starcoder-gpteacher-code-instruct / trainer_state.json
blair-johnson's picture
Upload final checkpoint
4a9afd8
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.962962962962963,
"global_step": 210,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 2.8571428571428573e-06,
"loss": 0.669,
"step": 1
},
{
"epoch": 0.03,
"learning_rate": 5.7142857142857145e-06,
"loss": 0.7098,
"step": 2
},
{
"epoch": 0.04,
"learning_rate": 8.571428571428571e-06,
"loss": 0.6918,
"step": 3
},
{
"epoch": 0.06,
"learning_rate": 1.1428571428571429e-05,
"loss": 0.594,
"step": 4
},
{
"epoch": 0.07,
"learning_rate": 1.4285714285714287e-05,
"loss": 0.4154,
"step": 5
},
{
"epoch": 0.08,
"learning_rate": 1.7142857142857142e-05,
"loss": 0.3512,
"step": 6
},
{
"epoch": 0.1,
"learning_rate": 2e-05,
"loss": 0.312,
"step": 7
},
{
"epoch": 0.11,
"learning_rate": 1.9998802517966852e-05,
"loss": 0.301,
"step": 8
},
{
"epoch": 0.13,
"learning_rate": 1.9995210358660037e-05,
"loss": 0.3112,
"step": 9
},
{
"epoch": 0.14,
"learning_rate": 1.9989224382388813e-05,
"loss": 0.3663,
"step": 10
},
{
"epoch": 0.16,
"learning_rate": 1.9980846022772978e-05,
"loss": 0.3181,
"step": 11
},
{
"epoch": 0.17,
"learning_rate": 1.997007728639956e-05,
"loss": 0.3037,
"step": 12
},
{
"epoch": 0.18,
"learning_rate": 1.9956920752342226e-05,
"loss": 0.2854,
"step": 13
},
{
"epoch": 0.2,
"learning_rate": 1.9941379571543597e-05,
"loss": 0.2912,
"step": 14
},
{
"epoch": 0.21,
"learning_rate": 1.9923457466060637e-05,
"loss": 0.2688,
"step": 15
},
{
"epoch": 0.23,
"learning_rate": 1.9903158728173206e-05,
"loss": 0.2637,
"step": 16
},
{
"epoch": 0.24,
"learning_rate": 1.9880488219356086e-05,
"loss": 0.3311,
"step": 17
},
{
"epoch": 0.25,
"learning_rate": 1.9855451369114677e-05,
"loss": 0.2928,
"step": 18
},
{
"epoch": 0.27,
"learning_rate": 1.9828054173684646e-05,
"loss": 0.3183,
"step": 19
},
{
"epoch": 0.28,
"learning_rate": 1.9798303194595846e-05,
"loss": 0.2449,
"step": 20
},
{
"epoch": 0.3,
"learning_rate": 1.976620555710087e-05,
"loss": 0.2834,
"step": 21
},
{
"epoch": 0.31,
"learning_rate": 1.973176894846855e-05,
"loss": 0.2859,
"step": 22
},
{
"epoch": 0.32,
"learning_rate": 1.9695001616142916e-05,
"loss": 0.3496,
"step": 23
},
{
"epoch": 0.34,
"learning_rate": 1.965591236576794e-05,
"loss": 0.2741,
"step": 24
},
{
"epoch": 0.35,
"learning_rate": 1.9614510559078626e-05,
"loss": 0.2452,
"step": 25
},
{
"epoch": 0.37,
"learning_rate": 1.95708061116589e-05,
"loss": 0.2666,
"step": 26
},
{
"epoch": 0.38,
"learning_rate": 1.9524809490566878e-05,
"loss": 0.4307,
"step": 27
},
{
"epoch": 0.4,
"learning_rate": 1.9476531711828027e-05,
"loss": 0.2608,
"step": 28
},
{
"epoch": 0.41,
"learning_rate": 1.942598433779687e-05,
