Files
snac-llm-full/last-checkpoint/trainer_state.json
ModelHub XC 6b6e60f317 初始化项目,由ModelHub XC社区提供模型
Model: YazoPi/snac-llm-full
Source: Original Platform
2026-05-30 05:31:19 +08:00

24093 lines
545 KiB
JSON

{
"best_global_step": 1000,
"best_metric": 4.025330543518066,
"best_model_checkpoint": "./snac_checkpoints-full/checkpoint-1000",
"epoch": 7.0,
"eval_steps": 500,
"global_step": 3430,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0020408163265306124,
"grad_norm": 270.0,
"learning_rate": 0.0,
"loss": 13.956,
"step": 1
},
{
"epoch": 0.004081632653061225,
"grad_norm": 262.0,
"learning_rate": 2.915451895043732e-07,
"loss": 13.8596,
"step": 2
},
{
"epoch": 0.006122448979591836,
"grad_norm": 286.0,
"learning_rate": 5.830903790087464e-07,
"loss": 13.9665,
"step": 3
},
{
"epoch": 0.00816326530612245,
"grad_norm": 270.0,
"learning_rate": 8.746355685131196e-07,
"loss": 13.9292,
"step": 4
},
{
"epoch": 0.01020408163265306,
"grad_norm": 214.0,
"learning_rate": 1.1661807580174927e-06,
"loss": 13.8249,
"step": 5
},
{
"epoch": 0.012244897959183673,
"grad_norm": 168.0,
"learning_rate": 1.457725947521866e-06,
"loss": 13.8095,
"step": 6
},
{
"epoch": 0.014285714285714285,
"grad_norm": 132.0,
"learning_rate": 1.7492711370262391e-06,
"loss": 13.6732,
"step": 7
},
{
"epoch": 0.0163265306122449,
"grad_norm": 112.0,
"learning_rate": 2.040816326530612e-06,
"loss": 13.6012,
"step": 8
},
{
"epoch": 0.018367346938775512,
"grad_norm": 93.5,
"learning_rate": 2.3323615160349855e-06,
"loss": 13.5982,
"step": 9
},
{
"epoch": 0.02040816326530612,
"grad_norm": 76.5,
"learning_rate": 2.623906705539359e-06,
"loss": 13.4279,
"step": 10
},
{
"epoch": 0.022448979591836733,
"grad_norm": 76.0,
"learning_rate": 2.915451895043732e-06,
"loss": 13.3568,
"step": 11
},
{
"epoch": 0.024489795918367346,
"grad_norm": 71.0,
"learning_rate": 3.2069970845481052e-06,
"loss": 13.2011,
"step": 12
},
{
"epoch": 0.026530612244897958,
"grad_norm": 63.5,
"learning_rate": 3.4985422740524782e-06,
"loss": 13.2092,
"step": 13
},
{
"epoch": 0.02857142857142857,
"grad_norm": 49.5,
"learning_rate": 3.7900874635568516e-06,
"loss": 13.1568,
"step": 14
},
{
"epoch": 0.030612244897959183,
"grad_norm": 43.75,
"learning_rate": 4.081632653061224e-06,
"loss": 13.0267,
"step": 15
},
{
"epoch": 0.0326530612244898,
"grad_norm": 35.75,
"learning_rate": 4.3731778425655976e-06,
"loss": 13.0138,
"step": 16
},
{
"epoch": 0.03469387755102041,
"grad_norm": 32.75,
"learning_rate": 4.664723032069971e-06,
"loss": 12.973,
"step": 17
},
{
"epoch": 0.036734693877551024,
"grad_norm": 33.0,
"learning_rate": 4.956268221574344e-06,
"loss": 12.8514,
"step": 18
},
{
"epoch": 0.03877551020408163,
"grad_norm": 26.375,
"learning_rate": 5.247813411078718e-06,
"loss": 12.8395,
"step": 19
},
{
"epoch": 0.04081632653061224,
"grad_norm": 22.25,
"learning_rate": 5.539358600583091e-06,
"loss": 12.7759,
"step": 20
},
{
"epoch": 0.04285714285714286,
"grad_norm": 17.25,
"learning_rate": 5.830903790087464e-06,
"loss": 12.6002,
"step": 21
},
{
"epoch": 0.044897959183673466,
"grad_norm": 19.375,
"learning_rate": 6.122448979591837e-06,
"loss": 12.6862,
"step": 22
},
{
"epoch": 0.04693877551020408,
"grad_norm": 17.125,
"learning_rate": 6.4139941690962105e-06,
"loss": 12.5866,
"step": 23
},
{
"epoch": 0.04897959183673469,
"grad_norm": 17.75,
"learning_rate": 6.705539358600584e-06,
"loss": 12.4753,
"step": 24
},
{
"epoch": 0.05102040816326531,
"grad_norm": 18.125,
"learning_rate": 6.9970845481049564e-06,
"loss": 12.4455,
"step": 25
},
{
"epoch": 0.053061224489795916,
"grad_norm": 12.9375,
"learning_rate": 7.28862973760933e-06,
"loss": 12.3216,
"step": 26
},
{
"epoch": 0.05510204081632653,
"grad_norm": 21.375,
"learning_rate": 7.580174927113703e-06,
"loss": 12.3599,
"step": 27
},
{
"epoch": 0.05714285714285714,
"grad_norm": 23.0,
"learning_rate": 7.871720116618077e-06,
"loss": 12.1911,
"step": 28
},
{
"epoch": 0.05918367346938776,
"grad_norm": 9.5,
"learning_rate": 8.163265306122448e-06,
"loss": 12.2376,
"step": 29
},
{
"epoch": 0.061224489795918366,
"grad_norm": 16.125,
"learning_rate": 8.454810495626823e-06,
"loss": 12.1463,
"step": 30
},
{
"epoch": 0.06326530612244897,
"grad_norm": 15.75,
"learning_rate": 8.746355685131195e-06,
"loss": 12.0956,
"step": 31
},
{
"epoch": 0.0653061224489796,
"grad_norm": 9.5625,
"learning_rate": 9.03790087463557e-06,
"loss": 12.0433,
"step": 32
},
{
"epoch": 0.0673469387755102,
"grad_norm": 7.5,
"learning_rate": 9.329446064139942e-06,
"loss": 11.9664,
"step": 33
},
{
"epoch": 0.06938775510204082,
"grad_norm": 12.375,
"learning_rate": 9.620991253644314e-06,
"loss": 11.8438,
"step": 34
},
{
"epoch": 0.07142857142857142,
"grad_norm": 19.5,
"learning_rate": 9.912536443148689e-06,
"loss": 11.935,
"step": 35
},
{
"epoch": 0.07346938775510205,
"grad_norm": 7.875,
"learning_rate": 1.0204081632653061e-05,
"loss": 11.8444,
"step": 36
},
{
"epoch": 0.07551020408163266,
"grad_norm": 9.6875,
"learning_rate": 1.0495626822157436e-05,
"loss": 11.7777,
"step": 37
},
{
"epoch": 0.07755102040816327,
"grad_norm": 11.6875,
"learning_rate": 1.0787172011661808e-05,
"loss": 11.8336,
"step": 38
},
{
"epoch": 0.07959183673469387,
"grad_norm": 7.53125,
"learning_rate": 1.1078717201166182e-05,
"loss": 11.6325,
"step": 39
},
{
"epoch": 0.08163265306122448,
"grad_norm": 11.75,
"learning_rate": 1.1370262390670553e-05,
"loss": 11.6474,
"step": 40
},
{
"epoch": 0.0836734693877551,
"grad_norm": 6.125,
"learning_rate": 1.1661807580174927e-05,
"loss": 11.6984,
"step": 41
},
{
"epoch": 0.08571428571428572,
"grad_norm": 6.375,
"learning_rate": 1.19533527696793e-05,
"loss": 11.7204,
"step": 42
},
{
"epoch": 0.08775510204081632,
"grad_norm": 14.625,
"learning_rate": 1.2244897959183674e-05,
"loss": 11.6667,
"step": 43
},
{
"epoch": 0.08979591836734693,
"grad_norm": 5.90625,
"learning_rate": 1.2536443148688048e-05,
"loss": 11.5053,
"step": 44
},
{
"epoch": 0.09183673469387756,
"grad_norm": 11.9375,
"learning_rate": 1.2827988338192421e-05,
"loss": 11.5791,
"step": 45
},
{
"epoch": 0.09387755102040816,
"grad_norm": 7.9375,
"learning_rate": 1.3119533527696792e-05,
"loss": 11.3534,
"step": 46
},
{
"epoch": 0.09591836734693877,
"grad_norm": 10.6875,
"learning_rate": 1.3411078717201168e-05,
"loss": 11.3246,
"step": 47
},
{
"epoch": 0.09795918367346938,
"grad_norm": 9.9375,
"learning_rate": 1.3702623906705539e-05,
"loss": 11.3148,
"step": 48
},
{
"epoch": 0.1,
"grad_norm": 4.125,
"learning_rate": 1.3994169096209913e-05,
"loss": 11.315,
"step": 49
},
{
"epoch": 0.10204081632653061,
"grad_norm": 8.4375,
"learning_rate": 1.4285714285714285e-05,
"loss": 11.2,
"step": 50
},
{
"epoch": 0.10408163265306122,
"grad_norm": 5.46875,
"learning_rate": 1.457725947521866e-05,
"loss": 11.289,
"step": 51
},
{
"epoch": 0.10612244897959183,
"grad_norm": 10.1875,
"learning_rate": 1.4868804664723032e-05,
"loss": 11.1126,
"step": 52
},
{
"epoch": 0.10816326530612246,
"grad_norm": 8.625,
"learning_rate": 1.5160349854227406e-05,
"loss": 11.2346,
"step": 53
},
{
"epoch": 0.11020408163265306,
"grad_norm": 5.71875,
"learning_rate": 1.545189504373178e-05,
"loss": 11.1143,
"step": 54
},
{
"epoch": 0.11224489795918367,
"grad_norm": 6.25,
"learning_rate": 1.5743440233236155e-05,
"loss": 10.9541,
"step": 55
},
{
"epoch": 0.11428571428571428,
"grad_norm": 4.59375,
"learning_rate": 1.6034985422740524e-05,
"loss": 10.9802,
"step": 56
},
{
"epoch": 0.11632653061224489,
"grad_norm": 7.09375,
"learning_rate": 1.6326530612244897e-05,
"loss": 10.9792,
"step": 57
},
{
"epoch": 0.11836734693877551,
"grad_norm": 5.6875,
"learning_rate": 1.6618075801749273e-05,
"loss": 10.8762,
"step": 58
},
{
"epoch": 0.12040816326530612,
"grad_norm": 6.78125,
"learning_rate": 1.6909620991253645e-05,
"loss": 10.6789,
"step": 59
},
{
"epoch": 0.12244897959183673,
"grad_norm": 5.65625,
"learning_rate": 1.7201166180758018e-05,
"loss": 10.6563,
"step": 60
},
{
"epoch": 0.12448979591836734,
"grad_norm": 6.0,
"learning_rate": 1.749271137026239e-05,
"loss": 10.4851,
"step": 61
},
{
"epoch": 0.12653061224489795,
"grad_norm": 7.28125,
"learning_rate": 1.7784256559766766e-05,
"loss": 10.3698,
"step": 62
},
{
"epoch": 0.12857142857142856,
"grad_norm": 6.84375,
"learning_rate": 1.807580174927114e-05,
"loss": 10.2304,
"step": 63
},
{
"epoch": 0.1306122448979592,
"grad_norm": 5.21875,
"learning_rate": 1.836734693877551e-05,
"loss": 10.0903,
"step": 64
},
{
"epoch": 0.1326530612244898,
"grad_norm": 15.4375,
"learning_rate": 1.8658892128279884e-05,
"loss": 10.0921,
"step": 65
},
{
"epoch": 0.1346938775510204,
"grad_norm": 9.375,
"learning_rate": 1.895043731778426e-05,
"loss": 9.909,
"step": 66
},
{
"epoch": 0.13673469387755102,
"grad_norm": 11.4375,
"learning_rate": 1.924198250728863e-05,
"loss": 9.7761,
"step": 67
},
{
"epoch": 0.13877551020408163,
"grad_norm": 7.5,
"learning_rate": 1.9533527696793e-05,
"loss": 9.6638,
"step": 68
},
{
"epoch": 0.14081632653061224,
"grad_norm": 9.0625,
"learning_rate": 1.9825072886297377e-05,
"loss": 9.6164,
"step": 69
},
{
"epoch": 0.14285714285714285,
"grad_norm": 6.3125,
"learning_rate": 2.011661807580175e-05,
"loss": 9.5539,
"step": 70
},
{
"epoch": 0.14489795918367346,
"grad_norm": 5.0,
"learning_rate": 2.0408163265306123e-05,
"loss": 9.529,
"step": 71
},
{
"epoch": 0.1469387755102041,
"grad_norm": 5.5625,
"learning_rate": 2.0699708454810495e-05,
"loss": 9.3138,
"step": 72
},
{
"epoch": 0.1489795918367347,
"grad_norm": 4.75,
"learning_rate": 2.099125364431487e-05,
"loss": 9.2833,
"step": 73
},
{
"epoch": 0.1510204081632653,
"grad_norm": 4.09375,
"learning_rate": 2.1282798833819244e-05,
"loss": 9.195,
"step": 74
},
{
"epoch": 0.15306122448979592,
"grad_norm": 3.1875,
"learning_rate": 2.1574344023323616e-05,
"loss": 9.1055,
"step": 75
},
{
"epoch": 0.15510204081632653,
"grad_norm": 3.5,
"learning_rate": 2.186588921282799e-05,
"loss": 9.0636,
"step": 76
},
{
"epoch": 0.15714285714285714,
"grad_norm": 3.21875,
"learning_rate": 2.2157434402332365e-05,
"loss": 8.9555,
"step": 77
},
{
"epoch": 0.15918367346938775,
"grad_norm": 2.765625,
"learning_rate": 2.2448979591836737e-05,
"loss": 8.9046,
"step": 78
},
{
"epoch": 0.16122448979591836,
"grad_norm": 2.359375,
"learning_rate": 2.2740524781341106e-05,
"loss": 8.8944,
"step": 79
},
{
"epoch": 0.16326530612244897,
"grad_norm": 2.9375,
"learning_rate": 2.3032069970845482e-05,
"loss": 8.6582,
"step": 80
},
{
"epoch": 0.1653061224489796,
"grad_norm": 3.0625,
"learning_rate": 2.3323615160349855e-05,
"loss": 8.7293,
"step": 81
},
{
"epoch": 0.1673469387755102,
"grad_norm": 3.53125,
"learning_rate": 2.3615160349854227e-05,
"loss": 8.5917,
"step": 82
},
{
"epoch": 0.16938775510204082,
"grad_norm": 2.75,
"learning_rate": 2.39067055393586e-05,
"loss": 8.6483,
"step": 83
},
{
"epoch": 0.17142857142857143,
"grad_norm": 2.546875,
"learning_rate": 2.4198250728862976e-05,
"loss": 8.5543,
"step": 84
},
{
"epoch": 0.17346938775510204,
"grad_norm": 2.859375,
"learning_rate": 2.448979591836735e-05,
"loss": 8.4662,
"step": 85
},
{
"epoch": 0.17551020408163265,
"grad_norm": 2.03125,
"learning_rate": 2.478134110787172e-05,
"loss": 8.6056,
"step": 86
},
{
"epoch": 0.17755102040816326,
"grad_norm": 2.03125,
"learning_rate": 2.5072886297376097e-05,
"loss": 8.5313,
"step": 87
},
{
"epoch": 0.17959183673469387,
"grad_norm": 2.375,
"learning_rate": 2.536443148688047e-05,
"loss": 8.551,
"step": 88
},
{
"epoch": 0.1816326530612245,
"grad_norm": 2.890625,
"learning_rate": 2.5655976676384842e-05,
"loss": 8.5305,
"step": 89
},
{
"epoch": 0.1836734693877551,
"grad_norm": 2.015625,
"learning_rate": 2.594752186588921e-05,
"loss": 8.5339,
"step": 90
},
{
"epoch": 0.18571428571428572,
"grad_norm": 2.03125,
"learning_rate": 2.6239067055393584e-05,
"loss": 8.5971,
"step": 91
},
{
"epoch": 0.18775510204081633,
"grad_norm": 2.140625,
"learning_rate": 2.6530612244897963e-05,
"loss": 8.4027,
"step": 92
},
{
"epoch": 0.18979591836734694,
"grad_norm": 3.15625,
"learning_rate": 2.6822157434402336e-05,
"loss": 8.5793,
"step": 93
},
{
"epoch": 0.19183673469387755,
"grad_norm": 2.65625,
"learning_rate": 2.7113702623906705e-05,
"loss": 8.4546,
"step": 94
},
{
"epoch": 0.19387755102040816,
"grad_norm": 1.6640625,
"learning_rate": 2.7405247813411077e-05,
"loss": 8.559,
"step": 95
},
{
"epoch": 0.19591836734693877,
"grad_norm": 4.59375,
"learning_rate": 2.7696793002915457e-05,
"loss": 8.5194,
"step": 96
},
{
"epoch": 0.19795918367346937,
"grad_norm": 1.796875,
"learning_rate": 2.7988338192419826e-05,
"loss": 8.4945,
"step": 97
},
{
"epoch": 0.2,
"grad_norm": 5.84375,
"learning_rate": 2.82798833819242e-05,
"loss": 8.5868,
"step": 98
},
{
"epoch": 0.20204081632653062,
"grad_norm": 2.5,
"learning_rate": 2.857142857142857e-05,
"loss": 8.5977,
"step": 99
},
{
"epoch": 0.20408163265306123,
"grad_norm": 1.6484375,
"learning_rate": 2.886297376093295e-05,
"loss": 8.4463,
"step": 100
},
{
"epoch": 0.20612244897959184,
"grad_norm": 3.203125,
"learning_rate": 2.915451895043732e-05,
"loss": 8.296,
"step": 101
},
{
"epoch": 0.20816326530612245,
"grad_norm": 2.078125,
"learning_rate": 2.9446064139941692e-05,
"loss": 8.5476,
"step": 102
},
{
"epoch": 0.21020408163265306,
"grad_norm": 2.15625,
"learning_rate": 2.9737609329446064e-05,
"loss": 8.3634,
"step": 103
},
{
"epoch": 0.21224489795918366,
"grad_norm": 2.5625,
"learning_rate": 3.0029154518950437e-05,
"loss": 8.4391,
"step": 104
},
{
"epoch": 0.21428571428571427,
"grad_norm": 3.03125,
"learning_rate": 3.0320699708454813e-05,
"loss": 8.5003,
"step": 105
},
{
"epoch": 0.2163265306122449,
"grad_norm": 2.140625,
"learning_rate": 3.061224489795919e-05,
"loss": 8.5502,
"step": 106
},
{
"epoch": 0.21836734693877552,
"grad_norm": 1.8359375,
"learning_rate": 3.090379008746356e-05,
"loss": 8.4291,
"step": 107
},
{
"epoch": 0.22040816326530613,
"grad_norm": 2.4375,
"learning_rate": 3.119533527696793e-05,
"loss": 8.3857,
"step": 108
},
{
"epoch": 0.22244897959183674,
"grad_norm": 2.078125,
"learning_rate": 3.148688046647231e-05,
"loss": 8.3713,
"step": 109
},
{
"epoch": 0.22448979591836735,
"grad_norm": 2.8125,
"learning_rate": 3.177842565597668e-05,
"loss": 8.4372,
"step": 110
},
{
"epoch": 0.22653061224489796,
"grad_norm": 2.015625,
"learning_rate": 3.206997084548105e-05,
"loss": 8.4845,
"step": 111
},
{
"epoch": 0.22857142857142856,
"grad_norm": 2.015625,
"learning_rate": 3.2361516034985424e-05,
"loss": 8.497,
"step": 112
},
{
"epoch": 0.23061224489795917,
"grad_norm": 1.953125,
"learning_rate": 3.265306122448979e-05,
"loss": 8.4082,
"step": 113
},
{
"epoch": 0.23265306122448978,
"grad_norm": 2.203125,
"learning_rate": 3.294460641399417e-05,
"loss": 8.345,
"step": 114
},
{
"epoch": 0.23469387755102042,
"grad_norm": 2.671875,
"learning_rate": 3.3236151603498545e-05,
"loss": 8.2966,
"step": 115
},
{
"epoch": 0.23673469387755103,
"grad_norm": 3.546875,
"learning_rate": 3.3527696793002914e-05,
"loss": 8.2451,
"step": 116
},
{
"epoch": 0.23877551020408164,
"grad_norm": 3.4375,
"learning_rate": 3.381924198250729e-05,
"loss": 8.4205,
"step": 117
},
{
"epoch": 0.24081632653061225,
"grad_norm": 2.25,
"learning_rate": 3.4110787172011666e-05,
"loss": 8.5652,
"step": 118
},
{
"epoch": 0.24285714285714285,
"grad_norm": 3.953125,
"learning_rate": 3.4402332361516035e-05,
"loss": 8.3901,
"step": 119
},
{
"epoch": 0.24489795918367346,
"grad_norm": 2.59375,
"learning_rate": 3.469387755102041e-05,
"loss": 8.4824,
"step": 120
},
{
"epoch": 0.24693877551020407,
"grad_norm": 2.359375,
"learning_rate": 3.498542274052478e-05,
"loss": 8.3196,
"step": 121
},
{
"epoch": 0.24897959183673468,
"grad_norm": 5.5,
"learning_rate": 3.5276967930029156e-05,
"loss": 8.4221,
"step": 122
},
{
"epoch": 0.2510204081632653,
"grad_norm": 4.625,
"learning_rate": 3.556851311953353e-05,
"loss": 8.3701,
"step": 123
},
{
"epoch": 0.2530612244897959,
"grad_norm": 2.15625,
"learning_rate": 3.58600583090379e-05,
"loss": 8.5719,
"step": 124
},
{
"epoch": 0.25510204081632654,
"grad_norm": 4.375,
"learning_rate": 3.615160349854228e-05,
"loss": 8.4045,
"step": 125
},
{
"epoch": 0.2571428571428571,
"grad_norm": 9.125,
"learning_rate": 3.644314868804665e-05,
"loss": 8.3438,
"step": 126
},
{
"epoch": 0.25918367346938775,
"grad_norm": 3.015625,
"learning_rate": 3.673469387755102e-05,
"loss": 8.4539,
"step": 127
},
{
"epoch": 0.2612244897959184,
"grad_norm": 15.875,
"learning_rate": 3.70262390670554e-05,
"loss": 8.4131,
"step": 128
},
{
"epoch": 0.26326530612244897,
"grad_norm": 13.625,
"learning_rate": 3.731778425655977e-05,
"loss": 8.4202,
"step": 129
},
{
"epoch": 0.2653061224489796,
"grad_norm": 2.453125,
"learning_rate": 3.760932944606414e-05,
"loss": 8.3407,
"step": 130
},
{
"epoch": 0.2673469387755102,
"grad_norm": 4.1875,
"learning_rate": 3.790087463556852e-05,
"loss": 8.3932,
"step": 131
},
{
"epoch": 0.2693877551020408,
"grad_norm": 4.46875,
"learning_rate": 3.819241982507289e-05,
"loss": 8.2858,
"step": 132
},
{
"epoch": 0.2714285714285714,
"grad_norm": 2.03125,
"learning_rate": 3.848396501457726e-05,
"loss": 8.1549,
"step": 133
},
{
"epoch": 0.27346938775510204,
"grad_norm": 10.9375,
"learning_rate": 3.8775510204081634e-05,
"loss": 8.3157,
"step": 134
},
{
"epoch": 0.2755102040816326,
"grad_norm": 6.15625,
"learning_rate": 3.9067055393586e-05,
"loss": 8.2587,
"step": 135
},
{
"epoch": 0.27755102040816326,
"grad_norm": 9.5,
"learning_rate": 3.9358600583090386e-05,
"loss": 8.1931,
"step": 136
},
{
"epoch": 0.2795918367346939,
"grad_norm": 8.875,
"learning_rate": 3.9650145772594755e-05,
"loss": 8.2118,
"step": 137
},
{
"epoch": 0.2816326530612245,
"grad_norm": 2.078125,
"learning_rate": 3.9941690962099124e-05,
"loss": 8.2175,
"step": 138
},
{
"epoch": 0.2836734693877551,
"grad_norm": 3.234375,
"learning_rate": 4.02332361516035e-05,
"loss": 8.4113,
"step": 139
},
{
"epoch": 0.2857142857142857,
"grad_norm": 5.4375,
"learning_rate": 4.0524781341107876e-05,
"loss": 8.1832,
"step": 140
},
{
"epoch": 0.28775510204081634,
"grad_norm": 3.046875,
"learning_rate": 4.0816326530612245e-05,
"loss": 8.1237,
"step": 141
},
{
"epoch": 0.2897959183673469,
"grad_norm": 5.28125,
"learning_rate": 4.110787172011662e-05,
"loss": 8.1893,
"step": 142
},
{
"epoch": 0.29183673469387755,
"grad_norm": 3.203125,
"learning_rate": 4.139941690962099e-05,
"loss": 8.2877,
"step": 143
},
{
"epoch": 0.2938775510204082,
"grad_norm": 8.1875,
"learning_rate": 4.1690962099125366e-05,
"loss": 8.2507,
"step": 144
},
{
"epoch": 0.29591836734693877,
"grad_norm": 7.28125,
"learning_rate": 4.198250728862974e-05,
"loss": 8.3109,
"step": 145
},
{
"epoch": 0.2979591836734694,
"grad_norm": 4.375,
"learning_rate": 4.227405247813411e-05,
"loss": 8.2102,
"step": 146
},
{
"epoch": 0.3,
"grad_norm": 4.3125,
"learning_rate": 4.256559766763849e-05,
"loss": 8.2071,
"step": 147
},
{
"epoch": 0.3020408163265306,
"grad_norm": 2.671875,
"learning_rate": 4.2857142857142856e-05,
"loss": 8.0322,
"step": 148
},
{
"epoch": 0.3040816326530612,
"grad_norm": 1.59375,
"learning_rate": 4.314868804664723e-05,
"loss": 8.0883,
"step": 149
},
{
"epoch": 0.30612244897959184,
"grad_norm": 4.25,
"learning_rate": 4.344023323615161e-05,
"loss": 8.0931,
"step": 150
},
{
"epoch": 0.3081632653061224,
"grad_norm": 1.84375,
"learning_rate": 4.373177842565598e-05,
"loss": 8.0258,
"step": 151
},
{
"epoch": 0.31020408163265306,
"grad_norm": 8.1875,
"learning_rate": 4.402332361516035e-05,
"loss": 8.134,
"step": 152
},
{
"epoch": 0.3122448979591837,
"grad_norm": 7.875,
"learning_rate": 4.431486880466473e-05,
"loss": 8.1399,
"step": 153
},
{
"epoch": 0.3142857142857143,
"grad_norm": 3.78125,
"learning_rate": 4.46064139941691e-05,
"loss": 8.2004,
"step": 154
},
{
"epoch": 0.3163265306122449,
"grad_norm": 4.0625,
"learning_rate": 4.4897959183673474e-05,
"loss": 7.9594,
"step": 155
},
{
"epoch": 0.3183673469387755,
"grad_norm": 2.453125,
"learning_rate": 4.5189504373177843e-05,
"loss": 8.1404,
"step": 156
},
{
"epoch": 0.32040816326530613,
"grad_norm": 1.640625,
"learning_rate": 4.548104956268221e-05,
"loss": 8.1451,
"step": 157
},
{
"epoch": 0.3224489795918367,
"grad_norm": 3.890625,
"learning_rate": 4.5772594752186595e-05,
"loss": 8.0985,
"step": 158
},
{
"epoch": 0.32448979591836735,
"grad_norm": 2.796875,
"learning_rate": 4.6064139941690965e-05,
"loss": 8.114,
"step": 159
},
{
"epoch": 0.32653061224489793,
"grad_norm": 1.640625,
"learning_rate": 4.6355685131195334e-05,
"loss": 8.1096,
"step": 160
},
{
"epoch": 0.32857142857142857,
"grad_norm": 2.109375,
"learning_rate": 4.664723032069971e-05,
"loss": 7.9051,
"step": 161
},
{
"epoch": 0.3306122448979592,
"grad_norm": 4.8125,
"learning_rate": 4.6938775510204086e-05,
"loss": 8.0538,
"step": 162
},
{
"epoch": 0.3326530612244898,
"grad_norm": 1.65625,
"learning_rate": 4.7230320699708455e-05,
"loss": 8.2233,
"step": 163
},
{
"epoch": 0.3346938775510204,
"grad_norm": 1.9140625,
"learning_rate": 4.752186588921283e-05,
"loss": 8.1843,
"step": 164
},
{
"epoch": 0.336734693877551,
"grad_norm": 2.09375,
"learning_rate": 4.78134110787172e-05,
"loss": 7.9962,
"step": 165
},
{
"epoch": 0.33877551020408164,
"grad_norm": 4.59375,
"learning_rate": 4.810495626822158e-05,
"loss": 8.0115,
"step": 166
},
{
"epoch": 0.3408163265306122,
"grad_norm": 6.84375,
"learning_rate": 4.839650145772595e-05,
"loss": 7.9945,
"step": 167
},
{
"epoch": 0.34285714285714286,
"grad_norm": 3.0,
"learning_rate": 4.868804664723032e-05,
"loss": 8.0635,
"step": 168
},
{
"epoch": 0.3448979591836735,
"grad_norm": 3.84375,
"learning_rate": 4.89795918367347e-05,
"loss": 7.9456,
"step": 169
},
{
"epoch": 0.3469387755102041,
"grad_norm": 17.625,
"learning_rate": 4.9271137026239066e-05,
"loss": 7.969,
"step": 170
},
{
"epoch": 0.3489795918367347,
"grad_norm": 13.4375,
"learning_rate": 4.956268221574344e-05,
"loss": 8.2427,
"step": 171
},
{
"epoch": 0.3510204081632653,
"grad_norm": 10.9375,
"learning_rate": 4.985422740524782e-05,
"loss": 8.0573,
"step": 172
},
{
"epoch": 0.35306122448979593,
"grad_norm": 8.0,
"learning_rate": 5.0145772594752194e-05,
"loss": 7.9694,
"step": 173
},
{
"epoch": 0.3551020408163265,
"grad_norm": 12.5625,
"learning_rate": 5.043731778425656e-05,
"loss": 8.3278,
"step": 174
},
{
"epoch": 0.35714285714285715,
"grad_norm": 9.4375,
"learning_rate": 5.072886297376094e-05,
"loss": 7.9835,
"step": 175
},
{
"epoch": 0.35918367346938773,
"grad_norm": 6.5,
"learning_rate": 5.102040816326531e-05,
"loss": 7.9495,
"step": 176
},
{
"epoch": 0.36122448979591837,
"grad_norm": 6.5,
"learning_rate": 5.1311953352769684e-05,
"loss": 7.9896,
"step": 177
},
{
"epoch": 0.363265306122449,
"grad_norm": 6.1875,
"learning_rate": 5.160349854227405e-05,
"loss": 7.9586,
"step": 178
},
{
"epoch": 0.3653061224489796,
"grad_norm": 4.375,
"learning_rate": 5.189504373177842e-05,
"loss": 7.8384,
"step": 179
},
{
"epoch": 0.3673469387755102,
"grad_norm": 4.8125,
"learning_rate": 5.21865889212828e-05,
"loss": 7.9217,
"step": 180
},
{
"epoch": 0.3693877551020408,
"grad_norm": 3.203125,
"learning_rate": 5.247813411078717e-05,
"loss": 7.9755,
"step": 181
},
{
"epoch": 0.37142857142857144,
"grad_norm": 3.453125,
"learning_rate": 5.276967930029155e-05,
"loss": 7.8748,
"step": 182
},
{
"epoch": 0.373469387755102,
"grad_norm": 4.625,
"learning_rate": 5.3061224489795926e-05,
"loss": 7.8079,
"step": 183
},
{
"epoch": 0.37551020408163266,
"grad_norm": 2.78125,
"learning_rate": 5.3352769679300295e-05,
"loss": 7.8928,
"step": 184
},
{
"epoch": 0.37755102040816324,
"grad_norm": 8.5625,
"learning_rate": 5.364431486880467e-05,
"loss": 7.6182,
"step": 185
},
{
"epoch": 0.3795918367346939,
"grad_norm": 7.53125,
"learning_rate": 5.393586005830904e-05,
"loss": 7.5909,
"step": 186
},
{
"epoch": 0.3816326530612245,
"grad_norm": 4.5,
"learning_rate": 5.422740524781341e-05,
"loss": 7.7326,
"step": 187
},
{
"epoch": 0.3836734693877551,
"grad_norm": 4.71875,
"learning_rate": 5.4518950437317785e-05,
"loss": 7.6624,
"step": 188
},
{
"epoch": 0.38571428571428573,
"grad_norm": 2.578125,
"learning_rate": 5.4810495626822155e-05,
"loss": 7.7293,
"step": 189
},
{
"epoch": 0.3877551020408163,
"grad_norm": 5.5,
"learning_rate": 5.510204081632653e-05,
"loss": 7.5851,
"step": 190
},
{
"epoch": 0.38979591836734695,
"grad_norm": 5.1875,
"learning_rate": 5.539358600583091e-05,
"loss": 7.7903,
"step": 191
},
{
"epoch": 0.39183673469387753,
"grad_norm": 7.46875,
"learning_rate": 5.568513119533528e-05,
"loss": 7.5057,
"step": 192
},
{
"epoch": 0.39387755102040817,
"grad_norm": 3.171875,
"learning_rate": 5.597667638483965e-05,
"loss": 7.6355,
"step": 193
},
{
"epoch": 0.39591836734693875,
"grad_norm": 8.75,
"learning_rate": 5.626822157434403e-05,
"loss": 7.5757,
"step": 194
},
{
"epoch": 0.3979591836734694,
"grad_norm": 4.0625,
"learning_rate": 5.65597667638484e-05,
"loss": 7.5217,
"step": 195
},
{
"epoch": 0.4,
"grad_norm": 10.875,
"learning_rate": 5.685131195335277e-05,
"loss": 7.4943,
"step": 196
},
{
"epoch": 0.4020408163265306,
"grad_norm": 7.3125,
"learning_rate": 5.714285714285714e-05,
"loss": 7.6952,
"step": 197
},
{
"epoch": 0.40408163265306124,
"grad_norm": 11.4375,
"learning_rate": 5.743440233236152e-05,
"loss": 7.3887,
"step": 198
},
{
"epoch": 0.4061224489795918,
"grad_norm": 11.6875,
"learning_rate": 5.77259475218659e-05,
"loss": 7.5169,
"step": 199
},
{
"epoch": 0.40816326530612246,
"grad_norm": 4.4375,
"learning_rate": 5.801749271137027e-05,
"loss": 7.321,
"step": 200
},
{
"epoch": 0.41020408163265304,
"grad_norm": 11.875,
"learning_rate": 5.830903790087464e-05,
"loss": 7.4407,
"step": 201
},
{
"epoch": 0.4122448979591837,
"grad_norm": 10.1875,
"learning_rate": 5.8600583090379015e-05,
"loss": 7.3076,
"step": 202
},
{
"epoch": 0.4142857142857143,
"grad_norm": 2.6875,
"learning_rate": 5.8892128279883384e-05,
"loss": 7.2927,
"step": 203
},
{
"epoch": 0.4163265306122449,
"grad_norm": 13.5625,
"learning_rate": 5.918367346938776e-05,
"loss": 7.3617,
"step": 204
},
{
"epoch": 0.41836734693877553,
"grad_norm": 6.96875,
"learning_rate": 5.947521865889213e-05,
"loss": 7.3366,
"step": 205
},
{
"epoch": 0.4204081632653061,
"grad_norm": 7.09375,
"learning_rate": 5.97667638483965e-05,
"loss": 7.1847,
"step": 206
},
{
"epoch": 0.42244897959183675,
"grad_norm": 4.3125,
"learning_rate": 6.0058309037900874e-05,
"loss": 7.1928,
"step": 207
},
{
"epoch": 0.42448979591836733,
"grad_norm": 3.03125,
"learning_rate": 6.034985422740526e-05,
"loss": 7.087,
"step": 208
},
{
"epoch": 0.42653061224489797,
"grad_norm": 4.0,
"learning_rate": 6.0641399416909626e-05,
"loss": 7.0556,
"step": 209
},
{
"epoch": 0.42857142857142855,
"grad_norm": 3.234375,
"learning_rate": 6.0932944606414e-05,
"loss": 7.1476,
"step": 210
},
{
"epoch": 0.4306122448979592,
"grad_norm": 6.6875,
"learning_rate": 6.122448979591838e-05,
"loss": 7.1851,
"step": 211
},
{
"epoch": 0.4326530612244898,
"grad_norm": 2.390625,
"learning_rate": 6.151603498542275e-05,
"loss": 6.8979,
"step": 212
},
{
"epoch": 0.4346938775510204,
"grad_norm": 8.375,
"learning_rate": 6.180758017492712e-05,
"loss": 6.9724,
"step": 213
},
{
"epoch": 0.43673469387755104,
"grad_norm": 5.65625,
"learning_rate": 6.209912536443149e-05,
"loss": 6.9267,
"step": 214
},
{
"epoch": 0.4387755102040816,
"grad_norm": 9.25,
"learning_rate": 6.239067055393585e-05,
"loss": 7.1214,
"step": 215
},
{
"epoch": 0.44081632653061226,
"grad_norm": 6.53125,
"learning_rate": 6.268221574344024e-05,
"loss": 6.8548,
"step": 216
},
{
"epoch": 0.44285714285714284,
"grad_norm": 4.15625,
"learning_rate": 6.297376093294462e-05,
"loss": 6.7708,
"step": 217
},
{
"epoch": 0.4448979591836735,
"grad_norm": 4.6875,
"learning_rate": 6.326530612244899e-05,
"loss": 6.7851,
"step": 218
},
{
"epoch": 0.44693877551020406,
"grad_norm": 5.15625,
"learning_rate": 6.355685131195336e-05,
"loss": 6.8873,
"step": 219
},
{
"epoch": 0.4489795918367347,
"grad_norm": 3.953125,
"learning_rate": 6.384839650145773e-05,
"loss": 6.6817,
"step": 220
},
{
"epoch": 0.45102040816326533,
"grad_norm": 3.328125,
"learning_rate": 6.41399416909621e-05,
"loss": 6.6812,
"step": 221
},
{
"epoch": 0.4530612244897959,
"grad_norm": 2.40625,
"learning_rate": 6.443148688046648e-05,
"loss": 6.693,
"step": 222
},
{
"epoch": 0.45510204081632655,
"grad_norm": 2.078125,
"learning_rate": 6.472303206997085e-05,
"loss": 6.6584,
"step": 223
},
{
"epoch": 0.45714285714285713,
"grad_norm": 3.78125,
"learning_rate": 6.501457725947522e-05,
"loss": 6.6324,
"step": 224
},
{
"epoch": 0.45918367346938777,
"grad_norm": 1.9609375,
"learning_rate": 6.530612244897959e-05,
"loss": 6.4791,
"step": 225
},
{
"epoch": 0.46122448979591835,
"grad_norm": 1.6953125,
"learning_rate": 6.559766763848397e-05,
"loss": 6.45,
"step": 226
},
{
"epoch": 0.463265306122449,
"grad_norm": 4.53125,
"learning_rate": 6.588921282798834e-05,
"loss": 6.5522,
"step": 227
},
{
"epoch": 0.46530612244897956,
"grad_norm": 2.578125,
"learning_rate": 6.618075801749272e-05,
"loss": 6.4091,
"step": 228
},
{
"epoch": 0.4673469387755102,
"grad_norm": 5.15625,
"learning_rate": 6.647230320699709e-05,
"loss": 6.4452,
"step": 229
},
{
"epoch": 0.46938775510204084,
"grad_norm": 2.15625,
"learning_rate": 6.676384839650146e-05,
"loss": 6.4287,
"step": 230
},
{
"epoch": 0.4714285714285714,
"grad_norm": 4.40625,
"learning_rate": 6.705539358600583e-05,
"loss": 6.4798,
"step": 231
},
{
"epoch": 0.47346938775510206,
"grad_norm": 1.703125,
"learning_rate": 6.73469387755102e-05,
"loss": 6.6685,
"step": 232
},
{
"epoch": 0.47551020408163264,
"grad_norm": 1.96875,
"learning_rate": 6.763848396501458e-05,
"loss": 6.3878,
"step": 233
},
{
"epoch": 0.4775510204081633,
"grad_norm": 3.28125,
"learning_rate": 6.793002915451895e-05,
"loss": 6.2616,
"step": 234
},
{
"epoch": 0.47959183673469385,
"grad_norm": 2.546875,
"learning_rate": 6.822157434402333e-05,
"loss": 6.365,
"step": 235
},
{
"epoch": 0.4816326530612245,
"grad_norm": 1.6171875,
"learning_rate": 6.85131195335277e-05,
"loss": 6.3051,
"step": 236
},
{
"epoch": 0.48367346938775513,
"grad_norm": 4.5,
"learning_rate": 6.880466472303207e-05,
"loss": 6.5448,
"step": 237
},
{
"epoch": 0.4857142857142857,
"grad_norm": 4.90625,
"learning_rate": 6.909620991253645e-05,
"loss": 6.404,
"step": 238
},
{
"epoch": 0.48775510204081635,
"grad_norm": 2.5625,
"learning_rate": 6.938775510204082e-05,
"loss": 6.3212,
"step": 239
},
{
"epoch": 0.4897959183673469,
"grad_norm": 10.625,
"learning_rate": 6.967930029154519e-05,
"loss": 6.4011,
"step": 240
},
{
"epoch": 0.49183673469387756,
"grad_norm": 8.6875,
"learning_rate": 6.997084548104956e-05,
"loss": 6.2483,
"step": 241
},
{
"epoch": 0.49387755102040815,
"grad_norm": 4.65625,
"learning_rate": 7.026239067055393e-05,
"loss": 6.283,
"step": 242
},
{
"epoch": 0.4959183673469388,
"grad_norm": 5.34375,
"learning_rate": 7.055393586005831e-05,
"loss": 6.3428,
"step": 243
},
{
"epoch": 0.49795918367346936,
"grad_norm": 3.90625,
"learning_rate": 7.08454810495627e-05,
"loss": 6.2511,
"step": 244
},
{
"epoch": 0.5,
"grad_norm": 2.890625,
"learning_rate": 7.113702623906706e-05,
"loss": 6.1408,
"step": 245
},
{
"epoch": 0.5020408163265306,
"grad_norm": 5.375,
"learning_rate": 7.142857142857143e-05,
"loss": 6.3555,
"step": 246
},
{
"epoch": 0.5040816326530613,
"grad_norm": 5.09375,
"learning_rate": 7.17201166180758e-05,
"loss": 6.1988,
"step": 247
},
{
"epoch": 0.5061224489795918,
"grad_norm": 2.734375,
"learning_rate": 7.201166180758017e-05,
"loss": 6.0844,
"step": 248
},
{
"epoch": 0.5081632653061224,
"grad_norm": 3.796875,
"learning_rate": 7.230320699708455e-05,
"loss": 6.2489,
"step": 249
},
{
"epoch": 0.5102040816326531,
"grad_norm": 4.75,
"learning_rate": 7.259475218658892e-05,
"loss": 6.0877,
"step": 250
},
{
"epoch": 0.5122448979591837,
"grad_norm": 2.828125,
"learning_rate": 7.28862973760933e-05,
"loss": 6.1329,
"step": 251
},
{
"epoch": 0.5142857142857142,
"grad_norm": 6.3125,
"learning_rate": 7.317784256559768e-05,
"loss": 6.2386,
"step": 252
},
{
"epoch": 0.5163265306122449,
"grad_norm": 4.375,
"learning_rate": 7.346938775510205e-05,
"loss": 6.1082,
"step": 253
},
{
"epoch": 0.5183673469387755,
"grad_norm": 5.40625,
"learning_rate": 7.376093294460641e-05,
"loss": 6.1372,
"step": 254
},
{
"epoch": 0.5204081632653061,
"grad_norm": 3.96875,
"learning_rate": 7.40524781341108e-05,
"loss": 6.1034,
"step": 255
},
{
"epoch": 0.5224489795918368,
"grad_norm": 5.90625,
"learning_rate": 7.434402332361517e-05,
"loss": 6.2069,
"step": 256
},
{
"epoch": 0.5244897959183673,
"grad_norm": 4.1875,
"learning_rate": 7.463556851311954e-05,
"loss": 6.1267,
"step": 257
},
{
"epoch": 0.5265306122448979,
"grad_norm": 3.984375,
"learning_rate": 7.49271137026239e-05,
"loss": 6.2217,
"step": 258
},
{
"epoch": 0.5285714285714286,
"grad_norm": 3.71875,
"learning_rate": 7.521865889212827e-05,
"loss": 6.1076,
"step": 259
},
{
"epoch": 0.5306122448979592,
"grad_norm": 3.953125,
"learning_rate": 7.551020408163266e-05,
"loss": 6.1139,
"step": 260
},
{
"epoch": 0.5326530612244897,
"grad_norm": 2.875,
"learning_rate": 7.580174927113704e-05,
"loss": 6.0507,
"step": 261
},
{
"epoch": 0.5346938775510204,
"grad_norm": 5.125,
"learning_rate": 7.609329446064141e-05,
"loss": 6.0944,
"step": 262
},
{
"epoch": 0.536734693877551,
"grad_norm": 4.09375,
"learning_rate": 7.638483965014578e-05,
"loss": 6.0211,
"step": 263
},
{
"epoch": 0.5387755102040817,
"grad_norm": 4.59375,
"learning_rate": 7.667638483965015e-05,
"loss": 6.1391,
"step": 264
},
{
"epoch": 0.5408163265306123,
"grad_norm": 4.84375,
"learning_rate": 7.696793002915452e-05,
"loss": 6.2732,
"step": 265
},
{
"epoch": 0.5428571428571428,
"grad_norm": 3.390625,
"learning_rate": 7.72594752186589e-05,
"loss": 6.1078,
"step": 266
},
{
"epoch": 0.5448979591836735,
"grad_norm": 2.640625,
"learning_rate": 7.755102040816327e-05,
"loss": 6.0451,
"step": 267
},
{
"epoch": 0.5469387755102041,
"grad_norm": 2.203125,
"learning_rate": 7.784256559766764e-05,
"loss": 6.2347,
"step": 268
},
{
"epoch": 0.5489795918367347,
"grad_norm": 1.625,
"learning_rate": 7.8134110787172e-05,
"loss": 5.9228,
"step": 269
},
{
"epoch": 0.5510204081632653,
"grad_norm": 2.8125,
"learning_rate": 7.842565597667639e-05,
"loss": 5.9698,
"step": 270
},
{
"epoch": 0.5530612244897959,
"grad_norm": 3.015625,
"learning_rate": 7.871720116618077e-05,
"loss": 6.1453,
"step": 271
},
{
"epoch": 0.5551020408163265,
"grad_norm": 2.390625,
"learning_rate": 7.900874635568514e-05,
"loss": 6.0078,
"step": 272
},
{
"epoch": 0.5571428571428572,
"grad_norm": 6.25,
"learning_rate": 7.930029154518951e-05,
"loss": 6.1259,
"step": 273
},
{
"epoch": 0.5591836734693878,
"grad_norm": 3.8125,
"learning_rate": 7.959183673469388e-05,
"loss": 6.1101,
"step": 274
},
{
"epoch": 0.5612244897959183,
"grad_norm": 4.5625,
"learning_rate": 7.988338192419825e-05,
"loss": 6.1051,
"step": 275
},
{
"epoch": 0.563265306122449,
"grad_norm": 3.515625,
"learning_rate": 8.017492711370263e-05,
"loss": 5.9927,
"step": 276
},
{
"epoch": 0.5653061224489796,
"grad_norm": 5.9375,
"learning_rate": 8.0466472303207e-05,
"loss": 5.9803,
"step": 277
},
{
"epoch": 0.5673469387755102,
"grad_norm": 5.59375,
"learning_rate": 8.075801749271137e-05,
"loss": 6.0926,
"step": 278
},
{
"epoch": 0.5693877551020409,
"grad_norm": 3.53125,
"learning_rate": 8.104956268221575e-05,
"loss": 5.9645,
"step": 279
},
{
"epoch": 0.5714285714285714,
"grad_norm": 4.3125,
"learning_rate": 8.134110787172012e-05,
"loss": 6.1563,
"step": 280
},
{
"epoch": 0.573469387755102,
"grad_norm": 1.6171875,
"learning_rate": 8.163265306122449e-05,
"loss": 6.0345,
"step": 281
},
{
"epoch": 0.5755102040816327,
"grad_norm": 2.203125,
"learning_rate": 8.192419825072887e-05,
"loss": 5.9936,
"step": 282
},
{
"epoch": 0.5775510204081633,
"grad_norm": 4.53125,
"learning_rate": 8.221574344023324e-05,
"loss": 5.8938,
"step": 283
},
{
"epoch": 0.5795918367346938,
"grad_norm": 2.734375,
"learning_rate": 8.250728862973761e-05,
"loss": 5.9197,
"step": 284
},
{
"epoch": 0.5816326530612245,
"grad_norm": 8.125,
"learning_rate": 8.279883381924198e-05,
"loss": 6.1707,
"step": 285
},
{
"epoch": 0.5836734693877551,
"grad_norm": 8.5625,
"learning_rate": 8.309037900874635e-05,
"loss": 6.032,
"step": 286
},
{
"epoch": 0.5857142857142857,
"grad_norm": 2.1875,
"learning_rate": 8.338192419825073e-05,
"loss": 6.0437,
"step": 287
},
{
"epoch": 0.5877551020408164,
"grad_norm": 8.125,
"learning_rate": 8.367346938775511e-05,
"loss": 6.057,
"step": 288
},
{
"epoch": 0.5897959183673469,
"grad_norm": 9.5625,
"learning_rate": 8.396501457725948e-05,
"loss": 6.2017,
"step": 289
},
{
"epoch": 0.5918367346938775,
"grad_norm": 3.765625,
"learning_rate": 8.425655976676385e-05,
"loss": 6.0977,
"step": 290
},
{
"epoch": 0.5938775510204082,
"grad_norm": 7.40625,
"learning_rate": 8.454810495626822e-05,
"loss": 6.1095,
"step": 291
},
{
"epoch": 0.5959183673469388,
"grad_norm": 6.15625,
"learning_rate": 8.483965014577259e-05,
"loss": 6.1066,
"step": 292
},
{
"epoch": 0.5979591836734693,
"grad_norm": 2.796875,
"learning_rate": 8.513119533527697e-05,
"loss": 6.0938,
"step": 293
},
{
"epoch": 0.6,
"grad_norm": 3.96875,
"learning_rate": 8.542274052478134e-05,
"loss": 6.0187,
"step": 294
