 |
+
"epoch": 1.28,
|
| 758 |
+
"learning_rate": 1.582786447995969e-05,
|
| 759 |
+
"loss": 0.6316,
|
| 760 |
"step": 620
|
| 761 |
},
|
| 762 |
{
|
| 763 |
+
"epoch": 1.29,
|
| 764 |
+
"learning_rate": 1.4436244182758039e-05,
|
| 765 |
+
"loss": 0.6119,
|
| 766 |
"step": 625
|
| 767 |
},
|
| 768 |
{
|
| 769 |
+
"epoch": 1.3,
|
| 770 |
+
"learning_rate": 1.3101434185879816e-05,
|
| 771 |
+
"loss": 0.9124,
|
| 772 |
"step": 630
|
| 773 |
},
|
| 774 |
{
|
| 775 |
+
"epoch": 1.31,
|
| 776 |
+
"learning_rate": 1.1824834520685365e-05,
|
| 777 |
+
"loss": 0.5674,
|
| 778 |
"step": 635
|
| 779 |
},
|
| 780 |
{
|
| 781 |
+
"epoch": 1.32,
|
| 782 |
+
"learning_rate": 1.060778416393771e-05,
|
| 783 |
+
"loss": 0.8984,
|
| 784 |
"step": 640
|
| 785 |
},
|
| 786 |
{
|
| 787 |
+
"epoch": 1.33,
|
| 788 |
+
"learning_rate": 9.451559633399314e-06,
|
| 789 |
+
"loss": 0.4093,
|
| 790 |
"step": 645
|
| 791 |
},
|
| 792 |
{
|
| 793 |
+
"epoch": 1.34,
|
| 794 |
+
"learning_rate": 8.35737364893442e-06,
|
| 795 |
+
"loss": 1.0756,
|
| 796 |
"step": 650
|
| 797 |
},
|
| 798 |
{
|
| 799 |
+
"epoch": 1.35,
|
| 800 |
+
"learning_rate": 7.326373860545556e-06,
|
| 801 |
+
"loss": 0.7388,
|
| 802 |
"step": 655
|
| 803 |
},
|
| 804 |
{
|
| 805 |
+
"epoch": 1.36,
|
| 806 |
+
"learning_rate": 6.359641644638905e-06,
|
| 807 |
+
"loss": 0.7588,
|
| 808 |
"step": 660
|
| 809 |
},
|
| 810 |
{
|
| 811 |
+
"epoch": 1.37,
|
| 812 |
+
"learning_rate": 5.4581909698134475e-06,
|
| 813 |
+
"loss": 0.6298,
|
| 814 |
"step": 665
|
| 815 |
},
|
| 816 |
{
|
| 817 |
+
"epoch": 1.38,
|
| 818 |
+
"learning_rate": 4.622967333341646e-06,
|
| 819 |
+
"loss": 0.5269,
|
| 820 |
"step": 670
|
| 821 |
},
|
| 822 |
{
|
| 823 |
+
"epoch": 1.39,
|
| 824 |
+
"learning_rate": 3.854846769483559e-06,
|
| 825 |
+
"loss": 0.8377,
|
| 826 |
"step": 675
|
| 827 |
},
|
| 828 |
{
|
| 829 |
+
"epoch": 1.4,
|
| 830 |
+
"learning_rate": 3.1546349306387612e-06,
|
| 831 |
+
"loss": 0.5796,
|
| 832 |
"step": 680
|
| 833 |
},
|
| 834 |
{
|
| 835 |
+
"epoch": 1.41,
|
| 836 |
+
"learning_rate": 2.5230662423349877e-06,
|
| 837 |
+
"loss": 0.4994,
|
| 838 |
"step": 685
|
| 839 |
},
|
| 840 |
{
|
| 841 |
+
"epoch": 1.42,
|
| 842 |
+
"learning_rate": 1.9608031329100813e-06,
|
| 843 |
+
"loss": 0.659,
|
| 844 |
"step": 690
|
| 845 |
},
|
| 846 |
{
|
| 847 |
+
"epoch": 1.43,
|
| 848 |
+
"learning_rate": 1.4684353387235077e-06,
|
| 849 |
+
"loss": 0.5819,
|
| 850 |
"step": 695
|
| 851 |
},
|
| 852 |
{
|
| 853 |
+
"epoch": 1.44,
|
| 854 |
+
"learning_rate": 1.0464792855997834e-06,
|
| 855 |
+
"loss": 0.5023,
|
| 856 |
"step": 700
|
| 857 |
},
|
| 858 |
{
|
| 859 |
+
"epoch": 1.45,
|
| 860 |
+
"learning_rate": 6.953775471708487e-07,
|
| 861 |
+
"loss": 0.5082,
|
| 862 |
"step": 705
|
| 863 |
},
|
| 864 |
{
|
| 865 |
+
"epoch": 1.46,
|
| 866 |
+
"learning_rate": 4.154983806750897e-07,
|
| 867 |
+
"loss": 0.6839,
|
| 868 |
"step": 710
|
| 869 |
},
|
| 870 |
{
|
| 871 |
+
"epoch": 1.47,
|
| 872 |
+
"learning_rate": 2.071353407100288e-07,
|
| 873 |
+
"loss": 0.7121,
|
| 874 |
"step": 715
|
| 875 |
},
|
| 876 |
{
|
| 877 |
+
"epoch": 1.48,
|
| 878 |
+
"learning_rate": 7.050697133161242e-08,
|
| 879 |
+
"loss": 0.4166,
|
| 880 |
"step": 720
|
| 881 |
},
|
| 882 |
{
|
| 883 |
+
"epoch": 1.49,
|
| 884 |
+
"learning_rate": 5.756576831951343e-09,
|
| 885 |
+
"loss": 0.7094,
|
| 886 |
"step": 725
|
| 887 |
},
|
| 888 |
{
|
| 889 |
+
"epoch": 1.51,
|
| 890 |
+
"learning_rate": 1.295207143343513e-08,
|
| 891 |
+
"loss": 0.6831,
|
| 892 |
"step": 730
|
| 893 |
},
|
| 894 |
{
|
| 895 |
+
