15e5c128-4606-4d4f-970a-6648680e368b

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: 0.0503

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: 0.000204
• train_batch_size: 4
• eval_batch_size: 4
• seed: 40
• 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	0.3617
0.0295	0.0058	50	0.0905
0.034	0.0116	100	0.1293
0.0456	0.0173	150	0.0878
0.0142	0.0231	200	0.0958
0.0162	0.0289	250	0.1030
0.003	0.0347	300	0.0791
0.0036	0.0404	350	0.0643
0.0013	0.0462	400	0.0559
0.0003	0.0520	450	0.0554
0.0017	0.0578	500	0.0503

Framework versions

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