{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 3.0, "eval_steps": 500, "global_step": 1467, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.02047082906857728, "grad_norm": 2.7419285797467823, "learning_rate": 6.122448979591837e-07, "loss": 0.5714, "step": 10 }, { "epoch": 0.04094165813715456, "grad_norm": 1.3395217822161771, "learning_rate": 1.2925170068027212e-06, "loss": 0.5607, "step": 20 }, { "epoch": 0.06141248720573183, "grad_norm": 0.7131203009670463, "learning_rate": 1.9727891156462586e-06, "loss": 0.5058, "step": 30 }, { "epoch": 0.08188331627430911, "grad_norm": 0.5939213129269232, "learning_rate": 2.6530612244897964e-06, "loss": 0.4748, "step": 40 }, { "epoch": 0.1023541453428864, "grad_norm": 0.4371524595984187, "learning_rate": 3.3333333333333333e-06, "loss": 0.4519, "step": 50 }, { "epoch": 0.12282497441146366, "grad_norm": 0.3502938420177603, "learning_rate": 4.013605442176871e-06, "loss": 0.4443, "step": 60 }, { "epoch": 0.14329580348004095, "grad_norm": 0.29761528774367, "learning_rate": 4.693877551020409e-06, "loss": 0.4251, "step": 70 }, { "epoch": 0.16376663254861823, "grad_norm": 0.2854822784474314, "learning_rate": 5.374149659863946e-06, "loss": 0.4159, "step": 80 }, { "epoch": 0.1842374616171955, "grad_norm": 0.3073495732358923, "learning_rate": 6.054421768707484e-06, "loss": 0.4206, "step": 90 }, { "epoch": 0.2047082906857728, "grad_norm": 0.3182797565439541, "learning_rate": 6.734693877551021e-06, "loss": 0.4105, "step": 100 }, { "epoch": 0.22517911975435004, "grad_norm": 0.2936005289527639, "learning_rate": 7.414965986394559e-06, "loss": 0.4066, "step": 110 }, { "epoch": 0.24564994882292732, "grad_norm": 0.3237498717947107, "learning_rate": 8.095238095238097e-06, "loss": 0.4016, "step": 120 }, { "epoch": 0.2661207778915046, "grad_norm": 0.29086892031699574, "learning_rate": 8.775510204081633e-06, "loss": 0.3988, "step": 130 }, { "epoch": 0.2865916069600819, "grad_norm": 0.32624665443263495, "learning_rate": 9.455782312925171e-06, "loss": 0.3926, "step": 140 }, { "epoch": 0.3070624360286592, "grad_norm": 0.41791983226234863, "learning_rate": 9.999943356371867e-06, "loss": 0.396, "step": 150 }, { "epoch": 0.32753326509723646, "grad_norm": 0.3103761740717932, "learning_rate": 9.997960964140946e-06, "loss": 0.3901, "step": 160 }, { "epoch": 0.34800409416581374, "grad_norm": 0.3251036078984643, "learning_rate": 9.993147673772869e-06, "loss": 0.3874, "step": 170 }, { "epoch": 0.368474923234391, "grad_norm": 0.29848102638048, "learning_rate": 9.985506211566388e-06, "loss": 0.3918, "step": 180 }, { "epoch": 0.3889457523029683, "grad_norm": 0.34239845549124515, "learning_rate": 9.975040905726799e-06, "loss": 0.3906, "step": 190 }, { "epoch": 0.4094165813715456, "grad_norm": 0.31464814584407047, "learning_rate": 9.961757683914406e-06, "loss": 0.3885, "step": 200 }, { "epoch": 0.42988741044012285, "grad_norm": 0.3151092550628075, "learning_rate": 9.945664069887028e-06, "loss": 0.3728, "step": 210 }, { "epoch": 0.4503582395087001, "grad_norm": 0.3176233859013783, "learning_rate": 9.926769179238467e-06, "loss": 0.3728, "step": 220 }, { "epoch": 0.47082906857727735, "grad_norm": 0.4612429659946746, "learning_rate": 9.905083714235326e-06, "loss": 0.3807, "step": 230 }, { "epoch": 0.49129989764585463, "grad_norm": 0.3058908611230555, "learning_rate": 9.880619957755151e-06, "loss": 