mistral-7b-lamia-v0.2 / trainer_state.json
basiliskinstitute's picture
Upload 8 files
4a48d0d verified
raw
history blame contribute delete
No virus
50.6 kB
{
"best_metric": 0.7442646622657776,
"best_model_checkpoint": "./mistral-lamia-7/checkpoint-309",
"epoch": 1.3333333333333333,
"eval_steps": 103,
"global_step": 412,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1e-05,
"loss": 2.0583,
"step": 1
},
{
"epoch": 0.0,
"eval_loss": 1.443671464920044,
"eval_runtime": 855.8822,
"eval_samples_per_second": 0.609,
"eval_steps_per_second": 0.153,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 2e-05,
"loss": 2.1547,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 3e-05,
"loss": 1.7915,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 4e-05,
"loss": 1.5082,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 5e-05,
"loss": 1.8973,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 6e-05,
"loss": 1.5764,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 7e-05,
"loss": 1.7784,
"step": 7
},
{
"epoch": 0.03,
"learning_rate": 8e-05,
"loss": 1.1673,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 9e-05,
"loss": 1.3696,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 0.0001,
"loss": 1.4372,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 9.999997399012391e-05,
"loss": 1.3773,
"step": 11
},
{
"epoch": 0.04,
"learning_rate": 9.999989596052265e-05,
"loss": 2.1384,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 9.999976591127746e-05,
"loss": 1.2998,
"step": 13
},
{
"epoch": 0.05,
"learning_rate": 9.999958384252362e-05,
"loss": 1.3715,
"step": 14
},
{
"epoch": 0.05,
"learning_rate": 9.999934975445053e-05,
"loss": 1.5568,
"step": 15
},
{
"epoch": 0.05,
"learning_rate": 9.999906364730176e-05,
"loss": 1.5464,
"step": 16
},
{
"epoch": 0.06,
"learning_rate": 9.999872552137497e-05,
"loss": 1.488,
"step": 17
},
{
"epoch": 0.06,
"learning_rate": 9.999833537702192e-05,
"loss": 1.258,
"step": 18
},
{
"epoch": 0.06,
"learning_rate": 9.999789321464857e-05,
"loss": 1.165,
"step": 19
},
{
"epoch": 0.06,
"learning_rate": 9.999739903471488e-05,
"loss": 1.1888,
"step": 20
},
{
"epoch": 0.07,
"learning_rate": 9.999685283773504e-05,
"loss": 1.4435,
"step": 21
},
{
"epoch": 0.07,
"learning_rate": 9.999625462427728e-05,
"loss": 1.5896,
"step": 22
},
{
"epoch": 0.07,
"learning_rate": 9.999560439496399e-05,
"loss": 1.663,
"step": 23
},
{
"epoch": 0.08,
"learning_rate": 9.999490215047167e-05,
"loss": 1.6058,
"step": 24
},
{
"epoch": 0.08,
"learning_rate": 9.999414789153094e-05,
"loss": 1.0705,
"step": 25
},
{
"epoch": 0.08,
"learning_rate": 9.999334161892648e-05,
"loss": 1.4235,
"step": 26
},
{
"epoch": 0.09,
"learning_rate": 9.99924833334972e-05,
"loss": 1.3092,
"step": 27
},
{
"epoch": 0.09,
"learning_rate": 9.999157303613601e-05,
"loss": 1.2291,
"step": 28
},
{
"epoch": 0.09,
"learning_rate": 9.999061072778999e-05,
"loss": 1.2964,
"step": 29
},
{
"epoch": 0.1,
"learning_rate": 9.998959640946033e-05,
"loss": 1.197,
"step": 30
},
{
"epoch": 0.1,
"learning_rate": 9.99885300822023e-05,
"loss": 1.5062,
"step": 31
},
{
"epoch": 0.1,
"learning_rate": 9.998741174712533e-05,
"loss": 1.2466,
"step": 32
},
{
"epoch": 0.11,
"learning_rate": 9.998624140539292e-05,
"loss": 1.1498,
"step": 33
},
{
"epoch": 0.11,
"learning_rate": 9.998501905822266e-05,
"loss": 1.2019,
"step": 34
},
{
"epoch": 0.11,
"learning_rate": 9.998374470688632e-05,
"loss": 0.9986,
"step": 35
},
{
"epoch": 0.12,
"learning_rate": 9.99824183527097e-05,
"loss": 1.2226,
"step": 36
},
{
"epoch": 0.12,
"learning_rate": 9.998103999707273e-05,
"loss": 1.0795,
"step": 37
},
{
"epoch": 0.12,
"learning_rate": 9.997960964140947e-05,
"loss": 1.2918,
"step": 38
},
{
"epoch": 0.13,
"learning_rate": 9.997812728720802e-05,
"loss": 1.2244,
"step": 39
},
{
"epoch": 0.13,
"learning_rate": 9.997659293601065e-05,
"loss": 1.126,
"step": 40
},
{
"epoch": 0.13,
"learning_rate": 9.997500658941366e-05,
"loss": 1.4344,
"step": 41
},
{
"epoch": 0.14,
"learning_rate": 9.997336824906748e-05,
"loss": 1.0974,
"step": 42
},
{
"epoch": 0.14,
"learning_rate": 9.997167791667667e-05,
"loss": 1.4621,
"step": 43
},
{
"epoch": 0.14,
"learning_rate": 9.99699355939998e-05,
"loss": 1.2877,
"step": 44
},
{
"epoch": 0.15,
"learning_rate": 9.99681412828496e-05,
"loss": 1.2676,
"step": 45
},
{
"epoch": 0.15,
"learning_rate": 9.996629498509283e-05,
"loss": 1.339,
"step": 46
},
{
"epoch": 0.15,
"learning_rate": 9.99643967026504e-05,
"loss": 1.1842,
"step": 47
},
{
"epoch": 0.16,
"learning_rate": 9.996244643749727e-05,
"loss": 1.4184,
"step": 48
},
{
"epoch": 0.16,
"learning_rate": 9.996044419166248e-05,
"loss": 1.2832,
"step": 49
},
{
"epoch": 0.16,
