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 3653851880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a4ae3d2c3a1543a871e5a58d63746709cdc8bf00389ba184eb24f003209868e
|
| 3 |
size 3653851880
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1856183844
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:819421be708c76366cc132d6fec8741cd1fb568bfeef053eeae3638e5107c6ab
|
| 3 |
size 1856183844
|
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 sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
|
| 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": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -357,6 +357,356 @@
|
|
| 357 |
"learning_rate": 0.00011736481776669306,
|
| 358 |
"loss": 0.2386,
|
| 359 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 360 |
}
|
| 361 |
],
|
| 362 |
"logging_steps": 1,
|
|
@@ -371,12 +721,12 @@
|
|
| 371 |
"should_evaluate": false,
|
| 372 |
"should_log": false,
|
| 373 |
"should_save": true,
|
| 374 |
-
"should_training_stop":
|
| 375 |
},
|
| 376 |
"attributes": {}
|
| 377 |
}
|
| 378 |
},
|
| 379 |
-
"total_flos":
|
| 380 |
"train_batch_size": 4,
|
| 381 |
"trial_name": null,
|
| 382 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.64,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 357 |
"learning_rate": 0.00011736481776669306,
|
| 358 |
"loss": 0.2386,
|
| 359 |
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.3264,
|
| 363 |
+
"grad_norm": 0.1110386997461319,
|
| 364 |
+
"learning_rate": 0.00011391731009600654,
|
| 365 |
+
"loss": 0.2862,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.3328,
|
| 370 |
+
"grad_norm": 0.11058996617794037,
|
| 371 |
+
"learning_rate": 0.00011045284632676536,
|
| 372 |
+
"loss": 0.3214,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.3392,
|
| 377 |
+
"grad_norm": 0.09535147994756699,
|
| 378 |
+
"learning_rate": 0.00010697564737441252,
|
| 379 |
+
"loss": 0.267,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.3456,
|
| 384 |
+
"grad_norm": 0.09183581173419952,
|
| 385 |
+
"learning_rate": 0.00010348994967025012,
|
| 386 |
+
"loss": 0.2545,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.352,
|
| 391 |
+
"grad_norm": 0.11743531376123428,
|
| 392 |
+
"learning_rate": 0.0001,
|
| 393 |
+
"loss": 0.2664,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.3584,
|
| 398 |
+
"grad_norm": 0.1046270951628685,
|
| 399 |
+
"learning_rate": 9.651005032974994e-05,
|
| 400 |
+
"loss": 0.2395,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3648,
|
| 405 |
+
"grad_norm": 0.11286702007055283,
|
| 406 |
+
"learning_rate": 9.302435262558747e-05,
|
| 407 |
+
"loss": 0.2463,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3712,
|
| 412 |
+
"grad_norm": 0.12298794090747833,
|
| 413 |
+
"learning_rate": 8.954715367323468e-05,
|
| 414 |
+
"loss": 0.254,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.3776,
|
| 419 |
+
"grad_norm": 0.1068972498178482,
|
| 420 |
+
"learning_rate": 8.608268990399349e-05,
|
| 421 |
+
"loss": 0.2714,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.384,
|
| 426 |
+
"grad_norm": 0.11853048950433731,
|
| 427 |
+
"learning_rate": 8.263518223330697e-05,
|
| 428 |
+
"loss": 0.2367,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3904,
|
| 433 |
+
"grad_norm": 0.0922948494553566,
|
| 434 |
+
"learning_rate": 7.920883091822408e-05,
|
| 435 |
+
"loss": 0.2219,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.3968,
|
| 440 |
+
"grad_norm": 0.1000463217496872,
|
| 441 |
+
"learning_rate": 7.580781044003324e-05,
|
| 442 |
+
"loss": 0.2424,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.4032,
|
| 447 |
+
"grad_norm": 0.0933864563703537,
