{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.1, "eval_steps": 500, "global_step": 3000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "step": 0, "train_flow_matching_loss": 0.326171875, "train_physics_loss": 0.0 }, { "grad_norm": 4.608675956726074, "learning_rate": 3.0000000000000004e-07, "loss": 0.2961, "step": 10 }, { "step": 10, "train_flow_matching_loss": 0.453125, "train_physics_loss": 1.1655902862548828 }, { "grad_norm": 6.491508960723877, "learning_rate": 6.333333333333333e-07, "loss": 0.269, "step": 20 }, { "step": 20, "train_flow_matching_loss": 0.29296875, "train_physics_loss": 0.0 }, { "grad_norm": 20.94609260559082, "learning_rate": 9.666666666666668e-07, "loss": 0.2762, "step": 30 }, { "step": 30, "train_flow_matching_loss": 0.236328125, "train_physics_loss": 0.0 }, { "grad_norm": 14.161486625671387, "learning_rate": 1.3e-06, "loss": 0.2519, "step": 40 }, { "step": 40, "train_flow_matching_loss": 0.279296875, "train_physics_loss": 0.0 }, { "grad_norm": 2.596518039703369, "learning_rate": 1.6333333333333333e-06, "loss": 0.2743, "step": 50 }, { "step": 50, "train_flow_matching_loss": 0.373046875, "train_physics_loss": 1.1627117395401 }, { "grad_norm": 1.793614149093628, "learning_rate": 1.9666666666666668e-06, "loss": 0.2641, "step": 60 }, { "step": 60, "train_flow_matching_loss": 0.193359375, "train_physics_loss": 0.0 }, { "grad_norm": 2.097046375274658, "learning_rate": 2.3e-06, "loss": 0.2583, "step": 70 }, { "step": 70, "train_flow_matching_loss": 0.2412109375, "train_physics_loss": 0.0 }, { "grad_norm": 2.097332239151001, "learning_rate": 2.6333333333333337e-06, "loss": 0.2466, "step": 80 }, { "step": 80, "train_flow_matching_loss": 0.1591796875, "train_physics_loss": 0.0 }, { "grad_norm": 1.5931936502456665, "learning_rate": 2.966666666666667e-06, "loss": 0.2396, "step": 90 }, { "step": 90, "train_flow_matching_loss": 0.193359375, "train_physics_loss": 1.241982102394104 }, { "grad_norm": 0.4996283948421478, "learning_rate": 3.3e-06, "loss": 0.2646, "step": 100 }, { "step": 100, "train_flow_matching_loss": 0.212890625, "train_physics_loss": 0.0 }, { "grad_norm": 0.8610798120498657, "learning_rate": 3.633333333333334e-06, "loss": 0.2498, "step": 110 }, { "step": 110, "train_flow_matching_loss": 0.193359375, "train_physics_loss": 0.0 }, { "grad_norm": 0.8145138621330261, "learning_rate": 3.966666666666667e-06, "loss": 0.2608, "step": 120 }, { "step": 120, "train_flow_matching_loss": 0.2041015625, "train_physics_loss": 0.0 }, { "grad_norm": 0.5870611071586609, "learning_rate": 4.2999999999999995e-06, "loss": 0.2163, "step": 130 }, { "step": 130, "train_flow_matching_loss": 0.294921875, "train_physics_loss": 1.3060048818588257 }, { "grad_norm": 0.4015425741672516, "learning_rate": 4.633333333333334e-06, "loss": 0.2404, "step": 140 }, { "step": 140, "train_flow_matching_loss": 0.2021484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.8249984383583069, "learning_rate": 4.966666666666667e-06, "loss": 0.2589, "step": 150 }, { "step": 150, "train_flow_matching_loss": 0.181640625, "train_physics_loss": 0.0 }, { "grad_norm": 0.8456190228462219, "learning_rate": 5.3e-06, "loss": 0.245, "step": 160 }, { "step": 160, "train_flow_matching_loss": 0.197265625, "train_physics_loss": 0.0 }, { "grad_norm": 0.5049912929534912, "learning_rate": 5.633333333333333e-06, "loss": 0.2202, "step": 170 }, { "step": 170, "train_flow_matching_loss": 0.33984375, "train_physics_loss": 1.0072226524353027 }, { "grad_norm": 0.3911513686180115, "learning_rate": 5.9666666666666666e-06, "loss": 0.2456, "step": 180 }, { "step": 180, "train_flow_matching_loss": 0.1611328125, "train_physics_loss": 0.0 }, { "grad_norm": 0.4234141707420349, "learning_rate": 6.300000000000001e-06, "loss": 0.2408, "step": 190 }, { "step": 190, "train_flow_matching_loss": 0.181640625, "train_physics_loss": 0.0 }, { "grad_norm": 0.4998401701450348, "learning_rate": 6.633333333333333e-06, "loss": 0.2404, "step": 200 }, { "step": 200, "train_flow_matching_loss": 0.2099609375, "train_physics_loss": 0.0 }, { "grad_norm": 0.3860056698322296, "learning_rate": 6.966666666666667e-06, "loss": 0.218, "step": 210 }, { "step": 210, "train_flow_matching_loss": 0.1806640625, "train_physics_loss": 1.2362585067749023 }, { "grad_norm": 0.23343786597251892, "learning_rate": 7.2999999999999996e-06, "loss": 0.2417, "step": 220 }, { "step": 220, "train_flow_matching_loss": 0.1669921875, "train_physics_loss": 0.0 }, { "grad_norm": 0.4194835126399994, "learning_rate": 7.633333333333334e-06, "loss": 0.2401, "step": 230 }, { "step": 230, "train_flow_matching_loss": 0.1884765625, "train_physics_loss": 0.0 }, { "grad_norm": 0.34282320737838745, "learning_rate": 7.966666666666666e-06, "loss": 0.2376, "step": 240 }, { "step": 240, "train_flow_matching_loss": 0.142578125, "train_physics_loss": 0.0 }, { "grad_norm": 0.3080269992351532, "learning_rate": 8.3e-06, "loss": 0.2253, "step": 250 }, { "step": 250, "train_flow_matching_loss": 0.1728515625, "train_physics_loss": 1.1502143144607544 }, { "grad_norm": 0.2572602331638336, "learning_rate": 8.633333333333334e-06, "loss": 0.2245, "step": 260 }, { "step": 260, "train_flow_matching_loss": 0.232421875, "train_physics_loss": 0.0 }, { "grad_norm": 0.3650667071342468, "learning_rate": 8.966666666666668e-06, "loss": 0.2423, "step": 270 }, { "step": 270, "train_flow_matching_loss": 0.205078125, "train_physics_loss": 0.0 }, { "grad_norm": 0.3034899830818176, "learning_rate": 9.3e-06, "loss": 0.2305, "step": 280 }, { "step": 280, "train_flow_matching_loss": 0.259765625, "train_physics_loss": 0.0 }, { "grad_norm": 0.5119873881340027, "learning_rate": 9.633333333333335e-06, "loss": 0.2384, "step": 290 }, { "step": 290, "train_flow_matching_loss": 0.138671875, "train_physics_loss": 1.1380618810653687 }, { "grad_norm": 0.3853524923324585, "learning_rate": 9.966666666666667e-06, "loss": 0.2341, "step": 300 }, { "step": 300, "train_flow_matching_loss": 0.140625, "train_physics_loss": 0.0 }, { "grad_norm": 0.37617555260658264, "learning_rate": 1.03e-05, "loss": 0.2242, "step": 310 }, { "step": 310, "train_flow_matching_loss": 0.1787109375, "train_physics_loss": 0.0 }, { "grad_norm": 0.37467101216316223, "learning_rate": 1.0633333333333334e-05, "loss": 0.223, "step": 320 }, { "step": 320, "train_flow_matching_loss": 0.1845703125, "train_physics_loss": 0.0 }, { "grad_norm": 0.24817711114883423, "learning_rate": 1.0966666666666666e-05, "loss": 0.2219, "step": 330 }, { "step": 330, "train_flow_matching_loss": 0.251953125, "train_physics_loss": 1.1071827411651611 }, { "grad_norm": 0.2167033553123474, "learning_rate": 1.13e-05, "loss": 0.2104, "step": 340 }, { "step": 340, "train_flow_matching_loss": 0.1943359375, "train_physics_loss": 0.0 }, { "grad_norm": 0.5935896635055542, "learning_rate": 1.1633333333333334e-05, "loss": 0.2388, "step": 350 }, { "step": 350, "train_flow_matching_loss": 0.154296875, "train_physics_loss": 0.0 }, { "grad_norm": 0.350766658782959, "learning_rate": 