Training in progress, step 100, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 140815952
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf986d044cd469da2e4227704b99c98d930874f220ef1dc90f0a82423f196a92
|
| 3 |
size 140815952
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 281824770
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54bd6ea538da0be811abd930225b74fd4587dc5b1a9b11695191e7055d62e103
|
| 3 |
size 281824770
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61279d92f4b304566cb5bb66d76f84377c5ebe8e741fc3e9c1dd4da05e59a1f2
|
| 3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03ad66011cfc1fc727a51190602a41adc332b48eeef62a5ee87c2ca9f9b90b2b
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7244487404823303,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -373,6 +373,364 @@
|
|
| 373 |
"eval_samples_per_second": 41.102,
|
| 374 |
"eval_steps_per_second": 10.275,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -387,7 +745,7 @@
|
|
| 387 |
"early_stopping_threshold": 0.0
|
| 388 |
},
|
| 389 |
"attributes": {
|
| 390 |
-
"early_stopping_patience_counter":
|
| 391 |
}
|
| 392 |
},
|
| 393 |
"TrainerControl": {
|
|
@@ -396,12 +754,12 @@
|
|
| 396 |
"should_evaluate": false,
|
| 397 |
"should_log": false,
|
| 398 |
"should_save": true,
|
| 399 |
-
"should_training_stop":
|
| 400 |
},
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 4,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.7244487404823303,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.8097165991902834,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 373 |
"eval_samples_per_second": 41.102,
|
| 374 |
"eval_steps_per_second": 10.275,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.41295546558704455,
|
| 379 |
+
"grad_norm": 6.105991363525391,
|
| 380 |
+
"learning_rate": 2.3816778784387097e-05,
|
| 381 |
+
"loss": 0.7112,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.42105263157894735,
|
| 386 |
+
"grad_norm": 5.9137163162231445,
|
| 387 |
+
"learning_rate": 2.3263454721781537e-05,
|
| 388 |
+
"loss": 0.6772,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.4291497975708502,
|
| 393 |
+
"grad_norm": 6.709981918334961,
|
| 394 |
+
"learning_rate": 2.2693489161088592e-05,
|
| 395 |
+
"loss": 0.7273,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.43724696356275305,
|
| 400 |
+
"grad_norm": 4.602910041809082,
|
| 401 |
+
"learning_rate": 2.210802993709498e-05,
|
| 402 |
+
"loss": 0.7377,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.44534412955465585,
|
| 407 |
+
"grad_norm": 8.946381568908691,
|
| 408 |
+
"learning_rate": 2.1508256086763372e-05,
|
| 409 |
+
"loss": 0.6814,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.4534412955465587,
|
| 414 |
+
"grad_norm": 5.092156887054443,
|
| 415 |
+
"learning_rate": 2.0895375474808857e-05,
|
| 416 |
+
"loss": 0.6879,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.46153846153846156,
|
| 421 |
+
"grad_norm": 4.789443016052246,
|
| 422 |
+
"learning_rate": 2.0270622361220143e-05,
|
| 423 |
+
"loss": 0.6239,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.46963562753036436,
|
| 428 |
+
"grad_norm": 4.035036087036133,
|
| 429 |
+
"learning_rate": 1.963525491562421e-05,
|
| 430 |
+
"loss": 0.6038,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.4777327935222672,
|
| 435 |
+
"grad_norm": 4.545828819274902,
|
| 436 |
+
"learning_rate": 1.8990552683500128e-05,
|
| 437 |
+
"loss": 0.7022,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.48582995951417,
|
| 442 |
+
"grad_norm": 6.806140899658203,
|
| 443 |
+
"learning_rate": 1.8337814009344716e-05,
|
| 444 |
+
"loss": 0.7606,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.4939271255060729,
|
| 449 |
+
"grad_norm": 4.344721794128418,
|
| 450 |
+
"learning_rate": 1.767835342197955e-05,
|
| 451 |
+
"loss": 0.6619,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.5020242914979757,
|
| 456 |
+
"grad_norm": 5.1954345703125,
|
| 457 |
+
"learning_rate": 1.7013498987264832e-05,
|
| 458 |
+
"loss": 0.6223,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.5101214574898786,