|
| 448 |
+
"learning_rate": 7.243626441830009e-05,
|
| 449 |
+
"loss": 0.2304,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.4096,
|
| 454 |
+
"grad_norm": 0.10009445250034332,
|
| 455 |
+
"learning_rate": 6.909830056250527e-05,
|
| 456 |
+
"loss": 0.2183,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.416,
|
| 461 |
+
"grad_norm": 0.10700756311416626,
|
| 462 |
+
"learning_rate": 6.579798566743314e-05,
|
| 463 |
+
"loss": 0.2861,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.4224,
|
| 468 |
+
"grad_norm": 0.08552579581737518,
|
| 469 |
+
"learning_rate": 6.25393406584088e-05,
|
| 470 |
+
"loss": 0.2508,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.4288,
|
| 475 |
+
"grad_norm": 0.08115057647228241,
|
| 476 |
+
"learning_rate": 5.9326335692419995e-05,
|
| 477 |
+
"loss": 0.28,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.4352,
|
| 482 |
+
"grad_norm": 0.09101542085409164,
|
| 483 |
+
"learning_rate": 5.616288532109225e-05,
|
| 484 |
+
"loss": 0.2905,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.4416,
|
| 489 |
+
"grad_norm": 0.08541923761367798,
|
| 490 |
+
"learning_rate": 5.305284372141095e-05,
|
| 491 |
+
"loss": 0.2369,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.448,
|
| 496 |
+
"grad_norm": 0.08494503796100616,
|
| 497 |
+
"learning_rate": 5.000000000000002e-05,
|
| 498 |
+
"loss": 0.2535,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.4544,
|
| 503 |
+
"grad_norm": 0.09222583472728729,
|
| 504 |
+
"learning_rate": 4.700807357667952e-05,
|
| 505 |
+
"loss": 0.2164,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.4608,
|
| 510 |
+
"grad_norm": 0.09007549285888672,
|
| 511 |
+
"learning_rate": 4.4080709652925336e-05,
|
| 512 |
+
"loss": 0.2911,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.4672,
|
| 517 |
+
"grad_norm": 0.10070206969976425,
|
| 518 |
+
"learning_rate": 4.12214747707527e-05,
|
| 519 |
+
"loss": 0.2687,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.4736,
|
| 524 |
+
"grad_norm": 0.11217208206653595,
|
| 525 |
+
"learning_rate": 3.843385246743417e-05,
|
| 526 |
+
"loss": 0.2376,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.48,
|
| 531 |
+
"grad_norm": 0.0864848643541336,
|
| 532 |
+
"learning_rate": 3.5721239031346066e-05,
|
| 533 |
+
"loss": 0.2826,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4864,
|
| 538 |
+
"grad_norm": 0.08239398896694183,
|
| 539 |
+
"learning_rate": 3.308693936411421e-05,
|
| 540 |
+
"loss": 0.2344,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.4928,
|
| 545 |
+
"grad_norm": 0.10607580840587616,
|
| 546 |
+
"learning_rate": 3.053416295410026e-05,
|
| 547 |
+
"loss": 0.272,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.4992,
|
| 552 |
+
"grad_norm": 0.11652331054210663,
|
| 553 |
+
"learning_rate": 2.8066019966134904e-05,
|
| 554 |
+
"loss": 0.2398,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.5056,
|
| 559 |
+
"grad_norm": 0.08097366243600845,
|
| 560 |
+
"learning_rate": 2.5685517452260567e-05,
|
| 561 |
+
"loss": 0.2289,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.512,
|
| 566 |
+
"grad_norm": 0.08761543780565262,
|
| 567 |
+
"learning_rate": 2.339555568810221e-05,
|
| 568 |
+
"loss": 0.2297,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.5184,
|
| 573 |
+
"grad_norm": 0.09609895944595337,
|
| 574 |
+
"learning_rate": 2.119892463932781e-05,
|
| 575 |
+
"loss": 0.2214,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.5248,
|
| 580 |
+
"grad_norm": 0.10124152898788452,
|
| 581 |
+
"learning_rate": 1.9098300562505266e-05,
|
| 582 |
+
"loss": 0.2442,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.5312,
|
| 587 |
+