1.1966666666666668e-05, "loss": 0.22, "step": 360 }, { "step": 360, "train_flow_matching_loss": 0.279296875, "train_physics_loss": 0.0 }, { "grad_norm": 0.24915441870689392, "learning_rate": 1.23e-05, "loss": 0.2195, "step": 370 }, { "step": 370, "train_flow_matching_loss": 0.43359375, "train_physics_loss": 0.0 }, { "grad_norm": 0.3285883367061615, "learning_rate": 1.2633333333333333e-05, "loss": 0.2257, "step": 380 }, { "step": 380, "train_flow_matching_loss": 0.1455078125, "train_physics_loss": 0.0 }, { "grad_norm": 0.2852630615234375, "learning_rate": 1.2966666666666669e-05, "loss": 0.2277, "step": 390 }, { "step": 390, "train_flow_matching_loss": 0.11669921875, "train_physics_loss": 0.0 }, { "grad_norm": 0.17581817507743835, "learning_rate": 1.3300000000000001e-05, "loss": 0.2136, "step": 400 }, { "step": 400, "train_flow_matching_loss": 0.2021484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.27428138256073, "learning_rate": 1.3633333333333334e-05, "loss": 0.2146, "step": 410 }, { "step": 410, "train_flow_matching_loss": 0.296875, "train_physics_loss": 1.2539079189300537 }, { "grad_norm": 0.16316437721252441, "learning_rate": 1.3966666666666666e-05, "loss": 0.2154, "step": 420 }, { "step": 420, "train_flow_matching_loss": 0.1630859375, "train_physics_loss": 0.0 }, { "grad_norm": 0.815127432346344, "learning_rate": 1.43e-05, "loss": 0.2357, "step": 430 }, { "step": 430, "train_flow_matching_loss": 0.318359375, "train_physics_loss": 0.0 }, { "grad_norm": 0.460473895072937, "learning_rate": 1.4633333333333334e-05, "loss": 0.2258, "step": 440 }, { "step": 440, "train_flow_matching_loss": 0.234375, "train_physics_loss": 0.0 }, { "grad_norm": 0.1416216492652893, "learning_rate": 1.4966666666666668e-05, "loss": 0.2165, "step": 450 }, { "step": 450, "train_flow_matching_loss": 0.34375, "train_physics_loss": 0.9498165249824524 }, { "grad_norm": 0.24502915143966675, "learning_rate": 1.53e-05, "loss": 0.2286, "step": 460 }, { "step": 460, "train_flow_matching_loss": 0.1494140625, "train_physics_loss": 0.0 }, { "grad_norm": 0.2592589259147644, "learning_rate": 1.563333333333333e-05, "loss": 0.2263, "step": 470 }, { "step": 470, "train_flow_matching_loss": 0.1796875, "train_physics_loss": 0.0 }, { "grad_norm": 0.90907883644104, "learning_rate": 1.5966666666666667e-05, "loss": 0.2325, "step": 480 }, { "step": 480, "train_flow_matching_loss": 0.244140625, "train_physics_loss": 0.0 }, { "grad_norm": 0.2792417109012604, "learning_rate": 1.63e-05, "loss": 0.2354, "step": 490 }, { "step": 490, "train_flow_matching_loss": 0.310546875, "train_physics_loss": 1.0009559392929077 }, { "grad_norm": 0.26415398716926575, "learning_rate": 1.6633333333333336e-05, "loss": 0.2251, "step": 500 }, { "step": 500, "train_flow_matching_loss": 0.1552734375, "train_physics_loss": 0.0 }, { "grad_norm": 0.1738256961107254, "learning_rate": 1.6966666666666668e-05, "loss": 0.2237, "step": 510 }, { "step": 510, "train_flow_matching_loss": 0.208984375, "train_physics_loss": 0.0 }, { "grad_norm": 0.19109994173049927, "learning_rate": 1.73e-05, "loss": 0.2211, "step": 520 }, { "step": 520, "train_flow_matching_loss": 0.177734375, "train_physics_loss": 0.0 }, { "grad_norm": 0.19409514963626862, "learning_rate": 1.7633333333333336e-05, "loss": 0.221, "step": 530 }, { "step": 530, "train_flow_matching_loss": 0.2314453125, "train_physics_loss": 1.2211284637451172 }, { "grad_norm": 0.15948127210140228, "learning_rate": 1.796666666666667e-05, "loss": 0.2248, "step": 540 }, { "step": 540, "train_flow_matching_loss": 0.181640625, "train_physics_loss": 0.0 }, { "grad_norm": 0.18917964398860931, "learning_rate": 1.83e-05, "loss": 0.2302, "step": 550 }, { "step": 550, "train_flow_matching_loss": 0.25390625, "train_physics_loss": 0.0 }, { "grad_norm": 0.367927223443985, "learning_rate": 1.8633333333333333e-05, "loss": 0.2435, "step": 560 }, { "step": 560, "train_flow_matching_loss": 0.1357421875, "train_physics_loss": 0.0 }, { "grad_norm": 0.16830769181251526, "learning_rate": 1.896666666666667e-05, "loss": 0.216, "step": 570 }, { "step": 570, "train_flow_matching_loss": 0.1708984375, "train_physics_loss": 1.1493914127349854 }, { "grad_norm": 0.2152395248413086, "learning_rate": 1.93e-05, "loss": 0.2205, "step": 580 }, { "step": 580, "train_flow_matching_loss": 0.140625, "train_physics_loss": 0.0 }, { "grad_norm": 0.22404998540878296, "learning_rate": 1.9633333333333334e-05, "loss": 0.2322, "step": 590 }, { "step": 590, "train_flow_matching_loss": 0.2314453125, "train_physics_loss": 0.0 }, { "grad_norm": 0.23788565397262573, "learning_rate": 1.9966666666666666e-05, "loss": 0.2235, "step": 600 }, { "step": 600, "train_flow_matching_loss": 0.185546875, "train_physics_loss": 0.0 }, { "grad_norm": 0.14863210916519165, "learning_rate": 2.0300000000000002e-05, "loss": 0.2163, "step": 610 }, { "step": 610, "train_flow_matching_loss": 0.220703125, "train_physics_loss": 0.9689019918441772 }, { "grad_norm": 0.11917997896671295, "learning_rate": 2.0633333333333335e-05, "loss": 0.2123, "step": 620 }, { "step": 620, "train_flow_matching_loss": 0.302734375, "train_physics_loss": 0.0 }, { "grad_norm": 0.23156337440013885, "learning_rate": 2.0966666666666667e-05, "loss": 0.2265, "step": 630 }, { "step": 630, "train_flow_matching_loss": 0.240234375, "train_physics_loss": 0.0 }, { "grad_norm": 0.21961408853530884, "learning_rate": 2.13e-05, "loss": 0.2207, "step": 640 }, { "step": 640, "train_flow_matching_loss": 0.224609375, "train_physics_loss": 0.0 }, { "grad_norm": 0.1400945484638214, "learning_rate": 2.1633333333333332e-05, "loss": 0.2121, "step": 650 }, { "step": 650, "train_flow_matching_loss": 0.322265625, "train_physics_loss": 1.0760555267333984 }, { "grad_norm": 0.18436451256275177, "learning_rate": 2.1966666666666668e-05, "loss": 0.2279, "step": 660 }, { "step": 660, "train_flow_matching_loss": 0.2060546875, "train_physics_loss": 0.0 }, { "grad_norm": 0.19369827210903168, "learning_rate": 2.23e-05, "loss": 0.2094, "step": 670 }, { "step": 670, "train_flow_matching_loss": 0.2451171875, "train_physics_loss": 0.0 }, { "grad_norm": 0.1745651811361313, "learning_rate": 2.2633333333333336e-05, "loss": 0.2323, "step": 680 }, { "step": 680, "train_flow_matching_loss": 0.1689453125, "train_physics_loss": 0.0 }, { "grad_norm": 0.22019273042678833, "learning_rate": 2.2966666666666668e-05, "loss": 0.2192, "step": 690 }, { "step": 690, "train_flow_matching_loss": 0.234375, "train_physics_loss": 1.089104175567627 }, { "grad_norm": 0.12370491772890091, "learning_rate": 2.3300000000000004e-05, "loss": 0.234, "step": 700 }, { "step": 700, "train_flow_matching_loss": 0.2138671875, "train_physics_loss": 0.0 }, { "grad_norm": 0.2408670336008072, "learning_rate": 2.3633333333333336e-05, "loss": 0.2253, "step": 710 }, { "step": 710, "train_flow_matching_loss": 0.2255859375, "train_physics_loss": 0.0 }, { "grad_norm": 0.16252945363521576, "learning_rate": 2.396666666666667e-05, "loss": 0.2238, "step": 720 }, { "step": 720, "train_flow_matching_loss": 0.1806640625, "train_physics_loss": 0.0 }, { "grad_norm": 0.11820516735315323, "learning_rate": 2.43e-05, "loss": 0.2215, "step": 730 }, { "step": 730, "train_flow_matching_loss": 0.1806640625, "train_physics_loss": 1.0379387140274048 }, { "grad_norm": 0.20267561078071594, "learning_rate": 2.4633333333333334e-05, "loss": 0.2231, "step": 740 }, { "step": 740, "train_flow_matching_loss": 0.2392578125, "train_physics_loss": 0.0 }, { "grad_norm": 0.2036902904510498, "learning_rate": 2.496666666666667e-05, "loss": 0.2372, "step": 750 }, { "step": 750, "train_flow_matching_loss": 0.1904296875, "train_physics_loss": 0.0 }, { "grad_norm": 0.270289808511734, "learning_rate": 2.5300000000000002e-05, "loss": 0.2215, "step": 760 }, { "step": 760, "train_flow_matching_loss": 0.1533203125, "train_physics_loss": 0.0 }, { "grad_norm": 0.13340096175670624, "learning_rate": 2.5633333333333338e-05, "loss": 0.2246, "step": 770 }, { "step": 770, "train_flow_matching_loss": 0.1689453125, "train_physics_loss": 1.0493122339248657 }, { "grad_norm": 0.13536763191223145, "learning_rate": 2.5966666666666667e-05, "loss": 0.2324, "step": 780 }, { "step": 780, "train_flow_matching_loss": 0.1904296875, "train_physics_loss": 0.0 }, { "grad_norm": 0.14027945697307587, "learning_rate": 2.6300000000000002e-05, "loss": 0.2158, "step": 790 }, { "step": 790, "train_flow_matching_loss": 0.2197265625, "train_physics_loss": 0.0 }, { "grad_norm": 0.23080722987651825, "learning_rate": 2.663333333333333e-05, "loss": 0.215, "step": 800 }, { "step": 800, "train_flow_matching_loss": 0.1748046875, "train_physics_loss": 0.0 }, { "grad_norm": 0.12672141194343567, "learning_rate": 2.6966666666666667e-05, "loss": 0.2059, "step": 810 }, { "step": 810, "train_flow_matching_loss": 0.1005859375, "train_physics_loss": 1.0300136804580688 }, { "grad_norm": 0.14777213335037231, "learning_rate": 2.7300000000000003e-05, "loss": 0.2307, "step": 820 }, { "step": 820, "train_flow_matching_loss": 0.25390625, "train_physics_loss": 0.0 }, { "grad_norm": 0.24080197513103485, "learning_rate": 2.7633333333333332e-05, "loss": 0.2369, "step": 830 }, { "step": 830, "train_flow_matching_loss": 0.2431640625, "train_physics_loss": 0.0 }, { "grad_norm": 0.2703765630722046, "learning_rate": 2.7966666666666668e-05, "loss": 0.214, "step": 840 }, { "step": 840, "train_flow_matching_loss": 0.228515625, "train_physics_loss": 0.0 }, { "grad_norm": 0.21210747957229614, "learning_rate": 2.83e-05, "loss": 0.2176, "step": 850 }, { "step": 850, "train_flow_matching_loss": 0.1904296875, "train_physics_loss": 1.1258294582366943 }, { "grad_norm": 0.19727841019630432, "learning_rate": 2.8633333333333336e-05, "loss": 0.2321, "step": 860 }, { "step": 860, "train_flow_matching_loss": 0.345703125, "train_physics_loss": 0.0 }, { "grad_norm": 0.17061693966388702, "learning_rate": 2.8966666666666668e-05, "loss": 0.2445, "step": 870 }, { "step": 870, "train_flow_matching_loss": 0.1552734375, "train_physics_loss": 0.0 }, { "grad_norm": 0.13961118459701538, "learning_rate": 2.93e-05, "loss": 0.2176, "step": 880 }, { "step": 880, "train_flow_matching_loss": 0.2265625, "train_physics_loss": 0.0 }, { "grad_norm": 0.21723823249340057, "learning_rate": 2.9633333333333336e-05, "loss": 0.216, "step": 890 }, { "step": 890, "train_flow_matching_loss": 0.1787109375, "train_physics_loss": 1.0784062147140503 }, { "grad_norm": 0.1270458996295929, "learning_rate": 2.9966666666666672e-05, "loss": 0.2123, "step": 900 }, { "step": 900, "train_flow_matching_loss": 0.1806640625, "train_physics_loss": 0.0 }, { "grad_norm": 0.29031702876091003, "learning_rate": 3.03e-05, "loss": 0.2136, "step": 910 }, { "step": 910, "train_flow_matching_loss": 0.2099609375, "train_physics_loss": 0.0 }, { "grad_norm": 0.16241152584552765, "learning_rate": 3.063333333333334e-05, "loss": 0.2122, "step": 920 }, { "step": 920, "train_flow_matching_loss": 0.263671875, "train_physics_loss": 0.0 }, { "grad_norm": 0.1760573536157608, "learning_rate": 3.096666666666666e-05, "loss": 0.2106, "step": 930 }, { "step": 930, "train_flow_matching_loss": 0.27734375, "train_physics_loss": 1.1044496297836304 }, { "grad_norm": 0.10349904000759125, "learning_rate": 3.13e-05, "loss": 0.2143, "step": 940 }, { "step": 940, "train_flow_matching_loss": 0.2119140625, "train_physics_loss": 0.0 }, { "grad_norm": 0.1912197321653366, "learning_rate": 3.1633333333333334e-05, "loss": 0.2239, "step": 950 }, { "step": 950, "train_flow_matching_loss": 0.2138671875, "train_physics_loss": 0.0 }, { "grad_norm": 0.12100717425346375, "learning_rate": 3.196666666666667e-05, "loss": 0.2167, "step": 960 }, { "step": 960, "train_flow_matching_loss": 0.146484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.10931448638439178, "learning_rate": 3.2300000000000006e-05, "loss": 0.2247, "step": 970 }, { "step": 970, "train_flow_matching_loss": 0.400390625, "train_physics_loss": 1.1122357845306396 }, { "grad_norm": 0.13774625957012177, "learning_rate": 3.263333333333333e-05, "loss": 0.214, "step": 980 }, { "step": 980, "train_flow_matching_loss": 0.2333984375, "train_physics_loss": 0.0 }, { "grad_norm": 0.13239137828350067, "learning_rate": 3.296666666666667e-05, "loss": 0.2072, "step": 990 }, { "step": 990, "train_flow_matching_loss": 0.12451171875, "train_physics_loss": 0.0 }, { "grad_norm": 0.17724885046482086, "learning_rate": 3.33e-05, "loss": 0.2073, "step": 1000 }, { "step": 1000, "train_flow_matching_loss": 0.208984375, "train_physics_loss": 0.0 }, { "grad_norm": 0.2090594619512558, "learning_rate": 3.3633333333333335e-05, "loss": 0.2062, "step": 1010 }, { "step": 1010, "train_flow_matching_loss": 0.3125, "train_physics_loss": 1.145290732383728 }, { "grad_norm": 0.08525966852903366, "learning_rate": 3.396666666666667e-05, "loss": 0.2251, "step": 1020 }, { "step": 1020, "train_flow_matching_loss": 0.30859375, "train_physics_loss": 0.0 }, { "grad_norm": 0.1390378624200821, "learning_rate": 3.430000000000001e-05, "loss": 0.2033, "step": 1030 }, { "step": 1030, "train_flow_matching_loss": 0.2109375, "train_physics_loss": 0.0 }, { "grad_norm": 0.13995292782783508, "learning_rate": 3.463333333333333e-05, "loss": 0.2123, "step": 1040 }, { "step": 1040, "train_flow_matching_loss": 0.232421875, "train_physics_loss": 0.0 }, { "grad_norm": 0.12666690349578857, "learning_rate": 3.496666666666667e-05, "loss": 0.2082, "step": 1050 }, { "step": 1050, "train_flow_matching_loss": 0.2060546875, "train_physics_loss": 0.0 }, { "grad_norm": 0.15384529531002045, "learning_rate": 3.53e-05, "loss": 0.1987, "step": 1060 }, { "step": 1060, "train_flow_matching_loss": 0.1708984375, "train_physics_loss": 0.0 }, { "grad_norm": 0.16806060075759888, "learning_rate": 3.563333333333334e-05, "loss": 0.2176, "step": 1070 }, { "step": 1070, "train_flow_matching_loss": 0.26953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.15492193400859833, "learning_rate": 3.596666666666667e-05, "loss": 0.2074, "step": 1080 }, { "step": 