{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 222,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.2358,
      "step": 1
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.21,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.1914,
      "step": 3
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00011428571428571428,
      "loss": 0.2148,
      "step": 4
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014285714285714287,
      "loss": 0.1733,
      "step": 5
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00017142857142857143,
      "loss": 0.1304,
      "step": 6
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0002,
      "loss": 0.1372,
      "step": 7
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019998932457674902,
      "loss": 0.124,
      "step": 8
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019995730058628927,
      "loss": 0.1387,
      "step": 9
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019990393486601384,
      "loss": 0.125,
      "step": 10
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019982923880995572,
      "loss": 0.123,
      "step": 11
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019973322836635518,
      "loss": 0.1196,
      "step": 12
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019961592403425468,
      "loss": 0.1223,
      "step": 13
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019947735085912207,
      "loss": 0.1208,
      "step": 14
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001993175384275033,
      "loss": 0.1211,
      "step": 15
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019913652086070535,
      "loss": 0.1084,
      "step": 16
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019893433680751103,
      "loss": 0.1169,
      "step": 17
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019871102943592715,
      "loss": 0.1125,
      "step": 18
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001984666464239679,
      "loss": 0.1206,
      "step": 19
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019820123994947504,
      "loss": 0.124,
      "step": 20
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001979148666789775,
      "loss": 0.116,
      "step": 21
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019760758775559274,
      "loss": 0.0994,
      "step": 22
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00019727946878597195,
      "loss": 0.1128,
      "step": 23
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019693057982629277,
      "loss": 0.1267,
      "step": 24
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019656099536730136,
      "loss": 0.1096,
      "step": 25
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001961707943184083,
      "loss": 0.1226,
      "step": 26
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001957600599908406,
      "loss": 0.1084,
      "step": 27
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019532888007985406,
      "loss": 0.1018,
      "step": 28
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019487734664600957,
      "loss": 0.1099,
      "step": 29
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0001944055560955176,
      "loss": 0.116,
      "step": 30
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019391360915965426,
      "loss": 0.1101,
      "step": 31
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001934016108732548,
      "loss": 0.1052,
      "step": 32
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019286967055228744,
      "loss": 0.1208,
      "step": 33
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00019231790177051355,
      "loss": 0.0981,
      "step": 34
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019174642233523877,
      "loss": 0.1147,
      "step": 35
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019115535426216017,
      "loss": 0.1003,
      "step": 36
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019054482374931467,
      "loss": 0.0989,
      "step": 37
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.000189914961150135,
      "loss": 0.1091,
      "step": 38
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00018926590094561782,
      "loss": 0.104,
      "step": 39
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00018859778171561114,