|
| 463 |
+
"grad_norm": 8.843324661254883,
|
| 464 |
+
"learning_rate": 1.6344589633551502e-05,
|
| 465 |
+
"loss": 0.833,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.5182186234817814,
|
| 470 |
+
"grad_norm": 8.470301628112793,
|
| 471 |
+
"learning_rate": 1.5672972455257726e-05,
|
| 472 |
+
"loss": 0.872,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.5263157894736842,
|
| 477 |
+
"grad_norm": 8.447321891784668,
|
| 478 |
+
"learning_rate": 1.5e-05,
|
| 479 |
+
"loss": 0.8794,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.5344129554655871,
|
| 484 |
+
"grad_norm": 7.982692241668701,
|
| 485 |
+
"learning_rate": 1.4327027544742281e-05,
|
| 486 |
+
"loss": 0.8019,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.5425101214574899,
|
| 491 |
+
"grad_norm": 9.073297500610352,
|
| 492 |
+
"learning_rate": 1.36554103664485e-05,
|
| 493 |
+
"loss": 0.6302,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.5506072874493927,
|
| 498 |
+
"grad_norm": 4.642770767211914,
|
| 499 |
+
"learning_rate": 1.2986501012735174e-05,
|
| 500 |
+
"loss": 0.6202,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.5587044534412956,
|
| 505 |
+
"grad_norm": 5.061112403869629,
|
| 506 |
+
"learning_rate": 1.2321646578020452e-05,
|
| 507 |
+
"loss": 0.6198,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.5668016194331984,
|
| 512 |
+
"grad_norm": 7.011550426483154,
|
| 513 |
+
"learning_rate": 1.1662185990655285e-05,
|
| 514 |
+
"loss": 0.8346,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.5748987854251012,
|
| 519 |
+
"grad_norm": 4.438355445861816,
|
| 520 |
+
"learning_rate": 1.1009447316499875e-05,
|
| 521 |
+
"loss": 0.6787,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.582995951417004,
|
| 526 |
+
"grad_norm": 6.0901055335998535,
|
| 527 |
+
"learning_rate": 1.036474508437579e-05,
|
| 528 |
+
"loss": 0.8458,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.5910931174089069,
|
| 533 |
+
"grad_norm": 76.47030639648438,
|
| 534 |
+
"learning_rate": 9.729377638779859e-06,
|
| 535 |
+
"loss": 0.8839,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.5991902834008097,
|
| 540 |
+
"grad_norm": 6.974242687225342,
|
| 541 |
+
"learning_rate": 9.104624525191147e-06,
|
| 542 |
+
"loss": 0.733,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.6072874493927125,
|
| 547 |
+
"grad_norm": 7.109065055847168,
|
| 548 |
+
"learning_rate": 8.491743913236629e-06,
|
| 549 |
+
"loss": 0.8075,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.6153846153846154,
|
| 554 |
+
"grad_norm": 8.350259780883789,
|
| 555 |
+
"learning_rate": 7.89197006290502e-06,
|
| 556 |
+
"loss": 0.7467,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.6234817813765182,
|
| 561 |
+
"grad_norm": 5.253984451293945,
|
| 562 |
+
"learning_rate": 7.30651083891141e-06,
|
| 563 |
+
"loss": 0.7108,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.631578947368421,
|
| 568 |
+
"grad_norm": 7.530630111694336,
|
| 569 |
+
"learning_rate": 6.736545278218464e-06,
|
| 570 |
+
"loss": 0.7081,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.6396761133603239,
|
| 575 |
+
"grad_norm": 18.218433380126953,
|
| 576 |
+
"learning_rate": 6.1832212156129045e-06,
|
| 577 |
+
"loss": 0.6932,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.6477732793522267,
|
| 582 |
+
"grad_norm": 5.084344387054443,
|
| 583 |
+
"learning_rate": 5.647652972118998e-06,
|
| 584 |
+
"loss": 0.7684,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.6558704453441295,
|
| 589 |
+
"grad_norm": 4.171597480773926,
|
| 590 |
+
"learning_rate": 5.130919110904311e-06,
|
| 591 |
+
"loss": 0.7214,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.6639676113360324,
|
| 596 |
+
"grad_norm": 5.165872573852539,
|
| 597 |
+
"learning_rate": 4.6340602651970304e-06,
|
| 598 |
+
"loss": 0.7379,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.6720647773279352,
|
| 603 |
+
"grad_norm": 8.189788818359375,
|
| 604 |
+
"learning_rate": 4.158077042589129e-06,
|
| 605 |
+
