wav2vec2-2-gpt2-grid-search / trainer_state.json
sanchit-gandhi's picture
End of training
768a552
raw
history blame
66.9 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9987389659520807,
"global_step": 594,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0,
"loss": 4.798,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 2e-06,
"loss": 4.9659,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 4e-06,
"loss": 4.8548,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 6e-06,
"loss": 4.7832,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 8e-06,
"loss": 4.7029,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 1e-05,
"loss": 4.6549,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 1.2e-05,
"loss": 4.6679,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 1.4e-05,
"loss": 4.5376,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 1.6e-05,
"loss": 4.6115,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 1.8e-05,
"loss": 4.4613,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 2e-05,
"loss": 4.4478,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 2.2e-05,
"loss": 4.4566,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 2.4e-05,
"loss": 4.3608,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 2.6e-05,
"loss": 4.3267,
"step": 14
},
{
"epoch": 0.03,
"learning_rate": 2.8e-05,
"loss": 4.237,
"step": 15
},
{
"epoch": 0.03,
"learning_rate": 3e-05,
"loss": 4.3687,
"step": 16
},
{
"epoch": 0.03,
"learning_rate": 3.2e-05,
"loss": 4.3606,
"step": 17
},
{
"epoch": 0.03,
"learning_rate": 3.4000000000000007e-05,
"loss": 4.4764,
"step": 18
},
{
"epoch": 0.03,
"learning_rate": 3.6e-05,
"loss": 4.2192,
"step": 19
},
{
"epoch": 0.03,
"learning_rate": 3.8e-05,
"loss": 4.4582,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 4e-05,
"loss": 4.3744,
"step": 21
},
{
"epoch": 0.04,
"learning_rate": 4.2000000000000004e-05,
"loss": 4.331,
"step": 22
},
{
"epoch": 0.04,
"learning_rate": 4.4e-05,
"loss": 4.3407,
"step": 23
},
{
"epoch": 0.04,
"learning_rate": 4.6e-05,
"loss": 4.3821,
"step": 24
},
{
"epoch": 0.04,
"learning_rate": 4.8e-05,
"loss": 4.1777,
"step": 25
},
{
"epoch": 0.04,
"learning_rate": 5e-05,
"loss": 4.5667,
"step": 26
},
{
"epoch": 0.05,
"learning_rate": 5.2e-05,
"loss": 4.2537,
"step": 27
},
{
"epoch": 0.05,
"learning_rate": 5.4e-05,
"loss": 4.1534,
"step": 28
},
{
"epoch": 0.05,
"learning_rate": 5.6e-05,
"loss": 4.1515,
"step": 29
},
{
"epoch": 0.05,
"learning_rate": 5.800000000000001e-05,
"loss": 4.3429,
"step": 30
},
{
"epoch": 0.05,
"learning_rate": 6e-05,
"loss": 4.348,
"step": 31
},
{
"epoch": 0.05,
"learning_rate": 6.2e-05,
"loss": 4.2301,
"step": 32
},
{
"epoch": 0.06,
"learning_rate": 6.4e-05,
"loss": 4.2124,
"step": 33
},
{
"epoch": 0.06,
"learning_rate": 6.6e-05,
"loss": 4.1963,
"step": 34
},
{
"epoch": 0.06,
"learning_rate": 6.800000000000001e-05,
"loss": 4.2277,
"step": 35
},
{
"epoch": 0.06,
"learning_rate": 7.000000000000001e-05,
"loss": 4.4154,
"step": 36
},
{
"epoch": 0.06,
"learning_rate": 7.2e-05,
"loss": 4.2038,
"step": 37
},
{
"epoch": 0.06,
"learning_rate": 7.4e-05,
"loss": 4.3656,
"step": 38
},
{
"epoch": 0.07,
"learning_rate": 7.6e-05,
"loss": 4.5172,
"step": 39
},
{
"epoch": 0.07,
"learning_rate": 7.8e-05,
"loss": 4.2148,
"step": 40
},
{
"epoch": 0.07,
"learning_rate": 8e-05,
"loss": 4.196,
"step": 41
},
{
"epoch": 0.07,
"learning_rate": 8.2e-05,
"loss": 4.4284,
"step": 42
},
{
"epoch": 0.07,
"learning_rate": 8.400000000000001e-05,
"loss": 4.1641,
"step": 43
},
{
"epoch": 0.07,
"learning_rate": 8.599999999999999e-05,
"loss": 4.3293,
"step": 44
},
{
"epoch": 0.08,
"learning_rate": 8.8e-05,
"loss": 4.4,
"step": 45
},
{
"epoch": 0.08,
"learning_rate": 8.999999999999999e-05,
"loss": 4.4597,
"step": 46
},
{
"epoch": 0.08,
"learning_rate": 9.2e-05,
"loss": 4.374,
"step": 47
},
{
"epoch": 0.08,
"learning_rate": 9.400000000000001e-05,
"loss": 4.7429,
"step": 48
},
{
"epoch": 0.08,
"learning_rate": 9.6e-05,
"loss": 4.6918,
"step": 49
},
{
"epoch": 0.08,
"learning_rate": 9.6e-05,
"loss": 4.4926,
"step": 50
},
{
"epoch": 0.09,
"learning_rate": 9.800000000000001e-05,
"loss": 4.2253,
"step": 51
},
{
"epoch": 0.09,
"learning_rate": 0.0001,
"loss": 4.2335,
"step": 52
},
{
"epoch": 0.09,
"learning_rate": 0.000102,
"loss": 4.2367,
"step": 53
},
{
"epoch": 0.09,
"learning_rate": 0.000104,
"loss": 4.3182,
"step": 54
},
{
"epoch": 0.09,
"learning_rate": 0.000106,
"loss": 4.1924,
"step": 55
},
{
"epoch": 0.09,
"learning_rate": 0.000108,
"loss": 4.3919,
"step": 56
},
{
"epoch": 0.1,
"learning_rate": 0.00011,
"loss": 4.1947,
"step": 57
},
{
"epoch": 0.1,
"learning_rate": 0.000112,
"loss": 4.5164,
"step": 58
},
{
"epoch": 0.1,
"learning_rate": 0.000114,
"loss": 4.2716,
"step": 59
},
{
"epoch": 0.1,
"learning_rate": 0.00011600000000000001,
"loss": 4.0629,
"step": 60
},
{
"epoch": 0.1,
"learning_rate": 0.000118,
"loss": 4.328,
"step": 61
},
{
"epoch": 0.1,
"learning_rate": 0.00012,
"loss": 4.3771,
"step": 62
},
{
"epoch": 0.11,
"learning_rate": 0.000122,
"loss": 4.2684,
"step": 63
},
{
"epoch": 0.11,
"learning_rate": 0.000124,
"loss": 4.2398,
"step": 64
},
{
"epoch": 0.11,
"learning_rate": 0.000126,
"loss": 4.2612,
"step": 65
},
{
"epoch": 0.11,
"learning_rate": 0.000128,
"loss": 4.1913,
"step": 66
},
{
"epoch": 0.11,
"learning_rate": 0.00013000000000000002,
"loss": 4.1965,
"step": 67
},
{
"epoch": 0.11,
"learning_rate": 0.000132,
"loss": 4.16,
"step": 68
},
{
"epoch": 0.12,
"learning_rate": 0.000134,
"loss": 4.2527,
"step": 69
},
{
"epoch": 0.12,
"learning_rate": 0.00013600000000000003,
"loss": 4.2567,
"step": 70
},
{
"epoch": 0.12,
"learning_rate": 0.00013800000000000002,
"loss": 4.3733,
"step": 71
},
{
"epoch": 0.12,
"learning_rate": 0.00014000000000000001,
"loss": 4.3124,
"step": 72
},
{
"epoch": 0.12,
"learning_rate": 0.00014199999999999998,
"loss": 4.1534,
"step": 73
},
{
"epoch": 0.12,
"learning_rate": 0.000144,
"loss": 4.3542,
"step": 74
},
{
"epoch": 0.13,
"learning_rate": 0.000146,
"loss": 4.3096,
"step": 75
},
{
"epoch": 0.13,
