ntv3_mdlm_8m_unconditional_t1 / training_log.jsonl
explcre's picture
Add files using upload-large-folder tool
0f8546d verified
Raw
History Blame Contribute Delete
8.61 kB
{"step": 1, "loss": 7.763705730438232, "elapsed_s": 1.0, "head": "mdlm"}
{"step": 20, "loss": 3.9720377922058105, "elapsed_s": 3.0, "head": "mdlm"}
{"step": 40, "loss": 42.18397903442383, "elapsed_s": 5.2, "head": "mdlm"}
{"step": 60, "loss": 15.69352912902832, "elapsed_s": 7.3, "head": "mdlm"}
{"step": 80, "loss": 6.967123985290527, "elapsed_s": 9.6, "head": "mdlm"}
{"step": 100, "loss": 3.3493056297302246, "elapsed_s": 11.1, "head": "mdlm"}
{"step": 120, "loss": 18.59830665588379, "elapsed_s": 12.9, "head": "mdlm"}
{"step": 140, "loss": 4.629162788391113, "elapsed_s": 15.1, "head": "mdlm"}
{"step": 160, "loss": 5.112680912017822, "elapsed_s": 16.8, "head": "mdlm"}
{"step": 180, "loss": 3.833908796310425, "elapsed_s": 18.7, "head": "mdlm"}
{"step": 200, "loss": 7.951632499694824, "elapsed_s": 20.6, "head": "mdlm"}
{"kind": "eval", "step": 200, "val_loss": 11.122749524388995, "val_n": 7000.0}
{"step": 220, "loss": 4.807468414306641, "elapsed_s": 39.4, "head": "mdlm"}
{"step": 240, "loss": 6.923015594482422, "elapsed_s": 41.3, "head": "mdlm"}
{"step": 260, "loss": 15.370270729064941, "elapsed_s": 43.7, "head": "mdlm"}
{"step": 280, "loss": 26.744260787963867, "elapsed_s": 45.4, "head": "mdlm"}
{"step": 300, "loss": 3.335010290145874, "elapsed_s": 47.0, "head": "mdlm"}
{"step": 320, "loss": 3.027705430984497, "elapsed_s": 48.6, "head": "mdlm"}
{"step": 340, "loss": 4.789960861206055, "elapsed_s": 50.5, "head": "mdlm"}
{"step": 360, "loss": 4.883223056793213, "elapsed_s": 52.1, "head": "mdlm"}
{"step": 380, "loss": 15.868343353271484, "elapsed_s": 53.7, "head": "mdlm"}
{"step": 400, "loss": 5.755954265594482, "elapsed_s": 55.3, "head": "mdlm"}
{"kind": "eval", "step": 400, "val_loss": 11.005335272244045, "val_n": 7000.0}
{"step": 420, "loss": 5.551031112670898, "elapsed_s": 72.7, "head": "mdlm"}
{"step": 440, "loss": 11.585519790649414, "elapsed_s": 74.5, "head": "mdlm"}
{"step": 460, "loss": 36.24274444580078, "elapsed_s": 76.9, "head": "mdlm"}
{"step": 480, "loss": 4.375256538391113, "elapsed_s": 78.9, "head": "mdlm"}
{"step": 500, "loss": 7.940896987915039, "elapsed_s": 80.5, "head": "mdlm"}
{"step": 520, "loss": 2.1085433959960938, "elapsed_s": 82.4, "head": "mdlm"}
{"step": 540, "loss": 5.605800151824951, "elapsed_s": 84.0, "head": "mdlm"}
{"step": 560, "loss": 7.5305962562561035, "elapsed_s": 85.7, "head": "mdlm"}
{"step": 580, "loss": 4.086808204650879, "elapsed_s": 88.2, "head": "mdlm"}
{"step": 600, "loss": 9.810787200927734, "elapsed_s": 90.7, "head": "mdlm"}
{"kind": "eval", "step": 600, "val_loss": 11.179654576301575, "val_n": 7000.0}
{"step": 620, "loss": 7.216514587402344, "elapsed_s": 110.4, "head": "mdlm"}
{"step": 640, "loss": 2.94865083694458, "elapsed_s": 112.2, "head": "mdlm"}
{"step": 660, "loss": 16.752029418945312, "elapsed_s": 114.0, "head": "mdlm"}
{"step": 680, "loss": 8.548652648925781, "elapsed_s": 115.5, "head": "mdlm"}
{"step": 700, "loss": 17.139795303344727, "elapsed_s": 117.1, "head": "mdlm"}
{"step": 720, "loss": 3.56426739692688, "elapsed_s": 119.6, "head": "mdlm"}
{"step": 740, "loss": 13.844051361083984, "elapsed_s": 121.4, "head": "mdlm"}
{"step": 760, "loss": 24.456756591796875, "elapsed_s": 123.0, "head": "mdlm"}
{"step": 780, "loss": 12.189183235168457, "elapsed_s": 125.2, "head": "mdlm"}
{"step": 800, "loss": 48.626041412353516, "elapsed_s": 127.0, "head": "mdlm"}
{"kind": "eval", "step": 800, "val_loss": 10.586385174615042, "val_n": 7000.0}
{"step": 820, "loss": 4.204320430755615, "elapsed_s": 141.1, "head": "mdlm"}
{"step": 840, "loss": 8.608379364013672, "elapsed_s": 143.1, "head": "mdlm"}
{"step": 860, "loss": 6.516913890838623, "elapsed_s": 144.5, "head": "mdlm"}
{"step": 880, "loss": 4.3451690673828125, "elapsed_s": 146.6, "head": "mdlm"}
{"step": 900, "loss": 9.949851989746094, "elapsed_s": 148.6, "head": "mdlm"}
{"step": 920, "loss": 5.580066204071045, "elapsed_s": 150.5, "head": "mdlm"}
{"step": 940, "loss": 13.972540855407715, "elapsed_s": 152.0, "head": "mdlm"}
{"step": 960, "loss": 8.865029335021973, "elapsed_s": 154.2, "head": "mdlm"}
{"step": 980, "loss": 11.108205795288086, "elapsed_s": 156.4, "head": "mdlm"}
{"step": 1000, "loss": 11.587594985961914, "elapsed_s": 158.1, "head": "mdlm"}
{"kind": "eval", "step": 1000, "val_loss": 11.378280388287136, "val_n": 7000.0}
{"step": 1020, "loss": 8.146681785583496, "elapsed_s": 171.3, "head": "mdlm"}
{"step": 1040, "loss": 7.216224193572998, "elapsed_s": 172.8, "head": "mdlm"}
{"step": 1060, "loss": 6.707790374755859, "elapsed_s": 174.6, "head": "mdlm"}
{"step": 1080, "loss": 10.743816375732422, "elapsed_s": 176.8, "head": "mdlm"}
{"step": 1100, "loss": 21.633676528930664, "elapsed_s": 178.6, "head": "mdlm"}
{"step": 1120, "loss": 15.295496940612793, "elapsed_s": 180.1, "head": "mdlm"}
{"step": 1140, "loss": 5.341646671295166, "elapsed_s": 181.7, "head": "mdlm"}
{"step": 1160, "loss": 3.061863899230957, "elapsed_s": 183.7, "head": "mdlm"}
{"step": 1180, "loss": 8.20213794708252, "elapsed_s": 185.1, "head": "mdlm"}
{"step": 1200, "loss": 4.078469276428223, "elapsed_s": 186.8, "head": "mdlm"}
{"kind": "eval", "step": 1200, "val_loss": 11.15837869984763, "val_n": 7000.0}
{"step": 1220, "loss": 5.688098907470703, "elapsed_s": 205.6, "head": "mdlm"}
{"step": 1240, "loss": 16.658817291259766, "elapsed_s": 207.2, "head": "mdlm"}
{"step": 1260, "loss": 9.281482696533203, "elapsed_s": 209.3, "head": "mdlm"}
{"step": 1280, "loss": 2.24838924407959, "elapsed_s": 210.8, "head": "mdlm"}
{"step": 1300, "loss": 4.776653289794922, "elapsed_s": 213.3, "head": "mdlm"}
{"step": 1320, "loss": 11.874520301818848, "elapsed_s": 215.5, "head": "mdlm"}
{"step": 1340, "loss": 4.5947980880737305, "elapsed_s": 217.3, "head": "mdlm"}
