e1c6f8e8-5823-422c-ae61-dbb86493c306

This model is a fine-tuned version of Orenguteng/Llama-3-8B-Lexi-Uncensored on the None dataset. It achieves the following results on the evaluation set:

• Loss: 2.4140

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: 0.000207
• train_batch_size: 4
• eval_batch_size: 4
• seed: 70
• 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	0.0000	1	2.8059
2.601	0.0020	50	2.5843
2.5476	0.0040	100	2.5653
2.5676	0.0060	150	2.5283
2.6086	0.0080	200	2.5085
2.6446	0.0100	250	2.4978
2.5045	0.0120	300	2.4739
2.6288	0.0140	350	2.4417
2.5061	0.0160	400	2.4203
2.518	0.0180	450	2.4150
2.5551	0.0200	500	2.4140

Framework versions

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