adalaw's picture
Upload folder using huggingface_hub
8e5dcf7 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.997778483021263,
"eval_steps": 500,
"global_step": 393,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 4.1666666666666667e-07,
"loss": 1.3058,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 8.333333333333333e-07,
"loss": 1.192,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 1.25e-06,
"loss": 1.2973,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 1.6666666666666667e-06,
"loss": 1.2629,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 2.0833333333333334e-06,
"loss": 1.2073,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 2.5e-06,
"loss": 1.1229,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 2.916666666666667e-06,
"loss": 1.2677,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.1353,
"step": 8
},
{
"epoch": 0.02,
"learning_rate": 3.7500000000000005e-06,
"loss": 1.0524,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 4.166666666666667e-06,
"loss": 1.0016,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 4.583333333333333e-06,
"loss": 1.1865,
"step": 11
},
{
"epoch": 0.03,
"learning_rate": 5e-06,
"loss": 1.0415,
"step": 12
},
{
"epoch": 0.03,
"learning_rate": 5.416666666666667e-06,
"loss": 0.9764,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 5.833333333333334e-06,
"loss": 1.0045,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 6.25e-06,
"loss": 0.8317,
"step": 15
},
{
"epoch": 0.04,
"learning_rate": 6.666666666666667e-06,
"loss": 0.9207,
"step": 16
},
{
"epoch": 0.04,
"learning_rate": 7.083333333333335e-06,
"loss": 0.8949,
"step": 17
},
{
"epoch": 0.05,
"learning_rate": 7.500000000000001e-06,
"loss": 0.8629,
"step": 18
},
{
"epoch": 0.05,
"learning_rate": 7.916666666666667e-06,
"loss": 0.9026,
"step": 19
},
{
"epoch": 0.05,
"learning_rate": 8.333333333333334e-06,
"loss": 0.8833,
"step": 20
},
{
"epoch": 0.05,
"learning_rate": 8.750000000000001e-06,
"loss": 0.8436,
"step": 21
},
{
"epoch": 0.06,
"learning_rate": 9.166666666666666e-06,
"loss": 0.868,
"step": 22
},
{
"epoch": 0.06,
"learning_rate": 9.583333333333335e-06,
"loss": 0.8943,
"step": 23
},
{
"epoch": 0.06,
"learning_rate": 1e-05,
"loss": 0.835,
"step": 24
},
{
"epoch": 0.06,
"learning_rate": 1.0416666666666668e-05,
"loss": 0.8719,
"step": 25
},
{
"epoch": 0.07,
"learning_rate": 1.0833333333333334e-05,
"loss": 0.8289,
"step": 26
},
{
"epoch": 0.07,
"learning_rate": 1.125e-05,
"loss": 0.8167,
"step": 27
},
{
"epoch": 0.07,
"learning_rate": 1.1666666666666668e-05,
"loss": 0.8897,
"step": 28
},
{
"epoch": 0.07,
"learning_rate": 1.2083333333333333e-05,
"loss": 0.895,
"step": 29
},
{
"epoch": 0.08,
"learning_rate": 1.25e-05,
"loss": 0.8243,
"step": 30
},
{
"epoch": 0.08,
"learning_rate": 1.2916666666666668e-05,
"loss": 0.8314,
"step": 31
},
{
"epoch": 0.08,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.8049,
"step": 32
},
{
"epoch": 0.08,
"learning_rate": 1.375e-05,
"loss": 0.8087,
"step": 33
},
{
"epoch": 0.09,
"learning_rate": 1.416666666666667e-05,
"loss": 0.7565,
"step": 34
},
{
"epoch": 0.09,
"learning_rate": 1.4583333333333333e-05,
"loss": 0.8179,
"step": 35
},
{
"epoch": 0.09,
"learning_rate": 1.5000000000000002e-05,
"loss": 0.8248,
"step": 36
},
{
"epoch": 0.09,
"learning_rate": 1.5416666666666668e-05,
"loss": 0.8214,
"step": 37
},
{
"epoch": 0.1,
"learning_rate": 1.5833333333333333e-05,
"loss": 0.8612,
"step": 38
},
{
"epoch": 0.1,
"learning_rate": 1.6250000000000002e-05,
"loss": 0.8087,
"step": 39
},
{
"epoch": 0.1,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.8338,
"step": 40
},
{
"epoch": 0.1,
"learning_rate": 1.7083333333333333e-05,
"loss": 0.8538,
"step": 41
},
{
"epoch": 0.11,
"learning_rate": 1.7500000000000002e-05,
"loss": 0.736,
"step": 42
},
{
"epoch": 0.11,
"learning_rate": 1.7916666666666667e-05,
"loss": 0.7752,
"step": 43
},
{
"epoch": 0.11,
"learning_rate": 1.8333333333333333e-05,
"loss": 0.8186,
"step": 44
},
{
"epoch": 0.11,
"learning_rate": 1.8750000000000002e-05,
"loss": 0.9004,
"step": 45
},
{
"epoch": 0.12,
"learning_rate": 1.916666666666667e-05,
"loss": 0.7464,
"step": 46
},
{
"epoch": 0.12,
"learning_rate": 1.9583333333333333e-05,
"loss": 0.8744,
"step": 47
},
{
"epoch": 0.12,
"learning_rate": 2e-05,
"loss": 0.7909,
"step": 48
},
{
"epoch": 0.12,
"learning_rate": 1.998687664041995e-05,
"loss": 0.7354,
"step": 49
},
