metadata
license: mit
base_model: MikeMpapa/4_bar_lmd_clean_custom_epochs10
tags:
- generated_from_trainer
model-index:
- name: 4_bar_lmd_clean_custom_epochs10
results: []
4_bar_lmd_clean_custom_epochs10
This model is a fine-tuned version of MikeMpapa/4_bar_lmd_clean_custom_epochs10 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8099
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: 0.005
- train_batch_size: 48
- eval_batch_size: 32
- seed: 1
- gradient_accumulation_steps: 2
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 81
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.078 | 9.42 | 12000 | 0.9938 |
| 0.9861 | 18.84 | 24000 | 0.9498 |
| 0.9367 | 28.26 | 36000 | 0.9170 |
| 0.8959 | 37.68 | 48000 | 0.8851 |
| 0.855 | 47.1 | 60000 | 0.8653 |
| 0.8125 | 56.51 | 72000 | 0.8325 |
| 0.772 | 65.93 | 84000 | 0.8155 |
| 0.7409 | 75.35 | 96000 | 0.8099 |
Framework versions
- Transformers 4.36.0
- Pytorch 2.1.0
- Datasets 2.15.0
- Tokenizers 0.15.1