selfrag-lora / trainer_state.json
Mousaicv's picture
selfrag zephyr-7b-sft-lora
8f6f1b7
raw
history blame
No virus
80.1 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9870000710378632,
"eval_steps": 500,
"global_step": 657,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.9999885675796825e-05,
"loss": 1.2537,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 1.9999542705801295e-05,
"loss": 1.1439,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 1.9998971097855372e-05,
"loss": 0.9631,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 1.9998170865028774e-05,
"loss": 0.9216,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 1.99971420256187e-05,
"loss": 0.771,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 1.9995884603149403e-05,
"loss": 0.7876,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 1.9994398626371643e-05,
"loss": 0.5925,
"step": 7
},
{
"epoch": 0.04,
"learning_rate": 1.9992684129262038e-05,
"loss": 0.5688,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 1.9990741151022302e-05,
"loss": 0.5276,
"step": 9
},
{
"epoch": 0.05,
"learning_rate": 1.9988569736078315e-05,
"loss": 0.4483,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 1.9986169934079135e-05,
"loss": 0.4298,
"step": 11
},
{
"epoch": 0.05,
"learning_rate": 1.998354179989585e-05,
"loss": 0.3731,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 1.998068539362034e-05,
"loss": 0.4158,
"step": 13
},
{
"epoch": 0.06,
"learning_rate": 1.9977600780563863e-05,
"loss": 0.3014,
"step": 14
},
{
"epoch": 0.07,
"learning_rate": 1.997428803125562e-05,
"loss": 0.311,
"step": 15
},
{
"epoch": 0.07,
"learning_rate": 1.9970747221441084e-05,
"loss": 0.2518,
"step": 16
},
{
"epoch": 0.08,
"learning_rate": 1.9966978432080316e-05,
"loss": 0.216,
"step": 17
},
{
"epoch": 0.08,
"learning_rate": 1.996298174934608e-05,
"loss": 0.2503,
"step": 18
},
{
"epoch": 0.09,
"learning_rate": 1.995875726462189e-05,
"loss": 0.255,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 1.9954305074499916e-05,
"loss": 0.2365,
"step": 20
},
{
"epoch": 0.1,
"learning_rate": 1.994962528077878e-05,
"loss": 0.2665,
"step": 21
},
{
"epoch": 0.1,
"learning_rate": 1.9944717990461208e-05,
"loss": 0.2059,
"step": 22
},
{
"epoch": 0.1,
"learning_rate": 1.9939583315751624e-05,
"loss": 0.257,
"step": 23
},
{
"epoch": 0.11,
"learning_rate": 1.9934221374053538e-05,
"loss": 0.2509,
"step": 24
},
{
"epoch": 0.11,
"learning_rate": 1.99286322879669e-05,
"loss": 0.2405,
"step": 25
},
{
"epoch": 0.12,
"learning_rate": 1.9922816185285264e-05,
"loss": 0.2793,
"step": 26
},
{
"epoch": 0.12,
"learning_rate": 1.99167731989929e-05,
"loss": 0.2513,
"step": 27
},
{
"epoch": 0.13,
"learning_rate": 1.9910503467261724e-05,
"loss": 0.2923,
"step": 28
},
{
"epoch": 0.13,
"learning_rate": 1.9904007133448147e-05,
"loss": 0.258,
"step": 29
},
{
"epoch": 0.14,
"learning_rate": 1.989728434608981e-05,
"loss": 0.3037,
"step": 30
},
{
"epoch": 0.14,
"learning_rate": 1.9890335258902177e-05,
"loss": 0.1534,
"step": 31
},
{
"epoch": 0.15,
"learning_rate": 1.9883160030775018e-05,
"loss": 0.1594,
"step": 32
},
{
"epoch": 0.15,
"learning_rate": 1.987575882576878e-05,
"loss": 0.2293,
"step": 33
},
{
"epoch": 0.15,
"learning_rate": 1.9868131813110835e-05,
"loss": 0.2364,
"step": 34
},
{
"epoch": 0.16,
"learning_rate": 1.986027916719161e-05,
"loss": 0.1932,
"step": 35
},
{
"epoch": 0.16,
"learning_rate": 1.9852201067560607e-05,
"loss": 0.2004,
"step": 36
},
{
"epoch": 0.17,
"learning_rate": 1.9843897698922284e-05,
"loss": 0.1773,
"step": 37
},
{
"epoch": 0.17,
"learning_rate": 1.9835369251131847e-05,
"loss": 0.2215,
"step": 38
},
{
"epoch": 0.18,
"learning_rate": 1.9826615919190886e-05,
"loss": 0.1996,
"step": 39
},
{
"epoch": 0.18,
"learning_rate": 1.981763790324295e-05,
"loss": 0.1933,
"step": 40
},
{
"epoch": 0.19,
"learning_rate": 1.9808435408568938e-05,
"loss": 0.19,
"step": 41
},
{
"epoch": 0.19,
"learning_rate": 1.9799008645582424e-05,
"loss": 0.2077,
"step": 42
},
{
"epoch": 0.2,
"learning_rate": 1.9789357829824842e-05,
"loss": 0.1683,
"step": 43
},
{
"epoch": 0.2,
"learning_rate": 1.9779483181960556e-05,
"loss": 0.173,
"step": 44
},
{
"epoch": 0.2,
"learning_rate": 1.976938492777182e-05,
"loss": 0.1938,
"step": 45
},
{
"epoch": 0.21,
"learning_rate": 1.97590632981536e-05,
"loss": 0.1655,
"step": 46
},
{
"epoch": 0.21,
"learning_rate": 1.9748518529108317e-05,
"loss": 0.1899,
"step": 47
},
{
"epoch": 0.22,
"learning_rate": 1.9737750861740434e-05,
"loss": 0.2034,
"step": 48
},
{
"epoch": 0.22,
"learning_rate": 1.9726760542250946e-05,
"loss": 0.176,
"step": 49
},
{
"epoch": 0.23,
"learning_rate": 1.971554782193176e-05,
"loss": 0.125,
"step": 50
},
{
"epoch": 0.23,
"learning_rate": 1.970411295715994e-05,
"loss": 0.1539,
"step": 51
},
{
"epoch": 0.24,
"learning_rate": 1.9692456209391845e-05,
"loss": 0.1794,
"step": 52
},
{
"epoch": 0.24,
"learning_rate": 1.9680577845157155e-05,
"loss": 0.1544,
"step": 53
},
{
"epoch": 0.25,
"learning_rate": 1.9668478136052776e-05,
"loss": 0.1948,
"step": 54
},
{
"epoch": 0.25,
"learning_rate": 1.9656157358736626e-05,
"loss": 0.1566,
"step": 55
},
{
"epoch": 0.25,
"learning_rate": 1.964361579492132e-05,
"loss": 0.1895,
"step": 56
},
{
"epoch": 0.26,
"learning_rate": 1.9630853731367715e-05,
"loss": 0.1456,
"step": 57
},
{
"epoch": 0.26,
"learning_rate": 1.961787145987835e-05,
"loss": 0.1425,
"step": 58
},
{
"epoch": 0.27,
"learning_rate": 1.9604669277290805e-05,
"loss": 0.1649,
"step": 59
},
{
"epoch": 0.27,
"learning_rate": 1.959124748547088e-05,
"loss": 0.1266,
"step": 60
},
{
"epoch": 0.28,
"learning_rate": 1.9577606391305705e-05,
"loss": 0.1112,
"step": 61
},
{
"epoch": 0.28,
"learning_rate": 1.956374630669672e-05,
"loss": 0.2214,
"step": 62
},
{
"epoch": 0.29,
"learning_rate": 1.9549667548552557e-05,
"loss": 0.1718,
"step": 63
},
{
"epoch": 0.29,
"learning_rate": 1.9535370438781766e-05,
"loss": 0.1172,
"step": 64
},
{
"epoch": 0.3,
"learning_rate": 1.95208553042855e-05,
"loss": 0.1136,
"step": 65
},
{
"epoch": 0.3,
"learning_rate": 1.950612247694998e-05,
"loss": 0.1382,
"step": 66
},
{
"epoch": 0.3,
"learning_rate": 1.9491172293638968e-05,
"loss": 0.1534,
"step": 67
},
{
"epoch": 0.31,
"learning_rate": 1.9476005096186017e-05,
"loss": 0.1223,
"step": 68
},
{
"epoch": 0.31,
"learning_rate": 1.946062123138668e-05,
"loss": 0.1115,
"step": 69
},
{
"epoch": 0.32,
"learning_rate": 1.9445021050990572e-05,
"loss": 0.144,
"step": 70
},
{
"epoch": 0.32,
"learning_rate": 1.9429204911693333e-05,
"loss": 0.1439,
"step": 71
},
{
"epoch": 0.33,
"learning_rate": 1.9413173175128472e-05,
"loss": 0.1694,
"step": 72
},
{
"epoch": 0.33,
"learning_rate": 1.9396926207859085e-05,
"loss": 0.1303,
"step": 73
},
{
"epoch": 0.34,
"learning_rate": 1.9380464381369493e-05,
"loss": 0.1308,
"step": 74
},
{
"epoch": 0.34,
"learning_rate": 1.936378807205673e-05,
"loss": 0.1064,
"step": 75
},
{
"epoch": 0.35,
"learning_rate": 1.9346897661221957e-05,
"loss": 0.1334,
"step": 76
},
{
"epoch": 0.35,
"learning_rate": 1.9329793535061724e-05,
"loss": 0.1245,
"step": 77
},
{
"epoch": 0.35,
"learning_rate": 1.931247608465915e-05,
"loss": 0.1271,
"step": 78
},
{
"epoch": 0.36,
"learning_rate": 1.9294945705974975e-05,
"loss": 0.1131,
"step": 79
},
{
"epoch": 0.36,
"learning_rate": 1.927720279983852e-05,
"loss": 0.1519,
"step": 80
},
{
"epoch": 0.37,
"learning_rate": 1.92592477719385e-05,
"loss": 0.1757,
"step": 81
},
{