},
{
"epoch": 0.6020408163265306,
"grad_norm": 2.921875,
"learning_rate": 8.571428571428571e-05,
"loss": 6.0705,
"step": 295
},
{
"epoch": 0.6040816326530613,
"grad_norm": 2.03125,
"learning_rate": 8.60058309037901e-05,
"loss": 5.9669,
"step": 296
},
{
"epoch": 0.6061224489795919,
"grad_norm": 1.9375,
"learning_rate": 8.629737609329446e-05,
"loss": 6.0344,
"step": 297
},
{
"epoch": 0.6081632653061224,
"grad_norm": 3.421875,
"learning_rate": 8.658892128279885e-05,
"loss": 5.8556,
"step": 298
},
{
"epoch": 0.610204081632653,
"grad_norm": 1.796875,
"learning_rate": 8.688046647230322e-05,
"loss": 5.9316,
"step": 299
},
{
"epoch": 0.6122448979591837,
"grad_norm": 2.78125,
"learning_rate": 8.717201166180759e-05,
"loss": 5.8865,
"step": 300
},
{
"epoch": 0.6142857142857143,
"grad_norm": 2.5,
"learning_rate": 8.746355685131195e-05,
"loss": 5.8613,
"step": 301
},
{
"epoch": 0.6163265306122448,
"grad_norm": 1.640625,
"learning_rate": 8.775510204081632e-05,
"loss": 5.9319,
"step": 302
},
{
"epoch": 0.6183673469387755,
"grad_norm": 2.71875,
"learning_rate": 8.80466472303207e-05,
"loss": 6.0128,
"step": 303
},
{
"epoch": 0.6204081632653061,
"grad_norm": 2.5625,
"learning_rate": 8.833819241982508e-05,
"loss": 6.0924,
"step": 304
},
{
"epoch": 0.6224489795918368,
"grad_norm": 1.9140625,
"learning_rate": 8.862973760932946e-05,
"loss": 5.987,
"step": 305
},
{
"epoch": 0.6244897959183674,
"grad_norm": 3.84375,
"learning_rate": 8.892128279883383e-05,
"loss": 5.9603,
"step": 306
},
{
"epoch": 0.6265306122448979,
"grad_norm": 2.203125,
"learning_rate": 8.92128279883382e-05,
"loss": 5.9091,
"step": 307
},
{
"epoch": 0.6285714285714286,
"grad_norm": 4.75,
"learning_rate": 8.950437317784257e-05,
"loss": 5.9154,
"step": 308
},
{
"epoch": 0.6306122448979592,
"grad_norm": 2.40625,
"learning_rate": 8.979591836734695e-05,
"loss": 6.0045,
"step": 309
},
{
"epoch": 0.6326530612244898,
"grad_norm": 4.15625,
"learning_rate": 9.008746355685132e-05,
"loss": 6.0836,
"step": 310
},
{
"epoch": 0.6346938775510204,
"grad_norm": 3.078125,
"learning_rate": 9.037900874635569e-05,
"loss": 5.9195,
"step": 311
},
{
"epoch": 0.636734693877551,
"grad_norm": 2.984375,
"learning_rate": 9.067055393586006e-05,
"loss": 6.0057,
"step": 312
},
{
"epoch": 0.6387755102040816,
"grad_norm": 1.890625,
"learning_rate": 9.096209912536443e-05,
"loss": 5.8223,
"step": 313
},
{
"epoch": 0.6408163265306123,
"grad_norm": 2.875,
"learning_rate": 9.125364431486881e-05,
"loss": 5.9448,
"step": 314
},
{
"epoch": 0.6428571428571429,
"grad_norm": 1.9453125,
"learning_rate": 9.154518950437319e-05,
"loss": 6.0801,
"step": 315
},
{
"epoch": 0.6448979591836734,
"grad_norm": 5.03125,
"learning_rate": 9.183673469387756e-05,
"loss": 5.9737,
"step": 316
},
{
"epoch": 0.6469387755102041,
"grad_norm": 2.25,
"learning_rate": 9.212827988338193e-05,
"loss": 5.7682,
"step": 317
},
{
"epoch": 0.6489795918367347,
"grad_norm": 2.875,
"learning_rate": 9.24198250728863e-05,
"loss": 5.836,
"step": 318
},
{
"epoch": 0.6510204081632653,
"grad_norm": 2.125,
"learning_rate": 9.271137026239067e-05,
"loss": 5.8778,
"step": 319
},
{
"epoch": 0.6530612244897959,
"grad_norm": 2.3125,
"learning_rate": 9.300291545189505e-05,
"loss": 5.9055,
"step": 320
},
{
"epoch": 0.6551020408163265,
"grad_norm": 2.734375,
"learning_rate": 9.329446064139942e-05,
"loss": 6.0365,
"step": 321
},
{
"epoch": 0.6571428571428571,
"grad_norm": 1.6796875,
"learning_rate": 9.358600583090379e-05,
"loss": 5.7881,
"step": 322
},
{
"epoch": 0.6591836734693878,
"grad_norm": 3.015625,
"learning_rate": 9.387755102040817e-05,
"loss": 5.9185,
"step": 323
},
{
"epoch": 0.6612244897959184,
"grad_norm": 1.9609375,
"learning_rate": 9.416909620991254e-05,
"loss": 5.7898,
"step": 324
},
{
"epoch": 0.6632653061224489,
"grad_norm": 3.75,
"learning_rate": 9.446064139941691e-05,
"loss": 5.9171,
"step": 325
},
{
"epoch": 0.6653061224489796,
"grad_norm": 2.28125,
"learning_rate": 9.475218658892129e-05,
"loss": 5.9707,
"step": 326
},
{
"epoch": 0.6673469387755102,
"grad_norm": 4.4375,
"learning_rate": 9.504373177842566e-05,
"loss": 5.8368,
"step": 327
},
{
"epoch": 0.6693877551020408,
"grad_norm": 3.5,
"learning_rate": 9.533527696793003e-05,
"loss": 5.9395,
"step": 328
},
{
"epoch": 0.6714285714285714,
"grad_norm": 2.75,
"learning_rate": 9.56268221574344e-05,
"loss": 5.9225,
"step": 329
},
{
"epoch": 0.673469387755102,
"grad_norm": 2.640625,
"learning_rate": 9.591836734693878e-05,
"loss": 5.8534,
"step": 330
},
{
"epoch": 0.6755102040816326,
"grad_norm": 2.625,
"learning_rate": 9.620991253644317e-05,
"loss": 5.8768,
"step": 331
},
{
"epoch": 0.6775510204081633,
"grad_norm": 2.546875,
"learning_rate": 9.650145772594753e-05,
"loss": 5.9243,
"step": 332
},
{
"epoch": 0.6795918367346939,
"grad_norm": 2.078125,
"learning_rate": 9.67930029154519e-05,
"loss": 5.8804,
"step": 333
},
{
"epoch": 0.6816326530612244,
"grad_norm": 4.40625,
"learning_rate": 9.708454810495627e-05,
"loss": 6.2647,
"step": 334
},
{
"epoch": 0.6836734693877551,
"grad_norm": 2.296875,
"learning_rate": 9.737609329446064e-05,
"loss": 5.8774,
"step": 335
},
{
"epoch": 0.6857142857142857,
"grad_norm": 3.96875,
"learning_rate": 9.766763848396502e-05,
"loss": 5.912,
"step": 336
},
{
"epoch": 0.6877551020408164,
"grad_norm": 3.71875,
"learning_rate": 9.79591836734694e-05,
"loss": 5.8912,
"step": 337
},
{
"epoch": 0.689795918367347,
"grad_norm": 4.28125,
"learning_rate": 9.825072886297376e-05,
"loss": 5.7401,
"step": 338
},
{
"epoch": 0.6918367346938775,
"grad_norm": 4.03125,
"learning_rate": 9.854227405247813e-05,
"loss": 5.8699,
"step": 339
},
{
"epoch": 0.6938775510204082,
"grad_norm": 2.328125,
"learning_rate": 9.883381924198251e-05,
"loss": 5.7914,
"step": 340
},
{
"epoch": 0.6959183673469388,
"grad_norm": 2.984375,
"learning_rate": 9.912536443148688e-05,
"loss": 5.8102,
"step": 341
},
{
"epoch": 0.6979591836734694,
"grad_norm": 1.875,
"learning_rate": 9.941690962099127e-05,
"loss": 5.98,
"step": 342
},
{
"epoch": 0.7,
"grad_norm": 2.828125,
"learning_rate": 9.970845481049564e-05,
"loss": 5.9031,
"step": 343
},
{
"epoch": 0.7020408163265306,
"grad_norm": 2.59375,
"learning_rate": 0.0001,
"loss": 5.6908,
"step": 344
},
{
"epoch": 0.7040816326530612,
"grad_norm": 1.671875,
"learning_rate": 9.996760609005507e-05,
"loss": 5.8475,
"step": 345
},
{
"epoch": 0.7061224489795919,
"grad_norm": 1.7265625,
"learning_rate": 9.993521218011015e-05,
"loss": 5.7639,
"step": 346
},
{
"epoch": 0.7081632653061225,
"grad_norm": 1.515625,
"learning_rate": 9.990281827016522e-05,
"loss": 5.5835,
"step": 347
},
{
"epoch": 0.710204081632653,
"grad_norm": 2.265625,
"learning_rate": 9.987042436022028e-05,
"loss": 5.7026,
"step": 348
},
{
"epoch": 0.7122448979591837,
"grad_norm": 1.9609375,
"learning_rate": 9.983803045027536e-05,
"loss": 5.6181,
"step": 349
},
{
"epoch": 0.7142857142857143,
"grad_norm": 2.28125,
"learning_rate": 9.980563654033043e-05,
"loss": 5.8685,
"step": 350
},
{
"epoch": 0.7163265306122449,
"grad_norm": 1.7265625,
"learning_rate": 9.977324263038549e-05,
"loss": 5.6348,
"step": 351
},
{
"epoch": 0.7183673469387755,
"grad_norm": 2.171875,
"learning_rate": 9.974084872044056e-05,
"loss": 5.7772,
"step": 352
},
{
"epoch": 0.7204081632653061,
"grad_norm": 1.75,
"learning_rate": 9.970845481049564e-05,
"loss": 5.773,
"step": 353
},
{
"epoch": 0.7224489795918367,
"grad_norm": 2.515625,
"learning_rate": 9.96760609005507e-05,
"loss": 5.747,
"step": 354
},
{
"epoch": 0.7244897959183674,
"grad_norm": 2.09375,
"learning_rate": 9.964366699060577e-05,
"loss": 5.8438,
"step": 355
},
{
"epoch": 0.726530612244898,
"grad_norm": 2.515625,
"learning_rate": 9.961127308066083e-05,
"loss": 5.6612,
"step": 356
},
{
"epoch": 0.7285714285714285,
"grad_norm": 2.21875,
"learning_rate": 9.957887917071591e-05,
"loss": 5.7914,
"step": 357
},
{
"epoch": 0.7306122448979592,
"grad_norm": 1.859375,
"learning_rate": 9.954648526077098e-05,
"loss": 5.8725,
"step": 358
},
{
"epoch": 0.7326530612244898,
"grad_norm": 2.34375,
"learning_rate": 9.951409135082604e-05,
"loss": 5.6965,
"step": 359
},
{
"epoch": 0.7346938775510204,
"grad_norm": 2.125,
"learning_rate": 9.948169744088112e-05,
"loss": 5.7224,
"step": 360
},
{
"epoch": 0.736734693877551,
"grad_norm": 1.7109375,
"learning_rate": 9.944930353093619e-05,
"loss": 5.6711,
"step": 361
},
{
"epoch": 0.7387755102040816,
"grad_norm": 1.890625,
"learning_rate": 9.941690962099127e-05,
"loss": 5.9616,
"step": 362
},
{
"epoch": 0.7408163265306122,
"grad_norm": 2.578125,
"learning_rate": 9.938451571104633e-05,
"loss": 5.8727,
"step": 363
},
{
"epoch": 0.7428571428571429,
"grad_norm": 2.875,
"learning_rate": 9.93521218011014e-05,
"loss": 5.6886,
"step": 364
},
{
"epoch": 0.7448979591836735,
"grad_norm": 2.796875,
"learning_rate": 9.931972789115646e-05,
"loss": 5.6566,
"step": 365
},
{
"epoch": 0.746938775510204,
"grad_norm": 2.125,
"learning_rate": 9.928733398121154e-05,
"loss": 5.8179,
"step": 366
},
{
"epoch": 0.7489795918367347,
"grad_norm": 3.515625,
"learning_rate": 9.925494007126661e-05,
"loss": 5.5646,
"step": 367
},
{
"epoch": 0.7510204081632653,
"grad_norm": 2.625,
"learning_rate": 9.922254616132167e-05,
"loss": 5.6489,
"step": 368
},
{
"epoch": 0.753061224489796,
"grad_norm": 3.65625,
"learning_rate": 9.919015225137674e-05,
"loss": 5.5983,
"step": 369
},
{
"epoch": 0.7551020408163265,
"grad_norm": 3.15625,
"learning_rate": 9.915775834143182e-05,
"loss": 5.5495,
"step": 370
},
{
"epoch": 0.7571428571428571,
"grad_norm": 3.828125,
"learning_rate": 9.912536443148688e-05,
"loss": 5.5367,
"step": 371
},
{
"epoch": 0.7591836734693878,
"grad_norm": 2.546875,
"learning_rate": 9.909297052154195e-05,
"loss": 5.6654,
"step": 372
},
{
"epoch": 0.7612244897959184,
"grad_norm": 3.5625,
"learning_rate": 9.906057661159703e-05,
"loss": 5.6685,
"step": 373
},
{
"epoch": 0.763265306122449,
"grad_norm": 2.59375,
"learning_rate": 9.90281827016521e-05,
"loss": 5.5552,
"step": 374
},
{
"epoch": 0.7653061224489796,
"grad_norm": 2.921875,
"learning_rate": 9.899578879170717e-05,
"loss": 5.764,
"step": 375
},
{
"epoch": 0.7673469387755102,
"grad_norm": 3.109375,
"learning_rate": 9.896339488176223e-05,
"loss": 5.7637,
"step": 376
},
{
"epoch": 0.7693877551020408,
"grad_norm": 1.6640625,
"learning_rate": 9.89310009718173e-05,
"loss": 5.6304,
"step": 377
},
{
"epoch": 0.7714285714285715,
"grad_norm": 2.5625,
"learning_rate": 9.889860706187237e-05,
"loss": 5.7364,
"step": 378
},
{
"epoch": 0.773469387755102,
"grad_norm": 1.78125,
"learning_rate": 9.886621315192745e-05,
"loss": 5.705,
"step": 379
},
{
"epoch": 0.7755102040816326,
"grad_norm": 2.578125,
"learning_rate": 9.883381924198251e-05,
"loss": 5.5901,
"step": 380
},
{
"epoch": 0.7775510204081633,
"grad_norm": 1.7265625,
"learning_rate": 9.880142533203758e-05,
"loss": 5.7524,
"step": 381
},
{
"epoch": 0.7795918367346939,
"grad_norm": 2.0625,
"learning_rate": 9.876903142209265e-05,
"loss": 5.5826,
"step": 382
},
{
"epoch": 0.7816326530612245,
"grad_norm": 2.28125,
"learning_rate": 9.873663751214772e-05,
"loss": 5.6024,
"step": 383
},
{
"epoch": 0.7836734693877551,
"grad_norm": 1.765625,
"learning_rate": 9.870424360220279e-05,
"loss": 5.5304,
"step": 384
},
{
"epoch": 0.7857142857142857,
"grad_norm": 2.484375,
"learning_rate": 9.867184969225786e-05,
"loss": 5.5228,
"step": 385
},
{
"epoch": 0.7877551020408163,
"grad_norm": 2.59375,
"learning_rate": 9.863945578231294e-05,
"loss": 5.7729,
"step": 386
},
{
"epoch": 0.789795918367347,
"grad_norm": 2.484375,
"learning_rate": 9.8607061872368e-05,
"loss": 5.5169,
"step": 387
},
{
"epoch": 0.7918367346938775,
"grad_norm": 2.140625,
"learning_rate": 9.857466796242307e-05,
"loss": 5.5264,
"step": 388
},
{
"epoch": 0.7938775510204081,
"grad_norm": 2.1875,
"learning_rate": 9.854227405247813e-05,
"loss": 5.5907,
"step": 389
},
{
"epoch": 0.7959183673469388,
"grad_norm": 1.7890625,
"learning_rate": 9.850988014253321e-05,
"loss": 5.5483,
"step": 390
},
{
"epoch": 0.7979591836734694,
"grad_norm": 1.90625,
"learning_rate": 9.847748623258828e-05,
"loss": 5.6224,
"step": 391
},
{
"epoch": 0.8,
"grad_norm": 2.265625,
"learning_rate": 9.844509232264336e-05,
"loss": 5.4087,
"step": 392
},
{
"epoch": 0.8020408163265306,
"grad_norm": 1.7421875,
"learning_rate": 9.841269841269841e-05,
"loss": 5.5928,
"step": 393
},
{
"epoch": 0.8040816326530612,
"grad_norm": 2.578125,
"learning_rate": 9.838030450275349e-05,
"loss": 5.6086,
"step": 394
},
{
"epoch": 0.8061224489795918,
"grad_norm": 2.21875,
"learning_rate": 9.834791059280855e-05,
"loss": 5.6237,
"step": 395
},
{
"epoch": 0.8081632653061225,
"grad_norm": 3.453125,
"learning_rate": 9.831551668286363e-05,
"loss": 5.5317,
"step": 396
},
{
"epoch": 0.810204081632653,
"grad_norm": 2.484375,
"learning_rate": 9.82831227729187e-05,
"loss": 5.539,
"step": 397
},
{
"epoch": 0.8122448979591836,
"grad_norm": 2.75,
"learning_rate": 9.825072886297376e-05,
"loss": 5.5483,
"step": 398
},
{
"epoch": 0.8142857142857143,
"grad_norm": 3.34375,
"learning_rate": 9.821833495302883e-05,
"loss": 5.491,
"step": 399
},
{
"epoch": 0.8163265306122449,
"grad_norm": 2.296875,
"learning_rate": 9.818594104308391e-05,
"loss": 5.5646,
"step": 400
},
{
"epoch": 0.8183673469387756,
"grad_norm": 2.296875,
"learning_rate": 9.815354713313897e-05,
"loss": 5.4056,
"step": 401
},
{
"epoch": 0.8204081632653061,
"grad_norm": 1.796875,
"learning_rate": 9.812115322319404e-05,
"loss": 5.4781,
"step": 402
},
{
"epoch": 0.8224489795918367,
"grad_norm": 2.34375,
"learning_rate": 9.808875931324912e-05,
"loss": 5.4442,
"step": 403
},
{
"epoch": 0.8244897959183674,
"grad_norm": 1.8359375,
"learning_rate": 9.805636540330418e-05,
"loss": 5.5673,
"step": 404
},
{
"epoch": 0.826530612244898,
"grad_norm": 2.34375,
"learning_rate": 9.802397149335926e-05,
"loss": 5.5,
"step": 405
},
{
"epoch": 0.8285714285714286,
"grad_norm": 1.9453125,
"learning_rate": 9.799157758341431e-05,
"loss": 5.483,
"step": 406
},
{
"epoch": 0.8306122448979592,
"grad_norm": 2.65625,
"learning_rate": 9.79591836734694e-05,
"loss": 5.3602,
"step": 407
},
{
"epoch": 0.8326530612244898,
"grad_norm": 2.234375,
"learning_rate": 9.792678976352446e-05,
"loss": 5.5128,
"step": 408
},
{
"epoch": 0.8346938775510204,
"grad_norm": 1.8828125,
"learning_rate": 9.789439585357954e-05,
"loss": 5.4923,
"step": 409
},
{
"epoch": 0.8367346938775511,
"grad_norm": 2.671875,
"learning_rate": 9.786200194363459e-05,
"loss": 5.4525,
"step": 410
},
{
"epoch": 0.8387755102040816,
"grad_norm": 1.71875,
"learning_rate": 9.782960803368967e-05,
"loss": 5.4164,
"step": 411
},
{
"epoch": 0.8408163265306122,
"grad_norm": 2.15625,
"learning_rate": 9.779721412374473e-05,
"loss": 5.415,
"step": 412
},
{
"epoch": 0.8428571428571429,
"grad_norm": 2.09375,
"learning_rate": 9.776482021379981e-05,
"loss": 5.4444,
"step": 413
},
{
"epoch": 0.8448979591836735,
"grad_norm": 2.171875,
"learning_rate": 9.773242630385488e-05,
"loss": 5.4948,
"step": 414
},
{
"epoch": 0.8469387755102041,
"grad_norm": 1.8203125,
"learning_rate": 9.770003239390995e-05,
"loss": 5.3823,
"step": 415
},
{
"epoch": 0.8489795918367347,
"grad_norm": 2.484375,
"learning_rate": 9.766763848396502e-05,
"loss": 5.4814,
"step": 416
},
{
"epoch": 0.8510204081632653,
"grad_norm": 1.625,
"learning_rate": 9.763524457402009e-05,
"loss": 5.2718,
"step": 417
},
{
"epoch": 0.8530612244897959,
"grad_norm": 2.375,
"learning_rate": 9.760285066407517e-05,
"loss": 5.2892,
"step": 418
},
{
"epoch": 0.8551020408163266,
"grad_norm": 2.21875,
"learning_rate": 9.757045675413022e-05,
"loss": 5.4267,
"step": 419
},
{
"epoch": 0.8571428571428571,
"grad_norm": 2.65625,
"learning_rate": 9.75380628441853e-05,
"loss": 5.4264,
"step": 420
},
{
"epoch": 0.8591836734693877,
"grad_norm": 2.0,
"learning_rate": 9.750566893424037e-05,
"loss": 5.4557,
"step": 421
},
{
"epoch": 0.8612244897959184,
"grad_norm": 2.203125,
"learning_rate": 9.747327502429544e-05,
"loss": 5.509,
"step": 422
},
{
"epoch": 0.863265306122449,
"grad_norm": 2.25,
"learning_rate": 9.74408811143505e-05,
"loss": 5.4043,
"step": 423
},
{
"epoch": 0.8653061224489796,
"grad_norm": 1.9140625,
"learning_rate": 9.740848720440558e-05,
"loss": 5.4319,
"step": 424
},
{
"epoch": 0.8673469387755102,
"grad_norm": 2.90625,
"learning_rate": 9.737609329446064e-05,
"loss": 5.3586,
"step": 425
},
{
"epoch": 0.8693877551020408,
"grad_norm": 1.9765625,
"learning_rate": 9.734369938451572e-05,
"loss": 5.3789,
"step": 426
},
{
"epoch": 0.8714285714285714,
"grad_norm": 2.90625,
"learning_rate": 9.731130547457079e-05,
"loss": 5.3776,
"step": 427
},
{
"epoch": 0.8734693877551021,
"grad_norm": 1.859375,
"learning_rate": 9.727891156462585e-05,
"loss": 5.3532,
"step": 428
},
{
"epoch": 0.8755102040816326,
"grad_norm": 2.609375,
"learning_rate": 9.724651765468092e-05,
"loss": 5.526,
"step": 429
},
{
"epoch": 0.8775510204081632,
"grad_norm": 2.59375,
"learning_rate": 9.7214123744736e-05,
"loss": 5.2067,
"step": 430
},
{
"epoch": 0.8795918367346939,
"grad_norm": 2.109375,
"learning_rate": 9.718172983479106e-05,
"loss": 5.4407,
"step": 431
},
{
"epoch": 0.8816326530612245,
"grad_norm": 2.515625,
"learning_rate": 9.714933592484613e-05,
"loss": 5.3648,
"step": 432
},
{
"epoch": 0.8836734693877552,
"grad_norm": 1.6953125,
"learning_rate": 9.711694201490121e-05,
"loss": 5.3088,
"step": 433
},
{
"epoch": 0.8857142857142857,
"grad_norm": 3.28125,
"learning_rate": 9.708454810495627e-05,
"loss": 5.2259,
"step": 434
},
{
"epoch": 0.8877551020408163,
"grad_norm": 1.84375,
"learning_rate": 9.705215419501135e-05,
"loss": 5.3369,
"step": 435
},
{
"epoch": 0.889795918367347,
"grad_norm": 2.9375,
"learning_rate": 9.70197602850664e-05,
"loss": 5.2903,
"step": 436
},
{
"epoch": 0.8918367346938776,
"grad_norm": 2.34375,
"learning_rate": 9.698736637512148e-05,
"loss": 5.3472,
"step": 437
},
{
"epoch": 0.8938775510204081,
"grad_norm": 3.5625,
"learning_rate": 9.695497246517655e-05,
"loss": 5.352,
"step": 438
},
{
"epoch": 0.8959183673469387,
"grad_norm": 2.546875,
"learning_rate": 9.692257855523163e-05,
"loss": 5.4007,
"step": 439
},
{
"epoch": 0.8979591836734694,
"grad_norm": 3.109375,
"learning_rate": 9.689018464528668e-05,
"loss": 5.2628,
"step": 440
},
{
"epoch": 0.9,
"grad_norm": 2.234375,
"learning_rate": 9.685779073534176e-05,
"loss": 5.2345,
"step": 441
},
{
"epoch": 0.9020408163265307,
"grad_norm": 3.15625,
"learning_rate": 9.682539682539682e-05,
"loss": 5.3104,
"step": 442
},
{
"epoch": 0.9040816326530612,
"grad_norm": 2.375,
"learning_rate": 9.67930029154519e-05,
"loss": 5.4044,
"step": 443
},
{
"epoch": 0.9061224489795918,
"grad_norm": 3.015625,
"learning_rate": 9.676060900550697e-05,
"loss": 5.2699,
"step": 444
},
{
"epoch": 0.9081632653061225,
"grad_norm": 2.5,
"learning_rate": 9.672821509556203e-05,
"loss": 5.2957,
"step": 445
},
{
"epoch": 0.9102040816326531,
"grad_norm": 2.640625,
"learning_rate": 9.669582118561711e-05,
"loss": 5.362,
"step": 446
},
{
"epoch": 0.9122448979591836,
"grad_norm": 2.515625,
"learning_rate": 9.666342727567218e-05,
"loss": 5.3189,
"step": 447
},
{
"epoch": 0.9142857142857143,
"grad_norm": 2.484375,
"learning_rate": 9.663103336572726e-05,
"loss": 5.3132,
"step": 448
},
{
"epoch": 0.9163265306122449,
"grad_norm": 1.9140625,
"learning_rate": 9.659863945578231e-05,
"loss": 5.234,
"step": 449
},
{
"epoch": 0.9183673469387755,
"grad_norm": 2.578125,
"learning_rate": 9.656624554583739e-05,
"loss": 5.2804,
"step": 450
},
{
"epoch": 0.9204081632653062,
"grad_norm": 2.375,
"learning_rate": 9.653385163589246e-05,
"loss": 5.3495,
"step": 451
},
{
"epoch": 0.9224489795918367,
"grad_norm": 1.890625,
"learning_rate": 9.650145772594753e-05,
"loss": 5.221,
"step": 452
},
{
"epoch": 0.9244897959183673,
"grad_norm": 3.0,
"learning_rate": 9.646906381600259e-05,
"loss": 5.1243,
"step": 453
},
{
"epoch": 0.926530612244898,
"grad_norm": 1.6015625,
"learning_rate": 9.643666990605767e-05,
"loss": 5.2523,
"step": 454
},
{
"epoch": 0.9285714285714286,
"grad_norm": 2.765625,
"learning_rate": 9.640427599611273e-05,
"loss": 5.2834,
"step": 455
},
{
"epoch": 0.9306122448979591,
"grad_norm": 1.6953125,
"learning_rate": 9.637188208616781e-05,
"loss": 5.3789,
"step": 456
},
{
"epoch": 0.9326530612244898,
"grad_norm": 2.65625,
"learning_rate": 9.633948817622288e-05,
"loss": 5.1874,
"step": 457
},
{
"epoch": 0.9346938775510204,
"grad_norm": 1.7734375,
"learning_rate": 9.630709426627794e-05,
"loss": 5.2311,
"step": 458
},
{
"epoch": 0.936734693877551,
"grad_norm": 3.046875,
"learning_rate": 9.627470035633302e-05,
"loss": 5.3345,
"step": 459
},
{
"epoch": 0.9387755102040817,
"grad_norm": 2.46875,
"learning_rate": 9.624230644638809e-05,
"loss": 5.2116,
"step": 460
},
{
"epoch": 0.9408163265306122,
"grad_norm": 2.140625,
"learning_rate": 9.620991253644317e-05,
"loss": 5.1734,
"step": 461
},
{
"epoch": 0.9428571428571428,
"grad_norm": 2.765625,
"learning_rate": 9.617751862649822e-05,
"loss": 5.1,
"step": 462
},
{
"epoch": 0.9448979591836735,
"grad_norm": 2.953125,
"learning_rate": 9.61451247165533e-05,
"loss": 5.2185,
"step": 463
},
{
"epoch": 0.9469387755102041,
"grad_norm": 2.0625,
"learning_rate": 9.611273080660836e-05,
"loss": 5.2862,
"step": 464
},
{
"epoch": 0.9489795918367347,
"grad_norm": 2.140625,
"learning_rate": 9.608033689666344e-05,
"loss": 5.2224,
"step": 465
},
{
"epoch": 0.9510204081632653,
"grad_norm": 1.9453125,
"learning_rate": 9.604794298671849e-05,
"loss": 5.1458,
"step": 466
},
{
"epoch": 0.9530612244897959,
"grad_norm": 2.0,
"learning_rate": 9.601554907677357e-05,
"loss": 5.1679,
"step": 467
},
{
"epoch": 0.9551020408163265,
"grad_norm": 2.390625,
"learning_rate": 9.598315516682864e-05,
"loss": 5.1953,
"step": 468
},
{
"epoch": 0.9571428571428572,
"grad_norm": 1.890625,
"learning_rate": 9.595076125688372e-05,
"loss": 5.1759,
"step": 469
},
{
"epoch": 0.9591836734693877,
"grad_norm": 2.46875,
"learning_rate": 9.591836734693878e-05,
"loss": 5.331,
"step": 470
},
{
"epoch": 0.9612244897959183,
"grad_norm": 2.046875,
"learning_rate": 9.588597343699385e-05,
"loss": 5.374,
"step": 471
},
{
"epoch": 0.963265306122449,
"grad_norm": 2.546875,
"learning_rate": 9.585357952704891e-05,
"loss": 5.0785,
"step": 472
},
{
"epoch": 0.9653061224489796,
"grad_norm": 2.390625,
"learning_rate": 9.582118561710399e-05,
"loss": 5.2189,
"step": 473
},
{
"epoch": 0.9673469387755103,
"grad_norm": 2.140625,
"learning_rate": 9.578879170715906e-05,
"loss": 5.1768,
"step": 474
},
{
"epoch": 0.9693877551020408,
"grad_norm": 2.203125,
"learning_rate": 9.575639779721412e-05,
"loss": 5.1351,
"step": 475
},
{
"epoch": 0.9714285714285714,
"grad_norm": 2.078125,
"learning_rate": 9.57240038872692e-05,
"loss": 5.2468,
"step": 476
},
{
"epoch": 0.9734693877551021,
"grad_norm": 2.546875,
"learning_rate": 9.569160997732427e-05,
"loss": 5.1924,
"step": 477
},
{
"epoch": 0.9755102040816327,
"grad_norm": 2.15625,
"learning_rate": 9.565921606737935e-05,
"loss": 5.1984,
"step": 478
},
{
"epoch": 0.9775510204081632,
"grad_norm": 2.234375,
"learning_rate": 9.56268221574344e-05,
"loss": 5.1939,
"step": 479
},
{
"epoch": 0.9795918367346939,
"grad_norm": 2.09375,
"learning_rate": 9.559442824748948e-05,
"loss": 5.3328,
"step": 480
},
{
"epoch": 0.9816326530612245,
"grad_norm": 2.78125,
"learning_rate": 9.556203433754454e-05,
"loss": 5.147,
"step": 481
},
{
"epoch": 0.9836734693877551,
"grad_norm": 2.15625,
"learning_rate": 9.552964042759962e-05,
"loss": 5.0896,
"step": 482
},
{
"epoch": 0.9857142857142858,
"grad_norm": 2.734375,
"learning_rate": 9.549724651765468e-05,
"loss": 5.2347,
"step": 483
},
{
"epoch": 0.9877551020408163,
"grad_norm": 2.359375,
"learning_rate": 9.546485260770975e-05,
"loss": 5.0827,
"step": 484
},
{
"epoch": 0.9897959183673469,
"grad_norm": 2.421875,
"learning_rate": 9.543245869776482e-05,
"loss": 5.1718,
"step": 485
},
{
"epoch": 0.9918367346938776,
"grad_norm": 1.9609375,
"learning_rate": 9.54000647878199e-05,
"loss": 5.2481,
"step": 486
},
{
"epoch": 0.9938775510204082,
"grad_norm": 2.0,
"learning_rate": 9.536767087787496e-05,
"loss": 5.106,
"step": 487
},
{
"epoch": 0.9959183673469387,
"grad_norm": 2.65625,
"learning_rate": 9.533527696793003e-05,
"loss": 5.1127,
"step": 488
},
{
"epoch": 0.9979591836734694,
"grad_norm": 1.78125,
"learning_rate": 9.530288305798511e-05,
"loss": 5.1815,
"step": 489
},
{
"epoch": 1.0,
"grad_norm": 2.4375,
"learning_rate": 9.527048914804018e-05,
"loss": 5.1918,
"step": 490
},
{
"epoch": 1.0020408163265306,
"grad_norm": 2.1875,
"learning_rate": 9.523809523809524e-05,
"loss": 5.0281,
"step": 491
},
{
"epoch": 1.0040816326530613,
"grad_norm": 2.40625,
"learning_rate": 9.52057013281503e-05,
"loss": 5.0703,
"step": 492
},
{
"epoch": 1.006122448979592,
"grad_norm": 2.1875,
"learning_rate": 9.517330741820539e-05,
"loss": 5.0325,
"step": 493
},
{
"epoch": 1.0081632653061225,
"grad_norm": 2.296875,
"learning_rate": 9.514091350826045e-05,
"loss": 5.1937,
"step": 494
},
{
"epoch": 1.010204081632653,
"grad_norm": 2.140625,
"learning_rate": 9.510851959831553e-05,
"loss": 4.9899,
"step": 495
},
{
"epoch": 1.0122448979591836,
"grad_norm": 1.9375,
"learning_rate": 9.507612568837058e-05,
"loss": 5.2111,
"step": 496
},
{
"epoch": 1.0142857142857142,
"grad_norm": 2.09375,
"learning_rate": 9.504373177842566e-05,
"loss": 5.0057,
"step": 497
},
{
"epoch": 1.0163265306122449,
"grad_norm": 2.0,
"learning_rate": 9.501133786848073e-05,
"loss": 5.0491,
"step": 498
},
{
"epoch": 1.0183673469387755,
"grad_norm": 2.328125,
"learning_rate": 9.49789439585358e-05,
"loss": 5.0318,
"step": 499
},
{
"epoch": 1.0204081632653061,
"grad_norm": 1.953125,
"learning_rate": 9.494655004859087e-05,
"loss": 5.1135,
"step": 500
},
{
"epoch": 1.0204081632653061,
"eval_loss": 4.40017032623291,
"eval_runtime": 14.6713,
"eval_samples_per_second": 10.906,
"eval_steps_per_second": 2.726,
"step": 500
},
{
"epoch": 1.0224489795918368,
"grad_norm": 1.9375,
"learning_rate": 9.491415613864594e-05,
"loss": 5.0543,
"step": 501
},
{
"epoch": 1.0244897959183674,
"grad_norm": 2.53125,
"learning_rate": 9.488176222870102e-05,
"loss": 5.113,
"step": 502
},
{
"epoch": 1.026530612244898,
"grad_norm": 2.78125,
"learning_rate": 9.484936831875608e-05,
"loss": 5.0466,
"step": 503
},
{
"epoch": 1.0285714285714285,
"grad_norm": 2.25,
"learning_rate": 9.481697440881115e-05,
"loss": 5.0092,
"step": 504
},
{
"epoch": 1.030612244897959,
"grad_norm": 2.203125,
"learning_rate": 9.478458049886621e-05,
"loss": 5.0907,
"step": 505
},
{
"epoch": 1.0326530612244897,
"grad_norm": 2.375,
"learning_rate": 9.475218658892129e-05,
"loss": 5.0782,
"step": 506
},
{
"epoch": 1.0346938775510204,
"grad_norm": 2.359375,
"learning_rate": 9.471979267897636e-05,
"loss": 4.9835,
"step": 507
},
{
"epoch": 1.036734693877551,
"grad_norm": 2.171875,
"learning_rate": 9.468739876903142e-05,
"loss": 5.0113,
"step": 508
},
{
"epoch": 1.0387755102040817,
"grad_norm": 2.375,
"learning_rate": 9.465500485908649e-05,
"loss": 4.9735,
"step": 509
},
{
"epoch": 1.0408163265306123,
"grad_norm": 2.078125,
"learning_rate": 9.462261094914157e-05,
"loss": 4.9344,
"step": 510
},
{
"epoch": 1.042857142857143,
"grad_norm": 2.609375,
"learning_rate": 9.459021703919663e-05,
"loss": 5.0704,
"step": 511
},
{
"epoch": 1.0448979591836736,
"grad_norm": 2.625,
"learning_rate": 9.455782312925171e-05,
"loss": 4.9382,
"step": 512
},
{
"epoch": 1.046938775510204,
"grad_norm": 2.265625,
"learning_rate": 9.452542921930676e-05,
"loss": 5.0419,
"step": 513
},
{
"epoch": 1.0489795918367346,
"grad_norm": 2.65625,
"learning_rate": 9.449303530936184e-05,
"loss": 4.9912,
"step": 514
},
{
"epoch": 1.0510204081632653,
"grad_norm": 2.53125,
"learning_rate": 9.446064139941691e-05,
"loss": 4.9545,
"step": 515
},
{
"epoch": 1.0530612244897959,
"grad_norm": 2.203125,
"learning_rate": 9.442824748947199e-05,
"loss": 5.0483,
"step": 516
},
{
"epoch": 1.0551020408163265,
"grad_norm": 2.09375,
"learning_rate": 9.439585357952705e-05,
"loss": 5.0521,
"step": 517
},
{
"epoch": 1.0571428571428572,
"grad_norm": 2.171875,
"learning_rate": 9.436345966958212e-05,
"loss": 4.9659,
"step": 518
},
{
"epoch": 1.0591836734693878,
"grad_norm": 2.265625,
"learning_rate": 9.43310657596372e-05,
"loss": 4.9462,
"step": 519
},
{
"epoch": 1.0612244897959184,
"grad_norm": 2.03125,
"learning_rate": 9.429867184969226e-05,
"loss": 4.9327,
"step": 520
},
{
"epoch": 1.063265306122449,
"grad_norm": 2.203125,
"learning_rate": 9.426627793974733e-05,
"loss": 5.001,
"step": 521
},
{
"epoch": 1.0653061224489795,
"grad_norm": 2.078125,
"learning_rate": 9.42338840298024e-05,
"loss": 4.8174,
"step": 522
},
{
"epoch": 1.0673469387755101,
"grad_norm": 2.28125,
"learning_rate": 9.420149011985747e-05,
"loss": 4.9902,
"step": 523
},
{
"epoch": 1.0693877551020408,
"grad_norm": 2.46875,
"learning_rate": 9.416909620991254e-05,
"loss": 4.9752,
"step": 524
},
{
"epoch": 1.0714285714285714,
"grad_norm": 2.421875,
"learning_rate": 9.41367022999676e-05,
"loss": 5.035,
"step": 525
},
{
"epoch": 1.073469387755102,
"grad_norm": 2.453125,
"learning_rate": 9.410430839002267e-05,
"loss": 4.9999,
"step": 526
},
{
"epoch": 1.0755102040816327,
"grad_norm": 2.265625,
"learning_rate": 9.407191448007775e-05,
"loss": 4.9897,
"step": 527
},
{
"epoch": 1.0775510204081633,
"grad_norm": 2.203125,
"learning_rate": 9.403952057013282e-05,
"loss": 4.9265,
"step": 528
},
{
"epoch": 1.079591836734694,
"grad_norm": 2.078125,
"learning_rate": 9.40071266601879e-05,
"loss": 5.024,
"step": 529
},
{
"epoch": 1.0816326530612246,
"grad_norm": 2.234375,
"learning_rate": 9.397473275024296e-05,
"loss": 4.8582,
"step": 530
},
{
"epoch": 1.083673469387755,
"grad_norm": 2.53125,
"learning_rate": 9.394233884029803e-05,
"loss": 4.9825,
"step": 531
},
{
"epoch": 1.0857142857142856,
"grad_norm": 2.53125,
"learning_rate": 9.39099449303531e-05,
"loss": 5.0188,
"step": 532
},
{
"epoch": 1.0877551020408163,
"grad_norm": 2.390625,
"learning_rate": 9.387755102040817e-05,
"loss": 4.9018,
"step": 533
},
{
"epoch": 1.089795918367347,
"grad_norm": 2.046875,
"learning_rate": 9.384515711046324e-05,
"loss": 5.101,
"step": 534
},
{
"epoch": 1.0918367346938775,
"grad_norm": 2.71875,
"learning_rate": 9.38127632005183e-05,
"loss": 5.0344,
"step": 535
},
{
"epoch": 1.0938775510204082,
"grad_norm": 2.5625,
"learning_rate": 9.378036929057338e-05,
"loss": 5.0846,
"step": 536
},
{
"epoch": 1.0959183673469388,
"grad_norm": 2.8125,
"learning_rate": 9.374797538062845e-05,
"loss": 4.9642,
"step": 537
},
{
"epoch": 1.0979591836734695,
"grad_norm": 2.28125,
"learning_rate": 9.371558147068351e-05,
"loss": 5.0037,
"step": 538
},
{
"epoch": 1.1,
"grad_norm": 2.09375,
"learning_rate": 9.368318756073858e-05,
"loss": 4.9107,
"step": 539
},
{
"epoch": 1.1020408163265305,
"grad_norm": 2.265625,
"learning_rate": 9.365079365079366e-05,
"loss": 4.9987,
"step": 540
},
{
"epoch": 1.1040816326530611,
"grad_norm": 2.078125,
"learning_rate": 9.361839974084872e-05,
"loss": 4.8866,
"step": 541
},
{
"epoch": 1.1061224489795918,
"grad_norm": 2.375,
"learning_rate": 9.358600583090379e-05,
"loss": 5.0313,
"step": 542
},
{
"epoch": 1.1081632653061224,
"grad_norm": 1.640625,
"learning_rate": 9.355361192095887e-05,
"loss": 4.8962,
"step": 543
},
{
"epoch": 1.110204081632653,
"grad_norm": 3.203125,
"learning_rate": 9.352121801101393e-05,
"loss": 4.992,
"step": 544
},
{
"epoch": 1.1122448979591837,
"grad_norm": 2.640625,
"learning_rate": 9.348882410106901e-05,
"loss": 5.0842,
"step": 545
},
{
"epoch": 1.1142857142857143,
"grad_norm": 2.46875,
"learning_rate": 9.345643019112408e-05,
"loss": 4.9707,
"step": 546
},
{
"epoch": 1.116326530612245,
"grad_norm": 2.984375,
"learning_rate": 9.342403628117914e-05,
"loss": 4.9968,
"step": 547
},
{
"epoch": 1.1183673469387756,
"grad_norm": 2.15625,
"learning_rate": 9.339164237123421e-05,
"loss": 4.8544,
"step": 548
},
{
"epoch": 1.120408163265306,
"grad_norm": 2.109375,
"learning_rate": 9.335924846128929e-05,
"loss": 4.9132,
"step": 549
},
{
"epoch": 1.1224489795918366,
"grad_norm": 2.203125,
"learning_rate": 9.332685455134435e-05,
"loss": 4.9301,
"step": 550
},
{
"epoch": 1.1244897959183673,
"grad_norm": 2.09375,
"learning_rate": 9.329446064139942e-05,
"loss": 4.9584,
"step": 551
},
{
"epoch": 1.126530612244898,
"grad_norm": 2.625,
"learning_rate": 9.326206673145448e-05,
"loss": 4.965,
"step": 552
},
{
"epoch": 1.1285714285714286,
"grad_norm": 2.046875,
"learning_rate": 9.322967282150956e-05,
"loss": 4.8883,
"step": 553
},
{
"epoch": 1.1306122448979592,
"grad_norm": 2.5625,
"learning_rate": 9.319727891156463e-05,
"loss": 4.9301,
"step": 554
},
{
"epoch": 1.1326530612244898,
"grad_norm": 1.9921875,
"learning_rate": 9.31648850016197e-05,
"loss": 4.9611,
"step": 555
},
{
"epoch": 1.1346938775510205,
"grad_norm": 2.421875,
"learning_rate": 9.313249109167476e-05,
"loss": 4.9668,
"step": 556
},
{
"epoch": 1.136734693877551,
"grad_norm": 2.015625,
"learning_rate": 9.310009718172984e-05,
"loss": 5.0554,
"step": 557
},
{
"epoch": 1.1387755102040815,
"grad_norm": 2.65625,
"learning_rate": 9.30677032717849e-05,
"loss": 5.0055,
"step": 558
},
{
"epoch": 1.1408163265306122,
"grad_norm": 2.3125,
"learning_rate": 9.303530936183998e-05,
"loss": 4.9066,
"step": 559
},
{
"epoch": 1.1428571428571428,
"grad_norm": 1.96875,
"learning_rate": 9.300291545189505e-05,
"loss": 5.0405,
"step": 560
},
{
"epoch": 1.1448979591836734,
"grad_norm": 2.09375,
"learning_rate": 9.297052154195012e-05,
"loss": 4.9479,
"step": 561
},
{
"epoch": 1.146938775510204,
"grad_norm": 1.9765625,
"learning_rate": 9.29381276320052e-05,
"loss": 4.9936,
"step": 562
},
{
"epoch": 1.1489795918367347,
"grad_norm": 2.140625,
"learning_rate": 9.290573372206026e-05,
"loss": 4.9178,
"step": 563
},
{
"epoch": 1.1510204081632653,
"grad_norm": 2.25,
"learning_rate": 9.287333981211533e-05,
"loss": 4.9577,
"step": 564
},
{
"epoch": 1.153061224489796,
"grad_norm": 2.328125,
"learning_rate": 9.284094590217039e-05,
"loss": 4.9056,
"step": 565
},
{
"epoch": 1.1551020408163266,
"grad_norm": 2.15625,
"learning_rate": 9.280855199222547e-05,
"loss": 4.9087,
"step": 566
},
{
"epoch": 1.157142857142857,
"grad_norm": 2.203125,
"learning_rate": 9.277615808228054e-05,
"loss": 4.869,
"step": 567
},
{
"epoch": 1.1591836734693877,
"grad_norm": 1.859375,
"learning_rate": 9.27437641723356e-05,
"loss": 5.0266,
"step": 568
},
{
"epoch": 1.1612244897959183,
"grad_norm": 2.328125,
"learning_rate": 9.271137026239067e-05,
"loss": 4.8804,
"step": 569
},
{
"epoch": 1.163265306122449,
"grad_norm": 2.46875,
"learning_rate": 9.267897635244575e-05,
"loss": 4.7398,
"step": 570
},
{
"epoch": 1.1653061224489796,
"grad_norm": 1.5390625,
"learning_rate": 9.264658244250081e-05,
"loss": 4.8832,
"step": 571
},
{
"epoch": 1.1673469387755102,
"grad_norm": 2.703125,
"learning_rate": 9.261418853255588e-05,
"loss": 4.945,
"step": 572
},
{
"epoch": 1.1693877551020408,
"grad_norm": 2.203125,
"learning_rate": 9.258179462261096e-05,
"loss": 4.9119,
"step": 573
},
{
"epoch": 1.1714285714285715,
"grad_norm": 2.203125,
"learning_rate": 9.254940071266602e-05,
"loss": 4.9341,
"step": 574
},
{
"epoch": 1.1734693877551021,
"grad_norm": 3.1875,
"learning_rate": 9.25170068027211e-05,
"loss": 4.9101,
"step": 575
},
{
"epoch": 1.1755102040816325,
"grad_norm": 2.09375,
"learning_rate": 9.248461289277617e-05,
"loss": 4.9925,
"step": 576
},
{
"epoch": 1.1775510204081632,
"grad_norm": 2.578125,
"learning_rate": 9.245221898283123e-05,
"loss": 4.9555,
"step": 577
},
{
"epoch": 1.1795918367346938,
"grad_norm": 2.203125,
"learning_rate": 9.24198250728863e-05,
"loss": 4.8755,
"step": 578
},
{
"epoch": 1.1816326530612244,
"grad_norm": 2.609375,
"learning_rate": 9.238743116294138e-05,
"loss": 4.9367,
"step": 579
},
{
"epoch": 1.183673469387755,
"grad_norm": 2.078125,
"learning_rate": 9.235503725299644e-05,
"loss": 4.9645,
"step": 580
},
{
"epoch": 1.1857142857142857,
"grad_norm": 2.203125,
"learning_rate": 9.232264334305151e-05,
"loss": 4.9078,
"step": 581
},
{
"epoch": 1.1877551020408164,
"grad_norm": 2.5,
"learning_rate": 9.229024943310657e-05,
"loss": 4.9647,
"step": 582
},
{
"epoch": 1.189795918367347,
"grad_norm": 2.09375,
"learning_rate": 9.225785552316165e-05,
"loss": 4.9639,
"step": 583
},
{
"epoch": 1.1918367346938776,
"grad_norm": 2.40625,
"learning_rate": 9.222546161321672e-05,
"loss": 4.8762,
"step": 584
},
{
"epoch": 1.193877551020408,
"grad_norm": 2.234375,
"learning_rate": 9.219306770327178e-05,
"loss": 4.9132,
"step": 585
},
{
"epoch": 1.1959183673469387,
"grad_norm": 1.859375,
"learning_rate": 9.216067379332686e-05,
"loss": 4.8061,
"step": 586
},
{
"epoch": 1.1979591836734693,
"grad_norm": 1.7265625,
"learning_rate": 9.212827988338193e-05,
"loss": 4.9384,
"step": 587
},
{
"epoch": 1.2,
"grad_norm": 2.203125,
"learning_rate": 9.209588597343701e-05,
"loss": 4.936,
"step": 588
},
{
"epoch": 1.2020408163265306,
"grad_norm": 2.078125,
"learning_rate": 9.206349206349206e-05,
"loss": 4.8928,
"step": 589
},
{
"epoch": 1.2040816326530612,
"grad_norm": 1.953125,
"learning_rate": 9.203109815354714e-05,
"loss": 4.886,
"step": 590
},
{
"epoch": 1.2061224489795919,