{
"epoch": 0.13,
"learning_rate": 1.9973753280839896e-05,
"loss": 0.7691,
"step": 50
},
{
"epoch": 0.13,
"learning_rate": 1.9960629921259843e-05,
"loss": 0.7398,
"step": 51
},
{
"epoch": 0.13,
"learning_rate": 1.9947506561679793e-05,
"loss": 0.814,
"step": 52
},
{
"epoch": 0.13,
"learning_rate": 1.9934383202099737e-05,
"loss": 0.8055,
"step": 53
},
{
"epoch": 0.14,
"learning_rate": 1.9921259842519688e-05,
"loss": 0.785,
"step": 54
},
{
"epoch": 0.14,
"learning_rate": 1.9908136482939635e-05,
"loss": 1.0027,
"step": 55
},
{
"epoch": 0.14,
"learning_rate": 1.9895013123359582e-05,
"loss": 0.8046,
"step": 56
},
{
"epoch": 0.14,
"learning_rate": 1.988188976377953e-05,
"loss": 0.6848,
"step": 57
},
{
"epoch": 0.15,
"learning_rate": 1.9868766404199476e-05,
"loss": 0.786,
"step": 58
},
{
"epoch": 0.15,
"learning_rate": 1.9855643044619423e-05,
"loss": 0.8834,
"step": 59
},
{
"epoch": 0.15,
"learning_rate": 1.984251968503937e-05,
"loss": 0.752,
"step": 60
},
{
"epoch": 0.15,
"learning_rate": 1.982939632545932e-05,
"loss": 0.6875,
"step": 61
},
{
"epoch": 0.16,
"learning_rate": 1.9816272965879265e-05,
"loss": 0.7118,
"step": 62
},
{
"epoch": 0.16,
"learning_rate": 1.9803149606299215e-05,
"loss": 0.6849,
"step": 63
},
{
"epoch": 0.16,
"learning_rate": 1.9790026246719162e-05,
"loss": 0.8545,
"step": 64
},
{
"epoch": 0.17,
"learning_rate": 1.977690288713911e-05,
"loss": 0.6823,
"step": 65
},
{
"epoch": 0.17,
"learning_rate": 1.9763779527559057e-05,
"loss": 0.7772,
"step": 66
},
{
"epoch": 0.17,
"learning_rate": 1.9750656167979004e-05,
"loss": 0.789,
"step": 67
},
{
"epoch": 0.17,
"learning_rate": 1.973753280839895e-05,
"loss": 0.7375,
"step": 68
},
{
"epoch": 0.18,
"learning_rate": 1.97244094488189e-05,
"loss": 0.8808,
"step": 69
},
{
"epoch": 0.18,
"learning_rate": 1.9711286089238845e-05,
"loss": 0.7628,
"step": 70
},
{
"epoch": 0.18,
"learning_rate": 1.9698162729658795e-05,
"loss": 0.732,
"step": 71
},
{
"epoch": 0.18,
"learning_rate": 1.9685039370078743e-05,
"loss": 0.7512,
"step": 72
},
{
"epoch": 0.19,
"learning_rate": 1.967191601049869e-05,
"loss": 0.7593,
"step": 73
},
{
"epoch": 0.19,
"learning_rate": 1.9658792650918637e-05,
"loss": 0.7135,
"step": 74
},
{
"epoch": 0.19,
"learning_rate": 1.9645669291338584e-05,
"loss": 0.8312,
"step": 75
},
{
"epoch": 0.19,
"learning_rate": 1.963254593175853e-05,
"loss": 0.7569,
"step": 76
},
{
"epoch": 0.2,
"learning_rate": 1.9619422572178478e-05,
"loss": 0.7697,
"step": 77
},
{
"epoch": 0.2,
"learning_rate": 1.960629921259843e-05,
"loss": 0.7605,
"step": 78
},
{
"epoch": 0.2,
"learning_rate": 1.9593175853018372e-05,
"loss": 0.6993,
"step": 79
},
{
"epoch": 0.2,
"learning_rate": 1.9580052493438323e-05,
"loss": 0.7379,
"step": 80
},
{
"epoch": 0.21,
"learning_rate": 1.956692913385827e-05,
"loss": 0.7636,
"step": 81
},
{
"epoch": 0.21,
"learning_rate": 1.9553805774278217e-05,
"loss": 0.7483,
"step": 82
},
{
"epoch": 0.21,
"learning_rate": 1.9540682414698164e-05,
"loss": 0.6927,
"step": 83
},
{
"epoch": 0.21,
"learning_rate": 1.952755905511811e-05,
"loss": 0.7517,
"step": 84
},
{
"epoch": 0.22,
"learning_rate": 1.951443569553806e-05,
"loss": 0.7909,
"step": 85
},
{
"epoch": 0.22,
"learning_rate": 1.9501312335958006e-05,
"loss": 0.8087,
"step": 86
},
{
"epoch": 0.22,
"learning_rate": 1.9488188976377956e-05,
"loss": 0.6628,
"step": 87
},
{
"epoch": 0.22,
"learning_rate": 1.94750656167979e-05,
"loss": 0.7129,
"step": 88
},
{
"epoch": 0.23,
"learning_rate": 1.946194225721785e-05,
"loss": 0.6922,
"step": 89
},
{
"epoch": 0.23,
"learning_rate": 1.9448818897637797e-05,
"loss": 0.7997,
"step": 90
},
{
"epoch": 0.23,
"learning_rate": 1.9435695538057745e-05,
"loss": 0.6905,
"step": 91
},
{
"epoch": 0.23,
"learning_rate": 1.9422572178477692e-05,
"loss": 0.8932,
"step": 92
},
{
"epoch": 0.24,
"learning_rate": 1.940944881889764e-05,
"loss": 0.7211,
"step": 93
},
{
"epoch": 0.24,
"learning_rate": 1.9396325459317586e-05,
"loss": 0.7291,
"step": 94
},
{
"epoch": 0.24,
"learning_rate": 1.9383202099737536e-05,
"loss": 0.7578,
"step": 95
},
{
"epoch": 0.24,
"learning_rate": 1.937007874015748e-05,
"loss": 0.8398,
"step": 96
},
{
"epoch": 0.25,
"learning_rate": 1.935695538057743e-05,
"loss": 0.7768,
"step": 97
},
{
"epoch": 0.25,
"learning_rate": 1.9343832020997378e-05,
"loss": 0.8122,
"step": 98
},
{
"epoch": 0.25,
"learning_rate": 1.9330708661417325e-05,
"loss": 0.7434,
"step": 99
