ad019el's picture
update model card README.md
2ee3af1
|
raw
history blame
1.55 kB
metadata
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: tamasheq-99-8
    results: []

tamasheq-99-8

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4990
  • Wer: 0.6059

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: 30

Training results

Training Loss Epoch Step Validation Loss Wer
9.617 6.0 300 3.2032 1.0
2.9621 12.0 600 1.6730 1.0339
0.9694 18.0 900 0.5657 0.6132
0.5765 24.0 1200 0.5097 0.6052
0.505 30.0 1500 0.4990 0.6059

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3