wav2vec2-2-gpt2-grid-search / trainer_state.json
sanchit-gandhi's picture
End of training
f49a2c6
raw
history blame
34.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9987389659520807,
"global_step": 297,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 6e-07,
"loss": 4.7618,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 1.2e-06,
"loss": 4.8369,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 1.8e-06,
"loss": 4.9039,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 2.4e-06,
"loss": 4.8342,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 2.9999999999999997e-06,
"loss": 4.7062,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 2.9999999999999997e-06,
"loss": 4.8101,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 3.6e-06,
"loss": 4.7869,
"step": 7
},
{
"epoch": 0.03,
"learning_rate": 4.2e-06,
"loss": 4.8273,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 4.8e-06,
"loss": 4.7126,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 5.399999999999999e-06,
"loss": 4.5265,
"step": 10
},
{
"epoch": 0.04,
"learning_rate": 5.999999999999999e-06,
"loss": 4.6391,
"step": 11
},
{
"epoch": 0.04,
"learning_rate": 6.599999999999999e-06,
"loss": 4.6458,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 7.2e-06,
"loss": 4.5424,
"step": 13
},
{
"epoch": 0.05,
"learning_rate": 7.799999999999998e-06,
"loss": 4.4681,
"step": 14
},
{
"epoch": 0.05,
"learning_rate": 8.4e-06,
"loss": 4.4776,
"step": 15
},
{
"epoch": 0.05,
"learning_rate": 8.999999999999999e-06,
"loss": 4.3842,
"step": 16
},
{
"epoch": 0.06,
"learning_rate": 9.6e-06,
"loss": 4.4551,
"step": 17
},
{
"epoch": 0.06,
"learning_rate": 1.02e-05,
"loss": 4.464,
"step": 18
},
{
"epoch": 0.06,
"learning_rate": 1.0799999999999998e-05,
"loss": 4.4038,
"step": 19
},
{
"epoch": 0.07,
"learning_rate": 1.14e-05,
"loss": 4.4641,
"step": 20
},
{
"epoch": 0.07,
"learning_rate": 1.1999999999999999e-05,
"loss": 4.4573,
"step": 21
},
{
"epoch": 0.07,
"learning_rate": 1.26e-05,
"loss": 4.4293,
"step": 22
},
{
"epoch": 0.08,
"learning_rate": 1.3199999999999997e-05,
"loss": 4.3034,
"step": 23
},
{
"epoch": 0.08,
"learning_rate": 1.3799999999999998e-05,
"loss": 4.4353,
"step": 24
},
{
"epoch": 0.08,
"learning_rate": 1.44e-05,
"loss": 4.2729,
"step": 25
},
{
"epoch": 0.09,
"learning_rate": 1.4999999999999999e-05,
"loss": 4.5593,
"step": 26
},
{
"epoch": 0.09,
"learning_rate": 1.5599999999999996e-05,
"loss": 4.3209,
"step": 27
},
{
"epoch": 0.09,
"learning_rate": 1.6199999999999997e-05,
"loss": 4.28,
"step": 28
},
{
"epoch": 0.1,
"learning_rate": 1.68e-05,
"loss": 4.1973,
"step": 29
},
{
"epoch": 0.1,
"learning_rate": 1.74e-05,
"loss": 4.3831,
"step": 30
},
{
"epoch": 0.1,
"learning_rate": 1.7999999999999997e-05,
"loss": 4.3821,
"step": 31
},
{
"epoch": 0.11,
"learning_rate": 1.8599999999999998e-05,
"loss": 4.2869,
"step": 32
},
{
"epoch": 0.11,
"learning_rate": 1.92e-05,
"loss": 4.3257,
"step": 33
},
{
"epoch": 0.11,
"learning_rate": 1.98e-05,
"loss": 4.2833,
"step": 34
},
{
"epoch": 0.12,
"learning_rate": 2.04e-05,
"loss": 4.2935,
"step": 35
},
{
"epoch": 0.12,
"learning_rate": 2.1e-05,