1080, "train_flow_matching_loss": 0.1796875, "train_physics_loss": 0.0 }, { "grad_norm": 0.15594938397407532, "learning_rate": 3.63e-05, "loss": 0.2124, "step": 1090 }, { "step": 1090, "train_flow_matching_loss": 0.2177734375, "train_physics_loss": 0.0 }, { "grad_norm": 0.15019504725933075, "learning_rate": 3.6633333333333334e-05, "loss": 0.2087, "step": 1100 }, { "step": 1100, "train_flow_matching_loss": 0.263671875, "train_physics_loss": 0.0 }, { "grad_norm": 0.17234057188034058, "learning_rate": 3.6966666666666666e-05, "loss": 0.2213, "step": 1110 }, { "step": 1110, "train_flow_matching_loss": 0.1533203125, "train_physics_loss": 0.0 }, { "grad_norm": 0.14086493849754333, "learning_rate": 3.73e-05, "loss": 0.1898, "step": 1120 }, { "step": 1120, "train_flow_matching_loss": 0.2314453125, "train_physics_loss": 0.0 }, { "grad_norm": 0.11141461879014969, "learning_rate": 3.763333333333334e-05, "loss": 0.2035, "step": 1130 }, { "step": 1130, "train_flow_matching_loss": 0.197265625, "train_physics_loss": 0.0 }, { "grad_norm": 0.14054706692695618, "learning_rate": 3.796666666666667e-05, "loss": 0.221, "step": 1140 }, { "step": 1140, "train_flow_matching_loss": 0.1796875, "train_physics_loss": 0.0 }, { "grad_norm": 0.14932797849178314, "learning_rate": 3.83e-05, "loss": 0.2066, "step": 1150 }, { "step": 1150, "train_flow_matching_loss": 0.197265625, "train_physics_loss": 0.0 }, { "grad_norm": 0.16277743875980377, "learning_rate": 3.8633333333333335e-05, "loss": 0.2111, "step": 1160 }, { "step": 1160, "train_flow_matching_loss": 0.142578125, "train_physics_loss": 0.0 }, { "grad_norm": 0.11082006990909576, "learning_rate": 3.896666666666667e-05, "loss": 0.1903, "step": 1170 }, { "step": 1170, "train_flow_matching_loss": 0.154296875, "train_physics_loss": 0.0 }, { "grad_norm": 0.13360130786895752, "learning_rate": 3.9300000000000007e-05, "loss": 0.2081, "step": 1180 }, { "step": 1180, "train_flow_matching_loss": 0.1875, "train_physics_loss": 0.0 }, { "grad_norm": 0.1160450279712677, "learning_rate": 3.963333333333333e-05, "loss": 0.2051, "step": 1190 }, { "step": 1190, "train_flow_matching_loss": 0.251953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.22500337660312653, "learning_rate": 3.996666666666667e-05, "loss": 0.2066, "step": 1200 }, { "step": 1200, "train_flow_matching_loss": 0.1689453125, "train_physics_loss": 0.0 }, { "grad_norm": 0.053447406738996506, "learning_rate": 4.0300000000000004e-05, "loss": 0.1995, "step": 1210 }, { "step": 1210, "train_flow_matching_loss": 0.1748046875, "train_physics_loss": 0.0 }, { "grad_norm": 0.11647965013980865, "learning_rate": 4.0633333333333336e-05, "loss": 0.2001, "step": 1220 }, { "step": 1220, "train_flow_matching_loss": 0.2255859375, "train_physics_loss": 0.0 }, { "grad_norm": 0.09430884569883347, "learning_rate": 4.096666666666667e-05, "loss": 0.2105, "step": 1230 }, { "step": 1230, "train_flow_matching_loss": 0.2119140625, "train_physics_loss": 0.0 }, { "grad_norm": 0.11110495775938034, "learning_rate": 4.13e-05, "loss": 0.2161, "step": 1240 }, { "step": 1240, "train_flow_matching_loss": 0.2294921875, "train_physics_loss": 0.0 }, { "grad_norm": 0.16343960165977478, "learning_rate": 4.1633333333333333e-05, "loss": 0.2078, "step": 1250 }, { "step": 1250, "train_flow_matching_loss": 0.1845703125, "train_physics_loss": 0.0 }, { "grad_norm": 0.1585990935564041, "learning_rate": 4.196666666666667e-05, "loss": 0.2176, "step": 1260 }, { "step": 1260, "train_flow_matching_loss": 0.26171875, "train_physics_loss": 0.0 }, { "grad_norm": 0.20427796244621277, "learning_rate": 4.23e-05, "loss": 0.197, "step": 1270 }, { "step": 1270, "train_flow_matching_loss": 0.1875, "train_physics_loss": 0.0 }, { "grad_norm": 0.12090642005205154, "learning_rate": 4.263333333333334e-05, "loss": 0.2063, "step": 1280 }, { "step": 1280, "train_flow_matching_loss": 0.1650390625, "train_physics_loss": 0.0 }, { "grad_norm": 0.1141805648803711, "learning_rate": 4.296666666666666e-05, "loss": 0.205, "step": 1290 }, { "step": 1290, "train_flow_matching_loss": 0.216796875, "train_physics_loss": 0.0 }, { "grad_norm": 0.08371470123529434, "learning_rate": 4.33e-05, "loss": 0.194, "step": 1300 }, { "step": 1300, "train_flow_matching_loss": 0.1640625, "train_physics_loss": 0.0 }, { "grad_norm": 0.1054680347442627, "learning_rate": 4.3633333333333335e-05, "loss": 0.2078, "step": 1310 }, { "step": 1310, "train_flow_matching_loss": 0.11767578125, "train_physics_loss": 0.0 }, { "grad_norm": 0.13427715003490448, "learning_rate": 4.396666666666667e-05, "loss": 0.2048, "step": 1320 }, { "step": 1320, "train_flow_matching_loss": 0.1962890625, "train_physics_loss": 0.0 }, { "grad_norm": 0.09480952471494675, "learning_rate": 4.43e-05, "loss": 0.2011, "step": 1330 }, { "step": 1330, "train_flow_matching_loss": 0.166015625, "train_physics_loss": 0.0 }, { "grad_norm": 0.13772359490394592, "learning_rate": 4.463333333333334e-05, "loss": 0.2137, "step": 1340 }, { "step": 1340, "train_flow_matching_loss": 0.1767578125, "train_physics_loss": 0.0 }, { "grad_norm": 0.11068810522556305, "learning_rate": 4.496666666666667e-05, "loss": 0.2063, "step": 1350 }, { "step": 1350, "train_flow_matching_loss": 0.1396484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.1888248175382614, "learning_rate": 4.53e-05, "loss": 0.2023, "step": 1360 }, { "step": 1360, "train_flow_matching_loss": 0.1357421875, "train_physics_loss": 0.0 }, { "grad_norm": 0.07723519206047058, "learning_rate": 4.5633333333333336e-05, "loss": 0.1973, "step": 1370 }, { "step": 1370, "train_flow_matching_loss": 0.146484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.1305299997329712, "learning_rate": 4.596666666666667e-05, "loss": 0.2043, "step": 1380 }, { "step": 1380, "train_flow_matching_loss": 0.15625, "train_physics_loss": 0.0 }, { "grad_norm": 0.12131906300783157, "learning_rate": 4.630000000000001e-05, "loss": 0.2034, "step": 1390 }, { "step": 1390, "train_flow_matching_loss": 0.2041015625, "train_physics_loss": 0.0 }, { "grad_norm": 0.07614162564277649, "learning_rate": 4.663333333333333e-05, "loss": 0.2011, "step": 1400 }, { "step": 1400, "train_flow_matching_loss": 0.1611328125, "train_physics_loss": 0.0 }, { "grad_norm": 0.14064112305641174, "learning_rate": 4.696666666666667e-05, "loss": 0.1985, "step": 1410 }, { "step": 1410, "train_flow_matching_loss": 0.2177734375, "train_physics_loss": 0.0 }, { "grad_norm": 0.16853322088718414, "learning_rate": 4.73e-05, "loss": 0.2156, "step": 1420 }, { "step": 1420, "train_flow_matching_loss": 0.232421875, "train_physics_loss": 0.0 }, { "grad_norm": 0.19376951456069946, "learning_rate": 4.763333333333334e-05, "loss": 0.213, "step": 1430 }, { "step": 1430, "train_flow_matching_loss": 0.244140625, "train_physics_loss": 0.0 }, { "grad_norm": 0.15284070372581482, "learning_rate": 4.796666666666667e-05, "loss": 0.2106, "step": 1440 }, { "step": 1440, "train_flow_matching_loss": 0.1953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.09303344041109085, "learning_rate": 