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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca07a323642b44659fe70629f3f7cd37c5b86ad11ace0f5ea4c41ab5d3affb22
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 341314196
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3f4190d474896e86929c6a931b56839bba9f5224cf8ff7c564ccbb60e633f7d
|
| 3 |
size 341314196
|
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:d03739d4f14e57b1756eacd65956bba7077bfde79859cee471a4c69daf9733c1
|
| 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 sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.005914478562772274,
|
| 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": 6.76,
|
| 374 |
"eval_steps_per_second": 1.705,
|
| 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": {
|
|
@@ -401,7 +759,7 @@
|
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 8,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.005914478562772274,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.49443757725587145,
|
| 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": 6.76,
|
| 374 |
"eval_steps_per_second": 1.705,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.2521631644004944,
|
| 379 |
+
"grad_norm": 0.14960375428199768,
|
| 380 |
+
"learning_rate": 8.894386393810563e-05,
|
| 381 |
+
"loss": 0.0053,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.25710754017305315,
|
| 386 |
+
"grad_norm": 0.13269616663455963,
|
| 387 |
+
"learning_rate": 8.842005554284296e-05,
|
| 388 |
+
"loss": 0.0026,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.2620519159456119,
|
| 393 |
+
"grad_norm": 0.06501085311174393,
|
| 394 |
+
"learning_rate": 8.788574348801675e-05,
|
| 395 |
+
"loss": 0.0013,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.2669962917181706,
|
| 400 |
+
"grad_norm": 0.05674945190548897,
|
| 401 |
+
"learning_rate": 8.73410738492077e-05,
|
| 402 |
+
"loss": 0.0009,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.2719406674907293,
|
| 407 |
+
"grad_norm": 0.022370589897036552,
|
| 408 |
+
"learning_rate": 8.678619553365659e-05,
|
| 409 |
+
"loss": 0.0005,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.276885043263288,
|
| 414 |
+
"grad_norm": 0.0845404639840126,
|
| 415 |
+
"learning_rate": 8.622126023955446e-05,
|
| 416 |
+
"loss": 0.0019,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.28182941903584674,
|
| 421 |
+
"grad_norm": 0.0986766517162323,
|
| 422 |
+
"learning_rate": 8.564642241456986e-05,
|
| 423 |
+
"loss": 0.003,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.2867737948084054,
|
| 428 |
+
"grad_norm": 0.19640104472637177,
|
| 429 |
+
"learning_rate": 8.506183921362443e-05,
|
| 430 |
+
"loss": 0.0053,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.29171817058096416,
|
| 435 |
+
"grad_norm": 0.130096897482872,
|
| 436 |
+
"learning_rate": 8.44676704559283e-05,
|
| 437 |
+
"loss": 0.0035,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.29666254635352285,
|
| 442 |
+
"grad_norm": 0.16641069948673248,
|
| 443 |
+
"learning_rate": 8.386407858128706e-05,
|
| 444 |
+
"loss": 0.0039,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.3016069221260816,
|
| 449 |
+
"grad_norm": 0.11631468683481216,
|
| 450 |
+
"learning_rate": 8.32512286056924e-05,
|
| 451 |
+
"loss": 0.0023,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.3065512978986403,
|
| 456 |
+
"grad_norm": 0.2868841588497162,
|
| 457 |
+
"learning_rate": 8.262928807620843e-05,
|
| 458 |
+
"loss": 0.0012,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.311495673671199,
|
| 463 |
+
"grad_norm": 0.015549149364233017,
|
| 464 |
+
"learning_rate": 8.199842702516583e-05,
|
| 465 |
+
"loss": 0.0004,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.3164400494437577,
|
| 470 |
+
"grad_norm": 0.2190394401550293,
|
