TachyHealthResearch's picture
Training in progress, step 150, checkpoint
d8f597c
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.06,
"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": 6.666666666666667e-05,
"loss": 2.4138,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 0.00013333333333333334,
"loss": 2.3782,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 0.0002,
"loss": 2.1039,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 0.00019863945578231293,
"loss": 2.4971,
"step": 4
},
{
"epoch": 0.0,
"learning_rate": 0.00019727891156462587,
"loss": 2.1249,
"step": 5
},
{
"epoch": 0.0,
"learning_rate": 0.0001959183673469388,
"loss": 2.649,
"step": 6
},
{
"epoch": 0.0,
"learning_rate": 0.0001945578231292517,
"loss": 2.9032,
"step": 7
},
{
"epoch": 0.0,
"learning_rate": 0.00019319727891156462,
"loss": 1.8552,
"step": 8
},
{
"epoch": 0.0,
"learning_rate": 0.00019183673469387756,
"loss": 2.3256,
"step": 9
},
{
"epoch": 0.0,
"learning_rate": 0.00019047619047619048,
"loss": 2.4122,
"step": 10
},
{
"epoch": 0.0,
"learning_rate": 0.00018911564625850343,
"loss": 2.0678,
"step": 11
},
{
"epoch": 0.0,
"learning_rate": 0.00018775510204081634,
"loss": 2.3379,
"step": 12
},
{
"epoch": 0.01,
"learning_rate": 0.00018639455782312926,
"loss": 2.1801,
"step": 13
},
{
"epoch": 0.01,
"learning_rate": 0.0001850340136054422,
"loss": 2.1896,
"step": 14
},
{
"epoch": 0.01,
"learning_rate": 0.00018367346938775512,
"loss": 2.0319,
"step": 15
},
{
"epoch": 0.01,
"learning_rate": 0.00018231292517006804,
"loss": 1.9579,
"step": 16
},
{
"epoch": 0.01,
"learning_rate": 0.00018095238095238095,
"loss": 2.1247,
"step": 17
},
{
"epoch": 0.01,
"learning_rate": 0.0001795918367346939,
"loss": 2.8723,
"step": 18
},
{
"epoch": 0.01,
"learning_rate": 0.00017823129251700681,
"loss": 1.8466,
"step": 19
},
{
"epoch": 0.01,
"learning_rate": 0.00017687074829931973,
"loss": 2.3306,
"step": 20
},
{
"epoch": 0.01,
"learning_rate": 0.00017551020408163265,
"loss": 2.3662,
"step": 21
},
{
"epoch": 0.01,
"learning_rate": 0.0001741496598639456,
"loss": 2.1281,
"step": 22
},
{
"epoch": 0.01,
"learning_rate": 0.0001727891156462585,
"loss": 2.0371,
"step": 23
},
{
"epoch": 0.01,
"learning_rate": 0.00017142857142857143,
"loss": 2.4064,
"step": 24
},
{
"epoch": 0.01,
"learning_rate": 0.00017006802721088434,
"loss": 1.8651,
"step": 25
},
{
"epoch": 0.01,
"learning_rate": 0.00016870748299319729,
"loss": 2.2024,
"step": 26
},
{
"epoch": 0.01,
"learning_rate": 0.00016734693877551023,
"loss": 1.8373,
"step": 27
},
{
"epoch": 0.01,
"learning_rate": 0.00016598639455782315,
"loss": 1.8414,
"step": 28
},
{
"epoch": 0.01,
"learning_rate": 0.00016462585034013606,
"loss": 2.0103,
"step": 29
