akkky02's picture
Upload folder using huggingface_hub
324199d verified
raw
history blame
43 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": 1.72,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.8132,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.9078,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.8052,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.8438,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.825,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.9306,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.974,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.8571,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.8504,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.7575,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.7789,
"step": 13
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.8259,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 1.8565,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 1.6923,
"step": 16
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 1.6105,
"step": 17
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 1.7956,
"step": 18
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 1.8311,
"step": 19
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 1.8265,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 1.6692,
"step": 21
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 1.7219,
"step": 22
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 1.7247,
"step": 23
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 1.7156,
"step": 24
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 1.6544,
"step": 25
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 1.6147,
"step": 26
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 1.6952,
"step": 27
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 1.6363,
"step": 28
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 1.6811,
"step": 29
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 1.6374,
"step": 30
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 1.6458,
"step": 31
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 1.6415,
"step": 32
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 1.594,
"step": 33
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 1.6181,
"step": 34
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 1.5891,
"step": 35
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 1.5248,
"step": 36
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 1.5157,
"step": 37
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 1.5007,
"step": 38
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 1.486,
"step": 39
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 1.4798,
"step": 40
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 1.4713,
"step": 41
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 1.3798,
"step": 42
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 1.436,
"step": 43
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 1.3604,
"step": 44
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 1.3978,
"step": 45
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 1.4132,
"step": 46
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 1.3985,
"step": 47
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 1.3759,
"step": 48
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 1.2946,
"step": 49
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 1.3607,
"step": 50
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 1.2797,
"step": 51
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 1.3139,
"step": 52
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 1.2902,
"step": 53
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 1.2871,
"step": 54
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 1.264,
"step": 55
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 1.2722,
"step": 56
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 1.3353,
"step": 57
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 1.2671,
"step": 58
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 1.2391,
"step": 59
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 1.2411,
"step": 60
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 1.2627,
"step": 61
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 1.2119,
"step": 62
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 1.2003,
"step": 63
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 1.2012,
"step": 64
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 1.2151,
"step": 65
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 1.1827,
"step": 66
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 1.2175,
"step": 67
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 1.2509,
"step": 68
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 1.1838,
"step": 69
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 1.2175,
"step": 70
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 1.1917,
"step": 71
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 1.1257,
"step": 72
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 1.1846,
"step": 73
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 1.1712,
"step": 74
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 1.1666,
"step": 75
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 1.1458,
"step": 76
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 1.1626,
"step": 77
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 1.156,
"step": 78
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 1.1197,
"step": 79
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 1.1276,
"step": 80
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 1.0668,
"step": 81
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 1.1402,
"step": 82
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 1.1018,
"step": 83
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 1.1016,
"step": 84
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 1.0985,
"step": 85
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 1.0898,
"step": 86
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 1.0751,
"step": 87
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 1.1144,
"step": 88
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 1.0894,
"step": 89
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 1.0848,
"step": 90
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.0618,
"step": 91
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.0935,
"step": 92
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.1183,
"step": 93
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.0726,
"step": 94
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.0828,
"step": 95
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 1.0749,
"step": 96
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 1.0831,
"step": 97
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 1.0656,
"step": 98
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 1.1092,
"step": 99
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 1.0781,
"step": 100
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 1.082,
"step": 101
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 1.0296,
"step": 102
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 1.0391,
"step": 103
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 1.0656,
"step": 104
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 1.0757,
"step": 105
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 1.0712,
"step": 106
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 1.065,
"step": 107
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 1.0654,
"step": 108
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 1.0278,
"step": 109
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 1.0234,
"step": 110
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 1.064,
"step": 111
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 1.0628,
"step": 112
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 1.0313,
"step": 113
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 1.0121,
"step": 114
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 0.9732,
"step": 115
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 1.03,
"step": 116
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 0.9903,
"step": 117
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 1.0218,
"step": 118
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 1.0171,
"step": 119
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 1.0498,
"step": 120
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 1.0041,
"step": 121
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.9944,
"step": 122
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 1.0359,
"step": 123
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.9887,
"step": 124
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 1.0103,
"step": 125
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 1.0208,
"step": 126
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.9706,
"step": 127
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.9826,
"step": 128
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.9936,
"step": 129
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.9816,
"step": 130
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 1.0494,
"step": 131
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 1.021,
"step": 132
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.959,
"step": 133
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.9593,
"step": 134
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.9884,
"step": 135
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.9866,
"step": 136
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.9605,
