Commit
·
6d2c1bd
1
Parent(s):
4a39723
huggingartists
Browse files- README.md +3 -3
- config.json +1 -1
- evaluation.txt +1 -1
- flax_model.msgpack +1 -1
- optimizer.pt +1 -1
- pytorch_model.bin +2 -2
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +555 -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/1u30jxqs/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/38khmsgm) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/38khmsgm/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
config.json
CHANGED
|
@@ -37,7 +37,7 @@
|
|
| 37 |
}
|
| 38 |
},
|
| 39 |
"torch_dtype": "float32",
|
| 40 |
-
"transformers_version": "4.
|
| 41 |
"use_cache": true,
|
| 42 |
"vocab_size": 50257
|
| 43 |
}
|
|
|
|
| 37 |
}
|
| 38 |
},
|
| 39 |
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.18.0",
|
| 41 |
"use_cache": true,
|
| 42 |
"vocab_size": 50257
|
| 43 |
}
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 0.
|
|
|
|
| 1 |
+
{"eval_loss": 0.21034620702266693, "eval_runtime": 15.1752, "eval_samples_per_second": 41.779, "eval_steps_per_second": 5.272, "epoch": 6.0}
|
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 sha256:23feba72d0f43086e6c74b84adee8455b0785e580e0aab25abcd70b41dbf0158
|
| 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 sha256:0307db0b2ba20c296872de4c51775c6f6f7c145d85ba4eba9883ae1714259f3e
|
| 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
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8eff03ee26d2091ee260f5505223bb3ad8b0787140cfe1662d5bebb6562fe0de
|
| 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 sha256:64318524f70467d7f035d4c29d2caf9c7a12a5d003c3d37e5cb258fa8e627862
|
| 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 sha256:8f9cf36b252c26cdc75b14e37b5b4fccbc15ca4a3843e9a29281707a78831c49
|
| 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,
|
|
@@ -566,11 +566,559 @@
|
|
| 566 |
"eval_samples_per_second": 43.661,
|
| 567 |
"eval_steps_per_second": 5.494,
|
| 568 |
"step": 460
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 569 |
}
|
| 570 |
],
|
| 571 |
-
"max_steps":
|
| 572 |
-
"num_train_epochs":
|
| 573 |
-
"total_flos":
|
| 574 |
"trial_name": null,
|
| 575 |
"trial_params": null
|
| 576 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.21034620702266693,
|
| 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,
|
|
|
|
| 566 |
"eval_samples_per_second": 43.661,
|
| 567 |
"eval_steps_per_second": 5.494,
|
| 568 |
"step": 460
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.02,
|
| 572 |
+
"learning_rate": 0.0001310364026633813,
|
| 573 |
+
"loss": 0.4239,
|
| 574 |
+
"step": 465
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.03,
|
| 578 |
+
"learning_rate": 0.0001319781359302741,
|
| 579 |
+
"loss": 0.5115,
|
| 580 |
+
"step": 470
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.04,
|
| 584 |
+
"learning_rate": 0.00013284467114611735,
|
| 585 |
+
"loss": 0.4756,
|
| 586 |
+
"step": 475
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.05,
|
| 590 |
+
"learning_rate": 0.00013363498016834413,
|
| 591 |
+
"loss": 0.4892,
|
| 592 |
+
"step": 480
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.06,
|
| 596 |
+
"learning_rate": 0.00013434812529663595,
|
| 597 |
+
"loss": 0.5002,
|
| 598 |
+
"step": 485
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.07,
|
| 602 |
+
"learning_rate": 0.00013498326038550478,
|
| 603 |
+
"loss": 0.5714,
|
| 604 |
+
"step": 490
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.09,
|
| 608 |
+
"learning_rate": 0.00013553963184824178,
|
