nllb-200-distilled-1.3B-ICFOSS-Malayalam_Tamil_Translation1

This model is a fine-tuned version of facebook/nllb-200-distilled-1.3B on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9585
• Bleu: 27.2186
• Rouge: {'rouge1': 0.24019241472720237, 'rouge2': 0.11743746052802109, 'rougeL': 0.23538895581779812, 'rougeLsum': 0.23566947893424423}
• Chrf: {'score': 61.354962127257075, 'char_order': 6, 'word_order': 0, 'beta': 2}

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: 0.0002
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Rouge	Chrf
1.0887	1.0	3200	0.9812	26.4453	{'rouge1': 0.23999162519568762, 'rouge2': 0.11750820308459373, 'rougeL': 0.2354759340604931, 'rougeLsum': 0.23574425317949493}	{'score': 60.78556495445389, 'char_order': 6, 'word_order': 0, 'beta': 2}
1.0235	2.0	6400	0.9633	27.2057	{'rouge1': 0.23965959444048868, 'rouge2': 0.11732010332857629, 'rougeL': 0.2348755068042092, 'rougeLsum': 0.2350956429627365}	{'score': 61.143671039500624, 'char_order': 6, 'word_order': 0, 'beta': 2}
1.0073	3.0	9600	0.9592	27.2471	{'rouge1': 0.24051300083618463, 'rouge2': 0.11760625620421375, 'rougeL': 0.23594757428338253, 'rougeLsum': 0.23612557860955713}	{'score': 61.30740344086827, 'char_order': 6, 'word_order': 0, 'beta': 2}
1.0022	4.0	12800	0.9587	27.2024	{'rouge1': 0.24037345843038344, 'rouge2': 0.1174835459617575, 'rougeL': 0.2356757544571015, 'rougeLsum': 0.23591228047430784}	{'score': 61.34302070824752, 'char_order': 6, 'word_order': 0, 'beta': 2}
1.0008	5.0	16000	0.9585	27.2186	{'rouge1': 0.24019241472720237, 'rouge2': 0.11743746052802109, 'rougeL': 0.23538895581779812, 'rougeLsum': 0.23566947893424423}	{'score': 61.354962127257075, 'char_order': 6, 'word_order': 0, 'beta': 2}

Framework versions

• PEFT 0.10.0
• Transformers 4.39.3
• Pytorch 2.1.0+cu121
• Datasets 2.19.0
• Tokenizers 0.15.0