akkky02's picture
Upload folder using huggingface_hub
f95a0ef verified
raw
history blame contribute delete
No virus
42.9 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9990726429675425,
"eval_steps": 500,
"global_step": 404,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0003,
"loss": 1.8161,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 0.0003,
"loss": 1.6317,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.6129,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.5679,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.362,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.2853,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.201,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.2034,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.1587,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.1093,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.1136,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.0783,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.0285,
"step": 13
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.045,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 1.034,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 1.013,
"step": 16
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 0.9754,
"step": 17
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 0.9695,
"step": 18
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 0.9904,
"step": 19
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 1.001,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 0.9761,
"step": 21
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 1.0067,
"step": 22
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 1.0043,
"step": 23
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 0.9413,
"step": 24
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 0.9184,
"step": 25
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 0.9195,
"step": 26
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 1.0034,
"step": 27
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 0.9402,
"step": 28
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 0.9435,
"step": 29
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 0.926,
"step": 30
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 0.95,
"step": 31
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 0.9769,
"step": 32
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 0.9486,
"step": 33
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 0.9792,
"step": 34
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 0.9295,
"step": 35
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 0.9626,
"step": 36
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 0.9384,
"step": 37
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 0.9353,
"step": 38
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 0.9399,
"step": 39
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 0.9133,
"step": 40
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 0.9591,
"step": 41
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 0.9347,
"step": 42
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 0.9327,
"step": 43
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 0.9298,
"step": 44
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 0.9145,
"step": 45
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 0.9582,
"step": 46
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 0.9267,
"step": 47
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 0.9291,
"step": 48
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 0.93,
"step": 49
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 0.9611,
"step": 50
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 0.9034,
"step": 51
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 0.9165,
"step": 52
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 0.916,
"step": 53
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 0.9142,
"step": 54
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 0.9333,
"step": 55
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 0.9275,
"step": 56
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 0.9769,
"step": 57
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 0.9139,
"step": 58
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 0.9059,
"step": 59
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 0.9276,
"step": 60
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 0.9222,
"step": 61
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 0.9264,
"step": 62
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 0.9135,
"step": 63
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 0.9217,
"step": 64
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 0.9304,
"step": 65
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 0.9167,
"step": 66
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 0.9308,
"step": 67
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 0.978,
"step": 68
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 0.9013,
"step": 69
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 0.9343,
"step": 70
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 0.937,
"step": 71
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 0.8707,
"step": 72
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 0.9298,
"step": 73
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 0.9293,
"step": 74
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 0.9321,
"step": 75
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 0.9192,
"step": 76
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 0.9288,
"step": 77
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 0.9244,
"step": 78
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 0.9112,
"step": 79
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 0.9097,
"step": 80
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 0.8756,
"step": 81
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 0.9292,
"step": 82
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 0.9191,
"step": 83
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 0.9132,
"step": 84
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 0.9052,
"step": 85
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 0.9292,
"step": 86
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 0.9086,
"step": 87
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 0.9355,
"step": 88
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 0.9233,
"step": 89
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 0.926,
"step": 90
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 0.8995,
"step": 91
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 0.926,
"step": 92
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 0.9479,
"step": 93
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 0.909,
"step": 94
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 0.9087,
"step": 95
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 0.9127,
"step": 96
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 0.921,
"step": 97
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 0.9023,
"step": 98
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 0.945,
"step": 99
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 0.9258,
"step": 100
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 0.9326,
"step": 101
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 0.8745,
"step": 102
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 0.8949,
"step": 103
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 0.9229,
"step": 104
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 0.9099,
"step": 105
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 0.9327,
"step": 106
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 0.9257,
"step": 107
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 0.932,
"step": 108
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 0.9016,
"step": 109
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 0.9054,
"step": 110
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 0.93,
"step": 111
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 0.9393,
"step": 112
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 0.9152,
"step": 113
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 0.89,
"step": 114
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 0.861,
"step": 115
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 0.9126,
"step": 116
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 0.8745,
"step": 117
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 0.9188,
"step": 118
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 0.9108,
"step": 119
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.9271,
"step": 120
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.911,
"step": 121
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.9043,
"step": 122
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.9303,
"step": 123
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.9014,
"step": 124
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.9245,
"step": 125
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.932,
"step": 126
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.8959,
"step": 127
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.9077,
"step": 128
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.905,
"step": 129
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.8965,
"step": 130
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.9647,
"step": 131
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.9436,
"step": 132
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.8752,
"step": 133
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.888,
"step": 134
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.9217,
