yi-6b-xllm-lora / last-checkpoint /trainer_state.json
nutorbit's picture
Training in progress, step 500, checkpoint
73fae74
raw
history blame contribute delete
No virus
60.2 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.09452689290103035,
"eval_steps": 1000,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4e-05,
"loss": 2.3108,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 8e-05,
"loss": 2.3414,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 8e-05,
"loss": 2.3482,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 8e-05,
"loss": 2.2906,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 0.00012,
"loss": 2.1098,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 0.00012,
"loss": 2.3712,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 0.00016,
"loss": 2.2602,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 0.00016,
"loss": 2.2053,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 0.00016,
"loss": 2.079,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 0.00016,
"loss": 2.3056,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1275,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 0.0001995967741935484,
"loss": 2.2192,
"step": 12
},
{
"epoch": 0.0,
"learning_rate": 0.0001991935483870968,
"loss": 2.11,
"step": 13
},
{
"epoch": 0.0,
"learning_rate": 0.0001991935483870968,
"loss": 2.0904,
"step": 14
},
{
"epoch": 0.0,
"learning_rate": 0.00019879032258064515,
"loss": 1.9425,
"step": 15
},
{
"epoch": 0.0,
"learning_rate": 0.00019838709677419357,
"loss": 1.8216,
"step": 16
},
{
"epoch": 0.0,
"learning_rate": 0.00019798387096774193,
"loss": 1.8774,
"step": 17
},
{
"epoch": 0.0,
"learning_rate": 0.00019758064516129035,
"loss": 2.0245,
"step": 18
},
{
"epoch": 0.0,
"learning_rate": 0.00019758064516129035,
"loss": 2.0149,
"step": 19
},
{
"epoch": 0.0,
"learning_rate": 0.0001971774193548387,
"loss": 2.0511,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 0.0001967741935483871,
"loss": 1.748,
"step": 21
},
{
"epoch": 0.0,
"learning_rate": 0.0001963709677419355,
"loss": 1.749,
"step": 22
},
{
"epoch": 0.0,
"learning_rate": 0.00019596774193548388,
"loss": 2.074,
"step": 23
},
{
"epoch": 0.0,
"learning_rate": 0.00019556451612903227,
"loss": 1.9857,
"step": 24
},
{
"epoch": 0.0,
"learning_rate": 0.00019556451612903227,
"loss": 1.8599,
"step": 25
},
{
"epoch": 0.0,
"learning_rate": 0.00019516129032258066,
"loss": 1.8882,
"step": 26
},
{
"epoch": 0.01,
"learning_rate": 0.00019475806451612905,
"loss": 1.7498,
"step": 27
},
{
"epoch": 0.01,
"learning_rate": 0.00019435483870967744,
"loss": 1.6461,
"step": 28
},
{
"epoch": 0.01,
"learning_rate": 0.0001939516129032258,
"loss": 1.9814,
"step": 29
},
{
"epoch": 0.01,
"learning_rate": 0.00019354838709677422,
"loss": 2.0338,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 0.00019314516129032258,
"loss": 2.0679,
"step": 31
},
{
"epoch": 0.01,
"learning_rate": 0.000192741935483871,
"loss": 1.9041,
"step": 32
},
{
"epoch": 0.01,
"learning_rate": 0.00019233870967741936,
"loss": 1.9297,
"step": 33
},
{
"epoch": 0.01,
"learning_rate": 0.00019193548387096775,
"loss": 1.7894,
"step": 34
},
{
"epoch": 0.01,
"learning_rate": 0.00019153225806451614,
"loss": 1.706,
"step": 35
},
{
"epoch": 0.01,
"learning_rate": 0.00019112903225806453,
"loss": 1.9426,
"step": 36
},
{
"epoch": 0.01,
"learning_rate": 0.00019072580645161291,
"loss": 1.6808,
"step": 37
},
{
"epoch": 0.01,
"learning_rate": 0.0001903225806451613,
"loss": 1.8675,
"step": 38
},
{
"epoch": 0.01,
"learning_rate": 0.0001899193548387097,
"loss": 1.8061,
"step": 39
},
{
"epoch": 0.01,
"learning_rate": 0.00018951612903225808,
"loss": 1.9412,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 0.00018911290322580645,
"loss": 1.9006,
"step": 41
},
{
"epoch": 0.01,
"learning_rate": 0.00018870967741935486,
"loss": 1.8384,
"step": 42
},
{
"epoch": 0.01,
"learning_rate": 0.00018830645161290322,
"loss": 1.6437,
"step": 43
},
{
"epoch": 0.01,
"learning_rate": 0.00018790322580645164,
"loss": 1.6731,
"step": 44
},
{
"epoch": 0.01,
"learning_rate": 0.0001875,
"loss": 1.8847,
"step": 45
},
{
"epoch": 0.01,
"learning_rate": 0.0001870967741935484,
"loss": 2.0385,
"step": 46
},
{
"epoch": 0.01,
"learning_rate": 0.00018669354838709678,
"loss": 1.9239,
"step": 47
},
{
"epoch": 0.01,
"learning_rate": 0.00018629032258064517,
"loss": 1.9099,
"step": 48
},
{
"epoch": 0.01,
"learning_rate": 0.00018588709677419356,
"loss": 1.8757,
"step": 49
},
{
"epoch": 0.01,
"learning_rate": 0.00018548387096774192,
"loss": 1.8522,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 0.00018508064516129034,
"loss": 1.6491,
"step": 51
},
{
"epoch": 0.01,
"learning_rate": 0.0001846774193548387,
"loss": 1.8618,
"step": 52
},
{
"epoch": 0.01,
"learning_rate": 0.00018427419354838712,
"loss": 1.9206,
"step": 53
},
{
"epoch": 0.01,
"learning_rate": 0.00018387096774193548,
"loss": 1.9207,
"step": 54
},
{
"epoch": 0.01,
"learning_rate": 0.00018346774193548387,
"loss": 1.74,
"step": 55
},
{
"epoch": 0.01,
"learning_rate": 0.00018306451612903226,
"loss": 1.7248,
"step": 56
},
{
"epoch": 0.01,
"learning_rate": 0.00018266129032258065,
"loss": 1.7827,
"step": 57
},
{
"epoch": 0.01,
"learning_rate": 0.00018225806451612904,
"loss": 1.7623,
"step": 58
},
{
"epoch": 0.01,
"learning_rate": 0.00018185483870967743,
"loss": 1.8197,
"step": 59
},
{
"epoch": 0.01,
"learning_rate": 0.00018145161290322582,
"loss": 1.8243,
"step": 60
},
{
"epoch": 0.01,
"learning_rate": 0.0001810483870967742,
"loss": 1.8143,
"step": 61
},
{
"epoch": 0.01,
"learning_rate": 0.00018064516129032257,
