metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
model-index:
- name: wav2vec_arabic_mdd_experiment2
results: []
wav2vec_arabic_mdd_experiment2
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1776
- Per: 0.0693
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: 8
- eval_batch_size: 6
- 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_steps: 250
- num_epochs: 20.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Per |
|---|---|---|---|---|
| 0.4089 | 1.0 | 427 | 0.1893 | 0.0889 |
| 0.4135 | 2.0 | 855 | 0.1783 | 0.0939 |
| 0.3924 | 3.0 | 1282 | 0.1825 | 0.0912 |
| 0.3598 | 4.0 | 1710 | 0.1768 | 0.0927 |
| 0.3349 | 5.0 | 2137 | 0.1695 | 0.0898 |
| 0.3068 | 6.0 | 2565 | 0.1749 | 0.0927 |
| 0.286 | 7.0 | 2992 | 0.1731 | 0.0852 |
| 0.2665 | 8.0 | 3420 | 0.1835 | 0.0784 |
| 0.246 | 9.0 | 3847 | 0.1824 | 0.0893 |
| 0.2314 | 10.0 | 4275 | 0.1768 | 0.0796 |
| 0.2105 | 11.0 | 4702 | 0.1721 | 0.0751 |
| 0.1982 | 12.0 | 5130 | 0.1842 | 0.0761 |
| 0.1877 | 13.0 | 5557 | 0.1802 | 0.0750 |
| 0.1735 | 14.0 | 5985 | 0.1740 | 0.0770 |
| 0.1733 | 15.0 | 6412 | 0.1695 | 0.0752 |
| 0.1634 | 16.0 | 6840 | 0.1720 | 0.0757 |
| 0.1542 | 17.0 | 7267 | 0.1757 | 0.0689 |
| 0.1444 | 18.0 | 7695 | 0.1748 | 0.0701 |
| 0.1365 | 19.0 | 8122 | 0.1777 | 0.0690 |
| 0.1331 | 19.98 | 8540 | 0.1776 | 0.0693 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1