openhermes / trainer_state.json
adhawan02's picture
Upload 8 files
3991692
raw
history blame
75.3 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.6609808102345416,
"eval_steps": 156,
"global_step": 624,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0,
"learning_rate": 0.0001,
"loss": 0.9889,
"step": 1
},
{
"epoch": 0.01,
"learning_rate": 0.0002,
"loss": 0.4951,
"step": 2
},
{
"epoch": 0.01,
"learning_rate": 0.00019971428571428573,
"loss": 0.5165,
"step": 3
},
{
"epoch": 0.02,
"learning_rate": 0.00019942857142857143,
"loss": 0.4097,
"step": 4
},
{
"epoch": 0.02,
"learning_rate": 0.00019914285714285715,
"loss": 0.7352,
"step": 5
},
{
"epoch": 0.03,
"learning_rate": 0.00019885714285714287,
"loss": 0.748,
"step": 6
},
{
"epoch": 0.03,
"learning_rate": 0.0001985714285714286,
"loss": 0.7403,
"step": 7
},
{
"epoch": 0.03,
"learning_rate": 0.0001982857142857143,
"loss": 0.419,
"step": 8
},
{
"epoch": 0.04,
"learning_rate": 0.00019800000000000002,
"loss": 0.3272,
"step": 9
},
{
"epoch": 0.04,
"learning_rate": 0.0001977142857142857,
"loss": 0.3405,
"step": 10
},
{
"epoch": 0.05,
"learning_rate": 0.00019742857142857143,
"loss": 0.7197,
"step": 11
},
{
"epoch": 0.05,
"learning_rate": 0.00019714285714285716,
"loss": 0.7352,
"step": 12
},
{
"epoch": 0.06,
"learning_rate": 0.00019685714285714288,
"loss": 0.6075,
"step": 13
},
{
"epoch": 0.06,
"learning_rate": 0.00019657142857142858,
"loss": 0.2958,
"step": 14
},
{
"epoch": 0.06,
"learning_rate": 0.0001962857142857143,
"loss": 0.3496,
"step": 15
},
{
"epoch": 0.07,
"learning_rate": 0.000196,
"loss": 0.6658,
"step": 16
},
{
"epoch": 0.07,
"learning_rate": 0.00019571428571428572,
"loss": 0.7549,
"step": 17
},
{
"epoch": 0.08,
"learning_rate": 0.00019542857142857144,
"loss": 0.0,
"step": 18
},
{
"epoch": 0.08,
"learning_rate": 0.00019514285714285716,
"loss": 0.6884,
"step": 19
},
{
"epoch": 0.09,
"learning_rate": 0.00019485714285714286,
"loss": 0.6409,
"step": 20
},
{
"epoch": 0.09,
"learning_rate": 0.00019457142857142858,
"loss": 0.7512,
"step": 21
},
{
"epoch": 0.09,
"learning_rate": 0.0001942857142857143,
"loss": 0.7013,
"step": 22
},
{
"epoch": 0.1,
"learning_rate": 0.000194,
"loss": 0.7292,
"step": 23
},
{
"epoch": 0.1,
"learning_rate": 0.00019371428571428572,
"loss": 0.3452,
"step": 24
},
{
"epoch": 0.11,
"learning_rate": 0.00019342857142857144,
"loss": 0.3501,
"step": 25
},
{
"epoch": 0.11,
"learning_rate": 0.00019314285714285717,
"loss": 0.3008,
"step": 26
},
{
"epoch": 0.12,
"learning_rate": 0.00019285714285714286,
"loss": 0.3964,
"step": 27
},
{
"epoch": 0.12,
"learning_rate": 0.00019257142857142859,
"loss": 0.3228,
"step": 28
},
{
"epoch": 0.12,
"learning_rate": 0.00019228571428571428,
"loss": 0.3513,
"step": 29
},
{
"epoch": 0.13,
"learning_rate": 0.000192,
"loss": 0.664,
"step": 30
},
{
"epoch": 0.13,
"learning_rate": 0.0001917142857142857,
"loss": 0.6402,
"step": 31
},
{
"epoch": 0.14,
"learning_rate": 0.00019142857142857145,
"loss": 0.3111,
"step": 32
},
{
"epoch": 0.14,
"learning_rate": 0.00019114285714285715,
"loss": 0.3587,
"step": 33
},
{
"epoch": 0.14,
"learning_rate": 0.00019085714285714287,
"loss": 0.6624,
"step": 34
},
{
"epoch": 0.15,
"learning_rate": 0.0001905714285714286,
"loss": 0.6812,
"step": 35
},
{
"epoch": 0.15,
"learning_rate": 0.0001902857142857143,
"loss": 0.7159,
"step": 36
},
{
"epoch": 0.16,
"learning_rate": 0.00019,
"loss": 0.5748,
"step": 37
},
{
"epoch": 0.16,
"learning_rate": 0.00018971428571428573,
"loss": 0.0,
"step": 38
},
{
"epoch": 0.17,
"learning_rate": 0.00018942857142857146,
"loss": 0.7387,
"step": 39
},
{
"epoch": 0.17,
"learning_rate": 0.00018914285714285715,
"loss": 0.6224,
"step": 40
},
{
"epoch": 0.17,
"learning_rate": 0.00018885714285714287,
"loss": 0.6408,
"step": 41
},
{
"epoch": 0.18,
"learning_rate": 0.00018857142857142857,
"loss": 0.3345,
"step": 42
},
{
"epoch": 0.18,
"learning_rate": 0.0001882857142857143,
"loss": 0.6047,
"step": 43
},
{
"epoch": 0.19,
"learning_rate": 0.000188,
"loss": 0.6938,
"step": 44
},
{
"epoch": 0.19,
"learning_rate": 0.00018771428571428574,
"loss": 0.5592,
"step": 45
},
{
"epoch": 0.2,
"learning_rate": 0.00018742857142857143,
"loss": 0.5506,
"step": 46
},
{
"epoch": 0.2,
"learning_rate": 0.00018714285714285716,
"loss": 0.6233,
"step": 47
},
{
"epoch": 0.2,
"learning_rate": 0.00018685714285714285,
"loss": 0.3068,
"step": 48
},
{
"epoch": 0.21,
"learning_rate": 0.00018657142857142858,
"loss": 0.6384,
"step": 49
},
{
"epoch": 0.21,
"learning_rate": 0.0001862857142857143,
"loss": 0.0,
"step": 50
},
{
"epoch": 0.22,
"learning_rate": 0.00018600000000000002,
"loss": 0.3308,
"step": 51
},
{
"epoch": 0.22,
"learning_rate": 0.00018571428571428572,
"loss": 0.3585,
"step": 52
},
{
"epoch": 0.23,
"learning_rate": 0.00018542857142857144,
"loss": 0.267,
"step": 53
},
{
"epoch": 0.23,
"learning_rate": 0.00018514285714285716,
"loss": 0.6211,
"step": 54
},
{
"epoch": 0.23,
"learning_rate": 0.00018485714285714286,
"loss": 0.6349,
"step": 55
},
{
"epoch": 0.24,
"learning_rate": 0.00018457142857142858,
"loss": 0.3467,
"step": 56
},
{
"epoch": 0.24,
"learning_rate": 0.00018428571428571428,
"loss": 0.3246,
"step": 57
},
{
"epoch": 0.25,
"learning_rate": 0.00018400000000000003,
"loss": 0.7163,
"step": 58
},
{
"epoch": 0.25,
"learning_rate": 0.00018371428571428572,
"loss": 0.3002,
"step": 59
},
{
"epoch": 0.26,
"learning_rate": 0.00018342857142857145,
"loss": 0.6595,
"step": 60
},
{
"epoch": 0.26,
"learning_rate": 0.00018314285714285714,
"loss": 0.2982,
"step": 61
},
{
"epoch": 0.26,
"learning_rate": 0.00018285714285714286,
"loss": 0.6394,
"step": 62
},
{
"epoch": 0.27,
"learning_rate": 0.00018257142857142856,
"loss": 0.6705,
"step": 63
},
{
"epoch": 0.27,
"learning_rate": 0.0001822857142857143,
"loss": 0.3373,
"step": 64
},
{
"epoch": 0.28,
"learning_rate": 0.000182,
"loss": 0.3306,
"step": 65
},
{
"epoch": 0.28,
"learning_rate": 0.00018171428571428573,
"loss": 0.0,
"step": 66
},
{
"epoch": 0.29,
"learning_rate": 0.00018142857142857142,
"loss": 0.6568,
"step": 67
},
{
"epoch": 0.29,
"learning_rate": 0.00018114285714285715,
"loss": 0.2512,
"step": 68
},
{
"epoch": 0.29,
"learning_rate": 0.00018085714285714287,
"loss": 0.5775,
"step": 69
},
{
"epoch": 0.3,
"learning_rate": 0.00018057142857142857,
"loss": 0.2991,
"step": 70
},
{
"epoch": 0.3,
"learning_rate": 0.00018028571428571432,
"loss": 0.5455,
"step": 71
},
{
"epoch": 0.31,
"learning_rate": 0.00018,
"loss": 0.5848,
"step": 72
},
{
"epoch": 0.31,
"learning_rate": 0.00017971428571428573,
"loss": 0.3182,
"step": 73
},
{
"epoch": 0.32,
"learning_rate": 0.00017942857142857143,
"loss": 0.2818,
"step": 74
},
{
"epoch": 0.32,
"learning_rate": 0.00017914285714285715,
"loss": 0.3182,
"step": 75
},
{
"epoch": 0.32,
"learning_rate": 0.00017885714285714285,
"loss": 0.7252,
"step": 76
},
{
"epoch": 0.33,
"learning_rate": 0.0001785714285714286,
"loss": 0.3285,
"step": 77
},
{
"epoch": 0.33,
"learning_rate": 0.0001782857142857143,