4.83e-05, "loss": 0.1973, "step": 1450 }, { "step": 1450, "train_flow_matching_loss": 0.125, "train_physics_loss": 0.0 }, { "grad_norm": 0.13489674031734467, "learning_rate": 4.8633333333333334e-05, "loss": 0.2072, "step": 1460 }, { "step": 1460, "train_flow_matching_loss": 0.271484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.18141049146652222, "learning_rate": 4.8966666666666667e-05, "loss": 0.2152, "step": 1470 }, { "step": 1470, "train_flow_matching_loss": 0.1357421875, "train_physics_loss": 0.0 }, { "grad_norm": 0.10011886060237885, "learning_rate": 4.93e-05, "loss": 0.1937, "step": 1480 }, { "step": 1480, "train_flow_matching_loss": 0.2333984375, "train_physics_loss": 0.0 }, { "grad_norm": 0.28559961915016174, "learning_rate": 4.963333333333334e-05, "loss": 0.1901, "step": 1490 }, { "step": 1490, "train_flow_matching_loss": 0.1875, "train_physics_loss": 0.0 }, { "grad_norm": 0.14008218050003052, "learning_rate": 4.996666666666667e-05, "loss": 0.2107, "step": 1500 }, { "step": 1500, "train_flow_matching_loss": 0.1806640625, "train_physics_loss": 0.0 }, { "grad_norm": 0.17018763720989227, "learning_rate": 5e-05, "loss": 0.197, "step": 1510 }, { "step": 1510, "train_flow_matching_loss": 0.2138671875, "train_physics_loss": 0.0 }, { "grad_norm": 0.154103621840477, "learning_rate": 5e-05, "loss": 0.2081, "step": 1520 }, { "step": 1520, "train_flow_matching_loss": 0.1396484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.14880219101905823, "learning_rate": 5e-05, "loss": 0.1974, "step": 1530 }, { "step": 1530, "train_flow_matching_loss": 0.275390625, "train_physics_loss": 0.0 }, { "grad_norm": 0.25544485449790955, "learning_rate": 5e-05, "loss": 0.1984, "step": 1540 }, { "step": 1540, "train_flow_matching_loss": 0.166015625, "train_physics_loss": 0.0 }, { "grad_norm": 0.08390001207590103, "learning_rate": 5e-05, "loss": 0.1951, "step": 1550 }, { "step": 1550, "train_flow_matching_loss": 0.205078125, "train_physics_loss": 0.0 }, { "grad_norm": 0.16957859694957733, "learning_rate": 5e-05, "loss": 0.2179, "step": 1560 }, { "step": 1560, "train_flow_matching_loss": 0.193359375, "train_physics_loss": 0.0 }, { "grad_norm": 0.12760458886623383, "learning_rate": 5e-05, "loss": 0.2061, "step": 1570 }, { "step": 1570, "train_flow_matching_loss": 0.28515625, "train_physics_loss": 0.0 }, { "grad_norm": 0.11256720870733261, "learning_rate": 5e-05, "loss": 0.1965, "step": 1580 }, { "step": 1580, "train_flow_matching_loss": 0.2294921875, "train_physics_loss": 0.0 }, { "grad_norm": 0.11947070062160492, "learning_rate": 5e-05, "loss": 0.206, "step": 1590 }, { "step": 1590, "train_flow_matching_loss": 0.1162109375, "train_physics_loss": 0.0 }, { "grad_norm": 0.20170576870441437, "learning_rate": 5e-05, "loss": 0.2077, "step": 1600 }, { "step": 1600, "train_flow_matching_loss": 0.1923828125, "train_physics_loss": 0.0 }, { "grad_norm": 0.08594629913568497, "learning_rate": 5e-05, "loss": 0.1819, "step": 1610 }, { "step": 1610, "train_flow_matching_loss": 0.1455078125, "train_physics_loss": 0.0 }, { "grad_norm": 0.11360633373260498, "learning_rate": 5e-05, "loss": 0.2008, "step": 1620 }, { "step": 1620, "train_flow_matching_loss": 0.29296875, "train_physics_loss": 0.0 }, { "grad_norm": 0.10472814738750458, "learning_rate": 5e-05, "loss": 0.2113, "step": 1630 }, { "step": 1630, "train_flow_matching_loss": 0.1484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.14456795156002045, "learning_rate": 5e-05, "loss": 0.2098, "step": 1640 }, { "step": 1640, "train_flow_matching_loss": 0.259765625, "train_physics_loss": 0.0 }, { "grad_norm": 0.1425119936466217, "learning_rate": 5e-05, "loss": 0.1898, "step": 1650 }, { "step": 1650, "train_flow_matching_loss": 0.2119140625, "train_physics_loss": 0.0 }, { "grad_norm": 0.12867321074008942, "learning_rate": 5e-05, "loss": 0.2064, "step": 1660 }, { "step": 1660, "train_flow_matching_loss": 0.158203125, "train_physics_loss": 0.0 }, { "grad_norm": 0.11371110379695892, "learning_rate": 5e-05, "loss": 0.1896, "step": 1670 }, { "step": 1670, "train_flow_matching_loss": 0.15625, "train_physics_loss": 0.0 }, { "grad_norm": 0.1063375398516655, "learning_rate": 5e-05, "loss": 0.2061, "step": 1680 }, { "step": 1680, "train_flow_matching_loss": 0.2236328125, "train_physics_loss": 0.0 }, { "grad_norm": 0.07955354452133179, "learning_rate": 5e-05, "loss": 0.1919, "step": 1690 }, { "step": 1690, "train_flow_matching_loss": 0.240234375, "train_physics_loss": 0.0 }, { "grad_norm": 0.23110023140907288, "learning_rate": 5e-05, "loss": 0.199, "step": 1700 }, { "step": 1700, "train_flow_matching_loss": 0.1904296875, "train_physics_loss": 0.0 }, { "grad_norm": 0.09667247533798218, "learning_rate": 5e-05, "loss": 0.2042, "step": 1710 }, { "step": 1710, "train_flow_matching_loss": 0.158203125, "train_physics_loss": 0.0 }, { "grad_norm": 0.16921964287757874, "learning_rate": 5e-05, "loss": 0.204, "step": 1720 }, { "step": 1720, "train_flow_matching_loss": 0.185546875, "train_physics_loss": 0.0 }, { "grad_norm": 0.08630548417568207, "learning_rate": 5e-05, "loss": 0.1975, "step": 1730 }, { "step": 1730, "train_flow_matching_loss": 0.1494140625, "train_physics_loss": 0.0 }, { "grad_norm": 0.1811220645904541, "learning_rate": 5e-05, "loss": 0.195, "step": 1740 }, { "step": 1740, "train_flow_matching_loss": 0.173828125, "train_physics_loss": 0.0 }, { "grad_norm": 0.07194963842630386, "learning_rate": 5e-05, "loss": 0.1875, "step": 1750 }, { "step": 1750, "train_flow_matching_loss": 0.142578125, "train_physics_loss": 0.0 }, { "grad_norm": 0.0755167230963707, "learning_rate": 5e-05, "loss": 0.2048, "step": 1760 }, { "step": 1760, "train_flow_matching_loss": 0.283203125, "train_physics_loss": 0.0 }, { "grad_norm": 0.09605410695075989, "learning_rate": 5e-05, "loss": 0.1931, "step": 1770 }, { "step": 1770, "train_flow_matching_loss": 0.2578125, "train_physics_loss": 0.0 }, { "grad_norm": 0.1389743685722351, "learning_rate": 5e-05, "loss": 0.2102, "step": 1780 }, { "step": 1780, "train_flow_matching_loss": 0.1240234375, "train_physics_loss": 0.0 }, { "grad_norm": 0.1709265261888504, "learning_rate": 5e-05, "loss": 0.1924, "step": 1790 }, { "step": 1790, "train_flow_matching_loss": 0.236328125, "train_physics_loss": 0.0 }, { "grad_norm": 0.10309681296348572, "learning_rate": 5e-05, "loss": 0.2078, "step": 1800 }, { "step": 1800, "train_flow_matching_loss": 0.21875, "train_physics_loss": 0.0 }, { "grad_norm": 0.0973629429936409, "learning_rate": 5e-05, "loss": 0.196, "step": 1810 }, { "step": 1810, "train_flow_matching_loss": 0.216796875, "train_physics_loss": 0.0 }, { "grad_norm": 0.19932492077350616, "learning_rate": 5e-05, "loss": 0.2043, "step": 1820 }, { "step": 1820, "train_flow_matching_loss": 0.1259765625, "train_physics_loss": 0.0 }, { "grad_norm": 0.05948347970843315, "learning_rate": 5e-05, "loss": 0.2076, "step": 1830 }, { "step": 1830, "train_flow_matching_loss": 0.158203125, "train_physics_loss": 0.0 }, { "grad_norm": 0.06767617911100388, "learning_rate": 5e-05, "loss": 0.2002, "step": 1840 }, { "step": 1840, "train_flow_matching_loss": 0.244140625, "train_physics_loss": 0.0 }, { "grad_norm": 0.08559475839138031, "learning_rate": 5e-05, "loss": 0.2145, "step": 1850 }, { "step": 1850, "train_flow_matching_loss": 0.1826171875, "train_physics_loss": 0.0 }, { "grad_norm": 0.09809610247612, "learning_rate": 5e-05, "loss": 0.2088, "step": 1860 }, { "step": 1860, "train_flow_matching_loss": 0.2001953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.08113548904657364, "learning_rate": 5e-05, "loss": 0.2, "step": 1870 }, { "step": 1870, "train_flow_matching_loss": 0.12353515625, "train_physics_loss": 0.0 }, { "grad_norm": 0.11370743811130524, "learning_rate": 5e-05, "loss": 0.1936, "step": 1880 }, { "step": 1880, "train_flow_matching_loss": 0.193359375, "train_physics_loss": 0.0 }, { "grad_norm": 0.1506226807832718, "learning_rate": 5e-05, "loss": 0.1925, "step": 1890 }, { "step": 1890, "train_flow_matching_loss": 0.1923828125, "train_physics_loss": 0.0 }, { "grad_norm": 0.1396436244249344, "learning_rate": 5e-05, "loss": 0.1994, "step": 1900 }, { "step": 1900, "train_flow_matching_loss": 0.1875, "train_physics_loss": 0.0 }, { "grad_norm": 0.0797683373093605, "learning_rate": 5e-05, "loss": 0.2171, "step": 1910 }, { "step": 1910, "train_flow_matching_loss": 0.1708984375, "train_physics_loss": 0.0 }, { "grad_norm": 0.09871801733970642, "learning_rate": 5e-05, "loss": 0.1956, "step": 1920 }, { "step": 1920, "train_flow_matching_loss": 0.2373046875, "train_physics_loss": 0.0 }, { "grad_norm": 0.09212425351142883, "learning_rate": 5e-05, "loss": 0.1978, "step": 1930 }, { "step": 1930, "train_flow_matching_loss": 0.1650390625, "train_physics_loss": 0.0 }, { "grad_norm": 0.12516924738883972, "learning_rate": 5e-05, "loss": 0.192, "step": 1940 }, { "step": 1940, "train_flow_matching_loss": 0.255859375, "train_physics_loss": 0.0 }, { "grad_norm": 0.09039215743541718, "learning_rate": 5e-05, "loss": 0.1953, "step": 1950 }, { "step": 1950, "train_flow_matching_loss": 0.1826171875, "train_physics_loss": 0.0 }, { "grad_norm": 0.16313427686691284, "learning_rate": 5e-05, "loss": 0.2007, "step": 1960 }, { "step": 1960, "train_flow_matching_loss": 0.271484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.09177539497613907, "learning_rate": 5e-05, "loss": 0.195, "step": 1970 }, { "step": 1970, "train_flow_matching_loss": 0.1533203125, "train_physics_loss": 0.0 }, { "grad_norm": 0.16960453987121582, "learning_rate": 5e-05, "loss": 0.212, "step": 1980 }, { "step": 1980, "train_flow_matching_loss": 0.197265625, "train_physics_loss": 0.0 }, { "grad_norm": 0.08709315955638885, "learning_rate": 5e-05, "loss": 0.1927, "step": 1990 }, { "step": 1990, "train_flow_matching_loss": 0.1923828125, "train_physics_loss": 0.0 }, { "grad_norm": 0.3476974666118622, "learning_rate": 5e-05, "loss": 0.2093, "step": 2000 }, { "step": 2000, "train_flow_matching_loss": 0.2412109375, "train_physics_loss": 0.0 }, { "grad_norm": 0.7255071401596069, "learning_rate": 5e-05, "loss": 0.2923, "step": 2010 }, { "step": 2010, "train_flow_matching_loss": 0.291015625, "train_physics_loss": 0.0 }, { "grad_norm": 0.5939329266548157, "learning_rate": 5e-05, "loss": 0.2738, "step": 2020 }, { "step": 2020, "train_flow_matching_loss": 0.1806640625, "train_physics_loss": 0.0 }, { "grad_norm": 0.5856655240058899, "learning_rate": 5e-05, "loss": 0.2476, "step": 2030 }, { "step": 2030, "train_flow_matching_loss": 0.146484375, "train_physics_loss": 0.0 }, { "grad_norm": 1.2197356224060059, "learning_rate": 5e-05, "loss": 0.2616, "step": 2040 }, { "step": 2040, "train_flow_matching_loss": 0.251953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.5224260091781616, "learning_rate": 5e-05, "loss": 0.2365, "step": 2050 }, { "step": 2050, "train_flow_matching_loss": 0.177734375, "train_physics_loss": 0.0 }, { "grad_norm": 0.7714827060699463, "learning_rate": 5e-05, "loss": 0.2357, "step": 2060 }, { "step": 2060, "train_flow_matching_loss": 0.193359375, "train_physics_loss": 0.0 }, { "grad_norm": 0.6806511878967285, "learning_rate": 5e-05, "loss": 0.2303, "step": 2070 }, { "step": 2070, "train_flow_matching_loss": 0.203125, "train_physics_loss": 0.0 }, { "grad_norm": 0.6126595735549927, "learning_rate": 5e-05, "loss": 0.2359, "step": 2080 }, { "step": 2080, "train_flow_matching_loss": 0.1611328125, "train_physics_loss": 0.0 }, { "grad_norm": 0.5415278077125549, "learning_rate": 5e-05, "loss": 0.2244, "step": 2090 }, { "step": 2090, "train_flow_matching_loss": 0.1953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.4795679450035095, "learning_rate": 5e-05, "loss": 0.2288, "step": 2100 }, { "step": 2100, "train_flow_matching_loss": 0.29296875, "train_physics_loss": 0.0 }, { "grad_norm": 0.5406513214111328, "learning_rate": 5e-05, "loss": 0.238, "step": 2110 }, { "step": 2110, "train_flow_matching_loss": 0.26171875, "train_physics_loss": 0.0 }, { "grad_norm": 0.5877923965454102, "learning_rate": 5e-05, "loss": 0.2291, "step": 2120 }, { "step": 2120, "train_flow_matching_loss": 0.333984375, "train_physics_loss": 0.0 }, { "grad_norm": 0.34861835837364197, "learning_rate": 5e-05, "loss": 0.2287, "step": 2130 }, { "step": 2130, "train_flow_matching_loss": 0.1689453125, "train_physics_loss": 0.0 }, { "grad_norm": 0.3895859122276306, "learning_rate": 5e-05, "loss": 0.1983, "step": 2140 }, { "step": 2140, "train_flow_matching_loss": 0.2578125, "train_physics_loss": 0.0 }, { "grad_norm": 0.565798282623291, "learning_rate": 5e-05, "loss": 0.2231, "step": 2150 }, { "step": 2150, "train_flow_matching_loss": 0.1591796875, "train_physics_loss": 0.0 }, { "grad_norm": 0.44795316457748413, "learning_rate": 5e-05, "loss": 0.2152, "step": 2160 }, { "step": 2160, "train_flow_matching_loss": 0.2021484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.6167258620262146, "learning_rate": 5e-05, "loss": 0.2073, "step": 2170 }, { "step": 2170, "train_flow_matching_loss": 0.2001953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.3856678307056427, "learning_rate": 5e-05, "loss": 0.2129, "step": 2180 }, { "step": 2180, "train_flow_matching_loss": 0.146484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.5398394465446472, "learning_rate": 5e-05, "loss": 0.2022, "step": 2190 }, { "step": 2190, "train_flow_matching_loss": 0.10791015625, "train_physics_loss": 0.0 }, { "grad_norm": 0.6242489814758301, "learning_rate": 5e-05, "loss": 0.2103, "step": 2200 }, { "step": 2200, "train_flow_matching_loss": 0.330078125, "train_physics_loss": 0.0 }, { "grad_norm": 0.4858343005180359, "learning_rate": 5e-05, "loss": 0.1993, "step": 2210 }, { "step": 2210, "train_flow_matching_loss": 0.1884765625, "train_physics_loss": 0.0 }, { "grad_norm": 0.6924743056297302, "learning_rate": 5e-05, "loss": 0.2084, "step": 2220 }, { "step": 2220, "train_flow_matching_loss": 0.26171875, "train_physics_loss": 0.0 }, { "grad_norm": 0.6019825339317322, "learning_rate": 