mixtral-8x7b-v0.1-english-to-hinglish-translation

This model is a fine-tuned version of mistralai/Mixtral-8x7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.0769
• Rouge Scores: {'rouge1': 0.9045408202972536, 'rouge2': 0.795425441228359, 'rougeL': 0.8399846297860634, 'rougeLsum': 0.9043739034131012}
• Bleu Scores: [0.0002881182166187815, 0.0002842750061873772, 0.0002764768847375588, 0.00026750640347869873]
• 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
1.1771	1.0	500	1.0579	{'rouge1': 0.9070255400902434, 'rouge2': 0.7976770190068221, 'rougeL': 0.8400261479965636, 'rougeLsum': 0.9069363147075731}	[0.00028395954091190866, 0.0002796973368739713, 0.0002722057765709132, 0.000263740024418467]	2047.996
0.7788	2.0	1000	1.0769	{'rouge1': 0.90.45408202972536, 'rouge2': 0.795425441228359, 'rougeL': 0.8399846297860634, 'rougeLsum': 0.9043739034131012}	[0.0002881182166187815, 0.0002842750061873772, 0.0002764768847375588, 0.00026750640347869873]	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