onuralp's picture
Upload folder using huggingface_hub
e17ea8c
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 20,
"global_step": 668,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.3333333333333334e-06,
"loss": 2.8327,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 2.666666666666667e-06,
"loss": 3.0988,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 4.000000000000001e-06,
"loss": 2.6419,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 5.333333333333334e-06,
"loss": 2.381,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 6.666666666666667e-06,
"loss": 2.657,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 8.000000000000001e-06,
"loss": 2.408,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 9.333333333333334e-06,
"loss": 3.2158,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 1.0666666666666667e-05,
"loss": 2.2635,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 1.2e-05,
"loss": 1.9091,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.9039,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 1.4666666666666668e-05,
"loss": 1.789,
"step": 11
},
{
"epoch": 0.04,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.3775,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 1.7333333333333336e-05,
"loss": 1.7759,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 1.866666666666667e-05,
"loss": 1.2334,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 2e-05,
"loss": 0.7635,
"step": 15
},
{
"epoch": 0.05,
"learning_rate": 2.1333333333333335e-05,
"loss": 0.8482,
"step": 16
},
{
"epoch": 0.05,
"learning_rate": 2.2666666666666668e-05,
"loss": 0.7464,
"step": 17
},
{
"epoch": 0.05,
"learning_rate": 2.4e-05,
"loss": 0.7694,
"step": 18
},
{
"epoch": 0.06,
"learning_rate": 2.5333333333333337e-05,
"loss": 0.6606,
"step": 19
},
{
"epoch": 0.06,
"learning_rate": 2.6666666666666667e-05,
"loss": 0.8333,
"step": 20
},
{
"epoch": 0.06,
"eval_loss": 0.6411340832710266,
"eval_runtime": 39.0251,
"eval_samples_per_second": 41.742,
"eval_steps_per_second": 20.884,
"step": 20
},
{
"epoch": 0.06,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.8225,
"step": 21
},
{
"epoch": 0.07,
"learning_rate": 2.9333333333333336e-05,
"loss": 0.7741,
"step": 22
},
{
"epoch": 0.07,
"learning_rate": 3.066666666666667e-05,
"loss": 0.8105,
"step": 23
},
{
"epoch": 0.07,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.6497,
"step": 24
},
{
"epoch": 0.07,
"learning_rate": 3.3333333333333335e-05,
"loss": 0.6973,
"step": 25
},
{
"epoch": 0.08,
"learning_rate": 3.466666666666667e-05,
"loss": 0.8275,
"step": 26
},
{
"epoch": 0.08,
"learning_rate": 3.6e-05,
"loss": 0.9258,
"step": 27
},
{
"epoch": 0.08,
"learning_rate": 3.733333333333334e-05,
"loss": 0.6865,
"step": 28
},
{
"epoch": 0.09,
"learning_rate": 3.866666666666667e-05,
"loss": 0.68,
"step": 29
},
{
"epoch": 0.09,
"learning_rate": 4e-05,
"loss": 0.7747,
"step": 30
},
{
"epoch": 0.09,
"learning_rate": 4.133333333333333e-05,
"loss": 0.725,
"step": 31
},
{
"epoch": 0.1,
"learning_rate": 4.266666666666667e-05,
"loss": 0.6831,
"step": 32
},
{
"epoch": 0.1,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.754,
"step": 33
},
{
"epoch": 0.1,
"learning_rate": 4.5333333333333335e-05,
"loss": 0.7415,
"step": 34
},
{
"epoch": 0.1,
"learning_rate": 4.666666666666667e-05,
"loss": 0.7404,
"step": 35
},
{
"epoch": 0.11,
"learning_rate": 4.8e-05,
"loss": 0.7474,
"step": 36
},
{
"epoch": 0.11,
"learning_rate": 4.933333333333334e-05,
"loss": 0.7268,
"step": 37
},
{
"epoch": 0.11,
"learning_rate": 5.0666666666666674e-05,
"loss": 0.7249,
"step": 38
},
{
"epoch": 0.12,
"learning_rate": 5.2000000000000004e-05,
"loss": 0.5853,
"step": 39
},
{
"epoch": 0.12,
"learning_rate": 5.333333333333333e-05,
"loss": 0.6715,
"step": 40
},
{
"epoch": 0.12,
"eval_loss": 0.5898512005805969,
"eval_runtime": 39.0712,
"eval_samples_per_second": 41.693,
"eval_steps_per_second": 20.859,
"step": 40
},
{
"epoch": 0.12,
"learning_rate": 5.466666666666666e-05,
"loss": 0.6705,
"step": 41
},
{
"epoch": 0.13,
"learning_rate": 5.6000000000000006e-05,
"loss": 0.6564,
"step": 42
},
{
"epoch": 0.13,
"learning_rate": 5.7333333333333336e-05,
"loss": 0.7193,
"step": 43
},
{
"epoch": 0.13,
"learning_rate": 5.866666666666667e-05,
"loss": 0.7587,
"step": 44
},
{
"epoch": 0.13,
"learning_rate": 6e-05,
"loss": 0.7327,
"step": 45
},
{
"epoch": 0.14,
"learning_rate": 6.133333333333334e-05,
"loss": 0.7989,
"step": 46
},
{
"epoch": 0.14,
"learning_rate": 6.266666666666667e-05,
"loss": 0.586,
"step": 47
},
{
"epoch": 0.14,
"learning_rate": 6.400000000000001e-05,
"loss": 0.6681,
"step": 48
},
{
"epoch": 0.15,
"learning_rate": 6.533333333333334e-05,
"loss": 0.7467,
"step": 49
},
{
"epoch": 0.15,
"learning_rate": 6.666666666666667e-05,
"loss": 0.5078,
"step": 50
},
{
"epoch": 0.15,
"learning_rate": 6.800000000000001e-05,
"loss": 0.7192,
"step": 51
},
{
"epoch": 0.16,
"learning_rate": 6.933333333333334e-05,
"loss": 0.8233,
"step": 52
},
{
"epoch": 0.16,
"learning_rate": 7.066666666666667e-05,
"loss": 0.7273,
"step": 53
},
{
"epoch": 0.16,
"learning_rate": 7.2e-05,
"loss": 0.6151,
"step": 54
},
{
"epoch": 0.16,
"learning_rate": 7.333333333333333e-05,
"loss": 0.7629,
"step": 55
},
{
"epoch": 0.17,
"learning_rate": 7.466666666666667e-05,
"loss": 0.6741,
"step": 56
},
{
"epoch": 0.17,
"learning_rate": 7.6e-05,
"loss": 0.5387,
"step": 57
},
{
"epoch": 0.17,
"learning_rate": 7.733333333333333e-05,
"loss": 0.7459,
"step": 58
},
{
"epoch": 0.18,
"learning_rate": 7.866666666666666e-05,
"loss": 0.5558,
"step": 59
},
{
"epoch": 0.18,
"learning_rate": 8e-05,
"loss": 0.5905,
"step": 60
},
{
"epoch": 0.18,
"eval_loss": 0.557337760925293,
"eval_runtime": 39.0718,
"eval_samples_per_second": 41.692,
"eval_steps_per_second": 20.859,
"step": 60
},
{
"epoch": 0.18,
"learning_rate": 8.133333333333334e-05,
"loss": 0.6305,
"step": 61
},
{
"epoch": 0.19,
"learning_rate": 8.266666666666667e-05,
"loss": 0.7207,
"step": 62
},
{
"epoch": 0.19,
"learning_rate": 8.4e-05,
"loss": 0.6926,
"step": 63
},
{
"epoch": 0.19,
"learning_rate": 8.533333333333334e-05,
"loss": 0.4858,
"step": 64
},
{
"epoch": 0.19,
"learning_rate": 8.666666666666667e-05,
"loss": 0.634,
"step": 65
},
{
"epoch": 0.2,
"learning_rate": 8.800000000000001e-05,
"loss": 0.6184,
"step": 66
},
{
"epoch": 0.2,
"learning_rate": 8.933333333333334e-05,
"loss": 0.5475,
"step": 67
},
{
"epoch": 0.2,
"learning_rate": 9.066666666666667e-05,
"loss": 0.5431,
"step": 68
},
{
"epoch": 0.21,
"learning_rate": 9.200000000000001e-05,
"loss": 0.659,
"step": 69
},
{
"epoch": 0.21,
"learning_rate": 9.333333333333334e-05,
"loss": 0.8016,
"step": 70
},
{
"epoch": 0.21,
"learning_rate": 9.466666666666667e-05,
"loss": 0.6429,
"step": 71
},
{
"epoch": 0.22,
"learning_rate": 9.6e-05,
"loss": 0.5628,
"step": 72
},
{
"epoch": 0.22,
"learning_rate": 9.733333333333335e-05,
"loss": 0.6041,
"step": 73
},
{
"epoch": 0.22,
"learning_rate": 9.866666666666668e-05,
"loss": 0.4893,
"step": 74
},
{
"epoch": 0.22,
"learning_rate": 0.0001,
"loss": 0.7429,
"step": 75
},
{
"epoch": 0.23,
"learning_rate": 0.00010133333333333335,
"loss": 0.5158,
"step": 76
},
{
"epoch": 0.23,
"learning_rate": 0.00010266666666666666,
"loss": 0.7377,
"step": 77
},
{
"epoch": 0.23,
"learning_rate": 0.00010400000000000001,
"loss": 0.5242,
"step": 78
},
{
"epoch": 0.24,
"learning_rate": 0.00010533333333333332,
"loss": 0.549,
"step": 79
},
{
"epoch": 0.24,
"learning_rate": 0.00010666666666666667,
"loss": 0.5845,
"step": 80
},
{
"epoch": 0.24,
"eval_loss": 0.5341688990592957,
"eval_runtime": 39.1341,
"eval_samples_per_second": 41.626,
"eval_steps_per_second": 20.826,
"step": 80
},
{
"epoch": 0.24,
"learning_rate": 0.00010800000000000001,
"loss": 0.5873,
"step": 81
},
{
"epoch": 0.25,
"learning_rate": 0.00010933333333333333,
"loss": 0.5998,
"step": 82
},
{
"epoch": 0.25,
"learning_rate": 0.00011066666666666667,
"loss": 0.8269,
"step": 83
},
{
"epoch": 0.25,
"learning_rate": 0.00011200000000000001,
"loss": 0.6924,
"step": 84
