tamasheq-98-2

This model is a fine-tuned version of ad019el/tamasheq-98-1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.5349
• Wer: 0.9667

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
7.6372	9.62	500	2.3244	1.0519
0.5009	19.23	1000	1.4651	0.9444
0.2431	28.85	1500	1.5561	0.9741
0.2013	38.46	2000	1.6960	1.0407
0.1857	48.08	2500	1.5349	0.9667

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0
• Datasets 2.1.0
• Tokenizers 0.12.1