Vishal74/Trained-gemma-2b-dolly

phi-lora-tuned-Ondolly

This model is a fine-tuned version of google/gemma-2b on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 2.4224

Model description

More information needed

Intended uses & limitations

More information needed

Hardware

Trained model on Intel 1550 GPU

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.05
• training_steps: 593

Training results

Training Loss	Epoch	Step	Validation Loss
2.9724	0.8197	100	2.8042
2.7286	1.6393	200	2.5881
2.5847	2.4590	300	2.4985
2.505	3.2787	400	2.4447
2.4737	4.0984	500	2.4224

Framework versions

• PEFT 0.11.1
• Transformers 4.41.2
• Pytorch 2.1.0.post0+cxx11.abi
• Datasets 2.19.1
• Tokenizers 0.19.1