"loss": 1.7474,
"step": 62
},
{
"epoch": 0.01,
"learning_rate": 0.000180241935483871,
"loss": 1.875,
"step": 63
},
{
"epoch": 0.01,
"learning_rate": 0.00017983870967741935,
"loss": 1.8221,
"step": 64
},
{
"epoch": 0.01,
"learning_rate": 0.00017943548387096777,
"loss": 1.825,
"step": 65
},
{
"epoch": 0.01,
"learning_rate": 0.00017903225806451613,
"loss": 2.0207,
"step": 66
},
{
"epoch": 0.01,
"learning_rate": 0.00017862903225806452,
"loss": 2.0541,
"step": 67
},
{
"epoch": 0.01,
"learning_rate": 0.0001782258064516129,
"loss": 1.8867,
"step": 68
},
{
"epoch": 0.01,
"learning_rate": 0.0001778225806451613,
"loss": 1.8147,
"step": 69
},
{
"epoch": 0.01,
"learning_rate": 0.0001774193548387097,
"loss": 1.8254,
"step": 70
},
{
"epoch": 0.01,
"learning_rate": 0.00017701612903225808,
"loss": 2.0532,
"step": 71
},
{
"epoch": 0.01,
"learning_rate": 0.00017661290322580647,
"loss": 1.8977,
"step": 72
},
{
"epoch": 0.01,
"learning_rate": 0.00017620967741935486,
"loss": 1.9586,
"step": 73
},
{
"epoch": 0.01,
"learning_rate": 0.00017580645161290325,
"loss": 1.8705,
"step": 74
},
{
"epoch": 0.01,
"learning_rate": 0.00017540322580645164,
"loss": 1.9479,
"step": 75
},
{
"epoch": 0.01,
"learning_rate": 0.000175,
"loss": 1.8673,
"step": 76
},
{
"epoch": 0.01,
"learning_rate": 0.0001745967741935484,
"loss": 1.6754,
"step": 77
},
{
"epoch": 0.01,
"learning_rate": 0.00017419354838709678,
"loss": 1.8657,
"step": 78
},
{
"epoch": 0.01,
"learning_rate": 0.00017379032258064517,
"loss": 1.8191,
"step": 79
},
{
"epoch": 0.02,
"learning_rate": 0.00017338709677419356,
"loss": 1.9399,
"step": 80
},
{
"epoch": 0.02,
"learning_rate": 0.00017298387096774195,
"loss": 1.8157,
"step": 81
},
{
"epoch": 0.02,
"learning_rate": 0.00017258064516129034,
"loss": 1.8119,
"step": 82
},
{
"epoch": 0.02,
"learning_rate": 0.0001721774193548387,
"loss": 1.7594,
"step": 83
},
{
"epoch": 0.02,
"learning_rate": 0.00017177419354838711,
"loss": 1.7433,
"step": 84
},
{
"epoch": 0.02,
"learning_rate": 0.00017137096774193548,
"loss": 1.9931,
"step": 85
},
{
"epoch": 0.02,
"learning_rate": 0.0001709677419354839,
"loss": 1.6113,
"step": 86
},
{
"epoch": 0.02,
"learning_rate": 0.00017056451612903226,
"loss": 1.8318,
"step": 87
},
{
"epoch": 0.02,
"learning_rate": 0.00017016129032258065,
"loss": 1.7549,
"step": 88
},
{
"epoch": 0.02,
"learning_rate": 0.00016975806451612904,
"loss": 1.6381,
"step": 89
},
{
"epoch": 0.02,
"learning_rate": 0.00016935483870967742,
"loss": 1.7636,
"step": 90
},
{
"epoch": 0.02,
"learning_rate": 0.00016895161290322581,
"loss": 1.9249,
"step": 91
},
{
"epoch": 0.02,
"learning_rate": 0.0001685483870967742,
"loss": 1.6256,
"step": 92
},
{
"epoch": 0.02,
"learning_rate": 0.0001681451612903226,
"loss": 1.8184,
"step": 93
},
{
"epoch": 0.02,
"learning_rate": 0.00016774193548387098,
"loss": 2.162,
"step": 94
},
{
"epoch": 0.02,
"learning_rate": 0.00016733870967741935,
"loss": 1.9889,
"step": 95
},
{
"epoch": 0.02,
"learning_rate": 0.00016693548387096776,
"loss": 2.0199,
"step": 96
},
{
"epoch": 0.02,
"learning_rate": 0.00016653225806451612,
"loss": 1.6522,
"step": 97
},
{
"epoch": 0.02,
"learning_rate": 0.00016612903225806454,
"loss": 1.7608,
"step": 98
},
{
"epoch": 0.02,
"learning_rate": 0.0001657258064516129,
"loss": 1.8731,
"step": 99
},
{
"epoch": 0.02,
"learning_rate": 0.00016532258064516132,
"loss": 1.7608,
"step": 100
},
{
"epoch": 0.02,
"learning_rate": 0.00016491935483870968,
"loss": 1.7622,
"step": 101
},
{
"epoch": 0.02,
"learning_rate": 0.00016451612903225807,
"loss": 1.9002,
"step": 102
},
{
"epoch": 0.02,
"learning_rate": 0.00016411290322580646,
"loss": 2.0436,
"step": 103
},
{
"epoch": 0.02,
"learning_rate": 0.00016370967741935485,
"loss": 1.8616,
"step": 104
},
{
"epoch": 0.02,
"learning_rate": 0.00016330645161290324,
"loss": 1.7176,
"step": 105
},
{
"epoch": 0.02,
"learning_rate": 0.00016290322580645163,
"loss": 1.6685,
"step": 106
},
{
"epoch": 0.02,
"learning_rate": 0.00016250000000000002,
"loss": 1.6372,
"step": 107
},
{
"epoch": 0.02,
"learning_rate": 0.00016209677419354838,
"loss": 1.6905,
"step": 108
},
{
"epoch": 0.02,
"learning_rate": 0.00016169354838709677,
"loss": 1.8648,
"step": 109
},
{
"epoch": 0.02,
"learning_rate": 0.00016129032258064516,
"loss": 1.6261,
"step": 110
},
{
"epoch": 0.02,
"learning_rate": 0.00016088709677419355,
"loss": 1.9515,
"step": 111
},
{
"epoch": 0.02,
"learning_rate": 0.00016048387096774194,
"loss": 1.8152,
"step": 112
},
{
"epoch": 0.02,
"learning_rate": 0.00016008064516129033,
"loss": 1.911,
"step": 113
},
{
"epoch": 0.02,
"learning_rate": 0.00015967741935483872,
"loss": 1.8369,
"step": 114
},
{
"epoch": 0.02,
"learning_rate": 0.0001592741935483871,
"loss": 2.0098,
"step": 115
},
{
"epoch": 0.02,
"learning_rate": 0.00015887096774193547,
"loss": 1.8714,
"step": 116
},
{
"epoch": 0.02,
"learning_rate": 0.0001584677419354839,
"loss": 1.8616,
"step": 117
},
{
"epoch": 0.02,
"learning_rate": 0.00015806451612903225,
"loss": 1.7949,
"step": 118
},
{
"epoch": 0.02,
"learning_rate": 0.00015766129032258067,
"loss": 1.8428,
"step": 119
},
{
"epoch": 0.02,
"learning_rate": 0.00015725806451612903,
"loss": 1.8926,
"step": 120
},
{
"epoch": 0.02,
"learning_rate": 0.00015685483870967742,
"loss": 1.9585,
"step": 121
},
{
"epoch": 0.02,
"learning_rate": 0.0001564516129032258,
"loss": 1.7365,
"step": 122
},
{
"epoch": 0.02,
"learning_rate": 0.0001560483870967742,
"loss": 1.7087,
"step": 123
},
{
"epoch": 0.02,
"learning_rate": 0.0001556451612903226,
"loss": 1.9679,
"step": 124
},
{
"epoch": 0.02,
"learning_rate": 0.00015524193548387098,
