dima806's picture
Upload folder using huggingface_hub
2506675
raw
history blame
No virus
73.5 kB
{
"best_metric": 0.18054482340812683,
"best_model_checkpoint": "cat_dog_sounds_classification/checkpoint-594",
"epoch": 9.0,
"global_step": 594,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 1.0000000000000001e-07,
"loss": 0.7073,
"step": 1
},
{
"epoch": 0.03,
"learning_rate": 2.0000000000000002e-07,
"loss": 0.6877,
"step": 2
},
{
"epoch": 0.05,
"learning_rate": 3.0000000000000004e-07,
"loss": 0.7053,
"step": 3
},
{
"epoch": 0.06,
"learning_rate": 4.0000000000000003e-07,
"loss": 0.6912,
"step": 4
},
{
"epoch": 0.08,
"learning_rate": 5.000000000000001e-07,
"loss": 0.6998,
"step": 5
},
{
"epoch": 0.09,
"learning_rate": 6.000000000000001e-07,
"loss": 0.6961,
"step": 6
},
{
"epoch": 0.11,
"learning_rate": 7.000000000000001e-07,
"loss": 0.7068,
"step": 7
},
{
"epoch": 0.12,
"learning_rate": 8.000000000000001e-07,
"loss": 0.7004,
"step": 8
},
{
"epoch": 0.14,
"learning_rate": 9.000000000000001e-07,
"loss": 0.6771,
"step": 9
},
{
"epoch": 0.15,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.6778,
"step": 10
},
{
"epoch": 0.17,
"learning_rate": 1.1e-06,
"loss": 0.6763,
"step": 11
},
{
"epoch": 0.18,
"learning_rate": 1.2000000000000002e-06,
"loss": 0.6894,
"step": 12
},
{
"epoch": 0.2,
"learning_rate": 1.3e-06,
"loss": 0.6848,
"step": 13
},
{
"epoch": 0.21,
"learning_rate": 1.4000000000000001e-06,
"loss": 0.6854,
"step": 14
},
{
"epoch": 0.23,
"learning_rate": 1.5e-06,
"loss": 0.6875,
"step": 15
},
{
"epoch": 0.24,
"learning_rate": 1.6000000000000001e-06,
"loss": 0.7022,
"step": 16
},
{
"epoch": 0.26,
"learning_rate": 1.7000000000000002e-06,
"loss": 0.6683,
"step": 17
},
{
"epoch": 0.27,
"learning_rate": 1.8000000000000001e-06,
"loss": 0.7008,
"step": 18
},
{
"epoch": 0.29,
"learning_rate": 1.9000000000000002e-06,
"loss": 0.6789,
"step": 19
},
{
"epoch": 0.3,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.7054,
"step": 20
},
{
"epoch": 0.32,
"learning_rate": 2.1000000000000002e-06,
"loss": 0.6824,
"step": 21
},
{
"epoch": 0.33,
"learning_rate": 2.2e-06,
"loss": 0.6826,
"step": 22
},
{
"epoch": 0.35,
"learning_rate": 2.3000000000000004e-06,
"loss": 0.688,
"step": 23
},
{
"epoch": 0.36,
"learning_rate": 2.4000000000000003e-06,
"loss": 0.6835,
"step": 24
},
{
"epoch": 0.38,
"learning_rate": 2.5e-06,
"loss": 0.7085,
"step": 25
},
{
"epoch": 0.39,
"learning_rate": 2.6e-06,
"loss": 0.7053,
"step": 26
},
{
"epoch": 0.41,
"learning_rate": 2.7000000000000004e-06,
"loss": 0.6684,
"step": 27
},
{
"epoch": 0.42,
"learning_rate": 2.8000000000000003e-06,
"loss": 0.6799,
"step": 28
},
{
"epoch": 0.44,
"learning_rate": 2.9e-06,
"loss": 0.6832,
"step": 29
},
{
"epoch": 0.45,
"learning_rate": 3e-06,
"loss": 0.6846,
"step": 30
},
{
"epoch": 0.47,
"learning_rate": 3.1000000000000004e-06,
"loss": 0.6922,
"step": 31
},
{
"epoch": 0.48,
"learning_rate": 3.2000000000000003e-06,
"loss": 0.6649,
"step": 32
},
{
"epoch": 0.5,
"learning_rate": 3.3000000000000006e-06,
"loss": 0.6956,
"step": 33
},
{
"epoch": 0.52,
"learning_rate": 3.4000000000000005e-06,
"loss": 0.6748,
"step": 34
},
{
"epoch": 0.53,
"learning_rate": 3.5e-06,
"loss": 0.686,
"step": 35
},
{
"epoch": 0.55,
"learning_rate": 3.6000000000000003e-06,
"loss": 0.6987,
"step": 36
},
{
"epoch": 0.56,
"learning_rate": 3.7e-06,
"loss": 0.7159,
"step": 37
},
{
"epoch": 0.58,
"learning_rate": 3.8000000000000005e-06,
"loss": 0.7099,
"step": 38
},
{
"epoch": 0.59,
"learning_rate": 3.900000000000001e-06,
"loss": 0.6821,
"step": 39
},
{
"epoch": 0.61,
"learning_rate": 4.000000000000001e-06,
"loss": 0.7196,
"step": 40
},
{
"epoch": 0.62,
"learning_rate": 4.1e-06,
"loss": 0.6929,
"step": 41
},
{
"epoch": 0.64,
"learning_rate": 4.2000000000000004e-06,
"loss": 0.6609,
"step": 42
},
{
"epoch": 0.65,
"learning_rate": 4.3e-06,
"loss": 0.6723,
"step": 43
},
{
"epoch": 0.67,
"learning_rate": 4.4e-06,
"loss": 0.6687,
"step": 44
},
{
"epoch": 0.68,
"learning_rate": 4.5e-06,
"loss": 0.6905,
"step": 45
},
{
"epoch": 0.7,
"learning_rate": 4.600000000000001e-06,
"loss": 0.703,
"step": 46
},
{
"epoch": 0.71,
"learning_rate": 4.7e-06,
"loss": 0.6729,
"step": 47
},
{
"epoch": 0.73,
"learning_rate": 4.800000000000001e-06,
"loss": 0.6754,
"step": 48
},
{
"epoch": 0.74,
"learning_rate": 4.9000000000000005e-06,
"loss": 0.6966,
"step": 49
},
{
"epoch": 0.76,
"learning_rate": 5e-06,
"loss": 0.6825,
"step": 50
},
{
"epoch": 0.77,
"learning_rate": 4.996062992125984e-06,
"loss": 0.6912,
"step": 51
},
{
"epoch": 0.79,
"learning_rate": 4.992125984251969e-06,
"loss": 0.6679,
"step": 52
},
{
"epoch": 0.8,
"learning_rate": 4.9881889763779535e-06,
"loss": 0.6755,
"step": 53
},
{
"epoch": 0.82,
"learning_rate": 4.984251968503937e-06,
"loss": 0.6728,
"step": 54
},
{
"epoch": 0.83,
"learning_rate": 4.980314960629922e-06,
"loss": 0.6923,
"step": 55
},
{
"epoch": 0.85,
"learning_rate": 4.976377952755906e-06,
"loss": 0.6701,
"step": 56
},
{
"epoch": 0.86,
"learning_rate": 4.97244094488189e-06,
"loss": 0.6872,
"step": 57
},
{
"epoch": 0.88,
"learning_rate": 4.968503937007874e-06,
"loss": 0.6747,
"step": 58
},
{
"epoch": 0.89,
"learning_rate": 4.964566929133859e-06,
"loss": 0.6365,
"step": 59
},
{
"epoch": 0.91,
"learning_rate": 4.960629921259843e-06,
"loss": 0.6946,
"step": 60
},
{
"epoch": 0.92,
"learning_rate": 4.956692913385827e-06,
"loss": 0.6871,
"step": 61
},
{
"epoch": 0.94,
"learning_rate": 4.952755905511811e-06,
"loss": 0.6927,
"step": 62
},
{
"epoch": 0.95,
"learning_rate": 4.948818897637796e-06,
"loss": 0.6347,
"step": 63
},
{
"epoch": 0.97,
"learning_rate": 4.94488188976378e-06,
"loss": 0.6879,
"step": 64
},
{
"epoch": 0.98,
"learning_rate": 4.940944881889764e-06,
"loss": 0.664,
"step": 65
},
{
"epoch": 1.0,
"learning_rate": 4.937007874015749e-06,
"loss": 0.6729,
"step": 66
},
{
"epoch": 1.0,
"eval_accuracy": 0.6060606060606061,
"eval_loss": 0.6856966614723206,
"eval_runtime": 6.2798,
"eval_samples_per_second": 10.51,
"eval_steps_per_second": 2.707,
"step": 66
},
{
"epoch": 1.02,
"learning_rate": 4.9330708661417326e-06,
"loss": 0.6889,
"step": 67
},
{
"epoch": 1.03,
"learning_rate": 4.929133858267716e-06,
"loss": 0.6719,
"step": 68
},
{
"epoch": 1.05,
"learning_rate": 4.925196850393702e-06,
"loss": 0.6741,
"step": 69
},
{
"epoch": 1.06,
"learning_rate": 4.921259842519686e-06,
"loss": 0.6327,
"step": 70
},
{
"epoch": 1.08,
"learning_rate": 4.9173228346456694e-06,
"loss": 0.6793,
"step": 71
},
{
"epoch": 1.09,
"learning_rate": 4.913385826771654e-06,
"loss": 0.672,
"step": 72
},
{
"epoch": 1.11,
"learning_rate": 4.909448818897638e-06,
"loss": 0.6736,
"step": 73
},
{
"epoch": 1.12,
"learning_rate": 4.9055118110236225e-06,
"loss": 0.6702,
"step": 74
},
{
"epoch": 1.14,
"learning_rate": 4.901574803149607e-06,
"loss": 0.6439,
"step": 75
},
