Commit
•
39ced10
1
Parent(s):
d3e6edc
Training in progress, step 3500, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2c0277f54c09c949fa6a8943edf7edac098878a0d43666f5fcb22403b14c145
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e5ea83ac97396889fe2821e60cc59e33e316d14ac1826fe80fb9efcd4c6f98b
|
3 |
size 1155772233
|
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:a414c666e8625c7f4e23102be45d01b76de4812ff286110f0f9a0e1c67f33573
|
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 sha256:3b37e9ef30e383e795affd2915d5979e774d36e929b105a379fff9b722cf9675
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.39595454931259155,
|
3 |
"best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/checkpoint-3000",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -475,6 +475,84 @@
|
|
475 |
"eval_samples_per_second": 28.143,
|
476 |
"eval_steps_per_second": 3.596,
|
477 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
478 |
}
|
479 |
],
|
480 |
"logging_steps": 50,
|
@@ -494,7 +572,7 @@
|
|
494 |
"attributes": {}
|
495 |
}
|
496 |
},
|
497 |
-
"total_flos":
|
498 |
"train_batch_size": 32,
|
499 |
"trial_name": null,
|
500 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.39595454931259155,
|
3 |
"best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/checkpoint-3000",
|
4 |
+
"epoch": 274.5098039215686,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 3500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
475 |
"eval_samples_per_second": 28.143,
|
476 |
"eval_steps_per_second": 3.596,
|
477 |
"step": 3000
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 239.2156862745098,
|
481 |
+
"grad_norm": 0.7012345790863037,
|
482 |
+
"learning_rate": 4.755e-06,
|
483 |
+
"loss": 0.4103,
|
484 |
+
"step": 3050
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 243.13725490196077,
|
488 |
+
"grad_norm": 0.7060217261314392,
|
489 |
+
"learning_rate": 4.505e-06,
|
490 |
+
"loss": 0.4114,
|
491 |
+
"step": 3100
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 247.05882352941177,
|
495 |
+
"grad_norm": 0.8892201781272888,
|
496 |
+
"learning_rate": 4.255e-06,
|
497 |
+
"loss": 0.4093,
|
498 |
+
"step": 3150
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 250.98039215686273,
|
502 |
+
"grad_norm": 0.6098002791404724,
|
503 |
+
"learning_rate": 4.005000000000001e-06,
|
504 |
+
"loss": 0.411,
|
505 |
+
"step": 3200
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 254.90196078431373,
|
509 |
+
"grad_norm": 0.7227322459220886,
|
510 |
+
"learning_rate": 3.7550000000000005e-06,
|
511 |
+
"loss": 0.4108,
|
512 |
+
"step": 3250
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 258.8235294117647,
|
516 |
+
"grad_norm": 0.8260012865066528,
|
517 |
+
"learning_rate": 3.505e-06,
|
518 |
+
"loss": 0.412,
|
519 |
+
"step": 3300
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 262.7450980392157,
|
523 |
+
"grad_norm": 0.6897534132003784,
|
524 |
+
"learning_rate": 3.255e-06,
|
525 |
+
"loss": 0.4112,
|
526 |
+
"step": 3350
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 266.6666666666667,
|
530 |
+
"grad_norm": 1.0072269439697266,
|
531 |
+
"learning_rate": 3.005e-06,
|
532 |
+
"loss": 0.413,
|
533 |
+
"step": 3400
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 270.5882352941176,
|
537 |
+
"grad_norm": 0.6094086170196533,
|
538 |
+
"learning_rate": 2.7550000000000003e-06,
|
539 |
+
"loss": 0.4104,
|
540 |
+
"step": 3450
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 274.5098039215686,
|
544 |
+
"grad_norm": 0.6129186749458313,
|
545 |
+
"learning_rate": 2.505e-06,
|
546 |
+
"loss": 0.4129,
|
547 |
+
"step": 3500
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 274.5098039215686,
|
551 |
+
"eval_loss": 0.39622604846954346,
|
552 |
+
"eval_runtime": 6.4203,
|
553 |
+
"eval_samples_per_second": 28.036,
|
554 |
+
"eval_steps_per_second": 3.582,
|
555 |
+
"step": 3500
|
556 |
}
|
557 |
],
|
558 |
"logging_steps": 50,
|
|
|
572 |
"attributes": {}
|
573 |
}
|
574 |
},
|
575 |
+
"total_flos": 7.616303628785914e+16,
|
576 |
"train_batch_size": 32,
|
577 |
"trial_name": null,
|
578 |
"trial_params": null
|