"grad_norm": 2.21875,
"learning_rate": 9.19987042436022e-05,
"loss": 4.9312,
"step": 591
},
{
"epoch": 1.2081632653061225,
"grad_norm": 1.5625,
"learning_rate": 9.196631033365728e-05,
"loss": 4.8449,
"step": 592
},
{
"epoch": 1.2102040816326531,
"grad_norm": 1.703125,
"learning_rate": 9.193391642371235e-05,
"loss": 4.6902,
"step": 593
},
{
"epoch": 1.2122448979591836,
"grad_norm": 1.5859375,
"learning_rate": 9.190152251376742e-05,
"loss": 4.9792,
"step": 594
},
{
"epoch": 1.2142857142857142,
"grad_norm": 1.7890625,
"learning_rate": 9.186912860382248e-05,
"loss": 4.8343,
"step": 595
},
{
"epoch": 1.2163265306122448,
"grad_norm": 2.09375,
"learning_rate": 9.183673469387756e-05,
"loss": 4.9856,
"step": 596
},
{
"epoch": 1.2183673469387755,
"grad_norm": 1.984375,
"learning_rate": 9.180434078393263e-05,
"loss": 5.0087,
"step": 597
},
{
"epoch": 1.220408163265306,
"grad_norm": 2.8125,
"learning_rate": 9.177194687398769e-05,
"loss": 4.9597,
"step": 598
},
{
"epoch": 1.2224489795918367,
"grad_norm": 1.609375,
"learning_rate": 9.173955296404276e-05,
"loss": 4.8544,
"step": 599
},
{
"epoch": 1.2244897959183674,
"grad_norm": 2.875,
"learning_rate": 9.170715905409784e-05,
"loss": 4.7941,
"step": 600
},
{
"epoch": 1.226530612244898,
"grad_norm": 1.9765625,
"learning_rate": 9.16747651441529e-05,
"loss": 4.8669,
"step": 601
},
{
"epoch": 1.2285714285714286,
"grad_norm": 3.03125,
"learning_rate": 9.164237123420797e-05,
"loss": 4.8347,
"step": 602
},
{
"epoch": 1.230612244897959,
"grad_norm": 2.328125,
"learning_rate": 9.160997732426305e-05,
"loss": 5.0321,
"step": 603
},
{
"epoch": 1.2326530612244897,
"grad_norm": 2.484375,
"learning_rate": 9.157758341431811e-05,
"loss": 4.9522,
"step": 604
},
{
"epoch": 1.2346938775510203,
"grad_norm": 2.453125,
"learning_rate": 9.154518950437319e-05,
"loss": 4.9245,
"step": 605
},
{
"epoch": 1.236734693877551,
"grad_norm": 1.890625,
"learning_rate": 9.151279559442824e-05,
"loss": 4.9363,
"step": 606
},
{
"epoch": 1.2387755102040816,
"grad_norm": 2.03125,
"learning_rate": 9.148040168448332e-05,
"loss": 4.8159,
"step": 607
},
{
"epoch": 1.2408163265306122,
"grad_norm": 1.703125,
"learning_rate": 9.144800777453839e-05,
"loss": 4.9212,
"step": 608
},
{
"epoch": 1.2428571428571429,
"grad_norm": 1.90625,
"learning_rate": 9.141561386459347e-05,
"loss": 4.9119,
"step": 609
},
{
"epoch": 1.2448979591836735,
"grad_norm": 2.109375,
"learning_rate": 9.138321995464853e-05,
"loss": 4.9227,
"step": 610
},
{
"epoch": 1.2469387755102042,
"grad_norm": 2.625,
"learning_rate": 9.13508260447036e-05,
"loss": 4.9165,
"step": 611
},
{
"epoch": 1.2489795918367346,
"grad_norm": 2.078125,
"learning_rate": 9.131843213475866e-05,
"loss": 4.8128,
"step": 612
},
{
"epoch": 1.2510204081632654,
"grad_norm": 1.703125,
"learning_rate": 9.128603822481374e-05,
"loss": 4.7524,
"step": 613
},
{
"epoch": 1.2530612244897958,
"grad_norm": 2.09375,
"learning_rate": 9.125364431486881e-05,
"loss": 4.8006,
"step": 614
},
{
"epoch": 1.2551020408163265,
"grad_norm": 1.640625,
"learning_rate": 9.122125040492387e-05,
"loss": 4.8151,
"step": 615
},
{
"epoch": 1.2571428571428571,
"grad_norm": 1.734375,
"learning_rate": 9.118885649497895e-05,
"loss": 4.9447,
"step": 616
},
{
"epoch": 1.2591836734693878,
"grad_norm": 2.28125,
"learning_rate": 9.115646258503402e-05,
"loss": 4.8381,
"step": 617
},
{
"epoch": 1.2612244897959184,
"grad_norm": 1.9140625,
"learning_rate": 9.11240686750891e-05,
"loss": 4.8053,
"step": 618
},
{
"epoch": 1.263265306122449,
"grad_norm": 2.03125,
"learning_rate": 9.109167476514415e-05,
"loss": 4.7734,
"step": 619
},
{
"epoch": 1.2653061224489797,
"grad_norm": 2.1875,
"learning_rate": 9.105928085519923e-05,
"loss": 4.7551,
"step": 620
},
{
"epoch": 1.26734693877551,
"grad_norm": 1.9609375,
"learning_rate": 9.10268869452543e-05,
"loss": 4.9713,
"step": 621
},
{
"epoch": 1.269387755102041,
"grad_norm": 1.7890625,
"learning_rate": 9.099449303530937e-05,
"loss": 4.8043,
"step": 622
},
{
"epoch": 1.2714285714285714,
"grad_norm": 1.8984375,
"learning_rate": 9.096209912536443e-05,
"loss": 4.7243,
"step": 623
},
{
"epoch": 1.273469387755102,
"grad_norm": 1.84375,
"learning_rate": 9.09297052154195e-05,
"loss": 4.8382,
"step": 624
},
{
"epoch": 1.2755102040816326,
"grad_norm": 1.7265625,
"learning_rate": 9.089731130547457e-05,
"loss": 4.9188,
"step": 625
},
{
"epoch": 1.2775510204081633,
"grad_norm": 2.46875,
"learning_rate": 9.086491739552965e-05,
"loss": 5.019,
"step": 626
},
{
"epoch": 1.279591836734694,
"grad_norm": 1.8359375,
"learning_rate": 9.083252348558471e-05,
"loss": 4.693,
"step": 627
},
{
"epoch": 1.2816326530612245,
"grad_norm": 1.984375,
"learning_rate": 9.080012957563978e-05,
"loss": 4.8015,
"step": 628
},
{
"epoch": 1.2836734693877552,
"grad_norm": 1.6875,
"learning_rate": 9.076773566569486e-05,
"loss": 4.8401,
"step": 629
},
{
"epoch": 1.2857142857142856,
"grad_norm": 1.796875,
"learning_rate": 9.073534175574992e-05,
"loss": 4.7409,
"step": 630
},
{
"epoch": 1.2877551020408164,
"grad_norm": 1.890625,
"learning_rate": 9.0702947845805e-05,
"loss": 4.7701,
"step": 631
},
{
"epoch": 1.2897959183673469,
"grad_norm": 1.6796875,
"learning_rate": 9.067055393586006e-05,
"loss": 4.7568,
"step": 632
},
{
"epoch": 1.2918367346938775,
"grad_norm": 2.03125,
"learning_rate": 9.063816002591514e-05,
"loss": 4.7754,
"step": 633
},
{
"epoch": 1.2938775510204081,
"grad_norm": 1.890625,
"learning_rate": 9.06057661159702e-05,
"loss": 4.8189,
"step": 634
},
{
"epoch": 1.2959183673469388,
"grad_norm": 2.9375,
"learning_rate": 9.057337220602528e-05,
"loss": 4.9332,
"step": 635
},
{
"epoch": 1.2979591836734694,
"grad_norm": 2.03125,
"learning_rate": 9.054097829608033e-05,
"loss": 4.8598,
"step": 636
},
{
"epoch": 1.3,
"grad_norm": 2.34375,
"learning_rate": 9.050858438613541e-05,
"loss": 4.745,
"step": 637
},
{
"epoch": 1.3020408163265307,
"grad_norm": 2.25,
"learning_rate": 9.047619047619048e-05,
"loss": 4.7094,
"step": 638
},
{
"epoch": 1.304081632653061,
"grad_norm": 2.171875,
"learning_rate": 9.044379656624556e-05,
"loss": 4.8985,
"step": 639
},
{
"epoch": 1.306122448979592,
"grad_norm": 2.265625,
"learning_rate": 9.041140265630061e-05,
"loss": 4.7035,
"step": 640
},
{
"epoch": 1.3081632653061224,
"grad_norm": 1.7890625,
"learning_rate": 9.037900874635569e-05,
"loss": 4.9557,
"step": 641
},
{
"epoch": 1.310204081632653,
"grad_norm": 1.9375,
"learning_rate": 9.034661483641075e-05,
"loss": 4.7488,
"step": 642
},
{
"epoch": 1.3122448979591836,
"grad_norm": 2.09375,
"learning_rate": 9.031422092646583e-05,
"loss": 4.905,
"step": 643
},
{
"epoch": 1.3142857142857143,
"grad_norm": 1.703125,
"learning_rate": 9.02818270165209e-05,
"loss": 4.8654,
"step": 644
},
{
"epoch": 1.316326530612245,
"grad_norm": 1.90625,
"learning_rate": 9.024943310657596e-05,
"loss": 4.7871,
"step": 645
},
{
"epoch": 1.3183673469387756,
"grad_norm": 1.734375,
"learning_rate": 9.021703919663104e-05,
"loss": 4.7715,
"step": 646
},
{
"epoch": 1.3204081632653062,
"grad_norm": 2.421875,
"learning_rate": 9.018464528668611e-05,
"loss": 4.7566,
"step": 647
},
{
"epoch": 1.3224489795918366,
"grad_norm": 1.671875,
"learning_rate": 9.015225137674119e-05,
"loss": 4.8316,
"step": 648
},
{
"epoch": 1.3244897959183675,
"grad_norm": 1.9375,
"learning_rate": 9.011985746679624e-05,
"loss": 4.7074,
"step": 649
},
{
"epoch": 1.3265306122448979,
"grad_norm": 2.015625,
"learning_rate": 9.008746355685132e-05,
"loss": 4.8533,
"step": 650
},
{
"epoch": 1.3285714285714285,
"grad_norm": 1.9375,
"learning_rate": 9.005506964690638e-05,
"loss": 4.8399,
"step": 651
},
{
"epoch": 1.3306122448979592,
"grad_norm": 2.234375,
"learning_rate": 9.002267573696146e-05,
"loss": 4.8714,
"step": 652
},
{
"epoch": 1.3326530612244898,
"grad_norm": 1.8046875,
"learning_rate": 8.999028182701651e-05,
"loss": 4.7215,
"step": 653
},
{
"epoch": 1.3346938775510204,
"grad_norm": 2.703125,
"learning_rate": 8.99578879170716e-05,
"loss": 4.7335,
"step": 654
},
{
"epoch": 1.336734693877551,
"grad_norm": 2.15625,
"learning_rate": 8.992549400712666e-05,
"loss": 4.7722,
"step": 655
},
{
"epoch": 1.3387755102040817,
"grad_norm": 2.21875,
"learning_rate": 8.989310009718174e-05,
"loss": 4.748,
"step": 656
},
{
"epoch": 1.3408163265306121,
"grad_norm": 2.234375,
"learning_rate": 8.98607061872368e-05,
"loss": 4.8914,
"step": 657
},
{
"epoch": 1.342857142857143,
"grad_norm": 2.078125,
"learning_rate": 8.982831227729187e-05,
"loss": 4.78,
"step": 658
},
{
"epoch": 1.3448979591836734,
"grad_norm": 2.140625,
"learning_rate": 8.979591836734695e-05,
"loss": 4.848,
"step": 659
},
{
"epoch": 1.346938775510204,
"grad_norm": 1.6953125,
"learning_rate": 8.976352445740201e-05,
"loss": 4.8411,
"step": 660
},
{
"epoch": 1.3489795918367347,
"grad_norm": 1.84375,
"learning_rate": 8.97311305474571e-05,
"loss": 4.7888,
"step": 661
},
{
"epoch": 1.3510204081632653,
"grad_norm": 1.828125,
"learning_rate": 8.969873663751215e-05,
"loss": 4.6929,
"step": 662
},
{
"epoch": 1.353061224489796,
"grad_norm": 1.953125,
"learning_rate": 8.966634272756722e-05,
"loss": 4.6919,
"step": 663
},
{
"epoch": 1.3551020408163266,
"grad_norm": 2.390625,
"learning_rate": 8.963394881762229e-05,
"loss": 4.909,
"step": 664
},
{
"epoch": 1.3571428571428572,
"grad_norm": 2.296875,
"learning_rate": 8.960155490767737e-05,
"loss": 4.8881,
"step": 665
},
{
"epoch": 1.3591836734693876,
"grad_norm": 2.203125,
"learning_rate": 8.956916099773242e-05,
"loss": 4.7653,
"step": 666
},
{
"epoch": 1.3612244897959185,
"grad_norm": 1.9765625,
"learning_rate": 8.95367670877875e-05,
"loss": 4.8264,
"step": 667
},
{
"epoch": 1.363265306122449,
"grad_norm": 1.7265625,
"learning_rate": 8.950437317784257e-05,
"loss": 4.7398,
"step": 668
},
{
"epoch": 1.3653061224489795,
"grad_norm": 2.03125,
"learning_rate": 8.947197926789765e-05,
"loss": 4.7321,
"step": 669
},
{
"epoch": 1.3673469387755102,
"grad_norm": 1.6796875,
"learning_rate": 8.943958535795271e-05,
"loss": 4.5985,
"step": 670
},
{
"epoch": 1.3693877551020408,
"grad_norm": 1.9375,
"learning_rate": 8.940719144800778e-05,
"loss": 4.7438,
"step": 671
},
{
"epoch": 1.3714285714285714,
"grad_norm": 1.6171875,
"learning_rate": 8.937479753806286e-05,
"loss": 4.8135,
"step": 672
},
{
"epoch": 1.373469387755102,
"grad_norm": 2.328125,
"learning_rate": 8.934240362811792e-05,
"loss": 4.696,
"step": 673
},
{
"epoch": 1.3755102040816327,
"grad_norm": 1.8359375,
"learning_rate": 8.931000971817299e-05,
"loss": 4.8524,
"step": 674
},
{
"epoch": 1.3775510204081631,
"grad_norm": 2.15625,
"learning_rate": 8.927761580822805e-05,
"loss": 4.7665,
"step": 675
},
{
"epoch": 1.379591836734694,
"grad_norm": 1.9140625,
"learning_rate": 8.924522189828313e-05,
"loss": 4.8345,
"step": 676
},
{
"epoch": 1.3816326530612244,
"grad_norm": 2.4375,
"learning_rate": 8.92128279883382e-05,
"loss": 4.7603,
"step": 677
},
{
"epoch": 1.383673469387755,
"grad_norm": 2.1875,
"learning_rate": 8.918043407839328e-05,
"loss": 4.8339,
"step": 678
},
{
"epoch": 1.3857142857142857,
"grad_norm": 1.8515625,
"learning_rate": 8.914804016844833e-05,
"loss": 4.7435,
"step": 679
},
{
"epoch": 1.3877551020408163,
"grad_norm": 2.125,
"learning_rate": 8.911564625850341e-05,
"loss": 4.8046,
"step": 680
},
{
"epoch": 1.389795918367347,
"grad_norm": 2.15625,
"learning_rate": 8.908325234855847e-05,
"loss": 4.7758,
"step": 681
},
{
"epoch": 1.3918367346938776,
"grad_norm": 1.6640625,
"learning_rate": 8.905085843861355e-05,
"loss": 4.6746,
"step": 682
},
{
"epoch": 1.3938775510204082,
"grad_norm": 2.046875,
"learning_rate": 8.90184645286686e-05,
"loss": 4.9647,
"step": 683
},
{
"epoch": 1.3959183673469386,
"grad_norm": 1.9296875,
"learning_rate": 8.898607061872368e-05,
"loss": 4.9418,
"step": 684
},
{
"epoch": 1.3979591836734695,
"grad_norm": 2.203125,
"learning_rate": 8.895367670877875e-05,
"loss": 4.8851,
"step": 685
},
{
"epoch": 1.4,
"grad_norm": 2.03125,
"learning_rate": 8.892128279883383e-05,
"loss": 4.7804,
"step": 686
},
{
"epoch": 1.4020408163265305,
"grad_norm": 2.015625,
"learning_rate": 8.888888888888889e-05,
"loss": 4.7336,
"step": 687
},
{
"epoch": 1.4040816326530612,
"grad_norm": 1.8125,
"learning_rate": 8.885649497894396e-05,
"loss": 4.7454,
"step": 688
},
{
"epoch": 1.4061224489795918,
"grad_norm": 1.9375,
"learning_rate": 8.882410106899904e-05,
"loss": 4.6825,
"step": 689
},
{
"epoch": 1.4081632653061225,
"grad_norm": 1.796875,
"learning_rate": 8.87917071590541e-05,
"loss": 4.72,
"step": 690
},
{
"epoch": 1.410204081632653,
"grad_norm": 2.125,
"learning_rate": 8.875931324910918e-05,
"loss": 4.8235,
"step": 691
},
{
"epoch": 1.4122448979591837,
"grad_norm": 2.0,
"learning_rate": 8.872691933916423e-05,
"loss": 4.6293,
"step": 692
},
{
"epoch": 1.4142857142857144,
"grad_norm": 2.046875,
"learning_rate": 8.869452542921931e-05,
"loss": 4.8867,
"step": 693
},
{
"epoch": 1.416326530612245,
"grad_norm": 2.0,
"learning_rate": 8.866213151927438e-05,
"loss": 4.7234,
"step": 694
},
{
"epoch": 1.4183673469387754,
"grad_norm": 1.6796875,
"learning_rate": 8.862973760932946e-05,
"loss": 4.7312,
"step": 695
},
{
"epoch": 1.420408163265306,
"grad_norm": 1.9296875,
"learning_rate": 8.859734369938451e-05,
"loss": 4.6994,
"step": 696
},
{
"epoch": 1.4224489795918367,
"grad_norm": 1.6875,
"learning_rate": 8.856494978943959e-05,
"loss": 4.7038,
"step": 697
},
{
"epoch": 1.4244897959183673,
"grad_norm": 1.84375,
"learning_rate": 8.853255587949466e-05,
"loss": 4.8444,
"step": 698
},
{
"epoch": 1.426530612244898,
"grad_norm": 1.7421875,
"learning_rate": 8.850016196954973e-05,
"loss": 4.7437,
"step": 699
},
{
"epoch": 1.4285714285714286,
"grad_norm": 1.6796875,
"learning_rate": 8.84677680596048e-05,
"loss": 4.6036,
"step": 700
},
{
"epoch": 1.4306122448979592,
"grad_norm": 2.15625,
"learning_rate": 8.843537414965987e-05,
"loss": 4.7024,
"step": 701
},
{
"epoch": 1.4326530612244899,
"grad_norm": 1.8125,
"learning_rate": 8.840298023971494e-05,
"loss": 4.8155,
"step": 702
},
{
"epoch": 1.4346938775510205,
"grad_norm": 2.4375,
"learning_rate": 8.837058632977001e-05,
"loss": 4.7073,
"step": 703
},
{
"epoch": 1.436734693877551,
"grad_norm": 1.90625,
"learning_rate": 8.833819241982508e-05,
"loss": 4.6878,
"step": 704
},
{
"epoch": 1.4387755102040816,
"grad_norm": 2.03125,
"learning_rate": 8.830579850988014e-05,
"loss": 4.6892,
"step": 705
},
{
"epoch": 1.4408163265306122,
"grad_norm": 2.140625,
"learning_rate": 8.827340459993522e-05,
"loss": 4.7653,
"step": 706
},
{
"epoch": 1.4428571428571428,
"grad_norm": 2.1875,
"learning_rate": 8.824101068999029e-05,
"loss": 4.7781,
"step": 707
},
{
"epoch": 1.4448979591836735,
"grad_norm": 1.8984375,
"learning_rate": 8.820861678004537e-05,
"loss": 4.695,
"step": 708
},
{
"epoch": 1.4469387755102041,
"grad_norm": 1.7890625,
"learning_rate": 8.817622287010042e-05,
"loss": 4.7224,
"step": 709
},
{
"epoch": 1.4489795918367347,
"grad_norm": 1.671875,
"learning_rate": 8.81438289601555e-05,
"loss": 4.7639,
"step": 710
},
{
"epoch": 1.4510204081632654,
"grad_norm": 1.8125,
"learning_rate": 8.811143505021056e-05,
"loss": 4.5957,
"step": 711
},
{
"epoch": 1.453061224489796,
"grad_norm": 1.78125,
"learning_rate": 8.807904114026564e-05,
"loss": 4.8636,
"step": 712
},
{
"epoch": 1.4551020408163264,
"grad_norm": 1.8828125,
"learning_rate": 8.80466472303207e-05,
"loss": 4.5423,
"step": 713
},
{
"epoch": 1.457142857142857,
"grad_norm": 1.8125,
"learning_rate": 8.801425332037577e-05,
"loss": 4.6605,
"step": 714
},
{
"epoch": 1.4591836734693877,
"grad_norm": 1.796875,
"learning_rate": 8.798185941043085e-05,
"loss": 4.6972,
"step": 715
},
{
"epoch": 1.4612244897959183,
"grad_norm": 1.78125,
"learning_rate": 8.794946550048592e-05,
"loss": 4.6256,
"step": 716
},
{
"epoch": 1.463265306122449,
"grad_norm": 1.875,
"learning_rate": 8.791707159054098e-05,
"loss": 4.7475,
"step": 717
},
{
"epoch": 1.4653061224489796,
"grad_norm": 1.9921875,
"learning_rate": 8.788467768059605e-05,
"loss": 4.7042,
"step": 718
},
{
"epoch": 1.4673469387755103,
"grad_norm": 2.015625,
"learning_rate": 8.785228377065113e-05,
"loss": 4.8132,
"step": 719
},
{
"epoch": 1.469387755102041,
"grad_norm": 1.953125,
"learning_rate": 8.781988986070619e-05,
"loss": 4.8131,
"step": 720
},
{
"epoch": 1.4714285714285715,
"grad_norm": 1.8046875,
"learning_rate": 8.778749595076126e-05,
"loss": 4.6683,
"step": 721
},
{
"epoch": 1.473469387755102,
"grad_norm": 2.015625,
"learning_rate": 8.775510204081632e-05,
"loss": 4.8674,
"step": 722
},
{
"epoch": 1.4755102040816326,
"grad_norm": 1.96875,
"learning_rate": 8.77227081308714e-05,
"loss": 4.7787,
"step": 723
},
{
"epoch": 1.4775510204081632,
"grad_norm": 1.8515625,
"learning_rate": 8.769031422092647e-05,
"loss": 4.7076,
"step": 724
},
{
"epoch": 1.4795918367346939,
"grad_norm": 1.75,
"learning_rate": 8.765792031098155e-05,
"loss": 4.6402,
"step": 725
},
{
"epoch": 1.4816326530612245,
"grad_norm": 1.9375,
"learning_rate": 8.76255264010366e-05,
"loss": 4.6897,
"step": 726
},
{
"epoch": 1.4836734693877551,
"grad_norm": 1.828125,
"learning_rate": 8.759313249109168e-05,
"loss": 4.7182,
"step": 727
},
{
"epoch": 1.4857142857142858,
"grad_norm": 1.9609375,
"learning_rate": 8.756073858114674e-05,
"loss": 4.7372,
"step": 728
},
{
"epoch": 1.4877551020408164,
"grad_norm": 1.9609375,
"learning_rate": 8.752834467120182e-05,
"loss": 4.73,
"step": 729
},
{
"epoch": 1.489795918367347,
"grad_norm": 1.9921875,
"learning_rate": 8.749595076125689e-05,
"loss": 4.6488,
"step": 730
},
{
"epoch": 1.4918367346938775,
"grad_norm": 2.125,
"learning_rate": 8.746355685131195e-05,
"loss": 4.6862,
"step": 731
},
{
"epoch": 1.493877551020408,
"grad_norm": 2.171875,
"learning_rate": 8.743116294136703e-05,
"loss": 4.7229,
"step": 732
},
{
"epoch": 1.4959183673469387,
"grad_norm": 2.140625,
"learning_rate": 8.73987690314221e-05,
"loss": 4.7505,
"step": 733
},
{
"epoch": 1.4979591836734694,
"grad_norm": 2.09375,
"learning_rate": 8.736637512147716e-05,
"loss": 4.7485,
"step": 734
},
{
"epoch": 1.5,
"grad_norm": 1.8828125,
"learning_rate": 8.733398121153223e-05,
"loss": 4.6776,
"step": 735
},
{
"epoch": 1.5020408163265306,
"grad_norm": 2.0,
"learning_rate": 8.730158730158731e-05,
"loss": 4.6363,
"step": 736
},
{
"epoch": 1.5040816326530613,
"grad_norm": 1.875,
"learning_rate": 8.726919339164238e-05,
"loss": 4.7541,
"step": 737
},
{
"epoch": 1.5061224489795917,
"grad_norm": 1.71875,
"learning_rate": 8.723679948169744e-05,
"loss": 4.6463,
"step": 738
},
{
"epoch": 1.5081632653061225,
"grad_norm": 1.7890625,
"learning_rate": 8.72044055717525e-05,
"loss": 4.7848,
"step": 739
},
{
"epoch": 1.510204081632653,
"grad_norm": 1.9296875,
"learning_rate": 8.717201166180759e-05,
"loss": 4.703,
"step": 740
},
{
"epoch": 1.5122448979591838,
"grad_norm": 2.046875,
"learning_rate": 8.713961775186265e-05,
"loss": 4.7346,
"step": 741
},
{
"epoch": 1.5142857142857142,
"grad_norm": 1.9609375,
"learning_rate": 8.710722384191773e-05,
"loss": 4.7878,
"step": 742
},
{
"epoch": 1.5163265306122449,
"grad_norm": 2.03125,
"learning_rate": 8.70748299319728e-05,
"loss": 4.7043,
"step": 743
},
{
"epoch": 1.5183673469387755,
"grad_norm": 1.765625,
"learning_rate": 8.704243602202786e-05,
"loss": 4.6572,
"step": 744
},
{
"epoch": 1.5204081632653061,
"grad_norm": 1.8984375,
"learning_rate": 8.701004211208294e-05,
"loss": 4.6817,
"step": 745
},
{
"epoch": 1.5224489795918368,
"grad_norm": 1.953125,
"learning_rate": 8.6977648202138e-05,
"loss": 4.7208,
"step": 746
},
{
"epoch": 1.5244897959183672,
"grad_norm": 1.7421875,
"learning_rate": 8.694525429219307e-05,
"loss": 4.6026,
"step": 747
},
{
"epoch": 1.526530612244898,
"grad_norm": 2.140625,
"learning_rate": 8.691286038224814e-05,
"loss": 4.8206,
"step": 748
},
{
"epoch": 1.5285714285714285,
"grad_norm": 1.9296875,
"learning_rate": 8.688046647230322e-05,
"loss": 4.6129,
"step": 749
},
{
"epoch": 1.5306122448979593,
"grad_norm": 1.671875,
"learning_rate": 8.684807256235828e-05,
"loss": 4.586,
"step": 750
},
{
"epoch": 1.5326530612244897,
"grad_norm": 2.515625,
"learning_rate": 8.681567865241335e-05,
"loss": 4.721,
"step": 751
},
{
"epoch": 1.5346938775510204,
"grad_norm": 2.0625,
"learning_rate": 8.678328474246841e-05,
"loss": 4.782,
"step": 752
},
{
"epoch": 1.536734693877551,
"grad_norm": 2.015625,
"learning_rate": 8.675089083252349e-05,
"loss": 4.6907,
"step": 753
},
{
"epoch": 1.5387755102040817,
"grad_norm": 2.140625,
"learning_rate": 8.671849692257856e-05,
"loss": 4.6905,
"step": 754
},
{
"epoch": 1.5408163265306123,
"grad_norm": 1.90625,
"learning_rate": 8.668610301263362e-05,
"loss": 4.6976,
"step": 755
},
{
"epoch": 1.5428571428571427,
"grad_norm": 1.828125,
"learning_rate": 8.66537091026887e-05,
"loss": 4.6916,
"step": 756
},
{
"epoch": 1.5448979591836736,
"grad_norm": 1.6875,
"learning_rate": 8.662131519274377e-05,
"loss": 4.7449,
"step": 757
},
{
"epoch": 1.546938775510204,
"grad_norm": 1.890625,
"learning_rate": 8.658892128279885e-05,
"loss": 4.7492,
"step": 758
},
{
"epoch": 1.5489795918367348,
"grad_norm": 2.15625,
"learning_rate": 8.655652737285391e-05,
"loss": 4.7508,
"step": 759
},
{
"epoch": 1.5510204081632653,
"grad_norm": 1.546875,
"learning_rate": 8.652413346290898e-05,
"loss": 4.6283,
"step": 760
},
{
"epoch": 1.5530612244897959,
"grad_norm": 2.15625,
"learning_rate": 8.649173955296404e-05,
"loss": 4.6828,
"step": 761
},
{
"epoch": 1.5551020408163265,
"grad_norm": 1.5703125,
"learning_rate": 8.645934564301912e-05,
"loss": 4.6093,
"step": 762
},
{
"epoch": 1.5571428571428572,
"grad_norm": 2.265625,
"learning_rate": 8.642695173307419e-05,
"loss": 4.7238,
"step": 763
},
{
"epoch": 1.5591836734693878,
"grad_norm": 1.625,
"learning_rate": 8.639455782312925e-05,
"loss": 4.777,
"step": 764
},
{
"epoch": 1.5612244897959182,
"grad_norm": 2.171875,
"learning_rate": 8.636216391318432e-05,
"loss": 4.7003,
"step": 765
},
{
"epoch": 1.563265306122449,
"grad_norm": 2.125,
"learning_rate": 8.63297700032394e-05,
"loss": 4.6712,
"step": 766
},
{
"epoch": 1.5653061224489795,
"grad_norm": 2.125,
"learning_rate": 8.629737609329446e-05,
"loss": 4.6514,
"step": 767
},
{
"epoch": 1.5673469387755103,
"grad_norm": 2.0625,
"learning_rate": 8.626498218334953e-05,
"loss": 4.7182,
"step": 768
},
{
"epoch": 1.5693877551020408,
"grad_norm": 2.21875,
"learning_rate": 8.62325882734046e-05,
"loss": 4.6265,
"step": 769
},
{
"epoch": 1.5714285714285714,
"grad_norm": 2.140625,
"learning_rate": 8.620019436345967e-05,
"loss": 4.6955,
"step": 770
},
{
"epoch": 1.573469387755102,
"grad_norm": 2.109375,
"learning_rate": 8.616780045351474e-05,
"loss": 4.774,
"step": 771
},
{
"epoch": 1.5755102040816327,
"grad_norm": 2.140625,
"learning_rate": 8.61354065435698e-05,
"loss": 4.6826,
"step": 772
},
{
"epoch": 1.5775510204081633,
"grad_norm": 1.6328125,
"learning_rate": 8.610301263362489e-05,
"loss": 4.6184,
"step": 773
},
{
"epoch": 1.5795918367346937,
"grad_norm": 2.15625,
"learning_rate": 8.607061872367995e-05,
"loss": 4.6233,
"step": 774
},
{
"epoch": 1.5816326530612246,
"grad_norm": 2.0,
"learning_rate": 8.603822481373503e-05,
"loss": 4.6778,
"step": 775
},
{
"epoch": 1.583673469387755,
"grad_norm": 1.8984375,
"learning_rate": 8.60058309037901e-05,
"loss": 4.7039,
"step": 776
},
{
"epoch": 1.5857142857142859,
"grad_norm": 2.1875,
"learning_rate": 8.597343699384516e-05,
"loss": 4.7812,
"step": 777
},
{
"epoch": 1.5877551020408163,
"grad_norm": 1.703125,
"learning_rate": 8.594104308390023e-05,
"loss": 4.7204,
"step": 778
},
{
"epoch": 1.589795918367347,
"grad_norm": 1.90625,
"learning_rate": 8.59086491739553e-05,
"loss": 4.5717,
"step": 779
},
{
"epoch": 1.5918367346938775,
"grad_norm": 1.796875,
"learning_rate": 8.587625526401037e-05,
"loss": 4.6323,
"step": 780
},
{
"epoch": 1.5938775510204082,
"grad_norm": 1.6171875,
"learning_rate": 8.584386135406544e-05,
"loss": 4.6432,
"step": 781
},
{
"epoch": 1.5959183673469388,
"grad_norm": 1.9296875,
"learning_rate": 8.58114674441205e-05,
"loss": 4.6226,
"step": 782
},
{
"epoch": 1.5979591836734692,
"grad_norm": 1.7109375,
"learning_rate": 8.577907353417558e-05,
"loss": 4.5679,
"step": 783
},
{
"epoch": 1.6,
"grad_norm": 1.578125,
"learning_rate": 8.574667962423065e-05,
"loss": 4.6916,
"step": 784
},
{
"epoch": 1.6020408163265305,
"grad_norm": 1.84375,
"learning_rate": 8.571428571428571e-05,
"loss": 4.732,
"step": 785
},
{
"epoch": 1.6040816326530614,
"grad_norm": 1.8984375,
"learning_rate": 8.568189180434079e-05,
"loss": 4.6267,
"step": 786
},
{
"epoch": 1.6061224489795918,
"grad_norm": 2.0,
"learning_rate": 8.564949789439586e-05,
"loss": 4.6426,
"step": 787
},
{
"epoch": 1.6081632653061224,
"grad_norm": 1.9453125,
"learning_rate": 8.561710398445094e-05,
"loss": 4.5167,
"step": 788
},
{
"epoch": 1.610204081632653,
"grad_norm": 2.078125,
"learning_rate": 8.558471007450599e-05,
"loss": 4.6252,
"step": 789
},
{
"epoch": 1.6122448979591837,
"grad_norm": 1.9765625,
"learning_rate": 8.555231616456107e-05,
"loss": 4.7217,
"step": 790
},
{
"epoch": 1.6142857142857143,
"grad_norm": 1.78125,
"learning_rate": 8.551992225461613e-05,
"loss": 4.7574,
"step": 791
},
{
"epoch": 1.6163265306122447,
"grad_norm": 1.90625,
"learning_rate": 8.548752834467121e-05,
"loss": 4.6235,
"step": 792
},
{
"epoch": 1.6183673469387756,
"grad_norm": 1.8515625,
"learning_rate": 8.545513443472628e-05,
"loss": 4.5076,
"step": 793
},
{
"epoch": 1.620408163265306,
"grad_norm": 1.75,
"learning_rate": 8.542274052478134e-05,
"loss": 4.6215,
"step": 794
},
{
"epoch": 1.6224489795918369,
"grad_norm": 1.53125,
"learning_rate": 8.539034661483641e-05,
"loss": 4.7553,
"step": 795
},
{
"epoch": 1.6244897959183673,
"grad_norm": 1.9453125,
"learning_rate": 8.535795270489149e-05,
"loss": 4.6397,
"step": 796
},
{
"epoch": 1.626530612244898,
"grad_norm": 2.390625,
"learning_rate": 8.532555879494655e-05,
"loss": 4.6758,
"step": 797
},
{
"epoch": 1.6285714285714286,
"grad_norm": 1.65625,
"learning_rate": 8.529316488500162e-05,
"loss": 4.7122,
"step": 798
},
{
"epoch": 1.6306122448979592,
"grad_norm": 1.859375,
"learning_rate": 8.52607709750567e-05,
"loss": 4.6288,
"step": 799
},
{
"epoch": 1.6326530612244898,
"grad_norm": 1.9609375,
"learning_rate": 8.522837706511176e-05,
"loss": 4.6764,
"step": 800
},
{
"epoch": 1.6346938775510202,
"grad_norm": 1.5859375,
"learning_rate": 8.519598315516684e-05,
"loss": 4.7576,
"step": 801
},
{
"epoch": 1.636734693877551,
"grad_norm": 1.96875,
"learning_rate": 8.51635892452219e-05,
"loss": 4.595,
"step": 802
},
{
"epoch": 1.6387755102040815,
"grad_norm": 1.7890625,
"learning_rate": 8.513119533527697e-05,
"loss": 4.5794,
"step": 803
},
{
"epoch": 1.6408163265306124,
"grad_norm": 1.859375,
"learning_rate": 8.509880142533204e-05,
"loss": 4.5352,
"step": 804
},
{
"epoch": 1.6428571428571428,
"grad_norm": 2.1875,
"learning_rate": 8.506640751538712e-05,
"loss": 4.6246,
"step": 805
},
{
"epoch": 1.6448979591836734,
"grad_norm": 1.953125,
"learning_rate": 8.503401360544217e-05,
"loss": 4.545,
"step": 806
},
{
"epoch": 1.646938775510204,
"grad_norm": 2.140625,
"learning_rate": 8.500161969549725e-05,
"loss": 4.5247,
"step": 807
},
{
"epoch": 1.6489795918367347,
"grad_norm": 1.8359375,
"learning_rate": 8.496922578555232e-05,
"loss": 4.6666,
"step": 808
},
{
"epoch": 1.6510204081632653,
"grad_norm": 1.6484375,
"learning_rate": 8.49368318756074e-05,
"loss": 4.7399,
"step": 809
},
{
"epoch": 1.6530612244897958,
"grad_norm": 1.8828125,
"learning_rate": 8.490443796566246e-05,
"loss": 4.6531,
"step": 810
},
{
"epoch": 1.6551020408163266,
"grad_norm": 1.7109375,
"learning_rate": 8.487204405571753e-05,
"loss": 4.6083,
"step": 811
},
{
"epoch": 1.657142857142857,
"grad_norm": 2.046875,
"learning_rate": 8.483965014577259e-05,
"loss": 4.6065,
"step": 812
},
{
"epoch": 1.6591836734693879,
"grad_norm": 2.15625,
"learning_rate": 8.480725623582767e-05,
"loss": 4.6641,
"step": 813
},
{
"epoch": 1.6612244897959183,
"grad_norm": 1.5078125,
"learning_rate": 8.477486232588274e-05,
"loss": 4.6133,
"step": 814
},
{
"epoch": 1.663265306122449,
"grad_norm": 1.890625,
"learning_rate": 8.47424684159378e-05,
"loss": 4.8044,
"step": 815
},
{
"epoch": 1.6653061224489796,
"grad_norm": 1.625,
"learning_rate": 8.471007450599288e-05,
"loss": 4.7161,
"step": 816
},
{
"epoch": 1.6673469387755102,
"grad_norm": 1.859375,
"learning_rate": 8.467768059604795e-05,
"loss": 4.5907,
"step": 817
},
{
"epoch": 1.6693877551020408,
"grad_norm": 1.9609375,
"learning_rate": 8.464528668610303e-05,
"loss": 4.656,
"step": 818
},
{
"epoch": 1.6714285714285713,
"grad_norm": 1.5546875,
"learning_rate": 8.461289277615808e-05,
"loss": 4.6804,
"step": 819
},
{
"epoch": 1.6734693877551021,
"grad_norm": 2.046875,
"learning_rate": 8.458049886621316e-05,
"loss": 4.5524,
"step": 820
},
{
"epoch": 1.6755102040816325,
"grad_norm": 1.640625,
"learning_rate": 8.454810495626822e-05,
"loss": 4.6481,
"step": 821
},
{
"epoch": 1.6775510204081634,
"grad_norm": 1.75,
"learning_rate": 8.45157110463233e-05,
"loss": 4.6662,
"step": 822
},
{
"epoch": 1.6795918367346938,
"grad_norm": 1.6015625,
"learning_rate": 8.448331713637837e-05,
"loss": 4.6497,
"step": 823
},
{
"epoch": 1.6816326530612244,
"grad_norm": 1.8125,
"learning_rate": 8.445092322643343e-05,
"loss": 4.6387,
"step": 824
},
{
"epoch": 1.683673469387755,
"grad_norm": 1.453125,
"learning_rate": 8.44185293164885e-05,
"loss": 4.5695,
"step": 825
},
{
"epoch": 1.6857142857142857,
"grad_norm": 1.6171875,
"learning_rate": 8.438613540654358e-05,
"loss": 4.5346,
"step": 826
},
{
"epoch": 1.6877551020408164,
"grad_norm": 1.78125,
"learning_rate": 8.435374149659864e-05,
"loss": 4.5943,
"step": 827
},
{
"epoch": 1.689795918367347,
"grad_norm": 1.7578125,
"learning_rate": 8.432134758665371e-05,
"loss": 4.5762,
"step": 828
},
{
"epoch": 1.6918367346938776,
"grad_norm": 1.375,
"learning_rate": 8.428895367670879e-05,
"loss": 4.5924,
"step": 829
},
{
"epoch": 1.693877551020408,
"grad_norm": 1.734375,
"learning_rate": 8.425655976676385e-05,
"loss": 4.584,
"step": 830
},
{
"epoch": 1.695918367346939,
"grad_norm": 1.4296875,
"learning_rate": 8.422416585681893e-05,
"loss": 4.5762,
"step": 831
},
{
"epoch": 1.6979591836734693,
"grad_norm": 1.7890625,
"learning_rate": 8.419177194687398e-05,
"loss": 4.6029,
"step": 832
},
{
"epoch": 1.7,
"grad_norm": 1.6953125,
"learning_rate": 8.415937803692906e-05,
"loss": 4.4798,
"step": 833
},
{
"epoch": 1.7020408163265306,
"grad_norm": 1.4765625,
"learning_rate": 8.412698412698413e-05,
"loss": 4.5757,
"step": 834
},
{
"epoch": 1.7040816326530612,
"grad_norm": 1.53125,
"learning_rate": 8.409459021703921e-05,
"loss": 4.6878,
"step": 835
},
{
"epoch": 1.7061224489795919,
"grad_norm": 1.578125,
"learning_rate": 8.406219630709426e-05,
"loss": 4.6447,
"step": 836
},
{
"epoch": 1.7081632653061225,
"grad_norm": 1.7421875,
"learning_rate": 8.402980239714934e-05,
"loss": 4.5543,
"step": 837
},
{
"epoch": 1.7102040816326531,
"grad_norm": 1.5,
"learning_rate": 8.39974084872044e-05,
"loss": 4.6474,
"step": 838
},
{
"epoch": 1.7122448979591836,
"grad_norm": 1.7890625,
"learning_rate": 8.396501457725948e-05,
"loss": 4.7255,
"step": 839
},
{
"epoch": 1.7142857142857144,
"grad_norm": 1.8828125,
"learning_rate": 8.393262066731455e-05,
"loss": 4.5725,
"step": 840
},
{
"epoch": 1.7163265306122448,
"grad_norm": 1.8125,
"learning_rate": 8.390022675736962e-05,
"loss": 4.6,
"step": 841
},
{
"epoch": 1.7183673469387755,
"grad_norm": 2.046875,
"learning_rate": 8.38678328474247e-05,
"loss": 4.6976,
"step": 842
},
{
"epoch": 1.720408163265306,
"grad_norm": 1.734375,
"learning_rate": 8.383543893747976e-05,
"loss": 4.6203,
"step": 843
},
{
"epoch": 1.7224489795918367,
"grad_norm": 1.75,
"learning_rate": 8.380304502753483e-05,
"loss": 4.6933,
"step": 844
},
{
"epoch": 1.7244897959183674,
"grad_norm": 1.90625,
"learning_rate": 8.377065111758989e-05,
"loss": 4.6168,
"step": 845
},
{
"epoch": 1.726530612244898,
"grad_norm": 1.7109375,
"learning_rate": 8.373825720764497e-05,
"loss": 4.6102,
"step": 846
},
{
"epoch": 1.7285714285714286,
"grad_norm": 1.8828125,
"learning_rate": 8.370586329770004e-05,
"loss": 4.5181,
"step": 847
},
{
"epoch": 1.730612244897959,
"grad_norm": 1.7265625,
"learning_rate": 8.367346938775511e-05,
"loss": 4.6109,
"step": 848
},
{
"epoch": 1.73265306122449,
"grad_norm": 1.765625,
"learning_rate": 8.364107547781017e-05,
"loss": 4.5518,
"step": 849
},
{
"epoch": 1.7346938775510203,
"grad_norm": 1.9296875,
"learning_rate": 8.360868156786525e-05,
"loss": 4.7668,
"step": 850
},
{
"epoch": 1.736734693877551,
"grad_norm": 1.6640625,
"learning_rate": 8.357628765792031e-05,
"loss": 4.6253,
"step": 851
},
{
"epoch": 1.7387755102040816,
"grad_norm": 1.59375,
"learning_rate": 8.354389374797539e-05,
"loss": 4.6144,
"step": 852
},
{
"epoch": 1.7408163265306122,
"grad_norm": 1.6796875,
"learning_rate": 8.351149983803044e-05,
"loss": 4.5956,
"step": 853
},
{
"epoch": 1.7428571428571429,
"grad_norm": 1.7421875,
"learning_rate": 8.347910592808552e-05,
"loss": 4.5898,
"step": 854
},
{
"epoch": 1.7448979591836735,
"grad_norm": 1.7734375,
"learning_rate": 8.344671201814059e-05,
"loss": 4.4947,
"step": 855
},
{
"epoch": 1.7469387755102042,
"grad_norm": 1.828125,
"learning_rate": 8.341431810819567e-05,
"loss": 4.7078,
"step": 856
},
{
"epoch": 1.7489795918367346,
"grad_norm": 1.734375,
"learning_rate": 8.338192419825073e-05,
"loss": 4.772,
"step": 857
},
{
"epoch": 1.7510204081632654,
"grad_norm": 1.5859375,
"learning_rate": 8.33495302883058e-05,
"loss": 4.5017,
"step": 858
},
{
"epoch": 1.7530612244897958,
"grad_norm": 1.65625,
"learning_rate": 8.331713637836088e-05,
"loss": 4.7137,
"step": 859
},
{
"epoch": 1.7551020408163265,
"grad_norm": 1.5078125,
"learning_rate": 8.328474246841594e-05,
"loss": 4.5628,
"step": 860
},
{
"epoch": 1.7571428571428571,
"grad_norm": 1.7265625,
"learning_rate": 8.325234855847102e-05,
"loss": 4.6,
"step": 861
},
{
"epoch": 1.7591836734693878,
"grad_norm": 1.8125,
"learning_rate": 8.321995464852607e-05,
"loss": 4.6522,
"step": 862
},
{
"epoch": 1.7612244897959184,
"grad_norm": 1.7734375,
"learning_rate": 8.318756073858115e-05,
"loss": 4.6517,
"step": 863
},
{
"epoch": 1.763265306122449,
"grad_norm": 2.34375,
"learning_rate": 8.315516682863622e-05,
"loss": 4.6358,
"step": 864
},
{
"epoch": 1.7653061224489797,
"grad_norm": 1.8125,
"learning_rate": 8.31227729186913e-05,
"loss": 4.57,
"step": 865
},
{
"epoch": 1.76734693877551,
"grad_norm": 2.078125,
"learning_rate": 8.309037900874635e-05,
"loss": 4.5503,
"step": 866
},
{
"epoch": 1.769387755102041,
"grad_norm": 1.828125,
"learning_rate": 8.305798509880143e-05,
"loss": 4.4925,
"step": 867
},
{
"epoch": 1.7714285714285714,
"grad_norm": 1.8125,
"learning_rate": 8.30255911888565e-05,
"loss": 4.6649,
"step": 868
},
{
"epoch": 1.773469387755102,
"grad_norm": 2.078125,
"learning_rate": 8.299319727891157e-05,
"loss": 4.5619,
"step": 869
},
{
"epoch": 1.7755102040816326,
"grad_norm": 1.71875,
"learning_rate": 8.296080336896664e-05,
"loss": 4.5747,
"step": 870
},
{
"epoch": 1.7775510204081633,
"grad_norm": 1.6875,
"learning_rate": 8.29284094590217e-05,
"loss": 4.5868,
"step": 871
},
{
"epoch": 1.779591836734694,
"grad_norm": 1.75,
"learning_rate": 8.289601554907678e-05,
"loss": 4.6435,
"step": 872
},
{
"epoch": 1.7816326530612245,
"grad_norm": 1.8046875,
"learning_rate": 8.286362163913185e-05,
"loss": 4.5665,
"step": 873
},
{
"epoch": 1.7836734693877552,
"grad_norm": 1.6015625,
"learning_rate": 8.283122772918693e-05,
"loss": 4.5897,
"step": 874
},
{
"epoch": 1.7857142857142856,
"grad_norm": 1.8359375,
"learning_rate": 8.279883381924198e-05,
"loss": 4.6342,
"step": 875
},
{
"epoch": 1.7877551020408164,
"grad_norm": 1.5234375,
"learning_rate": 8.276643990929706e-05,
"loss": 4.6099,
"step": 876
},
{
"epoch": 1.7897959183673469,
"grad_norm": 1.671875,
"learning_rate": 8.273404599935213e-05,
"loss": 4.5821,
"step": 877
},
{
"epoch": 1.7918367346938775,
"grad_norm": 1.7265625,
"learning_rate": 8.27016520894072e-05,
"loss": 4.4818,
"step": 878
},
{
"epoch": 1.7938775510204081,
"grad_norm": 1.9609375,
"learning_rate": 8.266925817946226e-05,
"loss": 4.6504,
"step": 879
},
{
"epoch": 1.7959183673469388,
"grad_norm": 1.7421875,
"learning_rate": 8.263686426951734e-05,
"loss": 4.559,
"step": 880
},
{
"epoch": 1.7979591836734694,
"grad_norm": 1.8203125,
"learning_rate": 8.26044703595724e-05,
"loss": 4.6844,
"step": 881
},
{
"epoch": 1.8,
"grad_norm": 1.765625,
"learning_rate": 8.257207644962748e-05,
"loss": 4.5474,
"step": 882
},
{
"epoch": 1.8020408163265307,
"grad_norm": 1.71875,
"learning_rate": 8.253968253968255e-05,
"loss": 4.6742,
"step": 883
},
{
"epoch": 1.804081632653061,
"grad_norm": 1.671875,
"learning_rate": 8.250728862973761e-05,
"loss": 4.5474,
"step": 884
},
{
"epoch": 1.806122448979592,
"grad_norm": 1.59375,
"learning_rate": 8.247489471979269e-05,
"loss": 4.5266,
"step": 885
},
{
"epoch": 1.8081632653061224,
"grad_norm": 1.5625,
"learning_rate": 8.244250080984776e-05,
"loss": 4.6557,
"step": 886
},
{
"epoch": 1.810204081632653,
"grad_norm": 1.453125,
"learning_rate": 8.241010689990282e-05,
"loss": 4.5406,
"step": 887
