5a8be0e6-a27d-4ab6-bd60-ac9c26afeac5

This model is a fine-tuned version of lcw99/zephykor-ko-7b-chang on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4118

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: 0.000213
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• 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: constant
• lr_scheduler_warmup_steps: 50
• training_steps: 400

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0001	1	4.5015
10.7549	0.0056	50	2.5672
9.4096	0.0113	100	2.4470
9.6569	0.0169	150	2.3822
9.6332	0.0226	200	2.3430
9.1757	0.0282	250	2.3987
9.1604	0.0339	300	2.4106
8.8226	0.0395	350	2.4118

Framework versions

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