Training in progress, step 4800, 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a48677be121fbdceeeabfe986e73dec1b480151800c1936b91cc4ace7b80e51
|
| 3 |
+
size 1266749168
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2499769978
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44e4a6a867bbc060d0c9facba78b7da76aadb4c3e6f9cafb001ecea1e69880d2
|
| 3 |
size 2499769978
|
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 sha256:5e347613182c5807d2f6db7accfb1c61cd49dff9dda43fd034155068ae72f90f
|
| 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 1256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8493cf662a0ef9cc409c1e71c561b4f018c668b3acc0b65f5c029d848604c14
|
| 3 |
size 1256
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 3 |
-
"best_model_checkpoint": "./output/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 150,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -3397,6 +3397,232 @@
|
|
| 3397 |
"eval_samples_per_second": 10.396,
|
| 3398 |
"eval_steps_per_second": 10.396,
|
| 3399 |
"step": 4500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3400 |
}
|
| 3401 |
],
|
| 3402 |
"logging_steps": 10,
|
|
@@ -3416,7 +3642,7 @@
|
|
| 3416 |
"attributes": {}
|
| 3417 |
}
|
| 3418 |
},
|
| 3419 |
-
"total_flos":
|
| 3420 |
"train_batch_size": 8,
|
| 3421 |
"trial_name": null,
|
| 3422 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.8088018894195557,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-4800",
|
| 4 |
+
"epoch": 0.15402881622436865,
|
| 5 |
"eval_steps": 150,
|
| 6 |
+
"global_step": 4800,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 3397 |
"eval_samples_per_second": 10.396,
|
| 3398 |
"eval_steps_per_second": 10.396,
|
| 3399 |
"step": 4500
|
| 3400 |
+
},
|
| 3401 |
+
{
|
| 3402 |
+
"epoch": 0.14472290857747971,
|
| 3403 |
+
"grad_norm": 16.851276397705078,
|
| 3404 |
+
"learning_rate": 2.447174185242324e-06,
|
| 3405 |
+
"loss": 2.711,
|
| 3406 |
+
"step": 4510
|
| 3407 |
+
},
|
| 3408 |
+
{
|
| 3409 |
+
"epoch": 0.1450438019446138,
|
| 3410 |
+
"grad_norm": 14.372878074645996,
|
| 3411 |
+
"learning_rate": 2.3490904314356415e-06,
|
| 3412 |
+
"loss": 2.5261,
|
| 3413 |
+
"step": 4520
|
| 3414 |
+
},
|
| 3415 |
+
{
|
| 3416 |
+
"epoch": 0.1453646953117479,
|
| 3417 |
+
"grad_norm": 15.558879852294922,
|
| 3418 |
+
"learning_rate": 2.252965419885484e-06,
|
| 3419 |
+
"loss": 2.7099,
|
| 3420 |
+
"step": 4530
|
| 3421 |
+
},
|
| 3422 |
+
{
|
| 3423 |
+
"epoch": 0.145685588678882,
|
| 3424 |
+
"grad_norm": 28.370328903198242,
|
| 3425 |
+
"learning_rate": 2.1588031019145645e-06,
|
| 3426 |
+
"loss": 2.822,
|
| 3427 |
+
"step": 4540
|
| 3428 |
+
},
|
| 3429 |
+
{
|
| 3430 |
+
"epoch": 0.1460064820460161,
|
| 3431 |
+
"grad_norm": 19.941558837890625,
|
| 3432 |
+
"learning_rate": 2.0666073481669716e-06,
|
| 3433 |
+
"loss": 2.7601,
|
| 3434 |
+
"step": 4550
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 0.14632737541315022,
|
| 3438 |
+
"grad_norm": 21.773801803588867,
|
| 3439 |
+
"learning_rate": 1.976381948449036e-06,
|
| 3440 |
+
"loss": 2.8107,
|
| 3441 |
+
"step": 4560
|
| 3442 |
+
},
|
| 3443 |
+
{
|