"epoch": 1.52,
|
| 896 |
+
"learning_rate": 9.208590805595201e-08,
|
| 897 |
+
"loss": 0.6554,
|
| 898 |
"step": 735
|
| 899 |
},
|
| 900 |
{
|
| 901 |
+
"epoch": 1.53,
|
| 902 |
+
"learning_rate": 2.4307508623258407e-07,
|
| 903 |
+
"loss": 0.3354,
|
| 904 |
"step": 740
|
| 905 |
},
|
| 906 |
{
|
| 907 |
+
"epoch": 1.54,
|
| 908 |
+
"learning_rate": 4.657612391656818e-07,
|
| 909 |
+
"loss": 0.4874,
|
| 910 |
"step": 745
|
| 911 |
},
|
| 912 |
{
|
| 913 |
+
"epoch": 1.55,
|
| 914 |
+
"learning_rate": 7.59910799831185e-07,
|
| 915 |
+
"loss": 0.6073,
|
| 916 |
"step": 750
|
| 917 |
},
|
| 918 |
{
|
| 919 |
+
"epoch": 1.56,
|
| 920 |
+
"learning_rate": 1.1252152459604225e-06,
|
| 921 |
+
"loss": 0.8413,
|
| 922 |
"step": 755
|
| 923 |
},
|
| 924 |
{
|
| 925 |
+
"epoch": 1.57,
|
| 926 |
+
"learning_rate": 1.5612914236342025e-06,
|
| 927 |
+
"loss": 0.3873,
|
| 928 |
"step": 760
|
| 929 |
},
|
| 930 |
{
|
| 931 |
+
"epoch": 1.58,
|
| 932 |
+
"learning_rate": 2.0676819491598904e-06,
|
| 933 |
+
"loss": 0.7879,
|
| 934 |
"step": 765
|
| 935 |
},
|
| 936 |
{
|
| 937 |
+
"epoch": 1.59,
|
| 938 |
+
"learning_rate": 2.643855688804542e-06,
|
| 939 |
+
"loss": 0.6646,
|
| 940 |
"step": 770
|
| 941 |
},
|
| 942 |
{
|
| 943 |
+
"epoch": 1.6,
|
| 944 |
+
"learning_rate": 3.2892083158796966e-06,
|
| 945 |
+
"loss": 0.5732,
|
| 946 |
"step": 775
|
| 947 |
},
|
| 948 |
{
|
| 949 |
+
"epoch": 1.61,
|
| 950 |
+
"learning_rate": 4.003062944597618e-06,
|
| 951 |
+
"loss": 0.5925,
|
| 952 |
"step": 780
|
| 953 |
},
|
| 954 |
{
|
| 955 |
+
"epoch": 1.62,
|
| 956 |
+
"learning_rate": 4.784670840029167e-06,
|
| 957 |
+
"loss": 0.5607,
|
| 958 |
"step": 785
|
| 959 |
},
|
| 960 |
{
|
| 961 |
+
"epoch": 1.63,
|
| 962 |
+
"learning_rate": 5.63321220342353e-06,
|
| 963 |
+
"loss": 0.7195,
|
| 964 |
"step": 790
|
| 965 |
},
|
| 966 |
{
|
| 967 |
+
"epoch": 1.64,
|
| 968 |
+
"learning_rate": 6.547797032069429e-06,
|
| 969 |
+
"loss": 0.4434,
|
| 970 |
"step": 795
|
| 971 |
},
|
| 972 |
{
|
| 973 |
+
"epoch": 1.65,
|
| 974 |
+
"learning_rate": 7.527466052776141e-06,
|
| 975 |
+
"loss": 0.6778,
|
| 976 |
"step": 800
|
| 977 |
},
|
| 978 |
{
|
| 979 |
+
"epoch": 1.66,
|
| 980 |
+
"learning_rate": 8.571191728024455e-06,
|
| 981 |
+
"loss": 0.7627,
|
| 982 |
"step": 805
|
| 983 |
},
|
| 984 |
{
|
| 985 |
+
"epoch": 1.67,
|
| 986 |
+
"learning_rate": 9.677879333708184e-06,
|
| 987 |
+
"loss": 0.7002,
|
| 988 |
"step": 810
|
| 989 |
},
|
| 990 |
{
|
| 991 |
+
"epoch": 1.68,
|
| 992 |
+
"learning_rate": 1.0846368107356494e-05,
|
| 993 |
+
"loss": 0.5221,
|
| 994 |
"step": 815
|
| 995 |
},
|
| 996 |
{
|
| 997 |
+
"epoch": 1.69,
|
| 998 |
+
"learning_rate": 1.2075432465600628e-05,
|
| 999 |
+
"loss": 0.5574,
|
| 1000 |
"step": 820
|
| 1001 |
},
|
| 1002 |
{
|
| 1003 |
+
"epoch": 1.7,
|
| 1004 |
+
"learning_rate": 1.336378328965373e-05,
|
| 1005 |
+
"loss": 0.7088,
|
| 1006 |
"step": 825
|
| 1007 |
},
|
| 1008 |
{
|
| 1009 |
+
"epoch": 1.71,
|
| 1010 |
+
"learning_rate": 1.4710069277408788e-05,
|
| 1011 |
+
"loss": 0.7595,
|
| 1012 |
"step": 830
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
+
"epoch": 1.72,
|
| 1016 |
+
"learning_rate": 1.6112878360775777e-05,
|
| 1017 |
+
"loss": 0.3203,
|
| 1018 |
"step": 835
|
| 1019 |
},
|
| 1020 |
{
|
| 1021 |
+
"epoch": 1.73,
|
| 1022 |
+
"learning_rate": 1.7570739186742892e-05,
|
| 1023 |
+
"loss": 0.5597,
|
| 1024 |
"step": 840
|
| 1025 |
},
|
| 1026 |
{
|
| 1027 |
+
"epoch": 1.74,
|
| 1028 |
+
"learning_rate": 1.9082122660619998e-05,
|
| 1029 |
+
"loss": 0.5739,
|
| 1030 |
"step": 845
