| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9965397923875432, | |
| "eval_steps": 500, | |
| "global_step": 144, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.006920415224913495, | |
| "grad_norm": 5.909927412110894, | |
| "learning_rate": 4.000000000000001e-06, | |
| "loss": 0.1796, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01384083044982699, | |
| "grad_norm": 5.814173094234023, | |
| "learning_rate": 8.000000000000001e-06, | |
| "loss": 0.1745, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.020761245674740483, | |
| "grad_norm": 7.527394332552472, | |
| "learning_rate": 1.2e-05, | |
| "loss": 0.1664, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02768166089965398, | |
| "grad_norm": 6.411723498568909, | |
| "learning_rate": 1.6000000000000003e-05, | |
| "loss": 0.1111, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.03460207612456748, | |
| "grad_norm": 29.463780179754565, | |
| "learning_rate": 2e-05, | |
| "loss": 0.3775, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.04152249134948097, | |
| "grad_norm": 25.873155743529786, | |
| "learning_rate": 1.999744599547812e-05, | |
| "loss": 0.5048, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.04844290657439446, | |
| "grad_norm": 6.21107647977612, | |
| "learning_rate": 1.9989785286500294e-05, | |
| "loss": 0.1919, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.05536332179930796, | |
| "grad_norm": 2.467176199809234, | |
| "learning_rate": 1.99770217861636e-05, | |
| "loss": 0.1488, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.06228373702422145, | |
| "grad_norm": 3.511922315343916, | |
| "learning_rate": 1.9959162014075553e-05, | |
| "loss": 0.1299, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.06920415224913495, | |
| "grad_norm": 1.5637990196383564, | |
| "learning_rate": 1.9936215093023884e-05, | |
| "loss": 0.1313, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.07612456747404844, | |
| "grad_norm": 5.108268285094946, | |
| "learning_rate": 1.990819274431662e-05, | |
| "loss": 0.092, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.08304498269896193, | |
| "grad_norm": 4.9693481281925465, | |
| "learning_rate": 1.9875109281794828e-05, | |
| "loss": 0.1171, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.08996539792387544, | |
| "grad_norm": 7.995002644534826, | |
| "learning_rate": 1.9836981604521077e-05, | |
| "loss": 0.1178, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.09688581314878893, | |
| "grad_norm": 3.4504191020747883, | |
| "learning_rate": 1.9793829188147406e-05, | |
| "loss": 0.0989, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.10380622837370242, | |
| "grad_norm": 8.263808135194267, | |
| "learning_rate": 1.974567407496712e-05, | |
| "loss": 0.1486, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.11072664359861592, | |
| "grad_norm": 1.367572738961488, | |
| "learning_rate": 1.9692540862655587e-05, | |
| "loss": 0.0847, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.11764705882352941, | |
| "grad_norm": 5.4076849647712635, | |
| "learning_rate": 1.9634456691705705e-05, | |
| "loss": 0.1004, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.1245674740484429, | |
| "grad_norm": 1.455150235552633, | |
| "learning_rate": 1.9571451231564523e-05, | |
| "loss": 0.0776, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.1314878892733564, | |
| "grad_norm": 0.9765353662178354, | |
| "learning_rate": 1.9503556665478066e-05, | |
| "loss": 0.0501, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.1384083044982699, | |
| "grad_norm": 3.1660835804785594, | |
| "learning_rate": 1.9430807674052092e-05, | |
| "loss": 0.0676, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1453287197231834, | |
