FIM_cpp / trainer_state.json
swzwan's picture
Upload folder using huggingface_hub
788a7cf verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0,
"loss": 83.3056,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 0.0,
"loss": 95.8665,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.0,
"loss": 97.972,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 0.0,
"loss": 76.0463,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 0.0,
"loss": 85.1404,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 5.000000000000001e-07,
"loss": 75.9646,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 5.000000000000001e-07,
"loss": 86.754,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 1.0000000000000002e-06,
"loss": 87.0865,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 1.5e-06,
"loss": 81.6646,
"step": 9
},
{
"epoch": 0.02,
"learning_rate": 2.0000000000000003e-06,
"loss": 69.9096,
"step": 10
},
{
"epoch": 0.02,
"learning_rate": 2.5e-06,
"loss": 79.4672,
"step": 11
},
{
"epoch": 0.02,
"learning_rate": 2.5e-06,
"loss": 87.2991,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 3e-06,
"loss": 86.586,
"step": 13
},
{
"epoch": 0.03,
"learning_rate": 3.5000000000000004e-06,
"loss": 68.1378,
"step": 14
},
{
"epoch": 0.03,
"learning_rate": 4.000000000000001e-06,
"loss": 56.5916,
"step": 15
},
{
"epoch": 0.03,
"learning_rate": 4.5e-06,
"loss": 73.8732,
"step": 16
},
{
"epoch": 0.03,
"learning_rate": 5e-06,
"loss": 53.5963,
"step": 17
},
{
"epoch": 0.04,
"learning_rate": 5.500000000000001e-06,
"loss": 37.9982,
"step": 18
},
{
"epoch": 0.04,
"learning_rate": 6e-06,
"loss": 45.8435,
"step": 19
},
{
"epoch": 0.04,
"learning_rate": 6.5000000000000004e-06,
"loss": 40.7565,
"step": 20
},
{
"epoch": 0.04,
"learning_rate": 7.000000000000001e-06,
"loss": 37.2394,
"step": 21
},
{
"epoch": 0.04,
"learning_rate": 7.5e-06,
"loss": 35.8049,
"step": 22
},
{
"epoch": 0.05,
"learning_rate": 8.000000000000001e-06,
"loss": 35.8737,
"step": 23
},
{
"epoch": 0.05,
"learning_rate": 8.500000000000002e-06,
"loss": 28.8236,
"step": 24
},
{
"epoch": 0.05,
"learning_rate": 9e-06,
"loss": 26.5792,
"step": 25
},
{
"epoch": 0.05,
"learning_rate": 9.5e-06,
"loss": 20.3758,
"step": 26
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 18.2907,
"step": 27
},
{
"epoch": 0.06,
"learning_rate": 1.05e-05,
"loss": 14.3071,
"step": 28
},
{
"epoch": 0.06,
"learning_rate": 1.1000000000000001e-05,
"loss": 9.7062,
"step": 29
},
{
"epoch": 0.06,
"learning_rate": 1.1500000000000002e-05,
"loss": 8.8146,
"step": 30
},
{
"epoch": 0.06,
"learning_rate": 1.2e-05,
"loss": 5.3928,
"step": 31
},
{
"epoch": 0.06,
"learning_rate": 1.25e-05,
"loss": 5.5117,
"step": 32
},
{
"epoch": 0.07,
"learning_rate": 1.3000000000000001e-05,
"loss": 4.8147,
"step": 33
},
{
"epoch": 0.07,
"learning_rate": 1.3500000000000001e-05,
"loss": 3.1978,
"step": 34
},
{
"epoch": 0.07,
"learning_rate": 1.4000000000000001e-05,
"loss": 3.1655,
"step": 35
},
{
"epoch": 0.07,
"learning_rate": 1.45e-05,
"loss": 3.0614,
"step": 36
},
{
"epoch": 0.07,
"learning_rate": 1.5e-05,
"loss": 2.5187,
"step": 37
},
{
"epoch": 0.08,
"learning_rate": 1.55e-05,
"loss": 3.2278,
"step": 38
},
{
"epoch": 0.08,
"learning_rate": 1.6000000000000003e-05,
"loss": 2.8507,
"step": 39
},
{
"epoch": 0.08,
"learning_rate": 1.65e-05,
"loss": 2.275,
"step": 40
},
{
"epoch": 0.08,
"learning_rate": 1.7000000000000003e-05,
"loss": 2.0627,
"step": 41
},
{
"epoch": 0.08,
"learning_rate": 1.75e-05,
"loss": 2.8432,
"step": 42
},
{
"epoch": 0.09,
"learning_rate": 1.8e-05,
"loss": 2.2149,
"step": 43
},
{
"epoch": 0.09,
"learning_rate": 1.85e-05,
"loss": 2.0645,
"step": 44
},
{
"epoch": 0.09,
"learning_rate": 1.9e-05,
"loss": 2.2229,
"step": 45
},
{
"epoch": 0.09,
"learning_rate": 1.9500000000000003e-05,
"loss": 3.0316,
"step": 46
},
{
"epoch": 0.09,
"learning_rate": 2e-05,
"loss": 2.3195,
"step": 47
},
{
"epoch": 0.1,
"learning_rate": 2.05e-05,
"loss": 1.7498,
"step": 48
},
{
"epoch": 0.1,
"learning_rate": 2.1e-05,
"loss": 2.5683,
"step": 49
},
{
"epoch": 0.1,
"learning_rate": 2.15e-05,
"loss": 2.3456,
"step": 50
},
{
"epoch": 0.1,
"learning_rate": 2.2000000000000003e-05,
"loss": 2.0581,
"step": 51
},
{
"epoch": 0.1,
"learning_rate": 2.25e-05,
"loss": 2.2809,
"step": 52
},
{
"epoch": 0.11,
"learning_rate": 2.3000000000000003e-05,
"loss": 2.3892,
"step": 53
},
{
"epoch": 0.11,
"learning_rate": 2.35e-05,
"loss": 2.0544,
"step": 54
},
{
"epoch": 0.11,
"learning_rate": 2.4e-05,
"loss": 2.1116,
"step": 55
},
{
"epoch": 0.11,
"learning_rate": 2.45e-05,
"loss": 2.5165,
"step": 56
},
{
"epoch": 0.11,
"learning_rate": 2.5e-05,
"loss": 2.3629,
"step": 57
},
{
"epoch": 0.12,
"learning_rate": 2.5500000000000003e-05,
"loss": 2.0548,
"step": 58
},
{
"epoch": 0.12,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.9614,
"step": 59
},
{
"epoch": 0.12,
"learning_rate": 2.6500000000000004e-05,
"loss": 2.0164,
"step": 60
},
{
"epoch": 0.12,
"learning_rate": 2.7000000000000002e-05,
"loss": 1.9013,
"step": 61
},
{
"epoch": 0.12,
"learning_rate": 2.7500000000000004e-05,
"loss": 2.0752,
"step": 62
},
{
"epoch": 0.13,
"learning_rate": 2.8000000000000003e-05,
"loss": 2.136,
"step": 63
},
{
"epoch": 0.13,
"learning_rate": 2.8499999999999998e-05,
"loss": 2.0806,
"step": 64
},
{
"epoch": 0.13,
"learning_rate": 2.9e-05,
"loss": 1.736,
"step": 65
},
{
"epoch": 0.13,
"learning_rate": 2.95e-05,
"loss": 1.9597,
"step": 66
},
{
"epoch": 0.13,
"learning_rate": 3e-05,
"loss": 2.0509,
"step": 67
},
{
"epoch": 0.14,
"learning_rate": 3.05e-05,
"loss": 1.938,
