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 sha256:4b271712254e01f3a756f80c9d91649a68f589f8083c68e28efa6bf81649af5f
|
| 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 sha256:4d70e0c506c43b6dd7bfc52aa23ed7049ddf97443e93d45fefb733a105c2b0c8
|
| 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:c4fea74c51f4405caaaae971a4ccfc94a699f62e8257c2d08259a26bff3fc4eb
|
| 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 sha256:8287c8e13a42f467f666595aef17b0751f60576eb55d01ba59d28223687d2973
|
| 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:b840cecfb7dec70c76a70327d64f5f23b2d66b0b6a1f665ecb2134abed6ccdbb
|
| 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 sha256:841574a58757d90b95116e1fd5d2951f131533acbad72a77bcd1a82810ab44b9
|
| 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 sha256:1b421b30093a741efda571bdeb6770d480a0573a9ee33dd469ec29cc944e02e2
|
| 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": 178.69,
|
| 382 |
"eval_steps_per_second": 46.46,
|
| 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": 1.9786142110824585,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 1.3034623217922607,
|
| 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": 178.69,
|
| 382 |
"eval_steps_per_second": 46.46,
|
| 383 |
"step": 50
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.664765784114053,
|
| 387 |
+
"grad_norm": 1.1472358703613281,
|
| 388 |
+
"learning_rate": 0.00023970785914785144,
|
| 389 |
+
"loss": 2.2791,
|
| 390 |
+
"step": 51
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.6778004073319756,
|
| 394 |
+
"grad_norm": 1.3499984741210938,
|
| 395 |
+
"learning_rate": 0.00023733661732216452,
|
| 396 |
+
"loss": 2.3292,
|
| 397 |
+
"step": 52
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 0.6908350305498981,
|
| 401 |
+
"grad_norm": 1.2178796529769897,
|
| 402 |
+
"learning_rate": 0.00023493364626537257,
|
| 403 |
+
"loss": 2.2938,
|
| 404 |
+
"step": 53
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.7038696537678207,
|
| 408 |
+
"grad_norm": 0.9463868737220764,
|
| 409 |
+
"learning_rate": 0.00023249999999999999,
|
| 410 |
+
"loss": 2.2173,
|
| 411 |
+
"step": 54
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.7169042769857433,
|
| 415 |
+
"grad_norm": 0.5750055909156799,
|
| 416 |
+
"learning_rate": 0.00023003674600373153,
|
| 417 |
+
"loss": 2.2036,
|
| 418 |
+
"step": 55
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.729938900203666,
|
| 422 |
+
"grad_norm": 0.3371862769126892,
|
| 423 |
+
"learning_rate": 0.00022754496474118133,
|
| 424 |
+
"loss": 2.167,
|
| 425 |
+
"step": 56
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.7429735234215886,
|
| 429 |
+
"grad_norm": 0.6258431673049927,
|
| 430 |
+
"learning_rate": 0.00022502574918996517,
|
| 431 |
+
"loss": 2.2211,
|
| 432 |
+
"step": 57
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.7560081466395112,
|
| 436 |
+
"grad_norm": 0.7280526161193848,
|
| 437 |
+
"learning_rate": 0.00022248020436128478,
|
| 438 |
+
"loss": 2.2122,
|
| 439 |
+
"step": 58
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.7690427698574338,
|
| 443 |
+
"grad_norm": 0.8275133371353149,
|
| 444 |
+
"learning_rate": 0.00021990944681523302,
|
| 445 |
+
"loss": 2.2137,
|
| 446 |
+
"step": 59
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.7820773930753564,
|
| 450 |
+
"grad_norm": 0.8840050101280212,
|
| 451 |
+
"learning_rate": 0.0002173146041710339,
|
| 452 |
+
"loss": 2.2311,
|
| 453 |
+
"step": 60
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.795112016293279,
|
| 457 |
+
"grad_norm": 0.957916796207428,
|
| 458 |
+
"learning_rate": 0.00021469681461243153,
|
| 459 |
+
"loss": 2.2478,
|
| 460 |
+
"step": 61
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.8081466395112016,
|
| 464 |
+
"grad_norm": 1.0393691062927246,
|
| 465 |
+
"learning_rate": 0.00021205722638844505,
|
| 466 |
+
"loss": 2.2579,
|
| 467 |
+
"step": 62
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.8211812627291243,
|
| 471 |
+
"grad_norm": 0.3389835059642792,
|
| 472 |
+
"learning_rate": 0.00020939699730970873,
|
| 473 |
+
"loss": 2.1799,
|
| 474 |
+
"step": 63
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.8342158859470469,
|
| 478 |
+
"grad_norm": 0.5756048560142517,
|
| 479 |
+
