Add files using upload-large-folder tool

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0000.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 22, "pred_class_confidence": 0.20943774282932281, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 95.10314178466797, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -88.31275177001953, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.63096284866333}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 21, "pred_class_confidence": 0.08274698257446289, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 139.97000122070312, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -86.24657440185547, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.0223073959350586}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.25701919198036194, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 122.35665130615234, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -89.04837799072266, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.6550559997558594}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 3, "pred_class_confidence": 0.08685597777366638, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 78.3121337890625, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -86.89379119873047, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.792309522628784}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 13, "pred_class_confidence": 0.15430307388305664, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 72.75104522705078, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -87.88502502441406, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.0865702629089355}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6922432780265808, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 184.4738006591797, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -85.74798583984375, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 3.089069366455078}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.16453227400779724, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 30.8409481048584, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -85.97007751464844, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.558300495147705}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.3693104088306427, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 216.4490203857422, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -85.93614959716797, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.9758992195129395}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 0, "pred_class_confidence": 0.29235565662384033, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 172.69363403320312, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -84.21171569824219, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.94923734664917}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.32236090302467346, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 171.01698303222656, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -86.50161743164062, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 2.8136396408081055}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 14, "pred_class_confidence": 0.2286118119955063, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 103.57414245605469, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -86.39310455322266, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.7206618785858154}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 11, "pred_class_confidence": 0.15533563494682312, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 140.32679748535156, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -88.28753662109375, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 2.9619131088256836}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 3, "pred_class_confidence": 0.2340685874223709, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 60.99531173706055, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -85.86876678466797, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.3235063552856445}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 10, "pred_class_confidence": 0.22664886713027954, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 148.3560333251953, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -84.94126892089844, "gt_distance_m": 4.411057949066162, "pred_distance_m": 2.823364734649658}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.09956525266170502, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 162.92434692382812, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -85.34722137451172, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 2.7010397911071777}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 8, "pred_class_confidence": 0.11359802633523941, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 146.50953674316406, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -87.88825988769531, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.75351881980896}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0001.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.5398035645484924, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 259.2090759277344, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -89.72164154052734, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.824531316757202}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.11014705896377563, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 124.94129180908203, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -87.08940124511719, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.3103396892547607}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.5014060139656067, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 334.8401184082031, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -89.69480895996094, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.698563814163208}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 11, "pred_class_confidence": 0.16000044345855713, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 132.97647094726562, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -85.37687683105469, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.9177534580230713}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 11, "pred_class_confidence": 0.22404919564723969, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 79.29479217529297, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -85.4792251586914, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.386671781539917}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5060648322105408, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 40.333614349365234, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -87.00402069091797, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.4104464054107666}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 12, "pred_class_confidence": 0.15281693637371063, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 76.24407196044922, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -86.45353698730469, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.7979977130889893}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 7, "pred_class_confidence": 0.3804944157600403, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 248.23162841796875, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -87.58191680908203, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.0649402141571045}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 0, "pred_class_confidence": 0.3375866115093231, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 82.94181823730469, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -87.4792709350586, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.3474886417388916}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.6750131249427795, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 106.33749389648438, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -86.18212890625, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.2518393993377686}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 14, "pred_class_confidence": 0.2736680209636688, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 61.007972717285156, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -87.41858673095703, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.977135419845581}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 11, "pred_class_confidence": 0.49437835812568665, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 105.23577117919922, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -86.34033966064453, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 3.444913625717163}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.4799036383628845, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 101.93029022216797, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -85.95760345458984, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.6949751377105713}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.4829128682613373, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 121.34658813476562, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -83.93673706054688, "gt_distance_m": 4.411057949066162, "pred_distance_m": 3.4456892013549805}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.21575477719306946, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 125.12853240966797, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -86.17791748046875, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 3.3593263626098633}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 13, "pred_class_confidence": 0.1455526053905487, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 75.83834838867188, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -86.51603698730469, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 3.3152544498443604}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0002.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.7363958358764648, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 251.0084991455078, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -87.72367858886719, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.957367181777954}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.11320145428180695, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 66.5219955444336, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -86.2350082397461, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.3813319206237793}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.671447217464447, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 246.82113647460938, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -87.43746185302734, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.7937798500061035}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 11, "pred_class_confidence": 0.1430879384279251, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 103.07308959960938, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -86.82466888427734, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.7873451709747314}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.3205321431159973, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 88.62324523925781, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -84.3255615234375, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.9326260089874268}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.3184909522533417, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 48.39522933959961, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -86.56721496582031, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.505540609359741}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 15, "pred_class_confidence": 0.37908318638801575, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 29.115631103515625, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -81.42166900634766, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.584986686706543}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.30171191692352295, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 286.7203674316406, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -87.57456970214844, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.022139072418213}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5621039867401123, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 71.76416015625, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -84.12867736816406, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.867588996887207}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.4969165325164795, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 89.58935546875, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -83.77596282958984, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.172386884689331}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 16, "pred_class_confidence": 0.21079370379447937, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 98.43448638916016, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -86.42269897460938, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.687659502029419}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 11, "pred_class_confidence": 0.285510390996933, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 84.31522369384766, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -84.67281341552734, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 3.3698766231536865}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.2505098879337311, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 85.60792541503906, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -84.13391876220703, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.251616954803467}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.32192400097846985, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 104.58251953125, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -82.9380874633789, "gt_distance_m": 4.411057949066162, "pred_distance_m": 2.97879958152771}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.2425459772348404, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 101.52884674072266, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -86.5947494506836, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 3.3367326259613037}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.37609440088272095, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 105.07261657714844, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -87.12840270996094, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 3.046220302581787}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0003.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.4722558557987213, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 256.4629211425781, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -86.30975341796875, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.030625820159912}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.11771152168512344, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 174.18417358398438, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -88.02989959716797, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.2644894123077393}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.43516048789024353, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 256.5947265625, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -85.64297485351562, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.878848075866699}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 11, "pred_class_confidence": 0.18869276344776154, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 188.36813354492188, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -87.6856460571289, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.9031145572662354}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.42281192541122437, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 145.69309997558594, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -89.65907287597656, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.945157766342163}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.4625229239463806, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 332.6702880859375, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -88.37840270996094, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.6858088970184326}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 15, "pred_class_confidence": 0.3063005208969116, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 317.32305908203125, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -86.17280578613281, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.2284035682678223}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.427645206451416, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 234.10791015625, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -84.25300598144531, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.144484519958496}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.4484482705593109, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 114.10635375976562, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -87.9709701538086, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 3.182933807373047}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.4777337908744812, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 111.50613403320312, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -88.34992218017578, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.105739116668701}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 14, "pred_class_confidence": 0.36501067876815796, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 272.216552734375, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -87.04090881347656, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.7054903507232666}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 11, "pred_class_confidence": 0.19916248321533203, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 159.336669921875, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -88.73374938964844, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 3.3902883529663086}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.26534485816955566, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 270.559326171875, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -89.51422119140625, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.6946427822113037}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.44523757696151733, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 156.34957885742188, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -87.44970703125, "gt_distance_m": 4.411057949066162, "pred_distance_m": 2.776845932006836}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.36021649837493896, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 176.51792907714844, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -87.17915344238281, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 3.259982109069824}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.33341944217681885, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 271.49090576171875, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -87.2926025390625, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.801452875137329}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0004.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.49762848019599915, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 208.77972412109375, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -82.7267837524414, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.921656847000122}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.13209430873394012, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 122.22718048095703, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -87.28899383544922, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.290489673614502}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.6743801832199097, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 227.88177490234375, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -70.57421112060547, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.473891258239746}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 11, "pred_class_confidence": 0.25008949637413025, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 43.635765075683594, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -87.66217041015625, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.868525505065918}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.18672272562980652, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 51.0861930847168, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -86.78478240966797, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.8114492893218994}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.3317795991897583, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 229.24679565429688, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -87.46125030517578, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.291659116744995}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 15, "pred_class_confidence": 0.1996193379163742, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 8.789519309997559, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -82.14694213867188, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.2234561443328857}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 1, "pred_class_confidence": 0.38680845499038696, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 232.23573303222656, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -81.02679443359375, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.889073133468628}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.28737032413482666, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 142.4145050048828, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -85.17813873291016, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.9414145946502686}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.6417555809020996, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 49.55837631225586, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -85.38917541503906, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.1585214138031006}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 16, "pred_class_confidence": 0.37779146432876587, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 209.20249938964844, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -85.93841552734375, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.1730844974517822}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 11, "pred_class_confidence": 0.16434958577156067, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 66.40737915039062, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -86.70075225830078, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 3.19435715675354}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.29620036482810974, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 37.909637451171875, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -85.46697998046875, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.5096986293792725}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.7130841612815857, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 102.86172485351562, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -84.62330627441406, "gt_distance_m": 4.411057949066162, "pred_distance_m": 2.919029951095581}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 37, "pred_class_confidence": 0.3113099932670593, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 109.81583404541016, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -86.50643920898438, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 3.1943299770355225}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.5130134224891663, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 178.36593627929688, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -87.93730163574219, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.6961405277252197}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0005.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.43845322728157043, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 168.76206970214844, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -85.85310363769531, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.3053104877471924}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.1677979826927185, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 178.14134216308594, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -87.80358123779297, "gt_distance_m": 4.594465255737305, "pred_distance_m": 2.9328036308288574}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.5011721253395081, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 224.44601440429688, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -84.90338134765625, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 3.0509138107299805}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 52, "pred_class_confidence": 0.17978332936763763, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 288.9637145996094, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -88.38275146484375, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.3999907970428467}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.5211015939712524, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 347.7273254394531, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -88.32158660888672, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.85876202583313}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6611700057983398, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 112.02821350097656, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -88.26133728027344, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.627081871032715}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 15, "pred_class_confidence": 0.5384537577629089, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 15.666543006896973, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -83.09669494628906, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.7666099071502686}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.6648035049438477, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 141.8068084716797, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -82.52561950683594, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.979674816131592}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.35068029165267944, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 110.45287322998047, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -82.36845397949219, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 3.2937679290771484}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.46701550483703613, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 32.27647399902344, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -88.8888168334961, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.1059937477111816}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 16, "pred_class_confidence": 0.3348231315612793, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 246.95281982421875, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -87.2350845336914, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.470877170562744}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 3, "pred_class_confidence": 0.15297621488571167, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 213.02114868164062, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -89.24333190917969, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 3.007011651992798}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.24530524015426636, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 304.4723815917969, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -87.31350708007812, "gt_distance_m": 3.011542320251465, "pred_distance_m": 2.878096342086792}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.3382621705532074, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 139.99497985839844, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -86.6431655883789, "gt_distance_m": 4.411057949066162, "pred_distance_m": 2.817945718765259}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 37, "pred_class_confidence": 0.2634238004684448, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 198.11495971679688, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -87.8726577758789, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 2.94472074508667}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.2983739376068115, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 244.55667114257812, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -88.2152328491211, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.7402515411376953}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0006.