Training in progress, step 100, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/global_step100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +1 -1
- last-checkpoint/global_step100/mp_rank_00_model_states.pt +2 -2
- last-checkpoint/latest +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/trainer_state.json +353 -3
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 42002584
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:007489c2aaad6597419109d7b913f6e1ea35e21bf22614272d4344f882f3264b
|
| 3 |
size 42002584
|
last-checkpoint/global_step100/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 251710672
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a810d4ffdf7384fc2e4178085ff96e240cfdac14eab075b43ab33e66a5d82ec
|
| 3 |
size 251710672
|
last-checkpoint/global_step100/mp_rank_00_model_states.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bc784b5e36ac71872cd69f7c28faae1e204fe69f3386e1391613fce2808ff224
|
| 3 |
+
size 153726649
|
last-checkpoint/latest
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
|
|
|
|
| 1 |
+
global_step100
|
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 sha256:6083b63ed272d04027047a9757474c4ad6a6a0c32cfe99d060023e5a6ec919c9
|
| 3 |
size 14244
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 1000,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -357,6 +357,356 @@
|
|
| 357 |
"learning_rate": 0.00010833333333333333,
|
| 358 |
"loss": 1.843,
|
| 359 |
"step": 50
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 360 |
}
|
| 361 |
],
|
| 362 |
"logging_steps": 1,
|
|
@@ -376,7 +726,7 @@
|
|
| 376 |
"attributes": {}
|
| 377 |
}
|
| 378 |
},
|
| 379 |
-
"total_flos":
|
| 380 |
"train_batch_size": 2,
|
| 381 |
"trial_name": null,
|
| 382 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.6116207951070336,
|
| 5 |
"eval_steps": 1000,
|
| 6 |
+
"global_step": 100,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 357 |
"learning_rate": 0.00010833333333333333,
|
| 358 |
"loss": 1.843,
|
| 359 |
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.3119266055045872,
|
| 363 |
+
"grad_norm": 6.078310966491699,
|
| 364 |
+
"learning_rate": 0.00010625000000000001,
|
| 365 |
+
"loss": 2.6343,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.3180428134556575,
|
| 370 |
+
"grad_norm": 4.997678279876709,
|
| 371 |
+
"learning_rate": 0.00010416666666666667,
|
| 372 |
+
"loss": 1.3599,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.3241590214067278,
|
| 377 |
+
"grad_norm": 3.9184954166412354,
|
| 378 |
+
"learning_rate": 0.00010208333333333333,
|
| 379 |
+
"loss": 1.1759,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.3302752293577982,
|
| 384 |
+
"grad_norm": 2.9978091716766357,
|
| 385 |
+
"learning_rate": 0.0001,
|
| 386 |
+
"loss": 1.1444,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.3363914373088685,
|
| 391 |
+
"grad_norm": 3.656428337097168,
|
| 392 |
+
"learning_rate": 9.791666666666667e-05,
|
| 393 |
+
"loss": 1.6992,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.3425076452599388,
|
| 398 |
+
"grad_norm": 4.245843410491943,
|
| 399 |
+
"learning_rate": 9.583333333333334e-05,
|
| 400 |
+
"loss": 1.3147,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.3486238532110092,
|
| 405 |
+
"grad_norm": 3.5236010551452637,
|
| 406 |
+
"learning_rate": 9.375e-05,
|
| 407 |
+
"loss": 1.4529,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.3547400611620795,
|
| 412 |
+
"grad_norm": 5.085486888885498,
|
| 413 |
+
"learning_rate": 9.166666666666667e-05,
|
| 414 |
+
"loss": 1.4496,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.36085626911314983,
|
| 419 |
+
"grad_norm": 3.34416127204895,
|
| 420 |
+
"learning_rate": 8.958333333333335e-05,
|
| 421 |
+
"loss": 1.5209,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.3669724770642202,
|
| 426 |
+
"grad_norm": 3.9783742427825928,
|
| 427 |
+
"learning_rate": 8.75e-05,
|
| 428 |
+
"loss": 1.6401,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.3730886850152905,
|
| 433 |
+
"grad_norm": 4.964531898498535,
|
| 434 |
+
"learning_rate": 8.541666666666666e-05,
|
| 435 |
+
"loss": 1.7851,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.37920489296636084,