"learning_rate": 9.995838996722914e-05,
"loss": 1.2316,
"step": 50
},
{
"epoch": 0.17,
"learning_rate": 9.99562837663345e-05,
"loss": 1.1826,
"step": 51
},
{
"epoch": 0.17,
"learning_rate": 9.995412559116979e-05,
"loss": 1.3186,
"step": 52
},
{
"epoch": 0.17,
"learning_rate": 9.995191544398039e-05,
"loss": 1.3744,
"step": 53
},
{
"epoch": 0.17,
"learning_rate": 9.994965332706573e-05,
"loss": 1.1803,
"step": 54
},
{
"epoch": 0.18,
"learning_rate": 9.99473392427793e-05,
"loss": 1.1569,
"step": 55
},
{
"epoch": 0.18,
"learning_rate": 9.994497319352867e-05,
"loss": 1.2095,
"step": 56
},
{
"epoch": 0.18,
"learning_rate": 9.994255518177544e-05,
"loss": 1.3214,
"step": 57
},
{
"epoch": 0.19,
"learning_rate": 9.994008521003533e-05,
"loss": 1.3726,
"step": 58
},
{
"epoch": 0.19,
"learning_rate": 9.993756328087805e-05,
"loss": 1.148,
"step": 59
},
{
"epoch": 0.19,
"learning_rate": 9.993498939692743e-05,
"loss": 1.065,
"step": 60
},
{
"epoch": 0.2,
"learning_rate": 9.993236356086133e-05,
"loss": 1.2071,
"step": 61
},
{
"epoch": 0.2,
"learning_rate": 9.992968577541163e-05,
"loss": 1.1237,
"step": 62
},
{
"epoch": 0.2,
"learning_rate": 9.992695604336431e-05,
"loss": 1.2605,
"step": 63
},
{
"epoch": 0.21,
"learning_rate": 9.992417436755936e-05,
"loss": 1.2115,
"step": 64
},
{
"epoch": 0.21,
"learning_rate": 9.992134075089084e-05,
"loss": 1.2713,
"step": 65
},
{
"epoch": 0.21,
"learning_rate": 9.991845519630678e-05,
"loss": 1.1697,
"step": 66
},
{
"epoch": 0.22,
"learning_rate": 9.991551770680936e-05,
"loss": 1.162,
"step": 67
},
{
"epoch": 0.22,
"learning_rate": 9.991252828545468e-05,
"loss": 1.1412,
"step": 68
},
{
"epoch": 0.22,
"learning_rate": 9.990948693535294e-05,
"loss": 1.388,
"step": 69
},
{
"epoch": 0.23,
"learning_rate": 9.990639365966836e-05,
"loss": 1.1837,
"step": 70
},
{
"epoch": 0.23,
"learning_rate": 9.990324846161913e-05,
"loss": 1.2843,
"step": 71
},
{
"epoch": 0.23,
"learning_rate": 9.990005134447753e-05,
"loss": 1.0951,
"step": 72
},
{
"epoch": 0.24,
"learning_rate": 9.989680231156981e-05,
"loss": 1.2402,
"step": 73
},
{
"epoch": 0.24,
"learning_rate": 9.989350136627627e-05,
"loss": 1.3355,
"step": 74
},
{
"epoch": 0.24,
"learning_rate": 9.989014851203117e-05,
"loss": 1.2216,
"step": 75
},
{
"epoch": 0.25,
"learning_rate": 9.98867437523228e-05,
"loss": 1.2621,
"step": 76
},
{
"epoch": 0.25,
"learning_rate": 9.98832870906935e-05,
"loss": 1.1265,
"step": 77
},
{
"epoch": 0.25,
"learning_rate": 9.98797785307395e-05,
"loss": 1.1277,
"step": 78
},
{
"epoch": 0.26,
"learning_rate": 9.987621807611114e-05,
"loss": 1.3614,
"step": 79
},
{
"epoch": 0.26,
"learning_rate": 9.987260573051269e-05,
"loss": 1.2972,
"step": 80
},
{
"epoch": 0.26,
"learning_rate": 9.986894149770238e-05,
"loss": 1.0557,
"step": 81
},
{
"epoch": 0.27,
"learning_rate": 9.98652253814925e-05,
"loss": 1.2714,
"step": 82
},
{
"epoch": 0.27,
"learning_rate": 9.986145738574927e-05,
"loss": 1.2355,
"step": 83
},
{
"epoch": 0.27,
"learning_rate": 9.985763751439288e-05,
"loss": 1.0934,
"step": 84
},
{
"epoch": 0.28,
"learning_rate": 9.985376577139753e-05,
"loss": 1.0878,
"step": 85
},
{
"epoch": 0.28,
"learning_rate": 9.984984216079132e-05,
"loss": 1.4082,
"step": 86
},
{
"epoch": 0.28,
"learning_rate": 9.98458666866564e-05,
"loss": 1.1796,
"step": 87
},
{
"epoch": 0.28,
"learning_rate": 9.984183935312881e-05,
"loss": 1.3199,
"step": 88
},
{
"epoch": 0.29,
"learning_rate": 9.983776016439859e-05,
"loss": 1.2988,
"step": 89
},
{
"epoch": 0.29,
"learning_rate": 9.983362912470966e-05,
"loss": 1.3196,
"step": 90
},
{
"epoch": 0.29,
"learning_rate": 9.982944623836e-05,
"loss": 1.2859,
"step": 91
},
{
"epoch": 0.3,
"learning_rate": 9.98252115097014e-05,
"loss": 1.3135,
"step": 92
},
{
"epoch": 0.3,
"learning_rate": 9.982092494313969e-05,
"loss": 1.0826,
"step": 93
},
{
"epoch": 0.3,
"learning_rate": 9.981658654313457e-05,
"loss": 1.0133,
"step": 94
},
{
"epoch": 0.31,
"learning_rate": 9.981219631419972e-05,
"loss": 1.089,
"step": 95
},
{
"epoch": 0.31,
"learning_rate": 9.980775426090268e-05,
"loss": 1.0537,
"step": 96
},
{
"epoch": 0.31,
"learning_rate": 9.980326038786496e-05,
"loss": 1.2502,
"step": 97
},
{
"epoch": 0.32,
"learning_rate": 9.979871469976196e-05,
"loss": 1.1967,
"step": 98
},
{
"epoch": 0.32,
"learning_rate": 9.979411720132299e-05,
"loss": 1.3497,
"step": 99
},
{
"epoch": 0.32,
"learning_rate": 9.978946789733126e-05,
"loss": 1.1884,
"step": 100
},
{
"epoch": 0.33,
"learning_rate": 9.978476679262387e-05,
"loss": 1.2027,
"step": 101
},
{
"epoch": 0.33,
"learning_rate": 9.978001389209186e-05,
"loss": 1.3288,
"step": 102
},
{
"epoch": 0.33,
"learning_rate": 9.977520920068011e-05,
"loss": 1.1651,
"step": 103
