| assistant_tag: assistant | |
| bf16: 'True' | |
| content_tag: value | |
| cutoff_len: '16384' | |
| dataloader_num_workers: '4' | |
| dataloader_persistent_workers: 'True' | |
| dataloader_pin_memory: 'True' | |
| dataset: open-thoughts/OpenThoughts-114k | |
| dataset_dir: ONLINE | |
| ddp_timeout: '180000000' | |
| deepspeed: /opt/ml/code/zero3.json | |
| do_train: 'True' | |
| enable_liger_kernel: 'True' | |
| finetuning_type: full | |
| formatting: sharegpt | |
| global_batch_size: '512' | |
| gradient_accumulation_steps: '16' | |
| hub_model_id: mlfoundations-dev/weight_decay_02 | |
| learning_rate: 8e-05 | |
| logging_steps: '1' | |
| lr_scheduler_type: cosine | |
| messages: conversations | |
| model_name_or_path: Qwen/Qwen2.5-7B-Instruct | |
| neat_packing: 'True' | |
| num_train_epochs: '3.0' | |
| output_dir: /opt/ml/model | |
| overwrite_cache: 'True' | |
| packing: 'True' | |
| per_device_train_batch_size: '1' | |
| plot_loss: 'True' | |
| preprocessing_num_workers: '16' | |
| push_to_db: 'True' | |
| push_to_hub: 'True' | |
| report_to: wandb | |
| role_tag: from | |
| run_name: weight_decay_02 | |
| save_strategy: epoch | |
| stage: sft | |
| template: qwen25 | |
| user_tag: user | |
| warmup_ratio: '0.1' | |
| weight_decay: '0.02' | |