| wandb_project: llm-training-platform | |
| wandb_name: II-Tulu-3B-SFT | |
| datasets: | |
| - path: allenai/tulu-3-sft-mixture | |
| split: train | |
| type: chat_template | |
| field_messages: messages | |
| message_field_role: role | |
| message_field_content: content | |
| roles: | |
| system: | |
| - system | |
| user: | |
| - user | |
| assistant: | |
| - assistant | |
| chat_template: qwen_25 | |
| sequence_len: 2048 | |
| base_model: Qwen/Qwen2.5-3B | |
| output_dir: checkpoints/1357e2cd-76bc-46d5-a394-949b712427c7 | |
| dataset_prepared_path: checkpoints/1357e2cd-76bc-46d5-a394-949b712427c7/dataset_prepared | |
| flash_attention: true | |
| train_on_inputs: false | |
| pad_to_sequence_len: true | |
| eval_sample_packing: false | |
| push_to_hub: true | |
| bf16: auto | |
| gradient_checkpointing: true | |
| logging_steps: 10 | |
| hub_model_id: phunguyen01/II-Tulu-3B-SFT | |
| learning_rate: 5.0e-06 | |
| micro_batch_size: 8 | |
| num_epochs: 2 | |
| seed: 42 | |
| gradient_accumulation_steps: 2 | |
| sample_packing: true | |
| val_set_size: 0 | |