},
{
"epoch": 1.8122448979591836,
"grad_norm": 1.625,
"learning_rate": 8.237771298995789e-05,
"loss": 4.5673,
"step": 888
},
{
"epoch": 1.8142857142857143,
"grad_norm": 1.7265625,
"learning_rate": 8.234531908001297e-05,
"loss": 4.6766,
"step": 889
},
{
"epoch": 1.816326530612245,
"grad_norm": 1.3359375,
"learning_rate": 8.231292517006803e-05,
"loss": 4.6166,
"step": 890
},
{
"epoch": 1.8183673469387756,
"grad_norm": 2.21875,
"learning_rate": 8.228053126012311e-05,
"loss": 4.5535,
"step": 891
},
{
"epoch": 1.8204081632653062,
"grad_norm": 1.8203125,
"learning_rate": 8.224813735017816e-05,
"loss": 4.4891,
"step": 892
},
{
"epoch": 1.8224489795918366,
"grad_norm": 1.5234375,
"learning_rate": 8.221574344023324e-05,
"loss": 4.5502,
"step": 893
},
{
"epoch": 1.8244897959183675,
"grad_norm": 1.859375,
"learning_rate": 8.218334953028831e-05,
"loss": 4.7406,
"step": 894
},
{
"epoch": 1.8265306122448979,
"grad_norm": 1.6875,
"learning_rate": 8.215095562034339e-05,
"loss": 4.5271,
"step": 895
},
{
"epoch": 1.8285714285714287,
"grad_norm": 1.59375,
"learning_rate": 8.211856171039844e-05,
"loss": 4.5788,
"step": 896
},
{
"epoch": 1.8306122448979592,
"grad_norm": 1.8046875,
"learning_rate": 8.208616780045352e-05,
"loss": 4.5234,
"step": 897
},
{
"epoch": 1.8326530612244898,
"grad_norm": 1.5078125,
"learning_rate": 8.205377389050858e-05,
"loss": 4.578,
"step": 898
},
{
"epoch": 1.8346938775510204,
"grad_norm": 1.7890625,
"learning_rate": 8.202137998056366e-05,
"loss": 4.4459,
"step": 899
},
{
"epoch": 1.836734693877551,
"grad_norm": 1.765625,
"learning_rate": 8.198898607061873e-05,
"loss": 4.5312,
"step": 900
},
{
"epoch": 1.8387755102040817,
"grad_norm": 1.890625,
"learning_rate": 8.19565921606738e-05,
"loss": 4.5001,
"step": 901
},
{
"epoch": 1.8408163265306121,
"grad_norm": 1.796875,
"learning_rate": 8.192419825072887e-05,
"loss": 4.4454,
"step": 902
},
{
"epoch": 1.842857142857143,
"grad_norm": 1.609375,
"learning_rate": 8.189180434078394e-05,
"loss": 4.6092,
"step": 903
},
{
"epoch": 1.8448979591836734,
"grad_norm": 1.6640625,
"learning_rate": 8.1859410430839e-05,
"loss": 4.5464,
"step": 904
},
{
"epoch": 1.8469387755102042,
"grad_norm": 1.6640625,
"learning_rate": 8.182701652089407e-05,
"loss": 4.4984,
"step": 905
},
{
"epoch": 1.8489795918367347,
"grad_norm": 1.6484375,
"learning_rate": 8.179462261094915e-05,
"loss": 4.5625,
"step": 906
},
{
"epoch": 1.8510204081632653,
"grad_norm": 1.875,
"learning_rate": 8.176222870100421e-05,
"loss": 4.5445,
"step": 907
},
{
"epoch": 1.853061224489796,
"grad_norm": 1.6015625,
"learning_rate": 8.17298347910593e-05,
"loss": 4.5562,
"step": 908
},
{
"epoch": 1.8551020408163266,
"grad_norm": 1.953125,
"learning_rate": 8.169744088111435e-05,
"loss": 4.5794,
"step": 909
},
{
"epoch": 1.8571428571428572,
"grad_norm": 1.7578125,
"learning_rate": 8.166504697116942e-05,
"loss": 4.5457,
"step": 910
},
{
"epoch": 1.8591836734693876,
"grad_norm": 1.5859375,
"learning_rate": 8.163265306122449e-05,
"loss": 4.5373,
"step": 911
},
{
"epoch": 1.8612244897959185,
"grad_norm": 1.8359375,
"learning_rate": 8.160025915127957e-05,
"loss": 4.5399,
"step": 912
},
{
"epoch": 1.863265306122449,
"grad_norm": 1.671875,
"learning_rate": 8.156786524133463e-05,
"loss": 4.5698,
"step": 913
},
{
"epoch": 1.8653061224489798,
"grad_norm": 1.6484375,
"learning_rate": 8.15354713313897e-05,
"loss": 4.5839,
"step": 914
},
{
"epoch": 1.8673469387755102,
"grad_norm": 1.6484375,
"learning_rate": 8.150307742144478e-05,
"loss": 4.6639,
"step": 915
},
{
"epoch": 1.8693877551020408,
"grad_norm": 1.4609375,
"learning_rate": 8.147068351149985e-05,
"loss": 4.5476,
"step": 916
},
{
"epoch": 1.8714285714285714,
"grad_norm": 1.546875,
"learning_rate": 8.143828960155491e-05,
"loss": 4.5894,
"step": 917
},
{
"epoch": 1.873469387755102,
"grad_norm": 1.8125,
"learning_rate": 8.140589569160998e-05,
"loss": 4.4782,
"step": 918
},
{
"epoch": 1.8755102040816327,
"grad_norm": 1.6484375,
"learning_rate": 8.137350178166506e-05,
"loss": 4.4375,
"step": 919
},
{
"epoch": 1.8775510204081631,
"grad_norm": 1.8125,
"learning_rate": 8.134110787172012e-05,
"loss": 4.5602,
"step": 920
},
{
"epoch": 1.879591836734694,
"grad_norm": 1.640625,
"learning_rate": 8.130871396177519e-05,
"loss": 4.6722,
"step": 921
},
{
"epoch": 1.8816326530612244,
"grad_norm": 1.7265625,
"learning_rate": 8.127632005183025e-05,
"loss": 4.5458,
"step": 922
},
{
"epoch": 1.8836734693877553,
"grad_norm": 1.609375,
"learning_rate": 8.124392614188533e-05,
"loss": 4.5878,
"step": 923
},
{
"epoch": 1.8857142857142857,
"grad_norm": 1.5703125,
"learning_rate": 8.12115322319404e-05,
"loss": 4.6634,
"step": 924
},
{
"epoch": 1.8877551020408163,
"grad_norm": 2.234375,
"learning_rate": 8.117913832199548e-05,
"loss": 4.5091,
"step": 925
},
{
"epoch": 1.889795918367347,
"grad_norm": 1.8046875,
"learning_rate": 8.114674441205054e-05,
"loss": 4.4966,
"step": 926
},
{
"epoch": 1.8918367346938776,
"grad_norm": 1.6640625,
"learning_rate": 8.111435050210561e-05,
"loss": 4.6033,
"step": 927
},
{
"epoch": 1.8938775510204082,
"grad_norm": 1.84375,
"learning_rate": 8.108195659216067e-05,
"loss": 4.5734,
"step": 928
},
{
"epoch": 1.8959183673469386,
"grad_norm": 1.78125,
"learning_rate": 8.104956268221575e-05,
"loss": 4.4716,
"step": 929
},
{
"epoch": 1.8979591836734695,
"grad_norm": 1.78125,
"learning_rate": 8.101716877227082e-05,
"loss": 4.4251,
"step": 930
},
{
"epoch": 1.9,
"grad_norm": 1.59375,
"learning_rate": 8.098477486232588e-05,
"loss": 4.5957,
"step": 931
},
{
"epoch": 1.9020408163265308,
"grad_norm": 1.40625,
"learning_rate": 8.095238095238096e-05,
"loss": 4.571,
"step": 932
},
{
"epoch": 1.9040816326530612,
"grad_norm": 1.53125,
"learning_rate": 8.091998704243603e-05,
"loss": 4.3549,
"step": 933
},
{
"epoch": 1.9061224489795918,
"grad_norm": 2.09375,
"learning_rate": 8.088759313249109e-05,
"loss": 4.6104,
"step": 934
},
{
"epoch": 1.9081632653061225,
"grad_norm": 1.6875,
"learning_rate": 8.085519922254616e-05,
"loss": 4.4906,
"step": 935
},
{
"epoch": 1.910204081632653,
"grad_norm": 1.859375,
"learning_rate": 8.082280531260124e-05,
"loss": 4.4406,
"step": 936
},
{
"epoch": 1.9122448979591837,
"grad_norm": 1.5234375,
"learning_rate": 8.07904114026563e-05,
"loss": 4.5944,
"step": 937
},
{
"epoch": 1.9142857142857141,
"grad_norm": 1.609375,
"learning_rate": 8.075801749271137e-05,
"loss": 4.6013,
"step": 938
},
{
"epoch": 1.916326530612245,
"grad_norm": 1.6015625,
"learning_rate": 8.072562358276643e-05,
"loss": 4.5243,
"step": 939
},
{
"epoch": 1.9183673469387754,
"grad_norm": 1.5625,
"learning_rate": 8.069322967282151e-05,
"loss": 4.5775,
"step": 940
},
{
"epoch": 1.9204081632653063,
"grad_norm": 2.03125,
"learning_rate": 8.066083576287658e-05,
"loss": 4.545,
"step": 941
},
{
"epoch": 1.9224489795918367,
"grad_norm": 1.734375,
"learning_rate": 8.062844185293166e-05,
"loss": 4.6464,
"step": 942
},
{
"epoch": 1.9244897959183673,
"grad_norm": 1.984375,
"learning_rate": 8.059604794298672e-05,
"loss": 4.4966,
"step": 943
},
{
"epoch": 1.926530612244898,
"grad_norm": 1.53125,
"learning_rate": 8.056365403304179e-05,
"loss": 4.4015,
"step": 944
},
{
"epoch": 1.9285714285714286,
"grad_norm": 1.921875,
"learning_rate": 8.053126012309687e-05,
"loss": 4.4975,
"step": 945
},
{
"epoch": 1.9306122448979592,
"grad_norm": 1.8046875,
"learning_rate": 8.049886621315193e-05,
"loss": 4.4132,
"step": 946
},
{
"epoch": 1.9326530612244897,
"grad_norm": 1.6171875,
"learning_rate": 8.0466472303207e-05,
"loss": 4.5068,
"step": 947
},
{
"epoch": 1.9346938775510205,
"grad_norm": 1.8984375,
"learning_rate": 8.043407839326207e-05,
"loss": 4.585,
"step": 948
},
{
"epoch": 1.936734693877551,
"grad_norm": 1.53125,
"learning_rate": 8.040168448331714e-05,
"loss": 4.6246,
"step": 949
},
{
"epoch": 1.9387755102040818,
"grad_norm": 1.5234375,
"learning_rate": 8.036929057337221e-05,
"loss": 4.4732,
"step": 950
},
{
"epoch": 1.9408163265306122,
"grad_norm": 1.78125,
"learning_rate": 8.033689666342728e-05,
"loss": 4.547,
"step": 951
},
{
"epoch": 1.9428571428571428,
"grad_norm": 1.875,
"learning_rate": 8.030450275348234e-05,
"loss": 4.6498,
"step": 952
},
{
"epoch": 1.9448979591836735,
"grad_norm": 1.6953125,
"learning_rate": 8.027210884353742e-05,
"loss": 4.5267,
"step": 953
},
{
"epoch": 1.9469387755102041,
"grad_norm": 1.609375,
"learning_rate": 8.023971493359249e-05,
"loss": 4.6491,
"step": 954
},
{
"epoch": 1.9489795918367347,
"grad_norm": 1.5859375,
"learning_rate": 8.020732102364757e-05,
"loss": 4.5664,
"step": 955
},
{
"epoch": 1.9510204081632652,
"grad_norm": 1.328125,
"learning_rate": 8.017492711370263e-05,
"loss": 4.4935,
"step": 956
},
{
"epoch": 1.953061224489796,
"grad_norm": 1.625,
"learning_rate": 8.01425332037577e-05,
"loss": 4.5979,
"step": 957
},
{
"epoch": 1.9551020408163264,
"grad_norm": 1.484375,
"learning_rate": 8.011013929381278e-05,
"loss": 4.5463,
"step": 958
},
{
"epoch": 1.9571428571428573,
"grad_norm": 1.71875,
"learning_rate": 8.007774538386784e-05,
"loss": 4.418,
"step": 959
},
{
"epoch": 1.9591836734693877,
"grad_norm": 1.6015625,
"learning_rate": 8.00453514739229e-05,
"loss": 4.5294,
"step": 960
},
{
"epoch": 1.9612244897959183,
"grad_norm": 1.7578125,
"learning_rate": 8.001295756397797e-05,
"loss": 4.475,
"step": 961
},
{
"epoch": 1.963265306122449,
"grad_norm": 1.4921875,
"learning_rate": 7.998056365403305e-05,
"loss": 4.5902,
"step": 962
},
{
"epoch": 1.9653061224489796,
"grad_norm": 1.7109375,
"learning_rate": 7.994816974408812e-05,
"loss": 4.5178,
"step": 963
},
{
"epoch": 1.9673469387755103,
"grad_norm": 1.4765625,
"learning_rate": 7.991577583414318e-05,
"loss": 4.6032,
"step": 964
},
{
"epoch": 1.9693877551020407,
"grad_norm": 1.5234375,
"learning_rate": 7.988338192419825e-05,
"loss": 4.5699,
"step": 965
},
{
"epoch": 1.9714285714285715,
"grad_norm": 1.5703125,
"learning_rate": 7.985098801425333e-05,
"loss": 4.5884,
"step": 966
},
{
"epoch": 1.973469387755102,
"grad_norm": 1.53125,
"learning_rate": 7.981859410430839e-05,
"loss": 4.5213,
"step": 967
},
{
"epoch": 1.9755102040816328,
"grad_norm": 1.46875,
"learning_rate": 7.978620019436346e-05,
"loss": 4.5347,
"step": 968
},
{
"epoch": 1.9775510204081632,
"grad_norm": 1.5546875,
"learning_rate": 7.975380628441854e-05,
"loss": 4.4596,
"step": 969
},
{
"epoch": 1.9795918367346939,
"grad_norm": 1.6953125,
"learning_rate": 7.97214123744736e-05,
"loss": 4.4387,
"step": 970
},
{
"epoch": 1.9816326530612245,
"grad_norm": 1.5703125,
"learning_rate": 7.968901846452867e-05,
"loss": 4.4685,
"step": 971
},
{
"epoch": 1.9836734693877551,
"grad_norm": 1.6640625,
"learning_rate": 7.965662455458375e-05,
"loss": 4.5439,
"step": 972
},
{
"epoch": 1.9857142857142858,
"grad_norm": 1.71875,
"learning_rate": 7.962423064463881e-05,
"loss": 4.5256,
"step": 973
},
{
"epoch": 1.9877551020408162,
"grad_norm": 1.453125,
"learning_rate": 7.959183673469388e-05,
"loss": 4.5381,
"step": 974
},
{
"epoch": 1.989795918367347,
"grad_norm": 1.65625,
"learning_rate": 7.955944282474896e-05,
"loss": 4.5995,
"step": 975
},
{
"epoch": 1.9918367346938775,
"grad_norm": 1.46875,
"learning_rate": 7.952704891480402e-05,
"loss": 4.4395,
"step": 976
},
{
"epoch": 1.9938775510204083,
"grad_norm": 1.5390625,
"learning_rate": 7.949465500485909e-05,
"loss": 4.4136,
"step": 977
},
{
"epoch": 1.9959183673469387,
"grad_norm": 1.7734375,
"learning_rate": 7.946226109491415e-05,
"loss": 4.5081,
"step": 978
},
{
"epoch": 1.9979591836734694,
"grad_norm": 1.6796875,
"learning_rate": 7.942986718496923e-05,
"loss": 4.4953,
"step": 979
},
{
"epoch": 2.0,
"grad_norm": 1.796875,
"learning_rate": 7.93974732750243e-05,
"loss": 4.5133,
"step": 980
},
{
"epoch": 2.0020408163265304,
"grad_norm": 1.7578125,
"learning_rate": 7.936507936507937e-05,
"loss": 4.2191,
"step": 981
},
{
"epoch": 2.0040816326530613,
"grad_norm": 1.734375,
"learning_rate": 7.933268545513443e-05,
"loss": 4.3466,
"step": 982
},
{
"epoch": 2.0061224489795917,
"grad_norm": 1.640625,
"learning_rate": 7.930029154518951e-05,
"loss": 4.2504,
"step": 983
},
{
"epoch": 2.0081632653061225,
"grad_norm": 1.6484375,
"learning_rate": 7.926789763524458e-05,
"loss": 4.4179,
"step": 984
},
{
"epoch": 2.010204081632653,
"grad_norm": 1.8203125,
"learning_rate": 7.923550372529964e-05,
"loss": 4.3759,
"step": 985
},
{
"epoch": 2.012244897959184,
"grad_norm": 1.7578125,
"learning_rate": 7.920310981535472e-05,
"loss": 4.3409,
"step": 986
},
{
"epoch": 2.0142857142857142,
"grad_norm": 1.6875,
"learning_rate": 7.917071590540979e-05,
"loss": 4.2449,
"step": 987
},
{
"epoch": 2.016326530612245,
"grad_norm": 1.6328125,
"learning_rate": 7.913832199546486e-05,
"loss": 4.3722,
"step": 988
},
{
"epoch": 2.0183673469387755,
"grad_norm": 1.8125,
"learning_rate": 7.910592808551993e-05,
"loss": 4.1739,
"step": 989
},
{
"epoch": 2.020408163265306,
"grad_norm": 2.09375,
"learning_rate": 7.9073534175575e-05,
"loss": 4.1077,
"step": 990
},
{
"epoch": 2.022448979591837,
"grad_norm": 1.578125,
"learning_rate": 7.904114026563006e-05,
"loss": 4.2163,
"step": 991
},
{
"epoch": 2.024489795918367,
"grad_norm": 2.28125,
"learning_rate": 7.900874635568514e-05,
"loss": 4.3382,
"step": 992
},
{
"epoch": 2.026530612244898,
"grad_norm": 2.15625,
"learning_rate": 7.89763524457402e-05,
"loss": 4.2353,
"step": 993
},
{
"epoch": 2.0285714285714285,
"grad_norm": 1.96875,
"learning_rate": 7.894395853579527e-05,
"loss": 4.1874,
"step": 994
},
{
"epoch": 2.0306122448979593,
"grad_norm": 1.921875,
"learning_rate": 7.891156462585034e-05,
"loss": 4.1556,
"step": 995
},
{
"epoch": 2.0326530612244897,
"grad_norm": 1.671875,
"learning_rate": 7.887917071590542e-05,
"loss": 4.2339,
"step": 996
},
{
"epoch": 2.0346938775510206,
"grad_norm": 2.09375,
"learning_rate": 7.884677680596048e-05,
"loss": 4.2934,
"step": 997
},
{
"epoch": 2.036734693877551,
"grad_norm": 1.8984375,
"learning_rate": 7.881438289601555e-05,
"loss": 4.2437,
"step": 998
},
{
"epoch": 2.0387755102040814,
"grad_norm": 1.890625,
"learning_rate": 7.878198898607063e-05,
"loss": 4.2019,
"step": 999
},
{
"epoch": 2.0408163265306123,
"grad_norm": 1.8671875,
"learning_rate": 7.874959507612569e-05,
"loss": 4.1762,
"step": 1000
},
{
"epoch": 2.0408163265306123,
"eval_loss": 4.025330543518066,
"eval_runtime": 5.4547,
"eval_samples_per_second": 29.333,
"eval_steps_per_second": 7.333,
"step": 1000
},
{
"epoch": 2.0428571428571427,
"grad_norm": 1.984375,
"learning_rate": 7.871720116618077e-05,
"loss": 4.4351,
"step": 1001
},
{
"epoch": 2.0448979591836736,
"grad_norm": 1.65625,
"learning_rate": 7.868480725623582e-05,
"loss": 4.2428,
"step": 1002
},
{
"epoch": 2.046938775510204,
"grad_norm": 2.046875,
"learning_rate": 7.86524133462909e-05,
"loss": 4.3199,
"step": 1003
},
{
"epoch": 2.048979591836735,
"grad_norm": 2.25,
"learning_rate": 7.862001943634597e-05,
"loss": 4.1872,
"step": 1004
},
{
"epoch": 2.0510204081632653,
"grad_norm": 1.859375,
"learning_rate": 7.858762552640105e-05,
"loss": 4.1688,
"step": 1005
},
{
"epoch": 2.053061224489796,
"grad_norm": 2.296875,
"learning_rate": 7.855523161645611e-05,
"loss": 4.337,
"step": 1006
},
{
"epoch": 2.0551020408163265,
"grad_norm": 2.15625,
"learning_rate": 7.852283770651118e-05,
"loss": 4.1198,
"step": 1007
},
{
"epoch": 2.057142857142857,
"grad_norm": 1.7265625,
"learning_rate": 7.849044379656624e-05,
"loss": 4.2986,
"step": 1008
},
{
"epoch": 2.059183673469388,
"grad_norm": 2.15625,
"learning_rate": 7.845804988662132e-05,
"loss": 4.0616,
"step": 1009
},
{
"epoch": 2.061224489795918,
"grad_norm": 2.0,
"learning_rate": 7.842565597667639e-05,
"loss": 4.2204,
"step": 1010
},
{
"epoch": 2.063265306122449,
"grad_norm": 1.796875,
"learning_rate": 7.839326206673145e-05,
"loss": 4.1761,
"step": 1011
},
{
"epoch": 2.0653061224489795,
"grad_norm": 2.09375,
"learning_rate": 7.836086815678652e-05,
"loss": 4.182,
"step": 1012
},
{
"epoch": 2.0673469387755103,
"grad_norm": 1.828125,
"learning_rate": 7.83284742468416e-05,
"loss": 4.2916,
"step": 1013
},
{
"epoch": 2.0693877551020408,
"grad_norm": 1.8046875,
"learning_rate": 7.829608033689666e-05,
"loss": 4.1519,
"step": 1014
},
{
"epoch": 2.0714285714285716,
"grad_norm": 1.78125,
"learning_rate": 7.826368642695173e-05,
"loss": 4.3492,
"step": 1015
},
{
"epoch": 2.073469387755102,
"grad_norm": 2.03125,
"learning_rate": 7.823129251700681e-05,
"loss": 4.174,
"step": 1016
},
{
"epoch": 2.0755102040816324,
"grad_norm": 1.78125,
"learning_rate": 7.819889860706187e-05,
"loss": 4.3547,
"step": 1017
},
{
"epoch": 2.0775510204081633,
"grad_norm": 1.859375,
"learning_rate": 7.816650469711695e-05,
"loss": 4.1761,
"step": 1018
},
{
"epoch": 2.0795918367346937,
"grad_norm": 1.9453125,
"learning_rate": 7.8134110787172e-05,
"loss": 4.3823,
"step": 1019
},
{
"epoch": 2.0816326530612246,
"grad_norm": 1.5625,
"learning_rate": 7.810171687722709e-05,
"loss": 4.361,
"step": 1020
},
{
"epoch": 2.083673469387755,
"grad_norm": 1.828125,
"learning_rate": 7.806932296728215e-05,
"loss": 4.1552,
"step": 1021
},
{
"epoch": 2.085714285714286,
"grad_norm": 1.625,
"learning_rate": 7.803692905733723e-05,
"loss": 4.2614,
"step": 1022
},
{
"epoch": 2.0877551020408163,
"grad_norm": 1.5859375,
"learning_rate": 7.80045351473923e-05,
"loss": 4.2051,
"step": 1023
},
{
"epoch": 2.089795918367347,
"grad_norm": 1.734375,
"learning_rate": 7.797214123744736e-05,
"loss": 4.1534,
"step": 1024
},
{
"epoch": 2.0918367346938775,
"grad_norm": 1.796875,
"learning_rate": 7.793974732750243e-05,
"loss": 4.1943,
"step": 1025
},
{
"epoch": 2.093877551020408,
"grad_norm": 1.921875,
"learning_rate": 7.79073534175575e-05,
"loss": 4.2191,
"step": 1026
},
{
"epoch": 2.095918367346939,
"grad_norm": 1.9609375,
"learning_rate": 7.787495950761257e-05,
"loss": 4.2108,
"step": 1027
},
{
"epoch": 2.0979591836734692,
"grad_norm": 1.609375,
"learning_rate": 7.784256559766764e-05,
"loss": 4.3035,
"step": 1028
},
{
"epoch": 2.1,
"grad_norm": 1.875,
"learning_rate": 7.781017168772272e-05,
"loss": 4.3197,
"step": 1029
},
{
"epoch": 2.1020408163265305,
"grad_norm": 1.90625,
"learning_rate": 7.777777777777778e-05,
"loss": 4.2912,
"step": 1030
},
{
"epoch": 2.1040816326530614,
"grad_norm": 1.84375,
"learning_rate": 7.774538386783286e-05,
"loss": 4.1402,
"step": 1031
},
{
"epoch": 2.1061224489795918,
"grad_norm": 1.921875,
"learning_rate": 7.771298995788791e-05,
"loss": 4.2356,
"step": 1032
},
{
"epoch": 2.1081632653061226,
"grad_norm": 1.8515625,
"learning_rate": 7.768059604794299e-05,
"loss": 4.2653,
"step": 1033
},
{
"epoch": 2.110204081632653,
"grad_norm": 1.90625,
"learning_rate": 7.764820213799806e-05,
"loss": 4.321,
"step": 1034
},
{
"epoch": 2.1122448979591835,
"grad_norm": 1.8515625,
"learning_rate": 7.761580822805314e-05,
"loss": 4.243,
"step": 1035
},
{
"epoch": 2.1142857142857143,
"grad_norm": 1.7421875,
"learning_rate": 7.758341431810819e-05,
"loss": 4.1279,
"step": 1036
},
{
"epoch": 2.1163265306122447,
"grad_norm": 1.90625,
"learning_rate": 7.755102040816327e-05,
"loss": 4.3547,
"step": 1037
},
{
"epoch": 2.1183673469387756,
"grad_norm": 1.6875,
"learning_rate": 7.751862649821833e-05,
"loss": 4.2522,
"step": 1038
},
{
"epoch": 2.120408163265306,
"grad_norm": 1.9375,
"learning_rate": 7.748623258827341e-05,
"loss": 4.2449,
"step": 1039
},
{
"epoch": 2.122448979591837,
"grad_norm": 1.75,
"learning_rate": 7.745383867832848e-05,
"loss": 4.2106,
"step": 1040
},
{
"epoch": 2.1244897959183673,
"grad_norm": 1.828125,
"learning_rate": 7.742144476838354e-05,
"loss": 4.2819,
"step": 1041
},
{
"epoch": 2.126530612244898,
"grad_norm": 1.78125,
"learning_rate": 7.738905085843862e-05,
"loss": 4.2978,
"step": 1042
},
{
"epoch": 2.1285714285714286,
"grad_norm": 1.75,
"learning_rate": 7.735665694849369e-05,
"loss": 4.1743,
"step": 1043
},
{
"epoch": 2.130612244897959,
"grad_norm": 1.9453125,
"learning_rate": 7.732426303854877e-05,
"loss": 4.1746,
"step": 1044
},
{
"epoch": 2.13265306122449,
"grad_norm": 1.7265625,
"learning_rate": 7.729186912860382e-05,
"loss": 4.1288,
"step": 1045
},
{
"epoch": 2.1346938775510202,
"grad_norm": 1.6796875,
"learning_rate": 7.72594752186589e-05,
"loss": 4.2504,
"step": 1046
},
{
"epoch": 2.136734693877551,
"grad_norm": 1.90625,
"learning_rate": 7.722708130871396e-05,
"loss": 4.2063,
"step": 1047
},
{
"epoch": 2.1387755102040815,
"grad_norm": 1.875,
"learning_rate": 7.719468739876904e-05,
"loss": 4.2249,
"step": 1048
},
{
"epoch": 2.1408163265306124,
"grad_norm": 1.75,
"learning_rate": 7.71622934888241e-05,
"loss": 4.2155,
"step": 1049
},
{
"epoch": 2.142857142857143,
"grad_norm": 1.90625,
"learning_rate": 7.712989957887917e-05,
"loss": 4.3042,
"step": 1050
},
{
"epoch": 2.1448979591836737,
"grad_norm": 1.609375,
"learning_rate": 7.709750566893424e-05,
"loss": 4.2049,
"step": 1051
},
{
"epoch": 2.146938775510204,
"grad_norm": 1.7421875,
"learning_rate": 7.706511175898932e-05,
"loss": 4.3375,
"step": 1052
},
{
"epoch": 2.148979591836735,
"grad_norm": 1.734375,
"learning_rate": 7.703271784904438e-05,
"loss": 4.3483,
"step": 1053
},
{
"epoch": 2.1510204081632653,
"grad_norm": 1.921875,
"learning_rate": 7.700032393909945e-05,
"loss": 4.2495,
"step": 1054
},
{
"epoch": 2.1530612244897958,
"grad_norm": 1.9375,
"learning_rate": 7.696793002915452e-05,
"loss": 4.0384,
"step": 1055
},
{
"epoch": 2.1551020408163266,
"grad_norm": 1.828125,
"learning_rate": 7.69355361192096e-05,
"loss": 4.2755,
"step": 1056
},
{
"epoch": 2.157142857142857,
"grad_norm": 1.7578125,
"learning_rate": 7.690314220926466e-05,
"loss": 4.273,
"step": 1057
},
{
"epoch": 2.159183673469388,
"grad_norm": 1.4375,
"learning_rate": 7.687074829931973e-05,
"loss": 4.1972,
"step": 1058
},
{
"epoch": 2.1612244897959183,
"grad_norm": 1.578125,
"learning_rate": 7.68383543893748e-05,
"loss": 4.2271,
"step": 1059
},
{
"epoch": 2.163265306122449,
"grad_norm": 1.7421875,
"learning_rate": 7.680596047942987e-05,
"loss": 4.2246,
"step": 1060
},
{
"epoch": 2.1653061224489796,
"grad_norm": 1.8359375,
"learning_rate": 7.677356656948495e-05,
"loss": 4.2787,
"step": 1061
},
{
"epoch": 2.16734693877551,
"grad_norm": 1.7890625,
"learning_rate": 7.674117265954e-05,
"loss": 4.2807,
"step": 1062
},
{
"epoch": 2.169387755102041,
"grad_norm": 1.828125,
"learning_rate": 7.670877874959508e-05,
"loss": 4.2996,
"step": 1063
},
{
"epoch": 2.1714285714285713,
"grad_norm": 1.7734375,
"learning_rate": 7.667638483965015e-05,
"loss": 4.2142,
"step": 1064
},
{
"epoch": 2.173469387755102,
"grad_norm": 1.765625,
"learning_rate": 7.664399092970523e-05,
"loss": 4.2761,
"step": 1065
},
{
"epoch": 2.1755102040816325,
"grad_norm": 1.734375,
"learning_rate": 7.661159701976028e-05,
"loss": 4.3326,
"step": 1066
},
{
"epoch": 2.1775510204081634,
"grad_norm": 1.8046875,
"learning_rate": 7.657920310981536e-05,
"loss": 4.3556,
"step": 1067
},
{
"epoch": 2.179591836734694,
"grad_norm": 1.7734375,
"learning_rate": 7.654680919987042e-05,
"loss": 4.2136,
"step": 1068
},
{
"epoch": 2.1816326530612247,
"grad_norm": 2.0,
"learning_rate": 7.65144152899255e-05,
"loss": 4.2234,
"step": 1069
},
{
"epoch": 2.183673469387755,
"grad_norm": 1.671875,
"learning_rate": 7.648202137998057e-05,
"loss": 4.3658,
"step": 1070
},
{
"epoch": 2.185714285714286,
"grad_norm": 1.6640625,
"learning_rate": 7.644962747003563e-05,
"loss": 4.3511,
"step": 1071
},
{
"epoch": 2.1877551020408164,
"grad_norm": 1.671875,
"learning_rate": 7.641723356009071e-05,
"loss": 4.1838,
"step": 1072
},
{
"epoch": 2.1897959183673468,
"grad_norm": 1.828125,
"learning_rate": 7.638483965014578e-05,
"loss": 4.2588,
"step": 1073
},
{
"epoch": 2.1918367346938776,
"grad_norm": 1.6015625,
"learning_rate": 7.635244574020086e-05,
"loss": 4.2983,
"step": 1074
},
{
"epoch": 2.193877551020408,
"grad_norm": 1.7734375,
"learning_rate": 7.632005183025591e-05,
"loss": 4.183,
"step": 1075
},
{
"epoch": 2.195918367346939,
"grad_norm": 1.8359375,
"learning_rate": 7.628765792031099e-05,
"loss": 4.155,
"step": 1076
},
{
"epoch": 2.1979591836734693,
"grad_norm": 1.6171875,
"learning_rate": 7.625526401036605e-05,
"loss": 4.1874,
"step": 1077
},
{
"epoch": 2.2,
"grad_norm": 1.7578125,
"learning_rate": 7.622287010042113e-05,
"loss": 4.3332,
"step": 1078
},
{
"epoch": 2.2020408163265306,
"grad_norm": 1.796875,
"learning_rate": 7.619047619047618e-05,
"loss": 4.2761,
"step": 1079
},
{
"epoch": 2.204081632653061,
"grad_norm": 1.6953125,
"learning_rate": 7.615808228053126e-05,
"loss": 4.1713,
"step": 1080
},
{
"epoch": 2.206122448979592,
"grad_norm": 2.234375,
"learning_rate": 7.612568837058633e-05,
"loss": 4.2792,
"step": 1081
},
{
"epoch": 2.2081632653061223,
"grad_norm": 1.7109375,
"learning_rate": 7.609329446064141e-05,
"loss": 4.1984,
"step": 1082
},
{
"epoch": 2.210204081632653,
"grad_norm": 1.5,
"learning_rate": 7.606090055069647e-05,
"loss": 4.2761,
"step": 1083
},
{
"epoch": 2.2122448979591836,
"grad_norm": 1.6484375,
"learning_rate": 7.602850664075154e-05,
"loss": 4.2548,
"step": 1084
},
{
"epoch": 2.2142857142857144,
"grad_norm": 1.5625,
"learning_rate": 7.599611273080662e-05,
"loss": 4.2747,
"step": 1085
},
{
"epoch": 2.216326530612245,
"grad_norm": 1.5546875,
"learning_rate": 7.596371882086168e-05,
"loss": 4.1591,
"step": 1086
},
{
"epoch": 2.2183673469387757,
"grad_norm": 1.703125,
"learning_rate": 7.593132491091676e-05,
"loss": 4.2701,
"step": 1087
},
{
"epoch": 2.220408163265306,
"grad_norm": 1.5859375,
"learning_rate": 7.589893100097182e-05,
"loss": 4.2033,
"step": 1088
},
{
"epoch": 2.222448979591837,
"grad_norm": 1.921875,
"learning_rate": 7.58665370910269e-05,
"loss": 4.2465,
"step": 1089
},
{
"epoch": 2.2244897959183674,
"grad_norm": 1.5546875,
"learning_rate": 7.583414318108196e-05,
"loss": 4.3297,
"step": 1090
},
{
"epoch": 2.226530612244898,
"grad_norm": 1.7109375,
"learning_rate": 7.580174927113704e-05,
"loss": 4.2206,
"step": 1091
},
{
"epoch": 2.2285714285714286,
"grad_norm": 1.71875,
"learning_rate": 7.576935536119209e-05,
"loss": 4.3086,
"step": 1092
},
{
"epoch": 2.230612244897959,
"grad_norm": 1.890625,
"learning_rate": 7.573696145124717e-05,
"loss": 4.2998,
"step": 1093
},
{
"epoch": 2.23265306122449,
"grad_norm": 1.671875,
"learning_rate": 7.570456754130224e-05,
"loss": 4.3213,
"step": 1094
},
{
"epoch": 2.2346938775510203,
"grad_norm": 1.578125,
"learning_rate": 7.567217363135731e-05,
"loss": 4.246,
"step": 1095
},
{
"epoch": 2.236734693877551,
"grad_norm": 2.140625,
"learning_rate": 7.563977972141238e-05,
"loss": 4.1913,
"step": 1096
},
{
"epoch": 2.2387755102040816,
"grad_norm": 1.671875,
"learning_rate": 7.560738581146745e-05,
"loss": 4.2934,
"step": 1097
},
{
"epoch": 2.240816326530612,
"grad_norm": 1.796875,
"learning_rate": 7.557499190152251e-05,
"loss": 4.244,
"step": 1098
},
{
"epoch": 2.242857142857143,
"grad_norm": 1.7578125,
"learning_rate": 7.554259799157759e-05,
"loss": 4.3621,
"step": 1099
},
{
"epoch": 2.2448979591836733,
"grad_norm": 1.6015625,
"learning_rate": 7.551020408163266e-05,
"loss": 4.2102,
"step": 1100
},
{
"epoch": 2.246938775510204,
"grad_norm": 1.75,
"learning_rate": 7.547781017168772e-05,
"loss": 4.262,
"step": 1101
},
{
"epoch": 2.2489795918367346,
"grad_norm": 1.640625,
"learning_rate": 7.54454162617428e-05,
"loss": 4.3077,
"step": 1102
},
{
"epoch": 2.2510204081632654,
"grad_norm": 1.9296875,
"learning_rate": 7.541302235179787e-05,
"loss": 4.2464,
"step": 1103
},
{
"epoch": 2.253061224489796,
"grad_norm": 1.796875,
"learning_rate": 7.538062844185295e-05,
"loss": 4.3553,
"step": 1104
},
{
"epoch": 2.2551020408163267,
"grad_norm": 1.5859375,
"learning_rate": 7.5348234531908e-05,
"loss": 4.3904,
"step": 1105
},
{
"epoch": 2.257142857142857,
"grad_norm": 1.9140625,
"learning_rate": 7.531584062196308e-05,
"loss": 4.1534,
"step": 1106
},
{
"epoch": 2.259183673469388,
"grad_norm": 1.6484375,
"learning_rate": 7.528344671201814e-05,
"loss": 4.2408,
"step": 1107
},
{
"epoch": 2.2612244897959184,
"grad_norm": 1.8125,
"learning_rate": 7.525105280207322e-05,
"loss": 4.3447,
"step": 1108
},
{
"epoch": 2.263265306122449,
"grad_norm": 1.9609375,
"learning_rate": 7.521865889212827e-05,
"loss": 4.1911,
"step": 1109
},
{
"epoch": 2.2653061224489797,
"grad_norm": 1.75,
"learning_rate": 7.518626498218335e-05,
"loss": 4.2798,
"step": 1110
},
{
"epoch": 2.26734693877551,
"grad_norm": 1.765625,
"learning_rate": 7.515387107223842e-05,
"loss": 4.1094,
"step": 1111
},
{
"epoch": 2.269387755102041,
"grad_norm": 1.625,
"learning_rate": 7.51214771622935e-05,
"loss": 4.2196,
"step": 1112
},
{
"epoch": 2.2714285714285714,
"grad_norm": 1.609375,
"learning_rate": 7.508908325234856e-05,
"loss": 4.278,
"step": 1113
},
{
"epoch": 2.273469387755102,
"grad_norm": 1.5859375,
"learning_rate": 7.505668934240363e-05,
"loss": 4.1459,
"step": 1114
},
{
"epoch": 2.2755102040816326,
"grad_norm": 1.7265625,
"learning_rate": 7.502429543245871e-05,
"loss": 4.2585,
"step": 1115
},
{
"epoch": 2.277551020408163,
"grad_norm": 1.7890625,
"learning_rate": 7.499190152251377e-05,
"loss": 4.3321,
"step": 1116
},
{
"epoch": 2.279591836734694,
"grad_norm": 1.6875,
"learning_rate": 7.495950761256884e-05,
"loss": 4.1766,
"step": 1117
},
{
"epoch": 2.2816326530612243,
"grad_norm": 1.921875,
"learning_rate": 7.49271137026239e-05,
"loss": 4.2266,
"step": 1118
},
{
"epoch": 2.283673469387755,
"grad_norm": 1.703125,
"learning_rate": 7.489471979267898e-05,
"loss": 4.3169,
"step": 1119
},
{
"epoch": 2.2857142857142856,
"grad_norm": 2.015625,
"learning_rate": 7.486232588273405e-05,
"loss": 4.2498,
"step": 1120
},
{
"epoch": 2.2877551020408164,
"grad_norm": 2.125,
"learning_rate": 7.482993197278913e-05,
"loss": 4.1544,
"step": 1121
},
{
"epoch": 2.289795918367347,
"grad_norm": 1.7578125,
"learning_rate": 7.479753806284418e-05,
"loss": 4.1903,
"step": 1122
},
{
"epoch": 2.2918367346938777,
"grad_norm": 1.828125,
"learning_rate": 7.476514415289926e-05,
"loss": 4.2425,
"step": 1123
},
{
"epoch": 2.293877551020408,
"grad_norm": 2.234375,
"learning_rate": 7.473275024295433e-05,
"loss": 4.2638,
"step": 1124
},
{
"epoch": 2.295918367346939,
"grad_norm": 1.890625,
"learning_rate": 7.47003563330094e-05,
"loss": 4.2894,
"step": 1125
},
{
"epoch": 2.2979591836734694,
"grad_norm": 2.015625,
"learning_rate": 7.466796242306447e-05,
"loss": 4.3134,
"step": 1126
},
{
"epoch": 2.3,
"grad_norm": 2.40625,
"learning_rate": 7.463556851311954e-05,
"loss": 4.2295,
"step": 1127
},
{
"epoch": 2.3020408163265307,
"grad_norm": 1.6171875,
"learning_rate": 7.460317460317461e-05,
"loss": 4.2266,
"step": 1128
},
{
"epoch": 2.304081632653061,
"grad_norm": 1.8125,
"learning_rate": 7.457078069322968e-05,
"loss": 4.1767,
"step": 1129
},
{
"epoch": 2.306122448979592,
"grad_norm": 1.8828125,
"learning_rate": 7.453838678328475e-05,
"loss": 4.3757,
"step": 1130
},
{
"epoch": 2.3081632653061224,
"grad_norm": 1.890625,
"learning_rate": 7.450599287333981e-05,
"loss": 4.149,
"step": 1131
},
{
"epoch": 2.3102040816326532,
"grad_norm": 1.7109375,
"learning_rate": 7.447359896339489e-05,
"loss": 4.3476,
"step": 1132
},
{
"epoch": 2.3122448979591836,
"grad_norm": 1.6640625,
"learning_rate": 7.444120505344996e-05,
"loss": 4.1284,
"step": 1133
},
{
"epoch": 2.314285714285714,
"grad_norm": 1.984375,
"learning_rate": 7.440881114350502e-05,
"loss": 4.1494,
"step": 1134
},
{
"epoch": 2.316326530612245,
"grad_norm": 1.5859375,
"learning_rate": 7.437641723356009e-05,
"loss": 4.3341,
"step": 1135
},
{
"epoch": 2.3183673469387753,
"grad_norm": 1.828125,
"learning_rate": 7.434402332361517e-05,
"loss": 4.3528,
"step": 1136
},
{
"epoch": 2.320408163265306,
"grad_norm": 1.9609375,
"learning_rate": 7.431162941367023e-05,
"loss": 4.1957,
"step": 1137
},
{
"epoch": 2.3224489795918366,
"grad_norm": 1.546875,
"learning_rate": 7.427923550372531e-05,
"loss": 4.1281,
"step": 1138
},
{
"epoch": 2.3244897959183675,
"grad_norm": 1.7109375,
"learning_rate": 7.424684159378036e-05,
"loss": 4.2159,
"step": 1139
},
{
"epoch": 2.326530612244898,
"grad_norm": 1.765625,
"learning_rate": 7.421444768383544e-05,
"loss": 4.1168,
"step": 1140
},
{
"epoch": 2.3285714285714287,
"grad_norm": 1.59375,
"learning_rate": 7.418205377389051e-05,
"loss": 4.3013,
"step": 1141
},
{
"epoch": 2.330612244897959,
"grad_norm": 1.625,
"learning_rate": 7.414965986394559e-05,
"loss": 4.1657,
"step": 1142
},
{
"epoch": 2.33265306122449,
"grad_norm": 1.6015625,
"learning_rate": 7.411726595400065e-05,
"loss": 4.2377,
"step": 1143
},
{
"epoch": 2.3346938775510204,
"grad_norm": 1.7109375,
"learning_rate": 7.408487204405572e-05,
"loss": 4.2896,
"step": 1144
},
{
"epoch": 2.336734693877551,
"grad_norm": 1.6875,
"learning_rate": 7.40524781341108e-05,
"loss": 4.2559,
"step": 1145
},
{
"epoch": 2.3387755102040817,
"grad_norm": 1.5390625,
"learning_rate": 7.402008422416586e-05,
"loss": 4.209,
"step": 1146
},
{
"epoch": 2.340816326530612,
"grad_norm": 1.8671875,
"learning_rate": 7.398769031422093e-05,
"loss": 4.1941,
"step": 1147
},
{
"epoch": 2.342857142857143,
"grad_norm": 1.7421875,
"learning_rate": 7.3955296404276e-05,
"loss": 4.2456,
"step": 1148
},
{
"epoch": 2.3448979591836734,
"grad_norm": 1.5625,
"learning_rate": 7.392290249433107e-05,
"loss": 4.1695,
"step": 1149
},
{
"epoch": 2.3469387755102042,
"grad_norm": 1.578125,
"learning_rate": 7.389050858438614e-05,
"loss": 4.172,
"step": 1150
},
{
"epoch": 2.3489795918367347,
"grad_norm": 1.6796875,
"learning_rate": 7.38581146744412e-05,
"loss": 4.2296,
"step": 1151
},
{
"epoch": 2.351020408163265,
"grad_norm": 1.7265625,
"learning_rate": 7.382572076449627e-05,
"loss": 4.2232,
"step": 1152
},
{
"epoch": 2.353061224489796,
"grad_norm": 1.671875,
"learning_rate": 7.379332685455135e-05,
"loss": 4.188,
"step": 1153
},
{
"epoch": 2.3551020408163263,
"grad_norm": 1.71875,
"learning_rate": 7.376093294460641e-05,
"loss": 4.2057,
"step": 1154
},
{
"epoch": 2.357142857142857,
"grad_norm": 1.859375,
"learning_rate": 7.37285390346615e-05,
"loss": 4.1379,
"step": 1155
},
{
"epoch": 2.3591836734693876,
"grad_norm": 1.6640625,
"learning_rate": 7.369614512471656e-05,
"loss": 4.1453,
"step": 1156
},
{
"epoch": 2.3612244897959185,
"grad_norm": 1.9296875,
"learning_rate": 7.366375121477162e-05,
"loss": 4.1431,
"step": 1157
},
{
"epoch": 2.363265306122449,
"grad_norm": 1.6015625,
"learning_rate": 7.36313573048267e-05,
"loss": 4.2932,
"step": 1158
},
{
"epoch": 2.3653061224489798,
"grad_norm": 1.7734375,
"learning_rate": 7.359896339488177e-05,
"loss": 4.1768,
"step": 1159
},
{
"epoch": 2.36734693877551,
"grad_norm": 1.8984375,
"learning_rate": 7.356656948493683e-05,
"loss": 4.0642,
"step": 1160
},
{
"epoch": 2.369387755102041,
"grad_norm": 1.6875,
"learning_rate": 7.35341755749919e-05,
"loss": 4.0023,
"step": 1161
},
{
"epoch": 2.3714285714285714,
"grad_norm": 1.734375,
"learning_rate": 7.350178166504698e-05,
"loss": 4.2168,
"step": 1162
},
{
"epoch": 2.373469387755102,
"grad_norm": 1.796875,
"learning_rate": 7.346938775510205e-05,
"loss": 4.2608,
"step": 1163
},
{
"epoch": 2.3755102040816327,
"grad_norm": 1.734375,
"learning_rate": 7.343699384515711e-05,
"loss": 4.2901,
"step": 1164
},
{
"epoch": 2.377551020408163,
"grad_norm": 1.7421875,
"learning_rate": 7.340459993521218e-05,
"loss": 4.2634,
"step": 1165
},
{
"epoch": 2.379591836734694,
"grad_norm": 1.6484375,
"learning_rate": 7.337220602526726e-05,
"loss": 4.0896,
"step": 1166
},
{
"epoch": 2.3816326530612244,
"grad_norm": 1.78125,
"learning_rate": 7.333981211532232e-05,
"loss": 4.1883,
"step": 1167
},
{
"epoch": 2.3836734693877553,
"grad_norm": 1.546875,
"learning_rate": 7.330741820537739e-05,
"loss": 4.1743,
"step": 1168
},
{
"epoch": 2.3857142857142857,
"grad_norm": 1.7265625,
"learning_rate": 7.327502429543247e-05,
"loss": 4.2351,
"step": 1169
},
{
"epoch": 2.387755102040816,
"grad_norm": 1.875,
"learning_rate": 7.324263038548753e-05,
"loss": 4.2279,
"step": 1170
},
{
"epoch": 2.389795918367347,
"grad_norm": 1.6796875,
"learning_rate": 7.321023647554261e-05,
"loss": 4.1565,
"step": 1171
},
{
"epoch": 2.3918367346938774,
"grad_norm": 1.890625,
"learning_rate": 7.317784256559768e-05,
"loss": 4.1795,
"step": 1172
},
{
"epoch": 2.3938775510204082,
"grad_norm": 1.9296875,
"learning_rate": 7.314544865565274e-05,
"loss": 4.1396,
"step": 1173
},
{
"epoch": 2.3959183673469386,
"grad_norm": 1.7890625,
"learning_rate": 7.311305474570781e-05,
"loss": 4.3018,
"step": 1174
},
{
"epoch": 2.3979591836734695,
"grad_norm": 2.09375,
"learning_rate": 7.308066083576289e-05,
"loss": 4.1999,
"step": 1175
},
{
"epoch": 2.4,
"grad_norm": 1.8671875,
"learning_rate": 7.304826692581795e-05,
"loss": 4.2324,
"step": 1176
},
{
"epoch": 2.4020408163265308,
"grad_norm": 1.8125,
"learning_rate": 7.301587301587302e-05,
"loss": 4.2292,
"step": 1177
},
{
"epoch": 2.404081632653061,
"grad_norm": 1.7421875,
"learning_rate": 7.298347910592808e-05,
"loss": 4.2312,
"step": 1178
},
{
"epoch": 2.406122448979592,
"grad_norm": 2.0,
"learning_rate": 7.295108519598316e-05,
"loss": 4.3041,
"step": 1179
},
{
"epoch": 2.4081632653061225,
"grad_norm": 2.0625,
"learning_rate": 7.291869128603823e-05,
"loss": 4.1451,
"step": 1180
},
{
"epoch": 2.410204081632653,
"grad_norm": 2.046875,
"learning_rate": 7.28862973760933e-05,
