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 sha256:398a63a914601e65fd72d955e3ee1636962e1c25746ced4da85c0451cbcc754c
|
| 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 1342555602
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27995e8c851b6ed1b65e6635000fe406eba2a896b7919c5074b4510897740b41
|
| 3 |
size 1342555602
|
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 sha256:1c7760b223f3bf0b5bc9dd2b260337eae03f343febddf5bffebf9d6c3538aff8
|
| 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.
|
| 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": 8.062,
|
| 374 |
"eval_steps_per_second": 2.017,
|
| 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": 0.23508746922016144,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.007125552230297848,
|
| 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": 8.062,
|
| 374 |
"eval_steps_per_second": 2.017,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.0036340316374519027,
|
| 379 |
+
"grad_norm": 0.9585462808609009,
|
| 380 |
+
"learning_rate": 2.3816778784387097e-05,
|
| 381 |
+
"loss": 0.4262,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.003705287159754881,
|
| 386 |
+
"grad_norm": 1.3350521326065063,
|
| 387 |
+
"learning_rate": 2.3263454721781537e-05,
|
| 388 |
+
"loss": 0.3508,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.0037765426820578593,
|
| 393 |
+
"grad_norm": 0.9149147868156433,
|
| 394 |
+
"learning_rate": 2.2693489161088592e-05,
|
| 395 |
+
"loss": 0.2918,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.003847798204360838,
|
| 400 |
+
"grad_norm": 0.9929086565971375,
|
| 401 |
+
"learning_rate": 2.210802993709498e-05,
|
| 402 |
+
"loss": 0.2762,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.003919053726663816,
|
| 407 |
+
"grad_norm": 1.152302861213684,
|
| 408 |
+
"learning_rate": 2.1508256086763372e-05,
|
| 409 |
+
"loss": 0.4493,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.003990309248966795,
|
| 414 |
+
"grad_norm": 0.7821376919746399,
|
| 415 |
+
"learning_rate": 2.0895375474808857e-05,
|
| 416 |
+
"loss": 0.3416,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.004061564771269773,
|
| 421 |
+
"grad_norm": 0.9475064277648926,
|
| 422 |
+
"learning_rate": 2.0270622361220143e-05,
|
| 423 |
+
"loss": 0.2441,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.004132820293572752,
|
| 428 |
+
"grad_norm": 1.1275452375411987,
|
| 429 |
+
"learning_rate": 1.963525491562421e-05,
|
| 430 |
+
"loss": 0.2919,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.0042040758158757305,
|
| 435 |
+
"grad_norm": 1.3180280923843384,
|
| 436 |
+
"learning_rate": 1.8990552683500128e-05,
|
| 437 |
+
"loss": 0.3509,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.004275331338178709,
|
| 442 |
+
"grad_norm": 0.9340567588806152,
|
| 443 |
+
"learning_rate": 1.8337814009344716e-05,
|
| 444 |
+
"loss": 0.3231,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.004346586860481687,
|
| 449 |
+
"grad_norm": 0.8491362929344177,
|
| 450 |
+
"learning_rate": 1.767835342197955e-05,
|
| 451 |
+
"loss": 0.241,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.004417842382784666,
|
| 456 |
+
"grad_norm": 1.1892591714859009,
|
| 457 |
+
"learning_rate": 1.7013498987264832e-05,
|
| 458 |
+
"loss": 0.2353,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.004489097905087645,
|
| 463 |
+
"grad_norm": 0.8448580503463745,
|
| 464 |
+
"learning_rate": 1.6344589633551502e-05,
|
| 465 |
+
"loss": 0.317,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.0045603534273906225,
|
| 470 |
+
"grad_norm": 1.1618448495864868,
|
| 471 |
+
"learning_rate": 1.5672972455257726e-05,
|
| 472 |
+
"loss": 0.3225,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.004631608949693601,
