v0.7a-adapter / trainer_state.json
gotzmann's picture
..
59058c1
raw
history blame contribute delete
No virus
228 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9998688524590164,
"eval_steps": 500,
"global_step": 1906,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 5.000000000000001e-07,
"loss": 1.4402,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.0000000000000002e-06,
"loss": 1.2974,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 1.5e-06,
"loss": 1.3829,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.2123,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 2.5e-06,
"loss": 1.2531,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 3e-06,
"loss": 1.2363,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 3.5000000000000004e-06,
"loss": 1.3185,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 4.000000000000001e-06,
"loss": 1.4033,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 4.5e-06,
"loss": 1.3155,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 5e-06,
"loss": 1.3133,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 5.500000000000001e-06,
"loss": 1.1435,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 6e-06,
"loss": 1.3102,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 6.5000000000000004e-06,
"loss": 1.3607,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 7.000000000000001e-06,
"loss": 1.3813,
"step": 14
},
{
"epoch": 0.01,
"learning_rate": 7.5e-06,
"loss": 1.0608,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 8.000000000000001e-06,
"loss": 1.231,
"step": 16
},
{
"epoch": 0.01,
"learning_rate": 8.500000000000002e-06,
"loss": 1.2295,
"step": 17
},
{
"epoch": 0.01,
"learning_rate": 9e-06,
"loss": 1.3969,
"step": 18
},
{
"epoch": 0.01,
"learning_rate": 9.5e-06,
"loss": 1.3138,
"step": 19
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 1.3306,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 1.05e-05,
"loss": 1.3093,
"step": 21
},
{
"epoch": 0.01,
"learning_rate": 1.1000000000000001e-05,
"loss": 1.3343,
"step": 22
},
{
"epoch": 0.01,
"learning_rate": 1.1500000000000002e-05,
"loss": 1.2608,
"step": 23
},
{
"epoch": 0.01,
"learning_rate": 1.2e-05,
"loss": 1.2221,
"step": 24
},
{
"epoch": 0.01,
"learning_rate": 1.25e-05,
"loss": 1.3127,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 1.3000000000000001e-05,
"loss": 1.1553,
"step": 26
},
{
"epoch": 0.01,
"learning_rate": 1.3500000000000001e-05,
"loss": 1.193,
"step": 27
},
{
"epoch": 0.01,
"learning_rate": 1.4000000000000001e-05,
"loss": 1.1875,
"step": 28
},
{
"epoch": 0.02,
"learning_rate": 1.45e-05,
"loss": 1.3608,
"step": 29
},
{
"epoch": 0.02,
"learning_rate": 1.5e-05,
"loss": 1.3877,
"step": 30
},
{
"epoch": 0.02,
"learning_rate": 1.55e-05,
"loss": 1.1709,
"step": 31
},
{
"epoch": 0.02,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.3518,
"step": 32
},
{
"epoch": 0.02,
"learning_rate": 1.65e-05,
"loss": 1.0326,
"step": 33
},
{
"epoch": 0.02,
"learning_rate": 1.7000000000000003e-05,
"loss": 1.2824,
"step": 34
},
{
"epoch": 0.02,
"learning_rate": 1.75e-05,
"loss": 1.1297,
"step": 35
},
{
"epoch": 0.02,
"learning_rate": 1.8e-05,
"loss": 1.375,
"step": 36
},
{
"epoch": 0.02,
"learning_rate": 1.85e-05,
"loss": 1.3613,
"step": 37
},
{
"epoch": 0.02,
"learning_rate": 1.9e-05,
"loss": 1.2704,
"step": 38
},
{
"epoch": 0.02,
"learning_rate": 1.9500000000000003e-05,
"loss": 1.2878,
"step": 39
},
{
"epoch": 0.02,
"learning_rate": 2e-05,
"loss": 1.2387,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 2.05e-05,
"loss": 1.2736,
"step": 41
},
{
"epoch": 0.02,
"learning_rate": 2.1e-05,
"loss": 1.0853,
"step": 42
},
{
"epoch": 0.02,
"learning_rate": 2.15e-05,
"loss": 1.3032,
"step": 43
},
{
"epoch": 0.02,
"learning_rate": 2.2000000000000003e-05,
"loss": 1.4046,
"step": 44
},
{
"epoch": 0.02,
"learning_rate": 2.25e-05,
"loss": 1.2216,
"step": 45
},
{
"epoch": 0.02,
"learning_rate": 2.3000000000000003e-05,
"loss": 1.3412,
"step": 46
},
{
"epoch": 0.02,
"learning_rate": 2.35e-05,
"loss": 1.1387,
"step": 47
},
{
"epoch": 0.03,
"learning_rate": 2.4e-05,
"loss": 1.2394,
"step": 48
},
{
"epoch": 0.03,
"learning_rate": 2.45e-05,
"loss": 1.1871,
"step": 49
},
{
"epoch": 0.03,
"learning_rate": 2.5e-05,
"loss": 1.3087,
"step": 50
},
{
"epoch": 0.03,
"learning_rate": 2.5500000000000003e-05,
"loss": 1.4174,
"step": 51
},
{
"epoch": 0.03,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.3503,
"step": 52
},
{
"epoch": 0.03,
"learning_rate": 2.6500000000000004e-05,
"loss": 1.0027,
"step": 53
},
{
"epoch": 0.03,
"learning_rate": 2.7000000000000002e-05,
"loss": 1.1663,
"step": 54
},
{
"epoch": 0.03,
"learning_rate": 2.7500000000000004e-05,
"loss": 1.267,
"step": 55
},
{
"epoch": 0.03,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.4091,
"step": 56
},
{
"epoch": 0.03,
"learning_rate": 2.8499999999999998e-05,
"loss": 1.1291,
"step": 57
},
{
"epoch": 0.03,
"learning_rate": 2.9e-05,
"loss": 1.1999,
"step": 58
},
{
"epoch": 0.03,
"learning_rate": 2.95e-05,
"loss": 1.4182,
"step": 59
},
{
"epoch": 0.03,
"learning_rate": 3e-05,
"loss": 1.2489,
"step": 60
},
{
"epoch": 0.03,
"learning_rate": 3.05e-05,
"loss": 1.3163,
"step": 61
},
{
"epoch": 0.03,
"learning_rate": 3.1e-05,
"loss": 1.4771,
"step": 62
},
{
"epoch": 0.03,
"learning_rate": 3.15e-05,
"loss": 1.3095,
"step": 63
},
{
"epoch": 0.03,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.342,
"step": 64
},
{
"epoch": 0.03,
"learning_rate": 3.2500000000000004e-05,
"loss": 1.2861,
"step": 65
},
{
"epoch": 0.03,
"learning_rate": 3.3e-05,
"loss": 1.3194,
"step": 66
},
{
"epoch": 0.04,
"learning_rate": 3.35e-05,
"loss": 1.453,
"step": 67
},
{
"epoch": 0.04,
"learning_rate": 3.4000000000000007e-05,
"loss": 1.3028,
"step": 68
},
{
"epoch": 0.04,
"learning_rate": 3.45e-05,
"loss": 1.2935,
"step": 69
},
{
"epoch": 0.04,
"learning_rate": 3.5e-05,
"loss": 1.1916,
"step": 70
},
{
"epoch": 0.04,
"learning_rate": 3.55e-05,
"loss": 1.0879,
"step": 71
},
{
"epoch": 0.04,
"learning_rate": 3.6e-05,
"loss": 1.1877,
"step": 72
},
{
"epoch": 0.04,
"learning_rate": 3.65e-05,
"loss": 1.4162,
"step": 73
},
{
"epoch": 0.04,
"learning_rate": 3.7e-05,
"loss": 1.2123,
"step": 74
},
{
"epoch": 0.04,
"learning_rate": 3.7500000000000003e-05,
"loss": 1.0477,
"step": 75
},
{
"epoch": 0.04,
"learning_rate": 3.8e-05,
"loss": 1.2846,
"step": 76
},
{
"epoch": 0.04,
"learning_rate": 3.85e-05,
"loss": 1.3299,
"step": 77
},
{
"epoch": 0.04,
"learning_rate": 3.9000000000000006e-05,
"loss": 1.1059,
"step": 78
},
{
"epoch": 0.04,
"learning_rate": 3.9500000000000005e-05,
"loss": 1.2354,
"step": 79
},
{
"epoch": 0.04,
"learning_rate": 4e-05,
"loss": 1.212,
"step": 80
},
{
"epoch": 0.04,
"learning_rate": 4.05e-05,
"loss": 1.3152,
"step": 81
},
{
"epoch": 0.04,
"learning_rate": 4.1e-05,
"loss": 1.3151,
"step": 82
},
{
"epoch": 0.04,
"learning_rate": 4.15e-05,
"loss": 1.1023,
"step": 83
},
{
"epoch": 0.04,
"learning_rate": 4.2e-05,
"loss": 0.955,
"step": 84
},
{
"epoch": 0.04,
"learning_rate": 4.25e-05,
"loss": 1.3137,
"step": 85
},
{
"epoch": 0.05,
"learning_rate": 4.3e-05,
"loss": 1.1734,
"step": 86
},
{
"epoch": 0.05,
"learning_rate": 4.35e-05,
"loss": 1.5858,
"step": 87
},
{
"epoch": 0.05,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.3958,
"step": 88
},
{
"epoch": 0.05,
"learning_rate": 4.4500000000000004e-05,
"loss": 1.2501,
"step": 89
},
{
"epoch": 0.05,
"learning_rate": 4.5e-05,
"loss": 0.9868,
"step": 90
},
{
"epoch": 0.05,
"learning_rate": 4.55e-05,
"loss": 1.4658,
"step": 91
},
{
"epoch": 0.05,
"learning_rate": 4.600000000000001e-05,
"loss": 1.2563,
"step": 92
},
{
"epoch": 0.05,
"learning_rate": 4.6500000000000005e-05,
"loss": 1.4123,
"step": 93
},
{
"epoch": 0.05,
"learning_rate": 4.7e-05,
"loss": 1.2969,
"step": 94
},
{
"epoch": 0.05,
"learning_rate": 4.75e-05,
"loss": 1.3332,
"step": 95
},
{
"epoch": 0.05,
"learning_rate": 4.8e-05,
"loss": 1.2221,
"step": 96
},
{
"epoch": 0.05,
"learning_rate": 4.85e-05,
"loss": 0.9418,
"step": 97
},
{
"epoch": 0.05,
"learning_rate": 4.9e-05,
"loss": 1.2269,
"step": 98
},
{
"epoch": 0.05,
"learning_rate": 4.9500000000000004e-05,
"loss": 1.2562,
"step": 99
},
{
"epoch": 0.05,
"learning_rate": 5e-05,
"loss": 1.2796,
"step": 100
},
{
"epoch": 0.05,
"learning_rate": 5.05e-05,
"loss": 1.2733,
"step": 101
},
{
"epoch": 0.05,
"learning_rate": 5.1000000000000006e-05,
"loss": 1.1599,
"step": 102
},
{
"epoch": 0.05,
"learning_rate": 5.1500000000000005e-05,
"loss": 1.4692,
"step": 103
},
{
"epoch": 0.05,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.2577,
"step": 104
},
{
"epoch": 0.06,
"learning_rate": 5.25e-05,
"loss": 1.1689,
"step": 105
},
{
"epoch": 0.06,
"learning_rate": 5.300000000000001e-05,
"loss": 1.2731,
"step": 106
},
{
"epoch": 0.06,
"learning_rate": 5.3500000000000006e-05,
"loss": 1.2086,
"step": 107
},
{
"epoch": 0.06,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.2367,
"step": 108
},
{
"epoch": 0.06,
"learning_rate": 5.45e-05,
"loss": 1.2464,
"step": 109
},
{
"epoch": 0.06,
"learning_rate": 5.500000000000001e-05,
"loss": 1.1808,
"step": 110
},
{
"epoch": 0.06,
"learning_rate": 5.550000000000001e-05,
"loss": 1.4329,
"step": 111
},
{
"epoch": 0.06,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.055,
"step": 112
},
{
"epoch": 0.06,
"learning_rate": 5.65e-05,
"loss": 1.2394,
"step": 113
},
{
"epoch": 0.06,
"learning_rate": 5.6999999999999996e-05,
"loss": 1.2869,
"step": 114
},
{
"epoch": 0.06,
"learning_rate": 5.7499999999999995e-05,
"loss": 1.4027,
"step": 115
},
{
"epoch": 0.06,
"learning_rate": 5.8e-05,
"loss": 1.4062,
"step": 116
},
{
"epoch": 0.06,
"learning_rate": 5.85e-05,
"loss": 1.4758,
"step": 117
},
{
"epoch": 0.06,
"learning_rate": 5.9e-05,
"loss": 1.3745,
"step": 118
},
{
"epoch": 0.06,
"learning_rate": 5.95e-05,
"loss": 1.0941,
"step": 119
},
{
"epoch": 0.06,
"learning_rate": 6e-05,
"loss": 1.3471,
"step": 120
},
{
"epoch": 0.06,
"learning_rate": 6.05e-05,
"loss": 1.4539,
"step": 121
},
{
"epoch": 0.06,
"learning_rate": 6.1e-05,
"loss": 1.2483,
"step": 122
},
{
"epoch": 0.06,
"learning_rate": 6.15e-05,
"loss": 1.288,
"step": 123
},
{
"epoch": 0.07,
"learning_rate": 6.2e-05,
"loss": 1.269,
"step": 124
},
{
"epoch": 0.07,
"learning_rate": 6.25e-05,
"loss": 1.3949,
"step": 125
},
{
"epoch": 0.07,
"learning_rate": 6.3e-05,
"loss": 1.1431,
"step": 126
},
{
"epoch": 0.07,
"learning_rate": 6.35e-05,
"loss": 1.2321,
"step": 127
},
{
"epoch": 0.07,
"learning_rate": 6.400000000000001e-05,
"loss": 1.3515,
"step": 128
},
{
"epoch": 0.07,
"learning_rate": 6.450000000000001e-05,
"loss": 1.1677,
"step": 129
},
{
"epoch": 0.07,
"learning_rate": 6.500000000000001e-05,
"loss": 1.1339,
"step": 130
},
{
"epoch": 0.07,
"learning_rate": 6.55e-05,
"loss": 1.1899,
"step": 131
},
{
"epoch": 0.07,
"learning_rate": 6.6e-05,
"loss": 1.224,
"step": 132
},
{
"epoch": 0.07,
"learning_rate": 6.65e-05,
"loss": 1.2669,
"step": 133
},
{
"epoch": 0.07,
"learning_rate": 6.7e-05,
"loss": 1.294,
"step": 134
},
{
"epoch": 0.07,
"learning_rate": 6.750000000000001e-05,
"loss": 1.4892,
"step": 135
},
{
"epoch": 0.07,
"learning_rate": 6.800000000000001e-05,
"loss": 1.3983,
"step": 136
},
{
"epoch": 0.07,
"learning_rate": 6.850000000000001e-05,
"loss": 1.1145,
"step": 137
},
{
"epoch": 0.07,
"learning_rate": 6.9e-05,
"loss": 1.3734,
"step": 138
},
{
"epoch": 0.07,
"learning_rate": 6.95e-05,
"loss": 1.3397,
"step": 139
},
{
"epoch": 0.07,
"learning_rate": 7e-05,
"loss": 1.2817,
"step": 140
},
{
"epoch": 0.07,
"learning_rate": 7.05e-05,
"loss": 1.4555,
"step": 141
},
{
"epoch": 0.07,
"learning_rate": 7.1e-05,
"loss": 1.0274,
"step": 142
},
{
"epoch": 0.08,
"learning_rate": 7.15e-05,
"loss": 1.3816,
"step": 143
},
{
"epoch": 0.08,
"learning_rate": 7.2e-05,
"loss": 1.2113,
"step": 144
},
{
"epoch": 0.08,
"learning_rate": 7.25e-05,
"loss": 1.4015,
"step": 145
},
{
"epoch": 0.08,
"learning_rate": 7.3e-05,
"loss": 1.4337,
"step": 146
},
{
"epoch": 0.08,
"learning_rate": 7.35e-05,
"loss": 1.0526,
"step": 147
},
{
"epoch": 0.08,
"learning_rate": 7.4e-05,
"loss": 1.512,
"step": 148
},
{
"epoch": 0.08,
"learning_rate": 7.450000000000001e-05,
"loss": 1.2425,
"step": 149
},
{
"epoch": 0.08,
"learning_rate": 7.500000000000001e-05,
"loss": 1.2719,
"step": 150
},
{
"epoch": 0.08,
"learning_rate": 7.55e-05,
"loss": 1.3005,
"step": 151
},
{
"epoch": 0.08,
"learning_rate": 7.6e-05,
"loss": 1.3609,
"step": 152
},
{
"epoch": 0.08,
"learning_rate": 7.65e-05,
"loss": 1.2509,
"step": 153
},
{
"epoch": 0.08,
"learning_rate": 7.7e-05,
"loss": 1.1672,
"step": 154
},
{
"epoch": 0.08,
"learning_rate": 7.75e-05,
"loss": 1.3381,
"step": 155
},
{
"epoch": 0.08,
"learning_rate": 7.800000000000001e-05,
"loss": 1.3018,
"step": 156
},
{
"epoch": 0.08,
"learning_rate": 7.850000000000001e-05,
"loss": 1.4406,
"step": 157
},
{
"epoch": 0.08,
"learning_rate": 7.900000000000001e-05,
"loss": 1.364,
"step": 158
},
{
"epoch": 0.08,
"learning_rate": 7.950000000000001e-05,
"loss": 1.228,
"step": 159
},
{
"epoch": 0.08,
"learning_rate": 8e-05,
"loss": 1.0226,
"step": 160
},
{
"epoch": 0.08,
"learning_rate": 8.05e-05,
"loss": 0.8691,
"step": 161
},
{
"epoch": 0.08,
"learning_rate": 8.1e-05,
"loss": 1.357,
"step": 162
},
{
"epoch": 0.09,
"learning_rate": 8.15e-05,
"loss": 1.2473,
"step": 163
},
{
"epoch": 0.09,
"learning_rate": 8.2e-05,
"loss": 1.3198,
"step": 164
},
{
"epoch": 0.09,
"learning_rate": 8.25e-05,
"loss": 1.0344,
"step": 165
},
{
"epoch": 0.09,
"learning_rate": 8.3e-05,
"loss": 1.158,
"step": 166
},
{
"epoch": 0.09,
"learning_rate": 8.35e-05,
"loss": 1.1938,
"step": 167
},
{
"epoch": 0.09,
"learning_rate": 8.4e-05,
"loss": 1.5798,
"step": 168
},
{
"epoch": 0.09,
"learning_rate": 8.450000000000001e-05,
"loss": 1.2496,
"step": 169
},
{
"epoch": 0.09,
"learning_rate": 8.5e-05,
"loss": 1.1503,
"step": 170
},
{
"epoch": 0.09,
"learning_rate": 8.55e-05,
"loss": 1.1272,
"step": 171
},
{
"epoch": 0.09,
"learning_rate": 8.6e-05,
"loss": 1.1914,
"step": 172
},
{
"epoch": 0.09,
"learning_rate": 8.65e-05,
"loss": 1.0894,
"step": 173
},
{
"epoch": 0.09,
"learning_rate": 8.7e-05,
"loss": 1.2987,
"step": 174
},
{
"epoch": 0.09,
"learning_rate": 8.75e-05,
"loss": 1.1007,
"step": 175
},
{
"epoch": 0.09,
"learning_rate": 8.800000000000001e-05,
"loss": 1.3069,
"step": 176
},
{
"epoch": 0.09,
"learning_rate": 8.850000000000001e-05,
"loss": 1.2621,
"step": 177
},
{
"epoch": 0.09,
"learning_rate": 8.900000000000001e-05,
"loss": 1.2495,
"step": 178
},
{
"epoch": 0.09,
"learning_rate": 8.950000000000001e-05,
"loss": 1.2971,
"step": 179
},
{
"epoch": 0.09,
"learning_rate": 9e-05,
"loss": 1.4206,
"step": 180
},
{
"epoch": 0.09,
"learning_rate": 9.05e-05,
"loss": 1.1317,
"step": 181
},
{
"epoch": 0.1,
"learning_rate": 9.1e-05,
"loss": 1.3848,
"step": 182
},
{
"epoch": 0.1,
"learning_rate": 9.15e-05,
"loss": 1.2269,
"step": 183
},
{
"epoch": 0.1,
"learning_rate": 9.200000000000001e-05,
"loss": 1.0285,
"step": 184
},
{
"epoch": 0.1,
"learning_rate": 9.250000000000001e-05,
"loss": 1.1156,
"step": 185
},
{
"epoch": 0.1,
"learning_rate": 9.300000000000001e-05,
"loss": 1.1655,
"step": 186
},
{
"epoch": 0.1,
"learning_rate": 9.350000000000001e-05,
"loss": 1.3893,
"step": 187
},
{
"epoch": 0.1,
"learning_rate": 9.4e-05,
"loss": 1.4152,
"step": 188
},
{
"epoch": 0.1,
"learning_rate": 9.449999999999999e-05,
"loss": 1.1634,
"step": 189
},
{
"epoch": 0.1,
"learning_rate": 9.5e-05,
"loss": 1.2566,
"step": 190
},
{
"epoch": 0.1,
"learning_rate": 9.55e-05,
"loss": 1.1817,
"step": 191
},
{
"epoch": 0.1,
"learning_rate": 9.6e-05,
"loss": 1.1584,
"step": 192
},
{
"epoch": 0.1,
"learning_rate": 9.65e-05,
"loss": 1.3525,
"step": 193
},
{
"epoch": 0.1,
"learning_rate": 9.7e-05,
"loss": 1.2545,
"step": 194
},
{
"epoch": 0.1,
"learning_rate": 9.75e-05,
"loss": 1.1936,
"step": 195
},
{
"epoch": 0.1,
"learning_rate": 9.8e-05,
"loss": 1.1608,
"step": 196
},
{
"epoch": 0.1,
"learning_rate": 9.850000000000001e-05,
"loss": 1.3834,
"step": 197
},
{
"epoch": 0.1,
"learning_rate": 9.900000000000001e-05,
"loss": 1.0125,
"step": 198
},
{
"epoch": 0.1,
"learning_rate": 9.95e-05,
"loss": 1.4028,
"step": 199
},
{
"epoch": 0.1,
"learning_rate": 0.0001,
"loss": 1.3749,
"step": 200
},
{
"epoch": 0.11,
"learning_rate": 9.999991522231024e-05,
"loss": 1.2947,
"step": 201
},
{
"epoch": 0.11,
"learning_rate": 9.999966088952841e-05,
"loss": 1.0832,
"step": 202
},
{
"epoch": 0.11,
"learning_rate": 9.999923700251703e-05,
"loss": 1.3497,
"step": 203
},
{
"epoch": 0.11,
"learning_rate": 9.99986435627135e-05,
"loss": 1.1604,
"step": 204
},
{
"epoch": 0.11,
"learning_rate": 9.999788057213027e-05,
"loss": 1.1839,
"step": 205
},
{
"epoch": 0.11,
"learning_rate": 9.999694803335468e-05,
"loss": 1.251,
"step": 206
},
{
"epoch": 0.11,
"learning_rate": 9.999584594954913e-05,
"loss": 1.1404,
"step": 207
},
{
"epoch": 0.11,
"learning_rate": 9.999457432445088e-05,
"loss": 1.5109,
"step": 208
},
{
"epoch": 0.11,
"learning_rate": 9.999313316237211e-05,
"loss": 1.2562,
"step": 209
},
{
"epoch": 0.11,
"learning_rate": 9.999152246820001e-05,
"loss": 1.0774,
"step": 210
},
{
"epoch": 0.11,
"learning_rate": 9.998974224739658e-05,
"loss": 1.1858,
"step": 211
},
{
"epoch": 0.11,
"learning_rate": 9.998779250599876e-05,
"loss": 1.3693,
"step": 212
},
{
"epoch": 0.11,
"learning_rate": 9.998567325061834e-05,
"loss": 1.3105,
"step": 213
},
{
"epoch": 0.11,
"learning_rate": 9.998338448844192e-05,
"loss": 1.183,
"step": 214
},
{
"epoch": 0.11,
"learning_rate": 9.998092622723096e-05,
"loss": 1.2715,
"step": 215
},
{
"epoch": 0.11,
"learning_rate": 9.997829847532166e-05,
"loss": 1.4714,
"step": 216
},
{
"epoch": 0.11,
"learning_rate": 9.997550124162503e-05,
"loss": 1.2119,
"step": 217
},
{
"epoch": 0.11,
"learning_rate": 9.99725345356268e-05,
"loss": 1.2402,
"step": 218
},
{
"epoch": 0.11,
"learning_rate": 9.996939836738737e-05,
"loss": 1.3608,
"step": 219
},
{
"epoch": 0.12,
"learning_rate": 9.996609274754182e-05,
"loss": 1.4216,
"step": 220
},
{
"epoch": 0.12,
"learning_rate": 9.99626176872999e-05,
"loss": 1.1339,
"step": 221
},
{
"epoch": 0.12,
"learning_rate": 9.995897319844587e-05,
"loss": 0.7566,
"step": 222
},
{
"epoch": 0.12,
"learning_rate": 9.99551592933386e-05,
"loss": 1.1302,
"step": 223
},
{
"epoch": 0.12,
"learning_rate": 9.995117598491145e-05,
"loss": 1.2968,
"step": 224
},
{
"epoch": 0.12,
"learning_rate": 9.994702328667224e-05,
"loss": 1.0836,
"step": 225
},
{
"epoch": 0.12,
"learning_rate": 9.994270121270326e-05,
"loss": 1.4386,
"step": 226
},
{
"epoch": 0.12,
"learning_rate": 9.993820977766108e-05,
"loss": 1.133,
"step": 227
},
{
"epoch": 0.12,
"learning_rate": 9.993354899677665e-05,
"loss": 0.8334,
"step": 228
},
{
"epoch": 0.12,
"learning_rate": 9.992871888585518e-05,
"loss": 1.2115,
"step": 229
},
{
"epoch": 0.12,
"learning_rate": 9.99237194612761e-05,
"loss": 1.355,
"step": 230
},
{
"epoch": 0.12,
"learning_rate": 9.991855073999299e-05,
"loss": 1.1176,
"step": 231
},
{
"epoch": 0.12,
"learning_rate": 9.991321273953355e-05,
"loss": 1.2793,
"step": 232
},
{
"epoch": 0.12,
"learning_rate": 9.990770547799952e-05,
"loss": 1.363,
"step": 233
},
{
"epoch": 0.12,
"learning_rate": 9.99020289740666e-05,
"loss": 1.0069,
"step": 234
},
{
"epoch": 0.12,
"learning_rate": 9.989618324698445e-05,
"loss": 1.3302,
"step": 235
},
{
"epoch": 0.12,
"learning_rate": 9.989016831657652e-05,
"loss": 1.1625,
"step": 236
},
{
"epoch": 0.12,
"learning_rate": 9.98839842032401e-05,
"loss": 1.273,
"step": 237
},
{
"epoch": 0.12,
"learning_rate": 9.98776309279462e-05,
"loss": 1.1127,
"step": 238
},
{
"epoch": 0.13,
"learning_rate": 9.987110851223947e-05,
"loss": 1.2729,
"step": 239
},
{
"epoch": 0.13,
"learning_rate": 9.986441697823808e-05,
"loss": 1.1195,
"step": 240
},
{
"epoch": 0.13,
"learning_rate": 9.985755634863378e-05,
"loss": 1.2677,
"step": 241
},
{
"epoch": 0.13,
"learning_rate": 9.985052664669167e-05,
"loss": 1.259,
"step": 242
},
{
"epoch": 0.13,
"learning_rate": 9.984332789625026e-05,
"loss": 1.3361,
"step": 243
},
{
"epoch": 0.13,
"learning_rate": 9.983596012172127e-05,
"loss": 1.1438,
"step": 244
},
{
"epoch": 0.13,
"learning_rate": 9.982842334808964e-05,
"loss": 1.0646,
"step": 245
},
{
"epoch": 0.13,
"learning_rate": 9.982071760091333e-05,
"loss": 1.3861,
"step": 246
},
{
"epoch": 0.13,
"learning_rate": 9.98128429063234e-05,
"loss": 1.4703,
"step": 247
},
{
"epoch": 0.13,
"learning_rate": 9.980479929102377e-05,
"loss": 1.2234,
"step": 248
},
{
"epoch": 0.13,
"learning_rate": 9.97965867822912e-05,
"loss": 1.2941,
"step": 249
},
{
"epoch": 0.13,
"learning_rate": 9.978820540797522e-05,
"loss": 0.9393,
"step": 250
},
{
"epoch": 0.13,
"learning_rate": 9.977965519649792e-05,
"loss": 1.3673,
"step": 251
},
{
"epoch": 0.13,
"learning_rate": 9.977093617685404e-05,
"loss": 1.083,
"step": 252
},
{
"epoch": 0.13,
"learning_rate": 9.976204837861069e-05,
"loss": 1.3907,
"step": 253
},
{
"epoch": 0.13,
"learning_rate": 9.975299183190734e-05,
"loss": 1.1981,
"step": 254
},
{
"epoch": 0.13,
"learning_rate": 9.974376656745575e-05,
"loss": 1.154,
"step": 255
},
{
"epoch": 0.13,
