nutorbit's picture
Training in progress, step 150, checkpoint
334213e
raw
history blame
18.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.028358067870309103,
"eval_steps": 1000,
"global_step": 150,
"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": 2.0452,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 8e-05,
"loss": 2.1339,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 0.00012,
"loss": 2.1537,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 0.00016,
"loss": 1.9245,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 1.6188,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 0.0001995967741935484,
"loss": 1.9631,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 0.0001991935483870968,
"loss": 1.8202,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 0.00019879032258064515,
"loss": 1.7829,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 0.00019838709677419357,
"loss": 1.6106,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 0.00019798387096774193,
"loss": 1.8472,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 0.00019758064516129035,
"loss": 1.752,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 0.0001971774193548387,
"loss": 1.8356,
"step": 12
},
{
"epoch": 0.0,
"learning_rate": 0.0001967741935483871,
"loss": 1.7975,
"step": 13
},
{
"epoch": 0.0,
"learning_rate": 0.0001963709677419355,
"loss": 1.6779,
"step": 14
},
{
"epoch": 0.0,
"learning_rate": 0.00019596774193548388,
"loss": 1.6186,
"step": 15
},
{
"epoch": 0.0,
"learning_rate": 0.00019556451612903227,
"loss": 1.6386,
"step": 16
},
{
"epoch": 0.0,
"learning_rate": 0.00019556451612903227,
"loss": 1.5367,
"step": 17
},
{
"epoch": 0.0,
"learning_rate": 0.00019516129032258066,
"loss": 1.7151,
"step": 18
},
{
"epoch": 0.0,
"learning_rate": 0.00019475806451612905,
"loss": 1.7181,
"step": 19
},
{
"epoch": 0.0,
"learning_rate": 0.00019435483870967744,
"loss": 1.8218,
"step": 20
},
{
"epoch": 0.0,
"learning_rate": 0.0001939516129032258,
"loss": 1.3944,
"step": 21
},
{
"epoch": 0.0,
"learning_rate": 0.0001939516129032258,
"loss": 1.5311,
"step": 22
},
{
"epoch": 0.0,
"learning_rate": 0.00019354838709677422,
"loss": 1.8437,
"step": 23
},
{
"epoch": 0.0,
"learning_rate": 0.00019314516129032258,
"loss": 1.7631,
"step": 24
},
{
"epoch": 0.0,
"learning_rate": 0.000192741935483871,
"loss": 1.6397,
"step": 25
},
{
"epoch": 0.0,
"learning_rate": 0.00019233870967741936,
"loss": 1.6021,
"step": 26
},
{
"epoch": 0.01,
"learning_rate": 0.00019193548387096775,
"loss": 1.5021,
"step": 27
},
{
"epoch": 0.01,
"learning_rate": 0.00019153225806451614,
"loss": 1.4953,
"step": 28
},
{
"epoch": 0.01,
"learning_rate": 0.00019112903225806453,
"loss": 1.8371,
"step": 29
},
{
"epoch": 0.01,
"learning_rate": 0.00019072580645161291,
"loss": 1.9104,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 0.0001903225806451613,
"loss": 1.8631,
"step": 31
},
{
"epoch": 0.01,
"learning_rate": 0.0001899193548387097,
"loss": 1.6603,
"step": 32
},
{
"epoch": 0.01,
"learning_rate": 0.00018951612903225808,
"loss": 1.713,
"step": 33
},
{
"epoch": 0.01,
"learning_rate": 0.00018911290322580645,
"loss": 1.6329,
"step": 34
},
{
"epoch": 0.01,
"learning_rate": 0.00018870967741935486,
"loss": 1.5225,
"step": 35
},
{
"epoch": 0.01,
"learning_rate": 0.00018830645161290322,
"loss": 1.7089,
"step": 36
},
{
"epoch": 0.01,
"learning_rate": 0.00018790322580645164,