"loss": 4.2883,
"step": 36
},
{
"epoch": 0.12,
"learning_rate": 2.1599999999999996e-05,
"loss": 4.383,
"step": 37
},
{
"epoch": 0.13,
"learning_rate": 2.2199999999999998e-05,
"loss": 4.3507,
"step": 38
},
{
"epoch": 0.13,
"learning_rate": 2.28e-05,
"loss": 4.3818,
"step": 39
},
{
"epoch": 0.13,
"learning_rate": 2.34e-05,
"loss": 4.2444,
"step": 40
},
{
"epoch": 0.14,
"learning_rate": 2.3999999999999997e-05,
"loss": 4.3261,
"step": 41
},
{
"epoch": 0.14,
"learning_rate": 2.4599999999999998e-05,
"loss": 4.3685,
"step": 42
},
{
"epoch": 0.14,
"learning_rate": 2.52e-05,
"loss": 4.173,
"step": 43
},
{
"epoch": 0.15,
"learning_rate": 2.5799999999999997e-05,
"loss": 4.4693,
"step": 44
},
{
"epoch": 0.15,
"learning_rate": 2.6399999999999995e-05,
"loss": 4.3993,
"step": 45
},
{
"epoch": 0.15,
"learning_rate": 2.6999999999999996e-05,
"loss": 4.4401,
"step": 46
},
{
"epoch": 0.16,
"learning_rate": 2.7599999999999997e-05,
"loss": 4.4005,
"step": 47
},
{
"epoch": 0.16,
"learning_rate": 2.8199999999999998e-05,
"loss": 4.5188,
"step": 48
},
{
"epoch": 0.16,
"learning_rate": 2.88e-05,
"loss": 4.5981,
"step": 49
},
{
"epoch": 0.17,
"learning_rate": 2.94e-05,
"loss": 4.33,
"step": 50
},
{
"epoch": 0.17,
"learning_rate": 2.9999999999999997e-05,
"loss": 4.2833,
"step": 51
},
{
"epoch": 0.17,
"learning_rate": 3.06e-05,
"loss": 4.1861,
"step": 52
},
{
"epoch": 0.18,
"learning_rate": 3.119999999999999e-05,
"loss": 4.1606,
"step": 53
},
{
"epoch": 0.18,
"learning_rate": 3.1799999999999994e-05,
"loss": 4.1487,
"step": 54
},
{
"epoch": 0.18,
"learning_rate": 3.2399999999999995e-05,
"loss": 4.1247,
"step": 55
},
{
"epoch": 0.19,
"learning_rate": 3.2999999999999996e-05,
"loss": 4.1405,
"step": 56
},
{
"epoch": 0.19,
"learning_rate": 3.36e-05,
"loss": 4.2426,
"step": 57
},
{
"epoch": 0.2,
"learning_rate": 3.42e-05,
"loss": 4.2457,
"step": 58
},
{
"epoch": 0.2,
"learning_rate": 3.48e-05,
"loss": 4.2196,
"step": 59
},
{
"epoch": 0.2,
"learning_rate": 3.539999999999999e-05,
"loss": 4.1715,
"step": 60
},
{
"epoch": 0.21,
"learning_rate": 3.5999999999999994e-05,
"loss": 4.2176,
"step": 61
},
{
"epoch": 0.21,
"learning_rate": 3.6599999999999995e-05,
"loss": 4.1274,
"step": 62
},
{
"epoch": 0.21,
"learning_rate": 3.7199999999999996e-05,
"loss": 4.2297,
"step": 63
},
{
"epoch": 0.22,
"learning_rate": 3.78e-05,
"loss": 4.1769,
"step": 64
},
{
"epoch": 0.22,
"learning_rate": 3.84e-05,
"loss": 4.2444,
"step": 65
},
{
"epoch": 0.22,
"learning_rate": 3.9e-05,
"loss": 4.269,
"step": 66
},
{
"epoch": 0.23,
"learning_rate": 3.96e-05,
"loss": 4.2211,
"step": 67
},
{
"epoch": 0.23,
"learning_rate": 4.02e-05,
"loss": 4.2461,
"step": 68
},
{
"epoch": 0.23,
"learning_rate": 4.08e-05,
"loss": 4.1886,
"step": 69
},
{
"epoch": 0.24,
"learning_rate": 4.14e-05,
"loss": 4.1348,
"step": 70
},
{
"epoch": 0.24,
"learning_rate": 4.2e-05,
"loss": 4.1446,
"step": 71
},
{
"epoch": 0.24,
"learning_rate": 4.259999999999999e-05,
"loss": 4.2637,
"step": 72
},
{
"epoch": 0.25,
"learning_rate": 4.319999999999999e-05,
"loss": 4.1766,
"step": 73
},
{
"epoch": 0.25,
"learning_rate": 4.3799999999999994e-05,
"loss": 4.1819,
"step": 74
},
{
"epoch": 0.25,
"learning_rate": 4.4399999999999995e-05,
"loss": 4.2714,
"step": 75
},
{
"epoch": 0.26,
"learning_rate": 4.4999999999999996e-05,
"loss": 4.1555,
"step": 76
},
{
"epoch": 0.26,
"learning_rate": 4.56e-05,
"loss": 4.115,
"step": 77
},
{
"epoch": 0.26,
"learning_rate": 4.62e-05,
"loss": 4.1782,
"step": 78
},
{
"epoch": 0.27,
"learning_rate": 4.68e-05,
"loss": 4.0608,
"step": 79
},
{
"epoch": 0.27,
"learning_rate": 4.7399999999999993e-05,
"loss": 4.2616,
"step": 80
},
{
"epoch": 0.27,
"learning_rate": 4.7999999999999994e-05,
"loss": 4.1796,
"step": 81
},
{
"epoch": 0.28,
"learning_rate": 4.8599999999999995e-05,
"loss": 4.1938,
"step": 82
},
{
"epoch": 0.28,
"learning_rate": 4.9199999999999997e-05,
"loss": 4.1566,
"step": 83
},
{
"epoch": 0.28,
"learning_rate": 4.98e-05,
"loss": 4.2077,
"step": 84
},
{
"epoch": 0.29,
"learning_rate": 5.04e-05,
"loss": 4.2998,
"step": 85
},
{
"epoch": 0.29,
"learning_rate": 5.1e-05,
"loss": 4.1818,
"step": 86
},
{
"epoch": 0.29,
"learning_rate": 5.1599999999999994e-05,
"loss": 4.2057,
"step": 87
},
{
"epoch": 0.3,
"learning_rate": 5.2199999999999995e-05,
"loss": 4.2609,
"step": 88
},
{
"epoch": 0.3,
"learning_rate": 5.279999999999999e-05,
"loss": 4.2556,
"step": 89
},
{
"epoch": 0.3,
"learning_rate": 5.339999999999999e-05,
"loss": 4.2753,
"step": 90
},
{
"epoch": 0.31,
"learning_rate": 5.399999999999999e-05,
"loss": 4.2857,
"step": 91
},
{
"epoch": 0.31,
"learning_rate": 5.459999999999999e-05,
"loss": 4.3769,
"step": 92
},
{
"epoch": 0.31,
"learning_rate": 5.519999999999999e-05,
"loss": 4.3304,
"step": 93
},
{
"epoch": 0.32,
"learning_rate": 5.5799999999999994e-05,
"loss": 4.2605,
"step": 94
},
{
"epoch": 0.32,
"learning_rate": 5.6399999999999995e-05,
"loss": 4.22,
"step": 95
},
{
"epoch": 0.32,
"learning_rate": 5.6999999999999996e-05,
"loss": 4.3934,
"step": 96
},
{
"epoch": 0.33,
"learning_rate": 5.76e-05,
"loss": 4.5994,
"step": 97
},
{
"epoch": 0.33,
"learning_rate": 5.82e-05,
"loss": 4.501,
"step": 98
},
{
"epoch": 0.33,
"learning_rate": 5.88e-05,
"loss": 4.5049,
"step": 99
},
{
"epoch": 0.34,
"learning_rate": 5.94e-05,
"loss": 4.5439,
"step": 100
},
{
"epoch": 0.34,
"learning_rate": 5.9999999999999995e-05,
"loss": 4.151,
"step": 101
},
{
"epoch": 0.34,
"learning_rate": 6.0599999999999996e-05,
"loss": 4.2256,
"step": 102
},
{
"epoch": 0.35,
"learning_rate": 6.12e-05,
"loss": 4.2254,
"step": 103
},
{
"epoch": 0.35,
"learning_rate": 6.18e-05,
"loss": 4.1119,
"step": 104
},
{
"epoch": 0.35,
"learning_rate": 6.239999999999999e-05,
"loss": 4.2265,
"step": 105
},
{
"epoch": 0.36,
"learning_rate": 6.299999999999999e-05,
"loss": 4.1184,
"step": 106
},
{
"epoch": 0.36,
"learning_rate": 6.359999999999999e-05,
"loss": 4.0849,
"step": 107
},
{
"epoch": 0.36,
"learning_rate": 6.419999999999999e-05,
"loss": 4.1875,
"step": 108
},
{
"epoch": 0.37,
"learning_rate": 6.479999999999999e-05,
"loss": 4.2126,
"step": 109
},
{
"epoch": 0.37,
"learning_rate": 6.539999999999999e-05,
"loss": 4.1841,
"step": 110
},
{
"epoch": 0.37,
"learning_rate": 6.599999999999999e-05,
"loss": 4.2574,
