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 80013120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0a96a2e7cf953b933f7821f6c6fe2ec6cc1df94a1c5fe701bc8d0c1480a161f
|
| 3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 41119636
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c804bba2dd8a410c88ebd927b70bfc7182d9cfb0d6a36bf9c4fc2dd815eb07d6
|
| 3 |
size 41119636
|
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 sha256:955fc11d95973ad3e55aafab2e3c2f9e1ac3dd672ace2bf41cd1f3359c6778ae
|
| 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": 26.551,
|
| 374 |
"eval_steps_per_second": 13.276,
|
| 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": 0.0121558378411232,
|
| 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": 26.551,
|
| 374 |
"eval_steps_per_second": 13.276,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.006199477298972832,
|
| 379 |
+
"grad_norm": 2.2631587982177734,
|
| 380 |
+
"learning_rate": 0.00017788772787621126,
|
| 381 |
+
"loss": 9.446,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.006321035677384064,
|
| 386 |
+
"grad_norm": 4.675655364990234,
|
| 387 |
+
"learning_rate": 0.00017684011108568592,
|
| 388 |
+
"loss": 9.3449,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.006442594055795296,
|
| 393 |
+
"grad_norm": 1.7152106761932373,
|
| 394 |
+
"learning_rate": 0.0001757714869760335,
|
| 395 |
+
"loss": 9.475,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.006564152434206528,
|
| 400 |
+
"grad_norm": 1.5290554761886597,
|
| 401 |
+
"learning_rate": 0.0001746821476984154,
|
| 402 |
+
"loss": 9.117,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.00668571081261776,
|
| 407 |
+
"grad_norm": 2.0921902656555176,
|
| 408 |
+
"learning_rate": 0.00017357239106731317,
|
| 409 |
+
"loss": 9.5546,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.006807269191028992,
|
| 414 |
+
"grad_norm": 2.1920764446258545,
|
| 415 |
+
"learning_rate": 0.00017244252047910892,
|
| 416 |
+
"loss": 8.953,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.0069288275694402235,
|
| 421 |
+
"grad_norm": 1.7566354274749756,
|
| 422 |
+
"learning_rate": 0.00017129284482913972,
|
| 423 |
+
"loss": 9.6787,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.0070503859478514555,
|
| 428 |
+
"grad_norm": 1.4819419384002686,
|
| 429 |
+
"learning_rate": 0.00017012367842724887,
|
| 430 |
+
"loss": 7.3843,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.007171944326262687,
|
| 435 |
+
"grad_norm": 1.6789450645446777,
|
| 436 |
+
"learning_rate": 0.0001689353409118566,
|
| 437 |
+
"loss": 9.802,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.007293502704673919,
|
| 442 |
+
"grad_norm": 1.282571792602539,
|
| 443 |
+
"learning_rate": 0.00016772815716257412,
|
| 444 |
+
"loss": 7.7288,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.007415061083085151,
|
| 449 |
+
"grad_norm": 2.066798448562622,
|
| 450 |
+
"learning_rate": 0.0001665024572113848,
|
| 451 |
+
"loss": 9.3806,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.007536619461496383,
|
| 456 |
+
"grad_norm": 1.7693638801574707,
|
| 457 |
+
"learning_rate": 0.00016525857615241687,
|
| 458 |
+
"loss": 9.6393,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.007658177839907615,
|
| 463 |
+
"grad_norm": 1.7502071857452393,
|
| 464 |
+
"learning_rate": 0.00016399685405033167,
|
| 465 |
+
"loss": 8.3708,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.007779736218318848,
|
| 470 |
+
"grad_norm": 2.8502800464630127,
|
| 471 |
+
"learning_rate": 0.0001627176358473537,
|
| 472 |
+
"loss": 8.8738,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.00790129459673008,
|
| 477 |
+
"grad_norm": 2.4103214740753174,
|
| 478 |
+
"learning_rate": 0.0001614212712689668,
|
| 479 |
+
"loss": 9.5765,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.008022852975141312,
|
| 484 |
+
"grad_norm": 1.8917535543441772,
|
| 485 |
+
"learning_rate": 0.00016010811472830252,
|
| 486 |
+
"loss": 9.4486,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.008144411353552544,
|
| 491 |
+
"grad_norm": 1.5890737771987915,
|
| 492 |
+
"learning_rate": 0.00015877852522924732,
|
| 493 |
+
"loss": 8.5677,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.008265969731963776,
|
| 498 |
+
"grad_norm": 2.1370444297790527,
|
| 499 |
+
"learning_rate": 0.00015743286626829437,
|
| 500 |
+
"loss": 9.4762,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.008387528110375008,
|
| 505 |
+
"grad_norm": 1.7275190353393555,
|
| 506 |
+
"learning_rate": 0.0001560715057351673,
|
| 507 |
+
"loss": 8.829,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.00850908648878624,
|
| 512 |
+
"grad_norm": 1.7048512697219849,
|
| 513 |
+
"learning_rate": 0.00015469481581224272,
|
| 514 |
+
"loss": 8.8259,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.008630644867197472,
|
| 519 |
+
"grad_norm": 1.903066635131836,
|
| 520 |
+
"learning_rate": 0.0001533031728727994,
|
| 521 |
+
"loss": 9.6929,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.008752203245608704,
|
| 526 |
+
"grad_norm": 1.5013515949249268,
|
| 527 |
+
"learning_rate": 0.00015189695737812152,
|
| 528 |
+
"loss": 8.1273,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.008873761624019936,
|
| 533 |
+
"grad_norm": 1.6483365297317505,
|
| 534 |
+
"learning_rate": 0.0001504765537734844,
|
| 535 |
+
"loss": 8.8742,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.008995320002431167,
|
| 540 |
+
"grad_norm": 1.8312402963638306,
|
| 541 |
+
"learning_rate": 0.00014904235038305083,
|
| 542 |
+
"loss": 8.7848,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.0091168783808424,
|
| 547 |
+
"grad_norm": 1.3816986083984375,
|
| 548 |
+
"learning_rate": 0.00014759473930370736,
|
| 549 |
+
"loss": 8.2036,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.009238436759253631,
|
| 554 |
+
"grad_norm": 2.2364020347595215,
|
| 555 |
+
"learning_rate": 0.0001461341162978688,
|
| 556 |
+
"loss": 10.4628,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.009359995137664863,
|
| 561 |
+
"grad_norm": 1.573431134223938,
|
| 562 |
+
"learning_rate": 0.00014466088068528068,
|
| 563 |
+
"loss": 8.8974,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.009481553516076095,
|
| 568 |
+
"grad_norm": 2.187255859375,
|
| 569 |
+
"learning_rate": 0.00014317543523384928,
|
| 570 |
+
"loss": 8.5312,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.009603111894487327,
|
| 575 |
+
"grad_norm": 2.0174520015716553,
|
| 576 |
+
"learning_rate": 0.00014167818604952906,
|
| 577 |
+
"loss": 8.829,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.00972467027289856,
|
| 582 |
+
"grad_norm": 1.8616173267364502,
|
| 583 |
+
"learning_rate": 0.00014016954246529696,
|
| 584 |
+
"loss": 8.3692,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.009846228651309791,
|
| 589 |
+
"grad_norm": 1.8460533618927002,
|
| 590 |
+
"learning_rate": 0.00013864991692924523,
|
| 591 |
+
"loss": 8.6283,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.009967787029721023,
|
| 596 |
+
"grad_norm": 2.5459718704223633,
|
| 597 |
+
"learning_rate": 0.00013711972489182208,
|
| 598 |
+
"loss": 8.4909,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.010089345408132255,
|
| 603 |
+
"grad_norm": 1.9989314079284668,
|
| 604 |
+
"learning_rate": 0.00013557938469225167,
|
| 605 |
+
"loss": 8.9659,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.010210903786543487,
|
| 610 |
+
"grad_norm": 1.3886724710464478,
|
| 611 |
+
"learning_rate": 0.00013402931744416433,
|
| 612 |
+
"loss": 9.1106,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.010332462164954719,
|
| 617 |
+
"grad_norm": 2.354243040084839,
|
| 618 |
+
"learning_rate": 0.00013246994692046836,
|
| 619 |
+
"loss": 9.2569,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.01045402054336595,
|
| 624 |
+
"grad_norm": 2.085102081298828,
|
| 625 |
+
"learning_rate": 0.00013090169943749476,
|
| 626 |
+
"loss": 8.9907,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.010575578921777183,
|
| 631 |
+
"grad_norm": 1.2773852348327637,
|
| 632 |
+
"learning_rate": 0.0001293250037384465,
|
| 633 |
+
"loss": 8.7438,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.010697137300188415,
|
| 638 |
+
"grad_norm": 1.6545124053955078,
|
| 639 |
+
"learning_rate": 0.00012774029087618446,
|
| 640 |
+
"loss": 8.7085,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.010818695678599647,
|
| 645 |
+
"grad_norm": 2.1138100624084473,
|
| 646 |
+
"learning_rate": 0.00012614799409538198,
|
| 647 |
+
"loss": 8.8577,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.010940254057010879,
|
| 652 |
+
"grad_norm": 1.8220653533935547,
|
| 653 |
+
"learning_rate": 0.00012454854871407994,
|
| 654 |
+
"loss": 9.198,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.011061812435422112,
|
| 659 |
+
"grad_norm": 1.6138783693313599,
|
| 660 |
+
"learning_rate": 0.00012294239200467516,
|
| 661 |
+
"loss": 8.9333,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.011183370813833344,
|
| 666 |
+
"grad_norm": 1.6465097665786743,
|
| 667 |
+
"learning_rate": 0.0001213299630743747,
|
| 668 |
+
"loss": 9.123,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.011304929192244576,
|
| 673 |
+
"grad_norm": 1.7768160104751587,
|
| 674 |
+
"learning_rate": 0.00011971170274514802,
|
| 675 |
+
"loss": 8.6597,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.011426487570655808,
|
| 680 |
+
"grad_norm": 1.6465460062026978,
|
| 681 |
+
"learning_rate": 0.000118088053433211,
|
| 682 |
+
"loss": 9.841,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.01154804594906704,
|
| 687 |
+
"grad_norm": 1.3596290349960327,
|
| 688 |
+
"learning_rate": 0.00011645945902807341,
|
| 689 |
+
"loss": 8.5273,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.011669604327478272,
|
| 694 |
+
"grad_norm": 1.612764596939087,
|
| 695 |
+
"learning_rate": 0.0001148263647711842,
|
| 696 |
+
"loss": 8.4275,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.011791162705889504,
|
| 701 |
+
"grad_norm": 2.3744266033172607,
|
| 702 |
+
"learning_rate": 0.00011318921713420691,
|
| 703 |
+
"loss": 9.6372,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.011912721084300736,
|
| 708 |
+
"grad_norm": 1.4123613834381104,
|
| 709 |
+
"learning_rate": 0.00011154846369695863,
|
| 710 |
+
"loss": 8.4314,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.012034279462711968,
|
| 715 |
+
"grad_norm": 1.9357587099075317,
|
| 716 |
+
"learning_rate": 0.0001099045530250463,
|
| 717 |
+
"loss": 8.7244,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.0121558378411232,
|
| 722 |
+
"grad_norm": 1.6507443189620972,
|
| 723 |
+
"learning_rate": 0.00010825793454723325,
|
| 724 |
+
"loss": 10.0314,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.0121558378411232,
|
| 729 |
+
"eval_loss": 2.20096755027771,
|
| 730 |
+
"eval_runtime": 130.4185,
|
| 731 |
+
"eval_samples_per_second": 26.561,
|
| 732 |
+
"eval_steps_per_second": 13.28,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 750 |
"attributes": {}
|
| 751 |
}
|
| 752 |
},
|
| 753 |
+
"total_flos": 1.873061628346368e+16,
|
| 754 |
"train_batch_size": 2,
|
| 755 |
"trial_name": null,
|
| 756 |
"trial_params": null
|