|
| 440 |
+
"grad_norm": 4.7241997718811035,
|
| 441 |
+
"learning_rate": 8.333333333333334e-05,
|
| 442 |
+
"loss": 2.2016,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.3853211009174312,
|
| 447 |
+
"grad_norm": 5.319520950317383,
|
| 448 |
+
"learning_rate": 8.125000000000001e-05,
|
| 449 |
+
"loss": 2.3873,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.39143730886850153,
|
| 454 |
+
"grad_norm": 8.982603073120117,
|
| 455 |
+
"learning_rate": 7.916666666666666e-05,
|
| 456 |
+
"loss": 2.6303,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.39755351681957185,
|
| 461 |
+
"grad_norm": 1.1205874681472778,
|
| 462 |
+
"learning_rate": 7.708333333333334e-05,
|
| 463 |
+
"loss": 0.1282,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.4036697247706422,
|
| 468 |
+
"grad_norm": 3.1795151233673096,
|
| 469 |
+
"learning_rate": 7.500000000000001e-05,
|
| 470 |
+
"loss": 1.2387,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.40978593272171254,
|
| 475 |
+
"grad_norm": 6.89016056060791,
|
| 476 |
+
"learning_rate": 7.291666666666667e-05,
|
| 477 |
+
"loss": 2.3982,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.41590214067278286,
|
| 482 |
+
"grad_norm": 5.013582706451416,
|
| 483 |
+
"learning_rate": 7.083333333333334e-05,
|
| 484 |
+
"loss": 2.0834,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.42201834862385323,
|
| 489 |
+
"grad_norm": 4.096442222595215,
|
| 490 |
+
"learning_rate": 6.875e-05,
|
| 491 |
+
"loss": 1.6025,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.42813455657492355,
|
| 496 |
+
"grad_norm": 4.867453098297119,
|
| 497 |
+
"learning_rate": 6.666666666666667e-05,
|
| 498 |
+
"loss": 1.7167,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.43425076452599387,
|
| 503 |
+
"grad_norm": 3.749317169189453,
|
| 504 |
+
"learning_rate": 6.458333333333334e-05,
|
| 505 |
+
"loss": 1.1032,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.44036697247706424,
|
| 510 |
+
"grad_norm": 5.7217535972595215,
|
| 511 |
+
"learning_rate": 6.25e-05,
|
| 512 |
+
"loss": 2.2715,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.44648318042813456,
|
| 517 |
+
"grad_norm": 3.721311330795288,
|
| 518 |
+
"learning_rate": 6.041666666666667e-05,
|
| 519 |
+
"loss": 1.8696,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.4525993883792049,
|
| 524 |
+
"grad_norm": 5.838470935821533,
|
| 525 |
+
"learning_rate": 5.833333333333334e-05,
|
| 526 |
+
"loss": 2.6274,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.45871559633027525,
|
| 531 |
+
"grad_norm": 2.226341724395752,
|
| 532 |
+
"learning_rate": 5.6250000000000005e-05,
|
| 533 |
+
"loss": 0.6009,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.4648318042813456,
|
| 538 |
+
"grad_norm": 2.5226593017578125,
|
| 539 |
+
"learning_rate": 5.4166666666666664e-05,
|
| 540 |
+
"loss": 0.2884,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.4709480122324159,
|
| 545 |
+
"grad_norm": 4.07631778717041,
|
| 546 |
+
"learning_rate": 5.208333333333334e-05,
|
| 547 |
+
"loss": 2.2146,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.47706422018348627,
|
| 552 |
+
"grad_norm": 5.328915119171143,
|
| 553 |
+
"learning_rate": 5e-05,
|
| 554 |
+
"loss": 2.5741,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.4831804281345566,
|
| 559 |
+
"grad_norm": 4.454275131225586,
|
| 560 |
+
"learning_rate": 4.791666666666667e-05,
|
| 561 |
+
"loss": 2.5801,
|
| 562 |
+
"step": 79
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.4892966360856269,
|
| 566 |
+
"grad_norm": 4.834322929382324,
|
| 567 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 568 |
+
"loss": 2.4515,
|
| 569 |
+
"step": 80
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.4954128440366973,
|
| 573 |
+
"grad_norm": 4.437044143676758,
|
| 574 |
+
"learning_rate": 4.375e-05,
|
| 575 |
+
"loss": 1.9943,
|
| 576 |
+
"step": 81
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.5015290519877675,
|
| 580 |
+
"grad_norm": 4.516618728637695,
|
| 581 |
+
"learning_rate": 4.166666666666667e-05,
|
| 582 |
+
"loss": 2.3656,
|
| 583 |
+
"step": 82
