Commit
•
608729c
1
Parent(s):
70e8d8c
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 +32 -6
- 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/2g2pefri/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/1cgpsnr9) for full transparency and reproducibility.
|
55 |
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1cgpsnr9/artifacts) is logged and versioned.
|
57 |
|
58 |
## How to use
|
59 |
|
evaluation.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eval_loss": 0.
|
|
|
1 |
+
{"eval_loss": 0.39583703875541687, "eval_runtime": 15.6845, "eval_samples_per_second": 40.996, "eval_steps_per_second": 5.164, "epoch": 3.0}
|
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 sha256:7cd580cdd6ae182fb6891fb3ab9c245878150973faa325cd10a031212867a481
|
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 sha256:7a56d81e45519802258d85034e9d148ff2c2b39b2cdab1bf361d45db8afd0826
|
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 sha256:84e26d6c93df97456fef9936ec00c747b477c398b1ba8e7fd2e39abb2d9d5485
|
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:de1ca01a858269cc17577c848b7dfeb3a25a3f97086ed6a27be4b05c3cb771b1
|
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:f2184305b4be28c3d577fb5099adb7f1233c0a22282f0740498d93642171b606
|
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": 2.0,
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -1096,11 +1096,37 @@
|
|
1096 |
"eval_samples_per_second": 20.587,
|
1097 |
"eval_steps_per_second": 2.588,
|
1098 |
"step": 898
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1099 |
}
|
1100 |
],
|
1101 |
-
"max_steps":
|
1102 |
-
"num_train_epochs":
|
1103 |
-
"total_flos":
|
1104 |
"trial_name": null,
|
1105 |
"trial_params": null
|
1106 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.39583703875541687,
|
3 |
+
"best_model_checkpoint": "output/eminem/checkpoint-910",
|
4 |
"epoch": 2.0,
|
5 |
+
"global_step": 910,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
1096 |
"eval_samples_per_second": 20.587,
|
1097 |
"eval_steps_per_second": 2.588,
|
1098 |
"step": 898
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 1.98,
|
1102 |
+
"learning_rate": 0.00013331119038948074,
|
1103 |
+
"loss": 0.7724,
|
1104 |
+
"step": 900
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 1.99,
|
1108 |
+
"learning_rate": 0.0001340585253974795,
|
1109 |
+
"loss": 0.7496,
|
1110 |
+
"step": 905
|
1111 |
+
},
|
1112 |
+
{
|
1113 |
+
"epoch": 2.0,
|
1114 |
+
"learning_rate": 0.0001347278522437355,
|
1115 |
+
"loss": 0.8119,
|
1116 |
+
"step": 910
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 2.0,
|
1120 |
+
"eval_loss": 0.39583703875541687,
|
1121 |
+
"eval_runtime": 13.6672,
|
1122 |
+
"eval_samples_per_second": 47.047,
|
1123 |
+
"eval_steps_per_second": 5.927,
|
1124 |
+
"step": 910
|
1125 |
}
|
1126 |
],
|
1127 |
+
"max_steps": 1365,
|
1128 |
+
"num_train_epochs": 3,
|
1129 |
+
"total_flos": 949404598272000.0,
|
1130 |
"trial_name": null,
|
1131 |
"trial_params": null
|
1132 |
}
|
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 sha256:772e3af6dfbf093ace803be6f7a82ae09aba1a764d9501254be31303aa54425c
|
3 |
size 3055
|