Claude-Kimiko / checkpoint-320 /trainer_state.json
Chat-Error's picture
Upload folder using huggingface_hub
b8d9662 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.4,
"eval_steps": 500,
"global_step": 320,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.000000000000001e-07,
"loss": 1.5526,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.6607,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 1.5e-06,
"loss": 1.372,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.4931,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 2.5e-06,
"loss": 1.5619,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 3e-06,
"loss": 1.718,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 3.5e-06,
"loss": 1.4011,
"step": 7
},
{
"epoch": 0.04,
"learning_rate": 4.000000000000001e-06,
"loss": 1.6706,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 4.5e-06,
"loss": 1.5431,
"step": 9
},
{
"epoch": 0.04,
"learning_rate": 5e-06,
"loss": 1.6866,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 4.999971592166969e-06,
"loss": 1.3485,
"step": 11
},
{
"epoch": 0.05,
"learning_rate": 4.999886369313478e-06,
"loss": 1.6039,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 4.999744333376324e-06,
"loss": 1.6092,
"step": 13
},
{
"epoch": 0.06,
"learning_rate": 4.999545487583456e-06,
"loss": 1.4041,
"step": 14
},
{
"epoch": 0.07,
"learning_rate": 4.999289836453894e-06,
"loss": 1.2342,
"step": 15
},
{
"epoch": 0.07,
"learning_rate": 4.998977385797635e-06,
"loss": 1.5679,
"step": 16
},
{
"epoch": 0.08,
"learning_rate": 4.998608142715515e-06,
"loss": 1.5122,
"step": 17
},
{
"epoch": 0.08,
"learning_rate": 4.998182115599052e-06,
"loss": 1.7621,
"step": 18
},
{
"epoch": 0.08,
"learning_rate": 4.99769931413025e-06,
"loss": 1.4677,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 4.997159749281385e-06,
"loss": 1.4017,
"step": 20
},
{
"epoch": 0.09,
"learning_rate": 4.996563433314751e-06,
"loss": 1.5041,
"step": 21
},
{
"epoch": 0.1,
"learning_rate": 4.9959103797823835e-06,
"loss": 1.7749,
"step": 22
},
{
"epoch": 0.1,
"learning_rate": 4.995200603525752e-06,
"loss": 1.5217,
"step": 23
},
{
"epoch": 0.11,
"learning_rate": 4.99443412067542e-06,
"loss": 1.5351,
"step": 24
},
{
"epoch": 0.11,
"learning_rate": 4.993610948650681e-06,
"loss": 1.6509,
"step": 25
},
{
"epoch": 0.12,
"learning_rate": 4.992731106159161e-06,
"loss": 1.3234,
"step": 26
},
{
"epoch": 0.12,
"learning_rate": 4.9917946131963965e-06,
"loss": 1.5587,
"step": 27
},
{
"epoch": 0.13,
"learning_rate": 4.990801491045376e-06,
"loss": 1.5141,
"step": 28
},
{
"epoch": 0.13,
"learning_rate": 4.989751762276056e-06,
"loss": 1.3626,
"step": 29
},
{
"epoch": 0.13,
"learning_rate": 4.988645450744855e-06,
"loss": 1.413,
"step": 30
},
{
"epoch": 0.14,
"learning_rate": 4.987482581594101e-06,
"loss": 1.5925,
"step": 31
},
{
"epoch": 0.14,
"learning_rate": 4.98626318125147e-06,
"loss": 1.6128,
"step": 32
},
{
"epoch": 0.15,
"learning_rate": 4.984987277429377e-06,
"loss": 1.5369,
"step": 33
},
{
"epoch": 0.15,
"learning_rate": 4.983654899124355e-06,
"loss": 1.4611,
"step": 34
},
{
"epoch": 0.16,
"learning_rate": 4.982266076616386e-06,
"loss": 1.3973,
"step": 35
},
{
"epoch": 0.16,
"learning_rate": 4.9808208414682215e-06,
"loss": 1.6418,
"step": 36
},
{
"epoch": 0.17,
"learning_rate": 4.979319226524661e-06,
"loss": 1.5317,
"step": 37
},
{
"epoch": 0.17,
"learning_rate": 4.9777612659118034e-06,
"loss": 1.3446,
"step": 38
},
{
"epoch": 0.17,
"learning_rate": 4.976146995036279e-06,
"loss": 1.6594,
"step": 39
},
{
"epoch": 0.18,
