Kun-PrimaryChatModel / trainer_state.json
XiaoY1's picture
Upload trainer_state.json with huggingface_hub
8f83a17 verified
raw
history blame contribute delete
No virus
59.4 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.962025316455696,
"eval_steps": 500,
"global_step": 490,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.01,
"learning_rate": 0.0,
"loss": 2.2689,
"step": 1
},
{
"epoch": 0.02,
"learning_rate": 4.306765580733931e-06,
"loss": 1.9111,
"step": 2
},
{
"epoch": 0.03,
"learning_rate": 6.826061944859854e-06,
"loss": 2.0757,
"step": 3
},
{
"epoch": 0.04,
"learning_rate": 8.613531161467863e-06,
"loss": 1.8188,
"step": 4
},
{
"epoch": 0.05,
"learning_rate": 1e-05,
"loss": 1.7535,
"step": 5
},
{
"epoch": 0.06,
"learning_rate": 1.1132827525593786e-05,
"loss": 1.6784,
"step": 6
},
{
"epoch": 0.07,
"learning_rate": 1.2090619551221676e-05,
"loss": 1.8318,
"step": 7
},
{
"epoch": 0.08,
"learning_rate": 1.2920296742201793e-05,
"loss": 1.7084,
"step": 8
},
{
"epoch": 0.09,
"learning_rate": 1.3652123889719709e-05,
"loss": 1.6416,
"step": 9
},
{
"epoch": 0.1,
"learning_rate": 1.4306765580733935e-05,
"loss": 1.6962,
"step": 10
},
{
"epoch": 0.11,
"learning_rate": 1.4898961024049785e-05,
"loss": 1.5732,
"step": 11
},
{
"epoch": 0.12,
"learning_rate": 1.543959310632772e-05,
"loss": 1.6528,
"step": 12
},
{
"epoch": 0.13,
"learning_rate": 1.5936926411670824e-05,
"loss": 1.716,
"step": 13
},
{
"epoch": 0.14,
"learning_rate": 1.639738513195561e-05,
"loss": 1.5802,
"step": 14
},
{
"epoch": 0.15,
"learning_rate": 1.6826061944859853e-05,
"loss": 1.6403,
"step": 15
},
{
"epoch": 0.16,
"learning_rate": 1.7227062322935725e-05,
"loss": 1.5923,
"step": 16
},
{
"epoch": 0.17,
"learning_rate": 1.7603744277225883e-05,
"loss": 1.6141,
"step": 17
},
{
"epoch": 0.18,
"learning_rate": 1.7958889470453637e-05,
"loss": 1.6916,
"step": 18
},
{
"epoch": 0.19,
"learning_rate": 1.8294828004351506e-05,
"loss": 1.5832,
"step": 19
},
{
"epoch": 0.2,
"learning_rate": 1.8613531161467863e-05,
"loss": 1.6152,
"step": 20
},
{
"epoch": 0.21,
"learning_rate": 1.891668149608153e-05,
"loss": 1.6234,
"step": 21
},
{
"epoch": 0.22,
"learning_rate": 1.9205726604783716e-05,
"loss": 1.6703,
"step": 22
},
{
"epoch": 0.23,
"learning_rate": 1.94819209346638e-05,
"loss": 1.6648,
"step": 23
},
{
"epoch": 0.24,
"learning_rate": 1.9746358687061647e-05,
"loss": 1.7037,
"step": 24
},
{
"epoch": 0.25,
"learning_rate": 2e-05,
"loss": 1.6608,
"step": 25
},
{
"epoch": 0.26,
"learning_rate": 2e-05,
"loss": 1.5428,
"step": 26
},
{
"epoch": 0.27,
"learning_rate": 1.995698924731183e-05,
"loss": 1.6165,
"step": 27
},
{
"epoch": 0.28,
"learning_rate": 1.991397849462366e-05,
"loss": 1.5947,
"step": 28
},
{
"epoch": 0.29,
"learning_rate": 1.9870967741935484e-05,
"loss": 1.6807,
"step": 29
},
{
"epoch": 0.3,
"learning_rate": 1.9827956989247316e-05,
"loss": 1.4922,
"step": 30
},
{
"epoch": 0.31,
"learning_rate": 1.978494623655914e-05,
"loss": 1.5233,
"step": 31
},
{
"epoch": 0.32,
"learning_rate": 1.974193548387097e-05,
"loss": 1.6164,
"step": 32
},
{
"epoch": 0.33,
"learning_rate": 1.96989247311828e-05,
"loss": 1.4448,
"step": 33
},
{
"epoch": 0.34,
"learning_rate": 1.9655913978494624e-05,
"loss": 1.7434,
"step": 34
},
{
"epoch": 0.35,
"learning_rate": 1.9612903225806452e-05,
"loss": 1.596,
"step": 35
},
{
"epoch": 0.36,
"learning_rate": 1.956989247311828e-05,
"loss": 1.7181,
"step": 36
},
{
"epoch": 0.37,
"learning_rate": 1.952688172043011e-05,
"loss": 1.5812,
"step": 37
},
{
"epoch": 0.38,
"learning_rate": 1.948387096774194e-05,
"loss": 1.6811,
"step": 38
},
{
"epoch": 0.39,
"learning_rate": 1.9440860215053764e-05,
"loss": 1.5775,
"step": 39
},
{
"epoch": 0.41,
"learning_rate": 1.9397849462365592e-05,
"loss": 1.6463,
"step": 40
},
{
"epoch": 0.42,
"learning_rate": 1.935483870967742e-05,
"loss": 1.5282,
"step": 41
},
{
"epoch": 0.43,
"learning_rate": 1.931182795698925e-05,
"loss": 1.6476,
"step": 42
},
{
"epoch": 0.44,
"learning_rate": 1.9268817204301078e-05,
"loss": 1.4159,
"step": 43
},
{
"epoch": 0.45,
"learning_rate": 1.9225806451612907e-05,
"loss": 1.51,
"step": 44
},
{
"epoch": 0.46,
"learning_rate": 1.9182795698924732e-05,
"loss": 1.5285,
"step": 45
},
{
"epoch": 0.47,
"learning_rate": 1.913978494623656e-05,
"loss": 1.7255,
"step": 46
},
{
"epoch": 0.48,
"learning_rate": 1.909677419354839e-05,
"loss": 1.6362,
"step": 47
},
{
"epoch": 0.49,
"learning_rate": 1.9053763440860214e-05,
"loss": 1.5058,
"step": 48
},
{
"epoch": 0.5,
"learning_rate": 1.9010752688172046e-05,
"loss": 1.6969,
"step": 49
},
{
"epoch": 0.51,
"learning_rate": 1.896774193548387e-05,
"loss": 1.7406,
"step": 50
},
{
"epoch": 0.52,
"learning_rate": 1.89247311827957e-05,
"loss": 1.595,
"step": 51
},
{
"epoch": 0.53,
"learning_rate": 1.888172043010753e-05,
"loss": 1.6272,
"step": 52
},
{
"epoch": 0.54,
"learning_rate": 1.8838709677419354e-05,
"loss": 1.6688,
"step": 53
},
{
"epoch": 0.55,
"learning_rate": 1.8795698924731186e-05,
"loss": 1.4956,
"step": 54
},
{
"epoch": 0.56,
"learning_rate": 1.875268817204301e-05,
"loss": 1.6564,
"step": 55
},
{
"epoch": 0.57,
"learning_rate": 1.870967741935484e-05,
"loss": 1.6055,
"step": 56
},
{
"epoch": 0.58,
"learning_rate": 1.866666666666667e-05,
"loss": 1.3791,
"step": 57
},
{
"epoch": 0.59,
"learning_rate": 1.8623655913978497e-05,
"loss": 1.4353,
"step": 58
},
{
"epoch": 0.6,
"learning_rate": 1.8580645161290326e-05,
"loss": 1.4798,
"step": 59
},
{
"epoch": 0.61,
"learning_rate": 1.853763440860215e-05,
"loss": 1.4247,
