tamasheq-99-2 / README.md
ad019el's picture
End of training
5d68611
|
raw
history blame
1.72 kB
metadata
base_model: ad019el/tamasheq-99-2
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-99-2 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2993
  • Wer: 0.9

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • 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
4.1781 4.62 300 1.7684 1.0853
1.1518 9.23 600 1.1398 0.8588
0.789 13.85 900 1.0551 0.8647
0.659 18.46 1200 1.1470 0.8735
0.5883 23.08 1500 1.2403 0.9
0.5239 27.69 1800 1.2993 0.9

Framework versions

  • Transformers 4.33.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3