akkky02's picture
Upload folder using huggingface_hub
67311e7 verified
raw
history blame
No virus
39.7 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9273570324574961,
"eval_steps": 500,
"global_step": 375,
"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": 1.8146,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 0.0003,
"loss": 1.719,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.8121,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.907,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.8035,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 0.0003,
"loss": 1.8421,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.8232,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.9286,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.9718,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 0.0003,
"loss": 1.8541,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.848,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.7545,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.7757,
"step": 13
},
{
"epoch": 0.03,
"learning_rate": 0.0003,
"loss": 1.8229,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 1.8526,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 1.6885,
"step": 16
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 1.6073,
"step": 17
},
{
"epoch": 0.04,
"learning_rate": 0.0003,
"loss": 1.7907,
"step": 18
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 1.827,
"step": 19
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 1.8215,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 1.6652,
"step": 21
},
{
"epoch": 0.05,
"learning_rate": 0.0003,
"loss": 1.7179,
"step": 22
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 1.7204,
"step": 23
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 1.7107,
"step": 24
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 1.6492,
"step": 25
},
{
"epoch": 0.06,
"learning_rate": 0.0003,
"loss": 1.6104,
"step": 26
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 1.6907,
"step": 27
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 1.6314,
"step": 28
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 1.6743,
"step": 29
},
{
"epoch": 0.07,
"learning_rate": 0.0003,
"loss": 1.6317,
"step": 30
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 1.6398,
"step": 31
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 1.6353,
"step": 32
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 1.5887,
"step": 33
},
{
"epoch": 0.08,
"learning_rate": 0.0003,
"loss": 1.6109,
"step": 34
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 1.5822,
"step": 35
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 1.5185,
"step": 36
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 1.5073,
"step": 37
},
{
"epoch": 0.09,
"learning_rate": 0.0003,
"loss": 1.4929,
"step": 38
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 1.4762,
"step": 39
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 1.4694,
"step": 40
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 1.4618,
"step": 41
},
{
"epoch": 0.1,
"learning_rate": 0.0003,
"loss": 1.3723,
"step": 42
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 1.4274,
"step": 43
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 1.3541,
"step": 44
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 1.392,
"step": 45
},
{
"epoch": 0.11,
"learning_rate": 0.0003,
"loss": 1.4076,
"step": 46
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 1.3934,
"step": 47
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 1.3725,
"step": 48
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 1.2922,
"step": 49
},
{
"epoch": 0.12,
"learning_rate": 0.0003,
"loss": 1.3569,
"step": 50
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 1.2762,
"step": 51
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 1.3087,
"step": 52
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 1.2841,
"step": 53
},
{
"epoch": 0.13,
"learning_rate": 0.0003,
"loss": 1.2812,
"step": 54
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 1.258,
"step": 55
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 1.266,
"step": 56
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 1.3278,
"step": 57
},
{
"epoch": 0.14,
"learning_rate": 0.0003,
"loss": 1.2598,
"step": 58
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 1.2328,
"step": 59
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 1.2364,
"step": 60
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 1.257,
"step": 61
},
{
"epoch": 0.15,
"learning_rate": 0.0003,
"loss": 1.2075,
"step": 62
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 1.1957,
"step": 63
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 1.1966,
"step": 64
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 1.211,
"step": 65
},
{
"epoch": 0.16,
"learning_rate": 0.0003,
"loss": 1.1787,
"step": 66
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 1.2128,
"step": 67
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 1.247,
"step": 68
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 1.1791,
"step": 69
},
{
"epoch": 0.17,
"learning_rate": 0.0003,
"loss": 1.2132,
"step": 70
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 1.1875,
"step": 71
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 1.1206,
"step": 72
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 1.1788,
"step": 73
},
{
"epoch": 0.18,
"learning_rate": 0.0003,
"loss": 1.1645,
"step": 74
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 1.1594,
