Upload 10 files
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +365 -5
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 20061432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d0a1a2ebc0f1f1e6bae76f519dbcc21bb42eeb93020fab49ae955c26480b74e
|
| 3 |
size 20061432
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 40205626
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a5ea25c6472ccaf3b15d44dfb9cfe3f95c2d03ee19001eee198898ac6253a32
|
| 3 |
size 40205626
|
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:c83fbbf7f760f16043b0c1585d6a2a676ee048a2decb272da8f2e2127ffb79b3
|
| 3 |
size 14244
|
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:d78a469aae0653b14dcccaea45eb52458c95afae1649e5d894a88bcf0a974d36
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "/home/nlplab5/Desktop/roberta-pretrain/ckpt/roberta/pretrain/medium/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 90,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -9583,6 +9583,366 @@
|
|
| 9583 |
"eval_samples_per_second": 457.867,
|
| 9584 |
"eval_steps_per_second": 2.045,
|
| 9585 |
"step": 11970
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9586 |
}
|
| 9587 |
],
|
| 9588 |
"logging_steps": 10,
|
|
@@ -9590,7 +9950,7 @@
|
|
| 9590 |
"num_input_tokens_seen": 0,
|
| 9591 |
"num_train_epochs": 10,
|
| 9592 |
"save_steps": 90,
|
| 9593 |
-
"total_flos": 1.
|
| 9594 |
"train_batch_size": 192,
|
| 9595 |
"trial_name": null,
|
| 9596 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.6068978309631348,
|
| 3 |
+
"best_model_checkpoint": "/home/nlplab5/Desktop/roberta-pretrain/ckpt/roberta/pretrain/medium/checkpoint-12420",
|
| 4 |
+
"epoch": 9.049218813243746,
|
| 5 |
"eval_steps": 90,
|
| 6 |
+
"global_step": 12420,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 9583 |
"eval_samples_per_second": 457.867,
|
| 9584 |
"eval_steps_per_second": 2.045,
|
| 9585 |
"step": 11970
|
| 9586 |
+
},
|
| 9587 |
+
{
|
| 9588 |
+
"epoch": 8.73,
|
| 9589 |
+
"grad_norm": 0.289413720369339,
|
| 9590 |
+
"learning_rate": 5.1485148514851485e-05,
|
| 9591 |
+
"loss": 1.758,
|
| 9592 |
+
"step": 11980
|
| 9593 |
+
},
|
| 9594 |
+
{
|
| 9595 |
+
"epoch": 8.74,
|
| 9596 |
+
"grad_norm": 0.2739205062389374,
|
| 9597 |
+
"learning_rate": 5.0495049504950497e-05,
|
| 9598 |
+
"loss": 1.7579,
|
| 9599 |
+
"step": 11990
|
| 9600 |
+
},
|
| 9601 |
+
{
|
| 9602 |
+
"epoch": 8.74,
|
| 9603 |
+
"grad_norm": 0.26597511768341064,
|
| 9604 |
+
"learning_rate": 4.950495049504951e-05,
|
| 9605 |
+
"loss": 1.7568,
|
| 9606 |
+
"step": 12000
|
| 9607 |
+
},
|
| 9608 |
+
{
|
| 9609 |
+
"epoch": 8.75,
|
| 9610 |
+
"grad_norm": 0.24635004997253418,
|
| 9611 |
+
"learning_rate": 4.851485148514852e-05,
|
| 9612 |
+
"loss": 1.7584,
|
| 9613 |
+
"step": 12010
|
| 9614 |
+
},
|
| 9615 |
+
{
|
| 9616 |
+
"epoch": 8.76,
|
| 9617 |
+
"grad_norm": 0.2534136474132538,
|
| 9618 |
+
"learning_rate": 4.7524752475247525e-05,
|
| 9619 |
+
"loss": 1.7602,
|
| 9620 |
+
"step": 12020
|
| 9621 |
+
},
|
| 9622 |
+
{
|
| 9623 |
+
"epoch": 8.77,
|
| 9624 |
+
"grad_norm": 0.26007363200187683,
|
| 9625 |
+
"learning_rate": 4.653465346534654e-05,
|
| 9626 |
+
"loss": 1.7567,
|
| 9627 |
+
"step": 12030
|
| 9628 |
+
},
|
| 9629 |
+
{
|
| 9630 |
+
"epoch": 8.77,
|
| 9631 |
+
"grad_norm": 0.2807808816432953,
|
| 9632 |
+
"learning_rate": 4.554455445544554e-05,
|
| 9633 |
+
"loss": 1.7566,
|
| 9634 |
+
"step": 12040
|
| 9635 |
+
},
|
| 9636 |
+
{
|
| 9637 |
+
"epoch": 8.78,
|
| 9638 |
+
"grad_norm": 0.2677513360977173,
|
| 9639 |
+
"learning_rate": 4.455445544554455e-05,
|
| 9640 |
+
"loss": 1.7567,
|
| 9641 |
+
"step": 12050
|
| 9642 |
+
},
|
| 9643 |
+
{
|
| 9644 |
+
"epoch": 8.79,
|
| 9645 |
+
"grad_norm": 0.2691977620124817,
|
| 9646 |
+
"learning_rate": 4.3564356435643565e-05,
|
| 9647 |
+
"loss": 1.757,
|
| 9648 |
+
"step": 12060
|
| 9649 |
+
},
|
| 9650 |
+
{
|
| 9651 |
+
"epoch": 8.79,
|
| 9652 |
+
"eval_accuracy": 0.6521601327172856,
|
| 9653 |
+
"eval_loss": 1.60829758644104,
|
| 9654 |
+
"eval_runtime": 1089.928,
|
| 9655 |
+
"eval_samples_per_second": 458.177,
|
| 9656 |
+
"eval_steps_per_second": 2.046,
|
| 9657 |
+
"step": 12060
|
| 9658 |
+
},
|
| 9659 |
+
{
|
| 9660 |
+
"epoch": 8.79,
|
| 9661 |
+
"grad_norm": 0.2577356696128845,
|
| 9662 |
+
"learning_rate": 4.257425742574258e-05,
|
| 9663 |
+
"loss": 1.7584,
|
| 9664 |
+
"step": 12070
|
| 9665 |
+
},
|
| 9666 |
+
{
|
| 9667 |
+
"epoch": 8.8,
|
| 9668 |
+
"grad_norm": 0.2654874324798584,
|
| 9669 |
+
"learning_rate": 4.158415841584159e-05,
|
| 9670 |
+
"loss": 1.7571,
|
| 9671 |
+
"step": 12080
|
| 9672 |
+
},
|
| 9673 |
+
{
|
| 9674 |
+
"epoch": 8.81,
|
| 9675 |
+
"grad_norm": 0.25344353914260864,
|
| 9676 |
+
"learning_rate": 4.0594059405940594e-05,
|
| 9677 |
+
"loss": 1.7581,
|
| 9678 |
+
"step": 12090
|
| 9679 |
+
},
|
| 9680 |
+
{
|
| 9681 |
+
"epoch": 8.82,
|
| 9682 |
+
"grad_norm": 0.25865158438682556,
|
| 9683 |
+
"learning_rate": 3.9603960396039605e-05,
|
| 9684 |
+
"loss": 1.7552,
|
| 9685 |
+
"step": 12100
|
| 9686 |
+
},
|
| 9687 |
+
{
|
| 9688 |
+
"epoch": 8.82,
|
| 9689 |
+
"grad_norm": 0.28875982761383057,
|
| 9690 |
+
"learning_rate": 3.861386138613862e-05,
|
| 9691 |
+
"loss": 1.757,
|
| 9692 |
+
"step": 12110
|
| 9693 |
+
},
|
| 9694 |
+
{
|
| 9695 |
+
"epoch": 8.83,
|
| 9696 |
+
"grad_norm": 0.2697414755821228,
|
| 9697 |
+
"learning_rate": 3.762376237623762e-05,