| "grad_norm": 4.601906713563019, | |
| "learning_rate": 1.9353241417537216e-05, | |
| "loss": 0.1148, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.1522491349480969, | |
| "grad_norm": 0.9410185517641271, | |
| "learning_rate": 1.9270897516847406e-05, | |
| "loss": 0.0644, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.15916955017301038, | |
| "grad_norm": 2.003001609282354, | |
| "learning_rate": 1.9183818033321612e-05, | |
| "loss": 0.0365, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.16608996539792387, | |
| "grad_norm": 3.8004697116265125, | |
| "learning_rate": 1.9092047447238775e-05, | |
| "loss": 0.0601, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.17301038062283736, | |
| "grad_norm": 1.505231605536048, | |
| "learning_rate": 1.899563263509725e-05, | |
| "loss": 0.032, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.17993079584775087, | |
| "grad_norm": 1.4483444591893908, | |
| "learning_rate": 1.8894622845670282e-05, | |
| "loss": 0.0814, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.18685121107266436, | |
| "grad_norm": 1.769291133502307, | |
| "learning_rate": 1.878906967484966e-05, | |
| "loss": 0.0835, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.19377162629757785, | |
| "grad_norm": 1.6052993878109532, | |
| "learning_rate": 1.86790270392905e-05, | |
| "loss": 0.0508, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.20069204152249134, | |
| "grad_norm": 3.4046119290691355, | |
| "learning_rate": 1.856455114887056e-05, | |
| "loss": 0.0769, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.20761245674740483, | |
| "grad_norm": 2.3275130236844026, | |
| "learning_rate": 1.8445700477978207e-05, | |
| "loss": 0.1246, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.21453287197231835, | |
| "grad_norm": 3.059909729816116, | |
| "learning_rate": 1.8322535735643604e-05, | |
| "loss": 0.07, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.22145328719723184, | |
| "grad_norm": 4.494006378640971, | |
| "learning_rate": 1.8195119834528535e-05, | |
| "loss": 0.0606, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.22837370242214533, | |
| "grad_norm": 1.1539839844534825, | |
| "learning_rate": 1.8063517858790517e-05, | |
| "loss": 0.0648, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 1.5380191902785147, | |
| "learning_rate": 1.792779703083777e-05, | |
| "loss": 0.0913, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.2422145328719723, | |
| "grad_norm": 0.7918508463404255, | |
| "learning_rate": 1.778802667699196e-05, | |
| "loss": 0.0299, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.2491349480968858, | |
| "grad_norm": 2.1853629013025704, | |
| "learning_rate": 1.764427819207624e-05, | |
| "loss": 0.0583, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.2560553633217993, | |
| "grad_norm": 2.316866722784186, | |
| "learning_rate": 1.7496625002946702e-05, | |
| "loss": 0.0543, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.2629757785467128, | |
| "grad_norm": 0.6907292526164213, | |
| "learning_rate": 1.734514253098589e-05, | |
| "loss": 0.0436, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2698961937716263, | |
| "grad_norm": 0.6929541264038483, | |
| "learning_rate": 1.7189908153577473e-05, | |
| "loss": 0.059, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.2768166089965398, | |
| "grad_norm": 0.766614669335446, | |
| "learning_rate": 1.7031001164581828e-05, | |
| "loss": 0.0364, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2837370242214533, | |
| "grad_norm": 1.1432954678059355, | |
| "learning_rate": 1.6868502733832647e-05, | |
| "loss": 0.0639, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.2906574394463668, | |
