tamasheq-99-2 / README.md
ad019el's picture
End of training
320ca73
|
raw
history blame
1.74 kB
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