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 78480072
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0586752f3979653235538cb76d586e933e30062b1a35ebf40ce0480b2ae556b4
|
| 3 |
size 78480072
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 157104826
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b976f4f7ca39bcc598e3150657e41d22566bfff384b274ef60bea64b58e4ba2
|
| 3 |
size 157104826
|
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 sha256:2b3c850cd945b590d66f8306a5dc2bcd4719c74f40e07cce9a03515237e59666
|
| 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 sha256:7929042630bdf72e45e8596f43c5141f02517487a96e15f8463617c2259ba7ce
|
| 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:afc2344264333f58c1f67871a8080082f1e7869b84cb88c38366c734877c212e
|
| 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:ef2c5cf3ce45f3fb7bf3784c5e4fb05a993b91767ce8e1730eb9c27ddb38b6c6
|
| 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:c5d2a6c6aafc669cea03b9634666f204de949a3d45ce2f48a07e7e3eaf18c715
|
| 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": 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": 65.71,
|
| 382 |
"eval_steps_per_second": 2.628,
|
| 383 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 384 |
}
|
| 385 |
],
|
| 386 |
"logging_steps": 1,
|
|
@@ -409,7 +775,7 @@
|
|
| 409 |
"attributes": {}
|
| 410 |
}
|
| 411 |
},
|
| 412 |
-
"total_flos":
|
| 413 |
"train_batch_size": 8,
|
| 414 |
"trial_name": null,
|
| 415 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.08561168611049652,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.38872691933916426,
|
| 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": 65.71,
|
| 382 |
"eval_steps_per_second": 2.628,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.19825072886297376,
|
| 387 |
+
"grad_norm": 0.13819019496440887,
|
| 388 |
+
"learning_rate": 0.0002668315918143169,
|
| 389 |
+
"loss": 0.0541,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.2021379980563654,
|
| 394 |
+
"grad_norm": 0.1316405087709427,
|
| 395 |
+
"learning_rate": 0.00026526016662852886,
|
| 396 |
+
"loss": 0.0405,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.20602526724975703,
|
| 401 |
+
"grad_norm": 0.06152060255408287,
|
| 402 |
+
"learning_rate": 0.00026365723046405023,
|
| 403 |
+
"loss": 0.0351,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.2099125364431487,
|
| 408 |
+
"grad_norm": 0.053634870797395706,
|
| 409 |
+
"learning_rate": 0.0002620232215476231,
|
| 410 |
+
"loss": 0.0469,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.21379980563654033,
|
| 415 |
+
"grad_norm": 0.06233103573322296,
|
| 416 |
+
"learning_rate": 0.0002603585866009697,
|
| 417 |
+
"loss": 0.0538,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.21768707482993196,
|
| 422 |
+
"grad_norm": 0.07677210867404938,
|
| 423 |
+
"learning_rate": 0.00025866378071866334,
|
| 424 |
+
"loss": 0.0547,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.22157434402332363,
|
| 429 |
+
"grad_norm": 0.09678474068641663,
|
| 430 |
+
"learning_rate": 0.00025693926724370956,
|
| 431 |
+
"loss": 0.0678,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.22546161321671526,
|
| 436 |
+
"grad_norm": 0.12184121459722519,
|
| 437 |
+
"learning_rate": 0.00025518551764087326,
|
| 438 |
+
"loss": 0.1066,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.2293488824101069,
|
| 443 |
+
"grad_norm": 0.1470523178577423,
|
| 444 |
+
"learning_rate": 0.00025340301136778483,
|
| 445 |
+
"loss": 0.1323,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.23323615160349853,
|
| 450 |
+
"grad_norm": 0.18343396484851837,
|
| 451 |
+
"learning_rate": 0.00025159223574386114,
|
| 452 |
+
"loss": 0.1909,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.2371234207968902,
|
| 457 |
+
"grad_norm": 0.18938356637954712,
|
| 458 |
+
"learning_rate": 0.0002497536858170772,
|
| 459 |
+
"loss": 0.2124,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.24101068999028183,
|
| 464 |
+
"grad_norm": 0.34483832120895386,
|
| 465 |
+
"learning_rate": 0.00024788786422862526,
|
| 466 |
+
