results

This model is a fine-tuned version of facebook/nllb-200-distilled-600M on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 12.3359
• Bleu: 0.2407
• Chrf: 6.2796
• Ter: 132.0388

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Use 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	Chrf	Ter
No log	1.0	2	12.9096	0.2594	6.3668	127.1845
No log	2.0	4	12.6801	0.2472	6.4225	132.0388
No log	3.0	6	12.5083	0.2290	6.3274	137.3786
No log	4.0	8	12.3900	0.2325	6.2686	135.4369
12.7423	5.0	10	12.3359	0.2407	6.2796	132.0388

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0