"learning_rate": 4.974476450584438e-06,
"loss": 1.3303,
"step": 40
},
{
"epoch": 0.18,
"learning_rate": 4.972749670521517e-06,
"loss": 1.391,
"step": 41
},
{
"epoch": 0.19,
"learning_rate": 4.970966694090781e-06,
"loss": 1.5491,
"step": 42
},
{
"epoch": 0.19,
"learning_rate": 4.969127561812626e-06,
"loss": 1.7895,
"step": 43
},
{
"epoch": 0.2,
"learning_rate": 4.967232315483664e-06,
"loss": 1.3842,
"step": 44
},
{
"epoch": 0.2,
"learning_rate": 4.965280998175767e-06,
"loss": 1.3015,
"step": 45
},
{
"epoch": 0.21,
"learning_rate": 4.963273654235092e-06,
"loss": 1.5276,
"step": 46
},
{
"epoch": 0.21,
"learning_rate": 4.961210329281072e-06,
"loss": 1.3836,
"step": 47
},
{
"epoch": 0.21,
"learning_rate": 4.959091070205381e-06,
"loss": 1.3379,
"step": 48
},
{
"epoch": 0.22,
"learning_rate": 4.9569159251708635e-06,
"loss": 1.385,
"step": 49
},
{
"epoch": 0.22,
"learning_rate": 4.954684943610446e-06,
"loss": 1.4117,
"step": 50
},
{
"epoch": 0.23,
"learning_rate": 4.95239817622601e-06,
"loss": 1.5684,
"step": 51
},
{
"epoch": 0.23,
"learning_rate": 4.95005567498724e-06,
"loss": 1.4568,
"step": 52
},
{
"epoch": 0.24,
"learning_rate": 4.947657493130443e-06,
"loss": 1.4549,
"step": 53
},
{
"epoch": 0.24,
"learning_rate": 4.945203685157339e-06,
"loss": 1.4898,
"step": 54
},
{
"epoch": 0.25,
"learning_rate": 4.942694306833823e-06,
"loss": 1.3103,
"step": 55
},
{
"epoch": 0.25,
"learning_rate": 4.940129415188693e-06,
"loss": 1.5988,
"step": 56
},
{
"epoch": 0.25,
"learning_rate": 4.937509068512362e-06,
"loss": 1.607,
"step": 57
},
{
"epoch": 0.26,
"learning_rate": 4.934833326355525e-06,
"loss": 1.5436,
"step": 58
},
{
"epoch": 0.26,
"learning_rate": 4.932102249527812e-06,
"loss": 1.5437,
"step": 59
},
{
"epoch": 0.27,
"learning_rate": 4.929315900096403e-06,
"loss": 1.2806,
"step": 60
},
{
"epoch": 0.27,
"learning_rate": 4.9264743413846175e-06,
"loss": 1.7067,
"step": 61
},
{
"epoch": 0.28,
"learning_rate": 4.923577637970475e-06,
"loss": 1.4578,
"step": 62
},
{
"epoch": 0.28,
"learning_rate": 4.920625855685229e-06,
"loss": 1.4264,
"step": 63
},
{
"epoch": 0.29,
"learning_rate": 4.917619061611871e-06,
"loss": 1.376,
"step": 64
},
{
"epoch": 0.29,
"learning_rate": 4.914557324083604e-06,
"loss": 1.5883,
"step": 65
},
{
"epoch": 0.29,
"learning_rate": 4.91144071268229e-06,
"loss": 1.5123,
"step": 66
},
{
"epoch": 0.3,
"learning_rate": 4.908269298236871e-06,
"loss": 1.5713,
"step": 67
},
{
"epoch": 0.3,
"learning_rate": 4.905043152821757e-06,
"loss": 1.7112,
"step": 68
},
{
"epoch": 0.31,
"learning_rate": 4.9017623497551865e-06,
"loss": 1.4226,
"step": 69
},
{
"epoch": 0.31,
"learning_rate": 4.898426963597566e-06,
"loss": 1.5532,
"step": 70
},
{
"epoch": 0.32,
"learning_rate": 4.895037070149769e-06,
"loss": 1.3635,
"step": 71
},
{
"epoch": 0.32,
"learning_rate": 4.8915927464514165e-06,
"loss": 1.4806,
"step": 72
},
{
"epoch": 0.33,
"learning_rate": 4.888094070779127e-06,
"loss": 1.5378,
"step": 73
},
{
"epoch": 0.33,
"learning_rate": 4.884541122644737e-06,
"loss": 1.5027,
"step": 74
},
{
"epoch": 0.34,
"learning_rate": 4.880933982793491e-06,
"loss": 1.5355,
"step": 75
},
{
"epoch": 0.34,
"learning_rate": 4.877272733202212e-06,
"loss": 1.5671,
"step": 76
},
{
"epoch": 0.34,
"learning_rate": 4.873557457077431e-06,
"loss": 1.5142,
"step": 77
},
{
"epoch": 0.35,
"learning_rate": 4.869788238853505e-06,
"loss": 1.4616,
"step": 78
},
{
"epoch": 0.35,
"learning_rate": 4.8659651641906925e-06,
"loss": 1.5574,
"step": 79
},
{
"epoch": 0.36,
"learning_rate": 4.862088319973205e-06,
"loss": 1.5764,
"step": 80
},
{
"epoch": 0.36,
