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 138995824
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3c565fdd0012eba344d8a5a9bf99f2ceb5cdb0e6617f1e360f26f57fe6bbf7e
|
| 3 |
size 138995824
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 71077780
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3d1ab1bba9d57de447039a0f18b2ff2cb92f1e9b95f49a880b3190607622561
|
| 3 |
size 71077780
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d56994a37818582f42a99c78ac5ae6261c4c4b790c720ca8a6407e6f312bdff
|
| 3 |
size 14960
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bbe57ff59ab6882912679030ba7251cac68625536a3494f51d56d0ab56150fb
|
| 3 |
size 14960
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b34aa465a56f381802b0571fea59dfe8cb269b0a34389220f95a122ea99863db
|
| 3 |
size 14960
|
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 14960
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07165f42e26281082b0b15052b99e85b5aba2b79e8d3a7f480bc813ae22d758a
|
| 3 |
size 14960
|
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": 1.
|
| 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": 328.098,
|
| 374 |
"eval_steps_per_second": 20.514,
|
| 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": 1.8241409063339233,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
| 4 |
+
"epoch": 0.13499831252109348,
|
| 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": 328.098,
|
| 374 |
"eval_steps_per_second": 20.514,
|
| 375 |
"step": 50
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.06884913938575768,
|
| 379 |
+
"grad_norm": 0.45811840891838074,
|
| 380 |
+
"learning_rate": 8.894386393810563e-05,
|
| 381 |
+
"loss": 1.2069,
|
| 382 |
+
"step": 51
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.07019912251096862,
|
| 386 |
+
"grad_norm": 0.447782963514328,
|
| 387 |
+
"learning_rate": 8.842005554284296e-05,
|
| 388 |
+
"loss": 1.5984,
|
| 389 |
+
"step": 52
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.07154910563617954,
|
| 393 |
+
"grad_norm": 0.4776899814605713,
|
| 394 |
+
"learning_rate": 8.788574348801675e-05,
|
| 395 |
+
"loss": 1.6739,
|
| 396 |
+
"step": 53
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.07289908876139048,
|
| 400 |
+
"grad_norm": 0.4807668924331665,
|
| 401 |
+
"learning_rate": 8.73410738492077e-05,
|
| 402 |
+
"loss": 1.7968,
|
| 403 |
+
"step": 54
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.07424907188660142,
|
| 407 |
+
"grad_norm": 0.4958879351615906,
|
| 408 |
+
"learning_rate": 8.678619553365659e-05,
|
| 409 |
+
"loss": 1.7628,
|
| 410 |
+
"step": 55
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.07559905501181235,
|
| 414 |
+
"grad_norm": 0.49120938777923584,
|
| 415 |
+
"learning_rate": 8.622126023955446e-05,
|
| 416 |
+
"loss": 1.9598,
|
| 417 |
+
"step": 56
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.07694903813702329,
|
| 421 |
+
"grad_norm": 0.5465077757835388,
|
| 422 |
+
"learning_rate": 8.564642241456986e-05,
|
| 423 |
+
"loss": 2.0605,
|
| 424 |
+
"step": 57
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.07829902126223422,
|
| 428 |
+
"grad_norm": 0.5541543960571289,
|
| 429 |
+
"learning_rate": 8.506183921362443e-05,
|
| 430 |
+
"loss": 1.9847,
|
| 431 |
+
"step": 58
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.07964900438744515,
|
| 435 |
+
"grad_norm": 0.5458495020866394,
|
| 436 |
+
"learning_rate": 8.44676704559283e-05,
|
| 437 |
+
"loss": 2.0529,
|
| 438 |
+
"step": 59
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.08099898751265609,
|
| 442 |
+
"grad_norm": 0.6789040565490723,
|
| 443 |
+
"learning_rate": 8.386407858128706e-05,
|
| 444 |
+
"loss": 2.0561,
|
| 445 |
+
"step": 60
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.08234897063786703,
|
| 449 |
+
"grad_norm": 0.613196611404419,
|
| 450 |
+
"learning_rate": 8.32512286056924e-05,
|
| 451 |
+
"loss": 2.2318,
|
| 452 |
+
"step": 61
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.08369895376307797,
|
| 456 |
+
"grad_norm": 0.6030352711677551,
|
| 457 |
+
"learning_rate": 8.262928807620843e-05,
|
| 458 |
+
"loss": 2.2167,
|
| 459 |
+
"step": 62
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.08504893688828889,
|
| 463 |
+
"grad_norm": 0.39666399359703064,
|
| 464 |
+
"learning_rate": 8.199842702516583e-05,
|
| 465 |
+
"loss": 1.4176,
|
| 466 |
+
