AlekseyKorshuk commited on
Commit
8bb79ae
1 Parent(s): 6309bc1

huggingartists

Browse files
README.md CHANGED
@@ -14,11 +14,11 @@ widget:
14
  <div class="inline-flex flex-col" style="line-height: 1.5;">
15
  <div class="flex">
16
  <div
17
- style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/22e752c5e4e7e4d2e8488babffb33bbf.1000x1000x1.jpg&#39;)">
18
  </div>
19
  </div>
20
  <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
21
- <div style="text-align: center; font-size: 16px; font-weight: 800">MORGENSHTERN</div>
22
  <a href="https://genius.com/artists/slava-marlow">
23
  <div style="text-align: center; font-size: 14px;">@slava-marlow</div>
24
  </a>
@@ -34,7 +34,7 @@ To understand how the model was developed, check the [W&B report](https://wandb.
34
 
35
  ## Training data
36
 
37
- The model was trained on lyrics from MORGENSHTERN.
38
 
39
  Dataset is available [here](https://huggingface.co/datasets/huggingartists/slava-marlow).
40
  And can be used with:
@@ -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/3sgmpuhy/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/omn4wgyz) for full transparency and reproducibility.
55
 
56
- At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/omn4wgyz/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
 
14
  <div class="inline-flex flex-col" style="line-height: 1.5;">
15
  <div class="flex">
16
  <div
17
+ style="display:DISPLAY_1; margin-left: auto; margin-right: auto; width: 92px; height:92px; border-radius: 50%; background-size: cover; background-image: url(&#39;https://images.genius.com/e308b1bc9eeb159ecfa9d807d715f095.1000x1000x1.jpg&#39;)">
18
  </div>
19
  </div>
20
  <div style="text-align: center; margin-top: 3px; font-size: 16px; font-weight: 800">🤖 HuggingArtists Model 🤖</div>
21
+ <div style="text-align: center; font-size: 16px; font-weight: 800">SLAVA MARLOW</div>
22
  <a href="https://genius.com/artists/slava-marlow">
23
  <div style="text-align: center; font-size: 14px;">@slava-marlow</div>
24
  </a>
 
34
 
35
  ## Training data
36
 
37
+ The model was trained on lyrics from SLAVA MARLOW.
38
 
39
  Dataset is available [here](https://huggingface.co/datasets/huggingartists/slava-marlow).
40
  And can be used with:
 