"learning_rate": 4.858157794307237e-06,
"loss": 1.3982,
"step": 81
},
{
"epoch": 0.37,
"learning_rate": 4.8541736765189625e-06,
"loss": 1.2708,
"step": 82
},
{
"epoch": 0.37,
"learning_rate": 4.850136057152505e-06,
"loss": 1.4724,
"step": 83
},
{
"epoch": 0.38,
"learning_rate": 4.8460450279678756e-06,
"loss": 1.3383,
"step": 84
},
{
"epoch": 0.38,
"learning_rate": 4.841900681938895e-06,
"loss": 1.3246,
"step": 85
},
{
"epoch": 0.38,
"learning_rate": 4.837703113251076e-06,
"loss": 1.296,
"step": 86
},
{
"epoch": 0.39,
"learning_rate": 4.83345241729948e-06,
"loss": 1.3624,
"step": 87
},
{
"epoch": 0.39,
"learning_rate": 4.8291486906865595e-06,
"loss": 1.4347,
"step": 88
},
{
"epoch": 0.4,
"learning_rate": 4.824792031219949e-06,
"loss": 1.5823,
"step": 89
},
{
"epoch": 0.4,
"learning_rate": 4.820382537910254e-06,
"loss": 1.4445,
"step": 90
},
{
"epoch": 0.41,
"learning_rate": 4.815920310968793e-06,
"loss": 1.5752,
"step": 91
},
{
"epoch": 0.41,
"learning_rate": 4.8114054518053265e-06,
"loss": 1.435,
"step": 92
},
{
"epoch": 0.42,
"learning_rate": 4.806838063025745e-06,
"loss": 1.5153,
"step": 93
},
{
"epoch": 0.42,
"learning_rate": 4.802218248429742e-06,
"loss": 1.4925,
"step": 94
},
{
"epoch": 0.42,
"learning_rate": 4.797546113008457e-06,
"loss": 1.5668,
"step": 95
},
{
"epoch": 0.43,
"learning_rate": 4.792821762942083e-06,
"loss": 1.3986,
"step": 96
},
{
"epoch": 0.43,
"learning_rate": 4.788045305597457e-06,
"loss": 1.5273,
"step": 97
},
{
"epoch": 0.44,
"learning_rate": 4.783216849525624e-06,
"loss": 1.5795,
"step": 98
},
{
"epoch": 0.44,
"learning_rate": 4.778336504459363e-06,
"loss": 1.4153,
"step": 99
},
{
"epoch": 0.45,
"learning_rate": 4.773404381310693e-06,
"loss": 1.3923,
"step": 100
},
{
"epoch": 0.45,
"learning_rate": 4.768420592168362e-06,
"loss": 1.5524,
"step": 101
},
{
"epoch": 0.46,
"learning_rate": 4.763385250295289e-06,
"loss": 1.4603,
"step": 102
},
{
"epoch": 0.46,
"learning_rate": 4.758298470125994e-06,
"loss": 1.1736,
"step": 103
},
{
"epoch": 0.46,
"learning_rate": 4.753160367263999e-06,
"loss": 1.5845,
"step": 104
},
{
"epoch": 0.47,
"learning_rate": 4.747971058479199e-06,
"loss": 1.4358,
"step": 105
},
{
"epoch": 0.47,
"learning_rate": 4.742730661705206e-06,
"loss": 1.3916,
"step": 106
},
{
"epoch": 0.48,
"learning_rate": 4.7374392960366765e-06,
"loss": 1.5518,
"step": 107
},
{
"epoch": 0.48,
"learning_rate": 4.732097081726594e-06,
"loss": 1.2674,
"step": 108
},
{
"epoch": 0.49,
"learning_rate": 4.7267041401835455e-06,
"loss": 1.6152,
"step": 109
},
{
"epoch": 0.49,
"learning_rate": 4.721260593968956e-06,
"loss": 1.3621,
"step": 110
},
{
"epoch": 0.5,
"learning_rate": 4.715766566794308e-06,
"loss": 1.349,
"step": 111
},
{
"epoch": 0.5,
"learning_rate": 4.710222183518327e-06,
"loss": 1.3356,
"step": 112
},
{
"epoch": 0.51,
"learning_rate": 4.704627570144144e-06,
"loss": 1.4364,
"step": 113
},
{
"epoch": 0.51,
"learning_rate": 4.698982853816434e-06,
"loss": 1.3736,
"step": 114
},
{
"epoch": 0.51,
"learning_rate": 4.693288162818522e-06,
"loss": 1.4143,
"step": 115
},
{
"epoch": 0.52,
"learning_rate": 4.687543626569476e-06,
"loss": 1.4389,
"step": 116
},
{
"epoch": 0.52,
"learning_rate": 4.681749375621154e-06,
"loss": 1.3867,
"step": 117
},
{
"epoch": 0.53,
"learning_rate": 4.675905541655249e-06,
"loss": 1.2436,
"step": 118
},
{
"epoch": 0.53,
"learning_rate": 4.670012257480287e-06,
"loss": 1.3963,
"step": 119
},
{
"epoch": 0.54,
"learning_rate": 4.664069657028617e-06,
"loss": 1.204,
"step": 120
},
{
"epoch": 0.54,
"learning_rate": 4.658077875353357e-06,
"loss": 1.5107,
