pranavSIT's picture
e20 added
9cfc379
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 20.0,
"eval_steps": 500,
"global_step": 840,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.02,
"learning_rate": 4.7619047619047623e-07,
"loss": 1.7249,
"step": 1
},
{
"epoch": 0.05,
"learning_rate": 9.523809523809525e-07,
"loss": 1.6668,
"step": 2
},
{
"epoch": 0.07,
"learning_rate": 1.4285714285714286e-06,
"loss": 1.6853,
"step": 3
},
{
"epoch": 0.1,
"learning_rate": 1.904761904761905e-06,
"loss": 1.7216,
"step": 4
},
{
"epoch": 0.12,
"learning_rate": 2.380952380952381e-06,
"loss": 1.6363,
"step": 5
},
{
"epoch": 0.14,
"learning_rate": 2.8571428571428573e-06,
"loss": 1.7242,
"step": 6
},
{
"epoch": 0.17,
"learning_rate": 3.3333333333333333e-06,
"loss": 1.71,
"step": 7
},
{
"epoch": 0.19,
"learning_rate": 3.80952380952381e-06,
"loss": 1.7635,
"step": 8
},
{
"epoch": 0.21,
"learning_rate": 4.2857142857142855e-06,
"loss": 1.7295,
"step": 9
},
{
"epoch": 0.24,
"learning_rate": 4.761904761904762e-06,
"loss": 1.7086,
"step": 10
},
{
"epoch": 0.26,
"learning_rate": 5.2380952380952384e-06,
"loss": 1.7307,
"step": 11
},
{
"epoch": 0.29,
"learning_rate": 5.7142857142857145e-06,
"loss": 1.7417,
"step": 12
},
{
"epoch": 0.31,
"learning_rate": 6.1904761904761914e-06,
"loss": 1.7345,
"step": 13
},
{
"epoch": 0.33,
"learning_rate": 6.666666666666667e-06,
"loss": 1.6883,
"step": 14
},
{
"epoch": 0.36,
"learning_rate": 7.1428571428571436e-06,
"loss": 1.6861,
"step": 15
},
{
"epoch": 0.38,
"learning_rate": 7.61904761904762e-06,
"loss": 1.7147,
"step": 16
},
{
"epoch": 0.4,
"learning_rate": 8.095238095238097e-06,
"loss": 1.7517,
"step": 17
},
{
"epoch": 0.43,
"learning_rate": 8.571428571428571e-06,
"loss": 1.6872,
"step": 18
},
{
"epoch": 0.45,
"learning_rate": 9.047619047619049e-06,
"loss": 1.7196,
"step": 19
},
{
"epoch": 0.48,
"learning_rate": 9.523809523809525e-06,
"loss": 1.6373,
"step": 20
},
{
"epoch": 0.5,
"learning_rate": 1e-05,
"loss": 1.6463,
"step": 21
},
{
"epoch": 0.52,
"learning_rate": 1.0476190476190477e-05,
"loss": 1.6902,
"step": 22
},
{
"epoch": 0.55,
"learning_rate": 1.0952380952380955e-05,
"loss": 1.6531,
"step": 23
},
{
"epoch": 0.57,
"learning_rate": 1.1428571428571429e-05,
"loss": 1.6366,
"step": 24
},
{
"epoch": 0.6,
"learning_rate": 1.1904761904761905e-05,
"loss": 1.665,
"step": 25
},
{
"epoch": 0.62,
"learning_rate": 1.2380952380952383e-05,
"loss": 1.5705,
"step": 26
},
{
"epoch": 0.64,
"learning_rate": 1.2857142857142859e-05,
"loss": 1.6188,
"step": 27
},
{
"epoch": 0.67,
"learning_rate": 1.3333333333333333e-05,
"loss": 1.6568,
"step": 28
},
{
"epoch": 0.69,
"learning_rate": 1.3809523809523811e-05,
"loss": 1.5702,
"step": 29
},
{
"epoch": 0.71,
"learning_rate": 1.4285714285714287e-05,
"loss": 1.5755,
"step": 30
},
{
"epoch": 0.74,
"learning_rate": 1.4761904761904763e-05,
"loss": 1.5817,
"step": 31
},
{
"epoch": 0.76,
"learning_rate": 1.523809523809524e-05,
"loss": 1.5441,
"step": 32
},
{
"epoch": 0.79,
"learning_rate": 1.5714285714285715e-05,
"loss": 1.6223,
"step": 33
},
{
"epoch": 0.81,
"learning_rate": 1.6190476190476193e-05,
"loss": 1.6135,
"step": 34
},
{
"epoch": 0.83,
"learning_rate": 1.6666666666666667e-05,
"loss": 1.5787,
"step": 35
},
{
"epoch": 0.86,
"learning_rate": 1.7142857142857142e-05,
"loss": 1.6007,
"step": 36
},
{
"epoch": 0.88,
"learning_rate": 1.761904761904762e-05,
"loss": 1.5691,
"step": 37
},
{
"epoch": 0.9,
"learning_rate": 1.8095238095238097e-05,
"loss": 1.5228,
"step": 38
},
{
"epoch": 0.93,
"learning_rate": 1.8571428571428575e-05,
"loss": 1.5104,
"step": 39
},
{
"epoch": 0.95,
"learning_rate": 1.904761904761905e-05,
"loss": 1.5337,
"step": 40
},
{
"epoch": 0.98,
"learning_rate": 1.9523809523809524e-05,
"loss": 1.5258,
"step": 41
},
{
"epoch": 1.0,
"learning_rate": 2e-05,
"loss": 1.5566,
"step": 42
},
{
"epoch": 1.02,
"learning_rate": 1.9999922506833706e-05,
"loss": 1.5089,
"step": 43
},
{
"epoch": 1.05,
"learning_rate": 1.9999690028535856e-05,
"loss": 1.5247,
"step": 44
},
{
"epoch": 1.07,
"learning_rate": 1.9999302568709548e-05,
"loss": 1.4854,
"step": 45
},
{
"epoch": 1.1,
"learning_rate": 1.9998760133359886e-05,
"loss": 1.485,
"step": 46
},
{
"epoch": 1.12,
"learning_rate": 1.9998062730893865e-05,
"loss": 1.4999,
"step": 47
},
{
"epoch": 1.14,
"learning_rate": 1.9997210372120276e-05,
"loss": 1.4542,
"step": 48
},
{
"epoch": 1.17,
"learning_rate": 1.9996203070249516e-05,
"loss": 1.4871,
"step": 49
},
{
"epoch": 1.19,
"learning_rate": 1.999504084089339e-05,
"loss": 1.4784,
"step": 50
},
{
"epoch": 1.21,
"learning_rate": 1.9993723702064852e-05,
"loss": 1.4403,
"step": 51
},
{
"epoch": 1.24,
"learning_rate": 1.9992251674177766e-05,
"loss": 1.448,
"step": 52
},
{
"epoch": 1.26,
"learning_rate": 1.999062478004655e-05,
"loss": 1.4367,
"step": 53
},
{
"epoch": 1.29,
"learning_rate": 1.998884304488584e-05,
"loss": 1.4361,
"step": 54
},
{
"epoch": 1.31,
"learning_rate": 1.998690649631009e-05,
"loss": 1.4114,
"step": 55
},
{
"epoch": 1.33,
"learning_rate": 1.9984815164333163e-05,
"loss": 1.4251,
"step": 56
},
{
"epoch": 1.36,
"learning_rate": 1.9982569081367844e-05,
"loss": 1.4494,
"step": 57
},
{
"epoch": 1.38,
"learning_rate": 1.998016828222535e-05,
"loss": 1.3464,
"step": 58
},
{
"epoch": 1.4,
"learning_rate": 1.997761280411478e-05,
"loss": 1.3714,
"step": 59
},
{
"epoch": 1.43,
"learning_rate": 1.997490268664256e-05,
"loss": 1.4056,
"step": 60
},
{
"epoch": 1.45,
"learning_rate": 1.9972037971811802e-05,
"loss": 1.4394,
"step": 61
},
{
"epoch": 1.48,
"learning_rate": 1.9969018704021677e-05,
"loss": 1.4287,
"step": 62
},
{
"epoch": 1.5,
"learning_rate": 1.99658449300667e-05,
"loss": 1.4253,
"step": 63
},
{
"epoch": 1.52,
"learning_rate": 1.9962516699136036e-05,
"loss": 1.3669,
"step": 64
},
{
"epoch": 1.55,
"learning_rate": 1.9959034062812714e-05,
"loss": 1.3652,
"step": 65
},
{
"epoch": 1.57,
"learning_rate": 1.995539707507284e-05,
"loss": 1.3716,
"step": 66
},
{
"epoch": 1.6,
"learning_rate": 1.9951605792284747e-05,
"loss": 1.3896,
"step": 67
},
{
"epoch": 1.62,
"learning_rate": 1.9947660273208135e-05,
"loss": 1.4071,
"step": 68
},
{
"epoch": 1.64,
"learning_rate": 1.994356057899317e-05,
"loss": 1.3848,
"step": 69
},
{
"epoch": 1.67,
"learning_rate": 1.9939306773179498e-05,
"loss": 1.2959,
"step": 70
},
{
"epoch": 1.69,
"learning_rate": 1.9934898921695296e-05,
"loss": 1.3269,
"step": 71
},
{
"epoch": 1.71,
"learning_rate": 1.9930337092856243e-05,
"loss": 1.3217,
"step": 72
},
{
"epoch": 1.74,
"learning_rate": 1.9925621357364446e-05,
"loss": 1.3787,
"step": 73
},
{
"epoch": 1.76,
"learning_rate": 1.9920751788307364e-05,
"loss": 1.3369,
"step": 74
},
{
"epoch": 1.79,
"learning_rate": 1.991572846115666e-05,
"loss": 1.447,
"step": 75
},
{
"epoch": 1.81,
"learning_rate": 1.9910551453767034e-05,
"loss": 1.3445,
"step": 76
},
{
"epoch": 1.83,
"learning_rate": 1.990522084637503e-05,
"loss": 1.3493,
"step": 77
},
{
"epoch": 1.86,
"learning_rate": 1.9899736721597787e-05,
"loss": 1.3385,
"step": 78
},
{
"epoch": 1.88,
"learning_rate": 1.9894099164431725e-05,
"loss": 1.3133,
"step": 79
},
{
"epoch": 1.9,
"learning_rate": 1.9888308262251286e-05,
"loss": 1.3586,
"step": 80
},
{
"epoch": 1.93,
"learning_rate": 1.9882364104807536e-05,
"loss": 1.3189,
"step": 81
},
{
"epoch": 1.95,
"learning_rate": 1.9876266784226798e-05,
"loss": 1.3558,
"step": 82
},
{
"epoch": 1.98,
"learning_rate": 1.9870016395009192e-05,
"loss": 1.3644,
"step": 83
},
{
"epoch": 2.0,
"learning_rate": 1.9863613034027224e-05,
"loss": 1.299,
"step": 84
},
{
"epoch": 2.02,
"learning_rate": 1.985705680052423e-05,
"loss": 1.3643,
"step": 85
},
{
"epoch": 2.05,
"learning_rate": 1.985034779611287e-05,
"loss": 1.3247,
"step": 86
},
{
"epoch": 2.07,
"learning_rate": 1.9843486124773546e-05,
"loss": 1.3183,
"step": 87
},
{
"epoch": 2.1,
"learning_rate": 1.9836471892852777e-05,
"loss": 1.3226,
"step": 88
},
{
"epoch": 2.12,
"learning_rate": 1.982930520906158e-05,
"loss": 1.3036,
"step": 89
},
{
"epoch": 2.14,
"learning_rate": 1.9821986184473757e-05,
"loss": 1.3249,
"step": 90
},
{
"epoch": 2.17,
"learning_rate": 1.981451493252418e-05,
"loss": 1.3252,
"step": 91
},
{
"epoch": 2.19,
"learning_rate": 1.980689156900705e-05,
"loss": 1.3145,
"step": 92
},
{
"epoch": 2.21,
"learning_rate": 1.9799116212074077e-05,
"loss": 1.2623,
"step": 93
},
{
"epoch": 2.24,
"learning_rate": 1.9791188982232672e-05,
"loss": 1.3382,
"step": 94
},
{
"epoch": 2.26,
"learning_rate": 1.9783110002344063e-05,
"loss": 1.3391,
"step": 95
},
{
"epoch": 2.29,
"learning_rate": 1.9774879397621387e-05,
"loss": 1.32,
"step": 96
},
{
"epoch": 2.31,
"learning_rate": 1.976649729562778e-05,
"loss": 1.3058,
"step": 97
},
{
"epoch": 2.33,
"learning_rate": 1.9757963826274357e-05,
"loss": 1.3443,
"step": 98
},
{
"epoch": 2.36,
"learning_rate": 1.9749279121818235e-05,
"loss": 1.2983,
"step": 99
},
{
"epoch": 2.38,
"learning_rate": 1.9740443316860466e-05,
"loss": 1.2629,
"step": 100
},
{
"epoch": 2.4,
"learning_rate": 1.9731456548343945e-05,
"loss": 1.2733,
"step": 101
},
{
"epoch": 2.43,
"learning_rate": 1.9722318955551307e-05,
"loss": 1.272,
"step": 102
},
{
"epoch": 2.45,
"learning_rate": 1.9713030680102748e-05,
"loss": 1.3342,
"step": 103
},
{
"epoch": 2.48,
"learning_rate": 1.9703591865953838e-05,
"loss": 1.3058,
"step": 104
},
{
"epoch": 2.5,
"learning_rate": 1.9694002659393306e-05,
"loss": 1.2888,
"step": 105
},
{
"epoch": 2.52,
"learning_rate": 1.968426320904074e-05,
