test / trainer_state.json
yuersan's picture
Upload 13 files
f1c87d0
raw
history blame
68.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 33.982300884955755,
"global_step": 600,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.06,
"learning_rate": 2.0000000000000003e-06,
"loss": 2.2431,
"step": 1
},
{
"epoch": 0.11,
"learning_rate": 4.000000000000001e-06,
"loss": 2.5758,
"step": 2
},
{
"epoch": 0.17,
"learning_rate": 6e-06,
"loss": 2.3017,
"step": 3
},
{
"epoch": 0.23,
"learning_rate": 8.000000000000001e-06,
"loss": 2.3675,
"step": 4
},
{
"epoch": 0.28,
"learning_rate": 1e-05,
"loss": 2.3984,
"step": 5
},
{
"epoch": 0.34,
"learning_rate": 1.2e-05,
"loss": 2.2344,
"step": 6
},
{
"epoch": 0.4,
"learning_rate": 1.4000000000000001e-05,
"loss": 2.3358,
"step": 7
},
{
"epoch": 0.45,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.183,
"step": 8
},
{
"epoch": 0.51,
"learning_rate": 1.8e-05,
"loss": 2.2045,
"step": 9
},
{
"epoch": 0.57,
"learning_rate": 2e-05,
"loss": 2.146,
"step": 10
},
{
"epoch": 0.62,
"learning_rate": 2.2000000000000003e-05,
"loss": 2.0256,
"step": 11
},
{
"epoch": 0.68,
"learning_rate": 2.4e-05,
"loss": 1.961,
"step": 12
},
{
"epoch": 0.74,
"learning_rate": 2.6000000000000002e-05,
"loss": 2.121,
"step": 13
},
{
"epoch": 0.79,
"learning_rate": 2.8000000000000003e-05,
"loss": 2.0502,
"step": 14
},
{
"epoch": 0.85,
"learning_rate": 3e-05,
"loss": 1.9754,
"step": 15
},
{
"epoch": 0.91,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.8381,
"step": 16
},
{
"epoch": 0.96,
"learning_rate": 3.4000000000000007e-05,
"loss": 1.8665,
"step": 17
},
{
"epoch": 1.02,
"learning_rate": 3.6e-05,
"loss": 2.0878,
"step": 18
},
{
"epoch": 1.08,
"learning_rate": 3.8e-05,
"loss": 1.7907,
"step": 19
},
{
"epoch": 1.13,
"learning_rate": 4e-05,
"loss": 2.0663,
"step": 20
},
{
"epoch": 1.19,
"learning_rate": 4.2e-05,
"loss": 1.7996,
"step": 21
},
{
"epoch": 1.25,
"learning_rate": 4.4000000000000006e-05,
"loss": 2.0797,
"step": 22
},
{
"epoch": 1.3,
"learning_rate": 4.600000000000001e-05,
"loss": 1.8656,
"step": 23
},
{
"epoch": 1.36,
"learning_rate": 4.8e-05,
"loss": 1.8085,
"step": 24
},
{
"epoch": 1.42,
"learning_rate": 5e-05,
"loss": 1.8279,
"step": 25
},
{
"epoch": 1.47,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.7922,
"step": 26
},
{
"epoch": 1.53,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.8851,
"step": 27
},
{
"epoch": 1.59,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.6355,
"step": 28
},
{
"epoch": 1.64,
"learning_rate": 5.8e-05,
"loss": 1.7099,
"step": 29
},
{
"epoch": 1.7,
"learning_rate": 6e-05,
"loss": 1.7664,
"step": 30
},
{
"epoch": 1.76,
"learning_rate": 6.2e-05,
"loss": 1.7728,
"step": 31
},
{
"epoch": 1.81,
"learning_rate": 6.400000000000001e-05,
"loss": 1.8335,
"step": 32
},
{
"epoch": 1.87,
"learning_rate": 6.6e-05,
"loss": 1.7173,
"step": 33
},
{
"epoch": 1.93,
"learning_rate": 6.800000000000001e-05,
"loss": 1.5278,
"step": 34
},
{
"epoch": 1.98,
"learning_rate": 7e-05,
"loss": 1.8614,
"step": 35
},
{
"epoch": 2.04,
"learning_rate": 7.2e-05,
"loss": 1.7847,
"step": 36
},
{
"epoch": 2.1,
"learning_rate": 7.4e-05,
"loss": 1.7366,
"step": 37
},
{
"epoch": 2.15,
"learning_rate": 7.6e-05,
"loss": 1.5379,
"step": 38
},
{
"epoch": 2.21,
"learning_rate": 7.800000000000001e-05,
"loss": 1.6856,
"step": 39
},
{
"epoch": 2.27,
"learning_rate": 8e-05,
"loss": 1.6452,
"step": 40
},
{
"epoch": 2.32,
"learning_rate": 8.2e-05,
"loss": 1.8233,
"step": 41
},
{
"epoch": 2.38,
"learning_rate": 8.4e-05,
"loss": 1.8079,
"step": 42
},
{
"epoch": 2.44,
"learning_rate": 8.6e-05,
"loss": 1.7128,
"step": 43
},
{
"epoch": 2.49,
"learning_rate": 8.800000000000001e-05,
"loss": 1.8746,
"step": 44
},
{
"epoch": 2.55,
"learning_rate": 9e-05,
"loss": 1.6117,
"step": 45
},
{
"epoch": 2.61,
"learning_rate": 9.200000000000001e-05,
"loss": 1.6552,
"step": 46
},
{
"epoch": 2.66,
"learning_rate": 9.4e-05,
"loss": 1.6429,
"step": 47
},
{
"epoch": 2.72,
"learning_rate": 9.6e-05,
"loss": 1.5429,
"step": 48
},
{
"epoch": 2.78,
"learning_rate": 9.8e-05,
"loss": 1.6358,
"step": 49
},
{
"epoch": 2.83,
"learning_rate": 0.0001,
"loss": 1.8581,
"step": 50
},
{
"epoch": 2.89,
"learning_rate": 0.00010200000000000001,
"loss": 1.6794,
"step": 51
},
{
"epoch": 2.95,
"learning_rate": 0.00010400000000000001,
"loss": 1.683,
"step": 52
},
{
"epoch": 3.0,
"learning_rate": 0.00010600000000000002,
"loss": 1.7204,
"step": 53
},
{
"epoch": 3.06,
"learning_rate": 0.00010800000000000001,
"loss": 1.7068,
"step": 54
},
{
"epoch": 3.12,
"learning_rate": 0.00011000000000000002,
"loss": 1.5245,
"step": 55
},
{
"epoch": 3.17,
"learning_rate": 0.00011200000000000001,
"loss": 1.5683,
"step": 56
},
{
"epoch": 3.23,
"learning_rate": 0.00011399999999999999,
"loss": 1.8291,
"step": 57
},
{
"epoch": 3.28,
"learning_rate": 0.000116,
"loss": 1.625,
"step": 58
},
{
"epoch": 3.34,
"learning_rate": 0.000118,
"loss": 1.7945,
"step": 59
},
{
"epoch": 3.4,
"learning_rate": 0.00012,
"loss": 1.5244,
"step": 60
},
{
"epoch": 3.45,
"learning_rate": 0.000122,
"loss": 1.6436,
"step": 61
},
{
"epoch": 3.51,
"learning_rate": 0.000124,
"loss": 1.6679,
"step": 62
},
{
"epoch": 3.57,
"learning_rate": 0.000126,
"loss": 1.7644,
"step": 63
},
{
"epoch": 3.62,
"learning_rate": 0.00012800000000000002,
"loss": 1.6776,
"step": 64
},
{
"epoch": 3.68,
"learning_rate": 0.00013000000000000002,
"loss": 1.627,
"step": 65
},
{
"epoch": 3.74,
"learning_rate": 0.000132,
"loss": 1.5084,
"step": 66
},
{
"epoch": 3.79,
"learning_rate": 0.000134,
"loss": 1.6967,
"step": 67
},
{
"epoch": 3.85,
"learning_rate": 0.00013600000000000003,
"loss": 1.5249,
"step": 68
},
{
"epoch": 3.91,
"learning_rate": 0.000138,
"loss": 1.6821,
"step": 69
},
{
"epoch": 3.96,
"learning_rate": 0.00014,
"loss": 1.5071,
"step": 70
},
{
"epoch": 4.02,
"learning_rate": 0.000142,
"loss": 1.7624,
"step": 71
},
{
"epoch": 4.08,
"learning_rate": 0.000144,
"loss": 1.6826,
"step": 72
},
{
"epoch": 4.13,
"learning_rate": 0.000146,
"loss": 1.6488,
"step": 73
},
{
"epoch": 4.19,
"learning_rate": 0.000148,
"loss": 1.5138,
"step": 74
},
{
"epoch": 4.25,
"learning_rate": 0.00015000000000000001,
"loss": 1.6149,
"step": 75
},
{
"epoch": 4.3,
"learning_rate": 0.000152,
