{ "checkpoint": "runs/deepcad_latent/resnet18_transformer_v1_ddp2/best.pt", "ids": "datasets/rescue_deepcad_latent/full_v0_len60_excluding_rescue_test/test_ids.txt", "is_multimodal": false, "text_root": null, "retrieval_mode": "direct", "compare_target": "true", "param_tolerance": 3, "num_samples": 5592, "summary": { "num_samples": 5592, "cmd_token_acc": 0.8391398004815825, "token_exact_acc": 0.5305168253604553, "sequence_cmd_exact_rate": 0.675071530758226, "sequence_exact_rate": 0.13125894134477825, "mean_pred_len": 8.831008583690988, "mean_gt_len": 9.420243204577968, "mean_len_abs_error": 1.8159871244635193, "first_divergence_missing_rate": 0.13125894134477825, "acc_cmd": 0.8634451846250522, "acc_param": 0.741478247165596, "pred_solid_valid_rate": 0.8134835479256081, "gt_solid_valid_rate": 0.9774678111587983, "invalidity_ratio": 0.18651645207439194, "cd_valid_count": 4928, "cd_invalid_count": 664, "cd_mean": 0.12981373850902178, "cd_median": 0.034327806811930595, "by_bucket": { "len_01_06": { "count": 3216, "cmd_token_acc": 0.9740033988990587, "token_exact_acc": 0.6861027642036345, "sequence_exact_rate": 0.1843905472636816, "mean_len_abs_error": 0.17319651741293532, "acc_cmd": 0.9847740464344948, "acc_param": 0.8519142227556925, "pred_solid_valid_rate": 0.970771144278607, "invalidity_ratio": 0.029228855721393, "cd_mean": 0.11898658033303332, "cd_median": 0.019705686610152172 }, "len_07_12": { "count": 1315, "cmd_token_acc": 0.7624808189216025, "token_exact_acc": 0.4048386834849154, "sequence_exact_rate": 0.0714828897338403, "mean_len_abs_error": 1.7931558935361216, "acc_cmd": 0.811738789305329, "acc_param": 0.7042623472758387, "pred_solid_valid_rate": 0.7262357414448669, "invalidity_ratio": 0.2737642585551331, "cd_mean": 0.14735227678297338, "cd_median": 0.06654237348776594 }, "len_13_24": { "count": 790, "cmd_token_acc": 0.5792265561163498, "token_exact_acc": 0.2490031207995815, "sequence_exact_rate": 0.056962025316455694, "mean_len_abs_error": 4.688607594936709, "acc_cmd": 0.6215911324139712, "acc_param": 0.5876221498371336, "pred_solid_valid_rate": 0.4835443037974684, "invalidity_ratio": 0.5164556962025316, "cd_mean": 0.13941998955960228, "cd_median": 0.057110440702972096 }, "len_25_plus": { "count": 271, "cmd_token_acc": 0.36835268346799277, "token_exact_acc": 0.11464303882817876, "sequence_exact_rate": 0.007380073800738007, "mean_len_abs_error": 13.047970479704796, "acc_cmd": 0.3795521643779019, "acc_param": 0.4598471487360376, "pred_solid_valid_rate": 0.33210332103321033, "invalidity_ratio": 0.6678966789667897, "cd_mean": 0.19125942949745178, "cd_median": 0.11478811091909968 } }, "worst_examples": [ { "sample_id": "0044/00449233_00001", "bucket": "len_25_plus", "pred_len": 4, "gt_len": 50, "len_abs_error": 46, "cmd_token_acc": 0.06, "token_exact_acc": 0.04, "sequence_exact": false, "first_divergence_step": 2, "cd": 0.1369912929596886, "pred_solid_valid": true }, { "sample_id": "0063/00638901_00001", "bucket": "len_25_plus", "pred_len": 6, "gt_len": 48, "len_abs_error": 42, "cmd_token_acc": 0.10416666666666667, "token_exact_acc": 0.020833333333333332, "sequence_exact": false, "first_divergence_step": 1, "cd": 0.8650329199152399, "pred_solid_valid": true }, { "sample_id": "0046/00461540_00002", "bucket": "len_25_plus", "pred_len": 14, "gt_len": 56, "len_abs_error": 42, "cmd_token_acc": 0.125, "token_exact_acc": 0.017857142857142856, "sequence_exact": false, "first_divergence_step": 1, "cd": 0.01608317231504478, "pred_solid_valid": false }, { "sample_id": "0055/00550713_00001", "bucket": "len_25_plus", "pred_len": 12, "gt_len": 53, "len_abs_error": 41, "cmd_token_acc": 0.1509433962264151, "token_exact_acc": 0.03773584905660377, "sequence_exact": false, "first_divergence_step": 1, "cd": -1.0, "pred_solid_valid": false }, { "sample_id": "0057/00571486_00001", "bucket": "len_25_plus", "pred_len": 11, "gt_len": 52, "len_abs_error": 41, "cmd_token_acc": 0.15384615384615385, "token_exact_acc": 0.038461538461538464, "sequence_exact": false, "first_divergence_step": 1, "cd": 0.372333608571029, "pred_solid_valid": true }, { "sample_id": "0094/00947145_00001", "bucket": "len_25_plus", "pred_len": 10, "gt_len": 49, "len_abs_error": 39, "cmd_token_acc": 0.20408163265306123, "token_exact_acc": 0.02040816326530612, "sequence_exact": false, "first_divergence_step": 