metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base_lr_4e-4
results: []
wav2vec2-base_lr_4e-4
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: 0.0997
- Accuracy: 0.9625
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: 0.0004
- 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 |
|---|---|---|---|---|
| 1.6571 | 0.9851 | 33 | 1.3089 | 0.5679 |
| 0.9453 | 2.0 | 67 | 0.6596 | 0.7769 |
| 0.5682 | 2.9851 | 100 | 0.4865 | 0.8482 |
| 0.5507 | 4.0 | 134 | 0.4255 | 0.8575 |
| 0.4859 | 4.9851 | 167 | 0.2552 | 0.9044 |
| 0.3461 | 6.0 | 201 | 0.3066 | 0.8969 |
| 0.358 | 6.9851 | 234 | 0.1916 | 0.9269 |
| 0.2854 | 8.0 | 268 | 0.1589 | 0.9447 |
| 0.192 | 8.9851 | 301 | 0.1160 | 0.9550 |
| 0.1969 | 9.8507 | 330 | 0.0997 | 0.9625 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1