"loss": 1.497,
"step": 37
},
{
"epoch": 0.01,
"learning_rate": 0.0001875,
"loss": 1.6165,
"step": 38
},
{
"epoch": 0.01,
"learning_rate": 0.0001870967741935484,
"loss": 1.6202,
"step": 39
},
{
"epoch": 0.01,
"learning_rate": 0.00018669354838709678,
"loss": 1.712,
"step": 40
},
{
"epoch": 0.01,
"learning_rate": 0.00018629032258064517,
"loss": 1.7133,
"step": 41
},
{
"epoch": 0.01,
"learning_rate": 0.00018588709677419356,
"loss": 1.6171,
"step": 42
},
{
"epoch": 0.01,
"learning_rate": 0.00018548387096774192,
"loss": 1.4604,
"step": 43
},
{
"epoch": 0.01,
"learning_rate": 0.00018508064516129034,
"loss": 1.4851,
"step": 44
},
{
"epoch": 0.01,
"learning_rate": 0.0001846774193548387,
"loss": 1.6546,
"step": 45
},
{
"epoch": 0.01,
"learning_rate": 0.00018427419354838712,
"loss": 1.7893,
"step": 46
},
{
"epoch": 0.01,
"learning_rate": 0.00018387096774193548,
"loss": 1.7062,
"step": 47
},
{
"epoch": 0.01,
"learning_rate": 0.00018346774193548387,
"loss": 1.623,
"step": 48
},
{
"epoch": 0.01,
"learning_rate": 0.00018306451612903226,
"loss": 1.6374,
"step": 49
},
{
"epoch": 0.01,
"learning_rate": 0.00018266129032258065,
"loss": 1.6614,
"step": 50
},
{
"epoch": 0.01,
"learning_rate": 0.00018225806451612904,
"loss": 1.4882,
"step": 51
},
{
"epoch": 0.01,
"learning_rate": 0.00018185483870967743,
"loss": 1.6825,
"step": 52
},
{
"epoch": 0.01,
"learning_rate": 0.00018145161290322582,
"loss": 1.7217,
"step": 53
},
{
"epoch": 0.01,
"learning_rate": 0.0001810483870967742,
"loss": 1.6998,
"step": 54
},
{
"epoch": 0.01,
"learning_rate": 0.00018064516129032257,
"loss": 1.501,
"step": 55
},
{
"epoch": 0.01,
"learning_rate": 0.000180241935483871,
"loss": 1.5068,
"step": 56
},
{
"epoch": 0.01,
"learning_rate": 0.00017983870967741935,
"loss": 1.5879,
"step": 57
},
{
"epoch": 0.01,
"learning_rate": 0.00017943548387096777,
"loss": 1.583,
"step": 58
},
{
"epoch": 0.01,
"learning_rate": 0.00017903225806451613,
"loss": 1.6105,
"step": 59
},
{
"epoch": 0.01,
"learning_rate": 0.00017862903225806452,
"loss": 1.6217,
"step": 60
},
{
"epoch": 0.01,
"learning_rate": 0.0001782258064516129,
"loss": 1.5975,
"step": 61
},
{
"epoch": 0.01,
"learning_rate": 0.0001778225806451613,
"loss": 1.4892,
"step": 62
},
{
"epoch": 0.01,
"learning_rate": 0.0001774193548387097,
"loss": 1.6847,
"step": 63
},
{
"epoch": 0.01,
"learning_rate": 0.00017701612903225808,
"loss": 1.6837,
"step": 64
},
{
"epoch": 0.01,
"learning_rate": 0.00017661290322580647,
"loss": 1.6239,
"step": 65
},
{
"epoch": 0.01,
"learning_rate": 0.00017620967741935486,
"loss": 1.7792,
"step": 66
},
{
"epoch": 0.01,
"learning_rate": 0.00017580645161290325,
"loss": 1.7764,
"step": 67
},
{
"epoch": 0.01,
"learning_rate": 0.00017540322580645164,
"loss": 1.5387,
"step": 68
},
{
"epoch": 0.01,
"learning_rate": 0.000175,
"loss": 1.6544,
"step": 69
},
{
"epoch": 0.01,
"learning_rate": 0.0001745967741935484,
"loss": 1.6512,
"step": 70
},
{
"epoch": 0.01,
"learning_rate": 0.00017419354838709678,
"loss": 1.9079,
"step": 71
},
{
"epoch": 0.01,
"learning_rate": 0.00017379032258064517,
"loss": 1.6991,
"step": 72
},
{
"epoch": 0.01,
"learning_rate": 0.00017338709677419356,
"loss": 1.7934,
"step": 73
},
{
"epoch": 0.01,
"learning_rate": 0.00017298387096774195,
"loss": 1.6651,
"step": 74
},
{
"epoch": 0.01,
"learning_rate": 0.00017258064516129034,
"loss": 1.7393,
"step": 75
},
{
"epoch": 0.01,
"learning_rate": 0.0001721774193548387,
