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 3152280
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef61279f2bf4cd12fc49c53183474bbc8bcc5097d72bf7a54e4c0beedf0bc5e7
|
| 3 |
size 3152280
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1655994
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98e82ed9d5b02b754fce7a6df7241dbb95c845559919e2228c85425b80faa5de
|
| 3 |
size 1655994
|
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:e749947282af1c35989f027faed8e39811320d0fc2e2b5979e076fc0359409ed
|
| 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": 5.861966609954834,
|
| 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": 322.452,
|
| 374 |
"eval_steps_per_second": 80.628,
|
| 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": 5.861966609954834,
|
| 3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
| 4 |
+
"epoch": 0.015958507879513265,
|
| 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": 322.452,
|
| 374 |
"eval_steps_per_second": 80.628,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.008138839018551766,
|
| 379 |
+
"grad_norm": 8223.1162109375,
|
| 380 |
+
"learning_rate": 8.894386393810563e-05,
|
| 381 |
+
"loss": 25.4945,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.008298424097346898,
|
| 386 |
+
"grad_norm": 10592.302734375,
|
| 387 |
+
"learning_rate": 8.842005554284296e-05,
|
| 388 |
+
"loss": 24.5778,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.00845800917614203,
|
| 393 |
+
"grad_norm": 8385.9677734375,
|
| 394 |
+
"learning_rate": 8.788574348801675e-05,
|
| 395 |
+
"loss": 25.9506,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.008617594254937163,
|
| 400 |
+
"grad_norm": 7335.70263671875,
|
| 401 |
+
"learning_rate": 8.73410738492077e-05,
|
| 402 |
+
"loss": 25.609,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.008777179333732297,
|
| 407 |
+
"grad_norm": 9103.0751953125,
|
| 408 |
+
"learning_rate": 8.678619553365659e-05,
|
| 409 |
+
"loss": 26.1317,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.008936764412527429,
|
| 414 |
+
"grad_norm": 7378.77001953125,
|
| 415 |
+
"learning_rate": 8.622126023955446e-05,
|
| 416 |
+
"loss": 25.7935,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.00909634949132256,
|
| 421 |
+
"grad_norm": 7147.00732421875,
|
| 422 |
+
"learning_rate": 8.564642241456986e-05,
|
| 423 |
+
"loss": 24.4496,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.009255934570117695,
|
| 428 |
+
"grad_norm": 12204.7705078125,
|
| 429 |
+
"learning_rate": 8.506183921362443e-05,
|
| 430 |
+
"loss": 24.6899,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.009415519648912827,
|
| 435 |
+
"grad_norm": 8410.1923828125,
|
| 436 |
+
"learning_rate": 8.44676704559283e-05,
|
| 437 |
+
"loss": 25.6707,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.009575104727707959,
|
| 442 |
+
"grad_norm": 10212.4814453125,
|
| 443 |
+
"learning_rate": 8.386407858128706e-05,
|
| 444 |
+
"loss": 23.6882,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.009734689806503091,
|
| 449 |
+
"grad_norm": 6584.47314453125,
|
| 450 |
+
"learning_rate": 8.32512286056924e-05,
|
| 451 |
+
"loss": 24.5397,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.009894274885298225,
|
| 456 |
+
"grad_norm": 5907.9482421875,
|
| 457 |
+
"learning_rate": 8.262928807620843e-05,
|
| 458 |
+
"loss": 22.6096,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.010053859964093357,
|
| 463 |
+
"grad_norm": 7186.22607421875,
|
| 464 |
+
"learning_rate": 8.199842702516583e-05,
|
| 465 |
+
"loss": 23.6209,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.01021344504288849,
|
| 470 |
+
"grad_norm": 6641.09033203125,
|
| 471 |
+
"learning_rate": 8.135881792367686e-05,