{
"epoch": 1.15,
"learning_rate": 4.897637795275591e-06,
"loss": 0.6697,
"step": 76
},
{
"epoch": 1.17,
"learning_rate": 4.893700787401575e-06,
"loss": 0.6766,
"step": 77
},
{
"epoch": 1.18,
"learning_rate": 4.889763779527559e-06,
"loss": 0.6173,
"step": 78
},
{
"epoch": 1.2,
"learning_rate": 4.885826771653543e-06,
"loss": 0.6802,
"step": 79
},
{
"epoch": 1.21,
"learning_rate": 4.881889763779528e-06,
"loss": 0.6312,
"step": 80
},
{
"epoch": 1.23,
"learning_rate": 4.8779527559055125e-06,
"loss": 0.6695,
"step": 81
},
{
"epoch": 1.24,
"learning_rate": 4.874015748031496e-06,
"loss": 0.6467,
"step": 82
},
{
"epoch": 1.26,
"learning_rate": 4.870078740157481e-06,
"loss": 0.6835,
"step": 83
},
{
"epoch": 1.27,
"learning_rate": 4.866141732283465e-06,
"loss": 0.638,
"step": 84
},
{
"epoch": 1.29,
"learning_rate": 4.862204724409449e-06,
"loss": 0.6197,
"step": 85
},
{
"epoch": 1.3,
"learning_rate": 4.858267716535434e-06,
"loss": 0.6398,
"step": 86
},
{
"epoch": 1.32,
"learning_rate": 4.854330708661418e-06,
"loss": 0.6617,
"step": 87
},
{
"epoch": 1.33,
"learning_rate": 4.850393700787402e-06,
"loss": 0.6413,
"step": 88
},
{
"epoch": 1.35,
"learning_rate": 4.846456692913386e-06,
"loss": 0.6386,
"step": 89
},
{
"epoch": 1.36,
"learning_rate": 4.84251968503937e-06,
"loss": 0.6712,
"step": 90
},
{
"epoch": 1.38,
"learning_rate": 4.838582677165355e-06,
"loss": 0.6349,
"step": 91
},
{
"epoch": 1.39,
"learning_rate": 4.834645669291339e-06,
"loss": 0.659,
"step": 92
},
{
"epoch": 1.41,
"learning_rate": 4.830708661417323e-06,
"loss": 0.6665,
"step": 93
},
{
"epoch": 1.42,
"learning_rate": 4.826771653543308e-06,
"loss": 0.6042,
"step": 94
},
{
"epoch": 1.44,
"learning_rate": 4.8228346456692916e-06,
"loss": 0.6762,
"step": 95
},
{
"epoch": 1.45,
"learning_rate": 4.818897637795276e-06,
"loss": 0.5887,
"step": 96
},
{
"epoch": 1.47,
"learning_rate": 4.81496062992126e-06,
"loss": 0.6614,
"step": 97
},
{
"epoch": 1.48,
"learning_rate": 4.811023622047245e-06,
"loss": 0.6639,
"step": 98
},
{
"epoch": 1.5,
"learning_rate": 4.8070866141732284e-06,
"loss": 0.6283,
"step": 99
},
{
"epoch": 1.52,
"learning_rate": 4.803149606299213e-06,
"loss": 0.6996,
"step": 100
},
{
"epoch": 1.53,
"learning_rate": 4.799212598425198e-06,
"loss": 0.6321,
"step": 101
},
{
"epoch": 1.55,
"learning_rate": 4.7952755905511815e-06,
"loss": 0.6023,
"step": 102
},
{
"epoch": 1.56,
"learning_rate": 4.791338582677166e-06,
"loss": 0.6921,
"step": 103
},
{
"epoch": 1.58,
"learning_rate": 4.78740157480315e-06,
"loss": 0.6572,
"step": 104
},
{
"epoch": 1.59,
"learning_rate": 4.783464566929134e-06,
"loss": 0.6463,
"step": 105
},
{
"epoch": 1.61,
"learning_rate": 4.779527559055118e-06,
"loss": 0.5887,
"step": 106
},
{
"epoch": 1.62,
"learning_rate": 4.775590551181103e-06,
"loss": 0.6794,
"step": 107
},
{
"epoch": 1.64,
"learning_rate": 4.771653543307087e-06,
"loss": 0.6947,
"step": 108
},
{
"epoch": 1.65,
"learning_rate": 4.7677165354330715e-06,
"loss": 0.6205,
"step": 109
},
{
"epoch": 1.67,
"learning_rate": 4.763779527559055e-06,
"loss": 0.6743,
"step": 110
},
{
"epoch": 1.68,
"learning_rate": 4.75984251968504e-06,
"loss": 0.6543,
"step": 111
},
{
"epoch": 1.7,
"learning_rate": 4.7559055118110246e-06,
"loss": 0.6636,
"step": 112
},
{
"epoch": 1.71,
"learning_rate": 4.751968503937008e-06,
"loss": 0.6826,
"step": 113
},
{
"epoch": 1.73,
"learning_rate": 4.748031496062992e-06,
"loss": 0.6454,
"step": 114
},
{
"epoch": 1.74,
"learning_rate": 4.744094488188977e-06,
"loss": 0.6453,
"step": 115
},
{
"epoch": 1.76,
"learning_rate": 4.740157480314961e-06,
"loss": 0.681,
"step": 116
},
{
"epoch": 1.77,
"learning_rate": 4.736220472440945e-06,
"loss": 0.5993,
"step": 117
},
{
"epoch": 1.79,
"learning_rate": 4.73228346456693e-06,
"loss": 0.6114,
"step": 118
},
{
"epoch": 1.8,
"learning_rate": 4.728346456692914e-06,
"loss": 0.6765,
"step": 119
},
{
"epoch": 1.82,
"learning_rate": 4.724409448818898e-06,
"loss": 0.7033,
"step": 120
},
{
"epoch": 1.83,
"learning_rate": 4.720472440944882e-06,
"loss": 0.64,
"step": 121
},
{
"epoch": 1.85,
"learning_rate": 4.716535433070866e-06,
"loss": 0.6224,
"step": 122
},
{
"epoch": 1.86,
"learning_rate": 4.7125984251968506e-06,
"loss": 0.5752,
"step": 123
},
{
"epoch": 1.88,
"learning_rate": 4.708661417322835e-06,
"loss": 0.6047,
"step": 124
},
{
"epoch": 1.89,
"learning_rate": 4.704724409448819e-06,
"loss": 0.6562,
"step": 125
},
{
"epoch": 1.91,
"learning_rate": 4.700787401574804e-06,
"loss": 0.6247,
"step": 126
},
{
"epoch": 1.92,
"learning_rate": 4.6968503937007874e-06,
"loss": 0.6994,
"step": 127
},
{
"epoch": 1.94,
"learning_rate": 4.692913385826772e-06,
"loss": 0.7222,
"step": 128
},
{
"epoch": 1.95,
"learning_rate": 4.688976377952757e-06,
"loss": 0.6639,
"step": 129
},
{
"epoch": 1.97,
"learning_rate": 4.6850393700787405e-06,
"loss": 0.6009,
"step": 130
},
{
"epoch": 1.98,
"learning_rate": 4.681102362204724e-06,
"loss": 0.6718,
"step": 131
},
{
"epoch": 2.0,
"learning_rate": 4.677165354330709e-06,
"loss": 0.5929,
"step": 132
},
{
"epoch": 2.0,
"eval_accuracy": 0.7121212121212122,
"eval_loss": 0.6547654867172241,
"eval_runtime": 6.4368,
"eval_samples_per_second": 10.254,
"eval_steps_per_second": 2.641,
"step": 132
},
{
"epoch": 2.02,
"learning_rate": 4.673228346456694e-06,
"loss": 0.5657,
"step": 133
},
{
"epoch": 2.03,
"learning_rate": 4.669291338582677e-06,
"loss": 0.6252,
"step": 134
},
{
"epoch": 2.05,
"learning_rate": 4.665354330708662e-06,
"loss": 0.5993,
"step": 135
},
{
"epoch": 2.06,
"learning_rate": 4.661417322834646e-06,
"loss": 0.6276,
"step": 136
},
{
"epoch": 2.08,
"learning_rate": 4.6574803149606305e-06,
"loss": 0.5883,
"step": 137
},
{
"epoch": 2.09,
"learning_rate": 4.653543307086614e-06,
"loss": 0.6206,
"step": 138
},
{
"epoch": 2.11,
"learning_rate": 4.649606299212599e-06,
"loss": 0.5486,
"step": 139
},
{
"epoch": 2.12,
"learning_rate": 4.645669291338583e-06,
"loss": 0.5415,
"step": 140
},
{
"epoch": 2.14,
"learning_rate": 4.641732283464567e-06,
"loss": 0.6378,
"step": 141
},
{
"epoch": 2.15,
"learning_rate": 4.637795275590551e-06,
"loss": 0.5229,
"step": 142
},
{
"epoch": 2.17,
"learning_rate": 4.633858267716536e-06,
"loss": 0.6823,
"step": 143
},
{
"epoch": 2.18,
"learning_rate": 4.6299212598425204e-06,
"loss": 0.7012,
"step": 144
},
{
"epoch": 2.2,
"learning_rate": 4.625984251968504e-06,
"loss": 0.6254,
"step": 145
},
{
"epoch": 2.21,
"learning_rate": 4.622047244094489e-06,
"loss": 0.6011,
"step": 146
},
{
"epoch": 2.23,
"learning_rate": 4.618110236220473e-06,
"loss": 0.5934,
"step": 147
},
{
"epoch": 2.24,
"learning_rate": 4.6141732283464565e-06,
"loss": 0.7028,
"step": 148
},
{
"epoch": 2.26,
"learning_rate": 4.610236220472442e-06,
"loss": 0.5105,
"step": 149
},
{
"epoch": 2.27,
"learning_rate": 4.606299212598426e-06,
"loss": 0.6125,
"step": 150