"learning_rate": 0.000148,
"loss": 4.3124,
"step": 76
},
{
"epoch": 0.13,
"learning_rate": 0.00015,
"loss": 4.2301,
"step": 77
},
{
"epoch": 0.13,
"learning_rate": 0.000152,
"loss": 4.274,
"step": 78
},
{
"epoch": 0.13,
"learning_rate": 0.000154,
"loss": 4.2065,
"step": 79
},
{
"epoch": 0.13,
"learning_rate": 0.000156,
"loss": 4.4052,
"step": 80
},
{
"epoch": 0.14,
"learning_rate": 0.000158,
"loss": 4.354,
"step": 81
},
{
"epoch": 0.14,
"learning_rate": 0.00016,
"loss": 4.3246,
"step": 82
},
{
"epoch": 0.14,
"learning_rate": 0.000162,
"loss": 4.4008,
"step": 83
},
{
"epoch": 0.14,
"learning_rate": 0.000164,
"loss": 4.3554,
"step": 84
},
{
"epoch": 0.14,
"learning_rate": 0.00016600000000000002,
"loss": 4.2769,
"step": 85
},
{
"epoch": 0.14,
"learning_rate": 0.00016800000000000002,
"loss": 4.2777,
"step": 86
},
{
"epoch": 0.15,
"learning_rate": 0.00017,
"loss": 4.5118,
"step": 87
},
{
"epoch": 0.15,
"learning_rate": 0.00017199999999999998,
"loss": 4.3368,
"step": 88
},
{
"epoch": 0.15,
"learning_rate": 0.000174,
"loss": 4.4394,
"step": 89
},
{
"epoch": 0.15,
"learning_rate": 0.000176,
"loss": 4.3865,
"step": 90
},
{
"epoch": 0.15,
"learning_rate": 0.000178,
"loss": 4.3442,
"step": 91
},
{
"epoch": 0.15,
"learning_rate": 0.00017999999999999998,
"loss": 4.4925,
"step": 92
},
{
"epoch": 0.16,
"learning_rate": 0.000182,
"loss": 4.3855,
"step": 93
},
{
"epoch": 0.16,
"learning_rate": 0.000184,
"loss": 4.5602,
"step": 94
},
{
"epoch": 0.16,
"learning_rate": 0.000186,
"loss": 4.4853,
"step": 95
},
{
"epoch": 0.16,
"learning_rate": 0.00018800000000000002,
"loss": 4.6151,
"step": 96
},
{
"epoch": 0.16,
"learning_rate": 0.00019,
"loss": 4.5962,
"step": 97
},
{
"epoch": 0.16,
"learning_rate": 0.000192,
"loss": 4.4133,
"step": 98
},
{
"epoch": 0.17,
"learning_rate": 0.000194,
"loss": 4.792,
"step": 99
},
{
"epoch": 0.17,
"learning_rate": 0.00019600000000000002,
"loss": 4.4569,
"step": 100
},
{
"epoch": 0.17,
"learning_rate": 0.00019800000000000002,
"loss": 4.5401,
"step": 101
},
{
"epoch": 0.17,
"learning_rate": 0.0002,
"loss": 4.3572,
"step": 102
},
{
"epoch": 0.17,
"learning_rate": 0.000202,
"loss": 4.4242,
"step": 103
},
{
"epoch": 0.17,
"learning_rate": 0.000204,
"loss": 4.3279,
"step": 104
},
{
"epoch": 0.18,
"learning_rate": 0.000206,
"loss": 4.3101,
"step": 105
},
{
"epoch": 0.18,
"learning_rate": 0.000208,
"loss": 4.2788,
"step": 106
},
{
"epoch": 0.18,
"learning_rate": 0.00021,
"loss": 4.4495,
"step": 107
},
{
"epoch": 0.18,
"learning_rate": 0.000212,
"loss": 4.4467,
"step": 108
},
{
"epoch": 0.18,
"learning_rate": 0.000214,
"loss": 4.5925,
"step": 109
},
{
"epoch": 0.18,
"learning_rate": 0.000216,
"loss": 4.4049,
"step": 110
},
{
"epoch": 0.19,
"learning_rate": 0.000218,
"loss": 4.3936,
"step": 111
},
{
"epoch": 0.19,
"learning_rate": 0.00022,
"loss": 4.4172,
"step": 112
},
{
"epoch": 0.19,
"learning_rate": 0.000222,
"loss": 4.3436,
"step": 113
},
{
"epoch": 0.19,
"learning_rate": 0.000224,
"loss": 4.4727,
"step": 114
},
{
"epoch": 0.19,
"learning_rate": 0.00022600000000000002,
"loss": 4.389,
"step": 115
},
{
"epoch": 0.2,
"learning_rate": 0.000228,
"loss": 4.4001,
"step": 116
},
{
"epoch": 0.2,
"learning_rate": 0.00023,
"loss": 4.5036,
"step": 117
},
{
"epoch": 0.2,
"learning_rate": 0.00023200000000000003,
"loss": 4.2843,
"step": 118
},
{
"epoch": 0.2,
"learning_rate": 0.00023400000000000002,
"loss": 4.3065,
"step": 119
},
{
"epoch": 0.2,
"learning_rate": 0.000236,
"loss": 4.5466,
"step": 120
},
{
"epoch": 0.2,
"learning_rate": 0.00023799999999999998,
"loss": 4.4443,
"step": 121
},
{
"epoch": 0.21,
"learning_rate": 0.00024,
"loss": 4.6387,
"step": 122
},
{
"epoch": 0.21,
"learning_rate": 0.000242,
"loss": 4.3381,
"step": 123
},
{
"epoch": 0.21,
"learning_rate": 0.000244,
"loss": 4.4811,
"step": 124
},
{
"epoch": 0.21,
"learning_rate": 0.000246,
"loss": 4.3945,
"step": 125
},
{
"epoch": 0.21,
"learning_rate": 0.000248,
"loss": 4.3425,
"step": 126
},
{
"epoch": 0.21,
"learning_rate": 0.00025,
"loss": 4.3311,
"step": 127
},
{
"epoch": 0.22,
"learning_rate": 0.000252,
"loss": 4.3136,
"step": 128
},
{
"epoch": 0.22,
"learning_rate": 0.000254,
"loss": 4.3739,
"step": 129
},
{
"epoch": 0.22,
"learning_rate": 0.000256,
"loss": 4.463,
"step": 130
},
{
"epoch": 0.22,
"learning_rate": 0.00025800000000000004,
"loss": 4.4122,
"step": 131
},
{
"epoch": 0.22,
"learning_rate": 0.00026000000000000003,
"loss": 4.4737,
"step": 132
},
{
"epoch": 0.22,
"learning_rate": 0.000262,
"loss": 4.3602,
"step": 133
},
{
"epoch": 0.23,
"learning_rate": 0.000264,
"loss": 4.7136,
"step": 134
},
{
"epoch": 0.23,
"learning_rate": 0.000266,
"loss": 4.4939,
"step": 135
},
{
"epoch": 0.23,
"learning_rate": 0.000268,
"loss": 4.383,
"step": 136
},
{
"epoch": 0.23,
"learning_rate": 0.00027,
"loss": 4.3695,
"step": 137
},
{
"epoch": 0.23,
"learning_rate": 0.00027200000000000005,
"loss": 4.3884,
"step": 138
},
{
"epoch": 0.23,
"learning_rate": 0.00027400000000000005,
"loss": 4.3642,
"step": 139
},
{
"epoch": 0.24,
"learning_rate": 0.00027600000000000004,
"loss": 4.4841,
"step": 140
},
{
"epoch": 0.24,
"learning_rate": 0.00027800000000000004,
"loss": 4.3954,
"step": 141
},
{
"epoch": 0.24,
"learning_rate": 0.00028000000000000003,
"loss": 4.62,
"step": 142
},
{
"epoch": 0.24,
"learning_rate": 0.00028199999999999997,
"loss": 4.9846,
"step": 143
},
{
"epoch": 0.24,
"learning_rate": 0.00028399999999999996,
"loss": 5.0245,
"step": 144
},
{
"epoch": 0.24,
"learning_rate": 0.00028599999999999996,
"loss": 4.5489,
"step": 145
},
{
"epoch": 0.25,
"learning_rate": 0.000288,
"loss": 5.0615,
"step": 146
},
{
"epoch": 0.25,
"learning_rate": 0.00029,
"loss": 4.8247,
"step": 147
},
{
"epoch": 0.25,
"learning_rate": 0.000292,
"loss": 5.7443,
"step": 148
},
{
"epoch": 0.25,
"learning_rate": 0.000294,
"loss": 4.9307,
"step": 149
},
{
"epoch": 0.25,
"learning_rate": 0.000296,
"loss": 4.8052,
"step": 150
},
{
"epoch": 0.25,
"learning_rate": 0.000298,
"loss": 4.8397,
"step": 151
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 4.5232,
