AnLLM-AC-7B-translation / trainer_state.json
pangjh3's picture
info
3b71912
raw
history blame contribute delete
No virus
45.5 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9880478087649402,
"global_step": 375,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 1.6666666666666667e-06,
"loss": 1.5044,
"step": 1
},
{
"epoch": 0.02,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.4514,
"step": 2
},
{
"epoch": 0.02,
"learning_rate": 5e-06,
"loss": 1.4498,
"step": 3
},
{
"epoch": 0.03,
"learning_rate": 6.666666666666667e-06,
"loss": 1.4186,
"step": 4
},
{
"epoch": 0.04,
"learning_rate": 8.333333333333334e-06,
"loss": 1.3586,
"step": 5
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 1.2792,
"step": 6
},
{
"epoch": 0.06,
"learning_rate": 1.1666666666666668e-05,
"loss": 1.2723,
"step": 7
},
{
"epoch": 0.06,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.2244,
"step": 8
},
{
"epoch": 0.07,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.1807,
"step": 9
},
{
"epoch": 0.08,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.1877,
"step": 10
},
{
"epoch": 0.09,
"learning_rate": 1.8333333333333333e-05,
"loss": 1.163,
"step": 11
},
{
"epoch": 0.1,
"learning_rate": 2e-05,
"loss": 1.1489,
"step": 12
},
{
"epoch": 0.1,
"learning_rate": 1.9999625498303936e-05,
"loss": 1.1348,
"step": 13
},
{
"epoch": 0.11,
"learning_rate": 1.999850202126604e-05,
"loss": 1.1368,
"step": 14
},
{
"epoch": 0.12,
"learning_rate": 1.9996629653035128e-05,
"loss": 1.1382,
"step": 15
},
{
"epoch": 0.13,
"learning_rate": 1.999400853385221e-05,
"loss": 1.1297,
"step": 16
},
{
"epoch": 0.14,
"learning_rate": 1.9990638860040007e-05,
"loss": 1.1365,
"step": 17
},
{
"epoch": 0.14,
"learning_rate": 1.9986520883988233e-05,
"loss": 1.1292,
"step": 18
},
{
"epoch": 0.15,
"learning_rate": 1.9981654914134684e-05,
"loss": 1.1278,
"step": 19
},
{
"epoch": 0.16,
"learning_rate": 1.9976041314942156e-05,
"loss": 1.106,
"step": 20
},
{
"epoch": 0.17,
"learning_rate": 1.9969680506871138e-05,
"loss": 1.1053,
"step": 21
},
{
"epoch": 0.18,
"learning_rate": 1.99625729663483e-05,
"loss": 1.11,
"step": 22
},
{
"epoch": 0.18,
"learning_rate": 1.9954719225730847e-05,
"loss": 1.1139,
"step": 23
},
{
"epoch": 0.19,
"learning_rate": 1.9946119873266615e-05,
"loss": 1.1226,
"step": 24
},
{
"epoch": 0.2,
"learning_rate": 1.9936775553050017e-05,
"loss": 1.046,
"step": 25
},
{
"epoch": 0.21,
"learning_rate": 1.9926686964973813e-05,
"loss": 1.1061,
"step": 26
},
{
"epoch": 0.22,
"learning_rate": 1.9915854864676665e-05,
"loss": 1.0507,
"step": 27
},
{
"epoch": 0.22,
"learning_rate": 1.9904280063486563e-05,
"loss": 1.0609,
"step": 28
},
{
"epoch": 0.23,
"learning_rate": 1.9891963428360043e-05,
"loss": 1.0782,
"step": 29
},
{
"epoch": 0.24,
"learning_rate": 1.9878905881817254e-05,
"loss": 1.1025,
"step": 30
},
{
"epoch": 0.25,
"learning_rate": 1.9865108401872856e-05,
"loss": 1.0876,
"step": 31
},
{
"epoch": 0.25,
"learning_rate": 1.9850572021962788e-05,
"loss": 1.1006,
"step": 32
},
{
"epoch": 0.26,
"learning_rate": 1.9835297830866827e-05,
"loss": 1.0444,
"step": 33
},
{
"epoch": 0.27,
"learning_rate": 1.9819286972627066e-05,
"loss": 1.0563,
"step": 34
},
{
"epoch": 0.28,
"learning_rate": 1.980254064646223e-05,
"loss": 1.0656,
"step": 35
},
{
"epoch": 0.29,
"learning_rate": 1.9785060106677818e-05,
"loss": 1.0823,
"step": 36
},
{
"epoch": 0.29,
"learning_rate": 1.976684666257219e-05,
"loss": 1.0634,
"step": 37
},
{
"epoch": 0.3,
"learning_rate": 1.9747901678338496e-05,
"loss": 1.0581,
"step": 38
},
{
"epoch": 0.31,
"learning_rate": 1.9728226572962474e-05,
"loss": 1.0588,
"step": 39
},
{
"epoch": 0.32,
"learning_rate": 1.9707822820116193e-05,
"loss": 1.0704,
"step": 40
},
{
"epoch": 0.33,
"learning_rate": 1.9686691948047665e-05,
"loss": 1.0822,
"step": 41
},
{
"epoch": 0.33,
"learning_rate": 1.966483553946637e-05,
"loss": 1.0621,
"step": 42
},
{
"epoch": 0.34,
"learning_rate": 1.964225523142473e-05,
"loss": 1.0648,
"step": 43
},
{
"epoch": 0.35,
"learning_rate": 1.9618952715195476e-05,
"loss": 1.0837,
"step": 44
},
{
"epoch": 0.36,
"learning_rate": 1.9594929736144978e-05,
"loss": 1.0543,
"step": 45
},
{
"epoch": 0.37,
"learning_rate": 1.9570188093602512e-05,
