Xenon-1 / checkpoint-300 /trainer_state.json
gagan3012's picture
Upload folder using huggingface_hub
1673c6d verified
raw
history blame
37 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5706134094151213,
"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": 1.8229,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 4.9999950203346446e-05,
"loss": 1.8352,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 4.999980081358417e-05,
"loss": 1.742,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 4.999955183130829e-05,
"loss": 1.6315,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 4.999920325751068e-05,
"loss": 1.6204,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 4.999875509357998e-05,
"loss": 1.5485,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 4.999820734130155e-05,
"loss": 1.4713,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 4.999756000285748e-05,
"loss": 1.4675,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 4.9996813080826606e-05,
"loss": 1.5091,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 4.999596657818445e-05,
"loss": 1.4009,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 4.9995020498303275e-05,
"loss": 1.2992,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 4.999397484495198e-05,
"loss": 1.2111,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 4.99928296222962e-05,
"loss": 1.2281,
"step": 13
},
{
"epoch": 0.03,
"learning_rate": 4.999158483489818e-05,
"loss": 1.2099,
"step": 14
},
{
"epoch": 0.03,
"learning_rate": 4.99902404877168e-05,
"loss": 1.1259,
"step": 15
},
{
"epoch": 0.03,
"learning_rate": 4.998879658610761e-05,
"loss": 1.022,
"step": 16
},
{
"epoch": 0.03,
"learning_rate": 4.998725313582272e-05,
"loss": 1.1276,
"step": 17
},
{
"epoch": 0.03,
"learning_rate": 4.998561014301081e-05,
"loss": 1.1276,
"step": 18
},
{
"epoch": 0.04,
"learning_rate": 4.998386761421714e-05,
"loss": 1.2404,
"step": 19
},
{
"epoch": 0.04,
"learning_rate": 4.998202555638346e-05,
"loss": 1.1622,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 4.998008397684806e-05,
"loss": 1.1335,
"step": 21
},
{
"epoch": 0.04,
"learning_rate": 4.997804288334565e-05,
"loss": 1.2187,
"step": 22
},
{
"epoch": 0.04,
"learning_rate": 4.9975902284007405e-05,
"loss": 1.0678,
"step": 23
},
{
"epoch": 0.05,
"learning_rate": 4.997366218736091e-05,
"loss": 1.0195,
"step": 24
},
{
"epoch": 0.05,
"learning_rate": 4.99713226023301e-05,
"loss": 1.0138,
"step": 25
},
{
"epoch": 0.05,
"learning_rate": 4.9968883538235264e-05,
"loss": 1.0706,
"step": 26
},
{
"epoch": 0.05,
"learning_rate": 4.996634500479297e-05,
"loss": 0.9617,
"step": 27
},
{
"epoch": 0.05,
"learning_rate": 4.996370701211607e-05,
"loss": 1.034,
"step": 28
},
{
"epoch": 0.06,
"learning_rate": 4.996096957071361e-05,
"loss": 0.9952,
"step": 29
},
{
"epoch": 0.06,
"learning_rate": 4.9958132691490816e-05,
"loss": 0.9598,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 4.995519638574907e-05,
"loss": 1.0342,
"step": 31
},
{
"epoch": 0.06,
"learning_rate": 4.9952160665185825e-05,
"loss": 0.9147,
"step": 32
},
{
"epoch": 0.06,
"learning_rate": 4.994902554189458e-05,
"loss": 0.924,
"step": 33
},
{
"epoch": 0.06,
"learning_rate": 4.994579102836482e-05,
"loss": 0.9021,
"step": 34
},
{
"epoch": 0.07,
"learning_rate": 4.994245713748198e-05,
"loss": 1.0732,
"step": 35
},
{
"epoch": 0.07,
"learning_rate": 4.993902388252739e-05,
"loss": 0.926,
"step": 36
},
{