"loss": 1.8046,
"step": 125
},
{
"epoch": 0.02,
"learning_rate": 0.00015483870967741937,
"loss": 1.8889,
"step": 126
},
{
"epoch": 0.02,
"learning_rate": 0.00015443548387096776,
"loss": 1.9183,
"step": 127
},
{
"epoch": 0.02,
"learning_rate": 0.00015403225806451615,
"loss": 1.6254,
"step": 128
},
{
"epoch": 0.02,
"learning_rate": 0.00015362903225806454,
"loss": 1.8339,
"step": 129
},
{
"epoch": 0.02,
"learning_rate": 0.0001532258064516129,
"loss": 1.94,
"step": 130
},
{
"epoch": 0.02,
"learning_rate": 0.00015282258064516131,
"loss": 1.9235,
"step": 131
},
{
"epoch": 0.02,
"learning_rate": 0.00015241935483870968,
"loss": 1.78,
"step": 132
},
{
"epoch": 0.03,
"learning_rate": 0.0001520161290322581,
"loss": 1.7514,
"step": 133
},
{
"epoch": 0.03,
"learning_rate": 0.00015161290322580646,
"loss": 1.8281,
"step": 134
},
{
"epoch": 0.03,
"learning_rate": 0.00015120967741935485,
"loss": 1.8109,
"step": 135
},
{
"epoch": 0.03,
"learning_rate": 0.00015080645161290323,
"loss": 1.9297,
"step": 136
},
{
"epoch": 0.03,
"learning_rate": 0.00015040322580645162,
"loss": 1.7198,
"step": 137
},
{
"epoch": 0.03,
"learning_rate": 0.00015000000000000001,
"loss": 1.7704,
"step": 138
},
{
"epoch": 0.03,
"learning_rate": 0.00014959677419354838,
"loss": 1.8345,
"step": 139
},
{
"epoch": 0.03,
"learning_rate": 0.0001491935483870968,
"loss": 1.7694,
"step": 140
},
{
"epoch": 0.03,
"learning_rate": 0.00014879032258064516,
"loss": 1.8196,
"step": 141
},
{
"epoch": 0.03,
"learning_rate": 0.00014838709677419355,
"loss": 1.8625,
"step": 142
},
{
"epoch": 0.03,
"learning_rate": 0.00014798387096774193,
"loss": 1.9182,
"step": 143
},
{
"epoch": 0.03,
"learning_rate": 0.00014758064516129032,
"loss": 1.4297,
"step": 144
},
{
"epoch": 0.03,
"learning_rate": 0.00014717741935483871,
"loss": 1.929,
"step": 145
},
{
"epoch": 0.03,
"learning_rate": 0.0001467741935483871,
"loss": 1.9118,
"step": 146
},
{
"epoch": 0.03,
"learning_rate": 0.0001463709677419355,
"loss": 2.0179,
"step": 147
},
{
"epoch": 0.03,
"learning_rate": 0.00014596774193548388,
"loss": 1.8938,
"step": 148
},
{
"epoch": 0.03,
"learning_rate": 0.00014556451612903224,
"loss": 1.8689,
"step": 149
},
{
"epoch": 0.03,
"learning_rate": 0.00014516129032258066,
"loss": 1.6793,
"step": 150
},
{
"epoch": 0.03,
"learning_rate": 0.00014475806451612902,
"loss": 1.8137,
"step": 151
},
{
"epoch": 0.03,
"learning_rate": 0.00014435483870967744,
"loss": 1.8723,
"step": 152
},
{
"epoch": 0.03,
"learning_rate": 0.0001439516129032258,
"loss": 2.1375,
"step": 153
},
{
"epoch": 0.03,
"learning_rate": 0.00014354838709677422,
"loss": 1.8179,
"step": 154
},
{
"epoch": 0.03,
"learning_rate": 0.00014314516129032258,
"loss": 1.931,
"step": 155
},
{
"epoch": 0.03,
"learning_rate": 0.00014274193548387097,
"loss": 1.98,
"step": 156
},
{
"epoch": 0.03,
"learning_rate": 0.00014233870967741936,
"loss": 1.821,
"step": 157
},
{
"epoch": 0.03,
"learning_rate": 0.00014193548387096775,
"loss": 1.5842,
"step": 158
},
{
"epoch": 0.03,
"learning_rate": 0.00014153225806451614,
"loss": 1.5374,
"step": 159
},
{
"epoch": 0.03,
"learning_rate": 0.00014112903225806453,
"loss": 1.6705,
"step": 160
},
{
"epoch": 0.03,
"learning_rate": 0.00014072580645161292,
"loss": 1.5556,
"step": 161
},
{
"epoch": 0.03,
"learning_rate": 0.0001403225806451613,
"loss": 1.8065,
"step": 162
},
{
"epoch": 0.03,
"learning_rate": 0.00013991935483870967,
"loss": 1.7033,
"step": 163
},
{
"epoch": 0.03,
"learning_rate": 0.0001395161290322581,
"loss": 1.7212,
"step": 164
},
{
"epoch": 0.03,
"learning_rate": 0.00013911290322580645,
"loss": 1.709,
"step": 165
},
{
"epoch": 0.03,
"learning_rate": 0.00013870967741935487,
"loss": 1.942,
"step": 166
},
{
"epoch": 0.03,
"learning_rate": 0.00013830645161290323,
"loss": 1.7319,
"step": 167
},
{
"epoch": 0.03,
"learning_rate": 0.00013790322580645162,
"loss": 1.7121,
"step": 168
},
{
"epoch": 0.03,
"learning_rate": 0.0001375,
"loss": 1.7898,
"step": 169
},
{
"epoch": 0.03,
"learning_rate": 0.00013709677419354837,
"loss": 1.5978,
"step": 170
},
{
"epoch": 0.03,
"learning_rate": 0.0001366935483870968,
"loss": 1.8471,
"step": 171
},
{
"epoch": 0.03,
"learning_rate": 0.00013629032258064515,
"loss": 1.5818,
"step": 172
},
{
"epoch": 0.03,
"learning_rate": 0.00013588709677419357,
"loss": 1.9192,
"step": 173
},
{
"epoch": 0.03,
"learning_rate": 0.00013548387096774193,
"loss": 1.822,
"step": 174
},
{
"epoch": 0.03,
"learning_rate": 0.00013508064516129032,
"loss": 1.9106,
"step": 175
},
{
"epoch": 0.03,
"learning_rate": 0.0001346774193548387,
"loss": 1.88,
"step": 176
},
{
"epoch": 0.03,
"learning_rate": 0.0001342741935483871,
"loss": 1.6629,
"step": 177
},
{
"epoch": 0.03,
"learning_rate": 0.0001338709677419355,
"loss": 1.7003,
"step": 178
},
{
"epoch": 0.03,
"learning_rate": 0.00013346774193548388,
"loss": 1.8718,
"step": 179
},
{
"epoch": 0.03,
"learning_rate": 0.00013306451612903227,
"loss": 1.6612,
"step": 180
},
{
"epoch": 0.03,
"learning_rate": 0.00013266129032258066,
"loss": 1.7508,
"step": 181
},
{
"epoch": 0.03,
"learning_rate": 0.00013225806451612905,
"loss": 1.7353,
"step": 182
},
{
"epoch": 0.03,
"learning_rate": 0.00013185483870967743,
"loss": 1.7166,
"step": 183
},
{
"epoch": 0.03,
"learning_rate": 0.0001314516129032258,
"loss": 1.645,
"step": 184
},
{
"epoch": 0.03,
"learning_rate": 0.00013104838709677421,
"loss": 1.9116,
"step": 185
},
{
"epoch": 0.04,
"learning_rate": 0.00013064516129032258,
"loss": 1.789,
"step": 186
},
{
"epoch": 0.04,
"learning_rate": 0.000130241935483871,
"loss": 1.6897,
"step": 187
},
{
"epoch": 0.04,