"loss": 0.3583,
"step": 29
},
{
"epoch": 0.42,
"learning_rate": 1.9373179474387858e-05,
"loss": 0.2916,
"step": 30
},
{
"epoch": 0.44,
"learning_rate": 1.9318129768176033e-05,
"loss": 0.29,
"step": 31
},
{
"epoch": 0.45,
"learning_rate": 1.926084840336821e-05,
"loss": 0.2483,
"step": 32
},
{
"epoch": 0.47,
"learning_rate": 1.9201349098645433e-05,
"loss": 0.2804,
"step": 33
},
{
"epoch": 0.48,
"learning_rate": 1.9139646103877378e-05,
"loss": 0.2559,
"step": 34
},
{
"epoch": 0.49,
"learning_rate": 1.9075754196709574e-05,
"loss": 0.3271,
"step": 35
},
{
"epoch": 0.51,
"learning_rate": 1.900968867902419e-05,
"loss": 0.264,
"step": 36
},
{
"epoch": 0.52,
"learning_rate": 1.894146537327533e-05,
"loss": 0.2554,
"step": 37
},
{
"epoch": 0.54,
"learning_rate": 1.8871100618699553e-05,
"loss": 0.2778,
"step": 38
},
{
"epoch": 0.55,
"learning_rate": 1.8798611267402745e-05,
"loss": 0.2578,
"step": 39
},
{
"epoch": 0.56,
"learning_rate": 1.872401468032406e-05,
"loss": 0.3066,
"step": 40
},
{
"epoch": 0.58,
"learning_rate": 1.864732872307804e-05,
"loss": 0.2532,
"step": 41
},
{
"epoch": 0.59,
"learning_rate": 1.8568571761675893e-05,
"loss": 0.3256,
"step": 42
},
{
"epoch": 0.61,
"learning_rate": 1.8487762658126872e-05,
"loss": 0.2798,
"step": 43
},
{
"epoch": 0.62,
"learning_rate": 1.8404920765920898e-05,
"loss": 0.2489,
"step": 44
},
{
"epoch": 0.63,
"learning_rate": 1.8320065925393468e-05,
"loss": 0.286,
"step": 45
},
{
"epoch": 0.65,
"learning_rate": 1.8233218458973984e-05,
"loss": 0.265,
"step": 46
},
{
"epoch": 0.66,
"learning_rate": 1.814439916631857e-05,
"loss": 0.2951,
"step": 47
},
{
"epoch": 0.68,
"learning_rate": 1.8053629319328662e-05,
"loss": 0.2865,
"step": 48
},
{
"epoch": 0.69,
"learning_rate": 1.796093065705644e-05,
"loss": 0.2891,
"step": 49
},
{
"epoch": 0.71,
"learning_rate": 1.786632538049842e-05,
"loss": 0.2097,
"step": 50
},
{
"epoch": 0.72,
"learning_rate": 1.776983614727838e-05,
"loss": 0.2211,
"step": 51
},
{
"epoch": 0.73,
"learning_rate": 1.7671486066220965e-05,
"loss": 0.2198,
"step": 52
},
{
"epoch": 0.75,
"learning_rate": 1.757129869181718e-05,
"loss": 0.1979,
"step": 53
},
{
"epoch": 0.76,
"learning_rate": 1.746929801858317e-05,
"loss": 0.237,
"step": 54
},
{
"epoch": 0.78,
"learning_rate": 1.736550847531366e-05,
"loss": 0.3031,
"step": 55
},
{
"epoch": 0.79,
"learning_rate": 1.725995491923131e-05,
"loss": 0.2582,
"step": 56
},
{
"epoch": 0.8,
"learning_rate": 1.7152662630033506e-05,
"loss": 0.3,
"step": 57
},
{
"epoch": 0.82,
"learning_rate": 1.7043657303837965e-05,
"loss": 0.2455,
"step": 58
},
{
"epoch": 0.83,
"learning_rate": 1.693296504702862e-05,
"loss": 0.2715,
"step": 59
},
{
"epoch": 0.85,
"learning_rate": 1.682061237000322e-05,