"epoch": 0.07,
"learning_rate": 4.9935491277178236e-05,
"loss": 0.9082,
"step": 37
},
{
"epoch": 0.07,
"learning_rate": 4.993185933550745e-05,
"loss": 0.8735,
"step": 38
},
{
"epoch": 0.07,
"learning_rate": 4.992812807198372e-05,
"loss": 1.0212,
"step": 39
},
{
"epoch": 0.08,
"learning_rate": 4.9924297501471414e-05,
"loss": 0.9495,
"step": 40
},
{
"epoch": 0.08,
"learning_rate": 4.9920367639230483e-05,
"loss": 0.9101,
"step": 41
},
{
"epoch": 0.08,
"learning_rate": 4.991633850091645e-05,
"loss": 1.0533,
"step": 42
},
{
"epoch": 0.08,
"learning_rate": 4.991221010258034e-05,
"loss": 0.8759,
"step": 43
},
{
"epoch": 0.08,
"learning_rate": 4.990798246066856e-05,
"loss": 0.969,
"step": 44
},
{
"epoch": 0.09,
"learning_rate": 4.9903655592022916e-05,
"loss": 0.8463,
"step": 45
},
{
"epoch": 0.09,
"learning_rate": 4.9899229513880494e-05,
"loss": 0.844,
"step": 46
},
{
"epoch": 0.09,
"learning_rate": 4.989470424387361e-05,
"loss": 0.8386,
"step": 47
},
{
"epoch": 0.09,
"learning_rate": 4.989007980002973e-05,
"loss": 0.93,
"step": 48
},
{
"epoch": 0.09,
"learning_rate": 4.988535620077138e-05,
"loss": 0.8551,
"step": 49
},
{
"epoch": 0.1,
"learning_rate": 4.988053346491613e-05,
"loss": 0.8633,
"step": 50
},
{
"epoch": 0.1,
"learning_rate": 4.987561161167648e-05,
"loss": 0.9056,
"step": 51
},
{
"epoch": 0.1,
"learning_rate": 4.9870590660659755e-05,
"loss": 0.9366,
"step": 52
},
{
"epoch": 0.1,
"learning_rate": 4.986547063186808e-05,
"loss": 1.0469,
"step": 53
},
{
"epoch": 0.1,
"learning_rate": 4.98602515456983e-05,
"loss": 0.8723,
"step": 54
},
{
"epoch": 0.1,
"learning_rate": 4.985493342294184e-05,
"loss": 0.9484,
"step": 55
},
{
"epoch": 0.11,
"learning_rate": 4.9849516284784676e-05,
"loss": 0.8346,
"step": 56
},
{
"epoch": 0.11,
"learning_rate": 4.984400015280724e-05,
"loss": 0.789,
"step": 57
},
{
"epoch": 0.11,
"learning_rate": 4.983838504898433e-05,
"loss": 0.8986,
"step": 58
},
{
"epoch": 0.11,
"learning_rate": 4.9832670995685006e-05,
"loss": 0.8799,
"step": 59
},
{
"epoch": 0.11,
"learning_rate": 4.9826858015672536e-05,
"loss": 0.9028,
"step": 60
},
{
"epoch": 0.12,
"learning_rate": 4.982094613210428e-05,
"loss": 0.8908,
"step": 61
},
{
"epoch": 0.12,
"learning_rate": 4.9814935368531586e-05,
"loss": 0.8273,
"step": 62
},
{
"epoch": 0.12,
"learning_rate": 4.980882574889973e-05,
"loss": 0.784,
"step": 63
},
{
"epoch": 0.12,
"learning_rate": 4.980261729754781e-05,
"loss": 0.9336,
"step": 64
},
{
"epoch": 0.12,
"learning_rate": 4.9796310039208623e-05,
"loss": 0.8943,
"step": 65
},
{
"epoch": 0.13,
"learning_rate": 4.978990399900861e-05,
"loss": 1.1,
"step": 66
},
{
"epoch": 0.13,
"learning_rate": 4.9783399202467714e-05,
"loss": 0.877,
"step": 67
},
{
"epoch": 0.13,
"learning_rate": 4.9776795675499296e-05,
"loss": 0.8291,
"step": 68
},
{
"epoch": 0.13,
"learning_rate": 4.9770093444410046e-05,
"loss": 0.7997,
"step": 69
},
{
"epoch": 0.13,
"learning_rate": 4.9763292535899866e-05,
"loss": 0.7911,
"step": 70
},
{
"epoch": 0.14,
"learning_rate": 4.9756392977061736e-05,
"loss": 0.8996,
"step": 71
},
{
"epoch": 0.14,
"learning_rate": 4.974939479538166e-05,
"loss": 0.8631,
"step": 72
},
{
"epoch": 0.14,
"learning_rate": 4.974229801873854e-05,
"loss": 0.8303,
"step": 73
},
{
"epoch": 0.14,
"learning_rate": 4.9735102675404004e-05,
"loss": 0.8708,
"step": 74
},
{
"epoch": 0.14,
"learning_rate": 4.972780879404239e-05,
"loss": 0.998,
"step": 75
},
{
"epoch": 0.14,
