{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4854368932038835,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 5e-05,
      "loss": 1.9981,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.9999675930251536e-05,
      "loss": 2.0613,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.99987037294078e-05,
      "loss": 1.8228,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.99970834226737e-05,
      "loss": 1.707,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999481505205661e-05,
      "loss": 1.5271,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999189867636535e-05,
      "loss": 1.4562,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.998833437120866e-05,
      "loss": 1.3805,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.998412222899321e-05,
      "loss": 1.2998,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.997926235892124e-05,
      "loss": 1.4383,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.997375488698769e-05,
      "loss": 1.2441,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.996759995597697e-05,
      "loss": 1.2275,
      "step": 11
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.996079772545923e-05,
      "loss": 1.2233,
      "step": 12
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.995334837178625e-05,
      "loss": 1.1886,
      "step": 13
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9945252088086825e-05,
      "loss": 1.1779,
      "step": 14
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.993650908426182e-05,
      "loss": 1.1122,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.992711958697868e-05,
      "loss": 1.0766,
      "step": 16
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.991708383966556e-05,
      "loss": 1.0836,
      "step": 17
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9906402102505026e-05,
      "loss": 0.9728,
      "step": 18
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.989507465242732e-05,
      "loss": 0.9883,
      "step": 19
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.988310178310315e-05,
      "loss": 1.0307,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9870483804936084e-05,
      "loss": 0.9613,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9857221045054535e-05,
      "loss": 1.1038,
      "step": 22
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9843313847303246e-05,
      "loss": 0.9206,
      "step": 23
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9828762572234374e-05,
      "loss": 0.9893,
      "step": 24
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9813567597098166e-05,
      "loss": 0.8328,
      "step": 25
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.979772931583317e-05,
      "loss": 0.8712,
      "step": 26
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.978124813905599e-05,
      "loss": 0.8031,
      "step": 27
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.976412449405072e-05,
      "loss": 0.7675,
      "step": 28
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.974635882475778e-05,
      "loss": 0.7851,
      "step": 29
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.972795159176243e-05,
      "loss": 0.7447,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9708903272282884e-05,
      "loss": 0.7719,
      "step": 31
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9689214360157844e-05,
      "loss": 0.7142,
      "step": 32
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.9668885365833795e-05,
      "loss": 0.8649,
      "step": 33
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.96479168163517e-05,
      "loss": 0.7574,
      "step": 34
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9626309255333346e-05,
      "loss": 0.9205,
      "step": 35
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9604063242967315e-05,
      "loss": 0.7987,
      "step": 36
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.958117935599434e-05,
      "loss": 0.7626,
      "step": 37
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.955765818769249e-05,
      "loss": 0.8332,
      "step": 38
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9533500347861675e-05,
      "loss": 0.9178,
      "step": 39
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.950870646280791e-05,
      "loss": 0.9919,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.948327717532705e-05,
      "loss": 0.7098,
      "step": 41
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.9457213144688095e-05,
      "loss": 0.7552,
      "step": 42
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.9430515046616175e-05,
      "loss": 0.7496,
      "step": 43
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.940318357327495e-05,
      "loss": 0.7667,
      "step": 44
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.937521943324873e-05,
      "loss": 0.8685,
      "step": 45
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.934662335152405e-05,
      "loss": 0.6715,
      "step": 46
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.931739606947091e-05,
      "loss": 0.8149,
      "step": 47
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.9287538344823544e-05,
      "loss": 0.7346,
      "step": 48
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.925705095166079e-05,
      "loss": 0.7803,
      "step": 49
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.922593468038599e-05,
      "loss": 0.7451,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.919419033770652e-05,
      "loss": 0.8402,
      "step": 51
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.916181874661286e-05,
      "loss": 0.7988,
      "step": 52
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.91288207463573e-05,
      "loss": 0.7444,
      "step": 53
