metadata
language:
- en
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
datasets:
- PolyAI/minds14
base_model: openai/whisper-small
model-index:
- name: Whisper Small Finetuned - SasiVardhan
results: []
Whisper Small Finetuned - SasiVardhan
This model is a fine-tuned version of openai/whisper-small on the minds 14 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7070
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: 8
- 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 |
---|---|---|---|
0.9334 | 1.0 | 56 | 0.5490 |
0.3311 | 2.0 | 112 | 0.4733 |
0.1602 | 3.0 | 168 | 0.5424 |
0.0487 | 4.0 | 224 | 0.5561 |
0.0253 | 5.0 | 280 | 0.6136 |
0.0064 | 6.0 | 336 | 0.6719 |
0.0043 | 7.0 | 392 | 0.6661 |
0.0045 | 8.0 | 448 | 0.6927 |
0.0017 | 9.0 | 504 | 0.7012 |
0.0014 | 10.0 | 560 | 0.7070 |
Framework versions
- PEFT 0.9.1.dev0
- Transformers 4.39.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2