gcode_peft / 44497593 /checkpoint-2000 /trainer_state.json
ke-lly's picture
Training in progress, step 500
5fe7002 verified
Raw
History Blame Contribute Delete
235 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 5.989144675276062,
"eval_steps": 100,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 1.4099295e-05,
"loss": 2.9964,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 1.409859e-05,
"loss": 2.9957,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 1.4097885e-05,
"loss": 2.9916,
"step": 3
},
{
"epoch": 0.01,
"learning_rate": 1.4097180000000001e-05,
"loss": 2.9905,
"step": 4
},
{
"epoch": 0.01,
"learning_rate": 1.4096475000000001e-05,
"loss": 2.9882,
"step": 5
},
{
"epoch": 0.02,
"learning_rate": 1.4095770000000001e-05,
"loss": 2.9911,
"step": 6
},
{
"epoch": 0.02,
"learning_rate": 1.4095065000000001e-05,
"loss": 2.9913,
"step": 7
},
{
"epoch": 0.02,
"learning_rate": 1.409436e-05,
"loss": 2.9884,
"step": 8
},
{
"epoch": 0.03,
"learning_rate": 1.4093655e-05,
"loss": 2.9906,
"step": 9
},
{
"epoch": 0.03,
"learning_rate": 1.4092950000000002e-05,
"loss": 2.9887,
"step": 10
},
{
"epoch": 0.03,
"learning_rate": 1.4092245e-05,
"loss": 2.9838,
"step": 11
},
{
"epoch": 0.04,
"learning_rate": 1.409154e-05,
"loss": 2.9889,
"step": 12
},
{
"epoch": 0.04,
"learning_rate": 1.4090835e-05,
"loss": 2.9816,
"step": 13
},
{
"epoch": 0.04,
"learning_rate": 1.409013e-05,
"loss": 2.9825,
"step": 14
},
{
"epoch": 0.04,
"learning_rate": 1.4089425e-05,
"loss": 2.9799,
"step": 15
},
{
"epoch": 0.05,
"learning_rate": 1.4088720000000001e-05,
"loss": 2.9763,
"step": 16
},
{
"epoch": 0.05,
"learning_rate": 1.4088015e-05,
"loss": 2.9825,
"step": 17
},
{
"epoch": 0.05,
"learning_rate": 1.408731e-05,
"loss": 2.9803,
"step": 18
},
{
"epoch": 0.06,
"learning_rate": 1.4086605e-05,
"loss": 2.98,
"step": 19
},
{
"epoch": 0.06,
"learning_rate": 1.40859e-05,
"loss": 2.9783,
"step": 20
},
{
"epoch": 0.06,
"learning_rate": 1.4085195e-05,
"loss": 2.9698,
"step": 21
},
{
"epoch": 0.07,
"learning_rate": 1.4084490000000001e-05,
"loss": 2.9732,
"step": 22
},
{
"epoch": 0.07,
"learning_rate": 1.4083785000000001e-05,
"loss": 2.9712,
"step": 23
},
{
"epoch": 0.07,
"learning_rate": 1.4083080000000001e-05,
"loss": 2.9768,
"step": 24
},
{
"epoch": 0.07,
"learning_rate": 1.4082375e-05,
"loss": 2.9704,
"step": 25
},
{
"epoch": 0.08,
"learning_rate": 1.408167e-05,
"loss": 2.9719,
"step": 26
},
{
"epoch": 0.08,
"learning_rate": 1.4080965e-05,
"loss": 2.9634,
"step": 27
},
{
"epoch": 0.08,
"learning_rate": 1.4080260000000002e-05,
"loss": 2.9662,
"step": 28
},
{
"epoch": 0.09,
"learning_rate": 1.4079555000000002e-05,
"loss": 2.9724,
"step": 29
},
{
"epoch": 0.09,
"learning_rate": 1.4078850000000002e-05,
"loss": 2.9685,
"step": 30
},
{
"epoch": 0.09,
"learning_rate": 1.4078145e-05,
"loss": 2.9624,
"step": 31
},
{
"epoch": 0.1,
"learning_rate": 1.407744e-05,
"loss": 2.9631,
"step": 32
},
{
"epoch": 0.1,
"learning_rate": 1.4076735e-05,
"loss": 2.9631,
"step": 33
},
{
"epoch": 0.1,
"learning_rate": 1.407603e-05,
"loss": 2.9575,
"step": 34
},
{
"epoch": 0.1,
"learning_rate": 1.4075325e-05,
"loss": 2.9589,
"step": 35
},
{
"epoch": 0.11,
"learning_rate": 1.407462e-05,
"loss": 2.9564,
"step": 36
},
{
"epoch": 0.11,
"learning_rate": 1.4073915e-05,
"loss": 2.9577,
"step": 37
},
{
"epoch": 0.11,
"learning_rate": 1.407321e-05,
"loss": 2.9524,
"step": 38
},
{
"epoch": 0.12,
"learning_rate": 1.4072505e-05,
"loss": 2.9536,
"step": 39
},
{
"epoch": 0.12,
"learning_rate": 1.40718e-05,
"loss": 2.9589,
"step": 40
},
{
"epoch": 0.12,
"learning_rate": 1.4071095000000001e-05,
"loss": 2.9515,
"step": 41
},
{
"epoch": 0.13,
"learning_rate": 1.4070390000000001e-05,
"loss": 2.9536,
"step": 42
},
{
"epoch": 0.13,
"learning_rate": 1.4069685e-05,
"loss": 2.9487,
"step": 43
},
{
"epoch": 0.13,
"learning_rate": 1.406898e-05,
"loss": 2.9465,
"step": 44
},
{
"epoch": 0.13,
"learning_rate": 1.4068275e-05,
"loss": 2.9504,
"step": 45
},
{
"epoch": 0.14,
"learning_rate": 1.406757e-05,
"loss": 2.9486,
"step": 46
},
{
"epoch": 0.14,
"learning_rate": 1.4066865000000002e-05,
"loss": 2.9473,
"step": 47
},
{
"epoch": 0.14,
"learning_rate": 1.4066160000000002e-05,
"loss": 2.9399,
"step": 48
},
{
"epoch": 0.15,
"learning_rate": 1.4065455000000001e-05,
"loss": 2.9475,
"step": 49
},
{
"epoch": 0.15,
"learning_rate": 1.4064750000000001e-05,
"loss": 2.9454,
"step": 50
},
{
"epoch": 0.15,
"learning_rate": 1.4064045e-05,
"loss": 2.9381,
"step": 51
},
{
"epoch": 0.16,
"learning_rate": 1.4063339999999999e-05,
"loss": 2.94,
"step": 52
},
{
"epoch": 0.16,
"learning_rate": 1.4062635e-05,
"loss": 2.9374,
"step": 53
},
{
"epoch": 0.16,
"learning_rate": 1.406193e-05,
"loss": 2.9369,
"step": 54
},
{
"epoch": 0.16,
"learning_rate": 1.4061225e-05,
"loss": 2.9316,
"step": 55
},
{
"epoch": 0.17,
"learning_rate": 1.406052e-05,
"loss": 2.9324,
"step": 56
},
{
"epoch": 0.17,
"learning_rate": 1.4059815e-05,
"loss": 2.9289,
"step": 57
},
{
"epoch": 0.17,
"learning_rate": 1.405911e-05,
"loss": 2.9286,
"step": 58
},
{
"epoch": 0.18,
"learning_rate": 1.4058405000000001e-05,
"loss": 2.9304,
"step": 59
},
{
"epoch": 0.18,
"learning_rate": 1.4057700000000001e-05,
"loss": 2.9225,
"step": 60
},
{
"epoch": 0.18,
"learning_rate": 1.4056995e-05,
"loss": 2.9263,
"step": 61
},
{
"epoch": 0.19,
"learning_rate": 1.405629e-05,
"loss": 2.9235,
"step": 62
},
{
"epoch": 0.19,
"learning_rate": 1.4055585e-05,
"loss": 2.9271,
"step": 63
},
{
"epoch": 0.19,
"learning_rate": 1.405488e-05,
"loss": 2.9214,
"step": 64
},
{
"epoch": 0.19,
"learning_rate": 1.4054175000000002e-05,
"loss": 2.9175,
"step": 65
},
{
"epoch": 0.2,
"learning_rate": 1.4053470000000001e-05,
"loss": 2.912,
"step": 66
},
{
"epoch": 0.2,
"learning_rate": 1.4052765000000001e-05,
"loss": 2.9184,
"step": 67
},
{
"epoch": 0.2,
"learning_rate": 1.4052060000000001e-05,
"loss": 2.918,
"step": 68
},
{
"epoch": 0.21,
"learning_rate": 1.4051355000000001e-05,
"loss": 2.9141,
"step": 69
},
{
"epoch": 0.21,
"learning_rate": 1.405065e-05,
"loss": 2.9137,
"step": 70
},
{
"epoch": 0.21,
"learning_rate": 1.4049945e-05,
"loss": 2.9099,
"step": 71
},
{
"epoch": 0.22,
"learning_rate": 1.404924e-05,
"loss": 2.9079,
"step": 72
},
{
"epoch": 0.22,
"learning_rate": 1.4048535e-05,
"loss": 2.9094,
"step": 73
},
{
"epoch": 0.22,
"learning_rate": 1.404783e-05,
"loss": 2.9001,
"step": 74
},
{
"epoch": 0.22,
"learning_rate": 1.4047125e-05,
"loss": 2.8997,
"step": 75
},
{
"epoch": 0.23,
"learning_rate": 1.404642e-05,
"loss": 2.8978,
"step": 76
},
{
"epoch": 0.23,
"learning_rate": 1.4045715e-05,
"loss": 2.9003,
"step": 77
},
{
"epoch": 0.23,
"learning_rate": 1.4045010000000001e-05,
"loss": 2.9061,
"step": 78
},
{
"epoch": 0.24,
"learning_rate": 1.4044305e-05,
"loss": 2.8936,
"step": 79
},
{
"epoch": 0.24,
"learning_rate": 1.40436e-05,
"loss": 2.902,
"step": 80
},
{
"epoch": 0.24,
"learning_rate": 1.4042895e-05,
"loss": 2.8964,
"step": 81
},
{
"epoch": 0.25,
"learning_rate": 1.404219e-05,
"loss": 2.8943,
"step": 82
},
{
"epoch": 0.25,
"learning_rate": 1.4041485e-05,
"loss": 2.8908,
"step": 83
},
{
"epoch": 0.25,
"learning_rate": 1.4040780000000001e-05,
"loss": 2.8891,
"step": 84
},
{
"epoch": 0.25,
"learning_rate": 1.4040075000000001e-05,
"loss": 2.8876,
"step": 85
},
{
"epoch": 0.26,
"learning_rate": 1.4039370000000001e-05,
"loss": 2.8885,
"step": 86
},
{
"epoch": 0.26,
"learning_rate": 1.4038665000000001e-05,
"loss": 2.8841,
"step": 87
},
{
"epoch": 0.26,
"learning_rate": 1.403796e-05,
"loss": 2.8817,
"step": 88
},
{
"epoch": 0.27,
"learning_rate": 1.4037255e-05,
"loss": 2.8828,
"step": 89
},
{
"epoch": 0.27,
"learning_rate": 1.4036550000000002e-05,
"loss": 2.8797,
"step": 90
},
{
"epoch": 0.27,
"learning_rate": 1.4035845e-05,
"loss": 2.8805,
"step": 91
},
{
"epoch": 0.28,
"learning_rate": 1.403514e-05,
"loss": 2.8751,
"step": 92
},
{
"epoch": 0.28,
"learning_rate": 1.4034435e-05,
"loss": 2.8732,
"step": 93
},
{
"epoch": 0.28,
"learning_rate": 1.403373e-05,
"loss": 2.8771,
"step": 94
},
{
"epoch": 0.28,
"learning_rate": 1.4033025e-05,
"loss": 2.8727,
"step": 95
},
{
"epoch": 0.29,
"learning_rate": 1.4032320000000001e-05,
"loss": 2.869,
"step": 96
},
{
"epoch": 0.29,
"learning_rate": 1.4031615e-05,
"loss": 2.8728,
"step": 97
},
{
"epoch": 0.29,
"learning_rate": 1.403091e-05,
"loss": 2.8638,
"step": 98
},
{
"epoch": 0.3,
"learning_rate": 1.4030205e-05,
"loss": 2.8644,
"step": 99
},
{
"epoch": 0.3,
"learning_rate": 1.40295e-05,
"loss": 2.8539,
"step": 100
},
{
"epoch": 0.3,
"eval_accuracy": 0.005741401006711409,
"eval_loss": 2.497692584991455,
"eval_runtime": 33.8362,
"eval_samples_per_second": 8.807,
"eval_steps_per_second": 0.562,
"step": 100
},
{
"epoch": 0.3,
"learning_rate": 1.4028795e-05,
"loss": 2.861,
"step": 101
},
{
"epoch": 0.31,
"learning_rate": 1.4028090000000001e-05,
"loss": 2.8592,
"step": 102
},
{
"epoch": 0.31,
"learning_rate": 1.4027385000000001e-05,
"loss": 2.8544,
"step": 103
},
{
"epoch": 0.31,
"learning_rate": 1.4026680000000001e-05,
"loss": 2.8535,
"step": 104
},
{
"epoch": 0.31,
"learning_rate": 1.4025975e-05,
"loss": 2.8537,
"step": 105
},
{
"epoch": 0.32,
"learning_rate": 1.402527e-05,
"loss": 2.856,
"step": 106
},
{
"epoch": 0.32,
"learning_rate": 1.4024565e-05,
"loss": 2.8547,
"step": 107
},
{
"epoch": 0.32,
"learning_rate": 1.402386e-05,
"loss": 2.851,
"step": 108
},
{
"epoch": 0.33,
"learning_rate": 1.4023155000000002e-05,
"loss": 2.8472,
"step": 109
},
{
"epoch": 0.33,
"learning_rate": 1.4022450000000002e-05,
"loss": 2.8439,
"step": 110
},
{
"epoch": 0.33,
"learning_rate": 1.4021745e-05,
"loss": 2.8429,
"step": 111
},
{
"epoch": 0.34,
"learning_rate": 1.402104e-05,
"loss": 2.8413,
"step": 112
},
{
"epoch": 0.34,
"learning_rate": 1.4020335e-05,
"loss": 2.8379,
"step": 113
},
{
"epoch": 0.34,
"learning_rate": 1.401963e-05,
"loss": 2.8411,
"step": 114
},
{
"epoch": 0.34,
"learning_rate": 1.4018925e-05,
"loss": 2.8384,
"step": 115
},
{
"epoch": 0.35,
"learning_rate": 1.401822e-05,
"loss": 2.8394,
"step": 116
},
{
"epoch": 0.35,
"learning_rate": 1.4017515e-05,
"loss": 2.8364,
"step": 117
},
{
"epoch": 0.35,
"learning_rate": 1.401681e-05,
"loss": 2.833,
"step": 118
},
{
"epoch": 0.36,
"learning_rate": 1.4016105e-05,
"loss": 2.8341,
"step": 119
},
{
"epoch": 0.36,
"learning_rate": 1.40154e-05,
"loss": 2.8285,
"step": 120
},
{
"epoch": 0.36,
"learning_rate": 1.4014695000000001e-05,
"loss": 2.8294,
"step": 121
},
{
"epoch": 0.37,
"learning_rate": 1.4013990000000001e-05,
"loss": 2.8247,
"step": 122
},
{
"epoch": 0.37,
"learning_rate": 1.4013285e-05,
"loss": 2.8241,
"step": 123
},
{
"epoch": 0.37,
"learning_rate": 1.401258e-05,
"loss": 2.8216,
"step": 124
},
{
"epoch": 0.37,
"learning_rate": 1.4011875e-05,
"loss": 2.8221,
"step": 125
},
{
"epoch": 0.38,
"learning_rate": 1.401117e-05,
"loss": 2.8218,
"step": 126
},
{
"epoch": 0.38,
"learning_rate": 1.4010465000000002e-05,
"loss": 2.8186,
"step": 127
},
{
"epoch": 0.38,
"learning_rate": 1.4009760000000002e-05,
"loss": 2.818,
"step": 128
},
{
"epoch": 0.39,
"learning_rate": 1.4009055000000001e-05,
"loss": 2.8136,
"step": 129
},
{
"epoch": 0.39,
"learning_rate": 1.4008350000000001e-05,
"loss": 2.8108,
"step": 130
},
{
"epoch": 0.39,
"learning_rate": 1.4007645000000001e-05,
"loss": 2.8121,
"step": 131
},
{
"epoch": 0.4,
"learning_rate": 1.4006939999999999e-05,
"loss": 2.8087,
"step": 132
},
{
"epoch": 0.4,
"learning_rate": 1.4006235e-05,
"loss": 2.8062,
"step": 133
},
{
"epoch": 0.4,
"learning_rate": 1.400553e-05,
"loss": 2.8097,
"step": 134
},
{
"epoch": 0.4,
"learning_rate": 1.4004825e-05,
"loss": 2.8043,
"step": 135
},
{
"epoch": 0.41,
"learning_rate": 1.400412e-05,
"loss": 2.8016,
"step": 136
},
{
"epoch": 0.41,
"learning_rate": 1.4003415e-05,
"loss": 2.8073,
"step": 137
},
{
"epoch": 0.41,
"learning_rate": 1.400271e-05,
"loss": 2.8062,
"step": 138
},
{
"epoch": 0.42,
"learning_rate": 1.4002005000000001e-05,
"loss": 2.7996,
"step": 139
},
{
"epoch": 0.42,
"learning_rate": 1.4001300000000001e-05,
"loss": 2.7946,
"step": 140
},
{
"epoch": 0.42,
"learning_rate": 1.4000595e-05,
"loss": 2.7949,
"step": 141
},
{
"epoch": 0.43,
"learning_rate": 1.399989e-05,
"loss": 2.7956,
"step": 142
},
{
"epoch": 0.43,
"learning_rate": 1.3999185e-05,
"loss": 2.7988,
"step": 143
},
{
"epoch": 0.43,
"learning_rate": 1.399848e-05,
"loss": 2.7909,
"step": 144
},
{
"epoch": 0.43,
"learning_rate": 1.3997775e-05,
"loss": 2.7933,
"step": 145
},
{
"epoch": 0.44,
"learning_rate": 1.3997070000000001e-05,
"loss": 2.7907,
"step": 146
},
{
"epoch": 0.44,
"learning_rate": 1.3996365000000001e-05,
"loss": 2.7888,
"step": 147
},
{
"epoch": 0.44,
"learning_rate": 1.3995660000000001e-05,
"loss": 2.7852,
"step": 148
},
{
"epoch": 0.45,
"learning_rate": 1.3994955000000001e-05,
"loss": 2.7824,
"step": 149
},
{
"epoch": 0.45,
"learning_rate": 1.399425e-05,
"loss": 2.7808,
"step": 150
},
{
"epoch": 0.45,
"learning_rate": 1.3993545e-05,
"loss": 2.7792,
"step": 151
},
{
"epoch": 0.46,
"learning_rate": 1.399284e-05,
"loss": 2.7799,
"step": 152
},
{
"epoch": 0.46,
"learning_rate": 1.3992135e-05,
"loss": 2.7773,
"step": 153
},
{
"epoch": 0.46,
"learning_rate": 1.399143e-05,
"loss": 2.7791,
"step": 154
},
{
"epoch": 0.46,
"learning_rate": 1.3990725e-05,
"loss": 2.7739,
"step": 155
},
{
"epoch": 0.47,
"learning_rate": 1.399002e-05,
"loss": 2.7666,
"step": 156
},
{
"epoch": 0.47,
"learning_rate": 1.3989315e-05,
"loss": 2.771,
"step": 157
},
{
"epoch": 0.47,
"learning_rate": 1.3988610000000001e-05,
"loss": 2.772,
"step": 158
},
{
"epoch": 0.48,
"learning_rate": 1.3987905e-05,
"loss": 2.7718,
"step": 159
},
{
"epoch": 0.48,
"learning_rate": 1.39872e-05,
"loss": 2.7697,
"step": 160
},
{
"epoch": 0.48,
"learning_rate": 1.3986495e-05,
"loss": 2.7691,
"step": 161
},
{
"epoch": 0.49,
"learning_rate": 1.398579e-05,
"loss": 2.7621,
"step": 162
},
{
"epoch": 0.49,
"learning_rate": 1.3985085e-05,
"loss": 2.7653,
"step": 163
},
{
"epoch": 0.49,
"learning_rate": 1.3984380000000001e-05,
"loss": 2.7639,
"step": 164
},
{
"epoch": 0.49,
"learning_rate": 1.3983675000000001e-05,
"loss": 2.7634,
"step": 165
},
{
"epoch": 0.5,
"learning_rate": 1.3982970000000001e-05,
"loss": 2.7599,
"step": 166
},
{
"epoch": 0.5,
"learning_rate": 1.3982265000000001e-05,
"loss": 2.757,
"step": 167
},
{
"epoch": 0.5,
"learning_rate": 1.398156e-05,
"loss": 2.756,
"step": 168
},
{
"epoch": 0.51,
"learning_rate": 1.3980855e-05,
"loss": 2.7508,
"step": 169
},
{
"epoch": 0.51,
"learning_rate": 1.3980150000000002e-05,
"loss": 2.7562,
"step": 170
},
{
"epoch": 0.51,
"learning_rate": 1.3979445000000002e-05,
"loss": 2.7515,
"step": 171
},
{
"epoch": 0.52,
"learning_rate": 1.397874e-05,
"loss": 2.7461,
"step": 172
},
{
"epoch": 0.52,
"learning_rate": 1.3978035e-05,
"loss": 2.7455,
"step": 173
},
{
"epoch": 0.52,
"learning_rate": 1.397733e-05,
"loss": 2.7471,
"step": 174
},
{
"epoch": 0.52,
"learning_rate": 1.3976625e-05,
"loss": 2.7457,
"step": 175
},
{
"epoch": 0.53,
"learning_rate": 1.3975920000000001e-05,
"loss": 2.7475,
"step": 176
},
{
"epoch": 0.53,
"learning_rate": 1.3975215e-05,
"loss": 2.7453,
"step": 177
},
{
"epoch": 0.53,
"learning_rate": 1.397451e-05,
"loss": 2.7447,
"step": 178
},
{
"epoch": 0.54,
"learning_rate": 1.3973805e-05,
"loss": 2.7409,
"step": 179
},
{
"epoch": 0.54,
"learning_rate": 1.39731e-05,
"loss": 2.7407,
"step": 180
},
{
"epoch": 0.54,
"learning_rate": 1.3972395e-05,
"loss": 2.7398,
"step": 181
},
{
"epoch": 0.55,
"learning_rate": 1.3971690000000001e-05,
"loss": 2.7378,
"step": 182
},
{
"epoch": 0.55,
"learning_rate": 1.3970985000000001e-05,
"loss": 2.7294,
"step": 183
},
{
"epoch": 0.55,
"learning_rate": 1.3970280000000001e-05,
"loss": 2.735,
"step": 184
},
{
"epoch": 0.55,
"learning_rate": 1.3969575e-05,
"loss": 2.7334,
"step": 185
},
{
"epoch": 0.56,
"learning_rate": 1.396887e-05,
"loss": 2.7327,
"step": 186
},
{
"epoch": 0.56,
"learning_rate": 1.3968165e-05,
"loss": 2.7246,
"step": 187
},
{
"epoch": 0.56,
"learning_rate": 1.396746e-05,
"loss": 2.7224,
"step": 188
},
{
"epoch": 0.57,
"learning_rate": 1.3966755000000002e-05,
"loss": 2.7281,
"step": 189
},
{
"epoch": 0.57,
"learning_rate": 1.3966050000000002e-05,
"loss": 2.7271,
"step": 190
},
{
"epoch": 0.57,
"learning_rate": 1.3965345000000001e-05,
"loss": 2.724,
"step": 191
},
{
"epoch": 0.57,
"learning_rate": 1.396464e-05,
"loss": 2.7223,
"step": 192
},
{
"epoch": 0.58,
"learning_rate": 1.3963935e-05,
"loss": 2.7201,
"step": 193
},
{
"epoch": 0.58,
"learning_rate": 1.3963229999999999e-05,
"loss": 2.7232,
"step": 194
},
{
"epoch": 0.58,
"learning_rate": 1.3962525e-05,
"loss": 2.7128,
"step": 195
},
{
"epoch": 0.59,
"learning_rate": 1.396182e-05,
"loss": 2.7158,
"step": 196
},
{
"epoch": 0.59,
"learning_rate": 1.3961115e-05,
"loss": 2.7163,
"step": 197
},
{
"epoch": 0.59,
"learning_rate": 1.396041e-05,
"loss": 2.714,
"step": 198
},
{
"epoch": 0.6,
"learning_rate": 1.3959705e-05,
"loss": 2.7111,
"step": 199
},
{
"epoch": 0.6,
"learning_rate": 1.3959e-05,
"loss": 2.7052,
"step": 200
},
{
"epoch": 0.6,
"eval_accuracy": 0.0041946308724832215,
"eval_loss": 2.438399076461792,
"eval_runtime": 33.6582,
"eval_samples_per_second": 8.854,
"eval_steps_per_second": 0.564,
"step": 200
},
{
"epoch": 0.6,
"learning_rate": 1.3958295000000001e-05,
"loss": 2.7084,
"step": 201
},
{
"epoch": 0.6,
"learning_rate": 1.3957590000000001e-05,
"loss": 2.7077,
"step": 202
},
{
"epoch": 0.61,
"learning_rate": 1.3956885e-05,
"loss": 2.7064,
"step": 203
},
{
"epoch": 0.61,
"learning_rate": 1.395618e-05,
"loss": 2.71,
"step": 204
},
{
"epoch": 0.61,
"learning_rate": 1.3955475e-05,
"loss": 2.708,
"step": 205
},
{
"epoch": 0.62,
"learning_rate": 1.395477e-05,
"loss": 2.7074,
"step": 206
},
{
"epoch": 0.62,
"learning_rate": 1.3954065000000002e-05,
"loss": 2.7065,
"step": 207
},
{
"epoch": 0.62,
"learning_rate": 1.3953360000000002e-05,
"loss": 2.6985,
"step": 208
},
{
"epoch": 0.63,
"learning_rate": 1.3952655000000001e-05,
"loss": 2.7002,
"step": 209
},
{
"epoch": 0.63,
"learning_rate": 1.3951950000000001e-05,
"loss": 2.6963,
"step": 210
},
{
"epoch": 0.63,
"learning_rate": 1.3951245000000001e-05,
"loss": 2.6959,
"step": 211
},
{
"epoch": 0.63,
"learning_rate": 1.3950539999999999e-05,
"loss": 2.6946,
"step": 212
},
{
"epoch": 0.64,
"learning_rate": 1.3949835e-05,
"loss": 2.6932,
"step": 213
},
{
"epoch": 0.64,
"learning_rate": 1.394913e-05,
"loss": 2.692,
"step": 214
},
{
"epoch": 0.64,
"learning_rate": 1.3948425e-05,
"loss": 2.6987,
"step": 215
},
{
"epoch": 0.65,
"learning_rate": 1.394772e-05,
"loss": 2.6903,
"step": 216
},
{
"epoch": 0.65,
"learning_rate": 1.3947015e-05,
"loss": 2.6875,
"step": 217
},
{
"epoch": 0.65,
"learning_rate": 1.394631e-05,
"loss": 2.6885,
"step": 218
},
{
"epoch": 0.66,
"learning_rate": 1.3945605000000001e-05,
"loss": 2.6877,
"step": 219
},
{
"epoch": 0.66,
"learning_rate": 1.3944900000000001e-05,
"loss": 2.6872,
"step": 220
},
{
"epoch": 0.66,
"learning_rate": 1.3944195e-05,
"loss": 2.6775,
"step": 221
},
{
"epoch": 0.66,
"learning_rate": 1.394349e-05,
"loss": 2.6808,
"step": 222
},
{
"epoch": 0.67,
"learning_rate": 1.3942785e-05,
"loss": 2.6791,
"step": 223
},
{
"epoch": 0.67,
"learning_rate": 1.394208e-05,
"loss": 2.6763,
"step": 224
},
{
"epoch": 0.67,
"learning_rate": 1.3941375e-05,
"loss": 2.6835,
"step": 225
},
{
"epoch": 0.68,
"learning_rate": 1.3940670000000001e-05,
"loss": 2.6773,
"step": 226
},
{
"epoch": 0.68,
"learning_rate": 1.3939965000000001e-05,
"loss": 2.6764,
"step": 227
},
{
"epoch": 0.68,
"learning_rate": 1.3939260000000001e-05,
"loss": 2.678,
"step": 228
},
{
"epoch": 0.69,
"learning_rate": 1.3938555000000001e-05,
"loss": 2.6695,
"step": 229
},
{
"epoch": 0.69,
"learning_rate": 1.393785e-05,
"loss": 2.6749,
"step": 230
},
{
"epoch": 0.69,
"learning_rate": 1.3937145e-05,
"loss": 2.6742,
"step": 231
},
{
"epoch": 0.69,
"learning_rate": 1.393644e-05,
"loss": 2.6649,
"step": 232
},
{
"epoch": 0.7,
"learning_rate": 1.3935735e-05,
"loss": 2.6663,
"step": 233
},
{
"epoch": 0.7,
"learning_rate": 1.393503e-05,
"loss": 2.6681,
"step": 234
},
{
"epoch": 0.7,
"learning_rate": 1.3934325e-05,
"loss": 2.6664,
"step": 235
},
{
"epoch": 0.71,
"learning_rate": 1.393362e-05,
"loss": 2.6668,
"step": 236
},
{
"epoch": 0.71,
"learning_rate": 1.3932915e-05,
"loss": 2.6658,
"step": 237
},
{
"epoch": 0.71,
"learning_rate": 1.3932210000000001e-05,
"loss": 2.6668,
"step": 238
},
{
"epoch": 0.72,
"learning_rate": 1.3931505e-05,
"loss": 2.6586,
"step": 239
},
{
"epoch": 0.72,
"learning_rate": 1.39308e-05,
"loss": 2.6622,
"step": 240
},
{
"epoch": 0.72,
"learning_rate": 1.3930095e-05,
"loss": 2.6635,
"step": 241
},
{
"epoch": 0.72,
"learning_rate": 1.392939e-05,
"loss": 2.6574,
"step": 242
},
{
"epoch": 0.73,
"learning_rate": 1.3928685e-05,
"loss": 2.6593,
"step": 243
},
{
"epoch": 0.73,
"learning_rate": 1.3927980000000001e-05,
"loss": 2.6537,
"step": 244
},
{
"epoch": 0.73,
"learning_rate": 1.3927275000000001e-05,
"loss": 2.6582,
"step": 245
},
{
"epoch": 0.74,
"learning_rate": 1.3926570000000001e-05,
"loss": 2.6518,
"step": 246
},
{
"epoch": 0.74,
"learning_rate": 1.3925865000000001e-05,
"loss": 2.6522,
"step": 247
},
{
"epoch": 0.74,
"learning_rate": 1.392516e-05,
"loss": 2.6522,
"step": 248
},
{
"epoch": 0.75,
"learning_rate": 1.3924455e-05,
"loss": 2.6469,
"step": 249
},
{
"epoch": 0.75,
"learning_rate": 1.392375e-05,
"loss": 2.6493,
"step": 250
},
{
"epoch": 0.75,
"learning_rate": 1.3923045000000002e-05,