"step": 75
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 1.1386,
"step": 76
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 1.1547,
"step": 77
},
{
"epoch": 0.19,
"learning_rate": 0.0003,
"loss": 1.1461,
"step": 78
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 1.1101,
"step": 79
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 1.1175,
"step": 80
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 1.0575,
"step": 81
},
{
"epoch": 0.2,
"learning_rate": 0.0003,
"loss": 1.131,
"step": 82
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 1.0944,
"step": 83
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 1.0955,
"step": 84
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 1.0931,
"step": 85
},
{
"epoch": 0.21,
"learning_rate": 0.0003,
"loss": 1.0859,
"step": 86
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 1.0716,
"step": 87
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 1.1111,
"step": 88
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 1.0859,
"step": 89
},
{
"epoch": 0.22,
"learning_rate": 0.0003,
"loss": 1.0816,
"step": 90
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.0579,
"step": 91
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.091,
"step": 92
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.1155,
"step": 93
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.069,
"step": 94
},
{
"epoch": 0.23,
"learning_rate": 0.0003,
"loss": 1.0793,
"step": 95
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 1.0728,
"step": 96
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 1.0802,
"step": 97
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 1.0615,
"step": 98
},
{
"epoch": 0.24,
"learning_rate": 0.0003,
"loss": 1.1055,
"step": 99
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 1.0742,
"step": 100
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 1.0771,
"step": 101
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 1.0248,
"step": 102
},
{
"epoch": 0.25,
"learning_rate": 0.0003,
"loss": 1.0341,
"step": 103
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 1.0612,
"step": 104
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 1.0678,
"step": 105
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 1.0624,
"step": 106
},
{
"epoch": 0.26,
"learning_rate": 0.0003,
"loss": 1.0544,
"step": 107
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 1.0588,
"step": 108
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 1.0198,
"step": 109
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 1.0159,
"step": 110
},
{
"epoch": 0.27,
"learning_rate": 0.0003,
"loss": 1.0584,
"step": 111
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 1.0595,
"step": 112
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 1.0274,
"step": 113
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 1.0058,
"step": 114
},
{
"epoch": 0.28,
"learning_rate": 0.0003,
"loss": 0.9667,
"step": 115
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 1.0237,
"step": 116
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 0.9844,
"step": 117
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 1.0164,
"step": 118
},
{
"epoch": 0.29,
"learning_rate": 0.0003,
"loss": 1.0122,
"step": 119
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 1.0444,
"step": 120
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.9999,
"step": 121
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 0.9905,
"step": 122
},
{
"epoch": 0.3,
"learning_rate": 0.0003,
"loss": 1.0312,
"step": 123
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.9849,
"step": 124
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 1.0065,
"step": 125
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 1.0168,
"step": 126
},
{
"epoch": 0.31,
"learning_rate": 0.0003,
"loss": 0.9674,
"step": 127
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.9786,
"step": 128
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.9901,
"step": 129
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 0.9782,
"step": 130
},
{
"epoch": 0.32,
"learning_rate": 0.0003,
"loss": 1.0455,
"step": 131
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 1.0182,
"step": 132
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.9556,
"step": 133
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.9567,
"step": 134
},
{
"epoch": 0.33,
"learning_rate": 0.0003,
"loss": 0.9853,
"step": 135
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.9841,
"step": 136
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.9579,
"step": 137
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 1.0118,
"step": 138
},
{
"epoch": 0.34,
"learning_rate": 0.0003,
"loss": 0.9789,
"step": 139
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.9843,
"step": 140
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.9877,
"step": 141
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.9949,
"step": 142
},
{
"epoch": 0.35,
"learning_rate": 0.0003,
"loss": 0.9482,
"step": 143
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.9455,
"step": 144
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.9686,
"step": 145
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 1.0011,
"step": 146
},
{
"epoch": 0.36,
"learning_rate": 0.0003,
"loss": 0.9502,
"step": 147
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 1.0058,
"step": 148
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.9465,
"step": 149
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.966,