"loss": 0.2782,
"step": 60
},
{
"epoch": 0.86,
"learning_rate": 1.6706626180824185e-05,
"loss": 0.2388,
"step": 61
},
{
"epoch": 0.87,
"learning_rate": 1.659103377877423e-05,
"loss": 0.242,
"step": 62
},
{
"epoch": 0.89,
"learning_rate": 1.647386284781828e-05,
"loss": 0.2191,
"step": 63
},
{
"epoch": 0.9,
"learning_rate": 1.6355141449973254e-05,
"loss": 0.3089,
"step": 64
},
{
"epoch": 0.92,
"learning_rate": 1.6234898018587336e-05,
"loss": 0.2384,
"step": 65
},
{
"epoch": 0.93,
"learning_rate": 1.611316135153026e-05,
"loss": 0.2447,
"step": 66
},
{
"epoch": 0.95,
"learning_rate": 1.598996060429634e-05,
"loss": 0.2376,
"step": 67
},
{
"epoch": 0.96,
"learning_rate": 1.586532528302183e-05,
"loss": 0.3756,
"step": 68
},
{
"epoch": 0.97,
"learning_rate": 1.5739285237418323e-05,
"loss": 0.2197,
"step": 69
},
{
"epoch": 0.99,
"learning_rate": 1.5611870653623826e-05,
"loss": 0.2428,
"step": 70
},
{
"epoch": 1.0,
"learning_rate": 1.548311204697331e-05,
"loss": 0.2383,
"step": 71
},
{
"epoch": 1.02,
"learning_rate": 1.5353040254690396e-05,
"loss": 0.1859,
"step": 72
},
{
"epoch": 1.03,
"learning_rate": 1.5221686428501929e-05,
"loss": 0.1586,
"step": 73
},
{
"epoch": 1.04,
"learning_rate": 1.5089082027177291e-05,
"loss": 0.1806,
"step": 74
},
{
"epoch": 1.06,
"learning_rate": 1.4955258808994096e-05,
"loss": 0.1709,
"step": 75
},
{
"epoch": 1.07,
"learning_rate": 1.4820248824132221e-05,
"loss": 0.1573,
"step": 76
},
{
"epoch": 1.09,
"learning_rate": 1.4684084406997903e-05,
"loss": 0.1553,
"step": 77
},
{
"epoch": 1.1,
"learning_rate": 1.4546798168479756e-05,
"loss": 0.1542,
"step": 78
},
{
"epoch": 1.11,
"learning_rate": 1.4408422988138585e-05,
"loss": 0.1641,
"step": 79
},
{
"epoch": 1.13,
"learning_rate": 1.4268992006332847e-05,
"loss": 0.1716,
"step": 80
},
{
"epoch": 1.14,
"learning_rate": 1.412853861628166e-05,
"loss": 0.155,
"step": 81
},
{
"epoch": 1.16,
"learning_rate": 1.3987096456067236e-05,
"loss": 0.1666,
"step": 82
},
{
"epoch": 1.17,
"learning_rate": 1.3844699400578696e-05,
"loss": 0.1607,
"step": 83
},
{
"epoch": 1.19,
"learning_rate": 1.3701381553399147e-05,
"loss": 0.1191,
"step": 84
},
{
"epoch": 1.2,
"learning_rate": 1.3557177238637987e-05,
"loss": 0.1316,
"step": 85
},
{
"epoch": 1.21,
"learning_rate": 1.3412120992710425e-05,
"loss": 0.1672,
"step": 86
},
{
"epoch": 1.23,
"learning_rate": 1.3266247556066122e-05,
"loss": 0.1196,
"step": 87
},
{
"epoch": 1.24,
"learning_rate": 1.3119591864868979e-05,
"loss": 0.1144,
"step": 88
},
{
"epoch": 1.26,
"learning_rate": 1.2972189042630044e-05,
"loss": 0.1339,
"step": 89
},
{
"epoch": 1.27,
"learning_rate": 1.2824074391795571e-05,
"loss": 0.1532,
"step": 90
},
{
"epoch": 1.28,
"learning_rate": 1.2675283385292212e-05,
