Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large-v2-ft-my_dataset_letter_BV_no_split-241025-v1
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: 7.5499
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 13.9778 | 1.0 | 2 | 13.5082 |
| 13.1164 | 2.0 | 4 | 11.4291 |
| 10.7363 | 3.0 | 6 | 9.4007 |
| 9.1462 | 4.0 | 8 | 8.5659 |
| 8.4123 | 5.0 | 10 | 8.1629 |
| 8.1021 | 6.0 | 12 | 7.9240 |
| 7.8847 | 7.0 | 14 | 7.7648 |
| 7.7321 | 8.0 | 16 | 7.6497 |
| 7.6318 | 9.0 | 18 | 7.5812 |
| 7.5679 | 10.0 | 20 | 7.5499 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.0.dev0
- Pytorch 2.3.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Downloads last month
- 7
Model tree for dylanewbie/whisper-large-v2-ft-my_dataset_letter_BV_no_split-241025-v1
Base model
openai/whisper-large-v2