metadata
license: apache-2.0
base_model: ad019el/tamasheq-99-1
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: tamasheq-99-2
results: []
tamasheq-99-2
This model is a fine-tuned version of ad019el/tamasheq-99-1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.3783
- Wer: 0.8147
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 500
- num_epochs: 200
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 7.9063 | 7.89 | 300 | 3.0656 | 1.0 |
| 2.7952 | 15.79 | 600 | 1.7388 | 0.9324 |
| 1.2354 | 23.68 | 900 | 1.0927 | 0.8618 |
| 0.8131 | 31.58 | 1200 | 1.1919 | 0.8618 |
| 0.6311 | 39.47 | 1500 | 1.2800 | 0.8559 |
| 0.5422 | 47.37 | 1800 | 1.3783 | 0.8147 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3