|
--- |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: 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. --> |
|
|
|
# model |
|
|
|
This model is a fine-tuned version of [floriangardin/musiclang_medium](https://huggingface.co/floriangardin/musiclang_medium) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5640 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 15 |
|
- num_epochs: 6 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| No log | 0.15 | 400 | 0.6429 | |
|
| 0.6819 | 0.3 | 800 | 0.6389 | |
|
| 0.6744 | 0.44 | 1200 | 0.6335 | |
|
| 0.6664 | 0.59 | 1600 | 0.6319 | |
|
| 0.659 | 0.74 | 2000 | 0.6246 | |
|
| 0.659 | 0.89 | 2400 | 0.6203 | |
|
| 0.6519 | 1.04 | 2800 | 0.6178 | |
|
| 0.6446 | 1.19 | 3200 | 0.6136 | |
|
| 0.6403 | 1.33 | 3600 | 0.6103 | |
|
| 0.6363 | 1.48 | 4000 | 0.6052 | |
|
| 0.6363 | 1.63 | 4400 | 0.6051 | |
|
| 0.6302 | 1.78 | 4800 | 0.6011 | |
|
| 0.6257 | 1.93 | 5200 | 0.5985 | |
|
| 0.6229 | 2.07 | 5600 | 0.5971 | |
|
| 0.6185 | 2.22 | 6000 | 0.5948 | |
|
| 0.6185 | 2.37 | 6400 | 0.5938 | |
|
| 0.6155 | 2.52 | 6800 | 0.5911 | |
|
| 0.6123 | 2.67 | 7200 | 0.5883 | |
|
| 0.6096 | 2.82 | 7600 | 0.5867 | |
|
| 0.6079 | 2.96 | 8000 | 0.5856 | |
|
| 0.6079 | 3.11 | 8400 | 0.5835 | |
|
| 0.6026 | 3.26 | 8800 | 0.5814 | |
|
| 0.5998 | 3.41 | 9200 | 0.5804 | |
|
| 0.5993 | 3.56 | 9600 | 0.5779 | |
|
| 0.5978 | 3.71 | 10000 | 0.5770 | |
|
| 0.5978 | 3.85 | 10400 | 0.5761 | |
|
| 0.5958 | 4.0 | 10800 | 0.5746 | |
|
| 0.5937 | 4.15 | 11200 | 0.5737 | |
|
| 0.5909 | 4.3 | 11600 | 0.5733 | |
|
| 0.5884 | 4.45 | 12000 | 0.5714 | |
|
| 0.5884 | 4.59 | 12400 | 0.5704 | |
|
| 0.588 | 4.74 | 12800 | 0.5690 | |
|
| 0.5875 | 4.89 | 13200 | 0.5685 | |
|
| 0.5848 | 5.04 | 13600 | 0.5679 | |
|
| 0.5827 | 5.19 | 14000 | 0.5668 | |
|
| 0.5827 | 5.34 | 14400 | 0.5663 | |
|
| 0.5839 | 5.48 | 14800 | 0.5658 | |
|
| 0.5806 | 5.63 | 15200 | 0.5650 | |
|
| 0.5803 | 5.78 | 15600 | 0.5644 | |
|
| 0.5796 | 5.93 | 16000 | 0.5640 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.29.2 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.12.0 |
|
- Tokenizers 0.13.3 |
|
|
