--- library_name: peft license: apache-2.0 base_model: unsloth/OpenHermes-2.5-Mistral-7B tags: - axolotl - generated_from_trainer model-index: - name: fcf9f8f5-8a47-48a9-9c3e-f63a3388257b results: [] --- [Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl)
See axolotl config axolotl version: `0.4.1` ```yaml adapter: lora base_model: unsloth/OpenHermes-2.5-Mistral-7B bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 2f1591347bf2ff02_train_data.json ds_type: json format: custom path: /workspace/input_data/2f1591347bf2ff02_train_data.json type: field_input: note field_instruction: conversation field_output: summary format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null early_stopping_patience: null eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 4 flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: true gradient_clipping: 1.0 group_by_length: false hub_model_id: leixa/fcf9f8f5-8a47-48a9-9c3e-f63a3388257b hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 5.0e-05 load_in_4bit: false load_in_8bit: false local_rank: 0 logging_steps: 3 lora_alpha: 32 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 16 lora_target_linear: true lr_scheduler: cosine max_steps: 150 micro_batch_size: 8 mlflow_experiment_name: /tmp/2f1591347bf2ff02_train_data.json model_type: AutoModelForCausalLM num_epochs: 3 optimizer: adamw_bnb_8bit output_dir: miner_id_24 pad_to_sequence_len: true resume_from_checkpoint: null s2_attention: null sample_packing: false saves_per_epoch: 4 sequence_len: 1024 strict: false tf32: false tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: techspear-hub wandb_mode: online wandb_name: 0784bd1f-31e8-4849-b800-e6b9b1ce831f wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: 0784bd1f-31e8-4849-b800-e6b9b1ce831f warmup_steps: 10 weight_decay: 0.01 xformers_attention: null ```

# fcf9f8f5-8a47-48a9-9c3e-f63a3388257b This model is a fine-tuned version of [unsloth/OpenHermes-2.5-Mistral-7B](https://huggingface.co/unsloth/OpenHermes-2.5-Mistral-7B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1276 ## 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: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - 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: 150 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | No log | 0.0011 | 1 | 0.7254 | | 1.6976 | 0.0147 | 13 | 0.2816 | | 0.6645 | 0.0294 | 26 | 0.1600 | | 0.6114 | 0.0441 | 39 | 0.1429 | | 0.5299 | 0.0588 | 52 | 0.1371 | | 0.5479 | 0.0735 | 65 | 0.1340 | | 0.4675 | 0.0882 | 78 | 0.1319 | | 0.5161 | 0.1029 | 91 | 0.1301 | | 0.5277 | 0.1175 | 104 | 0.1289 | | 0.5086 | 0.1322 | 117 | 0.1282 | | 0.5363 | 0.1469 | 130 | 0.1277 | | 0.4771 | 0.1616 | 143 | 0.1276 | ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1