Commit
•
2d6dc04
1
Parent(s):
f1dbedf
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 +2 -2
- scheduler.pt +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +587 -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/3vis8hub/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/vsi1kmha) for full transparency and reproducibility.
|
| 55 |
|
| 56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/vsi1kmha/artifacts) is logged and versioned.
|
| 57 |
|
| 58 |
## How to use
|
| 59 |
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "huggingartists/eminem",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2LMHeadModel"
|
evaluation.txt
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"eval_loss": 3.
|
|
|
|
| 1 |
+
{"eval_loss": 3.550342321395874, "eval_runtime": 15.4175, "eval_samples_per_second": 39.176, "eval_steps_per_second": 4.929, "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 sha256:50be979b8b3586b1733c928ce8490cf5cc1a14a66edbce08b2db156f4be93f15
|
| 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 sha256:632ddf0a9ff1dbc17c7ef3df2f3b5d2c7ea6dbc503edad780e47dfc8809d90bc
|
| 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 sha256:09add2f3ac2fd368dc8c57fd18053cdac18d00b8e1ac65a2d642833e74a0a759
|
| 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:a59e6426f4884c6a7dfc9127b714b01aad43ac43d68d147e4b7627a97abecd21
|
| 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 sha256:64d649c29e36fd0af6b34d053ac5a147e5edddf6dd49f7bdc7b41cd80c5d9b45
|
| 3 |
size 623
|
tokenizer_config.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "
|
|
|
|
| 1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "huggingartists/eminem", "tokenizer_class": "GPT2Tokenizer"}
|
trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 3.
|
| 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 +554,591 @@
|
|
| 554 |
"eval_samples_per_second": 22.388,
|
| 555 |
"eval_steps_per_second": 2.798,
|
| 556 |
"step": 453
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 557 |
}
|
| 558 |
],
|
| 559 |
-
"max_steps":
|
| 560 |
-
"num_train_epochs":
|
| 561 |
-
"total_flos":
|
| 562 |
"trial_name": null,
|
| 563 |
"trial_params": null
|
| 564 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 3.550342321395874,
|
| 3 |
+
"best_model_checkpoint": "output/eminem/checkpoint-920",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"global_step": 920,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 554 |
"eval_samples_per_second": 22.388,
|
| 555 |
"eval_steps_per_second": 2.798,
|
| 556 |
"step": 453
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.99,
|
| 560 |
+
"learning_rate": 3.9992265680461966e-08,
|
| 561 |
+
"loss": 3.6362,
|
| 562 |
+
"step": 455
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 1.0,
|
| 566 |
+
"learning_rate": 0.0,
|
| 567 |
+
"loss": 3.3994,
|
| 568 |
+
"step": 460
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.0,
|
| 572 |
+
"eval_loss": 3.5555710792541504,
|
| 573 |
+
"eval_runtime": 13.5198,
|
| 574 |
+
"eval_samples_per_second": 44.675,
|
| 575 |
+
"eval_steps_per_second": 5.621,
|
| 576 |
+
"step": 460
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.01,
|
| 580 |
+
"learning_rate": 3.9992265680461966e-08,
|
| 581 |
+
"loss": 3.5614,
|
| 582 |
+
"step": 465
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.02,
|
| 586 |
+
"learning_rate": 1.5992243352901425e-07,
|
| 587 |
+
"loss": 3.7249,
|
| 588 |
+
"step": 470
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.03,
|
| 592 |
+
"learning_rate": 3.5965067033469397e-07,
|
| 593 |
+
"loss": 3.4991,
|
| 594 |
+
"step": 475
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 1.04,
|
| 598 |
+
"learning_rate": 6.389441019077102e-07,
|
| 599 |
+
"loss": 3.439,
|
| 600 |
+
