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 50899792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7241015963b4e9312d8dda017ea8d135bae01bb1075895ed4565e38143f1395c
|
| 3 |
size 50899792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 102009558
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:544e079ad3d0910b3d99cf66ec12234cca5639883a74f4aab1937f1e70a088f1
|
| 3 |
size 102009558
|
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 sha256:378ebc1116a6ae28136fa27fe8b7439b5379e4d44a0fb7663a874d3084c60ed6
|
| 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 sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 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": 15.607,
|
| 374 |
"eval_steps_per_second": 7.803,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -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": 2,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.812772274017334,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.002362125676896639,
|
| 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": 15.607,
|
| 374 |
"eval_steps_per_second": 7.803,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.001204684095217286,
|
| 379 |
+
"grad_norm": 1.6444913148880005,
|
| 380 |
+
"learning_rate": 5.695865504800327e-05,
|
| 381 |
+
"loss": 1.8085,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.0012283053519862525,
|
| 386 |
+
"grad_norm": 1.6485252380371094,
|
| 387 |
+
"learning_rate": 5.522642316338268e-05,
|
| 388 |
+
"loss": 1.9418,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.0012519266087552188,
|
| 393 |
+
"grad_norm": 1.3757036924362183,
|
| 394 |
+
"learning_rate": 5.348782368720626e-05,
|
| 395 |
+
"loss": 1.8188,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.0012755478655241852,
|
| 400 |
+
"grad_norm": 1.4265061616897583,
|
| 401 |
+
"learning_rate": 5.174497483512506e-05,
|
| 402 |
+
"loss": 1.8015,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.0012991691222931517,
|
| 407 |
+
"grad_norm": 1.2143784761428833,
|
| 408 |
+
"learning_rate": 5e-05,
|
| 409 |
+
"loss": 2.0403,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.001322790379062118,
|
| 414 |
+
"grad_norm": 1.1464849710464478,
|
| 415 |
+
"learning_rate": 4.825502516487497e-05,
|
| 416 |
+
"loss": 1.9537,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.0013464116358310844,
|
| 421 |
+
"grad_norm": 1.017458200454712,
|
| 422 |
+
"learning_rate": 4.6512176312793736e-05,
|
| 423 |
+
"loss": 1.8258,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.0013700328926000507,
|
| 428 |
+
"grad_norm": 1.0252606868743896,
|
| 429 |
+
"learning_rate": 4.477357683661734e-05,
|
| 430 |
+
"loss": 1.7314,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.0013936541493690172,
|
| 435 |
+
"grad_norm": 1.1397935152053833,
|
| 436 |
+
"learning_rate": 4.3041344951996746e-05,
|
| 437 |
+
"loss": 1.7815,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.0014172754061379837,
|
| 442 |
+
"grad_norm": 1.2537386417388916,
|
| 443 |
+
"learning_rate": 4.131759111665349e-05,
|
| 444 |
+
"loss": 2.0948,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.00144089666290695,
|
| 449 |
+
"grad_norm": 1.226378083229065,
|
| 450 |
+
"learning_rate": 3.960441545911204e-05,
|
| 451 |
+
"loss": 1.7523,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.0014645179196759164,
|
| 456 |
+
"grad_norm": 1.1963748931884766,
|
| 457 |
+
"learning_rate": 3.790390522001662e-05,
|
| 458 |
+
"loss": 1.6124,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.0014881391764448827,
|
| 463 |
+
"grad_norm": 1.2817221879959106,
|
| 464 |
+
"learning_rate": 3.6218132209150045e-05,
|
| 465 |
+
"loss": 1.7639,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.0015117604332138491,
|
| 470 |
+
"grad_norm": 1.320666790008545,
|
| 471 |
+