"loss": 0.304,
"step": 78
},
{
"epoch": 0.34,
"learning_rate": 0.00017800000000000002,
"loss": 0.6182,
"step": 79
},
{
"epoch": 0.34,
"learning_rate": 0.0001777142857142857,
"loss": 0.3132,
"step": 80
},
{
"epoch": 0.35,
"learning_rate": 0.00017742857142857144,
"loss": 0.2945,
"step": 81
},
{
"epoch": 0.35,
"learning_rate": 0.00017714285714285713,
"loss": 0.3054,
"step": 82
},
{
"epoch": 0.35,
"learning_rate": 0.00017685714285714285,
"loss": 0.624,
"step": 83
},
{
"epoch": 0.36,
"learning_rate": 0.00017657142857142858,
"loss": 0.5924,
"step": 84
},
{
"epoch": 0.36,
"learning_rate": 0.0001762857142857143,
"loss": 0.5982,
"step": 85
},
{
"epoch": 0.37,
"learning_rate": 0.00017600000000000002,
"loss": 0.2506,
"step": 86
},
{
"epoch": 0.37,
"learning_rate": 0.00017571428571428572,
"loss": 0.6335,
"step": 87
},
{
"epoch": 0.38,
"learning_rate": 0.00017542857142857144,
"loss": 0.5653,
"step": 88
},
{
"epoch": 0.38,
"learning_rate": 0.00017514285714285714,
"loss": 0.6699,
"step": 89
},
{
"epoch": 0.38,
"learning_rate": 0.0001748571428571429,
"loss": 0.6922,
"step": 90
},
{
"epoch": 0.39,
"learning_rate": 0.00017457142857142858,
"loss": 0.5895,
"step": 91
},
{
"epoch": 0.39,
"learning_rate": 0.0001742857142857143,
"loss": 0.6538,
"step": 92
},
{
"epoch": 0.4,
"learning_rate": 0.000174,
"loss": 0.2546,
"step": 93
},
{
"epoch": 0.4,
"learning_rate": 0.00017371428571428572,
"loss": 0.5757,
"step": 94
},
{
"epoch": 0.41,
"learning_rate": 0.00017342857142857142,
"loss": 0.344,
"step": 95
},
{
"epoch": 0.41,
"learning_rate": 0.00017314285714285717,
"loss": 0.6754,
"step": 96
},
{
"epoch": 0.41,
"learning_rate": 0.00017285714285714287,
"loss": 0.6179,
"step": 97
},
{
"epoch": 0.42,
"learning_rate": 0.0001725714285714286,
"loss": 0.3944,
"step": 98
},
{
"epoch": 0.42,
"learning_rate": 0.00017228571428571428,
"loss": 0.2476,
"step": 99
},
{
"epoch": 0.43,
"learning_rate": 0.000172,
"loss": 0.6522,
"step": 100
},
{
"epoch": 0.43,
"learning_rate": 0.00017171428571428573,
"loss": 0.562,
"step": 101
},
{
"epoch": 0.43,
"learning_rate": 0.00017142857142857143,
"loss": 0.5576,
"step": 102
},
{
"epoch": 0.44,
"learning_rate": 0.00017114285714285715,
"loss": 0.6046,
"step": 103
},
{
"epoch": 0.44,
"learning_rate": 0.00017085714285714287,
"loss": 0.5753,
"step": 104
},
{
"epoch": 0.45,
"learning_rate": 0.0001705714285714286,
"loss": 0.2614,
"step": 105
},
{
"epoch": 0.45,
"learning_rate": 0.0001702857142857143,
"loss": 0.655,
"step": 106
},
{
"epoch": 0.46,
"learning_rate": 0.00017,
"loss": 0.2835,
"step": 107
},
{
"epoch": 0.46,
"learning_rate": 0.0001697142857142857,
"loss": 0.6546,
"step": 108
},
{
"epoch": 0.46,
"learning_rate": 0.00016942857142857146,
"loss": 0.5824,
"step": 109
},
{
"epoch": 0.47,
"learning_rate": 0.00016914285714285715,
"loss": 0.6677,
"step": 110
},
{
"epoch": 0.47,
"learning_rate": 0.00016885714285714288,
"loss": 0.2894,
"step": 111
},
{
"epoch": 0.48,
"learning_rate": 0.00016857142857142857,
"loss": 0.6486,
"step": 112
},
{
"epoch": 0.48,
"learning_rate": 0.0001682857142857143,
"loss": 0.3072,
"step": 113
},
{
"epoch": 0.49,
"learning_rate": 0.000168,
"loss": 0.7014,
"step": 114
},
{
"epoch": 0.49,
"learning_rate": 0.0001677142857142857,
"loss": 0.6132,
"step": 115
},
{
"epoch": 0.49,
"learning_rate": 0.00016742857142857144,
"loss": 0.6159,
"step": 116
},
{
"epoch": 0.5,
"learning_rate": 0.00016714285714285716,
"loss": 0.5856,
"step": 117
},
{
"epoch": 0.5,
"learning_rate": 0.00016685714285714285,
"loss": 0.3519,
"step": 118
},
{
"epoch": 0.51,
"learning_rate": 0.00016657142857142858,
"loss": 0.3182,
"step": 119
},
{
"epoch": 0.51,
"learning_rate": 0.0001662857142857143,
"loss": 0.3017,
"step": 120
},
{
"epoch": 0.52,
"learning_rate": 0.000166,
"loss": 0.6816,
"step": 121
},
{
"epoch": 0.52,
"learning_rate": 0.00016571428571428575,
"loss": 0.2703,
"step": 122
},
{
"epoch": 0.52,
"learning_rate": 0.00016542857142857144,
"loss": 0.6278,
"step": 123
},
{
"epoch": 0.53,
"learning_rate": 0.00016514285714285716,
"loss": 0.6233,
"step": 124
},
{
"epoch": 0.53,
"learning_rate": 0.00016485714285714286,
"loss": 0.5889,
"step": 125
},
{
"epoch": 0.54,
"learning_rate": 0.00016457142857142858,
"loss": 0.6905,
"step": 126
},
{
"epoch": 0.54,
"learning_rate": 0.00016428571428571428,
"loss": 0.6283,
"step": 127
},
{
"epoch": 0.55,
"learning_rate": 0.000164,
"loss": 0.3126,
"step": 128
},
{
"epoch": 0.55,
"learning_rate": 0.00016371428571428572,
"loss": 0.6339,
"step": 129
},
{
"epoch": 0.55,
"learning_rate": 0.00016342857142857145,
"loss": 0.5889,
"step": 130
},
{
"epoch": 0.56,
"learning_rate": 0.00016314285714285714,
"loss": 0.6218,
"step": 131
},
{
"epoch": 0.56,
"learning_rate": 0.00016285714285714287,
"loss": 0.5702,
"step": 132
},
{
"epoch": 0.57,
"learning_rate": 0.00016257142857142856,
"loss": 0.2685,
"step": 133
},
{
"epoch": 0.57,
"learning_rate": 0.00016228571428571428,
"loss": 0.6051,
"step": 134
},
{
"epoch": 0.58,
"learning_rate": 0.000162,
"loss": 0.2954,
"step": 135
},
{
"epoch": 0.58,
"learning_rate": 0.00016171428571428573,
"loss": 0.5462,
"step": 136
},
{
"epoch": 0.58,
"learning_rate": 0.00016142857142857145,
"loss": 0.2729,
"step": 137
},
{
"epoch": 0.59,
"learning_rate": 0.00016114285714285715,
"loss": 0.3568,
"step": 138
},
{
"epoch": 0.59,
"learning_rate": 0.00016085714285714287,
"loss": 0.5986,
"step": 139
},
{
"epoch": 0.6,
"learning_rate": 0.00016057142857142857,
"loss": 0.5628,
"step": 140
},
{
"epoch": 0.6,
"learning_rate": 0.0001602857142857143,
"loss": 0.5976,
"step": 141
},
{
"epoch": 0.61,
"learning_rate": 0.00016,
"loss": 0.5368,
"step": 142
},
{
"epoch": 0.61,
"learning_rate": 0.00015971428571428574,
"loss": 0.6045,
"step": 143
},
{
"epoch": 0.61,
"learning_rate": 0.00015942857142857143,
"loss": 0.6088,
"step": 144
},
{
"epoch": 0.62,
"learning_rate": 0.00015914285714285715,
"loss": 0.6173,
"step": 145
},
{
"epoch": 0.62,
"learning_rate": 0.00015885714285714285,
"loss": 0.5401,
"step": 146
},
{
"epoch": 0.63,
"learning_rate": 0.00015857142857142857,
"loss": 0.2776,
"step": 147
},
{
"epoch": 0.63,
"learning_rate": 0.0001582857142857143,
"loss": 0.6971,
"step": 148
},
{
"epoch": 0.64,
"learning_rate": 0.00015800000000000002,
"loss": 0.6465,
"step": 149
},
{
"epoch": 0.64,
"learning_rate": 0.00015771428571428571,
"loss": 0.3124,
"step": 150
},
{
"epoch": 0.64,
"learning_rate": 0.00015742857142857144,
"loss": 0.2749,
"step": 151
},
{
"epoch": 0.65,
"learning_rate": 0.00015714285714285716,
"loss": 0.5629,
"step": 152
},
{
"epoch": 0.65,
"learning_rate": 0.00015685714285714286,
"loss": 0.3584,
"step": 153
},
{
"epoch": 0.66,
"learning_rate": 0.00015657142857142858,
"loss": 0.6109,
"step": 154
},
{
"epoch": 0.66,
"learning_rate": 0.0001562857142857143,
"loss": 0.5622,
"step": 155
},
{
"epoch": 0.67,
"learning_rate": 0.00015600000000000002,
"loss": 0.6052,
"step": 156
},
{
"epoch": 0.67,
"eval_loss": 0.5988273620605469,
"eval_runtime": 1562.4866,
