7e10956b-c129-453b-be81-43b9e8a00193

This model is a fine-tuned version of oopsung/llama2-7b-koNqa-test-v1 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8757

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: 0.000208
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 8
• optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_steps: 50
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	2.8507
1.6873	0.0033	50	1.2731
1.545	0.0065	100	1.2757
1.3988	0.0098	150	1.1874
1.6102	0.0130	200	1.1087
1.3597	0.0163	250	1.0507
1.3285	0.0196	300	0.9809
1.0915	0.0228	350	0.9417
1.2449	0.0261	400	0.8955
1.0734	0.0293	450	0.8762
1.0317	0.0326	500	0.8757

Framework versions

• PEFT 0.13.2
• Transformers 4.46.0
• Pytorch 2.5.0+cu124
• Datasets 3.0.1
• Tokenizers 0.20.1