"learning_rate": 4.972041640371056e-05,
"loss": 1.1049,
"step": 76
},
{
"epoch": 0.15,
"learning_rate": 4.971292553385783e-05,
"loss": 0.774,
"step": 77
},
{
"epoch": 0.15,
"learning_rate": 4.970533621432581e-05,
"loss": 0.8142,
"step": 78
},
{
"epoch": 0.15,
"learning_rate": 4.969764847534832e-05,
"loss": 0.9968,
"step": 79
},
{
"epoch": 0.15,
"learning_rate": 4.9689862347551255e-05,
"loss": 0.9622,
"step": 80
},
{
"epoch": 0.15,
"learning_rate": 4.9681977861952464e-05,
"loss": 0.8342,
"step": 81
},
{
"epoch": 0.16,
"learning_rate": 4.967399504996162e-05,
"loss": 0.9,
"step": 82
},
{
"epoch": 0.16,
"learning_rate": 4.966591394338012e-05,
"loss": 0.8515,
"step": 83
},
{
"epoch": 0.16,
"learning_rate": 4.965773457440092e-05,
"loss": 0.7937,
"step": 84
},
{
"epoch": 0.16,
"learning_rate": 4.964945697560844e-05,
"loss": 0.9577,
"step": 85
},
{
"epoch": 0.16,
"learning_rate": 4.9641081179978424e-05,
"loss": 0.8233,
"step": 86
},
{
"epoch": 0.17,
"learning_rate": 4.963260722087779e-05,
"loss": 0.9769,
"step": 87
},
{
"epoch": 0.17,
"learning_rate": 4.9624035132064526e-05,
"loss": 0.8927,
"step": 88
},
{
"epoch": 0.17,
"learning_rate": 4.961536494768754e-05,
"loss": 0.9383,
"step": 89
},
{
"epoch": 0.17,
"learning_rate": 4.960659670228652e-05,
"loss": 0.9177,
"step": 90
},
{
"epoch": 0.17,
"learning_rate": 4.959773043079181e-05,
"loss": 0.8026,
"step": 91
},
{
"epoch": 0.17,
"learning_rate": 4.958876616852427e-05,
"loss": 0.9647,
"step": 92
},
{
"epoch": 0.18,
"learning_rate": 4.9579703951195113e-05,
"loss": 0.7545,
"step": 93
},
{
"epoch": 0.18,
"learning_rate": 4.957054381490579e-05,
"loss": 0.7836,
"step": 94
},
{
"epoch": 0.18,
"learning_rate": 4.9561285796147824e-05,
"loss": 0.8803,
"step": 95
},
{
"epoch": 0.18,
"learning_rate": 4.955192993180269e-05,
"loss": 0.8988,
"step": 96
},
{
"epoch": 0.18,
"learning_rate": 4.9542476259141656e-05,
"loss": 0.8418,
"step": 97
},
{
"epoch": 0.19,
"learning_rate": 4.953292481582561e-05,
"loss": 0.9004,
"step": 98
},
{
"epoch": 0.19,
"learning_rate": 4.9523275639904944e-05,
"loss": 0.9159,
"step": 99
},
{
"epoch": 0.19,
"learning_rate": 4.951352876981939e-05,
"loss": 0.7605,
"step": 100
},
{
"epoch": 0.19,
"eval_loss": 0.7751120924949646,
"eval_runtime": 2.7398,
"eval_samples_per_second": 3.285,
"eval_steps_per_second": 0.73,
"step": 100
},
{
"epoch": 0.19,
"learning_rate": 4.9503684244397894e-05,
"loss": 0.8228,
"step": 101
},
{
"epoch": 0.19,
"learning_rate": 4.949374210285838e-05,
"loss": 0.7176,
"step": 102
},
{
"epoch": 0.2,
"learning_rate": 4.948370238480769e-05,
"loss": 0.9403,
"step": 103
},
{
"epoch": 0.2,
"learning_rate": 4.9473565130241376e-05,
"loss": 0.7711,
"step": 104
},
{
"epoch": 0.2,
"learning_rate": 4.946333037954354e-05,
"loss": 0.8349,
"step": 105
},
{
"epoch": 0.2,
"learning_rate": 4.945299817348669e-05,
"loss": 0.7899,
"step": 106
},
{
"epoch": 0.2,
"learning_rate": 4.944256855323157e-05,
"loss": 0.913,
"step": 107
},
{
"epoch": 0.21,
"learning_rate": 4.9432041560326995e-05,
"loss": 0.9574,
"step": 108
},
{
"epoch": 0.21,
"learning_rate": 4.942141723670969e-05,
"loss": 0.8848,
"step": 109
},
{
"epoch": 0.21,
"learning_rate": 4.941069562470411e-05,
"loss": 0.9267,
"step": 110
},
{
"epoch": 0.21,
"learning_rate": 4.939987676702229e-05,
"loss": 0.7779,
"step": 111
},
{
"epoch": 0.21,
"learning_rate": 4.938896070676366e-05,
"loss": 0.9766,
"step": 112
},
{
"epoch": 0.21,
