Commit
•
70e8d8c
1
Parent(s):
cd21cbc
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 +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- tokenizer.json +0 -0
- trainer_state.json +543 -7
- training_args.bin +2 -2
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/3nw4yihh/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/d2518d5z) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/d2518d5z/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": "4.16.1",
|
| 41 |
"use_cache": true,
|
| 42 |
"vocab_size": 50257
|
| 43 |
}
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 0.
|
|
|
|
| 1 |
+
{"eval_loss": 0.5308113694190979, "eval_runtime": 33.6836, "eval_samples_per_second": 20.544, "eval_steps_per_second": 2.583, "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:a848a5f09ac15240e3985770765e24f91d15132b1d91e4e6609d31cfa9381998
|
| 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:c93aacf90961d37a1a7828ff46e2dc62c33c91fee3a84fdc5ef4c64587efa913
|
| 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 sha256:6a17213360ebd42855ba94ae341f8e0785b2c350210bb514a32c45f28a0a9946
|
| 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 14503
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3a41f6ecc4cb672b89916065240d6da95437b3116ab28fa8f83b9d0f50b7335
|
| 3 |
size 14503
|
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:e839905521debf4509c82b96247599aa8aabe5b0cbac84cd46b26dbe8819f271
|
| 3 |
size 623
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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,
|
|
@@ -560,11 +560,547 @@
|
|
| 560 |
"eval_samples_per_second": 17.527,
|
| 561 |
"eval_steps_per_second": 2.198,
|
| 562 |
"step": 457
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 0.5308113694190979,
|
| 3 |
+
"best_model_checkpoint": "output/eminem/checkpoint-898",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 898,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 560 |
"eval_samples_per_second": 17.527,
|
| 561 |
"eval_steps_per_second": 2.198,
|
| 562 |
"step": 457
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.02,
|
| 566 |
+
"learning_rate": 7.411387289257788e-05,
|
| 567 |
+
"loss": 0.7428,
|
| 568 |
+
"step": 460
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.04,
|
| 572 |
+
"learning_rate": 7.650217107773121e-05,
|
| 573 |
+
"loss": 0.7294,
|
| 574 |
+
"step": 465
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.05,
|
| 578 |
+
"learning_rate": 7.888079875674826e-05,
|
| 579 |
+
"loss": 0.8298,
|
| 580 |
+
"step": 470
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"epoch": 1.06,
|
| 584 |
+
"learning_rate": 8.1246845016499e-05,
|
| 585 |
+
"loss": 0.7537,
|
| 586 |
+
"step": 475
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 1.07,
|
| 590 |
+
"learning_rate": 8.359741434072031e-05,
|
| 591 |
+
"loss": 0.6783,
|
| 592 |
+
"step": 480
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 1.08,
|
| 596 |
+
"learning_rate": 8.59296301534902e-05,
|
| 597 |
+
"loss": 0.7367,
|
| 598 |
+
"step": 485
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.09,
|
| 602 |
+
"learning_rate": 8.824063833951144e-05,
|
| 603 |
+
"loss": 0.8382,
|
| 604 |
+
"step": 490
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.1,
|
| 608 |
+
"learning_rate": 9.052761073692769e-05,
|
| 609 |
+
"loss": 0.6501,
|
| 610 |
+
"step": 495
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.11,
|
| 614 |
+
"learning_rate": 9.2787748598361e-05,
|
| 615 |
+
"loss": 0.7697,
|
| 616 |
+
"step": 500
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.12,
|
| 620 |
+
"learning_rate": 9.501828601595296e-05,
|
| 621 |
+
"loss": 0.7842,
|
| 622 |
+
"step": 505
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 1.14,
|
| 626 |
+
"learning_rate": 9.72164933062357e-05,
|
| 627 |
+
"loss": 0.8064,
|
| 628 |
+
"step": 510
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 1.15,
|
| 632 |
+
"learning_rate": 9.937968035064501e-05,
|
| 633 |
+
"loss": 0.8361,
|
| 634 |
+
"step": 515
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 1.16,
|
| 638 |
+
"learning_rate": 0.00010150519988764197,
|
| 639 |
+
"loss": 0.7419,
|
| 640 |
+
"step": 520
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.17,
|
| 644 |
+
"learning_rate": 0.00010359045075236705,