0.3822, "step": 240 }, { "epoch": 0.5117707267144319, "grad_norm": 0.3091236211182382, "learning_rate": 9.853391766329264e-06, "loss": 0.3719, "step": 250 }, { "epoch": 0.5322415557830092, "grad_norm": 0.3303116552583245, "learning_rate": 9.82341456229428e-06, "loss": 0.3772, "step": 260 }, { "epoch": 0.5527123848515865, "grad_norm": 0.32625347302412766, "learning_rate": 9.790705325056735e-06, "loss": 0.3771, "step": 270 }, { "epoch": 0.5731832139201638, "grad_norm": 0.31108860222980084, "learning_rate": 9.755282581475769e-06, "loss": 0.3694, "step": 280 }, { "epoch": 0.593654042988741, "grad_norm": 0.35683232841035667, "learning_rate": 9.717166395369312e-06, "loss": 0.374, "step": 290 }, { "epoch": 0.6141248720573184, "grad_norm": 0.30708155807016757, "learning_rate": 9.676378356149733e-06, "loss": 0.3671, "step": 300 }, { "epoch": 0.6345957011258956, "grad_norm": 0.3512172588847162, "learning_rate": 9.632941566595357e-06, "loss": 0.3674, "step": 310 }, { "epoch": 0.6550665301944729, "grad_norm": 0.32150553015980243, "learning_rate": 9.586880629764817e-06, "loss": 0.3732, "step": 320 }, { "epoch": 0.6755373592630501, "grad_norm": 0.28994930563644283, "learning_rate": 9.538221635061611e-06, "loss": 0.3748, "step": 330 }, { "epoch": 0.6960081883316275, "grad_norm": 0.3317951897221946, "learning_rate": 9.486992143456792e-06, "loss": 0.3652, "step": 340 }, { "epoch": 0.7164790174002047, "grad_norm": 0.31325853168901024, "learning_rate": 9.433221171878144e-06, "loss": 0.3647, "step": 350 }, { "epoch": 0.736949846468782, "grad_norm": 0.3687088471057981, "learning_rate": 9.376939176774678e-06, "loss": 0.3624, "step": 360 }, { "epoch": 0.7574206755373593, "grad_norm": 0.3237568256415363, "learning_rate": 9.318178036865786e-06, "loss": 0.3595, "step": 370 }, { "epoch": 0.7778915046059366, "grad_norm": 0.29274287364928764, "learning_rate": 9.256971035084786e-06, "loss": 0.363, "step": 380 }, { "epoch": 0.7983623336745138, "grad_norm": 0.29836089389437453, "learning_rate": 9.193352839727122e-06, "loss": 0.3681, "step": 390 }, { "epoch": 0.8188331627430911, "grad_norm": 0.30001387212541714, "learning_rate": 9.12735948481387e-06, "loss": 0.3666, "step": 400 }, { "epoch": 0.8393039918116684, "grad_norm": 0.312461464326523, "learning_rate": 9.059028349681693e-06, "loss": 0.3672, "step": 410 }, { "epoch": 0.8597748208802457, "grad_norm": 0.2835800419598021, "learning_rate": 8.988398137810778e-06, "loss": 0.3512, "step": 420 }, { "epoch": 0.8802456499488229, "grad_norm": 0.3003334841564673, "learning_rate": 8.915508854902778e-06, "loss": 0.3649, "step": 430 }, { "epoch": 0.9007164790174002, "grad_norm": 0.32025481154259877, "learning_rate": 8.84040178622116e-06, "loss": 0.3596, "step": 440 }, { "epoch": 0.9211873080859775, "grad_norm": 0.3115117787294787, "learning_rate": 8.763119473206795e-06, "loss": 0.3608, "step": 450 }, { "epoch": 0.9416581371545547, "grad_norm": 0.3425972446675102, "learning_rate": 8.683705689382025e-06, "loss": 0.3637, "step": 460 }, { "epoch": 0.962128966223132, "grad_norm": 0.3663718766106508, "learning_rate": 8.602205415556889e-06, "loss": 0.3581, "step": 470 }, { "epoch": 0.9825997952917093, "grad_norm": 0.37122946179964184, "learning_rate": 8.518664814351502e-06, "loss": 0.363, "step": 480 }, { "epoch": 1.0020470829068577, "grad_norm": 0.35006617529270384, "learning_rate": 