"step": 152
},
{
"epoch": 0.26,
"learning_rate": 0.000302,
"loss": 4.7358,
"step": 153
},
{
"epoch": 0.26,
"learning_rate": 0.000304,
"loss": 4.4171,
"step": 154
},
{
"epoch": 0.26,
"learning_rate": 0.000306,
"loss": 4.4927,
"step": 155
},
{
"epoch": 0.26,
"learning_rate": 0.000308,
"loss": 4.5971,
"step": 156
},
{
"epoch": 0.26,
"learning_rate": 0.00031,
"loss": 4.5412,
"step": 157
},
{
"epoch": 0.27,
"learning_rate": 0.000312,
"loss": 4.3854,
"step": 158
},
{
"epoch": 0.27,
"learning_rate": 0.000314,
"loss": 4.3552,
"step": 159
},
{
"epoch": 0.27,
"learning_rate": 0.000316,
"loss": 4.466,
"step": 160
},
{
"epoch": 0.27,
"learning_rate": 0.00031800000000000003,
"loss": 4.4675,
"step": 161
},
{
"epoch": 0.27,
"learning_rate": 0.00032,
"loss": 4.3639,
"step": 162
},
{
"epoch": 0.27,
"learning_rate": 0.000322,
"loss": 4.4132,
"step": 163
},
{
"epoch": 0.28,
"learning_rate": 0.000324,
"loss": 4.411,
"step": 164
},
{
"epoch": 0.28,
"learning_rate": 0.000326,
"loss": 4.6485,
"step": 165
},
{
"epoch": 0.28,
"learning_rate": 0.000328,
"loss": 4.5554,
"step": 166
},
{
"epoch": 0.28,
"learning_rate": 0.00033,
"loss": 4.395,
"step": 167
},
{
"epoch": 0.28,
"learning_rate": 0.00033200000000000005,
"loss": 4.607,
"step": 168
},
{
"epoch": 0.28,
"learning_rate": 0.00033400000000000004,
"loss": 4.4171,
"step": 169
},
{
"epoch": 0.29,
"learning_rate": 0.00033600000000000004,
"loss": 4.4899,
"step": 170
},
{
"epoch": 0.29,
"learning_rate": 0.00033800000000000003,
"loss": 4.5043,
"step": 171
},
{
"epoch": 0.29,
"learning_rate": 0.00034,
"loss": 4.39,
"step": 172
},
{
"epoch": 0.29,
"learning_rate": 0.000342,
"loss": 4.4518,
"step": 173
},
{
"epoch": 0.29,
"learning_rate": 0.00034399999999999996,
"loss": 4.4439,
"step": 174
},
{
"epoch": 0.29,
"learning_rate": 0.000346,
"loss": 4.675,
"step": 175
},
{
"epoch": 0.3,
"learning_rate": 0.000348,
"loss": 4.6505,
"step": 176
},
{
"epoch": 0.3,
"learning_rate": 0.00035,
"loss": 4.5945,
"step": 177
},
{
"epoch": 0.3,
"learning_rate": 0.000352,
"loss": 4.395,
"step": 178
},
{
"epoch": 0.3,
"learning_rate": 0.000354,
"loss": 4.5278,
"step": 179
},
{
"epoch": 0.3,
"learning_rate": 0.000356,
"loss": 4.424,
"step": 180
},
{
"epoch": 0.3,
"learning_rate": 0.000358,
"loss": 4.8036,
"step": 181
},
{
"epoch": 0.31,
"learning_rate": 0.00035999999999999997,
"loss": 4.5129,
"step": 182
},
{
"epoch": 0.31,
"learning_rate": 0.000362,
"loss": 4.559,
"step": 183
},
{
"epoch": 0.31,
"learning_rate": 0.000364,
"loss": 4.3398,
"step": 184
},
{
"epoch": 0.31,
"learning_rate": 0.000366,
"loss": 4.9099,
"step": 185
},
{
"epoch": 0.31,
"learning_rate": 0.000368,
"loss": 4.5334,
"step": 186
},
{
"epoch": 0.31,
"learning_rate": 0.00037,
"loss": 4.6366,
"step": 187
},
{
"epoch": 0.32,
"learning_rate": 0.000372,
"loss": 10.5141,
"step": 188
},
{
"epoch": 0.32,
"learning_rate": 0.000374,
"loss": 5.2225,
"step": 189
},
{
"epoch": 0.32,
"learning_rate": 0.00037600000000000003,
"loss": 4.7898,
"step": 190
},
{
"epoch": 0.32,
"learning_rate": 0.000378,
"loss": 4.9854,
"step": 191
},
{
"epoch": 0.32,
"learning_rate": 0.00038,
"loss": 4.7617,
"step": 192
},
{
"epoch": 0.32,
"learning_rate": 0.000382,
"loss": 5.625,
"step": 193
},
{
"epoch": 0.33,
"learning_rate": 0.000384,
"loss": 4.8983,
"step": 194
},
{
"epoch": 0.33,
"learning_rate": 0.000386,
"loss": 4.7163,
"step": 195
},
{
"epoch": 0.33,
"learning_rate": 0.000388,
"loss": 4.709,
"step": 196
},
{
"epoch": 0.33,
"learning_rate": 0.00039000000000000005,
"loss": 5.4669,
"step": 197
},
{
"epoch": 0.33,
"learning_rate": 0.00039200000000000004,
"loss": 5.1185,
"step": 198
},
{
"epoch": 0.33,
"learning_rate": 0.00039400000000000004,
"loss": 5.4637,
"step": 199
},
{
"epoch": 0.34,
"learning_rate": 0.00039600000000000003,
"loss": 5.1612,
"step": 200
},
{
"epoch": 0.34,
"learning_rate": 0.000398,
"loss": 4.7685,
"step": 201
},
{
"epoch": 0.34,
"learning_rate": 0.0004,
"loss": 4.7321,
"step": 202
},
{
"epoch": 0.34,
"learning_rate": 0.000402,
"loss": 4.8251,
"step": 203
},
{
"epoch": 0.34,
"learning_rate": 0.000404,
"loss": 4.582,
"step": 204
},
{
"epoch": 0.34,
"learning_rate": 0.00040600000000000006,
"loss": 4.7087,
"step": 205
},
{
"epoch": 0.35,
"learning_rate": 0.000408,
"loss": 4.6998,
"step": 206
},
{
"epoch": 0.35,
"learning_rate": 0.00041,
"loss": 4.7384,
"step": 207
},
{
"epoch": 0.35,
"learning_rate": 0.000412,
"loss": 5.0725,
"step": 208
},
{
"epoch": 0.35,
"learning_rate": 0.000414,
"loss": 4.5905,
"step": 209
},
{
"epoch": 0.35,
"learning_rate": 0.000416,
"loss": 4.6788,
"step": 210
},
{
"epoch": 0.35,
"learning_rate": 0.00041799999999999997,
"loss": 4.7633,
"step": 211
},
{
"epoch": 0.36,
"learning_rate": 0.00042,
"loss": 4.5983,
"step": 212
},
{
"epoch": 0.36,
"learning_rate": 0.000422,
"loss": 4.7049,
"step": 213
},
{
"epoch": 0.36,
"learning_rate": 0.000424,
"loss": 4.7085,
"step": 214
},
{
"epoch": 0.36,
"learning_rate": 0.000426,
"loss": 4.7324,
"step": 215
},
{
"epoch": 0.36,
"learning_rate": 0.000428,
"loss": 4.7549,
"step": 216
},
{
"epoch": 0.36,
"learning_rate": 0.00043,
"loss": 4.5151,
"step": 217
},
{
"epoch": 0.37,
"learning_rate": 0.000432,
"loss": 4.737,
"step": 218
},
{
"epoch": 0.37,
"learning_rate": 0.00043400000000000003,
"loss": 5.079,
"step": 219
},
{
"epoch": 0.37,
"learning_rate": 0.000436,
"loss": 4.9301,
"step": 220
},
{
"epoch": 0.37,
"learning_rate": 0.000438,
"loss": 4.7236,
"step": 221
},
{
"epoch": 0.37,
"learning_rate": 0.00044,
"loss": 4.6851,
"step": 222
},
{
"epoch": 0.37,
"learning_rate": 0.000442,
"loss": 4.5696,
"step": 223
},
{
"epoch": 0.38,
"learning_rate": 0.000444,
"loss": 4.7287,
"step": 224
},
{
"epoch": 0.38,
"learning_rate": 0.000446,
"loss": 4.9131,
"step": 225
},
{
"epoch": 0.38,
"learning_rate": 0.000448,
"loss": 4.545,
"step": 226
},
{
"epoch": 0.38,
"learning_rate": 0.00045000000000000004,
"loss": 4.411,
"step": 227
},
{
"epoch": 0.38,
"learning_rate": 0.00045200000000000004,
"loss": 4.7007,
"step": 228
},
{
"epoch": 0.39,
"learning_rate": 0.00045400000000000003,
