biomistral-gptq-ft

This model is a fine-tuned version of LoneStriker/BioMistral-7B-SLERP-GPTQ on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.3391

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
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 2
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.9096	1.0	62	1.3700
1.3713	1.99	124	1.3455
1.3253	2.99	186	1.3391

Framework versions

• PEFT 0.11.1
• Transformers 4.39.3
• Pytorch 2.1.2
• Datasets 2.18.0
• Tokenizers 0.15.2