      "loss": 0.0955,
      "step": 40
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00018791074610922622,
      "loss": 0.1384,
      "step": 41
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00018720494081438078,
      "loss": 0.0906,
      "step": 42
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001864805165264799,
      "loss": 0.0945,
      "step": 43
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00018573762791624133,
      "loss": 0.0991,
      "step": 44
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0001849764335966719,
      "loss": 0.0876,
      "step": 45
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00018419709608920242,
      "loss": 0.0918,
      "step": 46
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0001833997817889878,
      "loss": 0.1074,
      "step": 47
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018258466092938044,
      "loss": 0.1099,
      "step": 48
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018175190754558384,
      "loss": 0.1045,
      "step": 49
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.1025,
      "step": 50
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00018003421813174127,
      "loss": 0.0847,
      "step": 51
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00017914964884292544,
      "loss": 0.0842,
      "step": 52
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00017824818043407826,
      "loss": 0.0991,
      "step": 53
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00017733000537633605,
      "loss": 0.1055,
      "step": 54
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00017639531970784593,
      "loss": 0.092,
      "step": 55
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00017544432299191026,
      "loss": 0.0923,
      "step": 56
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001744772182743782,
      "loss": 0.1121,
      "step": 57
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00017349421204029342,
      "loss": 0.0942,
      "step": 58
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00017249551416980804,
      "loss": 0.1079,
      "step": 59
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00017148133789337145,
      "loss": 0.0967,
      "step": 60
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0001704518997462037,
      "loss": 0.1094,
      "step": 61
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001694074195220634,
      "loss": 0.0942,
      "step": 62
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00016834812022631997,
      "loss": 0.0894,
      "step": 63
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00016727422802834,
      "loss": 0.0972,
      "step": 64
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00016618597221319833,
      "loss": 0.0894,
      "step": 65
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00016508358513272358,
      "loss": 0.0791,
      "step": 66
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00016396730215588915,
      "loss": 0.1182,
      "step": 67
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00016283736161855993,
      "loss": 0.1042,
      "step": 68
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00016169400477260566,
      "loss": 0.1021,
      "step": 69
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00016053747573439145,
      "loss": 0.0808,
      "step": 70
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001593680214326571,
      "loss": 0.0967,
      "step": 71
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001581858915557953,
      "loss": 0.0884,
      "step": 72
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00015699133849854163,
      "loss": 0.0903,
      "step": 73
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00015578461730808574,
      "loss": 0.0989,
      "step": 74
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.00015456598562961667,
      "loss": 0.0784,
      "step": 75
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00015333570365131353,
      "loss": 0.0815,
      "step": 76
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00015209403404879303,
      "loss": 0.0815,
      "step": 77
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0001508412419290261,
      "loss": 0.0786,
      "step": 78