|
| 1031 |
},
|
| 1032 |
{
|
| 1033 |
+
"epoch": 1.75,
|
| 1034 |
+
"learning_rate": 2.0645443549848698e-05,
|
| 1035 |
+
"loss": 0.531,
|
| 1036 |
"step": 850
|
| 1037 |
},
|
| 1038 |
{
|
| 1039 |
+
"epoch": 1.76,
|
| 1040 |
+
"learning_rate": 2.2259062146702276e-05,
|
| 1041 |
+
"loss": 0.5565,
|
| 1042 |
"step": 855
|
| 1043 |
},
|
| 1044 |
{
|
| 1045 |
+
"epoch": 1.77,
|
| 1046 |
+
"learning_rate": 2.392128598809619e-05,
|
| 1047 |
+
"loss": 0.7898,
|
| 1048 |
"step": 860
|
| 1049 |
},
|
| 1050 |
{
|
| 1051 |
+
"epoch": 1.78,
|
| 1052 |
+
"learning_rate": 2.5630371630759003e-05,
|
| 1053 |
+
"loss": 0.8282,
|
| 1054 |
"step": 865
|
| 1055 |
},
|
| 1056 |
{
|
| 1057 |
+
"epoch": 1.79,
|
| 1058 |
+
"learning_rate": 2.7384526479857852e-05,
|
| 1059 |
+
"loss": 0.6593,
|
| 1060 |
"step": 870
|
| 1061 |
},
|
| 1062 |
{
|
| 1063 |
+
"epoch": 1.8,
|
| 1064 |
+
"learning_rate": 2.9181910669195226e-05,
|
| 1065 |
+
"loss": 0.5809,
|
| 1066 |
"step": 875
|
| 1067 |
},
|
| 1068 |
{
|
| 1069 |
+
"epoch": 1.81,
|
| 1070 |
+
"learning_rate": 3.102063899095449e-05,
|
| 1071 |
+
"loss": 0.5236,
|
| 1072 |
"step": 880
|
| 1073 |
},
|
| 1074 |
{
|
| 1075 |
+
"epoch": 1.82,
|
| 1076 |
+
"learning_rate": 3.289878287304121e-05,
|
| 1077 |
+
"loss": 0.8349,
|
| 1078 |
"step": 885
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
+
"epoch": 1.84,
|
| 1082 |
+
"learning_rate": 3.481437240187291e-05,
|
| 1083 |
+
"loss": 0.5913,
|
| 1084 |
"step": 890
|
| 1085 |
},
|
| 1086 |
{
|
| 1087 |
+
"epoch": 1.85,
|
| 1088 |
+
"learning_rate": 3.6765398388566315e-05,
|
| 1089 |
+
"loss": 0.7902,
|
| 1090 |
"step": 895
|
| 1091 |
},
|
| 1092 |
{
|
| 1093 |
+
"epoch": 1.86,
|
| 1094 |
+
"learning_rate": 3.874981447627722e-05,
|
| 1095 |
+
"loss": 0.447,
|
| 1096 |
"step": 900
|
| 1097 |
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.87,
|
| 1100 |
+
"learning_rate": 4.076553928655969e-05,
|
| 1101 |
+
"loss": 0.5064,
|
| 1102 |
+
"step": 905
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.88,
|
| 1106 |
+
"learning_rate": 4.281045860243763e-05,
|
| 1107 |
+
"loss": 0.6135,
|
| 1108 |
+
"step": 910
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.89,
|
| 1112 |
+
"learning_rate": 4.4882427585940885e-05,
|
| 1113 |
+
"loss": 0.7355,
|
| 1114 |
+
"step": 915
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.9,
|
| 1118 |
+
"learning_rate": 4.69792730277225e-05,
|
| 1119 |
+
"loss": 0.6229,
|
| 1120 |
+
"step": 920
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 1.91,
|
| 1124 |
+
"learning_rate": 4.909879562646775e-05,
|
| 1125 |
+
"loss": 0.5816,
|
| 1126 |
+
"step": 925
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.92,
|
| 1130 |
+
"learning_rate": 5.123877229565941e-05,
|
| 1131 |
+
"loss": 0.558,
|
| 1132 |
+
"step": 930
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 1.93,
|
| 1136 |
+
"learning_rate": 5.3396958495283104e-05,
|
| 1137 |
+
"loss": 0.5434,
|
| 1138 |
+
"step": 935
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 1.94,
|
| 1142 |
+
"learning_rate": 5.557109058604349e-05,
|
| 1143 |
+
"loss": 0.7625,
|
| 1144 |
+
"step": 940
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.95,
|
| 1148 |
+
"learning_rate": 5.7758888203603614e-05,
|
| 1149 |
+
"loss": 0.6406,
|
| 1150 |
+
"step": 945
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.96,
|
| 1154 |
+
"learning_rate": 5.9958056650374005e-05,
|
| 1155 |
+
"loss": 0.6691,
|
| 1156 |
+
"step": 950
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 1.97,
|
| 1160 |
+
"learning_rate": 6.216628930234716e-05,