|
| 9698 |
+
"loss": 1.7579,
|
| 9699 |
+
"step": 12120
|
| 9700 |
+
},
|
| 9701 |
+
{
|
| 9702 |
+
"epoch": 8.84,
|
| 9703 |
+
"grad_norm": 0.2786589562892914,
|
| 9704 |
+
"learning_rate": 3.6633663366336634e-05,
|
| 9705 |
+
"loss": 1.7583,
|
| 9706 |
+
"step": 12130
|
| 9707 |
+
},
|
| 9708 |
+
{
|
| 9709 |
+
"epoch": 8.85,
|
| 9710 |
+
"grad_norm": 0.258486270904541,
|
| 9711 |
+
"learning_rate": 3.564356435643564e-05,
|
| 9712 |
+
"loss": 1.7581,
|
| 9713 |
+
"step": 12140
|
| 9714 |
+
},
|
| 9715 |
+
{
|
| 9716 |
+
"epoch": 8.85,
|
| 9717 |
+
"grad_norm": 0.2595365345478058,
|
| 9718 |
+
"learning_rate": 3.465346534653466e-05,
|
| 9719 |
+
"loss": 1.757,
|
| 9720 |
+
"step": 12150
|
| 9721 |
+
},
|
| 9722 |
+
{
|
| 9723 |
+
"epoch": 8.85,
|
| 9724 |
+
"eval_accuracy": 0.652040482066107,
|
| 9725 |
+
"eval_loss": 1.6086018085479736,
|
| 9726 |
+
"eval_runtime": 1089.5635,
|
| 9727 |
+
"eval_samples_per_second": 458.33,
|
| 9728 |
+
"eval_steps_per_second": 2.047,
|
| 9729 |
+
"step": 12150
|
| 9730 |
+
},
|
| 9731 |
+
{
|
| 9732 |
+
"epoch": 8.86,
|
| 9733 |
+
"grad_norm": 0.25674012303352356,
|
| 9734 |
+
"learning_rate": 3.366336633663367e-05,
|
| 9735 |
+
"loss": 1.7595,
|
| 9736 |
+
"step": 12160
|
| 9737 |
+
},
|
| 9738 |
+
{
|
| 9739 |
+
"epoch": 8.87,
|
| 9740 |
+
"grad_norm": 0.23194921016693115,
|
| 9741 |
+
"learning_rate": 3.2673267326732674e-05,
|
| 9742 |
+
"loss": 1.7574,
|
| 9743 |
+
"step": 12170
|
| 9744 |
+
},
|
| 9745 |
+
{
|
| 9746 |
+
"epoch": 8.87,
|
| 9747 |
+
"grad_norm": 0.2626875936985016,
|
| 9748 |
+
"learning_rate": 3.1683168316831686e-05,
|
| 9749 |
+
"loss": 1.7571,
|
| 9750 |
+
"step": 12180
|
| 9751 |
+
},
|
| 9752 |
+
{
|
| 9753 |
+
"epoch": 8.88,
|
| 9754 |
+
"grad_norm": 0.2361476868391037,
|
| 9755 |
+
"learning_rate": 3.069306930693069e-05,
|
| 9756 |
+
"loss": 1.7573,
|
| 9757 |
+
"step": 12190
|
| 9758 |
+
},
|
| 9759 |
+
{
|
| 9760 |
+
"epoch": 8.89,
|
| 9761 |
+
"grad_norm": 0.2606755793094635,
|
| 9762 |
+
"learning_rate": 2.9702970297029702e-05,
|
| 9763 |
+
"loss": 1.7567,
|
| 9764 |
+
"step": 12200
|
| 9765 |
+
},
|
| 9766 |
+
{
|
| 9767 |
+
"epoch": 8.9,
|
| 9768 |
+
"grad_norm": 0.27499887347221375,
|
| 9769 |
+
"learning_rate": 2.8712871287128714e-05,
|
| 9770 |
+
"loss": 1.7579,
|
| 9771 |
+
"step": 12210
|
| 9772 |
+
},
|
| 9773 |
+
{
|
| 9774 |
+
"epoch": 8.9,
|
| 9775 |
+
"grad_norm": 0.24832656979560852,
|
| 9776 |
+
"learning_rate": 2.7722772277227722e-05,
|
| 9777 |
+
"loss": 1.7566,
|
| 9778 |
+
"step": 12220
|
| 9779 |
+
},
|
| 9780 |
+
{
|
| 9781 |
+
"epoch": 8.91,
|
| 9782 |
+
"grad_norm": 0.24898388981819153,
|
| 9783 |
+
"learning_rate": 2.6732673267326734e-05,
|
| 9784 |
+
