metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: S5_M1_f2_Wav2Vec_42738269
results: []
S5_M1_f2_Wav2Vec_42738269
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: 0.0048
- Accuracy: 0.9984
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: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.0217 | 1.0 | 368 | 0.0157 | 0.9968 |
| 0.0095 | 2.0 | 737 | 0.0066 | 0.9976 |
| 0.0105 | 3.0 | 1105 | 0.0056 | 0.9976 |
| 0.0004 | 4.0 | 1474 | 0.0072 | 0.9984 |
| 0.0126 | 4.99 | 1840 | 0.0048 | 0.9984 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.16.1
- Tokenizers 0.15.0