},
{
"epoch": 0.33,
"eval_loss": 0.7769330739974976,
"eval_runtime": 859.2735,
"eval_samples_per_second": 0.606,
"eval_steps_per_second": 0.152,
"step": 103
},
{
"epoch": 0.34,
"learning_rate": 9.977035272338738e-05,
"loss": 1.164,
"step": 104
},
{
"epoch": 0.34,
"learning_rate": 9.976544446526634e-05,
"loss": 1.0954,
"step": 105
},
{
"epoch": 0.34,
"learning_rate": 9.976048443142354e-05,
"loss": 1.0738,
"step": 106
},
{
"epoch": 0.35,
"learning_rate": 9.975547262701932e-05,
"loss": 1.226,
"step": 107
},
{
"epoch": 0.35,
"learning_rate": 9.975040905726798e-05,
"loss": 1.2027,
"step": 108
},
{
"epoch": 0.35,
"learning_rate": 9.974529372743761e-05,
"loss": 1.2244,
"step": 109
},
{
"epoch": 0.36,
"learning_rate": 9.974012664285021e-05,
"loss": 1.3685,
"step": 110
},
{
"epoch": 0.36,
"learning_rate": 9.973490780888154e-05,
"loss": 1.1611,
"step": 111
},
{
"epoch": 0.36,
"learning_rate": 9.972963723096128e-05,
"loss": 1.152,
"step": 112
},
{
"epoch": 0.37,
"learning_rate": 9.97243149145729e-05,
"loss": 0.9295,
"step": 113
},
{
"epoch": 0.37,
"learning_rate": 9.971894086525372e-05,
"loss": 0.994,
"step": 114
},
{
"epoch": 0.37,
"learning_rate": 9.971351508859488e-05,
"loss": 1.2434,
"step": 115
},
{
"epoch": 0.38,
"learning_rate": 9.97080375902413e-05,
"loss": 1.1832,
"step": 116
},
{
"epoch": 0.38,
"learning_rate": 9.970250837589177e-05,
"loss": 1.1384,
"step": 117
},
{
"epoch": 0.38,
"learning_rate": 9.969692745129885e-05,
"loss": 1.1646,
"step": 118
},
{
"epoch": 0.39,
"learning_rate": 9.969129482226894e-05,
"loss": 1.2104,
"step": 119
},
{
"epoch": 0.39,
"learning_rate": 9.968561049466214e-05,
"loss": 1.0034,
"step": 120
},
{
"epoch": 0.39,
"learning_rate": 9.967987447439243e-05,
"loss": 1.1279,
"step": 121
},
{
"epoch": 0.39,
"learning_rate": 9.967408676742751e-05,
"loss": 1.003,
"step": 122
},
{
"epoch": 0.4,
"learning_rate": 9.966824737978893e-05,
"loss": 1.0833,
"step": 123
},
{
"epoch": 0.4,
"learning_rate": 9.966235631755192e-05,
"loss": 1.1952,
"step": 124
},
{
"epoch": 0.4,
"learning_rate": 9.965641358684553e-05,
"loss": 1.1463,
"step": 125
},
{
"epoch": 0.41,
"learning_rate": 9.965041919385252e-05,
"loss": 1.2657,
"step": 126
},
{
"epoch": 0.41,
"learning_rate": 9.964437314480947e-05,
"loss": 1.2557,
"step": 127
},
{
"epoch": 0.41,
"learning_rate": 9.963827544600662e-05,
"loss": 1.2098,
"step": 128
},
{
"epoch": 0.42,
"learning_rate": 9.963212610378803e-05,
"loss": 1.1649,
"step": 129
},
{
"epoch": 0.42,
"learning_rate": 9.962592512455138e-05,
"loss": 1.1723,
"step": 130
},
{
"epoch": 0.42,
"learning_rate": 9.961967251474822e-05,
"loss": 1.0861,
"step": 131
},
{
"epoch": 0.43,
"learning_rate": 9.961336828088365e-05,
"loss": 1.1231,
"step": 132
},
{
"epoch": 0.43,
"learning_rate": 9.960701242951663e-05,
"loss": 1.1572,
"step": 133
},
{
"epoch": 0.43,
"learning_rate": 9.960060496725974e-05,
"loss": 1.236,
"step": 134
},
{
"epoch": 0.44,
"learning_rate": 9.959414590077925e-05,
"loss": 1.0556,
"step": 135
},
{
"epoch": 0.44,
"learning_rate": 9.958763523679514e-05,
"loss": 1.0868,
"step": 136
},
{
"epoch": 0.44,
"learning_rate": 9.95810729820811e-05,
"loss": 1.1307,
"step": 137
},
{
"epoch": 0.45,
"learning_rate": 9.957445914346444e-05,
"loss": 1.1461,
"step": 138
},
{
"epoch": 0.45,
"learning_rate": 9.95677937278262e-05,
"loss": 1.1393,
"step": 139
},
{
"epoch": 0.45,
"learning_rate": 9.9561076742101e-05,
"loss": 1.2003,
"step": 140
},
{
"epoch": 0.46,
"learning_rate": 9.95543081932772e-05,
"loss": 1.1272,
"step": 141
},
{
"epoch": 0.46,
"learning_rate": 9.954748808839674e-05,
"loss": 1.0357,
"step": 142
},
{
"epoch": 0.46,
"learning_rate": 9.954061643455523e-05,
"loss": 1.2283,
"step": 143
},
{
"epoch": 0.47,
"learning_rate": 9.953369323890191e-05,
"loss": 1.1221,
"step": 144
},
{
"epoch": 0.47,
"learning_rate": 9.952671850863963e-05,
"loss": 1.2206,
"step": 145
},
{
"epoch": 0.47,
"learning_rate": 9.951969225102486e-05,
"loss": 1.4204,
"step": 146
},
{
"epoch": 0.48,
"learning_rate": 9.95126144733677e-05,
"loss": 1.012,
"step": 147
},
{
"epoch": 0.48,
"learning_rate": 9.950548518303183e-05,
"loss": 1.2038,
"step": 148
},
{
"epoch": 0.48,
"learning_rate": 9.949830438743453e-05,
"loss": 1.2403,
"step": 149
},
{
"epoch": 0.49,
"learning_rate": 9.949107209404665e-05,
"loss": 0.9957,
"step": 150
},
{
"epoch": 0.49,
"learning_rate": 9.948378831039264e-05,
"loss": 1.1783,
"step": 151
},
{
"epoch": 0.49,
"learning_rate": 9.947645304405051e-05,
"loss": 1.1181,
"step": 152
},
{
"epoch": 0.5,
"learning_rate": 9.946906630265184e-05,
"loss": 0.9741,
"step": 153
},
{
"epoch": 0.5,
"learning_rate": 9.946162809388176e-05,
"loss": 1.1431,
"step": 154
},
{
"epoch": 0.5,