"loss": 2.6504,
"step": 251
},
{
"epoch": 0.75,
"learning_rate": 1.3922340000000002e-05,
"loss": 2.6447,
"step": 252
},
{
"epoch": 0.76,
"learning_rate": 1.3921635e-05,
"loss": 2.6502,
"step": 253
},
{
"epoch": 0.76,
"learning_rate": 1.392093e-05,
"loss": 2.6415,
"step": 254
},
{
"epoch": 0.76,
"learning_rate": 1.3920225e-05,
"loss": 2.6425,
"step": 255
},
{
"epoch": 0.77,
"learning_rate": 1.3919520000000001e-05,
"loss": 2.6479,
"step": 256
},
{
"epoch": 0.77,
"learning_rate": 1.3918815e-05,
"loss": 2.6414,
"step": 257
},
{
"epoch": 0.77,
"learning_rate": 1.391811e-05,
"loss": 2.6387,
"step": 258
},
{
"epoch": 0.78,
"learning_rate": 1.3917405e-05,
"loss": 2.6374,
"step": 259
},
{
"epoch": 0.78,
"learning_rate": 1.39167e-05,
"loss": 2.6378,
"step": 260
},
{
"epoch": 0.78,
"learning_rate": 1.3915995e-05,
"loss": 2.6386,
"step": 261
},
{
"epoch": 0.78,
"learning_rate": 1.391529e-05,
"loss": 2.6332,
"step": 262
},
{
"epoch": 0.79,
"learning_rate": 1.3914585000000001e-05,
"loss": 2.6363,
"step": 263
},
{
"epoch": 0.79,
"learning_rate": 1.3913880000000001e-05,
"loss": 2.6347,
"step": 264
},
{
"epoch": 0.79,
"learning_rate": 1.3913175e-05,
"loss": 2.6322,
"step": 265
},
{
"epoch": 0.8,
"learning_rate": 1.391247e-05,
"loss": 2.6372,
"step": 266
},
{
"epoch": 0.8,
"learning_rate": 1.3911765e-05,
"loss": 2.6285,
"step": 267
},
{
"epoch": 0.8,
"learning_rate": 1.391106e-05,
"loss": 2.6306,
"step": 268
},
{
"epoch": 0.81,
"learning_rate": 1.3910355000000002e-05,
"loss": 2.6252,
"step": 269
},
{
"epoch": 0.81,
"learning_rate": 1.3909650000000002e-05,
"loss": 2.6298,
"step": 270
},
{
"epoch": 0.81,
"learning_rate": 1.3908945000000001e-05,
"loss": 2.6225,
"step": 271
},
{
"epoch": 0.81,
"learning_rate": 1.3908240000000001e-05,
"loss": 2.6257,
"step": 272
},
{
"epoch": 0.82,
"learning_rate": 1.3907535e-05,
"loss": 2.6219,
"step": 273
},
{
"epoch": 0.82,
"learning_rate": 1.3906829999999999e-05,
"loss": 2.622,
"step": 274
},
{
"epoch": 0.82,
"learning_rate": 1.3906125e-05,
"loss": 2.623,
"step": 275
},
{
"epoch": 0.83,
"learning_rate": 1.390542e-05,
"loss": 2.6237,
"step": 276
},
{
"epoch": 0.83,
"learning_rate": 1.3904715e-05,
"loss": 2.6161,
"step": 277
},
{
"epoch": 0.83,
"learning_rate": 1.390401e-05,
"loss": 2.6131,
"step": 278
},
{
"epoch": 0.84,
"learning_rate": 1.3903305e-05,
"loss": 2.6198,
"step": 279
},
{
"epoch": 0.84,
"learning_rate": 1.39026e-05,
"loss": 2.6129,
"step": 280
},
{
"epoch": 0.84,
"learning_rate": 1.3901895000000001e-05,
"loss": 2.6135,
"step": 281
},
{
"epoch": 0.84,
"learning_rate": 1.3901190000000001e-05,
"loss": 2.6161,
"step": 282
},
{
"epoch": 0.85,
"learning_rate": 1.3900485e-05,
"loss": 2.6112,
"step": 283
},
{
"epoch": 0.85,
"learning_rate": 1.389978e-05,
"loss": 2.6164,
"step": 284
},
{
"epoch": 0.85,
"learning_rate": 1.3899075e-05,
"loss": 2.6104,
"step": 285
},
{
"epoch": 0.86,
"learning_rate": 1.389837e-05,
"loss": 2.609,
"step": 286
},
{
"epoch": 0.86,
"learning_rate": 1.3897665000000002e-05,
"loss": 2.6048,
"step": 287
},
{
"epoch": 0.86,
"learning_rate": 1.3896960000000002e-05,
"loss": 2.6109,
"step": 288
},
{
"epoch": 0.87,
"learning_rate": 1.3896255000000001e-05,
"loss": 2.6075,
"step": 289
},
{
"epoch": 0.87,
"learning_rate": 1.3895550000000001e-05,
"loss": 2.6035,
"step": 290
},
{
"epoch": 0.87,
"learning_rate": 1.3894845000000001e-05,
"loss": 2.604,
"step": 291
},
{
"epoch": 0.87,
"learning_rate": 1.389414e-05,
"loss": 2.6067,
"step": 292
},
{
"epoch": 0.88,
"learning_rate": 1.3893435e-05,
"loss": 2.6034,
"step": 293
},
{
"epoch": 0.88,
"learning_rate": 1.389273e-05,
"loss": 2.5989,
"step": 294
},
{
"epoch": 0.88,
"learning_rate": 1.3892025e-05,
"loss": 2.6005,
"step": 295
},
{
"epoch": 0.89,
"learning_rate": 1.389132e-05,
"loss": 2.5971,
"step": 296
},
{
"epoch": 0.89,
"learning_rate": 1.3890615e-05,
"loss": 2.5977,
"step": 297
},
{
"epoch": 0.89,
"learning_rate": 1.388991e-05,
"loss": 2.5965,
"step": 298
},
{
"epoch": 0.9,
"learning_rate": 1.3889205e-05,
"loss": 2.5983,
"step": 299
},
{
"epoch": 0.9,
"learning_rate": 1.3888500000000001e-05,
"loss": 2.5933,
"step": 300
},
{
"epoch": 0.9,
"eval_accuracy": 0.0034212458053691276,
"eval_loss": 2.371124744415283,
"eval_runtime": 30.2278,
"eval_samples_per_second": 9.858,
"eval_steps_per_second": 0.629,
"step": 300
},
{
"epoch": 0.9,
"learning_rate": 1.3887795e-05,
"loss": 2.5961,
"step": 301
},
{
"epoch": 0.9,
"learning_rate": 1.388709e-05,
"loss": 2.5872,
"step": 302
},
{
"epoch": 0.91,
"learning_rate": 1.3886385e-05,
"loss": 2.592,
"step": 303
},
{
"epoch": 0.91,
"learning_rate": 1.388568e-05,
"loss": 2.5919,
"step": 304
},
{
"epoch": 0.91,
"learning_rate": 1.3884975e-05,
"loss": 2.591,
"step": 305
},
{
"epoch": 0.92,
"learning_rate": 1.3884270000000001e-05,
"loss": 2.5895,
"step": 306
},
{
"epoch": 0.92,
"learning_rate": 1.3883565000000001e-05,
"loss": 2.5905,
"step": 307
},
{
"epoch": 0.92,
"learning_rate": 1.3882860000000001e-05,
"loss": 2.5864,
"step": 308
},
{
"epoch": 0.93,
"learning_rate": 1.3882155000000001e-05,
"loss": 2.5824,
"step": 309
},
{
"epoch": 0.93,
"learning_rate": 1.388145e-05,
"loss": 2.58,
"step": 310
},
{
"epoch": 0.93,
"learning_rate": 1.3880745e-05,
"loss": 2.5861,
"step": 311
},
{
"epoch": 0.93,
"learning_rate": 1.3880040000000002e-05,
"loss": 2.5827,
"step": 312
},
{
"epoch": 0.94,
"learning_rate": 1.3879335e-05,
"loss": 2.5778,
"step": 313
},
{
"epoch": 0.94,
"learning_rate": 1.387863e-05,
"loss": 2.5792,
"step": 314
},
{
"epoch": 0.94,
"learning_rate": 1.3877925e-05,
"loss": 2.5824,
"step": 315
},
{
"epoch": 0.95,
"learning_rate": 1.387722e-05,
"loss": 2.5789,
"step": 316
},
{
"epoch": 0.95,
"learning_rate": 1.3876515e-05,
"loss": 2.5725,
"step": 317
},
{
"epoch": 0.95,
"learning_rate": 1.3875810000000001e-05,
"loss": 2.5796,
"step": 318
},
{
"epoch": 0.96,
"learning_rate": 1.3875105e-05,
"loss": 2.5782,
"step": 319
},
{
"epoch": 0.96,
"learning_rate": 1.38744e-05,
"loss": 2.5741,
"step": 320
},
{
"epoch": 0.96,
"learning_rate": 1.3873695e-05,
"loss": 2.5751,
"step": 321
},
{
"epoch": 0.96,
"learning_rate": 1.387299e-05,
"loss": 2.5727,
"step": 322
},
{
"epoch": 0.97,
"learning_rate": 1.3872285e-05,
"loss": 2.5733,
"step": 323
},
{
"epoch": 0.97,
"learning_rate": 1.3871580000000001e-05,
"loss": 2.5718,
"step": 324
},
{
"epoch": 0.97,
"learning_rate": 1.3870875000000001e-05,
"loss": 2.5659,
"step": 325
},
{
"epoch": 0.98,
"learning_rate": 1.3870170000000001e-05,
"loss": 2.5716,
"step": 326
},
{
"epoch": 0.98,
"learning_rate": 1.3869465000000001e-05,
"loss": 2.5701,
"step": 327
},
{
"epoch": 0.98,
"learning_rate": 1.386876e-05,
"loss": 2.5658,
"step": 328
},
{
"epoch": 0.99,
"learning_rate": 1.3868055e-05,
"loss": 2.5659,
"step": 329
},
{
"epoch": 0.99,
"learning_rate": 1.386735e-05,
"loss": 2.5592,
"step": 330
},
{
"epoch": 0.99,
"learning_rate": 1.3866645000000002e-05,
"loss": 2.5662,
"step": 331
},
{
"epoch": 0.99,
"learning_rate": 1.3865940000000002e-05,
"loss": 2.5658,
"step": 332
},
{
"epoch": 1.0,
"learning_rate": 1.3865235e-05,
"loss": 2.5678,
"step": 333
},
{
"epoch": 1.0,
"learning_rate": 1.386453e-05,
"loss": 2.5623,
"step": 334
},
{
"epoch": 1.0,
"learning_rate": 1.3863825e-05,
"loss": 2.5651,
"step": 335
},
{
"epoch": 1.01,
"learning_rate": 1.386312e-05,
"loss": 2.5635,
"step": 336
},
{
"epoch": 1.01,
"learning_rate": 1.3862415e-05,
"loss": 2.5584,
"step": 337
},
{
"epoch": 1.01,
"learning_rate": 1.386171e-05,
"loss": 2.5575,
"step": 338
},
{
"epoch": 1.02,
"learning_rate": 1.3861005e-05,
"loss": 2.5575,
"step": 339
},
{
"epoch": 1.02,
"learning_rate": 1.38603e-05,
"loss": 2.555,
"step": 340
},
{
"epoch": 1.02,
"learning_rate": 1.3859595e-05,
"loss": 2.5511,
"step": 341
},
{
"epoch": 1.02,
"learning_rate": 1.385889e-05,
"loss": 2.5517,
"step": 342
},
{
"epoch": 1.03,
"learning_rate": 1.3858185000000001e-05,
"loss": 2.5524,
"step": 343
},
{
"epoch": 1.03,
"learning_rate": 1.3857480000000001e-05,
"loss": 2.5545,
"step": 344
},
{
"epoch": 1.03,
"learning_rate": 1.3856775e-05,
"loss": 2.5505,
"step": 345
},
{
"epoch": 1.04,
"learning_rate": 1.385607e-05,
"loss": 2.5541,
"step": 346
},
{
"epoch": 1.04,
"learning_rate": 1.3855365e-05,
"loss": 2.5489,
"step": 347
},
{
"epoch": 1.04,
"learning_rate": 1.385466e-05,
"loss": 2.5481,
"step": 348
},
{
"epoch": 1.05,
"learning_rate": 1.3853955000000002e-05,
"loss": 2.5483,
"step": 349
},
{
"epoch": 1.05,
"learning_rate": 1.3853250000000002e-05,
"loss": 2.5401,
"step": 350
},
{
"epoch": 1.05,
"learning_rate": 1.3852545000000001e-05,
"loss": 2.5394,
"step": 351
},
{
"epoch": 1.05,
"learning_rate": 1.3851840000000001e-05,
"loss": 2.5434,
"step": 352
},
{
"epoch": 1.06,
"learning_rate": 1.3851135e-05,
"loss": 2.5389,
"step": 353
},
{
"epoch": 1.06,
"learning_rate": 1.3850429999999999e-05,
"loss": 2.5456,
"step": 354
},
{
"epoch": 1.06,
"learning_rate": 1.3849725e-05,
"loss": 2.5397,
"step": 355
},
{
"epoch": 1.07,
"learning_rate": 1.384902e-05,
"loss": 2.5402,
"step": 356
},
{
"epoch": 1.07,
"learning_rate": 1.3848315e-05,
"loss": 2.5409,
"step": 357
},
{
"epoch": 1.07,
"learning_rate": 1.384761e-05,
"loss": 2.5368,
"step": 358
},
{
"epoch": 1.08,
"learning_rate": 1.3846905e-05,
"loss": 2.5378,
"step": 359
},
{
"epoch": 1.08,
"learning_rate": 1.38462e-05,
"loss": 2.535,
"step": 360
},
{
"epoch": 1.08,
"learning_rate": 1.3845495000000001e-05,
"loss": 2.5334,
"step": 361
},
{
"epoch": 1.08,
"learning_rate": 1.3844790000000001e-05,
"loss": 2.5367,
"step": 362
},
{
"epoch": 1.09,
"learning_rate": 1.3844085e-05,
"loss": 2.5326,
"step": 363
},
{
"epoch": 1.09,
"learning_rate": 1.384338e-05,
"loss": 2.5292,
"step": 364
},
{
"epoch": 1.09,
"learning_rate": 1.3842675e-05,
"loss": 2.5399,
"step": 365
},
{
"epoch": 1.1,
"learning_rate": 1.384197e-05,
"loss": 2.5313,
"step": 366
},
{
"epoch": 1.1,
"learning_rate": 1.3841265e-05,
"loss": 2.5278,
"step": 367
},
{
"epoch": 1.1,
"learning_rate": 1.3840560000000002e-05,
"loss": 2.5322,
"step": 368
},
{
"epoch": 1.1,
"learning_rate": 1.3839855000000001e-05,
"loss": 2.5248,
"step": 369
},
{
"epoch": 1.11,
"learning_rate": 1.3839150000000001e-05,
"loss": 2.5254,
"step": 370
},
{
"epoch": 1.11,
"learning_rate": 1.3838445000000001e-05,
"loss": 2.5256,
"step": 371
},
{
"epoch": 1.11,
"learning_rate": 1.383774e-05,
"loss": 2.5246,
"step": 372
},
{
"epoch": 1.12,
"learning_rate": 1.3837035e-05,
"loss": 2.5232,
"step": 373
},
{
"epoch": 1.12,
"learning_rate": 1.383633e-05,
"loss": 2.5253,
"step": 374
},
{
"epoch": 1.12,
"learning_rate": 1.3835625e-05,
"loss": 2.5248,
"step": 375
},
{
"epoch": 1.13,
"learning_rate": 1.383492e-05,
"loss": 2.5224,
"step": 376
},
{
"epoch": 1.13,
"learning_rate": 1.3834215e-05,
"loss": 2.5225,
"step": 377
},
{
"epoch": 1.13,
"learning_rate": 1.383351e-05,
"loss": 2.5215,
"step": 378
},
{
"epoch": 1.13,
"learning_rate": 1.3832805e-05,
"loss": 2.5163,
"step": 379
},
{
"epoch": 1.14,
"learning_rate": 1.3832100000000001e-05,
"loss": 2.523,
"step": 380
},
{
"epoch": 1.14,
"learning_rate": 1.3831395e-05,
"loss": 2.5188,
"step": 381
},
{
"epoch": 1.14,
"learning_rate": 1.383069e-05,
"loss": 2.5183,
"step": 382
},
{
"epoch": 1.15,
"learning_rate": 1.3829985e-05,
"loss": 2.5164,
"step": 383
},
{
"epoch": 1.15,
"learning_rate": 1.382928e-05,
"loss": 2.5157,
"step": 384
},
{
"epoch": 1.15,
"learning_rate": 1.3828575e-05,
"loss": 2.518,
"step": 385
},
{
"epoch": 1.16,
"learning_rate": 1.3827870000000001e-05,
"loss": 2.5138,
"step": 386
},
{
"epoch": 1.16,
"learning_rate": 1.3827165000000001e-05,
"loss": 2.5122,
"step": 387
},
{
"epoch": 1.16,
"learning_rate": 1.3826460000000001e-05,
"loss": 2.5119,
"step": 388
},
{
"epoch": 1.16,
"learning_rate": 1.3825755000000001e-05,
"loss": 2.5115,
"step": 389
},
{
"epoch": 1.17,
"learning_rate": 1.382505e-05,
"loss": 2.5114,
"step": 390
},
{
"epoch": 1.17,
"learning_rate": 1.3824345e-05,
"loss": 2.5133,
"step": 391
},
{
"epoch": 1.17,
"learning_rate": 1.3823640000000002e-05,
"loss": 2.5062,
"step": 392
},
{
"epoch": 1.18,
"learning_rate": 1.3822935000000002e-05,
"loss": 2.5159,
"step": 393
},
{
"epoch": 1.18,
"learning_rate": 1.382223e-05,
"loss": 2.5064,
"step": 394
},
{
"epoch": 1.18,
"learning_rate": 1.3821525e-05,
"loss": 2.5111,
"step": 395
},
{
"epoch": 1.19,
"learning_rate": 1.382082e-05,
"loss": 2.5065,
"step": 396
},
{
"epoch": 1.19,
"learning_rate": 1.3820115e-05,
"loss": 2.5108,
"step": 397
},
{
"epoch": 1.19,
"learning_rate": 1.3819410000000001e-05,
"loss": 2.5064,
"step": 398
},
{
"epoch": 1.19,
"learning_rate": 1.3818705e-05,
"loss": 2.505,
"step": 399
},
{
"epoch": 1.2,
"learning_rate": 1.3818e-05,
"loss": 2.5043,
"step": 400
},
{
"epoch": 1.2,
"eval_accuracy": 0.0029886744966442953,
"eval_loss": 2.3105242252349854,
"eval_runtime": 30.6998,
"eval_samples_per_second": 9.707,
"eval_steps_per_second": 0.619,
"step": 400
},
{
"epoch": 1.2,
"learning_rate": 1.3817295e-05,
"loss": 2.5042,
"step": 401
},
{
"epoch": 1.2,
"learning_rate": 1.381659e-05,
"loss": 2.4984,
"step": 402
},
{
"epoch": 1.21,
"learning_rate": 1.3815885e-05,
"loss": 2.4995,
"step": 403
},
{
"epoch": 1.21,
"learning_rate": 1.381518e-05,
"loss": 2.5014,
"step": 404
},
{
"epoch": 1.21,
"learning_rate": 1.3814475000000001e-05,
"loss": 2.4969,
"step": 405
},
{
"epoch": 1.22,
"learning_rate": 1.3813770000000001e-05,
"loss": 2.4967,
"step": 406
},
{
"epoch": 1.22,
"learning_rate": 1.3813065000000001e-05,
"loss": 2.4999,
"step": 407
},
{
"epoch": 1.22,
"learning_rate": 1.381236e-05,
"loss": 2.4983,
"step": 408
},
{
"epoch": 1.22,
"learning_rate": 1.3811655e-05,
"loss": 2.4972,
"step": 409
},
{
"epoch": 1.23,
"learning_rate": 1.381095e-05,
"loss": 2.4921,
"step": 410
},
{
"epoch": 1.23,
"learning_rate": 1.3810245000000002e-05,
"loss": 2.4968,
"step": 411
},
{
"epoch": 1.23,
"learning_rate": 1.3809540000000002e-05,
"loss": 2.498,
"step": 412
},
{
"epoch": 1.24,
"learning_rate": 1.3808835000000001e-05,
"loss": 2.4945,
"step": 413
},
{
"epoch": 1.24,
"learning_rate": 1.380813e-05,
"loss": 2.4905,
"step": 414
},
{
"epoch": 1.24,
"learning_rate": 1.3807425e-05,
"loss": 2.4935,
"step": 415
},
{
"epoch": 1.25,
"learning_rate": 1.380672e-05,
"loss": 2.4909,
"step": 416
},
{
"epoch": 1.25,
"learning_rate": 1.3806015e-05,
"loss": 2.4922,
"step": 417
},
{
"epoch": 1.25,
"learning_rate": 1.380531e-05,
"loss": 2.4875,
"step": 418
},
{
"epoch": 1.25,
"learning_rate": 1.3804605e-05,
"loss": 2.4925,
"step": 419
},
{
"epoch": 1.26,
"learning_rate": 1.38039e-05,
"loss": 2.486,
"step": 420
},
{
"epoch": 1.26,
"learning_rate": 1.3803195e-05,
"loss": 2.4908,
"step": 421
},
{
"epoch": 1.26,
"learning_rate": 1.380249e-05,
"loss": 2.4869,
"step": 422
},
{
"epoch": 1.27,
"learning_rate": 1.3801785000000001e-05,
"loss": 2.4875,
"step": 423
},
{
"epoch": 1.27,
"learning_rate": 1.3801080000000001e-05,
"loss": 2.4809,
"step": 424
},
{
"epoch": 1.27,
"learning_rate": 1.3800375e-05,
"loss": 2.4857,
"step": 425
},
{
"epoch": 1.28,
"learning_rate": 1.379967e-05,
"loss": 2.4825,
"step": 426
},
{
"epoch": 1.28,
"learning_rate": 1.3798965e-05,
"loss": 2.4839,
"step": 427
},
{
"epoch": 1.28,
"learning_rate": 1.379826e-05,
"loss": 2.4823,
"step": 428
},
{
"epoch": 1.28,
"learning_rate": 1.3797555000000002e-05,
"loss": 2.4817,
"step": 429
},
{
"epoch": 1.29,
"learning_rate": 1.3796850000000002e-05,
"loss": 2.4814,
"step": 430
},
{
"epoch": 1.29,
"learning_rate": 1.3796145000000001e-05,
"loss": 2.4775,
"step": 431
},
{
"epoch": 1.29,
"learning_rate": 1.3795440000000001e-05,
"loss": 2.4767,
"step": 432
},
{
"epoch": 1.3,
"learning_rate": 1.3794735000000001e-05,
"loss": 2.4778,
"step": 433
},
{
"epoch": 1.3,
"learning_rate": 1.3794029999999999e-05,
"loss": 2.4752,
"step": 434
},
{
"epoch": 1.3,
"learning_rate": 1.3793325e-05,
"loss": 2.4787,
"step": 435
},
{
"epoch": 1.31,
"learning_rate": 1.379262e-05,
"loss": 2.4741,
"step": 436
},
{
"epoch": 1.31,
"learning_rate": 1.3791915e-05,
"loss": 2.4754,
"step": 437
},
{
"epoch": 1.31,
"learning_rate": 1.379121e-05,
"loss": 2.4787,
"step": 438
},
{
"epoch": 1.31,
"learning_rate": 1.3790505e-05,
"loss": 2.4718,
"step": 439
},
{
"epoch": 1.32,
"learning_rate": 1.37898e-05,
"loss": 2.4735,
"step": 440
},
{
"epoch": 1.32,
"learning_rate": 1.3789095e-05,
"loss": 2.4748,
"step": 441
},
{
"epoch": 1.32,
"learning_rate": 1.3788390000000001e-05,
"loss": 2.4666,
"step": 442
},
{
"epoch": 1.33,
"learning_rate": 1.3787685e-05,
"loss": 2.4652,
"step": 443
},
{
"epoch": 1.33,
"learning_rate": 1.378698e-05,
"loss": 2.4669,
"step": 444
},
{
"epoch": 1.33,
"learning_rate": 1.3786275e-05,
"loss": 2.4677,
"step": 445
},
{
"epoch": 1.34,
"learning_rate": 1.378557e-05,
"loss": 2.4666,
"step": 446
},
{
"epoch": 1.34,
"learning_rate": 1.3784865e-05,
"loss": 2.469,
"step": 447
},
{
"epoch": 1.34,
"learning_rate": 1.3784160000000002e-05,
"loss": 2.4665,
"step": 448
},
{
"epoch": 1.34,
"learning_rate": 1.3783455000000001e-05,
"loss": 2.463,
"step": 449
},
{
"epoch": 1.35,
"learning_rate": 1.3782750000000001e-05,
"loss": 2.4649,
"step": 450
},
{
"epoch": 1.35,
"learning_rate": 1.3782045000000001e-05,
"loss": 2.4683,
"step": 451
},
{
"epoch": 1.35,
"learning_rate": 1.378134e-05,
"loss": 2.4641,
"step": 452
},
{
"epoch": 1.36,
"learning_rate": 1.3780635e-05,
"loss": 2.4662,
"step": 453
},
{
"epoch": 1.36,
"learning_rate": 1.377993e-05,
"loss": 2.4617,
"step": 454
},
{
"epoch": 1.36,
"learning_rate": 1.3779225e-05,
"loss": 2.4604,
"step": 455
},
{
"epoch": 1.37,
"learning_rate": 1.377852e-05,
"loss": 2.4601,
"step": 456
},
{
"epoch": 1.37,
"learning_rate": 1.3777815e-05,
"loss": 2.4598,
"step": 457
},
{
"epoch": 1.37,
"learning_rate": 1.377711e-05,
"loss": 2.4602,
"step": 458
},
{
"epoch": 1.37,
"learning_rate": 1.3776405e-05,
"loss": 2.4589,
"step": 459
},
{
"epoch": 1.38,
"learning_rate": 1.3775700000000001e-05,
"loss": 2.4582,
"step": 460
},
{
"epoch": 1.38,
"learning_rate": 1.3774995e-05,
"loss": 2.4512,
"step": 461
},
{
"epoch": 1.38,
"learning_rate": 1.377429e-05,
"loss": 2.4536,
"step": 462
},
{
"epoch": 1.39,
"learning_rate": 1.3773585e-05,
"loss": 2.4576,
"step": 463
},
{
"epoch": 1.39,
"learning_rate": 1.377288e-05,
"loss": 2.4529,
"step": 464
},
{
"epoch": 1.39,
"learning_rate": 1.3772175e-05,
"loss": 2.4542,
"step": 465
},
{
"epoch": 1.4,
"learning_rate": 1.3771470000000001e-05,
"loss": 2.4535,
"step": 466
},
{
"epoch": 1.4,
"learning_rate": 1.3770765000000001e-05,
"loss": 2.4486,
"step": 467
},
{
"epoch": 1.4,
"learning_rate": 1.3770060000000001e-05,
"loss": 2.4491,
"step": 468
},
{
"epoch": 1.4,
"learning_rate": 1.3769355000000001e-05,
"loss": 2.4516,
"step": 469
},
{
"epoch": 1.41,
"learning_rate": 1.376865e-05,
"loss": 2.4498,
"step": 470
},
{
"epoch": 1.41,
"learning_rate": 1.3767945e-05,
"loss": 2.4487,
"step": 471
},
{
"epoch": 1.41,
"learning_rate": 1.376724e-05,
"loss": 2.4442,
"step": 472
},
{
"epoch": 1.42,
"learning_rate": 1.3766535000000002e-05,
"loss": 2.4496,
"step": 473
},
{
"epoch": 1.42,
"learning_rate": 1.376583e-05,
"loss": 2.4501,
"step": 474
},
{
"epoch": 1.42,
"learning_rate": 1.3765125e-05,
"loss": 2.4427,
"step": 475
},
{
"epoch": 1.43,
"learning_rate": 1.376442e-05,
"loss": 2.4463,
"step": 476
},
{
"epoch": 1.43,
"learning_rate": 1.3763715e-05,
"loss": 2.4426,
"step": 477
},
{
"epoch": 1.43,
"learning_rate": 1.3763010000000001e-05,
"loss": 2.4411,
"step": 478
},
{
"epoch": 1.43,
"learning_rate": 1.3762305e-05,
"loss": 2.4449,
"step": 479
},
{
"epoch": 1.44,
"learning_rate": 1.37616e-05,
"loss": 2.4428,
"step": 480
},
{
"epoch": 1.44,
"learning_rate": 1.3760895e-05,
"loss": 2.4395,
"step": 481
},
{
"epoch": 1.44,
"learning_rate": 1.376019e-05,
"loss": 2.4441,
"step": 482
},
{
"epoch": 1.45,
"learning_rate": 1.3759485e-05,
"loss": 2.4382,
"step": 483
},
{
"epoch": 1.45,
"learning_rate": 1.375878e-05,
"loss": 2.4403,
"step": 484
},
{
"epoch": 1.45,
"learning_rate": 1.3758075000000001e-05,
"loss": 2.4367,
"step": 485
},
{
"epoch": 1.46,
"learning_rate": 1.3757370000000001e-05,
"loss": 2.437,
"step": 486
},
{
"epoch": 1.46,
"learning_rate": 1.3756665000000001e-05,
"loss": 2.4393,
"step": 487
},
{
"epoch": 1.46,
"learning_rate": 1.375596e-05,
"loss": 2.435,
"step": 488
},
{
"epoch": 1.46,
"learning_rate": 1.3755255e-05,
"loss": 2.4335,
"step": 489
},
{
"epoch": 1.47,
"learning_rate": 1.375455e-05,
"loss": 2.4406,
"step": 490
},
{
"epoch": 1.47,
"learning_rate": 1.3753845000000002e-05,
"loss": 2.4342,
"step": 491
},
{
"epoch": 1.47,
"learning_rate": 1.3753140000000002e-05,
"loss": 2.4382,
"step": 492
},
{
"epoch": 1.48,
"learning_rate": 1.3752435000000001e-05,
"loss": 2.4326,
"step": 493
},
{
"epoch": 1.48,
"learning_rate": 1.375173e-05,
"loss": 2.4345,
"step": 494
},
{
"epoch": 1.48,
"learning_rate": 1.3751025e-05,
"loss": 2.4329,
"step": 495
},
{
"epoch": 1.49,
"learning_rate": 1.375032e-05,
"loss": 2.4311,
"step": 496
},
{
"epoch": 1.49,
"learning_rate": 1.3749615e-05,
"loss": 2.4285,
"step": 497
},
{
"epoch": 1.49,
"learning_rate": 1.374891e-05,
"loss": 2.4318,
"step": 498
},
{
"epoch": 1.49,
"learning_rate": 1.3748205e-05,
"loss": 2.4308,
"step": 499
},
{
"epoch": 1.5,
"learning_rate": 1.37475e-05,
"loss": 2.4304,
"step": 500
},
{
"epoch": 1.5,
"eval_accuracy": 0.0024905620805369126,
"eval_loss": 2.2562174797058105,
"eval_runtime": 29.675,
"eval_samples_per_second": 10.042,
"eval_steps_per_second": 0.64,
"step": 500
},
{
"epoch": 1.5,
"learning_rate": 1.3746795e-05,
"loss": 2.4269,
"step": 501
},
{
"epoch": 1.5,
"learning_rate": 1.374609e-05,
