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 125248064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d390719e90420061be92f39050ed8b64cd9737d7ae4dae9e7083760c10a798c2
|
| 3 |
size 125248064
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 250819170
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41c79e3c9d8abde902f0f433a732dc2e133877afdfdc0288440a45f0207f1588
|
| 3 |
size 250819170
|
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 sha256:609244416217270e346f73df1d9bee8ca588cf7a65d0547ea8b7f46db7233e83
|
| 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":
|
| 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": 9.1,
|
| 374 |
"eval_steps_per_second": 1.213,
|
| 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": 8,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 5.867722511291504,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.704225352112676,
|
| 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": 9.1,
|
| 374 |
"eval_steps_per_second": 1.213,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.3591549295774648,
|
| 379 |
+
"grad_norm": 3.2810099124908447,
|
| 380 |
+
"learning_rate": 3.969463130731183e-06,
|
| 381 |
+
"loss": 6.2124,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.36619718309859156,
|
| 386 |
+
"grad_norm": 3.4586217403411865,
|
| 387 |
+
"learning_rate": 3.8772424536302565e-06,
|
| 388 |
+
"loss": 6.9627,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.3732394366197183,
|
| 393 |
+
"grad_norm": 3.5371925830841064,
|
| 394 |
+
"learning_rate": 3.782248193514766e-06,
|
| 395 |
+
"loss": 5.8214,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.38028169014084506,
|
| 400 |
+
"grad_norm": 3.8232100009918213,
|
| 401 |
+
"learning_rate": 3.684671656182497e-06,
|
| 402 |
+
"loss": 6.1178,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.3873239436619718,
|
| 407 |
+
"grad_norm": 4.544223785400391,
|
| 408 |
+
"learning_rate": 3.5847093477938955e-06,
|
| 409 |
+
"loss": 6.2917,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.39436619718309857,
|
| 414 |
+
"grad_norm": 3.5962297916412354,
|
| 415 |
+
"learning_rate": 3.4825625791348093e-06,
|
| 416 |
+
"loss": 5.5094,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.4014084507042254,
|
| 421 |
+
"grad_norm": 4.584772109985352,
|
| 422 |
+
"learning_rate": 3.3784370602033572e-06,
|
| 423 |
+
"loss": 7.5249,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.4084507042253521,
|
| 428 |
+
"grad_norm": 4.308250427246094,
|
| 429 |
+
"learning_rate": 3.272542485937369e-06,
|
| 430 |
+
"loss": 6.3212,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.4154929577464789,
|
| 435 |
+
"grad_norm": 3.8824479579925537,
|
| 436 |
+
"learning_rate": 3.165092113916688e-06,
|
| 437 |
+
"loss": 5.7734,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.4225352112676056,
|
| 442 |
+
"grad_norm": 3.946568250656128,
|
| 443 |
+
"learning_rate": 3.056302334890786e-06,
|
| 444 |
+
"loss": 6.5095,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.4295774647887324,
|
| 449 |
+
"grad_norm": 3.413088083267212,
|
| 450 |
+
"learning_rate": 2.946392236996592e-06,
|
| 451 |
+
"loss": 6.5014,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.43661971830985913,
|
| 456 |
+
"grad_norm": 3.663517713546753,
|
| 457 |
+
"learning_rate": 2.835583164544139e-06,
|
| 458 |
+
"loss": 6.3028,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.44366197183098594,
|
| 463 |
+
"grad_norm": 3.5873265266418457,
|
| 464 |
+
"learning_rate": 2.724098272258584e-06,
|
| 465 |
+
"loss": 6.5212,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.4507042253521127,
|
| 470 |
+
"grad_norm": 3.847581148147583,
|
| 471 |
+
