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 59933632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9860b73015b15607627aceb40b08147e8f53966aa2cdaf579d26c56d260c4253
|
| 3 |
size 59933632
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 31822948
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66a968e36f5602a15c95b5682482753dacf50dd4f7eabf0937b3718f438ec804
|
| 3 |
size 31822948
|
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 sha256:63e5a52ccff9e6b431cd0b66738dcf15797c1e46a2c0785103a072af324fa007
|
| 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 sha256:3fc7800513a1b4dd006c457152c700dd768bb49ee4ed8e4d9665a4e42095b054
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 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": 27.347,
|
| 374 |
"eval_steps_per_second": 13.673,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -392,7 +750,7 @@
|
|
| 392 |
"attributes": {}
|
| 393 |
}
|
| 394 |
},
|
| 395 |
-
"total_flos":
|
| 396 |
"train_batch_size": 2,
|
| 397 |
"trial_name": null,
|
| 398 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.0063363325307312125,
|
| 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": 27.347,
|
| 374 |
"eval_steps_per_second": 13.673,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.0032315295906729185,
|
| 379 |
+
"grad_norm": 0.8580302596092224,
|
| 380 |
+
"learning_rate": 0.00017788772787621126,
|
| 381 |
+
"loss": 0.3992,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.0032948929159802307,
|
| 386 |
+
"grad_norm": 0.7331790328025818,
|
| 387 |
+
"learning_rate": 0.00017684011108568592,
|
| 388 |
+
"loss": 0.5749,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.003358256241287543,
|
| 393 |
+
"grad_norm": 1.4232603311538696,
|
| 394 |
+
"learning_rate": 0.0001757714869760335,
|
| 395 |
+
"loss": 0.633,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.003421619566594855,
|
| 400 |
+
"grad_norm": 0.6469828486442566,
|
| 401 |
+
"learning_rate": 0.0001746821476984154,
|
| 402 |
+
"loss": 0.4805,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.003484982891902167,
|
| 407 |
+
"grad_norm": 0.5833075046539307,
|
| 408 |
+
"learning_rate": 0.00017357239106731317,
|
| 409 |
+
"loss": 0.303,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.003548346217209479,
|
| 414 |
+
"grad_norm": 0.5430967807769775,
|
| 415 |
+
"learning_rate": 0.00017244252047910892,
|
| 416 |
+
"loss": 0.3606,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.0036117095425167913,
|
| 421 |
+
"grad_norm": 0.7270248532295227,
|
| 422 |
+
"learning_rate": 0.00017129284482913972,
|
| 423 |
+
"loss": 0.519,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.0036750728678241035,
|
| 428 |
+
"grad_norm": 0.497071236371994,
|
| 429 |
+
"learning_rate": 0.00017012367842724887,
|
| 430 |
+
"loss": 0.3192,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.0037384361931314157,
|
| 435 |
+
"grad_norm": 0.5522649884223938,
|
| 436 |
+
"learning_rate": 0.0001689353409118566,
|
| 437 |
+
"loss": 0.4403,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.0038017995184387275,
|
| 442 |
+
"grad_norm": 1.4259494543075562,
|
| 443 |
+
"learning_rate": 0.00016772815716257412,
|
| 444 |
+
"loss": 0.4538,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.0038651628437460397,
|
| 449 |
+
"grad_norm": 0.5942732095718384,
|
| 450 |
+
"learning_rate": 0.0001665024572113848,
|
| 451 |
+
"loss": 0.3762,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.003928526169053352,
|
| 456 |
+
"grad_norm": 0.5439912676811218,
|
| 457 |
+
"learning_rate": 0.00016525857615241687,
|
| 458 |
+
"loss": 0.4122,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.003991889494360664,
|
| 463 |
+
"grad_norm": 0.4867478311061859,
|
| 464 |
+
"learning_rate": 0.00016399685405033167,
|
| 465 |
+
"loss": 0.2925,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.004055252819667976,
|
| 470 |
+
"grad_norm": 0.8213767409324646,
|
| 471 |
+
"learning_rate": 0.0001627176358473537,
|
| 472 |
+
"loss": 0.4217,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.004118616144975288,
|
| 477 |
+
"grad_norm": 1.1848950386047363,
|
| 478 |
+
"learning_rate": 0.0001614212712689668,
|
| 479 |
+
"loss": 0.3365,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.004181979470282601,
|
| 484 |
+
"grad_norm": 0.7401292324066162,
|
| 485 |
+
"learning_rate": 0.00016010811472830252,
|
| 486 |
+
"loss": 0.7397,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.0042453427955899126,
|
| 491 |
+
"grad_norm": 0.910925030708313,
|
| 492 |
+
"learning_rate": 0.00015877852522924732,
|
| 493 |
+
"loss": 0.431,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.004308706120897224,
|
| 498 |
+
"grad_norm": 0.8558295965194702,
|
| 499 |
+
"learning_rate": 0.00015743286626829437,
|
| 500 |
+
"loss": 0.3999,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.004372069446204537,
|
| 505 |
+
"grad_norm": 0.5612680315971375,
|
| 506 |
+
"learning_rate": 0.0001560715057351673,
|
| 507 |
+
"loss": 0.4328,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.004435432771511849,
|
| 512 |
+
"grad_norm": 0.38900530338287354,
|
| 513 |
+
"learning_rate": 0.00015469481581224272,
|
| 514 |
+
"loss": 0.4551,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.004498796096819161,
|
| 519 |
+
"grad_norm": 0.5994769334793091,
|
| 520 |
+
"learning_rate": 0.0001533031728727994,
|
| 521 |
+
"loss": 0.4326,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.004562159422126473,
|
| 526 |
+
"grad_norm": 0.5441716909408569,
|
| 527 |
+
"learning_rate": 0.00015189695737812152,
|
| 528 |
+
"loss": 0.7896,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.004625522747433785,
|
| 533 |
+
"grad_norm": 1.3651723861694336,
|
| 534 |
+
"learning_rate": 0.0001504765537734844,
|
| 535 |
+
"loss": 0.3994,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.004688886072741098,
|
| 540 |
+
"grad_norm": 1.0307939052581787,
|
| 541 |
+
"learning_rate": 0.00014904235038305083,
|
| 542 |
+
"loss": 0.4365,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.004752249398048409,
|
| 547 |
+
"grad_norm": 0.5589604377746582,
|
| 548 |
+
"learning_rate": 0.00014759473930370736,
|
| 549 |
+
"loss": 0.4381,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.004815612723355722,
|
| 554 |
+
"grad_norm": 0.6483279466629028,
|
| 555 |
+
"learning_rate": 0.0001461341162978688,
|
| 556 |
+
"loss": 1.2379,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.004878976048663034,
|
| 561 |
+
"grad_norm": 0.688217282295227,
|
| 562 |
+
"learning_rate": 0.00014466088068528068,
|
| 563 |
+
"loss": 0.3769,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.004942339373970346,
|
| 568 |
+
"grad_norm": 0.6985648274421692,
|
| 569 |
+
"learning_rate": 0.00014317543523384928,
|
| 570 |
+
"loss": 0.2771,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.005005702699277658,
|
| 575 |
+
"grad_norm": 1.2414263486862183,
|
| 576 |
+
"learning_rate": 0.00014167818604952906,
|
| 577 |
+
"loss": 0.3534,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.00506906602458497,
|
| 582 |
+
"grad_norm": 0.6788727045059204,
|
| 583 |
+
"learning_rate": 0.00014016954246529696,
|
| 584 |
+
"loss": 0.5284,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.005132429349892283,
|
| 589 |
+
"grad_norm": 0.7818289995193481,
|
| 590 |
+
"learning_rate": 0.00013864991692924523,
|
| 591 |
+
"loss": 0.2941,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.0051957926751995944,
|
| 596 |
+
"grad_norm": 0.6787352561950684,
|
| 597 |
+
"learning_rate": 0.00013711972489182208,
|
| 598 |
+
"loss": 0.3318,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.005259156000506906,
|
| 603 |
+
"grad_norm": 0.971752941608429,
|
| 604 |
+
"learning_rate": 0.00013557938469225167,
|
| 605 |
+
"loss": 0.4559,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.005322519325814219,
|
| 610 |
+
"grad_norm": 0.5854300260543823,
|
| 611 |
+
"learning_rate": 0.00013402931744416433,
|
| 612 |
+
"loss": 0.3601,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.005385882651121531,
|
| 617 |
+
"grad_norm": 0.7647449374198914,
|
| 618 |
+
"learning_rate": 0.00013246994692046836,
|
| 619 |
+
"loss": 0.435,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.005449245976428843,
|
| 624 |
+
"grad_norm": 0.5981462001800537,
|
| 625 |
+
"learning_rate": 0.00013090169943749476,
|
| 626 |
+
"loss": 0.4311,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.005512609301736155,
|
| 631 |
+
"grad_norm": 0.4233483374118805,
|
| 632 |
+
"learning_rate": 0.0001293250037384465,
|
| 633 |
+
"loss": 0.415,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.005575972627043467,
|
| 638 |
+
"grad_norm": 0.8820663094520569,
|
| 639 |
+
"learning_rate": 0.00012774029087618446,
|
| 640 |
+
"loss": 0.3958,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.0056393359523507795,
|
| 645 |
+
"grad_norm": 0.6327323317527771,
|
| 646 |
+
"learning_rate": 0.00012614799409538198,
|
| 647 |
+
"loss": 0.6534,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.005702699277658091,
|
| 652 |
+
"grad_norm": 0.5511671304702759,
|
| 653 |
+
"learning_rate": 0.00012454854871407994,
|
| 654 |
+
"loss": 0.3668,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.005766062602965404,
|
| 659 |
+
"grad_norm": 0.7432234883308411,
|
| 660 |
+
"learning_rate": 0.00012294239200467516,
|
| 661 |
+
"loss": 0.3317,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.005829425928272716,
|
| 666 |
+
"grad_norm": 0.6933262348175049,
|
| 667 |
+
"learning_rate": 0.0001213299630743747,
|
| 668 |
+
"loss": 0.3444,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.0058927892535800275,
|
| 673 |
+
"grad_norm": 0.7745187878608704,
|
| 674 |
+
"learning_rate": 0.00011971170274514802,
|
| 675 |
+
"loss": 0.1975,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.00595615257888734,
|
| 680 |
+
"grad_norm": 0.6152411699295044,
|
| 681 |
+
"learning_rate": 0.000118088053433211,
|
| 682 |
+
"loss": 0.5463,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.006019515904194652,
|
| 687 |
+
"grad_norm": 1.3992512226104736,
|
| 688 |
+
"learning_rate": 0.00011645945902807341,
|
| 689 |
+
"loss": 0.4622,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.0060828792295019645,
|
| 694 |
+
"grad_norm": 0.8983330726623535,
|
| 695 |
+
"learning_rate": 0.0001148263647711842,
|
| 696 |
+
"loss": 0.466,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.006146242554809276,
|
| 701 |
+
"grad_norm": 0.5503897666931152,
|
| 702 |
+
"learning_rate": 0.00011318921713420691,
|
| 703 |
+
"loss": 0.37,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.006209605880116588,
|
| 708 |
+
"grad_norm": 0.5463910102844238,
|
| 709 |
+
"learning_rate": 0.00011154846369695863,
|
| 710 |
+
"loss": 0.3198,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.006272969205423901,
|
| 715 |
+
"grad_norm": 0.4767880141735077,
|
| 716 |
+
"learning_rate": 0.0001099045530250463,
|
| 717 |
+
"loss": 0.3526,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.0063363325307312125,
|
| 722 |
+
"grad_norm": 1.2058966159820557,
|
| 723 |
+
"learning_rate": 0.00010825793454723325,
|
| 724 |
+
"loss": 0.4968,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.0063363325307312125,
|
| 729 |
+
"eval_loss": 0.3803197145462036,
|
| 730 |
+
"eval_runtime": 243.4104,
|
| 731 |
+
"eval_samples_per_second": 27.304,
|
| 732 |
+
"eval_steps_per_second": 13.652,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 750 |
"attributes": {}
|
| 751 |
}
|
| 752 |
},
|
| 753 |
+
"total_flos": 1.3677852390064128e+16,
|
| 754 |
"train_batch_size": 2,
|
| 755 |
"trial_name": null,
|
| 756 |
"trial_params": null
|