"loss": 1.4464,
"step": 76
},
{
"epoch": 4.36,
"learning_rate": 0.000154,
"loss": 1.4529,
"step": 77
},
{
"epoch": 4.42,
"learning_rate": 0.00015600000000000002,
"loss": 1.3768,
"step": 78
},
{
"epoch": 4.47,
"learning_rate": 0.00015800000000000002,
"loss": 1.4852,
"step": 79
},
{
"epoch": 4.53,
"learning_rate": 0.00016,
"loss": 1.6161,
"step": 80
},
{
"epoch": 4.59,
"learning_rate": 0.000162,
"loss": 1.749,
"step": 81
},
{
"epoch": 4.64,
"learning_rate": 0.000164,
"loss": 1.7293,
"step": 82
},
{
"epoch": 4.7,
"learning_rate": 0.000166,
"loss": 1.6095,
"step": 83
},
{
"epoch": 4.76,
"learning_rate": 0.000168,
"loss": 1.6558,
"step": 84
},
{
"epoch": 4.81,
"learning_rate": 0.00017,
"loss": 1.7317,
"step": 85
},
{
"epoch": 4.87,
"learning_rate": 0.000172,
"loss": 1.6435,
"step": 86
},
{
"epoch": 4.93,
"learning_rate": 0.000174,
"loss": 1.8289,
"step": 87
},
{
"epoch": 4.98,
"learning_rate": 0.00017600000000000002,
"loss": 1.4689,
"step": 88
},
{
"epoch": 5.04,
"learning_rate": 0.00017800000000000002,
"loss": 1.728,
"step": 89
},
{
"epoch": 5.1,
"learning_rate": 0.00018,
"loss": 1.5481,
"step": 90
},
{
"epoch": 5.15,
"learning_rate": 0.000182,
"loss": 1.6498,
"step": 91
},
{
"epoch": 5.21,
"learning_rate": 0.00018400000000000003,
"loss": 1.5319,
"step": 92
},
{
"epoch": 5.27,
"learning_rate": 0.00018600000000000002,
"loss": 1.6678,
"step": 93
},
{
"epoch": 5.32,
"learning_rate": 0.000188,
"loss": 1.4058,
"step": 94
},
{
"epoch": 5.38,
"learning_rate": 0.00019,
"loss": 1.6551,
"step": 95
},
{
"epoch": 5.44,
"learning_rate": 0.000192,
"loss": 1.5329,
"step": 96
},
{
"epoch": 5.49,
"learning_rate": 0.000194,
"loss": 1.4911,
"step": 97
},
{
"epoch": 5.55,
"learning_rate": 0.000196,
"loss": 1.796,
"step": 98
},
{
"epoch": 5.61,
"learning_rate": 0.00019800000000000002,
"loss": 1.6878,
"step": 99
},
{
"epoch": 5.66,
"learning_rate": 0.0002,
"loss": 1.6483,
"step": 100
},
{
"epoch": 5.72,
"learning_rate": 0.00019987500000000002,
"loss": 1.4458,
"step": 101
},
{
"epoch": 5.78,
"learning_rate": 0.00019975,
"loss": 1.4612,
"step": 102
},
{
"epoch": 5.83,
"learning_rate": 0.00019962500000000001,
"loss": 1.6,
"step": 103
},
{
"epoch": 5.89,
"learning_rate": 0.00019950000000000002,
"loss": 1.5416,
"step": 104
},
{
"epoch": 5.95,
"learning_rate": 0.000199375,
"loss": 1.614,
"step": 105
},
{
"epoch": 6.0,
"learning_rate": 0.00019925,
"loss": 1.5744,
"step": 106
},
{
"epoch": 6.06,
"learning_rate": 0.000199125,
"loss": 1.4321,
"step": 107
},
{
"epoch": 6.12,
"learning_rate": 0.000199,
"loss": 1.5335,
"step": 108
},
{
"epoch": 6.17,
"learning_rate": 0.00019887500000000002,
"loss": 1.4739,
"step": 109
},
{
"epoch": 6.23,
"learning_rate": 0.00019875,
"loss": 1.4072,
"step": 110
},
{
"epoch": 6.29,
"learning_rate": 0.00019862500000000002,
"loss": 1.3836,
"step": 111
},
{
"epoch": 6.34,
"learning_rate": 0.00019850000000000003,
"loss": 1.5784,
"step": 112
},
{
"epoch": 6.4,
"learning_rate": 0.000198375,
"loss": 1.7039,
"step": 113
},
{
"epoch": 6.46,
"learning_rate": 0.00019825,
"loss": 1.587,
"step": 114
},
{
"epoch": 6.51,
"learning_rate": 0.000198125,
"loss": 1.4426,
"step": 115
},
{
"epoch": 6.57,
"learning_rate": 0.00019800000000000002,
"loss": 1.514,
"step": 116
},
{
"epoch": 6.63,
"learning_rate": 0.000197875,
"loss": 1.4913,
"step": 117
},
{
"epoch": 6.68,
"learning_rate": 0.00019775,
"loss": 1.5138,
"step": 118
},
{
"epoch": 6.74,
"learning_rate": 0.00019762500000000002,
"loss": 1.4991,
"step": 119
},
{
"epoch": 6.8,
"learning_rate": 0.00019750000000000003,
"loss": 1.6112,
"step": 120
},
{
"epoch": 6.85,
"learning_rate": 0.00019737499999999999,
"loss": 1.6294,
"step": 121
},
{
"epoch": 6.91,
"learning_rate": 0.00019725,
"loss": 1.6799,
"step": 122
},
{
"epoch": 6.97,
"learning_rate": 0.000197125,
"loss": 1.6058,
"step": 123
},
{
"epoch": 7.02,
"learning_rate": 0.00019700000000000002,
"loss": 1.7086,
"step": 124
},
{
"epoch": 7.08,
"learning_rate": 0.000196875,
"loss": 1.659,
"step": 125
},
{
"epoch": 7.14,
"learning_rate": 0.00019675,
"loss": 1.4066,
"step": 126
},
{
"epoch": 7.19,
"learning_rate": 0.00019662500000000002,
"loss": 1.4265,
"step": 127
},
{
"epoch": 7.25,
"learning_rate": 0.0001965,
"loss": 1.5891,
"step": 128
},
{
"epoch": 7.31,
"learning_rate": 0.00019637500000000002,
"loss": 1.6088,
"step": 129
},
{
"epoch": 7.36,
"learning_rate": 0.00019625,
"loss": 1.5274,
"step": 130
},
{
"epoch": 7.42,
"learning_rate": 0.000196125,
"loss": 1.5988,
"step": 131
},
{
"epoch": 7.48,
"learning_rate": 0.000196,
"loss": 1.6922,
"step": 132
},
{
"epoch": 7.53,
"learning_rate": 0.000195875,
"loss": 1.4708,
"step": 133
},
{
"epoch": 7.59,
"learning_rate": 0.00019575000000000001,
"loss": 1.3907,
"step": 134
},
{
"epoch": 7.65,
"learning_rate": 0.00019562500000000003,
"loss": 1.5097,
"step": 135
},
{
"epoch": 7.7,
"learning_rate": 0.0001955,
"loss": 1.5843,
"step": 136
},
{
"epoch": 7.76,
"learning_rate": 0.00019537500000000002,
"loss": 1.5949,
"step": 137
},
{
"epoch": 7.82,
"learning_rate": 0.00019525,
"loss": 1.5275,
"step": 138
},
{
"epoch": 7.87,
"learning_rate": 0.000195125,
"loss": 1.3971,
"step": 139
},
{
"epoch": 7.93,
"learning_rate": 0.000195,
"loss": 1.6457,
"step": 140
},
{
"epoch": 7.99,
"learning_rate": 0.000194875,
"loss": 1.4983,
"step": 141
},
{
"epoch": 8.04,
"learning_rate": 0.00019475000000000002,
"loss": 1.3942,
"step": 142
},
{
"epoch": 8.1,
"learning_rate": 0.000194625,
"loss": 1.3633,
"step": 143
},
{
"epoch": 8.16,
"learning_rate": 0.0001945,
"loss": 1.3908,
"step": 144
},
{
"epoch": 8.21,
"learning_rate": 0.00019437500000000002,
"loss": 1.4746,
"step": 145
},
{
"epoch": 8.27,
"learning_rate": 0.00019425,
"loss": 1.4776,
"step": 146
},
{
"epoch": 8.33,
"learning_rate": 0.000194125,
"loss": 1.5559,
"step": 147
},
{
"epoch": 8.38,
"learning_rate": 0.000194,
"loss": 1.5798,
"step": 148
},
{
"epoch": 8.44,
"learning_rate": 0.000193875,
"loss": 1.5173,
"step": 149
},
{
"epoch": 8.5,
"learning_rate": 0.00019375000000000002,
"loss": 1.4286,
"step": 150
},
{
"epoch": 8.55,
"learning_rate": 0.000193625,
"loss": 1.4609,
"step": 151
},
{
"epoch": 8.61,
"learning_rate": 0.00019350000000000001,
"loss": 1.361,
"step": 152
},
{
"epoch": 8.67,
"learning_rate": 0.00019337500000000002,