"grad_norm": 0.08449672907590866,
|
| 588 |
+
"learning_rate": 1.7096242744495837e-05,
|
| 589 |
+
"loss": 0.257,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.5376,
|
| 594 |
+
"grad_norm": 0.10185690224170685,
|
| 595 |
+
"learning_rate": 1.5195190384357404e-05,
|
| 596 |
+
"loss": 0.2331,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.544,
|
| 601 |
+
"grad_norm": 0.10394009202718735,
|
| 602 |
+
"learning_rate": 1.339745962155613e-05,
|
| 603 |
+
"loss": 0.2679,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.5504,
|
| 608 |
+
"grad_norm": 0.10671041160821915,
|
| 609 |
+
"learning_rate": 1.1705240714107302e-05,
|
| 610 |
+
"loss": 0.2953,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.5568,
|
| 615 |
+
"grad_norm": 0.09869690239429474,
|
| 616 |
+
"learning_rate": 1.0120595370083318e-05,
|
| 617 |
+
"loss": 0.2363,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.5632,
|
| 622 |
+
"grad_norm": 0.10397417098283768,
|
| 623 |
+
"learning_rate": 8.645454235739903e-06,
|
| 624 |
+
"loss": 0.2221,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5696,
|
| 629 |
+
"grad_norm": 0.10206641256809235,
|
| 630 |
+
"learning_rate": 7.281614543321269e-06,
|
| 631 |
+
"loss": 0.2329,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.576,
|
| 636 |
+
"grad_norm": 0.09630835801362991,
|
| 637 |
+
"learning_rate": 6.030737921409169e-06,
|
| 638 |
+
"loss": 0.2193,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5824,
|
| 643 |
+
"grad_norm": 0.09056926518678665,
|
| 644 |
+
"learning_rate": 4.8943483704846475e-06,
|
| 645 |
+
"loss": 0.2507,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.5888,
|
| 650 |
+
"grad_norm": 0.09456932544708252,
|
| 651 |
+
"learning_rate": 3.873830406168111e-06,
|
| 652 |
+
"loss": 0.2413,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.5952,
|
| 657 |
+
"grad_norm": 0.10614177584648132,
|
| 658 |
+
"learning_rate": 2.970427372400353e-06,
|
| 659 |
+
"loss": 0.2294,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.6016,
|
| 664 |
+
"grad_norm": 0.11094526201486588,
|
| 665 |
+
"learning_rate": 2.1852399266194314e-06,
|
| 666 |
+
"loss": 0.2282,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.608,
|
| 671 |
+
"grad_norm": 0.10783498734235764,
|
| 672 |
+
"learning_rate": 1.5192246987791981e-06,
|
| 673 |
+
"loss": 0.2099,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.6144,
|
| 678 |
+
"grad_norm": 0.12005529552698135,
|
| 679 |
+
"learning_rate": 9.731931258429638e-07,
|
| 680 |
+
"loss": 0.2289,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.6208,
|
| 685 |
+
"grad_norm": 0.09397509694099426,
|
| 686 |
+
"learning_rate": 5.478104631726711e-07,
|
| 687 |
+
"loss": 0.2478,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.6272,
|
| 692 |
+
"grad_norm": 0.08096156269311905,
|
| 693 |
+
"learning_rate": 2.4359497401758024e-07,
|
| 694 |
+
"loss": 0.2515,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.6336,
|
| 699 |
+
"grad_norm": 0.0987912192940712,
|
| 700 |
+
"learning_rate": 6.09172980904238e-08,
|
| 701 |
+
"loss": 0.2299,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.64,
|
| 706 |
+
"grad_norm": 0.10416976362466812,
|
| 707 |
+
"learning_rate": 0.0,
|
| 708 |
+
"loss": 0.1932,
|
| 709 |
+
"step": 100
|
| 710 |
}
|
| 711 |
],
|
| 712 |
"logging_steps": 1,
|
|
|
|
| 721 |
"should_evaluate": false,
|
| 722 |
"should_log": false,
|
| 723 |
"should_save": true,
|
| 724 |
+
"should_training_stop": true
|
| 725 |
},
|
| 726 |
"attributes": {}
|
| 727 |
}
|
| 728 |
},
|
| 729 |
+
"total_flos": 6.92661873012351e+17,
|
| 730 |
"train_batch_size": 4,
|
| 731 |
"trial_name": null,
|
| 732 |
"trial_params": null
|