},
{
"epoch": 0.25,
"learning_rate": 0.00011333333333333334,
"loss": 0.5342,
"step": 85
},
{
"epoch": 0.26,
"learning_rate": 0.00011466666666666667,
"loss": 0.5858,
"step": 86
},
{
"epoch": 0.26,
"learning_rate": 0.000116,
"loss": 0.5207,
"step": 87
},
{
"epoch": 0.26,
"learning_rate": 0.00011733333333333334,
"loss": 0.6034,
"step": 88
},
{
"epoch": 0.27,
"learning_rate": 0.00011866666666666669,
"loss": 0.707,
"step": 89
},
{
"epoch": 0.27,
"learning_rate": 0.00012,
"loss": 0.6256,
"step": 90
},
{
"epoch": 0.27,
"learning_rate": 0.00012133333333333335,
"loss": 0.8011,
"step": 91
},
{
"epoch": 0.28,
"learning_rate": 0.00012266666666666668,
"loss": 0.7638,
"step": 92
},
{
"epoch": 0.28,
"learning_rate": 0.000124,
"loss": 0.5857,
"step": 93
},
{
"epoch": 0.28,
"learning_rate": 0.00012533333333333334,
"loss": 0.5948,
"step": 94
},
{
"epoch": 0.28,
"learning_rate": 0.00012666666666666666,
"loss": 0.6051,
"step": 95
},
{
"epoch": 0.29,
"learning_rate": 0.00012800000000000002,
"loss": 0.6847,
"step": 96
},
{
"epoch": 0.29,
"learning_rate": 0.00012933333333333332,
"loss": 0.4701,
"step": 97
},
{
"epoch": 0.29,
"learning_rate": 0.00013066666666666668,
"loss": 0.6454,
"step": 98
},
{
"epoch": 0.3,
"learning_rate": 0.000132,
"loss": 0.5723,
"step": 99
},
{
"epoch": 0.3,
"learning_rate": 0.00013333333333333334,
"loss": 0.5524,
"step": 100
},
{
"epoch": 0.3,
"eval_loss": 0.5259758234024048,
"eval_runtime": 39.0597,
"eval_samples_per_second": 41.705,
"eval_steps_per_second": 20.865,
"step": 100
},
{
"epoch": 0.3,
"learning_rate": 0.00013466666666666667,
"loss": 0.6256,
"step": 101
},
{
"epoch": 0.31,
"learning_rate": 0.00013600000000000003,
"loss": 0.5798,
"step": 102
},
{
"epoch": 0.31,
"learning_rate": 0.00013733333333333333,
"loss": 0.6021,
"step": 103
},
{
"epoch": 0.31,
"learning_rate": 0.00013866666666666669,
"loss": 0.652,
"step": 104
},
{
"epoch": 0.31,
"learning_rate": 0.00014,
"loss": 0.5602,
"step": 105
},
{
"epoch": 0.32,
"learning_rate": 0.00014133333333333334,
"loss": 0.6358,
"step": 106
},
{
"epoch": 0.32,
"learning_rate": 0.00014266666666666667,
"loss": 0.6063,
"step": 107
},
{
"epoch": 0.32,
"learning_rate": 0.000144,
"loss": 0.6901,
"step": 108
},
{
"epoch": 0.33,
"learning_rate": 0.00014533333333333333,
"loss": 0.5586,
"step": 109
},
{
"epoch": 0.33,
"learning_rate": 0.00014666666666666666,
"loss": 0.6054,
"step": 110
},
{
"epoch": 0.33,
"learning_rate": 0.000148,
"loss": 0.4814,
"step": 111
},
{
"epoch": 0.34,
"learning_rate": 0.00014933333333333335,
"loss": 0.347,
"step": 112
},
{
"epoch": 0.34,
"learning_rate": 0.00015066666666666668,
"loss": 0.4877,
"step": 113
},
{
"epoch": 0.34,
"learning_rate": 0.000152,
"loss": 0.7594,
"step": 114
},
{
"epoch": 0.34,
"learning_rate": 0.00015333333333333334,
"loss": 0.5597,
"step": 115
},
{
"epoch": 0.35,
"learning_rate": 0.00015466666666666667,
"loss": 0.4975,
"step": 116
},
{
"epoch": 0.35,
"learning_rate": 0.00015600000000000002,
"loss": 0.6336,
"step": 117
},
{
"epoch": 0.35,
"learning_rate": 0.00015733333333333333,
"loss": 0.6042,
"step": 118
},
{
"epoch": 0.36,
"learning_rate": 0.00015866666666666668,
"loss": 0.4253,
"step": 119
},
{
"epoch": 0.36,
"learning_rate": 0.00016,
"loss": 0.5516,
"step": 120
},
{
"epoch": 0.36,
"eval_loss": 0.5273345708847046,
"eval_runtime": 39.0262,
"eval_samples_per_second": 41.741,
"eval_steps_per_second": 20.883,
"step": 120
},
{
"epoch": 0.36,
"learning_rate": 0.00016133333333333334,
"loss": 0.3813,
"step": 121
},
{
"epoch": 0.37,
"learning_rate": 0.00016266666666666667,
"loss": 0.5743,
"step": 122
},
{
"epoch": 0.37,
"learning_rate": 0.000164,
"loss": 0.5525,
"step": 123
},
{
"epoch": 0.37,
"learning_rate": 0.00016533333333333333,
"loss": 0.6549,
"step": 124
},
{
"epoch": 0.37,
"learning_rate": 0.0001666666666666667,
"loss": 0.6705,
"step": 125
},
{
"epoch": 0.38,
"learning_rate": 0.000168,
"loss": 0.6486,
"step": 126
},
{
"epoch": 0.38,
"learning_rate": 0.00016933333333333335,
"loss": 0.5122,
"step": 127
},
{
"epoch": 0.38,
"learning_rate": 0.00017066666666666668,
"loss": 0.6339,
"step": 128
},
{
"epoch": 0.39,
"learning_rate": 0.000172,
"loss": 0.5281,
"step": 129
},
{
"epoch": 0.39,
"learning_rate": 0.00017333333333333334,
"loss": 0.6219,
"step": 130
},
{
"epoch": 0.39,
"learning_rate": 0.00017466666666666667,
"loss": 0.548,
"step": 131
},
{
"epoch": 0.4,
"learning_rate": 0.00017600000000000002,
"loss": 0.6827,
"step": 132
},
{
"epoch": 0.4,
"learning_rate": 0.00017733333333333335,
"loss": 0.6162,
"step": 133
},
{
"epoch": 0.4,
"learning_rate": 0.00017866666666666668,
"loss": 0.4973,
"step": 134
},
{
"epoch": 0.4,
"learning_rate": 0.00018,
"loss": 0.7511,
"step": 135
},
{
"epoch": 0.41,
"learning_rate": 0.00018133333333333334,
"loss": 0.4998,
"step": 136
},
{
"epoch": 0.41,
"learning_rate": 0.00018266666666666667,
"loss": 0.4568,
"step": 137
},
{
"epoch": 0.41,
"learning_rate": 0.00018400000000000003,
"loss": 0.4537,
"step": 138
},
{
"epoch": 0.42,
"learning_rate": 0.00018533333333333333,
"loss": 0.5601,
"step": 139
},
{
"epoch": 0.42,
"learning_rate": 0.0001866666666666667,
"loss": 0.5465,
"step": 140
},
{
"epoch": 0.42,
"eval_loss": 0.5131502151489258,
"eval_runtime": 39.125,
"eval_samples_per_second": 41.636,
"eval_steps_per_second": 20.831,
"step": 140
},
{
"epoch": 0.42,
"learning_rate": 0.000188,
"loss": 0.5256,
"step": 141
},
{
"epoch": 0.43,
"learning_rate": 0.00018933333333333335,
"loss": 0.6077,
"step": 142
},
{
"epoch": 0.43,
"learning_rate": 0.00019066666666666668,
"loss": 0.6348,
"step": 143
},
{
"epoch": 0.43,
"learning_rate": 0.000192,
"loss": 0.5437,
"step": 144
},
{
"epoch": 0.43,
"learning_rate": 0.00019333333333333333,
"loss": 0.602,
"step": 145
},
{
"epoch": 0.44,
"learning_rate": 0.0001946666666666667,
"loss": 0.4774,
"step": 146
},
{
"epoch": 0.44,
"learning_rate": 0.000196,
"loss": 0.6249,
"step": 147
},
{
"epoch": 0.44,
"learning_rate": 0.00019733333333333335,
"loss": 0.6498,
"step": 148
},
{
"epoch": 0.45,
"learning_rate": 0.00019866666666666668,
"loss": 0.5419,
"step": 149
},
{
"epoch": 0.45,
"learning_rate": 0.0002,
"loss": 0.5724,
"step": 150
},
{
"epoch": 0.45,
"learning_rate": 0.00020133333333333334,
"loss": 0.6224,
"step": 151
},
{
"epoch": 0.46,
"learning_rate": 0.0002026666666666667,
"loss": 0.4996,
"step": 152
},
{
"epoch": 0.46,
"learning_rate": 0.00020400000000000003,
"loss": 0.5016,
"step": 153
},
{
"epoch": 0.46,
"learning_rate": 0.00020533333333333333,
"loss": 0.4315,
"step": 154
},
{
"epoch": 0.46,
"learning_rate": 0.00020666666666666668,
"loss": 0.5096,
"step": 155
},
{
"epoch": 0.47,
"learning_rate": 0.00020800000000000001,
"loss": 0.5167,
"step": 156
},
{
"epoch": 0.47,
"learning_rate": 0.00020933333333333334,
"loss": 0.6057,
"step": 157
},
{
"epoch": 0.47,
"learning_rate": 0.00021066666666666665,
"loss": 0.763,
"step": 158
},
{
"epoch": 0.48,
"learning_rate": 0.00021200000000000003,
"loss": 0.4568,
"step": 159
},
{
"epoch": 0.48,
"learning_rate": 0.00021333333333333333,
"loss": 0.439,
"step": 160
},
{
"epoch": 0.48,
"eval_loss": 0.5084798336029053,
"eval_runtime": 39.1227,
"eval_samples_per_second": 41.638,
"eval_steps_per_second": 20.832,
"step": 160
},
{
"epoch": 0.48,
"learning_rate": 0.00021466666666666666,
"loss": 0.3806,
"step": 161
},
{
"epoch": 0.49,
"learning_rate": 0.00021600000000000002,
"loss": 0.4544,
"step": 162
},
{
"epoch": 0.49,
"learning_rate": 0.00021733333333333335,
"loss": 0.5606,
"step": 163
},
{
"epoch": 0.49,
"learning_rate": 0.00021866666666666665,
"loss": 0.5595,
"step": 164
},
{
"epoch": 0.49,
"learning_rate": 0.00022000000000000003,
"loss": 0.5773,
"step": 165
},
{
"epoch": 0.5,
"learning_rate": 0.00022133333333333334,
"loss": 0.511,
"step": 166
},
{
"epoch": 0.5,
"learning_rate": 0.00022266666666666667,
"loss": 0.6515,
"step": 167
},
{
"epoch": 0.5,
"learning_rate": 0.00022400000000000002,
"loss": 0.4612,
"step": 168
},
{
"epoch": 0.51,
"learning_rate": 0.00022533333333333335,
"loss": 0.4674,
"step": 169
},
{
"epoch": 0.51,
