feat(vla): add SmolVLA conditioning and experiment artifacts

This commit is contained in:
Logic
2026-07-31 10:11:04 +08:00
parent acbd7c605a
commit 5ae9f5fa48
175 changed files with 317471 additions and 70 deletions
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,43 @@
{
"checkpoint": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/checkpoints/vla_model_step_83124.pt",
"num_rollouts": 5,
"episodes": [
{
"episode_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep01",
"avg_reward": 0.0,
"avg_max_reward": 0.0,
"video": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep01/rollout_front.mp4",
"summary_json": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep01/rollout_summary.json"
},
{
"episode_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep02",
"avg_reward": 0.0,
"avg_max_reward": 0.0,
"video": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep02/rollout_front.mp4",
"summary_json": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep02/rollout_summary.json"
},
{
"episode_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep03",
"avg_reward": 0.0,
"avg_max_reward": 0.0,
"video": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep03/rollout_front.mp4",
"summary_json": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep03/rollout_summary.json"
},
{
"episode_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep04",
"avg_reward": 2.0,
"avg_max_reward": 2.0,
"video": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep04/rollout_front.mp4",
"summary_json": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep04/rollout_summary.json"
},
{
"episode_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep05",
"avg_reward": 1408.0,
"avg_max_reward": 4.0,
"video": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep05/rollout_front.mp4",
"summary_json": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep05/rollout_summary.json"
}
],
"mean_avg_reward": 282.0,
"best_avg_reward": 1408.0
}
@@ -0,0 +1,216 @@
{
"num_episodes": 1,
"episode_rewards": [
0.0
],
"episode_max_rewards": [
0.0
],
"avg_reward": 0.0,
"avg_max_reward": 0.0,
"episodes": [
{
"inference_fps": 416.328579450197,
"control_fps": 16.62784691072735,
"avg_obs_read_time_ms": 2.911593945131504,
"avg_preprocess_time_ms": 6.928545483055392,
"avg_inference_time_ms": 2.401948963774235,
"avg_env_step_time_ms": 47.72096303665811,
"avg_total_time_ms": 60.14007738758145,
"num_inferences": 88,
"num_model_forwards": 88,
"num_steps": 700,
"episode_reward": 0.0,
"episode_max_reward": 0.0,
"artifact_paths": {
"video": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep01/rollout_front.mp4",
"trajectory": null,
"timing": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep01/rollout_summary.json"
},
"timing_breakdown_ms": {
"obs_read": {
"mean": 2.911593945131504,
"std": 0.2611419950299626,
"min": 2.712091023568064,
"max": 7.493758981581777
},
"preprocess": {
"mean": 6.928545483055392,
"std": 0.5543077871256182,
"min": 6.473146029748023,
"max": 19.883478991687298
},
"inference": {
"mean": 2.401948963774235,
"std": 12.794224178610442,
"min": 0.49940100871026516,
"max": 327.08223100053146
},
"env_step": {
"mean": 47.72096303665811,
"std": 2.1171372236113726,
"min": 39.931224018801004,
"max": 76.46449701860547
},
"loop_total": {
"mean": 60.14007738758145,
"std": 13.188809002297118,
"min": 56.274613016285,
"max": 389.8623649729416
}
},
"timing_summary": {
"count": 700,
"model_forward_count": 88,
"all_steps_ms": {
"obs_read": {
"mean": 2.911593945131504,
"std": 0.2611419950299626,
"min": 2.712091023568064,
"max": 7.493758981581777
},
"preprocess": {
"mean": 6.928545483055392,
"std": 0.5543077871256182,
"min": 6.473146029748023,
"max": 19.883478991687298
},
"inference": {
"mean": 2.401948963774235,
"std": 12.794224178610442,
"min": 0.49940100871026516,
"max": 327.08223100053146
},
"env_step": {
"mean": 47.72096303665811,
"std": 2.1171372236113726,
"min": 39.931224018801004,
"max": 76.46449701860547
},
"loop_total": {
"mean": 60.14007738758145,
"std": 13.188809002297118,
"min": 56.274613016285,
"max": 389.8623649729416
}
},
"model_forward_steps_ms": {
"obs_read": {
"mean": 2.8758058099562978,
"std": 0.0751506551331651,
"min": 2.712091023568064,
"max": 3.0596989672631025
},
"preprocess": {
"mean": 7.1382775310088284,
"std": 1.3865518440871207,
"min": 6.516602006740868,
"max": 19.883478991687298
},
"inference": {
"mean": 15.048258656778755,
"std": 33.453789958947034,
"min": 11.253663979005069,
"max": 327.08223100053146
},
"env_step": {
"mean": 47.788851250185296,