"learning_rate": 4.9377947487414886e-05,
"loss": 0.8737,
"step": 113
},
{
"epoch": 0.22,
"learning_rate": 4.936683715284968e-05,
"loss": 0.7962,
"step": 114
},
{
"epoch": 0.22,
"learning_rate": 4.935562974732865e-05,
"loss": 0.8711,
"step": 115
},
{
"epoch": 0.22,
"learning_rate": 4.934432531549909e-05,
"loss": 0.8212,
"step": 116
},
{
"epoch": 0.22,
"learning_rate": 4.933292390239483e-05,
"loss": 0.8364,
"step": 117
},
{
"epoch": 0.22,
"learning_rate": 4.9321425553436054e-05,
"loss": 0.8737,
"step": 118
},
{
"epoch": 0.23,
"learning_rate": 4.9309830314429095e-05,
"loss": 0.8382,
"step": 119
},
{
"epoch": 0.23,
"learning_rate": 4.92981382315663e-05,
"loss": 0.9143,
"step": 120
},
{
"epoch": 0.23,
"learning_rate": 4.9286349351425774e-05,
"loss": 0.9366,
"step": 121
},
{
"epoch": 0.23,
"learning_rate": 4.927446372097127e-05,
"loss": 0.7771,
"step": 122
},
{
"epoch": 0.23,
"learning_rate": 4.9262481387551976e-05,
"loss": 0.8218,
"step": 123
},
{
"epoch": 0.24,
"learning_rate": 4.925040239890227e-05,
"loss": 0.9309,
"step": 124
},
{
"epoch": 0.24,
"learning_rate": 4.923822680314162e-05,
"loss": 0.8345,
"step": 125
},
{
"epoch": 0.24,
"learning_rate": 4.922595464877435e-05,
"loss": 0.8479,
"step": 126
},
{
"epoch": 0.24,
"learning_rate": 4.921358598468942e-05,
"loss": 0.8879,
"step": 127
},
{
"epoch": 0.24,
"learning_rate": 4.920112086016029e-05,
"loss": 0.8235,
"step": 128
},
{
"epoch": 0.25,
"learning_rate": 4.918855932484468e-05,
"loss": 0.8693,
"step": 129
},
{
"epoch": 0.25,
"learning_rate": 4.917590142878437e-05,
"loss": 0.8928,
"step": 130
},
{
"epoch": 0.25,
"learning_rate": 4.916314722240504e-05,
"loss": 0.9152,
"step": 131
},
{
"epoch": 0.25,
"learning_rate": 4.915029675651604e-05,
"loss": 0.9386,
"step": 132
},
{
"epoch": 0.25,
"learning_rate": 4.913735008231016e-05,
"loss": 0.8565,
"step": 133
},
{
"epoch": 0.25,
"learning_rate": 4.9124307251363525e-05,
"loss": 0.8073,
"step": 134
},
{
"epoch": 0.26,
"learning_rate": 4.911116831563524e-05,
"loss": 0.8975,
"step": 135
},
{
"epoch": 0.26,
"learning_rate": 4.909793332746733e-05,
"loss": 0.7949,
"step": 136
},
{
"epoch": 0.26,
"learning_rate": 4.908460233958444e-05,
"loss": 0.8059,
"step": 137
},
{
"epoch": 0.26,
"learning_rate": 4.907117540509366e-05,
"loss": 0.8424,
"step": 138
},
{
"epoch": 0.26,
"learning_rate": 4.9057652577484293e-05,
"loss": 0.7911,
"step": 139
},
{
"epoch": 0.27,
"learning_rate": 4.9044033910627676e-05,
"loss": 0.858,
"step": 140
},
{
"epoch": 0.27,
"learning_rate": 4.9030319458776926e-05,
"loss": 0.977,
"step": 141
},
{
"epoch": 0.27,
"learning_rate": 4.9016509276566746e-05,
"loss": 0.8803,
"step": 142
},
{
"epoch": 0.27,
"learning_rate": 4.9002603419013205e-05,
"loss": 0.9155,
"step": 143
},
{
"epoch": 0.27,
"learning_rate": 4.8988601941513526e-05,
"loss": 0.6968,
"step": 144
},
{
"epoch": 0.28,
"learning_rate": 4.897450489984583e-05,
"loss": 0.8425,
"step": 145
},
{
"epoch": 0.28,
"learning_rate": 4.896031235016897e-05,
"loss": 0.9646,
"step": 146
},
{
"epoch": 0.28,
"learning_rate": 4.894602434902226e-05,
"loss": 0.8387,
"step": 147
},
{
"epoch": 0.28,
"learning_rate": 4.893164095332527e-05,
"loss": 0.9245,
"step": 148
},
{
"epoch": 0.28,
"learning_rate": 4.89171622203776e-05,
"loss": 0.861,
"step": 149
},
{
"epoch": 0.29,
"learning_rate": 4.890258820785865e-05,
"loss": 0.7925,
"step": 150
},
{
"epoch": 0.29,
"learning_rate": 4.8887918973827375e-05,
"loss": 0.8197,
"step": 151