5e-05, "loss": 0.2104, "step": 2230 }, { "step": 2230, "train_flow_matching_loss": 0.1376953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.5192358493804932, "learning_rate": 5e-05, "loss": 0.2023, "step": 2240 }, { "step": 2240, "train_flow_matching_loss": 0.201171875, "train_physics_loss": 0.0 }, { "grad_norm": 0.4772220253944397, "learning_rate": 5e-05, "loss": 0.2189, "step": 2250 }, { "step": 2250, "train_flow_matching_loss": 0.10205078125, "train_physics_loss": 0.0 }, { "grad_norm": 0.4331499934196472, "learning_rate": 5e-05, "loss": 0.2056, "step": 2260 }, { "step": 2260, "train_flow_matching_loss": 0.08251953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.44443851709365845, "learning_rate": 5e-05, "loss": 0.1979, "step": 2270 }, { "step": 2270, "train_flow_matching_loss": 0.1611328125, "train_physics_loss": 0.0 }, { "grad_norm": 0.5416576862335205, "learning_rate": 5e-05, "loss": 0.1995, "step": 2280 }, { "step": 2280, "train_flow_matching_loss": 0.2275390625, "train_physics_loss": 0.0 }, { "grad_norm": 0.6144620776176453, "learning_rate": 5e-05, "loss": 0.2119, "step": 2290 }, { "step": 2290, "train_flow_matching_loss": 0.10205078125, "train_physics_loss": 0.0 }, { "grad_norm": 0.5568708777427673, "learning_rate": 5e-05, "loss": 0.2091, "step": 2300 }, { "step": 2300, "train_flow_matching_loss": 0.15625, "train_physics_loss": 0.0 }, { "grad_norm": 0.533527672290802, "learning_rate": 5e-05, "loss": 0.2078, "step": 2310 }, { "step": 2310, "train_flow_matching_loss": 0.2138671875, "train_physics_loss": 0.0 }, { "grad_norm": 0.4842745363712311, "learning_rate": 5e-05, "loss": 0.2011, "step": 2320 }, { "step": 2320, "train_flow_matching_loss": 0.2080078125, "train_physics_loss": 0.0 }, { "grad_norm": 0.406303733587265, "learning_rate": 5e-05, "loss": 0.2083, "step": 2330 }, { "step": 2330, "train_flow_matching_loss": 0.271484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.5724268555641174, "learning_rate": 5e-05, "loss": 0.1993, "step": 2340 }, { "step": 2340, "train_flow_matching_loss": 0.1728515625, "train_physics_loss": 0.0 }, { "grad_norm": 0.5653353929519653, "learning_rate": 5e-05, "loss": 0.2018, "step": 2350 }, { "step": 2350, "train_flow_matching_loss": 0.2216796875, "train_physics_loss": 0.0 }, { "grad_norm": 0.5576412677764893, "learning_rate": 5e-05, "loss": 0.2066, "step": 2360 }, { "step": 2360, "train_flow_matching_loss": 0.1640625, "train_physics_loss": 0.0 }, { "grad_norm": 0.32648277282714844, "learning_rate": 5e-05, "loss": 0.1983, "step": 2370 }, { "step": 2370, "train_flow_matching_loss": 0.2255859375, "train_physics_loss": 0.0 }, { "grad_norm": 0.4026932120323181, "learning_rate": 5e-05, "loss": 0.2075, "step": 2380 }, { "step": 2380, "train_flow_matching_loss": 0.2001953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.4607785940170288, "learning_rate": 5e-05, "loss": 0.2036, "step": 2390 }, { "step": 2390, "train_flow_matching_loss": 0.162109375, "train_physics_loss": 0.0 }, { "grad_norm": 0.5389154553413391, "learning_rate": 5e-05, "loss": 0.2, "step": 2400 }, { "step": 2400, "train_flow_matching_loss": 0.2080078125, "train_physics_loss": 0.0 }, { "grad_norm": 0.3094935119152069, "learning_rate": 5e-05, "loss": 0.2066, "step": 2410 }, { "step": 2410, "train_flow_matching_loss": 0.1865234375, "train_physics_loss": 0.0 }, { "grad_norm": 0.30025774240493774, "learning_rate": 5e-05, "loss": 0.2276, "step": 2420 }, { "step": 2420, "train_flow_matching_loss": 0.1630859375, "train_physics_loss": 0.0 }, { "grad_norm": 0.5832370519638062, "learning_rate": 5e-05, "loss": 0.2029, "step": 2430 }, { "step": 2430, "train_flow_matching_loss": 0.1669921875, "train_physics_loss": 0.0 }, { "grad_norm": 0.48716628551483154, "learning_rate": 5e-05, "loss": 0.2189, "step": 2440 }, { "step": 2440, "train_flow_matching_loss": 0.1923828125, "train_physics_loss": 0.0 }, { "grad_norm": 0.5234631896018982, "learning_rate": 5e-05, "loss": 0.2035, "step": 2450 }, { "step": 2450, "train_flow_matching_loss": 0.255859375, "train_physics_loss": 0.0 }, { "grad_norm": 0.28142452239990234, "learning_rate": 5e-05, "loss": 0.1975, "step": 2460 }, { "step": 2460, "train_flow_matching_loss": 0.162109375, "train_physics_loss": 0.0 }, { "grad_norm": 0.43070247769355774, "learning_rate": 5e-05, "loss": 0.1958, "step": 2470 }, { "step": 2470, "train_flow_matching_loss": 0.2001953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.5085421800613403, "learning_rate": 5e-05, "loss": 0.2161, "step": 2480 }, { "step": 2480, "train_flow_matching_loss": 0.228515625, "train_physics_loss": 0.0 }, { "grad_norm": 0.5748714208602905, "learning_rate": 5e-05, "loss": 0.1906, "step": 2490 }, { "step": 2490, "train_flow_matching_loss": 0.1884765625, "train_physics_loss": 0.0 }, { "grad_norm": 0.27417269349098206, "learning_rate": 5e-05, "loss": 0.2005, "step": 2500 }, { "step": 2500, "train_flow_matching_loss": 0.1513671875, "train_physics_loss": 0.0 }, { "grad_norm": 0.42447590827941895, "learning_rate": 5e-05, "loss": 0.1875, "step": 2510 }, { "step": 2510, "train_flow_matching_loss": 0.125, "train_physics_loss": 0.0 }, { "grad_norm": 0.31858476996421814, "learning_rate": 5e-05, "loss": 0.1963, "step": 2520 }, { "step": 2520, "train_flow_matching_loss": 0.2177734375, "train_physics_loss": 0.0 }, { "grad_norm": 0.4768400192260742, "learning_rate": 5e-05, "loss": 0.1977, "step": 2530 }, { "step": 2530, "train_flow_matching_loss": 0.154296875, "train_physics_loss": 0.0 }, { "grad_norm": 0.3968905508518219, "learning_rate": 5e-05, "loss": 0.1927, "step": 2540 }, { "step": 2540, "train_flow_matching_loss": 0.193359375, "train_physics_loss": 0.0 }, { "grad_norm": 0.4107665419578552, "learning_rate": 5e-05, "loss": 0.1962, "step": 2550 }, { "step": 2550, "train_flow_matching_loss": 0.15625, "train_physics_loss": 0.0 }, { "grad_norm": 0.5272177457809448, "learning_rate": 5e-05, "loss": 0.1972, "step": 2560 }, { "step": 2560, "train_flow_matching_loss": 0.1396484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.5918838977813721, "learning_rate": 5e-05, "loss": 0.2133, "step": 2570 }, { "step": 2570, "train_flow_matching_loss": 0.173828125, "train_physics_loss": 0.0 }, { "grad_norm": 0.5348023772239685, "learning_rate": 5e-05, "loss": 0.2025, "step": 2580 }, { "step": 2580, "train_flow_matching_loss": 0.1611328125, "train_physics_loss": 0.0 }, { "grad_norm": 0.47232913970947266, "learning_rate": 5e-05, "loss": 0.1955, "step": 2590 }, { "step": 2590, "train_flow_matching_loss": 0.1337890625, "train_physics_loss": 0.0 }, { "grad_norm": 0.4018109142780304, "learning_rate": 5e-05, "loss": 0.191, "step": 2600 }, { "step": 2600, "train_flow_matching_loss": 0.2060546875, "train_physics_loss": 0.0 }, { "grad_norm": 0.3665876090526581, "learning_rate": 5e-05, "loss": 0.1998, "step": 2610 }, { "step": 2610, "train_flow_matching_loss": 0.208984375, "train_physics_loss": 0.0 }, { "grad_norm": 0.3991166949272156, "learning_rate": 5e-05, "loss": 0.1799, "step": 2620 }, { "step": 