|
| 1161 |
+
"loss": 0.6314,
|
| 1162 |
+
"step": 955
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 1.98,
|
| 1166 |
+
"learning_rate": 6.438127002840443e-05,
|
| 1167 |
+
"loss": 0.7209,
|
| 1168 |
+
"step": 960
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 1.99,
|
| 1172 |
+
"learning_rate": 6.660067561963313e-05,
|
| 1173 |
+
"loss": 0.5188,
|
| 1174 |
+
"step": 965
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 2.0,
|
| 1178 |
+
"learning_rate": 6.882217822604419e-05,
|
| 1179 |
+
"loss": 0.5676,
|
| 1180 |
+
"step": 970
|
| 1181 |
+
},
|
| 1182 |
{
|
| 1183 |
"epoch": 2.0,
|
| 1184 |
+
"eval_loss": 0.8053014278411865,
|
| 1185 |
+
"eval_runtime": 7.9895,
|
| 1186 |
+
"eval_samples_per_second": 81.231,
|
| 1187 |
+
"eval_steps_per_second": 10.263,
|
| 1188 |
+
"step": 970
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 2.01,
|
| 1192 |
+
"learning_rate": 7.104344779818084e-05,
|
| 1193 |
+
"loss": 0.8119,
|
| 1194 |
+
"step": 975
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.02,
|
| 1198 |
+
"learning_rate": 7.326215453099347e-05,
|
| 1199 |
+
"loss": 0.8241,
|
| 1200 |
+
"step": 980
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.03,
|
| 1204 |
+
"learning_rate": 7.547597130750675e-05,
|
| 1205 |
+
"loss": 0.4897,
|
| 1206 |
+
"step": 985
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 2.04,
|
| 1210 |
+
"learning_rate": 7.768257613962455e-05,
|
| 1211 |
+
"loss": 0.7487,
|
| 1212 |
+
"step": 990
|
| 1213 |
+
},
|
| 1214 |
+
{
|
| 1215 |
+
"epoch": 2.05,
|
| 1216 |
+
"learning_rate": 7.987965460359805e-05,
|
| 1217 |
+
"loss": 0.7651,
|
| 1218 |
+
"step": 995
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 2.06,
|
| 1222 |
+
"learning_rate": 8.206490226751148e-05,
|
| 1223 |
+
"loss": 0.6692,
|
| 1224 |
+
"step": 1000
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 2.07,
|
| 1228 |
+
"learning_rate": 8.423602710832848e-05,
|
| 1229 |
+
"loss": 0.7985,
|
| 1230 |
+
"step": 1005
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 2.08,
|
| 1234 |
+
"learning_rate": 8.639075191590017e-05,
|
| 1235 |
+
"loss": 0.5855,
|
| 1236 |
+
"step": 1010
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 2.09,
|
| 1240 |
+
"learning_rate": 8.852681668145908e-05,
|
| 1241 |
+
"loss": 0.6353,
|
| 1242 |
+
"step": 1015
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.1,
|
| 1246 |
+
"learning_rate": 9.064198096803377e-05,
|
| 1247 |
+
"loss": 0.552,
|
| 1248 |
+
"step": 1020
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 2.11,
|
| 1252 |
+
"learning_rate": 9.273402626037102e-05,
|
| 1253 |
+
"loss": 0.4755,
|
| 1254 |
+
"step": 1025
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 2.12,
|
| 1258 |
+
"learning_rate": 9.480075829185367e-05,
|
| 1259 |
+
"loss": 0.6665,
|
| 1260 |
+
"step": 1030
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 2.13,
|
| 1264 |
+
"learning_rate": 9.684000934597788e-05,
|
| 1265 |
+
"loss": 0.3769,
|
| 1266 |
+
"step": 1035
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 2.14,
|
| 1270 |
+
"learning_rate": 9.884964052999192e-05,
|
| 1271 |
+
"loss": 0.6127,
|
| 1272 |
+
"step": 1040
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 2.15,
|
| 1276 |
+
"learning_rate": 0.00010082754401829396,
|
| 1277 |
+
"loss": 0.7927,
|
| 1278 |
+
"step": 1045
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 2.16,
|
| 1282 |
+
"learning_rate": 0.00010277164526325214,
|
| 1283 |
+
"loss": 0.5635,
|
| 1284 |
+
"step": 1050
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.18,
