Commit
•
d624642
1
Parent(s):
d9cb9cb
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 +375 -7
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
| 45 |
dataset = load_dataset("huggingartists/scriptonite")
|
| 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 Скриптонит (Scriptonite)'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/scriptonite")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/13pxeww0/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 Скриптонит (Scriptonite)'s lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1itfp830) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1itfp830/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/scriptonite",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 1.
|
|
|
|
| 1 |
+
{"eval_loss": 1.5933494567871094, "eval_runtime": 22.2071, "eval_samples_per_second": 20.939, "eval_steps_per_second": 2.657, "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:c11bfa3837c0edca55ca9f7ccdb4f3d86d19b9ba23fe6cf05c899732f878fa76
|
| 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:bde59a917e4907642c41b1ba1a0796fe83190743077f4abc55b70f6d855f3a67
|
| 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 sha256:218d35bc6715a739b952792ffa8615837479989eea7021decc404a768b2fed37
|
| 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 sha256:34f8219694a6e795ffa0539af4f5ebbbfd0956e15ebc61431bdc1cbffbd00148
|
| 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:cc022d3bfdc6685b60396d3e5ef01fcd639162e46eae2acfcd548c1b5128e6c9
|
| 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/scriptonite", "tokenizer_class": "GPT2Tokenizer"}
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "output/scriptonite/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -380,11 +380,379 @@
|
|
| 380 |
"eval_samples_per_second": 21.336,
|
| 381 |
"eval_steps_per_second": 2.691,
|
| 382 |
"step": 306
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 383 |
}
|
| 384 |
],
|
| 385 |
-
"max_steps":
|
| 386 |
-
"num_train_epochs":
|
| 387 |
-
"total_flos":
|
| 388 |
"trial_name": null,
|
| 389 |
"trial_params": null
|
| 390 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.5933494567871094,
|
| 3 |
+
"best_model_checkpoint": "output/scriptonite/checkpoint-608",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 608,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 380 |
"eval_samples_per_second": 21.336,
|
| 381 |
"eval_steps_per_second": 2.691,
|
| 382 |
"step": 306
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.02,
|
| 386 |
+
"learning_rate": 1.3182872524144475e-07,
|
| 387 |
+
"loss": 1.7503,
|
| 388 |
+
"step": 310
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.04,
|
| 392 |
+
"learning_rate": 4.427558891872417e-07,
|
| 393 |
+
"loss": 1.7186,
|
| 394 |
+
"step": 315
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 1.05,
|
| 398 |
+
"learning_rate": 9.35614586573241e-07,
|
| 399 |
+
"loss": 1.7355,
|
| 400 |
+
"step": 320
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.07,
|
| 404 |
+
"learning_rate": 1.6090892340046806e-06,
|
| 405 |
+
"loss": 1.7325,
|
| 406 |
+
"step": 325
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.09,
|
| 410 |
+
"learning_rate": 2.461382131516746e-06,
|
| 411 |
+
"loss": 1.5602,
|
| 412 |
+
"step": 330
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"epoch": 1.1,
|
| 416 |
+
"learning_rate": 3.4902182611592783e-06,
|
| 417 |
+
"loss": 1.5739,
|
| 418 |
+
"step": 335
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.12,
|
| 422 |
+
"learning_rate": 4.692851359682261e-06,
|
| 423 |
+
"loss": 1.7024,
|
| 424 |
+
"step": 340
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.13,
|
| 428 |
+
"learning_rate": 6.066071249112177e-06,
|
| 429 |
+
"loss": 1.7912,
|
| 430 |
+
"step": 345
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.15,
|
| 434 |
+
"learning_rate": 7.606212405651899e-06,
|
| 435 |
+
"loss": 1.7776,
|
| 436 |
+
"step": 350
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 1.17,
|
| 440 |
+
"learning_rate": 9.309163744031197e-06,
|
| 441 |
+
"loss": 1.8068,
|
| 442 |
+
"step": 355
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.18,
|
| 446 |
+
"learning_rate": 1.1170379591190527e-05,
|
| 447 |
+
"loss": 1.7059,
|
| 448 |
+
"step": 360
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.2,
|
| 452 |
+
"learning_rate": 1.3184891820006337e-05,
|
| 453 |
+
"loss": 1.7498,
|
| 454 |
+
"step": 365
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.22,
|
| 458 |
+
"learning_rate": 1.5347323110669033e-05,
|
| 459 |
+
"loss": 1.7696,
|
| 460 |
+
"step": 370
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.23,
|
| 464 |
+
"learning_rate": 1.7651901304315657e-05,
|
| 465 |
+
"loss": 1.703,
|
| 466 |
+
"step": 375
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.25,
|
| 470 |
+
"learning_rate": 2.009247481060283e-05,
|
| 471 |
+
"loss": 1.6793,
|
| 472 |
+
"step": 380
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.27,
|
| 476 |
+
"learning_rate": 2.2662529028092886e-05,
|
| 477 |
+
"loss": 1.7064,
|
| 478 |
+
"step": 385
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 1.28,
|
| 482 |
+
"learning_rate": 2.5355203733622272e-05,
|
| 483 |
+
"loss": 1.6889,
|
| 484 |
+
"step": 390
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.3,
|
| 488 |
+
"learning_rate": 2.816331139423508e-05,
|
| 489 |
+
"loss": 1.7357,
|
| 490 |
+
"step": 395
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.32,
|
| 494 |
+
"learning_rate": 3.1079356352801514e-05,
|
| 495 |
+
"loss": 1.6548,
|
| 496 |
+
"step": 400
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 1.33,
|
| 500 |
+
"learning_rate": 3.4095554836109936e-05,
|
| 501 |
+
"loss": 1.7133,
|
| 502 |
+
"step": 405
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.35,
|
| 506 |
+
"learning_rate": 3.7203855732024184e-05,
|
| 507 |
+
"loss": 1.6095,
|
| 508 |
+
"step": 410
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.37,
|
| 512 |
+
"learning_rate": 4.039596208024663e-05,
|
| 513 |
+
"loss": 1.6151,
|
| 514 |
+
"step": 415
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.38,
|
| 518 |
+
"learning_rate": 4.3663353219321276e-05,
|
| 519 |
+
"loss": 1.6988,
|
| 520 |
+
"step": 420
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 1.4,
|
| 524 |
+
"learning_rate": 4.6997307530760796e-05,
|
| 525 |
+
"loss": 1.8323,
|
| 526 |
+
"step": 425
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.41,
|
| 530 |
+
"learning_rate": 5.038892571958626e-05,
|
| 531 |
+
"loss": 1.6735,
|
| 532 |
+
"step": 430
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.43,
|
| 536 |
+
"learning_rate": 5.382915456913676e-05,
|
| 537 |
+
"loss": 1.6212,
|
| 538 |
+
"step": 435
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 1.45,
|
| 542 |
+
"learning_rate": 5.7308811106741675e-05,
|
| 543 |
+
"loss": 1.7788,
|
| 544 |
+
"step": 440
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.46,
|
| 548 |
+
"learning_rate": 6.0818607115748475e-05,
|
| 549 |
+
"loss": 1.6847,
|
| 550 |
+
"step": 445
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.48,
|
| 554 |
+
"learning_rate": 6.434917392847842e-05,
|
| 555 |
+
"loss": 1.6746,
|
| 556 |
+
"step": 450
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.5,
|
| 560 |
+
"learning_rate": 6.78910874339285e-05,
|
| 561 |
+
"loss": 1.7122,
|
| 562 |
+
"step": 455
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.51,
|
| 566 |
+
"learning_rate": 7.143489323346855e-05,
|
| 567 |
+
"loss": 1.6207,
|
| 568 |
+
"step": 460
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.53,
|
| 572 |
+
"learning_rate": 7.497113187738444e-05,
|
| 573 |
+
"loss": 1.719,
|
| 574 |
+
"step": 465
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.55,
|
| 578 |
+
"learning_rate": 7.849036411490396e-05,
|
| 579 |
+
"loss": 1.814,
|
| 580 |
+
"step": 470
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.56,
|
| 584 |
+
"learning_rate": 8.19831960903064e-05,
|
| 585 |
+
"loss": 1.7822,
|
| 586 |
+
"step": 475
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.58,
|
| 590 |
+
"learning_rate": 8.54403044178588e-05,
|
| 591 |
+
"loss": 1.7602,
|
| 592 |
+
"step": 480
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.6,
|
| 596 |
+
"learning_rate": 8.885246106864805e-05,
|
| 597 |
+
"loss": 1.6178,
|
| 598 |
+
"step": 485
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.61,
|
| 602 |
+
"learning_rate": 9.221055800287699e-05,
|
| 603 |
+
"loss": 1.7397,
|
| 604 |
+
"step": 490
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.63,
|
| 608 |
+
"learning_rate": 9.550563148187563e-05,
|
| 609 |
+
"loss": 1.6071,
|
| 610 |
+
"step": 495
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.64,
|
| 614 |
+
"learning_rate": 9.87288859949296e-05,
|
| 615 |
+
"loss": 1.66,
|
| 616 |
+
"step": 500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.66,
|
| 620 |
+
"learning_rate": 0.00010187171773706003,
|
| 621 |
+
"loss": 1.6028,
|
| 622 |
+
"step": 505
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.68,
|
| 626 |
+
"learning_rate": 0.00010492573757508462,
|
| 627 |
+
"loss": 1.697,
|
| 628 |
+
"step": 510
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.69,
|
| 632 |
+
"learning_rate": 0.0001078827934406569,
|
| 633 |
+
"loss": 1.5973,
|
| 634 |
+
"step": 515
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.71,
|
| 638 |
+
"learning_rate": 0.00011073499209051121,
|
| 639 |
+
"loss": 1.6779,
|
| 640 |
+
"step": 520
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.73,
|
| 644 |
+
"learning_rate": 0.00011347472017582718,
|
| 645 |
+
"loss": 1.639,
|
| 646 |
+
"step": 525
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.74,
|
| 650 |
+
"learning_rate": 0.00011609466456447531,
|
| 651 |
+
"loss": 1.7209,
|
| 652 |
+
"step": 530
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.76,
|
| 656 |
+
"learning_rate": 0.00011858783186189604,
|
| 657 |
+
"loss": 1.7896,
|
| 658 |
+
"step": 535
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.78,
|
| 662 |
+
"learning_rate": 0.00012094756707850673,
|
| 663 |
+
"loss": 1.7093,
|
| 664 |
+
"step": 540
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.79,
|
| 668 |
+
"learning_rate": 0.00012316757139380674,
|
| 669 |
+
"loss": 1.614,
|
| 670 |
+
"step": 545
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.81,
|
| 674 |
+
"learning_rate": 0.0001252419189697637,
|
| 675 |
+
"loss": 1.7043,
|
| 676 |
+
"step": 550
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.83,
|
| 680 |
+
"learning_rate": 0.0001271650727686013,
|
| 681 |
+
"loss": 1.6544,
|
| 682 |
+
"step": 555
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.84,
|
| 686 |
+
"learning_rate": 0.00012893189933276512,
|
| 687 |
+
"loss": 1.6355,
|
| 688 |
+
"step": 560
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.86,
|
| 692 |
+
"learning_rate": 0.00013053768248761616,
|
| 693 |
+
"loss": 1.7327,
|
| 694 |
+
"step": 565
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.88,
|
| 698 |
+
"learning_rate": 0.00013197813593027427,
|
| 699 |
+
"loss": 1.5672,
|
| 700 |
+
"step": 570
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.89,
|
| 704 |
+
"learning_rate": 0.00013324941467100882,
|
| 705 |
+
"loss": 1.6036,
|
| 706 |
+
"step": 575
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.91,
|
| 710 |
+
"learning_rate": 0.00013434812529663614,
|
| 711 |
+
"loss": 1.5748,
|
| 712 |
+
"step": 580
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.92,
|
| 716 |
+
"learning_rate": 0.00013527133502852737,
|
| 717 |
+
"loss": 1.6181,
|
| 718 |
+
"step": 585
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.94,
|
| 722 |
+
"learning_rate": 0.00013601657955104887,
|
| 723 |
+
"loss": 1.6947,
|
| 724 |
+
"step": 590
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.96,
|
| 728 |
+
"learning_rate": 0.00013658186958953817,
|
| 729 |
+
"loss": 1.6579,
|
| 730 |
+
"step": 595
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.97,
|
| 734 |
+
"learning_rate": 0.00013696569622025754,
|
| 735 |
+
"loss": 1.6297,
|
| 736 |
+
"step": 600
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.99,
|
| 740 |
+
"learning_rate": 0.00013716703489815072,
|
| 741 |
+
"loss": 1.6272,
|
| 742 |
+
"step": 605
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.0,
|
| 746 |
+
"eval_loss": 1.5933494567871094,
|
| 747 |
+
"eval_runtime": 22.1769,
|
| 748 |
+
"eval_samples_per_second": 20.968,
|
| 749 |
+
"eval_steps_per_second": 2.66,
|
| 750 |
+
"step": 608
|
| 751 |
}
|
| 752 |
],
|
| 753 |
+
"max_steps": 608,
|
| 754 |
+
"num_train_epochs": 2,
|
| 755 |
+
"total_flos": 634286407680000.0,
|
| 756 |
"trial_name": null,
|
| 757 |
"trial_params": null
|
| 758 |
}
|
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 sha256:9edd5597a8f5fd166f6b738b741bd4ca0054d7d9cca4c5ca6734b697c0e34cda
|
| 3 |
size 2671
|