InkubaLM-0.4B_Kumshe_English-Chinese-Hausa_Dataset_test_size_0.002

This model is a fine-tuned version of lelapa/InkubaLM-0.4B on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.9928
• Chrf: 0.2391

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	177	3.5944	0.2520
No log	2.0	354	3.7417	0.2352
2.9421	3.0	531	3.9928	0.2391

Framework versions

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