"eval_samples_per_second": 1.2,
"eval_steps_per_second": 0.076,
"step": 156
},
{
"epoch": 0.67,
"learning_rate": 0.00015571428571428572,
"loss": 0.3597,
"step": 157
},
{
"epoch": 0.67,
"learning_rate": 0.00015542857142857144,
"loss": 0.6965,
"step": 158
},
{
"epoch": 0.68,
"learning_rate": 0.00015514285714285714,
"loss": 0.6494,
"step": 159
},
{
"epoch": 0.68,
"learning_rate": 0.00015485714285714286,
"loss": 0.3002,
"step": 160
},
{
"epoch": 0.69,
"learning_rate": 0.00015457142857142858,
"loss": 0.59,
"step": 161
},
{
"epoch": 0.69,
"learning_rate": 0.0001542857142857143,
"loss": 0.5645,
"step": 162
},
{
"epoch": 0.7,
"learning_rate": 0.000154,
"loss": 0.5341,
"step": 163
},
{
"epoch": 0.7,
"learning_rate": 0.00015371428571428573,
"loss": 0.5758,
"step": 164
},
{
"epoch": 0.7,
"learning_rate": 0.00015342857142857142,
"loss": 0.6477,
"step": 165
},
{
"epoch": 0.71,
"learning_rate": 0.00015314285714285714,
"loss": 0.4926,
"step": 166
},
{
"epoch": 0.71,
"learning_rate": 0.00015285714285714287,
"loss": 0.281,
"step": 167
},
{
"epoch": 0.72,
"learning_rate": 0.0001525714285714286,
"loss": 0.6374,
"step": 168
},
{
"epoch": 0.72,
"learning_rate": 0.00015228571428571429,
"loss": 0.2878,
"step": 169
},
{
"epoch": 0.72,
"learning_rate": 0.000152,
"loss": 0.6083,
"step": 170
},
{
"epoch": 0.73,
"learning_rate": 0.00015171428571428573,
"loss": 0.5585,
"step": 171
},
{
"epoch": 0.73,
"learning_rate": 0.00015142857142857143,
"loss": 0.5549,
"step": 172
},
{
"epoch": 0.74,
"learning_rate": 0.00015114285714285715,
"loss": 0.6644,
"step": 173
},
{
"epoch": 0.74,
"learning_rate": 0.00015085714285714287,
"loss": 0.5537,
"step": 174
},
{
"epoch": 0.75,
"learning_rate": 0.0001505714285714286,
"loss": 0.5041,
"step": 175
},
{
"epoch": 0.75,
"learning_rate": 0.0001502857142857143,
"loss": 0.66,
"step": 176
},
{
"epoch": 0.75,
"learning_rate": 0.00015000000000000001,
"loss": 0.6471,
"step": 177
},
{
"epoch": 0.76,
"learning_rate": 0.0001497142857142857,
"loss": 0.5704,
"step": 178
},
{
"epoch": 0.76,
"learning_rate": 0.00014942857142857143,
"loss": 0.6334,
"step": 179
},
{
"epoch": 0.77,
"learning_rate": 0.00014914285714285713,
"loss": 0.6374,
"step": 180
},
{
"epoch": 0.77,
"learning_rate": 0.00014885714285714288,
"loss": 0.612,
"step": 181
},
{
"epoch": 0.78,
"learning_rate": 0.00014857142857142857,
"loss": 0.6804,
"step": 182
},
{
"epoch": 0.78,
"learning_rate": 0.0001482857142857143,
"loss": 0.6188,
"step": 183
},
{
"epoch": 0.78,
"learning_rate": 0.000148,
"loss": 0.6924,
"step": 184
},
{
"epoch": 0.79,
"learning_rate": 0.00014771428571428572,
"loss": 0.2857,
"step": 185
},
{
"epoch": 0.79,
"learning_rate": 0.00014742857142857144,
"loss": 0.5372,
"step": 186
},
{
"epoch": 0.8,
"learning_rate": 0.00014714285714285716,
"loss": 0.5885,
"step": 187
},
{
"epoch": 0.8,
"learning_rate": 0.00014685714285714288,
"loss": 0.3706,
"step": 188
},
{
"epoch": 0.81,
"learning_rate": 0.00014657142857142858,
"loss": 0.5478,
"step": 189
},
{
"epoch": 0.81,
"learning_rate": 0.0001462857142857143,
"loss": 0.5627,
"step": 190
},
{
"epoch": 0.81,
"learning_rate": 0.000146,
"loss": 0.6149,
"step": 191
},
{
"epoch": 0.82,
"learning_rate": 0.00014571428571428572,
"loss": 0.6333,
"step": 192
},
{
"epoch": 0.82,
"learning_rate": 0.00014542857142857142,
"loss": 0.2941,
"step": 193
},
{
"epoch": 0.83,
"learning_rate": 0.00014514285714285717,
"loss": 0.5854,
"step": 194
},
{
"epoch": 0.83,
"learning_rate": 0.00014485714285714286,
"loss": 0.246,
"step": 195
},
{
"epoch": 0.84,
"learning_rate": 0.00014457142857142859,
"loss": 0.5762,
"step": 196
},
{
"epoch": 0.84,
"learning_rate": 0.00014428571428571428,
"loss": 0.2735,
"step": 197
},
{
"epoch": 0.84,
"learning_rate": 0.000144,
"loss": 0.5489,
"step": 198
},
{
"epoch": 0.85,
"learning_rate": 0.0001437142857142857,
"loss": 0.344,
"step": 199
},
{
"epoch": 0.85,
"learning_rate": 0.00014342857142857145,
"loss": 0.5864,
"step": 200
},
{
"epoch": 0.86,
"learning_rate": 0.00014314285714285715,
"loss": 0.5555,
"step": 201
},
{
"epoch": 0.86,
"learning_rate": 0.00014285714285714287,
"loss": 0.651,
"step": 202
},
{
"epoch": 0.87,
"learning_rate": 0.0001425714285714286,
"loss": 0.6941,
"step": 203
},
{
"epoch": 0.87,
"learning_rate": 0.00014228571428571429,
"loss": 0.2873,
"step": 204
},
{
"epoch": 0.87,
"learning_rate": 0.000142,
"loss": 0.7327,
"step": 205
},
{
"epoch": 0.88,
"learning_rate": 0.0001417142857142857,
"loss": 0.5948,
"step": 206
},
{
"epoch": 0.88,
"learning_rate": 0.00014142857142857145,
"loss": 0.5908,
"step": 207
},
{
"epoch": 0.89,
"learning_rate": 0.00014114285714285715,
"loss": 0.5264,
"step": 208
},
{
"epoch": 0.89,
"learning_rate": 0.00014085714285714287,
"loss": 0.6155,
"step": 209
},
{
"epoch": 0.9,
"learning_rate": 0.00014057142857142857,
"loss": 0.4768,
"step": 210
},
{
"epoch": 0.9,
"learning_rate": 0.0001402857142857143,
"loss": 0.3656,
"step": 211
},
{
"epoch": 0.9,
"learning_rate": 0.00014,
"loss": 0.5636,
"step": 212
},
{
"epoch": 0.91,
"learning_rate": 0.00013971428571428574,
"loss": 0.5509,
"step": 213
},
{
"epoch": 0.91,
"learning_rate": 0.00013942857142857143,
"loss": 0.2875,
"step": 214
},
{
"epoch": 0.92,
"learning_rate": 0.00013914285714285716,
"loss": 0.2768,
"step": 215
},
{
"epoch": 0.92,
"learning_rate": 0.00013885714285714285,
"loss": 0.2751,
"step": 216
},
{
"epoch": 0.93,
"learning_rate": 0.00013857142857142857,
"loss": 0.6671,
"step": 217
},
{
"epoch": 0.93,
"learning_rate": 0.0001382857142857143,
"loss": 0.5853,
"step": 218
},
{
"epoch": 0.93,
"learning_rate": 0.000138,
"loss": 0.6157,
"step": 219
},
{
"epoch": 0.94,
"learning_rate": 0.00013771428571428572,
"loss": 0.647,
"step": 220
},
{
"epoch": 0.94,
"learning_rate": 0.00013742857142857144,
"loss": 0.3454,
"step": 221
},
{
"epoch": 0.95,
"learning_rate": 0.00013714285714285716,
"loss": 0.252,
"step": 222
},
{
"epoch": 0.95,
"learning_rate": 0.00013685714285714286,
"loss": 0.5676,
"step": 223
},
{
"epoch": 0.96,
"learning_rate": 0.00013657142857142858,
"loss": 0.5248,
"step": 224
},
{
"epoch": 0.96,
"learning_rate": 0.00013628571428571428,
"loss": 0.4691,
"step": 225
},
{
"epoch": 0.96,
"learning_rate": 0.00013600000000000003,
"loss": 0.6254,
"step": 226
},
{
"epoch": 0.97,
"learning_rate": 0.00013571428571428572,
"loss": 0.5577,
"step": 227
},
{
"epoch": 0.97,
"learning_rate": 0.00013542857142857144,
"loss": 0.5842,
"step": 228
},
{
"epoch": 0.98,
"learning_rate": 0.00013514285714285714,
"loss": 0.2572,
"step": 229
},
{
"epoch": 0.98,
"learning_rate": 0.00013485714285714286,
"loss": 0.0,
"step": 230
},
{
"epoch": 0.99,
"learning_rate": 0.00013457142857142856,
"loss": 0.615,
"step": 231
},
{
"epoch": 0.99,
"learning_rate": 0.00013428571428571428,
"loss": 0.5286,
"step": 232
},
{
"epoch": 0.99,
"learning_rate": 0.000134,
"loss": 0.6437,
"step": 233
},
{
"epoch": 1.0,
"learning_rate": 0.00013371428571428573,
"loss": 0.6217,
"step": 234
},
{
"epoch": 1.0,
"learning_rate": 0.00013342857142857142,