"loss": 0.8242,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.680161943319838,
|
| 610 |
+
"grad_norm": 5.687074661254883,
|
| 611 |
+
"learning_rate": 3.7039280099458373e-06,
|
| 612 |
+
"loss": 0.6482,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.6882591093117408,
|
| 617 |
+
"grad_norm": 4.640507221221924,
|
| 618 |
+
"learning_rate": 3.272527762979553e-06,
|
| 619 |
+
"loss": 0.7058,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.6963562753036437,
|
| 624 |
+
"grad_norm": 4.909543514251709,
|
| 625 |
+
"learning_rate": 2.86474508437579e-06,
|
| 626 |
+
"loss": 0.6626,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.7044534412955465,
|
| 631 |
+
"grad_norm": 5.721399784088135,
|
| 632 |
+
"learning_rate": 2.4814011941804603e-06,
|
| 633 |
+
"loss": 0.7401,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.7125506072874493,
|
| 638 |
+
"grad_norm": 4.203503131866455,
|
| 639 |
+
"learning_rate": 2.1232680959720085e-06,
|
| 640 |
+
"loss": 0.7072,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.7206477732793523,
|
| 645 |
+
"grad_norm": 7.876823425292969,
|
| 646 |
+
"learning_rate": 1.79106702214893e-06,
|
| 647 |
+
"loss": 0.559,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.728744939271255,
|
| 652 |
+
"grad_norm": 9.562280654907227,
|
| 653 |
+
"learning_rate": 1.4854669814637145e-06,
|
| 654 |
+
"loss": 0.7441,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.7368421052631579,
|
| 659 |
+
"grad_norm": 4.9196319580078125,
|
| 660 |
+
"learning_rate": 1.2070834117282414e-06,
|
| 661 |
+
"loss": 0.6806,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.7449392712550608,
|
| 666 |
+
"grad_norm": 4.913059711456299,
|
| 667 |
+
"learning_rate": 9.56476940403942e-07,
|
| 668 |
+
"loss": 0.6895,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.7530364372469636,
|
| 673 |
+
"grad_norm": 6.508387088775635,
|
| 674 |
+
"learning_rate": 7.341522555726971e-07,
|
| 675 |
+
"loss": 0.7577,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.7611336032388664,
|
| 680 |
+
"grad_norm": 3.305694103240967,
|
| 681 |
+
"learning_rate": 5.405570895622014e-07,
|
| 682 |
+
"loss": 0.7149,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.7692307692307693,
|
| 687 |
+
"grad_norm": 6.714405536651611,
|
| 688 |
+
"learning_rate": 3.760813172726457e-07,
|
| 689 |
+
"loss": 0.7731,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.7773279352226721,
|
| 694 |
+
"grad_norm": 4.101876735687256,
|
| 695 |
+
"learning_rate": 2.41056171020555e-07,
|
| 696 |
+
"loss": 0.7061,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.7854251012145749,
|
| 701 |
+
"grad_norm": 3.9142746925354004,
|
| 702 |
+
"learning_rate": 1.357535734809795e-07,
|
| 703 |
+
"loss": 0.7258,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.7935222672064778,
|
| 708 |
+
"grad_norm": 3.286195993423462,
|
| 709 |
+
"learning_rate": 6.038559007141397e-08,
|
| 710 |
+
"loss": 0.7034,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.8016194331983806,
|
| 715 |
+
"grad_norm": 4.398167133331299,
|
| 716 |
+
"learning_rate": 1.510400188028116e-08,
|
| 717 |
+
"loss": 0.6205,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.8097165991902834,
|
| 722 |
+
"grad_norm": 4.571166515350342,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 0.733,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.8097165991902834,
|
| 729 |
+
"eval_loss": 0.728439450263977,
|
| 730 |
+
"eval_runtime": 1.266,
|
| 731 |
+
"eval_samples_per_second": 41.075,
|
| 732 |
+
"eval_steps_per_second": 10.269,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 745 |
"early_stopping_threshold": 0.0
|
| 746 |
},
|
| 747 |
"attributes": {
|
| 748 |
+
"early_stopping_patience_counter": 1
|
| 749 |
}
|
| 750 |
},
|
| 751 |
"TrainerControl": {
|
|
|
|
| 754 |
"should_evaluate": false,
|
| 755 |
"should_log": false,
|
| 756 |
"should_save": true,
|
| 757 |
+
"should_training_stop": true
|
| 758 |
},
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 1932120607948800.0,
|
| 763 |
"train_batch_size": 4,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|