Training in progress, step 5500, 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 5323528
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afdc7bd9d3bef6c5e894b53ed72a94b99726290b734e0bf561bc5081e613a3a5
|
| 3 |
size 5323528
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10707706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b8dc6e6ab63f8f2ab0a2ef7abcaaafacf3195f20706e2cf750f59052bce8207
|
| 3 |
size 10707706
|
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:ab1e40e99fab0633bd87e6ef55b536c62fe829ab788d235ef7008de5c52a1ab6
|
| 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 sha256:30332e8503dd44f865572ef943e9da8b0c9c1c0a4084d30212d8b7e0b9a4d2d8
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 3 |
-
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-
|
| 4 |
-
"epoch": 8.
|
| 5 |
"eval_steps": 100,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -3407,13 +3407,353 @@
|
|
| 3407 |
"eval_samples_per_second": 92.029,
|
| 3408 |
"eval_steps_per_second": 11.553,
|
| 3409 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3410 |
}
|
| 3411 |
],
|
| 3412 |
"logging_steps": 10,
|
| 3413 |
"max_steps": 6130,
|
| 3414 |
"num_train_epochs": 10,
|
| 3415 |
"save_steps": 500,
|
| 3416 |
-
"total_flos":
|
| 3417 |
"trial_name": null,
|
| 3418 |
"trial_params": null
|
| 3419 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.417066365480423,
|
| 3 |
+
"best_model_checkpoint": "bart_lora_outputs\\checkpoint-5500",
|
| 4 |
+
"epoch": 8.97226753670473,
|
| 5 |
"eval_steps": 100,
|
| 6 |
+
"global_step": 5500,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 3407 |
"eval_samples_per_second": 92.029,
|
| 3408 |
"eval_steps_per_second": 11.553,
|
| 3409 |
"step": 5000
|
| 3410 |
+
},
|
| 3411 |
+
{
|
| 3412 |
+
"epoch": 8.17,
|
| 3413 |
+
"learning_rate": 0.00019893428063943162,
|
| 3414 |
+
"loss": 0.3893,
|
| 3415 |
+
"step": 5010
|
| 3416 |
+
},
|
| 3417 |
+
{
|
| 3418 |
+
"epoch": 8.19,
|
| 3419 |
+
"learning_rate": 0.00019715808170515098,
|
| 3420 |
+
"loss": 0.3948,
|
| 3421 |
+
"step": 5020
|
| 3422 |
+
},
|
| 3423 |
+
{
|
| 3424 |
+
"epoch": 8.21,
|
| 3425 |
+
"learning_rate": 0.00019538188277087035,
|
| 3426 |
+
"loss": 0.3831,
|
| 3427 |
+
"step": 5030
|
| 3428 |
+
},
|
| 3429 |
+
{
|
| 3430 |
+
"epoch": 8.22,
|
| 3431 |
+
"learning_rate": 0.0001936056838365897,
|
| 3432 |
+
"loss": 0.3828,
|
| 3433 |
+
"step": 5040
|
| 3434 |
+
},
|
| 3435 |
+
{
|
| 3436 |
+
"epoch": 8.24,
|
| 3437 |
+
"learning_rate": 0.00019182948490230906,
|
| 3438 |
+
"loss": 0.3986,
|
| 3439 |
+
"step": 5050
|
| 3440 |
+
},
|
| 3441 |
+
{
|
| 3442 |
+
"epoch": 8.25,
|
| 3443 |
+
"learning_rate": 0.00019005328596802842,
|
| 3444 |
+
"loss": 0.3826,
|
| 3445 |
+
"step": 5060
|
| 3446 |
+
},
|
| 3447 |
+
{
|
| 3448 |
+
"epoch": 8.27,
|
| 3449 |
+
"learning_rate": 0.0001882770870337478,
|
| 3450 |
+
"loss": 0.4053,
|
| 3451 |
+
"step": 5070
|
| 3452 |
+
},
|