"step": 60
},
{
"epoch": 0.62,
"learning_rate": 1.849462365591398e-05,
"loss": 1.5351,
"step": 61
},
{
"epoch": 0.63,
"learning_rate": 1.845161290322581e-05,
"loss": 1.5758,
"step": 62
},
{
"epoch": 0.64,
"learning_rate": 1.8408602150537637e-05,
"loss": 1.6437,
"step": 63
},
{
"epoch": 0.65,
"learning_rate": 1.8365591397849466e-05,
"loss": 1.6213,
"step": 64
},
{
"epoch": 0.66,
"learning_rate": 1.832258064516129e-05,
"loss": 1.6822,
"step": 65
},
{
"epoch": 0.67,
"learning_rate": 1.827956989247312e-05,
"loss": 1.7296,
"step": 66
},
{
"epoch": 0.68,
"learning_rate": 1.8236559139784948e-05,
"loss": 1.7892,
"step": 67
},
{
"epoch": 0.69,
"learning_rate": 1.8193548387096777e-05,
"loss": 1.6259,
"step": 68
},
{
"epoch": 0.7,
"learning_rate": 1.8150537634408602e-05,
"loss": 1.4952,
"step": 69
},
{
"epoch": 0.71,
"learning_rate": 1.810752688172043e-05,
"loss": 1.6235,
"step": 70
},
{
"epoch": 0.72,
"learning_rate": 1.806451612903226e-05,
"loss": 1.6421,
"step": 71
},
{
"epoch": 0.73,
"learning_rate": 1.8021505376344088e-05,
"loss": 1.6154,
"step": 72
},
{
"epoch": 0.74,
"learning_rate": 1.7978494623655916e-05,
"loss": 1.47,
"step": 73
},
{
"epoch": 0.75,
"learning_rate": 1.7935483870967742e-05,
"loss": 1.4677,
"step": 74
},
{
"epoch": 0.76,
"learning_rate": 1.789247311827957e-05,
"loss": 1.4999,
"step": 75
},
{
"epoch": 0.77,
"learning_rate": 1.78494623655914e-05,
"loss": 1.6743,
"step": 76
},
{
"epoch": 0.78,
"learning_rate": 1.7806451612903228e-05,
"loss": 1.4953,
"step": 77
},
{
"epoch": 0.79,
"learning_rate": 1.7763440860215056e-05,
"loss": 1.6313,
"step": 78
},
{
"epoch": 0.8,
"learning_rate": 1.772043010752688e-05,
"loss": 1.5617,
"step": 79
},
{
"epoch": 0.81,
"learning_rate": 1.7677419354838713e-05,
"loss": 1.5945,
"step": 80
},
{
"epoch": 0.82,
"learning_rate": 1.763440860215054e-05,
"loss": 1.5671,
"step": 81
},
{
"epoch": 0.83,
"learning_rate": 1.7591397849462367e-05,
"loss": 1.4768,
"step": 82
},
{
"epoch": 0.84,
"learning_rate": 1.7548387096774196e-05,
"loss": 1.5294,
"step": 83
},
{
"epoch": 0.85,
"learning_rate": 1.750537634408602e-05,
"loss": 1.499,
"step": 84
},
{
"epoch": 0.86,
"learning_rate": 1.7462365591397853e-05,
"loss": 1.5867,
"step": 85
},
{
"epoch": 0.87,
"learning_rate": 1.741935483870968e-05,
"loss": 1.4942,
"step": 86
},
{
"epoch": 0.88,
"learning_rate": 1.7376344086021507e-05,
"loss": 1.5331,
"step": 87
},
{
"epoch": 0.89,
"learning_rate": 1.7333333333333336e-05,
"loss": 1.7325,
"step": 88
},
{
"epoch": 0.9,
"learning_rate": 1.729032258064516e-05,
"loss": 1.6354,
"step": 89
},
{
"epoch": 0.91,
"learning_rate": 1.724731182795699e-05,
"loss": 1.6768,
"step": 90
},
{
"epoch": 0.92,
"learning_rate": 1.7204301075268818e-05,
"loss": 1.4602,
"step": 91
},
{
"epoch": 0.93,
"learning_rate": 1.7161290322580647e-05,
"loss": 1.4933,
"step": 92
},
{
"epoch": 0.94,
"learning_rate": 1.7118279569892475e-05,
"loss": 1.4517,
"step": 93
},
{
"epoch": 0.95,
"learning_rate": 1.7075268817204304e-05,
"loss": 1.7103,
"step": 94
},
{
"epoch": 0.96,
"learning_rate": 1.703225806451613e-05,
"loss": 1.5579,
"step": 95
},
{
"epoch": 0.97,
"learning_rate": 1.6989247311827958e-05,
"loss": 1.4942,
"step": 96
},
{
"epoch": 0.98,
"learning_rate": 1.6946236559139786e-05,
"loss": 1.5904,
"step": 97
},
{
"epoch": 0.99,
"learning_rate": 1.6903225806451615e-05,
"loss": 1.5026,
"step": 98
},
{
"epoch": 1.0,
"learning_rate": 1.6860215053763444e-05,
"loss": 1.3493,
"step": 99
},
{
"epoch": 1.01,
"learning_rate": 1.681720430107527e-05,
"loss": 0.9543,
"step": 100
},
{
"epoch": 1.02,
"learning_rate": 1.6774193548387098e-05,
"loss": 0.9765,
"step": 101
},
{
"epoch": 1.03,
"learning_rate": 1.6731182795698926e-05,
"loss": 0.9687,
"step": 102
},
{
"epoch": 1.04,
"learning_rate": 1.668817204301075e-05,
"loss": 1.0385,
"step": 103
},
{
"epoch": 1.05,
"learning_rate": 1.6645161290322583e-05,
"loss": 1.0394,
"step": 104
},
{
"epoch": 1.06,
"learning_rate": 1.660215053763441e-05,
"loss": 0.9033,
"step": 105
},
{
"epoch": 1.07,
"learning_rate": 1.6559139784946237e-05,
"loss": 0.8905,
"step": 106
},
{
"epoch": 1.08,
"learning_rate": 1.6516129032258066e-05,
"loss": 1.4783,
"step": 107
},
{
"epoch": 1.09,
"learning_rate": 1.6473118279569895e-05,
"loss": 1.1471,
"step": 108
},
{
"epoch": 1.1,
"learning_rate": 1.6430107526881723e-05,
"loss": 1.061,
"step": 109
},
{
"epoch": 1.11,
"learning_rate": 1.638709677419355e-05,
"loss": 1.0713,
"step": 110
},
{
"epoch": 1.12,
"learning_rate": 1.6344086021505377e-05,
"loss": 0.918,
"step": 111
},
{
"epoch": 1.13,
"learning_rate": 1.6301075268817206e-05,
"loss": 1.0217,
"step": 112
},
{
"epoch": 1.14,
"learning_rate": 1.6258064516129034e-05,
"loss": 0.9848,
"step": 113
},
{
"epoch": 1.15,
"learning_rate": 1.6215053763440863e-05,
"loss": 1.0507,
"step": 114
},
{
"epoch": 1.16,
"learning_rate": 1.6172043010752688e-05,
"loss": 1.2116,
"step": 115
},
{
"epoch": 1.17,
"learning_rate": 1.6129032258064517e-05,
"loss": 1.1489,
"step": 116
},
{
"epoch": 1.18,
"learning_rate": 1.6086021505376345e-05,
"loss": 0.9653,
"step": 117
},
{
"epoch": 1.19,
"learning_rate": 1.6043010752688174e-05,
"loss": 0.912,
"step": 118
},
{
"epoch": 1.21,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.1097,
"step": 119
},
{
"epoch": 1.22,
"learning_rate": 1.5956989247311828e-05,
"loss": 1.0009,
"step": 120
},
{
"epoch": 1.23,
"learning_rate": 1.5913978494623657e-05,
"loss": 1.1487,
"step": 121
},
{
"epoch": 1.24,
"learning_rate": 1.5870967741935485e-05,
"loss": 0.9222,
"step": 122
},