"epoch": 0.37,
"learning_rate": 1.924108103281377e-05,
"loss": 0.1478,
"step": 82
},
{
"epoch": 0.38,
"learning_rate": 1.9222702997843928e-05,
"loss": 0.1007,
"step": 83
},
{
"epoch": 0.38,
"learning_rate": 1.9204114087239806e-05,
"loss": 0.1531,
"step": 84
},
{
"epoch": 0.39,
"learning_rate": 1.9185314726033893e-05,
"loss": 0.0998,
"step": 85
},
{
"epoch": 0.39,
"learning_rate": 1.916630534407058e-05,
"loss": 0.1236,
"step": 86
},
{
"epoch": 0.4,
"learning_rate": 1.914708637599636e-05,
"loss": 0.1078,
"step": 87
},
{
"epoch": 0.4,
"learning_rate": 1.9127658261249872e-05,
"loss": 0.1361,
"step": 88
},
{
"epoch": 0.4,
"learning_rate": 1.910802144405186e-05,
"loss": 0.1348,
"step": 89
},
{
"epoch": 0.41,
"learning_rate": 1.908817637339503e-05,
"loss": 0.1374,
"step": 90
},
{
"epoch": 0.41,
"learning_rate": 1.9068123503033752e-05,
"loss": 0.1645,
"step": 91
},
{
"epoch": 0.42,
"learning_rate": 1.9047863291473717e-05,
"loss": 0.1,
"step": 92
},
{
"epoch": 0.42,
"learning_rate": 1.902739620196143e-05,
"loss": 0.1438,
"step": 93
},
{
"epoch": 0.43,
"learning_rate": 1.900672270247363e-05,
"loss": 0.1164,
"step": 94
},
{
"epoch": 0.43,
"learning_rate": 1.898584326570659e-05,
"loss": 0.1417,
"step": 95
},
{
"epoch": 0.44,
"learning_rate": 1.8964758369065303e-05,
"loss": 0.1174,
"step": 96
},
{
"epoch": 0.44,
"learning_rate": 1.894346849465257e-05,
"loss": 0.0978,
"step": 97
},
{
"epoch": 0.45,
"learning_rate": 1.892197412925798e-05,
"loss": 0.1157,
"step": 98
},
{
"epoch": 0.45,
"learning_rate": 1.890027576434677e-05,
"loss": 0.108,
"step": 99
},
{
"epoch": 0.45,
"learning_rate": 1.8878373896048594e-05,
"loss": 0.1282,
"step": 100
},
{
"epoch": 0.46,
"learning_rate": 1.8856269025146182e-05,
"loss": 0.0976,
"step": 101
},
{
"epoch": 0.46,
"learning_rate": 1.8833961657063887e-05,
"loss": 0.1377,
"step": 102
},
{
"epoch": 0.47,
"learning_rate": 1.881145230185612e-05,
"loss": 0.1597,
"step": 103
},
{
"epoch": 0.47,
"learning_rate": 1.8788741474195706e-05,
"loss": 0.1306,
"step": 104
},
{
"epoch": 0.48,
"learning_rate": 1.8765829693362097e-05,
"loss": 0.1166,
"step": 105
},
{
"epoch": 0.48,
"learning_rate": 1.874271748322951e-05,
"loss": 0.1265,
"step": 106
},
{
"epoch": 0.49,
"learning_rate": 1.8719405372254947e-05,
"loss": 0.1464,
"step": 107
},
{
"epoch": 0.49,
"learning_rate": 1.869589389346611e-05,
"loss": 0.1258,
"step": 108
},
{
"epoch": 0.5,
"learning_rate": 1.8672183584449217e-05,
"loss": 0.1114,
"step": 109
},
{
"epoch": 0.5,
"learning_rate": 1.8648274987336706e-05,
"loss": 0.1234,
"step": 110
},
{
"epoch": 0.5,
"learning_rate": 1.8624168648794833e-05,
"loss": 0.1266,
"step": 111
},
{
"epoch": 0.51,
"learning_rate": 1.859986512001119e-05,
"loss": 0.1162,
"step": 112
},
{
"epoch": 0.51,
"learning_rate": 1.8575364956682097e-05,
"loss": 0.1484,
"step": 113
},
{
"epoch": 0.52,
"learning_rate": 1.8550668718999873e-05,
"loss": 0.127,
"step": 114
},
{
"epoch": 0.52,
"learning_rate": 1.8525776971640065e-05,
"loss": 0.1425,
"step": 115
},
{
"epoch": 0.53,
"learning_rate": 1.8500690283748502e-05,
"loss": 0.1416,
"step": 116
},
{
"epoch": 0.53,
"learning_rate": 1.8475409228928314e-05,
"loss": 0.1261,
"step": 117
},
{
"epoch": 0.54,
"learning_rate": 1.8449934385226784e-05,
"loss": 0.1208,
"step": 118
},
{
"epoch": 0.54,
"learning_rate": 1.842426633512215e-05,
"loss": 0.1326,
"step": 119
},
{
"epoch": 0.55,
"learning_rate": 1.83984056655103e-05,
"loss": 0.1141,
"step": 120
},
{
"epoch": 0.55,
"learning_rate": 1.837235296769131e-05,
"loss": 0.1275,
"step": 121
},
{
"epoch": 0.55,
"learning_rate": 1.834610883735597e-05,
"loss": 0.1379,
"step": 122
},
{
"epoch": 0.56,
"learning_rate": 1.831967387457214e-05,
"loss": 0.0989,
"step": 123
},
{
"epoch": 0.56,
"learning_rate": 1.8293048683771023e-05,
"loss": 0.1165,
"step": 124
},
{
"epoch": 0.57,
"learning_rate": 1.8266233873733376e-05,
"loss": 0.1221,
"step": 125
},
{
"epoch": 0.57,
"learning_rate": 1.8239230057575542e-05,
"loss": 0.0941,
"step": 126
},
{
"epoch": 0.58,
"learning_rate": 1.8212037852735487e-05,
"loss": 0.1147,
"step": 127
},
{
"epoch": 0.58,
"learning_rate": 1.8184657880958637e-05,
"loss": 0.1012,
"step": 128
},
{
"epoch": 0.59,
"learning_rate": 1.815709076828368e-05,
"loss": 0.0999,
"step": 129
},
{
"epoch": 0.59,
"learning_rate": 1.8129337145028257e-05,
"loss": 0.1083,
"step": 130
},
{
"epoch": 0.6,
"learning_rate": 1.810139764577454e-05,
"loss": 0.1,
"step": 131
},
{
"epoch": 0.6,
"learning_rate": 1.8073272909354727e-05,
"loss": 0.1283,
"step": 132
},
{
"epoch": 0.6,
"learning_rate": 1.8044963578836437e-05,
"loss": 0.1194,
"step": 133
},
{
"epoch": 0.61,
"learning_rate": 1.8016470301507995e-05,
"loss": 0.1098,
"step": 134
},
{
"epoch": 0.61,
"learning_rate": 1.798779372886365e-05,
"loss": 0.1099,
"step": 135
},
{
"epoch": 0.62,
"learning_rate": 1.7958934516588665e-05,
"loss": 0.0984,
"step": 136
},
{
"epoch": 0.62,
"learning_rate": 1.7929893324544333e-05,
"loss": 0.1062,
"step": 137
},
{
"epoch": 0.63,
"learning_rate": 1.7900670816752875e-05,
"loss": 0.1054,
"step": 138
},
{
"epoch": 0.63,
"learning_rate": 1.7871267661382278e-05,
"loss": 0.0968,
"step": 139
},
{
"epoch": 0.64,
"learning_rate": 1.7841684530731006e-05,
"loss": 0.0918,
"step": 140
},
{
"epoch": 0.64,
"learning_rate": 1.7811922101212622e-05,
"loss": 0.1491,
"step": 141
},
{
"epoch": 0.65,
"learning_rate": 1.778198105334034e-05,
"loss": 0.0946,
"step": 142
},
{
"epoch": 0.65,
"learning_rate": 1.775186207171144e-05,
"loss": 0.093,
"step": 143
},
{
"epoch": 0.65,
"learning_rate": 1.7721565844991643e-05,
"loss": 0.1105,
"step": 144
},
{
"epoch": 0.66,
"learning_rate": 1.7691093065899344e-05,
"loss": 0.095,
"step": 145
},
{
"epoch": 0.66,
"learning_rate": 1.766044443118978e-05,
"loss": 0.1255,
"step": 146
},
{
"epoch": 0.67,
"learning_rate": 1.7629620641639102e-05,
"loss": 0.0982,
"step": 147
},
{
"epoch": 0.67,
"learning_rate": 1.7598622402028344e-05,
"loss": 0.1035,
"step": 148
},
{
"epoch": 0.68,
"learning_rate": 1.756745042112731e-05,
"loss": 0.0932,
"step": 149
},
{
"epoch": 0.68,
"learning_rate": 1.753610541167838e-05,
"loss": 0.0954,
"step": 150
},
{
"epoch": 0.69,
"learning_rate": 1.75045880903802e-05,
"loss": 0.1083,
"step": 151
},
{
"epoch": 0.69,
"learning_rate": 1.74728991778713e-05,
"loss": 0.1025,
"step": 152
},
{
"epoch": 0.7,
"learning_rate": 1.744103939871361e-05,
"loss": 0.1337,
"step": 153
},
{
"epoch": 0.7,
"learning_rate": 1.7409009481375905e-05,
"loss": 0.1083,
"step": 154
},
{
"epoch": 0.7,
"learning_rate": 1.7376810158217142e-05,
"loss": 0.1003,
"step": 155
},
{
"epoch": 0.71,
"learning_rate": 1.7344442165469714e-05,
"loss": 0.1212,
"step": 156
},
{
"epoch": 0.71,
"learning_rate": 1.7311906243222613e-05,
"loss": 0.1267,
"step": 157
},
{
"epoch": 0.72,
"learning_rate": 1.7279203135404522e-05,
"loss": 0.1225,
"step": 158
},
{
"epoch": 0.72,
"learning_rate": 1.7246333589766786e-05,
"loss": 0.0981,
"step": 159
},
{
"epoch": 0.73,
"learning_rate": 1.7213298357866326e-05,
"loss": 0.1342,
"step": 160
},
{
"epoch": 0.73,
"learning_rate": 1.7180098195048458e-05,
"loss": 0.1031,
"step": 161
},
{
"epoch": 0.74,
"learning_rate": 1.7146733860429614e-05,
"loss": 0.1232,
"step": 162
},
{
"epoch": 0.74,
"learning_rate": 1.7113206116879983e-05,
"loss": 0.1193,
"step": 163
},
{
"epoch": 0.75,
"learning_rate": 1.7079515731006085e-05,
"loss": 0.0976,
"step": 164
},
{
"epoch": 0.75,
"learning_rate": 1.7045663473133215e-05,