"learning_rate": 0.00012983870967741936,
"loss": 1.95,
"step": 188
},
{
"epoch": 0.04,
"learning_rate": 0.00012943548387096774,
"loss": 1.7303,
"step": 189
},
{
"epoch": 0.04,
"learning_rate": 0.00012903225806451613,
"loss": 1.8367,
"step": 190
},
{
"epoch": 0.04,
"learning_rate": 0.00012862903225806452,
"loss": 1.85,
"step": 191
},
{
"epoch": 0.04,
"learning_rate": 0.0001282258064516129,
"loss": 1.9674,
"step": 192
},
{
"epoch": 0.04,
"learning_rate": 0.0001278225806451613,
"loss": 1.8232,
"step": 193
},
{
"epoch": 0.04,
"learning_rate": 0.0001274193548387097,
"loss": 1.8315,
"step": 194
},
{
"epoch": 0.04,
"learning_rate": 0.00012701612903225808,
"loss": 1.8721,
"step": 195
},
{
"epoch": 0.04,
"learning_rate": 0.00012661290322580644,
"loss": 1.8113,
"step": 196
},
{
"epoch": 0.04,
"learning_rate": 0.00012620967741935486,
"loss": 1.8035,
"step": 197
},
{
"epoch": 0.04,
"learning_rate": 0.00012580645161290322,
"loss": 1.7259,
"step": 198
},
{
"epoch": 0.04,
"learning_rate": 0.00012540322580645164,
"loss": 1.883,
"step": 199
},
{
"epoch": 0.04,
"learning_rate": 0.000125,
"loss": 1.7711,
"step": 200
},
{
"epoch": 0.04,
"learning_rate": 0.0001245967741935484,
"loss": 1.898,
"step": 201
},
{
"epoch": 0.04,
"learning_rate": 0.00012419354838709678,
"loss": 1.9863,
"step": 202
},
{
"epoch": 0.04,
"learning_rate": 0.00012379032258064514,
"loss": 1.7927,
"step": 203
},
{
"epoch": 0.04,
"learning_rate": 0.00012338709677419356,
"loss": 1.6175,
"step": 204
},
{
"epoch": 0.04,
"learning_rate": 0.00012298387096774192,
"loss": 1.7774,
"step": 205
},
{
"epoch": 0.04,
"learning_rate": 0.00012258064516129034,
"loss": 1.8218,
"step": 206
},
{
"epoch": 0.04,
"learning_rate": 0.0001221774193548387,
"loss": 1.7892,
"step": 207
},
{
"epoch": 0.04,
"learning_rate": 0.0001217741935483871,
"loss": 1.8224,
"step": 208
},
{
"epoch": 0.04,
"learning_rate": 0.00012137096774193548,
"loss": 1.8561,
"step": 209
},
{
"epoch": 0.04,
"learning_rate": 0.00012096774193548388,
"loss": 1.8629,
"step": 210
},
{
"epoch": 0.04,
"learning_rate": 0.00012056451612903226,
"loss": 1.6567,
"step": 211
},
{
"epoch": 0.04,
"learning_rate": 0.00012016129032258065,
"loss": 1.6718,
"step": 212
},
{
"epoch": 0.04,
"learning_rate": 0.00011975806451612903,
"loss": 1.8066,
"step": 213
},
{
"epoch": 0.04,
"learning_rate": 0.00011935483870967743,
"loss": 1.7233,
"step": 214
},
{
"epoch": 0.04,
"learning_rate": 0.0001189516129032258,
"loss": 1.6479,
"step": 215
},
{
"epoch": 0.04,
"learning_rate": 0.00011854838709677421,
"loss": 2.0369,
"step": 216
},
{
"epoch": 0.04,
"learning_rate": 0.00011814516129032258,
"loss": 1.7894,
"step": 217
},
{
"epoch": 0.04,
"learning_rate": 0.00011774193548387097,
"loss": 1.6236,
"step": 218
},
{
"epoch": 0.04,
"learning_rate": 0.00011733870967741935,
"loss": 1.8314,
"step": 219
},
{
"epoch": 0.04,
"learning_rate": 0.00011693548387096775,
"loss": 1.9224,
"step": 220
},
{
"epoch": 0.04,
"learning_rate": 0.00011653225806451613,
"loss": 1.9855,
"step": 221
},
{
"epoch": 0.04,
"learning_rate": 0.00011612903225806453,
"loss": 1.83,
"step": 222
},
{
"epoch": 0.04,
"learning_rate": 0.00011572580645161291,
"loss": 1.9531,
"step": 223
},
{
"epoch": 0.04,
"learning_rate": 0.00011532258064516131,
"loss": 1.8671,
"step": 224
},
{
"epoch": 0.04,
"learning_rate": 0.00011491935483870969,
"loss": 1.8854,
"step": 225
},
{
"epoch": 0.04,
"learning_rate": 0.00011451612903225808,
"loss": 1.646,
"step": 226
},
{
"epoch": 0.04,
"learning_rate": 0.00011411290322580645,
"loss": 1.785,
"step": 227
},
{
"epoch": 0.04,
"learning_rate": 0.00011370967741935486,
"loss": 1.8054,
"step": 228
},
{
"epoch": 0.04,
"learning_rate": 0.00011330645161290323,
"loss": 1.7348,
"step": 229
},
{
"epoch": 0.04,
"learning_rate": 0.00011290322580645163,
"loss": 1.8856,
"step": 230
},
{
"epoch": 0.04,
"learning_rate": 0.00011250000000000001,
"loss": 1.8276,
"step": 231
},
{
"epoch": 0.04,
"learning_rate": 0.00011209677419354839,
"loss": 1.852,
"step": 232
},
{
"epoch": 0.04,
"learning_rate": 0.00011169354838709678,
"loss": 1.6737,
"step": 233
},
{
"epoch": 0.04,
"learning_rate": 0.00011129032258064515,
"loss": 2.0757,
"step": 234
},
{
"epoch": 0.04,
"learning_rate": 0.00011088709677419356,
"loss": 1.7542,
"step": 235
},
{
"epoch": 0.04,
"learning_rate": 0.00011048387096774193,
"loss": 1.592,
"step": 236
},
{
"epoch": 0.04,
"learning_rate": 0.00011008064516129033,
"loss": 1.6739,
"step": 237
},
{
"epoch": 0.04,
"learning_rate": 0.00010967741935483871,
"loss": 1.6539,
"step": 238
},
{
"epoch": 0.05,
"learning_rate": 0.0001092741935483871,
"loss": 1.6618,
"step": 239
},
{
"epoch": 0.05,
"learning_rate": 0.00010887096774193548,
"loss": 1.8716,
"step": 240
},
{
"epoch": 0.05,
"learning_rate": 0.00010846774193548388,
"loss": 1.5938,
"step": 241
},
{
"epoch": 0.05,
"learning_rate": 0.00010806451612903225,
"loss": 1.746,
"step": 242
},
{
"epoch": 0.05,
"learning_rate": 0.00010766129032258066,
"loss": 1.8497,
"step": 243
},
{
"epoch": 0.05,
"learning_rate": 0.00010725806451612903,
"loss": 1.7258,
"step": 244
},
{
"epoch": 0.05,
"learning_rate": 0.00010685483870967742,
"loss": 1.8574,
"step": 245
},
{
"epoch": 0.05,
"learning_rate": 0.0001064516129032258,
"loss": 1.3634,
"step": 246
},
{
"epoch": 0.05,
"learning_rate": 0.0001060483870967742,
"loss": 1.7197,
"step": 247
},
{
"epoch": 0.05,
"learning_rate": 0.00010564516129032258,
"loss": 1.621,
"step": 248
},
{
"epoch": 0.05,
"learning_rate": 0.00010524193548387098,
"loss": 1.9533,
"step": 249
},
{
"epoch": 0.05,
"learning_rate": 0.00010483870967741936,