"step": 121
},
{
"epoch": 0.55,
"learning_rate": 4.652037048625336e-06,
"loss": 1.2643,
"step": 122
},
{
"epoch": 0.55,
"learning_rate": 4.64594731412999e-06,
"loss": 1.3832,
"step": 123
},
{
"epoch": 0.55,
"learning_rate": 4.6398088102642485e-06,
"loss": 1.2725,
"step": 124
},
{
"epoch": 0.56,
"learning_rate": 4.633621676533385e-06,
"loss": 1.3698,
"step": 125
},
{
"epoch": 0.56,
"learning_rate": 4.627386053547851e-06,
"loss": 1.3291,
"step": 126
},
{
"epoch": 0.57,
"learning_rate": 4.621102083020074e-06,
"loss": 1.3378,
"step": 127
},
{
"epoch": 0.57,
"learning_rate": 4.6147699077612425e-06,
"loss": 1.5546,
"step": 128
},
{
"epoch": 0.58,
"learning_rate": 4.60838967167806e-06,
"loss": 1.2718,
"step": 129
},
{
"epoch": 0.58,
"learning_rate": 4.60196151976947e-06,
"loss": 1.3865,
"step": 130
},
{
"epoch": 0.59,
"learning_rate": 4.595485598123366e-06,
"loss": 1.4959,
"step": 131
},
{
"epoch": 0.59,
"learning_rate": 4.588962053913268e-06,
"loss": 1.3494,
"step": 132
},
{
"epoch": 0.59,
"learning_rate": 4.582391035394981e-06,
"loss": 1.4601,
"step": 133
},
{
"epoch": 0.6,
"learning_rate": 4.5757726919032205e-06,
"loss": 1.4359,
"step": 134
},
{
"epoch": 0.6,
"learning_rate": 4.569107173848227e-06,
"loss": 1.3322,
"step": 135
},
{
"epoch": 0.61,
"learning_rate": 4.5623946327123375e-06,
"loss": 1.2575,
"step": 136
},
{
"epoch": 0.61,
"learning_rate": 4.55563522104655e-06,
"loss": 1.3388,
"step": 137
},
{
"epoch": 0.62,
"learning_rate": 4.548829092467058e-06,
"loss": 1.2733,
"step": 138
},
{
"epoch": 0.62,
"learning_rate": 4.541976401651749e-06,
"loss": 1.3894,
"step": 139
},
{
"epoch": 0.63,
"learning_rate": 4.535077304336701e-06,
"loss": 1.4156,
"step": 140
},
{
"epoch": 0.63,
"learning_rate": 4.5281319573126395e-06,
"loss": 1.3675,
"step": 141
},
{
"epoch": 0.63,
"learning_rate": 4.5211405184213705e-06,
"loss": 1.4117,
"step": 142
},
{
"epoch": 0.64,
"learning_rate": 4.514103146552196e-06,
"loss": 1.3661,
"step": 143
},
{
"epoch": 0.64,
"learning_rate": 4.507020001638306e-06,
"loss": 1.4448,
"step": 144
},
{
"epoch": 0.65,
"learning_rate": 4.499891244653136e-06,
"loss": 1.2039,
"step": 145
},
{
"epoch": 0.65,
"learning_rate": 4.49271703760672e-06,
"loss": 1.4663,
"step": 146
},
{
"epoch": 0.66,
"learning_rate": 4.485497543541997e-06,
"loss": 1.3761,
"step": 147
},
{
"epoch": 0.66,
"learning_rate": 4.478232926531112e-06,
"loss": 1.4133,
"step": 148
},
{
"epoch": 0.67,
"learning_rate": 4.4709233516716865e-06,
"loss": 1.4241,
"step": 149
},
{
"epoch": 0.67,
"learning_rate": 4.463568985083068e-06,
"loss": 1.2586,
"step": 150
},
{
"epoch": 0.67,
"learning_rate": 4.45616999390255e-06,
"loss": 1.3779,
"step": 151
},
{
"epoch": 0.68,
"learning_rate": 4.448726546281577e-06,
"loss": 1.5175,
"step": 152
},
{
"epoch": 0.68,
"learning_rate": 4.441238811381923e-06,
"loss": 1.4529,
"step": 153
},
{
"epoch": 0.69,
"learning_rate": 4.4337069593718466e-06,
"loss": 1.3275,
"step": 154
},
{
"epoch": 0.69,
"learning_rate": 4.426131161422223e-06,
"loss": 1.385,
"step": 155
},
{
"epoch": 0.7,
"learning_rate": 4.418511589702655e-06,
"loss": 1.6058,
"step": 156
},
{
"epoch": 0.7,
"learning_rate": 4.410848417377559e-06,
"loss": 1.3474,
"step": 157
},
{
"epoch": 0.71,
"learning_rate": 4.403141818602231e-06,
"loss": 1.4563,
"step": 158
},
{
"epoch": 0.71,
"learning_rate": 4.395391968518888e-06,
"loss": 1.4148,
"step": 159
},
{
"epoch": 0.72,
"learning_rate": 4.387599043252688e-06,
"loss": 1.2975,
"step": 160
},
{
"epoch": 0.72,
"learning_rate": 4.379763219907728e-06,
"loss": 1.3575,
"step": 161
},
{
"epoch": 0.72,