"loss": 1.3077,
"step": 106
},
{
"epoch": 2.55,
"learning_rate": 1.9674373665844315e-05,
"loss": 1.2859,
"step": 107
},
{
"epoch": 2.57,
"learning_rate": 1.966433418307843e-05,
"loss": 1.2978,
"step": 108
},
{
"epoch": 2.6,
"learning_rate": 1.9654144916341346e-05,
"loss": 1.3177,
"step": 109
},
{
"epoch": 2.62,
"learning_rate": 1.964380602355277e-05,
"loss": 1.2866,
"step": 110
},
{
"epoch": 2.64,
"learning_rate": 1.9633317664951418e-05,
"loss": 1.2745,
"step": 111
},
{
"epoch": 2.67,
"learning_rate": 1.9622680003092503e-05,
"loss": 1.2743,
"step": 112
},
{
"epoch": 2.69,
"learning_rate": 1.9611893202845257e-05,
"loss": 1.3205,
"step": 113
},
{
"epoch": 2.71,
"learning_rate": 1.960095743139033e-05,
"loss": 1.2828,
"step": 114
},
{
"epoch": 2.74,
"learning_rate": 1.9589872858217235e-05,
"loss": 1.2762,
"step": 115
},
{
"epoch": 2.76,
"learning_rate": 1.9578639655121708e-05,
"loss": 1.2393,
"step": 116
},
{
"epoch": 2.79,
"learning_rate": 1.956725799620305e-05,
"loss": 1.287,
"step": 117
},
{
"epoch": 2.81,
"learning_rate": 1.955572805786141e-05,
"loss": 1.2784,
"step": 118
},
{
"epoch": 2.83,
"learning_rate": 1.9544050018795076e-05,
"loss": 1.2433,
"step": 119
},
{
"epoch": 2.86,
"learning_rate": 1.9532224059997693e-05,
"loss": 1.2649,
"step": 120
},
{
"epoch": 2.88,
"learning_rate": 1.9520250364755464e-05,
"loss": 1.2976,
"step": 121
},
{
"epoch": 2.9,
"learning_rate": 1.9508129118644294e-05,
"loss": 1.3154,
"step": 122
},
{
"epoch": 2.93,
"learning_rate": 1.9495860509526935e-05,
"loss": 1.2961,
"step": 123
},
{
"epoch": 2.95,
"learning_rate": 1.9483444727550057e-05,
"loss": 1.3231,
"step": 124
},
{
"epoch": 2.98,
"learning_rate": 1.9470881965141312e-05,
"loss": 1.2698,
"step": 125
},
{
"epoch": 3.0,
"learning_rate": 1.9458172417006347e-05,
"loss": 1.2846,
"step": 126
},
{
"epoch": 3.02,
"learning_rate": 1.9445316280125795e-05,
"loss": 1.2787,
"step": 127
},
{
"epoch": 3.05,
"learning_rate": 1.9432313753752193e-05,
"loss": 1.2474,
"step": 128
},
{
"epoch": 3.07,
"learning_rate": 1.941916503940694e-05,
"loss": 1.2743,
"step": 129
},
{
"epoch": 3.1,
"learning_rate": 1.940587034087714e-05,
"loss": 1.2299,
"step": 130
},
{
"epoch": 3.12,
"learning_rate": 1.9392429864212436e-05,
"loss": 1.2648,
"step": 131
},
{
"epoch": 3.14,
"learning_rate": 1.9378843817721856e-05,
"loss": 1.2697,
"step": 132
},
{
"epoch": 3.17,
"learning_rate": 1.936511241197055e-05,
"loss": 1.2637,
"step": 133
},
{
"epoch": 3.19,
"learning_rate": 1.9351235859776542e-05,
"loss": 1.286,
"step": 134
},
{
"epoch": 3.21,
"learning_rate": 1.9337214376207417e-05,
"loss": 1.2914,
"step": 135
},
{
"epoch": 3.24,
"learning_rate": 1.932304817857702e-05,
"loss": 1.2728,
"step": 136
},
{
"epoch": 3.26,
"learning_rate": 1.9308737486442045e-05,
"loss": 1.2341,
"step": 137
},
{
"epoch": 3.29,
"learning_rate": 1.929428252159866e-05,
"loss": 1.2742,
"step": 138
},
{
"epoch": 3.31,
"learning_rate": 1.9279683508079067e-05,
"loss": 1.2435,
"step": 139
},
{
"epoch": 3.33,
"learning_rate": 1.9264940672148018e-05,
"loss": 1.2091,
"step": 140
},
{
"epoch": 3.36,
"learning_rate": 1.925005424229933e-05,
"loss": 1.2686,
"step": 141
},
{
"epoch": 3.38,
"learning_rate": 1.9235024449252306e-05,
"loss": 1.2382,
"step": 142
},
{
"epoch": 3.4,
"learning_rate": 1.9219851525948207e-05,
"loss": 1.2649,
"step": 143
},
{
"epoch": 3.43,
"learning_rate": 1.9204535707546602e-05,
"loss": 1.2782,
"step": 144
},
{
"epoch": 3.45,
"learning_rate": 1.918907723142175e-05,
"loss": 1.2478,
"step": 145
},
{
"epoch": 3.48,
"learning_rate": 1.9173476337158893e-05,
"loss": 1.2985,
"step": 146
},
{
"epoch": 3.5,
"learning_rate": 1.9157733266550577e-05,
"loss": 1.2351,
"step": 147
},
{
"epoch": 3.52,
"learning_rate": 1.9141848263592874e-05,
"loss": 1.2874,
"step": 148
},
{
"epoch": 3.55,
"learning_rate": 1.9125821574481628e-05,
"loss": 1.2306,
"step": 149
},
{
"epoch": 3.57,
"learning_rate": 1.9109653447608607e-05,
"loss": 1.2419,
"step": 150
},
{
"epoch": 3.6,
"learning_rate": 1.9093344133557684e-05,
"loss": 1.3145,
"step": 151
},
{
"epoch": 3.62,
"learning_rate": 1.9076893885100937e-05,
"loss": 1.2776,
"step": 152
},
{
"epoch": 3.64,
"learning_rate": 1.9060302957194732e-05,
"loss": 1.3093,
"step": 153
},
{
"epoch": 3.67,
"learning_rate": 1.9043571606975776e-05,
"loss": 1.2889,
"step": 154
},
{
"epoch": 3.69,
"learning_rate": 1.902670009375713e-05,
"loss": 1.2411,
"step": 155
},
{
"epoch": 3.71,
"learning_rate": 1.900968867902419e-05,
"loss": 1.2557,
"step": 156
},
{
"epoch": 3.74,
"learning_rate": 1.899253762643064e-05,
"loss": 1.2669,
"step": 157
},
{
"epoch": 3.76,
"learning_rate": 1.8975247201794344e-05,
"loss": 1.2086,
"step": 158
},
{
"epoch": 3.79,
"learning_rate": 1.8957817673093258e-05,
"loss": 1.2865,
"step": 159
},
{
"epoch": 3.81,
"learning_rate": 1.8940249310461254e-05,
"loss": 1.2282,
"step": 160
},
{
"epoch": 3.83,
"learning_rate": 1.8922542386183942e-05,
"loss": 1.2008,
"step": 161
},
{
"epoch": 3.86,
"learning_rate": 1.8904697174694447e-05,
"loss": 1.2691,
"step": 162
},
{
"epoch": 3.88,
"learning_rate": 1.888671395256916e-05,
"loss": 1.2761,
"step": 163
},
{
"epoch": 3.9,
"learning_rate": 1.8868592998523437e-05,
"loss": 1.2645,
"step": 164
},
{
"epoch": 3.93,
"learning_rate": 1.885033459340731e-05,
"loss": 1.2403,
"step": 165
},
{
"epoch": 3.95,
"learning_rate": 1.8831939020201097e-05,
"loss": 1.2084,
"step": 166
},
{
"epoch": 3.98,
"learning_rate": 1.8813406564011045e-05,
"loss": 1.2032,
"step": 167
},
{
"epoch": 4.0,
"learning_rate": 1.879473751206489e-05,
"loss": 1.2396,
"step": 168
},
{
"epoch": 4.02,
"learning_rate": 1.877593215370743e-05,
"loss": 1.2452,
"step": 169
},
{
"epoch": 4.05,
"learning_rate": 1.875699078039601e-05,
"loss": 1.2117,
"step": 170
},
{
"epoch": 4.07,
"learning_rate": 1.873791368569603e-05,
"loss": 1.2061,
"step": 171
},
{
"epoch": 4.1,
"learning_rate": 1.8718701165276386e-05,
"loss": 1.2322,
"step": 172
},
{
"epoch": 4.12,
"learning_rate": 1.8699353516904882e-05,
"loss": 1.1995,
"step": 173
},
{
"epoch": 4.14,
"learning_rate": 1.8679871040443632e-05,
"loss": 1.1931,
"step": 174
},
{
"epoch": 4.17,
"learning_rate": 1.866025403784439e-05,
"loss": 1.2559,
"step": 175
},
{
"epoch": 4.19,
"learning_rate": 1.864050281314388e-05,
"loss": 1.2158,
"step": 176
},
{
"epoch": 4.21,
"learning_rate": 1.8620617672459097e-05,
"loss": 1.2317,
"step": 177
},
{
"epoch": 4.24,
"learning_rate": 1.860059892398254e-05,
"loss": 1.2378,
"step": 178
},
{
"epoch": 4.26,
"learning_rate": 1.858044687797745e-05,
"loss": 1.2125,
"step": 179
},
{
"epoch": 4.29,
"learning_rate": 1.8560161846773002e-05,
"loss": 1.1897,
"step": 180
},
{
"epoch": 4.31,
"learning_rate": 1.853974414475945e-05,
"loss": 1.1718,
"step": 181
},
{
"epoch": 4.33,
"learning_rate": 1.851919408838327e-05,
"loss": 1.2464,
"step": 182
},
{
"epoch": 4.36,
"learning_rate": 1.8498511996142255e-05,
"loss": 1.2314,
"step": 183
},
{
"epoch": 4.38,
"learning_rate": 1.8477698188580558e-05,
"loss": 1.2439,
"step": 184
},
{
"epoch": 4.4,
"learning_rate": 1.845675298828376e-05,
"loss": 1.2274,
"step": 185
},
{
"epoch": 4.43,
"learning_rate": 1.8435676719873828e-05,
"loss": 1.2263,
"step": 186
},
{
"epoch": 4.45,
"learning_rate": 1.8414469710004124e-05,
"loss": 1.2215,
"step": 187
},
{
"epoch": 4.48,
"learning_rate": 1.8393132287354314e-05,
"loss": 1.262,
"step": 188
},
{
"epoch": 4.5,
"learning_rate": 1.8371664782625287e-05,
"loss": 1.2341,
"step": 189
},
{
"epoch": 4.52,
"learning_rate": 1.8350067528534026e-05,
"loss": 1.2126,
"step": 190
},
{
"epoch": 4.55,
"learning_rate": 1.832834085980845e-05,
"loss": 1.2043,
"step": 191
},
{
"epoch": 4.57,
"learning_rate": 1.830648511318223e-05,
"loss": 1.2146,
"step": 192
},
{
"epoch": 4.6,
"learning_rate": 1.828450062738957e-05,
"loss": 1.2319,
"step": 193
},
{
"epoch": 4.62,
"learning_rate": 1.826238774315995e-05,
"loss": 1.2319,
"step": 194
},
{
"epoch": 4.64,
"learning_rate": 1.8240146803212854e-05,
"loss": 1.2312,
"step": 195
},
{
"epoch": 4.67,
"learning_rate": 1.821777815225245e-05,
"loss": 1.2191,
"step": 196
},
{
"epoch": 4.69,
"learning_rate": 1.8195282136962266e-05,
"loss": 1.2829,
"step": 197
},
{
"epoch": 4.71,
"learning_rate": 1.817265910599978e-05,
"loss": 1.2105,
"step": 198
},
{
"epoch": 4.74,
"learning_rate": 1.8149909409991063e-05,
"loss": 1.2585,
"step": 199
},
{
"epoch": 4.76,
"learning_rate": 1.81270334015253e-05,
"loss": 1.2172,
"step": 200
},
{
"epoch": 4.79,
"learning_rate": 1.8104031435149366e-05,
"loss": 1.2689,
"step": 201
},
{
"epoch": 4.81,
"learning_rate": 1.8080903867362297e-05,
"loss": 1.25,
"step": 202
},
{
"epoch": 4.83,
"learning_rate": 1.8057651056609784e-05,
"loss": 1.2011,
"step": 203
},
{
"epoch": 4.86,
"learning_rate": 1.8034273363278615e-05,
"loss": 1.2261,
"step": 204
},
{
"epoch": 4.88,
"learning_rate": 1.8010771149691086e-05,
"loss": 1.1972,
"step": 205
},
{
"epoch": 4.9,
"learning_rate": 1.798714478009938e-05,
"loss": 1.2357,
"step": 206
},
{
"epoch": 4.93,
"learning_rate": 1.7963394620679945e-05,
"loss": 1.2283,
"step": 207
},
{
"epoch": 4.95,
"learning_rate": 1.7939521039527783e-05,
"loss": 1.2832,
"step": 208
},
{
"epoch": 4.98,
"learning_rate": 1.7915524406650778e-05,
"loss": 1.2123,
"step": 209
},
{
"epoch": 5.0,
"learning_rate": 1.789140509396394e-05,
"loss": 1.1928,
"step": 210
},
{
"epoch": 5.02,
"learning_rate": 1.7867163475283647e-05,
"loss": 1.1707,
"step": 211
},
{
"epoch": 5.05,
"learning_rate": 1.7842799926321867e-05,