},
{
"epoch": 0.29,
"learning_rate": 4.887315457672208e-05,
"loss": 0.8404,
"step": 152
},
{
"epoch": 0.29,
"learning_rate": 4.8858295075360175e-05,
"loss": 0.8094,
"step": 153
},
{
"epoch": 0.29,
"learning_rate": 4.884334052893793e-05,
"loss": 0.8282,
"step": 154
},
{
"epoch": 0.29,
"learning_rate": 4.882829099703026e-05,
"loss": 0.7838,
"step": 155
},
{
"epoch": 0.3,
"learning_rate": 4.881314653959046e-05,
"loss": 0.8562,
"step": 156
},
{
"epoch": 0.3,
"learning_rate": 4.8797907216950015e-05,
"loss": 0.818,
"step": 157
},
{
"epoch": 0.3,
"learning_rate": 4.878257308981827e-05,
"loss": 0.7874,
"step": 158
},
{
"epoch": 0.3,
"learning_rate": 4.8767144219282325e-05,
"loss": 0.9106,
"step": 159
},
{
"epoch": 0.3,
"learning_rate": 4.875162066680664e-05,
"loss": 0.9026,
"step": 160
},
{
"epoch": 0.31,
"learning_rate": 4.8736002494232904e-05,
"loss": 0.7882,
"step": 161
},
{
"epoch": 0.31,
"learning_rate": 4.872028976377974e-05,
"loss": 1.0285,
"step": 162
},
{
"epoch": 0.31,
"learning_rate": 4.870448253804244e-05,
"loss": 0.8034,
"step": 163
},
{
"epoch": 0.31,
"learning_rate": 4.868858087999279e-05,
"loss": 0.7977,
"step": 164
},
{
"epoch": 0.31,
"learning_rate": 4.86725848529787e-05,
"loss": 0.885,
"step": 165
},
{
"epoch": 0.32,
"learning_rate": 4.86564945207241e-05,
"loss": 0.804,
"step": 166
},
{
"epoch": 0.32,
"learning_rate": 4.864030994732852e-05,
"loss": 0.9618,
"step": 167
},
{
"epoch": 0.32,
"learning_rate": 4.862403119726702e-05,
"loss": 0.8042,
"step": 168
},
{
"epoch": 0.32,
"learning_rate": 4.860765833538974e-05,
"loss": 1.0271,
"step": 169
},
{
"epoch": 0.32,
"learning_rate": 4.85911914269218e-05,
"loss": 0.799,
"step": 170
},
{
"epoch": 0.33,
"learning_rate": 4.8574630537462954e-05,
"loss": 0.7454,
"step": 171
},
{
"epoch": 0.33,
"learning_rate": 4.855797573298734e-05,
"loss": 0.7428,
"step": 172
},
{
"epoch": 0.33,
"learning_rate": 4.8541227079843246e-05,
"loss": 0.9079,
"step": 173
},
{
"epoch": 0.33,
"learning_rate": 4.852438464475283e-05,
"loss": 0.7964,
"step": 174
},
{
"epoch": 0.33,
"learning_rate": 4.8507448494811834e-05,
"loss": 0.9262,
"step": 175
},
{
"epoch": 0.33,
"learning_rate": 4.849041869748935e-05,
"loss": 0.7817,
"step": 176
},
{
"epoch": 0.34,
"learning_rate": 4.847329532062753e-05,
"loss": 0.759,
"step": 177
},
{
"epoch": 0.34,
"learning_rate": 4.845607843244132e-05,
"loss": 0.9029,
"step": 178
},
{
"epoch": 0.34,
"learning_rate": 4.843876810151821e-05,
"loss": 0.7191,
"step": 179
},
{
"epoch": 0.34,
"learning_rate": 4.8421364396817905e-05,
"loss": 0.8861,
"step": 180
},
{
"epoch": 0.34,
"learning_rate": 4.840386738767211e-05,
"loss": 0.982,
"step": 181
},
{
"epoch": 0.35,
"learning_rate": 4.838627714378423e-05,
"loss": 0.8453,
"step": 182
},
{
"epoch": 0.35,
"learning_rate": 4.8368593735229074e-05,
"loss": 0.9402,
"step": 183
},
{
"epoch": 0.35,
"learning_rate": 4.8350817232452625e-05,
"loss": 0.7882,
"step": 184
},
{
"epoch": 0.35,
"learning_rate": 4.8332947706271706e-05,
"loss": 0.8458,
"step": 185
},
{
"epoch": 0.35,
"learning_rate": 4.831498522787372e-05,
"loss": 0.8955,
"step": 186
},
{
"epoch": 0.36,
"learning_rate": 4.829692986881638e-05,
"loss": 0.7777,
"step": 187
},
{
"epoch": 0.36,
"learning_rate": 4.8278781701027395e-05,
"loss": 0.7341,
"step": 188
},
{
"epoch": 0.36,
"learning_rate": 4.826054079680422e-05,
"loss": 0.8234,
"step": 189
},
{
"epoch": 0.36,
"learning_rate": 4.824220722881371e-05,
