Training in progress, step 100, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 50624
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff33f992fb27383e85fe93b11989f3c7636456acf6498e5ef658e1718aeb9331
|
| 3 |
size 50624
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 118090
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e2c29918aef0f6daf84b8a52c47ed39176c229d030db14ddebdea59bfbce04f
|
| 3 |
size 118090
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32c0575a4e86cdb910863db98f1f30ff2a9c0a1f845a4da4f00ef74648322528
|
| 3 |
size 14244
|
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:f2c4a11c3ec7ace2e963dc6e2b0b5b6372cc0250cefb36d5f7289475908638cb
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 10.
|
| 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": 491.624,
|
| 374 |
"eval_steps_per_second": 123.017,
|
| 375 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
}
|
| 377 |
],
|
| 378 |
"logging_steps": 1,
|
|
@@ -396,12 +754,12 @@
|
|
| 396 |
"should_evaluate": false,
|
| 397 |
"should_log": false,
|
| 398 |
"should_save": true,
|
| 399 |
-
"should_training_stop":
|
| 400 |
},
|
| 401 |
"attributes": {}
|
| 402 |
}
|
| 403 |
},
|
| 404 |
-
"total_flos":
|
| 405 |
"train_batch_size": 4,
|
| 406 |
"trial_name": null,
|
| 407 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 10.342756271362305,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.07594456047085628,
|
| 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": 491.624,
|
| 374 |
"eval_steps_per_second": 123.017,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.0387317258401367,
|
| 379 |
+
"grad_norm": 0.1932212859392166,
|
| 380 |
+
"learning_rate": 2.847932752400164e-06,
|
| 381 |
+
"loss": 10.3335,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.03949117144484526,
|
| 386 |
+
"grad_norm": 0.20674271881580353,
|
| 387 |
+
"learning_rate": 2.761321158169134e-06,
|
| 388 |
+
"loss": 10.3403,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.04025061704955383,
|
| 393 |
+
"grad_norm": 0.16978555917739868,
|
| 394 |
+
"learning_rate": 2.6743911843603134e-06,
|
| 395 |
+
"loss": 10.3549,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.04101006265426239,
|
| 400 |
+
"grad_norm": 0.2252632975578308,
|
| 401 |
+
"learning_rate": 2.587248741756253e-06,
|
| 402 |
+
"loss": 10.3375,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.04176950825897095,
|
| 407 |
+
"grad_norm": 0.21015048027038574,
|
| 408 |
+
"learning_rate": 2.5e-06,
|
| 409 |
+
"loss": 10.3468,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.04252895386367951,
|
| 414 |
+
"grad_norm": 0.19843299686908722,
|
| 415 |
+
"learning_rate": 2.4127512582437486e-06,
|
| 416 |
+
"loss": 10.3563,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.04328839946838808,
|
| 421 |
+
"grad_norm": 0.20154882967472076,
|
| 422 |
+
"learning_rate": 2.325608815639687e-06,
|
| 423 |
+
"loss": 10.3559,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.04404784507309664,
|
| 428 |
+
"grad_norm": 0.2109687328338623,
|
| 429 |
+
"learning_rate": 2.238678841830867e-06,
|
| 430 |
+
"loss": 10.3398,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.0448072906778052,
|
| 435 |
+
"grad_norm": 0.2115778774023056,
|
| 436 |
+
"learning_rate": 2.1520672475998374e-06,
|
| 437 |
+
"loss": 10.3424,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.045566736282513766,
|
| 442 |
+
"grad_norm": 0.23688730597496033,
|
| 443 |
+
"learning_rate": 2.0658795558326745e-06,
|
| 444 |
+
"loss": 10.3374,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.046326181887222324,
|
| 449 |
+
"grad_norm": 0.20714813470840454,
|
| 450 |
+
"learning_rate": 1.9802207729556023e-06,
|
| 451 |
+
"loss": 10.3575,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.04708562749193089,
|
| 456 |
+
"grad_norm": 0.2432180792093277,
|
| 457 |
+
"learning_rate": 1.895195261000831e-06,
|
| 458 |
+
"loss": 10.3398,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.047845073096639455,
|
| 463 |
+