"learning_rate": 9.945413842547894e-05,
"loss": 1.1987,
"step": 155
},
{
"epoch": 0.5,
"learning_rate": 9.94465973052356e-05,
"loss": 1.134,
"step": 156
},
{
"epoch": 0.51,
"learning_rate": 9.943900474099748e-05,
"loss": 1.2935,
"step": 157
},
{
"epoch": 0.51,
"learning_rate": 9.943136074066385e-05,
"loss": 0.9978,
"step": 158
},
{
"epoch": 0.51,
"learning_rate": 9.942366531218748e-05,
"loss": 1.1968,
"step": 159
},
{
"epoch": 0.52,
"learning_rate": 9.941591846357468e-05,
"loss": 1.1044,
"step": 160
},
{
"epoch": 0.52,
"learning_rate": 9.94081202028852e-05,
"loss": 1.1268,
"step": 161
},
{
"epoch": 0.52,
"learning_rate": 9.940027053823234e-05,
"loss": 1.2869,
"step": 162
},
{
"epoch": 0.53,
"learning_rate": 9.939236947778281e-05,
"loss": 1.2323,
"step": 163
},
{
"epoch": 0.53,
"learning_rate": 9.938441702975689e-05,
"loss": 1.1835,
"step": 164
},
{
"epoch": 0.53,
"learning_rate": 9.937641320242822e-05,
"loss": 1.0609,
"step": 165
},
{
"epoch": 0.54,
"learning_rate": 9.9368358004124e-05,
"loss": 1.2646,
"step": 166
},
{
"epoch": 0.54,
"learning_rate": 9.936025144322476e-05,
"loss": 1.1829,
"step": 167
},
{
"epoch": 0.54,
"learning_rate": 9.935209352816455e-05,
"loss": 1.1813,
"step": 168
},
{
"epoch": 0.55,
"learning_rate": 9.934388426743082e-05,
"loss": 1.1192,
"step": 169
},
{
"epoch": 0.55,
"learning_rate": 9.933562366956445e-05,
"loss": 1.264,
"step": 170
},
{
"epoch": 0.55,
"learning_rate": 9.932731174315972e-05,
"loss": 1.1099,
"step": 171
},
{
"epoch": 0.56,
"learning_rate": 9.931894849686432e-05,
"loss": 1.0458,
"step": 172
},
{
"epoch": 0.56,
"learning_rate": 9.931053393937932e-05,
"loss": 1.1754,
"step": 173
},
{
"epoch": 0.56,
"learning_rate": 9.93020680794592e-05,
"loss": 1.0062,
"step": 174
},
{
"epoch": 0.57,
"learning_rate": 9.92935509259118e-05,
"loss": 1.1492,
"step": 175
},
{
"epoch": 0.57,
"learning_rate": 9.92849824875983e-05,
"loss": 1.0825,
"step": 176
},
{
"epoch": 0.57,
"learning_rate": 9.927636277343329e-05,
"loss": 1.1788,
"step": 177
},
{
"epoch": 0.58,
"learning_rate": 9.926769179238466e-05,
"loss": 1.0398,
"step": 178
},
{
"epoch": 0.58,
"learning_rate": 9.925896955347364e-05,
"loss": 1.3753,
"step": 179
},
{
"epoch": 0.58,
"learning_rate": 9.925019606577486e-05,
"loss": 1.1793,
"step": 180
},
{
"epoch": 0.59,
"learning_rate": 9.924137133841616e-05,
"loss": 1.1719,
"step": 181
},
{
"epoch": 0.59,
"learning_rate": 9.923249538057875e-05,
"loss": 1.0094,
"step": 182
},
{
"epoch": 0.59,
"learning_rate": 9.922356820149715e-05,
"loss": 1.2844,
"step": 183
},
{
"epoch": 0.6,
"learning_rate": 9.921458981045914e-05,
"loss": 1.1394,
"step": 184
},
{
"epoch": 0.6,
"learning_rate": 9.92055602168058e-05,
"loss": 1.161,
"step": 185
},
{
"epoch": 0.6,
"learning_rate": 9.919647942993148e-05,
"loss": 1.2338,
"step": 186
},
{
"epoch": 0.61,
"learning_rate": 9.918734745928378e-05,
"loss": 1.1616,
"step": 187
},
{
"epoch": 0.61,
"learning_rate": 9.917816431436355e-05,
"loss": 1.1774,
"step": 188
},
{
"epoch": 0.61,
"learning_rate": 9.91689300047249e-05,
"loss": 1.1482,
"step": 189
},
{
"epoch": 0.61,
"learning_rate": 9.915964453997515e-05,
"loss": 1.1453,
"step": 190
},
{
"epoch": 0.62,
"learning_rate": 9.915030792977487e-05,
"loss": 1.2261,
"step": 191
},
{
"epoch": 0.62,
"learning_rate": 9.914092018383778e-05,
"loss": 0.9531,
"step": 192
},
{
"epoch": 0.62,
"learning_rate": 9.91314813119309e-05,
"loss": 1.1557,
"step": 193
},
{
"epoch": 0.63,
"learning_rate": 9.912199132387434e-05,
"loss": 1.2099,
"step": 194
},
{
"epoch": 0.63,
"learning_rate": 9.911245022954147e-05,
"loss": 1.0969,
"step": 195
},
{
"epoch": 0.63,
"learning_rate": 9.910285803885877e-05,
"loss": 1.3077,
"step": 196
},
{
"epoch": 0.64,
"learning_rate": 9.909321476180594e-05,
"loss": 1.2176,
"step": 197
},
{
"epoch": 0.64,
"learning_rate": 9.908352040841576e-05,
"loss": 1.1101,
"step": 198
},
{
"epoch": 0.64,
"learning_rate": 9.90737749887742e-05,
"loss": 1.3515,
"step": 199
},
{
"epoch": 0.65,
"learning_rate": 9.906397851302036e-05,
"loss": 0.9948,
"step": 200
},
{
"epoch": 0.65,
"learning_rate": 9.905413099134644e-05,
"loss": 1.1265,
"step": 201
},
{
"epoch": 0.65,
"learning_rate": 9.904423243399774e-05,
"loss": 1.4007,
"step": 202
},
{
"epoch": 0.66,
"learning_rate": 9.903428285127268e-05,
"loss": 1.0674,
"step": 203
},
{
"epoch": 0.66,
"learning_rate": 9.902428225352277e-05,
"loss": 1.0193,
"step": 204
},
{
"epoch": 0.66,
"learning_rate": 9.901423065115254e-05,
"loss": 1.0533,
"step": 205
},
{
"epoch": 0.67,
"learning_rate": 9.900412805461967e-05,
"loss": 1.1377,
"step": 206
},
{
"epoch": 0.67,
"eval_loss": 0.7517589926719666,
"eval_runtime": 859.1271,
"eval_samples_per_second": 0.606,