"learning_rate": 0.00022666666666666668,
"loss": 0.6907,
"step": 170
},
{
"epoch": 0.51,
"learning_rate": 0.00022799999999999999,
"loss": 0.6061,
"step": 171
},
{
"epoch": 0.51,
"learning_rate": 0.00022933333333333334,
"loss": 0.594,
"step": 172
},
{
"epoch": 0.52,
"learning_rate": 0.00023066666666666667,
"loss": 0.5703,
"step": 173
},
{
"epoch": 0.52,
"learning_rate": 0.000232,
"loss": 0.6094,
"step": 174
},
{
"epoch": 0.52,
"learning_rate": 0.00023333333333333336,
"loss": 0.5031,
"step": 175
},
{
"epoch": 0.53,
"learning_rate": 0.0002346666666666667,
"loss": 0.4689,
"step": 176
},
{
"epoch": 0.53,
"learning_rate": 0.000236,
"loss": 0.6271,
"step": 177
},
{
"epoch": 0.53,
"learning_rate": 0.00023733333333333337,
"loss": 0.4404,
"step": 178
},
{
"epoch": 0.54,
"learning_rate": 0.00023866666666666668,
"loss": 0.4846,
"step": 179
},
{
"epoch": 0.54,
"learning_rate": 0.00024,
"loss": 0.6857,
"step": 180
},
{
"epoch": 0.54,
"eval_loss": 0.49820253252983093,
"eval_runtime": 39.0562,
"eval_samples_per_second": 41.709,
"eval_steps_per_second": 20.867,
"step": 180
},
{
"epoch": 0.54,
"learning_rate": 0.00024133333333333336,
"loss": 0.6329,
"step": 181
},
{
"epoch": 0.54,
"learning_rate": 0.0002426666666666667,
"loss": 0.4513,
"step": 182
},
{
"epoch": 0.55,
"learning_rate": 0.000244,
"loss": 0.5719,
"step": 183
},
{
"epoch": 0.55,
"learning_rate": 0.00024533333333333335,
"loss": 0.5743,
"step": 184
},
{
"epoch": 0.55,
"learning_rate": 0.0002466666666666667,
"loss": 0.4558,
"step": 185
},
{
"epoch": 0.56,
"learning_rate": 0.000248,
"loss": 0.8386,
"step": 186
},
{
"epoch": 0.56,
"learning_rate": 0.00024933333333333334,
"loss": 0.5067,
"step": 187
},
{
"epoch": 0.56,
"learning_rate": 0.00025066666666666667,
"loss": 0.4633,
"step": 188
},
{
"epoch": 0.57,
"learning_rate": 0.000252,
"loss": 0.8261,
"step": 189
},
{
"epoch": 0.57,
"learning_rate": 0.00025333333333333333,
"loss": 0.4692,
"step": 190
},
{
"epoch": 0.57,
"learning_rate": 0.0002546666666666667,
"loss": 0.4346,
"step": 191
},
{
"epoch": 0.57,
"learning_rate": 0.00025600000000000004,
"loss": 0.4951,
"step": 192
},
{
"epoch": 0.58,
"learning_rate": 0.0002573333333333333,
"loss": 0.5326,
"step": 193
},
{
"epoch": 0.58,
"learning_rate": 0.00025866666666666665,
"loss": 0.7204,
"step": 194
},
{
"epoch": 0.58,
"learning_rate": 0.00026000000000000003,
"loss": 0.5423,
"step": 195
},
{
"epoch": 0.59,
"learning_rate": 0.00026133333333333336,
"loss": 0.5059,
"step": 196
},
{
"epoch": 0.59,
"learning_rate": 0.00026266666666666664,
"loss": 0.7371,
"step": 197
},
{
"epoch": 0.59,
"learning_rate": 0.000264,
"loss": 0.4905,
"step": 198
},
{
"epoch": 0.6,
"learning_rate": 0.00026533333333333335,
"loss": 0.5729,
"step": 199
},
{
"epoch": 0.6,
"learning_rate": 0.0002666666666666667,
"loss": 0.7326,
"step": 200
},
{
"epoch": 0.6,
"eval_loss": 0.5096016526222229,
"eval_runtime": 38.9974,
"eval_samples_per_second": 41.772,
"eval_steps_per_second": 20.899,
"step": 200
},
{
"epoch": 0.6,
"learning_rate": 0.000268,
"loss": 0.7271,
"step": 201
},
{
"epoch": 0.6,
"learning_rate": 0.00026933333333333334,
"loss": 0.5519,
"step": 202
},
{
"epoch": 0.61,
"learning_rate": 0.00027066666666666667,
"loss": 0.6148,
"step": 203
},
{
"epoch": 0.61,
"learning_rate": 0.00027200000000000005,
"loss": 0.5656,
"step": 204
},
{
"epoch": 0.61,
"learning_rate": 0.00027333333333333333,
"loss": 0.4745,
"step": 205
},
{
"epoch": 0.62,
"learning_rate": 0.00027466666666666666,
"loss": 0.3901,
"step": 206
},
{
"epoch": 0.62,
"learning_rate": 0.000276,
"loss": 0.5684,
"step": 207
},
{
"epoch": 0.62,
"learning_rate": 0.00027733333333333337,
"loss": 0.6405,
"step": 208
},
{
"epoch": 0.63,
"learning_rate": 0.0002786666666666667,
"loss": 0.6566,
"step": 209
},
{
"epoch": 0.63,
"learning_rate": 0.00028,
"loss": 0.6318,
"step": 210
},
{
"epoch": 0.63,
"learning_rate": 0.00028133333333333336,
"loss": 0.5454,
"step": 211
},
{
"epoch": 0.63,
"learning_rate": 0.0002826666666666667,
"loss": 0.7309,
"step": 212
},
{
"epoch": 0.64,
"learning_rate": 0.000284,
"loss": 0.4298,
"step": 213
},
{
"epoch": 0.64,
"learning_rate": 0.00028533333333333335,
"loss": 0.6239,
"step": 214
},
{
"epoch": 0.64,
"learning_rate": 0.0002866666666666667,
"loss": 0.6409,
"step": 215
},
{
"epoch": 0.65,
"learning_rate": 0.000288,
"loss": 0.5176,
"step": 216
},
{
"epoch": 0.65,
"learning_rate": 0.0002893333333333334,
"loss": 0.5586,
"step": 217
},
{
"epoch": 0.65,
"learning_rate": 0.00029066666666666667,
"loss": 0.5455,
"step": 218
},
{
"epoch": 0.66,
"learning_rate": 0.000292,
"loss": 0.5462,
"step": 219
},
{
"epoch": 0.66,
"learning_rate": 0.0002933333333333333,
"loss": 0.8225,
"step": 220
},
{
"epoch": 0.66,
"eval_loss": 0.5079875588417053,
"eval_runtime": 39.0413,
"eval_samples_per_second": 41.725,
"eval_steps_per_second": 20.875,
"step": 220
},
{
"epoch": 0.66,
"learning_rate": 0.0002946666666666667,
"loss": 0.5573,
"step": 221
},
{
"epoch": 0.66,
"learning_rate": 0.000296,
"loss": 0.53,
"step": 222
},
{
"epoch": 0.67,
"learning_rate": 0.0002973333333333333,
"loss": 0.4626,
"step": 223
},
{
"epoch": 0.67,
"learning_rate": 0.0002986666666666667,
"loss": 0.4893,
"step": 224
},
{
"epoch": 0.67,
"learning_rate": 0.00030000000000000003,
"loss": 0.4595,
"step": 225
},
{
"epoch": 0.68,
"learning_rate": 0.00030133333333333336,
"loss": 0.6778,
"step": 226
},
{
"epoch": 0.68,
"learning_rate": 0.0003026666666666667,
"loss": 0.6783,
"step": 227
},
{
"epoch": 0.68,
"learning_rate": 0.000304,
"loss": 0.6577,
"step": 228
},
{
"epoch": 0.69,
"learning_rate": 0.00030533333333333335,
"loss": 0.5897,
"step": 229
},
{
"epoch": 0.69,
"learning_rate": 0.0003066666666666667,
"loss": 0.6532,
"step": 230
},
{
"epoch": 0.69,
"learning_rate": 0.000308,
"loss": 0.6298,
"step": 231
},
{
"epoch": 0.69,
"learning_rate": 0.00030933333333333334,
"loss": 0.4022,
"step": 232
},
{
"epoch": 0.7,
"learning_rate": 0.00031066666666666666,
"loss": 0.5869,
"step": 233
},
{
"epoch": 0.7,
"learning_rate": 0.00031200000000000005,
"loss": 0.6087,
"step": 234
},
{
"epoch": 0.7,
"learning_rate": 0.0003133333333333333,
"loss": 0.5389,
"step": 235
},
{
"epoch": 0.71,
"learning_rate": 0.00031466666666666665,
"loss": 0.4441,
"step": 236
},
{
"epoch": 0.71,
"learning_rate": 0.00031600000000000004,
"loss": 0.4996,
"step": 237
},
{
"epoch": 0.71,
"learning_rate": 0.00031733333333333337,
"loss": 0.7413,
"step": 238
},
{
"epoch": 0.72,
"learning_rate": 0.00031866666666666664,
"loss": 0.5144,
"step": 239
},
{
"epoch": 0.72,
"learning_rate": 0.00032,
"loss": 0.6148,
"step": 240
},
{
"epoch": 0.72,
"eval_loss": 0.4882766604423523,
"eval_runtime": 39.1262,
"eval_samples_per_second": 41.635,
"eval_steps_per_second": 20.83,
"step": 240
},
{
"epoch": 0.72,
"learning_rate": 0.00032133333333333336,
"loss": 0.4032,
"step": 241
},
{
"epoch": 0.72,
"learning_rate": 0.0003226666666666667,
"loss": 0.5266,
"step": 242
},
{
"epoch": 0.73,
"learning_rate": 0.000324,
"loss": 0.6,
"step": 243
},
{
"epoch": 0.73,
"learning_rate": 0.00032533333333333334,
"loss": 0.55,
"step": 244
},
{
"epoch": 0.73,
"learning_rate": 0.0003266666666666667,
"loss": 0.5816,
"step": 245
},
{
"epoch": 0.74,
"learning_rate": 0.000328,
"loss": 0.4583,
"step": 246
},
{
"epoch": 0.74,
"learning_rate": 0.00032933333333333333,
"loss": 0.4872,
"step": 247
},
{
"epoch": 0.74,
"learning_rate": 0.00033066666666666666,
"loss": 0.5112,
"step": 248
},
{
"epoch": 0.75,
"learning_rate": 0.000332,
"loss": 0.4714,
"step": 249
},
{
"epoch": 0.75,
"learning_rate": 0.0003333333333333334,
"loss": 0.8368,
"step": 250
},
{
"epoch": 0.75,
"learning_rate": 0.0003346666666666667,
"loss": 0.4689,
"step": 251
},
{
"epoch": 0.75,
"learning_rate": 0.000336,
"loss": 0.6403,
"step": 252
},
{
"epoch": 0.76,
"learning_rate": 0.00033733333333333337,
"loss": 0.6252,
"step": 253
},
{
"epoch": 0.76,
"learning_rate": 0.0003386666666666667,
"loss": 0.6707,
"step": 254
},
{
"epoch": 0.76,
"learning_rate": 0.00034,
"loss": 0.6497,
"step": 255
},
{
"epoch": 0.77,