{
"epoch": 1.25,
"learning_rate": 1.5827956989247314e-05,
"loss": 0.9213,
"step": 123
},
{
"epoch": 1.26,
"learning_rate": 1.5784946236559142e-05,
"loss": 1.0347,
"step": 124
},
{
"epoch": 1.27,
"learning_rate": 1.5741935483870968e-05,
"loss": 1.014,
"step": 125
},
{
"epoch": 1.28,
"learning_rate": 1.5698924731182796e-05,
"loss": 0.9657,
"step": 126
},
{
"epoch": 1.29,
"learning_rate": 1.5655913978494625e-05,
"loss": 1.0616,
"step": 127
},
{
"epoch": 1.3,
"learning_rate": 1.5612903225806454e-05,
"loss": 0.8538,
"step": 128
},
{
"epoch": 1.31,
"learning_rate": 1.556989247311828e-05,
"loss": 0.8506,
"step": 129
},
{
"epoch": 1.32,
"learning_rate": 1.552688172043011e-05,
"loss": 1.0627,
"step": 130
},
{
"epoch": 1.33,
"learning_rate": 1.5483870967741936e-05,
"loss": 0.8975,
"step": 131
},
{
"epoch": 1.34,
"learning_rate": 1.5440860215053765e-05,
"loss": 0.8824,
"step": 132
},
{
"epoch": 1.35,
"learning_rate": 1.5397849462365593e-05,
"loss": 1.0609,
"step": 133
},
{
"epoch": 1.36,
"learning_rate": 1.535483870967742e-05,
"loss": 0.8495,
"step": 134
},
{
"epoch": 1.37,
"learning_rate": 1.531182795698925e-05,
"loss": 0.9624,
"step": 135
},
{
"epoch": 1.38,
"learning_rate": 1.5268817204301076e-05,
"loss": 0.9412,
"step": 136
},
{
"epoch": 1.39,
"learning_rate": 1.5225806451612903e-05,
"loss": 0.8386,
"step": 137
},
{
"epoch": 1.4,
"learning_rate": 1.5182795698924733e-05,
"loss": 0.912,
"step": 138
},
{
"epoch": 1.41,
"learning_rate": 1.513978494623656e-05,
"loss": 0.8699,
"step": 139
},
{
"epoch": 1.42,
"learning_rate": 1.5096774193548389e-05,
"loss": 0.9416,
"step": 140
},
{
"epoch": 1.43,
"learning_rate": 1.5053763440860215e-05,
"loss": 1.0873,
"step": 141
},
{
"epoch": 1.44,
"learning_rate": 1.5010752688172044e-05,
"loss": 0.9139,
"step": 142
},
{
"epoch": 1.45,
"learning_rate": 1.4967741935483873e-05,
"loss": 0.9538,
"step": 143
},
{
"epoch": 1.46,
"learning_rate": 1.49247311827957e-05,
"loss": 0.9326,
"step": 144
},
{
"epoch": 1.47,
"learning_rate": 1.4881720430107528e-05,
"loss": 1.0359,
"step": 145
},
{
"epoch": 1.48,
"learning_rate": 1.4838709677419357e-05,
"loss": 1.0978,
"step": 146
},
{
"epoch": 1.49,
"learning_rate": 1.4795698924731184e-05,
"loss": 0.922,
"step": 147
},
{
"epoch": 1.5,
"learning_rate": 1.4752688172043012e-05,
"loss": 0.9583,
"step": 148
},
{
"epoch": 1.51,
"learning_rate": 1.470967741935484e-05,
"loss": 0.9822,
"step": 149
},
{
"epoch": 1.52,
"learning_rate": 1.4666666666666666e-05,
"loss": 0.8844,
"step": 150
},
{
"epoch": 1.53,
"learning_rate": 1.4623655913978497e-05,
"loss": 0.9124,
"step": 151
},
{
"epoch": 1.54,
"learning_rate": 1.4580645161290324e-05,
"loss": 0.915,
"step": 152
},
{
"epoch": 1.55,
"learning_rate": 1.4537634408602152e-05,
"loss": 1.0011,
"step": 153
},
{
"epoch": 1.56,
"learning_rate": 1.4494623655913979e-05,
"loss": 0.9509,
"step": 154
},
{
"epoch": 1.57,
"learning_rate": 1.4451612903225806e-05,
"loss": 0.875,
"step": 155
},
{
"epoch": 1.58,
"learning_rate": 1.4408602150537636e-05,
"loss": 0.9167,
"step": 156
},
{
"epoch": 1.59,
"learning_rate": 1.4365591397849463e-05,
"loss": 1.0028,
"step": 157
},
{
"epoch": 1.6,
"learning_rate": 1.4322580645161292e-05,
"loss": 1.0519,
"step": 158
},
{
"epoch": 1.61,
"learning_rate": 1.4279569892473119e-05,
"loss": 0.9254,
"step": 159
},
{
"epoch": 1.62,
"learning_rate": 1.4236559139784947e-05,
"loss": 0.9952,
"step": 160
},
{
"epoch": 1.63,
"learning_rate": 1.4193548387096776e-05,
"loss": 0.8365,
"step": 161
},
{
"epoch": 1.64,
"learning_rate": 1.4150537634408603e-05,
"loss": 0.8959,
"step": 162
},
{
"epoch": 1.65,
"learning_rate": 1.410752688172043e-05,
"loss": 0.906,
"step": 163
},
{
"epoch": 1.66,
"learning_rate": 1.406451612903226e-05,
"loss": 0.9985,
"step": 164
},
{
"epoch": 1.67,
"learning_rate": 1.4021505376344087e-05,
"loss": 1.0443,
"step": 165
},
{
"epoch": 1.68,
"learning_rate": 1.3978494623655916e-05,
"loss": 0.8452,
"step": 166
},
{
"epoch": 1.69,
"learning_rate": 1.3935483870967743e-05,
"loss": 0.9754,
"step": 167
},
{
"epoch": 1.7,
"learning_rate": 1.389247311827957e-05,
"loss": 1.029,
"step": 168
},
{
"epoch": 1.71,
"learning_rate": 1.38494623655914e-05,
"loss": 0.9344,
"step": 169
},
{
"epoch": 1.72,
"learning_rate": 1.3806451612903227e-05,
"loss": 0.8564,
"step": 170
},
{
"epoch": 1.73,
"learning_rate": 1.3763440860215056e-05,
"loss": 0.8746,
"step": 171
},
{
"epoch": 1.74,
"learning_rate": 1.3720430107526882e-05,
"loss": 0.9671,
"step": 172
},
{
"epoch": 1.75,
"learning_rate": 1.367741935483871e-05,
"loss": 0.9063,
"step": 173
},
{
"epoch": 1.76,
"learning_rate": 1.363440860215054e-05,
"loss": 0.8366,
"step": 174
},
{
"epoch": 1.77,
"learning_rate": 1.3591397849462367e-05,
"loss": 0.9146,
"step": 175
},
{
"epoch": 1.78,
"learning_rate": 1.3548387096774194e-05,
"loss": 0.9435,
"step": 176
},
{
"epoch": 1.79,
"learning_rate": 1.3505376344086024e-05,
"loss": 1.0586,
"step": 177
},
{
"epoch": 1.8,
"learning_rate": 1.346236559139785e-05,
"loss": 0.9272,
"step": 178
},
{
"epoch": 1.81,
"learning_rate": 1.341935483870968e-05,
"loss": 0.9492,
"step": 179
},
{
"epoch": 1.82,
"learning_rate": 1.3376344086021506e-05,
"loss": 0.939,
"step": 180
},
{
"epoch": 1.83,
"learning_rate": 1.3333333333333333e-05,
"loss": 0.9346,
"step": 181
},
{
"epoch": 1.84,
"learning_rate": 1.3290322580645164e-05,
"loss": 0.9455,
"step": 182
},
{
"epoch": 1.85,
"learning_rate": 1.324731182795699e-05,
"loss": 0.8325,
"step": 183
},
{
"epoch": 1.86,
"learning_rate": 1.3204301075268817e-05,
"loss": 1.074,