"learning_rate": 0.00020671729424061788,
|
| 480 |
+
"loss": 2.1684,
|
| 481 |
+
"step": 64
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 0.8472505091649695,
|
| 485 |
+
"grad_norm": 0.7830222249031067,
|
| 486 |
+
"learning_rate": 0.00020401929258750365,
|
| 487 |
+
"loss": 2.1438,
|
| 488 |
+
"step": 65
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.8602851323828921,
|
| 492 |
+
"grad_norm": 0.8117411732673645,
|
| 493 |
+
"learning_rate": 0.00020130417578306082,
|
| 494 |
+
"loss": 2.1536,
|
| 495 |
+
"step": 66
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.8733197556008147,
|
| 499 |
+
"grad_norm": 0.7848119735717773,
|
| 500 |
+
"learning_rate": 0.0001985731347672554,
|
| 501 |
+
"loss": 2.129,
|
| 502 |
+
"step": 67
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.8863543788187372,
|
| 506 |
+
"grad_norm": 0.6703603863716125,
|
| 507 |
+
"learning_rate": 0.00019582736746493853,
|
| 508 |
+
"loss": 2.152,
|
| 509 |
+
"step": 68
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.8993890020366598,
|
| 513 |
+
"grad_norm": 0.4845719635486603,
|
| 514 |
+
"learning_rate": 0.00019306807826039747,
|
| 515 |
+
"loss": 2.1237,
|
| 516 |
+
"step": 69
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.9124236252545825,
|
| 520 |
+
"grad_norm": 0.3355918228626251,
|
| 521 |
+
"learning_rate": 0.00019029647746907283,
|
| 522 |
+
"loss": 2.0711,
|
| 523 |
+
"step": 70
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 0.9254582484725051,
|
| 527 |
+
"grad_norm": 0.33707523345947266,
|
| 528 |
+
"learning_rate": 0.00018751378080667378,
|
| 529 |
+
"loss": 2.1033,
|
| 530 |
+
"step": 71
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.9384928716904277,
|
| 534 |
+
"grad_norm": 0.5474686622619629,
|
| 535 |
+
"learning_rate": 0.00018472120885592555,
|
| 536 |
+
"loss": 2.0707,
|
| 537 |
+
"step": 72
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.9515274949083503,
|
| 541 |
+
"grad_norm": 0.71000075340271,
|
| 542 |
+
"learning_rate": 0.00018191998653118108,
|
| 543 |
+
"loss": 2.1169,
|
| 544 |
+
"step": 73
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.9645621181262729,
|
| 548 |
+
"grad_norm": 0.8560431003570557,
|
| 549 |
+
"learning_rate": 0.0001791113425411332,
|
| 550 |
+
"loss": 2.176,
|
| 551 |
+
"step": 74
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.9775967413441955,
|
| 555 |
+
"grad_norm": 1.2276349067687988,
|
| 556 |
+
"learning_rate": 0.0001762965088498626,
|
| 557 |
+
"loss": 2.2966,
|
| 558 |
+
"step": 75
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.9775967413441955,
|
| 562 |
+
"eval_loss": 2.044175148010254,
|
| 563 |
+
"eval_runtime": 0.2806,
|
| 564 |
+
"eval_samples_per_second": 178.197,
|
| 565 |
+
"eval_steps_per_second": 46.331,
|
| 566 |
+
"step": 75
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 0.9906313645621181,
|
| 570 |
+
"grad_norm": 0.28324252367019653,
|
| 571 |
+
"learning_rate": 0.0001734767201364573,
|
| 572 |
+
"loss": 2.0594,
|
| 573 |
+
"step": 76
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.0036659877800407,
|
| 577 |
+
"grad_norm": 0.4252139627933502,
|
| 578 |
+
"learning_rate": 0.00017065321325344194,
|
| 579 |
+
"loss": 2.9023,
|
| 580 |
+
"step": 77
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.0167006109979633,
|
| 584 |
+
"grad_norm": 0.532595157623291,
|
| 585 |
+
"learning_rate": 0.00016782722668425316,
|
| 586 |
+
"loss": 1.9476,
|
| 587 |
+
"step": 78
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 1.0297352342158859,
|
| 591 |
+
"grad_norm": 0.696269690990448,
|
| 592 |
+
"learning_rate": 0.000165,
|
| 593 |
+
"loss": 2.089,
|
| 594 |
+
"step": 79
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.0427698574338085,
|
| 598 |
+
"grad_norm": 0.6571292281150818,
|
| 599 |
+
"learning_rate": 0.00016217277331574678,
|
| 600 |
+
"loss": 2.0514,
|
| 601 |
+
"step": 80
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 1.055804480651731,
|
| 605 |
+
"grad_norm": 0.5735260248184204,
|
| 606 |
+
"learning_rate": 0.00015934678674655805,
|
| 607 |
+
"loss": 2.0645,
|
| 608 |
+
"step": 81
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.0688391038696539,
|
| 612 |
+
"grad_norm": 0.418550968170166,
|
| 613 |
+
"learning_rate": 0.0001565232798635427,
|
| 614 |
+
"loss": 2.0639,
|
| 615 |
+