"loss": 1.2545,
"step": 212
},
{
"epoch": 5.07,
"learning_rate": 1.78183148246803e-05,
"loss": 1.1989,
"step": 213
},
{
"epoch": 5.1,
"learning_rate": 1.779370854984456e-05,
"loss": 1.2443,
"step": 214
},
{
"epoch": 5.12,
"learning_rate": 1.776898148317828e-05,
"loss": 1.2468,
"step": 215
},
{
"epoch": 5.14,
"learning_rate": 1.7744134007917195e-05,
"loss": 1.2006,
"step": 216
},
{
"epoch": 5.17,
"learning_rate": 1.771916650916321e-05,
"loss": 1.2375,
"step": 217
},
{
"epoch": 5.19,
"learning_rate": 1.7694079373878435e-05,
"loss": 1.2188,
"step": 218
},
{
"epoch": 5.21,
"learning_rate": 1.7668872990879175e-05,
"loss": 1.1965,
"step": 219
},
{
"epoch": 5.24,
"learning_rate": 1.764354775082992e-05,
"loss": 1.1947,
"step": 220
},
{
"epoch": 5.26,
"learning_rate": 1.7618104046237276e-05,
"loss": 1.2187,
"step": 221
},
{
"epoch": 5.29,
"learning_rate": 1.7592542271443888e-05,
"loss": 1.1422,
"step": 222
},
{
"epoch": 5.31,
"learning_rate": 1.756686282262233e-05,
"loss": 1.1965,
"step": 223
},
{
"epoch": 5.33,
"learning_rate": 1.7541066097768965e-05,
"loss": 1.1757,
"step": 224
},
{
"epoch": 5.36,
"learning_rate": 1.7515152496697765e-05,
"loss": 1.2078,
"step": 225
},
{
"epoch": 5.38,
"learning_rate": 1.7489122421034134e-05,
"loss": 1.2014,
"step": 226
},
{
"epoch": 5.4,
"learning_rate": 1.7462976274208664e-05,
"loss": 1.1898,
"step": 227
},
{
"epoch": 5.43,
"learning_rate": 1.74367144614509e-05,
"loss": 1.1803,
"step": 228
},
{
"epoch": 5.45,
"learning_rate": 1.7410337389783044e-05,
"loss": 1.2173,
"step": 229
},
{
"epoch": 5.48,
"learning_rate": 1.7383845468013656e-05,
"loss": 1.1621,
"step": 230
},
{
"epoch": 5.5,
"learning_rate": 1.735723910673132e-05,
"loss": 1.1896,
"step": 231
},
{
"epoch": 5.52,
"learning_rate": 1.7330518718298263e-05,
"loss": 1.159,
"step": 232
},
{
"epoch": 5.55,
"learning_rate": 1.7303684716843998e-05,
"loss": 1.2068,
"step": 233
},
{
"epoch": 5.57,
"learning_rate": 1.7276737518258865e-05,
"loss": 1.2127,
"step": 234
},
{
"epoch": 5.6,
"learning_rate": 1.724967754018761e-05,
"loss": 1.1941,
"step": 235
},
{
"epoch": 5.62,
"learning_rate": 1.7222505202022915e-05,
"loss": 1.1612,
"step": 236
},
{
"epoch": 5.64,
"learning_rate": 1.7195220924898883e-05,
"loss": 1.2,
"step": 237
},
{
"epoch": 5.67,
"learning_rate": 1.7167825131684516e-05,
"loss": 1.1809,
"step": 238
},
{
"epoch": 5.69,
"learning_rate": 1.7140318246977167e-05,
"loss": 1.1858,
"step": 239
},
{
"epoch": 5.71,
"learning_rate": 1.7112700697095955e-05,
"loss": 1.2046,
"step": 240
},
{
"epoch": 5.74,
"learning_rate": 1.7084972910075156e-05,
"loss": 1.2101,
"step": 241
},
{
"epoch": 5.76,
"learning_rate": 1.705713531565757e-05,
"loss": 1.1582,
"step": 242
},
{
"epoch": 5.79,
"learning_rate": 1.7029188345287868e-05,
"loss": 1.2222,
"step": 243
},
{
"epoch": 5.81,
"learning_rate": 1.7001132432105896e-05,
"loss": 1.195,
"step": 244
},
{
"epoch": 5.83,
"learning_rate": 1.6972968010939953e-05,
"loss": 1.2012,
"step": 245
},
{
"epoch": 5.86,
"learning_rate": 1.6944695518300087e-05,
"loss": 1.229,
"step": 246
},
{
"epoch": 5.88,
"learning_rate": 1.6916315392371286e-05,
"loss": 1.2098,
"step": 247
},
{
"epoch": 5.9,
"learning_rate": 1.6887828073006713e-05,
"loss": 1.1405,
"step": 248
},
{
"epoch": 5.93,
"learning_rate": 1.6859234001720882e-05,
"loss": 1.2028,
"step": 249
},
{
"epoch": 5.95,
"learning_rate": 1.6830533621682825e-05,
"loss": 1.199,
"step": 250
},
{
"epoch": 5.98,
"learning_rate": 1.6801727377709195e-05,
"loss": 1.1794,
"step": 251
},
{
"epoch": 6.0,
"learning_rate": 1.6772815716257414e-05,
"loss": 1.1271,
"step": 252
},
{
"epoch": 6.02,
"learning_rate": 1.674379908541871e-05,
"loss": 1.1272,
"step": 253
},
{
"epoch": 6.05,
"learning_rate": 1.671467793491121e-05,
"loss": 1.1773,
"step": 254
},
{
"epoch": 6.07,
"learning_rate": 1.6685452716072946e-05,
"loss": 1.1242,
"step": 255
},
{
"epoch": 6.1,
"learning_rate": 1.665612388185486e-05,
"loss": 1.2029,
"step": 256
},
{
"epoch": 6.12,
"learning_rate": 1.6626691886813806e-05,
"loss": 1.1826,
"step": 257
},
{
"epoch": 6.14,
"learning_rate": 1.6597157187105475e-05,
"loss": 1.1481,
"step": 258
},
{
"epoch": 6.17,
"learning_rate": 1.6567520240477344e-05,
"loss": 1.1863,
"step": 259
},
{
"epoch": 6.19,
"learning_rate": 1.6537781506261588e-05,
"loss": 1.173,
"step": 260
},
{
"epoch": 6.21,
"learning_rate": 1.6507941445367935e-05,
"loss": 1.184,
"step": 261
},
{
"epoch": 6.24,
"learning_rate": 1.6478000520276554e-05,
"loss": 1.2008,
"step": 262
},
{
"epoch": 6.26,
"learning_rate": 1.644795919503085e-05,
"loss": 1.1658,
"step": 263
},
{
"epoch": 6.29,
"learning_rate": 1.6417817935230318e-05,
"loss": 1.2031,
"step": 264
},
{
"epoch": 6.31,
"learning_rate": 1.6387577208023278e-05,
"loss": 1.1583,
"step": 265
},
{
"epoch": 6.33,
"learning_rate": 1.6357237482099682e-05,
"loss": 1.1689,
"step": 266
},
{
"epoch": 6.36,
"learning_rate": 1.6326799227683806e-05,
"loss": 1.1765,
"step": 267
},
{
"epoch": 6.38,
"learning_rate": 1.6296262916526998e-05,
"loss": 1.1626,
"step": 268
},
{
"epoch": 6.4,
"learning_rate": 1.6265629021900343e-05,
"loss": 1.134,
"step": 269
},
{
"epoch": 6.43,
"learning_rate": 1.6234898018587336e-05,
"loss": 1.1654,
"step": 270
},
{
"epoch": 6.45,
"learning_rate": 1.6204070382876535e-05,
"loss": 1.1759,
"step": 271
},
{
"epoch": 6.48,
"learning_rate": 1.6173146592554155e-05,
"loss": 1.181,
"step": 272
},
{
"epoch": 6.5,
"learning_rate": 1.6142127126896682e-05,
"loss": 1.2101,
"step": 273
},
{
"epoch": 6.52,
"learning_rate": 1.6111012466663436e-05,
"loss": 1.2014,
"step": 274
},
{
"epoch": 6.55,
"learning_rate": 1.6079803094089128e-05,
"loss": 1.1889,
"step": 275
},
{
"epoch": 6.57,
"learning_rate": 1.6048499492876378e-05,
"loss": 1.1341,
"step": 276
},
{
"epoch": 6.6,
"learning_rate": 1.6017102148188216e-05,
"loss": 1.1401,
"step": 277
},
{
"epoch": 6.62,
"learning_rate": 1.598561154664058e-05,
"loss": 1.1377,
"step": 278
},
{
"epoch": 6.64,
"learning_rate": 1.595402817629475e-05,
"loss": 1.1575,
"step": 279
},
{
"epoch": 6.67,
"learning_rate": 1.5922352526649803e-05,
"loss": 1.1373,
"step": 280
},
{
"epoch": 6.69,
"learning_rate": 1.589058508863501e-05,
"loss": 1.2003,
"step": 281
},
{
"epoch": 6.71,
"learning_rate": 1.5858726354602248e-05,
"loss": 1.1796,
"step": 282
},
{
"epoch": 6.74,
"learning_rate": 1.582677681831835e-05,
"loss": 1.1885,
"step": 283
},
{
"epoch": 6.76,
"learning_rate": 1.5794736974957465e-05,
"loss": 1.1524,
"step": 284
},
{
"epoch": 6.79,
"learning_rate": 1.5762607321093368e-05,
"loss": 1.1674,
"step": 285
},
{
"epoch": 6.81,
"learning_rate": 1.573038835469179e-05,
"loss": 1.132,
"step": 286
},
{
"epoch": 6.83,
"learning_rate": 1.5698080575102662e-05,
"loss": 1.1613,
"step": 287
},
{
"epoch": 6.86,
"learning_rate": 1.5665684483052425e-05,
"loss": 1.176,
"step": 288
},
{
"epoch": 6.88,
"learning_rate": 1.563320058063622e-05,
"loss": 1.1631,
"step": 289
},
{
"epoch": 6.9,
"learning_rate": 1.5600629371310144e-05,
"loss": 1.1557,
"step": 290
},
{
"epoch": 6.93,
"learning_rate": 1.556797135988342e-05,
"loss": 1.2318,
"step": 291
},
{
"epoch": 6.95,
"learning_rate": 1.553522705251059e-05,
"loss": 1.1954,
"step": 292
},
{
"epoch": 6.98,
"learning_rate": 1.550239695668367e-05,
"loss": 1.139,
"step": 293
},
{
"epoch": 7.0,
"learning_rate": 1.5469481581224274e-05,
"loss": 1.1106,
"step": 294
},
{
"epoch": 7.02,
"learning_rate": 1.5436481436275726e-05,
"loss": 1.1347,
"step": 295
},
{
"epoch": 7.05,
"learning_rate": 1.540339703329518e-05,
"loss": 1.1467,
"step": 296
},
{
"epoch": 7.07,
"learning_rate": 1.5370228885045662e-05,
"loss": 1.1331,
"step": 297
},
{
"epoch": 7.1,
"learning_rate": 1.5336977505588135e-05,
"loss": 1.1193,
"step": 298
},
{
"epoch": 7.12,
"learning_rate": 1.5303643410273542e-05,
"loss": 1.167,
"step": 299
},
{
"epoch": 7.14,
"learning_rate": 1.527022711573479e-05,
"loss": 1.098,
"step": 300
},
{
"epoch": 7.17,
"learning_rate": 1.523672913987878e-05,
"loss": 1.1647,
"step": 301
},
{
"epoch": 7.19,
"learning_rate": 1.5203150001878355e-05,
"loss": 1.1498,
"step": 302
},
{
"epoch": 7.21,
"learning_rate": 1.5169490222164255e-05,
"loss": 1.1326,
"step": 303
},
{
"epoch": 7.24,
"learning_rate": 1.5135750322417069e-05,
"loss": 1.1118,
"step": 304
},
{
"epoch": 7.26,
"learning_rate": 1.5101930825559126e-05,
"loss": 1.1362,
"step": 305
},
{
"epoch": 7.29,
"learning_rate": 1.50680322557464e-05,
"loss": 1.1381,
"step": 306
},
{
"epoch": 7.31,
"learning_rate": 1.50340551383604e-05,
"loss": 1.1681,
"step": 307
},
{
"epoch": 7.33,
"learning_rate": 1.5000000000000002e-05,
"loss": 1.1504,
"step": 308
},
{
"epoch": 7.36,
"learning_rate": 1.4965867368473308e-05,
"loss": 1.1532,
"step": 309
},
{
"epoch": 7.38,
"learning_rate": 1.4931657772789458e-05,
"loss": 1.1541,
"step": 310
},
{
"epoch": 7.4,
"learning_rate": 1.4897371743150426e-05,
"loss": 1.1515,
"step": 311
},
{
"epoch": 7.43,
"learning_rate": 1.4863009810942814e-05,
"loss": 1.0962,
"step": 312
},
{
"epoch": 7.45,
"learning_rate": 1.4828572508729608e-05,
"loss": 1.1767,
"step": 313
},
{
"epoch": 7.48,
"learning_rate": 1.4794060370241923e-05,
"loss": 1.1498,
"step": 314
},
{
"epoch": 7.5,
"learning_rate": 1.4759473930370738e-05,
"loss": 1.1088,
"step": 315
},
{
"epoch": 7.52,
"learning_rate": 1.4724813725158598e-05,
"loss": 1.1688,
"step": 316
},
{
"epoch": 7.55,
"learning_rate": 1.4690080291791313e-05,
"loss": 1.15,
"step": 317
},
{
"epoch": 7.57,
"learning_rate": 1.4655274168589635e-05,