"loss": 1.0535,
"step": 46
},
{
"epoch": 0.37,
"learning_rate": 1.95447296407255e-05,
"loss": 1.0533,
"step": 47
},
{
"epoch": 0.38,
"learning_rate": 1.9518556284360696e-05,
"loss": 1.0191,
"step": 48
},
{
"epoch": 0.39,
"learning_rate": 1.9491669984901377e-05,
"loss": 1.0395,
"step": 49
},
{
"epoch": 0.4,
"learning_rate": 1.9464072756140487e-05,
"loss": 1.0173,
"step": 50
},
{
"epoch": 0.41,
"learning_rate": 1.9435766665119823e-05,
"loss": 1.048,
"step": 51
},
{
"epoch": 0.41,
"learning_rate": 1.9406753831975202e-05,
"loss": 1.0496,
"step": 52
},
{
"epoch": 0.42,
"learning_rate": 1.9377036429777673e-05,
"loss": 1.0616,
"step": 53
},
{
"epoch": 0.43,
"learning_rate": 1.934661668437073e-05,
"loss": 1.0504,
"step": 54
},
{
"epoch": 0.44,
"learning_rate": 1.9315496874203637e-05,
"loss": 1.0399,
"step": 55
},
{
"epoch": 0.45,
"learning_rate": 1.9283679330160726e-05,
"loss": 1.0416,
"step": 56
},
{
"epoch": 0.45,
"learning_rate": 1.9251166435386837e-05,
"loss": 1.0175,
"step": 57
},
{
"epoch": 0.46,
"learning_rate": 1.921796062510882e-05,
"loss": 1.0285,
"step": 58
},
{
"epoch": 0.47,
"learning_rate": 1.9184064386453127e-05,
"loss": 1.0312,
"step": 59
},
{
"epoch": 0.48,
"learning_rate": 1.9149480258259535e-05,
"loss": 1.0463,
"step": 60
},
{
"epoch": 0.49,
"learning_rate": 1.911421083089097e-05,
"loss": 1.0521,
"step": 61
},
{
"epoch": 0.49,
"learning_rate": 1.907825874603951e-05,
"loss": 1.0276,
"step": 62
},
{
"epoch": 0.5,
"learning_rate": 1.9041626696528503e-05,
"loss": 1.0256,
"step": 63
},
{
"epoch": 0.51,
"learning_rate": 1.9004317426110888e-05,
"loss": 1.0403,
"step": 64
},
{
"epoch": 0.52,
"learning_rate": 1.8966333729263674e-05,
"loss": 1.0687,
"step": 65
},
{
"epoch": 0.53,
"learning_rate": 1.892767845097864e-05,
"loss": 1.0394,
"step": 66
},
{
"epoch": 0.53,
"learning_rate": 1.8888354486549238e-05,
"loss": 0.9965,
"step": 67
},
{
"epoch": 0.54,
"learning_rate": 1.8848364781353744e-05,
"loss": 1.0397,
"step": 68
},
{
"epoch": 0.55,
"learning_rate": 1.8807712330634645e-05,
"loss": 1.027,
"step": 69
},
{
"epoch": 0.56,
"learning_rate": 1.8766400179274287e-05,
"loss": 1.0201,
"step": 70
},
{
"epoch": 0.57,
"learning_rate": 1.8724431421566822e-05,
"loss": 1.0081,
"step": 71
},
{
"epoch": 0.57,
"learning_rate": 1.868180920098644e-05,
"loss": 0.9956,
"step": 72
},
{
"epoch": 0.58,
"learning_rate": 1.8638536709951916e-05,
"loss": 1.0127,
"step": 73
},
{
"epoch": 0.59,
"learning_rate": 1.8594617189587515e-05,
"loss": 0.9887,
"step": 74
},
{
"epoch": 0.6,
"learning_rate": 1.8550053929480202e-05,
"loss": 1.0266,
"step": 75
},
{
"epoch": 0.61,
"learning_rate": 1.8504850267433278e-05,
"loss": 1.0102,
"step": 76
},
{
"epoch": 0.61,
"learning_rate": 1.8459009589216364e-05,
"loss": 0.9728,
"step": 77
},
{
"epoch": 0.62,
"learning_rate": 1.8412535328311813e-05,
"loss": 0.9944,
"step": 78
},
{
"epoch": 0.63,
"learning_rate": 1.8365430965657527e-05,
"loss": 1.0591,
"step": 79
},
{
"epoch": 0.64,
"learning_rate": 1.8317700029386245e-05,
"loss": 1.0032,
"step": 80
},
{
"epoch": 0.65,
"learning_rate": 1.826934609456129e-05,
"loss": 1.0094,
"step": 81
},
{
"epoch": 0.65,
"learning_rate": 1.8220372782908778e-05,
"loss": 1.0118,
"step": 82
},
{
"epoch": 0.66,
"learning_rate": 1.8170783762546363e-05,
"loss": 1.0254,
"step": 83
},
{
"epoch": 0.67,
"learning_rate": 1.8120582747708503e-05,
"loss": 1.0108,
"step": 84
},
{
"epoch": 0.68,
"learning_rate": 1.8069773498468224e-05,
"loss": 0.9887,
"step": 85
},
{
"epoch": 0.69,
"learning_rate": 1.8018359820455535e-05,
"loss": 1.0241,
"step": 86
},
{
"epoch": 0.69,
"learning_rate": 1.796634556457236e-05,
"loss": 1.0179,
"step": 87
},
{
"epoch": 0.7,
"learning_rate": 1.791373462670411e-05,
"loss": 1.0357,
"step": 88
},
{
"epoch": 0.71,
"learning_rate": 1.7860530947427878e-05,
"loss": 0.9963,
"step": 89
},
{
"epoch": 0.72,
"learning_rate": 1.780673851171728e-05,
"loss": 1.0084,
"step": 90
},
{
"epoch": 0.73,
"learning_rate": 1.7752361348644012e-05,
"loss": 1.0178,
"step": 91
},
{
"epoch": 0.73,
"learning_rate": 1.769740353107602e-05,
"loss": 0.9936,
"step": 92
},
{
"epoch": 0.74,
"learning_rate": 1.7641869175372493e-05,
"loss": 0.9838,
"step": 93
},
{
"epoch": 0.75,