|
| 645 |
+
"loss": 0.8181,
|
| 646 |
+
"step": 525
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 1.18,
|
| 650 |
+
"learning_rate": 0.00010563288105989297,
|
| 651 |
+
"loss": 0.7946,
|
| 652 |
+
"step": 530
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.19,
|
| 656 |
+
"learning_rate": 0.00010762999132815968,
|
| 657 |
+
"loss": 0.7522,
|
| 658 |
+
"step": 535
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.2,
|
| 662 |
+
"learning_rate": 0.00010957933753679646,
|
| 663 |
+
"loss": 0.721,
|
| 664 |
+
"step": 540
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 1.21,
|
| 668 |
+
"learning_rate": 0.00011147853411805452,
|
| 669 |
+
"loss": 0.7965,
|
| 670 |
+
"step": 545
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 1.22,
|
| 674 |
+
"learning_rate": 0.00011332525687621633,
|
| 675 |
+
"loss": 0.8731,
|
| 676 |
+
"step": 550
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.24,
|
| 680 |
+
"learning_rate": 0.00011511724583189029,
|
| 681 |
+
"loss": 0.7461,
|
| 682 |
+
"step": 555
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.25,
|
| 686 |
+
"learning_rate": 0.00011685230798773347,
|
| 687 |
+
"loss": 0.8536,
|
| 688 |
+
"step": 560
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 1.26,
|
| 692 |
+
"learning_rate": 0.00011852832001218846,
|
| 693 |
+
"loss": 0.8069,
|
| 694 |
+
"step": 565
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 1.27,
|
| 698 |
+
"learning_rate": 0.00012014323083797337,
|
| 699 |
+
"loss": 0.7363,
|
| 700 |
+
"step": 570
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 1.28,
|
| 704 |
+
"learning_rate": 0.00012169506417212839,
|
| 705 |
+
"loss": 0.8555,
|
| 706 |
+
"step": 575
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 1.29,
|
| 710 |
+
"learning_rate": 0.0001231819209145695,
|
| 711 |
+
"loss": 0.8844,
|
| 712 |
+
"step": 580
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.3,
|
| 716 |
+
"learning_rate": 0.00012460198148215605,
|
| 717 |
+
"loss": 0.8991,
|
| 718 |
+
"step": 585
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 1.31,
|
| 722 |
+
"learning_rate": 0.00012595350803546582,
|
| 723 |
+
"loss": 0.7508,
|
| 724 |
+
"step": 590
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.33,
|
| 728 |
+
"learning_rate": 0.0001272348466055214,
|
| 729 |
+
"loss": 0.8352,
|
| 730 |
+
"step": 595
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 1.34,
|
| 734 |
+
"learning_rate": 0.00012844442911787884,
|
| 735 |
+
"loss": 0.8305,
|
| 736 |
+
"step": 600
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 1.35,
|
| 740 |
+
"learning_rate": 0.00012958077531160963,
|
| 741 |
+
"loss": 0.8743,
|
| 742 |
+
"step": 605
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 1.36,
|
| 746 |
+
"learning_rate": 0.0001306424945508076,
|
| 747 |
+
"loss": 0.9164,
|
| 748 |
+
"step": 610
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.37,
|
| 752 |
+
"learning_rate": 0.00013162828752642103,
|
| 753 |
+
"loss": 0.8642,
|
| 754 |
+
"step": 615
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.38,
|
| 758 |
+
"learning_rate": 0.0001325369478463158,
|
| 759 |
+
"loss": 0.845,
|
| 760 |
+
"step": 620
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 1.39,
|
| 764 |
+
"learning_rate": 0.00013336736351163685,
|
| 765 |
+
"loss": 0.8869,
|
| 766 |
+
"step": 625
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.4,
|
| 770 |
+
"learning_rate": 0.00013411851827764502,
|
| 771 |
+
"loss": 0.8367,
|
| 772 |
+
"step": 630
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.41,
|
| 776 |
+
"learning_rate": 0.00013478949289737682,
|
| 777 |
+
"loss": 0.8495,
|
| 778 |
+
"step": 635
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.43,
|
| 782 |
+
"learning_rate": 0.00013537946624659676,
|
| 783 |
+
"loss": 0.9375,
|
| 784 |
+
"step": 640
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 1.44,
|
| 788 |
+
"learning_rate": 0.00013588771632867518,
|
| 789 |
+
"loss": 0.9639,
|
| 790 |
+
"step": 645
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.45,
|
| 794 |
+
"learning_rate": 0.00013631362115814792,
|
| 795 |
+
"loss": 0.8622,
|
| 796 |
+
"step": 650
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 1.46,
|
| 800 |
+
"learning_rate": 0.00013665665952189337,
|
| 801 |