"learning_rate": 4.3718846765630155e-06,
"loss": 1.1464,
"step": 162
},
{
"epoch": 0.73,
"learning_rate": 4.363963592268426e-06,
"loss": 1.291,
"step": 163
},
{
"epoch": 0.73,
"learning_rate": 4.35600014704063e-06,
"loss": 1.1857,
"step": 164
},
{
"epoch": 0.74,
"learning_rate": 4.347994521859008e-06,
"loss": 1.3634,
"step": 165
},
{
"epoch": 0.74,
"learning_rate": 4.33994689866153e-06,
"loss": 1.3407,
"step": 166
},
{
"epoch": 0.75,
"learning_rate": 4.3318574603406235e-06,
"loss": 1.2996,
"step": 167
},
{
"epoch": 0.75,
"learning_rate": 4.32372639073902e-06,
"loss": 1.2419,
"step": 168
},
{
"epoch": 0.76,
"learning_rate": 4.315553874645575e-06,
"loss": 1.5337,
"step": 169
},
{
"epoch": 0.76,
"learning_rate": 4.307340097791064e-06,
"loss": 1.3834,
"step": 170
},
{
"epoch": 0.76,
"learning_rate": 4.29908524684397e-06,
"loss": 1.3191,
"step": 171
},
{
"epoch": 0.77,
"learning_rate": 4.290789509406235e-06,
"loss": 1.2044,
"step": 172
},
{
"epoch": 0.77,
"learning_rate": 4.282453074008996e-06,
"loss": 1.4331,
"step": 173
},
{
"epoch": 0.78,
"learning_rate": 4.2740761301083075e-06,
"loss": 1.2252,
"step": 174
},
{
"epoch": 0.78,
"learning_rate": 4.265658868080826e-06,
"loss": 1.3924,
"step": 175
},
{
"epoch": 0.79,
"learning_rate": 4.257201479219494e-06,
"loss": 1.1913,
"step": 176
},
{
"epoch": 0.79,
"learning_rate": 4.2487041557291815e-06,
"loss": 1.3467,
"step": 177
},
{
"epoch": 0.8,
"learning_rate": 4.240167090722327e-06,
"loss": 1.3273,
"step": 178
},
{
"epoch": 0.8,
"learning_rate": 4.231590478214543e-06,
"loss": 1.6025,
"step": 179
},
{
"epoch": 0.8,
"learning_rate": 4.222974513120213e-06,
"loss": 1.268,
"step": 180
},
{
"epoch": 0.81,
"learning_rate": 4.214319391248053e-06,
"loss": 1.2604,
"step": 181
},
{
"epoch": 0.81,
"learning_rate": 4.205625309296669e-06,
"loss": 1.3002,
"step": 182
},
{
"epoch": 0.82,
"learning_rate": 4.196892464850085e-06,
"loss": 1.2501,
"step": 183
},
{
"epoch": 0.82,
"learning_rate": 4.18812105637325e-06,
"loss": 1.3065,
"step": 184
},
{
"epoch": 0.83,
"learning_rate": 4.1793112832075285e-06,
"loss": 1.3031,
"step": 185
},
{
"epoch": 0.83,
"learning_rate": 4.170463345566175e-06,
"loss": 1.2509,
"step": 186
},
{
"epoch": 0.84,
"learning_rate": 4.161577444529775e-06,
"loss": 1.3437,
"step": 187
},
{
"epoch": 0.84,
"learning_rate": 4.1526537820416845e-06,
"loss": 1.4109,
"step": 188
},
{
"epoch": 0.84,
"learning_rate": 4.143692560903435e-06,
"loss": 1.352,
"step": 189
},
{
"epoch": 0.85,
"learning_rate": 4.134693984770125e-06,
"loss": 1.3928,
"step": 190
},
{
"epoch": 0.85,
"learning_rate": 4.125658258145793e-06,
"loss": 1.1802,
"step": 191
},
{
"epoch": 0.86,
"learning_rate": 4.11658558637877e-06,
"loss": 1.2749,
"step": 192
},
{
"epoch": 0.86,
"learning_rate": 4.107476175657011e-06,
"loss": 1.3822,
"step": 193
},
{
"epoch": 0.87,
"learning_rate": 4.098330233003413e-06,
"loss": 1.6119,
"step": 194
},
{
"epoch": 0.87,
"learning_rate": 4.089147966271103e-06,
"loss": 1.3138,
"step": 195
},
{
"epoch": 0.88,
"learning_rate": 4.079929584138722e-06,
"loss": 1.3743,
"step": 196
},
{
"epoch": 0.88,
"learning_rate": 4.070675296105679e-06,
"loss": 1.3592,
"step": 197
},
{
"epoch": 0.88,
"learning_rate": 4.061385312487389e-06,
"loss": 1.3331,
"step": 198
},
{
"epoch": 0.89,
"learning_rate": 4.052059844410495e-06,
"loss": 1.4225,
"step": 199
},
{
"epoch": 0.89,
"learning_rate": 4.0426991038080695e-06,
"loss": 1.3818,
"step": 200
},
{
"epoch": 0.9,
"learning_rate": 4.033303303414795e-06,
"loss": 1.5789,
"step": 201
},
{
"epoch": 0.9,
"learning_rate": 4.023872656762138e-06,
