| { |
| "model": "HuggingFaceTB/SmolLM2-360M-Instruct", |
| "dataset_name": "unknown", |
| "output_dir": "./out_graph-memory", |
| "agentic_mode": true, |
| "tools": [ |
| "recall_kyc" |
| ], |
| "train_size": 40, |
| "eval_size": 0, |
| "final_loss": -0.17834244815167039, |
| "total_steps": 10, |
| "training_history": [], |
| "metrics": { |
| "train_runtime": 536.2452, |
| "train_samples_per_second": 0.075, |
| "train_steps_per_second": 0.019, |
| "total_flos": 0.0, |
| "train_loss": -0.17834244815167039, |
| "epoch": 1.0 |
| }, |
| "config_kwargs": { |
| "model": "HuggingFaceTB/SmolLM2-360M-Instruct", |
| "train_dataset": "Dataset({\n features: ['prompt', 'answer'],\n num_rows: 40\n})", |
| "reward_funcs": "<callable: combined_reward(reward_tool_used+reward_correct_answer)>", |
| "tools": [ |
| "<function recall_kyc at 0x7fb401e8cae0>" |
| ], |
| "system_prompt": "You are the Dallas DC graph recall agent.", |
| "output_dir": "./out_graph-memory", |
| "num_train_epochs": 1, |
| "per_device_train_batch_size": 2, |
| "gradient_accumulation_steps": 4, |
| "learning_rate": 1e-06, |
| "warmup_ratio": 0.03, |
| "warmup_steps": 10, |
| "weight_decay": 0.0, |
| "lr_scheduler_type": "linear", |
| "max_grad_norm": 1.0, |
| "seed": 42, |
| "data_seed": 42, |
| "optim": "adamw_torch", |
| "num_generations": 2, |
| "max_prompt_length": 1024, |
| "max_completion_length": 128, |
| "temperature": 0.7, |
| "top_p": 0.95, |
| "beta": 0.04, |
| "use_vllm": false, |
| "vllm_mode": "colocate", |
| "log_completions": true, |
| "chat_template_kwargs": { |
| "enable_thinking": false |
| }, |
| "max_steps_per_turn": 8, |
| "peft_config": { |
| "r": 8, |
| "lora_alpha": 16, |
| "lora_dropout": 0.0, |
| "bias": "none", |
| "task_type": "CAUSAL_LM" |
| }, |
| "bf16": true, |
| "fp16": false, |
| "gradient_checkpointing": true, |
| "dataloader_num_workers": 0, |
| "logging_steps": 1, |
| "save_steps": 500, |
| "report_to": "none", |
| "push_to_hub": false, |
| "eval_strategy": "no", |
| "remove_unused_columns": false |
| } |
| } |
