--- library_name: peft license: gemma base_model: unsloth/gemma-2-2b-it tags: - axolotl - generated_from_trainer model-index: - name: d4c3c6d1-1c00-49d8-b4d4-efa790829de4 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/gemma-2-2b-it bf16: auto chat_template: llama3 cosine_min_lr_ratio: 0.1 data_processes: 16 dataset_prepared_path: null datasets: - data_files: - 365fff3fb780485d_train_data.json ds_type: json format: custom path: /workspace/input_data/365fff3fb780485d_train_data.json type: field_input: Filename field_instruction: Class field_output: Category format: '{instruction} {input}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' debug: null deepspeed: null device_map: auto do_eval: true early_stopping_patience: 1 eval_batch_size: 1 eval_sample_packing: false eval_steps: 25 evaluation_strategy: steps flash_attention: false fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 32 gradient_checkpointing: true group_by_length: true hub_model_id: dada22231/d4c3c6d1-1c00-49d8-b4d4-efa790829de4 hub_strategy: checkpoint hub_token: null hub_username: dada22231 learning_rate: 0.0001 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 1 lora_alpha: 64 lora_dropout: 0.05 lora_fan_in_fan_out: null lora_model_dir: null lora_r: 32 lora_target_linear: true lora_target_modules: - q_proj - v_proj lr_scheduler: cosine max_grad_norm: 1.0 max_memory: 0: 70GiB 1: 70GiB 2: 70GiB 3: 70GiB max_steps: 200 micro_batch_size: 1 mlflow_experiment_name: /tmp/365fff3fb780485d_train_data.json model_type: AutoModelForCausalLM num_epochs: 3 optim_args: adam_beta1: 0.9 adam_beta2: 0.95 adam_epsilon: 1e-5 optimizer: adamw_torch output_dir: miner_id_24 pad_to_sequence_len: true repository_id: dada22231/d4c3c6d1-1c00-49d8-b4d4-efa790829de4 resume_from_checkpoint: null s2_attention: null sample_packing: false save_steps: 25 save_strategy: steps sequence_len: 2048 strict: false tf32: false tokenizer_type: AutoTokenizer torch_compile: false train_on_inputs: false trust_remote_code: true val_set_size: 50 wandb_entity: null wandb_mode: online wandb_name: d4c3c6d1-1c00-49d8-b4d4-efa790829de4 wandb_project: Public_TuningSN wandb_runid: d4c3c6d1-1c00-49d8-b4d4-efa790829de4 warmup_ratio: 0.04 weight_decay: 0.01 xformers_attention: null ```

# d4c3c6d1-1c00-49d8-b4d4-efa790829de4 This model is a fine-tuned version of [unsloth/gemma-2-2b-it](https://huggingface.co/unsloth/gemma-2-2b-it) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.0000 ## 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: 0.0001 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 32 - total_train_batch_size: 128 - total_eval_batch_size: 4 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 8 - training_steps: 200 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 3.9116 | 0.0022 | 1 | 5.8604 | | 0.0 | 0.0552 | 25 | 0.2251 | | 0.0 | 0.1104 | 50 | 0.0000 | | 0.0 | 0.1657 | 75 | 0.0000 | | 0.0 | 0.2209 | 100 | 0.0000 | | 0.0 | 0.2761 | 125 | 0.0000 | | 0.0 | 0.3313 | 150 | 0.0000 | | 0.0 | 0.3866 | 175 | 0.0000 | | 0.0 | 0.4418 | 200 | 0.0000 | ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1