"step": 63
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.08639892001349983,
|
| 470 |
+
"grad_norm": 0.4236837327480316,
|
| 471 |
+
"learning_rate": 8.135881792367686e-05,
|
| 472 |
+
"loss": 1.502,
|
| 473 |
+
"step": 64
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.08774890313871077,
|
| 477 |
+
"grad_norm": 0.3921578824520111,
|
| 478 |
+
"learning_rate": 8.07106356344834e-05,
|
| 479 |
+
"loss": 1.5816,
|
| 480 |
+
"step": 65
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.0890988862639217,
|
| 484 |
+
"grad_norm": 0.5283613204956055,
|
| 485 |
+
"learning_rate": 8.005405736415126e-05,
|
| 486 |
+
"loss": 1.7715,
|
| 487 |
+
"step": 66
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.09044886938913263,
|
| 491 |
+
"grad_norm": 0.6686879992485046,
|
| 492 |
+
"learning_rate": 7.938926261462366e-05,
|
| 493 |
+
"loss": 1.7861,
|
| 494 |
+
"step": 67
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.09179885251434357,
|
| 498 |
+
"grad_norm": 0.4964534044265747,
|
| 499 |
+
"learning_rate": 7.871643313414718e-05,
|
| 500 |
+
"loss": 1.8814,
|
| 501 |
+
"step": 68
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.0931488356395545,
|
| 505 |
+
"grad_norm": 0.4999064803123474,
|
| 506 |
+
"learning_rate": 7.803575286758364e-05,
|
| 507 |
+
"loss": 1.8395,
|
| 508 |
+
"step": 69
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.09449881876476544,
|
| 512 |
+
"grad_norm": 0.5323036313056946,
|
| 513 |
+
"learning_rate": 7.734740790612136e-05,
|
| 514 |
+
"loss": 1.9695,
|
| 515 |
+
"step": 70
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.09584880188997638,
|
| 519 |
+
"grad_norm": 0.5498347878456116,
|
| 520 |
+
"learning_rate": 7.66515864363997e-05,
|
| 521 |
+
"loss": 1.9505,
|
| 522 |
+
"step": 71
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.0971987850151873,
|
| 526 |
+
"grad_norm": 0.6689106822013855,
|
| 527 |
+
"learning_rate": 7.594847868906076e-05,
|
| 528 |
+
"loss": 2.076,
|
| 529 |
+
"step": 72
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.09854876814039824,
|
| 533 |
+
"grad_norm": 0.5689659118652344,
|
| 534 |
+
"learning_rate": 7.52382768867422e-05,
|
| 535 |
+
"loss": 2.1989,
|
| 536 |
+
"step": 73
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.09989875126560918,
|
| 540 |
+
"grad_norm": 0.6717419624328613,
|
| 541 |
+
"learning_rate": 7.452117519152542e-05,
|
| 542 |
+
"loss": 2.1737,
|
| 543 |
+
"step": 74
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.10124873439082012,
|
| 547 |
+
"grad_norm": 0.7925436496734619,
|
| 548 |
+
"learning_rate": 7.379736965185368e-05,
|
| 549 |
+
"loss": 2.288,
|
| 550 |
+
"step": 75
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.10259871751603104,
|
| 554 |
+
"grad_norm": 0.3465993404388428,
|
| 555 |
+
"learning_rate": 7.30670581489344e-05,
|
| 556 |
+
"loss": 1.1495,
|
| 557 |
+
"step": 76
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.10394870064124198,
|
| 561 |
+
"grad_norm": 0.5540285706520081,
|
| 562 |
+
"learning_rate": 7.233044034264034e-05,
|
| 563 |
+
"loss": 1.5059,
|
| 564 |
+
"step": 77
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.10529868376645292,
|
| 568 |
+
"grad_norm": 0.5064082741737366,
|
| 569 |
+
"learning_rate": 7.158771761692464e-05,
|
| 570 |
+
"loss": 1.6449,
|
| 571 |
+
"step": 78
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.10664866689166386,
|
| 575 |
+
"grad_norm": 0.5152279734611511,
|
| 576 |
+
"learning_rate": 7.083909302476453e-05,
|
| 577 |
+
"loss": 1.696,
|
| 578 |
+
"step": 79
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.1079986500168748,
|
| 582 |
+
"grad_norm": 0.5134519934654236,
|
| 583 |
+
"learning_rate": 7.008477123264848e-05,
|
| 584 |
+
"loss": 1.7405,
|
| 585 |
+
"step": 80
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.10934863314208572,
|
| 589 |
+
"grad_norm": 0.5233516693115234,
|
| 590 |
+
"learning_rate": 6.932495846462261e-05,
|
| 591 |
+
"loss": 1.8774,
|
| 592 |
+
"step": 81
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.11069861626729666,
|
| 596 |
+
"grad_norm": 0.5960975289344788,
|
| 597 |
+
"learning_rate": 6.855986244591104e-05,
|
| 598 |
+
"loss": 1.9146,
|
| 599 |
+
"step": 82
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.1120485993925076,
|
| 603 |
+
"grad_norm": 0.5546828508377075,
|
| 604 |
+
"learning_rate": 6.778969234612584e-05,