"eval_steps_per_second": 0.152,
"step": 206
},
{
"epoch": 0.67,
"learning_rate": 9.899397447443484e-05,
"loss": 1.2305,
"step": 207
},
{
"epoch": 0.67,
"learning_rate": 9.898376992116179e-05,
"loss": 1.2319,
"step": 208
},
{
"epoch": 0.68,
"learning_rate": 9.897351440541727e-05,
"loss": 1.0622,
"step": 209
},
{
"epoch": 0.68,
"learning_rate": 9.896320793787106e-05,
"loss": 1.1298,
"step": 210
},
{
"epoch": 0.68,
"learning_rate": 9.895285052924599e-05,
"loss": 1.1869,
"step": 211
},
{
"epoch": 0.69,
"learning_rate": 9.894244219031783e-05,
"loss": 1.3071,
"step": 212
},
{
"epoch": 0.69,
"learning_rate": 9.893198293191538e-05,
"loss": 1.1135,
"step": 213
},
{
"epoch": 0.69,
"learning_rate": 9.892147276492039e-05,
"loss": 1.1577,
"step": 214
},
{
"epoch": 0.7,
"learning_rate": 9.89109117002676e-05,
"loss": 1.1323,
"step": 215
},
{
"epoch": 0.7,
"learning_rate": 9.890029974894466e-05,
"loss": 1.1308,
"step": 216
},
{
"epoch": 0.7,
"learning_rate": 9.888963692199223e-05,
"loss": 1.0908,
"step": 217
},
{
"epoch": 0.71,
"learning_rate": 9.887892323050384e-05,
"loss": 1.2721,
"step": 218
},
{
"epoch": 0.71,
"learning_rate": 9.886815868562596e-05,
"loss": 1.1598,
"step": 219
},
{
"epoch": 0.71,
"learning_rate": 9.885734329855798e-05,
"loss": 0.9964,
"step": 220
},
{
"epoch": 0.72,
"learning_rate": 9.884647708055217e-05,
"loss": 1.1307,
"step": 221
},
{
"epoch": 0.72,
"learning_rate": 9.883556004291368e-05,
"loss": 1.3948,
"step": 222
},
{
"epoch": 0.72,
"learning_rate": 9.882459219700056e-05,
"loss": 0.9427,
"step": 223
},
{
"epoch": 0.72,
"learning_rate": 9.881357355422368e-05,
"loss": 1.2337,
"step": 224
},
{
"epoch": 0.73,
"learning_rate": 9.880250412604681e-05,
"loss": 1.0835,
"step": 225
},
{
"epoch": 0.73,
"learning_rate": 9.87913839239865e-05,
"loss": 1.263,
"step": 226
},
{
"epoch": 0.73,
"learning_rate": 9.878021295961217e-05,
"loss": 1.0411,
"step": 227
},
{
"epoch": 0.74,
"learning_rate": 9.876899124454604e-05,
"loss": 1.2549,
"step": 228
},
{
"epoch": 0.74,
"learning_rate": 9.87577187904631e-05,
"loss": 1.1883,
"step": 229
},
{
"epoch": 0.74,
"learning_rate": 9.874639560909117e-05,
"loss": 1.1391,
"step": 230
},
{
"epoch": 0.75,
"learning_rate": 9.873502171221087e-05,
"loss": 1.1801,
"step": 231
},
{
"epoch": 0.75,
"learning_rate": 9.872359711165549e-05,
"loss": 1.3583,
"step": 232
},
{
"epoch": 0.75,
"learning_rate": 9.871212181931115e-05,
"loss": 1.0431,
"step": 233
},
{
"epoch": 0.76,
"learning_rate": 9.870059584711668e-05,
"loss": 1.0404,
"step": 234
},
{
"epoch": 0.76,
"learning_rate": 9.868901920706366e-05,
"loss": 1.1149,
"step": 235
},
{
"epoch": 0.76,
"learning_rate": 9.867739191119636e-05,
"loss": 1.1922,
"step": 236
},
{
"epoch": 0.77,
"learning_rate": 9.866571397161175e-05,
"loss": 1.0328,
"step": 237
},
{
"epoch": 0.77,
"learning_rate": 9.865398540045952e-05,
"loss": 1.1225,
"step": 238
},
{
"epoch": 0.77,
"learning_rate": 9.864220620994201e-05,
"loss": 1.2339,
"step": 239
},
{
"epoch": 0.78,
"learning_rate": 9.863037641231422e-05,
"loss": 1.1169,
"step": 240
},
{
"epoch": 0.78,
"learning_rate": 9.861849601988383e-05,
"loss": 1.3356,
"step": 241
},
{
"epoch": 0.78,
"learning_rate": 9.860656504501113e-05,
"loss": 1.2194,
"step": 242
},
{
"epoch": 0.79,
"learning_rate": 9.859458350010905e-05,
"loss": 1.1395,
"step": 243
},
{
"epoch": 0.79,
"learning_rate": 9.858255139764315e-05,
"loss": 1.0451,
"step": 244
},
{
"epoch": 0.79,
"learning_rate": 9.857046875013154e-05,
"loss": 1.1524,
"step": 245
},
{
"epoch": 0.8,
"learning_rate": 9.855833557014495e-05,
"loss": 1.2449,
"step": 246
},
{
"epoch": 0.8,
"learning_rate": 9.85461518703067e-05,
"loss": 1.151,
"step": 247
},
{
"epoch": 0.8,
"learning_rate": 9.853391766329263e-05,
"loss": 1.1867,
"step": 248
},
{
"epoch": 0.81,
"learning_rate": 9.852163296183117e-05,
"loss": 1.1155,
"step": 249
},
{
"epoch": 0.81,
"learning_rate": 9.850929777870324e-05,
"loss": 1.0962,
"step": 250
},
{
"epoch": 0.81,
"learning_rate": 9.84969121267423e-05,
"loss": 1.16,
"step": 251
},
{
"epoch": 0.82,
"learning_rate": 9.848447601883435e-05,
"loss": 1.1288,
"step": 252
},
{
"epoch": 0.82,
"learning_rate": 9.847198946791784e-05,
"loss": 1.3088,
"step": 253
},
{
"epoch": 0.82,
"learning_rate": 9.84594524869837e-05,
"loss": 1.2906,
"step": 254
},
{
"epoch": 0.83,
"learning_rate": 9.844686508907537e-05,
"loss": 1.2188,
"step": 255
},
{
"epoch": 0.83,
"learning_rate": 9.843422728728871e-05,
"loss": 1.1946,
"step": 256
},
{
"epoch": 0.83,
"learning_rate": 9.842153909477201e-05,
"loss": 1.0312,
"step": 257
},
{
"epoch": 0.83,
"learning_rate": 9.840880052472601e-05,
"loss": 1.0968,
"step": 258
},
{
"epoch": 0.84,
"learning_rate": 9.839601159040386e-05,
