metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: wav2vec2-attempt2
results: []
wav2vec2-attempt2
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: 3.2060
- Accuracy: 0.0968
- F1: 0.0275
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: 0.0003
- train_batch_size: 9
- eval_batch_size: 9
- seed: 42
- gradient_accumulation_steps: 12
- total_train_batch_size: 108
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 2 | 3.1418 | 0.0161 | 0.0021 |
| No log | 2.0 | 4 | 3.1418 | 0.0161 | 0.0021 |
| No log | 3.0 | 6 | 3.1482 | 0.0323 | 0.0098 |
| No log | 4.0 | 8 | 3.2063 | 0.0484 | 0.0155 |
| 3.1173 | 5.0 | 10 | 3.2176 | 0.0968 | 0.0188 |
| 3.1173 | 6.0 | 12 | 3.2240 | 0.0645 | 0.0067 |
| 3.1173 | 7.0 | 14 | 3.2105 | 0.0806 | 0.0202 |
| 3.1173 | 8.0 | 16 | 3.2060 | 0.0968 | 0.0275 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0