Commit
•
6e67db2
1
Parent(s):
531a648
huggingartists
Browse files- README.md +3 -3
- config.json +1 -1
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +2 -2
- scheduler.pt +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +341 -7
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
| 45 |
dataset = load_dataset("huggingartists/50-cent")
|
| 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 50 Cent'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/50-cent")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1awg3ygb/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 50 Cent's lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/ld8pvc1j) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/ld8pvc1j/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "huggingartists/50-cent",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 3.
|
|
|
|
| 1 |
+
{"eval_loss": 3.3637726306915283, "eval_runtime": 16.4999, "eval_samples_per_second": 20.727, "eval_steps_per_second": 2.606, "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 sha256:358a6f342b56f9de0136e070ea234ddaa8e96700df6535caddb90f83533ad73a
|
| 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 sha256:54d8c0438e44a5c817661dde8d80235759dd9bf6fd31e60b82390ac67a903164
|
| 3 |
size 995604017
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510403817
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39028db0b9207c67d95d8bc7b1634c498f86342adff06c8b1c9d2d4614a45efe
|
| 3 |
size 510403817
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1962bee387c556be33f8635e4ecc47b5f5d760f1525f5cf294369a7e3bac39b
|
| 3 |
+
size 14439
|
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 sha256:56a03ee9c4f7d46c39bb609d5652834cf98daba2d29c096120b392bb7cba62b1
|
| 3 |
size 623
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "
|
|
|
|
| 1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "huggingartists/50-cent", "tokenizer_class": "GPT2Tokenizer"}
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 3.
|
| 3 |
-
"best_model_checkpoint": "output/50-cent/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -320,11 +320,345 @@
|
|
| 320 |
"eval_samples_per_second": 22.47,
|
| 321 |
"eval_steps_per_second": 2.854,
|
| 322 |
"step": 258
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 323 |
}
|
| 324 |
],
|
| 325 |
-
"max_steps":
|
| 326 |
-
"num_train_epochs":
|
| 327 |
-
"total_flos":
|
| 328 |
"trial_name": null,
|
| 329 |
"trial_params": null
|
| 330 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 3.3637726306915283,
|
| 3 |
+
"best_model_checkpoint": "output/50-cent/checkpoint-522",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 522,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 320 |
"eval_samples_per_second": 22.47,
|
| 321 |
"eval_steps_per_second": 2.854,
|
| 322 |
"step": 258
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.0,
|
| 326 |
+
"learning_rate": 4.969441783384187e-09,
|
| 327 |
+
"loss": 3.3342,
|
| 328 |
+
"step": 260
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.0,
|
| 332 |
+
"eval_loss": 3.3782756328582764,
|
| 333 |
+
"eval_runtime": 16.6767,
|
| 334 |
+
"eval_samples_per_second": 20.508,
|
| 335 |
+
"eval_steps_per_second": 2.578,
|
| 336 |
+
"step": 261
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.02,
|
| 340 |
+
"learning_rate": 7.949666974663345e-08,
|
| 341 |
+
"loss": 3.4715,
|
| 342 |
+
"step": 265
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.03,
|
| 346 |
+
"learning_rate": 4.0213613921093164e-07,
|
| 347 |
+
"loss": 3.4357,
|
| 348 |
+
"step": 270
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.05,
|
| 352 |
+
"learning_rate": 9.717195750166447e-07,
|
| 353 |
+
"loss": 3.3402,
|
| 354 |
+
"step": 275
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.07,
|
| 358 |
+
"learning_rate": 1.7861845197078197e-06,
|
| 359 |
+
"loss": 3.395,
|
| 360 |
+
"step": 280
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.09,
|
| 364 |
+
"learning_rate": 2.842581801675534e-06,
|
| 365 |
+
"loss": 3.3568,
|
| 366 |
+
"step": 285
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.11,
