| { | |
| "proj_name": "Qwen2.5-7B-Instruct-full-train", | |
| "learning_rate": 4e-06, | |
| "adam_epsilon": 1e-08, | |
| "batch_size": 4, | |
| "max_length": 8192, | |
| "num_train_epochs": 1, | |
| "train_data_path": "full-p2l-data", | |
| "val_data_path": "p2el/canonical_bt_val_data_11092024", | |
| "output_dir": "training_outputs", | |
| "pretrain_model_name": "Qwen/Qwen2.5-7B-Instruct", | |
| "gradient_accumulation_steps": 16, | |
| "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n\n", | |
| "model_type": "qwen2", | |
| "head_type": "bt", | |
| "loss_type": "bt_tie", | |
| "weighted_loss": false, | |
| "deepspeed_config_path": "deepspeed/zero1.json", | |
| "init_type": "reset_params", | |
| "load_train_data_from_disk": true | |
| } |