ToolLLaMA-2-7b-v1 / trainer_state.json
pooruss-lsh's picture
upload the rest of files
cbafc01
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9982222222222221,
"global_step": 1686,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 7.352941176470589e-07,
"loss": 1.4934,
"step": 1
},
{
"epoch": 0.0,
"learning_rate": 1.4705882352941177e-06,
"loss": 1.4308,
"step": 2
},
{
"epoch": 0.0,
"learning_rate": 2.2058823529411767e-06,
"loss": 1.5656,
"step": 3
},
{
"epoch": 0.0,
"learning_rate": 2.9411764705882355e-06,
"loss": 1.4176,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 3.6764705882352942e-06,
"loss": 1.3197,
"step": 5
},
{
"epoch": 0.01,
"learning_rate": 4.411764705882353e-06,
"loss": 1.1572,
"step": 6
},
{
"epoch": 0.01,
"learning_rate": 5.147058823529412e-06,
"loss": 0.9889,
"step": 7
},
{
"epoch": 0.01,
"learning_rate": 5.882352941176471e-06,
"loss": 0.7601,
"step": 8
},
{
"epoch": 0.01,
"learning_rate": 6.61764705882353e-06,
"loss": 0.5436,
"step": 9
},
{
"epoch": 0.01,
"learning_rate": 7.3529411764705884e-06,
"loss": 0.5049,
"step": 10
},
{
"epoch": 0.01,
"learning_rate": 8.088235294117648e-06,
"loss": 0.4444,
"step": 11
},
{
"epoch": 0.01,
"learning_rate": 8.823529411764707e-06,
"loss": 0.4241,
"step": 12
},
{
"epoch": 0.02,
"learning_rate": 9.558823529411764e-06,
"loss": 0.406,
"step": 13
},
{
"epoch": 0.02,
"learning_rate": 1.0294117647058824e-05,
"loss": 0.3248,
"step": 14
},
{
"epoch": 0.02,
"learning_rate": 1.1029411764705883e-05,
"loss": 0.3274,
"step": 15
},
{
"epoch": 0.02,
"learning_rate": 1.1764705882352942e-05,
"loss": 0.3797,
"step": 16
},
{
"epoch": 0.02,
"learning_rate": 1.25e-05,
"loss": 0.2718,
"step": 17
},
{
"epoch": 0.02,
"learning_rate": 1.323529411764706e-05,
"loss": 0.26,
"step": 18
},
{
"epoch": 0.02,
"learning_rate": 1.3970588235294118e-05,
"loss": 0.4324,
"step": 19
},
{
"epoch": 0.02,
"learning_rate": 1.4705882352941177e-05,
"loss": 0.2265,
"step": 20
},
{
"epoch": 0.02,
"learning_rate": 1.5441176470588237e-05,
"loss": 0.3209,
"step": 21
},
{
"epoch": 0.03,
"learning_rate": 1.6176470588235296e-05,
"loss": 0.3329,
"step": 22
},
{
"epoch": 0.03,
"learning_rate": 1.6911764705882355e-05,
"loss": 0.2335,
"step": 23
},
{
"epoch": 0.03,
"learning_rate": 1.7647058823529414e-05,
"loss": 0.2215,
"step": 24
},
{
"epoch": 0.03,
"learning_rate": 1.8382352941176472e-05,
"loss": 0.1997,
"step": 25
},
{
"epoch": 0.03,
"learning_rate": 1.9117647058823528e-05,
"loss": 0.2286,
"step": 26
},
{
"epoch": 0.03,
"learning_rate": 1.9852941176470586e-05,
"loss": 0.2931,
"step": 27
},
{
"epoch": 0.03,
"learning_rate": 2.058823529411765e-05,
"loss": 0.2361,
"step": 28
},
{
"epoch": 0.03,
"learning_rate": 2.1323529411764707e-05,
"loss": 0.3129,
"step": 29
},
{
"epoch": 0.04,
"learning_rate": 2.2058823529411766e-05,
"loss": 0.2784,
"step": 30
},
{
"epoch": 0.04,
"learning_rate": 2.2794117647058825e-05,
"loss": 0.2612,
"step": 31
},
{
"epoch": 0.04,
"learning_rate": 2.3529411764705884e-05,
"loss": 0.3002,
"step": 32
},
{
"epoch": 0.04,
"learning_rate": 2.4264705882352942e-05,
"loss": 0.1918,
"step": 33
},
{
"epoch": 0.04,
"learning_rate": 2.5e-05,
"loss": 0.2737,
"step": 34
},
{
"epoch": 0.04,
"learning_rate": 2.5735294117647057e-05,
"loss": 0.3001,
"step": 35
},
{
"epoch": 0.04,
"learning_rate": 2.647058823529412e-05,
"loss": 0.2636,
"step": 36
},
{
"epoch": 0.04,
"learning_rate": 2.7205882352941174e-05,
"loss": 0.2934,
"step": 37
},
{
"epoch": 0.05,
"learning_rate": 2.7941176470588236e-05,
"loss": 0.3193,
"step": 38
},
{
"epoch": 0.05,
"learning_rate": 2.8676470588235295e-05,
"loss": 0.3171,
"step": 39
},
{
"epoch": 0.05,
"learning_rate": 2.9411764705882354e-05,
"loss": 0.2971,
"step": 40
},
{
"epoch": 0.05,
"learning_rate": 3.0147058823529413e-05,
"loss": 0.2394,
"step": 41
},
{
"epoch": 0.05,
"learning_rate": 3.0882352941176475e-05,
"loss": 0.294,
"step": 42
},
{
"epoch": 0.05,
"learning_rate": 3.161764705882353e-05,
"loss": 0.2625,
"step": 43
},
{
"epoch": 0.05,
"learning_rate": 3.235294117647059e-05,
"loss": 0.3554,
"step": 44
},
{
"epoch": 0.05,
"learning_rate": 3.308823529411765e-05,
"loss": 0.3236,
"step": 45
},
{
"epoch": 0.05,
"learning_rate": 3.382352941176471e-05,
"loss": 0.2163,
"step": 46
},
{
"epoch": 0.06,
"learning_rate": 3.455882352941177e-05,
"loss": 0.3002,
"step": 47
},
{
"epoch": 0.06,
"learning_rate": 3.529411764705883e-05,
"loss": 0.3036,
"step": 48
},
{
"epoch": 0.06,
"learning_rate": 3.6029411764705886e-05,
"loss": 0.2182,
"step": 49
},
{
"epoch": 0.06,
"learning_rate": 3.6764705882352945e-05,
"loss": 0.2003,
"step": 50
},
{
"epoch": 0.06,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.3377,
"step": 51
},
{
"epoch": 0.06,
"learning_rate": 3.8235294117647055e-05,
"loss": 0.1783,
"step": 52
},
{
"epoch": 0.06,
"learning_rate": 3.897058823529412e-05,
"loss": 0.2838,
"step": 53
},
{
"epoch": 0.06,
"learning_rate": 3.970588235294117e-05,
"loss": 0.2711,
"step": 54
},
{
"epoch": 0.07,
"learning_rate": 4.044117647058824e-05,
"loss": 0.2823,
"step": 55
},
{
"epoch": 0.07,
"learning_rate": 4.11764705882353e-05,
"loss": 0.3191,
"step": 56
},
{
"epoch": 0.07,
"learning_rate": 4.1911764705882356e-05,
"loss": 0.329,
"step": 57
},
{
"epoch": 0.07,
"learning_rate": 4.2647058823529415e-05,
"loss": 0.1626,
"step": 58
},
{
"epoch": 0.07,
"learning_rate": 4.3382352941176474e-05,
"loss": 0.3719,
"step": 59
},
{
"epoch": 0.07,
"learning_rate": 4.411764705882353e-05,
"loss": 0.2546,
"step": 60
},
{
"epoch": 0.07,
"learning_rate": 4.485294117647059e-05,
"loss": 0.2373,
"step": 61
},
{
"epoch": 0.07,
"learning_rate": 4.558823529411765e-05,
"loss": 0.2828,
"step": 62
},
{
"epoch": 0.07,
"learning_rate": 4.632352941176471e-05,
"loss": 0.2987,
"step": 63
},
{
"epoch": 0.08,
"learning_rate": 4.705882352941177e-05,
"loss": 0.3749,
"step": 64
},
{
"epoch": 0.08,
"learning_rate": 4.7794117647058826e-05,
"loss": 0.2856,
"step": 65
},
{
"epoch": 0.08,
"learning_rate": 4.8529411764705885e-05,
"loss": 0.367,
"step": 66
},
{
"epoch": 0.08,
"learning_rate": 4.9264705882352944e-05,
"loss": 0.3635,
"step": 67
},
{
"epoch": 0.08,
"learning_rate": 5e-05,
"loss": 0.2624,
"step": 68
},
{
"epoch": 0.08,
"learning_rate": 4.9999952874867166e-05,
"loss": 0.3697,
"step": 69
},
{
"epoch": 0.08,
"learning_rate": 4.999981149964632e-05,
"loss": 0.2175,
"step": 70
},
{
"epoch": 0.08,
"learning_rate": 4.9999575874870454e-05,
"loss": 0.2936,
"step": 71
},
{
"epoch": 0.09,
"learning_rate": 4.999924600142787e-05,
"loss": 0.225,
"step": 72
},
{
"epoch": 0.09,
"learning_rate": 4.999882188056219e-05,
"loss": 0.3736,
"step": 73
},
{
"epoch": 0.09,
"learning_rate": 4.999830351387237e-05,
"loss": 0.2763,
"step": 74
},
{
"epoch": 0.09,
"learning_rate": 4.999769090331264e-05,
"loss": 0.3704,
"step": 75
},
{
"epoch": 0.09,
"learning_rate": 4.999698405119256e-05,
"loss": 0.3845,
"step": 76
},
{
"epoch": 0.09,
"learning_rate": 4.999618296017697e-05,
"loss": 0.275,
"step": 77
},
{
"epoch": 0.09,
"learning_rate": 4.999528763328598e-05,
"loss": 0.331,
"step": 78
},
{
"epoch": 0.09,
"learning_rate": 4.9994298073895e-05,
"loss": 0.2806,
"step": 79
},
{
"epoch": 0.09,
"learning_rate": 4.999321428573467e-05,
"loss": 0.2779,
"step": 80
},
{
"epoch": 0.1,
"learning_rate": 4.999203627289087e-05,
"loss": 0.1724,
"step": 81
},
{
"epoch": 0.1,
"learning_rate": 4.999076403980475e-05,
"loss": 0.3406,
"step": 82
},
{
"epoch": 0.1,
"learning_rate": 4.998939759127262e-05,
"loss": 0.3398,
"step": 83
},
{
"epoch": 0.1,
"learning_rate": 4.998793693244601e-05,
"loss": 0.3071,
"step": 84
},
{
"epoch": 0.1,
"learning_rate": 4.998638206883162e-05,
"loss": 0.321,
"step": 85
},
{
"epoch": 0.1,
"learning_rate": 4.9984733006291306e-05,
"loss": 0.2683,
"step": 86
},
{
"epoch": 0.1,
"learning_rate": 4.9982989751042046e-05,
"loss": 0.3641,
"step": 87
},
{
"epoch": 0.1,
"learning_rate": 4.998115230965593e-05,
"loss": 0.2668,
"step": 88
},
{
"epoch": 0.11,
"learning_rate": 4.997922068906015e-05,
"loss": 0.3709,
"step": 89
},
{
"epoch": 0.11,
"learning_rate": 4.9977194896536904e-05,
"loss": 0.2223,
"step": 90
},
{
"epoch": 0.11,
"learning_rate": 4.9975074939723476e-05,
"loss": 0.3262,
"step": 91
},
{
"epoch": 0.11,
"learning_rate": 4.997286082661211e-05,
"loss": 0.3202,
"step": 92
},
{
"epoch": 0.11,
"learning_rate": 4.9970552565550056e-05,
"loss": 0.5339,
"step": 93
},
{
"epoch": 0.11,
"learning_rate": 4.9968150165239455e-05,
"loss": 0.3457,
"step": 94
},
{
"epoch": 0.11,
"learning_rate": 4.9965653634737414e-05,
"loss": 0.2291,
"step": 95
},
{
"epoch": 0.11,
"learning_rate": 4.9963062983455856e-05,
"loss": 0.3465,
"step": 96
},
{
"epoch": 0.11,
"learning_rate": 4.9960378221161566e-05,
"loss": 0.2793,
"step": 97
},
{
"epoch": 0.12,
"learning_rate": 4.9957599357976135e-05,
"loss": 0.3772,
"step": 98
},
{
"epoch": 0.12,
"learning_rate": 4.995472640437591e-05,
"loss": 0.286,
"step": 99
},
{
"epoch": 0.12,
"learning_rate": 4.995175937119194e-05,
"loss": 0.236,
"step": 100
},
{
"epoch": 0.12,
"learning_rate": 4.9948698269609984e-05,
"loss": 0.2889,
"step": 101
},
{
"epoch": 0.12,
"learning_rate": 4.994554311117042e-05,
"loss": 0.3081,
"step": 102
},
{
"epoch": 0.12,
"learning_rate": 4.9942293907768244e-05,
"loss": 0.2765,
"step": 103
},
{
"epoch": 0.12,
"learning_rate": 4.993895067165297e-05,
"loss": 0.2452,
"step": 104
},
{
"epoch": 0.12,
"learning_rate": 4.9935513415428636e-05,
"loss": 0.2907,
"step": 105
},
{
"epoch": 0.13,
"learning_rate": 4.9931982152053744e-05,
"loss": 0.3427,
"step": 106
},
{
"epoch": 0.13,
"learning_rate": 4.9928356894841195e-05,
"loss": 0.4537,
"step": 107
},
{
"epoch": 0.13,
"learning_rate": 4.992463765745824e-05,
"loss": 0.2331,
"step": 108
},
{
"epoch": 0.13,
"learning_rate": 4.992082445392644e-05,
"loss": 0.248,
"step": 109
},
{
"epoch": 0.13,
"learning_rate": 4.991691729862161e-05,
"loss": 0.3122,
"step": 110
},
{
"epoch": 0.13,
"learning_rate": 4.991291620627379e-05,
"loss": 0.3075,
"step": 111
},
{
"epoch": 0.13,
"learning_rate": 4.990882119196712e-05,
"loss": 0.2334,
"step": 112
},
{
"epoch": 0.13,
"learning_rate": 4.990463227113985e-05,
"loss": 0.3013,
"step": 113
},
{
"epoch": 0.14,
"learning_rate": 4.990034945958427e-05,
"loss": 0.3308,
"step": 114
},
{
"epoch": 0.14,
"learning_rate": 4.98959727734466e-05,