|
| 1288 |
+
"learning_rate": 0.00010467990517113026,
|
| 1289 |
+
"loss": 0.694,
|
| 1290 |
+
"step": 1055
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 2.19,
|
| 1294 |
+
"learning_rate": 0.00010655032224079507,
|
| 1295 |
+
"loss": 0.75,
|
| 1296 |
+
"step": 1060
|
| 1297 |
+
},
|
| 1298 |
+
{
|
| 1299 |
+
"epoch": 2.2,
|
| 1300 |
+
"learning_rate": 0.00010838093466302835,
|
| 1301 |
+
"loss": 0.4615,
|
| 1302 |
+
"step": 1065
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 2.21,
|
| 1306 |
+
"learning_rate": 0.00011016982237818718,
|
| 1307 |
+
"loss": 0.4177,
|
| 1308 |
+
"step": 1070
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 2.22,
|
| 1312 |
+
"learning_rate": 0.00011191510909009402,
|
| 1313 |
+
"loss": 0.7636,
|
| 1314 |
+
"step": 1075
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 2.23,
|
| 1318 |
+
"learning_rate": 0.00011361496423399185,
|
| 1319 |
+
"loss": 0.5608,
|
| 1320 |
+
"step": 1080
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.24,
|
| 1324 |
+
"learning_rate": 0.00011526760489657245,
|
| 1325 |
+
"loss": 0.4228,
|
| 1326 |
+
"step": 1085
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 2.25,
|
| 1330 |
+
"learning_rate": 0.00011687129768599134,
|
| 1331 |
+
"loss": 0.6887,
|
| 1332 |
+
"step": 1090
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 2.26,
|
| 1336 |
+
"learning_rate": 0.00011842436054997366,
|
| 1337 |
+
"loss": 0.4605,
|
| 1338 |
+
"step": 1095
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 2.27,
|
| 1342 |
+
"learning_rate": 0.00011992516454003623,
|
| 1343 |
+
"loss": 0.5089,
|
| 1344 |
+
"step": 1100
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 2.28,
|
| 1348 |
+
"learning_rate": 0.00012137213552004109,
|
| 1349 |
+
"loss": 0.7078,
|
| 1350 |
+
"step": 1105
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 2.29,
|
| 1354 |
+
"learning_rate": 0.00012276375581724152,
|
| 1355 |
+
"loss": 0.5178,
|
| 1356 |
+
"step": 1110
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 2.3,
|
| 1360 |
+
"learning_rate": 0.0001240985658141209,
|
| 1361 |
+
"loss": 0.6848,
|
| 1362 |
+
"step": 1115
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.31,
|
| 1366 |
+
"learning_rate": 0.0001253751654793153,
|
| 1367 |
+
"loss": 0.5177,
|
| 1368 |
+
"step": 1120
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 2.32,
|
| 1372 |
+
"learning_rate": 0.00012659221583606188,
|
| 1373 |
+
"loss": 0.8266,
|
| 1374 |
+
"step": 1125
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 2.33,
|
| 1378 |
+
"learning_rate": 0.0001277484403666013,
|
| 1379 |
+
"loss": 0.5183,
|
| 1380 |
+
"step": 1130
|
| 1381 |
+
},
|
| 1382 |
+
{
|
| 1383 |
+
"epoch": 2.34,
|
| 1384 |
+
"learning_rate": 0.00012884262635106522,
|
| 1385 |
+
"loss": 0.8944,
|
| 1386 |
+
"step": 1135
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 2.35,
|
| 1390 |
+
"learning_rate": 0.00012987362613945414,
|
| 1391 |
+
"loss": 0.8195,
|
| 1392 |
+
"step": 1140
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 2.36,
|
| 1396 |
+
"learning_rate": 0.00013084035835536078,
|
| 1397 |
+
"loss": 0.8404,
|
| 1398 |
+
"step": 1145
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 2.37,
|
| 1402 |
+
"learning_rate": 0.00013174180903018627,
|
| 1403 |
+
"loss": 0.6088,
|
| 1404 |
+
"step": 1150
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.38,
|
| 1408 |
+
"learning_rate": 0.00013257703266665808,
|
| 1409 |
+
"loss": 0.6745,
|
| 1410 |
+
"step": 1155
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 2.39,
|
| 1414 |
+