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.5076452599388379,
|
| 587 |
+
"grad_norm": 4.112553596496582,
|
| 588 |
+
"learning_rate": 3.958333333333333e-05,
|
| 589 |
+
"loss": 1.6772,
|
| 590 |
+
"step": 83
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.5137614678899083,
|
| 594 |
+
"grad_norm": 3.116727590560913,
|
| 595 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 596 |
+
"loss": 0.8636,
|
| 597 |
+
"step": 84
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.5198776758409785,
|
| 601 |
+
"grad_norm": 5.432259559631348,
|
| 602 |
+
"learning_rate": 3.541666666666667e-05,
|
| 603 |
+
"loss": 2.3327,
|
| 604 |
+
"step": 85
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.5259938837920489,
|
| 608 |
+
"grad_norm": 5.103914737701416,
|
| 609 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 610 |
+
"loss": 1.3778,
|
| 611 |
+
"step": 86
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.5321100917431193,
|
| 615 |
+
"grad_norm": 3.614302158355713,
|
| 616 |
+
"learning_rate": 3.125e-05,
|
| 617 |
+
"loss": 1.4744,
|
| 618 |
+
"step": 87
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.5382262996941896,
|
| 622 |
+
"grad_norm": 5.543083190917969,
|
| 623 |
+
"learning_rate": 2.916666666666667e-05,
|
| 624 |
+
"loss": 2.5973,
|
| 625 |
+
"step": 88
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.5443425076452599,
|
| 629 |
+
"grad_norm": 2.4122681617736816,
|
| 630 |
+
"learning_rate": 2.7083333333333332e-05,
|
| 631 |
+
"loss": 0.7568,
|
| 632 |
+
"step": 89
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.5504587155963303,
|
| 636 |
+
"grad_norm": 3.6105504035949707,
|
| 637 |
+
"learning_rate": 2.5e-05,
|
| 638 |
+
"loss": 1.5159,
|
| 639 |
+
"step": 90
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.5565749235474006,
|
| 643 |
+
"grad_norm": 5.010311603546143,
|
| 644 |
+
"learning_rate": 2.2916666666666667e-05,
|
| 645 |
+
"loss": 2.6353,
|
| 646 |
+
"step": 91
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.5626911314984709,
|
| 650 |
+
"grad_norm": 3.6909067630767822,
|
| 651 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 652 |
+
"loss": 1.5439,
|
| 653 |
+
"step": 92
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.5688073394495413,
|
| 657 |
+
"grad_norm": 6.5463385581970215,
|
| 658 |
+
"learning_rate": 1.8750000000000002e-05,
|
| 659 |
+
"loss": 3.0133,
|
| 660 |
+
"step": 93
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.5749235474006116,
|
| 664 |
+
"grad_norm": 4.049159049987793,
|
| 665 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 666 |
+
"loss": 1.7854,
|
| 667 |
+
"step": 94
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.581039755351682,
|
| 671 |
+
"grad_norm": 5.64749813079834,
|
| 672 |
+
"learning_rate": 1.4583333333333335e-05,
|
| 673 |
+
"loss": 2.849,
|
| 674 |
+
"step": 95
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.5871559633027523,
|
| 678 |
+
"grad_norm": 4.905054092407227,
|
| 679 |
+
"learning_rate": 1.25e-05,
|
| 680 |
+
"loss": 2.1152,
|
| 681 |
+
"step": 96
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.5932721712538226,
|
| 685 |
+
"grad_norm": 3.8201253414154053,
|
| 686 |
+
"learning_rate": 1.0416666666666668e-05,
|
| 687 |
+
"loss": 1.6202,
|
| 688 |
+
"step": 97
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.599388379204893,
|
| 692 |
+
"grad_norm": 4.628500461578369,
|
| 693 |
+
"learning_rate": 8.333333333333334e-06,
|
| 694 |
+
"loss": 2.452,
|
| 695 |
+
"step": 98
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.6055045871559633,
|
| 699 |
+
"grad_norm": 4.139845848083496,
|
| 700 |
+
"learning_rate": 6.25e-06,
|
| 701 |
+
"loss": 1.12,
|
| 702 |
+
"step": 99
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.6116207951070336,
|
| 706 |
+
"grad_norm": 4.506109237670898,
|
| 707 |
+
"learning_rate": 4.166666666666667e-06,
|
| 708 |
+
"loss": 1.7944,
|
| 709 |
+
"step": 100
|
| 710 |
}
|
| 711 |
],
|
| 712 |
"logging_steps": 1,
|
|
|
|
| 726 |
"attributes": {}
|
| 727 |
}
|
| 728 |
},
|
| 729 |
+
"total_flos": 1052971141431296.0,
|
| 730 |
"train_batch_size": 2,
|
| 731 |
"trial_name": null,
|
| 732 |
"trial_params": null
|