Commit
·
ff7c133
1
Parent(s):
79978f0
huggingartists
Browse files- README.md +3 -3
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +2 -2
- scheduler.pt +1 -1
- trainer_state.json +561 -7
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
| 45 |
dataset = load_dataset("huggingartists/eminem")
|
| 46 |
```
|
| 47 |
|
| 48 |
-
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Eminem's lyrics.
|
| 53 |
|
| 54 |
-
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 55 |
|
| 56 |
-
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
|
|
|
| 45 |
dataset = load_dataset("huggingartists/eminem")
|
| 46 |
```
|
| 47 |
|
| 48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/316hyhlv/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
|
| 49 |
|
| 50 |
## Training procedure
|
| 51 |
|
| 52 |
The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Eminem's lyrics.
|
| 53 |
|
| 54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/37sdud3t) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/37sdud3t/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss":
|
|
|
|
| 1 |
+
{"eval_loss": 2.974085807800293, "eval_runtime": 28.0005, "eval_samples_per_second": 22.678, "eval_steps_per_second": 2.857, "epoch": 2.0}
|
flax_model.msgpack
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 497764120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3907d0d84fa2ea31b5f540749a121d2ccae6bdffa40d285c0dd1c6e8a3d1eb5
|
| 3 |
size 497764120
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 995604017
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b42a4e5be714fffe89fe58e4c384fa83aa9a91b4f05c3000d0ed5c42594f3edb
|
| 3 |
size 995604017
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 510403817
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a39907257eaed13ac218045b05181c72e468279a213562df24faf37a83ab079
|
| 3 |
size 510403817
|
rng_state.pth
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 sha256:03abbc1c05b5863d5a35d3b6be24f3f8cbbd22f05cd95cf6116141f0f3443282
|
| 3 |
+
size 14439
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 623
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bc5e07657bae6ba3ef6e18715e0dec58b1f9fe25e3657199acfbf39f7881854
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "output/eminem/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -560,11 +560,565 @@
|
|
| 560 |
"eval_samples_per_second": 22.102,
|
| 561 |
"eval_steps_per_second": 2.767,
|
| 562 |
"step": 458
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 563 |
}
|
| 564 |
],
|
| 565 |
-
"max_steps":
|
| 566 |
-
"num_train_epochs":
|
| 567 |
-
"total_flos":
|
| 568 |
"trial_name": null,
|
| 569 |
"trial_params": null
|
| 570 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.974085807800293,
|
| 3 |
+
"best_model_checkpoint": "output/eminem/checkpoint-912",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 912,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 560 |
"eval_samples_per_second": 22.102,
|
| 561 |
"eval_steps_per_second": 2.767,
|
| 562 |
"step": 458
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.01,
|
| 566 |
+
"learning_rate": 2.3430377974244087e-07,
|
| 567 |
+
"loss": 2.7959,
|
| 568 |
+
"step": 460
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.02,
|
| 572 |
+
"learning_rate": 4.699650061055066e-07,
|
| 573 |
+
"loss": 2.9272,
|
| 574 |
+
"step": 465
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.03,
|
| 578 |
+
"learning_rate": 7.864624037173071e-07,
|
| 579 |
+
"loss": 2.9085,
|
| 580 |
+
"step": 470
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.04,
|
| 584 |
+
"learning_rate": 1.183420448951144e-06,
|
| 585 |
+
"loss": 3.0019,
|
| 586 |
+
"step": 475
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.05,
|
| 590 |
+
"learning_rate": 1.6603681517579088e-06,
|
| 591 |
+
"loss": 2.8095,
|
| 592 |
+
"step": 480
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.06,
|
| 596 |
+
"learning_rate": 2.2167396144952024e-06,
|
| 597 |
+
"loss": 3.0455,
|
| 598 |
+
"step": 485
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.07,
|
| 602 |
+
"learning_rate": 2.8518747033638413e-06,
|
| 603 |
+
"loss": 3.1364,
|
| 604 |
+
"step": 490
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.09,
|
| 608 |
+
"learning_rate": 3.565019831655484e-06,
|
| 609 |
+
"loss": 2.7774,
|
| 610 |
+
"step": 495
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.1,
|
| 614 |
+
"learning_rate": 4.355328853882044e-06,
|
| 615 |
+
"loss": 3.113,
|
| 616 |
+
"step": 500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.11,
|
| 620 |
+
"learning_rate": 5.221864069725677e-06,
|
| 621 |
+
"loss": 2.8707,
|
| 622 |
+
"step": 505
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.12,
|
| 626 |
+
"learning_rate": 6.163597336619081e-06,
|
| 627 |
+
"loss": 2.7314,
|
| 628 |
+
"step": 510
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.13,
|
| 632 |
+
"learning_rate": 7.17941128963425e-06,
|
| 633 |
+
"loss": 3.0188,
|
| 634 |
+
"step": 515
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.14,
|
| 638 |
+
"learning_rate": 8.268100667234818e-06,
|
| 639 |
+
"loss": 2.9475,
|
| 640 |
+
"step": 520
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.15,
|
| 644 |
+
"learning_rate": 9.428373741316158e-06,
|
| 645 |
+
"loss": 3.002,
|
| 646 |
+
"step": 525
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.16,
|
| 650 |
+
"learning_rate": 1.0658853849838848e-05,
|
| 651 |
+
"loss": 3.1303,
|
| 652 |
+
"step": 530
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.17,
|
| 656 |
+
"learning_rate": 1.1958081030236264e-05,
|
| 657 |
+
"loss": 3.0132,
|
| 658 |
+
"step": 535
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.18,
|
| 662 |
+
"learning_rate": 1.3324513751656961e-05,
|
| 663 |
+
"loss": 3.0101,
|
| 664 |
+
"step": 540
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.2,
|
| 668 |
+
"learning_rate": 1.4756530743988715e-05,
|
| 669 |
+
"loss": 2.8486,
|
| 670 |
+
"step": 545
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.21,
|
| 674 |
+
"learning_rate": 1.6252432921493314e-05,
|
| 675 |
+
"loss": 2.9874,
|
| 676 |
+
"step": 550
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.22,
|
| 680 |
+
"learning_rate": 1.7810445398767802e-05,
|
| 681 |
+
"loss": 3.0359,
|
| 682 |
+
"step": 555
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.23,
|
| 686 |
+
"learning_rate": 1.9428719596644263e-05,
|
| 687 |
+
"loss": 3.0193,
|
| 688 |
+
"step": 560
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.24,
|
| 692 |
+
"learning_rate": 2.1105335435524594e-05,
|
| 693 |
+
"loss": 3.1116,
|
| 694 |
+
"step": 565
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.25,
|
| 698 |
+
"learning_rate": 2.2838303613553045e-05,
|
| 699 |
+
"loss": 2.9757,
|
| 700 |
+
"step": 570
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.26,
|
| 704 |
+
"learning_rate": 2.4625567966918084e-05,
|
| 705 |
+
"loss": 3.1412,
|
| 706 |
+
"step": 575
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.27,
|
| 710 |
+
"learning_rate": 2.646500790948875e-05,
|
| 711 |
+
"loss": 2.9872,
|
| 712 |
+
"step": 580
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.28,
|
| 716 |
+
"learning_rate": 2.8354440948885004e-05,
|
| 717 |
+
"loss": 2.9237,
|
| 718 |
+
"step": 585
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.29,
|
| 722 |
+
"learning_rate": 3.0291625276002797e-05,
|
| 723 |
+
"loss": 2.9595,
|
| 724 |
+
"step": 590
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.3,
|
| 728 |
+
"learning_rate": 3.22742624249154e-05,
|
| 729 |
+
"loss": 3.0059,
|
| 730 |
+
"step": 595
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.32,
|
| 734 |
+
"learning_rate": 3.429999999999989e-05,
|
| 735 |
+
"loss": 3.1845,
|
| 736 |
+
"step": 600
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.33,
|
| 740 |
+
"learning_rate": 3.6366434467051275e-05,
|
| 741 |
+
"loss": 2.8852,
|
| 742 |
+
"step": 605
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.34,
|
| 746 |
+
"learning_rate": 3.8471114005070465e-05,
|
| 747 |
+
"loss": 3.2446,
|
| 748 |
+
"step": 610
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.35,
|
| 752 |
+
"learning_rate": 4.061154141534634e-05,
|
| 753 |
+
"loss": 2.9609,
|
| 754 |
+
"step": 615
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.36,
|
| 758 |
+
"learning_rate": 4.278517708437853e-05,
|
| 759 |
+
"loss": 2.8409,
|
| 760 |
+
"step": 620
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.37,
|
| 764 |
+
"learning_rate": 4.498944199712314e-05,
|
| 765 |
+
"loss": 3.0191,
|
| 766 |
+
"step": 625
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.38,
|
| 770 |
+
"learning_rate": 4.722172079699043e-05,
|
| 771 |
+
"loss": 3.0244,
|
| 772 |
+
"step": 630
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.39,
|
| 776 |
+
"learning_rate": 4.9479364888961465e-05,
|
| 777 |
+
"loss": 2.9291,
|
| 778 |
+
"step": 635
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.4,
|
| 782 |
+
"learning_rate": 5.1759695582141145e-05,
|
| 783 |
+
"loss": 3.0212,
|
| 784 |
+
"step": 640
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.41,
|
| 788 |
+
"learning_rate": 5.40600072680197e-05,
|
| 789 |
+
"loss": 2.8915,
|
| 790 |
+
"step": 645
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.43,
|
| 794 |
+
"learning_rate": 5.637757063067428e-05,
|
| 795 |
+
"loss": 3.0374,
|
| 796 |
+
"step": 650
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.44,
|
| 800 |
+
"learning_rate": 5.87096358850958e-05,
|
| 801 |
+
"loss": 3.0343,
|
| 802 |
+
"step": 655
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.45,
|
| 806 |
+
"learning_rate": 6.105343603980605e-05,
|
| 807 |
+
"loss": 3.0016,
|
| 808 |
+
"step": 660
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.46,
|
| 812 |
+
"learning_rate": 6.34061901798868e-05,
|
| 813 |
+
"loss": 3.0565,
|
| 814 |
+
"step": 665
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.47,
|
| 818 |
+
"learning_rate": 6.576510676653128e-05,
|
| 819 |
+
"loss": 2.9675,
|
| 820 |
+
"step": 670
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 1.48,
|
| 824 |
+
"learning_rate": 6.812738694920105e-05,
|
| 825 |
+
"loss": 2.9261,
|
| 826 |
+
"step": 675
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.49,
|
| 830 |
+
"learning_rate": 7.049022788645597e-05,
|
| 831 |
+
"loss": 3.1299,
|
| 832 |
+
"step": 680
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 1.5,
|
| 836 |
+
"learning_rate": 7.285082607152151e-05,
|
| 837 |
+
"loss": 2.9347,
|
| 838 |
+
"step": 685
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.51,
|
| 842 |
+
"learning_rate": 7.520638065864555e-05,
|
| 843 |
+
"loss": 3.1446,
|
| 844 |
+
"step": 690
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 1.52,
|
| 848 |
+
"learning_rate": 7.755409678629566e-05,
|
| 849 |
+
"loss": 3.1137,
|
| 850 |
+
"step": 695
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.54,
|
| 854 |
+
"learning_rate": 7.989118889325833e-05,
|
| 855 |
+
"loss": 3.2962,
|
| 856 |
+
"step": 700
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.55,
|
| 860 |
+
"learning_rate": 8.22148840237031e-05,
|
| 861 |
+
"loss": 3.072,
|
| 862 |
+
"step": 705
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 1.56,
|
| 866 |
+
"learning_rate": 8.452242511728945e-05,
|
| 867 |
+
"loss": 3.1619,
|
| 868 |
+
"step": 710
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.57,
|
| 872 |
+
"learning_rate": 8.681107428041357e-05,
|
| 873 |
+
"loss": 3.1189,
|
| 874 |
+
"step": 715
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.58,
|
| 878 |
+
"learning_rate": 8.907811603471617e-05,
|
| 879 |
+
"loss": 2.989,
|
| 880 |
+
"step": 720
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 1.59,
|
| 884 |
+
"learning_rate": 9.132086053899117e-05,
|
| 885 |
+
"loss": 3.1561,
|
| 886 |
+
"step": 725
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.6,
|
| 890 |
+
"learning_rate": 9.353664678067862e-05,
|
| 891 |
+
"loss": 3.0616,
|
| 892 |
+
"step": 730
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.61,
|
| 896 |
+
"learning_rate": 9.572284573315215e-05,
|
| 897 |
+
"loss": 3.0366,
|
| 898 |
+
"step": 735
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.62,
|
| 902 |
+
"learning_rate": 9.787686347505336e-05,
|
| 903 |
+
"loss": 3.1121,
|
| 904 |
+
"step": 740
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.63,
|
| 908 |
+
"learning_rate": 9.999614426797571e-05,
|
| 909 |
+
"loss": 3.1418,
|
| 910 |
+
"step": 745
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.64,
|
| 914 |
+
"learning_rate": 0.0001020781735888445,
|
| 915 |
+
"loss": 3.1414,
|
| 916 |
+
"step": 750
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.66,
|
| 920 |
+
"learning_rate": 0.00010412048111339278,
|
| 921 |
+
"loss": 2.9303,
|
| 922 |
+
"step": 755
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.67,
|
| 926 |
+
"learning_rate": 0.0001061206436471985,
|
| 927 |
+
"loss": 3.125,
|
| 928 |
+
"step": 760
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.68,
|
| 932 |
+
"learning_rate": 0.00010807628800079923,
|
| 933 |
+
"loss": 2.9598,
|
| 934 |
+
"step": 765
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.69,
|
| 938 |
+
"learning_rate": 0.0001099850938054781,
|
| 939 |
+
"loss": 3.1258,
|
| 940 |
+
"step": 770
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.7,
|
| 944 |
+
"learning_rate": 0.00011184479626637759,
|
| 945 |
+
"loss": 3.0221,
|
| 946 |
+
"step": 775
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.71,
|
| 950 |
+
"learning_rate": 0.00011365318884967452,
|
| 951 |
+
"loss": 3.1814,
|
| 952 |
+
"step": 780
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 1.72,
|
| 956 |
+
"learning_rate": 0.00011540812590062814,
|
| 957 |
+
"loss": 3.0323,
|
| 958 |
+
"step": 785
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.73,
|
| 962 |
+
"learning_rate": 0.00011710752518939709,
|
| 963 |
+
"loss": 3.1137,
|
| 964 |
+
"step": 790
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 1.74,
|
| 968 |
+
"learning_rate": 0.0001187493703816003,
|
| 969 |
+
"loss": 3.0927,
|
| 970 |
+
"step": 795
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.75,
|
| 974 |
+
"learning_rate": 0.000120331713430695,
|
| 975 |
+
"loss": 2.9943,
|
| 976 |
+
"step": 800
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.77,
|
| 980 |
+
"learning_rate": 0.00012185267688933093,
|
| 981 |
+
"loss": 3.0428,
|
| 982 |
+
"step": 805
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.78,
|
| 986 |
+
"learning_rate": 0.00012331045613693767,
|
| 987 |
+
"loss": 3.1162,
|
| 988 |
+
"step": 810
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.79,
|
| 992 |
+
"learning_rate": 0.00012470332152090424,
|
| 993 |
+
"loss": 3.1383,
|
| 994 |
+
"step": 815
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.8,
|
| 998 |
+
"learning_rate": 0.00012602962040880947,
|
| 999 |
+
"loss": 3.1232,
|
| 1000 |
+
"step": 820
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.81,
|
| 1004 |
+
"learning_rate": 0.00012728777914926677,
|
| 1005 |
+
"loss": 2.9116,
|
| 1006 |
+
"step": 825
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.82,
|
| 1010 |
+
"learning_rate": 0.00012847630493905912,
|
| 1011 |
+
"loss": 3.0001,
|
| 1012 |
+
"step": 830
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.83,
|
| 1016 |
+
"learning_rate": 0.00012959378759434817,
|
| 1017 |
+
"loss": 2.8663,
|
| 1018 |
+
"step": 835
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.84,
|
| 1022 |
+
"learning_rate": 0.0001306389012238538,
|
| 1023 |
+
"loss": 3.0282,
|
| 1024 |
+
"step": 840
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.85,
|
| 1028 |
+
"learning_rate": 0.00013161040580202303,
|
| 1029 |
+
"loss": 3.0839,
|
| 1030 |
+
"step": 845
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.86,
|
| 1034 |
+
"learning_rate": 0.0001325071486403177,
|
| 1035 |
+
"loss": 3.0281,
|
| 1036 |
+
"step": 850
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 1.88,
|
| 1040 |
+
"learning_rate": 0.00013332806575487718,
|
| 1041 |
+
"loss": 2.8984,
|
| 1042 |
+
"step": 855
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.89,
|
| 1046 |
+
"learning_rate": 0.00013407218312893416,
|
| 1047 |
+
"loss": 3.014,
|
| 1048 |
+
"step": 860
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.9,
|
| 1052 |
+
"learning_rate": 0.00013473861786848323,
|
| 1053 |
+
"loss": 3.105,
|
| 1054 |
+
"step": 865
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 1.91,
|
| 1058 |
+
"learning_rate": 0.00013532657924983344,
|
| 1059 |
+
"loss": 3.075,
|
| 1060 |
+
"step": 870
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.92,
|
| 1064 |
+
"learning_rate": 0.0001358353696578007,
|
| 1065 |
+
"loss": 3.1963,
|
| 1066 |
+
"step": 875
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.93,
|
| 1070 |
+
"learning_rate": 0.00013626438541342677,
|
| 1071 |
+
"loss": 3.2466,
|
| 1072 |
+
"step": 880
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.94,
|
| 1076 |
+
"learning_rate": 0.0001366131174902434,
|
| 1077 |
+
"loss": 3.0784,
|
| 1078 |
+
"step": 885
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 1.95,
|
| 1082 |
+
"learning_rate": 0.00013688115211823152,
|
| 1083 |
+
"loss": 3.1067,
|
| 1084 |
+
"step": 890
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.96,
|
| 1088 |
+
"learning_rate": 0.00013706817127475857,
|
| 1089 |
+
"loss": 2.7045,
|
| 1090 |
+
"step": 895
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.97,
|
| 1094 |
+
"learning_rate": 0.00013717395306191168,
|
| 1095 |
+
"loss": 2.9886,
|
| 1096 |
+
"step": 900
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.98,
|
| 1100 |
+
"learning_rate": 0.00013719837196977938,
|
| 1101 |
+
"loss": 3.1332,
|
| 1102 |
+
"step": 905
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.0,
|
| 1106 |
+
"learning_rate": 0.00013714139902536884,
|
| 1107 |
+
"loss": 3.2141,
|
| 1108 |
+
"step": 910
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.0,
|
| 1112 |
+
"eval_loss": 2.974085807800293,
|
| 1113 |
+
"eval_runtime": 27.8918,
|
| 1114 |
+
"eval_samples_per_second": 22.767,
|
| 1115 |
+
"eval_steps_per_second": 2.868,
|
| 1116 |
+
"step": 912
|
| 1117 |
}
|
| 1118 |
],
|
| 1119 |
+
"max_steps": 912,
|
| 1120 |
+
"num_train_epochs": 2,
|
| 1121 |
+
"total_flos": 952148164608000.0,
|
| 1122 |
"trial_name": null,
|
| 1123 |
"trial_params": null
|
| 1124 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2671
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a7f4aa24de6bd1ce325fdc5850024a8dc7203da31346e260d5aa32184758fb6
|
| 3 |
size 2671
|