"loss": 1.2417,
"step": 259
},
{
"epoch": 0.84,
"learning_rate": 9.838317230511112e-05,
"loss": 1.1532,
"step": 260
},
{
"epoch": 0.84,
"learning_rate": 9.837028268220567e-05,
"loss": 1.3025,
"step": 261
},
{
"epoch": 0.85,
"learning_rate": 9.835734273509786e-05,
"loss": 1.0594,
"step": 262
},
{
"epoch": 0.85,
"learning_rate": 9.834435247725033e-05,
"loss": 1.3581,
"step": 263
},
{
"epoch": 0.85,
"learning_rate": 9.833131192217806e-05,
"loss": 1.1592,
"step": 264
},
{
"epoch": 0.86,
"learning_rate": 9.831822108344841e-05,
"loss": 1.043,
"step": 265
},
{
"epoch": 0.86,
"learning_rate": 9.830507997468101e-05,
"loss": 1.1142,
"step": 266
},
{
"epoch": 0.86,
"learning_rate": 9.829188860954781e-05,
"loss": 1.184,
"step": 267
},
{
"epoch": 0.87,
"learning_rate": 9.827864700177302e-05,
"loss": 1.3455,
"step": 268
},
{
"epoch": 0.87,
"learning_rate": 9.826535516513317e-05,
"loss": 1.0595,
"step": 269
},
{
"epoch": 0.87,
"learning_rate": 9.8252013113457e-05,
"loss": 1.2036,
"step": 270
},
{
"epoch": 0.88,
"learning_rate": 9.823862086062553e-05,
"loss": 1.2629,
"step": 271
},
{
"epoch": 0.88,
"learning_rate": 9.822517842057198e-05,
"loss": 1.1612,
"step": 272
},
{
"epoch": 0.88,
"learning_rate": 9.821168580728181e-05,
"loss": 1.1814,
"step": 273
},
{
"epoch": 0.89,
"learning_rate": 9.819814303479267e-05,
"loss": 1.0398,
"step": 274
},
{
"epoch": 0.89,
"learning_rate": 9.818455011719439e-05,
"loss": 1.123,
"step": 275
},
{
"epoch": 0.89,
"learning_rate": 9.817090706862895e-05,
"loss": 1.2314,
"step": 276
},
{
"epoch": 0.9,
"learning_rate": 9.815721390329055e-05,
"loss": 1.1784,
"step": 277
},
{
"epoch": 0.9,
"learning_rate": 9.814347063542546e-05,
"loss": 0.9881,
"step": 278
},
{
"epoch": 0.9,
"learning_rate": 9.812967727933213e-05,
"loss": 1.2049,
"step": 279
},
{
"epoch": 0.91,
"learning_rate": 9.811583384936107e-05,
"loss": 1.0459,
"step": 280
},
{
"epoch": 0.91,
"learning_rate": 9.810194035991495e-05,
"loss": 1.0323,
"step": 281
},
{
"epoch": 0.91,
"learning_rate": 9.808799682544846e-05,
"loss": 1.237,
"step": 282
},
{
"epoch": 0.92,
"learning_rate": 9.807400326046843e-05,
"loss": 1.1142,
"step": 283
},
{
"epoch": 0.92,
"learning_rate": 9.805995967953363e-05,
"loss": 1.1063,
"step": 284
},
{
"epoch": 0.92,
"learning_rate": 9.804586609725499e-05,
"loss": 1.0957,
"step": 285
},
{
"epoch": 0.93,
"learning_rate": 9.803172252829536e-05,
"loss": 0.8887,
"step": 286
},
{
"epoch": 0.93,
"learning_rate": 9.801752898736966e-05,
"loss": 1.0086,
"step": 287
},
{
"epoch": 0.93,
"learning_rate": 9.800328548924478e-05,
"loss": 1.1333,
"step": 288
},
{
"epoch": 0.94,
"learning_rate": 9.798899204873957e-05,
"loss": 1.0308,
"step": 289
},
{
"epoch": 0.94,
"learning_rate": 9.797464868072488e-05,
"loss": 1.0024,
"step": 290
},
{
"epoch": 0.94,
"learning_rate": 9.796025540012346e-05,
"loss": 1.1911,
"step": 291
},
{
"epoch": 0.94,
"learning_rate": 9.794581222191001e-05,
"loss": 1.0609,
"step": 292
},
{
"epoch": 0.95,
"learning_rate": 9.793131916111114e-05,
"loss": 1.2506,
"step": 293
},
{
"epoch": 0.95,
"learning_rate": 9.791677623280537e-05,
"loss": 1.0964,
"step": 294
},
{
"epoch": 0.95,
"learning_rate": 9.790218345212308e-05,
"loss": 1.037,
"step": 295
},
{
"epoch": 0.96,
"learning_rate": 9.788754083424652e-05,
"loss": 1.2541,
"step": 296
},
{
"epoch": 0.96,
"learning_rate": 9.787284839440982e-05,
"loss": 1.2164,
"step": 297
},
{
"epoch": 0.96,
"learning_rate": 9.785810614789891e-05,
"loss": 0.9282,
"step": 298
},
{
"epoch": 0.97,
"learning_rate": 9.784331411005155e-05,
"loss": 1.0881,
"step": 299
},
{
"epoch": 0.97,
"learning_rate": 9.782847229625729e-05,
"loss": 1.0904,
"step": 300
},
{
"epoch": 0.97,
"learning_rate": 9.78135807219575e-05,
"loss": 1.1065,
"step": 301
},
{
"epoch": 0.98,
"learning_rate": 9.779863940264529e-05,
"loss": 1.1201,
"step": 302
},
{
"epoch": 0.98,
"learning_rate": 9.778364835386553e-05,
"loss": 1.2199,
"step": 303
},
{
"epoch": 0.98,
"learning_rate": 9.776860759121484e-05,
"loss": 1.2194,
"step": 304
},
{
"epoch": 0.99,
"learning_rate": 9.775351713034156e-05,
"loss": 1.1701,
"step": 305
},
{
"epoch": 0.99,
"learning_rate": 9.773837698694571e-05,
"loss": 1.339,
"step": 306
},
{
"epoch": 0.99,
"learning_rate": 9.772318717677904e-05,
"loss": 1.0602,
"step": 307
},
{
"epoch": 1.0,
"learning_rate": 9.770794771564495e-05,
"loss": 1.0773,
"step": 308
},
{
"epoch": 1.0,
"learning_rate": 9.76926586193985e-05,
"loss": 1.166,
"step": 309
},
{
"epoch": 1.0,
"eval_loss": 0.7442646622657776,
"eval_runtime": 859.0542,
"eval_samples_per_second": 0.606,
"eval_steps_per_second": 0.152,
"step": 309
},
{
"epoch": 1.0,
"learning_rate": 9.767731990394638e-05,
"loss": 0.8696,