| 609 |
+
"loss": 0.5845,
|
| 610 |
+
"step": 495
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.1,
|
| 614 |
+
"learning_rate": 0.0001360165795510487,
|
| 615 |
+
"loss": 0.4911,
|
| 616 |
+
"step": 500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.11,
|
| 620 |
+
"learning_rate": 0.00013641353759628265,
|
| 621 |
+
"loss": 0.5275,
|
| 622 |
+
"step": 505
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.12,
|
| 626 |
+
"learning_rate": 0.00013673003499389456,
|
| 627 |
+
"loss": 0.5292,
|
| 628 |
+
"step": 510
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.13,
|
| 632 |
+
"learning_rate": 0.00013696569622025749,
|
| 633 |
+
"loss": 0.5506,
|
| 634 |
+
"step": 515
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.14,
|
| 638 |
+
"learning_rate": 0.00013712024166372548,
|
| 639 |
+
"loss": 0.5552,
|
| 640 |
+
"step": 520
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.15,
|
| 644 |
+
"learning_rate": 0.0001371934879563911,
|
| 645 |
+
"loss": 0.5404,
|
| 646 |
+
"step": 525
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.16,
|
| 650 |
+
"learning_rate": 0.0001371853481916521,
|
| 651 |
+
"loss": 0.5364,
|
| 652 |
+
"step": 530
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.17,
|
| 656 |
+
"learning_rate": 0.0001370958320273255,
|
| 657 |
+
"loss": 0.4954,
|
| 658 |
+
"step": 535
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.18,
|
| 662 |
+
"learning_rate": 0.00013692504567418905,
|
| 663 |
+
"loss": 0.6414,
|
| 664 |
+
"step": 540
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.2,
|
| 668 |
+
"learning_rate": 0.0001366731917699612,
|
| 669 |
+
"loss": 0.5806,
|
| 670 |
+
"step": 545
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.21,
|
| 674 |
+
"learning_rate": 0.00013634056913887406,
|
| 675 |
+
"loss": 0.5283,
|
| 676 |
+
"step": 550
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.22,
|
| 680 |
+
"learning_rate": 0.0001359275724371159,
|
| 681 |
+
"loss": 0.5036,
|
| 682 |
+
"step": 555
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.23,
|
| 686 |
+
"learning_rate": 0.00013543469168457526,
|
| 687 |
+
"loss": 0.583,
|
| 688 |
+
"step": 560
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.24,
|
| 692 |
+
"learning_rate": 0.00013486251168343032,
|
| 693 |
+
"loss": 0.5384,
|
| 694 |
+
"step": 565
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.25,
|
| 698 |
+
"learning_rate": 0.0001342117113242847,
|
| 699 |
+
"loss": 0.5136,
|
| 700 |
+
"step": 570
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.26,
|
| 704 |
+
"learning_rate": 0.00013348306278066345,
|
| 705 |
+
"loss": 0.5162,
|
| 706 |
+
"step": 575
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.27,
|
| 710 |
+
"learning_rate": 0.0001326774305928314,
|
| 711 |
+
"loss": 0.4983,
|
| 712 |
+
"step": 580
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.28,
|
| 716 |
+
"learning_rate": 0.00013179577064201505,
|
| 717 |
+
"loss": 0.5491,
|
| 718 |
+
"step": 585
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.29,
|
| 722 |
+
"learning_rate": 0.00013083912901625498,
|
| 723 |
+
"loss": 0.4611,
|
| 724 |
+
"step": 590
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.3,
|
| 728 |
+
"learning_rate": 0.0001298086407692224,
|
| 729 |
+
"loss": 0.5359,
|
| 730 |
+
"step": 595
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.32,
|
| 734 |
+
"learning_rate": 0.00012870552857347723,
|
| 735 |
+
"loss": 0.5226,
|
| 736 |
+
"step": 600
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.33,
|
| 740 |
+