},
{
"epoch": 0.01,
"learning_rate": 0.00016326530612244898,
"loss": 1.8933,
"step": 30
},
{
"epoch": 0.01,
"learning_rate": 0.00016190476190476192,
"loss": 1.9478,
"step": 31
},
{
"epoch": 0.01,
"learning_rate": 0.00016054421768707484,
"loss": 1.7242,
"step": 32
},
{
"epoch": 0.01,
"learning_rate": 0.00015918367346938776,
"loss": 2.6501,
"step": 33
},
{
"epoch": 0.01,
"learning_rate": 0.00015782312925170067,
"loss": 1.9442,
"step": 34
},
{
"epoch": 0.01,
"learning_rate": 0.00015646258503401362,
"loss": 2.097,
"step": 35
},
{
"epoch": 0.01,
"learning_rate": 0.00015510204081632654,
"loss": 1.9518,
"step": 36
},
{
"epoch": 0.01,
"learning_rate": 0.00015374149659863945,
"loss": 2.0381,
"step": 37
},
{
"epoch": 0.02,
"learning_rate": 0.00015238095238095237,
"loss": 2.1018,
"step": 38
},
{
"epoch": 0.02,
"learning_rate": 0.0001510204081632653,
"loss": 2.6064,
"step": 39
},
{
"epoch": 0.02,
"learning_rate": 0.00014965986394557826,
"loss": 1.8832,
"step": 40
},
{
"epoch": 0.02,
"learning_rate": 0.00014829931972789117,
"loss": 1.7176,
"step": 41
},
{
"epoch": 0.02,
"learning_rate": 0.0001469387755102041,
"loss": 1.9294,
"step": 42
},
{
"epoch": 0.02,
"learning_rate": 0.000145578231292517,
"loss": 2.2566,
"step": 43
},
{
"epoch": 0.02,
"learning_rate": 0.00014421768707482995,
"loss": 2.0185,
"step": 44
},
{
"epoch": 0.02,
"learning_rate": 0.00014285714285714287,
"loss": 1.9994,
"step": 45
},
{
"epoch": 0.02,
"learning_rate": 0.00014149659863945578,
"loss": 1.8176,
"step": 46
},
{
"epoch": 0.02,
"learning_rate": 0.0001401360544217687,
"loss": 2.2882,
"step": 47
},
{
"epoch": 0.02,
"learning_rate": 0.00013877551020408165,
"loss": 1.9445,
"step": 48
},
{
"epoch": 0.02,
"learning_rate": 0.00013741496598639456,
"loss": 2.1634,
"step": 49
},
{
"epoch": 0.02,
"learning_rate": 0.00013605442176870748,
"loss": 1.7348,
"step": 50
},
{
"epoch": 0.02,
"learning_rate": 0.0001346938775510204,
"loss": 2.1267,
"step": 51
},
{
"epoch": 0.02,
"learning_rate": 0.00013333333333333334,
"loss": 2.0458,
"step": 52
},
{
"epoch": 0.02,
"learning_rate": 0.00013197278911564626,
"loss": 1.8534,
"step": 53
},
{
"epoch": 0.02,
"learning_rate": 0.00013061224489795917,
"loss": 1.6838,
"step": 54
},
{
"epoch": 0.02,
"learning_rate": 0.00012925170068027212,
"loss": 1.896,
"step": 55
},
{
"epoch": 0.02,
"learning_rate": 0.00012789115646258506,
"loss": 2.2231,
"step": 56
},
{
"epoch": 0.02,
"learning_rate": 0.00012653061224489798,
"loss": 2.0001,
"step": 57
},
{
"epoch": 0.02,
"learning_rate": 0.0001251700680272109,
"loss": 1.9079,
"step": 58
},
{
"epoch": 0.02,
"learning_rate": 0.0001238095238095238,
"loss": 2.2205,
"step": 59
},
{
"epoch": 0.02,
"learning_rate": 0.00012244897959183676,