"loss": 0.4495,
"step": 235
},
{
"epoch": 1.01,
"learning_rate": 0.00013314285714285715,
"loss": 0.5384,
"step": 236
},
{
"epoch": 1.01,
"learning_rate": 0.00013285714285714287,
"loss": 0.2014,
"step": 237
},
{
"epoch": 1.01,
"learning_rate": 0.00013257142857142856,
"loss": 0.4747,
"step": 238
},
{
"epoch": 1.02,
"learning_rate": 0.00013228571428571431,
"loss": 0.549,
"step": 239
},
{
"epoch": 1.02,
"learning_rate": 0.000132,
"loss": 0.5945,
"step": 240
},
{
"epoch": 1.03,
"learning_rate": 0.00013171428571428573,
"loss": 0.602,
"step": 241
},
{
"epoch": 1.03,
"learning_rate": 0.00013142857142857143,
"loss": 0.2473,
"step": 242
},
{
"epoch": 1.04,
"learning_rate": 0.00013114285714285715,
"loss": 0.2374,
"step": 243
},
{
"epoch": 1.04,
"learning_rate": 0.00013085714285714285,
"loss": 0.5491,
"step": 244
},
{
"epoch": 1.04,
"learning_rate": 0.00013057142857142857,
"loss": 0.2381,
"step": 245
},
{
"epoch": 1.05,
"learning_rate": 0.0001302857142857143,
"loss": 0.5074,
"step": 246
},
{
"epoch": 1.05,
"learning_rate": 0.00013000000000000002,
"loss": 0.5585,
"step": 247
},
{
"epoch": 1.06,
"learning_rate": 0.0001297142857142857,
"loss": 0.4601,
"step": 248
},
{
"epoch": 1.06,
"learning_rate": 0.00012942857142857143,
"loss": 0.5361,
"step": 249
},
{
"epoch": 1.07,
"learning_rate": 0.00012914285714285713,
"loss": 0.5807,
"step": 250
},
{
"epoch": 1.07,
"learning_rate": 0.00012885714285714285,
"loss": 0.5401,
"step": 251
},
{
"epoch": 1.07,
"learning_rate": 0.00012857142857142858,
"loss": 0.2766,
"step": 252
},
{
"epoch": 1.08,
"learning_rate": 0.0001282857142857143,
"loss": 0.275,
"step": 253
},
{
"epoch": 1.08,
"learning_rate": 0.00012800000000000002,
"loss": 0.5953,
"step": 254
},
{
"epoch": 1.09,
"learning_rate": 0.00012771428571428572,
"loss": 0.4287,
"step": 255
},
{
"epoch": 1.09,
"learning_rate": 0.00012742857142857144,
"loss": 0.5142,
"step": 256
},
{
"epoch": 1.1,
"learning_rate": 0.00012714285714285714,
"loss": 0.5177,
"step": 257
},
{
"epoch": 1.1,
"learning_rate": 0.00012685714285714286,
"loss": 0.2883,
"step": 258
},
{
"epoch": 1.1,
"learning_rate": 0.00012657142857142858,
"loss": 0.4796,
"step": 259
},
{
"epoch": 1.11,
"learning_rate": 0.0001262857142857143,
"loss": 0.5072,
"step": 260
},
{
"epoch": 1.11,
"learning_rate": 0.000126,
"loss": 0.2662,
"step": 261
},
{
"epoch": 1.12,
"learning_rate": 0.00012571428571428572,
"loss": 0.5127,
"step": 262
},
{
"epoch": 1.12,
"learning_rate": 0.00012542857142857142,
"loss": 0.4958,
"step": 263
},
{
"epoch": 1.13,
"learning_rate": 0.00012514285714285714,
"loss": 0.5002,
"step": 264
},
{
"epoch": 1.13,
"learning_rate": 0.00012485714285714286,
"loss": 0.5474,
"step": 265
},
{
"epoch": 1.13,
"learning_rate": 0.0001245714285714286,
"loss": 0.4841,
"step": 266
},
{
"epoch": 1.14,
"learning_rate": 0.00012428571428571428,
"loss": 0.0,
"step": 267
},
{
"epoch": 1.14,
"learning_rate": 0.000124,
"loss": 0.2656,
"step": 268
},
{
"epoch": 1.15,
"learning_rate": 0.00012371428571428573,
"loss": 0.4862,
"step": 269
},
{
"epoch": 1.15,
"learning_rate": 0.00012342857142857142,
"loss": 0.4662,
"step": 270
},
{
"epoch": 1.16,
"learning_rate": 0.00012314285714285715,
"loss": 0.5515,
"step": 271
},
{
"epoch": 1.16,
"learning_rate": 0.00012285714285714287,
"loss": 0.3826,
"step": 272
},
{
"epoch": 1.16,
"learning_rate": 0.0001225714285714286,
"loss": 0.4942,
"step": 273
},
{
"epoch": 1.17,
"learning_rate": 0.0001222857142857143,
"loss": 0.2629,
"step": 274
},
{
"epoch": 1.17,
"learning_rate": 0.000122,
"loss": 0.5221,
"step": 275
},
{
"epoch": 1.18,
"learning_rate": 0.00012171428571428572,
"loss": 0.57,
"step": 276
},
{
"epoch": 1.18,
"learning_rate": 0.00012142857142857143,
"loss": 0.48,
"step": 277
},
{
"epoch": 1.19,
"learning_rate": 0.00012114285714285715,
"loss": 0.4564,
"step": 278
},
{
"epoch": 1.19,
"learning_rate": 0.00012085714285714288,
"loss": 0.5434,
"step": 279
},
{
"epoch": 1.19,
"learning_rate": 0.00012057142857142858,
"loss": 0.2221,
"step": 280
},
{
"epoch": 1.2,
"learning_rate": 0.0001202857142857143,
"loss": 0.2492,
"step": 281
},
{
"epoch": 1.2,
"learning_rate": 0.00012,
"loss": 0.5282,
"step": 282
},
{
"epoch": 1.21,
"learning_rate": 0.00011971428571428571,
"loss": 0.4681,
"step": 283
},
{
"epoch": 1.21,
"learning_rate": 0.00011942857142857145,
"loss": 0.6052,
"step": 284
},
{
"epoch": 1.22,
"learning_rate": 0.00011914285714285716,
"loss": 0.3102,
"step": 285
},
{
"epoch": 1.22,
"learning_rate": 0.00011885714285714287,
"loss": 0.5227,
"step": 286
},
{
"epoch": 1.22,
"learning_rate": 0.00011857142857142858,
"loss": 0.2566,
"step": 287
},
{
"epoch": 1.23,
"learning_rate": 0.00011828571428571429,
"loss": 0.5262,
"step": 288
},
{
"epoch": 1.23,
"learning_rate": 0.000118,
"loss": 0.551,
"step": 289
},
{
"epoch": 1.24,
"learning_rate": 0.0001177142857142857,
"loss": 0.5732,
"step": 290
},
{
"epoch": 1.24,
"learning_rate": 0.00011742857142857144,
"loss": 0.2717,
"step": 291
},
{
"epoch": 1.25,
"learning_rate": 0.00011714285714285715,
"loss": 0.2799,
"step": 292
},
{
"epoch": 1.25,
"learning_rate": 0.00011685714285714286,
"loss": 0.5684,
"step": 293
},
{
"epoch": 1.25,
"learning_rate": 0.00011657142857142858,
"loss": 0.2394,
"step": 294
},
{
"epoch": 1.26,
"learning_rate": 0.00011628571428571429,
"loss": 0.2429,
"step": 295
},
{
"epoch": 1.26,
"learning_rate": 0.000116,
"loss": 0.4925,
"step": 296
},
{
"epoch": 1.27,
"learning_rate": 0.00011571428571428574,
"loss": 0.2346,
"step": 297
},
{
"epoch": 1.27,
"learning_rate": 0.00011542857142857145,
"loss": 0.5282,
"step": 298
},
{
"epoch": 1.28,
"learning_rate": 0.00011514285714285716,
"loss": 0.5555,
"step": 299
},
{
"epoch": 1.28,
"learning_rate": 0.00011485714285714286,
"loss": 0.2847,
"step": 300
},
{
"epoch": 1.28,
"learning_rate": 0.00011457142857142857,
"loss": 0.5985,
"step": 301
},
{
"epoch": 1.29,
"learning_rate": 0.00011428571428571428,
"loss": 0.4664,
"step": 302
},
{
"epoch": 1.29,
"learning_rate": 0.00011399999999999999,
"loss": 0.2158,
"step": 303
},
{
"epoch": 1.3,
"learning_rate": 0.00011371428571428573,
"loss": 0.5453,
"step": 304
},
{
"epoch": 1.3,
"learning_rate": 0.00011342857142857144,
"loss": 0.0,
"step": 305
},
{
"epoch": 1.3,
"learning_rate": 0.00011314285714285715,
"loss": 0.4729,
"step": 306
},
{
"epoch": 1.31,
"learning_rate": 0.00011285714285714286,
"loss": 0.5862,
"step": 307
},
{
"epoch": 1.31,
"learning_rate": 0.00011257142857142857,
"loss": 0.5019,
"step": 308
},
{
"epoch": 1.32,
"learning_rate": 0.00011228571428571429,
"loss": 0.4349,
"step": 309
},
{
"epoch": 1.32,
"learning_rate": 0.00011200000000000001,
"loss": 0.4498,
"step": 310
},
{
"epoch": 1.33,
"learning_rate": 0.00011171428571428572,
"loss": 0.4801,
"step": 311
},
{
"epoch": 1.33,
"learning_rate": 0.00011142857142857144,
"loss": 0.543,
"step": 312
},
{
"epoch": 1.33,
"eval_loss": 0.5917356610298157,
"eval_runtime": 1562.9396,
"eval_samples_per_second": 1.2,
"eval_steps_per_second": 0.075,
