AlekseyKorshuk
commited on
Commit
•
16d8d65
1
Parent(s):
4cdd93d
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 +2 -2
- scheduler.pt +1 -1
- trainer_state.json +26 -6
- training_args.bin +1 -1
README.md
CHANGED
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
45 |
dataset = load_dataset("huggingartists/morgenshtern")
|
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 MORGENSHTERN'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/morgenshtern")
|
46 |
```
|
47 |
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2mqz06ef/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 MORGENSHTERN's lyrics.
|
53 |
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1u21f1zw) for full transparency and reproducibility.
|
55 |
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1u21f1zw/artifacts) is logged and versioned.
|
57 |
|
58 |
## How to use
|
59 |
|
evaluation.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eval_loss": 1.
|
|
|
1 |
+
{"eval_loss": 1.029100775718689, "eval_runtime": 7.2168, "eval_samples_per_second": 20.508, "eval_steps_per_second": 2.633, "epoch": 21.0}
|
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 sha256:22fb23883fc29f2e2299e376a3685d3899aa27180ebd009e6a276dd79c0f549a
|
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 sha256:6cae6db0edbbd42bbc453b0149987a6ee3a6ba790c60e2925ab382f8c1f160ba
|
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:b0d244ecace2e78de24953f6135d7cc932ff6489b68a4c749677efd661e57029
|
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 sha256:76d31626c3bac6215c579c04c793834783bc9d247d3009c55526f8f7392b8d8e
|
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 sha256:5d04e24471eba096654369d2172acef6ba07c54938134ee47e6aca1b621eca74
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "output/morgenshtern/checkpoint-
|
4 |
"epoch": 13.0,
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1654,11 +1654,31 @@
|
|
1654 |
"eval_samples_per_second": 22.241,
|
1655 |
"eval_steps_per_second": 2.851,
|
1656 |
"step": 1261
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1657 |
}
|
1658 |
],
|
1659 |
-
"max_steps":
|
1660 |
-
"num_train_epochs":
|
1661 |
-
"total_flos":
|
1662 |
"trial_name": null,
|
1663 |
"trial_params": null
|
1664 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.029100775718689,
|
3 |
+
"best_model_checkpoint": "output/morgenshtern/checkpoint-1274",
|
4 |
"epoch": 13.0,
|
5 |
+
"global_step": 1274,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1654 |
"eval_samples_per_second": 22.241,
|
1655 |
"eval_steps_per_second": 2.851,
|
1656 |
"step": 1261
|
1657 |
+
},
|
1658 |
+
{
|
1659 |
+
"epoch": 12.91,
|
1660 |
+
"learning_rate": 2.835385281685176e-06,
|
1661 |
+
"loss": 1.0594,
|
1662 |
+
"step": 1265
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 12.96,
|
1666 |
+
"learning_rate": 5.632050517253284e-07,
|
1667 |
+
"loss": 1.1527,
|
1668 |
+
"step": 1270
|
1669 |
+
},
|
1670 |
+
{
|
1671 |
+
"epoch": 13.0,
|
1672 |
+
"eval_loss": 1.029100775718689,
|
1673 |
+
"eval_runtime": 6.9675,
|
1674 |
+
"eval_samples_per_second": 21.242,
|
1675 |
+
"eval_steps_per_second": 2.727,
|
1676 |
+
"step": 1274
|
1677 |
}
|
1678 |
],
|
1679 |
+
"max_steps": 2058,
|
1680 |
+
"num_train_epochs": 21,
|
1681 |
+
"total_flos": 1320047345664000.0,
|
1682 |
"trial_name": null,
|
1683 |
"trial_params": null
|
1684 |
}
|
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 sha256:188b9cc77247d315e833007ec5b6ee4bead6e01dfa5781ac98b51d69684404d5
|
3 |
size 2671
|