metadata
library_name: transformers
tags:
- generated_from_trainer
model-index:
- name: okai-musiclang-content-t5-stable
results: []
okai-musiclang-content-t5-stable
This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4777
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine_with_restarts
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 1000
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.0354 | 0.4637 | 500 | 4.7884 |
| 4.2945 | 0.9274 | 1000 | 4.0578 |
| 3.5799 | 1.3904 | 1500 | 3.3671 |
| 3.1014 | 1.8542 | 2000 | 2.9227 |
| 2.844 | 2.3172 | 2500 | 2.6748 |
| 2.7116 | 2.7809 | 3000 | 2.5518 |
| 2.6486 | 3.2439 | 3500 | 2.4961 |
| 2.6292 | 3.7076 | 4000 | 2.4777 |
Framework versions
- Transformers 4.54.1
- Pytorch 2.6.0+cu124
- Datasets 4.0.0
- Tokenizers 0.21.4