dcvlm-1b-model / trainer_state.json
vishaal27's picture
add DCVLM-1B pretrained checkpoint (small-pool_10c-5m-15t-70i-capmix_scale-small)
ba63ec5 verified
Raw
History Blame Contribute Delete
114 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 939,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 6.896551724137931e-07,
"loss": 5.1237,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.3793103448275862e-06,
"loss": 5.7296,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 2.0689655172413796e-06,
"loss": 5.924,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 2.7586206896551725e-06,
"loss": 5.8862,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 3.448275862068966e-06,
"loss": 5.5826,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 4.137931034482759e-06,
"loss": 5.8288,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 4.8275862068965525e-06,
"loss": 5.5795,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 5.517241379310345e-06,
"loss": 5.5392,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 6.206896551724138e-06,
"loss": 4.9967,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 6.896551724137932e-06,
"loss": 4.9447,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 7.586206896551724e-06,
"loss": 4.6866,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 8.275862068965518e-06,
"loss": 4.413,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 8.965517241379312e-06,
"loss": 4.4076,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 9.655172413793105e-06,
"loss": 4.3401,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 1.0344827586206898e-05,
"loss": 4.154,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 1.103448275862069e-05,
"loss": 3.9791,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 1.1724137931034483e-05,
"loss": 3.8771,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 1.2413793103448277e-05,
"loss": 3.802,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 1.310344827586207e-05,
"loss": 3.743,
"step": 19
},
{
"epoch": 0.02,
"learning_rate": 1.3793103448275863e-05,
"loss": 3.6894,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 1.4482758620689657e-05,
"loss": 3.609,
"step": 21
},
{
"epoch": 0.02,
"learning_rate": 1.5172413793103448e-05,
"loss": 3.5269,
"step": 22
},
{
"epoch": 0.02,
"learning_rate": 1.586206896551724e-05,
"loss": 3.4855,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 1.6551724137931037e-05,
"loss": 3.4772,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 1.7241379310344828e-05,
"loss": 3.4633,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 1.7931034482758623e-05,
"loss": 3.4139,
"step": 26
},
{
"epoch": 0.03,
"learning_rate": 1.8620689655172415e-05,
"loss": 3.3906,
"step": 27
},
{
"epoch": 0.03,
"learning_rate": 1.931034482758621e-05,
"loss": 3.3875,
"step": 28
},
{
"epoch": 0.03,
"learning_rate": 2e-05,
"loss": 3.3116,
"step": 29
},
{
"epoch": 0.03,
"learning_rate": 1.9999940408195878e-05,
"loss": 3.3032,
"step": 30
},
{
"epoch": 0.03,
"learning_rate": 1.9999761633493754e-05,
"loss": 3.2292,
"step": 31
},
{
"epoch": 0.03,
"learning_rate": 1.9999463678024317e-05,
"loss": 3.266,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 1.999904654533872e-05,
"loss": 3.1841,
"step": 33
},
{
"epoch": 0.04,
"learning_rate": 1.9998510240408495e-05,
"loss": 3.1853,
"step": 34
},
{
"epoch": 0.04,
"learning_rate": 1.999785476962552e-05,
"loss": 3.1636,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 1.9997080140801932e-05,
"loss": 3.0675,
"step": 36
},
{
"epoch": 0.04,
"learning_rate": 1.9996186363170037e-05,
"loss": 3.0224,
"step": 37
},
{
"epoch": 0.04,
"learning_rate": 1.9995173447382193e-05,
"loss": 3.0083,
"step": 38
},
{
"epoch": 0.04,
"learning_rate": 1.9994041405510705e-05,
"loss": 2.9928,
"step": 39
},
{
"epoch": 0.04,
"learning_rate": 1.9992790251047655e-05,
"loss": 2.9403,
"step": 40
},
{
"epoch": 0.04,
"learning_rate": 1.999141999890475e-05,
"loss": 2.8692,
"step": 41
},
{
"epoch": 0.04,
"learning_rate": 1.9989930665413148e-05,
"loss": 2.8571,
"step": 42
},
{
"epoch": 0.05,
"learning_rate": 1.998832226832327e-05,
"loss": 2.8117,
"step": 43
},
{
"epoch": 0.05,
"learning_rate": 1.9986594826804563e-05,
"loss": 2.7913,
"step": 44
},
{
"epoch": 0.05,
"learning_rate": 1.9984748361445306e-05,
"loss": 2.7439,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 1.998278289425234e-05,
"loss": 2.7295,
"step": 46
},
{
"epoch": 0.05,
"learning_rate": 1.9980698448650805e-05,
"loss": 2.7054,
"step": 47
},
{
"epoch": 0.05,
"learning_rate": 1.9978495049483883e-05,
"loss": 2.6804,
"step": 48
},
{
"epoch": 0.05,
"learning_rate": 1.997617272301248e-05,
"loss": 2.6298,
"step": 49
},
{
"epoch": 0.05,
"learning_rate": 1.9973731496914914e-05,
"loss": 2.5362,
"step": 50
},
{
"epoch": 0.05,
"learning_rate": 1.9971171400286602e-05,
"loss": 2.5213,
"step": 51
},
{
"epoch": 0.06,
"learning_rate": 1.9968492463639704e-05,
"loss": 2.4668,
"step": 52
},
{
"epoch": 0.06,
"learning_rate": 1.9965694718902745e-05,
"loss": 2.4814,
"step": 53
},
{
"epoch": 0.06,
"learning_rate": 1.9962778199420265e-05,
"loss": 2.4504,
"step": 54
},
{
"epoch": 0.06,
"learning_rate": 1.9959742939952393e-05,
"loss": 2.3672,
"step": 55
},
{
"epoch": 0.06,
"learning_rate": 1.9956588976674442e-05,
"loss": 2.3613,
"step": 56
},
{
"epoch": 0.06,
"learning_rate": 1.995331634717649e-05,
"loss": 2.3475,
"step": 57
},
{
"epoch": 0.06,
"learning_rate": 1.994992509046291e-05,
"loss": 2.3959,
"step": 58
},
{
"epoch": 0.06,
"learning_rate": 1.9946415246951928e-05,
"loss": 2.3046,
"step": 59
},
{
"epoch": 0.06,
"learning_rate": 1.9942786858475126e-05,
"loss": 2.4284,
"step": 60
},
{
"epoch": 0.06,
"learning_rate": 1.9939039968276942e-05,
"loss": 2.3756,
"step": 61
},
{
"epoch": 0.07,
"learning_rate": 1.9935174621014173e-05,
"loss": 2.39,
"step": 62
},
{
"epoch": 0.07,
"learning_rate": 1.9931190862755416e-05,
"loss": 2.3903,
"step": 63
},
{
"epoch": 0.07,
"learning_rate": 1.992708874098054e-05,
"loss": 2.442,
"step": 64
},
{
"epoch": 0.07,
"learning_rate": 1.992286830458012e-05,
"loss": 2.359,
"step": 65
},
{
"epoch": 0.07,
"learning_rate": 1.9918529603854825e-05,
"loss": 2.3346,
"step": 66
},
{
"epoch": 0.07,
"learning_rate": 1.991407269051487e-05,
"loss": 2.292,
"step": 67
},
{
"epoch": 0.07,
"learning_rate": 1.990949761767935e-05,
"loss": 2.28,
"step": 68
},
{
"epoch": 0.07,
"learning_rate": 1.9904804439875635e-05,
"loss": 2.2916,
"step": 69
},
{
"epoch": 0.07,
"learning_rate": 1.989999321303871e-05,
"loss": 2.3141,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 1.9895063994510512e-05,
"loss": 2.3529,
"step": 71
},
{
"epoch": 0.08,
"learning_rate": 1.989001684303925e-05,
"loss": 2.2828,
"step": 72
},
{
"epoch": 0.08,
"learning_rate": 1.9884851818778695e-05,
"loss": 2.2649,
"step": 73
},
{
"epoch": 0.08,
"learning_rate": 1.9879568983287468e-05,
"loss": 2.2664,
"step": 74
},
{
"epoch": 0.08,
"learning_rate": 1.9874168399528307e-05,
"loss": 2.238,
"step": 75
},
{
"epoch": 0.08,
"learning_rate": 1.986865013186732e-05,
"loss": 2.3157,
"step": 76
},
{
"epoch": 0.08,
"learning_rate": 1.9863014246073216e-05,
"loss": 2.2864,
"step": 77
},
{
"epoch": 0.08,
"learning_rate": 1.985726080931651e-05,
"loss": 2.2403,
"step": 78
},
{
"epoch": 0.08,
"learning_rate": 1.9851389890168738e-05,
"loss": 2.2357,
"step": 79
},
{
"epoch": 0.09,
"learning_rate": 1.9845401558601634e-05,
"loss": 2.2194,
"step": 80
},
{
"epoch": 0.09,
"learning_rate": 1.98392958859863e-05,
"loss": 2.2217,
"step": 81
},
{
"epoch": 0.09,
"learning_rate": 1.9833072945092334e-05,
"loss": 2.2947,
"step": 82
},
{
"epoch": 0.09,
"learning_rate": 1.9826732810087e-05,
"loss": 2.2698,
"step": 83
},
{
"epoch": 0.09,
"learning_rate": 1.9820275556534306e-05,
"loss": 2.216,
"step": 84
},
{
"epoch": 0.09,
"learning_rate": 1.9813701261394136e-05,
"loss": 2.2506,
"step": 85
},
{
"epoch": 0.09,
"learning_rate": 1.980701000302131e-05,
"loss": 2.2222,
"step": 86
},
{
"epoch": 0.09,
"learning_rate": 1.9800201861164665e-05,
"loss": 2.2445,
"step": 87
},
{
"epoch": 0.09,
"learning_rate": 1.979327691696608e-05,
"loss": 2.2433,
"step": 88
},
{
"epoch": 0.09,
"learning_rate": 1.9786235252959555e-05,
"loss": 2.2092,
"step": 89
},
{
"epoch": 0.1,
"learning_rate": 1.977907695307017e-05,
"loss": 2.1709,
"step": 90
},
{
"epoch": 0.1,
"learning_rate": 1.9771802102613127e-05,
"loss": 2.1829,
"step": 91
},
{
"epoch": 0.1,
"learning_rate": 1.9764410788292724e-05,
"loss": 2.1449,
"step": 92
},
{
"epoch": 0.1,
"learning_rate": 1.975690309820131e-05,
"loss": 2.2027,
"step": 93
},
{
"epoch": 0.1,
"learning_rate": 1.9749279121818235e-05,
"loss": 2.1483,
"step": 94
},
{
"epoch": 0.1,
"learning_rate": 1.9741538950008817e-05,
"loss": 2.1529,
"step": 95
},
{
"epoch": 0.1,
"learning_rate": 1.9733682675023207e-05,
"loss": 2.1775,
"step": 96
},
{
"epoch": 0.1,
"learning_rate": 1.972571039049533e-05,
"loss": 2.2556,
"step": 97
},
{
"epoch": 0.1,
"learning_rate": 1.971762219144174e-05,
"loss": 2.1952,
"step": 98
},
{
"epoch": 0.11,
"learning_rate": 1.9709418174260523e-05,
"loss": 2.2392,
"step": 99
},
{
"epoch": 0.11,
"learning_rate": 1.9701098436730108e-05,
"loss": 2.1684,
"step": 100
},
{
"epoch": 0.11,
"learning_rate": 1.969266307800813e-05,
"loss": 2.1867,
"step": 101
},
{
"epoch": 0.11,
"learning_rate": 1.9684112198630246e-05,
"loss": 2.2206,
"step": 102
},
{
"epoch": 0.11,
"learning_rate": 1.967544590050891e-05,
"loss": 2.1954,
"step": 103
},
{
"epoch": 0.11,
"learning_rate": 1.9666664286932198e-05,
"loss": 2.1588,
"step": 104
},
{
"epoch": 0.11,
"learning_rate": 1.9657767462562544e-05,
"loss": 2.1967,
"step": 105
},
{
"epoch": 0.11,
"learning_rate": 1.9648755533435517e-05,
"loss": 2.1667,
"step": 106
},
{
"epoch": 0.11,
"learning_rate": 1.9639628606958535e-05,
"loss": 2.1777,
"step": 107
},
{
"epoch": 0.12,
"learning_rate": 1.96303867919096e-05,
"loss": 2.1759,
"step": 108
},
{
"epoch": 0.12,
"learning_rate": 1.9621030198436007e-05,
"loss": 2.2264,
"step": 109
},
{
"epoch": 0.12,
"learning_rate": 1.9611558938053003e-05,
"loss": 2.1599,
"step": 110
},
{
"epoch": 0.12,
"learning_rate": 1.9601973123642493e-05,
"loss": 2.1507,
"step": 111
},
{
"epoch": 0.12,
"learning_rate": 1.9592272869451672e-05,
"loss": 2.1195,
"step": 112
},
{
"epoch": 0.12,
"learning_rate": 1.9582458291091664e-05,
"loss": 2.1513,
"step": 113
},
{
"epoch": 0.12,
"learning_rate": 1.957252950553616e-05,
"loss": 2.1713,
"step": 114
},
{
"epoch": 0.12,
"learning_rate": 1.9562486631120007e-05,
"loss": 2.1608,
"step": 115
},
{
"epoch": 0.12,
"learning_rate": 1.9552329787537805e-05,
"loss": 2.1973,
"step": 116
},
{
"epoch": 0.12,
"learning_rate": 1.9542059095842484e-05,
"loss": 2.1715,
"step": 117
},
{
"epoch": 0.13,
"learning_rate": 1.9531674678443853e-05,
"loss": 2.1769,
"step": 118
},
{
"epoch": 0.13,
"learning_rate": 1.952117665910714e-05,
"loss": 2.2126,
"step": 119
},
{
"epoch": 0.13,
"learning_rate": 1.9510565162951538e-05,
"loss": 2.2229,
"step": 120
},
{
"epoch": 0.13,
"learning_rate": 1.9499840316448675e-05,
"loss": 2.1566,
"step": 121
},
{
"epoch": 0.13,
"learning_rate": 1.948900224742115e-05,
"loss": 2.129,
"step": 122
},
{
"epoch": 0.13,
"learning_rate": 1.9478051085040978e-05,
"loss": 2.1547,
"step": 123
},
{
"epoch": 0.13,
"learning_rate": 1.9466986959828063e-05,
"loss": 2.1429,
"step": 124
},
{
"epoch": 0.13,
"learning_rate": 1.945581000364864e-05,
"loss": 2.1888,
"step": 125
},
{
"epoch": 0.13,
"learning_rate": 1.9444520349713705e-05,
"loss": 2.1363,
"step": 126
},
{
"epoch": 0.14,
"learning_rate": 1.9433118132577432e-05,
"loss": 2.1178,
"step": 127
},
{
"epoch": 0.14,
"learning_rate": 1.942160348813556e-05,
"loss": 2.1386,
"step": 128
},
{
"epoch": 0.14,
"learning_rate": 1.9409976553623767e-05,
"loss": 2.0974,
"step": 129
},
{
"epoch": 0.14,
"learning_rate": 1.9398237467616063e-05,
"loss": 2.106,
"step": 130
},
{
"epoch": 0.14,
"learning_rate": 1.9386386370023104e-05,
"loss": 2.1594,
"step": 131
},
{
"epoch": 0.14,
"learning_rate": 1.9374423402090553e-05,
"loss": 2.1381,
"step": 132
},
{
"epoch": 0.14,
"learning_rate": 1.9362348706397374e-05,
"loss": 2.1512,
"step": 133
},
{
"epoch": 0.14,
"learning_rate": 1.9350162426854152e-05,
"loss": 2.2314,
"step": 134
},
{
"epoch": 0.14,
"learning_rate": 1.933786470870136e-05,
"loss": 2.2531,
"step": 135
},
{
"epoch": 0.14,
"learning_rate": 1.9325455698507638e-05,
"loss": 2.1817,
"step": 136
},
{
"epoch": 0.15,
"learning_rate": 1.931293554416805e-05,
"loss": 2.1562,
"step": 137
},
{
"epoch": 0.15,
"learning_rate": 1.9300304394902315e-05,
"loss": 2.1724,
"step": 138
},
{
"epoch": 0.15,
"learning_rate": 1.9287562401253023e-05,
"loss": 2.1648,
"step": 139
},
{
"epoch": 0.15,
"learning_rate": 1.927470971508386e-05,
"loss": 2.1819,
"step": 140
},
{
"epoch": 0.15,
"learning_rate": 1.9261746489577767e-05,
"loss": 2.1648,
"step": 141
},
{
"epoch": 0.15,
"learning_rate": 1.924867287923515e-05,
"loss": 2.1918,
"step": 142
},
{
"epoch": 0.15,
"learning_rate": 1.923548903987201e-05,
"loss": 2.1376,
"step": 143
},
{
"epoch": 0.15,
"learning_rate": 1.9222195128618108e-05,
"loss": 2.1286,
"step": 144
},
{
"epoch": 0.15,
"learning_rate": 1.9208791303915063e-05,
"loss": 2.1698,
"step": 145
},
{
"epoch": 0.16,
"learning_rate": 1.919527772551451e-05,
"loss": 2.1041,
"step": 146
},
{
"epoch": 0.16,
"learning_rate": 1.918165455447614e-05,
"loss": 2.1681,
"step": 147
},
{
"epoch": 0.16,
"learning_rate": 1.9167921953165827e-05,
"loss": 2.142,
"step": 148
},
{
"epoch": 0.16,
"learning_rate": 1.9154080085253665e-05,
"loss": 2.1089,
"step": 149
},
{
"epoch": 0.16,
"learning_rate": 1.9140129115712035e-05,
"loss": 2.1045,
"step": 150
},
{
"epoch": 0.16,
"learning_rate": 1.912606921081362e-05,
"loss": 2.0805,
"step": 151
},
{
"epoch": 0.16,
"learning_rate": 1.9111900538129443e-05,
"loss": 2.1049,
"step": 152
},
{
"epoch": 0.16,
"learning_rate": 1.909762326652686e-05,
"loss": 2.1226,
"step": 153
},
{
"epoch": 0.16,
"learning_rate": 1.908323756616754e-05,
"loss": 2.072,
"step": 154
},
{
"epoch": 0.17,
"learning_rate": 1.9068743608505454e-05,
"loss": 2.0802,
"step": 155
},
{
"epoch": 0.17,
"learning_rate": 1.9054141566284822e-05,
"loss": 2.0654,
"step": 156
},
{
"epoch": 0.17,
"learning_rate": 1.9039431613538047e-05,
"loss": 2.0425,
"step": 157
},
{
"epoch": 0.17,
"learning_rate": 1.9024613925583652e-05,
"loss": 2.0786,
"step": 158
},
{
"epoch": 0.17,
"learning_rate": 1.900968867902419e-05,
"loss": 2.0738,
"step": 159
},
{
"epoch": 0.17,
"learning_rate": 1.899465605174414e-05,
"loss": 2.0996,
"step": 160
},
{
"epoch": 0.17,
"learning_rate": 1.8979516222907776e-05,
"loss": 2.1035,
"step": 161
},
{
"epoch": 0.17,
"learning_rate": 1.896426937295704e-05,
"loss": 2.0776,
"step": 162
},
{
"epoch": 0.17,
"learning_rate": 1.8948915683609387e-05,
"loss": 2.1035,
"step": 163
},
{
"epoch": 0.17,
"learning_rate": 1.8933455337855633e-05,
"loss": 2.0905,
"step": 164
},
{
"epoch": 0.18,
"learning_rate": 1.8917888519957756e-05,
"loss": 2.1334,
"step": 165
},
{
"epoch": 0.18,
"learning_rate": 1.89022154154467e-05,
"loss": 2.1332,
"step": 166
},
{
"epoch": 0.18,
"learning_rate": 1.8886436211120195e-05,
"loss": 2.1182,
"step": 167
},
{
"epoch": 0.18,
"learning_rate": 1.8870551095040476e-05,
"loss": 2.1632,
"step": 168
},
{
"epoch": 0.18,
"learning_rate": 1.8854560256532098e-05,
"loss": 2.096,
"step": 169
},
{
"epoch": 0.18,
"learning_rate": 1.8838463886179647e-05,
"loss": 2.0229,
"step": 170
},
{
"epoch": 0.18,
"learning_rate": 1.8822262175825463e-05,
"loss": 2.101,
"step": 171
},
{
"epoch": 0.18,
"learning_rate": 1.880595531856738e-05,
"loss": 2.0535,
"step": 172
},
{
"epoch": 0.18,
"learning_rate": 1.878954350875641e-05,
"loss": 2.0442,
"step": 173
},
{
"epoch": 0.19,
"learning_rate": 1.877302694199442e-05,
"loss": 2.1081,
"step": 174
},
{
"epoch": 0.19,
"learning_rate": 1.8756405815131815e-05,
"loss": 2.091,
"step": 175
},
{
"epoch": 0.19,
"learning_rate": 1.873968032626518e-05,
"loss": 2.0799,
"step": 176
},
{
"epoch": 0.19,
"learning_rate": 1.872285067473493e-05,
"loss": 2.0459,
"step": 177
},
{
"epoch": 0.19,
"learning_rate": 1.8705917061122917e-05,
"loss": 2.0321,
"step": 178
},
{
"epoch": 0.19,
"learning_rate": 1.8688879687250067e-05,
"loss": 2.1009,
"step": 179
},
{
"epoch": 0.19,
"learning_rate": 1.8671738756173946e-05,
"loss": 2.0391,
"step": 180
},
{
"epoch": 0.19,
"learning_rate": 1.8654494472186352e-05,
"loss": 2.0751,
"step": 181
},
{
"epoch": 0.19,
"learning_rate": 1.8637147040810884e-05,
"loss": 2.0877,
"step": 182
},
{
"epoch": 0.19,
"learning_rate": 1.8619696668800494e-05,
"loss": 2.0487,
"step": 183
},
{
"epoch": 0.2,
"learning_rate": 1.860214356413501e-05,
"loss": 2.0817,
"step": 184
},
{
"epoch": 0.2,
"learning_rate": 1.8584487936018663e-05,
"loss": 2.0675,
"step": 185
},
{
"epoch": 0.2,
"learning_rate": 1.8566729994877604e-05,
"loss": 2.0669,
"step": 186
},
{
"epoch": 0.2,
"learning_rate": 1.854886995235738e-05,
"loss": 2.0176,
"step": 187
},
{
"epoch": 0.2,
"learning_rate": 1.8530908021320427e-05,
"loss": 2.0804,
"step": 188
},
{
"epoch": 0.2,
"learning_rate": 1.8512844415843514e-05,
"loss": 2.076,
"step": 189
},
{
"epoch": 0.2,
"learning_rate": 1.8494679351215212e-05,
"loss": 2.0979,
"step": 190
},
{
"epoch": 0.2,
"learning_rate": 1.8476413043933316e-05,
"loss": 2.0661,
"step": 191
},
{
"epoch": 0.2,
"learning_rate": 1.8458045711702264e-05,
"loss": 2.0968,
"step": 192
},
{
"epoch": 0.21,
"learning_rate": 1.8439577573430557e-05,
"loss": 2.0614,
"step": 193
},
{
"epoch": 0.21,
"learning_rate": 1.842100884922812e-05,
"loss": 2.1071,
"step": 194
},
{
"epoch": 0.21,
"learning_rate": 1.8402339760403715e-05,
"loss": 2.0511,
"step": 195
},
{
"epoch": 0.21,
"learning_rate": 1.8383570529462273e-05,
"loss": 2.0969,
"step": 196
},
{
"epoch": 0.21,
"learning_rate": 1.8364701380102267e-05,
"loss": 2.0003,
"step": 197
},
{
"epoch": 0.21,
"learning_rate": 1.834573253721303e-05,
"loss": 2.0352,
"step": 198
},
{
"epoch": 0.21,
"learning_rate": 1.8326664226872063e-05,
"loss": 2.0184,
"step": 199
},
{
"epoch": 0.21,
"learning_rate": 1.8307496676342384e-05,
"loss": 2.0792,
"step": 200
},
{
"epoch": 0.21,
"learning_rate": 1.828823011406977e-05,
"loss": 2.0516,
"step": 201
},
{
"epoch": 0.22,
"learning_rate": 1.8268864769680054e-05,
"loss": 2.0097,
"step": 202
},
{
"epoch": 0.22,
"learning_rate": 1.824940087397641e-05,
"loss": 2.0239,
"step": 203
},
{
"epoch": 0.22,
"learning_rate": 1.8229838658936566e-05,
"loss": 2.0418,
"step": 204
},
{
"epoch": 0.22,
"learning_rate": 1.8210178357710057e-05,
"loss": 2.0298,
"step": 205
},
{
"epoch": 0.22,
"learning_rate": 1.819042020461545e-05,
"loss": 2.0423,
"step": 206
},
{
"epoch": 0.22,
"learning_rate": 1.8170564435137542e-05,
"loss": 2.0812,
"step": 207
},
{
"epoch": 0.22,
"learning_rate": 1.8150611285924556e-05,
"loss": 2.0214,
"step": 208
},
{
"epoch": 0.22,
"learning_rate": 1.8130560994785325e-05,
"loss": 1.9945,
"step": 209
},
{
"epoch": 0.22,
"learning_rate": 1.8110413800686456e-05,
"loss": 2.0364,
"step": 210
},
{
"epoch": 0.22,
"learning_rate": 1.8090169943749477e-05,
"loss": 2.0654,
"step": 211
},
{
"epoch": 0.23,
"learning_rate": 1.8069829665247975e-05,
"loss": 2.0294,
"step": 212
},
{
"epoch": 0.23,
"learning_rate": 1.8049393207604734e-05,
"loss": 2.0242,
"step": 213
},
{
"epoch": 0.23,
"learning_rate": 1.8028860814388826e-05,
"loss": 2.0451,
"step": 214
},
{
"epoch": 0.23,
"learning_rate": 1.8008232730312724e-05,
"loss": 2.0449,
"step": 215
},
{
"epoch": 0.23,
"learning_rate": 1.7987509201229378e-05,
"loss": 1.9504,
"step": 216
},
{
"epoch": 0.23,
"learning_rate": 1.7966690474129285e-05,
"loss": 1.9944,
"step": 217
},
{
"epoch": 0.23,
"learning_rate": 1.7945776797137544e-05,
"loss": 2.0202,
"step": 218
},
{
"epoch": 0.23,
"learning_rate": 1.7924768419510906e-05,
"loss": 1.9857,
"step": 219
},
{
"epoch": 0.23,
"learning_rate": 1.7903665591634794e-05,
"loss": 2.0207,
"step": 220
},
{
"epoch": 0.24,
"learning_rate": 1.7882468565020327e-05,
"loss": 2.0292,
"step": 221
},
{
"epoch": 0.24,
"learning_rate": 1.786117759230132e-05,
"loss": 2.0856,
"step": 222
},
{
"epoch": 0.24,
"learning_rate": 1.7839792927231253e-05,
"loss": 2.0233,
"step": 223
},
{
"epoch": 0.24,
"learning_rate": 1.78183148246803e-05,
"loss": 2.0019,
"step": 224
},
{
"epoch": 0.24,
"learning_rate": 1.7796743540632226e-05,
"loss": 2.0365,
"step": 225
},
{
"epoch": 0.24,
"learning_rate": 1.777507933218138e-05,
"loss": 2.0481,
"step": 226
},
{
"epoch": 0.24,
"learning_rate": 1.7753322457529615e-05,
"loss": 1.9953,
"step": 227
},
{
"epoch": 0.24,
"learning_rate": 1.7731473175983215e-05,
"loss": 2.0558,
"step": 228
},
{
"epoch": 0.24,
"learning_rate": 1.7709531747949796e-05,
"loss": 2.0416,
"step": 229
},
{
"epoch": 0.24,
"learning_rate": 1.7687498434935224e-05,
"loss": 2.0619,
"step": 230
},
{
"epoch": 0.25,
"learning_rate": 1.7665373499540464e-05,
"loss": 1.9961,
"step": 231
},
{
"epoch": 0.25,
"learning_rate": 1.7643157205458483e-05,
"loss": 2.0245,
"step": 232
},
{
"epoch": 0.25,
"learning_rate": 1.7620849817471094e-05,
"loss": 2.0359,
"step": 233
},
{
"epoch": 0.25,
"learning_rate": 1.759845160144579e-05,
"loss": 2.0444,
"step": 234
},
{
"epoch": 0.25,
"learning_rate": 1.7575962824332595e-05,
"loss": 2.0368,
"step": 235
},
{
"epoch": 0.25,
"learning_rate": 1.7553383754160864e-05,
"loss": 1.9965,
"step": 236
},
{
"epoch": 0.25,
"learning_rate": 1.7530714660036112e-05,
"loss": 1.9485,
"step": 237
},
{
"epoch": 0.25,
"learning_rate": 1.7507955812136775e-05,
"loss": 1.9894,
"step": 238
},
{
"epoch": 0.25,
"learning_rate": 1.7485107481711014e-05,
"loss": 2.022,
"step": 239
},
{
"epoch": 0.26,
"learning_rate": 1.7462169941073478e-05,
"loss": 2.0031,
"step": 240
},
{
"epoch": 0.26,
"learning_rate": 1.7439143463602052e-05,
"loss": 2.0432,
"step": 241
},
{
"epoch": 0.26,
"learning_rate": 1.74160283237346e-05,
"loss": 2.0056,
"step": 242
},
{
"epoch": 0.26,
"learning_rate": 1.7392824796965703e-05,
"loss": 1.9853,
"step": 243
},
{
"epoch": 0.26,
"learning_rate": 1.7369533159843368e-05,
"loss": 2.0258,
"step": 244
},
{
"epoch": 0.26,
"learning_rate": 1.734615368996573e-05,
"loss": 2.0121,
"step": 245
},
{
"epoch": 0.26,
"learning_rate": 1.7322686665977738e-05,
"loss": 2.0352,
"step": 246
},
{
"epoch": 0.26,
"learning_rate": 1.7299132367567856e-05,
"loss": 2.0376,
"step": 247
},
{
"epoch": 0.26,
"learning_rate": 1.7275491075464716e-05,
"loss": 2.0135,
"step": 248
},
{
"epoch": 0.27,
"learning_rate": 1.7251763071433767e-05,
"loss": 2.0255,
"step": 249
},
{
"epoch": 0.27,
"learning_rate": 1.7227948638273918e-05,
"loss": 2.0076,
"step": 250
},
{
"epoch": 0.27,
"learning_rate": 1.7204048059814175e-05,
"loss": 2.0012,
"step": 251
},
{
"epoch": 0.27,
"learning_rate": 1.7180061620910263e-05,
"loss": 2.0581,
"step": 252
},
{
"epoch": 0.27,
"learning_rate": 1.715598960744121e-05,
"loss": 2.018,
"step": 253
},
{
"epoch": 0.27,
"learning_rate": 1.7131832306305964e-05,
"loss": 2.0612,
"step": 254
},
{
"epoch": 0.27,
"learning_rate": 1.710759000541995e-05,
"loss": 2.0168,
"step": 255
},
{
"epoch": 0.27,
"learning_rate": 1.7083262993711663e-05,
"loss": 2.0103,
"step": 256
},
{
"epoch": 0.27,
"learning_rate": 1.7058851561119198e-05,
"loss": 2.0133,
"step": 257
},
{
"epoch": 0.27,
"learning_rate": 1.7034355998586828e-05,
"loss": 2.0408,
"step": 258
},
{
"epoch": 0.28,
"learning_rate": 1.7009776598061496e-05,
"loss": 2.0019,
"step": 259
},
{
"epoch": 0.28,
"learning_rate": 1.6985113652489374e-05,
"loss": 1.9858,
"step": 260
},
{
"epoch": 0.28,
"learning_rate": 1.6960367455812336e-05,
"loss": 2.0273,
"step": 261
},
{
"epoch": 0.28,
"learning_rate": 1.6935538302964496e-05,
"loss": 2.05,
"step": 262
},
{
"epoch": 0.28,
"learning_rate": 1.691062648986865e-05,
"loss": 2.0205,
"step": 263
},
{
"epoch": 0.28,
"learning_rate": 1.6885632313432772e-05,
"loss": 2.0476,
"step": 264
},
{
"epoch": 0.28,
"learning_rate": 1.686055607154648e-05,
"loss": 2.0458,
"step": 265
},
{
"epoch": 0.28,
"learning_rate": 1.6835398063077476e-05,
"loss": 2.029,
"step": 266
},
{
"epoch": 0.28,
"learning_rate": 1.6810158587867973e-05,
"loss": 2.0169,
"step": 267
},
{
"epoch": 0.29,
"learning_rate": 1.6784837946731148e-05,
"loss": 2.0428,
"step": 268
},
{
"epoch": 0.29,
"learning_rate": 1.6759436441447544e-05,
"loss": 2.0516,
"step": 269
},
{
"epoch": 0.29,
"learning_rate": 1.673395437476146e-05,
"loss": 2.007,
"step": 270
},
{
"epoch": 0.29,
"learning_rate": 1.6708392050377365e-05,
"loss": 2.0236,
"step": 271
},
{
"epoch": 0.29,
"learning_rate": 1.668274977295626e-05,
"loss": 2.0442,
"step": 272
},
{
"epoch": 0.29,
"learning_rate": 1.6657027848112064e-05,
"loss": 1.9953,
"step": 273
},
{
"epoch": 0.29,
"learning_rate": 1.6631226582407954e-05,
"loss": 2.0082,
"step": 274
},
{
"epoch": 0.29,
"learning_rate": 1.660534628335273e-05,
"loss": 2.001,
"step": 275
},
{
"epoch": 0.29,
"learning_rate": 1.657938725939713e-05,
"loss": 1.9941,
"step": 276
},
{
"epoch": 0.29,
"learning_rate": 1.6553349819930167e-05,
"loss": 1.9668,
"step": 277
},
{
"epoch": 0.3,
"learning_rate": 1.6527234275275445e-05,
"loss": 1.9881,
"step": 278
},
{
"epoch": 0.3,
"learning_rate": 1.6501040936687444e-05,
"loss": 1.9477,
"step": 279
},
{
"epoch": 0.3,
"learning_rate": 1.6474770116347824e-05,
"loss": 1.9754,
"step": 280
},
{
"epoch": 0.3,
"learning_rate": 1.6448422127361707e-05,
"loss": 1.9388,
"step": 281
},
{
"epoch": 0.3,
"learning_rate": 1.6421997283753928e-05,
"loss": 1.948,
"step": 282
},
{
"epoch": 0.3,
"learning_rate": 1.6395495900465306e-05,
"loss": 1.9452,
"step": 283
},
{
"epoch": 0.3,
"learning_rate": 1.6368918293348893e-05,
"loss": 1.9431,
"step": 284
},
{
"epoch": 0.3,
"learning_rate": 1.63422647791662e-05,
"loss": 1.9589,
"step": 285
},
{
"epoch": 0.3,
"learning_rate": 1.6315535675583425e-05,
"loss": 1.9319,
"step": 286
},
{
"epoch": 0.31,
"learning_rate": 1.6288731301167667e-05,
"loss": 1.9924,
"step": 287
},
{
"epoch": 0.31,
"learning_rate": 1.626185197538314e-05,
"loss": 1.9417,
"step": 288
},
{
"epoch": 0.31,
"learning_rate": 1.6234898018587336e-05,
"loss": 1.9479,
"step": 289
},
{
"epoch": 0.31,
"learning_rate": 1.6207869752027248e-05,
"loss": 1.924,
"step": 290
},
{
"epoch": 0.31,
"learning_rate": 1.6180767497835503e-05,
"loss": 1.9599,
"step": 291
},
{
"epoch": 0.31,
"learning_rate": 1.6153591579026545e-05,
"loss": 1.975,
"step": 292
},
{
"epoch": 0.31,
"learning_rate": 1.6126342319492784e-05,
"loss": 1.9194,
"step": 293
},
{
"epoch": 0.31,
"learning_rate": 1.609902004400073e-05,
"loss": 1.8973,
"step": 294
},
{
"epoch": 0.31,
"learning_rate": 1.6071625078187113e-05,
"loss": 1.924,
"step": 295
},
{
"epoch": 0.32,
"learning_rate": 1.6044157748555024e-05,
"loss": 1.9795,
"step": 296
},
{
"epoch": 0.32,
"learning_rate": 1.6016618382470014e-05,
"loss": 1.9373,
"step": 297
},
{
"epoch": 0.32,
"learning_rate": 1.598900730815617e-05,
"loss": 1.9545,
"step": 298
},
{
"epoch": 0.32,
"learning_rate": 1.5961324854692254e-05,
"loss": 1.9249,
"step": 299
},
{
"epoch": 0.32,
"learning_rate": 1.593357135200773e-05,
"loss": 1.9577,
"step": 300
},
{
"epoch": 0.32,
"learning_rate": 1.5905747130878853e-05,
"loss": 1.9211,
"step": 301
},
{
"epoch": 0.32,
"learning_rate": 1.5877852522924733e-05,
"loss": 1.8955,
"step": 302
},
{
"epoch": 0.32,
"learning_rate": 1.5849887860603374e-05,
"loss": 1.8903,
"step": 303
},
{
"epoch": 0.32,
"learning_rate": 1.582185347720771e-05,
"loss": 1.962,
"step": 304
},
{
"epoch": 0.32,
"learning_rate": 1.5793749706861637e-05,
"loss": 1.9388,
"step": 305
},
{
"epoch": 0.33,
"learning_rate": 1.576557688451603e-05,
"loss": 1.9284,
"step": 306
},
{
"epoch": 0.33,
"learning_rate": 1.5737335345944758e-05,
"loss": 1.991,
"step": 307
},
{
"epoch": 0.33,
"learning_rate": 1.570902542774066e-05,
"loss": 1.9258,
"step": 308
},
{
"epoch": 0.33,
"learning_rate": 1.568064746731156e-05,
"loss": 1.9173,
"step": 309
},
{
"epoch": 0.33,
"learning_rate": 1.5652201802876227e-05,
"loss": 1.9272,
"step": 310
},
{
"epoch": 0.33,
"learning_rate": 1.5623688773460358e-05,
"loss": 1.9346,
"step": 311
},
{
"epoch": 0.33,
"learning_rate": 1.559510871889252e-05,
"loss": 1.9208,
"step": 312
},
{
"epoch": 0.33,
"learning_rate": 1.556646197980012e-05,
"loss": 1.9339,
"step": 313
},
{
"epoch": 0.33,
"learning_rate": 1.553774889760533e-05,
"loss": 1.9325,
"step": 314
},
{
"epoch": 0.34,
"learning_rate": 1.5508969814521026e-05,
"loss": 1.894,
"step": 315
},
{
"epoch": 0.34,
"learning_rate": 1.5480125073546705e-05,
"loss": 1.9005,
"step": 316
},
{
"epoch": 0.34,
"learning_rate": 1.5451215018464386e-05,
"loss": 1.9471,
"step": 317
},
{
"epoch": 0.34,
"learning_rate": 1.542223999383455e-05,
"loss": 1.9501,
"step": 318
},
{
"epoch": 0.34,
"learning_rate": 1.5393200344991993e-05,
"loss": 1.9279,
"step": 319
},
{
"epoch": 0.34,
"learning_rate": 1.5364096418041723e-05,
"loss": 1.911,
"step": 320
},
{
"epoch": 0.34,
"learning_rate": 1.533492855985485e-05,
"loss": 1.9226,
"step": 321
},
{
"epoch": 0.34,
"learning_rate": 1.530569711806443e-05,
"loss": 1.8663,
"step": 322
},
{
"epoch": 0.34,
"learning_rate": 1.527640244106133e-05,
"loss": 1.917,
"step": 323
},
{
"epoch": 0.35,
"learning_rate": 1.524704487799008e-05,
"loss": 1.9151,
"step": 324
},
{
"epoch": 0.35,
"learning_rate": 1.5217624778744718e-05,
"loss": 1.932,
"step": 325
},
{
"epoch": 0.35,
"learning_rate": 1.5188142493964595e-05,
"loss": 1.8824,
"step": 326
},
{
"epoch": 0.35,
"learning_rate": 1.5158598375030218e-05,
"loss": 1.8815,
"step": 327
},
{
"epoch": 0.35,
"learning_rate": 1.5128992774059063e-05,
"loss": 1.8756,
"step": 328
},
{
"epoch": 0.35,
"learning_rate": 1.5099326043901361e-05,
"loss": 1.8898,
"step": 329
},
{
"epoch": 0.35,
"learning_rate": 1.5069598538135905e-05,
"loss": 1.9098,
"step": 330
},
{
"epoch": 0.35,
"learning_rate": 1.503981061106584e-05,
"loss": 1.8946,
"step": 331
},
{
"epoch": 0.35,
"learning_rate": 1.5009962617714425e-05,
"loss": 1.8905,
"step": 332
},
{
"epoch": 0.35,
"learning_rate": 1.4980054913820814e-05,
"loss": 1.8373,
"step": 333
},
{
"epoch": 0.36,
"learning_rate": 1.4950087855835816e-05,
"loss": 1.8066,
"step": 334
},
{
"epoch": 0.36,
"learning_rate": 1.4920061800917637e-05,
"loss": 1.8382,
"step": 335
},
{
"epoch": 0.36,
"learning_rate": 1.4889977106927642e-05,
"loss": 1.8723,
"step": 336
},
{
"epoch": 0.36,
"learning_rate": 1.485983413242606e-05,
"loss": 1.8378,
"step": 337
},
{
"epoch": 0.36,
"learning_rate": 1.4829633236667746e-05,
"loss": 1.8164,
"step": 338
},
{
"epoch": 0.36,
"learning_rate": 1.4799374779597866e-05,
"loss": 1.8209,
"step": 339
},
{
"epoch": 0.36,
"learning_rate": 1.476905912184763e-05,
"loss": 1.8086,
"step": 340
},
{
"epoch": 0.36,
"learning_rate": 1.4738686624729987e-05,
"loss": 1.8513,
"step": 341
},
{
"epoch": 0.36,
"learning_rate": 1.470825765023532e-05,
"loss": 1.8583,
"step": 342
},
{
"epoch": 0.37,
"learning_rate": 1.4677772561027121e-05,
"loss": 1.8451,
"step": 343
},
{
"epoch": 0.37,
"learning_rate": 1.4647231720437687e-05,
"loss": 1.795,
"step": 344
},
{
"epoch": 0.37,
"learning_rate": 1.4616635492463775e-05,
"loss": 1.7621,
"step": 345
},
{
"epoch": 0.37,
"learning_rate": 1.4585984241762268e-05,
"loss": 1.8,
"step": 346
},
{
"epoch": 0.37,
"learning_rate": 1.4555278333645833e-05,
"loss": 1.8077,
"step": 347
},
{
"epoch": 0.37,
"learning_rate": 1.4524518134078565e-05,
"loss": 1.7797,
"step": 348
},
{
"epoch": 0.37,
"learning_rate": 1.4493704009671614e-05,
"loss": 1.8014,
"step": 349
},
{
"epoch": 0.37,
"learning_rate": 1.446283632767884e-05,
"loss": 1.7344,
"step": 350
},
{
"epoch": 0.37,
"learning_rate": 1.4431915455992416e-05,
"loss": 1.7834,
"step": 351
},
{
"epoch": 0.37,
"learning_rate": 1.440094176313844e-05,
"loss": 1.7593,
"step": 352
},
{
"epoch": 0.38,
"learning_rate": 1.4369915618272568e-05,
"loss": 1.7262,
"step": 353
},
{
"epoch": 0.38,
"learning_rate": 1.4338837391175582e-05,
"loss": 1.7339,
"step": 354
},
{
"epoch": 0.38,
"learning_rate": 1.4307707452249013e-05,
"loss": 1.7505,
"step": 355
},
{
"epoch": 0.38,
"learning_rate": 1.42765261725107e-05,
"loss": 1.7386,
"step": 356
},
{
"epoch": 0.38,
"learning_rate": 1.424529392359039e-05,
"loss": 1.7201,
"step": 357
},
{
"epoch": 0.38,
"learning_rate": 1.4214011077725293e-05,
"loss": 1.7213,
"step": 358
},
{
"epoch": 0.38,
"learning_rate": 1.4182678007755653e-05,
"loss": 1.7611,
"step": 359
},
{
"epoch": 0.38,
"learning_rate": 1.4151295087120307e-05,
"loss": 1.7203,
"step": 360
},
{
"epoch": 0.38,
"learning_rate": 1.4119862689852224e-05,
"loss": 1.7918,
"step": 361
},
{
"epoch": 0.39,
"learning_rate": 1.4088381190574051e-05,
"loss": 1.7427,
"step": 362
},
{
"epoch": 0.39,
"learning_rate": 1.4056850964493668e-05,
"loss": 1.7501,
"step": 363
},
{
"epoch": 0.39,
"learning_rate": 1.4025272387399676e-05,
"loss": 1.6939,
"step": 364
},
{
"epoch": 0.39,
"learning_rate": 1.3993645835656955e-05,
"loss": 1.6919,
"step": 365
},
{
"epoch": 0.39,
"learning_rate": 1.3961971686202163e-05,
"loss": 1.7027,
"step": 366
},
{
"epoch": 0.39,
"learning_rate": 1.3930250316539237e-05,
"loss": 1.6869,
"step": 367
},
{
"epoch": 0.39,
"learning_rate": 1.3898482104734909e-05,
"loss": 1.7047,
"step": 368
},
{
"epoch": 0.39,
"learning_rate": 1.3866667429414188e-05,
"loss": 1.7305,
"step": 369
},
{
"epoch": 0.39,
"learning_rate": 1.383480666975586e-05,
"loss": 1.6943,
"step": 370
},
{
"epoch": 0.4,
"learning_rate": 1.3802900205487948e-05,
"loss": 1.7114,
"step": 371
},
{
"epoch": 0.4,
"learning_rate": 1.3770948416883205e-05,
"loss": 1.6695,
"step": 372
},
{
"epoch": 0.4,
"learning_rate": 1.3738951684754585e-05,
"loss": 1.7023,
"step": 373
},
{
"epoch": 0.4,
"learning_rate": 1.3706910390450679e-05,
"loss": 1.6854,
"step": 374
},
{
"epoch": 0.4,
"learning_rate": 1.3674824915851193e-05,
"loss": 1.6373,
"step": 375
},
{
"epoch": 0.4,
"learning_rate": 1.3642695643362398e-05,
"loss": 1.6787,
"step": 376
},
{
"epoch": 0.4,
"learning_rate": 1.3610522955912551e-05,
"loss": 1.6689,
"step": 377
},
{
"epoch": 0.4,
"learning_rate": 1.3578307236947348e-05,
"loss": 1.6126,
"step": 378
},
{
"epoch": 0.4,
"learning_rate": 1.3546048870425356e-05,
"loss": 1.599,
"step": 379
},
{
"epoch": 0.4,
"learning_rate": 1.3513748240813429e-05,
"loss": 1.6326,
"step": 380
},
{
"epoch": 0.41,
"learning_rate": 1.3481405733082118e-05,
"loss": 1.6404,
"step": 381
},
{
"epoch": 0.41,
"learning_rate": 1.3449021732701106e-05,
"loss": 1.6267,
"step": 382
},
{
"epoch": 0.41,
"learning_rate": 1.3416596625634595e-05,
"loss": 1.598,
"step": 383
},
{
"epoch": 0.41,
"learning_rate": 1.3384130798336705e-05,
"loss": 1.6924,
"step": 384
},
{
"epoch": 0.41,
"learning_rate": 1.3351624637746885e-05,
"loss": 1.6279,
"step": 385
},
{
"epoch": 0.41,
"learning_rate": 1.3319078531285286e-05,
"loss": 1.6383,
"step": 386
},
{
"epoch": 0.41,
"learning_rate": 1.3286492866848143e-05,
"loss": 1.5918,
"step": 387
},
{
"epoch": 0.41,
"learning_rate": 1.3253868032803171e-05,
"loss": 1.661,
"step": 388
},
{
"epoch": 0.41,
"learning_rate": 1.3221204417984907e-05,
"loss": 1.6138,
"step": 389
},
{
"epoch": 0.42,
"learning_rate": 1.3188502411690101e-05,
"loss": 1.6252,
"step": 390
},
{
"epoch": 0.42,
"learning_rate": 1.3155762403673065e-05,
"loss": 1.6132,
"step": 391
},
{
"epoch": 0.42,
"learning_rate": 1.3122984784141021e-05,
"loss": 1.5681,
"step": 392
},
{
"epoch": 0.42,
"learning_rate": 1.3090169943749475e-05,
"loss": 1.6179,
"step": 393
},
{
"epoch": 0.42,
"learning_rate": 1.3057318273597531e-05,
"loss": 1.5614,
"step": 394
},
{
"epoch": 0.42,
"learning_rate": 1.3024430165223245e-05,
"loss": 1.597,
"step": 395
},
{
"epoch": 0.42,
"learning_rate": 1.2991506010598965e-05,
"loss": 1.6028,
"step": 396
},
{
"epoch": 0.42,
"learning_rate": 1.2958546202126638e-05,
"loss": 1.5998,
"step": 397
},
{
"epoch": 0.42,
"learning_rate": 1.2925551132633164e-05,
"loss": 1.5242,
"step": 398
},
{
"epoch": 0.42,
"learning_rate": 1.2892521195365679e-05,
"loss": 1.5613,
"step": 399
},
{
"epoch": 0.43,
"learning_rate": 1.2859456783986892e-05,
"loss": 1.6009,
"step": 400
},
{
"epoch": 0.43,
"learning_rate": 1.2826358292570398e-05,
"loss": 1.5715,
"step": 401
},
{
"epoch": 0.43,
"learning_rate": 1.2793226115595951e-05,
"loss": 1.5208,
"step": 402
},
{
"epoch": 0.43,
"learning_rate": 1.2760060647944794e-05,
"loss": 1.6277,
"step": 403
},
{
"epoch": 0.43,
"learning_rate": 1.2726862284894939e-05,
"loss": 1.5854,
"step": 404
},
{
"epoch": 0.43,
"learning_rate": 1.2693631422116455e-05,
"loss": 1.6306,
"step": 405
},
{
"epoch": 0.43,
"learning_rate": 1.2660368455666752e-05,
"loss": 1.5848,
"step": 406
},
{
"epoch": 0.43,
"learning_rate": 1.262707378198587e-05,
"loss": 1.5515,
"step": 407
},
{
"epoch": 0.43,
"learning_rate": 1.2593747797891743e-05,
"loss": 1.5633,
"step": 408
},
{
"epoch": 0.44,
"learning_rate": 1.2560390900575472e-05,
"loss": 1.5526,
"step": 409
},
{
"epoch": 0.44,
"learning_rate": 1.2527003487596598e-05,
"loss": 1.5676,
"step": 410
},
{
"epoch": 0.44,
"learning_rate": 1.2493585956878354e-05,
"loss": 1.616,
"step": 411
},
{
"epoch": 0.44,
"learning_rate": 1.2460138706702929e-05,
"loss": 1.6307,
"step": 412
},
{
"epoch": 0.44,
"learning_rate": 1.242666213570672e-05,
"loss": 1.5384,
"step": 413
},
{
"epoch": 0.44,
"learning_rate": 1.2393156642875579e-05,
"loss": 1.5709,
"step": 414
},
{
"epoch": 0.44,
"learning_rate": 1.2359622627540059e-05,
"loss": 1.5366,
"step": 415
},
{
"epoch": 0.44,
"learning_rate": 1.2326060489370655e-05,
"loss": 1.5036,
"step": 416
},
{
"epoch": 0.44,
"learning_rate": 1.229247062837304e-05,
"loss": 1.5044,
"step": 417
},
{
"epoch": 0.45,
"learning_rate": 1.2258853444883297e-05,
"loss": 1.4946,
"step": 418
},
{
"epoch": 0.45,
"learning_rate": 1.2225209339563144e-05,
"loss": 1.5741,
"step": 419
},
{
"epoch": 0.45,
"learning_rate": 1.219153871339518e-05,
"loss": 1.5061,
"step": 420
},
{
"epoch": 0.45,
"learning_rate": 1.2157841967678064e-05,
"loss": 1.5234,
"step": 421
},
{
"epoch": 0.45,
"learning_rate": 1.2124119504021776e-05,
"loss": 1.5237,
"step": 422
},
{
"epoch": 0.45,
"learning_rate": 1.2090371724342804e-05,
"loss": 1.5439,
"step": 423
},
{
"epoch": 0.45,
"learning_rate": 1.2056599030859367e-05,
"loss": 1.5217,
"step": 424
},
{
"epoch": 0.45,
"learning_rate": 1.2022801826086609e-05,
"loss": 1.5591,
"step": 425
},
{
"epoch": 0.45,
"learning_rate": 1.1988980512831809e-05,
"loss": 1.5428,
"step": 426
},
{
"epoch": 0.45,
"learning_rate": 1.195513549418959e-05,
"loss": 1.5374,
"step": 427
},
{
"epoch": 0.46,
"learning_rate": 1.1921267173537085e-05,
"loss": 1.5278,
"step": 428
},
{
"epoch": 0.46,
"learning_rate": 1.1887375954529167e-05,
"loss": 1.5654,
"step": 429
},
{
"epoch": 0.46,
"learning_rate": 1.1853462241093614e-05,
"loss": 1.5694,
"step": 430
},
{
"epoch": 0.46,
"learning_rate": 1.1819526437426298e-05,
"loss": 1.6166,
"step": 431
},
{
"epoch": 0.46,
"learning_rate": 1.1785568947986368e-05,
"loss": 1.6046,
"step": 432
},
{
"epoch": 0.46,
"learning_rate": 1.1751590177491441e-05,
"loss": 1.5662,
"step": 433
},
{
"epoch": 0.46,
"learning_rate": 1.1717590530912764e-05,
"loss": 1.6561,
"step": 434
},
{
"epoch": 0.46,
"learning_rate": 1.1683570413470384e-05,
"loss": 1.6045,
"step": 435
},
{
"epoch": 0.46,
"learning_rate": 1.164953023062835e-05,
"loss": 1.5069,
"step": 436
},
{
"epoch": 0.47,
"learning_rate": 1.1615470388089836e-05,
"loss": 1.5221,
"step": 437
},
{
"epoch": 0.47,
"learning_rate": 1.1581391291792336e-05,
"loss": 1.5519,
"step": 438
},
{
"epoch": 0.47,
"learning_rate": 1.1547293347902813e-05,
"loss": 1.5697,
"step": 439
},
{
"epoch": 0.47,
"learning_rate": 1.151317696281287e-05,
"loss": 1.4821,
"step": 440
},
{
"epoch": 0.47,
"learning_rate": 1.1479042543133895e-05,
"loss": 1.5687,
"step": 441
},
{
"epoch": 0.47,
"learning_rate": 1.1444890495692214e-05,
"loss": 1.5571,
"step": 442
},
{
"epoch": 0.47,
"learning_rate": 1.1410721227524256e-05,
"loss": 1.5223,
"step": 443
},
{
"epoch": 0.47,
"learning_rate": 1.1376535145871685e-05,
"loss": 1.5089,
"step": 444
},
{
"epoch": 0.47,
"learning_rate": 1.1342332658176556e-05,
"loss": 1.5,
"step": 445
},
{
"epoch": 0.47,
"learning_rate": 1.1308114172076464e-05,
"loss": 1.5304,
"step": 446
},
{
"epoch": 0.48,
"learning_rate": 1.1273880095399667e-05,
"loss": 1.5577,
"step": 447
},
{
"epoch": 0.48,
"learning_rate": 1.1239630836160246e-05,
"loss": 1.568,
"step": 448
},
{
"epoch": 0.48,
"learning_rate": 1.1205366802553231e-05,
"loss": 1.4804,
"step": 449
},
{
"epoch": 0.48,
"learning_rate": 1.1171088402949739e-05,
"loss": 1.5554,
"step": 450
},
{
"epoch": 0.48,
"learning_rate": 1.1136796045892102e-05,
"loss": 1.486,
"step": 451
},
{
"epoch": 0.48,
"learning_rate": 1.1102490140089009e-05,
"loss": 1.4831,
"step": 452
},
{
"epoch": 0.48,
"learning_rate": 1.1068171094410618e-05,
"loss": 1.5389,
"step": 453
},
{
"epoch": 0.48,
"learning_rate": 1.10338393178837e-05,
"loss": 1.5282,
"step": 454
},
{
"epoch": 0.48,
"learning_rate": 1.0999495219686762e-05,
"loss": 1.5615,
"step": 455
},
{
"epoch": 0.49,
"learning_rate": 1.0965139209145153e-05,
"loss": 1.528,
"step": 456
},
{
"epoch": 0.49,
"learning_rate": 1.0930771695726201e-05,
"loss": 1.5492,
"step": 457
},
{
"epoch": 0.49,
"learning_rate": 1.0896393089034336e-05,
"loss": 1.5267,
"step": 458
},
{
"epoch": 0.49,
"learning_rate": 1.0862003798806195e-05,
"loss": 1.5256,
"step": 459
},
{
"epoch": 0.49,
"learning_rate": 1.0827604234905749e-05,
"loss": 1.5787,
"step": 460
},
{
"epoch": 0.49,
"learning_rate": 1.079319480731941e-05,
"loss": 1.5437,
"step": 461
},
{
"epoch": 0.49,
"learning_rate": 1.0758775926151155e-05,
"loss": 1.5134,
"step": 462
},
{
"epoch": 0.49,
"learning_rate": 1.0724348001617626e-05,
"loss": 1.5477,
"step": 463
},
{
"epoch": 0.49,
"learning_rate": 1.0689911444043249e-05,
"loss": 1.5834,
"step": 464
},
{
"epoch": 0.5,
"learning_rate": 1.0655466663855349e-05,
"loss": 1.5576,
"step": 465
},
{
"epoch": 0.5,
"learning_rate": 1.0621014071579241e-05,
"loss": 1.5355,
"step": 466
},
{
"epoch": 0.5,
"learning_rate": 1.0586554077833346e-05,
"loss": 1.4932,
"step": 467
},
{
"epoch": 0.5,
"learning_rate": 1.0552087093324314e-05,
"loss": 1.4862,
"step": 468
},
{
"epoch": 0.5,
"learning_rate": 1.0517613528842096e-05,
"loss": 1.4609,
"step": 469
},
{
"epoch": 0.5,
"learning_rate": 1.0483133795255072e-05,
"loss": 1.4455,
"step": 470
},
{
"epoch": 0.5,
"learning_rate": 1.044864830350515e-05,
"loss": 1.4897,
"step": 471
},
{
"epoch": 0.5,
"learning_rate": 1.0414157464602866e-05,
"loss": 1.5053,
"step": 472
},
{
"epoch": 0.5,
"learning_rate": 1.0379661689622477e-05,
"loss": 1.4836,
"step": 473
},
{
"epoch": 0.5,
"learning_rate": 1.0345161389697083e-05,
"loss": 1.4327,
"step": 474
},
{
"epoch": 0.51,
"learning_rate": 1.0310656976013704e-05,
"loss": 1.5156,
"step": 475
},
{
"epoch": 0.51,
"learning_rate": 1.027614885980839e-05,
"loss": 1.4927,
"step": 476
},
{
"epoch": 0.51,
"learning_rate": 1.0241637452361323e-05,
"loss": 1.5262,
"step": 477
},
{
"epoch": 0.51,
"learning_rate": 1.0207123164991912e-05,
"loss": 1.486,
"step": 478
},
{
"epoch": 0.51,
"learning_rate": 1.0172606409053887e-05,
"loss": 1.491,
"step": 479
},
{
"epoch": 0.51,
"learning_rate": 1.0138087595930394e-05,
"loss": 1.52,
"step": 480
},
{
"epoch": 0.51,
"learning_rate": 1.0103567137029111e-05,
"loss": 1.4853,
"step": 481
},
{
"epoch": 0.51,
"learning_rate": 1.0069045443777318e-05,
"loss": 1.4453,
"step": 482
},
{
"epoch": 0.51,
"learning_rate": 1.0034522927617014e-05,
"loss": 1.4711,
"step": 483
},
{
"epoch": 0.52,
"learning_rate": 1e-05,
"loss": 1.4758,
"step": 484
},
{
"epoch": 0.52,
"learning_rate": 9.965477072382989e-06,
"loss": 1.4954,
"step": 485
},
{
"epoch": 0.52,
"learning_rate": 9.930954556222683e-06,
"loss": 1.5034,
"step": 486
},
{
"epoch": 0.52,
"learning_rate": 9.896432862970892e-06,
"loss": 1.4652,
"step": 487
},
{
"epoch": 0.52,
"learning_rate": 9.861912404069608e-06,
"loss": 1.4788,
"step": 488
},
{
"epoch": 0.52,
"learning_rate": 9.827393590946116e-06,
"loss": 1.5061,
"step": 489
},
{
"epoch": 0.52,
"learning_rate": 9.79287683500809e-06,
"loss": 1.4697,
"step": 490
},
{
"epoch": 0.52,
"learning_rate": 9.75836254763868e-06,
"loss": 1.4525,
"step": 491
},
{
"epoch": 0.52,
"learning_rate": 9.723851140191613e-06,
"loss": 1.4365,
"step": 492
},
{
"epoch": 0.53,
"learning_rate": 9.689343023986303e-06,
"loss": 1.4023,
"step": 493
},
{
"epoch": 0.53,
"learning_rate": 9.654838610302922e-06,
"loss": 1.4124,
"step": 494
},
{
"epoch": 0.53,
"learning_rate": 9.620338310377526e-06,
"loss": 1.4136,
"step": 495
},
{
"epoch": 0.53,
"learning_rate": 9.58584253539714e-06,
"loss": 1.4736,
"step": 496
},
{
"epoch": 0.53,
"learning_rate": 9.551351696494854e-06,
"loss": 1.4657,
"step": 497
},
{
"epoch": 0.53,
"learning_rate": 9.516866204744932e-06,
"loss": 1.5013,
"step": 498
},
{
"epoch": 0.53,
"learning_rate": 9.482386471157905e-06,
"loss": 1.5176,
"step": 499
},
{
"epoch": 0.53,
"learning_rate": 9.447912906675687e-06,
"loss": 1.4958,
"step": 500
},
{
"epoch": 0.53,
"learning_rate": 9.413445922166654e-06,
"loss": 1.4191,
"step": 501
},
{
"epoch": 0.53,
"learning_rate": 9.378985928420764e-06,
"loss": 1.4607,
"step": 502
},
{
"epoch": 0.54,
"learning_rate": 9.344533336144653e-06,
"loss": 1.4461,
"step": 503
},
{
"epoch": 0.54,
"learning_rate": 9.310088555956751e-06,
"loss": 1.4396,
"step": 504
},
{
"epoch": 0.54,
"learning_rate": 9.275651998382377e-06,
"loss": 1.5191,
"step": 505
},
{
"epoch": 0.54,
"learning_rate": 9.241224073848848e-06,
"loss": 1.5491,
"step": 506
},
{
"epoch": 0.54,
"learning_rate": 9.206805192680592e-06,
"loss": 1.4467,
"step": 507
},
{
"epoch": 0.54,
"learning_rate": 9.172395765094255e-06,
"loss": 1.4812,
"step": 508
},
{
"epoch": 0.54,
"learning_rate": 9.137996201193807e-06,
"loss": 1.4444,
"step": 509
},
{
"epoch": 0.54,
"learning_rate": 9.103606910965666e-06,
"loss": 1.4695,
"step": 510
},
{
"epoch": 0.54,
"learning_rate": 9.069228304273802e-06,
"loss": 1.4362,
"step": 511
},
{
"epoch": 0.55,
"learning_rate": 9.034860790854848e-06,
"loss": 1.4676,
"step": 512
},
{
"epoch": 0.55,
"learning_rate": 9.00050478031324e-06,
"loss": 1.4688,
"step": 513
},
{
"epoch": 0.55,
"learning_rate": 8.966160682116301e-06,
"loss": 1.4273,
"step": 514
},
{
"epoch": 0.55,
"learning_rate": 8.931828905589385e-06,
"loss": 1.4361,
"step": 515
},
{
"epoch": 0.55,
"learning_rate": 8.897509859910996e-06,
"loss": 1.4278,
"step": 516
},
{
"epoch": 0.55,
"learning_rate": 8.863203954107902e-06,
"loss": 1.4334,
"step": 517
},
{
"epoch": 0.55,
"learning_rate": 8.828911597050263e-06,
"loss": 1.415,
"step": 518
},
{
"epoch": 0.55,
"learning_rate": 8.79463319744677e-06,
"loss": 1.4608,
"step": 519
},
{
"epoch": 0.55,
"learning_rate": 8.760369163839759e-06,
"loss": 1.362,
"step": 520
},
{
"epoch": 0.55,
"learning_rate": 8.726119904600337e-06,
"loss": 1.3625,
"step": 521
},
{
"epoch": 0.56,
"learning_rate": 8.691885827923541e-06,
"loss": 1.4591,
"step": 522
},
{
"epoch": 0.56,
"learning_rate": 8.657667341823449e-06,
"loss": 1.4017,
"step": 523
},
{
"epoch": 0.56,
"learning_rate": 8.62346485412832e-06,
"loss": 1.4135,
"step": 524
},
{
"epoch": 0.56,
"learning_rate": 8.58927877247575e-06,
"loss": 1.4434,
"step": 525
},
{
"epoch": 0.56,
"learning_rate": 8.55510950430779e-06,
"loss": 1.3912,
"step": 526
},
{
"epoch": 0.56,
"learning_rate": 8.520957456866107e-06,
"loss": 1.4765,
"step": 527
},
{
"epoch": 0.56,
"learning_rate": 8.48682303718713e-06,
"loss": 1.4687,
"step": 528
},
{
"epoch": 0.56,
"learning_rate": 8.452706652097187e-06,
"loss": 1.401,
"step": 529
},
{
"epoch": 0.56,
"learning_rate": 8.418608708207667e-06,
"loss": 1.4322,
"step": 530
},
{
"epoch": 0.57,
"learning_rate": 8.384529611910164e-06,
"loss": 1.3841,
"step": 531
},
{
"epoch": 0.57,
"learning_rate": 8.35046976937165e-06,
"loss": 1.4182,
"step": 532
},
{
"epoch": 0.57,
"learning_rate": 8.316429586529616e-06,
"loss": 1.4691,
"step": 533
},
{
"epoch": 0.57,
"learning_rate": 8.28240946908724e-06,
"loss": 1.4368,
"step": 534
},
{
"epoch": 0.57,
"learning_rate": 8.24840982250856e-06,
"loss": 1.4479,
"step": 535
},
{
"epoch": 0.57,
"learning_rate": 8.214431052013636e-06,
"loss": 1.4682,
"step": 536
},
{
"epoch": 0.57,
"learning_rate": 8.180473562573705e-06,
"loss": 1.4286,
"step": 537
},
{
"epoch": 0.57,
"learning_rate": 8.146537758906388e-06,
"loss": 1.4364,
"step": 538
},
{
"epoch": 0.57,
"learning_rate": 8.112624045470834e-06,
"loss": 1.4052,
"step": 539
},
{
"epoch": 0.58,
"learning_rate": 8.078732826462917e-06,
"loss": 1.4235,
"step": 540
},
{
"epoch": 0.58,
"learning_rate": 8.044864505810415e-06,
"loss": 1.4048,
"step": 541
},
{
"epoch": 0.58,
"learning_rate": 8.011019487168193e-06,
"loss": 1.487,
"step": 542
},
{
"epoch": 0.58,
"learning_rate": 7.977198173913394e-06,
"loss": 1.4848,
"step": 543
},
{
"epoch": 0.58,
"learning_rate": 7.943400969140635e-06,
"loss": 1.432,
"step": 544
},
{
"epoch": 0.58,
"learning_rate": 7.909628275657199e-06,
"loss": 1.4852,
"step": 545
},
{
"epoch": 0.58,
"learning_rate": 7.875880495978227e-06,
"loss": 1.4763,
"step": 546
},
{
"epoch": 0.58,
"learning_rate": 7.84215803232194e-06,
"loss": 1.4305,
"step": 547
},
{
"epoch": 0.58,
"learning_rate": 7.808461286604828e-06,
"loss": 1.4274,
"step": 548
},
{
"epoch": 0.58,
"learning_rate": 7.774790660436857e-06,
"loss": 1.3993,
"step": 549
},
{
"epoch": 0.59,
"learning_rate": 7.741146555116708e-06,
"loss": 1.4163,
"step": 550
},
{
"epoch": 0.59,
"learning_rate": 7.707529371626966e-06,
"loss": 1.4009,
"step": 551
},
{
"epoch": 0.59,
"learning_rate": 7.67393951062935e-06,
"loss": 1.331,
"step": 552
},
{
"epoch": 0.59,
"learning_rate": 7.640377372459944e-06,
"loss": 1.453,
"step": 553
},
{
"epoch": 0.59,
"learning_rate": 7.606843357124426e-06,
"loss": 1.3836,
"step": 554
},
{
"epoch": 0.59,
"learning_rate": 7.573337864293283e-06,
"loss": 1.4307,
"step": 555
},
{
"epoch": 0.59,
"learning_rate": 7.539861293297073e-06,
"loss": 1.4456,
"step": 556
},
{
"epoch": 0.59,
"learning_rate": 7.506414043121647e-06,
"loss": 1.483,
"step": 557
},
{
"epoch": 0.59,
"learning_rate": 7.472996512403403e-06,
"loss": 1.4426,
"step": 558
},
{
"epoch": 0.6,
"learning_rate": 7.4396090994245295e-06,
"loss": 1.4282,
"step": 559
},
{
"epoch": 0.6,
"learning_rate": 7.406252202108258e-06,
"loss": 1.4644,
"step": 560
},
{
"epoch": 0.6,
"learning_rate": 7.372926218014131e-06,
"loss": 1.4577,
"step": 561
},
{
"epoch": 0.6,
"learning_rate": 7.33963154433325e-06,
"loss": 1.4751,
"step": 562
},
{
"epoch": 0.6,
"learning_rate": 7.306368577883547e-06,
"loss": 1.4365,
"step": 563
},
{
"epoch": 0.6,
"learning_rate": 7.273137715105063e-06,
"loss": 1.4584,
"step": 564
},
{
"epoch": 0.6,
"learning_rate": 7.239939352055208e-06,
"loss": 1.43,
"step": 565
},
{
"epoch": 0.6,
"learning_rate": 7.2067738844040516e-06,
"loss": 1.4368,
"step": 566
},
{
"epoch": 0.6,
"learning_rate": 7.173641707429606e-06,
"loss": 1.4278,
"step": 567
},
{
"epoch": 0.6,
"learning_rate": 7.140543216013109e-06,
"loss": 1.4523,
"step": 568
},
{
"epoch": 0.61,
"learning_rate": 7.107478804634324e-06,
"loss": 1.4504,
"step": 569
},
{
"epoch": 0.61,
"learning_rate": 7.07444886736684e-06,
"loss": 1.453,
"step": 570
},
{
"epoch": 0.61,
"learning_rate": 7.041453797873363e-06,
"loss": 1.4136,
"step": 571
},
{
"epoch": 0.61,
"learning_rate": 7.008493989401039e-06,
"loss": 1.4238,
"step": 572
},
{
"epoch": 0.61,
"learning_rate": 6.975569834776757e-06,
"loss": 1.446,
"step": 573
},
{
"epoch": 0.61,
"learning_rate": 6.942681726402474e-06,
"loss": 1.4173,
"step": 574
},
{
"epoch": 0.61,
"learning_rate": 6.909830056250527e-06,
"loss": 1.4124,
"step": 575
},
{
"epoch": 0.61,
"learning_rate": 6.8770152158589806e-06,
"loss": 1.4147,
"step": 576
},
{
"epoch": 0.61,
"learning_rate": 6.844237596326941e-06,
"loss": 1.3776,
"step": 577
},
{
"epoch": 0.62,
"learning_rate": 6.811497588309901e-06,
"loss": 1.4441,
"step": 578
},
{
"epoch": 0.62,
"learning_rate": 6.778795582015096e-06,
"loss": 1.3745,
"step": 579
},
{
"epoch": 0.62,
"learning_rate": 6.746131967196834e-06,
"loss": 1.4265,
"step": 580
},
{
"epoch": 0.62,
"learning_rate": 6.7135071331518575e-06,
"loss": 1.3996,
"step": 581
},
{
"epoch": 0.62,
"learning_rate": 6.680921468714718e-06,
"loss": 1.4101,
"step": 582
},
{
"epoch": 0.62,
"learning_rate": 6.648375362253119e-06,
"loss": 1.3856,
"step": 583
},
{
"epoch": 0.62,
"learning_rate": 6.615869201663296e-06,
"loss": 1.3706,
"step": 584
},
{
"epoch": 0.62,
"learning_rate": 6.583403374365406e-06,
"loss": 1.4177,
"step": 585
},
{
"epoch": 0.62,
"learning_rate": 6.550978267298893e-06,
"loss": 1.4148,
"step": 586
},
{
"epoch": 0.63,
"learning_rate": 6.518594266917883e-06,
"loss": 1.3752,
"step": 587
},
{
"epoch": 0.63,
"learning_rate": 6.486251759186573e-06,
"loss": 1.3888,
"step": 588
},
{
"epoch": 0.63,
"learning_rate": 6.453951129574644e-06,
"loss": 1.419,
"step": 589
},
{
"epoch": 0.63,
"learning_rate": 6.421692763052654e-06,
"loss": 1.376,
"step": 590
},
{
"epoch": 0.63,
"learning_rate": 6.3894770440874525e-06,
"loss": 1.3899,
"step": 591
},
{
"epoch": 0.63,
"learning_rate": 6.357304356637606e-06,
"loss": 1.4177,
"step": 592
},
{
"epoch": 0.63,
"learning_rate": 6.325175084148809e-06,
"loss": 1.4307,
"step": 593
},
{
"epoch": 0.63,
"learning_rate": 6.293089609549325e-06,
"loss": 1.4543,
"step": 594
},
{
"epoch": 0.63,
"learning_rate": 6.261048315245419e-06,
"loss": 1.4055,
"step": 595
},
{
"epoch": 0.63,
"learning_rate": 6.229051583116796e-06,
"loss": 1.4087,
"step": 596
},
{
"epoch": 0.64,
"learning_rate": 6.197099794512056e-06,
"loss": 1.4597,
"step": 597
},
{
"epoch": 0.64,
"learning_rate": 6.165193330244144e-06,
"loss": 1.4482,
"step": 598
},
{
"epoch": 0.64,
"learning_rate": 6.133332570585813e-06,
"loss": 1.4774,
"step": 599
},
{
"epoch": 0.64,
"learning_rate": 6.101517895265094e-06,
"loss": 1.4591,
"step": 600
},
{
"epoch": 0.64,
"learning_rate": 6.069749683460765e-06,
"loss": 1.4033,
"step": 601
},
{
"epoch": 0.64,
"learning_rate": 6.03802831379784e-06,
"loss": 1.4532,
"step": 602
},
{
"epoch": 0.64,
"learning_rate": 6.006354164343047e-06,
"loss": 1.4047,
"step": 603
},
{
"epoch": 0.64,
"learning_rate": 5.9747276126003265e-06,
"loss": 1.4038,
"step": 604
},
{
"epoch": 0.64,
"learning_rate": 5.943149035506337e-06,
"loss": 1.3674,
"step": 605
},
{
"epoch": 0.65,
"learning_rate": 5.911618809425952e-06,
"loss": 1.4148,
"step": 606
},
{
"epoch": 0.65,
"learning_rate": 5.880137310147782e-06,
"loss": 1.3599,
"step": 607
},
{
"epoch": 0.65,
"learning_rate": 5.848704912879699e-06,
"loss": 1.4117,
"step": 608
},
{
"epoch": 0.65,
"learning_rate": 5.8173219922443516e-06,
"loss": 1.3778,
"step": 609
},
{
"epoch": 0.65,
"learning_rate": 5.785988922274711e-06,
"loss": 1.3949,
"step": 610
},
{
"epoch": 0.65,
"learning_rate": 5.754706076409613e-06,
"loss": 1.3936,
"step": 611
},
{
"epoch": 0.65,
"learning_rate": 5.723473827489301e-06,
"loss": 1.3791,
"step": 612
},
{
"epoch": 0.65,
"learning_rate": 5.692292547750989e-06,
"loss": 1.3731,
"step": 613
},
{
"epoch": 0.65,
"learning_rate": 5.66116260882442e-06,
"loss": 1.3494,
"step": 614
},
{
"epoch": 0.65,
"learning_rate": 5.630084381727434e-06,
"loss": 1.3684,
"step": 615
},
{
"epoch": 0.66,
"learning_rate": 5.599058236861559e-06,
"loss": 1.393,
"step": 616
},
{
"epoch": 0.66,
"learning_rate": 5.5680845440075885e-06,
"loss": 1.3822,
"step": 617
},
{
"epoch": 0.66,
"learning_rate": 5.537163672321161e-06,
"loss": 1.4098,
"step": 618
},
{
"epoch": 0.66,
"learning_rate": 5.5062959903283855e-06,
"loss": 1.3855,
"step": 619
},
{
"epoch": 0.66,
"learning_rate": 5.475481865921441e-06,
"loss": 1.3947,
"step": 620
},
{
"epoch": 0.66,
"learning_rate": 5.444721666354169e-06,
"loss": 1.4017,
"step": 621
},
{
"epoch": 0.66,
"learning_rate": 5.414015758237734e-06,
"loss": 1.3624,
"step": 622
},
{
"epoch": 0.66,
"learning_rate": 5.3833645075362295e-06,
"loss": 1.3811,
"step": 623
},
{
"epoch": 0.66,
"learning_rate": 5.352768279562315e-06,
"loss": 1.36,
"step": 624
},
{
"epoch": 0.67,
"learning_rate": 5.32222743897288e-06,
"loss": 1.3381,
"step": 625
},
{
"epoch": 0.67,
"learning_rate": 5.2917423497646834e-06,
"loss": 1.3747,
"step": 626
},
{
"epoch": 0.67,
"learning_rate": 5.2613133752700145e-06,
"loss": 1.3995,
"step": 627
},
{
"epoch": 0.67,
"learning_rate": 5.230940878152371e-06,
"loss": 1.3959,
"step": 628
},
{
"epoch": 0.67,
"learning_rate": 5.200625220402139e-06,
"loss": 1.371,
"step": 629
},
{
"epoch": 0.67,
"learning_rate": 5.1703667633322575e-06,
"loss": 1.4439,
"step": 630
},
{
"epoch": 0.67,
"learning_rate": 5.14016586757394e-06,
"loss": 1.3963,
"step": 631
},
{
"epoch": 0.67,
"learning_rate": 5.110022893072361e-06,
"loss": 1.4649,
"step": 632
},
{
"epoch": 0.67,
"learning_rate": 5.079938199082363e-06,
"loss": 1.439,
"step": 633
},
{
"epoch": 0.68,
"learning_rate": 5.049912144164186e-06,
"loss": 1.4671,
"step": 634
},
{
"epoch": 0.68,
"learning_rate": 5.019945086179192e-06,
"loss": 1.4567,
"step": 635
},
{
"epoch": 0.68,
"learning_rate": 4.9900373822855805e-06,
"loss": 1.432,
"step": 636
},
{
"epoch": 0.68,
"learning_rate": 4.960189388934163e-06,
"loss": 1.3947,
"step": 637
},
{
"epoch": 0.68,
"learning_rate": 4.930401461864099e-06,
"loss": 1.3857,
"step": 638
},
{
"epoch": 0.68,
"learning_rate": 4.900673956098644e-06,
"loss": 1.4267,
"step": 639
},
{
"epoch": 0.68,
"learning_rate": 4.87100722594094e-06,
"loss": 1.3827,
"step": 640
},
{
"epoch": 0.68,
"learning_rate": 4.841401624969782e-06,
"loss": 1.4627,
"step": 641
},
{
"epoch": 0.68,
"learning_rate": 4.811857506035407e-06,
"loss": 1.4148,
"step": 642
},
{
"epoch": 0.68,
"learning_rate": 4.7823752212552855e-06,
"loss": 1.4149,
"step": 643
},
{
"epoch": 0.69,
"learning_rate": 4.75295512200992e-06,
"loss": 1.4331,
"step": 644
},
{
"epoch": 0.69,
"learning_rate": 4.7235975589386715e-06,
"loss": 1.3733,
"step": 645
},
{
"epoch": 0.69,
"learning_rate": 4.694302881935574e-06,
"loss": 1.4125,
"step": 646
},
{
"epoch": 0.69,
"learning_rate": 4.66507144014515e-06,
"loss": 1.3746,
"step": 647
},
{
"epoch": 0.69,
"learning_rate": 4.635903581958276e-06,
"loss": 1.4322,
"step": 648
},
{
"epoch": 0.69,
"learning_rate": 4.606799655008009e-06,
"loss": 1.3944,
"step": 649
},
{
"epoch": 0.69,
"learning_rate": 4.5777600061654505e-06,
"loss": 1.3978,
"step": 650
},
{
"epoch": 0.69,
"learning_rate": 4.5487849815356145e-06,
"loss": 1.4103,
"step": 651
},
{
"epoch": 0.69,
"learning_rate": 4.519874926453303e-06,
"loss": 1.3392,
"step": 652
},
{
"epoch": 0.7,
"learning_rate": 4.491030185478976e-06,
"loss": 1.423,
"step": 653
},
{
"epoch": 0.7,
"learning_rate": 4.462251102394669e-06,
"loss": 1.4242,
"step": 654
},
{
"epoch": 0.7,
"learning_rate": 4.433538020199882e-06,
"loss": 1.4049,
"step": 655
},
{
"epoch": 0.7,
"learning_rate": 4.404891281107482e-06,
"loss": 1.3881,
"step": 656
},
{
"epoch": 0.7,
"learning_rate": 4.3763112265396445e-06,
"loss": 1.4161,
"step": 657
},
{
"epoch": 0.7,
"learning_rate": 4.347798197123777e-06,
"loss": 1.3758,
"step": 658
},
{
"epoch": 0.7,
"learning_rate": 4.319352532688444e-06,
"loss": 1.4278,
"step": 659
},
{
"epoch": 0.7,
"learning_rate": 4.290974572259342e-06,
"loss": 1.392,
"step": 660
},
{
"epoch": 0.7,
"learning_rate": 4.262664654055247e-06,
"loss": 1.3901,
"step": 661
},
{
"epoch": 0.71,
"learning_rate": 4.234423115483971e-06,
"loss": 1.361,
"step": 662
},
{
"epoch": 0.71,
"learning_rate": 4.206250293138366e-06,
"loss": 1.4277,
"step": 663
},
{
"epoch": 0.71,
"learning_rate": 4.178146522792296e-06,
"loss": 1.4293,
"step": 664
},
{
"epoch": 0.71,
"learning_rate": 4.15011213939663e-06,
"loss": 1.4102,
"step": 665
},
{
"epoch": 0.71,
"learning_rate": 4.12214747707527e-06,
"loss": 1.4356,
"step": 666
},
{
"epoch": 0.71,
"learning_rate": 4.094252869121153e-06,
"loss": 1.4082,
"step": 667
},
{
"epoch": 0.71,
"learning_rate": 4.066428647992275e-06,
"loss": 1.4232,
"step": 668
},
{
"epoch": 0.71,
"learning_rate": 4.038675145307747e-06,
"loss": 1.3426,
"step": 669
},
{
"epoch": 0.71,
"learning_rate": 4.010992691843829e-06,
"loss": 1.3852,
"step": 670
},
{
"epoch": 0.71,
"learning_rate": 3.98338161752999e-06,
"loss": 1.4213,
"step": 671
},
{
"epoch": 0.72,
"learning_rate": 3.955842251444978e-06,
"loss": 1.4162,
"step": 672
},
{
"epoch": 0.72,
"learning_rate": 3.9283749218128885e-06,
"loss": 1.3963,
"step": 673
},
{
"epoch": 0.72,
"learning_rate": 3.900979955999271e-06,
"loss": 1.3691,
"step": 674
},
{
"epoch": 0.72,
"learning_rate": 3.8736576805072165e-06,
"loss": 1.4038,
"step": 675
},
{
"epoch": 0.72,
"learning_rate": 3.846408420973456e-06,
"loss": 1.4053,
"step": 676
},
{
"epoch": 0.72,
"learning_rate": 3.819232502164499e-06,
"loss": 1.4068,
"step": 677
},
{
"epoch": 0.72,
"learning_rate": 3.792130247972756e-06,
"loss": 1.4022,
"step": 678
},
{
"epoch": 0.72,
"learning_rate": 3.7651019814126656e-06,
"loss": 1.3781,
"step": 679
},
{
"epoch": 0.72,
"learning_rate": 3.738148024616863e-06,
"loss": 1.3778,
"step": 680
},
{
"epoch": 0.73,
"learning_rate": 3.7112686988323353e-06,
"loss": 1.4079,
"step": 681
},
{
"epoch": 0.73,
"learning_rate": 3.684464324416578e-06,
"loss": 1.3999,
"step": 682
},
{
"epoch": 0.73,
"learning_rate": 3.6577352208338015e-06,
"loss": 1.4448,
"step": 683
},
{
"epoch": 0.73,
"learning_rate": 3.6310817066511106e-06,
"loss": 1.3255,
"step": 684
},
{
"epoch": 0.73,
"learning_rate": 3.604504099534696e-06,
"loss": 1.4112,
"step": 685
},
{
"epoch": 0.73,
"learning_rate": 3.578002716246074e-06,
"loss": 1.3448,
"step": 686
},
{
"epoch": 0.73,
"learning_rate": 3.5515778726382967e-06,
"loss": 1.3451,
"step": 687
},
{
"epoch": 0.73,
"learning_rate": 3.525229883652177e-06,
"loss": 1.3654,
"step": 688
},
{
"epoch": 0.73,
"learning_rate": 3.4989590633125583e-06,
"loss": 1.395,
"step": 689
},
{
"epoch": 0.73,
"learning_rate": 3.4727657247245607e-06,
"loss": 1.3415,
"step": 690
},
{
"epoch": 0.74,
"learning_rate": 3.446650180069837e-06,
"loss": 1.3773,
"step": 691
},
{
"epoch": 0.74,
"learning_rate": 3.4206127406028744e-06,
"loss": 1.3573,
"step": 692
},
{
"epoch": 0.74,
"learning_rate": 3.394653716647277e-06,
"loss": 1.3794,
"step": 693
},
{
"epoch": 0.74,
"learning_rate": 3.3687734175920505e-06,
"loss": 1.4105,
"step": 694
},
{
"epoch": 0.74,
"learning_rate": 3.342972151887941e-06,
"loss": 1.4044,
"step": 695
},
{
"epoch": 0.74,
"learning_rate": 3.317250227043746e-06,
"loss": 1.363,
"step": 696
},
{
"epoch": 0.74,
"learning_rate": 3.2916079496226407e-06,
"loss": 1.4142,
"step": 697
},
{
"epoch": 0.74,
"learning_rate": 3.266045625238539e-06,
"loss": 1.3536,
"step": 698
},
{
"epoch": 0.74,
"learning_rate": 3.2405635585524566e-06,
"loss": 1.3509,
"step": 699
},
{
"epoch": 0.75,
"learning_rate": 3.21516205326885e-06,
"loss": 1.3867,
"step": 700
},
{
"epoch": 0.75,
"learning_rate": 3.1898414121320277e-06,
"loss": 1.3732,
"step": 701
},
{
"epoch": 0.75,
"learning_rate": 3.1646019369225277e-06,
"loss": 1.3868,
"step": 702
},
{
"epoch": 0.75,
"learning_rate": 3.1394439284535206e-06,
"loss": 1.3303,
"step": 703
},
{
"epoch": 0.75,
"learning_rate": 3.114367686567228e-06,
"loss": 1.3512,
"step": 704
},
{
"epoch": 0.75,
"learning_rate": 3.089373510131354e-06,
"loss": 1.272,
"step": 705
},
{
"epoch": 0.75,
"learning_rate": 3.064461697035506e-06,
"loss": 1.3246,
"step": 706
},
{
"epoch": 0.75,
"learning_rate": 3.0396325441876627e-06,
"loss": 1.3065,
"step": 707
},
{
"epoch": 0.75,
"learning_rate": 3.0148863475106315e-06,
"loss": 1.3174,
"step": 708
},
{
"epoch": 0.76,
"learning_rate": 2.9902234019385056e-06,
"loss": 1.3432,
"step": 709
},
{
"epoch": 0.76,
"learning_rate": 2.9656440014131737e-06,
"loss": 1.3074,
"step": 710
},
{
"epoch": 0.76,
"learning_rate": 2.941148438880803e-06,
"loss": 1.3473,
"step": 711
},
{
"epoch": 0.76,
"learning_rate": 2.9167370062883403e-06,
"loss": 1.367,
"step": 712
},
{
"epoch": 0.76,
"learning_rate": 2.8924099945800533e-06,
"loss": 1.3223,
"step": 713
},
{
"epoch": 0.76,
"learning_rate": 2.8681676936940397e-06,
"loss": 1.3527,
"step": 714
},
{
"epoch": 0.76,
"learning_rate": 2.8440103925587904e-06,
"loss": 1.3483,
"step": 715
},
{
"epoch": 0.76,
"learning_rate": 2.8199383790897405e-06,
"loss": 1.4005,
"step": 716
},
{
"epoch": 0.76,
"learning_rate": 2.795951940185827e-06,
"loss": 1.3571,
"step": 717
},
{
"epoch": 0.76,
"learning_rate": 2.7720513617260857e-06,
"loss": 1.3206,
"step": 718
},
{
"epoch": 0.77,
"learning_rate": 2.748236928566238e-06,
"loss": 1.3021,
"step": 719
},
{
"epoch": 0.77,
"learning_rate": 2.7245089245352864e-06,
"loss": 1.3046,
"step": 720
},
{
"epoch": 0.77,
"learning_rate": 2.700867632432145e-06,
"loss": 1.3088,
"step": 721
},
{
"epoch": 0.77,
"learning_rate": 2.6773133340222677e-06,
"loss": 1.3458,
"step": 722
},
{
"epoch": 0.77,
"learning_rate": 2.6538463100342773e-06,
"loss": 1.3551,
"step": 723
},
{
"epoch": 0.77,
"learning_rate": 2.6304668401566334e-06,
"loss": 1.3482,
"step": 724
},
{
"epoch": 0.77,
"learning_rate": 2.607175203034299e-06,
"loss": 1.4264,
"step": 725
},
{
"epoch": 0.77,
"learning_rate": 2.5839716762654e-06,
"loss": 1.3241,
"step": 726
},
{
"epoch": 0.77,
"learning_rate": 2.56085653639795e-06,
"loss": 1.3467,
"step": 727
},
{
"epoch": 0.78,
"learning_rate": 2.5378300589265258e-06,
"loss": 1.3043,
"step": 728
},
{
"epoch": 0.78,
"learning_rate": 2.514892518288988e-06,
"loss": 1.273,
"step": 729
},
{
"epoch": 0.78,
"learning_rate": 2.4920441878632273e-06,
"loss": 1.3116,
"step": 730
},
{
"epoch": 0.78,
"learning_rate": 2.469285339963892e-06,
"loss": 1.2757,
"step": 731
},
{
"epoch": 0.78,
"learning_rate": 2.4466162458391364e-06,
"loss": 1.3607,
"step": 732
},
{
"epoch": 0.78,
"learning_rate": 2.4240371756674063e-06,
"loss": 1.3103,
"step": 733
},
{
"epoch": 0.78,
"learning_rate": 2.401548398554213e-06,
"loss": 1.3143,
"step": 734
},
{
"epoch": 0.78,
"learning_rate": 2.379150182528909e-06,
"loss": 1.3441,
"step": 735
},
{
"epoch": 0.78,
"learning_rate": 2.3568427945415163e-06,
"loss": 1.342,
"step": 736
},
{
"epoch": 0.78,
"learning_rate": 2.334626500459539e-06,
"loss": 1.357,
"step": 737
},
{
"epoch": 0.79,
"learning_rate": 2.3125015650647798e-06,
"loss": 1.3311,
"step": 738
},
{
"epoch": 0.79,
"learning_rate": 2.290468252050204e-06,
"loss": 1.3029,
"step": 739
},
{
"epoch": 0.79,
"learning_rate": 2.26852682401679e-06,
"loss": 1.2941,
"step": 740
},
{
"epoch": 0.79,
"learning_rate": 2.246677542470388e-06,
"loss": 1.3345,
"step": 741
},
{
"epoch": 0.79,
"learning_rate": 2.224920667818622e-06,
"loss": 1.3293,
"step": 742
},
{
"epoch": 0.79,
"learning_rate": 2.2032564593677773e-06,
"loss": 1.3492,
"step": 743
},
{
"epoch": 0.79,
"learning_rate": 2.1816851753197023e-06,
"loss": 1.3409,
"step": 744
},
{
"epoch": 0.79,
"learning_rate": 2.1602070727687463e-06,
"loss": 1.2992,
"step": 745
},
{
"epoch": 0.79,
"learning_rate": 2.1388224076986872e-06,
"loss": 1.3174,
"step": 746
},
{
"epoch": 0.8,
"learning_rate": 2.117531434979675e-06,
"loss": 1.3369,
"step": 747
},
{
"epoch": 0.8,
"learning_rate": 2.096334408365207e-06,
"loss": 1.358,
"step": 748
},
{
"epoch": 0.8,
"learning_rate": 2.075231580489098e-06,
"loss": 1.2893,
"step": 749
},
{
"epoch": 0.8,
"learning_rate": 2.0542232028624585e-06,
"loss": 1.3591,
"step": 750
},
{
"epoch": 0.8,
"learning_rate": 2.033309525870717e-06,
"loss": 1.4026,
"step": 751
},
{
"epoch": 0.8,
"learning_rate": 2.0124907987706243e-06,
"loss": 1.3592,
"step": 752
},
{
"epoch": 0.8,
"learning_rate": 1.991767269687278e-06,
"loss": 1.3494,
"step": 753
},
{
"epoch": 0.8,
"learning_rate": 1.971139185611176e-06,
"loss": 1.4054,
"step": 754
},
{
"epoch": 0.8,
"learning_rate": 1.9506067923952676e-06,
"loss": 1.4085,
"step": 755
},
{
"epoch": 0.81,
"learning_rate": 1.930170334752025e-06,
"loss": 1.4354,
"step": 756
},
{
"epoch": 0.81,
"learning_rate": 1.9098300562505266e-06,
"loss": 1.3608,
"step": 757
},
{
"epoch": 0.81,
"learning_rate": 1.8895861993135444e-06,
"loss": 1.4078,
"step": 758
},
{
"epoch": 0.81,
"learning_rate": 1.8694390052146737e-06,
"loss": 1.4,
"step": 759
},
{
"epoch": 0.81,
"learning_rate": 1.8493887140754462e-06,
"loss": 1.3905,
"step": 760
},
{
"epoch": 0.81,
"learning_rate": 1.8294355648624607e-06,
"loss": 1.3273,
"step": 761
},
{
"epoch": 0.81,
"learning_rate": 1.8095797953845507e-06,
"loss": 1.3724,
"step": 762
},
{
"epoch": 0.81,
"learning_rate": 1.789821642289945e-06,
"loss": 1.3609,
"step": 763
},
{
"epoch": 0.81,
"learning_rate": 1.7701613410634367e-06,
"loss": 1.3325,
"step": 764
},
{
"epoch": 0.81,
"learning_rate": 1.750599126023591e-06,
"loss": 1.349,
"step": 765
},
{
"epoch": 0.82,
"learning_rate": 1.731135230319948e-06,
"loss": 1.3834,
"step": 766
},
{
"epoch": 0.82,
"learning_rate": 1.7117698859302357e-06,
"loss": 1.357,
"step": 767
},
{
"epoch": 0.82,
"learning_rate": 1.692503323657617e-06,
"loss": 1.324,
"step": 768
},
{
"epoch": 0.82,
"learning_rate": 1.6733357731279375e-06,
"loss": 1.3504,
"step": 769
},
{
"epoch": 0.82,
"learning_rate": 1.6542674627869738e-06,
"loss": 1.3336,
"step": 770
},
{
"epoch": 0.82,
"learning_rate": 1.6352986198977327e-06,
"loss": 1.4053,
"step": 771
},
{
"epoch": 0.82,
"learning_rate": 1.6164294705377292e-06,
"loss": 1.3555,
"step": 772
},
{
"epoch": 0.82,
"learning_rate": 1.5976602395962892e-06,
"loss": 1.4067,
"step": 773
},
{
"epoch": 0.82,
"learning_rate": 1.5789911507718824e-06,
"loss": 1.375,
"step": 774
},
{
"epoch": 0.83,
"learning_rate": 1.560422426569449e-06,
"loss": 1.4066,
"step": 775
},
{
"epoch": 0.83,
"learning_rate": 1.5419542882977367e-06,
"loss": 1.3717,
"step": 776
},
{
"epoch": 0.83,
"learning_rate": 1.523586956066686e-06,
"loss": 1.3841,
"step": 777
},
{
"epoch": 0.83,
"learning_rate": 1.5053206487847916e-06,
"loss": 1.4082,
"step": 778
},
{
"epoch": 0.83,
"learning_rate": 1.4871555841564889e-06,
"loss": 1.3902,
"step": 779
},
{
"epoch": 0.83,
"learning_rate": 1.4690919786795766e-06,
"loss": 1.3165,
"step": 780
},
{
"epoch": 0.83,
"learning_rate": 1.4511300476426227e-06,
"loss": 1.4285,
"step": 781
},
{
"epoch": 0.83,
"learning_rate": 1.433270005122399e-06,
"loss": 1.3688,
"step": 782
},
{
"epoch": 0.83,
"learning_rate": 1.4155120639813392e-06,
"loss": 1.3907,
"step": 783
},
{
"epoch": 0.83,
"learning_rate": 1.3978564358649926e-06,
"loss": 1.3385,
"step": 784
},
{
"epoch": 0.84,
"learning_rate": 1.3803033311995072e-06,
"loss": 1.3406,
"step": 785
},
{
"epoch": 0.84,
"learning_rate": 1.3628529591891181e-06,
"loss": 1.3904,
"step": 786
},
{
"epoch": 0.84,
"learning_rate": 1.345505527813652e-06,
"loss": 1.3294,
"step": 787
},
{
"epoch": 0.84,
"learning_rate": 1.3282612438260578e-06,
"loss": 1.3071,
"step": 788
},
{
"epoch": 0.84,
"learning_rate": 1.311120312749935e-06,
"loss": 1.3666,
"step": 789
},
{
"epoch": 0.84,
"learning_rate": 1.2940829388770837e-06,
"loss": 1.3324,
"step": 790
},
{
"epoch": 0.84,
"learning_rate": 1.2771493252650723e-06,
"loss": 1.3744,
"step": 791
},
{
"epoch": 0.84,
"learning_rate": 1.2603196737348211e-06,
"loss": 1.3823,
"step": 792
},
{
"epoch": 0.84,
"learning_rate": 1.2435941848681864e-06,
"loss": 1.3713,
"step": 793
},
{
"epoch": 0.85,
"learning_rate": 1.2269730580055806e-06,
"loss": 1.4273,
"step": 794
},
{
"epoch": 0.85,
"learning_rate": 1.2104564912435924e-06,
"loss": 1.4072,
"step": 795
},
{
"epoch": 0.85,
"learning_rate": 1.19404468143262e-06,
"loss": 1.422,
"step": 796
},
{
"epoch": 0.85,
"learning_rate": 1.1777378241745385e-06,
"loss": 1.4358,
"step": 797
},
{
"epoch": 0.85,
"learning_rate": 1.1615361138203574e-06,
"loss": 1.403,
"step": 798
},
{
"epoch": 0.85,
"learning_rate": 1.1454397434679022e-06,
"loss": 1.381,
"step": 799
},
{
"epoch": 0.85,
"learning_rate": 1.1294489049595247e-06,
"loss": 1.3256,
"step": 800
},
{
"epoch": 0.85,
"learning_rate": 1.1135637888798101e-06,
"loss": 1.3805,
"step": 801
},
{
"epoch": 0.85,
"learning_rate": 1.0977845845533009e-06,
"loss": 1.3827,
"step": 802
},
{
"epoch": 0.86,
"learning_rate": 1.0821114800422482e-06,
"loss": 1.3479,
"step": 803
},
{
"epoch": 0.86,
"learning_rate": 1.066544662144371e-06,
"loss": 1.3509,
"step": 804
},
{
"epoch": 0.86,
"learning_rate": 1.0510843163906148e-06,
"loss": 1.3852,
"step": 805
},
{
"epoch": 0.86,
"learning_rate": 1.0357306270429623e-06,
"loss": 1.3994,
"step": 806
},
{
"epoch": 0.86,
"learning_rate": 1.020483777092226e-06,
"loss": 1.4143,
"step": 807
},
{
"epoch": 0.86,
"learning_rate": 1.0053439482558602e-06,
"loss": 1.4318,
"step": 808
},
{
"epoch": 0.86,
"learning_rate": 9.903113209758098e-07,
"loss": 1.3666,
"step": 809
},
{
"epoch": 0.86,
"learning_rate": 9.753860744163524e-07,
"loss": 1.3442,
"step": 810
},
{
"epoch": 0.86,
"learning_rate": 9.605683864619574e-07,
"loss": 1.335,
"step": 811
},
{
"epoch": 0.86,
"learning_rate": 9.458584337151811e-07,
"loss": 1.3153,
"step": 812
},
{
"epoch": 0.87,
"learning_rate": 9.312563914945461e-07,
"loss": 1.3872,
"step": 813
},
{
"epoch": 0.87,
"learning_rate": 9.167624338324599e-07,
"loss": 1.3549,
"step": 814
},
{
"epoch": 0.87,
"learning_rate": 9.023767334731426e-07,
"loss": 1.37,
"step": 815
},
{
"epoch": 0.87,
"learning_rate": 8.880994618705574e-07,
"loss": 1.3776,
"step": 816
},
{
"epoch": 0.87,
"learning_rate": 8.739307891863813e-07,
"loss": 1.4034,
"step": 817
},
{
"epoch": 0.87,
"learning_rate": 8.598708842879688e-07,
"loss": 1.3344,
"step": 818
},
{
"epoch": 0.87,
"learning_rate": 8.459199147463371e-07,
"loss": 1.3836,
"step": 819
},
{
"epoch": 0.87,
"learning_rate": 8.320780468341761e-07,
"loss": 1.3771,
"step": 820
},
{
"epoch": 0.87,
"learning_rate": 8.183454455238638e-07,
"loss": 1.3803,
"step": 821
},
{
"epoch": 0.88,
"learning_rate": 8.047222744854943e-07,
"loss": 1.3975,
"step": 822
},
{
"epoch": 0.88,
"learning_rate": 7.912086960849374e-07,
"loss": 1.4242,
"step": 823
},
{
"epoch": 0.88,
"learning_rate": 7.778048713818975e-07,
"loss": 1.3461,
"step": 824
},
{
"epoch": 0.88,
"learning_rate": 7.645109601279921e-07,
"loss": 1.3611,
"step": 825
},
{
"epoch": 0.88,
"learning_rate": 7.513271207648531e-07,
"loss": 1.3385,
"step": 826
},
{
"epoch": 0.88,
"learning_rate": 7.382535104222366e-07,
"loss": 1.3512,
"step": 827
},
{
"epoch": 0.88,
"learning_rate": 7.252902849161436e-07,
"loss": 1.3598,
"step": 828
},
{
"epoch": 0.88,
"learning_rate": 7.124375987469767e-07,
"loss": 1.3474,
"step": 829
},
{
"epoch": 0.88,
"learning_rate": 6.996956050976878e-07,
"loss": 1.3655,
"step": 830
},
{
"epoch": 0.88,
"learning_rate": 6.870644558319528e-07,
"loss": 1.3836,
"step": 831
},
{
"epoch": 0.89,
"learning_rate": 6.745443014923658e-07,
"loss": 1.3639,
"step": 832
},
{
"epoch": 0.89,
"learning_rate": 6.621352912986468e-07,
"loss": 1.4108,
"step": 833
},
{
"epoch": 0.89,
"learning_rate": 6.498375731458529e-07,
"loss": 1.3678,
"step": 834
},
{
"epoch": 0.89,
"learning_rate": 6.37651293602628e-07,
"loss": 1.4289,
"step": 835
},
{
"epoch": 0.89,
"learning_rate": 6.255765979094519e-07,
"loss": 1.4015,
"step": 836
},
{
"epoch": 0.89,
"learning_rate": 6.136136299768991e-07,
"loss": 1.3921,
"step": 837
},
{
"epoch": 0.89,
"learning_rate": 6.017625323839415e-07,
"loss": 1.3222,
"step": 838
},
{
"epoch": 0.89,
"learning_rate": 5.900234463762367e-07,
"loss": 1.2964,
"step": 839
},
{
"epoch": 0.89,
"learning_rate": 5.783965118644441e-07,
"loss": 1.3172,
"step": 840
},
{
"epoch": 0.9,
"learning_rate": 5.668818674225684e-07,
"loss": 1.3086,
"step": 841
},
{
"epoch": 0.9,
"learning_rate": 5.554796502862958e-07,
"loss": 1.3555,
"step": 842
},
{
"epoch": 0.9,
"learning_rate": 5.441899963513631e-07,
"loss": 1.2839,
"step": 843
},
{
"epoch": 0.9,
"learning_rate": 5.330130401719413e-07,
"loss": 1.3084,
"step": 844
},
{
"epoch": 0.9,
"learning_rate": 5.219489149590251e-07,
"loss": 1.2955,
"step": 845
},
{
"epoch": 0.9,
"learning_rate": 5.109977525788512e-07,
"loss": 1.3494,
"step": 846
},
{
"epoch": 0.9,
"learning_rate": 5.001596835513256e-07,
"loss": 1.4028,
"step": 847
},
{
"epoch": 0.9,
"learning_rate": 4.894348370484648e-07,
"loss": 1.3142,
"step": 848
},
{
"epoch": 0.9,
"learning_rate": 4.788233408928588e-07,
"loss": 1.3089,
"step": 849
},
{
"epoch": 0.91,
"learning_rate": 4.6832532155614895e-07,
"loss": 1.3285,
"step": 850
},
{
"epoch": 0.91,
"learning_rate": 4.5794090415751666e-07,
"loss": 1.3344,
"step": 851
},
{
"epoch": 0.91,
"learning_rate": 4.4767021246219566e-07,
"loss": 1.3726,
"step": 852
},
{
"epoch": 0.91,
"learning_rate": 4.3751336887999597e-07,
"loss": 1.3551,
"step": 853
},
{
"epoch": 0.91,
"learning_rate": 4.27470494463843e-07,
"loss": 1.3477,
"step": 854
},
{
"epoch": 0.91,
"learning_rate": 4.1754170890833777e-07,
"loss": 1.3236,
"step": 855
},
{
"epoch": 0.91,
"learning_rate": 4.077271305483321e-07,
"loss": 1.3299,
"step": 856
},
{
"epoch": 0.91,
"learning_rate": 3.980268763575079e-07,
"loss": 1.3827,
"step": 857
},
{
"epoch": 0.91,
"learning_rate": 3.8844106194699696e-07,
"loss": 1.3768,
"step": 858
},
{
"epoch": 0.91,
"learning_rate": 3.7896980156399533e-07,
"loss": 1.2947,
"step": 859
},
{
"epoch": 0.92,
"learning_rate": 3.6961320809039914e-07,
"loss": 1.3143,
"step": 860
},
{
"epoch": 0.92,
"learning_rate": 3.603713930414676e-07,
"loss": 1.3345,
"step": 861
},
{
"epoch": 0.92,
"learning_rate": 3.5124446656448654e-07,
"loss": 1.3189,
"step": 862
},
{
"epoch": 0.92,
"learning_rate": 3.42232537437458e-07,
"loss": 1.315,
"step": 863
},
{
"epoch": 0.92,
"learning_rate": 3.33335713067805e-07,
"loss": 1.2837,
"step": 864
},
{
"epoch": 0.92,
"learning_rate": 3.245540994910934e-07,
"loss": 1.3529,
"step": 865
},
{
"epoch": 0.92,
"learning_rate": 3.158878013697586e-07,
"loss": 1.313,
"step": 866
},
{
"epoch": 0.92,
"learning_rate": 3.073369219918698e-07,
"loss": 1.3368,
"step": 867
},
{
"epoch": 0.92,
"learning_rate": 2.989015632698944e-07,
"loss": 1.3401,
"step": 868
},
{
"epoch": 0.93,
"learning_rate": 2.905818257394799e-07,
"loss": 1.3424,
"step": 869
},
{
"epoch": 0.93,
"learning_rate": 2.8237780855825957e-07,
"loss": 1.3414,
"step": 870
},
{
"epoch": 0.93,
"learning_rate": 2.742896095046732e-07,
"loss": 1.3981,
"step": 871
},
{
"epoch": 0.93,
"learning_rate": 2.6631732497679363e-07,
"loss": 1.3217,
"step": 872
},
{
"epoch": 0.93,
"learning_rate": 2.584610499911833e-07,
"loss": 1.362,
"step": 873
},
{
"epoch": 0.93,
"learning_rate": 2.507208781817638e-07,
"loss": 1.3685,
"step": 874
},
{
"epoch": 0.93,
"learning_rate": 2.4309690179869503e-07,
"loss": 1.3455,
"step": 875
},
{
"epoch": 0.93,
"learning_rate": 2.355892117072789e-07,
"loss": 1.3447,
"step": 876
},
{
"epoch": 0.93,
"learning_rate": 2.2819789738687482e-07,
"loss": 1.3809,
"step": 877
},
{
"epoch": 0.94,
"learning_rate": 2.2092304692983402e-07,
"loss": 1.3294,
"step": 878
},
{
"epoch": 0.94,
"learning_rate": 2.1376474704044693e-07,
"loss": 1.3443,
"step": 879
},
{
"epoch": 0.94,
"learning_rate": 2.067230830339184e-07,
"loss": 1.3464,
"step": 880
},
{
"epoch": 0.94,
"learning_rate": 1.9979813883533762e-07,
"loss": 1.3299,
"step": 881
},
{
"epoch": 0.94,
"learning_rate": 1.929899969786897e-07,
"loss": 1.3551,
"step": 882
},
{
"epoch": 0.94,
"learning_rate": 1.8629873860586567e-07,
"loss": 1.3127,
"step": 883
},
{
"epoch": 0.94,
"learning_rate": 1.7972444346569752e-07,
"loss": 1.321,
"step": 884
},
{
"epoch": 0.94,
"learning_rate": 1.7326718991300563e-07,
"loss": 1.3357,
"step": 885
},
{
"epoch": 0.94,
"learning_rate": 1.6692705490766958e-07,
"loss": 1.3313,
"step": 886
},
{
"epoch": 0.94,
"learning_rate": 1.6070411401370335e-07,
"loss": 1.3506,
"step": 887
},
{
"epoch": 0.95,
"learning_rate": 1.5459844139836476e-07,
"loss": 1.4046,
"step": 888
},
{
"epoch": 0.95,
"learning_rate": 1.4861010983126202e-07,
"loss": 1.3149,
"step": 889
},
{
"epoch": 0.95,
"learning_rate": 1.4273919068349184e-07,
"loss": 1.3421,
"step": 890
},
{
"epoch": 0.95,
"learning_rate": 1.3698575392678492e-07,
"loss": 1.33,
"step": 891
},
{
"epoch": 0.95,
"learning_rate": 1.3134986813267968e-07,
"loss": 1.2979,
"step": 892
},
{
"epoch": 0.95,
"learning_rate": 1.258316004716953e-07,
"loss": 1.3591,
"step": 893
},
{
"epoch": 0.95,
"learning_rate": 1.2043101671253553e-07,
"loss": 1.3829,
"step": 894
},
{
"epoch": 0.95,
"learning_rate": 1.1514818122130844e-07,
"loss": 1.3686,
"step": 895
},
{
"epoch": 0.95,
"learning_rate": 1.0998315696075123e-07,
"loss": 1.2892,
"step": 896
},
{
"epoch": 0.96,
"learning_rate": 1.0493600548948879e-07,
"loss": 1.321,
"step": 897
},
{
"epoch": 0.96,
"learning_rate": 1.0000678696129307e-07,
"loss": 1.3607,
"step": 898
},
{
"epoch": 0.96,
"learning_rate": 9.519556012436815e-08,
"loss": 1.3086,
"step": 899
},
{
"epoch": 0.96,
"learning_rate": 9.0502382320653e-08,
"loss": 1.4056,
"step": 900
},
{
"epoch": 0.96,
"learning_rate": 8.592730948513205e-08,
"loss": 1.4174,
"step": 901
},
{
"epoch": 0.96,
"learning_rate": 8.147039614517571e-08,
"loss": 1.351,
"step": 902
},
{
"epoch": 0.96,
"learning_rate": 7.71316954198853e-08,
"loss": 1.3241,
"step": 903
},
{
"epoch": 0.96,
"learning_rate": 7.291125901946027e-08,
"loss": 1.383,
"step": 904
},
{
"epoch": 0.96,
"learning_rate": 6.880913724458538e-08,
"loss": 1.4027,
"step": 905
},
{
"epoch": 0.96,
"learning_rate": 6.482537898582886e-08,
"loss": 1.3951,
"step": 906
},
{
"epoch": 0.97,
"learning_rate": 6.096003172305742e-08,
"loss": 1.3306,
"step": 907
},
{
"epoch": 0.97,
"learning_rate": 5.721314152487556e-08,
"loss": 1.3042,
"step": 908
},
{
"epoch": 0.97,
"learning_rate": 5.3584753048073756e-08,
"loss": 1.3237,
"step": 909
},
{
"epoch": 0.97,
"learning_rate": 5.007490953709227e-08,
"loss": 1.3512,
"step": 910
},
{
"epoch": 0.97,
"learning_rate": 4.6683652823513725e-08,
"loss": 1.3463,
"step": 911
},
{
"epoch": 0.97,
"learning_rate": 4.3411023325560245e-08,
"loss": 1.4014,
"step": 912
},
{
"epoch": 0.97,
"learning_rate": 4.025706004760932e-08,
"loss": 1.4032,
"step": 913
},
{
"epoch": 0.97,
"learning_rate": 3.7221800579735346e-08,
"loss": 1.376,
"step": 914
},
{
"epoch": 0.97,
"learning_rate": 3.430528109725439e-08,
"loss": 1.3516,
"step": 915
},
{
"epoch": 0.98,
"learning_rate": 3.150753636029902e-08,
"loss": 1.3278,
"step": 916
},
{
"epoch": 0.98,
"learning_rate": 2.8828599713398575e-08,
"loss": 1.3535,
"step": 917
},
{
"epoch": 0.98,
"learning_rate": 2.6268503085089547e-08,
"loss": 1.3505,
"step": 918
},
{
"epoch": 0.98,
"learning_rate": 2.3827276987524738e-08,
"loss": 1.3127,
"step": 919
},
{
"epoch": 0.98,
"learning_rate": 2.1504950516118007e-08,
"loss": 1.4123,
"step": 920
},
{
"epoch": 0.98,
"learning_rate": 1.9301551349195648e-08,
"loss": 1.3464,
"step": 921
},
{
"epoch": 0.98,
"learning_rate": 1.721710574766333e-08,
"loss": 1.3323,
"step": 922
},
{
"epoch": 0.98,
"learning_rate": 1.5251638554694137e-08,
"loss": 1.3436,
"step": 923
},
{
"epoch": 0.98,
"learning_rate": 1.340517319543877e-08,
"loss": 1.3348,
"step": 924
},
{
"epoch": 0.99,
"learning_rate": 1.1677731676733584e-08,
"loss": 1.3463,
"step": 925
},
{
"epoch": 0.99,
"learning_rate": 1.0069334586854106e-08,
"loss": 1.3532,
"step": 926
},
{
"epoch": 0.99,
"learning_rate": 8.580001095253032e-09,
"loss": 1.405,
"step": 927
},
{
"epoch": 0.99,
"learning_rate": 7.209748952347051e-09,
"loss": 1.3366,
"step": 928
},
{
"epoch": 0.99,
"learning_rate": 5.958594489295921e-09,
"loss": 1.3426,
"step": 929
},
{
"epoch": 0.99,
"learning_rate": 4.826552617807067e-09,
"loss": 1.3921,
"step": 930
},
{
"epoch": 0.99,
"learning_rate": 3.8136368299668266e-09,
"loss": 1.3739,
"step": 931
},
{
"epoch": 0.99,
"learning_rate": 2.9198591980705847e-09,
"loss": 1.4027,
"step": 932
},
{
"epoch": 0.99,
"learning_rate": 2.145230374481777e-09,
"loss": 1.3798,
"step": 933
},
{
"epoch": 0.99,
"learning_rate": 1.4897595915053242e-09,
"loss": 1.3796,
"step": 934
},
{
"epoch": 1.0,
"learning_rate": 9.534546612810502e-10,
"loss": 1.3458,
"step": 935
},
{
"epoch": 1.0,
"learning_rate": 5.363219756837624e-10,
"loss": 1.3594,
"step": 936
},
{
"epoch": 1.0,
"learning_rate": 2.3836650624997627e-10,
"loss": 1.3747,
"step": 937
},
{
"epoch": 1.0,
"learning_rate": 5.959180412129506e-11,
"loss": 1.3308,
"step": 938
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 1.3454,
"step": 939
},
{
"epoch": 1.0,
"step": 939,
"total_flos": 5.1566182660082416e+22,
"train_loss": 1.7596440274621479,
"train_runtime": 22964.7656,
"train_samples_per_second": 41.87,
"train_steps_per_second": 0.041
}
],
"logging_steps": 1.0,
"max_steps": 939,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"save_steps": 47,
"total_flos": 5.1566182660082416e+22,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}