"learning_rate": 9.973437261653973e-05,
"loss": 1.1126,
"step": 256
},
{
"epoch": 0.13,
"learning_rate": 9.972481001101522e-05,
"loss": 1.3774,
"step": 257
},
{
"epoch": 0.14,
"learning_rate": 9.971507878331004e-05,
"loss": 1.3103,
"step": 258
},
{
"epoch": 0.14,
"learning_rate": 9.970517896642382e-05,
"loss": 1.0752,
"step": 259
},
{
"epoch": 0.14,
"learning_rate": 9.96951105939279e-05,
"loss": 1.3074,
"step": 260
},
{
"epoch": 0.14,
"learning_rate": 9.968487369996522e-05,
"loss": 1.0814,
"step": 261
},
{
"epoch": 0.14,
"learning_rate": 9.967446831925021e-05,
"loss": 1.183,
"step": 262
},
{
"epoch": 0.14,
"learning_rate": 9.966389448706859e-05,
"loss": 1.2898,
"step": 263
},
{
"epoch": 0.14,
"learning_rate": 9.965315223927741e-05,
"loss": 1.0228,
"step": 264
},
{
"epoch": 0.14,
"learning_rate": 9.964224161230475e-05,
"loss": 1.2523,
"step": 265
},
{
"epoch": 0.14,
"learning_rate": 9.963116264314974e-05,
"loss": 1.1339,
"step": 266
},
{
"epoch": 0.14,
"learning_rate": 9.961991536938235e-05,
"loss": 1.13,
"step": 267
},
{
"epoch": 0.14,
"learning_rate": 9.960849982914331e-05,
"loss": 1.0781,
"step": 268
},
{
"epoch": 0.14,
"learning_rate": 9.959691606114393e-05,
"loss": 1.2281,
"step": 269
},
{
"epoch": 0.14,
"learning_rate": 9.9585164104666e-05,
"loss": 1.1895,
"step": 270
},
{
"epoch": 0.14,
"learning_rate": 9.957324399956172e-05,
"loss": 1.3988,
"step": 271
},
{
"epoch": 0.14,
"learning_rate": 9.956115578625338e-05,
"loss": 1.0442,
"step": 272
},
{
"epoch": 0.14,
"learning_rate": 9.954889950573348e-05,
"loss": 1.0827,
"step": 273
},
{
"epoch": 0.14,
"learning_rate": 9.953647519956433e-05,
"loss": 0.9302,
"step": 274
},
{
"epoch": 0.14,
"learning_rate": 9.95238829098781e-05,
"loss": 1.3566,
"step": 275
},
{
"epoch": 0.14,
"learning_rate": 9.951112267937663e-05,
"loss": 1.3031,
"step": 276
},
{
"epoch": 0.15,
"learning_rate": 9.94981945513312e-05,
"loss": 1.0653,
"step": 277
},
{
"epoch": 0.15,
"learning_rate": 9.948509856958252e-05,
"loss": 0.9141,
"step": 278
},
{
"epoch": 0.15,
"learning_rate": 9.947183477854042e-05,
"loss": 1.1823,
"step": 279
},
{
"epoch": 0.15,
"learning_rate": 9.945840322318391e-05,
"loss": 1.1461,
"step": 280
},
{
"epoch": 0.15,
"learning_rate": 9.944480394906078e-05,
"loss": 1.303,
"step": 281
},
{
"epoch": 0.15,
"learning_rate": 9.943103700228766e-05,
"loss": 1.065,
"step": 282
},
{
"epoch": 0.15,
"learning_rate": 9.941710242954976e-05,
"loss": 1.2391,
"step": 283
},
{
"epoch": 0.15,
"learning_rate": 9.940300027810067e-05,
"loss": 1.1476,
"step": 284
},
{
"epoch": 0.15,
"learning_rate": 9.938873059576235e-05,
"loss": 1.427,
"step": 285
},
{
"epoch": 0.15,
"learning_rate": 9.93742934309248e-05,
"loss": 1.1731,
"step": 286
},
{
"epoch": 0.15,
"learning_rate": 9.935968883254601e-05,
"loss": 1.2476,
"step": 287
},
{
"epoch": 0.15,
"learning_rate": 9.934491685015174e-05,
"loss": 1.3016,
"step": 288
},
{
"epoch": 0.15,
"learning_rate": 9.932997753383537e-05,
"loss": 1.2605,
"step": 289
},
{
"epoch": 0.15,
"learning_rate": 9.931487093425774e-05,
"loss": 1.2571,
"step": 290
},
{
"epoch": 0.15,
"learning_rate": 9.929959710264695e-05,
"loss": 1.1089,
"step": 291
},
{
"epoch": 0.15,
"learning_rate": 9.92841560907982e-05,
"loss": 1.2059,
"step": 292
},
{
"epoch": 0.15,
"learning_rate": 9.926854795107363e-05,
"loss": 1.1879,
"step": 293
},
{
"epoch": 0.15,
"learning_rate": 9.92527727364021e-05,
"loss": 1.3873,
"step": 294
},
{
"epoch": 0.15,
"learning_rate": 9.92368305002791e-05,
"loss": 1.3071,
"step": 295
},
{
"epoch": 0.16,
"learning_rate": 9.922072129676644e-05,
"loss": 1.011,
"step": 296
},
{
"epoch": 0.16,
"learning_rate": 9.920444518049217e-05,
"loss": 1.2344,
"step": 297
},
{
"epoch": 0.16,
"learning_rate": 9.918800220665035e-05,
"loss": 1.2956,
"step": 298
},
{
"epoch": 0.16,
"learning_rate": 9.917139243100087e-05,
"loss": 1.1677,
"step": 299
},
{
"epoch": 0.16,
"learning_rate": 9.915461590986926e-05,
"loss": 0.9923,
"step": 300
},
{
"epoch": 0.16,
"learning_rate": 9.91376727001465e-05,
"loss": 1.1869,
"step": 301
},
{
"epoch": 0.16,
"learning_rate": 9.912056285928891e-05,
"loss": 1.1501,
"step": 302
},
{
"epoch": 0.16,
"learning_rate": 9.91032864453177e-05,
"loss": 1.4009,
"step": 303
},
{
"epoch": 0.16,
"learning_rate": 9.908584351681911e-05,
"loss": 1.307,
"step": 304
},
{
"epoch": 0.16,
"learning_rate": 9.906823413294397e-05,
"loss": 1.3197,
"step": 305
},
{
"epoch": 0.16,
"learning_rate": 9.905045835340759e-05,
"loss": 1.1601,
"step": 306
},
{
"epoch": 0.16,
"learning_rate": 9.903251623848957e-05,
"loss": 1.0623,
"step": 307
},
{
"epoch": 0.16,
"learning_rate": 9.901440784903353e-05,
"loss": 1.2217,
"step": 308
},
{
"epoch": 0.16,
"learning_rate": 9.899613324644698e-05,
"loss": 1.2233,
"step": 309
},
{
"epoch": 0.16,
"learning_rate": 9.897769249270105e-05,
"loss": 1.2024,
"step": 310
},
{
"epoch": 0.16,
"learning_rate": 9.895908565033036e-05,
"loss": 1.1011,
"step": 311
},
{
"epoch": 0.16,
"learning_rate": 9.894031278243266e-05,
"loss": 1.1673,
"step": 312
},
{
"epoch": 0.16,
"learning_rate": 9.89213739526688e-05,
"loss": 1.2906,
"step": 313
},
{
"epoch": 0.16,
"learning_rate": 9.890226922526237e-05,
"loss": 1.3677,
"step": 314
},
{
"epoch": 0.17,
"learning_rate": 9.888299866499957e-05,
"loss": 1.1037,
"step": 315
},
{
"epoch": 0.17,
"learning_rate": 9.886356233722894e-05,
"loss": 1.234,
"step": 316
},
{
"epoch": 0.17,
"learning_rate": 9.884396030786115e-05,
"loss": 1.0158,
"step": 317
},
{
"epoch": 0.17,
"learning_rate": 9.88241926433688e-05,
"loss": 1.0984,
"step": 318
},
{
"epoch": 0.17,
"learning_rate": 9.880425941078617e-05,
"loss": 1.2505,
"step": 319
},
{
"epoch": 0.17,
"learning_rate": 9.878416067770898e-05,
"loss": 1.3511,
"step": 320
},
{
"epoch": 0.17,
"learning_rate": 9.87638965122942e-05,
"loss": 1.1775,
"step": 321
},
{
"epoch": 0.17,
"learning_rate": 9.874346698325983e-05,
"loss": 1.15,
"step": 322
},
{
"epoch": 0.17,
"learning_rate": 9.872287215988456e-05,
"loss": 1.1318,
"step": 323
},
{
"epoch": 0.17,
"learning_rate": 9.870211211200766e-05,
"loss": 1.1427,
"step": 324
},
{
"epoch": 0.17,
"learning_rate": 9.86811869100287e-05,
"loss": 1.1519,
"step": 325
},
{
"epoch": 0.17,
"learning_rate": 9.866009662490727e-05,
"loss": 1.1259,
"step": 326
},
{
"epoch": 0.17,
"learning_rate": 9.863884132816282e-05,
"loss": 1.353,
"step": 327
},
{
"epoch": 0.17,
"learning_rate": 9.861742109187432e-05,
"loss": 1.3784,
"step": 328
},
{
"epoch": 0.17,
"learning_rate": 9.859583598868012e-05,
"loss": 1.1854,
"step": 329
},
{
"epoch": 0.17,
"learning_rate": 9.857408609177762e-05,
"loss": 1.2821,
"step": 330
},
{
"epoch": 0.17,
"learning_rate": 9.855217147492309e-05,
"loss": 1.3438,
"step": 331
},
{
"epoch": 0.17,
"learning_rate": 9.853009221243127e-05,
"loss": 1.1585,
"step": 332
},
{
"epoch": 0.17,
"learning_rate": 9.850784837917542e-05,
"loss": 1.2573,
"step": 333
},
{
"epoch": 0.18,
"learning_rate": 9.848544005058668e-05,
"loss": 1.1598,
"step": 334
},
{
"epoch": 0.18,
"learning_rate": 9.846286730265417e-05,
"loss": 1.2003,
"step": 335
},
{
"epoch": 0.18,
"learning_rate": 9.844013021192447e-05,
"loss": 1.1554,
"step": 336
},
{
"epoch": 0.18,
"learning_rate": 9.841722885550152e-05,
"loss": 1.3157,
"step": 337
},
{
"epoch": 0.18,
"learning_rate": 9.839416331104625e-05,
"loss": 1.3834,
"step": 338
},
{
"epoch": 0.18,
"learning_rate": 9.837093365677644e-05,
"loss": 1.3736,
"step": 339
},
{
"epoch": 0.18,
"learning_rate": 9.834753997146633e-05,
"loss": 1.4065,
"step": 340
},
{
"epoch": 0.18,
"learning_rate": 9.832398233444644e-05,
"loss": 1.1594,
"step": 341
},
{
"epoch": 0.18,
"learning_rate": 9.830026082560324e-05,
"loss": 1.1042,
"step": 342
},
{
"epoch": 0.18,
"learning_rate": 9.827637552537892e-05,
"loss": 1.2533,
"step": 343
},
{
"epoch": 0.18,
"learning_rate": 9.825232651477109e-05,
"loss": 1.2629,
"step": 344
},
{
"epoch": 0.18,
"learning_rate": 9.822811387533255e-05,
"loss": 1.3435,
"step": 345
},
{
"epoch": 0.18,
"learning_rate": 9.820373768917095e-05,
"loss": 1.1654,
"step": 346
},
{
"epoch": 0.18,
"learning_rate": 9.817919803894857e-05,
"loss": 1.1599,
"step": 347
},
{
"epoch": 0.18,
"learning_rate": 9.815449500788202e-05,
"loss": 1.2459,
"step": 348
},
{
"epoch": 0.18,
"learning_rate": 9.812962867974191e-05,
"loss": 1.1792,
"step": 349
},
{
"epoch": 0.18,
"learning_rate": 9.810459913885265e-05,
"loss": 1.29,
"step": 350
},
{
"epoch": 0.18,
"learning_rate": 9.807940647009209e-05,
"loss": 1.184,
"step": 351
},
{
"epoch": 0.18,
"learning_rate": 9.805405075889129e-05,
"loss": 1.2152,
"step": 352
},
{
"epoch": 0.19,
"learning_rate": 9.802853209123421e-05,
"loss": 1.1893,
"step": 353
},
{
"epoch": 0.19,
"learning_rate": 9.800285055365736e-05,
"loss": 1.0028,
"step": 354
},
{
"epoch": 0.19,
"learning_rate": 9.797700623324963e-05,
"loss": 1.1743,
"step": 355
},
{
"epoch": 0.19,
"learning_rate": 9.79509992176519e-05,
"loss": 1.3778,
"step": 356
},
{
"epoch": 0.19,
"learning_rate": 9.79248295950567e-05,
"loss": 1.2219,
"step": 357
},
{
"epoch": 0.19,
"learning_rate": 9.789849745420812e-05,
"loss": 1.2271,
"step": 358
},
{
"epoch": 0.19,
"learning_rate": 9.787200288440119e-05,
"loss": 1.2562,
"step": 359
},
{
"epoch": 0.19,
"learning_rate": 9.784534597548193e-05,
"loss": 1.3299,
"step": 360
},
{
"epoch": 0.19,
"learning_rate": 9.781852681784673e-05,
"loss": 1.0952,
"step": 361
},
{
"epoch": 0.19,
"learning_rate": 9.779154550244228e-05,
"loss": 1.2017,
"step": 362
},
{
"epoch": 0.19,
"learning_rate": 9.776440212076508e-05,
"loss": 1.3052,
"step": 363
},
{
"epoch": 0.19,
"learning_rate": 9.773709676486129e-05,
"loss": 1.2865,
"step": 364
},
{
"epoch": 0.19,
"learning_rate": 9.77096295273263e-05,
"loss": 1.3906,
"step": 365
},
{
"epoch": 0.19,
"learning_rate": 9.768200050130446e-05,
"loss": 1.2156,
"step": 366
},
{
"epoch": 0.19,
"learning_rate": 9.765420978048878e-05,
"loss": 1.3526,
"step": 367
},
{
"epoch": 0.19,
"learning_rate": 9.76262574591206e-05,
"loss": 1.1161,
"step": 368
},
{
"epoch": 0.19,
"learning_rate": 9.75981436319892e-05,
"loss": 1.1305,
"step": 369
},
{
"epoch": 0.19,
"learning_rate": 9.756986839443165e-05,
"loss": 1.2702,
"step": 370
},
{
"epoch": 0.19,
"learning_rate": 9.754143184233229e-05,
"loss": 1.2484,
"step": 371
},
{
"epoch": 0.2,
"learning_rate": 9.751283407212252e-05,
"loss": 1.1719,
"step": 372
},
{
"epoch": 0.2,
"learning_rate": 9.748407518078048e-05,
"loss": 1.1618,
"step": 373
},
{
"epoch": 0.2,
"learning_rate": 9.745515526583065e-05,
"loss": 1.3899,
"step": 374
},
{
"epoch": 0.2,
"learning_rate": 9.74260744253436e-05,
"loss": 1.2776,
"step": 375
},
{
"epoch": 0.2,
"learning_rate": 9.739683275793554e-05,
"loss": 1.1928,
"step": 376
},
{
"epoch": 0.2,
"learning_rate": 9.736743036276815e-05,
"loss": 1.2492,
"step": 377
},
{
"epoch": 0.2,
"learning_rate": 9.733786733954809e-05,
"loss": 1.1258,
"step": 378
},
{
"epoch": 0.2,
"learning_rate": 9.730814378852678e-05,
"loss": 1.2204,
"step": 379
},
{
"epoch": 0.2,
"learning_rate": 9.727825981049994e-05,
"loss": 1.0736,
"step": 380
},
{
"epoch": 0.2,
"learning_rate": 9.72482155068074e-05,
"loss": 1.231,
"step": 381
},
{
"epoch": 0.2,
"learning_rate": 9.72180109793326e-05,
"loss": 1.3367,
"step": 382
},
{
"epoch": 0.2,
"learning_rate": 9.718764633050235e-05,
"loss": 1.3104,
"step": 383
},
{
"epoch": 0.2,
"learning_rate": 9.715712166328644e-05,
"loss": 1.2265,
"step": 384
},
{
"epoch": 0.2,
"learning_rate": 9.712643708119729e-05,
"loss": 1.2225,
"step": 385
},
{
"epoch": 0.2,
"learning_rate": 9.709559268828963e-05,
"loss": 1.3006,
"step": 386
},
{
"epoch": 0.2,
"learning_rate": 9.706458858916012e-05,
"loss": 1.3773,
"step": 387
},
{
"epoch": 0.2,
"learning_rate": 9.703342488894697e-05,
"loss": 1.2459,
"step": 388
},
{
"epoch": 0.2,
"learning_rate": 9.700210169332968e-05,
"loss": 1.2936,
"step": 389
},
{
"epoch": 0.2,
"learning_rate": 9.697061910852856e-05,
"loss": 1.1028,
"step": 390
},
{
"epoch": 0.21,
"learning_rate": 9.693897724130442e-05,
"loss": 1.1513,
"step": 391
},
{
"epoch": 0.21,
"learning_rate": 9.690717619895828e-05,
"loss": 1.2812,
"step": 392
},
{
"epoch": 0.21,
"learning_rate": 9.687521608933086e-05,
"loss": 1.1474,
"step": 393
},
{
"epoch": 0.21,
"learning_rate": 9.684309702080233e-05,
"loss": 1.1615,
"step": 394
},
{
"epoch": 0.21,
"learning_rate": 9.681081910229192e-05,
"loss": 1.0054,
"step": 395
},
{
"epoch": 0.21,
"learning_rate": 9.677838244325754e-05,
"loss": 1.1671,
"step": 396
},
{
"epoch": 0.21,
"learning_rate": 9.674578715369536e-05,
"loss": 1.3808,
"step": 397
},
{
"epoch": 0.21,
"learning_rate": 9.671303334413952e-05,
"loss": 1.3508,
"step": 398
},
{
"epoch": 0.21,
"learning_rate": 9.668012112566174e-05,
"loss": 1.0374,
"step": 399
},
{
"epoch": 0.21,
"learning_rate": 9.664705060987085e-05,
"loss": 1.2246,
"step": 400
},
{
"epoch": 0.21,
"learning_rate": 9.661382190891256e-05,
"loss": 1.3459,
"step": 401
},
{
"epoch": 0.21,
"learning_rate": 9.658043513546897e-05,
"loss": 1.237,
"step": 402
},
{
"epoch": 0.21,
"learning_rate": 9.654689040275819e-05,
"loss": 1.1525,
"step": 403
},
{
"epoch": 0.21,
"learning_rate": 9.651318782453407e-05,
"loss": 1.0688,
"step": 404
},
{
"epoch": 0.21,
"learning_rate": 9.647932751508562e-05,
"loss": 1.0431,
"step": 405
},
{
"epoch": 0.21,
"learning_rate": 9.644530958923683e-05,
"loss": 1.2472,
"step": 406
},
{
"epoch": 0.21,
"learning_rate": 9.641113416234615e-05,
"loss": 1.3164,
"step": 407
},
{
"epoch": 0.21,
"learning_rate": 9.637680135030609e-05,
"loss": 1.2452,
"step": 408
},
{
"epoch": 0.21,
"learning_rate": 9.634231126954296e-05,
"loss": 1.1477,
"step": 409
},
{
"epoch": 0.22,
"learning_rate": 9.63076640370163e-05,
"loss": 1.2717,
"step": 410
},
{
"epoch": 0.22,
"learning_rate": 9.62728597702186e-05,
"loss": 1.1911,
"step": 411
},
{
"epoch": 0.22,
"learning_rate": 9.623789858717492e-05,
"loss": 1.0488,
"step": 412
},
{
"epoch": 0.22,
"learning_rate": 9.620278060644232e-05,
"loss": 1.0588,
"step": 413
},
{
"epoch": 0.22,
"learning_rate": 9.616750594710973e-05,
"loss": 1.0693,
"step": 414
},
{
"epoch": 0.22,
"learning_rate": 9.613207472879725e-05,
"loss": 1.0284,
"step": 415
},
{
"epoch": 0.22,
"learning_rate": 9.6096487071656e-05,
"loss": 1.0446,
"step": 416
},
{
"epoch": 0.22,
"learning_rate": 9.60607430963675e-05,
"loss": 1.0755,
"step": 417
},
{
"epoch": 0.22,
"learning_rate": 9.602484292414349e-05,
"loss": 1.2591,
"step": 418
},
{
"epoch": 0.22,
"learning_rate": 9.598878667672526e-05,
"loss": 1.1403,
"step": 419
},
{
"epoch": 0.22,
"learning_rate": 9.595257447638343e-05,
"loss": 1.2955,
"step": 420
},
{
"epoch": 0.22,
"learning_rate": 9.59162064459175e-05,
"loss": 1.0571,
"step": 421
},
{
"epoch": 0.22,
"learning_rate": 9.587968270865532e-05,
"loss": 1.1257,
"step": 422
},
{
"epoch": 0.22,
"learning_rate": 9.584300338845287e-05,
"loss": 1.232,
"step": 423
},
{
"epoch": 0.22,
"learning_rate": 9.580616860969364e-05,
"loss": 1.3145,
"step": 424
},
{
"epoch": 0.22,
"learning_rate": 9.576917849728834e-05,
"loss": 1.3523,
"step": 425
},
{
"epoch": 0.22,
"learning_rate": 9.573203317667442e-05,
"loss": 1.102,
"step": 426
},
{
"epoch": 0.22,
"learning_rate": 9.569473277381565e-05,
"loss": 1.1006,
"step": 427
},
{
"epoch": 0.22,
"learning_rate": 9.56572774152017e-05,
"loss": 1.3029,
"step": 428
},
{
"epoch": 0.23,
"learning_rate": 9.561966722784774e-05,
"loss": 1.1221,
"step": 429
},
{
"epoch": 0.23,
"learning_rate": 9.558190233929396e-05,
"loss": 1.1844,
"step": 430
},
{
"epoch": 0.23,
"learning_rate": 9.554398287760515e-05,
"loss": 1.0214,
"step": 431
},
{
"epoch": 0.23,
"learning_rate": 9.55059089713703e-05,
"loss": 1.191,
"step": 432
},
{
"epoch": 0.23,
"learning_rate": 9.546768074970212e-05,
"loss": 1.2985,
"step": 433
},
{
"epoch": 0.23,
"learning_rate": 9.54292983422366e-05,
"loss": 1.032,
"step": 434
},
{
"epoch": 0.23,
"learning_rate": 9.539076187913262e-05,
"loss": 1.2591,
"step": 435
},
{
"epoch": 0.23,
"learning_rate": 9.53520714910715e-05,
"loss": 1.4778,
"step": 436
},
{
"epoch": 0.23,
"learning_rate": 9.531322730925649e-05,
"loss": 1.0842,
"step": 437
},
{
"epoch": 0.23,
"learning_rate": 9.527422946541238e-05,
"loss": 1.5779,
"step": 438
},
{
"epoch": 0.23,
"learning_rate": 9.523507809178506e-05,
"loss": 1.0615,
"step": 439
},
{
"epoch": 0.23,
"learning_rate": 9.519577332114106e-05,
"loss": 1.2474,
"step": 440
},
{
"epoch": 0.23,
"learning_rate": 9.51563152867671e-05,
"loss": 1.0115,
"step": 441
},
{
"epoch": 0.23,
"learning_rate": 9.511670412246957e-05,
"loss": 1.3013,
"step": 442
},
{
"epoch": 0.23,
"learning_rate": 9.507693996257423e-05,
"loss": 1.2232,
"step": 443
},
{
"epoch": 0.23,
"learning_rate": 9.503702294192563e-05,
"loss": 1.3789,
"step": 444
},
{
"epoch": 0.23,
"learning_rate": 9.499695319588664e-05,
"loss": 0.9632,
"step": 445
},
{
"epoch": 0.23,
"learning_rate": 9.495673086033813e-05,
"loss": 1.2701,
"step": 446
},
{
"epoch": 0.23,
"learning_rate": 9.491635607167832e-05,
"loss": 0.9906,
"step": 447
},
{
"epoch": 0.24,
"learning_rate": 9.487582896682252e-05,
"loss": 1.2195,
"step": 448
},
{
"epoch": 0.24,
"learning_rate": 9.483514968320243e-05,
"loss": 1.3335,
"step": 449
},
{
"epoch": 0.24,
"learning_rate": 9.479431835876596e-05,
"loss": 1.2713,
"step": 450
},
{
"epoch": 0.24,
"learning_rate": 9.475333513197644e-05,
"loss": 1.2689,
"step": 451
},
{
"epoch": 0.24,
"learning_rate": 9.471220014181246e-05,
"loss": 1.3115,
"step": 452
},
{
"epoch": 0.24,
"learning_rate": 9.467091352776719e-05,
"loss": 1.3231,
"step": 453
},
{
"epoch": 0.24,
"learning_rate": 9.462947542984795e-05,
"loss": 1.3568,
"step": 454
},
{
"epoch": 0.24,
"learning_rate": 9.458788598857582e-05,
"loss": 1.2475,
"step": 455
},
{
"epoch": 0.24,
"learning_rate": 9.454614534498506e-05,
"loss": 1.3989,
"step": 456
},
{
"epoch": 0.24,
"learning_rate": 9.450425364062268e-05,
"loss": 1.0536,
"step": 457
},
{
"epoch": 0.24,
"learning_rate": 9.446221101754795e-05,
"loss": 0.8546,
"step": 458
},
{
"epoch": 0.24,
"learning_rate": 9.442001761833194e-05,
"loss": 1.1789,
"step": 459
},
{
"epoch": 0.24,
"learning_rate": 9.4377673586057e-05,
"loss": 1.1837,
"step": 460
},
{
"epoch": 0.24,
"learning_rate": 9.433517906431631e-05,
"loss": 1.2079,
"step": 461
},
{
"epoch": 0.24,
"learning_rate": 9.429253419721336e-05,
"loss": 1.3602,
"step": 462
},
{
"epoch": 0.24,
"learning_rate": 9.424973912936147e-05,
"loss": 1.241,
"step": 463
},
{
"epoch": 0.24,
"learning_rate": 9.420679400588334e-05,
"loss": 0.9881,
"step": 464
},
{
"epoch": 0.24,
"learning_rate": 9.416369897241048e-05,
"loss": 1.3354,
"step": 465
},
{
"epoch": 0.24,
"learning_rate": 9.412045417508282e-05,
"loss": 1.4914,
"step": 466
},
{
"epoch": 0.24,
"learning_rate": 9.407705976054809e-05,
"loss": 1.2034,
"step": 467
},
{
"epoch": 0.25,
"learning_rate": 9.403351587596141e-05,
"loss": 1.3082,
"step": 468
},
{
"epoch": 0.25,
"learning_rate": 9.398982266898481e-05,
"loss": 1.1587,
"step": 469
},
{
"epoch": 0.25,
"learning_rate": 9.394598028778662e-05,
"loss": 1.1651,
"step": 470
},
{
"epoch": 0.25,
"learning_rate": 9.390198888104112e-05,
"loss": 1.0659,
"step": 471
},
{
"epoch": 0.25,
"learning_rate": 9.385784859792788e-05,
"loss": 1.1136,
"step": 472
},
{
"epoch": 0.25,
"learning_rate": 9.381355958813133e-05,
"loss": 1.0624,
"step": 473
},
{
"epoch": 0.25,
"learning_rate": 9.376912200184029e-05,
"loss": 1.1085,
"step": 474
},
{
"epoch": 0.25,
"learning_rate": 9.372453598974738e-05,
"loss": 1.3352,
"step": 475
},
{
"epoch": 0.25,
"learning_rate": 9.367980170304857e-05,
"loss": 1.2857,
"step": 476
},
{
"epoch": 0.25,
"learning_rate": 9.363491929344266e-05,
"loss": 1.0944,
"step": 477
},
{
"epoch": 0.25,
"learning_rate": 9.35898889131307e-05,
"loss": 1.2447,
"step": 478
},
{
"epoch": 0.25,
"learning_rate": 9.354471071481557e-05,
"loss": 1.3863,
"step": 479
},
{
"epoch": 0.25,
"learning_rate": 9.349938485170139e-05,
"loss": 1.217,
"step": 480
},
{
"epoch": 0.25,
"learning_rate": 9.345391147749305e-05,
"loss": 1.1874,
"step": 481
},
{
"epoch": 0.25,
"learning_rate": 9.340829074639565e-05,
"loss": 1.1632,
"step": 482
},
{
"epoch": 0.25,
"learning_rate": 9.3362522813114e-05,
"loss": 1.3235,
"step": 483
},
{
"epoch": 0.25,
"learning_rate": 9.331660783285208e-05,
"loss": 1.2446,
"step": 484
},
{
"epoch": 0.25,
"learning_rate": 9.327054596131256e-05,
"loss": 1.3024,
"step": 485
},
{
"epoch": 0.25,
"learning_rate": 9.322433735469614e-05,
"loss": 1.3746,
"step": 486
},
{
"epoch": 0.26,
"learning_rate": 9.317798216970122e-05,
"loss": 1.1546,
"step": 487
},
{
"epoch": 0.26,
"learning_rate": 9.31314805635232e-05,
"loss": 1.3817,
"step": 488
},
{
"epoch": 0.26,
"learning_rate": 9.308483269385406e-05,
"loss": 1.1122,
"step": 489
},
{
"epoch": 0.26,
"learning_rate": 9.303803871888172e-05,
"loss": 1.452,
"step": 490
},
{
"epoch": 0.26,
"learning_rate": 9.29910987972896e-05,
"loss": 1.4635,
"step": 491
},
{
"epoch": 0.26,
"learning_rate": 9.2944013088256e-05,
"loss": 1.084,
"step": 492
},
{
"epoch": 0.26,
"learning_rate": 9.289678175145364e-05,
"loss": 1.1933,
"step": 493
},
{
"epoch": 0.26,
"learning_rate": 9.284940494704906e-05,
"loss": 1.0819,
"step": 494
},
{
"epoch": 0.26,