"loss": 0.1021,
"step": 165
},
{
"epoch": 0.75,
"learning_rate": 1.7011650117287868e-05,
"loss": 0.1116,
"step": 166
},
{
"epoch": 0.76,
"learning_rate": 1.6977476441179993e-05,
"loss": 0.1164,
"step": 167
},
{
"epoch": 0.76,
"learning_rate": 1.6943143226185252e-05,
"loss": 0.1145,
"step": 168
},
{
"epoch": 0.77,
"learning_rate": 1.6908651257327138e-05,
"loss": 0.0901,
"step": 169
},
{
"epoch": 0.77,
"learning_rate": 1.6874001323259012e-05,
"loss": 0.0792,
"step": 170
},
{
"epoch": 0.78,
"learning_rate": 1.683919421624611e-05,
"loss": 0.0992,
"step": 171
},
{
"epoch": 0.78,
"learning_rate": 1.680423073214737e-05,
"loss": 0.107,
"step": 172
},
{
"epoch": 0.79,
"learning_rate": 1.67691116703973e-05,
"loss": 0.1006,
"step": 173
},
{
"epoch": 0.79,
"learning_rate": 1.6733837833987634e-05,
"loss": 0.0988,
"step": 174
},
{
"epoch": 0.8,
"learning_rate": 1.669841002944903e-05,
"loss": 0.1153,
"step": 175
},
{
"epoch": 0.8,
"learning_rate": 1.6662829066832595e-05,
"loss": 0.1173,
"step": 176
},
{
"epoch": 0.8,
"learning_rate": 1.6627095759691364e-05,
"loss": 0.1,
"step": 177
},
{
"epoch": 0.81,
"learning_rate": 1.659121092506171e-05,
"loss": 0.1007,
"step": 178
},
{
"epoch": 0.81,
"learning_rate": 1.6555175383444658e-05,
"loss": 0.1124,
"step": 179
},
{
"epoch": 0.82,
"learning_rate": 1.6518989958787126e-05,
"loss": 0.1206,
"step": 180
},
{
"epoch": 0.82,
"learning_rate": 1.648265547846308e-05,
"loss": 0.0997,
"step": 181
},
{
"epoch": 0.83,
"learning_rate": 1.6446172773254628e-05,
"loss": 0.0865,
"step": 182
},
{
"epoch": 0.83,
"learning_rate": 1.6409542677333007e-05,
"loss": 0.1221,
"step": 183
},
{
"epoch": 0.84,
"learning_rate": 1.6372766028239523e-05,
"loss": 0.0963,
"step": 184
},
{
"epoch": 0.84,
"learning_rate": 1.6335843666866388e-05,
"loss": 0.1199,
"step": 185
},
{
"epoch": 0.85,
"learning_rate": 1.6298776437437526e-05,
"loss": 0.1115,
"step": 186
},
{
"epoch": 0.85,
"learning_rate": 1.626156518748922e-05,
"loss": 0.1016,
"step": 187
},
{
"epoch": 0.85,
"learning_rate": 1.6224210767850773e-05,
"loss": 0.1037,
"step": 188
},
{
"epoch": 0.86,
"learning_rate": 1.6186714032625036e-05,
"loss": 0.1056,
"step": 189
},
{
"epoch": 0.86,
"learning_rate": 1.6149075839168886e-05,
"loss": 0.1125,
"step": 190
},
{
"epoch": 0.87,
"learning_rate": 1.611129704807362e-05,
"loss": 0.0969,
"step": 191
},
{
"epoch": 0.87,
"learning_rate": 1.6073378523145272e-05,
"loss": 0.1198,
"step": 192
},
{
"epoch": 0.88,
"learning_rate": 1.6035321131384872e-05,
"loss": 0.1097,
"step": 193
},
{
"epoch": 0.88,
"learning_rate": 1.599712574296862e-05,
"loss": 0.0976,
"step": 194
},
{
"epoch": 0.89,
"learning_rate": 1.595879323122798e-05,
"loss": 0.0937,
"step": 195
},
{
"epoch": 0.89,
"learning_rate": 1.592032447262973e-05,
"loss": 0.1166,
"step": 196
},
{
"epoch": 0.9,
"learning_rate": 1.5881720346755904e-05,
"loss": 0.0905,
"step": 197
},
{
"epoch": 0.9,
"learning_rate": 1.5842981736283686e-05,
"loss": 0.0879,
"step": 198
},
{
"epoch": 0.9,
"learning_rate": 1.5804109526965232e-05,
"loss": 0.127,
"step": 199
},
{
"epoch": 0.91,
"learning_rate": 1.576510460760741e-05,
"loss": 0.1016,
"step": 200
},
{
"epoch": 0.91,
"learning_rate": 1.572596787005149e-05,
"loss": 0.0996,
"step": 201
},
{
"epoch": 0.92,
"learning_rate": 1.568670020915274e-05,
"loss": 0.1011,
"step": 202
},
{
"epoch": 0.92,
"learning_rate": 1.564730252275996e-05,
"loss": 0.089,
"step": 203
},
{
"epoch": 0.93,
"learning_rate": 1.560777571169498e-05,
"loss": 0.1112,
"step": 204
},
{
"epoch": 0.93,
"learning_rate": 1.556812067973203e-05,
"loss": 0.1025,
"step": 205
},
{
"epoch": 0.94,
"learning_rate": 1.55283383335771e-05,
"loss": 0.1064,
"step": 206
},
{
"epoch": 0.94,
"learning_rate": 1.5488429582847194e-05,
"loss": 0.0977,
"step": 207
},
{
"epoch": 0.95,
"learning_rate": 1.5448395340049538e-05,
"loss": 0.0963,
"step": 208
},
{
"epoch": 0.95,
"learning_rate": 1.5408236520560707e-05,
"loss": 0.089,
"step": 209
},
{
"epoch": 0.95,
"learning_rate": 1.536795404260572e-05,
"loss": 0.1107,
"step": 210
},
{
"epoch": 0.96,
"learning_rate": 1.5327548827237008e-05,
"loss": 0.1046,
"step": 211
},
{
"epoch": 0.96,
"learning_rate": 1.528702179831338e-05,
"loss": 0.0926,
"step": 212
},
{
"epoch": 0.97,
"learning_rate": 1.5246373882478899e-05,
"loss": 0.1009,
"step": 213
},
{
"epoch": 0.97,
"learning_rate": 1.5205606009141683e-05,
"loss": 0.0965,
"step": 214
},
{
"epoch": 0.98,
"learning_rate": 1.5164719110452652e-05,
"loss": 0.1004,
"step": 215
},
{
"epoch": 0.98,
"learning_rate": 1.512371412128424e-05,
"loss": 0.0771,
"step": 216
},
{
"epoch": 0.99,
"learning_rate": 1.5082591979208977e-05,
"loss": 0.0901,
"step": 217
},
{
"epoch": 0.99,
"learning_rate": 1.5041353624478094e-05,
"loss": 0.0993,
"step": 218
},
{
"epoch": 1.0,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.1001,
"step": 219
},
{
"epoch": 1.0,
"eval_loss": 0.10058634728193283,
"eval_runtime": 1063.6983,
"eval_samples_per_second": 4.412,
"eval_steps_per_second": 2.206,
"step": 219
},
{
"epoch": 1.0,
"learning_rate": 1.4958532051318731e-05,
"loss": 0.091,
"step": 220
},
{
"epoch": 1.0,
"learning_rate": 1.4916950726592322e-05,
"loss": 0.0958,
"step": 221
},
{
"epoch": 1.01,
"learning_rate": 1.4875256976571135e-05,
"loss": 0.0909,
"step": 222
},
{
"epoch": 1.01,
"learning_rate": 1.4833451754576122e-05,
"loss": 0.0759,
"step": 223
},
{
"epoch": 1.02,
"learning_rate": 1.4791536016477021e-05,
"loss": 0.0987,
"step": 224
},
{
"epoch": 1.02,
"learning_rate": 1.4749510720670506e-05,
"loss": 0.0773,
"step": 225
},
{
"epoch": 1.03,
"learning_rate": 1.4707376828058264e-05,
"loss": 0.0942,
"step": 226
},
{
"epoch": 1.03,
"learning_rate": 1.4665135302025036e-05,
"loss": 0.081,
"step": 227
},
{
"epoch": 1.04,
"learning_rate": 1.4622787108416585e-05,
"loss": 0.0899,
"step": 228
},
{
"epoch": 1.04,
"learning_rate": 1.4580333215517608e-05,
"loss": 0.0945,
"step": 229
},
{
"epoch": 1.05,
"learning_rate": 1.45377745940296e-05,
"loss": 0.0787,
"step": 230
},
{
"epoch": 1.05,
"learning_rate": 1.449511221704866e-05,
"loss": 0.0965,
"step": 231
},
{
"epoch": 1.05,
"learning_rate": 1.4452347060043239e-05,
"loss": 0.0831,
"step": 232
},
{
"epoch": 1.06,
"learning_rate": 1.4409480100831834e-05,
"loss": 0.094,
"step": 233
},
{
"epoch": 1.06,
"learning_rate": 1.4366512319560642e-05,
"loss": 0.1029,
"step": 234
},
{
"epoch": 1.07,
"learning_rate": 1.4323444698681126e-05,
"loss": 0.0995,
"step": 235
},
{
"epoch": 1.07,
"learning_rate": 1.428027822292758e-05,
"loss": 0.0839,
"step": 236
},
{
"epoch": 1.08,
"learning_rate": 1.423701387929459e-05,
"loss": 0.0919,
"step": 237
},
{
"epoch": 1.08,
"learning_rate": 1.419365265701448e-05,
"loss": 0.091,
"step": 238
},
{
"epoch": 1.09,
"learning_rate": 1.4150195547534686e-05,
"loss": 0.1023,
"step": 239
},
{
"epoch": 1.09,
"learning_rate": 1.4106643544495092e-05,
"loss": 0.0821,
"step": 240
},
{
"epoch": 1.1,
"learning_rate": 1.4062997643705308e-05,
"loss": 0.0897,
"step": 241
},
{
"epoch": 1.1,
"learning_rate": 1.4019258843121893e-05,
"loss": 0.106,
"step": 242
},
{
"epoch": 1.1,
"learning_rate": 1.3975428142825562e-05,
"loss": 0.0902,
"step": 243
},
{
"epoch": 1.11,
"learning_rate": 1.3931506544998283e-05,
"loss": 0.0952,
"step": 244
},
{
"epoch": 1.11,
"learning_rate": 1.3887495053900398e-05,
"loss": 0.1105,
"step": 245
},
{
"epoch": 1.12,
"learning_rate": 1.3843394675847635e-05,
"loss": 0.0892,
"step": 246
},
{
"epoch": 1.12,
