gcode_peft / 44497593 /checkpoint-500 /trainer_state.json
ke-lly's picture
Training in progress, step 500
5fe7002 verified
Raw
History Blame Contribute Delete
58.9 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.4972861688190156,
"eval_steps": 100,
"global_step": 500,
"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
}
],
"logging_steps": 1.0,
"max_steps": 20000,
"num_input_tokens_seen": 0,
"num_train_epochs": 61,
"save_steps": 500,
"total_flos": 2.749578902765568e+17,
"train_batch_size": 128,
"trial_name": null,
"trial_params": null
}