AlekseyKorshuk
commited on
Commit
•
20c3f88
1
Parent(s):
8bb79ae
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 +20 -6
- training_args.bin +1 -1
README.md
CHANGED
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
45 |
dataset = load_dataset("huggingartists/slava-marlow")
|
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 SLAVA MARLOW'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/slava-marlow")
|
46 |
```
|
47 |
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1fdcz1s5/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 SLAVA MARLOW's lyrics.
|
53 |
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/ro4q353s) for full transparency and reproducibility.
|
55 |
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/ro4q353s/artifacts) is logged and versioned.
|
57 |
|
58 |
## How to use
|
59 |
|
evaluation.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eval_loss": 1.
|
|
|
1 |
+
{"eval_loss": 1.3606982231140137, "eval_runtime": 7.3833, "eval_samples_per_second": 21.129, "eval_steps_per_second": 2.709, "epoch": 4.0}
|
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 sha256:6de5112cbe4228b802fb6b2f1d86b9101d8c460145da927df0d9af62e9757cf1
|
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 sha256:6ae00f5bac3f0549cbee7f9952c6fd26ec32ab79e31649b794d02118952f2e52
|
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 sha256:70f27c25592190cf50121c5b3c309fea728d24a5d25c2956b78b878b1c9671b7
|
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:c45f584f404ff6c35b7f091be7f153b417156dd52345a73889f7b7af6e5bb990
|
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 sha256:268ef632d221476fc1686df5234f05a490d4a9176c570d0dcb5fdb5ff616d0fe
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "output/slava-marlow/checkpoint-
|
4 |
"epoch": 3.0,
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -404,11 +404,25 @@
|
|
404 |
"eval_samples_per_second": 21.227,
|
405 |
"eval_steps_per_second": 2.747,
|
406 |
"step": 327
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
407 |
}
|
408 |
],
|
409 |
-
"max_steps":
|
410 |
-
"num_train_epochs":
|
411 |
-
"total_flos":
|
412 |
"trial_name": null,
|
413 |
"trial_params": null
|
414 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.3606982231140137,
|
3 |
+
"best_model_checkpoint": "output/slava-marlow/checkpoint-333",
|
4 |
"epoch": 3.0,
|
5 |
+
"global_step": 333,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
404 |
"eval_samples_per_second": 21.227,
|
405 |
"eval_steps_per_second": 2.747,
|
406 |
"step": 327
|
407 |
+
},
|
408 |
+
{
|
409 |
+
"epoch": 2.97,
|
410 |
+
"learning_rate": 2.4713228598268823e-07,
|
411 |
+
"loss": 1.5213,
|
412 |
+
"step": 330
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 3.0,
|
416 |
+
"eval_loss": 1.3606982231140137,
|
417 |
+
"eval_runtime": 7.4703,
|
418 |
+
"eval_samples_per_second": 20.883,
|
419 |
+
"eval_steps_per_second": 2.677,
|
420 |
+
"step": 333
|
421 |
}
|
422 |
],
|
423 |
+
"max_steps": 444,
|
424 |
+
"num_train_epochs": 4,
|
425 |
+
"total_flos": 346081296384000.0,
|
426 |
"trial_name": null,
|
427 |
"trial_params": null
|
428 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2863
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bc20d77a5f3b1a200d6fd4c842752a456cf12cc4cfe556a9debe895cae75c6a
|
3 |
size 2863
|