"learning_rate": 0.00013334515323051684,
|
| 1415 |
+
"loss": 0.6451,
|
| 1416 |
+
"step": 1160
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 2.4,
|
| 1420 |
+
"learning_rate": 0.0001340453650693616,
|
| 1421 |
+
"loss": 0.7023,
|
| 1422 |
+
"step": 1165
|
| 1423 |
+
},
|
| 1424 |
+
{
|
| 1425 |
+
"epoch": 2.41,
|
| 1426 |
+
"learning_rate": 0.00013467693375766531,
|
| 1427 |
+
"loss": 0.8257,
|
| 1428 |
+
"step": 1170
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 2.42,
|
| 1432 |
+
"learning_rate": 0.0001352391968670902,
|
| 1433 |
+
"loss": 0.5857,
|
| 1434 |
+
"step": 1175
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 2.43,
|
| 1438 |
+
"learning_rate": 0.00013573156466127633,
|
| 1439 |
+
"loss": 0.3617,
|
| 1440 |
+
"step": 1180
|
| 1441 |
+
},
|
| 1442 |
+
{
|
| 1443 |
+
"epoch": 2.44,
|
| 1444 |
+
"learning_rate": 0.0001361535207144001,
|
| 1445 |
+
"loss": 0.7152,
|
| 1446 |
+
"step": 1185
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 2.45,
|
| 1450 |
+
"learning_rate": 0.00013650462245282905,
|
| 1451 |
+
"loss": 0.7494,
|
| 1452 |
+
"step": 1190
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 2.46,
|
| 1456 |
+
"learning_rate": 0.0001367845016193248,
|
| 1457 |
+
"loss": 0.5441,
|
| 1458 |
+
"step": 1195
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 2.47,
|
| 1462 |
+
"learning_rate": 0.00013699286465928992,
|
| 1463 |
+
"loss": 0.916,
|
| 1464 |
+
"step": 1200
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 2.48,
|
| 1468 |
+
"learning_rate": 0.00013712949302866845,
|
| 1469 |
+
"loss": 0.6266,
|
| 1470 |
+
"step": 1205
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 2.49,
|
| 1474 |
+
"learning_rate": 0.00013719424342316803,
|
| 1475 |
+
"loss": 0.8704,
|
| 1476 |
+
"step": 1210
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 2.51,
|
| 1480 |
+
"learning_rate": 0.00013718704792856654,
|
| 1481 |
+
"loss": 0.6092,
|
| 1482 |
+
"step": 1215
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 2.52,
|
| 1486 |
+
"learning_rate": 0.00013710791409194398,
|
| 1487 |
+
"loss": 0.6756,
|
| 1488 |
+
"step": 1220
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 2.53,
|
| 1492 |
+
"learning_rate": 0.00013695692491376746,
|
| 1493 |
+
"loss": 0.6538,
|
| 1494 |
+
"step": 1225
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 2.54,
|
| 1498 |
+
"learning_rate": 0.0001367342387608344,
|
| 1499 |
+
"loss": 0.5702,
|
| 1500 |
+
"step": 1230
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 2.55,
|
| 1504 |
+
"learning_rate": 0.0001364400892001689,
|
| 1505 |
+
"loss": 0.8016,
|
| 1506 |
+
"step": 1235
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 2.56,
|
| 1510 |
+
"learning_rate": 0.00013607478475403972,
|
| 1511 |
+
"loss": 0.6645,
|
| 1512 |
+
"step": 1240
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 2.57,
|
| 1516 |
+
"learning_rate": 0.00013563870857636595,
|
| 1517 |
+
"loss": 0.9163,
|
| 1518 |
+
"step": 1245
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 2.58,
|
| 1522 |
+
"learning_rate": 0.0001351323180508398,
|
| 1523 |
+
"loss": 0.6785,
|
| 1524 |
+
"step": 1250
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 2.59,
|
| 1528 |
+
"learning_rate": 0.00013455614431119567,
|
| 1529 |
+
"loss": 0.7625,
|
| 1530 |
+
"step": 1255
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 2.6,
|
| 1534 |
+
"learning_rate": 0.00013391079168411995,
|
| 1535 |
+
"loss": 0.5317,
|
| 1536 |
+
"step": 1260
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 2.61,
|
| 1540 |
+