"loss": 1.6866,
"step": 153
},
{
"epoch": 8.72,
"learning_rate": 0.00019325,
"loss": 1.5571,
"step": 154
},
{
"epoch": 8.78,
"learning_rate": 0.000193125,
"loss": 1.4351,
"step": 155
},
{
"epoch": 8.84,
"learning_rate": 0.000193,
"loss": 1.444,
"step": 156
},
{
"epoch": 8.89,
"learning_rate": 0.000192875,
"loss": 1.5379,
"step": 157
},
{
"epoch": 8.95,
"learning_rate": 0.00019275,
"loss": 1.4775,
"step": 158
},
{
"epoch": 9.01,
"learning_rate": 0.000192625,
"loss": 1.5141,
"step": 159
},
{
"epoch": 9.06,
"learning_rate": 0.00019250000000000002,
"loss": 1.491,
"step": 160
},
{
"epoch": 9.12,
"learning_rate": 0.00019237500000000003,
"loss": 1.6459,
"step": 161
},
{
"epoch": 9.18,
"learning_rate": 0.00019225,
"loss": 1.4853,
"step": 162
},
{
"epoch": 9.23,
"learning_rate": 0.000192125,
"loss": 1.5958,
"step": 163
},
{
"epoch": 9.29,
"learning_rate": 0.000192,
"loss": 1.228,
"step": 164
},
{
"epoch": 9.35,
"learning_rate": 0.00019187500000000002,
"loss": 1.3625,
"step": 165
},
{
"epoch": 9.4,
"learning_rate": 0.00019175,
"loss": 1.3645,
"step": 166
},
{
"epoch": 9.46,
"learning_rate": 0.000191625,
"loss": 1.4625,
"step": 167
},
{
"epoch": 9.52,
"learning_rate": 0.00019150000000000002,
"loss": 1.4005,
"step": 168
},
{
"epoch": 9.57,
"learning_rate": 0.000191375,
"loss": 1.4099,
"step": 169
},
{
"epoch": 9.63,
"learning_rate": 0.00019125000000000001,
"loss": 1.5099,
"step": 170
},
{
"epoch": 9.68,
"learning_rate": 0.000191125,
"loss": 1.5183,
"step": 171
},
{
"epoch": 9.74,
"learning_rate": 0.000191,
"loss": 1.5149,
"step": 172
},
{
"epoch": 9.8,
"learning_rate": 0.000190875,
"loss": 1.2841,
"step": 173
},
{
"epoch": 9.85,
"learning_rate": 0.00019075,
"loss": 1.6436,
"step": 174
},
{
"epoch": 9.91,
"learning_rate": 0.000190625,
"loss": 1.4587,
"step": 175
},
{
"epoch": 9.97,
"learning_rate": 0.00019050000000000002,
"loss": 1.7131,
"step": 176
},
{
"epoch": 10.02,
"learning_rate": 0.000190375,
"loss": 1.5204,
"step": 177
},
{
"epoch": 10.08,
"learning_rate": 0.00019025000000000002,
"loss": 1.2174,
"step": 178
},
{
"epoch": 10.14,
"learning_rate": 0.00019012500000000003,
"loss": 1.3831,
"step": 179
},
{
"epoch": 10.19,
"learning_rate": 0.00019,
"loss": 1.1915,
"step": 180
},
{
"epoch": 10.25,
"learning_rate": 0.000189875,
"loss": 1.4282,
"step": 181
},
{
"epoch": 10.31,
"learning_rate": 0.00018975,
"loss": 1.4675,
"step": 182
},
{
"epoch": 10.36,
"learning_rate": 0.00018962500000000001,
"loss": 1.4183,
"step": 183
},
{
"epoch": 10.42,
"learning_rate": 0.0001895,
"loss": 1.6309,
"step": 184
},
{
"epoch": 10.48,
"learning_rate": 0.000189375,
"loss": 1.4368,
"step": 185
},
{
"epoch": 10.53,
"learning_rate": 0.00018925000000000002,
"loss": 1.507,
"step": 186
},
{
"epoch": 10.59,
"learning_rate": 0.00018912500000000003,
"loss": 1.4642,
"step": 187
},
{
"epoch": 10.65,
"learning_rate": 0.00018899999999999999,
"loss": 1.5397,
"step": 188
},
{
"epoch": 10.7,
"learning_rate": 0.000188875,
"loss": 1.4003,
"step": 189
},
{
"epoch": 10.76,
"learning_rate": 0.00018875,
"loss": 1.5798,
"step": 190
},
{
"epoch": 10.82,
"learning_rate": 0.00018862500000000002,
"loss": 1.4797,
"step": 191
},
{
"epoch": 10.87,
"learning_rate": 0.0001885,
"loss": 1.429,
"step": 192
},
{
"epoch": 10.93,
"learning_rate": 0.000188375,
"loss": 1.49,
"step": 193
},
{
"epoch": 10.99,
"learning_rate": 0.00018825000000000002,
"loss": 1.5075,
"step": 194
},
{
"epoch": 11.04,
"learning_rate": 0.000188125,
"loss": 1.4662,
"step": 195
},
{
"epoch": 11.1,
"learning_rate": 0.000188,
"loss": 1.4103,
"step": 196
},
{
"epoch": 11.16,
"learning_rate": 0.000187875,
"loss": 1.4858,
"step": 197
},
{
"epoch": 11.21,
"learning_rate": 0.00018775,
"loss": 1.4841,
"step": 198
},
{
"epoch": 11.27,
"learning_rate": 0.000187625,
"loss": 1.4102,
"step": 199
},
{
"epoch": 11.33,
"learning_rate": 0.0001875,
"loss": 1.3401,
"step": 200
},
{
"epoch": 11.33,
"eval_loss": 2.023402452468872,
"eval_runtime": 59.5382,
"eval_samples_per_second": 4.216,
"eval_steps_per_second": 1.058,
"step": 200
},
{
"epoch": 11.38,
"learning_rate": 0.00018737500000000001,
"loss": 1.3293,
"step": 201
},
{
"epoch": 11.44,
"learning_rate": 0.00018725000000000002,
"loss": 1.5936,
"step": 202
},
{
"epoch": 11.5,
"learning_rate": 0.000187125,
"loss": 1.4509,
"step": 203
},
{
"epoch": 11.55,
"learning_rate": 0.00018700000000000002,
"loss": 1.4002,
"step": 204
},
{
"epoch": 11.61,
"learning_rate": 0.000186875,
"loss": 1.4654,
"step": 205
},
{
"epoch": 11.67,
"learning_rate": 0.00018675,
"loss": 1.456,
"step": 206
},
{
"epoch": 11.72,
"learning_rate": 0.000186625,
"loss": 1.5051,
"step": 207
},
{
"epoch": 11.78,
"learning_rate": 0.0001865,
"loss": 1.4447,
"step": 208
},
{
"epoch": 11.84,
"learning_rate": 0.00018637500000000002,
"loss": 1.4817,
"step": 209
},
{
"epoch": 11.89,
"learning_rate": 0.00018625,
"loss": 1.3649,
"step": 210
},
{
"epoch": 11.95,
"learning_rate": 0.000186125,
"loss": 1.4798,
"step": 211
},
{
"epoch": 12.01,
"learning_rate": 0.00018600000000000002,
"loss": 1.469,
"step": 212
},
{
"epoch": 12.06,
"learning_rate": 0.000185875,
"loss": 1.4963,
"step": 213
},
{
"epoch": 12.12,
"learning_rate": 0.00018575,
"loss": 1.377,
"step": 214
},
{
"epoch": 12.18,
"learning_rate": 0.000185625,
"loss": 1.6133,
"step": 215
},
{
"epoch": 12.23,
"learning_rate": 0.0001855,
"loss": 1.3288,
"step": 216
},
{
"epoch": 12.29,
"learning_rate": 0.00018537500000000002,
"loss": 1.514,
"step": 217
},
{
"epoch": 12.35,
"learning_rate": 0.00018525,
"loss": 1.4412,
"step": 218
},
{
"epoch": 12.4,
"learning_rate": 0.00018512500000000001,
"loss": 1.4004,
"step": 219
},
{
"epoch": 12.46,
"learning_rate": 0.00018500000000000002,
"loss": 1.359,
"step": 220
},
{
"epoch": 12.52,
"learning_rate": 0.000184875,
"loss": 1.3539,
"step": 221
},
{
"epoch": 12.57,
"learning_rate": 0.00018475,
"loss": 1.3255,
"step": 222
},
{
"epoch": 12.63,
"learning_rate": 0.000184625,
"loss": 1.4911,
"step": 223
},
{
"epoch": 12.69,
"learning_rate": 0.0001845,
"loss": 1.4146,
"step": 224
},
{
"epoch": 12.74,
"learning_rate": 0.000184375,
"loss": 1.3291,
"step": 225
},
{
"epoch": 12.8,
"learning_rate": 0.00018425,
"loss": 1.356,
"step": 226
},
{
"epoch": 12.86,
"learning_rate": 0.00018412500000000002,
