metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: wav2vec2-base-finetuned-ie
results: []
wav2vec2-base-finetuned-ie
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: 1.0066
- Accuracy: 0.6487
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.1544 | 1.0 | 102 | 1.1369 | 0.5063 |
| 1.0574 | 2.0 | 204 | 1.0677 | 0.5121 |
| 0.8303 | 3.0 | 306 | 0.9213 | 0.6091 |
| 0.7753 | 4.0 | 408 | 1.0430 | 0.5926 |
| 0.6142 | 5.0 | 510 | 1.1218 | 0.6033 |
| 0.5152 | 6.0 | 612 | 1.1629 | 0.6188 |
| 0.51 | 7.0 | 714 | 0.9371 | 0.6838 |
| 0.2368 | 8.0 | 816 | 1.2314 | 0.6343 |
| 0.2315 | 9.0 | 918 | 1.3838 | 0.6285 |
| 0.2324 | 10.0 | 1020 | 1.3675 | 0.6489 |
| 0.1919 | 11.0 | 1122 | 1.5164 | 0.6372 |
| 0.0962 | 12.0 | 1224 | 1.5281 | 0.6440 |
| 0.0851 | 13.0 | 1326 | 1.5718 | 0.6479 |
| 0.0358 | 14.0 | 1428 | 1.6729 | 0.6508 |
| 0.0754 | 15.0 | 1530 | 1.6681 | 0.6528 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2