},
{
"epoch": 0.25,
"learning_rate": 1.9317585301837272e-05,
"loss": 0.7193,
"step": 100
},
{
"epoch": 0.26,
"learning_rate": 1.930446194225722e-05,
"loss": 0.7587,
"step": 101
},
{
"epoch": 0.26,
"learning_rate": 1.9291338582677166e-05,
"loss": 0.7144,
"step": 102
},
{
"epoch": 0.26,
"learning_rate": 1.9278215223097113e-05,
"loss": 0.629,
"step": 103
},
{
"epoch": 0.26,
"learning_rate": 1.9265091863517064e-05,
"loss": 0.7723,
"step": 104
},
{
"epoch": 0.27,
"learning_rate": 1.9251968503937008e-05,
"loss": 0.7523,
"step": 105
},
{
"epoch": 0.27,
"learning_rate": 1.9238845144356958e-05,
"loss": 0.7475,
"step": 106
},
{
"epoch": 0.27,
"learning_rate": 1.9225721784776905e-05,
"loss": 0.789,
"step": 107
},
{
"epoch": 0.27,
"learning_rate": 1.9212598425196852e-05,
"loss": 0.7289,
"step": 108
},
{
"epoch": 0.28,
"learning_rate": 1.91994750656168e-05,
"loss": 0.7498,
"step": 109
},
{
"epoch": 0.28,
"learning_rate": 1.9186351706036747e-05,
"loss": 0.9547,
"step": 110
},
{
"epoch": 0.28,
"learning_rate": 1.9173228346456694e-05,
"loss": 0.8021,
"step": 111
},
{
"epoch": 0.28,
"learning_rate": 1.916010498687664e-05,
"loss": 0.7983,
"step": 112
},
{
"epoch": 0.29,
"learning_rate": 1.914698162729659e-05,
"loss": 0.6735,
"step": 113
},
{
"epoch": 0.29,
"learning_rate": 1.9133858267716535e-05,
"loss": 0.6658,
"step": 114
},
{
"epoch": 0.29,
"learning_rate": 1.9120734908136486e-05,
"loss": 0.7631,
"step": 115
},
{
"epoch": 0.29,
"learning_rate": 1.9107611548556433e-05,
"loss": 0.7936,
"step": 116
},
{
"epoch": 0.3,
"learning_rate": 1.909448818897638e-05,
"loss": 0.7189,
"step": 117
},
{
"epoch": 0.3,
"learning_rate": 1.9081364829396327e-05,
"loss": 0.7468,
"step": 118
},
{
"epoch": 0.3,
"learning_rate": 1.9068241469816274e-05,
"loss": 0.6605,
"step": 119
},
{
"epoch": 0.3,
"learning_rate": 1.905511811023622e-05,
"loss": 0.7652,
"step": 120
},
{
"epoch": 0.31,
"learning_rate": 1.9041994750656168e-05,
"loss": 0.7574,
"step": 121
},
{
"epoch": 0.31,
"learning_rate": 1.902887139107612e-05,
"loss": 0.7762,
"step": 122
},
{
"epoch": 0.31,
"learning_rate": 1.9015748031496062e-05,
"loss": 0.8641,
"step": 123
},
{
"epoch": 0.31,
"learning_rate": 1.9002624671916013e-05,
"loss": 0.8135,
"step": 124
},
{
"epoch": 0.32,
"learning_rate": 1.898950131233596e-05,
"loss": 0.7567,
"step": 125
},
{
"epoch": 0.32,
"learning_rate": 1.8976377952755907e-05,
"loss": 0.7335,
"step": 126
},
{
"epoch": 0.32,
"learning_rate": 1.8963254593175854e-05,
"loss": 0.7627,
"step": 127
},
{
"epoch": 0.32,
"learning_rate": 1.89501312335958e-05,
"loss": 0.6773,
"step": 128
},
{
"epoch": 0.33,
"learning_rate": 1.893700787401575e-05,
"loss": 0.729,
"step": 129
},
{
"epoch": 0.33,
"learning_rate": 1.89238845144357e-05,
"loss": 0.7523,
"step": 130
},
{
"epoch": 0.33,
"learning_rate": 1.8910761154855643e-05,
"loss": 0.8078,
"step": 131
},
{
"epoch": 0.34,
"learning_rate": 1.8897637795275593e-05,
"loss": 0.6969,
"step": 132
},
{
"epoch": 0.34,
"learning_rate": 1.888451443569554e-05,
"loss": 0.6729,
"step": 133
},
{
"epoch": 0.34,
"learning_rate": 1.8871391076115488e-05,
"loss": 0.6691,
"step": 134
},
{
"epoch": 0.34,
"learning_rate": 1.8858267716535435e-05,
"loss": 0.7116,
"step": 135
},
{
"epoch": 0.35,
"learning_rate": 1.8845144356955382e-05,
"loss": 0.7435,
"step": 136
},
{
"epoch": 0.35,
"learning_rate": 1.883202099737533e-05,
"loss": 0.7491,
"step": 137
},
{
"epoch": 0.35,
"learning_rate": 1.8818897637795276e-05,
"loss": 0.7642,
"step": 138
},
{
"epoch": 0.35,
"learning_rate": 1.8805774278215227e-05,
"loss": 0.7199,
"step": 139
},
{
"epoch": 0.36,
"learning_rate": 1.879265091863517e-05,
"loss": 0.8203,
"step": 140
},
{
"epoch": 0.36,
"learning_rate": 1.877952755905512e-05,
"loss": 0.7748,
"step": 141
},
{
"epoch": 0.36,
"learning_rate": 1.8766404199475068e-05,
"loss": 0.7709,
"step": 142
},
{
"epoch": 0.36,
"learning_rate": 1.8753280839895015e-05,
"loss": 0.8527,
"step": 143
},
{
"epoch": 0.37,
"learning_rate": 1.8740157480314962e-05,
"loss": 0.6678,
"step": 144
},
{
"epoch": 0.37,
"learning_rate": 1.872703412073491e-05,
"loss": 0.8097,
"step": 145
},
{
"epoch": 0.37,
"learning_rate": 1.8713910761154856e-05,
"loss": 0.7239,
"step": 146
},
{
"epoch": 0.37,
"learning_rate": 1.8700787401574803e-05,
"loss": 0.6475,
"step": 147
},
{
"epoch": 0.38,
"learning_rate": 1.8687664041994754e-05,
"loss": 0.6625,
"step": 148
},
{
"epoch": 0.38,
