metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: IDAT_grn_aug_648_novel_Wav2Vec
results: []
IDAT_grn_aug_648_novel_Wav2Vec
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: 0.5515
- Accuracy: 0.7325
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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 |
|---|---|---|---|---|
| 0.6971 | 1.0 | 200 | 0.6931 | 0.5 |
| 0.7013 | 2.0 | 400 | 0.6934 | 0.5 |
| 0.6976 | 3.0 | 600 | 0.6961 | 0.5 |
| 0.6952 | 4.0 | 800 | 0.6941 | 0.5 |
| 0.6948 | 5.0 | 1000 | 0.6932 | 0.5 |
| 0.6943 | 6.0 | 1200 | 0.6934 | 0.5 |
| 0.692 | 7.0 | 1400 | 0.6935 | 0.5 |
| 0.6938 | 8.0 | 1600 | 0.6942 | 0.5 |
| 0.4489 | 9.0 | 1800 | 0.4563 | 0.7975 |
| 0.4557 | 10.0 | 2000 | 0.5515 | 0.7325 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.13.3