| 3444 |
+
"epoch": 0.1466482687802843,
|
| 3445 |
+
"grad_norm": 20.395721435546875,
|
| 3446 |
+
"learning_rate": 1.8881306115735636e-06,
|
| 3447 |
+
"loss": 2.694,
|
| 3448 |
+
"step": 4570
|
| 3449 |
+
},
|
| 3450 |
+
{
|
| 3451 |
+
"epoch": 0.14696916214741843,
|
| 3452 |
+
"grad_norm": 17.162796020507812,
|
| 3453 |
+
"learning_rate": 1.8018569652073385e-06,
|
| 3454 |
+
"loss": 2.6769,
|
| 3455 |
+
"step": 4580
|
| 3456 |
+
},
|
| 3457 |
+
{
|
| 3458 |
+
"epoch": 0.14729005551455251,
|
| 3459 |
+
"grad_norm": 16.146156311035156,
|
| 3460 |
+
"learning_rate": 1.717564555722057e-06,
|
| 3461 |
+
"loss": 2.6239,
|
| 3462 |
+
"step": 4590
|
| 3463 |
+
},
|
| 3464 |
+
{
|
| 3465 |
+
"epoch": 0.1476109488816866,
|
| 3466 |
+
"grad_norm": 12.009928703308105,
|
| 3467 |
+
"learning_rate": 1.635256848048528e-06,
|
| 3468 |
+
"loss": 2.6344,
|
| 3469 |
+
"step": 4600
|
| 3470 |
+
},
|
| 3471 |
+
{
|
| 3472 |
+
"epoch": 0.14793184224882072,
|
| 3473 |
+
"grad_norm": 13.901936531066895,
|
| 3474 |
+
"learning_rate": 1.554937225534237e-06,
|
| 3475 |
+
"loss": 2.5777,
|
| 3476 |
+
"step": 4610
|
| 3477 |
+
},
|
| 3478 |
+
{
|
| 3479 |
+
"epoch": 0.1482527356159548,
|
| 3480 |
+
"grad_norm": 14.903900146484375,
|
| 3481 |
+
"learning_rate": 1.4766089898042682e-06,
|
| 3482 |
+
"loss": 2.7427,
|
| 3483 |
+
"step": 4620
|
| 3484 |
+
},
|
| 3485 |
+
{
|
| 3486 |
+
"epoch": 0.14857362898308893,
|
| 3487 |
+
"grad_norm": 19.381118774414062,
|
| 3488 |
+
"learning_rate": 1.4002753606256085e-06,
|
| 3489 |
+
"loss": 2.5458,
|
| 3490 |
+
"step": 4630
|
| 3491 |
+
},
|
| 3492 |
+
{
|
| 3493 |
+
"epoch": 0.14889452235022302,
|
| 3494 |
+
"grad_norm": 21.685401916503906,
|
| 3495 |
+
"learning_rate": 1.3259394757747681e-06,
|
| 3496 |
+
"loss": 2.8216,
|
| 3497 |
+
"step": 4640
|
| 3498 |
+
},
|
| 3499 |
+
{
|
| 3500 |
+
"epoch": 0.14921541571735714,
|
| 3501 |
+
"grad_norm": 14.941693305969238,
|
| 3502 |
+
"learning_rate": 1.2536043909088193e-06,
|
| 3503 |
+
"loss": 2.6604,
|
| 3504 |
+
"step": 4650
|
| 3505 |
+
},
|
| 3506 |
+
{
|
| 3507 |
+
"epoch": 0.14921541571735714,
|
| 3508 |
+
"eval_loss": 2.8094427585601807,
|
| 3509 |
+
"eval_runtime": 52.4562,
|
| 3510 |
+
"eval_samples_per_second": 9.532,
|
| 3511 |
+
"eval_steps_per_second": 9.532,
|
| 3512 |
+
"step": 4650
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 0.14953630908449123,
|
| 3516 |
+
"grad_norm": 16.120569229125977,
|
| 3517 |
+
"learning_rate": 1.1832730794397954e-06,
|
| 3518 |
+
"loss": 2.7746,
|
| 3519 |
+
"step": 4660
|
| 3520 |
+
},
|
| 3521 |
+
{
|
| 3522 |
+
"epoch": 0.14985720245162532,
|
| 3523 |
+
"grad_norm": 18.705150604248047,
|
| 3524 |
+
"learning_rate": 1.1149484324124329e-06,
|
| 3525 |
+
"loss": 2.7896,
|
| 3526 |
+
"step": 4670
|
| 3527 |
+
},
|
| 3528 |
+
{
|
| 3529 |
+
"epoch": 0.15017809581875943,
|
| 3530 |
+
"grad_norm": 16.73013687133789,
|
| 3531 |
+
"learning_rate": 1.0486332583853567e-06,
|
| 3532 |
+
"loss": 2.8454,
|
| 3533 |
+
"step": 4680
|
| 3534 |
+
},
|
| 3535 |
+
{
|
| 3536 |
+
"epoch": 0.15049898918589352,
|
| 3537 |
+
"grad_norm": 20.093090057373047,
|
| 3538 |
+