"loss": 2.1606,
"step": 60
},
{
"epoch": 0.02,
"learning_rate": 0.00012108843537414967,
"loss": 2.1003,
"step": 61
},
{
"epoch": 0.02,
"learning_rate": 0.00011972789115646259,
"loss": 2.0567,
"step": 62
},
{
"epoch": 0.03,
"learning_rate": 0.00011836734693877552,
"loss": 1.8886,
"step": 63
},
{
"epoch": 0.03,
"learning_rate": 0.00011700680272108844,
"loss": 1.565,
"step": 64
},
{
"epoch": 0.03,
"learning_rate": 0.00011564625850340137,
"loss": 1.7418,
"step": 65
},
{
"epoch": 0.03,
"learning_rate": 0.00011428571428571428,
"loss": 2.2,
"step": 66
},
{
"epoch": 0.03,
"learning_rate": 0.00011292517006802721,
"loss": 1.8804,
"step": 67
},
{
"epoch": 0.03,
"learning_rate": 0.00011156462585034013,
"loss": 1.8546,
"step": 68
},
{
"epoch": 0.03,
"learning_rate": 0.00011020408163265306,
"loss": 1.9946,
"step": 69
},
{
"epoch": 0.03,
"learning_rate": 0.000108843537414966,
"loss": 1.9766,
"step": 70
},
{
"epoch": 0.03,
"learning_rate": 0.00010748299319727892,
"loss": 2.5233,
"step": 71
},
{
"epoch": 0.03,
"learning_rate": 0.00010612244897959185,
"loss": 2.1251,
"step": 72
},
{
"epoch": 0.03,
"learning_rate": 0.00010476190476190477,
"loss": 1.6734,
"step": 73
},
{
"epoch": 0.03,
"learning_rate": 0.0001034013605442177,
"loss": 1.7247,
"step": 74
},
{
"epoch": 0.03,
"learning_rate": 0.00010204081632653062,
"loss": 1.7936,
"step": 75
},
{
"epoch": 0.03,
"learning_rate": 0.00010068027210884355,
"loss": 2.1881,
"step": 76
},
{
"epoch": 0.03,
"learning_rate": 9.931972789115646e-05,
"loss": 2.1806,
"step": 77
},
{
"epoch": 0.03,
"learning_rate": 9.79591836734694e-05,
"loss": 1.7475,
"step": 78
},
{
"epoch": 0.03,
"learning_rate": 9.659863945578231e-05,
"loss": 1.8856,
"step": 79
},
{
"epoch": 0.03,
"learning_rate": 9.523809523809524e-05,
"loss": 1.9571,
"step": 80
},
{
"epoch": 0.03,
"learning_rate": 9.387755102040817e-05,
"loss": 1.773,
"step": 81
},
{
"epoch": 0.03,
"learning_rate": 9.25170068027211e-05,
"loss": 2.0793,
"step": 82
},
{
"epoch": 0.03,
"learning_rate": 9.115646258503402e-05,
"loss": 1.6465,
"step": 83
},
{
"epoch": 0.03,
"learning_rate": 8.979591836734695e-05,
"loss": 2.3302,
"step": 84
},
{
"epoch": 0.03,
"learning_rate": 8.843537414965987e-05,
"loss": 1.9541,
"step": 85
},
{
"epoch": 0.03,
"learning_rate": 8.70748299319728e-05,
"loss": 1.9938,
"step": 86
},
{
"epoch": 0.03,
"learning_rate": 8.571428571428571e-05,
"loss": 1.7522,
"step": 87
},
{
"epoch": 0.04,
"learning_rate": 8.435374149659864e-05,
"loss": 2.1434,
"step": 88
},
{
"epoch": 0.04,
"learning_rate": 8.299319727891157e-05,
"loss": 2.1333,
"step": 89
},
{
"epoch": 0.04,
"learning_rate": 8.163265306122449e-05,
"loss": 2.2407,
"step": 90
},
{
"epoch": 0.04,