"loss": 1.1528,
"step": 318
},
{
"epoch": 7.6,
"learning_rate": 1.4620395895000892e-05,
"loss": 1.1977,
"step": 319
},
{
"epoch": 7.62,
"learning_rate": 1.458544601159066e-05,
"loss": 1.0661,
"step": 320
},
{
"epoch": 7.64,
"learning_rate": 1.4550425060034367e-05,
"loss": 1.1478,
"step": 321
},
{
"epoch": 7.67,
"learning_rate": 1.4515333583108896e-05,
"loss": 1.0997,
"step": 322
},
{
"epoch": 7.69,
"learning_rate": 1.4480172124684174e-05,
"loss": 1.1422,
"step": 323
},
{
"epoch": 7.71,
"learning_rate": 1.444494122971476e-05,
"loss": 1.1115,
"step": 324
},
{
"epoch": 7.74,
"learning_rate": 1.4409641444231361e-05,
"loss": 1.1642,
"step": 325
},
{
"epoch": 7.76,
"learning_rate": 1.4374273315332416e-05,
"loss": 1.1625,
"step": 326
},
{
"epoch": 7.79,
"learning_rate": 1.4338837391175582e-05,
"loss": 1.161,
"step": 327
},
{
"epoch": 7.81,
"learning_rate": 1.4303334220969251e-05,
"loss": 1.1108,
"step": 328
},
{
"epoch": 7.83,
"learning_rate": 1.4267764354964038e-05,
"loss": 1.1111,
"step": 329
},
{
"epoch": 7.86,
"learning_rate": 1.4232128344444251e-05,
"loss": 1.1177,
"step": 330
},
{
"epoch": 7.88,
"learning_rate": 1.4196426741719347e-05,
"loss": 1.1399,
"step": 331
},
{
"epoch": 7.9,
"learning_rate": 1.4160660100115375e-05,
"loss": 1.1928,
"step": 332
},
{
"epoch": 7.93,
"learning_rate": 1.4124828973966393e-05,
"loss": 1.1203,
"step": 333
},
{
"epoch": 7.95,
"learning_rate": 1.408893391860589e-05,
"loss": 1.1514,
"step": 334
},
{
"epoch": 7.98,
"learning_rate": 1.405297549035816e-05,
"loss": 1.1374,
"step": 335
},
{
"epoch": 8.0,
"learning_rate": 1.4016954246529697e-05,
"loss": 1.1419,
"step": 336
},
{
"epoch": 8.02,
"learning_rate": 1.3980870745400545e-05,
"loss": 1.0785,
"step": 337
},
{
"epoch": 8.05,
"learning_rate": 1.3944725546215665e-05,
"loss": 1.054,
"step": 338
},
{
"epoch": 8.07,
"learning_rate": 1.3908519209176227e-05,
"loss": 1.1491,
"step": 339
},
{
"epoch": 8.1,
"learning_rate": 1.3872252295430989e-05,
"loss": 1.1443,
"step": 340
},
{
"epoch": 8.12,
"learning_rate": 1.383592536706753e-05,
"loss": 1.1208,
"step": 341
},
{
"epoch": 8.14,
"learning_rate": 1.37995389871036e-05,
"loss": 1.0666,
"step": 342
},
{
"epoch": 8.17,
"learning_rate": 1.3763093719478357e-05,
"loss": 1.0772,
"step": 343
},
{
"epoch": 8.19,
"learning_rate": 1.3726590129043632e-05,
"loss": 1.1602,
"step": 344
},
{
"epoch": 8.21,
"learning_rate": 1.369002878155519e-05,
"loss": 1.1417,
"step": 345
},
{
"epoch": 8.24,
"learning_rate": 1.3653410243663953e-05,
"loss": 1.1424,
"step": 346
},
{
"epoch": 8.26,
"learning_rate": 1.3616735082907197e-05,
"loss": 1.0739,
"step": 347
},
{
"epoch": 8.29,
"learning_rate": 1.3580003867699801e-05,
"loss": 1.0881,
"step": 348
},
{
"epoch": 8.31,
"learning_rate": 1.3543217167325388e-05,
"loss": 1.1127,
"step": 349
},
{
"epoch": 8.33,
"learning_rate": 1.3506375551927546e-05,
"loss": 1.1271,
"step": 350
},
{
"epoch": 8.36,
"learning_rate": 1.3469479592500954e-05,
"loss": 1.1261,
"step": 351
},
{
"epoch": 8.38,
"learning_rate": 1.3432529860882558e-05,
"loss": 1.1453,
"step": 352
},
{
"epoch": 8.4,
"learning_rate": 1.3395526929742693e-05,
"loss": 1.1458,
"step": 353
},
{
"epoch": 8.43,
"learning_rate": 1.3358471372576229e-05,
"loss": 1.1292,
"step": 354
},
{
"epoch": 8.45,
"learning_rate": 1.3321363763693645e-05,
"loss": 1.0959,
"step": 355
},
{
"epoch": 8.48,
"learning_rate": 1.3284204678212169e-05,
"loss": 1.0748,
"step": 356
},
{
"epoch": 8.5,
"learning_rate": 1.3246994692046837e-05,
"loss": 1.0848,
"step": 357
},
{
"epoch": 8.52,
"learning_rate": 1.320973438190158e-05,
"loss": 1.1551,
"step": 358
},
{
"epoch": 8.55,
"learning_rate": 1.3172424325260274e-05,
"loss": 1.1393,
"step": 359
},
{
"epoch": 8.57,
"learning_rate": 1.3135065100377816e-05,
"loss": 1.1039,
"step": 360
},
{
"epoch": 8.6,
"learning_rate": 1.3097657286271118e-05,
"loss": 1.1396,
"step": 361
},
{
"epoch": 8.62,
"learning_rate": 1.3060201462710177e-05,
"loss": 1.0917,
"step": 362
},
{
"epoch": 8.64,
"learning_rate": 1.3022698210209069e-05,
"loss": 1.1137,
"step": 363
},
{
"epoch": 8.67,
"learning_rate": 1.2985148110016947e-05,
"loss": 1.1389,
"step": 364
},
{
"epoch": 8.69,
"learning_rate": 1.2947551744109044e-05,
"loss": 1.0677,
"step": 365
},
{
"epoch": 8.71,
"learning_rate": 1.2909909695177647e-05,
"loss": 1.1507,
"step": 366
},
{
"epoch": 8.74,
"learning_rate": 1.2872222546623065e-05,
"loss": 1.0752,
"step": 367
},
{
"epoch": 8.76,
"learning_rate": 1.2834490882544598e-05,
"loss": 1.0794,
"step": 368
},
{
"epoch": 8.79,
"learning_rate": 1.2796715287731463e-05,
"loss": 1.0454,
"step": 369
},
{
"epoch": 8.81,
"learning_rate": 1.2758896347653753e-05,
"loss": 1.0855,
"step": 370
},
{
"epoch": 8.83,
"learning_rate": 1.2721034648453353e-05,
"loss": 1.1525,
"step": 371
},
{
"epoch": 8.86,
"learning_rate": 1.268313077693485e-05,
"loss": 1.1405,
"step": 372
},
{
"epoch": 8.88,
"learning_rate": 1.2645185320556445e-05,
"loss": 1.1011,
"step": 373
},
{
"epoch": 8.9,
"learning_rate": 1.260719886742086e-05,
"loss": 1.1069,
"step": 374
},
{
"epoch": 8.93,
"learning_rate": 1.2569172006266192e-05,
"loss": 1.1229,
"step": 375
},
{
"epoch": 8.95,
"learning_rate": 1.2531105326456821e-05,
"loss": 1.1207,
"step": 376
},
{
"epoch": 8.98,
"learning_rate": 1.2492999417974253e-05,
"loss": 1.1077,
"step": 377
},
{
"epoch": 9.0,
"learning_rate": 1.2454854871407993e-05,
"loss": 1.0399,
"step": 378
},
{
"epoch": 9.02,
"learning_rate": 1.2416672277946375e-05,
"loss": 1.0753,
"step": 379
},
{
"epoch": 9.05,
"learning_rate": 1.2378452229367415e-05,
"loss": 1.0189,
"step": 380
},
{
"epoch": 9.07,
"learning_rate": 1.2340195318029623e-05,
"loss": 1.0859,
"step": 381
},
{
"epoch": 9.1,
"learning_rate": 1.2301902136862849e-05,
"loss": 1.1172,
"step": 382
},
{
"epoch": 9.12,
"learning_rate": 1.2263573279359054e-05,
"loss": 1.05,
"step": 383
},
{
"epoch": 9.14,
"learning_rate": 1.2225209339563144e-05,
"loss": 1.0992,
"step": 384
},
{
"epoch": 9.17,
"learning_rate": 1.218681091206376e-05,
"loss": 1.0926,
"step": 385
},
{
"epoch": 9.19,
"learning_rate": 1.2148378591984041e-05,
"loss": 1.0712,
"step": 386
},
{
"epoch": 9.21,
"learning_rate": 1.2109912974972424e-05,
"loss": 1.064,
"step": 387
},
{
"epoch": 9.24,
"learning_rate": 1.2071414657193397e-05,
"loss": 1.1093,
"step": 388
},
{
"epoch": 9.26,
"learning_rate": 1.203288423531827e-05,
"loss": 1.1061,
"step": 389
},
{
"epoch": 9.29,
"learning_rate": 1.1994322306515926e-05,
"loss": 1.1004,
"step": 390
},
{
"epoch": 9.31,
"learning_rate": 1.1955729468443546e-05,
"loss": 1.1072,
"step": 391
},
{
"epoch": 9.33,
"learning_rate": 1.1917106319237386e-05,
"loss": 1.0631,
"step": 392
},
{
"epoch": 9.36,
"learning_rate": 1.1878453457503465e-05,
"loss": 1.1143,
"step": 393
},
{
"epoch": 9.38,
"learning_rate": 1.183977148230831e-05,
"loss": 1.0769,
"step": 394
},
{
"epoch": 9.4,
"learning_rate": 1.1801060993169668e-05,
"loss": 1.0898,
"step": 395
},
{
"epoch": 9.43,
"learning_rate": 1.176232259004722e-05,
"loss": 1.0284,
"step": 396
},
{
"epoch": 9.45,
"learning_rate": 1.1723556873333261e-05,
"loss": 1.0935,
"step": 397
},
{
"epoch": 9.48,
"learning_rate": 1.1684764443843421e-05,
"loss": 1.0683,
"step": 398
},
{
"epoch": 9.5,
"learning_rate": 1.164594590280734e-05,
"loss": 1.0501,
"step": 399
},
{
"epoch": 9.52,
"learning_rate": 1.1607101851859347e-05,
"loss": 1.1211,
"step": 400
},
{
"epoch": 9.55,
"learning_rate": 1.1568232893029142e-05,
"loss": 1.0902,
"step": 401
},
{
"epoch": 9.57,
"learning_rate": 1.1529339628732462e-05,
"loss": 1.0446,
"step": 402
},
{
"epoch": 9.6,
"learning_rate": 1.1490422661761744e-05,
"loss": 1.0574,
"step": 403
},
{
"epoch": 9.62,
"learning_rate": 1.1451482595276798e-05,
"loss": 1.1487,
"step": 404
},
{
"epoch": 9.64,
"learning_rate": 1.141252003279542e-05,
"loss": 1.0812,
"step": 405
},
{
"epoch": 9.67,
"learning_rate": 1.1373535578184083e-05,
"loss": 1.0655,
"step": 406
},
{
"epoch": 9.69,
"learning_rate": 1.1334529835648554e-05,
"loss": 1.0956,
"step": 407
},
{
"epoch": 9.71,
"learning_rate": 1.1295503409724526e-05,
"loss": 1.0236,
"step": 408
},
{
"epoch": 9.74,
"learning_rate": 1.1256456905268264e-05,
"loss": 1.0874,
"step": 409
},
{
"epoch": 9.76,
"learning_rate": 1.1217390927447228e-05,
"loss": 1.1359,
"step": 410
},
{
"epoch": 9.79,
"learning_rate": 1.1178306081730666e-05,
"loss": 1.1012,
"step": 411
},
{
"epoch": 9.81,
"learning_rate": 1.113920297388028e-05,
"loss": 1.091,
"step": 412
},
{
"epoch": 9.83,
"learning_rate": 1.1100082209940795e-05,
"loss": 1.0136,
"step": 413
},
{
"epoch": 9.86,
"learning_rate": 1.1060944396230583e-05,
"loss": 1.0934,
"step": 414
},
{
"epoch": 9.88,
"learning_rate": 1.1021790139332264e-05,
"loss": 1.0876,
"step": 415
},
{
"epoch": 9.9,
"learning_rate": 1.0982620046083307e-05,
"loss": 1.0868,
"step": 416
},
{
"epoch": 9.93,
"learning_rate": 1.0943434723566624e-05,
"loss": 1.0973,
"step": 417
},
{
"epoch": 9.95,
"learning_rate": 1.090423477910116e-05,
"loss": 1.0986,
"step": 418
},
{
"epoch": 9.98,
"learning_rate": 1.0865020820232469e-05,
"loss": 1.0149,
"step": 419
},
{
"epoch": 10.0,
"learning_rate": 1.0825793454723325e-05,
"loss": 1.0666,
"step": 420
},
{
"epoch": 10.02,
"learning_rate": 1.0786553290544279e-05,
"loss": 1.0475,
"step": 421
},
{
"epoch": 10.05,
"learning_rate": 1.0747300935864245e-05,
"loss": 1.0498,
"step": 422
},
{
"epoch": 10.07,
"learning_rate": 1.0708036999041072e-05,
"loss": 1.1237,
"step": 423
},
{