8.433131204049067e-06, "loss": 0.3605, "step": 490 }, { "epoch": 1.022517911975435, "grad_norm": 0.3740591080146805, "learning_rate": 8.345653031794292e-06, "loss": 0.3366, "step": 500 }, { "epoch": 1.0429887410440122, "grad_norm": 0.3162453200296232, "learning_rate": 8.25627984615241e-06, "loss": 0.3399, "step": 510 }, { "epoch": 1.0634595701125895, "grad_norm": 0.3459734066982941, "learning_rate": 8.165062269044353e-06, "loss": 0.3347, "step": 520 }, { "epoch": 1.0839303991811668, "grad_norm": 0.3754414242837869, "learning_rate": 8.072051967073955e-06, "loss": 0.3393, "step": 530 }, { "epoch": 1.1044012282497442, "grad_norm": 0.31310887226269396, "learning_rate": 7.97730162226344e-06, "loss": 0.3378, "step": 540 }, { "epoch": 1.1248720573183213, "grad_norm": 0.2743343327695542, "learning_rate": 7.880864902213765e-06, "loss": 0.3339, "step": 550 }, { "epoch": 1.1453428863868986, "grad_norm": 0.29488856378638867, "learning_rate": 7.782796429706721e-06, "loss": 0.3371, "step": 560 }, { "epoch": 1.165813715455476, "grad_norm": 0.31936132904356773, "learning_rate": 7.683151751766005e-06, "loss": 0.3353, "step": 570 }, { "epoch": 1.1862845445240533, "grad_norm": 0.2862668653895022, "learning_rate": 7.5819873081948105e-06, "loss": 0.3437, "step": 580 }, { "epoch": 1.2067553735926304, "grad_norm": 0.373142212943522, "learning_rate": 7.479360399607707e-06, "loss": 0.34, "step": 590 }, { "epoch": 1.2272262026612077, "grad_norm": 0.26627867428916774, "learning_rate": 7.3753291549749764e-06, "loss": 0.3359, "step": 600 }, { "epoch": 1.247697031729785, "grad_norm": 0.29276632404031816, "learning_rate": 7.269952498697734e-06, "loss": 0.3332, "step": 610 }, { "epoch": 1.2681678607983624, "grad_norm": 0.28433544101185126, "learning_rate": 7.163290117232542e-06, "loss": 0.3282, "step": 620 }, { "epoch": 1.2886386898669397, "grad_norm": 0.2953581704843155, "learning_rate": 7.055402425284346e-06, "loss": 0.3367, "step": 630 }, { "epoch": 1.3091095189355169, "grad_norm": 0.33230185564417497, "learning_rate": 6.946350531586959e-06, "loss": 0.33, "step": 640 }, { "epoch": 1.3295803480040942, "grad_norm": 0.2886636563529011, "learning_rate": 6.836196204290417e-06, "loss": 0.3396, "step": 650 }, { "epoch": 1.3500511770726713, "grad_norm": 0.2999611703532613, "learning_rate": 6.725001835974854e-06, "loss": 0.3393, "step": 660 }, { "epoch": 1.3705220061412486, "grad_norm": 0.2726538110659223, "learning_rate": 6.612830408310671e-06, "loss": 0.3312, "step": 670 }, { "epoch": 1.390992835209826, "grad_norm": 0.291476742075843, "learning_rate": 6.499745456385054e-06, "loss": 0.3351, "step": 680 }, { "epoch": 1.4114636642784033, "grad_norm": 0.31263083981840367, "learning_rate": 6.385811032715031e-06, "loss": 0.3288, "step": 690 }, { "epoch": 1.4319344933469806, "grad_norm": 0.2902918227753739, "learning_rate": 6.271091670967437e-06, "loss": 0.3352, "step": 700 }, { "epoch": 1.4524053224155578, "grad_norm": 0.28079102264241496, "learning_rate": 6.155652349406366e-06, "loss": 0.335, "step": 710 }, { "epoch": 1.472876151484135, "grad_norm": 0.29347480666251813, "learning_rate": 6.039558454088796e-06, "loss": 0.3363, "step": 720 }, { "epoch": 1.4933469805527124, "grad_norm": 0.29437779600755265, "learning_rate": 5.922875741829227e-06, "loss": 0.3341, "step": 730 }, { "epoch": 1.5138178096212895, "grad_norm": 0.32924496076891324, "learning_rate": 