"step": 312
},
{
"epoch": 1.33,
"learning_rate": 0.00011114285714285715,
"loss": 0.4844,
"step": 313
},
{
"epoch": 1.34,
"learning_rate": 0.00011085714285714286,
"loss": 0.3309,
"step": 314
},
{
"epoch": 1.34,
"learning_rate": 0.00011057142857142857,
"loss": 0.506,
"step": 315
},
{
"epoch": 1.35,
"learning_rate": 0.00011028571428571428,
"loss": 0.5563,
"step": 316
},
{
"epoch": 1.35,
"learning_rate": 0.00011000000000000002,
"loss": 0.4575,
"step": 317
},
{
"epoch": 1.36,
"learning_rate": 0.00010971428571428573,
"loss": 0.2696,
"step": 318
},
{
"epoch": 1.36,
"learning_rate": 0.00010942857142857144,
"loss": 0.2765,
"step": 319
},
{
"epoch": 1.36,
"learning_rate": 0.00010914285714285715,
"loss": 0.4818,
"step": 320
},
{
"epoch": 1.37,
"learning_rate": 0.00010885714285714285,
"loss": 0.559,
"step": 321
},
{
"epoch": 1.37,
"learning_rate": 0.00010857142857142856,
"loss": 0.6017,
"step": 322
},
{
"epoch": 1.38,
"learning_rate": 0.0001082857142857143,
"loss": 0.4697,
"step": 323
},
{
"epoch": 1.38,
"learning_rate": 0.00010800000000000001,
"loss": 0.3145,
"step": 324
},
{
"epoch": 1.39,
"learning_rate": 0.00010771428571428572,
"loss": 0.5289,
"step": 325
},
{
"epoch": 1.39,
"learning_rate": 0.00010742857142857143,
"loss": 0.2548,
"step": 326
},
{
"epoch": 1.39,
"learning_rate": 0.00010714285714285715,
"loss": 0.4574,
"step": 327
},
{
"epoch": 1.4,
"learning_rate": 0.00010685714285714286,
"loss": 0.2218,
"step": 328
},
{
"epoch": 1.4,
"learning_rate": 0.00010657142857142857,
"loss": 0.2075,
"step": 329
},
{
"epoch": 1.41,
"learning_rate": 0.0001062857142857143,
"loss": 0.0,
"step": 330
},
{
"epoch": 1.41,
"learning_rate": 0.00010600000000000002,
"loss": 0.2811,
"step": 331
},
{
"epoch": 1.42,
"learning_rate": 0.00010571428571428572,
"loss": 0.5367,
"step": 332
},
{
"epoch": 1.42,
"learning_rate": 0.00010542857142857143,
"loss": 0.2492,
"step": 333
},
{
"epoch": 1.42,
"learning_rate": 0.00010514285714285714,
"loss": 0.5545,
"step": 334
},
{
"epoch": 1.43,
"learning_rate": 0.00010485714285714285,
"loss": 0.4695,
"step": 335
},
{
"epoch": 1.43,
"learning_rate": 0.00010457142857142859,
"loss": 0.2355,
"step": 336
},
{
"epoch": 1.44,
"learning_rate": 0.0001042857142857143,
"loss": 0.2043,
"step": 337
},
{
"epoch": 1.44,
"learning_rate": 0.00010400000000000001,
"loss": 0.2406,
"step": 338
},
{
"epoch": 1.45,
"learning_rate": 0.00010371428571428572,
"loss": 0.5014,
"step": 339
},
{
"epoch": 1.45,
"learning_rate": 0.00010342857142857143,
"loss": 0.5004,
"step": 340
},
{
"epoch": 1.45,
"learning_rate": 0.00010314285714285713,
"loss": 0.2107,
"step": 341
},
{
"epoch": 1.46,
"learning_rate": 0.00010285714285714286,
"loss": 0.504,
"step": 342
},
{
"epoch": 1.46,
"learning_rate": 0.00010257142857142858,
"loss": 0.4805,
"step": 343
},
{
"epoch": 1.47,
"learning_rate": 0.00010228571428571429,
"loss": 0.5978,
"step": 344
},
{
"epoch": 1.47,
"learning_rate": 0.00010200000000000001,
"loss": 0.6218,
"step": 345
},
{
"epoch": 1.48,
"learning_rate": 0.00010171428571428572,
"loss": 0.6061,
"step": 346
},
{
"epoch": 1.48,
"learning_rate": 0.00010142857142857143,
"loss": 0.2479,
"step": 347
},
{
"epoch": 1.48,
"learning_rate": 0.00010114285714285714,
"loss": 0.0,
"step": 348
},
{
"epoch": 1.49,
"learning_rate": 0.00010085714285714288,
"loss": 0.5067,
"step": 349
},
{
"epoch": 1.49,
"learning_rate": 0.00010057142857142859,
"loss": 0.5332,
"step": 350
},
{
"epoch": 1.5,
"learning_rate": 0.0001002857142857143,
"loss": 0.2303,
"step": 351
},
{
"epoch": 1.5,
"learning_rate": 0.0001,
"loss": 0.5534,
"step": 352
},
{
"epoch": 1.51,
"learning_rate": 9.971428571428571e-05,
"loss": 0.5458,
"step": 353
},
{
"epoch": 1.51,
"learning_rate": 9.942857142857144e-05,
"loss": 0.5636,
"step": 354
},
{
"epoch": 1.51,
"learning_rate": 9.914285714285715e-05,
"loss": 0.2772,
"step": 355
},
{
"epoch": 1.52,
"learning_rate": 9.885714285714286e-05,
"loss": 0.5272,
"step": 356
},
{
"epoch": 1.52,
"learning_rate": 9.857142857142858e-05,
"loss": 0.4601,
"step": 357
},
{
"epoch": 1.53,
"learning_rate": 9.828571428571429e-05,
"loss": 0.2554,
"step": 358
},
{
"epoch": 1.53,
"learning_rate": 9.8e-05,
"loss": 0.2182,
"step": 359
},
{
"epoch": 1.54,
"learning_rate": 9.771428571428572e-05,
"loss": 0.4628,
"step": 360
},
{
"epoch": 1.54,
"learning_rate": 9.742857142857143e-05,
"loss": 0.4876,
"step": 361
},
{
"epoch": 1.54,
"learning_rate": 9.714285714285715e-05,
"loss": 0.2391,
"step": 362
},
{
"epoch": 1.55,
"learning_rate": 9.685714285714286e-05,
"loss": 0.1768,
"step": 363
},
{
"epoch": 1.55,
"learning_rate": 9.657142857142858e-05,
"loss": 0.2388,
"step": 364
},
{
"epoch": 1.56,
"learning_rate": 9.628571428571429e-05,
"loss": 0.496,
"step": 365
},
{
"epoch": 1.56,
"learning_rate": 9.6e-05,
"loss": 0.4982,
"step": 366
},
{
"epoch": 1.57,
"learning_rate": 9.571428571428573e-05,
"loss": 0.359,
"step": 367
},
{
"epoch": 1.57,
"learning_rate": 9.542857142857143e-05,
"loss": 0.2397,
"step": 368
},
{
"epoch": 1.57,
"learning_rate": 9.514285714285714e-05,
"loss": 0.5008,
"step": 369
},
{
"epoch": 1.58,
"learning_rate": 9.485714285714287e-05,
"loss": 0.459,
"step": 370
},
{
"epoch": 1.58,
"learning_rate": 9.457142857142858e-05,
"loss": 0.531,
"step": 371
},
{
"epoch": 1.59,
"learning_rate": 9.428571428571429e-05,
"loss": 0.2583,
"step": 372
},
{
"epoch": 1.59,
"learning_rate": 9.4e-05,
"loss": 0.546,
"step": 373
},
{
"epoch": 1.59,
"learning_rate": 9.371428571428572e-05,
"loss": 0.5497,
"step": 374
},
{
"epoch": 1.6,
"learning_rate": 9.342857142857143e-05,
"loss": 0.5183,
"step": 375
},
{
"epoch": 1.6,
"learning_rate": 9.314285714285715e-05,
"loss": 0.4635,
"step": 376
},
{
"epoch": 1.61,
"learning_rate": 9.285714285714286e-05,
"loss": 0.3109,
"step": 377
},
{
"epoch": 1.61,
"learning_rate": 9.257142857142858e-05,
"loss": 0.6068,
"step": 378
},
{
"epoch": 1.62,
"learning_rate": 9.228571428571429e-05,
"loss": 0.5329,
"step": 379
},
{
"epoch": 1.62,
"learning_rate": 9.200000000000001e-05,
"loss": 0.0,
"step": 380
},
{
"epoch": 1.62,
"learning_rate": 9.171428571428572e-05,
"loss": 0.2379,
"step": 381
},
{
"epoch": 1.63,
"learning_rate": 9.142857142857143e-05,
"loss": 0.2438,
"step": 382
},
{
"epoch": 1.63,
"learning_rate": 9.114285714285716e-05,
"loss": 0.2955,
"step": 383
},
{
"epoch": 1.64,
"learning_rate": 9.085714285714286e-05,
"loss": 0.611,
"step": 384
},
{
"epoch": 1.64,
"learning_rate": 9.057142857142857e-05,
"loss": 0.5006,
"step": 385
},
{
"epoch": 1.65,
"learning_rate": 9.028571428571428e-05,
"loss": 0.2587,
"step": 386
},
{
"epoch": 1.65,
"learning_rate": 9e-05,
"loss": 0.4701,
"step": 387
},
{
"epoch": 1.65,
"learning_rate": 8.971428571428571e-05,
"loss": 0.4542,
"step": 388
},
{
"epoch": 1.66,
"learning_rate": 8.942857142857142e-05,
"loss": 0.5007,
"step": 389
},
{
"epoch": 1.66,
"learning_rate": 8.914285714285715e-05,
"loss": 0.4928,
"step": 390
},
{
"epoch": 1.67,
"learning_rate": 8.885714285714286e-05,
"loss": 0.2497,
