--- library_name: peft license: apache-2.0 base_model: TinyLlama/TinyLlama_v1.1 tags: - axolotl - generated_from_trainer model-index: - name: 60a877d8-a6ca-4bf5-84d8-0da0ec026edd results: [] --- [Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl)
See axolotl config axolotl version: `0.4.1` ```yaml adapter: lora base_model: TinyLlama/TinyLlama_v1.1 bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - a71f093e60988734_train_data.json ds_type: json format: custom path: /workspace/input_data/a71f093e60988734_train_data.json type: field_instruction: instruction field_output: output format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' ddp_find_unused_parameters: false distributed_type: ddp early_stopping_patience: null env: CUDA_VISIBLE_DEVICES: 0,1 MASTER_ADDR: localhost MASTER_PORT: '29500' NCCL_DEBUG: INFO NCCL_IB_DISABLE: '0' NCCL_P2P_DISABLE: '0' NCCL_P2P_LEVEL: NVL PYTORCH_CUDA_ALLOC_CONF: max_split_size_mb:512, garbage_collection_threshold:0.8 WORLD_SIZE: '2' eval_max_new_tokens: 128 eval_table_size: null evals_per_epoch: 4 flash_attention: false fp16: false gradient_accumulation_steps: 8 gradient_checkpointing: true group_by_length: true hub_model_id: fats-fme/60a877d8-a6ca-4bf5-84d8-0da0ec026edd hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0002 load_in_4bit: false load_in_8bit: true logging_steps: 1 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_memory_MB: 60000 max_steps: -1 micro_batch_size: 2 mlflow_experiment_name: /tmp/a71f093e60988734_train_data.json model_type: AutoModelForCausalLM num_devices: 2 num_epochs: 1 optimizer: adamw_torch 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: 2048 special_tokens: pad_token: strict: false tf32: true tokenizer_type: AutoTokenizer train_on_inputs: false trust_remote_code: true val_set_size: 0.05 wandb_entity: null wandb_mode: online wandb_name: 60a877d8-a6ca-4bf5-84d8-0da0ec026edd wandb_project: Gradients-On-Demand wandb_run: your_name wandb_runid: 60a877d8-a6ca-4bf5-84d8-0da0ec026edd warmup_steps: 50 world_size: 2 xformers_attention: true ```

# 60a877d8-a6ca-4bf5-84d8-0da0ec026edd This model is a fine-tuned version of [TinyLlama/TinyLlama_v1.1](https://huggingface.co/TinyLlama/TinyLlama_v1.1) on the None dataset. It achieves the following results on the evaluation set: - Loss: 2.0991 ## 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: 2 - eval_batch_size: 2 - seed: 42 - distributed_type: multi-GPU - num_devices: 2 - gradient_accumulation_steps: 8 - total_train_batch_size: 32 - total_eval_batch_size: 4 - optimizer: Use OptimizerNames.ADAMW_TORCH 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: 50 - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 1.1939 | 0.0007 | 1 | 2.1018 | | 1.5684 | 0.2502 | 383 | 2.0980 | | 1.8955 | 0.5004 | 766 | 2.0970 | | 3.4791 | 0.7506 | 1149 | 2.0991 | ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1