"learning_rate": 2.6121620758762877e-06,
|
| 472 |
+
"loss": 6.2379,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.45774647887323944,
|
| 477 |
+
"grad_norm": 3.835568428039551,
|
| 478 |
+
"learning_rate": 2.5e-06,
|
| 479 |
+
"loss": 5.7499,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.4647887323943662,
|
| 484 |
+
"grad_norm": 4.436716079711914,
|
| 485 |
+
"learning_rate": 2.3878379241237136e-06,
|
| 486 |
+
"loss": 6.0118,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.47183098591549294,
|
| 491 |
+
"grad_norm": 4.0455002784729,
|
| 492 |
+
"learning_rate": 2.2759017277414165e-06,
|
| 493 |
+
"loss": 5.9979,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.4788732394366197,
|
| 498 |
+
"grad_norm": 4.169304847717285,
|
| 499 |
+
"learning_rate": 2.1644168354558623e-06,
|
| 500 |
+
"loss": 5.4277,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.4859154929577465,
|
| 505 |
+
"grad_norm": 3.745866537094116,
|
| 506 |
+
"learning_rate": 2.053607763003409e-06,
|
| 507 |
+
"loss": 5.9037,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.49295774647887325,
|
| 512 |
+
"grad_norm": 5.223974704742432,
|
| 513 |
+
"learning_rate": 1.9436976651092143e-06,
|
| 514 |
+
"loss": 6.1697,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.5,
|
| 519 |
+
"grad_norm": 3.916987657546997,
|
| 520 |
+
"learning_rate": 1.8349078860833125e-06,
|
| 521 |
+
"loss": 5.6168,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.5070422535211268,
|
| 526 |
+
"grad_norm": 3.2705447673797607,
|
| 527 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 528 |
+
"loss": 5.3624,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.5140845070422535,
|
| 533 |
+
"grad_norm": 4.038527488708496,
|
| 534 |
+
"learning_rate": 1.6215629397966432e-06,
|
| 535 |
+
"loss": 5.6942,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.5211267605633803,
|
| 540 |
+
"grad_norm": 3.7204744815826416,
|
| 541 |
+
"learning_rate": 1.5174374208651913e-06,
|
| 542 |
+
"loss": 5.8837,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.528169014084507,
|
| 547 |
+
"grad_norm": 4.190001487731934,
|
| 548 |
+
"learning_rate": 1.415290652206105e-06,
|
| 549 |
+
"loss": 5.6448,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.5352112676056338,
|
| 554 |
+
"grad_norm": 3.036896228790283,
|
| 555 |
+
"learning_rate": 1.3153283438175036e-06,
|
| 556 |
+
"loss": 5.9509,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.5422535211267606,
|
| 561 |
+
"grad_norm": 4.141100883483887,
|
| 562 |
+
"learning_rate": 1.217751806485235e-06,
|
| 563 |
+
"loss": 5.5891,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.5492957746478874,
|
| 568 |
+
"grad_norm": 3.8306446075439453,
|
| 569 |
+
"learning_rate": 1.122757546369744e-06,
|
| 570 |
+
"loss": 6.0617,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.5563380281690141,
|
| 575 |
+
"grad_norm": 3.9133124351501465,
|
| 576 |
+
"learning_rate": 1.0305368692688175e-06,
|
| 577 |
+
"loss": 5.6559,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.5633802816901409,
|
| 582 |
+
"grad_norm": 3.6098997592926025,
|
| 583 |
+
"learning_rate": 9.412754953531664e-07,
|
| 584 |
+
"loss": 5.2484,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.5704225352112676,
|
| 589 |
+
"grad_norm": 3.8136210441589355,
|
| 590 |
+
"learning_rate": 8.551531851507186e-07,
|
| 591 |
+
"loss": 5.834,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.5774647887323944,
|
| 596 |
+
"grad_norm": 4.0824480056762695,
|
| 597 |
+
"learning_rate": 7.723433775328385e-07,
|
| 598 |
+
"loss": 5.732,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.5845070422535211,
|
| 603 |
+
"grad_norm": 4.940346717834473,
|
| 604 |
+
"learning_rate": 6.930128404315214e-07,
