Files
pi05-minimal-validation/outputs/overfit/evaluation.json
T
2026-07-12 19:16:27 +08:00

38 lines
1.3 KiB
JSON

[
{
"sample_id": "314f59c2-e420-4fcd-9df2-a51d572e0c20_1503899:aug0",
"target_subtask": "steer_left",
"task_instruction": "Follow the visible road.",
"predicted_subtask": "steer_left",
"vlm_action_tokens_valid": true,
"vlm_trajectory_mse": 0.07854792475700378,
"diffusion_trajectory_mse": 0.14029410481452942
},
{
"sample_id": "314f59c2-e420-4fcd-9df2-a51d572e0c20_1503899:aug1",
"target_subtask": "steer_left",
"task_instruction": "Follow the visible road.",
"predicted_subtask": "steer_left",
"vlm_action_tokens_valid": true,
"vlm_trajectory_mse": 0.025470610707998276,
"diffusion_trajectory_mse": 0.11049529910087585
},
{
"sample_id": "314f59c2-e420-4fcd-9df2-a51d572e0c20_1503899:aug2",
"target_subtask": "steer_left",
"task_instruction": "Follow the visible road.",
"predicted_subtask": "steer_left",
"vlm_action_tokens_valid": true,
"vlm_trajectory_mse": 0.013774838298559189,
"diffusion_trajectory_mse": 0.04682297259569168
},
{
"sample_id": "314f59c2-e420-4fcd-9df2-a51d572e0c20_1503899:aug3",
"target_subtask": "steer_left",
"task_instruction": "Follow the visible road.",
"predicted_subtask": "steer_left",
"vlm_action_tokens_valid": true,
"vlm_trajectory_mse": 0.059195056557655334,
"diffusion_trajectory_mse": 0.1004234328866005
}
]