"loss": 0.2707,
"step": 115
},
{
"epoch": 0.14,
"learning_rate": 4.989150222922702e-05,
"loss": 0.1658,
"step": 116
},
{
"epoch": 0.14,
"learning_rate": 4.988693784377951e-05,
"loss": 0.339,
"step": 117
},
{
"epoch": 0.14,
"learning_rate": 4.9882279634311855e-05,
"loss": 0.2905,
"step": 118
},
{
"epoch": 0.14,
"learning_rate": 4.987752761838557e-05,
"loss": 0.2974,
"step": 119
},
{
"epoch": 0.14,
"learning_rate": 4.987268181391578e-05,
"loss": 0.3136,
"step": 120
},
{
"epoch": 0.14,
"learning_rate": 4.986774223917123e-05,
"loss": 0.299,
"step": 121
},
{
"epoch": 0.14,
"learning_rate": 4.986270891277418e-05,
"loss": 0.1877,
"step": 122
},
{
"epoch": 0.15,
"learning_rate": 4.985758185370032e-05,
"loss": 0.4754,
"step": 123
},
{
"epoch": 0.15,
"learning_rate": 4.9852361081278704e-05,
"loss": 0.2564,
"step": 124
},
{
"epoch": 0.15,
"learning_rate": 4.984704661519171e-05,
"loss": 0.294,
"step": 125
},
{
"epoch": 0.15,
"learning_rate": 4.9841638475474936e-05,
"loss": 0.2843,
"step": 126
},
{
"epoch": 0.15,
"learning_rate": 4.9836136682517106e-05,
"loss": 0.3276,
"step": 127
},
{
"epoch": 0.15,
"learning_rate": 4.983054125706007e-05,
"loss": 0.3818,
"step": 128
},
{
"epoch": 0.15,
"learning_rate": 4.9824852220198615e-05,
"loss": 0.2484,
"step": 129
},
{
"epoch": 0.15,
"learning_rate": 4.9819069593380475e-05,
"loss": 0.3457,
"step": 130
},
{
"epoch": 0.16,
"learning_rate": 4.981319339840622e-05,
"loss": 0.2792,
"step": 131
},
{
"epoch": 0.16,
"learning_rate": 4.980722365742918e-05,
"loss": 0.2812,
"step": 132
},
{
"epoch": 0.16,
"learning_rate": 4.980116039295531e-05,
"loss": 0.3248,
"step": 133
},
{
"epoch": 0.16,
"learning_rate": 4.9795003627843204e-05,
"loss": 0.3296,
"step": 134
},
{
"epoch": 0.16,
"learning_rate": 4.9788753385303936e-05,
"loss": 0.3651,
"step": 135
},
{
"epoch": 0.16,
"learning_rate": 4.978240968890097e-05,
"loss": 0.2841,
"step": 136
},
{
"epoch": 0.16,
"learning_rate": 4.977597256255012e-05,
"loss": 0.321,
"step": 137
},
{
"epoch": 0.16,
"learning_rate": 4.976944203051942e-05,
"loss": 0.4024,
"step": 138
},
{
"epoch": 0.16,
"learning_rate": 4.9762818117429036e-05,
"loss": 0.3881,
"step": 139
},
{
"epoch": 0.17,
"learning_rate": 4.9756100848251194e-05,
"loss": 0.3207,
"step": 140
},
{
"epoch": 0.17,
"learning_rate": 4.974929024831009e-05,
"loss": 0.292,
"step": 141
},
{
"epoch": 0.17,
"learning_rate": 4.974238634328173e-05,
"loss": 0.2295,
"step": 142
},
{
"epoch": 0.17,
"learning_rate": 4.973538915919392e-05,
"loss": 0.2864,
"step": 143
},
{
"epoch": 0.17,
"learning_rate": 4.9728298722426124e-05,
"loss": 0.274,
"step": 144
},
{
"epoch": 0.17,
"learning_rate": 4.972111505970936e-05,
"loss": 0.3188,
"step": 145
},
{
"epoch": 0.17,
"learning_rate": 4.971383819812612e-05,
"loss": 0.2161,
"step": 146
},
{
"epoch": 0.17,
"learning_rate": 4.970646816511023e-05,
"loss": 0.3466,
"step": 147
},
{
"epoch": 0.18,
"learning_rate": 4.969900498844681e-05,
"loss": 0.3352,
"step": 148
},
{
"epoch": 0.18,
"learning_rate": 4.96914486962721e-05,
"loss": 0.2267,
"step": 149
},
{
"epoch": 0.18,
"learning_rate": 4.9683799317073425e-05,
"loss": 0.329,
"step": 150
},
{
"epoch": 0.18,
"learning_rate": 4.967605687968901e-05,
"loss": 0.2721,
"step": 151
},
{
"epoch": 0.18,
"learning_rate": 4.966822141330793e-05,
"loss": 0.3088,
"step": 152
},
{
"epoch": 0.18,
"learning_rate": 4.966029294746997e-05,
"loss": 0.2308,
"step": 153
},
{
"epoch": 0.18,
"learning_rate": 4.965227151206554e-05,
"loss": 0.3343,
"step": 154
},
{
"epoch": 0.18,
"learning_rate": 4.964415713733553e-05,
"loss": 0.3477,
"step": 155
},
{
"epoch": 0.18,
"learning_rate": 4.9635949853871225e-05,
"loss": 0.2654,
"step": 156
},
{
"epoch": 0.19,
"learning_rate": 4.9627649692614165e-05,
"loss": 0.2521,
"step": 157
},
{
"epoch": 0.19,
"learning_rate": 4.961925668485604e-05,
"loss": 0.3123,
"step": 158
},
{
"epoch": 0.19,
"learning_rate": 4.96107708622386e-05,
"loss": 0.3097,
"step": 159
},
{
"epoch": 0.19,
"learning_rate": 4.960219225675347e-05,
"loss": 0.4019,
"step": 160
},
{
"epoch": 0.19,
"learning_rate": 4.959352090074209e-05,
"loss": 0.3019,
"step": 161
},
{
"epoch": 0.19,
"learning_rate": 4.958475682689556e-05,
"loss": 0.2934,
"step": 162
},
{
"epoch": 0.19,
"learning_rate": 4.9575900068254526e-05,
"loss": 0.2897,
"step": 163
},
{
"epoch": 0.19,
"learning_rate": 4.9566950658209074e-05,
"loss": 0.2571,
"step": 164
},
{
"epoch": 0.2,
"learning_rate": 4.9557908630498573e-05,
"loss": 0.362,
"step": 165
},
{
"epoch": 0.2,
"learning_rate": 4.9548774019211566e-05,
"loss": 0.2667,
"step": 166
},
{
"epoch": 0.2,
"learning_rate": 4.953954685878562e-05,
"loss": 0.2559,
"step": 167
},
{
"epoch": 0.2,
"learning_rate": 4.953022718400724e-05,
"loss": 0.2787,
"step": 168
},
{
"epoch": 0.2,
"learning_rate": 4.952081503001169e-05,
"loss": 0.2514,
"step": 169
},
{
"epoch": 0.2,
"learning_rate": 4.951131043228291e-05,
"loss": 0.3691,
"step": 170
},
{
"epoch": 0.2,
"learning_rate": 4.950171342665332e-05,
"loss": 0.3312,
"step": 171
},
{
"epoch": 0.2,
"learning_rate": 4.949202404930372e-05,
"loss": 0.4162,
"step": 172
},
{
"epoch": 0.21,
"learning_rate": 4.94822423367632e-05,
"loss": 0.3788,
"step": 173
},
{
"epoch": 0.21,
"learning_rate": 4.947236832590888e-05,
"loss": 0.3016,
"step": 174
},
{
"epoch": 0.21,
"learning_rate": 4.9462402053965914e-05,
"loss": 0.3429,
"step": 175
},
{
"epoch": 0.21,
"learning_rate": 4.945234355850725e-05,
"loss": 0.2481,
"step": 176
},
{
"epoch": 0.21,
"learning_rate": 4.9442192877453516e-05,
"loss": 0.2757,
"step": 177
},
{
"epoch": 0.21,
"learning_rate": 4.9431950049072895e-05,
"loss": 0.2579,
"step": 178
},
{
"epoch": 0.21,
"learning_rate": 4.942161511198094e-05,
"loss": 0.3994,
"step": 179
},
{
"epoch": 0.21,
"learning_rate": 4.9411188105140505e-05,
"loss": 0.248,
"step": 180
},
{
"epoch": 0.21,
"learning_rate": 4.9400669067861486e-05,
"loss": 0.3515,
"step": 181
},
{
"epoch": 0.22,
"learning_rate": 4.939005803980078e-05,
"loss": 0.3575,
"step": 182
},
{
"epoch": 0.22,
"learning_rate": 4.937935506096207e-05,
"loss": 0.2387,
"step": 183
},
{
"epoch": 0.22,
"learning_rate": 4.936856017169572e-05,
"loss": 0.3204,
"step": 184
},
{
"epoch": 0.22,
"learning_rate": 4.9357673412698544e-05,
"loss": 0.3025,
"step": 185
},
{
"epoch": 0.22,
"learning_rate": 4.934669482501376e-05,
"loss": 0.248,
"step": 186
},
{
"epoch": 0.22,
"learning_rate": 4.933562445003076e-05,
"loss": 0.2191,
"step": 187
},
{
"epoch": 0.22,
"learning_rate": 4.932446232948497e-05,
"loss": 0.3097,
"step": 188
},
{
"epoch": 0.22,
"learning_rate": 4.93132085054577e-05,
"loss": 0.4397,
"step": 189
},
{
"epoch": 0.23,
"learning_rate": 4.9301863020375996e-05,
"loss": 0.2615,
"step": 190
},
{
"epoch": 0.23,
"learning_rate": 4.929042591701245e-05,
"loss": 0.3,
"step": 191
},
{
"epoch": 0.23,
"learning_rate": 4.9278897238485066e-05,
"loss": 0.3201,
"step": 192
},
{
"epoch": 0.23,
"learning_rate": 4.926727702825708e-05,
"loss": 0.2454,
"step": 193
},
{
"epoch": 0.23,
"learning_rate": 4.925556533013682e-05,
"loss": 0.328,
"step": 194
},
{
"epoch": 0.23,
"learning_rate": 4.9243762188277495e-05,
"loss": 0.2571,
"step": 195
},
{
"epoch": 0.23,
"learning_rate": 4.923186764717709e-05,
"loss": 0.3189,
"step": 196
},
{
"epoch": 0.23,
"learning_rate": 4.9219881751678146e-05,
"loss": 0.3703,
"step": 197
},
{
"epoch": 0.23,
"learning_rate": 4.9207804546967613e-05,
"loss": 0.442,
"step": 198
},
{
"epoch": 0.24,
"learning_rate": 4.9195636078576684e-05,
"loss": 0.3707,
"step": 199
},
{
"epoch": 0.24,
"learning_rate": 4.918337639238062e-05,
"loss": 0.2851,
"step": 200
},
{
"epoch": 0.24,
"learning_rate": 4.917102553459856e-05,
"loss": 0.323,
"step": 201
},
{
"epoch": 0.24,
"learning_rate": 4.9158583551793367e-05,
"loss": 0.2701,
"step": 202
},
{
"epoch": 0.24,
"learning_rate": 4.914605049087146e-05,
"loss": 0.3427,
"step": 203
},
{
"epoch": 0.24,
"learning_rate": 4.91334263990826e-05,
"loss": 0.329,
"step": 204
},
{
"epoch": 0.24,
"learning_rate": 4.912071132401975e-05,
"loss": 0.3434,
"step": 205
},
{
"epoch": 0.24,
"learning_rate": 4.9107905313618894e-05,
"loss": 0.3047,
"step": 206
},
{
"epoch": 0.25,
"learning_rate": 4.9095008416158805e-05,
"loss": 0.2534,
"step": 207
},
{
"epoch": 0.25,
"learning_rate": 4.908202068026093e-05,
"loss": 0.2302,
"step": 208
},
{
"epoch": 0.25,
"learning_rate": 4.906894215488917e-05,
"loss": 0.3817,
"step": 209
},
{
"epoch": 0.25,
"learning_rate": 4.905577288934971e-05,
"loss": 0.2872,
"step": 210
},
{
"epoch": 0.25,
"learning_rate": 4.904251293329083e-05,
"loss": 0.2572,
"step": 211
},
{
"epoch": 0.25,
"learning_rate": 4.902916233670269e-05,
"loss": 0.2797,
"step": 212
},
{
"epoch": 0.25,
"learning_rate": 4.9015721149917184e-05,
"loss": 0.2026,
"step": 213
},
{
"epoch": 0.25,
"learning_rate": 4.900218942360772e-05,
"loss": 0.2158,
"step": 214
},
{
"epoch": 0.25,
"learning_rate": 4.898856720878908e-05,
"loss": 0.442,
"step": 215
},
{
"epoch": 0.26,
"learning_rate": 4.897485455681713e-05,
"loss": 0.2516,
"step": 216
},
{
"epoch": 0.26,
"learning_rate": 4.896105151938872e-05,
"loss": 0.2612,
"step": 217
},
{
"epoch": 0.26,
"learning_rate": 4.894715814854145e-05,
"loss": 0.377,
"step": 218
},
{
"epoch": 0.26,
"learning_rate": 4.8933174496653476e-05,
"loss": 0.2989,
"step": 219
},
{
"epoch": 0.26,
"learning_rate": 4.891910061644332e-05,
"loss": 0.307,
"step": 220
},
{
"epoch": 0.26,
"learning_rate": 4.890493656096965e-05,
"loss": 0.3227,
"step": 221
},
{
"epoch": 0.26,
"learning_rate": 4.8890682383631115e-05,
"loss": 0.3266,
"step": 222
},
{
"epoch": 0.26,
"learning_rate": 4.8876338138166106e-05,
"loss": 0.2701,
"step": 223
},
{
"epoch": 0.27,
"learning_rate": 4.886190387865258e-05,
"loss": 0.1774,
"step": 224
},
{
"epoch": 0.27,
"learning_rate": 4.884737965950786e-05,
"loss": 0.3749,
"step": 225
},
{
"epoch": 0.27,
"learning_rate": 4.8832765535488404e-05,
"loss": 0.3485,
"step": 226
},
{
"epoch": 0.27,
"learning_rate": 4.881806156168961e-05,
"loss": 0.3136,
"step": 227
},
{
"epoch": 0.27,
"learning_rate": 4.880326779354561e-05,
"loss": 0.3249,
"step": 228
},
{
"epoch": 0.27,
"learning_rate": 4.878838428682908e-05,
"loss": 0.2764,
"step": 229
},
{
"epoch": 0.27,
"learning_rate": 4.877341109765099e-05,
"loss": 0.2733,
"step": 230
},
{
