mistral-7b-v0.1-english-to-hinglish-translation

This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.9017
• Rouge Scores: {'rouge1': 0.9052154858930703, 'rouge2': 0.7938118811886605, 'rougeL': 0.8365543601879399, 'rougeLsum': 0.9051011676969527}
• Bleu Scores: [0.9286814242037147, 0.9121661008968365, 0.8907823041130339, 0.8677722819236368]
• Gen Len: 2048.0

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: 0.0001
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 4
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• num_epochs: 2
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge Scores	Bleu Scores	Gen Len
0.9667	1.0	500	0.8997	{'rouge1': 0.9066197962103982, 'rouge2': 0.7949438120742293, 'rougeL': 0.8365583570941119, 'rougeLsum': 0.906542182776239}	[0.9280923249970773, 0.9116476390859075, 0.8901882800412136, 0.8671907395641425]	2048.0
0.5702	2.0	1000	0.9017	{'rouge1': 0.9052154858930703, 'rouge2': 0.7938118811886605, 'rougeL': 0.8365543601879399, 'rougeLsum': 0.9051011676969527}	[0.9286814242037147, 0.9121661008968365, 0.8907823041130339, 0.8677722819236368]	2048.0

Framework versions

• PEFT 0.8.2
• Transformers 4.38.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.16.2.dev0
• Tokenizers 0.15.1