Training in progress, step 100, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +371 -5
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13587864
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8360975599d9ee4a4ee411c8f1cc2b0c35825bf8d393ec9c864f89971ffde2ae
|
| 3 |
size 13587864
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 27273018
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49eecbd237b68ad70c577c8ff7e819b7e92e76ef96dd18fb804e48c36028f643
|
| 3 |
size 27273018
|
last-checkpoint/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4539c524f63404b02bfa58cff36e62ce8ae7b9c028d47aa10d725df6f040629c
|
| 3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd125cb9ecad77cadeadabb22b22642cf7e9de35acf800977a895980f38e3788
|
| 3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c3b86c562fbca6ea65842f86630024b1d2de4305e7c472c99265bcc81bc860e
|
| 3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ff0435b6c2a8a9add06442eacd037ea4c488f1cd755e7f1185edf5dac8a311c
|
| 3 |
size 15024
|
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:af0b17754e8379d35b8568fcdfcceb7a1b2d560c454ce4dd5fdb665e8ee0830c
|
| 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": 179.063,
|
| 382 |
"eval_steps_per_second": 46.557,
|
| 383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
|
@@ -409,7 +775,7 @@
|
|
| 409 |
"attributes": {}
|
| 410 |
}
|
| 411 |
},
|
| 412 |
-
"total_flos":
|
| 413 |
"train_batch_size": 1,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.7645323276519775,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.7626310772163966,
|
| 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": 179.063,
|
| 382 |
"eval_steps_per_second": 46.557,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.38894184938036225,
|
| 387 |
+
"grad_norm": 1.3231308460235596,
|
| 388 |
+
"learning_rate": 0.00028079336235003674,
|
| 389 |
+
"loss": 1.8672,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.3965681601525262,
|
| 394 |
+
"grad_norm": 0.3953985869884491,
|
| 395 |
+
"learning_rate": 0.0002799329510692108,
|
| 396 |
+
"loss": 1.7821,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.4041944709246902,
|
| 401 |
+
"grad_norm": 0.34664496779441833,
|
| 402 |
+
"learning_rate": 0.0002790552313087104,
|
| 403 |
+
"loss": 1.8357,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.41182078169685415,
|
| 408 |
+
"grad_norm": 0.32160669565200806,
|
| 409 |
+
"learning_rate": 0.0002781603352499031,
|
| 410 |
+
"loss": 1.8114,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.4194470924690181,
|
| 415 |
+
"grad_norm": 0.35647809505462646,
|
| 416 |
+
"learning_rate": 0.0002772483976608436,
|
| 417 |
+
"loss": 1.9044,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.4270734032411821,
|
| 422 |
+
"grad_norm": 0.5951141715049744,
|
| 423 |
+
"learning_rate": 0.0002763195558759784,
|
| 424 |
+
"loss": 1.8211,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.43469971401334606,
|
| 429 |
+
"grad_norm": 0.5895670652389526,
|
| 430 |
+
"learning_rate": 0.00027537394977546377,
|
| 431 |
+
"loss": 1.8736,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.44232602478551003,
|
| 436 |
+
"grad_norm": 0.3808022439479828,
|
| 437 |
+
"learning_rate": 0.00027441172176410027,
|
| 438 |
+
"loss": 1.8487,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.449952335557674,
|
| 443 |
+
"grad_norm": 0.3616071343421936,
|
| 444 |
+
"learning_rate": 0.000273433016749887,
|
| 445 |
+
"loss": 1.86,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.45757864632983797,
|
| 450 |
+
"grad_norm": 0.34098148345947266,
|
| 451 |
+
"learning_rate": 0.00027243798212219926,
|
| 452 |
+
"loss": 1.8849,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.4652049571020019,
|
| 457 |
+
"grad_norm": 0.3677496910095215,
|
| 458 |
+
"learning_rate": 0.0002714267677295918,
|
| 459 |
+
"loss": 1.9066,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.47283126787416585,
|
| 464 |
+
"grad_norm": 0.42355066537857056,
|
| 465 |
+
"learning_rate": 0.0002703995258572327,
|
| 466 |
+
