Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
lora-test
This model is a fine-tuned version of openai/whisper-medium on an unknown dataset. It achieves the following results on the evaluation set:
- eval_loss: 0.4051
- eval_wer: 0.4848
- eval_runtime: 42.6897
- eval_samples_per_second: 2.342
- eval_steps_per_second: 0.164
- epoch: 5.3765
- step: 5500
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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: 500
- num_epochs: 20
- mixed_precision_training: Native AMP
Framework versions
- PEFT 0.15.2.dev0
- Transformers 4.52.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.3.1
- Tokenizers 0.21.0
- Downloads last month
- 78
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Humphery7/lora-test
Base model
openai/whisper-medium