"step": 310
},
{
"epoch": 1.01,
"learning_rate": 9.766193158524692e-05,
"loss": 0.8288,
"step": 311
},
{
"epoch": 1.01,
"learning_rate": 9.764649367931007e-05,
"loss": 0.899,
"step": 312
},
{
"epoch": 1.01,
"learning_rate": 9.763100620219731e-05,
"loss": 0.8109,
"step": 313
},
{
"epoch": 1.02,
"learning_rate": 9.761546917002178e-05,
"loss": 0.882,
"step": 314
},
{
"epoch": 1.02,
"learning_rate": 9.759988259894808e-05,
"loss": 0.7985,
"step": 315
},
{
"epoch": 1.02,
"learning_rate": 9.758424650519244e-05,
"loss": 0.8101,
"step": 316
},
{
"epoch": 1.03,
"learning_rate": 9.756856090502258e-05,
"loss": 1.0696,
"step": 317
},
{
"epoch": 1.03,
"learning_rate": 9.755282581475769e-05,
"loss": 0.9892,
"step": 318
},
{
"epoch": 1.03,
"learning_rate": 9.753704125076848e-05,
"loss": 0.8788,
"step": 319
},
{
"epoch": 1.04,
"learning_rate": 9.752120722947718e-05,
"loss": 0.8815,
"step": 320
},
{
"epoch": 1.04,
"learning_rate": 9.750532376735736e-05,
"loss": 0.8671,
"step": 321
},
{
"epoch": 1.04,
"learning_rate": 9.748939088093413e-05,
"loss": 0.8458,
"step": 322
},
{
"epoch": 1.05,
"learning_rate": 9.747340858678402e-05,
"loss": 1.0109,
"step": 323
},
{
"epoch": 1.05,
"learning_rate": 9.745737690153487e-05,
"loss": 0.7822,
"step": 324
},
{
"epoch": 1.05,
"learning_rate": 9.744129584186598e-05,
"loss": 0.8424,
"step": 325
},
{
"epoch": 1.06,
"learning_rate": 9.742516542450803e-05,
"loss": 0.9926,
"step": 326
},
{
"epoch": 1.06,
"learning_rate": 9.740898566624302e-05,
"loss": 0.8599,
"step": 327
},
{
"epoch": 1.06,
"learning_rate": 9.739275658390427e-05,
"loss": 0.9044,
"step": 328
},
{
"epoch": 1.06,
"learning_rate": 9.737647819437645e-05,
"loss": 1.0284,
"step": 329
},
{
"epoch": 1.07,
"learning_rate": 9.73601505145955e-05,
"loss": 0.8623,
"step": 330
},
{
"epoch": 1.07,
"learning_rate": 9.734377356154869e-05,
"loss": 0.8071,
"step": 331
},
{
"epoch": 1.07,
"learning_rate": 9.73273473522745e-05,
"loss": 1.0447,
"step": 332
},
{
"epoch": 1.08,
"learning_rate": 9.731087190386268e-05,
"loss": 0.9164,
"step": 333
},
{
"epoch": 1.08,
"learning_rate": 9.72943472334542e-05,
"loss": 1.0258,
"step": 334
},
{
"epoch": 1.08,
"learning_rate": 9.727777335824124e-05,
"loss": 0.8969,
"step": 335
},
{
"epoch": 1.09,
"learning_rate": 9.726115029546721e-05,
"loss": 0.942,
"step": 336
},
{
"epoch": 1.09,
"learning_rate": 9.724447806242662e-05,
"loss": 1.1972,
"step": 337
},
{
"epoch": 1.09,
"learning_rate": 9.72277566764652e-05,
"loss": 0.8396,
"step": 338
},
{
"epoch": 1.1,
"learning_rate": 9.72109861549798e-05,
"loss": 1.0402,
"step": 339
},
{
"epoch": 1.1,
"learning_rate": 9.719416651541839e-05,
"loss": 0.9729,
"step": 340
},
{
"epoch": 1.1,
"learning_rate": 9.717729777528001e-05,
"loss": 0.9919,
"step": 341
},
{
"epoch": 1.11,
"learning_rate": 9.716037995211484e-05,
"loss": 1.2068,
"step": 342
},
{
"epoch": 1.11,
"learning_rate": 9.714341306352411e-05,
"loss": 0.9471,
"step": 343
},
{
"epoch": 1.11,
"learning_rate": 9.712639712716007e-05,
"loss": 1.0325,
"step": 344
},
{
"epoch": 1.12,
"learning_rate": 9.7109332160726e-05,
"loss": 0.9684,
"step": 345
},
{
"epoch": 1.12,
"learning_rate": 9.709221818197624e-05,
"loss": 0.8641,
"step": 346
},
{
"epoch": 1.12,
"learning_rate": 9.707505520871607e-05,
"loss": 0.9543,
"step": 347
},
{
"epoch": 1.13,
"learning_rate": 9.705784325880176e-05,
"loss": 1.1185,
"step": 348
},
{
"epoch": 1.13,
"learning_rate": 9.704058235014054e-05,
"loss": 0.7917,
"step": 349
},
{
"epoch": 1.13,
"learning_rate": 9.702327250069059e-05,
"loss": 0.8544,
"step": 350
},
{
"epoch": 1.14,
"learning_rate": 9.700591372846095e-05,
"loss": 0.8404,
"step": 351
},
{
"epoch": 1.14,
"learning_rate": 9.698850605151165e-05,
"loss": 1.023,
"step": 352
},
{
"epoch": 1.14,
"learning_rate": 9.697104948795352e-05,
"loss": 0.9241,
"step": 353
},
{
"epoch": 1.15,
"learning_rate": 9.69535440559483e-05,
"loss": 0.9049,
"step": 354
},
{
"epoch": 1.15,
"learning_rate": 9.693598977370854e-05,
"loss": 0.998,
"step": 355
},
{
"epoch": 1.15,
"learning_rate": 9.691838665949764e-05,
"loss": 1.1147,
"step": 356
},
{
"epoch": 1.16,
"learning_rate": 9.690073473162978e-05,
"loss": 1.0152,
"step": 357
},
{
"epoch": 1.16,
"learning_rate": 9.688303400846995e-05,
"loss": 0.8904,
"step": 358
},
{
"epoch": 1.16,
"learning_rate": 9.686528450843389e-05,
"loss": 0.9847,
"step": 359
},
{
"epoch": 1.17,
"learning_rate": 9.68474862499881e-05,
"loss": 1.1606,
"step": 360
},
{
"epoch": 1.17,
"learning_rate": 9.682963925164977e-05,
"loss": 0.86,
"step": 361
},
{
"epoch": 1.17,
"learning_rate": 9.681174353198687e-05,
"loss": 0.7986,
"step": 362
},
{
"epoch": 1.17,
"learning_rate": 9.679379910961799e-05,
"loss": 0.9406,