"learning_rate": 3.4549150281252636e-05,
|
| 472 |
+
"loss": 1.815,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.0015353816899828156,
|
| 477 |
+
"grad_norm": 1.1580308675765991,
|
| 478 |
+
"learning_rate": 3.289899283371657e-05,
|
| 479 |
+
"loss": 1.6898,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.0015590029467517819,
|
| 484 |
+
"grad_norm": 1.3005945682525635,
|
| 485 |
+
"learning_rate": 3.12696703292044e-05,
|
| 486 |
+
"loss": 1.7134,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.0015826242035207484,
|
| 491 |
+
"grad_norm": 1.460551142692566,
|
| 492 |
+
"learning_rate": 2.9663167846209998e-05,
|
| 493 |
+
"loss": 1.9224,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.0016062454602897146,
|
| 498 |
+
"grad_norm": 1.084309458732605,
|
| 499 |
+
"learning_rate": 2.8081442660546125e-05,
|
| 500 |
+
"loss": 1.6219,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.001629866717058681,
|
| 505 |
+
"grad_norm": 1.6280590295791626,
|
| 506 |
+
"learning_rate": 2.6526421860705473e-05,
|
| 507 |
+
"loss": 1.9883,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.0016534879738276476,
|
| 512 |
+
"grad_norm": 1.6045172214508057,
|
| 513 |
+
"learning_rate": 2.500000000000001e-05,
|
| 514 |
+
"loss": 1.9836,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.0016771092305966138,
|
| 519 |
+
"grad_norm": 1.6871895790100098,
|
| 520 |
+
"learning_rate": 2.350403678833976e-05,
|
| 521 |
+
"loss": 2.1157,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.0017007304873655803,
|
| 526 |
+
"grad_norm": 1.8046764135360718,
|
| 527 |
+
"learning_rate": 2.2040354826462668e-05,
|
| 528 |
+
"loss": 2.2028,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.0017243517441345468,
|
| 533 |
+
"grad_norm": 1.3781118392944336,
|
| 534 |
+
"learning_rate": 2.061073738537635e-05,
|
| 535 |
+
"loss": 1.8658,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.001747973000903513,
|
| 540 |
+
"grad_norm": 1.5428242683410645,
|
| 541 |
+
"learning_rate": 1.9216926233717085e-05,
|
| 542 |
+
"loss": 2.1846,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.0017715942576724795,
|
| 547 |
+
"grad_norm": 1.931896686553955,
|
| 548 |
+
"learning_rate": 1.7860619515673033e-05,
|
| 549 |
+
"loss": 1.8872,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.0017952155144414458,
|
| 554 |
+
"grad_norm": 1.6994593143463135,
|
| 555 |
+
"learning_rate": 1.6543469682057106e-05,
|
| 556 |
+
"loss": 2.0523,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.0018188367712104123,
|
| 561 |
+
"grad_norm": 1.7547457218170166,
|
| 562 |
+
"learning_rate": 1.526708147705013e-05,
|
| 563 |
+
"loss": 1.982,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.0018424580279793787,
|
| 568 |
+
"grad_norm": 1.5750082731246948,
|
| 569 |
+
"learning_rate": 1.4033009983067452e-05,
|
| 570 |
+
"loss": 1.9124,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.001866079284748345,
|
| 575 |
+
"grad_norm": 1.8795514106750488,
|
| 576 |
+
"learning_rate": 1.2842758726130283e-05,
|
| 577 |
+
"loss": 2.1477,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.0018897005415173115,
|
| 582 |
+
"grad_norm": 2.480574369430542,
|
| 583 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 584 |
+
"loss": 1.9591,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.0019133217982862777,
|
| 589 |
+
"grad_norm": 1.3811838626861572,
|
| 590 |
+
"learning_rate": 1.0599462319663905e-05,
|
| 591 |
+
"loss": 1.5521,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.0019369430550552442,
|
| 596 |
+
"grad_norm": 1.6117287874221802,
|
| 597 |
+
"learning_rate": 9.549150281252633e-06,
|
| 598 |
+
"loss": 1.6701,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.0019605643118242107,
|
| 603 |
+
"grad_norm": 1.5689414739608765,
|
| 604 |
+
"learning_rate": 8.548121372247918e-06,
|
| 605 |
+
