metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model
results: []
my_awesome_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: 0.3905
- Accuracy: 0.9158
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: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- 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
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
1.7774 | 0.99 | 27 | 1.6708 | 0.4856 |
1.3665 | 1.98 | 54 | 1.1744 | 0.7739 |
0.9392 | 2.97 | 81 | 0.8476 | 0.8374 |
0.7654 | 4.0 | 109 | 0.6763 | 0.8570 |
0.5547 | 4.99 | 136 | 0.5508 | 0.8870 |
0.4244 | 5.98 | 163 | 0.4724 | 0.8985 |
0.371 | 6.97 | 190 | 0.4536 | 0.9054 |
0.3302 | 8.0 | 218 | 0.4224 | 0.9031 |
0.2883 | 8.99 | 245 | 0.3924 | 0.9146 |
0.2642 | 9.91 | 270 | 0.3905 | 0.9158 |
Framework versions
- Transformers 4.37.0
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.1