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 97307544
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:344672b76a6eee910620b479fe729ea819e037970416a2da9c1f480b695cc16c
|
| 3 |
size 97307544
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 194840426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e2f7b880d09d0c3e663dd277d43931934dd5cae2c72a1d71171a7d9c4cdb79e1
|
| 3 |
size 194840426
|
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 sha256:0f040d6a8c201abcf3917e0a17887621ab7f00285dd9628429c57382ef120ecc
|
| 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:d96455b0fad3098637e80e0d67d418f96909245c6b651f9a052ab7d0d6a61b37
|
| 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:f8634313385285fd8196210c6d605ebf00c471ef08042ed77baf52e7f3ee383f
|
| 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 sha256:45d012378b6142add5604e3eaceff1e6b4f62ab3610e3a42446351ba5865dcab
|
| 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 sha256:9638e97525c935b52387c043e18f68d18c825b65e2c95cc7a3dc46bbe55a1e3b
|
| 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": 82.801,
|
| 382 |
"eval_steps_per_second": 8.28,
|
| 383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
|
@@ -409,7 +775,7 @@
|
|
| 409 |
"attributes": {}
|
| 410 |
}
|
| 411 |
},
|
| 412 |
-
"total_flos":
|
| 413 |
"train_batch_size": 3,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.0208970308303833,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.09225943352707815,
|
| 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": 82.801,
|
| 382 |
"eval_steps_per_second": 8.28,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.047052311098809856,
|
| 387 |
+
"grad_norm": 0.5303361415863037,
|
| 388 |
+
"learning_rate": 0.00019380934412829232,
|
| 389 |
+
"loss": 1.1873,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.04797490543408064,
|
| 394 |
+
"grad_norm": 0.717869222164154,
|
| 395 |
+
"learning_rate": 0.00019348327417301517,
|
| 396 |
+
"loss": 1.2218,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.04889749976935141,
|
| 401 |
+
"grad_norm": 0.6033234000205994,
|
| 402 |
+
"learning_rate": 0.00019314915792601581,
|
| 403 |
+
"loss": 1.2588,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.049820094104622195,
|
| 408 |
+
"grad_norm": 0.5174582004547119,
|
| 409 |
+
"learning_rate": 0.00019280702759011354,
|
| 410 |
+
"loss": 1.2331,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.05074268843989298,
|
| 415 |
+
"grad_norm": 0.4686112105846405,
|
| 416 |
+
"learning_rate": 0.00019245691614054226,
|
| 417 |
+
"loss": 1.1302,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.05166528277516376,
|
| 422 |
+
"grad_norm": 0.4974168539047241,
|
| 423 |
+
"learning_rate": 0.0001920988573217721,
|
| 424 |
+
"loss": 1.1626,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.05258787711043454,
|
| 429 |
+
"grad_norm": 0.5215023756027222,
|
| 430 |
+
"learning_rate": 0.00019173288564425733,
|
| 431 |
+
"loss": 1.1399,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.053510471445705324,
|
| 436 |
+
"grad_norm": 0.49643176794052124,
|
| 437 |
+
"learning_rate": 0.00019135903638110993,
|
| 438 |
+
"loss": 1.1402,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.054433065780976106,
|
| 443 |
+
"grad_norm": 0.5159599184989929,
|
| 444 |
+
"learning_rate": 0.00019097734556469995,
|
| 445 |
+
"loss": 1.0672,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.05535566011624689,
|
| 450 |
+
"grad_norm": 0.5096753239631653,
|
| 451 |
+
"learning_rate": 0.00019058784998318273,
|
| 452 |
+
"loss": 1.0373,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.05627825445151767,
|
| 457 |
+
"grad_norm": 0.5594645142555237,
|
| 458 |
+
"learning_rate": 0.0001901905871769531,
|
| 459 |
+
"loss": 1.0682,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.05720084878678845,
|
| 464 |
+
"grad_norm": 0.8526697158813477,
|
| 465 |
+
"learning_rate": 0.0001897855954350272,
|
| 466 |
+
"loss": 0.8273,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.05812344312205923,
