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 639691872
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1ae92bc53d4b07e719b3eb8e5693dd6b983be63136caea42f8c47c1e790b1a2
|
| 3 |
size 639691872
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 325339796
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:528008525c786f355c6d5740d46a419a2cca385651026e803928f6a15293f4d3
|
| 3 |
size 325339796
|
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 sha256:5276a53a63eea8b258dd72f4726671cfc19b963448b14f15e1fbaa2ced93922f
|
| 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 sha256:1977c844adb73af0fea2c1f1d9e1e7f3d8acdc9463168c38247b5949c7561fd7
|
| 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 sha256:61bbf69cbcab7d599417ae14b41a7483e039c3cf33fd5fdf1627ffb0df3da8b0
|
| 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:cf9fb37d499d23c4af5151720eacf3b0b1282ca1fc69e46fd1220133dd5a8967
|
| 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 sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
|
| 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": 83.89,
|
| 374 |
"eval_steps_per_second": 5.244,
|
| 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": 0.37990063428878784,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.034126780991382985,
|
| 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": 83.89,
|
| 374 |
"eval_steps_per_second": 5.244,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.017404658305605322,
|
| 379 |
+
"grad_norm": 0.2049894481897354,
|
| 380 |
+
"learning_rate": 8.894386393810563e-05,
|
| 381 |
+
"loss": 0.4993,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.017745926115519152,
|
| 386 |
+
"grad_norm": 0.21354451775550842,
|
| 387 |
+
"learning_rate": 8.842005554284296e-05,
|
| 388 |
+
"loss": 0.5209,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.018087193925432985,
|
| 393 |
+
"grad_norm": 0.24098210036754608,
|
| 394 |
+
"learning_rate": 8.788574348801675e-05,
|
| 395 |
+
"loss": 0.6135,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.018428461735346815,
|
| 400 |
+
"grad_norm": 0.22961851954460144,
|
| 401 |
+
"learning_rate": 8.73410738492077e-05,
|
| 402 |
+
"loss": 0.5341,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.018769729545260645,
|
| 407 |
+
"grad_norm": 0.201799213886261,
|
| 408 |
+
"learning_rate": 8.678619553365659e-05,
|
| 409 |
+
"loss": 0.3546,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.019110997355174474,
|
| 414 |
+
"grad_norm": 0.2120453268289566,
|
| 415 |
+
"learning_rate": 8.622126023955446e-05,
|
| 416 |
+
"loss": 0.318,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.019452265165088304,
|
| 421 |
+
"grad_norm": 0.20748455822467804,
|
| 422 |
+
"learning_rate": 8.564642241456986e-05,
|
| 423 |
+
"loss": 0.319,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.019793532975002134,
|
| 428 |
+
"grad_norm": 0.22522872686386108,
|
| 429 |
+
"learning_rate": 8.506183921362443e-05,
|
| 430 |
+
"loss": 0.3338,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.020134800784915963,
|
| 435 |
+
"grad_norm": 0.20345957577228546,
|
| 436 |
+
"learning_rate": 8.44676704559283e-05,
|
| 437 |
+
"loss": 0.3245,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.020476068594829793,
|
| 442 |
+
"grad_norm": 0.20043089985847473,
|
| 443 |
+
"learning_rate": 8.386407858128706e-05,
|
| 444 |
+
"loss": 0.3109,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.020817336404743623,
|
| 449 |
+
"grad_norm": 0.1963178813457489,
|
| 450 |
+
"learning_rate": 8.32512286056924e-05,
|
| 451 |
+
"loss": 0.333,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.021158604214657453,
|
| 456 |
+
"grad_norm": 0.24082720279693604,
|
| 457 |
+
"learning_rate": 8.262928807620843e-05,
|
| 458 |
+
"loss": 0.3488,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.021499872024571282,
|
| 463 |
+
"grad_norm": 0.21349981427192688,
