MT_final_model

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.9422
• Bleu: 18.04
• Gen Len: 40.6108

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: 7.5e-05
• train_batch_size: 8
• eval_batch_size: 8
• 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
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.8688	1.0	625	2.6826	17.7778	40.0702
0.5532	2.0	1250	2.7597	18.0252	40.4945
0.4398	3.0	1875	2.9079	17.9547	40.7372
0.3029	4.0	2500	2.8807	18.0278	40.5938
0.2512	5.0	3125	2.9422	18.04	40.6108

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1