| "grad_norm": 1.4246783694756413, | |
| "learning_rate": 1.670249586567531e-05, | |
| "loss": 0.028, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.2975778546712803, | |
| "grad_norm": 0.6960925404059692, | |
| "learning_rate": 1.6533065356568206e-05, | |
| "loss": 0.0563, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.3044982698961938, | |
| "grad_norm": 0.917801830468414, | |
| "learning_rate": 1.636029775176862e-05, | |
| "loss": 0.0645, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.31141868512110726, | |
| "grad_norm": 1.147360995244464, | |
| "learning_rate": 1.618428130112533e-05, | |
| "loss": 0.0483, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.31833910034602075, | |
| "grad_norm": 1.0760514929547755, | |
| "learning_rate": 1.6005105914000508e-05, | |
| "loss": 0.0466, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.32525951557093424, | |
| "grad_norm": 2.0668922589924006, | |
| "learning_rate": 1.5822863113343934e-05, | |
| "loss": 0.0343, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.33217993079584773, | |
| "grad_norm": 1.1035230066017743, | |
| "learning_rate": 1.5637645988943008e-05, | |
| "loss": 0.0198, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.3391003460207612, | |
| "grad_norm": 0.5094633252436404, | |
| "learning_rate": 1.544954914987238e-05, | |
| "loss": 0.0405, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.3460207612456747, | |
| "grad_norm": 1.4387866581529392, | |
| "learning_rate": 1.5258668676167548e-05, | |
| "loss": 0.046, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.35294117647058826, | |
| "grad_norm": 0.7482935385793746, | |
| "learning_rate": 1.5065102069747117e-05, | |
| "loss": 0.027, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.35986159169550175, | |
| "grad_norm": 3.7792094686292246, | |
| "learning_rate": 1.48689482046087e-05, | |
| "loss": 0.0581, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.36678200692041524, | |
| "grad_norm": 1.3731751352374644, | |
| "learning_rate": 1.467030727632401e-05, | |
| "loss": 0.0228, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.3737024221453287, | |
| "grad_norm": 0.7887909443777626, | |
| "learning_rate": 1.4469280750858854e-05, | |
| "loss": 0.0739, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.3806228373702422, | |
| "grad_norm": 0.8647483470113037, | |
| "learning_rate": 1.4265971312744252e-05, | |
| "loss": 0.0551, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.3875432525951557, | |
| "grad_norm": 1.2742301466453625, | |
| "learning_rate": 1.4060482812625055e-05, | |
| "loss": 0.0364, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.3944636678200692, | |
| "grad_norm": 0.37834231118319656, | |
| "learning_rate": 1.3852920214212966e-05, | |
| "loss": 0.0229, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.4013840830449827, | |
| "grad_norm": 0.38818516965237315, | |
| "learning_rate": 1.3643389540670963e-05, | |
| "loss": 0.0188, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.4083044982698962, | |
| "grad_norm": 1.1203564083475976, | |
| "learning_rate": 1.3431997820456592e-05, | |
| "loss": 0.0295, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.41522491349480967, | |
| "grad_norm": 2.7193984196484697, | |
| "learning_rate": 1.3218853032651719e-05, | |
| "loss": 0.0592, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.42214532871972316, | |
| "grad_norm": 0.8457919661498918, | |
| "learning_rate": 1.3004064051806712e-05, | |
| "loss": 0.0559, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.4290657439446367, | |
| "grad_norm": 1.9644511219937209, | |
| "learning_rate": 1.2787740592327232e-05, | |