"loss": 1.7544,
|
| 9785 |
+
"step": 12230
|
| 9786 |
+
},
|
| 9787 |
+
{
|
| 9788 |
+
"epoch": 8.92,
|
| 9789 |
+
"grad_norm": 0.24266423285007477,
|
| 9790 |
+
"learning_rate": 2.5742574257425742e-05,
|
| 9791 |
+
"loss": 1.7559,
|
| 9792 |
+
"step": 12240
|
| 9793 |
+
},
|
| 9794 |
+
{
|
| 9795 |
+
"epoch": 8.92,
|
| 9796 |
+
"eval_accuracy": 0.6522573824099933,
|
| 9797 |
+
"eval_loss": 1.6079708337783813,
|
| 9798 |
+
"eval_runtime": 1089.9176,
|
| 9799 |
+
"eval_samples_per_second": 458.181,
|
| 9800 |
+
"eval_steps_per_second": 2.046,
|
| 9801 |
+
"step": 12240
|
| 9802 |
+
},
|
| 9803 |
+
{
|
| 9804 |
+
"epoch": 8.93,
|
| 9805 |
+
"grad_norm": 0.2438860386610031,
|
| 9806 |
+
"learning_rate": 2.4752475247524754e-05,
|
| 9807 |
+
"loss": 1.7554,
|
| 9808 |
+
"step": 12250
|
| 9809 |
+
},
|
| 9810 |
+
{
|
| 9811 |
+
"epoch": 8.93,
|
| 9812 |
+
"grad_norm": 0.22911418974399567,
|
| 9813 |
+
"learning_rate": 2.3762376237623762e-05,
|
| 9814 |
+
"loss": 1.7547,
|
| 9815 |
+
"step": 12260
|
| 9816 |
+
},
|
| 9817 |
+
{
|
| 9818 |
+
"epoch": 8.94,
|
| 9819 |
+
"grad_norm": 0.2550877034664154,
|
| 9820 |
+
"learning_rate": 2.277227722772277e-05,
|
| 9821 |
+
"loss": 1.7567,
|
| 9822 |
+
"step": 12270
|
| 9823 |
+
},
|
| 9824 |
+
{
|
| 9825 |
+
"epoch": 8.95,
|
| 9826 |
+
"grad_norm": 0.2409505546092987,
|
| 9827 |
+
"learning_rate": 2.1782178217821783e-05,
|
| 9828 |
+
"loss": 1.7556,
|
| 9829 |
+
"step": 12280
|
| 9830 |
+
},
|
| 9831 |
+
{
|
| 9832 |
+
"epoch": 8.95,
|
| 9833 |
+
"grad_norm": 0.23632997274398804,
|
| 9834 |
+
"learning_rate": 2.0792079207920794e-05,
|
| 9835 |
+
"loss": 1.7573,
|
| 9836 |
+
"step": 12290
|
| 9837 |
+
},
|
| 9838 |
+
{
|
| 9839 |
+
"epoch": 8.96,
|
| 9840 |
+
"grad_norm": 0.22292740643024445,
|
| 9841 |
+
"learning_rate": 1.9801980198019803e-05,
|
| 9842 |
+
"loss": 1.757,
|
| 9843 |
+
"step": 12300
|
| 9844 |
+
},
|
| 9845 |
+
{
|
| 9846 |
+
"epoch": 8.97,
|
| 9847 |
+
"grad_norm": 0.2350420504808426,
|
| 9848 |
+
"learning_rate": 1.881188118811881e-05,
|
| 9849 |
+
"loss": 1.756,
|
| 9850 |
+
"step": 12310
|
| 9851 |
+
},
|
| 9852 |
+
{
|
| 9853 |
+
"epoch": 8.98,
|
| 9854 |
+
"grad_norm": 0.22938278317451477,
|
| 9855 |
+
"learning_rate": 1.782178217821782e-05,
|
| 9856 |
+
"loss": 1.7562,
|
| 9857 |
+
"step": 12320
|
| 9858 |
+
},
|
| 9859 |
+
{
|
| 9860 |
+
"epoch": 8.98,
|
| 9861 |
+
"grad_norm": 0.2246268391609192,
|
| 9862 |
+
"learning_rate": 1.6831683168316834e-05,
|
| 9863 |
+
"loss": 1.7556,
|
| 9864 |
+
"step": 12330
|
| 9865 |
+
},
|
| 9866 |
+
{
|
| 9867 |
+
"epoch": 8.98,
|
| 9868 |
+
"eval_accuracy": 0.652376308176148,
|
| 9869 |
+
"eval_loss": 1.6073620319366455,
|
| 9870 |
+
"eval_runtime": 1088.9818,
|
| 9871 |
+
"eval_samples_per_second": 458.575,
|
| 9872 |
+
"eval_steps_per_second": 2.048,
|
| 9873 |
+
"step": 12330
|
| 9874 |
+
},
|
| 9875 |
+
{
|
| 9876 |
+
"epoch": 8.99,
|
| 9877 |
+
"grad_norm": 0.22820483148097992,
|
| 9878 |
+
"learning_rate": 1.5841584158415843e-05,
|
| 9879 |
+
"loss": 1.7564,
|
| 9880 |
+
"step": 12340
|
| 9881 |
+
},
|
| 9882 |
+
{
|
| 9883 |
+
"epoch": 9.0,
|
| 9884 |
+
"grad_norm": 0.2315167486667633,
|
| 9885 |
+
"learning_rate": 1.4851485148514851e-05,
|
| 9886 |
+
"loss": 1.7558,
|
| 9887 |
+
"step": 12350
|
| 9888 |
+
},
|
| 9889 |
+
{
|
| 9890 |
+
"epoch": 9.01,
|
| 9891 |
+
"grad_norm": 0.21513350307941437,
|
| 9892 |
+
"learning_rate": 1.3861386138613861e-05,
|
| 9893 |
+
"loss": 1.757,
|
| 9894 |
+
"step": 12360
|
| 9895 |
+
},
|
| 9896 |
+
{
|
| 9897 |
+
"epoch": 9.01,
|
| 9898 |
+
"grad_norm": 0.21538245677947998,
|
| 9899 |
+
"learning_rate": 1.2871287128712871e-05,
|
| 9900 |
+
"loss": 1.7527,
|
| 9901 |
+
"step": 12370
|
| 9902 |
+
},
|
| 9903 |
+
{
|
| 9904 |
+
"epoch": 9.02,
|
| 9905 |
+
"grad_norm": 0.22796376049518585,
|
| 9906 |
+
"learning_rate": 1.1881188118811881e-05,
|
| 9907 |
+
"loss": 1.7549,
|
| 9908 |
+
"step": 12380
|
| 9909 |
+
},
|
| 9910 |
+
{
|
| 9911 |
+
"epoch": 9.03,
|
| 9912 |
+
"grad_norm": 0.21846508979797363,
|
| 9913 |
+
"learning_rate": 1.0891089108910891e-05,
|
| 9914 |
+
"loss": 1.7527,
|
| 9915 |
+
"step": 12390
|
| 9916 |
+
},
|
| 9917 |
+
{
|
| 9918 |
+
"epoch": 9.03,
|
| 9919 |
+
"grad_norm": 0.2252340316772461,
|
| 9920 |
+
"learning_rate": 9.900990099009901e-06,
|
| 9921 |
+
"loss": 1.757,
|
| 9922 |
+
"step": 12400
|
| 9923 |
+
},
|
| 9924 |
+
{
|
| 9925 |
+
"epoch": 9.04,
|
| 9926 |
+
"grad_norm": 0.22679966688156128,
|
| 9927 |
+
"learning_rate": 8.91089108910891e-06,
|
| 9928 |
+
"loss": 1.7547,
|
| 9929 |
+
"step": 12410
|
| 9930 |
+
},
|
| 9931 |
+
{
|
| 9932 |
+
"epoch": 9.05,
|
| 9933 |
+
"grad_norm": 0.21749068796634674,
|
| 9934 |
+
"learning_rate": 7.920792079207921e-06,
|
| 9935 |
+
"loss": 1.755,
|
| 9936 |
+
"step": 12420
|
| 9937 |
+
},
|
| 9938 |
+
{
|
| 9939 |
+
"epoch": 9.05,
|
| 9940 |
+
"eval_accuracy": 0.6525192559694988,
|
| 9941 |
+
"eval_loss": 1.6068978309631348,
|
| 9942 |
+
"eval_runtime": 1087.147,
|
| 9943 |
+
"eval_samples_per_second": 459.349,
|
| 9944 |
+
"eval_steps_per_second": 2.051,
|
| 9945 |
+
"step": 12420
|
| 9946 |
}
|
| 9947 |
],
|
| 9948 |
"logging_steps": 10,
|
|
|
|
| 9950 |
"num_input_tokens_seen": 0,
|
| 9951 |
"num_train_epochs": 10,
|
| 9952 |
"save_steps": 90,
|
| 9953 |
+
"total_flos": 1.28938481325833e+18,
|
| 9954 |
"train_batch_size": 192,
|
| 9955 |
"trial_name": null,
|
| 9956 |
"trial_params": null
|