"learning_rate": 0.00034133333333333335,
"loss": 0.3741,
"step": 256
},
{
"epoch": 0.77,
"learning_rate": 0.0003426666666666667,
"loss": 0.3442,
"step": 257
},
{
"epoch": 0.77,
"learning_rate": 0.000344,
"loss": 0.459,
"step": 258
},
{
"epoch": 0.78,
"learning_rate": 0.00034533333333333334,
"loss": 0.7909,
"step": 259
},
{
"epoch": 0.78,
"learning_rate": 0.00034666666666666667,
"loss": 0.4524,
"step": 260
},
{
"epoch": 0.78,
"eval_loss": 0.4969780147075653,
"eval_runtime": 39.097,
"eval_samples_per_second": 41.666,
"eval_steps_per_second": 20.846,
"step": 260
},
{
"epoch": 0.78,
"learning_rate": 0.000348,
"loss": 0.514,
"step": 261
},
{
"epoch": 0.78,
"learning_rate": 0.00034933333333333333,
"loss": 0.5195,
"step": 262
},
{
"epoch": 0.79,
"learning_rate": 0.0003506666666666667,
"loss": 0.5651,
"step": 263
},
{
"epoch": 0.79,
"learning_rate": 0.00035200000000000005,
"loss": 0.5681,
"step": 264
},
{
"epoch": 0.79,
"learning_rate": 0.0003533333333333333,
"loss": 0.4571,
"step": 265
},
{
"epoch": 0.8,
"learning_rate": 0.0003546666666666667,
"loss": 0.4669,
"step": 266
},
{
"epoch": 0.8,
"learning_rate": 0.00035600000000000003,
"loss": 0.6006,
"step": 267
},
{
"epoch": 0.8,
"learning_rate": 0.00035733333333333336,
"loss": 0.61,
"step": 268
},
{
"epoch": 0.81,
"learning_rate": 0.00035866666666666664,
"loss": 0.685,
"step": 269
},
{
"epoch": 0.81,
"learning_rate": 0.00036,
"loss": 0.5961,
"step": 270
},
{
"epoch": 0.81,
"learning_rate": 0.00036133333333333335,
"loss": 0.5775,
"step": 271
},
{
"epoch": 0.81,
"learning_rate": 0.0003626666666666667,
"loss": 0.5196,
"step": 272
},
{
"epoch": 0.82,
"learning_rate": 0.000364,
"loss": 0.5586,
"step": 273
},
{
"epoch": 0.82,
"learning_rate": 0.00036533333333333334,
"loss": 0.5283,
"step": 274
},
{
"epoch": 0.82,
"learning_rate": 0.00036666666666666667,
"loss": 0.5068,
"step": 275
},
{
"epoch": 0.83,
"learning_rate": 0.00036800000000000005,
"loss": 0.5045,
"step": 276
},
{
"epoch": 0.83,
"learning_rate": 0.00036933333333333333,
"loss": 0.5001,
"step": 277
},
{
"epoch": 0.83,
"learning_rate": 0.00037066666666666666,
"loss": 0.5021,
"step": 278
},
{
"epoch": 0.84,
"learning_rate": 0.00037200000000000004,
"loss": 0.4542,
"step": 279
},
{
"epoch": 0.84,
"learning_rate": 0.0003733333333333334,
"loss": 0.6084,
"step": 280
},
{
"epoch": 0.84,
"eval_loss": 0.5424579381942749,
"eval_runtime": 39.1219,
"eval_samples_per_second": 41.639,
"eval_steps_per_second": 20.832,
"step": 280
},
{
"epoch": 0.84,
"learning_rate": 0.0003746666666666667,
"loss": 0.5885,
"step": 281
},
{
"epoch": 0.84,
"learning_rate": 0.000376,
"loss": 0.7034,
"step": 282
},
{
"epoch": 0.85,
"learning_rate": 0.00037733333333333336,
"loss": 0.601,
"step": 283
},
{
"epoch": 0.85,
"learning_rate": 0.0003786666666666667,
"loss": 0.646,
"step": 284
},
{
"epoch": 0.85,
"learning_rate": 0.00038,
"loss": 0.5125,
"step": 285
},
{
"epoch": 0.86,
"learning_rate": 0.00038133333333333335,
"loss": 0.5087,
"step": 286
},
{
"epoch": 0.86,
"learning_rate": 0.0003826666666666667,
"loss": 0.6016,
"step": 287
},
{
"epoch": 0.86,
"learning_rate": 0.000384,
"loss": 0.5239,
"step": 288
},
{
"epoch": 0.87,
"learning_rate": 0.0003853333333333334,
"loss": 0.406,
"step": 289
},
{
"epoch": 0.87,
"learning_rate": 0.00038666666666666667,
"loss": 0.5812,
"step": 290
},
{
"epoch": 0.87,
"learning_rate": 0.000388,
"loss": 0.621,
"step": 291
},
{
"epoch": 0.87,
"learning_rate": 0.0003893333333333334,
"loss": 0.6048,
"step": 292
},
{
"epoch": 0.88,
"learning_rate": 0.0003906666666666667,
"loss": 0.4498,
"step": 293
},
{
"epoch": 0.88,
"learning_rate": 0.000392,
"loss": 0.6144,
"step": 294
},
{
"epoch": 0.88,
"learning_rate": 0.0003933333333333333,
"loss": 0.7374,
"step": 295
},
{
"epoch": 0.89,
"learning_rate": 0.0003946666666666667,
"loss": 0.5784,
"step": 296
},
{
"epoch": 0.89,
"learning_rate": 0.00039600000000000003,
"loss": 0.5084,
"step": 297
},
{
"epoch": 0.89,
"learning_rate": 0.00039733333333333336,
"loss": 0.5633,
"step": 298
},
{
"epoch": 0.9,
"learning_rate": 0.0003986666666666667,
"loss": 0.5172,
"step": 299
},
{
"epoch": 0.9,
"learning_rate": 0.0004,
"loss": 0.6737,
"step": 300
},
{
"epoch": 0.9,
"eval_loss": 0.5059300065040588,
"eval_runtime": 39.1035,
"eval_samples_per_second": 41.659,
"eval_steps_per_second": 20.842,
"step": 300
},
{
"epoch": 0.9,
"learning_rate": 0.0003999979972589652,
"loss": 0.6431,
"step": 301
},
{
"epoch": 0.9,
"learning_rate": 0.00039999198907597047,
"loss": 0.6727,
"step": 302
},
{
"epoch": 0.91,
"learning_rate": 0.00039998197557134424,
"loss": 0.4213,
"step": 303
},
{
"epoch": 0.91,
"learning_rate": 0.00039996795694563096,
"loss": 0.4473,
"step": 304
},
{
"epoch": 0.91,
"learning_rate": 0.0003999499334795875,
"loss": 0.5899,
"step": 305
},
{
"epoch": 0.92,
"learning_rate": 0.0003999279055341771,
"loss": 0.414,
"step": 306
},
{
"epoch": 0.92,
"learning_rate": 0.0003999018735505626,
"loss": 0.4664,
"step": 307
},
{
"epoch": 0.92,
"learning_rate": 0.0003998718380500971,
"loss": 0.6036,
"step": 308
},
{
"epoch": 0.93,
"learning_rate": 0.00039983779963431395,
"loss": 0.5764,
"step": 309
},
{
"epoch": 0.93,
"learning_rate": 0.00039979975898491447,
"loss": 0.4595,
"step": 310
},
{
"epoch": 0.93,
"learning_rate": 0.0003997577168637543,
"loss": 0.591,
"step": 311
},
{
"epoch": 0.93,
"learning_rate": 0.00039971167411282835,
"loss": 0.4327,
"step": 312
},
{
"epoch": 0.94,
"learning_rate": 0.0003996616316542537,
"loss": 0.4061,
"step": 313
},
{
"epoch": 0.94,
"learning_rate": 0.00039960759049025105,
"loss": 0.5463,
"step": 314
},
{
"epoch": 0.94,
"learning_rate": 0.00039954955170312504,
"loss": 0.7175,
"step": 315
},
{
"epoch": 0.95,
"learning_rate": 0.00039948751645524236,
"loss": 0.6533,
"step": 316
},
{
"epoch": 0.95,
"learning_rate": 0.0003994214859890082,
"loss": 0.5988,
"step": 317
},
{
"epoch": 0.95,
"learning_rate": 0.00039935146162684205,
"loss": 0.5692,
"step": 318
},
{
"epoch": 0.96,
"learning_rate": 0.0003992774447711503,
"loss": 0.5004,
"step": 319
},
{
"epoch": 0.96,
"learning_rate": 0.000399199436904299,
"loss": 0.459,
"step": 320
},
{
"epoch": 0.96,
"eval_loss": 0.49676987528800964,
"eval_runtime": 39.1916,
"eval_samples_per_second": 41.565,
"eval_steps_per_second": 20.795,
"step": 320
},
{
"epoch": 0.96,
"learning_rate": 0.0003991174395885838,
"loss": 0.532,
"step": 321
},
{
"epoch": 0.96,
"learning_rate": 0.0003990314544661984,
"loss": 0.4235,
"step": 322
},
{
"epoch": 0.97,
"learning_rate": 0.00039894148325920223,
"loss": 0.502,
"step": 323
},
{
"epoch": 0.97,
"learning_rate": 0.0003988475277694856,
"loss": 0.5263,
"step": 324
},
{
"epoch": 0.97,
"learning_rate": 0.00039874958987873364,
"loss": 0.5009,
"step": 325
},
{
"epoch": 0.98,
"learning_rate": 0.00039864767154838864,
"loss": 0.6524,
"step": 326
},
{
"epoch": 0.98,
"learning_rate": 0.0003985417748196108,
"loss": 0.731,
"step": 327
},
{
"epoch": 0.98,
"learning_rate": 0.00039843190181323746,
"loss": 0.4875,
"step": 328
},
{
"epoch": 0.99,
"learning_rate": 0.00039831805472974037,
"loss": 0.3963,
"step": 329
},
{
"epoch": 0.99,
"learning_rate": 0.00039820023584918174,
"loss": 0.7317,
"step": 330
},
{
"epoch": 0.99,
"learning_rate": 0.0003980784475311686,
"loss": 0.5558,
"step": 331
},
{
"epoch": 0.99,
"learning_rate": 0.00039795269221480574,
"loss": 0.5645,
"step": 332
},
{
"epoch": 1.0,
"learning_rate": 0.00039782297241864635,
"loss": 0.6321,
"step": 333
},
{
"epoch": 1.0,
"learning_rate": 0.000397689290740642,
"loss": 0.431,
"step": 334
},
{
"epoch": 1.0,
"learning_rate": 0.00039755164985809063,
"loss": 0.4686,
"step": 335
},
{
"epoch": 1.01,
"learning_rate": 0.00039741005252758255,
"loss": 0.6301,
"step": 336
},
{
"epoch": 1.01,
"learning_rate": 0.0003972645015849457,
"loss": 0.4018,
"step": 337
},
{
"epoch": 1.01,
"learning_rate": 0.00039711499994518856,
"loss": 0.6649,
"step": 338
},
{
"epoch": 1.01,
"learning_rate": 0.00039696155060244166,
"loss": 0.4922,
"step": 339
},
{
"epoch": 1.02,
"learning_rate": 0.000396804156629898,
"loss": 0.6138,