"learning_rate": 1.8674540682414698e-05,
"loss": 0.7769,
"step": 149
},
{
"epoch": 0.38,
"learning_rate": 1.8661417322834648e-05,
"loss": 0.7377,
"step": 150
},
{
"epoch": 0.38,
"learning_rate": 1.8648293963254595e-05,
"loss": 0.7023,
"step": 151
},
{
"epoch": 0.39,
"learning_rate": 1.8635170603674542e-05,
"loss": 0.7637,
"step": 152
},
{
"epoch": 0.39,
"learning_rate": 1.862204724409449e-05,
"loss": 0.7102,
"step": 153
},
{
"epoch": 0.39,
"learning_rate": 1.8608923884514437e-05,
"loss": 0.7238,
"step": 154
},
{
"epoch": 0.39,
"learning_rate": 1.8595800524934384e-05,
"loss": 0.7406,
"step": 155
},
{
"epoch": 0.4,
"learning_rate": 1.858267716535433e-05,
"loss": 0.834,
"step": 156
},
{
"epoch": 0.4,
"learning_rate": 1.856955380577428e-05,
"loss": 0.7231,
"step": 157
},
{
"epoch": 0.4,
"learning_rate": 1.855643044619423e-05,
"loss": 0.6133,
"step": 158
},
{
"epoch": 0.4,
"learning_rate": 1.8543307086614176e-05,
"loss": 0.7238,
"step": 159
},
{
"epoch": 0.41,
"learning_rate": 1.8530183727034123e-05,
"loss": 0.6676,
"step": 160
},
{
"epoch": 0.41,
"learning_rate": 1.851706036745407e-05,
"loss": 0.7014,
"step": 161
},
{
"epoch": 0.41,
"learning_rate": 1.8503937007874017e-05,
"loss": 0.7926,
"step": 162
},
{
"epoch": 0.41,
"learning_rate": 1.8490813648293964e-05,
"loss": 0.678,
"step": 163
},
{
"epoch": 0.42,
"learning_rate": 1.847769028871391e-05,
"loss": 0.7271,
"step": 164
},
{
"epoch": 0.42,
"learning_rate": 1.846456692913386e-05,
"loss": 0.7583,
"step": 165
},
{
"epoch": 0.42,
"learning_rate": 1.8451443569553805e-05,
"loss": 0.7569,
"step": 166
},
{
"epoch": 0.42,
"learning_rate": 1.8438320209973756e-05,
"loss": 0.6899,
"step": 167
},
{
"epoch": 0.43,
"learning_rate": 1.8425196850393703e-05,
"loss": 0.6988,
"step": 168
},
{
"epoch": 0.43,
"learning_rate": 1.841207349081365e-05,
"loss": 0.7114,
"step": 169
},
{
"epoch": 0.43,
"learning_rate": 1.8398950131233597e-05,
"loss": 0.6809,
"step": 170
},
{
"epoch": 0.43,
"learning_rate": 1.8385826771653544e-05,
"loss": 0.8045,
"step": 171
},
{
"epoch": 0.44,
"learning_rate": 1.837270341207349e-05,
"loss": 0.7361,
"step": 172
},
{
"epoch": 0.44,
"learning_rate": 1.835958005249344e-05,
"loss": 0.7402,
"step": 173
},
{
"epoch": 0.44,
"learning_rate": 1.834645669291339e-05,
"loss": 0.7559,
"step": 174
},
{
"epoch": 0.44,
"learning_rate": 1.8333333333333333e-05,
"loss": 0.7329,
"step": 175
},
{
"epoch": 0.45,
"learning_rate": 1.8320209973753283e-05,
"loss": 0.735,
"step": 176
},
{
"epoch": 0.45,
"learning_rate": 1.830708661417323e-05,
"loss": 0.6951,
"step": 177
},
{
"epoch": 0.45,
"learning_rate": 1.8293963254593178e-05,
"loss": 0.7412,
"step": 178
},
{
"epoch": 0.45,
"learning_rate": 1.8280839895013125e-05,
"loss": 0.8119,
"step": 179
},
{
"epoch": 0.46,
"learning_rate": 1.8267716535433072e-05,
"loss": 0.7192,
"step": 180
},
{
"epoch": 0.46,
"learning_rate": 1.825459317585302e-05,
"loss": 0.7069,
"step": 181
},
{
"epoch": 0.46,
"learning_rate": 1.8241469816272966e-05,
"loss": 0.7952,
"step": 182
},
{
"epoch": 0.46,
"learning_rate": 1.8228346456692917e-05,
"loss": 0.7064,
"step": 183
},
{
"epoch": 0.47,
"learning_rate": 1.821522309711286e-05,
"loss": 0.7563,
"step": 184
},
{
"epoch": 0.47,
"learning_rate": 1.820209973753281e-05,
"loss": 0.6829,
"step": 185
},
{
"epoch": 0.47,
"learning_rate": 1.8188976377952758e-05,
"loss": 0.6525,
"step": 186
},
{
"epoch": 0.47,
"learning_rate": 1.8175853018372705e-05,
"loss": 0.7344,
"step": 187
},
{
"epoch": 0.48,
"learning_rate": 1.8162729658792652e-05,
"loss": 0.7181,
"step": 188
},
{
"epoch": 0.48,
"learning_rate": 1.8149606299212603e-05,
"loss": 0.8006,
"step": 189
},
{
"epoch": 0.48,
"learning_rate": 1.8136482939632546e-05,
"loss": 0.6388,
"step": 190
},
{
"epoch": 0.48,
"learning_rate": 1.8123359580052497e-05,
"loss": 0.8009,
"step": 191
},
{
"epoch": 0.49,
"learning_rate": 1.811023622047244e-05,
"loss": 0.7908,
"step": 192
},
{
"epoch": 0.49,
"learning_rate": 1.809711286089239e-05,
"loss": 0.6814,
"step": 193
},
{
"epoch": 0.49,
"learning_rate": 1.8083989501312338e-05,
"loss": 0.7376,
"step": 194
},
{
"epoch": 0.5,
"learning_rate": 1.8070866141732285e-05,
"loss": 0.7501,
"step": 195
},
{
"epoch": 0.5,
"learning_rate": 1.8057742782152232e-05,
"loss": 0.7356,
"step": 196
},
{
"epoch": 0.5,
"learning_rate": 1.804461942257218e-05,
"loss": 0.7889,
"step": 197
},
{
"epoch": 0.5,
"learning_rate": 1.8031496062992127e-05,
