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 250422888
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30a702ee11aa57217448569c1d96935a04f058a576b208b0e6cc99ea36be366e
|
| 3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 501168482
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3024fe3f70943a7674cfd20e664968a631ff4fa5cd2b5fb2db7d15e7c5058a7f
|
| 3 |
size 501168482
|
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 sha256:132201abd885617e537d179cc1b008603572473f426c5dec98155cf41d88508e
|
| 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:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 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": 5.954,
|
| 374 |
"eval_steps_per_second": 1.489,
|
| 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": 4,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.786036252975464,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.03195270998921596,
|
| 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": 5.954,
|
| 374 |
"eval_steps_per_second": 1.489,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.01629588209450014,
|
| 379 |
+
"grad_norm": 0.4598936140537262,
|
| 380 |
+
"learning_rate": 2.847932752400164e-06,
|
| 381 |
+
"loss": 14.898,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.0166154091943923,
|
| 386 |
+
"grad_norm": 0.5623840689659119,
|
| 387 |
+
"learning_rate": 2.761321158169134e-06,
|
| 388 |
+
"loss": 14.9036,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.01693493629428446,
|
| 393 |
+
"grad_norm": 0.5559747815132141,
|
| 394 |
+
"learning_rate": 2.6743911843603134e-06,
|
| 395 |
+
"loss": 13.1005,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.01725446339417662,
|
| 400 |
+
"grad_norm": 0.7431466579437256,
|
| 401 |
+
"learning_rate": 2.587248741756253e-06,
|
| 402 |
+
"loss": 16.5878,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.017573990494068777,
|
| 407 |
+
"grad_norm": 0.8783532977104187,
|
| 408 |
+
"learning_rate": 2.5e-06,
|
| 409 |
+
"loss": 17.6206,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.017893517593960937,
|
| 414 |
+
"grad_norm": 0.8926708698272705,
|
| 415 |
+
"learning_rate": 2.4127512582437486e-06,
|
| 416 |
+
"loss": 16.7598,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.018213044693853098,
|
| 421 |
+
"grad_norm": 0.993622899055481,
|
| 422 |
+
"learning_rate": 2.325608815639687e-06,
|
| 423 |
+
"loss": 18.1749,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.018532571793745258,
|
| 428 |
+
"grad_norm": 1.064647912979126,
|
| 429 |
+
"learning_rate": 2.238678841830867e-06,
|
| 430 |
+
"loss": 16.2944,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.018852098893637415,
|
| 435 |
+
"grad_norm": 1.0806492567062378,
|
| 436 |
+
"learning_rate": 2.1520672475998374e-06,
|
| 437 |
+
"loss": 15.8283,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.019171625993529576,
|
| 442 |
+
"grad_norm": 1.020936369895935,
|
| 443 |
+
"learning_rate": 2.0658795558326745e-06,
|
| 444 |
+
"loss": 17.8089,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.019491153093421736,
|
| 449 |
+
"grad_norm": 1.0202960968017578,
|
| 450 |
+
"learning_rate": 1.9802207729556023e-06,
|
| 451 |
+
"loss": 16.9171,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.019810680193313897,
|
| 456 |
+
"grad_norm": 1.1508572101593018,
|
| 457 |
+
"learning_rate": 1.895195261000831e-06,
|
| 458 |
+
"loss": 17.2636,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.020130207293206054,
|
| 463 |
+
"grad_norm": 1.0971193313598633,
|
| 464 |
+
"learning_rate": 1.8109066104575023e-06,
|
| 465 |
+
"loss": 17.0854,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.020449734393098214,
|
| 470 |
+
"grad_norm": 1.3636854887008667,
|
| 471 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 472 |