"loss": 1.7434,
"step": 250
},
{
"epoch": 0.05,
"learning_rate": 0.00010443548387096776,
"loss": 1.8007,
"step": 251
},
{
"epoch": 0.05,
"learning_rate": 0.00010403225806451614,
"loss": 1.6433,
"step": 252
},
{
"epoch": 0.05,
"learning_rate": 0.00010362903225806453,
"loss": 1.7027,
"step": 253
},
{
"epoch": 0.05,
"learning_rate": 0.0001032258064516129,
"loss": 1.8701,
"step": 254
},
{
"epoch": 0.05,
"learning_rate": 0.0001028225806451613,
"loss": 1.8413,
"step": 255
},
{
"epoch": 0.05,
"learning_rate": 0.00010241935483870968,
"loss": 1.9269,
"step": 256
},
{
"epoch": 0.05,
"learning_rate": 0.00010201612903225808,
"loss": 1.7059,
"step": 257
},
{
"epoch": 0.05,
"learning_rate": 0.00010161290322580646,
"loss": 1.6181,
"step": 258
},
{
"epoch": 0.05,
"learning_rate": 0.00010120967741935485,
"loss": 1.8166,
"step": 259
},
{
"epoch": 0.05,
"learning_rate": 0.00010080645161290323,
"loss": 1.8045,
"step": 260
},
{
"epoch": 0.05,
"learning_rate": 0.00010040322580645163,
"loss": 1.8225,
"step": 261
},
{
"epoch": 0.05,
"learning_rate": 0.0001,
"loss": 1.8238,
"step": 262
},
{
"epoch": 0.05,
"learning_rate": 9.95967741935484e-05,
"loss": 1.7171,
"step": 263
},
{
"epoch": 0.05,
"learning_rate": 9.919354838709678e-05,
"loss": 1.9391,
"step": 264
},
{
"epoch": 0.05,
"learning_rate": 9.879032258064517e-05,
"loss": 1.82,
"step": 265
},
{
"epoch": 0.05,
"learning_rate": 9.838709677419355e-05,
"loss": 1.6228,
"step": 266
},
{
"epoch": 0.05,
"learning_rate": 9.798387096774194e-05,
"loss": 1.6614,
"step": 267
},
{
"epoch": 0.05,
"learning_rate": 9.758064516129033e-05,
"loss": 1.8507,
"step": 268
},
{
"epoch": 0.05,
"learning_rate": 9.717741935483872e-05,
"loss": 1.8328,
"step": 269
},
{
"epoch": 0.05,
"learning_rate": 9.677419354838711e-05,
"loss": 1.7367,
"step": 270
},
{
"epoch": 0.05,
"learning_rate": 9.63709677419355e-05,
"loss": 1.5467,
"step": 271
},
{
"epoch": 0.05,
"learning_rate": 9.596774193548387e-05,
"loss": 1.815,
"step": 272
},
{
"epoch": 0.05,
"learning_rate": 9.556451612903226e-05,
"loss": 1.7204,
"step": 273
},
{
"epoch": 0.05,
"learning_rate": 9.516129032258065e-05,
"loss": 1.7657,
"step": 274
},
{
"epoch": 0.05,
"learning_rate": 9.475806451612904e-05,
"loss": 1.8864,
"step": 275
},
{
"epoch": 0.05,
"learning_rate": 9.435483870967743e-05,
"loss": 1.8089,
"step": 276
},
{
"epoch": 0.05,
"learning_rate": 9.395161290322582e-05,
"loss": 1.5696,
"step": 277
},
{
"epoch": 0.05,
"learning_rate": 9.35483870967742e-05,
"loss": 1.8657,
"step": 278
},
{
"epoch": 0.05,
"learning_rate": 9.314516129032259e-05,
"loss": 1.7064,
"step": 279
},
{
"epoch": 0.05,
"learning_rate": 9.274193548387096e-05,
"loss": 1.6814,
"step": 280
},
{
"epoch": 0.05,
"learning_rate": 9.233870967741935e-05,
"loss": 1.9198,
"step": 281
},
{
"epoch": 0.05,
"learning_rate": 9.193548387096774e-05,
"loss": 1.8851,
"step": 282
},
{
"epoch": 0.05,
"learning_rate": 9.153225806451613e-05,
"loss": 2.0314,
"step": 283
},
{
"epoch": 0.05,
"learning_rate": 9.112903225806452e-05,
"loss": 1.9425,
"step": 284
},
{
"epoch": 0.05,
"learning_rate": 9.072580645161291e-05,
"loss": 1.5442,
"step": 285
},
{
"epoch": 0.05,
"learning_rate": 9.032258064516129e-05,
"loss": 1.8918,
"step": 286
},
{
"epoch": 0.05,
"learning_rate": 8.991935483870968e-05,
"loss": 1.7266,
"step": 287
},
{
"epoch": 0.05,
"learning_rate": 8.951612903225806e-05,
"loss": 1.8173,
"step": 288
},
{
"epoch": 0.05,
"learning_rate": 8.911290322580645e-05,
"loss": 1.8304,
"step": 289
},
{
"epoch": 0.05,
"learning_rate": 8.870967741935484e-05,
"loss": 1.8695,
"step": 290
},
{
"epoch": 0.06,
"learning_rate": 8.830645161290323e-05,
"loss": 1.7768,
"step": 291
},
{
"epoch": 0.06,
"learning_rate": 8.790322580645162e-05,
"loss": 1.6761,
"step": 292
},
{
"epoch": 0.06,
"learning_rate": 8.75e-05,
"loss": 1.9339,
"step": 293
},
{
"epoch": 0.06,
"learning_rate": 8.709677419354839e-05,
"loss": 1.6024,
"step": 294
},
{
"epoch": 0.06,
"learning_rate": 8.669354838709678e-05,
"loss": 1.888,
"step": 295
},
{
"epoch": 0.06,
"learning_rate": 8.629032258064517e-05,
"loss": 2.0134,
"step": 296
},
{
"epoch": 0.06,
"learning_rate": 8.588709677419356e-05,
"loss": 1.8298,
"step": 297
},
{
"epoch": 0.06,
"learning_rate": 8.548387096774195e-05,
"loss": 1.6569,
"step": 298
},
{
"epoch": 0.06,
"learning_rate": 8.508064516129032e-05,
"loss": 1.8178,
"step": 299
},
{
"epoch": 0.06,
"learning_rate": 8.467741935483871e-05,
"loss": 1.8671,
"step": 300
},
{
"epoch": 0.06,
"learning_rate": 8.42741935483871e-05,
"loss": 1.7377,
"step": 301
},
{
"epoch": 0.06,
"learning_rate": 8.387096774193549e-05,
"loss": 1.8159,
"step": 302
},
{
"epoch": 0.06,
"learning_rate": 8.346774193548388e-05,
"loss": 1.8228,
"step": 303
},
{
"epoch": 0.06,
"learning_rate": 8.306451612903227e-05,
"loss": 1.5063,
"step": 304
},
{
"epoch": 0.06,
"learning_rate": 8.266129032258066e-05,
"loss": 1.5956,
"step": 305
},
{
"epoch": 0.06,
"learning_rate": 8.225806451612904e-05,
"loss": 1.8835,
"step": 306
},
{
"epoch": 0.06,
"learning_rate": 8.185483870967743e-05,
"loss": 1.82,
"step": 307
},
{
"epoch": 0.06,
"learning_rate": 8.145161290322582e-05,
"loss": 1.84,
"step": 308
},
{
"epoch": 0.06,
"learning_rate": 8.104838709677419e-05,
"loss": 1.7437,
"step": 309
},
{
"epoch": 0.06,
"learning_rate": 8.064516129032258e-05,
"loss": 1.5967,
"step": 310
},
{
"epoch": 0.06,
"learning_rate": 8.024193548387097e-05,
"loss": 1.8747,
"step": 311
},
{
"epoch": 0.06,
"learning_rate": 7.983870967741936e-05,
"loss": 1.8412,
"step": 312
},
{
"epoch": 0.06,
"learning_rate": 7.943548387096774e-05,
"loss": 1.7066,
"step": 313