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.9095197192432105e-05,
      "loss": 0.8545,
      "step": 54
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.906094895654744e-05,
      "loss": 0.761,
      "step": 55
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.902607692660865e-05,
      "loss": 0.6741,
      "step": 56
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.8990582006693365e-05,
      "loss": 0.8457,
      "step": 57
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.895446511702793e-05,
      "loss": 0.8096,
      "step": 58
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.891772719396369e-05,
      "loss": 0.7989,
      "step": 59
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.888036918995258e-05,
      "loss": 0.7683,
      "step": 60
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.884239207352252e-05,
      "loss": 0.7912,
      "step": 61
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.880379682925228e-05,
      "loss": 0.7417,
      "step": 62
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.876458445774594e-05,
      "loss": 0.7511,
      "step": 63
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.872475597560699e-05,
      "loss": 0.8021,
      "step": 64
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.8684312415411897e-05,
      "loss": 0.8154,
      "step": 65
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.864325482568344e-05,
      "loss": 0.7109,
      "step": 66
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.860158427086341e-05,
      "loss": 0.7915,
      "step": 67
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.855930183128513e-05,
      "loss": 0.6363,
      "step": 68
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.851640860314536e-05,
      "loss": 0.6987,
      "step": 69
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.8472905698475906e-05,
      "loss": 0.6498,
      "step": 70
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.84287942451148e-05,
      "loss": 0.7768,
      "step": 71
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8384075386677054e-05,
      "loss": 0.7979,
      "step": 72
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.833875028252499e-05,
      "loss": 0.7611,
      "step": 73
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.8292820107738235e-05,
      "loss": 0.7889,
      "step": 74
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.824628605308319e-05,
      "loss": 0.6706,
      "step": 75
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.819914932498222e-05,
      "loss": 0.7762,
      "step": 76
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.815141114548232e-05,
      "loss": 0.7517,
      "step": 77
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.8103072752223486e-05,
      "loss": 0.7793,
      "step": 78
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.805413539840659e-05,
      "loss": 0.7306,
      "step": 79
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.80046003527609e-05,
      "loss": 0.834,
      "step": 80
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.7954468899511215e-05,
      "loss": 0.8076,
      "step": 81
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.790374233834452e-05,
      "loss": 0.8375,
      "step": 82
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.7852421984376324e-05,
      "loss": 0.7839,
      "step": 83
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.780050916811658e-05,
      "loss": 0.6221,
      "step": 84
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.7748005235435137e-05,
      "loss": 0.7212,
      "step": 85
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.76949115475269e-05,
      "loss": 0.6369,
      "step": 86
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.7641229480876515e-05,
      "loss": 0.7167,
      "step": 87
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.758696042722269e-05,
      "loss": 0.6908,
      "step": 88
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.753210579352211e-05,
      "loss": 0.6681,
      "step": 89
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.747666700191297e-05,
      "loss": 0.6566,
      "step": 90
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.7420645489678076e-05,
      "loss": 0.6869,
      "step": 91
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.7364042709207626e-05,
      "loss": 0.7106,
      "step": 92
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.730686012796153e-05,
      "loss": 0.6782,
      "step": 93
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.724909922843136e-05,
      "loss": 0.7148,
      "step": 94
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.719076150810193e-05,
      "loss": 0.8887,
      "step": 95
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.7131848479412476e-05,
      "loss": 0.7408,
      "step": 96
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.707236166971742e-05,
      "loss": 0.7046,
      "step": 97
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.7012302621246804e-05,
      "loss": 0.7657,
      "step": 98
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.695167289106629e-05,
      "loss": 0.8138,
      "step": 99
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.689047405103678e-05,
      "loss": 0.6964,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_loss": 0.796372652053833,
      "eval_runtime": 5.3558,
      "eval_samples_per_second": 1.867,
      "eval_steps_per_second": 0.373,
      "step": 100
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.68287076877737e-05,
      "loss": 0.6541,
      "step": 101
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.6766375402605824e-05,
      "loss": 0.714,
      "step": 102
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.6703478811533794e-05,