"loss": 4.375,
"step": 1181
},
{
"epoch": 2.4122448979591837,
"grad_norm": 1.78125,
"learning_rate": 7.285390346614836e-05,
"loss": 4.1891,
"step": 1182
},
{
"epoch": 2.414285714285714,
"grad_norm": 1.890625,
"learning_rate": 7.282150955620344e-05,
"loss": 4.169,
"step": 1183
},
{
"epoch": 2.416326530612245,
"grad_norm": 1.7109375,
"learning_rate": 7.27891156462585e-05,
"loss": 4.069,
"step": 1184
},
{
"epoch": 2.4183673469387754,
"grad_norm": 1.71875,
"learning_rate": 7.275672173631357e-05,
"loss": 4.3169,
"step": 1185
},
{
"epoch": 2.4204081632653063,
"grad_norm": 1.8515625,
"learning_rate": 7.272432782636865e-05,
"loss": 4.2691,
"step": 1186
},
{
"epoch": 2.4224489795918367,
"grad_norm": 1.84375,
"learning_rate": 7.269193391642371e-05,
"loss": 4.2444,
"step": 1187
},
{
"epoch": 2.424489795918367,
"grad_norm": 1.75,
"learning_rate": 7.265954000647879e-05,
"loss": 4.2382,
"step": 1188
},
{
"epoch": 2.426530612244898,
"grad_norm": 1.7265625,
"learning_rate": 7.262714609653386e-05,
"loss": 4.1333,
"step": 1189
},
{
"epoch": 2.4285714285714284,
"grad_norm": 1.796875,
"learning_rate": 7.259475218658892e-05,
"loss": 4.2535,
"step": 1190
},
{
"epoch": 2.4306122448979592,
"grad_norm": 1.6640625,
"learning_rate": 7.256235827664399e-05,
"loss": 4.325,
"step": 1191
},
{
"epoch": 2.4326530612244897,
"grad_norm": 1.796875,
"learning_rate": 7.252996436669907e-05,
"loss": 4.2599,
"step": 1192
},
{
"epoch": 2.4346938775510205,
"grad_norm": 1.9375,
"learning_rate": 7.249757045675413e-05,
"loss": 4.2822,
"step": 1193
},
{
"epoch": 2.436734693877551,
"grad_norm": 1.828125,
"learning_rate": 7.24651765468092e-05,
"loss": 4.1882,
"step": 1194
},
{
"epoch": 2.438775510204082,
"grad_norm": 1.75,
"learning_rate": 7.243278263686427e-05,
"loss": 4.1496,
"step": 1195
},
{
"epoch": 2.440816326530612,
"grad_norm": 1.6484375,
"learning_rate": 7.240038872691934e-05,
"loss": 4.1195,
"step": 1196
},
{
"epoch": 2.442857142857143,
"grad_norm": 1.796875,
"learning_rate": 7.236799481697441e-05,
"loss": 4.0929,
"step": 1197
},
{
"epoch": 2.4448979591836735,
"grad_norm": 1.6015625,
"learning_rate": 7.233560090702948e-05,
"loss": 4.1763,
"step": 1198
},
{
"epoch": 2.446938775510204,
"grad_norm": 1.765625,
"learning_rate": 7.230320699708455e-05,
"loss": 4.2162,
"step": 1199
},
{
"epoch": 2.4489795918367347,
"grad_norm": 1.671875,
"learning_rate": 7.227081308713962e-05,
"loss": 4.1681,
"step": 1200
},
{
"epoch": 2.451020408163265,
"grad_norm": 1.609375,
"learning_rate": 7.22384191771947e-05,
"loss": 4.1128,
"step": 1201
},
{
"epoch": 2.453061224489796,
"grad_norm": 1.765625,
"learning_rate": 7.220602526724975e-05,
"loss": 4.1233,
"step": 1202
},
{
"epoch": 2.4551020408163264,
"grad_norm": 1.6171875,
"learning_rate": 7.217363135730483e-05,
"loss": 4.1858,
"step": 1203
},
{
"epoch": 2.4571428571428573,
"grad_norm": 1.78125,
"learning_rate": 7.21412374473599e-05,
"loss": 4.1411,
"step": 1204
},
{
"epoch": 2.4591836734693877,
"grad_norm": 1.6875,
"learning_rate": 7.210884353741498e-05,
"loss": 4.1064,
"step": 1205
},
{
"epoch": 2.461224489795918,
"grad_norm": 1.671875,
"learning_rate": 7.207644962747004e-05,
"loss": 4.3317,
"step": 1206
},
{
"epoch": 2.463265306122449,
"grad_norm": 1.90625,
"learning_rate": 7.20440557175251e-05,
"loss": 4.1632,
"step": 1207
},
{
"epoch": 2.4653061224489794,
"grad_norm": 1.984375,
"learning_rate": 7.201166180758017e-05,
"loss": 4.2921,
"step": 1208
},
{
"epoch": 2.4673469387755103,
"grad_norm": 1.6328125,
"learning_rate": 7.197926789763525e-05,
"loss": 4.1569,
"step": 1209
},
{
"epoch": 2.4693877551020407,
"grad_norm": 1.6484375,
"learning_rate": 7.194687398769032e-05,
"loss": 4.2105,
"step": 1210
},
{
"epoch": 2.4714285714285715,
"grad_norm": 1.84375,
"learning_rate": 7.191448007774538e-05,
"loss": 4.2421,
"step": 1211
},
{
"epoch": 2.473469387755102,
"grad_norm": 1.4765625,
"learning_rate": 7.188208616780046e-05,
"loss": 4.2467,
"step": 1212
},
{
"epoch": 2.475510204081633,
"grad_norm": 2.28125,
"learning_rate": 7.184969225785553e-05,
"loss": 4.179,
"step": 1213
},
{
"epoch": 2.477551020408163,
"grad_norm": 1.828125,
"learning_rate": 7.18172983479106e-05,
"loss": 4.1903,
"step": 1214
},
{
"epoch": 2.479591836734694,
"grad_norm": 1.6875,
"learning_rate": 7.178490443796566e-05,
"loss": 4.2195,
"step": 1215
},
{
"epoch": 2.4816326530612245,
"grad_norm": 2.203125,
"learning_rate": 7.175251052802074e-05,
"loss": 4.167,
"step": 1216
},
{
"epoch": 2.483673469387755,
"grad_norm": 1.765625,
"learning_rate": 7.17201166180758e-05,
"loss": 4.252,
"step": 1217
},
{
"epoch": 2.4857142857142858,
"grad_norm": 1.75,
"learning_rate": 7.168772270813088e-05,
"loss": 4.2026,
"step": 1218
},
{
"epoch": 2.487755102040816,
"grad_norm": 2.234375,
"learning_rate": 7.165532879818595e-05,
"loss": 4.149,
"step": 1219
},
{
"epoch": 2.489795918367347,
"grad_norm": 2.046875,
"learning_rate": 7.162293488824101e-05,
"loss": 4.0355,
"step": 1220
},
{
"epoch": 2.4918367346938775,
"grad_norm": 1.96875,
"learning_rate": 7.159054097829608e-05,
"loss": 4.2366,
"step": 1221
},
{
"epoch": 2.4938775510204083,
"grad_norm": 2.171875,
"learning_rate": 7.155814706835116e-05,
"loss": 4.1593,
"step": 1222
},
{
"epoch": 2.4959183673469387,
"grad_norm": 1.6953125,
"learning_rate": 7.152575315840622e-05,
"loss": 4.1907,
"step": 1223
},
{
"epoch": 2.497959183673469,
"grad_norm": 1.75,
"learning_rate": 7.149335924846129e-05,
"loss": 4.1911,
"step": 1224
},
{
"epoch": 2.5,
"grad_norm": 1.7109375,
"learning_rate": 7.146096533851635e-05,
"loss": 4.3124,
"step": 1225
},
{
"epoch": 2.502040816326531,
"grad_norm": 1.6640625,
"learning_rate": 7.142857142857143e-05,
"loss": 4.1293,
"step": 1226
},
{
"epoch": 2.5040816326530613,
"grad_norm": 1.6328125,
"learning_rate": 7.13961775186265e-05,
"loss": 4.1912,
"step": 1227
},
{
"epoch": 2.5061224489795917,
"grad_norm": 2.0,
"learning_rate": 7.136378360868157e-05,
"loss": 4.1663,
"step": 1228
},
{
"epoch": 2.5081632653061225,
"grad_norm": 1.7421875,
"learning_rate": 7.133138969873664e-05,
"loss": 4.1641,
"step": 1229
},
{
"epoch": 2.510204081632653,
"grad_norm": 1.671875,
"learning_rate": 7.129899578879171e-05,
"loss": 4.1785,
"step": 1230
},
{
"epoch": 2.512244897959184,
"grad_norm": 1.734375,
"learning_rate": 7.126660187884679e-05,
"loss": 4.235,
"step": 1231
},
{
"epoch": 2.5142857142857142,
"grad_norm": 1.7421875,
"learning_rate": 7.123420796890184e-05,
"loss": 4.256,
"step": 1232
},
{
"epoch": 2.516326530612245,
"grad_norm": 1.9140625,
"learning_rate": 7.120181405895692e-05,
"loss": 4.1971,
"step": 1233
},
{
"epoch": 2.5183673469387755,
"grad_norm": 1.7890625,
"learning_rate": 7.116942014901199e-05,
"loss": 4.2035,
"step": 1234
},
{
"epoch": 2.520408163265306,
"grad_norm": 1.6953125,
"learning_rate": 7.113702623906706e-05,
"loss": 4.091,
"step": 1235
},
{
"epoch": 2.522448979591837,
"grad_norm": 1.9140625,
"learning_rate": 7.110463232912213e-05,
"loss": 4.1941,
"step": 1236
},
{
"epoch": 2.524489795918367,
"grad_norm": 2.0,
"learning_rate": 7.10722384191772e-05,
"loss": 4.15,
"step": 1237
},
{
"epoch": 2.526530612244898,
"grad_norm": 1.59375,
"learning_rate": 7.103984450923226e-05,
"loss": 4.1773,
"step": 1238
},
{
"epoch": 2.5285714285714285,
"grad_norm": 1.734375,
"learning_rate": 7.100745059928734e-05,
"loss": 4.0427,
"step": 1239
},
{
"epoch": 2.5306122448979593,
"grad_norm": 1.9609375,
"learning_rate": 7.09750566893424e-05,
"loss": 4.1933,
"step": 1240
},
{
"epoch": 2.5326530612244897,
"grad_norm": 1.625,
"learning_rate": 7.094266277939747e-05,
"loss": 4.1369,
"step": 1241
},
{
"epoch": 2.53469387755102,
"grad_norm": 1.9375,
"learning_rate": 7.091026886945255e-05,
"loss": 4.1467,
"step": 1242
},
{
"epoch": 2.536734693877551,
"grad_norm": 1.640625,
"learning_rate": 7.087787495950762e-05,
"loss": 4.1172,
"step": 1243
},
{
"epoch": 2.538775510204082,
"grad_norm": 1.9140625,
"learning_rate": 7.08454810495627e-05,
"loss": 4.1003,
"step": 1244
},
{
"epoch": 2.5408163265306123,
"grad_norm": 1.7734375,
"learning_rate": 7.081308713961775e-05,
"loss": 4.1787,
"step": 1245
},
{
"epoch": 2.5428571428571427,
"grad_norm": 1.7734375,
"learning_rate": 7.078069322967283e-05,
"loss": 4.144,
"step": 1246
},
{
"epoch": 2.5448979591836736,
"grad_norm": 1.8046875,
"learning_rate": 7.074829931972789e-05,
"loss": 4.1095,
"step": 1247
},
{
"epoch": 2.546938775510204,
"grad_norm": 1.75,
"learning_rate": 7.071590540978297e-05,
"loss": 4.0303,
"step": 1248
},
{
"epoch": 2.548979591836735,
"grad_norm": 1.8046875,
"learning_rate": 7.068351149983802e-05,
"loss": 4.163,
"step": 1249
},
{
"epoch": 2.5510204081632653,
"grad_norm": 2.109375,
"learning_rate": 7.06511175898931e-05,
"loss": 4.1751,
"step": 1250
},
{
"epoch": 2.553061224489796,
"grad_norm": 1.71875,
"learning_rate": 7.061872367994817e-05,
"loss": 4.1379,
"step": 1251
},
{
"epoch": 2.5551020408163265,
"grad_norm": 1.9921875,
"learning_rate": 7.058632977000325e-05,
"loss": 4.1562,
"step": 1252
},
{
"epoch": 2.557142857142857,
"grad_norm": 1.65625,
"learning_rate": 7.055393586005831e-05,
"loss": 4.0126,
"step": 1253
},
{
"epoch": 2.559183673469388,
"grad_norm": 1.8046875,
"learning_rate": 7.052154195011338e-05,
"loss": 4.1517,
"step": 1254
},
{
"epoch": 2.561224489795918,
"grad_norm": 1.84375,
"learning_rate": 7.048914804016846e-05,
"loss": 4.0808,
"step": 1255
},
{
"epoch": 2.563265306122449,
"grad_norm": 1.8671875,
"learning_rate": 7.045675413022352e-05,
"loss": 4.2167,
"step": 1256
},
{
"epoch": 2.5653061224489795,
"grad_norm": 1.8671875,
"learning_rate": 7.04243602202786e-05,
"loss": 4.203,
"step": 1257
},
{
"epoch": 2.5673469387755103,
"grad_norm": 1.8046875,
"learning_rate": 7.039196631033365e-05,
"loss": 4.1736,
"step": 1258
},
{
"epoch": 2.5693877551020408,
"grad_norm": 1.9765625,
"learning_rate": 7.035957240038873e-05,
"loss": 4.1056,
"step": 1259
},
{
"epoch": 2.571428571428571,
"grad_norm": 1.5703125,
"learning_rate": 7.03271784904438e-05,
"loss": 4.2005,
"step": 1260
},
{
"epoch": 2.573469387755102,
"grad_norm": 1.6484375,
"learning_rate": 7.029478458049888e-05,
"loss": 4.061,
"step": 1261
},
{
"epoch": 2.575510204081633,
"grad_norm": 1.8515625,
"learning_rate": 7.026239067055393e-05,
"loss": 4.1177,
"step": 1262
},
{
"epoch": 2.5775510204081633,
"grad_norm": 1.7734375,
"learning_rate": 7.022999676060901e-05,
"loss": 4.1006,
"step": 1263
},
{
"epoch": 2.5795918367346937,
"grad_norm": 1.90625,
"learning_rate": 7.019760285066407e-05,
"loss": 4.2119,
"step": 1264
},
{
"epoch": 2.5816326530612246,
"grad_norm": 1.8359375,
"learning_rate": 7.016520894071915e-05,
"loss": 4.2441,
"step": 1265
},
{
"epoch": 2.583673469387755,
"grad_norm": 1.84375,
"learning_rate": 7.01328150307742e-05,
"loss": 4.2145,
"step": 1266
},
{
"epoch": 2.585714285714286,
"grad_norm": 1.6875,
"learning_rate": 7.010042112082929e-05,
"loss": 4.1519,
"step": 1267
},
{
"epoch": 2.5877551020408163,
"grad_norm": 1.7578125,
"learning_rate": 7.006802721088435e-05,
"loss": 4.214,
"step": 1268
},
{
"epoch": 2.589795918367347,
"grad_norm": 1.8671875,
"learning_rate": 7.003563330093943e-05,
"loss": 4.06,
"step": 1269
},
{
"epoch": 2.5918367346938775,
"grad_norm": 1.9140625,
"learning_rate": 7.00032393909945e-05,
"loss": 4.2084,
"step": 1270
},
{
"epoch": 2.593877551020408,
"grad_norm": 1.8125,
"learning_rate": 6.997084548104956e-05,
"loss": 4.1669,
"step": 1271
},
{
"epoch": 2.595918367346939,
"grad_norm": 2.046875,
"learning_rate": 6.993845157110464e-05,
"loss": 4.1428,
"step": 1272
},
{
"epoch": 2.5979591836734692,
"grad_norm": 1.7578125,
"learning_rate": 6.99060576611597e-05,
"loss": 4.2427,
"step": 1273
},
{
"epoch": 2.6,
"grad_norm": 1.75,
"learning_rate": 6.987366375121478e-05,
"loss": 4.1758,
"step": 1274
},
{
"epoch": 2.6020408163265305,
"grad_norm": 1.8125,
"learning_rate": 6.984126984126984e-05,
"loss": 4.1984,
"step": 1275
},
{
"epoch": 2.6040816326530614,
"grad_norm": 1.9140625,
"learning_rate": 6.980887593132492e-05,
"loss": 4.0204,
"step": 1276
},
{
"epoch": 2.6061224489795918,
"grad_norm": 1.6796875,
"learning_rate": 6.977648202137998e-05,
"loss": 4.0882,
"step": 1277
},
{
"epoch": 2.608163265306122,
"grad_norm": 1.5078125,
"learning_rate": 6.974408811143506e-05,
"loss": 4.0657,
"step": 1278
},
{
"epoch": 2.610204081632653,
"grad_norm": 1.5234375,
"learning_rate": 6.971169420149011e-05,
"loss": 4.0665,
"step": 1279
},
{
"epoch": 2.612244897959184,
"grad_norm": 1.75,
"learning_rate": 6.967930029154519e-05,
"loss": 4.2238,
"step": 1280
},
{
"epoch": 2.6142857142857143,
"grad_norm": 1.6328125,
"learning_rate": 6.964690638160026e-05,
"loss": 4.18,
"step": 1281
},
{
"epoch": 2.6163265306122447,
"grad_norm": 1.7578125,
"learning_rate": 6.961451247165534e-05,
"loss": 4.1619,
"step": 1282
},
{
"epoch": 2.6183673469387756,
"grad_norm": 2.046875,
"learning_rate": 6.95821185617104e-05,
"loss": 4.1817,
"step": 1283
},
{
"epoch": 2.620408163265306,
"grad_norm": 1.71875,
"learning_rate": 6.954972465176547e-05,
"loss": 4.1065,
"step": 1284
},
{
"epoch": 2.622448979591837,
"grad_norm": 1.8203125,
"learning_rate": 6.951733074182055e-05,
"loss": 4.124,
"step": 1285
},
{
"epoch": 2.6244897959183673,
"grad_norm": 1.7890625,
"learning_rate": 6.948493683187561e-05,
"loss": 4.1385,
"step": 1286
},
{
"epoch": 2.626530612244898,
"grad_norm": 1.7578125,
"learning_rate": 6.945254292193069e-05,
"loss": 4.0894,
"step": 1287
},
{
"epoch": 2.6285714285714286,
"grad_norm": 1.5546875,
"learning_rate": 6.942014901198574e-05,
"loss": 4.055,
"step": 1288
},
{
"epoch": 2.630612244897959,
"grad_norm": 1.6953125,
"learning_rate": 6.938775510204082e-05,
"loss": 4.1706,
"step": 1289
},
{
"epoch": 2.63265306122449,
"grad_norm": 1.765625,
"learning_rate": 6.935536119209589e-05,
"loss": 4.0605,
"step": 1290
},
{
"epoch": 2.6346938775510202,
"grad_norm": 1.6953125,
"learning_rate": 6.932296728215097e-05,
"loss": 4.2112,
"step": 1291
},
{
"epoch": 2.636734693877551,
"grad_norm": 1.609375,
"learning_rate": 6.929057337220602e-05,
"loss": 4.024,
"step": 1292
},
{
"epoch": 2.6387755102040815,
"grad_norm": 1.609375,
"learning_rate": 6.92581794622611e-05,
"loss": 4.0457,
"step": 1293
},
{
"epoch": 2.6408163265306124,
"grad_norm": 1.6328125,
"learning_rate": 6.922578555231616e-05,
"loss": 4.2136,
"step": 1294
},
{
"epoch": 2.642857142857143,
"grad_norm": 1.6953125,
"learning_rate": 6.919339164237124e-05,
"loss": 4.02,
"step": 1295
},
{
"epoch": 2.644897959183673,
"grad_norm": 1.8359375,
"learning_rate": 6.916099773242631e-05,
"loss": 4.0376,
"step": 1296
},
{
"epoch": 2.646938775510204,
"grad_norm": 1.8203125,
"learning_rate": 6.912860382248137e-05,
"loss": 4.1891,
"step": 1297
},
{
"epoch": 2.648979591836735,
"grad_norm": 1.9453125,
"learning_rate": 6.909620991253645e-05,
"loss": 4.1496,
"step": 1298
},
{
"epoch": 2.6510204081632653,
"grad_norm": 1.71875,
"learning_rate": 6.906381600259152e-05,
"loss": 4.1239,
"step": 1299
},
{
"epoch": 2.6530612244897958,
"grad_norm": 1.828125,
"learning_rate": 6.903142209264658e-05,
"loss": 4.1085,
"step": 1300
},
{
"epoch": 2.6551020408163266,
"grad_norm": 1.4609375,
"learning_rate": 6.899902818270165e-05,
"loss": 4.1451,
"step": 1301
},
{
"epoch": 2.657142857142857,
"grad_norm": 1.796875,
"learning_rate": 6.896663427275673e-05,
"loss": 4.1994,
"step": 1302
},
{
"epoch": 2.659183673469388,
"grad_norm": 1.6953125,
"learning_rate": 6.89342403628118e-05,
"loss": 4.1493,
"step": 1303
},
{
"epoch": 2.6612244897959183,
"grad_norm": 1.6953125,
"learning_rate": 6.890184645286687e-05,
"loss": 4.0935,
"step": 1304
},
{
"epoch": 2.663265306122449,
"grad_norm": 1.6640625,
"learning_rate": 6.886945254292193e-05,
"loss": 4.1052,
"step": 1305
},
{
"epoch": 2.6653061224489796,
"grad_norm": 1.7578125,
"learning_rate": 6.8837058632977e-05,
"loss": 4.2225,
"step": 1306
},
{
"epoch": 2.66734693877551,
"grad_norm": 1.84375,
"learning_rate": 6.880466472303207e-05,
"loss": 4.1516,
"step": 1307
},
{
"epoch": 2.669387755102041,
"grad_norm": 1.640625,
"learning_rate": 6.877227081308715e-05,
"loss": 4.097,
"step": 1308
},
{
"epoch": 2.6714285714285713,
"grad_norm": 1.5546875,
"learning_rate": 6.87398769031422e-05,
"loss": 4.2107,
"step": 1309
},
{
"epoch": 2.673469387755102,
"grad_norm": 1.8203125,
"learning_rate": 6.870748299319728e-05,
"loss": 4.0556,
"step": 1310
},
{
"epoch": 2.6755102040816325,
"grad_norm": 1.7265625,
"learning_rate": 6.867508908325235e-05,
"loss": 4.1359,
"step": 1311
},
{
"epoch": 2.6775510204081634,
"grad_norm": 1.7734375,
"learning_rate": 6.864269517330743e-05,
"loss": 4.1303,
"step": 1312
},
{
"epoch": 2.679591836734694,
"grad_norm": 1.78125,
"learning_rate": 6.861030126336249e-05,
"loss": 4.0265,
"step": 1313
},
{
"epoch": 2.6816326530612242,
"grad_norm": 1.7578125,
"learning_rate": 6.857790735341756e-05,
"loss": 4.1672,
"step": 1314
},
{
"epoch": 2.683673469387755,
"grad_norm": 1.75,
"learning_rate": 6.854551344347264e-05,
"loss": 4.1208,
"step": 1315
},
{
"epoch": 2.685714285714286,
"grad_norm": 1.6484375,
"learning_rate": 6.85131195335277e-05,
"loss": 4.0832,
"step": 1316
},
{
"epoch": 2.6877551020408164,
"grad_norm": 1.8125,
"learning_rate": 6.848072562358277e-05,
"loss": 4.1623,
"step": 1317
},
{
"epoch": 2.6897959183673468,
"grad_norm": 1.6484375,
"learning_rate": 6.844833171363783e-05,
"loss": 4.0214,
"step": 1318
},
{
"epoch": 2.6918367346938776,
"grad_norm": 1.7421875,
"learning_rate": 6.841593780369291e-05,
"loss": 4.1563,
"step": 1319
},
{
"epoch": 2.693877551020408,
"grad_norm": 1.5859375,
"learning_rate": 6.838354389374798e-05,
"loss": 4.1611,
"step": 1320
},
{
"epoch": 2.695918367346939,
"grad_norm": 1.6484375,
"learning_rate": 6.835114998380306e-05,
"loss": 4.1354,
"step": 1321
},
{
"epoch": 2.6979591836734693,
"grad_norm": 1.7890625,
"learning_rate": 6.831875607385811e-05,
"loss": 4.0363,
"step": 1322
},
{
"epoch": 2.7,
"grad_norm": 1.84375,
"learning_rate": 6.828636216391319e-05,
"loss": 4.1147,
"step": 1323
},
{
"epoch": 2.7020408163265306,
"grad_norm": 1.65625,
"learning_rate": 6.825396825396825e-05,
"loss": 4.1469,
"step": 1324
},
{
"epoch": 2.704081632653061,
"grad_norm": 2.015625,
"learning_rate": 6.822157434402333e-05,
"loss": 4.0486,
"step": 1325
},
{
"epoch": 2.706122448979592,
"grad_norm": 1.765625,
"learning_rate": 6.81891804340784e-05,
"loss": 4.1049,
"step": 1326
},
{
"epoch": 2.7081632653061227,
"grad_norm": 1.6953125,
"learning_rate": 6.815678652413346e-05,
"loss": 4.0912,
"step": 1327
},
{
"epoch": 2.710204081632653,
"grad_norm": 2.0,
"learning_rate": 6.812439261418854e-05,
"loss": 4.0403,
"step": 1328
},
{
"epoch": 2.7122448979591836,
"grad_norm": 1.8359375,
"learning_rate": 6.809199870424361e-05,
"loss": 4.0231,
"step": 1329
},
{
"epoch": 2.7142857142857144,
"grad_norm": 1.6953125,
"learning_rate": 6.805960479429867e-05,
"loss": 4.1423,
"step": 1330
},
{
"epoch": 2.716326530612245,
"grad_norm": 1.890625,
"learning_rate": 6.802721088435374e-05,
"loss": 4.2771,
"step": 1331
},
{
"epoch": 2.7183673469387752,
"grad_norm": 1.703125,
"learning_rate": 6.799481697440882e-05,
"loss": 3.9857,
"step": 1332
},
{
"epoch": 2.720408163265306,
"grad_norm": 1.8515625,
"learning_rate": 6.796242306446388e-05,
"loss": 4.0519,
"step": 1333
},
{
"epoch": 2.722448979591837,
"grad_norm": 1.8125,
"learning_rate": 6.793002915451895e-05,
"loss": 4.0942,
"step": 1334
},
{
"epoch": 2.7244897959183674,
"grad_norm": 1.7890625,
"learning_rate": 6.789763524457402e-05,
"loss": 4.095,
"step": 1335
},
{
"epoch": 2.726530612244898,
"grad_norm": 1.9140625,
"learning_rate": 6.78652413346291e-05,
"loss": 4.0242,
"step": 1336
},
{
"epoch": 2.7285714285714286,
"grad_norm": 1.7421875,
"learning_rate": 6.783284742468416e-05,
"loss": 4.0388,
"step": 1337
},
{
"epoch": 2.730612244897959,
"grad_norm": 1.65625,
"learning_rate": 6.780045351473924e-05,
"loss": 4.0854,
"step": 1338
},
{
"epoch": 2.73265306122449,
"grad_norm": 1.859375,
"learning_rate": 6.77680596047943e-05,
"loss": 4.1267,
"step": 1339
},
{
"epoch": 2.7346938775510203,
"grad_norm": 1.5546875,
"learning_rate": 6.773566569484937e-05,
"loss": 4.0877,
"step": 1340
},
{
"epoch": 2.736734693877551,
"grad_norm": 1.59375,
"learning_rate": 6.770327178490445e-05,
"loss": 4.0559,
"step": 1341
},
{
"epoch": 2.7387755102040816,
"grad_norm": 1.6015625,
"learning_rate": 6.767087787495952e-05,
"loss": 4.0277,
"step": 1342
},
{
"epoch": 2.740816326530612,
"grad_norm": 1.703125,
"learning_rate": 6.763848396501458e-05,
"loss": 4.066,
"step": 1343
},
{
"epoch": 2.742857142857143,
"grad_norm": 1.796875,
"learning_rate": 6.760609005506965e-05,
"loss": 4.1804,
"step": 1344
},
{
"epoch": 2.7448979591836737,
"grad_norm": 1.6171875,
"learning_rate": 6.757369614512473e-05,
"loss": 4.0293,
"step": 1345
},
{
"epoch": 2.746938775510204,
"grad_norm": 2.125,
"learning_rate": 6.754130223517979e-05,
"loss": 4.1689,
"step": 1346
},
{
"epoch": 2.7489795918367346,
"grad_norm": 1.71875,
"learning_rate": 6.750890832523486e-05,
"loss": 4.036,
"step": 1347
},
{
"epoch": 2.7510204081632654,
"grad_norm": 1.921875,
"learning_rate": 6.747651441528992e-05,
"loss": 4.1353,
"step": 1348
},
{
"epoch": 2.753061224489796,
"grad_norm": 1.5703125,
"learning_rate": 6.7444120505345e-05,
"loss": 4.0922,
"step": 1349
},
{
"epoch": 2.7551020408163263,
"grad_norm": 1.8359375,
"learning_rate": 6.741172659540007e-05,
"loss": 4.126,
"step": 1350
},
{
"epoch": 2.757142857142857,
"grad_norm": 1.5625,
"learning_rate": 6.737933268545515e-05,
"loss": 4.1688,
"step": 1351
},
{
"epoch": 2.759183673469388,
"grad_norm": 1.6328125,
"learning_rate": 6.73469387755102e-05,
"loss": 3.9783,
"step": 1352
},
{
"epoch": 2.7612244897959184,
"grad_norm": 1.78125,
"learning_rate": 6.731454486556528e-05,
"loss": 3.9786,
"step": 1353
},
{
"epoch": 2.763265306122449,
"grad_norm": 1.71875,
"learning_rate": 6.728215095562034e-05,
"loss": 4.0809,
"step": 1354
},
{
"epoch": 2.7653061224489797,
"grad_norm": 1.6875,
"learning_rate": 6.724975704567542e-05,
"loss": 4.0654,
"step": 1355
},
{
"epoch": 2.76734693877551,
"grad_norm": 1.6484375,
"learning_rate": 6.721736313573049e-05,
"loss": 4.0846,
"step": 1356
},
{
"epoch": 2.769387755102041,
"grad_norm": 1.6640625,
"learning_rate": 6.718496922578555e-05,
"loss": 3.9995,
"step": 1357
},
{
"epoch": 2.7714285714285714,
"grad_norm": 1.6484375,
"learning_rate": 6.715257531584063e-05,
"loss": 4.1032,
"step": 1358
},
{
"epoch": 2.773469387755102,
"grad_norm": 1.78125,
"learning_rate": 6.71201814058957e-05,
"loss": 4.1243,
"step": 1359
},
{
"epoch": 2.7755102040816326,
"grad_norm": 1.6875,
"learning_rate": 6.708778749595076e-05,
"loss": 4.1856,
"step": 1360
},
{
"epoch": 2.777551020408163,
"grad_norm": 1.7421875,
"learning_rate": 6.705539358600583e-05,
"loss": 4.1611,
"step": 1361
},
{
"epoch": 2.779591836734694,
"grad_norm": 1.5546875,
"learning_rate": 6.702299967606091e-05,
"loss": 4.1322,
"step": 1362
},
{
"epoch": 2.7816326530612248,
"grad_norm": 1.6484375,
"learning_rate": 6.699060576611597e-05,
"loss": 4.1502,
"step": 1363
},
{
"epoch": 2.783673469387755,
"grad_norm": 1.875,
"learning_rate": 6.695821185617104e-05,
"loss": 4.1082,
"step": 1364
},
{
"epoch": 2.7857142857142856,
"grad_norm": 1.7265625,
"learning_rate": 6.69258179462261e-05,
"loss": 4.0393,
"step": 1365
},
{
"epoch": 2.7877551020408164,
"grad_norm": 1.84375,
"learning_rate": 6.689342403628118e-05,
"loss": 4.1083,
"step": 1366
},
{
"epoch": 2.789795918367347,
"grad_norm": 1.6953125,
"learning_rate": 6.686103012633625e-05,
"loss": 4.1162,
"step": 1367
},
{
"epoch": 2.7918367346938773,
"grad_norm": 1.796875,
"learning_rate": 6.682863621639133e-05,
"loss": 4.1943,
"step": 1368
},
{
"epoch": 2.793877551020408,
"grad_norm": 1.6171875,
"learning_rate": 6.67962423064464e-05,
"loss": 4.0067,
"step": 1369
},
{
"epoch": 2.795918367346939,
"grad_norm": 1.7421875,
"learning_rate": 6.676384839650146e-05,
"loss": 4.0821,
"step": 1370
},
{
"epoch": 2.7979591836734694,
"grad_norm": 1.734375,
"learning_rate": 6.673145448655654e-05,
"loss": 4.1228,
"step": 1371
},
{
"epoch": 2.8,
"grad_norm": 1.5625,
"learning_rate": 6.66990605766116e-05,
"loss": 4.0097,
"step": 1372
},
{
"epoch": 2.8020408163265307,
"grad_norm": 1.7890625,
"learning_rate": 6.666666666666667e-05,
"loss": 4.0162,
"step": 1373
},
{
"epoch": 2.804081632653061,
"grad_norm": 1.625,
"learning_rate": 6.663427275672174e-05,
"loss": 4.1394,
"step": 1374
},
{
"epoch": 2.806122448979592,
"grad_norm": 1.8671875,
"learning_rate": 6.660187884677681e-05,
"loss": 4.0067,
"step": 1375
},
{
"epoch": 2.8081632653061224,
"grad_norm": 1.6328125,
"learning_rate": 6.656948493683188e-05,
"loss": 4.1297,
"step": 1376
},
{
"epoch": 2.8102040816326532,
"grad_norm": 1.8359375,
"learning_rate": 6.653709102688695e-05,
"loss": 4.1559,
"step": 1377
},
{
"epoch": 2.8122448979591836,
"grad_norm": 1.75,
"learning_rate": 6.650469711694201e-05,
"loss": 4.0884,
"step": 1378
},
{
"epoch": 2.814285714285714,
"grad_norm": 1.6875,
"learning_rate": 6.647230320699709e-05,
"loss": 4.0185,
"step": 1379
},
{
"epoch": 2.816326530612245,
"grad_norm": 1.578125,
"learning_rate": 6.643990929705216e-05,
"loss": 4.0439,
"step": 1380
},
{
"epoch": 2.8183673469387758,
"grad_norm": 1.765625,
"learning_rate": 6.640751538710722e-05,
"loss": 4.1468,
"step": 1381
},
{
"epoch": 2.820408163265306,
"grad_norm": 1.578125,
"learning_rate": 6.63751214771623e-05,
"loss": 4.0969,
"step": 1382
},
{
"epoch": 2.8224489795918366,
"grad_norm": 1.8125,
"learning_rate": 6.634272756721737e-05,
"loss": 3.974,
"step": 1383
},
{
"epoch": 2.8244897959183675,
"grad_norm": 1.8515625,
"learning_rate": 6.631033365727245e-05,
"loss": 4.0772,
"step": 1384
},
{
"epoch": 2.826530612244898,
"grad_norm": 1.734375,
"learning_rate": 6.627793974732751e-05,
"loss": 3.9441,
"step": 1385
},
{
"epoch": 2.8285714285714287,
"grad_norm": 1.6796875,
"learning_rate": 6.624554583738258e-05,
"loss": 4.0557,
"step": 1386
},
{
"epoch": 2.830612244897959,
"grad_norm": 1.734375,
"learning_rate": 6.621315192743764e-05,
"loss": 4.0635,
"step": 1387
},
{
"epoch": 2.83265306122449,
"grad_norm": 1.6328125,
"learning_rate": 6.618075801749272e-05,
"loss": 4.0927,
"step": 1388
},
{
"epoch": 2.8346938775510204,
"grad_norm": 1.5078125,
"learning_rate": 6.614836410754779e-05,
"loss": 4.0129,
"step": 1389
},
{
"epoch": 2.836734693877551,
"grad_norm": 1.640625,
"learning_rate": 6.611597019760285e-05,
"loss": 4.0109,
"step": 1390
},
{
"epoch": 2.8387755102040817,
"grad_norm": 1.7890625,
"learning_rate": 6.608357628765792e-05,
"loss": 4.0952,
"step": 1391
},
{
"epoch": 2.840816326530612,
"grad_norm": 1.6015625,
"learning_rate": 6.6051182377713e-05,
"loss": 4.0377,
"step": 1392
},
{
"epoch": 2.842857142857143,
"grad_norm": 2.125,
"learning_rate": 6.601878846776806e-05,
"loss": 4.1198,
"step": 1393
},
{
"epoch": 2.8448979591836734,
"grad_norm": 1.609375,
"learning_rate": 6.598639455782313e-05,
"loss": 4.0528,
"step": 1394
},
{
"epoch": 2.8469387755102042,
"grad_norm": 1.9765625,
"learning_rate": 6.59540006478782e-05,
"loss": 4.0641,
"step": 1395
},
{
"epoch": 2.8489795918367347,
"grad_norm": 1.9140625,
"learning_rate": 6.592160673793327e-05,
"loss": 3.9933,
"step": 1396
},
{
"epoch": 2.851020408163265,
"grad_norm": 1.4921875,
"learning_rate": 6.588921282798834e-05,
"loss": 4.0936,
"step": 1397
},
{
"epoch": 2.853061224489796,
"grad_norm": 1.921875,
"learning_rate": 6.58568189180434e-05,
"loss": 4.1758,
"step": 1398
},
{
"epoch": 2.855102040816327,
"grad_norm": 1.8046875,
"learning_rate": 6.582442500809848e-05,
"loss": 4.0891,
"step": 1399
},
{
"epoch": 2.857142857142857,
"grad_norm": 1.765625,
"learning_rate": 6.579203109815355e-05,
"loss": 3.9412,
"step": 1400
},
{
"epoch": 2.8591836734693876,
"grad_norm": 1.6953125,
"learning_rate": 6.575963718820863e-05,
"loss": 4.1739,
"step": 1401
},
{
"epoch": 2.8612244897959185,
"grad_norm": 1.8203125,
"learning_rate": 6.57272432782637e-05,
"loss": 4.084,
"step": 1402
},
{
"epoch": 2.863265306122449,
"grad_norm": 1.625,
"learning_rate": 6.569484936831876e-05,
"loss": 4.1516,
"step": 1403
},
{
"epoch": 2.8653061224489798,
"grad_norm": 1.8046875,
"learning_rate": 6.566245545837382e-05,
"loss": 4.0697,
"step": 1404
},
{
"epoch": 2.86734693877551,
"grad_norm": 1.828125,
"learning_rate": 6.56300615484289e-05,
"loss": 3.9902,
"step": 1405
},
{
"epoch": 2.869387755102041,
"grad_norm": 1.7890625,
"learning_rate": 6.559766763848397e-05,
"loss": 4.1368,
"step": 1406
},
{
"epoch": 2.8714285714285714,
"grad_norm": 1.7734375,
"learning_rate": 6.556527372853903e-05,
"loss": 4.0122,
"step": 1407
},
{
"epoch": 2.873469387755102,
"grad_norm": 1.59375,
"learning_rate": 6.55328798185941e-05,
"loss": 4.0806,
"step": 1408
},
{
"epoch": 2.8755102040816327,
"grad_norm": 1.5546875,
"learning_rate": 6.550048590864918e-05,
"loss": 4.009,
"step": 1409
},
{
"epoch": 2.877551020408163,
"grad_norm": 1.7578125,
"learning_rate": 6.546809199870425e-05,
"loss": 3.9207,
"step": 1410
},
{
"epoch": 2.879591836734694,
"grad_norm": 1.734375,
"learning_rate": 6.543569808875931e-05,
"loss": 4.0075,
"step": 1411
},
{
"epoch": 2.8816326530612244,
"grad_norm": 1.6796875,
"learning_rate": 6.540330417881439e-05,
"loss": 4.079,
"step": 1412
},
{
"epoch": 2.8836734693877553,
"grad_norm": 1.7421875,
"learning_rate": 6.537091026886946e-05,
"loss": 3.973,
"step": 1413
},
{
"epoch": 2.8857142857142857,
"grad_norm": 1.6953125,
"learning_rate": 6.533851635892453e-05,
"loss": 4.1295,
"step": 1414
},
{
"epoch": 2.887755102040816,
"grad_norm": 1.75,
"learning_rate": 6.530612244897959e-05,
"loss": 4.1293,
"step": 1415
},
{
"epoch": 2.889795918367347,
"grad_norm": 1.59375,
"learning_rate": 6.527372853903467e-05,
"loss": 4.1797,
"step": 1416
},
{
"epoch": 2.891836734693878,
"grad_norm": 1.8125,
"learning_rate": 6.524133462908973e-05,
"loss": 4.068,
"step": 1417
},
{
"epoch": 2.8938775510204082,
"grad_norm": 1.5859375,
"learning_rate": 6.520894071914481e-05,
"loss": 4.0196,
"step": 1418
},
{
"epoch": 2.8959183673469386,
"grad_norm": 1.8203125,
"learning_rate": 6.517654680919988e-05,
"loss": 4.0543,
"step": 1419
},
{
"epoch": 2.8979591836734695,
"grad_norm": 1.8671875,
"learning_rate": 6.514415289925494e-05,
"loss": 4.1154,
"step": 1420
},
{
"epoch": 2.9,
"grad_norm": 1.7890625,
"learning_rate": 6.511175898931001e-05,
"loss": 4.1853,
"step": 1421
},
{
"epoch": 2.9020408163265308,
"grad_norm": 1.8125,
"learning_rate": 6.507936507936509e-05,
"loss": 3.9837,
"step": 1422
},
{
"epoch": 2.904081632653061,
"grad_norm": 1.765625,
"learning_rate": 6.504697116942015e-05,
"loss": 3.9968,
"step": 1423
},
{
"epoch": 2.906122448979592,
"grad_norm": 1.828125,
"learning_rate": 6.501457725947522e-05,
"loss": 4.0123,
"step": 1424
},
{
"epoch": 2.9081632653061225,
"grad_norm": 1.7890625,
"learning_rate": 6.49821833495303e-05,
"loss": 3.982,
"step": 1425
},
{
"epoch": 2.910204081632653,
"grad_norm": 1.65625,
"learning_rate": 6.494978943958536e-05,
"loss": 4.0876,
"step": 1426
},
{
"epoch": 2.9122448979591837,
"grad_norm": 1.6796875,
"learning_rate": 6.491739552964044e-05,
"loss": 3.9931,
"step": 1427
},
{
"epoch": 2.914285714285714,
"grad_norm": 1.640625,
"learning_rate": 6.48850016196955e-05,
"loss": 3.9378,
"step": 1428
},
{
"epoch": 2.916326530612245,
"grad_norm": 1.6171875,
"learning_rate": 6.485260770975057e-05,
"loss": 4.003,
"step": 1429
},
{
"epoch": 2.9183673469387754,
"grad_norm": 1.6640625,
"learning_rate": 6.482021379980564e-05,
"loss": 4.0363,
"step": 1430
},
{
"epoch": 2.9204081632653063,
"grad_norm": 1.7734375,
"learning_rate": 6.478781988986072e-05,
"loss": 4.2008,
"step": 1431
},
{
"epoch": 2.9224489795918367,
"grad_norm": 1.59375,
"learning_rate": 6.475542597991577e-05,
"loss": 3.9824,
"step": 1432
},
{
"epoch": 2.924489795918367,
"grad_norm": 1.703125,
"learning_rate": 6.472303206997085e-05,
"loss": 4.0711,
"step": 1433
},
{
"epoch": 2.926530612244898,
"grad_norm": 1.6953125,
"learning_rate": 6.469063816002591e-05,
"loss": 3.9777,
"step": 1434
},
{
"epoch": 2.928571428571429,
"grad_norm": 1.4375,
"learning_rate": 6.465824425008099e-05,
"loss": 4.0181,
"step": 1435
},
{
"epoch": 2.9306122448979592,
"grad_norm": 1.828125,
"learning_rate": 6.462585034013606e-05,
"loss": 3.9961,
"step": 1436
},
{
"epoch": 2.9326530612244897,
"grad_norm": 1.5,
"learning_rate": 6.459345643019112e-05,
"loss": 4.0267,
"step": 1437
},
{
"epoch": 2.9346938775510205,
"grad_norm": 1.6640625,
"learning_rate": 6.456106252024619e-05,
"loss": 4.0973,
"step": 1438
},
{
"epoch": 2.936734693877551,
"grad_norm": 1.6328125,
"learning_rate": 6.452866861030127e-05,
"loss": 4.1208,
"step": 1439
},
{
"epoch": 2.938775510204082,
"grad_norm": 1.75,
"learning_rate": 6.449627470035633e-05,
"loss": 4.0061,
"step": 1440
},
{
"epoch": 2.940816326530612,
"grad_norm": 1.8359375,
"learning_rate": 6.44638807904114e-05,
"loss": 4.0582,
"step": 1441
},
{
"epoch": 2.942857142857143,
"grad_norm": 1.9921875,
"learning_rate": 6.443148688046648e-05,
"loss": 4.1433,
"step": 1442
},
{
"epoch": 2.9448979591836735,
"grad_norm": 1.921875,
"learning_rate": 6.439909297052154e-05,
"loss": 4.0633,
"step": 1443
},
{
"epoch": 2.946938775510204,
"grad_norm": 1.671875,
"learning_rate": 6.436669906057662e-05,
"loss": 4.0253,
"step": 1444
},
{
"epoch": 2.9489795918367347,
"grad_norm": 1.7421875,
"learning_rate": 6.433430515063168e-05,
"loss": 4.1278,
"step": 1445
},
{
"epoch": 2.951020408163265,
"grad_norm": 2.1875,
"learning_rate": 6.430191124068676e-05,
"loss": 4.1774,
"step": 1446
},
{
"epoch": 2.953061224489796,
"grad_norm": 1.78125,
"learning_rate": 6.426951733074182e-05,
"loss": 4.0848,
"step": 1447
},
{
"epoch": 2.9551020408163264,
"grad_norm": 1.8515625,
"learning_rate": 6.42371234207969e-05,
"loss": 4.0593,
"step": 1448
},
{
"epoch": 2.9571428571428573,
"grad_norm": 1.7109375,
"learning_rate": 6.420472951085195e-05,
"loss": 4.0219,
"step": 1449
},
{
"epoch": 2.9591836734693877,
"grad_norm": 1.6328125,
"learning_rate": 6.417233560090703e-05,
"loss": 3.9959,
"step": 1450
},
{
"epoch": 2.961224489795918,
"grad_norm": 1.7421875,
"learning_rate": 6.41399416909621e-05,
"loss": 3.94,
"step": 1451
},
{
"epoch": 2.963265306122449,
"grad_norm": 1.609375,
"learning_rate": 6.410754778101718e-05,
"loss": 4.01,
"step": 1452
},
{
"epoch": 2.96530612244898,
"grad_norm": 1.453125,
"learning_rate": 6.407515387107224e-05,
"loss": 4.0706,
"step": 1453
},
{
"epoch": 2.9673469387755103,
"grad_norm": 1.6875,
"learning_rate": 6.40427599611273e-05,
"loss": 4.0636,
"step": 1454
},
{
"epoch": 2.9693877551020407,
"grad_norm": 1.4609375,
"learning_rate": 6.401036605118239e-05,
"loss": 4.0435,
"step": 1455
},
{
"epoch": 2.9714285714285715,
"grad_norm": 1.5234375,
"learning_rate": 6.397797214123745e-05,
"loss": 3.9866,
"step": 1456
},
{
"epoch": 2.973469387755102,
"grad_norm": 1.4765625,
"learning_rate": 6.394557823129253e-05,
"loss": 4.0314,
"step": 1457
},
{
"epoch": 2.975510204081633,
"grad_norm": 1.7265625,
"learning_rate": 6.391318432134758e-05,
"loss": 3.9391,
"step": 1458
},
{
"epoch": 2.977551020408163,
"grad_norm": 1.6875,
"learning_rate": 6.388079041140266e-05,
"loss": 4.0971,
"step": 1459
},
{
"epoch": 2.979591836734694,
"grad_norm": 1.65625,
"learning_rate": 6.384839650145773e-05,
"loss": 4.0204,
"step": 1460
},
{
"epoch": 2.9816326530612245,
"grad_norm": 1.609375,
"learning_rate": 6.38160025915128e-05,
"loss": 4.0229,
"step": 1461
},
{
"epoch": 2.983673469387755,
"grad_norm": 1.6796875,
"learning_rate": 6.378360868156786e-05,
"loss": 4.1219,
"step": 1462
},
{
"epoch": 2.9857142857142858,
"grad_norm": 1.6015625,
"learning_rate": 6.375121477162294e-05,
"loss": 4.089,
"step": 1463
},
{
"epoch": 2.987755102040816,
"grad_norm": 1.5625,
"learning_rate": 6.3718820861678e-05,
"loss": 4.0221,
"step": 1464
},
{
"epoch": 2.989795918367347,
"grad_norm": 1.7734375,
"learning_rate": 6.368642695173308e-05,
"loss": 4.0416,
"step": 1465
},
{
"epoch": 2.9918367346938775,
"grad_norm": 1.8046875,
"learning_rate": 6.365403304178815e-05,
"loss": 4.0376,
"step": 1466
},
{
"epoch": 2.9938775510204083,
"grad_norm": 2.046875,
"learning_rate": 6.362163913184321e-05,
"loss": 3.9165,
"step": 1467
},
{
"epoch": 2.9959183673469387,
"grad_norm": 1.796875,
"learning_rate": 6.358924522189829e-05,
"loss": 4.0583,
"step": 1468
},
{
"epoch": 2.997959183673469,
"grad_norm": 1.90625,
"learning_rate": 6.355685131195336e-05,
"loss": 4.0083,
"step": 1469
},
{
"epoch": 3.0,
"grad_norm": 1.640625,
"learning_rate": 6.352445740200842e-05,
"loss": 4.1371,
"step": 1470
},
{
"epoch": 3.0020408163265304,
"grad_norm": 1.9921875,
"learning_rate": 6.349206349206349e-05,
"loss": 3.8164,
"step": 1471
},
{
"epoch": 3.0040816326530613,
"grad_norm": 2.34375,
"learning_rate": 6.345966958211857e-05,
"loss": 3.5484,
"step": 1472
},
{
"epoch": 3.0061224489795917,
"grad_norm": 2.265625,
"learning_rate": 6.342727567217363e-05,
"loss": 3.6043,
"step": 1473
},
{
"epoch": 3.0081632653061225,
"grad_norm": 2.046875,
"learning_rate": 6.339488176222871e-05,
"loss": 3.6104,
"step": 1474
},
{
"epoch": 3.010204081632653,
"grad_norm": 2.21875,
"learning_rate": 6.336248785228377e-05,
"loss": 3.4885,
"step": 1475
},
{