|
| 471 |
+
"grad_norm": 0.5586766004562378,
|
| 472 |
+
"learning_rate": 0.00018937291379135196,
|
| 473 |
+
"loss": 1.1242,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.05904603745733001,
|
| 478 |
+
"grad_norm": 0.5625215172767639,
|
| 479 |
+
"learning_rate": 0.0001889525820210432,
|
| 480 |
+
"loss": 1.3812,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.05996863179260079,
|
| 485 |
+
"grad_norm": 0.46945062279701233,
|
| 486 |
+
"learning_rate": 0.00018852464063655176,
|
| 487 |
+
"loss": 1.2655,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.060891226127871574,
|
| 492 |
+
"grad_norm": 0.49760475754737854,
|
| 493 |
+
"learning_rate": 0.000188089130883759,
|
| 494 |
+
"loss": 1.1365,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.061813820463142356,
|
| 499 |
+
"grad_norm": 0.47834065556526184,
|
| 500 |
+
"learning_rate": 0.00018764609473800127,
|
| 501 |
+
"loss": 1.1662,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.06273641479841313,
|
| 506 |
+
"grad_norm": 0.508231520652771,
|
| 507 |
+
"learning_rate": 0.0001871955749000245,
|
| 508 |
+
"loss": 1.1352,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.06365900913368391,
|
| 513 |
+
"grad_norm": 0.5424789786338806,
|
| 514 |
+
"learning_rate": 0.00018673761479186832,
|
| 515 |
+
"loss": 1.1534,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.0645816034689547,
|
| 520 |
+
"grad_norm": 0.546637773513794,
|
| 521 |
+
"learning_rate": 0.0001862722585526811,
|
| 522 |
+
"loss": 1.1505,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.06550419780422548,
|
| 527 |
+
"grad_norm": 0.5321767330169678,
|
| 528 |
+
"learning_rate": 0.0001857995510344658,
|
| 529 |
+
"loss": 1.0851,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.06642679213949626,
|
| 534 |
+
"grad_norm": 0.5386099219322205,
|
| 535 |
+
"learning_rate": 0.00018531953779775683,
|
| 536 |
+
"loss": 1.0585,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.06734938647476704,
|
| 541 |
+
"grad_norm": 0.5138699412345886,
|
| 542 |
+
"learning_rate": 0.0001848322651072291,
|
| 543 |
+
"loss": 1.0444,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.06827198081003782,
|
| 548 |
+
"grad_norm": 0.6210483312606812,
|
| 549 |
+
"learning_rate": 0.0001843377799272386,
|
| 550 |
+
"loss": 0.9183,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.0691945751453086,
|
| 555 |
+
"grad_norm": 0.6338362097740173,
|
| 556 |
+
"learning_rate": 0.00018383612991729623,
|
| 557 |
+
"loss": 0.2692,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.0691945751453086,
|
| 562 |
+
"eval_loss": 1.0709586143493652,
|
| 563 |
+
"eval_runtime": 0.6044,
|
| 564 |
+
"eval_samples_per_second": 82.723,
|
| 565 |
+
"eval_steps_per_second": 8.272,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.07011716948057939,
|
| 570 |
+
"grad_norm": 0.4989747405052185,
|
| 571 |
+
"learning_rate": 0.00018332736342747404,
|
| 572 |
+
"loss": 1.2276,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.07103976381585017,
|
| 577 |
+
"grad_norm": 0.5539114475250244,
|
| 578 |
+
"learning_rate": 0.00018281152949374527,
|
| 579 |
+
"loss": 1.2626,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.07196235815112095,
|
| 584 |
+
"grad_norm": 0.45691347122192383,
|
| 585 |
+
"learning_rate": 0.00018228867783325804,
|
| 586 |
+
"loss": 1.2259,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.07288495248639174,
|
| 591 |
+
"grad_norm": 0.48130282759666443,
|
| 592 |
+
"learning_rate": 0.00018175885883954364,
|
| 593 |
+
"loss": 1.1878,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.07380754682166252,
|
| 598 |
+
"grad_norm": 0.4967883229255676,
|
| 599 |
+
"learning_rate": 0.00018122212357765945,
|
| 600 |
+
"loss": 1.1519,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.0747301411569333,
|
| 605 |
+
"grad_norm": 0.49831900000572205,
|
| 606 |
+
"learning_rate": 0.00018067852377926704,
|
| 607 |
+
"loss": 1.1397,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.07565273549220408,
|
| 612 |
+
"grad_norm": 0.5220170021057129,