"loss": 0.7693,
"step": 190
},
{
"epoch": 0.36,
"learning_rate": 4.8223781070091914e-05,
"loss": 0.8162,
"step": 191
},
{
"epoch": 0.37,
"learning_rate": 4.8205262394043705e-05,
"loss": 0.8983,
"step": 192
},
{
"epoch": 0.37,
"learning_rate": 4.818665127444253e-05,
"loss": 0.9481,
"step": 193
},
{
"epoch": 0.37,
"learning_rate": 4.816794778543011e-05,
"loss": 0.9685,
"step": 194
},
{
"epoch": 0.37,
"learning_rate": 4.814915200151614e-05,
"loss": 0.9092,
"step": 195
},
{
"epoch": 0.37,
"learning_rate": 4.813026399757799e-05,
"loss": 0.7715,
"step": 196
},
{
"epoch": 0.37,
"learning_rate": 4.811128384886041e-05,
"loss": 0.8279,
"step": 197
},
{
"epoch": 0.38,
"learning_rate": 4.809221163097523e-05,
"loss": 0.7468,
"step": 198
},
{
"epoch": 0.38,
"learning_rate": 4.807304741990106e-05,
"loss": 0.7938,
"step": 199
},
{
"epoch": 0.38,
"learning_rate": 4.805379129198299e-05,
"loss": 0.9049,
"step": 200
},
{
"epoch": 0.38,
"eval_loss": 0.7435702681541443,
"eval_runtime": 2.8319,
"eval_samples_per_second": 3.178,
"eval_steps_per_second": 0.706,
"step": 200
},
{
"epoch": 0.38,
"learning_rate": 4.803444332393227e-05,
"loss": 0.8812,
"step": 201
},
{
"epoch": 0.38,
"learning_rate": 4.801500359282605e-05,
"loss": 0.84,
"step": 202
},
{
"epoch": 0.39,
"learning_rate": 4.7995472176106974e-05,
"loss": 0.8609,
"step": 203
},
{
"epoch": 0.39,
"learning_rate": 4.797584915158301e-05,
"loss": 0.8207,
"step": 204
},
{
"epoch": 0.39,
"learning_rate": 4.795613459742702e-05,
"loss": 0.7714,
"step": 205
},
{
"epoch": 0.39,
"learning_rate": 4.7936328592176516e-05,
"loss": 0.7537,
"step": 206
},
{
"epoch": 0.39,
"learning_rate": 4.7916431214733314e-05,
"loss": 0.8651,
"step": 207
},
{
"epoch": 0.4,
"learning_rate": 4.7896442544363246e-05,
"loss": 0.8055,
"step": 208
},
{
"epoch": 0.4,
"learning_rate": 4.787636266069582e-05,
"loss": 0.8936,
"step": 209
},
{
"epoch": 0.4,
"learning_rate": 4.785619164372391e-05,
"loss": 0.701,
"step": 210
},
{
"epoch": 0.4,
"learning_rate": 4.783592957380346e-05,
"loss": 0.7145,
"step": 211
},
{
"epoch": 0.4,
"learning_rate": 4.781557653165313e-05,
"loss": 0.896,
"step": 212
},
{
"epoch": 0.41,
"learning_rate": 4.779513259835399e-05,
"loss": 0.7178,
"step": 213
},
{
"epoch": 0.41,
"learning_rate": 4.777459785534918e-05,
"loss": 0.8032,
"step": 214
},
{
"epoch": 0.41,
"learning_rate": 4.7753972384443644e-05,
"loss": 0.8792,
"step": 215
},
{
"epoch": 0.41,
"learning_rate": 4.773325626780373e-05,
"loss": 0.7246,
"step": 216
},
{
"epoch": 0.41,
"learning_rate": 4.771244958795688e-05,
"loss": 0.8574,
"step": 217
},
{
"epoch": 0.41,
"learning_rate": 4.7691552427791365e-05,
"loss": 0.7291,
"step": 218
},
{
"epoch": 0.42,
"learning_rate": 4.7670564870555864e-05,
"loss": 0.8259,
"step": 219
},
{
"epoch": 0.42,
"learning_rate": 4.7649486999859185e-05,
"loss": 0.7818,
"step": 220
},
{
"epoch": 0.42,
"learning_rate": 4.762831889966992e-05,
"loss": 0.8693,
"step": 221
},
{
"epoch": 0.42,
"learning_rate": 4.760706065431612e-05,
"loss": 0.8281,
"step": 222
},
{
"epoch": 0.42,
"learning_rate": 4.758571234848494e-05,
"loss": 0.8359,
"step": 223
},
{
"epoch": 0.43,
"learning_rate": 4.7564274067222314e-05,
"loss": 0.8119,
"step": 224
},
{
"epoch": 0.43,
"learning_rate": 4.754274589593262e-05,
"loss": 0.8577,
"step": 225
},
{
"epoch": 0.43,
"learning_rate": 4.752112792037832e-05,
"loss": 0.7509,
"step": 226
},
{
"epoch": 0.43,
"learning_rate": 4.7499420226679646e-05,