"loss": 0.1361,
"step": 91
},
{
"epoch": 1.3,
"learning_rate": 1.252585165803135e-05,
"loss": 0.1211,
"step": 92
},
{
"epoch": 1.31,
"learning_rate": 1.2375814998374714e-05,
"loss": 0.1377,
"step": 93
},
{
"epoch": 1.33,
"learning_rate": 1.2225209339563144e-05,
"loss": 0.1587,
"step": 94
},
{
"epoch": 1.34,
"learning_rate": 1.2074070751110752e-05,
"loss": 0.112,
"step": 95
},
{
"epoch": 1.35,
"learning_rate": 1.192243543016637e-05,
"loss": 0.1315,
"step": 96
},
{
"epoch": 1.37,
"learning_rate": 1.1770339692844484e-05,
"loss": 0.13,
"step": 97
},
{
"epoch": 1.38,
"learning_rate": 1.161781996552765e-05,
"loss": 0.1338,
"step": 98
},
{
"epoch": 1.4,
"learning_rate": 1.1464912776142494e-05,
"loss": 0.1408,
"step": 99
},
{
"epoch": 1.41,
"learning_rate": 1.1311654745411424e-05,
"loss": 0.1577,
"step": 100
},
{
"epoch": 1.43,
"learning_rate": 1.115808257808209e-05,
"loss": 0.188,
"step": 101
},
{
"epoch": 1.44,
"learning_rate": 1.1004233054136726e-05,
"loss": 0.159,
"step": 102
},
{
"epoch": 1.45,
"learning_rate": 1.0850143019983475e-05,
"loss": 0.1519,
"step": 103
},
{
"epoch": 1.47,
"learning_rate": 1.0695849379631813e-05,
"loss": 0.1161,
"step": 104
},
{
"epoch": 1.48,
"learning_rate": 1.0541389085854177e-05,
"loss": 0.151,
"step": 105
},
{
"epoch": 1.5,
"learning_rate": 1.038679913133589e-05,
"loss": 0.1445,
"step": 106
},
{
"epoch": 1.51,
"learning_rate": 1.0232116539815558e-05,
"loss": 0.1212,
"step": 107
},
{
"epoch": 1.52,
"learning_rate": 1.0077378357218022e-05,
"loss": 0.119,
"step": 108
},
{
"epoch": 1.54,
"learning_rate": 9.92262164278198e-06,
"loss": 0.1701,
"step": 109
},
{
"epoch": 1.55,
"learning_rate": 9.767883460184444e-06,
"loss": 0.1408,
"step": 110
},
{
"epoch": 1.57,
"learning_rate": 9.613200868664112e-06,
"loss": 0.154,
"step": 111
},
{
"epoch": 1.58,
"learning_rate": 9.458610914145826e-06,
"loss": 0.1452,
"step": 112
},
{
"epoch": 1.59,
"learning_rate": 9.304150620368189e-06,
"loss": 0.1496,
"step": 113
},
{
"epoch": 1.61,
"learning_rate": 9.149856980016529e-06,
"loss": 0.1476,
"step": 114
},
{
"epoch": 1.62,
"learning_rate": 8.995766945863278e-06,
"loss": 0.1381,
"step": 115
},
{
"epoch": 1.64,
"learning_rate": 8.841917421917913e-06,
"loss": 0.1923,
"step": 116
},
{
"epoch": 1.65,
"learning_rate": 8.688345254588579e-06,
"loss": 0.1439,
"step": 117
},
{
"epoch": 1.66,
"learning_rate": 8.53508722385751e-06,
"loss": 0.1434,
"step": 118
},
{
"epoch": 1.68,
"learning_rate": 8.382180034472353e-06,
"loss": 0.146,
"step": 119
},
{
"epoch": 1.69,
"learning_rate": 8.229660307155518e-06,
"loss": 0.1701,
"step": 120
},
{
"epoch": 1.71,
"learning_rate": 8.077564569833633e-06,
"loss": 0.1644,
"step": 121
},
{
"epoch": 1.72,