45
  dataset = load_dataset("huggingartists/slava-marlow")
46
  ```
47
 
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/dajo6l0v/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/1djy4mi8) for full transparency and reproducibility.
55
 
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1djy4mi8/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
config.json CHANGED
@@ -35,7 +35,7 @@
35
  }
36
  },
37
  "torch_dtype": "float32",
38
- "transformers_version": "4.9.2",
39
  "use_cache": true,
40
  "vocab_size": 50257
41
  }
 
35
  }
36
  },
37
  "torch_dtype": "float32",
38
+ "transformers_version": "4.11.3",
39
  "use_cache": true,
40
  "vocab_size": 50257
41
  }
evaluation.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eval_loss": 1.5765409469604492, "eval_runtime": 8.007, "eval_samples_per_second": 21.232, "eval_steps_per_second": 2.748, "epoch": 3.0}
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df1b2b8983b832ed22b122c66ed7bf7c9ff715a4eb640f438af09f67c85dcdb3
3
  size 497764120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f31f81a0ff5da76be1d7744122ddaa1d4c33c954bdadcae9976300407273a91
3
  size 497764120
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96d52890222d19bf8524cb84e4a332cd839ef36dc1eac420a410a07722ca8431
3
  size 995604017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61f1c361c857b02d5d0830f1edf1460b1f7dab9003211a02897fe30b5bd91d1
3
  size 995604017
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dbce2307bb9b496425c8f71076a4a1c33b5a768103d6507e3eacaf6b99edcf0
3
  size 510403817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fc237e81048121824c38df56404ddd7899a39fab731a11c12988aa8ebd5164c
3
  size 510403817
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13c058b8fa70d384486107f733302e1b72d74991a369b69e1c49457273f7c177
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5960c90ad81f7699bd122a5bfa6732fd3b57d2883f4ba4ed0d4dd0a79b0596f4
3
  size 14503
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3be7b21ee2235eef38a55c0348c96600344a2bc81677cfa58e757a83abbb30f2
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8267538b8f71047573a2bf4b20b591f7a175ff510694f359e666cbbd6a22e8c0
3
  size 623
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": null,
3
- "best_model_checkpoint": null,
4
- "epoch": 2.0,
5
- "global_step": 260,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -318,11 +318,97 @@
318
  "learning_rate": 0.0001372,
319
  "loss": 1.7608,
320
  "step": 260
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
321
  }
322
  ],
323
- "max_steps": 260,
324
- "num_train_epochs": 2,
325
- "total_flos": 271221129216000.0,
326
  "trial_name": null,
327
  "trial_params": null
328
  }
 
1
  {
2
+ "best_metric": 1.5765409469604492,
3
+ "best_model_checkpoint": "output/slava-marlow/checkpoint-327",
4
+ "epoch": 3.0,
5
+ "global_step": 327,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
318
  "learning_rate": 0.0001372,
319
  "loss": 1.7608,
320
  "step": 260
321
+ },
322
+ {
323
+ "epoch": 2.43,
324
+ "learning_rate": 8.331367795957333e-05,
325
+ "loss": 1.7155,
326
+ "step": 265
327
+ },
328
+ {
329
+ "epoch": 2.48,
330
+ "learning_rate": 7.353868846414889e-05,
331
+ "loss": 1.6697,
332
+ "step": 270
333
+ },
334
+ {
335
+ "epoch": 2.52,
336
+ "learning_rate": 6.366131153585115e-05,
337
+ "loss": 1.5567,
338
+ "step": 275
339
+ },
340
+ {
341
+ "epoch": 2.57,
342
+ "learning_rate": 5.3886322040426775e-05,
343
+ "loss": 1.5568,
344
+ "step": 280
345
+ },
346
+ {
347
+ "epoch": 2.61,
348
+ "learning_rate": 4.441637217755689e-05,
349
+ "loss": 1.678,
350
+ "step": 285
351
+ },
352
+ {
353
+ "epoch": 2.66,
354
+ "learning_rate": 3.544779015521354e-05,
355
+ "loss": 1.5895,
356
+ "step": 290
357
+ },
358
+ {
359
+ "epoch": 2.71,
360
+ "learning_rate": 2.716650997114681e-05,
361
+ "loss": 1.6833,
362
+ "step": 295
363
+ },
364
+ {
365
+ "epoch": 2.75,
366
+ "learning_rate": 1.9744216684073583e-05,
367
+ "loss": 1.5874,
368
+ "step": 300
369
+ },
370
+ {
371
+ "epoch": 2.8,
372
+ "learning_rate": 1.333478708966784e-05,
373
+ "loss": 1.5961,
374
+ "step": 305
375
+ },
376
+ {
377
+ "epoch": 2.84,
378
+ "learning_rate": 8.071099592209943e-06,
379
+ "loss": 1.6268,
380
+ "step": 310
381
+ },
382
+ {
383
+ "epoch": 2.89,
384
+ "learning_rate": 4.062279408693099e-06,
385
+ "loss": 1.5704,
386
+ "step": 315
387
+ },
388
+ {
389
+ "epoch": 2.94,
390
+ "learning_rate": 1.3914362170045804e-06,
391
+ "loss": 1.5144,
392
+ "step": 320
393
+ },
394
+ {
395
+ "epoch": 2.98,
396
+ "learning_rate": 1.139411505919223e-07,
397
+ "loss": 1.753,
398
+ "step": 325
399
+ },
400
+ {
401
+ "epoch": 3.0,
402
+ "eval_loss": 1.5765409469604492,
403
+ "eval_runtime": 8.0085,
404
+ "eval_samples_per_second": 21.227,
405
+ "eval_steps_per_second": 2.747,
406
+ "step": 327
407
  }
408
  ],
409
+ "max_steps": 327,
410
+ "num_train_epochs": 3,
411
+ "total_flos": 340594163712000.0,
412
  "trial_name": null,
413
  "trial_params": null
414
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5906cf86decfa153fcf84533fd92086ce9d1eb8f6ff2a692ce1232bc92d20c5
3
- size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d77fa0328ab599e88846dcdcfe668efcd1424c4a8c70e39af87fe4768ee0b599
3
+ size 2863