"step": 340
},
{
"epoch": 1.02,
"eval_loss": 0.5111443996429443,
"eval_runtime": 39.2254,
"eval_samples_per_second": 41.529,
"eval_steps_per_second": 20.777,
"step": 340
},
{
"epoch": 1.02,
"learning_rate": 0.0003966428211797514,
"loss": 0.4932,
"step": 341
},
{
"epoch": 1.02,
"learning_rate": 0.00039647754748313294,
"loss": 0.4322,
"step": 342
},
{
"epoch": 1.03,
"learning_rate": 0.0003963083388500469,
"loss": 0.577,
"step": 343
},
{
"epoch": 1.03,
"learning_rate": 0.000396135198669304,
"loss": 0.5161,
"step": 344
},
{
"epoch": 1.03,
"learning_rate": 0.00039595813040845353,
"loss": 0.6532,
"step": 345
},
{
"epoch": 1.04,
"learning_rate": 0.0003957771376137144,
"loss": 0.3927,
"step": 346
},
{
"epoch": 1.04,
"learning_rate": 0.00039559222390990353,
"loss": 0.5745,
"step": 347
},
{
"epoch": 1.04,
"learning_rate": 0.00039540339300036344,
"loss": 0.4108,
"step": 348
},
{
"epoch": 1.04,
"learning_rate": 0.0003952106486668884,
"loss": 0.549,
"step": 349
},
{
"epoch": 1.05,
"learning_rate": 0.00039501399476964805,
"loss": 0.3471,
"step": 350
},
{
"epoch": 1.05,
"learning_rate": 0.00039481343524711097,
"loss": 0.5154,
"step": 351
},
{
"epoch": 1.05,
"learning_rate": 0.00039460897411596477,
"loss": 0.4799,
"step": 352
},
{
"epoch": 1.06,
"learning_rate": 0.0003944006154710366,
"loss": 0.4751,
"step": 353
},
{
"epoch": 1.06,
"learning_rate": 0.0003941883634852104,
"loss": 0.429,
"step": 354
},
{
"epoch": 1.06,
"learning_rate": 0.0003939722224093439,
"loss": 0.4617,
"step": 355
},
{
"epoch": 1.07,
"learning_rate": 0.0003937521965721831,
"loss": 0.3747,
"step": 356
},
{
"epoch": 1.07,
"learning_rate": 0.00039352829038027563,
"loss": 0.478,
"step": 357
},
{
"epoch": 1.07,
"learning_rate": 0.0003933005083178828,
"loss": 0.3775,
"step": 358
},
{
"epoch": 1.07,
"learning_rate": 0.0003930688549468894,
"loss": 0.5047,
"step": 359
},
{
"epoch": 1.08,
"learning_rate": 0.0003928333349067125,
"loss": 0.4023,
"step": 360
},
{
"epoch": 1.08,
"eval_loss": 0.5498852729797363,
"eval_runtime": 39.0748,
"eval_samples_per_second": 41.689,
"eval_steps_per_second": 20.857,
"step": 360
},
{
"epoch": 1.08,
"learning_rate": 0.00039259395291420864,
"loss": 0.4544,
"step": 361
},
{
"epoch": 1.08,
"learning_rate": 0.0003923507137635792,
"loss": 0.5693,
"step": 362
},
{
"epoch": 1.09,
"learning_rate": 0.0003921036223262745,
"loss": 0.3904,
"step": 363
},
{
"epoch": 1.09,
"learning_rate": 0.0003918526835508961,
"loss": 0.3278,
"step": 364
},
{
"epoch": 1.09,
"learning_rate": 0.0003915979024630978,
"loss": 0.5908,
"step": 365
},
{
"epoch": 1.1,
"learning_rate": 0.0003913392841654851,
"loss": 0.6124,
"step": 366
},
{
"epoch": 1.1,
"learning_rate": 0.0003910768338375126,
"loss": 0.5616,
"step": 367
},
{
"epoch": 1.1,
"learning_rate": 0.00039081055673538095,
"loss": 0.509,
"step": 368
},
{
"epoch": 1.1,
"learning_rate": 0.0003905404581919307,
"loss": 0.5066,
"step": 369
},
{
"epoch": 1.11,
"learning_rate": 0.0003902665436165364,
"loss": 0.6078,
"step": 370
},
{
"epoch": 1.11,
"learning_rate": 0.00038998881849499755,
"loss": 0.457,
"step": 371
},
{
"epoch": 1.11,
"learning_rate": 0.0003897072883894291,
"loss": 0.4299,
"step": 372
},
{
"epoch": 1.12,
"learning_rate": 0.0003894219589381501,
"loss": 0.5378,
"step": 373
},
{
"epoch": 1.12,
"learning_rate": 0.0003891328358555705,
"loss": 0.3455,
"step": 374
},
{
"epoch": 1.12,
"learning_rate": 0.00038883992493207693,
"loss": 0.5129,
"step": 375
},
{
"epoch": 1.13,
"learning_rate": 0.00038854323203391664,
"loss": 0.5162,
"step": 376
},
{
"epoch": 1.13,
"learning_rate": 0.00038824276310308003,
"loss": 0.4989,
"step": 377
},
{
"epoch": 1.13,
"learning_rate": 0.0003879385241571817,
"loss": 0.4063,
"step": 378
},
{
"epoch": 1.13,
"learning_rate": 0.00038763052128933985,
"loss": 0.4347,
"step": 379
},
{
"epoch": 1.14,
"learning_rate": 0.0003873187606680543,
"loss": 0.4406,
"step": 380
},
{
"epoch": 1.14,
"eval_loss": 0.5657373070716858,
"eval_runtime": 39.1369,
"eval_samples_per_second": 41.623,
"eval_steps_per_second": 20.824,
"step": 380
},
{
"epoch": 1.14,
"learning_rate": 0.000387003248537083,
"loss": 0.6143,
"step": 381
},
{
"epoch": 1.14,
"learning_rate": 0.0003866839912153168,
"loss": 0.3564,
"step": 382
},
{
"epoch": 1.15,
"learning_rate": 0.00038636099509665306,
"loss": 0.3914,
"step": 383
},
{
"epoch": 1.15,
"learning_rate": 0.0003860342666498677,
"loss": 0.4229,
"step": 384
},
{
"epoch": 1.15,
"learning_rate": 0.0003857038124184853,
"loss": 0.52,
"step": 385
},
{
"epoch": 1.16,
"learning_rate": 0.00038536963902064834,
"loss": 0.4873,
"step": 386
},
{
"epoch": 1.16,
"learning_rate": 0.0003850317531489847,
"loss": 0.3773,
"step": 387
},
{
"epoch": 1.16,
"learning_rate": 0.00038469016157047334,
"loss": 0.3672,
"step": 388
},
{
"epoch": 1.16,
"learning_rate": 0.0003843448711263089,
"loss": 0.5072,
"step": 389
},
{
"epoch": 1.17,
"learning_rate": 0.00038399588873176487,
"loss": 0.5866,
"step": 390
},
{
"epoch": 1.17,
"learning_rate": 0.00038364322137605483,
"loss": 0.3751,
"step": 391
},
{
"epoch": 1.17,
"learning_rate": 0.00038328687612219263,
"loss": 0.5793,
"step": 392
},
{
"epoch": 1.18,
"learning_rate": 0.00038292686010685093,
"loss": 0.4443,
"step": 393
},
{
"epoch": 1.18,
"learning_rate": 0.0003825631805402182,
"loss": 0.3881,
"step": 394
},
{
"epoch": 1.18,
"learning_rate": 0.0003821958447058543,
"loss": 0.4709,
"step": 395
},
{
"epoch": 1.19,
"learning_rate": 0.0003818248599605448,
"loss": 0.4203,
"step": 396
},
{
"epoch": 1.19,
"learning_rate": 0.00038145023373415326,
"loss": 0.438,
"step": 397
},
{
"epoch": 1.19,
"learning_rate": 0.0003810719735294731,
"loss": 0.4127,
"step": 398
},
{
"epoch": 1.19,
"learning_rate": 0.00038069008692207646,
"loss": 0.3724,
"step": 399
},
{
"epoch": 1.2,
"learning_rate": 0.0003803045815601633,
"loss": 0.4054,
"step": 400
},
{
"epoch": 1.2,
"eval_loss": 0.5386510491371155,
"eval_runtime": 39.0231,
"eval_samples_per_second": 41.744,
"eval_steps_per_second": 20.885,
"step": 400
},
{
"epoch": 1.2,
"learning_rate": 0.00037991546516440746,
"loss": 0.3894,
"step": 401
},
{
"epoch": 1.2,
"learning_rate": 0.0003795227455278028,
"loss": 0.4255,
"step": 402
},
{
"epoch": 1.21,
"learning_rate": 0.00037912643051550674,
"loss": 0.5649,
"step": 403
},
{
"epoch": 1.21,
"learning_rate": 0.0003787265280646825,
"loss": 0.4947,
"step": 404
},
{
"epoch": 1.21,
"learning_rate": 0.0003783230461843406,
"loss": 0.3681,
"step": 405
},
{
"epoch": 1.22,
"learning_rate": 0.00037791599295517825,
"loss": 0.5551,
"step": 406
},
{
"epoch": 1.22,
"learning_rate": 0.00037750537652941744,
"loss": 0.3648,
"step": 407
},
{
"epoch": 1.22,
"learning_rate": 0.000377091205130642,
"loss": 0.4568,
"step": 408
},
{
"epoch": 1.22,
"learning_rate": 0.0003766734870536323,
"loss": 0.4425,
"step": 409
},
{
"epoch": 1.23,
"learning_rate": 0.0003762522306641998,
"loss": 0.4919,
"step": 410
},
{
"epoch": 1.23,
"learning_rate": 0.00037582744439901896,
"loss": 0.406,
"step": 411
},
{
"epoch": 1.23,
"learning_rate": 0.0003753991367654587,
"loss": 0.3955,
"step": 412
},
{
"epoch": 1.24,
"learning_rate": 0.0003749673163414117,
"loss": 0.6121,
"step": 413
},
{
"epoch": 1.24,
"learning_rate": 0.0003745319917751229,
"loss": 0.5588,
"step": 414
},
{
"epoch": 1.24,
"learning_rate": 0.0003740931717850159,
"loss": 0.4977,
"step": 415
},
{
"epoch": 1.25,
"learning_rate": 0.00037365086515951874,
"loss": 0.4462,
"step": 416
},
{
"epoch": 1.25,
"learning_rate": 0.00037320508075688776,
"loss": 0.4864,
"step": 417
},
{
"epoch": 1.25,
"learning_rate": 0.00037275582750503005,
"loss": 0.3771,
"step": 418
},
{
"epoch": 1.25,
"learning_rate": 0.00037230311440132494,
"loss": 0.4767,
"step": 419
},
{
"epoch": 1.26,
"learning_rate": 0.0003718469505124434,
"loss": 0.4707,
"step": 420
},
{
"epoch": 1.26,
"eval_loss": 0.5697975158691406,
"eval_runtime": 39.0417,
"eval_samples_per_second": 41.725,
"eval_steps_per_second": 20.875,
"step": 420
},
{
"epoch": 1.26,
"learning_rate": 0.00037138734497416684,
"loss": 0.6288,
"step": 421