"step": 480
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 1.05,
|
| 604 |
+
"learning_rate": 9.97477084600295e-07,
|
| 605 |
+
"loss": 3.6568,
|
| 606 |
+
"step": 485
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 1.07,
|
| 610 |
+
"learning_rate": 1.4348315849926483e-06,
|
| 611 |
+
"loss": 3.5489,
|
| 612 |
+
"step": 490
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.08,
|
| 616 |
+
"learning_rate": 1.9504976673012086e-06,
|
| 617 |
+
"loss": 3.6268,
|
| 618 |
+
"step": 495
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 1.09,
|
| 622 |
+
"learning_rate": 2.5438740879409643e-06,
|
| 623 |
+
"loss": 3.8246,
|
| 624 |
+
"step": 500
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.1,
|
| 628 |
+
"learning_rate": 3.2142689965485674e-06,
|
| 629 |
+
"loss": 3.5789,
|
| 630 |
+
"step": 505
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.11,
|
| 634 |
+
"learning_rate": 3.960900742648913e-06,
|
| 635 |
+
"loss": 3.618,
|
| 636 |
+
"step": 510
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 1.12,
|
| 640 |
+
"learning_rate": 4.782898787024646e-06,
|
| 641 |
+
"loss": 3.6802,
|
| 642 |
+
"step": 515
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 1.13,
|
| 646 |
+
"learning_rate": 5.679304716725914e-06,
|
| 647 |
+
"loss": 3.6302,
|
| 648 |
+
"step": 520
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 1.14,
|
| 652 |
+
"learning_rate": 6.649073362537048e-06,
|
| 653 |
+
"loss": 3.5926,
|
| 654 |
+
"step": 525
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.15,
|
| 658 |
+
"learning_rate": 7.691074017597052e-06,
|
| 659 |
+
"loss": 3.5005,
|
| 660 |
+
"step": 530
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 1.16,
|
| 664 |
+
"learning_rate": 8.804091755753263e-06,
|
| 665 |
+
"loss": 3.6247,
|
| 666 |
+
"step": 535
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.17,
|
| 670 |
+
"learning_rate": 9.986828848110884e-06,
|
| 671 |
+
"loss": 3.5699,
|
| 672 |
+
"step": 540
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.18,
|
| 676 |
+
"learning_rate": 1.1237906276126821e-05,
|
| 677 |
+
"loss": 3.5435,
|
| 678 |
+
"step": 545
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 1.2,
|
| 682 |
+
"learning_rate": 1.2555865339483672e-05,
|
| 683 |
+
"loss": 3.5681,
|
| 684 |
+
"step": 550
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 1.21,
|
| 688 |
+
"learning_rate": 1.3939169356868945e-05,
|
| 689 |
+
"loss": 3.5438,
|
| 690 |
+
"step": 555
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.22,
|
| 694 |
+
"learning_rate": 1.5386205457676803e-05,
|
| 695 |
+
"loss": 3.6615,
|
| 696 |
+
"step": 560
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.23,
|
| 700 |
+
"learning_rate": 1.6895286462543014e-05,
|
| 701 |
+
"loss": 3.5334,
|
| 702 |
+
"step": 565
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 1.24,
|
| 706 |
+
"learning_rate": 1.8464652850520678e-05,
|
| 707 |
+
"loss": 3.5256,
|
| 708 |
+
"step": 570
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 1.25,
|
| 712 |
+
"learning_rate": 2.009247481060283e-05,
|
| 713 |
+
"loss": 3.5908,
|
| 714 |
+
"step": 575
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 1.26,
|
| 718 |
+
"learning_rate": 2.1776854375200328e-05,
|
| 719 |
+
"loss": 3.6817,
|
| 720 |
+
"step": 580
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 1.27,
|
| 724 |
+
"learning_rate": 2.351582763308709e-05,
|
| 725 |
+
"loss": 3.6254,
|
| 726 |
+
"step": 585
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 1.28,
|
| 730 |
+
"learning_rate": 2.5307367019232758e-05,
|
| 731 |
+
"loss": 3.5371,
|
| 732 |
+
"step": 590
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 1.29,
|
| 736 |
+
"learning_rate": 2.714938367885288e-05,
|
| 737 |
+
"loss": 3.6406,
|
| 738 |
+
"step": 595