"learning_rate": 1.7585762441075504e-05,
"loss": 1.0163,
"step": 94
},
{
"epoch": 0.76,
"learning_rate": 1.752908753059849e-05,
"loss": 0.9954,
"step": 95
},
{
"epoch": 0.76,
"learning_rate": 1.7471848688911465e-05,
"loss": 1.0138,
"step": 96
},
{
"epoch": 0.77,
"learning_rate": 1.7414050203223092e-05,
"loss": 0.997,
"step": 97
},
{
"epoch": 0.78,
"learning_rate": 1.735569640265955e-05,
"loss": 1.011,
"step": 98
},
{
"epoch": 0.79,
"learning_rate": 1.72967916579403e-05,
"loss": 0.9625,
"step": 99
},
{
"epoch": 0.8,
"learning_rate": 1.72373403810507e-05,
"loss": 1.0054,
"step": 100
},
{
"epoch": 0.8,
"learning_rate": 1.7177347024911562e-05,
"loss": 1.0169,
"step": 101
},
{
"epoch": 0.81,
"learning_rate": 1.7116816083045603e-05,
"loss": 0.9911,
"step": 102
},
{
"epoch": 0.82,
"learning_rate": 1.7055752089240907e-05,
"loss": 1.0246,
"step": 103
},
{
"epoch": 0.83,
"learning_rate": 1.6994159617211318e-05,
"loss": 1.0024,
"step": 104
},
{
"epoch": 0.84,
"learning_rate": 1.6932043280253892e-05,
"loss": 0.9886,
"step": 105
},
{
"epoch": 0.84,
"learning_rate": 1.686940773090333e-05,
"loss": 0.9775,
"step": 106
},
{
"epoch": 0.85,
"learning_rate": 1.6806257660583534e-05,
"loss": 0.9755,
"step": 107
},
{
"epoch": 0.86,
"learning_rate": 1.6742597799256182e-05,
"loss": 1.0068,
"step": 108
},
{
"epoch": 0.87,
"learning_rate": 1.6678432915066488e-05,
"loss": 0.978,
"step": 109
},
{
"epoch": 0.88,
"learning_rate": 1.6613767813986045e-05,
"loss": 1.002,
"step": 110
},
{
"epoch": 0.88,
"learning_rate": 1.6548607339452853e-05,
"loss": 0.9859,
"step": 111
},
{
"epoch": 0.89,
"learning_rate": 1.648295637200856e-05,
"loss": 0.9753,
"step": 112
},
{
"epoch": 0.9,
"learning_rate": 1.64168198289329e-05,
"loss": 0.9771,
"step": 113
},
{
"epoch": 0.91,
"learning_rate": 1.6350202663875385e-05,
"loss": 0.9843,
"step": 114
},
{
"epoch": 0.92,
"learning_rate": 1.628310986648427e-05,
"loss": 0.9507,
"step": 115
},
{
"epoch": 0.92,
"learning_rate": 1.621554646203284e-05,
"loss": 0.9875,
"step": 116
},
{
"epoch": 0.93,
"learning_rate": 1.614751751104301e-05,
"loss": 0.9724,
"step": 117
},
{
"epoch": 0.94,
"learning_rate": 1.607902810890628e-05,
"loss": 0.9572,
"step": 118
},
{
"epoch": 0.95,
"learning_rate": 1.601008338550211e-05,
"loss": 0.9905,
"step": 119
},
{
"epoch": 0.96,
"learning_rate": 1.5940688504813664e-05,
"loss": 0.9758,
"step": 120
},
{
"epoch": 0.96,
"learning_rate": 1.5870848664541046e-05,
"loss": 0.9927,
"step": 121
},
{
"epoch": 0.97,
"learning_rate": 1.5800569095711983e-05,
"loss": 0.9696,
"step": 122
},
{
"epoch": 0.98,
"learning_rate": 1.5729855062290024e-05,
"loss": 0.9775,
"step": 123
},
{
"epoch": 0.99,
"learning_rate": 1.565871186078025e-05,
"loss": 0.9904,
"step": 124
},
{
"epoch": 1.0,
"learning_rate": 1.55871448198326e-05,
"loss": 0.9796,
"step": 125
},
{
"epoch": 1.0,
"learning_rate": 1.551515929984271e-05,
"loss": 0.8877,
"step": 126
},
{
"epoch": 1.01,
"learning_rate": 1.5442760692550443e-05,
"loss": 0.7575,
"step": 127
},
{
"epoch": 1.02,
"learning_rate": 1.5369954420636048e-05,
"loss": 0.7759,
"step": 128
},
{
"epoch": 1.03,
"learning_rate": 1.529674593731399e-05,
"loss": 0.7747,
"step": 129
},
{
"epoch": 1.04,
"learning_rate": 1.5223140725924494e-05,
"loss": 0.7596,
"step": 130
},
{
"epoch": 1.04,
"learning_rate": 1.5149144299522874e-05,
"loss": 0.7461,
"step": 131
},
{
"epoch": 1.05,
"learning_rate": 1.5074762200466557e-05,
"loss": 0.7336,
"step": 132
},
{
"epoch": 1.06,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.7054,
"step": 133
},
{
"epoch": 1.07,
"learning_rate": 1.4924863297837378e-05,
"loss": 0.7358,
"step": 134
},
{
"epoch": 1.08,
"learning_rate": 1.4849357721743169e-05,
"loss": 0.7282,
"step": 135
},
{
"epoch": 1.08,
"learning_rate": 1.4773488927110633e-05,
"loss": 0.7195,
"step": 136
},
{
"epoch": 1.09,
"learning_rate": 1.4697262596538227e-05,
"loss": 0.7279,
"step": 137
},
{
"epoch": 1.1,
"learning_rate": 1.4620684439403962e-05,
"loss": 0.7313,
"step": 138
},
{
"epoch": 1.11,
"learning_rate": 1.454376019143779e-05,
"loss": 0.7415,
"step": 139
},
{
"epoch": 1.12,
"learning_rate": 1.4466495614291977e-05,
"loss": 0.7305,
"step": 140
},
{
"epoch": 1.12,
"learning_rate": 1.438889649510956e-05,
"loss": 0.7545,