"loss": 1.8943,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.4804575786463298,
|
| 471 |
+
"grad_norm": 0.8111021518707275,
|
| 472 |
+
"learning_rate": 0.0002693564112039695,
|
| 473 |
+
"loss": 1.8816,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.4880838894184938,
|
| 478 |
+
"grad_norm": 0.5244035720825195,
|
| 479 |
+
"learning_rate": 0.00026829758085903196,
|
| 480 |
+
"loss": 1.7596,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.49571020019065776,
|
| 485 |
+
"grad_norm": 0.49128928780555725,
|
| 486 |
+
"learning_rate": 0.0002672231942783754,
|
| 487 |
+
"loss": 1.7882,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.5033365109628217,
|
| 492 |
+
"grad_norm": 0.35969385504722595,
|
| 493 |
+
"learning_rate": 0.000266133413260667,
|
| 494 |
+
"loss": 1.7607,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.5109628217349858,
|
| 499 |
+
"grad_norm": 0.30560654401779175,
|
| 500 |
+
"learning_rate": 0.0002650284019229195,
|
| 501 |
+
"loss": 1.7378,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.5185891325071497,
|
| 506 |
+
"grad_norm": 0.2821063697338104,
|
| 507 |
+
"learning_rate": 0.0002639083266757757,
|
| 508 |
+
"loss": 1.7452,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.5262154432793136,
|
| 513 |
+
"grad_norm": 0.30434897541999817,
|
| 514 |
+
"learning_rate": 0.000262773356198448,
|
| 515 |
+
"loss": 1.757,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.5338417540514776,
|
| 520 |
+
"grad_norm": 0.35866251587867737,
|
| 521 |
+
"learning_rate": 0.0002616236614133155,
|
| 522 |
+
"loss": 1.8456,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.5414680648236415,
|
| 527 |
+
"grad_norm": 0.36527636647224426,
|
| 528 |
+
"learning_rate": 0.0002604594154601839,
|
| 529 |
+
"loss": 1.7636,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.5490943755958055,
|
| 534 |
+
"grad_norm": 0.4293094575405121,
|
| 535 |
+
"learning_rate": 0.00025928079367021134,
|
| 536 |
+
"loss": 1.7983,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.5567206863679695,
|
| 541 |
+
"grad_norm": 0.4558382034301758,
|
| 542 |
+
"learning_rate": 0.000258087973539504,
|
| 543 |
+
"loss": 1.8167,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.5643469971401335,
|
| 548 |
+
"grad_norm": 0.46237555146217346,
|
| 549 |
+
"learning_rate": 0.00025688113470238616,
|
| 550 |
+
"loss": 1.8516,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.5719733079122974,
|
| 555 |
+
"grad_norm": 0.5830234885215759,
|
| 556 |
+
"learning_rate": 0.00025566045890434747,
|
| 557 |
+
"loss": 1.8979,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.5719733079122974,
|
| 562 |
+
"eval_loss": 1.8215560913085938,
|
| 563 |
+
"eval_runtime": 0.2804,
|
| 564 |
+
"eval_samples_per_second": 178.348,
|
| 565 |
+
"eval_steps_per_second": 46.371,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.5795996186844614,
|
| 570 |
+
"grad_norm": 0.4658236503601074,
|
| 571 |
+
"learning_rate": 0.00025442612997467315,
|
| 572 |
+
"loss": 1.7275,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.5872259294566253,
|
| 577 |
+
"grad_norm": 0.45749977231025696,
|
| 578 |
+
"learning_rate": 0.0002531783337987598,
|
| 579 |
+
"loss": 1.7482,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.5948522402287894,
|
| 584 |
+
"grad_norm": 0.4462372660636902,
|
| 585 |
+
"learning_rate": 0.0002519172582901218,
|
| 586 |
+
"loss": 1.7561,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.6024785510009533,
|
| 591 |
+
"grad_norm": 0.38078993558883667,
|
| 592 |
+
"learning_rate": 0.00025064309336209214,
|
| 593 |
+
"loss": 1.7398,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.6101048617731173,
|
| 598 |
+
"grad_norm": 0.3360918164253235,
|
| 599 |
+
"learning_rate": 0.00024935603089922215,
|
| 600 |
+
"loss": 1.7546,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.6177311725452812,
|
| 605 |
+
"grad_norm": 0.30906444787979126,
|
| 606 |
+
"learning_rate": 0.0002480562647283846,
|
| 607 |
+
"loss": 1.7487,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.6253574833174452,
|
| 612 |