},
{
"epoch": 1.26,
"learning_rate": 0.00037092430699120407,
"loss": 0.4509,
"step": 422
},
{
"epoch": 1.27,
"learning_rate": 0.0003704578458370067,
"loss": 0.456,
"step": 423
},
{
"epoch": 1.27,
"learning_rate": 0.00036998797085358373,
"loss": 0.3633,
"step": 424
},
{
"epoch": 1.27,
"learning_rate": 0.0003695146914513142,
"loss": 0.5356,
"step": 425
},
{
"epoch": 1.28,
"learning_rate": 0.000369038017108759,
"loss": 0.4065,
"step": 426
},
{
"epoch": 1.28,
"learning_rate": 0.0003685579573724707,
"loss": 0.4022,
"step": 427
},
{
"epoch": 1.28,
"learning_rate": 0.0003680745218568026,
"loss": 0.5808,
"step": 428
},
{
"epoch": 1.28,
"learning_rate": 0.0003675877202437163,
"loss": 0.5291,
"step": 429
},
{
"epoch": 1.29,
"learning_rate": 0.00036709756228258734,
"loss": 0.5039,
"step": 430
},
{
"epoch": 1.29,
"learning_rate": 0.0003666040577900104,
"loss": 0.5416,
"step": 431
},
{
"epoch": 1.29,
"learning_rate": 0.00036610721664960235,
"loss": 0.4544,
"step": 432
},
{
"epoch": 1.3,
"learning_rate": 0.0003656070488118047,
"loss": 0.5335,
"step": 433
},
{
"epoch": 1.3,
"learning_rate": 0.000365103564293684,
"loss": 0.3835,
"step": 434
},
{
"epoch": 1.3,
"learning_rate": 0.0003645967731787313,
"loss": 0.5434,
"step": 435
},
{
"epoch": 1.31,
"learning_rate": 0.00036408668561666014,
"loss": 0.4031,
"step": 436
},
{
"epoch": 1.31,
"learning_rate": 0.00036357331182320344,
"loss": 0.426,
"step": 437
},
{
"epoch": 1.31,
"learning_rate": 0.00036305666207990886,
"loss": 0.6629,
"step": 438
},
{
"epoch": 1.31,
"learning_rate": 0.0003625367467339329,
"loss": 0.3697,
"step": 439
},
{
"epoch": 1.32,
"learning_rate": 0.0003620135761978333,
"loss": 0.577,
"step": 440
},
{
"epoch": 1.32,
"eval_loss": 0.518071711063385,
"eval_runtime": 39.13,
"eval_samples_per_second": 41.631,
"eval_steps_per_second": 20.828,
"step": 440
},
{
"epoch": 1.32,
"learning_rate": 0.0003614871609493614,
"loss": 0.4543,
"step": 441
},
{
"epoch": 1.32,
"learning_rate": 0.00036095751153125113,
"loss": 0.5656,
"step": 442
},
{
"epoch": 1.33,
"learning_rate": 0.0003604246385510088,
"loss": 0.4478,
"step": 443
},
{
"epoch": 1.33,
"learning_rate": 0.0003598885526807003,
"loss": 0.3964,
"step": 444
},
{
"epoch": 1.33,
"learning_rate": 0.0003593492646567372,
"loss": 0.3682,
"step": 445
},
{
"epoch": 1.34,
"learning_rate": 0.00035880678527966224,
"loss": 0.4475,
"step": 446
},
{
"epoch": 1.34,
"learning_rate": 0.0003582611254139324,
"loss": 0.7257,
"step": 447
},
{
"epoch": 1.34,
"learning_rate": 0.00035771229598770174,
"loss": 0.5785,
"step": 448
},
{
"epoch": 1.34,
"learning_rate": 0.00035716030799260237,
"loss": 0.542,
"step": 449
},
{
"epoch": 1.35,
"learning_rate": 0.0003566051724835245,
"loss": 0.2928,
"step": 450
},
{
"epoch": 1.35,
"learning_rate": 0.0003560469005783945,
"loss": 0.5397,
"step": 451
},
{
"epoch": 1.35,
"learning_rate": 0.0003554855034579532,
"loss": 0.4156,
"step": 452
},
{
"epoch": 1.36,
"learning_rate": 0.0003549209923655309,
"loss": 0.5145,
"step": 453
},
{
"epoch": 1.36,
"learning_rate": 0.00035435337860682304,
"loss": 0.4941,
"step": 454
},
{
"epoch": 1.36,
"learning_rate": 0.0003537826735496631,
"loss": 0.4365,
"step": 455
},
{
"epoch": 1.37,
"learning_rate": 0.0003532088886237956,
"loss": 0.4155,
"step": 456
},
{
"epoch": 1.37,
"learning_rate": 0.0003526320353206467,
"loss": 0.5667,
"step": 457
},
{
"epoch": 1.37,
"learning_rate": 0.00035205212519309406,
"loss": 0.3406,
"step": 458
},
{
"epoch": 1.37,
"learning_rate": 0.00035146916985523603,
"loss": 0.5219,
"step": 459
},
{
"epoch": 1.38,
"learning_rate": 0.00035088318098215805,
"loss": 0.279,
"step": 460
},
{
"epoch": 1.38,
"eval_loss": 0.5242519378662109,
"eval_runtime": 39.0363,
"eval_samples_per_second": 41.73,
"eval_steps_per_second": 20.878,
"step": 460
},
{
"epoch": 1.38,
"learning_rate": 0.0003502941703097,
"loss": 0.3764,
"step": 461
},
{
"epoch": 1.38,
"learning_rate": 0.00034970214963422024,
"loss": 0.4389,
"step": 462
},
{
"epoch": 1.39,
"learning_rate": 0.0003491071308123598,
"loss": 0.4601,
"step": 463
},
{
"epoch": 1.39,
"learning_rate": 0.0003485091257608047,
"loss": 0.5373,
"step": 464
},
{
"epoch": 1.39,
"learning_rate": 0.00034790814645604745,
"loss": 0.4069,
"step": 465
},
{
"epoch": 1.4,
"learning_rate": 0.0003473042049341474,
"loss": 0.6186,
"step": 466
},
{
"epoch": 1.4,
"learning_rate": 0.0003466973132904892,
"loss": 0.6,
"step": 467
},
{
"epoch": 1.4,
"learning_rate": 0.00034608748367954067,
"loss": 0.4138,
"step": 468
},
{
"epoch": 1.4,
"learning_rate": 0.00034547472831460976,
"loss": 0.4754,
"step": 469
},
{
"epoch": 1.41,
"learning_rate": 0.00034485905946759967,
"loss": 0.5631,
"step": 470
},
{
"epoch": 1.41,
"learning_rate": 0.00034424048946876294,
"loss": 0.347,
"step": 471
},
{
"epoch": 1.41,
"learning_rate": 0.0003436190307064548,
"loss": 0.505,
"step": 472
},
{
"epoch": 1.42,
"learning_rate": 0.00034299469562688493,
"loss": 0.395,
"step": 473
},
{
"epoch": 1.42,
"learning_rate": 0.0003423674967338681,
"loss": 0.4521,
"step": 474
},
{
"epoch": 1.42,
"learning_rate": 0.000341737446588574,
"loss": 0.62,
"step": 475
},
{
"epoch": 1.43,
"learning_rate": 0.0003411045578092754,
"loss": 0.4563,
"step": 476
},
{
"epoch": 1.43,
"learning_rate": 0.00034046884307109554,
"loss": 0.426,
"step": 477
},
{
"epoch": 1.43,
"learning_rate": 0.0003398303151057543,
"loss": 0.3657,
"step": 478
},
{
"epoch": 1.43,
"learning_rate": 0.0003391889867013134,
"loss": 0.4089,
"step": 479
},
{
"epoch": 1.44,
"learning_rate": 0.00033854487070191994,
"loss": 0.5576,
"step": 480
},
{
"epoch": 1.44,
"eval_loss": 0.5171985626220703,
"eval_runtime": 39.1209,
"eval_samples_per_second": 41.64,
"eval_steps_per_second": 20.833,
"step": 480
},
{
"epoch": 1.44,
"learning_rate": 0.00033789798000754927,
"loss": 0.564,
"step": 481
},
{
"epoch": 1.44,
"learning_rate": 0.0003372483275737468,
"loss": 0.5006,
"step": 482
},
{
"epoch": 1.45,
"learning_rate": 0.0003365959264113683,
"loss": 0.4876,
"step": 483
},
{
"epoch": 1.45,
"learning_rate": 0.00033594078958631984,
"loss": 0.6769,
"step": 484
},
{
"epoch": 1.45,
"learning_rate": 0.00033528293021929526,
"loss": 0.5196,
"step": 485
},
{
"epoch": 1.46,
"learning_rate": 0.00033462236148551407,
"loss": 0.5664,
"step": 486
},
{
"epoch": 1.46,
"learning_rate": 0.00033395909661445737,
"loss": 0.2954,
"step": 487
},
{
"epoch": 1.46,
"learning_rate": 0.0003332931488896029,
"loss": 0.5158,
"step": 488
},
{
"epoch": 1.46,
"learning_rate": 0.00033262453164815904,
"loss": 0.3675,
"step": 489
},
{
"epoch": 1.47,
"learning_rate": 0.0003319532582807977,
"loss": 0.3627,
"step": 490
},
{
"epoch": 1.47,
"learning_rate": 0.00033127934223138594,
"loss": 0.5265,
"step": 491
},
{
"epoch": 1.47,
"learning_rate": 0.000330602796996717,
"loss": 0.4126,
"step": 492
},
{
"epoch": 1.48,
"learning_rate": 0.0003299236361262401,
"loss": 0.4083,
"step": 493
},
{
"epoch": 1.48,
"learning_rate": 0.00032924187322178863,
"loss": 0.4159,
"step": 494
},
{
"epoch": 1.48,
"learning_rate": 0.00032855752193730787,
"loss": 0.376,
"step": 495
},
{
"epoch": 1.49,
"learning_rate": 0.00032787059597858204,
"loss": 0.3039,
"step": 496
},
{
"epoch": 1.49,
"learning_rate": 0.000327181109102959,
"loss": 0.4458,
"step": 497
},
{
"epoch": 1.49,
"learning_rate": 0.00032648907511907547,
"loss": 0.4663,
"step": 498
},
{
"epoch": 1.49,
"learning_rate": 0.00032579450788658,
"loss": 0.4005,
"step": 499
},
{
"epoch": 1.5,
"learning_rate": 0.0003250974213158555,
"loss": 0.382,
"step": 500
},
{
"epoch": 1.5,
"eval_loss": 0.5177609920501709,
"eval_runtime": 39.1238,
"eval_samples_per_second": 41.637,
"eval_steps_per_second": 20.831,
"step": 500
},
{
"epoch": 1.5,
"learning_rate": 0.0003243978293677408,
"loss": 0.4902,
"step": 501
},
{
"epoch": 1.5,
"learning_rate": 0.000323695746053251,
"loss": 0.63,
"step": 502
},
{
"epoch": 1.51,
"learning_rate": 0.00032299118543329666,
"loss": 0.4135,
"step": 503
},
{
"epoch": 1.51,
"learning_rate": 0.00032228416161840246,
"loss": 0.4497,
"step": 504
},
{
"epoch": 1.51,