"step": 150
},
{
"epoch": 0.37,
"learning_rate": 0.0003,
"loss": 0.9448,
"step": 151
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.9883,
"step": 152
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.9655,
"step": 153
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 1.001,
"step": 154
},
{
"epoch": 0.38,
"learning_rate": 0.0003,
"loss": 0.9571,
"step": 155
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.9583,
"step": 156
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.9188,
"step": 157
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.9496,
"step": 158
},
{
"epoch": 0.39,
"learning_rate": 0.0003,
"loss": 0.9686,
"step": 159
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.9446,
"step": 160
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.9681,
"step": 161
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 1.0122,
"step": 162
},
{
"epoch": 0.4,
"learning_rate": 0.0003,
"loss": 0.95,
"step": 163
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.9449,
"step": 164
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.9404,
"step": 165
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.9636,
"step": 166
},
{
"epoch": 0.41,
"learning_rate": 0.0003,
"loss": 0.9979,
"step": 167
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.9856,
"step": 168
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.9899,
"step": 169
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.9573,
"step": 170
},
{
"epoch": 0.42,
"learning_rate": 0.0003,
"loss": 0.9773,
"step": 171
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.9303,
"step": 172
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.9733,
"step": 173
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.9741,
"step": 174
},
{
"epoch": 0.43,
"learning_rate": 0.0003,
"loss": 0.9544,
"step": 175
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.966,
"step": 176
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.9867,
"step": 177
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.9792,
"step": 178
},
{
"epoch": 0.44,
"learning_rate": 0.0003,
"loss": 0.9525,
"step": 179
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.9725,
"step": 180
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.9141,
"step": 181
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.9548,
"step": 182
},
{
"epoch": 0.45,
"learning_rate": 0.0003,
"loss": 0.9821,
"step": 183
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 1.0047,
"step": 184
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.9961,
"step": 185
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.965,
"step": 186
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.9573,
"step": 187
},
{
"epoch": 0.46,
"learning_rate": 0.0003,
"loss": 0.9579,
"step": 188
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.9826,
"step": 189
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.9877,
"step": 190
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.9396,
"step": 191
},
{
"epoch": 0.47,
"learning_rate": 0.0003,
"loss": 0.9648,
"step": 192
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.9787,
"step": 193
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.9832,
"step": 194
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.9692,
"step": 195
},
{
"epoch": 0.48,
"learning_rate": 0.0003,
"loss": 0.9537,
"step": 196
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.9805,
"step": 197
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.9194,
"step": 198
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.9582,
"step": 199
},
{
"epoch": 0.49,
"learning_rate": 0.0003,
"loss": 0.9254,
"step": 200
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.9589,
"step": 201
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.9354,
"step": 202
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.9529,
"step": 203
},
{
"epoch": 0.5,
"learning_rate": 0.0003,
"loss": 0.9816,
"step": 204
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.997,
"step": 205
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.9521,
"step": 206
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.9863,
"step": 207
},
{
"epoch": 0.51,
"learning_rate": 0.0003,
"loss": 0.957,
"step": 208
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.9358,
"step": 209
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.9512,
"step": 210
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.9165,
"step": 211
},
{
"epoch": 0.52,
"learning_rate": 0.0003,
"loss": 0.969,
"step": 212
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.937,
"step": 213
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 1.0185,
"step": 214
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.9527,
"step": 215
},
{
"epoch": 0.53,
"learning_rate": 0.0003,
"loss": 0.96,
"step": 216
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.9566,
"step": 217
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.9517,
"step": 218
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.9168,
"step": 219
},
{
"epoch": 0.54,
"learning_rate": 0.0003,
"loss": 0.9442,
"step": 220
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.9774,
"step": 221
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.9566,
"step": 222
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.9992,
"step": 223
},
{
"epoch": 0.55,
"learning_rate": 0.0003,
"loss": 0.9444,
"step": 224
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.9657,
"step": 225
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.9675,