| 471 |
+
"learning_rate": 8.135881792367686e-05,
|
| 472 |
+
"loss": 0.0012,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.32138442521631644,
|
| 477 |
+
"grad_norm": 0.05332758650183678,
|
| 478 |
+
"learning_rate": 8.07106356344834e-05,
|
| 479 |
+
"loss": 0.0012,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.3263288009888752,
|
| 484 |
+
"grad_norm": 0.008343772031366825,
|
| 485 |
+
"learning_rate": 8.005405736415126e-05,
|
| 486 |
+
"loss": 0.0002,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.33127317676143386,
|
| 491 |
+
"grad_norm": 0.09175986051559448,
|
| 492 |
+
"learning_rate": 7.938926261462366e-05,
|
| 493 |
+
"loss": 0.0018,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.3362175525339926,
|
| 498 |
+
"grad_norm": 0.2049993872642517,
|
| 499 |
+
"learning_rate": 7.871643313414718e-05,
|
| 500 |
+
"loss": 0.0021,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.3411619283065513,
|
| 505 |
+
"grad_norm": 0.034642044454813004,
|
| 506 |
+
"learning_rate": 7.803575286758364e-05,
|
| 507 |
+
"loss": 0.0007,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.34610630407911,
|
| 512 |
+
"grad_norm": 0.009048677049577236,
|
| 513 |
+
"learning_rate": 7.734740790612136e-05,
|
| 514 |
+
"loss": 0.0002,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.3510506798516687,
|
| 519 |
+
"grad_norm": 0.038504548370838165,
|
| 520 |
+
"learning_rate": 7.66515864363997e-05,
|
| 521 |
+
"loss": 0.0006,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.35599505562422745,
|
| 526 |
+
"grad_norm": 0.22435835003852844,
|
| 527 |
+
"learning_rate": 7.594847868906076e-05,
|
| 528 |
+
"loss": 0.004,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.36093943139678614,
|
| 533 |
+
"grad_norm": 0.00362699618563056,
|
| 534 |
+
"learning_rate": 7.52382768867422e-05,
|
| 535 |
+
"loss": 0.0001,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.3658838071693449,
|
| 540 |
+
"grad_norm": 0.22229711711406708,
|
| 541 |
+
"learning_rate": 7.452117519152542e-05,
|
| 542 |
+
"loss": 0.0009,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.37082818294190356,
|
| 547 |
+
"grad_norm": 0.003972846549004316,
|
| 548 |
+
"learning_rate": 7.379736965185368e-05,
|
| 549 |
+
"loss": 0.0001,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.3757725587144623,
|
| 554 |
+
"grad_norm": 0.005316532216966152,
|
| 555 |
+
"learning_rate": 7.30670581489344e-05,
|
| 556 |
+
"loss": 0.0001,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.380716934487021,
|
| 561 |
+
"grad_norm": 0.003356312867254019,
|
| 562 |
+
"learning_rate": 7.233044034264034e-05,
|
| 563 |
+
"loss": 0.0001,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.3856613102595797,
|
| 568 |
+
"grad_norm": 0.023712005466222763,
|
| 569 |
+
"learning_rate": 7.158771761692464e-05,
|
| 570 |
+
"loss": 0.0006,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.39060568603213847,
|
| 575 |
+
"grad_norm": 0.0036223619244992733,
|
| 576 |
+
"learning_rate": 7.083909302476453e-05,
|
| 577 |
+
"loss": 0.0001,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.39555006180469715,
|
| 582 |
+
"grad_norm": 0.07850874960422516,
|
| 583 |
+
"learning_rate": 7.008477123264848e-05,
|
| 584 |
+
"loss": 0.0008,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.4004944375772559,
|
| 589 |
+
"grad_norm": 2.543851852416992,
|
| 590 |
+
"learning_rate": 6.932495846462261e-05,
|
| 591 |
+
"loss": 0.0112,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.4054388133498146,
|
| 596 |
+
"grad_norm": 0.005454899277538061,
|
| 597 |
+
"learning_rate": 6.855986244591104e-05,
|
| 598 |
+
"loss": 0.0001,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.4103831891223733,
|
| 603 |
+
"grad_norm": 0.004248406272381544,
|
| 604 |
+
"learning_rate": 6.778969234612584e-05,
|
| 605 |
+