"grad_norm": 0.19799984991550446,
|
| 464 |
+
"learning_rate": 1.8109066104575023e-06,
|
| 465 |
+
"loss": 10.353,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.048604518701348014,
|
| 470 |
+
"grad_norm": 0.20568235218524933,
|
| 471 |
+
"learning_rate": 1.7274575140626318e-06,
|
| 472 |
+
"loss": 10.3497,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.04936396430605658,
|
| 477 |
+
"grad_norm": 0.20056724548339844,
|
| 478 |
+
"learning_rate": 1.6449496416858285e-06,
|
| 479 |
+
"loss": 10.3471,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.050123409910765145,
|
| 484 |
+
"grad_norm": 0.18637068569660187,
|
| 485 |
+
"learning_rate": 1.56348351646022e-06,
|
| 486 |
+
"loss": 10.3384,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.0508828555154737,
|
| 491 |
+
"grad_norm": 0.22628478705883026,
|
| 492 |
+
"learning_rate": 1.4831583923105e-06,
|
| 493 |
+
"loss": 10.3308,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.05164230112018227,
|
| 498 |
+
"grad_norm": 0.2501058578491211,
|
| 499 |
+
"learning_rate": 1.4040721330273063e-06,
|
| 500 |
+
"loss": 10.341,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.05240174672489083,
|
| 505 |
+
"grad_norm": 0.22660444676876068,
|
| 506 |
+
"learning_rate": 1.3263210930352737e-06,
|
| 507 |
+
"loss": 10.3273,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.05316119232959939,
|
| 512 |
+
"grad_norm": 0.20599226653575897,
|
| 513 |
+
"learning_rate": 1.2500000000000007e-06,
|
| 514 |
+
"loss": 10.3412,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.05392063793430796,
|
| 519 |
+
"grad_norm": 0.21871422231197357,
|
| 520 |
+
"learning_rate": 1.1752018394169882e-06,
|
| 521 |
+
"loss": 10.3326,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.054680083539016516,
|
| 526 |
+
"grad_norm": 0.237649068236351,
|
| 527 |
+
"learning_rate": 1.1020177413231334e-06,
|
| 528 |
+
"loss": 10.348,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.05543952914372508,
|
| 533 |
+
"grad_norm": 0.23702602088451385,
|
| 534 |
+
"learning_rate": 1.0305368692688175e-06,
|
| 535 |
+
"loss": 10.3462,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.05619897474843364,
|
| 540 |
+
"grad_norm": 0.22213907539844513,
|
| 541 |
+
"learning_rate": 9.608463116858544e-07,
|
| 542 |
+
"loss": 10.3396,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.056958420353142206,
|
| 547 |
+
"grad_norm": 0.2493429332971573,
|
| 548 |
+
"learning_rate": 8.930309757836517e-07,
|
| 549 |
+
"loss": 10.3436,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.05771786595785077,
|
| 554 |
+
"grad_norm": 0.21368595957756042,
|
| 555 |
+
"learning_rate": 8.271734841028553e-07,
|
| 556 |
+
"loss": 10.3512,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.05847731156255933,
|
| 561 |
+
"grad_norm": 0.2322058379650116,
|
| 562 |
+
"learning_rate": 7.633540738525066e-07,
|
| 563 |
+
"loss": 10.3496,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.059236757167267895,
|
| 568 |
+
"grad_norm": 0.23094195127487183,
|
| 569 |
+
"learning_rate": 7.016504991533727e-07,
|
| 570 |
+
"loss": 10.3491,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.05999620277197646,
|
| 575 |
+
"grad_norm": 0.261568158864975,
|
| 576 |
+
"learning_rate": 6.421379363065142e-07,
|
| 577 |
+
"loss": 10.3489,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.06075564837668502,
|
| 582 |
+
"grad_norm": 0.23905989527702332,
|
| 583 |
+
"learning_rate": 5.848888922025553e-07,
|
| 584 |
+
"loss": 10.3485,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.061515093981393584,
|
| 589 |
+
"grad_norm": 0.2564074695110321,
|
| 590 |
+
"learning_rate": 5.299731159831953e-07,
|
| 591 |
+
"loss": 10.3419,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.06227453958610214,
|
| 596 |
+
"grad_norm": 0.24325355887413025,
|
| 597 |
+
"learning_rate": 4.774575140626317e-07,
|
| 598 |
+
"loss": 10.3518,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.0630339851908107,
|
| 603 |
+
"grad_norm": 0.21921157836914062,
|
| 604 |
+