"learning_rate": 0.0003215746887684244,
"loss": 0.3634,
"step": 505
},
{
"epoch": 1.51,
"learning_rate": 0.0003208627810922665,
"loss": 0.3359,
"step": 506
},
{
"epoch": 1.52,
"learning_rate": 0.0003201484528475958,
"loss": 0.5302,
"step": 507
},
{
"epoch": 1.52,
"learning_rate": 0.00031943171834055724,
"loss": 0.4115,
"step": 508
},
{
"epoch": 1.52,
"learning_rate": 0.00031871259192548695,
"loss": 0.5049,
"step": 509
},
{
"epoch": 1.53,
"learning_rate": 0.00031799108800462464,
"loss": 0.3291,
"step": 510
},
{
"epoch": 1.53,
"learning_rate": 0.0003172672210278254,
"loss": 0.4867,
"step": 511
},
{
"epoch": 1.53,
"learning_rate": 0.00031654100549227026,
"loss": 0.5247,
"step": 512
},
{
"epoch": 1.54,
"learning_rate": 0.0003158124559421758,
"loss": 0.4055,
"step": 513
},
{
"epoch": 1.54,
"learning_rate": 0.00031508158696850276,
"loss": 0.4846,
"step": 514
},
{
"epoch": 1.54,
"learning_rate": 0.00031434841320866395,
"loss": 0.5182,
"step": 515
},
{
"epoch": 1.54,
"learning_rate": 0.00031361294934623114,
"loss": 0.5588,
"step": 516
},
{
"epoch": 1.55,
"learning_rate": 0.000312875210110641,
"loss": 0.6245,
"step": 517
},
{
"epoch": 1.55,
"learning_rate": 0.0003121352102768998,
"loss": 0.332,
"step": 518
},
{
"epoch": 1.55,
"learning_rate": 0.0003113929646652879,
"loss": 0.4909,
"step": 519
},
{
"epoch": 1.56,
"learning_rate": 0.0003106484881410628,
"loss": 0.4541,
"step": 520
},
{
"epoch": 1.56,
"eval_loss": 0.516572892665863,
"eval_runtime": 39.1297,
"eval_samples_per_second": 41.631,
"eval_steps_per_second": 20.828,
"step": 520
},
{
"epoch": 1.56,
"learning_rate": 0.0003099017956141612,
"loss": 0.2962,
"step": 521
},
{
"epoch": 1.56,
"learning_rate": 0.0003091529020389009,
"loss": 0.4434,
"step": 522
},
{
"epoch": 1.57,
"learning_rate": 0.0003084018224136808,
"loss": 0.4728,
"step": 523
},
{
"epoch": 1.57,
"learning_rate": 0.0003076485717806808,
"loss": 0.3787,
"step": 524
},
{
"epoch": 1.57,
"learning_rate": 0.0003068931652255602,
"loss": 0.5694,
"step": 525
},
{
"epoch": 1.57,
"learning_rate": 0.00030613561787715636,
"loss": 0.4464,
"step": 526
},
{
"epoch": 1.58,
"learning_rate": 0.0003053759449071807,
"loss": 0.6158,
"step": 527
},
{
"epoch": 1.58,
"learning_rate": 0.0003046141615299155,
"loss": 0.8141,
"step": 528
},
{
"epoch": 1.58,
"learning_rate": 0.0003038502830019092,
"loss": 0.6886,
"step": 529
},
{
"epoch": 1.59,
"learning_rate": 0.00030308432462167043,
"loss": 0.5019,
"step": 530
},
{
"epoch": 1.59,
"learning_rate": 0.00030231630172936205,
"loss": 0.4838,
"step": 531
},
{
"epoch": 1.59,
"learning_rate": 0.0003015462297064936,
"loss": 0.5484,
"step": 532
},
{
"epoch": 1.6,
"learning_rate": 0.00030077412397561343,
"loss": 0.5688,
"step": 533
},
{
"epoch": 1.6,
"learning_rate": 0.00030000000000000003,
"loss": 0.4014,
"step": 534
},
{
"epoch": 1.6,
"learning_rate": 0.0002992238732833518,
"loss": 0.4936,
"step": 535
},
{
"epoch": 1.6,
"learning_rate": 0.00029844575936947696,
"loss": 0.3926,
"step": 536
},
{
"epoch": 1.61,
"learning_rate": 0.00029766567384198223,
"loss": 0.4229,
"step": 537
},
{
"epoch": 1.61,
"learning_rate": 0.00029688363232396056,
"loss": 0.3198,
"step": 538
},
{
"epoch": 1.61,
"learning_rate": 0.0002960996504776783,
"loss": 0.5628,
"step": 539
},
{
"epoch": 1.62,
"learning_rate": 0.0002953137440042616,
"loss": 0.339,
"step": 540
},
{
"epoch": 1.62,
"eval_loss": 0.5086627006530762,
"eval_runtime": 39.1178,
"eval_samples_per_second": 41.643,
"eval_steps_per_second": 20.834,
"step": 540
},
{
"epoch": 1.62,
"learning_rate": 0.00029452592864338194,
"loss": 0.5298,
"step": 541
},
{
"epoch": 1.62,
"learning_rate": 0.00029373622017294076,
"loss": 0.4892,
"step": 542
},
{
"epoch": 1.63,
"learning_rate": 0.0002929446344087537,
"loss": 0.3387,
"step": 543
},
{
"epoch": 1.63,
"learning_rate": 0.0002921511872042337,
"loss": 0.4144,
"step": 544
},
{
"epoch": 1.63,
"learning_rate": 0.00029135589445007356,
"loss": 0.3239,
"step": 545
},
{
"epoch": 1.63,
"learning_rate": 0.00029055877207392753,
"loss": 0.3875,
"step": 546
},
{
"epoch": 1.64,
"learning_rate": 0.00028975983604009246,
"loss": 0.3716,
"step": 547
},
{
"epoch": 1.64,
"learning_rate": 0.00028895910234918824,
"loss": 0.6995,
"step": 548
},
{
"epoch": 1.64,
"learning_rate": 0.00028815658703783715,
"loss": 0.524,
"step": 549
},
{
"epoch": 1.65,
"learning_rate": 0.00028735230617834255,
"loss": 0.5495,
"step": 550
},
{
"epoch": 1.65,
"learning_rate": 0.00028654627587836723,
"loss": 0.5321,
"step": 551
},
{
"epoch": 1.65,
"learning_rate": 0.00028573851228061084,
"loss": 0.6363,
"step": 552
},
{
"epoch": 1.66,
"learning_rate": 0.0002849290315624864,
"loss": 0.4375,
"step": 553
},
{
"epoch": 1.66,
"learning_rate": 0.00028411784993579635,
"loss": 0.4915,
"step": 554
},
{
"epoch": 1.66,
"learning_rate": 0.00028330498364640804,
"loss": 0.4506,
"step": 555
},
{
"epoch": 1.66,
"learning_rate": 0.0002824904489739281,
"loss": 0.3577,
"step": 556
},
{
"epoch": 1.67,
"learning_rate": 0.00028167426223137685,
"loss": 0.3603,
"step": 557
},
{
"epoch": 1.67,
"learning_rate": 0.000280856439764861,
"loss": 0.4757,
"step": 558
},
{
"epoch": 1.67,
"learning_rate": 0.00028003699795324673,
"loss": 0.3465,
"step": 559
},
{
"epoch": 1.68,
"learning_rate": 0.0002792159532078314,
"loss": 0.4609,
"step": 560
},
{
"epoch": 1.68,
"eval_loss": 0.5257359147071838,
"eval_runtime": 39.0772,
"eval_samples_per_second": 41.687,
"eval_steps_per_second": 20.856,
"step": 560
},
{
"epoch": 1.68,
"learning_rate": 0.00027839332197201506,
"loss": 0.5903,
"step": 561
},
{
"epoch": 1.68,
"learning_rate": 0.000277569120720971,
"loss": 0.5743,
"step": 562
},
{
"epoch": 1.69,
"learning_rate": 0.0002767433659613159,
"loss": 0.5751,
"step": 563
},
{
"epoch": 1.69,
"learning_rate": 0.0002759160742307793,
"loss": 0.4579,
"step": 564
},
{
"epoch": 1.69,
"learning_rate": 0.000275087262097872,
"loss": 0.3828,
"step": 565
},
{
"epoch": 1.69,
"learning_rate": 0.0002742569461615547,
"loss": 0.3544,
"step": 566
},
{
"epoch": 1.7,
"learning_rate": 0.00027342514305090553,
"loss": 0.4301,
"step": 567
},
{
"epoch": 1.7,
"learning_rate": 0.00027259186942478654,
"loss": 0.3553,
"step": 568
},
{
"epoch": 1.7,
"learning_rate": 0.0002717571419715107,
"loss": 0.4837,
"step": 569
},
{
"epoch": 1.71,
"learning_rate": 0.0002709209774085071,
"loss": 0.4446,
"step": 570
},
{
"epoch": 1.71,
"learning_rate": 0.00027008339248198675,
"loss": 0.6023,
"step": 571
},
{
"epoch": 1.71,
"learning_rate": 0.00026924440396660656,
"loss": 0.4305,
"step": 572
},
{
"epoch": 1.72,
"learning_rate": 0.00026840402866513377,
"loss": 0.3237,
"step": 573
},
{
"epoch": 1.72,
"learning_rate": 0.0002675622834081095,
"loss": 0.6138,
"step": 574
},
{
"epoch": 1.72,
"learning_rate": 0.0002667191850535113,
"loss": 0.406,
"step": 575
},
{
"epoch": 1.72,
"learning_rate": 0.00026587475048641594,
"loss": 0.4759,
"step": 576
},
{
"epoch": 1.73,
"learning_rate": 0.000265028996618661,
"loss": 0.595,
"step": 577
},
{
"epoch": 1.73,
"learning_rate": 0.0002641819403885063,
"loss": 0.3512,
"step": 578
},
{
"epoch": 1.73,
"learning_rate": 0.00026333359876029453,
"loss": 0.4497,
"step": 579
},
{
"epoch": 1.74,
"learning_rate": 0.0002624839887241115,
"loss": 0.4768,
"step": 580
},
{
"epoch": 1.74,
"eval_loss": 0.4989789128303528,
"eval_runtime": 38.8281,
"eval_samples_per_second": 41.954,
"eval_steps_per_second": 20.99,
"step": 580
},
{
"epoch": 1.74,
"learning_rate": 0.00026163312729544615,
"loss": 0.3918,
"step": 581
},
{
"epoch": 1.74,
"learning_rate": 0.0002607810315148494,
"loss": 0.5133,
"step": 582
},
{
"epoch": 1.75,
"learning_rate": 0.00025992771844759316,
"loss": 0.5705,
"step": 583
},
{
"epoch": 1.75,
"learning_rate": 0.00025907320518332825,
"loss": 0.4736,
"step": 584
},
{
"epoch": 1.75,
"learning_rate": 0.00025821750883574257,
"loss": 0.3043,
"step": 585
},
{
"epoch": 1.75,
"learning_rate": 0.0002573606465422181,
"loss": 0.4725,
"step": 586
},
{
"epoch": 1.76,
"learning_rate": 0.0002565026354634874,
"loss": 0.522,
"step": 587
},