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.23341946303844452, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 213.73062133789062, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -86.38951873779297, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.2404751777648926}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.14568279683589935, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 214.9480438232422, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -83.74276733398438, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.4236819744110107}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.4557383358478546, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 246.98387145996094, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -83.74580383300781, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 3.0686001777648926}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 11, "pred_class_confidence": 0.2813423275947571, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 233.60186767578125, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -87.40678405761719, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.2403998374938965}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.6423636078834534, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 252.53857421875, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -88.31507110595703, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.365598201751709}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 14, "pred_class_confidence": 0.22918155789375305, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 245.01828002929688, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -88.34412384033203, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.5820794105529785}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 25, "pred_class_confidence": 0.12222818285226822, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 326.701416015625, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -86.75363159179688, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.4166007041931152}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 7, "pred_class_confidence": 0.39350324869155884, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 188.37100219726562, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -86.74581146240234, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.0884640216827393}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.6843397617340088, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 140.18772888183594, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -85.53582000732422, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 3.3020341396331787}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.659477949142456, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 182.92691040039062, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -89.37850189208984, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.6028389930725098}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 16, "pred_class_confidence": 0.3382132053375244, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 219.32504272460938, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -83.89757537841797, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.54551362991333}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 25, "pred_class_confidence": 0.17856155335903168, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 216.8057861328125, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -87.21441650390625, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 3.7244739532470703}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.33624953031539917, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 276.4429626464844, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -86.7275619506836, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.634424924850464}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.5107690095901489, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 162.1920623779297, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -85.09979248046875, "gt_distance_m": 4.411057949066162, "pred_distance_m": 3.197772741317749}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.3320308327674866, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 245.10671997070312, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -84.01810455322266, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 3.5839877128601074}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.41999125480651855, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 236.10227966308594, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -84.0893783569336, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 3.0452706813812256}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0007.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.5945493578910828, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 254.3120880126953, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -83.67959594726562, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.3697712421417236}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.2666841745376587, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 211.5528106689453, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -88.23153686523438, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.2081151008605957}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.7462973594665527, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 255.32933044433594, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -78.48332214355469, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 3.242957830429077}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 9, "pred_class_confidence": 0.22805963456630707, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 35.70598220825195, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -88.91592407226562, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.6730875968933105}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.35194969177246094, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 46.46154022216797, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -88.98760223388672, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.337353467941284}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5720697641372681, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 272.21185302734375, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -86.82917022705078, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.765537738800049}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.08381232619285583, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 355.18939208984375, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -83.00922393798828, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.3437201976776123}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 7, "pred_class_confidence": 0.564382791519165, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 199.69448852539062, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -82.02432250976562, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.016134738922119}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.6799862384796143, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 182.35147094726562, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -86.7762680053711, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 3.233858585357666}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.6147969365119934, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 91.09186553955078, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -86.24860382080078, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.5238800048828125}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 14, "pred_class_confidence": 0.27052009105682373, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 242.74099731445312, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -82.82523345947266, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.9398598670959473}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 3, "pred_class_confidence": 0.13368508219718933, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 147.48898315429688, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -88.75888061523438, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 3.357569932937622}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.37792930006980896, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 75.74090576171875, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -87.5086441040039, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.6714913845062256}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.5302823185920715, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 98.16935729980469, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -83.3426284790039, "gt_distance_m": 4.411057949066162, "pred_distance_m": 3.294687271118164}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.40341976284980774, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 196.2168426513672, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -88.53219604492188, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 3.276853561401367}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.4841809868812561, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 260.4775695800781, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -85.54737091064453, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 3.3576390743255615}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0008.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.5153819918632507, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 262.5889587402344, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -86.032470703125, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.3398211002349854}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.20355141162872314, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 204.75086975097656, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -84.58546447753906, "gt_distance_m": 4.594465255737305, "pred_distance_m": 2.812316417694092}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.844221293926239, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 263.457763671875, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -82.54075622558594, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 3.0647459030151367}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 52, "pred_class_confidence": 0.31045210361480713, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 197.42889404296875, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -89.02763366699219, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.5073065757751465}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.33978089690208435, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 175.84848022460938, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -88.66177368164062, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.3130545616149902}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.47069570422172546, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 7.920968532562256, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -86.39891815185547, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.525327205657959}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 54, "pred_class_confidence": 0.09703078866004944, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 334.37872314453125, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -84.3932876586914, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.1997382640838623}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.6474654078483582, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 217.5933380126953, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -84.7491683959961, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.2427635192871094}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.7945859432220459, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 35.466552734375, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -88.01524353027344, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 3.2158920764923096}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.5476231575012207, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 124.38267517089844, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -85.55586242675781, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.350133180618286}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 31, "pred_class_confidence": 0.3150434195995331, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 250.81906127929688, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -88.46290588378906, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.5988097190856934}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 3, "pred_class_confidence": 0.17810072004795074, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 202.71170043945312, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -87.30863189697266, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 3.424954414367676}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.2588080167770386, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 185.8130645751953, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -87.38198852539062, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.677495002746582}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.6254552006721497, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 108.79229736328125, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -81.51519775390625, "gt_distance_m": 4.411057949066162, "pred_distance_m": 3.083500862121582}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.4932045340538025, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 235.5537872314453, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -83.398681640625, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 3.105123996734619}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.3704327642917633, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 255.63955688476562, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -83.94365692138672, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.8592920303344727}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0009.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.7771486043930054, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 233.91131591796875, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -75.96107482910156, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.0603723526000977}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.21413031220436096, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 222.15296936035156, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -80.44352722167969, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.278877019882202}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.7441522479057312, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 257.7598876953125, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -75.39080810546875, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.792654275894165}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 11, "pred_class_confidence": 0.36172449588775635, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 151.24720764160156, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -88.22348022460938, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.982944965362549}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.5247285962104797, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 27.851318359375, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -89.67373657226562, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.8142757415771484}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5626543760299683, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 304.2606506347656, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -87.40550231933594, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.3668041229248047}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.2538531720638275, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 352.3966979980469, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -85.20866394042969, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.9632307291030884}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.729076087474823, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 244.06417846679688, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -85.778076171875, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.7752180099487305}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.524370551109314, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 115.85995483398438, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -88.25684356689453, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 3.1268115043640137}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.5977478623390198, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 128.0132598876953, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -85.35780334472656, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 2.9356613159179688}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 16, "pred_class_confidence": 0.3513960838317871, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 261.7582092285156, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -84.03382873535156, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.4354026317596436}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 37, "pred_class_confidence": 0.16443626582622528, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 210.9159393310547, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -86.80622863769531, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 3.1637120246887207}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.5444936752319336, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 352.68414306640625, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -89.6743392944336, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.451040029525757}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.3460087776184082, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 107.93921661376953, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -83.93977355957031, "gt_distance_m": 4.411057949066162, "pred_distance_m": 2.74336314201355}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.7535335421562195, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 235.53390502929688, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -80.01920318603516, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 2.866121292114258}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.5019993782043457, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 266.91741943359375, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -80.70410919189453, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.77571439743042}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0010.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.7085316181182861, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 239.17022705078125, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -73.31533813476562, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.171360969543457}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 8, "pred_class_confidence": 0.3672455847263336, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 145.5020294189453, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -87.97686767578125, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.0787739753723145}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.6025423407554626, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 243.9852294921875, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -73.9298095703125, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.927443027496338}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 9, "pred_class_confidence": 0.3895109295845032, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 72.64111328125, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -86.93887329101562, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.505141019821167}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.37433838844299316, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 32.594154357910156, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -87.14535522460938, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.9601008892059326}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.8251450061798096, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 283.5791015625, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -87.82030487060547, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.4877445697784424}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.13615138828754425, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 357.8766174316406, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -80.87992858886719, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.5747106075286865}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.7558251023292542, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 130.9620361328125, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -87.95330047607422, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.990340232849121}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.8558290004730225, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 336.4575500488281, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -89.09280395507812, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.9536428451538086}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.862381100654602, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 88.51725006103516, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -82.07815551757812, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.339627504348755}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 32, "pred_class_confidence": 0.3204112648963928, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 197.4766845703125, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -82.35787200927734, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.6320888996124268}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 52, "pred_class_confidence": 0.12434855103492737, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 293.2331237792969, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -88.3336410522461, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 3.3136484622955322}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 9, "pred_class_confidence": 0.21163438260555267, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 340.2481689453125, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -83.65918731689453, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.360186815261841}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.6306352615356445, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 99.54354858398438, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -75.60504913330078, "gt_distance_m": 4.411057949066162, "pred_distance_m": 3.3062331676483154}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.8161624073982239, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 233.4203643798828, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -85.88053894042969, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 3.241029977798462}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.6153209209442139, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 249.06094360351562, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -78.61197662353516, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.539787769317627}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0011.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.8181705474853516, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 258.8686828613281, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -81.2349853515625, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.289194345474243}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 13, "pred_class_confidence": 0.16360153257846832, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 222.6415557861328, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -81.80036926269531, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.431957960128784}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.6747801303863525, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 256.2131042480469, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -75.68799591064453, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.9299657344818115}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 9, "pred_class_confidence": 0.28005972504615784, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 352.07470703125, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -84.54443359375, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.612240791320801}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.43213197588920593, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 352.1619567871094, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -88.22303771972656, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.082961082458496}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.42281877994537354, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 5.979127407073975, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -88.44254302978516, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.5851757526397705}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.15690021216869354, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 320.7982482910156, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -78.24044036865234, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.631430149078369}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.7513875365257263, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 259.7835998535156, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -84.72968292236328, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.021350383758545}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.7556970119476318, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 322.947021484375, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -87.69420623779297, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 3.0850026607513428}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.44144582748413086, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 103.35979461669922, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -87.80643463134766, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.405637502670288}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 16, "pred_class_confidence": 0.31740763783454895, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 201.98590087890625, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -85.58905029296875, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.57486629486084}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 25, "pred_class_confidence": 0.18288874626159668, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 280.531494140625, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -87.73480224609375, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 3.0013134479522705}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.3990529477596283, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 323.6668395996094, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -82.4407730102539, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.473351001739502}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.31573396921157837, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 88.6242904663086, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -83.86531066894531, "gt_distance_m": 4.411057949066162, "pred_distance_m": 2.9126293659210205}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.6227344870567322, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 223.4770965576172, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -83.57801055908203, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 2.960981607437134}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.29370468854904175, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 263.3701477050781, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -82.32583618164062, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 3.1915247440338135}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0012.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.9314593076705933, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 261.5445556640625, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -79.61579132080078, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.0949838161468506}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.26551932096481323, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 281.1112060546875, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -84.11044311523438, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.2987844944000244}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.8442612886428833, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 253.0372314453125, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -74.78713989257812, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.8291985988616943}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 9, "pred_class_confidence": 0.6148809194564819, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 61.42504119873047, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -86.76106262207031, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.8650870323181152}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.5024840235710144, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 95.0219497680664, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -84.54196166992188, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.9854962825775146}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6547335982322693, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 67.1196517944336, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -86.56891632080078, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.3506579399108887}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.36014366149902344, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 334.3975524902344, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -77.47783660888672, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.9163737297058105}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.835178017616272, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 86.408447265625, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -87.86779022216797, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.721517562866211}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.3690882623195648, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 27.222442626953125, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -85.33931732177734, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.7733449935913086}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.45978328585624695, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 108.11682891845703, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -77.37814331054688, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.119901657104492}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 16, "pred_class_confidence": 0.7533761262893677, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 157.52149963378906, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -85.3932113647461, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.4166524410247803}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 37, "pred_class_confidence": 0.21061334013938904, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 109.85071563720703, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -87.03680419921875, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 3.1512718200683594}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.34824618697166443, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 89.51923370361328, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -83.55844116210938, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.625149965286255}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.44025054574012756, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 81.64292907714844, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -71.13065338134766, "gt_distance_m": 4.411057949066162, "pred_distance_m": 3.1663880348205566}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.33898741006851196, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 179.58277893066406, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -87.4316635131836, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 3.3971750736236572}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.7143104076385498, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 243.95352172851562, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -84.568115234375, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.9993338584899902}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0013.