"step": 141
},
{
"epoch": 1.13,
"learning_rate": 1.4310968646090884e-05,
"loss": 0.7307,
"step": 142
},
{
"epoch": 1.14,
"learning_rate": 1.423271790405828e-05,
"loss": 0.7327,
"step": 143
},
{
"epoch": 1.15,
"learning_rate": 1.4154150130018867e-05,
"loss": 0.7417,
"step": 144
},
{
"epoch": 1.16,
"learning_rate": 1.4075271208725572e-05,
"loss": 0.7491,
"step": 145
},
{
"epoch": 1.16,
"learning_rate": 1.3996087048236357e-05,
"loss": 0.7422,
"step": 146
},
{
"epoch": 1.17,
"learning_rate": 1.3916603579471705e-05,
"loss": 0.7551,
"step": 147
},
{
"epoch": 1.18,
"learning_rate": 1.3836826755770386e-05,
"loss": 0.7356,
"step": 148
},
{
"epoch": 1.19,
"learning_rate": 1.3756762552443555e-05,
"loss": 0.7139,
"step": 149
},
{
"epoch": 1.2,
"learning_rate": 1.3676416966327201e-05,
"loss": 0.7411,
"step": 150
},
{
"epoch": 1.2,
"learning_rate": 1.3595796015332986e-05,
"loss": 0.7511,
"step": 151
},
{
"epoch": 1.21,
"learning_rate": 1.3514905737997474e-05,
"loss": 0.747,
"step": 152
},
{
"epoch": 1.22,
"learning_rate": 1.3433752193029888e-05,
"loss": 0.7302,
"step": 153
},
{
"epoch": 1.23,
"learning_rate": 1.3352341458858264e-05,
"loss": 0.7489,
"step": 154
},
{
"epoch": 1.24,
"learning_rate": 1.3270679633174219e-05,
"loss": 0.7534,
"step": 155
},
{
"epoch": 1.24,
"learning_rate": 1.318877283247619e-05,
"loss": 0.7423,
"step": 156
},
{
"epoch": 1.25,
"learning_rate": 1.3106627191611333e-05,
"loss": 0.7141,
"step": 157
},
{
"epoch": 1.26,
"learning_rate": 1.3024248863316012e-05,
"loss": 0.7443,
"step": 158
},
{
"epoch": 1.27,
"learning_rate": 1.2941644017754964e-05,
"loss": 0.7383,
"step": 159
},
{
"epoch": 1.27,
"learning_rate": 1.2858818842059145e-05,
"loss": 0.7444,
"step": 160
},
{
"epoch": 1.28,
"learning_rate": 1.2775779539862305e-05,
"loss": 0.7489,
"step": 161
},
{
"epoch": 1.29,
"learning_rate": 1.2692532330836346e-05,
"loss": 0.7266,
"step": 162
},
{
"epoch": 1.3,
"learning_rate": 1.2609083450225468e-05,
"loss": 0.7159,
"step": 163
},
{
"epoch": 1.31,
"learning_rate": 1.2525439148379127e-05,
"loss": 0.7362,
"step": 164
},
{
"epoch": 1.31,
"learning_rate": 1.2441605690283915e-05,
"loss": 0.7174,
"step": 165
},
{
"epoch": 1.32,
"learning_rate": 1.2357589355094275e-05,
"loss": 0.7137,
"step": 166
},
{
"epoch": 1.33,
"learning_rate": 1.2273396435662212e-05,
"loss": 0.723,
"step": 167
},
{
"epoch": 1.34,
"learning_rate": 1.218903323806595e-05,
"loss": 0.7185,
"step": 168
},
{
"epoch": 1.35,
"learning_rate": 1.2104506081137608e-05,
"loss": 0.7306,
"step": 169
},
{
"epoch": 1.35,
"learning_rate": 1.2019821295989913e-05,
"loss": 0.7213,
"step": 170
},
{
"epoch": 1.36,
"learning_rate": 1.1934985225541998e-05,
"loss": 0.7159,
"step": 171
},
{
"epoch": 1.37,
"learning_rate": 1.1850004224044315e-05,
"loss": 0.7298,
"step": 172
},
{
"epoch": 1.38,
"learning_rate": 1.1764884656602711e-05,
"loss": 0.7324,
"step": 173
},
{
"epoch": 1.39,
"learning_rate": 1.1679632898701649e-05,
"loss": 0.7354,
"step": 174
},
{
"epoch": 1.39,
"learning_rate": 1.1594255335726725e-05,
"loss": 0.7195,
"step": 175
},
{
"epoch": 1.4,
"learning_rate": 1.1508758362486358e-05,
"loss": 0.7212,
"step": 176
},
{
"epoch": 1.41,
"learning_rate": 1.1423148382732854e-05,
"loss": 0.7272,
"step": 177
},
{
"epoch": 1.42,
"learning_rate": 1.133743180868273e-05,
"loss": 0.7302,
"step": 178
},
{
"epoch": 1.43,
"learning_rate": 1.125161506053646e-05,
"loss": 0.7399,
"step": 179
},
{
"epoch": 1.43,
"learning_rate": 1.1165704565997593e-05,
"loss": 0.7059,
"step": 180
},
{
"epoch": 1.44,
"learning_rate": 1.1079706759791311e-05,
"loss": 0.733,
"step": 181
},
{
"epoch": 1.45,
"learning_rate": 1.0993628083182468e-05,
"loss": 0.7086,
"step": 182
},
{
"epoch": 1.46,
"learning_rate": 1.0907474983493144e-05,
"loss": 0.7396,
"step": 183
},
{
"epoch": 1.47,
"learning_rate": 1.0821253913619727e-05,
"loss": 0.7405,
"step": 184
},
{
"epoch": 1.47,
"learning_rate": 1.0734971331549604e-05,
"loss": 0.7121,
"step": 185
},
{
"epoch": 1.48,
"learning_rate": 1.064863369987743e-05,
"loss": 0.7149,
"step": 186
},
{
"epoch": 1.49,
"learning_rate": 1.0562247485321116e-05,
"loss": 0.7227,
"step": 187
},
{
"epoch": 1.5,
"learning_rate": 1.0475819158237426e-05,
"loss": 0.7337,
"step": 188
},
{