"loss": 1.3729,
"step": 202
},
{
"epoch": 0.91,
"learning_rate": 4.0144073781734846e-06,
"loss": 1.6156,
"step": 203
},
{
"epoch": 0.91,
"learning_rate": 4.004907682759278e-06,
"loss": 1.111,
"step": 204
},
{
"epoch": 0.92,
"learning_rate": 3.995373786412127e-06,
"loss": 1.2214,
"step": 205
},
{
"epoch": 0.92,
"learning_rate": 3.985805905801902e-06,
"loss": 1.3483,
"step": 206
},
{
"epoch": 0.93,
"learning_rate": 3.976204258370804e-06,
"loss": 1.2765,
"step": 207
},
{
"epoch": 0.93,
"learning_rate": 3.966569062328433e-06,
"loss": 1.4661,
"step": 208
},
{
"epoch": 0.93,
"learning_rate": 3.956900536646819e-06,
"loss": 1.5378,
"step": 209
},
{
"epoch": 0.94,
"learning_rate": 3.947198901055455e-06,
"loss": 1.2259,
"step": 210
},
{
"epoch": 0.94,
"learning_rate": 3.937464376036295e-06,
"loss": 1.1897,
"step": 211
},
{
"epoch": 0.95,
"learning_rate": 3.927697182818748e-06,
"loss": 1.4262,
"step": 212
},
{
"epoch": 0.95,
"learning_rate": 3.917897543374651e-06,
"loss": 1.2388,
"step": 213
},
{
"epoch": 0.96,
"learning_rate": 3.908065680413217e-06,
"loss": 1.3931,
"step": 214
},
{
"epoch": 0.96,
"learning_rate": 3.898201817375987e-06,
"loss": 1.2559,
"step": 215
},
{
"epoch": 0.97,
"learning_rate": 3.8883061784317385e-06,
"loss": 1.2296,
"step": 216
},
{
"epoch": 0.97,
"learning_rate": 3.8783789884714e-06,
"loss": 1.4321,
"step": 217
},
{
"epoch": 0.97,
"learning_rate": 3.868420473102933e-06,
"loss": 1.2664,
"step": 218
},
{
"epoch": 0.98,
"learning_rate": 3.8584308586462126e-06,
"loss": 1.2723,
"step": 219
},
{
"epoch": 0.98,
"learning_rate": 3.8484103721278785e-06,
"loss": 1.2923,
"step": 220
},
{
"epoch": 0.99,
"learning_rate": 3.838359241276177e-06,
"loss": 1.3283,
"step": 221
},
{
"epoch": 0.99,
"learning_rate": 3.8282776945157855e-06,
"loss": 1.3631,
"step": 222
},
{
"epoch": 1.0,
"learning_rate": 3.818165960962621e-06,
"loss": 1.2481,
"step": 223
},
{
"epoch": 1.0,
"learning_rate": 3.8080242704186354e-06,
"loss": 1.3411,
"step": 224
},
{
"epoch": 1.01,
"learning_rate": 3.797852853366589e-06,
"loss": 1.3507,
"step": 225
},
{
"epoch": 1.01,
"learning_rate": 3.7876519409648166e-06,
"loss": 1.4371,
"step": 226
},
{
"epoch": 1.01,
"learning_rate": 3.77742176504197e-06,
"loss": 1.3098,
"step": 227
},
{
"epoch": 1.02,
"learning_rate": 3.767162558091755e-06,
"loss": 1.3359,
"step": 228
},
{
"epoch": 1.02,
"learning_rate": 3.7568745532676394e-06,
"loss": 1.133,
"step": 229
},
{
"epoch": 1.03,
"learning_rate": 3.7465579843775627e-06,
"loss": 1.2886,
"step": 230
},
{
"epoch": 1.0,
"learning_rate": 3.7362130858786195e-06,
"loss": 1.0256,
"step": 231
},
{
"epoch": 1.01,
"learning_rate": 3.7258400928717275e-06,
"loss": 1.4452,
"step": 232
},
{
"epoch": 1.01,
"learning_rate": 3.71543924109629e-06,
"loss": 1.1898,
"step": 233
},
{
"epoch": 1.02,
"learning_rate": 3.7050107669248354e-06,
"loss": 1.378,
"step": 234
},
{
"epoch": 1.02,
"learning_rate": 3.6945549073576463e-06,
"loss": 1.3333,
"step": 235
},
{
"epoch": 1.02,
"learning_rate": 3.6840719000173732e-06,
"loss": 1.2656,
"step": 236
},
{
"epoch": 1.03,
"learning_rate": 3.673561983143633e-06,
"loss": 1.2004,
"step": 237
},
{
"epoch": 1.03,
"learning_rate": 3.6630253955875984e-06,
"loss": 1.2611,
"step": 238
},
{
"epoch": 1.04,
"learning_rate": 3.6524623768065635e-06,
"loss": 1.2505,
"step": 239
},
{
"epoch": 1.04,
"learning_rate": 3.641873166858508e-06,
"loss": 1.3549,
"step": 240
},
{
"epoch": 1.05,
"learning_rate": 3.6312580063966386e-06,
"loss": 1.3383,
"step": 241
},
{
"epoch": 1.05,
"learning_rate": 3.6206171366639197e-06,
"loss": 1.0957,
