adalaw's picture
Upload folder using huggingface_hub
897c85c verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9978570900761102,
"eval_steps": 500,
"global_step": 422,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 3.921568627450981e-07,
"loss": 2.8563,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 7.843137254901962e-07,
"loss": 3.0208,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 1.1764705882352942e-06,
"loss": 4.0651,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 1.5686274509803923e-06,
"loss": 3.3154,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 1.96078431372549e-06,
"loss": 3.9875,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 2.3529411764705885e-06,
"loss": 9.4198,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 2.7450980392156867e-06,
"loss": 3.4956,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 3.1372549019607846e-06,
"loss": 3.646,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 3.529411764705883e-06,
"loss": 2.9569,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 3.92156862745098e-06,
"loss": 3.2712,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 4.313725490196079e-06,
"loss": 4.4552,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 4.705882352941177e-06,
"loss": 3.2141,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 5.098039215686274e-06,
"loss": 2.8645,
"step": 13
},
{
"epoch": 0.03,
"learning_rate": 5.4901960784313735e-06,
"loss": 2.9299,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 5.882352941176471e-06,
"loss": 3.2333,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 6.274509803921569e-06,
"loss": 3.3361,
"step": 16
},
{
"epoch": 0.04,
"learning_rate": 6.666666666666667e-06,
"loss": 2.8326,
"step": 17
},
{
"epoch": 0.04,
"learning_rate": 7.058823529411766e-06,
"loss": 5.9936,
"step": 18
},
{
"epoch": 0.04,
"learning_rate": 7.450980392156863e-06,
"loss": 2.7551,
"step": 19
},
{
"epoch": 0.05,
"learning_rate": 7.84313725490196e-06,
"loss": 2.3296,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 8.23529411764706e-06,
"loss": 2.1901,
"step": 21
},
{
"epoch": 0.05,
"learning_rate": 8.627450980392157e-06,
"loss": 1.7673,
"step": 22
},
{
"epoch": 0.05,
"learning_rate": 9.019607843137256e-06,
"loss": 1.6721,
"step": 23
},
{
"epoch": 0.06,
"learning_rate": 9.411764705882354e-06,
"loss": 1.7151,
"step": 24
},
{
"epoch": 0.06,
"learning_rate": 9.803921568627451e-06,
"loss": 1.7576,
"step": 25
},
{
"epoch": 0.06,
"learning_rate": 1.0196078431372549e-05,
"loss": 1.4461,
"step": 26
},
{
"epoch": 0.06,
"learning_rate": 1.0588235294117648e-05,
"loss": 3.8357,
"step": 27
},
{
"epoch": 0.07,
"learning_rate": 1.0980392156862747e-05,
"loss": 1.5292,
"step": 28
},
{
"epoch": 0.07,
"learning_rate": 1.1372549019607844e-05,
"loss": 1.484,
"step": 29
},
{
"epoch": 0.07,
"learning_rate": 1.1764705882352942e-05,
"loss": 1.2995,
"step": 30
},
{
"epoch": 0.07,
"learning_rate": 1.215686274509804e-05,
"loss": 1.1459,
"step": 31
},
{
"epoch": 0.08,
"learning_rate": 1.2549019607843138e-05,
"loss": 1.1017,
"step": 32
},
{
"epoch": 0.08,
"learning_rate": 1.2941176470588238e-05,
"loss": 1.2681,
"step": 33
},
{
"epoch": 0.08,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.7749,
"step": 34
},
{
"epoch": 0.08,
"learning_rate": 1.3725490196078432e-05,
"loss": 1.4039,
"step": 35
},
{
"epoch": 0.09,
"learning_rate": 1.4117647058823532e-05,
"loss": 1.304,
"step": 36
},
{
"epoch": 0.09,
"learning_rate": 1.4509803921568629e-05,
"loss": 1.1641,
"step": 37
},
{
"epoch": 0.09,
"learning_rate": 1.4901960784313726e-05,
"loss": 1.0715,
"step": 38
},
{
"epoch": 0.09,
"learning_rate": 1.5294117647058822e-05,
"loss": 1.0567,
"step": 39
},
{
"epoch": 0.09,
"learning_rate": 1.568627450980392e-05,
"loss": 1.3111,
"step": 40
},
{
"epoch": 0.1,
"learning_rate": 1.607843137254902e-05,
"loss": 1.4909,
"step": 41
},
{
"epoch": 0.1,
"learning_rate": 1.647058823529412e-05,
"loss": 0.961,
"step": 42
},
{
"epoch": 0.1,
"learning_rate": 1.686274509803922e-05,
"loss": 1.1519,
"step": 43
},
{
"epoch": 0.1,
"learning_rate": 1.7254901960784314e-05,
"loss": 0.9403,
"step": 44
},
{
"epoch": 0.11,
"learning_rate": 1.7647058823529414e-05,
"loss": 1.1603,
"step": 45
},
{
"epoch": 0.11,
"learning_rate": 1.8039215686274513e-05,
"loss": 0.9909,
"step": 46
},
{
"epoch": 0.11,
"learning_rate": 1.843137254901961e-05,
"loss": 1.0872,
"step": 47
},
{
"epoch": 0.11,
"learning_rate": 1.8823529411764708e-05,
"loss": 1.0935,
"step": 48
},
{
"epoch": 0.12,
"learning_rate": 1.9215686274509807e-05,
"loss": 1.2776,
"step": 49
},
{
"epoch": 0.12,
"learning_rate": 1.9607843137254903e-05,
"loss": 1.0812,
"step": 50
},
{
"epoch": 0.12,
"learning_rate": 2e-05,
"loss": 1.0436,
"step": 51
},