"epoch": 1.51,
"learning_rate": 1.0389355192137379e-05,
"loss": 0.7205,
"step": 189
},
{
"epoch": 1.51,
"learning_rate": 1.0302862063201367e-05,
"loss": 0.7189,
"step": 190
},
{
"epoch": 1.52,
"learning_rate": 1.0216346249794087e-05,
"loss": 0.7051,
"step": 191
},
{
"epoch": 1.53,
"learning_rate": 1.012981423197931e-05,
"loss": 0.718,
"step": 192
},
{
"epoch": 1.54,
"learning_rate": 1.0043272491034523e-05,
"loss": 0.7197,
"step": 193
},
{
"epoch": 1.55,
"learning_rate": 9.956727508965482e-06,
"loss": 0.7101,
"step": 194
},
{
"epoch": 1.55,
"learning_rate": 9.870185768020694e-06,
"loss": 0.7415,
"step": 195
},
{
"epoch": 1.56,
"learning_rate": 9.783653750205916e-06,
"loss": 0.7303,
"step": 196
},
{
"epoch": 1.57,
"learning_rate": 9.697137936798635e-06,
"loss": 0.6957,
"step": 197
},
{
"epoch": 1.58,
"learning_rate": 9.610644807862625e-06,
"loss": 0.699,
"step": 198
},
{
"epoch": 1.59,
"learning_rate": 9.524180841762577e-06,
"loss": 0.7184,
"step": 199
},
{
"epoch": 1.59,
"learning_rate": 9.437752514678888e-06,
"loss": 0.7473,
"step": 200
},
{
"epoch": 1.6,
"learning_rate": 9.351366300122569e-06,
"loss": 0.7197,
"step": 201
},
{
"epoch": 1.61,
"learning_rate": 9.265028668450403e-06,
"loss": 0.7005,
"step": 202
},
{
"epoch": 1.62,
"learning_rate": 9.178746086380274e-06,
"loss": 0.7279,
"step": 203
},
{
"epoch": 1.63,
"learning_rate": 9.092525016506858e-06,
"loss": 0.7326,
"step": 204
},
{
"epoch": 1.63,
"learning_rate": 9.006371916817533e-06,
"loss": 0.7041,
"step": 205
},
{
"epoch": 1.64,
"learning_rate": 8.920293240208694e-06,
"loss": 0.714,
"step": 206
},
{
"epoch": 1.65,
"learning_rate": 8.83429543400241e-06,
"loss": 0.7057,
"step": 207
},
{
"epoch": 1.66,
"learning_rate": 8.748384939463543e-06,
"loss": 0.7059,
"step": 208
},
{
"epoch": 1.67,
"learning_rate": 8.662568191317273e-06,
"loss": 0.7115,
"step": 209
},
{
"epoch": 1.67,
"learning_rate": 8.576851617267151e-06,
"loss": 0.707,
"step": 210
},
{
"epoch": 1.68,
"learning_rate": 8.491241637513644e-06,
"loss": 0.7443,
"step": 211
},
{
"epoch": 1.69,
"learning_rate": 8.405744664273278e-06,
"loss": 0.7306,
"step": 212
},
{
"epoch": 1.7,
"learning_rate": 8.320367101298351e-06,
"loss": 0.7078,
"step": 213
},
{
"epoch": 1.71,
"learning_rate": 8.235115343397295e-06,
"loss": 0.7113,
"step": 214
},
{
"epoch": 1.71,
"learning_rate": 8.149995775955686e-06,
"loss": 0.7032,
"step": 215
},
{
"epoch": 1.72,
"learning_rate": 8.065014774458004e-06,
"loss": 0.716,
"step": 216
},
{
"epoch": 1.73,
"learning_rate": 7.980178704010089e-06,
"loss": 0.7612,
"step": 217
},
{
"epoch": 1.74,
"learning_rate": 7.895493918862395e-06,
"loss": 0.6952,
"step": 218
},
{
"epoch": 1.75,
"learning_rate": 7.810966761934053e-06,
"loss": 0.7036,
"step": 219
},
{
"epoch": 1.75,
"learning_rate": 7.726603564337791e-06,
"loss": 0.7083,
"step": 220
},
{
"epoch": 1.76,
"learning_rate": 7.642410644905726e-06,
"loss": 0.7207,
"step": 221
},
{
"epoch": 1.77,
"learning_rate": 7.558394309716088e-06,
"loss": 0.7083,
"step": 222
},
{
"epoch": 1.78,
"learning_rate": 7.474560851620873e-06,
"loss": 0.7454,
"step": 223
},
{
"epoch": 1.78,
"learning_rate": 7.390916549774536e-06,
"loss": 0.7308,
"step": 224
},
{
"epoch": 1.79,
"learning_rate": 7.307467669163655e-06,
"loss": 0.7114,
"step": 225
},
{
"epoch": 1.8,
"learning_rate": 7.224220460137701e-06,
"loss": 0.7021,
"step": 226
},
{
"epoch": 1.81,
"learning_rate": 7.141181157940859e-06,
"loss": 0.7276,
"step": 227
},
{
"epoch": 1.82,
"learning_rate": 7.058355982245038e-06,
"loss": 0.711,
"step": 228
},
{
"epoch": 1.82,
"learning_rate": 6.97575113668399e-06,
"loss": 0.7256,
"step": 229
},
{
"epoch": 1.83,
"learning_rate": 6.893372808388674e-06,
"loss": 0.7044,
"step": 230
},
{
"epoch": 1.84,
"learning_rate": 6.8112271675238154e-06,
"loss": 0.6723,
"step": 231
},
{
"epoch": 1.85,
"learning_rate": 6.729320366825785e-06,
"loss": 0.7268,
"step": 232
},
{
"epoch": 1.86,
"learning_rate": 6.647658541141735e-06,
"loss": 0.7028,
"step": 233
},
{
"epoch": 1.86,
"learning_rate": 6.566247806970119e-06,
"loss": 0.729,
"step": 234
},
{
"epoch": 1.87,
"learning_rate": 6.485094262002529e-06,
"loss": 0.6692,
"step": 235
},
{
"epoch": 1.88,
"learning_rate": 6.404203984667019e-06,
