Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Whisper large - Noc Operation
This model is a fine-tuned version of biodatlab/whisper-th-large-v3 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3205
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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
- training_steps: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5345 | 0.7576 | 300 | 0.3798 |
| 0.4589 | 1.5152 | 600 | 0.3462 |
| 0.4135 | 2.2727 | 900 | 0.3301 |
| 0.411 | 3.0303 | 1200 | 0.3232 |
| 0.4038 | 3.7879 | 1500 | 0.3205 |
Framework versions
- PEFT 0.15.2
- Transformers 4.48.0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.2
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Mahafit/noc_combine_lora_1500step
Base model
biodatlab/whisper-th-large-v3