"learning_rate": 9.843302833156378e-07,
|
| 3539 |
+
"loss": 2.7689,
|
| 3540 |
+
"step": 4690
|
| 3541 |
+
},
|
| 3542 |
+
{
|
| 3543 |
+
"epoch": 0.15081988255302764,
|
| 3544 |
+
"grad_norm": 14.328740119934082,
|
| 3545 |
+
"learning_rate": 9.220421504467283e-07,
|
| 3546 |
+
"loss": 2.7829,
|
| 3547 |
+
"step": 4700
|
| 3548 |
+
},
|
| 3549 |
+
{
|
| 3550 |
+
"epoch": 0.15114077592016173,
|
| 3551 |
+
"grad_norm": 19.58456039428711,
|
| 3552 |
+
"learning_rate": 8.617714201998086e-07,
|
| 3553 |
+
"loss": 2.6827,
|
| 3554 |
+
"step": 4710
|
| 3555 |
+
},
|
| 3556 |
+
{
|
| 3557 |
+
"epoch": 0.15146166928729582,
|
| 3558 |
+
"grad_norm": 15.039648056030273,
|
| 3559 |
+
"learning_rate": 8.035205700685169e-07,
|
| 3560 |
+
"loss": 2.6102,
|
| 3561 |
+
"step": 4720
|
| 3562 |
+
},
|
| 3563 |
+
{
|
| 3564 |
+
"epoch": 0.15178256265442994,
|
| 3565 |
+
"grad_norm": 19.384174346923828,
|
| 3566 |
+
"learning_rate": 7.472919945171633e-07,
|
| 3567 |
+
"loss": 2.9844,
|
| 3568 |
+
"step": 4730
|
| 3569 |
+
},
|
| 3570 |
+
{
|
| 3571 |
+
"epoch": 0.15210345602156403,
|
| 3572 |
+
"grad_norm": 16.812217712402344,
|
| 3573 |
+
"learning_rate": 6.930880048822532e-07,
|
| 3574 |
+
"loss": 2.5543,
|
| 3575 |
+
"step": 4740
|
| 3576 |
+
},
|
| 3577 |
+
{
|
| 3578 |
+
"epoch": 0.15242434938869814,
|
| 3579 |
+
"grad_norm": 15.829549789428711,
|
| 3580 |
+
"learning_rate": 6.409108292774915e-07,
|
| 3581 |
+
"loss": 2.6509,
|
| 3582 |
+
"step": 4750
|
| 3583 |
+
},
|
| 3584 |
+
{
|
| 3585 |
+
"epoch": 0.15274524275583223,
|
| 3586 |
+
"grad_norm": 22.132287979125977,
|
| 3587 |
+
"learning_rate": 5.90762612502216e-07,
|
| 3588 |
+
"loss": 2.7741,
|
| 3589 |
+
"step": 4760
|
| 3590 |
+
},
|
| 3591 |
+
{
|
| 3592 |
+
"epoch": 0.15306613612296635,
|
| 3593 |
+
"grad_norm": 17.18742561340332,
|
| 3594 |
+
"learning_rate": 5.426454159531915e-07,
|
| 3595 |
+
"loss": 2.7961,
|
| 3596 |
+
"step": 4770
|
| 3597 |
+
},
|
| 3598 |
+
{
|
| 3599 |
+
"epoch": 0.15338702949010044,
|
| 3600 |
+
"grad_norm": 14.886670112609863,
|
| 3601 |
+
"learning_rate": 4.965612175399094e-07,
|
| 3602 |
+
"loss": 2.8282,
|
| 3603 |
+
"step": 4780
|
| 3604 |
+
},
|
| 3605 |
+
{
|
| 3606 |
+
"epoch": 0.15370792285723453,
|
| 3607 |
+
"grad_norm": 14.25700569152832,
|
| 3608 |
+
"learning_rate": 4.5251191160326514e-07,
|
| 3609 |
+
"loss": 2.7724,
|
| 3610 |
+
"step": 4790
|
| 3611 |
+
},
|
| 3612 |
+
{
|
| 3613 |
+
"epoch": 0.15402881622436865,
|
| 3614 |
+
"grad_norm": 13.147507667541504,
|
| 3615 |
+
"learning_rate": 4.104993088376975e-07,
|
| 3616 |
+
"loss": 2.7902,
|
| 3617 |
+
"step": 4800
|
| 3618 |
+
},
|
| 3619 |
+
{
|
| 3620 |
+
"epoch": 0.15402881622436865,
|
| 3621 |
+
"eval_loss": 2.8088018894195557,
|
| 3622 |
+
"eval_runtime": 44.5579,
|
| 3623 |
+
"eval_samples_per_second": 11.221,
|
| 3624 |
+
"eval_steps_per_second": 11.221,
|
| 3625 |
+
"step": 4800
|
| 3626 |
}
|
| 3627 |
],
|
| 3628 |
"logging_steps": 10,
|
|
|
|
| 3642 |
"attributes": {}
|
| 3643 |
}
|
| 3644 |
},
|
| 3645 |
+
"total_flos": 7.062562841064975e+17,
|
| 3646 |
"train_batch_size": 8,
|
| 3647 |
"trial_name": null,
|
| 3648 |
"trial_params": null
|