"epoch": 3.012244897959184,
"grad_norm": 2.0,
"learning_rate": 6.333009394233884e-05,
"loss": 3.6444,
"step": 1476
},
{
"epoch": 3.0142857142857142,
"grad_norm": 2.09375,
"learning_rate": 6.329770003239391e-05,
"loss": 3.4262,
"step": 1477
},
{
"epoch": 3.016326530612245,
"grad_norm": 2.0625,
"learning_rate": 6.326530612244899e-05,
"loss": 3.5901,
"step": 1478
},
{
"epoch": 3.0183673469387755,
"grad_norm": 2.09375,
"learning_rate": 6.323291221250404e-05,
"loss": 3.7082,
"step": 1479
},
{
"epoch": 3.020408163265306,
"grad_norm": 2.203125,
"learning_rate": 6.320051830255912e-05,
"loss": 3.6041,
"step": 1480
},
{
"epoch": 3.022448979591837,
"grad_norm": 2.03125,
"learning_rate": 6.316812439261419e-05,
"loss": 3.611,
"step": 1481
},
{
"epoch": 3.024489795918367,
"grad_norm": 1.71875,
"learning_rate": 6.313573048266926e-05,
"loss": 3.4937,
"step": 1482
},
{
"epoch": 3.026530612244898,
"grad_norm": 2.484375,
"learning_rate": 6.310333657272433e-05,
"loss": 3.6775,
"step": 1483
},
{
"epoch": 3.0285714285714285,
"grad_norm": 2.296875,
"learning_rate": 6.30709426627794e-05,
"loss": 3.6023,
"step": 1484
},
{
"epoch": 3.0306122448979593,
"grad_norm": 2.140625,
"learning_rate": 6.303854875283448e-05,
"loss": 3.5206,
"step": 1485
},
{
"epoch": 3.0326530612244897,
"grad_norm": 2.15625,
"learning_rate": 6.300615484288954e-05,
"loss": 3.4834,
"step": 1486
},
{
"epoch": 3.0346938775510206,
"grad_norm": 1.921875,
"learning_rate": 6.297376093294462e-05,
"loss": 3.2951,
"step": 1487
},
{
"epoch": 3.036734693877551,
"grad_norm": 1.90625,
"learning_rate": 6.294136702299967e-05,
"loss": 3.3867,
"step": 1488
},
{
"epoch": 3.0387755102040814,
"grad_norm": 2.15625,
"learning_rate": 6.290897311305475e-05,
"loss": 3.5583,
"step": 1489
},
{
"epoch": 3.0408163265306123,
"grad_norm": 2.140625,
"learning_rate": 6.287657920310982e-05,
"loss": 3.4877,
"step": 1490
},
{
"epoch": 3.0428571428571427,
"grad_norm": 1.7578125,
"learning_rate": 6.28441852931649e-05,
"loss": 3.5249,
"step": 1491
},
{
"epoch": 3.0448979591836736,
"grad_norm": 1.796875,
"learning_rate": 6.281179138321995e-05,
"loss": 3.5523,
"step": 1492
},
{
"epoch": 3.046938775510204,
"grad_norm": 1.9453125,
"learning_rate": 6.277939747327503e-05,
"loss": 3.4143,
"step": 1493
},
{
"epoch": 3.048979591836735,
"grad_norm": 1.9296875,
"learning_rate": 6.274700356333009e-05,
"loss": 3.4881,
"step": 1494
},
{
"epoch": 3.0510204081632653,
"grad_norm": 2.125,
"learning_rate": 6.271460965338517e-05,
"loss": 3.4368,
"step": 1495
},
{
"epoch": 3.053061224489796,
"grad_norm": 2.03125,
"learning_rate": 6.268221574344024e-05,
"loss": 3.4519,
"step": 1496
},
{
"epoch": 3.0551020408163265,
"grad_norm": 2.03125,
"learning_rate": 6.26498218334953e-05,
"loss": 3.4,
"step": 1497
},
{
"epoch": 3.057142857142857,
"grad_norm": 2.09375,
"learning_rate": 6.261742792355038e-05,
"loss": 3.5496,
"step": 1498
},
{
"epoch": 3.059183673469388,
"grad_norm": 2.015625,
"learning_rate": 6.258503401360545e-05,
"loss": 3.412,
"step": 1499
},
{
"epoch": 3.061224489795918,
"grad_norm": 2.015625,
"learning_rate": 6.255264010366053e-05,
"loss": 3.475,
"step": 1500
},
{
"epoch": 3.061224489795918,
"eval_loss": 4.029097080230713,
"eval_runtime": 5.3999,
"eval_samples_per_second": 29.63,
"eval_steps_per_second": 7.407,
"step": 1500
},
{
"epoch": 3.063265306122449,
"grad_norm": 2.53125,
"learning_rate": 6.252024619371558e-05,
"loss": 3.3333,
"step": 1501
},
{
"epoch": 3.0653061224489795,
"grad_norm": 2.40625,
"learning_rate": 6.248785228377066e-05,
"loss": 3.4222,
"step": 1502
},
{
"epoch": 3.0673469387755103,
"grad_norm": 2.46875,
"learning_rate": 6.245545837382572e-05,
"loss": 3.5303,
"step": 1503
},
{
"epoch": 3.0693877551020408,
"grad_norm": 2.140625,
"learning_rate": 6.24230644638808e-05,
"loss": 3.6131,
"step": 1504
},
{
"epoch": 3.0714285714285716,
"grad_norm": 2.375,
"learning_rate": 6.239067055393585e-05,
"loss": 3.34,
"step": 1505
},
{
"epoch": 3.073469387755102,
"grad_norm": 2.546875,
"learning_rate": 6.235827664399093e-05,
"loss": 3.4137,
"step": 1506
},
{
"epoch": 3.0755102040816324,
"grad_norm": 2.25,
"learning_rate": 6.2325882734046e-05,
"loss": 3.5074,
"step": 1507
},
{
"epoch": 3.0775510204081633,
"grad_norm": 1.9765625,
"learning_rate": 6.229348882410108e-05,
"loss": 3.4919,
"step": 1508
},
{
"epoch": 3.0795918367346937,
"grad_norm": 2.1875,
"learning_rate": 6.226109491415614e-05,
"loss": 3.5079,
"step": 1509
},
{
"epoch": 3.0816326530612246,
"grad_norm": 2.34375,
"learning_rate": 6.222870100421121e-05,
"loss": 3.4582,
"step": 1510
},
{
"epoch": 3.083673469387755,
"grad_norm": 2.28125,
"learning_rate": 6.219630709426629e-05,
"loss": 3.445,
"step": 1511
},
{
"epoch": 3.085714285714286,
"grad_norm": 2.125,
"learning_rate": 6.216391318432135e-05,
"loss": 3.4486,
"step": 1512
},
{
"epoch": 3.0877551020408163,
"grad_norm": 2.0625,
"learning_rate": 6.213151927437642e-05,
"loss": 3.5094,
"step": 1513
},
{
"epoch": 3.089795918367347,
"grad_norm": 2.09375,
"learning_rate": 6.209912536443149e-05,
"loss": 3.4263,
"step": 1514
},
{
"epoch": 3.0918367346938775,
"grad_norm": 2.109375,
"learning_rate": 6.206673145448656e-05,
"loss": 3.3779,
"step": 1515
},
{
"epoch": 3.093877551020408,
"grad_norm": 2.1875,
"learning_rate": 6.203433754454163e-05,
"loss": 3.639,
"step": 1516
},
{
"epoch": 3.095918367346939,
"grad_norm": 2.015625,
"learning_rate": 6.200194363459671e-05,
"loss": 3.5294,
"step": 1517
},
{
"epoch": 3.0979591836734692,
"grad_norm": 2.296875,
"learning_rate": 6.196954972465176e-05,
"loss": 3.559,
"step": 1518
},
{
"epoch": 3.1,
"grad_norm": 2.140625,
"learning_rate": 6.193715581470684e-05,
"loss": 3.4692,
"step": 1519
},
{
"epoch": 3.1020408163265305,
"grad_norm": 2.40625,
"learning_rate": 6.19047619047619e-05,
"loss": 3.4147,
"step": 1520
},
{
"epoch": 3.1040816326530614,
"grad_norm": 2.3125,
"learning_rate": 6.187236799481698e-05,
"loss": 3.4023,
"step": 1521
},
{
"epoch": 3.1061224489795918,
"grad_norm": 2.21875,
"learning_rate": 6.183997408487204e-05,
"loss": 3.3725,
"step": 1522
},
{
"epoch": 3.1081632653061226,
"grad_norm": 2.15625,
"learning_rate": 6.180758017492712e-05,
"loss": 3.4335,
"step": 1523
},
{
"epoch": 3.110204081632653,
"grad_norm": 2.5,
"learning_rate": 6.177518626498218e-05,
"loss": 3.3888,
"step": 1524
},
{
"epoch": 3.1122448979591835,
"grad_norm": 2.46875,
"learning_rate": 6.174279235503726e-05,
"loss": 3.4811,
"step": 1525
},
{
"epoch": 3.1142857142857143,
"grad_norm": 2.109375,
"learning_rate": 6.171039844509233e-05,
"loss": 3.4709,
"step": 1526
},
{
"epoch": 3.1163265306122447,
"grad_norm": 2.5625,
"learning_rate": 6.167800453514739e-05,
"loss": 3.3581,
"step": 1527
},
{
"epoch": 3.1183673469387756,
"grad_norm": 2.28125,
"learning_rate": 6.164561062520247e-05,
"loss": 3.4616,
"step": 1528
},
{
"epoch": 3.120408163265306,
"grad_norm": 2.328125,
"learning_rate": 6.161321671525754e-05,
"loss": 3.629,
"step": 1529
},
{
"epoch": 3.122448979591837,
"grad_norm": 1.9921875,
"learning_rate": 6.15808228053126e-05,
"loss": 3.3703,
"step": 1530
},
{
"epoch": 3.1244897959183673,
"grad_norm": 2.34375,
"learning_rate": 6.154842889536767e-05,
"loss": 3.5046,
"step": 1531
},
{
"epoch": 3.126530612244898,
"grad_norm": 2.203125,
"learning_rate": 6.151603498542275e-05,
"loss": 3.3817,
"step": 1532
},
{
"epoch": 3.1285714285714286,
"grad_norm": 1.9921875,
"learning_rate": 6.148364107547781e-05,
"loss": 3.3814,
"step": 1533
},
{
"epoch": 3.130612244897959,
"grad_norm": 2.0625,
"learning_rate": 6.145124716553289e-05,
"loss": 3.4488,
"step": 1534
},
{
"epoch": 3.13265306122449,
"grad_norm": 2.25,
"learning_rate": 6.141885325558794e-05,
"loss": 3.4689,
"step": 1535
},
{
"epoch": 3.1346938775510202,
"grad_norm": 1.8984375,
"learning_rate": 6.138645934564302e-05,
"loss": 3.442,
"step": 1536
},
{
"epoch": 3.136734693877551,
"grad_norm": 2.046875,
"learning_rate": 6.135406543569809e-05,
"loss": 3.3787,
"step": 1537
},
{
"epoch": 3.1387755102040815,
"grad_norm": 2.328125,
"learning_rate": 6.132167152575317e-05,
"loss": 3.5958,
"step": 1538
},
{
"epoch": 3.1408163265306124,
"grad_norm": 2.109375,
"learning_rate": 6.128927761580823e-05,
"loss": 3.5498,
"step": 1539
},
{
"epoch": 3.142857142857143,
"grad_norm": 2.0,
"learning_rate": 6.12568837058633e-05,
"loss": 3.3284,
"step": 1540
},
{
"epoch": 3.1448979591836737,
"grad_norm": 2.25,
"learning_rate": 6.122448979591838e-05,
"loss": 3.3005,
"step": 1541
},
{
"epoch": 3.146938775510204,
"grad_norm": 2.09375,
"learning_rate": 6.119209588597344e-05,
"loss": 3.5354,
"step": 1542
},
{
"epoch": 3.148979591836735,
"grad_norm": 1.9609375,
"learning_rate": 6.115970197602851e-05,
"loss": 3.3749,
"step": 1543
},
{
"epoch": 3.1510204081632653,
"grad_norm": 2.25,
"learning_rate": 6.112730806608357e-05,
"loss": 3.5468,
"step": 1544
},
{
"epoch": 3.1530612244897958,
"grad_norm": 2.125,
"learning_rate": 6.109491415613865e-05,
"loss": 3.4955,
"step": 1545
},
{
"epoch": 3.1551020408163266,
"grad_norm": 2.1875,
"learning_rate": 6.106252024619372e-05,
"loss": 3.5934,
"step": 1546
},
{
"epoch": 3.157142857142857,
"grad_norm": 2.015625,
"learning_rate": 6.1030126336248785e-05,
"loss": 3.5262,
"step": 1547
},
{
"epoch": 3.159183673469388,
"grad_norm": 2.078125,
"learning_rate": 6.099773242630386e-05,
"loss": 3.5055,
"step": 1548
},
{
"epoch": 3.1612244897959183,
"grad_norm": 2.265625,
"learning_rate": 6.096533851635893e-05,
"loss": 3.4818,
"step": 1549
},
{
"epoch": 3.163265306122449,
"grad_norm": 2.203125,
"learning_rate": 6.0932944606414e-05,
"loss": 3.5106,
"step": 1550
},
{
"epoch": 3.1653061224489796,
"grad_norm": 2.09375,
"learning_rate": 6.0900550696469074e-05,
"loss": 3.3524,
"step": 1551
},
{
"epoch": 3.16734693877551,
"grad_norm": 2.265625,
"learning_rate": 6.086815678652413e-05,
"loss": 3.3421,
"step": 1552
},
{
"epoch": 3.169387755102041,
"grad_norm": 2.4375,
"learning_rate": 6.0835762876579205e-05,
"loss": 3.397,
"step": 1553
},
{
"epoch": 3.1714285714285713,
"grad_norm": 2.171875,
"learning_rate": 6.080336896663428e-05,
"loss": 3.3626,
"step": 1554
},
{
"epoch": 3.173469387755102,
"grad_norm": 2.015625,
"learning_rate": 6.077097505668935e-05,
"loss": 3.5001,
"step": 1555
},
{
"epoch": 3.1755102040816325,
"grad_norm": 2.15625,
"learning_rate": 6.073858114674441e-05,
"loss": 3.487,
"step": 1556
},
{
"epoch": 3.1775510204081634,
"grad_norm": 2.09375,
"learning_rate": 6.070618723679948e-05,
"loss": 3.445,
"step": 1557
},
{
"epoch": 3.179591836734694,
"grad_norm": 1.8828125,
"learning_rate": 6.0673793326854554e-05,
"loss": 3.4881,
"step": 1558
},
{
"epoch": 3.1816326530612247,
"grad_norm": 2.390625,
"learning_rate": 6.0641399416909626e-05,
"loss": 3.3545,
"step": 1559
},
{
"epoch": 3.183673469387755,
"grad_norm": 2.09375,
"learning_rate": 6.060900550696469e-05,
"loss": 3.43,
"step": 1560
},
{
"epoch": 3.185714285714286,
"grad_norm": 2.203125,
"learning_rate": 6.0576611597019764e-05,
"loss": 3.4476,
"step": 1561
},
{
"epoch": 3.1877551020408164,
"grad_norm": 2.3125,
"learning_rate": 6.0544217687074836e-05,
"loss": 3.4598,
"step": 1562
},
{
"epoch": 3.1897959183673468,
"grad_norm": 2.3125,
"learning_rate": 6.051182377712991e-05,
"loss": 3.5228,
"step": 1563
},
{
"epoch": 3.1918367346938776,
"grad_norm": 2.421875,
"learning_rate": 6.047942986718497e-05,
"loss": 3.4505,
"step": 1564
},
{
"epoch": 3.193877551020408,
"grad_norm": 2.25,
"learning_rate": 6.044703595724004e-05,
"loss": 3.5197,
"step": 1565
},
{
"epoch": 3.195918367346939,
"grad_norm": 2.234375,
"learning_rate": 6.041464204729511e-05,
"loss": 3.4069,
"step": 1566
},
{
"epoch": 3.1979591836734693,
"grad_norm": 2.3125,
"learning_rate": 6.0382248137350184e-05,
"loss": 3.4133,
"step": 1567
},
{
"epoch": 3.2,
"grad_norm": 2.203125,
"learning_rate": 6.034985422740526e-05,
"loss": 3.4692,
"step": 1568
},
{
"epoch": 3.2020408163265306,
"grad_norm": 2.171875,
"learning_rate": 6.0317460317460316e-05,
"loss": 3.4681,
"step": 1569
},
{
"epoch": 3.204081632653061,
"grad_norm": 2.578125,
"learning_rate": 6.028506640751539e-05,
"loss": 3.3937,
"step": 1570
},
{
"epoch": 3.206122448979592,
"grad_norm": 2.40625,
"learning_rate": 6.025267249757046e-05,
"loss": 3.4462,
"step": 1571
},
{
"epoch": 3.2081632653061223,
"grad_norm": 2.171875,
"learning_rate": 6.022027858762553e-05,
"loss": 3.4723,
"step": 1572
},
{
"epoch": 3.210204081632653,
"grad_norm": 2.390625,
"learning_rate": 6.01878846776806e-05,
"loss": 3.3671,
"step": 1573
},
{
"epoch": 3.2122448979591836,
"grad_norm": 2.40625,
"learning_rate": 6.015549076773567e-05,
"loss": 3.4764,
"step": 1574
},
{
"epoch": 3.2142857142857144,
"grad_norm": 2.234375,
"learning_rate": 6.0123096857790736e-05,
"loss": 3.3898,
"step": 1575
},
{
"epoch": 3.216326530612245,
"grad_norm": 2.140625,
"learning_rate": 6.009070294784581e-05,
"loss": 3.4498,
"step": 1576
},
{
"epoch": 3.2183673469387757,
"grad_norm": 2.109375,
"learning_rate": 6.0058309037900874e-05,
"loss": 3.5924,
"step": 1577
},
{
"epoch": 3.220408163265306,
"grad_norm": 2.046875,
"learning_rate": 6.0025915127955946e-05,
"loss": 3.4354,
"step": 1578
},
{
"epoch": 3.222448979591837,
"grad_norm": 1.9765625,
"learning_rate": 5.999352121801102e-05,
"loss": 3.5289,
"step": 1579
},
{
"epoch": 3.2244897959183674,
"grad_norm": 2.328125,
"learning_rate": 5.996112730806609e-05,
"loss": 3.5256,
"step": 1580
},
{
"epoch": 3.226530612244898,
"grad_norm": 2.125,
"learning_rate": 5.992873339812115e-05,
"loss": 3.4633,
"step": 1581
},
{
"epoch": 3.2285714285714286,
"grad_norm": 2.0625,
"learning_rate": 5.989633948817622e-05,
"loss": 3.4646,
"step": 1582
},
{
"epoch": 3.230612244897959,
"grad_norm": 2.359375,
"learning_rate": 5.9863945578231295e-05,
"loss": 3.4958,
"step": 1583
},
{
"epoch": 3.23265306122449,
"grad_norm": 2.046875,
"learning_rate": 5.983155166828637e-05,
"loss": 3.5275,
"step": 1584
},
{
"epoch": 3.2346938775510203,
"grad_norm": 2.21875,
"learning_rate": 5.979915775834144e-05,
"loss": 3.4574,
"step": 1585
},
{
"epoch": 3.236734693877551,
"grad_norm": 2.203125,
"learning_rate": 5.97667638483965e-05,
"loss": 3.359,
"step": 1586
},
{
"epoch": 3.2387755102040816,
"grad_norm": 2.21875,
"learning_rate": 5.973436993845157e-05,
"loss": 3.4808,
"step": 1587
},
{
"epoch": 3.240816326530612,
"grad_norm": 2.328125,
"learning_rate": 5.970197602850664e-05,
"loss": 3.3058,
"step": 1588
},
{
"epoch": 3.242857142857143,
"grad_norm": 2.53125,
"learning_rate": 5.9669582118561715e-05,
"loss": 3.4738,
"step": 1589
},
{
"epoch": 3.2448979591836733,
"grad_norm": 2.578125,
"learning_rate": 5.963718820861678e-05,
"loss": 3.3784,
"step": 1590
},
{
"epoch": 3.246938775510204,
"grad_norm": 2.03125,
"learning_rate": 5.960479429867185e-05,
"loss": 3.4544,
"step": 1591
},
{
"epoch": 3.2489795918367346,
"grad_norm": 2.171875,
"learning_rate": 5.9572400388726925e-05,
"loss": 3.4022,
"step": 1592
},
{
"epoch": 3.2510204081632654,
"grad_norm": 2.28125,
"learning_rate": 5.9540006478782e-05,
"loss": 3.4635,
"step": 1593
},
{
"epoch": 3.253061224489796,
"grad_norm": 2.03125,
"learning_rate": 5.9507612568837057e-05,
"loss": 3.4679,
"step": 1594
},
{
"epoch": 3.2551020408163267,
"grad_norm": 2.109375,
"learning_rate": 5.947521865889213e-05,
"loss": 3.398,
"step": 1595
},
{
"epoch": 3.257142857142857,
"grad_norm": 2.21875,
"learning_rate": 5.94428247489472e-05,
"loss": 3.4493,
"step": 1596
},
{
"epoch": 3.259183673469388,
"grad_norm": 2.328125,
"learning_rate": 5.9410430839002274e-05,
"loss": 3.4511,
"step": 1597
},
{
"epoch": 3.2612244897959184,
"grad_norm": 2.09375,
"learning_rate": 5.937803692905733e-05,
"loss": 3.4364,
"step": 1598
},
{
"epoch": 3.263265306122449,
"grad_norm": 2.15625,
"learning_rate": 5.9345643019112405e-05,
"loss": 3.3668,
"step": 1599
},
{
"epoch": 3.2653061224489797,
"grad_norm": 2.203125,
"learning_rate": 5.931324910916748e-05,
"loss": 3.4555,
"step": 1600
},
{
"epoch": 3.26734693877551,
"grad_norm": 2.515625,
"learning_rate": 5.928085519922255e-05,
"loss": 3.4698,
"step": 1601
},
{
"epoch": 3.269387755102041,
"grad_norm": 2.265625,
"learning_rate": 5.924846128927762e-05,
"loss": 3.3644,
"step": 1602
},
{
"epoch": 3.2714285714285714,
"grad_norm": 2.21875,
"learning_rate": 5.921606737933269e-05,
"loss": 3.3963,
"step": 1603
},
{
"epoch": 3.273469387755102,
"grad_norm": 2.046875,
"learning_rate": 5.918367346938776e-05,
"loss": 3.463,
"step": 1604
},
{
"epoch": 3.2755102040816326,
"grad_norm": 2.09375,
"learning_rate": 5.915127955944283e-05,
"loss": 3.5902,
"step": 1605
},
{
"epoch": 3.277551020408163,
"grad_norm": 2.28125,
"learning_rate": 5.9118885649497904e-05,
"loss": 3.532,
"step": 1606
},
{
"epoch": 3.279591836734694,
"grad_norm": 2.046875,
"learning_rate": 5.908649173955296e-05,
"loss": 3.437,
"step": 1607
},
{
"epoch": 3.2816326530612243,
"grad_norm": 2.171875,
"learning_rate": 5.9054097829608036e-05,
"loss": 3.4692,
"step": 1608
},
{
"epoch": 3.283673469387755,
"grad_norm": 2.375,
"learning_rate": 5.902170391966311e-05,
"loss": 3.3673,
"step": 1609
},
{
"epoch": 3.2857142857142856,
"grad_norm": 2.125,
"learning_rate": 5.898931000971818e-05,
"loss": 3.5476,
"step": 1610
},
{
"epoch": 3.2877551020408164,
"grad_norm": 2.21875,
"learning_rate": 5.895691609977324e-05,
"loss": 3.5193,
"step": 1611
},
{
"epoch": 3.289795918367347,
"grad_norm": 2.0625,
"learning_rate": 5.892452218982831e-05,
"loss": 3.4981,
"step": 1612
},
{
"epoch": 3.2918367346938777,
"grad_norm": 2.3125,
"learning_rate": 5.8892128279883384e-05,
"loss": 3.5374,
"step": 1613
},
{
"epoch": 3.293877551020408,
"grad_norm": 2.203125,
"learning_rate": 5.8859734369938456e-05,
"loss": 3.5107,
"step": 1614
},
{
"epoch": 3.295918367346939,
"grad_norm": 2.25,
"learning_rate": 5.882734045999352e-05,
"loss": 3.4657,
"step": 1615
},
{
"epoch": 3.2979591836734694,
"grad_norm": 2.046875,
"learning_rate": 5.8794946550048594e-05,
"loss": 3.4252,
"step": 1616
},
{
"epoch": 3.3,
"grad_norm": 2.09375,
"learning_rate": 5.876255264010366e-05,
"loss": 3.4388,
"step": 1617
},
{
"epoch": 3.3020408163265307,
"grad_norm": 2.15625,
"learning_rate": 5.873015873015873e-05,
"loss": 3.665,
"step": 1618
},
{
"epoch": 3.304081632653061,
"grad_norm": 2.171875,
"learning_rate": 5.8697764820213804e-05,
"loss": 3.4056,
"step": 1619
},
{
"epoch": 3.306122448979592,
"grad_norm": 2.078125,
"learning_rate": 5.866537091026887e-05,
"loss": 3.4226,
"step": 1620
},
{
"epoch": 3.3081632653061224,
"grad_norm": 1.9375,
"learning_rate": 5.863297700032394e-05,
"loss": 3.4739,
"step": 1621
},
{
"epoch": 3.3102040816326532,
"grad_norm": 2.375,
"learning_rate": 5.8600583090379015e-05,
"loss": 3.483,
"step": 1622
},
{
"epoch": 3.3122448979591836,
"grad_norm": 2.15625,
"learning_rate": 5.856818918043409e-05,
"loss": 3.4722,
"step": 1623
},
{
"epoch": 3.314285714285714,
"grad_norm": 2.03125,
"learning_rate": 5.8535795270489146e-05,
"loss": 3.4285,
"step": 1624
},
{
"epoch": 3.316326530612245,
"grad_norm": 2.046875,
"learning_rate": 5.850340136054422e-05,
"loss": 3.3931,
"step": 1625
},
{
"epoch": 3.3183673469387753,
"grad_norm": 2.171875,
"learning_rate": 5.847100745059929e-05,
"loss": 3.4013,
"step": 1626
},
{
"epoch": 3.320408163265306,
"grad_norm": 2.234375,
"learning_rate": 5.843861354065436e-05,
"loss": 3.5122,
"step": 1627
},
{
"epoch": 3.3224489795918366,
"grad_norm": 2.234375,
"learning_rate": 5.840621963070942e-05,
"loss": 3.4111,
"step": 1628
},
{
"epoch": 3.3244897959183675,
"grad_norm": 2.28125,
"learning_rate": 5.8373825720764494e-05,
"loss": 3.4688,
"step": 1629
},
{
"epoch": 3.326530612244898,
"grad_norm": 2.25,
"learning_rate": 5.8341431810819566e-05,
"loss": 3.4653,
"step": 1630
},
{
"epoch": 3.3285714285714287,
"grad_norm": 1.9453125,
"learning_rate": 5.830903790087464e-05,
"loss": 3.5119,
"step": 1631
},
{
"epoch": 3.330612244897959,
"grad_norm": 2.140625,
"learning_rate": 5.827664399092971e-05,
"loss": 3.2836,
"step": 1632
},
{
"epoch": 3.33265306122449,
"grad_norm": 2.078125,
"learning_rate": 5.824425008098478e-05,
"loss": 3.3258,
"step": 1633
},
{
"epoch": 3.3346938775510204,
"grad_norm": 2.21875,
"learning_rate": 5.821185617103985e-05,
"loss": 3.6035,
"step": 1634
},
{
"epoch": 3.336734693877551,
"grad_norm": 1.96875,
"learning_rate": 5.817946226109492e-05,
"loss": 3.3718,
"step": 1635
},
{
"epoch": 3.3387755102040817,
"grad_norm": 2.109375,
"learning_rate": 5.8147068351149994e-05,
"loss": 3.3736,
"step": 1636
},
{
"epoch": 3.340816326530612,
"grad_norm": 2.1875,
"learning_rate": 5.811467444120505e-05,
"loss": 3.4401,
"step": 1637
},
{
"epoch": 3.342857142857143,
"grad_norm": 2.203125,
"learning_rate": 5.8082280531260125e-05,
"loss": 3.513,
"step": 1638
},
{
"epoch": 3.3448979591836734,
"grad_norm": 2.171875,
"learning_rate": 5.80498866213152e-05,
"loss": 3.4462,
"step": 1639
},
{
"epoch": 3.3469387755102042,
"grad_norm": 2.28125,
"learning_rate": 5.801749271137027e-05,
"loss": 3.4525,
"step": 1640
},
{
"epoch": 3.3489795918367347,
"grad_norm": 2.28125,
"learning_rate": 5.798509880142533e-05,
"loss": 3.4151,
"step": 1641
},
{
"epoch": 3.351020408163265,
"grad_norm": 2.1875,
"learning_rate": 5.79527048914804e-05,
"loss": 3.6145,
"step": 1642
},
{
"epoch": 3.353061224489796,
"grad_norm": 2.34375,
"learning_rate": 5.792031098153547e-05,
"loss": 3.401,
"step": 1643
},
{
"epoch": 3.3551020408163263,
"grad_norm": 2.40625,
"learning_rate": 5.7887917071590545e-05,
"loss": 3.5068,
"step": 1644
},
{
"epoch": 3.357142857142857,
"grad_norm": 2.015625,
"learning_rate": 5.785552316164561e-05,
"loss": 3.434,
"step": 1645
},
{
"epoch": 3.3591836734693876,
"grad_norm": 2.140625,
"learning_rate": 5.782312925170068e-05,
"loss": 3.4476,
"step": 1646
},
{
"epoch": 3.3612244897959185,
"grad_norm": 2.1875,
"learning_rate": 5.7790735341755756e-05,
"loss": 3.6293,
"step": 1647
},
{
"epoch": 3.363265306122449,
"grad_norm": 2.078125,
"learning_rate": 5.775834143181083e-05,
"loss": 3.4135,
"step": 1648
},
{
"epoch": 3.3653061224489798,
"grad_norm": 2.0625,
"learning_rate": 5.77259475218659e-05,
"loss": 3.4371,
"step": 1649
},
{
"epoch": 3.36734693877551,
"grad_norm": 2.0625,
"learning_rate": 5.769355361192096e-05,
"loss": 3.452,
"step": 1650
},
{
"epoch": 3.369387755102041,
"grad_norm": 2.1875,
"learning_rate": 5.766115970197603e-05,
"loss": 3.579,
"step": 1651
},
{
"epoch": 3.3714285714285714,
"grad_norm": 2.125,
"learning_rate": 5.7628765792031104e-05,
"loss": 3.4631,
"step": 1652
},
{
"epoch": 3.373469387755102,
"grad_norm": 2.34375,
"learning_rate": 5.7596371882086176e-05,
"loss": 3.4205,
"step": 1653
},
{
"epoch": 3.3755102040816327,
"grad_norm": 2.078125,
"learning_rate": 5.7563977972141235e-05,
"loss": 3.4985,
"step": 1654
},
{
"epoch": 3.377551020408163,
"grad_norm": 2.046875,
"learning_rate": 5.753158406219631e-05,
"loss": 3.4337,
"step": 1655
},
{
"epoch": 3.379591836734694,
"grad_norm": 2.203125,
"learning_rate": 5.749919015225138e-05,
"loss": 3.4344,
"step": 1656
},
{
"epoch": 3.3816326530612244,
"grad_norm": 1.8671875,
"learning_rate": 5.746679624230645e-05,
"loss": 3.5502,
"step": 1657
},
{
"epoch": 3.3836734693877553,
"grad_norm": 2.046875,
"learning_rate": 5.743440233236152e-05,
"loss": 3.463,
"step": 1658
},
{
"epoch": 3.3857142857142857,
"grad_norm": 2.25,
"learning_rate": 5.740200842241658e-05,
"loss": 3.4643,
"step": 1659
},
{
"epoch": 3.387755102040816,
"grad_norm": 1.9296875,
"learning_rate": 5.7369614512471656e-05,
"loss": 3.4755,
"step": 1660
},
{
"epoch": 3.389795918367347,
"grad_norm": 2.203125,
"learning_rate": 5.733722060252673e-05,
"loss": 3.4902,
"step": 1661
},
{
"epoch": 3.3918367346938774,
"grad_norm": 2.21875,
"learning_rate": 5.7304826692581794e-05,
"loss": 3.3551,
"step": 1662
},
{
"epoch": 3.3938775510204082,
"grad_norm": 2.328125,
"learning_rate": 5.7272432782636866e-05,
"loss": 3.4505,
"step": 1663
},
{
"epoch": 3.3959183673469386,
"grad_norm": 2.109375,
"learning_rate": 5.724003887269194e-05,
"loss": 3.4839,
"step": 1664
},
{
"epoch": 3.3979591836734695,
"grad_norm": 2.296875,
"learning_rate": 5.720764496274701e-05,
"loss": 3.4792,
"step": 1665
},
{
"epoch": 3.4,
"grad_norm": 2.6875,
"learning_rate": 5.717525105280208e-05,
"loss": 3.4532,
"step": 1666
},
{
"epoch": 3.4020408163265308,
"grad_norm": 2.234375,
"learning_rate": 5.714285714285714e-05,
"loss": 3.4527,
"step": 1667
},
{
"epoch": 3.404081632653061,
"grad_norm": 2.375,
"learning_rate": 5.7110463232912214e-05,
"loss": 3.4704,
"step": 1668
},
{
"epoch": 3.406122448979592,
"grad_norm": 2.109375,
"learning_rate": 5.7078069322967286e-05,
"loss": 3.4193,
"step": 1669
},
{
"epoch": 3.4081632653061225,
"grad_norm": 2.0,
"learning_rate": 5.704567541302236e-05,
"loss": 3.5038,
"step": 1670
},
{
"epoch": 3.410204081632653,
"grad_norm": 2.03125,
"learning_rate": 5.701328150307742e-05,
"loss": 3.4167,
"step": 1671
},
{
"epoch": 3.4122448979591837,
"grad_norm": 2.078125,
"learning_rate": 5.698088759313249e-05,
"loss": 3.4317,
"step": 1672
},
{
"epoch": 3.414285714285714,
"grad_norm": 2.078125,
"learning_rate": 5.694849368318756e-05,
"loss": 3.4,
"step": 1673
},
{
"epoch": 3.416326530612245,
"grad_norm": 2.3125,
"learning_rate": 5.6916099773242635e-05,
"loss": 3.4267,
"step": 1674
},
{
"epoch": 3.4183673469387754,
"grad_norm": 2.3125,
"learning_rate": 5.68837058632977e-05,
"loss": 3.45,
"step": 1675
},
{
"epoch": 3.4204081632653063,
"grad_norm": 2.078125,
"learning_rate": 5.685131195335277e-05,
"loss": 3.4605,
"step": 1676
},
{
"epoch": 3.4224489795918367,
"grad_norm": 2.125,
"learning_rate": 5.6818918043407845e-05,
"loss": 3.405,
"step": 1677
},
{
"epoch": 3.424489795918367,
"grad_norm": 2.359375,
"learning_rate": 5.678652413346292e-05,
"loss": 3.4619,
"step": 1678
},
{
"epoch": 3.426530612244898,
"grad_norm": 2.4375,
"learning_rate": 5.6754130223517976e-05,
"loss": 3.5701,
"step": 1679
},
{
"epoch": 3.4285714285714284,
"grad_norm": 2.265625,
"learning_rate": 5.672173631357305e-05,
"loss": 3.3769,
"step": 1680
},
{
"epoch": 3.4306122448979592,
"grad_norm": 2.03125,
"learning_rate": 5.668934240362812e-05,
"loss": 3.4463,
"step": 1681
},
{
"epoch": 3.4326530612244897,
"grad_norm": 2.109375,
"learning_rate": 5.665694849368319e-05,
"loss": 3.4429,
"step": 1682
},
{
"epoch": 3.4346938775510205,
"grad_norm": 2.015625,
"learning_rate": 5.6624554583738265e-05,
"loss": 3.3424,
"step": 1683
},
{
"epoch": 3.436734693877551,
"grad_norm": 1.9609375,
"learning_rate": 5.6592160673793324e-05,
"loss": 3.453,
"step": 1684
},
{
"epoch": 3.438775510204082,
"grad_norm": 2.140625,
"learning_rate": 5.65597667638484e-05,
"loss": 3.4612,
"step": 1685
},
{
"epoch": 3.440816326530612,
"grad_norm": 2.21875,
"learning_rate": 5.652737285390347e-05,
"loss": 3.5364,
"step": 1686
},
{
"epoch": 3.442857142857143,
"grad_norm": 2.09375,
"learning_rate": 5.649497894395854e-05,
"loss": 3.4779,
"step": 1687
},
{
"epoch": 3.4448979591836735,
"grad_norm": 1.953125,
"learning_rate": 5.646258503401361e-05,
"loss": 3.5381,
"step": 1688
},
{
"epoch": 3.446938775510204,
"grad_norm": 2.0625,
"learning_rate": 5.643019112406868e-05,
"loss": 3.3519,
"step": 1689
},
{
"epoch": 3.4489795918367347,
"grad_norm": 1.9140625,
"learning_rate": 5.639779721412375e-05,
"loss": 3.4751,
"step": 1690
},
{
"epoch": 3.451020408163265,
"grad_norm": 2.125,
"learning_rate": 5.6365403304178824e-05,
"loss": 3.4206,
"step": 1691
},
{
"epoch": 3.453061224489796,
"grad_norm": 2.171875,
"learning_rate": 5.633300939423388e-05,
"loss": 3.5207,
"step": 1692
},
{
"epoch": 3.4551020408163264,
"grad_norm": 2.15625,
"learning_rate": 5.6300615484288955e-05,
"loss": 3.4374,
"step": 1693
},
{
"epoch": 3.4571428571428573,
"grad_norm": 2.40625,
"learning_rate": 5.626822157434403e-05,
"loss": 3.4702,
"step": 1694
},
{
"epoch": 3.4591836734693877,
"grad_norm": 2.140625,
"learning_rate": 5.62358276643991e-05,
"loss": 3.341,
"step": 1695
},
{
"epoch": 3.461224489795918,
"grad_norm": 1.96875,
"learning_rate": 5.620343375445416e-05,
"loss": 3.4814,
"step": 1696
},
{
"epoch": 3.463265306122449,
"grad_norm": 2.546875,
"learning_rate": 5.617103984450923e-05,
"loss": 3.4101,
"step": 1697
},
{
"epoch": 3.4653061224489794,
"grad_norm": 2.28125,
"learning_rate": 5.61386459345643e-05,
"loss": 3.4463,
"step": 1698
},
{
"epoch": 3.4673469387755103,
"grad_norm": 2.28125,
"learning_rate": 5.6106252024619376e-05,
"loss": 3.537,
"step": 1699
},
{
"epoch": 3.4693877551020407,
"grad_norm": 2.25,
"learning_rate": 5.607385811467445e-05,
"loss": 3.4823,
"step": 1700
},
{
"epoch": 3.4714285714285715,
"grad_norm": 2.328125,
"learning_rate": 5.604146420472951e-05,
"loss": 3.4207,
"step": 1701
},
{
"epoch": 3.473469387755102,
"grad_norm": 2.171875,
"learning_rate": 5.600907029478458e-05,
"loss": 3.4705,
"step": 1702
},
{
"epoch": 3.475510204081633,
"grad_norm": 2.09375,
"learning_rate": 5.597667638483965e-05,
"loss": 3.5616,
"step": 1703
},
{
"epoch": 3.477551020408163,
"grad_norm": 2.078125,
"learning_rate": 5.5944282474894724e-05,
"loss": 3.5472,
"step": 1704
},
{
"epoch": 3.479591836734694,
"grad_norm": 2.078125,
"learning_rate": 5.591188856494979e-05,
"loss": 3.5233,
"step": 1705
},
{
"epoch": 3.4816326530612245,
"grad_norm": 2.1875,
"learning_rate": 5.587949465500486e-05,
"loss": 3.4823,
"step": 1706
},
{
"epoch": 3.483673469387755,
"grad_norm": 2.0625,
"learning_rate": 5.5847100745059934e-05,
"loss": 3.468,
"step": 1707
},
{
"epoch": 3.4857142857142858,
"grad_norm": 2.046875,
"learning_rate": 5.5814706835115007e-05,
"loss": 3.4776,
"step": 1708
},
{
"epoch": 3.487755102040816,
"grad_norm": 2.09375,
"learning_rate": 5.5782312925170065e-05,
"loss": 3.2895,
"step": 1709
},
{
"epoch": 3.489795918367347,
"grad_norm": 2.140625,
"learning_rate": 5.574991901522514e-05,
"loss": 3.3645,
"step": 1710
},
{
"epoch": 3.4918367346938775,
"grad_norm": 1.9765625,
"learning_rate": 5.571752510528021e-05,
"loss": 3.4161,
"step": 1711
},
{
"epoch": 3.4938775510204083,
"grad_norm": 2.296875,
"learning_rate": 5.568513119533528e-05,
"loss": 3.4979,
"step": 1712
},
{
"epoch": 3.4959183673469387,
"grad_norm": 2.125,
"learning_rate": 5.565273728539034e-05,
"loss": 3.5179,
"step": 1713
},
{
"epoch": 3.497959183673469,
"grad_norm": 2.171875,
"learning_rate": 5.5620343375445414e-05,
"loss": 3.5074,
"step": 1714
},
{
"epoch": 3.5,
"grad_norm": 2.21875,
"learning_rate": 5.5587949465500486e-05,
"loss": 3.3868,
"step": 1715
},
{
"epoch": 3.502040816326531,
"grad_norm": 2.015625,
"learning_rate": 5.555555555555556e-05,
"loss": 3.4591,
"step": 1716
},
{
"epoch": 3.5040816326530613,
"grad_norm": 2.125,
"learning_rate": 5.552316164561063e-05,
"loss": 3.324,
"step": 1717
},
{
"epoch": 3.5061224489795917,
"grad_norm": 2.078125,
"learning_rate": 5.5490767735665696e-05,
"loss": 3.4678,
"step": 1718
},
{
"epoch": 3.5081632653061225,
"grad_norm": 2.40625,
"learning_rate": 5.545837382572077e-05,
"loss": 3.4163,
"step": 1719
},
{
"epoch": 3.510204081632653,
"grad_norm": 2.109375,
"learning_rate": 5.542597991577584e-05,
"loss": 3.6051,
"step": 1720
},
{
"epoch": 3.512244897959184,
"grad_norm": 2.09375,
"learning_rate": 5.539358600583091e-05,
"loss": 3.5767,
"step": 1721
},
{
"epoch": 3.5142857142857142,
"grad_norm": 2.5,
"learning_rate": 5.536119209588597e-05,
"loss": 3.4834,
"step": 1722
},
{
"epoch": 3.516326530612245,
"grad_norm": 2.21875,
"learning_rate": 5.5328798185941044e-05,
"loss": 3.3741,
"step": 1723
},
{
"epoch": 3.5183673469387755,
"grad_norm": 1.9765625,
"learning_rate": 5.529640427599612e-05,
"loss": 3.4645,
"step": 1724
},
{
"epoch": 3.520408163265306,
"grad_norm": 2.09375,
"learning_rate": 5.526401036605119e-05,
"loss": 3.45,
"step": 1725
},
{
"epoch": 3.522448979591837,
"grad_norm": 2.34375,
"learning_rate": 5.523161645610625e-05,
"loss": 3.4607,
"step": 1726
},
{
"epoch": 3.524489795918367,
"grad_norm": 2.109375,
"learning_rate": 5.519922254616132e-05,
"loss": 3.5204,
"step": 1727
},
{
"epoch": 3.526530612244898,
"grad_norm": 2.09375,
"learning_rate": 5.516682863621639e-05,
"loss": 3.4598,
"step": 1728
},
{
"epoch": 3.5285714285714285,
"grad_norm": 2.03125,
"learning_rate": 5.5134434726271465e-05,
"loss": 3.5583,
"step": 1729
},
{
"epoch": 3.5306122448979593,
"grad_norm": 2.046875,
"learning_rate": 5.510204081632653e-05,
"loss": 3.4004,
"step": 1730
},
{
"epoch": 3.5326530612244897,
"grad_norm": 2.046875,
"learning_rate": 5.50696469063816e-05,
"loss": 3.4216,
"step": 1731
},
{
"epoch": 3.53469387755102,
"grad_norm": 2.140625,
"learning_rate": 5.5037252996436675e-05,
"loss": 3.5093,
"step": 1732
},
{
"epoch": 3.536734693877551,
"grad_norm": 2.421875,
"learning_rate": 5.500485908649175e-05,
"loss": 3.4257,
"step": 1733
},
{
"epoch": 3.538775510204082,
"grad_norm": 2.359375,
"learning_rate": 5.497246517654682e-05,
"loss": 3.5129,
"step": 1734
},
{
"epoch": 3.5408163265306123,
"grad_norm": 2.046875,
"learning_rate": 5.494007126660188e-05,
"loss": 3.4154,
"step": 1735
},
{
"epoch": 3.5428571428571427,
"grad_norm": 2.21875,
"learning_rate": 5.490767735665695e-05,
"loss": 3.3789,
"step": 1736
},
{
"epoch": 3.5448979591836736,
"grad_norm": 2.390625,
"learning_rate": 5.4875283446712023e-05,
"loss": 3.5026,
"step": 1737
},
{
"epoch": 3.546938775510204,
"grad_norm": 2.171875,
"learning_rate": 5.4842889536767096e-05,
"loss": 3.5932,
"step": 1738
},
{
"epoch": 3.548979591836735,
"grad_norm": 2.1875,
"learning_rate": 5.4810495626822155e-05,
"loss": 3.4834,
"step": 1739
},
{
"epoch": 3.5510204081632653,
"grad_norm": 2.078125,
"learning_rate": 5.477810171687723e-05,
"loss": 3.513,
"step": 1740
},
{
"epoch": 3.553061224489796,
"grad_norm": 2.0,
"learning_rate": 5.47457078069323e-05,
"loss": 3.4826,
"step": 1741
},
{
"epoch": 3.5551020408163265,
"grad_norm": 2.09375,
"learning_rate": 5.471331389698737e-05,
"loss": 3.5273,
"step": 1742
},
{
"epoch": 3.557142857142857,
"grad_norm": 2.09375,
"learning_rate": 5.468091998704244e-05,
"loss": 3.4701,
"step": 1743
},
{
"epoch": 3.559183673469388,
"grad_norm": 2.1875,
"learning_rate": 5.46485260770975e-05,
"loss": 3.4358,
"step": 1744
},
{
"epoch": 3.561224489795918,
"grad_norm": 2.0625,
"learning_rate": 5.4616132167152575e-05,
"loss": 3.5237,
"step": 1745
},
{
"epoch": 3.563265306122449,
"grad_norm": 2.234375,
"learning_rate": 5.458373825720765e-05,
"loss": 3.5329,
"step": 1746
},
{
"epoch": 3.5653061224489795,
"grad_norm": 2.109375,
"learning_rate": 5.455134434726271e-05,
"loss": 3.3236,
"step": 1747
},
{
"epoch": 3.5673469387755103,
"grad_norm": 2.265625,
"learning_rate": 5.4518950437317785e-05,
"loss": 3.4274,
"step": 1748
},
{
"epoch": 3.5693877551020408,
"grad_norm": 2.078125,
"learning_rate": 5.448655652737286e-05,
"loss": 3.4466,
"step": 1749
},
{
"epoch": 3.571428571428571,
"grad_norm": 2.046875,
"learning_rate": 5.445416261742793e-05,
"loss": 3.3402,
"step": 1750
},
{
"epoch": 3.573469387755102,
"grad_norm": 2.078125,
"learning_rate": 5.4421768707483e-05,
"loss": 3.489,
"step": 1751
},
{
"epoch": 3.575510204081633,
"grad_norm": 2.265625,
"learning_rate": 5.438937479753806e-05,
"loss": 3.3885,
"step": 1752
},
{
"epoch": 3.5775510204081633,
"grad_norm": 2.09375,
"learning_rate": 5.4356980887593134e-05,
"loss": 3.3484,
"step": 1753
},
{
"epoch": 3.5795918367346937,
"grad_norm": 2.34375,
"learning_rate": 5.4324586977648206e-05,
"loss": 3.3207,
"step": 1754
},
{
"epoch": 3.5816326530612246,
"grad_norm": 2.109375,
"learning_rate": 5.429219306770328e-05,
"loss": 3.4806,
"step": 1755
},
{
"epoch": 3.583673469387755,
"grad_norm": 1.9921875,
"learning_rate": 5.425979915775834e-05,
"loss": 3.436,
"step": 1756
},
{
"epoch": 3.585714285714286,
"grad_norm": 2.109375,
"learning_rate": 5.422740524781341e-05,
"loss": 3.4486,
"step": 1757
},
{
"epoch": 3.5877551020408163,
"grad_norm": 2.265625,
"learning_rate": 5.419501133786848e-05,
"loss": 3.4713,
"step": 1758
},
{
"epoch": 3.589795918367347,
"grad_norm": 2.15625,
"learning_rate": 5.4162617427923554e-05,
"loss": 3.432,
"step": 1759
},
{
"epoch": 3.5918367346938775,
"grad_norm": 2.265625,
"learning_rate": 5.413022351797862e-05,
"loss": 3.5235,
"step": 1760
},
{
"epoch": 3.593877551020408,
"grad_norm": 2.109375,
"learning_rate": 5.409782960803369e-05,
"loss": 3.5692,
"step": 1761
},
{
"epoch": 3.595918367346939,
"grad_norm": 2.28125,
"learning_rate": 5.4065435698088764e-05,
"loss": 3.4943,
"step": 1762
},
{
"epoch": 3.5979591836734692,
"grad_norm": 2.171875,
"learning_rate": 5.403304178814384e-05,
"loss": 3.4607,
"step": 1763
},
{
"epoch": 3.6,
"grad_norm": 2.140625,
"learning_rate": 5.400064787819891e-05,
"loss": 3.4316,
"step": 1764
},
{
"epoch": 3.6020408163265305,
"grad_norm": 2.078125,
"learning_rate": 5.396825396825397e-05,
"loss": 3.5074,
"step": 1765
},
{
"epoch": 3.6040816326530614,
"grad_norm": 2.4375,
"learning_rate": 5.393586005830904e-05,
"loss": 3.3814,
"step": 1766
},
{
"epoch": 3.6061224489795918,
"grad_norm": 2.140625,
"learning_rate": 5.390346614836411e-05,
"loss": 3.5379,
"step": 1767
},
{
"epoch": 3.608163265306122,
"grad_norm": 2.0625,
"learning_rate": 5.3871072238419185e-05,
"loss": 3.5695,
"step": 1768
},
{
"epoch": 3.610204081632653,
"grad_norm": 1.984375,
"learning_rate": 5.3838678328474244e-05,
"loss": 3.4012,
"step": 1769
},
{
"epoch": 3.612244897959184,