|
| 477 |
+
"grad_norm": 1.12700355052948,
|
| 478 |
+
"learning_rate": 1.5e-05,
|
| 479 |
+
"loss": 0.3619,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.00470286447199658,
|
| 484 |
+
"grad_norm": 1.1308168172836304,
|
| 485 |
+
"learning_rate": 1.4327027544742281e-05,
|
| 486 |
+
"loss": 0.3482,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.004774119994299558,
|
| 491 |
+
"grad_norm": 0.7516178488731384,
|
| 492 |
+
"learning_rate": 1.36554103664485e-05,
|
| 493 |
+
"loss": 0.1622,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.004845375516602537,
|
| 498 |
+
"grad_norm": 1.1769253015518188,
|
| 499 |
+
"learning_rate": 1.2986501012735174e-05,
|
| 500 |
+
"loss": 0.2047,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.004916631038905515,
|
| 505 |
+
"grad_norm": 0.9646146297454834,
|
| 506 |
+
"learning_rate": 1.2321646578020452e-05,
|
| 507 |
+
"loss": 0.2437,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.004987886561208493,
|
| 512 |
+
"grad_norm": 1.2298526763916016,
|
| 513 |
+
"learning_rate": 1.1662185990655285e-05,
|
| 514 |
+
"loss": 0.4731,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.005059142083511472,
|
| 519 |
+
"grad_norm": 0.7508978247642517,
|
| 520 |
+
"learning_rate": 1.1009447316499875e-05,
|
| 521 |
+
"loss": 0.1173,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.005130397605814451,
|
| 526 |
+
"grad_norm": 1.2414405345916748,
|
| 527 |
+
"learning_rate": 1.036474508437579e-05,
|
| 528 |
+
"loss": 0.293,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.0052016531281174295,
|
| 533 |
+
"grad_norm": 0.951433539390564,
|
| 534 |
+
"learning_rate": 9.729377638779859e-06,
|
| 535 |
+
"loss": 0.1768,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.005272908650420407,
|
| 540 |
+
"grad_norm": 1.0032628774642944,
|
| 541 |
+
"learning_rate": 9.104624525191147e-06,
|
| 542 |
+
"loss": 0.2115,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.005344164172723386,
|
| 547 |
+
"grad_norm": 1.182035207748413,
|
| 548 |
+
"learning_rate": 8.491743913236629e-06,
|
| 549 |
+
"loss": 0.2316,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.005415419695026365,
|
| 554 |
+
"grad_norm": 1.3811928033828735,
|
| 555 |
+
"learning_rate": 7.89197006290502e-06,
|
| 556 |
+
"loss": 0.2767,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.005486675217329343,
|
| 561 |
+
"grad_norm": 1.2715567350387573,
|
| 562 |
+
"learning_rate": 7.30651083891141e-06,
|
| 563 |
+
"loss": 0.1368,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.0055579307396323215,
|
| 568 |
+
"grad_norm": 1.1821553707122803,
|
| 569 |
+
"learning_rate": 6.736545278218464e-06,
|
| 570 |
+
"loss": 0.164,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.0056291862619353,
|
| 575 |
+
"grad_norm": 1.0368329286575317,
|
| 576 |
+
"learning_rate": 6.1832212156129045e-06,
|
| 577 |
+
"loss": 0.2001,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.005700441784238278,
|
| 582 |
+
"grad_norm": 0.8645971417427063,
|
| 583 |
+
"learning_rate": 5.647652972118998e-06,
|
| 584 |
+
"loss": 0.1707,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.005771697306541257,
|
| 589 |
+
"grad_norm": 0.9727141857147217,
|
| 590 |
+
"learning_rate": 5.130919110904311e-06,
|
| 591 |
+
"loss": 0.2369,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.005842952828844236,
|
| 596 |
+
"grad_norm": 0.7467105388641357,
|
| 597 |
+
"learning_rate": 4.6340602651970304e-06,
|
| 598 |
+
"loss": 0.1482,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.0059142083511472135,
|
| 603 |
+
"grad_norm": 1.139006495475769,
|
| 604 |
+
"learning_rate": 4.158077042589129e-06,
|
| 605 |
+
"loss": 0.1787,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.005985463873450192,