"loss": 0.7648,
"step": 227
},
{
"epoch": 0.43,
"learning_rate": 4.747762290131424e-05,
"loss": 0.7964,
"step": 228
},
{
"epoch": 0.44,
"learning_rate": 4.7455736031116804e-05,
"loss": 0.8229,
"step": 229
},
{
"epoch": 0.44,
"learning_rate": 4.7433759703278785e-05,
"loss": 0.7705,
"step": 230
},
{
"epoch": 0.44,
"learning_rate": 4.741169400534797e-05,
"loss": 0.8954,
"step": 231
},
{
"epoch": 0.44,
"learning_rate": 4.7389539025228217e-05,
"loss": 0.8405,
"step": 232
},
{
"epoch": 0.44,
"learning_rate": 4.7367294851179e-05,
"loss": 0.7539,
"step": 233
},
{
"epoch": 0.45,
"learning_rate": 4.734496157181518e-05,
"loss": 0.7844,
"step": 234
},
{
"epoch": 0.45,
"learning_rate": 4.732253927610657e-05,
"loss": 0.7417,
"step": 235
},
{
"epoch": 0.45,
"learning_rate": 4.7300028053377564e-05,
"loss": 0.8239,
"step": 236
},
{
"epoch": 0.45,
"learning_rate": 4.7277427993306867e-05,
"loss": 0.7526,
"step": 237
},
{
"epoch": 0.45,
"learning_rate": 4.7254739185927066e-05,
"loss": 0.8431,
"step": 238
},
{
"epoch": 0.45,
"learning_rate": 4.7231961721624296e-05,
"loss": 0.737,
"step": 239
},
{
"epoch": 0.46,
"learning_rate": 4.720909569113787e-05,
"loss": 0.751,
"step": 240
},
{
"epoch": 0.46,
"learning_rate": 4.718614118555993e-05,
"loss": 0.8756,
"step": 241
},
{
"epoch": 0.46,
"learning_rate": 4.71630982963351e-05,
"loss": 0.7679,
"step": 242
},
{
"epoch": 0.46,
"learning_rate": 4.713996711526005e-05,
"loss": 0.7593,
"step": 243
},
{
"epoch": 0.46,
"learning_rate": 4.7116747734483245e-05,
"loss": 0.8194,
"step": 244
},
{
"epoch": 0.47,
"learning_rate": 4.7093440246504465e-05,
"loss": 0.9187,
"step": 245
},
{
"epoch": 0.47,
"learning_rate": 4.70700447441745e-05,
"loss": 0.7543,
"step": 246
},
{
"epoch": 0.47,
"learning_rate": 4.704656132069478e-05,
"loss": 0.6961,
"step": 247
},
{
"epoch": 0.47,
"learning_rate": 4.7022990069616973e-05,
"loss": 0.8313,
"step": 248
},
{
"epoch": 0.47,
"learning_rate": 4.699933108484262e-05,
"loss": 0.8524,
"step": 249
},
{
"epoch": 0.48,
"learning_rate": 4.69755844606228e-05,
"loss": 0.7614,
"step": 250
},
{
"epoch": 0.48,
"learning_rate": 4.695175029155771e-05,
"loss": 0.7678,
"step": 251
},
{
"epoch": 0.48,
"learning_rate": 4.692782867259627e-05,
"loss": 0.9097,
"step": 252
},
{
"epoch": 0.48,
"learning_rate": 4.690381969903583e-05,
"loss": 0.8819,
"step": 253
},
{
"epoch": 0.48,
"learning_rate": 4.6879723466521706e-05,
"loss": 0.883,
"step": 254
},
{
"epoch": 0.49,
"learning_rate": 4.685554007104684e-05,
"loss": 0.7365,
"step": 255
},
{
"epoch": 0.49,
"learning_rate": 4.683126960895141e-05,
"loss": 0.8576,
"step": 256
},
{
"epoch": 0.49,
"learning_rate": 4.680691217692242e-05,
"loss": 0.8227,
"step": 257
},
{
"epoch": 0.49,
"learning_rate": 4.678246787199338e-05,
"loss": 0.7949,
"step": 258
},
{
"epoch": 0.49,
"learning_rate": 4.6757936791543846e-05,
"loss": 0.8524,
"step": 259
},
{
"epoch": 0.49,
"learning_rate": 4.6733319033299075e-05,
"loss": 0.7235,
"step": 260
},
{
"epoch": 0.5,
"learning_rate": 4.670861469532963e-05,
"loss": 0.8348,
"step": 261
},
{
"epoch": 0.5,
"learning_rate": 4.668382387605098e-05,
"loss": 0.7539,
"step": 262
},
{
"epoch": 0.5,
"learning_rate": 4.665894667422311e-05,
"loss": 0.7968,
"step": 263
},
{
"epoch": 0.5,
"learning_rate": 4.663398318895013e-05,
"loss": 1.0207,
"step": 264
},
{
"epoch": 0.5,
"learning_rate": 4.660893351967988e-05,
"loss": 0.7758,
"step": 265
},
{
"epoch": 0.51,