},
{
"epoch": 0.06,
"learning_rate": 7.903225806451613e-05,
"loss": 1.725,
"step": 314
},
{
"epoch": 0.06,
"learning_rate": 7.862903225806451e-05,
"loss": 1.8255,
"step": 315
},
{
"epoch": 0.06,
"learning_rate": 7.82258064516129e-05,
"loss": 1.7398,
"step": 316
},
{
"epoch": 0.06,
"learning_rate": 7.78225806451613e-05,
"loss": 1.8464,
"step": 317
},
{
"epoch": 0.06,
"learning_rate": 7.741935483870968e-05,
"loss": 1.8334,
"step": 318
},
{
"epoch": 0.06,
"learning_rate": 7.701612903225807e-05,
"loss": 1.7275,
"step": 319
},
{
"epoch": 0.06,
"learning_rate": 7.661290322580645e-05,
"loss": 1.8394,
"step": 320
},
{
"epoch": 0.06,
"learning_rate": 7.620967741935484e-05,
"loss": 1.8441,
"step": 321
},
{
"epoch": 0.06,
"learning_rate": 7.580645161290323e-05,
"loss": 1.9216,
"step": 322
},
{
"epoch": 0.06,
"learning_rate": 7.540322580645162e-05,
"loss": 1.7269,
"step": 323
},
{
"epoch": 0.06,
"learning_rate": 7.500000000000001e-05,
"loss": 1.7861,
"step": 324
},
{
"epoch": 0.06,
"learning_rate": 7.45967741935484e-05,
"loss": 1.8198,
"step": 325
},
{
"epoch": 0.06,
"learning_rate": 7.419354838709677e-05,
"loss": 2.0093,
"step": 326
},
{
"epoch": 0.06,
"learning_rate": 7.379032258064516e-05,
"loss": 1.9401,
"step": 327
},
{
"epoch": 0.06,
"learning_rate": 7.338709677419355e-05,
"loss": 1.9415,
"step": 328
},
{
"epoch": 0.06,
"learning_rate": 7.298387096774194e-05,
"loss": 1.8374,
"step": 329
},
{
"epoch": 0.06,
"learning_rate": 7.258064516129033e-05,
"loss": 1.7686,
"step": 330
},
{
"epoch": 0.06,
"learning_rate": 7.217741935483872e-05,
"loss": 1.8984,
"step": 331
},
{
"epoch": 0.06,
"learning_rate": 7.177419354838711e-05,
"loss": 1.7924,
"step": 332
},
{
"epoch": 0.06,
"learning_rate": 7.137096774193549e-05,
"loss": 1.7647,
"step": 333
},
{
"epoch": 0.06,
"learning_rate": 7.096774193548388e-05,
"loss": 1.8069,
"step": 334
},
{
"epoch": 0.06,
"learning_rate": 7.056451612903226e-05,
"loss": 2.001,
"step": 335
},
{
"epoch": 0.06,
"learning_rate": 7.016129032258065e-05,
"loss": 1.8589,
"step": 336
},
{
"epoch": 0.06,
"learning_rate": 6.975806451612904e-05,
"loss": 1.7668,
"step": 337
},
{
"epoch": 0.06,
"learning_rate": 6.935483870967743e-05,
"loss": 1.8,
"step": 338
},
{
"epoch": 0.06,
"learning_rate": 6.895161290322581e-05,
"loss": 1.9151,
"step": 339
},
{
"epoch": 0.06,
"learning_rate": 6.854838709677419e-05,
"loss": 1.6757,
"step": 340
},
{
"epoch": 0.06,
"learning_rate": 6.814516129032257e-05,
"loss": 1.8814,
"step": 341
},
{
"epoch": 0.06,
"learning_rate": 6.774193548387096e-05,
"loss": 1.9656,
"step": 342
},
{
"epoch": 0.06,
"learning_rate": 6.733870967741935e-05,
"loss": 1.7544,
"step": 343
},
{
"epoch": 0.07,
"learning_rate": 6.693548387096774e-05,
"loss": 1.6819,
"step": 344
},
{
"epoch": 0.07,
"learning_rate": 6.653225806451613e-05,
"loss": 1.8296,
"step": 345
},
{
"epoch": 0.07,
"learning_rate": 6.612903225806452e-05,
"loss": 1.7737,
"step": 346
},
{
"epoch": 0.07,
"learning_rate": 6.57258064516129e-05,
"loss": 1.8082,
"step": 347
},
{
"epoch": 0.07,
"learning_rate": 6.532258064516129e-05,
"loss": 1.842,
"step": 348
},
{
"epoch": 0.07,
"learning_rate": 6.491935483870968e-05,
"loss": 1.7791,
"step": 349
},
{
"epoch": 0.07,
"learning_rate": 6.451612903225807e-05,
"loss": 1.7993,
"step": 350
},
{
"epoch": 0.07,
"learning_rate": 6.411290322580646e-05,
"loss": 1.6751,
"step": 351
},
{
"epoch": 0.07,
"learning_rate": 6.370967741935485e-05,
"loss": 1.5395,
"step": 352
},
{
"epoch": 0.07,
"learning_rate": 6.330645161290322e-05,
"loss": 1.7641,
"step": 353
},
{
"epoch": 0.07,
"learning_rate": 6.290322580645161e-05,
"loss": 1.8276,
"step": 354
},
{
"epoch": 0.07,
"learning_rate": 6.25e-05,
"loss": 1.6124,
"step": 355
},
{
"epoch": 0.07,
"learning_rate": 6.209677419354839e-05,
"loss": 1.9139,
"step": 356
},
{
"epoch": 0.07,
"learning_rate": 6.169354838709678e-05,
"loss": 1.9209,
"step": 357
},
{
"epoch": 0.07,
"learning_rate": 6.129032258064517e-05,
"loss": 1.7141,
"step": 358
},
{
"epoch": 0.07,
"learning_rate": 6.088709677419355e-05,
"loss": 1.7097,
"step": 359
},
{
"epoch": 0.07,
"learning_rate": 6.048387096774194e-05,
"loss": 1.8613,
"step": 360
},
{
"epoch": 0.07,
"learning_rate": 6.0080645161290325e-05,
"loss": 1.8991,
"step": 361
},
{
"epoch": 0.07,
"learning_rate": 5.9677419354838715e-05,
"loss": 1.91,
"step": 362
},
{
"epoch": 0.07,
"learning_rate": 5.9274193548387104e-05,
"loss": 1.9808,
"step": 363
},
{
"epoch": 0.07,
"learning_rate": 5.887096774193549e-05,
"loss": 1.8814,
"step": 364
},
{
"epoch": 0.07,
"learning_rate": 5.8467741935483876e-05,
"loss": 1.927,
"step": 365
},
{
"epoch": 0.07,
"learning_rate": 5.8064516129032266e-05,
"loss": 1.6621,
"step": 366
},
{
"epoch": 0.07,
"learning_rate": 5.7661290322580655e-05,
"loss": 1.638,
"step": 367
},
{
"epoch": 0.07,
"learning_rate": 5.725806451612904e-05,
"loss": 1.7488,
"step": 368
},
{
"epoch": 0.07,
"learning_rate": 5.685483870967743e-05,
"loss": 1.7688,
"step": 369
},
{
"epoch": 0.07,
"learning_rate": 5.645161290322582e-05,
"loss": 1.8261,
"step": 370
},
{
"epoch": 0.07,
"learning_rate": 5.604838709677419e-05,
"loss": 1.7565,
"step": 371
},
{
"epoch": 0.07,
"learning_rate": 5.5645161290322576e-05,
"loss": 1.6734,
"step": 372
},
{
"epoch": 0.07,
"learning_rate": 5.5241935483870966e-05,
"loss": 1.7383,
"step": 373
},
{
"epoch": 0.07,
"learning_rate": 5.4838709677419355e-05,
"loss": 1.7189,
"step": 374
},
{
"epoch": 0.07,
"learning_rate": 5.443548387096774e-05,
"loss": 1.8827,
"step": 375
},
{
"epoch": 0.07,
"learning_rate": 5.403225806451613e-05,
"loss": 1.8262,
"step": 376
},
{