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.8123441934585571, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 263.07781982421875, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -78.32970428466797, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.007323741912842}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.17486609518527985, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 223.15689086914062, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -79.11776733398438, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.598302125930786}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.939117431640625, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 231.6605224609375, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -74.44581604003906, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.8571391105651855}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 9, "pred_class_confidence": 0.3040207326412201, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 68.73844146728516, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -85.6082763671875, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.4214181900024414}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.7569214701652527, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 68.45317077636719, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -84.52324676513672, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.6683239936828613}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.7044305205345154, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 300.46734619140625, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -87.06829071044922, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.5561017990112305}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 24, "pred_class_confidence": 0.14721108973026276, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 342.53143310546875, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -80.78852844238281, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.6594479084014893}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 7, "pred_class_confidence": 0.4161551892757416, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 11.495320320129395, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -83.87094116210938, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.8962950706481934}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.7438743114471436, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 283.03277587890625, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -81.62562561035156, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.974541664123535}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.3885713815689087, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 95.64908599853516, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -74.93338012695312, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 2.683534860610962}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 16, "pred_class_confidence": 0.5752855539321899, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 186.90933227539062, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -83.62947845458984, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.8299238681793213}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 37, "pred_class_confidence": 0.20526564121246338, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 94.89864349365234, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -87.67450714111328, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 2.644284248352051}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.33983269333839417, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 31.805875778198242, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -85.7658462524414, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.0280914306640625}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.3777795135974884, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 77.09150695800781, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -68.340576171875, "gt_distance_m": 4.411057949066162, "pred_distance_m": 2.470271587371826}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.4660917818546295, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 180.67041015625, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -85.90542602539062, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 2.554814100265503}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.40865519642829895, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 239.63742065429688, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -79.09771728515625, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.6256637573242188}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0014.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.7642064690589905, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 260.6844482421875, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -76.01499938964844, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.2904460430145264}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 42, "pred_class_confidence": 0.154591903090477, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 277.77899169921875, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -71.84359741210938, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.6305832862854004}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.9105119109153748, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 245.1907958984375, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -70.13159942626953, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.7070577144622803}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 9, "pred_class_confidence": 0.6446612477302551, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 97.1894302368164, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -81.90034484863281, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.8758435249328613}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.7201018929481506, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 78.19841766357422, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -85.37052154541016, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.833901882171631}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6855650544166565, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 295.3360900878906, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -87.2800521850586, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.4950592517852783}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.6449217796325684, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 19.26395034790039, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -80.71771240234375, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.1008410453796387}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.8199037909507751, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 44.67310333251953, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -73.43901824951172, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.6591827869415283}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.5964173674583435, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 356.5411376953125, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -86.0228500366211, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.92854642868042}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.4534422755241394, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 107.8329849243164, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -72.3077392578125, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.0134739875793457}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 16, "pred_class_confidence": 0.4210413098335266, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 194.43946838378906, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -83.9148178100586, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.9055354595184326}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 37, "pred_class_confidence": 0.1670485883951187, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 126.13523864746094, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -85.77909851074219, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 2.986208915710449}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.38585248589515686, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 70.52135467529297, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -85.63843536376953, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.2437386512756348}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.4657115042209625, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 74.21121215820312, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -65.38619995117188, "gt_distance_m": 4.411057949066162, "pred_distance_m": 2.8913309574127197}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.7741203308105469, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 192.85276794433594, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -82.27735137939453, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 3.0175204277038574}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.3185535967350006, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 255.25442504882812, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -77.51525115966797, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.684795379638672}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0015.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.935371994972229, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 249.87701416015625, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -73.1537094116211, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.2326433658599854}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.35750874876976013, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 280.35565185546875, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -80.57600402832031, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.2031776905059814}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.9194071292877197, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 233.72189331054688, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -65.78141021728516, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.732999563217163}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 9, "pred_class_confidence": 0.25996577739715576, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 78.5697250366211, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -76.33279418945312, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.5682408809661865}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.5489257574081421, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 330.3706970214844, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -86.89618682861328, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.805612325668335}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.640823245048523, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 75.1759262084961, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -88.0485610961914, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.4786107540130615}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 15, "pred_class_confidence": 0.3979576528072357, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 65.78152465820312, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -83.29228973388672, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.259308338165283}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 7, "pred_class_confidence": 0.42224541306495667, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 57.413272857666016, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -77.92771911621094, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.869140386581421}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.7894004583358765, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 328.7229919433594, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -85.03706359863281, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.977057695388794}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.37069931626319885, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 81.68990325927734, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -80.78535461425781, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.027292013168335}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 16, "pred_class_confidence": 0.4133683145046234, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 164.3036651611328, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -77.53484344482422, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.752948760986328}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 52, "pred_class_confidence": 0.18339847028255463, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 24.224754333496094, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -87.14686584472656, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 2.5035738945007324}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.29227715730667114, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 5.90382194519043, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -84.3819351196289, "gt_distance_m": 3.011542320251465, "pred_distance_m": 2.875514507293701}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.3651955723762512, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 58.32782745361328, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -70.0054702758789, "gt_distance_m": 4.411057949066162, "pred_distance_m": 3.0906035900115967}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.9049709439277649, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 296.2337646484375, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -81.99364471435547, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 2.74263596534729}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.3572750985622406, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 259.1252136230469, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -79.85494995117188, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.667048215866089}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0016.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.6870229840278625, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 288.9107971191406, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -62.578487396240234, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.2649600505828857}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 37, "pred_class_confidence": 0.21585595607757568, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 270.1251525878906, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -79.58318328857422, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.6539034843444824}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.9696488976478577, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 229.77935791015625, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -51.68230056762695, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.7586867809295654}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.492540568113327, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 68.98031616210938, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -72.4598159790039, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.0346486568450928}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.7814188599586487, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 103.15850830078125, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -76.74408721923828, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.6841506958007812}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.34475451707839966, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 297.14239501953125, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -87.50856018066406, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.3265597820281982}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 15, "pred_class_confidence": 0.3326573371887207, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 13.292381286621094, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -74.67144775390625, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.734318494796753}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 7, "pred_class_confidence": 0.389891117811203, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 37.458309173583984, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -72.83541870117188, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.9560441970825195}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.6786559224128723, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 311.3352355957031, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -83.79948425292969, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.9311697483062744}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.4043326675891876, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 103.46244812011719, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -63.797882080078125, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 2.748589038848877}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 32, "pred_class_confidence": 0.5693807005882263, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 86.6815185546875, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -86.05821990966797, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 3.0361006259918213}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 37, "pred_class_confidence": 0.18240956962108612, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 104.9292221069336, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -83.93314361572266, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 2.763148069381714}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.37305229902267456, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 73.93179321289062, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -83.84202575683594, "gt_distance_m": 3.011542320251465, "pred_distance_m": 2.789419174194336}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.22087383270263672, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 61.803733825683594, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -67.46341705322266, "gt_distance_m": 4.411057949066162, "pred_distance_m": 2.8193647861480713}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.8865721225738525, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 0.2510325312614441, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -84.74498748779297, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 2.872586250305176}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 14, "pred_class_confidence": 0.27064263820648193, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 266.7212829589844, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -77.20401763916016, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.935642719268799}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0017.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.9813717603683472, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 264.82818603515625, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -74.82501220703125, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.201674461364746}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 37, "pred_class_confidence": 0.473833829164505, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 222.47781372070312, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -69.46961212158203, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.254633903503418}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.9809846878051758, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 247.36859130859375, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -66.25328063964844, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.7040464878082275}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.37643855810165405, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 104.71451568603516, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -72.53073120117188, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.164328098297119}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.7050652503967285, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 144.52401733398438, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -83.86272430419922, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.9263031482696533}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6423827409744263, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 129.09295654296875, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -88.79569244384766, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.5283591747283936}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.1683296412229538, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 310.2166748046875, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -78.05006408691406, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.9644579887390137}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.48028242588043213, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 272.29107666015625, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -85.32471466064453, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.8911795616149902}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.6201068162918091, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 237.57672119140625, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -74.77362060546875, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.943354606628418}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.3917064070701599, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 127.73165893554688, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -79.80321502685547, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 2.8842525482177734}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 32, "pred_class_confidence": 0.38331034779548645, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 180.1895751953125, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -82.4954833984375, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 3.008944511413574}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 25, "pred_class_confidence": 0.14374634623527527, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 179.72735595703125, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -84.48213958740234, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 2.7772936820983887}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.3342735469341278, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 199.19317626953125, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -87.4935302734375, "gt_distance_m": 3.011542320251465, "pred_distance_m": 2.8646163940429688}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.35549163818359375, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 53.31925582885742, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -64.23371887207031, "gt_distance_m": 4.411057949066162, "pred_distance_m": 2.6492557525634766}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.35377880930900574, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 137.818359375, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -87.9040756225586, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 2.9907424449920654}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 16, "pred_class_confidence": 0.45133593678474426, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 269.6962585449219, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -70.66155242919922, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.8587098121643066}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0018.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.981025755405426, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 276.57000732421875, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -54.353084564208984, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.3758366107940674}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 37, "pred_class_confidence": 0.28410643339157104, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 242.49530029296875, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -77.13082885742188, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.419739007949829}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.9794082045555115, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 241.7017059326172, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -42.97001266479492, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.5652565956115723}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.6890814304351807, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 87.87628936767578, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -66.25083923339844, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.499073028564453}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.7125383019447327, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 198.96337890625, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -85.48321533203125, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.002502918243408}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.8159837126731873, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 12.072216987609863, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -80.97539520263672, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.5677647590637207}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 15, "pred_class_confidence": 0.5494944453239441, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 355.72308349609375, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -77.07222747802734, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.484623432159424}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.7736749649047852, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 24.309999465942383, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -72.86174011230469, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.982614517211914}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.5026773810386658, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 273.7975158691406, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -71.48839569091797, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 3.3327784538269043}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.3726899325847626, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 123.05218505859375, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -82.46016693115234, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 3.1891942024230957}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 16, "pred_class_confidence": 0.47587156295776367, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 117.71363830566406, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -77.5071029663086, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.964123249053955}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 9, "pred_class_confidence": 0.1895899623632431, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 147.38916015625, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -87.72996520996094, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 2.8673672676086426}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.4912422001361847, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 211.9219512939453, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -87.123291015625, "gt_distance_m": 3.011542320251465, "pred_distance_m": 3.249305248260498}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 25, "pred_class_confidence": 0.4687129557132721, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 65.6940689086914, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -65.79135131835938, "gt_distance_m": 4.411057949066162, "pred_distance_m": 3.0628764629364014}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.7201340794563293, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 205.10760498046875, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -80.8045883178711, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 3.065894603729248}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 5, "pred_class_confidence": 0.2972683012485504, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 271.779052734375, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -73.47648620605469, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 3.086118221282959}

