--- library_name: peft license: llama3 base_model: Orenguteng/Llama-3-8B-Lexi-Uncensored tags: - axolotl - generated_from_trainer model-index: - name: 03f640f1-7d7d-40be-98fe-9441de6cce1a results: [] --- [Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl)
See axolotl config axolotl version: `0.4.1` ```yaml adapter: lora base_model: Orenguteng/Llama-3-8B-Lexi-Uncensored bf16: true chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 05cde8954de2926d_train_data.json ds_type: json format: custom path: /workspace/input_data/05cde8954de2926d_train_data.json type: field_input: input field_instruction: instruction field_output: output format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null device_map: ? '' : 0,1,2,3,4,5,6,7 early_stopping_patience: 2 eval_max_new_tokens: 128 eval_steps: 100 eval_table_size: null flash_attention: true gradient_accumulation_steps: 8 gradient_checkpointing: true group_by_length: false hub_model_id: Alphatao/03f640f1-7d7d-40be-98fe-9441de6cce1a hub_repo: null hub_strategy: null hub_token: null learning_rate: 0.0002 load_best_model_at_end: true load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 128 lora_dropout: 0.1 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 64 lora_target_linear: true lora_target_modules: - q_proj - k_proj - v_proj - o_proj lr_scheduler: cosine max_grad_norm: 1.0 max_steps: 1143 micro_batch_size: 4 mlflow_experiment_name: /tmp/05cde8954de2926d_train_data.json model_type: AutoModelForCausalLM num_epochs: 10 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false save_steps: 100 sequence_len: 2048 strict: false tf32: true tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.04 wandb_entity: null wandb_mode: online wandb_name: a83710e1-aac7-468e-b7f3-ab70067370a5 wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: a83710e1-aac7-468e-b7f3-ab70067370a5 warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ```

# 03f640f1-7d7d-40be-98fe-9441de6cce1a This model is a fine-tuned version of [Orenguteng/Llama-3-8B-Lexi-Uncensored](https://huggingface.co/Orenguteng/Llama-3-8B-Lexi-Uncensored) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1977 ## 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: 0.0002 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - 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: 10 - training_steps: 1143 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 1.53 | 0.0011 | 1 | 1.8157 | | 0.2785 | 0.1063 | 100 | 0.2757 | | 0.2918 | 0.2125 | 200 | 0.2649 | | 0.2958 | 0.3188 | 300 | 0.2501 | | 0.2384 | 0.4250 | 400 | 0.2376 | | 0.2792 | 0.5313 | 500 | 0.2341 | | 0.2055 | 0.6375 | 600 | 0.2232 | | 0.2591 | 0.7438 | 700 | 0.2129 | | 0.2179 | 0.8500 | 800 | 0.2044 | | 0.1844 | 0.9563 | 900 | 0.1956 | | 0.1606 | 1.0626 | 1000 | 0.1973 | | 0.1286 | 1.1688 | 1100 | 0.1977 | ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1