"step": 391
},
{
"epoch": 1.67,
"learning_rate": 8.857142857142857e-05,
"loss": 0.2738,
"step": 392
},
{
"epoch": 1.68,
"learning_rate": 8.828571428571429e-05,
"loss": 0.2695,
"step": 393
},
{
"epoch": 1.68,
"learning_rate": 8.800000000000001e-05,
"loss": 0.5416,
"step": 394
},
{
"epoch": 1.68,
"learning_rate": 8.771428571428572e-05,
"loss": 0.2894,
"step": 395
},
{
"epoch": 1.69,
"learning_rate": 8.742857142857144e-05,
"loss": 0.4632,
"step": 396
},
{
"epoch": 1.69,
"learning_rate": 8.714285714285715e-05,
"loss": 0.2167,
"step": 397
},
{
"epoch": 1.7,
"learning_rate": 8.685714285714286e-05,
"loss": 0.4987,
"step": 398
},
{
"epoch": 1.7,
"learning_rate": 8.657142857142858e-05,
"loss": 0.512,
"step": 399
},
{
"epoch": 1.71,
"learning_rate": 8.62857142857143e-05,
"loss": 0.5179,
"step": 400
},
{
"epoch": 1.71,
"learning_rate": 8.6e-05,
"loss": 0.504,
"step": 401
},
{
"epoch": 1.71,
"learning_rate": 8.571428571428571e-05,
"loss": 0.2728,
"step": 402
},
{
"epoch": 1.72,
"learning_rate": 8.542857142857144e-05,
"loss": 0.5236,
"step": 403
},
{
"epoch": 1.72,
"learning_rate": 8.514285714285714e-05,
"loss": 0.5132,
"step": 404
},
{
"epoch": 1.73,
"learning_rate": 8.485714285714285e-05,
"loss": 0.2241,
"step": 405
},
{
"epoch": 1.73,
"learning_rate": 8.457142857142858e-05,
"loss": 0.5491,
"step": 406
},
{
"epoch": 1.74,
"learning_rate": 8.428571428571429e-05,
"loss": 0.1936,
"step": 407
},
{
"epoch": 1.74,
"learning_rate": 8.4e-05,
"loss": 0.5554,
"step": 408
},
{
"epoch": 1.74,
"learning_rate": 8.371428571428572e-05,
"loss": 0.0,
"step": 409
},
{
"epoch": 1.75,
"learning_rate": 8.342857142857143e-05,
"loss": 0.4438,
"step": 410
},
{
"epoch": 1.75,
"learning_rate": 8.314285714285715e-05,
"loss": 0.4715,
"step": 411
},
{
"epoch": 1.76,
"learning_rate": 8.285714285714287e-05,
"loss": 0.4966,
"step": 412
},
{
"epoch": 1.76,
"learning_rate": 8.257142857142858e-05,
"loss": 0.5258,
"step": 413
},
{
"epoch": 1.77,
"learning_rate": 8.228571428571429e-05,
"loss": 0.4949,
"step": 414
},
{
"epoch": 1.77,
"learning_rate": 8.2e-05,
"loss": 0.4774,
"step": 415
},
{
"epoch": 1.77,
"learning_rate": 8.171428571428572e-05,
"loss": 0.4824,
"step": 416
},
{
"epoch": 1.78,
"learning_rate": 8.142857142857143e-05,
"loss": 0.5794,
"step": 417
},
{
"epoch": 1.78,
"learning_rate": 8.114285714285714e-05,
"loss": 0.5633,
"step": 418
},
{
"epoch": 1.79,
"learning_rate": 8.085714285714287e-05,
"loss": 0.4954,
"step": 419
},
{
"epoch": 1.79,
"learning_rate": 8.057142857142857e-05,
"loss": 0.5098,
"step": 420
},
{
"epoch": 1.8,
"learning_rate": 8.028571428571428e-05,
"loss": 0.5255,
"step": 421
},
{
"epoch": 1.8,
"learning_rate": 8e-05,
"loss": 0.2379,
"step": 422
},
{
"epoch": 1.8,
"learning_rate": 7.971428571428572e-05,
"loss": 0.2548,
"step": 423
},
{
"epoch": 1.81,
"learning_rate": 7.942857142857143e-05,
"loss": 0.5137,
"step": 424
},
{
"epoch": 1.81,
"learning_rate": 7.914285714285715e-05,
"loss": 0.4868,
"step": 425
},
{
"epoch": 1.82,
"learning_rate": 7.885714285714286e-05,
"loss": 0.5019,
"step": 426
},
{
"epoch": 1.82,
"learning_rate": 7.857142857142858e-05,
"loss": 0.5176,
"step": 427
},
{
"epoch": 1.83,
"learning_rate": 7.828571428571429e-05,
"loss": 0.4978,
"step": 428
},
{
"epoch": 1.83,
"learning_rate": 7.800000000000001e-05,
"loss": 0.5346,
"step": 429
},
{
"epoch": 1.83,
"learning_rate": 7.771428571428572e-05,
"loss": 0.5214,
"step": 430
},
{
"epoch": 1.84,
"learning_rate": 7.742857142857143e-05,
"loss": 0.5191,
"step": 431
},
{
"epoch": 1.84,
"learning_rate": 7.714285714285715e-05,
"loss": 0.5597,
"step": 432
},
{
"epoch": 1.85,
"learning_rate": 7.685714285714286e-05,
"loss": 0.0,
"step": 433
},
{
"epoch": 1.85,
"learning_rate": 7.657142857142857e-05,
"loss": 0.483,
"step": 434
},
{
"epoch": 1.86,
"learning_rate": 7.62857142857143e-05,
"loss": 0.2921,
"step": 435
},
{
"epoch": 1.86,
"learning_rate": 7.6e-05,
"loss": 0.2412,
"step": 436
},
{
"epoch": 1.86,
"learning_rate": 7.571428571428571e-05,
"loss": 0.5215,
"step": 437
},
{
"epoch": 1.87,
"learning_rate": 7.542857142857144e-05,
"loss": 0.6186,
"step": 438
},
{
"epoch": 1.87,
"learning_rate": 7.514285714285715e-05,
"loss": 0.5237,
"step": 439
},
{
"epoch": 1.88,
"learning_rate": 7.485714285714285e-05,
"loss": 0.472,
"step": 440
},
{
"epoch": 1.88,
"learning_rate": 7.457142857142856e-05,
"loss": 0.2273,
"step": 441
},
{
"epoch": 1.88,
"learning_rate": 7.428571428571429e-05,
"loss": 0.2752,
"step": 442
},
{
"epoch": 1.89,
"learning_rate": 7.4e-05,
"loss": 0.276,
"step": 443
},
{
"epoch": 1.89,
"learning_rate": 7.371428571428572e-05,
"loss": 0.4708,
"step": 444
},
{
"epoch": 1.9,
"learning_rate": 7.342857142857144e-05,
"loss": 0.5655,
"step": 445
},
{
"epoch": 1.9,
"learning_rate": 7.314285714285715e-05,
"loss": 0.2586,
"step": 446
},
{
"epoch": 1.91,
"learning_rate": 7.285714285714286e-05,
"loss": 0.4855,
"step": 447
},
{
"epoch": 1.91,
"learning_rate": 7.257142857142858e-05,
"loss": 0.4462,
"step": 448
},
{
"epoch": 1.91,
"learning_rate": 7.228571428571429e-05,
"loss": 0.2632,
"step": 449
},
{
"epoch": 1.92,
"learning_rate": 7.2e-05,
"loss": 0.5313,
"step": 450
},
{
"epoch": 1.92,
"learning_rate": 7.171428571428572e-05,
"loss": 0.445,
"step": 451
},
{
"epoch": 1.93,
"learning_rate": 7.142857142857143e-05,
"loss": 0.5304,
"step": 452
},
{
"epoch": 1.93,
"learning_rate": 7.114285714285714e-05,
"loss": 0.4489,
"step": 453
},
{
"epoch": 1.94,
"learning_rate": 7.085714285714285e-05,
"loss": 0.2393,
"step": 454
},
{
"epoch": 1.94,
"learning_rate": 7.057142857142858e-05,
"loss": 0.5507,
"step": 455
},
{
"epoch": 1.94,
"learning_rate": 7.028571428571428e-05,
"loss": 0.5592,
"step": 456
},
{
"epoch": 1.95,
"learning_rate": 7e-05,
"loss": 0.5479,
"step": 457
},
{
"epoch": 1.95,
"learning_rate": 6.971428571428572e-05,
"loss": 0.4952,
"step": 458
},
{
"epoch": 1.96,
"learning_rate": 6.942857142857143e-05,
"loss": 0.4236,
"step": 459
},
{
"epoch": 1.96,
"learning_rate": 6.914285714285715e-05,
"loss": 0.251,
"step": 460
},
{
"epoch": 1.97,
"learning_rate": 6.885714285714286e-05,
"loss": 0.3061,
"step": 461
},
{
"epoch": 1.97,
"learning_rate": 6.857142857142858e-05,
"loss": 0.5265,
"step": 462
},
{
"epoch": 1.97,
"learning_rate": 6.828571428571429e-05,
"loss": 0.498,
"step": 463
},
{
"epoch": 1.98,
"learning_rate": 6.800000000000001e-05,
"loss": 0.5493,
"step": 464
},
{
"epoch": 1.98,
"learning_rate": 6.771428571428572e-05,
"loss": 0.5524,
"step": 465
},
{
"epoch": 1.99,
"learning_rate": 6.742857142857143e-05,
"loss": 0.2636,
"step": 466
},
{
"epoch": 1.99,
"learning_rate": 6.714285714285714e-05,
"loss": 0.5376,
"step": 467
},
{
"epoch": 2.0,
"learning_rate": 6.685714285714286e-05,
"loss": 0.5096,
"step": 468
},
{
"epoch": 2.0,
"eval_loss": 0.5827586054801941,
"eval_runtime": 1563.9385,
"eval_samples_per_second": 1.199,
"eval_steps_per_second": 0.075,
"step": 468
},
{
"epoch": 2.0,
"learning_rate": 6.657142857142857e-05,
"loss": 0.478,
"step": 469
},
{