"learning_rate": 8.027210884353742e-05,
"loss": 1.8978,
"step": 91
},
{
"epoch": 0.04,
"learning_rate": 7.891156462585034e-05,
"loss": 1.2992,
"step": 92
},
{
"epoch": 0.04,
"learning_rate": 7.755102040816327e-05,
"loss": 1.9454,
"step": 93
},
{
"epoch": 0.04,
"learning_rate": 7.619047619047618e-05,
"loss": 2.5311,
"step": 94
},
{
"epoch": 0.04,
"learning_rate": 7.482993197278913e-05,
"loss": 1.753,
"step": 95
},
{
"epoch": 0.04,
"learning_rate": 7.346938775510205e-05,
"loss": 1.8511,
"step": 96
},
{
"epoch": 0.04,
"learning_rate": 7.210884353741498e-05,
"loss": 1.96,
"step": 97
},
{
"epoch": 0.04,
"learning_rate": 7.074829931972789e-05,
"loss": 1.8998,
"step": 98
},
{
"epoch": 0.04,
"learning_rate": 6.938775510204082e-05,
"loss": 2.0674,
"step": 99
},
{
"epoch": 0.04,
"learning_rate": 6.802721088435374e-05,
"loss": 1.8385,
"step": 100
},
{
"epoch": 0.04,
"learning_rate": 6.666666666666667e-05,
"loss": 1.9221,
"step": 101
},
{
"epoch": 0.04,
"learning_rate": 6.530612244897959e-05,
"loss": 1.9015,
"step": 102
},
{
"epoch": 0.04,
"learning_rate": 6.394557823129253e-05,
"loss": 2.0576,
"step": 103
},
{
"epoch": 0.04,
"learning_rate": 6.258503401360545e-05,
"loss": 2.1968,
"step": 104
},
{
"epoch": 0.04,
"learning_rate": 6.122448979591838e-05,
"loss": 2.1305,
"step": 105
},
{
"epoch": 0.04,
"learning_rate": 5.9863945578231295e-05,
"loss": 1.7918,
"step": 106
},
{
"epoch": 0.04,
"learning_rate": 5.850340136054422e-05,
"loss": 1.8854,
"step": 107
},
{
"epoch": 0.04,
"learning_rate": 5.714285714285714e-05,
"loss": 1.8177,
"step": 108
},
{
"epoch": 0.04,
"learning_rate": 5.5782312925170065e-05,
"loss": 2.1727,
"step": 109
},
{
"epoch": 0.04,
"learning_rate": 5.4421768707483e-05,
"loss": 1.8914,
"step": 110
},
{
"epoch": 0.04,
"learning_rate": 5.3061224489795926e-05,
"loss": 1.7695,
"step": 111
},
{
"epoch": 0.04,
"learning_rate": 5.170068027210885e-05,
"loss": 1.8377,
"step": 112
},
{
"epoch": 0.05,
"learning_rate": 5.034013605442177e-05,
"loss": 2.294,
"step": 113
},
{
"epoch": 0.05,
"learning_rate": 4.89795918367347e-05,
"loss": 2.0519,
"step": 114
},
{
"epoch": 0.05,
"learning_rate": 4.761904761904762e-05,
"loss": 2.1649,
"step": 115
},
{
"epoch": 0.05,
"learning_rate": 4.625850340136055e-05,
"loss": 2.1548,
"step": 116
},
{
"epoch": 0.05,
"learning_rate": 4.4897959183673474e-05,
"loss": 2.0267,
"step": 117
},
{
"epoch": 0.05,
"learning_rate": 4.35374149659864e-05,
"loss": 2.036,
"step": 118
},
{
"epoch": 0.05,
"learning_rate": 4.217687074829932e-05,
"loss": 1.8979,
"step": 119
},
{
"epoch": 0.05,
"learning_rate": 4.0816326530612245e-05,
"loss": 1.6725,
"step": 120
},
{
"epoch": 0.05,
"learning_rate": 3.945578231292517e-05,
"loss": 1.6443,
"step": 121
},
{