checkpoints/spatial_beats_ov1_ast_run1/val_predictions/epoch_0019.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 41, "pred_class_confidence": 0.9393150806427002, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 305.616455078125, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -45.84992218017578, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.0432474613189697}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 13, "pred_class_confidence": 0.20651525259017944, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 190.7899932861328, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -80.94193267822266, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.739271640777588}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 41, "pred_class_confidence": 0.9441160559654236, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 266.5236511230469, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -49.47288513183594, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.2778379917144775}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.7085686326026917, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 103.98422241210938, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -67.96978759765625, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.1399343013763428}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 25, "pred_class_confidence": 0.4921712875366211, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 239.73951721191406, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -30.538482666015625, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.6133103370666504}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6889459490776062, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 333.63604736328125, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -74.96875762939453, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.3844034671783447}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 15, "pred_class_confidence": 0.42247629165649414, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 79.73149108886719, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -78.82197570800781, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.2353568077087402}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.5577388405799866, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 49.60295104980469, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -69.49465942382812, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.3403067588806152}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.6990635395050049, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 294.7301025390625, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -57.87156677246094, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.8565914630889893}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.7584629654884338, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 174.0705108642578, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -68.63327026367188, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 2.6880550384521484}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 16, "pred_class_confidence": 0.5534400939941406, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 282.74542236328125, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -85.68952178955078, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.7223587036132812}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 37, "pred_class_confidence": 0.1927434802055359, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 232.97079467773438, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -83.13395690917969, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 2.660010814666748}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 11, "pred_class_confidence": 0.8118007183074951, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 255.653076171875, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -79.43740844726562, "gt_distance_m": 3.011542320251465, "pred_distance_m": 2.6902263164520264}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 39, "pred_class_confidence": 0.21950963139533997, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 64.9007339477539, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -70.67786407470703, "gt_distance_m": 4.411057949066162, "pred_distance_m": 3.054412364959717}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 21, "pred_class_confidence": 0.7858917117118835, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 182.63958740234375, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -73.98565673828125, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 2.4054927825927734}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 18, "pred_class_confidence": 0.32466140389442444, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 313.34283447265625, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -77.15978240966797, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 2.364305257797241}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/01_classwarmup/val_predictions/epoch_0000.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 0, "pred_class_confidence": 0.2077757865190506, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 192.44448852539062, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -86.03987884521484, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.0518717765808105}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 10, "pred_class_confidence": 0.12086521834135056, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 108.92499542236328, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -88.30349731445312, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 2.8589746952056885}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 10, "pred_class_confidence": 0.10091246664524078, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 89.66616821289062, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -88.81534576416016, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.127668619155884}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 1, "pred_class_confidence": 0.43400099873542786, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 226.40606689453125, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -85.89301300048828, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 3.1747074127197266}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 0, "pred_class_confidence": 0.31413963437080383, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 197.0107879638672, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -85.80571746826172, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 3.096667528152466}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.11565279215574265, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 109.82015228271484, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -87.61468505859375, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.667060375213623}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 10, "pred_class_confidence": 0.07322967052459717, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 101.57374572753906, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -87.96337127685547, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.7592406272888184}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.34571388363838196, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 145.54588317871094, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -87.02671813964844, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 2.757969617843628}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.2660254240036011, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 129.4569549560547, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -87.53629302978516, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.7276036739349365}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 19, "pred_class_confidence": 0.13068938255310059, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 100.9592056274414, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -88.59069061279297, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 2.991366147994995}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6693540215492249, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 236.212890625, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -84.22433471679688, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 3.2857251167297363}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.15414457023143768, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 115.81018829345703, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -87.6248779296875, "gt_distance_m": 1.098374366760254, "pred_distance_m": 2.6933445930480957}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.24433784186840057, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 106.19481658935547, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -87.7940673828125, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.7553696632385254}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 4, "pred_class_confidence": 0.11063014715909958, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 103.3110580444336, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -87.86540222167969, "gt_distance_m": 5.218364715576172, "pred_distance_m": 2.7583162784576416}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5732210874557495, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 234.5303497314453, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -86.29492950439453, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.1443042755126953}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 2, "pred_class_confidence": 0.1839522123336792, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 149.18309020996094, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -86.9720458984375, "gt_distance_m": 4.348083972930908, "pred_distance_m": 2.759096384048462}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/01_classwarmup/val_predictions/epoch_0001.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.4177500307559967, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 184.3673553466797, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -87.85296630859375, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.891463041305542}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 10, "pred_class_confidence": 0.2795671224594116, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 134.08096313476562, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -86.14460754394531, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 3.1065101623535156}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 11, "pred_class_confidence": 0.1376088708639145, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 117.12095642089844, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -86.87744903564453, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.148261785507202}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 1, "pred_class_confidence": 0.308562695980072, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 308.3176574707031, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -87.42192077636719, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 3.1283979415893555}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 0, "pred_class_confidence": 0.6926404237747192, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 302.29296875, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -88.0069808959961, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 3.059555768966675}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 14, "pred_class_confidence": 0.25341516733169556, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 77.3510513305664, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -88.392822265625, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.9737191200256348}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 13, "pred_class_confidence": 0.11881102621555328, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 87.64878845214844, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -87.36738586425781, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.98083233833313}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.1379299759864807, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 146.71006774902344, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -88.21490478515625, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 2.961111068725586}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.33074837923049927, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 111.45413970947266, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -87.23954772949219, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.9813976287841797}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 29, "pred_class_confidence": 0.39012768864631653, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 133.0031280517578, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -85.72103118896484, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 3.2216248512268066}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.9568278193473816, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 319.0404052734375, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -87.41282653808594, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.9880995750427246}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 14, "pred_class_confidence": 0.2732696533203125, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 88.36222839355469, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -88.49897003173828, "gt_distance_m": 1.098374366760254, "pred_distance_m": 2.9637985229492188}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.1769534796476364, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 83.94258117675781, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -86.38615417480469, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.9686572551727295}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 13, "pred_class_confidence": 0.1977066993713379, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 71.35364532470703, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -87.52796936035156, "gt_distance_m": 5.218364715576172, "pred_distance_m": 3.0273427963256836}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6663969159126282, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 347.6366271972656, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -85.54464721679688, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.9687070846557617}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.27746742963790894, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 202.12132263183594, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -88.0594253540039, "gt_distance_m": 4.348083972930908, "pred_distance_m": 2.9808380603790283}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/01_classwarmup/val_predictions/epoch_0002.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 1, "pred_class_confidence": 0.2427753210067749, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 139.61129760742188, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -88.83365631103516, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.8199658393859863}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 19, "pred_class_confidence": 0.3443748652935028, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 111.70709228515625, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -87.76620483398438, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 3.022665023803711}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.17368079721927643, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 308.24847412109375, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -88.09556579589844, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.1317636966705322}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 7, "pred_class_confidence": 0.36938950419425964, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 348.90057373046875, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -88.89730072021484, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 2.9491686820983887}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 0, "pred_class_confidence": 0.3075474500656128, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 47.87802505493164, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -89.53648376464844, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.8624613285064697}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 31, "pred_class_confidence": 0.19187873601913452, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 68.68067932128906, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -86.33056640625, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.690669059753418}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.08145652711391449, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 70.8620834350586, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -86.27179718017578, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.7665913105010986}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.2666194438934326, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 82.3283920288086, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -87.23473358154297, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 2.7373712062835693}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.2809225022792816, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 80.93574523925781, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -86.71610260009766, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.773493528366089}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 29, "pred_class_confidence": 0.3174387514591217, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 114.45384979248047, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -88.80744934082031, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 3.314821481704712}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.895871639251709, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 351.6354675292969, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -88.13912200927734, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.8705556392669678}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 16, "pred_class_confidence": 0.16645638644695282, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 70.4442138671875, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -86.44097137451172, "gt_distance_m": 1.098374366760254, "pred_distance_m": 2.6703221797943115}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.3287329077720642, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 72.02784729003906, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -86.14562225341797, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.707756996154785}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 31, "pred_class_confidence": 0.17474476993083954, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 65.6029281616211, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -86.13001251220703, "gt_distance_m": 5.218364715576172, "pred_distance_m": 2.728984832763672}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5587161779403687, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 2.3774831295013428, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -88.32859802246094, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.8327295780181885}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.25528740882873535, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 93.81526184082031, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -88.60184478759766, "gt_distance_m": 4.348083972930908, "pred_distance_m": 2.8289268016815186}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/01_classwarmup/val_predictions/epoch_0003.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.4167589247226715, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 238.03680419921875, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -86.08768463134766, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.993767738342285}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 22, "pred_class_confidence": 0.22137965261936188, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 210.616455078125, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -86.68412780761719, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 2.751842498779297}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.31648996472358704, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 237.18655395507812, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -85.50794982910156, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.215711832046509}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 0, "pred_class_confidence": 0.2858690619468689, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 302.51513671875, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -85.2462158203125, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 2.8704137802124023}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 0, "pred_class_confidence": 0.5451273918151855, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 264.1223449707031, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -86.0114974975586, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.9368703365325928}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 31, "pred_class_confidence": 0.2003985345363617, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 23.01184844970703, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -89.02021026611328, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.8734130859375}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.1548069715499878, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 211.94459533691406, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -89.15558624267578, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.8608827590942383}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 7, "pred_class_confidence": 0.1991136521100998, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 208.28627014160156, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -87.21322631835938, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 3.0488672256469727}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 2, "pred_class_confidence": 0.12861770391464233, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 58.69031524658203, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -89.74666595458984, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.743166923522949}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 29, "pred_class_confidence": 0.41096657514572144, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 218.08058166503906, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -84.40052795410156, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 3.130765676498413}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.9948645234107971, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 309.23046875, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -84.05370330810547, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.7646780014038086}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 16, "pred_class_confidence": 0.19611534476280212, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 37.85841751098633, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -89.18482971191406, "gt_distance_m": 1.098374366760254, "pred_distance_m": 2.849940776824951}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.4691546559333801, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 102.8917007446289, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -88.95995330810547, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.8742117881774902}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 13, "pred_class_confidence": 0.1909533143043518, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 18.306135177612305, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -89.29169464111328, "gt_distance_m": 5.218364715576172, "pred_distance_m": 2.9930331707000732}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6247293949127197, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 288.93206787109375, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -85.79774475097656, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.854142665863037}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.3993346095085144, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 243.15682983398438, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -86.51081085205078, "gt_distance_m": 4.348083972930908, "pred_distance_m": 3.095303535461426}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/01_classwarmup/val_predictions/epoch_0004.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.5982263684272766, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 196.22720336914062, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -84.29020690917969, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.725231885910034}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 10, "pred_class_confidence": 0.3148449957370758, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 162.29417419433594, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -84.57819366455078, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 2.6344478130340576}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.23718437552452087, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 245.59756469726562, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -85.72108459472656, "gt_distance_m": 4.594465255737305, "pred_distance_m": 2.973532199859619}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 1, "pred_class_confidence": 0.4853203594684601, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 279.47210693359375, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -87.64058685302734, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 2.8089964389801025}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 7, "pred_class_confidence": 0.3994365632534027, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 201.2781524658203, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -85.03974914550781, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.7228434085845947}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 16, "pred_class_confidence": 0.1628076732158661, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 65.5665054321289, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -87.56417846679688, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.8246657848358154}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.12516184151172638, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 131.82626342773438, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -88.7774658203125, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.7980117797851562}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.21248437464237213, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 132.29177856445312, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -85.84974670410156, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 2.732487440109253}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 2, "pred_class_confidence": 0.11116882413625717, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 80.14898681640625, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -87.85050964355469, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.772075891494751}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 29, "pred_class_confidence": 0.43316715955734253, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 190.7914276123047, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -84.23027801513672, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 3.0269479751586914}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.985831081867218, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 278.9244384765625, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -87.2520523071289, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.8468236923217773}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 16, "pred_class_confidence": 0.20104925334453583, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 73.96753692626953, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -87.43409729003906, "gt_distance_m": 1.098374366760254, "pred_distance_m": 2.819049119949341}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.3390546441078186, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 100.53083038330078, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -86.00227355957031, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 2.8597917556762695}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 5, "pred_class_confidence": 0.20329782366752625, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 75.97219848632812, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -88.0588150024414, "gt_distance_m": 5.218364715576172, "pred_distance_m": 2.7116024494171143}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.8498138189315796, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 268.6129150390625, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -86.6956558227539, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.756209135055542}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.2148284614086151, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 196.38186645507812, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -84.93798065185547, "gt_distance_m": 4.348083972930908, "pred_distance_m": 2.8351078033447266}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/01_classwarmup/val_predictions/epoch_0005.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.43760034441947937, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 189.6923065185547, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -87.78565979003906, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.023519277572632}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 19, "pred_class_confidence": 0.3441677391529083, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 159.91514587402344, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -85.80511474609375, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 2.680398941040039}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 12, "pred_class_confidence": 0.17284594476222992, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 246.62957763671875, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -84.0813217163086, "gt_distance_m": 4.594465255737305, "pred_distance_m": 2.8241724967956543}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.435116171836853, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 62.0299072265625, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -88.44972229003906, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 3.0021331310272217}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 7, "pred_class_confidence": 0.2785252034664154, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 188.2601318359375, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -88.03546905517578, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 3.030820608139038}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 16, "pred_class_confidence": 0.17403680086135864, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 55.740779876708984, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -88.14027404785156, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.901122570037842}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.23171547055244446, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 12.365338325500488, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -89.61589050292969, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.015955924987793}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.38514670729637146, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 115.0447006225586, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -83.41983032226562, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 2.767425537109375}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.3539946675300598, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 125.47000122070312, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -87.19613647460938, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.7337229251861572}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 19, "pred_class_confidence": 0.29915833473205566, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 171.89334106445312, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -85.24099731445312, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 2.806993007659912}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.9840133786201477, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 332.64678955078125, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -89.40422821044922, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.9726078510284424}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 16, "pred_class_confidence": 0.1844460517168045, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 71.28897857666016, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -87.72901153564453, "gt_distance_m": 1.098374366760254, "pred_distance_m": 2.8135650157928467}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.4148012101650238, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 119.97582244873047, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -81.48790740966797, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 3.325394868850708}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 13, "pred_class_confidence": 0.15591081976890564, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 61.22260665893555, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -89.00751495361328, "gt_distance_m": 5.218364715576172, "pred_distance_m": 2.9384849071502686}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5746760368347168, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 196.4139404296875, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -89.60435485839844, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.002817392349243}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6380756497383118, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 187.15115356445312, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -88.36589813232422, "gt_distance_m": 4.348083972930908, "pred_distance_m": 3.1111581325531006}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/01_classwarmup/val_predictions/epoch_0006.