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 an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6441
- Accuracy: 0.8966
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: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 0.9231 | 3 | 1.0856 | 0.5517 |
| No log | 1.8462 | 6 | 1.0685 | 0.7586 |
| No log | 2.7692 | 9 | 0.9550 | 0.7931 |
| No log | 4.0 | 13 | 0.8194 | 0.7931 |
| No log | 4.9231 | 16 | 0.7648 | 0.7931 |
| No log | 5.8462 | 19 | 0.7405 | 0.7931 |
| No log | 6.7692 | 22 | 0.6911 | 0.7931 |
| No log | 8.0 | 26 | 0.6441 | 0.8966 |
| No log | 8.9231 | 29 | 0.6226 | 0.8966 |
| No log | 9.2308 | 30 | 0.6165 | 0.8966 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1