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001495775947737352,
      "loss": 0.0776,
      "step": 79
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0001483033623822848,
      "loss": 0.0925,
      "step": 80
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.00014701881681407683,
      "loss": 0.0713,
      "step": 81
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00014572423233046386,
      "loss": 0.0918,
      "step": 82
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00014441988533619182,
      "loss": 0.0981,
      "step": 83
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00014310605432038526,
      "loss": 0.0781,
      "step": 84
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0001417830197970877,
      "loss": 0.0811,
      "step": 85
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.00014045106424536937,
      "loss": 0.0811,
      "step": 86
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001391104720490156,
      "loss": 0.1033,
      "step": 87
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00013776152943580848,
      "loss": 0.0828,
      "step": 88
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00013640452441641463,
      "loss": 0.0933,
      "step": 89
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00013503974672289296,
      "loss": 0.0818,
      "step": 90
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00013366748774683375,
      "loss": 0.0764,
      "step": 91
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00013228804047714463,
      "loss": 0.0774,
      "step": 92
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.1003,
      "step": 93
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00012950876062343148,
      "loss": 0.0674,
      "step": 94
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00012810952143918285,
      "loss": 0.0684,
      "step": 95
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0001267042806341593,
      "loss": 0.0815,
      "step": 96
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00012529333823916807,
      "loss": 0.0938,
      "step": 97
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001238769955023542,
      "loss": 0.0791,
      "step": 98
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00012245555482488134,
      "loss": 0.0828,
      "step": 99
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00012102931969636664,
      "loss": 0.0693,
      "step": 100
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00011959859463008316,
      "loss": 0.0979,
      "step": 101
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.00011816368509794364,
      "loss": 0.0996,
      "step": 102
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.00011672489746527979,
      "loss": 0.0774,
      "step": 103
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.00011528253892543053,
      "loss": 0.0852,
      "step": 104
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00011383691743415363,
      "loss": 0.0701,
      "step": 105
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0001123883416438748,
      "loss": 0.0618,
      "step": 106
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.00011093712083778746,
      "loss": 0.0669,
      "step": 107
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.00010948356486381827,
      "loss": 0.103,
      "step": 108
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00010802798406847212,
      "loss": 0.0793,
      "step": 109
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0001065706892305703,
      "loss": 0.0837,
      "step": 110
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.00010511199149489673,
      "loss": 0.0659,
      "step": 111
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001036522023057659,
      "loss": 0.0945,
      "step": 112
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00010219163334052682,
      "loss": 0.0901,
      "step": 113
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.0001007305964430173,
      "loss": 0.0867,
      "step": 114
    },
    {
      "epoch": 1.55,
      "learning_rate": 9.92694035569827e-05,
      "loss": 0.0752,
      "step": 115
    },
    {
      "epoch": 1.57,
      "learning_rate": 9.780836665947319e-05,
      "loss": 0.092,
      "step": 116
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.63477976942341e-05,
      "loss": 0.084,
      "step": 117
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.48880085051033e-05,
      "loss": 0.0732,
      "step": 118
    },
    {
      "epoch": 1.61,
      "learning_rate": 9.342931076942972e-05,
      "loss": 0.1045,
      "step": 119
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.19720159315279e-05,
      "loss": 0.0955,
      "step": 120
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.051643513618175e-05,
      "loss": 0.1003,
      "step": 121
    },
    {
      "epoch": 1.65,
      "learning_rate": 8.906287916221259e-05,
      "loss": 0.0901,
      "step": 122
    },
    {
      "epoch": 1.66,
      "learning_rate": 8.76116583561252e-05,
      "loss": 0.0732,
      "step": 123
    },
    {
      "epoch": 1.68,
      "learning_rate": 8.616308256584637e-05,
      "loss": 0.0852,
      "step": 124
    },
    {
      "epoch": 1.69,
      "learning_rate": 8.47174610745695e-05,
      "loss": 0.0989,
      "step": 125
    },
    {
      "epoch": 1.7,
      "learning_rate": 8.327510253472023e-05,
      "loss": 0.0701,
      "step": 126
    },
    {
      "epoch": 1.72,
      "learning_rate": 8.183631490205637e-05,
      "loss": 0.0898,
      "step": 127
    },
    {
      "epoch": 1.73,
      "learning_rate": 8.040140536991687e-05,
      "loss": 0.0867,
      "step": 128
    },
    {
      "epoch": 1.74,
      "learning_rate": 7.89706803036334e-05,
      "loss": 0.0901,
      "step": 129
    },
    {
      "epoch": 1.76,
      "learning_rate": 7.75444451751187e-05,
      "loss": 0.0697,
      "step": 130
    },
    {
      "epoch": 1.77,
      "learning_rate": 7.61230044976458e-05,
      "loss": 0.0854,
      "step": 131
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.470666176083192e-05,
      "loss": 0.0779,
      "step": 132
    },
    {
      "epoch": 1.8,
      "learning_rate": 7.329571936584072e-05,
      "loss": 0.0852,
      "step": 133
    },
    {
      "epoch": 1.81,
      "learning_rate": 7.189047856081719e-05,
      "loss": 0.0747,
      "step": 134
    },
    {
      "epoch": 1.82,
      "learning_rate": 7.049123937656855e-05,
      "loss": 0.0928,
      "step": 135
    },
    {
      "epoch": 1.84,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.0786,
      "step": 136
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.77119595228554e-05,
      "loss": 0.0933,
      "step": 137
    },
    {
      "epoch": 1.86,
      "learning_rate": 6.63325122531663e-05,
      "loss": 0.0662,
      "step": 138
    },
    {
      "epoch": 1.88,
      "learning_rate": 6.496025327710707e-05,
      "loss": 0.0847,
      "step": 139
    },
    {
      "epoch": 1.89,
      "learning_rate": 6.359547558358533e-05,
      "loss": 0.0808,
      "step": 140
    },
    {
      "epoch": 1.91,
      "learning_rate": 6.223847056419154e-05,
      "loss": 0.0776,
      "step": 141
    },
    {
      "epoch": 1.92,
      "learning_rate": 6.0889527950984416e-05,
      "loss": 0.1028,
      "step": 142
    },
    {
      "epoch": 1.93,
      "learning_rate": 5.954893575463064e-05,
      "loss": 0.0725,
      "step": 143
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.821698020291234e-05,
      "loss": 0.072,
      "step": 144
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.689394567961477e-05,
      "loss": 0.0823,
      "step": 145
    },
    {
      "epoch": 1.97,
      "learning_rate": 5.558011466380823e-05,
      "loss": 0.083,
      "step": 146
    },
    {
      "epoch": 1.99,
      "learning_rate": 5.4275767669536146e-05,
      "loss": 0.0752,
      "step": 147
    },
    {
      "epoch": 2.0,
      "learning_rate": 5.2981183185923156e-05,
      "loss": 0.0928,
      "step": 148
    },
    {
      "epoch": 2.01,
      "learning_rate": 5.169663761771521e-05,
      "loss": 0.0654,
      "step": 149
    },
    {
      "epoch": 2.03,
      "learning_rate": 5.042240522626482e-05,
      "loss": 0.0669,
      "step": 150
    },
    {
      "epoch": 2.04,
      "learning_rate": 4.91587580709739e-05,
      "loss": 0.079,
      "step": 151
    },
    {
      "epoch": 2.05,
      "learning_rate": 4.790596595120699e-05,
      "loss": 0.0623,
      "step": 152
    },
    {
      "epoch": 2.07,
      "learning_rate": 4.666429634868651e-05,
      "loss": 0.0542,
      "step": 153
    },
    {
      "epoch": 2.08,
      "learning_rate": 4.543401437038335e-05,
      "loss": 0.0703,
      "step": 154
    },
    {
      "epoch": 2.09,
      "learning_rate": 4.4215382691914266e-05,
      "loss": 0.0664,
      "step": 155
    },
    {
      "epoch": 2.11,
      "learning_rate": 4.300866150145837e-05,
      "loss": 0.0723,
      "step": 156
    },
    {
      "epoch": 2.12,
      "learning_rate": 4.181410844420474e-05,
      "loss": 0.0591,
      "step": 157
    },
    {
      "epoch": 2.14,
      "learning_rate": 4.0631978567342946e-05,
      "loss": 0.0537,
      "step": 158
    },
    {
      "epoch": 2.15,
      "learning_rate": 3.946252426560855e-05,
      "loss": 0.0554,
      "step": 159
    },
    {
      "epoch": 2.16,
      "learning_rate": 3.8305995227394365e-05,
      "loss": 0.0703,
      "step": 160
    },
    {
      "epoch": 2.18,
      "learning_rate": 3.716263838144007e-05,
      "loss": 0.0525,
      "step": 161
    },
    {
      "epoch": 2.19,
      "learning_rate": 3.60326978441109e-05,
      "loss": 0.0798,
      "step": 162
    },
    {
      "epoch": 2.2,
      "learning_rate": 3.491641486727645e-05,
      "loss": 0.054,
      "step": 163
    },
    {
      "epoch": 2.22,
      "learning_rate": 3.3814027786801673e-05,
      "loss": 0.0657,
      "step": 164
    },
    {
      "epoch": 2.23,
      "learning_rate": 3.272577197166e-05,
      "loss": 0.0546,
      "step": 165
    },
    {
      "epoch": 2.24,
      "learning_rate": 3.1651879773680074e-05,
      "loss": 0.0648,
      "step": 166
    },
    {
      "epoch": 2.26,
      "learning_rate": 3.059258047793661e-05,
      "loss": 0.0575,
      "step": 167
    },
    {
      "epoch": 2.27,
      "learning_rate": 2.954810025379633e-05,
      "loss": 0.0476,
      "step": 168
    },
    {
      "epoch": 2.28,
      "learning_rate": 2.851866210662858e-05,
      "loss": 0.0433,
      "step": 169
    },
    {
      "epoch": 2.3,
      "learning_rate": 2.7504485830191984e-05,
      "loss": 0.0784,
      "step": 170
    },
    {
      "epoch": 2.31,
      "learning_rate": 2.650578795970661e-05,
      "loss": 0.0466,
      "step": 171
    },
    {
      "epoch": 2.32,
      "learning_rate": 2.5522781725621813e-05,
      "loss": 0.0612,
      "step": 172
    },
    {
      "epoch": 2.34,
      "learning_rate": 2.455567700808974e-05,
      "loss": 0.0498,
      "step": 173
    },
    {
      "epoch": 2.35,
      "learning_rate": 2.360468029215409e-05,
      "loss": 0.0426,
      "step": 174
    },
    {
      "epoch": 2.36,
      "learning_rate": 2.2669994623664005e-05,
      "loss": 0.049,
      "step": 175
    },
    {
      "epoch": 2.38,
      "learning_rate": 2.1751819565921773e-05,
      "loss": 0.047,
      "step": 176
    },
    {
      "epoch": 2.39,
      "learning_rate": 2.0850351157074598e-05,
      "loss": 0.0652,
      "step": 177
    },
    {
      "epoch": 2.41,
      "learning_rate": 1.996578186825876e-05,
      "loss": 0.0532,
      "step": 178
    },
    {
      "epoch": 2.42,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.0613,
      "step": 179
    },
    {
      "epoch": 2.43,
      "learning_rate": 1.8248092454416165e-05,
      "loss": 0.0614,
      "step": 180
    },
    {
      "epoch": 2.45,
      "learning_rate": 1.7415339070619586e-05,
      "loss": 0.048,
      "step": 181
    },
    {
      "epoch": 2.46,
      "learning_rate": 1.660021821101222e-05,
      "loss": 0.0685,
      "step": 182
    },
    {
      "epoch": 2.47,
      "learning_rate": 1.5802903910797583e-05,
      "loss": 0.0409,
      "step": 183
    },
    {
      "epoch": 2.49,
      "learning_rate": 1.5023566403328104e-05,
      "loss": 0.0531,
      "step": 184
    },
    {
      "epoch": 2.5,
      "learning_rate": 1.4262372083758713e-05,
      "loss": 0.0634,
      "step": 185
    },
    {
      "epoch": 2.51,
      "learning_rate": 1.3519483473520122e-05,
      "loss": 0.0593,
      "step": 186
    },
    {
      "epoch": 2.53,
      "learning_rate": 1.2795059185619229e-05,
      "loss": 0.0687,
      "step": 187
    },
    {
      "epoch": 2.54,
      "learning_rate": 1.2089253890773789e-05,
      "loss": 0.0696,
      "step": 188
    },
    {
      "epoch": 2.55,
      "learning_rate": 1.1402218284388844e-05,
      "loss": 0.0641,
      "step": 189
    },
    {
      "epoch": 2.57,
      "learning_rate": 1.0734099054382185e-05,
      "loss": 0.059,
      "step": 190
    },
    {
      "epoch": 2.58,
      "learning_rate": 1.0085038849865025e-05,
      "loss": 0.0601,
      "step": 191
    },
    {
      "epoch": 2.59,
      "learning_rate": 9.455176250685338e-06,
      "loss": 0.0424,
      "step": 192
    },
    {
      "epoch": 2.61,
      "learning_rate": 8.844645737839873e-06,
      "loss": 0.0754,
      "step": 193
    },
    {
      "epoch": 2.62,
      "learning_rate": 8.253577664761258e-06,
      "loss": 0.0491,
      "step": 194
    },
    {
      "epoch": 2.64,
      "learning_rate": 7.682098229486479e-06,
      "loss": 0.0425,
      "step": 195
    },
    {
      "epoch": 2.65,
      "learning_rate": 7.130329447712581e-06,
      "loss": 0.0505,
      "step": 196
    },
    {
      "epoch": 2.66,
      "learning_rate": 6.598389126745208e-06,
      "loss": 0.0499,
      "step": 197
    },
    {
      "epoch": 2.68,
      "learning_rate": 6.086390840345757e-06,
      "loss": 0.0457,
      "step": 198
    },
    {
      "epoch": 2.69,
      "learning_rate": 5.594443904482438e-06,
      "loss": 0.0533,
      "step": 199
    },
    {
      "epoch": 2.7,
      "learning_rate": 5.122653353990436e-06,
      "loss": 0.0522,
      "step": 200
    },
    {
      "epoch": 2.72,
      "learning_rate": 4.671119920145983e-06,
      "loss": 0.0596,
      "step": 201
    },
    {
      "epoch": 2.73,
      "learning_rate": 4.2399400091594154e-06,
      "loss": 0.0486,
      "step": 202
    },
    {
      "epoch": 2.74,
      "learning_rate": 3.829205681591697e-06,
      "loss": 0.0425,
      "step": 203
    },
    {
      "epoch": 2.76,
      "learning_rate": 3.4390046326986504e-06,
      "loss": 0.0455,
      "step": 204
    },
    {
      "epoch": 2.77,
      "learning_rate": 3.0694201737072492e-06,
      "loss": 0.0505,
      "step": 205
    },
    {
      "epoch": 2.78,
      "learning_rate": 2.720531214028055e-06,
      "loss": 0.0503,
      "step": 206
    },
    {
      "epoch": 2.8,
      "learning_rate": 2.392412244407294e-06,
      "loss": 0.0674,
      "step": 207
    },
    {
      "epoch": 2.81,
      "learning_rate": 2.0851333210225033e-06,
      "loss": 0.0629,
      "step": 208
    },
    {
      "epoch": 2.82,
      "learning_rate": 1.7987600505249724e-06,
      "loss": 0.0491,
      "step": 209
    },
    {
      "epoch": 2.84,
      "learning_rate": 1.5333535760320928e-06,
      "loss": 0.0413,
      "step": 210
    },
    {
      "epoch": 2.85,
      "learning_rate": 1.2889705640728444e-06,
      "loss": 0.0515,
      "step": 211
    },
    {
      "epoch": 2.86,
      "learning_rate": 1.0656631924889749e-06,
      "loss": 0.0476,
      "step": 212
    },
    {
      "epoch": 2.88,
      "learning_rate": 8.634791392946428e-07,
      "loss": 0.0555,
      "step": 213
    },
    {
      "epoch": 2.89,
      "learning_rate": 6.824615724966843e-07,
      "loss": 0.0582,
      "step": 214
    },
    {
      "epoch": 2.91,
      "learning_rate": 5.226491408779288e-07,
      "loss": 0.0586,
      "step": 215
    },
    {
      "epoch": 2.92,
      "learning_rate": 3.840759657453452e-07,
      "loss": 0.0559,
      "step": 216
    },
    {
      "epoch": 2.93,
      "learning_rate": 2.667716336448356e-07,
      "loss": 0.0583,
      "step": 217
    },
    {
      "epoch": 2.95,
      "learning_rate": 1.707611900442996e-07,
      "loss": 0.0441,
      "step": 218
    },
    {
      "epoch": 2.96,
      "learning_rate": 9.606513398617845e-08,
      "loss": 0.0754,
      "step": 219
    },
    {
      "epoch": 2.97,
      "learning_rate": 4.269941371073394e-08,
      "loss": 0.0579,
      "step": 220
    },
    {
      "epoch": 2.99,
      "learning_rate": 1.0675423250994243e-08,
      "loss": 0.0377,
      "step": 221
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.0,
      "loss": 0.0557,
      "step": 222
    },
    {
      "epoch": 3.0,
      "step": 222,
      "total_flos": 5266094948352.0,
      "train_loss": 0.08446495812218469,
      "train_runtime": 2892.0758,
      "train_samples_per_second": 4.87,
      "train_steps_per_second": 0.077
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 222,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 800,
  "total_flos": 5266094948352.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}