| 3453 |
+
{
|
| 3454 |
+
"epoch": 8.29,
|
| 3455 |
+
"learning_rate": 0.00018650088809946713,
|
| 3456 |
+
"loss": 0.399,
|
| 3457 |
+
"step": 5080
|
| 3458 |
+
},
|
| 3459 |
+
{
|
| 3460 |
+
"epoch": 8.3,
|
| 3461 |
+
"learning_rate": 0.0001847246891651865,
|
| 3462 |
+
"loss": 0.4096,
|
| 3463 |
+
"step": 5090
|
| 3464 |
+
},
|
| 3465 |
+
{
|
| 3466 |
+
"epoch": 8.32,
|
| 3467 |
+
"learning_rate": 0.00018294849023090586,
|
| 3468 |
+
"loss": 0.3931,
|
| 3469 |
+
"step": 5100
|
| 3470 |
+
},
|
| 3471 |
+
{
|
| 3472 |
+
"epoch": 8.32,
|
| 3473 |
+
"eval_loss": 0.4182140529155731,
|
| 3474 |
+
"eval_runtime": 12.7337,
|
| 3475 |
+
"eval_samples_per_second": 91.961,
|
| 3476 |
+
"eval_steps_per_second": 11.544,
|
| 3477 |
+
"step": 5100
|
| 3478 |
+
},
|
| 3479 |
+
{
|
| 3480 |
+
"epoch": 8.34,
|
| 3481 |
+
"learning_rate": 0.0001811722912966252,
|
| 3482 |
+
"loss": 0.4117,
|
| 3483 |
+
"step": 5110
|
| 3484 |
+
},
|
| 3485 |
+
{
|
| 3486 |
+
"epoch": 8.35,
|
| 3487 |
+
"learning_rate": 0.0001793960923623446,
|
| 3488 |
+
"loss": 0.3754,
|
| 3489 |
+
"step": 5120
|
| 3490 |
+
},
|
| 3491 |
+
{
|
| 3492 |
+
"epoch": 8.37,
|
| 3493 |
+
"learning_rate": 0.00017761989342806396,
|
| 3494 |
+
"loss": 0.3688,
|
| 3495 |
+
"step": 5130
|
| 3496 |
+
},
|
| 3497 |
+
{
|
| 3498 |
+
"epoch": 8.38,
|
| 3499 |
+
"learning_rate": 0.00017584369449378333,
|
| 3500 |
+
"loss": 0.4199,
|
| 3501 |
+
"step": 5140
|
| 3502 |
+
},
|
| 3503 |
+
{
|
| 3504 |
+
"epoch": 8.4,
|
| 3505 |
+
"learning_rate": 0.00017406749555950267,
|
| 3506 |
+
"loss": 0.4011,
|
| 3507 |
+
"step": 5150
|
| 3508 |
+
},
|
| 3509 |
+
{
|
| 3510 |
+
"epoch": 8.42,
|
| 3511 |
+
"learning_rate": 0.00017229129662522203,
|
| 3512 |
+
"loss": 0.4013,
|
| 3513 |
+
"step": 5160
|
| 3514 |
+
},
|
| 3515 |
+
{
|
| 3516 |
+
"epoch": 8.43,
|
| 3517 |
+
"learning_rate": 0.0001705150976909414,
|
| 3518 |
+
"loss": 0.414,
|
| 3519 |
+
"step": 5170
|
| 3520 |
+
},
|
| 3521 |
+
{
|
| 3522 |
+
"epoch": 8.45,
|
| 3523 |
+
"learning_rate": 0.00016873889875666074,
|
| 3524 |
+
"loss": 0.3682,
|
| 3525 |
+
"step": 5180
|
| 3526 |
+
},
|
| 3527 |
+
{
|
| 3528 |
+
"epoch": 8.47,
|
| 3529 |
+
"learning_rate": 0.0001669626998223801,
|
| 3530 |
+
"loss": 0.377,
|
| 3531 |
+
"step": 5190
|
| 3532 |
+
},
|
| 3533 |
+
{
|
| 3534 |
+
"epoch": 8.48,
|
| 3535 |
+
"learning_rate": 0.00016518650088809947,
|
| 3536 |
+
"loss": 0.3904,
|
| 3537 |
+
"step": 5200
|
| 3538 |
+
},
|
| 3539 |
+
{
|
| 3540 |
+
"epoch": 8.48,
|
| 3541 |
+
"eval_loss": 0.41562286019325256,
|
| 3542 |
+
"eval_runtime": 12.9077,
|
| 3543 |
+
"eval_samples_per_second": 90.721,
|
| 3544 |
+
"eval_steps_per_second": 11.389,
|
| 3545 |
+
"step": 5200
|
| 3546 |
+
},
|
| 3547 |
+
{
|
| 3548 |
+
"epoch": 8.5,
|
| 3549 |
+
"learning_rate": 0.00016341030195381884,
|
| 3550 |
+
"loss": 0.3955,
|
| 3551 |
+
"step": 5210
|
| 3552 |
+
},
|
| 3553 |
+
{
|
| 3554 |
+
"epoch": 8.52,
|
| 3555 |
+