"loss": 0.7564,
"step": 198
},
{
"epoch": 0.51,
"learning_rate": 1.8018372703412074e-05,
"loss": 0.759,
"step": 199
},
{
"epoch": 0.51,
"learning_rate": 1.8005249343832024e-05,
"loss": 0.7271,
"step": 200
},
{
"epoch": 0.51,
"learning_rate": 1.7992125984251968e-05,
"loss": 0.7391,
"step": 201
},
{
"epoch": 0.51,
"learning_rate": 1.797900262467192e-05,
"loss": 0.7416,
"step": 202
},
{
"epoch": 0.52,
"learning_rate": 1.7965879265091866e-05,
"loss": 0.816,
"step": 203
},
{
"epoch": 0.52,
"learning_rate": 1.7952755905511813e-05,
"loss": 0.8431,
"step": 204
},
{
"epoch": 0.52,
"learning_rate": 1.793963254593176e-05,
"loss": 0.7536,
"step": 205
},
{
"epoch": 0.52,
"learning_rate": 1.7926509186351707e-05,
"loss": 0.8151,
"step": 206
},
{
"epoch": 0.53,
"learning_rate": 1.7913385826771654e-05,
"loss": 0.7686,
"step": 207
},
{
"epoch": 0.53,
"learning_rate": 1.79002624671916e-05,
"loss": 0.8059,
"step": 208
},
{
"epoch": 0.53,
"learning_rate": 1.7887139107611552e-05,
"loss": 0.7326,
"step": 209
},
{
"epoch": 0.53,
"learning_rate": 1.7874015748031495e-05,
"loss": 0.7793,
"step": 210
},
{
"epoch": 0.54,
"learning_rate": 1.7860892388451446e-05,
"loss": 0.7138,
"step": 211
},
{
"epoch": 0.54,
"learning_rate": 1.7847769028871393e-05,
"loss": 0.7229,
"step": 212
},
{
"epoch": 0.54,
"learning_rate": 1.783464566929134e-05,
"loss": 0.6943,
"step": 213
},
{
"epoch": 0.54,
"learning_rate": 1.7821522309711287e-05,
"loss": 0.7195,
"step": 214
},
{
"epoch": 0.55,
"learning_rate": 1.7808398950131234e-05,
"loss": 0.7308,
"step": 215
},
{
"epoch": 0.55,
"learning_rate": 1.779527559055118e-05,
"loss": 0.7402,
"step": 216
},
{
"epoch": 0.55,
"learning_rate": 1.778215223097113e-05,
"loss": 0.744,
"step": 217
},
{
"epoch": 0.55,
"learning_rate": 1.776902887139108e-05,
"loss": 0.7673,
"step": 218
},
{
"epoch": 0.56,
"learning_rate": 1.7755905511811026e-05,
"loss": 0.7006,
"step": 219
},
{
"epoch": 0.56,
"learning_rate": 1.7742782152230973e-05,
"loss": 0.6871,
"step": 220
},
{
"epoch": 0.56,
"learning_rate": 1.772965879265092e-05,
"loss": 0.7029,
"step": 221
},
{
"epoch": 0.56,
"learning_rate": 1.7716535433070868e-05,
"loss": 0.7153,
"step": 222
},
{
"epoch": 0.57,
"learning_rate": 1.7703412073490815e-05,
"loss": 0.7385,
"step": 223
},
{
"epoch": 0.57,
"learning_rate": 1.7690288713910762e-05,
"loss": 0.712,
"step": 224
},
{
"epoch": 0.57,
"learning_rate": 1.767716535433071e-05,
"loss": 0.7185,
"step": 225
},
{
"epoch": 0.57,
"learning_rate": 1.766404199475066e-05,
"loss": 0.7657,
"step": 226
},
{
"epoch": 0.58,
"learning_rate": 1.7650918635170603e-05,
"loss": 0.7549,
"step": 227
},
{
"epoch": 0.58,
"learning_rate": 1.7637795275590554e-05,
"loss": 0.7118,
"step": 228
},
{
"epoch": 0.58,
"learning_rate": 1.76246719160105e-05,
"loss": 0.6845,
"step": 229
},
{
"epoch": 0.58,
"learning_rate": 1.7611548556430448e-05,
"loss": 0.689,
"step": 230
},
{
"epoch": 0.59,
"learning_rate": 1.7598425196850395e-05,
"loss": 0.7365,
"step": 231
},
{
"epoch": 0.59,
"learning_rate": 1.7585301837270342e-05,
"loss": 0.7297,
"step": 232
},
{
"epoch": 0.59,
"learning_rate": 1.757217847769029e-05,
"loss": 0.7449,
"step": 233
},
{
"epoch": 0.59,
"learning_rate": 1.7559055118110236e-05,
"loss": 0.7652,
"step": 234
},
{
"epoch": 0.6,
"learning_rate": 1.7545931758530187e-05,
"loss": 0.719,
"step": 235
},
{
"epoch": 0.6,
"learning_rate": 1.753280839895013e-05,
"loss": 0.6519,
"step": 236
},
{
"epoch": 0.6,
"learning_rate": 1.751968503937008e-05,
"loss": 0.7801,
"step": 237
},
{
"epoch": 0.6,
"learning_rate": 1.7506561679790028e-05,
"loss": 0.7334,
"step": 238
},
{
"epoch": 0.61,
"learning_rate": 1.7493438320209975e-05,
"loss": 0.689,
"step": 239
},
{
"epoch": 0.61,
"learning_rate": 1.7480314960629923e-05,
"loss": 0.8085,
"step": 240
},
{
"epoch": 0.61,
"learning_rate": 1.746719160104987e-05,
"loss": 0.8845,
"step": 241
},
{
"epoch": 0.61,
"learning_rate": 1.7454068241469817e-05,
"loss": 0.6735,
"step": 242
},
{
"epoch": 0.62,
"learning_rate": 1.7440944881889764e-05,
"loss": 0.7002,
"step": 243
},
{
"epoch": 0.62,
"learning_rate": 1.7427821522309714e-05,
"loss": 0.6246,
"step": 244
},
{
"epoch": 0.62,
"learning_rate": 1.7414698162729658e-05,
"loss": 0.6858,
"step": 245
},
{
"epoch": 0.62,
"learning_rate": 1.740157480314961e-05,
"loss": 0.6897,
"step": 246
},
{
"epoch": 0.63,
"learning_rate": 1.7388451443569556e-05,
"loss": 0.6294,
"step": 247
},
{