"loss": 0.0001,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.415327564894932,
|
| 610 |
+
"grad_norm": 0.24411757290363312,
|
| 611 |
+
"learning_rate": 6.701465872208216e-05,
|
| 612 |
+
"loss": 0.003,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.42027194066749074,
|
| 617 |
+
"grad_norm": 0.22071103751659393,
|
| 618 |
+
"learning_rate": 6.623497346023418e-05,
|
| 619 |
+
"loss": 0.0008,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.4252163164400494,
|
| 624 |
+
"grad_norm": 0.35767996311187744,
|
| 625 |
+
"learning_rate": 6.545084971874738e-05,
|
| 626 |
+
"loss": 0.0045,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.43016069221260816,
|
| 631 |
+
"grad_norm": 0.009658634662628174,
|
| 632 |
+
"learning_rate": 6.466250186922325e-05,
|
| 633 |
+
"loss": 0.0001,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.43510506798516685,
|
| 638 |
+
"grad_norm": 0.4618425965309143,
|
| 639 |
+
"learning_rate": 6.387014543809223e-05,
|
| 640 |
+
"loss": 0.0089,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.4400494437577256,
|
| 645 |
+
"grad_norm": 0.039499297738075256,
|
| 646 |
+
"learning_rate": 6.307399704769099e-05,
|
| 647 |
+
"loss": 0.0005,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.44499381953028433,
|
| 652 |
+
"grad_norm": 0.12824542820453644,
|
| 653 |
+
"learning_rate": 6.227427435703997e-05,
|
| 654 |
+
"loss": 0.0016,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.449938195302843,
|
| 659 |
+
"grad_norm": 0.04189825803041458,
|
| 660 |
+
"learning_rate": 6.147119600233758e-05,
|
| 661 |
+
"loss": 0.0005,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.45488257107540175,
|
| 666 |
+
"grad_norm": 0.03173510730266571,
|
| 667 |
+
"learning_rate": 6.066498153718735e-05,
|
| 668 |
+
"loss": 0.0004,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.45982694684796044,
|
| 673 |
+
"grad_norm": 0.2132241427898407,
|
| 674 |
+
"learning_rate": 5.985585137257401e-05,
|
| 675 |
+
"loss": 0.0106,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.4647713226205192,
|
| 680 |
+
"grad_norm": 0.5073721408843994,
|
| 681 |
+
"learning_rate": 5.90440267166055e-05,
|
| 682 |
+
"loss": 0.0038,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.46971569839307786,
|
| 687 |
+
"grad_norm": 0.08248043805360794,
|
| 688 |
+
"learning_rate": 5.8229729514036705e-05,
|
| 689 |
+
"loss": 0.0005,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.4746600741656366,
|
| 694 |
+
"grad_norm": 0.00955149345099926,
|
| 695 |
+
"learning_rate": 5.74131823855921e-05,
|
| 696 |
+
"loss": 0.0002,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.4796044499381953,
|
| 701 |
+
"grad_norm": 0.09334550052881241,
|
| 702 |
+
"learning_rate": 5.6594608567103456e-05,
|
| 703 |
+
"loss": 0.0006,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.484548825710754,
|
| 708 |
+
"grad_norm": 0.2532207667827606,
|
| 709 |
+
"learning_rate": 5.577423184847932e-05,
|
| 710 |
+
"loss": 0.0054,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.4894932014833127,
|
| 715 |
+
"grad_norm": 0.030377449467778206,
|
| 716 |
+
"learning_rate": 5.495227651252315e-05,
|
| 717 |
+
"loss": 0.0005,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.49443757725587145,
|
| 722 |
+
"grad_norm": 0.8488153219223022,
|
| 723 |
+
"learning_rate": 5.4128967273616625e-05,
|
| 724 |
+
"loss": 0.0039,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.49443757725587145,
|
| 729 |
+
"eval_loss": 0.008121917955577374,
|
| 730 |
+
"eval_runtime": 50.4991,
|
| 731 |
+
"eval_samples_per_second": 6.753,
|
| 732 |
+
"eval_steps_per_second": 1.703,
|
| 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": {
|
|
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 3.017027157491712e+17,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|