|
| 370 |
+
"learning_rate": 4.137086214086682e-06,
|
| 371 |
+
"loss": 3.6921,
|
| 372 |
+
"step": 290
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.13,
|
| 376 |
+
"learning_rate": 5.66501036593004e-06,
|
| 377 |
+
"loss": 3.4689,
|
| 378 |
+
"step": 295
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.15,
|
| 382 |
+
"learning_rate": 7.420821655024756e-06,
|
| 383 |
+
"loss": 3.5794,
|
| 384 |
+
"step": 300
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.17,
|
| 388 |
+
"learning_rate": 9.39816230153247e-06,
|
| 389 |
+
"loss": 3.4054,
|
| 390 |
+
"step": 305
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.19,
|
| 394 |
+
"learning_rate": 1.1589872369431459e-05,
|
| 395 |
+
"loss": 3.5207,
|
| 396 |
+
"step": 310
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.21,
|
| 400 |
+
"learning_rate": 1.3988015692592823e-05,
|
| 401 |
+
"loss": 3.352,
|
| 402 |
+
"step": 315
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.23,
|
| 406 |
+
"learning_rate": 1.658390861157988e-05,
|
| 407 |
+
"loss": 3.5263,
|
| 408 |
+
"step": 320
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.25,
|
| 412 |
+
"learning_rate": 1.936815141711555e-05,
|
| 413 |
+
"loss": 3.4251,
|
| 414 |
+
"step": 325
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.26,
|
| 418 |
+
"learning_rate": 2.2330662386360735e-05,
|
| 419 |
+
"loss": 3.5036,
|
| 420 |
+
"step": 330
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.28,
|
| 424 |
+
"learning_rate": 2.5460714288759305e-05,
|
| 425 |
+
"loss": 3.6056,
|
| 426 |
+
"step": 335
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.3,
|
| 430 |
+
"learning_rate": 2.8746973229261208e-05,
|
| 431 |
+
"loss": 3.4339,
|
| 432 |
+
"step": 340
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.32,
|
| 436 |
+
"learning_rate": 3.2177539688273746e-05,
|
| 437 |
+
"loss": 3.2688,
|
| 438 |
+
"step": 345
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.34,
|
| 442 |
+
"learning_rate": 3.5739991609734934e-05,
|
| 443 |
+
"loss": 3.6447,
|
| 444 |
+
"step": 350
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.36,
|
| 448 |
+
"learning_rate": 3.9421429381287695e-05,
|
| 449 |
+
"loss": 3.4024,
|
| 450 |
+
"step": 355
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 1.38,
|
| 454 |
+
"learning_rate": 4.320852254368187e-05,
|
| 455 |
+
"loss": 3.332,
|
| 456 |
+
"step": 360
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.4,
|
| 460 |
+
"learning_rate": 4.7087558060269536e-05,
|
| 461 |
+
"loss": 3.4638,
|
| 462 |
+
"step": 365
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.42,
|
| 466 |
+
"learning_rate": 5.1044489971810725e-05,
|
| 467 |
+
"loss": 3.5294,
|
| 468 |
+
"step": 370
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.44,
|
| 472 |
+
"learning_rate": 5.506499025678891e-05,
|
| 473 |
+
"loss": 3.4554,
|
| 474 |
+
"step": 375
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.46,
|
| 478 |
+
"learning_rate": 5.9134500713072235e-05,
|
| 479 |
+
"loss": 3.2164,
|
| 480 |
+
"step": 380
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.48,
|
| 484 |
+
"learning_rate": 6.323828567305678e-05,
|
| 485 |
+
"loss": 3.5425,
|
| 486 |
+
"step": 385
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.49,
|
| 490 |
+
"learning_rate": 6.736148536141151e-05,
|
| 491 |
+
"loss": 3.3742,
|
| 492 |
+
"step": 390
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.51,
|
| 496 |
+
"learning_rate": 7.148916970221591e-05,
|
| 497 |
+
"loss": 3.4436,
|
| 498 |
+
"step": 395
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.53,
|
| 502 |
+
"learning_rate": 7.560639238065579e-05,
|
| 503 |
+
"loss": 3.4376,
|
| 504 |
+
"step": 400
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.55,
|
| 508 |
+
"learning_rate": 7.969824496351964e-05,
|
| 509 |
+
"loss": 3.5896,
|
| 510 |
+
"step": 405
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 1.57,
|
| 514 |
+
"learning_rate": 8.374991088252677e-05,
|
| 515 |
+
"loss": 3.4729,
|
| 516 |
+
"step": 410
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.59,
|
| 520 |
+
"learning_rate": 8.774671908501242e-05,
|