"learning_rate": 4.27406068612396e-07,
|
| 605 |
+
"loss": 10.3405,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.06379343079551927,
|
| 610 |
+
"grad_norm": 0.21654434502124786,
|
| 611 |
+
"learning_rate": 3.798797596089351e-07,
|
| 612 |
+
"loss": 10.3553,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.06455287640022783,
|
| 617 |
+
"grad_norm": 0.2687203586101532,
|
| 618 |
+
"learning_rate": 3.3493649053890325e-07,
|
| 619 |
+
"loss": 10.3464,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.06531232200493639,
|
| 624 |
+
"grad_norm": 0.21483434736728668,
|
| 625 |
+
"learning_rate": 2.9263101785268253e-07,
|
| 626 |
+
"loss": 10.3408,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.06607176760964496,
|
| 631 |
+
"grad_norm": 0.21876099705696106,
|
| 632 |
+
"learning_rate": 2.53014884252083e-07,
|
| 633 |
+
"loss": 10.3406,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.06683121321435352,
|
| 638 |
+
"grad_norm": 0.22782814502716064,
|
| 639 |
+
"learning_rate": 2.1613635589349756e-07,
|
| 640 |
+
"loss": 10.3377,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.06759065881906208,
|
| 645 |
+
"grad_norm": 0.3331179618835449,
|
| 646 |
+
"learning_rate": 1.8204036358303173e-07,
|
| 647 |
+
"loss": 10.3426,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.06835010442377065,
|
| 652 |
+
"grad_norm": 0.24991817772388458,
|
| 653 |
+
"learning_rate": 1.507684480352292e-07,
|
| 654 |
+
"loss": 10.3352,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.06910955002847921,
|
| 659 |
+
"grad_norm": 0.2640218734741211,
|
| 660 |
+
"learning_rate": 1.223587092621162e-07,
|
| 661 |
+
"loss": 10.3305,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.06986899563318777,
|
| 666 |
+
"grad_norm": 0.2834155559539795,
|
| 667 |
+
"learning_rate": 9.684576015420277e-08,
|
| 668 |
+
"loss": 10.3433,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.07062844123789634,
|
| 673 |
+
"grad_norm": 0.283803790807724,
|
| 674 |
+
"learning_rate": 7.426068431000883e-08,
|
| 675 |
+
"loss": 10.3395,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.0713878868426049,
|
| 680 |
+
"grad_norm": 0.2507743239402771,
|
| 681 |
+
"learning_rate": 5.463099816548578e-08,
|
| 682 |
+
"loss": 10.3413,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.07214733244731346,
|
| 687 |
+
"grad_norm": 0.2620439827442169,
|
| 688 |
+
"learning_rate": 3.798061746947995e-08,
|
| 689 |
+
"loss": 10.3463,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.07290677805202202,
|
| 694 |
+
"grad_norm": 0.2948286235332489,
|
| 695 |
+
"learning_rate": 2.4329828146074096e-08,
|
| 696 |
+
"loss": 10.3418,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.07366622365673059,
|
| 701 |
+
"grad_norm": 0.3654595613479614,
|
| 702 |
+
"learning_rate": 1.3695261579316776e-08,
|
| 703 |
+
"loss": 10.3411,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.07442566926143915,
|
| 708 |
+
"grad_norm": 0.3371923863887787,
|
| 709 |
+
"learning_rate": 6.089874350439507e-09,
|
| 710 |
+
"loss": 10.3374,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.0751851148661477,
|
| 715 |
+
"grad_norm": 0.3659217357635498,
|
| 716 |
+
"learning_rate": 1.5229324522605949e-09,
|
| 717 |
+
"loss": 10.3461,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.07594456047085628,
|
| 722 |
+
"grad_norm": 0.2947441041469574,
|
| 723 |
+
"learning_rate": 0.0,
|
| 724 |
+
"loss": 10.3475,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.07594456047085628,
|
| 729 |
+
"eval_loss": 10.342756271362305,
|
| 730 |
+
"eval_runtime": 4.5134,
|
| 731 |
+
"eval_samples_per_second": 491.43,
|
| 732 |
+
"eval_steps_per_second": 122.968,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 754 |
"should_evaluate": false,
|
| 755 |
"should_log": false,
|
| 756 |
"should_save": true,
|
| 757 |
+
"should_training_stop": true
|
| 758 |
},
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 10473564930048.0,
|
| 763 |
"train_batch_size": 4,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|