|
| 613 |
+
"learning_rate": 0.0001801281118376465,
|
| 614 |
+
"loss": 1.0622,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.07657532982747486,
|
| 619 |
+
"grad_norm": 0.5449658632278442,
|
| 620 |
+
"learning_rate": 0.00017957094080264634,
|
| 621 |
+
"loss": 1.0355,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.07749792416274565,
|
| 626 |
+
"grad_norm": 0.6329752206802368,
|
| 627 |
+
"learning_rate": 0.00017900706437557054,
|
| 628 |
+
"loss": 1.0584,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.07842051849801643,
|
| 633 |
+
"grad_norm": 0.6001924276351929,
|
| 634 |
+
"learning_rate": 0.00017843653690400278,
|
| 635 |
+
"loss": 1.022,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.07934311283328721,
|
| 640 |
+
"grad_norm": 0.5846312046051025,
|
| 641 |
+
"learning_rate": 0.00017785941337656827,
|
| 642 |
+
"loss": 0.9959,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.08026570716855798,
|
| 647 |
+
"grad_norm": 0.6020424365997314,
|
| 648 |
+
"learning_rate": 0.00017727574941763373,
|
| 649 |
+
"loss": 0.4521,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.08118830150382876,
|
| 654 |
+
"grad_norm": 0.43142932653427124,
|
| 655 |
+
"learning_rate": 0.00017668560128194635,
|
| 656 |
+
"loss": 1.1681,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.08211089583909954,
|
| 661 |
+
"grad_norm": 0.660566508769989,
|
| 662 |
+
"learning_rate": 0.0001760890258492117,
|
| 663 |
+
"loss": 1.3461,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.08303349017437033,
|
| 668 |
+
"grad_norm": 0.5984129309654236,
|
| 669 |
+
"learning_rate": 0.00017548608061861176,
|
| 670 |
+
"loss": 1.2538,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.08395608450964111,
|
| 675 |
+
"grad_norm": 0.5732012391090393,
|
| 676 |
+
"learning_rate": 0.0001748768237032627,
|
| 677 |
+
"loss": 1.2725,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.08487867884491189,
|
| 682 |
+
"grad_norm": 0.5434936881065369,
|
| 683 |
+
"learning_rate": 0.00017426131382461415,
|
| 684 |
+
"loss": 1.0838,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.08580127318018267,
|
| 689 |
+
"grad_norm": 0.4646851718425751,
|
| 690 |
+
"learning_rate": 0.00017363961030678927,
|
| 691 |
+
"loss": 1.0811,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.08672386751545345,
|
| 696 |
+
"grad_norm": 0.48649483919143677,
|
| 697 |
+
"learning_rate": 0.00017301177307086713,
|
| 698 |
+
"loss": 1.0298,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.08764646185072424,
|
| 703 |
+
"grad_norm": 0.5579357147216797,
|
| 704 |
+
"learning_rate": 0.00017237786262910726,
|
| 705 |
+
"loss": 1.0374,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.08856905618599502,
|
| 710 |
+
"grad_norm": 0.612695574760437,
|
| 711 |
+
"learning_rate": 0.00017173794007911735,
|
| 712 |
+
"loss": 1.0592,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.0894916505212658,
|
| 717 |
+
"grad_norm": 0.5733603239059448,
|
| 718 |
+
"learning_rate": 0.00017109206709796477,
|
| 719 |
+
"loss": 1.0191,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.09041424485653658,
|
| 724 |
+
"grad_norm": 0.6126962304115295,
|
| 725 |
+
"learning_rate": 0.00017044030593623167,
|
| 726 |
+
"loss": 1.0036,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.09133683919180736,
|
| 731 |
+
"grad_norm": 0.6726813912391663,
|
| 732 |
+
"learning_rate": 0.00016978271941201536,
|
| 733 |
+
"loss": 0.8152,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.09225943352707815,
|
| 738 |
+
"grad_norm": 0.40060344338417053,
|
| 739 |
+
"learning_rate": 0.00016911937090487373,
|
| 740 |
+
"loss": 0.0465,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.09225943352707815,
|
| 745 |
+
"eval_loss": 1.0208970308303833,
|
| 746 |
+
"eval_runtime": 0.6034,
|
| 747 |
+
"eval_samples_per_second": 82.859,
|
| 748 |
+
"eval_steps_per_second": 8.286,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 4.1985528232411136e+17,
|
| 779 |
"train_batch_size": 3,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|