{
"epoch": 0.12,
"learning_rate": 1.9987782529016497e-05,
"loss": 1.275,
"step": 52
},
{
"epoch": 0.13,
"learning_rate": 1.997556505803299e-05,
"loss": 1.1309,
"step": 53
},
{
"epoch": 0.13,
"learning_rate": 1.9963347587049484e-05,
"loss": 1.0838,
"step": 54
},
{
"epoch": 0.13,
"learning_rate": 1.9951130116065975e-05,
"loss": 1.0861,
"step": 55
},
{
"epoch": 0.13,
"learning_rate": 1.993891264508247e-05,
"loss": 0.9737,
"step": 56
},
{
"epoch": 0.13,
"learning_rate": 1.9926695174098962e-05,
"loss": 0.9726,
"step": 57
},
{
"epoch": 0.14,
"learning_rate": 1.9914477703115457e-05,
"loss": 1.1044,
"step": 58
},
{
"epoch": 0.14,
"learning_rate": 1.9902260232131952e-05,
"loss": 1.2198,
"step": 59
},
{
"epoch": 0.14,
"learning_rate": 1.9890042761148444e-05,
"loss": 1.2454,
"step": 60
},
{
"epoch": 0.14,
"learning_rate": 1.987782529016494e-05,
"loss": 1.0945,
"step": 61
},
{
"epoch": 0.15,
"learning_rate": 1.986560781918143e-05,
"loss": 1.2243,
"step": 62
},
{
"epoch": 0.15,
"learning_rate": 1.9853390348197926e-05,
"loss": 1.0895,
"step": 63
},
{
"epoch": 0.15,
"learning_rate": 1.9841172877214418e-05,
"loss": 1.3153,
"step": 64
},
{
"epoch": 0.15,
"learning_rate": 1.9828955406230913e-05,
"loss": 1.3891,
"step": 65
},
{
"epoch": 0.16,
"learning_rate": 1.9816737935247404e-05,
"loss": 1.1219,
"step": 66
},
{
"epoch": 0.16,
"learning_rate": 1.98045204642639e-05,
"loss": 1.0493,
"step": 67
},
{
"epoch": 0.16,
"learning_rate": 1.979230299328039e-05,
"loss": 1.0645,
"step": 68
},
{
"epoch": 0.16,
"learning_rate": 1.9780085522296886e-05,
"loss": 1.3425,
"step": 69
},
{
"epoch": 0.17,
"learning_rate": 1.9767868051313378e-05,
"loss": 1.8974,
"step": 70
},
{
"epoch": 0.17,
"learning_rate": 1.9755650580329873e-05,
"loss": 1.0191,
"step": 71
},
{
"epoch": 0.17,
"learning_rate": 1.9743433109346365e-05,
"loss": 1.1784,
"step": 72
},
{
"epoch": 0.17,
"learning_rate": 1.973121563836286e-05,
"loss": 1.0353,
"step": 73
},
{
"epoch": 0.17,
"learning_rate": 1.9718998167379355e-05,
"loss": 1.2755,
"step": 74
},
{
"epoch": 0.18,
"learning_rate": 1.970678069639585e-05,
"loss": 0.9851,
"step": 75
},
{
"epoch": 0.18,
"learning_rate": 1.9694563225412342e-05,
"loss": 1.2396,
"step": 76
},
{
"epoch": 0.18,
"learning_rate": 1.9682345754428837e-05,
"loss": 1.2519,
"step": 77
},
{
"epoch": 0.18,
"learning_rate": 1.967012828344533e-05,
"loss": 0.9313,
"step": 78
},
{
"epoch": 0.19,
"learning_rate": 1.9657910812461824e-05,
"loss": 1.1745,
"step": 79
},
{
"epoch": 0.19,
"learning_rate": 1.9645693341478315e-05,
"loss": 1.0521,
"step": 80
},
{
"epoch": 0.19,
"learning_rate": 1.963347587049481e-05,
"loss": 0.9781,
"step": 81
},
{
"epoch": 0.19,
"learning_rate": 1.9621258399511302e-05,
"loss": 1.0292,
"step": 82
},
{
"epoch": 0.2,
"learning_rate": 1.9609040928527797e-05,
"loss": 0.851,
"step": 83
},
{
"epoch": 0.2,
"learning_rate": 1.959682345754429e-05,
"loss": 1.1486,
"step": 84
},
{
"epoch": 0.2,
"learning_rate": 1.9584605986560784e-05,
"loss": 1.0732,
"step": 85
},
{
"epoch": 0.2,
"learning_rate": 1.9572388515577276e-05,
"loss": 1.0466,
"step": 86
},
{
"epoch": 0.21,
"learning_rate": 1.956017104459377e-05,
"loss": 0.9275,
"step": 87
},
{
"epoch": 0.21,
"learning_rate": 1.9547953573610263e-05,
"loss": 1.7509,
"step": 88
},
{
"epoch": 0.21,
"learning_rate": 1.9535736102626758e-05,
"loss": 1.3038,
"step": 89
},
{
"epoch": 0.21,
"learning_rate": 1.9523518631643253e-05,
"loss": 0.8664,
"step": 90
},
{
"epoch": 0.22,
"learning_rate": 1.9511301160659744e-05,
"loss": 1.1555,
"step": 91
},
{
"epoch": 0.22,
"learning_rate": 1.949908368967624e-05,
"loss": 1.1517,
"step": 92
},
{
"epoch": 0.22,
"learning_rate": 1.948686621869273e-05,
"loss": 1.0223,
"step": 93
},
{
"epoch": 0.22,
"learning_rate": 1.9474648747709226e-05,
"loss": 1.0649,
"step": 94
},
{
"epoch": 0.22,
"learning_rate": 1.9462431276725718e-05,
"loss": 1.0147,
"step": 95
},
{
"epoch": 0.23,
"learning_rate": 1.9450213805742213e-05,
"loss": 1.3624,
"step": 96
},
{
"epoch": 0.23,
"learning_rate": 1.9437996334758705e-05,
"loss": 1.1294,
"step": 97
},
{
"epoch": 0.23,
"learning_rate": 1.94257788637752e-05,
"loss": 1.1903,
"step": 98
},
{
"epoch": 0.23,
"learning_rate": 1.941356139279169e-05,
"loss": 0.8732,
"step": 99
},
{
"epoch": 0.24,
"learning_rate": 1.9401343921808187e-05,
"loss": 1.1793,
"step": 100
},
{
"epoch": 0.24,
"learning_rate": 1.938912645082468e-05,
"loss": 0.9008,
"step": 101
},
{
"epoch": 0.24,
"learning_rate": 1.9376908979841174e-05,
"loss": 1.2374,
"step": 102
},
{
"epoch": 0.24,
"learning_rate": 1.936469150885767e-05,
"loss": 0.9163,
"step": 103
},
{
"epoch": 0.25,
"learning_rate": 1.9352474037874164e-05,
"loss": 0.9702,
"step": 104
},
{
"epoch": 0.25,
"learning_rate": 1.9340256566890655e-05,