      "loss": 0.6823,
      "step": 103
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.6640019545188216e-05,
      "loss": 0.8283,
      "step": 104
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.657599924878736e-05,
      "loss": 0.7126,
      "step": 105
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.651141958209453e-05,
      "loss": 0.6612,
      "step": 106
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.644628221937504e-05,
      "loss": 0.7339,
      "step": 107
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.638058884935279e-05,
      "loss": 0.6852,
      "step": 108
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.6314341175166485e-05,
      "loss": 0.6804,
      "step": 109
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.6247540914325504e-05,
      "loss": 0.7904,
      "step": 110
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.618018979866534e-05,
      "loss": 0.6545,
      "step": 111
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.611228957430272e-05,
      "loss": 0.7545,
      "step": 112
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.6043842001590344e-05,
      "loss": 0.7478,
      "step": 113
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.5974848855071206e-05,
      "loss": 0.8083,
      "step": 114
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.590531192343266e-05,
      "loss": 0.7435,
      "step": 115
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.5835233009459964e-05,
      "loss": 0.7647,
      "step": 116
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.576461392998961e-05,
      "loss": 0.7631,
      "step": 117
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.569345651586218e-05,
      "loss": 0.7674,
      "step": 118
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.5621762611874904e-05,
      "loss": 0.6737,
      "step": 119
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.55495340767338e-05,
      "loss": 0.6901,
      "step": 120
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.547677278300555e-05,
      "loss": 0.709,
      "step": 121
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.540348061706886e-05,
      "loss": 0.5995,
      "step": 122
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.5329659479065655e-05,
      "loss": 0.6832,
      "step": 123
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.525531128285173e-05,
      "loss": 0.7584,
      "step": 124
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.5180437955947195e-05,
      "loss": 0.6998,
      "step": 125
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.510504143948646e-05,
      "loss": 0.6477,
      "step": 126
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.502912368816794e-05,
      "loss": 0.681,
      "step": 127
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.4952686670203357e-05,
      "loss": 0.7638,
      "step": 128
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.487573236726673e-05,
      "loss": 0.7086,
      "step": 129
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.4798262774442986e-05,
      "loss": 0.6166,
      "step": 130
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.472027990017623e-05,
      "loss": 0.5901,
      "step": 131
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.464178576621771e-05,
      "loss": 0.8138,
      "step": 132
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.456278240757338e-05,
      "loss": 0.6773,
      "step": 133
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.4483271872451094e-05,
      "loss": 0.6576,
      "step": 134
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.44032562222076e-05,
      "loss": 0.7106,
      "step": 135
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.432273753129502e-05,
      "loss": 0.6479,
      "step": 136
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.4241717887207124e-05,
      "loss": 0.7102,
      "step": 137
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.416019939042515e-05,
      "loss": 0.7188,
      "step": 138
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.40781841543634e-05,
      "loss": 0.6996,
      "step": 139
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.399567430531444e-05,
      "loss": 0.7523,
      "step": 140
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.391267198239394e-05,
      "loss": 0.6279,
      "step": 141
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.3829179337485254e-05,
      "loss": 0.6718,
      "step": 142
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.374519853518362e-05,
      "loss": 0.668,
      "step": 143
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.366073175274004e-05,
      "loss": 0.8341,
      "step": 144
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.357578118000482e-05,
      "loss": 0.7262,
      "step": 145
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.3490349019370824e-05,
      "loss": 0.7613,
      "step": 146
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.340443748571636e-05,
      "loss": 0.6722,
      "step": 147
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.331804880634775e-05,
      "loss": 0.7229,
      "step": 148
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.3231185220941605e-05,
      "loss": 0.7265,
      "step": 149
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.3143848981486746e-05,
      "loss": 0.7289,
      "step": 150
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.305604235222582e-05,
      "loss": 0.6441,
      "step": 151
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.2967767609596624e-05,
      "loss": 0.772,
      "step": 152
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.287902704217304e-05,
      "loss": 0.705,
      "step": 153
