|
--- |
|
base_model: ad019el/Kabyle_xlsr-finetuned-tamasheq |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: Kabyle_xlsr-finetuned-tamasheq-1 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# Kabyle_xlsr-finetuned-tamasheq-1 |
|
|
|
This model is a fine-tuned version of [ad019el/Kabyle_xlsr-finetuned-tamasheq](https://huggingface.co/ad019el/Kabyle_xlsr-finetuned-tamasheq) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.3077 |
|
- Wer: 0.8414 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 6.1717 | 15.79 | 300 | 2.8410 | 1.0 | |
|
| 2.1673 | 31.58 | 600 | 1.1010 | 0.8612 | |
|
| 0.7139 | 47.37 | 900 | 1.0831 | 0.8215 | |
|
| 0.4832 | 63.16 | 1200 | 1.1500 | 0.8187 | |
|
| 0.37 | 78.95 | 1500 | 1.2485 | 0.8130 | |
|
| 0.3206 | 94.74 | 1800 | 1.3077 | 0.8414 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