"loss": 2.4234,
"step": 502
},
{
"epoch": 1.51,
"learning_rate": 1.3745385000000001e-05,
"loss": 2.4268,
"step": 503
},
{
"epoch": 1.51,
"learning_rate": 1.3744680000000001e-05,
"loss": 2.427,
"step": 504
},
{
"epoch": 1.51,
"learning_rate": 1.3743975e-05,
"loss": 2.4247,
"step": 505
},
{
"epoch": 1.52,
"learning_rate": 1.374327e-05,
"loss": 2.4236,
"step": 506
},
{
"epoch": 1.52,
"learning_rate": 1.3742565e-05,
"loss": 2.4264,
"step": 507
},
{
"epoch": 1.52,
"learning_rate": 1.374186e-05,
"loss": 2.4248,
"step": 508
},
{
"epoch": 1.52,
"learning_rate": 1.3741155e-05,
"loss": 2.4239,
"step": 509
},
{
"epoch": 1.53,
"learning_rate": 1.3740450000000002e-05,
"loss": 2.4253,
"step": 510
},
{
"epoch": 1.53,
"learning_rate": 1.3739745000000001e-05,
"loss": 2.4205,
"step": 511
},
{
"epoch": 1.53,
"learning_rate": 1.3739040000000001e-05,
"loss": 2.4188,
"step": 512
},
{
"epoch": 1.54,
"learning_rate": 1.3738335000000001e-05,
"loss": 2.4149,
"step": 513
},
{
"epoch": 1.54,
"learning_rate": 1.373763e-05,
"loss": 2.4146,
"step": 514
},
{
"epoch": 1.54,
"learning_rate": 1.3736925e-05,
"loss": 2.414,
"step": 515
},
{
"epoch": 1.55,
"learning_rate": 1.373622e-05,
"loss": 2.4188,
"step": 516
},
{
"epoch": 1.55,
"learning_rate": 1.3735515e-05,
"loss": 2.4164,
"step": 517
},
{
"epoch": 1.55,
"learning_rate": 1.373481e-05,
"loss": 2.4181,
"step": 518
},
{
"epoch": 1.55,
"learning_rate": 1.3734105e-05,
"loss": 2.4169,
"step": 519
},
{
"epoch": 1.56,
"learning_rate": 1.37334e-05,
"loss": 2.4139,
"step": 520
},
{
"epoch": 1.56,
"learning_rate": 1.3732695e-05,
"loss": 2.4151,
"step": 521
},
{
"epoch": 1.56,
"learning_rate": 1.3731990000000001e-05,
"loss": 2.4144,
"step": 522
},
{
"epoch": 1.57,
"learning_rate": 1.3731285e-05,
"loss": 2.413,
"step": 523
},
{
"epoch": 1.57,
"learning_rate": 1.373058e-05,
"loss": 2.4125,
"step": 524
},
{
"epoch": 1.57,
"learning_rate": 1.3729875e-05,
"loss": 2.4145,
"step": 525
},
{
"epoch": 1.58,
"learning_rate": 1.372917e-05,
"loss": 2.41,
"step": 526
},
{
"epoch": 1.58,
"learning_rate": 1.3728465e-05,
"loss": 2.4106,
"step": 527
},
{
"epoch": 1.58,
"learning_rate": 1.3727760000000002e-05,
"loss": 2.4082,
"step": 528
},
{
"epoch": 1.58,
"learning_rate": 1.3727055000000001e-05,
"loss": 2.4055,
"step": 529
},
{
"epoch": 1.59,
"learning_rate": 1.3726350000000001e-05,
"loss": 2.4068,
"step": 530
},
{
"epoch": 1.59,
"learning_rate": 1.3725645000000001e-05,
"loss": 2.4092,
"step": 531
},
{
"epoch": 1.59,
"learning_rate": 1.372494e-05,
"loss": 2.4058,
"step": 532
},
{
"epoch": 1.6,
"learning_rate": 1.3724235e-05,
"loss": 2.4051,
"step": 533
},
{
"epoch": 1.6,
"learning_rate": 1.3723530000000002e-05,
"loss": 2.4061,
"step": 534
},
{
"epoch": 1.6,
"learning_rate": 1.3722825e-05,
"loss": 2.4096,
"step": 535
},
{
"epoch": 1.61,
"learning_rate": 1.372212e-05,
"loss": 2.4022,
"step": 536
},
{
"epoch": 1.61,
"learning_rate": 1.3721415e-05,
"loss": 2.4057,
"step": 537
},
{
"epoch": 1.61,
"learning_rate": 1.372071e-05,
"loss": 2.4001,
"step": 538
},
{
"epoch": 1.61,
"learning_rate": 1.3720005e-05,
"loss": 2.398,
"step": 539
},
{
"epoch": 1.62,
"learning_rate": 1.3719300000000001e-05,
"loss": 2.4043,
"step": 540
},
{
"epoch": 1.62,
"learning_rate": 1.3718595e-05,
"loss": 2.4035,
"step": 541
},
{
"epoch": 1.62,
"learning_rate": 1.371789e-05,
"loss": 2.3986,
"step": 542
},
{
"epoch": 1.63,
"learning_rate": 1.3717185e-05,
"loss": 2.3977,
"step": 543
},
{
"epoch": 1.63,
"learning_rate": 1.371648e-05,
"loss": 2.3995,
"step": 544
},
{
"epoch": 1.63,
"learning_rate": 1.3715775e-05,
"loss": 2.397,
"step": 545
},
{
"epoch": 1.64,
"learning_rate": 1.3715070000000001e-05,
"loss": 2.395,
"step": 546
},
{
"epoch": 1.64,
"learning_rate": 1.3714365000000001e-05,
"loss": 2.3952,
"step": 547
},
{
"epoch": 1.64,
"learning_rate": 1.3713660000000001e-05,
"loss": 2.3951,
"step": 548
},
{
"epoch": 1.64,
"learning_rate": 1.3712955000000001e-05,
"loss": 2.3995,
"step": 549
},
{
"epoch": 1.65,
"learning_rate": 1.371225e-05,
"loss": 2.3954,
"step": 550
},
{
"epoch": 1.65,
"learning_rate": 1.3711545e-05,
"loss": 2.3945,
"step": 551
},
{
"epoch": 1.65,
"learning_rate": 1.371084e-05,
"loss": 2.39,
"step": 552
},
{
"epoch": 1.66,
"learning_rate": 1.3710135000000002e-05,
"loss": 2.394,
"step": 553
},
{
"epoch": 1.66,
"learning_rate": 1.3709430000000002e-05,
"loss": 2.3926,
"step": 554
},
{
"epoch": 1.66,
"learning_rate": 1.3708725e-05,
"loss": 2.3947,
"step": 555
},
{
"epoch": 1.66,
"learning_rate": 1.370802e-05,
"loss": 2.3915,
"step": 556
},
{
"epoch": 1.67,
"learning_rate": 1.3707315e-05,
"loss": 2.3904,
"step": 557
},
{
"epoch": 1.67,
"learning_rate": 1.370661e-05,
"loss": 2.3888,
"step": 558
},
{
"epoch": 1.67,
"learning_rate": 1.3705905e-05,
"loss": 2.39,
"step": 559
},
{
"epoch": 1.68,
"learning_rate": 1.37052e-05,
"loss": 2.3905,
"step": 560
},
{
"epoch": 1.68,
"learning_rate": 1.3704495e-05,
"loss": 2.3853,
"step": 561
},
{
"epoch": 1.68,
"learning_rate": 1.370379e-05,
"loss": 2.3879,
"step": 562
},
{
"epoch": 1.69,
"learning_rate": 1.3703085e-05,
"loss": 2.3856,
"step": 563
},
{
"epoch": 1.69,
"learning_rate": 1.370238e-05,
"loss": 2.3843,
"step": 564
},
{
"epoch": 1.69,
"learning_rate": 1.3701675000000001e-05,
"loss": 2.3835,
"step": 565
},
{
"epoch": 1.69,
"learning_rate": 1.3700970000000001e-05,
"loss": 2.3844,
"step": 566
},
{
"epoch": 1.7,
"learning_rate": 1.3700265000000001e-05,
"loss": 2.3822,
"step": 567
},
{
"epoch": 1.7,
"learning_rate": 1.369956e-05,
"loss": 2.3816,
"step": 568
},
{
"epoch": 1.7,
"learning_rate": 1.3698855e-05,
"loss": 2.3811,
"step": 569
},
{
"epoch": 1.71,
"learning_rate": 1.369815e-05,
"loss": 2.3809,
"step": 570
},
{
"epoch": 1.71,
"learning_rate": 1.3697445000000002e-05,
"loss": 2.3803,
"step": 571
},
{
"epoch": 1.71,
"learning_rate": 1.3696740000000002e-05,
"loss": 2.3781,
"step": 572
},
{
"epoch": 1.72,
"learning_rate": 1.3696035000000001e-05,
"loss": 2.3798,
"step": 573
},
{
"epoch": 1.72,
"learning_rate": 1.3695330000000001e-05,
"loss": 2.378,
"step": 574
},
{
"epoch": 1.72,
"learning_rate": 1.3694625e-05,
"loss": 2.3789,
"step": 575
},
{
"epoch": 1.72,
"learning_rate": 1.369392e-05,
"loss": 2.3782,
"step": 576
},
{
"epoch": 1.73,
"learning_rate": 1.3693215e-05,
"loss": 2.3763,
"step": 577
},
{
"epoch": 1.73,
"learning_rate": 1.369251e-05,
"loss": 2.3776,
"step": 578
},
{
"epoch": 1.73,
"learning_rate": 1.3691805e-05,
"loss": 2.373,
"step": 579
},
{
"epoch": 1.74,
"learning_rate": 1.36911e-05,
"loss": 2.3732,
"step": 580
},
{
"epoch": 1.74,
"learning_rate": 1.3690395e-05,
"loss": 2.3735,
"step": 581
},
{
"epoch": 1.74,
"learning_rate": 1.368969e-05,
"loss": 2.3739,
"step": 582
},
{
"epoch": 1.75,
"learning_rate": 1.3688985000000001e-05,
"loss": 2.3756,
"step": 583
},
{
"epoch": 1.75,
"learning_rate": 1.3688280000000001e-05,
"loss": 2.3727,
"step": 584
},
{
"epoch": 1.75,
"learning_rate": 1.3687575e-05,
"loss": 2.3713,
"step": 585
},
{
"epoch": 1.75,
"learning_rate": 1.368687e-05,
"loss": 2.3704,
"step": 586
},
{
"epoch": 1.76,
"learning_rate": 1.3686165e-05,
"loss": 2.3722,
"step": 587
},
{
"epoch": 1.76,
"learning_rate": 1.368546e-05,
"loss": 2.3651,
"step": 588
},
{
"epoch": 1.76,
"learning_rate": 1.3684755e-05,
"loss": 2.3736,
"step": 589
},
{
"epoch": 1.77,
"learning_rate": 1.3684050000000002e-05,
"loss": 2.3715,
"step": 590
},
{
"epoch": 1.77,
"learning_rate": 1.3683345000000001e-05,
"loss": 2.3674,
"step": 591
},
{
"epoch": 1.77,
"learning_rate": 1.3682640000000001e-05,
"loss": 2.3684,
"step": 592
},
{
"epoch": 1.78,
"learning_rate": 1.3681935000000001e-05,
"loss": 2.3664,
"step": 593
},
{
"epoch": 1.78,
"learning_rate": 1.368123e-05,
"loss": 2.3692,
"step": 594
},
{
"epoch": 1.78,
"learning_rate": 1.3680524999999999e-05,
"loss": 2.3655,
"step": 595
},
{
"epoch": 1.78,
"learning_rate": 1.367982e-05,
"loss": 2.3641,
"step": 596
},
{
"epoch": 1.79,
"learning_rate": 1.3679115e-05,
"loss": 2.3629,
"step": 597
},
{
"epoch": 1.79,
"learning_rate": 1.367841e-05,
"loss": 2.3611,
"step": 598
},
{
"epoch": 1.79,
"learning_rate": 1.3677705e-05,
"loss": 2.3621,
"step": 599
},
{
"epoch": 1.8,
"learning_rate": 1.3677e-05,
"loss": 2.3609,
"step": 600
},
{
"epoch": 1.8,
"eval_accuracy": 0.001743393456375839,
"eval_loss": 2.2031397819519043,
"eval_runtime": 28.9856,
"eval_samples_per_second": 10.281,
"eval_steps_per_second": 0.655,
"step": 600
},
{
"epoch": 1.8,
"learning_rate": 1.3676295e-05,
"loss": 2.3616,
"step": 601
},
{
"epoch": 1.8,
"learning_rate": 1.3675590000000001e-05,
"loss": 2.3643,
"step": 602
},
{
"epoch": 1.81,
"learning_rate": 1.3674885e-05,
"loss": 2.3584,
"step": 603
},
{
"epoch": 1.81,
"learning_rate": 1.367418e-05,
"loss": 2.3563,
"step": 604
},
{
"epoch": 1.81,
"learning_rate": 1.3673475e-05,
"loss": 2.36,
"step": 605
},
{
"epoch": 1.81,
"learning_rate": 1.367277e-05,
"loss": 2.3584,
"step": 606
},
{
"epoch": 1.82,
"learning_rate": 1.3672065e-05,
"loss": 2.3584,
"step": 607
},
{
"epoch": 1.82,
"learning_rate": 1.3671360000000002e-05,
"loss": 2.3554,
"step": 608
},
{
"epoch": 1.82,
"learning_rate": 1.3670655000000001e-05,
"loss": 2.3559,
"step": 609
},
{
"epoch": 1.83,
"learning_rate": 1.3669950000000001e-05,
"loss": 2.3542,
"step": 610
},
{
"epoch": 1.83,
"learning_rate": 1.3669245000000001e-05,
"loss": 2.3518,
"step": 611
},
{
"epoch": 1.83,
"learning_rate": 1.366854e-05,
"loss": 2.3574,
"step": 612
},
{
"epoch": 1.84,
"learning_rate": 1.3667835e-05,
"loss": 2.3535,
"step": 613
},
{
"epoch": 1.84,
"learning_rate": 1.366713e-05,
"loss": 2.3571,
"step": 614
},
{
"epoch": 1.84,
"learning_rate": 1.3666425e-05,
"loss": 2.3518,
"step": 615
},
{
"epoch": 1.84,
"learning_rate": 1.366572e-05,
"loss": 2.352,
"step": 616
},
{
"epoch": 1.85,
"learning_rate": 1.3665015e-05,
"loss": 2.3523,
"step": 617
},
{
"epoch": 1.85,
"learning_rate": 1.366431e-05,
"loss": 2.3475,
"step": 618
},
{
"epoch": 1.85,
"learning_rate": 1.3663605e-05,
"loss": 2.352,
"step": 619
},
{
"epoch": 1.86,
"learning_rate": 1.3662900000000001e-05,
"loss": 2.3494,
"step": 620
},
{
"epoch": 1.86,
"learning_rate": 1.3662195e-05,
"loss": 2.3477,
"step": 621
},
{
"epoch": 1.86,
"learning_rate": 1.366149e-05,
"loss": 2.3473,
"step": 622
},
{
"epoch": 1.87,
"learning_rate": 1.3660785e-05,
"loss": 2.3454,
"step": 623
},
{
"epoch": 1.87,
"learning_rate": 1.366008e-05,
"loss": 2.3478,
"step": 624
},
{
"epoch": 1.87,
"learning_rate": 1.3659375e-05,
"loss": 2.3471,
"step": 625
},
{
"epoch": 1.87,
"learning_rate": 1.365867e-05,
"loss": 2.3452,
"step": 626
},
{
"epoch": 1.88,
"learning_rate": 1.3657965000000001e-05,
"loss": 2.3457,
"step": 627
},
{
"epoch": 1.88,
"learning_rate": 1.3657260000000001e-05,
"loss": 2.3466,
"step": 628
},
{
"epoch": 1.88,
"learning_rate": 1.3656555000000001e-05,
"loss": 2.3474,
"step": 629
},
{
"epoch": 1.89,
"learning_rate": 1.365585e-05,
"loss": 2.3438,
"step": 630
},
{
"epoch": 1.89,
"learning_rate": 1.3655145e-05,
"loss": 2.3393,
"step": 631
},
{
"epoch": 1.89,
"learning_rate": 1.365444e-05,
"loss": 2.3443,
"step": 632
},
{
"epoch": 1.9,
"learning_rate": 1.3653735000000002e-05,
"loss": 2.3386,
"step": 633
},
{
"epoch": 1.9,
"learning_rate": 1.3653030000000002e-05,
"loss": 2.3392,
"step": 634
},
{
"epoch": 1.9,
"learning_rate": 1.3652325000000001e-05,
"loss": 2.3413,
"step": 635
},
{
"epoch": 1.9,
"learning_rate": 1.365162e-05,
"loss": 2.3397,
"step": 636
},
{
"epoch": 1.91,
"learning_rate": 1.3650915e-05,
"loss": 2.3381,
"step": 637
},
{
"epoch": 1.91,
"learning_rate": 1.365021e-05,
"loss": 2.3402,
"step": 638
},
{
"epoch": 1.91,
"learning_rate": 1.3649505e-05,
"loss": 2.3404,
"step": 639
},
{
"epoch": 1.92,
"learning_rate": 1.36488e-05,
"loss": 2.3378,
"step": 640
},
{
"epoch": 1.92,
"learning_rate": 1.3648095e-05,
"loss": 2.3353,
"step": 641
},
{
"epoch": 1.92,
"learning_rate": 1.364739e-05,
"loss": 2.3346,
"step": 642
},
{
"epoch": 1.93,
"learning_rate": 1.3646685e-05,
"loss": 2.3397,
"step": 643
},
{
"epoch": 1.93,
"learning_rate": 1.364598e-05,
"loss": 2.3349,
"step": 644
},
{
"epoch": 1.93,
"learning_rate": 1.3645275000000001e-05,
"loss": 2.3332,
"step": 645
},
{
"epoch": 1.93,
"learning_rate": 1.3644570000000001e-05,
"loss": 2.3325,
"step": 646
},
{
"epoch": 1.94,
"learning_rate": 1.3643865000000001e-05,
"loss": 2.3295,
"step": 647
},
{
"epoch": 1.94,
"learning_rate": 1.364316e-05,
"loss": 2.3308,
"step": 648
},
{
"epoch": 1.94,
"learning_rate": 1.3642455e-05,
"loss": 2.3355,
"step": 649
},
{
"epoch": 1.95,
"learning_rate": 1.364175e-05,
"loss": 2.3315,
"step": 650
},
{
"epoch": 1.95,
"learning_rate": 1.3641045000000002e-05,
"loss": 2.334,
"step": 651
},
{
"epoch": 1.95,
"learning_rate": 1.3640340000000002e-05,
"loss": 2.3325,
"step": 652
},
{
"epoch": 1.96,
"learning_rate": 1.3639635000000001e-05,
"loss": 2.3307,
"step": 653
},
{
"epoch": 1.96,
"learning_rate": 1.3638930000000001e-05,
"loss": 2.3301,
"step": 654
},
{
"epoch": 1.96,
"learning_rate": 1.3638225000000001e-05,
"loss": 2.3253,
"step": 655
},
{
"epoch": 1.96,
"learning_rate": 1.363752e-05,
"loss": 2.3259,
"step": 656
},
{
"epoch": 1.97,
"learning_rate": 1.3636815e-05,
"loss": 2.3294,
"step": 657
},
{
"epoch": 1.97,
"learning_rate": 1.363611e-05,
"loss": 2.3279,
"step": 658
},
{
"epoch": 1.97,
"learning_rate": 1.3635405e-05,
"loss": 2.3255,
"step": 659
},
{
"epoch": 1.98,
"learning_rate": 1.36347e-05,
"loss": 2.3286,
"step": 660
},
{
"epoch": 1.98,
"learning_rate": 1.3633995e-05,
"loss": 2.3249,
"step": 661
},
{
"epoch": 1.98,
"learning_rate": 1.363329e-05,
"loss": 2.3327,
"step": 662
},
{
"epoch": 1.99,
"learning_rate": 1.3632585e-05,
"loss": 2.324,
"step": 663
},
{
"epoch": 1.99,
"learning_rate": 1.3631880000000001e-05,
"loss": 2.3259,
"step": 664
},
{
"epoch": 1.99,
"learning_rate": 1.3631175e-05,
"loss": 2.3267,
"step": 665
},
{
"epoch": 1.99,
"learning_rate": 1.363047e-05,
"loss": 2.3213,
"step": 666
},
{
"epoch": 2.0,
"learning_rate": 1.3629765e-05,
"loss": 2.3203,
"step": 667
},
{
"epoch": 2.0,
"learning_rate": 1.362906e-05,
"loss": 2.3226,
"step": 668
},
{
"epoch": 2.0,
"learning_rate": 1.3628355e-05,
"loss": 2.322,
"step": 669
},
{
"epoch": 2.01,
"learning_rate": 1.3627650000000002e-05,
"loss": 2.3189,
"step": 670
},
{
"epoch": 2.01,
"learning_rate": 1.3626945000000001e-05,
"loss": 2.3158,
"step": 671
},
{
"epoch": 2.01,
"learning_rate": 1.3626240000000001e-05,
"loss": 2.3139,
"step": 672
},
{
"epoch": 2.02,
"learning_rate": 1.3625535000000001e-05,
"loss": 2.3161,
"step": 673
},
{
"epoch": 2.02,
"learning_rate": 1.362483e-05,
"loss": 2.3208,
"step": 674
},
{
"epoch": 2.02,
"learning_rate": 1.3624125e-05,
"loss": 2.3186,
"step": 675
},
{
"epoch": 2.02,
"learning_rate": 1.362342e-05,
"loss": 2.3169,
"step": 676
},
{
"epoch": 2.03,
"learning_rate": 1.3622715e-05,
"loss": 2.3147,
"step": 677
},
{
"epoch": 2.03,
"learning_rate": 1.362201e-05,
"loss": 2.3135,
"step": 678
},
{
"epoch": 2.03,
"learning_rate": 1.3621305e-05,
"loss": 2.3128,
"step": 679
},
{
"epoch": 2.04,
"learning_rate": 1.36206e-05,
"loss": 2.3165,
"step": 680
},
{
"epoch": 2.04,
"learning_rate": 1.3619895e-05,
"loss": 2.3157,
"step": 681
},
{
"epoch": 2.04,
"learning_rate": 1.3619190000000001e-05,
"loss": 2.3113,
"step": 682
},
{
"epoch": 2.05,
"learning_rate": 1.3618485e-05,
"loss": 2.3172,
"step": 683
},
{
"epoch": 2.05,
"learning_rate": 1.361778e-05,
"loss": 2.3145,
"step": 684
},
{
"epoch": 2.05,
"learning_rate": 1.3617075e-05,
"loss": 2.3141,
"step": 685
},
{
"epoch": 2.05,
"learning_rate": 1.361637e-05,
"loss": 2.3153,
"step": 686
},
{
"epoch": 2.06,
"learning_rate": 1.3615665e-05,
"loss": 2.3123,
"step": 687
},
{
"epoch": 2.06,
"learning_rate": 1.3614960000000002e-05,
"loss": 2.3071,
"step": 688
},
{
"epoch": 2.06,
"learning_rate": 1.3614255000000001e-05,
"loss": 2.3087,
"step": 689
},
{
"epoch": 2.07,
"learning_rate": 1.3613550000000001e-05,
"loss": 2.3076,
"step": 690
},
{
"epoch": 2.07,
"learning_rate": 1.3612845000000001e-05,
"loss": 2.305,
"step": 691
},
{
"epoch": 2.07,
"learning_rate": 1.361214e-05,
"loss": 2.3081,
"step": 692
},
{
"epoch": 2.08,
"learning_rate": 1.3611435e-05,
"loss": 2.3042,
"step": 693
},
{
"epoch": 2.08,
"learning_rate": 1.361073e-05,
"loss": 2.3103,
"step": 694
},
{
"epoch": 2.08,
"learning_rate": 1.3610025000000002e-05,
"loss": 2.3044,
"step": 695
},
{
"epoch": 2.08,
"learning_rate": 1.360932e-05,
"loss": 2.3062,
"step": 696
},
{
"epoch": 2.09,
"learning_rate": 1.3608615e-05,
"loss": 2.3059,
"step": 697
},
{
"epoch": 2.09,
"learning_rate": 1.360791e-05,
"loss": 2.3049,
"step": 698
},
{
"epoch": 2.09,
"learning_rate": 1.3607205e-05,
"loss": 2.3006,
"step": 699
},
{
"epoch": 2.1,
"learning_rate": 1.36065e-05,
"loss": 2.3016,
"step": 700
},
{
"epoch": 2.1,
"eval_accuracy": 0.0011141988255033556,
"eval_loss": 2.153825521469116,
"eval_runtime": 31.6811,
"eval_samples_per_second": 9.406,
"eval_steps_per_second": 0.6,
"step": 700
},
{
"epoch": 2.1,
"learning_rate": 1.3605795e-05,
"loss": 2.3034,
"step": 701
},
{
"epoch": 2.1,
"learning_rate": 1.360509e-05,
"loss": 2.303,
"step": 702
},
{
"epoch": 2.11,
"learning_rate": 1.3604385e-05,
"loss": 2.3006,
"step": 703
},
{
"epoch": 2.11,
"learning_rate": 1.360368e-05,
"loss": 2.3043,
"step": 704
},
{
"epoch": 2.11,
"learning_rate": 1.3602975e-05,
"loss": 2.3016,
"step": 705
},
{
"epoch": 2.11,
"learning_rate": 1.360227e-05,
"loss": 2.3004,
"step": 706
},
{
"epoch": 2.12,
"learning_rate": 1.3601565000000001e-05,
"loss": 2.3,
"step": 707
},
{
"epoch": 2.12,
"learning_rate": 1.3600860000000001e-05,
"loss": 2.2944,
"step": 708
},
{
"epoch": 2.12,
"learning_rate": 1.3600155000000001e-05,
"loss": 2.2992,
"step": 709
},
{
"epoch": 2.13,
"learning_rate": 1.359945e-05,
"loss": 2.2984,
"step": 710
},
{
"epoch": 2.13,
"learning_rate": 1.3598745e-05,
"loss": 2.2934,
"step": 711
},
{
"epoch": 2.13,
"learning_rate": 1.359804e-05,
"loss": 2.2936,
"step": 712
},
{
"epoch": 2.14,
"learning_rate": 1.3597335000000002e-05,
"loss": 2.3006,
"step": 713
},
{
"epoch": 2.14,
"learning_rate": 1.3596630000000002e-05,
"loss": 2.2955,
"step": 714
},
{
"epoch": 2.14,
"learning_rate": 1.3595925000000001e-05,
"loss": 2.295,
"step": 715
},
{
"epoch": 2.14,
"learning_rate": 1.359522e-05,
"loss": 2.2949,
"step": 716
},
{
"epoch": 2.15,
"learning_rate": 1.3594515e-05,
"loss": 2.2908,
"step": 717
},
{
"epoch": 2.15,
"learning_rate": 1.359381e-05,
"loss": 2.2915,
"step": 718
},
{
"epoch": 2.15,
"learning_rate": 1.3593105e-05,
"loss": 2.2963,
"step": 719
},
{
"epoch": 2.16,
"learning_rate": 1.35924e-05,
"loss": 2.2918,
"step": 720
},
{
"epoch": 2.16,
"learning_rate": 1.3591695e-05,
"loss": 2.2962,
"step": 721
},
{
"epoch": 2.16,
"learning_rate": 1.359099e-05,
"loss": 2.2924,
"step": 722
},
{
"epoch": 2.17,
"learning_rate": 1.3590285e-05,
"loss": 2.2918,
"step": 723
},
{
"epoch": 2.17,
"learning_rate": 1.358958e-05,
"loss": 2.2875,
"step": 724
},
{
"epoch": 2.17,
"learning_rate": 1.3588875000000001e-05,
"loss": 2.2917,
"step": 725
},
{
"epoch": 2.17,
"learning_rate": 1.3588170000000001e-05,
"loss": 2.2896,
"step": 726
},
{
"epoch": 2.18,
"learning_rate": 1.3587465000000001e-05,
"loss": 2.2891,
"step": 727
},
{
"epoch": 2.18,
"learning_rate": 1.358676e-05,
"loss": 2.2908,
"step": 728
},
{
"epoch": 2.18,
"learning_rate": 1.3586055e-05,
"loss": 2.2888,
"step": 729
},
{
"epoch": 2.19,
"learning_rate": 1.358535e-05,
"loss": 2.2861,
"step": 730
},
{
"epoch": 2.19,
"learning_rate": 1.3584645e-05,
"loss": 2.2824,
"step": 731
},
{
"epoch": 2.19,
"learning_rate": 1.3583940000000002e-05,
"loss": 2.2845,
"step": 732
},
{
"epoch": 2.2,
"learning_rate": 1.3583235000000001e-05,
"loss": 2.2838,
"step": 733
},
{
"epoch": 2.2,
"learning_rate": 1.3582530000000001e-05,
"loss": 2.291,
"step": 734
},
{
"epoch": 2.2,
"learning_rate": 1.3581825000000001e-05,
"loss": 2.2837,
"step": 735
},
{
"epoch": 2.2,
"learning_rate": 1.3581119999999999e-05,
"loss": 2.2829,
"step": 736
},
{
"epoch": 2.21,
"learning_rate": 1.3580415e-05,
"loss": 2.2825,
"step": 737
},
{
"epoch": 2.21,
"learning_rate": 1.357971e-05,
"loss": 2.2871,
"step": 738
},
{
"epoch": 2.21,
"learning_rate": 1.3579005e-05,
"loss": 2.2818,
"step": 739
},
{
"epoch": 2.22,
"learning_rate": 1.35783e-05,
"loss": 2.2798,
"step": 740
},
{
"epoch": 2.22,
"learning_rate": 1.3577595e-05,
"loss": 2.2806,
"step": 741
},
{
"epoch": 2.22,
"learning_rate": 1.357689e-05,
"loss": 2.2837,
"step": 742
},
{
"epoch": 2.22,
"learning_rate": 1.3576185e-05,
"loss": 2.2765,
"step": 743
},
{
"epoch": 2.23,
"learning_rate": 1.3575480000000001e-05,
"loss": 2.2815,
"step": 744
},
{
"epoch": 2.23,
"learning_rate": 1.3574775e-05,
"loss": 2.2773,
"step": 745
},
{
"epoch": 2.23,
"learning_rate": 1.357407e-05,
"loss": 2.2796,
"step": 746
},
{
"epoch": 2.24,
"learning_rate": 1.3573365e-05,
"loss": 2.2773,
"step": 747
},
{
"epoch": 2.24,
"learning_rate": 1.357266e-05,
"loss": 2.2781,
"step": 748
},
{
"epoch": 2.24,
"learning_rate": 1.3571955e-05,
"loss": 2.2787,
"step": 749
},
{
"epoch": 2.25,
"learning_rate": 1.3571250000000002e-05,
"loss": 2.2791,
"step": 750
},
{
"epoch": 2.25,
"learning_rate": 1.3570545000000001e-05,
"loss": 2.2749,
"step": 751
},
{
"epoch": 2.25,
"learning_rate": 1.3569840000000001e-05,
"loss": 2.2752,
"step": 752
},
{
"epoch": 2.25,
"learning_rate": 1.3569135000000001e-05,
"loss": 2.2778,
"step": 753
},
{
"epoch": 2.26,
"learning_rate": 1.356843e-05,
"loss": 2.2746,
"step": 754
},
{
"epoch": 2.26,
"learning_rate": 1.3567725e-05,
"loss": 2.2717,
