metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: openai/whisper-small
model-index:
- name: whisper-nf-1
results: []
whisper-nf-1
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0186
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 5 | 0.0284 |
| No log | 2.0 | 10 | 0.0168 |
| No log | 3.0 | 15 | 0.0125 |
| No log | 4.0 | 20 | 0.0085 |
| 0.0188 | 5.0 | 25 | 0.0061 |
| 0.0188 | 6.0 | 30 | 0.0042 |
| 0.0188 | 7.0 | 35 | 0.0031 |
| 0.0188 | 8.0 | 40 | 0.0023 |
| 0.0188 | 9.0 | 45 | 0.0018 |
| 0.0031 | 10.0 | 50 | 0.0186 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1