murat_chem_translation_model

This model is a fine-tuned version of Helsinki-NLP/opus-mt-de-en on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2397
• Bleu: 46.8627
• Rouge: {'rouge1': 0.7695104784598361, 'rouge2': 0.5863697996443074, 'rougeL': 0.7478497975171696, 'rougeLsum': 0.7479448985343391}

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Rouge
1.6658	0.9882	42	1.1978	45.7366	{'rouge1': 0.7467289256684114, 'rouge2': 0.5571647898288651, 'rougeL': 0.7252847750618231, 'rougeLsum': 0.7252328383526336}
0.8913	2.0	85	1.1930	47.3050	{'rouge1': 0.7661425108412243, 'rouge2': 0.5837435255422405, 'rougeL': 0.7453049514994822, 'rougeLsum': 0.7453292458394836}
0.8207	2.9882	127	1.2109	46.9471	{'rouge1': 0.7698964789465585, 'rouge2': 0.5885563783228516, 'rougeL': 0.7486852327603906, 'rougeLsum': 0.7486604897820754}
0.6947	4.0	170	1.2213	46.8747	{'rouge1': 0.768211392698957, 'rouge2': 0.5849757545893366, 'rougeL': 0.7464201059797938, 'rougeLsum': 0.7464705647035457}
0.5649	4.9882	212	1.2328	46.9369	{'rouge1': 0.7675442716234215, 'rouge2': 0.5865240030083476, 'rougeL': 0.7464873416227668, 'rougeLsum': 0.7464176283193402}
0.4656	5.9294	252	1.2397	46.8627	{'rouge1': 0.7695104784598361, 'rouge2': 0.5863697996443074, 'rougeL': 0.7478497975171696, 'rougeLsum': 0.7479448985343391}

Framework versions

• Transformers 4.43.3
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1