"step": 755
},
{
"epoch": 2.26,
"learning_rate": 1.3567020000000002e-05,
"loss": 2.2761,
"step": 756
},
{
"epoch": 2.27,
"learning_rate": 1.3566315e-05,
"loss": 2.2705,
"step": 757
},
{
"epoch": 2.27,
"learning_rate": 1.356561e-05,
"loss": 2.2722,
"step": 758
},
{
"epoch": 2.27,
"learning_rate": 1.3564905e-05,
"loss": 2.2705,
"step": 759
},
{
"epoch": 2.28,
"learning_rate": 1.35642e-05,
"loss": 2.2718,
"step": 760
},
{
"epoch": 2.28,
"learning_rate": 1.3563495e-05,
"loss": 2.2731,
"step": 761
},
{
"epoch": 2.28,
"learning_rate": 1.3562790000000001e-05,
"loss": 2.2668,
"step": 762
},
{
"epoch": 2.28,
"learning_rate": 1.3562085e-05,
"loss": 2.2704,
"step": 763
},
{
"epoch": 2.29,
"learning_rate": 1.356138e-05,
"loss": 2.2707,
"step": 764
},
{
"epoch": 2.29,
"learning_rate": 1.3560675e-05,
"loss": 2.268,
"step": 765
},
{
"epoch": 2.29,
"learning_rate": 1.355997e-05,
"loss": 2.2648,
"step": 766
},
{
"epoch": 2.3,
"learning_rate": 1.3559265e-05,
"loss": 2.2669,
"step": 767
},
{
"epoch": 2.3,
"learning_rate": 1.355856e-05,
"loss": 2.2648,
"step": 768
},
{
"epoch": 2.3,
"learning_rate": 1.3557855000000001e-05,
"loss": 2.2659,
"step": 769
},
{
"epoch": 2.31,
"learning_rate": 1.3557150000000001e-05,
"loss": 2.2635,
"step": 770
},
{
"epoch": 2.31,
"learning_rate": 1.3556445000000001e-05,
"loss": 2.2663,
"step": 771
},
{
"epoch": 2.31,
"learning_rate": 1.355574e-05,
"loss": 2.2644,
"step": 772
},
{
"epoch": 2.31,
"learning_rate": 1.3555035e-05,
"loss": 2.2613,
"step": 773
},
{
"epoch": 2.32,
"learning_rate": 1.355433e-05,
"loss": 2.2622,
"step": 774
},
{
"epoch": 2.32,
"learning_rate": 1.3553625000000002e-05,
"loss": 2.2637,
"step": 775
},
{
"epoch": 2.32,
"learning_rate": 1.3552920000000002e-05,
"loss": 2.2636,
"step": 776
},
{
"epoch": 2.33,
"learning_rate": 1.3552215e-05,
"loss": 2.2638,
"step": 777
},
{
"epoch": 2.33,
"learning_rate": 1.355151e-05,
"loss": 2.2605,
"step": 778
},
{
"epoch": 2.33,
"learning_rate": 1.3550805e-05,
"loss": 2.2578,
"step": 779
},
{
"epoch": 2.34,
"learning_rate": 1.35501e-05,
"loss": 2.263,
"step": 780
},
{
"epoch": 2.34,
"learning_rate": 1.3549395e-05,
"loss": 2.261,
"step": 781
},
{
"epoch": 2.34,
"learning_rate": 1.354869e-05,
"loss": 2.2605,
"step": 782
},
{
"epoch": 2.34,
"learning_rate": 1.3547985e-05,
"loss": 2.2606,
"step": 783
},
{
"epoch": 2.35,
"learning_rate": 1.354728e-05,
"loss": 2.2574,
"step": 784
},
{
"epoch": 2.35,
"learning_rate": 1.3546575e-05,
"loss": 2.258,
"step": 785
},
{
"epoch": 2.35,
"learning_rate": 1.354587e-05,
"loss": 2.2592,
"step": 786
},
{
"epoch": 2.36,
"learning_rate": 1.3545165000000001e-05,
"loss": 2.2572,
"step": 787
},
{
"epoch": 2.36,
"learning_rate": 1.3544460000000001e-05,
"loss": 2.2539,
"step": 788
},
{
"epoch": 2.36,
"learning_rate": 1.3543755000000001e-05,
"loss": 2.254,
"step": 789
},
{
"epoch": 2.37,
"learning_rate": 1.354305e-05,
"loss": 2.2553,
"step": 790
},
{
"epoch": 2.37,
"learning_rate": 1.3542345e-05,
"loss": 2.2593,
"step": 791
},
{
"epoch": 2.37,
"learning_rate": 1.354164e-05,
"loss": 2.2536,
"step": 792
},
{
"epoch": 2.37,
"learning_rate": 1.3540935000000002e-05,
"loss": 2.2534,
"step": 793
},
{
"epoch": 2.38,
"learning_rate": 1.3540230000000002e-05,
"loss": 2.2515,
"step": 794
},
{
"epoch": 2.38,
"learning_rate": 1.3539525000000001e-05,
"loss": 2.2541,
"step": 795
},
{
"epoch": 2.38,
"learning_rate": 1.3538820000000001e-05,
"loss": 2.2512,
"step": 796
},
{
"epoch": 2.39,
"learning_rate": 1.3538115e-05,
"loss": 2.2523,
"step": 797
},
{
"epoch": 2.39,
"learning_rate": 1.353741e-05,
"loss": 2.2506,
"step": 798
},
{
"epoch": 2.39,
"learning_rate": 1.3536705e-05,
"loss": 2.2541,
"step": 799
},
{
"epoch": 2.4,
"learning_rate": 1.3536e-05,
"loss": 2.2483,
"step": 800
},
{
"epoch": 2.4,
"eval_accuracy": 0.0010158871644295301,
"eval_loss": 2.1085779666900635,
"eval_runtime": 30.8027,
"eval_samples_per_second": 9.674,
"eval_steps_per_second": 0.617,
"step": 800
},
{
"epoch": 2.4,
"learning_rate": 1.3535295e-05,
"loss": 2.2459,
"step": 801
},
{
"epoch": 2.4,
"learning_rate": 1.353459e-05,
"loss": 2.2505,
"step": 802
},
{
"epoch": 2.4,
"learning_rate": 1.3533885e-05,
"loss": 2.2479,
"step": 803
},
{
"epoch": 2.41,
"learning_rate": 1.353318e-05,
"loss": 2.2445,
"step": 804
},
{
"epoch": 2.41,
"learning_rate": 1.3532475e-05,
"loss": 2.2459,
"step": 805
},
{
"epoch": 2.41,
"learning_rate": 1.3531770000000001e-05,
"loss": 2.2436,
"step": 806
},
{
"epoch": 2.42,
"learning_rate": 1.3531065000000001e-05,
"loss": 2.2475,
"step": 807
},
{
"epoch": 2.42,
"learning_rate": 1.353036e-05,
"loss": 2.2426,
"step": 808
},
{
"epoch": 2.42,
"learning_rate": 1.3529655e-05,
"loss": 2.2424,
"step": 809
},
{
"epoch": 2.43,
"learning_rate": 1.352895e-05,
"loss": 2.2437,
"step": 810
},
{
"epoch": 2.43,
"learning_rate": 1.3528245e-05,
"loss": 2.246,
"step": 811
},
{
"epoch": 2.43,
"learning_rate": 1.3527540000000002e-05,
"loss": 2.2496,
"step": 812
},
{
"epoch": 2.43,
"learning_rate": 1.3526835000000001e-05,
"loss": 2.2455,
"step": 813
},
{
"epoch": 2.44,
"learning_rate": 1.3526130000000001e-05,
"loss": 2.2465,
"step": 814
},
{
"epoch": 2.44,
"learning_rate": 1.3525425000000001e-05,
"loss": 2.2419,
"step": 815
},
{
"epoch": 2.44,
"learning_rate": 1.352472e-05,
"loss": 2.2445,
"step": 816
},
{
"epoch": 2.45,
"learning_rate": 1.3524014999999999e-05,
"loss": 2.2406,
"step": 817
},
{
"epoch": 2.45,
"learning_rate": 1.352331e-05,
"loss": 2.2413,
"step": 818
},
{
"epoch": 2.45,
"learning_rate": 1.3522605e-05,
"loss": 2.2387,
"step": 819
},
{
"epoch": 2.46,
"learning_rate": 1.35219e-05,
"loss": 2.2386,
"step": 820
},
{
"epoch": 2.46,
"learning_rate": 1.3521195e-05,
"loss": 2.2379,
"step": 821
},
{
"epoch": 2.46,
"learning_rate": 1.352049e-05,
"loss": 2.2376,
"step": 822
},
{
"epoch": 2.46,
"learning_rate": 1.3519785e-05,
"loss": 2.2351,
"step": 823
},
{
"epoch": 2.47,
"learning_rate": 1.3519080000000001e-05,
"loss": 2.2363,
"step": 824
},
{
"epoch": 2.47,
"learning_rate": 1.3518375e-05,
"loss": 2.2323,
"step": 825
},
{
"epoch": 2.47,
"learning_rate": 1.351767e-05,
"loss": 2.2326,
"step": 826
},
{
"epoch": 2.48,
"learning_rate": 1.3516965e-05,
"loss": 2.2358,
"step": 827
},
{
"epoch": 2.48,
"learning_rate": 1.351626e-05,
"loss": 2.2348,
"step": 828
},
{
"epoch": 2.48,
"learning_rate": 1.3515555e-05,
"loss": 2.2324,
"step": 829
},
{
"epoch": 2.49,
"learning_rate": 1.3514850000000002e-05,
"loss": 2.2365,
"step": 830
},
{
"epoch": 2.49,
"learning_rate": 1.3514145000000001e-05,
"loss": 2.2355,
"step": 831
},
{
"epoch": 2.49,
"learning_rate": 1.3513440000000001e-05,
"loss": 2.2342,
"step": 832
},
{
"epoch": 2.49,
"learning_rate": 1.3512735000000001e-05,
"loss": 2.235,
"step": 833
},
{
"epoch": 2.5,
"learning_rate": 1.351203e-05,
"loss": 2.2317,
"step": 834
},
{
"epoch": 2.5,
"learning_rate": 1.3511325e-05,
"loss": 2.2316,
"step": 835
},
{
"epoch": 2.5,
"learning_rate": 1.351062e-05,
"loss": 2.2336,
"step": 836
},
{
"epoch": 2.51,
"learning_rate": 1.3509915e-05,
"loss": 2.2328,
"step": 837
},
{
"epoch": 2.51,
"learning_rate": 1.350921e-05,
"loss": 2.2343,
"step": 838
},
{
"epoch": 2.51,
"learning_rate": 1.3508505e-05,
"loss": 2.231,
"step": 839
},
{
"epoch": 2.52,
"learning_rate": 1.35078e-05,
"loss": 2.2337,
"step": 840
},
{
"epoch": 2.52,
"learning_rate": 1.3507095e-05,
"loss": 2.2288,
"step": 841
},
{
"epoch": 2.52,
"learning_rate": 1.3506390000000001e-05,
"loss": 2.2278,
"step": 842
},
{
"epoch": 2.52,
"learning_rate": 1.3505685e-05,
"loss": 2.2299,
"step": 843
},
{
"epoch": 2.53,
"learning_rate": 1.350498e-05,
"loss": 2.2274,
"step": 844
},
{
"epoch": 2.53,
"learning_rate": 1.3504275e-05,
"loss": 2.2249,
"step": 845
},
{
"epoch": 2.53,
"learning_rate": 1.350357e-05,
"loss": 2.226,
"step": 846
},
{
"epoch": 2.54,
"learning_rate": 1.3502865e-05,
"loss": 2.2245,
"step": 847
},
{
"epoch": 2.54,
"learning_rate": 1.350216e-05,
"loss": 2.231,
"step": 848
},
{
"epoch": 2.54,
"learning_rate": 1.3501455000000001e-05,
"loss": 2.2244,
"step": 849
},
{
"epoch": 2.55,
"learning_rate": 1.3500750000000001e-05,
"loss": 2.226,
"step": 850
},
{
"epoch": 2.55,
"learning_rate": 1.3500045000000001e-05,
"loss": 2.225,
"step": 851
},
{
"epoch": 2.55,
"learning_rate": 1.349934e-05,
"loss": 2.2225,
"step": 852
},
{
"epoch": 2.55,
"learning_rate": 1.3498635e-05,
"loss": 2.2213,
"step": 853
},
{
"epoch": 2.56,
"learning_rate": 1.349793e-05,
"loss": 2.2207,
"step": 854
},
{
"epoch": 2.56,
"learning_rate": 1.3497225000000002e-05,
"loss": 2.2243,
"step": 855
},
{
"epoch": 2.56,
"learning_rate": 1.3496520000000002e-05,
"loss": 2.2244,
"step": 856
},
{
"epoch": 2.57,
"learning_rate": 1.3495815e-05,
"loss": 2.2195,
"step": 857
},
{
"epoch": 2.57,
"learning_rate": 1.349511e-05,
"loss": 2.2242,
"step": 858
},
{
"epoch": 2.57,
"learning_rate": 1.3494405e-05,
"loss": 2.2199,
"step": 859
},
{
"epoch": 2.58,
"learning_rate": 1.34937e-05,
"loss": 2.2215,
"step": 860
},
{
"epoch": 2.58,
"learning_rate": 1.3492995e-05,
"loss": 2.2216,
"step": 861
},
{
"epoch": 2.58,
"learning_rate": 1.349229e-05,
"loss": 2.2164,
"step": 862
},
{
"epoch": 2.58,
"learning_rate": 1.3491585e-05,
"loss": 2.2203,
"step": 863
},
{
"epoch": 2.59,
"learning_rate": 1.349088e-05,
"loss": 2.2167,
"step": 864
},
{
"epoch": 2.59,
"learning_rate": 1.3490175e-05,
"loss": 2.2143,
"step": 865
},
{
"epoch": 2.59,
"learning_rate": 1.348947e-05,
"loss": 2.2161,
"step": 866
},
{
"epoch": 2.6,
"learning_rate": 1.3488765000000001e-05,
"loss": 2.2132,
"step": 867
},
{
"epoch": 2.6,
"learning_rate": 1.3488060000000001e-05,
"loss": 2.216,
"step": 868
},
{
"epoch": 2.6,
"learning_rate": 1.3487355000000001e-05,
"loss": 2.216,
"step": 869
},
{
"epoch": 2.61,
"learning_rate": 1.348665e-05,
"loss": 2.2159,
"step": 870
},
{
"epoch": 2.61,
"learning_rate": 1.3485945e-05,
"loss": 2.2128,
"step": 871
},
{
"epoch": 2.61,
"learning_rate": 1.348524e-05,
"loss": 2.215,
"step": 872
},
{
"epoch": 2.61,
"learning_rate": 1.3484535e-05,
"loss": 2.215,
"step": 873
},
{
"epoch": 2.62,
"learning_rate": 1.3483830000000002e-05,
"loss": 2.213,
"step": 874
},
{
"epoch": 2.62,
"learning_rate": 1.3483125000000001e-05,
"loss": 2.2151,
"step": 875
},
{
"epoch": 2.62,
"learning_rate": 1.3482420000000001e-05,
"loss": 2.2142,
"step": 876
},
{
"epoch": 2.63,
"learning_rate": 1.3481715000000001e-05,
"loss": 2.2108,
"step": 877
},
{
"epoch": 2.63,
"learning_rate": 1.348101e-05,
"loss": 2.2119,
"step": 878
},
{
"epoch": 2.63,
"learning_rate": 1.3480305e-05,
"loss": 2.2142,
"step": 879
},
{
"epoch": 2.64,
"learning_rate": 1.34796e-05,
"loss": 2.2083,
"step": 880
},
{
"epoch": 2.64,
"learning_rate": 1.3478895e-05,
"loss": 2.2085,
"step": 881
},
{
"epoch": 2.64,
"learning_rate": 1.347819e-05,
"loss": 2.2095,
"step": 882
},
{
"epoch": 2.64,
"learning_rate": 1.3477485e-05,
"loss": 2.2127,
"step": 883
},
{
"epoch": 2.65,
"learning_rate": 1.347678e-05,
"loss": 2.2085,
"step": 884
},
{
"epoch": 2.65,
"learning_rate": 1.3476075e-05,
"loss": 2.2086,
"step": 885
},
{
"epoch": 2.65,
"learning_rate": 1.3475370000000001e-05,
"loss": 2.2102,
"step": 886
},
{
"epoch": 2.66,
"learning_rate": 1.3474665000000001e-05,
"loss": 2.2021,
"step": 887
},
{
"epoch": 2.66,
"learning_rate": 1.347396e-05,
"loss": 2.2049,
"step": 888
},
{
"epoch": 2.66,
"learning_rate": 1.3473255e-05,
"loss": 2.2052,
"step": 889
},
{
"epoch": 2.67,
"learning_rate": 1.347255e-05,
"loss": 2.2112,
"step": 890
},
{
"epoch": 2.67,
"learning_rate": 1.3471845e-05,
"loss": 2.2049,
"step": 891
},
{
"epoch": 2.67,
"learning_rate": 1.3471140000000002e-05,
"loss": 2.203,
"step": 892
},
{
"epoch": 2.67,
"learning_rate": 1.3470435000000001e-05,
"loss": 2.2066,
"step": 893
},
{
"epoch": 2.68,
"learning_rate": 1.3469730000000001e-05,
"loss": 2.2032,
"step": 894
},
{
"epoch": 2.68,
"learning_rate": 1.3469025000000001e-05,
"loss": 2.2051,
"step": 895
},
{
"epoch": 2.68,
"learning_rate": 1.346832e-05,
"loss": 2.2032,
"step": 896
},
{
"epoch": 2.69,
"learning_rate": 1.3467615e-05,
"loss": 2.2006,
"step": 897
},
{
"epoch": 2.69,
"learning_rate": 1.346691e-05,
"loss": 2.2001,
"step": 898
},
{
"epoch": 2.69,
"learning_rate": 1.3466205e-05,
"loss": 2.2,
"step": 899
},
{
"epoch": 2.7,
"learning_rate": 1.34655e-05,
"loss": 2.2009,
"step": 900
},
{
"epoch": 2.7,
"eval_accuracy": 0.0007930473993288591,
"eval_loss": 2.0654594898223877,
"eval_runtime": 31.3594,
"eval_samples_per_second": 9.503,
"eval_steps_per_second": 0.606,
"step": 900
},
{
"epoch": 2.7,
"learning_rate": 1.3464795e-05,
"loss": 2.199,
"step": 901
},
{
"epoch": 2.7,
"learning_rate": 1.346409e-05,
"loss": 2.1994,
"step": 902
},
{
"epoch": 2.7,
"learning_rate": 1.3463385e-05,
"loss": 2.1972,
"step": 903
},
{
"epoch": 2.71,
"learning_rate": 1.3462680000000001e-05,
"loss": 2.1981,
"step": 904
},
{
"epoch": 2.71,
"learning_rate": 1.3461975e-05,
"loss": 2.1997,
"step": 905
},
{
"epoch": 2.71,
"learning_rate": 1.346127e-05,
"loss": 2.1998,
"step": 906
},
{
"epoch": 2.72,
"learning_rate": 1.3460565e-05,
"loss": 2.1983,
"step": 907
},
{
"epoch": 2.72,
"learning_rate": 1.345986e-05,
"loss": 2.2003,
"step": 908
},
{
"epoch": 2.72,
"learning_rate": 1.3459155e-05,
"loss": 2.1958,
"step": 909
},
{
"epoch": 2.73,
"learning_rate": 1.3458450000000002e-05,
"loss": 2.1987,
"step": 910
},
{
"epoch": 2.73,
"learning_rate": 1.3457745000000001e-05,
"loss": 2.1943,
"step": 911
},
{
"epoch": 2.73,
"learning_rate": 1.3457040000000001e-05,
"loss": 2.1955,
"step": 912
},
{
"epoch": 2.73,
"learning_rate": 1.3456335000000001e-05,
"loss": 2.1976,
"step": 913
},
{
"epoch": 2.74,
"learning_rate": 1.345563e-05,
"loss": 2.1953,
"step": 914
},
{
"epoch": 2.74,
"learning_rate": 1.3454925e-05,
"loss": 2.1963,
"step": 915
},
{
"epoch": 2.74,
"learning_rate": 1.345422e-05,
"loss": 2.1944,
"step": 916
},
{
"epoch": 2.75,
"learning_rate": 1.3453515000000002e-05,
"loss": 2.1934,
"step": 917
},
{
"epoch": 2.75,
"learning_rate": 1.345281e-05,
"loss": 2.1891,
"step": 918
},
{
"epoch": 2.75,
"learning_rate": 1.3452105e-05,
"loss": 2.1917,
"step": 919
},
{
"epoch": 2.76,
"learning_rate": 1.34514e-05,
"loss": 2.1911,
"step": 920
},
{
"epoch": 2.76,
"learning_rate": 1.3450695e-05,
"loss": 2.1907,
"step": 921
},
{
"epoch": 2.76,
"learning_rate": 1.344999e-05,
"loss": 2.1899,
"step": 922
},
{
"epoch": 2.76,
"learning_rate": 1.3449285e-05,
"loss": 2.1925,
"step": 923
},
{
"epoch": 2.77,
"learning_rate": 1.344858e-05,
"loss": 2.1905,
"step": 924
},
{
"epoch": 2.77,
"learning_rate": 1.3447875e-05,
"loss": 2.1925,
"step": 925
},
{
"epoch": 2.77,
"learning_rate": 1.344717e-05,
"loss": 2.1879,
"step": 926
},
{
"epoch": 2.78,
"learning_rate": 1.3446465e-05,
"loss": 2.184,
"step": 927
},
{
"epoch": 2.78,
"learning_rate": 1.344576e-05,
"loss": 2.1859,
"step": 928
},
{
"epoch": 2.78,
"learning_rate": 1.3445055000000001e-05,
"loss": 2.1845,
"step": 929
},
{
"epoch": 2.78,
"learning_rate": 1.3444350000000001e-05,
"loss": 2.1855,
"step": 930
},
{
"epoch": 2.79,
"learning_rate": 1.3443645000000001e-05,
"loss": 2.1883,
"step": 931
},
{
"epoch": 2.79,
"learning_rate": 1.344294e-05,
"loss": 2.1854,
"step": 932
},
{
"epoch": 2.79,
"learning_rate": 1.3442235e-05,
"loss": 2.1842,
"step": 933
},
{
"epoch": 2.8,
"learning_rate": 1.344153e-05,
"loss": 2.1818,
"step": 934
},
{
"epoch": 2.8,
"learning_rate": 1.3440825000000002e-05,
"loss": 2.1855,
"step": 935
},
{
"epoch": 2.8,
"learning_rate": 1.3440120000000002e-05,
"loss": 2.1844,
"step": 936
},
{
"epoch": 2.81,
"learning_rate": 1.3439415000000001e-05,
"loss": 2.1831,
"step": 937
},
{
"epoch": 2.81,
"learning_rate": 1.343871e-05,
"loss": 2.1814,
"step": 938
},
{
"epoch": 2.81,
"learning_rate": 1.3438005e-05,
"loss": 2.1791,
"step": 939
},
{
"epoch": 2.81,
"learning_rate": 1.34373e-05,
"loss": 2.1811,
"step": 940
},
{
"epoch": 2.82,
"learning_rate": 1.3436595e-05,
"loss": 2.1788,
"step": 941
},
{
"epoch": 2.82,
"learning_rate": 1.343589e-05,
"loss": 2.1797,
"step": 942
},
{
"epoch": 2.82,
"learning_rate": 1.3435185e-05,
"loss": 2.1823,
"step": 943
},
{
"epoch": 2.83,
"learning_rate": 1.343448e-05,
"loss": 2.1786,
"step": 944
},
{
"epoch": 2.83,
"learning_rate": 1.3433775e-05,
"loss": 2.1816,
"step": 945
},
{
"epoch": 2.83,
"learning_rate": 1.343307e-05,
"loss": 2.1767,
"step": 946
},
{
"epoch": 2.84,
"learning_rate": 1.3432365000000001e-05,
"loss": 2.18,
"step": 947
},
{
"epoch": 2.84,
"learning_rate": 1.3431660000000001e-05,
"loss": 2.1768,
"step": 948
},
{
"epoch": 2.84,
"learning_rate": 1.3430955000000001e-05,
"loss": 2.1794,
"step": 949
},
{
"epoch": 2.84,
"learning_rate": 1.343025e-05,
"loss": 2.1794,
"step": 950
},
{
"epoch": 2.85,
"learning_rate": 1.3429545e-05,
"loss": 2.1777,
"step": 951
},
{
"epoch": 2.85,
"learning_rate": 1.342884e-05,
"loss": 2.1757,
"step": 952
},
{
"epoch": 2.85,
"learning_rate": 1.3428135e-05,
"loss": 2.1735,
"step": 953
},
{
"epoch": 2.86,
"learning_rate": 1.3427430000000002e-05,
"loss": 2.177,
"step": 954
},
{
"epoch": 2.86,
"learning_rate": 1.3426725000000001e-05,
"loss": 2.173,
"step": 955
},
{
"epoch": 2.86,
"learning_rate": 1.3426020000000001e-05,
"loss": 2.1757,
"step": 956
},
{
"epoch": 2.87,
"learning_rate": 1.3425315000000001e-05,
"loss": 2.1717,
"step": 957
},
{
"epoch": 2.87,
"learning_rate": 1.342461e-05,
"loss": 2.1737,
"step": 958
},
{
"epoch": 2.87,
"learning_rate": 1.3423904999999999e-05,
"loss": 2.1723,
"step": 959
},
{
"epoch": 2.87,
"learning_rate": 1.34232e-05,
"loss": 2.1737,
"step": 960
},
{
"epoch": 2.88,
"learning_rate": 1.3422495e-05,
"loss": 2.1701,
"step": 961
},
{
"epoch": 2.88,
"learning_rate": 1.342179e-05,
"loss": 2.1718,
"step": 962
},
{
"epoch": 2.88,
"learning_rate": 1.3421085e-05,
"loss": 2.1727,
"step": 963
},
{
"epoch": 2.89,
"learning_rate": 1.342038e-05,
"loss": 2.1673,
"step": 964
},
{
"epoch": 2.89,
"learning_rate": 1.3419675e-05,
"loss": 2.1689,
"step": 965
},
{
"epoch": 2.89,
"learning_rate": 1.3418970000000001e-05,
"loss": 2.1687,
"step": 966
},
{
"epoch": 2.9,
"learning_rate": 1.3418265000000001e-05,
"loss": 2.1691,
"step": 967
},
{
"epoch": 2.9,
"learning_rate": 1.341756e-05,
"loss": 2.1727,
"step": 968
},
{
"epoch": 2.9,
"learning_rate": 1.3416855e-05,
"loss": 2.1678,
"step": 969
},
{
"epoch": 2.9,
"learning_rate": 1.341615e-05,
"loss": 2.1654,
"step": 970
},
{
"epoch": 2.91,
"learning_rate": 1.3415445e-05,
"loss": 2.1702,
"step": 971
},
{
"epoch": 2.91,
"learning_rate": 1.3414740000000002e-05,
"loss": 2.1675,
"step": 972
},
{
"epoch": 2.91,
"learning_rate": 1.3414035000000001e-05,
"loss": 2.1658,
"step": 973
},
{
"epoch": 2.92,
"learning_rate": 1.3413330000000001e-05,
"loss": 2.1681,
"step": 974
},
{
"epoch": 2.92,
"learning_rate": 1.3412625000000001e-05,
"loss": 2.1651,
"step": 975
},
{
"epoch": 2.92,
"learning_rate": 1.341192e-05,
"loss": 2.1674,
"step": 976
},
{
"epoch": 2.93,
"learning_rate": 1.3411215e-05,
"loss": 2.1654,
"step": 977
},
{
"epoch": 2.93,
"learning_rate": 1.341051e-05,
"loss": 2.1632,
"step": 978
},
{
"epoch": 2.93,
"learning_rate": 1.3409805e-05,
"loss": 2.1632,
"step": 979
},
{
"epoch": 2.93,
"learning_rate": 1.34091e-05,
"loss": 2.1666,
"step": 980
},
{
"epoch": 2.94,
"learning_rate": 1.3408395e-05,
"loss": 2.1618,
"step": 981
},
{
"epoch": 2.94,
"learning_rate": 1.340769e-05,
"loss": 2.1622,
"step": 982
},
{
"epoch": 2.94,
"learning_rate": 1.3406985e-05,
"loss": 2.1605,
"step": 983
},
{
"epoch": 2.95,
"learning_rate": 1.3406280000000001e-05,
"loss": 2.1599,
"step": 984
},
{
"epoch": 2.95,
"learning_rate": 1.3405575e-05,
"loss": 2.1627,
"step": 985
},
{
"epoch": 2.95,
"learning_rate": 1.340487e-05,
"loss": 2.1599,
"step": 986
},
{
"epoch": 2.96,
"learning_rate": 1.3404165e-05,
"loss": 2.1596,
"step": 987
},
{
"epoch": 2.96,
"learning_rate": 1.340346e-05,
"loss": 2.1604,
"step": 988
},
{
"epoch": 2.96,
"learning_rate": 1.3402755e-05,
"loss": 2.1608,
"step": 989
},
{
"epoch": 2.96,
"learning_rate": 1.340205e-05,
"loss": 2.1583,
"step": 990
},
{
"epoch": 2.97,
"learning_rate": 1.3401345000000001e-05,
"loss": 2.1618,
"step": 991
},
{
"epoch": 2.97,
"learning_rate": 1.3400640000000001e-05,
"loss": 2.1574,
"step": 992
},
{
"epoch": 2.97,
"learning_rate": 1.3399935000000001e-05,
"loss": 2.1654,
"step": 993
},
{
"epoch": 2.98,
"learning_rate": 1.339923e-05,
"loss": 2.1567,
"step": 994
},
{
"epoch": 2.98,
"learning_rate": 1.3398525e-05,
"loss": 2.1563,
"step": 995
},
{
"epoch": 2.98,
"learning_rate": 1.339782e-05,
"loss": 2.1574,
"step": 996
},
{
"epoch": 2.99,
"learning_rate": 1.3397115000000002e-05,
"loss": 2.1577,
"step": 997
},
{
"epoch": 2.99,
"learning_rate": 1.339641e-05,
"loss": 2.1567,
"step": 998
},
{
"epoch": 2.99,
"learning_rate": 1.3395705e-05,
"loss": 2.1572,
"step": 999
},
{
"epoch": 2.99,
"learning_rate": 1.3395e-05,
"loss": 2.1542,
"step": 1000
},
{
"epoch": 2.99,
"eval_accuracy": 0.0006947357382550335,
"eval_loss": 2.0252981185913086,
"eval_runtime": 30.5941,
"eval_samples_per_second": 9.74,
"eval_steps_per_second": 0.621,
"step": 1000
},
{
"epoch": 3.0,
"learning_rate": 1.3394295e-05,
"loss": 2.1554,
"step": 1001
},
{
"epoch": 3.0,
"learning_rate": 1.339359e-05,
"loss": 2.1527,
"step": 1002
},
{
"epoch": 3.0,
"learning_rate": 1.3392885e-05,
"loss": 2.1579,
"step": 1003
},
{
"epoch": 3.01,
"learning_rate": 1.339218e-05,
"loss": 2.1558,
"step": 1004
},
{
"epoch": 3.01,
"learning_rate": 1.3391475e-05,
"loss": 2.1526,
"step": 1005
},
{
"epoch": 3.01,
"learning_rate": 1.339077e-05,
"loss": 2.1519,
"step": 1006
},
{
"epoch": 3.02,
"learning_rate": 1.3390065e-05,