"loss": 4.8379,
"step": 229
},
{
"epoch": 0.39,
"learning_rate": 0.000456,
"loss": 4.6935,
"step": 230
},
{
"epoch": 0.39,
"learning_rate": 0.000458,
"loss": 4.6056,
"step": 231
},
{
"epoch": 0.39,
"learning_rate": 0.00046,
"loss": 4.695,
"step": 232
},
{
"epoch": 0.39,
"learning_rate": 0.000462,
"loss": 5.4116,
"step": 233
},
{
"epoch": 0.39,
"learning_rate": 0.00046400000000000006,
"loss": 4.7751,
"step": 234
},
{
"epoch": 0.4,
"learning_rate": 0.00046600000000000005,
"loss": 4.8383,
"step": 235
},
{
"epoch": 0.4,
"learning_rate": 0.00046800000000000005,
"loss": 4.5302,
"step": 236
},
{
"epoch": 0.4,
"learning_rate": 0.00047,
"loss": 4.4752,
"step": 237
},
{
"epoch": 0.4,
"learning_rate": 0.000472,
"loss": 4.4729,
"step": 238
},
{
"epoch": 0.4,
"learning_rate": 0.000474,
"loss": 4.6228,
"step": 239
},
{
"epoch": 0.4,
"learning_rate": 0.00047599999999999997,
"loss": 4.5783,
"step": 240
},
{
"epoch": 0.41,
"learning_rate": 0.00047799999999999996,
"loss": 4.9697,
"step": 241
},
{
"epoch": 0.41,
"learning_rate": 0.00048,
"loss": 4.8311,
"step": 242
},
{
"epoch": 0.41,
"learning_rate": 0.000482,
"loss": 4.7072,
"step": 243
},
{
"epoch": 0.41,
"learning_rate": 0.000484,
"loss": 4.7736,
"step": 244
},
{
"epoch": 0.41,
"learning_rate": 0.000486,
"loss": 5.3237,
"step": 245
},
{
"epoch": 0.41,
"learning_rate": 0.000488,
"loss": 4.9429,
"step": 246
},
{
"epoch": 0.42,
"learning_rate": 0.00049,
"loss": 5.2372,
"step": 247
},
{
"epoch": 0.42,
"learning_rate": 0.000492,
"loss": 5.3449,
"step": 248
},
{
"epoch": 0.42,
"learning_rate": 0.000494,
"loss": 5.7414,
"step": 249
},
{
"epoch": 0.42,
"learning_rate": 0.000496,
"loss": 5.3932,
"step": 250
},
{
"epoch": 0.42,
"learning_rate": 0.000498,
"loss": 5.1953,
"step": 251
},
{
"epoch": 0.42,
"learning_rate": 0.0005,
"loss": 4.9961,
"step": 252
},
{
"epoch": 0.43,
"learning_rate": 0.0005020000000000001,
"loss": 4.8454,
"step": 253
},
{
"epoch": 0.43,
"learning_rate": 0.000504,
"loss": 4.7123,
"step": 254
},
{
"epoch": 0.43,
"learning_rate": 0.000506,
"loss": 5.0182,
"step": 255
},
{
"epoch": 0.43,
"learning_rate": 0.000508,
"loss": 4.715,
"step": 256
},
{
"epoch": 0.43,
"learning_rate": 0.00051,
"loss": 4.7092,
"step": 257
},
{
"epoch": 0.43,
"learning_rate": 0.000512,
"loss": 4.6732,
"step": 258
},
{
"epoch": 0.44,
"learning_rate": 0.000514,
"loss": 4.7211,
"step": 259
},
{
"epoch": 0.44,
"learning_rate": 0.0005160000000000001,
"loss": 4.8059,
"step": 260
},
{
"epoch": 0.44,
"learning_rate": 0.000518,
"loss": 4.6999,
"step": 261
},
{
"epoch": 0.44,
"learning_rate": 0.0005200000000000001,
"loss": 4.7275,
"step": 262
},
{
"epoch": 0.44,
"learning_rate": 0.000522,
"loss": 5.2414,
"step": 263
},
{
"epoch": 0.44,
"learning_rate": 0.000524,
"loss": 4.4321,
"step": 264
},
{
"epoch": 0.45,
"learning_rate": 0.000526,
"loss": 4.6628,
"step": 265
},
{
"epoch": 0.45,
"learning_rate": 0.000528,
"loss": 4.6351,
"step": 266
},
{
"epoch": 0.45,
"learning_rate": 0.0005300000000000001,
"loss": 4.8597,
"step": 267
},
{
"epoch": 0.45,
"learning_rate": 0.000532,
"loss": 4.6425,
"step": 268
},
{
"epoch": 0.45,
"learning_rate": 0.0005340000000000001,
"loss": 4.7052,
"step": 269
},
{
"epoch": 0.45,
"learning_rate": 0.000536,
"loss": 4.7256,
"step": 270
},
{
"epoch": 0.46,
"learning_rate": 0.0005380000000000001,
"loss": 4.6104,
"step": 271
},
{
"epoch": 0.46,
"learning_rate": 0.00054,
"loss": 4.819,
"step": 272
},
{
"epoch": 0.46,
"learning_rate": 0.0005420000000000001,
"loss": 4.9087,
"step": 273
},
{
"epoch": 0.46,
"learning_rate": 0.0005440000000000001,
"loss": 4.7817,
"step": 274
},
{
"epoch": 0.46,
"learning_rate": 0.000546,
"loss": 4.7076,
"step": 275
},
{
"epoch": 0.46,
"learning_rate": 0.0005480000000000001,
"loss": 4.7856,
"step": 276
},
{
"epoch": 0.47,
"learning_rate": 0.00055,
"loss": 4.8639,
"step": 277
},
{
"epoch": 0.47,
"learning_rate": 0.0005520000000000001,
"loss": 4.9141,
"step": 278
},
{
"epoch": 0.47,
"learning_rate": 0.000554,
"loss": 4.7599,
"step": 279
},
{
"epoch": 0.47,
"learning_rate": 0.0005560000000000001,
"loss": 4.8849,
"step": 280
},
{
"epoch": 0.47,
"learning_rate": 0.000558,
"loss": 4.8114,
"step": 281
},
{
"epoch": 0.47,
"learning_rate": 0.0005600000000000001,
"loss": 4.8759,
"step": 282
},
{
"epoch": 0.48,
"learning_rate": 0.0005620000000000001,
"loss": 4.6076,
"step": 283
},
{
"epoch": 0.48,
"learning_rate": 0.0005639999999999999,
"loss": 4.6381,
"step": 284
},
{
"epoch": 0.48,
"learning_rate": 0.000566,
"loss": 4.8706,
"step": 285
},
{
"epoch": 0.48,
"learning_rate": 0.0005679999999999999,
"loss": 4.7356,
"step": 286
},
{
"epoch": 0.48,
"learning_rate": 0.00057,
"loss": 5.0577,
"step": 287
},
{
"epoch": 0.48,
"learning_rate": 0.0005719999999999999,
"loss": 4.5367,
"step": 288
},
{
"epoch": 0.49,
"learning_rate": 0.000574,
"loss": 4.7395,
"step": 289
},
{
"epoch": 0.49,
"learning_rate": 0.000576,
"loss": 4.7516,
"step": 290
},
{
"epoch": 0.49,
"learning_rate": 0.000578,
"loss": 4.8814,
"step": 291
},
{
"epoch": 0.49,
"learning_rate": 0.00058,
"loss": 4.7253,
"step": 292
},
{
"epoch": 0.49,
"learning_rate": 0.0005819999999999999,
"loss": 4.8064,
"step": 293
},
{
"epoch": 0.49,
"learning_rate": 0.000584,
"loss": 4.9757,
"step": 294
},
{
"epoch": 0.5,
"learning_rate": 0.0005859999999999999,
"loss": 4.8986,
"step": 295
},
{
"epoch": 0.5,
"learning_rate": 0.000588,
"loss": 4.7132,
"step": 296
},
{
"epoch": 0.5,
"learning_rate": 0.00059,
"loss": 5.6149,
"step": 297
},
{
"epoch": 0.5,
"learning_rate": 0.000592,
"loss": 6.4538,
"step": 298
},
{
"epoch": 0.5,
"learning_rate": 0.000594,
"loss": 5.2126,
"step": 299
},
{
"epoch": 0.5,
"learning_rate": 0.000596,
"loss": 5.7153,
"step": 300
},
{
"epoch": 0.51,
"learning_rate": 0.000598,
"loss": 5.235,
"step": 301
},
{
"epoch": 0.51,
"learning_rate": 0.0006,
"loss": 4.9152,
"step": 302
},
{
"epoch": 0.51,
"learning_rate": 0.000602,
"loss": 5.0532,
"step": 303
},
{
"epoch": 0.51,
"learning_rate": 0.000604,
"loss": 4.7904,
"step": 304
},
{
"epoch": 0.51,
"learning_rate": 0.000606,
"loss": 5.0049,
