YassineBenlaria's picture
End of training
3015079
|
raw
history blame
1.66 kB
metadata
tags:
  - generated_from_trainer
metrics:
  - wer
model-index:
  - name: testing_pretrained_tamasheq_only
    results: []

testing_pretrained_tamasheq_only

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

  • Loss: 1.5616
  • Wer: 0.8593

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: 250

Training results

Training Loss Epoch Step Validation Loss Wer
6.486 35.29 300 2.9498 1.0
2.859 70.59 600 2.7420 1.0
2.7652 105.88 900 2.7188 1.0
2.6354 141.18 1200 2.2511 1.0
1.9486 176.47 1500 1.5854 0.9111
1.3512 211.76 1800 1.5616 0.8593

Framework versions

  • Transformers 4.33.2
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3