5.805670302954322e-06, "loss": 0.3376, "step": 740 }, { "epoch": 1.5342886386898669, "grad_norm": 0.28214414735311516, "learning_rate": 5.688008523868646e-06, "loss": 0.3316, "step": 750 }, { "epoch": 1.5547594677584442, "grad_norm": 0.27441915869668093, "learning_rate": 5.569957049452703e-06, "loss": 0.3334, "step": 760 }, { "epoch": 1.5752302968270215, "grad_norm": 0.2832467579497326, "learning_rate": 5.451582745314576e-06, "loss": 0.3338, "step": 770 }, { "epoch": 1.5957011258955989, "grad_norm": 0.2662158568853315, "learning_rate": 5.33295265991652e-06, "loss": 0.3394, "step": 780 }, { "epoch": 1.6161719549641762, "grad_norm": 0.28021626464260035, "learning_rate": 5.214133986598014e-06, "loss": 0.3401, "step": 790 }, { "epoch": 1.6366427840327533, "grad_norm": 0.27748535569979166, "learning_rate": 5.095194025516733e-06, "loss": 0.3389, "step": 800 }, { "epoch": 1.6571136131013307, "grad_norm": 0.27557614607505543, "learning_rate": 4.976200145529039e-06, "loss": 0.3297, "step": 810 }, { "epoch": 1.6775844421699078, "grad_norm": 0.29920349158775145, "learning_rate": 4.85721974603152e-06, "loss": 0.3332, "step": 820 }, { "epoch": 1.698055271238485, "grad_norm": 0.28020907502801123, "learning_rate": 4.738320218785281e-06, "loss": 0.3331, "step": 830 }, { "epoch": 1.7185261003070624, "grad_norm": 0.275720710241024, "learning_rate": 4.619568909744524e-06, "loss": 0.334, "step": 840 }, { "epoch": 1.7389969293756398, "grad_norm": 0.2981912122148231, "learning_rate": 4.501033080911087e-06, "loss": 0.3275, "step": 850 }, { "epoch": 1.759467758444217, "grad_norm": 0.2867885235447855, "learning_rate": 4.382779872236527e-06, "loss": 0.3279, "step": 860 }, { "epoch": 1.7799385875127944, "grad_norm": 0.3130758313387298, "learning_rate": 4.264876263593347e-06, "loss": 0.3339, "step": 870 }, { "epoch": 1.8004094165813715, "grad_norm": 0.2964510943375963, "learning_rate": 4.147389036836881e-06, "loss": 0.3279, "step": 880 }, { "epoch": 1.8208802456499487, "grad_norm": 0.2583942550882026, "learning_rate": 4.030384737979345e-06, "loss": 0.3286, "step": 890 }, { "epoch": 1.841351074718526, "grad_norm": 0.2922177868095114, "learning_rate": 3.913929639497462e-06, "loss": 0.3343, "step": 900 }, { "epoch": 1.8618219037871033, "grad_norm": 0.28649431693767013, "learning_rate": 3.798089702795038e-06, "loss": 0.337, "step": 910 }, { "epoch": 1.8822927328556807, "grad_norm": 0.2719777009560596, "learning_rate": 3.682930540841717e-06, "loss": 0.3255, "step": 920 }, { "epoch": 1.902763561924258, "grad_norm": 0.2592856290273692, "learning_rate": 3.568517381009099e-06, "loss": 0.3334, "step": 930 }, { "epoch": 1.9232343909928353, "grad_norm": 0.2669776100626122, "learning_rate": 3.4549150281252635e-06, "loss": 0.3274, "step": 940 }, { "epoch": 1.9437052200614124, "grad_norm": 0.2644660634287941, "learning_rate": 3.3421878277686315e-06, "loss": 0.329, "step": 950 }, { "epoch": 1.9641760491299898, "grad_norm": 0.255388401567599, "learning_rate": 3.230399629821942e-06, "loss": 0.333, "step": 960 }, { "epoch": 1.9846468781985669, "grad_norm": 0.26076402769472123, "learning_rate": 3.119613752307002e-06, "loss": 0.3277, "step": 970 }, { "epoch": 2.0040941658137155, "grad_norm": 0.34035031287023115, "learning_rate": 3.0098929455206905e-06, "loss": 0.3239, "step": 980 }, { "epoch": 2.024564994882293, "grad_norm": 