"step": 184
},
{
"epoch": 1.87,
"learning_rate": 1.3161290322580646e-05,
"loss": 1.1218,
"step": 185
},
{
"epoch": 1.88,
"learning_rate": 1.3118279569892473e-05,
"loss": 0.9108,
"step": 186
},
{
"epoch": 1.89,
"learning_rate": 1.3075268817204303e-05,
"loss": 0.9461,
"step": 187
},
{
"epoch": 1.9,
"learning_rate": 1.303225806451613e-05,
"loss": 0.9079,
"step": 188
},
{
"epoch": 1.91,
"learning_rate": 1.2989247311827957e-05,
"loss": 0.8472,
"step": 189
},
{
"epoch": 1.92,
"learning_rate": 1.2946236559139786e-05,
"loss": 0.8697,
"step": 190
},
{
"epoch": 1.93,
"learning_rate": 1.2903225806451613e-05,
"loss": 0.9297,
"step": 191
},
{
"epoch": 1.94,
"learning_rate": 1.2860215053763443e-05,
"loss": 0.8979,
"step": 192
},
{
"epoch": 1.95,
"learning_rate": 1.281720430107527e-05,
"loss": 0.7667,
"step": 193
},
{
"epoch": 1.96,
"learning_rate": 1.2774193548387097e-05,
"loss": 0.9026,
"step": 194
},
{
"epoch": 1.97,
"learning_rate": 1.2731182795698927e-05,
"loss": 0.9931,
"step": 195
},
{
"epoch": 1.98,
"learning_rate": 1.2688172043010754e-05,
"loss": 1.0038,
"step": 196
},
{
"epoch": 1.99,
"learning_rate": 1.2645161290322581e-05,
"loss": 0.9209,
"step": 197
},
{
"epoch": 2.01,
"learning_rate": 1.260215053763441e-05,
"loss": 0.7258,
"step": 198
},
{
"epoch": 2.02,
"learning_rate": 1.2559139784946237e-05,
"loss": 0.491,
"step": 199
},
{
"epoch": 2.03,
"learning_rate": 1.2516129032258067e-05,
"loss": 0.6607,
"step": 200
},
{
"epoch": 2.04,
"learning_rate": 1.2473118279569894e-05,
"loss": 0.5564,
"step": 201
},
{
"epoch": 2.05,
"learning_rate": 1.243010752688172e-05,
"loss": 0.5636,
"step": 202
},
{
"epoch": 2.06,
"learning_rate": 1.238709677419355e-05,
"loss": 0.5425,
"step": 203
},
{
"epoch": 2.07,
"learning_rate": 1.2344086021505376e-05,
"loss": 0.5245,
"step": 204
},
{
"epoch": 2.08,
"learning_rate": 1.2301075268817207e-05,
"loss": 0.4281,
"step": 205
},
{
"epoch": 2.09,
"learning_rate": 1.2258064516129034e-05,
"loss": 0.5537,
"step": 206
},
{
"epoch": 2.1,
"learning_rate": 1.221505376344086e-05,
"loss": 0.5108,
"step": 207
},
{
"epoch": 2.11,
"learning_rate": 1.217204301075269e-05,
"loss": 0.5137,
"step": 208
},
{
"epoch": 2.12,
"learning_rate": 1.2129032258064518e-05,
"loss": 0.5287,
"step": 209
},
{
"epoch": 2.13,
"learning_rate": 1.2086021505376345e-05,
"loss": 0.5948,
"step": 210
},
{
"epoch": 2.14,
"learning_rate": 1.2043010752688173e-05,
"loss": 0.5296,
"step": 211
},
{
"epoch": 2.15,
"learning_rate": 1.2e-05,
"loss": 0.5619,
"step": 212
},
{
"epoch": 2.16,
"learning_rate": 1.195698924731183e-05,
"loss": 0.5297,
"step": 213
},
{
"epoch": 2.17,
"learning_rate": 1.1913978494623658e-05,
"loss": 0.5508,
"step": 214
},
{
"epoch": 2.18,
"learning_rate": 1.1870967741935484e-05,
"loss": 0.5285,
"step": 215
},
{
"epoch": 2.19,
"learning_rate": 1.1827956989247313e-05,
"loss": 0.5449,
"step": 216
},
{
"epoch": 2.2,
"learning_rate": 1.178494623655914e-05,
"loss": 0.5877,
"step": 217
},
{
"epoch": 2.21,
"learning_rate": 1.1741935483870967e-05,
"loss": 0.6124,
"step": 218
},
{
"epoch": 2.22,
"learning_rate": 1.1698924731182797e-05,
"loss": 0.4578,
"step": 219
},
{
"epoch": 2.23,
"learning_rate": 1.1655913978494624e-05,
"loss": 0.5648,
"step": 220
},
{
"epoch": 2.24,
"learning_rate": 1.1612903225806453e-05,
"loss": 0.5497,
"step": 221
},
{
"epoch": 2.25,
"learning_rate": 1.156989247311828e-05,
"loss": 0.4563,
"step": 222
},
{
"epoch": 2.26,
"learning_rate": 1.1526881720430108e-05,
"loss": 0.5004,
"step": 223
},
{
"epoch": 2.27,
"learning_rate": 1.1483870967741937e-05,
"loss": 0.5579,
"step": 224
},
{
"epoch": 2.28,
"learning_rate": 1.1440860215053764e-05,
"loss": 0.5161,
"step": 225
},
{
"epoch": 2.29,
"learning_rate": 1.1397849462365593e-05,
"loss": 0.4854,
"step": 226
},
{
"epoch": 2.3,
"learning_rate": 1.1354838709677421e-05,
"loss": 0.5003,
"step": 227
},
{
"epoch": 2.31,
"learning_rate": 1.1311827956989248e-05,
"loss": 0.5601,
"step": 228
},
{
"epoch": 2.32,
"learning_rate": 1.1268817204301077e-05,
"loss": 0.4731,
"step": 229
},
{
"epoch": 2.33,
"learning_rate": 1.1225806451612904e-05,
"loss": 0.5628,
"step": 230
},
{
"epoch": 2.34,
"learning_rate": 1.118279569892473e-05,
"loss": 0.502,
"step": 231
},
{
"epoch": 2.35,
"learning_rate": 1.1139784946236561e-05,
"loss": 0.4052,
"step": 232
},
{
"epoch": 2.36,
"learning_rate": 1.1096774193548388e-05,
"loss": 0.5881,
"step": 233
},
{
"epoch": 2.37,
"learning_rate": 1.1053763440860216e-05,
"loss": 0.5344,
"step": 234
},
{
"epoch": 2.38,
"learning_rate": 1.1010752688172043e-05,
"loss": 0.5503,
"step": 235
},
{
"epoch": 2.39,
"learning_rate": 1.096774193548387e-05,
"loss": 0.4168,
"step": 236
},
{
"epoch": 2.4,
"learning_rate": 1.09247311827957e-05,
"loss": 0.4879,
"step": 237
},
{
"epoch": 2.41,
"learning_rate": 1.0881720430107528e-05,
"loss": 0.4623,
"step": 238
},
{
"epoch": 2.42,
"learning_rate": 1.0838709677419356e-05,
"loss": 0.4799,
"step": 239
},
{
"epoch": 2.43,
"learning_rate": 1.0795698924731183e-05,
"loss": 0.5277,
"step": 240
},
{
"epoch": 2.44,
"learning_rate": 1.0752688172043012e-05,
"loss": 0.6051,
"step": 241
},
{
"epoch": 2.45,
"learning_rate": 1.070967741935484e-05,
"loss": 0.5192,
"step": 242
},
{
"epoch": 2.46,
"learning_rate": 1.0666666666666667e-05,
"loss": 0.4111,
"step": 243
},
{
"epoch": 2.47,
"learning_rate": 1.0623655913978494e-05,
"loss": 0.5806,
"step": 244
},
{
"epoch": 2.48,
"learning_rate": 1.0580645161290325e-05,
"loss": 0.5616,
"step": 245
},
{
"epoch": 2.49,
"learning_rate": 1.0537634408602151e-05,