"epoch": 0.63,
"learning_rate": 1.7375328083989503e-05,
"loss": 0.6608,
"step": 248
},
{
"epoch": 0.63,
"learning_rate": 1.736220472440945e-05,
"loss": 0.6644,
"step": 249
},
{
"epoch": 0.63,
"learning_rate": 1.7349081364829397e-05,
"loss": 0.6894,
"step": 250
},
{
"epoch": 0.64,
"learning_rate": 1.7335958005249344e-05,
"loss": 0.6826,
"step": 251
},
{
"epoch": 0.64,
"learning_rate": 1.7322834645669295e-05,
"loss": 0.719,
"step": 252
},
{
"epoch": 0.64,
"learning_rate": 1.7309711286089242e-05,
"loss": 0.7302,
"step": 253
},
{
"epoch": 0.64,
"learning_rate": 1.729658792650919e-05,
"loss": 0.7835,
"step": 254
},
{
"epoch": 0.65,
"learning_rate": 1.7283464566929136e-05,
"loss": 0.8102,
"step": 255
},
{
"epoch": 0.65,
"learning_rate": 1.7270341207349083e-05,
"loss": 0.7183,
"step": 256
},
{
"epoch": 0.65,
"learning_rate": 1.725721784776903e-05,
"loss": 0.7524,
"step": 257
},
{
"epoch": 0.66,
"learning_rate": 1.7244094488188977e-05,
"loss": 0.7385,
"step": 258
},
{
"epoch": 0.66,
"learning_rate": 1.7230971128608925e-05,
"loss": 0.7174,
"step": 259
},
{
"epoch": 0.66,
"learning_rate": 1.721784776902887e-05,
"loss": 0.6565,
"step": 260
},
{
"epoch": 0.66,
"learning_rate": 1.7204724409448822e-05,
"loss": 0.7028,
"step": 261
},
{
"epoch": 0.67,
"learning_rate": 1.7191601049868766e-05,
"loss": 0.6655,
"step": 262
},
{
"epoch": 0.67,
"learning_rate": 1.7178477690288716e-05,
"loss": 0.6893,
"step": 263
},
{
"epoch": 0.67,
"learning_rate": 1.7165354330708663e-05,
"loss": 0.6681,
"step": 264
},
{
"epoch": 0.67,
"learning_rate": 1.715223097112861e-05,
"loss": 0.6808,
"step": 265
},
{
"epoch": 0.68,
"learning_rate": 1.7139107611548558e-05,
"loss": 0.6594,
"step": 266
},
{
"epoch": 0.68,
"learning_rate": 1.7125984251968505e-05,
"loss": 0.7971,
"step": 267
},
{
"epoch": 0.68,
"learning_rate": 1.7112860892388452e-05,
"loss": 0.7395,
"step": 268
},
{
"epoch": 0.68,
"learning_rate": 1.70997375328084e-05,
"loss": 0.6938,
"step": 269
},
{
"epoch": 0.69,
"learning_rate": 1.708661417322835e-05,
"loss": 0.7269,
"step": 270
},
{
"epoch": 0.69,
"learning_rate": 1.7073490813648293e-05,
"loss": 0.6377,
"step": 271
},
{
"epoch": 0.69,
"learning_rate": 1.7060367454068244e-05,
"loss": 0.6876,
"step": 272
},
{
"epoch": 0.69,
"learning_rate": 1.704724409448819e-05,
"loss": 0.7468,
"step": 273
},
{
"epoch": 0.7,
"learning_rate": 1.7034120734908138e-05,
"loss": 0.7081,
"step": 274
},
{
"epoch": 0.7,
"learning_rate": 1.7020997375328085e-05,
"loss": 0.7155,
"step": 275
},
{
"epoch": 0.7,
"learning_rate": 1.7007874015748032e-05,
"loss": 0.7403,
"step": 276
},
{
"epoch": 0.7,
"learning_rate": 1.699475065616798e-05,
"loss": 0.7509,
"step": 277
},
{
"epoch": 0.71,
"learning_rate": 1.6981627296587927e-05,
"loss": 0.7691,
"step": 278
},
{
"epoch": 0.71,
"learning_rate": 1.6968503937007877e-05,
"loss": 0.6769,
"step": 279
},
{
"epoch": 0.71,
"learning_rate": 1.695538057742782e-05,
"loss": 0.7203,
"step": 280
},
{
"epoch": 0.71,
"learning_rate": 1.694225721784777e-05,
"loss": 0.6667,
"step": 281
},
{
"epoch": 0.72,
"learning_rate": 1.692913385826772e-05,
"loss": 0.6891,
"step": 282
},
{
"epoch": 0.72,
"learning_rate": 1.6916010498687665e-05,
"loss": 0.6798,
"step": 283
},
{
"epoch": 0.72,
"learning_rate": 1.6902887139107613e-05,
"loss": 0.6851,
"step": 284
},
{
"epoch": 0.72,
"learning_rate": 1.6889763779527563e-05,
"loss": 0.6759,
"step": 285
},
{
"epoch": 0.73,
"learning_rate": 1.6876640419947507e-05,
"loss": 0.704,
"step": 286
},
{
"epoch": 0.73,
"learning_rate": 1.6863517060367457e-05,
"loss": 0.6572,
"step": 287
},
{
"epoch": 0.73,
"learning_rate": 1.68503937007874e-05,
"loss": 0.7341,
"step": 288
},
{
"epoch": 0.73,
"learning_rate": 1.683727034120735e-05,
"loss": 0.7115,
"step": 289
},
{
"epoch": 0.74,
"learning_rate": 1.68241469816273e-05,
"loss": 0.7271,
"step": 290
},
{
"epoch": 0.74,
"learning_rate": 1.6811023622047246e-05,
"loss": 0.703,
"step": 291
},
{
"epoch": 0.74,
"learning_rate": 1.6797900262467193e-05,
"loss": 0.7439,
"step": 292
},
{
"epoch": 0.74,
"learning_rate": 1.678477690288714e-05,
"loss": 0.6744,
"step": 293
},
{
"epoch": 0.75,
"learning_rate": 1.6771653543307087e-05,
"loss": 0.7919,
"step": 294
},
{
"epoch": 0.75,
"learning_rate": 1.6758530183727034e-05,
"loss": 0.773,
"step": 295
},
{
"epoch": 0.75,
"learning_rate": 1.6745406824146985e-05,
"loss": 0.7258,
"step": 296
},
{
"epoch": 0.75,
