InkubaLM-0.4B_Kumshe_English-Chinese-Hausa_Dataset_test_size_0.002_lelapa_mtt_train

This model is a fine-tuned version of danielbyiringiro/InkubaLM-0.4B_Kumshe_English-Chinese-Hausa_Dataset_test_size_0.002 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 4.2594
• Chrf: 0.2063

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Chrf
No log	1.0	60	4.2178	0.1991
No log	2.0	120	4.1079	0.1955
No log	3.0	180	4.2594	0.2063

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.3.1
• Tokenizers 0.21.0