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 +363 -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 671149168
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f30139c3e6d445346dcdf3bf65b041747c7285344052b14d742880d1017ef1f
|
| 3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1342555602
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79ce9714e9d750a4539013ddfaa09d4f4547c29ebae67c70738b7e5f3e32403d
|
| 3 |
size 1342555602
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab5e10010e57371a1b8a59b364051037a27e75dbbd3ba2a8a40601e31fecfb6e
|
| 3 |
size 14960
|
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:d9457f0e49fafeaa4e39070d5a0b76df7f19a0ef84b6d9a330dbda6b3c59bb74
|
| 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:d2a8d48b1b719399b27c7cd139ee53a77c8f20b06ff1903eba06cd58f41ce5a9
|
| 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 sha256:7f78afd008f544c4d6389a2dadc3ea6f3312ac264009a4d96b2be974f3425696
|
| 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 sha256:5c9fd70aa4cf68daad2242bc04a8a03f22adc681e42e4ebf5294902cea9d0a87
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 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": 32.649,
|
| 374 |
"eval_steps_per_second": 4.081,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -401,7 +759,7 @@
|
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 8,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.922777533531189,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.08743169398907104,
|
| 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": 32.649,
|
| 374 |
"eval_steps_per_second": 4.081,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.04459016393442623,
|
| 379 |
+
"grad_norm": 4.682861804962158,
|
| 380 |
+
"learning_rate": 9.628188298907782e-05,
|
| 381 |
+
"loss": 5.3309,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.04546448087431694,
|
| 386 |
+
"grad_norm": 3.6267170906066895,
|
| 387 |
+
"learning_rate": 9.592434928729616e-05,
|
| 388 |
+
"loss": 4.896,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.046338797814207654,
|
| 393 |
+
"grad_norm": 2.9397659301757812,
|
| 394 |
+
"learning_rate": 9.555113246230442e-05,
|
| 395 |
+
"loss": 4.594,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.04721311475409836,
|
| 400 |
+
"grad_norm": 3.7889232635498047,
|
| 401 |
+
"learning_rate": 9.516235996730645e-05,
|
| 402 |
+
"loss": 4.6179,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.048087431693989074,
|
| 407 |
+
"grad_norm": 3.4238991737365723,
|
| 408 |
+
"learning_rate": 9.475816456775313e-05,
|
| 409 |
+
"loss": 4.3046,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.04896174863387978,
|
| 414 |
+
"grad_norm": 6.835710048675537,
|
| 415 |
+
"learning_rate": 9.43386842960031e-05,
|
| 416 |
+
"loss": 1.9497,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.049836065573770495,
|
| 421 |
+
"grad_norm": 6.923791885375977,
|
| 422 |
+
"learning_rate": 9.39040624041849e-05,
|
| 423 |
+
"loss": 2.179,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.0507103825136612,
|
| 428 |
+
"grad_norm": 4.5648932456970215,
|
| 429 |
+
"learning_rate": 9.345444731527642e-05,
|
| 430 |
+
"loss": 4.3407,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.051584699453551916,
|
| 435 |
+
"grad_norm": 3.808917284011841,
|
| 436 |
+
"learning_rate": 9.298999257241863e-05,
|
| 437 |
+
"loss": 4.3087,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.05245901639344262,
|
| 442 |
+
"grad_norm": 3.44407320022583,
|
| 443 |
+
"learning_rate": 9.251085678648072e-05,
|
| 444 |
+
"loss": 4.0944,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.05333333333333334,
|
| 449 |
+
"grad_norm": 3.4684829711914062,
|
| 450 |
+
"learning_rate": 9.201720358189464e-05,
|
| 451 |
+
"loss": 3.9452,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.054207650273224044,
|
| 456 |
+
"grad_norm": 4.555397033691406,
|
| 457 |
+