"epoch": 0.27,
"learning_rate": 4.875834828246042e-05,
"loss": 0.3222,
"step": 231
},
{
"epoch": 0.27,
"learning_rate": 4.874319589804436e-05,
"loss": 0.2733,
"step": 232
},
{
"epoch": 0.28,
"learning_rate": 4.872795400152743e-05,
"loss": 0.2473,
"step": 233
},
{
"epoch": 0.28,
"learning_rate": 4.871262265037178e-05,
"loss": 0.2949,
"step": 234
},
{
"epoch": 0.28,
"learning_rate": 4.869720190237673e-05,
"loss": 0.1997,
"step": 235
},
{
"epoch": 0.28,
"learning_rate": 4.868169181567869e-05,
"loss": 0.3084,
"step": 236
},
{
"epoch": 0.28,
"learning_rate": 4.866609244875084e-05,
"loss": 0.3271,
"step": 237
},
{
"epoch": 0.28,
"learning_rate": 4.865040386040296e-05,
"loss": 0.3074,
"step": 238
},
{
"epoch": 0.28,
"learning_rate": 4.86346261097812e-05,
"loss": 0.2595,
"step": 239
},
{
"epoch": 0.28,
"learning_rate": 4.861875925636784e-05,
"loss": 0.2023,
"step": 240
},
{
"epoch": 0.29,
"learning_rate": 4.8602803359981084e-05,
"loss": 0.2991,
"step": 241
},
{
"epoch": 0.29,
"learning_rate": 4.858675848077485e-05,
"loss": 0.2447,
"step": 242
},
{
"epoch": 0.29,
"learning_rate": 4.857062467923848e-05,
"loss": 0.33,
"step": 243
},
{
"epoch": 0.29,
"learning_rate": 4.855440201619659e-05,
"loss": 0.3225,
"step": 244
},
{
"epoch": 0.29,
"learning_rate": 4.853809055280879e-05,
"loss": 0.2931,
"step": 245
},
{
"epoch": 0.29,
"learning_rate": 4.852169035056947e-05,
"loss": 0.3839,
"step": 246
},
{
"epoch": 0.29,
"learning_rate": 4.850520147130756e-05,
"loss": 0.3014,
"step": 247
},
{
"epoch": 0.29,
"learning_rate": 4.848862397718632e-05,
"loss": 0.3673,
"step": 248
},
{
"epoch": 0.3,
"learning_rate": 4.8471957930703074e-05,
"loss": 0.2698,
"step": 249
},
{
"epoch": 0.3,
"learning_rate": 4.8455203394689e-05,
"loss": 0.3481,
"step": 250
},
{
"epoch": 0.3,
"learning_rate": 4.843836043230886e-05,
"loss": 0.3211,
"step": 251
},
{
"epoch": 0.3,
"learning_rate": 4.842142910706083e-05,
"loss": 0.3669,
"step": 252
},
{
"epoch": 0.3,
"learning_rate": 4.840440948277616e-05,
"loss": 0.3269,
"step": 253
},
{
"epoch": 0.3,
"learning_rate": 4.838730162361903e-05,
"loss": 0.2302,
"step": 254
},
{
"epoch": 0.3,
"learning_rate": 4.8370105594086236e-05,
"loss": 0.3316,
"step": 255
},
{
"epoch": 0.3,
"learning_rate": 4.8352821459007005e-05,
"loss": 0.2298,
"step": 256
},
{
"epoch": 0.3,
"learning_rate": 4.833544928354271e-05,
"loss": 0.2148,
"step": 257
},
{
"epoch": 0.31,
"learning_rate": 4.8317989133186624e-05,
"loss": 0.2909,
"step": 258
},
{
"epoch": 0.31,
"learning_rate": 4.8300441073763717e-05,
"loss": 0.2634,
"step": 259
},
{
"epoch": 0.31,
"learning_rate": 4.8282805171430346e-05,
"loss": 0.3172,
"step": 260
},
{
"epoch": 0.31,
"learning_rate": 4.826508149267406e-05,
"loss": 0.2554,
"step": 261
},
{
"epoch": 0.31,
"learning_rate": 4.82472701043133e-05,
"loss": 0.3023,
"step": 262
},
{
"epoch": 0.31,
"learning_rate": 4.822937107349721e-05,
"loss": 0.3491,
"step": 263
},
{
"epoch": 0.31,
"learning_rate": 4.8211384467705315e-05,
"loss": 0.259,
"step": 264
},
{
"epoch": 0.31,
"learning_rate": 4.819331035474731e-05,
"loss": 0.3185,
"step": 265
},
{
"epoch": 0.32,
"learning_rate": 4.81751488027628e-05,
"loss": 0.3491,
"step": 266
},
{
"epoch": 0.32,
"learning_rate": 4.8156899880221016e-05,
"loss": 0.4103,
"step": 267
},
{
"epoch": 0.32,
"learning_rate": 4.813856365592061e-05,
"loss": 0.2375,
"step": 268
},
{
"epoch": 0.32,
"learning_rate": 4.812014019898932e-05,
"loss": 0.3101,
"step": 269
},
{
"epoch": 0.32,
"learning_rate": 4.810162957888379e-05,
"loss": 0.2408,
"step": 270
},
{
"epoch": 0.32,
"learning_rate": 4.808303186538925e-05,
"loss": 0.3545,
"step": 271
},
{
"epoch": 0.32,
"learning_rate": 4.806434712861927e-05,
"loss": 0.2684,
"step": 272
},
{
"epoch": 0.32,
"learning_rate": 4.8045575439015514e-05,
"loss": 0.2132,
"step": 273
},
{
"epoch": 0.32,
"learning_rate": 4.8026716867347456e-05,
"loss": 0.2239,
"step": 274
},
{
"epoch": 0.33,
"learning_rate": 4.80077714847121e-05,
"loss": 0.2421,
"step": 275
},
{
"epoch": 0.33,
"learning_rate": 4.798873936253375e-05,
"loss": 0.3354,
"step": 276
},
{
"epoch": 0.33,
"learning_rate": 4.79696205725637e-05,
"loss": 0.2413,
"step": 277
},
{
"epoch": 0.33,
"learning_rate": 4.795041518688001e-05,
"loss": 0.2617,
"step": 278
},
{
"epoch": 0.33,
"learning_rate": 4.793112327788716e-05,
"loss": 0.3021,
"step": 279
},
{
"epoch": 0.33,
"learning_rate": 4.791174491831586e-05,
"loss": 0.3067,
"step": 280
},
{
"epoch": 0.33,
"learning_rate": 4.789228018122275e-05,
"loss": 0.386,
"step": 281
},
{
"epoch": 0.33,
"learning_rate": 4.787272913999008e-05,
"loss": 0.3342,
"step": 282
},
{
"epoch": 0.34,
"learning_rate": 4.7853091868325485e-05,
"loss": 0.3078,
"step": 283
},
{
"epoch": 0.34,
"learning_rate": 4.783336844026169e-05,
"loss": 0.2851,
"step": 284
},
{
"epoch": 0.34,
"learning_rate": 4.781355893015623e-05,
"loss": 0.2788,
"step": 285
},
{
"epoch": 0.34,
"learning_rate": 4.7793663412691164e-05,
"loss": 0.3291,
"step": 286
},
{
"epoch": 0.34,
"learning_rate": 4.777368196287281e-05,
"loss": 0.2228,
"step": 287
},
{
"epoch": 0.34,
"learning_rate": 4.775361465603143e-05,
"loss": 0.1885,
"step": 288
},
{
"epoch": 0.34,
"learning_rate": 4.773346156782101e-05,
"loss": 0.3855,
"step": 289
},
{
"epoch": 0.34,
"learning_rate": 4.771322277421889e-05,
"loss": 0.2679,
"step": 290
},
{
"epoch": 0.34,
"learning_rate": 4.769289835152554e-05,
"loss": 0.285,
"step": 291
},
{
"epoch": 0.35,
"learning_rate": 4.767248837636425e-05,
"loss": 0.2531,
"step": 292
},
{
"epoch": 0.35,
"learning_rate": 4.7651992925680846e-05,
"loss": 0.2426,
"step": 293
},
{
"epoch": 0.35,
"learning_rate": 4.7631412076743386e-05,
"loss": 0.2714,
"step": 294
},
{
"epoch": 0.35,
"learning_rate": 4.761074590714189e-05,
"loss": 0.2188,
"step": 295
},
{
"epoch": 0.35,
"learning_rate": 4.7589994494788056e-05,
"loss": 0.2659,
"step": 296
},
{
"epoch": 0.35,
"learning_rate": 4.756915791791491e-05,
"loss": 0.3369,
"step": 297
},
{
"epoch": 0.35,
"learning_rate": 4.754823625507657e-05,
"loss": 0.2152,
"step": 298
},
{
"epoch": 0.35,
"learning_rate": 4.752722958514794e-05,
"loss": 0.3117,
"step": 299
},
{
"epoch": 0.36,
"learning_rate": 4.7506137987324375e-05,
"loss": 0.2674,
"step": 300
},
{
"epoch": 0.36,
"learning_rate": 4.748496154112142e-05,
"loss": 0.2886,
"step": 301
},
{
"epoch": 0.36,
"learning_rate": 4.746370032637452e-05,
"loss": 0.2769,
"step": 302
},
{
"epoch": 0.36,
"learning_rate": 4.744235442323866e-05,
"loss": 0.2641,
"step": 303
},
{
"epoch": 0.36,
"learning_rate": 4.742092391218814e-05,
"loss": 0.2774,
"step": 304
},
{
"epoch": 0.36,
"learning_rate": 4.7399408874016206e-05,
"loss": 0.3404,
"step": 305
},
{
"epoch": 0.36,
"learning_rate": 4.737780938983478e-05,
"loss": 0.2063,
"step": 306
},
{
"epoch": 0.36,
"learning_rate": 4.735612554107415e-05,
"loss": 0.2887,
"step": 307
},
{
"epoch": 0.37,
"learning_rate": 4.733435740948265e-05,
"loss": 0.4375,
"step": 308
},
{
"epoch": 0.37,
"learning_rate": 4.731250507712637e-05,
"loss": 0.2218,
"step": 309
},
{
"epoch": 0.37,
"learning_rate": 4.7290568626388844e-05,
"loss": 0.3174,
"step": 310
},
{
"epoch": 0.37,
"learning_rate": 4.726854813997071e-05,
"loss": 0.3613,
"step": 311
},
{
"epoch": 0.37,
"learning_rate": 4.7246443700889453e-05,
"loss": 0.2768,
"step": 312
},
{
"epoch": 0.37,
"learning_rate": 4.722425539247902e-05,
"loss": 0.29,
"step": 313
},
{
"epoch": 0.37,
"learning_rate": 4.7201983298389595e-05,
"loss": 0.2188,
"step": 314
},
{
"epoch": 0.37,
"learning_rate": 4.717962750258719e-05,
"loss": 0.2425,
"step": 315
},
{
"epoch": 0.37,
"learning_rate": 4.71571880893534e-05,
"loss": 0.2412,
"step": 316
},
{
"epoch": 0.38,
"learning_rate": 4.713466514328505e-05,
"loss": 0.2124,
"step": 317
},
{
"epoch": 0.38,
"learning_rate": 4.7112058749293894e-05,
"loss": 0.3265,
"step": 318
},
{
"epoch": 0.38,
"learning_rate": 4.708936899260626e-05,
"loss": 0.1941,
"step": 319
},
{
"epoch": 0.38,
"learning_rate": 4.7066595958762794e-05,
"loss": 0.2355,
"step": 320
},
{
"epoch": 0.38,
"learning_rate": 4.7043739733618066e-05,
"loss": 0.304,
"step": 321
},
{
"epoch": 0.38,
"learning_rate": 4.702080040334027e-05,
"loss": 0.3028,
"step": 322
},
{
"epoch": 0.38,
"learning_rate": 4.6997778054410956e-05,
"loss": 0.2999,
"step": 323
},
{
"epoch": 0.38,
"learning_rate": 4.6974672773624606e-05,
"loss": 0.3101,
"step": 324
},
{
"epoch": 0.39,
"learning_rate": 4.695148464808837e-05,
"loss": 0.379,
"step": 325
},
{
"epoch": 0.39,
"learning_rate": 4.692821376522174e-05,
"loss": 0.2935,
"step": 326
},
{
"epoch": 0.39,
"learning_rate": 4.690486021275619e-05,
"loss": 0.2777,
"step": 327
},
{
"epoch": 0.39,
"learning_rate": 4.688142407873485e-05,
"loss": 0.2829,
"step": 328
},
{
"epoch": 0.39,
"learning_rate": 4.6857905451512205e-05,
"loss": 0.2161,
"step": 329
},
{
"epoch": 0.39,
"learning_rate": 4.683430441975373e-05,
"loss": 0.286,
"step": 330
},
{
"epoch": 0.39,
"learning_rate": 4.6810621072435553e-05,
"loss": 0.298,
"step": 331
},
{
"epoch": 0.39,
"learning_rate": 4.6786855498844165e-05,
"loss": 0.2971,
"step": 332
},
{
"epoch": 0.39,
"learning_rate": 4.676300778857601e-05,
"loss": 0.4267,
"step": 333
},
{
"epoch": 0.4,
"learning_rate": 4.6739078031537226e-05,
"loss": 0.4661,
"step": 334
},
{
"epoch": 0.4,
"learning_rate": 4.6715066317943246e-05,
"loss": 0.2975,
"step": 335
},
{
"epoch": 0.4,
"learning_rate": 4.669097273831847e-05,
"loss": 0.3425,
"step": 336
},
{
"epoch": 0.4,
"learning_rate": 4.666679738349597e-05,
"loss": 0.2916,
"step": 337
},
{
"epoch": 0.4,
"learning_rate": 4.664254034461709e-05,
"loss": 0.2832,
"step": 338
},
{
"epoch": 0.4,
"learning_rate": 4.6618201713131116e-05,
"loss": 0.3136,
"step": 339
},
{
"epoch": 0.4,
"learning_rate": 4.659378158079495e-05,
"loss": 0.3325,
"step": 340
},
{
"epoch": 0.4,
"learning_rate": 4.6569280039672747e-05,
"loss": 0.3296,
"step": 341
},
{
"epoch": 0.41,
"learning_rate": 4.654469718213558e-05,
"loss": 0.2936,
"step": 342
},
{
"epoch": 0.41,
"learning_rate": 4.6520033100861084e-05,
"loss": 0.2644,
"step": 343
},
{
"epoch": 0.41,
"learning_rate": 4.649528788883311e-05,
"loss": 0.2932,
"step": 344
},
{
"epoch": 0.41,
"learning_rate": 4.6470461639341365e-05,
"loss": 0.376,
"step": 345
},
{
"epoch": 0.41,
"learning_rate": 4.644555444598107e-05,