"loss": 2.1521,
"step": 1007
},
{
"epoch": 3.02,
"learning_rate": 1.338936e-05,
"loss": 2.1533,
"step": 1008
},
{
"epoch": 3.02,
"learning_rate": 1.3388655000000001e-05,
"loss": 2.1564,
"step": 1009
},
{
"epoch": 3.02,
"learning_rate": 1.3387950000000001e-05,
"loss": 2.1519,
"step": 1010
},
{
"epoch": 3.03,
"learning_rate": 1.3387245000000001e-05,
"loss": 2.1485,
"step": 1011
},
{
"epoch": 3.03,
"learning_rate": 1.338654e-05,
"loss": 2.1514,
"step": 1012
},
{
"epoch": 3.03,
"learning_rate": 1.3385835e-05,
"loss": 2.1513,
"step": 1013
},
{
"epoch": 3.04,
"learning_rate": 1.338513e-05,
"loss": 2.1527,
"step": 1014
},
{
"epoch": 3.04,
"learning_rate": 1.3384425000000002e-05,
"loss": 2.1487,
"step": 1015
},
{
"epoch": 3.04,
"learning_rate": 1.3383720000000002e-05,
"loss": 2.1501,
"step": 1016
},
{
"epoch": 3.05,
"learning_rate": 1.3383015000000001e-05,
"loss": 2.1472,
"step": 1017
},
{
"epoch": 3.05,
"learning_rate": 1.3382310000000001e-05,
"loss": 2.1503,
"step": 1018
},
{
"epoch": 3.05,
"learning_rate": 1.3381605e-05,
"loss": 2.1477,
"step": 1019
},
{
"epoch": 3.05,
"learning_rate": 1.33809e-05,
"loss": 2.1475,
"step": 1020
},
{
"epoch": 3.06,
"learning_rate": 1.3380195e-05,
"loss": 2.1451,
"step": 1021
},
{
"epoch": 3.06,
"learning_rate": 1.337949e-05,
"loss": 2.1459,
"step": 1022
},
{
"epoch": 3.06,
"learning_rate": 1.3378785e-05,
"loss": 2.1461,
"step": 1023
},
{
"epoch": 3.07,
"learning_rate": 1.337808e-05,
"loss": 2.1455,
"step": 1024
},
{
"epoch": 3.07,
"learning_rate": 1.3377375e-05,
"loss": 2.143,
"step": 1025
},
{
"epoch": 3.07,
"learning_rate": 1.337667e-05,
"loss": 2.1452,
"step": 1026
},
{
"epoch": 3.08,
"learning_rate": 1.3375965e-05,
"loss": 2.1442,
"step": 1027
},
{
"epoch": 3.08,
"learning_rate": 1.3375260000000001e-05,
"loss": 2.1416,
"step": 1028
},
{
"epoch": 3.08,
"learning_rate": 1.3374555000000001e-05,
"loss": 2.1421,
"step": 1029
},
{
"epoch": 3.08,
"learning_rate": 1.337385e-05,
"loss": 2.1419,
"step": 1030
},
{
"epoch": 3.09,
"learning_rate": 1.3373145e-05,
"loss": 2.1426,
"step": 1031
},
{
"epoch": 3.09,
"learning_rate": 1.337244e-05,
"loss": 2.1437,
"step": 1032
},
{
"epoch": 3.09,
"learning_rate": 1.3371735e-05,
"loss": 2.14,
"step": 1033
},
{
"epoch": 3.1,
"learning_rate": 1.3371030000000002e-05,
"loss": 2.1422,
"step": 1034
},
{
"epoch": 3.1,
"learning_rate": 1.3370325000000001e-05,
"loss": 2.1399,
"step": 1035
},
{
"epoch": 3.1,
"learning_rate": 1.3369620000000001e-05,
"loss": 2.1402,
"step": 1036
},
{
"epoch": 3.11,
"learning_rate": 1.3368915000000001e-05,
"loss": 2.1432,
"step": 1037
},
{
"epoch": 3.11,
"learning_rate": 1.3368210000000001e-05,
"loss": 2.1396,
"step": 1038
},
{
"epoch": 3.11,
"learning_rate": 1.3367504999999999e-05,
"loss": 2.1398,
"step": 1039
},
{
"epoch": 3.11,
"learning_rate": 1.33668e-05,
"loss": 2.1392,
"step": 1040
},
{
"epoch": 3.12,
"learning_rate": 1.3366095e-05,
"loss": 2.1372,
"step": 1041
},
{
"epoch": 3.12,
"learning_rate": 1.336539e-05,
"loss": 2.1392,
"step": 1042
},
{
"epoch": 3.12,
"learning_rate": 1.3364685e-05,
"loss": 2.1357,
"step": 1043
},
{
"epoch": 3.13,
"learning_rate": 1.336398e-05,
"loss": 2.1354,
"step": 1044
},
{
"epoch": 3.13,
"learning_rate": 1.3363275e-05,
"loss": 2.1377,
"step": 1045
},
{
"epoch": 3.13,
"learning_rate": 1.3362570000000001e-05,
"loss": 2.1379,
"step": 1046
},
{
"epoch": 3.14,
"learning_rate": 1.3361865000000001e-05,
"loss": 2.1371,
"step": 1047
},
{
"epoch": 3.14,
"learning_rate": 1.336116e-05,
"loss": 2.1383,
"step": 1048
},
{
"epoch": 3.14,
"learning_rate": 1.3360455e-05,
"loss": 2.1385,
"step": 1049
},
{
"epoch": 3.14,
"learning_rate": 1.335975e-05,
"loss": 2.136,
"step": 1050
},
{
"epoch": 3.15,
"learning_rate": 1.3359045e-05,
"loss": 2.136,
"step": 1051
},
{
"epoch": 3.15,
"learning_rate": 1.3358340000000002e-05,
"loss": 2.1356,
"step": 1052
},
{
"epoch": 3.15,
"learning_rate": 1.3357635000000001e-05,
"loss": 2.1342,
"step": 1053
},
{
"epoch": 3.16,
"learning_rate": 1.3356930000000001e-05,
"loss": 2.1321,
"step": 1054
},
{
"epoch": 3.16,
"learning_rate": 1.3356225000000001e-05,
"loss": 2.1309,
"step": 1055
},
{
"epoch": 3.16,
"learning_rate": 1.335552e-05,
"loss": 2.1334,
"step": 1056
},
{
"epoch": 3.17,
"learning_rate": 1.3354815e-05,
"loss": 2.1344,
"step": 1057
},
{
"epoch": 3.17,
"learning_rate": 1.335411e-05,
"loss": 2.1341,
"step": 1058
},
{
"epoch": 3.17,
"learning_rate": 1.3353405e-05,
"loss": 2.1346,
"step": 1059
},
{
"epoch": 3.17,
"learning_rate": 1.33527e-05,
"loss": 2.1308,
"step": 1060
},
{
"epoch": 3.18,
"learning_rate": 1.3351995e-05,
"loss": 2.1302,
"step": 1061
},
{
"epoch": 3.18,
"learning_rate": 1.335129e-05,
"loss": 2.1301,
"step": 1062
},
{
"epoch": 3.18,
"learning_rate": 1.3350585e-05,
"loss": 2.1307,
"step": 1063
},
{
"epoch": 3.19,
"learning_rate": 1.334988e-05,
"loss": 2.129,
"step": 1064
},
{
"epoch": 3.19,
"learning_rate": 1.3349175e-05,
"loss": 2.134,
"step": 1065
},
{
"epoch": 3.19,
"learning_rate": 1.334847e-05,
"loss": 2.1269,
"step": 1066
},
{
"epoch": 3.2,
"learning_rate": 1.3347765e-05,
"loss": 2.1289,
"step": 1067
},
{
"epoch": 3.2,
"learning_rate": 1.334706e-05,
"loss": 2.1304,
"step": 1068
},
{
"epoch": 3.2,
"learning_rate": 1.3346355e-05,
"loss": 2.1272,
"step": 1069
},
{
"epoch": 3.2,
"learning_rate": 1.334565e-05,
"loss": 2.1281,
"step": 1070
},
{
"epoch": 3.21,
"learning_rate": 1.3344945000000001e-05,
"loss": 2.1268,
"step": 1071
},
{
"epoch": 3.21,
"learning_rate": 1.3344240000000001e-05,
"loss": 2.1279,
"step": 1072
},
{
"epoch": 3.21,
"learning_rate": 1.3343535000000001e-05,
"loss": 2.1297,
"step": 1073
},
{
"epoch": 3.22,
"learning_rate": 1.334283e-05,
"loss": 2.1251,
"step": 1074
},
{
"epoch": 3.22,
"learning_rate": 1.3342125e-05,
"loss": 2.125,
"step": 1075
},
{
"epoch": 3.22,
"learning_rate": 1.334142e-05,
"loss": 2.126,
"step": 1076
},
{
"epoch": 3.23,
"learning_rate": 1.3340715000000002e-05,
"loss": 2.1249,
"step": 1077
},
{
"epoch": 3.23,
"learning_rate": 1.3340010000000002e-05,
"loss": 2.1218,
"step": 1078
},
{
"epoch": 3.23,
"learning_rate": 1.3339305e-05,
"loss": 2.124,
"step": 1079
},
{
"epoch": 3.23,
"learning_rate": 1.33386e-05,
"loss": 2.1261,
"step": 1080
},
{
"epoch": 3.24,
"learning_rate": 1.3337895e-05,
"loss": 2.1254,
"step": 1081
},
{
"epoch": 3.24,
"learning_rate": 1.333719e-05,
"loss": 2.1227,
"step": 1082
},
{
"epoch": 3.24,
"learning_rate": 1.3336485e-05,
"loss": 2.126,
"step": 1083
},
{
"epoch": 3.25,
"learning_rate": 1.333578e-05,
"loss": 2.1224,
"step": 1084
},
{
"epoch": 3.25,
"learning_rate": 1.3335075e-05,
"loss": 2.1197,
"step": 1085
},
{
"epoch": 3.25,
"learning_rate": 1.333437e-05,
"loss": 2.1219,
"step": 1086
},
{
"epoch": 3.26,
"learning_rate": 1.3333665e-05,
"loss": 2.1234,
"step": 1087
},
{
"epoch": 3.26,
"learning_rate": 1.333296e-05,
"loss": 2.1208,
"step": 1088
},
{
"epoch": 3.26,
"learning_rate": 1.3332255000000001e-05,
"loss": 2.1222,
"step": 1089
},
{
"epoch": 3.26,
"learning_rate": 1.3331550000000001e-05,
"loss": 2.1204,
"step": 1090
},
{
"epoch": 3.27,
"learning_rate": 1.3330845000000001e-05,
"loss": 2.1196,
"step": 1091
},
{
"epoch": 3.27,
"learning_rate": 1.333014e-05,
"loss": 2.1154,
"step": 1092
},
{
"epoch": 3.27,
"learning_rate": 1.3329435e-05,
"loss": 2.1247,
"step": 1093
},
{
"epoch": 3.28,
"learning_rate": 1.332873e-05,
"loss": 2.1211,
"step": 1094
},
{
"epoch": 3.28,
"learning_rate": 1.3328025e-05,
"loss": 2.1197,
"step": 1095
},
{
"epoch": 3.28,
"learning_rate": 1.3327320000000002e-05,
"loss": 2.1182,
"step": 1096
},
{
"epoch": 3.29,
"learning_rate": 1.3326615000000001e-05,
"loss": 2.12,
"step": 1097
},
{
"epoch": 3.29,
"learning_rate": 1.3325910000000001e-05,
"loss": 2.1179,
"step": 1098
},
{
"epoch": 3.29,
"learning_rate": 1.3325205e-05,
"loss": 2.1187,
"step": 1099
},
{
"epoch": 3.29,
"learning_rate": 1.33245e-05,
"loss": 2.1181,
"step": 1100
},
{
"epoch": 3.29,
"eval_accuracy": 0.0005570994127516778,
"eval_loss": 1.9922733306884766,
"eval_runtime": 29.2202,
"eval_samples_per_second": 10.198,
"eval_steps_per_second": 0.65,
"step": 1100
},
{
"epoch": 3.3,
"learning_rate": 1.3323795e-05,
"loss": 2.1142,
"step": 1101
},
{
"epoch": 3.3,
"learning_rate": 1.332309e-05,
"loss": 2.1128,
"step": 1102
},
{
"epoch": 3.3,
"learning_rate": 1.3322385e-05,
"loss": 2.1157,
"step": 1103
},
{
"epoch": 3.31,
"learning_rate": 1.332168e-05,
"loss": 2.1159,
"step": 1104
},
{
"epoch": 3.31,
"learning_rate": 1.3320975e-05,
"loss": 2.1139,
"step": 1105
},
{
"epoch": 3.31,
"learning_rate": 1.332027e-05,
"loss": 2.1147,
"step": 1106
},
{
"epoch": 3.31,
"learning_rate": 1.3319565e-05,
"loss": 2.1167,
"step": 1107
},
{
"epoch": 3.32,
"learning_rate": 1.3318860000000001e-05,
"loss": 2.1132,
"step": 1108
},
{
"epoch": 3.32,
"learning_rate": 1.3318155000000001e-05,
"loss": 2.1111,
"step": 1109
},
{
"epoch": 3.32,
"learning_rate": 1.331745e-05,
"loss": 2.1135,
"step": 1110
},
{
"epoch": 3.33,
"learning_rate": 1.3316745e-05,
"loss": 2.1147,
"step": 1111
},
{
"epoch": 3.33,
"learning_rate": 1.331604e-05,
"loss": 2.1113,
"step": 1112
},
{
"epoch": 3.33,
"learning_rate": 1.3315335e-05,
"loss": 2.1105,
"step": 1113
},
{
"epoch": 3.34,
"learning_rate": 1.3314630000000002e-05,
"loss": 2.1119,
"step": 1114
},
{
"epoch": 3.34,
"learning_rate": 1.3313925000000001e-05,
"loss": 2.1126,
"step": 1115
},
{
"epoch": 3.34,
"learning_rate": 1.3313220000000001e-05,
"loss": 2.1094,
"step": 1116
},
{
"epoch": 3.34,
"learning_rate": 1.3312515000000001e-05,
"loss": 2.1093,
"step": 1117
},
{
"epoch": 3.35,
"learning_rate": 1.3311810000000001e-05,
"loss": 2.1102,
"step": 1118
},
{
"epoch": 3.35,
"learning_rate": 1.3311104999999999e-05,
"loss": 2.1102,
"step": 1119
},
{
"epoch": 3.35,
"learning_rate": 1.33104e-05,
"loss": 2.1117,
"step": 1120
},
{
"epoch": 3.36,
"learning_rate": 1.3309695e-05,
"loss": 2.1104,
"step": 1121
},
{
"epoch": 3.36,
"learning_rate": 1.330899e-05,
"loss": 2.1089,
"step": 1122
},
{
"epoch": 3.36,
"learning_rate": 1.3308285e-05,
"loss": 2.1081,
"step": 1123
},
{
"epoch": 3.37,
"learning_rate": 1.330758e-05,
"loss": 2.1106,
"step": 1124
},
{
"epoch": 3.37,
"learning_rate": 1.3306875e-05,
"loss": 2.1063,
"step": 1125
},
{
"epoch": 3.37,
"learning_rate": 1.3306170000000001e-05,
"loss": 2.1093,
"step": 1126
},
{
"epoch": 3.37,
"learning_rate": 1.3305465000000001e-05,
"loss": 2.108,
"step": 1127
},
{
"epoch": 3.38,
"learning_rate": 1.330476e-05,
"loss": 2.1084,
"step": 1128
},
{
"epoch": 3.38,
"learning_rate": 1.3304055e-05,
"loss": 2.1056,
"step": 1129
},
{
"epoch": 3.38,
"learning_rate": 1.330335e-05,
"loss": 2.1072,
"step": 1130
},
{
"epoch": 3.39,
"learning_rate": 1.3302645e-05,
"loss": 2.1078,
"step": 1131
},
{
"epoch": 3.39,
"learning_rate": 1.330194e-05,
"loss": 2.1063,
"step": 1132
},
{
"epoch": 3.39,
"learning_rate": 1.3301235000000001e-05,
"loss": 2.1054,
"step": 1133
},
{
"epoch": 3.4,
"learning_rate": 1.3300530000000001e-05,
"loss": 2.1051,
"step": 1134
},
{
"epoch": 3.4,
"learning_rate": 1.3299825000000001e-05,
"loss": 2.107,
"step": 1135
},
{
"epoch": 3.4,
"learning_rate": 1.329912e-05,
"loss": 2.1014,
"step": 1136
},
{
"epoch": 3.4,
"learning_rate": 1.3298415e-05,
"loss": 2.103,
"step": 1137
},
{
"epoch": 3.41,
"learning_rate": 1.329771e-05,
"loss": 2.1053,
"step": 1138
},
{
"epoch": 3.41,
"learning_rate": 1.3297005000000002e-05,
"loss": 2.1008,
"step": 1139
},
{
"epoch": 3.41,
"learning_rate": 1.32963e-05,
"loss": 2.1021,
"step": 1140
},
{
"epoch": 3.42,
"learning_rate": 1.3295595e-05,
"loss": 2.1022,
"step": 1141
},
{
"epoch": 3.42,
"learning_rate": 1.329489e-05,
"loss": 2.1019,
"step": 1142
},
{
"epoch": 3.42,
"learning_rate": 1.3294185e-05,
"loss": 2.103,
"step": 1143
},
{
"epoch": 3.43,
"learning_rate": 1.329348e-05,
"loss": 2.104,
"step": 1144
},
{
"epoch": 3.43,
"learning_rate": 1.3292775e-05,
"loss": 2.1004,
"step": 1145
},
{
"epoch": 3.43,
"learning_rate": 1.329207e-05,
"loss": 2.1005,
"step": 1146
},
{
"epoch": 3.43,
"learning_rate": 1.3291365e-05,
"loss": 2.0983,
"step": 1147
},
{
"epoch": 3.44,
"learning_rate": 1.329066e-05,
"loss": 2.0994,
"step": 1148
},
{
"epoch": 3.44,
"learning_rate": 1.3289955e-05,
"loss": 2.1015,
"step": 1149
},
{
"epoch": 3.44,
"learning_rate": 1.328925e-05,
"loss": 2.1023,
"step": 1150
},
{
"epoch": 3.45,
"learning_rate": 1.3288545000000001e-05,
"loss": 2.1027,
"step": 1151
},
{
"epoch": 3.45,
"learning_rate": 1.3287840000000001e-05,
"loss": 2.1043,
"step": 1152
},
{
"epoch": 3.45,
"learning_rate": 1.3287135000000001e-05,
"loss": 2.0993,
"step": 1153
},
{
"epoch": 3.46,
"learning_rate": 1.328643e-05,
"loss": 2.1008,
"step": 1154
},
{
"epoch": 3.46,
"learning_rate": 1.3285725e-05,
"loss": 2.0956,
"step": 1155
},
{
"epoch": 3.46,
"learning_rate": 1.328502e-05,
"loss": 2.0944,
"step": 1156
},
{
"epoch": 3.46,
"learning_rate": 1.3284315000000002e-05,
"loss": 2.0933,
"step": 1157
},
{
"epoch": 3.47,
"learning_rate": 1.3283610000000002e-05,
"loss": 2.0965,
"step": 1158
},
{
"epoch": 3.47,
"learning_rate": 1.3282905000000002e-05,
"loss": 2.1014,
"step": 1159
},
{
"epoch": 3.47,
"learning_rate": 1.32822e-05,
"loss": 2.0943,
"step": 1160
},
{
"epoch": 3.48,
"learning_rate": 1.3281495e-05,
"loss": 2.0942,
"step": 1161
},
{
"epoch": 3.48,
"learning_rate": 1.328079e-05,
"loss": 2.0954,
"step": 1162
},
{
"epoch": 3.48,
"learning_rate": 1.3280085e-05,
"loss": 2.0963,
"step": 1163
},
{
"epoch": 3.49,
"learning_rate": 1.327938e-05,
"loss": 2.0961,
"step": 1164
},
{
"epoch": 3.49,
"learning_rate": 1.3278675e-05,
"loss": 2.0951,
"step": 1165
},
{
"epoch": 3.49,
"learning_rate": 1.327797e-05,
"loss": 2.0935,
"step": 1166
},
{
"epoch": 3.49,
"learning_rate": 1.3277265e-05,
"loss": 2.0922,
"step": 1167
},
{
"epoch": 3.5,
"learning_rate": 1.327656e-05,
"loss": 2.0945,
"step": 1168
},
{
"epoch": 3.5,
"learning_rate": 1.3275855e-05,
"loss": 2.0969,
"step": 1169
},
{
"epoch": 3.5,
"learning_rate": 1.3275150000000001e-05,
"loss": 2.0938,
"step": 1170
},
{
"epoch": 3.51,
"learning_rate": 1.3274445000000001e-05,
"loss": 2.0963,
"step": 1171
},
{
"epoch": 3.51,
"learning_rate": 1.327374e-05,
"loss": 2.0916,
"step": 1172
},
{
"epoch": 3.51,
"learning_rate": 1.3273035e-05,
"loss": 2.0926,
"step": 1173
},
{
"epoch": 3.52,
"learning_rate": 1.327233e-05,
"loss": 2.0899,
"step": 1174
},
{
"epoch": 3.52,
"learning_rate": 1.3271625e-05,
"loss": 2.0897,
"step": 1175
},
{
"epoch": 3.52,
"learning_rate": 1.3270920000000002e-05,
"loss": 2.0965,
"step": 1176
},
{
"epoch": 3.52,
"learning_rate": 1.3270215000000001e-05,
"loss": 2.0912,
"step": 1177
},
{
"epoch": 3.53,
"learning_rate": 1.3269510000000001e-05,
"loss": 2.0916,
"step": 1178
},
{
"epoch": 3.53,
"learning_rate": 1.3268805000000001e-05,
"loss": 2.0898,
"step": 1179
},
{
"epoch": 3.53,
"learning_rate": 1.32681e-05,
"loss": 2.0906,
"step": 1180
},
{
"epoch": 3.54,
"learning_rate": 1.3267394999999999e-05,
"loss": 2.0902,
"step": 1181
},
{
"epoch": 3.54,
"learning_rate": 1.326669e-05,
"loss": 2.0889,
"step": 1182
},
{
"epoch": 3.54,
"learning_rate": 1.3265985e-05,
"loss": 2.091,
"step": 1183
},
{
"epoch": 3.55,
"learning_rate": 1.326528e-05,
"loss": 2.0872,
"step": 1184
},
{
"epoch": 3.55,
"learning_rate": 1.3264575e-05,
"loss": 2.0853,
"step": 1185
},
{
"epoch": 3.55,
"learning_rate": 1.326387e-05,
"loss": 2.0863,
"step": 1186
},
{
"epoch": 3.55,
"learning_rate": 1.3263165e-05,
"loss": 2.0879,
"step": 1187
},
{
"epoch": 3.56,
"learning_rate": 1.3262460000000001e-05,
"loss": 2.0865,
"step": 1188
},
{
"epoch": 3.56,
"learning_rate": 1.3261755000000001e-05,
"loss": 2.0888,
"step": 1189
},
{
"epoch": 3.56,
"learning_rate": 1.326105e-05,
"loss": 2.0866,
"step": 1190
},
{
"epoch": 3.57,
"learning_rate": 1.3260345e-05,
"loss": 2.0848,
"step": 1191
},
{
"epoch": 3.57,
"learning_rate": 1.325964e-05,
"loss": 2.0859,
"step": 1192
},
{
"epoch": 3.57,
"learning_rate": 1.3258935e-05,
"loss": 2.0872,
"step": 1193
},
{
"epoch": 3.58,
"learning_rate": 1.3258230000000002e-05,
"loss": 2.0839,
"step": 1194
},
{
"epoch": 3.58,
"learning_rate": 1.3257525000000001e-05,
"loss": 2.0864,
"step": 1195
},
{
"epoch": 3.58,
"learning_rate": 1.3256820000000001e-05,
"loss": 2.0849,
"step": 1196
},
{
"epoch": 3.58,
"learning_rate": 1.3256115000000001e-05,
"loss": 2.0852,
"step": 1197
},
{
"epoch": 3.59,
"learning_rate": 1.3255410000000001e-05,
"loss": 2.0893,
"step": 1198
},
{
"epoch": 3.59,
"learning_rate": 1.3254705e-05,
"loss": 2.0865,
"step": 1199
},
{
"epoch": 3.59,
"learning_rate": 1.3254e-05,
"loss": 2.0823,
"step": 1200
},
{
"epoch": 3.59,
"eval_accuracy": 0.000576761744966443,
"eval_loss": 1.9653271436691284,
"eval_runtime": 31.0176,
"eval_samples_per_second": 9.607,
"eval_steps_per_second": 0.613,
"step": 1200
},
{
"epoch": 3.6,
"learning_rate": 1.3253295e-05,
"loss": 2.0842,
"step": 1201
},
{
"epoch": 3.6,
"learning_rate": 1.325259e-05,
"loss": 2.0832,
"step": 1202
},
{
"epoch": 3.6,
"learning_rate": 1.3251885e-05,
"loss": 2.0839,
"step": 1203
},
{
"epoch": 3.61,
"learning_rate": 1.325118e-05,
"loss": 2.0826,
"step": 1204
},
{
"epoch": 3.61,
"learning_rate": 1.3250475e-05,
"loss": 2.0845,
"step": 1205
},
{
"epoch": 3.61,
"learning_rate": 1.3249770000000001e-05,
"loss": 2.0829,
"step": 1206
},
{
"epoch": 3.61,
"learning_rate": 1.3249065000000001e-05,
"loss": 2.0813,
"step": 1207
},
{
"epoch": 3.62,
"learning_rate": 1.324836e-05,
"loss": 2.0803,
"step": 1208
},
{
"epoch": 3.62,
"learning_rate": 1.3247655e-05,
"loss": 2.0814,
"step": 1209
},
{
"epoch": 3.62,
"learning_rate": 1.324695e-05,
"loss": 2.0809,
"step": 1210
},
{
"epoch": 3.63,
"learning_rate": 1.3246245e-05,
"loss": 2.0833,
"step": 1211
},
{
"epoch": 3.63,
"learning_rate": 1.324554e-05,
"loss": 2.0806,
"step": 1212
},
{
"epoch": 3.63,
"learning_rate": 1.3244835000000001e-05,
"loss": 2.0807,
"step": 1213
},
{
"epoch": 3.64,
"learning_rate": 1.3244130000000001e-05,
"loss": 2.0827,
"step": 1214
},
{
"epoch": 3.64,
"learning_rate": 1.3243425000000001e-05,
"loss": 2.0779,
"step": 1215
},
{
"epoch": 3.64,
"learning_rate": 1.324272e-05,
"loss": 2.0797,
"step": 1216
},
{
"epoch": 3.64,
"learning_rate": 1.3242015e-05,
"loss": 2.0802,
"step": 1217
},
{
"epoch": 3.65,
"learning_rate": 1.324131e-05,
"loss": 2.0786,
"step": 1218
},
{
"epoch": 3.65,
"learning_rate": 1.3240605000000002e-05,
"loss": 2.0785,
"step": 1219
},
{
"epoch": 3.65,
"learning_rate": 1.32399e-05,
"loss": 2.0788,
"step": 1220
},
{
"epoch": 3.66,
"learning_rate": 1.3239195e-05,
"loss": 2.0774,
"step": 1221
},
{
"epoch": 3.66,
"learning_rate": 1.323849e-05,
"loss": 2.0786,
"step": 1222
},
{
"epoch": 3.66,
"learning_rate": 1.3237785e-05,
"loss": 2.0771,
"step": 1223
},
{
"epoch": 3.67,
"learning_rate": 1.323708e-05,
"loss": 2.0729,
"step": 1224
},
{
"epoch": 3.67,
"learning_rate": 1.3236375e-05,
"loss": 2.0794,
"step": 1225
},
{
"epoch": 3.67,
"learning_rate": 1.323567e-05,
"loss": 2.0786,
"step": 1226
},
{
"epoch": 3.67,
"learning_rate": 1.3234965e-05,
"loss": 2.0792,
"step": 1227
},
{
"epoch": 3.68,
"learning_rate": 1.323426e-05,
"loss": 2.0785,
"step": 1228
},
{
"epoch": 3.68,
"learning_rate": 1.3233555e-05,
"loss": 2.0781,
"step": 1229
},
{
"epoch": 3.68,
"learning_rate": 1.323285e-05,
"loss": 2.076,
"step": 1230
},
{
"epoch": 3.69,
"learning_rate": 1.3232145000000001e-05,
"loss": 2.0743,
"step": 1231
},
{
"epoch": 3.69,
"learning_rate": 1.3231440000000001e-05,
"loss": 2.0743,
"step": 1232
},
{
"epoch": 3.69,
"learning_rate": 1.3230735000000001e-05,
"loss": 2.0743,
"step": 1233
},
{
"epoch": 3.7,
"learning_rate": 1.323003e-05,
"loss": 2.0734,
"step": 1234
},
{
"epoch": 3.7,
"learning_rate": 1.3229325e-05,
"loss": 2.0729,
"step": 1235
},
{
"epoch": 3.7,
"learning_rate": 1.322862e-05,
"loss": 2.0755,
"step": 1236
},
{
"epoch": 3.7,
"learning_rate": 1.3227915e-05,
"loss": 2.0722,
"step": 1237
},
{
"epoch": 3.71,
"learning_rate": 1.3227210000000002e-05,
"loss": 2.0764,
"step": 1238
},
{
"epoch": 3.71,
"learning_rate": 1.3226505000000002e-05,
"loss": 2.0742,
"step": 1239
},
{
"epoch": 3.71,
"learning_rate": 1.32258e-05,
"loss": 2.0738,
"step": 1240
},
{
"epoch": 3.72,
"learning_rate": 1.3225095e-05,
"loss": 2.0682,
"step": 1241
},
{
"epoch": 3.72,
"learning_rate": 1.322439e-05,
"loss": 2.0721,
"step": 1242
},
{
"epoch": 3.72,
"learning_rate": 1.3223685e-05,
"loss": 2.0732,
"step": 1243
},
{
"epoch": 3.73,
"learning_rate": 1.322298e-05,
"loss": 2.0728,
"step": 1244
},
{
"epoch": 3.73,
"learning_rate": 1.3222275e-05,
"loss": 2.0715,
"step": 1245
},
{
"epoch": 3.73,
"learning_rate": 1.322157e-05,
"loss": 2.0662,
"step": 1246
},
{
"epoch": 3.73,
"learning_rate": 1.3220865e-05,
"loss": 2.07,
"step": 1247
},
{
"epoch": 3.74,
"learning_rate": 1.322016e-05,
"loss": 2.071,
"step": 1248
},
{
"epoch": 3.74,
"learning_rate": 1.3219455e-05,
"loss": 2.0711,
"step": 1249
},
{
"epoch": 3.74,
"learning_rate": 1.3218750000000001e-05,
"loss": 2.0696,
"step": 1250
},
{
"epoch": 3.75,
"learning_rate": 1.3218045000000001e-05,
"loss": 2.0713,
"step": 1251
},
{
"epoch": 3.75,
"learning_rate": 1.321734e-05,
"loss": 2.0673,
"step": 1252
},
{
"epoch": 3.75,
"learning_rate": 1.3216635e-05,
"loss": 2.0661,
"step": 1253
},
{
"epoch": 3.76,
"learning_rate": 1.321593e-05,
"loss": 2.0683,
"step": 1254
},
{
"epoch": 3.76,
"learning_rate": 1.3215225e-05,
"loss": 2.0719,
"step": 1255
},
{
"epoch": 3.76,
"learning_rate": 1.3214520000000002e-05,
"loss": 2.0677,
"step": 1256
},
{
"epoch": 3.76,
"learning_rate": 1.3213815000000001e-05,
"loss": 2.0684,
"step": 1257