"learning_rate": 0.00012753110126977415,
|
| 741 |
+
"loss": 0.5316,
|
| 742 |
+
"step": 605
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.34,
|
| 746 |
+
"learning_rate": 0.00012628675231412197,
|
| 747 |
+
"loss": 0.5227,
|
| 748 |
+
"step": 610
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.35,
|
| 752 |
+
"learning_rate": 0.0001249739581244523,
|
| 753 |
+
"loss": 0.4961,
|
| 754 |
+
"step": 615
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.36,
|
| 758 |
+
"learning_rate": 0.00012359427632884786,
|
| 759 |
+
"loss": 0.5487,
|
| 760 |
+
"step": 620
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.37,
|
| 764 |
+
"learning_rate": 0.0001221493439174271,
|
| 765 |
+
"loss": 0.5994,
|
| 766 |
+
"step": 625
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.38,
|
| 770 |
+
"learning_rate": 0.00012064087530004776,
|
| 771 |
+
"loss": 0.5401,
|
| 772 |
+
"step": 630
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.39,
|
| 776 |
+
"learning_rate": 0.00011907066027217711,
|
| 777 |
+
"loss": 0.5615,
|
| 778 |
+
"step": 635
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.4,
|
| 782 |
+
"learning_rate": 0.00011744056189128525,
|
| 783 |
+
"loss": 0.5705,
|
| 784 |
+
"step": 640
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.41,
|
| 788 |
+
"learning_rate": 0.00011575251426634572,
|
| 789 |
+
"loss": 0.5663,
|
| 790 |
+
"step": 645
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.43,
|
| 794 |
+
"learning_rate": 0.00011400852026300672,
|
| 795 |
+
"loss": 0.5623,
|
| 796 |
+
"step": 650
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.44,
|
| 800 |
+
"learning_rate": 0.00011221064912720382,
|
| 801 |
+
"loss": 0.5898,
|
| 802 |
+
"step": 655
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.45,
|
| 806 |
+
"learning_rate": 0.00011036103402999931,
|
| 807 |
+
"loss": 0.5708,
|
| 808 |
+
"step": 660
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.46,
|
| 812 |
+
"learning_rate": 0.00010846186953657361,
|
| 813 |
+
"loss": 0.5299,
|
| 814 |
+
"step": 665
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.47,
|
| 818 |
+
"learning_rate": 0.00010651540900238634,
|
| 819 |
+
"loss": 0.6369,
|
| 820 |
+
"step": 670
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 1.48,
|
| 824 |
+
"learning_rate": 0.00010452396189956808,
|
| 825 |
+
"loss": 0.532,
|
| 826 |
+
"step": 675
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.49,
|
| 830 |
+
"learning_rate": 0.0001024898910767386,
|
| 831 |
+
"loss": 0.5957,
|
| 832 |
+
"step": 680
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 1.5,
|
| 836 |
+
"learning_rate": 0.00010041560995548433,
|
| 837 |
+
"loss": 0.4907,
|
| 838 |
+
"step": 685
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.51,
|
| 842 |
+
"learning_rate": 9.830357966684779e-05,
|
| 843 |
+
"loss": 0.5726,
|
| 844 |
+
"step": 690
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 1.52,
|
| 848 |
+
"learning_rate": 9.615630613119297e-05,
|
| 849 |
+
"loss": 0.5582,
|
| 850 |
+
"step": 695
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.54,
|
| 854 |
+
"learning_rate": 9.397633708493872e-05,
|
| 855 |
+
"loss": 0.6085,
|
| 856 |
+
"step": 700
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.55,
|
| 860 |
+
"learning_rate": 9.17662590576683e-05,
|
| 861 |
+
"loss": 0.6075,
|
| 862 |
+
"step": 705
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 1.56,
|
| 866 |
+
"learning_rate": 8.95286943032199e-05,
|
| 867 |
+
"loss": 0.5199,
|
| 868 |
+
"step": 710
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.57,
