thanhkt's picture
Upload eval from run_all.sh
188d9aa verified
Raw History Blame Contribute Delete
20.8 kB
{
"per_task": [
{
"task_group": "nexarm",
"task_id": 0,
"metrics": {
"sum_rewards": [
19.99920067423207,
19.999372628119914,
19.99926422729372,
19.99918616074759,
19.99927323479038,
19.99932314982245,
19.99910349448996,
19.999397015865892,
20.000916807904925,
19.999355267028037,
9.999290942134582,
19.998559888181553,
20.00027048099187,
20.00040202941416,
19.9994315552777,
19.998991598784666,
19.999686528674985,
19.998855976846755,
19.999508972670203,
19.999456924250694,
19.999965159693012,
19.998779757585098,
19.99863958089083,
19.99915046099613,
19.999665862911304,
19.99973936154222,
19.99937722537097,
19.999838036321158,
19.99892409685475,
9.998970621685768,
19.998846716037455,
19.99879684881501,
19.999014338457965,
19.999998540196206,
20.000330571899685,
19.99881522118737,
19.999278899879666,
20.00046927728295,
20.00073299616591,
19.998863231732862,
19.999652636605056,
19.999819681013584,
19.99997230150668,
20.000663162388754,
19.999262958140825,
19.9986629155888,
19.99979255248457,
19.999813551173027,
20.00000402560931,
19.999854757569537
],
"max_rewards": [
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
1.6617342835010067,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
4.873556154065287,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0,
10.0
],
"successes": [
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
false,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
false,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true,
true
],
"video_paths": [
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_0.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_1.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_2.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_3.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_4.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_5.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_6.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_7.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_8.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_9.mp4"
],
"predicted_video_paths": [],
"stages": [
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
},
{
"picked_middle": true,
"nested_middle": true,
"released_middle": true,
"picked_top": true,
"nested_top": true,
"released_top": true
}
],
"pc_picked_middle": 100.0,
"pc_nested_middle": 100.0,
"pc_released_middle": 100.0,
"pc_picked_top": 100.0,
"pc_nested_top": 100.0,
"pc_released_top": 100.0
},
"n_episodes": 50,
"n_success": 48,
"pc_success": 96.0,
"pc_success_ci95": [
86.53990931249298,
98.89611156723801
]
}
],
"per_group": {
"nexarm": {
"avg_sum_reward": 19.599490858102175,
"avg_max_reward": 9.730705808751326,
"pc_success": 96.0,
"n_episodes": 50,
"n_success": 48,
"pc_success_ci95": [
86.53990931249298,
98.89611156723801
],
"video_paths": [
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_0.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_1.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_2.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_3.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_4.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_5.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_6.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_7.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_8.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_9.mp4"
],
"predicted_video_paths": [],
"pc_picked_middle": 100.0,
"pc_nested_middle": 100.0,
"pc_released_middle": 100.0,
"pc_picked_top": 100.0,
"pc_nested_top": 100.0,
"pc_released_top": 100.0
}
},
"overall": {
"avg_sum_reward": 19.599490858102175,
"avg_max_reward": 9.730705808751326,
"pc_success": 96.0,
"n_episodes": 50,
"n_success": 48,
"pc_success_ci95": [
86.53990931249298,
98.89611156723801
],
"eval_s": 536.4697637557983,
"eval_ep_s": 10.729395298957824,
"video_paths": [
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_0.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_1.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_2.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_3.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_4.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_5.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_6.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_7.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_8.mp4",
"/workspace/lerobot-nexarm/experiments/261027-plan-bind-two-step/outputs/full/eval/planbind_L6_latency/videos/nexarm_0/eval_episode_9.mp4"
],
"predicted_video_paths": [],
"pc_picked_middle": 100.0,
"pc_nested_middle": 100.0,
"pc_released_middle": 100.0,
"pc_picked_top": 100.0,
"pc_nested_top": 100.0,
"pc_released_top": 100.0
}
}