"step": 226
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.9576,
"step": 227
},
{
"epoch": 0.56,
"learning_rate": 0.0003,
"loss": 0.9473,
"step": 228
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.9662,
"step": 229
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.9519,
"step": 230
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.9801,
"step": 231
},
{
"epoch": 0.57,
"learning_rate": 0.0003,
"loss": 0.9775,
"step": 232
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.9406,
"step": 233
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.9517,
"step": 234
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.9188,
"step": 235
},
{
"epoch": 0.58,
"learning_rate": 0.0003,
"loss": 0.9358,
"step": 236
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.9627,
"step": 237
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.9731,
"step": 238
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 0.9555,
"step": 239
},
{
"epoch": 0.59,
"learning_rate": 0.0003,
"loss": 1.0039,
"step": 240
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.937,
"step": 241
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.9521,
"step": 242
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.9531,
"step": 243
},
{
"epoch": 0.6,
"learning_rate": 0.0003,
"loss": 0.9517,
"step": 244
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.9605,
"step": 245
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.9669,
"step": 246
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.9798,
"step": 247
},
{
"epoch": 0.61,
"learning_rate": 0.0003,
"loss": 0.9566,
"step": 248
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.9542,
"step": 249
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.8942,
"step": 250
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.9583,
"step": 251
},
{
"epoch": 0.62,
"learning_rate": 0.0003,
"loss": 0.9605,
"step": 252
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.9599,
"step": 253
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.9436,
"step": 254
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.9426,
"step": 255
},
{
"epoch": 0.63,
"learning_rate": 0.0003,
"loss": 0.9646,
"step": 256
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.9237,
"step": 257
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.9427,
"step": 258
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.9554,
"step": 259
},
{
"epoch": 0.64,
"learning_rate": 0.0003,
"loss": 0.9093,
"step": 260
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.936,
"step": 261
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.995,
"step": 262
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.9461,
"step": 263
},
{
"epoch": 0.65,
"learning_rate": 0.0003,
"loss": 0.9712,
"step": 264
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.9124,
"step": 265
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.9385,
"step": 266
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.906,
"step": 267
},
{
"epoch": 0.66,
"learning_rate": 0.0003,
"loss": 0.9401,
"step": 268
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.954,
"step": 269
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.9932,
"step": 270
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.9201,
"step": 271
},
{
"epoch": 0.67,
"learning_rate": 0.0003,
"loss": 0.9199,
"step": 272
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.9223,
"step": 273
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.9582,
"step": 274
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.9565,
"step": 275
},
{
"epoch": 0.68,
"learning_rate": 0.0003,
"loss": 0.9486,
"step": 276
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.9167,
"step": 277
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.9628,
"step": 278
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.9725,
"step": 279
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.9354,
"step": 280
},
{
"epoch": 0.69,
"learning_rate": 0.0003,
"loss": 0.9377,
"step": 281
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.9508,
"step": 282
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.9369,
"step": 283
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.9179,
"step": 284
},
{
"epoch": 0.7,
"learning_rate": 0.0003,
"loss": 0.9455,
"step": 285
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.9455,
"step": 286
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.9493,
"step": 287
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.9732,
"step": 288
},
{
"epoch": 0.71,
"learning_rate": 0.0003,
"loss": 0.9304,
"step": 289
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.9401,
"step": 290
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.8876,
"step": 291
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.9278,
"step": 292
},
{
"epoch": 0.72,
"learning_rate": 0.0003,
"loss": 0.9343,
"step": 293
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.9192,
"step": 294
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.9494,
"step": 295
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.9241,
"step": 296
},
{
"epoch": 0.73,
"learning_rate": 0.0003,
"loss": 0.9554,
"step": 297
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.9397,
"step": 298
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.9651,
"step": 299
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.9587,
"step": 300
},
{
"epoch": 0.74,
"learning_rate": 0.0003,
"loss": 0.9342,
"step": 301
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.9268,