"learning_rate": 1.673228346456693e-05,
"loss": 0.7358,
"step": 297
},
{
"epoch": 0.76,
"learning_rate": 1.671916010498688e-05,
"loss": 0.7336,
"step": 298
},
{
"epoch": 0.76,
"learning_rate": 1.6706036745406826e-05,
"loss": 0.6757,
"step": 299
},
{
"epoch": 0.76,
"learning_rate": 1.6692913385826773e-05,
"loss": 0.7411,
"step": 300
},
{
"epoch": 0.76,
"learning_rate": 1.667979002624672e-05,
"loss": 0.8021,
"step": 301
},
{
"epoch": 0.77,
"learning_rate": 1.6666666666666667e-05,
"loss": 0.7287,
"step": 302
},
{
"epoch": 0.77,
"learning_rate": 1.6653543307086615e-05,
"loss": 0.7613,
"step": 303
},
{
"epoch": 0.77,
"learning_rate": 1.6640419947506562e-05,
"loss": 0.8577,
"step": 304
},
{
"epoch": 0.77,
"learning_rate": 1.6627296587926512e-05,
"loss": 0.7202,
"step": 305
},
{
"epoch": 0.78,
"learning_rate": 1.6614173228346456e-05,
"loss": 0.7679,
"step": 306
},
{
"epoch": 0.78,
"learning_rate": 1.6601049868766406e-05,
"loss": 0.6743,
"step": 307
},
{
"epoch": 0.78,
"learning_rate": 1.6587926509186354e-05,
"loss": 0.7753,
"step": 308
},
{
"epoch": 0.78,
"learning_rate": 1.65748031496063e-05,
"loss": 0.7147,
"step": 309
},
{
"epoch": 0.79,
"learning_rate": 1.6561679790026248e-05,
"loss": 0.6653,
"step": 310
},
{
"epoch": 0.79,
"learning_rate": 1.6548556430446195e-05,
"loss": 0.6641,
"step": 311
},
{
"epoch": 0.79,
"learning_rate": 1.6535433070866142e-05,
"loss": 0.7154,
"step": 312
},
{
"epoch": 0.79,
"learning_rate": 1.6522309711286093e-05,
"loss": 0.7679,
"step": 313
},
{
"epoch": 0.8,
"learning_rate": 1.650918635170604e-05,
"loss": 0.6796,
"step": 314
},
{
"epoch": 0.8,
"learning_rate": 1.6496062992125987e-05,
"loss": 0.7906,
"step": 315
},
{
"epoch": 0.8,
"learning_rate": 1.6482939632545934e-05,
"loss": 0.6748,
"step": 316
},
{
"epoch": 0.8,
"learning_rate": 1.646981627296588e-05,
"loss": 0.6933,
"step": 317
},
{
"epoch": 0.81,
"learning_rate": 1.6456692913385828e-05,
"loss": 0.7913,
"step": 318
},
{
"epoch": 0.81,
"learning_rate": 1.6443569553805775e-05,
"loss": 0.7508,
"step": 319
},
{
"epoch": 0.81,
"learning_rate": 1.6430446194225722e-05,
"loss": 0.6814,
"step": 320
},
{
"epoch": 0.81,
"learning_rate": 1.641732283464567e-05,
"loss": 0.7016,
"step": 321
},
{
"epoch": 0.82,
"learning_rate": 1.640419947506562e-05,
"loss": 0.7073,
"step": 322
},
{
"epoch": 0.82,
"learning_rate": 1.6391076115485564e-05,
"loss": 0.7956,
"step": 323
},
{
"epoch": 0.82,
"learning_rate": 1.6377952755905514e-05,
"loss": 0.6889,
"step": 324
},
{
"epoch": 0.83,
"learning_rate": 1.636482939632546e-05,
"loss": 0.6842,
"step": 325
},
{
"epoch": 0.83,
"learning_rate": 1.635170603674541e-05,
"loss": 0.7083,
"step": 326
},
{
"epoch": 0.83,
"learning_rate": 1.6338582677165356e-05,
"loss": 0.695,
"step": 327
},
{
"epoch": 0.83,
"learning_rate": 1.6325459317585303e-05,
"loss": 0.6817,
"step": 328
},
{
"epoch": 0.84,
"learning_rate": 1.631233595800525e-05,
"loss": 0.6597,
"step": 329
},
{
"epoch": 0.84,
"learning_rate": 1.6299212598425197e-05,
"loss": 0.8122,
"step": 330
},
{
"epoch": 0.84,
"learning_rate": 1.6286089238845147e-05,
"loss": 0.7084,
"step": 331
},
{
"epoch": 0.84,
"learning_rate": 1.627296587926509e-05,
"loss": 0.6669,
"step": 332
},
{
"epoch": 0.85,
"learning_rate": 1.625984251968504e-05,
"loss": 0.7016,
"step": 333
},
{
"epoch": 0.85,
"learning_rate": 1.624671916010499e-05,
"loss": 0.6762,
"step": 334
},
{
"epoch": 0.85,
"learning_rate": 1.6233595800524936e-05,
"loss": 0.707,
"step": 335
},
{
"epoch": 0.85,
"learning_rate": 1.6220472440944883e-05,
"loss": 0.7484,
"step": 336
},
{
"epoch": 0.86,
"learning_rate": 1.620734908136483e-05,
"loss": 0.6942,
"step": 337
},
{
"epoch": 0.86,
"learning_rate": 1.6194225721784777e-05,
"loss": 0.657,
"step": 338
},
{
"epoch": 0.86,
"learning_rate": 1.6181102362204724e-05,
"loss": 0.7008,
"step": 339
},
{
"epoch": 0.86,
"learning_rate": 1.6167979002624675e-05,
"loss": 0.7285,
"step": 340
},
{
"epoch": 0.87,
"learning_rate": 1.615485564304462e-05,
"loss": 0.6876,
"step": 341
},
{
"epoch": 0.87,
"learning_rate": 1.614173228346457e-05,
"loss": 0.7145,
"step": 342
},
{
"epoch": 0.87,
"learning_rate": 1.6128608923884516e-05,
"loss": 0.6675,
"step": 343
},
{
"epoch": 0.87,
"learning_rate": 1.6115485564304463e-05,
"loss": 0.6565,
"step": 344
},
{
"epoch": 0.88,
"learning_rate": 1.610236220472441e-05,
"loss": 0.7392,
"step": 345
},
{
"epoch": 0.88,
"learning_rate": 1.608923884514436e-05,
"loss": 0.6847,