"step": 111
},
{
"epoch": 0.38,
"learning_rate": 6.659999999999999e-05,
"loss": 4.1733,
"step": 112
},
{
"epoch": 0.38,
"learning_rate": 6.72e-05,
"loss": 4.1252,
"step": 113
},
{
"epoch": 0.38,
"learning_rate": 6.78e-05,
"loss": 4.1765,
"step": 114
},
{
"epoch": 0.39,
"learning_rate": 6.84e-05,
"loss": 4.1348,
"step": 115
},
{
"epoch": 0.39,
"learning_rate": 6.9e-05,
"loss": 4.1559,
"step": 116
},
{
"epoch": 0.39,
"learning_rate": 6.96e-05,
"loss": 4.0819,
"step": 117
},
{
"epoch": 0.4,
"learning_rate": 7.02e-05,
"loss": 4.1073,
"step": 118
},
{
"epoch": 0.4,
"learning_rate": 7.079999999999999e-05,
"loss": 4.1662,
"step": 119
},
{
"epoch": 0.4,
"learning_rate": 7.139999999999999e-05,
"loss": 4.1839,
"step": 120
},
{
"epoch": 0.41,
"learning_rate": 7.199999999999999e-05,
"loss": 4.1792,
"step": 121
},
{
"epoch": 0.41,
"learning_rate": 7.259999999999999e-05,
"loss": 4.2598,
"step": 122
},
{
"epoch": 0.41,
"learning_rate": 7.319999999999999e-05,
"loss": 4.1077,
"step": 123
},
{
"epoch": 0.42,
"learning_rate": 7.379999999999999e-05,
"loss": 4.2183,
"step": 124
},
{
"epoch": 0.42,
"learning_rate": 7.439999999999999e-05,
"loss": 4.2679,
"step": 125
},
{
"epoch": 0.42,
"learning_rate": 7.5e-05,
"loss": 4.1706,
"step": 126
},
{
"epoch": 0.43,
"learning_rate": 7.56e-05,
"loss": 4.1944,
"step": 127
},
{
"epoch": 0.43,
"learning_rate": 7.62e-05,
"loss": 4.1017,
"step": 128
},
{
"epoch": 0.43,
"learning_rate": 7.68e-05,
"loss": 4.2433,
"step": 129
},
{
"epoch": 0.44,
"learning_rate": 7.74e-05,
"loss": 4.3565,
"step": 130
},
{
"epoch": 0.44,
"learning_rate": 7.8e-05,
"loss": 4.2272,
"step": 131
},
{
"epoch": 0.44,
"learning_rate": 7.86e-05,
"loss": 4.0888,
"step": 132
},
{
"epoch": 0.45,
"learning_rate": 7.92e-05,
"loss": 4.2885,
"step": 133
},
{
"epoch": 0.45,
"learning_rate": 7.98e-05,
"loss": 4.1271,
"step": 134
},
{
"epoch": 0.45,
"learning_rate": 8.04e-05,
"loss": 4.2945,
"step": 135
},
{
"epoch": 0.46,
"learning_rate": 8.1e-05,
"loss": 4.2135,
"step": 136
},
{
"epoch": 0.46,
"learning_rate": 8.16e-05,
"loss": 4.1432,
"step": 137
},
{
"epoch": 0.46,
"learning_rate": 8.22e-05,
"loss": 4.0684,
"step": 138
},
{
"epoch": 0.47,
"learning_rate": 8.28e-05,
"loss": 4.1384,
"step": 139
},
{
"epoch": 0.47,
"learning_rate": 8.34e-05,
"loss": 4.1156,
"step": 140
},
{
"epoch": 0.47,
"learning_rate": 8.4e-05,
"loss": 4.3396,
"step": 141
},
{
"epoch": 0.48,
"learning_rate": 8.459999999999998e-05,
"loss": 4.1454,
"step": 142
},
{
"epoch": 0.48,
"learning_rate": 8.519999999999998e-05,
"loss": 4.2154,
"step": 143
},
{
"epoch": 0.48,
"learning_rate": 8.579999999999998e-05,
"loss": 4.2913,
"step": 144
},
{
"epoch": 0.49,
"learning_rate": 8.639999999999999e-05,
"loss": 4.4081,
"step": 145
},
{
"epoch": 0.49,
"learning_rate": 8.699999999999999e-05,
"loss": 4.1594,
"step": 146
},
{
"epoch": 0.49,
"learning_rate": 8.759999999999999e-05,
"loss": 4.4372,
"step": 147
},
{
"epoch": 0.5,
"learning_rate": 8.819999999999999e-05,
"loss": 4.4614,
"step": 148
},
{
"epoch": 0.5,
"learning_rate": 8.879999999999999e-05,
"loss": 4.364,
"step": 149
},
{
"epoch": 0.5,
"learning_rate": 8.939999999999999e-05,
"loss": 4.509,
"step": 150
},
{
"epoch": 0.51,
"learning_rate": 8.999999999999999e-05,
"loss": 4.3189,
"step": 151
},
{
"epoch": 0.51,
"learning_rate": 9.059999999999999e-05,
"loss": 4.2422,
"step": 152
},
{
"epoch": 0.51,
"learning_rate": 9.12e-05,
"loss": 4.2332,
"step": 153
},
{
"epoch": 0.52,
"learning_rate": 9.18e-05,
"loss": 4.1696,
"step": 154
},
{
"epoch": 0.52,
"learning_rate": 9.24e-05,
"loss": 4.1948,
"step": 155
},
{
"epoch": 0.52,
"learning_rate": 9.3e-05,
"loss": 4.2067,
"step": 156
},
{
"epoch": 0.53,
"learning_rate": 9.36e-05,
"loss": 4.1373,
"step": 157
},
{
"epoch": 0.53,
"learning_rate": 9.419999999999999e-05,
"loss": 4.1534,
"step": 158
},
{
"epoch": 0.53,
"learning_rate": 9.479999999999999e-05,
"loss": 4.2066,
"step": 159
},
{
"epoch": 0.54,
"learning_rate": 9.539999999999999e-05,
"loss": 4.1735,
"step": 160
},
{
"epoch": 0.54,
"learning_rate": 9.599999999999999e-05,
"loss": 4.1721,
"step": 161
},
{
"epoch": 0.54,
"learning_rate": 9.659999999999999e-05,
"loss": 4.1015,
"step": 162
},
{
"epoch": 0.55,
"learning_rate": 9.719999999999999e-05,
"loss": 4.2207,
"step": 163
},
{
"epoch": 0.55,
"learning_rate": 9.779999999999999e-05,
"loss": 4.121,
"step": 164
},
{
"epoch": 0.55,
"learning_rate": 9.839999999999999e-05,
"loss": 4.2027,
"step": 165
},
{
"epoch": 0.56,
"learning_rate": 9.9e-05,
"loss": 4.1739,
"step": 166
},
{
"epoch": 0.56,
"learning_rate": 9.96e-05,
"loss": 4.137,
"step": 167
},
{
"epoch": 0.56,
"learning_rate": 0.0001002,
"loss": 4.1687,
"step": 168
},
{
"epoch": 0.57,
"learning_rate": 0.0001008,
"loss": 4.2167,
"step": 169
},
{
"epoch": 0.57,
"learning_rate": 0.0001014,
"loss": 4.109,
"step": 170
},
{
"epoch": 0.58,
"learning_rate": 0.000102,
"loss": 4.1,
"step": 171
},
{
"epoch": 0.58,
"learning_rate": 0.0001026,
"loss": 4.1818,
"step": 172
},
{
"epoch": 0.58,
"learning_rate": 0.00010319999999999999,
"loss": 4.078,
"step": 173
},
{
"epoch": 0.59,
"learning_rate": 0.00010379999999999999,
"loss": 4.1348,
"step": 174
},
{
"epoch": 0.59,
"learning_rate": 0.00010439999999999999,
"loss": 4.2973,
"step": 175
},
{
"epoch": 0.59,
"learning_rate": 0.00010499999999999999,
"loss": 4.131,
"step": 176
},
{
"epoch": 0.6,
"learning_rate": 0.00010559999999999998,
"loss": 4.24,
"step": 177
},
{
"epoch": 0.6,
"learning_rate": 0.00010619999999999998,
"loss": 4.1048,
"step": 178
},
{
"epoch": 0.6,
"learning_rate": 0.00010679999999999998,
"loss": 4.0966,
"step": 179
},
{
"epoch": 0.61,
"learning_rate": 0.00010739999999999998,
"loss": 4.3612,
"step": 180
},
{
"epoch": 0.61,
"learning_rate": 0.00010799999999999998,
"loss": 4.1656,
"step": 181
},
{
"epoch": 0.61,
"learning_rate": 0.00010859999999999998,
"loss": 4.0714,
"step": 182
},
{
"epoch": 0.62,
"learning_rate": 0.00010919999999999998,
"loss": 4.1186,
"step": 183
},
{
"epoch": 0.62,
"learning_rate": 0.00010979999999999999,
"loss": 4.196,
"step": 184
},
{
"epoch": 0.62,
"learning_rate": 0.00011039999999999999,
"loss": 4.2281,
"step": 185
},
{
"epoch": 0.63,
"learning_rate": 0.00011099999999999999,
"loss": 4.148,
"step": 186
},
{
"epoch": 0.63,
"learning_rate": 0.00011159999999999999,
"loss": 4.1811,
"step": 187
},
{
"epoch": 0.63,
"learning_rate": 0.00011219999999999999,
"loss": 4.1562,
"step": 188
},
{
"epoch": 0.64,
"learning_rate": 0.00011279999999999999,
"loss": 4.1377,
"step": 189
},
{
"epoch": 0.64,
"learning_rate": 0.00011339999999999999,
"loss": 4.2104,
"step": 190
},
{
"epoch": 0.64,
"learning_rate": 0.00011399999999999999,
"loss": 4.3507,
"step": 191
},
{
"epoch": 0.65,
"learning_rate": 0.0001146,
"loss": 4.3164,
"step": 192
},
{
"epoch": 0.65,
"learning_rate": 0.0001152,
"loss": 4.3561,
"step": 193
},
{
"epoch": 0.65,
"learning_rate": 0.0001158,
"loss": 4.3035,
"step": 194
},
{
"epoch": 0.66,
"learning_rate": 0.0001164,
"loss": 4.2593,
"step": 195
},
{
"epoch": 0.66,
"learning_rate": 0.000117,
"loss": 4.2925,
"step": 196
},
{
"epoch": 0.66,
"learning_rate": 0.0001176,
"loss": 4.1292,
"step": 197
},
{
"epoch": 0.67,
"learning_rate": 0.0001182,
"loss": 4.6228,
"step": 198
},
{
"epoch": 0.67,
"learning_rate": 0.0001188,
"loss": 4.3744,
"step": 199
},
{
"epoch": 0.67,
"learning_rate": 0.0001194,
"loss": 4.5764,
"step": 200
},
{
"epoch": 0.68,
"learning_rate": 0.00011999999999999999,
"loss": 4.2862,
"step": 201
},
{
"epoch": 0.68,
"learning_rate": 0.00012059999999999999,
"loss": 4.2762,
"step": 202
},
{
"epoch": 0.68,
"learning_rate": 0.00012119999999999999,
"loss": 4.1847,
"step": 203
},
{
"epoch": 0.69,
"learning_rate": 0.00012179999999999999,
"loss": 4.1506,
"step": 204
},
{
"epoch": 0.69,
"learning_rate": 0.0001224,
"loss": 4.1855,
"step": 205
},
{
"epoch": 0.69,
"learning_rate": 0.00012299999999999998,
"loss": 4.143,
"step": 206
},
{
"epoch": 0.7,
"learning_rate": 0.0001236,
"loss": 4.2922,
"step": 207
},
{
"epoch": 0.7,
"learning_rate": 0.00012419999999999998,
"loss": 4.1974,
"step": 208
},
{
"epoch": 0.7,
"learning_rate": 0.00012479999999999997,
"loss": 4.1757,
"step": 209
},
{
"epoch": 0.71,
"learning_rate": 0.00012539999999999999,
"loss": 4.2773,
"step": 210
},
{
"epoch": 0.71,
"learning_rate": 0.00012599999999999997,
"loss": 4.0609,
"step": 211
},
{
"epoch": 0.71,
"learning_rate": 0.0001266,
"loss": 4.1788,
"step": 212
},
{
"epoch": 0.72,
"learning_rate": 0.00012719999999999997,
"loss": 4.3651,
"step": 213
},
{
"epoch": 0.72,
"learning_rate": 0.0001278,
"loss": 4.1737,
"step": 214
},
{
"epoch": 0.72,
"learning_rate": 0.00012839999999999998,
"loss": 4.2565,
"step": 215
},
{
"epoch": 0.73,
"learning_rate": 0.000129,
"loss": 4.1837,
"step": 216
},
{
"epoch": 0.73,
"learning_rate": 0.00012959999999999998,
"loss": 4.178,
"step": 217
},
{
"epoch": 0.73,
"learning_rate": 0.0001302,
"loss": 4.0968,
"step": 218
},
{
"epoch": 0.74,
"learning_rate": 0.00013079999999999998,
"loss": 4.1217,
"step": 219
},
{
"epoch": 0.74,
"learning_rate": 0.0001314,
"loss": 4.22,
"step": 220
},
{
"epoch": 0.74,
"learning_rate": 0.00013199999999999998,
"loss": 4.1422,
"step": 221
},
{
"epoch": 0.75,
"learning_rate": 0.0001326,
"loss": 4.0738,
"step": 222
},
{
"epoch": 0.75,
"learning_rate": 0.00013319999999999999,
"loss": 4.1446,
"step": 223
},
{
"epoch": 0.75,
"learning_rate": 0.0001338,
"loss": 4.1761,
"step": 224
},
{
"epoch": 0.76,
"learning_rate": 0.0001344,
"loss": 4.1628,
"step": 225
},
{
"epoch": 0.76,
"learning_rate": 0.000135,
"loss": 4.2661,
"step": 226
},
{
"epoch": 0.76,
"learning_rate": 0.0001356,
"loss": 4.1528,
"step": 227
},
{
"epoch": 0.77,
"learning_rate": 0.0001362,
"loss": 4.099,
"step": 228
},
{
"epoch": 0.77,
"learning_rate": 0.0001368,
"loss": 4.1245,
"step": 229
},
{
"epoch": 0.77,
"learning_rate": 0.0001374,
"loss": 4.1312,
"step": 230
},
{
"epoch": 0.78,
"learning_rate": 0.000138,
"loss": 4.3371,
"step": 231
},
{
"epoch": 0.78,
"learning_rate": 0.0001386,
"loss": 4.2686,
"step": 232
},
{
"epoch": 0.78,
"learning_rate": 0.0001392,
"loss": 4.2302,
"step": 233
},
{
"epoch": 0.79,
"learning_rate": 0.00013979999999999998,
"loss": 4.2847,
"step": 234
},
{
"epoch": 0.79,
"learning_rate": 0.0001404,
"loss": 4.2916,
"step": 235
},
{
"epoch": 0.79,
"learning_rate": 0.00014099999999999998,
"loss": 4.131,
"step": 236
},
{
"epoch": 0.8,
"learning_rate": 0.00014159999999999997,
"loss": 4.1995,
"step": 237
},
{
"epoch": 0.8,
"learning_rate": 0.0001422,
"loss": 4.3171,
"step": 238
},
{
"epoch": 0.8,
"learning_rate": 0.00014279999999999997,
"loss": 4.1429,
"step": 239
},
{
"epoch": 0.81,
"learning_rate": 0.0001434,
"loss": 4.2302,
"step": 240
},
{
"epoch": 0.81,
"learning_rate": 0.00014399999999999998,
"loss": 4.3246,
"step": 241
},
{
"epoch": 0.81,
"learning_rate": 0.0001446,
"loss": 4.3286,
"step": 242
},
{
"epoch": 0.82,
"learning_rate": 0.00014519999999999998,
"loss": 4.1907,
"step": 243
},
{
"epoch": 0.82,
"learning_rate": 0.0001458,
"loss": 4.224,
"step": 244
},
{
"epoch": 0.82,
"learning_rate": 0.00014639999999999998,
"loss": 4.2403,
"step": 245
},
{
"epoch": 0.83,
"learning_rate": 0.000147,
"loss": 4.3453,
"step": 246
},
{
"epoch": 0.83,
"learning_rate": 0.00014759999999999998,
"loss": 4.3658,
"step": 247
},
{
"epoch": 0.83,
"learning_rate": 0.0001482,
"loss": 4.2811,
"step": 248
},
{
"epoch": 0.84,
"learning_rate": 0.00014879999999999998,
"loss": 4.411,
"step": 249
},
{
"epoch": 0.84,
"learning_rate": 0.0001494,
"loss": 4.2885,
"step": 250
},
{
"epoch": 0.84,
"learning_rate": 0.00015,
"loss": 4.3184,
"step": 251
},
{
"epoch": 0.85,
"learning_rate": 0.00015059999999999997,
"loss": 4.227,
"step": 252
},
{
"epoch": 0.85,
"learning_rate": 0.0001512,
"loss": 4.1634,
"step": 253
},
{
"epoch": 0.85,
"learning_rate": 0.00015179999999999998,
"loss": 4.1924,
"step": 254
},
{
"epoch": 0.86,
"learning_rate": 0.0001524,
"loss": 4.1476,
"step": 255
},
{
"epoch": 0.86,
"learning_rate": 0.00015299999999999998,
"loss": 4.1701,
"step": 256
},
{
"epoch": 0.86,
"learning_rate": 0.0001536,
"loss": 4.3748,
"step": 257
},
{
"epoch": 0.87,
"learning_rate": 0.00015419999999999998,
"loss": 4.1509,
"step": 258
},
{
"epoch": 0.87,
"learning_rate": 0.0001548,
"loss": 4.164,
"step": 259
},
{
"epoch": 0.87,
"learning_rate": 0.00015539999999999998,
"loss": 4.1074,
"step": 260
},
{
"epoch": 0.88,
"learning_rate": 0.000156,
"loss": 4.2334,
"step": 261
},
{
"epoch": 0.88,
"learning_rate": 0.00015659999999999998,
"loss": 4.2673,
"step": 262
},
{
"epoch": 0.88,
"learning_rate": 0.0001572,
"loss": 4.1299,
"step": 263
},
{
"epoch": 0.89,
"learning_rate": 0.0001578,
"loss": 4.1901,
"step": 264
},
{
"epoch": 0.89,
"learning_rate": 0.0001584,
"loss": 4.1528,
"step": 265
},
{
"epoch": 0.89,
"learning_rate": 0.000159,
"loss": 4.3665,
"step": 266
},
{
"epoch": 0.9,
"learning_rate": 0.0001596,
"loss": 4.175,
"step": 267
},
{
"epoch": 0.9,
"learning_rate": 0.0001602,
"loss": 4.2186,
"step": 268
},
{
"epoch": 0.9,
"learning_rate": 0.0001608,
"loss": 4.0586,
"step": 269
},
{
"epoch": 0.91,
"learning_rate": 0.0001614,
"loss": 4.2644,
"step": 270
},
{
"epoch": 0.91,
"learning_rate": 0.000162,
"loss": 4.1701,
"step": 271
},
{
"epoch": 0.91,
"learning_rate": 0.0001626,
"loss": 4.0608,
"step": 272
},
{
"epoch": 0.92,
"learning_rate": 0.0001632,
"loss": 4.1655,
"step": 273
},
{
"epoch": 0.92,
"learning_rate": 0.0001638,
"loss": 4.1351,
"step": 274
},
{
"epoch": 0.92,
"learning_rate": 0.0001644,
"loss": 4.2868,
"step": 275
},
{
"epoch": 0.93,
"learning_rate": 0.000165,
"loss": 4.2033,
"step": 276
},
{
"epoch": 0.93,
"learning_rate": 0.0001656,
"loss": 4.1803,
"step": 277
},
{
"epoch": 0.93,
"learning_rate": 0.0001662,
"loss": 4.1039,
"step": 278
},
{
"epoch": 0.94,
"learning_rate": 0.0001668,
"loss": 4.1866,
"step": 279
},
{
"epoch": 0.94,
"learning_rate": 0.0001674,
"loss": 4.0807,
"step": 280
},
{
"epoch": 0.94,
"learning_rate": 0.000168,
"loss": 4.2522,
"step": 281
},
{
"epoch": 0.95,
"learning_rate": 0.0001686,
"loss": 4.116,
"step": 282
},
{
"epoch": 0.95,
"learning_rate": 0.00016919999999999997,
"loss": 4.3943,
"step": 283
},
{
"epoch": 0.96,
"learning_rate": 0.00016979999999999998,
"loss": 4.1157,
"step": 284
},
{
"epoch": 0.96,
"learning_rate": 0.00017039999999999997,
"loss": 4.2309,
"step": 285
},
{
"epoch": 0.96,
"learning_rate": 0.00017099999999999998,
"loss": 4.2554,
"step": 286
},
{
"epoch": 0.97,
"learning_rate": 0.00017159999999999997,
"loss": 4.2046,
"step": 287
},
{
"epoch": 0.97,
"learning_rate": 0.00017219999999999998,
"loss": 4.1851,
"step": 288
},
{
"epoch": 0.97,
"learning_rate": 0.00017279999999999997,
"loss": 4.2101,
"step": 289
},
{
"epoch": 0.98,
"learning_rate": 0.00017339999999999996,
"loss": 4.2161,
"step": 290
},
{
"epoch": 0.98,
"learning_rate": 0.00017399999999999997,
"loss": 4.7758,
"step": 291
},
{
"epoch": 0.98,
"learning_rate": 0.00017459999999999996,
"loss": 4.3671,
"step": 292
},
{
"epoch": 0.99,
"learning_rate": 0.00017519999999999998,
"loss": 4.2551,
"step": 293
},
{
"epoch": 0.99,
"learning_rate": 0.00017579999999999996,
"loss": 4.7932,
"step": 294
},
{
"epoch": 0.99,
"learning_rate": 0.00017639999999999998,
"loss": 4.3071,
"step": 295
},
{
"epoch": 1.0,
"learning_rate": 0.00017699999999999997,
"loss": 4.9658,
"step": 296
},
{
"epoch": 1.0,
"learning_rate": 0.00017759999999999998,
"loss": 4.5744,
"step": 297
},
{
"epoch": 1.0,
"step": 297,
"total_flos": 0.0,
"train_loss": 4.267116984935722,
"train_runtime": 4548.8356,
"train_samples_per_second": 6.274,
"train_steps_per_second": 0.065
}
],
"max_steps": 297,
"num_train_epochs": 1,
"total_flos": 0.0,
"trial_name": null,
"trial_params": null
}