"loss": 1.7071,
"step": 76
},
{
"epoch": 0.01,
"learning_rate": 0.00017177419354838711,
"loss": 1.5009,
"step": 77
},
{
"epoch": 0.01,
"learning_rate": 0.00017137096774193548,
"loss": 1.658,
"step": 78
},
{
"epoch": 0.01,
"learning_rate": 0.0001709677419354839,
"loss": 1.6428,
"step": 79
},
{
"epoch": 0.02,
"learning_rate": 0.00017056451612903226,
"loss": 1.7405,
"step": 80
},
{
"epoch": 0.02,
"learning_rate": 0.00017016129032258065,
"loss": 1.7162,
"step": 81
},
{
"epoch": 0.02,
"learning_rate": 0.00016975806451612904,
"loss": 1.6236,
"step": 82
},
{
"epoch": 0.02,
"learning_rate": 0.00016935483870967742,
"loss": 1.5788,
"step": 83
},
{
"epoch": 0.02,
"learning_rate": 0.00016895161290322581,
"loss": 1.5383,
"step": 84
},
{
"epoch": 0.02,
"learning_rate": 0.0001685483870967742,
"loss": 1.8091,
"step": 85
},
{
"epoch": 0.02,
"learning_rate": 0.0001681451612903226,
"loss": 1.4177,
"step": 86
},
{
"epoch": 0.02,
"learning_rate": 0.00016774193548387098,
"loss": 1.6378,
"step": 87
},
{
"epoch": 0.02,
"learning_rate": 0.00016733870967741935,
"loss": 1.5325,
"step": 88
},
{
"epoch": 0.02,
"learning_rate": 0.00016693548387096776,
"loss": 1.4395,
"step": 89
},
{
"epoch": 0.02,
"learning_rate": 0.00016653225806451612,
"loss": 1.577,
"step": 90
},
{
"epoch": 0.02,
"learning_rate": 0.00016612903225806454,
"loss": 1.7508,
"step": 91
},
{
"epoch": 0.02,
"learning_rate": 0.0001657258064516129,
"loss": 1.5263,
"step": 92
},
{
"epoch": 0.02,
"learning_rate": 0.00016532258064516132,
"loss": 1.6134,
"step": 93
},
{
"epoch": 0.02,
"learning_rate": 0.00016491935483870968,
"loss": 1.9328,
"step": 94
},
{
"epoch": 0.02,
"learning_rate": 0.00016451612903225807,
"loss": 1.7819,
"step": 95
},
{
"epoch": 0.02,
"learning_rate": 0.00016411290322580646,
"loss": 1.8635,
"step": 96
},
{
"epoch": 0.02,
"learning_rate": 0.00016370967741935485,
"loss": 1.4804,
"step": 97
},
{
"epoch": 0.02,
"learning_rate": 0.00016330645161290324,
"loss": 1.6171,
"step": 98
},
{
"epoch": 0.02,
"learning_rate": 0.00016290322580645163,
"loss": 1.6722,
"step": 99
},
{
"epoch": 0.02,
"learning_rate": 0.00016250000000000002,
"loss": 1.5711,
"step": 100
},
{
"epoch": 0.02,
"learning_rate": 0.00016209677419354838,
"loss": 1.6117,
"step": 101
},
{
"epoch": 0.02,
"learning_rate": 0.00016169354838709677,
"loss": 1.6901,
"step": 102
},
{
"epoch": 0.02,
"learning_rate": 0.00016129032258064516,
"loss": 1.8487,
"step": 103
},
{
"epoch": 0.02,
"learning_rate": 0.00016088709677419355,
"loss": 1.6705,
"step": 104
},
{
"epoch": 0.02,
"learning_rate": 0.00016048387096774194,
"loss": 1.5581,
"step": 105
},
{
"epoch": 0.02,
"learning_rate": 0.00016008064516129033,
"loss": 1.4694,
"step": 106
},
{
"epoch": 0.02,
"learning_rate": 0.00015967741935483872,
"loss": 1.4355,
"step": 107
},
{
"epoch": 0.02,
"learning_rate": 0.0001592741935483871,
"loss": 1.4237,
"step": 108
},
{
"epoch": 0.02,
"learning_rate": 0.00015887096774193547,
"loss": 1.6782,
"step": 109
},
{
"epoch": 0.02,
"learning_rate": 0.0001584677419354839,
"loss": 1.4701,
"step": 110
},
{
"epoch": 0.02,
"learning_rate": 0.00015806451612903225,
"loss": 1.7806,
"step": 111
},
{
"epoch": 0.02,
"learning_rate": 0.00015766129032258067,
"loss": 1.5857,
"step": 112
},
{
"epoch": 0.02,
"learning_rate": 0.00015725806451612903,
"loss": 1.7187,
"step": 113
},
{
"epoch": 0.02,
"learning_rate": 0.00015685483870967742,