"loss": 1.4216,
"step": 227
},
{
"epoch": 12.91,
"learning_rate": 0.00018400000000000003,
"loss": 1.4282,
"step": 228
},
{
"epoch": 12.97,
"learning_rate": 0.000183875,
"loss": 1.354,
"step": 229
},
{
"epoch": 13.03,
"learning_rate": 0.00018375,
"loss": 1.4358,
"step": 230
},
{
"epoch": 13.08,
"learning_rate": 0.000183625,
"loss": 1.5088,
"step": 231
},
{
"epoch": 13.14,
"learning_rate": 0.00018350000000000002,
"loss": 1.3588,
"step": 232
},
{
"epoch": 13.2,
"learning_rate": 0.000183375,
"loss": 1.3718,
"step": 233
},
{
"epoch": 13.25,
"learning_rate": 0.00018325,
"loss": 1.4119,
"step": 234
},
{
"epoch": 13.31,
"learning_rate": 0.00018312500000000002,
"loss": 1.2867,
"step": 235
},
{
"epoch": 13.37,
"learning_rate": 0.000183,
"loss": 1.2827,
"step": 236
},
{
"epoch": 13.42,
"learning_rate": 0.000182875,
"loss": 1.4267,
"step": 237
},
{
"epoch": 13.48,
"learning_rate": 0.00018275,
"loss": 1.3174,
"step": 238
},
{
"epoch": 13.54,
"learning_rate": 0.000182625,
"loss": 1.4199,
"step": 239
},
{
"epoch": 13.59,
"learning_rate": 0.0001825,
"loss": 1.4644,
"step": 240
},
{
"epoch": 13.65,
"learning_rate": 0.000182375,
"loss": 1.3819,
"step": 241
},
{
"epoch": 13.71,
"learning_rate": 0.00018225,
"loss": 1.3101,
"step": 242
},
{
"epoch": 13.76,
"learning_rate": 0.00018212500000000002,
"loss": 1.353,
"step": 243
},
{
"epoch": 13.82,
"learning_rate": 0.000182,
"loss": 1.3191,
"step": 244
},
{
"epoch": 13.88,
"learning_rate": 0.00018187500000000002,
"loss": 1.3851,
"step": 245
},
{
"epoch": 13.93,
"learning_rate": 0.00018175,
"loss": 1.3599,
"step": 246
},
{
"epoch": 13.99,
"learning_rate": 0.000181625,
"loss": 1.4739,
"step": 247
},
{
"epoch": 14.05,
"learning_rate": 0.0001815,
"loss": 1.3944,
"step": 248
},
{
"epoch": 14.1,
"learning_rate": 0.000181375,
"loss": 1.208,
"step": 249
},
{
"epoch": 14.16,
"learning_rate": 0.00018125000000000001,
"loss": 1.4049,
"step": 250
},
{
"epoch": 14.22,
"learning_rate": 0.000181125,
"loss": 1.2871,
"step": 251
},
{
"epoch": 14.27,
"learning_rate": 0.000181,
"loss": 1.4616,
"step": 252
},
{
"epoch": 14.33,
"learning_rate": 0.00018087500000000002,
"loss": 1.3318,
"step": 253
},
{
"epoch": 14.39,
"learning_rate": 0.00018075000000000003,
"loss": 1.328,
"step": 254
},
{
"epoch": 14.44,
"learning_rate": 0.000180625,
"loss": 1.2645,
"step": 255
},
{
"epoch": 14.5,
"learning_rate": 0.0001805,
"loss": 1.2477,
"step": 256
},
{
"epoch": 14.56,
"learning_rate": 0.000180375,
"loss": 1.4021,
"step": 257
},
{
"epoch": 14.61,
"learning_rate": 0.00018025000000000002,
"loss": 1.424,
"step": 258
},
{
"epoch": 14.67,
"learning_rate": 0.000180125,
"loss": 1.3124,
"step": 259
},
{
"epoch": 14.73,
"learning_rate": 0.00018,
"loss": 1.3239,
"step": 260
},
{
"epoch": 14.78,
"learning_rate": 0.00017987500000000002,
"loss": 1.3568,
"step": 261
},
{
"epoch": 14.84,
"learning_rate": 0.00017975,
"loss": 1.1723,
"step": 262
},
{
"epoch": 14.9,
"learning_rate": 0.000179625,
"loss": 1.3399,
"step": 263
},
{
"epoch": 14.95,
"learning_rate": 0.0001795,
"loss": 1.3437,
"step": 264
},
{
"epoch": 15.01,
"learning_rate": 0.000179375,
"loss": 1.3229,
"step": 265
},
{
"epoch": 15.07,
"learning_rate": 0.00017925000000000002,
"loss": 1.2831,
"step": 266
},
{
"epoch": 15.12,
"learning_rate": 0.000179125,
"loss": 1.1986,
"step": 267
},
{
"epoch": 15.18,
"learning_rate": 0.00017900000000000001,
"loss": 1.236,
"step": 268
},
{
"epoch": 15.24,
"learning_rate": 0.00017887500000000002,
"loss": 1.3338,
"step": 269
},
{
"epoch": 15.29,
"learning_rate": 0.00017875,
"loss": 1.2406,
"step": 270
},
{
"epoch": 15.35,
"learning_rate": 0.000178625,
"loss": 1.1528,
"step": 271
},
{
"epoch": 15.41,
"learning_rate": 0.0001785,
"loss": 1.3401,
"step": 272
},
{
"epoch": 15.46,
"learning_rate": 0.000178375,
"loss": 1.3493,
"step": 273
},
{
"epoch": 15.52,
"learning_rate": 0.00017825,
"loss": 1.2721,
"step": 274
},
{
"epoch": 15.58,
"learning_rate": 0.000178125,
"loss": 1.3501,
"step": 275
},
{
"epoch": 15.63,
"learning_rate": 0.00017800000000000002,
"loss": 1.3662,
"step": 276
},
{
"epoch": 15.69,
"learning_rate": 0.000177875,
"loss": 1.2117,
"step": 277
},
{
"epoch": 15.75,
"learning_rate": 0.00017775,
"loss": 1.3798,
"step": 278
},
{
"epoch": 15.8,
"learning_rate": 0.00017762500000000002,
"loss": 1.3108,
"step": 279
},
{
"epoch": 15.86,
"learning_rate": 0.0001775,
"loss": 1.3565,
"step": 280
},
{
"epoch": 15.92,
"learning_rate": 0.00017737500000000002,
"loss": 1.3961,
"step": 281
},
{
"epoch": 15.97,
"learning_rate": 0.00017725,
"loss": 1.216,
"step": 282
},
{
"epoch": 16.03,
"learning_rate": 0.000177125,
"loss": 1.3027,
"step": 283
},
{
"epoch": 16.08,
"learning_rate": 0.00017700000000000002,
"loss": 1.1798,
"step": 284
},
{
"epoch": 16.14,
"learning_rate": 0.000176875,
"loss": 1.2375,
"step": 285
},
{
"epoch": 16.2,
"learning_rate": 0.00017675000000000001,
"loss": 1.2179,
"step": 286
},
{
"epoch": 16.25,
"learning_rate": 0.00017662500000000002,
"loss": 1.1218,
"step": 287
},
{
"epoch": 16.31,
"learning_rate": 0.0001765,
"loss": 1.2144,
"step": 288
},
{
"epoch": 16.37,
"learning_rate": 0.000176375,
"loss": 1.1878,
"step": 289
},
{
"epoch": 16.42,
"learning_rate": 0.00017625,
"loss": 1.2809,
"step": 290
},
{
"epoch": 16.48,
"learning_rate": 0.000176125,
"loss": 1.1862,
"step": 291
},
{
"epoch": 16.54,
"learning_rate": 0.00017600000000000002,
"loss": 1.2139,
"step": 292
},
{
"epoch": 16.59,
"learning_rate": 0.000175875,
"loss": 1.2991,
"step": 293
},
{
"epoch": 16.65,
"learning_rate": 0.00017575000000000002,
"loss": 1.3304,
"step": 294
},
{
"epoch": 16.71,
"learning_rate": 0.00017562500000000003,
"loss": 1.4349,
"step": 295
},
{
"epoch": 16.76,
"learning_rate": 0.0001755,
"loss": 1.2817,
"step": 296
},
{
"epoch": 16.82,
"learning_rate": 0.000175375,
"loss": 1.2263,
"step": 297
},
{
"epoch": 16.88,
"learning_rate": 0.00017525,
"loss": 1.3584,
"step": 298
},
{
"epoch": 16.93,
"learning_rate": 0.00017512500000000001,
"loss": 1.4542,
"step": 299
},
{
"epoch": 16.99,
"learning_rate": 0.000175,
"loss": 1.392,
"step": 300
},
{
"epoch": 17.05,
"learning_rate": 0.000174875,
"loss": 1.2685,
"step": 301
},
{
"epoch": 17.1,
"learning_rate": 0.00017475000000000002,
"loss": 1.2337,
"step": 302