},
{
"epoch": 2.29,
"learning_rate": 4.6023622047244096e-06,
"loss": 0.6041,
"step": 151
},
{
"epoch": 2.3,
"learning_rate": 4.598425196850394e-06,
"loss": 0.5185,
"step": 152
},
{
"epoch": 2.32,
"learning_rate": 4.594488188976378e-06,
"loss": 0.6009,
"step": 153
},
{
"epoch": 2.33,
"learning_rate": 4.590551181102363e-06,
"loss": 0.6171,
"step": 154
},
{
"epoch": 2.35,
"learning_rate": 4.586614173228347e-06,
"loss": 0.5724,
"step": 155
},
{
"epoch": 2.36,
"learning_rate": 4.582677165354331e-06,
"loss": 0.5557,
"step": 156
},
{
"epoch": 2.38,
"learning_rate": 4.578740157480316e-06,
"loss": 0.5141,
"step": 157
},
{
"epoch": 2.39,
"learning_rate": 4.5748031496062995e-06,
"loss": 0.5375,
"step": 158
},
{
"epoch": 2.41,
"learning_rate": 4.570866141732283e-06,
"loss": 0.5167,
"step": 159
},
{
"epoch": 2.42,
"learning_rate": 4.566929133858268e-06,
"loss": 0.7095,
"step": 160
},
{
"epoch": 2.44,
"learning_rate": 4.562992125984253e-06,
"loss": 0.6252,
"step": 161
},
{
"epoch": 2.45,
"learning_rate": 4.559055118110236e-06,
"loss": 0.5686,
"step": 162
},
{
"epoch": 2.47,
"learning_rate": 4.555118110236221e-06,
"loss": 0.5789,
"step": 163
},
{
"epoch": 2.48,
"learning_rate": 4.551181102362205e-06,
"loss": 0.4726,
"step": 164
},
{
"epoch": 2.5,
"learning_rate": 4.5472440944881895e-06,
"loss": 0.6467,
"step": 165
},
{
"epoch": 2.52,
"learning_rate": 4.543307086614174e-06,
"loss": 0.4756,
"step": 166
},
{
"epoch": 2.53,
"learning_rate": 4.539370078740158e-06,
"loss": 0.5845,
"step": 167
},
{
"epoch": 2.55,
"learning_rate": 4.535433070866142e-06,
"loss": 0.5993,
"step": 168
},
{
"epoch": 2.56,
"learning_rate": 4.531496062992126e-06,
"loss": 0.6704,
"step": 169
},
{
"epoch": 2.58,
"learning_rate": 4.52755905511811e-06,
"loss": 0.5848,
"step": 170
},
{
"epoch": 2.59,
"learning_rate": 4.523622047244095e-06,
"loss": 0.459,
"step": 171
},
{
"epoch": 2.61,
"learning_rate": 4.5196850393700794e-06,
"loss": 0.7056,
"step": 172
},
{
"epoch": 2.62,
"learning_rate": 4.515748031496063e-06,
"loss": 0.6121,
"step": 173
},
{
"epoch": 2.64,
"learning_rate": 4.511811023622048e-06,
"loss": 0.641,
"step": 174
},
{
"epoch": 2.65,
"learning_rate": 4.507874015748032e-06,
"loss": 0.5589,
"step": 175
},
{
"epoch": 2.67,
"learning_rate": 4.503937007874016e-06,
"loss": 0.4841,
"step": 176
},
{
"epoch": 2.68,
"learning_rate": 4.5e-06,
"loss": 0.5499,
"step": 177
},
{
"epoch": 2.7,
"learning_rate": 4.496062992125985e-06,
"loss": 0.6007,
"step": 178
},
{
"epoch": 2.71,
"learning_rate": 4.4921259842519686e-06,
"loss": 0.6004,
"step": 179
},
{
"epoch": 2.73,
"learning_rate": 4.488188976377953e-06,
"loss": 0.5338,
"step": 180
},
{
"epoch": 2.74,
"learning_rate": 4.484251968503938e-06,
"loss": 0.4604,
"step": 181
},
{
"epoch": 2.76,
"learning_rate": 4.480314960629922e-06,
"loss": 0.5016,
"step": 182
},
{
"epoch": 2.77,
"learning_rate": 4.476377952755906e-06,
"loss": 0.477,
"step": 183
},
{
"epoch": 2.79,
"learning_rate": 4.47244094488189e-06,
"loss": 0.5267,
"step": 184
},
{
"epoch": 2.8,
"learning_rate": 4.468503937007874e-06,
"loss": 0.5974,
"step": 185
},
{
"epoch": 2.82,
"learning_rate": 4.4645669291338585e-06,
"loss": 0.6451,
"step": 186
},
{
"epoch": 2.83,
"learning_rate": 4.460629921259843e-06,
"loss": 0.4955,
"step": 187
},
{
"epoch": 2.85,
"learning_rate": 4.456692913385827e-06,
"loss": 0.5164,
"step": 188
},
{
"epoch": 2.86,
"learning_rate": 4.452755905511812e-06,
"loss": 0.6009,
"step": 189
},
{
"epoch": 2.88,
"learning_rate": 4.448818897637795e-06,
"loss": 0.4405,
"step": 190
},
{
"epoch": 2.89,
"learning_rate": 4.44488188976378e-06,
"loss": 0.6577,
"step": 191
},
{
"epoch": 2.91,
"learning_rate": 4.440944881889765e-06,
"loss": 0.5552,
"step": 192
},
{
"epoch": 2.92,
"learning_rate": 4.4370078740157485e-06,
"loss": 0.4946,
"step": 193
},
{
"epoch": 2.94,
"learning_rate": 4.433070866141732e-06,
"loss": 0.6111,
"step": 194
},
{
"epoch": 2.95,
"learning_rate": 4.429133858267717e-06,
"loss": 0.6654,
"step": 195
},
{
"epoch": 2.97,
"learning_rate": 4.425196850393701e-06,
"loss": 0.5907,
"step": 196
},
{
"epoch": 2.98,
"learning_rate": 4.421259842519685e-06,
"loss": 0.4857,
"step": 197
},
{
"epoch": 3.0,
"learning_rate": 4.41732283464567e-06,
"loss": 0.3732,
"step": 198
},
{
"epoch": 3.0,
"eval_accuracy": 0.803030303030303,
"eval_loss": 0.567893385887146,
"eval_runtime": 6.3298,
"eval_samples_per_second": 10.427,
"eval_steps_per_second": 2.686,
"step": 198
},
{
"epoch": 3.02,
"learning_rate": 4.413385826771654e-06,
"loss": 0.5889,
"step": 199
},
{
"epoch": 3.03,
"learning_rate": 4.4094488188976384e-06,
"loss": 0.5622,
"step": 200
},
{
"epoch": 3.05,
"learning_rate": 4.405511811023622e-06,
"loss": 0.5293,
"step": 201
},
{
"epoch": 3.06,
"learning_rate": 4.401574803149606e-06,
"loss": 0.5314,
"step": 202
},
{
"epoch": 3.08,
"learning_rate": 4.397637795275591e-06,
"loss": 0.558,
"step": 203
},
{
"epoch": 3.09,
"learning_rate": 4.393700787401575e-06,
"loss": 0.6215,
"step": 204
},
{
"epoch": 3.11,
"learning_rate": 4.389763779527559e-06,
"loss": 0.5632,
"step": 205
},
{
"epoch": 3.12,
"learning_rate": 4.385826771653544e-06,
"loss": 0.4325,
"step": 206
},
{
"epoch": 3.14,
"learning_rate": 4.3818897637795276e-06,
"loss": 0.4294,
"step": 207
},
{
"epoch": 3.15,
"learning_rate": 4.377952755905512e-06,
"loss": 0.5966,
"step": 208
},
{
"epoch": 3.17,
"learning_rate": 4.374015748031497e-06,
"loss": 0.4259,
"step": 209
},
{
"epoch": 3.18,
"learning_rate": 4.370078740157481e-06,
"loss": 0.5215,
"step": 210
},
{
"epoch": 3.2,
"learning_rate": 4.3661417322834644e-06,
"loss": 0.5925,
"step": 211
},
{
"epoch": 3.21,
"learning_rate": 4.362204724409449e-06,
"loss": 0.6151,
"step": 212
},
{
"epoch": 3.23,
"learning_rate": 4.358267716535434e-06,
"loss": 0.4599,
"step": 213
},
{
"epoch": 3.24,
"learning_rate": 4.3543307086614175e-06,
"loss": 0.4949,
"step": 214
},
{
"epoch": 3.26,
"learning_rate": 4.350393700787402e-06,
"loss": 0.5712,
"step": 215
},
{
"epoch": 3.27,
"learning_rate": 4.346456692913386e-06,
"loss": 0.4125,
"step": 216
},
{
"epoch": 3.29,
"learning_rate": 4.342519685039371e-06,
"loss": 0.5483,
"step": 217
},
{
"epoch": 3.3,
"learning_rate": 4.338582677165354e-06,
"loss": 0.4794,
"step": 218
},
{
"epoch": 3.32,
"learning_rate": 4.334645669291339e-06,
"loss": 0.5533,
"step": 219
},
{
"epoch": 3.33,
"learning_rate": 4.330708661417324e-06,
"loss": 0.6201,
"step": 220
},
{
"epoch": 3.35,
"learning_rate": 4.3267716535433075e-06,
"loss": 0.3873,
"step": 221
},
{
"epoch": 3.36,
"learning_rate": 4.322834645669291e-06,
"loss": 0.3827,
"step": 222
},
{
"epoch": 3.38,
"learning_rate": 4.318897637795276e-06,
"loss": 0.5698,
"step": 223
},
{
"epoch": 3.39,
"learning_rate": 4.3149606299212606e-06,
"loss": 0.3458,
"step": 224
},
{
"epoch": 3.41,
"learning_rate": 4.311023622047244e-06,
"loss": 0.5704,
