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 1521616
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5939366f8e0c4bfe7979f5551b49b628228d8ab0e5bf7c4503e74b912e5c8bd7
|
| 3 |
size 1521616
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3108666
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3a92e30fa822d7cfa2f2461ed09366ad8c4f5720138cf1caee3a6c7173e724f
|
| 3 |
size 3108666
|
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:f4c4c3ec5df6eba4c05a06b4188110a85b051b2b13e1681cb16e463ef78abe17
|
| 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:cbc53838d71d7ffbc88192ec7303d7e6bbca69387969f4dd64884419c5fd8735
|
| 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:d38ca30957f1bae8c2f8be41072eb1e4564215c1b03164f3762535e35c2f63d5
|
| 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:bfa6812679ba3104c6d0c851d5e9ffb6d9a1a191ceb230d4b225523e0da3d8aa
|
| 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 sha256:4104d3ca8fe9069127dc26e97c51fd3e36819b64c5c1d64d2ff7604a3c21107e
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch":
|
| 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": 254.354,
|
| 382 |
"eval_steps_per_second": 66.132,
|
| 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": 1.994510531425476,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 1.8465303771955082,
|
| 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": 254.354,
|
| 382 |
"eval_steps_per_second": 66.132,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.9398214799884825,
|
| 387 |
+
"grad_norm": 3.3888142108917236,
|
| 388 |
+
"learning_rate": 8.295635440954695e-05,
|
| 389 |
+
"loss": 2.2467,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.9582493521451195,
|
| 394 |
+
"grad_norm": 1.6675165891647339,
|
| 395 |
+
"learning_rate": 8.224519749672376e-05,
|
| 396 |
+
"loss": 2.1031,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.9766772243017564,
|
| 401 |
+
"grad_norm": 1.0358479022979736,
|
| 402 |
+
"learning_rate": 8.152313181077242e-05,
|
| 403 |
+
"loss": 2.0694,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.9951050964583933,
|
| 408 |
+
"grad_norm": 1.0793170928955078,
|
| 409 |
+
"learning_rate": 8.079044646138837e-05,
|
| 410 |
+
"loss": 2.0398,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.0172761301468471,
|
| 415 |
+
"grad_norm": 5.010680675506592,
|
| 416 |
+
"learning_rate": 8.004743481030088e-05,
|
| 417 |
+
"loss": 4.036,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.035704002303484,
|
| 422 |
+
"grad_norm": 3.263810873031616,
|
| 423 |
+
"learning_rate": 7.929439435381305e-05,
|
| 424 |
+
"loss": 2.2462,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.054131874460121,
|
| 429 |
+
"grad_norm": 2.19437837600708,
|
| 430 |
+
"learning_rate": 7.853162660368662e-05,
|
| 431 |
+
"loss": 2.1076,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.0725597466167578,
|
| 436 |
+
"grad_norm": 1.1197891235351562,
|
| 437 |
+
"learning_rate": 7.775943696641888e-05,
|
| 438 |
+
"loss": 2.0394,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.0909876187733947,
|
| 443 |
+
"grad_norm": 1.35910964012146,
|
| 444 |
+
"learning_rate": 7.697813462096025e-05,
|
| 445 |
+
"loss": 2.0473,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.1094154909300316,
|
| 450 |
+
"grad_norm": 1.9377872943878174,
|
| 451 |
+
"learning_rate": 7.618803239492121e-05,
|
| 452 |
+
"loss": 2.0849,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.1278433630866687,
|
| 457 |
+
"grad_norm": 1.510143756866455,
|
| 458 |
+
"learning_rate": 7.538944663931862e-05,
|
| 459 |
+
"loss": 2.0566,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.1462712352433055,
|
| 464 |
+
"grad_norm": 2.0934293270111084,
|
| 465 |
+
"learning_rate": 7.458269710191101e-05,
|
| 466 |
+
"loss": 1.9738,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.1646991073999424,
|
| 471 |
+
"grad_norm": 0.8613946437835693,
|
| 472 |
+
"learning_rate": 7.376810679917411e-05,
|
