metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-finetuned-eos_poc5_ge-di-v6
results: []
wav2vec2-base-finetuned-eos_poc5_ge-di-v6
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: 0.7719
- Accuracy: 0.7027
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 |
|---|---|---|---|---|
| 0.4983 | 1.0 | 969 | 0.5273 | 0.7689 |
| 0.5294 | 2.0 | 1938 | 0.5109 | 0.7689 |
| 0.4616 | 3.0 | 2907 | 0.5272 | 0.7689 |
| 0.4737 | 4.0 | 3876 | 0.5198 | 0.7574 |
| 0.4532 | 5.0 | 4845 | 0.5339 | 0.7380 |
| 0.427 | 6.0 | 5814 | 0.5641 | 0.7256 |
| 0.3511 | 7.0 | 6783 | 0.6205 | 0.7383 |
| 0.3435 | 8.0 | 7752 | 0.6753 | 0.7104 |
| 0.3003 | 9.0 | 8721 | 0.7102 | 0.7226 |
| 0.251 | 10.0 | 9690 | 0.7719 | 0.7027 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0