| 521 |
+
"loss": 3.4136,
|
| 522 |
+
"step": 415
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.61,
|
| 526 |
+
"learning_rate": 9.1674197157702e-05,
|
| 527 |
+
"loss": 3.475,
|
| 528 |
+
"step": 420
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.63,
|
| 532 |
+
"learning_rate": 9.551812373121417e-05,
|
| 533 |
+
"loss": 3.3729,
|
| 534 |
+
"step": 425
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 1.65,
|
| 538 |
+
"learning_rate": 9.926457997553504e-05,
|
| 539 |
+
"loss": 3.5851,
|
| 540 |
+
"step": 430
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.67,
|
| 544 |
+
"learning_rate": 0.00010290000000000001,
|
| 545 |
+
"loss": 3.4967,
|
| 546 |
+
"step": 435
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.69,
|
| 550 |
+
"learning_rate": 0.0001064112199752845,
|
| 551 |
+
"loss": 3.3427,
|
| 552 |
+
"step": 440
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 1.7,
|
| 556 |
+
"learning_rate": 0.0001097855257995339,
|
| 557 |
+
"loss": 3.5208,
|
| 558 |
+
"step": 445
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.72,
|
| 562 |
+
"learning_rate": 0.00011301069913603334,
|
| 563 |
+
"loss": 3.4049,
|
| 564 |
+
"step": 450
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.74,
|
| 568 |
+
"learning_rate": 0.00011607506165571554,
|
| 569 |
+
"loss": 3.452,
|
| 570 |
+
"step": 455
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.76,
|
| 574 |
+
"learning_rate": 0.00011896751732430487,
|
| 575 |
+
"loss": 3.5148,
|
| 576 |
+
"step": 460
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.78,
|
| 580 |
+
"learning_rate": 0.00012167759258097654,
|
| 581 |
+
"loss": 3.3147,
|
| 582 |
+
"step": 465
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.8,
|
| 586 |
+
"learning_rate": 0.00012419547426304373,
|
| 587 |
+
"loss": 3.38,
|
| 588 |
+
"step": 470
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.82,
|
| 592 |
+
"learning_rate": 0.00012651204513934757,
|
| 593 |
+
"loss": 3.3329,
|
| 594 |
+
"step": 475
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.84,
|
| 598 |
+
"learning_rate": 0.00012861891692368509,
|
| 599 |
+
"loss": 3.5188,
|
| 600 |
+
"step": 480
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.86,
|
| 604 |
+
"learning_rate": 0.00013050846064873163,
|
| 605 |
+
"loss": 3.4628,
|
| 606 |
+
"step": 485
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 1.88,
|
| 610 |
+
"learning_rate": 0.0001321738342904763,
|
| 611 |
+
"loss": 3.5377,
|
| 612 |
+
"step": 490
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.9,
|
| 616 |
+
"learning_rate": 0.00013360900754314024,
|
| 617 |
+
"loss": 3.4683,
|
| 618 |
+
"step": 495
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.92,
|
| 622 |
+
"learning_rate": 0.00013480878365487042,
|
| 623 |
+
"loss": 3.4532,
|
| 624 |
+
"step": 500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.93,
|
| 628 |
+
"learning_rate": 0.00013576881824513962,
|
| 629 |
+
"loss": 3.5582,
|
| 630 |
+
"step": 505
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.95,
|
| 634 |
+
"learning_rate": 0.00013648563503571674,
|
| 635 |
+
"loss": 3.5528,
|
| 636 |
+
"step": 510
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.97,
|
| 640 |
+
"learning_rate": 0.00013695663843824482,
|
| 641 |
+
"loss": 3.4235,
|
| 642 |
+
"step": 515
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.99,
|
| 646 |
+
"learning_rate": 0.00013718012295284757,
|
| 647 |
+
"loss": 3.5739,
|
| 648 |
+
"step": 520
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.0,
|
| 652 |
+
"eval_loss": 3.3637726306915283,
|
| 653 |
+
"eval_runtime": 16.4835,
|
| 654 |
+
"eval_samples_per_second": 20.748,
|
| 655 |
+
"eval_steps_per_second": 2.609,
|
| 656 |
+
"step": 522
|
| 657 |
}
|
| 658 |
],
|
| 659 |
+
"max_steps": 522,
|
| 660 |
+
"num_train_epochs": 2,
|
| 661 |
+
"total_flos": 544271302656000.0,
|
| 662 |
"trial_name": null,
|
| 663 |
"trial_params": null
|
| 664 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2671
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6f290bf43c68f84d50f113a11b20c55809e90aac8aa7e58b408f5dbe3f578ab
|
| 3 |
size 2671
|