"loss": 1.0813,
"step": 105
},
{
"epoch": 0.25,
"learning_rate": 1.932803909590715e-05,
"loss": 1.1164,
"step": 106
},
{
"epoch": 0.25,
"learning_rate": 1.9315821624923642e-05,
"loss": 0.9403,
"step": 107
},
{
"epoch": 0.26,
"learning_rate": 1.9303604153940137e-05,
"loss": 1.074,
"step": 108
},
{
"epoch": 0.26,
"learning_rate": 1.929138668295663e-05,
"loss": 1.1077,
"step": 109
},
{
"epoch": 0.26,
"learning_rate": 1.9279169211973124e-05,
"loss": 1.0153,
"step": 110
},
{
"epoch": 0.26,
"learning_rate": 1.9266951740989616e-05,
"loss": 1.0281,
"step": 111
},
{
"epoch": 0.26,
"learning_rate": 1.925473427000611e-05,
"loss": 0.9075,
"step": 112
},
{
"epoch": 0.27,
"learning_rate": 1.9242516799022603e-05,
"loss": 1.2191,
"step": 113
},
{
"epoch": 0.27,
"learning_rate": 1.9230299328039098e-05,
"loss": 1.0649,
"step": 114
},
{
"epoch": 0.27,
"learning_rate": 1.921808185705559e-05,
"loss": 0.9901,
"step": 115
},
{
"epoch": 0.27,
"learning_rate": 1.9205864386072085e-05,
"loss": 1.0329,
"step": 116
},
{
"epoch": 0.28,
"learning_rate": 1.9193646915088576e-05,
"loss": 1.4406,
"step": 117
},
{
"epoch": 0.28,
"learning_rate": 1.918142944410507e-05,
"loss": 1.138,
"step": 118
},
{
"epoch": 0.28,
"learning_rate": 1.9169211973121567e-05,
"loss": 1.1755,
"step": 119
},
{
"epoch": 0.28,
"learning_rate": 1.9156994502138058e-05,
"loss": 0.9568,
"step": 120
},
{
"epoch": 0.29,
"learning_rate": 1.9144777031154553e-05,
"loss": 1.0204,
"step": 121
},
{
"epoch": 0.29,
"learning_rate": 1.913255956017105e-05,
"loss": 0.9391,
"step": 122
},
{
"epoch": 0.29,
"learning_rate": 1.912034208918754e-05,
"loss": 1.109,
"step": 123
},
{
"epoch": 0.29,
"learning_rate": 1.9108124618204035e-05,
"loss": 1.2183,
"step": 124
},
{
"epoch": 0.3,
"learning_rate": 1.9095907147220527e-05,
"loss": 0.9377,
"step": 125
},
{
"epoch": 0.3,
"learning_rate": 1.9083689676237022e-05,
"loss": 1.0865,
"step": 126
},
{
"epoch": 0.3,
"learning_rate": 1.9071472205253514e-05,
"loss": 1.2078,
"step": 127
},
{
"epoch": 0.3,
"learning_rate": 1.905925473427001e-05,
"loss": 1.0149,
"step": 128
},
{
"epoch": 0.31,
"learning_rate": 1.90470372632865e-05,
"loss": 1.1191,
"step": 129
},
{
"epoch": 0.31,
"learning_rate": 1.9034819792302996e-05,
"loss": 1.0933,
"step": 130
},
{
"epoch": 0.31,
"learning_rate": 1.9022602321319487e-05,
"loss": 0.9312,
"step": 131
},
{
"epoch": 0.31,
"learning_rate": 1.9010384850335982e-05,
"loss": 0.794,
"step": 132
},
{
"epoch": 0.31,
"learning_rate": 1.8998167379352474e-05,
"loss": 0.8745,
"step": 133
},
{
"epoch": 0.32,
"learning_rate": 1.898594990836897e-05,
"loss": 0.9092,
"step": 134
},
{
"epoch": 0.32,
"learning_rate": 1.8973732437385464e-05,
"loss": 0.7504,
"step": 135
},
{
"epoch": 0.32,
"learning_rate": 1.8961514966401956e-05,
"loss": 1.2165,
"step": 136
},
{
"epoch": 0.32,
"learning_rate": 1.894929749541845e-05,
"loss": 0.9727,
"step": 137
},
{
"epoch": 0.33,
"learning_rate": 1.8937080024434943e-05,
"loss": 1.0236,
"step": 138
},
{
"epoch": 0.33,
"learning_rate": 1.8924862553451438e-05,
"loss": 0.9628,
"step": 139
},
{
"epoch": 0.33,
"learning_rate": 1.891264508246793e-05,
"loss": 0.8762,
"step": 140
},
{
"epoch": 0.33,
"learning_rate": 1.8900427611484425e-05,
"loss": 1.0712,
"step": 141
},
{
"epoch": 0.34,
"learning_rate": 1.8888210140500916e-05,
"loss": 0.7999,
"step": 142
},
{
"epoch": 0.34,
"learning_rate": 1.887599266951741e-05,
"loss": 0.9812,
"step": 143
},
{
"epoch": 0.34,
"learning_rate": 1.8863775198533903e-05,
"loss": 1.8394,
"step": 144
},
{
"epoch": 0.34,
"learning_rate": 1.88515577275504e-05,
"loss": 0.9033,
"step": 145
},
{
"epoch": 0.35,
"learning_rate": 1.883934025656689e-05,
"loss": 0.9813,
"step": 146
},
{
"epoch": 0.35,
"learning_rate": 1.8827122785583385e-05,
"loss": 0.7722,
"step": 147
},
{
"epoch": 0.35,
"learning_rate": 1.8814905314599877e-05,
"loss": 0.9991,
"step": 148
},
{
"epoch": 0.35,
"learning_rate": 1.8802687843616375e-05,
"loss": 0.9531,
"step": 149
},
{
"epoch": 0.35,
"learning_rate": 1.8790470372632867e-05,
"loss": 0.9034,
"step": 150
},
{
"epoch": 0.36,
"learning_rate": 1.8778252901649362e-05,
"loss": 0.8741,
"step": 151
},
{
"epoch": 0.36,
"learning_rate": 1.8766035430665854e-05,
"loss": 1.1228,
"step": 152
},
{
"epoch": 0.36,
"learning_rate": 1.875381795968235e-05,
"loss": 0.7849,
"step": 153
},
{
"epoch": 0.36,
"learning_rate": 1.874160048869884e-05,
"loss": 0.9642,
"step": 154
},
{
"epoch": 0.37,
"learning_rate": 1.8729383017715336e-05,
"loss": 1.0823,
"step": 155
},
{
"epoch": 0.37,
"learning_rate": 1.8717165546731827e-05,
"loss": 1.2156,
"step": 156
},
{
"epoch": 0.37,
"learning_rate": 1.8704948075748323e-05,
"loss": 1.4682,
"step": 157
},
{
"epoch": 0.37,
"learning_rate": 1.8692730604764814e-05,
"loss": 1.2043,