"step": 68
},
{
"epoch": 0.14,
"learning_rate": 3.1e-05,
"loss": 2.0082,
"step": 69
},
{
"epoch": 0.14,
"learning_rate": 3.15e-05,
"loss": 2.4926,
"step": 70
},
{
"epoch": 0.14,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.6101,
"step": 71
},
{
"epoch": 0.14,
"learning_rate": 3.2500000000000004e-05,
"loss": 1.7914,
"step": 72
},
{
"epoch": 0.15,
"learning_rate": 3.3e-05,
"loss": 2.0132,
"step": 73
},
{
"epoch": 0.15,
"learning_rate": 3.35e-05,
"loss": 1.6407,
"step": 74
},
{
"epoch": 0.15,
"learning_rate": 3.4000000000000007e-05,
"loss": 2.1127,
"step": 75
},
{
"epoch": 0.15,
"learning_rate": 3.45e-05,
"loss": 2.3478,
"step": 76
},
{
"epoch": 0.15,
"learning_rate": 3.5e-05,
"loss": 2.3729,
"step": 77
},
{
"epoch": 0.16,
"learning_rate": 3.55e-05,
"loss": 1.7706,
"step": 78
},
{
"epoch": 0.16,
"learning_rate": 3.6e-05,
"loss": 1.8671,
"step": 79
},
{
"epoch": 0.16,
"learning_rate": 3.65e-05,
"loss": 1.7771,
"step": 80
},
{
"epoch": 0.16,
"learning_rate": 3.7e-05,
"loss": 1.9566,
"step": 81
},
{
"epoch": 0.16,
"learning_rate": 3.7500000000000003e-05,
"loss": 1.9079,
"step": 82
},
{
"epoch": 0.17,
"learning_rate": 3.8e-05,
"loss": 2.0504,
"step": 83
},
{
"epoch": 0.17,
"learning_rate": 3.85e-05,
"loss": 2.2557,
"step": 84
},
{
"epoch": 0.17,
"learning_rate": 3.9000000000000006e-05,
"loss": 2.054,
"step": 85
},
{
"epoch": 0.17,
"learning_rate": 3.9500000000000005e-05,
"loss": 2.0602,
"step": 86
},
{
"epoch": 0.17,
"learning_rate": 4e-05,
"loss": 1.9849,
"step": 87
},
{
"epoch": 0.18,
"learning_rate": 4.05e-05,
"loss": 2.0352,
"step": 88
},
{
"epoch": 0.18,
"learning_rate": 4.1e-05,
"loss": 2.0,
"step": 89
},
{
"epoch": 0.18,
"learning_rate": 4.15e-05,
"loss": 1.9662,
"step": 90
},
{
"epoch": 0.18,
"learning_rate": 4.2e-05,
"loss": 1.7563,
"step": 91
},
{
"epoch": 0.18,
"learning_rate": 4.25e-05,
"loss": 1.8681,
"step": 92
},
{
"epoch": 0.19,
"learning_rate": 4.3e-05,
"loss": 1.6307,
"step": 93
},
{
"epoch": 0.19,
"learning_rate": 4.35e-05,
"loss": 1.7752,
"step": 94
},
{
"epoch": 0.19,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.9107,
"step": 95
},
{
"epoch": 0.19,
"learning_rate": 4.4500000000000004e-05,
"loss": 2.1152,
"step": 96
},
{
"epoch": 0.19,
"learning_rate": 4.5e-05,
"loss": 1.8788,
"step": 97
},
{
"epoch": 0.2,
"learning_rate": 4.55e-05,
"loss": 1.9173,
"step": 98
},
{
"epoch": 0.2,
"learning_rate": 4.600000000000001e-05,
"loss": 1.6978,
"step": 99
},
{
"epoch": 0.2,
"learning_rate": 4.6500000000000005e-05,
"loss": 1.9182,
"step": 100
},
{
"epoch": 0.2,
"eval_loss": 1.551979660987854,
"eval_runtime": 4178.1095,
"eval_samples_per_second": 27.385,
"eval_steps_per_second": 13.693,
"step": 100
},
{
"epoch": 0.2,
"learning_rate": 4.7e-05,
"loss": 1.6893,
"step": 101
},
{
"epoch": 0.2,
"learning_rate": 4.75e-05,
"loss": 1.6763,
"step": 102
},
{
"epoch": 0.21,
"learning_rate": 4.8e-05,
"loss": 1.7825,
"step": 103
},
{
"epoch": 0.21,
"learning_rate": 4.85e-05,
"loss": 1.5596,
"step": 104
},
{
"epoch": 0.21,
"learning_rate": 4.9e-05,
"loss": 1.7855,
"step": 105
},
{
"epoch": 0.21,
"learning_rate": 4.9500000000000004e-05,
"loss": 1.6738,
"step": 106
},
{
"epoch": 0.21,
"learning_rate": 5e-05,
"loss": 1.8853,
"step": 107
},
{
"epoch": 0.22,
"learning_rate": 4.9999228941119745e-05,
"loss": 1.5495,
"step": 108
},
{
"epoch": 0.22,
"learning_rate": 4.999691581204152e-05,
"loss": 1.74,
"step": 109
},
{
"epoch": 0.22,
"learning_rate": 4.9993060755450015e-05,
"loss": 1.6969,
"step": 110
},
{
"epoch": 0.22,
"learning_rate": 4.998766400914329e-05,
"loss": 1.6482,
"step": 111
},
{
"epoch": 0.22,
"learning_rate": 4.9980725906018074e-05,
"loss": 1.7053,
"step": 112
},
{
"epoch": 0.23,
"learning_rate": 4.9972246874049254e-05,
"loss": 1.6929,
"step": 113
},
{
"epoch": 0.23,
"learning_rate": 4.9962227436263453e-05,
"loss": 1.7185,
"step": 114
},
{
"epoch": 0.23,
"learning_rate": 4.995066821070679e-05,
"loss": 1.5287,
"step": 115
},
{
"epoch": 0.23,
"learning_rate": 4.9937569910406756e-05,
"loss": 1.8321,
"step": 116
},
{
"epoch": 0.23,
"learning_rate": 4.99229333433282e-05,
"loss": 1.7286,
"step": 117
},
{
"epoch": 0.24,
"learning_rate": 4.990675941232353e-05,
"loss": 1.3939,
"step": 118
},
{
"epoch": 0.24,
"learning_rate": 4.9889049115077005e-05,
"loss": 1.7136,
"step": 119
},
{
"epoch": 0.24,
"learning_rate": 4.9869803544043166e-05,
"loss": 1.6449,
"step": 120
},
{
"epoch": 0.24,
"learning_rate": 4.98490238863795e-05,
"loss": 1.4612,
"step": 121
},
{
"epoch": 0.24,
"learning_rate": 4.982671142387316e-05,
"loss": 1.4071,
"step": 122
},
{
"epoch": 0.25,
"learning_rate": 4.980286753286195e-05,
"loss": 1.4904,
"step": 123
},
{
"epoch": 0.25,
"learning_rate": 4.9777493684149375e-05,
"loss": 1.7834,
"step": 124
},
{
"epoch": 0.25,
"learning_rate": 4.975059144291394e-05,
"loss": 1.7078,
"step": 125
},
{
"epoch": 0.25,
"learning_rate": 4.972216246861262e-05,
"loss": 1.4912,
"step": 126
},
{
"epoch": 0.25,
"learning_rate": 4.9692208514878444e-05,
"loss": 1.8625,
"step": 127
},
{
"epoch": 0.26,
"learning_rate": 4.966073142941239e-05,
"loss": 1.5348,
"step": 128
},
{
"epoch": 0.26,
"learning_rate": 4.962773315386935e-05,
"loss": 1.4056,
"step": 129
},
{
"epoch": 0.26,
"learning_rate": 4.9593215723738404e-05,
"loss": 1.1799,
"step": 130
},
{
"epoch": 0.26,
"learning_rate": 4.9557181268217227e-05,
"loss": 1.2923,
"step": 131
},
{
"epoch": 0.26,
"learning_rate": 4.951963201008076e-05,
"loss": 1.3528,
"step": 132
},
{
"epoch": 0.27,
"learning_rate": 4.9480570265544144e-05,
"loss": 1.2402,
"step": 133
},
{
"epoch": 0.27,