+
"loss": 0.7462,
|
| 802 |
+
"step": 655
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.47,
|
| 806 |
+
"learning_rate": 0.0001369164116169769,
|
| 807 |
+
"loss": 0.8065,
|
| 808 |
+
"step": 660
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.48,
|
| 812 |
+
"learning_rate": 0.0001370925595644003,
|
| 813 |
+
"loss": 0.7944,
|
| 814 |
+
"step": 665
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.49,
|
| 818 |
+
"learning_rate": 0.00013718488779811326,
|
| 819 |
+
"loss": 0.9673,
|
| 820 |
+
"step": 670
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 1.5,
|
| 824 |
+
"learning_rate": 0.00013719328332881955,
|
| 825 |
+
"loss": 0.8319,
|
| 826 |
+
"step": 675
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.51,
|
| 830 |
+
"learning_rate": 0.00013711773588225001,
|
| 831 |
+
"loss": 0.7709,
|
| 832 |
+
"step": 680
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 1.53,
|
| 836 |
+
"learning_rate": 0.00013695833791173674,
|
| 837 |
+
"loss": 0.8833,
|
| 838 |
+
"step": 685
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.54,
|
| 842 |
+
"learning_rate": 0.00013671528448507009,
|
| 843 |
+
"loss": 0.8851,
|
| 844 |
+
"step": 690
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 1.55,
|
| 848 |
+
"learning_rate": 0.00013638887304577923,
|
| 849 |
+
"loss": 0.8425,
|
| 850 |
+
"step": 695
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.56,
|
| 854 |
+
"learning_rate": 0.00013597950304912684,
|
| 855 |
+
"loss": 0.9205,
|
| 856 |
+
"step": 700
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 1.57,
|
| 860 |
+
"learning_rate": 0.0001354876754732656,
|
| 861 |
+
"loss": 0.9954,
|
| 862 |
+
"step": 705
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 1.58,
|
| 866 |
+
"learning_rate": 0.00013491399220615015,
|
| 867 |
+
"loss": 0.8622,
|
| 868 |
+
"step": 710
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 1.59,
|
| 872 |
+
"learning_rate": 0.00013425915530896078,
|
| 873 |
+
"loss": 0.8284,
|
| 874 |
+
"step": 715
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.6,
|
| 878 |
+
"learning_rate": 0.00013352396615693527,
|
| 879 |
+
"loss": 0.8501,
|
| 880 |
+
"step": 720
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 1.61,
|
| 884 |
+
"learning_rate": 0.00013270932445866562,
|
| 885 |
+
"loss": 0.7884,
|
| 886 |
+
"step": 725
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.63,
|
| 890 |
+
"learning_rate": 0.00013181622715504977,
|
| 891 |
+
"loss": 0.9186,
|
| 892 |
+
"step": 730
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.64,
|
| 896 |
+
"learning_rate": 0.000130845767199263,
|
| 897 |
+
"loss": 0.8647,
|
| 898 |
+
"step": 735
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.65,
|
| 902 |
+
"learning_rate": 0.0001297991322192165,
|
| 903 |
+
"loss": 0.8587,
|
| 904 |
+
"step": 740
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 1.66,
|
| 908 |
+
"learning_rate": 0.00012867760306417496,
|
| 909 |
+
"loss": 0.8789,
|
| 910 |
+
"step": 745
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.67,
|
| 914 |
+
"learning_rate": 0.00012748255223727105,
|
| 915 |
+
"loss": 0.7334,
|
| 916 |
+
"step": 750
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.68,
|
| 920 |
+
"learning_rate": 0.00012621544221587383,
|
| 921 |
+
"loss": 0.854,
|
| 922 |
+
"step": 755
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.69,
|
| 926 |
+
"learning_rate": 0.000124877823661834,
|
| 927 |
+
"loss": 0.8584,
|
| 928 |
+
"step": 760
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.7,
|
| 932 |
+
"learning_rate": 0.0001234713335238199,
|
| 933 |
+
"loss": 0.8898,
|
| 934 |
+
"step": 765
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.71,
|
| 938 |
+
"learning_rate": 0.00012199769303405894,
|
| 939 |
+
"loss": 0.842,
|
| 940 |
+
"step": 770
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.73,
|
| 944 |
+
"learning_rate": 0.00012045870560192401,
|
| 945 |
+
"loss": 0.8657,
|
| 946 |
+
"step": 775
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.74,
|
| 950 |
+
"learning_rate": 0.00011885625460696435,
|
| 951 |
+
"loss": 0.8646,
|
| 952 |
+
"step": 780
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 1.75,
|
| 956 |
+
"learning_rate": 0.00011719230109406423,
|
| 957 |
+
"loss": 0.974,
|
| 958 |
+