|
| 605 |
+
"loss": 7.0341,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.5915492957746479,
|
| 610 |
+
"grad_norm": 3.8270716667175293,
|
| 611 |
+
"learning_rate": 6.17321334990973e-07,
|
| 612 |
+
"loss": 5.5377,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.5985915492957746,
|
| 617 |
+
"grad_norm": 3.9446895122528076,
|
| 618 |
+
"learning_rate": 5.454212938299256e-07,
|
| 619 |
+
"loss": 5.6576,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.6056338028169014,
|
| 624 |
+
"grad_norm": 4.037410259246826,
|
| 625 |
+
"learning_rate": 4.774575140626317e-07,
|
| 626 |
+
"loss": 5.758,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.6126760563380281,
|
| 631 |
+
"grad_norm": 4.448607921600342,
|
| 632 |
+
"learning_rate": 4.1356686569674344e-07,
|
| 633 |
+
"loss": 5.8112,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.6197183098591549,
|
| 638 |
+
"grad_norm": 3.8815934658050537,
|
| 639 |
+
"learning_rate": 3.538780159953348e-07,
|
| 640 |
+
"loss": 5.6519,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.6267605633802817,
|
| 645 |
+
"grad_norm": 4.358070373535156,
|
| 646 |
+
"learning_rate": 2.98511170358155e-07,
|
| 647 |
+
"loss": 5.7299,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.6338028169014085,
|
| 652 |
+
"grad_norm": 3.2126142978668213,
|
| 653 |
+
"learning_rate": 2.4757783024395244e-07,
|
| 654 |
+
"loss": 6.0813,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.6408450704225352,
|
| 659 |
+
"grad_norm": 3.676884651184082,
|
| 660 |
+
"learning_rate": 2.0118056862137358e-07,
|
| 661 |
+
"loss": 5.6813,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.647887323943662,
|
| 666 |
+
"grad_norm": 3.7823681831359863,
|
| 667 |
+
"learning_rate": 1.59412823400657e-07,
|
| 668 |
+
"loss": 6.4328,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.6549295774647887,
|
| 673 |
+
"grad_norm": 4.694835186004639,
|
| 674 |
+
"learning_rate": 1.223587092621162e-07,
|
| 675 |
+
"loss": 6.0319,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.6619718309859155,
|
| 680 |
+
"grad_norm": 4.232463836669922,
|
| 681 |
+
"learning_rate": 9.00928482603669e-08,
|
| 682 |
+
"loss": 6.6748,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.6690140845070423,
|
| 687 |
+
"grad_norm": 4.175792217254639,
|
| 688 |
+
"learning_rate": 6.268021954544095e-08,
|
| 689 |
+
"loss": 5.7904,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.676056338028169,
|
| 694 |
+
"grad_norm": 3.6760425567626953,
|
| 695 |
+
"learning_rate": 4.017602850342584e-08,
|
| 696 |
+
"loss": 6.246,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.6830985915492958,
|
| 701 |
+
"grad_norm": 3.92482328414917,
|
| 702 |
+
"learning_rate": 2.262559558016325e-08,
|
| 703 |
+
"loss": 6.2813,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.6901408450704225,
|
| 708 |
+
"grad_norm": 3.756988525390625,
|
| 709 |
+
"learning_rate": 1.006426501190233e-08,
|
| 710 |
+
"loss": 6.542,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.6971830985915493,
|
| 715 |
+
"grad_norm": 3.8519887924194336,
|
| 716 |
+
"learning_rate": 2.5173336467135266e-09,
|
| 717 |
+
"loss": 5.1306,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.704225352112676,
|
| 722 |
+
"grad_norm": 5.956462383270264,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 6.0674,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.704225352112676,
|
| 729 |
+
"eval_loss": 5.867722511291504,
|
| 730 |
+
"eval_runtime": 6.5984,
|
| 731 |
+
"eval_samples_per_second": 9.093,
|
| 732 |
+
"eval_steps_per_second": 1.212,
|
| 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": 6.3324486107136e+16,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|