"learning_rate": 4.943999844411977e-05,
"loss": 1.3492,
"step": 134
},
{
"epoch": 0.27,
"learning_rate": 4.939791904846869e-05,
"loss": 1.329,
"step": 135
},
{
"epoch": 0.27,
"learning_rate": 4.935433467424624e-05,
"loss": 1.3137,
"step": 136
},
{
"epoch": 0.27,
"learning_rate": 4.9309248009941914e-05,
"loss": 1.1167,
"step": 137
},
{
"epoch": 0.28,
"learning_rate": 4.9262661836713564e-05,
"loss": 1.0645,
"step": 138
},
{
"epoch": 0.28,
"learning_rate": 4.9214579028215776e-05,
"loss": 1.3611,
"step": 139
},
{
"epoch": 0.28,
"learning_rate": 4.916500255042268e-05,
"loss": 1.2777,
"step": 140
},
{
"epoch": 0.28,
"learning_rate": 4.9113935461444955e-05,
"loss": 1.2108,
"step": 141
},
{
"epoch": 0.28,
"learning_rate": 4.906138091134118e-05,
"loss": 1.1025,
"step": 142
},
{
"epoch": 0.29,
"learning_rate": 4.900734214192358e-05,
"loss": 1.0768,
"step": 143
},
{
"epoch": 0.29,
"learning_rate": 4.8951822486557986e-05,
"loss": 1.3846,
"step": 144
},
{
"epoch": 0.29,
"learning_rate": 4.8894825369958255e-05,
"loss": 1.1072,
"step": 145
},
{
"epoch": 0.29,
"learning_rate": 4.8836354307975026e-05,
"loss": 1.2182,
"step": 146
},
{
"epoch": 0.29,
"learning_rate": 4.877641290737884e-05,
"loss": 1.2538,
"step": 147
},
{
"epoch": 0.3,
"learning_rate": 4.8715004865637614e-05,
"loss": 1.1044,
"step": 148
},
{
"epoch": 0.3,
"learning_rate": 4.8652133970688636e-05,
"loss": 1.0941,
"step": 149
},
{
"epoch": 0.3,
"learning_rate": 4.8587804100704845e-05,
"loss": 0.9369,
"step": 150
},
{
"epoch": 0.3,
"learning_rate": 4.852201922385564e-05,
"loss": 0.9077,
"step": 151
},
{
"epoch": 0.3,
"learning_rate": 4.8454783398062106e-05,
"loss": 1.0606,
"step": 152
},
{
"epoch": 0.31,
"learning_rate": 4.838610077074669e-05,
"loss": 1.2465,
"step": 153
},
{
"epoch": 0.31,
"learning_rate": 4.8315975578577355e-05,
"loss": 1.16,
"step": 154
},
{
"epoch": 0.31,
"learning_rate": 4.8244412147206284e-05,
"loss": 1.2837,
"step": 155
},
{
"epoch": 0.31,
"learning_rate": 4.817141489100302e-05,
"loss": 1.2553,
"step": 156
},
{
"epoch": 0.31,
"learning_rate": 4.8096988312782174e-05,
"loss": 1.0804,
"step": 157
},
{
"epoch": 0.32,
"learning_rate": 4.8021137003525664e-05,
"loss": 0.9331,
"step": 158
},
{
"epoch": 0.32,
"learning_rate": 4.794386564209953e-05,
"loss": 0.952,
"step": 159
},
{
"epoch": 0.32,
"learning_rate": 4.7865178994965344e-05,
"loss": 0.9735,
"step": 160
},
{
"epoch": 0.32,
"learning_rate": 4.7785081915886134e-05,
"loss": 0.8972,
"step": 161
},
{
"epoch": 0.32,
"learning_rate": 4.7703579345627035e-05,
"loss": 1.2156,
"step": 162
},
{
"epoch": 0.33,
"learning_rate": 4.762067631165049e-05,
"loss": 1.2272,
"step": 163
},
{
"epoch": 0.33,
"learning_rate": 4.753637792780614e-05,
"loss": 0.8432,
"step": 164
},
{
"epoch": 0.33,
"learning_rate": 4.745068939401539e-05,
"loss": 0.9018,
"step": 165
},
{
"epoch": 0.33,
"learning_rate": 4.7363615995950626e-05,
"loss": 0.8768,
"step": 166
},
{
"epoch": 0.33,
"learning_rate": 4.72751631047092e-05,
"loss": 0.8826,
"step": 167
},
{
"epoch": 0.34,
"learning_rate": 4.718533617648209e-05,
"loss": 0.907,
"step": 168
},
{
"epoch": 0.34,
"learning_rate": 4.709414075221734e-05,
"loss": 0.9951,
"step": 169
},
{
"epoch": 0.34,
"learning_rate": 4.7001582457278304e-05,
"loss": 0.9882,
"step": 170
},
{
"epoch": 0.34,
"learning_rate": 4.690766700109659e-05,
"loss": 1.0546,
"step": 171
},
{
"epoch": 0.34,
"learning_rate": 4.681240017681993e-05,
"loss": 0.7883,
"step": 172
},
{
"epoch": 0.35,
"learning_rate": 4.671578786095478e-05,
"loss": 1.1422,
"step": 173
},
{
"epoch": 0.35,
"learning_rate": 4.661783601300388e-05,
"loss": 0.9893,
"step": 174
},
{
"epoch": 0.35,
"learning_rate": 4.65185506750986e-05,
"loss": 1.0088,
"step": 175
},
{
"epoch": 0.35,
"learning_rate": 4.6417937971626245e-05,
"loss": 0.8233,
"step": 176
},
{
"epoch": 0.35,
"learning_rate": 4.6316004108852305e-05,
"loss": 1.0708,
"step": 177
},
{
"epoch": 0.36,
"learning_rate": 4.6212755374537596e-05,
"loss": 1.0227,
"step": 178
},
{
"epoch": 0.36,
"learning_rate": 4.610819813755038e-05,
"loss": 0.9609,
"step": 179
},
{
"epoch": 0.36,
"learning_rate": 4.600233884747355e-05,
"loss": 0.8691,
"step": 180
},
{
"epoch": 0.36,
"learning_rate": 4.5895184034206765e-05,
"loss": 1.0931,
"step": 181
},
{
"epoch": 0.36,
"learning_rate": 4.5786740307563636e-05,
"loss": 0.8013,
"step": 182
},
{
"epoch": 0.37,
"learning_rate": 4.567701435686404e-05,
"loss": 0.817,
"step": 183
},
{
"epoch": 0.37,
"learning_rate": 4.55660129505215e-05,
"loss": 1.0999,
"step": 184
},
{
"epoch": 0.37,
"learning_rate": 4.545374293562559e-05,
"loss": 1.0032,
"step": 185
},
{
"epoch": 0.37,
"learning_rate": 4.534021123751968e-05,
"loss": 0.9359,
"step": 186
},
{
"epoch": 0.37,
"learning_rate": 4.522542485937369e-05,
"loss": 0.92,
"step": 187
},
{
"epoch": 0.38,
"learning_rate": 4.5109390881752114e-05,
"loss": 0.8375,
"step": 188
},
{
"epoch": 0.38,
"learning_rate": 4.499211646217727e-05,
"loss": 1.1646,
"step": 189
},
{
"epoch": 0.38,
"learning_rate": 4.487360883468775e-05,
"loss": 0.9532,
"step": 190
},
{
"epoch": 0.38,
"learning_rate": 4.4753875309392266e-05,
"loss": 1.2272,
"step": 191
},
{
"epoch": 0.38,
"learning_rate": 4.463292327201862e-05,
"loss": 1.0792,
"step": 192
},
{
"epoch": 0.39,
"learning_rate": 4.451076018345825e-05,
"loss": 0.9567,
"step": 193
},
{
"epoch": 0.39,
"learning_rate": 4.4387393579305865e-05,
"loss": 0.6387,
"step": 194
},
{
"epoch": 0.39,
"learning_rate": 4.426283106939474e-05,
"loss": 1.1238,
"step": 195
},
{
"epoch": 0.39,
"learning_rate": 4.4137080337327205e-05,
"loss": 0.8722,
