|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: chord_model |
|
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. --> |
|
|
|
# chord_model |
|
|
|
This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4598 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 444 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine_with_restarts |
|
- lr_scheduler_warmup_ratio: 0.3 |
|
- training_steps: 0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 1.2264 | 0.11 | 500 | 1.1269 | |
|
| 0.9624 | 0.21 | 1000 | 0.9066 | |
|
| 0.8598 | 0.32 | 1500 | 0.8128 | |
|
| 0.8209 | 0.43 | 2000 | 0.7626 | |
|
| 0.7483 | 0.53 | 2500 | 0.7272 | |
|
| 0.7391 | 0.64 | 3000 | 0.7032 | |
|
| 0.7052 | 0.75 | 3500 | 0.6739 | |
|
| 0.6998 | 0.86 | 4000 | 0.6503 | |
|
| 0.6901 | 0.96 | 4500 | 0.6244 | |
|
| 0.6348 | 1.07 | 5000 | 0.6100 | |
|
| 0.654 | 1.18 | 5500 | 0.5891 | |
|
| 0.6227 | 1.28 | 6000 | 0.5765 | |
|
| 0.6148 | 1.39 | 6500 | 0.5624 | |
|
| 0.5973 | 1.5 | 7000 | 0.5538 | |
|
| 0.5853 | 1.6 | 7500 | 0.5441 | |
|
| 0.56 | 1.71 | 8000 | 0.5407 | |
|
| 0.574 | 1.82 | 8500 | 0.5342 | |
|
| 0.5589 | 1.92 | 9000 | 0.5296 | |
|
| 0.5634 | 2.03 | 9500 | 0.5254 | |
|
| 0.543 | 2.14 | 10000 | 0.5208 | |
|
| 0.5792 | 2.25 | 10500 | 0.5159 | |
|
| 0.5571 | 2.35 | 11000 | 0.5064 | |
|
| 0.5408 | 2.46 | 11500 | 0.4957 | |
|
| 0.5398 | 2.57 | 12000 | 0.4882 | |
|
| 0.537 | 2.67 | 12500 | 0.4834 | |
|
| 0.5512 | 2.78 | 13000 | 0.4786 | |
|
| 0.4842 | 2.89 | 13500 | 0.4753 | |
|
| 0.5275 | 2.99 | 14000 | 0.4721 | |
|
| 0.4899 | 3.1 | 14500 | 0.4710 | |
|
| 0.5222 | 3.21 | 15000 | 0.4666 | |
|
| 0.4929 | 3.31 | 15500 | 0.4645 | |
|
| 0.5049 | 3.42 | 16000 | 0.4631 | |
|
| 0.5002 | 3.53 | 16500 | 0.4613 | |
|
| 0.505 | 3.64 | 17000 | 0.4611 | |
|
| 0.507 | 3.74 | 17500 | 0.4602 | |
|
| 0.5169 | 3.85 | 18000 | 0.4598 | |
|
| 0.501 | 3.96 | 18500 | 0.4598 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|