"step": 137
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 1.0139,
"step": 138
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.9807,
"step": 139
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.9864,
"step": 140
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.9898,
"step": 141
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.9964,
"step": 142
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.9494,
"step": 143
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.9476,
"step": 144
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.9698,
"step": 145
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 1.0026,
"step": 146
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.9519,
"step": 147
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 1.0075,
"step": 148
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.948,
"step": 149
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.9678,
"step": 150
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.9455,
"step": 151
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.9889,
"step": 152
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.9668,
"step": 153
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 1.0025,
"step": 154
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.9583,
"step": 155
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.9594,
"step": 156
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.9207,
"step": 157
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.9512,
"step": 158
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.9698,
"step": 159
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.9463,
"step": 160
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.9696,
"step": 161
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 1.0138,
"step": 162
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.9508,
"step": 163
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.9464,
"step": 164
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.9413,
"step": 165
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.9647,
"step": 166
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.9991,
"step": 167
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.9873,
"step": 168
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.9908,
"step": 169
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.9588,
"step": 170
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.9789,
"step": 171
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.9318,
"step": 172
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.9742,
"step": 173
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.9755,
"step": 174
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.9555,
"step": 175
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.967,
"step": 176
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.9878,
"step": 177
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.981,
"step": 178
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.9537,
"step": 179
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.9734,
"step": 180
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.9147,
"step": 181
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.9557,
"step": 182
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.9834,
"step": 183
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 1.006,
"step": 184
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.9976,
"step": 185
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.966,
"step": 186
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.9583,
"step": 187
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.9589,
"step": 188
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.9837,
"step": 189
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.9886,
"step": 190
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.9406,
"step": 191
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.9663,
"step": 192
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.9797,
"step": 193
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.9844,
"step": 194
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.9703,
"step": 195
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.955,
"step": 196
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.9814,
"step": 197
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.9203,
"step": 198
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.9594,
"step": 199
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.9267,
"step": 200
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.9594,
"step": 201
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.9358,
"step": 202
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.9541,
"step": 203
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.9827,
"step": 204
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.9981,
"step": 205
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.9539,
"step": 206
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.9874,
"step": 207
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.9585,
"step": 208
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.9373,
"step": 209
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.9524,
"step": 210
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.9174,
"step": 211
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.9695,
"step": 212
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.9375,
"step": 213
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 1.0197,
"step": 214
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.9542,
"step": 215
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.9614,
"step": 216
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.9576,
"step": 217
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.9527,
"step": 218
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.918,
"step": 219
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.9453,
"step": 220
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.9785,
"step": 221
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.9577,
"step": 222
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 1.0007,
"step": 223
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.9459,
"step": 224
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.9669,
"step": 225
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.9689,
"step": 226
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.9592,
"step": 227
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.9486,
"step": 228
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.9677,
"step": 229
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.9529,
"step": 230
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.981,
"step": 231
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.9783,
"step": 232
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.9412,
"step": 233
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.9522,
"step": 234
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.9204,
"step": 235
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.9372,
"step": 236
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.964,
"step": 237
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.9739,
"step": 238
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.9569,
"step": 239
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 1.0048,
"step": 240
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.9381,
"step": 241
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.953,
"step": 242
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.9545,
"step": 243
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.9531,
"step": 244
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.9621,
"step": 245
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.9677,
"step": 246
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.9811,
"step": 247
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.9573,
"step": 248
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.9548,
"step": 249
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.895,
"step": 250
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.9589,
"step": 251
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.9616,
"step": 252
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.9606,
"step": 253
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.945,
"step": 254
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.943,
"step": 255
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.9654,
"step": 256
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.9251,
"step": 257
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.9437,
"step": 258
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.956,
"step": 259
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.9104,
"step": 260
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.9372,
"step": 261
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.996,
"step": 262
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.947,
"step": 263
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.9721,
"step": 264
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.9134,
"step": 265
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.9393,
"step": 266
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.9073,
"step": 267
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.9417,
"step": 268
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.9549,
"step": 269
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.9945,
"step": 270
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.9214,
"step": 271
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.921,
"step": 272
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.9234,
"step": 273
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.9595,
"step": 274
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.9574,
"step": 275
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.9495,
"step": 276
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.9171,
"step": 277
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.9634,
"step": 278
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.974,
"step": 279
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.936,
"step": 280
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.9382,
"step": 281
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.9519,
"step": 282
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.9383,
"step": 283
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.9192,
"step": 284
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.9467,
"step": 285
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.9465,
"step": 286
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.9498,
"step": 287
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.974,
"step": 288
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.9318,
"step": 289
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.9411,
"step": 290
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.8889,
"step": 291
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.9287,
"step": 292
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.9357,
"step": 293
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.9194,
"step": 294
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.9503,
"step": 295
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.9251,
"step": 296
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.9559,
"step": 297
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.9412,
"step": 298
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.9656,
"step": 299
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.9595,
"step": 300
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.9348,
"step": 301
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.9277,
"step": 302
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.9549,
"step": 303
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.9279,
"step": 304
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.9341,
"step": 305
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.9653,
"step": 306
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.9369,
"step": 307
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.9655,
"step": 308
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.9618,
"step": 309
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.9524,
"step": 310
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.944,
"step": 311
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.9164,
"step": 312
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.9464,
"step": 313
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.9597,
"step": 314
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.9465,
"step": 315
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.948,
"step": 316
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.9838,
"step": 317
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.943,
"step": 318
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.8999,
"step": 319
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.9026,
"step": 320
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.9629,
"step": 321
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.9688,
"step": 322
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.9711,
"step": 323
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.9277,
"step": 324
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.9543,
"step": 325
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.9424,
"step": 326
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.9546,
"step": 327
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.9285,
"step": 328
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.912,
"step": 329
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.9303,
"step": 330
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.9301,
"step": 331
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.9818,
"step": 332
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.9259,
"step": 333
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.949,
"step": 334
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.9186,
"step": 335
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.9572,
"step": 336
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.9144,
"step": 337
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.9527,
"step": 338
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.9406,
"step": 339
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.9474,
"step": 340
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.9271,
"step": 341
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.9436,
"step": 342
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.9473,
"step": 343
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.9599,
"step": 344
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.9473,
"step": 345
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.9636,
"step": 346
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.9399,
"step": 347
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.9484,
"step": 348
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.9419,
"step": 349
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.9379,
"step": 350
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.9375,
"step": 351
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.9258,
"step": 352
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.9336,
"step": 353
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.9508,
"step": 354
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.9495,
"step": 355
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.9443,
"step": 356
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.9897,
"step": 357
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.9291,
"step": 358
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.9287,
"step": 359
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.9141,
"step": 360
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.9924,
"step": 361
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.9366,
"step": 362
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.9103,
"step": 363
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.9298,
"step": 364
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.9481,
"step": 365
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.9346,
"step": 366
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.9323,
"step": 367
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.9592,
"step": 368
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.9714,
"step": 369
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.9392,
"step": 370
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.9393,
"step": 371
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.9097,
"step": 372
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.9249,
"step": 373
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.9366,
"step": 374
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.9199,
"step": 375
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.9348,
"step": 376
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.9678,
"step": 377
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.9106,
"step": 378
},
{
"epoch": 0.94,
"learning_rate": 0.0003,
"loss": 0.93,
"step": 379
},
{
"epoch": 0.94,
"learning_rate": 0.0003,
"loss": 0.9528,
"step": 380
},
{
"epoch": 0.94,
"learning_rate": 0.0003,
"loss": 0.955,
"step": 381
},
{
"epoch": 0.94,
"learning_rate": 0.0003,
"loss": 0.9556,
"step": 382
},
{
"epoch": 0.95,
"learning_rate": 0.0003,
"loss": 0.9569,
"step": 383
},
{
"epoch": 0.95,
"learning_rate": 0.0003,
"loss": 0.9371,
"step": 384
},
{
"epoch": 0.95,
"learning_rate": 0.0003,
"loss": 0.9371,
"step": 385
},
{
"epoch": 0.95,
"learning_rate": 0.0003,
"loss": 0.9516,
"step": 386
},
{
"epoch": 0.96,
"learning_rate": 0.0003,
"loss": 0.9162,
"step": 387
},
{
"epoch": 0.96,
"learning_rate": 0.0003,
"loss": 0.9035,
"step": 388
},
{
"epoch": 0.96,
"learning_rate": 0.0003,
"loss": 0.9187,
"step": 389
},
{
"epoch": 0.96,
"learning_rate": 0.0003,
"loss": 0.9863,
"step": 390
},
{
"epoch": 0.97,
"learning_rate": 0.0003,
"loss": 0.9371,
"step": 391
},
{
"epoch": 0.97,
"learning_rate": 0.0003,
"loss": 0.955,
"step": 392
},
{
"epoch": 0.97,
"learning_rate": 0.0003,
"loss": 0.9322,
"step": 393
},
{
"epoch": 0.97,
"learning_rate": 0.0003,
"loss": 0.949,
"step": 394
},
{
"epoch": 0.98,
"learning_rate": 0.0003,
"loss": 0.9021,
"step": 395
},
{
"epoch": 0.98,
"learning_rate": 0.0003,
"loss": 0.956,
"step": 396
},
{
"epoch": 0.98,
"learning_rate": 0.0003,
"loss": 0.9445,
"step": 397
},
{
"epoch": 0.98,
"learning_rate": 0.0003,
"loss": 0.9505,
"step": 398
},
{
"epoch": 0.99,
"learning_rate": 0.0003,
"loss": 0.9439,
"step": 399
},
{
"epoch": 0.99,
"learning_rate": 0.0003,
"loss": 0.912,
"step": 400
},
{
"epoch": 0.99,
"learning_rate": 0.0003,
"loss": 0.9265,
"step": 401
},
{
"epoch": 0.99,
"learning_rate": 0.0003,
"loss": 0.9212,
"step": 402
},
{
"epoch": 1.0,
"learning_rate": 0.0003,
"loss": 0.9532,
"step": 403
},
{
"epoch": 1.0,
"learning_rate": 0.0003,
"loss": 0.9261,
"step": 404
},
{
"epoch": 1.0,
"step": 404,
"total_flos": 4.562264684211487e+17,
"train_loss": 1.0707487719188822,
"train_runtime": 21622.6067,
"train_samples_per_second": 2.394,
"train_steps_per_second": 0.019
}
],
"logging_steps": 1,
"max_steps": 404,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"total_flos": 4.562264684211487e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}