"step": 158
},
{
"epoch": 0.38,
"learning_rate": 1.868051313378131e-05,
"loss": 0.9802,
"step": 159
},
{
"epoch": 0.38,
"learning_rate": 1.86682956627978e-05,
"loss": 1.1539,
"step": 160
},
{
"epoch": 0.38,
"learning_rate": 1.8656078191814296e-05,
"loss": 1.1245,
"step": 161
},
{
"epoch": 0.38,
"learning_rate": 1.8643860720830788e-05,
"loss": 1.099,
"step": 162
},
{
"epoch": 0.39,
"learning_rate": 1.8631643249847283e-05,
"loss": 1.0272,
"step": 163
},
{
"epoch": 0.39,
"learning_rate": 1.8619425778863778e-05,
"loss": 1.0072,
"step": 164
},
{
"epoch": 0.39,
"learning_rate": 1.860720830788027e-05,
"loss": 1.0215,
"step": 165
},
{
"epoch": 0.39,
"learning_rate": 1.8594990836896765e-05,
"loss": 1.0221,
"step": 166
},
{
"epoch": 0.39,
"learning_rate": 1.8582773365913257e-05,
"loss": 1.0754,
"step": 167
},
{
"epoch": 0.4,
"learning_rate": 1.857055589492975e-05,
"loss": 0.9724,
"step": 168
},
{
"epoch": 0.4,
"learning_rate": 1.8558338423946243e-05,
"loss": 1.031,
"step": 169
},
{
"epoch": 0.4,
"learning_rate": 1.854612095296274e-05,
"loss": 1.157,
"step": 170
},
{
"epoch": 0.4,
"learning_rate": 1.853390348197923e-05,
"loss": 0.9819,
"step": 171
},
{
"epoch": 0.41,
"learning_rate": 1.8521686010995725e-05,
"loss": 1.1156,
"step": 172
},
{
"epoch": 0.41,
"learning_rate": 1.850946854001222e-05,
"loss": 1.0699,
"step": 173
},
{
"epoch": 0.41,
"learning_rate": 1.8497251069028712e-05,
"loss": 1.1092,
"step": 174
},
{
"epoch": 0.41,
"learning_rate": 1.8485033598045207e-05,
"loss": 1.0092,
"step": 175
},
{
"epoch": 0.42,
"learning_rate": 1.84728161270617e-05,
"loss": 1.0403,
"step": 176
},
{
"epoch": 0.42,
"learning_rate": 1.8460598656078194e-05,
"loss": 0.8809,
"step": 177
},
{
"epoch": 0.42,
"learning_rate": 1.8448381185094686e-05,
"loss": 1.0139,
"step": 178
},
{
"epoch": 0.42,
"learning_rate": 1.843616371411118e-05,
"loss": 1.0701,
"step": 179
},
{
"epoch": 0.43,
"learning_rate": 1.8423946243127676e-05,
"loss": 0.9199,
"step": 180
},
{
"epoch": 0.43,
"learning_rate": 1.8411728772144168e-05,
"loss": 0.8542,
"step": 181
},
{
"epoch": 0.43,
"learning_rate": 1.8399511301160663e-05,
"loss": 1.0369,
"step": 182
},
{
"epoch": 0.43,
"learning_rate": 1.8387293830177154e-05,
"loss": 0.9847,
"step": 183
},
{
"epoch": 0.44,
"learning_rate": 1.837507635919365e-05,
"loss": 0.8046,
"step": 184
},
{
"epoch": 0.44,
"learning_rate": 1.836285888821014e-05,
"loss": 1.2821,
"step": 185
},
{
"epoch": 0.44,
"learning_rate": 1.8350641417226636e-05,
"loss": 1.0127,
"step": 186
},
{
"epoch": 0.44,
"learning_rate": 1.8338423946243128e-05,
"loss": 0.8535,
"step": 187
},
{
"epoch": 0.44,
"learning_rate": 1.8326206475259623e-05,
"loss": 0.984,
"step": 188
},
{
"epoch": 0.45,
"learning_rate": 1.8313989004276115e-05,
"loss": 0.771,
"step": 189
},
{
"epoch": 0.45,
"learning_rate": 1.830177153329261e-05,
"loss": 2.1482,
"step": 190
},
{
"epoch": 0.45,
"learning_rate": 1.82895540623091e-05,
"loss": 0.7799,
"step": 191
},
{
"epoch": 0.45,
"learning_rate": 1.8277336591325597e-05,
"loss": 1.1474,
"step": 192
},
{
"epoch": 0.46,
"learning_rate": 1.826511912034209e-05,
"loss": 1.0967,
"step": 193
},
{
"epoch": 0.46,
"learning_rate": 1.8252901649358587e-05,
"loss": 0.8824,
"step": 194
},
{
"epoch": 0.46,
"learning_rate": 1.824068417837508e-05,
"loss": 0.9202,
"step": 195
},
{
"epoch": 0.46,
"learning_rate": 1.8228466707391574e-05,
"loss": 0.8055,
"step": 196
},
{
"epoch": 0.47,
"learning_rate": 1.8216249236408065e-05,
"loss": 0.7309,
"step": 197
},
{
"epoch": 0.47,
"learning_rate": 1.820403176542456e-05,
"loss": 1.1121,
"step": 198
},
{
"epoch": 0.47,
"learning_rate": 1.8191814294441052e-05,
"loss": 1.5694,
"step": 199
},
{
"epoch": 0.47,
"learning_rate": 1.8179596823457547e-05,
"loss": 1.2677,
"step": 200
},
{
"epoch": 0.48,
"learning_rate": 1.816737935247404e-05,
"loss": 1.1242,
"step": 201
},
{
"epoch": 0.48,
"learning_rate": 1.8155161881490534e-05,
"loss": 0.8419,
"step": 202
},
{
"epoch": 0.48,
"learning_rate": 1.8142944410507026e-05,
"loss": 1.1399,
"step": 203
},
{
"epoch": 0.48,
"learning_rate": 1.813072693952352e-05,
"loss": 0.7964,
"step": 204
},
{
"epoch": 0.48,
"learning_rate": 1.8118509468540013e-05,
"loss": 0.9321,
"step": 205
},
{
"epoch": 0.49,
"learning_rate": 1.8106291997556508e-05,
"loss": 0.8461,
"step": 206
},
{
"epoch": 0.49,
"learning_rate": 1.8094074526573e-05,
"loss": 1.0457,
"step": 207
},
{
"epoch": 0.49,
"learning_rate": 1.8081857055589494e-05,
"loss": 1.085,
"step": 208
},
{
"epoch": 0.49,
"learning_rate": 1.806963958460599e-05,
"loss": 0.9105,
"step": 209
},
{
"epoch": 0.5,
"learning_rate": 1.805742211362248e-05,
"loss": 0.9143,
"step": 210
},
{
"epoch": 0.5,
"learning_rate": 1.8045204642638976e-05,
"loss": 1.0978,
"step": 211
},
{
"epoch": 0.5,