"learning_rate": 1.3799206419188104e-05,
"loss": 0.0953,
"step": 247
},
{
"epoch": 1.13,
"learning_rate": 1.3754931294279264e-05,
"loss": 0.0891,
"step": 248
},
{
"epoch": 1.13,
"learning_rate": 1.3710570313464778e-05,
"loss": 0.0972,
"step": 249
},
{
"epoch": 1.14,
"learning_rate": 1.3666124491051408e-05,
"loss": 0.1029,
"step": 250
},
{
"epoch": 1.14,
"learning_rate": 1.3621594843285801e-05,
"loss": 0.0975,
"step": 251
},
{
"epoch": 1.15,
"learning_rate": 1.3576982388331258e-05,
"loss": 0.0863,
"step": 252
},
{
"epoch": 1.15,
"learning_rate": 1.3532288146244446e-05,
"loss": 0.0879,
"step": 253
},
{
"epoch": 1.15,
"learning_rate": 1.3487513138952092e-05,
"loss": 0.0879,
"step": 254
},
{
"epoch": 1.16,
"learning_rate": 1.3442658390227604e-05,
"loss": 0.1132,
"step": 255
},
{
"epoch": 1.16,
"learning_rate": 1.3397724925667657e-05,
"loss": 0.0877,
"step": 256
},
{
"epoch": 1.17,
"learning_rate": 1.3352713772668766e-05,
"loss": 0.0793,
"step": 257
},
{
"epoch": 1.17,
"learning_rate": 1.3307625960403763e-05,
"loss": 0.0964,
"step": 258
},
{
"epoch": 1.18,
"learning_rate": 1.3262462519798294e-05,
"loss": 0.1016,
"step": 259
},
{
"epoch": 1.18,
"learning_rate": 1.321722448350723e-05,
"loss": 0.0865,
"step": 260
},
{
"epoch": 1.19,
"learning_rate": 1.3171912885891063e-05,
"loss": 0.0847,
"step": 261
},
{
"epoch": 1.19,
"learning_rate": 1.3126528762992248e-05,
"loss": 0.0942,
"step": 262
},
{
"epoch": 1.2,
"learning_rate": 1.3081073152511525e-05,
"loss": 0.0873,
"step": 263
},
{
"epoch": 1.2,
"learning_rate": 1.3035547093784187e-05,
"loss": 0.1064,
"step": 264
},
{
"epoch": 1.2,
"learning_rate": 1.2989951627756306e-05,
"loss": 0.0818,
"step": 265
},
{
"epoch": 1.21,
"learning_rate": 1.2944287796960949e-05,
"loss": 0.0976,
"step": 266
},
{
"epoch": 1.21,
"learning_rate": 1.2898556645494327e-05,
"loss": 0.0864,
"step": 267
},
{
"epoch": 1.22,
"learning_rate": 1.2852759218991935e-05,
"loss": 0.0918,
"step": 268
},
{
"epoch": 1.22,
"learning_rate": 1.2806896564604627e-05,
"loss": 0.0966,
"step": 269
},
{
"epoch": 1.23,
"learning_rate": 1.2760969730974692e-05,
"loss": 0.0872,
"step": 270
},
{
"epoch": 1.23,
"learning_rate": 1.2714979768211854e-05,
"loss": 0.0814,
"step": 271
},
{
"epoch": 1.24,
"learning_rate": 1.2668927727869292e-05,
"loss": 0.0898,
"step": 272
},
{
"epoch": 1.24,
"learning_rate": 1.2622814662919562e-05,
"loss": 0.0823,
"step": 273
},
{
"epoch": 1.25,
"learning_rate": 1.2576641627730548e-05,
"loss": 0.0926,
"step": 274
},
{
"epoch": 1.25,
"learning_rate": 1.2530409678041342e-05,
"loss": 0.0844,
"step": 275
},
{
"epoch": 1.25,
"learning_rate": 1.2484119870938102e-05,
"loss": 0.0949,
"step": 276
},
{
"epoch": 1.26,
"learning_rate": 1.2437773264829898e-05,
"loss": 0.087,
"step": 277
},
{
"epoch": 1.26,
"learning_rate": 1.2391370919424485e-05,
"loss": 0.0862,
"step": 278
},
{
"epoch": 1.27,
"learning_rate": 1.2344913895704099e-05,
"loss": 0.1098,
"step": 279
},
{
"epoch": 1.27,
"learning_rate": 1.2298403255901185e-05,
"loss": 0.0773,
"step": 280
},
{
"epoch": 1.28,
"learning_rate": 1.2251840063474108e-05,
"loss": 0.0907,
"step": 281
},
{
"epoch": 1.28,
"learning_rate": 1.2205225383082844e-05,
"loss": 0.1035,
"step": 282
},
{
"epoch": 1.29,
"learning_rate": 1.2158560280564627e-05,
"loss": 0.0833,
"step": 283
},
{
"epoch": 1.29,
"learning_rate": 1.2111845822909596e-05,
"loss": 0.1147,
"step": 284
},
{
"epoch": 1.3,
"learning_rate": 1.2065083078236375e-05,
"loss": 0.0753,
"step": 285
},
{
"epoch": 1.3,
"learning_rate": 1.2018273115767673e-05,
"loss": 0.1022,
"step": 286
},
{
"epoch": 1.3,
"learning_rate": 1.1971417005805818e-05,
"loss": 0.0887,
"step": 287
},
{
"epoch": 1.31,
"learning_rate": 1.19245158197083e-05,
"loss": 0.0874,
"step": 288
},
{
"epoch": 1.31,
"learning_rate": 1.1877570629863267e-05,
"loss": 0.0867,
"step": 289
},
{
"epoch": 1.32,
"learning_rate": 1.1830582509664997e-05,
"loss": 0.0775,
"step": 290
},
{
"epoch": 1.32,
"learning_rate": 1.1783552533489372e-05,
"loss": 0.0743,
"step": 291
},
{
"epoch": 1.33,
"learning_rate": 1.1736481776669307e-05,
"loss": 0.1133,
"step": 292
},
{
"epoch": 1.33,
"learning_rate": 1.1689371315470151e-05,
"loss": 0.0895,
"step": 293
},
{
"epoch": 1.34,
"learning_rate": 1.164222222706509e-05,
"loss": 0.0853,
"step": 294
},
{
"epoch": 1.34,
"learning_rate": 1.1595035589510522e-05,
"loss": 0.1079,
"step": 295
},
{
"epoch": 1.35,
"learning_rate": 1.1547812481721387e-05,
"loss": 0.098,
"step": 296
},
{
"epoch": 1.35,
"learning_rate": 1.1500553983446527e-05,
"loss": 0.0954,
"step": 297
},
{
"epoch": 1.35,
"learning_rate": 1.1453261175243972e-05,
"loss": 0.0821,
"step": 298
},
{
"epoch": 1.36,
"learning_rate": 1.140593513845624e-05,
"loss": 0.0968,
"step": 299
},
{
"epoch": 1.36,
"learning_rate": 1.135857695518563e-05,
"loss": 0.0868,
"step": 300
},
{
"epoch": 1.37,
"learning_rate": 1.1311187708269442e-05,
"loss": 0.0861,
"step": 301
},
{
"epoch": 1.37,
"learning_rate": 1.1263768481255264e-05,
"loss": 0.0734,
"step": 302
},
{
"epoch": 1.38,
"learning_rate": 1.1216320358376158e-05,
"loss": 0.1116,
"step": 303
},
{
"epoch": 1.38,
"learning_rate": 1.1168844424525902e-05,
"loss": 0.0836,
"step": 304
},
{
"epoch": 1.39,
"learning_rate": 1.1121341765234146e-05,
"loss": 0.0913,
"step": 305
},
{
"epoch": 1.39,
"learning_rate": 1.1073813466641633e-05,
"loss": 0.0841,
"step": 306
},
{
"epoch": 1.4,
"learning_rate": 1.1026260615475333e-05,
"loss": 0.094,
"step": 307
},
{
"epoch": 1.4,
"learning_rate": 1.0978684299023608e-05,
"loss": 0.0954,
"step": 308
},
{
"epoch": 1.4,
"learning_rate": 1.0931085605111354e-05,
"loss": 0.0892,
"step": 309
},
{
"epoch": 1.41,
"learning_rate": 1.088346562207512e-05,
"loss": 0.1037,
"step": 310
},
{
"epoch": 1.41,
"learning_rate": 1.0835825438738232e-05,
"loss": 0.0885,
"step": 311
},
{
"epoch": 1.42,
"learning_rate": 1.0788166144385888e-05,
"loss": 0.0872,
"step": 312
},
{
"epoch": 1.42,
"learning_rate": 1.0740488828740258e-05,
"loss": 0.0845,
"step": 313
},
{
"epoch": 1.43,
"learning_rate": 1.0692794581935566e-05,
"loss": 0.1027,
"step": 314
},
{
"epoch": 1.43,
"learning_rate": 1.0645084494493166e-05,
"loss": 0.1171,
"step": 315
},
{
"epoch": 1.44,
"learning_rate": 1.0597359657296602e-05,
"loss": 0.1043,
"step": 316
},
{
"epoch": 1.44,
"learning_rate": 1.054962116156667e-05,
"loss": 0.0894,
"step": 317
},
{
"epoch": 1.45,
"learning_rate": 1.0501870098836473e-05,
"loss": 0.0916,
"step": 318
},
{
"epoch": 1.45,
"learning_rate": 1.0454107560926444e-05,
"loss": 0.0836,
"step": 319
},
{
"epoch": 1.45,
"learning_rate": 1.0406334639919404e-05,
"loss": 0.0926,
"step": 320
},
{
"epoch": 1.46,
"learning_rate": 1.0358552428135576e-05,
"loss": 0.1158,
"step": 321
},
{
"epoch": 1.46,
"learning_rate": 1.031076201810762e-05,
"loss": 0.0906,
"step": 322
},
{
"epoch": 1.47,
"learning_rate": 1.0262964502555643e-05,
"loss": 0.093,
"step": 323
},
{
"epoch": 1.47,
"learning_rate": 1.0215160974362224e-05,
"loss": 0.0844,
"step": 324
},
{
"epoch": 1.48,
"learning_rate": 1.0167352526547416e-05,
"loss": 0.0869,
"step": 325
},
{
"epoch": 1.48,
"learning_rate": 1.0119540252243755e-05,
"loss": 0.0916,
"step": 326
},
{
"epoch": 1.49,
"learning_rate": 1.0071725244671281e-05,
"loss": 0.096,
"step": 327
},
{
"epoch": 1.49,
"learning_rate": 1.0023908597112514e-05,
"loss": 0.0859,
"step": 328
},
{
"epoch": 1.5,
"learning_rate": 9.976091402887487e-06,
"loss": 0.1097,
"step": 329
},
{
"epoch": 1.5,
"learning_rate": 9.928274755328724e-06,
"loss": 0.077,
"step": 330
},
{
"epoch": 1.5,
"learning_rate": 9.880459747756247e-06,
"loss": 0.0881,
"step": 331
},
{
"epoch": 1.51,
"learning_rate": 9.83264747345259e-06,
"loss": 0.0955,
"step": 332
},
{
"epoch": 1.51,
"learning_rate": 9.78483902563778e-06,
"loss": 0.0815,
"step": 333
},
{
"epoch": 1.52,
"learning_rate": 9.737035497444362e-06,
"loss": 0.0778,
"step": 334
},
{
"epoch": 1.52,
"learning_rate": 9.689237981892381e-06,
"loss": 0.0894,
"step": 335
},
{
"epoch": 1.53,
"learning_rate": 9.641447571864429e-06,
"loss": 0.0892,
"step": 336
},
{
"epoch": 1.53,
"learning_rate": 9.5936653600806e-06,
"loss": 0.0925,
"step": 337
},
{
"epoch": 1.54,
"learning_rate": 9.545892439073561e-06,
"loss": 0.1305,
"step": 338
},
{
"epoch": 1.54,
"learning_rate": 9.49812990116353e-06,
"loss": 0.1104,
"step": 339
},
{
"epoch": 1.55,
"learning_rate": 9.450378838433332e-06,
"loss": 0.0779,
"step": 340
},
{
"epoch": 1.55,
"learning_rate": 9.402640342703401e-06,
"loss": 0.0886,
"step": 341
},
{
"epoch": 1.55,
"learning_rate": 9.354915505506839e-06,
"loss": 0.1002,
"step": 342
},
{
"epoch": 1.56,
"learning_rate": 9.307205418064436e-06,
"loss": 0.0833,
"step": 343
},
{
"epoch": 1.56,
"learning_rate": 9.259511171259747e-06,
"loss": 0.0915,
"step": 344
},
{
"epoch": 1.57,
"learning_rate": 9.211833855614115e-06,
"loss": 0.0887,
"step": 345
},
{
"epoch": 1.57,
"learning_rate": 9.164174561261771e-06,
"loss": 0.0946,
"step": 346
},
{
"epoch": 1.58,
"learning_rate": 9.116534377924882e-06,
"loss": 0.0942,
"step": 347
},
{
"epoch": 1.58,
"learning_rate": 9.068914394888651e-06,
"loss": 0.0901,
"step": 348
},
{
"epoch": 1.59,
"learning_rate": 9.021315700976397e-06,
"loss": 0.0811,
"step": 349
},
{
"epoch": 1.59,
"learning_rate": 8.973739384524674e-06,
"loss": 0.0924,
"step": 350
},
{
"epoch": 1.6,
"learning_rate": 8.92618653335837e-06,
"loss": 0.089,
"step": 351
},
{
"epoch": 1.6,
"learning_rate": 8.87865823476586e-06,
"loss": 0.0971,
"step": 352
},
{
"epoch": 1.6,
"learning_rate": 8.831155575474103e-06,
"loss": 0.0826,
"step": 353
},
{
"epoch": 1.61,
"learning_rate": 8.783679641623845e-06,
"loss": 0.093,
"step": 354
},
{
"epoch": 1.61,
"learning_rate": 8.73623151874474e-06,
"loss": 0.1005,
"step": 355
},
{
"epoch": 1.62,
"learning_rate": 8.688812291730565e-06,
"loss": 0.0839,
"step": 356
},
{
"epoch": 1.62,
"learning_rate": 8.641423044814375e-06,
"loss": 0.0867,
"step": 357
},
{
"epoch": 1.63,
"learning_rate": 8.594064861543761e-06,
"loss": 0.1104,
"step": 358
},
{
"epoch": 1.63,
"learning_rate": 8.54673882475603e-06,
"loss": 0.084,
"step": 359
},
{
"epoch": 1.64,
"learning_rate": 8.499446016553475e-06,
"loss": 0.0751,
"step": 360
},
{
"epoch": 1.64,
"learning_rate": 8.452187518278615e-06,
"loss": 0.1002,
"step": 361
},
{
"epoch": 1.65,
"learning_rate": 8.404964410489485e-06,
"loss": 0.0707,
"step": 362
},
{
"epoch": 1.65,
"learning_rate": 8.357777772934914e-06,
"loss": 0.0877,
"step": 363
},
{
"epoch": 1.65,
"learning_rate": 8.310628684529856e-06,
"loss": 0.0888,
"step": 364
},
{
"epoch": 1.66,
"learning_rate": 8.263518223330698e-06,
"loss": 0.0877,
"step": 365
},
{
"epoch": 1.66,
"learning_rate": 8.216447466510633e-06,
"loss": 0.0852,
"step": 366
},
{
"epoch": 1.67,
"learning_rate": 8.169417490335008e-06,
"loss": 0.082,
"step": 367
},
{
"epoch": 1.67,
"learning_rate": 8.12242937013674e-06,
"loss": 0.0881,
"step": 368
},
{
"epoch": 1.68,
"learning_rate": 8.075484180291702e-06,
"loss": 0.0766,
"step": 369
},
{
"epoch": 1.68,
"learning_rate": 8.028582994194185e-06,
"loss": 0.0882,
"step": 370
},
{
"epoch": 1.69,
"learning_rate": 7.981726884232328e-06,
"loss": 0.103,
"step": 371
},
{
"epoch": 1.69,
"learning_rate": 7.93491692176363e-06,
"loss": 0.1006,
"step": 372
},
{
"epoch": 1.7,
"learning_rate": 7.888154177090406e-06,
"loss": 0.0961,
"step": 373
},
{
"epoch": 1.7,
"learning_rate": 7.841439719435378e-06,
"loss": 0.1091,
"step": 374
},
{
"epoch": 1.7,
"learning_rate": 7.79477461691716e-06,
"loss": 0.0939,
"step": 375
},
{
"epoch": 1.71,
"learning_rate": 7.748159936525896e-06,
"loss": 0.092,
"step": 376
},
{
"epoch": 1.71,
"learning_rate": 7.701596744098818e-06,
"loss": 0.1116,
"step": 377
},
{
"epoch": 1.72,
"learning_rate": 7.655086104295904e-06,
"loss": 0.0849,
"step": 378
},
{
"epoch": 1.72,
"learning_rate": 7.608629080575518e-06,
"loss": 0.0696,
"step": 379
},
{
"epoch": 1.73,
"learning_rate": 7.5622267351701065e-06,
"loss": 0.0829,
"step": 380
},
{
"epoch": 1.73,
"learning_rate": 7.5158801290619e-06,
"loss": 0.0976,
"step": 381
},
{
"epoch": 1.74,
"learning_rate": 7.469590321958663e-06,
"loss": 0.0943,
"step": 382
},
{
"epoch": 1.74,
"learning_rate": 7.423358372269456e-06,
"loss": 0.0843,
"step": 383
},
{
"epoch": 1.75,
"learning_rate": 7.377185337080443e-06,
"loss": 0.0894,
"step": 384
},
{
"epoch": 1.75,
"learning_rate": 7.331072272130713e-06,
"loss": 0.089,
"step": 385
},
{
"epoch": 1.75,
"learning_rate": 7.285020231788149e-06,
"loss": 0.0771,
"step": 386
},
{
"epoch": 1.76,
"learning_rate": 7.239030269025311e-06,
"loss": 0.0879,
"step": 387
},
{
"epoch": 1.76,
"learning_rate": 7.193103435395378e-06,
"loss": 0.1241,
"step": 388
},
{
"epoch": 1.77,
"learning_rate": 7.147240781008068e-06,
"loss": 0.0782,
"step": 389
},
{
"epoch": 1.77,
"learning_rate": 7.1014433545056785e-06,
"loss": 0.0958,
"step": 390
},
{
"epoch": 1.78,
"learning_rate": 7.0557122030390545e-06,
"loss": 0.0877,
"step": 391
},
{
"epoch": 1.78,
"learning_rate": 7.0100483722436985e-06,
"loss": 0.0867,
"step": 392
},
{
"epoch": 1.79,
"learning_rate": 6.964452906215815e-06,
"loss": 0.075,
"step": 393
},
{
"epoch": 1.79,
"learning_rate": 6.918926847488477e-06,
"loss": 0.0921,
"step": 394
},
{
"epoch": 1.8,
"learning_rate": 6.873471237007754e-06,
"loss": 0.1001,
"step": 395
},
{
"epoch": 1.8,
"learning_rate": 6.8280871141089415e-06,
"loss": 0.0913,
"step": 396
},
{
"epoch": 1.8,
"learning_rate": 6.782775516492772e-06,
"loss": 0.1061,
"step": 397
},
{
"epoch": 1.81,
"learning_rate": 6.73753748020171e-06,
"loss": 0.0903,
"step": 398
},
{
"epoch": 1.81,
"learning_rate": 6.692374039596241e-06,
"loss": 0.0819,
"step": 399
},
{
"epoch": 1.82,
"learning_rate": 6.64728622733124e-06,
"loss": 0.096,
"step": 400
},
{
"epoch": 1.82,
"learning_rate": 6.602275074332345e-06,
"loss": 0.0983,
"step": 401
},
{
"epoch": 1.83,
"learning_rate": 6.5573416097724e-06,
"loss": 0.0965,
"step": 402
},
{
"epoch": 1.83,
"learning_rate": 6.512486861047911e-06,
"loss": 0.0936,
"step": 403
},
{
"epoch": 1.84,
"learning_rate": 6.467711853755558e-06,
"loss": 0.092,
"step": 404
},
{
"epoch": 1.84,
"learning_rate": 6.423017611668745e-06,
"loss": 0.0929,
"step": 405
},
{
"epoch": 1.85,
"learning_rate": 6.378405156714202e-06,
"loss": 0.0856,
"step": 406
},
{
"epoch": 1.85,
"learning_rate": 6.333875508948592e-06,
"loss": 0.0947,
"step": 407
},
{
"epoch": 1.85,
"learning_rate": 6.289429686535226e-06,
"loss": 0.0819,
"step": 408
},
{
"epoch": 1.86,
"learning_rate": 6.2450687057207395e-06,
"loss": 0.0854,
"step": 409
},
{
"epoch": 1.86,
"learning_rate": 6.200793580811897e-06,
"loss": 0.0853,
"step": 410
},
{
"epoch": 1.87,
"learning_rate": 6.156605324152369e-06,
"loss": 0.0836,
"step": 411
},
{
"epoch": 1.87,
"learning_rate": 6.112504946099605e-06,
"loss": 0.0856,
"step": 412
},
{
"epoch": 1.88,
"learning_rate": 6.068493455001718e-06,
"loss": 0.0998,
"step": 413
},
{
"epoch": 1.88,
"learning_rate": 6.024571857174443e-06,
"loss": 0.0738,
"step": 414
},
{
"epoch": 1.89,
"learning_rate": 5.98074115687811e-06,
"loss": 0.0758,
"step": 415
},
{
"epoch": 1.89,
"learning_rate": 5.937002356294699e-06,
"loss": 0.0953,
"step": 416
},
{
"epoch": 1.9,
"learning_rate": 5.893356455504911e-06,
"loss": 0.0919,
"step": 417
},
{
"epoch": 1.9,
"learning_rate": 5.8498044524653175e-06,
"loss": 0.0927,
"step": 418
},
{
"epoch": 1.9,
"learning_rate": 5.806347342985521e-06,
"loss": 0.085,
"step": 419
},
{
"epoch": 1.91,
"learning_rate": 5.7629861207054135e-06,
"loss": 0.071,
"step": 420
},
{
"epoch": 1.91,
"learning_rate": 5.719721777072425e-06,
"loss": 0.0737,
"step": 421
},
{
"epoch": 1.92,
"learning_rate": 5.676555301318877e-06,
"loss": 0.0854,
"step": 422
},
{
"epoch": 1.92,
"learning_rate": 5.633487680439362e-06,
"loss": 0.0858,
"step": 423
},
{
"epoch": 1.93,
"learning_rate": 5.5905198991681695e-06,
"loss": 0.0788,
"step": 424
},
{
"epoch": 1.93,
"learning_rate": 5.547652939956764e-06,
"loss": 0.1029,
"step": 425
},
{
"epoch": 1.94,
"learning_rate": 5.504887782951343e-06,
"loss": 0.0871,
"step": 426
},
{
"epoch": 1.94,
"learning_rate": 5.462225405970401e-06,
"loss": 0.0727,
"step": 427
},
{
"epoch": 1.95,
"learning_rate": 5.419666784482398e-06,
"loss": 0.0787,
"step": 428
},
{
"epoch": 1.95,
"learning_rate": 5.377212891583419e-06,
"loss": 0.1104,
"step": 429
},
{
"epoch": 1.95,
"learning_rate": 5.3348646979749685e-06,
"loss": 0.1016,
"step": 430
},
{
"epoch": 1.96,
"learning_rate": 5.29262317194174e-06,
"loss": 0.0821,
"step": 431
},
{
"epoch": 1.96,
"learning_rate": 5.250489279329501e-06,
"loss": 0.0838,
"step": 432
},
{
"epoch": 1.97,
"learning_rate": 5.20846398352298e-06,
"loss": 0.0849,
"step": 433
},
{
"epoch": 1.97,
"learning_rate": 5.1665482454238815e-06,
"loss": 0.07,
"step": 434
},
{
"epoch": 1.98,
"learning_rate": 5.124743023428867e-06,
"loss": 0.072,
"step": 435
},
{
"epoch": 1.98,
"learning_rate": 5.083049273407681e-06,
"loss": 0.077,
"step": 436
},
{
"epoch": 1.99,
"learning_rate": 5.041467948681269e-06,
"loss": 0.0832,
"step": 437
},
{
"epoch": 1.99,
"learning_rate": 5.000000000000003e-06,
"loss": 0.0964,
"step": 438
},
{
"epoch": 2.0,
"learning_rate": 4.958646375521909e-06,
"loss": 0.0969,
"step": 439
},
{
"epoch": 2.0,
"eval_loss": 0.0929914191365242,
"eval_runtime": 1063.5196,
"eval_samples_per_second": 4.413,
"eval_steps_per_second": 2.207,
"step": 439
},
{
"epoch": 2.0,
"learning_rate": 4.917408020791027e-06,
"loss": 0.1064,
"step": 440
},
{
"epoch": 2.0,
"learning_rate": 4.876285878715764e-06,
"loss": 0.0924,
"step": 441
},
{
"epoch": 2.01,
"learning_rate": 4.8352808895473516e-06,
"loss": 0.086,
"step": 442
},
{
"epoch": 2.01,
"learning_rate": 4.794393990858321e-06,
"loss": 0.0829,
"step": 443
},
{
"epoch": 2.02,
"learning_rate": 4.753626117521103e-06,
"loss": 0.088,
"step": 444
},
{
"epoch": 2.02,
"learning_rate": 4.712978201686621e-06,
"loss": 0.0954,
"step": 445
},
{
"epoch": 2.03,
"learning_rate": 4.672451172762998e-06,
"loss": 0.0955,
"step": 446
},
{
"epoch": 2.03,
"learning_rate": 4.632045957394286e-06,
"loss": 0.1074,
"step": 447
},
{
"epoch": 2.04,
"learning_rate": 4.591763479439295e-06,
"loss": 0.0955,
"step": 448
},
{
"epoch": 2.04,
"learning_rate": 4.551604659950466e-06,
"loss": 0.0795,
"step": 449
},
{
"epoch": 2.05,
"learning_rate": 4.5115704171528105e-06,
"loss": 0.0857,
"step": 450
},
{
"epoch": 2.05,
"learning_rate": 4.471661666422899e-06,
"loss": 0.0914,
"step": 451
},
{
"epoch": 2.05,
"learning_rate": 4.431879320267972e-06,
"loss": 0.0808,
"step": 452
},
{
"epoch": 2.06,
"learning_rate": 4.3922242883050226e-06,
"loss": 0.0854,
"step": 453
},
{
"epoch": 2.06,
"learning_rate": 4.3526974772400406e-06,
"loss": 0.0941,
"step": 454
},
{
"epoch": 2.07,
"learning_rate": 4.313299790847263e-06,
"loss": 0.09,
"step": 455
},
{
"epoch": 2.07,
"learning_rate": 4.274032129948512e-06,
"loss": 0.0686,
"step": 456
},
{
"epoch": 2.08,
"learning_rate": 4.234895392392591e-06,
"loss": 0.0753,
"step": 457
},
{
"epoch": 2.08,
"learning_rate": 4.19589047303477e-06,
"loss": 0.0982,
"step": 458
},
{
"epoch": 2.09,
"learning_rate": 4.1570182637163155e-06,
"loss": 0.0897,
"step": 459
},
{
"epoch": 2.09,
"learning_rate": 4.1182796532441e-06,
"loss": 0.0719,
"step": 460
},
{
"epoch": 2.1,
"learning_rate": 4.079675527370273e-06,
"loss": 0.0744,
"step": 461
},
{
"epoch": 2.1,
"learning_rate": 4.041206768772023e-06,
"loss": 0.0858,
"step": 462
},
{
"epoch": 2.1,
"learning_rate": 4.002874257031384e-06,
"loss": 0.0785,
"step": 463
},
{
"epoch": 2.11,
"learning_rate": 3.9646788686151335e-06,
"loss": 0.0837,
"step": 464
},
{
"epoch": 2.11,
"learning_rate": 3.9266214768547335e-06,
"loss": 0.0791,
"step": 465
},
{
"epoch": 2.12,
"learning_rate": 3.888702951926384e-06,
"loss": 0.0691,
"step": 466
},
{
"epoch": 2.12,
"learning_rate": 3.850924160831116e-06,
"loss": 0.0881,
"step": 467
},
{
"epoch": 2.13,
"learning_rate": 3.8132859673749688e-06,
"loss": 0.0748,
"step": 468
},
{
"epoch": 2.13,
"learning_rate": 3.7757892321492297e-06,
"loss": 0.0796,
"step": 469
},
{
"epoch": 2.14,
"learning_rate": 3.738434812510785e-06,
"loss": 0.0789,
"step": 470
},
{
"epoch": 2.14,
"learning_rate": 3.701223562562478e-06,
"loss": 0.0819,
"step": 471
},
{
"epoch": 2.15,
"learning_rate": 3.6641563331336126e-06,
"loss": 0.0814,
"step": 472
},
{
"epoch": 2.15,
"learning_rate": 3.627233971760481e-06,
"loss": 0.0704,
"step": 473
},
{
"epoch": 2.16,
"learning_rate": 3.590457322666997e-06,
"loss": 0.0734,
"step": 474
},
{
"epoch": 2.16,
"learning_rate": 3.5538272267453734e-06,
"loss": 0.0944,
"step": 475
},
{
"epoch": 2.16,
"learning_rate": 3.5173445215369183e-06,
"loss": 0.0931,
"step": 476
},
{
"epoch": 2.17,
"learning_rate": 3.4810100412128743e-06,
"loss": 0.0793,
"step": 477
},
{
"epoch": 2.17,
"learning_rate": 3.4448246165553465e-06,
"loss": 0.0686,
"step": 478
},
{
"epoch": 2.18,
"learning_rate": 3.4087890749382947e-06,
"loss": 0.087,
"step": 479
},
{
"epoch": 2.18,
"learning_rate": 3.37290424030864e-06,
"loss": 0.0983,
"step": 480
},
{
"epoch": 2.19,
"learning_rate": 3.3371709331674075e-06,
"loss": 0.079,
"step": 481
},
{
"epoch": 2.19,
"learning_rate": 3.3015899705509734e-06,
"loss": 0.0807,
"step": 482
},
{
"epoch": 2.2,
"learning_rate": 3.2661621660123666e-06,
"loss": 0.1039,
"step": 483
},
{
"epoch": 2.2,
"learning_rate": 3.2308883296027073e-06,
"loss": 0.074,
"step": 484
},
{
"epoch": 2.21,
"learning_rate": 3.195769267852632e-06,
"loss": 0.0684,
"step": 485
},
{
"epoch": 2.21,
"learning_rate": 3.1608057837538976e-06,
"loss": 0.0934,
"step": 486
},
{
"epoch": 2.21,
"learning_rate": 3.1259986767409866e-06,
"loss": 0.0656,
"step": 487
},
{
"epoch": 2.22,
"learning_rate": 3.0913487426728672e-06,
"loss": 0.0694,
"step": 488
},
{
"epoch": 2.22,
"learning_rate": 3.0568567738147505e-06,
"loss": 0.0806,
"step": 489
},
{
"epoch": 2.23,
"learning_rate": 3.0225235588200096e-06,
"loss": 0.0727,
"step": 490
},
{
"epoch": 2.23,
"learning_rate": 2.988349882712135e-06,
"loss": 0.0808,
"step": 491
},
{
"epoch": 2.24,
"learning_rate": 2.9543365268667866e-06,
"loss": 0.0867,
"step": 492
},
{
"epoch": 2.24,
"learning_rate": 2.9204842689939207e-06,
"loss": 0.0908,
"step": 493
},
{
"epoch": 2.25,
"learning_rate": 2.8867938831200203e-06,
"loss": 0.0773,
"step": 494
},
{
"epoch": 2.25,
"learning_rate": 2.853266139570391e-06,
"loss": 0.083,
"step": 495
},
{
"epoch": 2.26,
"learning_rate": 2.819901804951547e-06,