"loss": 0.5773,
"step": 246
},
{
"epoch": 2.5,
"learning_rate": 1.049462365591398e-05,
"loss": 0.4419,
"step": 247
},
{
"epoch": 2.51,
"learning_rate": 1.0451612903225807e-05,
"loss": 0.6086,
"step": 248
},
{
"epoch": 2.52,
"learning_rate": 1.0408602150537634e-05,
"loss": 0.5957,
"step": 249
},
{
"epoch": 2.53,
"learning_rate": 1.0365591397849464e-05,
"loss": 0.4609,
"step": 250
},
{
"epoch": 2.54,
"learning_rate": 1.0322580645161291e-05,
"loss": 0.4956,
"step": 251
},
{
"epoch": 2.55,
"learning_rate": 1.027956989247312e-05,
"loss": 0.5612,
"step": 252
},
{
"epoch": 2.56,
"learning_rate": 1.0236559139784947e-05,
"loss": 0.5157,
"step": 253
},
{
"epoch": 2.57,
"learning_rate": 1.0193548387096774e-05,
"loss": 0.4884,
"step": 254
},
{
"epoch": 2.58,
"learning_rate": 1.0150537634408604e-05,
"loss": 0.4576,
"step": 255
},
{
"epoch": 2.59,
"learning_rate": 1.0107526881720431e-05,
"loss": 0.4093,
"step": 256
},
{
"epoch": 2.6,
"learning_rate": 1.0064516129032258e-05,
"loss": 0.5521,
"step": 257
},
{
"epoch": 2.61,
"learning_rate": 1.0021505376344087e-05,
"loss": 0.6088,
"step": 258
},
{
"epoch": 2.62,
"learning_rate": 9.978494623655915e-06,
"loss": 0.4471,
"step": 259
},
{
"epoch": 2.63,
"learning_rate": 9.935483870967742e-06,
"loss": 0.488,
"step": 260
},
{
"epoch": 2.64,
"learning_rate": 9.89247311827957e-06,
"loss": 0.552,
"step": 261
},
{
"epoch": 2.65,
"learning_rate": 9.8494623655914e-06,
"loss": 0.4774,
"step": 262
},
{
"epoch": 2.66,
"learning_rate": 9.806451612903226e-06,
"loss": 0.5985,
"step": 263
},
{
"epoch": 2.67,
"learning_rate": 9.763440860215055e-06,
"loss": 0.4899,
"step": 264
},
{
"epoch": 2.68,
"learning_rate": 9.720430107526882e-06,
"loss": 0.5514,
"step": 265
},
{
"epoch": 2.69,
"learning_rate": 9.67741935483871e-06,
"loss": 0.5196,
"step": 266
},
{
"epoch": 2.7,
"learning_rate": 9.634408602150539e-06,
"loss": 0.4633,
"step": 267
},
{
"epoch": 2.71,
"learning_rate": 9.591397849462366e-06,
"loss": 0.4797,
"step": 268
},
{
"epoch": 2.72,
"learning_rate": 9.548387096774195e-06,
"loss": 0.6344,
"step": 269
},
{
"epoch": 2.73,
"learning_rate": 9.505376344086023e-06,
"loss": 0.4854,
"step": 270
},
{
"epoch": 2.74,
"learning_rate": 9.46236559139785e-06,
"loss": 0.4978,
"step": 271
},
{
"epoch": 2.75,
"learning_rate": 9.419354838709677e-06,
"loss": 0.4673,
"step": 272
},
{
"epoch": 2.76,
"learning_rate": 9.376344086021506e-06,
"loss": 0.5449,
"step": 273
},
{
"epoch": 2.77,
"learning_rate": 9.333333333333334e-06,
"loss": 0.4383,
"step": 274
},
{
"epoch": 2.78,
"learning_rate": 9.290322580645163e-06,
"loss": 0.4366,
"step": 275
},
{
"epoch": 2.79,
"learning_rate": 9.24731182795699e-06,
"loss": 0.496,
"step": 276
},
{
"epoch": 2.81,
"learning_rate": 9.204301075268819e-06,
"loss": 0.4166,
"step": 277
},
{
"epoch": 2.82,
"learning_rate": 9.161290322580645e-06,
"loss": 0.5266,
"step": 278
},
{
"epoch": 2.83,
"learning_rate": 9.118279569892474e-06,
"loss": 0.6554,
"step": 279
},
{
"epoch": 2.84,
"learning_rate": 9.075268817204301e-06,
"loss": 0.5783,
"step": 280
},
{
"epoch": 2.85,
"learning_rate": 9.03225806451613e-06,
"loss": 0.4905,
"step": 281
},
{
"epoch": 2.86,
"learning_rate": 8.989247311827958e-06,
"loss": 0.4702,
"step": 282
},
{
"epoch": 2.87,
"learning_rate": 8.946236559139785e-06,
"loss": 0.4972,
"step": 283
},
{
"epoch": 2.88,
"learning_rate": 8.903225806451614e-06,
"loss": 0.4287,
"step": 284
},
{
"epoch": 2.89,
"learning_rate": 8.86021505376344e-06,
"loss": 0.6365,
"step": 285
},
{
"epoch": 2.9,
"learning_rate": 8.81720430107527e-06,
"loss": 0.5102,
"step": 286
},
{
"epoch": 2.91,
"learning_rate": 8.774193548387098e-06,
"loss": 0.4436,
"step": 287
},
{
"epoch": 2.92,
"learning_rate": 8.731182795698927e-06,
"loss": 0.4853,
"step": 288
},
{
"epoch": 2.93,
"learning_rate": 8.688172043010754e-06,
"loss": 0.612,
"step": 289
},
{
"epoch": 2.94,
"learning_rate": 8.64516129032258e-06,
"loss": 0.51,
"step": 290
},
{
"epoch": 2.95,
"learning_rate": 8.602150537634409e-06,
"loss": 0.552,
"step": 291
},
{
"epoch": 2.96,
"learning_rate": 8.559139784946238e-06,
"loss": 0.5142,
"step": 292
},
{
"epoch": 2.97,
"learning_rate": 8.516129032258065e-06,
"loss": 0.5301,
"step": 293
},
{
"epoch": 2.98,
"learning_rate": 8.473118279569893e-06,
"loss": 0.5718,
"step": 294
},
{
"epoch": 2.99,
"learning_rate": 8.430107526881722e-06,
"loss": 0.5609,
"step": 295
},
{
"epoch": 3.0,
"learning_rate": 8.387096774193549e-06,
"loss": 0.6477,
"step": 296
},
{
"epoch": 3.01,
"learning_rate": 8.344086021505376e-06,
"loss": 0.2912,
"step": 297
},
{
"epoch": 3.02,
"learning_rate": 8.301075268817204e-06,
"loss": 0.2973,
"step": 298
},
{
"epoch": 3.03,
"learning_rate": 8.258064516129033e-06,
"loss": 0.2227,
"step": 299
},
{
"epoch": 3.04,
"learning_rate": 8.215053763440862e-06,
"loss": 0.2563,
"step": 300
},
{
"epoch": 3.05,
"learning_rate": 8.172043010752689e-06,
"loss": 0.2987,
"step": 301
},
{
"epoch": 3.06,
"learning_rate": 8.129032258064517e-06,
"loss": 0.2424,
"step": 302
},
{
"epoch": 3.07,
"learning_rate": 8.086021505376344e-06,
"loss": 0.284,
"step": 303
},
{
"epoch": 3.08,
"learning_rate": 8.043010752688173e-06,
"loss": 0.2172,
"step": 304
},
{
"epoch": 3.09,
"learning_rate": 8.000000000000001e-06,
"loss": 0.2786,
"step": 305
},
{
"epoch": 3.1,
"learning_rate": 7.956989247311828e-06,
"loss": 0.245,
"step": 306
},
{
"epoch": 3.11,
"learning_rate": 7.913978494623657e-06,
"loss": 0.241,
"step": 307
},
{
"epoch": 3.12,
"learning_rate": 7.870967741935484e-06,
"loss": 0.2075,
"step": 308