"epoch": 10.1,
"learning_rate": 1.0668762088612114e-05,
"loss": 1.041,
"step": 424
},
{
"epoch": 10.12,
"learning_rate": 1.062947681328481e-05,
"loss": 1.0346,
"step": 425
},
{
"epoch": 10.14,
"learning_rate": 1.0590181781927229e-05,
"loss": 1.0454,
"step": 426
},
{
"epoch": 10.17,
"learning_rate": 1.0550877603558656e-05,
"loss": 1.0188,
"step": 427
},
{
"epoch": 10.19,
"learning_rate": 1.0511564887340136e-05,
"loss": 1.0445,
"step": 428
},
{
"epoch": 10.21,
"learning_rate": 1.0472244242565035e-05,
"loss": 1.0456,
"step": 429
},
{
"epoch": 10.24,
"learning_rate": 1.0432916278649611e-05,
"loss": 1.0846,
"step": 430
},
{
"epoch": 10.26,
"learning_rate": 1.0393581605123552e-05,
"loss": 1.0209,
"step": 431
},
{
"epoch": 10.29,
"learning_rate": 1.0354240831620542e-05,
"loss": 1.0131,
"step": 432
},
{
"epoch": 10.31,
"learning_rate": 1.0314894567868791e-05,
"loss": 1.0495,
"step": 433
},
{
"epoch": 10.33,
"learning_rate": 1.0275543423681622e-05,
"loss": 1.0614,
"step": 434
},
{
"epoch": 10.36,
"learning_rate": 1.023618800894798e-05,
"loss": 1.0807,
"step": 435
},
{
"epoch": 10.38,
"learning_rate": 1.0196828933623008e-05,
"loss": 1.0494,
"step": 436
},
{
"epoch": 10.4,
"learning_rate": 1.015746680771858e-05,
"loss": 1.0863,
"step": 437
},
{
"epoch": 10.43,
"learning_rate": 1.0118102241293848e-05,
"loss": 1.0293,
"step": 438
},
{
"epoch": 10.45,
"learning_rate": 1.0078735844445788e-05,
"loss": 1.0974,
"step": 439
},
{
"epoch": 10.48,
"learning_rate": 1.0039368227299755e-05,
"loss": 1.0537,
"step": 440
},
{
"epoch": 10.5,
"learning_rate": 1e-05,
"loss": 1.0427,
"step": 441
},
{
"epoch": 10.52,
"learning_rate": 9.96063177270025e-06,
"loss": 1.0566,
"step": 442
},
{
"epoch": 10.55,
"learning_rate": 9.921264155554214e-06,
"loss": 1.0275,
"step": 443
},
{
"epoch": 10.57,
"learning_rate": 9.881897758706155e-06,
"loss": 1.0517,
"step": 444
},
{
"epoch": 10.6,
"learning_rate": 9.842533192281424e-06,
"loss": 1.0893,
"step": 445
},
{
"epoch": 10.62,
"learning_rate": 9.803171066376997e-06,
"loss": 1.0351,
"step": 446
},
{
"epoch": 10.64,
"learning_rate": 9.763811991052021e-06,
"loss": 1.0341,
"step": 447
},
{
"epoch": 10.67,
"learning_rate": 9.724456576318383e-06,
"loss": 1.0358,
"step": 448
},
{
"epoch": 10.69,
"learning_rate": 9.68510543213121e-06,
"loss": 1.0689,
"step": 449
},
{
"epoch": 10.71,
"learning_rate": 9.645759168379463e-06,
"loss": 1.0401,
"step": 450
},
{
"epoch": 10.74,
"learning_rate": 9.606418394876448e-06,
"loss": 1.0526,
"step": 451
},
{
"epoch": 10.76,
"learning_rate": 9.56708372135039e-06,
"loss": 1.0468,
"step": 452
},
{
"epoch": 10.79,
"learning_rate": 9.527755757434968e-06,
"loss": 1.0863,
"step": 453
},
{
"epoch": 10.81,
"learning_rate": 9.48843511265987e-06,
"loss": 1.0803,
"step": 454
},
{
"epoch": 10.83,
"learning_rate": 9.449122396441344e-06,
"loss": 1.0079,
"step": 455
},
{
"epoch": 10.86,
"learning_rate": 9.409818218072774e-06,
"loss": 0.9972,
"step": 456
},
{
"epoch": 10.88,
"learning_rate": 9.370523186715195e-06,
"loss": 1.1057,
"step": 457
},
{
"epoch": 10.9,
"learning_rate": 9.331237911387889e-06,
"loss": 1.0704,
"step": 458
},
{
"epoch": 10.93,
"learning_rate": 9.291963000958932e-06,
"loss": 1.0686,
"step": 459
},
{
"epoch": 10.95,
"learning_rate": 9.252699064135759e-06,
"loss": 1.0426,
"step": 460
},
{
"epoch": 10.98,
"learning_rate": 9.213446709455723e-06,
"loss": 1.0079,
"step": 461
},
{
"epoch": 11.0,
"learning_rate": 9.174206545276678e-06,
"loss": 1.0105,
"step": 462
},
{
"epoch": 11.02,
"learning_rate": 9.134979179767533e-06,
"loss": 1.0359,
"step": 463
},
{
"epoch": 11.05,
"learning_rate": 9.095765220898845e-06,
"loss": 1.0158,
"step": 464
},
{
"epoch": 11.07,
"learning_rate": 9.056565276433378e-06,
"loss": 0.9912,
"step": 465
},
{
"epoch": 11.1,
"learning_rate": 9.017379953916696e-06,
"loss": 1.03,
"step": 466
},
{
"epoch": 11.12,
"learning_rate": 8.97820986066774e-06,
"loss": 0.9834,
"step": 467
},
{
"epoch": 11.14,
"learning_rate": 8.93905560376942e-06,
"loss": 1.0317,
"step": 468
},
{
"epoch": 11.17,
"learning_rate": 8.899917790059208e-06,
"loss": 1.0377,
"step": 469
},
{
"epoch": 11.19,
"learning_rate": 8.860797026119723e-06,
"loss": 1.0341,
"step": 470
},
{
"epoch": 11.21,
"learning_rate": 8.821693918269334e-06,
"loss": 1.0094,
"step": 471
},
{
"epoch": 11.24,
"learning_rate": 8.782609072552777e-06,
"loss": 1.0577,
"step": 472
},
{
"epoch": 11.26,
"learning_rate": 8.743543094731737e-06,
"loss": 1.0605,
"step": 473
},
{
"epoch": 11.29,
"learning_rate": 8.704496590275479e-06,
"loss": 1.0302,
"step": 474
},
{
"epoch": 11.31,
"learning_rate": 8.665470164351448e-06,
"loss": 0.9656,
"step": 475
},
{
"epoch": 11.33,
"learning_rate": 8.626464421815919e-06,
"loss": 1.0251,
"step": 476
},
{
"epoch": 11.36,
"learning_rate": 8.587479967204584e-06,
"loss": 1.0265,
"step": 477
},
{
"epoch": 11.38,
"learning_rate": 8.548517404723207e-06,
"loss": 1.0109,
"step": 478
},
{
"epoch": 11.4,
"learning_rate": 8.509577338238255e-06,
"loss": 1.0191,
"step": 479
},
{
"epoch": 11.43,
"learning_rate": 8.47066037126754e-06,
"loss": 1.0336,
"step": 480
},
{
"epoch": 11.45,
"learning_rate": 8.431767106970862e-06,
"loss": 1.0139,
"step": 481
},
{
"epoch": 11.48,
"learning_rate": 8.392898148140658e-06,
"loss": 1.0145,
"step": 482
},
{
"epoch": 11.5,
"learning_rate": 8.35405409719266e-06,
"loss": 1.0164,
"step": 483
},
{
"epoch": 11.52,
"learning_rate": 8.31523555615658e-06,
"loss": 1.0154,
"step": 484
},
{
"epoch": 11.55,
"learning_rate": 8.276443126666742e-06,
"loss": 0.9998,
"step": 485
},
{
"epoch": 11.57,
"learning_rate": 8.237677409952784e-06,
"loss": 1.0417,
"step": 486
},
{
"epoch": 11.6,
"learning_rate": 8.198939006830333e-06,
"loss": 1.0135,
"step": 487
},
{
"epoch": 11.62,
"learning_rate": 8.160228517691692e-06,
"loss": 1.0336,
"step": 488
},
{
"epoch": 11.64,
"learning_rate": 8.12154654249654e-06,
"loss": 1.0121,
"step": 489
},
{
"epoch": 11.67,
"learning_rate": 8.082893680762619e-06,
"loss": 1.0377,
"step": 490
},
{
"epoch": 11.69,
"learning_rate": 8.044270531556453e-06,
"loss": 1.0629,
"step": 491
},
{
"epoch": 11.71,
"learning_rate": 8.005677693484077e-06,
"loss": 1.0168,
"step": 492
},
{
"epoch": 11.74,
"learning_rate": 7.967115764681732e-06,
"loss": 0.9859,
"step": 493
},
{
"epoch": 11.76,
"learning_rate": 7.928585342806607e-06,
"loss": 1.0279,
"step": 494
},
{
"epoch": 11.79,
"learning_rate": 7.89008702502758e-06,
"loss": 1.0263,
"step": 495
},
{
"epoch": 11.81,
"learning_rate": 7.85162140801596e-06,
"loss": 1.0451,
"step": 496
},
{
"epoch": 11.83,
"learning_rate": 7.813189087936243e-06,
"loss": 0.9924,
"step": 497
},
{
"epoch": 11.86,
"learning_rate": 7.774790660436857e-06,
"loss": 1.0383,
"step": 498
},
{
"epoch": 11.88,
"learning_rate": 7.736426720640948e-06,
"loss": 1.0594,
"step": 499
},
{
"epoch": 11.9,
"learning_rate": 7.698097863137153e-06,
"loss": 1.0546,
"step": 500
},
{
"epoch": 11.93,
"learning_rate": 7.659804681970378e-06,
"loss": 1.0541,
"step": 501
},
{
"epoch": 11.95,
"learning_rate": 7.6215477706325905e-06,
"loss": 0.9874,
"step": 502
},
{
"epoch": 11.98,
"learning_rate": 7.583327722053628e-06,
"loss": 0.9774,
"step": 503
},
{
"epoch": 12.0,
"learning_rate": 7.545145128592009e-06,
"loss": 1.064,
"step": 504
},
{
"epoch": 12.02,
"learning_rate": 7.507000582025748e-06,
"loss": 0.9901,
"step": 505
},
{
"epoch": 12.05,
"learning_rate": 7.468894673543182e-06,
"loss": 0.9792,
"step": 506
},
{
"epoch": 12.07,
"learning_rate": 7.430827993733809e-06,
"loss": 0.9907,
"step": 507
},
{
"epoch": 12.1,
"learning_rate": 7.392801132579142e-06,
"loss": 0.991,
"step": 508
},
{
"epoch": 12.12,
"learning_rate": 7.354814679443557e-06,
"loss": 0.9837,
"step": 509
},
{
"epoch": 12.14,
"learning_rate": 7.316869223065156e-06,
"loss": 1.0326,
"step": 510
},
{
"epoch": 12.17,
"learning_rate": 7.278965351546648e-06,
"loss": 1.0077,
"step": 511
},
{
"epoch": 12.19,
"learning_rate": 7.241103652346249e-06,
"loss": 0.9827,
"step": 512
},
{
"epoch": 12.21,
"learning_rate": 7.203284712268541e-06,
"loss": 0.9624,
"step": 513
},
{
"epoch": 12.24,
"learning_rate": 7.165509117455407e-06,
"loss": 1.0249,
"step": 514
},
{
"epoch": 12.26,
"learning_rate": 7.1277774533769365e-06,
"loss": 0.9844,
"step": 515
},
{
"epoch": 12.29,
"learning_rate": 7.090090304822356e-06,
"loss": 1.0157,
"step": 516
},
{
"epoch": 12.31,
"learning_rate": 7.052448255890958e-06,
"loss": 0.9653,
"step": 517
},
{
"epoch": 12.33,
"learning_rate": 7.014851889983058e-06,
"loss": 1.0153,
"step": 518
},
{
"epoch": 12.36,
"learning_rate": 6.977301789790931e-06,
"loss": 1.0179,
"step": 519
},
{
"epoch": 12.38,
"learning_rate": 6.939798537289826e-06,
"loss": 1.0019,
"step": 520
},
{
"epoch": 12.4,
"learning_rate": 6.9023427137288865e-06,
"loss": 1.042,
"step": 521
},
{
"epoch": 12.43,
"learning_rate": 6.864934899622191e-06,
"loss": 1.0202,
"step": 522
},
{
"epoch": 12.45,
"learning_rate": 6.827575674739726e-06,
"loss": 1.0376,
"step": 523
},
{
"epoch": 12.48,
"learning_rate": 6.790265618098424e-06,
"loss": 1.003,
"step": 524
},
{
"epoch": 12.5,
"learning_rate": 6.7530053079531664e-06,
"loss": 0.9291,
"step": 525
},
{
"epoch": 12.52,
"learning_rate": 6.715795321787837e-06,
"loss": 1.0135,
"step": 526
},
{
"epoch": 12.55,
"learning_rate": 6.678636236306357e-06,
"loss": 1.0106,
"step": 527
},
{
"epoch": 12.57,
"learning_rate": 6.6415286274237744e-06,
"loss": 0.9983,
"step": 528
},
{
"epoch": 12.6,
"learning_rate": 6.604473070257309e-06,