"loss": 0.6896,
"step": 236
},
{
"epoch": 1.89,
"learning_rate": 6.323583033672799e-06,
"loss": 0.715,
"step": 237
},
{
"epoch": 1.9,
"learning_rate": 6.24323744755645e-06,
"loss": 0.7148,
"step": 238
},
{
"epoch": 1.9,
"learning_rate": 6.163173244229618e-06,
"loss": 0.7357,
"step": 239
},
{
"epoch": 1.91,
"learning_rate": 6.083396420528298e-06,
"loss": 0.71,
"step": 240
},
{
"epoch": 1.92,
"learning_rate": 6.003912951763644e-06,
"loss": 0.696,
"step": 241
},
{
"epoch": 1.93,
"learning_rate": 5.924728791274432e-06,
"loss": 0.6842,
"step": 242
},
{
"epoch": 1.94,
"learning_rate": 5.845849869981137e-06,
"loss": 0.7091,
"step": 243
},
{
"epoch": 1.94,
"learning_rate": 5.767282095941725e-06,
"loss": 0.6849,
"step": 244
},
{
"epoch": 1.95,
"learning_rate": 5.68903135390912e-06,
"loss": 0.7449,
"step": 245
},
{
"epoch": 1.96,
"learning_rate": 5.611103504890444e-06,
"loss": 0.7074,
"step": 246
},
{
"epoch": 1.97,
"learning_rate": 5.533504385708024e-06,
"loss": 0.7138,
"step": 247
},
{
"epoch": 1.98,
"learning_rate": 5.45623980856221e-06,
"loss": 0.7145,
"step": 248
},
{
"epoch": 1.98,
"learning_rate": 5.379315560596037e-06,
"loss": 0.7426,
"step": 249
},
{
"epoch": 1.99,
"learning_rate": 5.302737403461778e-06,
"loss": 0.6741,
"step": 250
},
{
"epoch": 2.0,
"learning_rate": 5.226511072889371e-06,
"loss": 0.6832,
"step": 251
},
{
"epoch": 2.01,
"learning_rate": 5.1506422782568345e-06,
"loss": 0.5329,
"step": 252
},
{
"epoch": 2.02,
"learning_rate": 5.075136702162622e-06,
"loss": 0.5358,
"step": 253
},
{
"epoch": 2.02,
"learning_rate": 5.000000000000003e-06,
"loss": 0.5402,
"step": 254
},
{
"epoch": 2.03,
"learning_rate": 4.925237799533445e-06,
"loss": 0.5159,
"step": 255
},
{
"epoch": 2.04,
"learning_rate": 4.85085570047713e-06,
"loss": 0.5301,
"step": 256
},
{
"epoch": 2.05,
"learning_rate": 4.776859274075506e-06,
"loss": 0.535,
"step": 257
},
{
"epoch": 2.06,
"learning_rate": 4.703254062686017e-06,
"loss": 0.5051,
"step": 258
},
{
"epoch": 2.06,
"learning_rate": 4.6300455793639565e-06,
"loss": 0.5253,
"step": 259
},
{
"epoch": 2.07,
"learning_rate": 4.557239307449562e-06,
"loss": 0.5146,
"step": 260
},
{
"epoch": 2.08,
"learning_rate": 4.4848407001572945e-06,
"loss": 0.5272,
"step": 261
},
{
"epoch": 2.09,
"learning_rate": 4.412855180167406e-06,
"loss": 0.531,
"step": 262
},
{
"epoch": 2.1,
"learning_rate": 4.341288139219752e-06,
"loss": 0.5101,
"step": 263
},
{
"epoch": 2.1,
"learning_rate": 4.270144937709981e-06,
"loss": 0.4964,
"step": 264
},
{
"epoch": 2.11,
"learning_rate": 4.19943090428802e-06,
"loss": 0.5403,
"step": 265
},
{
"epoch": 2.12,
"learning_rate": 4.1291513354589576e-06,
"loss": 0.5303,
"step": 266
},
{
"epoch": 2.13,
"learning_rate": 4.059311495186338e-06,
"loss": 0.5164,
"step": 267
},
{
"epoch": 2.14,
"learning_rate": 3.989916614497891e-06,
"loss": 0.486,
"step": 268
},
{
"epoch": 2.14,
"learning_rate": 3.9209718910937174e-06,
"loss": 0.4951,
"step": 269
},
{
"epoch": 2.15,
"learning_rate": 3.852482488956992e-06,
"loss": 0.5051,
"step": 270
},
{
"epoch": 2.16,
"learning_rate": 3.784453537967161e-06,
"loss": 0.5312,
"step": 271
},
{
"epoch": 2.17,
"learning_rate": 3.7168901335157313e-06,
"loss": 0.481,
"step": 272
},
{
"epoch": 2.18,
"learning_rate": 3.6497973361246153e-06,
"loss": 0.5259,
"step": 273
},
{
"epoch": 2.18,
"learning_rate": 3.583180171067101e-06,
"loss": 0.5091,
"step": 274
},
{
"epoch": 2.19,
"learning_rate": 3.517043627991441e-06,
"loss": 0.5071,
"step": 275
},
{
"epoch": 2.2,
"learning_rate": 3.4513926605471504e-06,
"loss": 0.5263,
"step": 276
},
{
"epoch": 2.21,
"learning_rate": 3.3862321860139578e-06,
"loss": 0.5056,
"step": 277
},
{
"epoch": 2.22,
"learning_rate": 3.3215670849335156e-06,
"loss": 0.5187,
"step": 278
},
{
"epoch": 2.22,
"learning_rate": 3.257402200743821e-06,
"loss": 0.521,
"step": 279
},
{
"epoch": 2.23,
"learning_rate": 3.19374233941647e-06,
"loss": 0.5028,
"step": 280
},
{
"epoch": 2.24,
"learning_rate": 3.1305922690966705e-06,
"loss": 0.4968,
"step": 281
},
{
"epoch": 2.25,
"learning_rate": 3.0679567197461135e-06,
"loss": 0.4963,
"step": 282
},
{
"epoch": 2.25,
"learning_rate": 3.005840382788685e-06,
"loss": 0.5082,
"step": 283
},
{
"epoch": 2.26,