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.7973992824554443, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 211.7518768310547, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -86.11213684082031, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.9791691303253174}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 10, "pred_class_confidence": 0.2492295503616333, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 172.16070556640625, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -86.0189208984375, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 3.100552797317505}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.2193998098373413, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 216.8191375732422, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -83.68592834472656, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.408409595489502}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.6051347851753235, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 279.73419189453125, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -87.49555969238281, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 3.0806121826171875}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 7, "pred_class_confidence": 0.6702505350112915, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 229.7716827392578, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -87.0943832397461, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.9981448650360107}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 2, "pred_class_confidence": 0.15867289900779724, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 112.7530746459961, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -88.72175598144531, "gt_distance_m": 2.184462070465088, "pred_distance_m": 3.1930959224700928}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.2717592418193817, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 204.24160766601562, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -88.40811920166016, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.2333269119262695}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.6704449653625488, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 173.4195098876953, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -83.76068115234375, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 3.0492193698883057}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 2, "pred_class_confidence": 0.4330315887928009, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 146.1498260498047, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -85.76580047607422, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.8881638050079346}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 10, "pred_class_confidence": 0.311931312084198, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 183.82496643066406, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -84.89500427246094, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 3.2574503421783447}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.9928832054138184, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 305.28399658203125, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -87.42686462402344, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 3.0565452575683594}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.2600213885307312, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 119.96648406982422, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -87.86714172363281, "gt_distance_m": 1.098374366760254, "pred_distance_m": 3.0879595279693604}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.6720613837242126, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 144.4062042236328, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -86.77717590332031, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 3.7469677925109863}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 13, "pred_class_confidence": 0.29845625162124634, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 124.51685333251953, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -88.72113800048828, "gt_distance_m": 5.218364715576172, "pred_distance_m": 3.238253593444824}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.579326868057251, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 267.8050842285156, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -87.34597778320312, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.042428731918335}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 7, "pred_class_confidence": 0.6569686532020569, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 209.80941772460938, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -85.66993713378906, "gt_distance_m": 4.348083972930908, "pred_distance_m": 3.028733730316162}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/01_classwarmup/val_predictions/epoch_0007.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.7820585370063782, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 237.69241333007812, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -87.43120574951172, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.6781880855560303}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 22, "pred_class_confidence": 0.3241922855377197, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 142.78109741210938, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -87.41252136230469, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 2.8254587650299072}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 9, "pred_class_confidence": 0.21934731304645538, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 235.92857360839844, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -86.58161163330078, "gt_distance_m": 4.594465255737305, "pred_distance_m": 2.9227917194366455}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.5385294556617737, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 284.747802734375, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -86.95053100585938, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 2.7729432582855225}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 7, "pred_class_confidence": 0.7740986943244934, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 273.8326721191406, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -87.32291412353516, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.6689422130584717}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 16, "pred_class_confidence": 0.14706669747829437, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 46.37238311767578, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -88.6803207397461, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.970524311065674}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.3174057602882385, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 333.65386962890625, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -89.71332550048828, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.756760358810425}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.6349827647209167, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 135.548828125, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -80.68124389648438, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 2.799286127090454}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 2, "pred_class_confidence": 0.5726048946380615, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 136.22671508789062, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -82.99198150634766, "gt_distance_m": 2.820817708969116, "pred_distance_m": 2.769343137741089}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 19, "pred_class_confidence": 0.3055132329463959, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 164.13034057617188, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -85.39057159423828, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 2.9067046642303467}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.9945893287658691, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 319.99249267578125, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -85.98511505126953, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.9897477626800537}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 14, "pred_class_confidence": 0.15290123224258423, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 77.0268783569336, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -89.22924041748047, "gt_distance_m": 1.098374366760254, "pred_distance_m": 3.0005667209625244}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.6288846731185913, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 131.86985778808594, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -85.84744262695312, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 3.172532081604004}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 13, "pred_class_confidence": 0.28499507904052734, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 68.90787506103516, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -88.93485260009766, "gt_distance_m": 5.218364715576172, "pred_distance_m": 2.81485915184021}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 1, "pred_class_confidence": 0.5121561884880066, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 287.36993408203125, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -85.74549865722656, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.8419113159179688}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 2, "pred_class_confidence": 0.3681410551071167, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 228.06275939941406, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -85.93707275390625, "gt_distance_m": 4.348083972930908, "pred_distance_m": 2.8297221660614014}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/02_spatialfirst/val_predictions/epoch_0000.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 2, "pred_class_confidence": 0.1842181533575058, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 242.2880859375, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -87.18965148925781, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.0027222633361816}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 7, "pred_class_confidence": 0.17907750606536865, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 266.39422607421875, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -87.17305755615234, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 1.6579458713531494}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 10, "pred_class_confidence": 0.07382023334503174, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 158.7823944091797, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -87.1989974975586, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.109580993652344}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.38836464285850525, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 163.77505493164062, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -84.98702239990234, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.101230144500732}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 0, "pred_class_confidence": 0.24564765393733978, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 187.7404022216797, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -86.56726837158203, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.211400032043457}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.21665379405021667, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 215.1326904296875, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -86.44636535644531, "gt_distance_m": 2.184462070465088, "pred_distance_m": 1.8882602453231812}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 6, "pred_class_confidence": 0.06643790006637573, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 207.71006774902344, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -88.09217834472656, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.4589364528656006}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.17496709525585175, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 138.178955078125, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -87.24132537841797, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 4.19605827331543}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.4197176694869995, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 162.9755096435547, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -83.69351196289062, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.2167186737060547}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 29, "pred_class_confidence": 0.16639043390750885, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 278.5922546386719, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -87.02448272705078, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.4726388454437256}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5537721514701843, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 255.37655639648438, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -85.69075012207031, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 1.9814658164978027}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.31322580575942993, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 239.4549560546875, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -86.63256072998047, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.6517294645309448}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.6351975202560425, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 254.5460968017578, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -87.26598358154297, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.6430332660675049}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 13, "pred_class_confidence": 0.1008089929819107, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 129.087890625, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -87.3441390991211, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.002801895141602}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.3341854512691498, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 186.7333221435547, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -86.19502258300781, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 4.144696235656738}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.7998284697532654, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 195.0401153564453, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -86.78028106689453, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.132260322570801}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/02_spatialfirst/val_predictions/epoch_0001.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 1, "pred_class_confidence": 0.23604774475097656, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 290.2876892089844, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -89.20919799804688, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 1.5677040815353394}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 7, "pred_class_confidence": 0.2399582713842392, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 171.3031768798828, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -89.53732299804688, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 1.5048867464065552}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.1377362459897995, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 210.5475311279297, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -88.45832824707031, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.076488494873047}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.4638460874557495, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 242.27078247070312, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -89.0857162475586, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.156817436218262}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 7, "pred_class_confidence": 0.27235421538352966, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 247.12249755859375, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -87.81251525878906, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.1668782234191895}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 16, "pred_class_confidence": 0.12200619280338287, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 87.5782699584961, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -87.94385528564453, "gt_distance_m": 2.184462070465088, "pred_distance_m": 1.5681365728378296}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 6, "pred_class_confidence": 0.07778424769639969, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 224.93153381347656, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -88.73050689697266, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.878324031829834}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.30701249837875366, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 134.2526397705078, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -88.58087158203125, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 4.203412055969238}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 6, "pred_class_confidence": 0.11630166321992874, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 91.116943359375, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -89.25558471679688, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.4734909534454346}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 7, "pred_class_confidence": 0.24852925539016724, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 122.05976867675781, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -88.72789764404297, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.3890657424926758}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6930921673774719, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 344.87261962890625, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -88.48819732666016, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 1.4302438497543335}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.23693248629570007, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 103.85223388671875, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -86.78435516357422, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.3506407737731934}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.20689240097999573, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 111.69815826416016, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -85.50376892089844, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.280545949935913}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 13, "pred_class_confidence": 0.10134036839008331, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 30.440837860107422, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -89.44046783447266, "gt_distance_m": 5.218364715576172, "pred_distance_m": 3.5440664291381836}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.3863019645214081, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 236.61788940429688, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -87.99874877929688, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 4.174871921539307}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.90957111120224, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 255.87509155273438, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -88.29302978515625, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.141119480133057}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/02_spatialfirst/val_predictions/epoch_0002.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 0, "pred_class_confidence": 0.6154087781906128, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 339.8513488769531, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -82.1708755493164, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 1.6180689334869385}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 1, "pred_class_confidence": 0.23723044991493225, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 336.7609558105469, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -87.10025024414062, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 1.567537784576416}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.1292053610086441, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 206.4298553466797, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -87.69208526611328, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.948810338973999}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.6370878219604492, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 131.3355712890625, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -88.18856811523438, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 3.83034610748291}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 7, "pred_class_confidence": 0.23559090495109558, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 193.63893127441406, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -88.62869262695312, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 3.9984545707702637}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 0, "pred_class_confidence": 0.18883374333381653, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 10.331754684448242, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -86.6597671508789, "gt_distance_m": 2.184462070465088, "pred_distance_m": 1.2551906108856201}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 17, "pred_class_confidence": 0.1143765076994896, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 240.3717498779297, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -89.56976318359375, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.637484312057495}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.25647109746932983, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 105.65584564208984, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -85.03671264648438, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 4.110285758972168}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.395953893661499, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 110.42460632324219, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -85.32982635498047, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.252749443054199}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 1, "pred_class_confidence": 0.22794084250926971, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 347.5928955078125, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -87.5119400024414, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.4344736337661743}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.8146648406982422, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 337.9477844238281, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -81.46919250488281, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 1.6759634017944336}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 7, "pred_class_confidence": 0.2817837595939636, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 8.807220458984375, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -86.21400451660156, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.227555513381958}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.17470847070217133, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 47.45779800415039, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -86.92604064941406, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.2161848545074463}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 3, "pred_class_confidence": 0.08124850690364838, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 51.35554504394531, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -87.57844543457031, "gt_distance_m": 5.218364715576172, "pred_distance_m": 3.734299421310425}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 7, "pred_class_confidence": 0.3032054603099823, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 182.6240997314453, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -89.04632568359375, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.8028793334960938}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.7256353497505188, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 182.890869140625, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -88.73035430908203, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.064864158630371}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/02_spatialfirst/val_predictions/epoch_0003.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 0, "pred_class_confidence": 0.7265748977661133, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 325.0418395996094, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -81.45368957519531, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 1.5435583591461182}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 20, "pred_class_confidence": 0.13446912169456482, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 285.33154296875, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -87.32036590576172, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 1.4416807889938354}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.1241818219423294, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 123.1075210571289, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -88.53406524658203, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.151132106781006}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.491653174161911, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 127.34757995605469, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -87.28804779052734, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.026843070983887}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 7, "pred_class_confidence": 0.24640792608261108, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 152.802978515625, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -88.1434326171875, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.203063488006592}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 16, "pred_class_confidence": 0.14447517693042755, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 316.45916748046875, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -88.12079620361328, "gt_distance_m": 2.184462070465088, "pred_distance_m": 1.256854772567749}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 14, "pred_class_confidence": 0.15916799008846283, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 228.0225067138672, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -88.14807891845703, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.8617076873779297}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.30303502082824707, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 116.41097259521484, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -84.43577575683594, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 4.021000385284424}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 4, "pred_class_confidence": 0.3374704420566559, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 148.51300048828125, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -88.00139617919922, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.324589967727661}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 28, "pred_class_confidence": 0.13778097927570343, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 277.2407531738281, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -88.34188079833984, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.2546195983886719}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.9165917038917542, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 323.5370178222656, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -82.02760314941406, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 1.453973650932312}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 0, "pred_class_confidence": 0.11296730488538742, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 326.32891845703125, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -88.97587585449219, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.1206188201904297}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.23866526782512665, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 309.8128356933594, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -89.7788314819336, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.086606502532959}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 13, "pred_class_confidence": 0.09926322102546692, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 162.1435546875, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -89.05561065673828, "gt_distance_m": 5.218364715576172, "pred_distance_m": 3.9057719707489014}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 1, "pred_class_confidence": 0.3207423686981201, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 141.40084838867188, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -88.49949645996094, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 4.050907135009766}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6484941840171814, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 175.71815490722656, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -88.45098114013672, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.1194844245910645}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/02_spatialfirst/val_predictions/epoch_0004.