"loss": 0.3354,
"step": 346
},
{
"epoch": 0.41,
"learning_rate": 4.6420566402652623e-05,
"loss": 0.2584,
"step": 347
},
{
"epoch": 0.41,
"learning_rate": 4.63954976035612e-05,
"loss": 0.2196,
"step": 348
},
{
"epoch": 0.41,
"learning_rate": 4.6370348143216436e-05,
"loss": 0.3061,
"step": 349
},
{
"epoch": 0.41,
"learning_rate": 4.6345118116432085e-05,
"loss": 0.3528,
"step": 350
},
{
"epoch": 0.42,
"learning_rate": 4.63198076183256e-05,
"loss": 0.2717,
"step": 351
},
{
"epoch": 0.42,
"learning_rate": 4.629441674431783e-05,
"loss": 0.4058,
"step": 352
},
{
"epoch": 0.42,
"learning_rate": 4.626894559013263e-05,
"loss": 0.3199,
"step": 353
},
{
"epoch": 0.42,
"learning_rate": 4.6243394251796544e-05,
"loss": 0.362,
"step": 354
},
{
"epoch": 0.42,
"learning_rate": 4.621776282563838e-05,
"loss": 0.2788,
"step": 355
},
{
"epoch": 0.42,
"learning_rate": 4.6192051408288875e-05,
"loss": 0.2861,
"step": 356
},
{
"epoch": 0.42,
"learning_rate": 4.616626009668036e-05,
"loss": 0.2636,
"step": 357
},
{
"epoch": 0.42,
"learning_rate": 4.6140388988046345e-05,
"loss": 0.2872,
"step": 358
},
{
"epoch": 0.43,
"learning_rate": 4.611443817992119e-05,
"loss": 0.2773,
"step": 359
},
{
"epoch": 0.43,
"learning_rate": 4.6088407770139726e-05,
"loss": 0.2935,
"step": 360
},
{
"epoch": 0.43,
"learning_rate": 4.606229785683686e-05,
"loss": 0.3182,
"step": 361
},
{
"epoch": 0.43,
"learning_rate": 4.603610853844724e-05,
"loss": 0.2632,
"step": 362
},
{
"epoch": 0.43,
"learning_rate": 4.600983991370489e-05,
"loss": 0.2177,
"step": 363
},
{
"epoch": 0.43,
"learning_rate": 4.5983492081642784e-05,
"loss": 0.3008,
"step": 364
},
{
"epoch": 0.43,
"learning_rate": 4.595706514159255e-05,
"loss": 0.2536,
"step": 365
},
{
"epoch": 0.43,
"learning_rate": 4.593055919318402e-05,
"loss": 0.2911,
"step": 366
},
{
"epoch": 0.43,
"learning_rate": 4.590397433634491e-05,
"loss": 0.2796,
"step": 367
},
{
"epoch": 0.44,
"learning_rate": 4.5877310671300414e-05,
"loss": 0.2053,
"step": 368
},
{
"epoch": 0.44,
"learning_rate": 4.585056829857281e-05,
"loss": 0.3824,
"step": 369
},
{
"epoch": 0.44,
"learning_rate": 4.582374731898115e-05,
"loss": 0.3492,
"step": 370
},
{
"epoch": 0.44,
"learning_rate": 4.579684783364081e-05,
"loss": 0.2639,
"step": 371
},
{
"epoch": 0.44,
"learning_rate": 4.576986994396313e-05,
"loss": 0.2315,
"step": 372
},
{
"epoch": 0.44,
"learning_rate": 4.5742813751655046e-05,
"loss": 0.2623,
"step": 373
},
{
"epoch": 0.44,
"learning_rate": 4.571567935871868e-05,
"loss": 0.2882,
"step": 374
},
{
"epoch": 0.44,
"learning_rate": 4.568846686745098e-05,
"loss": 0.1957,
"step": 375
},
{
"epoch": 0.45,
"learning_rate": 4.5661176380443354e-05,
"loss": 0.2981,
"step": 376
},
{
"epoch": 0.45,
"learning_rate": 4.56338080005812e-05,
"loss": 0.3681,
"step": 377
},
{
"epoch": 0.45,
"learning_rate": 4.560636183104361e-05,
"loss": 0.2598,
"step": 378
},
{
"epoch": 0.45,
"learning_rate": 4.557883797530295e-05,
"loss": 0.3944,
"step": 379
},
{
"epoch": 0.45,
"learning_rate": 4.555123653712441e-05,
"loss": 0.3041,
"step": 380
},
{
"epoch": 0.45,
"learning_rate": 4.552355762056575e-05,
"loss": 0.2686,
"step": 381
},
{
"epoch": 0.45,
"learning_rate": 4.549580132997675e-05,
"loss": 0.3159,
"step": 382
},
{
"epoch": 0.45,
"learning_rate": 4.546796776999893e-05,
"loss": 0.1752,
"step": 383
},
{
"epoch": 0.46,
"learning_rate": 4.54400570455651e-05,
"loss": 0.2823,
"step": 384
},
{
"epoch": 0.46,
"learning_rate": 4.5412069261899e-05,
"loss": 0.2172,
"step": 385
},
{
"epoch": 0.46,
"learning_rate": 4.5384004524514875e-05,
"loss": 0.3612,
"step": 386
},
{
"epoch": 0.46,
"learning_rate": 4.535586293921707e-05,
"loss": 0.3427,
"step": 387
},
{
"epoch": 0.46,
"learning_rate": 4.532764461209965e-05,
"loss": 0.3054,
"step": 388
},
{
"epoch": 0.46,
"learning_rate": 4.529934964954603e-05,
"loss": 0.2617,
"step": 389
},
{
"epoch": 0.46,
"learning_rate": 4.527097815822852e-05,
"loss": 0.2361,
"step": 390
},
{
"epoch": 0.46,
"learning_rate": 4.524253024510793e-05,
"loss": 0.2966,
"step": 391
},
{
"epoch": 0.46,
"learning_rate": 4.5214006017433206e-05,
"loss": 0.207,
"step": 392
},
{
"epoch": 0.47,
"learning_rate": 4.518540558274098e-05,
"loss": 0.307,
"step": 393
},
{
"epoch": 0.47,
"learning_rate": 4.51567290488552e-05,
"loss": 0.2536,
"step": 394
},
{
"epoch": 0.47,
"learning_rate": 4.5127976523886707e-05,
"loss": 0.1883,
"step": 395
},
{
"epoch": 0.47,
"learning_rate": 4.509914811623282e-05,
"loss": 0.7126,
"step": 396
},
{
"epoch": 0.47,
"learning_rate": 4.507024393457693e-05,
"loss": 0.2616,
"step": 397
},
{
"epoch": 0.47,
"learning_rate": 4.504126408788814e-05,
"loss": 0.234,
"step": 398
},
{
"epoch": 0.47,
"learning_rate": 4.501220868542075e-05,
"loss": 0.3386,
"step": 399
},
{
"epoch": 0.47,
"learning_rate": 4.498307783671395e-05,
"loss": 0.2801,
"step": 400
},
{
"epoch": 0.48,
"learning_rate": 4.4953871651591354e-05,
"loss": 0.3349,
"step": 401
},
{
"epoch": 0.48,
"learning_rate": 4.492459024016058e-05,
"loss": 0.4669,
"step": 402
},
{
"epoch": 0.48,
"learning_rate": 4.4895233712812866e-05,
"loss": 0.1998,
"step": 403
},
{
"epoch": 0.48,
"learning_rate": 4.486580218022263e-05,
"loss": 0.4003,
"step": 404
},
{
"epoch": 0.48,
"learning_rate": 4.483629575334707e-05,
"loss": 0.3852,
"step": 405
},
{
"epoch": 0.48,
"learning_rate": 4.480671454342571e-05,
"loss": 0.2936,
"step": 406
},
{
"epoch": 0.48,
"learning_rate": 4.477705866198004e-05,
"loss": 0.2771,
"step": 407
},
{
"epoch": 0.48,
"learning_rate": 4.4747328220813054e-05,
"loss": 0.2904,
"step": 408
},
{
"epoch": 0.48,
"learning_rate": 4.471752333200882e-05,
"loss": 0.2923,
"step": 409
},
{
"epoch": 0.49,
"learning_rate": 4.468764410793208e-05,
"loss": 0.3194,
"step": 410
},
{
"epoch": 0.49,
"learning_rate": 4.465769066122784e-05,
"loss": 0.248,
"step": 411
},
{
"epoch": 0.49,
"learning_rate": 4.46276631048209e-05,
"loss": 0.4047,
"step": 412
},
{
"epoch": 0.49,
"learning_rate": 4.459756155191549e-05,
"loss": 0.2548,
"step": 413
},
{
"epoch": 0.49,
"learning_rate": 4.4567386115994756e-05,
"loss": 0.3067,
"step": 414
},
{
"epoch": 0.49,
"learning_rate": 4.4537136910820426e-05,
"loss": 0.2111,
"step": 415
},
{
"epoch": 0.49,
"learning_rate": 4.450681405043232e-05,
"loss": 0.221,
"step": 416
},
{
"epoch": 0.49,
"learning_rate": 4.447641764914796e-05,
"loss": 0.2154,
"step": 417
},
{
"epoch": 0.5,
"learning_rate": 4.4445947821562087e-05,
"loss": 0.4225,
"step": 418
},
{
"epoch": 0.5,
"learning_rate": 4.441540468254626e-05,
"loss": 0.2937,
"step": 419
},
{
"epoch": 0.5,
"learning_rate": 4.438478834724847e-05,
"loss": 0.2467,
"step": 420
},
{
"epoch": 0.5,
"learning_rate": 4.43540989310926e-05,
"loss": 0.2943,
"step": 421
},
{
"epoch": 0.5,
"learning_rate": 4.432333654977809e-05,
"loss": 0.331,
"step": 422
},
{
"epoch": 0.5,
"learning_rate": 4.429250131927945e-05,
"loss": 0.2773,
"step": 423
},
{
"epoch": 0.5,
"learning_rate": 4.426159335584581e-05,
"loss": 0.262,
"step": 424
},
{
"epoch": 0.5,
"learning_rate": 4.423061277600053e-05,
"loss": 0.3498,
"step": 425
},
{
"epoch": 0.5,
"learning_rate": 4.4199559696540716e-05,
"loss": 0.4043,
"step": 426
},
{
"epoch": 0.51,
"learning_rate": 4.4168434234536825e-05,
"loss": 0.2111,
"step": 427
},
{
"epoch": 0.51,
"learning_rate": 4.413723650733216e-05,
"loss": 0.3302,
"step": 428
},
{
"epoch": 0.51,
"learning_rate": 4.4105966632542495e-05,
"loss": 0.3073,
"step": 429
},
{
"epoch": 0.51,
"learning_rate": 4.407462472805559e-05,
"loss": 0.2049,
"step": 430
},
{
"epoch": 0.51,
"learning_rate": 4.404321091203076e-05,
"loss": 0.2015,
"step": 431
},
{
"epoch": 0.51,
"learning_rate": 4.401172530289842e-05,
"loss": 0.262,
"step": 432
},
{
"epoch": 0.51,
"learning_rate": 4.3980168019359645e-05,
"loss": 0.3501,
"step": 433
},
{
"epoch": 0.51,
"learning_rate": 4.3948539180385744e-05,
"loss": 0.2372,
"step": 434
},
{
"epoch": 0.52,
"learning_rate": 4.391683890521777e-05,
"loss": 0.307,
"step": 435
},
{
"epoch": 0.52,
"learning_rate": 4.388506731336609e-05,
"loss": 0.2429,
"step": 436
},
{
"epoch": 0.52,
"learning_rate": 4.385322452460995e-05,
"loss": 0.2586,
"step": 437
},
{
"epoch": 0.52,
"learning_rate": 4.382131065899701e-05,
"loss": 0.278,
"step": 438
},
{
"epoch": 0.52,
"learning_rate": 4.378932583684286e-05,
"loss": 0.4167,
"step": 439
},
{
"epoch": 0.52,
"learning_rate": 4.375727017873065e-05,
"loss": 0.3226,
"step": 440
},
{
"epoch": 0.52,
"learning_rate": 4.372514380551052e-05,
"loss": 0.2661,
"step": 441
},
{
"epoch": 0.52,
"learning_rate": 4.369294683829926e-05,
"loss": 0.3259,
"step": 442
},
{
"epoch": 0.53,
"learning_rate": 4.366067939847977e-05,
"loss": 0.2947,
"step": 443
},
{
"epoch": 0.53,
"learning_rate": 4.362834160770064e-05,
"loss": 0.4092,
"step": 444
},
{
"epoch": 0.53,
"learning_rate": 4.359593358787569e-05,
"loss": 0.2933,
"step": 445
},
{
"epoch": 0.53,
"learning_rate": 4.35634554611835e-05,
"loss": 0.3961,
"step": 446
},
{
"epoch": 0.53,
"learning_rate": 4.353090735006695e-05,
"loss": 0.298,
"step": 447
},
{
"epoch": 0.53,
"learning_rate": 4.349828937723276e-05,
"loss": 0.3062,
"step": 448
},
{
"epoch": 0.53,
"learning_rate": 4.346560166565105e-05,
"loss": 0.3218,
"step": 449
},
{
"epoch": 0.53,
"learning_rate": 4.343284433855481e-05,
"loss": 0.3342,
"step": 450
},
{
"epoch": 0.53,
"learning_rate": 4.340001751943954e-05,
"loss": 0.37,
"step": 451
},
{
"epoch": 0.54,
"learning_rate": 4.336712133206269e-05,
"loss": 0.3375,
"step": 452
},
{
"epoch": 0.54,
"learning_rate": 4.333415590044323e-05,
"loss": 0.2818,
"step": 453
},
{
"epoch": 0.54,
"learning_rate": 4.330112134886119e-05,
"loss": 0.3518,
"step": 454
},
{
"epoch": 0.54,
"learning_rate": 4.3268017801857176e-05,
"loss": 0.2463,
"step": 455
},
{
"epoch": 0.54,
"learning_rate": 4.323484538423192e-05,
"loss": 0.2906,
"step": 456
},
{
"epoch": 0.54,
"learning_rate": 4.320160422104579e-05,
"loss": 0.2432,
"step": 457
},
{
"epoch": 0.54,
"learning_rate": 4.316829443761832e-05,
"loss": 0.2806,
"step": 458
},
{
"epoch": 0.54,
"learning_rate": 4.3134916159527735e-05,
"loss": 0.1853,
"step": 459
},
{
"epoch": 0.55,
"learning_rate": 4.3101469512610525e-05,
"loss": 0.2855,
"step": 460
},
{
"epoch": 0.55,
"learning_rate": 4.306795462296088e-05,
"loss": 0.3396,
"step": 461
},
{
"epoch": 0.55,
