metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
model-index:
- name: wav2vec2-large-xls-r-300m-Arabic-phoneme-based-MDD
results: []
wav2vec2-large-xls-r-300m-Arabic-phoneme-based-MDD
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5458
- Per: 0.2292
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: 2
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- num_epochs: 30.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Per |
|---|---|---|---|---|
| 3.2235 | 1.0 | 2187 | 1.9282 | 0.6005 |
| 1.5785 | 2.0 | 4374 | 1.4976 | 0.4575 |
| 1.2838 | 3.0 | 6561 | 1.3438 | 0.4153 |
| 1.1328 | 4.0 | 8748 | 1.3677 | 0.3842 |
| 1.0331 | 5.0 | 10935 | 1.2632 | 0.3575 |
| 0.9463 | 6.0 | 13122 | 1.2040 | 0.3515 |
| 0.8686 | 7.0 | 15309 | 1.1669 | 0.3333 |
| 0.8009 | 8.0 | 17496 | 1.1435 | 0.3233 |
| 0.748 | 9.0 | 19683 | 1.1334 | 0.3122 |
| 0.6908 | 10.0 | 21870 | 1.1131 | 0.2925 |
| 0.6339 | 11.0 | 24057 | 1.1514 | 0.2872 |
| 0.5911 | 12.0 | 26244 | 1.1188 | 0.2784 |
| 0.5513 | 13.0 | 28431 | 1.1334 | 0.2790 |
| 0.5127 | 14.0 | 30618 | 1.1662 | 0.2694 |
| 0.4782 | 15.0 | 32805 | 1.1719 | 0.2634 |
| 0.4448 | 16.0 | 34992 | 1.1635 | 0.2600 |
| 0.4167 | 17.0 | 37179 | 1.2173 | 0.2561 |
| 0.3913 | 18.0 | 39366 | 1.2252 | 0.2542 |
| 0.3639 | 19.0 | 41553 | 1.2478 | 0.2490 |
| 0.3441 | 20.0 | 43740 | 1.2977 | 0.2504 |
| 0.3245 | 21.0 | 45927 | 1.3575 | 0.2477 |
| 0.3048 | 22.0 | 48114 | 1.3489 | 0.2420 |
| 0.2885 | 23.0 | 50301 | 1.3860 | 0.2398 |
| 0.2715 | 24.0 | 52488 | 1.4116 | 0.2406 |
| 0.2588 | 25.0 | 54675 | 1.4896 | 0.2374 |
| 0.2454 | 26.0 | 56862 | 1.4672 | 0.2324 |
| 0.2344 | 27.0 | 59049 | 1.5015 | 0.2324 |
| 0.2245 | 28.0 | 61236 | 1.5205 | 0.2308 |
| 0.2183 | 29.0 | 63423 | 1.5248 | 0.2302 |
| 0.2089 | 30.0 | 65610 | 1.5458 | 0.2292 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 1.18.3
- Tokenizers 0.13.3