results_qlora

This model is a fine-tuned version of oz1115/gemma-2b-it-ko_v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.3518

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: 2e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 30
• training_steps: 300

Training results

Training Loss	Epoch	Step	Validation Loss
5.2353	0.4	50	4.1671
3.7317	0.8	100	3.5712
3.504	1.2	150	3.4571
3.3398	1.6	200	3.3932
3.1833	2.0	250	3.3614
3.1209	2.4	300	3.3518

Framework versions

• PEFT 0.11.1
• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1