"step": 196
},
{
"epoch": 0.39,
"learning_rate": 4.401014914000078e-05,
"loss": 0.8679,
"step": 197
},
{
"epoch": 0.4,
"learning_rate": 4.3882045307129594e-05,
"loss": 0.9063,
"step": 198
},
{
"epoch": 0.4,
"learning_rate": 4.375277674076149e-05,
"loss": 1.0135,
"step": 199
},
{
"epoch": 0.4,
"learning_rate": 4.3622351414790554e-05,
"loss": 1.0026,
"step": 200
},
{
"epoch": 0.4,
"eval_loss": 1.3784873485565186,
"eval_runtime": 4792.6678,
"eval_samples_per_second": 23.873,
"eval_steps_per_second": 11.937,
"step": 200
},
{
"epoch": 0.4,
"learning_rate": 4.349077737446525e-05,
"loss": 1.4974,
"step": 201
},
{
"epoch": 0.4,
"learning_rate": 4.335806273589214e-05,
"loss": 1.3078,
"step": 202
},
{
"epoch": 0.41,
"learning_rate": 4.3224215685535294e-05,
"loss": 1.6193,
"step": 203
},
{
"epoch": 0.41,
"learning_rate": 4.3089244479711236e-05,
"loss": 1.3764,
"step": 204
},
{
"epoch": 0.41,
"learning_rate": 4.295315744407972e-05,
"loss": 1.5635,
"step": 205
},
{
"epoch": 0.41,
"learning_rate": 4.281596297313013e-05,
"loss": 1.4103,
"step": 206
},
{
"epoch": 0.41,
"learning_rate": 4.267766952966369e-05,
"loss": 1.3984,
"step": 207
},
{
"epoch": 0.42,
"learning_rate": 4.25382856442714e-05,
"loss": 1.5663,
"step": 208
},
{
"epoch": 0.42,
"learning_rate": 4.2397819914807856e-05,
"loss": 1.348,
"step": 209
},
{
"epoch": 0.42,
"learning_rate": 4.225628100586093e-05,
"loss": 1.4036,
"step": 210
},
{
"epoch": 0.42,
"learning_rate": 4.211367764821722e-05,
"loss": 1.4676,
"step": 211
},
{
"epoch": 0.42,
"learning_rate": 4.197001863832355e-05,
"loss": 1.2909,
"step": 212
},
{
"epoch": 0.43,
"learning_rate": 4.182531283774434e-05,
"loss": 1.3502,
"step": 213
},
{
"epoch": 0.43,
"learning_rate": 4.1679569172614996e-05,
"loss": 1.3483,
"step": 214
},
{
"epoch": 0.43,
"learning_rate": 4.1532796633091296e-05,
"loss": 1.4727,
"step": 215
},
{
"epoch": 0.43,
"learning_rate": 4.138500427279485e-05,
"loss": 1.216,
"step": 216
},
{
"epoch": 0.43,
"learning_rate": 4.123620120825459e-05,
"loss": 1.2367,
"step": 217
},
{
"epoch": 0.44,
"learning_rate": 4.1086396618344476e-05,
"loss": 1.4552,
"step": 218
},
{
"epoch": 0.44,
"learning_rate": 4.093559974371725e-05,
"loss": 1.6128,
"step": 219
},
{
"epoch": 0.44,
"learning_rate": 4.0783819886234445e-05,
"loss": 1.2725,
"step": 220
},
{
"epoch": 0.44,
"learning_rate": 4.063106640839264e-05,
"loss": 1.3104,
"step": 221
},
{
"epoch": 0.44,
"learning_rate": 4.047734873274586e-05,
"loss": 1.4107,
"step": 222
},
{
"epoch": 0.45,
"learning_rate": 4.0322676341324415e-05,
"loss": 1.2777,
"step": 223
},
{
"epoch": 0.45,
"learning_rate": 4.0167058775049996e-05,
"loss": 1.2636,
"step": 224
},
{
"epoch": 0.45,
"learning_rate": 4.0010505633147106e-05,
"loss": 1.2956,
"step": 225
},
{
"epoch": 0.45,
"learning_rate": 3.985302657255097e-05,
"loss": 1.1578,
"step": 226
},
{
"epoch": 0.45,
"learning_rate": 3.969463130731183e-05,
"loss": 1.3663,
"step": 227
},
{
"epoch": 0.46,
"learning_rate": 3.953532960799577e-05,
"loss": 1.3132,
"step": 228
},
{
"epoch": 0.46,
"learning_rate": 3.937513130108197e-05,
"loss": 1.114,
"step": 229
},
{
"epoch": 0.46,
"learning_rate": 3.92140462683566e-05,
"loss": 1.266,
"step": 230
},
{
"epoch": 0.46,
"learning_rate": 3.905208444630327e-05,
"loss": 1.3218,
"step": 231
},
{
"epoch": 0.46,
"learning_rate": 3.888925582549006e-05,
"loss": 1.2201,
"step": 232
},
{
"epoch": 0.47,
"learning_rate": 3.87255704499533e-05,
"loss": 1.3779,
"step": 233
},
{
"epoch": 0.47,
"learning_rate": 3.856103841657797e-05,
"loss": 1.1852,
"step": 234
},
{
"epoch": 0.47,
"learning_rate": 3.8395669874474915e-05,
"loss": 1.254,
"step": 235
},
{
"epoch": 0.47,
"learning_rate": 3.822947502435477e-05,
"loss": 1.5058,
"step": 236
},
{
"epoch": 0.47,
"learning_rate": 3.8062464117898724e-05,
"loss": 1.5119,
"step": 237
},
{
"epoch": 0.48,
"learning_rate": 3.789464745712619e-05,
"loss": 1.1567,
"step": 238
},
{
"epoch": 0.48,
"learning_rate": 3.7726035393759285e-05,
"loss": 1.2842,
"step": 239
},
{
"epoch": 0.48,
"learning_rate": 3.755663832858432e-05,
"loss": 1.3541,
"step": 240
},
{
"epoch": 0.48,
"learning_rate": 3.7386466710810194e-05,
"loss": 1.2379,
"step": 241
},
{
"epoch": 0.48,
"learning_rate": 3.721553103742388e-05,
"loss": 1.2396,
"step": 242
},
{
"epoch": 0.49,
"learning_rate": 3.704384185254288e-05,
"loss": 1.2146,
"step": 243
},
{
"epoch": 0.49,
"learning_rate": 3.6871409746764865e-05,
"loss": 1.2261,
"step": 244
},
{
"epoch": 0.49,
"learning_rate": 3.6698245356514335e-05,
"loss": 1.4124,
"step": 245
},
{
"epoch": 0.49,
"learning_rate": 3.652435936338656e-05,
"loss": 0.9498,
"step": 246
},
{
"epoch": 0.49,
"learning_rate": 3.634976249348867e-05,
"loss": 1.147,
"step": 247
},
{
"epoch": 0.5,
"learning_rate": 3.6174465516778035e-05,
"loss": 1.2871,
"step": 248
},
{
"epoch": 0.5,
"learning_rate": 3.599847924639788e-05,
"loss": 1.3978,
"step": 249
},
{
"epoch": 0.5,
"learning_rate": 3.582181453801036e-05,
"loss": 1.2626,
"step": 250
},
{
"epoch": 0.5,
"learning_rate": 3.564448228912682e-05,
"loss": 1.2497,
"step": 251
},
{
"epoch": 0.5,
"learning_rate": 3.54664934384357e-05,
"loss": 1.1724,
"step": 252
},
{
"epoch": 0.51,
"learning_rate": 3.528785896512772e-05,
"loss": 1.2546,
"step": 253
},
{
"epoch": 0.51,
"learning_rate": 3.510858988821863e-05,
"loss": 1.668,
"step": 254
},
{
"epoch": 0.51,
"learning_rate": 3.4928697265869515e-05,
"loss": 1.2541,
"step": 255
},
{
"epoch": 0.51,
"learning_rate": 3.474819219470471e-05,
"loss": 1.0438,
"step": 256
},
{
"epoch": 0.51,
"learning_rate": 3.456708580912725e-05,