"learning_rate": 1.8032987171655468e-05,
"loss": 0.9884,
"step": 212
},
{
"epoch": 0.5,
"learning_rate": 1.8020769700671963e-05,
"loss": 1.0179,
"step": 213
},
{
"epoch": 0.51,
"learning_rate": 1.8008552229688455e-05,
"loss": 1.2135,
"step": 214
},
{
"epoch": 0.51,
"learning_rate": 1.799633475870495e-05,
"loss": 0.9051,
"step": 215
},
{
"epoch": 0.51,
"learning_rate": 1.7984117287721442e-05,
"loss": 0.8954,
"step": 216
},
{
"epoch": 0.51,
"learning_rate": 1.7971899816737937e-05,
"loss": 1.1429,
"step": 217
},
{
"epoch": 0.52,
"learning_rate": 1.795968234575443e-05,
"loss": 1.0803,
"step": 218
},
{
"epoch": 0.52,
"learning_rate": 1.7947464874770924e-05,
"loss": 1.0558,
"step": 219
},
{
"epoch": 0.52,
"learning_rate": 1.7935247403787415e-05,
"loss": 1.0904,
"step": 220
},
{
"epoch": 0.52,
"learning_rate": 1.792302993280391e-05,
"loss": 1.0909,
"step": 221
},
{
"epoch": 0.52,
"learning_rate": 1.7910812461820402e-05,
"loss": 1.1515,
"step": 222
},
{
"epoch": 0.53,
"learning_rate": 1.7898594990836897e-05,
"loss": 1.0393,
"step": 223
},
{
"epoch": 0.53,
"learning_rate": 1.7886377519853392e-05,
"loss": 1.0072,
"step": 224
},
{
"epoch": 0.53,
"learning_rate": 1.7874160048869887e-05,
"loss": 0.8387,
"step": 225
},
{
"epoch": 0.53,
"learning_rate": 1.786194257788638e-05,
"loss": 0.8908,
"step": 226
},
{
"epoch": 0.54,
"learning_rate": 1.7849725106902874e-05,
"loss": 0.875,
"step": 227
},
{
"epoch": 0.54,
"learning_rate": 1.7837507635919366e-05,
"loss": 1.0477,
"step": 228
},
{
"epoch": 0.54,
"learning_rate": 1.782529016493586e-05,
"loss": 1.0117,
"step": 229
},
{
"epoch": 0.54,
"learning_rate": 1.7813072693952353e-05,
"loss": 1.1684,
"step": 230
},
{
"epoch": 0.55,
"learning_rate": 1.7800855222968848e-05,
"loss": 1.1475,
"step": 231
},
{
"epoch": 0.55,
"learning_rate": 1.778863775198534e-05,
"loss": 1.2069,
"step": 232
},
{
"epoch": 0.55,
"learning_rate": 1.7776420281001835e-05,
"loss": 1.1107,
"step": 233
},
{
"epoch": 0.55,
"learning_rate": 1.7764202810018326e-05,
"loss": 0.9738,
"step": 234
},
{
"epoch": 0.56,
"learning_rate": 1.775198533903482e-05,
"loss": 0.8838,
"step": 235
},
{
"epoch": 0.56,
"learning_rate": 1.7739767868051313e-05,
"loss": 1.0103,
"step": 236
},
{
"epoch": 0.56,
"learning_rate": 1.7727550397067808e-05,
"loss": 0.9279,
"step": 237
},
{
"epoch": 0.56,
"learning_rate": 1.77153329260843e-05,
"loss": 0.9682,
"step": 238
},
{
"epoch": 0.57,
"learning_rate": 1.7703115455100795e-05,
"loss": 1.2049,
"step": 239
},
{
"epoch": 0.57,
"learning_rate": 1.769089798411729e-05,
"loss": 1.0387,
"step": 240
},
{
"epoch": 0.57,
"learning_rate": 1.7678680513133785e-05,
"loss": 0.9754,
"step": 241
},
{
"epoch": 0.57,
"learning_rate": 1.7666463042150277e-05,
"loss": 1.0202,
"step": 242
},
{
"epoch": 0.57,
"learning_rate": 1.7654245571166772e-05,
"loss": 1.0224,
"step": 243
},
{
"epoch": 0.58,
"learning_rate": 1.7642028100183264e-05,
"loss": 0.8577,
"step": 244
},
{
"epoch": 0.58,
"learning_rate": 1.762981062919976e-05,
"loss": 0.9112,
"step": 245
},
{
"epoch": 0.58,
"learning_rate": 1.761759315821625e-05,
"loss": 0.9395,
"step": 246
},
{
"epoch": 0.58,
"learning_rate": 1.7605375687232746e-05,
"loss": 1.1198,
"step": 247
},
{
"epoch": 0.59,
"learning_rate": 1.7593158216249237e-05,
"loss": 1.4934,
"step": 248
},
{
"epoch": 0.59,
"learning_rate": 1.7580940745265732e-05,
"loss": 1.0408,
"step": 249
},
{
"epoch": 0.59,
"learning_rate": 1.7568723274282224e-05,
"loss": 0.9475,
"step": 250
},
{
"epoch": 0.59,
"learning_rate": 1.755650580329872e-05,
"loss": 1.1368,
"step": 251
},
{
"epoch": 0.6,
"learning_rate": 1.754428833231521e-05,
"loss": 0.9984,
"step": 252
},
{
"epoch": 0.6,
"learning_rate": 1.7532070861331706e-05,
"loss": 1.1552,
"step": 253
},
{
"epoch": 0.6,
"learning_rate": 1.75198533903482e-05,
"loss": 1.0785,
"step": 254
},
{
"epoch": 0.6,
"learning_rate": 1.7507635919364693e-05,
"loss": 0.8089,
"step": 255
},
{
"epoch": 0.61,
"learning_rate": 1.7495418448381188e-05,
"loss": 1.0439,
"step": 256
},
{
"epoch": 0.61,
"learning_rate": 1.748320097739768e-05,
"loss": 0.7603,
"step": 257
},
{
"epoch": 0.61,
"learning_rate": 1.7470983506414175e-05,
"loss": 0.8235,
"step": 258
},
{
"epoch": 0.61,
"learning_rate": 1.7458766035430666e-05,
"loss": 1.7352,
"step": 259
},
{
"epoch": 0.61,
"learning_rate": 1.744654856444716e-05,
"loss": 0.9731,
"step": 260
},
{
"epoch": 0.62,
"learning_rate": 1.7434331093463653e-05,
"loss": 0.8848,
"step": 261
},
{
"epoch": 0.62,
"learning_rate": 1.742211362248015e-05,
"loss": 0.8874,
"step": 262
},
{
"epoch": 0.62,
"learning_rate": 1.740989615149664e-05,
"loss": 1.0125,
"step": 263
},
{
"epoch": 0.62,
"learning_rate": 1.7397678680513135e-05,
"loss": 1.0552,
"step": 264
},
{
"epoch": 0.63,