},
{
"epoch": 3.77,
"learning_rate": 1.3213110000000001e-05,
"loss": 2.0665,
"step": 1258
},
{
"epoch": 3.77,
"learning_rate": 1.3212405000000001e-05,
"loss": 2.0635,
"step": 1259
},
{
"epoch": 3.77,
"learning_rate": 1.3211700000000001e-05,
"loss": 2.0647,
"step": 1260
},
{
"epoch": 3.78,
"learning_rate": 1.3210994999999999e-05,
"loss": 2.0655,
"step": 1261
},
{
"epoch": 3.78,
"learning_rate": 1.321029e-05,
"loss": 2.0652,
"step": 1262
},
{
"epoch": 3.78,
"learning_rate": 1.3209585e-05,
"loss": 2.0697,
"step": 1263
},
{
"epoch": 3.79,
"learning_rate": 1.320888e-05,
"loss": 2.0675,
"step": 1264
},
{
"epoch": 3.79,
"learning_rate": 1.3208175e-05,
"loss": 2.0656,
"step": 1265
},
{
"epoch": 3.79,
"learning_rate": 1.320747e-05,
"loss": 2.064,
"step": 1266
},
{
"epoch": 3.79,
"learning_rate": 1.3206765e-05,
"loss": 2.0626,
"step": 1267
},
{
"epoch": 3.8,
"learning_rate": 1.3206060000000001e-05,
"loss": 2.065,
"step": 1268
},
{
"epoch": 3.8,
"learning_rate": 1.3205355000000001e-05,
"loss": 2.0639,
"step": 1269
},
{
"epoch": 3.8,
"learning_rate": 1.320465e-05,
"loss": 2.0614,
"step": 1270
},
{
"epoch": 3.81,
"learning_rate": 1.3203945e-05,
"loss": 2.0629,
"step": 1271
},
{
"epoch": 3.81,
"learning_rate": 1.320324e-05,
"loss": 2.0658,
"step": 1272
},
{
"epoch": 3.81,
"learning_rate": 1.3202535e-05,
"loss": 2.0637,
"step": 1273
},
{
"epoch": 3.82,
"learning_rate": 1.3201830000000002e-05,
"loss": 2.0617,
"step": 1274
},
{
"epoch": 3.82,
"learning_rate": 1.3201125000000001e-05,
"loss": 2.0644,
"step": 1275
},
{
"epoch": 3.82,
"learning_rate": 1.3200420000000001e-05,
"loss": 2.0588,
"step": 1276
},
{
"epoch": 3.82,
"learning_rate": 1.3199715000000001e-05,
"loss": 2.0641,
"step": 1277
},
{
"epoch": 3.83,
"learning_rate": 1.3199010000000001e-05,
"loss": 2.0639,
"step": 1278
},
{
"epoch": 3.83,
"learning_rate": 1.3198305e-05,
"loss": 2.0622,
"step": 1279
},
{
"epoch": 3.83,
"learning_rate": 1.31976e-05,
"loss": 2.0604,
"step": 1280
},
{
"epoch": 3.84,
"learning_rate": 1.3196895e-05,
"loss": 2.0625,
"step": 1281
},
{
"epoch": 3.84,
"learning_rate": 1.319619e-05,
"loss": 2.0607,
"step": 1282
},
{
"epoch": 3.84,
"learning_rate": 1.3195485e-05,
"loss": 2.0613,
"step": 1283
},
{
"epoch": 3.85,
"learning_rate": 1.319478e-05,
"loss": 2.0611,
"step": 1284
},
{
"epoch": 3.85,
"learning_rate": 1.3194075e-05,
"loss": 2.064,
"step": 1285
},
{
"epoch": 3.85,
"learning_rate": 1.319337e-05,
"loss": 2.0584,
"step": 1286
},
{
"epoch": 3.85,
"learning_rate": 1.3192665000000001e-05,
"loss": 2.0619,
"step": 1287
},
{
"epoch": 3.86,
"learning_rate": 1.319196e-05,
"loss": 2.0599,
"step": 1288
},
{
"epoch": 3.86,
"learning_rate": 1.3191255e-05,
"loss": 2.0598,
"step": 1289
},
{
"epoch": 3.86,
"learning_rate": 1.319055e-05,
"loss": 2.0566,
"step": 1290
},
{
"epoch": 3.87,
"learning_rate": 1.3189845e-05,
"loss": 2.0591,
"step": 1291
},
{
"epoch": 3.87,
"learning_rate": 1.318914e-05,
"loss": 2.0604,
"step": 1292
},
{
"epoch": 3.87,
"learning_rate": 1.3188435000000001e-05,
"loss": 2.0593,
"step": 1293
},
{
"epoch": 3.87,
"learning_rate": 1.3187730000000001e-05,
"loss": 2.0607,
"step": 1294
},
{
"epoch": 3.88,
"learning_rate": 1.3187025000000001e-05,
"loss": 2.0561,
"step": 1295
},
{
"epoch": 3.88,
"learning_rate": 1.318632e-05,
"loss": 2.0556,
"step": 1296
},
{
"epoch": 3.88,
"learning_rate": 1.3185615e-05,
"loss": 2.0549,
"step": 1297
},
{
"epoch": 3.89,
"learning_rate": 1.318491e-05,
"loss": 2.0544,
"step": 1298
},
{
"epoch": 3.89,
"learning_rate": 1.3184205000000002e-05,
"loss": 2.0585,
"step": 1299
},
{
"epoch": 3.89,
"learning_rate": 1.3183500000000002e-05,
"loss": 2.0568,
"step": 1300
},
{
"epoch": 3.89,
"eval_accuracy": 0.0006947357382550335,
"eval_loss": 1.942599892616272,
"eval_runtime": 29.7388,
"eval_samples_per_second": 10.021,
"eval_steps_per_second": 0.639,
"step": 1300
},
{
"epoch": 3.9,
"learning_rate": 1.3182795e-05,
"loss": 2.0559,
"step": 1301
},
{
"epoch": 3.9,
"learning_rate": 1.318209e-05,
"loss": 2.0577,
"step": 1302
},
{
"epoch": 3.9,
"learning_rate": 1.3181385e-05,
"loss": 2.0558,
"step": 1303
},
{
"epoch": 3.9,
"learning_rate": 1.318068e-05,
"loss": 2.0553,
"step": 1304
},
{
"epoch": 3.91,
"learning_rate": 1.3179975e-05,
"loss": 2.0544,
"step": 1305
},
{
"epoch": 3.91,
"learning_rate": 1.317927e-05,
"loss": 2.0583,
"step": 1306
},
{
"epoch": 3.91,
"learning_rate": 1.3178565e-05,
"loss": 2.0559,
"step": 1307
},
{
"epoch": 3.92,
"learning_rate": 1.317786e-05,
"loss": 2.0549,
"step": 1308
},
{
"epoch": 3.92,
"learning_rate": 1.3177155e-05,
"loss": 2.0555,
"step": 1309
},
{
"epoch": 3.92,
"learning_rate": 1.317645e-05,
"loss": 2.0525,
"step": 1310
},
{
"epoch": 3.93,
"learning_rate": 1.3175745000000001e-05,
"loss": 2.0535,
"step": 1311
},
{
"epoch": 3.93,
"learning_rate": 1.3175040000000001e-05,
"loss": 2.0505,
"step": 1312
},
{
"epoch": 3.93,
"learning_rate": 1.3174335000000001e-05,
"loss": 2.0537,
"step": 1313
},
{
"epoch": 3.93,
"learning_rate": 1.317363e-05,
"loss": 2.0519,
"step": 1314
},
{
"epoch": 3.94,
"learning_rate": 1.3172925e-05,
"loss": 2.0548,
"step": 1315
},
{
"epoch": 3.94,
"learning_rate": 1.317222e-05,
"loss": 2.0549,
"step": 1316
},
{
"epoch": 3.94,
"learning_rate": 1.3171515e-05,
"loss": 2.0537,
"step": 1317
},
{
"epoch": 3.95,
"learning_rate": 1.3170810000000002e-05,
"loss": 2.0522,
"step": 1318
},
{
"epoch": 3.95,
"learning_rate": 1.3170105000000002e-05,
"loss": 2.0502,
"step": 1319
},
{
"epoch": 3.95,
"learning_rate": 1.3169400000000001e-05,
"loss": 2.0523,
"step": 1320
},
{
"epoch": 3.96,
"learning_rate": 1.3168695e-05,
"loss": 2.0485,
"step": 1321
},
{
"epoch": 3.96,
"learning_rate": 1.316799e-05,
"loss": 2.051,
"step": 1322
},
{
"epoch": 3.96,
"learning_rate": 1.3167284999999999e-05,
"loss": 2.0509,
"step": 1323
},
{
"epoch": 3.96,
"learning_rate": 1.316658e-05,
"loss": 2.0493,
"step": 1324
},
{
"epoch": 3.97,
"learning_rate": 1.3165875e-05,
"loss": 2.0482,
"step": 1325
},
{
"epoch": 3.97,
"learning_rate": 1.316517e-05,
"loss": 2.047,
"step": 1326
},
{
"epoch": 3.97,
"learning_rate": 1.3164465e-05,
"loss": 2.0497,
"step": 1327
},
{
"epoch": 3.98,
"learning_rate": 1.316376e-05,
"loss": 2.0488,
"step": 1328
},
{
"epoch": 3.98,
"learning_rate": 1.3163055e-05,
"loss": 2.0492,
"step": 1329
},
{
"epoch": 3.98,
"learning_rate": 1.3162350000000001e-05,
"loss": 2.0499,
"step": 1330
},
{
"epoch": 3.99,
"learning_rate": 1.3161645000000001e-05,
"loss": 2.0497,
"step": 1331
},
{
"epoch": 3.99,
"learning_rate": 1.316094e-05,
"loss": 2.0472,
"step": 1332
},
{
"epoch": 3.99,
"learning_rate": 1.3160235e-05,
"loss": 2.0466,
"step": 1333
},
{
"epoch": 3.99,
"learning_rate": 1.315953e-05,
"loss": 2.0497,
"step": 1334
},
{
"epoch": 4.0,
"learning_rate": 1.3158825e-05,
"loss": 2.0488,
"step": 1335
},
{
"epoch": 4.0,
"learning_rate": 1.3158120000000002e-05,
"loss": 2.0474,
"step": 1336
},
{
"epoch": 4.0,
"learning_rate": 1.3157415000000001e-05,
"loss": 2.0481,
"step": 1337
},
{
"epoch": 4.01,
"learning_rate": 1.3156710000000001e-05,
"loss": 2.0492,
"step": 1338
},
{
"epoch": 4.01,
"learning_rate": 1.3156005000000001e-05,
"loss": 2.0495,
"step": 1339
},
{
"epoch": 4.01,
"learning_rate": 1.3155300000000001e-05,
"loss": 2.0471,
"step": 1340
},
{
"epoch": 4.02,
"learning_rate": 1.3154594999999999e-05,
"loss": 2.0429,
"step": 1341
},
{
"epoch": 4.02,
"learning_rate": 1.315389e-05,
"loss": 2.0461,
"step": 1342
},
{
"epoch": 4.02,
"learning_rate": 1.3153185e-05,
"loss": 2.0437,
"step": 1343
},
{
"epoch": 4.02,
"learning_rate": 1.315248e-05,
"loss": 2.0421,
"step": 1344
},
{
"epoch": 4.03,
"learning_rate": 1.3151775e-05,
"loss": 2.0425,
"step": 1345
},
{
"epoch": 4.03,
"learning_rate": 1.315107e-05,
"loss": 2.0478,
"step": 1346
},
{
"epoch": 4.03,
"learning_rate": 1.3150365e-05,
"loss": 2.044,
"step": 1347
},
{
"epoch": 4.04,
"learning_rate": 1.3149660000000001e-05,
"loss": 2.0462,
"step": 1348
},
{
"epoch": 4.04,
"learning_rate": 1.3148955000000001e-05,
"loss": 2.0447,
"step": 1349
},
{
"epoch": 4.04,
"learning_rate": 1.314825e-05,
"loss": 2.0428,
"step": 1350
},
{
"epoch": 4.05,
"learning_rate": 1.3147545e-05,
"loss": 2.0416,
"step": 1351
},
{
"epoch": 4.05,
"learning_rate": 1.314684e-05,
"loss": 2.0444,
"step": 1352
},
{
"epoch": 4.05,
"learning_rate": 1.3146135e-05,
"loss": 2.0455,
"step": 1353
},
{
"epoch": 4.05,
"learning_rate": 1.314543e-05,
"loss": 2.0428,
"step": 1354
},
{
"epoch": 4.06,
"learning_rate": 1.3144725000000001e-05,
"loss": 2.0432,
"step": 1355
},
{
"epoch": 4.06,
"learning_rate": 1.3144020000000001e-05,
"loss": 2.0452,
"step": 1356
},
{
"epoch": 4.06,
"learning_rate": 1.3143315000000001e-05,
"loss": 2.041,
"step": 1357
},
{
"epoch": 4.07,
"learning_rate": 1.3142610000000001e-05,
"loss": 2.0402,
"step": 1358
},
{
"epoch": 4.07,
"learning_rate": 1.3141905e-05,
"loss": 2.0457,
"step": 1359
},
{
"epoch": 4.07,
"learning_rate": 1.31412e-05,
"loss": 2.0428,
"step": 1360
},
{
"epoch": 4.08,
"learning_rate": 1.3140495e-05,
"loss": 2.0423,
"step": 1361
},
{
"epoch": 4.08,
"learning_rate": 1.313979e-05,
"loss": 2.043,
"step": 1362
},
{
"epoch": 4.08,
"learning_rate": 1.3139085e-05,
"loss": 2.0423,
"step": 1363
},
{
"epoch": 4.08,
"learning_rate": 1.313838e-05,
"loss": 2.0381,
"step": 1364
},
{
"epoch": 4.09,
"learning_rate": 1.3137675e-05,
"loss": 2.0403,
"step": 1365
},
{
"epoch": 4.09,
"learning_rate": 1.313697e-05,
"loss": 2.0401,
"step": 1366
},
{
"epoch": 4.09,
"learning_rate": 1.3136265000000001e-05,
"loss": 2.0401,
"step": 1367
},
{
"epoch": 4.1,
"learning_rate": 1.313556e-05,
"loss": 2.0385,
"step": 1368
},
{
"epoch": 4.1,
"learning_rate": 1.3134855e-05,
"loss": 2.0399,
"step": 1369
},
{
"epoch": 4.1,
"learning_rate": 1.313415e-05,
"loss": 2.0379,
"step": 1370
},
{
"epoch": 4.11,
"learning_rate": 1.3133445e-05,
"loss": 2.037,
"step": 1371
},
{
"epoch": 4.11,
"learning_rate": 1.313274e-05,
"loss": 2.0408,
"step": 1372
},
{
"epoch": 4.11,
"learning_rate": 1.3132035000000001e-05,
"loss": 2.0397,
"step": 1373
},
{
"epoch": 4.11,
"learning_rate": 1.3131330000000001e-05,
"loss": 2.0394,
"step": 1374
},
{
"epoch": 4.12,
"learning_rate": 1.3130625000000001e-05,
"loss": 2.0417,
"step": 1375
},
{
"epoch": 4.12,
"learning_rate": 1.312992e-05,
"loss": 2.0363,
"step": 1376
},
{
"epoch": 4.12,
"learning_rate": 1.3129215e-05,
"loss": 2.0356,
"step": 1377
},
{
"epoch": 4.13,
"learning_rate": 1.312851e-05,
"loss": 2.0354,
"step": 1378
},
{
"epoch": 4.13,
"learning_rate": 1.3127805000000002e-05,
"loss": 2.0368,
"step": 1379
},
{
"epoch": 4.13,
"learning_rate": 1.3127100000000002e-05,
"loss": 2.037,
"step": 1380
},
{
"epoch": 4.14,
"learning_rate": 1.3126395000000002e-05,
"loss": 2.0358,
"step": 1381
},
{
"epoch": 4.14,
"learning_rate": 1.312569e-05,
"loss": 2.0358,
"step": 1382
},
{
"epoch": 4.14,
"learning_rate": 1.3124985e-05,
"loss": 2.0389,
"step": 1383
},
{
"epoch": 4.14,
"learning_rate": 1.312428e-05,
"loss": 2.0385,
"step": 1384
},
{
"epoch": 4.15,
"learning_rate": 1.3123575e-05,
"loss": 2.035,
"step": 1385
},
{
"epoch": 4.15,
"learning_rate": 1.312287e-05,
"loss": 2.0358,
"step": 1386
},
{
"epoch": 4.15,
"learning_rate": 1.3122165e-05,
"loss": 2.0351,
"step": 1387
},
{
"epoch": 4.16,
"learning_rate": 1.312146e-05,
"loss": 2.0349,
"step": 1388
},
{
"epoch": 4.16,
"learning_rate": 1.3120755e-05,
"loss": 2.0303,
"step": 1389
},
{
"epoch": 4.16,
"learning_rate": 1.312005e-05,
"loss": 2.0352,
"step": 1390
},
{
"epoch": 4.17,
"learning_rate": 1.3119345e-05,
"loss": 2.032,
"step": 1391
},
{
"epoch": 4.17,
"learning_rate": 1.3118640000000001e-05,
"loss": 2.0325,
"step": 1392
},
{
"epoch": 4.17,
"learning_rate": 1.3117935000000001e-05,
"loss": 2.0356,
"step": 1393
},
{
"epoch": 4.17,
"learning_rate": 1.311723e-05,
"loss": 2.0357,
"step": 1394
},
{
"epoch": 4.18,
"learning_rate": 1.3116525e-05,
"loss": 2.0305,
"step": 1395
},
{
"epoch": 4.18,
"learning_rate": 1.311582e-05,
"loss": 2.0339,
"step": 1396
},
{
"epoch": 4.18,
"learning_rate": 1.3115115e-05,
"loss": 2.0341,
"step": 1397
},
{
"epoch": 4.19,
"learning_rate": 1.3114410000000002e-05,
"loss": 2.0325,
"step": 1398
},
{
"epoch": 4.19,
"learning_rate": 1.3113705000000002e-05,
"loss": 2.0318,
"step": 1399
},
{
"epoch": 4.19,
"learning_rate": 1.3113000000000001e-05,
"loss": 2.037,
"step": 1400
},
{
"epoch": 4.19,
"eval_accuracy": 0.0007471686241610738,
"eval_loss": 1.9238648414611816,
"eval_runtime": 29.3673,
"eval_samples_per_second": 10.147,
"eval_steps_per_second": 0.647,
"step": 1400
},
{
"epoch": 4.2,
"learning_rate": 1.3112295000000001e-05,
"loss": 2.0293,
"step": 1401
},
{
"epoch": 4.2,
"learning_rate": 1.311159e-05,
"loss": 2.0303,
"step": 1402
},
{
"epoch": 4.2,
"learning_rate": 1.3110884999999999e-05,
"loss": 2.0333,
"step": 1403
},
{
"epoch": 4.2,
"learning_rate": 1.311018e-05,
"loss": 2.0299,
"step": 1404
},
{
"epoch": 4.21,
"learning_rate": 1.3109475e-05,
"loss": 2.0315,
"step": 1405
},
{
"epoch": 4.21,
"learning_rate": 1.310877e-05,
"loss": 2.0338,
"step": 1406
},
{
"epoch": 4.21,
"learning_rate": 1.3108065e-05,
"loss": 2.0305,
"step": 1407
},
{
"epoch": 4.22,
"learning_rate": 1.310736e-05,
"loss": 2.0303,
"step": 1408
},
{
"epoch": 4.22,
"learning_rate": 1.3106655e-05,
"loss": 2.0279,
"step": 1409
},
{
"epoch": 4.22,
"learning_rate": 1.3105950000000001e-05,
"loss": 2.03,
"step": 1410
},
{
"epoch": 4.23,
"learning_rate": 1.3105245000000001e-05,
"loss": 2.0307,
"step": 1411
},
{
"epoch": 4.23,
"learning_rate": 1.310454e-05,
"loss": 2.0286,
"step": 1412
},
{
"epoch": 4.23,
"learning_rate": 1.3103835e-05,
"loss": 2.0302,
"step": 1413
},
{
"epoch": 4.23,
"learning_rate": 1.310313e-05,
"loss": 2.0276,
"step": 1414
},
{
"epoch": 4.24,
"learning_rate": 1.3102425e-05,
"loss": 2.0276,
"step": 1415
},
{
"epoch": 4.24,
"learning_rate": 1.3101720000000002e-05,
"loss": 2.0288,
"step": 1416
},
{
"epoch": 4.24,
"learning_rate": 1.3101015000000001e-05,
"loss": 2.0262,
"step": 1417
},
{
"epoch": 4.25,
"learning_rate": 1.3100310000000001e-05,
"loss": 2.0292,
"step": 1418
},
{
"epoch": 4.25,
"learning_rate": 1.3099605000000001e-05,
"loss": 2.0275,
"step": 1419
},
{
"epoch": 4.25,
"learning_rate": 1.3098900000000001e-05,
"loss": 2.0279,
"step": 1420
},
{
"epoch": 4.26,
"learning_rate": 1.3098195e-05,
"loss": 2.0266,
"step": 1421
},
{
"epoch": 4.26,
"learning_rate": 1.309749e-05,
"loss": 2.028,
"step": 1422
},
{
"epoch": 4.26,
"learning_rate": 1.3096785e-05,
"loss": 2.028,
"step": 1423
},
{
"epoch": 4.26,
"learning_rate": 1.309608e-05,
"loss": 2.0238,
"step": 1424
},
{
"epoch": 4.27,
"learning_rate": 1.3095375e-05,
"loss": 2.0265,
"step": 1425
},
{
"epoch": 4.27,
"learning_rate": 1.309467e-05,
"loss": 2.0256,
"step": 1426
},
{
"epoch": 4.27,
"learning_rate": 1.3093965e-05,
"loss": 2.0249,
"step": 1427
},
{
"epoch": 4.28,
"learning_rate": 1.309326e-05,
"loss": 2.027,
"step": 1428
},
{
"epoch": 4.28,
"learning_rate": 1.3092555000000001e-05,
"loss": 2.0276,
"step": 1429
},
{
"epoch": 4.28,
"learning_rate": 1.309185e-05,
"loss": 2.0268,
"step": 1430
},
{
"epoch": 4.29,
"learning_rate": 1.3091145e-05,
"loss": 2.0279,
"step": 1431
},
{
"epoch": 4.29,
"learning_rate": 1.309044e-05,
"loss": 2.0243,
"step": 1432
},
{
"epoch": 4.29,
"learning_rate": 1.3089735e-05,
"loss": 2.0256,
"step": 1433
},
{
"epoch": 4.29,
"learning_rate": 1.308903e-05,
"loss": 2.0229,
"step": 1434
},
{
"epoch": 4.3,
"learning_rate": 1.3088325000000001e-05,
"loss": 2.0239,
"step": 1435
},
{
"epoch": 4.3,
"learning_rate": 1.3087620000000001e-05,
"loss": 2.0237,
"step": 1436
},
{
"epoch": 4.3,
"learning_rate": 1.3086915000000001e-05,
"loss": 2.0236,
"step": 1437
},
{
"epoch": 4.31,
"learning_rate": 1.3086210000000001e-05,
"loss": 2.0267,
"step": 1438
},
{
"epoch": 4.31,
"learning_rate": 1.3085505e-05,
"loss": 2.0244,
"step": 1439
},
{
"epoch": 4.31,
"learning_rate": 1.30848e-05,
"loss": 2.0231,
"step": 1440
},
{
"epoch": 4.32,
"learning_rate": 1.3084095000000002e-05,
"loss": 2.022,
"step": 1441
},
{
"epoch": 4.32,
"learning_rate": 1.308339e-05,
"loss": 2.0243,
"step": 1442
},
{
"epoch": 4.32,
"learning_rate": 1.3082685e-05,
"loss": 2.0237,
"step": 1443
},
{
"epoch": 4.32,
"learning_rate": 1.308198e-05,
"loss": 2.023,
"step": 1444
},
{
"epoch": 4.33,
"learning_rate": 1.3081275e-05,
"loss": 2.0216,
"step": 1445
},
{
"epoch": 4.33,
"learning_rate": 1.308057e-05,
"loss": 2.0212,
"step": 1446
},
{
"epoch": 4.33,
"learning_rate": 1.3079865000000001e-05,
"loss": 2.0216,
"step": 1447
},
{
"epoch": 4.34,
"learning_rate": 1.307916e-05,
"loss": 2.0205,
"step": 1448
},
{
"epoch": 4.34,
"learning_rate": 1.3078455e-05,
"loss": 2.0207,
"step": 1449
},
{
"epoch": 4.34,
"learning_rate": 1.307775e-05,
"loss": 2.0228,
"step": 1450
},
{
"epoch": 4.35,
"learning_rate": 1.3077045e-05,
"loss": 2.0231,
"step": 1451
},
{
"epoch": 4.35,
"learning_rate": 1.307634e-05,
"loss": 2.0201,
"step": 1452
},
{
"epoch": 4.35,
"learning_rate": 1.3075635000000001e-05,
"loss": 2.022,
"step": 1453
},
{
"epoch": 4.35,
"learning_rate": 1.3074930000000001e-05,
"loss": 2.0204,
"step": 1454
},
{
"epoch": 4.36,
"learning_rate": 1.3074225000000001e-05,
"loss": 2.0237,
"step": 1455
},
{
"epoch": 4.36,
"learning_rate": 1.307352e-05,
"loss": 2.0203,
"step": 1456
},
{
"epoch": 4.36,
"learning_rate": 1.3072815e-05,
"loss": 2.0193,
"step": 1457
},
{
"epoch": 4.37,
"learning_rate": 1.307211e-05,
"loss": 2.0183,
"step": 1458
},
{
"epoch": 4.37,
"learning_rate": 1.3071405e-05,
"loss": 2.022,
"step": 1459
},
{
"epoch": 4.37,
"learning_rate": 1.3070700000000002e-05,
"loss": 2.0194,
"step": 1460
},
{
"epoch": 4.38,
"learning_rate": 1.3069995000000002e-05,
"loss": 2.0188,
"step": 1461
},
{
"epoch": 4.38,
"learning_rate": 1.306929e-05,
"loss": 2.0215,
"step": 1462
},
{
"epoch": 4.38,
"learning_rate": 1.3068585e-05,
"loss": 2.021,
"step": 1463
},
{
"epoch": 4.38,
"learning_rate": 1.306788e-05,
"loss": 2.0194,
"step": 1464
},
{
"epoch": 4.39,
"learning_rate": 1.3067175e-05,
"loss": 2.0172,
"step": 1465
},
{
"epoch": 4.39,
"learning_rate": 1.306647e-05,
"loss": 2.019,
"step": 1466
},
{
"epoch": 4.39,
"learning_rate": 1.3065765e-05,
"loss": 2.018,
"step": 1467
},
{
"epoch": 4.4,
"learning_rate": 1.306506e-05,
"loss": 2.018,
"step": 1468
},
{
"epoch": 4.4,
"learning_rate": 1.3064355e-05,
"loss": 2.0159,
"step": 1469
},
{
"epoch": 4.4,
"learning_rate": 1.306365e-05,
"loss": 2.0183,
"step": 1470
},
{
"epoch": 4.41,
"learning_rate": 1.3062945e-05,
"loss": 2.0199,
"step": 1471
},
{
"epoch": 4.41,
"learning_rate": 1.3062240000000001e-05,
"loss": 2.0153,
"step": 1472
},
{
"epoch": 4.41,
"learning_rate": 1.3061535000000001e-05,
"loss": 2.016,
"step": 1473
},
{
"epoch": 4.41,
"learning_rate": 1.306083e-05,
"loss": 2.014,
"step": 1474
},
{
"epoch": 4.42,
"learning_rate": 1.3060125e-05,
"loss": 2.0183,
"step": 1475
},
{
"epoch": 4.42,
"learning_rate": 1.305942e-05,
"loss": 2.0175,
"step": 1476
},
{
"epoch": 4.42,
"learning_rate": 1.3058715e-05,
"loss": 2.0172,
"step": 1477
},
{
"epoch": 4.43,
"learning_rate": 1.3058010000000002e-05,
"loss": 2.0162,
"step": 1478
},
{
"epoch": 4.43,
"learning_rate": 1.3057305000000002e-05,
"loss": 2.0136,
"step": 1479
},
{
"epoch": 4.43,
"learning_rate": 1.3056600000000001e-05,
"loss": 2.0144,
"step": 1480
},
{
"epoch": 4.43,
"learning_rate": 1.3055895000000001e-05,
"loss": 2.0148,
"step": 1481
},
{
"epoch": 4.44,
"learning_rate": 1.305519e-05,
"loss": 2.0146,
"step": 1482
},
{
"epoch": 4.44,
"learning_rate": 1.3054484999999999e-05,
"loss": 2.0108,
"step": 1483
},
{
"epoch": 4.44,
"learning_rate": 1.305378e-05,
"loss": 2.015,
"step": 1484
},
{
"epoch": 4.45,
"learning_rate": 1.3053075e-05,
"loss": 2.0148,
"step": 1485
},
{
"epoch": 4.45,
"learning_rate": 1.305237e-05,
"loss": 2.0144,
"step": 1486
},
{
"epoch": 4.45,
"learning_rate": 1.3051665e-05,
"loss": 2.0189,
"step": 1487
},
{
"epoch": 4.46,
"learning_rate": 1.305096e-05,
"loss": 2.0152,
"step": 1488
},
{
"epoch": 4.46,
"learning_rate": 1.3050255e-05,
"loss": 2.0137,
"step": 1489
},
{
"epoch": 4.46,
"learning_rate": 1.3049550000000001e-05,
"loss": 2.0127,
"step": 1490
},
{
"epoch": 4.46,
"learning_rate": 1.3048845000000001e-05,
"loss": 2.0163,
"step": 1491
},
{
"epoch": 4.47,
"learning_rate": 1.304814e-05,
"loss": 2.0135,
"step": 1492
},
{
"epoch": 4.47,
"learning_rate": 1.3047435e-05,
"loss": 2.0138,
"step": 1493
},
{
"epoch": 4.47,
"learning_rate": 1.304673e-05,
"loss": 2.0149,
"step": 1494
},
{
"epoch": 4.48,
"learning_rate": 1.3046025e-05,
"loss": 2.0118,
"step": 1495
},
{
"epoch": 4.48,
"learning_rate": 1.304532e-05,
"loss": 2.0091,
"step": 1496
},
{
"epoch": 4.48,
"learning_rate": 1.3044615000000001e-05,
"loss": 2.0105,
"step": 1497
},
{
"epoch": 4.49,
"learning_rate": 1.3043910000000001e-05,
"loss": 2.0154,
"step": 1498
},
{
"epoch": 4.49,
"learning_rate": 1.3043205000000001e-05,
"loss": 2.0116,
"step": 1499
},
{
"epoch": 4.49,
"learning_rate": 1.3042500000000001e-05,
"loss": 2.0123,
"step": 1500
},
{
"epoch": 4.49,
"eval_accuracy": 0.0007537227348993289,
"eval_loss": 1.9082914590835571,
"eval_runtime": 28.7685,
"eval_samples_per_second": 10.359,
"eval_steps_per_second": 0.66,
"step": 1500
},
{
"epoch": 4.49,
"learning_rate": 1.3041795e-05,
"loss": 2.0104,
"step": 1501
},
{
"epoch": 4.5,
"learning_rate": 1.304109e-05,
"loss": 2.0095,
"step": 1502
},
{
"epoch": 4.5,
"learning_rate": 1.3040385e-05,
"loss": 2.0137,
"step": 1503
},
{
"epoch": 4.5,
"learning_rate": 1.303968e-05,
"loss": 2.0109,
"step": 1504
},
{
"epoch": 4.51,
"learning_rate": 1.3038975e-05,
