c13ce62a-d99a-4324-89e4-7fffe6f7420d

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: 0.4179

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	0.0002	1	1.0138
0.6265	0.0094	50	0.6459
0.6473	0.0189	100	0.5986
0.6184	0.0283	150	0.5655
0.545	0.0377	200	0.5426
0.5588	0.0472	250	0.4952
0.5059	0.0566	300	0.4922
0.4714	0.0660	350	0.4458
0.4662	0.0754	400	0.4301
0.4667	0.0849	450	0.4206
0.4152	0.0943	500	0.4179

Framework versions

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