2620, "train_flow_matching_loss": 0.1845703125, "train_physics_loss": 0.0 }, { "grad_norm": 0.3932301700115204, "learning_rate": 5e-05, "loss": 0.1942, "step": 2630 }, { "step": 2630, "train_flow_matching_loss": 0.208984375, "train_physics_loss": 0.0 }, { "grad_norm": 0.38071948289871216, "learning_rate": 5e-05, "loss": 0.2101, "step": 2640 }, { "step": 2640, "train_flow_matching_loss": 0.134765625, "train_physics_loss": 0.0 }, { "grad_norm": 0.4843887388706207, "learning_rate": 5e-05, "loss": 0.2003, "step": 2650 }, { "step": 2650, "train_flow_matching_loss": 0.1953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.35446372628211975, "learning_rate": 5e-05, "loss": 0.1977, "step": 2660 }, { "step": 2660, "train_flow_matching_loss": 0.2353515625, "train_physics_loss": 0.0 }, { "grad_norm": 0.2824874222278595, "learning_rate": 5e-05, "loss": 0.2002, "step": 2670 }, { "step": 2670, "train_flow_matching_loss": 0.2109375, "train_physics_loss": 0.0 }, { "grad_norm": 0.3969775438308716, "learning_rate": 5e-05, "loss": 0.2062, "step": 2680 }, { "step": 2680, "train_flow_matching_loss": 0.1513671875, "train_physics_loss": 0.0 }, { "grad_norm": 0.449605792760849, "learning_rate": 5e-05, "loss": 0.1924, "step": 2690 }, { "step": 2690, "train_flow_matching_loss": 0.142578125, "train_physics_loss": 0.0 }, { "grad_norm": 0.3818964660167694, "learning_rate": 5e-05, "loss": 0.1848, "step": 2700 }, { "step": 2700, "train_flow_matching_loss": 0.1767578125, "train_physics_loss": 0.0 }, { "grad_norm": 0.4869641065597534, "learning_rate": 5e-05, "loss": 0.1969, "step": 2710 }, { "step": 2710, "train_flow_matching_loss": 0.2177734375, "train_physics_loss": 0.0 }, { "grad_norm": 0.3469415307044983, "learning_rate": 5e-05, "loss": 0.2066, "step": 2720 }, { "step": 2720, "train_flow_matching_loss": 0.2080078125, "train_physics_loss": 0.0 }, { "grad_norm": 0.2785400450229645, "learning_rate": 5e-05, "loss": 0.2007, "step": 2730 }, { "step": 2730, "train_flow_matching_loss": 0.1484375, "train_physics_loss": 0.0 }, { "grad_norm": 0.4444355070590973, "learning_rate": 5e-05, "loss": 0.1825, "step": 2740 }, { "step": 2740, "train_flow_matching_loss": 0.11572265625, "train_physics_loss": 0.0 }, { "grad_norm": 0.48016658425331116, "learning_rate": 5e-05, "loss": 0.1998, "step": 2750 }, { "step": 2750, "train_flow_matching_loss": 0.205078125, "train_physics_loss": 0.0 }, { "grad_norm": 0.5644499659538269, "learning_rate": 5e-05, "loss": 0.1834, "step": 2760 }, { "step": 2760, "train_flow_matching_loss": 0.234375, "train_physics_loss": 0.0 }, { "grad_norm": 0.399831086397171, "learning_rate": 5e-05, "loss": 0.181, "step": 2770 }, { "step": 2770, "train_flow_matching_loss": 0.11474609375, "train_physics_loss": 0.0 }, { "grad_norm": 0.3855477273464203, "learning_rate": 5e-05, "loss": 0.1849, "step": 2780 }, { "step": 2780, "train_flow_matching_loss": 0.1650390625, "train_physics_loss": 0.0 }, { "grad_norm": 0.4709649085998535, "learning_rate": 5e-05, "loss": 0.1949, "step": 2790 }, { "step": 2790, "train_flow_matching_loss": 0.11376953125, "train_physics_loss": 0.0 }, { "grad_norm": 0.5084549784660339, "learning_rate": 5e-05, "loss": 0.2031, "step": 2800 }, { "step": 2800, "train_flow_matching_loss": 0.1689453125, "train_physics_loss": 0.0 }, { "grad_norm": 0.8005664348602295, "learning_rate": 5e-05, "loss": 0.2014, "step": 2810 }, { "step": 2810, "train_flow_matching_loss": 0.1259765625, "train_physics_loss": 0.0 }, { "grad_norm": 0.5107675790786743, "learning_rate": 5e-05, "loss": 0.1891, "step": 2820 }, { "step": 2820, "train_flow_matching_loss": 0.11865234375, "train_physics_loss": 0.0 }, { "grad_norm": 0.3172883689403534, "learning_rate": 5e-05, "loss": 0.1842, "step": 2830 }, { "step": 2830, "train_flow_matching_loss": 0.171875, "train_physics_loss": 0.0 }, { "grad_norm": 0.5041273236274719, "learning_rate": 5e-05, "loss": 0.2015, "step": 2840 }, { "step": 2840, "train_flow_matching_loss": 0.1728515625, "train_physics_loss": 0.0 }, { "grad_norm": 0.5120939612388611, "learning_rate": 5e-05, "loss": 0.1978, "step": 2850 }, { "step": 2850, "train_flow_matching_loss": 0.2060546875, "train_physics_loss": 0.0 }, { "grad_norm": 0.37928086519241333, "learning_rate": 5e-05, "loss": 0.185, "step": 2860 }, { "step": 2860, "train_flow_matching_loss": 0.142578125, "train_physics_loss": 0.0 }, { "grad_norm": 0.716517984867096, "learning_rate": 5e-05, "loss": 0.1967, "step": 2870 }, { "step": 2870, "train_flow_matching_loss": 0.1357421875, "train_physics_loss": 0.0 }, { "grad_norm": 0.5275052189826965, "learning_rate": 5e-05, "loss": 0.1906, "step": 2880 }, { "step": 2880, "train_flow_matching_loss": 0.1640625, "train_physics_loss": 0.0 }, { "grad_norm": 0.3330939710140228, "learning_rate": 5e-05, "loss": 0.1916, "step": 2890 }, { "step": 2890, "train_flow_matching_loss": 0.1767578125, "train_physics_loss": 0.0 }, { "grad_norm": 0.46944984793663025, "learning_rate": 5e-05, "loss": 0.1928, "step": 2900 }, { "step": 2900, "train_flow_matching_loss": 0.2197265625, "train_physics_loss": 0.0 }, { "grad_norm": 0.7221873998641968, "learning_rate": 5e-05, "loss": 0.1868, "step": 2910 }, { "step": 2910, "train_flow_matching_loss": 0.1162109375, "train_physics_loss": 0.0 }, { "grad_norm": 0.38209056854248047, "learning_rate": 5e-05, "loss": 0.1829, "step": 2920 }, { "step": 2920, "train_flow_matching_loss": 0.2216796875, "train_physics_loss": 0.0 }, { "grad_norm": 0.40676459670066833, "learning_rate": 5e-05, "loss": 0.1815, "step": 2930 }, { "step": 2930, "train_flow_matching_loss": 0.2333984375, "train_physics_loss": 0.0 }, { "grad_norm": 0.42865288257598877, "learning_rate": 5e-05, "loss": 0.1759, "step": 2940 }, { "step": 2940, "train_flow_matching_loss": 0.166015625, "train_physics_loss": 0.0 }, { "grad_norm": 0.5857993960380554, "learning_rate": 5e-05, "loss": 0.1857, "step": 2950 }, { "step": 2950, "train_flow_matching_loss": 0.1640625, "train_physics_loss": 0.0 }, { "grad_norm": 0.4326969087123871, "learning_rate": 5e-05, "loss": 0.1926, "step": 2960 }, { "step": 2960, "train_flow_matching_loss": 0.1826171875, "train_physics_loss": 0.0 }, { "grad_norm": 0.5522880554199219, "learning_rate": 5e-05, "loss": 0.1804, "step": 2970 }, { "step": 2970, "train_flow_matching_loss": 0.158203125, "train_physics_loss": 0.0 }, { "grad_norm": 0.40297242999076843, "learning_rate": 5e-05, "loss": 0.1915, "step": 2980 }, { "step": 2980, "train_flow_matching_loss": 0.1689453125, "train_physics_loss": 0.0 }, { "grad_norm": 0.3447861969470978, "learning_rate": 5e-05, "loss": 0.1901, "step": 2990 }, { "step": 2990, "train_flow_matching_loss": 0.1298828125, "train_physics_loss": 0.0 }, { "grad_norm": 0.4612976312637329, "learning_rate": 5e-05, "loss": 0.1875, "step": 3000 } ], "logging_steps": 10, "max_steps": 30000, "num_input_tokens_seen": 0, "num_train_epochs": 9223372036854775807, "save_steps": 1000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 0.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }