| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 5000, | |
| "global_step": 1049, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.009532888465204958, | |
| "grad_norm": 9735.205078125, | |
| "learning_rate": 6.000000000000001e-07, | |
| "loss": 14.3342, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.019065776930409915, | |
| "grad_norm": 12878.38671875, | |
| "learning_rate": 2.2e-06, | |
| "loss": 13.2398, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028598665395614873, | |
| "grad_norm": 7679.97412109375, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 11.5969, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03813155386081983, | |
| "grad_norm": 1830.318603515625, | |
| "learning_rate": 5.2e-06, | |
| "loss": 7.4151, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.047664442326024785, | |
| "grad_norm": 1004.4345092773438, | |
| "learning_rate": 7.2e-06, | |
| "loss": 5.4187, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.057197330791229746, | |
| "grad_norm": 588.986328125, | |
| "learning_rate": 9.2e-06, | |
| "loss": 4.4843, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.0667302192564347, | |
| "grad_norm": 599.4677734375, | |
| "learning_rate": 1.1200000000000001e-05, | |
| "loss": 3.5594, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.07626310772163966, | |
| "grad_norm": 360.55419921875, | |
| "learning_rate": 1.32e-05, | |
| "loss": 2.8006, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.08579599618684461, | |
| "grad_norm": 78.43992614746094, | |
| "learning_rate": 1.52e-05, | |
| "loss": 1.9745, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.09532888465204957, | |
| "grad_norm": 49.44837951660156, | |
| "learning_rate": 1.7199999999999998e-05, | |
| "loss": 1.1316, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.10486177311725453, | |
| "grad_norm": 25.379404067993164, | |
| "learning_rate": 1.9200000000000003e-05, | |
| "loss": 0.5633, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.11439466158245949, | |
| "grad_norm": 57.260284423828125, | |
| "learning_rate": 2.12e-05, | |
| "loss": 0.3606, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.12392755004766444, | |
| "grad_norm": 83.0460205078125, | |
| "learning_rate": 2.32e-05, | |
| "loss": 0.3603, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.1334604385128694, | |
| "grad_norm": 91.75605773925781, | |
| "learning_rate": 2.5200000000000003e-05, | |
| "loss": 0.2501, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.14299332697807435, | |
| "grad_norm": 84.04005432128906, | |
| "learning_rate": 2.7200000000000004e-05, | |
| "loss": 0.2193, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.15252621544327932, | |
| "grad_norm": 28.945568084716797, | |
| "learning_rate": 2.9199999999999998e-05, | |
| "loss": 0.2095, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.16205910390848427, | |
| "grad_norm": 9.935993194580078, | |
| "learning_rate": 3.12e-05, | |
| "loss": 0.1697, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.17159199237368922, | |
| "grad_norm": 5.943849563598633, | |
| "learning_rate": 3.32e-05, | |
| "loss": 0.1945, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.1811248808388942, | |
| "grad_norm": 13.284988403320312, | |
| "learning_rate": 3.52e-05, | |
| "loss": 0.1817, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.19065776930409914, | |
| "grad_norm": 42.371212005615234, | |
| "learning_rate": 3.72e-05, | |
| "loss": 0.5578, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2001906577693041, | |
| "grad_norm": 17.454591751098633, | |
| "learning_rate": 3.9200000000000004e-05, | |
| "loss": 0.2339, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.20972354623450906, | |
| "grad_norm": 248.91416931152344, | |
| "learning_rate": 4.12e-05, | |
| "loss": 0.1741, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.219256434699714, | |
| "grad_norm": 1.8945605754852295, | |
| "learning_rate": 4.32e-05, | |
| "loss": 0.1669, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.22878932316491898, | |
| "grad_norm": 2.4241456985473633, | |
| "learning_rate": 4.52e-05, | |
| "loss": 0.1693, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.23832221163012393, | |
| "grad_norm": 1.1613476276397705, | |
| "learning_rate": 4.72e-05, | |
| "loss": 0.1331, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 0.24785510009532888, | |
| "grad_norm": 2.931299924850464, | |
| "learning_rate": 4.92e-05, | |
| "loss": 0.1527, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.25738798856053385, | |
| "grad_norm": 139.0654754638672, | |
| "learning_rate": 5.1200000000000004e-05, | |
| "loss": 0.1426, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 0.2669208770257388, | |
| "grad_norm": 1.6811221837997437, | |
| "learning_rate": 5.3200000000000006e-05, | |
| "loss": 0.1377, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.27645376549094375, | |
| "grad_norm": 2.773026466369629, | |
| "learning_rate": 5.520000000000001e-05, | |
| "loss": 0.1551, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 0.2859866539561487, | |
| "grad_norm": 0.9235513210296631, | |
| "learning_rate": 5.72e-05, | |
| "loss": 0.1328, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.29551954242135364, | |
| "grad_norm": 0.634608805179596, | |
| "learning_rate": 5.92e-05, | |
| "loss": 0.1203, | |
| "step": 310 | |
| }, | |
| { | |
| "epoch": 0.30505243088655865, | |
| "grad_norm": 1.2987741231918335, | |
| "learning_rate": 6.12e-05, | |
| "loss": 0.1127, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.3145853193517636, | |
| "grad_norm": 1.1649960279464722, | |
| "learning_rate": 6.32e-05, | |
| "loss": 0.1228, | |
| "step": 330 | |
| }, | |
| { | |
| "epoch": 0.32411820781696854, | |
| "grad_norm": 1.1517277956008911, | |
| "learning_rate": 6.52e-05, | |
| "loss": 0.15, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.3336510962821735, | |
| "grad_norm": 2.274184465408325, | |
| "learning_rate": 6.720000000000001e-05, | |
| "loss": 0.1121, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 0.34318398474737843, | |
| "grad_norm": 0.8627381324768066, | |
| "learning_rate": 6.92e-05, | |
| "loss": 0.1171, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.35271687321258344, | |
| "grad_norm": 1.2641953229904175, | |
| "learning_rate": 7.12e-05, | |
| "loss": 0.1437, | |
| "step": 370 | |
| }, | |
| { | |
| "epoch": 0.3622497616777884, | |
| "grad_norm": 14.235816955566406, | |
| "learning_rate": 7.32e-05, | |
| "loss": 0.1719, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.37178265014299333, | |
| "grad_norm": 1.2613039016723633, | |
| "learning_rate": 7.52e-05, | |
| "loss": 0.1401, | |
| "step": 390 | |
| }, | |
| { | |
| "epoch": 0.3813155386081983, | |
| "grad_norm": 1.125999927520752, | |
| "learning_rate": 7.72e-05, | |
| "loss": 0.1176, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.3908484270734032, | |
| "grad_norm": 2.6700384616851807, | |
| "learning_rate": 7.920000000000001e-05, | |
| "loss": 0.116, | |
| "step": 410 | |
| }, | |
| { | |
| "epoch": 0.4003813155386082, | |
| "grad_norm": 0.9148916602134705, | |
| "learning_rate": 8.120000000000001e-05, | |
| "loss": 0.1392, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.4099142040038132, | |
| "grad_norm": 1.3875360488891602, | |
| "learning_rate": 8.32e-05, | |
| "loss": 0.168, | |
| "step": 430 | |
| }, | |
| { | |
| "epoch": 0.4194470924690181, | |
| "grad_norm": 0.6264955997467041, | |
| "learning_rate": 8.52e-05, | |
| "loss": 0.1484, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.42897998093422307, | |
| "grad_norm": 1.0963646173477173, | |
| "learning_rate": 8.72e-05, | |
| "loss": 0.1457, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 0.438512869399428, | |
| "grad_norm": 0.6666226387023926, | |
| "learning_rate": 8.92e-05, | |
| "loss": 0.1311, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.44804575786463297, | |
| "grad_norm": 0.9684863686561584, | |
| "learning_rate": 9.120000000000001e-05, | |
| "loss": 0.1428, | |
| "step": 470 | |
| }, | |
| { | |
| "epoch": 0.45757864632983797, | |
| "grad_norm": 0.6623441576957703, | |
| "learning_rate": 9.320000000000002e-05, | |
| "loss": 0.1317, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.4671115347950429, | |
| "grad_norm": 14.834782600402832, | |
| "learning_rate": 9.52e-05, | |
| "loss": 0.2165, | |
| "step": 490 | |
| }, | |
| { | |
| "epoch": 0.47664442326024786, | |
| "grad_norm": 2.777594566345215, | |
| "learning_rate": 9.72e-05, | |
| "loss": 0.2189, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.4861773117254528, | |
| "grad_norm": 0.6071160435676575, | |
| "learning_rate": 9.92e-05, | |
| "loss": 0.1401, | |
| "step": 510 | |
| }, | |
| { | |
| "epoch": 0.49571020019065776, | |
| "grad_norm": 0.9390038251876831, | |
| "learning_rate": 9.890710382513662e-05, | |
| "loss": 0.2272, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.5052430886558628, | |
| "grad_norm": 0.527932345867157, | |
| "learning_rate": 9.708561020036431e-05, | |
| "loss": 0.1311, | |
| "step": 530 | |
| }, | |
| { | |
| "epoch": 0.5147759771210677, | |
| "grad_norm": 0.7770779728889465, | |
| "learning_rate": 9.5264116575592e-05, | |
| "loss": 0.1278, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.5243088655862727, | |
| "grad_norm": 0.5907878279685974, | |
| "learning_rate": 9.344262295081968e-05, | |
| "loss": 0.1331, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 0.5338417540514776, | |
| "grad_norm": 0.8410826325416565, | |
| "learning_rate": 9.162112932604736e-05, | |
| "loss": 0.1274, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.5433746425166825, | |
| "grad_norm": 7.286756992340088, | |
| "learning_rate": 8.979963570127505e-05, | |
| "loss": 0.108, | |
| "step": 570 | |
| }, | |
| { | |
| "epoch": 0.5529075309818875, | |
| "grad_norm": 1.711925745010376, | |
| "learning_rate": 8.797814207650273e-05, | |
| "loss": 0.1128, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.5624404194470924, | |
| "grad_norm": 1.0234737396240234, | |
| "learning_rate": 8.615664845173043e-05, | |
| "loss": 0.1405, | |
| "step": 590 | |
| }, | |
| { | |
| "epoch": 0.5719733079122974, | |
| "grad_norm": 12.920223236083984, | |
| "learning_rate": 8.433515482695811e-05, | |
| "loss": 0.3122, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.5815061963775023, | |
| "grad_norm": 1.8921475410461426, | |
| "learning_rate": 8.25136612021858e-05, | |
| "loss": 0.1527, | |
| "step": 610 | |
| }, | |
| { | |
| "epoch": 0.5910390848427073, | |
| "grad_norm": 0.22176694869995117, | |
| "learning_rate": 8.069216757741349e-05, | |
| "loss": 0.0753, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.6005719733079123, | |
| "grad_norm": 5.071296691894531, | |
| "learning_rate": 7.887067395264117e-05, | |
| "loss": 0.1564, | |
| "step": 630 | |
| }, | |
| { | |
| "epoch": 0.6101048617731173, | |
| "grad_norm": 0.5505660772323608, | |
| "learning_rate": 7.704918032786885e-05, | |
| "loss": 0.1145, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.6196377502383222, | |
| "grad_norm": 10.267545700073242, | |
| "learning_rate": 7.522768670309654e-05, | |
| "loss": 0.1342, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 0.6291706387035272, | |
| "grad_norm": 0.65236496925354, | |
| "learning_rate": 7.340619307832422e-05, | |
| "loss": 0.156, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.6387035271687321, | |
| "grad_norm": 117.93495178222656, | |
| "learning_rate": 7.158469945355192e-05, | |
| "loss": 0.1338, | |
| "step": 670 | |
| }, | |
| { | |
| "epoch": 0.6482364156339371, | |
| "grad_norm": 0.8004688024520874, | |
| "learning_rate": 6.97632058287796e-05, | |
| "loss": 0.1319, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.657769304099142, | |
| "grad_norm": 0.7219289541244507, | |
| "learning_rate": 6.79417122040073e-05, | |
| "loss": 0.1115, | |
| "step": 690 | |
| }, | |
| { | |
| "epoch": 0.667302192564347, | |
| "grad_norm": 0.35620227456092834, | |
| "learning_rate": 6.612021857923498e-05, | |
| "loss": 0.1471, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.6768350810295519, | |
| "grad_norm": 1.245010495185852, | |
| "learning_rate": 6.429872495446266e-05, | |
| "loss": 0.1107, | |
| "step": 710 | |
| }, | |
| { | |
| "epoch": 0.6863679694947569, | |
| "grad_norm": 0.7738503217697144, | |
| "learning_rate": 6.247723132969034e-05, | |
| "loss": 0.1153, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.6959008579599618, | |
| "grad_norm": 0.8265978693962097, | |
| "learning_rate": 6.0655737704918034e-05, | |
| "loss": 0.1653, | |
| "step": 730 | |
| }, | |
| { | |
| "epoch": 0.7054337464251669, | |
| "grad_norm": 0.6407246589660645, | |
| "learning_rate": 5.8834244080145716e-05, | |
| "loss": 0.1236, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.7149666348903718, | |
| "grad_norm": 1.0173193216323853, | |
| "learning_rate": 5.701275045537341e-05, | |
| "loss": 0.1167, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 0.7244995233555768, | |
| "grad_norm": 0.8038718104362488, | |
| "learning_rate": 5.519125683060109e-05, | |
| "loss": 0.1183, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.7340324118207817, | |
| "grad_norm": 0.5294243097305298, | |
| "learning_rate": 5.336976320582878e-05, | |
| "loss": 0.1066, | |
| "step": 770 | |
| }, | |
| { | |
| "epoch": 0.7435653002859867, | |
| "grad_norm": 0.5142996311187744, | |
| "learning_rate": 5.1548269581056475e-05, | |
| "loss": 0.1085, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.7530981887511916, | |
| "grad_norm": 0.5086462497711182, | |
| "learning_rate": 4.9726775956284156e-05, | |
| "loss": 0.1077, | |
| "step": 790 | |
| }, | |
| { | |
| "epoch": 0.7626310772163966, | |
| "grad_norm": 0.3155575394630432, | |
| "learning_rate": 4.7905282331511844e-05, | |
| "loss": 0.0976, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.7721639656816015, | |
| "grad_norm": 0.6338363289833069, | |
| "learning_rate": 4.6083788706739525e-05, | |
| "loss": 0.104, | |
| "step": 810 | |
| }, | |
| { | |
| "epoch": 0.7816968541468065, | |
| "grad_norm": 0.6568697094917297, | |
| "learning_rate": 4.426229508196721e-05, | |
| "loss": 0.1092, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.7912297426120114, | |
| "grad_norm": 0.5086967349052429, | |
| "learning_rate": 4.24408014571949e-05, | |
| "loss": 0.1209, | |
| "step": 830 | |
| }, | |
| { | |
| "epoch": 0.8007626310772163, | |
| "grad_norm": 0.466325044631958, | |
| "learning_rate": 4.061930783242259e-05, | |
| "loss": 0.1113, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.8102955195424214, | |
| "grad_norm": 0.8668030500411987, | |
| "learning_rate": 3.879781420765027e-05, | |
| "loss": 0.1015, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 0.8198284080076264, | |
| "grad_norm": 0.7336855530738831, | |
| "learning_rate": 3.697632058287796e-05, | |
| "loss": 0.0947, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.8293612964728313, | |
| "grad_norm": 0.8070642948150635, | |
| "learning_rate": 3.515482695810565e-05, | |
| "loss": 0.1254, | |
| "step": 870 | |
| }, | |
| { | |
| "epoch": 0.8388941849380362, | |
| "grad_norm": 0.5929535031318665, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0781, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.8484270734032412, | |
| "grad_norm": 0.585108757019043, | |
| "learning_rate": 3.1511839708561016e-05, | |
| "loss": 0.0882, | |
| "step": 890 | |
| }, | |
| { | |
| "epoch": 0.8579599618684461, | |
| "grad_norm": 0.6924892067909241, | |
| "learning_rate": 2.9690346083788704e-05, | |
| "loss": 0.1026, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.8674928503336511, | |
| "grad_norm": 0.968221127986908, | |
| "learning_rate": 2.7868852459016392e-05, | |
| "loss": 0.109, | |
| "step": 910 | |
| }, | |
| { | |
| "epoch": 0.877025738798856, | |
| "grad_norm": 0.5783460736274719, | |
| "learning_rate": 2.604735883424408e-05, | |
| "loss": 0.0762, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.886558627264061, | |
| "grad_norm": 0.44456052780151367, | |
| "learning_rate": 2.422586520947177e-05, | |
| "loss": 0.0963, | |
| "step": 930 | |
| }, | |
| { | |
| "epoch": 0.8960915157292659, | |
| "grad_norm": 0.49880489706993103, | |
| "learning_rate": 2.2404371584699453e-05, | |
| "loss": 0.0988, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.9056244041944709, | |
| "grad_norm": 0.5427205562591553, | |
| "learning_rate": 2.058287795992714e-05, | |
| "loss": 0.0909, | |
| "step": 950 | |
| }, | |
| { | |
| "epoch": 0.9151572926596759, | |
| "grad_norm": 0.5747605562210083, | |
| "learning_rate": 1.8761384335154826e-05, | |
| "loss": 0.0983, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.9246901811248809, | |
| "grad_norm": 0.8023502230644226, | |
| "learning_rate": 1.6939890710382514e-05, | |
| "loss": 0.1178, | |
| "step": 970 | |
| }, | |
| { | |
| "epoch": 0.9342230695900858, | |
| "grad_norm": 0.5023919939994812, | |
| "learning_rate": 1.51183970856102e-05, | |
| "loss": 0.0837, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.9437559580552908, | |
| "grad_norm": 0.5053642392158508, | |
| "learning_rate": 1.3296903460837887e-05, | |
| "loss": 0.0964, | |
| "step": 990 | |
| }, | |
| { | |
| "epoch": 0.9532888465204957, | |
| "grad_norm": 0.9289111495018005, | |
| "learning_rate": 1.1475409836065575e-05, | |
| "loss": 0.1087, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.9628217349857007, | |
| "grad_norm": 0.6367629766464233, | |
| "learning_rate": 9.653916211293261e-06, | |
| "loss": 0.0936, | |
| "step": 1010 | |
| }, | |
| { | |
| "epoch": 0.9723546234509056, | |
| "grad_norm": 0.7083348035812378, | |
| "learning_rate": 7.832422586520947e-06, | |
| "loss": 0.0905, | |
| "step": 1020 | |
| }, | |
| { | |
| "epoch": 0.9818875119161106, | |
| "grad_norm": 0.9046676158905029, | |
| "learning_rate": 6.010928961748634e-06, | |
| "loss": 0.1157, | |
| "step": 1030 | |
| }, | |
| { | |
| "epoch": 0.9914204003813155, | |
| "grad_norm": 0.5118803977966309, | |
| "learning_rate": 4.189435336976321e-06, | |
| "loss": 0.104, | |
| "step": 1040 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1049, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.394667177161523e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |