Wiki_200 / checkpoint-600 /trainer_state.json
CreatorPhan's picture
Upload folder using huggingface_hub (#9)
f60fda1
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 15.118110236220472,
"eval_steps": 500,
"global_step": 600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03,
"learning_rate": 0.000499599358974359,
"loss": 3.1389,
"step": 1
},
{
"epoch": 0.05,
"learning_rate": 0.000499198717948718,
"loss": 2.8569,
"step": 2
},
{
"epoch": 0.08,
"learning_rate": 0.0004987980769230769,
"loss": 2.75,
"step": 3
},
{
"epoch": 0.1,
"learning_rate": 0.0004983974358974359,
"loss": 2.7375,
"step": 4
},
{
"epoch": 0.13,
"learning_rate": 0.0004979967948717949,
"loss": 2.7342,
"step": 5
},
{
"epoch": 0.15,
"learning_rate": 0.0004975961538461539,
"loss": 2.753,
"step": 6
},
{
"epoch": 0.18,
"learning_rate": 0.0004971955128205128,
"loss": 2.7124,
"step": 7
},
{
"epoch": 0.2,
"learning_rate": 0.0004967948717948718,
"loss": 2.7038,
"step": 8
},
{
"epoch": 0.23,
"learning_rate": 0.0004963942307692308,
"loss": 2.6142,
"step": 9
},
{
"epoch": 0.25,
"learning_rate": 0.0004959935897435898,
"loss": 2.6427,
"step": 10
},
{
"epoch": 0.28,
"learning_rate": 0.0004955929487179487,
"loss": 2.6265,
"step": 11
},
{
"epoch": 0.3,
"learning_rate": 0.0004951923076923077,
"loss": 2.6352,
"step": 12
},
{
"epoch": 0.33,
"learning_rate": 0.0004947916666666667,
"loss": 2.616,
"step": 13
},
{
"epoch": 0.35,
"learning_rate": 0.0004943910256410257,
"loss": 2.6937,
"step": 14
},
{
"epoch": 0.38,
"learning_rate": 0.0004939903846153846,
"loss": 2.6719,
"step": 15
},
{
"epoch": 0.4,
"learning_rate": 0.0004935897435897436,
"loss": 2.6043,
"step": 16
},
{
"epoch": 0.43,
"learning_rate": 0.0004931891025641026,
"loss": 2.565,
"step": 17
},
{
"epoch": 0.45,
"learning_rate": 0.0004927884615384616,
"loss": 2.5776,
"step": 18
},
{
"epoch": 0.48,
"learning_rate": 0.0004923878205128205,
"loss": 2.6326,
"step": 19
},
{
"epoch": 0.5,
"learning_rate": 0.0004919871794871795,
"loss": 2.5868,
"step": 20
},
{
"epoch": 0.53,
"learning_rate": 0.0004915865384615384,
"loss": 2.5499,
"step": 21
},
{
"epoch": 0.55,
"learning_rate": 0.0004911858974358974,
"loss": 2.5823,
"step": 22
},
{
"epoch": 0.58,
"learning_rate": 0.0004907852564102564,
"loss": 2.5858,
"step": 23
},
{
"epoch": 0.6,
"learning_rate": 0.0004903846153846154,
"loss": 2.5688,
"step": 24
},
{
"epoch": 0.63,
"learning_rate": 0.0004899839743589743,
"loss": 2.57,
"step": 25
},
{
"epoch": 0.66,
"learning_rate": 0.0004895833333333333,
"loss": 2.5569,
"step": 26
},
{
"epoch": 0.68,
"learning_rate": 0.0004891826923076923,
"loss": 2.5067,
"step": 27
},
{
"epoch": 0.71,
"learning_rate": 0.0004887820512820513,
"loss": 2.4936,
"step": 28
},
{
"epoch": 0.73,
"learning_rate": 0.0004883814102564103,
"loss": 2.5958,
"step": 29
},
{
"epoch": 0.76,
"learning_rate": 0.00048798076923076925,
"loss": 2.5213,
"step": 30
},
{
"epoch": 0.78,
"learning_rate": 0.0004875801282051282,
"loss": 2.6369,
"step": 31
},
{
"epoch": 0.81,
"learning_rate": 0.0004871794871794872,
"loss": 2.578,
"step": 32
},
{
"epoch": 0.83,
"learning_rate": 0.00048677884615384615,
"loss": 2.6214,
"step": 33
},
{
"epoch": 0.86,
"learning_rate": 0.00048637820512820515,
"loss": 2.6193,
"step": 34
},
{
"epoch": 0.88,
"learning_rate": 0.0004859775641025641,
"loss": 2.5948,
"step": 35
},
{
"epoch": 0.91,
"learning_rate": 0.0004855769230769231,
"loss": 2.5615,
"step": 36
},
{
"epoch": 0.93,
"learning_rate": 0.00048517628205128205,
"loss": 2.5246,
"step": 37
},
{
"epoch": 0.96,
"learning_rate": 0.00048477564102564105,
"loss": 2.4585,
"step": 38
},
{
"epoch": 0.98,
"learning_rate": 0.000484375,
"loss": 2.5621,
"step": 39
},
{
"epoch": 1.01,
"learning_rate": 0.000483974358974359,
"loss": 2.571,
"step": 40
},
{
"epoch": 1.03,
"learning_rate": 0.00048357371794871795,
"loss": 2.5382,
"step": 41
},
{
"epoch": 1.06,
"learning_rate": 0.00048317307692307695,
"loss": 2.5028,
"step": 42
},
{
"epoch": 1.08,
"learning_rate": 0.0004827724358974359,
"loss": 2.4812,
"step": 43
},
{
"epoch": 1.11,
"learning_rate": 0.0004823717948717949,
"loss": 2.5161,
"step": 44
},
{
"epoch": 1.13,
"learning_rate": 0.00048197115384615384,
"loss": 2.4557,
"step": 45
},
{
"epoch": 1.16,
"learning_rate": 0.00048157051282051285,
"loss": 2.4617,
"step": 46
},
{
"epoch": 1.18,
"learning_rate": 0.0004811698717948718,
"loss": 2.5267,
"step": 47
},
{
"epoch": 1.21,
"learning_rate": 0.0004807692307692308,
"loss": 2.4555,
"step": 48
},
{
"epoch": 1.23,
"learning_rate": 0.00048036858974358974,
"loss": 2.37,
"step": 49
},
{
"epoch": 1.26,
"learning_rate": 0.00047996794871794875,
"loss": 2.4829,
"step": 50
},
{
"epoch": 1.29,
"learning_rate": 0.0004795673076923077,
"loss": 2.5022,
"step": 51
},
{
"epoch": 1.31,
"learning_rate": 0.0004791666666666667,
"loss": 2.4958,
"step": 52
},
{
"epoch": 1.34,
"learning_rate": 0.0004787660256410257,
"loss": 2.4358,
"step": 53
},
{
"epoch": 1.36,
"learning_rate": 0.00047836538461538464,
"loss": 2.4742,
"step": 54
},
{
"epoch": 1.39,
"learning_rate": 0.00047796474358974365,
"loss": 2.4158,
"step": 55
},
{
"epoch": 1.41,
"learning_rate": 0.0004775641025641026,
"loss": 2.5216,
"step": 56
},
{
"epoch": 1.44,
"learning_rate": 0.0004771634615384616,
"loss": 2.5239,
"step": 57
},
{
"epoch": 1.46,
"learning_rate": 0.00047676282051282054,
"loss": 2.3946,
"step": 58
},
{
"epoch": 1.49,
"learning_rate": 0.0004763621794871795,
"loss": 2.4457,
"step": 59
},
{
"epoch": 1.51,
"learning_rate": 0.00047596153846153844,
"loss": 2.4379,
"step": 60
},
{
"epoch": 1.54,
"learning_rate": 0.00047556089743589744,
"loss": 2.4812,
"step": 61
},
{
"epoch": 1.56,
"learning_rate": 0.0004751602564102564,
"loss": 2.4153,
"step": 62
},
{
"epoch": 1.59,
"learning_rate": 0.0004747596153846154,
"loss": 2.4115,
"step": 63
},
{
"epoch": 1.61,
"learning_rate": 0.00047435897435897434,
"loss": 2.3637,
"step": 64
},
{
"epoch": 1.64,
"learning_rate": 0.00047395833333333334,
"loss": 2.3741,
"step": 65
},
{
"epoch": 1.66,
"learning_rate": 0.0004735576923076923,
"loss": 2.4461,
"step": 66
},
{
"epoch": 1.69,
"learning_rate": 0.0004731570512820513,
"loss": 2.4694,
"step": 67
},
{
"epoch": 1.71,
"learning_rate": 0.00047275641025641024,
"loss": 2.5177,
"step": 68
},
{
"epoch": 1.74,
"learning_rate": 0.00047235576923076924,
"loss": 2.4964,
"step": 69
},
{
"epoch": 1.76,
"learning_rate": 0.0004719551282051282,
"loss": 2.5114,
"step": 70
},
{
"epoch": 1.79,
"learning_rate": 0.0004715544871794872,
"loss": 2.4447,
"step": 71
},
{
"epoch": 1.81,
"learning_rate": 0.00047115384615384613,
"loss": 2.4112,
"step": 72
},
{
"epoch": 1.84,
"learning_rate": 0.00047075320512820514,
"loss": 2.4585,
"step": 73
},
{
"epoch": 1.86,
"learning_rate": 0.0004703525641025641,
"loss": 2.4696,
"step": 74
},
{
"epoch": 1.89,
"learning_rate": 0.0004699519230769231,
"loss": 2.3813,
"step": 75
},
{
"epoch": 1.91,
"learning_rate": 0.00046955128205128203,
"loss": 2.4962,
"step": 76
},
{
"epoch": 1.94,
"learning_rate": 0.00046915064102564104,
"loss": 2.4392,
"step": 77
},
{
"epoch": 1.97,
"learning_rate": 0.00046875,
"loss": 2.3436,
"step": 78
},
{
"epoch": 1.99,
"learning_rate": 0.000468349358974359,
"loss": 2.4758,
"step": 79
},
{
"epoch": 2.02,
"learning_rate": 0.000467948717948718,
"loss": 2.4026,
"step": 80
},
{
"epoch": 2.04,
"learning_rate": 0.00046754807692307693,
"loss": 2.3728,
"step": 81
},
{
"epoch": 2.07,
"learning_rate": 0.00046714743589743594,
"loss": 2.395,
"step": 82
},
{
"epoch": 2.09,
"learning_rate": 0.0004667467948717949,
"loss": 2.2767,
"step": 83
},
{
"epoch": 2.12,
"learning_rate": 0.0004663461538461539,
"loss": 2.3483,
"step": 84
},
{
"epoch": 2.14,
"learning_rate": 0.00046594551282051283,
"loss": 2.2911,
"step": 85
},
{
"epoch": 2.17,
"learning_rate": 0.00046554487179487183,
"loss": 2.3502,
"step": 86
},
{
"epoch": 2.19,
"learning_rate": 0.0004651442307692308,
"loss": 2.3532,
"step": 87
},
{
"epoch": 2.22,
"learning_rate": 0.0004647435897435898,
"loss": 2.266,
"step": 88
},
{
"epoch": 2.24,
"learning_rate": 0.00046434294871794873,
"loss": 2.3046,
"step": 89
},
{
"epoch": 2.27,
"learning_rate": 0.00046394230769230773,
"loss": 2.2458,
"step": 90
},
{
"epoch": 2.29,
"learning_rate": 0.0004635416666666667,
"loss": 2.3324,
"step": 91
},
{
"epoch": 2.32,
"learning_rate": 0.0004631410256410257,
"loss": 2.3016,
"step": 92
},
{
"epoch": 2.34,
"learning_rate": 0.00046274038461538463,
"loss": 2.379,
"step": 93
},
{
"epoch": 2.37,
"learning_rate": 0.00046233974358974363,
"loss": 2.3075,
"step": 94
},
{
"epoch": 2.39,
"learning_rate": 0.0004619391025641026,
"loss": 2.3942,
"step": 95
},
{
"epoch": 2.42,
"learning_rate": 0.0004615384615384616,
"loss": 2.2891,
"step": 96
},
{
"epoch": 2.44,
"learning_rate": 0.00046113782051282053,
"loss": 2.4199,
"step": 97
},
{
"epoch": 2.47,
"learning_rate": 0.0004607371794871795,
"loss": 2.3662,
"step": 98
},
{
"epoch": 2.49,
"learning_rate": 0.0004603365384615384,
"loss": 2.3346,
"step": 99
},
{
"epoch": 2.52,
"learning_rate": 0.0004599358974358974,
"loss": 2.2607,
"step": 100
},
{
"epoch": 2.54,
"learning_rate": 0.0004595352564102564,
"loss": 2.3446,
"step": 101
},
{
"epoch": 2.57,
"learning_rate": 0.0004591346153846154,
"loss": 2.3649,
"step": 102
},
{
"epoch": 2.6,
"learning_rate": 0.0004587339743589743,
"loss": 2.2394,
"step": 103
},
{
"epoch": 2.62,
"learning_rate": 0.0004583333333333333,
"loss": 2.3278,
"step": 104
},
{
"epoch": 2.65,
"learning_rate": 0.0004579326923076923,
"loss": 2.2725,
"step": 105
},
{
"epoch": 2.67,
"learning_rate": 0.0004575320512820513,
"loss": 2.3328,
"step": 106
},
{
"epoch": 2.7,
"learning_rate": 0.0004571314102564103,
"loss": 2.296,
"step": 107
},
{
"epoch": 2.72,
"learning_rate": 0.0004567307692307692,
"loss": 2.2562,
"step": 108
},
{
"epoch": 2.75,
"learning_rate": 0.0004563301282051282,
"loss": 2.3062,
"step": 109
},
{
"epoch": 2.77,
"learning_rate": 0.0004559294871794872,
"loss": 2.3125,
"step": 110
},
{
"epoch": 2.8,
"learning_rate": 0.0004555288461538462,
"loss": 2.3257,
"step": 111
},
{
"epoch": 2.82,
"learning_rate": 0.0004551282051282051,
"loss": 2.3431,
"step": 112
},
{
"epoch": 2.85,
"learning_rate": 0.0004547275641025641,
"loss": 2.3507,
"step": 113
},
{
"epoch": 2.87,
"learning_rate": 0.00045432692307692307,
"loss": 2.3621,
"step": 114
},
{
"epoch": 2.9,
"learning_rate": 0.0004539262820512821,
"loss": 2.2937,
"step": 115
},
{
"epoch": 2.92,
"learning_rate": 0.000453525641025641,
"loss": 2.3356,
"step": 116
},
{
"epoch": 2.95,
"learning_rate": 0.000453125,
"loss": 2.2228,
"step": 117
},
{
"epoch": 2.97,
"learning_rate": 0.00045272435897435897,
"loss": 2.3189,
"step": 118
},
{
"epoch": 3.0,
"learning_rate": 0.00045232371794871797,
"loss": 2.3605,
"step": 119
},
{
"epoch": 3.02,
"learning_rate": 0.0004519230769230769,
"loss": 2.1857,
"step": 120
},
{
"epoch": 3.05,
"learning_rate": 0.0004515224358974359,
"loss": 2.1538,
"step": 121
},
{
"epoch": 3.07,
"learning_rate": 0.00045112179487179487,
"loss": 2.2092,
"step": 122
},
{
"epoch": 3.1,
"learning_rate": 0.00045072115384615387,
"loss": 2.2089,
"step": 123
},
{
"epoch": 3.12,
"learning_rate": 0.0004503205128205128,
"loss": 2.1746,
"step": 124
},
{
"epoch": 3.15,
"learning_rate": 0.0004499198717948718,
"loss": 2.1455,
"step": 125
},
{
"epoch": 3.17,
"learning_rate": 0.00044951923076923077,
"loss": 2.119,
"step": 126
},
{
"epoch": 3.2,
"learning_rate": 0.00044911858974358977,
"loss": 2.2341,
"step": 127
},
{
"epoch": 3.23,
"learning_rate": 0.0004487179487179487,
"loss": 2.2275,
"step": 128
},
{
"epoch": 3.25,
"learning_rate": 0.0004483173076923077,
"loss": 2.176,
"step": 129
},
{
"epoch": 3.28,
"learning_rate": 0.0004479166666666667,
"loss": 2.1187,
"step": 130
},
{
"epoch": 3.3,
"learning_rate": 0.00044751602564102567,
"loss": 2.1175,
"step": 131
},
{
"epoch": 3.33,
"learning_rate": 0.00044711538461538467,
"loss": 2.1818,
"step": 132
},
{
"epoch": 3.35,
"learning_rate": 0.0004467147435897436,
"loss": 2.1193,
"step": 133
},
{
"epoch": 3.38,
"learning_rate": 0.0004463141025641026,
"loss": 2.2079,
"step": 134
},
{
"epoch": 3.4,
"learning_rate": 0.00044591346153846157,
"loss": 2.1361,
"step": 135
},
{
"epoch": 3.43,
"learning_rate": 0.00044551282051282057,
"loss": 2.2246,
"step": 136
},
{
"epoch": 3.45,
"learning_rate": 0.00044511217948717946,
"loss": 2.1139,
"step": 137
},
{
"epoch": 3.48,
"learning_rate": 0.00044471153846153846,
"loss": 2.1058,
"step": 138
},
{
"epoch": 3.5,
"learning_rate": 0.0004443108974358974,
"loss": 2.1442,
"step": 139
},
{
"epoch": 3.53,
"learning_rate": 0.0004439102564102564,
"loss": 2.1039,
"step": 140
},
{
"epoch": 3.55,
"learning_rate": 0.00044350961538461536,
"loss": 2.1884,
"step": 141
},
{
"epoch": 3.58,
"learning_rate": 0.00044310897435897436,
"loss": 2.21,
"step": 142
},
{
"epoch": 3.6,
"learning_rate": 0.0004427083333333333,
"loss": 2.1139,
"step": 143
},
{
"epoch": 3.63,
"learning_rate": 0.0004423076923076923,
"loss": 2.1049,
"step": 144
},
{
"epoch": 3.65,
"learning_rate": 0.00044190705128205126,
"loss": 2.1282,
"step": 145
},
{
"epoch": 3.68,
"learning_rate": 0.00044150641025641026,
"loss": 2.1803,
"step": 146
},
{
"epoch": 3.7,
"learning_rate": 0.0004411057692307692,
"loss": 2.1406,
"step": 147
},
{
"epoch": 3.73,
"learning_rate": 0.0004407051282051282,
"loss": 2.1841,
"step": 148
},
{
"epoch": 3.75,
"learning_rate": 0.00044030448717948716,
"loss": 2.1961,
"step": 149
},
{
"epoch": 3.78,
"learning_rate": 0.00043990384615384616,
"loss": 2.1265,
"step": 150
},
{
"epoch": 3.8,
"learning_rate": 0.0004395032051282051,
"loss": 2.1708,
"step": 151
},
{
"epoch": 3.83,
"learning_rate": 0.0004391025641025641,
"loss": 2.1555,
"step": 152
},
{
"epoch": 3.86,
"learning_rate": 0.00043870192307692306,
"loss": 2.1463,
"step": 153
},
{
"epoch": 3.88,
"learning_rate": 0.00043830128205128206,
"loss": 2.1947,
"step": 154
},
{
"epoch": 3.91,
"learning_rate": 0.000437900641025641,
"loss": 2.1962,
"step": 155
},
{
"epoch": 3.93,
"learning_rate": 0.0004375,
"loss": 2.2109,
"step": 156
},
{
"epoch": 3.96,
"learning_rate": 0.000437099358974359,
"loss": 2.1556,
"step": 157
},
{
"epoch": 3.98,
"learning_rate": 0.00043669871794871796,
"loss": 2.1605,
"step": 158
},
{
"epoch": 4.01,
"learning_rate": 0.00043629807692307696,
"loss": 2.155,
"step": 159
},
{
"epoch": 4.03,
"learning_rate": 0.0004358974358974359,
"loss": 2.0347,
"step": 160
},
{
"epoch": 4.06,
"learning_rate": 0.0004354967948717949,
"loss": 1.9321,
"step": 161
},
{
"epoch": 4.08,
"learning_rate": 0.00043509615384615386,
"loss": 2.0034,
"step": 162
},
{
"epoch": 4.11,
"learning_rate": 0.00043469551282051286,
"loss": 2.0203,
"step": 163
},
{
"epoch": 4.13,
"learning_rate": 0.0004342948717948718,
"loss": 1.9189,
"step": 164
},
{
"epoch": 4.16,
"learning_rate": 0.0004338942307692308,
"loss": 1.9868,
"step": 165
},
{
"epoch": 4.18,
"learning_rate": 0.00043349358974358976,
"loss": 1.9343,
"step": 166
},
{
"epoch": 4.21,
"learning_rate": 0.00043309294871794876,
"loss": 1.8894,
"step": 167
},
{
"epoch": 4.23,
"learning_rate": 0.0004326923076923077,
"loss": 1.9735,
"step": 168
},
{
"epoch": 4.26,
"learning_rate": 0.0004322916666666667,
"loss": 2.0012,
"step": 169
},
{
"epoch": 4.28,
"learning_rate": 0.00043189102564102565,
"loss": 1.9087,
"step": 170
},
{
"epoch": 4.31,
"learning_rate": 0.00043149038461538466,
"loss": 1.9213,
"step": 171
},
{
"epoch": 4.33,
"learning_rate": 0.0004310897435897436,
"loss": 2.0195,
"step": 172
},
{
"epoch": 4.36,
"learning_rate": 0.0004306891025641026,
"loss": 1.9806,
"step": 173
},
{
"epoch": 4.38,
"learning_rate": 0.00043028846153846155,
"loss": 1.9731,
"step": 174
},
{
"epoch": 4.41,
"learning_rate": 0.00042988782051282056,
"loss": 1.9282,
"step": 175
},
{
"epoch": 4.43,
"learning_rate": 0.00042948717948717945,
"loss": 1.9433,
"step": 176
},
{
"epoch": 4.46,
"learning_rate": 0.00042908653846153845,
"loss": 1.9633,
"step": 177
},
{
"epoch": 4.49,
"learning_rate": 0.0004286858974358974,
"loss": 1.9918,
"step": 178
},
{
"epoch": 4.51,
"learning_rate": 0.0004282852564102564,
"loss": 1.9265,
"step": 179
},
{
"epoch": 4.54,
"learning_rate": 0.00042788461538461535,
"loss": 1.9198,
"step": 180
},
{
"epoch": 4.56,
"learning_rate": 0.00042748397435897435,
"loss": 2.0159,
"step": 181
},
{
"epoch": 4.59,
"learning_rate": 0.0004270833333333333,
"loss": 1.9474,
"step": 182
},
{
"epoch": 4.61,
"learning_rate": 0.0004266826923076923,
"loss": 2.0152,
"step": 183
},
{
"epoch": 4.64,
"learning_rate": 0.0004262820512820513,
"loss": 1.9006,
"step": 184
},
{
"epoch": 4.66,
"learning_rate": 0.00042588141025641025,
"loss": 1.9862,
"step": 185
},
{
"epoch": 4.69,
"learning_rate": 0.00042548076923076925,
"loss": 1.9945,
"step": 186
},
{
"epoch": 4.71,
"learning_rate": 0.0004250801282051282,
"loss": 1.985,
"step": 187
},
{
"epoch": 4.74,
"learning_rate": 0.0004246794871794872,
"loss": 1.9899,
"step": 188
},
{
"epoch": 4.76,
"learning_rate": 0.00042427884615384615,
"loss": 2.0149,
"step": 189
},
{
"epoch": 4.79,
"learning_rate": 0.00042387820512820515,
"loss": 1.9768,
"step": 190
},
{
"epoch": 4.81,
"learning_rate": 0.0004234775641025641,
"loss": 2.0204,
"step": 191
},
{
"epoch": 4.84,
"learning_rate": 0.0004230769230769231,
"loss": 1.9343,
"step": 192
},
{
"epoch": 4.86,
"learning_rate": 0.00042267628205128205,
"loss": 2.0574,
"step": 193
},
{
"epoch": 4.89,
"learning_rate": 0.00042227564102564105,
"loss": 2.0245,
"step": 194
},
{
"epoch": 4.91,
"learning_rate": 0.000421875,
"loss": 2.0356,
"step": 195
},
{
"epoch": 4.94,
"learning_rate": 0.000421474358974359,
"loss": 1.9984,
"step": 196
},
{
"epoch": 4.96,
"learning_rate": 0.00042107371794871794,
"loss": 1.9826,
"step": 197
},
{
"epoch": 4.99,
"learning_rate": 0.00042067307692307695,
"loss": 1.9846,
"step": 198
},
{
"epoch": 5.01,
"learning_rate": 0.0004202724358974359,
"loss": 1.8931,
"step": 199
},
{
"epoch": 5.04,
"learning_rate": 0.0004198717948717949,
"loss": 1.7642,
"step": 200
},
{
"epoch": 5.06,
"learning_rate": 0.00041947115384615384,
"loss": 1.7235,
"step": 201
},
{
"epoch": 5.09,
"learning_rate": 0.00041907051282051285,
"loss": 1.7058,
"step": 202
},
{
"epoch": 5.11,
"learning_rate": 0.0004186698717948718,
"loss": 1.8022,
"step": 203
},
{
"epoch": 5.14,
"learning_rate": 0.0004182692307692308,
"loss": 1.7819,
"step": 204
},
{
"epoch": 5.17,
"learning_rate": 0.00041786858974358974,
"loss": 1.7047,
"step": 205
},
{
"epoch": 5.19,
"learning_rate": 0.00041746794871794874,
"loss": 1.773,
"step": 206
},
{
"epoch": 5.22,
"learning_rate": 0.0004170673076923077,
"loss": 1.7324,
"step": 207
},
{
"epoch": 5.24,
"learning_rate": 0.0004166666666666667,
"loss": 1.7862,
"step": 208
},
{
"epoch": 5.27,
"learning_rate": 0.0004162660256410257,
"loss": 1.764,
"step": 209
},
{
"epoch": 5.29,
"learning_rate": 0.00041586538461538464,
"loss": 1.7156,
"step": 210
},
{
"epoch": 5.32,
"learning_rate": 0.00041546474358974364,
"loss": 1.7948,
"step": 211
},
{
"epoch": 5.34,
"learning_rate": 0.0004150641025641026,
"loss": 1.7608,
"step": 212
},
{
"epoch": 5.37,
"learning_rate": 0.0004146634615384616,
"loss": 1.7204,
"step": 213
},
{
"epoch": 5.39,
"learning_rate": 0.00041426282051282054,
"loss": 1.7691,
"step": 214
},
{
"epoch": 5.42,
"learning_rate": 0.0004138621794871795,
"loss": 1.7969,
"step": 215
},
{
"epoch": 5.44,
"learning_rate": 0.00041346153846153844,
"loss": 1.7194,
"step": 216
},
{
"epoch": 5.47,
"learning_rate": 0.00041306089743589744,
"loss": 1.7022,
"step": 217
},
{
"epoch": 5.49,
"learning_rate": 0.0004126602564102564,
"loss": 1.8287,
"step": 218
},
{
"epoch": 5.52,
"learning_rate": 0.0004122596153846154,
"loss": 1.7074,
"step": 219
},
{
"epoch": 5.54,
"learning_rate": 0.00041185897435897434,
"loss": 1.8354,
"step": 220
},
{
"epoch": 5.57,
"learning_rate": 0.00041145833333333334,
"loss": 1.791,
"step": 221
},
{
"epoch": 5.59,
"learning_rate": 0.0004110576923076923,
"loss": 1.7633,
"step": 222
},
{
"epoch": 5.62,
"learning_rate": 0.0004106570512820513,
"loss": 1.811,
"step": 223
},
{
"epoch": 5.64,
"learning_rate": 0.00041025641025641023,
"loss": 1.7498,
"step": 224
},
{
"epoch": 5.67,
"learning_rate": 0.00040985576923076924,
"loss": 1.7662,
"step": 225
},
{
"epoch": 5.69,
"learning_rate": 0.0004094551282051282,
"loss": 1.7686,
"step": 226
},
{
"epoch": 5.72,
"learning_rate": 0.0004090544871794872,
"loss": 1.8357,
"step": 227
},
{
"epoch": 5.74,
"learning_rate": 0.00040865384615384613,
"loss": 1.7981,
"step": 228
},
{
"epoch": 5.77,
"learning_rate": 0.00040825320512820513,
"loss": 1.7502,
"step": 229
},
{
"epoch": 5.8,
"learning_rate": 0.0004078525641025641,
"loss": 1.7666,
"step": 230
},
{
"epoch": 5.82,
"learning_rate": 0.0004074519230769231,
"loss": 1.798,
"step": 231
},
{
"epoch": 5.85,
"learning_rate": 0.00040705128205128203,
"loss": 1.8072,
"step": 232
},
{
"epoch": 5.87,
"learning_rate": 0.00040665064102564103,
"loss": 1.7611,
"step": 233
},
{
"epoch": 5.9,
"learning_rate": 0.00040625000000000004,
"loss": 1.8126,
"step": 234
},
{
"epoch": 5.92,
"learning_rate": 0.000405849358974359,
"loss": 1.8361,
"step": 235
},
{
"epoch": 5.95,
"learning_rate": 0.000405448717948718,
"loss": 1.7938,
"step": 236
},
{
"epoch": 5.97,
"learning_rate": 0.00040504807692307693,
"loss": 1.7524,
"step": 237
},
{
"epoch": 6.0,
"learning_rate": 0.00040464743589743593,
"loss": 1.7601,
"step": 238
},
{
"epoch": 6.02,
"learning_rate": 0.0004042467948717949,
"loss": 1.5373,
"step": 239
},
{
"epoch": 6.05,
"learning_rate": 0.0004038461538461539,
"loss": 1.5108,
"step": 240
},
{
"epoch": 6.07,
"learning_rate": 0.00040344551282051283,
"loss": 1.568,
"step": 241
},
{
"epoch": 6.1,
"learning_rate": 0.00040304487179487183,
"loss": 1.5175,
"step": 242
},
{
"epoch": 6.12,
"learning_rate": 0.0004026442307692308,
"loss": 1.5748,
"step": 243
},
{
"epoch": 6.15,
"learning_rate": 0.0004022435897435898,
"loss": 1.4772,
"step": 244
},
{
"epoch": 6.17,
"learning_rate": 0.00040184294871794873,
"loss": 1.5035,
"step": 245
},
{
"epoch": 6.2,
"learning_rate": 0.00040144230769230773,
"loss": 1.5318,
"step": 246
},
{
"epoch": 6.22,
"learning_rate": 0.0004010416666666667,
"loss": 1.5139,
"step": 247
},
{
"epoch": 6.25,
"learning_rate": 0.0004006410256410257,
"loss": 1.5599,
"step": 248
},
{
"epoch": 6.27,
"learning_rate": 0.00040024038461538463,
"loss": 1.5475,
"step": 249
},
{
"epoch": 6.3,
"learning_rate": 0.00039983974358974363,
"loss": 1.4819,
"step": 250
},
{
"epoch": 6.32,
"learning_rate": 0.0003994391025641026,
"loss": 1.5419,
"step": 251
},
{
"epoch": 6.35,
"learning_rate": 0.0003990384615384616,
"loss": 1.6027,
"step": 252
},
{
"epoch": 6.37,
"learning_rate": 0.00039863782051282053,
"loss": 1.5683,
"step": 253
},
{
"epoch": 6.4,
"learning_rate": 0.0003982371794871795,
"loss": 1.5963,
"step": 254
},
{
"epoch": 6.43,
"learning_rate": 0.0003978365384615384,
"loss": 1.5874,
"step": 255
},
{
"epoch": 6.45,
"learning_rate": 0.0003974358974358974,
"loss": 1.5161,
"step": 256
},
{
"epoch": 6.48,
"learning_rate": 0.00039703525641025637,
"loss": 1.57,
"step": 257
},
{
"epoch": 6.5,
"learning_rate": 0.0003966346153846154,
"loss": 1.534,
"step": 258
},
{
"epoch": 6.53,
"learning_rate": 0.0003962339743589743,
"loss": 1.5513,
"step": 259
},
{
"epoch": 6.55,
"learning_rate": 0.0003958333333333333,
"loss": 1.5454,
"step": 260
},
{
"epoch": 6.58,
"learning_rate": 0.0003954326923076923,
"loss": 1.5695,
"step": 261
},
{
"epoch": 6.6,
"learning_rate": 0.0003950320512820513,
"loss": 1.5777,
"step": 262
},
{
"epoch": 6.63,
"learning_rate": 0.0003946314102564103,
"loss": 1.5629,
"step": 263
},
{
"epoch": 6.65,
"learning_rate": 0.0003942307692307692,
"loss": 1.5031,
"step": 264
},
{
"epoch": 6.68,
"learning_rate": 0.0003938301282051282,
"loss": 1.5964,
"step": 265
},
{
"epoch": 6.7,
"learning_rate": 0.00039342948717948717,
"loss": 1.5472,
"step": 266
},
{
"epoch": 6.73,
"learning_rate": 0.0003930288461538462,
"loss": 1.5654,
"step": 267
},
{
"epoch": 6.75,
"learning_rate": 0.0003926282051282051,
"loss": 1.5932,
"step": 268
},
{
"epoch": 6.78,
"learning_rate": 0.0003922275641025641,
"loss": 1.6037,
"step": 269
},
{
"epoch": 6.8,
"learning_rate": 0.00039182692307692307,
"loss": 1.6394,
"step": 270
},
{
"epoch": 6.83,
"learning_rate": 0.00039142628205128207,
"loss": 1.5745,
"step": 271
},
{
"epoch": 6.85,
"learning_rate": 0.000391025641025641,
"loss": 1.6512,
"step": 272
},
{
"epoch": 6.88,
"learning_rate": 0.000390625,
"loss": 1.6107,
"step": 273
},
{
"epoch": 6.9,
"learning_rate": 0.00039022435897435897,
"loss": 1.5798,
"step": 274
},
{
"epoch": 6.93,
"learning_rate": 0.00038982371794871797,
"loss": 1.6087,
"step": 275
},
{
"epoch": 6.95,
"learning_rate": 0.0003894230769230769,
"loss": 1.5362,
"step": 276
},
{
"epoch": 6.98,
"learning_rate": 0.0003890224358974359,
"loss": 1.5899,
"step": 277
},
{
"epoch": 7.0,
"learning_rate": 0.00038862179487179487,
"loss": 1.59,
"step": 278
},
{
"epoch": 7.03,
"learning_rate": 0.00038822115384615387,
"loss": 1.3327,
"step": 279
},
{
"epoch": 7.06,
"learning_rate": 0.0003878205128205128,
"loss": 1.3214,
"step": 280
},
{
"epoch": 7.08,
"learning_rate": 0.0003874198717948718,
"loss": 1.2891,
"step": 281
},
{
"epoch": 7.11,
"learning_rate": 0.00038701923076923077,
"loss": 1.3321,
"step": 282
},
{
"epoch": 7.13,
"learning_rate": 0.00038661858974358977,
"loss": 1.284,
"step": 283
},
{
"epoch": 7.16,
"learning_rate": 0.0003862179487179487,
"loss": 1.3346,
"step": 284
},
{
"epoch": 7.18,
"learning_rate": 0.0003858173076923077,
"loss": 1.2874,
"step": 285
},
{
"epoch": 7.21,
"learning_rate": 0.0003854166666666667,
"loss": 1.3104,
"step": 286
},
{
"epoch": 7.23,
"learning_rate": 0.00038501602564102567,
"loss": 1.3138,
"step": 287
},
{
"epoch": 7.26,
"learning_rate": 0.00038461538461538467,
"loss": 1.2871,
"step": 288
},
{
"epoch": 7.28,
"learning_rate": 0.0003842147435897436,
"loss": 1.2885,
"step": 289
},
{
"epoch": 7.31,
"learning_rate": 0.0003838141025641026,
"loss": 1.338,
"step": 290
},
{
"epoch": 7.33,
"learning_rate": 0.00038341346153846157,
"loss": 1.3189,
"step": 291
},
{
"epoch": 7.36,
"learning_rate": 0.00038301282051282057,
"loss": 1.3013,
"step": 292
},
{
"epoch": 7.38,
"learning_rate": 0.00038261217948717946,
"loss": 1.3505,
"step": 293
},
{
"epoch": 7.41,
"learning_rate": 0.00038221153846153846,
"loss": 1.3469,
"step": 294
},
{
"epoch": 7.43,
"learning_rate": 0.0003818108974358974,
"loss": 1.3156,
"step": 295
},
{
"epoch": 7.46,
"learning_rate": 0.0003814102564102564,
"loss": 1.3796,
"step": 296
},
{
"epoch": 7.48,
"learning_rate": 0.00038100961538461536,
"loss": 1.3649,
"step": 297
},
{
"epoch": 7.51,
"learning_rate": 0.00038060897435897436,
"loss": 1.3483,
"step": 298
},
{
"epoch": 7.53,
"learning_rate": 0.0003802083333333333,
"loss": 1.3481,
"step": 299
},
{
"epoch": 7.56,
"learning_rate": 0.0003798076923076923,
"loss": 1.334,
"step": 300
},
{
"epoch": 7.58,
"learning_rate": 0.00037940705128205126,
"loss": 1.3495,
"step": 301
},
{
"epoch": 7.61,
"learning_rate": 0.00037900641025641026,
"loss": 1.4102,
"step": 302
},
{
"epoch": 7.63,
"learning_rate": 0.0003786057692307692,
"loss": 1.3794,
"step": 303
},
{
"epoch": 7.66,
"learning_rate": 0.0003782051282051282,
"loss": 1.3802,
"step": 304
},
{
"epoch": 7.69,
"learning_rate": 0.00037780448717948716,
"loss": 1.3835,
"step": 305
},
{
"epoch": 7.71,
"learning_rate": 0.00037740384615384616,
"loss": 1.4197,
"step": 306
},
{
"epoch": 7.74,
"learning_rate": 0.0003770032051282051,
"loss": 1.3947,
"step": 307
},
{
"epoch": 7.76,
"learning_rate": 0.0003766025641025641,
"loss": 1.3891,
"step": 308
},
{
"epoch": 7.79,
"learning_rate": 0.00037620192307692306,
"loss": 1.3904,
"step": 309
},
{
"epoch": 7.81,
"learning_rate": 0.00037580128205128206,
"loss": 1.3937,
"step": 310
},
{
"epoch": 7.84,
"learning_rate": 0.000375400641025641,
"loss": 1.4258,
"step": 311
},
{
"epoch": 7.86,
"learning_rate": 0.000375,
"loss": 1.3816,
"step": 312
},
{
"epoch": 7.89,
"learning_rate": 0.000374599358974359,
"loss": 1.4251,
"step": 313
},
{
"epoch": 7.91,
"learning_rate": 0.00037419871794871796,
"loss": 1.3946,
"step": 314
},
{
"epoch": 7.94,
"learning_rate": 0.00037379807692307696,
"loss": 1.3968,
"step": 315
},
{
"epoch": 7.96,
"learning_rate": 0.0003733974358974359,
"loss": 1.4108,
"step": 316
},
{
"epoch": 7.99,
"learning_rate": 0.0003729967948717949,
"loss": 1.4673,
"step": 317
},
{
"epoch": 8.01,
"learning_rate": 0.00037259615384615386,
"loss": 1.2339,
"step": 318
},
{
"epoch": 8.04,
"learning_rate": 0.00037219551282051286,
"loss": 1.1775,
"step": 319
},
{
"epoch": 8.06,
"learning_rate": 0.0003717948717948718,
"loss": 1.1061,
"step": 320
},
{
"epoch": 8.09,
"learning_rate": 0.0003713942307692308,
"loss": 1.0912,
"step": 321
},
{
"epoch": 8.11,
"learning_rate": 0.00037099358974358975,
"loss": 1.1214,
"step": 322
},
{
"epoch": 8.14,
"learning_rate": 0.00037059294871794876,
"loss": 1.1537,
"step": 323
},
{
"epoch": 8.16,
"learning_rate": 0.0003701923076923077,
"loss": 1.116,
"step": 324
},
{
"epoch": 8.19,
"learning_rate": 0.0003697916666666667,
"loss": 1.1292,
"step": 325
},
{
"epoch": 8.21,
"learning_rate": 0.00036939102564102565,
"loss": 1.0948,
"step": 326
},
{
"epoch": 8.24,
"learning_rate": 0.00036899038461538466,
"loss": 1.0968,
"step": 327
},
{
"epoch": 8.26,
"learning_rate": 0.0003685897435897436,
"loss": 1.118,
"step": 328
},
{
"epoch": 8.29,
"learning_rate": 0.0003681891025641026,
"loss": 1.1488,
"step": 329
},
{
"epoch": 8.31,
"learning_rate": 0.00036778846153846155,
"loss": 1.137,
"step": 330
},
{
"epoch": 8.34,
"learning_rate": 0.00036738782051282055,
"loss": 1.0832,
"step": 331
},
{
"epoch": 8.37,
"learning_rate": 0.00036698717948717945,
"loss": 1.1609,
"step": 332
},
{
"epoch": 8.39,
"learning_rate": 0.00036658653846153845,
"loss": 1.1497,
"step": 333
},
{
"epoch": 8.42,
"learning_rate": 0.0003661858974358974,
"loss": 1.1289,
"step": 334
},
{
"epoch": 8.44,
"learning_rate": 0.0003657852564102564,
"loss": 1.1938,
"step": 335
},
{
"epoch": 8.47,
"learning_rate": 0.00036538461538461535,
"loss": 1.1441,
"step": 336
},
{
"epoch": 8.49,
"learning_rate": 0.00036498397435897435,
"loss": 1.1233,
"step": 337
},
{
"epoch": 8.52,
"learning_rate": 0.0003645833333333333,
"loss": 1.1273,
"step": 338
},
{
"epoch": 8.54,
"learning_rate": 0.0003641826923076923,
"loss": 1.1498,
"step": 339
},
{
"epoch": 8.57,
"learning_rate": 0.0003637820512820513,
"loss": 1.1848,
"step": 340
},
{
"epoch": 8.59,
"learning_rate": 0.00036338141025641025,
"loss": 1.1991,
"step": 341
},
{
"epoch": 8.62,
"learning_rate": 0.00036298076923076925,
"loss": 1.1705,
"step": 342
},
{
"epoch": 8.64,
"learning_rate": 0.0003625801282051282,
"loss": 1.1613,
"step": 343
},
{
"epoch": 8.67,
"learning_rate": 0.0003621794871794872,
"loss": 1.2599,
"step": 344
},
{
"epoch": 8.69,
"learning_rate": 0.00036177884615384615,
"loss": 1.1824,
"step": 345
},
{
"epoch": 8.72,
"learning_rate": 0.00036137820512820515,
"loss": 1.1763,
"step": 346
},
{
"epoch": 8.74,
"learning_rate": 0.0003609775641025641,
"loss": 1.1882,
"step": 347
},
{
"epoch": 8.77,
"learning_rate": 0.0003605769230769231,
"loss": 1.2043,
"step": 348
},
{
"epoch": 8.79,
"learning_rate": 0.00036017628205128204,
"loss": 1.2123,
"step": 349
},
{
"epoch": 8.82,
"learning_rate": 0.00035977564102564105,
"loss": 1.1831,
"step": 350
},
{
"epoch": 8.84,
"learning_rate": 0.000359375,
"loss": 1.2265,
"step": 351
},
{
"epoch": 8.87,
"learning_rate": 0.000358974358974359,
"loss": 1.1658,
"step": 352
},
{
"epoch": 8.89,
"learning_rate": 0.00035857371794871794,
"loss": 1.1787,
"step": 353
},
{
"epoch": 8.92,
"learning_rate": 0.00035817307692307695,
"loss": 1.1904,
"step": 354
},
{
"epoch": 8.94,
"learning_rate": 0.0003577724358974359,
"loss": 1.2753,
"step": 355
},
{
"epoch": 8.97,
"learning_rate": 0.0003573717948717949,
"loss": 1.2076,
"step": 356
},
{
"epoch": 9.0,
"learning_rate": 0.00035697115384615384,
"loss": 1.2433,
"step": 357
},
{
"epoch": 9.02,
"learning_rate": 0.00035657051282051284,
"loss": 0.9733,
"step": 358
},
{
"epoch": 9.05,
"learning_rate": 0.0003561698717948718,
"loss": 0.9765,
"step": 359
},
{
"epoch": 9.07,
"learning_rate": 0.0003557692307692308,
"loss": 0.9626,
"step": 360
},
{
"epoch": 9.1,
"learning_rate": 0.00035536858974358974,
"loss": 0.9382,
"step": 361
},
{
"epoch": 9.12,
"learning_rate": 0.00035496794871794874,
"loss": 0.8644,
"step": 362
},
{
"epoch": 9.15,
"learning_rate": 0.0003545673076923077,
"loss": 0.9299,
"step": 363
},
{
"epoch": 9.17,
"learning_rate": 0.0003541666666666667,
"loss": 0.9618,
"step": 364
},
{
"epoch": 9.2,
"learning_rate": 0.0003537660256410257,
"loss": 0.9417,
"step": 365
},
{
"epoch": 9.22,
"learning_rate": 0.00035336538461538464,
"loss": 0.9873,
"step": 366
},
{
"epoch": 9.25,
"learning_rate": 0.00035296474358974364,
"loss": 0.9135,
"step": 367
},
{
"epoch": 9.27,
"learning_rate": 0.0003525641025641026,
"loss": 0.9652,
"step": 368
},
{
"epoch": 9.3,
"learning_rate": 0.0003521634615384616,
"loss": 0.9347,
"step": 369
},
{
"epoch": 9.32,
"learning_rate": 0.00035176282051282054,
"loss": 0.914,
"step": 370
},
{
"epoch": 9.35,
"learning_rate": 0.0003513621794871795,
"loss": 0.9622,
"step": 371
},
{
"epoch": 9.37,
"learning_rate": 0.00035096153846153844,
"loss": 0.9652,
"step": 372
},
{
"epoch": 9.4,
"learning_rate": 0.00035056089743589744,
"loss": 0.8865,
"step": 373
},
{
"epoch": 9.42,
"learning_rate": 0.0003501602564102564,
"loss": 0.9997,
"step": 374
},
{
"epoch": 9.45,
"learning_rate": 0.0003497596153846154,
"loss": 0.9695,
"step": 375
},
{
"epoch": 9.47,
"learning_rate": 0.00034935897435897433,
"loss": 1.0172,
"step": 376
},
{
"epoch": 9.5,
"learning_rate": 0.00034895833333333334,
"loss": 0.9955,
"step": 377
},
{
"epoch": 9.52,
"learning_rate": 0.0003485576923076923,
"loss": 0.9902,
"step": 378
},
{
"epoch": 9.55,
"learning_rate": 0.0003481570512820513,
"loss": 1.0225,
"step": 379
},
{
"epoch": 9.57,
"learning_rate": 0.00034775641025641023,
"loss": 0.9773,
"step": 380
},
{
"epoch": 9.6,
"learning_rate": 0.00034735576923076923,
"loss": 0.9947,
"step": 381
},
{
"epoch": 9.63,
"learning_rate": 0.0003469551282051282,
"loss": 1.0234,
"step": 382
},
{
"epoch": 9.65,
"learning_rate": 0.0003465544871794872,
"loss": 0.9692,
"step": 383
},
{
"epoch": 9.68,
"learning_rate": 0.00034615384615384613,
"loss": 0.9782,
"step": 384
},
{
"epoch": 9.7,
"learning_rate": 0.00034575320512820513,
"loss": 1.0416,
"step": 385
},
{
"epoch": 9.73,
"learning_rate": 0.0003453525641025641,
"loss": 1.0008,
"step": 386
},
{
"epoch": 9.75,
"learning_rate": 0.0003449519230769231,
"loss": 1.0854,
"step": 387
},
{
"epoch": 9.78,
"learning_rate": 0.00034455128205128203,
"loss": 1.085,
"step": 388
},
{
"epoch": 9.8,
"learning_rate": 0.00034415064102564103,
"loss": 1.007,
"step": 389
},
{
"epoch": 9.83,
"learning_rate": 0.00034375,
"loss": 1.0516,
"step": 390
},
{
"epoch": 9.85,
"learning_rate": 0.000343349358974359,
"loss": 0.9729,
"step": 391
},
{
"epoch": 9.88,
"learning_rate": 0.000342948717948718,
"loss": 1.0174,
"step": 392
},
{
"epoch": 9.9,
"learning_rate": 0.00034254807692307693,
"loss": 1.0392,
"step": 393
},
{
"epoch": 9.93,
"learning_rate": 0.00034214743589743593,
"loss": 1.0534,
"step": 394
},
{
"epoch": 9.95,
"learning_rate": 0.0003417467948717949,
"loss": 1.0584,
"step": 395
},
{
"epoch": 9.98,
"learning_rate": 0.0003413461538461539,
"loss": 1.0727,
"step": 396
},
{
"epoch": 10.0,
"learning_rate": 0.00034094551282051283,
"loss": 1.0023,
"step": 397
},
{
"epoch": 10.03,
"learning_rate": 0.00034054487179487183,
"loss": 0.8029,
"step": 398
},
{
"epoch": 10.05,
"learning_rate": 0.0003401442307692308,
"loss": 0.7901,
"step": 399
},
{
"epoch": 10.08,
"learning_rate": 0.0003397435897435898,
"loss": 0.7791,
"step": 400
},
{
"epoch": 10.1,
"learning_rate": 0.00033934294871794873,
"loss": 0.7635,
"step": 401
},
{
"epoch": 10.13,
"learning_rate": 0.00033894230769230773,
"loss": 0.7713,
"step": 402
},
{
"epoch": 10.15,
"learning_rate": 0.0003385416666666667,
"loss": 0.827,
"step": 403
},
{
"epoch": 10.18,
"learning_rate": 0.0003381410256410257,
"loss": 0.7844,
"step": 404
},
{
"epoch": 10.2,
"learning_rate": 0.00033774038461538463,
"loss": 0.7839,
"step": 405
},
{
"epoch": 10.23,
"learning_rate": 0.00033733974358974363,
"loss": 0.7702,
"step": 406
},
{
"epoch": 10.26,
"learning_rate": 0.0003369391025641026,
"loss": 0.7855,
"step": 407
},
{
"epoch": 10.28,
"learning_rate": 0.0003365384615384616,
"loss": 0.7669,
"step": 408
},
{
"epoch": 10.31,
"learning_rate": 0.0003361378205128205,
"loss": 0.8054,
"step": 409
},
{
"epoch": 10.33,
"learning_rate": 0.0003357371794871795,
"loss": 0.7792,
"step": 410
},
{
"epoch": 10.36,
"learning_rate": 0.0003353365384615384,
"loss": 0.7986,
"step": 411
},
{
"epoch": 10.38,
"learning_rate": 0.0003349358974358974,
"loss": 0.8269,
"step": 412
},
{
"epoch": 10.41,
"learning_rate": 0.00033453525641025637,
"loss": 0.7923,
"step": 413
},
{
"epoch": 10.43,
"learning_rate": 0.00033413461538461537,
"loss": 0.8242,
"step": 414
},
{
"epoch": 10.46,
"learning_rate": 0.0003337339743589743,
"loss": 0.8496,
"step": 415
},
{
"epoch": 10.48,
"learning_rate": 0.0003333333333333333,
"loss": 0.8236,
"step": 416
},
{
"epoch": 10.51,
"learning_rate": 0.0003329326923076923,
"loss": 0.8685,
"step": 417
},
{
"epoch": 10.53,
"learning_rate": 0.00033253205128205127,
"loss": 0.8542,
"step": 418
},
{
"epoch": 10.56,
"learning_rate": 0.0003321314102564103,
"loss": 0.8185,
"step": 419
},
{
"epoch": 10.58,
"learning_rate": 0.0003317307692307692,
"loss": 0.8477,
"step": 420
},
{
"epoch": 10.61,
"learning_rate": 0.0003313301282051282,
"loss": 0.8372,
"step": 421
},
{
"epoch": 10.63,
"learning_rate": 0.00033092948717948717,
"loss": 0.8731,
"step": 422
},
{
"epoch": 10.66,
"learning_rate": 0.00033052884615384617,
"loss": 0.8322,
"step": 423
},
{
"epoch": 10.68,
"learning_rate": 0.0003301282051282051,
"loss": 0.8514,
"step": 424
},
{
"epoch": 10.71,
"learning_rate": 0.0003297275641025641,
"loss": 0.8564,
"step": 425
},
{
"epoch": 10.73,
"learning_rate": 0.00032932692307692307,
"loss": 0.8278,
"step": 426
},
{
"epoch": 10.76,
"learning_rate": 0.00032892628205128207,
"loss": 0.8408,
"step": 427
},
{
"epoch": 10.78,
"learning_rate": 0.000328525641025641,
"loss": 0.8438,
"step": 428
},
{
"epoch": 10.81,
"learning_rate": 0.000328125,
"loss": 0.8862,
"step": 429
},
{
"epoch": 10.83,
"learning_rate": 0.00032772435897435897,
"loss": 0.8631,
"step": 430
},
{
"epoch": 10.86,
"learning_rate": 0.00032732371794871797,
"loss": 0.883,
"step": 431
},
{
"epoch": 10.89,
"learning_rate": 0.0003269230769230769,
"loss": 0.8644,
"step": 432
},
{
"epoch": 10.91,
"learning_rate": 0.0003265224358974359,
"loss": 0.8907,
"step": 433
},
{
"epoch": 10.94,
"learning_rate": 0.00032612179487179487,
"loss": 0.9141,
"step": 434
},
{
"epoch": 10.96,
"learning_rate": 0.00032572115384615387,
"loss": 0.8877,
"step": 435
},
{
"epoch": 10.99,
"learning_rate": 0.0003253205128205128,
"loss": 0.8521,
"step": 436
},
{
"epoch": 11.01,
"learning_rate": 0.0003249198717948718,
"loss": 0.7842,
"step": 437
},
{
"epoch": 11.04,
"learning_rate": 0.00032451923076923077,
"loss": 0.6516,
"step": 438
},
{
"epoch": 11.06,
"learning_rate": 0.00032411858974358977,
"loss": 0.6549,
"step": 439
},
{
"epoch": 11.09,
"learning_rate": 0.0003237179487179487,
"loss": 0.6736,
"step": 440
},
{
"epoch": 11.11,
"learning_rate": 0.0003233173076923077,
"loss": 0.6625,
"step": 441
},
{
"epoch": 11.14,
"learning_rate": 0.0003229166666666667,
"loss": 0.6466,
"step": 442
},
{
"epoch": 11.16,
"learning_rate": 0.00032251602564102567,
"loss": 0.6362,
"step": 443
},
{
"epoch": 11.19,
"learning_rate": 0.00032211538461538467,
"loss": 0.674,
"step": 444
},
{
"epoch": 11.21,
"learning_rate": 0.0003217147435897436,
"loss": 0.6509,
"step": 445
},
{
"epoch": 11.24,
"learning_rate": 0.0003213141025641026,
"loss": 0.618,
"step": 446
},
{
"epoch": 11.26,
"learning_rate": 0.00032091346153846156,
"loss": 0.6654,
"step": 447
},
{
"epoch": 11.29,
"learning_rate": 0.00032051282051282057,
"loss": 0.6632,
"step": 448
},
{
"epoch": 11.31,
"learning_rate": 0.00032011217948717946,
"loss": 0.6599,
"step": 449
},
{
"epoch": 11.34,
"learning_rate": 0.00031971153846153846,
"loss": 0.6537,
"step": 450
},
{
"epoch": 11.36,
"learning_rate": 0.0003193108974358974,
"loss": 0.678,
"step": 451
},
{
"epoch": 11.39,
"learning_rate": 0.0003189102564102564,
"loss": 0.684,
"step": 452
},
{
"epoch": 11.41,
"learning_rate": 0.00031850961538461536,
"loss": 0.6419,
"step": 453
},
{
"epoch": 11.44,
"learning_rate": 0.00031810897435897436,
"loss": 0.6614,
"step": 454
},
{
"epoch": 11.46,
"learning_rate": 0.0003177083333333333,
"loss": 0.7037,
"step": 455
},
{
"epoch": 11.49,
"learning_rate": 0.0003173076923076923,
"loss": 0.6944,
"step": 456
},
{
"epoch": 11.51,
"learning_rate": 0.00031690705128205126,
"loss": 0.6818,
"step": 457
},
{
"epoch": 11.54,
"learning_rate": 0.00031650641025641026,
"loss": 0.692,
"step": 458
},
{
"epoch": 11.57,
"learning_rate": 0.0003161057692307692,
"loss": 0.7028,
"step": 459
},
{
"epoch": 11.59,
"learning_rate": 0.0003157051282051282,
"loss": 0.7009,
"step": 460
},
{
"epoch": 11.62,
"learning_rate": 0.00031530448717948716,
"loss": 0.7325,
"step": 461
},
{
"epoch": 11.64,
"learning_rate": 0.00031490384615384616,
"loss": 0.6738,
"step": 462
},
{
"epoch": 11.67,
"learning_rate": 0.0003145032051282051,
"loss": 0.7008,
"step": 463
},
{
"epoch": 11.69,
"learning_rate": 0.0003141025641025641,
"loss": 0.6838,
"step": 464
},
{
"epoch": 11.72,
"learning_rate": 0.00031370192307692306,
"loss": 0.726,
"step": 465
},
{
"epoch": 11.74,
"learning_rate": 0.00031330128205128206,
"loss": 0.7167,
"step": 466
},
{
"epoch": 11.77,
"learning_rate": 0.000312900641025641,
"loss": 0.7236,
"step": 467
},
{
"epoch": 11.79,
"learning_rate": 0.0003125,
"loss": 0.7076,
"step": 468
},
{
"epoch": 11.82,
"learning_rate": 0.000312099358974359,
"loss": 0.7415,
"step": 469
},
{
"epoch": 11.84,
"learning_rate": 0.00031169871794871796,
"loss": 0.7313,
"step": 470
},
{
"epoch": 11.87,
"learning_rate": 0.00031129807692307696,
"loss": 0.7403,
"step": 471
},
{
"epoch": 11.89,
"learning_rate": 0.0003108974358974359,
"loss": 0.7145,
"step": 472
},
{
"epoch": 11.92,
"learning_rate": 0.0003104967948717949,
"loss": 0.7532,
"step": 473
},
{
"epoch": 11.94,
"learning_rate": 0.00031009615384615385,
"loss": 0.7326,
"step": 474
},
{
"epoch": 11.97,
"learning_rate": 0.00030969551282051286,
"loss": 0.7699,
"step": 475
},
{
"epoch": 11.99,
"learning_rate": 0.0003092948717948718,
"loss": 0.7251,
"step": 476
},
{
"epoch": 12.02,
"learning_rate": 0.0003088942307692308,
"loss": 0.5773,
"step": 477
},
{
"epoch": 12.04,
"learning_rate": 0.00030849358974358975,
"loss": 0.5288,
"step": 478
},
{
"epoch": 12.07,
"learning_rate": 0.00030809294871794876,
"loss": 0.5312,
"step": 479
},
{
"epoch": 12.09,
"learning_rate": 0.0003076923076923077,
"loss": 0.5445,
"step": 480
},
{
"epoch": 12.12,
"learning_rate": 0.0003072916666666667,
"loss": 0.5218,
"step": 481
},
{
"epoch": 12.14,
"learning_rate": 0.00030689102564102565,
"loss": 0.5311,
"step": 482
},
{
"epoch": 12.17,
"learning_rate": 0.00030649038461538465,
"loss": 0.5541,
"step": 483
},
{
"epoch": 12.2,
"learning_rate": 0.0003060897435897436,
"loss": 0.5242,
"step": 484
},
{
"epoch": 12.22,
"learning_rate": 0.0003056891025641026,
"loss": 0.5302,
"step": 485
},
{
"epoch": 12.25,
"learning_rate": 0.00030528846153846155,
"loss": 0.536,
"step": 486
},
{
"epoch": 12.27,
"learning_rate": 0.00030488782051282055,
"loss": 0.5545,
"step": 487
},
{
"epoch": 12.3,
"learning_rate": 0.00030448717948717945,
"loss": 0.5476,
"step": 488
},
{
"epoch": 12.32,
"learning_rate": 0.00030408653846153845,
"loss": 0.5528,
"step": 489
},
{
"epoch": 12.35,
"learning_rate": 0.0003036858974358974,
"loss": 0.5633,
"step": 490
},
{
"epoch": 12.37,
"learning_rate": 0.0003032852564102564,
"loss": 0.571,
"step": 491
},
{
"epoch": 12.4,
"learning_rate": 0.00030288461538461535,
"loss": 0.5637,
"step": 492
},
{
"epoch": 12.42,
"learning_rate": 0.00030248397435897435,
"loss": 0.5613,
"step": 493
},
{
"epoch": 12.45,
"learning_rate": 0.0003020833333333333,
"loss": 0.5999,
"step": 494
},
{
"epoch": 12.47,
"learning_rate": 0.0003016826923076923,
"loss": 0.5633,
"step": 495
},
{
"epoch": 12.5,
"learning_rate": 0.0003012820512820513,
"loss": 0.5811,
"step": 496
},
{
"epoch": 12.52,
"learning_rate": 0.00030088141025641025,
"loss": 0.5711,
"step": 497
},
{
"epoch": 12.55,
"learning_rate": 0.00030048076923076925,
"loss": 0.5669,
"step": 498
},
{
"epoch": 12.57,
"learning_rate": 0.0003000801282051282,
"loss": 0.5424,
"step": 499
},
{
"epoch": 12.6,
"learning_rate": 0.0002996794871794872,
"loss": 0.5592,
"step": 500
},
{
"epoch": 12.62,
"learning_rate": 0.00029927884615384614,
"loss": 0.5645,
"step": 501
},
{
"epoch": 12.65,
"learning_rate": 0.00029887820512820515,
"loss": 0.6089,
"step": 502
},
{
"epoch": 12.67,
"learning_rate": 0.0002984775641025641,
"loss": 0.57,
"step": 503
},
{
"epoch": 12.7,
"learning_rate": 0.0002980769230769231,
"loss": 0.57,
"step": 504
},
{
"epoch": 12.72,
"learning_rate": 0.00029767628205128204,
"loss": 0.5511,
"step": 505
},
{
"epoch": 12.75,
"learning_rate": 0.00029727564102564105,
"loss": 0.5765,
"step": 506
},
{
"epoch": 12.77,
"learning_rate": 0.000296875,
"loss": 0.5896,
"step": 507
},
{
"epoch": 12.8,
"learning_rate": 0.000296474358974359,
"loss": 0.6329,
"step": 508
},
{
"epoch": 12.83,
"learning_rate": 0.00029607371794871794,
"loss": 0.5682,
"step": 509
},
{
"epoch": 12.85,
"learning_rate": 0.00029567307692307694,
"loss": 0.58,
"step": 510
},
{
"epoch": 12.88,
"learning_rate": 0.0002952724358974359,
"loss": 0.6014,
"step": 511
},
{
"epoch": 12.9,
"learning_rate": 0.0002948717948717949,
"loss": 0.6082,
"step": 512
},
{
"epoch": 12.93,
"learning_rate": 0.00029447115384615384,
"loss": 0.6392,
"step": 513
},
{
"epoch": 12.95,
"learning_rate": 0.00029407051282051284,
"loss": 0.609,
"step": 514
},
{
"epoch": 12.98,
"learning_rate": 0.0002936698717948718,
"loss": 0.6247,
"step": 515
},
{
"epoch": 13.0,
"learning_rate": 0.0002932692307692308,
"loss": 0.5943,
"step": 516
},
{
"epoch": 13.03,
"learning_rate": 0.00029286858974358974,
"loss": 0.4499,
"step": 517
},
{
"epoch": 13.05,
"learning_rate": 0.00029246794871794874,
"loss": 0.4412,
"step": 518
},
{
"epoch": 13.08,
"learning_rate": 0.0002920673076923077,
"loss": 0.4409,
"step": 519
},
{
"epoch": 13.1,
"learning_rate": 0.0002916666666666667,
"loss": 0.4505,
"step": 520
},
{
"epoch": 13.13,
"learning_rate": 0.0002912660256410257,
"loss": 0.4489,
"step": 521
},
{
"epoch": 13.15,
"learning_rate": 0.00029086538461538464,
"loss": 0.4235,
"step": 522
},
{
"epoch": 13.18,
"learning_rate": 0.00029046474358974364,
"loss": 0.4276,
"step": 523
},
{
"epoch": 13.2,
"learning_rate": 0.0002900641025641026,
"loss": 0.4544,
"step": 524
},
{
"epoch": 13.23,
"learning_rate": 0.0002896634615384616,
"loss": 0.4625,
"step": 525
},
{
"epoch": 13.25,
"learning_rate": 0.00028926282051282054,
"loss": 0.4266,
"step": 526
},
{
"epoch": 13.28,
"learning_rate": 0.0002888621794871795,
"loss": 0.4459,
"step": 527
},
{