"loss": 1.009,
"step": 529
},
{
"epoch": 12.62,
"learning_rate": 6.5674701391174475e-06,
"loss": 1.0141,
"step": 530
},
{
"epoch": 12.64,
"learning_rate": 6.530520407499049e-06,
"loss": 0.9776,
"step": 531
},
{
"epoch": 12.67,
"learning_rate": 6.4936244480724575e-06,
"loss": 0.9636,
"step": 532
},
{
"epoch": 12.69,
"learning_rate": 6.456782832674613e-06,
"loss": 1.0022,
"step": 533
},
{
"epoch": 12.71,
"learning_rate": 6.419996132300203e-06,
"loss": 0.9595,
"step": 534
},
{
"epoch": 12.74,
"learning_rate": 6.383264917092802e-06,
"loss": 1.0212,
"step": 535
},
{
"epoch": 12.76,
"learning_rate": 6.34658975633605e-06,
"loss": 0.9781,
"step": 536
},
{
"epoch": 12.79,
"learning_rate": 6.30997121844481e-06,
"loss": 0.9901,
"step": 537
},
{
"epoch": 12.81,
"learning_rate": 6.273409870956371e-06,
"loss": 0.9886,
"step": 538
},
{
"epoch": 12.83,
"learning_rate": 6.236906280521646e-06,
"loss": 0.9921,
"step": 539
},
{
"epoch": 12.86,
"learning_rate": 6.200461012896401e-06,
"loss": 1.0337,
"step": 540
},
{
"epoch": 12.88,
"learning_rate": 6.164074632932472e-06,
"loss": 0.9958,
"step": 541
},
{
"epoch": 12.9,
"learning_rate": 6.127747704569016e-06,
"loss": 0.9766,
"step": 542
},
{
"epoch": 12.93,
"learning_rate": 6.091480790823772e-06,
"loss": 0.9876,
"step": 543
},
{
"epoch": 12.95,
"learning_rate": 6.055274453784339e-06,
"loss": 0.9724,
"step": 544
},
{
"epoch": 12.98,
"learning_rate": 6.019129254599456e-06,
"loss": 1.0358,
"step": 545
},
{
"epoch": 13.0,
"learning_rate": 5.983045753470308e-06,
"loss": 0.9826,
"step": 546
},
{
"epoch": 13.02,
"learning_rate": 5.947024509641841e-06,
"loss": 1.0172,
"step": 547
},
{
"epoch": 13.05,
"learning_rate": 5.9110660813941136e-06,
"loss": 1.001,
"step": 548
},
{
"epoch": 13.07,
"learning_rate": 5.875171026033609e-06,
"loss": 0.9531,
"step": 549
},
{
"epoch": 13.1,
"learning_rate": 5.839339899884629e-06,
"loss": 0.963,
"step": 550
},
{
"epoch": 13.12,
"learning_rate": 5.803573258280655e-06,
"loss": 0.9556,
"step": 551
},
{
"epoch": 13.14,
"learning_rate": 5.7678716555557515e-06,
"loss": 1.0018,
"step": 552
},
{
"epoch": 13.17,
"learning_rate": 5.732235645035964e-06,
"loss": 0.9657,
"step": 553
},
{
"epoch": 13.19,
"learning_rate": 5.69666577903075e-06,
"loss": 0.9885,
"step": 554
},
{
"epoch": 13.21,
"learning_rate": 5.66116260882442e-06,
"loss": 0.9444,
"step": 555
},
{
"epoch": 13.24,
"learning_rate": 5.6257266846675865e-06,
"loss": 0.9886,
"step": 556
},
{
"epoch": 13.26,
"learning_rate": 5.590358555768642e-06,
"loss": 0.9665,
"step": 557
},
{
"epoch": 13.29,
"learning_rate": 5.5550587702852465e-06,
"loss": 0.9831,
"step": 558
},
{
"epoch": 13.31,
"learning_rate": 5.519827875315824e-06,
"loss": 0.9913,
"step": 559
},
{
"epoch": 13.33,
"learning_rate": 5.484666416891109e-06,
"loss": 0.9994,
"step": 560
},
{
"epoch": 13.36,
"learning_rate": 5.449574939965637e-06,
"loss": 0.9419,
"step": 561
},
{
"epoch": 13.38,
"learning_rate": 5.414553988409343e-06,
"loss": 0.9928,
"step": 562
},
{
"epoch": 13.4,
"learning_rate": 5.37960410499911e-06,
"loss": 0.9695,
"step": 563
},
{
"epoch": 13.43,
"learning_rate": 5.344725831410369e-06,
"loss": 0.9364,
"step": 564
},
{
"epoch": 13.45,
"learning_rate": 5.3099197082086866e-06,
"loss": 0.9577,
"step": 565
},
{
"epoch": 13.48,
"learning_rate": 5.275186274841404e-06,
"loss": 0.9328,
"step": 566
},
{
"epoch": 13.5,
"learning_rate": 5.240526069629265e-06,
"loss": 0.9714,
"step": 567
},
{
"epoch": 13.52,
"learning_rate": 5.2059396297580785e-06,
"loss": 0.9898,
"step": 568
},
{
"epoch": 13.55,
"learning_rate": 5.171427491270394e-06,
"loss": 1.0452,
"step": 569
},
{
"epoch": 13.57,
"learning_rate": 5.136990189057187e-06,
"loss": 0.9622,
"step": 570
},
{
"epoch": 13.6,
"learning_rate": 5.102628256849576e-06,
"loss": 0.9686,
"step": 571
},
{
"epoch": 13.62,
"learning_rate": 5.0683422272105455e-06,
"loss": 0.9826,
"step": 572
},
{
"epoch": 13.64,
"learning_rate": 5.034132631526696e-06,
"loss": 0.9745,
"step": 573
},
{
"epoch": 13.67,
"learning_rate": 5.000000000000003e-06,
"loss": 0.9667,
"step": 574
},
{
"epoch": 13.69,
"learning_rate": 4.965944861639601e-06,
"loss": 0.961,
"step": 575
},
{
"epoch": 13.71,
"learning_rate": 4.931967744253601e-06,
"loss": 0.9716,
"step": 576
},
{
"epoch": 13.74,
"learning_rate": 4.898069174440881e-06,
"loss": 0.9528,
"step": 577
},
{
"epoch": 13.76,
"learning_rate": 4.864249677582935e-06,
"loss": 1.0056,
"step": 578
},
{
"epoch": 13.79,
"learning_rate": 4.8305097778357445e-06,
"loss": 0.9697,
"step": 579
},
{
"epoch": 13.81,
"learning_rate": 4.796849998121647e-06,
"loss": 0.9844,
"step": 580
},
{
"epoch": 13.83,
"learning_rate": 4.763270860121222e-06,
"loss": 0.9888,
"step": 581
},
{
"epoch": 13.86,
"learning_rate": 4.729772884265212e-06,
"loss": 0.9286,
"step": 582
},
{
"epoch": 13.88,
"learning_rate": 4.696356589726463e-06,
"loss": 0.9946,
"step": 583
},
{
"epoch": 13.9,
"learning_rate": 4.663022494411866e-06,
"loss": 0.9975,
"step": 584
},
{
"epoch": 13.93,
"learning_rate": 4.629771114954341e-06,
"loss": 0.9382,
"step": 585
},
{
"epoch": 13.95,
"learning_rate": 4.596602966704823e-06,
"loss": 0.9665,
"step": 586
},
{
"epoch": 13.98,
"learning_rate": 4.563518563724274e-06,
"loss": 0.9589,
"step": 587
},
{
"epoch": 14.0,
"learning_rate": 4.530518418775734e-06,
"loss": 0.9829,
"step": 588
},
{
"epoch": 14.02,
"learning_rate": 4.497603043316334e-06,
"loss": 0.9504,
"step": 589
},
{
"epoch": 14.05,
"learning_rate": 4.464772947489413e-06,
"loss": 1.0077,
"step": 590
},
{
"epoch": 14.07,
"learning_rate": 4.432028640116581e-06,
"loss": 0.9822,
"step": 591
},
{
"epoch": 14.1,
"learning_rate": 4.399370628689857e-06,
"loss": 0.9483,
"step": 592
},
{
"epoch": 14.12,
"learning_rate": 4.3667994193637794e-06,
"loss": 0.9793,
"step": 593
},
{
"epoch": 14.14,
"learning_rate": 4.33431551694758e-06,
"loss": 0.9626,
"step": 594
},
{
"epoch": 14.17,
"learning_rate": 4.301919424897339e-06,
"loss": 0.9223,
"step": 595
},
{
"epoch": 14.19,
"learning_rate": 4.2696116453082145e-06,
"loss": 0.976,
"step": 596
},
{
"epoch": 14.21,
"learning_rate": 4.237392678906633e-06,
"loss": 0.9845,
"step": 597
},
{
"epoch": 14.24,
"learning_rate": 4.205263025042538e-06,
"loss": 0.988,
"step": 598
},
{
"epoch": 14.26,
"learning_rate": 4.173223181681652e-06,
"loss": 0.9283,
"step": 599
},
{
"epoch": 14.29,
"learning_rate": 4.1412736453977545e-06,
"loss": 0.978,
"step": 600
},
{
"epoch": 14.31,
"learning_rate": 4.109414911364993e-06,
"loss": 0.9209,
"step": 601
},
{
"epoch": 14.33,
"learning_rate": 4.077647473350201e-06,
"loss": 0.9651,
"step": 602
},
{
"epoch": 14.36,
"learning_rate": 4.045971823705249e-06,
"loss": 0.9592,
"step": 603
},
{
"epoch": 14.38,
"learning_rate": 4.01438845335942e-06,
"loss": 0.9321,
"step": 604
},
{
"epoch": 14.4,
"learning_rate": 3.982897851811787e-06,
"loss": 0.9376,
"step": 605
},
{
"epoch": 14.43,
"learning_rate": 3.9515005071236274e-06,
"loss": 0.9603,
"step": 606
},
{
"epoch": 14.45,
"learning_rate": 3.920196905910873e-06,
"loss": 0.9377,
"step": 607
},
{
"epoch": 14.48,
"learning_rate": 3.888987533336567e-06,
"loss": 0.9108,
"step": 608
},
{
"epoch": 14.5,
"learning_rate": 3.857872873103322e-06,
"loss": 1.0242,
"step": 609
},
{
"epoch": 14.52,
"learning_rate": 3.826853407445848e-06,
"loss": 0.9593,
"step": 610
},
{
"epoch": 14.55,
"learning_rate": 3.7959296171234683e-06,
"loss": 0.9501,
"step": 611
},
{
"epoch": 14.57,
"learning_rate": 3.7651019814126656e-06,
"loss": 0.9784,
"step": 612
},
{
"epoch": 14.6,
"learning_rate": 3.7343709780996616e-06,
"loss": 0.9565,
"step": 613
},
{
"epoch": 14.62,
"learning_rate": 3.703737083473006e-06,
"loss": 0.905,
"step": 614
},
{
"epoch": 14.64,
"learning_rate": 3.6732007723161933e-06,
"loss": 0.9637,
"step": 615
},
{
"epoch": 14.67,
"learning_rate": 3.6427625179003223e-06,
"loss": 0.9505,
"step": 616
},
{
"epoch": 14.69,
"learning_rate": 3.612422791976723e-06,
"loss": 0.9012,
"step": 617
},
{
"epoch": 14.71,
"learning_rate": 3.582182064769687e-06,
"loss": 0.9635,
"step": 618
},
{
"epoch": 14.74,
"learning_rate": 3.552040804969149e-06,
"loss": 0.9679,
"step": 619
},
{
"epoch": 14.76,
"learning_rate": 3.521999479723448e-06,
"loss": 0.945,
"step": 620
},
{
"epoch": 14.79,
"learning_rate": 3.492058554632063e-06,
"loss": 0.9131,
"step": 621
},
{
"epoch": 14.81,
"learning_rate": 3.4622184937384164e-06,
"loss": 0.9336,
"step": 622
},
{
"epoch": 14.83,
"learning_rate": 3.4324797595226567e-06,
"loss": 0.9752,
"step": 623
},
{
"epoch": 14.86,
"learning_rate": 3.402842812894529e-06,
"loss": 0.9491,
"step": 624
},
{
"epoch": 14.88,
"learning_rate": 3.373308113186198e-06,
"loss": 0.9195,
"step": 625
},
{
"epoch": 14.9,
"learning_rate": 3.343876118145142e-06,
"loss": 0.9496,
"step": 626
},
{
"epoch": 14.93,
"learning_rate": 3.3145472839270575e-06,
"loss": 0.9565,
"step": 627
},
{
"epoch": 14.95,
"learning_rate": 3.285322065088792e-06,
"loss": 0.9973,
"step": 628
},
{
"epoch": 14.98,
"learning_rate": 3.2562009145812924e-06,
"loss": 0.9596,
"step": 629
},
{
"epoch": 15.0,
"learning_rate": 3.2271842837425917e-06,
"loss": 0.9416,
"step": 630
},
{
"epoch": 15.02,
"learning_rate": 3.1982726222908046e-06,
"loss": 0.8841,
"step": 631
},
{
"epoch": 15.05,
"learning_rate": 3.1694663783171775e-06,
"loss": 0.9554,
"step": 632
},
{
"epoch": 15.07,
"learning_rate": 3.1407659982791204e-06,
"loss": 0.9484,
"step": 633
},
{
"epoch": 15.1,
"learning_rate": 3.1121719269932914e-06,
"loss": 0.954,
"step": 634