"learning_rate": 9.280188283570211e-05,
"loss": 1.0246,
"step": 495
},
{
"epoch": 0.26,
"learning_rate": 9.275421557856536e-05,
"loss": 1.3393,
"step": 496
},
{
"epoch": 0.26,
"learning_rate": 9.270640333728365e-05,
"loss": 1.4799,
"step": 497
},
{
"epoch": 0.26,
"learning_rate": 9.265844627399339e-05,
"loss": 1.4177,
"step": 498
},
{
"epoch": 0.26,
"learning_rate": 9.261034455132218e-05,
"loss": 1.2253,
"step": 499
},
{
"epoch": 0.26,
"learning_rate": 9.25620983323881e-05,
"loss": 1.3142,
"step": 500
},
{
"epoch": 0.26,
"learning_rate": 9.251370778079929e-05,
"loss": 1.0313,
"step": 501
},
{
"epoch": 0.26,
"learning_rate": 9.246517306065332e-05,
"loss": 1.3404,
"step": 502
},
{
"epoch": 0.26,
"learning_rate": 9.241649433653663e-05,
"loss": 1.2644,
"step": 503
},
{
"epoch": 0.26,
"learning_rate": 9.236767177352403e-05,
"loss": 1.2247,
"step": 504
},
{
"epoch": 0.26,
"learning_rate": 9.231870553717807e-05,
"loss": 1.38,
"step": 505
},
{
"epoch": 0.27,
"learning_rate": 9.226959579354855e-05,
"loss": 1.209,
"step": 506
},
{
"epoch": 0.27,
"learning_rate": 9.222034270917185e-05,
"loss": 1.2786,
"step": 507
},
{
"epoch": 0.27,
"learning_rate": 9.217094645107053e-05,
"loss": 1.1664,
"step": 508
},
{
"epoch": 0.27,
"learning_rate": 9.212140718675257e-05,
"loss": 1.0972,
"step": 509
},
{
"epoch": 0.27,
"learning_rate": 9.207172508421098e-05,
"loss": 1.3686,
"step": 510
},
{
"epoch": 0.27,
"learning_rate": 9.20219003119231e-05,
"loss": 0.9582,
"step": 511
},
{
"epoch": 0.27,
"learning_rate": 9.197193303885008e-05,
"loss": 1.124,
"step": 512
},
{
"epoch": 0.27,
"learning_rate": 9.192182343443634e-05,
"loss": 1.2647,
"step": 513
},
{
"epoch": 0.27,
"learning_rate": 9.187157166860894e-05,
"loss": 1.2692,
"step": 514
},
{
"epoch": 0.27,
"learning_rate": 9.182117791177701e-05,
"loss": 1.1562,
"step": 515
},
{
"epoch": 0.27,
"learning_rate": 9.177064233483121e-05,
"loss": 1.1139,
"step": 516
},
{
"epoch": 0.27,
"learning_rate": 9.171996510914311e-05,
"loss": 1.099,
"step": 517
},
{
"epoch": 0.27,
"learning_rate": 9.166914640656467e-05,
"loss": 1.3154,
"step": 518
},
{
"epoch": 0.27,
"learning_rate": 9.161818639942753e-05,
"loss": 1.2462,
"step": 519
},
{
"epoch": 0.27,
"learning_rate": 9.156708526054256e-05,
"loss": 1.4607,
"step": 520
},
{
"epoch": 0.27,
"learning_rate": 9.151584316319926e-05,
"loss": 1.3882,
"step": 521
},
{
"epoch": 0.27,
"learning_rate": 9.146446028116507e-05,
"loss": 1.503,
"step": 522
},
{
"epoch": 0.27,
"learning_rate": 9.141293678868487e-05,
"loss": 1.3261,
"step": 523
},
{
"epoch": 0.27,
"learning_rate": 9.136127286048038e-05,
"loss": 1.2509,
"step": 524
},
{
"epoch": 0.28,
"learning_rate": 9.130946867174952e-05,
"loss": 0.903,
"step": 525
},
{
"epoch": 0.28,
"learning_rate": 9.125752439816588e-05,
"loss": 1.0597,
"step": 526
},
{
"epoch": 0.28,
"learning_rate": 9.120544021587808e-05,
"loss": 1.086,
"step": 527
},
{
"epoch": 0.28,
"learning_rate": 9.115321630150919e-05,
"loss": 1.3303,
"step": 528
},
{
"epoch": 0.28,
"learning_rate": 9.11008528321561e-05,
"loss": 1.3007,
"step": 529
},
{
"epoch": 0.28,
"learning_rate": 9.104834998538898e-05,
"loss": 1.228,
"step": 530
},
{
"epoch": 0.28,
"learning_rate": 9.099570793925066e-05,
"loss": 1.3628,
"step": 531
},
{
"epoch": 0.28,
"learning_rate": 9.094292687225595e-05,
"loss": 1.3378,
"step": 532
},
{
"epoch": 0.28,
"learning_rate": 9.089000696339112e-05,
"loss": 1.2781,
"step": 533
},
{
"epoch": 0.28,
"learning_rate": 9.083694839211329e-05,
"loss": 1.2291,
"step": 534
},
{
"epoch": 0.28,
"learning_rate": 9.078375133834981e-05,
"loss": 1.4619,
"step": 535
},
{
"epoch": 0.28,
"learning_rate": 9.073041598249756e-05,
"loss": 1.1273,
"step": 536
},
{
"epoch": 0.28,
"learning_rate": 9.067694250542251e-05,
"loss": 1.2815,
"step": 537
},
{
"epoch": 0.28,
"learning_rate": 9.062333108845898e-05,
"loss": 0.9991,
"step": 538
},
{
"epoch": 0.28,
"learning_rate": 9.056958191340901e-05,
"loss": 1.3539,
"step": 539
},
{
"epoch": 0.28,
"learning_rate": 9.051569516254185e-05,
"loss": 1.3121,
"step": 540
},
{
"epoch": 0.28,
"learning_rate": 9.046167101859331e-05,
"loss": 1.3959,
"step": 541
},
{
"epoch": 0.28,
"learning_rate": 9.040750966476503e-05,
"loss": 1.1305,
"step": 542
},
{
"epoch": 0.28,
"learning_rate": 9.035321128472398e-05,
"loss": 1.2801,
"step": 543
},
{
"epoch": 0.29,
"learning_rate": 9.029877606260186e-05,
"loss": 1.3347,
"step": 544
},
{
"epoch": 0.29,
"learning_rate": 9.024420418299434e-05,
"loss": 1.1528,
"step": 545
},
{
"epoch": 0.29,
"learning_rate": 9.01894958309605e-05,
"loss": 1.0547,
"step": 546
},
{
"epoch": 0.29,
"learning_rate": 9.01346511920223e-05,
"loss": 1.2588,
"step": 547
},
{
"epoch": 0.29,
"learning_rate": 9.007967045216379e-05,
"loss": 1.4318,
"step": 548
},
{
"epoch": 0.29,
"learning_rate": 9.002455379783057e-05,
"loss": 0.9583,
"step": 549
},
{
"epoch": 0.29,
"learning_rate": 8.996930141592915e-05,
"loss": 1.1918,
"step": 550
},
{
"epoch": 0.29,
"learning_rate": 8.99139134938263e-05,
"loss": 1.2918,
"step": 551
},
{
"epoch": 0.29,
"learning_rate": 8.985839021934843e-05,
"loss": 1.2838,
"step": 552
},
{
"epoch": 0.29,
"learning_rate": 8.980273178078094e-05,
"loss": 1.1537,
"step": 553
},
{
"epoch": 0.29,
"learning_rate": 8.974693836686754e-05,
"loss": 1.3874,
"step": 554
},
{
"epoch": 0.29,
"learning_rate": 8.969101016680977e-05,
"loss": 1.0477,
"step": 555
},
{
"epoch": 0.29,
"learning_rate": 8.963494737026611e-05,
"loss": 1.3685,
"step": 556
},
{
"epoch": 0.29,
"learning_rate": 8.957875016735159e-05,
"loss": 1.1138,
"step": 557
},
{
"epoch": 0.29,
"learning_rate": 8.952241874863694e-05,
"loss": 1.4457,
"step": 558
},
{
"epoch": 0.29,
"learning_rate": 8.946595330514806e-05,
"loss": 1.1432,
"step": 559
},
{
"epoch": 0.29,
"learning_rate": 8.940935402836535e-05,
"loss": 1.1733,
"step": 560
},
{
"epoch": 0.29,
"learning_rate": 8.935262111022306e-05,
"loss": 1.3109,
"step": 561
},
{
"epoch": 0.29,
"learning_rate": 8.929575474310858e-05,
"loss": 1.245,
"step": 562
},
{
"epoch": 0.3,
"learning_rate": 8.923875511986193e-05,
"loss": 1.1425,
"step": 563
},
{
"epoch": 0.3,
"learning_rate": 8.918162243377493e-05,
"loss": 1.1255,
"step": 564
},
{
"epoch": 0.3,
"learning_rate": 8.912435687859068e-05,
"loss": 1.0995,
"step": 565
},
{
"epoch": 0.3,
"learning_rate": 8.906695864850284e-05,
"loss": 1.1619,
"step": 566
},
{
"epoch": 0.3,
"learning_rate": 8.900942793815498e-05,
"loss": 1.1144,
"step": 567
},
{
"epoch": 0.3,
"learning_rate": 8.895176494263992e-05,
"loss": 1.2095,
"step": 568
},
{
"epoch": 0.3,
"learning_rate": 8.88939698574991e-05,
"loss": 0.8601,
"step": 569
},
{
"epoch": 0.3,
"learning_rate": 8.883604287872184e-05,
"loss": 1.1284,
"step": 570
},
{
"epoch": 0.3,
"learning_rate": 8.87779842027448e-05,
"loss": 1.1979,
"step": 571
},
{
"epoch": 0.3,
"learning_rate": 8.871979402645116e-05,
"loss": 0.9438,
"step": 572
},
{
"epoch": 0.3,
"learning_rate": 8.86614725471701e-05,
"loss": 1.1268,
"step": 573
},
{
"epoch": 0.3,
"learning_rate": 8.860301996267602e-05,
"loss": 1.1528,
"step": 574
},
{
"epoch": 0.3,
"learning_rate": 8.85444364711879e-05,
"loss": 1.3826,
"step": 575
},
{
"epoch": 0.3,
"learning_rate": 8.848572227136868e-05,
"loss": 1.1664,
"step": 576
},
{
"epoch": 0.3,
"learning_rate": 8.842687756232454e-05,
"loss": 1.1893,
"step": 577
},
{
"epoch": 0.3,
"learning_rate": 8.836790254360421e-05,
"loss": 0.9256,
"step": 578
},
{
"epoch": 0.3,
"learning_rate": 8.830879741519832e-05,
"loss": 1.2873,
"step": 579
},
{
"epoch": 0.3,
"learning_rate": 8.824956237753872e-05,
"loss": 0.9982,
"step": 580
},
{
"epoch": 0.3,
"learning_rate": 8.81901976314978e-05,
"loss": 1.4097,
"step": 581
},
{
"epoch": 0.31,
"learning_rate": 8.81307033783878e-05,
"loss": 1.2972,
"step": 582
},
{
"epoch": 0.31,
"learning_rate": 8.807107981996013e-05,
"loss": 1.3306,
"step": 583
},
{
"epoch": 0.31,
"learning_rate": 8.80113271584047e-05,
"loss": 1.0644,
"step": 584
},
{
"epoch": 0.31,
"learning_rate": 8.79514455963492e-05,
"loss": 1.2069,
"step": 585
},
{
"epoch": 0.31,
"learning_rate": 8.789143533685846e-05,
"loss": 1.4917,
"step": 586
},
{
"epoch": 0.31,
"learning_rate": 8.783129658343374e-05,
"loss": 1.0882,
"step": 587
},
{
"epoch": 0.31,
"learning_rate": 8.7771029540012e-05,
"loss": 1.1785,
"step": 588
},
{
"epoch": 0.31,
"learning_rate": 8.771063441096526e-05,
"loss": 1.5195,
"step": 589
},
{
"epoch": 0.31,
"learning_rate": 8.765011140109994e-05,
"loss": 1.2203,
"step": 590
},
{
"epoch": 0.31,
"learning_rate": 8.758946071565603e-05,
"loss": 1.0685,
"step": 591
},
{
"epoch": 0.31,
"learning_rate": 8.752868256030658e-05,
"loss": 1.0948,
"step": 592
},
{
"epoch": 0.31,
"learning_rate": 8.74677771411568e-05,
"loss": 1.0642,
"step": 593
},
{
"epoch": 0.31,
"learning_rate": 8.740674466474356e-05,
"loss": 1.4473,
"step": 594
},
{
"epoch": 0.31,
"learning_rate": 8.734558533803456e-05,
"loss": 1.4501,
"step": 595
},
{
"epoch": 0.31,
"learning_rate": 8.728429936842762e-05,
"loss": 1.1295,
"step": 596
},
{
"epoch": 0.31,
"learning_rate": 8.722288696375009e-05,
"loss": 1.0889,
"step": 597
},
{
"epoch": 0.31,
"learning_rate": 8.716134833225802e-05,
"loss": 1.074,
"step": 598
},
{
"epoch": 0.31,
"learning_rate": 8.709968368263553e-05,
"loss": 1.2429,
"step": 599
},
{
"epoch": 0.31,
"learning_rate": 8.703789322399409e-05,
"loss": 1.0163,
"step": 600
},
{
"epoch": 0.32,
"learning_rate": 8.69759771658718e-05,
"loss": 1.0135,
"step": 601
},
{
"epoch": 0.32,
"learning_rate": 8.691393571823265e-05,
"loss": 0.9524,
"step": 602
},
{
"epoch": 0.32,
"learning_rate": 8.68517690914659e-05,
"loss": 1.1386,
"step": 603
},
{
"epoch": 0.32,
"learning_rate": 8.678947749638526e-05,
"loss": 1.2415,
"step": 604
},
{
"epoch": 0.32,
"learning_rate": 8.672706114422819e-05,
"loss": 1.2505,
"step": 605
},
{
"epoch": 0.32,
"learning_rate": 8.666452024665532e-05,
"loss": 1.129,
"step": 606
},
{
"epoch": 0.32,
"learning_rate": 8.66018550157495e-05,
"loss": 1.2245,
"step": 607
},
{
"epoch": 0.32,
"learning_rate": 8.653906566401533e-05,
"loss": 0.9779,
"step": 608
},
{
"epoch": 0.32,
"learning_rate": 8.647615240437821e-05,
"loss": 1.0941,
"step": 609
},
{
"epoch": 0.32,
"learning_rate": 8.64131154501838e-05,
"loss": 1.1956,
"step": 610
},
{
"epoch": 0.32,
"learning_rate": 8.634995501519718e-05,
"loss": 1.041,
"step": 611
},
{
"epoch": 0.32,
"learning_rate": 8.628667131360218e-05,
"loss": 1.3644,
"step": 612
},
{
"epoch": 0.32,
"learning_rate": 8.622326456000065e-05,
"loss": 1.1445,
"step": 613
},
{
"epoch": 0.32,
"learning_rate": 8.615973496941169e-05,
"loss": 0.8436,
"step": 614
},
{
"epoch": 0.32,
"learning_rate": 8.609608275727102e-05,
"loss": 1.3154,
"step": 615
},
{
"epoch": 0.32,
"learning_rate": 8.60323081394301e-05,
"loss": 1.1636,
"step": 616
},
{
"epoch": 0.32,
"learning_rate": 8.596841133215554e-05,
"loss": 1.3078,
"step": 617
},
{
"epoch": 0.32,
"learning_rate": 8.590439255212829e-05,
"loss": 1.3831,
"step": 618
},
{
"epoch": 0.32,
"learning_rate": 8.584025201644292e-05,
"loss": 1.306,
"step": 619
},
{
"epoch": 0.33,
"learning_rate": 8.577598994260688e-05,
"loss": 1.1494,
"step": 620
},
{
"epoch": 0.33,
"learning_rate": 8.571160654853975e-05,
"loss": 1.1917,
"step": 621
},
{
"epoch": 0.33,
"learning_rate": 8.56471020525726e-05,
"loss": 1.1931,
"step": 622
},
{
"epoch": 0.33,
"learning_rate": 8.55824766734471e-05,
"loss": 1.0079,
"step": 623
},
{
"epoch": 0.33,
"learning_rate": 8.551773063031484e-05,
"loss": 1.2898,
"step": 624
},
{
"epoch": 0.33,
"learning_rate": 8.545286414273664e-05,
"loss": 1.4111,
"step": 625
},
{
"epoch": 0.33,
"learning_rate": 8.538787743068171e-05,
"loss": 1.2392,
"step": 626
},
{
"epoch": 0.33,
"learning_rate": 8.532277071452704e-05,
"loss": 1.4933,
"step": 627
},
{
"epoch": 0.33,
"learning_rate": 8.525754421505646e-05,
"loss": 1.1419,
"step": 628
},
{
"epoch": 0.33,
"learning_rate": 8.519219815346004e-05,
"loss": 1.2934,
"step": 629
},
{
"epoch": 0.33,
"learning_rate": 8.512673275133334e-05,
"loss": 1.2549,
"step": 630
},
{
"epoch": 0.33,
"learning_rate": 8.506114823067657e-05,
"loss": 1.2358,
"step": 631
},
{
"epoch": 0.33,
"learning_rate": 8.49954448138939e-05,
"loss": 1.1946,
"step": 632
},
{
"epoch": 0.33,
"learning_rate": 8.492962272379267e-05,
"loss": 1.4094,
"step": 633
},
{
"epoch": 0.33,
"learning_rate": 8.486368218358268e-05,
"loss": 1.2118,
"step": 634
},
{
"epoch": 0.33,
"learning_rate": 8.479762341687541e-05,
"loss": 1.1866,
"step": 635
},
{
"epoch": 0.33,
"learning_rate": 8.473144664768321e-05,
"loss": 1.3067,
"step": 636
},
{
"epoch": 0.33,
"learning_rate": 8.466515210041865e-05,
"loss": 1.3868,
"step": 637
},
{
"epoch": 0.33,
"learning_rate": 8.459873999989367e-05,
"loss": 0.9928,
"step": 638
},
{
"epoch": 0.34,
"learning_rate": 8.453221057131886e-05,
"loss": 1.1484,
"step": 639
},
{
"epoch": 0.34,
"learning_rate": 8.446556404030264e-05,
"loss": 1.2613,
"step": 640
},
{
"epoch": 0.34,
"learning_rate": 8.43988006328506e-05,
"loss": 1.3083,
"step": 641
},
{
"epoch": 0.34,
"learning_rate": 8.433192057536458e-05,
"loss": 1.3283,
"step": 642
},
{
"epoch": 0.34,
"learning_rate": 8.426492409464213e-05,
"loss": 0.9239,
"step": 643
},
{
"epoch": 0.34,
"learning_rate": 8.419781141787548e-05,
"loss": 1.3879,
"step": 644
},
{
"epoch": 0.34,
"learning_rate": 8.413058277265093e-05,
"loss": 1.3417,
"step": 645
},
{
"epoch": 0.34,
"learning_rate": 8.406323838694808e-05,
"loss": 1.4364,
"step": 646
},
{
"epoch": 0.34,
"learning_rate": 8.399577848913895e-05,
"loss": 1.2996,
"step": 647
},
{
"epoch": 0.34,
"learning_rate": 8.392820330798733e-05,
"loss": 1.0691,
"step": 648
},
{
"epoch": 0.34,
"learning_rate": 8.386051307264797e-05,
"loss": 1.2127,
"step": 649
},
{
"epoch": 0.34,
"learning_rate": 8.379270801266568e-05,
"loss": 1.1981,
"step": 650
},
{
"epoch": 0.34,
"learning_rate": 8.372478835797473e-05,
"loss": 1.2008,
"step": 651
},
{
"epoch": 0.34,
"learning_rate": 8.365675433889799e-05,
"loss": 1.2538,
"step": 652
},
{
"epoch": 0.34,
"learning_rate": 8.358860618614612e-05,
"loss": 1.0027,
"step": 653
},
{
"epoch": 0.34,
"learning_rate": 8.352034413081686e-05,
"loss": 1.2904,
"step": 654
},
{
"epoch": 0.34,
"learning_rate": 8.345196840439416e-05,
"loss": 1.1954,
"step": 655
},
{
"epoch": 0.34,
"learning_rate": 8.338347923874749e-05,
"loss": 1.2785,
"step": 656
},
{
"epoch": 0.34,
"learning_rate": 8.331487686613097e-05,
"loss": 1.2965,
"step": 657
},
{
"epoch": 0.35,
"learning_rate": 8.324616151918261e-05,
"loss": 1.2346,
"step": 658
},
{
"epoch": 0.35,
"learning_rate": 8.317733343092357e-05,
"loss": 1.3271,
"step": 659
},
{
"epoch": 0.35,
"learning_rate": 8.31083928347573e-05,
"loss": 1.4484,
"step": 660
},
{
"epoch": 0.35,
"learning_rate": 8.303933996446876e-05,
"loss": 1.2238,
"step": 661
},
{
"epoch": 0.35,
"learning_rate": 8.297017505422367e-05,
"loss": 1.1706,
"step": 662
},
{
"epoch": 0.35,
"learning_rate": 8.290089833856769e-05,
"loss": 1.3222,
"step": 663
},
{
"epoch": 0.35,
"learning_rate": 8.28315100524256e-05,
"loss": 1.0899,
"step": 664
},
{
"epoch": 0.35,
"learning_rate": 8.276201043110057e-05,
"loss": 1.4266,
"step": 665
},
{
"epoch": 0.35,
"learning_rate": 8.269239971027328e-05,
"loss": 1.2182,
"step": 666
},
{
"epoch": 0.35,
"learning_rate": 8.262267812600115e-05,
"loss": 1.2767,
"step": 667
},
{
"epoch": 0.35,
"learning_rate": 8.255284591471762e-05,
"loss": 1.1922,
"step": 668
},
{
"epoch": 0.35,
"learning_rate": 8.24829033132312e-05,
"loss": 1.4014,
"step": 669
},
{
"epoch": 0.35,
"learning_rate": 8.241285055872478e-05,
"loss": 1.2795,
"step": 670
},
{
"epoch": 0.35,
"learning_rate": 8.234268788875479e-05,
"loss": 1.0033,
"step": 671
},
{
"epoch": 0.35,
"learning_rate": 8.22724155412504e-05,
"loss": 1.2398,
"step": 672
},
{
"epoch": 0.35,
"learning_rate": 8.220203375451269e-05,
"loss": 1.0794,
"step": 673
},
{
"epoch": 0.35,
"learning_rate": 8.213154276721388e-05,
"loss": 1.2707,
"step": 674
},
{
"epoch": 0.35,
"learning_rate": 8.20609428183965e-05,
"loss": 1.1187,
"step": 675
},
{
"epoch": 0.35,
"learning_rate": 8.199023414747256e-05,
"loss": 1.1923,
"step": 676
},
{
"epoch": 0.36,
"learning_rate": 8.191941699422276e-05,
"loss": 1.0582,
"step": 677
},
{
"epoch": 0.36,
"learning_rate": 8.184849159879571e-05,
"loss": 1.3767,
"step": 678
},
{
"epoch": 0.36,
"learning_rate": 8.177745820170705e-05,
"loss": 1.2931,
"step": 679
},
{
"epoch": 0.36,
"learning_rate": 8.170631704383866e-05,
"loss": 1.2684,
"step": 680
},
{
"epoch": 0.36,
"learning_rate": 8.163506836643786e-05,
"loss": 1.0971,
"step": 681
},
{
"epoch": 0.36,
"learning_rate": 8.15637124111166e-05,
"loss": 1.2454,
"step": 682
},
{
"epoch": 0.36,
"learning_rate": 8.149224941985058e-05,
"loss": 1.2759,
"step": 683
},
{
"epoch": 0.36,
"learning_rate": 8.142067963497851e-05,
"loss": 1.2909,
"step": 684
},
{
"epoch": 0.36,
"learning_rate": 8.134900329920121e-05,
"loss": 0.9601,
"step": 685
},
{
"epoch": 0.36,
"learning_rate": 8.127722065558087e-05,
"loss": 1.3069,
"step": 686
},
{
"epoch": 0.36,
"learning_rate": 8.120533194754014e-05,
"loss": 1.3113,
"step": 687
},
{
"epoch": 0.36,
"learning_rate": 8.113333741886138e-05,
"loss": 0.981,
"step": 688
},
{
"epoch": 0.36,
"learning_rate": 8.106123731368578e-05,
"loss": 1.0584,
"step": 689
},
{
"epoch": 0.36,
"learning_rate": 8.098903187651252e-05,
"loss": 1.3073,
"step": 690
},
{
"epoch": 0.36,
"learning_rate": 8.091672135219805e-05,
"loss": 1.3101,
"step": 691
},
{
"epoch": 0.36,
"learning_rate": 8.084430598595513e-05,
"loss": 1.0588,
"step": 692
},
{
"epoch": 0.36,
"learning_rate": 8.077178602335204e-05,
"loss": 1.1701,
"step": 693
},
{
"epoch": 0.36,
"learning_rate": 8.06991617103118e-05,
"loss": 1.0507,
"step": 694
},
{
"epoch": 0.36,
"learning_rate": 8.062643329311124e-05,
"loss": 1.1813,
"step": 695
},
{
"epoch": 0.37,
"learning_rate": 8.055360101838026e-05,
"loss": 1.2416,
"step": 696
},
{
"epoch": 0.37,
"learning_rate": 8.048066513310093e-05,
"loss": 1.2705,
"step": 697
},
{
"epoch": 0.37,
"learning_rate": 8.04076258846067e-05,
"loss": 1.119,
"step": 698
},
{
"epoch": 0.37,
"learning_rate": 8.033448352058154e-05,
"loss": 1.1883,
"step": 699
},
{
"epoch": 0.37,
"learning_rate": 8.026123828905903e-05,
"loss": 1.267,
"step": 700
},
{
"epoch": 0.37,
"learning_rate": 8.018789043842166e-05,
"loss": 1.1738,
"step": 701
},
{
"epoch": 0.37,
"learning_rate": 8.011444021739987e-05,
"loss": 1.2885,
"step": 702
},
{
"epoch": 0.37,
"learning_rate": 8.004088787507128e-05,
"loss": 1.1987,
"step": 703
},
{
"epoch": 0.37,
"learning_rate": 7.996723366085977e-05,
"loss": 1.2403,
"step": 704
},
{
"epoch": 0.37,
"learning_rate": 7.989347782453473e-05,
"loss": 0.9733,
"step": 705
},
{
"epoch": 0.37,
"learning_rate": 7.981962061621012e-05,
"loss": 1.2572,
"step": 706
},
{
"epoch": 0.37,
"learning_rate": 7.974566228634368e-05,
"loss": 1.0905,
"step": 707
},
{
"epoch": 0.37,
"learning_rate": 7.967160308573607e-05,
"loss": 1.0659,
"step": 708
},
{
"epoch": 0.37,
"learning_rate": 7.959744326553001e-05,
"loss": 1.349,
"step": 709
},
{
"epoch": 0.37,
"learning_rate": 7.952318307720943e-05,
"loss": 1.0868,
"step": 710
},
{
"epoch": 0.37,
"learning_rate": 7.94488227725986e-05,
"loss": 1.2632,
"step": 711
},
{
"epoch": 0.37,
"learning_rate": 7.937436260386134e-05,
"loss": 1.2386,
"step": 712
},
{
"epoch": 0.37,
"learning_rate": 7.929980282350008e-05,
"loss": 1.2145,
"step": 713
},
{
"epoch": 0.37,
"learning_rate": 7.922514368435505e-05,
"loss": 1.1532,
"step": 714
},
{
"epoch": 0.38,
"learning_rate": 7.915038543960342e-05,
"loss": 1.3916,
"step": 715
},
{
"epoch": 0.38,
"learning_rate": 7.907552834275847e-05,
"loss": 1.1152,
"step": 716
},
{
"epoch": 0.38,
"learning_rate": 7.900057264766865e-05,
"loss": 0.9355,
"step": 717
},
{
"epoch": 0.38,
"learning_rate": 7.892551860851679e-05,
"loss": 1.037,
"step": 718
},
{
"epoch": 0.38,
"learning_rate": 7.885036647981921e-05,
"loss": 0.9923,
"step": 719
},
{
"epoch": 0.38,
"learning_rate": 7.877511651642486e-05,
"loss": 1.2507,
"step": 720
},
{
"epoch": 0.38,
"learning_rate": 7.869976897351446e-05,
"loss": 1.256,
"step": 721
},
{
"epoch": 0.38,
"learning_rate": 7.862432410659964e-05,
"loss": 1.2936,
"step": 722
},
{
"epoch": 0.38,
"learning_rate": 7.854878217152208e-05,
"loss": 1.0659,
"step": 723
},
{
"epoch": 0.38,
"learning_rate": 7.847314342445258e-05,
"loss": 1.282,
"step": 724
},
{
"epoch": 0.38,
"learning_rate": 7.839740812189028e-05,
"loss": 1.3023,
"step": 725
},
{
"epoch": 0.38,
"learning_rate": 7.832157652066173e-05,
"loss": 1.2871,
"step": 726
},
{
"epoch": 0.38,
"learning_rate": 7.824564887792007e-05,
"loss": 1.3008,
"step": 727
},
{
"epoch": 0.38,
"learning_rate": 7.81696254511441e-05,
"loss": 1.1695,
"step": 728
},
{
"epoch": 0.38,
"learning_rate": 7.809350649813743e-05,
"loss": 1.4763,
"step": 729
},
{
"epoch": 0.38,
"learning_rate": 7.801729227702761e-05,
"loss": 1.1502,
"step": 730
},
{
"epoch": 0.38,
"learning_rate": 7.79409830462653e-05,
"loss": 1.2635,
"step": 731
},
{
"epoch": 0.38,
"learning_rate": 7.786457906462328e-05,
"loss": 1.3654,
"step": 732
},
{
"epoch": 0.38,
"learning_rate": 7.778808059119567e-05,
"loss": 1.2267,