"step": 225
},
{
"epoch": 3.42,
"learning_rate": 4.307086614173229e-06,
"loss": 0.432,
"step": 226
},
{
"epoch": 3.44,
"learning_rate": 4.303149606299213e-06,
"loss": 0.706,
"step": 227
},
{
"epoch": 3.45,
"learning_rate": 4.299212598425197e-06,
"loss": 0.5699,
"step": 228
},
{
"epoch": 3.47,
"learning_rate": 4.295275590551182e-06,
"loss": 0.5042,
"step": 229
},
{
"epoch": 3.48,
"learning_rate": 4.291338582677166e-06,
"loss": 0.3555,
"step": 230
},
{
"epoch": 3.5,
"learning_rate": 4.28740157480315e-06,
"loss": 0.4435,
"step": 231
},
{
"epoch": 3.52,
"learning_rate": 4.283464566929134e-06,
"loss": 0.516,
"step": 232
},
{
"epoch": 3.53,
"learning_rate": 4.279527559055118e-06,
"loss": 0.3766,
"step": 233
},
{
"epoch": 3.55,
"learning_rate": 4.275590551181103e-06,
"loss": 0.3667,
"step": 234
},
{
"epoch": 3.56,
"learning_rate": 4.271653543307087e-06,
"loss": 0.4945,
"step": 235
},
{
"epoch": 3.58,
"learning_rate": 4.267716535433071e-06,
"loss": 0.3392,
"step": 236
},
{
"epoch": 3.59,
"learning_rate": 4.263779527559056e-06,
"loss": 0.5006,
"step": 237
},
{
"epoch": 3.61,
"learning_rate": 4.25984251968504e-06,
"loss": 0.3513,
"step": 238
},
{
"epoch": 3.62,
"learning_rate": 4.2559055118110234e-06,
"loss": 0.5244,
"step": 239
},
{
"epoch": 3.64,
"learning_rate": 4.251968503937008e-06,
"loss": 0.5114,
"step": 240
},
{
"epoch": 3.65,
"learning_rate": 4.248031496062993e-06,
"loss": 0.2958,
"step": 241
},
{
"epoch": 3.67,
"learning_rate": 4.2440944881889765e-06,
"loss": 0.3114,
"step": 242
},
{
"epoch": 3.68,
"learning_rate": 4.240157480314961e-06,
"loss": 0.3446,
"step": 243
},
{
"epoch": 3.7,
"learning_rate": 4.236220472440945e-06,
"loss": 0.4279,
"step": 244
},
{
"epoch": 3.71,
"learning_rate": 4.23228346456693e-06,
"loss": 0.3878,
"step": 245
},
{
"epoch": 3.73,
"learning_rate": 4.228346456692914e-06,
"loss": 0.7247,
"step": 246
},
{
"epoch": 3.74,
"learning_rate": 4.224409448818898e-06,
"loss": 0.3515,
"step": 247
},
{
"epoch": 3.76,
"learning_rate": 4.220472440944882e-06,
"loss": 0.4386,
"step": 248
},
{
"epoch": 3.77,
"learning_rate": 4.2165354330708665e-06,
"loss": 0.3985,
"step": 249
},
{
"epoch": 3.79,
"learning_rate": 4.21259842519685e-06,
"loss": 0.2859,
"step": 250
},
{
"epoch": 3.8,
"learning_rate": 4.208661417322835e-06,
"loss": 0.6352,
"step": 251
},
{
"epoch": 3.82,
"learning_rate": 4.2047244094488196e-06,
"loss": 0.3076,
"step": 252
},
{
"epoch": 3.83,
"learning_rate": 4.200787401574803e-06,
"loss": 0.2918,
"step": 253
},
{
"epoch": 3.85,
"learning_rate": 4.196850393700788e-06,
"loss": 0.5486,
"step": 254
},
{
"epoch": 3.86,
"learning_rate": 4.192913385826772e-06,
"loss": 0.6028,
"step": 255
},
{
"epoch": 3.88,
"learning_rate": 4.1889763779527564e-06,
"loss": 0.5627,
"step": 256
},
{
"epoch": 3.89,
"learning_rate": 4.18503937007874e-06,
"loss": 0.6596,
"step": 257
},
{
"epoch": 3.91,
"learning_rate": 4.181102362204725e-06,
"loss": 0.4707,
"step": 258
},
{
"epoch": 3.92,
"learning_rate": 4.177165354330709e-06,
"loss": 0.3549,
"step": 259
},
{
"epoch": 3.94,
"learning_rate": 4.173228346456693e-06,
"loss": 0.5753,
"step": 260
},
{
"epoch": 3.95,
"learning_rate": 4.169291338582678e-06,
"loss": 0.5335,
"step": 261
},
{
"epoch": 3.97,
"learning_rate": 4.165354330708662e-06,
"loss": 0.3238,
"step": 262
},
{
"epoch": 3.98,
"learning_rate": 4.161417322834646e-06,
"loss": 0.4037,
"step": 263
},
{
"epoch": 4.0,
"learning_rate": 4.15748031496063e-06,
"loss": 0.4637,
"step": 264
},
{
"epoch": 4.0,
"eval_accuracy": 0.8181818181818182,
"eval_loss": 0.4488632380962372,
"eval_runtime": 6.8798,
"eval_samples_per_second": 9.593,
"eval_steps_per_second": 2.471,
"step": 264
},
{
"epoch": 4.02,
"learning_rate": 4.153543307086614e-06,
"loss": 0.3581,
"step": 265
},
{
"epoch": 4.03,
"learning_rate": 4.149606299212599e-06,
"loss": 0.3822,
"step": 266
},
{
"epoch": 4.05,
"learning_rate": 4.145669291338583e-06,
"loss": 0.5748,
"step": 267
},
{
"epoch": 4.06,
"learning_rate": 4.141732283464567e-06,
"loss": 0.2967,
"step": 268
},
{
"epoch": 4.08,
"learning_rate": 4.137795275590552e-06,
"loss": 0.588,
"step": 269
},
{
"epoch": 4.09,
"learning_rate": 4.1338582677165355e-06,
"loss": 0.5945,
"step": 270
},
{
"epoch": 4.11,
"learning_rate": 4.12992125984252e-06,
"loss": 0.4901,
"step": 271
},
{
"epoch": 4.12,
"learning_rate": 4.125984251968505e-06,
"loss": 0.4632,
"step": 272
},
{
"epoch": 4.14,
"learning_rate": 4.122047244094489e-06,
"loss": 0.3848,
"step": 273
},
{
"epoch": 4.15,
"learning_rate": 4.118110236220472e-06,
"loss": 0.425,
"step": 274
},
{
"epoch": 4.17,
"learning_rate": 4.114173228346457e-06,
"loss": 0.5269,
"step": 275
},
{
"epoch": 4.18,
"learning_rate": 4.110236220472441e-06,
"loss": 0.2838,
"step": 276
},
{
"epoch": 4.2,
"learning_rate": 4.1062992125984255e-06,
"loss": 0.2754,
"step": 277
},
{
"epoch": 4.21,
"learning_rate": 4.10236220472441e-06,
"loss": 0.4213,
"step": 278
},
{
"epoch": 4.23,
"learning_rate": 4.098425196850394e-06,
"loss": 0.286,
"step": 279
},
{
"epoch": 4.24,
"learning_rate": 4.0944881889763785e-06,
"loss": 0.5367,
"step": 280
},
{
"epoch": 4.26,
"learning_rate": 4.090551181102362e-06,
"loss": 0.5445,
"step": 281
},
{
"epoch": 4.27,
"learning_rate": 4.086614173228346e-06,
"loss": 0.4772,
"step": 282
},
{
"epoch": 4.29,
"learning_rate": 4.082677165354332e-06,
"loss": 0.2597,
"step": 283
},
{
"epoch": 4.3,
"learning_rate": 4.0787401574803154e-06,
"loss": 0.378,
"step": 284
},
{
"epoch": 4.32,
"learning_rate": 4.074803149606299e-06,
"loss": 0.4049,
"step": 285
},
{
"epoch": 4.33,
"learning_rate": 4.070866141732284e-06,
"loss": 0.408,
"step": 286
},
{
"epoch": 4.35,
"learning_rate": 4.066929133858268e-06,
"loss": 0.5702,
"step": 287
},
{
"epoch": 4.36,
"learning_rate": 4.062992125984252e-06,
"loss": 0.2844,
"step": 288
},
{
"epoch": 4.38,
"learning_rate": 4.059055118110237e-06,
"loss": 0.2546,
"step": 289
},
{
"epoch": 4.39,
"learning_rate": 4.055118110236221e-06,
"loss": 0.26,
"step": 290
},
{
"epoch": 4.41,
"learning_rate": 4.051181102362205e-06,
"loss": 0.548,
"step": 291
},
{
"epoch": 4.42,
"learning_rate": 4.047244094488189e-06,
"loss": 0.5079,
"step": 292
},
{
"epoch": 4.44,
"learning_rate": 4.043307086614174e-06,
"loss": 0.3426,
"step": 293
},
{
"epoch": 4.45,
"learning_rate": 4.039370078740158e-06,
"loss": 0.2459,
"step": 294
},
{
"epoch": 4.47,
"learning_rate": 4.035433070866142e-06,
"loss": 0.6087,
"step": 295
},
{
"epoch": 4.48,
"learning_rate": 4.031496062992126e-06,
"loss": 0.303,
"step": 296
},
{
"epoch": 4.5,
"learning_rate": 4.027559055118111e-06,
"loss": 0.2649,
"step": 297
},
{
"epoch": 4.52,
"learning_rate": 4.0236220472440945e-06,
"loss": 0.4792,
"step": 298
},
{
"epoch": 4.53,
"learning_rate": 4.019685039370079e-06,
"loss": 0.353,
"step": 299
},
{
"epoch": 4.55,
"learning_rate": 4.015748031496064e-06,