|
| 464 |
+
"learning_rate": 8.199842702516583e-05,
|
| 465 |
+
"loss": 0.4438,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.021841139834485112,
|
| 470 |
+
"grad_norm": 0.22440080344676971,
|
| 471 |
+
"learning_rate": 8.135881792367686e-05,
|
| 472 |
+
"loss": 0.5258,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.02218240764439894,
|
| 477 |
+
"grad_norm": 0.22355695068836212,
|
| 478 |
+
"learning_rate": 8.07106356344834e-05,
|
| 479 |
+
"loss": 0.5843,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.02252367545431277,
|
| 484 |
+
"grad_norm": 0.24970658123493195,
|
| 485 |
+
"learning_rate": 8.005405736415126e-05,
|
| 486 |
+
"loss": 0.5235,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.0228649432642266,
|
| 491 |
+
"grad_norm": 0.21168158948421478,
|
| 492 |
+
"learning_rate": 7.938926261462366e-05,
|
| 493 |
+
"loss": 0.3448,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.02320621107414043,
|
| 498 |
+
"grad_norm": 0.23335349559783936,
|
| 499 |
+
"learning_rate": 7.871643313414718e-05,
|
| 500 |
+
"loss": 0.3174,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.02354747888405426,
|
| 505 |
+
"grad_norm": 0.23679345846176147,
|
| 506 |
+
"learning_rate": 7.803575286758364e-05,
|
| 507 |
+
"loss": 0.3314,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.02388874669396809,
|
| 512 |
+
"grad_norm": 0.23558004200458527,
|
| 513 |
+
"learning_rate": 7.734740790612136e-05,
|
| 514 |
+
"loss": 0.3422,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.02423001450388192,
|
| 519 |
+
"grad_norm": 0.21740683913230896,
|
| 520 |
+
"learning_rate": 7.66515864363997e-05,
|
| 521 |
+
"loss": 0.2909,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.02457128231379575,
|
| 526 |
+
"grad_norm": 0.22649434208869934,
|
| 527 |
+
"learning_rate": 7.594847868906076e-05,
|
| 528 |
+
"loss": 0.3312,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.024912550123709583,
|
| 533 |
+
"grad_norm": 0.2355552613735199,
|
| 534 |
+
"learning_rate": 7.52382768867422e-05,
|
| 535 |
+
"loss": 0.3424,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.025253817933623413,
|
| 540 |
+
"grad_norm": 0.22028999030590057,
|
| 541 |
+
"learning_rate": 7.452117519152542e-05,
|
| 542 |
+
"loss": 0.3335,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.025595085743537242,
|
| 547 |
+
"grad_norm": 0.26820605993270874,
|
| 548 |
+
"learning_rate": 7.379736965185368e-05,
|
| 549 |
+
"loss": 0.3398,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.025936353553451072,
|
| 554 |
+
"grad_norm": 0.16274772584438324,
|
| 555 |
+
"learning_rate": 7.30670581489344e-05,
|
| 556 |
+
"loss": 0.4729,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.0262776213633649,
|
| 561 |
+
"grad_norm": 0.2291819006204605,
|
| 562 |
+
"learning_rate": 7.233044034264034e-05,
|
| 563 |
+
"loss": 0.5704,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.02661888917327873,
|
| 568 |
+
"grad_norm": 0.24846778810024261,
|
| 569 |
+
"learning_rate": 7.158771761692464e-05,
|
| 570 |
+
"loss": 0.5439,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.02696015698319256,
|
| 575 |
+
"grad_norm": 0.31617650389671326,
|
| 576 |
+
"learning_rate": 7.083909302476453e-05,
|
| 577 |
+
"loss": 0.5253,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.02730142479310639,
|
| 582 |
+
"grad_norm": 0.2205945998430252,
|
| 583 |
+
"learning_rate": 7.008477123264848e-05,
|
| 584 |
+
"loss": 0.3299,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.02764269260302022,
|
| 589 |
+
"grad_norm": 0.20009973645210266,
|
| 590 |
+
"learning_rate": 6.932495846462261e-05,
|
| 591 |
+
"loss": 0.3252,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.02798396041293405,
|
| 596 |
+
"grad_norm": 0.21673430502414703,
|
| 597 |
+
"learning_rate": 6.855986244591104e-05,
|
| 598 |
+
"loss": 0.3123,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.02832522822284788,