"step": 242
},
{
"epoch": 1.06,
"learning_rate": 3.6099507994875925e-06,
"loss": 1.4655,
"step": 243
},
{
"epoch": 1.06,
"learning_rate": 3.5992592372736774e-06,
"loss": 1.1838,
"step": 244
},
{
"epoch": 1.06,
"learning_rate": 3.5885426930014656e-06,
"loss": 1.0051,
"step": 245
},
{
"epoch": 1.07,
"learning_rate": 3.5778014102179963e-06,
"loss": 1.4507,
"step": 246
},
{
"epoch": 1.07,
"learning_rate": 3.5670356330325255e-06,
"loss": 1.0756,
"step": 247
},
{
"epoch": 1.08,
"learning_rate": 3.5562456061109736e-06,
"loss": 1.2223,
"step": 248
},
{
"epoch": 1.08,
"learning_rate": 3.5454315746703655e-06,
"loss": 1.4531,
"step": 249
},
{
"epoch": 1.09,
"learning_rate": 3.5345937844732626e-06,
"loss": 1.2236,
"step": 250
},
{
"epoch": 1.09,
"learning_rate": 3.523732481822172e-06,
"loss": 1.4589,
"step": 251
},
{
"epoch": 1.1,
"learning_rate": 3.5128479135539508e-06,
"loss": 1.2666,
"step": 252
},
{
"epoch": 1.1,
"learning_rate": 3.501940327034198e-06,
"loss": 1.1842,
"step": 253
},
{
"epoch": 1.11,
"learning_rate": 3.4910099701516304e-06,
"loss": 1.1918,
"step": 254
},
{
"epoch": 1.11,
"learning_rate": 3.4800570913124516e-06,
"loss": 1.2559,
"step": 255
},
{
"epoch": 1.11,
"learning_rate": 3.4690819394347026e-06,
"loss": 1.3341,
"step": 256
},
{
"epoch": 1.12,
"learning_rate": 3.4580847639426107e-06,
"loss": 1.362,
"step": 257
},
{
"epoch": 1.12,
"learning_rate": 3.447065814760915e-06,
"loss": 1.1807,
"step": 258
},
{
"epoch": 1.13,
"learning_rate": 3.436025342309191e-06,
"loss": 1.2527,
"step": 259
},
{
"epoch": 1.13,
"learning_rate": 3.4249635974961565e-06,
"loss": 1.2667,
"step": 260
},
{
"epoch": 1.14,
"learning_rate": 3.413880831713972e-06,
"loss": 1.2294,
"step": 261
},
{
"epoch": 1.14,
"learning_rate": 3.402777296832525e-06,
"loss": 1.0922,
"step": 262
},
{
"epoch": 1.15,
"learning_rate": 3.3916532451937073e-06,
"loss": 1.2812,
"step": 263
},
{
"epoch": 1.15,
"learning_rate": 3.3805089296056804e-06,
"loss": 1.3606,
"step": 264
},
{
"epoch": 1.15,
"learning_rate": 3.369344603337129e-06,
"loss": 1.292,
"step": 265
},
{
"epoch": 1.16,
"learning_rate": 3.3581605201115075e-06,
"loss": 1.0838,
"step": 266
},
{
"epoch": 1.16,
"learning_rate": 3.3469569341012697e-06,
"loss": 1.2345,
"step": 267
},
{
"epoch": 1.17,
"learning_rate": 3.335734099922097e-06,
"loss": 1.1845,
"step": 268
},
{
"epoch": 1.17,
"learning_rate": 3.3244922726271085e-06,
"loss": 1.1805,
"step": 269
},
{
"epoch": 1.18,
"learning_rate": 3.313231707701066e-06,
"loss": 1.1419,
"step": 270
},
{
"epoch": 1.18,
"learning_rate": 3.3019526610545693e-06,
"loss": 1.4507,
"step": 271
},
{
"epoch": 1.19,
"learning_rate": 3.2906553890182374e-06,
"loss": 1.3256,
"step": 272
},
{
"epoch": 1.19,
"learning_rate": 3.2793401483368837e-06,
"loss": 1.2014,
"step": 273
},
{
"epoch": 1.19,
"learning_rate": 3.268007196163683e-06,
"loss": 1.2178,
"step": 274
},
{
"epoch": 1.2,
"learning_rate": 3.2566567900543256e-06,
"loss": 1.2846,
"step": 275
},
{
"epoch": 1.2,
"learning_rate": 3.2452891879611646e-06,
"loss": 1.1853,
"step": 276
},
{
"epoch": 1.21,
"learning_rate": 3.2339046482273546e-06,
"loss": 1.2271,
"step": 277
},
{
"epoch": 1.21,
"learning_rate": 3.2225034295809783e-06,
"loss": 1.309,
"step": 278
},
{
"epoch": 1.22,
"learning_rate": 3.2110857911291677e-06,
"loss": 1.5285,
"step": 279
},
{
"epoch": 1.22,
"learning_rate": 3.199651992352216e-06,
"loss": 1.3272,
"step": 280
},
{
"epoch": 1.23,
"learning_rate": 3.1882022930976824e-06,
"loss": 1.0063,
"step": 281
},
{
"epoch": 1.23,
"learning_rate": 3.1767369535744807e-06,
"loss": 1.368,