| "loss": 0.0755, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.4359861591695502, | |
| "grad_norm": 2.8810823496302977, | |
| "learning_rate": 1.2569993152432028e-05, | |
| "loss": 0.0771, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.4429065743944637, | |
| "grad_norm": 1.237673547458137, | |
| "learning_rate": 1.2350932957710322e-05, | |
| "loss": 0.0161, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.44982698961937717, | |
| "grad_norm": 1.0351256257207866, | |
| "learning_rate": 1.2130671904307692e-05, | |
| "loss": 0.0285, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.45674740484429066, | |
| "grad_norm": 2.390190069024017, | |
| "learning_rate": 1.1909322501769407e-05, | |
| "loss": 0.0595, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.46366782006920415, | |
| "grad_norm": 0.4602512676359961, | |
| "learning_rate": 1.1686997815570473e-05, | |
| "loss": 0.0565, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.5724949291122662, | |
| "learning_rate": 1.1463811409361667e-05, | |
| "loss": 0.0306, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.47750865051903113, | |
| "grad_norm": 0.6234367847233119, | |
| "learning_rate": 1.1239877286961123e-05, | |
| "loss": 0.041, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.4844290657439446, | |
| "grad_norm": 0.6525151506863333, | |
| "learning_rate": 1.1015309834121083e-05, | |
| "loss": 0.0315, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.4913494809688581, | |
| "grad_norm": 1.2107180201820262, | |
| "learning_rate": 1.079022376009955e-05, | |
| "loss": 0.0463, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.4982698961937716, | |
| "grad_norm": 0.36904102477700823, | |
| "learning_rate": 1.05647340390667e-05, | |
| "loss": 0.0354, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.5051903114186851, | |
| "grad_norm": 0.4623564155552934, | |
| "learning_rate": 1.0338955851375962e-05, | |
| "loss": 0.0401, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.5121107266435986, | |
| "grad_norm": 0.4464635221070512, | |
| "learning_rate": 1.01130045247298e-05, | |
| "loss": 0.0178, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.5190311418685121, | |
| "grad_norm": 0.8151026231175525, | |
| "learning_rate": 9.886995475270205e-06, | |
| "loss": 0.0339, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.5259515570934256, | |
| "grad_norm": 0.8737807325813413, | |
| "learning_rate": 9.661044148624038e-06, | |
| "loss": 0.0431, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.532871972318339, | |
| "grad_norm": 0.5650128573973728, | |
| "learning_rate": 9.435265960933304e-06, | |
| "loss": 0.0429, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.5397923875432526, | |
| "grad_norm": 2.3196808467192658, | |
| "learning_rate": 9.209776239900453e-06, | |
| "loss": 0.0744, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.5467128027681661, | |
| "grad_norm": 0.6763919787895529, | |
| "learning_rate": 8.98469016587892e-06, | |
| "loss": 0.0273, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.5536332179930796, | |
| "grad_norm": 0.73804041555226, | |
| "learning_rate": 8.76012271303888e-06, | |
| "loss": 0.0414, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5605536332179931, | |
| "grad_norm": 0.4375261353904343, | |
| "learning_rate": 8.536188590638334e-06, | |
| "loss": 0.0489, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.5674740484429066, | |
| "grad_norm": 1.9813329567182527, | |
| "learning_rate": 8.313002184429529e-06, | |
| "loss": 0.0455, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.5743944636678201, | |
| "grad_norm": 0.448941103281106, | |
| "learning_rate": 8.090677498230598e-06, | |
| "loss": 0.0432, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.5813148788927336, | |
