4d8a83c6-b15c-4324-9571-2f06a1409031

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: 1.8171

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: 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	0.0006	1	2.7084
1.9311	0.0284	50	2.3252
2.0342	0.0569	100	2.5893
2.1179	0.0853	150	2.5301
1.8545	0.1137	200	2.2152
2.114	0.1421	250	2.1017
1.8763	0.1706	300	2.0436
1.8018	0.1990	350	1.9168
1.8091	0.2274	400	1.8501
2.0217	0.2558	450	1.8225
1.707	0.2843	500	1.8171

Framework versions

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