--- library_name: peft license: apache-2.0 base_model: unsloth/gemma-1.1-2b-it tags: - axolotl - generated_from_trainer model-index: - name: 2906295d-e2bf-4923-adfd-93dcf32eeb0a 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-1.1-2b-it bf16: auto chat_template: llama3 dataloader_num_workers: 12 dataset_prepared_path: null datasets: - data_files: - 9a34ae94e5706c4f_train_data.json ds_type: json format: custom path: /workspace/input_data/9a34ae94e5706c4f_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 device_map: auto do_eval: true early_stopping_patience: 2 eval_batch_size: 8 eval_max_new_tokens: 128 eval_steps: 300 eval_table_size: null evals_per_epoch: null flash_attention: true fp16: null fsdp: null fsdp_config: null gradient_accumulation_steps: 8 gradient_checkpointing: true group_by_length: true hub_model_id: nttx/2906295d-e2bf-4923-adfd-93dcf32eeb0a hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0004 load_in_4bit: false load_in_8bit: false local_rank: null logging_steps: 300 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_grad_norm: 1.0 max_memory: 0: 75GB max_steps: 3000 micro_batch_size: 8 mlflow_experiment_name: /tmp/9a34ae94e5706c4f_train_data.json model_type: AutoModelForCausalLM num_epochs: 100 optim_args: adam_beta1: 0.9 adam_beta2: 0.95 adam_epsilon: 1e-5 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: 300 saves_per_epoch: null 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: 9d29453f-c2af-4ec4-83a0-272f263b82eb wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: 9d29453f-c2af-4ec4-83a0-272f263b82eb warmup_steps: 100 weight_decay: 0.0 xformers_attention: null ```

# 2906295d-e2bf-4923-adfd-93dcf32eeb0a This model is a fine-tuned version of [unsloth/gemma-1.1-2b-it](https://huggingface.co/unsloth/gemma-1.1-2b-it) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.6998 ## 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: 0.0004 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 64 - optimizer: Use OptimizerNames.ADAMW_BNB 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: 100 - training_steps: 3000 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | No log | 0.0013 | 1 | 3.4993 | | 1.9459 | 0.3920 | 300 | 2.0434 | | 1.7489 | 0.7839 | 600 | 1.8941 | | 1.6123 | 1.1759 | 900 | 1.7152 | | 1.5098 | 1.5679 | 1200 | 1.6758 | | 1.4944 | 1.9598 | 1500 | 1.6400 | | 1.2823 | 2.3518 | 1800 | 1.6630 | | 1.2428 | 2.7438 | 2100 | 1.6395 | | 1.1651 | 3.1357 | 2400 | 1.7229 | | 1.0362 | 3.5277 | 2700 | 1.6998 | ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1