metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-finetuned-ks
results: []
wav2vec2-base-finetuned-ks
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: 0.7101
- Accuracy: 0.7538
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: 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 7 | 1.1448 | 0.5769 |
| 1.0433 | 2.0 | 14 | 1.0463 | 0.6077 |
| 0.9904 | 3.0 | 21 | 1.0912 | 0.5923 |
| 0.9904 | 4.0 | 28 | 1.0639 | 0.5769 |
| 0.8697 | 5.0 | 35 | 1.0283 | 0.6 |
| 0.7873 | 6.0 | 42 | 0.8870 | 0.7077 |
| 0.7873 | 7.0 | 49 | 0.8815 | 0.6538 |
| 0.7124 | 8.0 | 56 | 0.8828 | 0.6538 |
| 0.666 | 9.0 | 63 | 0.8701 | 0.6846 |
| 0.6376 | 10.0 | 70 | 0.8704 | 0.6692 |
| 0.6376 | 11.0 | 77 | 0.8934 | 0.7077 |
| 0.6552 | 12.0 | 84 | 0.8678 | 0.6692 |
| 0.5827 | 13.0 | 91 | 0.8471 | 0.7 |
| 0.5827 | 14.0 | 98 | 0.7986 | 0.7154 |
| 0.5557 | 15.0 | 105 | 0.7614 | 0.7462 |
| 0.5255 | 16.0 | 112 | 0.7847 | 0.7231 |
| 0.5255 | 17.0 | 119 | 0.7917 | 0.7154 |
| 0.5129 | 18.0 | 126 | 0.7101 | 0.7538 |
| 0.4621 | 19.0 | 133 | 0.7437 | 0.7385 |
| 0.4552 | 20.0 | 140 | 0.7404 | 0.7308 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu111
- Datasets 2.0.0
- Tokenizers 0.10.3