"learning_rate": 0.00016163410301953818,
|
| 3556 |
+
"loss": 0.386,
|
| 3557 |
+
"step": 5220
|
| 3558 |
+
},
|
| 3559 |
+
{
|
| 3560 |
+
"epoch": 8.53,
|
| 3561 |
+
"learning_rate": 0.00015985790408525754,
|
| 3562 |
+
"loss": 0.3862,
|
| 3563 |
+
"step": 5230
|
| 3564 |
+
},
|
| 3565 |
+
{
|
| 3566 |
+
"epoch": 8.55,
|
| 3567 |
+
"learning_rate": 0.0001580817051509769,
|
| 3568 |
+
"loss": 0.3979,
|
| 3569 |
+
"step": 5240
|
| 3570 |
+
},
|
| 3571 |
+
{
|
| 3572 |
+
"epoch": 8.56,
|
| 3573 |
+
"learning_rate": 0.00015630550621669628,
|
| 3574 |
+
"loss": 0.381,
|
| 3575 |
+
"step": 5250
|
| 3576 |
+
},
|
| 3577 |
+
{
|
| 3578 |
+
"epoch": 8.58,
|
| 3579 |
+
"learning_rate": 0.00015452930728241561,
|
| 3580 |
+
"loss": 0.4016,
|
| 3581 |
+
"step": 5260
|
| 3582 |
+
},
|
| 3583 |
+
{
|
| 3584 |
+
"epoch": 8.6,
|
| 3585 |
+
"learning_rate": 0.000152753108348135,
|
| 3586 |
+
"loss": 0.4191,
|
| 3587 |
+
"step": 5270
|
| 3588 |
+
},
|
| 3589 |
+
{
|
| 3590 |
+
"epoch": 8.61,
|
| 3591 |
+
"learning_rate": 0.00015097690941385437,
|
| 3592 |
+
"loss": 0.3832,
|
| 3593 |
+
"step": 5280
|
| 3594 |
+
},
|
| 3595 |
+
{
|
| 3596 |
+
"epoch": 8.63,
|
| 3597 |
+
"learning_rate": 0.00014920071047957371,
|
| 3598 |
+
"loss": 0.3934,
|
| 3599 |
+
"step": 5290
|
| 3600 |
+
},
|
| 3601 |
+
{
|
| 3602 |
+
"epoch": 8.65,
|
| 3603 |
+
"learning_rate": 0.00014742451154529308,
|
| 3604 |
+
"loss": 0.3968,
|
| 3605 |
+
"step": 5300
|
| 3606 |
+
},
|
| 3607 |
+
{
|
| 3608 |
+
"epoch": 8.65,
|
| 3609 |
+
"eval_loss": 0.41458660364151,
|
| 3610 |
+
"eval_runtime": 12.7995,
|
| 3611 |
+
"eval_samples_per_second": 91.488,
|
| 3612 |
+
"eval_steps_per_second": 11.485,
|
| 3613 |
+
"step": 5300
|
| 3614 |
+
},
|
| 3615 |
+
{
|
| 3616 |
+
"epoch": 8.66,
|
| 3617 |
+
"learning_rate": 0.00014564831261101245,
|
| 3618 |
+
"loss": 0.409,
|
| 3619 |
+
"step": 5310
|
| 3620 |
+
},
|
| 3621 |
+
{
|
| 3622 |
+
"epoch": 8.68,
|
| 3623 |
+
"learning_rate": 0.0001438721136767318,
|
| 3624 |
+
"loss": 0.3797,
|
| 3625 |
+
"step": 5320
|
| 3626 |
+
},
|
| 3627 |
+
{
|
| 3628 |
+
"epoch": 8.69,
|
| 3629 |
+
"learning_rate": 0.00014209591474245115,
|
| 3630 |
+
"loss": 0.3895,
|
| 3631 |
+
"step": 5330
|
| 3632 |
+
},
|
| 3633 |
+
{
|
| 3634 |
+
"epoch": 8.71,
|
| 3635 |
+
"learning_rate": 0.00014031971580817052,
|
| 3636 |
+
"loss": 0.3722,
|
| 3637 |
+
"step": 5340
|
| 3638 |
+
},
|
| 3639 |
+
{
|
| 3640 |
+
"epoch": 8.73,
|
| 3641 |
+
"learning_rate": 0.00013854351687388988,
|
| 3642 |
+
"loss": 0.4083,
|
| 3643 |
+
"step": 5350
|
| 3644 |
+
},
|
| 3645 |
+
{
|
| 3646 |
+
"epoch": 8.74,
|
| 3647 |
+
"learning_rate": 0.00013676731793960922,
|
| 3648 |
+
"loss": 0.4032,
|
| 3649 |
+
"step": 5360
|
| 3650 |
+
},
|
| 3651 |
+
{
|
| 3652 |
+
"epoch": 8.76,
|
| 3653 |
+
"learning_rate": 0.0001349911190053286,
|
| 3654 |
+
"loss": 0.3985,
|
| 3655 |
+
"step": 5370
|
| 3656 |
+
},
|
| 3657 |
+
{
|
| 3658 |
+
"epoch": 8.78,
|