"grad_norm": 2.390625,
"learning_rate": 5.3806284418529316e-05,
"loss": 3.4255,
"step": 1770
},
{
"epoch": 3.6142857142857143,
"grad_norm": 1.9765625,
"learning_rate": 5.377389050858439e-05,
"loss": 3.5002,
"step": 1771
},
{
"epoch": 3.6163265306122447,
"grad_norm": 2.046875,
"learning_rate": 5.374149659863946e-05,
"loss": 3.551,
"step": 1772
},
{
"epoch": 3.6183673469387756,
"grad_norm": 2.046875,
"learning_rate": 5.3709102688694526e-05,
"loss": 3.41,
"step": 1773
},
{
"epoch": 3.620408163265306,
"grad_norm": 2.203125,
"learning_rate": 5.36767087787496e-05,
"loss": 3.3829,
"step": 1774
},
{
"epoch": 3.622448979591837,
"grad_norm": 2.109375,
"learning_rate": 5.364431486880467e-05,
"loss": 3.3713,
"step": 1775
},
{
"epoch": 3.6244897959183673,
"grad_norm": 2.0625,
"learning_rate": 5.3611920958859743e-05,
"loss": 3.4234,
"step": 1776
},
{
"epoch": 3.626530612244898,
"grad_norm": 1.984375,
"learning_rate": 5.35795270489148e-05,
"loss": 3.5053,
"step": 1777
},
{
"epoch": 3.6285714285714286,
"grad_norm": 2.53125,
"learning_rate": 5.3547133138969875e-05,
"loss": 3.4278,
"step": 1778
},
{
"epoch": 3.630612244897959,
"grad_norm": 2.109375,
"learning_rate": 5.351473922902495e-05,
"loss": 3.5675,
"step": 1779
},
{
"epoch": 3.63265306122449,
"grad_norm": 2.109375,
"learning_rate": 5.348234531908002e-05,
"loss": 3.4621,
"step": 1780
},
{
"epoch": 3.6346938775510202,
"grad_norm": 2.109375,
"learning_rate": 5.344995140913509e-05,
"loss": 3.4983,
"step": 1781
},
{
"epoch": 3.636734693877551,
"grad_norm": 2.265625,
"learning_rate": 5.341755749919015e-05,
"loss": 3.5221,
"step": 1782
},
{
"epoch": 3.6387755102040815,
"grad_norm": 2.375,
"learning_rate": 5.338516358924522e-05,
"loss": 3.3525,
"step": 1783
},
{
"epoch": 3.6408163265306124,
"grad_norm": 2.078125,
"learning_rate": 5.3352769679300295e-05,
"loss": 3.4281,
"step": 1784
},
{
"epoch": 3.642857142857143,
"grad_norm": 2.28125,
"learning_rate": 5.332037576935537e-05,
"loss": 3.4991,
"step": 1785
},
{
"epoch": 3.644897959183673,
"grad_norm": 2.421875,
"learning_rate": 5.3287981859410426e-05,
"loss": 3.4093,
"step": 1786
},
{
"epoch": 3.646938775510204,
"grad_norm": 2.359375,
"learning_rate": 5.32555879494655e-05,
"loss": 3.4789,
"step": 1787
},
{
"epoch": 3.648979591836735,
"grad_norm": 2.109375,
"learning_rate": 5.322319403952057e-05,
"loss": 3.522,
"step": 1788
},
{
"epoch": 3.6510204081632653,
"grad_norm": 2.125,
"learning_rate": 5.3190800129575643e-05,
"loss": 3.4683,
"step": 1789
},
{
"epoch": 3.6530612244897958,
"grad_norm": 2.171875,
"learning_rate": 5.315840621963071e-05,
"loss": 3.5317,
"step": 1790
},
{
"epoch": 3.6551020408163266,
"grad_norm": 2.375,
"learning_rate": 5.312601230968578e-05,
"loss": 3.3725,
"step": 1791
},
{
"epoch": 3.657142857142857,
"grad_norm": 2.15625,
"learning_rate": 5.3093618399740854e-05,
"loss": 3.4804,
"step": 1792
},
{
"epoch": 3.659183673469388,
"grad_norm": 2.21875,
"learning_rate": 5.3061224489795926e-05,
"loss": 3.3837,
"step": 1793
},
{
"epoch": 3.6612244897959183,
"grad_norm": 2.28125,
"learning_rate": 5.3028830579850985e-05,
"loss": 3.4372,
"step": 1794
},
{
"epoch": 3.663265306122449,
"grad_norm": 2.328125,
"learning_rate": 5.299643666990606e-05,
"loss": 3.5749,
"step": 1795
},
{
"epoch": 3.6653061224489796,
"grad_norm": 2.0,
"learning_rate": 5.296404275996113e-05,
"loss": 3.4979,
"step": 1796
},
{
"epoch": 3.66734693877551,
"grad_norm": 2.1875,
"learning_rate": 5.29316488500162e-05,
"loss": 3.406,
"step": 1797
},
{
"epoch": 3.669387755102041,
"grad_norm": 2.125,
"learning_rate": 5.2899254940071274e-05,
"loss": 3.4661,
"step": 1798
},
{
"epoch": 3.6714285714285713,
"grad_norm": 2.21875,
"learning_rate": 5.286686103012633e-05,
"loss": 3.4207,
"step": 1799
},
{
"epoch": 3.673469387755102,
"grad_norm": 1.9375,
"learning_rate": 5.2834467120181405e-05,
"loss": 3.4303,
"step": 1800
},
{
"epoch": 3.6755102040816325,
"grad_norm": 2.03125,
"learning_rate": 5.280207321023648e-05,
"loss": 3.4304,
"step": 1801
},
{
"epoch": 3.6775510204081634,
"grad_norm": 2.1875,
"learning_rate": 5.276967930029155e-05,
"loss": 3.4682,
"step": 1802
},
{
"epoch": 3.679591836734694,
"grad_norm": 2.15625,
"learning_rate": 5.2737285390346616e-05,
"loss": 3.3661,
"step": 1803
},
{
"epoch": 3.6816326530612242,
"grad_norm": 2.109375,
"learning_rate": 5.270489148040169e-05,
"loss": 3.4982,
"step": 1804
},
{
"epoch": 3.683673469387755,
"grad_norm": 2.0625,
"learning_rate": 5.267249757045676e-05,
"loss": 3.4119,
"step": 1805
},
{
"epoch": 3.685714285714286,
"grad_norm": 2.015625,
"learning_rate": 5.264010366051183e-05,
"loss": 3.3957,
"step": 1806
},
{
"epoch": 3.6877551020408164,
"grad_norm": 2.234375,
"learning_rate": 5.260770975056689e-05,
"loss": 3.4879,
"step": 1807
},
{
"epoch": 3.6897959183673468,
"grad_norm": 2.1875,
"learning_rate": 5.2575315840621964e-05,
"loss": 3.4575,
"step": 1808
},
{
"epoch": 3.6918367346938776,
"grad_norm": 2.203125,
"learning_rate": 5.2542921930677036e-05,
"loss": 3.5858,
"step": 1809
},
{
"epoch": 3.693877551020408,
"grad_norm": 2.046875,
"learning_rate": 5.251052802073211e-05,
"loss": 3.4657,
"step": 1810
},
{
"epoch": 3.695918367346939,
"grad_norm": 2.015625,
"learning_rate": 5.247813411078717e-05,
"loss": 3.455,
"step": 1811
},
{
"epoch": 3.6979591836734693,
"grad_norm": 2.40625,
"learning_rate": 5.244574020084224e-05,
"loss": 3.4047,
"step": 1812
},
{
"epoch": 3.7,
"grad_norm": 2.046875,
"learning_rate": 5.241334629089731e-05,
"loss": 3.4825,
"step": 1813
},
{
"epoch": 3.7020408163265306,
"grad_norm": 2.0625,
"learning_rate": 5.2380952380952384e-05,
"loss": 3.4515,
"step": 1814
},
{
"epoch": 3.704081632653061,
"grad_norm": 1.953125,
"learning_rate": 5.234855847100746e-05,
"loss": 3.4283,
"step": 1815
},
{
"epoch": 3.706122448979592,
"grad_norm": 2.09375,
"learning_rate": 5.231616456106252e-05,
"loss": 3.3681,
"step": 1816
},
{
"epoch": 3.7081632653061227,
"grad_norm": 2.09375,
"learning_rate": 5.2283770651117595e-05,
"loss": 3.3375,
"step": 1817
},
{
"epoch": 3.710204081632653,
"grad_norm": 2.125,
"learning_rate": 5.225137674117267e-05,
"loss": 3.5474,
"step": 1818
},
{
"epoch": 3.7122448979591836,
"grad_norm": 2.328125,
"learning_rate": 5.221898283122774e-05,
"loss": 3.2789,
"step": 1819
},
{
"epoch": 3.7142857142857144,
"grad_norm": 2.25,
"learning_rate": 5.21865889212828e-05,
"loss": 3.4298,
"step": 1820
},
{
"epoch": 3.716326530612245,
"grad_norm": 2.03125,
"learning_rate": 5.215419501133787e-05,
"loss": 3.3686,
"step": 1821
},
{
"epoch": 3.7183673469387752,
"grad_norm": 2.3125,
"learning_rate": 5.212180110139294e-05,
"loss": 3.393,
"step": 1822
},
{
"epoch": 3.720408163265306,
"grad_norm": 2.21875,
"learning_rate": 5.2089407191448015e-05,
"loss": 3.3894,
"step": 1823
},
{
"epoch": 3.722448979591837,
"grad_norm": 2.0625,
"learning_rate": 5.2057013281503074e-05,
"loss": 3.4169,
"step": 1824
},
{
"epoch": 3.7244897959183674,
"grad_norm": 2.234375,
"learning_rate": 5.2024619371558146e-05,
"loss": 3.3835,
"step": 1825
},
{
"epoch": 3.726530612244898,
"grad_norm": 2.140625,
"learning_rate": 5.199222546161322e-05,
"loss": 3.3875,
"step": 1826
},
{
"epoch": 3.7285714285714286,
"grad_norm": 2.203125,
"learning_rate": 5.195983155166829e-05,
"loss": 3.3243,
"step": 1827
},
{
"epoch": 3.730612244897959,
"grad_norm": 2.15625,
"learning_rate": 5.192743764172335e-05,
"loss": 3.4338,
"step": 1828
},
{
"epoch": 3.73265306122449,
"grad_norm": 2.203125,
"learning_rate": 5.189504373177842e-05,
"loss": 3.3227,
"step": 1829
},
{
"epoch": 3.7346938775510203,
"grad_norm": 2.203125,
"learning_rate": 5.1862649821833495e-05,
"loss": 3.3953,
"step": 1830
},
{
"epoch": 3.736734693877551,
"grad_norm": 1.953125,
"learning_rate": 5.183025591188857e-05,
"loss": 3.4606,
"step": 1831
},
{
"epoch": 3.7387755102040816,
"grad_norm": 2.171875,
"learning_rate": 5.179786200194364e-05,
"loss": 3.441,
"step": 1832
},
{
"epoch": 3.740816326530612,
"grad_norm": 2.25,
"learning_rate": 5.1765468091998705e-05,
"loss": 3.407,
"step": 1833
},
{
"epoch": 3.742857142857143,
"grad_norm": 2.046875,
"learning_rate": 5.173307418205378e-05,
"loss": 3.3686,
"step": 1834
},
{
"epoch": 3.7448979591836737,
"grad_norm": 2.25,
"learning_rate": 5.170068027210885e-05,
"loss": 3.5301,
"step": 1835
},
{
"epoch": 3.746938775510204,
"grad_norm": 2.390625,
"learning_rate": 5.166828636216392e-05,
"loss": 3.5177,
"step": 1836
},
{
"epoch": 3.7489795918367346,
"grad_norm": 2.25,
"learning_rate": 5.163589245221898e-05,
"loss": 3.5998,
"step": 1837
},
{
"epoch": 3.7510204081632654,
"grad_norm": 2.09375,
"learning_rate": 5.160349854227405e-05,
"loss": 3.4615,
"step": 1838
},
{
"epoch": 3.753061224489796,
"grad_norm": 2.046875,
"learning_rate": 5.1571104632329125e-05,
"loss": 3.3793,
"step": 1839
},
{
"epoch": 3.7551020408163263,
"grad_norm": 2.421875,
"learning_rate": 5.15387107223842e-05,
"loss": 3.4338,
"step": 1840
},
{
"epoch": 3.757142857142857,
"grad_norm": 2.34375,
"learning_rate": 5.150631681243926e-05,
"loss": 3.5112,
"step": 1841
},
{
"epoch": 3.759183673469388,
"grad_norm": 2.109375,
"learning_rate": 5.147392290249433e-05,
"loss": 3.3838,
"step": 1842
},
{
"epoch": 3.7612244897959184,
"grad_norm": 2.140625,
"learning_rate": 5.14415289925494e-05,
"loss": 3.3898,
"step": 1843
},
{
"epoch": 3.763265306122449,
"grad_norm": 2.375,
"learning_rate": 5.1409135082604474e-05,
"loss": 3.4269,
"step": 1844
},
{
"epoch": 3.7653061224489797,
"grad_norm": 2.15625,
"learning_rate": 5.137674117265954e-05,
"loss": 3.4232,
"step": 1845
},
{
"epoch": 3.76734693877551,
"grad_norm": 2.15625,
"learning_rate": 5.134434726271461e-05,
"loss": 3.3834,
"step": 1846
},
{
"epoch": 3.769387755102041,
"grad_norm": 2.109375,
"learning_rate": 5.1311953352769684e-05,
"loss": 3.4413,
"step": 1847
},
{
"epoch": 3.7714285714285714,
"grad_norm": 2.015625,
"learning_rate": 5.1279559442824756e-05,
"loss": 3.4406,
"step": 1848
},
{
"epoch": 3.773469387755102,
"grad_norm": 2.21875,
"learning_rate": 5.124716553287983e-05,
"loss": 3.3265,
"step": 1849
},
{
"epoch": 3.7755102040816326,
"grad_norm": 2.328125,
"learning_rate": 5.121477162293489e-05,
"loss": 3.3894,
"step": 1850
},
{
"epoch": 3.777551020408163,
"grad_norm": 2.359375,
"learning_rate": 5.118237771298996e-05,
"loss": 3.5265,
"step": 1851
},
{
"epoch": 3.779591836734694,
"grad_norm": 2.1875,
"learning_rate": 5.114998380304503e-05,
"loss": 3.4177,
"step": 1852
},
{
"epoch": 3.7816326530612248,
"grad_norm": 2.140625,
"learning_rate": 5.1117589893100105e-05,
"loss": 3.3482,
"step": 1853
},
{
"epoch": 3.783673469387755,
"grad_norm": 2.1875,
"learning_rate": 5.108519598315516e-05,
"loss": 3.3905,
"step": 1854
},
{
"epoch": 3.7857142857142856,
"grad_norm": 2.0625,
"learning_rate": 5.1052802073210236e-05,
"loss": 3.4622,
"step": 1855
},
{
"epoch": 3.7877551020408164,
"grad_norm": 1.953125,
"learning_rate": 5.102040816326531e-05,
"loss": 3.4652,
"step": 1856
},
{
"epoch": 3.789795918367347,
"grad_norm": 2.34375,
"learning_rate": 5.098801425332038e-05,
"loss": 3.4067,
"step": 1857
},
{
"epoch": 3.7918367346938773,
"grad_norm": 2.421875,
"learning_rate": 5.0955620343375446e-05,
"loss": 3.4768,
"step": 1858
},
{
"epoch": 3.793877551020408,
"grad_norm": 2.21875,
"learning_rate": 5.092322643343052e-05,
"loss": 3.2912,
"step": 1859
},
{
"epoch": 3.795918367346939,
"grad_norm": 2.28125,
"learning_rate": 5.089083252348559e-05,
"loss": 3.4539,
"step": 1860
},
{
"epoch": 3.7979591836734694,
"grad_norm": 2.21875,
"learning_rate": 5.085843861354066e-05,
"loss": 3.4313,
"step": 1861
},
{
"epoch": 3.8,
"grad_norm": 2.390625,
"learning_rate": 5.082604470359572e-05,
"loss": 3.4548,
"step": 1862
},
{
"epoch": 3.8020408163265307,
"grad_norm": 2.265625,
"learning_rate": 5.0793650793650794e-05,
"loss": 3.402,
"step": 1863
},
{
"epoch": 3.804081632653061,
"grad_norm": 2.15625,
"learning_rate": 5.0761256883705867e-05,
"loss": 3.3511,
"step": 1864
},
{
"epoch": 3.806122448979592,
"grad_norm": 2.265625,
"learning_rate": 5.072886297376094e-05,
"loss": 3.3626,
"step": 1865
},
{
"epoch": 3.8081632653061224,
"grad_norm": 2.078125,
"learning_rate": 5.069646906381601e-05,
"loss": 3.5008,
"step": 1866
},
{
"epoch": 3.8102040816326532,
"grad_norm": 2.21875,
"learning_rate": 5.066407515387107e-05,
"loss": 3.4178,
"step": 1867
},
{
"epoch": 3.8122448979591836,
"grad_norm": 2.25,
"learning_rate": 5.063168124392614e-05,
"loss": 3.5174,
"step": 1868
},
{
"epoch": 3.814285714285714,
"grad_norm": 2.125,
"learning_rate": 5.0599287333981215e-05,
"loss": 3.4194,
"step": 1869
},
{
"epoch": 3.816326530612245,
"grad_norm": 2.078125,
"learning_rate": 5.056689342403629e-05,
"loss": 3.2913,
"step": 1870
},
{
"epoch": 3.8183673469387758,
"grad_norm": 2.359375,
"learning_rate": 5.0534499514091346e-05,
"loss": 3.4444,
"step": 1871
},
{
"epoch": 3.820408163265306,
"grad_norm": 2.3125,
"learning_rate": 5.050210560414642e-05,
"loss": 3.4171,
"step": 1872
},
{
"epoch": 3.8224489795918366,
"grad_norm": 2.0625,
"learning_rate": 5.046971169420149e-05,
"loss": 3.4258,
"step": 1873
},
{
"epoch": 3.8244897959183675,
"grad_norm": 2.40625,
"learning_rate": 5.043731778425656e-05,
"loss": 3.3949,
"step": 1874
},
{
"epoch": 3.826530612244898,
"grad_norm": 2.171875,
"learning_rate": 5.040492387431163e-05,
"loss": 3.4803,
"step": 1875
},
{
"epoch": 3.8285714285714287,
"grad_norm": 2.25,
"learning_rate": 5.03725299643667e-05,
"loss": 3.5589,
"step": 1876
},
{
"epoch": 3.830612244897959,
"grad_norm": 2.265625,
"learning_rate": 5.034013605442177e-05,
"loss": 3.4583,
"step": 1877
},
{
"epoch": 3.83265306122449,
"grad_norm": 2.203125,
"learning_rate": 5.0307742144476846e-05,
"loss": 3.4857,
"step": 1878
},
{
"epoch": 3.8346938775510204,
"grad_norm": 2.28125,
"learning_rate": 5.0275348234531904e-05,
"loss": 3.542,
"step": 1879
},
{
"epoch": 3.836734693877551,
"grad_norm": 2.28125,
"learning_rate": 5.024295432458698e-05,
"loss": 3.4379,
"step": 1880
},
{
"epoch": 3.8387755102040817,
"grad_norm": 2.1875,
"learning_rate": 5.021056041464205e-05,
"loss": 3.5353,
"step": 1881
},
{
"epoch": 3.840816326530612,
"grad_norm": 2.4375,
"learning_rate": 5.017816650469712e-05,
"loss": 3.2997,
"step": 1882
},
{
"epoch": 3.842857142857143,
"grad_norm": 2.3125,
"learning_rate": 5.0145772594752194e-05,
"loss": 3.5132,
"step": 1883
},
{
"epoch": 3.8448979591836734,
"grad_norm": 2.3125,
"learning_rate": 5.011337868480725e-05,
"loss": 3.503,
"step": 1884
},
{
"epoch": 3.8469387755102042,
"grad_norm": 2.265625,
"learning_rate": 5.0080984774862325e-05,
"loss": 3.4214,
"step": 1885
},
{
"epoch": 3.8489795918367347,
"grad_norm": 2.140625,
"learning_rate": 5.00485908649174e-05,
"loss": 3.3291,
"step": 1886
},
{
"epoch": 3.851020408163265,
"grad_norm": 2.1875,
"learning_rate": 5.001619695497247e-05,
"loss": 3.4123,
"step": 1887
},
{
"epoch": 3.853061224489796,
"grad_norm": 1.953125,
"learning_rate": 4.9983803045027535e-05,
"loss": 3.3773,
"step": 1888
},
{
"epoch": 3.855102040816327,
"grad_norm": 2.265625,
"learning_rate": 4.995140913508261e-05,
"loss": 3.3662,
"step": 1889
},
{
"epoch": 3.857142857142857,
"grad_norm": 2.328125,
"learning_rate": 4.991901522513768e-05,
"loss": 3.4996,
"step": 1890
},
{
"epoch": 3.8591836734693876,
"grad_norm": 2.015625,
"learning_rate": 4.9886621315192745e-05,
"loss": 3.4603,
"step": 1891
},
{
"epoch": 3.8612244897959185,
"grad_norm": 2.140625,
"learning_rate": 4.985422740524782e-05,
"loss": 3.5081,
"step": 1892
},
{
"epoch": 3.863265306122449,
"grad_norm": 2.1875,
"learning_rate": 4.9821833495302883e-05,
"loss": 3.5083,
"step": 1893
},
{
"epoch": 3.8653061224489798,
"grad_norm": 2.21875,
"learning_rate": 4.9789439585357956e-05,
"loss": 3.5541,
"step": 1894
},
{
"epoch": 3.86734693877551,
"grad_norm": 2.109375,
"learning_rate": 4.975704567541302e-05,
"loss": 3.4129,
"step": 1895
},
{
"epoch": 3.869387755102041,
"grad_norm": 2.3125,
"learning_rate": 4.9724651765468094e-05,
"loss": 3.457,
"step": 1896
},
{
"epoch": 3.8714285714285714,
"grad_norm": 2.1875,
"learning_rate": 4.9692257855523166e-05,
"loss": 3.4321,
"step": 1897
},
{
"epoch": 3.873469387755102,
"grad_norm": 2.0625,
"learning_rate": 4.965986394557823e-05,
"loss": 3.3792,
"step": 1898
},
{
"epoch": 3.8755102040816327,
"grad_norm": 2.234375,
"learning_rate": 4.9627470035633304e-05,
"loss": 3.3566,
"step": 1899
},
{
"epoch": 3.877551020408163,
"grad_norm": 2.40625,
"learning_rate": 4.959507612568837e-05,
"loss": 3.4019,
"step": 1900
},
{
"epoch": 3.879591836734694,
"grad_norm": 2.078125,
"learning_rate": 4.956268221574344e-05,
"loss": 3.4609,
"step": 1901
},
{
"epoch": 3.8816326530612244,
"grad_norm": 2.046875,
"learning_rate": 4.9530288305798514e-05,
"loss": 3.4236,
"step": 1902
},
{
"epoch": 3.8836734693877553,
"grad_norm": 2.3125,
"learning_rate": 4.9497894395853587e-05,
"loss": 3.3307,
"step": 1903
},
{
"epoch": 3.8857142857142857,
"grad_norm": 2.1875,
"learning_rate": 4.946550048590865e-05,
"loss": 3.3809,
"step": 1904
},
{
"epoch": 3.887755102040816,
"grad_norm": 2.046875,
"learning_rate": 4.9433106575963725e-05,
"loss": 3.4671,
"step": 1905
},
{
"epoch": 3.889795918367347,
"grad_norm": 2.015625,
"learning_rate": 4.940071266601879e-05,
"loss": 3.3508,
"step": 1906
},
{
"epoch": 3.891836734693878,
"grad_norm": 1.859375,
"learning_rate": 4.936831875607386e-05,
"loss": 3.3628,
"step": 1907
},
{
"epoch": 3.8938775510204082,
"grad_norm": 2.140625,
"learning_rate": 4.933592484612893e-05,
"loss": 3.5081,
"step": 1908
},
{
"epoch": 3.8959183673469386,
"grad_norm": 2.109375,
"learning_rate": 4.9303530936184e-05,
"loss": 3.4169,
"step": 1909
},
{
"epoch": 3.8979591836734695,
"grad_norm": 2.0625,
"learning_rate": 4.9271137026239066e-05,
"loss": 3.472,
"step": 1910
},
{
"epoch": 3.9,
"grad_norm": 2.203125,
"learning_rate": 4.923874311629414e-05,
"loss": 3.4098,
"step": 1911
},
{
"epoch": 3.9020408163265308,
"grad_norm": 2.09375,
"learning_rate": 4.9206349206349204e-05,
"loss": 3.4763,
"step": 1912
},
{
"epoch": 3.904081632653061,
"grad_norm": 2.125,
"learning_rate": 4.9173955296404276e-05,
"loss": 3.4713,
"step": 1913
},
{
"epoch": 3.906122448979592,
"grad_norm": 2.140625,
"learning_rate": 4.914156138645935e-05,
"loss": 3.3181,
"step": 1914
},
{
"epoch": 3.9081632653061225,
"grad_norm": 2.296875,
"learning_rate": 4.9109167476514414e-05,
"loss": 3.462,
"step": 1915
},
{
"epoch": 3.910204081632653,
"grad_norm": 1.875,
"learning_rate": 4.9076773566569486e-05,
"loss": 3.4091,
"step": 1916
},
{
"epoch": 3.9122448979591837,
"grad_norm": 1.96875,
"learning_rate": 4.904437965662456e-05,
"loss": 3.4491,
"step": 1917
},
{
"epoch": 3.914285714285714,
"grad_norm": 2.125,
"learning_rate": 4.901198574667963e-05,
"loss": 3.5265,
"step": 1918
},
{
"epoch": 3.916326530612245,
"grad_norm": 2.25,
"learning_rate": 4.89795918367347e-05,
"loss": 3.4668,
"step": 1919
},
{
"epoch": 3.9183673469387754,
"grad_norm": 2.078125,
"learning_rate": 4.894719792678977e-05,
"loss": 3.5042,
"step": 1920
},
{
"epoch": 3.9204081632653063,
"grad_norm": 2.125,
"learning_rate": 4.8914804016844835e-05,
"loss": 3.4502,
"step": 1921
},
{
"epoch": 3.9224489795918367,
"grad_norm": 2.375,
"learning_rate": 4.888241010689991e-05,
"loss": 3.3559,
"step": 1922
},
{
"epoch": 3.924489795918367,
"grad_norm": 2.078125,
"learning_rate": 4.885001619695497e-05,
"loss": 3.4113,
"step": 1923
},
{
"epoch": 3.926530612244898,
"grad_norm": 1.984375,
"learning_rate": 4.8817622287010045e-05,
"loss": 3.3915,
"step": 1924
},
{
"epoch": 3.928571428571429,
"grad_norm": 2.453125,
"learning_rate": 4.878522837706511e-05,
"loss": 3.3372,
"step": 1925
},
{
"epoch": 3.9306122448979592,
"grad_norm": 2.5,
"learning_rate": 4.875283446712018e-05,
"loss": 3.3469,
"step": 1926
},
{
"epoch": 3.9326530612244897,
"grad_norm": 2.09375,
"learning_rate": 4.872044055717525e-05,
"loss": 3.4411,
"step": 1927
},
{
"epoch": 3.9346938775510205,
"grad_norm": 1.9921875,
"learning_rate": 4.868804664723032e-05,
"loss": 3.4401,
"step": 1928
},
{
"epoch": 3.936734693877551,
"grad_norm": 2.25,
"learning_rate": 4.865565273728539e-05,
"loss": 3.3855,
"step": 1929
},
{
"epoch": 3.938775510204082,
"grad_norm": 2.21875,
"learning_rate": 4.862325882734046e-05,
"loss": 3.4084,
"step": 1930
},
{
"epoch": 3.940816326530612,
"grad_norm": 2.390625,
"learning_rate": 4.859086491739553e-05,
"loss": 3.4121,
"step": 1931
},
{
"epoch": 3.942857142857143,
"grad_norm": 2.3125,
"learning_rate": 4.8558471007450603e-05,
"loss": 3.4183,
"step": 1932
},
{
"epoch": 3.9448979591836735,
"grad_norm": 2.078125,
"learning_rate": 4.8526077097505676e-05,
"loss": 3.4573,
"step": 1933
},
{
"epoch": 3.946938775510204,
"grad_norm": 2.40625,
"learning_rate": 4.849368318756074e-05,
"loss": 3.3916,
"step": 1934
},
{
"epoch": 3.9489795918367347,
"grad_norm": 2.375,
"learning_rate": 4.8461289277615814e-05,
"loss": 3.3188,
"step": 1935
},
{
"epoch": 3.951020408163265,
"grad_norm": 2.21875,
"learning_rate": 4.842889536767088e-05,
"loss": 3.4503,
"step": 1936
},
{
"epoch": 3.953061224489796,
"grad_norm": 2.671875,
"learning_rate": 4.839650145772595e-05,
"loss": 3.4937,
"step": 1937
},
{
"epoch": 3.9551020408163264,
"grad_norm": 2.3125,
"learning_rate": 4.836410754778102e-05,
"loss": 3.4968,
"step": 1938
},
{
"epoch": 3.9571428571428573,
"grad_norm": 2.03125,
"learning_rate": 4.833171363783609e-05,
"loss": 3.5098,
"step": 1939
},
{
"epoch": 3.9591836734693877,
"grad_norm": 2.125,
"learning_rate": 4.8299319727891155e-05,
"loss": 3.4109,
"step": 1940
},
{
"epoch": 3.961224489795918,
"grad_norm": 2.265625,
"learning_rate": 4.826692581794623e-05,
"loss": 3.4511,
"step": 1941
},
{
"epoch": 3.963265306122449,
"grad_norm": 2.1875,
"learning_rate": 4.823453190800129e-05,
"loss": 3.5554,
"step": 1942
},
{
"epoch": 3.96530612244898,
"grad_norm": 2.234375,
"learning_rate": 4.8202137998056365e-05,
"loss": 3.4561,
"step": 1943
},
{
"epoch": 3.9673469387755103,
"grad_norm": 2.15625,
"learning_rate": 4.816974408811144e-05,
"loss": 3.522,
"step": 1944
},
{
"epoch": 3.9693877551020407,
"grad_norm": 2.171875,
"learning_rate": 4.813735017816651e-05,
"loss": 3.5313,
"step": 1945
},
{
"epoch": 3.9714285714285715,
"grad_norm": 2.21875,
"learning_rate": 4.810495626822158e-05,
"loss": 3.2735,
"step": 1946
},
{
"epoch": 3.973469387755102,
"grad_norm": 2.09375,
"learning_rate": 4.807256235827665e-05,
"loss": 3.3529,
"step": 1947
},
{
"epoch": 3.975510204081633,
"grad_norm": 2.0625,
"learning_rate": 4.804016844833172e-05,
"loss": 3.6025,
"step": 1948
},
{
"epoch": 3.977551020408163,
"grad_norm": 2.03125,
"learning_rate": 4.8007774538386786e-05,
"loss": 3.4223,
"step": 1949
},
{
"epoch": 3.979591836734694,
"grad_norm": 2.078125,
"learning_rate": 4.797538062844186e-05,
"loss": 3.3337,
"step": 1950
},
{
"epoch": 3.9816326530612245,
"grad_norm": 2.046875,
"learning_rate": 4.7942986718496924e-05,
"loss": 3.3363,
"step": 1951
},
{
"epoch": 3.983673469387755,
"grad_norm": 2.21875,
"learning_rate": 4.7910592808551996e-05,
"loss": 3.454,
"step": 1952
},
{
"epoch": 3.9857142857142858,
"grad_norm": 2.265625,
"learning_rate": 4.787819889860706e-05,
"loss": 3.408,
"step": 1953
},
{
"epoch": 3.987755102040816,
"grad_norm": 2.25,
"learning_rate": 4.7845804988662134e-05,
"loss": 3.3896,
"step": 1954
},
{
"epoch": 3.989795918367347,
"grad_norm": 2.421875,
"learning_rate": 4.78134110787172e-05,
"loss": 3.4961,
"step": 1955
},
{
"epoch": 3.9918367346938775,
"grad_norm": 2.3125,
"learning_rate": 4.778101716877227e-05,
"loss": 3.3614,
"step": 1956
},
{
"epoch": 3.9938775510204083,
"grad_norm": 2.171875,
"learning_rate": 4.774862325882734e-05,
"loss": 3.3644,
"step": 1957
},
{
"epoch": 3.9959183673469387,
"grad_norm": 1.9140625,
"learning_rate": 4.771622934888241e-05,
"loss": 3.3965,
"step": 1958
},
{
"epoch": 3.997959183673469,
"grad_norm": 2.0625,
"learning_rate": 4.768383543893748e-05,
"loss": 3.4523,
"step": 1959
},
{
"epoch": 4.0,
"grad_norm": 2.046875,
"learning_rate": 4.7651441528992555e-05,
"loss": 3.3894,
"step": 1960
},
{
"epoch": 4.002040816326531,
"grad_norm": 4.40625,
"learning_rate": 4.761904761904762e-05,
"loss": 2.7113,
"step": 1961
},
{
"epoch": 4.004081632653061,
"grad_norm": 4.28125,
"learning_rate": 4.758665370910269e-05,
"loss": 2.6844,
"step": 1962
},
{
"epoch": 4.006122448979592,
"grad_norm": 3.140625,
"learning_rate": 4.7554259799157765e-05,
"loss": 2.5534,
"step": 1963
},
{
"epoch": 4.0081632653061225,
"grad_norm": 3.046875,
"learning_rate": 4.752186588921283e-05,
"loss": 2.6762,
"step": 1964
},
{
"epoch": 4.010204081632653,
"grad_norm": 3.578125,
"learning_rate": 4.74894719792679e-05,
"loss": 2.5501,
"step": 1965
},
{
"epoch": 4.012244897959183,
"grad_norm": 4.5625,
"learning_rate": 4.745707806932297e-05,
"loss": 2.6461,
"step": 1966
},
{
"epoch": 4.014285714285714,
"grad_norm": 4.21875,
"learning_rate": 4.742468415937804e-05,
"loss": 2.5861,
"step": 1967
},
{
"epoch": 4.016326530612245,
"grad_norm": 3.546875,
"learning_rate": 4.7392290249433106e-05,
"loss": 2.664,
"step": 1968
},
{
"epoch": 4.018367346938776,
"grad_norm": 3.359375,
"learning_rate": 4.735989633948818e-05,
"loss": 2.5438,
"step": 1969
},
{
"epoch": 4.020408163265306,
"grad_norm": 3.28125,
"learning_rate": 4.7327502429543244e-05,
"loss": 2.4938,
"step": 1970
},
{
"epoch": 4.022448979591837,
"grad_norm": 3.109375,
"learning_rate": 4.729510851959832e-05,
"loss": 2.5062,
"step": 1971
},
{
"epoch": 4.024489795918368,
"grad_norm": 3.046875,
"learning_rate": 4.726271460965338e-05,
"loss": 2.4742,
"step": 1972
},
{
"epoch": 4.026530612244898,
"grad_norm": 3.015625,
"learning_rate": 4.7230320699708455e-05,
"loss": 2.4641,
"step": 1973
},
{
"epoch": 4.0285714285714285,
"grad_norm": 2.875,
"learning_rate": 4.719792678976353e-05,
"loss": 2.3775,
"step": 1974
},
{
"epoch": 4.030612244897959,
"grad_norm": 3.015625,
"learning_rate": 4.71655328798186e-05,
"loss": 2.4747,
"step": 1975
},
{
"epoch": 4.03265306122449,
"grad_norm": 2.953125,
"learning_rate": 4.7133138969873665e-05,
"loss": 2.5731,
"step": 1976
},
{
"epoch": 4.03469387755102,
"grad_norm": 2.78125,
"learning_rate": 4.710074505992874e-05,
"loss": 2.5632,
"step": 1977
},
{
"epoch": 4.036734693877551,
"grad_norm": 2.71875,
"learning_rate": 4.70683511499838e-05,
"loss": 2.3868,
"step": 1978
},
{
"epoch": 4.038775510204082,
"grad_norm": 2.765625,
"learning_rate": 4.7035957240038875e-05,
"loss": 2.4346,
"step": 1979
},
{
"epoch": 4.040816326530612,
"grad_norm": 2.6875,
"learning_rate": 4.700356333009395e-05,
"loss": 2.4132,
"step": 1980
},
{
"epoch": 4.042857142857143,
"grad_norm": 2.828125,
"learning_rate": 4.697116942014901e-05,
"loss": 2.4468,
"step": 1981
},
{
"epoch": 4.044897959183674,
"grad_norm": 2.96875,
"learning_rate": 4.6938775510204086e-05,
"loss": 2.45,
"step": 1982
},
{
"epoch": 4.046938775510204,
"grad_norm": 3.015625,
"learning_rate": 4.690638160025915e-05,
"loss": 2.4232,
"step": 1983
},
{
"epoch": 4.048979591836734,
"grad_norm": 2.65625,
"learning_rate": 4.6873987690314223e-05,
"loss": 2.4314,
"step": 1984
},
{
"epoch": 4.051020408163265,
"grad_norm": 2.921875,
"learning_rate": 4.684159378036929e-05,
"loss": 2.2679,
"step": 1985
},
{
"epoch": 4.053061224489796,
"grad_norm": 2.828125,
"learning_rate": 4.680919987042436e-05,
"loss": 2.447,
"step": 1986
},
{
"epoch": 4.055102040816327,
"grad_norm": 2.890625,
"learning_rate": 4.6776805960479434e-05,
"loss": 2.3749,
"step": 1987
},
{
"epoch": 4.057142857142857,
"grad_norm": 2.8125,
"learning_rate": 4.6744412050534506e-05,
"loss": 2.4267,
"step": 1988
},
{
"epoch": 4.059183673469388,
"grad_norm": 3.015625,
"learning_rate": 4.671201814058957e-05,
"loss": 2.3769,
"step": 1989
},
{
"epoch": 4.061224489795919,
"grad_norm": 2.640625,
"learning_rate": 4.6679624230644644e-05,
"loss": 2.3978,
"step": 1990
},
{
"epoch": 4.063265306122449,
"grad_norm": 2.90625,
"learning_rate": 4.664723032069971e-05,
"loss": 2.3004,
"step": 1991
},
{
"epoch": 4.0653061224489795,
"grad_norm": 2.953125,
"learning_rate": 4.661483641075478e-05,
"loss": 2.3596,
"step": 1992
},
{
"epoch": 4.06734693877551,
"grad_norm": 2.796875,
"learning_rate": 4.658244250080985e-05,
"loss": 2.4023,
"step": 1993
},
{
"epoch": 4.069387755102041,
"grad_norm": 2.859375,
"learning_rate": 4.655004859086492e-05,
"loss": 2.465,
"step": 1994
},
{
"epoch": 4.071428571428571,
"grad_norm": 2.90625,
"learning_rate": 4.651765468091999e-05,
"loss": 2.3229,
"step": 1995
},
{
"epoch": 4.073469387755102,
"grad_norm": 2.8125,
"learning_rate": 4.648526077097506e-05,
"loss": 2.3934,
"step": 1996
},
{
"epoch": 4.075510204081633,
"grad_norm": 2.921875,
"learning_rate": 4.645286686103013e-05,
"loss": 2.4088,
"step": 1997
},
{
"epoch": 4.077551020408163,
"grad_norm": 2.859375,
"learning_rate": 4.6420472951085196e-05,
"loss": 2.2878,
"step": 1998
},
{
"epoch": 4.079591836734694,
"grad_norm": 2.796875,
"learning_rate": 4.638807904114027e-05,
"loss": 2.3958,
"step": 1999
},
{
"epoch": 4.081632653061225,
"grad_norm": 3.09375,
"learning_rate": 4.6355685131195334e-05,
"loss": 2.4641,
"step": 2000
},
{
"epoch": 4.081632653061225,
"eval_loss": 4.328609943389893,
"eval_runtime": 5.3793,
"eval_samples_per_second": 29.744,
"eval_steps_per_second": 7.436,
"step": 2000
},
{
"epoch": 4.083673469387755,
"grad_norm": 2.90625,
"learning_rate": 4.6323291221250406e-05,
"loss": 2.4247,
"step": 2001
},
{
"epoch": 4.085714285714285,
"grad_norm": 2.921875,
"learning_rate": 4.629089731130548e-05,
"loss": 2.3869,
"step": 2002
},
{
"epoch": 4.087755102040816,
"grad_norm": 2.953125,
"learning_rate": 4.625850340136055e-05,
"loss": 2.3143,
"step": 2003
},
{
"epoch": 4.089795918367347,
"grad_norm": 2.875,
"learning_rate": 4.6226109491415616e-05,
"loss": 2.3457,
"step": 2004
},
{
"epoch": 4.091836734693878,
"grad_norm": 3.109375,
"learning_rate": 4.619371558147069e-05,
"loss": 2.3232,
"step": 2005
},
{
"epoch": 4.093877551020408,
"grad_norm": 2.859375,
"learning_rate": 4.6161321671525754e-05,
"loss": 2.321,
"step": 2006
},
{
"epoch": 4.095918367346939,
"grad_norm": 3.0,
"learning_rate": 4.6128927761580827e-05,
"loss": 2.4116,
"step": 2007
},
{
"epoch": 4.09795918367347,
"grad_norm": 2.828125,
"learning_rate": 4.609653385163589e-05,
"loss": 2.431,
"step": 2008
},
{
"epoch": 4.1,
"grad_norm": 3.03125,
"learning_rate": 4.6064139941690965e-05,
"loss": 2.3627,
"step": 2009
},
{
"epoch": 4.1020408163265305,
"grad_norm": 2.796875,
"learning_rate": 4.603174603174603e-05,
"loss": 2.2277,
"step": 2010
},
{
"epoch": 4.104081632653061,
"grad_norm": 3.078125,
"learning_rate": 4.59993521218011e-05,
"loss": 2.3831,
"step": 2011
},
{
"epoch": 4.106122448979592,
"grad_norm": 2.921875,
"learning_rate": 4.5966958211856175e-05,
"loss": 2.3938,
"step": 2012
},
{
"epoch": 4.108163265306122,
"grad_norm": 3.046875,
"learning_rate": 4.593456430191124e-05,
"loss": 2.2894,
"step": 2013
},
{
"epoch": 4.110204081632653,
"grad_norm": 3.234375,
"learning_rate": 4.590217039196631e-05,
"loss": 2.4361,
"step": 2014
},
{
"epoch": 4.112244897959184,
"grad_norm": 3.1875,
"learning_rate": 4.586977648202138e-05,
"loss": 2.2841,
"step": 2015
},
{
"epoch": 4.114285714285714,
"grad_norm": 2.765625,
"learning_rate": 4.583738257207645e-05,
"loss": 2.3232,
"step": 2016
},
{
"epoch": 4.116326530612245,
"grad_norm": 2.828125,
"learning_rate": 4.580498866213152e-05,
"loss": 2.3634,
"step": 2017
},
{
"epoch": 4.118367346938776,
"grad_norm": 3.03125,
"learning_rate": 4.5772594752186595e-05,
"loss": 2.3481,
"step": 2018
},
{
"epoch": 4.1204081632653065,
"grad_norm": 3.265625,
"learning_rate": 4.574020084224166e-05,
"loss": 2.2324,
"step": 2019
},
{
"epoch": 4.122448979591836,
"grad_norm": 2.875,
"learning_rate": 4.570780693229673e-05,
"loss": 2.2846,
"step": 2020
},
{
"epoch": 4.124489795918367,
"grad_norm": 2.953125,
"learning_rate": 4.56754130223518e-05,
"loss": 2.3354,
"step": 2021
},
{
"epoch": 4.126530612244898,
"grad_norm": 2.796875,
"learning_rate": 4.564301911240687e-05,
"loss": 2.3512,
"step": 2022
},
{
"epoch": 4.128571428571428,
"grad_norm": 2.96875,
"learning_rate": 4.561062520246194e-05,
"loss": 2.3471,
"step": 2023
},
{
"epoch": 4.130612244897959,
"grad_norm": 2.671875,
"learning_rate": 4.557823129251701e-05,
"loss": 2.2946,
"step": 2024
},
{
"epoch": 4.13265306122449,
"grad_norm": 2.609375,
"learning_rate": 4.5545837382572075e-05,
"loss": 2.3754,
"step": 2025
},
{
"epoch": 4.134693877551021,
"grad_norm": 2.9375,
"learning_rate": 4.551344347262715e-05,
"loss": 2.2485,
"step": 2026
},
{
"epoch": 4.136734693877551,
"grad_norm": 2.96875,
"learning_rate": 4.548104956268221e-05,
"loss": 2.3208,
"step": 2027
},
{
"epoch": 4.1387755102040815,
"grad_norm": 2.78125,
"learning_rate": 4.5448655652737285e-05,
"loss": 2.3455,
"step": 2028
},
{
"epoch": 4.140816326530612,
"grad_norm": 2.84375,
"learning_rate": 4.541626174279236e-05,
"loss": 2.2831,
"step": 2029
},
{
"epoch": 4.142857142857143,
"grad_norm": 3.0625,
"learning_rate": 4.538386783284743e-05,
"loss": 2.259,
"step": 2030
},
{
"epoch": 4.144897959183673,
"grad_norm": 3.0,
"learning_rate": 4.53514739229025e-05,
"loss": 2.2822,
"step": 2031
},
{
"epoch": 4.146938775510204,
"grad_norm": 2.703125,
"learning_rate": 4.531908001295757e-05,
"loss": 2.3315,
"step": 2032
},
{
"epoch": 4.148979591836735,
"grad_norm": 3.171875,
"learning_rate": 4.528668610301264e-05,
"loss": 2.3228,
"step": 2033
},
{
"epoch": 4.151020408163265,
"grad_norm": 2.828125,
"learning_rate": 4.5254292193067706e-05,
"loss": 2.2717,
"step": 2034
},
{
"epoch": 4.153061224489796,
"grad_norm": 3.0,
"learning_rate": 4.522189828312278e-05,
"loss": 2.2878,
"step": 2035
},
{
"epoch": 4.155102040816327,
"grad_norm": 3.0,
"learning_rate": 4.5189504373177843e-05,
"loss": 2.3047,
"step": 2036
},
{
"epoch": 4.1571428571428575,
"grad_norm": 2.984375,
"learning_rate": 4.5157110463232916e-05,
"loss": 2.376,
"step": 2037
},
{
"epoch": 4.159183673469387,
"grad_norm": 3.34375,
"learning_rate": 4.512471655328798e-05,
"loss": 2.5557,
"step": 2038
},
{
"epoch": 4.161224489795918,
"grad_norm": 2.90625,
"learning_rate": 4.5092322643343054e-05,
"loss": 2.3314,
"step": 2039
},
{
"epoch": 4.163265306122449,
"grad_norm": 2.8125,
"learning_rate": 4.505992873339812e-05,
"loss": 2.4084,
"step": 2040
},
{
"epoch": 4.16530612244898,
"grad_norm": 3.203125,
"learning_rate": 4.502753482345319e-05,
"loss": 2.3107,
"step": 2041
},
{
"epoch": 4.16734693877551,
"grad_norm": 3.15625,
"learning_rate": 4.499514091350826e-05,
"loss": 2.3594,
"step": 2042
},
{
"epoch": 4.169387755102041,
"grad_norm": 2.96875,
"learning_rate": 4.496274700356333e-05,
"loss": 2.4199,
"step": 2043
},
{
"epoch": 4.171428571428572,
"grad_norm": 3.125,
"learning_rate": 4.49303530936184e-05,
"loss": 2.4666,
"step": 2044
},
{
"epoch": 4.173469387755102,
"grad_norm": 3.15625,
"learning_rate": 4.4897959183673474e-05,
"loss": 2.3937,
"step": 2045
},
{
"epoch": 4.1755102040816325,
"grad_norm": 2.9375,
"learning_rate": 4.486556527372855e-05,
"loss": 2.2491,
"step": 2046
},
{
"epoch": 4.177551020408163,
"grad_norm": 3.046875,
"learning_rate": 4.483317136378361e-05,
"loss": 2.337,
"step": 2047
},
{
"epoch": 4.179591836734694,
"grad_norm": 3.0,
"learning_rate": 4.4800777453838685e-05,
"loss": 2.2909,
"step": 2048
},
{
"epoch": 4.181632653061224,
"grad_norm": 2.96875,
"learning_rate": 4.476838354389375e-05,
"loss": 2.4016,
"step": 2049
},
{
"epoch": 4.183673469387755,
"grad_norm": 2.921875,
"learning_rate": 4.473598963394882e-05,
"loss": 2.2899,
"step": 2050
},
{
"epoch": 4.185714285714286,
"grad_norm": 2.875,
"learning_rate": 4.470359572400389e-05,
"loss": 2.338,
"step": 2051
},
{
"epoch": 4.187755102040816,
"grad_norm": 2.921875,
"learning_rate": 4.467120181405896e-05,
"loss": 2.2785,
"step": 2052
},
{
"epoch": 4.189795918367347,
"grad_norm": 3.03125,
"learning_rate": 4.4638807904114026e-05,
"loss": 2.2287,
"step": 2053
},
{
"epoch": 4.191836734693878,
"grad_norm": 3.265625,
"learning_rate": 4.46064139941691e-05,
"loss": 2.1878,
"step": 2054
},
{
"epoch": 4.1938775510204085,
"grad_norm": 2.96875,
"learning_rate": 4.4574020084224164e-05,
"loss": 2.2929,
"step": 2055
},
{
"epoch": 4.1959183673469385,
"grad_norm": 2.84375,
"learning_rate": 4.4541626174279236e-05,
"loss": 2.2614,
"step": 2056
},
{
"epoch": 4.197959183673469,
"grad_norm": 3.0625,
"learning_rate": 4.45092322643343e-05,
"loss": 2.483,
"step": 2057
},
{
"epoch": 4.2,
"grad_norm": 2.796875,
"learning_rate": 4.4476838354389374e-05,
"loss": 2.4164,
"step": 2058
},
{
"epoch": 4.202040816326531,
"grad_norm": 3.203125,
"learning_rate": 4.4444444444444447e-05,
"loss": 2.2091,
"step": 2059
},
{
"epoch": 4.204081632653061,
"grad_norm": 3.03125,
"learning_rate": 4.441205053449952e-05,
"loss": 2.3491,
"step": 2060
},
{
"epoch": 4.206122448979592,
"grad_norm": 2.859375,
"learning_rate": 4.437965662455459e-05,
"loss": 2.2463,
"step": 2061
},
{
"epoch": 4.208163265306123,
"grad_norm": 2.796875,
"learning_rate": 4.434726271460966e-05,
"loss": 2.3224,
"step": 2062
},
{
"epoch": 4.210204081632653,
"grad_norm": 3.203125,
"learning_rate": 4.431486880466473e-05,
"loss": 2.3437,
"step": 2063
},
{
"epoch": 4.2122448979591836,
"grad_norm": 2.921875,
"learning_rate": 4.4282474894719795e-05,