"std": 1.684109686362168,
"min": 39.931224018801004,
"max": 56.31602002540603
},
"loop_total": {
"mean": 73.03679807624907,
"std": 34.000319709963435,
"min": 67.7422959706746,
"max": 389.8623649729416
}
}
}
}
],
"artifact_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep01",
"artifacts": {
"output_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep01",
"summary_json": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep01/rollout_summary.json",
"timing_json": null,
"trajectory_npz": null,
"video_mp4": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep01/rollout_front.mp4",
"video_camera_name": "front"
},
"avg_inference_fps": 416.328579450197,
"avg_control_fps": 16.62784691072735,
"avg_obs_read_time_ms": 2.911593945131504,
"avg_preprocess_time_ms": 6.928545483055392,
"avg_inference_time_ms": 2.401948963774235,
"avg_env_step_time_ms": 47.72096303665811,
"avg_total_time_ms": 60.14007738758145,
"timing_summary": {
"count": 700,
"model_forward_count": 88,
"all_steps_ms": {
"obs_read": {
"mean": 2.911593945131504,
"std": 0.2611419950299626,
"min": 2.712091023568064,
"max": 7.493758981581777
},
"preprocess": {
"mean": 6.928545483055392,
"std": 0.5543077871256182,
"min": 6.473146029748023,
"max": 19.883478991687298
},
"inference": {
"mean": 2.401948963774235,
"std": 12.794224178610442,
"min": 0.49940100871026516,
"max": 327.08223100053146
},
"env_step": {
"mean": 47.72096303665811,
"std": 2.1171372236113726,
"min": 39.931224018801004,
"max": 76.46449701860547
},
"loop_total": {
"mean": 60.14007738758145,
"std": 13.188809002297118,
"min": 56.274613016285,
"max": 389.8623649729416
}
},
"model_forward_steps_ms": {
"obs_read": {
"mean": 2.8758058099562978,
"std": 0.0751506551331651,
"min": 2.712091023568064,
"max": 3.0596989672631025
},
"preprocess": {
"mean": 7.1382775310088284,
"std": 1.3865518440871207,
"min": 6.516602006740868,
"max": 19.883478991687298
},
"inference": {
"mean": 15.048258656778755,
"std": 33.453789958947034,
"min": 11.253663979005069,
"max": 327.08223100053146
},
"env_step": {
"mean": 47.788851250185296,
"std": 1.684109686362168,
"min": 39.931224018801004,
"max": 56.31602002540603
},
"loop_total": {
"mean": 73.03679807624907,
"std": 34.000319709963435,
"min": 67.7422959706746,
"max": 389.8623649729416
}
}
}
}
@@ -0,0 +1,216 @@
{
"num_episodes": 1,
"episode_rewards": [
0.0
],
"episode_max_rewards": [
0.0
],
"avg_reward": 0.0,
"avg_max_reward": 0.0,
"episodes": [
{
"inference_fps": 423.2530657749397,
"control_fps": 16.369630991018912,
"avg_obs_read_time_ms": 2.922768201263222,
"avg_preprocess_time_ms": 7.034949533491662,
"avg_inference_time_ms": 2.362652703221621,
"avg_env_step_time_ms": 48.58740326665741,
"avg_total_time_ms": 61.088731966447085,
"num_inferences": 88,
"num_model_forwards": 88,
"num_steps": 700,
"episode_reward": 0.0,
"episode_max_reward": 0.0,
"artifact_paths": {
"video": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep02/rollout_front.mp4",
"trajectory": null,
"timing": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep02/rollout_summary.json"
},
"timing_breakdown_ms": {
"obs_read": {
"mean": 2.922768201263222,
"std": 0.20864628356732534,
"min": 2.7384720160625875,
"max": 4.775333974976093
},
"preprocess": {
"mean": 7.034949533491662,
"std": 0.6020329090344461,
"min": 6.419215991627425,
"max": 10.473316011484712
},
"inference": {
"mean": 2.362652703221621,
"std": 12.69272670328858,
"min": 0.4969470319338143,
"max": 324.9893220490776
},
"env_step": {
"mean": 48.58740326665741,
"std": 3.577976984950618,
"min": 41.04071902111173,
"max": 67.934600985609
},
"loop_total": {
"mean": 61.088731966447085,
"std": 13.227582693702194,
"min": 56.584795005619526,
"max": 378.0319819925353
}
},
"timing_summary": {
"count": 700,
"model_forward_count": 88,
"all_steps_ms": {
"obs_read": {
"mean": 2.922768201263222,
"std": 0.20864628356732534,
"min": 2.7384720160625875,
"max": 4.775333974976093
},
"preprocess": {
"mean": 7.034949533491662,
"std": 0.6020329090344461,
"min": 6.419215991627425,
"max": 10.473316011484712
},
"inference": {
"mean": 2.362652703221621,
"std": 12.69272670328858,
"min": 0.4969470319338143,
"max": 324.9893220490776
},
"env_step": {
"mean": 48.58740326665741,
"std": 3.577976984950618,
"min": 41.04071902111173,
"max": 67.934600985609
},
"loop_total": {
"mean": 61.088731966447085,
"std": 13.227582693702194,
"min": 56.584795005619526,
"max": 378.0319819925353
}
},
"model_forward_steps_ms": {
"obs_read": {
"mean": 2.89267532604175,
"std": 0.11125532360169263,
"min": 2.7624600334092975,