|
| 472 |
+
"loss": 23.338,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.010373030121683623,
|
| 477 |
+
"grad_norm": 5658.81591796875,
|
| 478 |
+
"learning_rate": 8.07106356344834e-05,
|
| 479 |
+
"loss": 23.7207,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.010532615200478756,
|
| 484 |
+
"grad_norm": 7177.013671875,
|
| 485 |
+
"learning_rate": 8.005405736415126e-05,
|
| 486 |
+
"loss": 23.9108,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.010692200279273888,
|
| 491 |
+
"grad_norm": 6732.58935546875,
|
| 492 |
+
"learning_rate": 7.938926261462366e-05,
|
| 493 |
+
"loss": 24.5683,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.01085178535806902,
|
| 498 |
+
"grad_norm": 7358.6181640625,
|
| 499 |
+
"learning_rate": 7.871643313414718e-05,
|
| 500 |
+
"loss": 23.825,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.011011370436864154,
|
| 505 |
+
"grad_norm": 7550.85009765625,
|
| 506 |
+
"learning_rate": 7.803575286758364e-05,
|
| 507 |
+
"loss": 24.299,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.011170955515659286,
|
| 512 |
+
"grad_norm": 6815.85986328125,
|
| 513 |
+
"learning_rate": 7.734740790612136e-05,
|
| 514 |
+
"loss": 23.8657,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.011330540594454418,
|
| 519 |
+
"grad_norm": 6606.3193359375,
|
| 520 |
+
"learning_rate": 7.66515864363997e-05,
|
| 521 |
+
"loss": 24.9416,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.011490125673249552,
|
| 526 |
+
"grad_norm": 7326.29052734375,
|
| 527 |
+
"learning_rate": 7.594847868906076e-05,
|
| 528 |
+
"loss": 25.5042,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.011649710752044684,
|
| 533 |
+
"grad_norm": 8125.580078125,
|
| 534 |
+
"learning_rate": 7.52382768867422e-05,
|
| 535 |
+
"loss": 23.907,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.011809295830839816,
|
| 540 |
+
"grad_norm": 6935.78564453125,
|
| 541 |
+
"learning_rate": 7.452117519152542e-05,
|
| 542 |
+
"loss": 25.4303,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.011968880909634948,
|
| 547 |
+
"grad_norm": 9573.265625,
|
| 548 |
+
"learning_rate": 7.379736965185368e-05,
|
| 549 |
+
"loss": 24.8344,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.012128465988430082,
|
| 554 |
+
"grad_norm": 28533.166015625,
|
| 555 |
+
"learning_rate": 7.30670581489344e-05,
|
| 556 |
+
"loss": 25.245,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.012288051067225214,
|
| 561 |
+
"grad_norm": 12368.263671875,
|
| 562 |
+
"learning_rate": 7.233044034264034e-05,
|
| 563 |
+
"loss": 25.6614,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.012447636146020347,
|
| 568 |
+
"grad_norm": 9880.244140625,
|
| 569 |
+
"learning_rate": 7.158771761692464e-05,
|
| 570 |
+
"loss": 26.473,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.01260722122481548,
|
| 575 |
+
"grad_norm": 7134.77099609375,
|
| 576 |
+
"learning_rate": 7.083909302476453e-05,
|
| 577 |
+
"loss": 25.645,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.012766806303610613,
|
| 582 |
+
"grad_norm": 10363.2744140625,
|
| 583 |
+
"learning_rate": 7.008477123264848e-05,
|
| 584 |
+
"loss": 25.9955,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.012926391382405745,
|
| 589 |
+
"grad_norm": 9974.3515625,
|
| 590 |
+
"learning_rate": 6.932495846462261e-05,
|
| 591 |
+
"loss": 27.4792,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.013085976461200877,
|
| 596 |
+
"grad_norm": 9845.5234375,
|
| 597 |
+
"learning_rate": 6.855986244591104e-05,
|
| 598 |
+
"loss": 26.5811,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.013245561539996011,
|
| 603 |
+
"grad_norm": 8836.052734375,
|
| 604 |
+
"learning_rate": 6.778969234612584e-05,
|
| 605 |
