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: 0.6644
- Accuracy: 0.9596
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 | 0.9771 | 32 | 2.2835 | 0.4242 |
| No log | 1.9847 | 65 | 1.8355 | 0.6700 |
| No log | 2.9924 | 98 | 1.4781 | 0.7576 |
| 2.2064 | 4.0 | 131 | 1.1889 | 0.8721 |
| 2.2064 | 4.9771 | 163 | 1.0536 | 0.8687 |
| 2.2064 | 5.9847 | 196 | 0.8963 | 0.8956 |
| 1.3725 | 6.9924 | 229 | 0.7865 | 0.9293 |
| 1.3725 | 8.0 | 262 | 0.7059 | 0.9495 |
| 1.3725 | 8.9771 | 294 | 0.6644 | 0.9596 |
| 0.9706 | 9.7710 | 320 | 0.6516 | 0.9596 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1