"learning_rate": 9.150920154077754e-05,
|
| 458 |
+
"loss": 3.8704,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.05508196721311476,
|
| 463 |
+
"grad_norm": 3.6485466957092285,
|
| 464 |
+
"learning_rate": 9.098702414536107e-05,
|
| 465 |
+
"loss": 3.9606,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.055956284153005464,
|
| 470 |
+
"grad_norm": 3.0883123874664307,
|
| 471 |
+
"learning_rate": 9.045084971874738e-05,
|
| 472 |
+
"loss": 5.0169,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.05683060109289618,
|
| 477 |
+
"grad_norm": 2.731473684310913,
|
| 478 |
+
"learning_rate": 8.9900861364012e-05,
|
| 479 |
+
"loss": 4.6796,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.057704918032786885,
|
| 484 |
+
"grad_norm": 3.1372900009155273,
|
| 485 |
+
"learning_rate": 8.933724690167417e-05,
|
| 486 |
+
"loss": 4.5271,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.0585792349726776,
|
| 491 |
+
"grad_norm": 2.9355735778808594,
|
| 492 |
+
"learning_rate": 8.876019880555649e-05,
|
| 493 |
+
"loss": 4.2805,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.059453551912568306,
|
| 498 |
+
"grad_norm": 2.6107537746429443,
|
| 499 |
+
"learning_rate": 8.816991413705516e-05,
|
| 500 |
+
"loss": 3.3194,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.06032786885245902,
|
| 505 |
+
"grad_norm": 9.008191108703613,
|
| 506 |
+
"learning_rate": 8.756659447784368e-05,
|
| 507 |
+
"loss": 1.2466,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.06120218579234973,
|
| 512 |
+
"grad_norm": 3.1812331676483154,
|
| 513 |
+
"learning_rate": 8.695044586103296e-05,
|
| 514 |
+
"loss": 3.4345,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.06207650273224044,
|
| 519 |
+
"grad_norm": 3.384528636932373,
|
| 520 |
+
"learning_rate": 8.632167870081121e-05,
|
| 521 |
+
"loss": 4.3751,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.06295081967213115,
|
| 526 |
+
"grad_norm": 2.8234190940856934,
|
| 527 |
+
"learning_rate": 8.568050772058762e-05,
|
| 528 |
+
"loss": 4.2436,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.06382513661202185,
|
| 533 |
+
"grad_norm": 3.3963890075683594,
|
| 534 |
+
"learning_rate": 8.502715187966455e-05,
|
| 535 |
+
"loss": 4.0892,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.06469945355191258,
|
| 540 |
+
"grad_norm": 3.8028182983398438,
|
| 541 |
+
"learning_rate": 8.436183429846313e-05,
|
| 542 |
+
"loss": 3.8655,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.06557377049180328,
|
| 547 |
+
"grad_norm": 4.164633274078369,
|
| 548 |
+
"learning_rate": 8.368478218232787e-05,
|
| 549 |
+
"loss": 3.1239,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.06644808743169399,
|
| 554 |
+
"grad_norm": 2.5254907608032227,
|
| 555 |
+
"learning_rate": 8.299622674393614e-05,
|
| 556 |
+
"loss": 5.017,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.0673224043715847,
|
| 561 |
+
"grad_norm": 2.449016809463501,
|
| 562 |
+
"learning_rate": 8.229640312433937e-05,
|
| 563 |
+
"loss": 4.8344,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.06819672131147542,
|
| 568 |
+
"grad_norm": 2.4585683345794678,
|
| 569 |
+
"learning_rate": 8.158555031266254e-05,
|
| 570 |
+
"loss": 4.6238,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.06907103825136612,
|
| 575 |
+
"grad_norm": 2.7618460655212402,
|
| 576 |
+
"learning_rate": 8.086391106448965e-05,
|
| 577 |
+
"loss": 4.4138,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.06994535519125683,
|
| 582 |
+
"grad_norm": 2.7431366443634033,
|
| 583 |
+
"learning_rate": 8.013173181896283e-05,
|
| 584 |
+
"loss": 4.3351,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.07081967213114754,
|
| 589 |
+
"grad_norm": 2.915708541870117,
|
| 590 |
+
"learning_rate": 7.938926261462366e-05,
|
| 591 |
+
"loss": 2.7006,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.07169398907103826,
|
| 596 |
+
"grad_norm": 6.260775566101074,
|
| 597 |
+
"learning_rate": 7.863675700402526e-05,
