AlekseyKorshuk commited on
Commit
8422a17
1 Parent(s): c7221a1

huggingartists

Browse files
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/2myyormf/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/7knioj7l) for full transparency and reproducibility.
55
 
56
- At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/7knioj7l/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
 
45
  dataset = load_dataset("huggingartists/6ix9ine")
46
  ```
47
 
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/23c4qor5/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/8askquwf) for full transparency and reproducibility.
55
 
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/8askquwf/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
evaluation.txt CHANGED
@@ -1 +1 @@
1
- {"eval_loss": 2.900149345397949, "eval_runtime": 2.5222, "eval_samples_per_second": 21.013, "eval_steps_per_second": 2.775, "epoch": 3.0}
 
1
+ {"eval_loss": 2.566208600997925, "eval_runtime": 2.6338, "eval_samples_per_second": 20.882, "eval_steps_per_second": 2.658, "epoch": 4.0}
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9509193c5fd5514fa34c5b8e4deef5d7ef27e6f54a88541e72dc9bbdcf0a7cd
3
  size 497764120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1828e0611eb3dd2b0e31ca17d4310d4d7489f09c72ac60fd8ea14bbf161796e
3
  size 497764120
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ab2bc41a7353a377e1364b89258475aeb37844383ea22bc18242bc8ff867965
3
  size 995603825
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41f3f5703dac31ae7a5401c632b68029d736e86bfffe760b46a0f472c96db60
3
  size 995603825
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30fde55c2cd1fd62cf61de771d05ea50c736a8b1286a06e577692582cfdeed20
3
  size 510403817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8d9d316dc2aba5868d7f29d4e845259d1702edafe69690c706ad4d698822e2
3
  size 510403817
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc87f4591da50bc4de4f46a7c5f73ef224136f280b5366df533254560016512d
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21430a2736694d7f20ccf719d4c7704a6abda2499225d98352d67c327ad5baa9
3
  size 14503
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:744fcc656fe1f449c2ea79ccccba224c3e3c1abb31179e9ce51f592461ac2c71
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81c6de287d0aeee2c682cd2a01e5e01657f181e757ee594a86aa0945f540d0b1
3
  size 623
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 2.900149345397949,
3
- "best_model_checkpoint": "output/6ix9ine/checkpoint-126",
4
- "epoch": 3.0,
5
- "global_step": 126,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -180,11 +180,67 @@
180
  "eval_samples_per_second": 20.775,
181
  "eval_steps_per_second": 2.744,
182
  "step": 126
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
183
  }
184
  ],
185
- "max_steps": 126,
186
- "num_train_epochs": 3,
187
- "total_flos": 129600847872000.0,
188
  "trial_name": null,
189
  "trial_params": null
190
  }
 
1
  {
2
+ "best_metric": 2.566208600997925,
3
+ "best_model_checkpoint": "output/6ix9ine/checkpoint-168",
4
+ "epoch": 4.0,
5
+ "global_step": 168,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
180
  "eval_samples_per_second": 20.775,
181
  "eval_steps_per_second": 2.744,
182
  "step": 126
183
+ },
184
+ {
185
+ "epoch": 3.1,
186
+ "learning_rate": 0.00013415229447692926,
187
+ "loss": 2.6428,
188
+ "step": 130
189
+ },
190
+ {
191
+ "epoch": 3.21,
192
+ "learning_rate": 0.00012223363969730686,
193
+ "loss": 2.6782,
194
+ "step": 135
195
+ },
196
+ {
197
+ "epoch": 3.33,
198
+ "learning_rate": 0.00010290000000000009,
199
+ "loss": 2.6065,
200
+ "step": 140
201
+ },
202
+ {
203
+ "epoch": 3.45,
204
+ "learning_rate": 7.882429945968553e-05,
205
+ "loss": 2.5807,
206
+ "step": 145
207
+ },
208
+ {
209
+ "epoch": 3.57,
210
+ "learning_rate": 5.333506393059687e-05,
211
+ "loss": 2.5988,
212
+ "step": 150
213
+ },
214
+ {
215
+ "epoch": 3.69,
216
+ "learning_rate": 2.9956244016835525e-05,
217
+ "loss": 2.5281,
218
+ "step": 155
219
+ },
220
+ {
221
+ "epoch": 3.81,
222
+ "learning_rate": 1.1920020081922795e-05,
223
+ "loss": 2.6676,
224
+ "step": 160
225
+ },
226
+ {
227
+ "epoch": 3.93,
228
+ "learning_rate": 1.7199452243269073e-06,
229
+ "loss": 2.6813,
230
+ "step": 165
231
+ },
232
+ {
233
+ "epoch": 4.0,
234
+ "eval_loss": 2.566208600997925,
235
+ "eval_runtime": 2.6398,
236
+ "eval_samples_per_second": 20.835,
237
+ "eval_steps_per_second": 2.652,
238
+ "step": 168
239
  }
240
  ],
241
+ "max_steps": 168,
242
+ "num_train_epochs": 4,
243
+ "total_flos": 172714033152000.0,
244
  "trial_name": null,
245
  "trial_params": null
246
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e93bb873917a9ff90818f9d9ee0e70a0a0c0493fe6d3d599f966dfc8cd40a4e
3
  size 2863
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecac0d19b2e1f0f637a36c6ba81af1b5f98eeb060b14910c27f5bc5242b68a0d
3
  size 2863