0.26481931821481197, "learning_rate": 2.901299356492516e-06, "loss": 0.3082, "step": 990 }, { "epoch": 2.04503582395087, "grad_norm": 0.27840797715546095, "learning_rate": 2.7938944937838924e-06, "loss": 0.3141, "step": 1000 }, { "epoch": 2.0655066530194475, "grad_norm": 0.264803380198392, "learning_rate": 2.687739192649026e-06, "loss": 0.309, "step": 1010 }, { "epoch": 2.0859774820880244, "grad_norm": 0.2503878058457451, "learning_rate": 2.5828935805771804e-06, "loss": 0.3055, "step": 1020 }, { "epoch": 2.1064483111566017, "grad_norm": 0.24288791515168753, "learning_rate": 2.4794170432358415e-06, "loss": 0.3101, "step": 1030 }, { "epoch": 2.126919140225179, "grad_norm": 0.3260568670065737, "learning_rate": 2.3773681908340284e-06, "loss": 0.3174, "step": 1040 }, { "epoch": 2.1473899692937564, "grad_norm": 0.2752973297448372, "learning_rate": 2.2768048249248648e-06, "loss": 0.3161, "step": 1050 }, { "epoch": 2.1678607983623337, "grad_norm": 0.2525589153397712, "learning_rate": 2.1777839056661555e-06, "loss": 0.3127, "step": 1060 }, { "epoch": 2.188331627430911, "grad_norm": 0.2721221125171894, "learning_rate": 2.080361519557548e-06, "loss": 0.3095, "step": 1070 }, { "epoch": 2.2088024564994884, "grad_norm": 0.256857141944826, "learning_rate": 1.9845928476725522e-06, "loss": 0.3117, "step": 1080 }, { "epoch": 2.2292732855680657, "grad_norm": 0.23983629928731875, "learning_rate": 1.89053213440339e-06, "loss": 0.3096, "step": 1090 }, { "epoch": 2.2497441146366426, "grad_norm": 0.2576559289401722, "learning_rate": 1.798232656736389e-06, "loss": 0.3167, "step": 1100 }, { "epoch": 2.27021494370522, "grad_norm": 0.25400768886970904, "learning_rate": 1.7077466940753446e-06, "loss": 0.3085, "step": 1110 }, { "epoch": 2.2906857727737973, "grad_norm": 0.2464137122590109, "learning_rate": 1.6191254986299044e-06, "loss": 0.309, "step": 1120 }, { "epoch": 2.3111566018423746, "grad_norm": 0.24550795789449772, "learning_rate": 1.5324192663857673e-06, "loss": 0.3159, "step": 1130 }, { "epoch": 2.331627430910952, "grad_norm": 0.28852640148423236, "learning_rate": 1.4476771086731567e-06, "loss": 0.3123, "step": 1140 }, { "epoch": 2.3520982599795293, "grad_norm": 0.37687841751171514, "learning_rate": 1.3649470243496327e-06, "loss": 0.3098, "step": 1150 }, { "epoch": 2.3725690890481066, "grad_norm": 0.25339405885205124, "learning_rate": 1.2842758726130283e-06, "loss": 0.308, "step": 1160 }, { "epoch": 2.393039918116684, "grad_norm": 0.2487646284184678, "learning_rate": 1.2057093464599156e-06, "loss": 0.3127, "step": 1170 }, { "epoch": 2.413510747185261, "grad_norm": 0.32463394959288167, "learning_rate": 1.1292919468045876e-06, "loss": 0.3139, "step": 1180 }, { "epoch": 2.433981576253838, "grad_norm": 0.255238902256777, "learning_rate": 1.0550669572732862e-06, "loss": 0.3111, "step": 1190 }, { "epoch": 2.4544524053224155, "grad_norm": 0.23908874761946466, "learning_rate": 9.830764196878872e-07, "loss": 0.3164, "step": 1200 }, { "epoch": 2.474923234390993, "grad_norm": 0.2649523347415388, "learning_rate": 9.133611102529655e-07, "loss": 0.3149, "step": 1210 }, { "epoch": 2.49539406345957, "grad_norm": 0.24534103849668815, "learning_rate": 8.459605164597268e-07, "loss": 0.3098, "step": 1220 }, { "epoch": 2.5158648925281475, "grad_norm": 0.2416421159869344, "learning_rate": 7.809128147198692e-07, "loss": 0.3091, "step": 1230 }, { "epoch": 