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 0, "pred_class_confidence": 0.3362879157066345, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 348.50494384765625, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -85.35746002197266, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 1.9219107627868652}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 23, "pred_class_confidence": 0.0723949745297432, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 305.7777404785156, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -88.91537475585938, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 1.886937141418457}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 8, "pred_class_confidence": 0.12280303984880447, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 82.73833465576172, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -83.60999298095703, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.309861183166504}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.4078243374824524, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 107.46949005126953, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -83.25415802001953, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.046388626098633}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 0, "pred_class_confidence": 0.37625107169151306, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 88.80558776855469, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -86.70045471191406, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.07476282119751}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.3122151494026184, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 359.7106628417969, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -86.53101348876953, "gt_distance_m": 2.184462070465088, "pred_distance_m": 1.8012553453445435}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.11233662068843842, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 328.52642822265625, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -89.46331787109375, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.663923740386963}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 7, "pred_class_confidence": 0.37322068214416504, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 108.86420440673828, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -81.533203125, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 4.064419746398926}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 4, "pred_class_confidence": 0.3545735776424408, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 149.4806365966797, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -88.21996307373047, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.3888802528381348}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 10, "pred_class_confidence": 0.082695871591568, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 173.2398681640625, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -85.03682708740234, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.3753101825714111}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.8810299038887024, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 336.4554443359375, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -80.20064544677734, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 1.4835453033447266}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.282911092042923, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 63.222049713134766, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -88.41143798828125, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.222899317741394}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.2515726685523987, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 131.95726013183594, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -87.63569641113281, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.1826128959655762}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 13, "pred_class_confidence": 0.11708520352840424, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 84.36300659179688, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -86.81986236572266, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.0561137199401855}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 7, "pred_class_confidence": 0.4017229378223419, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 106.38560485839844, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -84.4130630493164, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 4.089489936828613}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.7544826865196228, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 81.36842346191406, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -86.61962890625, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.07277774810791}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/02_spatialfirst/val_predictions/epoch_0005.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 1, "pred_class_confidence": 0.30733999609947205, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 27.2742919921875, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -68.56988525390625, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.983203411102295}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 23, "pred_class_confidence": 0.06535225361585617, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 13.621317863464355, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -73.99421691894531, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 1.6599960327148438}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.146770179271698, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 171.03102111816406, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -78.69329833984375, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.214133262634277}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.4220227301120758, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 50.93333053588867, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -72.16019439697266, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.029428958892822}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 19, "pred_class_confidence": 0.07747285068035126, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 48.189964294433594, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -70.71077728271484, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.101426124572754}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.32930898666381836, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 17.3682804107666, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -73.63523864746094, "gt_distance_m": 2.184462070465088, "pred_distance_m": 1.7781744003295898}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.23990768194198608, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 34.72922134399414, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -77.7436752319336, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.6741204261779785}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.2950180172920227, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 56.286678314208984, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -72.94683837890625, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 4.032769680023193}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 2, "pred_class_confidence": 0.2938154935836792, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 54.86298751831055, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -71.95001983642578, "gt_distance_m": 2.820817708969116, "pred_distance_m": 4.104629039764404}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 1, "pred_class_confidence": 0.10529171675443649, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 17.767297744750977, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -80.35090637207031, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.3892574310302734}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5497933030128479, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 13.819836616516113, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -59.5242919921875, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 1.4283077716827393}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.24634838104248047, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 14.431900978088379, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -79.7176284790039, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.225313425064087}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 2, "pred_class_confidence": 0.23758246004581451, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 16.832090377807617, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -80.99066925048828, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.2367801666259766}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 3, "pred_class_confidence": 0.08070862293243408, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 214.2764434814453, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -79.2563247680664, "gt_distance_m": 5.218364715576172, "pred_distance_m": 3.8844735622406006}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.2853425145149231, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 48.202110290527344, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -73.0481185913086, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.8571372032165527}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5100939869880676, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 44.34428024291992, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -69.45442199707031, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.116118431091309}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/02_spatialfirst/val_predictions/epoch_0006.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.2891608774662018, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 19.859954833984375, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -28.472009658813477, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 1.6670606136322021}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 10, "pred_class_confidence": 0.06680840253829956, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 18.9505615234375, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -27.357851028442383, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 1.5062495470046997}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.10437053442001343, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 215.90382385253906, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -13.725715637207031, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.0469160079956055}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 0, "pred_class_confidence": 0.08924225717782974, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 28.824058532714844, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -34.58315658569336, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 3.9442906379699707}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 22, "pred_class_confidence": 0.08321725577116013, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 35.21337127685547, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -52.71466827392578, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.0779876708984375}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.14267417788505554, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 23.2374210357666, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -20.876392364501953, "gt_distance_m": 2.184462070465088, "pred_distance_m": 1.7199467420578003}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.1844451129436493, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 20.805936813354492, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -53.05499267578125, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.4472575187683105}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 2, "pred_class_confidence": 0.3049895763397217, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 43.2120475769043, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -51.256065368652344, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 4.275245189666748}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.07173357903957367, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 28.954200744628906, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -24.557836532592773, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.826049566268921}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 0, "pred_class_confidence": 0.14470906555652618, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 19.940412521362305, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -23.596200942993164, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.52981698513031}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.40070822834968567, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 19.765642166137695, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -23.914541244506836, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 1.490602731704712}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 0, "pred_class_confidence": 0.0960691049695015, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 23.95151710510254, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -15.950019836425781, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.7573373317718506}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.3060649037361145, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 21.693561553955078, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -21.827856063842773, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.4363194704055786}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 13, "pred_class_confidence": 0.09270334243774414, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 35.61207962036133, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -38.99148941040039, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.221929550170898}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.41691854596138, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 19.248958587646484, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -29.189207077026367, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 1.5390760898590088}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 8, "pred_class_confidence": 0.06699439883232117, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 27.10343360900879, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -20.32318687438965, "gt_distance_m": 4.348083972930908, "pred_distance_m": 3.9770305156707764}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/02_spatialfirst/val_predictions/epoch_0007.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 0, "pred_class_confidence": 0.3811262249946594, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 9.91541576385498, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -31.48126792907715, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 1.4414701461791992}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 10, "pred_class_confidence": 0.07592280954122543, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 1.5317362546920776, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -53.87804412841797, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 1.6216018199920654}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.10762906819581985, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 197.42335510253906, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -22.391189575195312, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.004449367523193}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.23902618885040283, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 175.1829376220703, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -60.31757354736328, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.04435920715332}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 0, "pred_class_confidence": 0.1846790611743927, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 178.57373046875, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -39.08467102050781, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.188295841217041}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.13886617124080658, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 14.800865173339844, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -20.123441696166992, "gt_distance_m": 2.184462070465088, "pred_distance_m": 1.4907358884811401}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 0, "pred_class_confidence": 0.11610491573810577, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 2.0846314430236816, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -71.55736541748047, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.867082118988037}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.26412490010261536, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 30.068832397460938, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -34.648590087890625, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 3.7460646629333496}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.16197654604911804, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 21.219459533691406, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -27.241413116455078, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.7014834880828857}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 8, "pred_class_confidence": 0.059830911457538605, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 11.79393482208252, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -16.070451736450195, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.3791263103485107}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5110611915588379, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 16.607881546020508, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -14.34990119934082, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 1.2898790836334229}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 3, "pred_class_confidence": 0.08700252324342728, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 20.163528442382812, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -7.444327354431152, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.7124649286270142}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.22073130309581757, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 9.664789199829102, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -26.688058853149414, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.1500797271728516}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 13, "pred_class_confidence": 0.07398305088281631, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 22.852312088012695, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -16.459016799926758, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.021945953369141}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.613322913646698, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 186.1415252685547, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -62.06060791015625, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 1.647478461265564}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.11333189904689789, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 21.598115921020508, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -23.643369674682617, "gt_distance_m": 4.348083972930908, "pred_distance_m": 3.9786834716796875}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/02_spatialfirst/val_predictions/epoch_0008.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 0, "pred_class_confidence": 0.4727197289466858, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 15.81711196899414, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -40.50346755981445, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.0300846099853516}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 0, "pred_class_confidence": 0.07131000608205795, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 188.18321228027344, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -34.12173843383789, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 1.6420577764511108}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.11158869415521622, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 192.82647705078125, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -17.480077743530273, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.747472047805786}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 0, "pred_class_confidence": 0.2478265017271042, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 177.17538452148438, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -62.15421676635742, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 3.924701452255249}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 0, "pred_class_confidence": 0.08116898685693741, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 176.4780731201172, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -31.911184310913086, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.154928207397461}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.23950164020061493, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 29.64412498474121, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -32.49911117553711, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.7538979053497314}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 0, "pred_class_confidence": 0.23716244101524353, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 204.5200653076172, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -77.37539672851562, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.2816054821014404}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.18487851321697235, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 38.94072723388672, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -26.528240203857422, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 4.129016876220703}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 4, "pred_class_confidence": 0.23928318917751312, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 36.22593688964844, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -31.10800552368164, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.9436872005462646}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 2, "pred_class_confidence": 0.10804975777864456, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 13.06958293914795, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -28.685941696166992, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.5617934465408325}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.4142349064350128, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 29.08485221862793, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -21.805301666259766, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 1.8977105617523193}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 15, "pred_class_confidence": 0.09280695021152496, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 18.301603317260742, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -18.909536361694336, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.5327130556106567}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.1972472369670868, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 5.627338886260986, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -25.642333984375, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.1450921297073364}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 1, "pred_class_confidence": 0.15434810519218445, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 35.7542724609375, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -24.385103225708008, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.015671730041504}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.574513852596283, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 189.94232177734375, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -30.152263641357422, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 1.477799654006958}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.17849907279014587, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 32.42461013793945, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -24.163593292236328, "gt_distance_m": 4.348083972930908, "pred_distance_m": 3.972759962081909}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/02_spatialfirst/val_predictions/epoch_0009.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 0, "pred_class_confidence": 0.5784065127372742, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 20.24344253540039, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -37.869895935058594, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.392991065979004}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 0, "pred_class_confidence": 0.14627552032470703, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 179.76345825195312, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -38.72079086303711, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 2.397534132003784}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 6, "pred_class_confidence": 0.09101244807243347, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 198.7750701904297, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -17.385089874267578, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.9982006549835205}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 0, "pred_class_confidence": 0.22538436949253082, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 27.805240631103516, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -76.04486083984375, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.0056843757629395}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 10, "pred_class_confidence": 0.09721050411462784, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 156.7548065185547, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -46.42653274536133, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.294397830963135}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 4, "pred_class_confidence": 0.23808781802654266, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 26.05145835876465, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -21.10895347595215, "gt_distance_m": 2.184462070465088, "pred_distance_m": 3.050579071044922}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 0, "pred_class_confidence": 0.3434954583644867, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 194.17483520507812, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -75.04415893554688, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.579716444015503}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.1792079657316208, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 36.0395393371582, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -23.018037796020508, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 4.12028694152832}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 4, "pred_class_confidence": 0.2522953450679779, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 31.846813201904297, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -20.414447784423828, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.790785551071167}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 2, "pred_class_confidence": 0.17815539240837097, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 16.48630714416504, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -24.849363327026367, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.6938118934631348}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6797819137573242, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 30.07630729675293, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -13.780400276184082, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.842555522918701}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.1449049711227417, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 21.425487518310547, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -16.12574005126953, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.8154659271240234}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.18907897174358368, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 3.6424968242645264, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -20.398635864257812, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.1470651626586914}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 1, "pred_class_confidence": 0.15372514724731445, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 37.61888122558594, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -24.945823669433594, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.227797985076904}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5893138647079468, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 184.84339904785156, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -30.276107788085938, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.011122703552246}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 2, "pred_class_confidence": 0.10526897013187408, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 39.82246398925781, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -23.105180740356445, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.238950252532959}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/02_spatialfirst/val_predictions/epoch_0010.