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.3,
|
| 742 |
+
"learning_rate": 2.9039729902920112e-05,
|
| 743 |
+
"loss": 3.5787,
|
| 744 |
+
"step": 600
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 1.32,
|
| 748 |
+
"learning_rate": 3.097620163229676e-05,
|
| 749 |
+
"loss": 3.5732,
|
| 750 |
+
"step": 605
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 1.33,
|
| 754 |
+
"learning_rate": 3.295654102756921e-05,
|
| 755 |
+
"loss": 3.5091,
|
| 756 |
+
"step": 610
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 1.34,
|
| 760 |
+
"learning_rate": 3.4978439101588006e-05,
|
| 761 |
+
"loss": 3.617,
|
| 762 |
+
"step": 615
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 1.35,
|
| 766 |
+
"learning_rate": 3.703953841164292e-05,
|
| 767 |
+
"loss": 3.582,
|
| 768 |
+
"step": 620
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 1.36,
|
| 772 |
+
"learning_rate": 3.913743580813637e-05,
|
| 773 |
+
"loss": 3.6594,
|
| 774 |
+
"step": 625
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 1.37,
|
| 778 |
+
"learning_rate": 4.126968523654786e-05,
|
| 779 |
+
"loss": 3.6063,
|
| 780 |
+
"step": 630
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.38,
|
| 784 |
+
"learning_rate": 4.343380058942427e-05,
|
| 785 |
+
"loss": 3.6137,
|
| 786 |
+
"step": 635
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 1.39,
|
| 790 |
+
"learning_rate": 4.562725860507034e-05,
|
| 791 |
+
"loss": 3.5565,
|
| 792 |
+
"step": 640
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 1.4,
|
| 796 |
+
"learning_rate": 4.784750180955822e-05,
|
| 797 |
+
"loss": 3.6099,
|
| 798 |
+
"step": 645
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 1.41,
|
| 802 |
+
"learning_rate": 5.009194149862813e-05,
|
| 803 |
+
"loss": 3.6417,
|
| 804 |
+
"step": 650
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 1.42,
|
| 808 |
+
"learning_rate": 5.235796075600178e-05,
|
| 809 |
+
"loss": 3.7049,
|
| 810 |
+
"step": 655
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 1.43,
|
| 814 |
+
"learning_rate": 5.4642917504589275e-05,
|
| 815 |
+
"loss": 3.7319,
|
| 816 |
+
"step": 660
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 1.45,
|
| 820 |
+
"learning_rate": 5.694414758703346e-05,
|
| 821 |
+
"loss": 3.554,
|
| 822 |
+
"step": 665
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.46,
|
| 826 |
+
"learning_rate": 5.92589678719975e-05,
|
| 827 |
+
"loss": 3.5522,
|
| 828 |
+
"step": 670
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 1.47,
|
| 832 |
+
"learning_rate": 6.158467938257645e-05,
|
| 833 |
+
"loss": 3.6115,
|
| 834 |
+
"step": 675
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 1.48,
|
| 838 |
+
"learning_rate": 6.391857044318355e-05,
|
| 839 |
+
"loss": 3.6475,
|
| 840 |
+
"step": 680
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 1.49,
|
| 844 |
+
"learning_rate": 6.625791984124255e-05,
|
| 845 |
+
"loss": 3.5034,
|
| 846 |
+
"step": 685
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 1.5,
|
| 850 |
+
"learning_rate": 6.859999999999999e-05,
|
| 851 |
+
"loss": 3.5767,
|
| 852 |
+
"step": 690
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 1.51,
|
| 856 |
+
"learning_rate": 7.094208015875743e-05,
|
| 857 |
+
"loss": 3.6471,
|
| 858 |
+
"step": 695
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 1.52,
|
| 862 |
+
"learning_rate": 7.328142955681643e-05,
|
| 863 |
+
"loss": 3.6515,
|
| 864 |
+
"step": 700
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.53,
|
| 868 |
+
"learning_rate": 7.561532061742353e-05,
|
| 869 |
+
"loss": 3.6649,
|
| 870 |
+
"step": 705
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 1.54,
|
| 874 |
+
"learning_rate": 7.794103212800247e-05,
|
| 875 |
+
"loss": 3.4103,
|
| 876 |
+
"step": 710