"loss": 0.2387,
"step": 300
},
{
"epoch": 4.56,
"learning_rate": 4.011811023622048e-06,
"loss": 0.5596,
"step": 301
},
{
"epoch": 4.58,
"learning_rate": 4.007874015748031e-06,
"loss": 0.2684,
"step": 302
},
{
"epoch": 4.59,
"learning_rate": 4.003937007874016e-06,
"loss": 0.3403,
"step": 303
},
{
"epoch": 4.61,
"learning_rate": 4.000000000000001e-06,
"loss": 0.2609,
"step": 304
},
{
"epoch": 4.62,
"learning_rate": 3.9960629921259845e-06,
"loss": 0.2897,
"step": 305
},
{
"epoch": 4.64,
"learning_rate": 3.992125984251969e-06,
"loss": 0.4744,
"step": 306
},
{
"epoch": 4.65,
"learning_rate": 3.988188976377953e-06,
"loss": 0.2779,
"step": 307
},
{
"epoch": 4.67,
"learning_rate": 3.9842519685039375e-06,
"loss": 0.2217,
"step": 308
},
{
"epoch": 4.68,
"learning_rate": 3.980314960629922e-06,
"loss": 0.4549,
"step": 309
},
{
"epoch": 4.7,
"learning_rate": 3.976377952755906e-06,
"loss": 0.5696,
"step": 310
},
{
"epoch": 4.71,
"learning_rate": 3.97244094488189e-06,
"loss": 0.2175,
"step": 311
},
{
"epoch": 4.73,
"learning_rate": 3.968503937007874e-06,
"loss": 0.2406,
"step": 312
},
{
"epoch": 4.74,
"learning_rate": 3.964566929133858e-06,
"loss": 0.5512,
"step": 313
},
{
"epoch": 4.76,
"learning_rate": 3.960629921259843e-06,
"loss": 0.2105,
"step": 314
},
{
"epoch": 4.77,
"learning_rate": 3.9566929133858275e-06,
"loss": 0.8069,
"step": 315
},
{
"epoch": 4.79,
"learning_rate": 3.952755905511811e-06,
"loss": 0.4629,
"step": 316
},
{
"epoch": 4.8,
"learning_rate": 3.948818897637796e-06,
"loss": 0.2115,
"step": 317
},
{
"epoch": 4.82,
"learning_rate": 3.94488188976378e-06,
"loss": 0.2883,
"step": 318
},
{
"epoch": 4.83,
"learning_rate": 3.9409448818897635e-06,
"loss": 0.5092,
"step": 319
},
{
"epoch": 4.85,
"learning_rate": 3.937007874015748e-06,
"loss": 0.3486,
"step": 320
},
{
"epoch": 4.86,
"learning_rate": 3.933070866141733e-06,
"loss": 0.5374,
"step": 321
},
{
"epoch": 4.88,
"learning_rate": 3.929133858267717e-06,
"loss": 0.3302,
"step": 322
},
{
"epoch": 4.89,
"learning_rate": 3.925196850393701e-06,
"loss": 0.5962,
"step": 323
},
{
"epoch": 4.91,
"learning_rate": 3.921259842519685e-06,
"loss": 0.2028,
"step": 324
},
{
"epoch": 4.92,
"learning_rate": 3.91732283464567e-06,
"loss": 0.4314,
"step": 325
},
{
"epoch": 4.94,
"learning_rate": 3.913385826771654e-06,
"loss": 0.2254,
"step": 326
},
{
"epoch": 4.95,
"learning_rate": 3.909448818897638e-06,
"loss": 0.5416,
"step": 327
},
{
"epoch": 4.97,
"learning_rate": 3.905511811023622e-06,
"loss": 0.1982,
"step": 328
},
{
"epoch": 4.98,
"learning_rate": 3.901574803149607e-06,
"loss": 0.2117,
"step": 329
},
{
"epoch": 5.0,
"learning_rate": 3.89763779527559e-06,
"loss": 0.2166,
"step": 330
},
{
"epoch": 5.0,
"eval_accuracy": 0.8939393939393939,
"eval_loss": 0.3404465913772583,
"eval_runtime": 6.3639,
"eval_samples_per_second": 10.371,
"eval_steps_per_second": 2.671,
"step": 330
},
{
"epoch": 5.02,
"learning_rate": 3.893700787401575e-06,
"loss": 0.3983,
"step": 331
},
{
"epoch": 5.03,
"learning_rate": 3.88976377952756e-06,
"loss": 0.566,
"step": 332
},
{
"epoch": 5.05,
"learning_rate": 3.8858267716535435e-06,
"loss": 0.2756,
"step": 333
},
{
"epoch": 5.06,
"learning_rate": 3.881889763779528e-06,
"loss": 0.2214,
"step": 334
},
{
"epoch": 5.08,
"learning_rate": 3.877952755905512e-06,
"loss": 0.21,
"step": 335
},
{
"epoch": 5.09,
"learning_rate": 3.8740157480314965e-06,
"loss": 0.2232,
"step": 336
},
{
"epoch": 5.11,
"learning_rate": 3.87007874015748e-06,
"loss": 0.2061,
"step": 337
},
{
"epoch": 5.12,
"learning_rate": 3.866141732283465e-06,
"loss": 0.311,
"step": 338
},
{
"epoch": 5.14,
"learning_rate": 3.862204724409449e-06,
"loss": 0.1845,
"step": 339
},
{
"epoch": 5.15,
"learning_rate": 3.858267716535433e-06,
"loss": 0.2081,
"step": 340
},
{
"epoch": 5.17,
"learning_rate": 3.854330708661418e-06,
"loss": 0.4295,
"step": 341
},
{
"epoch": 5.18,
"learning_rate": 3.850393700787402e-06,
"loss": 0.1863,
"step": 342
},
{
"epoch": 5.2,
"learning_rate": 3.8464566929133865e-06,
"loss": 0.2167,
"step": 343
},
{
"epoch": 5.21,
"learning_rate": 3.84251968503937e-06,
"loss": 0.5119,
"step": 344
},
{
"epoch": 5.23,
"learning_rate": 3.838582677165354e-06,
"loss": 0.4946,
"step": 345
},
{
"epoch": 5.24,
"learning_rate": 3.834645669291339e-06,
"loss": 0.2194,
"step": 346
},
{
"epoch": 5.26,
"learning_rate": 3.830708661417323e-06,
"loss": 0.1861,
"step": 347
},
{
"epoch": 5.27,
"learning_rate": 3.826771653543307e-06,
"loss": 0.1871,
"step": 348
},
{
"epoch": 5.29,
"learning_rate": 3.822834645669292e-06,
"loss": 0.293,
"step": 349
},
{
"epoch": 5.3,
"learning_rate": 3.818897637795276e-06,
"loss": 0.183,
"step": 350
},
{
"epoch": 5.32,
"learning_rate": 3.81496062992126e-06,
"loss": 0.4737,
"step": 351
},
{
"epoch": 5.33,
"learning_rate": 3.8110236220472445e-06,
"loss": 0.1968,
"step": 352
},
{
"epoch": 5.35,
"learning_rate": 3.8070866141732287e-06,
"loss": 0.5645,
"step": 353
},
{
"epoch": 5.36,
"learning_rate": 3.803149606299213e-06,
"loss": 0.2107,
"step": 354
},
{
"epoch": 5.38,
"learning_rate": 3.799212598425197e-06,
"loss": 0.6736,
"step": 355
},
{
"epoch": 5.39,
"learning_rate": 3.7952755905511814e-06,
"loss": 0.1696,
"step": 356
},
{
"epoch": 5.41,
"learning_rate": 3.791338582677166e-06,
"loss": 0.204,
"step": 357
},
{
"epoch": 5.42,
"learning_rate": 3.7874015748031502e-06,
"loss": 0.1744,
"step": 358
},
{
"epoch": 5.44,
"learning_rate": 3.783464566929134e-06,
"loss": 0.1769,
"step": 359
},
{
"epoch": 5.45,
"learning_rate": 3.7795275590551182e-06,
"loss": 0.164,
"step": 360
},
{
"epoch": 5.47,
"learning_rate": 3.7755905511811025e-06,
"loss": 0.7071,
"step": 361
},
{
"epoch": 5.48,
"learning_rate": 3.7716535433070867e-06,
"loss": 0.1572,
"step": 362
},
{
"epoch": 5.5,
"learning_rate": 3.7677165354330713e-06,
"loss": 0.3369,
"step": 363
},
{
"epoch": 5.52,
"learning_rate": 3.7637795275590555e-06,
"loss": 0.1589,
"step": 364
},
{
"epoch": 5.53,
"learning_rate": 3.7598425196850398e-06,
"loss": 0.1886,
"step": 365
},
{
"epoch": 5.55,
"learning_rate": 3.755905511811024e-06,
"loss": 0.2163,
"step": 366
},
{
"epoch": 5.56,
"learning_rate": 3.7519685039370078e-06,
"loss": 0.1526,
"step": 367
},
{
"epoch": 5.58,
"learning_rate": 3.748031496062993e-06,
"loss": 0.5631,
"step": 368
},
{
"epoch": 5.59,
"learning_rate": 3.7440944881889766e-06,
"loss": 0.1584,
"step": 369
},
{
"epoch": 5.61,
"learning_rate": 3.740157480314961e-06,
"loss": 0.5094,
"step": 370
},
{
"epoch": 5.62,
"learning_rate": 3.736220472440945e-06,
"loss": 0.4171,
"step": 371
},
{
"epoch": 5.64,
"learning_rate": 3.7322834645669293e-06,
"loss": 0.5874,
"step": 372
},
{
"epoch": 5.65,
"learning_rate": 3.728346456692914e-06,
"loss": 0.177,
"step": 373
},
{
"epoch": 5.67,
"learning_rate": 3.724409448818898e-06,
"loss": 0.1753,
"step": 374
},
{
"epoch": 5.68,
