AlekseyKorshuk commited on
Commit
f00cb76
1 Parent(s): 2be8f97

huggingartists

Browse files
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/tusv3cma/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/kcn90ud5) for full transparency and reproducibility.
55
 
56
- At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/kcn90ud5/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
 
45
  dataset = load_dataset("huggingartists/eminem")
46
  ```
47
 
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1tfdfdyn/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/2oam1me5) for full transparency and reproducibility.
55
 
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2oam1me5/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
evaluation.txt CHANGED
@@ -1 +1 @@
1
- {"eval_loss": 0.15162613987922668, "eval_runtime": 14.5602, "eval_samples_per_second": 44.23, "eval_steps_per_second": 5.563, "epoch": 2.0}
 
1
+ {"eval_loss": 0.13430377840995789, "eval_runtime": 14.0446, "eval_samples_per_second": 44.43, "eval_steps_per_second": 5.554, "epoch": 2.0}
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7761ecce8eb19c94742f6c9fd9bee473e591dcc45cbcb2ee94e93dee113edf7
3
  size 497764120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f31ed1a889f71569ec3a441f9ef396888cfb72a5e5321c231c3f7e3422f2e3a
3
  size 497764120
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4476e576f6e7c72bcefb1035b67b146bab7f5ece7faedb85e92bffb11d4796ce
3
  size 995604017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8304c5fd2768fa01ba9b5712d995a5731bfc92f999564aa85fb2fc766e8d8311
3
  size 995604017
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5516fb13956d24eaaff944923fb65d6b9148d14860382a06da5c8132587cd3dc
3
  size 510396521
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2036ba89317ecba125c1a82916377c1352593504a5278d40be3161990dfc19f9
3
  size 510396521
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27912df59e20e4b2d528762eeb52cf6b416a98f296d07fe6caab6324eee7cd93
3
  size 14567
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91789756b00c246c75939e963082e15fe38636b3074ce10218a12d23c35888d0
3
  size 14567
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7dd0d4fbaf273821538ccb639a7a35444f70ec1b31c607e5a8601956d595803c
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:573b86203c7261a17ef6809968ba821e820b1e71725b2471dc35d45266479890
3
  size 623
tokenizer_config.json CHANGED
@@ -3,7 +3,7 @@
3
  "bos_token": "<|endoftext|>",
4
  "eos_token": "<|endoftext|>",
5
  "model_max_length": 1024,
6
- "name_or_path": "gpt2",
7
  "special_tokens_map_file": null,
8
  "tokenizer_class": "GPT2Tokenizer",
9
  "unk_token": "<|endoftext|>"
 
3
  "bos_token": "<|endoftext|>",
4
  "eos_token": "<|endoftext|>",
5
  "model_max_length": 1024,
6
+ "name_or_path": "huggingartists/eminem",
7
  "special_tokens_map_file": null,
8
  "tokenizer_class": "GPT2Tokenizer",
9
  "unk_token": "<|endoftext|>"
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.15162613987922668,
3
- "best_model_checkpoint": "output/eminem/checkpoint-455",
4
  "epoch": 1.0,
5
- "global_step": 455,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -568,11 +568,19 @@
568
  "eval_samples_per_second": 48.139,
569
  "eval_steps_per_second": 6.055,
570
  "step": 455
 
 
 
 
 
 
 
 
571
  }
572
  ],
573
- "max_steps": 910,
574
  "num_train_epochs": 2,
575
- "total_flos": 474636976128000.0,
576
  "trial_name": null,
577
  "trial_params": null
578
  }
 
1
  {
2
+ "best_metric": 0.13430377840995789,
3
+ "best_model_checkpoint": "output/eminem/checkpoint-457",
4
  "epoch": 1.0,
5
+ "global_step": 457,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
568
  "eval_samples_per_second": 48.139,
569
  "eval_steps_per_second": 6.055,
570
  "step": 455
571
+ },
572
+ {
573
+ "epoch": 1.0,
574
+ "eval_loss": 0.13430377840995789,
575
+ "eval_runtime": 12.7773,
576
+ "eval_samples_per_second": 48.837,
577
+ "eval_steps_per_second": 6.105,
578
+ "step": 457
579
  }
580
  ],
581
+ "max_steps": 914,
582
  "num_train_epochs": 2,
583
+ "total_flos": 476466020352000.0,
584
  "trial_name": null,
585
  "trial_params": null
586
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8430f2d6c4d4f936bbbf8c552b5578f9269d0dd84df240e93b07571cd47afa8e
3
  size 3311
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ddd6b3bcc43d3e1b4aaa3a7e199709a9472aec3721534af1679511cccab1a47
3
  size 3311