"max": 3.5272870445623994
},
"preprocess": {
"mean": 7.164920194720088,
"std": 0.6480595307828021,
"min": 6.461958982981741,
"max": 10.244207980576903
},
"inference": {
"mean": 14.722178172881037,
"std": 33.26832928567316,
"min": 10.894106002524495,
"max": 324.9893220490776
},
"env_step": {
"mean": 48.64498521717244,
"std": 3.7269116621985248,
"min": 41.04071902111173,
"max": 67.934600985609
},
"loop_total": {
"mean": 73.61584814432057,
"std": 32.98871154259634,
"min": 67.3744379892014,
"max": 378.0319819925353
}
}
}
}
],
"artifact_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep02",
"artifacts": {
"output_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep02",
"summary_json": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep02/rollout_summary.json",
"timing_json": null,
"trajectory_npz": null,
"video_mp4": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep02/rollout_front.mp4",
"video_camera_name": "front"
},
"avg_inference_fps": 423.2530657749397,
"avg_control_fps": 16.369630991018912,
"avg_obs_read_time_ms": 2.922768201263222,
"avg_preprocess_time_ms": 7.034949533491662,
"avg_inference_time_ms": 2.362652703221621,
"avg_env_step_time_ms": 48.58740326665741,
"avg_total_time_ms": 61.088731966447085,
"timing_summary": {
"count": 700,
"model_forward_count": 88,
"all_steps_ms": {
"obs_read": {
"mean": 2.922768201263222,
"std": 0.20864628356732534,
"min": 2.7384720160625875,
"max": 4.775333974976093
},
"preprocess": {
"mean": 7.034949533491662,
"std": 0.6020329090344461,
"min": 6.419215991627425,
"max": 10.473316011484712
},
"inference": {
"mean": 2.362652703221621,
"std": 12.69272670328858,
"min": 0.4969470319338143,
"max": 324.9893220490776
},
"env_step": {
"mean": 48.58740326665741,
"std": 3.577976984950618,
"min": 41.04071902111173,
"max": 67.934600985609
},
"loop_total": {
"mean": 61.088731966447085,
"std": 13.227582693702194,
"min": 56.584795005619526,
"max": 378.0319819925353
}
},
"model_forward_steps_ms": {
"obs_read": {
"mean": 2.89267532604175,
"std": 0.11125532360169263,
"min": 2.7624600334092975,
"max": 3.5272870445623994
},
"preprocess": {
"mean": 7.164920194720088,
"std": 0.6480595307828021,
"min": 6.461958982981741,
"max": 10.244207980576903
},
"inference": {
"mean": 14.722178172881037,
"std": 33.26832928567316,
"min": 10.894106002524495,
"max": 324.9893220490776
},
"env_step": {
"mean": 48.64498521717244,
"std": 3.7269116621985248,
"min": 41.04071902111173,
"max": 67.934600985609
},
"loop_total": {
"mean": 73.61584814432057,
"std": 32.98871154259634,
"min": 67.3744379892014,
"max": 378.0319819925353
}
}
}
}
@@ -0,0 +1,216 @@
{
"num_episodes": 1,
"episode_rewards": [
0.0
],
"episode_max_rewards": [
0.0
],
"avg_reward": 0.0,
"avg_max_reward": 0.0,
"episodes": [
{
"inference_fps": 428.38141787855113,
"control_fps": 16.74224842048907,
"avg_obs_read_time_ms": 2.900395128443571,
"avg_preprocess_time_ms": 6.847853548159557,
"avg_inference_time_ms": 2.3343682948533178,
"avg_env_step_time_ms": 47.4696740059049,
"avg_total_time_ms": 59.7291340377082,
"num_inferences": 88,
"num_model_forwards": 88,
"num_steps": 700,
"episode_reward": 0.0,
"episode_max_reward": 0.0,
"artifact_paths": {
"video": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep03/rollout_front.mp4",
"trajectory": null,
"timing": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep03/rollout_summary.json"
},
"timing_breakdown_ms": {
"obs_read": {
"mean": 2.900395128443571,
"std": 0.2916878594282876,
"min": 2.68459296785295,
"max": 7.19653902342543
},
"preprocess": {
"mean": 6.847853548159557,
"std": 0.21243417443892795,
"min": 6.388033041730523,
"max": 9.000881982501596
},
"inference": {
"mean": 2.3343682948533178,
"std": 11.800465870815552,
"min": 0.49768202006816864,
"max": 300.0851860269904
},
"env_step": {
"mean": 47.4696740059049,
"std": 1.7681566119287178,
"min": 41.32056800881401,
"max": 82.69464899785817
},
"loop_total": {
"mean": 59.7291340377082,
"std": 11.80948193858811,
"min": 56.34060001466423,
"max": 353.5165900248103
}
},
"timing_summary": {
"count": 700,
"model_forward_count": 88,
"all_steps_ms": {
"obs_read": {
"mean": 2.900395128443571,
"std": 0.2916878594282876,
"min": 2.68459296785295,
"max": 7.19653902342543
},
"preprocess": {
"mean": 6.847853548159557,
"std": 0.21243417443892795,
"min": 6.388033041730523,
"max": 9.000881982501596
},
"inference": {
"mean": 2.3343682948533178,
"std": 11.800465870815552,
"min": 0.49768202006816864,
"max": 300.0851860269904
},
"env_step": {
"mean": 47.4696740059049,
"std": 1.7681566119287178,