},
{
"epoch": 3.13,
"learning_rate": 7.827956989247312e-06,
"loss": 0.243,
"step": 309
},
{
"epoch": 3.14,
"learning_rate": 7.78494623655914e-06,
"loss": 0.2792,
"step": 310
},
{
"epoch": 3.15,
"learning_rate": 7.741935483870968e-06,
"loss": 0.2247,
"step": 311
},
{
"epoch": 3.16,
"learning_rate": 7.698924731182797e-06,
"loss": 0.2449,
"step": 312
},
{
"epoch": 3.17,
"learning_rate": 7.655913978494625e-06,
"loss": 0.2253,
"step": 313
},
{
"epoch": 3.18,
"learning_rate": 7.612903225806451e-06,
"loss": 0.3203,
"step": 314
},
{
"epoch": 3.19,
"learning_rate": 7.56989247311828e-06,
"loss": 0.1737,
"step": 315
},
{
"epoch": 3.2,
"learning_rate": 7.526881720430108e-06,
"loss": 0.2394,
"step": 316
},
{
"epoch": 3.21,
"learning_rate": 7.483870967741936e-06,
"loss": 0.3014,
"step": 317
},
{
"epoch": 3.22,
"learning_rate": 7.440860215053764e-06,
"loss": 0.2347,
"step": 318
},
{
"epoch": 3.23,
"learning_rate": 7.397849462365592e-06,
"loss": 0.2315,
"step": 319
},
{
"epoch": 3.24,
"learning_rate": 7.35483870967742e-06,
"loss": 0.2328,
"step": 320
},
{
"epoch": 3.25,
"learning_rate": 7.311827956989248e-06,
"loss": 0.2297,
"step": 321
},
{
"epoch": 3.26,
"learning_rate": 7.268817204301076e-06,
"loss": 0.3137,
"step": 322
},
{
"epoch": 3.27,
"learning_rate": 7.225806451612903e-06,
"loss": 0.2103,
"step": 323
},
{
"epoch": 3.28,
"learning_rate": 7.182795698924732e-06,
"loss": 0.1881,
"step": 324
},
{
"epoch": 3.29,
"learning_rate": 7.139784946236559e-06,
"loss": 0.2187,
"step": 325
},
{
"epoch": 3.3,
"learning_rate": 7.096774193548388e-06,
"loss": 0.2592,
"step": 326
},
{
"epoch": 3.31,
"learning_rate": 7.053763440860215e-06,
"loss": 0.1173,
"step": 327
},
{
"epoch": 3.32,
"learning_rate": 7.010752688172044e-06,
"loss": 0.1956,
"step": 328
},
{
"epoch": 3.33,
"learning_rate": 6.967741935483871e-06,
"loss": 0.214,
"step": 329
},
{
"epoch": 3.34,
"learning_rate": 6.9247311827957e-06,
"loss": 0.211,
"step": 330
},
{
"epoch": 3.35,
"learning_rate": 6.881720430107528e-06,
"loss": 0.2597,
"step": 331
},
{
"epoch": 3.36,
"learning_rate": 6.838709677419355e-06,
"loss": 0.1829,
"step": 332
},
{
"epoch": 3.37,
"learning_rate": 6.795698924731183e-06,
"loss": 0.2693,
"step": 333
},
{
"epoch": 3.38,
"learning_rate": 6.752688172043012e-06,
"loss": 0.2176,
"step": 334
},
{
"epoch": 3.39,
"learning_rate": 6.70967741935484e-06,
"loss": 0.1621,
"step": 335
},
{
"epoch": 3.4,
"learning_rate": 6.666666666666667e-06,
"loss": 0.2793,
"step": 336
},
{
"epoch": 3.41,
"learning_rate": 6.623655913978495e-06,
"loss": 0.22,
"step": 337
},
{
"epoch": 3.42,
"learning_rate": 6.580645161290323e-06,
"loss": 0.2257,
"step": 338
},
{
"epoch": 3.43,
"learning_rate": 6.537634408602152e-06,
"loss": 0.2905,
"step": 339
},
{
"epoch": 3.44,
"learning_rate": 6.494623655913979e-06,
"loss": 0.2309,
"step": 340
},
{
"epoch": 3.45,
"learning_rate": 6.451612903225806e-06,
"loss": 0.2152,
"step": 341
},
{
"epoch": 3.46,
"learning_rate": 6.408602150537635e-06,
"loss": 0.3047,
"step": 342
},
{
"epoch": 3.47,
"learning_rate": 6.365591397849464e-06,
"loss": 0.2,
"step": 343
},
{
"epoch": 3.48,
"learning_rate": 6.3225806451612906e-06,
"loss": 0.1949,
"step": 344
},
{
"epoch": 3.49,
"learning_rate": 6.279569892473118e-06,
"loss": 0.2897,
"step": 345
},
{
"epoch": 3.5,
"learning_rate": 6.236559139784947e-06,
"loss": 0.2341,
"step": 346
},
{
"epoch": 3.51,
"learning_rate": 6.193548387096775e-06,
"loss": 0.286,
"step": 347
},
{
"epoch": 3.52,
"learning_rate": 6.150537634408603e-06,
"loss": 0.291,
"step": 348
},
{
"epoch": 3.53,
"learning_rate": 6.10752688172043e-06,
"loss": 0.2408,
"step": 349
},
{
"epoch": 3.54,
"learning_rate": 6.064516129032259e-06,
"loss": 0.2166,
"step": 350
},
{
"epoch": 3.55,
"learning_rate": 6.021505376344087e-06,
"loss": 0.213,
"step": 351
},
{
"epoch": 3.56,
"learning_rate": 5.978494623655915e-06,
"loss": 0.2057,
"step": 352
},
{
"epoch": 3.57,
"learning_rate": 5.935483870967742e-06,
"loss": 0.2169,
"step": 353
},
{
"epoch": 3.58,
"learning_rate": 5.89247311827957e-06,
"loss": 0.19,
"step": 354
},
{
"epoch": 3.59,
"learning_rate": 5.849462365591399e-06,
"loss": 0.2565,
"step": 355
},
{
"epoch": 3.61,
"learning_rate": 5.806451612903226e-06,
"loss": 0.2503,
"step": 356
},
{
"epoch": 3.62,
"learning_rate": 5.763440860215054e-06,
"loss": 0.207,
"step": 357
},
{
"epoch": 3.63,
"learning_rate": 5.720430107526882e-06,
"loss": 0.1996,
"step": 358
},
{
"epoch": 3.64,
"learning_rate": 5.677419354838711e-06,
"loss": 0.2092,
"step": 359
},
{
"epoch": 3.65,
"learning_rate": 5.634408602150538e-06,
"loss": 0.1877,
"step": 360
},
{
"epoch": 3.66,
"learning_rate": 5.591397849462365e-06,
"loss": 0.2511,
"step": 361
},
{
"epoch": 3.67,
"learning_rate": 5.548387096774194e-06,
"loss": 0.2252,
"step": 362
},
{
"epoch": 3.68,
"learning_rate": 5.505376344086022e-06,
"loss": 0.212,
"step": 363
},
{
"epoch": 3.69,
"learning_rate": 5.46236559139785e-06,
"loss": 0.2778,
"step": 364
},
{
"epoch": 3.7,
"learning_rate": 5.419354838709678e-06,
"loss": 0.2931,
"step": 365
},
{
"epoch": 3.71,
"learning_rate": 5.376344086021506e-06,
"loss": 0.2711,
"step": 366
},
{
"epoch": 3.72,
"learning_rate": 5.333333333333334e-06,
"loss": 0.2175,
"step": 367
},
{
"epoch": 3.73,
"learning_rate": 5.290322580645162e-06,
"loss": 0.1713,
"step": 368
},
{
"epoch": 3.74,
"learning_rate": 5.24731182795699e-06,
"loss": 0.2586,
"step": 369
},
{
"epoch": 3.75,
"learning_rate": 5.204301075268817e-06,
"loss": 0.249,
"step": 370
},
{
"epoch": 3.76,