"step": 305
},
{
"epoch": 0.51,
"learning_rate": 0.000608,
"loss": 4.9579,
"step": 306
},
{
"epoch": 0.52,
"learning_rate": 0.00061,
"loss": 4.8652,
"step": 307
},
{
"epoch": 0.52,
"learning_rate": 0.000612,
"loss": 5.024,
"step": 308
},
{
"epoch": 0.52,
"learning_rate": 0.000614,
"loss": 4.9125,
"step": 309
},
{
"epoch": 0.52,
"learning_rate": 0.000616,
"loss": 4.8775,
"step": 310
},
{
"epoch": 0.52,
"learning_rate": 0.0006180000000000001,
"loss": 4.6219,
"step": 311
},
{
"epoch": 0.52,
"learning_rate": 0.00062,
"loss": 4.9048,
"step": 312
},
{
"epoch": 0.53,
"learning_rate": 0.000622,
"loss": 4.8739,
"step": 313
},
{
"epoch": 0.53,
"learning_rate": 0.000624,
"loss": 4.8017,
"step": 314
},
{
"epoch": 0.53,
"learning_rate": 0.000626,
"loss": 4.7513,
"step": 315
},
{
"epoch": 0.53,
"learning_rate": 0.000628,
"loss": 4.8819,
"step": 316
},
{
"epoch": 0.53,
"learning_rate": 0.00063,
"loss": 4.7052,
"step": 317
},
{
"epoch": 0.53,
"learning_rate": 0.000632,
"loss": 5.1057,
"step": 318
},
{
"epoch": 0.54,
"learning_rate": 0.000634,
"loss": 5.0369,
"step": 319
},
{
"epoch": 0.54,
"learning_rate": 0.0006360000000000001,
"loss": 4.8897,
"step": 320
},
{
"epoch": 0.54,
"learning_rate": 0.000638,
"loss": 4.6517,
"step": 321
},
{
"epoch": 0.54,
"learning_rate": 0.00064,
"loss": 4.662,
"step": 322
},
{
"epoch": 0.54,
"learning_rate": 0.000642,
"loss": 5.0655,
"step": 323
},
{
"epoch": 0.54,
"learning_rate": 0.000644,
"loss": 4.7497,
"step": 324
},
{
"epoch": 0.55,
"learning_rate": 0.000646,
"loss": 4.9575,
"step": 325
},
{
"epoch": 0.55,
"learning_rate": 0.000648,
"loss": 4.8104,
"step": 326
},
{
"epoch": 0.55,
"learning_rate": 0.0006500000000000001,
"loss": 5.0224,
"step": 327
},
{
"epoch": 0.55,
"learning_rate": 0.000652,
"loss": 4.7339,
"step": 328
},
{
"epoch": 0.55,
"learning_rate": 0.0006540000000000001,
"loss": 4.6435,
"step": 329
},
{
"epoch": 0.55,
"learning_rate": 0.000656,
"loss": 4.8785,
"step": 330
},
{
"epoch": 0.56,
"learning_rate": 0.0006580000000000001,
"loss": 4.8467,
"step": 331
},
{
"epoch": 0.56,
"learning_rate": 0.00066,
"loss": 4.6529,
"step": 332
},
{
"epoch": 0.56,
"learning_rate": 0.000662,
"loss": 5.1175,
"step": 333
},
{
"epoch": 0.56,
"learning_rate": 0.0006640000000000001,
"loss": 5.1239,
"step": 334
},
{
"epoch": 0.56,
"learning_rate": 0.000666,
"loss": 4.916,
"step": 335
},
{
"epoch": 0.56,
"learning_rate": 0.0006680000000000001,
"loss": 4.6657,
"step": 336
},
{
"epoch": 0.57,
"learning_rate": 0.00067,
"loss": 4.7292,
"step": 337
},
{
"epoch": 0.57,
"learning_rate": 0.0006720000000000001,
"loss": 4.6982,
"step": 338
},
{
"epoch": 0.57,
"learning_rate": 0.000674,
"loss": 4.689,
"step": 339
},
{
"epoch": 0.57,
"learning_rate": 0.0006760000000000001,
"loss": 5.0327,
"step": 340
},
{
"epoch": 0.57,
"learning_rate": 0.0006780000000000001,
"loss": 4.813,
"step": 341
},
{
"epoch": 0.58,
"learning_rate": 0.00068,
"loss": 4.8782,
"step": 342
},
{
"epoch": 0.58,
"learning_rate": 0.0006820000000000001,
"loss": 4.9557,
"step": 343
},
{
"epoch": 0.58,
"learning_rate": 0.000684,
"loss": 4.9666,
"step": 344
},
{
"epoch": 0.58,
"learning_rate": 0.0006860000000000001,
"loss": 5.353,
"step": 345
},
{
"epoch": 0.58,
"learning_rate": 0.0006879999999999999,
"loss": 4.8186,
"step": 346
},
{
"epoch": 0.58,
"learning_rate": 0.00069,
"loss": 4.7452,
"step": 347
},
{
"epoch": 0.59,
"learning_rate": 0.000692,
"loss": 5.1056,
"step": 348
},
{
"epoch": 0.59,
"learning_rate": 0.000694,
"loss": 4.8236,
"step": 349
},
{
"epoch": 0.59,
"learning_rate": 0.000696,
"loss": 4.9508,
"step": 350
},
{
"epoch": 0.59,
"learning_rate": 0.0006979999999999999,
"loss": 5.2547,
"step": 351
},
{
"epoch": 0.59,
"learning_rate": 0.0007,
"loss": 5.0417,
"step": 352
},
{
"epoch": 0.59,
"learning_rate": 0.0007019999999999999,
"loss": 4.9277,
"step": 353
},
{
"epoch": 0.6,
"learning_rate": 0.000704,
"loss": 4.7628,
"step": 354
},
{
"epoch": 0.6,
"learning_rate": 0.0007059999999999999,
"loss": 4.8104,
"step": 355
},
{
"epoch": 0.6,
"learning_rate": 0.000708,
"loss": 4.8422,
"step": 356
},
{
"epoch": 0.6,
"learning_rate": 0.00071,
"loss": 4.8045,
"step": 357
},
{
"epoch": 0.6,
"learning_rate": 0.000712,
"loss": 4.9178,
"step": 358
},
{
"epoch": 0.6,
"learning_rate": 0.000714,
"loss": 4.8115,
"step": 359
},
{
"epoch": 0.61,
"learning_rate": 0.000716,
"loss": 5.0046,
"step": 360
},
{
"epoch": 0.61,
"learning_rate": 0.000718,
"loss": 4.8284,
"step": 361
},
{
"epoch": 0.61,
"learning_rate": 0.0007199999999999999,
"loss": 4.746,
"step": 362
},
{
"epoch": 0.61,
"learning_rate": 0.000722,
"loss": 5.0836,
"step": 363
},
{
"epoch": 0.61,
"learning_rate": 0.000724,
"loss": 4.7086,
"step": 364
},
{
"epoch": 0.61,
"learning_rate": 0.000726,
"loss": 4.8806,
"step": 365
},
{
"epoch": 0.62,
"learning_rate": 0.000728,
"loss": 4.7059,
"step": 366
},
{
"epoch": 0.62,
"learning_rate": 0.00073,
"loss": 4.8378,
"step": 367
},
{
"epoch": 0.62,
"learning_rate": 0.000732,
"loss": 4.8017,
"step": 368
},
{
"epoch": 0.62,
"learning_rate": 0.000734,
"loss": 4.8343,
"step": 369
},
{
"epoch": 0.62,
"learning_rate": 0.000736,
"loss": 5.0083,
"step": 370
},
{
"epoch": 0.62,
"learning_rate": 0.000738,
"loss": 4.7563,
"step": 371
},
{
"epoch": 0.63,
"learning_rate": 0.00074,
"loss": 4.7571,
"step": 372
},
{
"epoch": 0.63,
"learning_rate": 0.000742,
"loss": 4.7098,
"step": 373
},
{
"epoch": 0.63,
"learning_rate": 0.000744,
"loss": 5.308,
"step": 374
},
{
"epoch": 0.63,
"learning_rate": 0.000746,
"loss": 5.0252,
"step": 375
},
{
"epoch": 0.63,
"learning_rate": 0.000748,
"loss": 5.1313,
"step": 376
},
{
"epoch": 0.63,
"learning_rate": 0.00075,
"loss": 4.8109,
"step": 377
},
{
"epoch": 0.64,
"learning_rate": 0.0007520000000000001,
"loss": 4.8508,
"step": 378
},
{
"epoch": 0.64,
"learning_rate": 0.000754,
"loss": 4.8471,
"step": 379
},
{
"epoch": 0.64,
"learning_rate": 0.000756,
"loss": 4.9023,
"step": 380
},
{
"epoch": 0.64,
"learning_rate": 0.000758,
"loss": 4.9553,
"step": 381
},
{
"epoch": 0.64,
"learning_rate": 0.00076,
"loss": 4.7834,
"step": 382
},
{
"epoch": 0.64,
"learning_rate": 0.000762,
"loss": 5.1141,
"step": 383
},
{
"epoch": 0.65,
"learning_rate": 0.000764,
"loss": 4.8394,
"step": 384
},
{
"epoch": 0.65,
"learning_rate": 0.0007660000000000001,
"loss": 4.8951,
"step": 385
},
{
"epoch": 0.65,
"learning_rate": 0.000768,
"loss": 4.9039,
"step": 386
},
{
"epoch": 0.65,
"learning_rate": 0.0007700000000000001,
"loss": 5.2676,
"step": 387
},
{
"epoch": 0.65,
"learning_rate": 0.000772,
"loss": 4.8199,
"step": 388
},
{
"epoch": 0.65,
"learning_rate": 0.0007740000000000001,
"loss": 4.7974,
"step": 389
},
{
"epoch": 0.66,
"learning_rate": 0.000776,
"loss": 4.8914,
"step": 390
},
{
"epoch": 0.66,
"learning_rate": 0.000778,
"loss": 4.965,
"step": 391
},
{
"epoch": 0.66,
"learning_rate": 0.0007800000000000001,
"loss": 5.3528,
"step": 392
},
{
"epoch": 0.66,
"learning_rate": 0.000782,
"loss": 5.4938,
"step": 393
},
{
"epoch": 0.66,
"learning_rate": 0.0007840000000000001,
"loss": 5.1061,
"step": 394
},
{
"epoch": 0.66,
"learning_rate": 0.000786,
"loss": 5.2562,
"step": 395
},
{
"epoch": 0.67,
"learning_rate": 0.0007880000000000001,
"loss": 5.2242,
"step": 396
},
{
"epoch": 0.67,
"learning_rate": 0.00079,
"loss": 5.0489,
"step": 397
},
{
"epoch": 0.67,
"learning_rate": 0.0007920000000000001,
"loss": 5.7935,
"step": 398
},
{
"epoch": 0.67,
"learning_rate": 0.0007940000000000001,
"loss": 5.1701,
"step": 399
},
{
"epoch": 0.67,
"learning_rate": 0.000796,
"loss": 4.8904,
"step": 400
},
{
"epoch": 0.67,
"learning_rate": 0.0007980000000000001,
"loss": 5.0654,
"step": 401
},
{
"epoch": 0.68,
"learning_rate": 0.0008,
"loss": 4.8698,
"step": 402
},
{
"epoch": 0.68,
"learning_rate": 0.0008020000000000001,
"loss": 4.9322,
"step": 403
},
{
"epoch": 0.68,
"learning_rate": 0.000804,
"loss": 4.8403,
"step": 404
},
{
"epoch": 0.68,
"learning_rate": 0.0008060000000000001,
"loss": 4.8574,
"step": 405
},
{
"epoch": 0.68,
"learning_rate": 0.000808,
"loss": 4.742,
"step": 406
},
{
"epoch": 0.68,
"learning_rate": 0.0008100000000000001,
"loss": 5.2273,
"step": 407
},
{
"epoch": 0.69,
"learning_rate": 0.0008120000000000001,
"loss": 4.7645,
"step": 408
},
{
"epoch": 0.69,
"learning_rate": 0.0008139999999999999,
"loss": 4.752,
"step": 409
},
{
"epoch": 0.69,
"learning_rate": 0.000816,
"loss": 4.7622,
"step": 410
},
{
"epoch": 0.69,
"learning_rate": 0.0008179999999999999,
"loss": 4.688,
"step": 411
},
{
"epoch": 0.69,
"learning_rate": 0.00082,
"loss": 4.929,
"step": 412
},
{
"epoch": 0.69,
"learning_rate": 0.0008219999999999999,
"loss": 4.886,
"step": 413
},
{
"epoch": 0.7,
"learning_rate": 0.000824,
"loss": 4.9073,
"step": 414
},
{
"epoch": 0.7,
"learning_rate": 0.000826,
"loss": 4.8768,
"step": 415
},
{
"epoch": 0.7,
"learning_rate": 0.000828,
"loss": 4.7801,
"step": 416
},
{
"epoch": 0.7,
"learning_rate": 0.00083,
"loss": 4.734,
"step": 417
},
{
"epoch": 0.7,
"learning_rate": 0.000832,
"loss": 4.4348,
"step": 418
},
{
"epoch": 0.7,
"learning_rate": 0.000834,
"loss": 4.8986,
"step": 419
},
{
"epoch": 0.71,
"learning_rate": 0.0008359999999999999,
"loss": 4.8039,
"step": 420
},
{
"epoch": 0.71,
"learning_rate": 0.000838,
"loss": 4.4695,
"step": 421
},
{
"epoch": 0.71,
"learning_rate": 0.00084,
"loss": 4.6531,
"step": 422
},
{
"epoch": 0.71,
"learning_rate": 0.000842,
"loss": 4.8529,
"step": 423
},
{
"epoch": 0.71,
"learning_rate": 0.000844,
"loss": 4.7331,
"step": 424
},
{
"epoch": 0.71,
"learning_rate": 0.000846,
"loss": 4.8075,
"step": 425
},
{
"epoch": 0.72,
"learning_rate": 0.000848,
"loss": 4.8201,
"step": 426
},
{
"epoch": 0.72,
"learning_rate": 0.00085,
"loss": 4.5947,
"step": 427
},
{
"epoch": 0.72,
"learning_rate": 0.000852,
"loss": 4.5512,
"step": 428
},
{
"epoch": 0.72,
"learning_rate": 0.000854,
"loss": 4.9711,
"step": 429
},
{
"epoch": 0.72,
"learning_rate": 0.000856,
"loss": 4.742,
"step": 430
},
{
"epoch": 0.72,
"learning_rate": 0.000858,
"loss": 5.1297,
"step": 431
},
{
"epoch": 0.73,
"learning_rate": 0.00086,
"loss": 4.6386,
"step": 432
},
{
"epoch": 0.73,
"learning_rate": 0.000862,
"loss": 4.9415,
"step": 433
},
{
"epoch": 0.73,
"learning_rate": 0.000864,
"loss": 4.808,
"step": 434
},
{
"epoch": 0.73,
"learning_rate": 0.000866,
"loss": 4.9157,
"step": 435
},
{
"epoch": 0.73,
"learning_rate": 0.0008680000000000001,
"loss": 4.7158,
"step": 436
},
{
"epoch": 0.73,
"learning_rate": 0.00087,
"loss": 4.8154,
"step": 437
},
{
"epoch": 0.74,
"learning_rate": 0.000872,
"loss": 4.7926,
"step": 438
},
{
"epoch": 0.74,
"learning_rate": 0.000874,
"loss": 4.936,
"step": 439
},
{
"epoch": 0.74,
"learning_rate": 0.000876,
"loss": 5.1139,
"step": 440
},
{
"epoch": 0.74,
"learning_rate": 0.000878,
"loss": 5.2978,
"step": 441
},
{
"epoch": 0.74,
"learning_rate": 0.00088,
"loss": 6.1523,
"step": 442
},
{
"epoch": 0.74,
"learning_rate": 0.000882,
"loss": 5.2146,
"step": 443
},
{
"epoch": 0.75,
"learning_rate": 0.000884,
"loss": 5.0577,
"step": 444
},
{
"epoch": 0.75,
"learning_rate": 0.0008860000000000001,
"loss": 4.7544,
"step": 445
},
{
"epoch": 0.75,
"learning_rate": 0.000888,
"loss": 4.9598,
"step": 446
},
{
"epoch": 0.75,
"learning_rate": 0.0008900000000000001,
"loss": 4.9329,
"step": 447
},
{
"epoch": 0.75,
"learning_rate": 0.000892,
"loss": 4.969,
"step": 448
},
{
"epoch": 0.75,
"learning_rate": 0.000894,
"loss": 5.5613,
"step": 449
},
{
"epoch": 0.76,
"learning_rate": 0.000896,
"loss": 5.0466,
"step": 450
},
{
"epoch": 0.76,
"learning_rate": 0.000898,
"loss": 5.0624,
"step": 451
},
{
"epoch": 0.76,
"learning_rate": 0.0009000000000000001,
"loss": 5.1022,
"step": 452
},
{
"epoch": 0.76,
"learning_rate": 0.000902,
"loss": 4.892,
"step": 453
},
{
"epoch": 0.76,
"learning_rate": 0.0009040000000000001,
"loss": 4.9988,
"step": 454
},
{
"epoch": 0.77,
"learning_rate": 0.000906,
"loss": 5.0485,
"step": 455
},
{
"epoch": 0.77,
"learning_rate": 0.0009080000000000001,
"loss": 4.9697,
"step": 456
},
{
"epoch": 0.77,
"learning_rate": 0.00091,
"loss": 5.1938,
"step": 457
},
{
"epoch": 0.77,
"learning_rate": 0.000912,
"loss": 5.1972,
"step": 458
},
{
"epoch": 0.77,
"learning_rate": 0.0009140000000000001,
"loss": 5.088,
"step": 459
},
{
"epoch": 0.77,
"learning_rate": 0.000916,
"loss": 4.9671,
"step": 460
},
{
"epoch": 0.78,
"learning_rate": 0.0009180000000000001,
"loss": 5.0251,
"step": 461
},
{
"epoch": 0.78,
"learning_rate": 0.00092,
"loss": 4.7734,
"step": 462
},
{
"epoch": 0.78,
"learning_rate": 0.0009220000000000001,
"loss": 4.8,
"step": 463
},
{
"epoch": 0.78,
"learning_rate": 0.000924,
"loss": 5.2001,
"step": 464
},
{
"epoch": 0.78,
"learning_rate": 0.0009260000000000001,
"loss": 5.2366,
"step": 465
},
{
"epoch": 0.78,
"learning_rate": 0.0009280000000000001,
"loss": 5.0479,
"step": 466
},
{
"epoch": 0.79,
"learning_rate": 0.00093,
"loss": 4.9839,
"step": 467
},
{
"epoch": 0.79,
"learning_rate": 0.0009320000000000001,
"loss": 4.8302,
"step": 468
},
{
"epoch": 0.79,
"learning_rate": 0.000934,
"loss": 5.0382,
"step": 469
},
{
"epoch": 0.79,
"learning_rate": 0.0009360000000000001,
"loss": 4.7301,
"step": 470
},
{
"epoch": 0.79,
"learning_rate": 0.0009379999999999999,
"loss": 4.8497,
"step": 471
},
{
"epoch": 0.79,
"learning_rate": 0.00094,
"loss": 4.819,
"step": 472
},
{
"epoch": 0.8,
"learning_rate": 0.000942,
"loss": 4.9396,
"step": 473
},
{
"epoch": 0.8,
"learning_rate": 0.000944,
"loss": 4.8436,
"step": 474
},
{
"epoch": 0.8,
"learning_rate": 0.000946,
"loss": 4.8317,
"step": 475
},
{
"epoch": 0.8,
"learning_rate": 0.000948,
"loss": 5.2336,
"step": 476
},
{
"epoch": 0.8,
"learning_rate": 0.00095,
"loss": 4.9405,
"step": 477
},
{
"epoch": 0.8,
"learning_rate": 0.0009519999999999999,
"loss": 4.927,
"step": 478
},
{
"epoch": 0.81,
"learning_rate": 0.000954,
"loss": 4.6957,
"step": 479
},
{
"epoch": 0.81,
"learning_rate": 0.0009559999999999999,
"loss": 4.625,
"step": 480
},
{
"epoch": 0.81,
"learning_rate": 0.000958,
"loss": 5.3568,
"step": 481
},
{
"epoch": 0.81,
"learning_rate": 0.00096,
"loss": 5.7506,
"step": 482
},
{
"epoch": 0.81,
"learning_rate": 0.000962,
"loss": 5.1788,
"step": 483
},
{
"epoch": 0.81,
"learning_rate": 0.000964,
"loss": 5.0361,
"step": 484
},
{
"epoch": 0.82,
"learning_rate": 0.000966,
"loss": 4.8903,
"step": 485
},
{
"epoch": 0.82,
"learning_rate": 0.000968,
"loss": 4.8917,
"step": 486
},
{
"epoch": 0.82,
"learning_rate": 0.0009699999999999999,
"loss": 4.8628,
"step": 487
},
{
"epoch": 0.82,
"learning_rate": 0.000972,
"loss": 4.8763,
"step": 488
},
{
"epoch": 0.82,
"learning_rate": 0.000974,
"loss": 5.002,
"step": 489
},
{
"epoch": 0.82,
"learning_rate": 0.000976,
"loss": 4.7335,
"step": 490
},
{
"epoch": 0.83,
"learning_rate": 0.000978,
"loss": 4.9556,
"step": 491
},
{
"epoch": 0.83,
"learning_rate": 0.00098,
"loss": 4.9359,
"step": 492
},
{
"epoch": 0.83,
"learning_rate": 0.000982,
"loss": 4.715,
"step": 493
},
{
"epoch": 0.83,
"learning_rate": 0.000984,
"loss": 4.8199,
"step": 494
},
{
"epoch": 0.83,
"learning_rate": 0.0009860000000000001,
"loss": 4.9607,
"step": 495
},
{
"epoch": 0.83,
"learning_rate": 0.000988,
"loss": 5.1614,
"step": 496
},
{
"epoch": 0.84,
"learning_rate": 0.00099,
"loss": 4.9319,
"step": 497
},
{
"epoch": 0.84,
"learning_rate": 0.000992,
"loss": 4.8599,
"step": 498
},
{
"epoch": 0.84,
"learning_rate": 0.000994,
"loss": 4.9016,
"step": 499
},
{
"epoch": 0.84,
"learning_rate": 0.000996,
"loss": 4.8633,
"step": 500
},
{
"epoch": 0.84,
"eval_loss": 5.217503070831299,
"eval_runtime": 761.5786,
"eval_samples_per_second": 3.469,
"eval_steps_per_second": 0.29,
"eval_wer": 2.0223324077746927,
"step": 500
},
{
"epoch": 0.84,
"learning_rate": 0.000998,
"loss": 5.0821,
"step": 501
},
{
"epoch": 0.84,
"learning_rate": 0.001,
"loss": 4.9581,
"step": 502
},
{
"epoch": 0.85,
"learning_rate": 0.0009893617021276596,
"loss": 4.9624,
"step": 503
},
{
"epoch": 0.85,
"learning_rate": 0.0009787234042553192,
"loss": 5.1349,
"step": 504
},
{
"epoch": 0.85,
"learning_rate": 0.0009680851063829787,
"loss": 5.0018,
"step": 505
},
{
"epoch": 0.85,
"learning_rate": 0.0009574468085106384,
"loss": 5.6814,
"step": 506
},
{
"epoch": 0.85,
"learning_rate": 0.0009468085106382979,
"loss": 4.8924,
"step": 507
},
{
"epoch": 0.85,
"learning_rate": 0.0009361702127659575,
"loss": 4.9127,
"step": 508
},
{
"epoch": 0.86,
"learning_rate": 0.000925531914893617,
"loss": 4.9308,
"step": 509
},
{
"epoch": 0.86,
"learning_rate": 0.0009148936170212766,
"loss": 5.075,
"step": 510
},
{
"epoch": 0.86,
"learning_rate": 0.0009042553191489362,
"loss": 5.0711,
"step": 511
},
{
"epoch": 0.86,
"learning_rate": 0.0008936170212765957,
"loss": 4.7922,
"step": 512
},
{
"epoch": 0.86,
"learning_rate": 0.0008829787234042553,
"loss": 4.8064,
"step": 513
},
{
"epoch": 0.86,
"learning_rate": 0.0008723404255319149,
"loss": 5.0308,
"step": 514
},
{
"epoch": 0.87,
"learning_rate": 0.0008617021276595744,
"loss": 4.9314,
"step": 515
},
{
"epoch": 0.87,
"learning_rate": 0.000851063829787234,
"loss": 4.8477,
"step": 516
},
{
"epoch": 0.87,
"learning_rate": 0.0008404255319148936,
"loss": 4.9286,
"step": 517
},
{
"epoch": 0.87,
"learning_rate": 0.0008297872340425531,
"loss": 5.4933,
"step": 518
},
{
"epoch": 0.87,
"learning_rate": 0.0008191489361702128,
"loss": 4.8794,
"step": 519
},
{
"epoch": 0.87,
"learning_rate": 0.0008085106382978723,
"loss": 4.8869,
"step": 520
},
{
"epoch": 0.88,
"learning_rate": 0.0007978723404255319,
"loss": 5.1175,
"step": 521
},
{
"epoch": 0.88,
"learning_rate": 0.0007872340425531915,
"loss": 4.9459,
"step": 522
},
{
"epoch": 0.88,
"learning_rate": 0.000776595744680851,
"loss": 4.7847,
"step": 523
},
{
"epoch": 0.88,
"learning_rate": 0.0007659574468085106,
"loss": 4.5425,
"step": 524
},
{
"epoch": 0.88,
"learning_rate": 0.0007553191489361702,
"loss": 4.8546,
"step": 525
},
{
"epoch": 0.88,
"learning_rate": 0.0007446808510638298,
"loss": 4.9989,
"step": 526
},
{
"epoch": 0.89,
"learning_rate": 0.0007340425531914894,
"loss": 5.0116,
"step": 527
},
{
"epoch": 0.89,
"learning_rate": 0.000723404255319149,
"loss": 4.7372,
"step": 528
},
{
"epoch": 0.89,
"learning_rate": 0.0007127659574468085,
"loss": 4.8166,
"step": 529
},
{
"epoch": 0.89,
"learning_rate": 0.0007021276595744682,
"loss": 4.6332,
"step": 530
},
{
"epoch": 0.89,
"learning_rate": 0.0006914893617021278,
"loss": 4.6867,
"step": 531
},
{
"epoch": 0.89,
"learning_rate": 0.0006808510638297873,
"loss": 4.987,
"step": 532
},
{
"epoch": 0.9,
"learning_rate": 0.0006702127659574469,
"loss": 4.8099,
"step": 533
},
{
"epoch": 0.9,
"learning_rate": 0.0006595744680851064,
"loss": 4.7489,
"step": 534
},
{
"epoch": 0.9,
"learning_rate": 0.000648936170212766,
"loss": 4.736,
"step": 535
},
{
"epoch": 0.9,
"learning_rate": 0.0006382978723404256,
"loss": 5.0293,
"step": 536
},
{
"epoch": 0.9,
"learning_rate": 0.0006276595744680851,
"loss": 4.9617,
"step": 537
},
{
"epoch": 0.9,
"learning_rate": 0.0006170212765957447,
"loss": 4.794,
"step": 538
},
{
"epoch": 0.91,
"learning_rate": 0.0006063829787234043,
"loss": 4.7831,
"step": 539
},
{
"epoch": 0.91,
"learning_rate": 0.0005957446808510638,
"loss": 4.718,
"step": 540
},
{
"epoch": 0.91,
"learning_rate": 0.0005851063829787234,
"loss": 4.6424,
"step": 541
},
{
"epoch": 0.91,
"learning_rate": 0.0005744680851063831,
"loss": 4.9381,
"step": 542
},
{
"epoch": 0.91,
"learning_rate": 0.0005638297872340426,
"loss": 4.7384,
"step": 543
},
{
"epoch": 0.91,
"learning_rate": 0.0005531914893617022,
"loss": 4.8799,
"step": 544
},
{
"epoch": 0.92,
"learning_rate": 0.0005425531914893617,
"loss": 4.8677,
"step": 545
},
{
"epoch": 0.92,
"learning_rate": 0.0005319148936170213,
"loss": 5.0294,
"step": 546
},
{
"epoch": 0.92,
"learning_rate": 0.0005212765957446809,
"loss": 4.6956,
"step": 547
},
{
"epoch": 0.92,
"learning_rate": 0.0005106382978723404,
"loss": 5.2215,
"step": 548
},
{
"epoch": 0.92,
"learning_rate": 0.0005,
"loss": 5.5748,
"step": 549
},
{
"epoch": 0.92,
"learning_rate": 0.0004893617021276596,
"loss": 4.9262,
"step": 550
},
{
"epoch": 0.93,
"learning_rate": 0.0004787234042553192,
"loss": 4.9315,
"step": 551
},
{
"epoch": 0.93,
"learning_rate": 0.00046808510638297874,
"loss": 5.0552,
"step": 552
},
{
"epoch": 0.93,
"learning_rate": 0.0004574468085106383,
"loss": 4.862,
"step": 553
},
{
"epoch": 0.93,
"learning_rate": 0.00044680851063829785,
"loss": 4.6946,
"step": 554
},
{
"epoch": 0.93,
"learning_rate": 0.00043617021276595746,
"loss": 4.7878,
"step": 555
},
{
"epoch": 0.93,
"learning_rate": 0.000425531914893617,
"loss": 4.8172,
"step": 556
},
{
"epoch": 0.94,
"learning_rate": 0.0004148936170212766,
"loss": 4.9713,
"step": 557
},
{
"epoch": 0.94,
"learning_rate": 0.00040425531914893613,
"loss": 4.7684,
"step": 558
},
{
"epoch": 0.94,
"learning_rate": 0.00039361702127659574,
"loss": 4.5917,
"step": 559
},
{
"epoch": 0.94,
"learning_rate": 0.0003829787234042553,
"loss": 4.5853,
"step": 560
},
{
"epoch": 0.94,
"learning_rate": 0.0003723404255319149,
"loss": 5.0219,
"step": 561
},
{
"epoch": 0.94,
"learning_rate": 0.0003617021276595745,
"loss": 4.6859,
"step": 562
},
{
"epoch": 0.95,
"learning_rate": 0.0003510638297872341,
"loss": 4.6475,
"step": 563
},
{
"epoch": 0.95,
"learning_rate": 0.00034042553191489364,
"loss": 5.0037,
"step": 564
},
{
"epoch": 0.95,
"learning_rate": 0.0003297872340425532,
"loss": 4.6778,
"step": 565
},
{
"epoch": 0.95,
"learning_rate": 0.0003191489361702128,
"loss": 5.0328,
"step": 566
},
{
"epoch": 0.95,
"learning_rate": 0.00030851063829787236,
"loss": 4.7141,
"step": 567
},
{
"epoch": 0.96,
"learning_rate": 0.0002978723404255319,
"loss": 4.7798,
"step": 568
},
{
"epoch": 0.96,
"learning_rate": 0.00028723404255319153,
"loss": 4.6515,
"step": 569
},
{
"epoch": 0.96,
"learning_rate": 0.0002765957446808511,
"loss": 4.7992,
"step": 570
},
{
"epoch": 0.96,
"learning_rate": 0.00026595744680851064,
"loss": 4.8235,
"step": 571
},
{
"epoch": 0.96,
"learning_rate": 0.0002553191489361702,
"loss": 4.7412,
"step": 572
},
{
"epoch": 0.96,
"learning_rate": 0.0002446808510638298,
"loss": 4.7087,
"step": 573
},
{
"epoch": 0.97,
"learning_rate": 0.00023404255319148937,
"loss": 4.5968,
"step": 574
},
{
"epoch": 0.97,
"learning_rate": 0.00022340425531914892,
"loss": 4.7226,
"step": 575
},
{
"epoch": 0.97,
"learning_rate": 0.0002127659574468085,
"loss": 4.7007,
"step": 576
},
{
"epoch": 0.97,
"learning_rate": 0.00020212765957446807,
"loss": 4.6527,
"step": 577
},
{
"epoch": 0.97,
"learning_rate": 0.00019148936170212765,
"loss": 4.4518,
"step": 578
},
{
"epoch": 0.97,
"learning_rate": 0.00018085106382978726,
"loss": 4.4938,
"step": 579
},
{
"epoch": 0.98,
"learning_rate": 0.00017021276595744682,
"loss": 4.6588,
"step": 580
},
{
"epoch": 0.98,
"learning_rate": 0.0001595744680851064,
"loss": 4.8716,
"step": 581
},
{
"epoch": 0.98,
"learning_rate": 0.00014893617021276596,
"loss": 4.6649,
"step": 582
},
{
"epoch": 0.98,
"learning_rate": 0.00013829787234042554,
"loss": 4.5137,
"step": 583
},
{
"epoch": 0.98,
"learning_rate": 0.0001276595744680851,
"loss": 4.6762,
"step": 584
},
{
"epoch": 0.98,
"learning_rate": 0.00011702127659574468,
"loss": 4.7224,
"step": 585
},
{
"epoch": 0.99,
"learning_rate": 0.00010638297872340425,
"loss": 4.5619,
"step": 586
},
{
"epoch": 0.99,
"learning_rate": 9.574468085106382e-05,
"loss": 4.6919,
"step": 587
},
{
"epoch": 0.99,
"learning_rate": 8.510638297872341e-05,
"loss": 4.7372,
"step": 588
},
{
"epoch": 0.99,
"learning_rate": 7.446808510638298e-05,
"loss": 4.749,
"step": 589
},
{
"epoch": 0.99,
"learning_rate": 6.382978723404255e-05,
"loss": 4.5827,
"step": 590
},
{
"epoch": 0.99,
"learning_rate": 5.319148936170213e-05,
"loss": 4.8585,
"step": 591
},
{
"epoch": 1.0,
"learning_rate": 4.2553191489361704e-05,
"loss": 6.0408,
"step": 592
},
{
"epoch": 1.0,
"learning_rate": 3.1914893617021275e-05,
"loss": 4.9389,
"step": 593
},
{
"epoch": 1.0,
"learning_rate": 2.1276595744680852e-05,
"loss": 4.8241,
"step": 594
},
{
"epoch": 1.0,
"step": 594,
"total_flos": 0.0,
"train_loss": 4.7614816479409985,
"train_runtime": 5563.7628,
"train_samples_per_second": 5.129,
"train_steps_per_second": 0.107
}
],
"max_steps": 594,
"num_train_epochs": 1,
"total_flos": 0.0,
"trial_name": null,
"trial_params": null
}