"min": 41.32056800881401,
"max": 82.69464899785817
},
"loop_total": {
"mean": 59.7291340377082,
"std": 11.80948193858811,
"min": 56.34060001466423,
"max": 353.5165900248103
}
},
"model_forward_steps_ms": {
"obs_read": {
"mean": 2.850530921105846,
"std": 0.06315892633423309,
"min": 2.729182015173137,
"max": 2.99588602501899
},
"preprocess": {
"mean": 6.963662055733783,
"std": 0.3317973295122339,
"min": 6.484561017714441,
"max": 9.000881982501596
},
"inference": {
"mean": 14.542899646171877,
"std": 30.613461495155526,
"min": 11.056077957618982,
"max": 300.0851860269904
},
"env_step": {
"mean": 47.46852555862543,
"std": 0.9486706652557946,
"min": 41.32056800881401,
"max": 49.64756895788014
},
"loop_total": {
"mean": 72.01395506920313,
"std": 30.190598270939223,
"min": 67.28241901146248,
"max": 353.5165900248103
}
}
}
}
],
"artifact_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep03",
"artifacts": {
"output_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep03",
"summary_json": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep03/rollout_summary.json",
"timing_json": null,
"trajectory_npz": null,
"video_mp4": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep03/rollout_front.mp4",
"video_camera_name": "front"
},
"avg_inference_fps": 428.38141787855113,
"avg_control_fps": 16.74224842048907,
"avg_obs_read_time_ms": 2.900395128443571,
"avg_preprocess_time_ms": 6.847853548159557,
"avg_inference_time_ms": 2.3343682948533178,
"avg_env_step_time_ms": 47.4696740059049,
"avg_total_time_ms": 59.7291340377082,
"timing_summary": {
"count": 700,
"model_forward_count": 88,
"all_steps_ms": {
"obs_read": {
"mean": 2.900395128443571,
"std": 0.2916878594282876,
"min": 2.68459296785295,
"max": 7.19653902342543
},
"preprocess": {
"mean": 6.847853548159557,
"std": 0.21243417443892795,
"min": 6.388033041730523,
"max": 9.000881982501596
},
"inference": {
"mean": 2.3343682948533178,
"std": 11.800465870815552,
"min": 0.49768202006816864,
"max": 300.0851860269904
},
"env_step": {
"mean": 47.4696740059049,
"std": 1.7681566119287178,
"min": 41.32056800881401,
"max": 82.69464899785817
},
"loop_total": {
"mean": 59.7291340377082,
"std": 11.80948193858811,
"min": 56.34060001466423,
"max": 353.5165900248103
}
},
"model_forward_steps_ms": {
"obs_read": {
"mean": 2.850530921105846,
"std": 0.06315892633423309,
"min": 2.729182015173137,
"max": 2.99588602501899
},
"preprocess": {
"mean": 6.963662055733783,
"std": 0.3317973295122339,
"min": 6.484561017714441,
"max": 9.000881982501596
},
"inference": {
"mean": 14.542899646171877,
"std": 30.613461495155526,
"min": 11.056077957618982,
"max": 300.0851860269904
},
"env_step": {
"mean": 47.46852555862543,
"std": 0.9486706652557946,
"min": 41.32056800881401,
"max": 49.64756895788014
},
"loop_total": {
"mean": 72.01395506920313,
"std": 30.190598270939223,
"min": 67.28241901146248,
"max": 353.5165900248103
}
}
}
}
@@ -0,0 +1,216 @@
{
"num_episodes": 1,
"episode_rewards": [
2.0
],
"episode_max_rewards": [
2.0
],
"avg_reward": 2.0,
"avg_max_reward": 2.0,
"episodes": [
{
"inference_fps": 425.1027328138825,
"control_fps": 17.116880794537646,
"avg_obs_read_time_ms": 2.8568991100681678,
"avg_preprocess_time_ms": 6.912527064227366,
"avg_inference_time_ms": 2.3523725509377464,
"avg_env_step_time_ms": 46.12416496566896,
"avg_total_time_ms": 58.42185921626099,
"num_inferences": 88,
"num_model_forwards": 88,
"num_steps": 700,
"episode_reward": 2.0,
"episode_max_reward": 2.0,
"artifact_paths": {
"video": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep04/rollout_front.mp4",
"trajectory": null,
"timing": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep04/rollout_summary.json"
},
"timing_breakdown_ms": {
"obs_read": {
"mean": 2.8568991100681678,
"std": 0.20988493064877758,
"min": 2.6854430325329304,
"max": 5.505044013261795
},
"preprocess": {
"mean": 6.912527064227366,
"std": 0.3468982959934229,
"min": 6.422812002710998,
"max": 13.460688991472125
},
"inference": {
"mean": 2.3523725509377464,
"std": 12.345277540311537,
"min": 0.4927710397168994,
"max": 315.18344301730394
},
"env_step": {
"mean": 46.12416496566896,
"std": 1.6786026968893601,
"min": 40.27245403267443,
"max": 69.19108401052654
},
"loop_total": {
"mean": 58.42185921626099,
"std": 12.395693709763066,
"min": 54.73730497760698,
"max": 368.8187550287694
}
},
"timing_summary": {
"count": 700,
"model_forward_count": 88,
"all_steps_ms": {
"obs_read": {
"mean": 2.8568991100681678,
"std": 0.20988493064877758,
"min": 2.6854430325329304,
"max": 5.505044013261795