+
"loss": 17.5989,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.020769261492990375,
|
| 477 |
+
"grad_norm": 1.2558183670043945,
|
| 478 |
+
"learning_rate": 1.6449496416858285e-06,
|
| 479 |
+
"loss": 17.343,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.021088788592882535,
|
| 484 |
+
"grad_norm": 1.7393505573272705,
|
| 485 |
+
"learning_rate": 1.56348351646022e-06,
|
| 486 |
+
"loss": 18.1173,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.021408315692774692,
|
| 491 |
+
"grad_norm": 1.3264778852462769,
|
| 492 |
+
"learning_rate": 1.4831583923105e-06,
|
| 493 |
+
"loss": 17.7952,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.021727842792666853,
|
| 498 |
+
"grad_norm": 1.246366024017334,
|
| 499 |
+
"learning_rate": 1.4040721330273063e-06,
|
| 500 |
+
"loss": 18.808,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.022047369892559013,
|
| 505 |
+
"grad_norm": 1.3943363428115845,
|
| 506 |
+
"learning_rate": 1.3263210930352737e-06,
|
| 507 |
+
"loss": 19.9147,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.02236689699245117,
|
| 512 |
+
"grad_norm": 1.5551766157150269,
|
| 513 |
+
"learning_rate": 1.2500000000000007e-06,
|
| 514 |
+
"loss": 18.7218,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.02268642409234333,
|
| 519 |
+
"grad_norm": 1.5984143018722534,
|
| 520 |
+
"learning_rate": 1.1752018394169882e-06,
|
| 521 |
+
"loss": 19.9538,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.02300595119223549,
|
| 526 |
+
"grad_norm": 1.7078524827957153,
|
| 527 |
+
"learning_rate": 1.1020177413231334e-06,
|
| 528 |
+
"loss": 19.0477,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.023325478292127652,
|
| 533 |
+
"grad_norm": 1.86801278591156,
|
| 534 |
+
"learning_rate": 1.0305368692688175e-06,
|
| 535 |
+
"loss": 19.7327,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.02364500539201981,
|
| 540 |
+
"grad_norm": 1.7517181634902954,
|
| 541 |
+
"learning_rate": 9.608463116858544e-07,
|
| 542 |
+
"loss": 19.406,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.02396453249191197,
|
| 547 |
+
"grad_norm": 1.7723991870880127,
|
| 548 |
+
"learning_rate": 8.930309757836517e-07,
|
| 549 |
+
"loss": 19.6767,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.02428405959180413,
|
| 554 |
+
"grad_norm": 1.7405762672424316,
|
| 555 |
+
"learning_rate": 8.271734841028553e-07,
|
| 556 |
+
"loss": 18.9852,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.02460358669169629,
|
| 561 |
+
"grad_norm": 2.2709810733795166,
|
| 562 |
+
"learning_rate": 7.633540738525066e-07,
|
| 563 |
+
"loss": 16.1077,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.024923113791588448,
|
| 568 |
+
"grad_norm": 2.5845401287078857,
|
| 569 |
+
"learning_rate": 7.016504991533727e-07,
|
| 570 |
+
"loss": 16.7456,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.02524264089148061,
|
| 575 |
+
"grad_norm": 2.6944775581359863,
|
| 576 |
+
"learning_rate": 6.421379363065142e-07,
|
| 577 |
+
"loss": 17.1069,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.02556216799137277,
|
| 582 |
+
"grad_norm": 2.878634214401245,
|
| 583 |
+
"learning_rate": 5.848888922025553e-07,
|
| 584 |
+
"loss": 18.3942,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.02588169509126493,
|
| 589 |
+
"grad_norm": 3.0304110050201416,
|
| 590 |
+
"learning_rate": 5.299731159831953e-07,
|
| 591 |
+
"loss": 17.8819,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.026201222191157086,
|
| 596 |
+
"grad_norm": 3.3057451248168945,
|
| 597 |
+
"learning_rate": 4.774575140626317e-07,
|
| 598 |
+
"loss": 18.5736,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.026520749291049247,
|
| 603 |
+
"grad_norm": 3.3953466415405273,
|
| 604 |
+
"learning_rate": 4.27406068612396e-07,
|