"step": 785
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.76,
|
| 962 |
+
"learning_rate": 0.00011546888137356373,
|
| 963 |
+
"loss": 0.892,
|
| 964 |
+
"step": 790
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 1.77,
|
| 968 |
+
"learning_rate": 0.00011368810452925682,
|
| 969 |
+
"loss": 0.8279,
|
| 970 |
+
"step": 795
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.78,
|
| 974 |
+
"learning_rate": 0.00011185214983735281,
|
| 975 |
+
"loss": 0.9267,
|
| 976 |
+
"step": 800
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.79,
|
| 980 |
+
"learning_rate": 0.0001099632640995077,
|
| 981 |
+
"loss": 0.8753,
|
| 982 |
+
"step": 805
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.8,
|
| 986 |
+
"learning_rate": 0.00010802375889325772,
|
| 987 |
+
"loss": 0.8341,
|
| 988 |
+
"step": 810
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 1.82,
|
| 992 |
+
"learning_rate": 0.00010603600774314254,
|
| 993 |
+
"loss": 0.9575,
|
| 994 |
+
"step": 815
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.83,
|
| 998 |
+
"learning_rate": 0.00010400244321605133,
|
| 999 |
+
"loss": 0.851,
|
| 1000 |
+
"step": 820
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 1.84,
|
| 1004 |
+
"learning_rate": 0.0001019255539442888,
|
| 1005 |
+
"loss": 0.7728,
|
| 1006 |
+
"step": 825
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.85,
|
| 1010 |
+
"learning_rate": 9.980788158004715e-05,
|
| 1011 |
+
"loss": 0.8267,
|
| 1012 |
+
"step": 830
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 1.86,
|
| 1016 |
+
"learning_rate": 9.765201768498375e-05,
|
| 1017 |
+
"loss": 0.8464,
|
| 1018 |
+
"step": 835
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.87,
|
| 1022 |
+
"learning_rate": 9.546060055873103e-05,
|
| 1023 |
+
"loss": 0.8036,
|
| 1024 |
+
"step": 840
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 1.88,
|
| 1028 |
+
"learning_rate": 9.32363120101919e-05,
|
| 1029 |
+
"loss": 0.9536,
|
| 1030 |
+
"step": 845
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.89,
|
| 1034 |
+
"learning_rate": 9.098187407560697e-05,
|
| 1035 |
+
"loss": 0.8601,
|
| 1036 |
+
"step": 850
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 1.9,
|
| 1040 |
+
"learning_rate": 8.870004568738188e-05,
|
| 1041 |
+
"loss": 0.78,
|
| 1042 |
+
"step": 855
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.92,
|
| 1046 |
+
"learning_rate": 8.639361929777101e-05,
|
| 1047 |
+
"loss": 0.8761,
|
| 1048 |
+
"step": 860
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 1.93,
|
| 1052 |
+
"learning_rate": 8.406541746153297e-05,
|
| 1053 |
+
"loss": 0.8593,
|
| 1054 |
+
"step": 865
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 1.94,
|
| 1058 |
+
"learning_rate": 8.171828938173595e-05,
|
| 1059 |
+
"loss": 0.7247,
|
| 1060 |
+
"step": 870
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.95,
|
| 1064 |
+
"learning_rate": 7.935510742298902e-05,
|
| 1065 |
+
"loss": 0.8669,
|
| 1066 |
+
"step": 875
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.96,
|
| 1070 |
+
"learning_rate": 7.697876359628178e-05,
|
| 1071 |
+
"loss": 0.9187,
|
| 1072 |
+
"step": 880
|
| 1073 |
+
},
|
| 1074 |
+
{
|
| 1075 |
+
"epoch": 1.97,
|
| 1076 |
+
"learning_rate": 7.459216601982097e-05,
|
| 1077 |
+
"loss": 0.8965,
|
| 1078 |
+
"step": 885
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 1.98,
|
| 1082 |
+
"learning_rate": 7.219823536012484e-05,
|
| 1083 |
+
"loss": 0.9159,
|
| 1084 |
+
"step": 890
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 1.99,
|
| 1088 |
+
"learning_rate": 6.97999012577823e-05,
|
| 1089 |
+
"loss": 1.0147,
|
| 1090 |
+
"step": 895
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 2.0,
|
| 1094 |
+
"eval_loss": 0.5308113694190979,
|
| 1095 |
+
"eval_runtime": 33.6128,
|
| 1096 |
+
"eval_samples_per_second": 20.587,
|
| 1097 |
+
"eval_steps_per_second": 2.588,
|
| 1098 |
+
"step": 898
|
| 1099 |
}
|
| 1100 |
],
|
| 1101 |
+
"max_steps": 898,
|
| 1102 |
+
"num_train_epochs": 2,
|
| 1103 |
+
"total_flos": 937515810816000.0,
|
| 1104 |
"trial_name": null,
|
| 1105 |
"trial_params": null
|
| 1106 |
}
|
training_args.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 sha256:17e1bade9dac46ba2611ae8c7e18e7545beeeb1e60ed8853a281799cdfbbfd97
|
| 3 |
+
size 3055
|