"loss": 0.36,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.24489795918367346,
|
| 471 |
+
"grad_norm": 0.07590112835168839,
|
| 472 |
+
"learning_rate": 0.00024599528107549745,
|
| 473 |
+
"loss": 0.0741,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.2487852283770651,
|
| 478 |
+
"grad_norm": 0.0571330301463604,
|
| 479 |
+
"learning_rate": 0.00024407645377103054,
|
| 480 |
+
"loss": 0.05,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.25267249757045673,
|
| 485 |
+
"grad_norm": 0.045787546783685684,
|
| 486 |
+
"learning_rate": 0.00024213190690345018,
|
| 487 |
+
"loss": 0.0402,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.2565597667638484,
|
| 492 |
+
"grad_norm": 0.05736127123236656,
|
| 493 |
+
"learning_rate": 0.00024016217209245374,
|
| 494 |
+
"loss": 0.0411,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.26044703595724006,
|
| 499 |
+
"grad_norm": 0.07004929333925247,
|
| 500 |
+
"learning_rate": 0.00023816778784387094,
|
| 501 |
+
"loss": 0.0401,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.26433430515063167,
|
| 506 |
+
"grad_norm": 0.07149740308523178,
|
| 507 |
+
"learning_rate": 0.0002361492994024415,
|
| 508 |
+
"loss": 0.0527,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.26822157434402333,
|
| 513 |
+
"grad_norm": 0.08593209832906723,
|
| 514 |
+
"learning_rate": 0.0002341072586027509,
|
| 515 |
+
"loss": 0.0663,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.272108843537415,
|
| 520 |
+
"grad_norm": 0.09691403806209564,
|
| 521 |
+
"learning_rate": 0.00023204222371836405,
|
| 522 |
+
"loss": 0.091,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.2759961127308066,
|
| 527 |
+
"grad_norm": 0.10673736780881882,
|
| 528 |
+
"learning_rate": 0.00022995475930919905,
|
| 529 |
+
"loss": 0.1131,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.27988338192419826,
|
| 534 |
+
"grad_norm": 0.12909558415412903,
|
| 535 |
+
"learning_rate": 0.00022784543606718227,
|
| 536 |
+
"loss": 0.1338,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.28377065111758987,
|
| 541 |
+
"grad_norm": 0.18475858867168427,
|
| 542 |
+
"learning_rate": 0.00022571483066022657,
|
| 543 |
+
"loss": 0.1931,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.28765792031098153,
|
| 548 |
+
"grad_norm": 0.24942803382873535,
|
| 549 |
+
"learning_rate": 0.0002235635255745762,
|
| 550 |
+
"loss": 0.2827,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.2915451895043732,
|
| 555 |
+
"grad_norm": 0.34233248233795166,
|
| 556 |
+
"learning_rate": 0.00022139210895556104,
|
| 557 |
+
"loss": 0.3967,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.2915451895043732,
|
| 562 |
+
"eval_loss": 0.09369731694459915,
|
| 563 |
+
"eval_runtime": 0.7613,
|
| 564 |
+
"eval_samples_per_second": 65.673,
|
| 565 |
+
"eval_steps_per_second": 2.627,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.2954324586977648,
|
| 570 |
+
"grad_norm": 0.0579577200114727,
|
| 571 |
+
"learning_rate": 0.00021920117444680317,
|
| 572 |
+
"loss": 0.0548,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.29931972789115646,
|
| 577 |
+
"grad_norm": 0.05240903049707413,
|
| 578 |
+
"learning_rate": 0.00021699132102792097,
|
| 579 |
+
"loss": 0.0393,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 0.3032069970845481,
|
| 584 |
+
"grad_norm": 0.061587151139974594,
|
| 585 |
+
"learning_rate": 0.0002147631528507739,
|
| 586 |
+
"loss": 0.0334,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.30709426627793973,
|
| 591 |
+
"grad_norm": 0.05840449780225754,
|
| 592 |
+
"learning_rate": 0.00021251727907429355,
|
| 593 |
+
"loss": 0.039,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.3109815354713314,
|
| 598 |
+
"grad_norm": 0.060217294842004776,
|
| 599 |
+
"learning_rate": 0.0002102543136979454,
|
| 600 |
+
"loss": 0.0456,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 0.31486880466472306,
|
| 605 |
+
"grad_norm": 0.08354919403791428,
|
| 606 |
+
"learning_rate": 0.0002079748753938678,
|
| 607 |
+
"loss": 0.067,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.31875607385811466,
|
| 612 |
+
"grad_norm": 0.08509140461683273,
|
| 613 |
+
"learning_rate": 0.0002056795873377331,