"learning_rate": 4.303437161693031e-05,
"loss": 0.3534,
"step": 462
},
{
"epoch": 0.55,
"learning_rate": 4.3000720621127096e-05,
"loss": 0.3458,
"step": 463
},
{
"epoch": 0.55,
"learning_rate": 4.296700176241584e-05,
"loss": 0.2457,
"step": 464
},
{
"epoch": 0.55,
"learning_rate": 4.293321516791701e-05,
"loss": 0.2472,
"step": 465
},
{
"epoch": 0.55,
"learning_rate": 4.2899360965006424e-05,
"loss": 0.4089,
"step": 466
},
{
"epoch": 0.55,
"learning_rate": 4.2865439281314785e-05,
"loss": 0.3292,
"step": 467
},
{
"epoch": 0.55,
"learning_rate": 4.28314502447272e-05,
"loss": 0.2968,
"step": 468
},
{
"epoch": 0.56,
"learning_rate": 4.2797393983382706e-05,
"loss": 0.3879,
"step": 469
},
{
"epoch": 0.56,
"learning_rate": 4.276327062567376e-05,
"loss": 0.2874,
"step": 470
},
{
"epoch": 0.56,
"learning_rate": 4.272908030024578e-05,
"loss": 0.3083,
"step": 471
},
{
"epoch": 0.56,
"learning_rate": 4.269482313599666e-05,
"loss": 0.224,
"step": 472
},
{
"epoch": 0.56,
"learning_rate": 4.266049926207629e-05,
"loss": 0.2349,
"step": 473
},
{
"epoch": 0.56,
"learning_rate": 4.262610880788602e-05,
"loss": 0.2517,
"step": 474
},
{
"epoch": 0.56,
"learning_rate": 4.259165190307823e-05,
"loss": 0.3074,
"step": 475
},
{
"epoch": 0.56,
"learning_rate": 4.255712867755583e-05,
"loss": 0.2581,
"step": 476
},
{
"epoch": 0.57,
"learning_rate": 4.252253926147174e-05,
"loss": 0.2062,
"step": 477
},
{
"epoch": 0.57,
"learning_rate": 4.248788378522841e-05,
"loss": 0.205,
"step": 478
},
{
"epoch": 0.57,
"learning_rate": 4.245316237947738e-05,
"loss": 0.2171,
"step": 479
},
{
"epoch": 0.57,
"learning_rate": 4.2418375175118694e-05,
"loss": 0.3009,
"step": 480
},
{
"epoch": 0.57,
"learning_rate": 4.2383522303300515e-05,
"loss": 0.2514,
"step": 481
},
{
"epoch": 0.57,
"learning_rate": 4.23486038954185e-05,
"loss": 0.1759,
"step": 482
},
{
"epoch": 0.57,
"learning_rate": 4.231362008311545e-05,
"loss": 0.1742,
"step": 483
},
{
"epoch": 0.57,
"learning_rate": 4.227857099828069e-05,
"loss": 0.3008,
"step": 484
},
{
"epoch": 0.57,
"learning_rate": 4.224345677304965e-05,
"loss": 0.3944,
"step": 485
},
{
"epoch": 0.58,
"learning_rate": 4.2208277539803334e-05,
"loss": 0.2892,
"step": 486
},
{
"epoch": 0.58,
"learning_rate": 4.217303343116782e-05,
"loss": 0.3013,
"step": 487
},
{
"epoch": 0.58,
"learning_rate": 4.213772458001378e-05,
"loss": 0.3311,
"step": 488
},
{
"epoch": 0.58,
"learning_rate": 4.210235111945594e-05,
"loss": 0.4286,
"step": 489
},
{
"epoch": 0.58,
"learning_rate": 4.206691318285265e-05,
"loss": 0.22,
"step": 490
},
{
"epoch": 0.58,
"learning_rate": 4.203141090380528e-05,
"loss": 0.2426,
"step": 491
},
{
"epoch": 0.58,
"learning_rate": 4.199584441615782e-05,
"loss": 0.3117,
"step": 492
},
{
"epoch": 0.58,
"learning_rate": 4.19602138539963e-05,
"loss": 0.4433,
"step": 493
},
{
"epoch": 0.59,
"learning_rate": 4.19245193516483e-05,
"loss": 0.4025,
"step": 494
},
{
"epoch": 0.59,
"learning_rate": 4.188876104368251e-05,
"loss": 0.2673,
"step": 495
},
{
"epoch": 0.59,
"learning_rate": 4.18529390649081e-05,
"loss": 0.3724,
"step": 496
},
{
"epoch": 0.59,
"learning_rate": 4.181705355037433e-05,
"loss": 0.2437,
"step": 497
},
{
"epoch": 0.59,
"learning_rate": 4.178110463536995e-05,
"loss": 0.2298,
"step": 498
},
{
"epoch": 0.59,
"learning_rate": 4.174509245542277e-05,
"loss": 0.3817,
"step": 499
},
{
"epoch": 0.59,
"learning_rate": 4.1709017146299087e-05,
"loss": 0.2266,
"step": 500
},
{
"epoch": 0.59,
"learning_rate": 4.167287884400319e-05,
"loss": 0.2456,
"step": 501
},
{
"epoch": 0.59,
"learning_rate": 4.163667768477688e-05,
"loss": 0.3525,
"step": 502
},
{
"epoch": 0.6,
"learning_rate": 4.160041380509889e-05,
"loss": 0.2361,
"step": 503
},
{
"epoch": 0.6,
"learning_rate": 4.156408734168445e-05,
"loss": 0.2911,
"step": 504
},
{
"epoch": 0.6,
"learning_rate": 4.152769843148471e-05,
"loss": 0.2309,
"step": 505
},
{
"epoch": 0.6,
"learning_rate": 4.149124721168625e-05,
"loss": 0.2448,
"step": 506
},
{
"epoch": 0.6,
"learning_rate": 4.145473381971054e-05,
"loss": 0.2787,
"step": 507
},
{
"epoch": 0.6,
"learning_rate": 4.141815839321347e-05,
"loss": 0.3903,
"step": 508
},
{
"epoch": 0.6,
"learning_rate": 4.138152107008478e-05,
"loss": 0.2205,
"step": 509
},
{
"epoch": 0.6,
"learning_rate": 4.134482198844758e-05,
"loss": 0.3232,
"step": 510
},
{
"epoch": 0.61,
"learning_rate": 4.130806128665779e-05,
"loss": 0.2219,
"step": 511
},
{
"epoch": 0.61,
"learning_rate": 4.1271239103303636e-05,
"loss": 0.2765,
"step": 512
},
{
"epoch": 0.61,
"learning_rate": 4.1234355577205164e-05,
"loss": 0.2903,
"step": 513
},
{
"epoch": 0.61,
"learning_rate": 4.119741084741363e-05,
"loss": 0.2991,
"step": 514
},
{
"epoch": 0.61,
"learning_rate": 4.1160405053211084e-05,
"loss": 0.2697,
"step": 515
},
{
"epoch": 0.61,
"learning_rate": 4.112333833410975e-05,
"loss": 0.1415,
"step": 516
},
{
"epoch": 0.61,
"learning_rate": 4.108621082985155e-05,
"loss": 0.2174,
"step": 517
},
{
"epoch": 0.61,
"learning_rate": 4.104902268040758e-05,
"loss": 0.394,
"step": 518
},
{
"epoch": 0.62,
"learning_rate": 4.101177402597755e-05,
"loss": 0.2551,
"step": 519
},
{
"epoch": 0.62,
"learning_rate": 4.097446500698929e-05,
"loss": 0.2233,
"step": 520
},
{
"epoch": 0.62,
"learning_rate": 4.09370957640982e-05,
"loss": 0.2172,
"step": 521
},
{
"epoch": 0.62,
"learning_rate": 4.089966643818671e-05,
"loss": 0.2568,
"step": 522
},
{
"epoch": 0.62,
"learning_rate": 4.0862177170363784e-05,
"loss": 0.2724,
"step": 523
},
{
"epoch": 0.62,
"learning_rate": 4.0824628101964354e-05,
"loss": 0.2839,
"step": 524
},
{
"epoch": 0.62,
"learning_rate": 4.078701937454883e-05,
"loss": 0.2476,
"step": 525
},
{
"epoch": 0.62,
"learning_rate": 4.074935112990249e-05,
"loss": 0.2791,
"step": 526
},
{
"epoch": 0.62,
"learning_rate": 4.071162351003502e-05,
"loss": 0.2558,
"step": 527
},
{
"epoch": 0.63,
"learning_rate": 4.0673836657179953e-05,
"loss": 0.2586,
"step": 528
},
{
"epoch": 0.63,
"learning_rate": 4.0635990713794124e-05,
"loss": 0.2541,
"step": 529
},
{
"epoch": 0.63,
"learning_rate": 4.059808582255715e-05,
"loss": 0.2765,
"step": 530
},
{
"epoch": 0.63,
"learning_rate": 4.0560122126370856e-05,
"loss": 0.2609,
"step": 531
},
{
"epoch": 0.63,
"learning_rate": 4.052209976835879e-05,
"loss": 0.236,
"step": 532
},
{
"epoch": 0.63,
"learning_rate": 4.048401889186565e-05,
"loss": 0.1511,
"step": 533
},
{
"epoch": 0.63,
"learning_rate": 4.0445879640456744e-05,
"loss": 0.2454,
"step": 534
},
{
"epoch": 0.63,
"learning_rate": 4.040768215791745e-05,
"loss": 0.2546,
"step": 535
},
{
"epoch": 0.64,
"learning_rate": 4.036942658825267e-05,
"loss": 0.2466,
"step": 536
},
{
"epoch": 0.64,
"learning_rate": 4.0331113075686344e-05,
"loss": 0.2293,
"step": 537
},
{
"epoch": 0.64,
"learning_rate": 4.029274176466079e-05,
"loss": 0.2017,
"step": 538
},
{
"epoch": 0.64,
"learning_rate": 4.025431279983627e-05,
"loss": 0.3737,
"step": 539
},
{
"epoch": 0.64,
"learning_rate": 4.021582632609039e-05,
"loss": 0.1394,
"step": 540
},
{
"epoch": 0.64,
"learning_rate": 4.017728248851756e-05,
"loss": 0.244,
"step": 541
},
{
"epoch": 0.64,
"learning_rate": 4.013868143242847e-05,
"loss": 0.3704,
"step": 542
},
{
"epoch": 0.64,
"learning_rate": 4.01000233033495e-05,
"loss": 0.3224,
"step": 543
},
{
"epoch": 0.64,
"learning_rate": 4.00613082470222e-05,
"loss": 0.252,
"step": 544
},
{
"epoch": 0.65,
"learning_rate": 4.002253640940277e-05,
"loss": 0.2751,
"step": 545
},
{
"epoch": 0.65,
"learning_rate": 3.998370793666142e-05,
"loss": 0.2885,
"step": 546
},
{
"epoch": 0.65,
"learning_rate": 3.994482297518192e-05,
"loss": 0.2324,
"step": 547
},
{
"epoch": 0.65,
"learning_rate": 3.9905881671560994e-05,
"loss": 0.2592,
"step": 548
},
{
"epoch": 0.65,
"learning_rate": 3.986688417260776e-05,
"loss": 0.4748,
"step": 549
},
{
"epoch": 0.65,
"learning_rate": 3.982783062534321e-05,
"loss": 0.4343,
"step": 550
},
{
"epoch": 0.65,
"learning_rate": 3.978872117699962e-05,
"loss": 0.2425,
"step": 551
},
{
"epoch": 0.65,
"learning_rate": 3.974955597502004e-05,
"loss": 0.3459,
"step": 552
},
{
"epoch": 0.66,
"learning_rate": 3.971033516705769e-05,
"loss": 0.324,
"step": 553
},
{
"epoch": 0.66,
"learning_rate": 3.9671058900975446e-05,
"loss": 0.1953,
"step": 554
},
{
"epoch": 0.66,
"learning_rate": 3.963172732484522e-05,
"loss": 0.2776,
"step": 555
},
{
"epoch": 0.66,
"learning_rate": 3.95923405869475e-05,
"loss": 0.2916,
"step": 556
},
{
"epoch": 0.66,
"learning_rate": 3.95528988357707e-05,
"loss": 0.2366,
"step": 557
},
{
"epoch": 0.66,
"learning_rate": 3.9513402220010634e-05,
"loss": 0.2539,
"step": 558
},
{
"epoch": 0.66,
"learning_rate": 3.947385088856996e-05,
"loss": 0.3312,
"step": 559
},
{
"epoch": 0.66,
"learning_rate": 3.943424499055763e-05,
"loss": 0.2937,
"step": 560
},
{
"epoch": 0.66,
"learning_rate": 3.9394584675288296e-05,
"loss": 0.2306,
"step": 561
},
{
"epoch": 0.67,
"learning_rate": 3.935487009228176e-05,
"loss": 0.2333,
"step": 562
},
{
"epoch": 0.67,
"learning_rate": 3.931510139126243e-05,
"loss": 0.2186,
"step": 563
},
{
"epoch": 0.67,
"learning_rate": 3.9275278722158735e-05,
"loss": 0.2813,
"step": 564
},
{
"epoch": 0.67,
"learning_rate": 3.9235402235102545e-05,
"loss": 0.2282,
"step": 565
},
{
"epoch": 0.67,
"learning_rate": 3.919547208042866e-05,
"loss": 0.3022,
"step": 566
},
{
"epoch": 0.67,
"learning_rate": 3.915548840867418e-05,
"loss": 0.2804,
"step": 567
},
{
"epoch": 0.67,
"learning_rate": 3.911545137057796e-05,
"loss": 0.306,
"step": 568
},
{
"epoch": 0.67,
"learning_rate": 3.907536111708008e-05,
"loss": 0.2364,
"step": 569
},
{
"epoch": 0.68,
"learning_rate": 3.903521779932121e-05,
"loss": 0.2579,
"step": 570
},
{
"epoch": 0.68,
"learning_rate": 3.899502156864209e-05,
"loss": 0.3072,
"step": 571
},
{
"epoch": 0.68,
"learning_rate": 3.895477257658292e-05,
"loss": 0.2572,
"step": 572
},
{
"epoch": 0.68,
"learning_rate": 3.8914470974882846e-05,
"loss": 0.2716,
"step": 573
},
{
"epoch": 0.68,
"learning_rate": 3.887411691547933e-05,
"loss": 0.2007,
"step": 574
},
{
"epoch": 0.68,
"learning_rate": 3.8833710550507605e-05,
"loss": 0.2523,
"step": 575
},
{
"epoch": 0.68,
"learning_rate": 3.87932520323001e-05,
"loss": 0.1348,
"step": 576
},
{
"epoch": 0.68,
"learning_rate": 3.875274151338584e-05,
"loss": 0.4596,
