--- library_name: peft license: apache-2.0 base_model: unsloth/codellama-7b tags: - axolotl - generated_from_trainer model-index: - name: dd64f970-279f-41e1-8e54-0bacfded2f4b results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.1` ```yaml adapter: lora base_model: unsloth/codellama-7b bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 7f556eada13b5f90_train_data.json ds_type: json format: custom path: /workspace/input_data/7f556eada13b5f90_train_data.json type: field_input: Value Set Name field_instruction: 'Purpose: Clinical Focus' field_output: Description 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: oldiday/dd64f970-279f-41e1-8e54-0bacfded2f4b 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: 100 micro_batch_size: 8 mlflow_experiment_name: /tmp/7f556eada13b5f90_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: b53f8171-7317-4ec1-a798-3977bf40a782 wandb_project: Gradients-On-Six wandb_run: your_name wandb_runid: b53f8171-7317-4ec1-a798-3977bf40a782 warmup_steps: 10 weight_decay: 0.01 xformers_attention: null ``` </details><br> # dd64f970-279f-41e1-8e54-0bacfded2f4b This model is a fine-tuned version of [unsloth/codellama-7b](https://huggingface.co/unsloth/codellama-7b) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.8335 ## 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: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | No log | 0.0001 | 1 | 3.7913 | | 3.5933 | 0.0009 | 9 | 3.5998 | | 2.5824 | 0.0019 | 18 | 2.4453 | | 2.1124 | 0.0028 | 27 | 2.0731 | | 1.9676 | 0.0038 | 36 | 1.9431 | | 2.0108 | 0.0047 | 45 | 1.8958 | | 1.8197 | 0.0057 | 54 | 1.8702 | | 1.8829 | 0.0066 | 63 | 1.8533 | | 1.7421 | 0.0075 | 72 | 1.8453 | | 1.857 | 0.0085 | 81 | 1.8364 | | 1.7811 | 0.0094 | 90 | 1.8340 | | 1.7912 | 0.0104 | 99 | 1.8335 | ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1