"learning_rate": 0.00013319693705540197,
|
| 1541 |
+
"loss": 0.6176,
|
| 1542 |
+
"step": 1265
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 2.62,
|
| 1546 |
+
"learning_rate": 0.0001324153291599711,
|
| 1547 |
+
"loss": 0.4044,
|
| 1548 |
+
"step": 1270
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 2.63,
|
| 1552 |
+
"learning_rate": 0.000131566787796576,
|
| 1553 |
+
"loss": 0.6815,
|
| 1554 |
+
"step": 1275
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 2.64,
|
| 1558 |
+
"learning_rate": 0.0001306522029679309,
|
| 1559 |
+
"loss": 0.7421,
|
| 1560 |
+
"step": 1280
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 2.65,
|
| 1564 |
+
"learning_rate": 0.0001296725339472242,
|
| 1565 |
+
"loss": 0.9262,
|
| 1566 |
+
"step": 1285
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"epoch": 2.66,
|
| 1570 |
+
"learning_rate": 0.00012862880827197592,
|
| 1571 |
+
"loss": 0.5789,
|
| 1572 |
+
"step": 1290
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 2.67,
|
| 1576 |
+
"learning_rate": 0.0001275221206662922,
|
| 1577 |
+
"loss": 0.6176,
|
| 1578 |
+
"step": 1295
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 2.68,
|
| 1582 |
+
"learning_rate": 0.00012635363189264392,
|
| 1583 |
+
"loss": 0.5932,
|
| 1584 |
+
"step": 1300
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 2.69,
|
| 1588 |
+
"learning_rate": 0.00012512456753439868,
|
| 1589 |
+
"loss": 0.5771,
|
| 1590 |
+
"step": 1305
|
| 1591 |
+
},
|
| 1592 |
+
{
|
| 1593 |
+
"epoch": 2.7,
|
| 1594 |
+
"learning_rate": 0.00012383621671034555,
|
| 1595 |
+
"loss": 0.5197,
|
| 1596 |
+
"step": 1310
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 2.71,
|
| 1600 |
+
"learning_rate": 0.00012248993072259167,
|
| 1601 |
+
"loss": 0.5347,
|
| 1602 |
+
"step": 1315
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 2.72,
|
| 1606 |
+
"learning_rate": 0.00012108712163922345,
|
| 1607 |
+
"loss": 0.7577,
|
| 1608 |
+
"step": 1320
|
| 1609 |
+
},
|
| 1610 |
+
{
|
| 1611 |
+
"epoch": 2.73,
|
| 1612 |
+
"learning_rate": 0.0001196292608132576,
|
| 1613 |
+
"loss": 0.6237,
|
| 1614 |
+
"step": 1325
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.74,
|
| 1618 |
+
"learning_rate": 0.00011811787733938051,
|
| 1619 |
+
"loss": 0.9522,
|
| 1620 |
+
"step": 1330
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.75,
|
| 1624 |
+
"learning_rate": 0.00011655455645015182,
|
| 1625 |
+
"loss": 0.6511,
|
| 1626 |
+
"step": 1335
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 2.76,
|
| 1630 |
+
"learning_rate": 0.00011494093785329826,
|
| 1631 |
+
"loss": 0.7683,
|
| 1632 |
+
"step": 1340
|
| 1633 |
+
},
|
| 1634 |
+
{
|
| 1635 |
+
"epoch": 2.77,
|
| 1636 |
+
"learning_rate": 0.00011327871401190438,
|
| 1637 |
+
"loss": 0.8408,
|
| 1638 |
+
"step": 1345
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 2.78,
|
| 1642 |
+
"learning_rate": 0.00011156962836924156,
|
| 1643 |
+
"loss": 0.7132,
|
| 1644 |
+
"step": 1350
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 2.79,
|
| 1648 |
+
"learning_rate": 0.00010981547352014274,
|
| 1649 |
+
"loss": 0.7741,
|
| 1650 |
+
"step": 1355
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 2.8,
|
| 1654 |
+
"learning_rate": 0.00010801808933080536,
|
| 1655 |
+
"loss": 0.6007,
|
| 1656 |
+
"step": 1360
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 2.81,
|
| 1660 |
+
"learning_rate": 0.0001061793610090445,
|
| 1661 |
+
"loss": 0.7367,
|
| 1662 |
+
"step": 1365
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.82,
|
| 1666 |
+
"learning_rate": 0.00010430121712695943,