|
| 614 |
+
"loss": 0.0761,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.3226433430515063,
|
| 619 |
+
"grad_norm": 0.09227221459150314,
|
| 620 |
+
"learning_rate": 0.00020336907703837748,
|
| 621 |
+
"loss": 0.0854,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.32653061224489793,
|
| 626 |
+
"grad_norm": 0.11894426494836807,
|
| 627 |
+
"learning_rate": 0.00020104397616624645,
|
| 628 |
+
"loss": 0.1199,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.3304178814382896,
|
| 633 |
+
"grad_norm": 0.12877412140369415,
|
| 634 |
+
"learning_rate": 0.00019870492038070252,
|
| 635 |
+
"loss": 0.1401,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 0.33430515063168126,
|
| 640 |
+
"grad_norm": 0.2026694416999817,
|
| 641 |
+
"learning_rate": 0.0001963525491562421,
|
| 642 |
+
"loss": 0.2156,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.33819241982507287,
|
| 647 |
+
"grad_norm": 0.25777146220207214,
|
| 648 |
+
"learning_rate": 0.0001939875056076697,
|
| 649 |
+
"loss": 0.2802,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.34207968901846453,
|
| 654 |
+
"grad_norm": 0.07381570339202881,
|
| 655 |
+
"learning_rate": 0.00019161043631427666,
|
| 656 |
+
"loss": 0.0682,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.3459669582118562,
|
| 661 |
+
"grad_norm": 0.047046344727277756,
|
| 662 |
+
"learning_rate": 0.00018922199114307294,
|
| 663 |
+
"loss": 0.0355,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.3498542274052478,
|
| 668 |
+
"grad_norm": 0.07161912322044373,
|
| 669 |
+
"learning_rate": 0.00018682282307111987,
|
| 670 |
+
"loss": 0.0368,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.35374149659863946,
|
| 675 |
+
"grad_norm": 0.04765067622065544,
|
| 676 |
+
"learning_rate": 0.00018441358800701273,
|
| 677 |
+
"loss": 0.0342,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.3576287657920311,
|
| 682 |
+
"grad_norm": 0.05586829036474228,
|
| 683 |
+
"learning_rate": 0.00018199494461156203,
|
| 684 |
+
"loss": 0.0383,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 0.36151603498542273,
|
| 689 |
+
"grad_norm": 0.05112822353839874,
|
| 690 |
+
"learning_rate": 0.000179567554117722,
|
| 691 |
+
"loss": 0.0457,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.3654033041788144,
|
| 696 |
+
"grad_norm": 0.06726202368736267,
|
| 697 |
+
"learning_rate": 0.00017713208014981648,
|
| 698 |
+
"loss": 0.0575,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.369290573372206,
|
| 703 |
+
"grad_norm": 0.11716607213020325,
|
| 704 |
+
"learning_rate": 0.00017468918854211007,
|
| 705 |
+
"loss": 0.0752,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.37317784256559766,
|
| 710 |
+
"grad_norm": 0.12760676443576813,
|
| 711 |
+
"learning_rate": 0.00017223954715677627,
|
| 712 |
+
"loss": 0.1276,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.3770651117589893,
|
| 717 |
+
"grad_norm": 0.14696328341960907,
|
| 718 |
+
"learning_rate": 0.00016978382570131034,
|
| 719 |
+
"loss": 0.14,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 0.38095238095238093,
|
| 724 |
+
"grad_norm": 0.16512975096702576,
|
| 725 |
+
"learning_rate": 0.00016732269554543794,
|
| 726 |
+
"loss": 0.2012,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 0.3848396501457726,
|
| 731 |
+
"grad_norm": 0.22031673789024353,
|
| 732 |
+
"learning_rate": 0.00016485682953756942,
|
| 733 |
+
"loss": 0.2332,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.38872691933916426,
|
| 738 |
+
"grad_norm": 0.332925021648407,
|
| 739 |
+
"learning_rate": 0.00016238690182084986,
|
| 740 |
+
"loss": 0.394,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.38872691933916426,
|
| 745 |
+
"eval_loss": 0.08561168611049652,
|
| 746 |
+
"eval_runtime": 0.7609,
|
| 747 |
+
"eval_samples_per_second": 65.715,
|
| 748 |
+
"eval_steps_per_second": 2.629,
|
| 749 |
+
"step": 100
|
| 750 |
}
|
| 751 |
],
|
| 752 |
"logging_steps": 1,
|
|
|
|
| 775 |
"attributes": {}
|
| 776 |
}
|
| 777 |
},
|
| 778 |
+
"total_flos": 2.328842228371292e+17,
|
| 779 |
"train_batch_size": 8,
|
| 780 |
"trial_name": null,
|
| 781 |
"trial_params": null
|