"step": 346
},
{
"epoch": 0.88,
"learning_rate": 1.6076115485564305e-05,
"loss": 0.6308,
"step": 347
},
{
"epoch": 0.88,
"learning_rate": 1.6062992125984255e-05,
"loss": 0.6739,
"step": 348
},
{
"epoch": 0.89,
"learning_rate": 1.6049868766404202e-05,
"loss": 0.645,
"step": 349
},
{
"epoch": 0.89,
"learning_rate": 1.603674540682415e-05,
"loss": 0.6569,
"step": 350
},
{
"epoch": 0.89,
"learning_rate": 1.6023622047244096e-05,
"loss": 0.8016,
"step": 351
},
{
"epoch": 0.89,
"learning_rate": 1.6010498687664044e-05,
"loss": 0.6679,
"step": 352
},
{
"epoch": 0.9,
"learning_rate": 1.599737532808399e-05,
"loss": 0.7299,
"step": 353
},
{
"epoch": 0.9,
"learning_rate": 1.5984251968503938e-05,
"loss": 0.6514,
"step": 354
},
{
"epoch": 0.9,
"learning_rate": 1.5971128608923885e-05,
"loss": 0.6613,
"step": 355
},
{
"epoch": 0.9,
"learning_rate": 1.5958005249343832e-05,
"loss": 0.6922,
"step": 356
},
{
"epoch": 0.91,
"learning_rate": 1.5944881889763783e-05,
"loss": 0.7856,
"step": 357
},
{
"epoch": 0.91,
"learning_rate": 1.5931758530183726e-05,
"loss": 0.7365,
"step": 358
},
{
"epoch": 0.91,
"learning_rate": 1.5918635170603677e-05,
"loss": 0.6569,
"step": 359
},
{
"epoch": 0.91,
"learning_rate": 1.5905511811023624e-05,
"loss": 0.7049,
"step": 360
},
{
"epoch": 0.92,
"learning_rate": 1.589238845144357e-05,
"loss": 0.7298,
"step": 361
},
{
"epoch": 0.92,
"learning_rate": 1.5879265091863518e-05,
"loss": 0.6846,
"step": 362
},
{
"epoch": 0.92,
"learning_rate": 1.5866141732283465e-05,
"loss": 0.6876,
"step": 363
},
{
"epoch": 0.92,
"learning_rate": 1.5853018372703412e-05,
"loss": 0.8115,
"step": 364
},
{
"epoch": 0.93,
"learning_rate": 1.583989501312336e-05,
"loss": 0.7524,
"step": 365
},
{
"epoch": 0.93,
"learning_rate": 1.582677165354331e-05,
"loss": 0.6977,
"step": 366
},
{
"epoch": 0.93,
"learning_rate": 1.5813648293963254e-05,
"loss": 0.7187,
"step": 367
},
{
"epoch": 0.93,
"learning_rate": 1.5800524934383204e-05,
"loss": 0.7026,
"step": 368
},
{
"epoch": 0.94,
"learning_rate": 1.578740157480315e-05,
"loss": 0.7194,
"step": 369
},
{
"epoch": 0.94,
"learning_rate": 1.57742782152231e-05,
"loss": 0.6877,
"step": 370
},
{
"epoch": 0.94,
"learning_rate": 1.5761154855643046e-05,
"loss": 0.8635,
"step": 371
},
{
"epoch": 0.94,
"learning_rate": 1.5748031496062993e-05,
"loss": 0.6863,
"step": 372
},
{
"epoch": 0.95,
"learning_rate": 1.573490813648294e-05,
"loss": 0.6409,
"step": 373
},
{
"epoch": 0.95,
"learning_rate": 1.5721784776902887e-05,
"loss": 0.7026,
"step": 374
},
{
"epoch": 0.95,
"learning_rate": 1.5708661417322837e-05,
"loss": 0.7152,
"step": 375
},
{
"epoch": 0.95,
"learning_rate": 1.5695538057742785e-05,
"loss": 0.6851,
"step": 376
},
{
"epoch": 0.96,
"learning_rate": 1.568241469816273e-05,
"loss": 0.7097,
"step": 377
},
{
"epoch": 0.96,
"learning_rate": 1.566929133858268e-05,
"loss": 0.6708,
"step": 378
},
{
"epoch": 0.96,
"learning_rate": 1.5656167979002626e-05,
"loss": 0.7262,
"step": 379
},
{
"epoch": 0.96,
"learning_rate": 1.5643044619422573e-05,
"loss": 0.692,
"step": 380
},
{
"epoch": 0.97,
"learning_rate": 1.5629921259842524e-05,
"loss": 0.7964,
"step": 381
},
{
"epoch": 0.97,
"learning_rate": 1.5616797900262467e-05,
"loss": 0.6485,
"step": 382
},
{
"epoch": 0.97,
"learning_rate": 1.5603674540682418e-05,
"loss": 0.6548,
"step": 383
},
{
"epoch": 0.97,
"learning_rate": 1.559055118110236e-05,
"loss": 0.7234,
"step": 384
},
{
"epoch": 0.98,
"learning_rate": 1.5577427821522312e-05,
"loss": 0.6184,
"step": 385
},
{
"epoch": 0.98,
"learning_rate": 1.556430446194226e-05,
"loss": 0.6784,
"step": 386
},
{
"epoch": 0.98,
"learning_rate": 1.5551181102362206e-05,
"loss": 0.6862,
"step": 387
},
{
"epoch": 0.99,
"learning_rate": 1.5538057742782153e-05,
"loss": 0.6898,
"step": 388
},
{
"epoch": 0.99,
"learning_rate": 1.55249343832021e-05,
"loss": 0.6877,
"step": 389
},
{
"epoch": 0.99,
"learning_rate": 1.5511811023622048e-05,
"loss": 0.63,
"step": 390
},
{
"epoch": 0.99,
"learning_rate": 1.5498687664041995e-05,
"loss": 0.7392,
"step": 391
},
{
"epoch": 1.0,
"learning_rate": 1.5485564304461945e-05,
"loss": 0.7621,
"step": 392
},
{
"epoch": 1.0,
"learning_rate": 1.547244094488189e-05,
"loss": 0.7172,
"step": 393
}
],
"logging_steps": 1.0,
"max_steps": 1572,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 500,
"total_flos": 1.063305153127383e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}