"epoch": 2.0,
"learning_rate": 6.628571428571428e-05,
"loss": 0.4552,
"step": 470
},
{
"epoch": 2.01,
"learning_rate": 6.6e-05,
"loss": 0.4154,
"step": 471
},
{
"epoch": 2.01,
"learning_rate": 6.571428571428571e-05,
"loss": 0.4325,
"step": 472
},
{
"epoch": 2.02,
"learning_rate": 6.542857142857142e-05,
"loss": 0.4623,
"step": 473
},
{
"epoch": 2.02,
"learning_rate": 6.514285714285715e-05,
"loss": 0.213,
"step": 474
},
{
"epoch": 2.03,
"learning_rate": 6.485714285714286e-05,
"loss": 0.4647,
"step": 475
},
{
"epoch": 2.03,
"learning_rate": 6.457142857142856e-05,
"loss": 0.2709,
"step": 476
},
{
"epoch": 2.03,
"learning_rate": 6.428571428571429e-05,
"loss": 0.2404,
"step": 477
},
{
"epoch": 2.04,
"learning_rate": 6.400000000000001e-05,
"loss": 0.3752,
"step": 478
},
{
"epoch": 2.04,
"learning_rate": 6.371428571428572e-05,
"loss": 0.1919,
"step": 479
},
{
"epoch": 2.05,
"learning_rate": 6.342857142857143e-05,
"loss": 0.1925,
"step": 480
},
{
"epoch": 2.05,
"learning_rate": 6.314285714285715e-05,
"loss": 0.4813,
"step": 481
},
{
"epoch": 2.06,
"learning_rate": 6.285714285714286e-05,
"loss": 0.3845,
"step": 482
},
{
"epoch": 2.06,
"learning_rate": 6.257142857142857e-05,
"loss": 0.4856,
"step": 483
},
{
"epoch": 2.06,
"learning_rate": 6.22857142857143e-05,
"loss": 0.2222,
"step": 484
},
{
"epoch": 2.07,
"learning_rate": 6.2e-05,
"loss": 0.432,
"step": 485
},
{
"epoch": 2.07,
"learning_rate": 6.171428571428571e-05,
"loss": 0.4278,
"step": 486
},
{
"epoch": 2.08,
"learning_rate": 6.142857142857143e-05,
"loss": 0.4307,
"step": 487
},
{
"epoch": 2.08,
"learning_rate": 6.114285714285714e-05,
"loss": 0.3181,
"step": 488
},
{
"epoch": 2.09,
"learning_rate": 6.085714285714286e-05,
"loss": 0.4632,
"step": 489
},
{
"epoch": 2.09,
"learning_rate": 6.0571428571428576e-05,
"loss": 0.5209,
"step": 490
},
{
"epoch": 2.09,
"learning_rate": 6.028571428571429e-05,
"loss": 0.1741,
"step": 491
},
{
"epoch": 2.1,
"learning_rate": 6e-05,
"loss": 0.4042,
"step": 492
},
{
"epoch": 2.1,
"learning_rate": 5.9714285714285724e-05,
"loss": 0.4208,
"step": 493
},
{
"epoch": 2.11,
"learning_rate": 5.9428571428571434e-05,
"loss": 0.1973,
"step": 494
},
{
"epoch": 2.11,
"learning_rate": 5.914285714285714e-05,
"loss": 0.4091,
"step": 495
},
{
"epoch": 2.12,
"learning_rate": 5.885714285714285e-05,
"loss": 0.194,
"step": 496
},
{
"epoch": 2.12,
"learning_rate": 5.8571428571428575e-05,
"loss": 0.4531,
"step": 497
},
{
"epoch": 2.12,
"learning_rate": 5.828571428571429e-05,
"loss": 0.5006,
"step": 498
},
{
"epoch": 2.13,
"learning_rate": 5.8e-05,
"loss": 0.4122,
"step": 499
},
{
"epoch": 2.13,
"learning_rate": 5.771428571428572e-05,
"loss": 0.3595,
"step": 500
},
{
"epoch": 2.14,
"learning_rate": 5.742857142857143e-05,
"loss": 0.4742,
"step": 501
},
{
"epoch": 2.14,
"learning_rate": 5.714285714285714e-05,
"loss": 0.4729,
"step": 502
},
{
"epoch": 2.14,
"learning_rate": 5.6857142857142865e-05,
"loss": 0.2293,
"step": 503
},
{
"epoch": 2.15,
"learning_rate": 5.6571428571428574e-05,
"loss": 0.148,
"step": 504
},
{
"epoch": 2.15,
"learning_rate": 5.628571428571428e-05,
"loss": 0.4009,
"step": 505
},
{
"epoch": 2.16,
"learning_rate": 5.6000000000000006e-05,
"loss": 0.4595,
"step": 506
},
{
"epoch": 2.16,
"learning_rate": 5.571428571428572e-05,
"loss": 0.3895,
"step": 507
},
{
"epoch": 2.17,
"learning_rate": 5.542857142857143e-05,
"loss": 0.496,
"step": 508
},
{
"epoch": 2.17,
"learning_rate": 5.514285714285714e-05,
"loss": 0.3753,
"step": 509
},
{
"epoch": 2.17,
"learning_rate": 5.485714285714286e-05,
"loss": 0.2138,
"step": 510
},
{
"epoch": 2.18,
"learning_rate": 5.457142857142857e-05,
"loss": 0.4423,
"step": 511
},
{
"epoch": 2.18,
"learning_rate": 5.428571428571428e-05,
"loss": 0.2311,
"step": 512
},
{
"epoch": 2.19,
"learning_rate": 5.4000000000000005e-05,
"loss": 0.1998,
"step": 513
},
{
"epoch": 2.19,
"learning_rate": 5.3714285714285714e-05,
"loss": 0.4036,
"step": 514
},
{
"epoch": 2.2,
"learning_rate": 5.342857142857143e-05,
"loss": 0.3902,
"step": 515
},
{
"epoch": 2.2,
"learning_rate": 5.314285714285715e-05,
"loss": 0.4179,
"step": 516
},
{
"epoch": 2.2,
"learning_rate": 5.285714285714286e-05,
"loss": 0.4109,
"step": 517
},
{
"epoch": 2.21,
"learning_rate": 5.257142857142857e-05,
"loss": 0.4367,
"step": 518
},
{
"epoch": 2.21,
"learning_rate": 5.2285714285714294e-05,
"loss": 0.4399,
"step": 519
},
{
"epoch": 2.22,
"learning_rate": 5.2000000000000004e-05,
"loss": 0.4855,
"step": 520
},
{
"epoch": 2.22,
"learning_rate": 5.171428571428571e-05,
"loss": 0.5074,
"step": 521
},
{
"epoch": 2.23,
"learning_rate": 5.142857142857143e-05,
"loss": 0.2548,
"step": 522
},
{
"epoch": 2.23,
"learning_rate": 5.1142857142857145e-05,
"loss": 0.428,
"step": 523
},
{
"epoch": 2.23,
"learning_rate": 5.085714285714286e-05,
"loss": 0.4145,
"step": 524
},
{
"epoch": 2.24,
"learning_rate": 5.057142857142857e-05,
"loss": 0.4008,
"step": 525
},
{
"epoch": 2.24,
"learning_rate": 5.028571428571429e-05,
"loss": 0.1577,
"step": 526
},
{
"epoch": 2.25,
"learning_rate": 5e-05,
"loss": 0.4742,
"step": 527
},
{
"epoch": 2.25,
"learning_rate": 4.971428571428572e-05,
"loss": 0.3333,
"step": 528
},
{
"epoch": 2.26,
"learning_rate": 4.942857142857143e-05,
"loss": 0.1753,
"step": 529
},
{
"epoch": 2.26,
"learning_rate": 4.9142857142857144e-05,
"loss": 0.0,
"step": 530
},
{
"epoch": 2.26,
"learning_rate": 4.885714285714286e-05,
"loss": 0.5164,
"step": 531
},
{
"epoch": 2.27,
"learning_rate": 4.8571428571428576e-05,
"loss": 0.6013,
"step": 532
},
{
"epoch": 2.27,
"learning_rate": 4.828571428571429e-05,
"loss": 0.2088,
"step": 533
},
{
"epoch": 2.28,
"learning_rate": 4.8e-05,
"loss": 0.2234,
"step": 534
},
{
"epoch": 2.28,
"learning_rate": 4.771428571428572e-05,
"loss": 0.2207,
"step": 535
},
{
"epoch": 2.29,
"learning_rate": 4.742857142857143e-05,
"loss": 0.2416,
"step": 536
},
{
"epoch": 2.29,
"learning_rate": 4.714285714285714e-05,
"loss": 0.4357,
"step": 537
},
{
"epoch": 2.29,
"learning_rate": 4.685714285714286e-05,
"loss": 0.1677,
"step": 538
},
{
"epoch": 2.3,
"learning_rate": 4.6571428571428575e-05,
"loss": 0.38,
"step": 539
},
{
"epoch": 2.3,
"learning_rate": 4.628571428571429e-05,
"loss": 0.1935,
"step": 540
},
{
"epoch": 2.31,
"learning_rate": 4.600000000000001e-05,
"loss": 0.4036,
"step": 541
},
{
"epoch": 2.31,
"learning_rate": 4.5714285714285716e-05,
"loss": 0.441,
"step": 542
},
{
"epoch": 2.32,
"learning_rate": 4.542857142857143e-05,
"loss": 0.4819,
"step": 543
},
{
"epoch": 2.32,
"learning_rate": 4.514285714285714e-05,
"loss": 0.4479,
"step": 544
},
{
"epoch": 2.32,
"learning_rate": 4.485714285714286e-05,
"loss": 0.3762,
"step": 545
},
{
"epoch": 2.33,
"learning_rate": 4.4571428571428574e-05,
"loss": 0.4078,
"step": 546
},
{
"epoch": 2.33,
"learning_rate": 4.428571428571428e-05,
"loss": 0.4524,
"step": 547
},
{
"epoch": 2.34,
"learning_rate": 4.4000000000000006e-05,
"loss": 0.1786,
"step": 548
},
{
"epoch": 2.34,
"learning_rate": 4.371428571428572e-05,