"loss": 2.0106,
"step": 1505
},
{
"epoch": 4.51,
"learning_rate": 1.303827e-05,
"loss": 2.0108,
"step": 1506
},
{
"epoch": 4.51,
"learning_rate": 1.3037565e-05,
"loss": 2.0109,
"step": 1507
},
{
"epoch": 4.52,
"learning_rate": 1.303686e-05,
"loss": 2.0107,
"step": 1508
},
{
"epoch": 4.52,
"learning_rate": 1.3036155000000001e-05,
"loss": 2.0093,
"step": 1509
},
{
"epoch": 4.52,
"learning_rate": 1.303545e-05,
"loss": 2.0083,
"step": 1510
},
{
"epoch": 4.52,
"learning_rate": 1.3034745e-05,
"loss": 2.0118,
"step": 1511
},
{
"epoch": 4.53,
"learning_rate": 1.303404e-05,
"loss": 2.0086,
"step": 1512
},
{
"epoch": 4.53,
"learning_rate": 1.3033335e-05,
"loss": 2.0088,
"step": 1513
},
{
"epoch": 4.53,
"learning_rate": 1.303263e-05,
"loss": 2.0092,
"step": 1514
},
{
"epoch": 4.54,
"learning_rate": 1.3031925000000001e-05,
"loss": 2.009,
"step": 1515
},
{
"epoch": 4.54,
"learning_rate": 1.3031220000000001e-05,
"loss": 2.0101,
"step": 1516
},
{
"epoch": 4.54,
"learning_rate": 1.3030515000000001e-05,
"loss": 2.0079,
"step": 1517
},
{
"epoch": 4.55,
"learning_rate": 1.3029810000000001e-05,
"loss": 2.0075,
"step": 1518
},
{
"epoch": 4.55,
"learning_rate": 1.3029105e-05,
"loss": 2.0048,
"step": 1519
},
{
"epoch": 4.55,
"learning_rate": 1.30284e-05,
"loss": 2.0059,
"step": 1520
},
{
"epoch": 4.55,
"learning_rate": 1.3027695000000002e-05,
"loss": 2.0086,
"step": 1521
},
{
"epoch": 4.56,
"learning_rate": 1.3026990000000002e-05,
"loss": 2.0077,
"step": 1522
},
{
"epoch": 4.56,
"learning_rate": 1.3026285e-05,
"loss": 2.0067,
"step": 1523
},
{
"epoch": 4.56,
"learning_rate": 1.302558e-05,
"loss": 2.0095,
"step": 1524
},
{
"epoch": 4.57,
"learning_rate": 1.3024875e-05,
"loss": 2.007,
"step": 1525
},
{
"epoch": 4.57,
"learning_rate": 1.302417e-05,
"loss": 2.0076,
"step": 1526
},
{
"epoch": 4.57,
"learning_rate": 1.3023465e-05,
"loss": 2.0061,
"step": 1527
},
{
"epoch": 4.58,
"learning_rate": 1.302276e-05,
"loss": 2.0058,
"step": 1528
},
{
"epoch": 4.58,
"learning_rate": 1.3022055e-05,
"loss": 2.0083,
"step": 1529
},
{
"epoch": 4.58,
"learning_rate": 1.302135e-05,
"loss": 2.0063,
"step": 1530
},
{
"epoch": 4.58,
"learning_rate": 1.3020645e-05,
"loss": 2.0068,
"step": 1531
},
{
"epoch": 4.59,
"learning_rate": 1.301994e-05,
"loss": 2.0053,
"step": 1532
},
{
"epoch": 4.59,
"learning_rate": 1.3019235e-05,
"loss": 2.0081,
"step": 1533
},
{
"epoch": 4.59,
"learning_rate": 1.3018530000000001e-05,
"loss": 2.0066,
"step": 1534
},
{
"epoch": 4.6,
"learning_rate": 1.3017825000000001e-05,
"loss": 2.0048,
"step": 1535
},
{
"epoch": 4.6,
"learning_rate": 1.301712e-05,
"loss": 2.005,
"step": 1536
},
{
"epoch": 4.6,
"learning_rate": 1.3016415e-05,
"loss": 2.006,
"step": 1537
},
{
"epoch": 4.61,
"learning_rate": 1.301571e-05,
"loss": 2.0038,
"step": 1538
},
{
"epoch": 4.61,
"learning_rate": 1.3015005e-05,
"loss": 2.0041,
"step": 1539
},
{
"epoch": 4.61,
"learning_rate": 1.3014300000000002e-05,
"loss": 2.0027,
"step": 1540
},
{
"epoch": 4.61,
"learning_rate": 1.3013595000000002e-05,
"loss": 2.0032,
"step": 1541
},
{
"epoch": 4.62,
"learning_rate": 1.3012890000000001e-05,
"loss": 2.0013,
"step": 1542
},
{
"epoch": 4.62,
"learning_rate": 1.3012185e-05,
"loss": 2.0043,
"step": 1543
},
{
"epoch": 4.62,
"learning_rate": 1.301148e-05,
"loss": 2.005,
"step": 1544
},
{
"epoch": 4.63,
"learning_rate": 1.3010774999999999e-05,
"loss": 2.0046,
"step": 1545
},
{
"epoch": 4.63,
"learning_rate": 1.301007e-05,
"loss": 2.0002,
"step": 1546
},
{
"epoch": 4.63,
"learning_rate": 1.3009365e-05,
"loss": 2.0032,
"step": 1547
},
{
"epoch": 4.64,
"learning_rate": 1.300866e-05,
"loss": 2.0031,
"step": 1548
},
{
"epoch": 4.64,
"learning_rate": 1.3007955e-05,
"loss": 1.9991,
"step": 1549
},
{
"epoch": 4.64,
"learning_rate": 1.300725e-05,
"loss": 2.0035,
"step": 1550
},
{
"epoch": 4.64,
"learning_rate": 1.3006545e-05,
"loss": 2.0056,
"step": 1551
},
{
"epoch": 4.65,
"learning_rate": 1.3005840000000001e-05,
"loss": 2.0037,
"step": 1552
},
{
"epoch": 4.65,
"learning_rate": 1.3005135000000001e-05,
"loss": 1.9987,
"step": 1553
},
{
"epoch": 4.65,
"learning_rate": 1.300443e-05,
"loss": 1.999,
"step": 1554
},
{
"epoch": 4.66,
"learning_rate": 1.3003725e-05,
"loss": 2.003,
"step": 1555
},
{
"epoch": 4.66,
"learning_rate": 1.300302e-05,
"loss": 1.9964,
"step": 1556
},
{
"epoch": 4.66,
"learning_rate": 1.3002315e-05,
"loss": 2.0006,
"step": 1557
},
{
"epoch": 4.67,
"learning_rate": 1.3001610000000002e-05,
"loss": 2.0003,
"step": 1558
},
{
"epoch": 4.67,
"learning_rate": 1.3000905000000002e-05,
"loss": 1.9989,
"step": 1559
},
{
"epoch": 4.67,
"learning_rate": 1.3000200000000001e-05,
"loss": 1.9993,
"step": 1560
},
{
"epoch": 4.67,
"learning_rate": 1.2999495000000001e-05,
"loss": 2.001,
"step": 1561
},
{
"epoch": 4.68,
"learning_rate": 1.2998790000000001e-05,
"loss": 2.0022,
"step": 1562
},
{
"epoch": 4.68,
"learning_rate": 1.2998084999999999e-05,
"loss": 2.0003,
"step": 1563
},
{
"epoch": 4.68,
"learning_rate": 1.299738e-05,
"loss": 2.0025,
"step": 1564
},
{
"epoch": 4.69,
"learning_rate": 1.2996675e-05,
"loss": 2.0009,
"step": 1565
},
{
"epoch": 4.69,
"learning_rate": 1.299597e-05,
"loss": 1.9984,
"step": 1566
},
{
"epoch": 4.69,
"learning_rate": 1.2995265e-05,
"loss": 2.0001,
"step": 1567
},
{
"epoch": 4.7,
"learning_rate": 1.299456e-05,
"loss": 1.9977,
"step": 1568
},
{
"epoch": 4.7,
"learning_rate": 1.2993855e-05,
"loss": 1.9984,
"step": 1569
},
{
"epoch": 4.7,
"learning_rate": 1.2993150000000001e-05,
"loss": 1.9986,
"step": 1570
},
{
"epoch": 4.7,
"learning_rate": 1.2992445000000001e-05,
"loss": 1.9987,
"step": 1571
},
{
"epoch": 4.71,
"learning_rate": 1.299174e-05,
"loss": 1.9976,
"step": 1572
},
{
"epoch": 4.71,
"learning_rate": 1.2991035e-05,
"loss": 1.9958,
"step": 1573
},
{
"epoch": 4.71,
"learning_rate": 1.299033e-05,
"loss": 1.9988,
"step": 1574
},
{
"epoch": 4.72,
"learning_rate": 1.2989625e-05,
"loss": 1.9989,
"step": 1575
},
{
"epoch": 4.72,
"learning_rate": 1.298892e-05,
"loss": 1.9962,
"step": 1576
},
{
"epoch": 4.72,
"learning_rate": 1.2988215000000001e-05,
"loss": 1.9943,
"step": 1577
},
{
"epoch": 4.73,
"learning_rate": 1.2987510000000001e-05,
"loss": 1.9996,
"step": 1578
},
{
"epoch": 4.73,
"learning_rate": 1.2986805000000001e-05,
"loss": 1.9976,
"step": 1579
},
{
"epoch": 4.73,
"learning_rate": 1.2986100000000001e-05,
"loss": 1.9949,
"step": 1580
},
{
"epoch": 4.73,
"learning_rate": 1.2985395e-05,
"loss": 1.9982,
"step": 1581
},
{
"epoch": 4.74,
"learning_rate": 1.298469e-05,
"loss": 1.9989,
"step": 1582
},
{
"epoch": 4.74,
"learning_rate": 1.2983985e-05,
"loss": 1.9943,
"step": 1583
},
{
"epoch": 4.74,
"learning_rate": 1.298328e-05,
"loss": 1.9945,
"step": 1584
},
{
"epoch": 4.75,
"learning_rate": 1.2982575e-05,
"loss": 1.9955,
"step": 1585
},
{
"epoch": 4.75,
"learning_rate": 1.298187e-05,
"loss": 1.9983,
"step": 1586
},
{
"epoch": 4.75,
"learning_rate": 1.2981165e-05,
"loss": 1.9932,
"step": 1587
},
{
"epoch": 4.76,
"learning_rate": 1.298046e-05,
"loss": 1.9942,
"step": 1588
},
{
"epoch": 4.76,
"learning_rate": 1.2979755000000001e-05,
"loss": 1.9984,
"step": 1589
},
{
"epoch": 4.76,
"learning_rate": 1.297905e-05,
"loss": 1.9944,
"step": 1590
},
{
"epoch": 4.76,
"learning_rate": 1.2978345e-05,
"loss": 1.9979,
"step": 1591
},
{
"epoch": 4.77,
"learning_rate": 1.297764e-05,
"loss": 1.9967,
"step": 1592
},
{
"epoch": 4.77,
"learning_rate": 1.2976935e-05,
"loss": 1.9959,
"step": 1593
},
{
"epoch": 4.77,
"learning_rate": 1.297623e-05,
"loss": 1.9964,
"step": 1594
},
{
"epoch": 4.78,
"learning_rate": 1.2975525000000001e-05,
"loss": 1.9943,
"step": 1595
},
{
"epoch": 4.78,
"learning_rate": 1.2974820000000001e-05,
"loss": 1.9953,
"step": 1596
},
{
"epoch": 4.78,
"learning_rate": 1.2974115000000001e-05,
"loss": 1.9955,
"step": 1597
},
{
"epoch": 4.79,
"learning_rate": 1.2973410000000001e-05,
"loss": 1.9966,
"step": 1598
},
{
"epoch": 4.79,
"learning_rate": 1.2972705e-05,
"loss": 1.9955,
"step": 1599
},
{
"epoch": 4.79,
"learning_rate": 1.2972e-05,
"loss": 1.9929,
"step": 1600
},
{
"epoch": 4.79,
"eval_accuracy": 0.000779939177852349,
"eval_loss": 1.8949816226959229,
"eval_runtime": 28.9264,
"eval_samples_per_second": 10.302,
"eval_steps_per_second": 0.657,
"step": 1600
},
{
"epoch": 4.79,
"learning_rate": 1.2971295e-05,
"loss": 1.9927,
"step": 1601
},
{
"epoch": 4.8,
"learning_rate": 1.2970590000000002e-05,
"loss": 1.9927,
"step": 1602
},
{
"epoch": 4.8,
"learning_rate": 1.2969885e-05,
"loss": 1.996,
"step": 1603
},
{
"epoch": 4.8,
"learning_rate": 1.296918e-05,
"loss": 1.9936,
"step": 1604
},
{
"epoch": 4.81,
"learning_rate": 1.2968475e-05,
"loss": 1.9926,
"step": 1605
},
{
"epoch": 4.81,
"learning_rate": 1.296777e-05,
"loss": 1.9934,
"step": 1606
},
{
"epoch": 4.81,
"learning_rate": 1.2967065e-05,
"loss": 1.9945,
"step": 1607
},
{
"epoch": 4.82,
"learning_rate": 1.296636e-05,
"loss": 1.9927,
"step": 1608
},
{
"epoch": 4.82,
"learning_rate": 1.2965655e-05,
"loss": 1.9922,
"step": 1609
},
{
"epoch": 4.82,
"learning_rate": 1.296495e-05,
"loss": 1.9898,
"step": 1610
},
{
"epoch": 4.82,
"learning_rate": 1.2964245e-05,
"loss": 1.9884,
"step": 1611
},
{
"epoch": 4.83,
"learning_rate": 1.296354e-05,
"loss": 1.9962,
"step": 1612
},
{
"epoch": 4.83,
"learning_rate": 1.2962835e-05,
"loss": 1.9916,
"step": 1613
},
{
"epoch": 4.83,
"learning_rate": 1.2962130000000001e-05,
"loss": 1.9887,
"step": 1614
},
{
"epoch": 4.84,
"learning_rate": 1.2961425000000001e-05,
"loss": 1.992,
"step": 1615
},
{
"epoch": 4.84,
"learning_rate": 1.296072e-05,
"loss": 1.9911,
"step": 1616
},
{
"epoch": 4.84,
"learning_rate": 1.2960015e-05,
"loss": 1.9917,
"step": 1617
},
{
"epoch": 4.85,
"learning_rate": 1.295931e-05,
"loss": 1.9921,
"step": 1618
},
{
"epoch": 4.85,
"learning_rate": 1.2958605e-05,
"loss": 1.9908,
"step": 1619
},
{
"epoch": 4.85,
"learning_rate": 1.2957900000000002e-05,
"loss": 1.9906,
"step": 1620
},
{
"epoch": 4.85,
"learning_rate": 1.2957195000000002e-05,
"loss": 1.9879,
"step": 1621
},
{
"epoch": 4.86,
"learning_rate": 1.2956490000000001e-05,
"loss": 1.9896,
"step": 1622
},
{
"epoch": 4.86,
"learning_rate": 1.2955785e-05,
"loss": 1.9909,
"step": 1623
},
{
"epoch": 4.86,
"learning_rate": 1.295508e-05,
"loss": 1.9888,
"step": 1624
},
{
"epoch": 4.87,
"learning_rate": 1.2954374999999999e-05,
"loss": 1.9885,
"step": 1625
},
{
"epoch": 4.87,
"learning_rate": 1.295367e-05,
"loss": 1.991,
"step": 1626
},
{
"epoch": 4.87,
"learning_rate": 1.2952965e-05,
"loss": 1.9891,
"step": 1627
},
{
"epoch": 4.88,
"learning_rate": 1.295226e-05,
"loss": 1.9883,
"step": 1628
},
{
"epoch": 4.88,
"learning_rate": 1.2951555e-05,
"loss": 1.9902,
"step": 1629
},
{
"epoch": 4.88,
"learning_rate": 1.295085e-05,
"loss": 1.9905,
"step": 1630
},
{
"epoch": 4.88,
"learning_rate": 1.2950145e-05,
"loss": 1.9888,
"step": 1631
},
{
"epoch": 4.89,
"learning_rate": 1.2949440000000001e-05,
"loss": 1.9865,
"step": 1632
},
{
"epoch": 4.89,
"learning_rate": 1.2948735000000001e-05,
"loss": 1.9878,
"step": 1633
},
{
"epoch": 4.89,
"learning_rate": 1.294803e-05,
"loss": 1.9903,
"step": 1634
},
{
"epoch": 4.9,
"learning_rate": 1.2947325e-05,
"loss": 1.9896,
"step": 1635
},
{
"epoch": 4.9,
"learning_rate": 1.294662e-05,
"loss": 1.9873,
"step": 1636
},
{
"epoch": 4.9,
"learning_rate": 1.2945915e-05,
"loss": 1.9846,
"step": 1637
},
{
"epoch": 4.91,
"learning_rate": 1.2945210000000002e-05,
"loss": 1.9854,
"step": 1638
},
{
"epoch": 4.91,
"learning_rate": 1.2944505000000002e-05,
"loss": 1.9868,
"step": 1639
},
{
"epoch": 4.91,
"learning_rate": 1.2943800000000001e-05,
"loss": 1.9897,
"step": 1640
},
{
"epoch": 4.91,
"learning_rate": 1.2943095000000001e-05,
"loss": 1.9863,
"step": 1641
},
{
"epoch": 4.92,
"learning_rate": 1.2942390000000001e-05,
"loss": 1.9885,
"step": 1642
},
{
"epoch": 4.92,
"learning_rate": 1.2941685e-05,
"loss": 1.9845,
"step": 1643
},
{
"epoch": 4.92,
"learning_rate": 1.294098e-05,
"loss": 1.9877,
"step": 1644
},
{
"epoch": 4.93,
"learning_rate": 1.2940275e-05,
"loss": 1.986,
"step": 1645
},
{
"epoch": 4.93,
"learning_rate": 1.293957e-05,
"loss": 1.9872,
"step": 1646
},
{
"epoch": 4.93,
"learning_rate": 1.2938865e-05,
"loss": 1.9854,
"step": 1647
},
{
"epoch": 4.94,
"learning_rate": 1.293816e-05,
"loss": 1.9866,
"step": 1648
},
{
"epoch": 4.94,
"learning_rate": 1.2937455e-05,
"loss": 1.9863,
"step": 1649
},
{
"epoch": 4.94,
"learning_rate": 1.293675e-05,
"loss": 1.9849,
"step": 1650
},
{
"epoch": 4.94,
"learning_rate": 1.2936045000000001e-05,
"loss": 1.9851,
"step": 1651
},
{
"epoch": 4.95,
"learning_rate": 1.293534e-05,
"loss": 1.9859,
"step": 1652
},
{
"epoch": 4.95,
"learning_rate": 1.2934635e-05,
"loss": 1.9872,
"step": 1653
},
{
"epoch": 4.95,
"learning_rate": 1.293393e-05,
"loss": 1.9859,
"step": 1654
},
{
"epoch": 4.96,
"learning_rate": 1.2933225e-05,
"loss": 1.9878,
"step": 1655
},
{
"epoch": 4.96,
"learning_rate": 1.293252e-05,
"loss": 1.9838,
"step": 1656
},
{
"epoch": 4.96,
"learning_rate": 1.2931815000000001e-05,
"loss": 1.9852,
"step": 1657
},
{
"epoch": 4.97,
"learning_rate": 1.2931110000000001e-05,
"loss": 1.9826,
"step": 1658
},
{
"epoch": 4.97,
"learning_rate": 1.2930405000000001e-05,
"loss": 1.9834,
"step": 1659
},
{
"epoch": 4.97,
"learning_rate": 1.2929700000000001e-05,
"loss": 1.9837,
"step": 1660
},
{
"epoch": 4.97,
"learning_rate": 1.2928995e-05,
"loss": 1.9833,
"step": 1661
},
{
"epoch": 4.98,
"learning_rate": 1.292829e-05,
"loss": 1.9826,
"step": 1662
},
{
"epoch": 4.98,
"learning_rate": 1.2927585000000002e-05,
"loss": 1.9814,
"step": 1663
},
{
"epoch": 4.98,
"learning_rate": 1.292688e-05,
"loss": 1.9803,
"step": 1664
},
{
"epoch": 4.99,
"learning_rate": 1.2926175e-05,
"loss": 1.982,
"step": 1665
},
{
"epoch": 4.99,
"learning_rate": 1.292547e-05,
"loss": 1.9823,
"step": 1666
},
{
"epoch": 4.99,
"learning_rate": 1.2924765e-05,
"loss": 1.9815,
"step": 1667
},
{
"epoch": 4.99,
"learning_rate": 1.292406e-05,
"loss": 1.9832,
"step": 1668
},
{
"epoch": 5.0,
"learning_rate": 1.2923355000000001e-05,
"loss": 1.9859,
"step": 1669
},
{
"epoch": 5.0,
"learning_rate": 1.292265e-05,
"loss": 1.9858,
"step": 1670
},
{
"epoch": 5.0,
"learning_rate": 1.2921945e-05,
"loss": 1.9822,
"step": 1671
},
{
"epoch": 5.01,
"learning_rate": 1.292124e-05,
"loss": 1.9809,
"step": 1672
},
{
"epoch": 5.01,
"learning_rate": 1.2920535e-05,
"loss": 1.986,
"step": 1673
},
{
"epoch": 5.01,
"learning_rate": 1.291983e-05,
"loss": 1.9818,
"step": 1674
},
{
"epoch": 5.02,
"learning_rate": 1.2919125000000001e-05,
"loss": 1.9813,
"step": 1675
},
{
"epoch": 5.02,
"learning_rate": 1.2918420000000001e-05,
"loss": 1.9841,
"step": 1676
},
{
"epoch": 5.02,
"learning_rate": 1.2917715000000001e-05,
"loss": 1.9815,
"step": 1677
},
{
"epoch": 5.02,
"learning_rate": 1.2917010000000001e-05,
"loss": 1.9809,
"step": 1678
},
{
"epoch": 5.03,
"learning_rate": 1.2916305e-05,
"loss": 1.9808,
"step": 1679
},
{
"epoch": 5.03,
"learning_rate": 1.29156e-05,
"loss": 1.9816,
"step": 1680
},
{
"epoch": 5.03,
"learning_rate": 1.2914895e-05,
"loss": 1.9797,
"step": 1681
},
{
"epoch": 5.04,
"learning_rate": 1.2914190000000002e-05,
"loss": 1.984,
"step": 1682
},
{
"epoch": 5.04,
"learning_rate": 1.2913485000000002e-05,
"loss": 1.9808,
"step": 1683
},
{
"epoch": 5.04,
"learning_rate": 1.291278e-05,
"loss": 1.9805,
"step": 1684
},
{
"epoch": 5.05,
"learning_rate": 1.2912075e-05,
"loss": 1.9792,
"step": 1685
},
{
"epoch": 5.05,
"learning_rate": 1.291137e-05,
"loss": 1.9794,
"step": 1686
},
{
"epoch": 5.05,
"learning_rate": 1.2910664999999999e-05,
"loss": 1.9806,
"step": 1687
},
{
"epoch": 5.05,
"learning_rate": 1.290996e-05,
"loss": 1.9801,
"step": 1688
},
{
"epoch": 5.06,
"learning_rate": 1.2909255e-05,
"loss": 1.9777,
"step": 1689
},
{
"epoch": 5.06,
"learning_rate": 1.290855e-05,
"loss": 1.98,
"step": 1690
},
{
"epoch": 5.06,
"learning_rate": 1.2907845e-05,
"loss": 1.9799,
"step": 1691
},
{
"epoch": 5.07,
"learning_rate": 1.290714e-05,
"loss": 1.9766,
"step": 1692
},
{
"epoch": 5.07,
"learning_rate": 1.2906435e-05,
"loss": 1.9809,
"step": 1693
},
{
"epoch": 5.07,
"learning_rate": 1.2905730000000001e-05,
"loss": 1.9811,
"step": 1694
},
{
"epoch": 5.08,
"learning_rate": 1.2905025000000001e-05,
"loss": 1.9801,
"step": 1695
},
{
"epoch": 5.08,
"learning_rate": 1.290432e-05,
"loss": 1.9766,
"step": 1696
},
{
"epoch": 5.08,
"learning_rate": 1.2903615e-05,
"loss": 1.9767,
"step": 1697
},
{
"epoch": 5.08,
"learning_rate": 1.290291e-05,
"loss": 1.9764,
"step": 1698
},
{
"epoch": 5.09,
"learning_rate": 1.2902205e-05,
"loss": 1.9775,
"step": 1699
},
{
"epoch": 5.09,
"learning_rate": 1.2901500000000002e-05,
"loss": 1.9811,
"step": 1700
},
{
"epoch": 5.09,
"eval_accuracy": 0.0007930473993288591,
"eval_loss": 1.883575677871704,
"eval_runtime": 38.2512,
"eval_samples_per_second": 7.791,
"eval_steps_per_second": 0.497,
"step": 1700
},
{
"epoch": 5.09,
"learning_rate": 1.2900795000000002e-05,
"loss": 1.9771,
"step": 1701
},
{
"epoch": 5.1,
"learning_rate": 1.2900090000000001e-05,
"loss": 1.9774,
"step": 1702
},
{
"epoch": 5.1,
"learning_rate": 1.2899385000000001e-05,
"loss": 1.9789,
"step": 1703
},
{
"epoch": 5.1,
"learning_rate": 1.289868e-05,
"loss": 1.9769,
"step": 1704
},
{
"epoch": 5.11,
"learning_rate": 1.2897974999999999e-05,
"loss": 1.9749,
"step": 1705
},
{
"epoch": 5.11,
"learning_rate": 1.289727e-05,
"loss": 1.9771,
"step": 1706
},
{
"epoch": 5.11,
"learning_rate": 1.2896565e-05,
"loss": 1.9759,
"step": 1707
},
{
"epoch": 5.11,
"learning_rate": 1.289586e-05,
"loss": 1.978,
"step": 1708
},
{
"epoch": 5.12,
"learning_rate": 1.2895155e-05,
"loss": 1.9785,
"step": 1709
},
{
"epoch": 5.12,
"learning_rate": 1.289445e-05,
"loss": 1.9779,
"step": 1710
},
{
"epoch": 5.12,
"learning_rate": 1.2893745e-05,
"loss": 1.9766,
"step": 1711
},
{
"epoch": 5.13,
"learning_rate": 1.2893040000000001e-05,
"loss": 1.9751,
"step": 1712
},
{
"epoch": 5.13,
"learning_rate": 1.2892335000000001e-05,
"loss": 1.9734,
"step": 1713
},
{
"epoch": 5.13,
"learning_rate": 1.289163e-05,
"loss": 1.9747,
"step": 1714
},
{
"epoch": 5.14,
"learning_rate": 1.2890925e-05,
"loss": 1.9766,
"step": 1715
},
{
"epoch": 5.14,
"learning_rate": 1.289022e-05,
"loss": 1.9767,
"step": 1716
},
{
"epoch": 5.14,
"learning_rate": 1.2889515e-05,
"loss": 1.9775,
"step": 1717
},
{
"epoch": 5.14,
"learning_rate": 1.288881e-05,
"loss": 1.9739,
"step": 1718
},
{
"epoch": 5.15,
"learning_rate": 1.2888105000000002e-05,
"loss": 1.9761,
"step": 1719
},
{
"epoch": 5.15,
"learning_rate": 1.2887400000000001e-05,
"loss": 1.9761,
"step": 1720
},
{
"epoch": 5.15,
"learning_rate": 1.2886695000000001e-05,
"loss": 1.9763,
"step": 1721
},
{
"epoch": 5.16,
"learning_rate": 1.2885990000000001e-05,
"loss": 1.9746,
"step": 1722
},
{
"epoch": 5.16,
"learning_rate": 1.2885285e-05,
"loss": 1.9769,
"step": 1723
},
{
"epoch": 5.16,
"learning_rate": 1.2884579999999999e-05,
"loss": 1.9755,
"step": 1724
},
{
"epoch": 5.17,
"learning_rate": 1.2883875e-05,
"loss": 1.9744,
"step": 1725
},
{
"epoch": 5.17,
"learning_rate": 1.288317e-05,
"loss": 1.9725,
"step": 1726
},
{
"epoch": 5.17,
"learning_rate": 1.2882465e-05,
"loss": 1.976,
"step": 1727
},
{
"epoch": 5.17,
"learning_rate": 1.288176e-05,
"loss": 1.9747,
"step": 1728
},
{
"epoch": 5.18,
"learning_rate": 1.2881055e-05,
"loss": 1.9711,
"step": 1729
},
{
"epoch": 5.18,
"learning_rate": 1.288035e-05,
"loss": 1.9739,
"step": 1730
},
{
"epoch": 5.18,
"learning_rate": 1.2879645000000001e-05,
"loss": 1.9733,
"step": 1731
},
{
"epoch": 5.19,
"learning_rate": 1.287894e-05,
"loss": 1.9728,
"step": 1732
},
{
"epoch": 5.19,
"learning_rate": 1.2878235e-05,
"loss": 1.9742,
"step": 1733
},
{
"epoch": 5.19,
"learning_rate": 1.287753e-05,
"loss": 1.9744,
"step": 1734
},
{
"epoch": 5.2,
"learning_rate": 1.2876825e-05,
"loss": 1.9727,
"step": 1735
},
{
"epoch": 5.2,
"learning_rate": 1.287612e-05,
"loss": 1.9701,
"step": 1736
},
{
"epoch": 5.2,
"learning_rate": 1.2875415000000001e-05,
"loss": 1.9753,
"step": 1737
},
{
"epoch": 5.2,
"learning_rate": 1.2874710000000001e-05,
"loss": 1.9705,
"step": 1738
},
{
"epoch": 5.21,
"learning_rate": 1.2874005000000001e-05,
"loss": 1.9734,
"step": 1739
},
{
"epoch": 5.21,
"learning_rate": 1.2873300000000001e-05,
"loss": 1.972,
"step": 1740
},
{
"epoch": 5.21,
"learning_rate": 1.2872595e-05,
"loss": 1.974,
"step": 1741
},
{
"epoch": 5.22,
"learning_rate": 1.287189e-05,
"loss": 1.9743,
"step": 1742
},
{
"epoch": 5.22,
"learning_rate": 1.2871185000000002e-05,
"loss": 1.974,
"step": 1743
},
{
"epoch": 5.22,
"learning_rate": 1.287048e-05,
"loss": 1.9694,
"step": 1744
},
{
"epoch": 5.23,
"learning_rate": 1.2869775e-05,
"loss": 1.972,
"step": 1745
},
{
"epoch": 5.23,
"learning_rate": 1.286907e-05,
"loss": 1.9708,
"step": 1746
},
{
"epoch": 5.23,
"learning_rate": 1.2868365e-05,
"loss": 1.9738,
"step": 1747
},
{
"epoch": 5.23,
"learning_rate": 1.286766e-05,
"loss": 1.9715,
"step": 1748
},
{
"epoch": 5.24,
"learning_rate": 1.2866955000000001e-05,
"loss": 1.975,
"step": 1749
},
{
"epoch": 5.24,
"learning_rate": 1.286625e-05,
"loss": 1.9735,
"step": 1750
},
{
"epoch": 5.24,
"learning_rate": 1.2865545e-05,
"loss": 1.9706,
"step": 1751
},
{
"epoch": 5.25,
"learning_rate": 1.286484e-05,
"loss": 1.973,
"step": 1752
},
{
"epoch": 5.25,
"learning_rate": 1.2864135e-05,
"loss": 1.9702,
"step": 1753
},
{
"epoch": 5.25,
"learning_rate": 1.286343e-05,
"loss": 1.9692,
"step": 1754
},
{
"epoch": 5.26,
"learning_rate": 1.2862725e-05,
"loss": 1.9703,
