bilingual-en-yo

This model is a fine-tuned version of Hakeem750/bilingual-en-yo on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6641

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
2.1668	0.5021	500	1.3081
1.186	1.0040	1000	0.9654
0.8996	1.5062	1500	0.8351
0.801	2.0080	2000	0.7674
0.6875	2.5102	2500	0.7309
0.642	3.0121	3000	0.7221
0.6345	3.5142	3500	0.6956
0.616	4.0161	4000	0.6764
0.5553	4.5182	4500	0.6641

Framework versions

• Transformers 4.57.0
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1