AlekseyKorshuk commited on
Commit
720a1af
1 Parent(s): 51fbe29

huggingartists

Browse files
README.md CHANGED
@@ -45,15 +45,15 @@ from datasets import load_dataset
45
  dataset = load_dataset("huggingartists/tanzy-minus")
46
  ```
47
 
48
- [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/17sshu4k/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 Танцы Минус (Tanzy Minus)'s lyrics.
53
 
54
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/30av9l8d) for full transparency and reproducibility.
55
 
56
- At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/30av9l8d/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
 
45
  dataset = load_dataset("huggingartists/tanzy-minus")
46
  ```
47
 
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/14vmwaxq/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 Танцы Минус (Tanzy Minus)'s lyrics.
53
 
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/ru5wxieh) for full transparency and reproducibility.
55
 
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/ru5wxieh/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
1
  {
2
+ "_name_or_path": "huggingartists/tanzy-minus",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
evaluation.txt CHANGED
@@ -1 +1 @@
1
- {"eval_loss": 2.3025755882263184, "eval_runtime": 0.0684, "eval_samples_per_second": 14.628, "eval_steps_per_second": 14.628, "epoch": 1.0}
 
1
+ {"eval_loss": 2.2600128650665283, "eval_runtime": 0.0702, "eval_samples_per_second": 14.242, "eval_steps_per_second": 14.242, "epoch": 2.0}
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a51a4f2a2967f74397b7fd94bf6b1b988bae0854a168721170a55f426ad0ca84
3
  size 497764120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:deea6216f8bd0fc3ecd3c921e0294f800b584b7c0470e376e4deaed72cd729c9
3
  size 497764120
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c675fdebdd92cc6c93793a6c883f866602cd0e2e0d3a605740d28f9a6df02ec9
3
  size 995603825
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36b2f63ea74e748017933e056f13001e95e1cb0383acd18b6fc37604fa60c00a
3
  size 995603825
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6b20329a63e2d962c173b530a08535b50829ccbe9d69a462adab696216abcd9
3
  size 510403817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0a084eb21589a31d2f71fdd846ad97bf74fe5a77c379cd435f159619fb85a42
3
  size 510403817
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f05ab89097ecebe552ad2f2339170c107b7844ee48669607b1b463055a12c92e
3
- size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34de8d1658e0de5a34053983dc4c4f7d60b43f48aa10eaadbd98f3546900423c
3
+ size 14567
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65743554f2ecb2daf21a2ff122c42c16f71111e187870af247c6234935d13ea2
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bed544ea42e37a9349fba621b6d9d0a1264bcf93ade35290aea045a6f78dd156
3
  size 623
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
 
1
+ {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "huggingartists/tanzy-minus", "tokenizer_class": "GPT2Tokenizer"}
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 2.3025755882263184,
3
- "best_model_checkpoint": "output/tanzy-minus/checkpoint-3",
4
- "epoch": 1.0,
5
- "global_step": 3,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -14,11 +14,25 @@
14
  "eval_samples_per_second": 12.994,
15
  "eval_steps_per_second": 12.994,
16
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  }
18
  ],
19
- "max_steps": 3,
20
- "num_train_epochs": 1,
21
- "total_flos": 2482274304000.0,
22
  "trial_name": null,
23
  "trial_params": null
24
  }
 
1
  {
2
+ "best_metric": 2.2600128650665283,
3
+ "best_model_checkpoint": "output/tanzy-minus/checkpoint-6",
4
+ "epoch": 2.0,
5
+ "global_step": 6,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
14
  "eval_samples_per_second": 12.994,
15
  "eval_steps_per_second": 12.994,
16
  "step": 3
17
+ },
18
+ {
19
+ "epoch": 1.67,
20
+ "learning_rate": 0.00010290000000000001,
21
+ "loss": 2.2031,
22
+ "step": 5
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "eval_loss": 2.2600128650665283,
27
+ "eval_runtime": 0.0621,
28
+ "eval_samples_per_second": 16.098,
29
+ "eval_steps_per_second": 16.098,
30
+ "step": 6
31
  }
32
  ],
33
+ "max_steps": 6,
34
+ "num_train_epochs": 2,
35
+ "total_flos": 4964548608000.0,
36
  "trial_name": null,
37
  "trial_params": null
38
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b98969a3260a09b2c0aff1884f9c7feff1d176efab4a24d83b2f5a8246c0ebe1
3
  size 2863
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1306bb5b67c8064524955487b58bead8a4593dcddbc57da84258f4313a5a5126
3
  size 2863