},
"preprocess": {
"mean": 6.912527064227366,
"std": 0.3468982959934229,
"min": 6.422812002710998,
"max": 13.460688991472125
},
"inference": {
"mean": 2.3523725509377464,
"std": 12.345277540311537,
"min": 0.4927710397168994,
"max": 315.18344301730394
},
"env_step": {
"mean": 46.12416496566896,
"std": 1.6786026968893601,
"min": 40.27245403267443,
"max": 69.19108401052654
},
"loop_total": {
"mean": 58.42185921626099,
"std": 12.395693709763066,
"min": 54.73730497760698,
"max": 368.8187550287694
}
},
"model_forward_steps_ms": {
"obs_read": {
"mean": 2.8195713563367133,
"std": 0.05933493418683723,
"min": 2.6968690217472613,
"max": 2.953937044367194
},
"preprocess": {
"mean": 7.006697107333986,
"std": 0.4376351299601935,
"min": 6.50148798013106,
"max": 10.386412963271141
},
"inference": {
"mean": 14.704165457012344,
"std": 32.214912229767435,
"min": 11.083905992563814,
"max": 315.18344301730394
},
"env_step": {
"mean": 46.088106907105114,
"std": 1.088099613967191,
"min": 40.27245403267443,
"max": 49.108261009678245
},
"loop_total": {
"mean": 70.80417735150232,
"std": 31.96448918725213,
"min": 65.67699601873755,
"max": 368.8187550287694
}
}
}
}
],
"artifact_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep04",
"artifacts": {
"output_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep04",
"summary_json": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep04/rollout_summary.json",
"timing_json": null,
"trajectory_npz": null,
"video_mp4": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep04/rollout_front.mp4",
"video_camera_name": "front"
},
"avg_inference_fps": 425.1027328138825,
"avg_control_fps": 17.116880794537646,
"avg_obs_read_time_ms": 2.8568991100681678,
"avg_preprocess_time_ms": 6.912527064227366,
"avg_inference_time_ms": 2.3523725509377464,
"avg_env_step_time_ms": 46.12416496566896,
"avg_total_time_ms": 58.42185921626099,
"timing_summary": {
"count": 700,
"model_forward_count": 88,
"all_steps_ms": {
"obs_read": {
"mean": 2.8568991100681678,
"std": 0.20988493064877758,
"min": 2.6854430325329304,
"max": 5.505044013261795
},
"preprocess": {
"mean": 6.912527064227366,
"std": 0.3468982959934229,
"min": 6.422812002710998,
"max": 13.460688991472125
},
"inference": {
"mean": 2.3523725509377464,
"std": 12.345277540311537,
"min": 0.4927710397168994,
"max": 315.18344301730394
},
"env_step": {
"mean": 46.12416496566896,
"std": 1.6786026968893601,
"min": 40.27245403267443,
"max": 69.19108401052654
},
"loop_total": {
"mean": 58.42185921626099,
"std": 12.395693709763066,
"min": 54.73730497760698,
"max": 368.8187550287694
}
},
"model_forward_steps_ms": {
"obs_read": {
"mean": 2.8195713563367133,
"std": 0.05933493418683723,
"min": 2.6968690217472613,
"max": 2.953937044367194
},
"preprocess": {
"mean": 7.006697107333986,
"std": 0.4376351299601935,
"min": 6.50148798013106,
"max": 10.386412963271141
},
"inference": {
"mean": 14.704165457012344,
"std": 32.214912229767435,
"min": 11.083905992563814,
"max": 315.18344301730394
},
"env_step": {
"mean": 46.088106907105114,
"std": 1.088099613967191,
"min": 40.27245403267443,
"max": 49.108261009678245
},
"loop_total": {
"mean": 70.80417735150232,
"std": 31.96448918725213,
"min": 65.67699601873755,
"max": 368.8187550287694
}
}
}
}
@@ -0,0 +1,216 @@
{
"num_episodes": 1,
"episode_rewards": [
1408.0
],
"episode_max_rewards": [
4.0
],
"avg_reward": 1408.0,
"avg_max_reward": 4.0,
"episodes": [
{
"inference_fps": 421.5143683898348,
"control_fps": 15.98697584872221,
"avg_obs_read_time_ms": 2.916401576450361,
"avg_preprocess_time_ms": 6.9587834345709,
"avg_inference_time_ms": 2.372398368814694,
"avg_env_step_time_ms": 50.12335285793857,
"avg_total_time_ms": 62.55091703787912,
"num_inferences": 88,
"num_model_forwards": 88,
"num_steps": 700,
"episode_reward": 1408.0,
"episode_max_reward": 4.0,
"artifact_paths": {
"video": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep05/rollout_front.mp4",
"trajectory": null,
"timing": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep05/rollout_summary.json"
},
"timing_breakdown_ms": {
"obs_read": {
"mean": 2.916401576450361,
"std": 0.19681075249117103,
"min": 2.723354031331837,
"max": 4.304414032958448
},
"preprocess": {
"mean": 6.9587834345709,
"std": 0.32918428959573737,
"min": 6.440367025788873,
"max": 10.836776986252517
},
"inference": {
"mean": 2.372398368814694,
"std": 12.755981125405425,
"min": 0.4968460416421294,
"max": 326.6250739688985
},
"env_step": {
"mean": 50.12335285793857,
"std": 2.0541933730540083,
"min": 41.243349958676845,
"max": 59.02870395220816
},
"loop_total": {
"mean": 62.55091703787912,
"std": 12.685506605997542,
"min": 57.05423402832821,
"max": 379.86371299484745
}
},
"timing_summary": {
"count": 700,
"model_forward_count": 88,
"all_steps_ms": {
"obs_read": {
"mean": 2.916401576450361,
"std": 0.19681075249117103,
"min": 2.723354031331837,
"max": 4.304414032958448
},
"preprocess": {
"mean": 6.9587834345709,
"std": 0.32918428959573737,
"min": 6.440367025788873,
"max": 10.836776986252517
},
"inference": {
"mean": 2.372398368814694,
"std": 12.755981125405425,
"min": 0.4968460416421294,
"max": 326.6250739688985
},
"env_step": {
"mean": 50.12335285793857,
"std": 2.0541933730540083,
"min": 41.243349958676845,
"max": 59.02870395220816
},
"loop_total": {
"mean": 62.55091703787912,
"std": 12.685506605997542,
"min": 57.05423402832821,
"max": 379.86371299484745
}
},
"model_forward_steps_ms": {
"obs_read": {
"mean": 2.8879472850927743,
"std": 0.09183274389315361,
"min": 2.758314018137753,
"max": 3.517468983773142
},
"preprocess": {
"mean": 7.111402045914226,
"std": 0.5243812452094909,
"min": 6.641154002863914,
"max": 10.836776986252517
},
"inference": {
"mean": 14.798059454320041,
"std": 33.432189809551524,
"min": 10.985016997437924,
"max": 326.6250739688985
},
"env_step": {
"mean": 49.97409828435841,
"std": 2.1747279952000875,
"min": 41.243349958676845,
"max": 56.928464968223125
},
"loop_total": {
"mean": 74.9630101153426,
"std": 32.74896535841012,
"min": 67.58100300794467,
"max": 379.86371299484745
}
}
}
}
],
"artifact_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep05",
"artifacts": {
"output_dir": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep05",
"summary_json": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep05/rollout_summary.json",
"timing_json": null,
"trajectory_npz": null,
"video_mp4": "/home/droid/roboimi_imf_attnres/runs/sim-transfer-imf-attnres-emb384-l12-ph16-step150k-roll5x5-lr2p5e4-restart-20260402-104553/rollout-step83124-front-5x-20260403-090744/ep05/rollout_front.mp4",
"video_camera_name": "front"
},
"avg_inference_fps": 421.5143683898348,
"avg_control_fps": 15.98697584872221,
"avg_obs_read_time_ms": 2.916401576450361,
"avg_preprocess_time_ms": 6.9587834345709,
"avg_inference_time_ms": 2.372398368814694,
"avg_env_step_time_ms": 50.12335285793857,
"avg_total_time_ms": 62.55091703787912,
"timing_summary": {
"count": 700,
"model_forward_count": 88,
"all_steps_ms": {
"obs_read": {
"mean": 2.916401576450361,
"std": 0.19681075249117103,
"min": 2.723354031331837,
"max": 4.304414032958448
},
"preprocess": {
"mean": 6.9587834345709,
"std": 0.32918428959573737,
"min": 6.440367025788873,
"max": 10.836776986252517
},
"inference": {
"mean": 2.372398368814694,
"std": 12.755981125405425,
"min": 0.4968460416421294,
"max": 326.6250739688985
},
"env_step": {
"mean": 50.12335285793857,
"std": 2.0541933730540083,
"min": 41.243349958676845,
"max": 59.02870395220816
},
"loop_total": {
"mean": 62.55091703787912,
"std": 12.685506605997542,
"min": 57.05423402832821,
"max": 379.86371299484745
}
},
"model_forward_steps_ms": {
"obs_read": {
"mean": 2.8879472850927743,
"std": 0.09183274389315361,
"min": 2.758314018137753,
"max": 3.517468983773142
},
"preprocess": {
"mean": 7.111402045914226,
"std": 0.5243812452094909,
"min": 6.641154002863914,
"max": 10.836776986252517
},
"inference": {
"mean": 14.798059454320041,
"std": 33.432189809551524,
"min": 10.985016997437924,
"max": 326.6250739688985
},
"env_step": {
"mean": 49.97409828435841,
"std": 2.1747279952000875,
"min": 41.243349958676845,
"max": 56.928464968223125
},
"loop_total": {
"mean": 74.9630101153426,
"std": 32.74896535841012,
"min": 67.58100300794467,
"max": 379.86371299484745
}
}
}
}
@@ -0,0 +1,41 @@
{
"status": "success",
"task_name": "sim_transfer",
"success_video": "/data/roboimi_rollout_videos/scripted_success_20260529/sim_transfer/success_front.mp4",
"max_reward_required": 4,
"attempts": [
{
"attempt": 1,
"task_name": "sim_transfer",
"success": true,
"sum_reward": 1238.0,
"max_reward": 4.0,
"max_reward_required": 4,
"max_reward_step": 503,
"episode_len": 700,
"elapsed_s": 29.355701208114624,
"sim_steps_per_wall_s": 23.845453223461178,
"video_path": "/data/roboimi_rollout_videos/scripted_success_20260529/sim_transfer/attempt_001_front.mp4",
"task_state": [
0.0338307802064175,
0.9599788062599779,
0.47
],
"reward_trace": [
{
"step": 0,
"reward": 0.0
},
{
"step": 278,
"reward": 2.0
},
{
"step": 503,
"reward": 4.0
}
]
}
],
"created_at": "2026-05-29T19:28:23+0800"
}
@@ -0,0 +1,80 @@
{
"status": "success",
"task_name": "sim_air_insert_socket_peg",
"success_video": "/data/roboimi_rollout_videos/scripted_success_20260529/sim_air_insert_socket_peg/success_front.mp4",
"max_reward_required": 5,
"attempts": [
{
"attempt": 1,
"task_name": "sim_air_insert_socket_peg",
"success": true,
"sum_reward": 1942.0,
"max_reward": 5.0,
"max_reward_required": 5,
"max_reward_step": 583,
"episode_len": 750,
"elapsed_s": 35.83620357513428,
"sim_steps_per_wall_s": 20.92855618557775,
"video_path": "/data/roboimi_rollout_videos/scripted_success_20260529/sim_air_insert_socket_peg/attempt_001_front.mp4",
"task_state": {
"socket_pos": [
-0.14154230058193207,
0.9299893975257874,
0.47200000286102295
],
"socket_quat": [
1.0,
0.0,
0.0,
0.0
],
"peg_pos": [
0.13059355318546295,
0.881460428237915,
0.46000000834465027
],
"peg_quat": [
1.0,
0.0,
0.0,
0.0
]
},
"reward_trace": [
{
"step": 0,
"reward": 0.0
},
{
"step": 132,
"reward": 1.0
},
{
"step": 171,
"reward": 2.0
},
{
"step": 185,
"reward": 3.0
},
{
"step": 186,
"reward": 2.0
},
{
"step": 190,
"reward": 3.0
},
{
"step": 351,
"reward": 4.0
},
{
"step": 583,
"reward": 5.0
}
]
}
],
"created_at": "2026-05-29T19:31:20+0800"
}
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,191 @@
{
"agent": {
"vision_backbone": {
"_target_": "roboimi.vla.models.backbones.resnet_diffusion.ResNetDiffusionBackbone",
"vision_backbone": "resnet18",
"pretrained_backbone_weights": null,
"vision_backbone_mode": "resnet",
"freeze_backbone": false,
"input_shape": [
3,
224,
224
],
"crop_shape": null,
"crop_is_random": true,
"use_group_norm": true,
"spatial_softmax_num_keypoints": 32,
"use_separate_rgb_encoder_per_camera": true,
"output_tokens_per_camera": false,
"num_cameras": 3,
"attnres_stem_dim": 64,
"attnres_stage_dims": [
64,
128,
256,
512
],
"attnres_stage_depths": [
2,
2,
2,
2
],
"attnres_stage_heads": [
4,
4,
8,
8
],
"attnres_stage_kv_heads": [
1,
1,
1,
1
],
"attnres_stage_window_sizes": [
7,
7,
7,
7
],
"attnres_dropout": 0.0,
"attnres_ffn_mult": 2.667,
"attnres_eps": 1e-06,
"attnres_rope_theta": 10000.0,
"camera_names": [
"r_vis",
"top",
"front"
]
},
"state_encoder": {
"_target_": "roboimi.vla.modules.encoders.IdentityStateEncoder"
},
"action_encoder": {
"_target_": "roboimi.vla.modules.encoders.IdentityActionEncoder"
},
"head": {
"_target_": "roboimi.vla.models.heads.transformer1d.Transformer1D",
"_partial_": true,
"n_layer": 18,
"n_head": 4,
"n_emb": 384,
"p_drop_emb": 0.05,
"p_drop_attn": 0.05,
"causal_attn": false,
"time_as_cond": true,
"obs_as_cond": true,
"n_cond_layers": 1,
"input_dim": 16,
"output_dim": 16,
"horizon": 16,
"n_obs_steps": 2,
"cond_dim": 208
},
"_target_": "roboimi.vla.agent.VLAAgent",
"action_dim": 16,
"obs_dim": 16,
"normalization_type": "min_max",
"pred_horizon": 16,
"obs_horizon": 2,
"num_action_steps": 8,
"camera_names": [
"r_vis",
"top",
"front"
],
"num_cams": 3,
"diffusion_steps": 100,
"inference_steps": 100,
"head_type": "transformer"
},
"data": {
"_target_": "roboimi.vla.data.simpe_robot_dataset.SimpleRobotDataset",
"dataset_dir": "/home/droid/project/diana_sim/sim_transfer",
"pred_horizon": 16,
"obs_horizon": 2,
"camera_names": [
"r_vis",
"top",
"front"
],
"image_resize_shape": [
224,
224
]
},
"eval": {
"ckpt_path": "/home/droid/project/roboimi/runs/sim-transfer-no-pretrain-ph16-emb384-l18-infer100-unfreeze-150k-roll5x5-20260331-235043/checkpoints/vla_model_best.pt",
"num_episodes": 3,
"num_workers": 1,
"cuda_devices": null,
"response_timeout_s": 300.0,
"server_startup_timeout_s": 300.0,
"max_timesteps": 700,
"device": "cuda",
"task_name": "sim_transfer",
"task_description": null,
"num_queries": 8,
"obs_horizon": 2,
"camera_names": [
"r_vis",
"top",
"front"
],
"use_smoothing": false,
"smooth_method": "ema",
"smooth_alpha": 0.3,
"headless": true,
"verbose_action": false,
"artifact_dir": null,
"save_artifacts": false,
"save_timing": false,
"save_trajectory": false,
"save_summary_json": false,
"save_trajectory_npz": false,
"save_trajectory_image": false,
"trajectory_image_camera": null,
"trajectory_image_camera_name": null,
"record_video": false,
"video_camera": null,
"video_camera_name": null,
"video_fps": 30
},
"train": {
"batch_size": 16,
"lr": 0.0001,
"max_steps": 100000,
"device": "cuda",
"disable_cudnn": false,
"num_workers": 12,
"val_split": 0.0,
"val_episode_indices": null,
"action_mse_val_freq_epochs": 0,
"seed": 42,
"log_freq": 100,
"save_freq": 2000,
"use_swanlab": false,
"swanlab_project": "roboimi-vla",
"swanlab_run_name": null,
"rollout_val_freq_epochs": 50,
"rollout_validate_on_checkpoint": false,
"rollout_num_episodes": 3,
"rollout_device": "cuda",
"rollout_num_workers": null,
"rollout_cuda_devices": null,
"rollout_response_timeout_s": 300.0,
"rollout_server_startup_timeout_s": 300.0,
"warmup_steps": 2000,
"scheduler_type": "cosine",
"min_lr": 1e-06,
"weight_decay": 1e-05,
"grad_clip": 1.0,
"pretrained_ckpt": null
},
"experiment": {
"name": "vla_diffusion",
"notes": "",
"tags": []
}
}
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,198 @@
{
"agent": {
"vision_backbone": {
"_target_": "roboimi.vla.models.backbones.resnet_diffusion.ResNetDiffusionBackbone",
"vision_backbone": "resnet18",
"pretrained_backbone_weights": null,
"vision_backbone_mode": "resnet",
"freeze_backbone": false,
"input_shape": [
3,
224,
224
],
"crop_shape": null,
"crop_is_random": true,
"use_group_norm": true,
"spatial_softmax_num_keypoints": 32,
"use_separate_rgb_encoder_per_camera": true,
"output_tokens_per_camera": false,
"num_cameras": 3,
"attnres_stem_dim": 64,
"attnres_stage_dims": [
64,
128,
256,
512
],
"attnres_stage_depths": [
2,
2,
2,
2
],
"attnres_stage_heads": [
4,
4,
8,
8
],
"attnres_stage_kv_heads": [
1,
1,
1,
1
],
"attnres_stage_window_sizes": [
7,
7,
7,
7
],
"attnres_dropout": 0.0,
"attnres_ffn_mult": 2.667,
"attnres_eps": 1e-06,
"attnres_rope_theta": 10000.0,
"camera_names": [
"r_vis",
"top",
"front"
]
},
"state_encoder": {
"_target_": "roboimi.vla.modules.encoders.IdentityStateEncoder"
},
"action_encoder": {
"_target_": "roboimi.vla.modules.encoders.IdentityActionEncoder"
},
"head": {
"_target_": "roboimi.vla.models.heads.imf_transformer1d.IMFTransformer1D",
"_partial_": true,
"input_dim": 16,
"output_dim": 16,
"horizon": 32,
"n_obs_steps": 2,
"cond_dim": 208,
"n_layer": 12,
"n_head": 1,
"n_emb": 384,
"p_drop_emb": 0.1,
"p_drop_attn": 0.1,
"causal_attn": false,
"time_as_cond": true,
"obs_as_cond": true,
"n_cond_layers": 0,
"backbone_type": "attnres_full",
"n_kv_head": 1,
"attn_res_ffn_mult": 2.667,
"attn_res_eps": 1e-06,
"attn_res_rope_theta": 10000.0
},
"_target_": "roboimi.vla.agent_imf.IMFVLAAgent",
"action_dim": 16,
"obs_dim": 16,
"normalization_type": "min_max",
"pred_horizon": 32,
"obs_horizon": 2,
"num_action_steps": 16,
"camera_names": [
"r_vis",
"top",
"front"
],
"num_cams": 3,
"diffusion_steps": 100,
"inference_steps": 1,
"head_type": "transformer",
"loss_type": "pseudo_huber",
"pseudo_huber_delta": 1.0
},
"data": {
"_target_": "roboimi.vla.data.simpe_robot_dataset.SimpleRobotDataset",
"dataset_dir": "/home/droid/project/diana_sim/sim_transfer",
"pred_horizon": 32,
"obs_horizon": 2,
"camera_names": [
"r_vis",
"top",
"front"
],
"image_resize_shape": [
224,
224
]
},
"eval": {
"ckpt_path": "/home/droid/project/roboimi/.worktrees/feat-imf-attnres-policy/runs/sim-transfer-imf-attnres-ph32-exec16-emb384-l12-infer1-unfreeze-step50k-roll5x5-20260403-141304/checkpoints/vla_model_best.pt",
"num_episodes": 3,
"num_workers": 1,
"cuda_devices": null,
"response_timeout_s": 300.0,
"server_startup_timeout_s": 300.0,
"max_timesteps": 700,
"device": "cuda",
"task_name": "sim_transfer",
"task_description": null,
"num_queries": 16,
"obs_horizon": 2,
"camera_names": [
"r_vis",
"top",
"front"
],
"use_smoothing": false,
"smooth_method": "ema",
"smooth_alpha": 0.3,
"headless": true,
"verbose_action": false,
"artifact_dir": null,
"save_artifacts": false,
"save_timing": false,
"save_trajectory": false,
"save_summary_json": false,
"save_trajectory_npz": false,
"save_trajectory_image": false,
"trajectory_image_camera": null,
"trajectory_image_camera_name": null,
"record_video": false,
"video_camera": null,
"video_camera_name": null,
"video_fps": 30
},
"train": {
"batch_size": 16,
"lr": 0.0001,
"max_steps": 100000,
"device": "cuda",
"disable_cudnn": false,
"num_workers": 12,
"val_split": 0.0,
"val_episode_indices": null,
"action_mse_val_freq_epochs": 0,
"seed": 42,
"log_freq": 100,
"save_freq": 2000,
"use_swanlab": false,
"swanlab_project": "roboimi-vla",
"swanlab_run_name": null,
"rollout_val_freq_epochs": 50,
"rollout_validate_on_checkpoint": false,
"rollout_num_episodes": 3,
"rollout_device": "cuda",
"rollout_num_workers": null,
"rollout_cuda_devices": null,
"rollout_response_timeout_s": 300.0,
"rollout_server_startup_timeout_s": 300.0,
"warmup_steps": 2000,
"scheduler_type": "cosine",
"min_lr": 1e-06,
"weight_decay": 1e-05,
"grad_clip": 1.0,
"pretrained_ckpt": null
},
"experiment": {
"name": "vla_diffusion",
"notes": "",
"tags": []
}
}
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff
File diff suppressed because it is too large Load Diff