"loss": 1.4656,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.001984185568593177,
|
| 610 |
+
"grad_norm": 1.580367088317871,
|
| 611 |
+
"learning_rate": 7.597595192178702e-06,
|
| 612 |
+
"loss": 1.6255,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.002007806825362143,
|
| 617 |
+
"grad_norm": 1.5394359827041626,
|
| 618 |
+
"learning_rate": 6.698729810778065e-06,
|
| 619 |
+
"loss": 1.6227,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.0020314280821311097,
|
| 624 |
+
"grad_norm": 1.3796682357788086,
|
| 625 |
+
"learning_rate": 5.852620357053651e-06,
|
| 626 |
+
"loss": 1.4377,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.002055049338900076,
|
| 631 |
+
"grad_norm": 1.5555745363235474,
|
| 632 |
+
"learning_rate": 5.060297685041659e-06,
|
| 633 |
+
"loss": 1.7109,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.0020786705956690426,
|
| 638 |
+
"grad_norm": 1.5756012201309204,
|
| 639 |
+
"learning_rate": 4.322727117869951e-06,
|
| 640 |
+
"loss": 1.913,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.002102291852438009,
|
| 645 |
+
"grad_norm": 1.368099331855774,
|
| 646 |
+
"learning_rate": 3.6408072716606346e-06,
|
| 647 |
+
"loss": 1.446,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.002125913109206975,
|
| 652 |
+
"grad_norm": 1.5308266878128052,
|
| 653 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 654 |
+
"loss": 1.6731,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.0021495343659759416,
|
| 659 |
+
"grad_norm": 1.6399803161621094,
|
| 660 |
+
"learning_rate": 2.4471741852423237e-06,
|
| 661 |
+
"loss": 1.9263,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.002173155622744908,
|
| 666 |
+
"grad_norm": 1.7179704904556274,
|
| 667 |
+
"learning_rate": 1.9369152030840556e-06,
|
| 668 |
+
"loss": 1.4546,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.0021967768795138746,
|
| 673 |
+
"grad_norm": 1.9310886859893799,
|
| 674 |
+
"learning_rate": 1.4852136862001764e-06,
|
| 675 |
+
"loss": 1.7588,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.002220398136282841,
|
| 680 |
+
"grad_norm": 1.8719663619995117,
|
| 681 |
+
"learning_rate": 1.0926199633097157e-06,
|
| 682 |
+
"loss": 1.7902,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.002244019393051807,
|
| 687 |
+
"grad_norm": 2.372739791870117,
|
| 688 |
+
"learning_rate": 7.596123493895991e-07,
|
| 689 |
+
"loss": 1.6732,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.0022676406498207736,
|
| 694 |
+
"grad_norm": 1.6990795135498047,
|
| 695 |
+
"learning_rate": 4.865965629214819e-07,
|
| 696 |
+
"loss": 1.8265,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.00229126190658974,
|
| 701 |
+
"grad_norm": 1.6857136487960815,
|
| 702 |
+
"learning_rate": 2.7390523158633554e-07,
|
| 703 |
+
"loss": 1.5841,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.0023148831633587066,
|
| 708 |
+
"grad_norm": 1.8094323873519897,
|
| 709 |
+
"learning_rate": 1.2179748700879012e-07,
|
| 710 |
+
"loss": 1.6073,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.002338504420127673,
|
| 715 |
+
"grad_norm": 1.8924447298049927,
|
| 716 |
+
"learning_rate": 3.04586490452119e-08,
|
| 717 |
+
"loss": 1.5823,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.002362125676896639,
|
| 722 |
+
"grad_norm": 1.920559287071228,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 1.6138,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.002362125676896639,
|
| 729 |
+
"eval_loss": 1.812772274017334,
|
| 730 |
+
"eval_runtime": 1141.2879,
|
| 731 |
+
"eval_samples_per_second": 15.619,
|
| 732 |
+
"eval_steps_per_second": 7.81,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 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": 1.334629202264064e+16,
|
| 763 |
"train_batch_size": 2,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|