"learning_rate": 5.161290322580646e-06,
"loss": 0.1845,
"step": 371
},
{
"epoch": 3.77,
"learning_rate": 5.118279569892473e-06,
"loss": 0.2393,
"step": 372
},
{
"epoch": 3.78,
"learning_rate": 5.075268817204302e-06,
"loss": 0.2239,
"step": 373
},
{
"epoch": 3.79,
"learning_rate": 5.032258064516129e-06,
"loss": 0.247,
"step": 374
},
{
"epoch": 3.8,
"learning_rate": 4.9892473118279576e-06,
"loss": 0.2714,
"step": 375
},
{
"epoch": 3.81,
"learning_rate": 4.946236559139785e-06,
"loss": 0.256,
"step": 376
},
{
"epoch": 3.82,
"learning_rate": 4.903225806451613e-06,
"loss": 0.253,
"step": 377
},
{
"epoch": 3.83,
"learning_rate": 4.860215053763441e-06,
"loss": 0.2299,
"step": 378
},
{
"epoch": 3.84,
"learning_rate": 4.8172043010752695e-06,
"loss": 0.2029,
"step": 379
},
{
"epoch": 3.85,
"learning_rate": 4.774193548387097e-06,
"loss": 0.2053,
"step": 380
},
{
"epoch": 3.86,
"learning_rate": 4.731182795698925e-06,
"loss": 0.1907,
"step": 381
},
{
"epoch": 3.87,
"learning_rate": 4.688172043010753e-06,
"loss": 0.271,
"step": 382
},
{
"epoch": 3.88,
"learning_rate": 4.6451612903225815e-06,
"loss": 0.2088,
"step": 383
},
{
"epoch": 3.89,
"learning_rate": 4.602150537634409e-06,
"loss": 0.251,
"step": 384
},
{
"epoch": 3.9,
"learning_rate": 4.559139784946237e-06,
"loss": 0.2438,
"step": 385
},
{
"epoch": 3.91,
"learning_rate": 4.516129032258065e-06,
"loss": 0.272,
"step": 386
},
{
"epoch": 3.92,
"learning_rate": 4.473118279569893e-06,
"loss": 0.1858,
"step": 387
},
{
"epoch": 3.93,
"learning_rate": 4.43010752688172e-06,
"loss": 0.2267,
"step": 388
},
{
"epoch": 3.94,
"learning_rate": 4.387096774193549e-06,
"loss": 0.2414,
"step": 389
},
{
"epoch": 3.95,
"learning_rate": 4.344086021505377e-06,
"loss": 0.2263,
"step": 390
},
{
"epoch": 3.96,
"learning_rate": 4.3010752688172045e-06,
"loss": 0.2687,
"step": 391
},
{
"epoch": 3.97,
"learning_rate": 4.258064516129032e-06,
"loss": 0.1808,
"step": 392
},
{
"epoch": 3.98,
"learning_rate": 4.215053763440861e-06,
"loss": 0.2385,
"step": 393
},
{
"epoch": 3.99,
"learning_rate": 4.172043010752688e-06,
"loss": 0.1518,
"step": 394
},
{
"epoch": 4.0,
"learning_rate": 4.1290322580645165e-06,
"loss": 0.212,
"step": 395
},
{
"epoch": 4.01,
"learning_rate": 4.086021505376344e-06,
"loss": 0.1282,
"step": 396
},
{
"epoch": 4.02,
"learning_rate": 4.043010752688172e-06,
"loss": 0.1112,
"step": 397
},
{
"epoch": 4.03,
"learning_rate": 4.000000000000001e-06,
"loss": 0.0839,
"step": 398
},
{
"epoch": 4.04,
"learning_rate": 3.9569892473118284e-06,
"loss": 0.1306,
"step": 399
},
{
"epoch": 4.05,
"learning_rate": 3.913978494623656e-06,
"loss": 0.0748,
"step": 400
},
{
"epoch": 4.06,
"learning_rate": 3.870967741935484e-06,
"loss": 0.119,
"step": 401
},
{
"epoch": 4.07,
"learning_rate": 3.827956989247313e-06,
"loss": 0.0837,
"step": 402
},
{
"epoch": 4.08,
"learning_rate": 3.78494623655914e-06,
"loss": 0.1067,
"step": 403
},
{
"epoch": 4.09,
"learning_rate": 3.741935483870968e-06,
"loss": 0.1242,
"step": 404
},
{
"epoch": 4.1,
"learning_rate": 3.698924731182796e-06,
"loss": 0.0896,
"step": 405
},
{
"epoch": 4.11,
"learning_rate": 3.655913978494624e-06,
"loss": 0.0752,
"step": 406
},
{
"epoch": 4.12,
"learning_rate": 3.6129032258064515e-06,
"loss": 0.0812,
"step": 407
},
{
"epoch": 4.13,
"learning_rate": 3.5698924731182797e-06,
"loss": 0.0839,
"step": 408
},
{
"epoch": 4.14,
"learning_rate": 3.5268817204301075e-06,
"loss": 0.1174,
"step": 409
},
{
"epoch": 4.15,
"learning_rate": 3.4838709677419357e-06,
"loss": 0.1314,
"step": 410
},
{
"epoch": 4.16,
"learning_rate": 3.440860215053764e-06,
"loss": 0.1054,
"step": 411
},
{
"epoch": 4.17,
"learning_rate": 3.3978494623655917e-06,
"loss": 0.0968,
"step": 412
},
{
"epoch": 4.18,
"learning_rate": 3.35483870967742e-06,
"loss": 0.1095,
"step": 413
},
{
"epoch": 4.19,
"learning_rate": 3.3118279569892476e-06,
"loss": 0.1358,
"step": 414
},
{
"epoch": 4.2,
"learning_rate": 3.268817204301076e-06,
"loss": 0.0977,
"step": 415
},
{
"epoch": 4.21,
"learning_rate": 3.225806451612903e-06,
"loss": 0.1667,
"step": 416
},
{
"epoch": 4.22,
"learning_rate": 3.182795698924732e-06,
"loss": 0.0975,
"step": 417
},
{
"epoch": 4.23,
"learning_rate": 3.139784946236559e-06,
"loss": 0.0999,
"step": 418
},
{
"epoch": 4.24,
"learning_rate": 3.0967741935483874e-06,
"loss": 0.0908,
"step": 419
},
{
"epoch": 4.25,
"learning_rate": 3.053763440860215e-06,
"loss": 0.1005,
"step": 420
},
{
"epoch": 4.26,
"learning_rate": 3.0107526881720433e-06,
"loss": 0.0656,
"step": 421
},
{
"epoch": 4.27,
"learning_rate": 2.967741935483871e-06,
"loss": 0.1301,
"step": 422
},
{
"epoch": 4.28,
"learning_rate": 2.9247311827956993e-06,
"loss": 0.0677,
"step": 423
},
{
"epoch": 4.29,
"learning_rate": 2.881720430107527e-06,
"loss": 0.0866,
"step": 424
},
{
"epoch": 4.3,
"learning_rate": 2.8387096774193553e-06,
"loss": 0.0847,
"step": 425
},
{
"epoch": 4.31,
"learning_rate": 2.7956989247311827e-06,
"loss": 0.1039,
"step": 426
},
{
"epoch": 4.32,
"learning_rate": 2.752688172043011e-06,
"loss": 0.0864,
"step": 427
},
{
"epoch": 4.33,
"learning_rate": 2.709677419354839e-06,
"loss": 0.1166,
"step": 428
},
{
"epoch": 4.34,
"learning_rate": 2.666666666666667e-06,
"loss": 0.0743,
"step": 429
},
{
"epoch": 4.35,
"learning_rate": 2.623655913978495e-06,
"loss": 0.1162,
"step": 430
},
{
"epoch": 4.36,
"learning_rate": 2.580645161290323e-06,
"loss": 0.1068,
"step": 431
},
{
"epoch": 4.37,
"learning_rate": 2.537634408602151e-06,
"loss": 0.12,
"step": 432
},
{
"epoch": 4.38,
"learning_rate": 2.4946236559139788e-06,