2.536335721596725, "grad_norm": 0.23831181790073264, "learning_rate": 7.182548487420555e-07, "loss": 0.3118, "step": 1240 }, { "epoch": 2.5568065506653017, "grad_norm": 0.23798865253936233, "learning_rate": 6.580221086632516e-07, "loss": 0.3138, "step": 1250 }, { "epoch": 2.5772773797338795, "grad_norm": 0.2483650737490233, "learning_rate": 6.002487109467347e-07, "loss": 0.3044, "step": 1260 }, { "epoch": 2.5977482088024564, "grad_norm": 0.24574354382203337, "learning_rate": 5.449673790581611e-07, "loss": 0.3117, "step": 1270 }, { "epoch": 2.6182190378710337, "grad_norm": 0.25945540600991146, "learning_rate": 4.922094249306559e-07, "loss": 0.3077, "step": 1280 }, { "epoch": 2.638689866939611, "grad_norm": 0.2376843101597617, "learning_rate": 4.420047312293946e-07, "loss": 0.3099, "step": 1290 }, { "epoch": 2.6591606960081884, "grad_norm": 0.23445126717886705, "learning_rate": 3.9438173442575e-07, "loss": 0.3153, "step": 1300 }, { "epoch": 2.6796315250767657, "grad_norm": 0.23799144075624934, "learning_rate": 3.4936740869057075e-07, "loss": 0.3052, "step": 1310 }, { "epoch": 2.7001023541453426, "grad_norm": 0.23443772087547457, "learning_rate": 3.069872506157212e-07, "loss": 0.3077, "step": 1320 }, { "epoch": 2.7205731832139204, "grad_norm": 0.24404450847384368, "learning_rate": 2.6726526477254986e-07, "loss": 0.3111, "step": 1330 }, { "epoch": 2.7410440122824973, "grad_norm": 0.2537534925687698, "learning_rate": 2.3022395011543687e-07, "loss": 0.3127, "step": 1340 }, { "epoch": 2.7615148413510746, "grad_norm": 0.2531714733259407, "learning_rate": 1.9588428723814945e-07, "loss": 0.3126, "step": 1350 }, { "epoch": 2.781985670419652, "grad_norm": 0.2476065493877303, "learning_rate": 1.6426572649021477e-07, "loss": 0.3147, "step": 1360 }, { "epoch": 2.8024564994882293, "grad_norm": 0.22861950264891634, "learning_rate": 1.3538617696003066e-07, "loss": 0.3206, "step": 1370 }, { "epoch": 2.8229273285568066, "grad_norm": 0.23238655363179303, "learning_rate": 1.0926199633097156e-07, "loss": 0.3074, "step": 1380 }, { "epoch": 2.843398157625384, "grad_norm": 0.25027856224860606, "learning_rate": 8.590798161622227e-08, "loss": 0.3086, "step": 1390 }, { "epoch": 2.8638689866939613, "grad_norm": 0.45100936356107935, "learning_rate": 6.533736077758868e-08, "loss": 0.3089, "step": 1400 }, { "epoch": 2.884339815762538, "grad_norm": 0.23851515762515696, "learning_rate": 4.756178523304622e-08, "loss": 0.3082, "step": 1410 }, { "epoch": 2.9048106448311155, "grad_norm": 0.23121697809405467, "learning_rate": 3.25913232572489e-08, "loss": 0.3124, "step": 1420 }, { "epoch": 2.925281473899693, "grad_norm": 0.23935340813095157, "learning_rate": 2.0434454278752126e-08, "loss": 0.3122, "step": 1430 }, { "epoch": 2.94575230296827, "grad_norm": 0.24056630460754483, "learning_rate": 1.109806407717462e-08, "loss": 0.3094, "step": 1440 }, { "epoch": 2.9662231320368475, "grad_norm": 0.24275000924008874, "learning_rate": 4.587440883021543e-09, "loss": 0.3058, "step": 1450 }, { "epoch": 2.986693961105425, "grad_norm": 0.2672744704384668, "learning_rate": 9.062723823710651e-10, "loss": 0.3045, "step": 1460 } ], "logging_steps": 10, "max_steps": 1467, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 10000000, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 4881065357344768.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }