Commit ·
ead4f2b
1
Parent(s): 87b9240
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 +1 -1
- scheduler.pt +1 -1
- trainer_state.json +553 -5
- 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/2h8vhx6h/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/pgt39elq) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/pgt39elq/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 0.
|
|
|
|
| 1 |
+
{"eval_loss": 0.16843362152576447, "eval_runtime": 14.4995, "eval_samples_per_second": 46.002, "eval_steps_per_second": 5.793, "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 sha256:4cbc2dc6c04035b853abb568761bd8612c26a994ae1b4cb08ca188a90f7258f7
|
| 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:b0b0ffb22e8927b64da356533cf5641440c81b02790d88dfdd9c9a2662c01425
|
| 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 510396521
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dea39169802d87733535e8d73438aea36ade457c6da7d750e53cf28cf547775e
|
| 3 |
size 510396521
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14567
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b13d0791a1d73977e6a5d1788aa28b8116f3253e4dd3057d9f0de48e5eb2ad9b
|
| 3 |
size 14567
|
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:abd9b10a0f69d3f57880116c4b912f46c3554e429f40c6e581557f00b105907d
|
| 3 |
size 623
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 0.
|
| 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,
|
|
@@ -554,11 +554,559 @@
|
|
| 554 |
"eval_samples_per_second": 41.79,
|
| 555 |
"eval_steps_per_second": 5.271,
|
| 556 |
"step": 452
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 557 |
}
|
| 558 |
],
|
| 559 |
"max_steps": 904,
|
| 560 |
"num_train_epochs": 2,
|
| 561 |
-
"total_flos":
|
| 562 |
"trial_name": null,
|
| 563 |
"trial_params": null
|
| 564 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.16843362152576447,
|
| 3 |
+
"best_model_checkpoint": "output/eminem/checkpoint-904",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 904,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 554 |
"eval_samples_per_second": 41.79,
|
| 555 |
"eval_steps_per_second": 5.271,
|
| 556 |
"step": 452
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.01,
|
| 560 |
+
"learning_rate": 5.486625907525938e-05,
|
| 561 |
+
"loss": 0.3706,
|
| 562 |
+
"step": 455
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.02,
|
| 566 |
+
"learning_rate": 5.7209813478478894e-05,
|
| 567 |
+
"loss": 0.3441,
|
| 568 |
+
"step": 460
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.03,
|
| 572 |
+
"learning_rate": 5.956712254650734e-05,
|
| 573 |
+
"loss": 0.336,
|
| 574 |
+
"step": 465
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.04,
|
| 578 |
+
"learning_rate": 6.193533961866664e-05,
|
| 579 |
+
"loss": 0.3351,
|
| 580 |
+
"step": 470
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.05,
|
| 584 |
+
"learning_rate": 6.431160486189602e-05,
|
| 585 |
+
"loss": 0.379,
|
| 586 |
+
"step": 475
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.06,
|
| 590 |
+
"learning_rate": 6.669304872424543e-05,
|
| 591 |
+
"loss": 0.348,
|
| 592 |
+
"step": 480
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.07,
|
| 596 |
+
"learning_rate": 6.907679540012287e-05,
|
| 597 |
+
"loss": 0.3403,
|
| 598 |
+
"step": 485
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.08,
|
| 602 |
+
"learning_rate": 7.145996630308584e-05,
|
| 603 |
+
"loss": 0.3578,
|
| 604 |
+
"step": 490
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.1,
|
| 608 |
+
"learning_rate": 7.383968354198309e-05,
|
| 609 |
+
"loss": 0.313,
|
| 610 |
+
"step": 495
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.11,
|
| 614 |
+
"learning_rate": 7.621307339627422e-05,
|
| 615 |
+
"loss": 0.3456,
|
| 616 |
+
"step": 500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.12,
|
| 620 |
+
"learning_rate": 7.857726978630327e-05,
|
| 621 |
+
"loss": 0.3309,
|
| 622 |
+
"step": 505
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.13,
|
| 626 |
+
"learning_rate": 8.09294177343355e-05,
|
| 627 |
+
"loss": 0.3781,
|
| 628 |
+
"step": 510
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.14,
|
| 632 |
+
"learning_rate": 8.326667681220494e-05,
|
| 633 |
+
"loss": 0.3312,
|
| 634 |
+
"step": 515
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.15,
|
| 638 |
+
"learning_rate": 8.558622457138458e-05,
