nllb-200-1.3B-ICFOSS-malayalam_Hindi_Translator

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

• Loss: 0.3788
• Bleu: 62.5154
• Rouge: {'rouge1': 0.42504662037099206, 'rouge2': 0.2891987093258279, 'rougeL': 0.4211514655126128, 'rougeLsum': 0.42156526904087943}
• Chrf: {'score': 79.24933104383702, '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
0.5095	1.0	4698	0.4099	59.5376	{'rouge1': 0.4220305313233426, 'rouge2': 0.2866519629954242, 'rougeL': 0.41646494668344247, 'rougeLsum': 0.4167340351207185}	{'score': 77.52631821685847, 'char_order': 6, 'word_order': 0, 'beta': 2}
0.4213	2.0	9396	0.3842	61.7541	{'rouge1': 0.4247871478803683, 'rouge2': 0.28898946927686797, 'rougeL': 0.42099815319030365, 'rougeLsum': 0.4209781732451786}	{'score': 78.54007352748269, 'char_order': 6, 'word_order': 0, 'beta': 2}
0.3888	3.0	14094	0.3785	62.2691	{'rouge1': 0.42665978089706913, 'rouge2': 0.28916951694997156, 'rougeL': 0.42136280849134333, 'rougeLsum': 0.4219221144613403}	{'score': 79.11003191466068, 'char_order': 6, 'word_order': 0, 'beta': 2}
0.3764	4.0	18792	0.3785	62.4514	{'rouge1': 0.42373682879235186, 'rouge2': 0.2891987093258279, 'rougeL': 0.41970156954196886, 'rougeLsum': 0.4201735443294585}	{'score': 79.20088697777769, 'char_order': 6, 'word_order': 0, 'beta': 2}
0.3741	5.0	23490	0.3788	62.5154	{'rouge1': 0.42504662037099206, 'rouge2': 0.2891987093258279, 'rougeL': 0.4211514655126128, 'rougeLsum': 0.42156526904087943}	{'score': 79.24933104383702, 'char_order': 6, 'word_order': 0, 'beta': 2}

Framework versions

• PEFT 0.10.0
• Transformers 4.40.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.19.1