|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: gpt2-medium |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: lyrics-main |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# lyrics-main |
|
|
|
This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.0601 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-05 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 3.7651 | 0.1550 | 50 | 3.4887 | |
|
| 3.6031 | 0.3101 | 100 | 3.3498 | |
|
| 3.4463 | 0.4651 | 150 | 3.2707 | |
|
| 3.4016 | 0.6202 | 200 | 3.2325 | |
|
| 3.3733 | 0.7752 | 250 | 3.2004 | |
|
| 3.3827 | 0.9302 | 300 | 3.1764 | |
|
| 3.1805 | 1.0853 | 350 | 3.1566 | |
|
| 3.1353 | 1.2403 | 400 | 3.1435 | |
|
| 3.1613 | 1.3953 | 450 | 3.1296 | |
|
| 3.2172 | 1.5504 | 500 | 3.1210 | |
|
| 3.1419 | 1.7054 | 550 | 3.1074 | |
|
| 3.0979 | 1.8605 | 600 | 3.0954 | |
|
| 3.1357 | 2.0155 | 650 | 3.0860 | |
|
| 2.9513 | 2.1705 | 700 | 3.0827 | |
|
| 2.9206 | 2.3256 | 750 | 3.0738 | |
|
| 2.9016 | 2.4806 | 800 | 3.0678 | |
|
| 2.9043 | 2.6357 | 850 | 3.0620 | |
|
| 3.0086 | 2.7907 | 900 | 3.0606 | |
|
| 2.9851 | 2.9457 | 950 | 3.0601 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.2 |
|
- Pytorch 2.5.1+cu121 |
|
- Tokenizers 0.20.3 |
|
|