"step": 577
},
{
"epoch": 0.69,
"learning_rate": 3.871217914648994e-05,
"loss": 0.3232,
"step": 578
},
{
"epoch": 0.69,
"learning_rate": 3.867156508453293e-05,
"loss": 0.332,
"step": 579
},
{
"epoch": 0.69,
"learning_rate": 3.863089948063027e-05,
"loss": 0.3265,
"step": 580
},
{
"epoch": 0.69,
"learning_rate": 3.859018248809172e-05,
"loss": 0.2594,
"step": 581
},
{
"epoch": 0.69,
"learning_rate": 3.854941426042076e-05,
"loss": 0.233,
"step": 582
},
{
"epoch": 0.69,
"learning_rate": 3.850859495131405e-05,
"loss": 0.2867,
"step": 583
},
{
"epoch": 0.69,
"learning_rate": 3.846772471466081e-05,
"loss": 0.2477,
"step": 584
},
{
"epoch": 0.69,
"learning_rate": 3.84268037045423e-05,
"loss": 0.2583,
"step": 585
},
{
"epoch": 0.69,
"learning_rate": 3.8385832075231124e-05,
"loss": 0.2449,
"step": 586
},
{
"epoch": 0.7,
"learning_rate": 3.834480998119078e-05,
"loss": 0.2729,
"step": 587
},
{
"epoch": 0.7,
"learning_rate": 3.830373757707498e-05,
"loss": 0.3224,
"step": 588
},
{
"epoch": 0.7,
"learning_rate": 3.826261501772715e-05,
"loss": 0.2189,
"step": 589
},
{
"epoch": 0.7,
"learning_rate": 3.822144245817976e-05,
"loss": 0.3783,
"step": 590
},
{
"epoch": 0.7,
"learning_rate": 3.818022005365379e-05,
"loss": 0.2048,
"step": 591
},
{
"epoch": 0.7,
"learning_rate": 3.813894795955817e-05,
"loss": 0.2587,
"step": 592
},
{
"epoch": 0.7,
"learning_rate": 3.8097626331489106e-05,
"loss": 0.3626,
"step": 593
},
{
"epoch": 0.7,
"learning_rate": 3.805625532522959e-05,
"loss": 0.1753,
"step": 594
},
{
"epoch": 0.71,
"learning_rate": 3.801483509674875e-05,
"loss": 0.268,
"step": 595
},
{
"epoch": 0.71,
"learning_rate": 3.797336580220129e-05,
"loss": 0.2268,
"step": 596
},
{
"epoch": 0.71,
"learning_rate": 3.793184759792688e-05,
"loss": 0.2217,
"step": 597
},
{
"epoch": 0.71,
"learning_rate": 3.7890280640449605e-05,
"loss": 0.3057,
"step": 598
},
{
"epoch": 0.71,
"learning_rate": 3.7848665086477334e-05,
"loss": 0.1427,
"step": 599
},
{
"epoch": 0.71,
"learning_rate": 3.780700109290115e-05,
"loss": 0.3914,
"step": 600
},
{
"epoch": 0.71,
"learning_rate": 3.776528881679474e-05,
"loss": 0.2081,
"step": 601
},
{
"epoch": 0.71,
"learning_rate": 3.772352841541384e-05,
"loss": 0.1958,
"step": 602
},
{
"epoch": 0.71,
"learning_rate": 3.76817200461956e-05,
"loss": 0.2173,
"step": 603
},
{
"epoch": 0.72,
"learning_rate": 3.763986386675802e-05,
"loss": 0.3855,
"step": 604
},
{
"epoch": 0.72,
"learning_rate": 3.7597960034899335e-05,
"loss": 0.3793,
"step": 605
},
{
"epoch": 0.72,
"learning_rate": 3.7556008708597446e-05,
"loss": 0.3456,
"step": 606
},
{
"epoch": 0.72,
"learning_rate": 3.751401004600929e-05,
"loss": 0.2731,
"step": 607
},
{
"epoch": 0.72,
"learning_rate": 3.747196420547029e-05,
"loss": 0.2725,
"step": 608
},
{
"epoch": 0.72,
"learning_rate": 3.742987134549369e-05,
"loss": 0.3186,
"step": 609
},
{
"epoch": 0.72,
"learning_rate": 3.738773162477001e-05,
"loss": 0.2341,
"step": 610
},
{
"epoch": 0.72,
"learning_rate": 3.7345545202166476e-05,
"loss": 0.4402,
"step": 611
},
{
"epoch": 0.73,
"learning_rate": 3.730331223672633e-05,
"loss": 0.2449,
"step": 612
},
{
"epoch": 0.73,
"learning_rate": 3.726103288766832e-05,
"loss": 0.2957,
"step": 613
},
{
"epoch": 0.73,
"learning_rate": 3.721870731438601e-05,
"loss": 0.2161,
"step": 614
},
{
"epoch": 0.73,
"learning_rate": 3.717633567644729e-05,
"loss": 0.2128,
"step": 615
},
{
"epoch": 0.73,
"learning_rate": 3.713391813359366e-05,
"loss": 0.2113,
"step": 616
},
{
"epoch": 0.73,
"learning_rate": 3.7091454845739734e-05,
"loss": 0.2892,
"step": 617
},
{
"epoch": 0.73,
"learning_rate": 3.704894597297254e-05,
"loss": 0.2417,
"step": 618
},
{
"epoch": 0.73,
"learning_rate": 3.700639167555098e-05,
"loss": 0.3562,
"step": 619
},
{
"epoch": 0.73,
"learning_rate": 3.696379211390522e-05,
"loss": 0.1681,
"step": 620
},
{
"epoch": 0.74,
"learning_rate": 3.6921147448636045e-05,
"loss": 0.3111,
"step": 621
},
{
"epoch": 0.74,
"learning_rate": 3.6878457840514316e-05,
"loss": 0.3029,
"step": 622
},
{
"epoch": 0.74,
"learning_rate": 3.6835723450480283e-05,
"loss": 0.1842,
"step": 623
},
{
"epoch": 0.74,
"learning_rate": 3.679294443964307e-05,
"loss": 0.2543,
"step": 624
},
{
"epoch": 0.74,
"learning_rate": 3.675012096928e-05,
"loss": 0.3299,
"step": 625
},
{
"epoch": 0.74,
"learning_rate": 3.670725320083601e-05,
"loss": 0.2311,
"step": 626
},
{
"epoch": 0.74,
"learning_rate": 3.6664341295923035e-05,
"loss": 0.2829,
"step": 627
},
{
"epoch": 0.74,
"learning_rate": 3.6621385416319425e-05,
"loss": 0.2554,
"step": 628
},
{
"epoch": 0.75,
"learning_rate": 3.657838572396929e-05,
"loss": 0.3379,
"step": 629
},
{
"epoch": 0.75,
"learning_rate": 3.653534238098194e-05,
"loss": 0.1747,
"step": 630
},
{
"epoch": 0.75,
"learning_rate": 3.649225554963123e-05,
"loss": 0.3012,
"step": 631
},
{
"epoch": 0.75,
"learning_rate": 3.644912539235496e-05,
"loss": 0.2631,
"step": 632
},
{
"epoch": 0.75,
"learning_rate": 3.64059520717543e-05,
"loss": 0.3087,
"step": 633
},
{
"epoch": 0.75,
"learning_rate": 3.636273575059312e-05,
"loss": 0.2936,
"step": 634
},
{
"epoch": 0.75,
"learning_rate": 3.631947659179741e-05,
"loss": 0.3079,
"step": 635
},
{
"epoch": 0.75,
"learning_rate": 3.627617475845466e-05,
"loss": 0.1422,
"step": 636
},
{
"epoch": 0.75,
"learning_rate": 3.6232830413813235e-05,
"loss": 0.2727,
"step": 637
},
{
"epoch": 0.76,
"learning_rate": 3.6189443721281786e-05,
"loss": 0.2239,
"step": 638
},
{
"epoch": 0.76,
"learning_rate": 3.614601484442859e-05,
"loss": 0.2528,
"step": 639
},
{
"epoch": 0.76,
"learning_rate": 3.6102543946980985e-05,
"loss": 0.2446,
"step": 640
},
{
"epoch": 0.76,
"learning_rate": 3.605903119282472e-05,
"loss": 0.2392,
"step": 641
},
{
"epoch": 0.76,
"learning_rate": 3.601547674600333e-05,
"loss": 0.2591,
"step": 642
},
{
"epoch": 0.76,
"learning_rate": 3.5971880770717554e-05,
"loss": 0.28,
"step": 643
},
{
"epoch": 0.76,
"learning_rate": 3.592824343132467e-05,
"loss": 0.4283,
"step": 644
},
{
"epoch": 0.76,
"learning_rate": 3.588456489233792e-05,
"loss": 0.2747,
"step": 645
},
{
"epoch": 0.77,
"learning_rate": 3.5840845318425855e-05,
"loss": 0.2312,
"step": 646
},
{
"epoch": 0.77,
"learning_rate": 3.5797084874411735e-05,
"loss": 0.2521,
"step": 647
},
{
"epoch": 0.77,
"learning_rate": 3.57532837252729e-05,
"loss": 0.262,
"step": 648
},
{
"epoch": 0.77,
"learning_rate": 3.570944203614014e-05,
"loss": 0.1989,
"step": 649
},
{
"epoch": 0.77,
"learning_rate": 3.56655599722971e-05,
"loss": 0.2692,
"step": 650
},
{
"epoch": 0.77,
"learning_rate": 3.562163769917963e-05,
"loss": 0.2294,
"step": 651
},
{
"epoch": 0.77,
"learning_rate": 3.5577675382375157e-05,
"loss": 0.2673,
"step": 652
},
{
"epoch": 0.77,
"learning_rate": 3.5533673187622075e-05,
"loss": 0.3452,
"step": 653
},
{
"epoch": 0.78,
"learning_rate": 3.548963128080915e-05,
"loss": 0.2076,
"step": 654
},
{
"epoch": 0.78,
"learning_rate": 3.544554982797481e-05,
"loss": 0.2218,
"step": 655
},
{
"epoch": 0.78,
"learning_rate": 3.540142899530662e-05,
"loss": 0.254,
"step": 656
},
{
"epoch": 0.78,
"learning_rate": 3.535726894914058e-05,
"loss": 0.1941,
"step": 657
},
{
"epoch": 0.78,
"learning_rate": 3.531306985596055e-05,
"loss": 0.2272,
"step": 658
},
{
"epoch": 0.78,
"learning_rate": 3.526883188239755e-05,
"loss": 0.3485,
"step": 659
},
{
"epoch": 0.78,
"learning_rate": 3.5224555195229234e-05,
"loss": 0.1742,
"step": 660
},
{
"epoch": 0.78,
"learning_rate": 3.518023996137918e-05,
"loss": 0.2912,
"step": 661
},
{
"epoch": 0.78,
"learning_rate": 3.513588634791628e-05,
"loss": 0.1661,
"step": 662
},
{
"epoch": 0.79,
"learning_rate": 3.509149452205414e-05,
"loss": 0.2866,
"step": 663
},
{
"epoch": 0.79,
"learning_rate": 3.504706465115042e-05,
"loss": 0.3944,
"step": 664
},
{
"epoch": 0.79,
"learning_rate": 3.500259690270618e-05,
"loss": 0.2728,
"step": 665
},
{
"epoch": 0.79,
"learning_rate": 3.495809144436533e-05,
"loss": 0.2458,
"step": 666
},
{
"epoch": 0.79,
"learning_rate": 3.491354844391391e-05,
"loss": 0.152,
"step": 667
},
{
"epoch": 0.79,
"learning_rate": 3.486896806927951e-05,
"loss": 0.2026,
"step": 668
},
{
"epoch": 0.79,
"learning_rate": 3.48243504885306e-05,
"loss": 0.2478,
"step": 669
},
{
"epoch": 0.79,
"learning_rate": 3.477969586987596e-05,
"loss": 0.2907,
"step": 670
},
{
"epoch": 0.8,
"learning_rate": 3.4735004381663955e-05,
"loss": 0.2569,
"step": 671
},
{
"epoch": 0.8,
"learning_rate": 3.4690276192381975e-05,
"loss": 0.3092,
"step": 672
},
{
"epoch": 0.8,
"learning_rate": 3.464551147065578e-05,
"loss": 0.1909,
"step": 673
},
{
"epoch": 0.8,
"learning_rate": 3.460071038524883e-05,
"loss": 0.2399,
"step": 674
},
{
"epoch": 0.8,
"learning_rate": 3.455587310506171e-05,
"loss": 0.2615,
"step": 675
},
{
"epoch": 0.8,
"learning_rate": 3.451099979913143e-05,
"loss": 0.3121,
"step": 676
},
{
"epoch": 0.8,
"learning_rate": 3.446609063663084e-05,
"loss": 0.2779,
"step": 677
},
{
"epoch": 0.8,
"learning_rate": 3.442114578686795e-05,
"loss": 0.2808,
"step": 678
},
{
"epoch": 0.8,
"learning_rate": 3.4376165419285336e-05,
"loss": 0.271,
"step": 679
},
{
"epoch": 0.81,
"learning_rate": 3.433114970345944e-05,
"loss": 0.2158,
"step": 680
},
{
"epoch": 0.81,
"learning_rate": 3.4286098809100005e-05,
"loss": 0.2295,
"step": 681
},
{
"epoch": 0.81,
"learning_rate": 3.424101290604938e-05,
"loss": 0.3262,
"step": 682
},
{
"epoch": 0.81,
"learning_rate": 3.41958921642819e-05,
"loss": 0.2281,
"step": 683
},
{
"epoch": 0.81,
"learning_rate": 3.415073675390322e-05,
"loss": 0.3043,
"step": 684
},
{
"epoch": 0.81,
"learning_rate": 3.410554684514975e-05,
"loss": 0.2987,
"step": 685
},
{
"epoch": 0.81,
"learning_rate": 3.4060322608387896e-05,
"loss": 0.2203,
"step": 686
},
{
"epoch": 0.81,
"learning_rate": 3.401506421411354e-05,
"loss": 0.252,
"step": 687
},
{
"epoch": 0.82,
"learning_rate": 3.3969771832951284e-05,
"loss": 0.2814,
"step": 688
},
{
"epoch": 0.82,
"learning_rate": 3.39244456356539e-05,
"loss": 0.2556,
"step": 689
},
{
"epoch": 0.82,
"learning_rate": 3.387908579310164e-05,
"loss": 0.2388,
"step": 690
},
{
"epoch": 0.82,
"learning_rate": 3.3833692476301574e-05,
"loss": 0.3186,
"step": 691
},
{
"epoch": 0.82,
"learning_rate": 3.3788265856387e-05,
"loss": 0.2689,
"step": 692
},
{
"epoch": 0.82,
"learning_rate": 3.374280610461675e-05,