|
| 639 |
+
"loss": 0.3715,
|
| 640 |
+
"step": 520
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.16,
|
| 644 |
+
"learning_rate": 8.78852599513366e-05,
|
| 645 |
+
"loss": 0.3699,
|
| 646 |
+
"step": 525
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.17,
|
| 650 |
+
"learning_rate": 9.016100666205213e-05,
|
| 651 |
+
"loss": 0.3742,
|
| 652 |
+
"step": 530
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.18,
|
| 656 |
+
"learning_rate": 9.241071653666853e-05,
|
| 657 |
+
"loss": 0.3531,
|
| 658 |
+
"step": 535
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.19,
|
| 662 |
+
"learning_rate": 9.46316728501164e-05,
|
| 663 |
+
"loss": 0.3666,
|
| 664 |
+
"step": 540
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.21,
|
| 668 |
+
"learning_rate": 9.682119359981451e-05,
|
| 669 |
+
"loss": 0.3454,
|
| 670 |
+
"step": 545
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.22,
|
| 674 |
+
"learning_rate": 9.897663474442683e-05,
|
| 675 |
+
"loss": 0.3345,
|
| 676 |
+
"step": 550
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.23,
|
| 680 |
+
"learning_rate": 0.00010109539339676733,
|
| 681 |
+
"loss": 0.3631,
|
| 682 |
+
"step": 555
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.24,
|
| 686 |
+
"learning_rate": 0.00010317491096704431,
|
| 687 |
+
"loss": 0.3796,
|
| 688 |
+
"step": 560
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.25,
|
| 692 |
+
"learning_rate": 0.00010521267625255079,
|
| 693 |
+
"loss": 0.3308,
|
| 694 |
+
"step": 565
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.26,
|
| 698 |
+
"learning_rate": 0.00010720622847019136,
|
| 699 |
+
"loss": 0.3771,
|
| 700 |
+
"step": 570
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.27,
|
| 704 |
+
"learning_rate": 0.00010915316022808663,
|
| 705 |
+
"loss": 0.3416,
|
| 706 |
+
"step": 575
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.28,
|
| 710 |
+
"learning_rate": 0.00011105112043271663,
|
| 711 |
+
"loss": 0.3921,
|
| 712 |
+
"step": 580
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.29,
|
| 716 |
+
"learning_rate": 0.00011289781712806653,
|
| 717 |
+
"loss": 0.3541,
|
| 718 |
+
"step": 585
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.31,
|
| 722 |
+
"learning_rate": 0.00011469102026339036,
|
| 723 |
+
"loss": 0.3366,
|
| 724 |
+
"step": 590
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.32,
|
| 728 |
+
"learning_rate": 0.00011642856438616586,
|
| 729 |
+
"loss": 0.348,
|
| 730 |
+
"step": 595
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.33,
|
| 734 |
+
"learning_rate": 0.00011810835125709373,
|
| 735 |
+
"loss": 0.3918,
|
| 736 |
+
"step": 600
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.34,
|
| 740 |
+
"learning_rate": 0.00011972835238389949,
|
| 741 |
+
"loss": 0.3821,
|
| 742 |
+
"step": 605
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.35,
|
| 746 |
+
"learning_rate": 0.00012128661147092148,
|
| 747 |
+
"loss": 0.3542,
|
| 748 |
+
"step": 610
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.36,
|
| 752 |
+
"learning_rate": 0.0001227812467815045,
|
| 753 |
+
"loss": 0.3587,
|
| 754 |
+
"step": 615
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.37,
|
| 758 |
+
"learning_rate": 0.00012421045341038303,
|
| 759 |
+
"loss": 0.4155,
|
| 760 |
+
"step": 620
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.38,
|
| 764 |
+
"learning_rate": 0.00012557250546324066,
|
| 765 |
+
"loss": 0.4249,
|
| 766 |
+
"step": 625
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.39,
|
| 770 |
+
"learning_rate": 0.00012686575814089933,
|
| 771 |
+
"loss": 0.4011,
|
| 772 |
+
"step": 630
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.4,
|
| 776 |
+
"learning_rate": 0.00012808864972555366,
|
| 777 |
+
"loss": 0.4206,
|
| 778 |
+
"step": 635
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.42,
|
| 782 |
+
"learning_rate": 0.00012923970346668468,
|
| 783 |
+
"loss": 0.3698,
|
| 784 |
+
"step": 640
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.43,
|
| 788 |
+
"learning_rate": 0.00013031752936437118,
|
| 789 |
+
"loss": 0.3907,
|
| 790 |
+
"step": 645
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.44,
|
| 794 |
+
"learning_rate": 0.0001313208258478337,
|
| 795 |
+
"loss": 0.3931,
|
| 796 |
+
"step": 650
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.45,
|
| 800 |
+
"learning_rate": 0.00013224838134719776,