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 0, "pred_class_confidence": 0.3529302775859833, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 45.93572235107422, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -44.47427749633789, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.6020724773406982}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 0, "pred_class_confidence": 0.09492944180965424, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 186.52252197265625, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -40.6455192565918, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 2.1468799114227295}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 14, "pred_class_confidence": 0.08508722484111786, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 190.17359924316406, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -19.185548782348633, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.229578018188477}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.3716968894004822, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 179.648193359375, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -44.18914031982422, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.26961088180542}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 10, "pred_class_confidence": 0.0841796025633812, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 158.17929077148438, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -53.600242614746094, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.391000270843506}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.23880958557128906, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 35.1049690246582, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -30.013486862182617, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.741266965866089}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.19782665371894836, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 192.1910400390625, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -56.476749420166016, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.463538408279419}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 7, "pred_class_confidence": 0.2930178642272949, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 149.1195068359375, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -70.55850982666016, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 3.972562551498413}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.13750001788139343, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 31.323209762573242, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -24.672466278076172, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.769169569015503}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 7, "pred_class_confidence": 0.24532684683799744, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 38.27500534057617, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -35.018680572509766, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.8240113258361816}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5066956281661987, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 46.22343826293945, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -34.48890686035156, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 3.1851842403411865}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.23100684583187103, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 34.126312255859375, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -24.795879364013672, "gt_distance_m": 1.098374366760254, "pred_distance_m": 2.180421829223633}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.19835861027240753, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 13.889735221862793, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -27.862167358398438, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.4012025594711304}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 0, "pred_class_confidence": 0.07024668902158737, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 30.478219985961914, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -28.896102905273438, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.298463821411133}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6004331707954407, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 191.0487060546875, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -24.091537475585938, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 1.7873883247375488}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.26172810792922974, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 51.49317169189453, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -41.28761291503906, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.363895893096924}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/02_spatialfirst/val_predictions/epoch_0011.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.2936277687549591, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 54.37763977050781, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -34.073158264160156, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.8879928588867188}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 7, "pred_class_confidence": 0.11887457966804504, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 356.40472412109375, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -44.22403335571289, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 1.7441933155059814}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 8, "pred_class_confidence": 0.11361327767372131, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 186.8942108154297, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -23.18293571472168, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.476709365844727}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.25213146209716797, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 180.9129638671875, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -50.5263786315918, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.2325639724731445}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 0, "pred_class_confidence": 0.23602426052093506, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 178.74159240722656, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -41.17512130737305, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.259487152099609}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.21080978214740753, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 33.47902297973633, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -26.96748161315918, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.861840009689331}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.16497907042503357, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 258.41339111328125, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -82.763671875, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.516000270843506}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.19525183737277985, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 38.17619705200195, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -35.95234298706055, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 4.357637882232666}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.09910251945257187, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 31.503141403198242, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -21.925243377685547, "gt_distance_m": 2.820817708969116, "pred_distance_m": 4.200061798095703}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 7, "pred_class_confidence": 0.2019810974597931, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 41.44724655151367, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -27.63321304321289, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.6027958393096924}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.3347563147544861, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 44.61481857299805, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -23.521739959716797, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.310530662536621}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.10558511316776276, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 25.22488784790039, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -17.12963104248047, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.686606526374817}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.20963715016841888, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 2.1165120601654053, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -6.9181413650512695, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.1667884588241577}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 1, "pred_class_confidence": 0.1584499478340149, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 40.64081954956055, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -22.34649658203125, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.1041717529296875}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6557804942131042, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 190.84378051757812, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -21.950794219970703, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 2.54002046585083}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 10, "pred_class_confidence": 0.0929039791226387, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 49.958683013916016, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -23.52704429626465, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.0188751220703125}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/03_balanced/val_predictions/epoch_0000.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.4652293920516968, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 50.440147399902344, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -37.956478118896484, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.7112948894500732}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 2, "pred_class_confidence": 0.3081551790237427, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 185.0527801513672, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -77.72425842285156, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 2.678518056869507}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.12380285561084747, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 198.48670959472656, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -22.2397518157959, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.0617570877075195}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.45436930656433105, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 139.30731201171875, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -68.28666687011719, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.20196008682251}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 7, "pred_class_confidence": 0.1656206250190735, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 58.21692657470703, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -34.14799499511719, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.20672082901001}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.41705796122550964, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 33.62894058227539, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -21.45591163635254, "gt_distance_m": 2.184462070465088, "pred_distance_m": 1.8474503755569458}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.44597184658050537, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 106.37283325195312, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -78.1629409790039, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.9628946781158447}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.2721915543079376, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 35.18821716308594, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -27.667463302612305, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 3.963090419769287}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.2630229592323303, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 30.382604598999023, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -19.05586051940918, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.8736486434936523}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 2, "pred_class_confidence": 0.4888960123062134, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 35.02552032470703, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -28.698795318603516, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.625534176826477}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.613919734954834, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 37.434757232666016, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -16.705774307250977, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 2.3411858081817627}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.4290921092033386, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 29.51958656311035, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -17.447904586791992, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.4204987287521362}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.3079037368297577, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 340.7200012207031, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -9.99478530883789, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.1879559755325317}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 3, "pred_class_confidence": 0.08870331943035126, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 21.869403839111328, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -21.582040786743164, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.190743446350098}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.4463835656642914, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 181.08416748046875, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -22.99847984313965, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 3.684169054031372}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 10, "pred_class_confidence": 0.13738584518432617, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 52.207149505615234, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -22.76544952392578, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.211691856384277}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/03_balanced/val_predictions/epoch_0001.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.491860955953598, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 56.66563034057617, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -42.2235107421875, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.291419506072998}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 2, "pred_class_confidence": 0.2614237070083618, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 181.33175659179688, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -18.915407180786133, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 3.3964908123016357}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.14415985345840454, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 206.7694854736328, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -21.475114822387695, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.091799259185791}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.5470665693283081, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 56.65910339355469, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -48.69205856323242, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.214100360870361}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 8, "pred_class_confidence": 0.10153017938137054, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 180.68309020996094, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -28.127729415893555, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.307629585266113}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.4577651619911194, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 31.88543128967285, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -15.482254981994629, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.047370433807373}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.1827295422554016, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 179.75119018554688, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -26.407119750976562, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.8324103355407715}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.3590684235095978, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 41.62413787841797, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -38.4423942565918, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 4.215652942657471}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.2791205942630768, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 33.65408706665039, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -24.952150344848633, "gt_distance_m": 2.820817708969116, "pred_distance_m": 4.1644439697265625}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 2, "pred_class_confidence": 0.5486277937889099, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 36.48413848876953, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -27.84297752380371, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.553680419921875}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.7034838795661926, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 38.82562255859375, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -19.502765655517578, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 4.0867533683776855}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.36678647994995117, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 30.38776206970215, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -14.15998649597168, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.4811965227127075}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 0, "pred_class_confidence": 0.2071860134601593, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 3.621171712875366, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -14.08041000366211, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.1699351072311401}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 5, "pred_class_confidence": 0.10242180526256561, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 13.531332015991211, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -29.585412979125977, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.125040531158447}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.288541316986084, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 186.05575561523438, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -24.747211456298828, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 4.243627071380615}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 19, "pred_class_confidence": 0.12464463710784912, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 43.703041076660156, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -20.47214698791504, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.141945838928223}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/03_balanced/val_predictions/epoch_0002.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.5306370854377747, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 42.92330551147461, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -43.41891860961914, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.0460147857666016}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 10, "pred_class_confidence": 0.10475330799818039, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 169.823974609375, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -26.621299743652344, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 3.4691033363342285}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.16167820990085602, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 201.53282165527344, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -17.45585060119629, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.225067138671875}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.6088465452194214, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 31.33527183532715, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -41.11969757080078, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.041346073150635}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 0, "pred_class_confidence": 0.2817031443119049, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 178.04835510253906, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -28.531742095947266, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.389072418212891}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.40591859817504883, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 28.727510452270508, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -13.010272979736328, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.0853495597839355}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.13064579665660858, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 179.3424072265625, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -61.412750244140625, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.7068729400634766}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 7, "pred_class_confidence": 0.3271382749080658, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 10.363973617553711, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -40.74729537963867, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 3.6168224811553955}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.33084341883659363, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 29.6706600189209, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -22.97655487060547, "gt_distance_m": 2.820817708969116, "pred_distance_m": 4.1391448974609375}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 2, "pred_class_confidence": 0.3382672071456909, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 25.414857864379883, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -29.19236183166504, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.7232050895690918}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.5783479809761047, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 31.04372215270996, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -18.87343406677246, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 4.187031269073486}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.2510078549385071, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 23.498838424682617, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -11.646946907043457, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.4687786102294922}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.21331076323986053, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 336.5492858886719, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -25.348438262939453, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.1275973320007324}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 5, "pred_class_confidence": 0.0978168174624443, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 15.764838218688965, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -25.022266387939453, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.194984436035156}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.30789345502853394, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 168.814208984375, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -29.469921112060547, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 4.2835612297058105}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 10, "pred_class_confidence": 0.13816861808300018, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 37.611968994140625, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -17.26757049560547, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.17315673828125}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/03_balanced/val_predictions/epoch_0003.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.4969058632850647, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 49.3546028137207, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -30.056886672973633, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.0487539768218994}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 2, "pred_class_confidence": 0.5240582823753357, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 24.349292755126953, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -67.02215576171875, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 3.0346808433532715}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 3, "pred_class_confidence": 0.11902865022420883, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 203.7489013671875, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -15.182748794555664, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.965588331222534}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.6151682734489441, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 57.16372299194336, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -58.73400115966797, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.131400108337402}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 7, "pred_class_confidence": 0.24947182834148407, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 70.57550048828125, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -23.916353225708008, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.215686321258545}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.36580196022987366, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 26.82112693786621, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -17.266178131103516, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.2577686309814453}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.1785728484392166, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 183.54055786132812, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -53.72905349731445, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.8652164936065674}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 7, "pred_class_confidence": 0.41342899203300476, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 96.77799224853516, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -80.07484436035156, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 3.6875622272491455}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.33068835735321045, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 24.533477783203125, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -25.108957290649414, "gt_distance_m": 2.820817708969116, "pred_distance_m": 4.149332046508789}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 2, "pred_class_confidence": 0.439523309469223, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 30.78750228881836, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -25.75278091430664, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.8958789110183716}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.3286114037036896, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 41.20746994018555, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -18.637929916381836, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 4.239571571350098}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.2959814667701721, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 24.874469757080078, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -16.03327751159668, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.719274878501892}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.2554350793361664, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 339.3896179199219, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -38.261451721191406, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.094611406326294}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 5, "pred_class_confidence": 0.09247386455535889, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 16.68075942993164, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -29.246566772460938, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.2014665603637695}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.3468647003173828, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 176.18617248535156, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -28.434680938720703, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 4.381868839263916}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 10, "pred_class_confidence": 0.1204647645354271, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 55.82065963745117, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -18.246845245361328, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.269623279571533}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/03_balanced/val_predictions/epoch_0004.