},
{
"epoch": 15.12,
"learning_rate": 3.0836846076287153e-06,
"loss": 0.905,
"step": 635
},
{
"epoch": 15.14,
"learning_rate": 3.0553044816999133e-06,
"loss": 0.9789,
"step": 636
},
{
"epoch": 15.17,
"learning_rate": 3.0270319890600465e-06,
"loss": 0.9545,
"step": 637
},
{
"epoch": 15.19,
"learning_rate": 2.998867567894108e-06,
"loss": 0.9337,
"step": 638
},
{
"epoch": 15.21,
"learning_rate": 2.9708116547121333e-06,
"loss": 0.9455,
"step": 639
},
{
"epoch": 15.24,
"learning_rate": 2.9428646843424326e-06,
"loss": 0.909,
"step": 640
},
{
"epoch": 15.26,
"learning_rate": 2.9150270899248502e-06,
"loss": 0.9235,
"step": 641
},
{
"epoch": 15.29,
"learning_rate": 2.8872993029040506e-06,
"loss": 0.9396,
"step": 642
},
{
"epoch": 15.31,
"learning_rate": 2.8596817530228382e-06,
"loss": 0.9371,
"step": 643
},
{
"epoch": 15.33,
"learning_rate": 2.8321748683154893e-06,
"loss": 0.9437,
"step": 644
},
{
"epoch": 15.36,
"learning_rate": 2.8047790751011216e-06,
"loss": 0.9231,
"step": 645
},
{
"epoch": 15.38,
"learning_rate": 2.7774947979770882e-06,
"loss": 0.894,
"step": 646
},
{
"epoch": 15.4,
"learning_rate": 2.75032245981239e-06,
"loss": 0.9742,
"step": 647
},
{
"epoch": 15.43,
"learning_rate": 2.723262481741138e-06,
"loss": 0.906,
"step": 648
},
{
"epoch": 15.45,
"learning_rate": 2.696315283156007e-06,
"loss": 0.9236,
"step": 649
},
{
"epoch": 15.48,
"learning_rate": 2.669481281701739e-06,
"loss": 0.9272,
"step": 650
},
{
"epoch": 15.5,
"learning_rate": 2.642760893268684e-06,
"loss": 0.9282,
"step": 651
},
{
"epoch": 15.52,
"learning_rate": 2.6161545319863457e-06,
"loss": 0.9908,
"step": 652
},
{
"epoch": 15.55,
"learning_rate": 2.58966261021696e-06,
"loss": 0.9661,
"step": 653
},
{
"epoch": 15.57,
"learning_rate": 2.563285538549104e-06,
"loss": 0.9412,
"step": 654
},
{
"epoch": 15.6,
"learning_rate": 2.53702372579134e-06,
"loss": 0.9421,
"step": 655
},
{
"epoch": 15.62,
"learning_rate": 2.51087757896587e-06,
"loss": 0.9457,
"step": 656
},
{
"epoch": 15.64,
"learning_rate": 2.484847503302238e-06,
"loss": 0.9606,
"step": 657
},
{
"epoch": 15.67,
"learning_rate": 2.4589339022310386e-06,
"loss": 0.9308,
"step": 658
},
{
"epoch": 15.69,
"learning_rate": 2.4331371773776692e-06,
"loss": 0.9439,
"step": 659
},
{
"epoch": 15.71,
"learning_rate": 2.407457728556115e-06,
"loss": 0.9901,
"step": 660
},
{
"epoch": 15.74,
"learning_rate": 2.3818959537627282e-06,
"loss": 0.9643,
"step": 661
},
{
"epoch": 15.76,
"learning_rate": 2.3564522491700835e-06,
"loss": 0.8979,
"step": 662
},
{
"epoch": 15.79,
"learning_rate": 2.331127009120826e-06,
"loss": 0.9693,
"step": 663
},
{
"epoch": 15.81,
"learning_rate": 2.3059206261215673e-06,
"loss": 0.9196,
"step": 664
},
{
"epoch": 15.83,
"learning_rate": 2.2808334908367914e-06,
"loss": 0.9259,
"step": 665
},
{
"epoch": 15.86,
"learning_rate": 2.2558659920828095e-06,
"loss": 0.938,
"step": 666
},
{
"epoch": 15.88,
"learning_rate": 2.2310185168217212e-06,
"loss": 0.9214,
"step": 667
},
{
"epoch": 15.9,
"learning_rate": 2.206291450155441e-06,
"loss": 0.9702,
"step": 668
},
{
"epoch": 15.93,
"learning_rate": 2.1816851753197023e-06,
"loss": 0.9438,
"step": 669
},
{
"epoch": 15.95,
"learning_rate": 2.157200073678137e-06,
"loss": 0.9198,
"step": 670
},
{
"epoch": 15.98,
"learning_rate": 2.1328365247163553e-06,
"loss": 0.9596,
"step": 671
},
{
"epoch": 16.0,
"learning_rate": 2.1085949060360654e-06,
"loss": 0.8977,
"step": 672
},
{
"epoch": 16.02,
"learning_rate": 2.0844755933492266e-06,
"loss": 0.8807,
"step": 673
},
{
"epoch": 16.05,
"learning_rate": 2.0604789604722208e-06,
"loss": 0.9459,
"step": 674
},
{
"epoch": 16.07,
"learning_rate": 2.0366053793200567e-06,
"loss": 0.9208,
"step": 675
},
{
"epoch": 16.1,
"learning_rate": 2.01285521990062e-06,
"loss": 0.9032,
"step": 676
},
{
"epoch": 16.12,
"learning_rate": 1.9892288503089207e-06,
"loss": 0.9417,
"step": 677
},
{
"epoch": 16.14,
"learning_rate": 1.96572663672139e-06,
"loss": 0.9333,
"step": 678
},
{
"epoch": 16.17,
"learning_rate": 1.9423489433902186e-06,
"loss": 0.9111,
"step": 679
},
{
"epoch": 16.19,
"learning_rate": 1.9190961326377056e-06,
"loss": 0.8754,
"step": 680
},
{
"epoch": 16.21,
"learning_rate": 1.8959685648506365e-06,
"loss": 0.9469,
"step": 681
},
{
"epoch": 16.24,
"learning_rate": 1.8729665984747002e-06,
"loss": 0.9407,
"step": 682
},
{
"epoch": 16.26,
"learning_rate": 1.8500905900089405e-06,
"loss": 0.9379,
"step": 683
},
{
"epoch": 16.29,
"learning_rate": 1.8273408940002202e-06,
"loss": 0.9322,
"step": 684
},
{
"epoch": 16.31,
"learning_rate": 1.8047178630377372e-06,
"loss": 0.9381,
"step": 685
},
{
"epoch": 16.33,
"learning_rate": 1.7822218477475496e-06,
"loss": 0.8907,
"step": 686
},
{
"epoch": 16.36,
"learning_rate": 1.7598531967871468e-06,
"loss": 0.9327,
"step": 687
},
{
"epoch": 16.38,
"learning_rate": 1.7376122568400533e-06,
"loss": 0.9619,
"step": 688
},
{
"epoch": 16.4,
"learning_rate": 1.715499372610433e-06,
"loss": 0.8911,
"step": 689
},
{
"epoch": 16.43,
"learning_rate": 1.693514886817772e-06,
"loss": 0.9983,
"step": 690
},
{
"epoch": 16.45,
"learning_rate": 1.6716591401915506e-06,
"loss": 0.967,
"step": 691
},
{
"epoch": 16.48,
"learning_rate": 1.649932471465976e-06,
"loss": 0.919,
"step": 692
},
{
"epoch": 16.5,
"learning_rate": 1.6283352173747148e-06,
"loss": 0.9258,
"step": 693
},
{
"epoch": 16.52,
"learning_rate": 1.60686771264569e-06,
"loss": 0.9273,
"step": 694
},
{
"epoch": 16.55,
"learning_rate": 1.585530289995878e-06,
"loss": 0.9248,
"step": 695
},
{
"epoch": 16.57,
"learning_rate": 1.5643232801261731e-06,
"loss": 0.9195,
"step": 696
},
{
"epoch": 16.6,
"learning_rate": 1.5432470117162435e-06,
"loss": 0.9665,
"step": 697
},
{
"epoch": 16.62,
"learning_rate": 1.5223018114194422e-06,
"loss": 0.9637,
"step": 698
},
{
"epoch": 16.64,
"learning_rate": 1.5014880038577485e-06,
"loss": 0.9163,
"step": 699
},
{
"epoch": 16.67,
"learning_rate": 1.4808059116167306e-06,
"loss": 0.9372,
"step": 700
},
{
"epoch": 16.69,
"learning_rate": 1.4602558552405521e-06,
"loss": 0.9175,
"step": 701
},
{
"epoch": 16.71,
"learning_rate": 1.4398381532270001e-06,
"loss": 0.9092,
"step": 702
},
{
"epoch": 16.74,
"learning_rate": 1.419553122022549e-06,
"loss": 0.8933,
"step": 703
},
{
"epoch": 16.76,
"learning_rate": 1.3994010760174603e-06,
"loss": 0.9423,
"step": 704
},
{
"epoch": 16.79,
"learning_rate": 1.3793823275409068e-06,
"loss": 0.888,
"step": 705
},
{
"epoch": 16.81,
"learning_rate": 1.3594971868561235e-06,
"loss": 0.9067,
"step": 706
},
{
"epoch": 16.83,
"learning_rate": 1.339745962155613e-06,
"loss": 0.9404,
"step": 707
},
{
"epoch": 16.86,
"learning_rate": 1.3201289595563693e-06,
"loss": 0.9732,
"step": 708
},
{
"epoch": 16.88,
"learning_rate": 1.3006464830951182e-06,
"loss": 0.9221,
"step": 709
},
{
"epoch": 16.9,
"learning_rate": 1.2812988347236166e-06,
"loss": 0.9617,
"step": 710
},
{
"epoch": 16.93,
"learning_rate": 1.262086314303973e-06,
"loss": 0.9538,
"step": 711
},
{
"epoch": 16.95,
"learning_rate": 1.2430092196039934e-06,
"loss": 0.9333,
"step": 712
},
{
"epoch": 16.98,
"learning_rate": 1.2240678462925725e-06,
"loss": 0.9071,
"step": 713
},
{
"epoch": 17.0,
"learning_rate": 1.2052624879351105e-06,
"loss": 0.8859,
"step": 714
},
{
"epoch": 17.02,
"learning_rate": 1.1865934359889576e-06,
"loss": 0.9442,
"step": 715
},
{
"epoch": 17.05,
"learning_rate": 1.168060979798904e-06,
"loss": 0.9211,
"step": 716
},
{
"epoch": 17.07,
"learning_rate": 1.1496654065926927e-06,
"loss": 0.8865,
"step": 717
},
{
"epoch": 17.1,
"learning_rate": 1.1314070014765644e-06,
"loss": 0.9205,
"step": 718
},
{
"epoch": 17.12,
"learning_rate": 1.1132860474308438e-06,
"loss": 0.9126,
"step": 719
},
{
"epoch": 17.14,
"learning_rate": 1.0953028253055541e-06,
"loss": 0.9431,
"step": 720
},
{
"epoch": 17.17,
"learning_rate": 1.0774576138160596e-06,
"loss": 0.8831,
"step": 721
},
{
"epoch": 17.19,
"learning_rate": 1.05975068953875e-06,
"loss": 0.8594,
"step": 722
},
{
"epoch": 17.21,
"learning_rate": 1.0421823269067443e-06,
"loss": 0.9342,
"step": 723
},
{
"epoch": 17.24,
"learning_rate": 1.0247527982056581e-06,
"loss": 0.8987,
"step": 724
},
{
"epoch": 17.26,
"learning_rate": 1.0074623735693633e-06,
"loss": 0.9475,
"step": 725
},
{
"epoch": 17.29,
"learning_rate": 9.903113209758098e-07,
"loss": 0.9067,
"step": 726
},
{
"epoch": 17.31,
"learning_rate": 9.732999062428705e-07,
"loss": 0.9223,
"step": 727
},
{
"epoch": 17.33,
"learning_rate": 9.564283930242258e-07,
"loss": 0.9135,
"step": 728
},
{
"epoch": 17.36,
"learning_rate": 9.396970428052698e-07,
"loss": 0.9277,
"step": 729
},
{
"epoch": 17.38,
"learning_rate": 9.23106114899065e-07,
"loss": 0.9232,
"step": 730
},
{
"epoch": 17.4,
"learning_rate": 9.066558664423164e-07,
"loss": 0.9797,
"step": 731
},
{
"epoch": 17.43,
"learning_rate": 8.903465523913957e-07,
"loss": 0.9229,
"step": 732
},
{
"epoch": 17.45,
"learning_rate": 8.74178425518376e-07,
"loss": 0.9189,
"step": 733
},
{
"epoch": 17.48,
"learning_rate": 8.581517364071267e-07,
"loss": 0.9436,
"step": 734
},
{
"epoch": 17.5,
"learning_rate": 8.42266733449425e-07,
"loss": 0.968,
"step": 735
},
{
"epoch": 17.52,
"learning_rate": 8.265236628411088e-07,
"loss": 0.9412,
"step": 736
},
{
"epoch": 17.55,
"learning_rate": 8.109227685782539e-07,
"loss": 0.9402,
"step": 737
},
{
"epoch": 17.57,
"learning_rate": 7.954642924533995e-07,
"loss": 0.9172,
"step": 738
},
{
"epoch": 17.6,
"learning_rate": 7.80148474051794e-07,
"loss": 0.8998,
"step": 739
