addbdac6-1161-45e6-8f1a-9e89695db7dd

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: 1.9243

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: 0.000201
• train_batch_size: 4
• eval_batch_size: 4
• seed: 10
• 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	3.0447
2.2652	0.0065	50	2.2982
2.4891	0.0130	100	2.3210
2.4471	0.0194	150	2.3965
2.43	0.0259	200	2.1481
2.3287	0.0324	250	2.1142
2.198	0.0389	300	2.0234
2.2078	0.0453	350	1.9824
2.182	0.0518	400	1.9551
2.1305	0.0583	450	1.9404
2.2448	0.0648	500	1.9243

Framework versions

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