"epoch": 0.05,
"learning_rate": 3.809523809523809e-05,
"loss": 2.0864,
"step": 122
},
{
"epoch": 0.05,
"learning_rate": 3.673469387755102e-05,
"loss": 1.7234,
"step": 123
},
{
"epoch": 0.05,
"learning_rate": 3.5374149659863946e-05,
"loss": 1.8916,
"step": 124
},
{
"epoch": 0.05,
"learning_rate": 3.401360544217687e-05,
"loss": 2.2922,
"step": 125
},
{
"epoch": 0.05,
"learning_rate": 3.265306122448979e-05,
"loss": 1.9379,
"step": 126
},
{
"epoch": 0.05,
"learning_rate": 3.1292517006802724e-05,
"loss": 2.0516,
"step": 127
},
{
"epoch": 0.05,
"learning_rate": 2.9931972789115647e-05,
"loss": 1.5403,
"step": 128
},
{
"epoch": 0.05,
"learning_rate": 2.857142857142857e-05,
"loss": 1.9823,
"step": 129
},
{
"epoch": 0.05,
"learning_rate": 2.72108843537415e-05,
"loss": 2.5569,
"step": 130
},
{
"epoch": 0.05,
"learning_rate": 2.5850340136054425e-05,
"loss": 2.0392,
"step": 131
},
{
"epoch": 0.05,
"learning_rate": 2.448979591836735e-05,
"loss": 1.3206,
"step": 132
},
{
"epoch": 0.05,
"learning_rate": 2.3129251700680275e-05,
"loss": 1.4851,
"step": 133
},
{
"epoch": 0.05,
"learning_rate": 2.17687074829932e-05,
"loss": 1.8076,
"step": 134
},
{
"epoch": 0.05,
"learning_rate": 2.0408163265306123e-05,
"loss": 2.2816,
"step": 135
},
{
"epoch": 0.05,
"learning_rate": 1.9047619047619046e-05,
"loss": 2.044,
"step": 136
},
{
"epoch": 0.05,
"learning_rate": 1.7687074829931973e-05,
"loss": 2.0136,
"step": 137
},
{
"epoch": 0.06,
"learning_rate": 1.6326530612244897e-05,
"loss": 1.5755,
"step": 138
},
{
"epoch": 0.06,
"learning_rate": 1.4965986394557824e-05,
"loss": 1.9756,
"step": 139
},
{
"epoch": 0.06,
"learning_rate": 1.360544217687075e-05,
"loss": 1.9262,
"step": 140
},
{
"epoch": 0.06,
"learning_rate": 1.2244897959183674e-05,
"loss": 1.8739,
"step": 141
},
{
"epoch": 0.06,
"learning_rate": 1.08843537414966e-05,
"loss": 1.8307,
"step": 142
},
{
"epoch": 0.06,
"learning_rate": 9.523809523809523e-06,
"loss": 1.8247,
"step": 143
},
{
"epoch": 0.06,
"learning_rate": 8.163265306122448e-06,
"loss": 1.8952,
"step": 144
},
{
"epoch": 0.06,
"learning_rate": 6.802721088435375e-06,
"loss": 1.8041,
"step": 145
},
{
"epoch": 0.06,
"learning_rate": 5.4421768707483e-06,
"loss": 1.8557,
"step": 146
},
{
"epoch": 0.06,
"learning_rate": 4.081632653061224e-06,
"loss": 1.9398,
"step": 147
},
{
"epoch": 0.06,
"learning_rate": 2.72108843537415e-06,
"loss": 1.944,
"step": 148
},
{
"epoch": 0.06,
"learning_rate": 1.360544217687075e-06,
"loss": 2.0813,
"step": 149
},
{
"epoch": 0.06,
"learning_rate": 0.0,
"loss": 1.8519,
"step": 150
}
],
"logging_steps": 1,
"max_steps": 150,
"num_train_epochs": 1,
"save_steps": 5,
"total_flos": 8125557976793088.0,
"trial_name": null,
"trial_params": null
}