"loss": 0.3176,
"step": 693
},
{
"epoch": 0.82,
"learning_rate": 3.3697313392374585e-05,
"loss": 0.2756,
"step": 694
},
{
"epoch": 0.82,
"learning_rate": 3.365178789116849e-05,
"loss": 0.2494,
"step": 695
},
{
"epoch": 0.82,
"learning_rate": 3.3606229772630125e-05,
"loss": 0.2898,
"step": 696
},
{
"epoch": 0.83,
"learning_rate": 3.356063920851405e-05,
"loss": 0.2514,
"step": 697
},
{
"epoch": 0.83,
"learning_rate": 3.351501637069719e-05,
"loss": 0.3513,
"step": 698
},
{
"epoch": 0.83,
"learning_rate": 3.346936143117811e-05,
"loss": 0.2898,
"step": 699
},
{
"epoch": 0.83,
"learning_rate": 3.3423674562076446e-05,
"loss": 0.1813,
"step": 700
},
{
"epoch": 0.83,
"learning_rate": 3.337795593563217e-05,
"loss": 0.1925,
"step": 701
},
{
"epoch": 0.83,
"learning_rate": 3.333220572420497e-05,
"loss": 0.268,
"step": 702
},
{
"epoch": 0.83,
"learning_rate": 3.328642410027366e-05,
"loss": 0.2425,
"step": 703
},
{
"epoch": 0.83,
"learning_rate": 3.3240611236435415e-05,
"loss": 0.273,
"step": 704
},
{
"epoch": 0.84,
"learning_rate": 3.319476730540525e-05,
"loss": 0.2221,
"step": 705
},
{
"epoch": 0.84,
"learning_rate": 3.314889248001525e-05,
"loss": 0.1541,
"step": 706
},
{
"epoch": 0.84,
"learning_rate": 3.3102986933214e-05,
"loss": 0.2146,
"step": 707
},
{
"epoch": 0.84,
"learning_rate": 3.305705083806592e-05,
"loss": 0.2487,
"step": 708
},
{
"epoch": 0.84,
"learning_rate": 3.3011084367750544e-05,
"loss": 0.2341,
"step": 709
},
{
"epoch": 0.84,
"learning_rate": 3.296508769556198e-05,
"loss": 0.1824,
"step": 710
},
{
"epoch": 0.84,
"learning_rate": 3.291906099490815e-05,
"loss": 0.2224,
"step": 711
},
{
"epoch": 0.84,
"learning_rate": 3.2873004439310216e-05,
"loss": 0.252,
"step": 712
},
{
"epoch": 0.85,
"learning_rate": 3.282691820240188e-05,
"loss": 0.3569,
"step": 713
},
{
"epoch": 0.85,
"learning_rate": 3.278080245792875e-05,
"loss": 0.2553,
"step": 714
},
{
"epoch": 0.85,
"learning_rate": 3.273465737974767e-05,
"loss": 0.397,
"step": 715
},
{
"epoch": 0.85,
"learning_rate": 3.268848314182606e-05,
"loss": 0.2171,
"step": 716
},
{
"epoch": 0.85,
"learning_rate": 3.264227991824131e-05,
"loss": 0.3236,
"step": 717
},
{
"epoch": 0.85,
"learning_rate": 3.259604788318005e-05,
"loss": 0.2252,
"step": 718
},
{
"epoch": 0.85,
"learning_rate": 3.254978721093755e-05,
"loss": 0.2994,
"step": 719
},
{
"epoch": 0.85,
"learning_rate": 3.250349807591704e-05,
"loss": 0.2406,
"step": 720
},
{
"epoch": 0.85,
"learning_rate": 3.245718065262904e-05,
"loss": 0.2831,
"step": 721
},
{
"epoch": 0.86,
"learning_rate": 3.2410835115690735e-05,
"loss": 0.175,
"step": 722
},
{
"epoch": 0.86,
"learning_rate": 3.236446163982528e-05,
"loss": 0.2545,
"step": 723
},
{
"epoch": 0.86,
"learning_rate": 3.23180603998612e-05,
"loss": 0.2398,
"step": 724
},
{
"epoch": 0.86,
"learning_rate": 3.227163157073163e-05,
"loss": 0.2577,
"step": 725
},
{
"epoch": 0.86,
"learning_rate": 3.222517532747377e-05,
"loss": 0.2555,
"step": 726
},
{
"epoch": 0.86,
"learning_rate": 3.2178691845228136e-05,
"loss": 0.2365,
"step": 727
},
{
"epoch": 0.86,
"learning_rate": 3.2132181299237975e-05,
"loss": 0.3234,
"step": 728
},
{
"epoch": 0.86,
"learning_rate": 3.2085643864848504e-05,
"loss": 0.223,
"step": 729
},
{
"epoch": 0.87,
"learning_rate": 3.203907971750637e-05,
"loss": 0.321,
"step": 730
},
{
"epoch": 0.87,
"learning_rate": 3.1992489032758897e-05,
"loss": 0.2785,
"step": 731
},
{
"epoch": 0.87,
"learning_rate": 3.194587198625347e-05,
"loss": 0.2555,
"step": 732
},
{
"epoch": 0.87,
"learning_rate": 3.189922875373684e-05,
"loss": 0.2354,
"step": 733
},
{
"epoch": 0.87,
"learning_rate": 3.1852559511054484e-05,
"loss": 0.2835,
"step": 734
},
{
"epoch": 0.87,
"learning_rate": 3.180586443414996e-05,
"loss": 0.2872,
"step": 735
},
{
"epoch": 0.87,
"learning_rate": 3.175914369906418e-05,
"loss": 0.2141,
"step": 736
},
{
"epoch": 0.87,
"learning_rate": 3.171239748193483e-05,
"loss": 0.228,
"step": 737
},
{
"epoch": 0.87,
"learning_rate": 3.166562595899565e-05,
"loss": 0.143,
"step": 738
},
{
"epoch": 0.88,
"learning_rate": 3.161882930657576e-05,
"loss": 0.2461,
"step": 739
},
{
"epoch": 0.88,
"learning_rate": 3.157200770109905e-05,
"loss": 0.2437,
"step": 740
},
{
"epoch": 0.88,
"learning_rate": 3.152516131908347e-05,
"loss": 0.2225,
"step": 741
},
{
"epoch": 0.88,
"learning_rate": 3.147829033714038e-05,
"loss": 0.3087,
"step": 742
},
{
"epoch": 0.88,
"learning_rate": 3.143139493197387e-05,
"loss": 0.1815,
"step": 743
},
{
"epoch": 0.88,
"learning_rate": 3.138447528038011e-05,
"loss": 0.3681,
"step": 744
},
{
"epoch": 0.88,
"learning_rate": 3.133753155924671e-05,
"loss": 0.1193,
"step": 745
},
{
"epoch": 0.88,
"learning_rate": 3.129056394555197e-05,
"loss": 0.2512,
"step": 746
},
{
"epoch": 0.89,
"learning_rate": 3.1243572616364324e-05,
"loss": 0.4096,
"step": 747
},
{
"epoch": 0.89,
"learning_rate": 3.1196557748841555e-05,
"loss": 0.1937,
"step": 748
},
{
"epoch": 0.89,
"learning_rate": 3.1149519520230224e-05,
"loss": 0.2525,
"step": 749
},
{
"epoch": 0.89,
"learning_rate": 3.1102458107864944e-05,
"loss": 0.2583,
"step": 750
},
{
"epoch": 0.89,
"learning_rate": 3.105537368916775e-05,
"loss": 0.2784,
"step": 751
},
{
"epoch": 0.89,
"learning_rate": 3.10082664416474e-05,
"loss": 0.2542,
"step": 752
},
{
"epoch": 0.89,
"learning_rate": 3.096113654289873e-05,
"loss": 0.3522,
"step": 753
},
{
"epoch": 0.89,
"learning_rate": 3.091398417060193e-05,
"loss": 0.3038,
"step": 754
},
{
"epoch": 0.89,
"learning_rate": 3.086680950252196e-05,
"loss": 0.2119,
"step": 755
},
{
"epoch": 0.9,
"learning_rate": 3.0819612716507825e-05,
"loss": 0.2564,
"step": 756
},
{
"epoch": 0.9,
"learning_rate": 3.077239399049189e-05,
"loss": 0.121,
"step": 757
},
{
"epoch": 0.9,
"learning_rate": 3.0725153502489285e-05,
"loss": 0.3507,
"step": 758
},
{
"epoch": 0.9,
"learning_rate": 3.067789143059713e-05,
"loss": 0.1827,
"step": 759
},
{
"epoch": 0.9,
"learning_rate": 3.063060795299394e-05,
"loss": 0.2606,
"step": 760
},
{
"epoch": 0.9,
"learning_rate": 3.058330324793894e-05,
"loss": 0.2924,
"step": 761
},
{
"epoch": 0.9,
"learning_rate": 3.053597749377135e-05,
"loss": 0.2594,
"step": 762
},
{
"epoch": 0.9,
"learning_rate": 3.0488630868909786e-05,
"loss": 0.2064,
"step": 763
},
{
"epoch": 0.91,
"learning_rate": 3.044126355185151e-05,
"loss": 0.3151,
"step": 764
},
{
"epoch": 0.91,
"learning_rate": 3.0393875721171832e-05,
"loss": 0.3077,
"step": 765
},
{
"epoch": 0.91,
"learning_rate": 3.034646755552336e-05,
"loss": 0.2053,
"step": 766
},
{
"epoch": 0.91,
"learning_rate": 3.029903923363539e-05,
"loss": 0.1773,
"step": 767
},
{
"epoch": 0.91,
"learning_rate": 3.0251590934313197e-05,
"loss": 0.1823,
"step": 768
},
{
"epoch": 0.91,
"learning_rate": 3.0204122836437366e-05,
"loss": 0.2068,
"step": 769
},
{
"epoch": 0.91,
"learning_rate": 3.0156635118963146e-05,
"loss": 0.185,
"step": 770
},
{
"epoch": 0.91,
"learning_rate": 3.0109127960919725e-05,
"loss": 0.2399,
"step": 771
},
{
"epoch": 0.91,
"learning_rate": 3.0061601541409595e-05,
"loss": 0.2785,
"step": 772
},
{
"epoch": 0.92,
"learning_rate": 3.0014056039607875e-05,
"loss": 0.3422,
"step": 773
},
{
"epoch": 0.92,
"learning_rate": 2.996649163476159e-05,
"loss": 0.2575,
"step": 774
},
{
"epoch": 0.92,
"learning_rate": 2.991890850618907e-05,
"loss": 0.2477,
"step": 775
},
{
"epoch": 0.92,
"learning_rate": 2.9871306833279205e-05,
"loss": 0.2519,
"step": 776
},
{
"epoch": 0.92,
"learning_rate": 2.982368679549081e-05,
"loss": 0.2906,
"step": 777
},
{
"epoch": 0.92,
"learning_rate": 2.977604857235194e-05,
"loss": 0.2857,
"step": 778
},
{
"epoch": 0.92,
"learning_rate": 2.9728392343459205e-05,
"loss": 0.2739,
"step": 779
},
{
"epoch": 0.92,
"learning_rate": 2.9680718288477078e-05,
"loss": 0.18,
"step": 780
},
{
"epoch": 0.93,
"learning_rate": 2.963302658713726e-05,
"loss": 0.361,
"step": 781
},
{
"epoch": 0.93,
"learning_rate": 2.9585317419237977e-05,
"loss": 0.273,
"step": 782
},
{
"epoch": 0.93,
"learning_rate": 2.953759096464329e-05,
"loss": 0.2964,
"step": 783
},
{
"epoch": 0.93,
"learning_rate": 2.9489847403282454e-05,
"loss": 0.1882,
"step": 784
},
{
"epoch": 0.93,
"learning_rate": 2.9442086915149198e-05,
"loss": 0.2735,
"step": 785
},
{
"epoch": 0.93,
"learning_rate": 2.9394309680301063e-05,
"loss": 0.1811,
"step": 786
},
{
"epoch": 0.93,
"learning_rate": 2.9346515878858728e-05,
"loss": 0.1866,
"step": 787
},
{
"epoch": 0.93,
"learning_rate": 2.929870569100534e-05,
"loss": 0.3179,
"step": 788
},
{
"epoch": 0.94,
"learning_rate": 2.9250879296985822e-05,
"loss": 0.2438,
"step": 789
},
{
"epoch": 0.94,
"learning_rate": 2.9203036877106178e-05,
"loss": 0.2603,
"step": 790
},
{
"epoch": 0.94,
"learning_rate": 2.915517861173284e-05,
"loss": 0.2509,
"step": 791
},
{
"epoch": 0.94,
"learning_rate": 2.9107304681291987e-05,
"loss": 0.1607,
"step": 792
},
{
"epoch": 0.94,
"learning_rate": 2.9059415266268835e-05,
"loss": 0.2151,
"step": 793
},
{
"epoch": 0.94,
"learning_rate": 2.9011510547206983e-05,
"loss": 0.1825,
"step": 794
},
{
"epoch": 0.94,
"learning_rate": 2.8963590704707744e-05,
"loss": 0.2732,
"step": 795
},
{
"epoch": 0.94,
"learning_rate": 2.8915655919429424e-05,
"loss": 0.2262,
"step": 796
},
{
"epoch": 0.94,
"learning_rate": 2.8867706372086684e-05,
"loss": 0.2756,
"step": 797
},
{
"epoch": 0.95,
"learning_rate": 2.8819742243449815e-05,
"loss": 0.244,
"step": 798
},
{
"epoch": 0.95,
"learning_rate": 2.877176371434409e-05,
"loss": 0.2626,
"step": 799
},
{
"epoch": 0.95,
"learning_rate": 2.872377096564909e-05,
"loss": 0.2115,
"step": 800
},
{
"epoch": 0.95,
"learning_rate": 2.867576417829797e-05,
"loss": 0.2856,
"step": 801
},
{
"epoch": 0.95,
"learning_rate": 2.862774353327684e-05,
"loss": 0.1677,
"step": 802
},
{
"epoch": 0.95,
"learning_rate": 2.8579709211624034e-05,
"loss": 0.3426,
"step": 803
},
{
"epoch": 0.95,
"learning_rate": 2.8531661394429464e-05,
"loss": 0.3588,
"step": 804
},
{
"epoch": 0.95,
"learning_rate": 2.8483600262833903e-05,
"loss": 0.2081,
"step": 805
},
{
"epoch": 0.96,
"learning_rate": 2.8435525998028334e-05,
"loss": 0.1989,
"step": 806
},
{
"epoch": 0.96,
"learning_rate": 2.838743878125324e-05,
"loss": 0.1828,
"step": 807
},
{
"epoch": 0.96,
"learning_rate": 2.8339338793797942e-05,
"loss": 0.1784,