"learning_rate": 2.944247910759097e-06,
"loss": 0.5287,
"step": 284
},
{
"epoch": 2.27,
"learning_rate": 2.8831839169543998e-06,
"loss": 0.5074,
"step": 285
},
{
"epoch": 2.28,
"learning_rate": 2.8226529750884403e-06,
"loss": 0.5049,
"step": 286
},
{
"epoch": 2.29,
"learning_rate": 2.7626596189492983e-06,
"loss": 0.477,
"step": 287
},
{
"epoch": 2.29,
"learning_rate": 2.7032083420597e-06,
"loss": 0.5196,
"step": 288
},
{
"epoch": 2.3,
"learning_rate": 2.6443035973404497e-06,
"loss": 0.5186,
"step": 289
},
{
"epoch": 2.31,
"learning_rate": 2.585949796776912e-06,
"loss": 0.4904,
"step": 290
},
{
"epoch": 2.32,
"learning_rate": 2.528151311088537e-06,
"loss": 0.5234,
"step": 291
},
{
"epoch": 2.33,
"learning_rate": 2.470912469401512e-06,
"loss": 0.4933,
"step": 292
},
{
"epoch": 2.33,
"learning_rate": 2.414237558924496e-06,
"loss": 0.5143,
"step": 293
},
{
"epoch": 2.34,
"learning_rate": 2.3581308246275103e-06,
"loss": 0.5168,
"step": 294
},
{
"epoch": 2.35,
"learning_rate": 2.302596468923981e-06,
"loss": 0.5049,
"step": 295
},
{
"epoch": 2.36,
"learning_rate": 2.247638651355991e-06,
"loss": 0.517,
"step": 296
},
{
"epoch": 2.37,
"learning_rate": 2.1932614882827196e-06,
"loss": 0.4923,
"step": 297
},
{
"epoch": 2.37,
"learning_rate": 2.1394690525721275e-06,
"loss": 0.4897,
"step": 298
},
{
"epoch": 2.38,
"learning_rate": 2.0862653732958914e-06,
"loss": 0.5118,
"step": 299
},
{
"epoch": 2.39,
"learning_rate": 2.03365443542764e-06,
"loss": 0.508,
"step": 300
},
{
"epoch": 2.4,
"learning_rate": 1.9816401795444664e-06,
"loss": 0.4983,
"step": 301
},
{
"epoch": 2.41,
"learning_rate": 1.93022650153178e-06,
"loss": 0.5127,
"step": 302
},
{
"epoch": 2.41,
"learning_rate": 1.8794172522915022e-06,
"loss": 0.5146,
"step": 303
},
{
"epoch": 2.42,
"learning_rate": 1.829216237453637e-06,
"loss": 0.5289,
"step": 304
},
{
"epoch": 2.43,
"learning_rate": 1.7796272170912255e-06,
"loss": 0.4871,
"step": 305
},
{
"epoch": 2.44,
"learning_rate": 1.730653905438714e-06,
"loss": 0.5142,
"step": 306
},
{
"epoch": 2.45,
"learning_rate": 1.6822999706137565e-06,
"loss": 0.5167,
"step": 307
},
{
"epoch": 2.45,
"learning_rate": 1.6345690343424758e-06,
"loss": 0.5056,
"step": 308
},
{
"epoch": 2.46,
"learning_rate": 1.587464671688187e-06,
"loss": 0.5192,
"step": 309
},
{
"epoch": 2.47,
"learning_rate": 1.540990410783636e-06,
"loss": 0.5187,
"step": 310
},
{
"epoch": 2.48,
"learning_rate": 1.495149732566723e-06,
"loss": 0.5175,
"step": 311
},
{
"epoch": 2.49,
"learning_rate": 1.4499460705198e-06,
"loss": 0.5055,
"step": 312
},
{
"epoch": 2.49,
"learning_rate": 1.4053828104124867e-06,
"loss": 0.5286,
"step": 313
},
{
"epoch": 2.5,
"learning_rate": 1.361463290048085e-06,
"loss": 0.526,
"step": 314
},
{
"epoch": 2.51,
"learning_rate": 1.3181907990135624e-06,
"loss": 0.5038,
"step": 315
},
{
"epoch": 2.52,
"learning_rate": 1.2755685784331784e-06,
"loss": 0.4852,
"step": 316
},
{
"epoch": 2.53,
"learning_rate": 1.2335998207257138e-06,
"loss": 0.5,
"step": 317
},
{
"epoch": 2.53,
"learning_rate": 1.1922876693653584e-06,
"loss": 0.5182,
"step": 318
},
{
"epoch": 2.54,
"learning_rate": 1.1516352186462588e-06,
"loss": 0.5406,
"step": 319
},
{
"epoch": 2.55,
"learning_rate": 1.1116455134507665e-06,
"loss": 0.488,
"step": 320
},
{
"epoch": 2.56,
"learning_rate": 1.0723215490213635e-06,
"loss": 0.5261,
"step": 321
},
{
"epoch": 2.57,
"learning_rate": 1.0336662707363287e-06,
"loss": 0.5127,
"step": 322
},
{
"epoch": 2.57,
"learning_rate": 9.95682573889114e-07,
"loss": 0.5145,
"step": 323
},
{
"epoch": 2.58,
"learning_rate": 9.583733034714982e-07,
"loss": 0.4902,
"step": 324
},
{
"epoch": 2.59,
"learning_rate": 9.217412539604942e-07,
"loss": 0.4974,
"step": 325
},
{
"epoch": 2.6,
"learning_rate": 8.857891691090336e-07,
"loss": 0.4695,
"step": 326
},
{
"epoch": 2.61,
"learning_rate": 8.505197417404687e-07,
"loss": 0.4944,
"step": 327
},
{
"epoch": 2.61,
"learning_rate": 8.159356135468721e-07,
"loss": 0.4966,
"step": 328
},
{
"epoch": 2.62,
"learning_rate": 7.820393748911792e-07,
"loss": 0.5097,
"step": 329
},
{
"epoch": 2.63,
"learning_rate": 7.488335646131628e-07,
"loss": 0.525,
"step": 330
},
{
"epoch": 2.64,
"learning_rate": 7.163206698392744e-07,
"loss": 0.4993,