"loss": 1.2363,
"step": 257
},
{
"epoch": 0.52,
"learning_rate": 3.438538928063208e-05,
"loss": 1.1372,
"step": 258
},
{
"epoch": 0.52,
"learning_rate": 3.4203113817116957e-05,
"loss": 1.0645,
"step": 259
},
{
"epoch": 0.52,
"learning_rate": 3.402027066219105e-05,
"loss": 1.077,
"step": 260
},
{
"epoch": 0.52,
"learning_rate": 3.383687109448143e-05,
"loss": 1.2661,
"step": 261
},
{
"epoch": 0.52,
"learning_rate": 3.365292642693732e-05,
"loss": 1.2931,
"step": 262
},
{
"epoch": 0.53,
"learning_rate": 3.346844800613229e-05,
"loss": 1.4293,
"step": 263
},
{
"epoch": 0.53,
"learning_rate": 3.3283447211564276e-05,
"loss": 1.4949,
"step": 264
},
{
"epoch": 0.53,
"learning_rate": 3.309793545495374e-05,
"loss": 1.456,
"step": 265
},
{
"epoch": 0.53,
"learning_rate": 3.2911924179539656e-05,
"loss": 1.4819,
"step": 266
},
{
"epoch": 0.53,
"learning_rate": 3.272542485937369e-05,
"loss": 1.3641,
"step": 267
},
{
"epoch": 0.54,
"learning_rate": 3.253844899861239e-05,
"loss": 1.2427,
"step": 268
},
{
"epoch": 0.54,
"learning_rate": 3.23510081308076e-05,
"loss": 1.3287,
"step": 269
},
{
"epoch": 0.54,
"learning_rate": 3.2163113818194964e-05,
"loss": 1.4616,
"step": 270
},
{
"epoch": 0.54,
"learning_rate": 3.1974777650980735e-05,
"loss": 1.502,
"step": 271
},
{
"epoch": 0.54,
"learning_rate": 3.178601124662686e-05,
"loss": 1.2544,
"step": 272
},
{
"epoch": 0.55,
"learning_rate": 3.1596826249134324e-05,
"loss": 1.2749,
"step": 273
},
{
"epoch": 0.55,
"learning_rate": 3.140723432832492e-05,
"loss": 1.3278,
"step": 274
},
{
"epoch": 0.55,
"learning_rate": 3.121724717912138e-05,
"loss": 1.2634,
"step": 275
},
{
"epoch": 0.55,
"learning_rate": 3.102687652082597e-05,
"loss": 1.4866,
"step": 276
},
{
"epoch": 0.55,
"learning_rate": 3.083613409639764e-05,
"loss": 1.2986,
"step": 277
},
{
"epoch": 0.56,
"learning_rate": 3.06450316717276e-05,
"loss": 1.2379,
"step": 278
},
{
"epoch": 0.56,
"learning_rate": 3.045358103491357e-05,
"loss": 1.2092,
"step": 279
},
{
"epoch": 0.56,
"learning_rate": 3.026179399553264e-05,
"loss": 1.3209,
"step": 280
},
{
"epoch": 0.56,
"learning_rate": 3.0069682383912813e-05,
"loss": 1.4146,
"step": 281
},
{
"epoch": 0.56,
"learning_rate": 2.9877258050403212e-05,
"loss": 1.2452,
"step": 282
},
{
"epoch": 0.57,
"learning_rate": 2.9684532864643122e-05,
"loss": 1.3337,
"step": 283
},
{
"epoch": 0.57,
"learning_rate": 2.949151871482982e-05,
"loss": 1.3038,
"step": 284
},
{
"epoch": 0.57,
"learning_rate": 2.929822750698524e-05,
"loss": 1.3654,
"step": 285
},
{
"epoch": 0.57,
"learning_rate": 2.9104671164221576e-05,
"loss": 1.4753,
"step": 286
},
{
"epoch": 0.57,
"learning_rate": 2.8910861626005776e-05,
"loss": 1.2995,
"step": 287
},
{
"epoch": 0.58,
"learning_rate": 2.871681084742308e-05,
"loss": 1.2287,
"step": 288
},
{
"epoch": 0.58,
"learning_rate": 2.8522530798439567e-05,
"loss": 1.1932,
"step": 289
},
{
"epoch": 0.58,
"learning_rate": 2.832803346316381e-05,
"loss": 1.2312,
"step": 290
},
{
"epoch": 0.58,
"learning_rate": 2.8133330839107608e-05,
"loss": 1.4553,
"step": 291
},
{
"epoch": 0.58,
"learning_rate": 2.7938434936445945e-05,
"loss": 1.1896,
"step": 292
},
{
"epoch": 0.59,
"learning_rate": 2.774335777727613e-05,
"loss": 1.2998,
"step": 293
},
{
"epoch": 0.59,
"learning_rate": 2.754811139487625e-05,
"loss": 1.2403,
"step": 294
},
{
"epoch": 0.59,
"learning_rate": 2.7352707832962865e-05,
"loss": 1.5125,
"step": 295
},
{
"epoch": 0.59,
"learning_rate": 2.7157159144948092e-05,
"loss": 1.2591,
"step": 296
},
{
"epoch": 0.59,
"learning_rate": 2.6961477393196126e-05,
"loss": 1.2907,
"step": 297
},
{
"epoch": 0.6,
"learning_rate": 2.6765674648279172e-05,
"loss": 1.3376,
"step": 298
},
{
"epoch": 0.6,
"learning_rate": 2.656976298823284e-05,
"loss": 1.1303,
"step": 299
},
{
"epoch": 0.6,
"learning_rate": 2.637375449781115e-05,
"loss": 1.3983,
"step": 300
},
{
"epoch": 0.6,
"eval_loss": 1.3045283555984497,
"eval_runtime": 4572.2865,
"eval_samples_per_second": 25.024,
"eval_steps_per_second": 12.512,
"step": 300
},
{
"epoch": 0.6,
"learning_rate": 2.6177661267741065e-05,
"loss": 1.2213,
"step": 301
},
{
"epoch": 0.6,
"learning_rate": 2.598149539397672e-05,
"loss": 1.3029,
"step": 302
},
{
"epoch": 0.61,
"learning_rate": 2.578526897695321e-05,
"loss": 1.4005,
"step": 303
},
{
"epoch": 0.61,
"learning_rate": 2.558899412084026e-05,
"loss": 1.4929,
"step": 304
},
{
"epoch": 0.61,
"learning_rate": 2.539268293279552e-05,
"loss": 1.2246,
"step": 305
},
{
"epoch": 0.61,
"learning_rate": 2.5196347522217784e-05,
"loss": 1.2211,
"step": 306
},
{
"epoch": 0.61,
"learning_rate": 2.5e-05,
"loss": 1.3308,
"step": 307
},
{
"epoch": 0.62,
"learning_rate": 2.480365247778223e-05,
"loss": 1.471,
"step": 308
},
{
"epoch": 0.62,
"learning_rate": 2.460731706720449e-05,
"loss": 1.2822,
"step": 309
},
{
"epoch": 0.62,
"learning_rate": 2.4411005879159753e-05,
"loss": 1.1612,
"step": 310
},
{
"epoch": 0.62,
"learning_rate": 2.4214731023046793e-05,
"loss": 1.4232,
"step": 311
},
{
"epoch": 0.62,
"learning_rate": 2.4018504606023293e-05,
"loss": 1.1328,
"step": 312
},
{
"epoch": 0.63,
"learning_rate": 2.3822338732258937e-05,
"loss": 1.3512,
"step": 313
},
{
"epoch": 0.63,
"learning_rate": 2.3626245502188864e-05,
"loss": 1.2963,
"step": 314
},
{
"epoch": 0.63,
"learning_rate": 2.3430237011767167e-05,
"loss": 1.453,
"step": 315
},
{
"epoch": 0.63,
"learning_rate": 2.323432535172084e-05,
"loss": 1.4939,
"step": 316
},
{
"epoch": 0.63,
"learning_rate": 2.303852260680388e-05,
"loss": 1.2504,
"step": 317
},
{
"epoch": 0.64,
"learning_rate": 2.284284085505192e-05,