"epoch": 0.07,
"learning_rate": 5.362903225806452e-05,
"loss": 1.7789,
"step": 377
},
{
"epoch": 0.07,
"learning_rate": 5.32258064516129e-05,
"loss": 1.7937,
"step": 378
},
{
"epoch": 0.07,
"learning_rate": 5.282258064516129e-05,
"loss": 1.8751,
"step": 379
},
{
"epoch": 0.07,
"learning_rate": 5.241935483870968e-05,
"loss": 1.7343,
"step": 380
},
{
"epoch": 0.07,
"learning_rate": 5.201612903225807e-05,
"loss": 1.68,
"step": 381
},
{
"epoch": 0.07,
"learning_rate": 5.161290322580645e-05,
"loss": 1.7465,
"step": 382
},
{
"epoch": 0.07,
"learning_rate": 5.120967741935484e-05,
"loss": 1.8655,
"step": 383
},
{
"epoch": 0.07,
"learning_rate": 5.080645161290323e-05,
"loss": 1.7398,
"step": 384
},
{
"epoch": 0.07,
"learning_rate": 5.040322580645161e-05,
"loss": 1.8772,
"step": 385
},
{
"epoch": 0.07,
"learning_rate": 5e-05,
"loss": 1.8151,
"step": 386
},
{
"epoch": 0.07,
"learning_rate": 4.959677419354839e-05,
"loss": 1.8336,
"step": 387
},
{
"epoch": 0.07,
"learning_rate": 4.9193548387096775e-05,
"loss": 1.8974,
"step": 388
},
{
"epoch": 0.07,
"learning_rate": 4.8790322580645164e-05,
"loss": 1.8635,
"step": 389
},
{
"epoch": 0.07,
"learning_rate": 4.8387096774193554e-05,
"loss": 1.8573,
"step": 390
},
{
"epoch": 0.07,
"learning_rate": 4.7983870967741937e-05,
"loss": 1.8567,
"step": 391
},
{
"epoch": 0.07,
"learning_rate": 4.7580645161290326e-05,
"loss": 1.7087,
"step": 392
},
{
"epoch": 0.07,
"learning_rate": 4.7177419354838716e-05,
"loss": 1.9176,
"step": 393
},
{
"epoch": 0.07,
"learning_rate": 4.67741935483871e-05,
"loss": 1.7583,
"step": 394
},
{
"epoch": 0.07,
"learning_rate": 4.637096774193548e-05,
"loss": 1.9632,
"step": 395
},
{
"epoch": 0.07,
"learning_rate": 4.596774193548387e-05,
"loss": 1.9195,
"step": 396
},
{
"epoch": 0.08,
"learning_rate": 4.556451612903226e-05,
"loss": 1.3862,
"step": 397
},
{
"epoch": 0.08,
"learning_rate": 4.516129032258064e-05,
"loss": 2.0477,
"step": 398
},
{
"epoch": 0.08,
"learning_rate": 4.475806451612903e-05,
"loss": 1.8659,
"step": 399
},
{
"epoch": 0.08,
"learning_rate": 4.435483870967742e-05,
"loss": 1.7193,
"step": 400
},
{
"epoch": 0.08,
"learning_rate": 4.395161290322581e-05,
"loss": 1.7234,
"step": 401
},
{
"epoch": 0.08,
"learning_rate": 4.3548387096774194e-05,
"loss": 1.8746,
"step": 402
},
{
"epoch": 0.08,
"learning_rate": 4.3145161290322584e-05,
"loss": 1.5882,
"step": 403
},
{
"epoch": 0.08,
"learning_rate": 4.2741935483870973e-05,
"loss": 1.5586,
"step": 404
},
{
"epoch": 0.08,
"learning_rate": 4.2338709677419356e-05,
"loss": 1.615,
"step": 405
},
{
"epoch": 0.08,
"learning_rate": 4.1935483870967746e-05,
"loss": 1.8383,
"step": 406
},
{
"epoch": 0.08,
"learning_rate": 4.1532258064516135e-05,
"loss": 1.9046,
"step": 407
},
{
"epoch": 0.08,
"learning_rate": 4.112903225806452e-05,
"loss": 1.8287,
"step": 408
},
{
"epoch": 0.08,
"learning_rate": 4.072580645161291e-05,
"loss": 1.9579,
"step": 409
},
{
"epoch": 0.08,
"learning_rate": 4.032258064516129e-05,
"loss": 1.8904,
"step": 410
},
{
"epoch": 0.08,
"learning_rate": 3.991935483870968e-05,
"loss": 1.8667,
"step": 411
},
{
"epoch": 0.08,
"learning_rate": 3.951612903225806e-05,
"loss": 1.9754,
"step": 412
},
{
"epoch": 0.08,
"learning_rate": 3.911290322580645e-05,
"loss": 1.983,
"step": 413
},
{
"epoch": 0.08,
"learning_rate": 3.870967741935484e-05,
"loss": 1.7894,
"step": 414
},
{
"epoch": 0.08,
"learning_rate": 3.8306451612903224e-05,
"loss": 1.9031,
"step": 415
},
{
"epoch": 0.08,
"learning_rate": 3.7903225806451614e-05,
"loss": 1.7932,
"step": 416
},
{
"epoch": 0.08,
"learning_rate": 3.7500000000000003e-05,
"loss": 1.9418,
"step": 417
},
{
"epoch": 0.08,
"learning_rate": 3.7096774193548386e-05,
"loss": 1.7507,
"step": 418
},
{
"epoch": 0.08,
"learning_rate": 3.6693548387096776e-05,
"loss": 1.9235,
"step": 419
},
{
"epoch": 0.08,
"learning_rate": 3.6290322580645165e-05,
"loss": 1.759,
"step": 420
},
{
"epoch": 0.08,
"learning_rate": 3.5887096774193555e-05,
"loss": 1.7274,
"step": 421
},
{
"epoch": 0.08,
"learning_rate": 3.548387096774194e-05,
"loss": 1.8985,
"step": 422
},
{
"epoch": 0.08,
"learning_rate": 3.508064516129033e-05,
"loss": 1.7546,
"step": 423
},
{
"epoch": 0.08,
"learning_rate": 3.467741935483872e-05,
"loss": 1.6047,
"step": 424
},
{
"epoch": 0.08,
"learning_rate": 3.427419354838709e-05,
"loss": 1.9262,
"step": 425
},
{
"epoch": 0.08,
"learning_rate": 3.387096774193548e-05,
"loss": 1.8559,
"step": 426
},
{
"epoch": 0.08,
"learning_rate": 3.346774193548387e-05,
"loss": 1.7824,
"step": 427
},
{
"epoch": 0.08,
"learning_rate": 3.306451612903226e-05,
"loss": 1.6361,
"step": 428
},
{
"epoch": 0.08,
"learning_rate": 3.2661290322580644e-05,
"loss": 1.6609,
"step": 429
},
{
"epoch": 0.08,
"learning_rate": 3.2258064516129034e-05,
"loss": 1.6655,
"step": 430
},
{
"epoch": 0.08,
"learning_rate": 3.185483870967742e-05,
"loss": 1.8693,
"step": 431
},
{
"epoch": 0.08,
"learning_rate": 3.1451612903225806e-05,
"loss": 1.8403,
"step": 432
},
{
"epoch": 0.08,
"learning_rate": 3.1048387096774195e-05,
"loss": 1.9332,
"step": 433
},
{
"epoch": 0.08,
"learning_rate": 3.0645161290322585e-05,
"loss": 1.7775,
"step": 434
},
{
"epoch": 0.08,
"learning_rate": 3.024193548387097e-05,
"loss": 1.9003,
"step": 435
},
{
"epoch": 0.08,
"learning_rate": 2.9838709677419357e-05,
"loss": 1.8671,
"step": 436
},
{
"epoch": 0.08,
"learning_rate": 2.9435483870967743e-05,
"loss": 1.7864,
"step": 437
},
{
"epoch": 0.08,
"learning_rate": 2.9032258064516133e-05,
"loss": 2.0316,
"step": 438
},
{
"epoch": 0.08,
"learning_rate": 2.862903225806452e-05,
"loss": 1.8689,