"loss": 0.0818,
"step": 496
},
{
"epoch": 2.26,
"learning_rate": 2.786701642133678e-06,
"loss": 0.0895,
"step": 497
},
{
"epoch": 2.26,
"learning_rate": 2.7536664102332177e-06,
"loss": 0.0895,
"step": 498
},
{
"epoch": 2.27,
"learning_rate": 2.7207968645954806e-06,
"loss": 0.0727,
"step": 499
},
{
"epoch": 2.27,
"learning_rate": 2.6880937567773903e-06,
"loss": 0.1001,
"step": 500
},
{
"epoch": 2.28,
"learning_rate": 2.655557834530288e-06,
"loss": 0.0789,
"step": 501
},
{
"epoch": 2.28,
"learning_rate": 2.6231898417828605e-06,
"loss": 0.0821,
"step": 502
},
{
"epoch": 2.29,
"learning_rate": 2.590990518624098e-06,
"loss": 0.0942,
"step": 503
},
{
"epoch": 2.29,
"learning_rate": 2.5589606012863968e-06,
"loss": 0.0825,
"step": 504
},
{
"epoch": 2.3,
"learning_rate": 2.5271008221287043e-06,
"loss": 0.1024,
"step": 505
},
{
"epoch": 2.3,
"learning_rate": 2.495411909619804e-06,
"loss": 0.083,
"step": 506
},
{
"epoch": 2.31,
"learning_rate": 2.4638945883216236e-06,
"loss": 0.0887,
"step": 507
},
{
"epoch": 2.31,
"learning_rate": 2.432549578872694e-06,
"loss": 0.0871,
"step": 508
},
{
"epoch": 2.31,
"learning_rate": 2.4013775979716602e-06,
"loss": 0.0817,
"step": 509
},
{
"epoch": 2.32,
"learning_rate": 2.3703793583609013e-06,
"loss": 0.0728,
"step": 510
},
{
"epoch": 2.32,
"learning_rate": 2.339555568810221e-06,
"loss": 0.0996,
"step": 511
},
{
"epoch": 2.33,
"learning_rate": 2.3089069341006563e-06,
"loss": 0.0884,
"step": 512
},
{
"epoch": 2.33,
"learning_rate": 2.2784341550083577e-06,
"loss": 0.0915,
"step": 513
},
{
"epoch": 2.34,
"learning_rate": 2.248137928288564e-06,
"loss": 0.0912,
"step": 514
},
{
"epoch": 2.34,
"learning_rate": 2.218018946659666e-06,
"loss": 0.0992,
"step": 515
},
{
"epoch": 2.35,
"learning_rate": 2.1880778987873806e-06,
"loss": 0.0741,
"step": 516
},
{
"epoch": 2.35,
"learning_rate": 2.158315469268998e-06,
"loss": 0.0845,
"step": 517
},
{
"epoch": 2.36,
"learning_rate": 2.128732338617726e-06,
"loss": 0.0811,
"step": 518
},
{
"epoch": 2.36,
"learning_rate": 2.099329183247126e-06,
"loss": 0.0805,
"step": 519
},
{
"epoch": 2.36,
"learning_rate": 2.0701066754556708e-06,
"loss": 0.0911,
"step": 520
},
{
"epoch": 2.37,
"learning_rate": 2.0410654834113362e-06,
"loss": 0.0873,
"step": 521
},
{
"epoch": 2.37,
"learning_rate": 2.012206271136353e-06,
"loss": 0.0807,
"step": 522
},
{
"epoch": 2.38,
"learning_rate": 1.983529698492006e-06,
"loss": 0.072,
"step": 523
},
{
"epoch": 2.38,
"learning_rate": 1.9550364211635674e-06,
"loss": 0.0962,
"step": 524
},
{
"epoch": 2.39,
"learning_rate": 1.926727090645275e-06,
"loss": 0.0838,
"step": 525
},
{
"epoch": 2.39,
"learning_rate": 1.8986023542254617e-06,
"loss": 0.0791,
"step": 526
},
{
"epoch": 2.4,
"learning_rate": 1.8706628549717453e-06,
"loss": 0.0748,
"step": 527
},
{
"epoch": 2.4,
"learning_rate": 1.8429092317163244e-06,
"loss": 0.1024,
"step": 528
},
{
"epoch": 2.41,
"learning_rate": 1.8153421190413668e-06,
"loss": 0.0797,
"step": 529
},
{
"epoch": 2.41,
"learning_rate": 1.7879621472645147e-06,
"loss": 0.0757,
"step": 530
},
{
"epoch": 2.41,
"learning_rate": 1.7607699424244583e-06,
"loss": 0.0907,
"step": 531
},
{
"epoch": 2.42,
"learning_rate": 1.7337661262666294e-06,
"loss": 0.0787,
"step": 532
},
{
"epoch": 2.42,
"learning_rate": 1.7069513162289786e-06,
"loss": 0.0882,
"step": 533
},
{
"epoch": 2.43,
"learning_rate": 1.6803261254278635e-06,
"loss": 0.0727,
"step": 534
},
{
"epoch": 2.43,
"learning_rate": 1.6538911626440312e-06,
"loss": 0.0866,
"step": 535
},
{
"epoch": 2.44,
"learning_rate": 1.6276470323086936e-06,
"loss": 0.0836,
"step": 536
},
{
"epoch": 2.44,
"learning_rate": 1.6015943344897022e-06,
"loss": 0.0765,
"step": 537
},
{
"epoch": 2.45,
"learning_rate": 1.575733664877851e-06,
"loss": 0.0732,
"step": 538
},
{
"epoch": 2.45,
"learning_rate": 1.5500656147732208e-06,
"loss": 0.0869,
"step": 539
},
{
"epoch": 2.46,
"learning_rate": 1.5245907710716912e-06,
"loss": 0.0878,
"step": 540
},
{
"epoch": 2.46,
"learning_rate": 1.499309716251498e-06,
"loss": 0.0655,
"step": 541
},
{
"epoch": 2.46,
"learning_rate": 1.474223028359939e-06,
"loss": 0.0876,
"step": 542
},
{
"epoch": 2.47,
"learning_rate": 1.4493312810001293e-06,
"loss": 0.0951,
"step": 543
},
{
"epoch": 2.47,
"learning_rate": 1.4246350433179057e-06,
"loss": 0.0748,
"step": 544
},
{
"epoch": 2.48,
"learning_rate": 1.4001348799888093e-06,
"loss": 0.0889,
"step": 545
},
{
"epoch": 2.48,
"learning_rate": 1.3758313512051702e-06,
"loss": 0.0862,
"step": 546
},
{
"epoch": 2.49,
"learning_rate": 1.3517250126632986e-06,
"loss": 0.0766,
"step": 547
},
{
"epoch": 2.49,
"learning_rate": 1.3278164155507844e-06,
"loss": 0.0801,
"step": 548
},
{
"epoch": 2.5,
"learning_rate": 1.30410610653389e-06,
"loss": 0.0878,
"step": 549
},
{
"epoch": 2.5,
"learning_rate": 1.2805946277450565e-06,
"loss": 0.0827,
"step": 550
},
{
"epoch": 2.51,
"learning_rate": 1.257282516770494e-06,
"loss": 0.0775,
"step": 551
},
{
"epoch": 2.51,
"learning_rate": 1.2341703066379073e-06,
"loss": 0.084,
"step": 552
},
{
"epoch": 2.51,
"learning_rate": 1.2112585258042963e-06,
"loss": 0.0907,
"step": 553
},
{
"epoch": 2.52,
"learning_rate": 1.1885476981438837e-06,
"loss": 0.0802,
"step": 554
},
{
"epoch": 2.52,
"learning_rate": 1.1660383429361155e-06,
"loss": 0.0793,
"step": 555
},
{
"epoch": 2.53,
"learning_rate": 1.1437309748538205e-06,
"loss": 0.0753,
"step": 556
},
{
"epoch": 2.53,
"learning_rate": 1.1216261039514087e-06,
"loss": 0.0823,
"step": 557
},
{
"epoch": 2.54,
"learning_rate": 1.0997242356532335e-06,
"loss": 0.0719,
"step": 558
},
{
"epoch": 2.54,
"learning_rate": 1.0780258707420222e-06,
"loss": 0.069,
"step": 559
},
{
"epoch": 2.55,
"learning_rate": 1.0565315053474324e-06,
"loss": 0.0797,
"step": 560
},
{
"epoch": 2.55,
"learning_rate": 1.0352416309347003e-06,
"loss": 0.0728,
"step": 561
},
{
"epoch": 2.56,
"learning_rate": 1.0141567342934134e-06,
"loss": 0.0973,
"step": 562
},
{
"epoch": 2.56,
"learning_rate": 9.932772975263727e-07,
"loss": 0.0648,
"step": 563
},
{
"epoch": 2.56,
"learning_rate": 9.72603798038574e-07,
"loss": 0.0849,
"step": 564
},
{
"epoch": 2.57,
"learning_rate": 9.521367085262845e-07,
"loss": 0.0751,
"step": 565
},
{
"epoch": 2.57,
"learning_rate": 9.318764969662475e-07,
"loss": 0.0951,
"step": 566
},
{
"epoch": 2.58,
"learning_rate": 9.118236266049707e-07,
"loss": 0.0763,
"step": 567
},
{
"epoch": 2.58,
"learning_rate": 8.919785559481409e-07,
"loss": 0.077,
"step": 568
},
{
"epoch": 2.59,
"learning_rate": 8.723417387501332e-07,
"loss": 0.0663,
"step": 569
},
{
"epoch": 2.59,
"learning_rate": 8.529136240036439e-07,
"loss": 0.0694,
"step": 570
},
{
"epoch": 2.6,
"learning_rate": 8.336946559294223e-07,
"loss": 0.0931,
"step": 571
},
{
"epoch": 2.6,
"learning_rate": 8.146852739661104e-07,
"loss": 0.081,
"step": 572
},
{
"epoch": 2.61,
"learning_rate": 7.958859127601937e-07,
"loss": 0.0875,
"step": 573
},
{
"epoch": 2.61,
"learning_rate": 7.772970021560755e-07,
"loss": 0.087,
"step": 574
},
{
"epoch": 2.61,
"learning_rate": 7.589189671862307e-07,
"loss": 0.0823,
"step": 575
},
{
"epoch": 2.62,
"learning_rate": 7.40752228061502e-07,
"loss": 0.0971,
"step": 576
},
{
"epoch": 2.62,
"learning_rate": 7.227972001614825e-07,
"loss": 0.085,
"step": 577
},
{
"epoch": 2.63,
"learning_rate": 7.050542940250271e-07,
"loss": 0.0876,
"step": 578
},
{
"epoch": 2.63,
"learning_rate": 6.875239153408541e-07,
"loss": 0.0934,
"step": 579
},
{
