AlekseyKorshuk
commited on
Commit
•
50d3bb6
1
Parent(s):
8422a17
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 +63 -7
- training_args.bin +1 -1
README.md
CHANGED
@@ -45,15 +45,15 @@ from datasets import load_dataset
|
|
45 |
dataset = load_dataset("huggingartists/6ix9ine")
|
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 6ix9ine'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/6ix9ine")
|
46 |
```
|
47 |
|
48 |
+
[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/eqmcaj0r/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 6ix9ine's lyrics.
|
53 |
|
54 |
+
Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/s5dpg3h2) for full transparency and reproducibility.
|
55 |
|
56 |
+
At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/s5dpg3h2/artifacts) is logged and versioned.
|
57 |
|
58 |
## How to use
|
59 |
|
evaluation.txt
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"eval_loss": 2.
|
|
|
1 |
+
{"eval_loss": 2.4751908779144287, "eval_runtime": 3.052, "eval_samples_per_second": 20.97, "eval_steps_per_second": 2.621, "epoch": 5.0}
|
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:b3f1fd139ad3512f861c6cd5592c2ace1fac98271efc42a42e36236dd6c48b59
|
3 |
size 497764120
|
optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 995603825
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aceace990143d629f3db6198ece7069e41e3adcbd2ede64c0751815e4e703dab
|
3 |
size 995603825
|
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:dd7892196cf4da7ad9d98e0b4363158ba3daf1bd31982643189b086d83d48268
|
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 sha256:9a2571a29377ff85a1a70c33edf6c6403f4d3f4301398dc6bfae9afd8ec5e8db
|
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 sha256:851e454e65c7fab7dc2d566df885ced9c351f3fb626f4834f3f43f9a6d1bcacf
|
3 |
size 623
|
trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "output/6ix9ine/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -236,11 +236,67 @@
|
|
236 |
"eval_samples_per_second": 20.835,
|
237 |
"eval_steps_per_second": 2.652,
|
238 |
"step": 168
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
239 |
}
|
240 |
],
|
241 |
-
"max_steps":
|
242 |
-
"num_train_epochs":
|
243 |
-
"total_flos":
|
244 |
"trial_name": null,
|
245 |
"trial_params": null
|
246 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.4751908779144287,
|
3 |
+
"best_model_checkpoint": "output/6ix9ine/checkpoint-205",
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 205,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
236 |
"eval_samples_per_second": 20.835,
|
237 |
"eval_steps_per_second": 2.652,
|
238 |
"step": 168
|
239 |
+
},
|
240 |
+
{
|
241 |
+
"epoch": 4.15,
|
242 |
+
"learning_rate": 9.63352496067802e-06,
|
243 |
+
"loss": 2.2438,
|
244 |
+
"step": 170
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 4.27,
|
248 |
+
"learning_rate": 2.7012936807688713e-05,
|
249 |
+
"loss": 2.4722,
|
250 |
+
"step": 175
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 4.39,
|
254 |
+
"learning_rate": 5.042226894930893e-05,
|
255 |
+
"loss": 2.5159,
|
256 |
+
"step": 180
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 4.51,
|
260 |
+
"learning_rate": 7.646728298233023e-05,
|
261 |
+
"loss": 2.2916,
|
262 |
+
"step": 185
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 4.63,
|
266 |
+
"learning_rate": 0.00010137157954994105,
|
267 |
+
"loss": 2.3591,
|
268 |
+
"step": 190
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 4.76,
|
272 |
+
"learning_rate": 0.00012152415773578518,
|
273 |
+
"loss": 2.7456,
|
274 |
+
"step": 195
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 4.88,
|
278 |
+
"learning_rate": 0.0001340029924949682,
|
279 |
+
"loss": 2.4208,
|
280 |
+
"step": 200
|
281 |
+
},
|
282 |
+
{
|
283 |
+
"epoch": 5.0,
|
284 |
+
"learning_rate": 0.0001369987139612046,
|
285 |
+
"loss": 2.3052,
|
286 |
+
"step": 205
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 5.0,
|
290 |
+
"eval_loss": 2.4751908779144287,
|
291 |
+
"eval_runtime": 3.015,
|
292 |
+
"eval_samples_per_second": 21.227,
|
293 |
+
"eval_steps_per_second": 2.653,
|
294 |
+
"step": 205
|
295 |
}
|
296 |
],
|
297 |
+
"max_steps": 205,
|
298 |
+
"num_train_epochs": 5,
|
299 |
+
"total_flos": 210470731776000.0,
|
300 |
"trial_name": null,
|
301 |
"trial_params": null
|
302 |
}
|
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 sha256:60e6f694485954cbb3712355594581b180503eb9abe9206152317c41a5b1ee51
|
3 |
size 2863
|