6b0f310e-8dfe-4d77-ab87-585c355ba4ee

This model is a fine-tuned version of Korabbit/llama-2-ko-7b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.8646

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: 0.000218
• 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	1.3929
0.9803	0.0047	50	1.0977
0.7452	0.0094	100	1.0563
0.8894	0.0142	150	1.0474
0.878	0.0189	200	1.0044
0.8014	0.0236	250	0.9554
0.7658	0.0283	300	0.9113
0.6401	0.0331	350	0.8867
0.7264	0.0378	400	0.8729
0.7121	0.0425	450	0.8641
0.7067	0.0472	500	0.8646

Framework versions

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