metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: openai/whisper-large-v3
model-index:
- name: Modelo_3_Whisper_Large_v3_10_Epochs
results: []
Modelo_3_Whisper_Large_v3_10_Epochs
This model is a fine-tuned version of openai/whisper-large-v3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1001
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: 64
- 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 |
|---|---|---|---|
| 0.5337 | 1.0 | 324 | 0.3439 |
| 0.3739 | 2.0 | 648 | 0.2438 |
| 0.2592 | 3.0 | 972 | 0.1949 |
| 0.1722 | 4.0 | 1296 | 0.1579 |
| 0.0989 | 5.0 | 1620 | 0.1303 |
| 0.0635 | 6.0 | 1944 | 0.1161 |
| 0.0338 | 7.0 | 2268 | 0.1050 |
| 0.0148 | 8.0 | 2592 | 0.1008 |
| 0.0083 | 9.0 | 2916 | 0.0990 |
| 0.0054 | 10.0 | 3240 | 0.1001 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.0+cu118
- Datasets 2.16.1
- Tokenizers 0.15.2