metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: openai/whisper-large-v2
model-index:
- name: int8-whisper-large-v2-asr-gn-15-all-a100
results: []
int8-whisper-large-v2-asr-gn-15-all-a100
This model is a fine-tuned version of openai/whisper-large-v2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1441
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5271 | 1.0 | 292 | 0.3598 |
| 0.3254 | 2.0 | 584 | 0.2609 |
| 0.2019 | 3.0 | 876 | 0.2030 |
| 0.1125 | 4.0 | 1168 | 0.1562 |
| 0.0543 | 5.0 | 1460 | 0.1441 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.0+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0