{
"epoch": 1.76,
"learning_rate": 0.0002556434927832906,
"loss": 0.3749,
"step": 588
},
{
"epoch": 1.76,
"learning_rate": 0.00025478323570803053,
"loss": 0.482,
"step": 589
},
{
"epoch": 1.77,
"learning_rate": 0.0002539218814664288,
"loss": 0.6841,
"step": 590
},
{
"epoch": 1.77,
"learning_rate": 0.0002530594473091802,
"loss": 0.2958,
"step": 591
},
{
"epoch": 1.77,
"learning_rate": 0.00025219595050860746,
"loss": 0.5809,
"step": 592
},
{
"epoch": 1.78,
"learning_rate": 0.00025133140835831535,
"loss": 0.5042,
"step": 593
},
{
"epoch": 1.78,
"learning_rate": 0.00025046583817284434,
"loss": 0.6835,
"step": 594
},
{
"epoch": 1.78,
"learning_rate": 0.0002495992572873237,
"loss": 0.4265,
"step": 595
},
{
"epoch": 1.78,
"learning_rate": 0.0002487316830571244,
"loss": 0.427,
"step": 596
},
{
"epoch": 1.79,
"learning_rate": 0.0002478631328575116,
"loss": 0.2882,
"step": 597
},
{
"epoch": 1.79,
"learning_rate": 0.0002469936240832965,
"loss": 0.4629,
"step": 598
},
{
"epoch": 1.79,
"learning_rate": 0.00024612317414848806,
"loss": 0.6129,
"step": 599
},
{
"epoch": 1.8,
"learning_rate": 0.0002452518004859445,
"loss": 0.5313,
"step": 600
},
{
"epoch": 1.8,
"eval_loss": 0.4951966106891632,
"eval_runtime": 39.0975,
"eval_samples_per_second": 41.665,
"eval_steps_per_second": 20.845,
"step": 600
},
{
"epoch": 1.8,
"learning_rate": 0.00024437952054702354,
"loss": 0.5254,
"step": 601
},
{
"epoch": 1.8,
"learning_rate": 0.00024350635180123349,
"loss": 0.467,
"step": 602
},
{
"epoch": 1.81,
"learning_rate": 0.0002426323117358832,
"loss": 0.4913,
"step": 603
},
{
"epoch": 1.81,
"learning_rate": 0.00024175741785573176,
"loss": 0.4806,
"step": 604
},
{
"epoch": 1.81,
"learning_rate": 0.0002408816876826378,
"loss": 0.421,
"step": 605
},
{
"epoch": 1.81,
"learning_rate": 0.0002400051387552089,
"loss": 0.5413,
"step": 606
},
{
"epoch": 1.82,
"learning_rate": 0.00023912778862845014,
"loss": 0.5817,
"step": 607
},
{
"epoch": 1.82,
"learning_rate": 0.00023824965487341247,
"loss": 0.4123,
"step": 608
},
{
"epoch": 1.82,
"learning_rate": 0.00023737075507684102,
"loss": 0.4143,
"step": 609
},
{
"epoch": 1.83,
"learning_rate": 0.00023649110684082256,
"loss": 0.5556,
"step": 610
},
{
"epoch": 1.83,
"learning_rate": 0.00023561072778243336,
"loss": 0.7397,
"step": 611
},
{
"epoch": 1.83,
"learning_rate": 0.00023472963553338613,
"loss": 0.2856,
"step": 612
},
{
"epoch": 1.84,
"learning_rate": 0.00023384784773967674,
"loss": 0.3371,
"step": 613
},
{
"epoch": 1.84,
"learning_rate": 0.00023296538206123133,
"loss": 0.5207,
"step": 614
},
{
"epoch": 1.84,
"learning_rate": 0.00023208225617155206,
"loss": 0.4478,
"step": 615
},
{
"epoch": 1.84,
"learning_rate": 0.00023119848775736358,
"loss": 0.4692,
"step": 616
},
{
"epoch": 1.85,
"learning_rate": 0.00023031409451825853,
"loss": 0.4573,
"step": 617
},
{
"epoch": 1.85,
"learning_rate": 0.00022942909416634325,
"loss": 0.4242,
"step": 618
},
{
"epoch": 1.85,
"learning_rate": 0.00022854350442588287,
"loss": 0.5599,
"step": 619
},
{
"epoch": 1.86,
"learning_rate": 0.00022765734303294664,
"loss": 0.347,
"step": 620
},
{
"epoch": 1.86,
"eval_loss": 0.4822976887226105,
"eval_runtime": 39.0799,
"eval_samples_per_second": 41.684,
"eval_steps_per_second": 20.855,
"step": 620
},
{
"epoch": 1.86,
"learning_rate": 0.00022677062773505236,
"loss": 0.4158,
"step": 621
},
{
"epoch": 1.86,
"learning_rate": 0.00022588337629081106,
"loss": 0.3382,
"step": 622
},
{
"epoch": 1.87,
"learning_rate": 0.0002249956064695717,
"loss": 0.4924,
"step": 623
},
{
"epoch": 1.87,
"learning_rate": 0.0002241073360510646,
"loss": 0.3995,
"step": 624
},
{
"epoch": 1.87,
"learning_rate": 0.00022321858282504605,
"loss": 0.4438,
"step": 625
},
{
"epoch": 1.87,
"learning_rate": 0.0002223293645909416,
"loss": 0.3933,
"step": 626
},
{
"epoch": 1.88,
"learning_rate": 0.00022143969915748959,
"loss": 0.386,
"step": 627
},
{
"epoch": 1.88,
"learning_rate": 0.00022054960434238487,
"loss": 0.6419,
"step": 628
},
{
"epoch": 1.88,
"learning_rate": 0.00021965909797192143,
"loss": 0.3969,
"step": 629
},
{
"epoch": 1.89,
"learning_rate": 0.00021876819788063588,
"loss": 0.3944,
"step": 630
},
{
"epoch": 1.89,
"learning_rate": 0.00021787692191094986,
"loss": 0.4672,
"step": 631
},
{
"epoch": 1.89,
"learning_rate": 0.00021698528791281297,
"loss": 0.5495,
"step": 632
},
{
"epoch": 1.9,
"learning_rate": 0.00021609331374334523,
"loss": 0.49,
"step": 633
},
{
"epoch": 1.9,
"learning_rate": 0.00021520101726647922,
"loss": 0.4275,
"step": 634
},
{
"epoch": 1.9,
"learning_rate": 0.00021430841635260275,
"loss": 0.4274,
"step": 635
},
{
"epoch": 1.9,
"learning_rate": 0.0002134155288782005,
"loss": 0.5855,
"step": 636
},
{
"epoch": 1.91,
"learning_rate": 0.0002125223727254964,
"loss": 0.5355,
"step": 637
},
{
"epoch": 1.91,
"learning_rate": 0.00021162896578209517,
"loss": 0.3813,
"step": 638
},
{
"epoch": 1.91,
"learning_rate": 0.0002107353259406243,
"loss": 0.4637,
"step": 639
},
{
"epoch": 1.92,
"learning_rate": 0.00020984147109837564,
"loss": 0.4216,
"step": 640
},
{
"epoch": 1.92,
"eval_loss": 0.48321226239204407,
"eval_runtime": 38.9518,
"eval_samples_per_second": 41.821,
"eval_steps_per_second": 20.923,
"step": 640
},
{
"epoch": 1.92,
"learning_rate": 0.00020894741915694685,
"loss": 0.3868,
"step": 641
},
{
"epoch": 1.92,
"learning_rate": 0.00020805318802188304,
"loss": 0.4371,
"step": 642
},
{
"epoch": 1.93,
"learning_rate": 0.00020715879560231811,
"loss": 0.3519,
"step": 643
},
{
"epoch": 1.93,
"learning_rate": 0.00020626425981061606,
"loss": 0.4148,
"step": 644
},
{
"epoch": 1.93,
"learning_rate": 0.00020536959856201227,
"loss": 0.3349,
"step": 645
},
{
"epoch": 1.93,
"learning_rate": 0.00020447482977425466,
"loss": 0.3314,
"step": 646
},
{
"epoch": 1.94,
"learning_rate": 0.00020357997136724487,
"loss": 0.5866,
"step": 647
},
{
"epoch": 1.94,
"learning_rate": 0.0002026850412626795,
"loss": 0.4521,
"step": 648
},
{
"epoch": 1.94,
"learning_rate": 0.00020179005738369096,
"loss": 0.4659,
"step": 649
},
{
"epoch": 1.95,
"learning_rate": 0.0002008950376544887,
"loss": 0.5333,
"step": 650
},
{
"epoch": 1.95,
"learning_rate": 0.0002,
"loss": 0.4153,
"step": 651
},
{
"epoch": 1.95,
"learning_rate": 0.00019910496234551133,
"loss": 0.4381,
"step": 652
},
{
"epoch": 1.96,
"learning_rate": 0.0001982099426163091,
"loss": 0.3161,
"step": 653
},
{
"epoch": 1.96,
"learning_rate": 0.00019731495873732055,
"loss": 0.444,
"step": 654
},
{
"epoch": 1.96,
"learning_rate": 0.00019642002863275518,
"loss": 0.3875,
"step": 655
},
{
"epoch": 1.96,
"learning_rate": 0.00019552517022574541,
"loss": 0.3661,
"step": 656
},
{
"epoch": 1.97,
"learning_rate": 0.0001946304014379878,
"loss": 0.376,
"step": 657
},
{
"epoch": 1.97,
"learning_rate": 0.000193735740189384,
"loss": 0.4913,
"step": 658
},
{
"epoch": 1.97,
"learning_rate": 0.0001928412043976819,
"loss": 0.5028,
"step": 659
},
{
"epoch": 1.98,
"learning_rate": 0.00019194681197811704,
"loss": 0.3905,
"step": 660
},
{
"epoch": 1.98,
"eval_loss": 0.47484511137008667,
"eval_runtime": 39.0824,
"eval_samples_per_second": 41.681,
"eval_steps_per_second": 20.853,
"step": 660
},
{
"epoch": 1.98,
"learning_rate": 0.0001910525808430532,
"loss": 0.4522,
"step": 661
},
{
"epoch": 1.98,
"learning_rate": 0.00019015852890162438,
"loss": 0.303,
"step": 662
},
{
"epoch": 1.99,
"learning_rate": 0.00018926467405937567,
"loss": 0.3451,
"step": 663
},
{
"epoch": 1.99,
"learning_rate": 0.00018837103421790485,
"loss": 0.4639,
"step": 664
},
{
"epoch": 1.99,
"learning_rate": 0.00018747762727450363,
"loss": 0.5916,
"step": 665
},
{
"epoch": 1.99,
"learning_rate": 0.0001865844711217995,
"loss": 0.5945,
"step": 666
},
{
"epoch": 2.0,
"learning_rate": 0.00018569158364739735,
"loss": 0.4625,
"step": 667
},
{
"epoch": 2.0,
"learning_rate": 0.00018479898273352082,
"loss": 0.3358,
"step": 668
}
],
"logging_steps": 1,
"max_steps": 1002,
"num_train_epochs": 3,
"save_steps": 500,
"total_flos": 1.8897791269868667e+18,
"trial_name": null,
"trial_params": null
}