},
{
"epoch": 17.16,
"learning_rate": 0.00017462500000000003,
"loss": 1.3299,
"step": 303
},
{
"epoch": 17.22,
"learning_rate": 0.0001745,
"loss": 1.2579,
"step": 304
},
{
"epoch": 17.27,
"learning_rate": 0.000174375,
"loss": 1.234,
"step": 305
},
{
"epoch": 17.33,
"learning_rate": 0.00017425,
"loss": 1.2273,
"step": 306
},
{
"epoch": 17.39,
"learning_rate": 0.00017412500000000002,
"loss": 1.3174,
"step": 307
},
{
"epoch": 17.44,
"learning_rate": 0.000174,
"loss": 1.1738,
"step": 308
},
{
"epoch": 17.5,
"learning_rate": 0.000173875,
"loss": 1.0985,
"step": 309
},
{
"epoch": 17.56,
"learning_rate": 0.00017375000000000002,
"loss": 1.283,
"step": 310
},
{
"epoch": 17.61,
"learning_rate": 0.000173625,
"loss": 1.318,
"step": 311
},
{
"epoch": 17.67,
"learning_rate": 0.00017350000000000002,
"loss": 1.3006,
"step": 312
},
{
"epoch": 17.73,
"learning_rate": 0.000173375,
"loss": 1.3629,
"step": 313
},
{
"epoch": 17.78,
"learning_rate": 0.00017325,
"loss": 1.3144,
"step": 314
},
{
"epoch": 17.84,
"learning_rate": 0.000173125,
"loss": 1.3476,
"step": 315
},
{
"epoch": 17.9,
"learning_rate": 0.000173,
"loss": 1.1403,
"step": 316
},
{
"epoch": 17.95,
"learning_rate": 0.00017287500000000001,
"loss": 1.1434,
"step": 317
},
{
"epoch": 18.01,
"learning_rate": 0.00017275000000000002,
"loss": 1.1653,
"step": 318
},
{
"epoch": 18.07,
"learning_rate": 0.000172625,
"loss": 1.1411,
"step": 319
},
{
"epoch": 18.12,
"learning_rate": 0.00017250000000000002,
"loss": 1.2393,
"step": 320
},
{
"epoch": 18.18,
"learning_rate": 0.000172375,
"loss": 1.2092,
"step": 321
},
{
"epoch": 18.24,
"learning_rate": 0.00017225,
"loss": 1.1437,
"step": 322
},
{
"epoch": 18.29,
"learning_rate": 0.000172125,
"loss": 1.1145,
"step": 323
},
{
"epoch": 18.35,
"learning_rate": 0.000172,
"loss": 1.2723,
"step": 324
},
{
"epoch": 18.41,
"learning_rate": 0.00017187500000000002,
"loss": 1.2471,
"step": 325
},
{
"epoch": 18.46,
"learning_rate": 0.00017175,
"loss": 1.1047,
"step": 326
},
{
"epoch": 18.52,
"learning_rate": 0.000171625,
"loss": 1.0908,
"step": 327
},
{
"epoch": 18.58,
"learning_rate": 0.00017150000000000002,
"loss": 1.3261,
"step": 328
},
{
"epoch": 18.63,
"learning_rate": 0.00017137500000000003,
"loss": 1.2138,
"step": 329
},
{
"epoch": 18.69,
"learning_rate": 0.00017125,
"loss": 1.253,
"step": 330
},
{
"epoch": 18.75,
"learning_rate": 0.000171125,
"loss": 1.2831,
"step": 331
},
{
"epoch": 18.8,
"learning_rate": 0.000171,
"loss": 1.1795,
"step": 332
},
{
"epoch": 18.86,
"learning_rate": 0.00017087500000000002,
"loss": 1.2454,
"step": 333
},
{
"epoch": 18.92,
"learning_rate": 0.00017075,
"loss": 1.2997,
"step": 334
},
{
"epoch": 18.97,
"learning_rate": 0.00017062500000000001,
"loss": 1.2243,
"step": 335
},
{
"epoch": 19.03,
"learning_rate": 0.00017050000000000002,
"loss": 1.1705,
"step": 336
},
{
"epoch": 19.09,
"learning_rate": 0.000170375,
"loss": 1.133,
"step": 337
},
{
"epoch": 19.14,
"learning_rate": 0.00017025,
"loss": 1.1997,
"step": 338
},
{
"epoch": 19.2,
"learning_rate": 0.000170125,
"loss": 1.1572,
"step": 339
},
{
"epoch": 19.26,
"learning_rate": 0.00017,
"loss": 1.2115,
"step": 340
},
{
"epoch": 19.31,
"learning_rate": 0.000169875,
"loss": 1.0557,
"step": 341
},
{
"epoch": 19.37,
"learning_rate": 0.00016975,
"loss": 1.2455,
"step": 342
},
{
"epoch": 19.43,
"learning_rate": 0.00016962500000000002,
"loss": 1.1917,
"step": 343
},
{
"epoch": 19.48,
"learning_rate": 0.00016950000000000003,
"loss": 1.2846,
"step": 344
},
{
"epoch": 19.54,
"learning_rate": 0.000169375,
"loss": 1.2735,
"step": 345
},
{
"epoch": 19.6,
"learning_rate": 0.00016925,
"loss": 1.1168,
"step": 346
},
{
"epoch": 19.65,
"learning_rate": 0.000169125,
"loss": 1.2314,
"step": 347
},
{
"epoch": 19.71,
"learning_rate": 0.00016900000000000002,
"loss": 1.1641,
"step": 348
},
{
"epoch": 19.77,
"learning_rate": 0.000168875,
"loss": 1.2631,
"step": 349
},
{
"epoch": 19.82,
"learning_rate": 0.00016875,
"loss": 1.0431,
"step": 350
},
{
"epoch": 19.88,
"learning_rate": 0.00016862500000000002,
"loss": 1.0931,
"step": 351
},
{
"epoch": 19.94,
"learning_rate": 0.0001685,
"loss": 1.2183,
"step": 352
},
{
"epoch": 19.99,
"learning_rate": 0.000168375,
"loss": 1.0584,
"step": 353
},
{
"epoch": 20.05,
"learning_rate": 0.00016825000000000002,
"loss": 1.1146,
"step": 354
},
{
"epoch": 20.11,
"learning_rate": 0.000168125,
"loss": 1.0702,
"step": 355
},
{
"epoch": 20.16,
"learning_rate": 0.000168,
"loss": 1.0612,
"step": 356
},
{
"epoch": 20.22,
"learning_rate": 0.000167875,
"loss": 1.2609,
"step": 357
},
{
"epoch": 20.28,
"learning_rate": 0.00016775,
"loss": 0.9842,
"step": 358
},
{
"epoch": 20.33,
"learning_rate": 0.00016762500000000002,
"loss": 1.0986,
"step": 359
},
{
"epoch": 20.39,
"learning_rate": 0.0001675,
"loss": 1.2615,
"step": 360
},
{
"epoch": 20.45,
"learning_rate": 0.00016737500000000002,
"loss": 1.187,
"step": 361
},
{
"epoch": 20.5,
"learning_rate": 0.00016725000000000003,
"loss": 1.1115,
"step": 362
},
{
"epoch": 20.56,
"learning_rate": 0.000167125,
"loss": 1.1215,
"step": 363
},
{
"epoch": 20.62,
"learning_rate": 0.000167,
"loss": 1.0814,
"step": 364
},
{
"epoch": 20.67,
"learning_rate": 0.000166875,
"loss": 1.2158,
"step": 365
},
{
"epoch": 20.73,
"learning_rate": 0.00016675000000000001,
"loss": 1.1993,
"step": 366
},
{
"epoch": 20.79,
"learning_rate": 0.000166625,
"loss": 1.2018,
"step": 367
},
{
"epoch": 20.84,
"learning_rate": 0.0001665,
"loss": 1.1376,
"step": 368
},
{
"epoch": 20.9,
"learning_rate": 0.00016637500000000002,
"loss": 1.1453,
"step": 369
},
{
"epoch": 20.96,
"learning_rate": 0.00016625000000000003,
"loss": 1.2199,
"step": 370
},
{
"epoch": 21.01,
"learning_rate": 0.00016612499999999999,
"loss": 1.2592,
"step": 371
},
{
"epoch": 21.07,
"learning_rate": 0.000166,
"loss": 1.1196,
"step": 372
},
{
"epoch": 21.13,
"learning_rate": 0.000165875,
"loss": 1.2162,
"step": 373
},
{
"epoch": 21.18,
"learning_rate": 0.00016575000000000002,
"loss": 1.2218,
"step": 374
},
{
"epoch": 21.24,
"learning_rate": 0.000165625,
"loss": 1.2069,
"step": 375
},
{
"epoch": 21.3,
"learning_rate": 0.0001655,
"loss": 1.0723,
"step": 376
},
{
"epoch": 21.35,
"learning_rate": 0.00016537500000000002,
"loss": 1.0855,
"step": 377
},
{
"epoch": 21.41,
"learning_rate": 0.00016525,
"loss": 1.0705,
"step": 378
},
{
"epoch": 21.47,
"learning_rate": 0.00016512500000000002,
"loss": 1.1985,
"step": 379
},
{
"epoch": 21.52,
"learning_rate": 0.000165,
"loss": 1.1375,
"step": 380
},
{
"epoch": 21.58,
"learning_rate": 0.000164875,
"loss": 1.0706,
"step": 381
},
{
"epoch": 21.64,
"learning_rate": 0.00016475,
"loss": 1.1144,
"step": 382
},
{
"epoch": 21.69,
"learning_rate": 0.000164625,
"loss": 1.1604,
"step": 383
},
{
"epoch": 21.75,
"learning_rate": 0.00016450000000000001,
"loss": 1.0285,
"step": 384
},
{
"epoch": 21.81,
"learning_rate": 0.00016437500000000002,
"loss": 1.2177,
"step": 385
},
{
"epoch": 21.86,
"learning_rate": 0.00016425,
"loss": 1.1429,
"step": 386
},
{
"epoch": 21.92,
"learning_rate": 0.00016412500000000002,
"loss": 1.067,
"step": 387
},
{
"epoch": 21.98,
"learning_rate": 0.000164,
"loss": 1.1697,
"step": 388
},
{
"epoch": 22.03,
"learning_rate": 0.000163875,
"loss": 1.0991,
"step": 389
},
{
"epoch": 22.09,
"learning_rate": 0.00016375,
"loss": 1.0132,
"step": 390
},
{
"epoch": 22.15,
"learning_rate": 0.000163625,
"loss": 1.0528,
"step": 391
},
{
"epoch": 22.2,
"learning_rate": 0.00016350000000000002,
"loss": 1.1334,
"step": 392
},
{
"epoch": 22.26,
"learning_rate": 0.000163375,
"loss": 1.0935,
"step": 393
},
{
"epoch": 22.32,
"learning_rate": 0.00016325,
"loss": 0.9794,
"step": 394
},
{
"epoch": 22.37,
"learning_rate": 0.00016312500000000002,
"loss": 1.1197,
"step": 395
},
{
"epoch": 22.43,
"learning_rate": 0.000163,
"loss": 1.0824,
"step": 396
},
{
"epoch": 22.48,
"learning_rate": 0.000162875,
"loss": 1.1128,
"step": 397
},
{
"epoch": 22.54,
"learning_rate": 0.00016275,
"loss": 1.1092,
"step": 398
},
{
"epoch": 22.6,
"learning_rate": 0.000162625,
"loss": 1.1914,
"step": 399
},
{
"epoch": 22.65,
"learning_rate": 0.00016250000000000002,
"loss": 1.1871,
"step": 400
},
{
"epoch": 22.65,
"eval_loss": 2.3080484867095947,
"eval_runtime": 67.9996,
"eval_samples_per_second": 3.691,
"eval_steps_per_second": 0.926,
"step": 400
},
{
"epoch": 22.71,
"learning_rate": 0.000162375,
"loss": 1.1742,
"step": 401
},
{
"epoch": 22.77,
"learning_rate": 0.00016225000000000001,
"loss": 1.3617,
"step": 402
},
{
"epoch": 22.82,
"learning_rate": 0.00016212500000000002,
"loss": 1.0186,
"step": 403
},
{
"epoch": 22.88,
"learning_rate": 0.000162,
"loss": 1.1819,
"step": 404
},
{
"epoch": 22.94,
"learning_rate": 0.000161875,
"loss": 1.0858,
"step": 405
},
{
"epoch": 22.99,
"learning_rate": 0.00016175,
"loss": 1.084,
"step": 406
},
{
"epoch": 23.05,
"learning_rate": 0.000161625,
"loss": 1.0896,
"step": 407
},
{
"epoch": 23.11,
"learning_rate": 0.0001615,
"loss": 0.9239,
"step": 408
},
{
"epoch": 23.16,
"learning_rate": 0.000161375,
"loss": 1.16,
"step": 409
},
{
"epoch": 23.22,
"learning_rate": 0.00016125000000000002,
"loss": 1.0874,
"step": 410
},
{
"epoch": 23.28,
"learning_rate": 0.00016112500000000003,
"loss": 1.0956,
"step": 411
},
{
"epoch": 23.33,
"learning_rate": 0.000161,
"loss": 1.1366,
"step": 412
},
{
"epoch": 23.39,
"learning_rate": 0.000160875,
"loss": 1.1507,
"step": 413
},
{
"epoch": 23.45,
"learning_rate": 0.00016075,
"loss": 1.0451,
"step": 414
},
{
"epoch": 23.5,
"learning_rate": 0.00016062500000000001,
"loss": 1.1593,
"step": 415
},
{
"epoch": 23.56,
"learning_rate": 0.0001605,
"loss": 1.0692,
"step": 416
},
{
"epoch": 23.62,
"learning_rate": 0.000160375,
"loss": 1.0252,
"step": 417
},
{
"epoch": 23.67,
"learning_rate": 0.00016025000000000002,
"loss": 1.0877,
"step": 418
},
{
"epoch": 23.73,
"learning_rate": 0.000160125,
"loss": 1.2211,
"step": 419
},
{
"epoch": 23.79,
"learning_rate": 0.00016,
"loss": 1.1834,
"step": 420
},
{
"epoch": 23.84,
"learning_rate": 0.000159875,
"loss": 1.0965,
"step": 421
},
{
"epoch": 23.9,
"learning_rate": 0.00015975,
"loss": 1.0839,
"step": 422
},
{
"epoch": 23.96,
"learning_rate": 0.000159625,
"loss": 1.0622,
"step": 423
},
{
"epoch": 24.01,
"learning_rate": 0.0001595,
"loss": 1.1252,
"step": 424
},
{
"epoch": 24.07,
"learning_rate": 0.000159375,
"loss": 1.1057,
"step": 425
},
{
"epoch": 24.13,
"learning_rate": 0.00015925000000000002,
"loss": 1.0499,
"step": 426
},
{
"epoch": 24.18,
"learning_rate": 0.000159125,
"loss": 1.2239,
"step": 427
},
{
"epoch": 24.24,
"learning_rate": 0.00015900000000000002,
"loss": 1.0456,
"step": 428
},
{
"epoch": 24.3,
"learning_rate": 0.00015887500000000003,
"loss": 1.1966,
"step": 429
},
{
"epoch": 24.35,
"learning_rate": 0.00015875,
"loss": 1.0116,
"step": 430
},
{
"epoch": 24.41,
"learning_rate": 0.000158625,
"loss": 1.0544,
"step": 431
},
{
"epoch": 24.47,
"learning_rate": 0.0001585,
"loss": 0.9815,
"step": 432
},
{
"epoch": 24.52,
"learning_rate": 0.00015837500000000001,
"loss": 1.0492,
"step": 433
},
{
"epoch": 24.58,
"learning_rate": 0.00015825,
"loss": 1.067,
"step": 434
},
{
"epoch": 24.64,
"learning_rate": 0.000158125,
"loss": 1.0854,
"step": 435
},
{
"epoch": 24.69,
"learning_rate": 0.00015800000000000002,
"loss": 1.1032,
"step": 436
},
{
"epoch": 24.75,
"learning_rate": 0.00015787500000000003,
"loss": 1.0008,
"step": 437
},
{
"epoch": 24.81,
"learning_rate": 0.00015774999999999999,
"loss": 1.0489,
"step": 438
},
{
"epoch": 24.86,
"learning_rate": 0.000157625,
"loss": 1.0176,
"step": 439
},
{
"epoch": 24.92,
"learning_rate": 0.0001575,
"loss": 0.9086,
"step": 440
},
{
"epoch": 24.98,
"learning_rate": 0.00015737500000000002,
"loss": 1.105,
"step": 441
},
{
"epoch": 25.03,
"learning_rate": 0.00015725,
"loss": 1.163,
"step": 442
},
{
"epoch": 25.09,
"learning_rate": 0.000157125,
"loss": 1.0763,
"step": 443
},
{
"epoch": 25.15,
"learning_rate": 0.00015700000000000002,
"loss": 0.9489,
"step": 444
},
{
"epoch": 25.2,
"learning_rate": 0.000156875,
"loss": 1.0961,
"step": 445
},
{
"epoch": 25.26,
"learning_rate": 0.00015675,
"loss": 1.1935,
"step": 446
},
{
"epoch": 25.32,
"learning_rate": 0.000156625,
"loss": 1.0047,
"step": 447
},
{
"epoch": 25.37,
"learning_rate": 0.0001565,
"loss": 1.0807,
"step": 448
},
{
"epoch": 25.43,
"learning_rate": 0.000156375,
"loss": 1.0766,
"step": 449
},
{
"epoch": 25.49,
"learning_rate": 0.00015625,
"loss": 0.9833,
"step": 450
},
{
"epoch": 25.54,
"learning_rate": 0.00015612500000000001,
"loss": 1.032,
"step": 451
},
{
"epoch": 25.6,
"learning_rate": 0.00015600000000000002,
"loss": 1.0264,
"step": 452
},
{
"epoch": 25.66,
"learning_rate": 0.000155875,
"loss": 1.1064,
"step": 453
},
{
"epoch": 25.71,
"learning_rate": 0.00015575000000000002,
"loss": 0.9957,
"step": 454
},
{
"epoch": 25.77,
"learning_rate": 0.000155625,
"loss": 1.1988,
"step": 455
},
{
"epoch": 25.83,
"learning_rate": 0.0001555,
"loss": 1.0918,
"step": 456
},
{
"epoch": 25.88,
"learning_rate": 0.000155375,
"loss": 1.0202,
"step": 457
},
{
"epoch": 25.94,
"learning_rate": 0.00015525,
"loss": 1.0904,
"step": 458
},
{
"epoch": 26.0,
"learning_rate": 0.00015512500000000002,
"loss": 1.0169,
"step": 459
},
{
"epoch": 26.05,
"learning_rate": 0.000155,
"loss": 1.0173,
"step": 460
},
{
"epoch": 26.11,
"learning_rate": 0.000154875,
"loss": 1.1198,
"step": 461
},
{
"epoch": 26.17,
"learning_rate": 0.00015475000000000002,
"loss": 1.1392,
"step": 462
},
{
"epoch": 26.22,
"learning_rate": 0.000154625,
"loss": 1.014,
"step": 463
},
{
"epoch": 26.28,
"learning_rate": 0.0001545,
"loss": 0.9519,
"step": 464
},
{
"epoch": 26.34,
"learning_rate": 0.000154375,
"loss": 0.9909,
"step": 465
},
{
"epoch": 26.39,
"learning_rate": 0.00015425,
"loss": 0.9521,
"step": 466
},
{
"epoch": 26.45,
"learning_rate": 0.00015412500000000002,
"loss": 1.1342,
"step": 467
},
{
"epoch": 26.51,
"learning_rate": 0.000154,
"loss": 1.0784,
"step": 468
},
{
"epoch": 26.56,
"learning_rate": 0.000153875,
"loss": 1.0328,
"step": 469
},
{
"epoch": 26.62,
"learning_rate": 0.00015375000000000002,
"loss": 1.0087,
"step": 470
},
{
"epoch": 26.68,
"learning_rate": 0.000153625,
"loss": 1.0398,
"step": 471
},
{
"epoch": 26.73,
"learning_rate": 0.0001535,
"loss": 0.9858,
"step": 472
},
{
"epoch": 26.79,
"learning_rate": 0.000153375,
"loss": 1.2076,
"step": 473
},
{
"epoch": 26.85,
"learning_rate": 0.00015325,
"loss": 1.1085,
"step": 474
},
{
"epoch": 26.9,
"learning_rate": 0.000153125,
"loss": 1.1035,
"step": 475
},
{
"epoch": 26.96,
"learning_rate": 0.000153,
"loss": 0.9399,
"step": 476
},
{
"epoch": 27.02,
"learning_rate": 0.00015287500000000002,
"loss": 1.0872,
"step": 477
},
{
"epoch": 27.07,
"learning_rate": 0.00015275000000000003,
"loss": 1.0331,
"step": 478
},
{
"epoch": 27.13,
"learning_rate": 0.000152625,
"loss": 0.9109,
"step": 479
},
{
"epoch": 27.19,
"learning_rate": 0.0001525,
"loss": 0.9697,
"step": 480
},
{
"epoch": 27.24,
"learning_rate": 0.000152375,
"loss": 1.0549,
"step": 481
},
{
"epoch": 27.3,
"learning_rate": 0.00015225000000000001,
"loss": 0.998,
"step": 482
},
{
"epoch": 27.36,
"learning_rate": 0.000152125,
"loss": 1.0075,
"step": 483
},
{
"epoch": 27.41,
"learning_rate": 0.000152,
"loss": 1.0581,
"step": 484
},
{
"epoch": 27.47,
"learning_rate": 0.00015187500000000002,
"loss": 1.0142,
"step": 485
},
{
"epoch": 27.53,
"learning_rate": 0.00015175,
"loss": 0.9666,
"step": 486
},
{
"epoch": 27.58,
"learning_rate": 0.000151625,
"loss": 1.0657,
"step": 487
},
{
"epoch": 27.64,
"learning_rate": 0.0001515,
"loss": 1.0518,
"step": 488
},
{
"epoch": 27.7,
"learning_rate": 0.000151375,
"loss": 1.0108,
"step": 489
},
{
"epoch": 27.75,
"learning_rate": 0.00015125,
"loss": 1.0609,
"step": 490
},
{
"epoch": 27.81,
"learning_rate": 0.000151125,
"loss": 0.9527,
"step": 491
},
{
"epoch": 27.87,
"learning_rate": 0.000151,
"loss": 1.0935,
"step": 492
},
{
"epoch": 27.92,
"learning_rate": 0.00015087500000000002,
"loss": 1.0846,
"step": 493
},
{
"epoch": 27.98,
"learning_rate": 0.00015075,
"loss": 1.155,
"step": 494
},
{
"epoch": 28.04,
"learning_rate": 0.00015062500000000002,
"loss": 1.0016,
"step": 495
},
{
"epoch": 28.09,
"learning_rate": 0.0001505,
"loss": 0.9649,
"step": 496
},
{
"epoch": 28.15,
"learning_rate": 0.000150375,
"loss": 0.8216,
"step": 497
},
{
"epoch": 28.21,
"learning_rate": 0.00015025,
"loss": 0.8122,
"step": 498
},
{
"epoch": 28.26,
"learning_rate": 0.000150125,
"loss": 0.9406,
"step": 499
},
{
"epoch": 28.32,
"learning_rate": 0.00015000000000000001,
"loss": 0.9773,
"step": 500
},
{
"epoch": 28.38,
"learning_rate": 0.000149875,
"loss": 1.0644,
"step": 501
},
{
"epoch": 28.43,
"learning_rate": 0.00014975,
"loss": 0.94,
"step": 502
},
{
"epoch": 28.49,
"learning_rate": 0.00014962500000000002,
"loss": 0.9985,
"step": 503
},
{
"epoch": 28.55,
"learning_rate": 0.00014950000000000003,
"loss": 0.9291,
"step": 504
},
{
"epoch": 28.6,
"learning_rate": 0.00014937499999999999,
"loss": 1.105,
"step": 505
},
{
"epoch": 28.66,
"learning_rate": 0.00014925,
"loss": 1.0298,
"step": 506
},
{
"epoch": 28.72,
"learning_rate": 0.000149125,
"loss": 0.8352,
"step": 507
},
{
"epoch": 28.77,
"learning_rate": 0.00014900000000000002,
"loss": 0.9752,
"step": 508
},
{
"epoch": 28.83,
"learning_rate": 0.000148875,
"loss": 1.0227,
"step": 509
},
{
"epoch": 28.88,
"learning_rate": 0.00014875,
"loss": 1.0159,
"step": 510
},
{
"epoch": 28.94,
"learning_rate": 0.00014862500000000002,
"loss": 0.9519,
"step": 511
},
{
"epoch": 29.0,
"learning_rate": 0.0001485,
"loss": 1.0509,
"step": 512
},
{
"epoch": 29.05,
"learning_rate": 0.000148375,
"loss": 0.9518,
"step": 513
},
{
"epoch": 29.11,
"learning_rate": 0.00014825,
"loss": 0.916,
"step": 514
},
{
"epoch": 29.17,
"learning_rate": 0.000148125,
"loss": 0.9861,
"step": 515
},
{
"epoch": 29.22,
"learning_rate": 0.000148,
"loss": 0.8708,
"step": 516
},
{
"epoch": 29.28,
"learning_rate": 0.000147875,
"loss": 0.9761,
"step": 517
},
{
"epoch": 29.34,
"learning_rate": 0.00014775,
"loss": 0.9873,
"step": 518
},
{
"epoch": 29.39,
"learning_rate": 0.00014762500000000002,
"loss": 0.9831,
"step": 519
},
{
"epoch": 29.45,
"learning_rate": 0.0001475,
"loss": 0.9699,
"step": 520
},
{
"epoch": 29.51,
"learning_rate": 0.000147375,
"loss": 1.0476,
"step": 521
},
{
"epoch": 29.56,
"learning_rate": 0.00014725,
"loss": 0.9194,
"step": 522
},
{
"epoch": 29.62,
"learning_rate": 0.000147125,
"loss": 0.8511,
"step": 523
},
{
"epoch": 29.68,
"learning_rate": 0.000147,
"loss": 0.9279,
"step": 524
},
{
"epoch": 29.73,
"learning_rate": 0.000146875,
"loss": 0.9263,
"step": 525
},
{
"epoch": 29.79,
"learning_rate": 0.00014675000000000002,
"loss": 1.0193,
"step": 526
},
{
"epoch": 29.85,
"learning_rate": 0.000146625,
"loss": 0.855,