"step": 302
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.9537,
"step": 303
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.9266,
"step": 304
},
{
"epoch": 0.75,
"learning_rate": 0.0003,
"loss": 0.9332,
"step": 305
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.9641,
"step": 306
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.9361,
"step": 307
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.9645,
"step": 308
},
{
"epoch": 0.76,
"learning_rate": 0.0003,
"loss": 0.9605,
"step": 309
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.9512,
"step": 310
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.9436,
"step": 311
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.9155,
"step": 312
},
{
"epoch": 0.77,
"learning_rate": 0.0003,
"loss": 0.9457,
"step": 313
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.9584,
"step": 314
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.9449,
"step": 315
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.947,
"step": 316
},
{
"epoch": 0.78,
"learning_rate": 0.0003,
"loss": 0.9826,
"step": 317
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.9416,
"step": 318
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.8989,
"step": 319
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.9016,
"step": 320
},
{
"epoch": 0.79,
"learning_rate": 0.0003,
"loss": 0.9614,
"step": 321
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.9672,
"step": 322
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.9702,
"step": 323
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.9265,
"step": 324
},
{
"epoch": 0.8,
"learning_rate": 0.0003,
"loss": 0.9535,
"step": 325
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.9413,
"step": 326
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.9534,
"step": 327
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.9271,
"step": 328
},
{
"epoch": 0.81,
"learning_rate": 0.0003,
"loss": 0.911,
"step": 329
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.929,
"step": 330
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.929,
"step": 331
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.9812,
"step": 332
},
{
"epoch": 0.82,
"learning_rate": 0.0003,
"loss": 0.9251,
"step": 333
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.9482,
"step": 334
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.9177,
"step": 335
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.9559,
"step": 336
},
{
"epoch": 0.83,
"learning_rate": 0.0003,
"loss": 0.9133,
"step": 337
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.9514,
"step": 338
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.9396,
"step": 339
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.9466,
"step": 340
},
{
"epoch": 0.84,
"learning_rate": 0.0003,
"loss": 0.926,
"step": 341
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.9421,
"step": 342
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.9463,
"step": 343
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.9585,
"step": 344
},
{
"epoch": 0.85,
"learning_rate": 0.0003,
"loss": 0.946,
"step": 345
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.9623,
"step": 346
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.9395,
"step": 347
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.9475,
"step": 348
},
{
"epoch": 0.86,
"learning_rate": 0.0003,
"loss": 0.9406,
"step": 349
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.937,
"step": 350
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.9374,
"step": 351
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.9246,
"step": 352
},
{
"epoch": 0.87,
"learning_rate": 0.0003,
"loss": 0.9326,
"step": 353
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.9493,
"step": 354
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.9483,
"step": 355
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.9436,
"step": 356
},
{
"epoch": 0.88,
"learning_rate": 0.0003,
"loss": 0.9888,
"step": 357
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.9281,
"step": 358
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.9276,
"step": 359
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.9129,
"step": 360
},
{
"epoch": 0.89,
"learning_rate": 0.0003,
"loss": 0.9911,
"step": 361
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.9352,
"step": 362
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.9098,
"step": 363
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.9292,
"step": 364
},
{
"epoch": 0.9,
"learning_rate": 0.0003,
"loss": 0.9467,
"step": 365
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.934,
"step": 366
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.9312,
"step": 367
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.9582,
"step": 368
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.9701,
"step": 369
},
{
"epoch": 0.91,
"learning_rate": 0.0003,
"loss": 0.9384,
"step": 370
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.9382,
"step": 371
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.9086,
"step": 372
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.9235,
"step": 373
},
{
"epoch": 0.92,
"learning_rate": 0.0003,
"loss": 0.9355,
"step": 374
},
{
"epoch": 0.93,
"learning_rate": 0.0003,
"loss": 0.9191,
"step": 375
}
],
"logging_steps": 1,
"max_steps": 404,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"total_flos": 4.2184716376979866e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}