|
| 603 |
+
"grad_norm": 0.21185316145420074,
|
| 604 |
+
"learning_rate": 6.778969234612584e-05,
|
| 605 |
+
"loss": 0.3224,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.02866649603276171,
|
| 610 |
+
"grad_norm": 0.23723237216472626,
|
| 611 |
+
"learning_rate": 6.701465872208216e-05,
|
| 612 |
+
"loss": 0.352,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.02900776384267554,
|
| 617 |
+
"grad_norm": 0.2370431125164032,
|
| 618 |
+
"learning_rate": 6.623497346023418e-05,
|
| 619 |
+
"loss": 0.308,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.02934903165258937,
|
| 624 |
+
"grad_norm": 0.2488846629858017,
|
| 625 |
+
"learning_rate": 6.545084971874738e-05,
|
| 626 |
+
"loss": 0.3473,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.0296902994625032,
|
| 631 |
+
"grad_norm": 0.2445327639579773,
|
| 632 |
+
"learning_rate": 6.466250186922325e-05,
|
| 633 |
+
"loss": 0.3578,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.03003156727241703,
|
| 638 |
+
"grad_norm": 0.18646804988384247,
|
| 639 |
+
"learning_rate": 6.387014543809223e-05,
|
| 640 |
+
"loss": 0.4408,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.030372835082330858,
|
| 645 |
+
"grad_norm": 0.21375317871570587,
|
| 646 |
+
"learning_rate": 6.307399704769099e-05,
|
| 647 |
+
"loss": 0.4763,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.030714102892244688,
|
| 652 |
+
"grad_norm": 0.23985172808170319,
|
| 653 |
+
"learning_rate": 6.227427435703997e-05,
|
| 654 |
+
"loss": 0.5524,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.031055370702158518,
|
| 659 |
+
"grad_norm": 0.28279000520706177,
|
| 660 |
+
"learning_rate": 6.147119600233758e-05,
|
| 661 |
+
"loss": 0.5787,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.03139663851207235,
|
| 666 |
+
"grad_norm": 0.2413223385810852,
|
| 667 |
+
"learning_rate": 6.066498153718735e-05,
|
| 668 |
+
"loss": 0.3587,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.03173790632198618,
|
| 673 |
+
"grad_norm": 0.20742368698120117,
|
| 674 |
+
"learning_rate": 5.985585137257401e-05,
|
| 675 |
+
"loss": 0.293,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.03207917413190001,
|
| 680 |
+
"grad_norm": 0.2049570530653,
|
| 681 |
+
"learning_rate": 5.90440267166055e-05,
|
| 682 |
+
"loss": 0.318,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.032420441941813836,
|
| 687 |
+
"grad_norm": 0.24469810724258423,
|
| 688 |
+
"learning_rate": 5.8229729514036705e-05,
|
| 689 |
+
"loss": 0.3157,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.032761709751727666,
|
| 694 |
+
"grad_norm": 0.20401744544506073,
|
| 695 |
+
"learning_rate": 5.74131823855921e-05,
|
| 696 |
+
"loss": 0.3375,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.033102977561641496,
|
| 701 |
+
"grad_norm": 0.22278253734111786,
|
| 702 |
+
"learning_rate": 5.6594608567103456e-05,
|
| 703 |
+
"loss": 0.2931,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.033444245371555326,
|
| 708 |
+
"grad_norm": 0.2358473837375641,
|
| 709 |
+
"learning_rate": 5.577423184847932e-05,
|
| 710 |
+
"loss": 0.2938,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.033785513181469155,
|
| 715 |
+
"grad_norm": 0.24663186073303223,
|
| 716 |
+
"learning_rate": 5.495227651252315e-05,
|
| 717 |
+
"loss": 0.3375,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.034126780991382985,
|
| 722 |
+
"grad_norm": 0.26277956366539,
|
| 723 |
+
"learning_rate": 5.4128967273616625e-05,
|
| 724 |
+
"loss": 0.3735,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.034126780991382985,
|
| 729 |
+
"eval_loss": 0.37990063428878784,
|
| 730 |
+
"eval_runtime": 234.965,
|
| 731 |
+
"eval_samples_per_second": 84.012,
|
| 732 |
+
"eval_steps_per_second": 5.252,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 7.251201977776865e+17,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|