"epoch": 2.64,
"learning_rate": 6.702064649382778e-07,
"loss": 0.0782,
"step": 580
},
{
"epoch": 2.64,
"learning_rate": 6.531023387780433e-07,
"loss": 0.0758,
"step": 581
},
{
"epoch": 2.65,
"learning_rate": 6.36211927943271e-07,
"loss": 0.1023,
"step": 582
},
{
"epoch": 2.65,
"learning_rate": 6.195356186305101e-07,
"loss": 0.1103,
"step": 583
},
{
"epoch": 2.66,
"learning_rate": 6.030737921409169e-07,
"loss": 0.0871,
"step": 584
},
{
"epoch": 2.66,
"learning_rate": 5.868268248715292e-07,
"loss": 0.0756,
"step": 585
},
{
"epoch": 2.66,
"learning_rate": 5.707950883066681e-07,
"loss": 0.0849,
"step": 586
},
{
"epoch": 2.67,
"learning_rate": 5.549789490094304e-07,
"loss": 0.0877,
"step": 587
},
{
"epoch": 2.67,
"learning_rate": 5.393787686133234e-07,
"loss": 0.0862,
"step": 588
},
{
"epoch": 2.68,
"learning_rate": 5.239949038139858e-07,
"loss": 0.1067,
"step": 589
},
{
"epoch": 2.68,
"learning_rate": 5.088277063610347e-07,
"loss": 0.0804,
"step": 590
},
{
"epoch": 2.69,
"learning_rate": 4.938775230500192e-07,
"loss": 0.0877,
"step": 591
},
{
"epoch": 2.69,
"learning_rate": 4.791446957145041e-07,
"loss": 0.0774,
"step": 592
},
{
"epoch": 2.7,
"learning_rate": 4.646295612182339e-07,
"loss": 0.0769,
"step": 593
},
{
"epoch": 2.7,
"learning_rate": 4.503324514474483e-07,
"loss": 0.0745,
"step": 594
},
{
"epoch": 2.71,
"learning_rate": 4.3625369330328127e-07,
"loss": 0.094,
"step": 595
},
{
"epoch": 2.71,
"learning_rate": 4.223936086942981e-07,
"loss": 0.0775,
"step": 596
},
{
"epoch": 2.71,
"learning_rate": 4.087525145291205e-07,
"loss": 0.1056,
"step": 597
},
{
"epoch": 2.72,
"learning_rate": 3.95330722709194e-07,
"loss": 0.0898,
"step": 598
},
{
"epoch": 2.72,
"learning_rate": 3.821285401216501e-07,
"loss": 0.0896,
"step": 599
},
{
"epoch": 2.73,
"learning_rate": 3.6914626863229e-07,
"loss": 0.0738,
"step": 600
},
{
"epoch": 2.73,
"learning_rate": 3.5638420507868145e-07,
"loss": 0.0854,
"step": 601
},
{
"epoch": 2.74,
"learning_rate": 3.438426412633733e-07,
"loss": 0.0809,
"step": 602
},
{
"epoch": 2.74,
"learning_rate": 3.3152186394722506e-07,
"loss": 0.0891,
"step": 603
},
{
"epoch": 2.75,
"learning_rate": 3.1942215484284666e-07,
"loss": 0.0825,
"step": 604
},
{
"epoch": 2.75,
"learning_rate": 3.075437906081558e-07,
"loss": 0.0721,
"step": 605
},
{
"epoch": 2.76,
"learning_rate": 2.9588704284006176e-07,
"loss": 0.0731,
"step": 606
},
{
"epoch": 2.76,
"learning_rate": 2.844521780682408e-07,
"loss": 0.0932,
"step": 607
},
{
"epoch": 2.76,
"learning_rate": 2.7323945774905714e-07,
"loss": 0.0827,
"step": 608
},
{
"epoch": 2.77,
"learning_rate": 2.6224913825956933e-07,
"loss": 0.0824,
"step": 609
},
{
"epoch": 2.77,
"learning_rate": 2.5148147089168573e-07,
"loss": 0.0726,
"step": 610
},
{
"epoch": 2.78,
"learning_rate": 2.4093670184640263e-07,
"loss": 0.0922,
"step": 611
},
{
"epoch": 2.78,
"learning_rate": 2.3061507222818303e-07,
"loss": 0.0792,
"step": 612
},
{
"epoch": 2.79,
"learning_rate": 2.2051681803944457e-07,
"loss": 0.0916,
"step": 613
},
{
"epoch": 2.79,
"learning_rate": 2.1064217017516154e-07,
"loss": 0.1045,
"step": 614
},
{
"epoch": 2.8,
"learning_rate": 2.00991354417579e-07,
"loss": 0.0695,
"step": 615
},
{
"epoch": 2.8,
"learning_rate": 1.9156459143106598e-07,
"loss": 0.0729,
"step": 616
},
{
"epoch": 2.81,
"learning_rate": 1.8236209675705275e-07,
"loss": 0.0842,
"step": 617
},
{
"epoch": 2.81,
"learning_rate": 1.7338408080911473e-07,
"loss": 0.0746,
"step": 618
},
{
"epoch": 2.81,
"learning_rate": 1.6463074886815644e-07,
"loss": 0.0999,
"step": 619
},
{
"epoch": 2.82,
"learning_rate": 1.5610230107771518e-07,
"loss": 0.0964,
"step": 620
},
{
"epoch": 2.82,
"learning_rate": 1.4779893243939358e-07,
"loss": 0.0894,
"step": 621
},
{
"epoch": 2.83,
"learning_rate": 1.397208328083921e-07,
"loss": 0.0926,
"step": 622
},
{
"epoch": 2.83,
"learning_rate": 1.3186818688916803e-07,
"loss": 0.1041,
"step": 623
},
{
"epoch": 2.84,
"learning_rate": 1.242411742312233e-07,
"loss": 0.08,
"step": 624
},
{
"epoch": 2.84,
"learning_rate": 1.168399692249833e-07,
"loss": 0.0925,
"step": 625
},
{
"epoch": 2.85,
"learning_rate": 1.0966474109782354e-07,
"loss": 0.0745,
"step": 626
},
{
"epoch": 2.85,
"learning_rate": 1.0271565391018922e-07,
"loss": 0.0791,
"step": 627
},
{
"epoch": 2.86,
"learning_rate": 9.599286655185502e-08,
"loss": 0.0964,
"step": 628
},
{
"epoch": 2.86,
"learning_rate": 8.949653273827907e-08,
"loss": 0.0654,
"step": 629
},
{
"epoch": 2.86,
"learning_rate": 8.322680100710023e-08,
"loss": 0.0887,
"step": 630
},
{
"epoch": 2.87,
"learning_rate": 7.718381471473524e-08,
"loss": 0.0951,
"step": 631
},
{
"epoch": 2.87,
"learning_rate": 7.136771203310244e-08,
"loss": 0.0881,
"step": 632
},
{
"epoch": 2.88,
"learning_rate": 6.577862594646323e-08,
"loss": 0.0658,
"step": 633
},
{
"epoch": 2.88,
"learning_rate": 6.041668424837888e-08,
"loss": 0.096,
"step": 634
},
{
"epoch": 2.89,
"learning_rate": 5.5282009538794036e-08,
"loss": 0.0998,
"step": 635
},
{
"epoch": 2.89,
"learning_rate": 5.037471922122561e-08,
"loss": 0.087,
"step": 636
},
{
"epoch": 2.9,
"learning_rate": 4.569492550008603e-08,
"loss": 0.0887,
"step": 637
},
{
"epoch": 2.9,
"learning_rate": 4.1242735378111966e-08,
"loss": 0.0916,
"step": 638
},
{
"epoch": 2.91,
"learning_rate": 3.701825065392184e-08,
"loss": 0.09,
"step": 639
},
{
"epoch": 2.91,
"learning_rate": 3.3021567919686583e-08,
"loss": 0.0741,
"step": 640
},
{
"epoch": 2.91,
"learning_rate": 2.925277855891695e-08,
"loss": 0.1025,
"step": 641
},
{
"epoch": 2.92,
"learning_rate": 2.5711968744382975e-08,
"loss": 0.0833,
"step": 642
},
{
"epoch": 2.92,
"learning_rate": 2.2399219436137765e-08,
"loss": 0.093,
"step": 643
},
{
"epoch": 2.93,
"learning_rate": 1.9314606379664537e-08,
"loss": 0.0936,
"step": 644
},
{
"epoch": 2.93,
"learning_rate": 1.6458200104149115e-08,
"loss": 0.081,
"step": 645
},
{
"epoch": 2.94,
"learning_rate": 1.3830065920867886e-08,
"loss": 0.0901,
"step": 646
},
{
"epoch": 2.94,
"learning_rate": 1.143026392168789e-08,
"loss": 0.0878,
"step": 647
},
{
"epoch": 2.95,
"learning_rate": 9.25884897770013e-09,
"loss": 0.0743,
"step": 648
},
{
"epoch": 2.95,
"learning_rate": 7.315870737961694e-09,
"loss": 0.0736,
"step": 649
},
{
"epoch": 2.96,
"learning_rate": 5.6013736283611065e-09,
"loss": 0.0815,
"step": 650
},
{
"epoch": 2.96,
"learning_rate": 4.11539685059914e-09,
"loss": 0.089,
"step": 651
},
{
"epoch": 2.96,
"learning_rate": 2.8579743813006434e-09,
"loss": 0.0774,
"step": 652
},
{
"epoch": 2.97,
"learning_rate": 1.8291349712273864e-09,
"loss": 0.0751,
"step": 653
},
{
"epoch": 2.97,
"learning_rate": 1.0289021446308057e-09,
"loss": 0.0823,
"step": 654
},
{
"epoch": 2.98,
"learning_rate": 4.5729419870577106e-10,
"loss": 0.1049,
"step": 655
},
{
"epoch": 2.98,
"learning_rate": 1.1432420317758486e-10,
"loss": 0.0864,
"step": 656
},
{
"epoch": 2.99,
"learning_rate": 0.0,
"loss": 0.0795,
"step": 657
},
{
"epoch": 2.99,
"eval_loss": 0.09112608432769775,
"eval_runtime": 1063.7673,
"eval_samples_per_second": 4.412,
"eval_steps_per_second": 2.206,
"step": 657
},
{
"epoch": 2.99,
"step": 657,
"total_flos": 3.0284260385446953e+18,
"train_loss": 0.11520915337848155,
"train_runtime": 83607.727,
"train_samples_per_second": 1.515,
"train_steps_per_second": 0.008
}
],
"logging_steps": 1,
"max_steps": 657,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 3.0284260385446953e+18,
"trial_name": null,
"trial_params": null
}