gemma-2b-it-finetuned-new

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

• Loss: 5.9116

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-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
15.0058	0.9778	11	8.7770
8.5905	1.9556	22	6.5263
6.8553	2.9333	33	5.9116

Framework versions

• PEFT 0.13.2
• Transformers 4.46.2
• Pytorch 2.1.0+cu118
• Datasets 3.1.0
• Tokenizers 0.20.3