| "grad_norm": 0.9180761063192592, | |
| "learning_rate": 7.869328095692313e-06, | |
| "loss": 0.0234, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 0.5883629574508615, | |
| "learning_rate": 7.649067042289681e-06, | |
| "loss": 0.0509, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.5951557093425606, | |
| "grad_norm": 0.8009555104412699, | |
| "learning_rate": 7.430006847567972e-06, | |
| "loss": 0.0282, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.6020761245674741, | |
| "grad_norm": 1.3285299052953212, | |
| "learning_rate": 7.2122594076727705e-06, | |
| "loss": 0.0514, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.6089965397923875, | |
| "grad_norm": 0.8852543518710448, | |
| "learning_rate": 6.995935948193294e-06, | |
| "loss": 0.0248, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.615916955017301, | |
| "grad_norm": 2.3353752448807725, | |
| "learning_rate": 6.781146967348283e-06, | |
| "loss": 0.0693, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.6228373702422145, | |
| "grad_norm": 1.3882240308976475, | |
| "learning_rate": 6.568002179543409e-06, | |
| "loss": 0.0407, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.629757785467128, | |
| "grad_norm": 1.183088785309517, | |
| "learning_rate": 6.356610459329038e-06, | |
| "loss": 0.0234, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.6366782006920415, | |
| "grad_norm": 1.0365553239602958, | |
| "learning_rate": 6.147079785787038e-06, | |
| "loss": 0.0672, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.643598615916955, | |
| "grad_norm": 0.6479773351825772, | |
| "learning_rate": 5.93951718737495e-06, | |
| "loss": 0.0516, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.6505190311418685, | |
| "grad_norm": 0.5248885554897967, | |
| "learning_rate": 5.7340286872557515e-06, | |
| "loss": 0.0302, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.657439446366782, | |
| "grad_norm": 0.6857902639461477, | |
| "learning_rate": 5.530719249141148e-06, | |
| "loss": 0.0418, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.6643598615916955, | |
| "grad_norm": 0.7622230565978657, | |
| "learning_rate": 5.329692723675994e-06, | |
| "loss": 0.0302, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.671280276816609, | |
| "grad_norm": 0.5694955322805975, | |
| "learning_rate": 5.131051795391302e-06, | |
| "loss": 0.0297, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.6782006920415224, | |
| "grad_norm": 0.48280429993709745, | |
| "learning_rate": 4.934897930252887e-06, | |
| "loss": 0.0467, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.6851211072664359, | |
| "grad_norm": 0.7969826708541765, | |
| "learning_rate": 4.7413313238324556e-06, | |
| "loss": 0.0431, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.6920415224913494, | |
| "grad_norm": 0.40791439903766624, | |
| "learning_rate": 4.550450850127626e-06, | |
| "loss": 0.0296, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.698961937716263, | |
| "grad_norm": 0.8229666980540179, | |
| "learning_rate": 4.3623540110569935e-06, | |
| "loss": 0.068, | |
| "step": 101 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.3873805504039957, | |
| "learning_rate": 4.177136886656067e-06, | |
| "loss": 0.0395, | |
| "step": 102 | |
| }, | |
| { | |
| "epoch": 0.71280276816609, | |
| "grad_norm": 0.6160253305799199, | |
| "learning_rate": 3.9948940859994964e-06, | |
| "loss": 0.0426, | |
| "step": 103 | |
| }, | |
| { | |
| "epoch": 0.7197231833910035, | |
| "grad_norm": 0.437203350354127, | |
| "learning_rate": 3.815718698874672e-06, | |
| "loss": 0.0493, | |
| "step": 104 | |
| }, | |
| { | |
| "epoch": 0.726643598615917, | |