+
"grad_norm": 0.36905303597450256,
|
| 613 |
+
"learning_rate": 0.00024674399058958394,
|
| 614 |
+
"loss": 1.7589,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.6329837940896091,
|
| 619 |
+
"grad_norm": 0.3760243058204651,
|
| 620 |
+
"learning_rate": 0.0002454194061064785,
|
| 621 |
+
"loss": 1.7732,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.6406101048617732,
|
| 626 |
+
"grad_norm": 0.41075772047042847,
|
| 627 |
+
"learning_rate": 0.0002440827107566192,
|
| 628 |
+
"loss": 1.7812,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.6482364156339371,
|
| 633 |
+
"grad_norm": 0.41905277967453003,
|
| 634 |
+
"learning_rate": 0.00024273410584140913,
|
| 635 |
+
"loss": 1.7692,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.655862726406101,
|
| 640 |
+
"grad_norm": 0.41411152482032776,
|
| 641 |
+
"learning_rate": 0.00024137379445578774,
|
| 642 |
+
"loss": 1.8508,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.663489037178265,
|
| 647 |
+
"grad_norm": 0.47408804297447205,
|
| 648 |
+
"learning_rate": 0.0002400019814576463,
|
| 649 |
+
"loss": 1.847,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.6711153479504289,
|
| 654 |
+
"grad_norm": 0.4235435724258423,
|
| 655 |
+
"learning_rate": 0.00023861887343697624,
|
| 656 |
+
"loss": 1.8122,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.678741658722593,
|
| 661 |
+
"grad_norm": 0.3859807252883911,
|
| 662 |
+
"learning_rate": 0.00023722467868475812,
|
| 663 |
+
"loss": 1.6975,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.6863679694947569,
|
| 668 |
+
"grad_norm": 0.3468429148197174,
|
| 669 |
+
"learning_rate": 0.0002358196071615933,
|
| 670 |
+
"loss": 1.694,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.6939942802669209,
|
| 675 |
+
"grad_norm": 0.3533165156841278,
|
| 676 |
+
"learning_rate": 0.00023440387046608487,
|
| 677 |
+
"loss": 1.6882,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.7016205910390848,
|
| 682 |
+
"grad_norm": 0.3266445994377136,
|
| 683 |
+
"learning_rate": 0.00023297768180297187,
|
| 684 |
+
"loss": 1.6909,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.7092469018112488,
|
| 689 |
+
"grad_norm": 0.3379365801811218,
|
| 690 |
+
"learning_rate": 0.00023154125595102083,
|
| 691 |
+
"loss": 1.7055,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.7168732125834127,
|
| 696 |
+
"grad_norm": 0.32845547795295715,
|
| 697 |
+
"learning_rate": 0.00023009480923068157,
|
| 698 |
+
"loss": 1.7529,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.7244995233555768,
|
| 703 |
+
"grad_norm": 0.3393206000328064,
|
| 704 |
+
"learning_rate": 0.00022863855947150968,
|
| 705 |
+
"loss": 1.7702,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.7321258341277407,
|
| 710 |
+
"grad_norm": 0.3422520160675049,
|
| 711 |
+
"learning_rate": 0.0002271727259793624,
|
| 712 |
+
"loss": 1.7063,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.7397521448999047,
|
| 717 |
+
"grad_norm": 0.378302663564682,
|
| 718 |
+
"learning_rate": 0.0002256975295033719,
|
| 719 |
+
"loss": 1.7602,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.7473784556720686,
|
| 724 |
+
"grad_norm": 0.41780129075050354,
|
| 725 |
+
"learning_rate": 0.0002242131922027012,
|
| 726 |
+
"loss": 1.8039,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.7550047664442326,
|
| 731 |
+
"grad_norm": 0.44365987181663513,
|
| 732 |
+
"learning_rate": 0.00022271993761308807,
|
| 733 |
+
"loss": 1.7738,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.7626310772163966,
|
| 738 |
+
"grad_norm": 0.5752303600311279,
|
| 739 |
+
"learning_rate": 0.00022121799061318104,
|
| 740 |
+
"loss": 1.9044,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.7626310772163966,
|
| 745 |
+
"eval_loss": 1.7645323276519775,
|
| 746 |
+
"eval_runtime": 0.28,
|
| 747 |
+
"eval_samples_per_second": 178.583,
|
| 748 |
+
"eval_steps_per_second": 46.431,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 4.44280275468288e+16,
|
| 779 |
"train_batch_size": 1,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|