metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: CS337_finetune_wav2vec_base
results: []
CS337_finetune_wav2vec_base
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: 0.9254
- Accuracy: 0.6485
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: 0.0005
- 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 |
|---|---|---|---|---|
| 1.2727 | 0.97 | 28 | 1.2536 | 0.5520 |
| 1.2855 | 1.98 | 57 | 1.1553 | 0.5520 |
| 1.2834 | 2.99 | 86 | 1.1334 | 0.5305 |
| 1.127 | 4.0 | 115 | 0.9970 | 0.5799 |
| 1.1262 | 4.97 | 143 | 0.9905 | 0.6168 |
| 1.2568 | 5.98 | 172 | 0.9853 | 0.6155 |
| 1.1343 | 6.99 | 201 | 0.9947 | 0.6218 |
| 1.0321 | 8.0 | 230 | 0.9495 | 0.6294 |
| 1.0019 | 8.97 | 258 | 0.9227 | 0.6548 |
| 0.9676 | 9.74 | 280 | 0.9254 | 0.6485 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1