"step": 733
},
{
"epoch": 0.39,
"learning_rate": 7.771148788539704e-05,
"loss": 1.3194,
"step": 734
},
{
"epoch": 0.39,
"learning_rate": 7.763480120696149e-05,
"loss": 1.2976,
"step": 735
},
{
"epoch": 0.39,
"learning_rate": 7.755802081594179e-05,
"loss": 0.9709,
"step": 736
},
{
"epoch": 0.39,
"learning_rate": 7.748114697270853e-05,
"loss": 1.0617,
"step": 737
},
{
"epoch": 0.39,
"learning_rate": 7.740417993794918e-05,
"loss": 1.402,
"step": 738
},
{
"epoch": 0.39,
"learning_rate": 7.732711997266719e-05,
"loss": 1.1975,
"step": 739
},
{
"epoch": 0.39,
"learning_rate": 7.724996733818124e-05,
"loss": 1.2343,
"step": 740
},
{
"epoch": 0.39,
"learning_rate": 7.71727222961242e-05,
"loss": 1.1829,
"step": 741
},
{
"epoch": 0.39,
"learning_rate": 7.709538510844233e-05,
"loss": 1.0001,
"step": 742
},
{
"epoch": 0.39,
"learning_rate": 7.701795603739435e-05,
"loss": 1.1391,
"step": 743
},
{
"epoch": 0.39,
"learning_rate": 7.694043534555055e-05,
"loss": 1.1496,
"step": 744
},
{
"epoch": 0.39,
"learning_rate": 7.686282329579196e-05,
"loss": 1.0934,
"step": 745
},
{
"epoch": 0.39,
"learning_rate": 7.678512015130937e-05,
"loss": 1.2875,
"step": 746
},
{
"epoch": 0.39,
"learning_rate": 7.670732617560253e-05,
"loss": 1.2206,
"step": 747
},
{
"epoch": 0.39,
"learning_rate": 7.662944163247916e-05,
"loss": 1.2561,
"step": 748
},
{
"epoch": 0.39,
"learning_rate": 7.655146678605414e-05,
"loss": 1.213,
"step": 749
},
{
"epoch": 0.39,
"learning_rate": 7.647340190074855e-05,
"loss": 1.2487,
"step": 750
},
{
"epoch": 0.39,
"learning_rate": 7.63952472412888e-05,
"loss": 1.1735,
"step": 751
},
{
"epoch": 0.39,
"learning_rate": 7.63170030727058e-05,
"loss": 1.3249,
"step": 752
},
{
"epoch": 0.4,
"learning_rate": 7.623866966033391e-05,
"loss": 1.3793,
"step": 753
},
{
"epoch": 0.4,
"learning_rate": 7.616024726981015e-05,
"loss": 1.1992,
"step": 754
},
{
"epoch": 0.4,
"learning_rate": 7.60817361670733e-05,
"loss": 1.4108,
"step": 755
},
{
"epoch": 0.4,
"learning_rate": 7.600313661836298e-05,
"loss": 1.106,
"step": 756
},
{
"epoch": 0.4,
"learning_rate": 7.592444889021866e-05,
"loss": 1.2202,
"step": 757
},
{
"epoch": 0.4,
"learning_rate": 7.584567324947893e-05,
"loss": 1.461,
"step": 758
},
{
"epoch": 0.4,
"learning_rate": 7.576680996328045e-05,
"loss": 1.2801,
"step": 759
},
{
"epoch": 0.4,
"learning_rate": 7.568785929905713e-05,
"loss": 1.4448,
"step": 760
},
{
"epoch": 0.4,
"learning_rate": 7.560882152453914e-05,
"loss": 1.075,
"step": 761
},
{
"epoch": 0.4,
"learning_rate": 7.552969690775209e-05,
"loss": 0.9568,
"step": 762
},
{
"epoch": 0.4,
"learning_rate": 7.545048571701605e-05,
"loss": 1.1432,
"step": 763
},
{
"epoch": 0.4,
"learning_rate": 7.537118822094474e-05,
"loss": 1.3191,
"step": 764
},
{
"epoch": 0.4,
"learning_rate": 7.529180468844444e-05,
"loss": 1.2781,
"step": 765
},
{
"epoch": 0.4,
"learning_rate": 7.521233538871329e-05,
"loss": 1.2839,
"step": 766
},
{
"epoch": 0.4,
"learning_rate": 7.513278059124022e-05,
"loss": 1.3867,
"step": 767
},
{
"epoch": 0.4,
"learning_rate": 7.50531405658041e-05,
"loss": 1.2937,
"step": 768
},
{
"epoch": 0.4,
"learning_rate": 7.497341558247286e-05,
"loss": 1.3274,
"step": 769
},
{
"epoch": 0.4,
"learning_rate": 7.489360591160244e-05,
"loss": 1.2399,
"step": 770
},
{
"epoch": 0.4,
"learning_rate": 7.481371182383607e-05,
"loss": 1.1877,
"step": 771
},
{
"epoch": 0.4,
"learning_rate": 7.473373359010318e-05,
"loss": 1.0751,
"step": 772
},
{
"epoch": 0.41,
"learning_rate": 7.465367148161856e-05,
"loss": 1.3145,
"step": 773
},
{
"epoch": 0.41,
"learning_rate": 7.457352576988144e-05,
"loss": 1.0667,
"step": 774
},
{
"epoch": 0.41,
"learning_rate": 7.449329672667456e-05,
"loss": 1.176,
"step": 775
},
{
"epoch": 0.41,
"learning_rate": 7.441298462406321e-05,
"loss": 1.2446,
"step": 776
},
{
"epoch": 0.41,
"learning_rate": 7.43325897343944e-05,
"loss": 1.095,
"step": 777
},
{
"epoch": 0.41,
"learning_rate": 7.425211233029583e-05,
"loss": 1.4673,
"step": 778
},
{
"epoch": 0.41,
"learning_rate": 7.417155268467505e-05,
"loss": 1.389,
"step": 779
},
{
"epoch": 0.41,
"learning_rate": 7.409091107071848e-05,
"loss": 1.1901,
"step": 780
},
{
"epoch": 0.41,
"learning_rate": 7.40101877618905e-05,
"loss": 1.1656,
"step": 781
},
{
"epoch": 0.41,
"learning_rate": 7.392938303193256e-05,
"loss": 1.276,
"step": 782
},
{
"epoch": 0.41,
"learning_rate": 7.384849715486217e-05,
"loss": 1.116,
"step": 783
},
{
"epoch": 0.41,
"learning_rate": 7.376753040497206e-05,
"loss": 1.1236,
"step": 784
},
{
"epoch": 0.41,
"learning_rate": 7.368648305682917e-05,
"loss": 1.1392,
"step": 785
},
{
"epoch": 0.41,
"learning_rate": 7.36053553852738e-05,
"loss": 1.1715,
"step": 786
},
{
"epoch": 0.41,
"learning_rate": 7.352414766541859e-05,
"loss": 1.3388,
"step": 787
},
{
"epoch": 0.41,
"learning_rate": 7.344286017264765e-05,
"loss": 1.2815,
"step": 788
},
{
"epoch": 0.41,
"learning_rate": 7.336149318261565e-05,
"loss": 1.2,
"step": 789
},
{
"epoch": 0.41,
"learning_rate": 7.328004697124679e-05,
"loss": 1.0053,
"step": 790
},
{
"epoch": 0.41,
"learning_rate": 7.319852181473393e-05,
"loss": 1.3813,
"step": 791
},
{
"epoch": 0.42,
"learning_rate": 7.311691798953765e-05,
"loss": 1.1228,
"step": 792
},
{
"epoch": 0.42,
"learning_rate": 7.303523577238529e-05,
"loss": 1.1688,
"step": 793
},
{
"epoch": 0.42,
"learning_rate": 7.295347544027006e-05,
"loss": 1.153,
"step": 794
},
{
"epoch": 0.42,
"learning_rate": 7.287163727045001e-05,
"loss": 1.2582,
"step": 795
},
{
"epoch": 0.42,
"learning_rate": 7.278972154044722e-05,
"loss": 1.2573,
"step": 796
},
{
"epoch": 0.42,
"learning_rate": 7.270772852804672e-05,
"loss": 1.1999,
"step": 797
},
{
"epoch": 0.42,
"learning_rate": 7.262565851129564e-05,
"loss": 1.377,
"step": 798
},
{
"epoch": 0.42,
"learning_rate": 7.254351176850222e-05,
"loss": 1.1847,
"step": 799
},
{
"epoch": 0.42,
"learning_rate": 7.246128857823495e-05,
"loss": 1.3181,
"step": 800
},
{
"epoch": 0.42,
"learning_rate": 7.237898921932146e-05,
"loss": 1.037,
"step": 801
},
{
"epoch": 0.42,
"learning_rate": 7.229661397084776e-05,
"loss": 1.4083,
"step": 802
},
{
"epoch": 0.42,
"learning_rate": 7.221416311215717e-05,
"loss": 1.2283,
"step": 803
},
{
"epoch": 0.42,
"learning_rate": 7.213163692284943e-05,
"loss": 1.1925,
"step": 804
},
{
"epoch": 0.42,
"learning_rate": 7.204903568277974e-05,
"loss": 1.2007,
"step": 805
},
{
"epoch": 0.42,
"learning_rate": 7.196635967205776e-05,
"loss": 1.1356,
"step": 806
},
{
"epoch": 0.42,
"learning_rate": 7.188360917104677e-05,
"loss": 1.1845,
"step": 807
},
{
"epoch": 0.42,
"learning_rate": 7.180078446036259e-05,
"loss": 1.2703,
"step": 808
},
{
"epoch": 0.42,
"learning_rate": 7.171788582087277e-05,
"loss": 1.2917,
"step": 809
},
{
"epoch": 0.42,
"learning_rate": 7.163491353369545e-05,
"loss": 1.226,
"step": 810
},
{
"epoch": 0.43,
"learning_rate": 7.155186788019864e-05,
"loss": 1.3631,
"step": 811
},
{
"epoch": 0.43,
"learning_rate": 7.146874914199906e-05,
"loss": 1.3167,
"step": 812
},
{
"epoch": 0.43,
"learning_rate": 7.13855576009613e-05,
"loss": 1.0606,
"step": 813
},
{
"epoch": 0.43,
"learning_rate": 7.130229353919684e-05,
"loss": 1.061,
"step": 814
},
{
"epoch": 0.43,
"learning_rate": 7.121895723906306e-05,
"loss": 1.2346,
"step": 815
},
{
"epoch": 0.43,
"learning_rate": 7.11355489831623e-05,
"loss": 1.3658,
"step": 816
},
{
"epoch": 0.43,
"learning_rate": 7.105206905434096e-05,
"loss": 1.0964,
"step": 817
},
{
"epoch": 0.43,
"learning_rate": 7.096851773568844e-05,
"loss": 1.134,
"step": 818
},
{
"epoch": 0.43,
"learning_rate": 7.088489531053627e-05,
"loss": 1.1763,
"step": 819
},
{
"epoch": 0.43,
"learning_rate": 7.080120206245709e-05,
"loss": 1.2423,
"step": 820
},
{
"epoch": 0.43,
"learning_rate": 7.071743827526366e-05,
"loss": 1.2917,
"step": 821
},
{
"epoch": 0.43,
"learning_rate": 7.063360423300808e-05,
"loss": 1.2818,
"step": 822
},
{
"epoch": 0.43,
"learning_rate": 7.054970021998053e-05,
"loss": 1.1765,
"step": 823
},
{
"epoch": 0.43,
"learning_rate": 7.04657265207086e-05,
"loss": 1.3552,
"step": 824
},
{
"epoch": 0.43,
"learning_rate": 7.038168341995609e-05,
"loss": 1.2988,
"step": 825
},
{
"epoch": 0.43,
"learning_rate": 7.029757120272223e-05,
"loss": 1.3411,
"step": 826
},
{
"epoch": 0.43,
"learning_rate": 7.02133901542406e-05,
"loss": 0.9321,
"step": 827
},
{
"epoch": 0.43,
"learning_rate": 7.012914055997817e-05,
"loss": 1.1216,
"step": 828
},
{
"epoch": 0.43,
"learning_rate": 7.004482270563441e-05,
"loss": 1.3039,
"step": 829
},
{
"epoch": 0.44,
"learning_rate": 6.99604368771402e-05,
"loss": 1.1697,
"step": 830
},
{
"epoch": 0.44,
"learning_rate": 6.9875983360657e-05,
"loss": 1.2737,
"step": 831
},
{
"epoch": 0.44,
"learning_rate": 6.979146244257572e-05,
"loss": 1.2087,
"step": 832
},
{
"epoch": 0.44,
"learning_rate": 6.970687440951593e-05,
"loss": 1.2569,
"step": 833
},
{
"epoch": 0.44,
"learning_rate": 6.962221954832476e-05,
"loss": 1.4302,
"step": 834
},
{
"epoch": 0.44,
"learning_rate": 6.953749814607592e-05,
"loss": 1.2295,
"step": 835
},
{
"epoch": 0.44,
"learning_rate": 6.945271049006882e-05,
"loss": 1.2631,
"step": 836
},
{
"epoch": 0.44,
"learning_rate": 6.936785686782751e-05,
"loss": 1.1279,
"step": 837
},
{
"epoch": 0.44,
"learning_rate": 6.928293756709975e-05,
"loss": 1.184,
"step": 838
},
{
"epoch": 0.44,
"learning_rate": 6.919795287585604e-05,
"loss": 1.1165,
"step": 839
},
{
"epoch": 0.44,
"learning_rate": 6.911290308228861e-05,
"loss": 0.9758,
"step": 840
},
{
"epoch": 0.44,
"learning_rate": 6.902778847481046e-05,
"loss": 1.233,
"step": 841
},
{
"epoch": 0.44,
"learning_rate": 6.894260934205437e-05,
"loss": 1.3657,
"step": 842
},
{
"epoch": 0.44,
"learning_rate": 6.885736597287194e-05,
"loss": 1.2249,
"step": 843
},
{
"epoch": 0.44,
"learning_rate": 6.877205865633262e-05,
"loss": 1.1283,
"step": 844
},
{
"epoch": 0.44,
"learning_rate": 6.868668768172272e-05,
"loss": 1.1403,
"step": 845
},
{
"epoch": 0.44,
"learning_rate": 6.860125333854437e-05,
"loss": 1.2103,
"step": 846
},
{
"epoch": 0.44,
"learning_rate": 6.851575591651461e-05,
"loss": 1.0768,
"step": 847
},
{
"epoch": 0.44,
"learning_rate": 6.843019570556443e-05,
"loss": 1.1469,
"step": 848
},
{
"epoch": 0.45,
"learning_rate": 6.834457299583768e-05,
"loss": 1.2445,
"step": 849
},
{
"epoch": 0.45,
"learning_rate": 6.82588880776902e-05,
"loss": 1.2965,
"step": 850
},
{
"epoch": 0.45,
"learning_rate": 6.817314124168877e-05,
"loss": 1.2222,
"step": 851
},
{
"epoch": 0.45,
"learning_rate": 6.808733277861012e-05,
"loss": 1.252,
"step": 852
},
{
"epoch": 0.45,
"learning_rate": 6.800146297943998e-05,
"loss": 1.2799,
"step": 853
},
{
"epoch": 0.45,
"learning_rate": 6.791553213537209e-05,
"loss": 1.2599,
"step": 854
},
{
"epoch": 0.45,
"learning_rate": 6.782954053780719e-05,
"loss": 1.0473,
"step": 855
},
{
"epoch": 0.45,
"learning_rate": 6.774348847835202e-05,
"loss": 1.0644,
"step": 856
},
{
"epoch": 0.45,
"learning_rate": 6.765737624881839e-05,
"loss": 1.3575,
"step": 857
},
{
"epoch": 0.45,
"learning_rate": 6.757120414122214e-05,
"loss": 0.8829,
"step": 858
},
{
"epoch": 0.45,
"learning_rate": 6.748497244778214e-05,
"loss": 1.2545,
"step": 859
},
{
"epoch": 0.45,
"learning_rate": 6.739868146091934e-05,
"loss": 1.3259,
"step": 860
},
{
"epoch": 0.45,
"learning_rate": 6.731233147325578e-05,
"loss": 1.0904,
"step": 861
},
{
"epoch": 0.45,
"learning_rate": 6.722592277761355e-05,
"loss": 1.1134,
"step": 862
},
{
"epoch": 0.45,
"learning_rate": 6.713945566701383e-05,
"loss": 1.1543,
"step": 863
},
{
"epoch": 0.45,
"learning_rate": 6.705293043467589e-05,
"loss": 1.0005,
"step": 864
},
{
"epoch": 0.45,
"learning_rate": 6.69663473740161e-05,
"loss": 1.3961,
"step": 865
},
{
"epoch": 0.45,
"learning_rate": 6.687970677864696e-05,
"loss": 1.0416,
"step": 866
},
{
"epoch": 0.45,
"learning_rate": 6.679300894237602e-05,
"loss": 1.1632,
"step": 867
},
{
"epoch": 0.46,
"learning_rate": 6.670625415920499e-05,
"loss": 1.08,
"step": 868
},
{
"epoch": 0.46,
"learning_rate": 6.661944272332867e-05,
"loss": 1.2152,
"step": 869
},
{
"epoch": 0.46,
"learning_rate": 6.653257492913397e-05,
"loss": 1.2323,
"step": 870
},
{
"epoch": 0.46,
"learning_rate": 6.644565107119894e-05,
"loss": 0.9387,
"step": 871
},
{
"epoch": 0.46,
"learning_rate": 6.635867144429173e-05,
"loss": 1.1786,
"step": 872
},
{
"epoch": 0.46,
"learning_rate": 6.62716363433696e-05,
"loss": 1.1721,
"step": 873
},
{
"epoch": 0.46,
"learning_rate": 6.618454606357796e-05,
"loss": 1.1166,
"step": 874
},
{
"epoch": 0.46,
"learning_rate": 6.60974009002493e-05,
"loss": 1.3361,
"step": 875
},
{
"epoch": 0.46,
"learning_rate": 6.601020114890228e-05,
"loss": 1.1175,
"step": 876
},
{
"epoch": 0.46,
"learning_rate": 6.592294710524058e-05,
"loss": 1.1079,
"step": 877
},
{
"epoch": 0.46,
"learning_rate": 6.58356390651521e-05,
"loss": 1.2961,
"step": 878
},
{
"epoch": 0.46,
"learning_rate": 6.574827732470779e-05,
"loss": 1.2133,
"step": 879
},
{
"epoch": 0.46,
"learning_rate": 6.56608621801607e-05,
"loss": 1.0169,
"step": 880
},
{
"epoch": 0.46,
"learning_rate": 6.5573393927945e-05,
"loss": 1.2873,
"step": 881
},
{
"epoch": 0.46,
"learning_rate": 6.548587286467491e-05,
"loss": 1.1346,
"step": 882
},
{
"epoch": 0.46,
"learning_rate": 6.539829928714383e-05,
"loss": 1.168,
"step": 883
},
{
"epoch": 0.46,
"learning_rate": 6.531067349232313e-05,
"loss": 1.0916,
"step": 884
},
{
"epoch": 0.46,
"learning_rate": 6.522299577736133e-05,
"loss": 1.2535,
"step": 885
},
{
"epoch": 0.46,
"learning_rate": 6.513526643958301e-05,
"loss": 1.2332,
"step": 886
},
{
"epoch": 0.47,
"learning_rate": 6.504748577648778e-05,
"loss": 1.1259,
"step": 887
},
{
"epoch": 0.47,
"learning_rate": 6.49596540857493e-05,
"loss": 1.1833,
"step": 888
},
{
"epoch": 0.47,
"learning_rate": 6.48717716652143e-05,
"loss": 1.1894,
"step": 889
},
{
"epoch": 0.47,
"learning_rate": 6.478383881290152e-05,
"loss": 1.1131,
"step": 890
},
{
"epoch": 0.47,
"learning_rate": 6.469585582700071e-05,
"loss": 1.2203,
"step": 891
},
{
"epoch": 0.47,
"learning_rate": 6.460782300587166e-05,
"loss": 1.3577,
"step": 892
},
{
"epoch": 0.47,
"learning_rate": 6.451974064804312e-05,
"loss": 1.2248,
"step": 893
},
{
"epoch": 0.47,
"learning_rate": 6.443160905221187e-05,
"loss": 1.3831,
"step": 894
},
{
"epoch": 0.47,
"learning_rate": 6.43434285172416e-05,
"loss": 1.2409,
"step": 895
},
{
"epoch": 0.47,
"learning_rate": 6.425519934216203e-05,
"loss": 1.3693,
"step": 896
},
{
"epoch": 0.47,
"learning_rate": 6.416692182616775e-05,
"loss": 1.1685,
"step": 897
},
{
"epoch": 0.47,
"learning_rate": 6.407859626861735e-05,
"loss": 1.2228,
"step": 898
},
{
"epoch": 0.47,
"learning_rate": 6.399022296903224e-05,
"loss": 1.0375,
"step": 899
},
{
"epoch": 0.47,
"learning_rate": 6.390180222709583e-05,
"loss": 0.9321,
"step": 900
},
{
"epoch": 0.47,
"learning_rate": 6.381333434265238e-05,
"loss": 1.2262,
"step": 901
},
{
"epoch": 0.47,
"learning_rate": 6.372481961570597e-05,
"loss": 1.1371,
"step": 902
},
{
"epoch": 0.47,
"learning_rate": 6.363625834641959e-05,
"loss": 1.1375,
"step": 903
},
{
"epoch": 0.47,
"learning_rate": 6.354765083511401e-05,
"loss": 1.2385,
"step": 904
},
{
"epoch": 0.47,
"learning_rate": 6.345899738226687e-05,
"loss": 1.2664,
"step": 905
},
{
"epoch": 0.48,
"learning_rate": 6.337029828851151e-05,
"loss": 1.3064,
"step": 906
},
{
"epoch": 0.48,
"learning_rate": 6.328155385463615e-05,
"loss": 1.0658,
"step": 907
},
{
"epoch": 0.48,
"learning_rate": 6.31927643815827e-05,
"loss": 1.0843,
"step": 908
},
{
"epoch": 0.48,
"learning_rate": 6.310393017044582e-05,
"loss": 1.1444,
"step": 909
},
{
"epoch": 0.48,
"learning_rate": 6.301505152247184e-05,
"loss": 1.2787,
"step": 910
},
{
"epoch": 0.48,
"learning_rate": 6.292612873905788e-05,
"loss": 1.3589,
"step": 911
},
{
"epoch": 0.48,
"learning_rate": 6.283716212175062e-05,
"loss": 1.3724,
"step": 912
},
{
"epoch": 0.48,
"learning_rate": 6.274815197224545e-05,
"loss": 1.1862,
"step": 913
},
{
"epoch": 0.48,
"learning_rate": 6.265909859238535e-05,
"loss": 1.2664,
"step": 914
},
{
"epoch": 0.48,
"learning_rate": 6.257000228415994e-05,
"loss": 1.0545,
"step": 915
},
{
"epoch": 0.48,
"learning_rate": 6.248086334970435e-05,
"loss": 1.3467,
"step": 916
},
{
"epoch": 0.48,
"learning_rate": 6.239168209129833e-05,
"loss": 1.4016,
"step": 917
},
{
"epoch": 0.48,
"learning_rate": 6.230245881136508e-05,
"loss": 1.4289,
"step": 918
},
{
"epoch": 0.48,
"learning_rate": 6.22131938124704e-05,
"loss": 1.3223,
"step": 919
},
{
"epoch": 0.48,
"learning_rate": 6.212388739732145e-05,
"loss": 1.4146,
"step": 920
},
{
"epoch": 0.48,
"learning_rate": 6.203453986876594e-05,
"loss": 1.1499,
"step": 921
},
{
"epoch": 0.48,
"learning_rate": 6.194515152979093e-05,
"loss": 1.2879,
"step": 922
},
{
"epoch": 0.48,
"learning_rate": 6.185572268352187e-05,
"loss": 1.0874,
"step": 923
},
{
"epoch": 0.48,
"learning_rate": 6.176625363322163e-05,
"loss": 1.2427,
"step": 924
},
{
"epoch": 0.49,
"learning_rate": 6.167674468228941e-05,
"loss": 1.3649,
"step": 925
},
{
"epoch": 0.49,
"learning_rate": 6.158719613425964e-05,
"loss": 1.2718,
"step": 926
},
{
"epoch": 0.49,
"learning_rate": 6.14976082928011e-05,
"loss": 1.3047,
"step": 927
},
{
"epoch": 0.49,
"learning_rate": 6.140798146171582e-05,
"loss": 1.3723,
"step": 928
},
{
"epoch": 0.49,
"learning_rate": 6.131831594493799e-05,
"loss": 1.2044,
"step": 929
},
{
"epoch": 0.49,
"learning_rate": 6.122861204653303e-05,
"loss": 1.3015,
"step": 930
},
{
"epoch": 0.49,
"learning_rate": 6.113887007069656e-05,
"loss": 1.052,
"step": 931
},
{
"epoch": 0.49,
"learning_rate": 6.104909032175323e-05,
"loss": 1.3608,
"step": 932
},
{
"epoch": 0.49,
"learning_rate": 6.095927310415584e-05,
"loss": 1.1729,
"step": 933
},
{
"epoch": 0.49,
"learning_rate": 6.086941872248424e-05,
"loss": 1.1226,
"step": 934
},
{
"epoch": 0.49,
"learning_rate": 6.07795274814443e-05,
"loss": 1.2384,
"step": 935
},
{
"epoch": 0.49,
"learning_rate": 6.068959968586689e-05,
"loss": 1.2275,
"step": 936
},
{
"epoch": 0.49,
"learning_rate": 6.059963564070683e-05,
"loss": 1.1939,
"step": 937
},
{
"epoch": 0.49,
"learning_rate": 6.050963565104191e-05,
"loss": 1.293,
"step": 938
},
{
"epoch": 0.49,
"learning_rate": 6.041960002207174e-05,
"loss": 0.9448,
"step": 939
},
{
"epoch": 0.49,
"learning_rate": 6.032952905911686e-05,
"loss": 1.259,
"step": 940
},
{
"epoch": 0.49,
"learning_rate": 6.023942306761757e-05,
"loss": 1.3718,
"step": 941
},
{
"epoch": 0.49,
"learning_rate": 6.014928235313301e-05,
"loss": 1.3526,
"step": 942
},
{
"epoch": 0.49,
"learning_rate": 6.0059107221340004e-05,
"loss": 0.7851,
"step": 943
},
{
"epoch": 0.5,
"learning_rate": 5.9968897978032135e-05,
"loss": 1.3295,
"step": 944
},
{
"epoch": 0.5,
"learning_rate": 5.987865492911866e-05,
"loss": 1.4182,
"step": 945
},
{
"epoch": 0.5,
"learning_rate": 5.9788378380623475e-05,
"loss": 1.3184,
"step": 946
},
{
"epoch": 0.5,
"learning_rate": 5.969806863868407e-05,
"loss": 1.2503,
"step": 947
},
{
"epoch": 0.5,
"learning_rate": 5.960772600955049e-05,
"loss": 1.0603,
"step": 948
},
{
"epoch": 0.5,
"learning_rate": 5.9517350799584307e-05,
"loss": 1.1791,
"step": 949
},
{
"epoch": 0.5,
"learning_rate": 5.9426943315257575e-05,
"loss": 1.3167,
"step": 950
},
{
"epoch": 0.5,
"learning_rate": 5.933650386315183e-05,
"loss": 1.4345,
"step": 951
},
{
"epoch": 0.5,
"learning_rate": 5.924603274995692e-05,
"loss": 1.0739,
"step": 952
},
{
"epoch": 0.5,
"learning_rate": 5.915553028247021e-05,
"loss": 1.1927,
"step": 953
},
{
"epoch": 0.5,
"learning_rate": 5.9064996767595236e-05,
"loss": 1.182,
"step": 954
},
{
"epoch": 0.5,
"learning_rate": 5.8974432512340926e-05,
"loss": 1.0244,
"step": 955
},
{
"epoch": 0.5,
"learning_rate": 5.88838378238204e-05,
"loss": 1.3127,
"step": 956
},
{
"epoch": 0.5,
"learning_rate": 5.879321300924999e-05,
"loss": 1.2116,
"step": 957
},
{
"epoch": 0.5,
"learning_rate": 5.87025583759482e-05,
"loss": 1.3396,
"step": 958
},
{
"epoch": 0.5,
"learning_rate": 5.861187423133464e-05,
"loss": 1.1122,
"step": 959
},
{
"epoch": 0.5,
"learning_rate": 5.8521160882929006e-05,
"loss": 1.0469,
"step": 960
},
{
"epoch": 0.5,
"learning_rate": 5.843041863835003e-05,
"loss": 1.3309,
"step": 961
},
{
"epoch": 0.5,
"learning_rate": 5.83396478053144e-05,
"loss": 1.2289,
"step": 962
},
{
"epoch": 0.51,
"learning_rate": 5.82488486916358e-05,
"loss": 1.2619,
"step": 963
},
{
"epoch": 0.51,
"learning_rate": 5.815802160522379e-05,
"loss": 1.189,
"step": 964
},
{
"epoch": 0.51,
"learning_rate": 5.8067166854082774e-05,
"loss": 1.3728,
"step": 965
},
{
"epoch": 0.51,
"learning_rate": 5.797628474631102e-05,
"loss": 1.2453,
"step": 966
},
{
"epoch": 0.51,
"learning_rate": 5.7885375590099514e-05,
"loss": 1.3382,
"step": 967
},
{
"epoch": 0.51,
"learning_rate": 5.779443969373097e-05,
"loss": 1.2999,
"step": 968
},
{
"epoch": 0.51,
"learning_rate": 5.770347736557884e-05,
"loss": 1.4029,
"step": 969
},
{
"epoch": 0.51,
"learning_rate": 5.761248891410613e-05,
"loss": 1.2411,
"step": 970
},
{
"epoch": 0.51,
"learning_rate": 5.752147464786448e-05,
"loss": 1.2294,
"step": 971
},
{
"epoch": 0.51,
"learning_rate": 5.7430434875493056e-05,