"loss": 0.5071,
"step": 549
},
{
"epoch": 2.35,
"learning_rate": 4.342857142857143e-05,
"loss": 0.4131,
"step": 550
},
{
"epoch": 2.35,
"learning_rate": 4.314285714285715e-05,
"loss": 0.3809,
"step": 551
},
{
"epoch": 2.35,
"learning_rate": 4.2857142857142856e-05,
"loss": 0.3859,
"step": 552
},
{
"epoch": 2.36,
"learning_rate": 4.257142857142857e-05,
"loss": 0.4347,
"step": 553
},
{
"epoch": 2.36,
"learning_rate": 4.228571428571429e-05,
"loss": 0.4118,
"step": 554
},
{
"epoch": 2.37,
"learning_rate": 4.2e-05,
"loss": 0.4506,
"step": 555
},
{
"epoch": 2.37,
"learning_rate": 4.1714285714285714e-05,
"loss": 0.1577,
"step": 556
},
{
"epoch": 2.38,
"learning_rate": 4.1428571428571437e-05,
"loss": 0.5172,
"step": 557
},
{
"epoch": 2.38,
"learning_rate": 4.1142857142857146e-05,
"loss": 0.3893,
"step": 558
},
{
"epoch": 2.38,
"learning_rate": 4.085714285714286e-05,
"loss": 0.2105,
"step": 559
},
{
"epoch": 2.39,
"learning_rate": 4.057142857142857e-05,
"loss": 0.3578,
"step": 560
},
{
"epoch": 2.39,
"learning_rate": 4.028571428571429e-05,
"loss": 0.4687,
"step": 561
},
{
"epoch": 2.4,
"learning_rate": 4e-05,
"loss": 0.4575,
"step": 562
},
{
"epoch": 2.4,
"learning_rate": 3.971428571428571e-05,
"loss": 0.4601,
"step": 563
},
{
"epoch": 2.41,
"learning_rate": 3.942857142857143e-05,
"loss": 0.415,
"step": 564
},
{
"epoch": 2.41,
"learning_rate": 3.9142857142857145e-05,
"loss": 0.3903,
"step": 565
},
{
"epoch": 2.41,
"learning_rate": 3.885714285714286e-05,
"loss": 0.3971,
"step": 566
},
{
"epoch": 2.42,
"learning_rate": 3.857142857142858e-05,
"loss": 0.2367,
"step": 567
},
{
"epoch": 2.42,
"learning_rate": 3.8285714285714286e-05,
"loss": 0.4101,
"step": 568
},
{
"epoch": 2.43,
"learning_rate": 3.8e-05,
"loss": 0.2097,
"step": 569
},
{
"epoch": 2.43,
"learning_rate": 3.771428571428572e-05,
"loss": 0.2104,
"step": 570
},
{
"epoch": 2.43,
"learning_rate": 3.742857142857143e-05,
"loss": 0.2127,
"step": 571
},
{
"epoch": 2.44,
"learning_rate": 3.7142857142857143e-05,
"loss": 0.0,
"step": 572
},
{
"epoch": 2.44,
"learning_rate": 3.685714285714286e-05,
"loss": 0.2634,
"step": 573
},
{
"epoch": 2.45,
"learning_rate": 3.6571428571428576e-05,
"loss": 0.2355,
"step": 574
},
{
"epoch": 2.45,
"learning_rate": 3.628571428571429e-05,
"loss": 0.4657,
"step": 575
},
{
"epoch": 2.46,
"learning_rate": 3.6e-05,
"loss": 0.4302,
"step": 576
},
{
"epoch": 2.46,
"learning_rate": 3.571428571428572e-05,
"loss": 0.4919,
"step": 577
},
{
"epoch": 2.46,
"learning_rate": 3.5428571428571426e-05,
"loss": 0.3743,
"step": 578
},
{
"epoch": 2.47,
"learning_rate": 3.514285714285714e-05,
"loss": 0.5134,
"step": 579
},
{
"epoch": 2.47,
"learning_rate": 3.485714285714286e-05,
"loss": 0.1762,
"step": 580
},
{
"epoch": 2.48,
"learning_rate": 3.4571428571428574e-05,
"loss": 0.2209,
"step": 581
},
{
"epoch": 2.48,
"learning_rate": 3.428571428571429e-05,
"loss": 0.3631,
"step": 582
},
{
"epoch": 2.49,
"learning_rate": 3.4000000000000007e-05,
"loss": 0.2325,
"step": 583
},
{
"epoch": 2.49,
"learning_rate": 3.3714285714285716e-05,
"loss": 0.2333,
"step": 584
},
{
"epoch": 2.49,
"learning_rate": 3.342857142857143e-05,
"loss": 0.1782,
"step": 585
},
{
"epoch": 2.5,
"learning_rate": 3.314285714285714e-05,
"loss": 0.3975,
"step": 586
},
{
"epoch": 2.5,
"learning_rate": 3.285714285714286e-05,
"loss": 0.3905,
"step": 587
},
{
"epoch": 2.51,
"learning_rate": 3.257142857142857e-05,
"loss": 0.422,
"step": 588
},
{
"epoch": 2.51,
"learning_rate": 3.228571428571428e-05,
"loss": 0.3792,
"step": 589
},
{
"epoch": 2.52,
"learning_rate": 3.2000000000000005e-05,
"loss": 0.4195,
"step": 590
},
{
"epoch": 2.52,
"learning_rate": 3.1714285714285715e-05,
"loss": 0.4027,
"step": 591
},
{
"epoch": 2.52,
"learning_rate": 3.142857142857143e-05,
"loss": 0.4494,
"step": 592
},
{
"epoch": 2.53,
"learning_rate": 3.114285714285715e-05,
"loss": 0.196,
"step": 593
},
{
"epoch": 2.53,
"learning_rate": 3.0857142857142856e-05,
"loss": 0.416,
"step": 594
},
{
"epoch": 2.54,
"learning_rate": 3.057142857142857e-05,
"loss": 0.3842,
"step": 595
},
{
"epoch": 2.54,
"learning_rate": 3.0285714285714288e-05,
"loss": 0.3978,
"step": 596
},
{
"epoch": 2.55,
"learning_rate": 3e-05,
"loss": 0.3982,
"step": 597
},
{
"epoch": 2.55,
"learning_rate": 2.9714285714285717e-05,
"loss": 0.2196,
"step": 598
},
{
"epoch": 2.55,
"learning_rate": 2.9428571428571426e-05,
"loss": 0.4399,
"step": 599
},
{
"epoch": 2.56,
"learning_rate": 2.9142857142857146e-05,
"loss": 0.4312,
"step": 600
},
{
"epoch": 2.56,
"learning_rate": 2.885714285714286e-05,
"loss": 0.4123,
"step": 601
},
{
"epoch": 2.57,
"learning_rate": 2.857142857142857e-05,
"loss": 0.468,
"step": 602
},
{
"epoch": 2.57,
"learning_rate": 2.8285714285714287e-05,
"loss": 0.4677,
"step": 603
},
{
"epoch": 2.58,
"learning_rate": 2.8000000000000003e-05,
"loss": 0.2242,
"step": 604
},
{
"epoch": 2.58,
"learning_rate": 2.7714285714285716e-05,
"loss": 0.1985,
"step": 605
},
{
"epoch": 2.58,
"learning_rate": 2.742857142857143e-05,
"loss": 0.3907,
"step": 606
},
{
"epoch": 2.59,
"learning_rate": 2.714285714285714e-05,
"loss": 0.473,
"step": 607
},
{
"epoch": 2.59,
"learning_rate": 2.6857142857142857e-05,
"loss": 0.206,
"step": 608
},
{
"epoch": 2.6,
"learning_rate": 2.6571428571428576e-05,
"loss": 0.418,
"step": 609
},
{
"epoch": 2.6,
"learning_rate": 2.6285714285714286e-05,
"loss": 0.4309,
"step": 610
},
{
"epoch": 2.61,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.1727,
"step": 611
},
{
"epoch": 2.61,
"learning_rate": 2.5714285714285714e-05,
"loss": 0.1889,
"step": 612
},
{
"epoch": 2.61,
"learning_rate": 2.542857142857143e-05,
"loss": 0.4209,
"step": 613
},
{
"epoch": 2.62,
"learning_rate": 2.5142857142857147e-05,
"loss": 0.3901,
"step": 614
},
{
"epoch": 2.62,
"learning_rate": 2.485714285714286e-05,
"loss": 0.3941,
"step": 615
},
{
"epoch": 2.63,
"learning_rate": 2.4571428571428572e-05,
"loss": 0.2347,
"step": 616
},
{
"epoch": 2.63,
"learning_rate": 2.4285714285714288e-05,
"loss": 0.2015,
"step": 617
},
{
"epoch": 2.64,
"learning_rate": 2.4e-05,
"loss": 0.1937,
"step": 618
},
{
"epoch": 2.64,
"learning_rate": 2.3714285714285717e-05,
"loss": 0.2606,
"step": 619
},
{
"epoch": 2.64,
"learning_rate": 2.342857142857143e-05,
"loss": 0.4302,
"step": 620
},
{
"epoch": 2.65,
"learning_rate": 2.3142857142857145e-05,
"loss": 0.1846,
"step": 621
},
{
"epoch": 2.65,
"learning_rate": 2.2857142857142858e-05,
"loss": 0.4557,
"step": 622
},
{
"epoch": 2.66,
"learning_rate": 2.257142857142857e-05,
"loss": 0.4581,
"step": 623
},
{
"epoch": 2.66,
"learning_rate": 2.2285714285714287e-05,
"loss": 0.3848,
"step": 624
},
{
"epoch": 2.66,
"eval_loss": 0.6022217273712158,
"eval_runtime": 1562.5817,
"eval_samples_per_second": 1.2,
"eval_steps_per_second": 0.076,
"step": 624
}
],
"logging_steps": 1,
"max_steps": 702,
"num_train_epochs": 3,
"save_steps": 156,
"total_flos": 4.242236129791181e+17,
"trial_name": null,
"trial_params": null
}