"step": 363
},
{
"epoch": 1.18,
"learning_rate": 9.677580600321242e-05,
"loss": 1.0272,
"step": 364
},
{
"epoch": 1.18,
"learning_rate": 9.675776423149013e-05,
"loss": 0.8774,
"step": 365
},
{
"epoch": 1.18,
"learning_rate": 9.673967381322163e-05,
"loss": 1.037,
"step": 366
},
{
"epoch": 1.19,
"learning_rate": 9.672153476722816e-05,
"loss": 0.8539,
"step": 367
},
{
"epoch": 1.19,
"learning_rate": 9.670334711238145e-05,
"loss": 0.8378,
"step": 368
},
{
"epoch": 1.19,
"learning_rate": 9.668511086760389e-05,
"loss": 0.8108,
"step": 369
},
{
"epoch": 1.2,
"learning_rate": 9.666682605186835e-05,
"loss": 0.7509,
"step": 370
},
{
"epoch": 1.2,
"learning_rate": 9.664849268419825e-05,
"loss": 1.1062,
"step": 371
},
{
"epoch": 1.2,
"learning_rate": 9.663011078366757e-05,
"loss": 0.8277,
"step": 372
},
{
"epoch": 1.21,
"learning_rate": 9.661168036940071e-05,
"loss": 0.8602,
"step": 373
},
{
"epoch": 1.21,
"learning_rate": 9.659320146057262e-05,
"loss": 1.0327,
"step": 374
},
{
"epoch": 1.21,
"learning_rate": 9.657467407640864e-05,
"loss": 0.9697,
"step": 375
},
{
"epoch": 1.22,
"learning_rate": 9.655609823618457e-05,
"loss": 1.0604,
"step": 376
},
{
"epoch": 1.22,
"learning_rate": 9.653747395922663e-05,
"loss": 0.8769,
"step": 377
},
{
"epoch": 1.22,
"learning_rate": 9.651880126491144e-05,
"loss": 0.8384,
"step": 378
},
{
"epoch": 1.23,
"learning_rate": 9.650008017266594e-05,
"loss": 0.9498,
"step": 379
},
{
"epoch": 1.23,
"learning_rate": 9.648131070196749e-05,
"loss": 0.987,
"step": 380
},
{
"epoch": 1.23,
"learning_rate": 9.646249287234374e-05,
"loss": 0.9841,
"step": 381
},
{
"epoch": 1.24,
"learning_rate": 9.644362670337268e-05,
"loss": 1.034,
"step": 382
},
{
"epoch": 1.24,
"learning_rate": 9.642471221468257e-05,
"loss": 0.9491,
"step": 383
},
{
"epoch": 1.24,
"learning_rate": 9.640574942595196e-05,
"loss": 0.9272,
"step": 384
},
{
"epoch": 1.25,
"learning_rate": 9.638673835690961e-05,
"loss": 1.0313,
"step": 385
},
{
"epoch": 1.25,
"learning_rate": 9.636767902733458e-05,
"loss": 0.8084,
"step": 386
},
{
"epoch": 1.25,
"learning_rate": 9.634857145705612e-05,
"loss": 1.0232,
"step": 387
},
{
"epoch": 1.26,
"learning_rate": 9.632941566595357e-05,
"loss": 0.7735,
"step": 388
},
{
"epoch": 1.26,
"learning_rate": 9.631021167395659e-05,
"loss": 0.801,
"step": 389
},
{
"epoch": 1.26,
"learning_rate": 9.62909595010449e-05,
"loss": 0.792,
"step": 390
},
{
"epoch": 1.27,
"learning_rate": 9.627165916724837e-05,
"loss": 1.2264,
"step": 391
},
{
"epoch": 1.27,
"learning_rate": 9.625231069264696e-05,
"loss": 0.9676,
"step": 392
},
{
"epoch": 1.27,
"learning_rate": 9.623291409737074e-05,
"loss": 1.0697,
"step": 393
},
{
"epoch": 1.28,
"learning_rate": 9.62134694015998e-05,
"loss": 0.8656,
"step": 394
},
{
"epoch": 1.28,
"learning_rate": 9.619397662556435e-05,
"loss": 0.952,
"step": 395
},
{
"epoch": 1.28,
"learning_rate": 9.617443578954455e-05,
"loss": 0.9509,
"step": 396
},
{
"epoch": 1.28,
"learning_rate": 9.615484691387058e-05,
"loss": 0.9439,
"step": 397
},
{
"epoch": 1.29,
"learning_rate": 9.613521001892264e-05,
"loss": 0.8009,
"step": 398
},
{
"epoch": 1.29,
"learning_rate": 9.611552512513085e-05,
"loss": 0.7669,
"step": 399
},
{
"epoch": 1.29,
"learning_rate": 9.609579225297525e-05,
"loss": 1.0578,
"step": 400
},
{
"epoch": 1.3,
"learning_rate": 9.607601142298584e-05,
"loss": 0.7875,
"step": 401
},
{
"epoch": 1.3,
"learning_rate": 9.60561826557425e-05,
"loss": 0.8935,
"step": 402
},
{
"epoch": 1.3,
"learning_rate": 9.603630597187499e-05,
"loss": 1.0119,
"step": 403
},
{
"epoch": 1.31,
"learning_rate": 9.601638139206291e-05,
"loss": 0.8773,
"step": 404
},
{
"epoch": 1.31,
"learning_rate": 9.599640893703568e-05,
"loss": 1.0947,
"step": 405
},
{
"epoch": 1.31,
"learning_rate": 9.597638862757255e-05,
"loss": 0.9826,
"step": 406
},
{
"epoch": 1.32,
"learning_rate": 9.595632048450254e-05,
"loss": 0.9346,
"step": 407
},
{
"epoch": 1.32,
"learning_rate": 9.593620452870446e-05,
"loss": 1.1038,
"step": 408
},
{
"epoch": 1.32,
"learning_rate": 9.591604078110685e-05,
"loss": 0.8444,
"step": 409
},
{
"epoch": 1.33,
"learning_rate": 9.589582926268798e-05,
"loss": 0.8715,
"step": 410
},
{
"epoch": 1.33,
"learning_rate": 9.587556999447579e-05,
"loss": 0.931,
"step": 411
},
{
"epoch": 1.33,
"learning_rate": 9.585526299754794e-05,
"loss": 0.9218,
"step": 412
},
{
"epoch": 1.33,
"eval_loss": 0.7483064532279968,
"eval_runtime": 858.4676,
"eval_samples_per_second": 0.607,
"eval_steps_per_second": 0.153,
"step": 412
}
],
"logging_steps": 1,
"max_steps": 3090,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 103,
"total_flos": 9.494314946301788e+18,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}