"step": 331
},
{
"epoch": 2.65,
"learning_rate": 6.845031257963619e-07,
"loss": 0.489,
"step": 332
},
{
"epoch": 2.65,
"learning_rate": 6.53383315629268e-07,
"loss": 0.4964,
"step": 333
},
{
"epoch": 2.66,
"learning_rate": 6.229635702223325e-07,
"loss": 0.5255,
"step": 334
},
{
"epoch": 2.67,
"learning_rate": 5.932461680248014e-07,
"loss": 0.5094,
"step": 335
},
{
"epoch": 2.68,
"learning_rate": 5.64233334880181e-07,
"loss": 0.4925,
"step": 336
},
{
"epoch": 2.69,
"learning_rate": 5.359272438595153e-07,
"loss": 0.511,
"step": 337
},
{
"epoch": 2.69,
"learning_rate": 5.083300150986259e-07,
"loss": 0.5087,
"step": 338
},
{
"epoch": 2.7,
"learning_rate": 4.814437156393048e-07,
"loss": 0.5189,
"step": 339
},
{
"epoch": 2.71,
"learning_rate": 4.5527035927450337e-07,
"loss": 0.4896,
"step": 340
},
{
"epoch": 2.72,
"learning_rate": 4.298119063974915e-07,
"loss": 0.5004,
"step": 341
},
{
"epoch": 2.73,
"learning_rate": 4.0507026385502747e-07,
"loss": 0.5096,
"step": 342
},
{
"epoch": 2.73,
"learning_rate": 3.810472848045266e-07,
"loss": 0.5195,
"step": 343
},
{
"epoch": 2.74,
"learning_rate": 3.5774476857527107e-07,
"loss": 0.5102,
"step": 344
},
{
"epoch": 2.75,
"learning_rate": 3.3516446053363015e-07,
"loss": 0.4774,
"step": 345
},
{
"epoch": 2.76,
"learning_rate": 3.1330805195233684e-07,
"loss": 0.5122,
"step": 346
},
{
"epoch": 2.76,
"learning_rate": 2.921771798838069e-07,
"loss": 0.4839,
"step": 347
},
{
"epoch": 2.77,
"learning_rate": 2.717734270375272e-07,
"loss": 0.4781,
"step": 348
},
{
"epoch": 2.78,
"learning_rate": 2.520983216615047e-07,
"loss": 0.5338,
"step": 349
},
{
"epoch": 2.79,
"learning_rate": 2.3315333742780942e-07,
"loss": 0.5009,
"step": 350
},
{
"epoch": 2.8,
"learning_rate": 2.1493989332218468e-07,
"loss": 0.4998,
"step": 351
},
{
"epoch": 2.8,
"learning_rate": 1.9745935353777222e-07,
"loss": 0.5426,
"step": 352
},
{
"epoch": 2.81,
"learning_rate": 1.8071302737293294e-07,
"loss": 0.4944,
"step": 353
},
{
"epoch": 2.82,
"learning_rate": 1.6470216913317628e-07,
"loss": 0.5074,
"step": 354
},
{
"epoch": 2.83,
"learning_rate": 1.4942797803721543e-07,
"loss": 0.4987,
"step": 355
},
{
"epoch": 2.84,
"learning_rate": 1.348915981271437e-07,
"loss": 0.5302,
"step": 356
},
{
"epoch": 2.84,
"learning_rate": 1.2109411818274851e-07,
"loss": 0.4965,
"step": 357
},
{
"epoch": 2.85,
"learning_rate": 1.0803657163995896e-07,
"loss": 0.5119,
"step": 358
},
{
"epoch": 2.86,
"learning_rate": 9.571993651343869e-08,
"loss": 0.4805,
"step": 359
},
{
"epoch": 2.87,
"learning_rate": 8.41451353233369e-08,
"loss": 0.5057,
"step": 360
},
{
"epoch": 2.88,
"learning_rate": 7.331303502618903e-08,
"loss": 0.4891,
"step": 361
},
{
"epoch": 2.88,
"learning_rate": 6.32244469499832e-08,
"loss": 0.5223,
"step": 362
},
{
"epoch": 2.89,
"learning_rate": 5.388012673338661e-08,
"loss": 0.5151,
"step": 363
},
{
"epoch": 2.9,
"learning_rate": 4.528077426915412e-08,
"loss": 0.4966,
"step": 364
},
{
"epoch": 2.91,
"learning_rate": 3.7427033651702414e-08,
"loss": 0.5096,
"step": 365
},
{
"epoch": 2.92,
"learning_rate": 3.03194931288664e-08,
"loss": 0.5051,
"step": 366
},
{
"epoch": 2.92,
"learning_rate": 2.3958685057844378e-08,
"loss": 0.5117,
"step": 367
},
{
"epoch": 2.93,
"learning_rate": 1.83450858653178e-08,
"loss": 0.4816,
"step": 368
},
{
"epoch": 2.94,
"learning_rate": 1.3479116011769766e-08,
"loss": 0.4839,
"step": 369
},
{
"epoch": 2.95,
"learning_rate": 9.361139959993549e-09,
"loss": 0.5347,
"step": 370
},
{
"epoch": 2.96,
"learning_rate": 5.991466147791114e-09,
"loss": 0.5263,
"step": 371
},
{
"epoch": 2.96,
"learning_rate": 3.3703469648760367e-09,
"loss": 0.5253,
"step": 372
},
{
"epoch": 2.97,
"learning_rate": 1.497978733961958e-09,
"loss": 0.5517,
"step": 373
},
{
"epoch": 2.98,
"learning_rate": 3.745016960665648e-10,
"loss": 0.5018,
"step": 374
},
{
"epoch": 2.99,
"learning_rate": 0.0,
"loss": 0.514,
"step": 375
},
{
"epoch": 2.99,
"step": 375,
"total_flos": 144378314096640.0,
"train_loss": 0.765017323811849,
"train_runtime": 10075.457,
"train_samples_per_second": 19.117,
"train_steps_per_second": 0.037
}
],
"max_steps": 375,
"num_train_epochs": 3,
"total_flos": 144378314096640.0,
"trial_name": null,
"trial_params": null
}