"learning_rate": 3.7204724409448824e-06,
"loss": 0.158,
"step": 375
},
{
"epoch": 5.7,
"learning_rate": 3.7165354330708666e-06,
"loss": 0.1736,
"step": 376
},
{
"epoch": 5.71,
"learning_rate": 3.7125984251968504e-06,
"loss": 0.2736,
"step": 377
},
{
"epoch": 5.73,
"learning_rate": 3.7086614173228346e-06,
"loss": 0.2054,
"step": 378
},
{
"epoch": 5.74,
"learning_rate": 3.7047244094488193e-06,
"loss": 0.383,
"step": 379
},
{
"epoch": 5.76,
"learning_rate": 3.7007874015748035e-06,
"loss": 0.146,
"step": 380
},
{
"epoch": 5.77,
"learning_rate": 3.6968503937007877e-06,
"loss": 0.1785,
"step": 381
},
{
"epoch": 5.79,
"learning_rate": 3.692913385826772e-06,
"loss": 0.599,
"step": 382
},
{
"epoch": 5.8,
"learning_rate": 3.688976377952756e-06,
"loss": 0.5044,
"step": 383
},
{
"epoch": 5.82,
"learning_rate": 3.6850393700787408e-06,
"loss": 0.1508,
"step": 384
},
{
"epoch": 5.83,
"learning_rate": 3.681102362204725e-06,
"loss": 0.1437,
"step": 385
},
{
"epoch": 5.85,
"learning_rate": 3.677165354330709e-06,
"loss": 0.2467,
"step": 386
},
{
"epoch": 5.86,
"learning_rate": 3.673228346456693e-06,
"loss": 0.1497,
"step": 387
},
{
"epoch": 5.88,
"learning_rate": 3.6692913385826772e-06,
"loss": 0.3545,
"step": 388
},
{
"epoch": 5.89,
"learning_rate": 3.665354330708662e-06,
"loss": 0.1441,
"step": 389
},
{
"epoch": 5.91,
"learning_rate": 3.661417322834646e-06,
"loss": 0.1408,
"step": 390
},
{
"epoch": 5.92,
"learning_rate": 3.6574803149606303e-06,
"loss": 0.156,
"step": 391
},
{
"epoch": 5.94,
"learning_rate": 3.6535433070866145e-06,
"loss": 0.1311,
"step": 392
},
{
"epoch": 5.95,
"learning_rate": 3.6496062992125988e-06,
"loss": 0.6291,
"step": 393
},
{
"epoch": 5.97,
"learning_rate": 3.6456692913385826e-06,
"loss": 0.408,
"step": 394
},
{
"epoch": 5.98,
"learning_rate": 3.6417322834645676e-06,
"loss": 0.1383,
"step": 395
},
{
"epoch": 6.0,
"learning_rate": 3.6377952755905514e-06,
"loss": 0.2411,
"step": 396
},
{
"epoch": 6.0,
"eval_accuracy": 0.9393939393939394,
"eval_loss": 0.2369035929441452,
"eval_runtime": 6.2358,
"eval_samples_per_second": 10.584,
"eval_steps_per_second": 2.726,
"step": 396
},
{
"epoch": 6.02,
"learning_rate": 3.6338582677165356e-06,
"loss": 0.5985,
"step": 397
},
{
"epoch": 6.03,
"learning_rate": 3.62992125984252e-06,
"loss": 0.1448,
"step": 398
},
{
"epoch": 6.05,
"learning_rate": 3.625984251968504e-06,
"loss": 0.5026,
"step": 399
},
{
"epoch": 6.06,
"learning_rate": 3.6220472440944887e-06,
"loss": 0.1389,
"step": 400
},
{
"epoch": 6.08,
"learning_rate": 3.618110236220473e-06,
"loss": 0.5432,
"step": 401
},
{
"epoch": 6.09,
"learning_rate": 3.614173228346457e-06,
"loss": 0.5761,
"step": 402
},
{
"epoch": 6.11,
"learning_rate": 3.610236220472441e-06,
"loss": 0.2165,
"step": 403
},
{
"epoch": 6.12,
"learning_rate": 3.606299212598425e-06,
"loss": 0.1467,
"step": 404
},
{
"epoch": 6.14,
"learning_rate": 3.60236220472441e-06,
"loss": 0.1382,
"step": 405
},
{
"epoch": 6.15,
"learning_rate": 3.598425196850394e-06,
"loss": 0.3128,
"step": 406
},
{
"epoch": 6.17,
"learning_rate": 3.5944881889763783e-06,
"loss": 0.1911,
"step": 407
},
{
"epoch": 6.18,
"learning_rate": 3.5905511811023625e-06,
"loss": 0.1306,
"step": 408
},
{
"epoch": 6.2,
"learning_rate": 3.5866141732283467e-06,
"loss": 0.1925,
"step": 409
},
{
"epoch": 6.21,
"learning_rate": 3.582677165354331e-06,
"loss": 0.1275,
"step": 410
},
{
"epoch": 6.23,
"learning_rate": 3.5787401574803156e-06,
"loss": 0.1296,
"step": 411
},
{
"epoch": 6.24,
"learning_rate": 3.5748031496062998e-06,
"loss": 0.1237,
"step": 412
},
{
"epoch": 6.26,
"learning_rate": 3.5708661417322836e-06,
"loss": 1.1349,
"step": 413
},
{
"epoch": 6.27,
"learning_rate": 3.566929133858268e-06,
"loss": 0.1208,
"step": 414
},
{
"epoch": 6.29,
"learning_rate": 3.562992125984252e-06,
"loss": 0.1221,
"step": 415
},
{
"epoch": 6.3,
"learning_rate": 3.5590551181102367e-06,
"loss": 0.6214,
"step": 416
},
{
"epoch": 6.32,
"learning_rate": 3.555118110236221e-06,
"loss": 0.1193,
"step": 417
},
{
"epoch": 6.33,
"learning_rate": 3.551181102362205e-06,
"loss": 0.1218,
"step": 418
},
{
"epoch": 6.35,
"learning_rate": 3.5472440944881893e-06,
"loss": 0.1493,
"step": 419
},
{
"epoch": 6.36,
"learning_rate": 3.5433070866141735e-06,
"loss": 0.1247,
"step": 420
},
{
"epoch": 6.38,
"learning_rate": 3.539370078740158e-06,
"loss": 0.1158,
"step": 421
},
{
"epoch": 6.39,
"learning_rate": 3.535433070866142e-06,
"loss": 0.1201,
"step": 422
},
{
"epoch": 6.41,
"learning_rate": 3.531496062992126e-06,
"loss": 0.6259,
"step": 423
},
{
"epoch": 6.42,
"learning_rate": 3.5275590551181104e-06,
"loss": 0.1146,
"step": 424
},
{
"epoch": 6.44,
"learning_rate": 3.5236220472440946e-06,
"loss": 0.1311,
"step": 425
},
{
"epoch": 6.45,
"learning_rate": 3.519685039370079e-06,
"loss": 0.1097,
"step": 426
},
{
"epoch": 6.47,
"learning_rate": 3.5157480314960635e-06,
"loss": 0.4229,
"step": 427
},
{
"epoch": 6.48,
"learning_rate": 3.5118110236220477e-06,
"loss": 0.1245,
"step": 428
},
{
"epoch": 6.5,
"learning_rate": 3.507874015748032e-06,
"loss": 0.1066,
"step": 429
},
{
"epoch": 6.52,
"learning_rate": 3.5039370078740157e-06,
"loss": 0.1215,
"step": 430
},
{
"epoch": 6.53,
"learning_rate": 3.5e-06,
"loss": 0.1178,
"step": 431
},
{
"epoch": 6.55,
"learning_rate": 3.4960629921259846e-06,
"loss": 0.5898,
"step": 432
},
{
"epoch": 6.56,
"learning_rate": 3.492125984251969e-06,
"loss": 0.1037,
"step": 433
},
{
"epoch": 6.58,
"learning_rate": 3.488188976377953e-06,
"loss": 0.1185,
"step": 434
},
{
"epoch": 6.59,
"learning_rate": 3.4842519685039372e-06,
"loss": 0.4492,
"step": 435
},
{
"epoch": 6.61,
"learning_rate": 3.4803149606299215e-06,
"loss": 0.4031,
"step": 436
},
{
"epoch": 6.62,
"learning_rate": 3.476377952755906e-06,
"loss": 0.2397,
"step": 437
},
{
"epoch": 6.64,
"learning_rate": 3.4724409448818903e-06,
"loss": 0.1238,
"step": 438
},
{
"epoch": 6.65,
"learning_rate": 3.4685039370078746e-06,
"loss": 0.6626,
"step": 439
},
{
"epoch": 6.67,
"learning_rate": 3.4645669291338583e-06,
"loss": 0.1303,
"step": 440
},
{
"epoch": 6.68,
"learning_rate": 3.4606299212598426e-06,
"loss": 0.1235,
"step": 441
},
{
"epoch": 6.7,
"learning_rate": 3.4566929133858268e-06,
"loss": 0.1008,
"step": 442
},
{
"epoch": 6.71,
"learning_rate": 3.4527559055118114e-06,
"loss": 0.1055,
"step": 443
},
{
"epoch": 6.73,
"learning_rate": 3.4488188976377956e-06,
"loss": 0.0986,
"step": 444
},
{
"epoch": 6.74,
"learning_rate": 3.44488188976378e-06,
"loss": 0.0998,
"step": 445
},
{
"epoch": 6.76,
"learning_rate": 3.440944881889764e-06,
"loss": 0.1114,
"step": 446
},
{
"epoch": 6.77,
"learning_rate": 3.437007874015748e-06,
"loss": 0.1749,
"step": 447
},
{
"epoch": 6.79,
"learning_rate": 3.433070866141733e-06,
"loss": 0.0985,
"step": 448
},
{
"epoch": 6.8,
"learning_rate": 3.4291338582677167e-06,
"loss": 0.0948,