"loss": 1.1427,
"step": 972
},
{
"epoch": 0.51,
"learning_rate": 5.733936990571752e-05,
"loss": 1.2474,
"step": 973
},
{
"epoch": 0.51,
"learning_rate": 5.724828004734899e-05,
"loss": 1.1501,
"step": 974
},
{
"epoch": 0.51,
"learning_rate": 5.715716560928297e-05,
"loss": 1.0521,
"step": 975
},
{
"epoch": 0.51,
"learning_rate": 5.7066026900498314e-05,
"loss": 1.2757,
"step": 976
},
{
"epoch": 0.51,
"learning_rate": 5.697486423005621e-05,
"loss": 1.363,
"step": 977
},
{
"epoch": 0.51,
"learning_rate": 5.6883677907099085e-05,
"loss": 1.0824,
"step": 978
},
{
"epoch": 0.51,
"learning_rate": 5.679246824084955e-05,
"loss": 1.2215,
"step": 979
},
{
"epoch": 0.51,
"learning_rate": 5.67012355406094e-05,
"loss": 1.1607,
"step": 980
},
{
"epoch": 0.51,
"learning_rate": 5.660998011575853e-05,
"loss": 1.1333,
"step": 981
},
{
"epoch": 0.52,
"learning_rate": 5.651870227575391e-05,
"loss": 1.065,
"step": 982
},
{
"epoch": 0.52,
"learning_rate": 5.642740233012853e-05,
"loss": 1.1918,
"step": 983
},
{
"epoch": 0.52,
"learning_rate": 5.6336080588490326e-05,
"loss": 1.1603,
"step": 984
},
{
"epoch": 0.52,
"learning_rate": 5.624473736052114e-05,
"loss": 1.051,
"step": 985
},
{
"epoch": 0.52,
"learning_rate": 5.615337295597569e-05,
"loss": 1.5568,
"step": 986
},
{
"epoch": 0.52,
"learning_rate": 5.6061987684680506e-05,
"loss": 1.2837,
"step": 987
},
{
"epoch": 0.52,
"learning_rate": 5.5970581856532866e-05,
"loss": 1.1235,
"step": 988
},
{
"epoch": 0.52,
"learning_rate": 5.587915578149976e-05,
"loss": 1.0204,
"step": 989
},
{
"epoch": 0.52,
"learning_rate": 5.5787709769616846e-05,
"loss": 1.2447,
"step": 990
},
{
"epoch": 0.52,
"learning_rate": 5.5696244130987415e-05,
"loss": 1.4469,
"step": 991
},
{
"epoch": 0.52,
"learning_rate": 5.5604759175781286e-05,
"loss": 1.3223,
"step": 992
},
{
"epoch": 0.52,
"learning_rate": 5.551325521423375e-05,
"loss": 1.1734,
"step": 993
},
{
"epoch": 0.52,
"learning_rate": 5.542173255664462e-05,
"loss": 1.2144,
"step": 994
},
{
"epoch": 0.52,
"learning_rate": 5.5330191513377064e-05,
"loss": 1.3377,
"step": 995
},
{
"epoch": 0.52,
"learning_rate": 5.52386323948566e-05,
"loss": 1.0928,
"step": 996
},
{
"epoch": 0.52,
"learning_rate": 5.514705551157006e-05,
"loss": 1.1444,
"step": 997
},
{
"epoch": 0.52,
"learning_rate": 5.505546117406449e-05,
"loss": 1.2559,
"step": 998
},
{
"epoch": 0.52,
"learning_rate": 5.4963849692946166e-05,
"loss": 1.1396,
"step": 999
},
{
"epoch": 0.52,
"learning_rate": 5.487222137887949e-05,
"loss": 1.3016,
"step": 1000
},
{
"epoch": 0.53,
"learning_rate": 5.4780576542585883e-05,
"loss": 1.3395,
"step": 1001
},
{
"epoch": 0.53,
"learning_rate": 5.468891549484289e-05,
"loss": 1.0733,
"step": 1002
},
{
"epoch": 0.53,
"learning_rate": 5.459723854648297e-05,
"loss": 1.1816,
"step": 1003
},
{
"epoch": 0.53,
"learning_rate": 5.4505546008392505e-05,
"loss": 1.0665,
"step": 1004
},
{
"epoch": 0.53,
"learning_rate": 5.441383819151078e-05,
"loss": 1.2515,
"step": 1005
},
{
"epoch": 0.53,
"learning_rate": 5.432211540682887e-05,
"loss": 1.2566,
"step": 1006
},
{
"epoch": 0.53,
"learning_rate": 5.423037796538858e-05,
"loss": 1.0183,
"step": 1007
},
{
"epoch": 0.53,
"learning_rate": 5.413862617828147e-05,
"loss": 1.2808,
"step": 1008
},
{
"epoch": 0.53,
"learning_rate": 5.40468603566477e-05,
"loss": 1.062,
"step": 1009
},
{
"epoch": 0.53,
"learning_rate": 5.395508081167506e-05,
"loss": 1.0936,
"step": 1010
},
{
"epoch": 0.53,
"learning_rate": 5.386328785459787e-05,
"loss": 1.1886,
"step": 1011
},
{
"epoch": 0.53,
"learning_rate": 5.37714817966959e-05,
"loss": 1.41,
"step": 1012
},
{
"epoch": 0.53,
"learning_rate": 5.367966294929336e-05,
"loss": 0.9884,
"step": 1013
},
{
"epoch": 0.53,
"learning_rate": 5.35878316237579e-05,
"loss": 1.1373,
"step": 1014
},
{
"epoch": 0.53,
"learning_rate": 5.349598813149936e-05,
"loss": 1.1247,
"step": 1015
},
{
"epoch": 0.53,
"learning_rate": 5.340413278396895e-05,
"loss": 1.2176,
"step": 1016
},
{
"epoch": 0.53,
"learning_rate": 5.331226589265801e-05,
"loss": 1.1515,
"step": 1017
},
{
"epoch": 0.53,
"learning_rate": 5.322038776909705e-05,
"loss": 1.2422,
"step": 1018
},
{
"epoch": 0.53,
"learning_rate": 5.312849872485468e-05,
"loss": 1.504,
"step": 1019
},
{
"epoch": 0.54,
"learning_rate": 5.3036599071536544e-05,
"loss": 1.1377,
"step": 1020
},
{
"epoch": 0.54,
"learning_rate": 5.294468912078424e-05,
"loss": 1.1078,
"step": 1021
},
{
"epoch": 0.54,
"learning_rate": 5.285276918427432e-05,
"loss": 1.2656,
"step": 1022
},
{
"epoch": 0.54,
"learning_rate": 5.276083957371716e-05,
"loss": 1.0643,
"step": 1023
},
{
"epoch": 0.54,
"learning_rate": 5.266890060085595e-05,
"loss": 1.3832,
"step": 1024
},
{
"epoch": 0.54,
"learning_rate": 5.2576952577465664e-05,
"loss": 1.038,
"step": 1025
},
{
"epoch": 0.54,
"learning_rate": 5.248499581535193e-05,
"loss": 1.1451,
"step": 1026
},
{
"epoch": 0.54,
"learning_rate": 5.239303062635001e-05,
"loss": 1.3984,
"step": 1027
},
{
"epoch": 0.54,
"learning_rate": 5.230105732232379e-05,
"loss": 1.2597,
"step": 1028
},
{
"epoch": 0.54,
"learning_rate": 5.220907621516461e-05,
"loss": 1.0798,
"step": 1029
},
{
"epoch": 0.54,
"learning_rate": 5.2117087616790304e-05,
"loss": 1.297,
"step": 1030
},
{
"epoch": 0.54,
"learning_rate": 5.202509183914412e-05,
"loss": 1.024,
"step": 1031
},
{
"epoch": 0.54,
"learning_rate": 5.193308919419363e-05,
"loss": 1.0174,
"step": 1032
},
{
"epoch": 0.54,
"learning_rate": 5.18410799939297e-05,
"loss": 1.3293,
"step": 1033
},
{
"epoch": 0.54,
"learning_rate": 5.1749064550365414e-05,
"loss": 1.2362,
"step": 1034
},
{
"epoch": 0.54,
"learning_rate": 5.165704317553505e-05,
"loss": 1.5172,
"step": 1035
},
{
"epoch": 0.54,
"learning_rate": 5.1565016181493006e-05,
"loss": 1.1196,
"step": 1036
},
{
"epoch": 0.54,
"learning_rate": 5.147298388031271e-05,
"loss": 1.3309,
"step": 1037
},
{
"epoch": 0.54,
"learning_rate": 5.1380946584085596e-05,
"loss": 1.3208,
"step": 1038
},
{
"epoch": 0.55,
"learning_rate": 5.128890460492004e-05,
"loss": 1.2953,
"step": 1039
},
{
"epoch": 0.55,
"learning_rate": 5.1196858254940305e-05,
"loss": 1.0986,
"step": 1040
},
{
"epoch": 0.55,
"learning_rate": 5.110480784628544e-05,
"loss": 1.2564,
"step": 1041
},
{
"epoch": 0.55,
"learning_rate": 5.1012753691108295e-05,
"loss": 1.2837,
"step": 1042
},
{
"epoch": 0.55,
"learning_rate": 5.092069610157443e-05,
"loss": 1.3492,
"step": 1043
},
{
"epoch": 0.55,
"learning_rate": 5.082863538986102e-05,
"loss": 1.2833,
"step": 1044
},
{
"epoch": 0.55,
"learning_rate": 5.073657186815586e-05,
"loss": 1.4483,
"step": 1045
},
{
"epoch": 0.55,
"learning_rate": 5.064450584865624e-05,
"loss": 1.2237,
"step": 1046
},
{
"epoch": 0.55,
"learning_rate": 5.055243764356795e-05,
"loss": 1.1658,
"step": 1047
},
{
"epoch": 0.55,
"learning_rate": 5.046036756510417e-05,
"loss": 1.2706,
"step": 1048
},
{
"epoch": 0.55,
"learning_rate": 5.036829592548446e-05,
"loss": 1.0426,
"step": 1049
},
{
"epoch": 0.55,
"learning_rate": 5.0276223036933626e-05,
"loss": 1.1844,
"step": 1050
},
{
"epoch": 0.55,
"learning_rate": 5.018414921168075e-05,
"loss": 1.155,
"step": 1051
},
{
"epoch": 0.55,
"learning_rate": 5.0092074761958086e-05,
"loss": 1.1265,
"step": 1052
},
{
"epoch": 0.55,
"learning_rate": 5e-05,
"loss": 1.2486,
"step": 1053
},
{
"epoch": 0.55,
"learning_rate": 4.9907925238041925e-05,
"loss": 1.151,
"step": 1054
},
{
"epoch": 0.55,
"learning_rate": 4.981585078831926e-05,
"loss": 1.4085,
"step": 1055
},
{
"epoch": 0.55,
"learning_rate": 4.972377696306639e-05,
"loss": 1.2894,
"step": 1056
},
{
"epoch": 0.55,
"learning_rate": 4.963170407451556e-05,
"loss": 1.2555,
"step": 1057
},
{
"epoch": 0.56,
"learning_rate": 4.953963243489583e-05,
"loss": 0.9528,
"step": 1058
},
{
"epoch": 0.56,
"learning_rate": 4.944756235643205e-05,
"loss": 1.2463,
"step": 1059
},
{
"epoch": 0.56,
"learning_rate": 4.9355494151343756e-05,
"loss": 1.1701,
"step": 1060
},
{
"epoch": 0.56,
"learning_rate": 4.926342813184414e-05,
"loss": 1.3017,
"step": 1061
},
{
"epoch": 0.56,
"learning_rate": 4.9171364610139e-05,
"loss": 1.1233,
"step": 1062
},
{
"epoch": 0.56,
"learning_rate": 4.9079303898425585e-05,
"loss": 1.1004,
"step": 1063
},
{
"epoch": 0.56,
"learning_rate": 4.8987246308891716e-05,
"loss": 1.2572,
"step": 1064
},
{
"epoch": 0.56,
"learning_rate": 4.889519215371458e-05,
"loss": 1.081,
"step": 1065
},
{
"epoch": 0.56,
"learning_rate": 4.880314174505972e-05,
"loss": 1.3523,
"step": 1066
},
{
"epoch": 0.56,
"learning_rate": 4.871109539507997e-05,
"loss": 1.0426,
"step": 1067
},
{
"epoch": 0.56,
"learning_rate": 4.8619053415914415e-05,
"loss": 1.3245,
"step": 1068
},
{
"epoch": 0.56,
"learning_rate": 4.85270161196873e-05,
"loss": 1.2372,
"step": 1069
},
{
"epoch": 0.56,
"learning_rate": 4.8434983818507005e-05,
"loss": 1.031,
"step": 1070
},
{
"epoch": 0.56,
"learning_rate": 4.834295682446496e-05,
"loss": 1.2342,
"step": 1071
},
{
"epoch": 0.56,
"learning_rate": 4.82509354496346e-05,
"loss": 1.3401,
"step": 1072
},
{
"epoch": 0.56,
"learning_rate": 4.815892000607032e-05,
"loss": 1.4023,
"step": 1073
},
{
"epoch": 0.56,
"learning_rate": 4.806691080580638e-05,
"loss": 1.2549,
"step": 1074
},
{
"epoch": 0.56,
"learning_rate": 4.797490816085588e-05,
"loss": 1.2023,
"step": 1075
},
{
"epoch": 0.56,
"learning_rate": 4.7882912383209694e-05,
"loss": 1.2136,
"step": 1076
},
{
"epoch": 0.56,
"learning_rate": 4.779092378483539e-05,
"loss": 1.4782,
"step": 1077
},
{
"epoch": 0.57,
"learning_rate": 4.769894267767621e-05,
"loss": 0.9413,
"step": 1078
},
{
"epoch": 0.57,
"learning_rate": 4.7606969373649986e-05,
"loss": 1.1232,
"step": 1079
},
{
"epoch": 0.57,
"learning_rate": 4.7515004184648086e-05,
"loss": 1.4187,
"step": 1080
},
{
"epoch": 0.57,
"learning_rate": 4.7423047422534354e-05,
"loss": 1.3423,
"step": 1081
},
{
"epoch": 0.57,
"learning_rate": 4.733109939914407e-05,
"loss": 1.0831,
"step": 1082
},
{
"epoch": 0.57,
"learning_rate": 4.723916042628287e-05,
"loss": 0.9331,
"step": 1083
},
{
"epoch": 0.57,
"learning_rate": 4.71472308157257e-05,
"loss": 1.2319,
"step": 1084
},
{
"epoch": 0.57,
"learning_rate": 4.705531087921577e-05,
"loss": 1.1965,
"step": 1085
},
{
"epoch": 0.57,
"learning_rate": 4.6963400928463474e-05,
"loss": 1.3236,
"step": 1086
},
{
"epoch": 0.57,
"learning_rate": 4.687150127514533e-05,
"loss": 1.2908,
"step": 1087
},
{
"epoch": 0.57,
"learning_rate": 4.6779612230902965e-05,
"loss": 1.3047,
"step": 1088
},
{
"epoch": 0.57,
"learning_rate": 4.668773410734201e-05,
"loss": 1.0924,
"step": 1089
},
{
"epoch": 0.57,
"learning_rate": 4.6595867216031066e-05,
"loss": 1.3568,
"step": 1090
},
{
"epoch": 0.57,
"learning_rate": 4.650401186850064e-05,
"loss": 1.1631,
"step": 1091
},
{
"epoch": 0.57,
"learning_rate": 4.641216837624211e-05,
"loss": 1.2808,
"step": 1092
},
{
"epoch": 0.57,
"learning_rate": 4.632033705070664e-05,
"loss": 1.2646,
"step": 1093
},
{
"epoch": 0.57,
"learning_rate": 4.622851820330412e-05,
"loss": 1.0823,
"step": 1094
},
{
"epoch": 0.57,
"learning_rate": 4.6136712145402144e-05,
"loss": 1.2418,
"step": 1095
},
{
"epoch": 0.57,
"learning_rate": 4.604491918832494e-05,
"loss": 1.1149,
"step": 1096
},
{
"epoch": 0.58,
"learning_rate": 4.59531396433523e-05,
"loss": 1.2756,
"step": 1097
},
{
"epoch": 0.58,
"learning_rate": 4.5861373821718555e-05,
"loss": 1.0218,
"step": 1098
},
{
"epoch": 0.58,
"learning_rate": 4.576962203461144e-05,
"loss": 1.2293,
"step": 1099
},
{
"epoch": 0.58,
"learning_rate": 4.567788459317116e-05,
"loss": 1.1739,
"step": 1100
},
{
"epoch": 0.58,
"learning_rate": 4.558616180848922e-05,
"loss": 1.1339,
"step": 1101
},
{
"epoch": 0.58,
"learning_rate": 4.54944539916075e-05,
"loss": 1.2657,
"step": 1102
},
{
"epoch": 0.58,
"learning_rate": 4.5402761453517044e-05,
"loss": 1.3037,
"step": 1103
},
{
"epoch": 0.58,
"learning_rate": 4.531108450515712e-05,
"loss": 1.2414,
"step": 1104
},
{
"epoch": 0.58,
"learning_rate": 4.521942345741412e-05,
"loss": 1.3885,
"step": 1105
},
{
"epoch": 0.58,
"learning_rate": 4.512777862112053e-05,
"loss": 1.2721,
"step": 1106
},
{
"epoch": 0.58,
"learning_rate": 4.503615030705384e-05,
"loss": 1.182,
"step": 1107
},
{
"epoch": 0.58,
"learning_rate": 4.494453882593552e-05,
"loss": 1.0801,
"step": 1108
},
{
"epoch": 0.58,
"learning_rate": 4.485294448842996e-05,
"loss": 1.243,
"step": 1109
},
{
"epoch": 0.58,
"learning_rate": 4.476136760514341e-05,
"loss": 1.3275,
"step": 1110
},
{
"epoch": 0.58,
"learning_rate": 4.466980848662294e-05,
"loss": 1.1791,
"step": 1111
},
{
"epoch": 0.58,
"learning_rate": 4.4578267443355384e-05,
"loss": 0.9916,
"step": 1112
},
{
"epoch": 0.58,
"learning_rate": 4.448674478576625e-05,
"loss": 1.1714,
"step": 1113
},
{
"epoch": 0.58,
"learning_rate": 4.439524082421872e-05,
"loss": 1.3951,
"step": 1114
},
{
"epoch": 0.58,
"learning_rate": 4.4303755869012576e-05,
"loss": 1.1565,
"step": 1115
},
{
"epoch": 0.59,
"learning_rate": 4.421229023038316e-05,
"loss": 1.3776,
"step": 1116
},
{
"epoch": 0.59,
"learning_rate": 4.412084421850026e-05,
"loss": 1.185,
"step": 1117
},
{
"epoch": 0.59,
"learning_rate": 4.402941814346716e-05,
"loss": 1.0763,
"step": 1118
},
{
"epoch": 0.59,
"learning_rate": 4.393801231531952e-05,
"loss": 1.0781,
"step": 1119
},
{
"epoch": 0.59,
"learning_rate": 4.384662704402432e-05,
"loss": 1.0173,
"step": 1120
},
{
"epoch": 0.59,
"learning_rate": 4.3755262639478874e-05,
"loss": 1.3302,
"step": 1121
},
{
"epoch": 0.59,
"learning_rate": 4.3663919411509686e-05,
"loss": 1.2739,
"step": 1122
},
{
"epoch": 0.59,
"learning_rate": 4.3572597669871475e-05,
"loss": 1.317,
"step": 1123
},
{
"epoch": 0.59,
"learning_rate": 4.34812977242461e-05,
"loss": 1.0408,
"step": 1124
},
{
"epoch": 0.59,
"learning_rate": 4.339001988424148e-05,
"loss": 1.1187,
"step": 1125
},
{
"epoch": 0.59,
"learning_rate": 4.329876445939062e-05,
"loss": 1.297,
"step": 1126
},
{
"epoch": 0.59,
"learning_rate": 4.320753175915047e-05,
"loss": 1.238,
"step": 1127
},
{
"epoch": 0.59,
"learning_rate": 4.3116322092900926e-05,
"loss": 0.8729,
"step": 1128
},
{
"epoch": 0.59,
"learning_rate": 4.302513576994378e-05,
"loss": 1.1245,
"step": 1129
},
{
"epoch": 0.59,
"learning_rate": 4.293397309950168e-05,
"loss": 1.3215,
"step": 1130
},
{
"epoch": 0.59,
"learning_rate": 4.2842834390717036e-05,
"loss": 1.1446,
"step": 1131
},
{
"epoch": 0.59,
"learning_rate": 4.2751719952651015e-05,
"loss": 1.241,
"step": 1132
},
{
"epoch": 0.59,
"learning_rate": 4.26606300942825e-05,
"loss": 1.1225,
"step": 1133
},
{
"epoch": 0.59,
"learning_rate": 4.256956512450696e-05,
"loss": 1.2456,
"step": 1134
},
{
"epoch": 0.6,
"learning_rate": 4.247852535213554e-05,
"loss": 1.2693,
"step": 1135
},
{
"epoch": 0.6,
"learning_rate": 4.2387511085893895e-05,
"loss": 1.0317,
"step": 1136
},
{
"epoch": 0.6,
"learning_rate": 4.229652263442118e-05,
"loss": 1.0834,
"step": 1137
},
{
"epoch": 0.6,
"learning_rate": 4.220556030626904e-05,
"loss": 1.0985,
"step": 1138
},
{
"epoch": 0.6,
"learning_rate": 4.21146244099005e-05,
"loss": 1.0909,
"step": 1139
},
{
"epoch": 0.6,
"learning_rate": 4.2023715253688987e-05,
"loss": 1.2587,
"step": 1140
},
{
"epoch": 0.6,
"learning_rate": 4.193283314591723e-05,
"loss": 1.2601,
"step": 1141
},
{
"epoch": 0.6,
"learning_rate": 4.184197839477623e-05,
"loss": 1.277,
"step": 1142
},
{
"epoch": 0.6,
"learning_rate": 4.175115130836421e-05,
"loss": 1.4979,
"step": 1143
},
{
"epoch": 0.6,
"learning_rate": 4.166035219468562e-05,
"loss": 1.0265,
"step": 1144
},
{
"epoch": 0.6,
"learning_rate": 4.156958136164999e-05,
"loss": 1.2503,
"step": 1145
},
{
"epoch": 0.6,
"learning_rate": 4.1478839117071e-05,
"loss": 1.2521,
"step": 1146
},
{
"epoch": 0.6,
"learning_rate": 4.1388125768665364e-05,
"loss": 1.2168,
"step": 1147
},
{
"epoch": 0.6,
"learning_rate": 4.1297441624051796e-05,
"loss": 1.2362,
"step": 1148
},
{
"epoch": 0.6,
"learning_rate": 4.1206786990750005e-05,
"loss": 1.1674,
"step": 1149
},
{
"epoch": 0.6,
"learning_rate": 4.11161621761796e-05,
"loss": 1.1533,
"step": 1150
},
{
"epoch": 0.6,
"learning_rate": 4.102556748765909e-05,
"loss": 1.1444,
"step": 1151
},
{
"epoch": 0.6,
"learning_rate": 4.093500323240478e-05,
"loss": 1.3611,
"step": 1152
},
{
"epoch": 0.6,
"learning_rate": 4.084446971752981e-05,
"loss": 0.949,
"step": 1153
},
{
"epoch": 0.61,
"learning_rate": 4.075396725004308e-05,
"loss": 1.2392,
"step": 1154
},
{
"epoch": 0.61,
"learning_rate": 4.06634961368482e-05,
"loss": 1.2627,
"step": 1155
},
{
"epoch": 0.61,
"learning_rate": 4.0573056684742437e-05,
"loss": 1.1446,
"step": 1156
},
{
"epoch": 0.61,
"learning_rate": 4.048264920041571e-05,
"loss": 1.2606,
"step": 1157
},
{
"epoch": 0.61,
"learning_rate": 4.0392273990449526e-05,
"loss": 1.0948,
"step": 1158
},
{
"epoch": 0.61,
"learning_rate": 4.0301931361315937e-05,
"loss": 1.0528,
"step": 1159
},
{
"epoch": 0.61,
"learning_rate": 4.021162161937653e-05,
"loss": 1.0092,
"step": 1160
},
{
"epoch": 0.61,
"learning_rate": 4.0121345070881345e-05,
"loss": 1.2607,
"step": 1161
},
{
"epoch": 0.61,
"learning_rate": 4.003110202196787e-05,
"loss": 1.0265,
"step": 1162
},
{
"epoch": 0.61,
"learning_rate": 3.994089277866001e-05,
"loss": 1.2582,
"step": 1163
},
{
"epoch": 0.61,
"learning_rate": 3.985071764686701e-05,
"loss": 1.3616,
"step": 1164
},
{
"epoch": 0.61,
"learning_rate": 3.976057693238243e-05,
"loss": 1.1759,
"step": 1165
},
{
"epoch": 0.61,
"learning_rate": 3.9670470940883144e-05,
"loss": 1.1679,
"step": 1166
},
{
"epoch": 0.61,
"learning_rate": 3.958039997792825e-05,
"loss": 1.2321,
"step": 1167
},
{
"epoch": 0.61,
"learning_rate": 3.94903643489581e-05,
"loss": 1.1551,
"step": 1168
},
{
"epoch": 0.61,
"learning_rate": 3.940036435929318e-05,
"loss": 1.4267,
"step": 1169
},
{
"epoch": 0.61,
"learning_rate": 3.9310400314133135e-05,
"loss": 1.3853,
"step": 1170
},
{
"epoch": 0.61,
"learning_rate": 3.9220472518555724e-05,
"loss": 1.1791,
"step": 1171
},
{
"epoch": 0.61,
"learning_rate": 3.9130581277515785e-05,
"loss": 1.1589,
"step": 1172
},
{
"epoch": 0.62,
"learning_rate": 3.9040726895844174e-05,
"loss": 1.2076,
"step": 1173
},
{
"epoch": 0.62,
"learning_rate": 3.8950909678246784e-05,
"loss": 1.3118,
"step": 1174
},
{
"epoch": 0.62,
"learning_rate": 3.8861129929303454e-05,
"loss": 1.4017,
"step": 1175
},
{
"epoch": 0.62,
"learning_rate": 3.877138795346697e-05,
"loss": 1.1258,
"step": 1176
},
{
"epoch": 0.62,
"learning_rate": 3.868168405506202e-05,
"loss": 1.1977,
"step": 1177
},
{
"epoch": 0.62,
"learning_rate": 3.85920185382842e-05,
"loss": 1.2062,
"step": 1178
},
{
"epoch": 0.62,
"learning_rate": 3.850239170719891e-05,
"loss": 1.254,
"step": 1179
},
{
"epoch": 0.62,
"learning_rate": 3.8412803865740375e-05,
"loss": 1.2368,
"step": 1180
},
{
"epoch": 0.62,
"learning_rate": 3.83232553177106e-05,
"loss": 1.2982,
"step": 1181
},
{
"epoch": 0.62,
"learning_rate": 3.823374636677837e-05,
"loss": 1.3586,
"step": 1182
},
{
"epoch": 0.62,
"learning_rate": 3.814427731647813e-05,
"loss": 1.0685,
"step": 1183
},
{
"epoch": 0.62,
"learning_rate": 3.8054848470209095e-05,
"loss": 1.1598,
"step": 1184
},
{
"epoch": 0.62,
"learning_rate": 3.796546013123407e-05,
"loss": 1.1086,
"step": 1185
},
{
"epoch": 0.62,
"learning_rate": 3.7876112602678546e-05,
"loss": 1.1408,
"step": 1186
},
{
"epoch": 0.62,
"learning_rate": 3.778680618752963e-05,
"loss": 1.2318,
"step": 1187
},
{
"epoch": 0.62,
"learning_rate": 3.769754118863493e-05,
"loss": 1.3748,
"step": 1188
},
{
"epoch": 0.62,
"learning_rate": 3.7608317908701706e-05,
"loss": 1.3031,
"step": 1189
},
{
"epoch": 0.62,
"learning_rate": 3.751913665029567e-05,
"loss": 0.9961,
"step": 1190
},
{
"epoch": 0.62,
"learning_rate": 3.7429997715840084e-05,
"loss": 1.2784,
"step": 1191
},
{
"epoch": 0.63,
"learning_rate": 3.734090140761466e-05,
"loss": 1.2326,
"step": 1192
},
{
"epoch": 0.63,
"learning_rate": 3.7251848027754565e-05,
"loss": 1.2761,
"step": 1193
},
{
"epoch": 0.63,
"learning_rate": 3.716283787824939e-05,
"loss": 1.4119,
"step": 1194
},
{
"epoch": 0.63,
"learning_rate": 3.7073871260942125e-05,
"loss": 1.3497,
"step": 1195
},
{
"epoch": 0.63,
"learning_rate": 3.6984948477528157e-05,
"loss": 1.1329,
"step": 1196
},
{
"epoch": 0.63,
"learning_rate": 3.68960698295542e-05,
"loss": 1.1757,
"step": 1197
},
{
"epoch": 0.63,
"learning_rate": 3.6807235618417316e-05,
"loss": 1.0434,
"step": 1198
},
{
"epoch": 0.63,
"learning_rate": 3.6718446145363854e-05,
"loss": 1.0727,
"step": 1199
},
{
"epoch": 0.63,
"learning_rate": 3.662970171148849e-05,
"loss": 1.3552,
"step": 1200
},
{
"epoch": 0.63,
"learning_rate": 3.6541002617733146e-05,
"loss": 0.9735,
"step": 1201
},
{
"epoch": 0.63,
"learning_rate": 3.645234916488599e-05,
"loss": 0.8415,
"step": 1202
},
{
"epoch": 0.63,
"learning_rate": 3.636374165358042e-05,
"loss": 1.4925,
"step": 1203
},
{
"epoch": 0.63,
"learning_rate": 3.627518038429403e-05,
"loss": 1.1336,
"step": 1204
},
{
"epoch": 0.63,
"learning_rate": 3.618666565734764e-05,
"loss": 1.2341,
"step": 1205
},
{
"epoch": 0.63,
"learning_rate": 3.609819777290418e-05,
"loss": 1.2162,
"step": 1206
},
{
"epoch": 0.63,
"learning_rate": 3.600977703096778e-05,
"loss": 0.9718,
"step": 1207
},
{
"epoch": 0.63,
"learning_rate": 3.592140373138269e-05,
"loss": 1.3183,
"step": 1208
},
{
"epoch": 0.63,
"learning_rate": 3.5833078173832256e-05,
"loss": 1.2114,
"step": 1209
},
{
"epoch": 0.63,
"learning_rate": 3.5744800657837985e-05,
"loss": 1.3612,
"step": 1210
},
{
"epoch": 0.64,
"learning_rate": 3.56565714827584e-05,
"loss": 1.3131,
"step": 1211
},
{
"epoch": 0.64,
"learning_rate": 3.5568390947788135e-05,
"loss": 1.2154,
"step": 1212
},
{
"epoch": 0.64,
"learning_rate": 3.548025935195688e-05,
"loss": 1.299,
"step": 1213
},
{
"epoch": 0.64,
"learning_rate": 3.5392176994128354e-05,
"loss": 1.1693,
"step": 1214
},
{
"epoch": 0.64,
"learning_rate": 3.530414417299929e-05,
"loss": 1.1611,
"step": 1215
},
{
"epoch": 0.64,
"learning_rate": 3.5216161187098495e-05,
"loss": 1.2259,
"step": 1216
},
{
"epoch": 0.64,
"learning_rate": 3.5128228334785703e-05,
"loss": 1.0022,
"step": 1217
},
{
"epoch": 0.64,
"learning_rate": 3.5040345914250704e-05,
"loss": 1.1038,
"step": 1218
},
{
"epoch": 0.64,
"learning_rate": 3.4952514223512235e-05,
"loss": 1.1872,
"step": 1219
},
{
"epoch": 0.64,
"learning_rate": 3.4864733560417e-05,
"loss": 1.2469,
"step": 1220
},
{
"epoch": 0.64,
"learning_rate": 3.477700422263867e-05,
"loss": 1.3855,
"step": 1221
},
{
"epoch": 0.64,
"learning_rate": 3.4689326507676886e-05,
"loss": 1.2645,
"step": 1222
},
{
"epoch": 0.64,
"learning_rate": 3.46017007128562e-05,
"loss": 1.2546,
"step": 1223
},
{
"epoch": 0.64,
"learning_rate": 3.4514127135325103e-05,
"loss": 1.2321,
"step": 1224
},
{
"epoch": 0.64,
"learning_rate": 3.4426606072055036e-05,
"loss": 1.0954,
"step": 1225
},
{
"epoch": 0.64,
"learning_rate": 3.433913781983932e-05,
"loss": 1.0545,
"step": 1226
},
{
"epoch": 0.64,
"learning_rate": 3.425172267529223e-05,
"loss": 1.4396,
"step": 1227
},
{
"epoch": 0.64,
"learning_rate": 3.4164360934847914e-05,
"loss": 1.2859,
"step": 1228
},
{
"epoch": 0.64,
"learning_rate": 3.407705289475942e-05,
"loss": 1.1176,
"step": 1229
},
{
"epoch": 0.65,
"learning_rate": 3.398979885109774e-05,
"loss": 1.2284,
"step": 1230
},
{
"epoch": 0.65,
"learning_rate": 3.3902599099750707e-05,
"loss": 1.1778,
"step": 1231
},
{
"epoch": 0.65,
"learning_rate": 3.381545393642205e-05,
"loss": 1.3364,
"step": 1232
},
{
"epoch": 0.65,
"learning_rate": 3.372836365663041e-05,
"loss": 1.1908,
"step": 1233
},
{
"epoch": 0.65,
"learning_rate": 3.364132855570829e-05,
"loss": 1.1588,
"step": 1234
},
{
"epoch": 0.65,
"learning_rate": 3.355434892880107e-05,
"loss": 1.3075,
"step": 1235
},
{
"epoch": 0.65,
"learning_rate": 3.3467425070866035e-05,
"loss": 1.3005,
"step": 1236
},
{
"epoch": 0.65,
"learning_rate": 3.3380557276671345e-05,
"loss": 1.1527,
"step": 1237
},
{
"epoch": 0.65,
"learning_rate": 3.3293745840795e-05,
"loss": 1.3768,
"step": 1238
},
{
"epoch": 0.65,
"learning_rate": 3.3206991057623974e-05,
"loss": 1.088,
"step": 1239
},
{
"epoch": 0.65,
"learning_rate": 3.312029322135306e-05,
"loss": 1.2779,
"step": 1240
},
{
"epoch": 0.65,
"learning_rate": 3.3033652625983915e-05,
"loss": 1.3483,
"step": 1241
},
{
"epoch": 0.65,
"learning_rate": 3.294706956532413e-05,
"loss": 0.8055,
"step": 1242
},
{
"epoch": 0.65,
"learning_rate": 3.286054433298619e-05,
"loss": 1.2302,
"step": 1243
},
{
"epoch": 0.65,
"learning_rate": 3.277407722238646e-05,
"loss": 1.3869,
"step": 1244
},
{
"epoch": 0.65,
"learning_rate": 3.2687668526744224e-05,
"loss": 1.145,
"step": 1245
},
{
"epoch": 0.65,
"learning_rate": 3.260131853908066e-05,
"loss": 1.0956,
"step": 1246
},
{
"epoch": 0.65,
"learning_rate": 3.251502755221787e-05,
"loss": 1.3329,
"step": 1247
},
{
"epoch": 0.65,
"learning_rate": 3.242879585877787e-05,
"loss": 1.3474,
"step": 1248
},
{
"epoch": 0.66,
"learning_rate": 3.234262375118161e-05,
"loss": 1.2398,
"step": 1249
},
{
"epoch": 0.66,
"learning_rate": 3.225651152164799e-05,
"loss": 1.0887,
"step": 1250
},
{
"epoch": 0.66,
"learning_rate": 3.2170459462192826e-05,
"loss": 1.2679,
"step": 1251
},
{
"epoch": 0.66,
"learning_rate": 3.208446786462791e-05,
"loss": 0.9408,
"step": 1252
},
{
"epoch": 0.66,
"learning_rate": 3.199853702056003e-05,
"loss": 1.2024,
"step": 1253
},
{
"epoch": 0.66,
"learning_rate": 3.191266722138989e-05,
"loss": 1.2051,
"step": 1254
},
{
"epoch": 0.66,
"learning_rate": 3.182685875831124e-05,
"loss": 1.1828,
"step": 1255
},
{
"epoch": 0.66,
"learning_rate": 3.17411119223098e-05,
"loss": 1.1571,
"step": 1256
},
{
"epoch": 0.66,
"learning_rate": 3.165542700416232e-05,
"loss": 1.2901,
"step": 1257
},
{
"epoch": 0.66,
"learning_rate": 3.156980429443559e-05,
"loss": 1.3149,
"step": 1258
},
{
"epoch": 0.66,
"learning_rate": 3.1484244083485396e-05,
"loss": 1.0309,
"step": 1259
},
{
"epoch": 0.66,
"learning_rate": 3.1398746661455646e-05,
"loss": 1.3031,
"step": 1260
},
{
"epoch": 0.66,
"learning_rate": 3.131331231827729e-05,
"loss": 1.2569,
"step": 1261
},
{
"epoch": 0.66,
"learning_rate": 3.1227941343667374e-05,
"loss": 1.2363,
"step": 1262
},
{
"epoch": 0.66,
"learning_rate": 3.114263402712807e-05,
"loss": 1.1,
"step": 1263
},
{
"epoch": 0.66,
"learning_rate": 3.1057390657945653e-05,
"loss": 1.3165,
"step": 1264
},
{
"epoch": 0.66,
"learning_rate": 3.097221152518956e-05,
"loss": 1.2885,
"step": 1265
},
{
"epoch": 0.66,
"learning_rate": 3.08870969177114e-05,
"loss": 1.0581,
"step": 1266
},
{
"epoch": 0.66,
"learning_rate": 3.0802047124143964e-05,
"loss": 1.1709,
"step": 1267
},
{
"epoch": 0.67,
"learning_rate": 3.071706243290026e-05,
"loss": 1.2625,
"step": 1268
},
{
"epoch": 0.67,
"learning_rate": 3.0632143132172504e-05,
"loss": 1.3506,
"step": 1269
},
{
"epoch": 0.67,
"learning_rate": 3.054728950993119e-05,
"loss": 1.2595,
"step": 1270
},
{
"epoch": 0.67,
"learning_rate": 3.0462501853924087e-05,
"loss": 1.1551,
"step": 1271
},
{
"epoch": 0.67,
"learning_rate": 3.037778045167524e-05,
"loss": 1.1417,
"step": 1272
},
{
"epoch": 0.67,
"learning_rate": 3.029312559048406e-05,
"loss": 1.1699,
"step": 1273
},
{
"epoch": 0.67,
"learning_rate": 3.0208537557424277e-05,
"loss": 1.1594,
"step": 1274
},
{
"epoch": 0.67,
"learning_rate": 3.0124016639343022e-05,
"loss": 1.3783,
"step": 1275
},
{
"epoch": 0.67,
"learning_rate": 3.0039563122859817e-05,
"loss": 1.2226,
"step": 1276
},
{
"epoch": 0.67,
"learning_rate": 2.995517729436561e-05,
"loss": 1.3955,
"step": 1277
},
{
"epoch": 0.67,
"learning_rate": 2.9870859440021842e-05,
"loss": 1.3198,
"step": 1278
},
{
"epoch": 0.67,
"learning_rate": 2.9786609845759418e-05,
"loss": 1.429,
"step": 1279
},
{
"epoch": 0.67,
"learning_rate": 2.970242879727778e-05,
"loss": 1.0394,
"step": 1280
},
{
"epoch": 0.67,
"learning_rate": 2.9618316580043915e-05,
"loss": 1.1531,
"step": 1281
},
{
"epoch": 0.67,
"learning_rate": 2.953427347929142e-05,
"loss": 1.2417,
"step": 1282
},
{
"epoch": 0.67,
"learning_rate": 2.9450299780019474e-05,
"loss": 1.2562,
"step": 1283
},
{
"epoch": 0.67,
"learning_rate": 2.936639576699194e-05,
"loss": 1.0393,
"step": 1284
},
{
"epoch": 0.67,
"learning_rate": 2.9282561724736335e-05,
"loss": 1.2222,
"step": 1285
},
{
"epoch": 0.67,
"learning_rate": 2.919879793754293e-05,
"loss": 1.3213,
"step": 1286
},
{
"epoch": 0.68,
"learning_rate": 2.9115104689463724e-05,
"loss": 1.3782,
"step": 1287
},
{
"epoch": 0.68,
"learning_rate": 2.9031482264311548e-05,
"loss": 1.4448,
"step": 1288
},
{
"epoch": 0.68,
"learning_rate": 2.894793094565904e-05,
"loss": 1.1885,
"step": 1289
},
{
"epoch": 0.68,
"learning_rate": 2.88644510168377e-05,
"loss": 0.9915,
"step": 1290
},
{
"epoch": 0.68,
"learning_rate": 2.878104276093695e-05,
"loss": 1.3803,
"step": 1291
},
{
"epoch": 0.68,
"learning_rate": 2.869770646080316e-05,
"loss": 0.9869,
"step": 1292
},
{
"epoch": 0.68,
"learning_rate": 2.861444239903871e-05,
"loss": 1.2829,
"step": 1293
},
{
"epoch": 0.68,
"learning_rate": 2.853125085800096e-05,
"loss": 1.2863,
"step": 1294
},
{
"epoch": 0.68,
"learning_rate": 2.8448132119801386e-05,
"loss": 1.0569,
"step": 1295
},
{
"epoch": 0.68,
"learning_rate": 2.836508646630457e-05,
"loss": 1.1295,
"step": 1296
},
{
"epoch": 0.68,
"learning_rate": 2.8282114179127268e-05,
"loss": 1.23,
"step": 1297
},
{
"epoch": 0.68,
"learning_rate": 2.8199215539637424e-05,
"loss": 1.0819,
"step": 1298
},
{
"epoch": 0.68,
"learning_rate": 2.8116390828953253e-05,
"loss": 1.0494,
"step": 1299
},
{
"epoch": 0.68,
"learning_rate": 2.8033640327942234e-05,
"loss": 0.9276,
"step": 1300
},
{
"epoch": 0.68,
"learning_rate": 2.795096431722026e-05,
"loss": 1.3069,
"step": 1301
},
{
"epoch": 0.68,
"learning_rate": 2.786836307715056e-05,
"loss": 1.0837,
"step": 1302
},
{
"epoch": 0.68,
"learning_rate": 2.778583688784283e-05,
"loss": 1.1688,
"step": 1303
},
{
"epoch": 0.68,
"learning_rate": 2.7703386029152246e-05,
"loss": 1.2329,
"step": 1304
},
{
"epoch": 0.68,
"learning_rate": 2.7621010780678547e-05,
"loss": 1.3319,
"step": 1305
},
{
"epoch": 0.69,
"learning_rate": 2.753871142176506e-05,
"loss": 1.1118,
"step": 1306
},
{
"epoch": 0.69,
"learning_rate": 2.7456488231497778e-05,
"loss": 1.1439,
"step": 1307
},
{
"epoch": 0.69,
"learning_rate": 2.737434148870437e-05,
"loss": 1.0275,
"step": 1308
},
{
"epoch": 0.69,
"learning_rate": 2.7292271471953284e-05,
"loss": 1.3342,
"step": 1309
},
{
"epoch": 0.69,
"learning_rate": 2.7210278459552785e-05,
"loss": 1.35,
"step": 1310
},
{
"epoch": 0.69,
"learning_rate": 2.7128362729550005e-05,
"loss": 1.291,
"step": 1311
},
{
"epoch": 0.69,
"learning_rate": 2.7046524559729968e-05,
"loss": 1.3303,
"step": 1312
},
{
"epoch": 0.69,
"learning_rate": 2.6964764227614736e-05,
"loss": 0.9718,
"step": 1313
},
{
"epoch": 0.69,
"learning_rate": 2.688308201046236e-05,
"loss": 1.2921,
"step": 1314
},
{
"epoch": 0.69,
"learning_rate": 2.6801478185266076e-05,
"loss": 1.0728,
"step": 1315
},
{
"epoch": 0.69,
"learning_rate": 2.6719953028753214e-05,
"loss": 1.2965,
"step": 1316
},
{
"epoch": 0.69,
"learning_rate": 2.6638506817384347e-05,
"loss": 1.2749,
"step": 1317
},
{
"epoch": 0.69,
"learning_rate": 2.655713982735234e-05,
"loss": 1.3782,
"step": 1318
},
{
"epoch": 0.69,
"learning_rate": 2.647585233458142e-05,
"loss": 1.0089,
"step": 1319
},
{
"epoch": 0.69,
"learning_rate": 2.6394644614726216e-05,
"loss": 1.0192,
"step": 1320
},
{
"epoch": 0.69,
"learning_rate": 2.6313516943170836e-05,
"loss": 0.9587,
"step": 1321
},
{
"epoch": 0.69,
"learning_rate": 2.623246959502795e-05,
"loss": 1.1867,
"step": 1322
},
{
"epoch": 0.69,
"learning_rate": 2.615150284513783e-05,
"loss": 1.2985,
"step": 1323
},
{
"epoch": 0.69,
"learning_rate": 2.6070616968067445e-05,
"loss": 1.3737,
"step": 1324
},
{
"epoch": 0.7,
"learning_rate": 2.5989812238109502e-05,
"loss": 1.0816,
"step": 1325
},
{
"epoch": 0.7,
"learning_rate": 2.5909088929281533e-05,
"loss": 1.2715,
"step": 1326
},
{
"epoch": 0.7,
"learning_rate": 2.5828447315324962e-05,
"loss": 1.2235,
"step": 1327
},
{
"epoch": 0.7,
"learning_rate": 2.574788766970418e-05,
"loss": 1.1379,
"step": 1328
},
{
"epoch": 0.7,
"learning_rate": 2.5667410265605617e-05,
"loss": 0.9785,
"step": 1329
},
{
"epoch": 0.7,
"learning_rate": 2.5587015375936802e-05,
"loss": 1.0824,
"step": 1330
},
{
"epoch": 0.7,
"learning_rate": 2.550670327332546e-05,
"loss": 1.3527,
"step": 1331
},
{
"epoch": 0.7,
"learning_rate": 2.5426474230118567e-05,
"loss": 1.4121,
"step": 1332
},
{
"epoch": 0.7,
"learning_rate": 2.5346328518381445e-05,
"loss": 0.9755,
"step": 1333
},
{
"epoch": 0.7,
"learning_rate": 2.5266266409896834e-05,
"loss": 1.2786,
"step": 1334
},
{
"epoch": 0.7,
"learning_rate": 2.518628817616394e-05,
"loss": 1.2678,
"step": 1335
},
{
"epoch": 0.7,
"learning_rate": 2.5106394088397566e-05,
"loss": 1.1993,
"step": 1336
},
{
"epoch": 0.7,
"learning_rate": 2.502658441752716e-05,
"loss": 1.0807,
"step": 1337
},
{
"epoch": 0.7,
"learning_rate": 2.49468594341959e-05,
"loss": 1.1373,
"step": 1338
},
{
"epoch": 0.7,
"learning_rate": 2.4867219408759794e-05,
"loss": 1.0183,
"step": 1339
},
{
"epoch": 0.7,
"learning_rate": 2.4787664611286722e-05,
"loss": 1.2953,
"step": 1340
},
{
"epoch": 0.7,
"learning_rate": 2.4708195311555572e-05,
"loss": 1.1941,
"step": 1341
},
{
"epoch": 0.7,
"learning_rate": 2.4628811779055277e-05,
"loss": 1.0912,
"step": 1342
},
{
"epoch": 0.7,
"learning_rate": 2.4549514282983947e-05,
"loss": 1.3223,
"step": 1343
},
{
"epoch": 0.71,
"learning_rate": 2.4470303092247926e-05,
"loss": 0.9993,
"step": 1344
},
{
"epoch": 0.71,
"learning_rate": 2.4391178475460875e-05,
"loss": 1.4854,
"step": 1345
},
{
"epoch": 0.71,
"learning_rate": 2.4312140700942888e-05,
"loss": 1.1286,
"step": 1346
},
{
"epoch": 0.71,
"learning_rate": 2.4233190036719562e-05,
"loss": 1.294,
"step": 1347
},
{
"epoch": 0.71,
"learning_rate": 2.4154326750521083e-05,
"loss": 1.1159,
"step": 1348
},
{
"epoch": 0.71,
"learning_rate": 2.4075551109781358e-05,
"loss": 1.3525,
"step": 1349
},
{
"epoch": 0.71,
"learning_rate": 2.3996863381637046e-05,
"loss": 1.2539,
"step": 1350
},
{
"epoch": 0.71,
"learning_rate": 2.3918263832926708e-05,
"loss": 1.2386,
"step": 1351
},
{
"epoch": 0.71,
"learning_rate": 2.3839752730189862e-05,
"loss": 1.2319,
"step": 1352
},
{
"epoch": 0.71,
"learning_rate": 2.376133033966611e-05,
"loss": 1.2072,
"step": 1353
},
{
"epoch": 0.71,
"learning_rate": 2.3682996927294214e-05,
"loss": 0.8596,
"step": 1354
},
{
"epoch": 0.71,
"learning_rate": 2.3604752758711206e-05,
"loss": 1.1563,
"step": 1355
},
{
"epoch": 0.71,
"learning_rate": 2.3526598099251472e-05,
"loss": 1.0832,
"step": 1356
},
{
"epoch": 0.71,
"learning_rate": 2.3448533213945884e-05,
"loss": 1.2598,
"step": 1357
},
{
"epoch": 0.71,
"learning_rate": 2.3370558367520855e-05,
"loss": 1.1482,
"step": 1358
},
{
"epoch": 0.71,
"learning_rate": 2.3292673824397487e-05,
"loss": 1.1527,
"step": 1359
},
{
"epoch": 0.71,
"learning_rate": 2.321487984869064e-05,
"loss": 1.2964,
"step": 1360
},
{
"epoch": 0.71,
"learning_rate": 2.313717670420804e-05,
"loss": 1.1139,
"step": 1361
},
{
"epoch": 0.71,
"learning_rate": 2.305956465444945e-05,
"loss": 1.3739,
"step": 1362
},
{
"epoch": 0.72,
"learning_rate": 2.2982043962605655e-05,
"loss": 1.3723,
"step": 1363
},
{
"epoch": 0.72,
"learning_rate": 2.290461489155768e-05,
"loss": 1.1796,
"step": 1364
},
{
"epoch": 0.72,
"learning_rate": 2.2827277703875805e-05,
"loss": 0.8906,
"step": 1365
},
{
"epoch": 0.72,
"learning_rate": 2.275003266181877e-05,
"loss": 1.1503,
"step": 1366
},
{
"epoch": 0.72,
"learning_rate": 2.2672880027332828e-05,
"loss": 1.2305,
"step": 1367
},
{
"epoch": 0.72,
"learning_rate": 2.2595820062050855e-05,
"loss": 1.292,
"step": 1368
},
{
"epoch": 0.72,
"learning_rate": 2.2518853027291487e-05,
"loss": 0.9769,
"step": 1369
},
{
"epoch": 0.72,
"learning_rate": 2.2441979184058222e-05,
"loss": 1.237,
"step": 1370
},
{
"epoch": 0.72,
"learning_rate": 2.236519879303853e-05,
"loss": 1.2916,
"step": 1371
},
{
"epoch": 0.72,
"learning_rate": 2.2288512114602983e-05,
"loss": 0.9576,
"step": 1372
},
{
"epoch": 0.72,
"learning_rate": 2.2211919408804353e-05,
"loss": 1.0593,
"step": 1373
},
{
"epoch": 0.72,
"learning_rate": 2.213542093537675e-05,
"loss": 1.2593,
"step": 1374
},
{
"epoch": 0.72,
"learning_rate": 2.2059016953734725e-05,
"loss": 1.4077,
"step": 1375
},
{
"epoch": 0.72,
"learning_rate": 2.1982707722972383e-05,
"loss": 1.3385,
"step": 1376
},
{
"epoch": 0.72,
"learning_rate": 2.1906493501862575e-05,
"loss": 1.2153,
"step": 1377
},
{
"epoch": 0.72,
"learning_rate": 2.1830374548855902e-05,
"loss": 1.0724,
"step": 1378
},
{
"epoch": 0.72,
"learning_rate": 2.1754351122079923e-05,
"loss": 1.1901,
"step": 1379
},
{
"epoch": 0.72,
"learning_rate": 2.167842347933826e-05,
"loss": 1.2802,
"step": 1380
},
{
"epoch": 0.72,
"learning_rate": 2.1602591878109723e-05,
"loss": 1.1832,
"step": 1381
},
{
"epoch": 0.72,
"learning_rate": 2.1526856575547444e-05,
"loss": 1.27,
"step": 1382
},
{
"epoch": 0.73,
"learning_rate": 2.1451217828477944e-05,
"loss": 1.1813,
"step": 1383
},
{
"epoch": 0.73,
"learning_rate": 2.1375675893400372e-05,
"loss": 1.2412,
"step": 1384
},
{
"epoch": 0.73,
"learning_rate": 2.1300231026485556e-05,
"loss": 1.3666,
"step": 1385
},
{
"epoch": 0.73,
"learning_rate": 2.1224883483575163e-05,
"loss": 1.0566,
"step": 1386
},
{
"epoch": 0.73,
"learning_rate": 2.114963352018081e-05,
"loss": 1.2551,
"step": 1387
},
{
"epoch": 0.73,
"learning_rate": 2.107448139148323e-05,
"loss": 1.4707,
"step": 1388
},
{
"epoch": 0.73,
"learning_rate": 2.0999427352331362e-05,
"loss": 1.102,
"step": 1389
},
{
"epoch": 0.73,
"learning_rate": 2.0924471657241524e-05,
"loss": 1.0989,
"step": 1390
},
{
"epoch": 0.73,
"learning_rate": 2.084961456039657e-05,
"loss": 1.1448,
"step": 1391
},
{
"epoch": 0.73,
"learning_rate": 2.0774856315644954e-05,
"loss": 1.1827,
"step": 1392
},
{
"epoch": 0.73,
"learning_rate": 2.0700197176499925e-05,
"loss": 1.2116,
"step": 1393
},
{
"epoch": 0.73,
"learning_rate": 2.0625637396138664e-05,
"loss": 1.2914,
"step": 1394
},
{
"epoch": 0.73,
"learning_rate": 2.0551177227401398e-05,
"loss": 1.2934,
"step": 1395
},
{
"epoch": 0.73,
"learning_rate": 2.0476816922790575e-05,
"loss": 1.2691,
"step": 1396
},
{
"epoch": 0.73,
"learning_rate": 2.040255673446999e-05,
"loss": 1.3639,
"step": 1397
},
{
"epoch": 0.73,
"learning_rate": 2.0328396914263927e-05,
"loss": 1.0915,
"step": 1398
},
{
"epoch": 0.73,
"learning_rate": 2.025433771365632e-05,
"loss": 1.0743,
"step": 1399
},
{
"epoch": 0.73,
"learning_rate": 2.0180379383789903e-05,
"loss": 1.4099,
"step": 1400
},
{
"epoch": 0.73,
"learning_rate": 2.0106522175465292e-05,
"loss": 1.1789,
"step": 1401
},
{
"epoch": 0.74,
"learning_rate": 2.0032766339140248e-05,
"loss": 1.1932,
"step": 1402
},
{
"epoch": 0.74,
"learning_rate": 1.9959112124928743e-05,
"loss": 1.3066,
"step": 1403
},
{
"epoch": 0.74,
"learning_rate": 1.9885559782600126e-05,
"loss": 1.4066,
"step": 1404
},
{
"epoch": 0.74,
"learning_rate": 1.981210956157834e-05,
"loss": 1.1259,
"step": 1405
},
{
"epoch": 0.74,
"learning_rate": 1.9738761710940968e-05,
"loss": 1.1671,
"step": 1406
},
{
"epoch": 0.74,
"learning_rate": 1.9665516479418467e-05,
"loss": 1.0956,
"step": 1407
},
{
"epoch": 0.74,
"learning_rate": 1.9592374115393292e-05,
"loss": 1.1723,
"step": 1408
},
{
"epoch": 0.74,
"learning_rate": 1.951933486689907e-05,
"loss": 1.1064,
"step": 1409
},
{
"epoch": 0.74,
"learning_rate": 1.9446398981619756e-05,
"loss": 1.4602,
"step": 1410
},
{
"epoch": 0.74,
"learning_rate": 1.937356670688878e-05,
"loss": 1.2421,
"step": 1411
},
{
"epoch": 0.74,
"learning_rate": 1.9300838289688216e-05,
"loss": 1.0283,
"step": 1412
},
{
"epoch": 0.74,
"learning_rate": 1.9228213976647964e-05,
"loss": 1.1432,
"step": 1413
},
{
"epoch": 0.74,
"learning_rate": 1.9155694014044877e-05,
"loss": 1.1459,
"step": 1414
},
{
"epoch": 0.74,
"learning_rate": 1.908327864780195e-05,
"loss": 1.1085,
"step": 1415
},
{
"epoch": 0.74,
"learning_rate": 1.9010968123487477e-05,
"loss": 1.1844,
"step": 1416
},
{
"epoch": 0.74,
"learning_rate": 1.8938762686314238e-05,
"loss": 1.4597,
"step": 1417
},
{
"epoch": 0.74,
"learning_rate": 1.8866662581138646e-05,
"loss": 1.3673,
"step": 1418
},
{
"epoch": 0.74,
"learning_rate": 1.879466805245986e-05,
"loss": 1.2964,
"step": 1419
},
{
"epoch": 0.74,
"learning_rate": 1.872277934441914e-05,
"loss": 1.1169,
"step": 1420
},
{
"epoch": 0.75,
"learning_rate": 1.8650996700798795e-05,
"loss": 0.9918,
"step": 1421
},
{
"epoch": 0.75,
"learning_rate": 1.8579320365021508e-05,
"loss": 1.3039,
"step": 1422
},
{
"epoch": 0.75,
"learning_rate": 1.8507750580149436e-05,
"loss": 1.2077,
"step": 1423
},
{
"epoch": 0.75,
"learning_rate": 1.8436287588883417e-05,
"loss": 1.047,
"step": 1424
},
{
"epoch": 0.75,
"learning_rate": 1.8364931633562148e-05,
"loss": 1.3578,
"step": 1425
},
{
"epoch": 0.75,
"learning_rate": 1.8293682956161357e-05,
"loss": 0.9352,
"step": 1426
},
{
"epoch": 0.75,
"learning_rate": 1.8222541798292963e-05,
"loss": 1.1146,
"step": 1427
},
{
"epoch": 0.75,
"learning_rate": 1.8151508401204297e-05,
"loss": 1.0679,
"step": 1428
},
{
"epoch": 0.75,
"learning_rate": 1.808058300577724e-05,
"loss": 1.2617,
"step": 1429
},
{
"epoch": 0.75,
"learning_rate": 1.800976585252745e-05,
"loss": 1.2403,
"step": 1430
},
{
"epoch": 0.75,
"learning_rate": 1.7939057181603503e-05,
"loss": 1.2127,
"step": 1431
},
{
"epoch": 0.75,
"learning_rate": 1.7868457232786117e-05,
"loss": 1.372,
"step": 1432
},
{
"epoch": 0.75,
"learning_rate": 1.7797966245487314e-05,
"loss": 1.2297,
"step": 1433
},
{
"epoch": 0.75,
"learning_rate": 1.7727584458749608e-05,
"loss": 1.1727,
"step": 1434
},
{
"epoch": 0.75,
"learning_rate": 1.7657312111245215e-05,
"loss": 1.3122,
"step": 1435
},
{
"epoch": 0.75,
"learning_rate": 1.7587149441275235e-05,
"loss": 1.1499,
"step": 1436
},
{
"epoch": 0.75,
"learning_rate": 1.751709668676882e-05,
"loss": 1.4439,
"step": 1437
},
{
"epoch": 0.75,
"learning_rate": 1.7447154085282396e-05,
"loss": 1.1983,
"step": 1438
},
{
"epoch": 0.75,
"learning_rate": 1.737732187399886e-05,
"loss": 1.0593,
"step": 1439
},
{
"epoch": 0.76,
"learning_rate": 1.7307600289726746e-05,
"loss": 1.1317,
"step": 1440
},
{
"epoch": 0.76,
"learning_rate": 1.7237989568899443e-05,
"loss": 1.016,
"step": 1441
},
{
"epoch": 0.76,
"learning_rate": 1.7168489947574406e-05,
"loss": 1.3522,
"step": 1442
},
{
"epoch": 0.76,
"learning_rate": 1.7099101661432328e-05,
"loss": 1.318,
"step": 1443
},
{
"epoch": 0.76,
"learning_rate": 1.7029824945776345e-05,
"loss": 1.1763,
"step": 1444
},
{
"epoch": 0.76,
"learning_rate": 1.6960660035531256e-05,
"loss": 1.1405,
"step": 1445
},
{
"epoch": 0.76,
"learning_rate": 1.6891607165242716e-05,
"loss": 1.1446,
"step": 1446
},
{
"epoch": 0.76,
"learning_rate": 1.6822666569076434e-05,
"loss": 1.1657,
"step": 1447
},
{
"epoch": 0.76,
"learning_rate": 1.6753838480817398e-05,
"loss": 1.2864,
"step": 1448
},
{
"epoch": 0.76,
"learning_rate": 1.6685123133869044e-05,
"loss": 1.0678,
"step": 1449
},
{
"epoch": 0.76,
"learning_rate": 1.661652076125252e-05,
"loss": 1.2132,
"step": 1450
},
{
"epoch": 0.76,
"learning_rate": 1.654803159560583e-05,
"loss": 1.3107,
"step": 1451
},
{
"epoch": 0.76,
"learning_rate": 1.647965586918314e-05,
"loss": 0.9526,
"step": 1452
},
{
"epoch": 0.76,
"learning_rate": 1.6411393813853892e-05,
"loss": 1.3004,
"step": 1453
},
{
"epoch": 0.76,
"learning_rate": 1.634324566110203e-05,
"loss": 1.1973,
"step": 1454
},
{
"epoch": 0.76,
"learning_rate": 1.6275211642025285e-05,
"loss": 1.584,
"step": 1455
},
{
"epoch": 0.76,
"learning_rate": 1.6207291987334338e-05,
"loss": 1.0228,
"step": 1456
},
{
"epoch": 0.76,
"learning_rate": 1.613948692735205e-05,
"loss": 1.1348,
"step": 1457
},
{
"epoch": 0.76,
"learning_rate": 1.6071796692012663e-05,
"loss": 0.9529,
"step": 1458
},
{
"epoch": 0.77,
"learning_rate": 1.6004221510861057e-05,
"loss": 1.2817,
"step": 1459
},
{
"epoch": 0.77,
"learning_rate": 1.5936761613051937e-05,
"loss": 1.1639,
"step": 1460
},
{
"epoch": 0.77,
"learning_rate": 1.5869417227349075e-05,
"loss": 0.9147,
"step": 1461
},
{
"epoch": 0.77,
"learning_rate": 1.5802188582124538e-05,
"loss": 1.2894,
"step": 1462
},
{
"epoch": 0.77,
"learning_rate": 1.5735075905357884e-05,
"loss": 1.0294,
"step": 1463
},
{
"epoch": 0.77,
"learning_rate": 1.5668079424635424e-05,
"loss": 1.0803,
"step": 1464
},
{
"epoch": 0.77,
"learning_rate": 1.5601199367149432e-05,
"loss": 1.0402,
"step": 1465
},
{
"epoch": 0.77,
"learning_rate": 1.5534435959697363e-05,
"loss": 1.0795,
"step": 1466
},
{
"epoch": 0.77,
"learning_rate": 1.5467789428681146e-05,
"loss": 1.3021,
"step": 1467
},
{
"epoch": 0.77,
"learning_rate": 1.540126000010632e-05,
"loss": 1.267,
"step": 1468
},
{
"epoch": 0.77,
"learning_rate": 1.5334847899581346e-05,
"loss": 1.2536,
"step": 1469
},
{
"epoch": 0.77,
"learning_rate": 1.5268553352316788e-05,
"loss": 1.1807,
"step": 1470
},
{
"epoch": 0.77,
"learning_rate": 1.5202376583124616e-05,
"loss": 1.1125,
"step": 1471
},
{
"epoch": 0.77,
"learning_rate": 1.5136317816417334e-05,
"loss": 1.356,
"step": 1472
},
{
"epoch": 0.77,
"learning_rate": 1.5070377276207348e-05,
"loss": 1.2827,
"step": 1473
},
{
"epoch": 0.77,
"learning_rate": 1.5004555186106122e-05,
"loss": 1.2565,
"step": 1474
},
{
"epoch": 0.77,
"learning_rate": 1.4938851769323447e-05,
"loss": 1.1855,
"step": 1475
},
{
"epoch": 0.77,
"learning_rate": 1.4873267248666678e-05,
"loss": 1.3973,
"step": 1476
},
{
"epoch": 0.77,
"learning_rate": 1.4807801846539976e-05,
"loss": 1.1853,
"step": 1477
},
{
"epoch": 0.78,
"learning_rate": 1.4742455784943576e-05,
"loss": 1.5008,
"step": 1478
},
{
"epoch": 0.78,
"learning_rate": 1.4677229285472988e-05,
"loss": 0.9897,
"step": 1479
},
{
"epoch": 0.78,
"learning_rate": 1.4612122569318281e-05,
"loss": 1.4022,
"step": 1480
},
{
"epoch": 0.78,
"learning_rate": 1.4547135857263371e-05,
"loss": 1.1371,
"step": 1481
},
{
"epoch": 0.78,
"learning_rate": 1.448226936968517e-05,
"loss": 0.9957,
"step": 1482
},
{
"epoch": 0.78,
"learning_rate": 1.4417523326552912e-05,
"loss": 1.3553,
"step": 1483
},
{
"epoch": 0.78,
"learning_rate": 1.4352897947427396e-05,
"loss": 1.2868,
"step": 1484
},
{
"epoch": 0.78,
"learning_rate": 1.4288393451460248e-05,
"loss": 1.1517,
"step": 1485
},
{
"epoch": 0.78,
"learning_rate": 1.4224010057393139e-05,
"loss": 1.1406,
"step": 1486
},
{
"epoch": 0.78,
"learning_rate": 1.4159747983557092e-05,
"loss": 1.1375,
"step": 1487
},
{
"epoch": 0.78,
"learning_rate": 1.4095607447871712e-05,
"loss": 1.3648,
"step": 1488
},
{
"epoch": 0.78,
"learning_rate": 1.4031588667844476e-05,
"loss": 1.1563,
"step": 1489
},
{
"epoch": 0.78,
"learning_rate": 1.3967691860569915e-05,
"loss": 1.1333,
"step": 1490
},
{
"epoch": 0.78,
"learning_rate": 1.3903917242729003e-05,
"loss": 1.3929,
"step": 1491
},
{
"epoch": 0.78,
"learning_rate": 1.3840265030588323e-05,
"loss": 1.2062,
"step": 1492
},
{
"epoch": 0.78,
"learning_rate": 1.3776735439999378e-05,
"loss": 1.17,
"step": 1493
},
{
"epoch": 0.78,
"learning_rate": 1.371332868639783e-05,
"loss": 1.1508,
"step": 1494
},
{
"epoch": 0.78,
"learning_rate": 1.3650044984802829e-05,
"loss": 1.4525,
"step": 1495
},
{
"epoch": 0.78,
"learning_rate": 1.358688454981621e-05,
"loss": 1.3368,
"step": 1496
},
{
"epoch": 0.79,
"learning_rate": 1.352384759562179e-05,
"loss": 1.2405,
"step": 1497
},
{
"epoch": 0.79,
"learning_rate": 1.3460934335984677e-05,
"loss": 1.2914,
"step": 1498
},
{
"epoch": 0.79,
"learning_rate": 1.3398144984250494e-05,
"loss": 1.3549,
"step": 1499
},
{
"epoch": 0.79,
"learning_rate": 1.3335479753344687e-05,
"loss": 1.0794,
"step": 1500
},
{
"epoch": 0.79,
"learning_rate": 1.3272938855771805e-05,
"loss": 1.275,
"step": 1501
},
{
"epoch": 0.79,
"learning_rate": 1.3210522503614754e-05,
"loss": 1.3397,
"step": 1502
},
{
"epoch": 0.79,
"learning_rate": 1.3148230908534098e-05,
"loss": 1.0313,
"step": 1503
},
{
"epoch": 0.79,
"learning_rate": 1.3086064281767346e-05,
"loss": 1.286,
"step": 1504
},
{
"epoch": 0.79,
"learning_rate": 1.3024022834128208e-05,
"loss": 1.2771,
"step": 1505
},
{
"epoch": 0.79,
"learning_rate": 1.2962106776005916e-05,
"loss": 1.1995,
"step": 1506
},
{
"epoch": 0.79,
"learning_rate": 1.2900316317364497e-05,
"loss": 1.4086,
"step": 1507
},
{
"epoch": 0.79,
"learning_rate": 1.2838651667742012e-05,
"loss": 1.0927,
"step": 1508
},
{
"epoch": 0.79,
"learning_rate": 1.2777113036249928e-05,
"loss": 1.1783,
"step": 1509
},
{
"epoch": 0.79,
"learning_rate": 1.2715700631572386e-05,
"loss": 1.4828,
"step": 1510
},
{
"epoch": 0.79,
"learning_rate": 1.2654414661965447e-05,
"loss": 1.199,
"step": 1511
},
{
"epoch": 0.79,
"learning_rate": 1.2593255335256437e-05,
"loss": 1.346,
"step": 1512
},
{
"epoch": 0.79,
"learning_rate": 1.25322228588432e-05,
"loss": 1.2825,
"step": 1513
},
{
"epoch": 0.79,
"learning_rate": 1.2471317439693436e-05,
"loss": 1.3238,
"step": 1514
},
{
"epoch": 0.79,
"learning_rate": 1.2410539284343976e-05,
"loss": 1.2738,
"step": 1515
},
{
"epoch": 0.8,
"learning_rate": 1.2349888598900077e-05,
"loss": 1.1887,
"step": 1516
},
{
"epoch": 0.8,
"learning_rate": 1.2289365589034745e-05,
"loss": 1.1967,
"step": 1517
},
{
"epoch": 0.8,
"learning_rate": 1.2228970459988015e-05,
"loss": 1.0423,
"step": 1518
},
{
"epoch": 0.8,
"learning_rate": 1.2168703416566274e-05,
"loss": 1.104,
"step": 1519
},
{
"epoch": 0.8,
"learning_rate": 1.2108564663141542e-05,
"loss": 1.3101,
"step": 1520
},
{
"epoch": 0.8,
"learning_rate": 1.2048554403650803e-05,
"loss": 1.224,
"step": 1521
},
{
"epoch": 0.8,
"learning_rate": 1.198867284159531e-05,
"loss": 1.2758,
"step": 1522
},
{
"epoch": 0.8,
"learning_rate": 1.1928920180039877e-05,
"loss": 1.1773,
"step": 1523
},
{
"epoch": 0.8,
"learning_rate": 1.1869296621612209e-05,
"loss": 1.2702,
"step": 1524
},
{
"epoch": 0.8,
"learning_rate": 1.180980236850221e-05,
"loss": 1.1148,
"step": 1525
},
{
"epoch": 0.8,
"learning_rate": 1.175043762246129e-05,
"loss": 1.2368,
"step": 1526
},
{
"epoch": 0.8,
"learning_rate": 1.1691202584801692e-05,
"loss": 0.8922,
"step": 1527
},
{
"epoch": 0.8,
"learning_rate": 1.1632097456395802e-05,
"loss": 1.2246,
"step": 1528
},
{
"epoch": 0.8,
"learning_rate": 1.1573122437675466e-05,
"loss": 1.2745,
"step": 1529
},
{
"epoch": 0.8,
"learning_rate": 1.1514277728631324e-05,
"loss": 1.2237,
"step": 1530
},
{
"epoch": 0.8,
"learning_rate": 1.1455563528812113e-05,
"loss": 1.3435,
"step": 1531
},
{
"epoch": 0.8,
"learning_rate": 1.1396980037324002e-05,
"loss": 1.2888,
"step": 1532
},
{
"epoch": 0.8,
"learning_rate": 1.1338527452829911e-05,
"loss": 1.3382,
"step": 1533
},
{
"epoch": 0.8,
"learning_rate": 1.128020597354884e-05,
"loss": 1.313,
"step": 1534
},
{
"epoch": 0.81,
"learning_rate": 1.122201579725521e-05,
"loss": 1.1705,
"step": 1535
},
{
"epoch": 0.81,
"learning_rate": 1.1163957121278163e-05,
"loss": 1.2137,
"step": 1536
},
{
"epoch": 0.81,
"learning_rate": 1.1106030142500917e-05,
"loss": 1.24,
"step": 1537
},
{
"epoch": 0.81,
"learning_rate": 1.104823505736009e-05,
"loss": 1.1323,
"step": 1538
},
{
"epoch": 0.81,
"learning_rate": 1.0990572061845034e-05,
"loss": 1.2191,
"step": 1539
},
{
"epoch": 0.81,
"learning_rate": 1.093304135149717e-05,
"loss": 1.0818,
"step": 1540
},
{
"epoch": 0.81,
"learning_rate": 1.0875643121409307e-05,
"loss": 1.2488,
"step": 1541
},
{
"epoch": 0.81,
"learning_rate": 1.0818377566225074e-05,
"loss": 1.1697,
"step": 1542
},
{
"epoch": 0.81,
"learning_rate": 1.0761244880138078e-05,
"loss": 1.0373,
"step": 1543
},
{
"epoch": 0.81,
"learning_rate": 1.0704245256891421e-05,
"loss": 1.1307,
"step": 1544
},
{
"epoch": 0.81,
"learning_rate": 1.0647378889776954e-05,
"loss": 1.3626,
"step": 1545
},
{
"epoch": 0.81,
"learning_rate": 1.0590645971634655e-05,
"loss": 1.3001,
"step": 1546
},
{
"epoch": 0.81,
"learning_rate": 1.0534046694851945e-05,
"loss": 1.1761,
"step": 1547
},
{
"epoch": 0.81,
"learning_rate": 1.0477581251363067e-05,
"loss": 0.9441,
"step": 1548
},
{
"epoch": 0.81,
"learning_rate": 1.0421249832648417e-05,
"loss": 1.1267,
"step": 1549
},
{
"epoch": 0.81,
"learning_rate": 1.0365052629733884e-05,
"loss": 1.2547,
"step": 1550
},
{
"epoch": 0.81,
"learning_rate": 1.030898983319024e-05,
"loss": 1.1233,
"step": 1551
},
{
"epoch": 0.81,
"learning_rate": 1.0253061633132461e-05,
"loss": 0.9727,
"step": 1552
},
{
"epoch": 0.81,
"learning_rate": 1.0197268219219087e-05,
"loss": 1.0764,
"step": 1553
},
{
"epoch": 0.82,
"learning_rate": 1.0141609780651584e-05,
"loss": 1.1134,
"step": 1554
},
{
"epoch": 0.82,
"learning_rate": 1.008608650617371e-05,
"loss": 1.0289,
"step": 1555
},
{
"epoch": 0.82,
"learning_rate": 1.0030698584070847e-05,
"loss": 1.246,
"step": 1556
},
{
"epoch": 0.82,
"learning_rate": 9.975446202169431e-06,
"loss": 1.1342,
"step": 1557
},
{
"epoch": 0.82,
"learning_rate": 9.92032954783621e-06,
"loss": 1.4847,
"step": 1558
},
{
"epoch": 0.82,
"learning_rate": 9.865348807977698e-06,
"loss": 1.0856,
"step": 1559
},
{
"epoch": 0.82,
"learning_rate": 9.810504169039509e-06,
"loss": 1.115,
"step": 1560
},
{
"epoch": 0.82,
"learning_rate": 9.755795817005686e-06,
"loss": 1.3651,
"step": 1561
},
{
"epoch": 0.82,
"learning_rate": 9.701223937398152e-06,
"loss": 1.1679,
"step": 1562
},
{
"epoch": 0.82,
"learning_rate": 9.646788715276023e-06,
"loss": 0.8894,
"step": 1563
},
{
"epoch": 0.82,
"learning_rate": 9.592490335234994e-06,
"loss": 1.3147,
"step": 1564
},
{
"epoch": 0.82,
"learning_rate": 9.538328981406713e-06,
"loss": 1.2616,
"step": 1565
},
{
"epoch": 0.82,
"learning_rate": 9.484304837458157e-06,
"loss": 1.1916,
"step": 1566
},
{
"epoch": 0.82,
"learning_rate": 9.430418086591009e-06,
"loss": 1.0985,
"step": 1567
},
{
"epoch": 0.82,
"learning_rate": 9.376668911541042e-06,
"loss": 1.1392,
"step": 1568
},
{
"epoch": 0.82,
"learning_rate": 9.323057494577498e-06,
"loss": 1.0583,
"step": 1569
},
{
"epoch": 0.82,
"learning_rate": 9.269584017502431e-06,
"loss": 1.1925,
"step": 1570
},
{
"epoch": 0.82,
"learning_rate": 9.216248661650195e-06,
"loss": 1.4009,
"step": 1571
},
{
"epoch": 0.82,
"learning_rate": 9.163051607886703e-06,
"loss": 1.0857,
"step": 1572
},
{
"epoch": 0.83,
"learning_rate": 9.109993036608883e-06,
"loss": 1.4733,
"step": 1573
},
{
"epoch": 0.83,
"learning_rate": 9.057073127744064e-06,
"loss": 1.3363,
"step": 1574
},
{
"epoch": 0.83,
"learning_rate": 9.004292060749348e-06,
"loss": 1.2422,
"step": 1575
},
{
"epoch": 0.83,
"learning_rate": 8.951650014611018e-06,
"loss": 1.3727,
"step": 1576
},
{
"epoch": 0.83,
"learning_rate": 8.899147167843908e-06,
"loss": 1.0963,
"step": 1577
},
{
"epoch": 0.83,
"learning_rate": 8.846783698490834e-06,
"loss": 1.3198,
"step": 1578
},
{
"epoch": 0.83,
"learning_rate": 8.794559784121937e-06,
"loss": 1.4718,
"step": 1579
},
{
"epoch": 0.83,
"learning_rate": 8.742475601834132e-06,
"loss": 1.237,
"step": 1580
},
{
"epoch": 0.83,
"learning_rate": 8.690531328250489e-06,
"loss": 1.3897,
"step": 1581
},
{
"epoch": 0.83,
"learning_rate": 8.638727139519636e-06,
"loss": 1.2511,
"step": 1582
},
{
"epoch": 0.83,
"learning_rate": 8.587063211315139e-06,
"loss": 1.1449,
"step": 1583
},
{
"epoch": 0.83,
"learning_rate": 8.535539718834929e-06,
"loss": 1.1666,
"step": 1584
},
{
"epoch": 0.83,
"learning_rate": 8.484156836800739e-06,
"loss": 1.1349,
"step": 1585
},
{
"epoch": 0.83,
"learning_rate": 8.432914739457432e-06,
"loss": 1.1784,
"step": 1586
},
{
"epoch": 0.83,
"learning_rate": 8.381813600572481e-06,
"loss": 1.0811,
"step": 1587
},
{
"epoch": 0.83,
"learning_rate": 8.330853593435345e-06,
"loss": 0.9825,
"step": 1588
},
{
"epoch": 0.83,
"learning_rate": 8.280034890856885e-06,
"loss": 1.2873,
"step": 1589
},
{
"epoch": 0.83,
"learning_rate": 8.22935766516879e-06,
"loss": 1.0751,
"step": 1590
},
{
"epoch": 0.83,
"learning_rate": 8.178822088222993e-06,
"loss": 1.3585,
"step": 1591
},
{
"epoch": 0.84,
"learning_rate": 8.12842833139107e-06,
"loss": 1.2388,
"step": 1592
},
{
"epoch": 0.84,
"learning_rate": 8.078176565563661e-06,
"loss": 1.2442,
"step": 1593
},
{
"epoch": 0.84,
"learning_rate": 8.02806696114992e-06,
"loss": 1.3153,
"step": 1594
},
{
"epoch": 0.84,
"learning_rate": 7.978099688076913e-06,
"loss": 0.9505,
"step": 1595
},
{
"epoch": 0.84,
"learning_rate": 7.928274915789036e-06,
"loss": 1.2725,
"step": 1596
},
{
"epoch": 0.84,
"learning_rate": 7.878592813247443e-06,
"loss": 1.1283,
"step": 1597
},
{
"epoch": 0.84,
"learning_rate": 7.829053548929489e-06,
"loss": 1.1668,
"step": 1598
},
{
"epoch": 0.84,
"learning_rate": 7.779657290828146e-06,
"loss": 1.2682,
"step": 1599
},
{
"epoch": 0.84,
"learning_rate": 7.730404206451457e-06,
"loss": 1.1203,
"step": 1600
},
{
"epoch": 0.84,
"learning_rate": 7.681294462821925e-06,
"loss": 1.2335,
"step": 1601
},
{
"epoch": 0.84,
"learning_rate": 7.632328226475971e-06,
"loss": 0.9757,
"step": 1602
},
{
"epoch": 0.84,
"learning_rate": 7.58350566346337e-06,
"loss": 1.3396,
"step": 1603
},
{
"epoch": 0.84,
"learning_rate": 7.5348269393466896e-06,
"loss": 0.9868,
"step": 1604
},
{
"epoch": 0.84,
"learning_rate": 7.486292219200713e-06,
"loss": 1.1997,
"step": 1605
},
{
"epoch": 0.84,
"learning_rate": 7.437901667611907e-06,
"loss": 1.3741,
"step": 1606
},
{
"epoch": 0.84,
"learning_rate": 7.389655448677835e-06,
"loss": 1.2155,
"step": 1607
},
{
"epoch": 0.84,
"learning_rate": 7.341553726006611e-06,
"loss": 0.9943,
"step": 1608
},
{
"epoch": 0.84,
"learning_rate": 7.293596662716362e-06,
"loss": 1.1267,
"step": 1609
},
{
"epoch": 0.84,
"learning_rate": 7.2457844214346425e-06,
"loss": 1.34,
"step": 1610
},
{
"epoch": 0.85,
"learning_rate": 7.198117164297907e-06,
"loss": 1.2177,
"step": 1611
},
{
"epoch": 0.85,
"learning_rate": 7.150595052950954e-06,
"loss": 1.1015,
"step": 1612
},
{
"epoch": 0.85,
"learning_rate": 7.103218248546378e-06,
"loss": 1.0381,
"step": 1613
},
{
"epoch": 0.85,
"learning_rate": 7.055986911744017e-06,
"loss": 1.0556,
"step": 1614
},
{
"epoch": 0.85,
"learning_rate": 7.0089012027104165e-06,
"loss": 1.1059,
"step": 1615
},
{
"epoch": 0.85,
"learning_rate": 6.961961281118284e-06,
"loss": 1.1099,
"step": 1616
},
{
"epoch": 0.85,
"learning_rate": 6.915167306145942e-06,
"loss": 1.2652,
"step": 1617
},
{
"epoch": 0.85,
"learning_rate": 6.868519436476795e-06,
"loss": 1.2154,
"step": 1618
},
{
"epoch": 0.85,
"learning_rate": 6.822017830298788e-06,
"loss": 1.2193,
"step": 1619
},
{
"epoch": 0.85,
"learning_rate": 6.775662645303871e-06,
"loss": 1.1096,
"step": 1620
},
{
"epoch": 0.85,
"learning_rate": 6.7294540386874605e-06,
"loss": 1.2095,
"step": 1621
},
{
"epoch": 0.85,
"learning_rate": 6.683392167147917e-06,
"loss": 1.0729,
"step": 1622
},
{
"epoch": 0.85,
"learning_rate": 6.6374771868860045e-06,
"loss": 1.461,
"step": 1623
},
{
"epoch": 0.85,
"learning_rate": 6.591709253604356e-06,
"loss": 1.1322,
"step": 1624
},
{
"epoch": 0.85,
"learning_rate": 6.546088522506955e-06,
"loss": 1.1282,
"step": 1625
},
{
"epoch": 0.85,
"learning_rate": 6.500615148298617e-06,
"loss": 1.1667,
"step": 1626
},
{
"epoch": 0.85,
"learning_rate": 6.455289285184446e-06,
"loss": 1.1554,
"step": 1627
},
{
"epoch": 0.85,
"learning_rate": 6.410111086869314e-06,
"loss": 0.9844,
"step": 1628
},
{
"epoch": 0.85,
"learning_rate": 6.365080706557352e-06,
"loss": 1.2855,
"step": 1629
},
{
"epoch": 0.86,
"learning_rate": 6.320198296951435e-06,
"loss": 1.278,
"step": 1630
},
{
"epoch": 0.86,
"learning_rate": 6.275464010252629e-06,
"loss": 1.1833,
"step": 1631
},
{
"epoch": 0.86,
"learning_rate": 6.230877998159723e-06,
"loss": 1.3404,
"step": 1632
},
{
"epoch": 0.86,
"learning_rate": 6.186440411868682e-06,
"loss": 1.1578,
"step": 1633
},
{
"epoch": 0.86,
"learning_rate": 6.142151402072132e-06,
"loss": 1.3695,
"step": 1634
},
{
"epoch": 0.86,
"learning_rate": 6.098011118958885e-06,
"loss": 1.2596,
"step": 1635
},
{
"epoch": 0.86,
"learning_rate": 6.054019712213377e-06,
"loss": 1.0202,
"step": 1636
},
{
"epoch": 0.86,
"learning_rate": 6.010177331015204e-06,
"loss": 1.1857,
"step": 1637
},
{
"epoch": 0.86,
"learning_rate": 5.966484124038602e-06,
"loss": 0.9059,
"step": 1638
},
{
"epoch": 0.86,
"learning_rate": 5.922940239451935e-06,
"loss": 1.4132,
"step": 1639
},
{
"epoch": 0.86,
"learning_rate": 5.879545824917199e-06,
"loss": 1.1798,
"step": 1640
},
{
"epoch": 0.86,
"learning_rate": 5.836301027589525e-06,
"loss": 1.1492,
"step": 1641
},
{
"epoch": 0.86,
"learning_rate": 5.793205994116674e-06,
"loss": 1.4875,
"step": 1642
},
{
"epoch": 0.86,
"learning_rate": 5.75026087063854e-06,
"loss": 1.3959,
"step": 1643
},
{
"epoch": 0.86,
"learning_rate": 5.707465802786654e-06,
"loss": 0.9615,
"step": 1644
},
{
"epoch": 0.86,
"learning_rate": 5.664820935683696e-06,
"loss": 1.3538,
"step": 1645
},
{
"epoch": 0.86,
"learning_rate": 5.622326413942996e-06,
"loss": 1.2193,
"step": 1646
},
{
"epoch": 0.86,
"learning_rate": 5.5799823816680586e-06,
"loss": 1.0537,
"step": 1647
},
{
"epoch": 0.86,
"learning_rate": 5.537788982452052e-06,
"loss": 1.1547,
"step": 1648
},
{
"epoch": 0.87,
"learning_rate": 5.495746359377335e-06,
"loss": 1.3141,
"step": 1649
},
{
"epoch": 0.87,
"learning_rate": 5.453854655014956e-06,
"loss": 1.3389,
"step": 1650
},
{
"epoch": 0.87,
"learning_rate": 5.412114011424191e-06,
"loss": 1.0036,
"step": 1651
},
{
"epoch": 0.87,
"learning_rate": 5.370524570152058e-06,
"loss": 1.0442,
"step": 1652
},
{
"epoch": 0.87,
"learning_rate": 5.329086472232825e-06,
"loss": 1.2034,
"step": 1653
},
{
"epoch": 0.87,
"learning_rate": 5.287799858187548e-06,
"loss": 1.3755,
"step": 1654
},
{
"epoch": 0.87,
"learning_rate": 5.2466648680235654e-06,
"loss": 1.0389,
"step": 1655
},
{
"epoch": 0.87,
"learning_rate": 5.205681641234061e-06,
"loss": 1.3614,
"step": 1656
},
{
"epoch": 0.87,
"learning_rate": 5.1648503167975705e-06,
"loss": 1.2396,
"step": 1657
},
{
"epoch": 0.87,
"learning_rate": 5.124171033177499e-06,
"loss": 1.1014,
"step": 1658
},
{
"epoch": 0.87,
"learning_rate": 5.083643928321679e-06,
"loss": 1.2946,
"step": 1659
},
{
"epoch": 0.87,
"learning_rate": 5.043269139661871e-06,
"loss": 1.1439,
"step": 1660
},
{
"epoch": 0.87,
"learning_rate": 5.0030468041133535e-06,
"loss": 0.9891,
"step": 1661
},
{
"epoch": 0.87,
"learning_rate": 4.962977058074381e-06,
"loss": 1.2912,
"step": 1662
},
{
"epoch": 0.87,
"learning_rate": 4.92306003742577e-06,
"loss": 1.3515,
"step": 1663
},
{
"epoch": 0.87,
"learning_rate": 4.88329587753043e-06,
"loss": 1.0298,
"step": 1664
},
{
"epoch": 0.87,
"learning_rate": 4.843684713232915e-06,
"loss": 1.3006,
"step": 1665
},
{
"epoch": 0.87,
"learning_rate": 4.804226678858936e-06,
"loss": 1.1417,
"step": 1666
},
{
"epoch": 0.87,
"learning_rate": 4.7649219082149475e-06,
"loss": 1.191,
"step": 1667
},
{
"epoch": 0.88,
"learning_rate": 4.7257705345876365e-06,
"loss": 1.3271,
"step": 1668
},
{
"epoch": 0.88,
"learning_rate": 4.686772690743529e-06,
"loss": 1.4339,
"step": 1669
},
{
"epoch": 0.88,
"learning_rate": 4.647928508928512e-06,
"loss": 1.1019,
"step": 1670
},
{
"epoch": 0.88,
"learning_rate": 4.609238120867387e-06,
"loss": 0.9552,
"step": 1671
},
{
"epoch": 0.88,
"learning_rate": 4.570701657763415e-06,
"loss": 1.3462,
"step": 1672
},
{
"epoch": 0.88,
"learning_rate": 4.532319250297901e-06,
"loss": 1.3213,
"step": 1673
},
{
"epoch": 0.88,
"learning_rate": 4.494091028629699e-06,
"loss": 1.3868,
"step": 1674
},
{
"epoch": 0.88,
"learning_rate": 4.4560171223948455e-06,
"loss": 1.2072,
"step": 1675
},
{
"epoch": 0.88,
"learning_rate": 4.418097660706039e-06,