"step": 527
},
{
"epoch": 29.9,
"learning_rate": 0.0001465,
"loss": 1.0262,
"step": 528
},
{
"epoch": 29.96,
"learning_rate": 0.00014637500000000002,
"loss": 0.9289,
"step": 529
},
{
"epoch": 30.02,
"learning_rate": 0.00014625,
"loss": 0.9726,
"step": 530
},
{
"epoch": 30.07,
"learning_rate": 0.000146125,
"loss": 0.9372,
"step": 531
},
{
"epoch": 30.13,
"learning_rate": 0.000146,
"loss": 0.9264,
"step": 532
},
{
"epoch": 30.19,
"learning_rate": 0.000145875,
"loss": 1.082,
"step": 533
},
{
"epoch": 30.24,
"learning_rate": 0.00014575000000000002,
"loss": 0.8726,
"step": 534
},
{
"epoch": 30.3,
"learning_rate": 0.000145625,
"loss": 0.946,
"step": 535
},
{
"epoch": 30.36,
"learning_rate": 0.0001455,
"loss": 0.9745,
"step": 536
},
{
"epoch": 30.41,
"learning_rate": 0.00014537500000000002,
"loss": 0.9029,
"step": 537
},
{
"epoch": 30.47,
"learning_rate": 0.00014525,
"loss": 0.9419,
"step": 538
},
{
"epoch": 30.53,
"learning_rate": 0.000145125,
"loss": 0.9483,
"step": 539
},
{
"epoch": 30.58,
"learning_rate": 0.000145,
"loss": 0.931,
"step": 540
},
{
"epoch": 30.64,
"learning_rate": 0.000144875,
"loss": 0.8506,
"step": 541
},
{
"epoch": 30.7,
"learning_rate": 0.00014475,
"loss": 0.9794,
"step": 542
},
{
"epoch": 30.75,
"learning_rate": 0.000144625,
"loss": 0.9518,
"step": 543
},
{
"epoch": 30.81,
"learning_rate": 0.00014450000000000002,
"loss": 1.0354,
"step": 544
},
{
"epoch": 30.87,
"learning_rate": 0.00014437500000000003,
"loss": 0.942,
"step": 545
},
{
"epoch": 30.92,
"learning_rate": 0.00014425,
"loss": 1.0193,
"step": 546
},
{
"epoch": 30.98,
"learning_rate": 0.000144125,
"loss": 1.0498,
"step": 547
},
{
"epoch": 31.04,
"learning_rate": 0.000144,
"loss": 0.8734,
"step": 548
},
{
"epoch": 31.09,
"learning_rate": 0.00014387500000000001,
"loss": 0.8525,
"step": 549
},
{
"epoch": 31.15,
"learning_rate": 0.00014375,
"loss": 0.8724,
"step": 550
},
{
"epoch": 31.21,
"learning_rate": 0.000143625,
"loss": 0.8856,
"step": 551
},
{
"epoch": 31.26,
"learning_rate": 0.00014350000000000002,
"loss": 0.9098,
"step": 552
},
{
"epoch": 31.32,
"learning_rate": 0.000143375,
"loss": 0.8638,
"step": 553
},
{
"epoch": 31.38,
"learning_rate": 0.00014325,
"loss": 0.869,
"step": 554
},
{
"epoch": 31.43,
"learning_rate": 0.000143125,
"loss": 0.9197,
"step": 555
},
{
"epoch": 31.49,
"learning_rate": 0.000143,
"loss": 0.9562,
"step": 556
},
{
"epoch": 31.55,
"learning_rate": 0.000142875,
"loss": 0.9259,
"step": 557
},
{
"epoch": 31.6,
"learning_rate": 0.00014275,
"loss": 0.9913,
"step": 558
},
{
"epoch": 31.66,
"learning_rate": 0.000142625,
"loss": 0.8817,
"step": 559
},
{
"epoch": 31.72,
"learning_rate": 0.00014250000000000002,
"loss": 0.9828,
"step": 560
},
{
"epoch": 31.77,
"learning_rate": 0.000142375,
"loss": 1.019,
"step": 561
},
{
"epoch": 31.83,
"learning_rate": 0.00014225000000000002,
"loss": 1.0316,
"step": 562
},
{
"epoch": 31.89,
"learning_rate": 0.000142125,
"loss": 0.8991,
"step": 563
},
{
"epoch": 31.94,
"learning_rate": 0.000142,
"loss": 0.9081,
"step": 564
},
{
"epoch": 32.0,
"learning_rate": 0.000141875,
"loss": 0.9126,
"step": 565
},
{
"epoch": 32.06,
"learning_rate": 0.00014175,
"loss": 0.8007,
"step": 566
},
{
"epoch": 32.11,
"learning_rate": 0.00014162500000000001,
"loss": 0.9289,
"step": 567
},
{
"epoch": 32.17,
"learning_rate": 0.0001415,
"loss": 1.001,
"step": 568
},
{
"epoch": 32.23,
"learning_rate": 0.000141375,
"loss": 0.896,
"step": 569
},
{
"epoch": 32.28,
"learning_rate": 0.00014125000000000002,
"loss": 0.9181,
"step": 570
},
{
"epoch": 32.34,
"learning_rate": 0.000141125,
"loss": 0.9645,
"step": 571
},
{
"epoch": 32.4,
"learning_rate": 0.000141,
"loss": 0.8713,
"step": 572
},
{
"epoch": 32.45,
"learning_rate": 0.000140875,
"loss": 0.8495,
"step": 573
},
{
"epoch": 32.51,
"learning_rate": 0.00014075,
"loss": 0.8962,
"step": 574
},
{
"epoch": 32.57,
"learning_rate": 0.00014062500000000002,
"loss": 0.8542,
"step": 575
},
{
"epoch": 32.62,
"learning_rate": 0.0001405,
"loss": 0.8794,
"step": 576
},
{
"epoch": 32.68,
"learning_rate": 0.000140375,
"loss": 0.9115,
"step": 577
},
{
"epoch": 32.74,
"learning_rate": 0.00014025000000000002,
"loss": 0.815,
"step": 578
},
{
"epoch": 32.79,
"learning_rate": 0.000140125,
"loss": 0.8095,
"step": 579
},
{
"epoch": 32.85,
"learning_rate": 0.00014,
"loss": 0.8478,
"step": 580
},
{
"epoch": 32.91,
"learning_rate": 0.000139875,
"loss": 0.8056,
"step": 581
},
{
"epoch": 32.96,
"learning_rate": 0.00013975,
"loss": 0.9301,
"step": 582
},
{
"epoch": 33.02,
"learning_rate": 0.00013962500000000002,
"loss": 0.8053,
"step": 583
},
{
"epoch": 33.08,
"learning_rate": 0.0001395,
"loss": 0.8094,
"step": 584
},
{
"epoch": 33.13,
"learning_rate": 0.000139375,
"loss": 0.8191,
"step": 585
},
{
"epoch": 33.19,
"learning_rate": 0.00013925000000000002,
"loss": 0.8934,
"step": 586
},
{
"epoch": 33.25,
"learning_rate": 0.000139125,
"loss": 0.88,
"step": 587
},
{
"epoch": 33.3,
"learning_rate": 0.000139,
"loss": 0.9598,
"step": 588
},
{
"epoch": 33.36,
"learning_rate": 0.000138875,
"loss": 0.8177,
"step": 589
},
{
"epoch": 33.42,
"learning_rate": 0.00013875,
"loss": 0.7988,
"step": 590
},
{
"epoch": 33.47,
"learning_rate": 0.000138625,
"loss": 0.976,
"step": 591
},
{
"epoch": 33.53,
"learning_rate": 0.0001385,
"loss": 0.7895,
"step": 592
},
{
"epoch": 33.59,
"learning_rate": 0.00013837500000000002,
"loss": 0.8736,
"step": 593
},
{
"epoch": 33.64,
"learning_rate": 0.00013825,
"loss": 0.821,
"step": 594
},
{
"epoch": 33.7,
"learning_rate": 0.000138125,
"loss": 0.8448,
"step": 595
},
{
"epoch": 33.76,
"learning_rate": 0.000138,
"loss": 0.8763,
"step": 596
},
{
"epoch": 33.81,
"learning_rate": 0.000137875,
"loss": 0.9005,
"step": 597
},
{
"epoch": 33.87,
"learning_rate": 0.00013775000000000001,
"loss": 0.7962,
"step": 598
},
{
"epoch": 33.93,
"learning_rate": 0.000137625,
"loss": 0.9145,
"step": 599
},
{
"epoch": 33.98,
"learning_rate": 0.0001375,
"loss": 0.8612,
"step": 600
},
{
"epoch": 33.98,
"eval_loss": 2.6225430965423584,
"eval_runtime": 90.4931,
"eval_samples_per_second": 2.774,
"eval_steps_per_second": 0.696,
"step": 600
}
],
"max_steps": 1700,
"num_train_epochs": 100,
"total_flos": 4.163924540462285e+17,
"trial_name": null,
"trial_params": null
}