"learning_rate": 7.92592924888925e-06,
"loss": 0.1434,
"step": 122
},
{
"epoch": 1.74,
"learning_rate": 7.774790660436857e-06,
"loss": 0.1168,
"step": 123
},
{
"epoch": 1.75,
"learning_rate": 7.6241850016252915e-06,
"loss": 0.129,
"step": 124
},
{
"epoch": 1.76,
"learning_rate": 7.4741483419686525e-06,
"loss": 0.1464,
"step": 125
},
{
"epoch": 1.78,
"learning_rate": 7.324716614707794e-06,
"loss": 0.1555,
"step": 126
},
{
"epoch": 1.79,
"learning_rate": 7.175925608204428e-06,
"loss": 0.1389,
"step": 127
},
{
"epoch": 1.81,
"learning_rate": 7.0278109573699574e-06,
"loss": 0.1436,
"step": 128
},
{
"epoch": 1.82,
"learning_rate": 6.880408135131022e-06,
"loss": 0.1447,
"step": 129
},
{
"epoch": 1.83,
"learning_rate": 6.733752443933879e-06,
"loss": 0.1796,
"step": 130
},
{
"epoch": 1.85,
"learning_rate": 6.587879007289576e-06,
"loss": 0.1306,
"step": 131
},
{
"epoch": 1.86,
"learning_rate": 6.442822761362015e-06,
"loss": 0.1554,
"step": 132
},
{
"epoch": 1.88,
"learning_rate": 6.298618446600856e-06,
"loss": 0.1344,
"step": 133
},
{
"epoch": 1.89,
"learning_rate": 6.155300599421305e-06,
"loss": 0.1345,
"step": 134
},
{
"epoch": 1.9,
"learning_rate": 6.0129035439327665e-06,
"loss": 0.1351,
"step": 135
},
{
"epoch": 1.92,
"learning_rate": 5.871461383718344e-06,
"loss": 0.1344,
"step": 136
},
{
"epoch": 1.93,
"learning_rate": 5.731007993667155e-06,
"loss": 0.1493,
"step": 137
},
{
"epoch": 1.95,
"learning_rate": 5.5915770118614195e-06,
"loss": 0.1505,
"step": 138
},
{
"epoch": 1.96,
"learning_rate": 5.453201831520245e-06,
"loss": 0.1524,
"step": 139
},
{
"epoch": 1.98,
"learning_rate": 5.3159155930021e-06,
"loss": 0.1473,
"step": 140
},
{
"epoch": 1.99,
"learning_rate": 5.179751175867784e-06,
"loss": 0.1477,
"step": 141
},
{
"epoch": 2.0,
"learning_rate": 5.044741191005908e-06,
"loss": 0.1246,
"step": 142
},
{
"epoch": 2.02,
"learning_rate": 4.910917972822713e-06,
"loss": 0.0945,
"step": 143
},
{
"epoch": 2.03,
"learning_rate": 4.778313571498075e-06,
"loss": 0.0797,
"step": 144
},
{
"epoch": 2.05,
"learning_rate": 4.64695974530961e-06,
"loss": 0.0814,
"step": 145
},
{
"epoch": 2.06,
"learning_rate": 4.5168879530266906e-06,
"loss": 0.0963,
"step": 146
},
{
"epoch": 2.07,
"learning_rate": 4.388129346376177e-06,
"loss": 0.0914,
"step": 147
},
{
"epoch": 2.09,
"learning_rate": 4.260714762581677e-06,
"loss": 0.0904,
"step": 148
},
{
"epoch": 2.1,
"learning_rate": 4.1346747169781695e-06,
"loss": 0.0961,
"step": 149
},
{
"epoch": 2.12,
"learning_rate": 4.010039395703665e-06,
"loss": 0.0813,
"step": 150
},
{
"epoch": 2.13,
"learning_rate": 3.886838648469742e-06,
"loss": 0.0762,
"step": 151
},
{
"epoch": 2.14,
"learning_rate": 3.7651019814126656e-06,
"loss": 0.0838,
"step": 152
},
{
"epoch": 2.16,