"loss": 1.5743,
"step": 1676
},
{
"epoch": 0.88,
"learning_rate": 4.380332772152257e-06,
"loss": 1.1274,
"step": 1677
},
{
"epoch": 0.88,
"learning_rate": 4.342722584798298e-06,
"loss": 1.1995,
"step": 1678
},
{
"epoch": 0.88,
"learning_rate": 4.305267226184356e-06,
"loss": 1.1405,
"step": 1679
},
{
"epoch": 0.88,
"learning_rate": 4.267966823325581e-06,
"loss": 1.0487,
"step": 1680
},
{
"epoch": 0.88,
"learning_rate": 4.230821502711657e-06,
"loss": 1.0078,
"step": 1681
},
{
"epoch": 0.88,
"learning_rate": 4.193831390306352e-06,
"loss": 1.1674,
"step": 1682
},
{
"epoch": 0.88,
"learning_rate": 4.1569966115471255e-06,
"loss": 1.0929,
"step": 1683
},
{
"epoch": 0.88,
"learning_rate": 4.1203172913446775e-06,
"loss": 1.5074,
"step": 1684
},
{
"epoch": 0.88,
"learning_rate": 4.083793554082521e-06,
"loss": 1.1008,
"step": 1685
},
{
"epoch": 0.88,
"learning_rate": 4.047425523616577e-06,
"loss": 1.1701,
"step": 1686
},
{
"epoch": 0.88,
"learning_rate": 4.01121332327476e-06,
"loss": 1.0381,
"step": 1687
},
{
"epoch": 0.89,
"learning_rate": 3.975157075856528e-06,
"loss": 1.1124,
"step": 1688
},
{
"epoch": 0.89,
"learning_rate": 3.939256903632494e-06,
"loss": 1.1795,
"step": 1689
},
{
"epoch": 0.89,
"learning_rate": 3.903512928344017e-06,
"loss": 1.1264,
"step": 1690
},
{
"epoch": 0.89,
"learning_rate": 3.867925271202755e-06,
"loss": 1.159,
"step": 1691
},
{
"epoch": 0.89,
"learning_rate": 3.832494052890284e-06,
"loss": 1.2922,
"step": 1692
},
{
"epoch": 0.89,
"learning_rate": 3.7972193935576774e-06,
"loss": 1.1712,
"step": 1693
},
{
"epoch": 0.89,
"learning_rate": 3.7621014128250977e-06,
"loss": 1.2098,
"step": 1694
},
{
"epoch": 0.89,
"learning_rate": 3.7271402297814006e-06,
"loss": 1.3432,
"step": 1695
},
{
"epoch": 0.89,
"learning_rate": 3.692335962983712e-06,
"loss": 1.4964,
"step": 1696
},
{
"epoch": 0.89,
"learning_rate": 3.657688730457054e-06,
"loss": 1.3647,
"step": 1697
},
{
"epoch": 0.89,
"learning_rate": 3.623198649693915e-06,
"loss": 1.2143,
"step": 1698
},
{
"epoch": 0.89,
"learning_rate": 3.5888658376538655e-06,
"loss": 1.1209,
"step": 1699
},
{
"epoch": 0.89,
"learning_rate": 3.554690410763173e-06,
"loss": 1.0583,
"step": 1700
},
{
"epoch": 0.89,
"learning_rate": 3.5206724849143837e-06,
"loss": 1.4116,
"step": 1701
},
{
"epoch": 0.89,
"learning_rate": 3.4868121754659533e-06,
"loss": 1.1682,
"step": 1702
},
{
"epoch": 0.89,
"learning_rate": 3.4531095972418105e-06,
"loss": 1.1478,
"step": 1703
},
{
"epoch": 0.89,
"learning_rate": 3.419564864531044e-06,
"loss": 1.4356,
"step": 1704
},
{
"epoch": 0.89,
"learning_rate": 3.386178091087444e-06,
"loss": 1.3359,
"step": 1705
},
{
"epoch": 0.89,
"learning_rate": 3.3529493901291564e-06,
"loss": 0.8788,
"step": 1706
},
{
"epoch": 0.9,
"learning_rate": 3.319878874338278e-06,
"loss": 1.1486,
"step": 1707
},
{
"epoch": 0.9,
"learning_rate": 3.286966655860485e-06,
"loss": 1.1786,
"step": 1708
},
{
"epoch": 0.9,
"learning_rate": 3.2542128463046497e-06,
"loss": 1.1263,
"step": 1709
},
{
"epoch": 0.9,
"learning_rate": 3.2216175567424734e-06,
"loss": 1.3651,
"step": 1710
},
{
"epoch": 0.9,
"learning_rate": 3.1891808977080826e-06,
"loss": 1.2084,
"step": 1711
},
{
"epoch": 0.9,
"learning_rate": 3.156902979197679e-06,
"loss": 1.022,
"step": 1712
},
{
"epoch": 0.9,
"learning_rate": 3.1247839106691543e-06,
"loss": 1.2045,
"step": 1713
},
{
"epoch": 0.9,
"learning_rate": 3.0928238010417275e-06,
"loss": 1.242,
"step": 1714
},
{
"epoch": 0.9,
"learning_rate": 3.061022758695575e-06,
"loss": 1.3751,
"step": 1715
},
{
"epoch": 0.9,
"learning_rate": 3.029380891471445e-06,
"loss": 1.1772,
"step": 1716
},
{
"epoch": 0.9,
"learning_rate": 2.9978983066703212e-06,
"loss": 1.2256,
"step": 1717
},
{
"epoch": 0.9,
"learning_rate": 2.966575111053027e-06,
"loss": 1.2171,
"step": 1718
},
{
"epoch": 0.9,
"learning_rate": 2.935411410839889e-06,
"loss": 1.2218,
"step": 1719
},
{
"epoch": 0.9,
"learning_rate": 2.9044073117103778e-06,
"loss": 1.1875,
"step": 1720
},
{
"epoch": 0.9,
"learning_rate": 2.8735629188027245e-06,
"loss": 1.0663,
"step": 1721
},
{
"epoch": 0.9,
"learning_rate": 2.842878336713578e-06,
"loss": 1.1733,
"step": 1722
},
{
"epoch": 0.9,
"learning_rate": 2.812353669497664e-06,
"loss": 1.1406,
"step": 1723
},
{
"epoch": 0.9,
"learning_rate": 2.7819890206674084e-06,
"loss": 0.8795,
"step": 1724
},
{
"epoch": 0.9,
"learning_rate": 2.7517844931926107e-06,
"loss": 1.2653,
"step": 1725
},
{
"epoch": 0.91,
"learning_rate": 2.721740189500066e-06,
"loss": 1.3022,
"step": 1726
},
{
"epoch": 0.91,
"learning_rate": 2.691856211473237e-06,
"loss": 1.0345,
"step": 1727
},
{
"epoch": 0.91,
"learning_rate": 2.6621326604519215e-06,
"loss": 1.327,
"step": 1728
},
{
"epoch": 0.91,
"learning_rate": 2.6325696372318688e-06,
"loss": 1.1517,
"step": 1729
},
{
"epoch": 0.91,
"learning_rate": 2.6031672420644692e-06,
"loss": 1.0326,
"step": 1730
},
{
"epoch": 0.91,
"learning_rate": 2.5739255746564216e-06,
"loss": 1.2462,
"step": 1731
},
{
"epoch": 0.91,
"learning_rate": 2.5448447341693495e-06,
"loss": 1.0468,
"step": 1732
},
{
"epoch": 0.91,
"learning_rate": 2.5159248192195283e-06,
"loss": 1.2062,
"step": 1733
},
{
"epoch": 0.91,
"learning_rate": 2.4871659278774883e-06,
"loss": 1.1731,
"step": 1734
},
{
"epoch": 0.91,
"learning_rate": 2.458568157667729e-06,
"loss": 1.0717,
"step": 1735
},
{
"epoch": 0.91,
"learning_rate": 2.430131605568353e-06,
"loss": 1.4119,
"step": 1736
},
{
"epoch": 0.91,
"learning_rate": 2.4018563680107962e-06,
"loss": 1.1063,
"step": 1737
},
{
"epoch": 0.91,
"learning_rate": 2.37374254087942e-06,
"loss": 1.3684,
"step": 1738
},
{
"epoch": 0.91,
"learning_rate": 2.3457902195112236e-06,
"loss": 1.0844,
"step": 1739
},
{
"epoch": 0.91,
"learning_rate": 2.31799949869555e-06,
"loss": 1.3613,
"step": 1740
},
{
"epoch": 0.91,
"learning_rate": 2.290370472673714e-06,
"loss": 0.9189,
"step": 1741
},
{
"epoch": 0.91,
"learning_rate": 2.262903235138725e-06,
"loss": 1.4039,
"step": 1742
},
{
"epoch": 0.91,
"learning_rate": 2.2355978792349295e-06,
"loss": 1.0626,
"step": 1743
},
{
"epoch": 0.91,
"learning_rate": 2.2084544975577383e-06,
"loss": 1.3145,
"step": 1744
},
{
"epoch": 0.92,
"learning_rate": 2.1814731821532762e-06,
"loss": 1.1313,
"step": 1745
},
{
"epoch": 0.92,
"learning_rate": 2.1546540245180826e-06,
"loss": 1.0545,
"step": 1746
},
{
"epoch": 0.92,
"learning_rate": 2.1279971155988066e-06,
"loss": 1.2812,
"step": 1747
},
{
"epoch": 0.92,
"learning_rate": 2.1015025457919004e-06,
"loss": 1.1375,
"step": 1748
},
{
"epoch": 0.92,
"learning_rate": 2.0751704049432943e-06,
"loss": 1.1879,
"step": 1749
},
{
"epoch": 0.92,
"learning_rate": 2.0490007823481092e-06,
"loss": 0.9773,
"step": 1750
},
{
"epoch": 0.92,
"learning_rate": 2.022993766750364e-06,
"loss": 1.3692,
"step": 1751
},
{
"epoch": 0.92,
"learning_rate": 1.997149446342633e-06,
"loss": 1.2848,
"step": 1752
},
{
"epoch": 0.92,
"learning_rate": 1.971467908765795e-06,
"loss": 0.9358,
"step": 1753
},
{
"epoch": 0.92,
"learning_rate": 1.945949241108708e-06,
"loss": 1.2165,
"step": 1754
},
{
"epoch": 0.92,
"learning_rate": 1.920593529907916e-06,
"loss": 1.0563,
"step": 1755
},
{
"epoch": 0.92,
"learning_rate": 1.8954008611473616e-06,
"loss": 1.2586,
"step": 1756
},
{
"epoch": 0.92,
"learning_rate": 1.8703713202580963e-06,
"loss": 1.4222,
"step": 1757
},
{
"epoch": 0.92,
"learning_rate": 1.8455049921179856e-06,
"loss": 1.2894,
"step": 1758
},
{
"epoch": 0.92,
"learning_rate": 1.820801961051427e-06,
"loss": 1.1405,
"step": 1759
},
{
"epoch": 0.92,
"learning_rate": 1.7962623108290554e-06,
"loss": 1.2014,
"step": 1760
},
{
"epoch": 0.92,
"learning_rate": 1.7718861246674656e-06,
"loss": 1.1223,
"step": 1761
},
{
"epoch": 0.92,
"learning_rate": 1.7476734852289234e-06,
"loss": 1.23,
"step": 1762
},
{
"epoch": 0.92,
"learning_rate": 1.7236244746210994e-06,
"loss": 1.2078,
"step": 1763
},
{
"epoch": 0.93,
"learning_rate": 1.6997391743967695e-06,
"loss": 0.9517,
"step": 1764
},
{
"epoch": 0.93,
"learning_rate": 1.6760176655535641e-06,
"loss": 1.1362,
"step": 1765
},
{
"epoch": 0.93,
"learning_rate": 1.65246002853367e-06,
"loss": 1.1904,
"step": 1766
},
{
"epoch": 0.93,
"learning_rate": 1.629066343223562e-06,
"loss": 1.4042,
"step": 1767
},
{
"epoch": 0.93,
"learning_rate": 1.6058366889537547e-06,
"loss": 0.9662,
"step": 1768
},
{
"epoch": 0.93,
"learning_rate": 1.5827711444985016e-06,
"loss": 1.1057,
"step": 1769
},
{
"epoch": 0.93,
"learning_rate": 1.559869788075541e-06,
"loss": 1.3034,
"step": 1770
},
{
"epoch": 0.93,
"learning_rate": 1.5371326973458389e-06,
"loss": 1.1779,
"step": 1771
},
{
"epoch": 0.93,
"learning_rate": 1.514559949413319e-06,
"loss": 1.2365,
"step": 1772
},
{
"epoch": 0.93,
"learning_rate": 1.4921516208246e-06,
"loss": 1.4841,
"step": 1773
},
{
"epoch": 0.93,
"learning_rate": 1.4699077875687251e-06,
"loss": 0.9955,
"step": 1774
},
{
"epoch": 0.93,
"learning_rate": 1.447828525076933e-06,
"loss": 1.3027,
"step": 1775
},
{
"epoch": 0.93,
"learning_rate": 1.425913908222376e-06,
"loss": 1.2471,
"step": 1776
},
{
"epoch": 0.93,
"learning_rate": 1.404164011319875e-06,
"loss": 1.2244,
"step": 1777
},
{
"epoch": 0.93,
"learning_rate": 1.3825789081256813e-06,
"loss": 1.0797,
"step": 1778
},
{
"epoch": 0.93,
"learning_rate": 1.3611586718371871e-06,
"loss": 1.2535,
"step": 1779
},
{
"epoch": 0.93,
"learning_rate": 1.3399033750927325e-06,
"loss": 1.3052,
"step": 1780
},
{
"epoch": 0.93,
"learning_rate": 1.3188130899713102e-06,
"loss": 1.2229,
"step": 1781
},
{
"epoch": 0.93,
"learning_rate": 1.2978878879923439e-06,
"loss": 1.1745,
"step": 1782
},
{
"epoch": 0.94,
"learning_rate": 1.2771278401154495e-06,
"loss": 1.116,
"step": 1783
},
{
"epoch": 0.94,
"learning_rate": 1.2565330167401745e-06,
"loss": 1.1535,
"step": 1784
},
{
"epoch": 0.94,
"learning_rate": 1.236103487705792e-06,
"loss": 1.6101,
"step": 1785
},
{
"epoch": 0.94,
"learning_rate": 1.2158393222910236e-06,
"loss": 1.2188,
"step": 1786
},
{
"epoch": 0.94,
"learning_rate": 1.1957405892138396e-06,
"loss": 1.4719,
"step": 1787
},
{
"epoch": 0.94,
"learning_rate": 1.175807356631209e-06,
"loss": 1.2328,
"step": 1788
},
{
"epoch": 0.94,
"learning_rate": 1.156039692138855e-06,
"loss": 1.1181,
"step": 1789
},
{
"epoch": 0.94,
"learning_rate": 1.1364376627710726e-06,
"loss": 1.3365,
"step": 1790
},
{
"epoch": 0.94,
"learning_rate": 1.1170013350004448e-06,
"loss": 1.1572,
"step": 1791
},
{
"epoch": 0.94,
"learning_rate": 1.097730774737643e-06,
"loss": 1.2458,
"step": 1792
},
{
"epoch": 0.94,
"learning_rate": 1.0786260473312105e-06,
"loss": 1.3213,
"step": 1793
},
{
"epoch": 0.94,
"learning_rate": 1.0596872175673455e-06,
"loss": 1.2084,
"step": 1794
},
{
"epoch": 0.94,
"learning_rate": 1.0409143496696527e-06,
"loss": 1.3271,
"step": 1795
},
{
"epoch": 0.94,
"learning_rate": 1.0223075072989418e-06,
"loss": 1.2337,
"step": 1796
},
{
"epoch": 0.94,
"learning_rate": 1.0038667535530232e-06,
"loss": 1.2558,
"step": 1797
},
{
"epoch": 0.94,
"learning_rate": 9.855921509664746e-07,
"loss": 1.1997,
"step": 1798
},
{
"epoch": 0.94,
"learning_rate": 9.674837615104349e-07,
"loss": 1.3758,
"step": 1799
},
{
"epoch": 0.94,
"learning_rate": 9.495416465924112e-07,
"loss": 1.0377,
"step": 1800
},
{
"epoch": 0.94,
"learning_rate": 9.317658670560336e-07,
"loss": 1.1146,
"step": 1801
},
{
"epoch": 0.95,
"learning_rate": 9.141564831808947e-07,
"loss": 0.9778,
"step": 1802
},
{
"epoch": 0.95,
"learning_rate": 8.967135546823047e-07,
"loss": 1.138,
"step": 1803
},
{
"epoch": 0.95,
"learning_rate": 8.794371407111091e-07,
"loss": 1.2464,
"step": 1804
},
{
"epoch": 0.95,
"learning_rate": 8.623272998534881e-07,
"loss": 1.2632,
"step": 1805
},
{
"epoch": 0.95,
"learning_rate": 8.453840901307519e-07,
"loss": 1.2735,
"step": 1806
},
{
"epoch": 0.95,
"learning_rate": 8.286075689991457e-07,
"loss": 1.1872,
"step": 1807
},
{
"epoch": 0.95,
"learning_rate": 8.11997793349667e-07,
"loss": 1.1971,
"step": 1808
},
{
"epoch": 0.95,
"learning_rate": 7.955548195078433e-07,
"loss": 1.3481,
"step": 1809
},
{
"epoch": 0.95,
"learning_rate": 7.792787032335658e-07,
"loss": 0.9743,
"step": 1810
},
{
"epoch": 0.95,
"learning_rate": 7.63169499720906e-07,
"loss": 1.2233,
"step": 1811
},
{
"epoch": 0.95,
"learning_rate": 7.472272635978994e-07,
"loss": 1.4467,
"step": 1812
},
{
"epoch": 0.95,
"learning_rate": 7.314520489263788e-07,
"loss": 1.3375,
"step": 1813
},
{
"epoch": 0.95,
"learning_rate": 7.158439092018076e-07,
"loss": 1.3292,
"step": 1814
},
{
"epoch": 0.95,
"learning_rate": 7.004028973530585e-07,
"loss": 1.0034,
"step": 1815
},
{
"epoch": 0.95,
"learning_rate": 6.851290657422627e-07,
"loss": 0.915,
"step": 1816
},
{
"epoch": 0.95,
"learning_rate": 6.700224661646326e-07,
"loss": 1.0902,
"step": 1817
},
{
"epoch": 0.95,
"learning_rate": 6.550831498482679e-07,
"loss": 1.0471,
"step": 1818
},
{
"epoch": 0.95,
"learning_rate": 6.403111674539997e-07,
"loss": 1.2116,
"step": 1819
},
{
"epoch": 0.95,
"learning_rate": 6.257065690752128e-07,
"loss": 0.9323,
"step": 1820
},
{
"epoch": 0.96,
"learning_rate": 6.112694042376632e-07,
"loss": 1.0216,
"step": 1821
},
{
"epoch": 0.96,
"learning_rate": 5.969997218993328e-07,
"loss": 1.1321,
"step": 1822
},
{
"epoch": 0.96,
"learning_rate": 5.828975704502582e-07,
"loss": 1.0969,
"step": 1823
},
{
"epoch": 0.96,
"learning_rate": 5.689629977123412e-07,
"loss": 1.3603,
"step": 1824
},
{
"epoch": 0.96,
"learning_rate": 5.551960509392218e-07,
"loss": 1.1131,
"step": 1825
},
{
"epoch": 0.96,
"learning_rate": 5.415967768160945e-07,
"loss": 1.1443,
"step": 1826
},
{
"epoch": 0.96,
"learning_rate": 5.2816522145957e-07,
"loss": 1.2909,
"step": 1827
},
{
"epoch": 0.96,
"learning_rate": 5.149014304174915e-07,
"loss": 1.4178,
"step": 1828
},
{
"epoch": 0.96,
"learning_rate": 5.018054486687962e-07,
"loss": 1.0522,
"step": 1829
},
{
"epoch": 0.96,
"learning_rate": 4.888773206233765e-07,
"loss": 1.2744,
"step": 1830
},
{
"epoch": 0.96,
"learning_rate": 4.7611709012190253e-07,
"loss": 1.3265,
"step": 1831
},
{
"epoch": 0.96,
"learning_rate": 4.6352480043568845e-07,
"loss": 1.3634,
"step": 1832
},
{
"epoch": 0.96,
"learning_rate": 4.5110049426653755e-07,
"loss": 1.4133,
"step": 1833
},
{
"epoch": 0.96,
"learning_rate": 4.3884421374661975e-07,
"loss": 1.249,
"step": 1834
},
{
"epoch": 0.96,
"learning_rate": 4.267560004382942e-07,
"loss": 1.2334,
"step": 1835
},
{
"epoch": 0.96,
"learning_rate": 4.1483589533399257e-07,
"loss": 1.0328,
"step": 1836
},
{
"epoch": 0.96,
"learning_rate": 4.030839388560803e-07,
"loss": 1.0827,
"step": 1837
},
{
"epoch": 0.96,
"learning_rate": 3.9150017085669565e-07,
"loss": 1.2826,
"step": 1838
},
{
"epoch": 0.96,
"learning_rate": 3.8008463061764977e-07,
"loss": 1.3065,
"step": 1839
},
{
"epoch": 0.97,
"learning_rate": 3.688373568502601e-07,
"loss": 1.2179,
"step": 1840
},
{
"epoch": 0.97,
"learning_rate": 3.5775838769525615e-07,
"loss": 0.9292,
"step": 1841
},
{
"epoch": 0.97,
"learning_rate": 3.4684776072260173e-07,
"loss": 1.4614,
"step": 1842
},
{
"epoch": 0.97,
"learning_rate": 3.361055129314117e-07,
"loss": 1.0518,
"step": 1843
},
{
"epoch": 0.97,
"learning_rate": 3.255316807498077e-07,
"loss": 1.1854,
"step": 1844
},
{
"epoch": 0.97,
"learning_rate": 3.151263000347793e-07,
"loss": 1.0778,
"step": 1845
},
{
"epoch": 0.97,
"learning_rate": 3.0488940607210637e-07,
"loss": 1.1983,
"step": 1846
},
{
"epoch": 0.97,
"learning_rate": 2.948210335761925e-07,
"loss": 1.0366,
"step": 1847
},
{
"epoch": 0.97,
"learning_rate": 2.8492121668997065e-07,
"loss": 1.1459,
"step": 1848
},
{
"epoch": 0.97,
"learning_rate": 2.751899889847864e-07,
"loss": 1.1982,
"step": 1849
},
{
"epoch": 0.97,
"learning_rate": 2.656273834602763e-07,
"loss": 0.9119,
"step": 1850
},
{
"epoch": 0.97,
"learning_rate": 2.562334325442728e-07,
"loss": 1.1973,
"step": 1851
},
{
"epoch": 0.97,
"learning_rate": 2.4700816809266616e-07,
"loss": 1.2599,
"step": 1852
},
{
"epoch": 0.97,
"learning_rate": 2.379516213893207e-07,
"loss": 1.3151,
"step": 1853
},
{
"epoch": 0.97,
"learning_rate": 2.290638231459641e-07,
"loss": 1.2084,
"step": 1854
},
{
"epoch": 0.97,
"learning_rate": 2.2034480350208164e-07,
"loss": 1.2637,
"step": 1855
},
{
"epoch": 0.97,
"learning_rate": 2.1179459202479435e-07,
"loss": 1.2562,
"step": 1856
},
{
"epoch": 0.97,
"learning_rate": 2.0341321770880327e-07,
"loss": 0.9374,
"step": 1857
},
{
"epoch": 0.97,
"learning_rate": 1.9520070897623978e-07,
"loss": 1.2063,
"step": 1858
},
{
"epoch": 0.98,
"learning_rate": 1.8715709367660982e-07,
"loss": 1.1011,
"step": 1859
},
{
"epoch": 0.98,
"learning_rate": 1.792823990866721e-07,
"loss": 1.3395,
"step": 1860
},
{
"epoch": 0.98,
"learning_rate": 1.715766519103712e-07,
"loss": 1.1728,
"step": 1861
},
{
"epoch": 0.98,
"learning_rate": 1.6403987827872669e-07,
"loss": 1.0144,
"step": 1862
},
{
"epoch": 0.98,
"learning_rate": 1.5667210374973874e-07,
"loss": 1.1882,
"step": 1863
},
{
"epoch": 0.98,
"learning_rate": 1.4947335330832702e-07,
"loss": 1.411,
"step": 1864
},
{
"epoch": 0.98,
"learning_rate": 1.4244365136623085e-07,
"loss": 1.2906,
"step": 1865
},
{
"epoch": 0.98,
"learning_rate": 1.3558302176192583e-07,
"loss": 1.1126,
"step": 1866
},
{
"epoch": 0.98,
"learning_rate": 1.2889148776054628e-07,
"loss": 1.4038,
"step": 1867
},
{
"epoch": 0.98,
"learning_rate": 1.2236907205379623e-07,
"loss": 1.2224,
"step": 1868
},
{
"epoch": 0.98,
"learning_rate": 1.160157967598996e-07,
"loss": 1.3104,
"step": 1869
},
{
"epoch": 0.98,
"learning_rate": 1.0983168342348915e-07,
"loss": 1.1886,
"step": 1870
},
{
"epoch": 0.98,
"learning_rate": 1.0381675301556759e-07,
"loss": 1.0505,
"step": 1871
},
{
"epoch": 0.98,
"learning_rate": 9.797102593339658e-08,
"loss": 1.0326,
"step": 1872
},
{
"epoch": 0.98,
"learning_rate": 9.229452200048005e-08,
"loss": 1.2758,
"step": 1873
},
{
"epoch": 0.98,
"learning_rate": 8.678726046644214e-08,
"loss": 1.1204,
"step": 1874
},
{
"epoch": 0.98,
"learning_rate": 8.144926000701048e-08,
"loss": 1.0465,
"step": 1875
},
{
"epoch": 0.98,
"learning_rate": 7.628053872390517e-08,
"loss": 1.0711,
"step": 1876
},
{
"epoch": 0.98,
"learning_rate": 7.128111414482775e-08,
"loss": 1.2398,
"step": 1877
},
{
"epoch": 0.99,
"learning_rate": 6.645100322336117e-08,
"loss": 1.2506,
"step": 1878
},
{
"epoch": 0.99,
"learning_rate": 6.179022233893106e-08,
"loss": 1.4724,
"step": 1879
},
{
"epoch": 0.99,
"learning_rate": 5.729878729675009e-08,
"loss": 1.0328,
"step": 1880
},
{
"epoch": 0.99,
"learning_rate": 5.297671332775145e-08,
"loss": 1.1325,
"step": 1881
},
{
"epoch": 0.99,
"learning_rate": 4.88240150885555e-08,
"loss": 1.1838,
"step": 1882
},
{
"epoch": 0.99,
"learning_rate": 4.484070666140872e-08,
"loss": 1.1584,
"step": 1883
},
{
"epoch": 0.99,
"learning_rate": 4.102680155413929e-08,
"loss": 1.4427,
"step": 1884
},
{
"epoch": 0.99,
"learning_rate": 3.738231270010717e-08,
"loss": 1.1909,
"step": 1885
},
{
"epoch": 0.99,
"learning_rate": 3.3907252458176276e-08,
"loss": 1.2926,
"step": 1886
},
{
"epoch": 0.99,
"learning_rate": 3.060163261263682e-08,
"loss": 1.1723,
"step": 1887
},
{
"epoch": 0.99,
"learning_rate": 2.7465464373205298e-08,
"loss": 1.066,
"step": 1888
},
{
"epoch": 0.99,
"learning_rate": 2.4498758374968954e-08,
"loss": 1.0458,
"step": 1889
},
{
"epoch": 0.99,
"learning_rate": 2.1701524678346963e-08,
"loss": 1.1118,
"step": 1890
},
{
"epoch": 0.99,
"learning_rate": 1.9073772769051533e-08,
"loss": 1.2084,
"step": 1891
},
{
"epoch": 0.99,
"learning_rate": 1.6615511558082385e-08,
"loss": 1.2864,
"step": 1892
},
{
"epoch": 0.99,
"learning_rate": 1.4326749381665672e-08,
"loss": 1.0176,
"step": 1893
},
{
"epoch": 0.99,
"learning_rate": 1.220749400123733e-08,
"loss": 1.3828,
"step": 1894
},
{
"epoch": 0.99,
"learning_rate": 1.0257752603420879e-08,
"loss": 1.1612,
"step": 1895
},
{
"epoch": 0.99,
"learning_rate": 8.47753179999966e-09,
"loss": 1.3129,
"step": 1896
},
{
"epoch": 1.0,
"learning_rate": 6.866837627889089e-09,
"loss": 1.3022,
"step": 1897
},
{
"epoch": 1.0,
"learning_rate": 5.425675549136644e-09,
"loss": 1.3343,
"step": 1898
},
{
"epoch": 1.0,
"learning_rate": 4.154050450871916e-09,
"loss": 1.0691,
"step": 1899
},
{
"epoch": 1.0,
"learning_rate": 3.0519666453121544e-09,
"loss": 1.0664,
"step": 1900
},
{
"epoch": 1.0,
"learning_rate": 2.119427869745616e-09,
"loss": 1.355,
"step": 1901
},
{
"epoch": 1.0,
"learning_rate": 1.356437286503809e-09,
"loss": 1.0196,
"step": 1902
},
{
"epoch": 1.0,
"learning_rate": 7.62997482978145e-10,
"loss": 1.1987,
"step": 1903
},
{
"epoch": 1.0,
"learning_rate": 3.3911047158663447e-10,
"loss": 1.0693,
"step": 1904
},
{
"epoch": 1.0,
"learning_rate": 8.477768976833389e-11,
"loss": 1.343,
"step": 1905
},
{
"epoch": 1.0,
"learning_rate": 0.0,
"loss": 1.166,
"step": 1906
},
{
"epoch": 1.0,
"step": 1906,
"total_flos": 1.288320957371174e+19,
"train_loss": 1.2139620957319535,
"train_runtime": 124170.7649,
"train_samples_per_second": 0.061,
"train_steps_per_second": 0.015
}
],
"logging_steps": 1.0,
"max_steps": 1906,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 100,
"total_flos": 1.288320957371174e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}