--- library_name: peft base_model: jingyeom/seal3.1.6n_7b tags: - axolotl - generated_from_trainer model-index: - name: d1d2cdc6-6825-4080-8488-177ec6d1faf0 results: [] --- [Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl)
See axolotl config axolotl version: `0.4.1` ```yaml adapter: lora base_model: jingyeom/seal3.1.6n_7b bf16: auto chat_template: llama3 dataset_prepared_path: null datasets: - data_files: - 01f09831d8709f24_train_data.json ds_type: json format: custom path: /workspace/input_data/01f09831d8709f24_train_data.json type: field_input: '' field_instruction: article field_output: highlights format: '{instruction}' no_input_format: '{instruction}' system_format: '{system}' system_prompt: '' 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: null fsdp: null fsdp_config: null gradient_accumulation_steps: 4 gradient_checkpointing: true gradient_clipping: 1.0 group_by_length: false hub_model_id: dixedus/d1d2cdc6-6825-4080-8488-177ec6d1faf0 hub_repo: null hub_strategy: checkpoint hub_token: null learning_rate: 0.0001 load_in_4bit: false load_in_8bit: false local_rank: 0 logging_steps: 3 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_steps: 100 micro_batch_size: 8 mlflow_experiment_name: /tmp/01f09831d8709f24_train_data.json model_type: AutoModelForCausalLM num_epochs: 3 optimizer: adamw_bnb_8bit 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: techspear-hub wandb_mode: online wandb_name: 31f717bb-12c9-4927-818a-7504fc9b95d9 wandb_project: Gradients-On-Eight wandb_run: your_name wandb_runid: 31f717bb-12c9-4927-818a-7504fc9b95d9 warmup_steps: 10 weight_decay: 0.01 xformers_attention: null ```

# d1d2cdc6-6825-4080-8488-177ec6d1faf0 This model is a fine-tuned version of [jingyeom/seal3.1.6n_7b](https://huggingface.co/jingyeom/seal3.1.6n_7b) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.7690 ## 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: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Use OptimizerNames.ADAMW_BNB 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: 100 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | No log | 0.0001 | 1 | 2.5258 | | 2.2655 | 0.0010 | 9 | 2.2789 | | 2.0609 | 0.0019 | 18 | 2.0205 | | 1.9568 | 0.0029 | 27 | 1.9334 | | 1.8507 | 0.0039 | 36 | 1.8806 | | 1.829 | 0.0049 | 45 | 1.8408 | | 1.7582 | 0.0058 | 54 | 1.8140 | | 1.7586 | 0.0068 | 63 | 1.7939 | | 1.704 | 0.0078 | 72 | 1.7806 | | 1.804 | 0.0088 | 81 | 1.7733 | | 1.7666 | 0.0097 | 90 | 1.7698 | | 1.7767 | 0.0107 | 99 | 1.7690 | ### Framework versions - PEFT 0.13.2 - Transformers 4.46.0 - Pytorch 2.5.0+cu124 - Datasets 3.0.1 - Tokenizers 0.20.1