Model save
Browse files- README.md +82 -0
- generation_config.json +6 -0
README.md
ADDED
|
@@ -0,0 +1,82 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: mit
|
| 4 |
+
base_model: gpt2
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: music-generation
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# music-generation
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.5312
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0001
|
| 39 |
+
- train_batch_size: 16
|
| 40 |
+
- eval_batch_size: 16
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 16
|
| 43 |
+
- total_train_batch_size: 256
|
| 44 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_steps: 100
|
| 47 |
+
- num_epochs: 20
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 54 |
+
| 3.7238 | 0.9217 | 100 | 2.8460 |
|
| 55 |
+
| 2.4643 | 1.8387 | 200 | 1.8829 |
|
| 56 |
+
| 1.8339 | 2.7558 | 300 | 1.4234 |
|
| 57 |
+
| 1.5013 | 3.6728 | 400 | 1.2203 |
|
| 58 |
+
| 1.3125 | 4.5899 | 500 | 1.0966 |
|
| 59 |
+
| 1.1899 | 5.5069 | 600 | 1.0028 |
|
| 60 |
+
| 1.0982 | 6.4240 | 700 | 0.9353 |
|
| 61 |
+
| 1.0302 | 7.3410 | 800 | 0.8779 |
|
| 62 |
+
| 0.9766 | 8.2581 | 900 | 0.8276 |
|
| 63 |
+
| 0.9243 | 9.1751 | 1000 | 0.7757 |
|
| 64 |
+
| 0.8825 | 10.0922 | 1100 | 0.7345 |
|
| 65 |
+
| 0.845 | 11.0092 | 1200 | 0.7000 |
|
| 66 |
+
| 0.8083 | 11.9309 | 1300 | 0.6624 |
|
| 67 |
+
| 0.7784 | 12.8479 | 1400 | 0.6328 |
|
| 68 |
+
| 0.7502 | 13.7650 | 1500 | 0.6052 |
|
| 69 |
+
| 0.7281 | 14.6820 | 1600 | 0.5816 |
|
| 70 |
+
| 0.7072 | 15.5991 | 1700 | 0.5622 |
|
| 71 |
+
| 0.6903 | 16.5161 | 1800 | 0.5486 |
|
| 72 |
+
| 0.6796 | 17.4332 | 1900 | 0.5386 |
|
| 73 |
+
| 0.6705 | 18.3502 | 2000 | 0.5335 |
|
| 74 |
+
| 0.6646 | 19.2673 | 2100 | 0.5312 |
|
| 75 |
+
|
| 76 |
+
|
| 77 |
+
### Framework versions
|
| 78 |
+
|
| 79 |
+
- Transformers 4.55.0
|
| 80 |
+
- Pytorch 2.6.0+cu124
|
| 81 |
+
- Datasets 4.0.0
|
| 82 |
+
- Tokenizers 0.21.4
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 0,
|
| 5 |
+
"transformers_version": "4.55.0"
|
| 6 |
+
}
|