},
{
"epoch": 17.62,
"learning_rate": 7.649755507476953e-07,
"loss": 0.8634,
"step": 740
},
{
"epoch": 17.64,
"learning_rate": 7.499457577006753e-07,
"loss": 0.886,
"step": 741
},
{
"epoch": 17.67,
"learning_rate": 7.350593278519824e-07,
"loss": 0.9592,
"step": 742
},
{
"epoch": 17.69,
"learning_rate": 7.20316491920936e-07,
"loss": 0.9348,
"step": 743
},
{
"epoch": 17.71,
"learning_rate": 7.057174784013432e-07,
"loss": 0.8924,
"step": 744
},
{
"epoch": 17.74,
"learning_rate": 6.912625135579587e-07,
"loss": 0.9493,
"step": 745
},
{
"epoch": 17.76,
"learning_rate": 6.76951821422982e-07,
"loss": 0.8917,
"step": 746
},
{
"epoch": 17.79,
"learning_rate": 6.627856237925812e-07,
"loss": 0.8867,
"step": 747
},
{
"epoch": 17.81,
"learning_rate": 6.487641402234612e-07,
"loss": 0.9424,
"step": 748
},
{
"epoch": 17.83,
"learning_rate": 6.348875880294536e-07,
"loss": 0.9141,
"step": 749
},
{
"epoch": 17.86,
"learning_rate": 6.211561822781476e-07,
"loss": 0.923,
"step": 750
},
{
"epoch": 17.88,
"learning_rate": 6.075701357875663e-07,
"loss": 0.9054,
"step": 751
},
{
"epoch": 17.9,
"learning_rate": 5.94129659122864e-07,
"loss": 0.9585,
"step": 752
},
{
"epoch": 17.93,
"learning_rate": 5.808349605930586e-07,
"loss": 0.9271,
"step": 753
},
{
"epoch": 17.95,
"learning_rate": 5.676862462478061e-07,
"loss": 0.9654,
"step": 754
},
{
"epoch": 17.98,
"learning_rate": 5.546837198742094e-07,
"loss": 0.9182,
"step": 755
},
{
"epoch": 18.0,
"learning_rate": 5.418275829936537e-07,
"loss": 0.8896,
"step": 756
},
{
"epoch": 18.02,
"learning_rate": 5.291180348586911e-07,
"loss": 0.9334,
"step": 757
},
{
"epoch": 18.05,
"learning_rate": 5.165552724499478e-07,
"loss": 0.877,
"step": 758
},
{
"epoch": 18.07,
"learning_rate": 5.04139490473069e-07,
"loss": 0.8995,
"step": 759
},
{
"epoch": 18.1,
"learning_rate": 4.918708813557094e-07,
"loss": 0.9171,
"step": 760
},
{
"epoch": 18.12,
"learning_rate": 4.797496352445397e-07,
"loss": 0.978,
"step": 761
},
{
"epoch": 18.14,
"learning_rate": 4.6777594000230855e-07,
"loss": 0.9441,
"step": 762
},
{
"epoch": 18.17,
"learning_rate": 4.5594998120492505e-07,
"loss": 0.9457,
"step": 763
},
{
"epoch": 18.19,
"learning_rate": 4.4427194213859216e-07,
"loss": 0.8822,
"step": 764
},
{
"epoch": 18.21,
"learning_rate": 4.327420037969532e-07,
"loss": 0.8921,
"step": 765
},
{
"epoch": 18.24,
"learning_rate": 4.2136034487829327e-07,
"loss": 0.9229,
"step": 766
},
{
"epoch": 18.26,
"learning_rate": 4.101271417827668e-07,
"loss": 0.9788,
"step": 767
},
{
"epoch": 18.29,
"learning_rate": 3.9904256860967436e-07,
"loss": 0.9015,
"step": 768
},
{
"epoch": 18.31,
"learning_rate": 3.8810679715474696e-07,
"loss": 0.9112,
"step": 769
},
{
"epoch": 18.33,
"learning_rate": 3.773199969074959e-07,
"loss": 0.9191,
"step": 770
},
{
"epoch": 18.36,
"learning_rate": 3.6668233504858486e-07,
"loss": 0.903,
"step": 771
},
{
"epoch": 18.38,
"learning_rate": 3.5619397644723e-07,
"loss": 0.9461,
"step": 772
},
{
"epoch": 18.4,
"learning_rate": 3.458550836586583e-07,
"loss": 0.8458,
"step": 773
},
{
"epoch": 18.43,
"learning_rate": 3.356658169215743e-07,
"loss": 0.9351,
"step": 774
},
{
"epoch": 18.45,
"learning_rate": 3.2562633415568754e-07,
"loss": 0.9545,
"step": 775
},
{
"epoch": 18.48,
"learning_rate": 3.1573679095926015e-07,
"loss": 0.8709,
"step": 776
},
{
"epoch": 18.5,
"learning_rate": 3.059973406066963e-07,
"loss": 0.9137,
"step": 777
},
{
"epoch": 18.52,
"learning_rate": 2.964081340461633e-07,
"loss": 0.9398,
"step": 778
},
{
"epoch": 18.55,
"learning_rate": 2.8696931989725565e-07,
"loss": 0.8681,
"step": 779
},
{
"epoch": 18.57,
"learning_rate": 2.776810444486944e-07,
"loss": 0.9411,
"step": 780
},
{
"epoch": 18.6,
"learning_rate": 2.685434516560548e-07,
"loss": 0.9235,
"step": 781
},
{
"epoch": 18.62,
"learning_rate": 2.5955668313953466e-07,
"loss": 0.9081,
"step": 782
},
{
"epoch": 18.64,
"learning_rate": 2.507208781817638e-07,
"loss": 0.8829,
"step": 783
},
{
"epoch": 18.67,
"learning_rate": 2.420361737256438e-07,
"loss": 0.9264,
"step": 784
},
{
"epoch": 18.69,
"learning_rate": 2.3350270437222377e-07,
"loss": 0.9386,
"step": 785
},
{
"epoch": 18.71,
"learning_rate": 2.2512060237861455e-07,
"loss": 0.918,
"step": 786
},
{
"epoch": 18.74,
"learning_rate": 2.1688999765594022e-07,
"loss": 0.9053,
"step": 787
},
{
"epoch": 18.76,
"learning_rate": 2.088110177673297e-07,
"loss": 0.936,
"step": 788
},
{
"epoch": 18.79,
"learning_rate": 2.0088378792592288e-07,
"loss": 0.9258,
"step": 789
},
{
"epoch": 18.81,
"learning_rate": 1.9310843099295206e-07,
"loss": 0.8929,
"step": 790
},
{
"epoch": 18.83,
"learning_rate": 1.854850674758213e-07,
"loss": 0.9206,
"step": 791
},
{
"epoch": 18.86,
"learning_rate": 1.7801381552624565e-07,
"loss": 0.9273,
"step": 792
},
{
"epoch": 18.88,
"learning_rate": 1.7069479093842046e-07,
"loss": 0.9406,
"step": 793
},
{
"epoch": 18.9,
"learning_rate": 1.6352810714722388e-07,
"loss": 0.9295,
"step": 794
},
{
"epoch": 18.93,
"learning_rate": 1.5651387522645721e-07,
"loss": 0.9233,
"step": 795
},
{
"epoch": 18.95,
"learning_rate": 1.4965220388712955e-07,
"loss": 0.8998,
"step": 796
},
{
"epoch": 18.98,
"learning_rate": 1.4294319947577017e-07,
"loss": 0.9188,
"step": 797
},
{
"epoch": 19.0,
"learning_rate": 1.3638696597277678e-07,
"loss": 0.9261,
"step": 798
},
{
"epoch": 19.02,
"learning_rate": 1.2998360499080763e-07,
"loss": 0.8955,
"step": 799
},
{
"epoch": 19.05,
"learning_rate": 1.237332157732063e-07,
"loss": 0.8873,
"step": 800
},
{
"epoch": 19.07,
"learning_rate": 1.1763589519246388e-07,
"loss": 0.8945,
"step": 801
},
{
"epoch": 19.1,
"learning_rate": 1.1169173774871478e-07,
"loss": 0.9241,
"step": 802
},
{
"epoch": 19.12,
"learning_rate": 1.0590083556827557e-07,
"loss": 0.9776,
"step": 803
},
{
"epoch": 19.14,
"learning_rate": 1.0026327840221728e-07,
"loss": 0.8988,
"step": 804
},
{
"epoch": 19.17,
"learning_rate": 9.47791536249676e-08,
"loss": 0.9342,
"step": 805
},
{
"epoch": 19.19,
"learning_rate": 8.944854623296751e-08,
"loss": 0.9167,
"step": 806
},
{
"epoch": 19.21,
"learning_rate": 8.42715388433446e-08,
"loss": 0.9024,
"step": 807
},
{
"epoch": 19.24,
"learning_rate": 7.924821169263963e-08,
"loss": 0.9438,
"step": 808
},
{
"epoch": 19.26,
"learning_rate": 7.437864263555638e-08,
"loss": 0.8941,
"step": 809
},
{
"epoch": 19.29,
"learning_rate": 6.966290714375934e-08,
"loss": 0.9006,
"step": 810
},
{
"epoch": 19.31,
"learning_rate": 6.510107830470569e-08,
"loss": 0.9158,
"step": 811
},
{
"epoch": 19.33,
"learning_rate": 6.069322682050516e-08,
"loss": 0.9577,
"step": 812
},
{
"epoch": 19.36,
"learning_rate": 5.6439421006833086e-08,
"loss": 0.8756,
"step": 813
},
{
"epoch": 19.38,
"learning_rate": 5.233972679186461e-08,
"loss": 0.9224,
"step": 814
},
{
"epoch": 19.4,
"learning_rate": 4.8394207715257715e-08,
"loss": 0.9459,
"step": 815
},
{
"epoch": 19.43,
"learning_rate": 4.460292492716512e-08,
"loss": 0.9481,
"step": 816
},
{
"epoch": 19.45,
"learning_rate": 4.096593718728725e-08,
"loss": 0.9053,
"step": 817
},
{
"epoch": 19.48,
"learning_rate": 3.748330086396523e-08,
"loss": 0.9107,
"step": 818
},
{
"epoch": 19.5,
"learning_rate": 3.4155069933301535e-08,
"loss": 0.8989,
"step": 819
},
{
"epoch": 19.52,
"learning_rate": 3.098129597832622e-08,
"loss": 0.9167,
"step": 820
},
{
"epoch": 19.55,
"learning_rate": 2.796202818819871e-08,
"loss": 0.9405,
"step": 821
},
{
"epoch": 19.57,
"learning_rate": 2.509731335744281e-08,
"loss": 0.9337,
"step": 822
},
{
"epoch": 19.6,
"learning_rate": 2.238719588522176e-08,
"loss": 0.8863,
"step": 823
},
{
"epoch": 19.62,
"learning_rate": 1.9831717774654314e-08,
"loss": 0.9399,
"step": 824
},
{
"epoch": 19.64,
"learning_rate": 1.7430918632157513e-08,
"loss": 0.8885,
"step": 825
},
{
"epoch": 19.67,
"learning_rate": 1.518483566683826e-08,
"loss": 0.8862,
"step": 826
},
{
"epoch": 19.69,
"learning_rate": 1.309350368991047e-08,
"loss": 0.9073,
"step": 827
},
{
"epoch": 19.71,
"learning_rate": 1.1156955114162149e-08,
"loss": 0.938,
"step": 828
},
{
"epoch": 19.74,
"learning_rate": 9.375219953450254e-09,
"loss": 0.8979,
"step": 829
},
{
"epoch": 19.76,
"learning_rate": 7.748325822234392e-09,
"loss": 0.8994,
"step": 830
},
{
"epoch": 19.79,
"learning_rate": 6.276297935149389e-09,
"loss": 0.8913,
"step": 831
},
{
"epoch": 19.81,
"learning_rate": 4.959159106615596e-09,
"loss": 0.9235,
"step": 832
},
{
"epoch": 19.83,
"learning_rate": 3.7969297504858445e-09,
"loss": 0.8867,
"step": 833
},
{
"epoch": 19.86,
"learning_rate": 2.7896278797256983e-09,
"loss": 0.9064,
"step": 834
},
{
"epoch": 19.88,
"learning_rate": 1.9372691061381177e-09,
"loss": 0.9691,
"step": 835
},
{
"epoch": 19.9,
"learning_rate": 1.2398666401181037e-09,
"loss": 0.9767,
"step": 836
},
{
"epoch": 19.93,
"learning_rate": 6.974312904517444e-10,
"loss": 0.9125,
"step": 837
},
{
"epoch": 19.95,
"learning_rate": 3.0997146414524225e-10,
"loss": 0.8985,
"step": 838
},
{
"epoch": 19.98,
"learning_rate": 7.749316629612757e-11,
"loss": 0.9332,
"step": 839
},
{
"epoch": 20.0,
"learning_rate": 0.0,
"loss": 0.8924,
"step": 840
},
{
"epoch": 20.0,
"step": 840,
"total_flos": 135384939331584.0,
"train_loss": 1.1074120781251362,
"train_runtime": 4158.7267,
"train_samples_per_second": 3.184,
"train_steps_per_second": 0.202
}
],
"logging_steps": 1.0,
"max_steps": 840,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 5000,
"total_flos": 135384939331584.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}