metadata
library_name: peft
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
- generated_from_trainer
model-index:
- name: bamarasper-large
results: []
bamarasper-large
This model is a fine-tuned version of openai/whisper-large-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.7710
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.802 | 1.0 | 1062 | 0.8339 |
| 0.6385 | 2.0 | 2124 | 0.7577 |
| 0.488 | 3.0 | 3186 | 0.7136 |
| 0.4109 | 4.0 | 4248 | 0.6923 |
| 0.2838 | 5.0 | 5310 | 0.7161 |
| 0.1842 | 5.9948 | 6366 | 0.7710 |
Framework versions
- PEFT 0.14.1.dev0
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0