metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: test-model
results: []
test-model
This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2280
- Accuracy: 0.9399
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: 4e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- training_steps: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0215 | 0.9639 | 60 | 0.8933 | 0.5734 |
| 0.7629 | 1.9277 | 120 | 0.6155 | 0.7565 |
| 0.664 | 2.8916 | 180 | 0.5293 | 0.7827 |
| 0.4882 | 3.8554 | 240 | 0.3675 | 0.8893 |
| 0.3573 | 4.8193 | 300 | 0.3523 | 0.8974 |
| 0.3088 | 5.7831 | 360 | 0.3125 | 0.9034 |
| 0.2715 | 6.7470 | 420 | 0.2085 | 0.9477 |
| 0.2154 | 7.7108 | 480 | 0.2546 | 0.9336 |
| 0.2016 | 8.6747 | 540 | 0.1955 | 0.9517 |
| 0.193 | 9.6386 | 600 | 0.1969 | 0.9457 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1