"learning_rate": 4.658379776620354e-05,
"loss": 0.8379,
"step": 266
},
{
"epoch": 0.51,
"learning_rate": 4.6558576028655226e-05,
"loss": 0.8968,
"step": 267
},
{
"epoch": 0.51,
"learning_rate": 4.6533268407511586e-05,
"loss": 0.8639,
"step": 268
},
{
"epoch": 0.51,
"learning_rate": 4.650787500359141e-05,
"loss": 0.713,
"step": 269
},
{
"epoch": 0.51,
"learning_rate": 4.6482395918055197e-05,
"loss": 0.9117,
"step": 270
},
{
"epoch": 0.52,
"learning_rate": 4.6456831252404844e-05,
"loss": 0.7259,
"step": 271
},
{
"epoch": 0.52,
"learning_rate": 4.64311811084831e-05,
"loss": 0.7107,
"step": 272
},
{
"epoch": 0.52,
"learning_rate": 4.64054455884733e-05,
"loss": 0.8522,
"step": 273
},
{
"epoch": 0.52,
"learning_rate": 4.637962479489883e-05,
"loss": 0.764,
"step": 274
},
{
"epoch": 0.52,
"learning_rate": 4.635371883062286e-05,
"loss": 0.8385,
"step": 275
},
{
"epoch": 0.52,
"learning_rate": 4.6327727798847785e-05,
"loss": 0.9269,
"step": 276
},
{
"epoch": 0.53,
"learning_rate": 4.630165180311493e-05,
"loss": 0.7428,
"step": 277
},
{
"epoch": 0.53,
"learning_rate": 4.6275490947304084e-05,
"loss": 0.8363,
"step": 278
},
{
"epoch": 0.53,
"learning_rate": 4.6249245335633086e-05,
"loss": 0.8526,
"step": 279
},
{
"epoch": 0.53,
"learning_rate": 4.6222915072657424e-05,
"loss": 0.8759,
"step": 280
},
{
"epoch": 0.53,
"learning_rate": 4.6196500263269824e-05,
"loss": 0.7692,
"step": 281
},
{
"epoch": 0.54,
"learning_rate": 4.617000101269982e-05,
"loss": 0.8109,
"step": 282
},
{
"epoch": 0.54,
"learning_rate": 4.614341742651332e-05,
"loss": 0.6978,
"step": 283
},
{
"epoch": 0.54,
"learning_rate": 4.6116749610612214e-05,
"loss": 0.7617,
"step": 284
},
{
"epoch": 0.54,
"learning_rate": 4.6089997671233955e-05,
"loss": 0.8812,
"step": 285
},
{
"epoch": 0.54,
"learning_rate": 4.606316171495109e-05,
"loss": 0.7013,
"step": 286
},
{
"epoch": 0.55,
"learning_rate": 4.60362418486709e-05,
"loss": 0.8073,
"step": 287
},
{
"epoch": 0.55,
"learning_rate": 4.6009238179634916e-05,
"loss": 0.8615,
"step": 288
},
{
"epoch": 0.55,
"learning_rate": 4.598215081541853e-05,
"loss": 0.9124,
"step": 289
},
{
"epoch": 0.55,
"learning_rate": 4.595497986393055e-05,
"loss": 0.8016,
"step": 290
},
{
"epoch": 0.55,
"learning_rate": 4.592772543341276e-05,
"loss": 0.8414,
"step": 291
},
{
"epoch": 0.56,
"learning_rate": 4.590038763243953e-05,
"loss": 0.7662,
"step": 292
},
{
"epoch": 0.56,
"learning_rate": 4.587296656991734e-05,
"loss": 0.7667,
"step": 293
},
{
"epoch": 0.56,
"learning_rate": 4.584546235508436e-05,
"loss": 0.8404,
"step": 294
},
{
"epoch": 0.56,
"learning_rate": 4.581787509751001e-05,
"loss": 0.9285,
"step": 295
},
{
"epoch": 0.56,
"learning_rate": 4.5790204907094554e-05,
"loss": 0.863,
"step": 296
},
{
"epoch": 0.56,
"learning_rate": 4.5762451894068606e-05,
"loss": 0.941,
"step": 297
},
{
"epoch": 0.57,
"learning_rate": 4.573461616899275e-05,
"loss": 0.9033,
"step": 298
},
{
"epoch": 0.57,
"learning_rate": 4.570669784275706e-05,
"loss": 0.8648,
"step": 299
},
{
"epoch": 0.57,
"learning_rate": 4.567869702658067e-05,
"loss": 0.8397,
"step": 300
},
{
"epoch": 0.57,
"eval_loss": 0.7216992974281311,
"eval_runtime": 2.8122,
"eval_samples_per_second": 3.2,
"eval_steps_per_second": 0.711,
"step": 300
}
],
"logging_steps": 1,
"max_steps": 1575,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 100,
"total_flos": 4.218776992088064e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}