"loss": 1.2362,
"step": 318
},
{
"epoch": 0.64,
"learning_rate": 2.2647292167037144e-05,
"loss": 1.3078,
"step": 319
},
{
"epoch": 0.64,
"learning_rate": 2.2451888605123754e-05,
"loss": 1.442,
"step": 320
},
{
"epoch": 0.64,
"learning_rate": 2.225664222272387e-05,
"loss": 1.4557,
"step": 321
},
{
"epoch": 0.64,
"learning_rate": 2.2061565063554064e-05,
"loss": 1.472,
"step": 322
},
{
"epoch": 0.65,
"learning_rate": 2.186666916089239e-05,
"loss": 1.292,
"step": 323
},
{
"epoch": 0.65,
"learning_rate": 2.1671966536836196e-05,
"loss": 1.4428,
"step": 324
},
{
"epoch": 0.65,
"learning_rate": 2.1477469201560435e-05,
"loss": 1.2264,
"step": 325
},
{
"epoch": 0.65,
"learning_rate": 2.1283189152576925e-05,
"loss": 1.3822,
"step": 326
},
{
"epoch": 0.65,
"learning_rate": 2.1089138373994223e-05,
"loss": 1.4051,
"step": 327
},
{
"epoch": 0.66,
"learning_rate": 2.089532883577843e-05,
"loss": 1.2993,
"step": 328
},
{
"epoch": 0.66,
"learning_rate": 2.070177249301476e-05,
"loss": 1.3713,
"step": 329
},
{
"epoch": 0.66,
"learning_rate": 2.0508481285170186e-05,
"loss": 1.297,
"step": 330
},
{
"epoch": 0.66,
"learning_rate": 2.031546713535688e-05,
"loss": 1.4,
"step": 331
},
{
"epoch": 0.66,
"learning_rate": 2.0122741949596797e-05,
"loss": 1.3429,
"step": 332
},
{
"epoch": 0.67,
"learning_rate": 1.9930317616087196e-05,
"loss": 1.3994,
"step": 333
},
{
"epoch": 0.67,
"learning_rate": 1.9738206004467363e-05,
"loss": 1.5288,
"step": 334
},
{
"epoch": 0.67,
"learning_rate": 1.9546418965086442e-05,
"loss": 1.2621,
"step": 335
},
{
"epoch": 0.67,
"learning_rate": 1.935496832827241e-05,
"loss": 1.4992,
"step": 336
},
{
"epoch": 0.67,
"learning_rate": 1.9163865903602374e-05,
"loss": 1.2588,
"step": 337
},
{
"epoch": 0.68,
"learning_rate": 1.897312347917404e-05,
"loss": 1.5055,
"step": 338
},
{
"epoch": 0.68,
"learning_rate": 1.8782752820878634e-05,
"loss": 1.2727,
"step": 339
},
{
"epoch": 0.68,
"learning_rate": 1.8592765671675084e-05,
"loss": 0.9645,
"step": 340
},
{
"epoch": 0.68,
"learning_rate": 1.8403173750865685e-05,
"loss": 1.2442,
"step": 341
},
{
"epoch": 0.68,
"learning_rate": 1.8213988753373146e-05,
"loss": 1.3001,
"step": 342
},
{
"epoch": 0.69,
"learning_rate": 1.802522234901927e-05,
"loss": 1.3376,
"step": 343
},
{
"epoch": 0.69,
"learning_rate": 1.783688618180504e-05,
"loss": 1.3671,
"step": 344
},
{
"epoch": 0.69,
"learning_rate": 1.7648991869192405e-05,
"loss": 1.2345,
"step": 345
},
{
"epoch": 0.69,
"learning_rate": 1.746155100138761e-05,
"loss": 1.151,
"step": 346
},
{
"epoch": 0.69,
"learning_rate": 1.7274575140626318e-05,
"loss": 1.3213,
"step": 347
},
{
"epoch": 0.7,
"learning_rate": 1.7088075820460346e-05,
"loss": 1.2663,
"step": 348
},
{
"epoch": 0.7,
"learning_rate": 1.690206454504627e-05,
"loss": 1.5264,
"step": 349
},
{
"epoch": 0.7,
"learning_rate": 1.6716552788435724e-05,
"loss": 1.3686,
"step": 350
},
{
"epoch": 0.7,
"learning_rate": 1.6531551993867717e-05,
"loss": 1.3005,
"step": 351
},
{
"epoch": 0.7,
"learning_rate": 1.6347073573062672e-05,
"loss": 1.2474,
"step": 352
},
{
"epoch": 0.71,
"learning_rate": 1.6163128905518578e-05,
"loss": 1.3205,
"step": 353
},
{
"epoch": 0.71,
"learning_rate": 1.5979729337808955e-05,
"loss": 1.4708,
"step": 354
},
{
"epoch": 0.71,
"learning_rate": 1.5796886182883053e-05,
"loss": 0.9178,
"step": 355
},
{
"epoch": 0.71,
"learning_rate": 1.561461071936792e-05,
"loss": 1.1726,
"step": 356
},
{
"epoch": 0.71,
"learning_rate": 1.5432914190872757e-05,
"loss": 1.4034,
"step": 357
},
{
"epoch": 0.72,
"learning_rate": 1.5251807805295302e-05,
"loss": 1.2072,
"step": 358
},
{
"epoch": 0.72,
"learning_rate": 1.5071302734130489e-05,
"loss": 1.0984,
"step": 359
},
{
"epoch": 0.72,
"learning_rate": 1.4891410111781378e-05,
"loss": 1.29,
"step": 360
},
{
"epoch": 0.72,
"learning_rate": 1.4712141034872282e-05,
"loss": 1.1494,
"step": 361
},
{
"epoch": 0.72,
"learning_rate": 1.4533506561564306e-05,
"loss": 1.3977,
"step": 362
},
{
"epoch": 0.73,
"learning_rate": 1.4355517710873184e-05,
"loss": 1.2525,
"step": 363
},
{
"epoch": 0.73,
"learning_rate": 1.4178185461989662e-05,
"loss": 1.1666,
"step": 364
},
{
"epoch": 0.73,
"learning_rate": 1.4001520753602121e-05,
"loss": 1.3341,
"step": 365
},
{
"epoch": 0.73,
"learning_rate": 1.3825534483221974e-05,
"loss": 1.2377,
"step": 366
},
{
"epoch": 0.73,
"learning_rate": 1.3650237506511331e-05,
"loss": 1.3557,
"step": 367
},
{
"epoch": 0.74,
"learning_rate": 1.3475640636613446e-05,
"loss": 1.1775,
"step": 368
},
{
"epoch": 0.74,
"learning_rate": 1.330175464348567e-05,
"loss": 1.3356,
"step": 369
},
{
"epoch": 0.74,
"learning_rate": 1.312859025323514e-05,
"loss": 1.4126,
"step": 370
},
{
"epoch": 0.74,
"learning_rate": 1.2956158147457115e-05,
"loss": 1.4473,
"step": 371
},
{
"epoch": 0.74,
"learning_rate": 1.2784468962576136e-05,
"loss": 1.1903,
"step": 372
},
{
"epoch": 0.75,
"learning_rate": 1.261353328918981e-05,
"loss": 1.357,
"step": 373
},
{
"epoch": 0.75,
"learning_rate": 1.2443361671415687e-05,
"loss": 1.1659,
"step": 374
},
{
"epoch": 0.75,
"learning_rate": 1.2273964606240718e-05,
"loss": 1.3215,
"step": 375
},
{
"epoch": 0.75,
"learning_rate": 1.2105352542873815e-05,
"loss": 1.3099,
"step": 376
},
{
"epoch": 0.75,
"learning_rate": 1.1937535882101281e-05,
"loss": 1.2418,
"step": 377
},
{
"epoch": 0.76,
"learning_rate": 1.1770524975645238e-05,
"loss": 1.4179,
"step": 378
},
{
"epoch": 0.76,
"learning_rate": 1.1604330125525079e-05,
"loss": 1.1883,
"step": 379
},
{
"epoch": 0.76,
"learning_rate": 1.1438961583422037e-05,
"loss": 1.0938,