|
| 801 |
+
"loss": 0.3725,
|
| 802 |
+
"step": 655
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.46,
|
| 806 |
+
"learning_rate": 0.00013309907575657624,
|
| 807 |
+
"loss": 0.4056,
|
| 808 |
+
"step": 660
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.47,
|
| 812 |
+
"learning_rate": 0.00013387188178669445,
|
| 813 |
+
"loss": 0.3753,
|
| 814 |
+
"step": 665
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.48,
|
| 818 |
+
"learning_rate": 0.0001345658662054306,
|
| 819 |
+
"loss": 0.4041,
|
| 820 |
+
"step": 670
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 1.49,
|
| 824 |
+
"learning_rate": 0.0001351801909647851,
|
| 825 |
+
"loss": 0.421,
|
| 826 |
+
"step": 675
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.5,
|
| 830 |
+
"learning_rate": 0.0001357141142128889,
|
| 831 |
+
"loss": 0.3516,
|
| 832 |
+
"step": 680
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 1.52,
|
| 836 |
+
"learning_rate": 0.0001361669911898596,
|
| 837 |
+
"loss": 0.4309,
|
| 838 |
+
"step": 685
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.53,
|
| 842 |
+
"learning_rate": 0.00013653827500640774,
|
| 843 |
+
"loss": 0.3797,
|
| 844 |
+
"step": 690
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 1.54,
|
| 848 |
+
"learning_rate": 0.0001368275173042528,
|
| 849 |
+
"loss": 0.4128,
|
| 850 |
+
"step": 695
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.55,
|
| 854 |
+
"learning_rate": 0.00013703436879755498,
|
| 855 |
+
"loss": 0.4107,
|
| 856 |
+
"step": 700
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.56,
|
| 860 |
+
"learning_rate": 0.00013715857969471166,
|
| 861 |
+
"loss": 0.4123,
|
| 862 |
+
"step": 705
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 1.57,
|
| 866 |
+
"learning_rate": 0.0001372,
|
| 867 |
+
"loss": 0.4361,
|
| 868 |
+
"step": 710
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.58,
|
| 872 |
+
"learning_rate": 0.00013715857969471174,
|
| 873 |
+
"loss": 0.3861,
|
| 874 |
+
"step": 715
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.59,
|
| 878 |
+
"learning_rate": 0.00013703436879755515,
|
| 879 |
+
"loss": 0.4283,
|
| 880 |
+
"step": 720
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 1.6,
|
| 884 |
+
"learning_rate": 0.00013682751730425283,
|
| 885 |
+
"loss": 0.4119,
|
| 886 |
+
"step": 725
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.62,
|
| 890 |
+
"learning_rate": 0.00013653827500640804,
|
| 891 |
+
"loss": 0.3837,
|
| 892 |
+
"step": 730
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.63,
|
| 896 |
+
"learning_rate": 0.00013616699118985964,
|
| 897 |
+
"loss": 0.409,
|
| 898 |
+
"step": 735
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.64,
|
| 902 |
+
"learning_rate": 0.00013571411421288895,
|
| 903 |
+
"loss": 0.4209,
|
| 904 |
+
"step": 740
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.65,
|
| 908 |
+
"learning_rate": 0.00013518019096478564,
|
| 909 |
+
"loss": 0.4686,
|
| 910 |
+
"step": 745
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.66,
|
| 914 |
+
"learning_rate": 0.00013456586620543123,
|
| 915 |
+
"loss": 0.4259,
|
| 916 |
+
"step": 750
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.67,
|
| 920 |
+
"learning_rate": 0.00013387188178669453,
|
| 921 |
+
"loss": 0.4255,
|
| 922 |
+
"step": 755
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.68,
|
| 926 |
+
"learning_rate": 0.000133099075756577,
|
| 927 |
+
"loss": 0.3998,
|
| 928 |
+
"step": 760
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.69,
|
| 932 |
+
"learning_rate": 0.00013224838134719786,
|
| 933 |
+
"loss": 0.4879,
|
| 934 |
+
"step": 765
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.7,
|
| 938 |
+
"learning_rate": 0.00013132082584783384,
|
| 939 |
+
"loss": 0.4157,
|
| 940 |
+
"step": 770
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.71,
|
| 944 |
+
"learning_rate": 0.00013031752936437215,
|
| 945 |
+
"loss": 0.4395,
|
| 946 |
+
"step": 775
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.73,
|
| 950 |
+
"learning_rate": 0.00012923970346668571,
|
| 951 |
+
"loss": 0.3997,
|
| 952 |
+
"step": 780
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 1.74,
|
| 956 |
+
"learning_rate": 0.00012808864972555477,
|
| 957 |
+
"loss": 0.3993,
|
| 958 |
+
"step": 785
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.75,
|
| 962 |
+
"learning_rate": 0.0001268657581409005,
|
| 963 |
+
"loss": 0.4962,
|
| 964 |
+
"step": 790
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 1.76,
|
| 968 |
+
"learning_rate": 0.00012557250546324083,
|
| 969 |
+
"loss": 0.3908,
|
| 970 |
+
"step": 795
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.77,
|
| 974 |
+
"learning_rate": 0.00012421045341038322,
|
| 975 |
+
"loss": 0.447,
|
| 976 |
+
"step": 800
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.78,
|
| 980 |
+
"learning_rate": 0.00012278124678150585,
|
| 981 |
+
"loss": 0.4202,
|
| 982 |
+
"step": 805
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.79,
|
| 986 |
+
"learning_rate": 0.00012128661147092164,
|
| 987 |
+
"loss": 0.4339,
|
| 988 |
+
"step": 810
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.8,
|
| 992 |
+
"learning_rate": 0.00011972835238390097,
|
| 993 |
+
"loss": 0.4362,
|
| 994 |
+
"step": 815
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.81,
|
| 998 |
+
"learning_rate": 0.00011810835125709524,
|
| 999 |
+
"loss": 0.462,
|
| 1000 |
+
"step": 820
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.83,
|
| 1004 |
+
"learning_rate": 0.00011642856438616606,
|
| 1005 |
+
"loss": 0.3672,
|
| 1006 |
+
"step": 825
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.84,
|
| 1010 |
+
"learning_rate": 0.00011469102026339056,
|
| 1011 |
+
"loss": 0.4118,
|
| 1012 |
+
"step": 830
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.85,
|
| 1016 |
+
"learning_rate": 0.00011289781712806821,
|
| 1017 |
+
"loss": 0.3731,
|
| 1018 |
+
"step": 835
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.86,
|
| 1022 |
+
"learning_rate": 0.00011105112043271685,
|
| 1023 |
+
"loss": 0.4515,
|
| 1024 |
+
"step": 840
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.87,
|
| 1028 |
+
"learning_rate": 0.00010915316022808842,
|
| 1029 |
+
"loss": 0.4245,
|
| 1030 |
+
"step": 845
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.88,
|
| 1034 |
+
"learning_rate": 0.00010720622847019321,
|
| 1035 |
+
"loss": 0.4166,
|
| 1036 |
+
"step": 850
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 1.89,
|
| 1040 |
+
"learning_rate": 0.00010521267625255102,
|
| 1041 |
+
"loss": 0.3902,
|
| 1042 |
+
"step": 855
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.9,
|
| 1046 |
+
"learning_rate": 0.00010317491096704455,
|
| 1047 |
+
"loss": 0.442,
|
| 1048 |
+
"step": 860
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.91,
|
| 1052 |
+
"learning_rate": 0.00010109539339676927,
|
| 1053 |
+
"loss": 0.3854,
|
| 1054 |
+
"step": 865
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 1.92,
|
| 1058 |
+
"learning_rate": 9.897663474442706e-05,
|
| 1059 |
+
"loss": 0.4236,
|
| 1060 |
+
"step": 870
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.94,
|
| 1064 |
+
"learning_rate": 9.682119359981653e-05,
|
| 1065 |
+
"loss": 0.4067,
|
| 1066 |
+
"step": 875
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.95,
|
| 1070 |
+
"learning_rate": 9.463167285011846e-05,
|
| 1071 |
+
"loss": 0.4098,
|
| 1072 |
+
"step": 880
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.96,
|
| 1076 |
+
"learning_rate": 9.241071653666879e-05,
|
| 1077 |
+
"loss": 0.4841,
|
| 1078 |
+
"step": 885
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 1.97,
|
| 1082 |
+
"learning_rate": 9.016100666205239e-05,
|
| 1083 |
+
"loss": 0.4236,
|
| 1084 |
+
"step": 890
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.98,
|
| 1088 |
+
"learning_rate": 8.788525995133685e-05,
|
| 1089 |
+
"loss": 0.4312,
|
| 1090 |
+
"step": 895
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.99,
|
| 1094 |
+
"learning_rate": 8.558622457138483e-05,
|
| 1095 |
+
"loss": 0.4461,
|
| 1096 |
+
"step": 900
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.0,
|
| 1100 |
+
"eval_loss": 0.16843362152576447,
|
| 1101 |
+
"eval_runtime": 14.4984,
|
| 1102 |
+
"eval_samples_per_second": 46.005,
|
| 1103 |
+
"eval_steps_per_second": 5.794,
|
| 1104 |
+
"step": 904
|
| 1105 |
}
|
| 1106 |
],
|
| 1107 |
"max_steps": 904,
|
| 1108 |
"num_train_epochs": 2,
|
| 1109 |
+
"total_flos": 943525527552000.0,
|
| 1110 |
"trial_name": null,
|
| 1111 |
"trial_params": null
|
| 1112 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3311
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e84296bccc90d0b22db3e3194cc96d5bb127c9114f366720d2a31b8eb99c77a
|
| 3 |
size 3311
|