"step": 282
},
{
"epoch": 1.23,
"learning_rate": 3.165256234346972e-06,
"loss": 1.1793,
"step": 283
},
{
"epoch": 1.24,
"learning_rate": 3.1537603963290406e-06,
"loss": 1.1235,
"step": 284
},
{
"epoch": 1.24,
"learning_rate": 3.1422497007781645e-06,
"loss": 1.3773,
"step": 285
},
{
"epoch": 1.25,
"learning_rate": 3.1307244092894763e-06,
"loss": 1.2891,
"step": 286
},
{
"epoch": 1.25,
"learning_rate": 3.1191847837898215e-06,
"loss": 1.3376,
"step": 287
},
{
"epoch": 1.26,
"learning_rate": 3.1076310865318037e-06,
"loss": 1.1235,
"step": 288
},
{
"epoch": 1.26,
"learning_rate": 3.0960635800878254e-06,
"loss": 1.0054,
"step": 289
},
{
"epoch": 1.27,
"learning_rate": 3.08448252734412e-06,
"loss": 0.9459,
"step": 290
},
{
"epoch": 1.27,
"learning_rate": 3.072888191494776e-06,
"loss": 1.1185,
"step": 291
},
{
"epoch": 1.27,
"learning_rate": 3.061280836035761e-06,
"loss": 1.1609,
"step": 292
},
{
"epoch": 1.28,
"learning_rate": 3.049660724758926e-06,
"loss": 1.3326,
"step": 293
},
{
"epoch": 1.28,
"learning_rate": 3.0380281217460177e-06,
"loss": 1.2813,
"step": 294
},
{
"epoch": 1.29,
"learning_rate": 3.02638329136267e-06,
"loss": 1.2793,
"step": 295
},
{
"epoch": 1.29,
"learning_rate": 3.014726498252401e-06,
"loss": 1.317,
"step": 296
},
{
"epoch": 1.3,
"learning_rate": 3.003058007330596e-06,
"loss": 1.3697,
"step": 297
},
{
"epoch": 1.3,
"learning_rate": 2.9913780837784894e-06,
"loss": 1.2674,
"step": 298
},
{
"epoch": 1.31,
"learning_rate": 2.9796869930371354e-06,
"loss": 1.3353,
"step": 299
},
{
"epoch": 1.31,
"learning_rate": 2.967985000801376e-06,
"loss": 1.1276,
"step": 300
},
{
"epoch": 1.32,
"learning_rate": 2.9562723730138067e-06,
"loss": 1.089,
"step": 301
},
{
"epoch": 1.32,
"learning_rate": 2.944549375858725e-06,
"loss": 1.3092,
"step": 302
},
{
"epoch": 1.32,
"learning_rate": 2.932816275756088e-06,
"loss": 1.1604,
"step": 303
},
{
"epoch": 1.33,
"learning_rate": 2.921073339355456e-06,
"loss": 1.2496,
"step": 304
},
{
"epoch": 1.33,
"learning_rate": 2.9093208335299283e-06,
"loss": 1.2698,
"step": 305
},
{
"epoch": 1.34,
"learning_rate": 2.8975590253700847e-06,
"loss": 1.2362,
"step": 306
},
{
"epoch": 1.34,
"learning_rate": 2.88578818217791e-06,
"loss": 1.1404,
"step": 307
},
{
"epoch": 1.35,
"learning_rate": 2.8740085714607243e-06,
"loss": 1.374,
"step": 308
},
{
"epoch": 1.35,
"learning_rate": 2.862220460925098e-06,
"loss": 1.047,
"step": 309
},
{
"epoch": 1.36,
"learning_rate": 2.8504241184707715e-06,
"loss": 1.2832,
"step": 310
},
{
"epoch": 1.36,
"learning_rate": 2.8386198121845677e-06,
"loss": 1.3308,
"step": 311
},
{
"epoch": 1.36,
"learning_rate": 2.826807810334295e-06,
"loss": 1.0979,
"step": 312
},
{
"epoch": 1.37,
"learning_rate": 2.814988381362654e-06,
"loss": 1.0286,
"step": 313
},
{
"epoch": 1.37,
"learning_rate": 2.8031617938811378e-06,
"loss": 1.2865,
"step": 314
},
{
"epoch": 1.38,
"learning_rate": 2.7913283166639244e-06,
"loss": 1.321,
"step": 315
},
{
"epoch": 1.38,
"learning_rate": 2.779488218641768e-06,
"loss": 1.1839,
"step": 316
},
{
"epoch": 1.39,
"learning_rate": 2.767641768895893e-06,
"loss": 1.3904,
"step": 317
},
{
"epoch": 1.39,
"learning_rate": 2.7557892366518713e-06,
"loss": 1.1613,
"step": 318
},
{
"epoch": 1.4,
"learning_rate": 2.743930891273509e-06,
"loss": 1.1307,
"step": 319
},
{
"epoch": 1.4,
"learning_rate": 2.7320670022567213e-06,
"loss": 1.0942,
"step": 320
}
],
"logging_steps": 1,
"max_steps": 669,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 20,
"total_flos": 2.2632085353136128e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}