"step": 449
},
{
"epoch": 6.82,
"learning_rate": 3.425196850393701e-06,
"loss": 0.0961,
"step": 450
},
{
"epoch": 6.83,
"learning_rate": 3.421259842519685e-06,
"loss": 0.6144,
"step": 451
},
{
"epoch": 6.85,
"learning_rate": 3.4173228346456694e-06,
"loss": 0.7958,
"step": 452
},
{
"epoch": 6.86,
"learning_rate": 3.413385826771654e-06,
"loss": 0.2617,
"step": 453
},
{
"epoch": 6.88,
"learning_rate": 3.4094488188976383e-06,
"loss": 0.0962,
"step": 454
},
{
"epoch": 6.89,
"learning_rate": 3.4055118110236225e-06,
"loss": 0.0918,
"step": 455
},
{
"epoch": 6.91,
"learning_rate": 3.4015748031496067e-06,
"loss": 0.3138,
"step": 456
},
{
"epoch": 6.92,
"learning_rate": 3.3976377952755905e-06,
"loss": 0.0919,
"step": 457
},
{
"epoch": 6.94,
"learning_rate": 3.3937007874015747e-06,
"loss": 0.0918,
"step": 458
},
{
"epoch": 6.95,
"learning_rate": 3.3897637795275594e-06,
"loss": 0.0895,
"step": 459
},
{
"epoch": 6.97,
"learning_rate": 3.3858267716535436e-06,
"loss": 0.0912,
"step": 460
},
{
"epoch": 6.98,
"learning_rate": 3.381889763779528e-06,
"loss": 0.0922,
"step": 461
},
{
"epoch": 7.0,
"learning_rate": 3.377952755905512e-06,
"loss": 0.1105,
"step": 462
},
{
"epoch": 7.0,
"eval_accuracy": 0.9393939393939394,
"eval_loss": 0.2016882747411728,
"eval_runtime": 6.2203,
"eval_samples_per_second": 10.61,
"eval_steps_per_second": 2.733,
"step": 462
},
{
"epoch": 7.02,
"learning_rate": 3.3740157480314962e-06,
"loss": 0.0905,
"step": 463
},
{
"epoch": 7.03,
"learning_rate": 3.370078740157481e-06,
"loss": 0.2391,
"step": 464
},
{
"epoch": 7.05,
"learning_rate": 3.366141732283465e-06,
"loss": 0.0839,
"step": 465
},
{
"epoch": 7.06,
"learning_rate": 3.362204724409449e-06,
"loss": 0.0859,
"step": 466
},
{
"epoch": 7.08,
"learning_rate": 3.358267716535433e-06,
"loss": 0.0863,
"step": 467
},
{
"epoch": 7.09,
"learning_rate": 3.3543307086614173e-06,
"loss": 0.169,
"step": 468
},
{
"epoch": 7.11,
"learning_rate": 3.350393700787402e-06,
"loss": 0.4396,
"step": 469
},
{
"epoch": 7.12,
"learning_rate": 3.346456692913386e-06,
"loss": 0.3005,
"step": 470
},
{
"epoch": 7.14,
"learning_rate": 3.3425196850393704e-06,
"loss": 0.0832,
"step": 471
},
{
"epoch": 7.15,
"learning_rate": 3.3385826771653546e-06,
"loss": 0.4338,
"step": 472
},
{
"epoch": 7.17,
"learning_rate": 3.334645669291339e-06,
"loss": 0.0898,
"step": 473
},
{
"epoch": 7.18,
"learning_rate": 3.3307086614173227e-06,
"loss": 0.0873,
"step": 474
},
{
"epoch": 7.2,
"learning_rate": 3.3267716535433077e-06,
"loss": 0.0856,
"step": 475
},
{
"epoch": 7.21,
"learning_rate": 3.3228346456692915e-06,
"loss": 0.6076,
"step": 476
},
{
"epoch": 7.23,
"learning_rate": 3.3188976377952757e-06,
"loss": 0.8815,
"step": 477
},
{
"epoch": 7.24,
"learning_rate": 3.31496062992126e-06,
"loss": 0.3032,
"step": 478
},
{
"epoch": 7.26,
"learning_rate": 3.311023622047244e-06,
"loss": 0.0893,
"step": 479
},
{
"epoch": 7.27,
"learning_rate": 3.307086614173229e-06,
"loss": 0.0791,
"step": 480
},
{
"epoch": 7.29,
"learning_rate": 3.303149606299213e-06,
"loss": 0.0757,
"step": 481
},
{
"epoch": 7.3,
"learning_rate": 3.2992125984251973e-06,
"loss": 0.0902,
"step": 482
},
{
"epoch": 7.32,
"learning_rate": 3.2952755905511815e-06,
"loss": 0.0793,
"step": 483
},
{
"epoch": 7.33,
"learning_rate": 3.2913385826771653e-06,
"loss": 0.7039,
"step": 484
},
{
"epoch": 7.35,
"learning_rate": 3.2874015748031503e-06,
"loss": 0.0776,
"step": 485
},
{
"epoch": 7.36,
"learning_rate": 3.283464566929134e-06,
"loss": 0.0861,
"step": 486
},
{
"epoch": 7.38,
"learning_rate": 3.2795275590551184e-06,
"loss": 0.9843,
"step": 487
},
{
"epoch": 7.39,
"learning_rate": 3.2755905511811026e-06,
"loss": 0.2719,
"step": 488
},
{
"epoch": 7.41,
"learning_rate": 3.271653543307087e-06,
"loss": 0.0826,
"step": 489
},
{
"epoch": 7.42,
"learning_rate": 3.267716535433071e-06,
"loss": 0.0747,
"step": 490
},
{
"epoch": 7.44,
"learning_rate": 3.2637795275590557e-06,
"loss": 0.0754,
"step": 491
},
{
"epoch": 7.45,
"learning_rate": 3.25984251968504e-06,
"loss": 0.0743,
"step": 492
},
{
"epoch": 7.47,
"learning_rate": 3.2559055118110237e-06,
"loss": 0.0739,
"step": 493
},
{
"epoch": 7.48,
"learning_rate": 3.251968503937008e-06,
"loss": 0.073,
"step": 494
},
{
"epoch": 7.5,
"learning_rate": 3.248031496062992e-06,
"loss": 0.7082,
"step": 495
},
{
"epoch": 7.52,
"learning_rate": 3.2440944881889768e-06,
"loss": 0.0758,
"step": 496
},
{
"epoch": 7.53,
"learning_rate": 3.240157480314961e-06,
"loss": 0.0714,
"step": 497
},
{
"epoch": 7.55,
"learning_rate": 3.236220472440945e-06,
"loss": 0.079,
"step": 498
},
{
"epoch": 7.56,
"learning_rate": 3.2322834645669294e-06,
"loss": 0.0703,
"step": 499
},
{
"epoch": 7.58,
"learning_rate": 3.2283464566929136e-06,
"loss": 0.0716,
"step": 500
},
{
"epoch": 7.59,
"learning_rate": 3.2244094488188983e-06,
"loss": 0.0742,
"step": 501
},
{
"epoch": 7.61,
"learning_rate": 3.2204724409448825e-06,
"loss": 0.0691,
"step": 502
},
{
"epoch": 7.62,
"learning_rate": 3.2165354330708663e-06,
"loss": 0.0697,
"step": 503
},
{
"epoch": 7.64,
"learning_rate": 3.2125984251968505e-06,
"loss": 0.0791,
"step": 504
},
{
"epoch": 7.65,
"learning_rate": 3.2086614173228347e-06,
"loss": 0.2838,
"step": 505
},
{
"epoch": 7.67,
"learning_rate": 3.204724409448819e-06,
"loss": 0.0683,
"step": 506
},
{
"epoch": 7.68,
"learning_rate": 3.2007874015748036e-06,
"loss": 0.4993,
"step": 507
},
{
"epoch": 7.7,
"learning_rate": 3.196850393700788e-06,
"loss": 0.2051,
"step": 508
},
{
"epoch": 7.71,
"learning_rate": 3.192913385826772e-06,
"loss": 0.0673,
"step": 509
},
{
"epoch": 7.73,
"learning_rate": 3.1889763779527563e-06,
"loss": 0.0676,
"step": 510
},
{
"epoch": 7.74,
"learning_rate": 3.18503937007874e-06,
"loss": 0.7316,
"step": 511
},
{
"epoch": 7.76,
"learning_rate": 3.1811023622047247e-06,
"loss": 0.065,
"step": 512
},
{
"epoch": 7.77,
"learning_rate": 3.177165354330709e-06,
"loss": 0.2066,
"step": 513
},
{
"epoch": 7.79,
"learning_rate": 3.173228346456693e-06,
"loss": 0.1082,
"step": 514
},
{
"epoch": 7.8,
"learning_rate": 3.1692913385826774e-06,
"loss": 0.1039,
"step": 515
},
{
"epoch": 7.82,
"learning_rate": 3.1653543307086616e-06,
"loss": 0.0752,
"step": 516
},
{
"epoch": 7.83,
"learning_rate": 3.1614173228346462e-06,
"loss": 0.0647,
"step": 517
},
{
"epoch": 7.85,
"learning_rate": 3.1574803149606304e-06,
"loss": 0.0636,
"step": 518
},
{
"epoch": 7.86,
"learning_rate": 3.1535433070866147e-06,
"loss": 0.2198,
"step": 519
},
{
"epoch": 7.88,
"learning_rate": 3.1496062992125985e-06,
"loss": 0.0719,
"step": 520
},
{
"epoch": 7.89,
"learning_rate": 3.1456692913385827e-06,
"loss": 0.0642,
"step": 521
},
{
"epoch": 7.91,
"learning_rate": 3.141732283464567e-06,
"loss": 0.0711,
"step": 522
},
{
"epoch": 7.92,
"learning_rate": 3.1377952755905515e-06,
"loss": 0.0645,
"step": 523
},
{