|
| 610 |
+
"grad_norm": 1.2143248319625854,
|
| 611 |
+
"learning_rate": 3.7039280099458373e-06,
|
| 612 |
+
"loss": 0.2871,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.006056719395753171,
|
| 617 |
+
"grad_norm": 2.230907678604126,
|
| 618 |
+
"learning_rate": 3.272527762979553e-06,
|
| 619 |
+
"loss": 0.2485,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.00612797491805615,
|
| 624 |
+
"grad_norm": 1.4834065437316895,
|
| 625 |
+
"learning_rate": 2.86474508437579e-06,
|
| 626 |
+
"loss": 0.2082,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.006199230440359128,
|
| 631 |
+
"grad_norm": 1.2078521251678467,
|
| 632 |
+
"learning_rate": 2.4814011941804603e-06,
|
| 633 |
+
"loss": 0.205,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.006270485962662106,
|
| 638 |
+
"grad_norm": 1.078839659690857,
|
| 639 |
+
"learning_rate": 2.1232680959720085e-06,
|
| 640 |
+
"loss": 0.1255,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.006341741484965085,
|
| 645 |
+
"grad_norm": 1.7553359270095825,
|
| 646 |
+
"learning_rate": 1.79106702214893e-06,
|
| 647 |
+
"loss": 0.271,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.006412997007268063,
|
| 652 |
+
"grad_norm": 1.4102157354354858,
|
| 653 |
+
"learning_rate": 1.4854669814637145e-06,
|
| 654 |
+
"loss": 0.192,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.006484252529571042,
|
| 659 |
+
"grad_norm": 0.9362900853157043,
|
| 660 |
+
"learning_rate": 1.2070834117282414e-06,
|
| 661 |
+
"loss": 0.1759,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.0065555080518740205,
|
| 666 |
+
"grad_norm": 1.3166675567626953,
|
| 667 |
+
"learning_rate": 9.56476940403942e-07,
|
| 668 |
+
"loss": 0.2363,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.006626763574176998,
|
| 673 |
+
"grad_norm": 1.0089662075042725,
|
| 674 |
+
"learning_rate": 7.341522555726971e-07,
|
| 675 |
+
"loss": 0.2477,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.006698019096479977,
|
| 680 |
+
"grad_norm": 1.362122654914856,
|
| 681 |
+
"learning_rate": 5.405570895622014e-07,
|
| 682 |
+
"loss": 0.2324,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.006769274618782956,
|
| 687 |
+
"grad_norm": 0.8471099734306335,
|
| 688 |
+
"learning_rate": 3.760813172726457e-07,
|
| 689 |
+
"loss": 0.1179,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.006840530141085934,
|
| 694 |
+
"grad_norm": 1.2971007823944092,
|
| 695 |
+
"learning_rate": 2.41056171020555e-07,
|
| 696 |
+
"loss": 0.1556,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.0069117856633889125,
|
| 701 |
+
"grad_norm": 1.1084494590759277,
|
| 702 |
+
"learning_rate": 1.357535734809795e-07,
|
| 703 |
+
"loss": 0.2148,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.006983041185691891,
|
| 708 |
+
"grad_norm": 1.6969143152236938,
|
| 709 |
+
"learning_rate": 6.038559007141397e-08,
|
| 710 |
+
"loss": 0.2654,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.00705429670799487,
|
| 715 |
+
"grad_norm": 1.321176290512085,
|
| 716 |
+
"learning_rate": 1.510400188028116e-08,
|
| 717 |
+
"loss": 0.2057,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.007125552230297848,
|
| 722 |
+
"grad_norm": 1.1489577293395996,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 0.1503,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.007125552230297848,
|
| 729 |
+
"eval_loss": 0.23508746922016144,
|
| 730 |
+
"eval_runtime": 733.1631,
|
| 731 |
+
"eval_samples_per_second": 8.06,
|
| 732 |
+
"eval_steps_per_second": 2.016,
|
| 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": 3.808996786333286e+16,
|
| 763 |
"train_batch_size": 4,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|