"learning_rate": 1.7385461209529627e-05,
"loss": 0.9488,
"step": 265
},
{
"epoch": 0.63,
"learning_rate": 1.7373243738546122e-05,
"loss": 0.794,
"step": 266
},
{
"epoch": 0.63,
"learning_rate": 1.7361026267562614e-05,
"loss": 1.0277,
"step": 267
},
{
"epoch": 0.63,
"learning_rate": 1.734880879657911e-05,
"loss": 0.835,
"step": 268
},
{
"epoch": 0.64,
"learning_rate": 1.7336591325595604e-05,
"loss": 1.2321,
"step": 269
},
{
"epoch": 0.64,
"learning_rate": 1.73243738546121e-05,
"loss": 0.9804,
"step": 270
},
{
"epoch": 0.64,
"learning_rate": 1.731215638362859e-05,
"loss": 1.1228,
"step": 271
},
{
"epoch": 0.64,
"learning_rate": 1.7299938912645086e-05,
"loss": 1.1392,
"step": 272
},
{
"epoch": 0.65,
"learning_rate": 1.7287721441661577e-05,
"loss": 0.8711,
"step": 273
},
{
"epoch": 0.65,
"learning_rate": 1.7275503970678073e-05,
"loss": 0.9201,
"step": 274
},
{
"epoch": 0.65,
"learning_rate": 1.7263286499694564e-05,
"loss": 1.008,
"step": 275
},
{
"epoch": 0.65,
"learning_rate": 1.725106902871106e-05,
"loss": 1.0344,
"step": 276
},
{
"epoch": 0.65,
"learning_rate": 1.723885155772755e-05,
"loss": 0.9427,
"step": 277
},
{
"epoch": 0.66,
"learning_rate": 1.7226634086744046e-05,
"loss": 0.8963,
"step": 278
},
{
"epoch": 0.66,
"learning_rate": 1.7214416615760538e-05,
"loss": 1.3487,
"step": 279
},
{
"epoch": 0.66,
"learning_rate": 1.7202199144777033e-05,
"loss": 1.0002,
"step": 280
},
{
"epoch": 0.66,
"learning_rate": 1.7189981673793525e-05,
"loss": 0.961,
"step": 281
},
{
"epoch": 0.67,
"learning_rate": 1.717776420281002e-05,
"loss": 0.9015,
"step": 282
},
{
"epoch": 0.67,
"learning_rate": 1.716554673182651e-05,
"loss": 0.9172,
"step": 283
},
{
"epoch": 0.67,
"learning_rate": 1.7153329260843007e-05,
"loss": 0.9849,
"step": 284
},
{
"epoch": 0.67,
"learning_rate": 1.71411117898595e-05,
"loss": 0.9166,
"step": 285
},
{
"epoch": 0.68,
"learning_rate": 1.7128894318875993e-05,
"loss": 1.0685,
"step": 286
},
{
"epoch": 0.68,
"learning_rate": 1.711667684789249e-05,
"loss": 1.0196,
"step": 287
},
{
"epoch": 0.68,
"learning_rate": 1.710445937690898e-05,
"loss": 0.8409,
"step": 288
},
{
"epoch": 0.68,
"learning_rate": 1.7092241905925475e-05,
"loss": 0.9327,
"step": 289
},
{
"epoch": 0.69,
"learning_rate": 1.7080024434941967e-05,
"loss": 0.8675,
"step": 290
},
{
"epoch": 0.69,
"learning_rate": 1.7067806963958462e-05,
"loss": 1.1109,
"step": 291
},
{
"epoch": 0.69,
"learning_rate": 1.7055589492974954e-05,
"loss": 0.8427,
"step": 292
},
{
"epoch": 0.69,
"learning_rate": 1.704337202199145e-05,
"loss": 1.1322,
"step": 293
},
{
"epoch": 0.7,
"learning_rate": 1.7031154551007944e-05,
"loss": 0.9094,
"step": 294
},
{
"epoch": 0.7,
"learning_rate": 1.7018937080024436e-05,
"loss": 1.1168,
"step": 295
},
{
"epoch": 0.7,
"learning_rate": 1.700671960904093e-05,
"loss": 0.9982,
"step": 296
},
{
"epoch": 0.7,
"learning_rate": 1.6994502138057422e-05,
"loss": 0.7812,
"step": 297
},
{
"epoch": 0.7,
"learning_rate": 1.6982284667073918e-05,
"loss": 0.8858,
"step": 298
},
{
"epoch": 0.71,
"learning_rate": 1.6970067196090413e-05,
"loss": 0.9693,
"step": 299
},
{
"epoch": 0.71,
"learning_rate": 1.6957849725106904e-05,
"loss": 0.9097,
"step": 300
},
{
"epoch": 0.71,
"learning_rate": 1.69456322541234e-05,
"loss": 0.9178,
"step": 301
},
{
"epoch": 0.71,
"learning_rate": 1.693341478313989e-05,
"loss": 1.0581,
"step": 302
},
{
"epoch": 0.72,
"learning_rate": 1.6921197312156386e-05,
"loss": 1.1521,
"step": 303
},
{
"epoch": 0.72,
"learning_rate": 1.6908979841172878e-05,
"loss": 1.065,
"step": 304
},
{
"epoch": 0.72,
"learning_rate": 1.6896762370189373e-05,
"loss": 0.8954,
"step": 305
},
{
"epoch": 0.72,
"learning_rate": 1.6884544899205865e-05,
"loss": 0.7037,
"step": 306
},
{
"epoch": 0.73,
"learning_rate": 1.687232742822236e-05,
"loss": 0.9347,
"step": 307
},
{
"epoch": 0.73,
"learning_rate": 1.686010995723885e-05,
"loss": 0.9681,
"step": 308
},
{
"epoch": 0.73,
"learning_rate": 1.6847892486255347e-05,
"loss": 0.8554,
"step": 309
},
{
"epoch": 0.73,
"learning_rate": 1.683567501527184e-05,
"loss": 0.8793,
"step": 310
},
{
"epoch": 0.74,
"learning_rate": 1.6823457544288334e-05,
"loss": 0.8881,
"step": 311
},
{
"epoch": 0.74,
"learning_rate": 1.6811240073304825e-05,
"loss": 0.9284,
"step": 312
},
{
"epoch": 0.74,
"learning_rate": 1.679902260232132e-05,
"loss": 0.9632,
"step": 313
},
{
"epoch": 0.74,
"learning_rate": 1.6786805131337815e-05,
"loss": 1.0815,
"step": 314
},
{
"epoch": 0.74,
"learning_rate": 1.677458766035431e-05,
"loss": 0.9314,
"step": 315
},
{
"epoch": 0.75,
"learning_rate": 1.6762370189370802e-05,
"loss": 0.7965,
"step": 316
},
{
"epoch": 0.75,
"learning_rate": 1.6750152718387297e-05,
"loss": 0.8365,
"step": 317
},
{
"epoch": 0.75,
"learning_rate": 1.673793524740379e-05,