| "grad_norm": 0.970248480584735, | |
| "learning_rate": 3.6397022482313804e-06, | |
| "loss": 0.0157, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.7335640138408305, | |
| "grad_norm": 1.0489044138676327, | |
| "learning_rate": 3.466934643431795e-06, | |
| "loss": 0.0223, | |
| "step": 106 | |
| }, | |
| { | |
| "epoch": 0.740484429065744, | |
| "grad_norm": 0.8154744910449274, | |
| "learning_rate": 3.2975041343246937e-06, | |
| "loss": 0.0372, | |
| "step": 107 | |
| }, | |
| { | |
| "epoch": 0.7474048442906575, | |
| "grad_norm": 0.8284356354573794, | |
| "learning_rate": 3.1314972661673572e-06, | |
| "loss": 0.0595, | |
| "step": 108 | |
| }, | |
| { | |
| "epoch": 0.754325259515571, | |
| "grad_norm": 0.891688730913265, | |
| "learning_rate": 2.9689988354181742e-06, | |
| "loss": 0.0371, | |
| "step": 109 | |
| }, | |
| { | |
| "epoch": 0.7612456747404844, | |
| "grad_norm": 0.5373575786911854, | |
| "learning_rate": 2.8100918464225304e-06, | |
| "loss": 0.0359, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7681660899653979, | |
| "grad_norm": 1.5437209149978486, | |
| "learning_rate": 2.654857469014113e-06, | |
| "loss": 0.0377, | |
| "step": 111 | |
| }, | |
| { | |
| "epoch": 0.7750865051903114, | |
| "grad_norm": 0.8917767418171114, | |
| "learning_rate": 2.5033749970533015e-06, | |
| "loss": 0.0489, | |
| "step": 112 | |
| }, | |
| { | |
| "epoch": 0.7820069204152249, | |
| "grad_norm": 0.6967641711242976, | |
| "learning_rate": 2.3557218079237608e-06, | |
| "loss": 0.0412, | |
| "step": 113 | |
| }, | |
| { | |
| "epoch": 0.7889273356401384, | |
| "grad_norm": 0.6010523621864098, | |
| "learning_rate": 2.211973323008041e-06, | |
| "loss": 0.0496, | |
| "step": 114 | |
| }, | |
| { | |
| "epoch": 0.7958477508650519, | |
| "grad_norm": 0.9326834234151709, | |
| "learning_rate": 2.072202969162234e-06, | |
| "loss": 0.0382, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.8027681660899654, | |
| "grad_norm": 0.28932924745655303, | |
| "learning_rate": 1.936482141209486e-06, | |
| "loss": 0.0246, | |
| "step": 116 | |
| }, | |
| { | |
| "epoch": 0.8096885813148789, | |
| "grad_norm": 0.3646152590947324, | |
| "learning_rate": 1.8048801654714687e-06, | |
| "loss": 0.0363, | |
| "step": 117 | |
| }, | |
| { | |
| "epoch": 0.8166089965397924, | |
| "grad_norm": 0.8316990911384655, | |
| "learning_rate": 1.6774642643563955e-06, | |
| "loss": 0.015, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.8235294117647058, | |
| "grad_norm": 0.7109476986868478, | |
| "learning_rate": 1.5542995220217961e-06, | |
| "loss": 0.0466, | |
| "step": 119 | |
| }, | |
| { | |
| "epoch": 0.8304498269896193, | |
| "grad_norm": 0.6558256138579013, | |
| "learning_rate": 1.4354488511294418e-06, | |
| "loss": 0.0493, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.8373702422145328, | |
| "grad_norm": 0.6071205282852766, | |
| "learning_rate": 1.3209729607095022e-06, | |
| "loss": 0.0185, | |
| "step": 121 | |
| }, | |
| { | |
| "epoch": 0.8442906574394463, | |
| "grad_norm": 0.8574874934268059, | |
| "learning_rate": 1.2109303251503434e-06, | |
| "loss": 0.0409, | |
| "step": 122 | |
| }, | |
| { | |
| "epoch": 0.8512110726643599, | |
| "grad_norm": 0.26203721412837916, | |
| "learning_rate": 1.1053771543297198e-06, | |
| "loss": 0.03, | |
| "step": 123 | |
| }, | |
| { | |
| "epoch": 0.8581314878892734, | |
| "grad_norm": 0.36209922289830276, | |
| "learning_rate": 1.0043673649027519e-06, | |
| "loss": 0.014, | |
| "step": 124 | |
| }, | |
| { | |
| "epoch": 0.8650519031141869, | |
| "grad_norm": 0.37375093500576706, | |
| "learning_rate": 9.079525527612321e-07, | |
| "loss": 0.0208, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.8719723183391004, | |