"loss": 1.6985,
"step": 114
},
{
"epoch": 0.02,
"learning_rate": 0.0001564516129032258,
"loss": 1.809,
"step": 115
},
{
"epoch": 0.02,
"learning_rate": 0.0001560483870967742,
"loss": 1.6915,
"step": 116
},
{
"epoch": 0.02,
"learning_rate": 0.0001556451612903226,
"loss": 1.6854,
"step": 117
},
{
"epoch": 0.02,
"learning_rate": 0.00015524193548387098,
"loss": 1.6484,
"step": 118
},
{
"epoch": 0.02,
"learning_rate": 0.00015483870967741937,
"loss": 1.6628,
"step": 119
},
{
"epoch": 0.02,
"learning_rate": 0.00015443548387096776,
"loss": 1.6994,
"step": 120
},
{
"epoch": 0.02,
"learning_rate": 0.00015403225806451615,
"loss": 1.7657,
"step": 121
},
{
"epoch": 0.02,
"learning_rate": 0.00015362903225806454,
"loss": 1.5611,
"step": 122
},
{
"epoch": 0.02,
"learning_rate": 0.0001532258064516129,
"loss": 1.5338,
"step": 123
},
{
"epoch": 0.02,
"learning_rate": 0.00015282258064516131,
"loss": 1.7617,
"step": 124
},
{
"epoch": 0.02,
"learning_rate": 0.00015241935483870968,
"loss": 1.67,
"step": 125
},
{
"epoch": 0.02,
"learning_rate": 0.0001520161290322581,
"loss": 1.7283,
"step": 126
},
{
"epoch": 0.02,
"learning_rate": 0.00015161290322580646,
"loss": 1.7582,
"step": 127
},
{
"epoch": 0.02,
"learning_rate": 0.00015120967741935485,
"loss": 1.3957,
"step": 128
},
{
"epoch": 0.02,
"learning_rate": 0.00015080645161290323,
"loss": 1.6221,
"step": 129
},
{
"epoch": 0.02,
"learning_rate": 0.00015040322580645162,
"loss": 1.7759,
"step": 130
},
{
"epoch": 0.02,
"learning_rate": 0.00015000000000000001,
"loss": 1.7331,
"step": 131
},
{
"epoch": 0.02,
"learning_rate": 0.00014959677419354838,
"loss": 1.6689,
"step": 132
},
{
"epoch": 0.03,
"learning_rate": 0.0001491935483870968,
"loss": 1.5734,
"step": 133
},
{
"epoch": 0.03,
"learning_rate": 0.00014879032258064516,
"loss": 1.6629,
"step": 134
},
{
"epoch": 0.03,
"learning_rate": 0.00014838709677419355,
"loss": 1.6368,
"step": 135
},
{
"epoch": 0.03,
"learning_rate": 0.00014798387096774193,
"loss": 1.742,
"step": 136
},
{
"epoch": 0.03,
"learning_rate": 0.00014758064516129032,
"loss": 1.4901,
"step": 137
},
{
"epoch": 0.03,
"learning_rate": 0.00014717741935483871,
"loss": 1.6417,
"step": 138
},
{
"epoch": 0.03,
"learning_rate": 0.0001467741935483871,
"loss": 1.6693,
"step": 139
},
{
"epoch": 0.03,
"learning_rate": 0.0001463709677419355,
"loss": 1.588,
"step": 140
},
{
"epoch": 0.03,
"learning_rate": 0.00014596774193548388,
"loss": 1.6614,
"step": 141
},
{
"epoch": 0.03,
"learning_rate": 0.00014556451612903224,
"loss": 1.7408,
"step": 142
},
{
"epoch": 0.03,
"learning_rate": 0.00014516129032258066,
"loss": 1.7049,
"step": 143
},
{
"epoch": 0.03,
"learning_rate": 0.00014475806451612902,
"loss": 1.2828,
"step": 144
},
{
"epoch": 0.03,
"learning_rate": 0.00014435483870967744,
"loss": 1.7891,
"step": 145
},
{
"epoch": 0.03,
"learning_rate": 0.0001439516129032258,
"loss": 1.7558,
"step": 146
},
{
"epoch": 0.03,
"learning_rate": 0.00014354838709677422,
"loss": 1.8506,
"step": 147
},
{
"epoch": 0.03,
"learning_rate": 0.00014314516129032258,
"loss": 1.7095,
"step": 148
},
{
"epoch": 0.03,
"learning_rate": 0.00014274193548387097,
"loss": 1.7061,
"step": 149
},
{
"epoch": 0.03,
"learning_rate": 0.00014233870967741936,
"loss": 1.4998,
"step": 150
}
],
"logging_steps": 1,
"max_steps": 501,
"num_train_epochs": 1,
"save_steps": 25,
"total_flos": 9333394508070912.0,
"trial_name": null,
"trial_params": null
}