"step": 439
},
{
"epoch": 0.08,
"learning_rate": 2.822580645161291e-05,
"loss": 1.9074,
"step": 440
},
{
"epoch": 0.08,
"learning_rate": 2.7822580645161288e-05,
"loss": 1.6603,
"step": 441
},
{
"epoch": 0.08,
"learning_rate": 2.7419354838709678e-05,
"loss": 1.9507,
"step": 442
},
{
"epoch": 0.08,
"learning_rate": 2.7016129032258064e-05,
"loss": 1.929,
"step": 443
},
{
"epoch": 0.08,
"learning_rate": 2.661290322580645e-05,
"loss": 1.8807,
"step": 444
},
{
"epoch": 0.08,
"learning_rate": 2.620967741935484e-05,
"loss": 1.8871,
"step": 445
},
{
"epoch": 0.08,
"learning_rate": 2.5806451612903226e-05,
"loss": 1.8061,
"step": 446
},
{
"epoch": 0.08,
"learning_rate": 2.5403225806451615e-05,
"loss": 1.8968,
"step": 447
},
{
"epoch": 0.08,
"learning_rate": 2.5e-05,
"loss": 1.7265,
"step": 448
},
{
"epoch": 0.08,
"learning_rate": 2.4596774193548387e-05,
"loss": 1.9261,
"step": 449
},
{
"epoch": 0.09,
"learning_rate": 2.4193548387096777e-05,
"loss": 1.7733,
"step": 450
},
{
"epoch": 0.09,
"learning_rate": 2.3790322580645163e-05,
"loss": 1.6785,
"step": 451
},
{
"epoch": 0.09,
"learning_rate": 2.338709677419355e-05,
"loss": 1.6109,
"step": 452
},
{
"epoch": 0.09,
"learning_rate": 2.2983870967741935e-05,
"loss": 1.5554,
"step": 453
},
{
"epoch": 0.09,
"learning_rate": 2.258064516129032e-05,
"loss": 1.5901,
"step": 454
},
{
"epoch": 0.09,
"learning_rate": 2.217741935483871e-05,
"loss": 1.687,
"step": 455
},
{
"epoch": 0.09,
"learning_rate": 2.1774193548387097e-05,
"loss": 1.7672,
"step": 456
},
{
"epoch": 0.09,
"learning_rate": 2.1370967741935487e-05,
"loss": 1.9025,
"step": 457
},
{
"epoch": 0.09,
"learning_rate": 2.0967741935483873e-05,
"loss": 1.804,
"step": 458
},
{
"epoch": 0.09,
"learning_rate": 2.056451612903226e-05,
"loss": 1.725,
"step": 459
},
{
"epoch": 0.09,
"learning_rate": 2.0161290322580645e-05,
"loss": 1.6565,
"step": 460
},
{
"epoch": 0.09,
"learning_rate": 1.975806451612903e-05,
"loss": 1.8996,
"step": 461
},
{
"epoch": 0.09,
"learning_rate": 1.935483870967742e-05,
"loss": 1.7974,
"step": 462
},
{
"epoch": 0.09,
"learning_rate": 1.8951612903225807e-05,
"loss": 1.8168,
"step": 463
},
{
"epoch": 0.09,
"learning_rate": 1.8548387096774193e-05,
"loss": 1.7012,
"step": 464
},
{
"epoch": 0.09,
"learning_rate": 1.8145161290322583e-05,
"loss": 1.9804,
"step": 465
},
{
"epoch": 0.09,
"learning_rate": 1.774193548387097e-05,
"loss": 1.7656,
"step": 466
},
{
"epoch": 0.09,
"learning_rate": 1.733870967741936e-05,
"loss": 1.5495,
"step": 467
},
{
"epoch": 0.09,
"learning_rate": 1.693548387096774e-05,
"loss": 1.8389,
"step": 468
},
{
"epoch": 0.09,
"learning_rate": 1.653225806451613e-05,
"loss": 1.7781,
"step": 469
},
{
"epoch": 0.09,
"learning_rate": 1.6129032258064517e-05,
"loss": 1.6191,
"step": 470
},
{
"epoch": 0.09,
"learning_rate": 1.5725806451612903e-05,
"loss": 1.6805,
"step": 471
},
{
"epoch": 0.09,
"learning_rate": 1.5322580645161292e-05,
"loss": 1.9133,
"step": 472
},
{
"epoch": 0.09,
"learning_rate": 1.4919354838709679e-05,
"loss": 1.5507,
"step": 473
},
{
"epoch": 0.09,
"learning_rate": 1.4516129032258066e-05,
"loss": 2.0498,
"step": 474
},
{
"epoch": 0.09,
"learning_rate": 1.4112903225806454e-05,
"loss": 1.6849,
"step": 475
},
{
"epoch": 0.09,
"learning_rate": 1.3709677419354839e-05,
"loss": 1.9449,
"step": 476
},
{
"epoch": 0.09,
"learning_rate": 1.3306451612903225e-05,
"loss": 1.6432,
"step": 477
},
{
"epoch": 0.09,
"learning_rate": 1.2903225806451613e-05,
"loss": 1.725,
"step": 478
},
{
"epoch": 0.09,
"learning_rate": 1.25e-05,
"loss": 1.7214,
"step": 479
},
{
"epoch": 0.09,
"learning_rate": 1.2096774193548388e-05,
"loss": 1.9034,
"step": 480
},
{
"epoch": 0.09,
"learning_rate": 1.1693548387096775e-05,
"loss": 1.691,
"step": 481
},
{
"epoch": 0.09,
"learning_rate": 1.129032258064516e-05,
"loss": 2.1742,
"step": 482
},
{
"epoch": 0.09,
"learning_rate": 1.0887096774193549e-05,
"loss": 1.6739,
"step": 483
},
{
"epoch": 0.09,
"learning_rate": 1.0483870967741936e-05,
"loss": 1.7993,
"step": 484
},
{
"epoch": 0.09,
"learning_rate": 1.0080645161290323e-05,
"loss": 1.544,
"step": 485
},
{
"epoch": 0.09,
"learning_rate": 9.67741935483871e-06,
"loss": 1.8974,
"step": 486
},
{
"epoch": 0.09,
"learning_rate": 9.274193548387097e-06,
"loss": 1.774,
"step": 487
},
{
"epoch": 0.09,
"learning_rate": 8.870967741935484e-06,
"loss": 1.4694,
"step": 488
},
{
"epoch": 0.09,
"learning_rate": 8.46774193548387e-06,
"loss": 1.7621,
"step": 489
},
{
"epoch": 0.09,
"learning_rate": 8.064516129032258e-06,
"loss": 1.7785,
"step": 490
},
{
"epoch": 0.09,
"learning_rate": 7.661290322580646e-06,
"loss": 2.0437,
"step": 491
},
{
"epoch": 0.09,
"learning_rate": 7.258064516129033e-06,
"loss": 1.7494,
"step": 492
},
{
"epoch": 0.09,
"learning_rate": 6.854838709677419e-06,
"loss": 1.7531,
"step": 493
},
{
"epoch": 0.09,
"learning_rate": 6.451612903225806e-06,
"loss": 1.9762,
"step": 494
},
{
"epoch": 0.09,
"learning_rate": 6.048387096774194e-06,
"loss": 1.6643,
"step": 495
},
{
"epoch": 0.09,
"learning_rate": 5.64516129032258e-06,
"loss": 1.8211,
"step": 496
},
{
"epoch": 0.09,
"learning_rate": 5.241935483870968e-06,
"loss": 1.6926,
"step": 497
},
{
"epoch": 0.09,
"learning_rate": 4.838709677419355e-06,
"loss": 1.8867,
"step": 498
},
{
"epoch": 0.09,
"learning_rate": 4.435483870967742e-06,
"loss": 1.6068,
"step": 499
},
{
"epoch": 0.09,
"learning_rate": 4.032258064516129e-06,
"loss": 1.6741,
"step": 500
}
],
"logging_steps": 1,
"max_steps": 501,
"num_train_epochs": 1,
"save_steps": 25,
"total_flos": 2.396005929934848e+16,
"trial_name": null,
"trial_params": null
}