| 473 |
+
"loss": 2.0698,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.1831269795565793,
|
| 478 |
+
"grad_norm": 0.933632493019104,
|
| 479 |
+
"learning_rate": 7.294600188696732e-05,
|
| 480 |
+
"loss": 2.0709,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 1.2015548517132162,
|
| 485 |
+
"grad_norm": 1.4427233934402466,
|
| 486 |
+
"learning_rate": 7.211671152994348e-05,
|
| 487 |
+
"loss": 1.9954,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.219982723869853,
|
| 492 |
+
"grad_norm": 2.0800139904022217,
|
| 493 |
+
"learning_rate": 7.128056776975369e-05,
|
| 494 |
+
"loss": 1.9794,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.23841059602649,
|
| 499 |
+
"grad_norm": 1.3812874555587769,
|
| 500 |
+
"learning_rate": 7.043790539210045e-05,
|
| 501 |
+
"loss": 2.0207,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 1.256838468183127,
|
| 506 |
+
"grad_norm": 1.9489840269088745,
|
| 507 |
+
"learning_rate": 6.95890617926918e-05,
|
| 508 |
+
"loss": 2.0679,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.275266340339764,
|
| 513 |
+
"grad_norm": 1.545703411102295,
|
| 514 |
+
"learning_rate": 6.873437684215077e-05,
|
| 515 |
+
"loss": 2.0753,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 1.2936942124964008,
|
| 520 |
+
"grad_norm": 1.9554816484451294,
|
| 521 |
+
"learning_rate": 6.787419274993366e-05,
|
| 522 |
+
"loss": 2.0324,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 1.3121220846530377,
|
| 527 |
+
"grad_norm": 2.3300676345825195,
|
| 528 |
+
"learning_rate": 6.700885392731187e-05,
|
| 529 |
+
"loss": 2.0034,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 1.3305499568096746,
|
| 534 |
+
"grad_norm": 1.7361541986465454,
|
| 535 |
+
"learning_rate": 6.613870684947231e-05,
|
| 536 |
+
"loss": 2.0202,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.3489778289663115,
|
| 541 |
+
"grad_norm": 1.2443159818649292,
|
| 542 |
+
"learning_rate": 6.526409991679134e-05,
|
| 543 |
+
"loss": 1.9933,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 1.3674057011229483,
|
| 548 |
+
"grad_norm": 0.6612122654914856,
|
| 549 |
+
"learning_rate": 6.438538331533768e-05,
|
| 550 |
+
"loss": 1.9769,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 1.3858335732795855,
|
| 555 |
+
"grad_norm": 0.6065022945404053,
|
| 556 |
+
"learning_rate": 6.350290887666078e-05,
|
| 557 |
+
"loss": 2.0084,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 1.3858335732795855,
|
| 562 |
+
"eval_loss": 2.0034306049346924,
|
| 563 |
+
"eval_runtime": 0.1919,
|
| 564 |
+
"eval_samples_per_second": 260.533,
|
| 565 |
+
"eval_steps_per_second": 67.739,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.4042614454362223,
|
| 570 |
+
"grad_norm": 0.7181031107902527,
|
| 571 |
+
"learning_rate": 6.261702993691994e-05,
|
| 572 |
+
"loss": 2.0097,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.4226893175928592,
|
| 577 |
+
"grad_norm": 1.1980915069580078,
|
| 578 |
+
"learning_rate": 6.172810119541118e-05,
|
| 579 |
+
"loss": 2.0081,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.441117189749496,
|
| 584 |
+
"grad_norm": 2.185781478881836,
|
| 585 |
+
"learning_rate": 6.083647857254837e-05,
|
| 586 |
+
"loss": 1.9817,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.459545061906133,
|
| 591 |
+
"grad_norm": 0.7530511021614075,
|
| 592 |
+
"learning_rate": 5.9942519067355284e-05,
|
| 593 |
+
"loss": 1.9986,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.4779729340627699,
|
| 598 |
+
"grad_norm": 1.7427482604980469,
|
| 599 |
+
"learning_rate": 5.904658061452585e-05,
|
| 600 |
+
"loss": 2.0496,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.4964008062194067,
|
| 605 |
+
"grad_norm": 2.031916618347168,
|
| 606 |
+
"learning_rate": 5.814902194110988e-05,
|
| 607 |
+
"loss": 2.0361,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.5148286783760438,
|
| 612 |
+
"grad_norm": 1.6156734228134155,
|
| 613 |
+
"learning_rate": 5.7250202422881336e-05,