"loss": 0.0886,
"step": 433
},
{
"epoch": 4.39,
"learning_rate": 2.4516129032258066e-06,
"loss": 0.0796,
"step": 434
},
{
"epoch": 4.41,
"learning_rate": 2.4086021505376348e-06,
"loss": 0.0748,
"step": 435
},
{
"epoch": 4.42,
"learning_rate": 2.3655913978494625e-06,
"loss": 0.1078,
"step": 436
},
{
"epoch": 4.43,
"learning_rate": 2.3225806451612907e-06,
"loss": 0.1135,
"step": 437
},
{
"epoch": 4.44,
"learning_rate": 2.2795698924731185e-06,
"loss": 0.1138,
"step": 438
},
{
"epoch": 4.45,
"learning_rate": 2.2365591397849463e-06,
"loss": 0.0867,
"step": 439
},
{
"epoch": 4.46,
"learning_rate": 2.1935483870967745e-06,
"loss": 0.0923,
"step": 440
},
{
"epoch": 4.47,
"learning_rate": 2.1505376344086023e-06,
"loss": 0.0791,
"step": 441
},
{
"epoch": 4.48,
"learning_rate": 2.1075268817204305e-06,
"loss": 0.0905,
"step": 442
},
{
"epoch": 4.49,
"learning_rate": 2.0645161290322582e-06,
"loss": 0.0952,
"step": 443
},
{
"epoch": 4.5,
"learning_rate": 2.021505376344086e-06,
"loss": 0.1213,
"step": 444
},
{
"epoch": 4.51,
"learning_rate": 1.9784946236559142e-06,
"loss": 0.0832,
"step": 445
},
{
"epoch": 4.52,
"learning_rate": 1.935483870967742e-06,
"loss": 0.1241,
"step": 446
},
{
"epoch": 4.53,
"learning_rate": 1.89247311827957e-06,
"loss": 0.0873,
"step": 447
},
{
"epoch": 4.54,
"learning_rate": 1.849462365591398e-06,
"loss": 0.0956,
"step": 448
},
{
"epoch": 4.55,
"learning_rate": 1.8064516129032258e-06,
"loss": 0.0793,
"step": 449
},
{
"epoch": 4.56,
"learning_rate": 1.7634408602150537e-06,
"loss": 0.1163,
"step": 450
},
{
"epoch": 4.57,
"learning_rate": 1.720430107526882e-06,
"loss": 0.1128,
"step": 451
},
{
"epoch": 4.58,
"learning_rate": 1.67741935483871e-06,
"loss": 0.1018,
"step": 452
},
{
"epoch": 4.59,
"learning_rate": 1.634408602150538e-06,
"loss": 0.0715,
"step": 453
},
{
"epoch": 4.6,
"learning_rate": 1.591397849462366e-06,
"loss": 0.1088,
"step": 454
},
{
"epoch": 4.61,
"learning_rate": 1.5483870967741937e-06,
"loss": 0.1119,
"step": 455
},
{
"epoch": 4.62,
"learning_rate": 1.5053763440860217e-06,
"loss": 0.1086,
"step": 456
},
{
"epoch": 4.63,
"learning_rate": 1.4623655913978497e-06,
"loss": 0.049,
"step": 457
},
{
"epoch": 4.64,
"learning_rate": 1.4193548387096776e-06,
"loss": 0.1056,
"step": 458
},
{
"epoch": 4.65,
"learning_rate": 1.3763440860215054e-06,
"loss": 0.1173,
"step": 459
},
{
"epoch": 4.66,
"learning_rate": 1.3333333333333334e-06,
"loss": 0.0988,
"step": 460
},
{
"epoch": 4.67,
"learning_rate": 1.2903225806451614e-06,
"loss": 0.1257,
"step": 461
},
{
"epoch": 4.68,
"learning_rate": 1.2473118279569894e-06,
"loss": 0.0812,
"step": 462
},
{
"epoch": 4.69,
"learning_rate": 1.2043010752688174e-06,
"loss": 0.0941,
"step": 463
},
{
"epoch": 4.7,
"learning_rate": 1.1612903225806454e-06,
"loss": 0.0967,
"step": 464
},
{
"epoch": 4.71,
"learning_rate": 1.1182795698924731e-06,
"loss": 0.0848,
"step": 465
},
{
"epoch": 4.72,
"learning_rate": 1.0752688172043011e-06,
"loss": 0.1152,
"step": 466
},
{
"epoch": 4.73,
"learning_rate": 1.0322580645161291e-06,
"loss": 0.1088,
"step": 467
},
{
"epoch": 4.74,
"learning_rate": 9.892473118279571e-07,
"loss": 0.134,
"step": 468
},
{
"epoch": 4.75,
"learning_rate": 9.46236559139785e-07,
"loss": 0.0838,
"step": 469
},
{
"epoch": 4.76,
"learning_rate": 9.032258064516129e-07,
"loss": 0.0887,
"step": 470
},
{
"epoch": 4.77,
"learning_rate": 8.60215053763441e-07,
"loss": 0.1532,
"step": 471
},
{
"epoch": 4.78,
"learning_rate": 8.17204301075269e-07,
"loss": 0.0614,
"step": 472
},
{
"epoch": 4.79,
"learning_rate": 7.741935483870968e-07,
"loss": 0.0752,
"step": 473
},
{
"epoch": 4.8,
"learning_rate": 7.311827956989248e-07,
"loss": 0.0647,
"step": 474
},
{
"epoch": 4.81,
"learning_rate": 6.881720430107527e-07,
"loss": 0.0669,
"step": 475
},
{
"epoch": 4.82,
"learning_rate": 6.451612903225807e-07,
"loss": 0.141,
"step": 476
},
{
"epoch": 4.83,
"learning_rate": 6.021505376344087e-07,
"loss": 0.1032,
"step": 477
},
{
"epoch": 4.84,
"learning_rate": 5.591397849462366e-07,
"loss": 0.1112,
"step": 478
},
{
"epoch": 4.85,
"learning_rate": 5.161290322580646e-07,
"loss": 0.0817,
"step": 479
},
{
"epoch": 4.86,
"learning_rate": 4.731182795698925e-07,
"loss": 0.0868,
"step": 480
},
{
"epoch": 4.87,
"learning_rate": 4.301075268817205e-07,
"loss": 0.1169,
"step": 481
},
{
"epoch": 4.88,
"learning_rate": 3.870967741935484e-07,
"loss": 0.1297,
"step": 482
},
{
"epoch": 4.89,
"learning_rate": 3.4408602150537636e-07,
"loss": 0.0974,
"step": 483
},
{
"epoch": 4.9,
"learning_rate": 3.0107526881720434e-07,
"loss": 0.0888,
"step": 484
},
{
"epoch": 4.91,
"learning_rate": 2.580645161290323e-07,
"loss": 0.1391,
"step": 485
},
{
"epoch": 4.92,
"learning_rate": 2.1505376344086024e-07,
"loss": 0.0777,
"step": 486
},
{
"epoch": 4.93,
"learning_rate": 1.7204301075268818e-07,
"loss": 0.0964,
"step": 487
},
{
"epoch": 4.94,
"learning_rate": 1.2903225806451614e-07,
"loss": 0.0738,
"step": 488
},
{
"epoch": 4.95,
"learning_rate": 8.602150537634409e-08,
"loss": 0.1061,
"step": 489
},
{
"epoch": 4.96,
"learning_rate": 4.3010752688172045e-08,
"loss": 0.098,
"step": 490
},
{
"epoch": 4.96,
"step": 490,
"total_flos": 146652980723712.0,
"train_loss": 0.6916719505221259,
"train_runtime": 14223.7593,
"train_samples_per_second": 4.44,
"train_steps_per_second": 0.034
}
],
"logging_steps": 1.0,
"max_steps": 490,
"num_input_tokens_seen": 0,
"num_train_epochs": 5,
"save_steps": 500,
"total_flos": 146652980723712.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}