--- library_name: peft license: apache-2.0 base_model: NousResearch/Hermes-2-Theta-Llama-3-8B tags: - axolotl - generated_from_trainer model-index: - name: c76c4e64-725f-470c-8133-1b1a456a3ed0 results: [] --- [Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl)
See axolotl config axolotl version: `0.4.1` ```yaml adapter: lora base_model: NousResearch/Hermes-2-Theta-Llama-3-8B bf16: true chat_template: llama3 datasets: - data_files: - d973708dfb2e26dc_train_data.json ds_type: json format: custom path: /workspace/input_data/d973708dfb2e26dc_train_data.json type: field_instruction: instruction field_output: output format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: 2 eval_max_new_tokens: 128 eval_steps: 5 eval_table_size: null flash_attention: false fp16: false fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: false group_by_length: false hub_model_id: lesso08/c76c4e64-725f-470c-8133-1b1a456a3ed0 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: true local_rank: null logging_steps: 1 lora_alpha: 16 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 8 lora_target_linear: true lr_scheduler: cosine max_steps: 25 micro_batch_size: 2 mlflow_experiment_name: /tmp/d973708dfb2e26dc_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 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: 10 sequence_len: 512 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 933e709a-a5de-4f0e-a98f-3d0b01422ec3 wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: 933e709a-a5de-4f0e-a98f-3d0b01422ec3 warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ```

# c76c4e64-725f-470c-8133-1b1a456a3ed0 This model is a fine-tuned version of [NousResearch/Hermes-2-Theta-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.5401 ## 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: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - 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: 10 - training_steps: 25 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 0.6132 | 0.0002 | 1 | 0.6598 | | 0.6878 | 0.0012 | 5 | 0.6516 | | 0.6979 | 0.0024 | 10 | 0.5909 | | 0.6092 | 0.0035 | 15 | 0.5491 | | 0.4083 | 0.0047 | 20 | 0.5420 | | 0.5403 | 0.0059 | 25 | 0.5401 | ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1