2493e57b-de64-4dd4-b986-1eff20f15fa3

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: 0.5627

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: 0.000214
• train_batch_size: 4
• eval_batch_size: 4
• seed: 140
• 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	0.0005	1	1.1167
0.5741	0.0258	50	0.6580
0.5458	0.0516	100	0.6708
0.541	0.0774	150	0.6404
0.5495	0.1033	200	0.6214
0.5433	0.1291	250	0.6066
0.5177	0.1549	300	0.5884
0.535	0.1807	350	0.5746
0.4859	0.2065	400	0.5650
0.4975	0.2323	450	0.5632
0.4496	0.2581	500	0.5627

Framework versions

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