| 3659 |
+
"learning_rate": 0.00013321492007104796,
|
| 3660 |
+
"loss": 0.3894,
|
| 3661 |
+
"step": 5380
|
| 3662 |
+
},
|
| 3663 |
+
{
|
| 3664 |
+
"epoch": 8.79,
|
| 3665 |
+
"learning_rate": 0.00013143872113676732,
|
| 3666 |
+
"loss": 0.3924,
|
| 3667 |
+
"step": 5390
|
| 3668 |
+
},
|
| 3669 |
+
{
|
| 3670 |
+
"epoch": 8.81,
|
| 3671 |
+
"learning_rate": 0.00012966252220248666,
|
| 3672 |
+
"loss": 0.3677,
|
| 3673 |
+
"step": 5400
|
| 3674 |
+
},
|
| 3675 |
+
{
|
| 3676 |
+
"epoch": 8.81,
|
| 3677 |
+
"eval_loss": 0.41405031085014343,
|
| 3678 |
+
"eval_runtime": 12.6828,
|
| 3679 |
+
"eval_samples_per_second": 92.33,
|
| 3680 |
+
"eval_steps_per_second": 11.591,
|
| 3681 |
+
"step": 5400
|
| 3682 |
+
},
|
| 3683 |
+
{
|
| 3684 |
+
"epoch": 8.83,
|
| 3685 |
+
"learning_rate": 0.00012788632326820603,
|
| 3686 |
+
"loss": 0.3836,
|
| 3687 |
+
"step": 5410
|
| 3688 |
+
},
|
| 3689 |
+
{
|
| 3690 |
+
"epoch": 8.84,
|
| 3691 |
+
"learning_rate": 0.0001261101243339254,
|
| 3692 |
+
"loss": 0.4018,
|
| 3693 |
+
"step": 5420
|
| 3694 |
+
},
|
| 3695 |
+
{
|
| 3696 |
+
"epoch": 8.86,
|
| 3697 |
+
"learning_rate": 0.00012433392539964476,
|
| 3698 |
+
"loss": 0.4,
|
| 3699 |
+
"step": 5430
|
| 3700 |
+
},
|
| 3701 |
+
{
|
| 3702 |
+
"epoch": 8.87,
|
| 3703 |
+
"learning_rate": 0.00012255772646536413,
|
| 3704 |
+
"loss": 0.3869,
|
| 3705 |
+
"step": 5440
|
| 3706 |
+
},
|
| 3707 |
+
{
|
| 3708 |
+
"epoch": 8.89,
|
| 3709 |
+
"learning_rate": 0.00012078152753108348,
|
| 3710 |
+
"loss": 0.4168,
|
| 3711 |
+
"step": 5450
|
| 3712 |
+
},
|
| 3713 |
+
{
|
| 3714 |
+
"epoch": 8.91,
|
| 3715 |
+
"learning_rate": 0.00011900532859680283,
|
| 3716 |
+
"loss": 0.3929,
|
| 3717 |
+
"step": 5460
|
| 3718 |
+
},
|
| 3719 |
+
{
|
| 3720 |
+
"epoch": 8.92,
|
| 3721 |
+
"learning_rate": 0.00011722912966252221,
|
| 3722 |
+
"loss": 0.4153,
|
| 3723 |
+
"step": 5470
|
| 3724 |
+
},
|
| 3725 |
+
{
|
| 3726 |
+
"epoch": 8.94,
|
| 3727 |
+
"learning_rate": 0.00011545293072824157,
|
| 3728 |
+
"loss": 0.4017,
|
| 3729 |
+
"step": 5480
|
| 3730 |
+
},
|
| 3731 |
+
{
|
| 3732 |
+
"epoch": 8.96,
|
| 3733 |
+
"learning_rate": 0.00011367673179396093,
|
| 3734 |
+
"loss": 0.3844,
|
| 3735 |
+
"step": 5490
|
| 3736 |
+
},
|
| 3737 |
+
{
|
| 3738 |
+
"epoch": 8.97,
|
| 3739 |
+
"learning_rate": 0.00011190053285968029,
|
| 3740 |
+
"loss": 0.3823,
|
| 3741 |
+
"step": 5500
|
| 3742 |
+
},
|
| 3743 |
+
{
|
| 3744 |
+
"epoch": 8.97,
|
| 3745 |
+
"eval_loss": 0.417066365480423,
|
| 3746 |
+
"eval_runtime": 12.7641,
|
| 3747 |
+
"eval_samples_per_second": 91.742,
|
| 3748 |
+
"eval_steps_per_second": 11.517,
|
| 3749 |
+
"step": 5500
|
| 3750 |
}
|
| 3751 |
],
|
| 3752 |
"logging_steps": 10,
|
| 3753 |
"max_steps": 6130,
|
| 3754 |
"num_train_epochs": 10,
|
| 3755 |
"save_steps": 500,
|
| 3756 |
+
"total_flos": 1.039214421393408e+16,
|
| 3757 |
"trial_name": null,
|
| 3758 |
"trial_params": null
|
| 3759 |
}
|