metadata
base_model: ad019el/Kabyle_xlsr-finetuned-tamasheq.en
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: Kabyle_xlsr-finetuned-tamasheq.en
results: []
Kabyle_xlsr-finetuned-tamasheq.en
This model is a fine-tuned version of ad019el/Kabyle_xlsr-finetuned-tamasheq.en on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.4232
- Wer: 0.8219
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 |
|---|---|---|---|---|
| 5.78 | 7.89 | 300 | 2.8068 | 1.0 |
| 1.8082 | 15.79 | 600 | 1.2761 | 0.8704 |
| 0.5823 | 23.68 | 900 | 1.3180 | 0.8575 |
| 0.4394 | 31.58 | 1200 | 1.3429 | 0.8533 |
| 0.3509 | 39.47 | 1500 | 1.4232 | 0.8219 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3