{"step": 1360, "loss": 3.34250807762146, "elapsed_s": 219.0, "head": "mdlm"}
{"step": 1380, "loss": 18.579822540283203, "elapsed_s": 220.7, "head": "mdlm"}
{"step": 1400, "loss": 4.719513893127441, "elapsed_s": 222.7, "head": "mdlm"}
{"kind": "eval", "step": 1400, "val_loss": 10.961528215953281, "val_n": 7000.0}
{"step": 1420, "loss": 10.5309419631958, "elapsed_s": 241.7, "head": "mdlm"}
{"step": 1440, "loss": 4.446271896362305, "elapsed_s": 243.9, "head": "mdlm"}
{"step": 1460, "loss": 16.688425064086914, "elapsed_s": 245.6, "head": "mdlm"}
{"step": 1480, "loss": 4.855653285980225, "elapsed_s": 247.2, "head": "mdlm"}
{"step": 1500, "loss": 7.653467655181885, "elapsed_s": 249.3, "head": "mdlm"}
{"step": 1520, "loss": 3.454191207885742, "elapsed_s": 251.1, "head": "mdlm"}
{"step": 1540, "loss": 8.881498336791992, "elapsed_s": 253.0, "head": "mdlm"}
{"step": 1560, "loss": 10.777250289916992, "elapsed_s": 255.0, "head": "mdlm"}
{"step": 1580, "loss": 15.550907135009766, "elapsed_s": 256.5, "head": "mdlm"}
{"step": 1600, "loss": 11.529050827026367, "elapsed_s": 258.1, "head": "mdlm"}
{"kind": "eval", "step": 1600, "val_loss": 10.338015226364135, "val_n": 7000.0}
{"step": 1620, "loss": 2.4384262561798096, "elapsed_s": 270.9, "head": "mdlm"}
{"step": 1640, "loss": 11.73444652557373, "elapsed_s": 273.5, "head": "mdlm"}
{"step": 1660, "loss": 11.205860137939453, "elapsed_s": 276.1, "head": "mdlm"}
{"step": 1680, "loss": 4.479555130004883, "elapsed_s": 277.8, "head": "mdlm"}
{"step": 1700, "loss": 23.528430938720703, "elapsed_s": 279.5, "head": "mdlm"}
{"step": 1720, "loss": 4.903354644775391, "elapsed_s": 281.7, "head": "mdlm"}
{"step": 1740, "loss": 4.240989685058594, "elapsed_s": 283.2, "head": "mdlm"}
{"step": 1760, "loss": 8.465856552124023, "elapsed_s": 284.7, "head": "mdlm"}
{"step": 1780, "loss": 16.80489158630371, "elapsed_s": 286.4, "head": "mdlm"}
{"step": 1800, "loss": 6.588719367980957, "elapsed_s": 288.0, "head": "mdlm"}
{"kind": "eval", "step": 1800, "val_loss": 11.128818316323416, "val_n": 7000.0}
{"step": 1820, "loss": 8.557101249694824, "elapsed_s": 301.7, "head": "mdlm"}
{"step": 1840, "loss": 4.6366777420043945, "elapsed_s": 303.8, "head": "mdlm"}
{"step": 1860, "loss": 18.225486755371094, "elapsed_s": 305.2, "head": "mdlm"}
{"step": 1880, "loss": 5.314108848571777, "elapsed_s": 307.1, "head": "mdlm"}
{"step": 1900, "loss": 9.939878463745117, "elapsed_s": 309.3, "head": "mdlm"}
{"step": 1920, "loss": 19.58873748779297, "elapsed_s": 310.7, "head": "mdlm"}
{"step": 1940, "loss": 3.7417125701904297, "elapsed_s": 313.3, "head": "mdlm"}
{"step": 1960, "loss": 4.637796878814697, "elapsed_s": 314.8, "head": "mdlm"}
{"step": 1980, "loss": 8.76892375946045, "elapsed_s": 316.6, "head": "mdlm"}
{"step": 2000, "loss": 4.643191814422607, "elapsed_s": 319.2, "head": "mdlm"}
{"kind": "eval", "step": 2000, "val_loss": 10.376388350486755, "val_n": 7000.0}