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.36668726801872253, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 53.389739990234375, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -18.216156005859375, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.090918779373169}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 10, "pred_class_confidence": 0.1489073783159256, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 142.3124237060547, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -61.085628509521484, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 3.2502615451812744}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.13575394451618195, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 202.75384521484375, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -19.534055709838867, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.069623947143555}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.49272051453590393, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 45.18400573730469, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -36.26020050048828, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 3.9959397315979004}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 7, "pred_class_confidence": 0.2098257839679718, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 63.7413215637207, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -23.296127319335938, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.081606388092041}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.27401262521743774, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 27.923194885253906, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -10.274205207824707, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.14341402053833}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.08811087161302567, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 166.62722778320312, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -55.76592254638672, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.78812837600708}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.29383131861686707, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 11.316704750061035, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -31.218732833862305, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 3.8120555877685547}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.40940409898757935, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 23.418785095214844, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -43.197906494140625, "gt_distance_m": 2.820817708969116, "pred_distance_m": 4.041573524475098}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 2, "pred_class_confidence": 0.2585445046424866, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 27.259559631347656, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -24.142305374145508, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.5913126468658447}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.2962912321090698, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 41.65180969238281, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -13.223244667053223, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 3.9353930950164795}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.135005384683609, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 23.7468204498291, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -8.643409729003906, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.6530851125717163}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.2002989798784256, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 355.485107421875, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -14.288707733154297, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.184759259223938}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 3, "pred_class_confidence": 0.08815532922744751, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 16.933849334716797, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -11.859153747558594, "gt_distance_m": 5.218364715576172, "pred_distance_m": 3.6899592876434326}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.2822698652744293, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 138.39459228515625, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -29.536380767822266, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 4.170068264007568}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 2, "pred_class_confidence": 0.1462743580341339, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 51.35338592529297, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -13.25876235961914, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.0402445793151855}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/03_balanced/val_predictions/epoch_0005.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 7, "pred_class_confidence": 0.5684023499488831, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 49.294586181640625, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -20.36109733581543, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.14642071723938}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 2, "pred_class_confidence": 0.2598978579044342, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 139.60548400878906, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -56.18867492675781, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 2.908604383468628}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 3, "pred_class_confidence": 0.12660335004329681, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 208.51287841796875, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -17.09160614013672, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.936523199081421}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.6796190142631531, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 55.76845932006836, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -27.077999114990234, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.045652389526367}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 7, "pred_class_confidence": 0.31998294591903687, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 83.61080169677734, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -28.856788635253906, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.091882705688477}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.3478494882583618, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 28.360322952270508, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -12.441612243652344, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.3693771362304688}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 2, "pred_class_confidence": 0.12985767424106598, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 191.5695343017578, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -79.37123107910156, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.5894503593444824}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.3706074655056, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 14.915197372436523, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -25.962291717529297, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 3.7263569831848145}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.3022766709327698, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 32.478309631347656, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -23.468481063842773, "gt_distance_m": 2.820817708969116, "pred_distance_m": 4.053379535675049}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 2, "pred_class_confidence": 0.26591184735298157, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 34.15822219848633, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -20.970502853393555, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.6218172311782837}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 0, "pred_class_confidence": 0.6869387626647949, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 41.420650482177734, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -16.07975196838379, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 4.0829877853393555}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.24988727271556854, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 26.80458641052246, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -11.824210166931152, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.7465434074401855}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.4254617393016815, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 9.574161529541016, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -15.800172805786133, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.209755778312683}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 3, "pred_class_confidence": 0.11079861223697662, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 17.46584701538086, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -15.65481948852539, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.041066646575928}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.2044188380241394, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 160.77291870117188, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -30.245765686035156, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 4.2760210037231445}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 2, "pred_class_confidence": 0.17045503854751587, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 53.509944915771484, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -13.818686485290527, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.109755516052246}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/03_balanced/val_predictions/epoch_0006.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 10, "pred_class_confidence": 0.19377020001411438, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 76.6161117553711, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -15.09941577911377, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 3.7638397216796875}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 2, "pred_class_confidence": 0.34092527627944946, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 43.981990814208984, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -52.26350402832031, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 3.1519954204559326}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 3, "pred_class_confidence": 0.11585363000631332, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 209.416015625, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -17.461711883544922, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.152933120727539}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.7309088706970215, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 106.72573852539062, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -40.07912063598633, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.087317943572998}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 10, "pred_class_confidence": 0.17216987907886505, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 80.20958709716797, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -15.214683532714844, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.018107891082764}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.40284648537635803, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 37.73902130126953, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -14.574090957641602, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.1627800464630127}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.12768647074699402, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 174.7464141845703, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -45.509857177734375, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.649264335632324}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.23371492326259613, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 17.436979293823242, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -29.80406951904297, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 3.8507649898529053}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.28621622920036316, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 34.21063232421875, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -32.322452545166016, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.973515748977661}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 2, "pred_class_confidence": 0.2954769730567932, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 46.51826858520508, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -21.661821365356445, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.6573007106781006}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 2, "pred_class_confidence": 0.17348983883857727, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 56.53490447998047, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -14.903194427490234, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 3.8851704597473145}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.36544838547706604, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 33.40488052368164, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -12.049354553222656, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.5398414134979248}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.39662209153175354, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 358.4902648925781, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -15.62355899810791, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.1751528978347778}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 5, "pred_class_confidence": 0.0943506732583046, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 27.049560546875, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -18.950162887573242, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.091588973999023}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 2, "pred_class_confidence": 0.3902750611305237, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 156.07362365722656, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -28.563066482543945, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 4.289440155029297}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 10, "pred_class_confidence": 0.12656047940254211, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 69.16877746582031, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -13.92994213104248, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.068374156951904}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/03_balanced/val_predictions/epoch_0007.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 2, "pred_class_confidence": 0.4289436936378479, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 55.807159423828125, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -14.156928062438965, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 2.7917613983154297}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 2, "pred_class_confidence": 0.5189502835273743, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 55.98291015625, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -55.546119689941406, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 3.2425942420959473}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 5, "pred_class_confidence": 0.11802694946527481, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 216.17971801757812, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -17.432310104370117, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.905496835708618}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.5908661484718323, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 58.81517028808594, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -37.11732482910156, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.0387091636657715}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 7, "pred_class_confidence": 0.5120279788970947, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 62.522254943847656, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -14.967637062072754, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 3.739856481552124}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 1, "pred_class_confidence": 0.38491177558898926, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 34.35289764404297, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -11.765726089477539, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.020695447921753}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.17783123254776, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 137.14340209960938, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -82.05216217041016, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.6943469047546387}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.32592901587486267, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 14.407281875610352, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -30.550687789916992, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 3.2618789672851562}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.3511850833892822, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 39.19068908691406, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -19.216894149780273, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.8793785572052}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 2, "pred_class_confidence": 0.3727220594882965, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 42.052337646484375, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -18.001415252685547, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 1.6544055938720703}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 2, "pred_class_confidence": 0.22597436606884003, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 46.17280197143555, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -14.176298141479492, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 3.871159791946411}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.1576126217842102, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 26.006980895996094, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -11.206754684448242, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.4796788692474365}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.5866517424583435, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 6.5470805168151855, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -8.721088409423828, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.1473580598831177}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 13, "pred_class_confidence": 0.1032567247748375, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 23.277084350585938, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -11.771560668945312, "gt_distance_m": 5.218364715576172, "pred_distance_m": 3.448881149291992}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.3500141501426697, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 126.26097869873047, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -29.468233108520508, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 4.302454948425293}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 2, "pred_class_confidence": 0.15285655856132507, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 57.4243049621582, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -13.850285530090332, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.0551066398620605}

checkpoints/spatial_beats_ov1_ast_three_stage_v2/03_balanced/val_predictions/epoch_0008.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 2, "pred_class_confidence": 0.3785944879055023, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 82.58953094482422, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -15.115882873535156, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 4.090758323669434}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000004-foa__144815", "gt_class_index": 38, "gt_class_name": "camera", "pred_class_index": 2, "pred_class_confidence": 0.561265230178833, "gt_azimuth_deg": 177.78807067871094, "pred_azimuth_deg": 105.57334899902344, "gt_elevation_deg": -35.406551361083984, "pred_elevation_deg": -48.148040771484375, "gt_distance_m": 0.8211097717285156, "pred_distance_m": 3.5760343074798584}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 3, "pred_class_confidence": 0.11135193705558777, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 217.31861877441406, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -14.186772346496582, "gt_distance_m": 4.594465255737305, "pred_distance_m": 3.668046712875366}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000012-foa__372488", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 2, "pred_class_confidence": 0.500741720199585, "gt_azimuth_deg": -107.67652130126953, "pred_azimuth_deg": 127.15911865234375, "gt_elevation_deg": 0.005136481486260891, "pred_elevation_deg": -38.631256103515625, "gt_distance_m": 3.5567243099212646, "pred_distance_m": 4.302134037017822}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 10, "pred_class_confidence": 0.10565713047981262, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 85.83656311035156, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -15.41881275177002, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 4.247963905334473}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000020-foa__86142", "gt_class_index": 26, "gt_class_name": "kitchenware", "pred_class_index": 4, "pred_class_confidence": 0.36240485310554504, "gt_azimuth_deg": 96.20484161376953, "pred_azimuth_deg": 36.41193771362305, "gt_elevation_deg": 8.378170013427734, "pred_elevation_deg": -16.07903289794922, "gt_distance_m": 2.184462070465088, "pred_distance_m": 2.1672134399414062}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 4, "pred_class_confidence": 0.19940978288650513, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 168.3665313720703, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -28.740995407104492, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 3.7417654991149902}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000028-foa__61565", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.3793940544128418, "gt_azimuth_deg": 171.40408325195312, "pred_azimuth_deg": 50.18540954589844, "gt_elevation_deg": -38.36641311645508, "pred_elevation_deg": -75.34228515625, "gt_distance_m": 3.1514837741851807, "pred_distance_m": 3.61342716217041}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 4, "pred_class_confidence": 0.3772972524166107, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 59.93186569213867, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -18.665748596191406, "gt_distance_m": 2.820817708969116, "pred_distance_m": 4.28657341003418}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000036-foa__418494", "gt_class_index": 22, "gt_class_name": "train", "pred_class_index": 2, "pred_class_confidence": 0.6535046100616455, "gt_azimuth_deg": 40.96934127807617, "pred_azimuth_deg": 45.126869201660156, "gt_elevation_deg": -40.88724136352539, "pred_elevation_deg": -23.89653968811035, "gt_distance_m": 1.1888867616653442, "pred_distance_m": 2.2218780517578125}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 2, "pred_class_confidence": 0.2475711554288864, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 54.97673034667969, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -14.959712982177734, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 4.207846164703369}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000044-foa__413718", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.2700205445289612, "gt_azimuth_deg": 28.888479232788086, "pred_azimuth_deg": 32.761417388916016, "gt_elevation_deg": -38.93251419067383, "pred_elevation_deg": -14.76196002960205, "gt_distance_m": 1.098374366760254, "pred_distance_m": 1.7940764427185059}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 4, "pred_class_confidence": 0.47918978333473206, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 357.8261413574219, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": -16.051986694335938, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 1.1580069065093994}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000052-foa__86148", "gt_class_index": 59, "gt_class_name": "tape", "pred_class_index": 11, "pred_class_confidence": 0.12798649072647095, "gt_azimuth_deg": -92.65625762939453, "pred_azimuth_deg": 30.549516677856445, "gt_elevation_deg": -20.02092933654785, "pred_elevation_deg": -14.810710906982422, "gt_distance_m": 5.218364715576172, "pred_distance_m": 4.05912971496582}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 1, "pred_class_confidence": 0.36989331245422363, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 156.15838623046875, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": -22.953941345214844, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 4.325282096862793}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000060-foa__54399", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 2, "pred_class_confidence": 0.13523542881011963, "gt_azimuth_deg": -92.6680679321289, "pred_azimuth_deg": 63.59720230102539, "gt_elevation_deg": -0.8184879422187805, "pred_elevation_deg": -14.096915245056152, "gt_distance_m": 4.348083972930908, "pred_distance_m": 4.266963958740234}

checkpoints/spatial_beats_ov1_local_spatial_beatsfrontend_run1/val_predictions/epoch_0000.jsonl

@@ -0,0 +1,16 @@
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000000-foa__132991", "gt_class_index": 56, "gt_class_name": "female_singing", "pred_class_index": 2, "pred_class_confidence": 0.27646803855895996, "gt_azimuth_deg": 121.2662582397461, "pred_azimuth_deg": 113.28823852539062, "gt_elevation_deg": -42.34892654418945, "pred_elevation_deg": -17.430150985717773, "gt_distance_m": 2.3379604816436768, "pred_distance_m": 1.785346269607544}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000008-foa__368453", "gt_class_index": 25, "gt_class_name": "wind", "pred_class_index": 2, "pred_class_confidence": 0.14157158136367798, "gt_azimuth_deg": -132.3766632080078, "pred_azimuth_deg": 241.96026611328125, "gt_elevation_deg": -5.357852458953857, "pred_elevation_deg": -16.79607582092285, "gt_distance_m": 4.594465255737305, "pred_distance_m": 4.086968421936035}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000016-foa__57325", "gt_class_index": 55, "gt_class_name": "aircraft", "pred_class_index": 2, "pred_class_confidence": 0.22427380084991455, "gt_azimuth_deg": -165.8902130126953, "pred_azimuth_deg": 193.80804443359375, "gt_elevation_deg": -34.53343200683594, "pred_elevation_deg": -11.191356658935547, "gt_distance_m": 3.1432597637176514, "pred_distance_m": 2.6807994842529297}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000024-foa__33624", "gt_class_index": 12, "gt_class_name": "metal_clink", "pred_class_index": 1, "pred_class_confidence": 0.12510795891284943, "gt_azimuth_deg": 170.71868896484375, "pred_azimuth_deg": 170.6802215576172, "gt_elevation_deg": -14.377400398254395, "pred_elevation_deg": -9.833852767944336, "gt_distance_m": 2.6324522495269775, "pred_distance_m": 2.0514235496520996}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000032-foa__118401", "gt_class_index": 9, "gt_class_name": "tool", "pred_class_index": 1, "pred_class_confidence": 0.1668020486831665, "gt_azimuth_deg": 134.8607177734375, "pred_azimuth_deg": 117.16987609863281, "gt_elevation_deg": -9.617217063903809, "pred_elevation_deg": -10.900530815124512, "gt_distance_m": 2.820817708969116, "pred_distance_m": 3.1056485176086426}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000040-foa__2640", "gt_class_index": 0, "gt_class_name": "wind_instrument", "pred_class_index": 2, "pred_class_confidence": 0.27631378173828125, "gt_azimuth_deg": 40.66659164428711, "pred_azimuth_deg": 64.93964385986328, "gt_elevation_deg": -13.705007553100586, "pred_elevation_deg": -10.741341590881348, "gt_distance_m": 1.4382526874542236, "pred_distance_m": 1.815384864807129}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000048-foa__2050", "gt_class_index": 1, "gt_class_name": "string_instrument", "pred_class_index": 1, "pred_class_confidence": 0.21600529551506042, "gt_azimuth_deg": -41.99135971069336, "pred_azimuth_deg": 306.85186767578125, "gt_elevation_deg": 6.244300842285156, "pred_elevation_deg": 21.644874572753906, "gt_distance_m": 1.1382137537002563, "pred_distance_m": 0.9953142404556274}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000056-foa__321160", "gt_class_index": 7, "gt_class_name": "keyboard_instrument", "pred_class_index": 0, "pred_class_confidence": 0.3120131492614746, "gt_azimuth_deg": -150.31336975097656, "pred_azimuth_deg": 207.552734375, "gt_elevation_deg": 7.255143165588379, "pred_elevation_deg": 12.22233772277832, "gt_distance_m": 0.9987623691558838, "pred_distance_m": 1.05790376663208}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000064-foa__347902", "gt_class_index": 28, "gt_class_name": "musical_instrument", "pred_class_index": 0, "pred_class_confidence": 0.17401468753814697, "gt_azimuth_deg": 80.07795715332031, "pred_azimuth_deg": 81.10263061523438, "gt_elevation_deg": -31.087900161743164, "pred_elevation_deg": -12.079465866088867, "gt_distance_m": 3.3884599208831787, "pred_distance_m": 2.613574266433716}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000072-foa__60822", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 0, "pred_class_confidence": 0.2559112012386322, "gt_azimuth_deg": 19.612287521362305, "pred_azimuth_deg": 17.468156814575195, "gt_elevation_deg": -35.90705490112305, "pred_elevation_deg": -11.198664665222168, "gt_distance_m": 1.4592041969299316, "pred_distance_m": 1.6627596616744995}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000080-foa__174944", "gt_class_index": 16, "gt_class_name": "speech", "pred_class_index": 4, "pred_class_confidence": 0.351718932390213, "gt_azimuth_deg": -33.693973541259766, "pred_azimuth_deg": 329.13604736328125, "gt_elevation_deg": -19.951570510864258, "pred_elevation_deg": -17.260669708251953, "gt_distance_m": 3.0693788528442383, "pred_distance_m": 2.3435096740722656}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000088-foa__402628", "gt_class_index": 3, "gt_class_name": "body_sound", "pred_class_index": 4, "pred_class_confidence": 0.3201330602169037, "gt_azimuth_deg": -153.89576721191406, "pred_azimuth_deg": 226.86822509765625, "gt_elevation_deg": -52.02226638793945, "pred_elevation_deg": -19.710243225097656, "gt_distance_m": 0.9056954383850098, "pred_distance_m": 1.3049248456954956}
+{"sample_id": "valid/hm3d/00034-6imZUJGRUq4/000096-foa__161195", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 4, "pred_class_confidence": 0.3673483431339264, "gt_azimuth_deg": 43.23616409301758, "pred_azimuth_deg": 109.25592041015625, "gt_elevation_deg": -30.50249671936035, "pred_elevation_deg": -14.060944557189941, "gt_distance_m": 3.011542320251465, "pred_distance_m": 4.146271705627441}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000004-foa__160791", "gt_class_index": 11, "gt_class_name": "war_sound", "pred_class_index": 2, "pred_class_confidence": 0.17205673456192017, "gt_azimuth_deg": 26.153356552124023, "pred_azimuth_deg": 260.6724853515625, "gt_elevation_deg": -9.317741394042969, "pred_elevation_deg": -24.988601684570312, "gt_distance_m": 4.411057949066162, "pred_distance_m": 4.19356632232666}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000012-foa__278193", "gt_class_index": 43, "gt_class_name": "writing", "pred_class_index": 1, "pred_class_confidence": 0.1775190681219101, "gt_azimuth_deg": 49.463783264160156, "pred_azimuth_deg": 59.18430709838867, "gt_elevation_deg": -45.57375717163086, "pred_elevation_deg": -14.726547241210938, "gt_distance_m": 2.1329946517944336, "pred_distance_m": 2.070706605911255}
+{"sample_id": "valid/hm3d/00056-kdw2Uapns3b/000020-foa__89741", "gt_class_index": 5, "gt_class_name": "water", "pred_class_index": 2, "pred_class_confidence": 0.125033438205719, "gt_azimuth_deg": -158.04286193847656, "pred_azimuth_deg": 196.50013732910156, "gt_elevation_deg": -8.935344696044922, "pred_elevation_deg": -8.057361602783203, "gt_distance_m": 1.7858494520187378, "pred_distance_m": 1.2330656051635742}