| 605 |
+
"loss": 23.0032,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.026840276390941407,
|
| 610 |
+
"grad_norm": 4.374539375305176,
|
| 611 |
+
"learning_rate": 3.798797596089351e-07,
|
| 612 |
+
"loss": 25.4286,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.027159803490833568,
|
| 617 |
+
"grad_norm": 3.490527391433716,
|
| 618 |
+
"learning_rate": 3.3493649053890325e-07,
|
| 619 |
+
"loss": 26.9727,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.027479330590725725,
|
| 624 |
+
"grad_norm": 4.934103488922119,
|
| 625 |
+
"learning_rate": 2.9263101785268253e-07,
|
| 626 |
+
"loss": 28.1652,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.027798857690617886,
|
| 631 |
+
"grad_norm": 4.795266151428223,
|
| 632 |
+
"learning_rate": 2.53014884252083e-07,
|
| 633 |
+
"loss": 30.8333,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.028118384790510046,
|
| 638 |
+
"grad_norm": 4.224905490875244,
|
| 639 |
+
"learning_rate": 2.1613635589349756e-07,
|
| 640 |
+
"loss": 27.3162,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.028437911890402203,
|
| 645 |
+
"grad_norm": 4.559455394744873,
|
| 646 |
+
"learning_rate": 1.8204036358303173e-07,
|
| 647 |
+
"loss": 29.1512,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.028757438990294364,
|
| 652 |
+
"grad_norm": 4.907705307006836,
|
| 653 |
+
"learning_rate": 1.507684480352292e-07,
|
| 654 |
+
"loss": 29.6763,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.029076966090186524,
|
| 659 |
+
"grad_norm": 5.672667026519775,
|
| 660 |
+
"learning_rate": 1.223587092621162e-07,
|
| 661 |
+
"loss": 30.8263,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.029396493190078685,
|
| 666 |
+
"grad_norm": 8.072755813598633,
|
| 667 |
+
"learning_rate": 9.684576015420277e-08,
|
| 668 |
+
"loss": 30.6112,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.02971602028997084,
|
| 673 |
+
"grad_norm": 6.152291774749756,
|
| 674 |
+
"learning_rate": 7.426068431000883e-08,
|
| 675 |
+
"loss": 31.3257,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.030035547389863002,
|
| 680 |
+
"grad_norm": 7.361919403076172,
|
| 681 |
+
"learning_rate": 5.463099816548578e-08,
|
| 682 |
+
"loss": 31.6235,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.030355074489755163,
|
| 687 |
+
"grad_norm": 6.712725639343262,
|
| 688 |
+
"learning_rate": 3.798061746947995e-08,
|
| 689 |
+
"loss": 33.694,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.030674601589647323,
|
| 694 |
+
"grad_norm": 8.276151657104492,
|
| 695 |
+
"learning_rate": 2.4329828146074096e-08,
|
| 696 |
+
"loss": 34.3615,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.03099412868953948,
|
| 701 |
+
"grad_norm": 7.104736804962158,
|
| 702 |
+
"learning_rate": 1.3695261579316776e-08,
|
| 703 |
+
"loss": 34.9578,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.03131365578943164,
|
| 708 |
+
"grad_norm": 9.987726211547852,
|
| 709 |
+
"learning_rate": 6.089874350439507e-09,
|
| 710 |
+
"loss": 34.2474,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.0316331828893238,
|
| 715 |
+
"grad_norm": 10.876480102539062,
|
| 716 |
+
"learning_rate": 1.5229324522605949e-09,
|
| 717 |
+
"loss": 38.6954,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.03195270998921596,
|
| 722 |
+
"grad_norm": 15.421370506286621,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 41.5902,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.03195270998921596,
|
| 729 |
+
"eval_loss": 2.786036252975464,
|
| 730 |
+
"eval_runtime": 886.1971,
|
| 731 |
+
"eval_samples_per_second": 5.948,
|
| 732 |
+
"eval_steps_per_second": 1.487,
|
| 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": 2.6533929242591232e+17,
|
| 763 |
"train_batch_size": 4,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|