Training in progress, step 100, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1008303016
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa0366c83d309f7521675441df462578bea7f619437923da130a73f4b3e1ef98
|
| 3 |
size 1008303016
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1086712487
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44564ad6d459ee8b6824ecc63fbcda48f4afb20f4f7137194943df892c91515f
|
| 3 |
size 1086712487
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9efd33af97ed562c15fc83318701d580bcf56272c251b44d09ee6d97b4cc32c1
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccc24e81b738d82c9183e6957980e5f32ed351a8d1b2f1f22e0d6adc4bee1861
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 50,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -366,6 +366,364 @@
|
|
| 366 |
"eval_samples_per_second": 11.856,
|
| 367 |
"eval_steps_per_second": 2.969,
|
| 368 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 369 |
}
|
| 370 |
],
|
| 371 |
"logging_steps": 1,
|
|
@@ -385,7 +743,7 @@
|
|
| 385 |
"attributes": {}
|
| 386 |
}
|
| 387 |
},
|
| 388 |
-
"total_flos":
|
| 389 |
"train_batch_size": 4,
|
| 390 |
"trial_name": null,
|
| 391 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.8561872909698997,
|
| 6 |
"eval_steps": 50,
|
| 7 |
+
"global_step": 100,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 366 |
"eval_samples_per_second": 11.856,
|
| 367 |
"eval_steps_per_second": 2.969,
|
| 368 |
"step": 50
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.43665551839464883,
|
| 372 |
+
"grad_norm": 0.490234375,
|
| 373 |
+
"learning_rate": 0.02154667547631338,
|
| 374 |
+
"loss": 6.548553466796875,
|
| 375 |
+
"step": 51
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.44521739130434784,
|
| 379 |
+
"grad_norm": 0.4296875,
|
| 380 |
+
"learning_rate": 0.02140867714223579,
|
| 381 |
+
"loss": 6.469072341918945,
|
| 382 |
+
"step": 52
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.4537792642140468,
|
| 386 |
+
"grad_norm": 0.369140625,
|
| 387 |
+
"learning_rate": 0.021268436096329016,
|
| 388 |
+
"loss": 6.5030717849731445,
|
| 389 |
+
"step": 53
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.4623411371237458,
|
| 393 |
+
"grad_norm": 0.3984375,
|
| 394 |
+
"learning_rate": 0.0211259876435264,
|
| 395 |
+
"loss": 6.464090347290039,
|
| 396 |
+
"step": 54
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.4709030100334448,
|
| 400 |
+
"grad_norm": 0.4140625,
|
| 401 |
+
"learning_rate": 0.020981367644464153,
|
| 402 |
+
"loss": 6.415444374084473,
|
| 403 |
+
"step": 55
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.4794648829431438,
|
| 407 |
+
"grad_norm": 0.400390625,
|
| 408 |
+
"learning_rate": 0.020834612506453645,
|
| 409 |
+
"loss": 6.36262845993042,
|
| 410 |
+
"step": 56
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.48802675585284283,
|
| 414 |
+
"grad_norm": 0.421875,
|
| 415 |
+
"learning_rate": 0.020685759174316067,
|
| 416 |
+
"loss": 6.345418930053711,
|
| 417 |
+
"step": 57
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.4965886287625418,
|
| 421 |
+
"grad_norm": 0.333984375,
|
| 422 |
+
"learning_rate": 0.02053484512108174,
|
| 423 |
+
"loss": 6.309205532073975,
|
| 424 |
+
"step": 58
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.5051505016722408,
|
| 428 |
+
"grad_norm": 0.41015625,
|
| 429 |
+
"learning_rate": 0.020381908338556534,
|
| 430 |
+
"loss": 6.3184638023376465,
|
| 431 |
+
"step": 59
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.5137123745819397,
|
| 435 |
+
"grad_norm": 0.390625,
|
| 436 |
+
"learning_rate": 0.020226987327757566,
|
| 437 |
+
"loss": 6.273001670837402,
|
| 438 |
+
"step": 60
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.5222742474916388,
|
| 442 |
+
"grad_norm": 0.40234375,
|
| 443 |
+
"learning_rate": 0.020070121089220835,
|
| 444 |
+
"loss": 6.3029961585998535,
|
| 445 |
+
"step": 61
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.5308361204013378,
|
| 449 |
+
"grad_norm": 0.365234375,
|
| 450 |
+
"learning_rate": 0.01991134911318301,
|
| 451 |
+
"loss": 6.250678062438965,
|
| 452 |
+
"step": 62
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.5393979933110368,
|
| 456 |
+
"grad_norm": 0.359375,
|
| 457 |
+
"learning_rate": 0.01975071136963998,
|
| 458 |
+
"loss": 6.183889865875244,
|
| 459 |
+
"step": 63
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.5479598662207358,
|
| 463 |
+
"grad_norm": 0.3515625,
|
| 464 |
+
"learning_rate": 0.019588248298284636,
|
| 465 |
+
"loss": 6.137822151184082,
|
| 466 |
+
"step": 64
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.5565217391304348,
|
| 470 |
+
"grad_norm": 0.3203125,
|
| 471 |
+
"learning_rate": 0.01942400079832638,
|
| 472 |
+
"loss": 6.1106767654418945,
|
| 473 |
+
"step": 65
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.5650836120401338,
|
| 477 |
+
"grad_norm": 0.333984375,
|
| 478 |
+
"learning_rate": 0.01925801021819497,
|
| 479 |
+
"loss": 6.08446741104126,
|
| 480 |
+
"step": 66
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.5736454849498328,
|
| 484 |
+
"grad_norm": 0.302734375,
|
| 485 |
+
"learning_rate": 0.01909031834513128,
|
| 486 |
+
"loss": 6.131768226623535,
|
| 487 |
+
"step": 67
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.5822073578595318,
|
| 491 |
+
"grad_norm": 0.326171875,
|
| 492 |
+
"learning_rate": 0.018920967394667584,
|
| 493 |
+
"loss": 6.065019607543945,
|
| 494 |
+
"step": 68
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.5907692307692308,
|
| 498 |
+
"grad_norm": 0.3046875,
|
| 499 |
+
"learning_rate": 0.018750000000000003,
|
| 500 |
+
"loss": 6.0482282638549805,
|
| 501 |
+
"step": 69
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.5993311036789297,
|
| 505 |
+
"grad_norm": 0.357421875,
|
| 506 |
+
"learning_rate": 0.01857745920125586,
|
| 507 |
+
"loss": 6.048603057861328,
|
| 508 |
+
"step": 70
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.6078929765886287,
|
| 512 |
+
"grad_norm": 0.365234375,
|
| 513 |
+
"learning_rate": 0.018403388434658535,
|
| 514 |
+
"loss": 5.998836517333984,
|
| 515 |
+
"step": 71
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.6164548494983277,
|
| 519 |
+
"grad_norm": 0.3515625,
|
| 520 |
+
"learning_rate": 0.01822783152159263,
|
| 521 |
+
"loss": 5.9749650955200195,
|
| 522 |
+
"step": 72
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.6250167224080267,
|
| 526 |
+
"grad_norm": 0.30859375,
|
| 527 |
+
"learning_rate": 0.018050832657572177,
|
| 528 |
+
"loss": 5.919043064117432,
|
| 529 |
+
"step": 73
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.6335785953177258,
|
| 533 |
+
"grad_norm": 0.314453125,
|
| 534 |
+
"learning_rate": 0.017872436401114647,
|
| 535 |
+
"loss": 5.9278059005737305,
|
| 536 |
+
"step": 74
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.6421404682274248,
|
| 540 |
+
"grad_norm": 0.3046875,
|
| 541 |
+
"learning_rate": 0.017692687662523583,
|
| 542 |
+
"loss": 5.9064860343933105,
|
| 543 |
+
"step": 75
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.6507023411371238,
|
| 547 |
+
"grad_norm": 0.275390625,
|
| 548 |
+
"learning_rate": 0.01751163169258267,
|
| 549 |
+
"loss": 5.921048164367676,
|
| 550 |
+
"step": 76
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.6592642140468228,
|
| 554 |
+
"grad_norm": 0.28125,
|
| 555 |
+
"learning_rate": 0.017329314071164108,
|
| 556 |
+
"loss": 5.8522515296936035,
|
| 557 |
+
"step": 77
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.6678260869565218,
|
| 561 |
+
"grad_norm": 0.29296875,
|
| 562 |
+
"learning_rate": 0.017145780695754093,
|
| 563 |
+
"loss": 5.846250057220459,
|
| 564 |
+
"step": 78
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.6763879598662207,
|
| 568 |
+
"grad_norm": 0.37109375,
|
| 569 |
+
"learning_rate": 0.016961077769898397,
|
| 570 |
+
"loss": 5.8790435791015625,
|
| 571 |
+
"step": 79
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.6849498327759197,
|
| 575 |
+
"grad_norm": 0.30078125,
|
| 576 |
+
"learning_rate": 0.016775251791570862,
|
| 577 |
+
"loss": 5.849973201751709,
|
| 578 |
+
"step": 80
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.6935117056856187,
|
| 582 |
+
"grad_norm": 0.3125,
|
| 583 |
+
"learning_rate": 0.016588349541467772,
|
| 584 |
+
"loss": 5.8167405128479,
|
| 585 |
+
"step": 81
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.7020735785953177,
|
| 589 |
+
"grad_norm": 0.27734375,
|
| 590 |
+
"learning_rate": 0.016400418071231087,
|
| 591 |
+
"loss": 5.796406269073486,
|
| 592 |
+
"step": 82
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.7106354515050167,
|
| 596 |
+
"grad_norm": 0.30859375,
|
| 597 |
+
"learning_rate": 0.01621150469160344,
|
| 598 |
+
"loss": 5.828444004058838,
|
| 599 |
+
"step": 83
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.7191973244147157,
|
| 603 |
+
"grad_norm": 0.373046875,
|
| 604 |
+
"learning_rate": 0.016021656960517872,
|
| 605 |
+
"loss": 5.763159275054932,
|
| 606 |
+
"step": 84
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.7277591973244147,
|
| 610 |
+
"grad_norm": 0.3359375,
|
| 611 |
+
"learning_rate": 0.015830922671125437,
|
| 612 |
+
"loss": 5.761376857757568,
|
| 613 |
+
"step": 85
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.7363210702341138,
|
| 617 |
+
"grad_norm": 0.3515625,
|
| 618 |
+
"learning_rate": 0.015639349839763488,
|
| 619 |
+
"loss": 5.724917411804199,
|
| 620 |
+
"step": 86
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.7448829431438128,
|
| 624 |
+
"grad_norm": 0.283203125,
|
| 625 |
+
"learning_rate": 0.015446986693867843,
|
| 626 |
+
"loss": 5.740510940551758,
|
| 627 |
+
"step": 87
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.7534448160535117,
|
| 631 |
+
"grad_norm": 0.275390625,
|
| 632 |
+
"learning_rate": 0.015253881659831759,
|
| 633 |
+
"loss": 5.739223480224609,
|
| 634 |
+
"step": 88
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.7620066889632107,
|
| 638 |
+
"grad_norm": 0.2890625,
|
| 639 |
+
"learning_rate": 0.015060083350814886,
|
| 640 |
+
"loss": 5.749945163726807,
|
| 641 |
+
"step": 89
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.7705685618729097,
|
| 645 |
+
"grad_norm": 0.294921875,
|
| 646 |
+
"learning_rate": 0.014865640554505129,
|
| 647 |
+
"loss": 5.627425670623779,
|
| 648 |
+
"step": 90
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.7791304347826087,
|
| 652 |
+
"grad_norm": 0.287109375,
|
| 653 |
+
"learning_rate": 0.014670602220836632,
|
| 654 |
+
"loss": 5.6766133308410645,
|
| 655 |
+
"step": 91
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.7876923076923077,
|
| 659 |
+
"grad_norm": 0.263671875,
|
| 660 |
+
"learning_rate": 0.014475017449666875,
|
| 661 |
+
"loss": 5.628288269042969,
|
| 662 |
+
"step": 92
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.7962541806020067,
|
| 666 |
+
"grad_norm": 0.287109375,
|
| 667 |
+
"learning_rate": 0.014278935478416067,
|
| 668 |
+
"loss": 5.660680294036865,
|
| 669 |
+
"step": 93
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.8048160535117057,
|
| 673 |
+
"grad_norm": 0.25390625,
|
| 674 |
+
"learning_rate": 0.014082405669671866,
|
| 675 |
+
"loss": 5.6099348068237305,
|
| 676 |
+
"step": 94
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.8133779264214047,
|
| 680 |
+
"grad_norm": 0.265625,
|
| 681 |
+
"learning_rate": 0.013885477498762639,
|
| 682 |
+
"loss": 5.595584869384766,
|
| 683 |
+
"step": 95
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.8219397993311037,
|
| 687 |
+
"grad_norm": 0.2431640625,
|
| 688 |
+
"learning_rate": 0.013688200541302282,
|
| 689 |
+
"loss": 5.5869598388671875,
|
| 690 |
+
"step": 96
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.8305016722408026,
|
| 694 |
+
"grad_norm": 0.259765625,
|
| 695 |
+
"learning_rate": 0.013490624460709855,
|
| 696 |
+
"loss": 5.562591552734375,
|
| 697 |
+
"step": 97
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.8390635451505016,
|
| 701 |
+
"grad_norm": 0.2734375,
|
| 702 |
+
"learning_rate": 0.013292798995707057,
|
| 703 |
+
"loss": 5.562747955322266,
|
| 704 |
+
"step": 98
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.8476254180602006,
|
| 708 |
+
"grad_norm": 0.271484375,
|
| 709 |
+
"learning_rate": 0.013094773947796783,
|
| 710 |
+
"loss": 5.608129501342773,
|
| 711 |
+
"step": 99
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.8561872909698997,
|
| 715 |
+
"grad_norm": 0.265625,
|
| 716 |
+
"learning_rate": 0.012896599168725847,
|
| 717 |
+
"loss": 5.565805912017822,
|
| 718 |
+
"step": 100
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.8561872909698997,
|
| 722 |
+
"eval_loss": 5.537259578704834,
|
| 723 |
+
"eval_runtime": 51.1142,
|
| 724 |
+
"eval_samples_per_second": 11.954,
|
| 725 |
+
"eval_steps_per_second": 2.993,
|
| 726 |
+
"step": 100
|
| 727 |
}
|
| 728 |
],
|
| 729 |
"logging_steps": 1,
|
|
|
|
| 743 |
"attributes": {}
|
| 744 |
}
|
| 745 |
},
|
| 746 |
+
"total_flos": 1.4579790139891507e+17,
|
| 747 |
"train_batch_size": 4,
|
| 748 |
"trial_name": null,
|
| 749 |
"trial_params": null
|