"loss": 1.2019,
"step": 318
},
{
"epoch": 0.75,
"learning_rate": 1.6725717776420284e-05,
"loss": 0.9525,
"step": 319
},
{
"epoch": 0.76,
"learning_rate": 1.6713500305436776e-05,
"loss": 0.7911,
"step": 320
},
{
"epoch": 0.76,
"learning_rate": 1.670128283445327e-05,
"loss": 0.9614,
"step": 321
},
{
"epoch": 0.76,
"learning_rate": 1.6689065363469763e-05,
"loss": 1.0212,
"step": 322
},
{
"epoch": 0.76,
"learning_rate": 1.6676847892486258e-05,
"loss": 1.128,
"step": 323
},
{
"epoch": 0.77,
"learning_rate": 1.666463042150275e-05,
"loss": 0.9668,
"step": 324
},
{
"epoch": 0.77,
"learning_rate": 1.6652412950519245e-05,
"loss": 0.9095,
"step": 325
},
{
"epoch": 0.77,
"learning_rate": 1.6640195479535736e-05,
"loss": 0.8985,
"step": 326
},
{
"epoch": 0.77,
"learning_rate": 1.662797800855223e-05,
"loss": 0.8876,
"step": 327
},
{
"epoch": 0.78,
"learning_rate": 1.6615760537568723e-05,
"loss": 0.9104,
"step": 328
},
{
"epoch": 0.78,
"learning_rate": 1.6603543066585218e-05,
"loss": 0.9719,
"step": 329
},
{
"epoch": 0.78,
"learning_rate": 1.6591325595601713e-05,
"loss": 1.2485,
"step": 330
},
{
"epoch": 0.78,
"learning_rate": 1.6579108124618205e-05,
"loss": 0.8247,
"step": 331
},
{
"epoch": 0.79,
"learning_rate": 1.65668906536347e-05,
"loss": 1.1209,
"step": 332
},
{
"epoch": 0.79,
"learning_rate": 1.6554673182651192e-05,
"loss": 1.0325,
"step": 333
},
{
"epoch": 0.79,
"learning_rate": 1.6542455711667687e-05,
"loss": 1.0139,
"step": 334
},
{
"epoch": 0.79,
"learning_rate": 1.653023824068418e-05,
"loss": 1.0233,
"step": 335
},
{
"epoch": 0.79,
"learning_rate": 1.6518020769700674e-05,
"loss": 0.8545,
"step": 336
},
{
"epoch": 0.8,
"learning_rate": 1.6505803298717165e-05,
"loss": 1.2186,
"step": 337
},
{
"epoch": 0.8,
"learning_rate": 1.649358582773366e-05,
"loss": 0.9952,
"step": 338
},
{
"epoch": 0.8,
"learning_rate": 1.6481368356750152e-05,
"loss": 1.2843,
"step": 339
},
{
"epoch": 0.8,
"learning_rate": 1.6469150885766647e-05,
"loss": 1.2914,
"step": 340
},
{
"epoch": 0.81,
"learning_rate": 1.645693341478314e-05,
"loss": 0.7621,
"step": 341
},
{
"epoch": 0.81,
"learning_rate": 1.6444715943799634e-05,
"loss": 1.0924,
"step": 342
},
{
"epoch": 0.81,
"learning_rate": 1.6432498472816126e-05,
"loss": 1.1418,
"step": 343
},
{
"epoch": 0.81,
"learning_rate": 1.6420281001832624e-05,
"loss": 0.9116,
"step": 344
},
{
"epoch": 0.82,
"learning_rate": 1.6408063530849116e-05,
"loss": 1.7392,
"step": 345
},
{
"epoch": 0.82,
"learning_rate": 1.639584605986561e-05,
"loss": 0.7273,
"step": 346
},
{
"epoch": 0.82,
"learning_rate": 1.6383628588882103e-05,
"loss": 0.9469,
"step": 347
},
{
"epoch": 0.82,
"learning_rate": 1.6371411117898598e-05,
"loss": 0.7986,
"step": 348
},
{
"epoch": 0.83,
"learning_rate": 1.635919364691509e-05,
"loss": 0.8359,
"step": 349
},
{
"epoch": 0.83,
"learning_rate": 1.6346976175931585e-05,
"loss": 0.7852,
"step": 350
},
{
"epoch": 0.83,
"learning_rate": 1.6334758704948076e-05,
"loss": 1.1206,
"step": 351
},
{
"epoch": 0.83,
"learning_rate": 1.632254123396457e-05,
"loss": 0.9291,
"step": 352
},
{
"epoch": 0.83,
"learning_rate": 1.6310323762981063e-05,
"loss": 1.0176,
"step": 353
},
{
"epoch": 0.84,
"learning_rate": 1.6298106291997558e-05,
"loss": 1.018,
"step": 354
},
{
"epoch": 0.84,
"learning_rate": 1.628588882101405e-05,
"loss": 0.7873,
"step": 355
},
{
"epoch": 0.84,
"learning_rate": 1.6273671350030545e-05,
"loss": 0.9801,
"step": 356
},
{
"epoch": 0.84,
"learning_rate": 1.6261453879047037e-05,
"loss": 0.752,
"step": 357
},
{
"epoch": 0.85,
"learning_rate": 1.6249236408063532e-05,
"loss": 0.8991,
"step": 358
},
{
"epoch": 0.85,
"learning_rate": 1.6237018937080027e-05,
"loss": 0.8771,
"step": 359
},
{
"epoch": 0.85,
"learning_rate": 1.622480146609652e-05,
"loss": 0.8734,
"step": 360
},
{
"epoch": 0.85,
"learning_rate": 1.6212583995113014e-05,
"loss": 0.9302,
"step": 361
},
{
"epoch": 0.86,
"learning_rate": 1.620036652412951e-05,
"loss": 0.9362,
"step": 362
},
{
"epoch": 0.86,
"learning_rate": 1.6188149053146e-05,
"loss": 0.9994,
"step": 363
},
{
"epoch": 0.86,
"learning_rate": 1.6175931582162496e-05,
"loss": 0.7499,
"step": 364
},
{
"epoch": 0.86,
"learning_rate": 1.6163714111178987e-05,
"loss": 1.7184,
"step": 365
},
{
"epoch": 0.87,
"learning_rate": 1.6151496640195482e-05,
"loss": 1.0205,
"step": 366
},
{
"epoch": 0.87,
"learning_rate": 1.6139279169211974e-05,
"loss": 0.8763,
"step": 367
},
{
"epoch": 0.87,
"learning_rate": 1.612706169822847e-05,
"loss": 1.0264,
"step": 368
},
{
"epoch": 0.87,
"learning_rate": 1.611484422724496e-05,
"loss": 0.9088,
"step": 369
},
{
"epoch": 0.87,
"learning_rate": 1.6102626756261456e-05,
"loss": 0.7762,
"step": 370
},
{
"epoch": 0.88,
"learning_rate": 1.6090409285277948e-05,