1, "cd": -1.0, "pred_solid_valid": false }, { "sample_id": "0043/00432451_00001", "bucket": "len_25_plus", "pred_len": 3, "gt_len": 39, "len_abs_error": 36, "cmd_token_acc": 0.02564102564102564, "token_exact_acc": 0.02564102564102564, "sequence_exact": false, "first_divergence_step": 1, "cd": 0.31735212582855776, "pred_solid_valid": true }, { "sample_id": "0054/00542394_00001", "bucket": "len_25_plus", "pred_len": 11, "gt_len": 46, "len_abs_error": 35, "cmd_token_acc": 0.15217391304347827, "token_exact_acc": 0.021739130434782608, "sequence_exact": false, "first_divergence_step": 1, "cd": -1.0, "pred_solid_valid": false }, { "sample_id": "0024/00244336_00001", "bucket": "len_25_plus", "pred_len": 22, "gt_len": 57, "len_abs_error": 35, "cmd_token_acc": 0.2982456140350877, "token_exact_acc": 0.017543859649122806, "sequence_exact": false, "first_divergence_step": 1, "cd": -1.0, "pred_solid_valid": false }, { "sample_id": "0065/00658127_00001", "bucket": "len_25_plus", "pred_len": 17, "gt_len": 51, "len_abs_error": 34, "cmd_token_acc": 0.21568627450980393, "token_exact_acc": 0.0196078431372549, "sequence_exact": false, "first_divergence_step": 1, "cd": 0.08852288401841818, "pred_solid_valid": false }, { "sample_id": "0098/00980287_00001", "bucket": "len_25_plus", "pred_len": 18, "gt_len": 50, "len_abs_error": 32, "cmd_token_acc": 0.1, "token_exact_acc": 0.04, "sequence_exact": false, "first_divergence_step": 1, "cd": -1.0, "pred_solid_valid": false }, { "sample_id": "0062/00620669_00001", "bucket": "len_25_plus", "pred_len": 6, "gt_len": 38, "len_abs_error": 32, "cmd_token_acc": 0.10526315789473684, "token_exact_acc": 0.02631578947368421, "sequence_exact": false, "first_divergence_step": 1, "cd": 0.13130972784010514, "pred_solid_valid": true }, { "sample_id": "0044/00446170_00001", "bucket": "len_25_plus", "pred_len": 16, "gt_len": 48, "len_abs_error": 32, "cmd_token_acc": 0.125, "token_exact_acc": 0.020833333333333332, "sequence_exact": false, "first_divergence_step": 1, "cd": -1.0, "pred_solid_valid": false }, { "sample_id": "0087/00873259_00001", "bucket": "len_25_plus", "pred_len": 10, "gt_len": 42, "len_abs_error": 32, "cmd_token_acc": 0.16666666666666666, "token_exact_acc": 0.023809523809523808, "sequence_exact": false, "first_divergence_step": 1, "cd": 0.074099495283291, "pred_solid_valid": false }, { "sample_id": "0033/00331543_00002", "bucket": "len_25_plus", "pred_len": 12, "gt_len": 44, "len_abs_error": 32, "cmd_token_acc": 0.18181818181818182, "token_exact_acc": 0.022727272727272728, "sequence_exact": false, "first_divergence_step": 1, "cd": 0.3762435364793075, "pred_solid_valid": true }, { "sample_id": "0033/00339538_00001", "bucket": "len_25_plus", "pred_len": 20, "gt_len": 52, "len_abs_error": 32, "cmd_token_acc": 0.19230769230769232, "token_exact_acc": 0.019230769230769232, "sequence_exact": false, "first_divergence_step": 1, "cd": 0.03264505643227296, "pred_solid_valid": false }, { "sample_id": "0004/00043885_00001", "bucket": "len_25_plus", "pred_len": 12, "gt_len": 43, "len_abs_error": 31, "cmd_token_acc": 0.18604651162790697, "token_exact_acc": 0.023255813953488372, "sequence_exact": false, "first_divergence_step": 1, "cd": -1.0, "pred_solid_valid": false }, { "sample_id": "0048/00486655_00001", "bucket": "len_25_plus", "pred_len": 19, "gt_len": 50, "len_abs_error": 31, "cmd_token_acc": 0.2, "token_exact_acc": 0.02, "sequence_exact": false, "first_divergence_step": 1, "cd": -1.0, "pred_solid_valid": false }, { "sample_id": "0013/00134148_00001", "bucket": "len_25_plus", "pred_len": 6, "gt_len": 36, "len_abs_error": 30, "cmd_token_acc": 0.16666666666666666, "token_exact_acc": 0.08333333333333333, "sequence_exact": false, "first_divergence_step": 2, "cd": 0.1194260991804219, "pred_solid_valid": true }, { "sample_id": "0017/00178584_00001", "bucket": "len_25_plus", "pred_len": 6, "gt_len": 36, "len_abs_error": 30, "cmd_token_acc": 0.16666666666666666, "token_exact_acc": 0.08333333333333333, "sequence_exact": false, "first_divergence_step": 1, "cd": 0.7222374409952519, "pred_solid_valid": true } ] }, "paper_metrics": { "acc_cmd": 0.8634451846250522, "acc_param": 0.741478247165596, "invalidity_ratio": 0.18651645207439194, "cd_mean": 0.12981373850902178, "cd_median": 0.034327806811930595 } }