--- license: other library_name: peft tags: - generated_from_trainer base_model: meta-llama/Meta-Llama-3-8B model-index: - name: lora-out 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/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) <details><summary>See axolotl config</summary> axolotl version: `0.4.0` ```yaml base_model: meta-llama/Meta-Llama-3-8B model_type: LlamaForCausalLM tokenizer_type: AutoTokenizer load_in_8bit: true load_in_4bit: false strict: false datasets: - path: kloodia/raw_medic type: oasst dataset_prepared_path: val_set_size: 0.05 output_dir: ./lora-out sequence_len: 4096 sample_packing: true pad_to_sequence_len: true adapter: lora lora_model_dir: lora_r: 32 lora_alpha: 16 lora_dropout: 0.05 lora_target_linear: true lora_fan_in_fan_out: wandb_project: wandb_entity: wandb_watch: wandb_name: wandb_log_model: gradient_accumulation_steps: 4 micro_batch_size: 1 num_epochs: 3 optimizer: adamw_bnb_8bit lr_scheduler: cosine learning_rate: 0.0002 train_on_inputs: false group_by_length: false bf16: auto fp16: tf32: false gradient_checkpointing: true early_stopping_patience: resume_from_checkpoint: local_rank: logging_steps: 1 xformers_attention: flash_attention: true s2_attention: warmup_steps: 10 evals_per_epoch: 4 eval_table_size: eval_max_new_tokens: 128 saves_per_epoch: 1 debug: deepspeed: weight_decay: 0.0 fsdp: fsdp_config: special_tokens: pad_token: <|end_of_text|> ``` </details><br> # lora-out This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.5741 ## 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 - distributed_type: multi-GPU - num_devices: 4 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - total_eval_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 2.3216 | 0.0 | 1 | 2.2561 | | 1.7379 | 0.25 | 92 | 1.7855 | | 1.6935 | 0.5 | 184 | 1.7075 | | 1.7016 | 0.75 | 276 | 1.6663 | | 1.5761 | 1.0 | 368 | 1.6371 | | 1.4785 | 1.23 | 460 | 1.6220 | | 1.4492 | 1.49 | 552 | 1.6023 | | 1.6224 | 1.74 | 644 | 1.5887 | | 1.5154 | 1.99 | 736 | 1.5789 | | 1.4758 | 2.22 | 828 | 1.5787 | | 1.4005 | 2.47 | 920 | 1.5758 | | 1.458 | 2.72 | 1012 | 1.5741 | ### Framework versions - PEFT 0.10.0 - Transformers 4.40.0.dev0 - Pytorch 2.1.2+cu118 - Datasets 2.15.0 - Tokenizers 0.15.0