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.2789822950605725e-05,
      "loss": 0.7711,
      "step": 154
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.2700157647562486e-05,
      "loss": 0.7688,
      "step": 155
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.261003345766832e-05,
      "loss": 0.6978,
      "step": 156
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.251945271744509e-05,
      "loss": 0.7418,
      "step": 157
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.242841777525101e-05,
      "loss": 0.6258,
      "step": 158
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.233693099121976e-05,
      "loss": 0.7988,
      "step": 159
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.224499473719926e-05,
      "loss": 0.6947,
      "step": 160
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.21526113966902e-05,
      "loss": 0.6712,
      "step": 161
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.205978336478427e-05,
      "loss": 0.6871,
      "step": 162
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.196651304810202e-05,
      "loss": 0.6682,
      "step": 163
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.187280286473048e-05,
      "loss": 0.6139,
      "step": 164
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.177865524416052e-05,
      "loss": 0.6259,
      "step": 165
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.168407262722377e-05,
      "loss": 0.6894,
      "step": 166
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.1589057466029444e-05,
      "loss": 0.8107,
      "step": 167
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.149361222390068e-05,
      "loss": 0.728,
      "step": 168
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.1397739375310736e-05,
      "loss": 0.6987,
      "step": 169
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.1301441405818794e-05,
      "loss": 0.7855,
      "step": 170
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.120472081200556e-05,
      "loss": 0.6786,
      "step": 171
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.1107580101408524e-05,
      "loss": 0.805,
      "step": 172
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.101002179245693e-05,
      "loss": 0.7006,
      "step": 173
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.09120484144065e-05,
      "loss": 0.7023,
      "step": 174
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.0813662507273885e-05,
      "loss": 0.7802,
      "step": 175
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.0714866621770775e-05,
      "loss": 0.6794,
      "step": 176
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.06156633192378e-05,
      "loss": 0.6833,
      "step": 177
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.051605517157809e-05,
      "loss": 0.7591,
      "step": 178
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.041604476119064e-05,
      "loss": 0.7059,
      "step": 179
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.0315634680903336e-05,
      "loss": 0.713,
      "step": 180
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.021482753390573e-05,
      "loss": 0.686,
      "step": 181
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.011362593368156e-05,
      "loss": 0.718,
      "step": 182
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.001203250394101e-05,
      "loss": 0.8431,
      "step": 183
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.9910049878552646e-05,
      "loss": 0.7043,
      "step": 184
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.9807680701475174e-05,
      "loss": 0.7591,
      "step": 185
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.970492762668887e-05,
      "loss": 0.7677,
      "step": 186
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.9601793318126776e-05,
      "loss": 0.6897,
      "step": 187
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.9498280449605664e-05,
      "loss": 0.753,
      "step": 188
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.939439170475666e-05,
      "loss": 0.7049,
      "step": 189
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.929012977695572e-05,
      "loss": 0.6654,
      "step": 190
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.918549736925378e-05,
      "loss": 0.6969,
      "step": 191
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.9080497194306686e-05,
      "loss": 0.6655,
      "step": 192
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.897513197430486e-05,
      "loss": 0.7118,
      "step": 193
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.8869404440902735e-05,
      "loss": 0.5986,
      "step": 194
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.876331733514792e-05,
      "loss": 0.7191,
      "step": 195
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.865687340741014e-05,
      "loss": 0.6433,
      "step": 196
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.855007541730996e-05,
      "loss": 0.6386,
      "step": 197
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.844292613364719e-05,
      "loss": 0.8535,
      "step": 198
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.833542833432916e-05,
      "loss": 0.7112,
      "step": 199
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.822758480629864e-05,
      "loss": 0.7226,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_loss": 0.7749701738357544,
      "eval_runtime": 5.4698,
      "eval_samples_per_second": 1.828,
      "eval_steps_per_second": 0.366,
      "step": 200
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.811939834546163e-05,
      "loss": 0.6725,
      "step": 201
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.801087175661488e-05,
      "loss": 0.711,
      "step": 202
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.790200785337311e-05,
      "loss": 0.6973,
      "step": 203
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.7792809458096146e-05,
      "loss": 0.7107,
      "step": 204
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.768327940181572e-05,
      "loss": 0.6809,
      "step": 205
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.757342052416205e-05,
      "loss": 0.6272,
      "step": 206
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.746323567329024e-05,
      "loss": 0.7267,
      "step": 207
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.7352727705806446e-05,
      "loss": 0.764,
      "step": 208
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.724189948669381e-05,
      "loss": 0.7307,
      "step": 209
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.7130753889238165e-05,
      "loss": 0.8486,
      "step": 210
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.7019293794953595e-05,
      "loss": 0.7304,
      "step": 211
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.690752209350767e-05,
      "loss": 0.8079,
      "step": 212
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.679544168264656e-05,
      "loss": 0.6661,
      "step": 213
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.668305546811991e-05,
      "loss": 0.7078,
      "step": 214
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.65703663636055e-05,
      "loss": 0.6363,
      "step": 215
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.645737729063372e-05,
      "loss": 0.6479,
      "step": 216
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.63440911785118e-05,
      "loss": 0.8032,
      "step": 217
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.6230510964247886e-05,
      "loss": 0.7619,
      "step": 218
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.61166395924749e-05,
      "loss": 0.6744,
      "step": 219
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.600248001537418e-05,
      "loss": 0.5971,
      "step": 220
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.588803519259898e-05,
      "loss": 0.7197,
      "step": 221
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.577330809119768e-05,
      "loss": 0.7581,
      "step": 222
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.565830168553691e-05,
      "loss": 0.6288,
      "step": 223
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.554301895722442e-05,
      "loss": 0.8863,
      "step": 224
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.542746289503181e-05,
      "loss": 0.6523,
      "step": 225
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.5311636494816984e-05,
      "loss": 0.6503,
      "step": 226
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.519554275944655e-05,
      "loss": 0.7903,
      "step": 227
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.50791846987179e-05,
      "loss": 0.7974,
      "step": 228
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.496256532928125e-05,
      "loss": 0.712,
      "step": 229
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.484568767456135e-05,
      "loss": 0.6632,
      "step": 230
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.47285547646792e-05,
      "loss": 0.7328,
      "step": 231
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.46111696363734e-05,
      "loss": 0.6455,
      "step": 232
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.4493535332921475e-05,
      "loss": 0.6295,
      "step": 233
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.4375654904060956e-05,
      "loss": 0.6613,
      "step": 234
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.425753140591031e-05,
      "loss": 0.6991,
      "step": 235
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.413916790088973e-05,
      "loss": 0.6047,
      "step": 236
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.402056745764172e-05,
      "loss": 0.7401,
      "step": 237
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.3901733150951535e-05,
      "loss": 0.6909,
      "step": 238
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.37826680616675e-05,
      "loss": 0.6293,
      "step": 239
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.366337527662109e-05,
      "loss": 0.7261,
      "step": 240
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.354385788854694e-05,
      "loss": 0.8233,
      "step": 241
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.3424118996002624e-05,
      "loss": 0.7349,
      "step": 242
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.3304161703288385e-05,
      "loss": 0.6952,
      "step": 243
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.318398912036658e-05,
      "loss": 0.6676,
      "step": 244
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.3063604362781125e-05,
      "loss": 0.6929,
      "step": 245
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.2943010551576654e-05,
      "loss": 0.7219,
      "step": 246
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.282221081321766e-05,
      "loss": 0.7747,
      "step": 247
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.27012082795074e-05,
      "loss": 0.6931,
      "step": 248
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.258000608750674e-05,
      "loss": 0.6869,
      "step": 249
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.245860737945278e-05,
      "loss": 0.6864,
      "step": 250
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.233701530267743e-05,
      "loss": 0.7052,
      "step": 251
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.2215233009525786e-05,
      "loss": 0.7917,
      "step": 252
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.209326365727441e-05,
      "loss": 0.7137,
      "step": 253
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.19711104080495e-05,
      "loss": 0.7149,
      "step": 254
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.184877642874486e-05,
      "loss": 0.694,
      "step": 255
    },
    {
      "epoch": 0.41,
      "learning_rate": 3.172626489093986e-05,
      "loss": 0.6155,
      "step": 256
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.1603578970817146e-05,
      "loss": 0.743,
      "step": 257
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.1480721849080344e-05,
      "loss": 0.6893,
      "step": 258
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.1357696710871576e-05,
      "loss": 0.6215,
      "step": 259
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.123450674568889e-05,
      "loss": 0.6225,
      "step": 260
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.1111155147303574e-05,
      "loss": 0.795,
      "step": 261
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.0987645113677335e-05,
      "loss": 0.84,
      "step": 262
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.086397984687943e-05,
      "loss": 0.6852,
      "step": 263
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.074016255300359e-05,
      "loss": 0.7301,
      "step": 264
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.061619644208498e-05,
      "loss": 0.7638,
      "step": 265
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.0492084728016902e-05,
      "loss": 0.7403,
      "step": 266
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.036783062846751e-05,
      "loss": 0.8257,
      "step": 267
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.0243437364796386e-05,
      "loss": 0.6582,
      "step": 268
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.0118908161971025e-05,
      "loss": 0.6031,
      "step": 269
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.9994246248483228e-05,
      "loss": 0.6981,
      "step": 270
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.9869454856265376e-05,
      "loss": 0.6632,
      "step": 271
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.9744537220606693e-05,
      "loss": 0.7312,
      "step": 272
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.9619496580069317e-05,
      "loss": 0.6421,
      "step": 273
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.9494336176404357e-05,
      "loss": 0.6031,
      "step": 274
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.9369059254467858e-05,
      "loss": 0.77,
      "step": 275
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.9243669062136664e-05,
      "loss": 0.7053,
      "step": 276
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.9118168850224226e-05,
      "loss": 0.7678,
      "step": 277
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.8992561872396313e-05,
      "loss": 0.5997,
      "step": 278
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.8866851385086652e-05,
      "loss": 0.772,
      "step": 279
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.8741040647412538e-05,
      "loss": 0.6521,
      "step": 280
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.8615132921090292e-05,
      "loss": 0.6677,
      "step": 281
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.8489131470350727e-05,
      "loss": 0.6277,
      "step": 282
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.836303956185453e-05,
      "loss": 0.7005,
      "step": 283
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.8236860464607534e-05,
      "loss": 0.8361,
      "step": 284
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.8110597449876014e-05,
      "loss": 0.6893,
      "step": 285
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.7984253791101834e-05,
      "loss": 0.7185,
      "step": 286
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.7857832763817622e-05,
      "loss": 0.703,
      "step": 287
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.773133764556181e-05,
      "loss": 0.6402,
      "step": 288
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.7604771715793697e-05,
      "loss": 0.6384,
      "step": 289
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.74781382558084e-05,
      "loss": 0.8262,
      "step": 290
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.735144054865181e-05,
      "loss": 0.7639,
      "step": 291
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.722468187903544e-05,
      "loss": 0.7043,
      "step": 292
    },
    {
      "epoch": 0.47,
      "learning_rate": 2.7097865533251314e-05,
      "loss": 0.5832,
      "step": 293
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.6970994799086735e-05,
      "loss": 0.681,
      "step": 294
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.6844072965739054e-05,
      "loss": 0.658,
      "step": 295
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.6717103323730396e-05,
      "loss": 0.6749,
      "step": 296
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.6590089164822364e-05,
      "loss": 0.6759,
      "step": 297
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.6463033781930673e-05,
      "loss": 0.5983,
      "step": 298
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.633594046903981e-05,
      "loss": 0.7378,
      "step": 299
    },
    {
      "epoch": 0.49,
      "learning_rate": 2.62088125211176e-05,
      "loss": 0.7041,
      "step": 300
    },
    {
      "epoch": 0.49,
      "eval_loss": 0.7667814493179321,
      "eval_runtime": 5.4254,
      "eval_samples_per_second": 1.843,
      "eval_steps_per_second": 0.369,
      "step": 300
    }
  ],
  "logging_steps": 1,
  "max_steps": 618,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 7.561791160713216e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}