|
| 872 |
+
"learning_rate": 8.726629768839068e-05,
|
| 873 |
+
"loss": 0.565,
|
| 874 |
+
"step": 715
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.58,
|
| 878 |
+
"learning_rate": 8.49817535429363e-05,
|
| 879 |
+
"loss": 0.5779,
|
| 880 |
+
"step": 720
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 1.59,
|
| 884 |
+
"learning_rate": 8.267777247462197e-05,
|
| 885 |
+
"loss": 0.514,
|
| 886 |
+
"step": 725
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.6,
|
| 890 |
+
"learning_rate": 8.035708815308325e-05,
|
| 891 |
+
"loss": 0.6287,
|
| 892 |
+
"step": 730
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.61,
|
| 896 |
+
"learning_rate": 7.802245406634311e-05,
|
| 897 |
+
"loss": 0.5617,
|
| 898 |
+
"step": 735
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.62,
|
| 902 |
+
"learning_rate": 7.56766402537954e-05,
|
| 903 |
+
"loss": 0.6135,
|
| 904 |
+
"step": 740
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.63,
|
| 908 |
+
"learning_rate": 7.332243001956172e-05,
|
| 909 |
+
"loss": 0.5151,
|
| 910 |
+
"step": 745
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.64,
|
| 914 |
+
"learning_rate": 7.096261663009792e-05,
|
| 915 |
+
"loss": 0.5282,
|
| 916 |
+
"step": 750
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.66,
|
| 920 |
+
"learning_rate": 6.85999999999999e-05,
|
| 921 |
+
"loss": 0.5488,
|
| 922 |
+
"step": 755
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.67,
|
| 926 |
+
"learning_rate": 6.623738336990383e-05,
|
| 927 |
+
"loss": 0.5678,
|
| 928 |
+
"step": 760
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.68,
|
| 932 |
+
"learning_rate": 6.387756998044003e-05,
|
| 933 |
+
"loss": 0.5534,
|
| 934 |
+
"step": 765
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.69,
|
| 938 |
+
"learning_rate": 6.152335974620634e-05,
|
| 939 |
+
"loss": 0.6249,
|
| 940 |
+
"step": 770
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.7,
|
| 944 |
+
"learning_rate": 5.917754593365669e-05,
|
| 945 |
+
"loss": 0.5588,
|
| 946 |
+
"step": 775
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.71,
|
| 950 |
+
"learning_rate": 5.684291184691846e-05,
|
| 951 |
+
"loss": 0.4985,
|
| 952 |
+
"step": 780
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 1.72,
|
| 956 |
+
"learning_rate": 5.452222752537974e-05,
|
| 957 |
+
"loss": 0.545,
|
| 958 |
+
"step": 785
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.73,
|
| 962 |
+
"learning_rate": 5.2218246457065396e-05,
|
| 963 |
+
"loss": 0.5905,
|
| 964 |
+
"step": 790
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 1.74,
|
| 968 |
+
"learning_rate": 4.993370231160913e-05,
|
| 969 |
+
"loss": 0.4741,
|
| 970 |
+
"step": 795
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.75,
|
| 974 |
+
"learning_rate": 4.767130569678176e-05,
|
| 975 |
+
"loss": 0.5473,
|
| 976 |
+
"step": 800
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.77,
|
| 980 |
+
"learning_rate": 4.543374094233335e-05,
|
| 981 |
+
"loss": 0.525,
|
| 982 |
+
"step": 805
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.78,
|
| 986 |
+
"learning_rate": 4.3223662915062914e-05,
|
| 987 |
+
"loss": 0.5134,
|
| 988 |
+
"step": 810
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.79,
|
| 992 |
+
"learning_rate": 4.104369386880686e-05,
|
| 993 |
+
"loss": 0.5726,
|
| 994 |
+
"step": 815
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.8,
|
| 998 |
+
"learning_rate": 3.8896420333152035e-05,
|
| 999 |
+
"loss": 0.4985,
|
| 1000 |
+
"step": 820
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.81,
|
| 1004 |
+
"learning_rate": 3.6784390044517205e-05,
|
| 1005 |
+
"loss": 0.5251,
|
| 1006 |
+
"step": 825
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.82,
|
| 1010 |
+
"learning_rate": 3.471010892326291e-05,
|
| 1011 |
+
"loss": 0.6068,
|
| 1012 |
+
"step": 830
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.83,
|
| 1016 |
+
"learning_rate": 3.267603810043175e-05,
|
| 1017 |
+
"loss": 0.5227,
|
| 1018 |
+
"step": 835
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.84,
|
| 1022 |
+
"learning_rate": 3.068459099761349e-05,
|
| 1023 |
+
"loss": 0.5061,
|
| 1024 |
+
"step": 840
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.85,
|
| 1028 |
+
"learning_rate": 2.8738130463427823e-05,
|
| 1029 |
+
"loss": 0.5539,
|
| 1030 |
+
"step": 845
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.86,
|
| 1034 |
+
"learning_rate": 2.683896597000207e-05,
|
| 1035 |
+
"loss": 0.5975,
|
| 1036 |
+
"step": 850
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 1.88,
|
| 1040 |
+
"learning_rate": 2.4989350872796035e-05,
|
| 1041 |
+
"loss": 0.5843,
|
| 1042 |
+
"step": 855
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.89,
|
| 1046 |
+
"learning_rate": 2.3191479736993138e-05,
|
| 1047 |
+
"loss": 0.571,
|
| 1048 |
+
"step": 860
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.9,
|
| 1052 |
+
"learning_rate": 2.1447485733655544e-05,
|
| 1053 |
+
"loss": 0.5282,
|
| 1054 |
+
"step": 865
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 1.91,
|
| 1058 |
+
"learning_rate": 1.975943810871599e-05,
|
| 1059 |
+
"loss": 0.5626,
|
| 1060 |
+
"step": 870
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.92,
|
| 1064 |
+
"learning_rate": 1.8129339727824064e-05,
|
| 1065 |
+
"loss": 0.5394,
|
| 1066 |
+
"step": 875
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.93,
|
| 1070 |
+
"learning_rate": 1.6559124699952118e-05,
|
| 1071 |
+
"loss": 0.4747,
|
| 1072 |
+
"step": 880
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.94,
|
| 1076 |
+
"learning_rate": 1.5050656082574002e-05,
|
| 1077 |
+
"loss": 0.5601,
|
| 1078 |
+
"step": 885
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 1.95,
|
| 1082 |
+
"learning_rate": 1.3605723671153187e-05,
|
| 1083 |
+
"loss": 0.4725,
|
| 1084 |
+
"step": 890
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.96,
|
| 1088 |
+
"learning_rate": 1.22260418755487e-05,
|
| 1089 |
+
"loss": 0.5171,
|
| 1090 |
+
"step": 895
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.97,
|
| 1094 |
+
"learning_rate": 1.0913247685877927e-05,
|
| 1095 |
+
"loss": 0.5425,
|
| 1096 |
+
"step": 900
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 1.98,
|
| 1100 |
+
"learning_rate": 9.66889873022574e-06,
|
| 1101 |
+
"loss": 0.4969,
|
| 1102 |
+
"step": 905
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.0,
|
| 1106 |
+
"learning_rate": 8.494471426523612e-06,
|
| 1107 |
+
"loss": 0.5235,
|
| 1108 |
+
"step": 910
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 2.0,
|
| 1112 |
+
"eval_loss": 0.21034620702266693,
|
| 1113 |
+
"eval_runtime": 15.3022,
|
| 1114 |
+
"eval_samples_per_second": 41.432,
|
| 1115 |
+
"eval_steps_per_second": 5.228,
|
| 1116 |
+
"step": 912
|
| 1117 |
}
|
| 1118 |
],
|
| 1119 |
+
"max_steps": 2736,
|
| 1120 |
+
"num_train_epochs": 6,
|
| 1121 |
+
"total_flos": 951886872576000.0,
|
| 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 3055
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1ea3cda2785536f15c20f453c0b9bcc0101903ca9e2ecd4b40b57e318d77ca5
|
| 3 |
size 3055
|