| # AGORA Debug Config — Quick smoke test (2 epochs, tiny batch) | |
| [training] | |
| batch_size = 2 | |
| learning_rate = 0.0001 | |
| epochs = 2 | |
| optimizer = "adamw" | |
| weight_decay = 0.01 | |
| scheduler = "cosine" | |
| warmup_steps = 5 | |
| precision = "bf16" | |
| gradient_accumulation = 1 | |
| max_grad_norm = 1.0 | |
| seed = 42 | |
| [model] | |
| base_model = "Qwen/Qwen2.5-1.5B-Instruct" | |
| lora_r = 16 | |
| lora_alpha = 32 | |
| lora_dropout = 0.05 | |
| target_modules = ["q_proj", "v_proj", "k_proj", "o_proj"] | |
| [data] | |
| train_samples = 20 | |
| eval_samples = 5 | |
| train_path = "/mnt/artifacts-datai/logs/project_agora/planning_train.jsonl" | |
| eval_path = "/mnt/artifacts-datai/logs/project_agora/planning_eval.jsonl" | |
| num_workers = 0 | |
| pin_memory = false | |
| [checkpoint] | |
| output_dir = "/mnt/artifacts-datai/checkpoints/project_agora/debug" | |
| save_every_n_steps = 5 | |
| keep_top_k = 1 | |
| metric = "eval_loss" | |
| mode = "min" | |
| [early_stopping] | |
| enabled = false | |
| patience = 5 | |
| min_delta = 0.001 | |
| [logging] | |
| log_dir = "/mnt/artifacts-datai/logs/project_agora" | |
| tensorboard_dir = "/mnt/artifacts-datai/tensorboard/project_agora" | |