"step": 380
},
{
"epoch": 0.76,
"learning_rate": 1.1274429550046704e-05,
"loss": 1.2686,
"step": 381
},
{
"epoch": 0.76,
"learning_rate": 1.1110744174509952e-05,
"loss": 1.2447,
"step": 382
},
{
"epoch": 0.77,
"learning_rate": 1.0947915553696742e-05,
"loss": 1.3854,
"step": 383
},
{
"epoch": 0.77,
"learning_rate": 1.07859537316434e-05,
"loss": 1.126,
"step": 384
},
{
"epoch": 0.77,
"learning_rate": 1.0624868698918045e-05,
"loss": 1.3622,
"step": 385
},
{
"epoch": 0.77,
"learning_rate": 1.0464670392004235e-05,
"loss": 1.4624,
"step": 386
},
{
"epoch": 0.77,
"learning_rate": 1.0305368692688174e-05,
"loss": 1.3589,
"step": 387
},
{
"epoch": 0.78,
"learning_rate": 1.0146973427449038e-05,
"loss": 1.3111,
"step": 388
},
{
"epoch": 0.78,
"learning_rate": 9.989494366852904e-06,
"loss": 1.3436,
"step": 389
},
{
"epoch": 0.78,
"learning_rate": 9.832941224950012e-06,
"loss": 1.4172,
"step": 390
},
{
"epoch": 0.78,
"learning_rate": 9.677323658675594e-06,
"loss": 1.587,
"step": 391
},
{
"epoch": 0.78,
"learning_rate": 9.522651267254149e-06,
"loss": 1.3277,
"step": 392
},
{
"epoch": 0.79,
"learning_rate": 9.368933591607378e-06,
"loss": 1.3433,
"step": 393
},
{
"epoch": 0.79,
"learning_rate": 9.216180113765558e-06,
"loss": 1.3489,
"step": 394
},
{
"epoch": 0.79,
"learning_rate": 9.064400256282757e-06,
"loss": 1.4577,
"step": 395
},
{
"epoch": 0.79,
"learning_rate": 8.913603381655528e-06,
"loss": 1.214,
"step": 396
},
{
"epoch": 0.79,
"learning_rate": 8.763798791745411e-06,
"loss": 1.5018,
"step": 397
},
{
"epoch": 0.8,
"learning_rate": 8.614995727205156e-06,
"loss": 1.2649,
"step": 398
},
{
"epoch": 0.8,
"learning_rate": 8.467203366908707e-06,
"loss": 1.3475,
"step": 399
},
{
"epoch": 0.8,
"learning_rate": 8.320430827385003e-06,
"loss": 1.4731,
"step": 400
},
{
"epoch": 0.8,
"eval_loss": 1.2786192893981934,
"eval_runtime": 4649.2009,
"eval_samples_per_second": 24.61,
"eval_steps_per_second": 12.305,
"step": 400
},
{
"epoch": 0.8,
"learning_rate": 8.174687162255672e-06,
"loss": 1.3442,
"step": 401
},
{
"epoch": 0.8,
"learning_rate": 8.029981361676456e-06,
"loss": 1.3979,
"step": 402
},
{
"epoch": 0.81,
"learning_rate": 7.886322351782783e-06,
"loss": 1.3131,
"step": 403
},
{
"epoch": 0.81,
"learning_rate": 7.743718994139071e-06,
"loss": 1.4709,
"step": 404
},
{
"epoch": 0.81,
"learning_rate": 7.602180085192143e-06,
"loss": 1.4698,
"step": 405
},
{
"epoch": 0.81,
"learning_rate": 7.461714355728608e-06,
"loss": 1.4866,
"step": 406
},
{
"epoch": 0.81,
"learning_rate": 7.3223304703363135e-06,
"loss": 1.3777,
"step": 407
},
{
"epoch": 0.82,
"learning_rate": 7.184037026869867e-06,
"loss": 1.4086,
"step": 408
},
{
"epoch": 0.82,
"learning_rate": 7.046842555920283e-06,
"loss": 1.2764,
"step": 409
},
{
"epoch": 0.82,
"learning_rate": 6.91075552028877e-06,
"loss": 1.3425,
"step": 410
},
{
"epoch": 0.82,
"learning_rate": 6.775784314464717e-06,
"loss": 1.2727,
"step": 411
},
{
"epoch": 0.82,
"learning_rate": 6.641937264107867e-06,
"loss": 1.3265,
"step": 412
},
{
"epoch": 0.83,
"learning_rate": 6.509222625534755e-06,
"loss": 1.5573,
"step": 413
},
{
"epoch": 0.83,
"learning_rate": 6.377648585209456e-06,
"loss": 1.2084,
"step": 414
},
{
"epoch": 0.83,
"learning_rate": 6.247223259238511e-06,
"loss": 1.3,
"step": 415
},
{
"epoch": 0.83,
"learning_rate": 6.117954692870412e-06,
"loss": 1.2939,
"step": 416
},
{
"epoch": 0.83,
"learning_rate": 5.989850859999227e-06,
"loss": 1.3688,
"step": 417
},
{
"epoch": 0.84,
"learning_rate": 5.8629196626728e-06,
"loss": 1.3784,
"step": 418
},
{
"epoch": 0.84,
"learning_rate": 5.737168930605272e-06,
"loss": 1.4403,
"step": 419
},
{
"epoch": 0.84,
"learning_rate": 5.612606420694141e-06,
"loss": 1.3014,
"step": 420
},
{
"epoch": 0.84,
"learning_rate": 5.489239816541755e-06,
"loss": 1.3343,
"step": 421
},
{
"epoch": 0.84,
"learning_rate": 5.367076727981382e-06,
"loss": 1.4141,
"step": 422
},
{
"epoch": 0.85,
"learning_rate": 5.24612469060774e-06,
"loss": 1.4151,
"step": 423
},
{
"epoch": 0.85,
"learning_rate": 5.12639116531225e-06,
"loss": 1.2296,
"step": 424
},
{
"epoch": 0.85,
"learning_rate": 5.007883537822736e-06,
"loss": 1.4797,
"step": 425
},
{
"epoch": 0.85,
"learning_rate": 4.890609118247888e-06,
"loss": 1.299,
"step": 426
},
{
"epoch": 0.85,
"learning_rate": 4.7745751406263165e-06,
"loss": 1.2994,
"step": 427
},
{
"epoch": 0.86,
"learning_rate": 4.659788762480327e-06,
"loss": 1.4391,
"step": 428
},
{
"epoch": 0.86,
"learning_rate": 4.54625706437441e-06,
"loss": 1.2876,
"step": 429
},
{
"epoch": 0.86,
"learning_rate": 4.433987049478508e-06,
"loss": 1.2708,
"step": 430
},
{
"epoch": 0.86,
"learning_rate": 4.322985643135952e-06,
"loss": 1.463,
"step": 431
},
{
"epoch": 0.86,
"learning_rate": 4.213259692436367e-06,
"loss": 1.2678,
"step": 432
},
{
"epoch": 0.87,
"learning_rate": 4.104815965793249e-06,
"loss": 1.2462,
"step": 433
},
{
"epoch": 0.87,
"learning_rate": 3.9976611525264525e-06,
"loss": 1.266,
"step": 434
},
{
"epoch": 0.87,
"learning_rate": 3.891801862449629e-06,
"loss": 1.3158,
"step": 435
},
{
"epoch": 0.87,
"learning_rate": 3.7872446254624104e-06,
"loss": 1.1578,
"step": 436
},
{
"epoch": 0.87,
"learning_rate": 3.6839958911476957e-06,
"loss": 1.0904,
"step": 437
},
{
"epoch": 0.88,
"learning_rate": 3.5820620283737616e-06,
"loss": 1.3362,
"step": 438
},
{
"epoch": 0.88,
"learning_rate": 3.4814493249014116e-06,
"loss": 1.2818,
"step": 439
},
{
"epoch": 0.88,
"learning_rate": 3.382163986996126e-06,
"loss": 1.326,
"step": 440
},
{
"epoch": 0.88,
"learning_rate": 3.284212139045223e-06,
"loss": 1.3425,