"learning_rate": 3.6448585500267487e-06,
"loss": 0.0662,
"step": 153
},
{
"epoch": 2.17,
"learning_rate": 3.5261371521817247e-06,
"loss": 0.085,
"step": 154
},
{
"epoch": 2.19,
"learning_rate": 3.4089662212257733e-06,
"loss": 0.0691,
"step": 155
},
{
"epoch": 2.2,
"learning_rate": 3.2933738191758158e-06,
"loss": 0.0852,
"step": 156
},
{
"epoch": 2.22,
"learning_rate": 3.179387629996782e-06,
"loss": 0.0788,
"step": 157
},
{
"epoch": 2.23,
"learning_rate": 3.067034952971382e-06,
"loss": 0.0889,
"step": 158
},
{
"epoch": 2.24,
"learning_rate": 2.956342696162037e-06,
"loss": 0.0766,
"step": 159
},
{
"epoch": 2.26,
"learning_rate": 2.8473373699664995e-06,
"loss": 0.0733,
"step": 160
},
{
"epoch": 2.27,
"learning_rate": 2.740045080768694e-06,
"loss": 0.0868,
"step": 161
},
{
"epoch": 2.29,
"learning_rate": 2.634491524686341e-06,
"loss": 0.08,
"step": 162
},
{
"epoch": 2.3,
"learning_rate": 2.5307019814168343e-06,
"loss": 0.0727,
"step": 163
},
{
"epoch": 2.31,
"learning_rate": 2.428701308182826e-06,
"loss": 0.0879,
"step": 164
},
{
"epoch": 2.33,
"learning_rate": 2.3285139337790343e-06,
"loss": 0.084,
"step": 165
},
{
"epoch": 2.34,
"learning_rate": 2.2301638527216196e-06,
"loss": 0.0841,
"step": 166
},
{
"epoch": 2.36,
"learning_rate": 2.1336746195015845e-06,
"loss": 0.0699,
"step": 167
},
{
"epoch": 2.37,
"learning_rate": 2.0390693429435626e-06,
"loss": 0.0872,
"step": 168
},
{
"epoch": 2.38,
"learning_rate": 1.946370680671341e-06,
"loss": 0.0872,
"step": 169
},
{
"epoch": 2.4,
"learning_rate": 1.8556008336814302e-06,
"loss": 0.09,
"step": 170
},
{
"epoch": 2.41,
"learning_rate": 1.7667815410260181e-06,
"loss": 0.0815,
"step": 171
},
{
"epoch": 2.43,
"learning_rate": 1.679934074606533e-06,
"loss": 0.0725,
"step": 172
},
{
"epoch": 2.44,
"learning_rate": 1.5950792340791044e-06,
"loss": 0.0718,
"step": 173
},
{
"epoch": 2.46,
"learning_rate": 1.5122373418731306e-06,
"loss": 0.0749,
"step": 174
},
{
"epoch": 2.47,
"learning_rate": 1.4314282383241097e-06,
"loss": 0.0785,
"step": 175
},
{
"epoch": 2.48,
"learning_rate": 1.3526712769219619e-06,
"loss": 0.0824,
"step": 176
},
{
"epoch": 2.5,
"learning_rate": 1.2759853196759454e-06,
"loss": 0.0736,
"step": 177
},
{
"epoch": 2.51,
"learning_rate": 1.201388732597255e-06,
"loss": 0.0784,
"step": 178
},
{
"epoch": 2.53,
"learning_rate": 1.1288993813004467e-06,
"loss": 0.0737,
"step": 179
},
{
"epoch": 2.54,
"learning_rate": 1.0585346267246743e-06,
"loss": 0.0739,
"step": 180
},
{
"epoch": 2.55,
"learning_rate": 9.903113209758098e-07,
"loss": 0.0768,
"step": 181
},
{
"epoch": 2.57,
"learning_rate": 9.242458032904311e-07,
"loss": 0.0691,
"step": 182
},
{
"epoch": 2.58,
"learning_rate": 8.603538961226233e-07,
"loss": 0.0923,