|
| 598 |
+
"loss": 1.3999,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.07256830601092897,
|
| 603 |
+
"grad_norm": 3.342338800430298,
|
| 604 |
+
"learning_rate": 7.787447196714427e-05,
|
| 605 |
+
"loss": 3.8281,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.07344262295081967,
|
| 610 |
+
"grad_norm": 3.0507147312164307,
|
| 611 |
+
"learning_rate": 7.710266782362247e-05,
|
| 612 |
+
"loss": 4.256,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.07431693989071038,
|
| 617 |
+
"grad_norm": 3.881892681121826,
|
| 618 |
+
"learning_rate": 7.63216081438678e-05,
|
| 619 |
+
"loss": 4.2829,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.0751912568306011,
|
| 624 |
+
"grad_norm": 3.3180391788482666,
|
| 625 |
+
"learning_rate": 7.553155965904535e-05,
|
| 626 |
+
"loss": 3.8737,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.0760655737704918,
|
| 631 |
+
"grad_norm": 3.3876357078552246,
|
| 632 |
+
"learning_rate": 7.473279216998895e-05,
|
| 633 |
+
"loss": 3.9718,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.07693989071038251,
|
| 638 |
+
"grad_norm": 5.030557155609131,
|
| 639 |
+
"learning_rate": 7.392557845506432e-05,
|
| 640 |
+
"loss": 3.6383,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.07781420765027322,
|
| 645 |
+
"grad_norm": 2.6808958053588867,
|
| 646 |
+
"learning_rate": 7.311019417701566e-05,
|
| 647 |
+
"loss": 4.9168,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.07868852459016394,
|
| 652 |
+
"grad_norm": 2.51533842086792,
|
| 653 |
+
"learning_rate": 7.228691778882693e-05,
|
| 654 |
+
"loss": 4.7042,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.07956284153005465,
|
| 659 |
+
"grad_norm": 2.41265869140625,
|
| 660 |
+
"learning_rate": 7.145603043863045e-05,
|
| 661 |
+
"loss": 4.3564,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.08043715846994536,
|
| 666 |
+
"grad_norm": 2.5100467205047607,
|
| 667 |
+
"learning_rate": 7.061781587369519e-05,
|
| 668 |
+
"loss": 4.3584,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.08131147540983606,
|
| 673 |
+
"grad_norm": 2.604959487915039,
|
| 674 |
+
"learning_rate": 6.977256034352712e-05,
|
| 675 |
+
"loss": 4.0976,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.08218579234972678,
|
| 680 |
+
"grad_norm": 5.754001617431641,
|
| 681 |
+
"learning_rate": 6.892055250211552e-05,
|
| 682 |
+
"loss": 0.9558,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.08306010928961749,
|
| 687 |
+
"grad_norm": 3.077754020690918,
|
| 688 |
+
"learning_rate": 6.806208330935766e-05,
|
| 689 |
+
"loss": 3.4805,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.0839344262295082,
|
| 694 |
+
"grad_norm": 2.9729459285736084,
|
| 695 |
+
"learning_rate": 6.719744593169641e-05,
|
| 696 |
+
"loss": 4.2485,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.0848087431693989,
|
| 701 |
+
"grad_norm": 2.972970962524414,
|
| 702 |
+
"learning_rate": 6.632693564200416e-05,
|
| 703 |
+
"loss": 4.1844,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.08568306010928962,
|
| 708 |
+
"grad_norm": 2.8650026321411133,
|
| 709 |
+
"learning_rate": 6.545084971874738e-05,
|
| 710 |
+
"loss": 3.9211,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.08655737704918033,
|
| 715 |
+
"grad_norm": 3.496151924133301,
|
| 716 |
+
"learning_rate": 6.456948734446624e-05,
|
| 717 |
+
"loss": 3.981,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.08743169398907104,
|
| 722 |
+
"grad_norm": 4.358485698699951,
|
| 723 |
+
"learning_rate": 6.368314950360415e-05,
|
| 724 |
+
"loss": 3.0869,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.08743169398907104,
|
| 729 |
+
"eval_loss": 0.922777533531189,
|
| 730 |
+
"eval_runtime": 236.35,
|
| 731 |
+
"eval_samples_per_second": 32.596,
|
| 732 |
+
"eval_steps_per_second": 4.074,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 8.940170116071424e+17,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|