|
| 1667 |
+
"loss": 0.7996,
|
| 1668 |
+
"step": 1370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 2.84,
|
| 1672 |
+
"learning_rate": 0.00010238562759812602,
|
| 1673 |
+
"loss": 0.5623,
|
| 1674 |
+
"step": 1375
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 2.85,
|
| 1678 |
+
"learning_rate": 0.00010043460161143261,
|
| 1679 |
+
"loss": 0.5343,
|
| 1680 |
+
"step": 1380
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 2.86,
|
| 1684 |
+
"learning_rate": 9.845018552372344e-05,
|
| 1685 |
+
"loss": 1.0444,
|
| 1686 |
+
"step": 1385
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 2.87,
|
| 1690 |
+
"learning_rate": 9.643446071344098e-05,
|
| 1691 |
+
"loss": 0.6887,
|
| 1692 |
+
"step": 1390
|
| 1693 |
+
},
|
| 1694 |
+
{
|
| 1695 |
+
"epoch": 2.88,
|
| 1696 |
+
"learning_rate": 9.438954139756306e-05,
|
| 1697 |
+
"loss": 0.8487,
|
| 1698 |
+
"step": 1395
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 2.89,
|
| 1702 |
+
"learning_rate": 9.231757241405981e-05,
|
| 1703 |
+
"loss": 0.7323,
|
| 1704 |
+
"step": 1400
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.9,
|
| 1708 |
+
"learning_rate": 9.02207269722782e-05,
|
| 1709 |
+
"loss": 0.6256,
|
| 1710 |
+
"step": 1405
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 2.91,
|
| 1714 |
+
"learning_rate": 8.81012043735311e-05,
|
| 1715 |
+
"loss": 0.832,
|
| 1716 |
+
"step": 1410
|
| 1717 |
+
},
|
| 1718 |
+
{
|
| 1719 |
+
"epoch": 2.92,
|
| 1720 |
+
"learning_rate": 8.59612277043413e-05,
|
| 1721 |
+
"loss": 0.539,
|
| 1722 |
+
"step": 1415
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 2.93,
|
| 1726 |
+
"learning_rate": 8.380304150471572e-05,
|
| 1727 |
+
"loss": 0.6064,
|
| 1728 |
+
"step": 1420
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 2.94,
|
| 1732 |
+
"learning_rate": 8.162890941395533e-05,
|
| 1733 |
+
"loss": 0.6207,
|
| 1734 |
+
"step": 1425
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 2.95,
|
| 1738 |
+
"learning_rate": 7.944111179639712e-05,
|
| 1739 |
+
"loss": 0.5802,
|
| 1740 |
+
"step": 1430
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 2.96,
|
| 1744 |
+
"learning_rate": 7.72419433496248e-05,
|
| 1745 |
+
"loss": 0.6887,
|
| 1746 |
+
"step": 1435
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.97,
|
| 1750 |
+
"learning_rate": 7.503371069765357e-05,
|
| 1751 |
+
"loss": 0.8306,
|
| 1752 |
+
"step": 1440
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 2.98,
|
| 1756 |
+
"learning_rate": 7.28187299715963e-05,
|
| 1757 |
+
"loss": 0.4574,
|
| 1758 |
+
"step": 1445
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 2.99,
|
| 1762 |
+
"learning_rate": 7.059932438036761e-05,
|
| 1763 |
+
"loss": 0.6537,
|
| 1764 |
+
"step": 1450
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 3.0,
|
| 1768 |
+
"learning_rate": 6.837782177395655e-05,
|
| 1769 |
+
"loss": 0.8464,
|
| 1770 |
+
"step": 1455
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 3.0,
|
| 1774 |
+
"eval_loss": 0.7975038886070251,
|
| 1775 |
+
"eval_runtime": 7.9678,
|
| 1776 |
+
"eval_samples_per_second": 81.452,
|
| 1777 |
+
"eval_steps_per_second": 10.291,
|
| 1778 |
+
"step": 1455
|
| 1779 |
}
|
| 1780 |
],
|
| 1781 |
+
"max_steps": 1455,
|
| 1782 |
+
"num_train_epochs": 3,
|
| 1783 |
+
"total_flos": 1519151874048000.0,
|
| 1784 |
"trial_name": null,
|
| 1785 |
"trial_params": null
|
| 1786 |
}
|
training_args.bin
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 sha256:6a191d7ddb4193d5d88e644c72ac19b8cc1f37c551be0aecf17ab07f676a5dc3
|
| 3 |
+
size 3375
|