|
| 614 |
+
"loss": 2.0416,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.5332565505326807,
|
| 619 |
+
"grad_norm": 0.9678031206130981,
|
| 620 |
+
"learning_rate": 5.635048194044702e-05,
|
| 621 |
+
"loss": 2.0342,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.5516844226893176,
|
| 626 |
+
"grad_norm": 0.4935534596443176,
|
| 627 |
+
"learning_rate": 5.5450220735153056e-05,
|
| 628 |
+
"loss": 1.9647,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.5701122948459545,
|
| 633 |
+
"grad_norm": 1.1301989555358887,
|
| 634 |
+
"learning_rate": 5.4549779264846955e-05,
|
| 635 |
+
"loss": 1.9986,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.5885401670025914,
|
| 640 |
+
"grad_norm": 2.0241589546203613,
|
| 641 |
+
"learning_rate": 5.3649518059552994e-05,
|
| 642 |
+
"loss": 2.0601,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.6069680391592285,
|
| 647 |
+
"grad_norm": 1.204086184501648,
|
| 648 |
+
"learning_rate": 5.2749797577118675e-05,
|
| 649 |
+
"loss": 1.9727,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.6253959113158651,
|
| 654 |
+
"grad_norm": 1.2840675115585327,
|
| 655 |
+
"learning_rate": 5.185097805889013e-05,
|
| 656 |
+
"loss": 2.0326,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.6438237834725022,
|
| 661 |
+
"grad_norm": 1.003303050994873,
|
| 662 |
+
"learning_rate": 5.0953419385474155e-05,
|
| 663 |
+
"loss": 1.9445,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.6622516556291391,
|
| 668 |
+
"grad_norm": 0.5838247537612915,
|
| 669 |
+
"learning_rate": 5.005748093264473e-05,
|
| 670 |
+
"loss": 1.9922,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.680679527785776,
|
| 675 |
+
"grad_norm": 0.7593981623649597,
|
| 676 |
+
"learning_rate": 4.916352142745163e-05,
|
| 677 |
+
"loss": 1.966,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.6991073999424129,
|
| 682 |
+
"grad_norm": 0.8177780508995056,
|
| 683 |
+
"learning_rate": 4.827189880458882e-05,
|
| 684 |
+
"loss": 1.9918,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.7175352720990498,
|
| 689 |
+
"grad_norm": 0.8616487979888916,
|
| 690 |
+
"learning_rate": 4.7382970063080076e-05,
|
| 691 |
+
"loss": 2.0279,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.7359631442556869,
|
| 696 |
+
"grad_norm": 1.1605690717697144,
|
| 697 |
+
"learning_rate": 4.649709112333923e-05,
|
| 698 |
+
"loss": 2.0104,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.7543910164123235,
|
| 703 |
+
"grad_norm": 1.9952294826507568,
|
| 704 |
+
"learning_rate": 4.561461668466233e-05,
|
| 705 |
+
"loss": 1.9628,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.7728188885689606,
|
| 710 |
+
"grad_norm": 1.4495019912719727,
|
| 711 |
+
"learning_rate": 4.473590008320868e-05,
|
| 712 |
+
"loss": 2.0058,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.7912467607255975,
|
| 717 |
+
"grad_norm": 1.114969253540039,
|
| 718 |
+
"learning_rate": 4.386129315052768e-05,
|
| 719 |
+
"loss": 2.0131,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.8096746328822344,
|
| 724 |
+
"grad_norm": 0.8008613586425781,
|
| 725 |
+
"learning_rate": 4.299114607268814e-05,
|
| 726 |
+
"loss": 1.9947,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.8281025050388713,
|
| 731 |
+
"grad_norm": 0.7169589400291443,
|
| 732 |
+
"learning_rate": 4.2125807250066354e-05,
|
| 733 |
+
"loss": 1.9454,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.8465303771955082,
|
| 738 |
+
"grad_norm": 1.009277582168579,
|
| 739 |
+
"learning_rate": 4.1265623157849235e-05,
|
| 740 |
+
"loss": 2.0115,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.8465303771955082,
|
| 745 |
+
"eval_loss": 1.994510531425476,
|
| 746 |
+
"eval_runtime": 0.192,
|
| 747 |
+
"eval_samples_per_second": 260.351,
|
| 748 |
+
"eval_steps_per_second": 67.691,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 928417715322880.0,
|
| 779 |
"train_batch_size": 1,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|