--- library_name: peft license: llama3.2 base_model: unsloth/Llama-3.2-3B tags: - axolotl - generated_from_trainer model-index: - name: a411a2a2-036c-4b0f-9747-7c5e0c9b3409 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/Llama-3.2-3B bf16: false chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 171a2b6e29515e8b_train_data.json ds_type: json field: text path: /workspace/input_data/171a2b6e29515e8b_train_data.json type: completion 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: true fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: true group_by_length: false hub_model_id: lesso/a411a2a2-036c-4b0f-9747-7c5e0c9b3409 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: false 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: 10 micro_batch_size: 1 mlflow_experiment_name: /tmp/171a2b6e29515e8b_train_data.json model_type: AutoModelForCausalLM num_epochs: 1 optimizer: adamw_hf 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: null wandb_mode: online wandb_name: a411a2a2-036c-4b0f-9747-7c5e0c9b3409 wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: a411a2a2-036c-4b0f-9747-7c5e0c9b3409 warmup_steps: 10 weight_decay: 0.0 xformers_attention: null ```

# a411a2a2-036c-4b0f-9747-7c5e0c9b3409 This model is a fine-tuned version of [unsloth/Llama-3.2-3B](https://huggingface.co/unsloth/Llama-3.2-3B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.1502 ## 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: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 4 - optimizer: Use OptimizerNames.ADAMW_HF 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: 10 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 2.0097 | 0.0002 | 1 | 2.2259 | | 2.2437 | 0.0006 | 3 | 2.2234 | | 2.223 | 0.0011 | 6 | 2.2032 | | 2.0592 | 0.0017 | 9 | 2.1502 | ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1