"step": 441
},
{
"epoch": 0.88,
"learning_rate": 3.187599823180071e-06,
"loss": 1.5054,
"step": 442
},
{
"epoch": 0.89,
"learning_rate": 3.092332998903416e-06,
"loss": 1.2616,
"step": 443
},
{
"epoch": 0.89,
"learning_rate": 2.9984175427217016e-06,
"loss": 1.394,
"step": 444
},
{
"epoch": 0.89,
"learning_rate": 2.9058592477826636e-06,
"loss": 1.4627,
"step": 445
},
{
"epoch": 0.89,
"learning_rate": 2.8146638235179213e-06,
"loss": 1.218,
"step": 446
},
{
"epoch": 0.89,
"learning_rate": 2.7248368952908053e-06,
"loss": 1.5982,
"step": 447
},
{
"epoch": 0.9,
"learning_rate": 2.6363840040493747e-06,
"loss": 1.2318,
"step": 448
},
{
"epoch": 0.9,
"learning_rate": 2.5493106059846116e-06,
"loss": 1.5119,
"step": 449
},
{
"epoch": 0.9,
"learning_rate": 2.4636220721938554e-06,
"loss": 1.4656,
"step": 450
},
{
"epoch": 0.9,
"learning_rate": 2.379323688349516e-06,
"loss": 1.4699,
"step": 451
},
{
"epoch": 0.9,
"learning_rate": 2.296420654372966e-06,
"loss": 1.3212,
"step": 452
},
{
"epoch": 0.91,
"learning_rate": 2.2149180841138676e-06,
"loss": 1.4466,
"step": 453
},
{
"epoch": 0.91,
"learning_rate": 2.1348210050346595e-06,
"loss": 1.3307,
"step": 454
},
{
"epoch": 0.91,
"learning_rate": 2.0561343579004715e-06,
"loss": 1.2307,
"step": 455
},
{
"epoch": 0.91,
"learning_rate": 1.9788629964743455e-06,
"loss": 1.3392,
"step": 456
},
{
"epoch": 0.91,
"learning_rate": 1.9030116872178316e-06,
"loss": 1.3646,
"step": 457
},
{
"epoch": 0.92,
"learning_rate": 1.8285851089969802e-06,
"loss": 1.4209,
"step": 458
},
{
"epoch": 0.92,
"learning_rate": 1.7555878527937164e-06,
"loss": 1.5344,
"step": 459
},
{
"epoch": 0.92,
"learning_rate": 1.6840244214226502e-06,
"loss": 1.3534,
"step": 460
},
{
"epoch": 0.92,
"learning_rate": 1.6138992292533183e-06,
"loss": 1.1762,
"step": 461
},
{
"epoch": 0.92,
"learning_rate": 1.5452166019378989e-06,
"loss": 1.6005,
"step": 462
},
{
"epoch": 0.93,
"learning_rate": 1.4779807761443636e-06,
"loss": 1.4277,
"step": 463
},
{
"epoch": 0.93,
"learning_rate": 1.4121958992951629e-06,
"loss": 1.5691,
"step": 464
},
{
"epoch": 0.93,
"learning_rate": 1.3478660293113676e-06,
"loss": 1.3057,
"step": 465
},
{
"epoch": 0.93,
"learning_rate": 1.284995134362385e-06,
"loss": 1.4196,
"step": 466
},
{
"epoch": 0.93,
"learning_rate": 1.2235870926211619e-06,
"loss": 1.3259,
"step": 467
},
{
"epoch": 0.94,
"learning_rate": 1.16364569202497e-06,
"loss": 1.4289,
"step": 468
},
{
"epoch": 0.94,
"learning_rate": 1.105174630041747e-06,
"loss": 1.4029,
"step": 469
},
{
"epoch": 0.94,
"learning_rate": 1.0481775134420225e-06,
"loss": 1.3532,
"step": 470
},
{
"epoch": 0.94,
"learning_rate": 9.926578580764234e-07,
"loss": 1.3901,
"step": 471
},
{
"epoch": 0.94,
"learning_rate": 9.386190886588208e-07,
"loss": 1.3493,
"step": 472
},
{
"epoch": 0.95,
"learning_rate": 8.860645385550481e-07,
"loss": 1.4783,
"step": 473
},
{
"epoch": 0.95,
"learning_rate": 8.349974495773183e-07,
"loss": 1.406,
"step": 474
},
{
"epoch": 0.95,
"learning_rate": 7.854209717842231e-07,
"loss": 1.1884,
"step": 475
},
{
"epoch": 0.95,
"learning_rate": 7.373381632864384e-07,
"loss": 1.4137,
"step": 476
},
{
"epoch": 0.95,
"learning_rate": 6.907519900580861e-07,
"loss": 1.4141,
"step": 477
},
{
"epoch": 0.96,
"learning_rate": 6.456653257537665e-07,
"loss": 1.4732,
"step": 478
},
{
"epoch": 0.96,
"learning_rate": 6.020809515313142e-07,
"loss": 1.6633,
"step": 479
},
{
"epoch": 0.96,
"learning_rate": 5.600015558802352e-07,
"loss": 1.2823,
"step": 480
},
{
"epoch": 0.96,
"learning_rate": 5.194297344558536e-07,
"loss": 1.2236,
"step": 481
},
{
"epoch": 0.96,
"learning_rate": 4.803679899192392e-07,
"loss": 1.5525,
"step": 482
},
{
"epoch": 0.97,
"learning_rate": 4.4281873178278475e-07,
"loss": 1.4783,
"step": 483
},
{
"epoch": 0.97,
"learning_rate": 4.067842762616014e-07,
"loss": 1.359,
"step": 484
},
{
"epoch": 0.97,
"learning_rate": 3.7226684613065333e-07,
"loss": 1.5369,
"step": 485
},
{
"epoch": 0.97,
"learning_rate": 3.3926857058761417e-07,
"loss": 1.2518,
"step": 486
},
{
"epoch": 0.97,
"learning_rate": 3.077914851215585e-07,
"loss": 1.3272,
"step": 487
},
{
"epoch": 0.98,
"learning_rate": 2.778375313873871e-07,
"loss": 1.3623,
"step": 488
},
{
"epoch": 0.98,
"learning_rate": 2.494085570860616e-07,
"loss": 1.5239,
"step": 489
},
{
"epoch": 0.98,
"learning_rate": 2.2250631585063186e-07,
"loss": 1.3619,
"step": 490
},
{
"epoch": 0.98,
"learning_rate": 1.9713246713805588e-07,
"loss": 1.1757,
"step": 491
},
{
"epoch": 0.98,
"learning_rate": 1.732885761268427e-07,
"loss": 1.193,
"step": 492
},
{
"epoch": 0.99,
"learning_rate": 1.509761136205101e-07,
"loss": 1.469,
"step": 493
},
{
"epoch": 0.99,
"learning_rate": 1.3019645595683806e-07,
"loss": 1.2552,
"step": 494
},
{
"epoch": 0.99,
"learning_rate": 1.109508849230001e-07,
"loss": 1.3539,
"step": 495
},
{
"epoch": 0.99,
"learning_rate": 9.324058767646859e-08,
"loss": 1.2407,
"step": 496
},
{
"epoch": 0.99,
"learning_rate": 7.706665667180091e-08,
"loss": 1.1192,
"step": 497
},
{
"epoch": 1.0,
"learning_rate": 6.243008959324892e-08,
"loss": 1.2434,
"step": 498
},
{
"epoch": 1.0,
"learning_rate": 4.9331789293211026e-08,
"loss": 1.4577,
"step": 499
},
{
"epoch": 1.0,
"learning_rate": 3.7772563736551694e-08,
"loss": 1.4546,
"step": 500
},
{
"epoch": 1.0,
"eval_loss": 1.2736687660217285,
"eval_runtime": 4627.6472,
"eval_samples_per_second": 24.725,
"eval_steps_per_second": 12.362,
"step": 500
}
],
"max_steps": 500,
"num_train_epochs": 9223372036854775807,
"total_flos": 1.4859211112448e+16,
"trial_name": null,
"trial_params": null
}