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 the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2342
- Accuracy: 0.9356
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 8
- 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: 0.3
- training_steps: 600
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.0226 | 0.9639 | 60 | 0.8861 | 0.5453 |
| 0.8233 | 1.9277 | 120 | 0.6863 | 0.7123 |
| 0.672 | 2.8916 | 180 | 0.4994 | 0.7988 |
| 0.5346 | 3.8554 | 240 | 0.4163 | 0.8692 |
| 0.4306 | 4.8193 | 300 | 0.3459 | 0.8934 |
| 0.3544 | 5.7831 | 360 | 0.3317 | 0.8853 |
| 0.3214 | 6.7470 | 420 | 0.2763 | 0.9115 |
| 0.2778 | 7.7108 | 480 | 0.2877 | 0.9296 |
| 0.2264 | 8.6747 | 540 | 0.2487 | 0.9336 |
| 0.2127 | 9.6386 | 600 | 0.2342 | 0.9356 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1