"epoch": 13.3,
"learning_rate": 0.00028846153846153843,
"loss": 0.4261,
"step": 528
},
{
"epoch": 13.33,
"learning_rate": 0.00028806089743589744,
"loss": 0.4376,
"step": 529
},
{
"epoch": 13.35,
"learning_rate": 0.0002876602564102564,
"loss": 0.4418,
"step": 530
},
{
"epoch": 13.38,
"learning_rate": 0.0002872596153846154,
"loss": 0.4667,
"step": 531
},
{
"epoch": 13.4,
"learning_rate": 0.00028685897435897433,
"loss": 0.4504,
"step": 532
},
{
"epoch": 13.43,
"learning_rate": 0.00028645833333333333,
"loss": 0.4691,
"step": 533
},
{
"epoch": 13.46,
"learning_rate": 0.0002860576923076923,
"loss": 0.4684,
"step": 534
},
{
"epoch": 13.48,
"learning_rate": 0.0002856570512820513,
"loss": 0.467,
"step": 535
},
{
"epoch": 13.51,
"learning_rate": 0.00028525641025641023,
"loss": 0.4716,
"step": 536
},
{
"epoch": 13.53,
"learning_rate": 0.00028485576923076923,
"loss": 0.4619,
"step": 537
},
{
"epoch": 13.56,
"learning_rate": 0.0002844551282051282,
"loss": 0.4775,
"step": 538
},
{
"epoch": 13.58,
"learning_rate": 0.0002840544871794872,
"loss": 0.4568,
"step": 539
},
{
"epoch": 13.61,
"learning_rate": 0.00028365384615384613,
"loss": 0.4763,
"step": 540
},
{
"epoch": 13.63,
"learning_rate": 0.00028325320512820513,
"loss": 0.466,
"step": 541
},
{
"epoch": 13.66,
"learning_rate": 0.0002828525641025641,
"loss": 0.4543,
"step": 542
},
{
"epoch": 13.68,
"learning_rate": 0.0002824519230769231,
"loss": 0.4666,
"step": 543
},
{
"epoch": 13.71,
"learning_rate": 0.00028205128205128203,
"loss": 0.489,
"step": 544
},
{
"epoch": 13.73,
"learning_rate": 0.00028165064102564103,
"loss": 0.491,
"step": 545
},
{
"epoch": 13.76,
"learning_rate": 0.00028125000000000003,
"loss": 0.4847,
"step": 546
},
{
"epoch": 13.78,
"learning_rate": 0.000280849358974359,
"loss": 0.4899,
"step": 547
},
{
"epoch": 13.81,
"learning_rate": 0.000280448717948718,
"loss": 0.5169,
"step": 548
},
{
"epoch": 13.83,
"learning_rate": 0.00028004807692307693,
"loss": 0.4968,
"step": 549
},
{
"epoch": 13.86,
"learning_rate": 0.00027964743589743593,
"loss": 0.4774,
"step": 550
},
{
"epoch": 13.88,
"learning_rate": 0.0002792467948717949,
"loss": 0.5105,
"step": 551
},
{
"epoch": 13.91,
"learning_rate": 0.0002788461538461539,
"loss": 0.4997,
"step": 552
},
{
"epoch": 13.93,
"learning_rate": 0.00027844551282051283,
"loss": 0.5088,
"step": 553
},
{
"epoch": 13.96,
"learning_rate": 0.00027804487179487183,
"loss": 0.5091,
"step": 554
},
{
"epoch": 13.98,
"learning_rate": 0.0002776442307692308,
"loss": 0.532,
"step": 555
},
{
"epoch": 14.01,
"learning_rate": 0.0002772435897435898,
"loss": 0.4487,
"step": 556
},
{
"epoch": 14.03,
"learning_rate": 0.00027684294871794873,
"loss": 0.3525,
"step": 557
},
{
"epoch": 14.06,
"learning_rate": 0.00027644230769230773,
"loss": 0.3715,
"step": 558
},
{
"epoch": 14.09,
"learning_rate": 0.0002760416666666667,
"loss": 0.3547,
"step": 559
},
{
"epoch": 14.11,
"learning_rate": 0.0002756410256410257,
"loss": 0.3862,
"step": 560
},
{
"epoch": 14.14,
"learning_rate": 0.0002752403846153846,
"loss": 0.3514,
"step": 561
},
{
"epoch": 14.16,
"learning_rate": 0.00027483974358974363,
"loss": 0.362,
"step": 562
},
{
"epoch": 14.19,
"learning_rate": 0.0002744391025641026,
"loss": 0.3457,
"step": 563
},
{
"epoch": 14.21,
"learning_rate": 0.0002740384615384616,
"loss": 0.3662,
"step": 564
},
{
"epoch": 14.24,
"learning_rate": 0.0002736378205128205,
"loss": 0.3746,
"step": 565
},
{
"epoch": 14.26,
"learning_rate": 0.00027323717948717947,
"loss": 0.3388,
"step": 566
},
{
"epoch": 14.29,
"learning_rate": 0.0002728365384615384,
"loss": 0.3824,
"step": 567
},
{
"epoch": 14.31,
"learning_rate": 0.0002724358974358974,
"loss": 0.3584,
"step": 568
},
{
"epoch": 14.34,
"learning_rate": 0.00027203525641025637,
"loss": 0.3544,
"step": 569
},
{
"epoch": 14.36,
"learning_rate": 0.00027163461538461537,
"loss": 0.3721,
"step": 570
},
{
"epoch": 14.39,
"learning_rate": 0.0002712339743589743,
"loss": 0.3769,
"step": 571
},
{
"epoch": 14.41,
"learning_rate": 0.0002708333333333333,
"loss": 0.3872,
"step": 572
},
{
"epoch": 14.44,
"learning_rate": 0.0002704326923076923,
"loss": 0.363,
"step": 573
},
{
"epoch": 14.46,
"learning_rate": 0.00027003205128205127,
"loss": 0.3842,
"step": 574
},
{
"epoch": 14.49,
"learning_rate": 0.00026963141025641027,
"loss": 0.3737,
"step": 575
},
{
"epoch": 14.51,
"learning_rate": 0.0002692307692307692,
"loss": 0.3981,
"step": 576
},
{
"epoch": 14.54,
"learning_rate": 0.0002688301282051282,
"loss": 0.3656,
"step": 577
},
{
"epoch": 14.56,
"learning_rate": 0.00026842948717948717,
"loss": 0.3852,
"step": 578
},
{
"epoch": 14.59,
"learning_rate": 0.00026802884615384617,
"loss": 0.3865,
"step": 579
},
{
"epoch": 14.61,
"learning_rate": 0.0002676282051282051,
"loss": 0.3747,
"step": 580
},
{
"epoch": 14.64,
"learning_rate": 0.0002672275641025641,
"loss": 0.3729,
"step": 581
},
{
"epoch": 14.66,
"learning_rate": 0.00026682692307692307,
"loss": 0.3785,
"step": 582
},
{
"epoch": 14.69,
"learning_rate": 0.00026642628205128207,
"loss": 0.4018,
"step": 583
},
{
"epoch": 14.71,
"learning_rate": 0.000266025641025641,
"loss": 0.3854,
"step": 584
},
{
"epoch": 14.74,
"learning_rate": 0.000265625,
"loss": 0.4161,
"step": 585
},
{
"epoch": 14.77,
"learning_rate": 0.00026522435897435897,
"loss": 0.4093,
"step": 586
},
{
"epoch": 14.79,
"learning_rate": 0.00026482371794871797,
"loss": 0.4126,
"step": 587
},
{
"epoch": 14.82,
"learning_rate": 0.0002644230769230769,
"loss": 0.3977,
"step": 588
},
{
"epoch": 14.84,
"learning_rate": 0.0002640224358974359,
"loss": 0.4286,
"step": 589
},
{
"epoch": 14.87,
"learning_rate": 0.00026362179487179487,
"loss": 0.4371,
"step": 590
},
{
"epoch": 14.89,
"learning_rate": 0.00026322115384615387,
"loss": 0.4066,
"step": 591
},
{
"epoch": 14.92,
"learning_rate": 0.0002628205128205128,
"loss": 0.433,
"step": 592
},
{
"epoch": 14.94,
"learning_rate": 0.0002624198717948718,
"loss": 0.4361,
"step": 593
},
{
"epoch": 14.97,
"learning_rate": 0.00026201923076923076,
"loss": 0.4276,
"step": 594
},
{
"epoch": 14.99,
"learning_rate": 0.00026161858974358977,
"loss": 0.4401,
"step": 595
},
{
"epoch": 15.02,
"learning_rate": 0.0002612179487179487,
"loss": 0.3514,
"step": 596
},
{
"epoch": 15.04,
"learning_rate": 0.0002608173076923077,
"loss": 0.306,
"step": 597
},
{
"epoch": 15.07,
"learning_rate": 0.0002604166666666667,
"loss": 0.2862,
"step": 598
},
{
"epoch": 15.09,
"learning_rate": 0.00026001602564102566,
"loss": 0.3042,
"step": 599
},
{
"epoch": 15.12,
"learning_rate": 0.00025961538461538467,
"loss": 0.2978,
"step": 600
}
],
"logging_steps": 1,
"max_steps": 1248,
"num_train_epochs": 32,
"save_steps": 100,
"total_flos": 3.374598554368205e+17,
"trial_name": null,
"trial_params": null
}