| "grad_norm": 0.9164555453155439, | |
| "learning_rate": 8.161819666783888e-07, | |
| "loss": 0.0563, | |
| "step": 126 | |
| }, | |
| { | |
| "epoch": 0.8788927335640139, | |
| "grad_norm": 0.7396537836277686, | |
| "learning_rate": 7.291024831525961e-07, | |
| "loss": 0.0516, | |
| "step": 127 | |
| }, | |
| { | |
| "epoch": 0.8858131487889274, | |
| "grad_norm": 0.7564027962900852, | |
| "learning_rate": 6.467585824627886e-07, | |
| "loss": 0.0797, | |
| "step": 128 | |
| }, | |
| { | |
| "epoch": 0.8927335640138409, | |
| "grad_norm": 0.701813356416935, | |
| "learning_rate": 5.691923259479093e-07, | |
| "loss": 0.0323, | |
| "step": 129 | |
| }, | |
| { | |
| "epoch": 0.8996539792387543, | |
| "grad_norm": 0.6642690626780311, | |
| "learning_rate": 4.964433345219354e-07, | |
| "loss": 0.027, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.9065743944636678, | |
| "grad_norm": 0.5832787512217212, | |
| "learning_rate": 4.285487684354772e-07, | |
| "loss": 0.0227, | |
| "step": 131 | |
| }, | |
| { | |
| "epoch": 0.9134948096885813, | |
| "grad_norm": 1.301649161039514, | |
| "learning_rate": 3.6554330829429716e-07, | |
| "loss": 0.0778, | |
| "step": 132 | |
| }, | |
| { | |
| "epoch": 0.9204152249134948, | |
| "grad_norm": 0.8528660745704756, | |
| "learning_rate": 3.0745913734441357e-07, | |
| "loss": 0.033, | |
| "step": 133 | |
| }, | |
| { | |
| "epoch": 0.9273356401384083, | |
| "grad_norm": 1.1082351009137044, | |
| "learning_rate": 2.5432592503288e-07, | |
| "loss": 0.0306, | |
| "step": 134 | |
| }, | |
| { | |
| "epoch": 0.9342560553633218, | |
| "grad_norm": 0.9544686893620227, | |
| "learning_rate": 2.0617081185259512e-07, | |
| "loss": 0.0434, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.4186137702661263, | |
| "learning_rate": 1.630183954789233e-07, | |
| "loss": 0.0275, | |
| "step": 136 | |
| }, | |
| { | |
| "epoch": 0.9480968858131488, | |
| "grad_norm": 0.8661220155566242, | |
| "learning_rate": 1.2489071820517394e-07, | |
| "loss": 0.0397, | |
| "step": 137 | |
| }, | |
| { | |
| "epoch": 0.9550173010380623, | |
| "grad_norm": 0.9542879421585415, | |
| "learning_rate": 9.180725568338045e-08, | |
| "loss": 0.0177, | |
| "step": 138 | |
| }, | |
| { | |
| "epoch": 0.9619377162629758, | |
| "grad_norm": 1.221781165267405, | |
| "learning_rate": 6.378490697611761e-08, | |
| "loss": 0.0439, | |
| "step": 139 | |
| }, | |
| { | |
| "epoch": 0.9688581314878892, | |
| "grad_norm": 0.47755949195114916, | |
| "learning_rate": 4.083798592444899e-08, | |
| "loss": 0.0573, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9757785467128027, | |
| "grad_norm": 0.562330479749174, | |
| "learning_rate": 2.2978213836400974e-08, | |
| "loss": 0.045, | |
| "step": 141 | |
| }, | |
| { | |
| "epoch": 0.9826989619377162, | |
| "grad_norm": 0.5335816510886274, | |
| "learning_rate": 1.0214713499706596e-08, | |
| "loss": 0.0416, | |
| "step": 142 | |
| }, | |
| { | |
| "epoch": 0.9896193771626297, | |
| "grad_norm": 0.3303782652790597, | |
| "learning_rate": 2.5540045218819256e-09, | |
| "loss": 0.0314, | |
| "step": 143 | |
| }, | |
| { | |
| "epoch": 0.9965397923875432, | |
| "grad_norm": 0.8440597744595137, | |
| "learning_rate": 0.0, | |
| "loss": 0.0266, | |
| "step": 144 | |
| }, | |
| { | |
| "epoch": 0.9965397923875432, | |
| "step": 144, | |
| "total_flos": 4.85462032515072e+16, | |
| "train_loss": 0.05981730037860365, | |
| "train_runtime": 2168.0646, | |
| "train_samples_per_second": 8.526, | |
| "train_steps_per_second": 0.066 | |
| } | |
| ], | |
| "logging_steps": 1.0, | |
| "max_steps": 144, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.85462032515072e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |