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 101752088
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f7a53eee5421ae3b39ecc2457fe20ae032b74e00a98ba595d0f22e5f627c6b8
|
| 3 |
size 101752088
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 203713238
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:196e430203a65ea85e34422b38ff6f2440b6bc815ebc65dbde376089c51fd881
|
| 3 |
size 203713238
|
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:d8de97686278eaa22189e02799ab66deb53b5f217012fba91cd1d20549125959
|
| 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:c5d2a6c6aafc669cea03b9634666f204de949a3d45ce2f48a07e7e3eaf18c715
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 25,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -381,6 +381,372 @@
|
|
| 381 |
"eval_samples_per_second": 7.613,
|
| 382 |
"eval_steps_per_second": 1.066,
|
| 383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
|
@@ -409,7 +775,7 @@
|
|
| 409 |
"attributes": {}
|
| 410 |
}
|
| 411 |
},
|
| 412 |
-
"total_flos":
|
| 413 |
"train_batch_size": 8,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.2889782190322876,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.2828854314002829,
|
| 5 |
"eval_steps": 25,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 381 |
"eval_samples_per_second": 7.613,
|
| 382 |
"eval_steps_per_second": 1.066,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.14427157001414428,
|
| 387 |
+
"grad_norm": 2.2015700340270996,
|
| 388 |
+
"learning_rate": 0.0002668315918143169,
|
| 389 |
+
"loss": 1.723,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.1471004243281471,
|
| 394 |
+
"grad_norm": 2.95166015625,
|
| 395 |
+
"learning_rate": 0.00026526016662852886,
|
| 396 |
+
"loss": 1.7648,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.14992927864214992,
|
| 401 |
+
"grad_norm": 2.075843095779419,
|
| 402 |
+
"learning_rate": 0.00026365723046405023,
|
| 403 |
+
"loss": 1.6472,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.15275813295615276,
|
| 408 |
+
"grad_norm": 1.718432068824768,
|
| 409 |
+
"learning_rate": 0.0002620232215476231,
|
| 410 |
+
"loss": 1.4924,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.15558698727015557,
|
| 415 |
+
"grad_norm": 1.5728050470352173,
|
| 416 |
+
"learning_rate": 0.0002603585866009697,
|
| 417 |
+
"loss": 1.6117,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.15841584158415842,
|
| 422 |
+
"grad_norm": 1.6196128129959106,
|
| 423 |
+
"learning_rate": 0.00025866378071866334,
|
| 424 |
+
"loss": 1.5618,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.16124469589816123,
|
| 429 |
+
"grad_norm": 1.5551187992095947,
|
| 430 |
+
"learning_rate": 0.00025693926724370956,
|
| 431 |
+
"loss": 1.5645,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.16407355021216408,
|
| 436 |
+
"grad_norm": 1.5316717624664307,
|
| 437 |
+
"learning_rate": 0.00025518551764087326,
|
| 438 |
+
"loss": 1.3852,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.1669024045261669,
|
| 443 |
+
"grad_norm": 1.300549864768982,
|
| 444 |
+
"learning_rate": 0.00025340301136778483,
|
| 445 |
+
"loss": 1.3003,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.16973125884016974,
|
| 450 |
+
"grad_norm": 1.4803193807601929,
|
| 451 |
+
"learning_rate": 0.00025159223574386114,
|
| 452 |
+
"loss": 1.4779,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.17256011315417255,
|
| 457 |
+
"grad_norm": 1.7613025903701782,
|
| 458 |
+
"learning_rate": 0.0002497536858170772,
|
| 459 |
+
"loss": 1.7583,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.1753889674681754,
|
| 464 |
+
"grad_norm": 1.4396024942398071,
|
| 465 |
+
"learning_rate": 0.00024788786422862526,
|
| 466 |
+
"loss": 1.6944,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.1782178217821782,
|
| 471 |
+
"grad_norm": 1.3759733438491821,
|
| 472 |
+
"learning_rate": 0.00024599528107549745,
|
| 473 |
+
"loss": 1.4027,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.18104667609618105,
|
| 478 |
+
"grad_norm": 1.580557942390442,
|
| 479 |
+
"learning_rate": 0.00024407645377103054,
|
| 480 |
+
"loss": 1.4777,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.18387553041018387,
|
| 485 |
+
"grad_norm": 1.2791796922683716,
|
| 486 |
+
"learning_rate": 0.00024213190690345018,
|
| 487 |
+
"loss": 1.1189,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.1867043847241867,
|
| 492 |
+
"grad_norm": 1.6268357038497925,
|
| 493 |
+
"learning_rate": 0.00024016217209245374,
|
| 494 |
+
"loss": 1.6708,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.18953323903818953,
|
| 499 |
+
"grad_norm": 1.5571532249450684,
|
| 500 |
+
"learning_rate": 0.00023816778784387094,
|
| 501 |
+
"loss": 1.5666,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.19236209335219237,
|
| 506 |
+
"grad_norm": 1.6624035835266113,
|
| 507 |
+
"learning_rate": 0.0002361492994024415,
|
| 508 |
+
"loss": 1.7207,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.19519094766619519,
|
| 513 |
+
"grad_norm": 1.3323289155960083,
|
| 514 |
+
"learning_rate": 0.0002341072586027509,
|
| 515 |
+
"loss": 1.3077,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.19801980198019803,
|
| 520 |
+
"grad_norm": 1.5438517332077026,
|
| 521 |
+
"learning_rate": 0.00023204222371836405,
|
| 522 |
+
"loss": 1.5942,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.20084865629420084,
|
| 527 |
+
"grad_norm": 1.2273508310317993,
|
| 528 |
+
"learning_rate": 0.00022995475930919905,
|
| 529 |
+
"loss": 1.3817,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.2036775106082037,
|
| 534 |
+
"grad_norm": 1.4077955484390259,
|
| 535 |
+
"learning_rate": 0.00022784543606718227,
|
| 536 |
+
"loss": 1.2022,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.2065063649222065,
|
| 541 |
+
"grad_norm": 1.3565106391906738,
|
| 542 |
+
"learning_rate": 0.00022571483066022657,
|
| 543 |
+
"loss": 1.339,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.20933521923620935,
|
| 548 |
+
"grad_norm": 1.4129908084869385,
|
| 549 |
+
"learning_rate": 0.0002235635255745762,
|
| 550 |
+
"loss": 1.4171,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.21216407355021216,
|
| 555 |
+
"grad_norm": 1.4590212106704712,
|
| 556 |
+
"learning_rate": 0.00022139210895556104,
|
| 557 |
+
"loss": 1.5713,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.21216407355021216,
|
| 562 |
+
"eval_loss": 1.2917476892471313,
|
| 563 |
+
"eval_runtime": 6.5719,
|
| 564 |
+
"eval_samples_per_second": 7.608,
|
| 565 |
+
"eval_steps_per_second": 1.065,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.214992927864215,
|
| 570 |
+
"grad_norm": 1.6218371391296387,
|
| 571 |
+
"learning_rate": 0.00021920117444680317,
|
| 572 |
+
"loss": 1.6171,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.21782178217821782,
|
| 577 |
+
"grad_norm": 1.7404510974884033,
|
| 578 |
+
"learning_rate": 0.00021699132102792097,
|
| 579 |
+
"loss": 1.4111,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.22065063649222066,
|
| 584 |
+
"grad_norm": 1.81099534034729,
|
| 585 |
+
"learning_rate": 0.0002147631528507739,
|
| 586 |
+
"loss": 1.5029,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.22347949080622348,
|
| 591 |
+
"grad_norm": 1.3451523780822754,
|
| 592 |
+
"learning_rate": 0.00021251727907429355,
|
| 593 |
+
"loss": 1.3834,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.2263083451202263,
|
| 598 |
+
"grad_norm": 1.5676521062850952,
|
| 599 |
+
"learning_rate": 0.0002102543136979454,
|
| 600 |
+
"loss": 1.5501,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.22913719943422914,
|
| 605 |
+
"grad_norm": 1.5862256288528442,
|
| 606 |
+
"learning_rate": 0.0002079748753938678,
|
| 607 |
+
"loss": 1.5968,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.23196605374823195,
|
| 612 |
+
"grad_norm": 1.3945386409759521,
|
| 613 |
+
"learning_rate": 0.0002056795873377331,
|
| 614 |
+
"loss": 1.3185,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.2347949080622348,
|
| 619 |
+
"grad_norm": 1.3496489524841309,
|
| 620 |
+
"learning_rate": 0.00020336907703837748,
|
| 621 |
+
"loss": 1.6249,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.2376237623762376,
|
| 626 |
+
"grad_norm": 1.3319957256317139,
|
| 627 |
+
"learning_rate": 0.00020104397616624645,
|
| 628 |
+
"loss": 1.5383,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.24045261669024046,
|
| 633 |
+
"grad_norm": 1.3285038471221924,
|
| 634 |
+
"learning_rate": 0.00019870492038070252,
|
| 635 |
+
"loss": 1.2833,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.24328147100424327,
|
| 640 |
+
"grad_norm": 1.6563820838928223,
|
| 641 |
+
"learning_rate": 0.0001963525491562421,
|
| 642 |
+
"loss": 1.6086,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.24611032531824611,
|
| 647 |
+
"grad_norm": 1.2712721824645996,
|
| 648 |
+
"learning_rate": 0.0001939875056076697,
|
| 649 |
+
"loss": 1.3406,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.24893917963224893,
|
| 654 |
+
"grad_norm": 1.366113305091858,
|
| 655 |
+
"learning_rate": 0.00019161043631427666,
|
| 656 |
+
"loss": 1.389,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.25176803394625175,
|
| 661 |
+
"grad_norm": 1.3829034566879272,
|
| 662 |
+
"learning_rate": 0.00018922199114307294,
|
| 663 |
+
"loss": 1.4316,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.2545968882602546,
|
| 668 |
+
"grad_norm": 1.272460699081421,
|
| 669 |
+
"learning_rate": 0.00018682282307111987,
|
| 670 |
+
"loss": 1.185,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.25742574257425743,
|
| 675 |
+
"grad_norm": 1.2852873802185059,
|
| 676 |
+
"learning_rate": 0.00018441358800701273,
|
| 677 |
+
"loss": 1.1195,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.26025459688826025,
|
| 682 |
+
"grad_norm": 2.1650853157043457,
|
| 683 |
+
"learning_rate": 0.00018199494461156203,
|
| 684 |
+
"loss": 1.2838,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.26308345120226306,
|
| 689 |
+
"grad_norm": 1.4193148612976074,
|
| 690 |
+
"learning_rate": 0.000179567554117722,
|
| 691 |
+
"loss": 1.4974,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.26591230551626593,
|
| 696 |
+
"grad_norm": 1.585532784461975,
|
| 697 |
+
"learning_rate": 0.00017713208014981648,
|
| 698 |
+
"loss": 1.686,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.26874115983026875,
|
| 703 |
+
"grad_norm": 1.6499223709106445,
|
| 704 |
+
"learning_rate": 0.00017468918854211007,
|
| 705 |
+
"loss": 1.4436,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.27157001414427157,
|
| 710 |
+
"grad_norm": 1.9879748821258545,
|
| 711 |
+
"learning_rate": 0.00017223954715677627,
|
| 712 |
+
"loss": 1.7356,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.2743988684582744,
|
| 717 |
+
"grad_norm": 1.7074717283248901,
|
| 718 |
+
"learning_rate": 0.00016978382570131034,
|
| 719 |
+
"loss": 1.273,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.27722772277227725,
|
| 724 |
+
"grad_norm": 2.2398312091827393,
|
| 725 |
+
"learning_rate": 0.00016732269554543794,
|
| 726 |
+
"loss": 2.1488,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.28005657708628007,
|
| 731 |
+
"grad_norm": 1.637342929840088,
|
| 732 |
+
"learning_rate": 0.00016485682953756942,
|
| 733 |
+
"loss": 1.4976,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.2828854314002829,
|
| 738 |
+
"grad_norm": 2.2957942485809326,
|
| 739 |
+
"learning_rate": 0.00016238690182084986,
|
| 740 |
+
"loss": 1.4783,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.2828854314002829,
|
| 745 |
+
"eval_loss": 1.2889782190322876,
|
| 746 |
+
"eval_runtime": 6.5649,
|
| 747 |
+
"eval_samples_per_second": 7.616,
|
| 748 |
+
"eval_steps_per_second": 1.066,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 6.9969705172992e+16,
|
| 779 |
"train_batch_size": 8,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|