"loss": 0.876,
"step": 371
},
{
"epoch": 0.88,
"learning_rate": 1.6078191814294443e-05,
"loss": 1.0591,
"step": 372
},
{
"epoch": 0.88,
"learning_rate": 1.6065974343310935e-05,
"loss": 0.8602,
"step": 373
},
{
"epoch": 0.88,
"learning_rate": 1.605375687232743e-05,
"loss": 0.8489,
"step": 374
},
{
"epoch": 0.89,
"learning_rate": 1.6041539401343925e-05,
"loss": 0.9205,
"step": 375
},
{
"epoch": 0.89,
"learning_rate": 1.6029321930360416e-05,
"loss": 0.926,
"step": 376
},
{
"epoch": 0.89,
"learning_rate": 1.601710445937691e-05,
"loss": 0.8983,
"step": 377
},
{
"epoch": 0.89,
"learning_rate": 1.6004886988393403e-05,
"loss": 1.0779,
"step": 378
},
{
"epoch": 0.9,
"learning_rate": 1.59926695174099e-05,
"loss": 0.9446,
"step": 379
},
{
"epoch": 0.9,
"learning_rate": 1.598045204642639e-05,
"loss": 1.1564,
"step": 380
},
{
"epoch": 0.9,
"learning_rate": 1.5968234575442885e-05,
"loss": 1.0101,
"step": 381
},
{
"epoch": 0.9,
"learning_rate": 1.5956017104459377e-05,
"loss": 1.0597,
"step": 382
},
{
"epoch": 0.91,
"learning_rate": 1.5943799633475872e-05,
"loss": 0.9408,
"step": 383
},
{
"epoch": 0.91,
"learning_rate": 1.5931582162492364e-05,
"loss": 1.1833,
"step": 384
},
{
"epoch": 0.91,
"learning_rate": 1.591936469150886e-05,
"loss": 1.0106,
"step": 385
},
{
"epoch": 0.91,
"learning_rate": 1.590714722052535e-05,
"loss": 1.6698,
"step": 386
},
{
"epoch": 0.92,
"learning_rate": 1.5894929749541846e-05,
"loss": 1.0123,
"step": 387
},
{
"epoch": 0.92,
"learning_rate": 1.5882712278558337e-05,
"loss": 0.9237,
"step": 388
},
{
"epoch": 0.92,
"learning_rate": 1.5870494807574836e-05,
"loss": 0.9182,
"step": 389
},
{
"epoch": 0.92,
"learning_rate": 1.5858277336591327e-05,
"loss": 0.9832,
"step": 390
},
{
"epoch": 0.92,
"learning_rate": 1.5846059865607823e-05,
"loss": 0.7884,
"step": 391
},
{
"epoch": 0.93,
"learning_rate": 1.5833842394624314e-05,
"loss": 1.0028,
"step": 392
},
{
"epoch": 0.93,
"learning_rate": 1.582162492364081e-05,
"loss": 1.0835,
"step": 393
},
{
"epoch": 0.93,
"learning_rate": 1.58094074526573e-05,
"loss": 0.9394,
"step": 394
},
{
"epoch": 0.93,
"learning_rate": 1.5797189981673796e-05,
"loss": 1.25,
"step": 395
},
{
"epoch": 0.94,
"learning_rate": 1.5784972510690288e-05,
"loss": 1.0046,
"step": 396
},
{
"epoch": 0.94,
"learning_rate": 1.5772755039706783e-05,
"loss": 0.6862,
"step": 397
},
{
"epoch": 0.94,
"learning_rate": 1.5760537568723275e-05,
"loss": 0.9672,
"step": 398
},
{
"epoch": 0.94,
"learning_rate": 1.574832009773977e-05,
"loss": 0.847,
"step": 399
},
{
"epoch": 0.95,
"learning_rate": 1.573610262675626e-05,
"loss": 1.1316,
"step": 400
},
{
"epoch": 0.95,
"learning_rate": 1.5723885155772757e-05,
"loss": 1.1577,
"step": 401
},
{
"epoch": 0.95,
"learning_rate": 1.5711667684789248e-05,
"loss": 0.7909,
"step": 402
},
{
"epoch": 0.95,
"learning_rate": 1.5699450213805743e-05,
"loss": 0.9476,
"step": 403
},
{
"epoch": 0.96,
"learning_rate": 1.568723274282224e-05,
"loss": 0.8651,
"step": 404
},
{
"epoch": 0.96,
"learning_rate": 1.567501527183873e-05,
"loss": 0.8349,
"step": 405
},
{
"epoch": 0.96,
"learning_rate": 1.5662797800855225e-05,
"loss": 1.0023,
"step": 406
},
{
"epoch": 0.96,
"learning_rate": 1.5650580329871717e-05,
"loss": 0.9267,
"step": 407
},
{
"epoch": 0.96,
"learning_rate": 1.5638362858888212e-05,
"loss": 0.7568,
"step": 408
},
{
"epoch": 0.97,
"learning_rate": 1.5626145387904704e-05,
"loss": 0.9849,
"step": 409
},
{
"epoch": 0.97,
"learning_rate": 1.56139279169212e-05,
"loss": 0.8452,
"step": 410
},
{
"epoch": 0.97,
"learning_rate": 1.560171044593769e-05,
"loss": 0.9507,
"step": 411
},
{
"epoch": 0.97,
"learning_rate": 1.5589492974954186e-05,
"loss": 0.9459,
"step": 412
},
{
"epoch": 0.98,
"learning_rate": 1.557727550397068e-05,
"loss": 0.9053,
"step": 413
},
{
"epoch": 0.98,
"learning_rate": 1.5565058032987173e-05,
"loss": 1.0029,
"step": 414
},
{
"epoch": 0.98,
"learning_rate": 1.5552840562003668e-05,
"loss": 0.7987,
"step": 415
},
{
"epoch": 0.98,
"learning_rate": 1.554062309102016e-05,
"loss": 0.7423,
"step": 416
},
{
"epoch": 0.99,
"learning_rate": 1.5528405620036654e-05,
"loss": 1.0905,
"step": 417
},
{
"epoch": 0.99,
"learning_rate": 1.5516188149053146e-05,
"loss": 0.829,
"step": 418
},
{
"epoch": 0.99,
"learning_rate": 1.550397067806964e-05,
"loss": 0.698,
"step": 419
},
{
"epoch": 0.99,
"learning_rate": 1.5491753207086136e-05,
"loss": 0.8893,
"step": 420
},
{
"epoch": 1.0,
"learning_rate": 1.5479535736102628e-05,
"loss": 0.992,
"step": 421
},
{
"epoch": 1.0,
"learning_rate": 1.5467318265119123e-05,
"loss": 1.0658,
"step": 422
}
],
"logging_steps": 1.0,
"max_steps": 1688,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 2.030735869261906e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}