"step": 183
},
{
"epoch": 2.6,
"learning_rate": 7.986509013545673e-07,
"loss": 0.0729,
"step": 184
},
{
"epoch": 2.61,
"learning_rate": 7.391515966317908e-07,
"loss": 0.0889,
"step": 185
},
{
"epoch": 2.62,
"learning_rate": 6.81870231823969e-07,
"loss": 0.0793,
"step": 186
},
{
"epoch": 2.64,
"learning_rate": 6.268205256121396e-07,
"loss": 0.0743,
"step": 187
},
{
"epoch": 2.65,
"learning_rate": 5.740156622031301e-07,
"loss": 0.0906,
"step": 188
},
{
"epoch": 2.67,
"learning_rate": 5.234682881719766e-07,
"loss": 0.0911,
"step": 189
},
{
"epoch": 2.68,
"learning_rate": 4.7519050943312326e-07,
"loss": 0.0798,
"step": 190
},
{
"epoch": 2.69,
"learning_rate": 4.2919388834110066e-07,
"loss": 0.0758,
"step": 191
},
{
"epoch": 2.71,
"learning_rate": 3.854894409213761e-07,
"loss": 0.1325,
"step": 192
},
{
"epoch": 2.72,
"learning_rate": 3.4408763423206093e-07,
"loss": 0.0739,
"step": 193
},
{
"epoch": 2.74,
"learning_rate": 3.049983838570858e-07,
"loss": 0.0721,
"step": 194
},
{
"epoch": 2.75,
"learning_rate": 2.6823105153145125e-07,
"loss": 0.0763,
"step": 195
},
{
"epoch": 2.77,
"learning_rate": 2.3379444289913344e-07,
"loss": 0.067,
"step": 196
},
{
"epoch": 2.78,
"learning_rate": 2.016968054041546e-07,
"loss": 0.0793,
"step": 197
},
{
"epoch": 2.79,
"learning_rate": 1.7194582631535616e-07,
"loss": 0.0841,
"step": 198
},
{
"epoch": 2.81,
"learning_rate": 1.4454863088532388e-07,
"loss": 0.0743,
"step": 199
},
{
"epoch": 2.82,
"learning_rate": 1.19511780643915e-07,
"loss": 0.069,
"step": 200
},
{
"epoch": 2.84,
"learning_rate": 9.684127182679526e-08,
"loss": 0.07,
"step": 201
},
{
"epoch": 2.85,
"learning_rate": 7.65425339393644e-08,
"loss": 0.0662,
"step": 202
},
{
"epoch": 2.86,
"learning_rate": 5.862042845640403e-08,
"loss": 0.0736,
"step": 203
},
{
"epoch": 2.88,
"learning_rate": 4.307924765777682e-08,
"loss": 0.0768,
"step": 204
},
{
"epoch": 2.89,
"learning_rate": 2.992271360043986e-08,
"loss": 0.0752,
"step": 205
},
{
"epoch": 2.91,
"learning_rate": 1.9153977227022168e-08,
"loss": 0.0587,
"step": 206
},
{
"epoch": 2.92,
"learning_rate": 1.0775617611189504e-08,
"loss": 0.078,
"step": 207
},
{
"epoch": 2.93,
"learning_rate": 4.7896413399639575e-09,
"loss": 0.0812,
"step": 208
},
{
"epoch": 2.95,
"learning_rate": 1.1974820331517313e-09,
"loss": 0.0895,
"step": 209
},
{
"epoch": 2.96,
"learning_rate": 0.0,
"loss": 0.0794,
"step": 210
},
{
"epoch": 2.96,
"step": 210,
"total_flos": 2.460909336054989e+16,
"train_loss": 0.17814085531447615,
"train_runtime": 18631.8164,
"train_samples_per_second": 0.73,
"train_steps_per_second": 0.011
}
],
"max_steps": 210,
"num_train_epochs": 3,
"total_flos": 2.460909336054989e+16,
"trial_name": null,
"trial_params": null
}