"epoch": 7.94,
"learning_rate": 3.1338582677165358e-06,
"loss": 0.1827,
"step": 524
},
{
"epoch": 7.95,
"learning_rate": 3.12992125984252e-06,
"loss": 0.0636,
"step": 525
},
{
"epoch": 7.97,
"learning_rate": 3.125984251968504e-06,
"loss": 0.0634,
"step": 526
},
{
"epoch": 7.98,
"learning_rate": 3.1220472440944884e-06,
"loss": 0.2832,
"step": 527
},
{
"epoch": 8.0,
"learning_rate": 3.118110236220473e-06,
"loss": 0.0683,
"step": 528
},
{
"epoch": 8.0,
"eval_accuracy": 0.9545454545454546,
"eval_loss": 0.18883031606674194,
"eval_runtime": 6.9079,
"eval_samples_per_second": 9.554,
"eval_steps_per_second": 2.461,
"step": 528
},
{
"epoch": 8.02,
"learning_rate": 3.1141732283464573e-06,
"loss": 0.0693,
"step": 529
},
{
"epoch": 8.03,
"learning_rate": 3.110236220472441e-06,
"loss": 0.7524,
"step": 530
},
{
"epoch": 8.05,
"learning_rate": 3.1062992125984253e-06,
"loss": 0.1929,
"step": 531
},
{
"epoch": 8.06,
"learning_rate": 3.1023622047244095e-06,
"loss": 0.0604,
"step": 532
},
{
"epoch": 8.08,
"learning_rate": 3.098425196850394e-06,
"loss": 0.0603,
"step": 533
},
{
"epoch": 8.09,
"learning_rate": 3.0944881889763784e-06,
"loss": 0.1681,
"step": 534
},
{
"epoch": 8.11,
"learning_rate": 3.0905511811023626e-06,
"loss": 0.0663,
"step": 535
},
{
"epoch": 8.12,
"learning_rate": 3.086614173228347e-06,
"loss": 0.0625,
"step": 536
},
{
"epoch": 8.14,
"learning_rate": 3.0826771653543306e-06,
"loss": 0.0799,
"step": 537
},
{
"epoch": 8.15,
"learning_rate": 3.078740157480315e-06,
"loss": 0.29,
"step": 538
},
{
"epoch": 8.17,
"learning_rate": 3.0748031496062995e-06,
"loss": 0.5023,
"step": 539
},
{
"epoch": 8.18,
"learning_rate": 3.0708661417322837e-06,
"loss": 0.0811,
"step": 540
},
{
"epoch": 8.2,
"learning_rate": 3.066929133858268e-06,
"loss": 0.0576,
"step": 541
},
{
"epoch": 8.21,
"learning_rate": 3.062992125984252e-06,
"loss": 0.0572,
"step": 542
},
{
"epoch": 8.23,
"learning_rate": 3.0590551181102364e-06,
"loss": 0.0571,
"step": 543
},
{
"epoch": 8.24,
"learning_rate": 3.055118110236221e-06,
"loss": 0.0626,
"step": 544
},
{
"epoch": 8.26,
"learning_rate": 3.0511811023622052e-06,
"loss": 0.5849,
"step": 545
},
{
"epoch": 8.27,
"learning_rate": 3.0472440944881894e-06,
"loss": 0.7242,
"step": 546
},
{
"epoch": 8.29,
"learning_rate": 3.0433070866141732e-06,
"loss": 0.0564,
"step": 547
},
{
"epoch": 8.3,
"learning_rate": 3.0393700787401575e-06,
"loss": 0.0649,
"step": 548
},
{
"epoch": 8.32,
"learning_rate": 3.035433070866142e-06,
"loss": 0.0547,
"step": 549
},
{
"epoch": 8.33,
"learning_rate": 3.0314960629921263e-06,
"loss": 0.2119,
"step": 550
},
{
"epoch": 8.35,
"learning_rate": 3.0275590551181105e-06,
"loss": 0.0541,
"step": 551
},
{
"epoch": 8.36,
"learning_rate": 3.0236220472440948e-06,
"loss": 0.0551,
"step": 552
},
{
"epoch": 8.38,
"learning_rate": 3.019685039370079e-06,
"loss": 0.0596,
"step": 553
},
{
"epoch": 8.39,
"learning_rate": 3.015748031496063e-06,
"loss": 0.0533,
"step": 554
},
{
"epoch": 8.41,
"learning_rate": 3.011811023622048e-06,
"loss": 0.4296,
"step": 555
},
{
"epoch": 8.42,
"learning_rate": 3.0078740157480316e-06,
"loss": 0.1105,
"step": 556
},
{
"epoch": 8.44,
"learning_rate": 3.003937007874016e-06,
"loss": 0.054,
"step": 557
},
{
"epoch": 8.45,
"learning_rate": 3e-06,
"loss": 0.055,
"step": 558
},
{
"epoch": 8.47,
"learning_rate": 2.9960629921259843e-06,
"loss": 0.0517,
"step": 559
},
{
"epoch": 8.48,
"learning_rate": 2.992125984251969e-06,
"loss": 0.7577,
"step": 560
},
{
"epoch": 8.5,
"learning_rate": 2.988188976377953e-06,
"loss": 0.0598,
"step": 561
},
{
"epoch": 8.52,
"learning_rate": 2.9842519685039374e-06,
"loss": 0.0517,
"step": 562
},
{
"epoch": 8.53,
"learning_rate": 2.9803149606299216e-06,
"loss": 0.5103,
"step": 563
},
{
"epoch": 8.55,
"learning_rate": 2.9763779527559054e-06,
"loss": 0.0534,
"step": 564
},
{
"epoch": 8.56,
"learning_rate": 2.9724409448818905e-06,
"loss": 0.0527,
"step": 565
},
{
"epoch": 8.58,
"learning_rate": 2.9685039370078743e-06,
"loss": 0.0585,
"step": 566
},
{
"epoch": 8.59,
"learning_rate": 2.9645669291338585e-06,
"loss": 0.0834,
"step": 567
},
{
"epoch": 8.61,
"learning_rate": 2.9606299212598427e-06,
"loss": 0.7881,
"step": 568
},
{
"epoch": 8.62,
"learning_rate": 2.956692913385827e-06,
"loss": 0.071,
"step": 569
},
{
"epoch": 8.64,
"learning_rate": 2.952755905511811e-06,
"loss": 0.0518,
"step": 570
},
{
"epoch": 8.65,
"learning_rate": 2.9488188976377958e-06,
"loss": 0.0574,
"step": 571
},
{
"epoch": 8.67,
"learning_rate": 2.94488188976378e-06,
"loss": 0.0522,
"step": 572
},
{
"epoch": 8.68,
"learning_rate": 2.9409448818897642e-06,
"loss": 0.0486,
"step": 573
},
{
"epoch": 8.7,
"learning_rate": 2.937007874015748e-06,
"loss": 0.1236,
"step": 574
},
{
"epoch": 8.71,
"learning_rate": 2.9330708661417322e-06,
"loss": 0.0501,
"step": 575
},
{
"epoch": 8.73,
"learning_rate": 2.929133858267717e-06,
"loss": 0.0509,
"step": 576
},
{
"epoch": 8.74,
"learning_rate": 2.925196850393701e-06,
"loss": 0.0497,
"step": 577
},
{
"epoch": 8.76,
"learning_rate": 2.9212598425196853e-06,
"loss": 0.3165,
"step": 578
},
{
"epoch": 8.77,
"learning_rate": 2.9173228346456695e-06,
"loss": 0.0532,
"step": 579
},
{
"epoch": 8.79,
"learning_rate": 2.9133858267716538e-06,
"loss": 0.1789,
"step": 580
},
{
"epoch": 8.8,
"learning_rate": 2.9094488188976384e-06,
"loss": 0.119,
"step": 581
},
{
"epoch": 8.82,
"learning_rate": 2.9055118110236226e-06,
"loss": 0.0476,
"step": 582
},
{
"epoch": 8.83,
"learning_rate": 2.9015748031496064e-06,
"loss": 0.0482,
"step": 583
},
{
"epoch": 8.85,
"learning_rate": 2.8976377952755906e-06,
"loss": 0.2127,
"step": 584
},
{
"epoch": 8.86,
"learning_rate": 2.893700787401575e-06,
"loss": 0.0508,
"step": 585
},
{
"epoch": 8.88,
"learning_rate": 2.889763779527559e-06,
"loss": 0.0935,
"step": 586
},
{
"epoch": 8.89,
"learning_rate": 2.8858267716535437e-06,
"loss": 0.0468,
"step": 587
},
{
"epoch": 8.91,
"learning_rate": 2.881889763779528e-06,
"loss": 0.0463,
"step": 588
},
{
"epoch": 8.92,
"learning_rate": 2.877952755905512e-06,
"loss": 0.078,
"step": 589
},
{
"epoch": 8.94,
"learning_rate": 2.8740157480314964e-06,
"loss": 0.0486,
"step": 590
},
{
"epoch": 8.95,
"learning_rate": 2.87007874015748e-06,
"loss": 0.1974,
"step": 591
},
{
"epoch": 8.97,
"learning_rate": 2.8661417322834652e-06,
"loss": 1.5522,
"step": 592
},
{
"epoch": 8.98,
"learning_rate": 2.862204724409449e-06,
"loss": 0.046,
"step": 593
},
{
"epoch": 9.0,
"learning_rate": 2.8582677165354333e-06,
"loss": 0.0572,
"step": 594
},
{
"epoch": 9.0,
"eval_accuracy": 0.9545454545454546,
"eval_loss": 0.18054482340812683,
"eval_runtime": 6.2699,
"eval_samples_per_second": 10.526,
"eval_steps_per_second": 2.711,
"step": 594
}
],
"max_steps": 1320,
"num_train_epochs": 20,
"total_flos": 2.0278844132667123e+17,
"trial_name": null,
"trial_params": null
}