metadata
library_name: peft
license: llama3
base_model: Orenguteng/Llama-3-8B-Lexi-Uncensored
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 234de95a-352d-4a70-b496-8cbc55e31388
results: []
234de95a-352d-4a70-b496-8cbc55e31388
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: 2.4129
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: 0.000202
- train_batch_size: 4
- eval_batch_size: 4
- seed: 20
- 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 | 2.8058 |
| 2.5305 | 0.0020 | 50 | 2.5678 |
| 2.5086 | 0.0040 | 100 | 2.5354 |
| 2.4889 | 0.0060 | 150 | 2.5138 |
| 2.6504 | 0.0080 | 200 | 2.5272 |
| 2.5837 | 0.0100 | 250 | 2.5475 |
| 2.5573 | 0.0120 | 300 | 2.4923 |
| 2.4235 | 0.0140 | 350 | 2.4377 |
| 2.6366 | 0.0160 | 400 | 2.4177 |
| 2.4536 | 0.0180 | 450 | 2.4135 |
| 2.4976 | 0.0200 | 500 | 2.4129 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1