"step": 1755
},
{
"epoch": 5.26,
"learning_rate": 1.2862020000000001e-05,
"loss": 1.968,
"step": 1756
},
{
"epoch": 5.26,
"learning_rate": 1.2861315000000001e-05,
"loss": 1.9736,
"step": 1757
},
{
"epoch": 5.26,
"learning_rate": 1.2860610000000001e-05,
"loss": 1.9679,
"step": 1758
},
{
"epoch": 5.27,
"learning_rate": 1.2859905e-05,
"loss": 1.9717,
"step": 1759
},
{
"epoch": 5.27,
"learning_rate": 1.28592e-05,
"loss": 1.9696,
"step": 1760
},
{
"epoch": 5.27,
"learning_rate": 1.2858495e-05,
"loss": 1.9701,
"step": 1761
},
{
"epoch": 5.28,
"learning_rate": 1.2857790000000002e-05,
"loss": 1.9714,
"step": 1762
},
{
"epoch": 5.28,
"learning_rate": 1.2857085000000002e-05,
"loss": 1.9703,
"step": 1763
},
{
"epoch": 5.28,
"learning_rate": 1.2856380000000001e-05,
"loss": 1.9696,
"step": 1764
},
{
"epoch": 5.29,
"learning_rate": 1.2855675e-05,
"loss": 1.9701,
"step": 1765
},
{
"epoch": 5.29,
"learning_rate": 1.285497e-05,
"loss": 1.9678,
"step": 1766
},
{
"epoch": 5.29,
"learning_rate": 1.2854264999999999e-05,
"loss": 1.9677,
"step": 1767
},
{
"epoch": 5.29,
"learning_rate": 1.285356e-05,
"loss": 1.9695,
"step": 1768
},
{
"epoch": 5.3,
"learning_rate": 1.2852855e-05,
"loss": 1.9688,
"step": 1769
},
{
"epoch": 5.3,
"learning_rate": 1.285215e-05,
"loss": 1.9694,
"step": 1770
},
{
"epoch": 5.3,
"learning_rate": 1.2851445e-05,
"loss": 1.9679,
"step": 1771
},
{
"epoch": 5.31,
"learning_rate": 1.285074e-05,
"loss": 1.9699,
"step": 1772
},
{
"epoch": 5.31,
"learning_rate": 1.2850035e-05,
"loss": 1.9698,
"step": 1773
},
{
"epoch": 5.31,
"learning_rate": 1.2849330000000001e-05,
"loss": 1.9702,
"step": 1774
},
{
"epoch": 5.32,
"learning_rate": 1.2848625000000001e-05,
"loss": 1.9658,
"step": 1775
},
{
"epoch": 5.32,
"learning_rate": 1.284792e-05,
"loss": 1.9674,
"step": 1776
},
{
"epoch": 5.32,
"learning_rate": 1.2847215e-05,
"loss": 1.9716,
"step": 1777
},
{
"epoch": 5.32,
"learning_rate": 1.284651e-05,
"loss": 1.9652,
"step": 1778
},
{
"epoch": 5.33,
"learning_rate": 1.2845805e-05,
"loss": 1.9701,
"step": 1779
},
{
"epoch": 5.33,
"learning_rate": 1.2845100000000002e-05,
"loss": 1.9654,
"step": 1780
},
{
"epoch": 5.33,
"learning_rate": 1.2844395000000002e-05,
"loss": 1.965,
"step": 1781
},
{
"epoch": 5.34,
"learning_rate": 1.2843690000000001e-05,
"loss": 1.9662,
"step": 1782
},
{
"epoch": 5.34,
"learning_rate": 1.2842985000000001e-05,
"loss": 1.9666,
"step": 1783
},
{
"epoch": 5.34,
"learning_rate": 1.2842280000000001e-05,
"loss": 1.9657,
"step": 1784
},
{
"epoch": 5.35,
"learning_rate": 1.2841574999999999e-05,
"loss": 1.9692,
"step": 1785
},
{
"epoch": 5.35,
"learning_rate": 1.284087e-05,
"loss": 1.9661,
"step": 1786
},
{
"epoch": 5.35,
"learning_rate": 1.2840165e-05,
"loss": 1.9671,
"step": 1787
},
{
"epoch": 5.35,
"learning_rate": 1.283946e-05,
"loss": 1.9681,
"step": 1788
},
{
"epoch": 5.36,
"learning_rate": 1.2838755e-05,
"loss": 1.9653,
"step": 1789
},
{
"epoch": 5.36,
"learning_rate": 1.283805e-05,
"loss": 1.9678,
"step": 1790
},
{
"epoch": 5.36,
"learning_rate": 1.2837345e-05,
"loss": 1.9666,
"step": 1791
},
{
"epoch": 5.37,
"learning_rate": 1.283664e-05,
"loss": 1.9647,
"step": 1792
},
{
"epoch": 5.37,
"learning_rate": 1.2835935000000001e-05,
"loss": 1.9645,
"step": 1793
},
{
"epoch": 5.37,
"learning_rate": 1.283523e-05,
"loss": 1.965,
"step": 1794
},
{
"epoch": 5.38,
"learning_rate": 1.2834525e-05,
"loss": 1.9646,
"step": 1795
},
{
"epoch": 5.38,
"learning_rate": 1.283382e-05,
"loss": 1.9681,
"step": 1796
},
{
"epoch": 5.38,
"learning_rate": 1.2833115e-05,
"loss": 1.9684,
"step": 1797
},
{
"epoch": 5.38,
"learning_rate": 1.283241e-05,
"loss": 1.9648,
"step": 1798
},
{
"epoch": 5.39,
"learning_rate": 1.2831705000000002e-05,
"loss": 1.9663,
"step": 1799
},
{
"epoch": 5.39,
"learning_rate": 1.2831000000000001e-05,
"loss": 1.9639,
"step": 1800
},
{
"epoch": 5.39,
"eval_accuracy": 0.0007537227348993289,
"eval_loss": 1.8735462427139282,
"eval_runtime": 34.1757,
"eval_samples_per_second": 8.72,
"eval_steps_per_second": 0.556,
"step": 1800
},
{
"epoch": 5.39,
"learning_rate": 1.2830295000000001e-05,
"loss": 1.9634,
"step": 1801
},
{
"epoch": 5.4,
"learning_rate": 1.2829590000000001e-05,
"loss": 1.9626,
"step": 1802
},
{
"epoch": 5.4,
"learning_rate": 1.2828885e-05,
"loss": 1.964,
"step": 1803
},
{
"epoch": 5.4,
"learning_rate": 1.282818e-05,
"loss": 1.9631,
"step": 1804
},
{
"epoch": 5.41,
"learning_rate": 1.2827475e-05,
"loss": 1.965,
"step": 1805
},
{
"epoch": 5.41,
"learning_rate": 1.282677e-05,
"loss": 1.964,
"step": 1806
},
{
"epoch": 5.41,
"learning_rate": 1.2826065e-05,
"loss": 1.9649,
"step": 1807
},
{
"epoch": 5.41,
"learning_rate": 1.282536e-05,
"loss": 1.9636,
"step": 1808
},
{
"epoch": 5.42,
"learning_rate": 1.2824655e-05,
"loss": 1.964,
"step": 1809
},
{
"epoch": 5.42,
"learning_rate": 1.282395e-05,
"loss": 1.9624,
"step": 1810
},
{
"epoch": 5.42,
"learning_rate": 1.2823245000000001e-05,
"loss": 1.9645,
"step": 1811
},
{
"epoch": 5.43,
"learning_rate": 1.282254e-05,
"loss": 1.965,
"step": 1812
},
{
"epoch": 5.43,
"learning_rate": 1.2821835e-05,
"loss": 1.9622,
"step": 1813
},
{
"epoch": 5.43,
"learning_rate": 1.282113e-05,
"loss": 1.963,
"step": 1814
},
{
"epoch": 5.44,
"learning_rate": 1.2820425e-05,
"loss": 1.9622,
"step": 1815
},
{
"epoch": 5.44,
"learning_rate": 1.281972e-05,
"loss": 1.9641,
"step": 1816
},
{
"epoch": 5.44,
"learning_rate": 1.2819015000000001e-05,
"loss": 1.9615,
"step": 1817
},
{
"epoch": 5.44,
"learning_rate": 1.2818310000000001e-05,
"loss": 1.9632,
"step": 1818
},
{
"epoch": 5.45,
"learning_rate": 1.2817605000000001e-05,
"loss": 1.962,
"step": 1819
},
{
"epoch": 5.45,
"learning_rate": 1.2816900000000001e-05,
"loss": 1.962,
"step": 1820
},
{
"epoch": 5.45,
"learning_rate": 1.2816195e-05,
"loss": 1.9612,
"step": 1821
},
{
"epoch": 5.46,
"learning_rate": 1.281549e-05,
"loss": 1.9616,
"step": 1822
},
{
"epoch": 5.46,
"learning_rate": 1.2814785e-05,
"loss": 1.9606,
"step": 1823
},
{
"epoch": 5.46,
"learning_rate": 1.2814080000000002e-05,
"loss": 1.9617,
"step": 1824
},
{
"epoch": 5.47,
"learning_rate": 1.2813375e-05,
"loss": 1.9583,
"step": 1825
},
{
"epoch": 5.47,
"learning_rate": 1.281267e-05,
"loss": 1.9596,
"step": 1826
},
{
"epoch": 5.47,
"learning_rate": 1.2811965e-05,
"loss": 1.9612,
"step": 1827
},
{
"epoch": 5.47,
"learning_rate": 1.281126e-05,
"loss": 1.9617,
"step": 1828
},
{
"epoch": 5.48,
"learning_rate": 1.2810555000000001e-05,
"loss": 1.9634,
"step": 1829
},
{
"epoch": 5.48,
"learning_rate": 1.280985e-05,
"loss": 1.9612,
"step": 1830
},
{
"epoch": 5.48,
"learning_rate": 1.2809145e-05,
"loss": 1.96,
"step": 1831
},
{
"epoch": 5.49,
"learning_rate": 1.280844e-05,
"loss": 1.9606,
"step": 1832
},
{
"epoch": 5.49,
"learning_rate": 1.2807735e-05,
"loss": 1.9595,
"step": 1833
},
{
"epoch": 5.49,
"learning_rate": 1.280703e-05,
"loss": 1.959,
"step": 1834
},
{
"epoch": 5.5,
"learning_rate": 1.2806325e-05,
"loss": 1.9605,
"step": 1835
},
{
"epoch": 5.5,
"learning_rate": 1.2805620000000001e-05,
"loss": 1.9581,
"step": 1836
},
{
"epoch": 5.5,
"learning_rate": 1.2804915000000001e-05,
"loss": 1.9604,
"step": 1837
},
{
"epoch": 5.5,
"learning_rate": 1.2804210000000001e-05,
"loss": 1.9566,
"step": 1838
},
{
"epoch": 5.51,
"learning_rate": 1.2803505e-05,
"loss": 1.9599,
"step": 1839
},
{
"epoch": 5.51,
"learning_rate": 1.28028e-05,
"loss": 1.96,
"step": 1840
},
{
"epoch": 5.51,
"learning_rate": 1.2802095e-05,
"loss": 1.961,
"step": 1841
},
{
"epoch": 5.52,
"learning_rate": 1.2801390000000002e-05,
"loss": 1.9595,
"step": 1842
},
{
"epoch": 5.52,
"learning_rate": 1.2800685000000002e-05,
"loss": 1.9593,
"step": 1843
},
{
"epoch": 5.52,
"learning_rate": 1.2799980000000001e-05,
"loss": 1.9573,
"step": 1844
},
{
"epoch": 5.52,
"learning_rate": 1.2799275e-05,
"loss": 1.9584,
"step": 1845
},
{
"epoch": 5.53,
"learning_rate": 1.279857e-05,
"loss": 1.96,
"step": 1846
},
{
"epoch": 5.53,
"learning_rate": 1.2797864999999999e-05,
"loss": 1.9599,
"step": 1847
},
{
"epoch": 5.53,
"learning_rate": 1.279716e-05,
"loss": 1.9595,
"step": 1848
},
{
"epoch": 5.54,
"learning_rate": 1.2796455e-05,
"loss": 1.9579,
"step": 1849
},
{
"epoch": 5.54,
"learning_rate": 1.279575e-05,
"loss": 1.9554,
"step": 1850
},
{
"epoch": 5.54,
"learning_rate": 1.2795045e-05,
"loss": 1.96,
"step": 1851
},
{
"epoch": 5.55,
"learning_rate": 1.279434e-05,
"loss": 1.9584,
"step": 1852
},
{
"epoch": 5.55,
"learning_rate": 1.2793635e-05,
"loss": 1.9579,
"step": 1853
},
{
"epoch": 5.55,
"learning_rate": 1.2792930000000001e-05,
"loss": 1.9585,
"step": 1854
},
{
"epoch": 5.55,
"learning_rate": 1.2792225000000001e-05,
"loss": 1.9596,
"step": 1855
},
{
"epoch": 5.56,
"learning_rate": 1.279152e-05,
"loss": 1.9557,
"step": 1856
},
{
"epoch": 5.56,
"learning_rate": 1.2790815e-05,
"loss": 1.9581,
"step": 1857
},
{
"epoch": 5.56,
"learning_rate": 1.279011e-05,
"loss": 1.9572,
"step": 1858
},
{
"epoch": 5.57,
"learning_rate": 1.2789405e-05,
"loss": 1.9542,
"step": 1859
},
{
"epoch": 5.57,
"learning_rate": 1.27887e-05,
"loss": 1.9575,
"step": 1860
},
{
"epoch": 5.57,
"learning_rate": 1.2787995000000002e-05,
"loss": 1.9539,
"step": 1861
},
{
"epoch": 5.58,
"learning_rate": 1.2787290000000001e-05,
"loss": 1.9567,
"step": 1862
},
{
"epoch": 5.58,
"learning_rate": 1.2786585000000001e-05,
"loss": 1.9573,
"step": 1863
},
{
"epoch": 5.58,
"learning_rate": 1.2785880000000001e-05,
"loss": 1.9578,
"step": 1864
},
{
"epoch": 5.58,
"learning_rate": 1.2785174999999999e-05,
"loss": 1.9556,
"step": 1865
},
{
"epoch": 5.59,
"learning_rate": 1.278447e-05,
"loss": 1.958,
"step": 1866
},
{
"epoch": 5.59,
"learning_rate": 1.2783765e-05,
"loss": 1.9587,
"step": 1867
},
{
"epoch": 5.59,
"learning_rate": 1.278306e-05,
"loss": 1.9584,
"step": 1868
},
{
"epoch": 5.6,
"learning_rate": 1.2782355e-05,
"loss": 1.9545,
"step": 1869
},
{
"epoch": 5.6,
"learning_rate": 1.278165e-05,
"loss": 1.9579,
"step": 1870
},
{
"epoch": 5.6,
"learning_rate": 1.2780945e-05,
"loss": 1.9528,
"step": 1871
},
{
"epoch": 5.61,
"learning_rate": 1.278024e-05,
"loss": 1.9569,
"step": 1872
},
{
"epoch": 5.61,
"learning_rate": 1.2779535000000001e-05,
"loss": 1.9545,
"step": 1873
},
{
"epoch": 5.61,
"learning_rate": 1.277883e-05,
"loss": 1.9575,
"step": 1874
},
{
"epoch": 5.61,
"learning_rate": 1.2778125e-05,
"loss": 1.954,
"step": 1875
},
{
"epoch": 5.62,
"learning_rate": 1.277742e-05,
"loss": 1.9555,
"step": 1876
},
{
"epoch": 5.62,
"learning_rate": 1.2776715e-05,
"loss": 1.953,
"step": 1877
},
{
"epoch": 5.62,
"learning_rate": 1.277601e-05,
"loss": 1.9549,
"step": 1878
},
{
"epoch": 5.63,
"learning_rate": 1.2775305000000002e-05,
"loss": 1.9574,
"step": 1879
},
{
"epoch": 5.63,
"learning_rate": 1.2774600000000001e-05,
"loss": 1.9541,
"step": 1880
},
{
"epoch": 5.63,
"learning_rate": 1.2773895000000001e-05,
"loss": 1.9555,
"step": 1881
},
{
"epoch": 5.64,
"learning_rate": 1.2773190000000001e-05,
"loss": 1.9523,
"step": 1882
},
{
"epoch": 5.64,
"learning_rate": 1.2772485e-05,
"loss": 1.9545,
"step": 1883
},
{
"epoch": 5.64,
"learning_rate": 1.277178e-05,
"loss": 1.9553,
"step": 1884
},
{
"epoch": 5.64,
"learning_rate": 1.2771075000000002e-05,
"loss": 1.952,
"step": 1885
},
{
"epoch": 5.65,
"learning_rate": 1.277037e-05,
"loss": 1.9532,
"step": 1886
},
{
"epoch": 5.65,
"learning_rate": 1.2769665e-05,
"loss": 1.9546,
"step": 1887
},
{
"epoch": 5.65,
"learning_rate": 1.276896e-05,
"loss": 1.9554,
"step": 1888
},
{
"epoch": 5.66,
"learning_rate": 1.2768255e-05,
"loss": 1.9555,
"step": 1889
},
{
"epoch": 5.66,
"learning_rate": 1.276755e-05,
"loss": 1.9536,
"step": 1890
},
{
"epoch": 5.66,
"learning_rate": 1.2766845000000001e-05,
"loss": 1.9528,
"step": 1891
},
{
"epoch": 5.67,
"learning_rate": 1.276614e-05,
"loss": 1.9547,
"step": 1892
},
{
"epoch": 5.67,
"learning_rate": 1.2765435e-05,
"loss": 1.954,
"step": 1893
},
{
"epoch": 5.67,
"learning_rate": 1.276473e-05,
"loss": 1.9543,
"step": 1894
},
{
"epoch": 5.67,
"learning_rate": 1.2764025e-05,
"loss": 1.9541,
"step": 1895
},
{
"epoch": 5.68,
"learning_rate": 1.276332e-05,
"loss": 1.9529,
"step": 1896
},
{
"epoch": 5.68,
"learning_rate": 1.2762615e-05,
"loss": 1.9541,
"step": 1897
},
{
"epoch": 5.68,
"learning_rate": 1.2761910000000001e-05,
"loss": 1.9518,
"step": 1898
},
{
"epoch": 5.69,
"learning_rate": 1.2761205000000001e-05,
"loss": 1.955,
"step": 1899
},
{
"epoch": 5.69,
"learning_rate": 1.2760500000000001e-05,
"loss": 1.9562,
"step": 1900
},
{
"epoch": 5.69,
"eval_accuracy": 0.000786493288590604,
"eval_loss": 1.8642175197601318,
"eval_runtime": 33.4685,
"eval_samples_per_second": 8.904,
"eval_steps_per_second": 0.568,
"step": 1900
},
{
"epoch": 5.69,
"learning_rate": 1.2759795e-05,
"loss": 1.9508,
"step": 1901
},
{
"epoch": 5.7,
"learning_rate": 1.275909e-05,
"loss": 1.9529,
"step": 1902
},
{
"epoch": 5.7,
"learning_rate": 1.2758385e-05,
"loss": 1.9544,
"step": 1903
},
{
"epoch": 5.7,
"learning_rate": 1.2757680000000002e-05,
"loss": 1.9532,
"step": 1904
},
{
"epoch": 5.7,
"learning_rate": 1.2756975000000002e-05,
"loss": 1.9505,
"step": 1905
},
{
"epoch": 5.71,
"learning_rate": 1.275627e-05,
"loss": 1.9533,
"step": 1906
},
{
"epoch": 5.71,
"learning_rate": 1.2755565e-05,
"loss": 1.9503,
"step": 1907
},
{
"epoch": 5.71,
"learning_rate": 1.275486e-05,
"loss": 1.9485,
"step": 1908
},
{
"epoch": 5.72,
"learning_rate": 1.2754155e-05,
"loss": 1.9502,
"step": 1909
},
{
"epoch": 5.72,
"learning_rate": 1.275345e-05,
"loss": 1.9535,
"step": 1910
},
{
"epoch": 5.72,
"learning_rate": 1.2752745e-05,
"loss": 1.95,
"step": 1911
},
{
"epoch": 5.73,
"learning_rate": 1.275204e-05,
"loss": 1.9527,
"step": 1912
},
{
"epoch": 5.73,
"learning_rate": 1.2751335e-05,
"loss": 1.9497,
"step": 1913
},
{
"epoch": 5.73,
"learning_rate": 1.275063e-05,
"loss": 1.9534,
"step": 1914
},
{
"epoch": 5.73,
"learning_rate": 1.2749925e-05,
"loss": 1.9506,
"step": 1915
},
{
"epoch": 5.74,
"learning_rate": 1.2749220000000001e-05,
"loss": 1.951,
"step": 1916
},
{
"epoch": 5.74,
"learning_rate": 1.2748515000000001e-05,
"loss": 1.9494,
"step": 1917
},
{
"epoch": 5.74,
"learning_rate": 1.2747810000000001e-05,
"loss": 1.9497,
"step": 1918
},
{
"epoch": 5.75,
"learning_rate": 1.2747105e-05,
"loss": 1.9506,
"step": 1919
},
{
"epoch": 5.75,
"learning_rate": 1.27464e-05,
"loss": 1.9497,
"step": 1920
},
{
"epoch": 5.75,
"learning_rate": 1.2745695e-05,
"loss": 1.9485,
"step": 1921
},
{
"epoch": 5.76,
"learning_rate": 1.2744990000000002e-05,
"loss": 1.9499,
"step": 1922
},
{
"epoch": 5.76,
"learning_rate": 1.2744285000000002e-05,
"loss": 1.9492,
"step": 1923
},
{
"epoch": 5.76,
"learning_rate": 1.2743580000000001e-05,
"loss": 1.9517,
"step": 1924
},
{
"epoch": 5.76,
"learning_rate": 1.2742875000000001e-05,
"loss": 1.9476,
"step": 1925
},
{
"epoch": 5.77,
"learning_rate": 1.274217e-05,
"loss": 1.9505,
"step": 1926
},
{
"epoch": 5.77,
"learning_rate": 1.2741464999999999e-05,
"loss": 1.9486,
"step": 1927
},
{
"epoch": 5.77,
"learning_rate": 1.274076e-05,
"loss": 1.9491,
"step": 1928
},
{
"epoch": 5.78,
"learning_rate": 1.2740055e-05,
"loss": 1.9475,
"step": 1929
},
{
"epoch": 5.78,
"learning_rate": 1.273935e-05,
"loss": 1.9491,
"step": 1930
},
{
"epoch": 5.78,
"learning_rate": 1.2738645e-05,
"loss": 1.9499,
"step": 1931
},
{
"epoch": 5.79,
"learning_rate": 1.273794e-05,
"loss": 1.9496,
"step": 1932
},
{
"epoch": 5.79,
"learning_rate": 1.2737235e-05,
"loss": 1.9477,
"step": 1933
},
{
"epoch": 5.79,
"learning_rate": 1.2736530000000001e-05,
"loss": 1.9472,
"step": 1934
},
{
"epoch": 5.79,
"learning_rate": 1.2735825000000001e-05,
"loss": 1.9474,
"step": 1935
},
{
"epoch": 5.8,
"learning_rate": 1.273512e-05,
"loss": 1.9489,
"step": 1936
},
{
"epoch": 5.8,
"learning_rate": 1.2734415e-05,
"loss": 1.9488,
"step": 1937
},
{
"epoch": 5.8,
"learning_rate": 1.273371e-05,
"loss": 1.9524,
"step": 1938
},
{
"epoch": 5.81,
"learning_rate": 1.2733005e-05,
"loss": 1.9486,
"step": 1939
},
{
"epoch": 5.81,
"learning_rate": 1.27323e-05,
"loss": 1.9468,
"step": 1940
},
{
"epoch": 5.81,
"learning_rate": 1.2731595000000002e-05,
"loss": 1.9463,
"step": 1941
},
{
"epoch": 5.82,
"learning_rate": 1.2730890000000001e-05,
"loss": 1.9495,
"step": 1942
},
{
"epoch": 5.82,
"learning_rate": 1.2730185000000001e-05,
"loss": 1.9474,
"step": 1943
},
{
"epoch": 5.82,
"learning_rate": 1.2729480000000001e-05,
"loss": 1.9457,
"step": 1944
},
{
"epoch": 5.82,
"learning_rate": 1.2728775e-05,
"loss": 1.9504,
"step": 1945
},
{
"epoch": 5.83,
"learning_rate": 1.2728069999999999e-05,
"loss": 1.9488,
"step": 1946
},
{
"epoch": 5.83,
"learning_rate": 1.2727365e-05,
"loss": 1.9477,
"step": 1947
},
{
"epoch": 5.83,
"learning_rate": 1.272666e-05,
"loss": 1.9466,
"step": 1948
},
{
"epoch": 5.84,
"learning_rate": 1.2725955e-05,
"loss": 1.948,
"step": 1949
},
{
"epoch": 5.84,
"learning_rate": 1.272525e-05,
"loss": 1.9475,
"step": 1950
},
{
"epoch": 5.84,
"learning_rate": 1.2724545e-05,
"loss": 1.9452,
"step": 1951
},
{
"epoch": 5.85,
"learning_rate": 1.272384e-05,
"loss": 1.9446,
"step": 1952
},
{
"epoch": 5.85,
"learning_rate": 1.2723135000000001e-05,
"loss": 1.9469,
"step": 1953
},
{
"epoch": 5.85,
"learning_rate": 1.272243e-05,
"loss": 1.9451,
"step": 1954
},
{
"epoch": 5.85,
"learning_rate": 1.2721725e-05,
"loss": 1.9462,
"step": 1955
},
{
"epoch": 5.86,
"learning_rate": 1.272102e-05,
"loss": 1.9473,
"step": 1956
},
{
"epoch": 5.86,
"learning_rate": 1.2720315e-05,
"loss": 1.9423,
"step": 1957
},
{
"epoch": 5.86,
"learning_rate": 1.271961e-05,
"loss": 1.9463,
"step": 1958
},
{
"epoch": 5.87,
"learning_rate": 1.2718905000000002e-05,
"loss": 1.9471,
"step": 1959
},
{
"epoch": 5.87,
"learning_rate": 1.2718200000000001e-05,
"loss": 1.9456,
"step": 1960
},
{
"epoch": 5.87,
"learning_rate": 1.2717495000000001e-05,
"loss": 1.9452,
"step": 1961
},
{
"epoch": 5.88,
"learning_rate": 1.2716790000000001e-05,
"loss": 1.9459,
"step": 1962
},
{
"epoch": 5.88,
"learning_rate": 1.2716085e-05,
"loss": 1.9436,
"step": 1963
},
{
"epoch": 5.88,
"learning_rate": 1.271538e-05,
"loss": 1.9408,
"step": 1964
},
{
"epoch": 5.88,
"learning_rate": 1.2714675e-05,
"loss": 1.9443,
"step": 1965
},
{
"epoch": 5.89,
"learning_rate": 1.271397e-05,
"loss": 1.9441,
"step": 1966
},
{
"epoch": 5.89,
"learning_rate": 1.2713265e-05,
"loss": 1.9436,
"step": 1967
},
{
"epoch": 5.89,
"learning_rate": 1.271256e-05,
"loss": 1.9458,
"step": 1968
},
{
"epoch": 5.9,
"learning_rate": 1.2711855e-05,
"loss": 1.9461,
"step": 1969
},
{
"epoch": 5.9,
"learning_rate": 1.271115e-05,
"loss": 1.9462,
"step": 1970
},
{
"epoch": 5.9,
"learning_rate": 1.2710445000000001e-05,
"loss": 1.9448,
"step": 1971
},
{
"epoch": 5.91,
"learning_rate": 1.270974e-05,
"loss": 1.9436,
"step": 1972
},
{
"epoch": 5.91,
"learning_rate": 1.2709035e-05,
"loss": 1.9443,
"step": 1973
},
{
"epoch": 5.91,
"learning_rate": 1.270833e-05,
"loss": 1.9441,
"step": 1974
},
{
"epoch": 5.91,
"learning_rate": 1.2707625e-05,
"loss": 1.9437,
"step": 1975
},
{
"epoch": 5.92,
"learning_rate": 1.270692e-05,
"loss": 1.9441,
"step": 1976
},
{
"epoch": 5.92,
"learning_rate": 1.2706215e-05,
"loss": 1.9442,
"step": 1977
},
{
"epoch": 5.92,
"learning_rate": 1.2705510000000001e-05,
"loss": 1.9419,
"step": 1978
},
{
"epoch": 5.93,
"learning_rate": 1.2704805000000001e-05,
"loss": 1.944,
"step": 1979
},
{
"epoch": 5.93,
"learning_rate": 1.2704100000000001e-05,
"loss": 1.9443,
"step": 1980
},
{
"epoch": 5.93,
"learning_rate": 1.2703395e-05,
"loss": 1.9442,
"step": 1981
},
{
"epoch": 5.94,
"learning_rate": 1.270269e-05,
"loss": 1.944,
"step": 1982
},
{
"epoch": 5.94,
"learning_rate": 1.2701985e-05,
"loss": 1.9441,
"step": 1983
},
{
"epoch": 5.94,
"learning_rate": 1.2701280000000002e-05,
"loss": 1.9431,
"step": 1984
},
{
"epoch": 5.94,
"learning_rate": 1.2700575000000002e-05,
"loss": 1.9431,
"step": 1985
},
{
"epoch": 5.95,
"learning_rate": 1.269987e-05,
"loss": 1.9439,
"step": 1986
},
{
"epoch": 5.95,
"learning_rate": 1.2699165e-05,
"loss": 1.943,
"step": 1987
},
{
"epoch": 5.95,
"learning_rate": 1.269846e-05,
"loss": 1.9422,
"step": 1988
},
{
"epoch": 5.96,
"learning_rate": 1.2697755e-05,
"loss": 1.9414,
"step": 1989
},
{
"epoch": 5.96,
"learning_rate": 1.269705e-05,
"loss": 1.9454,
"step": 1990
},
{
"epoch": 5.96,
"learning_rate": 1.2696345e-05,
"loss": 1.9418,
"step": 1991
},
{
"epoch": 5.97,
"learning_rate": 1.269564e-05,
"loss": 1.9419,
"step": 1992
},
{
"epoch": 5.97,
"learning_rate": 1.2694935e-05,
"loss": 1.9433,
"step": 1993
},
{
"epoch": 5.97,
"learning_rate": 1.269423e-05,
"loss": 1.9414,
"step": 1994
},
{
"epoch": 5.97,
"learning_rate": 1.2693525e-05,
"loss": 1.9424,
"step": 1995
},
{
"epoch": 5.98,
"learning_rate": 1.2692820000000001e-05,
"loss": 1.9415,
"step": 1996
},
{
"epoch": 5.98,
"learning_rate": 1.2692115000000001e-05,
"loss": 1.9418,
"step": 1997
},
{
"epoch": 5.98,
"learning_rate": 1.2691410000000001e-05,
"loss": 1.9402,
"step": 1998
},
{
"epoch": 5.99,
"learning_rate": 1.2690705e-05,
"loss": 1.9438,
"step": 1999
},
{
"epoch": 5.99,
"learning_rate": 1.269e-05,
"loss": 1.94,
"step": 2000
},
{
"epoch": 5.99,
"eval_accuracy": 0.000779939177852349,
"eval_loss": 1.8559544086456299,
"eval_runtime": 34.2874,
"eval_samples_per_second": 8.691,
"eval_steps_per_second": 0.554,
"step": 2000
}
],
"logging_steps": 1.0,
"max_steps": 20000,
"num_input_tokens_seen": 0,
"num_train_epochs": 61,
"save_steps": 500,
"total_flos": 1.099804707127296e+18,
"train_batch_size": 128,
"trial_name": null,
"trial_params": null
}