+
"loss": 26.6617,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.013405146618791143,
|
| 610 |
+
"grad_norm": 12927.6728515625,
|
| 611 |
+
"learning_rate": 6.701465872208216e-05,
|
| 612 |
+
"loss": 26.2224,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.013564731697586275,
|
| 617 |
+
"grad_norm": 9045.453125,
|
| 618 |
+
"learning_rate": 6.623497346023418e-05,
|
| 619 |
+
"loss": 27.1035,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.013724316776381409,
|
| 624 |
+
"grad_norm": 11554.251953125,
|
| 625 |
+
"learning_rate": 6.545084971874738e-05,
|
| 626 |
+
"loss": 27.4664,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.013883901855176541,
|
| 631 |
+
"grad_norm": 7964.716796875,
|
| 632 |
+
"learning_rate": 6.466250186922325e-05,
|
| 633 |
+
"loss": 28.1889,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.014043486933971673,
|
| 638 |
+
"grad_norm": 12251.1572265625,
|
| 639 |
+
"learning_rate": 6.387014543809223e-05,
|
| 640 |
+
"loss": 28.7062,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.014203072012766806,
|
| 645 |
+
"grad_norm": 7720.21044921875,
|
| 646 |
+
"learning_rate": 6.307399704769099e-05,
|
| 647 |
+
"loss": 27.1419,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.01436265709156194,
|
| 652 |
+
"grad_norm": 10327.4296875,
|
| 653 |
+
"learning_rate": 6.227427435703997e-05,
|
| 654 |
+
"loss": 27.173,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.014522242170357072,
|
| 659 |
+
"grad_norm": 7908.88818359375,
|
| 660 |
+
"learning_rate": 6.147119600233758e-05,
|
| 661 |
+
"loss": 27.7945,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.014681827249152204,
|
| 666 |
+
"grad_norm": 9216.611328125,
|
| 667 |
+
"learning_rate": 6.066498153718735e-05,
|
| 668 |
+
"loss": 28.2228,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.014841412327947338,
|
| 673 |
+
"grad_norm": 8026.3251953125,
|
| 674 |
+
"learning_rate": 5.985585137257401e-05,
|
| 675 |
+
"loss": 29.4098,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.01500099740674247,
|
| 680 |
+
"grad_norm": 12522.5390625,
|
| 681 |
+
"learning_rate": 5.90440267166055e-05,
|
| 682 |
+
"loss": 27.7349,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.015160582485537602,
|
| 687 |
+
"grad_norm": 15574.728515625,
|
| 688 |
+
"learning_rate": 5.8229729514036705e-05,
|
| 689 |
+
"loss": 27.6102,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.015320167564332734,
|
| 694 |
+
"grad_norm": 8906.1865234375,
|
| 695 |
+
"learning_rate": 5.74131823855921e-05,
|
| 696 |
+
"loss": 27.8437,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.015479752643127868,
|
| 701 |
+
"grad_norm": 8768.921875,
|
| 702 |
+
"learning_rate": 5.6594608567103456e-05,
|
| 703 |
+
"loss": 27.9484,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.015639337721923,
|
| 708 |
+
"grad_norm": 12503.8388671875,
|
| 709 |
+
"learning_rate": 5.577423184847932e-05,
|
| 710 |
+
"loss": 27.5709,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.015798922800718134,
|
| 715 |
+
"grad_norm": 8710.9033203125,
|
| 716 |
+
"learning_rate": 5.495227651252315e-05,
|
| 717 |
+
"loss": 26.647,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.015958507879513265,
|
| 722 |
+
"grad_norm": 10781.9287109375,
|
| 723 |
+
"learning_rate": 5.4128967273616625e-05,
|
| 724 |
+
"loss": 27.155,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.015958507879513265,
|
| 729 |
+
"eval_loss": 6.847575664520264,
|
| 730 |
+
"eval_runtime": 32.938,
|
| 731 |
+
"eval_samples_per_second": 320.42,
|
| 732 |
+
"eval_steps_per_second": 80.12,
|
| 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": 166277444272128.0,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|