"step": 82
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.0818737270875765,
|
| 619 |
+
"grad_norm": 0.32165512442588806,
|
| 620 |
+
"learning_rate": 0.00015370349115013742,
|
| 621 |
+
"loss": 2.0412,
|
| 622 |
+
"step": 83
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.094908350305499,
|
| 626 |
+
"grad_norm": 0.3411344289779663,
|
| 627 |
+
"learning_rate": 0.0001508886574588668,
|
| 628 |
+
"loss": 2.0738,
|
| 629 |
+
"step": 84
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.1079429735234216,
|
| 633 |
+
"grad_norm": 0.4526989459991455,
|
| 634 |
+
"learning_rate": 0.0001480800134688189,
|
| 635 |
+
"loss": 2.0482,
|
| 636 |
+
"step": 85
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.1209775967413442,
|
| 640 |
+
"grad_norm": 0.5264050960540771,
|
| 641 |
+
"learning_rate": 0.00014527879114407445,
|
| 642 |
+
"loss": 2.0155,
|
| 643 |
+
"step": 86
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 1.1340122199592668,
|
| 647 |
+
"grad_norm": 0.6333541870117188,
|
| 648 |
+
"learning_rate": 0.0001424862191933262,
|
| 649 |
+
"loss": 2.029,
|
| 650 |
+
"step": 87
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 1.1470468431771894,
|
| 654 |
+
"grad_norm": 0.6475998759269714,
|
| 655 |
+
"learning_rate": 0.00013970352253092714,
|
| 656 |
+
"loss": 2.0732,
|
| 657 |
+
"step": 88
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.160081466395112,
|
| 661 |
+
"grad_norm": 0.5682183504104614,
|
| 662 |
+
"learning_rate": 0.00013693192173960253,
|
| 663 |
+
"loss": 1.6717,
|
| 664 |
+
"step": 89
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.1731160896130346,
|
| 668 |
+
"grad_norm": 0.48593777418136597,
|
| 669 |
+
"learning_rate": 0.00013417263253506147,
|
| 670 |
+
"loss": 2.5498,
|
| 671 |
+
"step": 90
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 1.1861507128309572,
|
| 675 |
+
"grad_norm": 0.517917811870575,
|
| 676 |
+
"learning_rate": 0.00013142686523274463,
|
| 677 |
+
"loss": 2.0097,
|
| 678 |
+
"step": 91
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.1991853360488798,
|
| 682 |
+
"grad_norm": 0.5828862190246582,
|
| 683 |
+
"learning_rate": 0.00012869582421693912,
|
| 684 |
+
"loss": 1.9987,
|
| 685 |
+
"step": 92
|
| 686 |
+
},
|
| 687 |
+
{
|
| 688 |
+
"epoch": 1.2122199592668024,
|
| 689 |
+
"grad_norm": 0.5273678302764893,
|
| 690 |
+
"learning_rate": 0.00012598070741249632,
|
| 691 |
+
"loss": 2.0205,
|
| 692 |
+
"step": 93
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 1.225254582484725,
|
| 696 |
+
"grad_norm": 0.49020346999168396,
|
| 697 |
+
"learning_rate": 0.00012328270575938212,
|
| 698 |
+
"loss": 1.9981,
|
| 699 |
+
"step": 94
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 1.2382892057026478,
|
| 703 |
+
"grad_norm": 0.35303086042404175,
|
| 704 |
+
"learning_rate": 0.00012060300269029128,
|
| 705 |
+
"loss": 1.9699,
|
| 706 |
+
"step": 95
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.2513238289205701,
|
| 710 |
+
"grad_norm": 0.27531367540359497,
|
| 711 |
+
"learning_rate": 0.00011794277361155495,
|
| 712 |
+
"loss": 2.0035,
|
| 713 |
+
"step": 96
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 1.264358452138493,
|
| 717 |
+
"grad_norm": 0.31903597712516785,
|
| 718 |
+
"learning_rate": 0.00011530318538756846,
|
| 719 |
+
"loss": 1.9783,
|
| 720 |
+
"step": 97
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.2773930753564156,
|
| 724 |
+
"grad_norm": 0.43081673979759216,
|
| 725 |
+
"learning_rate": 0.0001126853958289661,
|
| 726 |
+
"loss": 2.0053,
|
| 727 |
+
"step": 98
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 1.2904276985743381,
|
| 731 |
+
"grad_norm": 0.5114902257919312,
|
| 732 |
+
"learning_rate": 0.00011009055318476698,
|
| 733 |
+
"loss": 2.0032,
|
| 734 |
+
"step": 99
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 1.3034623217922607,
|
| 738 |
+
"grad_norm": 0.6454872488975525,
|
| 739 |
+
"learning_rate": 0.00010751979563871518,
|
| 740 |
+
"loss": 2.0436,
|
| 741 |
+
"step": 100
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.3034623217922607,
|
| 745 |
+
"eval_loss": 1.9786142110824585,
|
| 746 |
+
"eval_runtime": 0.2787,
|
| 747 |
+
"eval_samples_per_second": 179.386,
|
| 748 |
+
"eval_steps_per_second": 46.64,
|
| 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
|