"step": 135
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.9091,
"step": 136
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.8898,
"step": 137
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.9453,
"step": 138
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.9148,
"step": 139
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.9161,
"step": 140
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.9205,
"step": 141
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.931,
"step": 142
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.8875,
"step": 143
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.8822,
"step": 144
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.9075,
"step": 145
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.9376,
"step": 146
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.8904,
"step": 147
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.9457,
"step": 148
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.8855,
"step": 149
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.9068,
"step": 150
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.8868,
"step": 151
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.9234,
"step": 152
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.9014,
"step": 153
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.938,
"step": 154
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.8992,
"step": 155
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.9106,
"step": 156
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.8678,
"step": 157
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.8879,
"step": 158
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.9149,
"step": 159
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.8919,
"step": 160
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.9104,
"step": 161
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.9576,
"step": 162
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.8911,
"step": 163
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.8898,
"step": 164
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.8829,
"step": 165
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.9111,
"step": 166
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.9391,
"step": 167
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.9343,
"step": 168
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.9298,
"step": 169
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.9041,
"step": 170
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.926,
"step": 171
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.8824,
"step": 172
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.9217,
"step": 173
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.9171,
"step": 174
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.9041,
"step": 175
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.9118,
"step": 176
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.9357,
"step": 177
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.9343,
"step": 178
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.9018,
"step": 179
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.9128,
"step": 180
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.8631,
"step": 181
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.8982,
"step": 182
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.9262,
"step": 183
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.9452,
"step": 184
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.9434,
"step": 185
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.9192,
"step": 186
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.9068,
"step": 187
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.9092,
"step": 188
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.9346,
"step": 189
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.9375,
"step": 190
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.8884,
"step": 191
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.9127,
"step": 192
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.9275,
"step": 193
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.9361,
"step": 194
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.9182,
"step": 195
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.9007,
"step": 196
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.9294,
"step": 197
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.8693,
"step": 198
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.9096,
"step": 199
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.8738,
"step": 200
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.9004,
"step": 201
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.8822,
"step": 202
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.9085,
"step": 203
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.9348,
"step": 204
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.9393,
"step": 205
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.906,
"step": 206
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.9388,
"step": 207
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.9018,
"step": 208
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.8881,
"step": 209
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.8999,
"step": 210
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.8647,
"step": 211
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.918,
"step": 212
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.8958,
"step": 213
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.9586,
"step": 214
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.9017,
"step": 215
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.9139,
"step": 216
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.8994,
"step": 217
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.8979,
"step": 218
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.8756,
"step": 219
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.8903,
"step": 220
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.9368,
"step": 221
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.9054,
"step": 222
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.9501,
"step": 223
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.8966,
"step": 224
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.9123,
"step": 225
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.9053,
"step": 226
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.9153,
"step": 227
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.8943,
"step": 228
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.9195,
"step": 229
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.9013,
"step": 230
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.9236,
"step": 231
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.9223,
"step": 232
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.8959,
"step": 233
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.9025,
"step": 234
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.8764,
"step": 235
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.8937,
"step": 236
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.916,
"step": 237
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.9291,
"step": 238
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.9104,
"step": 239
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.9552,
"step": 240
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.8864,
"step": 241
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.9015,
"step": 242
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.9051,
"step": 243
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.8966,
"step": 244
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.9091,
"step": 245
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.9157,
"step": 246
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.927,
"step": 247
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.9016,
"step": 248
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.9027,
"step": 249
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.8417,
"step": 250
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.9147,
"step": 251
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.9153,
"step": 252
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.9145,
"step": 253
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.9025,
"step": 254
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.9036,
"step": 255
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.9177,
"step": 256
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.8781,
"step": 257
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.8934,
"step": 258
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.9098,
"step": 259
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.8631,
"step": 260
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.8852,
"step": 261
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.9475,
"step": 262
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.8961,
"step": 263
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.9209,
"step": 264
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.863,
"step": 265
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.8938,
"step": 266
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.8648,
"step": 267
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.8957,
"step": 268
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.9136,
"step": 269
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.9399,
"step": 270
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.8741,
"step": 271
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.8775,
"step": 272
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.873,
"step": 273
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.9135,
"step": 274
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.9046,
"step": 275
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.9017,
"step": 276
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.874,
"step": 277
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.9144,
"step": 278
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.9263,
"step": 279
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.8943,
"step": 280
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.8921,
"step": 281
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.9045,
"step": 282
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.893,
"step": 283
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.8765,
"step": 284
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.8958,
"step": 285
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.8968,
"step": 286
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.8992,
"step": 287
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.9237,
"step": 288
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.8795,
"step": 289
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.8946,
"step": 290
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.8475,
"step": 291
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.8839,
"step": 292
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.895,
"step": 293
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.8795,
"step": 294
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.9038,
"step": 295
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.8781,
"step": 296
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.9091,
"step": 297
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.8835,
"step": 298
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.9179,
"step": 299
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.911,
"step": 300
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.8919,
"step": 301
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.8766,
"step": 302
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.9094,
"step": 303
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.8834,
"step": 304
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.8922,
"step": 305
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.9125,
"step": 306
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.8945,
"step": 307
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.919,
"step": 308
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.9205,
"step": 309
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.91,
"step": 310
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.8947,
"step": 311
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.8668,
"step": 312
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.901,
"step": 313
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.9118,
"step": 314
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.8964,
"step": 315
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.9059,
"step": 316
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.9365,
"step": 317
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.8955,
"step": 318
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.8586,
"step": 319
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.8609,
"step": 320
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.9143,
"step": 321
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.9209,
"step": 322
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.9334,
"step": 323
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.8891,
"step": 324
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.9026,
"step": 325
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.8963,
"step": 326
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.9135,
"step": 327
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.887,
"step": 328
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.8714,
"step": 329
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.8856,
"step": 330
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.8823,
"step": 331
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.9338,
"step": 332
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.8812,
"step": 333
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.9086,
"step": 334
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.8788,
"step": 335
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.9138,
"step": 336
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.8709,
"step": 337
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.905,
"step": 338
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.8954,
"step": 339
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.9098,
"step": 340
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.8843,
"step": 341
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.8991,
"step": 342
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.9067,
"step": 343
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.915,
"step": 344
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.903,
"step": 345
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.9172,
"step": 346
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.8973,
"step": 347
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.9014,
"step": 348
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.8992,
"step": 349
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.8963,
"step": 350
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.8911,
"step": 351
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.8751,
"step": 352
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.8941,
"step": 353
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.9053,
"step": 354
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.9126,
"step": 355
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.9006,
"step": 356
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.9449,
"step": 357
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.886,
"step": 358
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.8843,
"step": 359
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.8725,
"step": 360
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.9445,
"step": 361
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.8902,
"step": 362
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.866,
"step": 363
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.8889,
"step": 364
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.9055,
"step": 365
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.8942,
"step": 366
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.8893,
"step": 367
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.9144,
"step": 368
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.9304,
"step": 369
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.8981,
"step": 370
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.8963,
"step": 371
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.8662,
"step": 372
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.8823,
"step": 373
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.8928,
"step": 374
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.8789,
"step": 375
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.8892,
"step": 376
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.9237,
"step": 377
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.8653,
"step": 378
},
{
"epoch": 0.94,
"learning_rate": 0.0003,
"loss": 0.8914,
"step": 379
},
{
"epoch": 0.94,
"learning_rate": 0.0003,
"loss": 0.906,
"step": 380
},
{
"epoch": 0.94,
"learning_rate": 0.0003,
"loss": 0.9069,
"step": 381
},
{
"epoch": 0.94,
"learning_rate": 0.0003,
"loss": 0.9076,
"step": 382
},
{
"epoch": 0.95,
"learning_rate": 0.0003,
"loss": 0.9061,
"step": 383
},
{
"epoch": 0.95,
"learning_rate": 0.0003,
"loss": 0.8983,
"step": 384
},
{
"epoch": 0.95,
"learning_rate": 0.0003,
"loss": 0.8933,
"step": 385
},
{
"epoch": 0.95,
"learning_rate": 0.0003,
"loss": 0.909,
"step": 386
},
{
"epoch": 0.96,
"learning_rate": 0.0003,
"loss": 0.874,
"step": 387
},
{
"epoch": 0.96,
"learning_rate": 0.0003,
"loss": 0.8617,
"step": 388
},
{
"epoch": 0.96,
"learning_rate": 0.0003,
"loss": 0.8736,
"step": 389
},
{
"epoch": 0.96,
"learning_rate": 0.0003,
"loss": 0.939,
"step": 390
},
{
"epoch": 0.97,
"learning_rate": 0.0003,
"loss": 0.8937,
"step": 391
},
{
"epoch": 0.97,
"learning_rate": 0.0003,
"loss": 0.9151,
"step": 392
},
{
"epoch": 0.97,
"learning_rate": 0.0003,
"loss": 0.8863,
"step": 393
},
{
"epoch": 0.97,
"learning_rate": 0.0003,
"loss": 0.9079,
"step": 394
},
{
"epoch": 0.98,
"learning_rate": 0.0003,
"loss": 0.8665,
"step": 395
},
{
"epoch": 0.98,
"learning_rate": 0.0003,
"loss": 0.9081,
"step": 396
},
{
"epoch": 0.98,
"learning_rate": 0.0003,
"loss": 0.8966,
"step": 397
},
{
"epoch": 0.98,
"learning_rate": 0.0003,
"loss": 0.9048,
"step": 398
},
{
"epoch": 0.99,
"learning_rate": 0.0003,
"loss": 0.9024,
"step": 399
},
{
"epoch": 0.99,
"learning_rate": 0.0003,
"loss": 0.8764,
"step": 400
},
{
"epoch": 0.99,
"learning_rate": 0.0003,
"loss": 0.8854,
"step": 401
},
{
"epoch": 0.99,
"learning_rate": 0.0003,
"loss": 0.882,
"step": 402
},
{
"epoch": 1.0,
"learning_rate": 0.0003,
"loss": 0.9126,
"step": 403
},
{
"epoch": 1.0,
"learning_rate": 0.0003,
"loss": 0.8861,
"step": 404
},
{
"epoch": 1.0,
"step": 404,
"total_flos": 4.585316415920947e+17,
"train_loss": 0.9242179525075572,
"train_runtime": 18375.2967,
"train_samples_per_second": 2.817,
"train_steps_per_second": 0.022
}
],
"logging_steps": 1,
"max_steps": 404,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"total_flos": 4.585316415920947e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}