|
| 605 |
+
"loss": 1.895,
|
| 606 |
+
"step": 83
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.11339858251771853,
|
| 610 |
+
"grad_norm": 0.5760257840156555,
|
| 611 |
+
"learning_rate": 6.701465872208216e-05,
|
| 612 |
+
"loss": 1.8824,
|
| 613 |
+
"step": 84
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.11474856564292946,
|
| 617 |
+
"grad_norm": 0.6636323928833008,
|
| 618 |
+
"learning_rate": 6.623497346023418e-05,
|
| 619 |
+
"loss": 2.0239,
|
| 620 |
+
"step": 85
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.1160985487681404,
|
| 624 |
+
"grad_norm": 0.5874965786933899,
|
| 625 |
+
"learning_rate": 6.545084971874738e-05,
|
| 626 |
+
"loss": 2.1653,
|
| 627 |
+
"step": 86
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.11744853189335133,
|
| 631 |
+
"grad_norm": 0.7196479439735413,
|
| 632 |
+
"learning_rate": 6.466250186922325e-05,
|
| 633 |
+
"loss": 2.2116,
|
| 634 |
+
"step": 87
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.11879851501856227,
|
| 638 |
+
"grad_norm": 0.47423693537712097,
|
| 639 |
+
"learning_rate": 6.387014543809223e-05,
|
| 640 |
+
"loss": 1.3431,
|
| 641 |
+
"step": 88
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.12014849814377321,
|
| 645 |
+
"grad_norm": 0.3962845802307129,
|
| 646 |
+
"learning_rate": 6.307399704769099e-05,
|
| 647 |
+
"loss": 1.3365,
|
| 648 |
+
"step": 89
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.12149848126898413,
|
| 652 |
+
"grad_norm": 0.47901609539985657,
|
| 653 |
+
"learning_rate": 6.227427435703997e-05,
|
| 654 |
+
"loss": 1.6389,
|
| 655 |
+
"step": 90
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.12284846439419507,
|
| 659 |
+
"grad_norm": 0.4754610061645508,
|
| 660 |
+
"learning_rate": 6.147119600233758e-05,
|
| 661 |
+
"loss": 1.7121,
|
| 662 |
+
"step": 91
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.12419844751940601,
|
| 666 |
+
"grad_norm": 0.5723981857299805,
|
| 667 |
+
"learning_rate": 6.066498153718735e-05,
|
| 668 |
+
"loss": 1.8633,
|
| 669 |
+
"step": 92
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.12554843064461693,
|
| 673 |
+
"grad_norm": 0.5481359362602234,
|
| 674 |
+
"learning_rate": 5.985585137257401e-05,
|
| 675 |
+
"loss": 1.7504,
|
| 676 |
+
"step": 93
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.12689841376982788,
|
| 680 |
+
"grad_norm": 0.5384538769721985,
|
| 681 |
+
"learning_rate": 5.90440267166055e-05,
|
| 682 |
+
"loss": 1.8486,
|
| 683 |
+
"step": 94
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.1282483968950388,
|
| 687 |
+
"grad_norm": 0.6528523564338684,
|
| 688 |
+
"learning_rate": 5.8229729514036705e-05,
|
| 689 |
+
"loss": 1.9868,
|
| 690 |
+
"step": 95
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.12959838002024976,
|
| 694 |
+
"grad_norm": 0.5357434749603271,
|
| 695 |
+
"learning_rate": 5.74131823855921e-05,
|
| 696 |
+
"loss": 1.9507,
|
| 697 |
+
"step": 96
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.13094836314546068,
|
| 701 |
+
"grad_norm": 0.6054865717887878,
|
| 702 |
+
"learning_rate": 5.6594608567103456e-05,
|
| 703 |
+
"loss": 1.9732,
|
| 704 |
+
"step": 97
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.1322983462706716,
|
| 708 |
+
"grad_norm": 0.6194401383399963,
|
| 709 |
+
"learning_rate": 5.577423184847932e-05,
|
| 710 |
+
"loss": 2.0267,
|
| 711 |
+
"step": 98
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.13364832939588256,
|
| 715 |
+
"grad_norm": 0.6116562485694885,
|
| 716 |
+
"learning_rate": 5.495227651252315e-05,
|
| 717 |
+
"loss": 2.2024,
|
| 718 |
+
"step": 99
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.13499831252109348,
|
| 722 |
+
"grad_norm": 0.7421515583992004,
|
| 723 |
+
"learning_rate": 5.4128967273616625e-05,
|
| 724 |
+
"loss": 2.3756,
|
| 725 |
+
"step": 100
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.13499831252109348,
|
| 729 |
+
"eval_loss": 1.8241409063339233,
|
| 730 |
+
"eval_runtime": 15.1329,
|
| 731 |
+
"eval_samples_per_second": 329.745,
|
| 732 |
+
"eval_steps_per_second": 20.617,
|
| 733 |
+
"step": 100
|
| 734 |
}
|
| 735 |
],
|
| 736 |
"logging_steps": 1,
|
|
|
|
| 759 |
"attributes": {}
|
| 760 |
}
|
| 761 |
},
|
| 762 |
+
"total_flos": 2.7475518160896e+16,
|
| 763 |
"train_batch_size": 8,
|
| 764 |
"trial_name": null,
|
| 765 |
"trial_params": null
|