IMPORTANT !!

I strongly recommend using the DPO model instead, as it is optimized for better performance and efficiency. This model has been fine-tuned for improved results, making it the preferred choice.

Please refrain from using the SFT model unless you specifically need a base model to build upon. If you require a strong starting point for further fine-tuning, the SFT model can serve that purpose, but for general use, the DPO model is the better option.

Gemma2b-v1.0-sft

This model is a fine-tuned version of google/gemma-2-2b-it on an unknown dataset.

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-06
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.2
• num_epochs: 1

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0