"step": 808
},
{
"epoch": 0.96,
"learning_rate": 2.829122621699991e-05,
"loss": 0.2827,
"step": 809
},
{
"epoch": 0.96,
"learning_rate": 2.8243101232244064e-05,
"loss": 0.2907,
"step": 810
},
{
"epoch": 0.96,
"learning_rate": 2.8194964020962106e-05,
"loss": 0.1445,
"step": 811
},
{
"epoch": 0.96,
"learning_rate": 2.8146814764631835e-05,
"loss": 0.2718,
"step": 812
},
{
"epoch": 0.96,
"learning_rate": 2.8098653644776462e-05,
"loss": 0.2541,
"step": 813
},
{
"epoch": 0.96,
"learning_rate": 2.8050480842963923e-05,
"loss": 0.2368,
"step": 814
},
{
"epoch": 0.97,
"learning_rate": 2.8002296540806176e-05,
"loss": 0.388,
"step": 815
},
{
"epoch": 0.97,
"learning_rate": 2.795410091995858e-05,
"loss": 0.2741,
"step": 816
},
{
"epoch": 0.97,
"learning_rate": 2.7905894162119118e-05,
"loss": 0.2027,
"step": 817
},
{
"epoch": 0.97,
"learning_rate": 2.785767644902778e-05,
"loss": 0.2919,
"step": 818
},
{
"epoch": 0.97,
"learning_rate": 2.780944796246587e-05,
"loss": 0.2176,
"step": 819
},
{
"epoch": 0.97,
"learning_rate": 2.7761208884255274e-05,
"loss": 0.2243,
"step": 820
},
{
"epoch": 0.97,
"learning_rate": 2.7712959396257847e-05,
"loss": 0.2093,
"step": 821
},
{
"epoch": 0.97,
"learning_rate": 2.7664699680374668e-05,
"loss": 0.2598,
"step": 822
},
{
"epoch": 0.98,
"learning_rate": 2.7616429918545372e-05,
"loss": 0.2837,
"step": 823
},
{
"epoch": 0.98,
"learning_rate": 2.7568150292747487e-05,
"loss": 0.3447,
"step": 824
},
{
"epoch": 0.98,
"learning_rate": 2.7519860984995703e-05,
"loss": 0.1362,
"step": 825
},
{
"epoch": 0.98,
"learning_rate": 2.747156217734122e-05,
"loss": 0.2897,
"step": 826
},
{
"epoch": 0.98,
"learning_rate": 2.7423254051871067e-05,
"loss": 0.3078,
"step": 827
},
{
"epoch": 0.98,
"learning_rate": 2.737493679070739e-05,
"loss": 0.3228,
"step": 828
},
{
"epoch": 0.98,
"learning_rate": 2.732661057600678e-05,
"loss": 0.2625,
"step": 829
},
{
"epoch": 0.98,
"learning_rate": 2.7278275589959567e-05,
"loss": 0.3225,
"step": 830
},
{
"epoch": 0.98,
"learning_rate": 2.722993201478916e-05,
"loss": 0.347,
"step": 831
},
{
"epoch": 0.99,
"learning_rate": 2.7181580032751375e-05,
"loss": 0.1953,
"step": 832
},
{
"epoch": 0.99,
"learning_rate": 2.713321982613367e-05,
"loss": 0.2488,
"step": 833
},
{
"epoch": 0.99,
"learning_rate": 2.7084851577254554e-05,
"loss": 0.1825,
"step": 834
},
{
"epoch": 0.99,
"learning_rate": 2.7036475468462847e-05,
"loss": 0.2255,
"step": 835
},
{
"epoch": 0.99,
"learning_rate": 2.6988091682136973e-05,
"loss": 0.2152,
"step": 836
},
{
"epoch": 0.99,
"learning_rate": 2.6939700400684337e-05,
"loss": 0.3146,
"step": 837
},
{
"epoch": 0.99,
"learning_rate": 2.6891301806540568e-05,
"loss": 0.3407,
"step": 838
},
{
"epoch": 0.99,
"learning_rate": 2.6842896082168893e-05,
"loss": 0.2713,
"step": 839
},
{
"epoch": 1.0,
"learning_rate": 2.6794483410059406e-05,
"loss": 0.1729,
"step": 840
},
{
"epoch": 1.0,
"learning_rate": 2.674606397272839e-05,
"loss": 0.2376,
"step": 841
},
{
"epoch": 1.0,
"learning_rate": 2.6697637952717646e-05,
"loss": 0.2077,
"step": 842
},
{
"epoch": 1.0,
"learning_rate": 2.664920553259378e-05,
"loss": 0.2652,
"step": 843
},
{
"epoch": 1.0,
"eval_loss": 0.2752176523208618,
"eval_runtime": 119.1657,
"eval_samples_per_second": 2.518,
"eval_steps_per_second": 0.629,
"step": 843
},
{
"epoch": 1.0,
"learning_rate": 2.6600766894947532e-05,
"loss": 0.2246,
"step": 844
},
{
"epoch": 1.0,
"learning_rate": 2.655232222239307e-05,
"loss": 0.1462,
"step": 845
},
{
"epoch": 1.0,
"learning_rate": 2.650387169756734e-05,
"loss": 0.2393,
"step": 846
},
{
"epoch": 1.0,
"learning_rate": 2.6455415503129326e-05,
"loss": 0.1314,
"step": 847
},
{
"epoch": 1.01,
"learning_rate": 2.64069538217594e-05,
"loss": 0.192,
"step": 848
},
{
"epoch": 1.01,
"learning_rate": 2.635848683615862e-05,
"loss": 0.0874,
"step": 849
},
{
"epoch": 1.01,
"learning_rate": 2.6310014729048023e-05,
"loss": 0.0998,
"step": 850
},
{
"epoch": 1.01,
"learning_rate": 2.6261537683167976e-05,
"loss": 0.1193,
"step": 851
},
{
"epoch": 1.01,
"learning_rate": 2.621305588127746e-05,
"loss": 0.1411,
"step": 852
},
{
"epoch": 1.01,
"learning_rate": 2.616456950615338e-05,
"loss": 0.1109,
"step": 853
},
{
"epoch": 1.01,
"learning_rate": 2.6116078740589883e-05,
"loss": 0.143,
"step": 854
},
{
"epoch": 1.01,
"learning_rate": 2.606758376739768e-05,
"loss": 0.1552,
"step": 855
},
{
"epoch": 1.01,
"learning_rate": 2.6019084769403322e-05,
"loss": 0.1401,
"step": 856
},
{
"epoch": 1.02,
"learning_rate": 2.5970581929448555e-05,
"loss": 0.1238,
"step": 857
},
{
"epoch": 1.02,
"learning_rate": 2.592207543038961e-05,
"loss": 0.157,
"step": 858
},
{
"epoch": 1.02,
"learning_rate": 2.587356545509648e-05,
"loss": 0.1354,
"step": 859
},
{
"epoch": 1.02,
"learning_rate": 2.5825052186452307e-05,
"loss": 0.0772,
"step": 860
},
{
"epoch": 1.02,
"learning_rate": 2.5776535807352624e-05,
"loss": 0.1249,
"step": 861
},
{
"epoch": 1.02,
"learning_rate": 2.5728016500704698e-05,
"loss": 0.1722,
"step": 862
},
{
"epoch": 1.02,
"learning_rate": 2.5679494449426822e-05,
"loss": 0.1109,
"step": 863
},
{
"epoch": 1.02,
"learning_rate": 2.563096983644765e-05,
"loss": 0.1392,
"step": 864
},
{
"epoch": 1.03,
"learning_rate": 2.5582442844705496e-05,
"loss": 0.2738,
"step": 865
},
{
"epoch": 1.03,
"learning_rate": 2.5533913657147617e-05,
"loss": 0.1032,
"step": 866
},
{
"epoch": 1.03,
"learning_rate": 2.548538245672959e-05,
"loss": 0.1362,
"step": 867
},
{
"epoch": 1.03,
"learning_rate": 2.543684942641454e-05,
"loss": 0.1145,
"step": 868
},
{
"epoch": 1.03,
"learning_rate": 2.5388314749172504e-05,
"loss": 0.1221,
"step": 869
},
{
"epoch": 1.03,
"learning_rate": 2.5339778607979735e-05,
"loss": 0.1397,
"step": 870
},
{
"epoch": 1.03,
"learning_rate": 2.5291241185818003e-05,
"loss": 0.1286,
"step": 871
},
{
"epoch": 1.03,
"learning_rate": 2.5242702665673917e-05,
"loss": 0.1395,
"step": 872
},
{
"epoch": 1.03,
"learning_rate": 2.5194163230538193e-05,
"loss": 0.1255,
"step": 873
},
{
"epoch": 1.04,
"learning_rate": 2.5145623063405032e-05,
"loss": 0.1144,
"step": 874
},
{
"epoch": 1.04,
"learning_rate": 2.5097082347271374e-05,
"loss": 0.1663,
"step": 875
},
{
"epoch": 1.04,
"learning_rate": 2.5048541265136232e-05,
"loss": 0.0835,
"step": 876
},
{
"epoch": 1.04,
"learning_rate": 2.5e-05,
"loss": 0.1649,
"step": 877
},
{
"epoch": 1.04,
"learning_rate": 2.4951458734863774e-05,
"loss": 0.1575,
"step": 878
},
{
"epoch": 1.04,
"learning_rate": 2.490291765272863e-05,
"loss": 0.1065,
"step": 879
},
{
"epoch": 1.04,
"learning_rate": 2.4854376936594977e-05,
"loss": 0.1426,
"step": 880
},
{
"epoch": 1.04,
"learning_rate": 2.4805836769461813e-05,
"loss": 0.1179,
"step": 881
},
{
"epoch": 1.05,
"learning_rate": 2.475729733432609e-05,
"loss": 0.0955,
"step": 882
},
{
"epoch": 1.05,
"learning_rate": 2.4708758814181992e-05,
"loss": 0.1272,
"step": 883
},
{
"epoch": 1.05,
"learning_rate": 2.4660221392020274e-05,
"loss": 0.1693,
"step": 884
},
{
"epoch": 1.05,
"learning_rate": 2.461168525082751e-05,
"loss": 0.1303,
"step": 885
},
{
"epoch": 1.05,
"learning_rate": 2.456315057358547e-05,
"loss": 0.1074,
"step": 886
},
{
"epoch": 1.05,
"learning_rate": 2.451461754327042e-05,
"loss": 0.1135,
"step": 887
},
{
"epoch": 1.05,
"learning_rate": 2.4466086342852382e-05,
"loss": 0.1152,
"step": 888
},
{
"epoch": 1.05,
"learning_rate": 2.441755715529452e-05,
"loss": 0.1625,
"step": 889
},
{
"epoch": 1.05,
"learning_rate": 2.4369030163552357e-05,
"loss": 0.1822,
"step": 890
},
{
"epoch": 1.06,
"learning_rate": 2.4320505550573183e-05,
"loss": 0.1428,
"step": 891
},
{
"epoch": 1.06,
"learning_rate": 2.4271983499295305e-05,
"loss": 0.1132,
"step": 892
},
{
"epoch": 1.06,
"learning_rate": 2.422346419264738e-05,
"loss": 0.1193,
"step": 893
},
{
"epoch": 1.06,
"learning_rate": 2.4174947813547702e-05,
"loss": 0.1895,
"step": 894
},
{
"epoch": 1.06,
"learning_rate": 2.4126434544903525e-05,
"loss": 0.1162,
"step": 895
},
{
"epoch": 1.06,
"learning_rate": 2.4077924569610396e-05,
"loss": 0.1293,
"step": 896
},
{
"epoch": 1.06,
"learning_rate": 2.402941807055144e-05,
"loss": 0.0926,
"step": 897
},
{
"epoch": 1.06,
"learning_rate": 2.3980915230596684e-05,
"loss": 0.1238,
"step": 898
},
{
"epoch": 1.07,
"learning_rate": 2.3932416232602327e-05,
"loss": 0.1547,
"step": 899
},
{
"epoch": 1.07,
"learning_rate": 2.3883921259410123e-05,
"loss": 0.1359,
"step": 900
},
{
"epoch": 1.07,
"learning_rate": 2.3835430493846626e-05,
"loss": 0.1336,
"step": 901
},
{
"epoch": 1.07,
"learning_rate": 2.378694411872254e-05,
"loss": 0.1205,
"step": 902
},
{
"epoch": 1.07,
"learning_rate": 2.3738462316832033e-05,
"loss": 0.1257,
"step": 903
},
{
"epoch": 1.07,
"learning_rate": 2.3689985270951987e-05,
"loss": 0.149,
"step": 904
},
{
"epoch": 1.07,
"learning_rate": 2.364151316384139e-05,
"loss": 0.0938,
"step": 905
},
{
"epoch": 1.07,
"learning_rate": 2.3593046178240606e-05,
"loss": 0.15,
"step": 906
},
{
"epoch": 1.07,
"learning_rate": 2.3544584496870677e-05,
"loss": 0.2233,
"step": 907
},
{
"epoch": 1.08,
"learning_rate": 2.3496128302432667e-05,
"loss": 0.1576,
"step": 908
},
{
"epoch": 1.08,
"learning_rate": 2.3447677777606935e-05,
"loss": 0.0962,
"step": 909
},
{
"epoch": 1.08,
"learning_rate": 2.3399233105052477e-05,
"loss": 0.1173,
"step": 910
},
{
"epoch": 1.08,
"learning_rate": 2.335079446740622e-05,
"loss": 0.0992,
"step": 911
},
{
"epoch": 1.08,
"learning_rate": 2.330236204728236e-05,
"loss": 0.135,
"step": 912
},
{
"epoch": 1.08,
"learning_rate": 2.3253936027271618e-05,
"loss": 0.18,
"step": 913
},
{
"epoch": 1.08,
"learning_rate": 2.32055165899406e-05,
"loss": 0.1581,
"step": 914
},
{
"epoch": 1.08,
"learning_rate": 2.315710391783111e-05,
"loss": 0.1085,
"step": 915
},
{
"epoch": 1.09,
"learning_rate": 2.3108698193459434e-05,
"loss": 0.1132,
"step": 916
},
{
"epoch": 1.09,
"learning_rate": 2.3060299599315676e-05,
"loss": 0.1664,
"step": 917
},
{
"epoch": 1.09,
"learning_rate": 2.3011908317863033e-05,
"loss": 0.2236,
"step": 918
},
{
"epoch": 1.09,
"learning_rate": 2.2963524531537163e-05,
"loss": 0.1851,
"step": 919
},
{
"epoch": 1.09,
"learning_rate": 2.2915148422745445e-05,
"loss": 0.1282,
"step": 920
},
{
"epoch": 1.09,
"learning_rate": 2.286678017386634e-05,
"loss": 0.1503,
"step": 921
},
{
"epoch": 1.09