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 1.55,
|
| 880 |
+
"learning_rate": 8.025585241296653e-05,
|
| 881 |
+
"loss": 3.5488,
|
| 882 |
+
"step": 715
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 1.57,
|
| 886 |
+
"learning_rate": 8.25570824954107e-05,
|
| 887 |
+
"loss": 3.5076,
|
| 888 |
+
"step": 720
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 1.58,
|
| 892 |
+
"learning_rate": 8.484203924399819e-05,
|
| 893 |
+
"loss": 3.5708,
|
| 894 |
+
"step": 725
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 1.59,
|
| 898 |
+
"learning_rate": 8.710805850137184e-05,
|
| 899 |
+
"loss": 3.7272,
|
| 900 |
+
"step": 730
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 1.6,
|
| 904 |
+
"learning_rate": 8.935249819044176e-05,
|
| 905 |
+
"loss": 3.6548,
|
| 906 |
+
"step": 735
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.61,
|
| 910 |
+
"learning_rate": 9.157274139492964e-05,
|
| 911 |
+
"loss": 3.6463,
|
| 912 |
+
"step": 740
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 1.62,
|
| 916 |
+
"learning_rate": 9.376619941057571e-05,
|
| 917 |
+
"loss": 3.484,
|
| 918 |
+
"step": 745
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 1.63,
|
| 922 |
+
"learning_rate": 9.593031476345212e-05,
|
| 923 |
+
"loss": 3.5106,
|
| 924 |
+
"step": 750
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 1.64,
|
| 928 |
+
"learning_rate": 9.80625641918636e-05,
|
| 929 |
+
"loss": 3.6845,
|
| 930 |
+
"step": 755
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 1.65,
|
| 934 |
+
"learning_rate": 0.00010016046158835706,
|
| 935 |
+
"loss": 3.5078,
|
| 936 |
+
"step": 760
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 1.66,
|
| 940 |
+
"learning_rate": 0.00010222156089841198,
|
| 941 |
+
"loss": 3.62,
|
| 942 |
+
"step": 765
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 1.67,
|
| 946 |
+
"learning_rate": 0.00010424345897243078,
|
| 947 |
+
"loss": 3.644,
|
| 948 |
+
"step": 770
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.68,
|
| 952 |
+
"learning_rate": 0.00010622379836770322,
|
| 953 |
+
"loss": 3.7684,
|
| 954 |
+
"step": 775
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 1.7,
|
| 958 |
+
"learning_rate": 0.00010816027009707987,
|
| 959 |
+
"loss": 3.5978,
|
| 960 |
+
"step": 780
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 1.71,
|
| 964 |
+
"learning_rate": 0.0001100506163211471,
|
| 965 |
+
"loss": 3.5937,
|
| 966 |
+
"step": 785
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 1.72,
|
| 970 |
+
"learning_rate": 0.00011189263298076723,
|
| 971 |
+
"loss": 3.6434,
|
| 972 |
+
"step": 790
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 1.73,
|
| 976 |
+
"learning_rate": 0.00011368417236691289,
|
| 977 |
+
"loss": 3.6893,
|
| 978 |
+
"step": 795
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.74,
|
| 982 |
+
"learning_rate": 0.00011542314562479964,
|
| 983 |
+
"loss": 3.6739,
|
| 984 |
+
"step": 800
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.75,
|
| 988 |
+
"learning_rate": 0.00011710752518939715,
|
| 989 |
+
"loss": 3.5122,
|
| 990 |
+
"step": 805
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.76,
|
| 994 |
+
"learning_rate": 0.00011873534714947934,
|
| 995 |
+
"loss": 3.6633,
|
| 996 |
+
"step": 810
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.77,
|
| 1000 |
+
"learning_rate": 0.00012030471353745696,
|
| 1001 |
+
"loss": 3.5101,
|
| 1002 |
+
"step": 815
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.78,
|
| 1006 |
+
"learning_rate": 0.00012181379454232318,
|
| 1007 |
+
"loss": 3.6736,
|
| 1008 |
+
"step": 820
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 1.79,
|
| 1012 |
+
"learning_rate": 0.00012326083064313103,
|
| 1013 |
+
"loss": 3.4271,
|
| 1014 |
+
"step": 825
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 1.8,
|
| 1018 |
+
"learning_rate": 0.0001246441346605163,
|
| 1019 |
+
"loss": 3.5088,
|
| 1020 |
+
"step": 830
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 1.82,
|
| 1024 |
+
"learning_rate": 0.00012596209372387317,
|
| 1025 |
+
"loss": 3.5845,
|
| 1026 |
+
"step": 835
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 1.83,
|
| 1030 |
+
"learning_rate": 0.0001272131711518891,
|
| 1031 |
+
"loss": 3.6172,
|
| 1032 |
+
"step": 840
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.84,
|
| 1036 |
+
"learning_rate": 0.00012839590824424672,
|
| 1037 |
+
"loss": 3.5649,
|
| 1038 |
+
"step": 845
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 1.85,
|
| 1042 |
+
"learning_rate": 0.00012950892598240292,
|
| 1043 |
+
"loss": 3.5506,
|
| 1044 |
+
"step": 850
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 1.86,
|
| 1048 |
+
"learning_rate": 0.00013055092663746294,
|
| 1049 |
+
"loss": 3.4779,
|
| 1050 |
+
"step": 855
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 1.87,
|
| 1054 |
+
"learning_rate": 0.00013152069528327408,
|
| 1055 |
+
"loss": 3.5707,
|
| 1056 |
+
"step": 860
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 1.88,
|
| 1060 |
+
"learning_rate": 0.00013241710121297533,
|
| 1061 |
+
"loss": 3.497,
|
| 1062 |
+
"step": 865
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 1.89,
|
| 1066 |
+
"learning_rate": 0.0001332390992573511,
|
| 1067 |
+
"loss": 3.6343,
|
| 1068 |
+
"step": 870
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 1.9,
|
| 1072 |
+
"learning_rate": 0.00013398573100345144,
|
| 1073 |
+
"loss": 3.5251,
|
| 1074 |
+
"step": 875
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.91,
|
| 1078 |
+
"learning_rate": 0.00013465612591205902,
|
| 1079 |
+
"loss": 3.7421,
|
| 1080 |
+
"step": 880
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 1.92,
|
| 1084 |
+
"learning_rate": 0.00013524950233269879,
|
| 1085 |
+
"loss": 3.5967,
|
| 1086 |
+
"step": 885
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"epoch": 1.93,
|
| 1090 |
+
"learning_rate": 0.00013576516841500732,
|
| 1091 |
+
"loss": 3.5853,
|
| 1092 |
+
"step": 890
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 1.95,
|
| 1096 |
+
"learning_rate": 0.0001362025229153997,
|
| 1097 |
+
"loss": 3.7016,
|
| 1098 |
+
"step": 895
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 1.96,
|
| 1102 |
+
"learning_rate": 0.00013656105589809228,
|
| 1103 |
+
"loss": 3.7649,
|
| 1104 |
+
"step": 900
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 1.97,
|
| 1108 |
+
"learning_rate": 0.0001368403493296653,
|
| 1109 |
+
"loss": 3.6488,
|
| 1110 |
+
"step": 905
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 1.98,
|
| 1114 |
+
"learning_rate": 0.000137040077566471,
|
| 1115 |
+
"loss": 3.5113,
|
| 1116 |
+
"step": 910
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.99,
|
| 1120 |
+
"learning_rate": 0.00013716000773431953,
|
| 1121 |
+
"loss": 3.4688,
|
| 1122 |
+
"step": 915
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 2.0,
|
| 1126 |
+
"learning_rate": 0.0001372,
|
| 1127 |
+
"loss": 3.5363,
|
| 1128 |
+
"step": 920
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 2.0,
|
| 1132 |
+
"eval_loss": 3.550342321395874,
|
| 1133 |
+
"eval_runtime": 15.5302,
|
| 1134 |
+
"eval_samples_per_second": 38.892,
|
| 1135 |
+
"eval_steps_per_second": 4.894,
|
| 1136 |
+
"step": 920
|
| 1137 |
}
|
| 1138 |
],
|
| 1139 |
+
"max_steps": 920,
|
| 1140 |
+
"num_train_epochs": 2,
|
| 1141 |
+
"total_flos": 959594987520000.0,
|
| 1142 |
"trial_name": null,
|
| 1143 |
"trial_params": null
|
| 1144 |
}
|
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:b5708224240385f21adb137af8222892ce526560dfb553f1518c008662fb3365
|
| 3 |
size 2671
|