"loss": 2.274,
"step": 2064
},
{
"epoch": 4.214285714285714,
"grad_norm": 3.0,
"learning_rate": 4.425008098477487e-05,
"loss": 2.3115,
"step": 2065
},
{
"epoch": 4.216326530612245,
"grad_norm": 3.125,
"learning_rate": 4.421768707482993e-05,
"loss": 2.3288,
"step": 2066
},
{
"epoch": 4.218367346938775,
"grad_norm": 2.8125,
"learning_rate": 4.4185293164885005e-05,
"loss": 2.2974,
"step": 2067
},
{
"epoch": 4.220408163265306,
"grad_norm": 3.0,
"learning_rate": 4.415289925494007e-05,
"loss": 2.3152,
"step": 2068
},
{
"epoch": 4.222448979591837,
"grad_norm": 3.4375,
"learning_rate": 4.412050534499514e-05,
"loss": 2.2816,
"step": 2069
},
{
"epoch": 4.224489795918367,
"grad_norm": 3.046875,
"learning_rate": 4.408811143505021e-05,
"loss": 2.2808,
"step": 2070
},
{
"epoch": 4.226530612244898,
"grad_norm": 2.984375,
"learning_rate": 4.405571752510528e-05,
"loss": 2.3282,
"step": 2071
},
{
"epoch": 4.228571428571429,
"grad_norm": 3.015625,
"learning_rate": 4.402332361516035e-05,
"loss": 2.3877,
"step": 2072
},
{
"epoch": 4.2306122448979595,
"grad_norm": 3.40625,
"learning_rate": 4.3990929705215426e-05,
"loss": 2.3049,
"step": 2073
},
{
"epoch": 4.2326530612244895,
"grad_norm": 3.140625,
"learning_rate": 4.395853579527049e-05,
"loss": 2.4455,
"step": 2074
},
{
"epoch": 4.23469387755102,
"grad_norm": 2.953125,
"learning_rate": 4.3926141885325564e-05,
"loss": 2.2927,
"step": 2075
},
{
"epoch": 4.236734693877551,
"grad_norm": 3.25,
"learning_rate": 4.389374797538063e-05,
"loss": 2.2821,
"step": 2076
},
{
"epoch": 4.238775510204082,
"grad_norm": 3.15625,
"learning_rate": 4.38613540654357e-05,
"loss": 2.3114,
"step": 2077
},
{
"epoch": 4.240816326530612,
"grad_norm": 3.125,
"learning_rate": 4.3828960155490774e-05,
"loss": 2.2439,
"step": 2078
},
{
"epoch": 4.242857142857143,
"grad_norm": 3.171875,
"learning_rate": 4.379656624554584e-05,
"loss": 2.3257,
"step": 2079
},
{
"epoch": 4.244897959183674,
"grad_norm": 3.0625,
"learning_rate": 4.376417233560091e-05,
"loss": 2.3629,
"step": 2080
},
{
"epoch": 4.246938775510204,
"grad_norm": 3.0625,
"learning_rate": 4.373177842565598e-05,
"loss": 2.2832,
"step": 2081
},
{
"epoch": 4.248979591836735,
"grad_norm": 2.859375,
"learning_rate": 4.369938451571105e-05,
"loss": 2.3394,
"step": 2082
},
{
"epoch": 4.251020408163265,
"grad_norm": 3.1875,
"learning_rate": 4.3666990605766115e-05,
"loss": 2.3128,
"step": 2083
},
{
"epoch": 4.253061224489796,
"grad_norm": 3.0625,
"learning_rate": 4.363459669582119e-05,
"loss": 2.2695,
"step": 2084
},
{
"epoch": 4.255102040816326,
"grad_norm": 2.96875,
"learning_rate": 4.360220278587625e-05,
"loss": 2.4655,
"step": 2085
},
{
"epoch": 4.257142857142857,
"grad_norm": 3.109375,
"learning_rate": 4.3569808875931326e-05,
"loss": 2.2337,
"step": 2086
},
{
"epoch": 4.259183673469388,
"grad_norm": 3.09375,
"learning_rate": 4.35374149659864e-05,
"loss": 2.3701,
"step": 2087
},
{
"epoch": 4.261224489795918,
"grad_norm": 2.90625,
"learning_rate": 4.350502105604147e-05,
"loss": 2.2859,
"step": 2088
},
{
"epoch": 4.263265306122449,
"grad_norm": 2.875,
"learning_rate": 4.3472627146096536e-05,
"loss": 2.2047,
"step": 2089
},
{
"epoch": 4.26530612244898,
"grad_norm": 2.953125,
"learning_rate": 4.344023323615161e-05,
"loss": 2.3578,
"step": 2090
},
{
"epoch": 4.2673469387755105,
"grad_norm": 2.984375,
"learning_rate": 4.3407839326206674e-05,
"loss": 2.3058,
"step": 2091
},
{
"epoch": 4.2693877551020405,
"grad_norm": 3.125,
"learning_rate": 4.3375445416261746e-05,
"loss": 2.3138,
"step": 2092
},
{
"epoch": 4.271428571428571,
"grad_norm": 2.953125,
"learning_rate": 4.334305150631681e-05,
"loss": 2.2521,
"step": 2093
},
{
"epoch": 4.273469387755102,
"grad_norm": 3.5,
"learning_rate": 4.3310657596371884e-05,
"loss": 2.3911,
"step": 2094
},
{
"epoch": 4.275510204081632,
"grad_norm": 3.3125,
"learning_rate": 4.3278263686426956e-05,
"loss": 2.3058,
"step": 2095
},
{
"epoch": 4.277551020408163,
"grad_norm": 2.765625,
"learning_rate": 4.324586977648202e-05,
"loss": 2.271,
"step": 2096
},
{
"epoch": 4.279591836734694,
"grad_norm": 3.15625,
"learning_rate": 4.3213475866537094e-05,
"loss": 2.4797,
"step": 2097
},
{
"epoch": 4.281632653061225,
"grad_norm": 3.515625,
"learning_rate": 4.318108195659216e-05,
"loss": 2.3293,
"step": 2098
},
{
"epoch": 4.283673469387755,
"grad_norm": 3.546875,
"learning_rate": 4.314868804664723e-05,
"loss": 2.2801,
"step": 2099
},
{
"epoch": 4.285714285714286,
"grad_norm": 2.796875,
"learning_rate": 4.31162941367023e-05,
"loss": 2.3641,
"step": 2100
},
{
"epoch": 4.2877551020408164,
"grad_norm": 3.0,
"learning_rate": 4.308390022675737e-05,
"loss": 2.3088,
"step": 2101
},
{
"epoch": 4.289795918367347,
"grad_norm": 3.484375,
"learning_rate": 4.305150631681244e-05,
"loss": 2.2893,
"step": 2102
},
{
"epoch": 4.291836734693877,
"grad_norm": 3.515625,
"learning_rate": 4.3019112406867515e-05,
"loss": 2.2868,
"step": 2103
},
{
"epoch": 4.293877551020408,
"grad_norm": 3.4375,
"learning_rate": 4.298671849692258e-05,
"loss": 2.2957,
"step": 2104
},
{
"epoch": 4.295918367346939,
"grad_norm": 3.109375,
"learning_rate": 4.295432458697765e-05,
"loss": 2.3539,
"step": 2105
},
{
"epoch": 4.29795918367347,
"grad_norm": 3.265625,
"learning_rate": 4.292193067703272e-05,
"loss": 2.4365,
"step": 2106
},
{
"epoch": 4.3,
"grad_norm": 3.203125,
"learning_rate": 4.288953676708779e-05,
"loss": 2.2233,
"step": 2107
},
{
"epoch": 4.302040816326531,
"grad_norm": 3.234375,
"learning_rate": 4.2857142857142856e-05,
"loss": 2.2647,
"step": 2108
},
{
"epoch": 4.3040816326530615,
"grad_norm": 3.140625,
"learning_rate": 4.282474894719793e-05,
"loss": 2.3727,
"step": 2109
},
{
"epoch": 4.3061224489795915,
"grad_norm": 3.03125,
"learning_rate": 4.2792355037252994e-05,
"loss": 2.2632,
"step": 2110
},
{
"epoch": 4.308163265306122,
"grad_norm": 3.03125,
"learning_rate": 4.2759961127308067e-05,
"loss": 2.3352,
"step": 2111
},
{
"epoch": 4.310204081632653,
"grad_norm": 3.28125,
"learning_rate": 4.272756721736314e-05,
"loss": 2.1889,
"step": 2112
},
{
"epoch": 4.312244897959184,
"grad_norm": 3.046875,
"learning_rate": 4.2695173307418204e-05,
"loss": 2.3447,
"step": 2113
},
{
"epoch": 4.314285714285714,
"grad_norm": 3.328125,
"learning_rate": 4.266277939747328e-05,
"loss": 2.3224,
"step": 2114
},
{
"epoch": 4.316326530612245,
"grad_norm": 2.921875,
"learning_rate": 4.263038548752835e-05,
"loss": 2.3803,
"step": 2115
},
{
"epoch": 4.318367346938776,
"grad_norm": 3.078125,
"learning_rate": 4.259799157758342e-05,
"loss": 2.3084,
"step": 2116
},
{
"epoch": 4.320408163265306,
"grad_norm": 3.109375,
"learning_rate": 4.256559766763849e-05,
"loss": 2.3899,
"step": 2117
},
{
"epoch": 4.322448979591837,
"grad_norm": 3.46875,
"learning_rate": 4.253320375769356e-05,
"loss": 2.3742,
"step": 2118
},
{
"epoch": 4.3244897959183675,
"grad_norm": 3.421875,
"learning_rate": 4.2500809847748625e-05,
"loss": 2.3441,
"step": 2119
},
{
"epoch": 4.326530612244898,
"grad_norm": 3.15625,
"learning_rate": 4.24684159378037e-05,
"loss": 2.3004,
"step": 2120
},
{
"epoch": 4.328571428571428,
"grad_norm": 2.859375,
"learning_rate": 4.243602202785876e-05,
"loss": 2.4438,
"step": 2121
},
{
"epoch": 4.330612244897959,
"grad_norm": 3.046875,
"learning_rate": 4.2403628117913835e-05,
"loss": 2.4046,
"step": 2122
},
{
"epoch": 4.33265306122449,
"grad_norm": 3.234375,
"learning_rate": 4.23712342079689e-05,
"loss": 2.3087,
"step": 2123
},
{
"epoch": 4.33469387755102,
"grad_norm": 3.125,
"learning_rate": 4.233884029802397e-05,
"loss": 2.3644,
"step": 2124
},
{
"epoch": 4.336734693877551,
"grad_norm": 2.96875,
"learning_rate": 4.230644638807904e-05,
"loss": 2.37,
"step": 2125
},
{
"epoch": 4.338775510204082,
"grad_norm": 3.3125,
"learning_rate": 4.227405247813411e-05,
"loss": 2.2831,
"step": 2126
},
{
"epoch": 4.340816326530613,
"grad_norm": 3.171875,
"learning_rate": 4.2241658568189184e-05,
"loss": 2.3253,
"step": 2127
},
{
"epoch": 4.3428571428571425,
"grad_norm": 3.328125,
"learning_rate": 4.220926465824425e-05,
"loss": 2.3343,
"step": 2128
},
{
"epoch": 4.344897959183673,
"grad_norm": 3.46875,
"learning_rate": 4.217687074829932e-05,
"loss": 2.2406,
"step": 2129
},
{
"epoch": 4.346938775510204,
"grad_norm": 3.015625,
"learning_rate": 4.2144476838354394e-05,
"loss": 2.2875,
"step": 2130
},
{
"epoch": 4.348979591836735,
"grad_norm": 3.078125,
"learning_rate": 4.2112082928409466e-05,
"loss": 2.2989,
"step": 2131
},
{
"epoch": 4.351020408163265,
"grad_norm": 3.078125,
"learning_rate": 4.207968901846453e-05,
"loss": 2.3268,
"step": 2132
},
{
"epoch": 4.353061224489796,
"grad_norm": 3.40625,
"learning_rate": 4.2047295108519604e-05,
"loss": 2.3127,
"step": 2133
},
{
"epoch": 4.355102040816327,
"grad_norm": 3.125,
"learning_rate": 4.201490119857467e-05,
"loss": 2.3932,
"step": 2134
},
{
"epoch": 4.357142857142857,
"grad_norm": 3.203125,
"learning_rate": 4.198250728862974e-05,
"loss": 2.2967,
"step": 2135
},
{
"epoch": 4.359183673469388,
"grad_norm": 3.140625,
"learning_rate": 4.195011337868481e-05,
"loss": 2.2364,
"step": 2136
},
{
"epoch": 4.3612244897959185,
"grad_norm": 3.265625,
"learning_rate": 4.191771946873988e-05,
"loss": 2.3888,
"step": 2137
},
{
"epoch": 4.363265306122449,
"grad_norm": 3.0625,
"learning_rate": 4.1885325558794946e-05,
"loss": 2.2268,
"step": 2138
},
{
"epoch": 4.365306122448979,
"grad_norm": 3.046875,
"learning_rate": 4.185293164885002e-05,
"loss": 2.2972,
"step": 2139
},
{
"epoch": 4.36734693877551,
"grad_norm": 3.140625,
"learning_rate": 4.1820537738905083e-05,
"loss": 2.3227,
"step": 2140
},
{
"epoch": 4.369387755102041,
"grad_norm": 3.09375,
"learning_rate": 4.1788143828960156e-05,
"loss": 2.2882,
"step": 2141
},
{
"epoch": 4.371428571428572,
"grad_norm": 3.546875,
"learning_rate": 4.175574991901522e-05,
"loss": 2.4363,
"step": 2142
},
{
"epoch": 4.373469387755102,
"grad_norm": 3.171875,
"learning_rate": 4.1723356009070294e-05,
"loss": 2.3141,
"step": 2143
},
{
"epoch": 4.375510204081633,
"grad_norm": 3.1875,
"learning_rate": 4.1690962099125366e-05,
"loss": 2.222,
"step": 2144
},
{
"epoch": 4.377551020408164,
"grad_norm": 3.15625,
"learning_rate": 4.165856818918044e-05,
"loss": 2.1358,
"step": 2145
},
{
"epoch": 4.3795918367346935,
"grad_norm": 3.0625,
"learning_rate": 4.162617427923551e-05,
"loss": 2.3755,
"step": 2146
},
{
"epoch": 4.381632653061224,
"grad_norm": 3.34375,
"learning_rate": 4.1593780369290576e-05,
"loss": 2.3114,
"step": 2147
},
{
"epoch": 4.383673469387755,
"grad_norm": 3.390625,
"learning_rate": 4.156138645934565e-05,
"loss": 2.2699,
"step": 2148
},
{
"epoch": 4.385714285714286,
"grad_norm": 3.515625,
"learning_rate": 4.1528992549400714e-05,
"loss": 2.2426,
"step": 2149
},
{
"epoch": 4.387755102040816,
"grad_norm": 3.59375,
"learning_rate": 4.149659863945579e-05,
"loss": 2.2792,
"step": 2150
},
{
"epoch": 4.389795918367347,
"grad_norm": 2.9375,
"learning_rate": 4.146420472951085e-05,
"loss": 2.2197,
"step": 2151
},
{
"epoch": 4.391836734693878,
"grad_norm": 3.3125,
"learning_rate": 4.1431810819565925e-05,
"loss": 2.2405,
"step": 2152
},
{
"epoch": 4.393877551020408,
"grad_norm": 3.484375,
"learning_rate": 4.139941690962099e-05,
"loss": 2.2902,
"step": 2153
},
{
"epoch": 4.395918367346939,
"grad_norm": 3.234375,
"learning_rate": 4.136702299967606e-05,
"loss": 2.3196,
"step": 2154
},
{
"epoch": 4.3979591836734695,
"grad_norm": 3.34375,
"learning_rate": 4.133462908973113e-05,
"loss": 2.3054,
"step": 2155
},
{
"epoch": 4.4,
"grad_norm": 3.484375,
"learning_rate": 4.13022351797862e-05,
"loss": 2.3002,
"step": 2156
},
{
"epoch": 4.40204081632653,
"grad_norm": 3.046875,
"learning_rate": 4.126984126984127e-05,
"loss": 2.3733,
"step": 2157
},
{
"epoch": 4.404081632653061,
"grad_norm": 3.296875,
"learning_rate": 4.1237447359896345e-05,
"loss": 2.3329,
"step": 2158
},
{
"epoch": 4.406122448979592,
"grad_norm": 3.15625,
"learning_rate": 4.120505344995141e-05,
"loss": 2.2688,
"step": 2159
},
{
"epoch": 4.408163265306122,
"grad_norm": 3.140625,
"learning_rate": 4.117265954000648e-05,
"loss": 2.3077,
"step": 2160
},
{
"epoch": 4.410204081632653,
"grad_norm": 3.171875,
"learning_rate": 4.1140265630061555e-05,
"loss": 2.2758,
"step": 2161
},
{
"epoch": 4.412244897959184,
"grad_norm": 3.03125,
"learning_rate": 4.110787172011662e-05,
"loss": 2.3628,
"step": 2162
},
{
"epoch": 4.414285714285715,
"grad_norm": 3.03125,
"learning_rate": 4.107547781017169e-05,
"loss": 2.2839,
"step": 2163
},
{
"epoch": 4.416326530612245,
"grad_norm": 3.0625,
"learning_rate": 4.104308390022676e-05,
"loss": 2.3052,
"step": 2164
},
{
"epoch": 4.418367346938775,
"grad_norm": 2.9375,
"learning_rate": 4.101068999028183e-05,
"loss": 2.2163,
"step": 2165
},
{
"epoch": 4.420408163265306,
"grad_norm": 2.96875,
"learning_rate": 4.09782960803369e-05,
"loss": 2.2438,
"step": 2166
},
{
"epoch": 4.422448979591837,
"grad_norm": 3.0625,
"learning_rate": 4.094590217039197e-05,
"loss": 2.2954,
"step": 2167
},
{
"epoch": 4.424489795918367,
"grad_norm": 3.0,
"learning_rate": 4.0913508260447035e-05,
"loss": 2.2444,
"step": 2168
},
{
"epoch": 4.426530612244898,
"grad_norm": 3.46875,
"learning_rate": 4.088111435050211e-05,
"loss": 2.3634,
"step": 2169
},
{
"epoch": 4.428571428571429,
"grad_norm": 3.171875,
"learning_rate": 4.084872044055717e-05,
"loss": 2.319,
"step": 2170
},
{
"epoch": 4.430612244897959,
"grad_norm": 3.265625,
"learning_rate": 4.0816326530612245e-05,
"loss": 2.3047,
"step": 2171
},
{
"epoch": 4.43265306122449,
"grad_norm": 3.125,
"learning_rate": 4.078393262066732e-05,
"loss": 2.4314,
"step": 2172
},
{
"epoch": 4.4346938775510205,
"grad_norm": 3.0625,
"learning_rate": 4.075153871072239e-05,
"loss": 2.2784,
"step": 2173
},
{
"epoch": 4.436734693877551,
"grad_norm": 3.109375,
"learning_rate": 4.0719144800777455e-05,
"loss": 2.254,
"step": 2174
},
{
"epoch": 4.438775510204081,
"grad_norm": 3.28125,
"learning_rate": 4.068675089083253e-05,
"loss": 2.293,
"step": 2175
},
{
"epoch": 4.440816326530612,
"grad_norm": 3.0625,
"learning_rate": 4.065435698088759e-05,
"loss": 2.3435,
"step": 2176
},
{
"epoch": 4.442857142857143,
"grad_norm": 3.015625,
"learning_rate": 4.0621963070942666e-05,
"loss": 2.4057,
"step": 2177
},
{
"epoch": 4.444897959183674,
"grad_norm": 3.484375,
"learning_rate": 4.058956916099774e-05,
"loss": 2.2771,
"step": 2178
},
{
"epoch": 4.446938775510204,
"grad_norm": 3.34375,
"learning_rate": 4.0557175251052804e-05,
"loss": 2.3165,
"step": 2179
},
{
"epoch": 4.448979591836735,
"grad_norm": 3.515625,
"learning_rate": 4.0524781341107876e-05,
"loss": 2.374,
"step": 2180
},
{
"epoch": 4.451020408163266,
"grad_norm": 3.15625,
"learning_rate": 4.049238743116294e-05,
"loss": 2.2465,
"step": 2181
},
{
"epoch": 4.453061224489796,
"grad_norm": 3.125,
"learning_rate": 4.0459993521218014e-05,
"loss": 2.3633,
"step": 2182
},
{
"epoch": 4.455102040816326,
"grad_norm": 3.21875,
"learning_rate": 4.042759961127308e-05,
"loss": 2.2687,
"step": 2183
},
{
"epoch": 4.457142857142857,
"grad_norm": 3.25,
"learning_rate": 4.039520570132815e-05,
"loss": 2.3047,
"step": 2184
},
{
"epoch": 4.459183673469388,
"grad_norm": 3.421875,
"learning_rate": 4.036281179138322e-05,
"loss": 2.367,
"step": 2185
},
{
"epoch": 4.461224489795918,
"grad_norm": 3.328125,
"learning_rate": 4.033041788143829e-05,
"loss": 2.2379,
"step": 2186
},
{
"epoch": 4.463265306122449,
"grad_norm": 3.5,
"learning_rate": 4.029802397149336e-05,
"loss": 2.294,
"step": 2187
},
{
"epoch": 4.46530612244898,
"grad_norm": 3.203125,
"learning_rate": 4.0265630061548434e-05,
"loss": 2.3282,
"step": 2188
},
{
"epoch": 4.46734693877551,
"grad_norm": 3.34375,
"learning_rate": 4.02332361516035e-05,
"loss": 2.2332,
"step": 2189
},
{
"epoch": 4.469387755102041,
"grad_norm": 3.625,
"learning_rate": 4.020084224165857e-05,
"loss": 2.3489,
"step": 2190
},
{
"epoch": 4.4714285714285715,
"grad_norm": 3.671875,
"learning_rate": 4.016844833171364e-05,
"loss": 2.3762,
"step": 2191
},
{
"epoch": 4.473469387755102,
"grad_norm": 3.4375,
"learning_rate": 4.013605442176871e-05,
"loss": 2.2647,
"step": 2192
},
{
"epoch": 4.475510204081632,
"grad_norm": 3.234375,
"learning_rate": 4.010366051182378e-05,
"loss": 2.3382,
"step": 2193
},
{
"epoch": 4.477551020408163,
"grad_norm": 3.3125,
"learning_rate": 4.007126660187885e-05,
"loss": 2.3578,
"step": 2194
},
{
"epoch": 4.479591836734694,
"grad_norm": 3.171875,
"learning_rate": 4.003887269193392e-05,
"loss": 2.1607,
"step": 2195
},
{
"epoch": 4.481632653061224,
"grad_norm": 3.265625,
"learning_rate": 4.0006478781988986e-05,
"loss": 2.3133,
"step": 2196
},
{
"epoch": 4.483673469387755,
"grad_norm": 3.203125,
"learning_rate": 3.997408487204406e-05,
"loss": 2.3943,
"step": 2197
},
{
"epoch": 4.485714285714286,
"grad_norm": 3.203125,
"learning_rate": 3.9941690962099124e-05,
"loss": 2.3481,
"step": 2198
},
{
"epoch": 4.487755102040817,
"grad_norm": 3.46875,
"learning_rate": 3.9909297052154196e-05,
"loss": 2.2339,
"step": 2199
},
{
"epoch": 4.489795918367347,
"grad_norm": 3.578125,
"learning_rate": 3.987690314220927e-05,
"loss": 2.3585,
"step": 2200
},
{
"epoch": 4.4918367346938775,
"grad_norm": 3.25,
"learning_rate": 3.9844509232264334e-05,
"loss": 2.473,
"step": 2201
},
{
"epoch": 4.493877551020408,
"grad_norm": 3.34375,
"learning_rate": 3.981211532231941e-05,
"loss": 2.1893,
"step": 2202
},
{
"epoch": 4.495918367346939,
"grad_norm": 3.5,
"learning_rate": 3.977972141237448e-05,
"loss": 2.2884,
"step": 2203
},
{
"epoch": 4.497959183673469,
"grad_norm": 3.453125,
"learning_rate": 3.9747327502429545e-05,
"loss": 2.3442,
"step": 2204
},
{
"epoch": 4.5,
"grad_norm": 3.3125,
"learning_rate": 3.971493359248462e-05,
"loss": 2.4096,
"step": 2205
},
{
"epoch": 4.502040816326531,
"grad_norm": 3.578125,
"learning_rate": 3.968253968253968e-05,
"loss": 2.3427,
"step": 2206
},
{
"epoch": 4.504081632653062,
"grad_norm": 3.5625,
"learning_rate": 3.9650145772594755e-05,
"loss": 2.2469,
"step": 2207
},
{
"epoch": 4.506122448979592,
"grad_norm": 3.171875,
"learning_rate": 3.961775186264982e-05,
"loss": 2.2269,
"step": 2208
},
{
"epoch": 4.5081632653061225,
"grad_norm": 3.078125,
"learning_rate": 3.958535795270489e-05,
"loss": 2.2079,
"step": 2209
},
{
"epoch": 4.510204081632653,
"grad_norm": 3.484375,
"learning_rate": 3.9552964042759965e-05,
"loss": 2.4031,
"step": 2210
},
{
"epoch": 4.512244897959183,
"grad_norm": 3.3125,
"learning_rate": 3.952057013281503e-05,
"loss": 2.3187,
"step": 2211
},
{
"epoch": 4.514285714285714,
"grad_norm": 3.390625,
"learning_rate": 3.94881762228701e-05,
"loss": 2.2405,
"step": 2212
},
{
"epoch": 4.516326530612245,
"grad_norm": 3.28125,
"learning_rate": 3.945578231292517e-05,
"loss": 2.2019,
"step": 2213
},
{
"epoch": 4.518367346938776,
"grad_norm": 3.28125,
"learning_rate": 3.942338840298024e-05,
"loss": 2.3451,
"step": 2214
},
{
"epoch": 4.520408163265306,
"grad_norm": 3.5625,
"learning_rate": 3.939099449303531e-05,
"loss": 2.3575,
"step": 2215
},
{
"epoch": 4.522448979591837,
"grad_norm": 3.25,
"learning_rate": 3.9358600583090386e-05,
"loss": 2.36,
"step": 2216
},
{
"epoch": 4.524489795918368,
"grad_norm": 3.015625,
"learning_rate": 3.932620667314545e-05,
"loss": 2.2484,
"step": 2217
},
{
"epoch": 4.526530612244898,
"grad_norm": 3.5625,
"learning_rate": 3.9293812763200524e-05,
"loss": 2.2207,
"step": 2218
},
{
"epoch": 4.5285714285714285,
"grad_norm": 3.296875,
"learning_rate": 3.926141885325559e-05,
"loss": 2.2256,
"step": 2219
},
{
"epoch": 4.530612244897959,
"grad_norm": 3.375,
"learning_rate": 3.922902494331066e-05,
"loss": 2.2105,
"step": 2220
},
{
"epoch": 4.53265306122449,
"grad_norm": 3.375,
"learning_rate": 3.919663103336573e-05,
"loss": 2.3634,
"step": 2221
},
{
"epoch": 4.53469387755102,
"grad_norm": 3.359375,
"learning_rate": 3.91642371234208e-05,
"loss": 2.394,
"step": 2222
},
{
"epoch": 4.536734693877551,
"grad_norm": 3.25,
"learning_rate": 3.9131843213475865e-05,
"loss": 2.3118,
"step": 2223
},
{
"epoch": 4.538775510204082,
"grad_norm": 3.203125,
"learning_rate": 3.909944930353094e-05,
"loss": 2.2581,
"step": 2224
},
{
"epoch": 4.540816326530612,
"grad_norm": 3.3125,
"learning_rate": 3.9067055393586e-05,
"loss": 2.1581,
"step": 2225
},
{
"epoch": 4.542857142857143,
"grad_norm": 3.234375,
"learning_rate": 3.9034661483641075e-05,
"loss": 2.2618,
"step": 2226
},
{
"epoch": 4.544897959183674,
"grad_norm": 3.328125,
"learning_rate": 3.900226757369615e-05,
"loss": 2.2772,
"step": 2227
},
{
"epoch": 4.546938775510204,
"grad_norm": 3.25,
"learning_rate": 3.896987366375121e-05,
"loss": 2.3496,
"step": 2228
},
{
"epoch": 4.548979591836734,
"grad_norm": 3.296875,
"learning_rate": 3.8937479753806286e-05,
"loss": 2.1943,
"step": 2229
},
{
"epoch": 4.551020408163265,
"grad_norm": 3.390625,
"learning_rate": 3.890508584386136e-05,
"loss": 2.3699,
"step": 2230
},
{
"epoch": 4.553061224489796,
"grad_norm": 3.390625,
"learning_rate": 3.887269193391643e-05,
"loss": 2.2422,
"step": 2231
},
{
"epoch": 4.555102040816326,
"grad_norm": 3.3125,
"learning_rate": 3.8840298023971496e-05,
"loss": 2.3076,
"step": 2232
},
{
"epoch": 4.557142857142857,
"grad_norm": 3.15625,
"learning_rate": 3.880790411402657e-05,
"loss": 2.2568,
"step": 2233
},
{
"epoch": 4.559183673469388,
"grad_norm": 3.296875,
"learning_rate": 3.8775510204081634e-05,
"loss": 2.337,
"step": 2234
},
{
"epoch": 4.561224489795919,
"grad_norm": 3.078125,
"learning_rate": 3.8743116294136706e-05,
"loss": 2.3332,
"step": 2235
},
{
"epoch": 4.563265306122449,
"grad_norm": 3.21875,
"learning_rate": 3.871072238419177e-05,
"loss": 2.1755,
"step": 2236
},
{
"epoch": 4.5653061224489795,
"grad_norm": 3.15625,
"learning_rate": 3.8678328474246844e-05,
"loss": 2.3502,
"step": 2237
},
{
"epoch": 4.56734693877551,
"grad_norm": 3.359375,
"learning_rate": 3.864593456430191e-05,
"loss": 2.2582,
"step": 2238
},
{
"epoch": 4.569387755102041,
"grad_norm": 3.609375,
"learning_rate": 3.861354065435698e-05,
"loss": 2.2802,
"step": 2239
},
{
"epoch": 4.571428571428571,
"grad_norm": 3.28125,
"learning_rate": 3.858114674441205e-05,
"loss": 2.3594,
"step": 2240
},
{
"epoch": 4.573469387755102,
"grad_norm": 3.359375,
"learning_rate": 3.854875283446712e-05,
"loss": 2.3601,
"step": 2241
},
{
"epoch": 4.575510204081633,
"grad_norm": 3.234375,
"learning_rate": 3.851635892452219e-05,
"loss": 2.2309,
"step": 2242
},
{
"epoch": 4.577551020408164,
"grad_norm": 3.3125,
"learning_rate": 3.848396501457726e-05,
"loss": 2.1997,
"step": 2243
},
{
"epoch": 4.579591836734694,
"grad_norm": 3.5625,
"learning_rate": 3.845157110463233e-05,
"loss": 2.3115,
"step": 2244
},
{
"epoch": 4.581632653061225,
"grad_norm": 3.4375,
"learning_rate": 3.84191771946874e-05,
"loss": 2.2591,
"step": 2245
},
{
"epoch": 4.583673469387755,
"grad_norm": 3.1875,
"learning_rate": 3.8386783284742475e-05,
"loss": 2.2988,
"step": 2246
},
{
"epoch": 4.585714285714285,
"grad_norm": 3.21875,
"learning_rate": 3.835438937479754e-05,
"loss": 2.4913,
"step": 2247
},
{
"epoch": 4.587755102040816,
"grad_norm": 3.53125,
"learning_rate": 3.832199546485261e-05,
"loss": 2.2173,
"step": 2248
},
{
"epoch": 4.589795918367347,
"grad_norm": 3.15625,
"learning_rate": 3.828960155490768e-05,
"loss": 2.3466,
"step": 2249
},
{
"epoch": 4.591836734693878,
"grad_norm": 3.234375,
"learning_rate": 3.825720764496275e-05,
"loss": 2.2675,
"step": 2250
},
{
"epoch": 4.593877551020408,
"grad_norm": 3.15625,
"learning_rate": 3.8224813735017816e-05,
"loss": 2.308,
"step": 2251
},
{
"epoch": 4.595918367346939,
"grad_norm": 3.171875,
"learning_rate": 3.819241982507289e-05,
"loss": 2.1674,
"step": 2252
},
{
"epoch": 4.59795918367347,
"grad_norm": 3.421875,
"learning_rate": 3.8160025915127954e-05,
"loss": 2.399,
"step": 2253
},
{
"epoch": 4.6,
"grad_norm": 3.171875,
"learning_rate": 3.812763200518303e-05,
"loss": 2.2129,
"step": 2254
},
{
"epoch": 4.6020408163265305,
"grad_norm": 3.1875,
"learning_rate": 3.809523809523809e-05,
"loss": 2.255,
"step": 2255
},
{
"epoch": 4.604081632653061,
"grad_norm": 3.1875,
"learning_rate": 3.8062844185293165e-05,
"loss": 2.3283,
"step": 2256
},
{
"epoch": 4.606122448979592,
"grad_norm": 3.046875,
"learning_rate": 3.803045027534824e-05,
"loss": 2.2885,
"step": 2257
},
{
"epoch": 4.608163265306122,
"grad_norm": 3.46875,
"learning_rate": 3.799805636540331e-05,
"loss": 2.3862,
"step": 2258
},
{
"epoch": 4.610204081632653,
"grad_norm": 3.484375,
"learning_rate": 3.796566245545838e-05,
"loss": 2.3183,
"step": 2259
},
{
"epoch": 4.612244897959184,
"grad_norm": 3.40625,
"learning_rate": 3.793326854551345e-05,
"loss": 2.1886,
"step": 2260
},
{
"epoch": 4.614285714285714,
"grad_norm": 3.40625,
"learning_rate": 3.790087463556852e-05,
"loss": 2.2727,
"step": 2261
},
{
"epoch": 4.616326530612245,
"grad_norm": 3.375,
"learning_rate": 3.7868480725623585e-05,
"loss": 2.2427,
"step": 2262
},
{
"epoch": 4.618367346938776,
"grad_norm": 3.484375,
"learning_rate": 3.783608681567866e-05,
"loss": 2.3151,
"step": 2263
},
{
"epoch": 4.6204081632653065,
"grad_norm": 3.75,
"learning_rate": 3.780369290573372e-05,
"loss": 2.21,
"step": 2264
},
{
"epoch": 4.622448979591836,
"grad_norm": 3.46875,
"learning_rate": 3.7771298995788795e-05,
"loss": 2.1821,
"step": 2265
},
{
"epoch": 4.624489795918367,
"grad_norm": 3.265625,
"learning_rate": 3.773890508584386e-05,
"loss": 2.2586,
"step": 2266
},
{
"epoch": 4.626530612244898,
"grad_norm": 3.515625,
"learning_rate": 3.770651117589893e-05,
"loss": 2.2232,
"step": 2267
},
{
"epoch": 4.628571428571428,
"grad_norm": 3.46875,
"learning_rate": 3.7674117265954e-05,
"loss": 2.4146,
"step": 2268
},
{
"epoch": 4.630612244897959,
"grad_norm": 3.3125,
"learning_rate": 3.764172335600907e-05,
"loss": 2.2865,
"step": 2269
},
{
"epoch": 4.63265306122449,
"grad_norm": 3.296875,
"learning_rate": 3.760932944606414e-05,
"loss": 2.276,
"step": 2270
},
{
"epoch": 4.634693877551021,
"grad_norm": 3.4375,
"learning_rate": 3.757693553611921e-05,
"loss": 2.3539,
"step": 2271
},
{
"epoch": 4.636734693877551,
"grad_norm": 3.265625,
"learning_rate": 3.754454162617428e-05,
"loss": 2.2647,
"step": 2272
},
{
"epoch": 4.6387755102040815,
"grad_norm": 3.234375,
"learning_rate": 3.7512147716229354e-05,
"loss": 2.268,
"step": 2273
},
{
"epoch": 4.640816326530612,
"grad_norm": 3.15625,
"learning_rate": 3.747975380628442e-05,
"loss": 2.2764,
"step": 2274
},
{
"epoch": 4.642857142857143,
"grad_norm": 3.3125,
"learning_rate": 3.744735989633949e-05,
"loss": 2.227,
"step": 2275
},
{
"epoch": 4.644897959183673,
"grad_norm": 3.3125,
"learning_rate": 3.7414965986394564e-05,
"loss": 2.2502,
"step": 2276
},
{
"epoch": 4.646938775510204,
"grad_norm": 3.46875,
"learning_rate": 3.738257207644963e-05,
"loss": 2.2629,
"step": 2277
},
{
"epoch": 4.648979591836735,
"grad_norm": 3.140625,
"learning_rate": 3.73501781665047e-05,
"loss": 2.3425,
"step": 2278
},
{
"epoch": 4.651020408163266,
"grad_norm": 3.09375,
"learning_rate": 3.731778425655977e-05,
"loss": 2.275,
"step": 2279
},
{
"epoch": 4.653061224489796,
"grad_norm": 3.171875,
"learning_rate": 3.728539034661484e-05,
"loss": 2.197,
"step": 2280
},
{
"epoch": 4.655102040816327,
"grad_norm": 3.34375,
"learning_rate": 3.7252996436669906e-05,
"loss": 2.2701,
"step": 2281
},
{
"epoch": 4.6571428571428575,
"grad_norm": 3.65625,
"learning_rate": 3.722060252672498e-05,
"loss": 2.22,
"step": 2282
},
{
"epoch": 4.659183673469387,
"grad_norm": 3.109375,
"learning_rate": 3.7188208616780044e-05,
"loss": 2.191,
"step": 2283
},
{
"epoch": 4.661224489795918,
"grad_norm": 3.4375,
"learning_rate": 3.7155814706835116e-05,
"loss": 2.1995,
"step": 2284
},
{
"epoch": 4.663265306122449,
"grad_norm": 3.0,
"learning_rate": 3.712342079689018e-05,
"loss": 2.2231,
"step": 2285
},
{
"epoch": 4.66530612244898,
"grad_norm": 3.203125,
"learning_rate": 3.7091026886945254e-05,
"loss": 2.3985,
"step": 2286
},
{
"epoch": 4.66734693877551,
"grad_norm": 3.375,
"learning_rate": 3.7058632977000326e-05,
"loss": 2.2468,
"step": 2287
},
{
"epoch": 4.669387755102041,
"grad_norm": 3.328125,
"learning_rate": 3.70262390670554e-05,
"loss": 2.1784,
"step": 2288
},
{
"epoch": 4.671428571428572,
"grad_norm": 3.203125,
"learning_rate": 3.6993845157110464e-05,
"loss": 2.4038,
"step": 2289
},
{
"epoch": 4.673469387755102,
"grad_norm": 3.125,
"learning_rate": 3.6961451247165536e-05,
"loss": 2.4142,
"step": 2290
},
{
"epoch": 4.6755102040816325,
"grad_norm": 3.078125,
"learning_rate": 3.69290573372206e-05,
"loss": 2.3681,
"step": 2291
},
{
"epoch": 4.677551020408163,
"grad_norm": 3.140625,
"learning_rate": 3.6896663427275674e-05,
"loss": 2.2282,
"step": 2292
},
{
"epoch": 4.679591836734694,
"grad_norm": 3.109375,
"learning_rate": 3.686426951733075e-05,
"loss": 2.231,
"step": 2293
},
{
"epoch": 4.681632653061224,
"grad_norm": 3.28125,
"learning_rate": 3.683187560738581e-05,
"loss": 2.2173,
"step": 2294
},
{
"epoch": 4.683673469387755,
"grad_norm": 3.109375,
"learning_rate": 3.6799481697440885e-05,
"loss": 2.3312,
"step": 2295
},
{
"epoch": 4.685714285714286,
"grad_norm": 3.4375,
"learning_rate": 3.676708778749595e-05,
"loss": 2.2334,
"step": 2296
},
{
"epoch": 4.687755102040816,
"grad_norm": 3.375,
"learning_rate": 3.673469387755102e-05,
"loss": 2.4849,
"step": 2297
},
{
"epoch": 4.689795918367347,
"grad_norm": 3.4375,
"learning_rate": 3.670229996760609e-05,
"loss": 2.3023,
"step": 2298
},
{
"epoch": 4.691836734693878,
"grad_norm": 3.296875,
"learning_rate": 3.666990605766116e-05,
"loss": 2.3127,
"step": 2299
},
{
"epoch": 4.6938775510204085,
"grad_norm": 3.0,
"learning_rate": 3.663751214771623e-05,
"loss": 2.283,
"step": 2300
},
{
"epoch": 4.6959183673469385,
"grad_norm": 3.40625,
"learning_rate": 3.6605118237771305e-05,
"loss": 2.2927,
"step": 2301
},
{
"epoch": 4.697959183673469,
"grad_norm": 3.25,
"learning_rate": 3.657272432782637e-05,
"loss": 2.406,
"step": 2302
},
{
"epoch": 4.7,
"grad_norm": 2.8125,
"learning_rate": 3.654033041788144e-05,
"loss": 2.428,
"step": 2303
},
{
"epoch": 4.70204081632653,
"grad_norm": 3.0625,
"learning_rate": 3.650793650793651e-05,
"loss": 2.36,
"step": 2304
},
{
"epoch": 4.704081632653061,
"grad_norm": 3.375,
"learning_rate": 3.647554259799158e-05,
"loss": 2.2085,
"step": 2305
},
{
"epoch": 4.706122448979592,
"grad_norm": 3.609375,
"learning_rate": 3.644314868804665e-05,
"loss": 2.2612,
"step": 2306
},
{
"epoch": 4.708163265306123,
"grad_norm": 3.328125,
"learning_rate": 3.641075477810172e-05,
"loss": 2.2946,
"step": 2307
},
{
"epoch": 4.710204081632653,
"grad_norm": 3.40625,
"learning_rate": 3.6378360868156785e-05,
"loss": 2.3941,
"step": 2308
},
{
"epoch": 4.7122448979591836,
"grad_norm": 3.53125,
"learning_rate": 3.634596695821186e-05,
"loss": 2.3753,
"step": 2309
},
{
"epoch": 4.714285714285714,
"grad_norm": 3.265625,
"learning_rate": 3.631357304826693e-05,
"loss": 2.2934,
"step": 2310
},
{
"epoch": 4.716326530612245,
"grad_norm": 3.28125,
"learning_rate": 3.6281179138321995e-05,
"loss": 2.2682,
"step": 2311
},
{
"epoch": 4.718367346938775,
"grad_norm": 3.203125,
"learning_rate": 3.624878522837707e-05,
"loss": 2.1994,
"step": 2312
},
{
"epoch": 4.720408163265306,
"grad_norm": 3.375,
"learning_rate": 3.621639131843213e-05,
"loss": 2.1798,
"step": 2313
},
{
"epoch": 4.722448979591837,
"grad_norm": 3.15625,
"learning_rate": 3.6183997408487205e-05,
"loss": 2.2524,
"step": 2314
},
{
"epoch": 4.724489795918368,
"grad_norm": 3.328125,
"learning_rate": 3.615160349854228e-05,
"loss": 2.2764,
"step": 2315
},
{
"epoch": 4.726530612244898,
"grad_norm": 3.109375,
"learning_rate": 3.611920958859735e-05,
"loss": 2.3008,
"step": 2316
},
{
"epoch": 4.728571428571429,
"grad_norm": 3.28125,
"learning_rate": 3.6086815678652415e-05,
"loss": 2.22,
"step": 2317
},
{
"epoch": 4.7306122448979595,
"grad_norm": 3.6875,
"learning_rate": 3.605442176870749e-05,
"loss": 2.1657,
"step": 2318
},
{
"epoch": 4.7326530612244895,
"grad_norm": 3.484375,
"learning_rate": 3.602202785876255e-05,
"loss": 2.3555,
"step": 2319
},
{
"epoch": 4.73469387755102,
"grad_norm": 3.0,
"learning_rate": 3.5989633948817626e-05,
"loss": 2.4143,
"step": 2320
},
{
"epoch": 4.736734693877551,
"grad_norm": 3.515625,
"learning_rate": 3.595724003887269e-05,
"loss": 2.2175,
"step": 2321
},
{
"epoch": 4.738775510204082,
"grad_norm": 3.328125,
"learning_rate": 3.5924846128927764e-05,
"loss": 2.3945,
"step": 2322
},
{
"epoch": 4.740816326530612,
"grad_norm": 3.3125,
"learning_rate": 3.589245221898283e-05,
"loss": 2.2442,
"step": 2323
},
{
"epoch": 4.742857142857143,
"grad_norm": 3.515625,
"learning_rate": 3.58600583090379e-05,
"loss": 2.2946,
"step": 2324
},
{
"epoch": 4.744897959183674,
"grad_norm": 3.390625,
"learning_rate": 3.5827664399092974e-05,
"loss": 2.1753,
"step": 2325
},
{
"epoch": 4.746938775510204,
"grad_norm": 3.15625,
"learning_rate": 3.579527048914804e-05,
"loss": 2.2528,
"step": 2326
},
{
"epoch": 4.748979591836735,
"grad_norm": 3.296875,
"learning_rate": 3.576287657920311e-05,
"loss": 2.2531,
"step": 2327
},
{
"epoch": 4.751020408163265,
"grad_norm": 3.46875,
"learning_rate": 3.573048266925818e-05,
"loss": 2.3729,
"step": 2328
},
{
"epoch": 4.753061224489796,
"grad_norm": 3.46875,
"learning_rate": 3.569808875931325e-05,
"loss": 2.2643,
"step": 2329
},
{
"epoch": 4.755102040816326,
"grad_norm": 3.046875,
"learning_rate": 3.566569484936832e-05,
"loss": 2.3632,
"step": 2330
},
{
"epoch": 4.757142857142857,
"grad_norm": 3.40625,
"learning_rate": 3.5633300939423394e-05,
"loss": 2.2615,
"step": 2331
},
{
"epoch": 4.759183673469388,
"grad_norm": 3.1875,
"learning_rate": 3.560090702947846e-05,
"loss": 2.2969,
"step": 2332
},
{
"epoch": 4.761224489795918,
"grad_norm": 3.328125,
"learning_rate": 3.556851311953353e-05,
"loss": 2.314,
"step": 2333
},
{
"epoch": 4.763265306122449,
"grad_norm": 3.328125,
"learning_rate": 3.55361192095886e-05,
"loss": 2.1318,
"step": 2334
},
{
"epoch": 4.76530612244898,
"grad_norm": 2.984375,
"learning_rate": 3.550372529964367e-05,
"loss": 2.1664,
"step": 2335
},
{
"epoch": 4.7673469387755105,
"grad_norm": 3.0625,
"learning_rate": 3.5471331389698736e-05,
"loss": 2.2789,
"step": 2336
},
{
"epoch": 4.7693877551020405,
"grad_norm": 3.390625,
"learning_rate": 3.543893747975381e-05,
"loss": 2.2788,
"step": 2337
},
{
"epoch": 4.771428571428571,
"grad_norm": 3.46875,
"learning_rate": 3.5406543569808874e-05,
"loss": 2.2144,
"step": 2338
},
{
"epoch": 4.773469387755102,
"grad_norm": 3.515625,
"learning_rate": 3.5374149659863946e-05,
"loss": 2.6044,
"step": 2339
},
{
"epoch": 4.775510204081632,
"grad_norm": 3.265625,
"learning_rate": 3.534175574991901e-05,
"loss": 2.3675,
"step": 2340
},
{
"epoch": 4.777551020408163,
"grad_norm": 3.140625,
"learning_rate": 3.5309361839974084e-05,
"loss": 2.1589,
"step": 2341
},
{
"epoch": 4.779591836734694,
"grad_norm": 3.4375,
"learning_rate": 3.5276967930029156e-05,
"loss": 2.3659,
"step": 2342
},
{
"epoch": 4.781632653061225,
"grad_norm": 3.4375,
"learning_rate": 3.524457402008423e-05,
"loss": 2.287,
"step": 2343
},
{
"epoch": 4.783673469387755,
"grad_norm": 3.109375,
"learning_rate": 3.52121801101393e-05,
"loss": 2.291,
"step": 2344
},
{
"epoch": 4.785714285714286,
"grad_norm": 3.375,
"learning_rate": 3.517978620019437e-05,
"loss": 2.239,
"step": 2345
},
{
"epoch": 4.7877551020408164,
"grad_norm": 3.28125,
"learning_rate": 3.514739229024944e-05,
"loss": 2.3535,
"step": 2346
},
{
"epoch": 4.789795918367347,
"grad_norm": 3.140625,
"learning_rate": 3.5114998380304505e-05,
"loss": 2.279,
"step": 2347
},
{
"epoch": 4.791836734693877,
"grad_norm": 3.328125,
"learning_rate": 3.508260447035958e-05,
"loss": 2.2341,
"step": 2348
},
{
"epoch": 4.793877551020408,
"grad_norm": 3.203125,
"learning_rate": 3.505021056041464e-05,
"loss": 2.3609,
"step": 2349
},
{
"epoch": 4.795918367346939,
"grad_norm": 3.34375,
"learning_rate": 3.5017816650469715e-05,
"loss": 2.2761,
"step": 2350
},
{
"epoch": 4.79795918367347,
"grad_norm": 3.015625,
"learning_rate": 3.498542274052478e-05,
"loss": 2.309,
"step": 2351
},
{
"epoch": 4.8,
"grad_norm": 3.171875,
"learning_rate": 3.495302883057985e-05,
"loss": 2.2444,
"step": 2352
},
{
"epoch": 4.802040816326531,
"grad_norm": 3.265625,
"learning_rate": 3.492063492063492e-05,
"loss": 2.3059,
"step": 2353
},
{
"epoch": 4.8040816326530615,
"grad_norm": 3.296875,
"learning_rate": 3.488824101068999e-05,
"loss": 2.2313,
"step": 2354
},
{
"epoch": 4.8061224489795915,
"grad_norm": 3.09375,
"learning_rate": 3.4855847100745056e-05,
"loss": 2.2899,
"step": 2355
},
{
"epoch": 4.808163265306122,
"grad_norm": 3.4375,
"learning_rate": 3.482345319080013e-05,
"loss": 2.2664,
"step": 2356
},
{
"epoch": 4.810204081632653,
"grad_norm": 3.390625,
"learning_rate": 3.47910592808552e-05,
"loss": 2.3391,
"step": 2357
},
{
"epoch": 4.812244897959184,
"grad_norm": 3.359375,
"learning_rate": 3.4758665370910273e-05,
"loss": 2.171,
"step": 2358
},
{
"epoch": 4.814285714285714,
"grad_norm": 3.296875,
"learning_rate": 3.4726271460965346e-05,
"loss": 2.1208,
"step": 2359
},
{
"epoch": 4.816326530612245,
"grad_norm": 3.078125,
"learning_rate": 3.469387755102041e-05,
"loss": 2.3106,
"step": 2360
},
{
"epoch": 4.818367346938776,
"grad_norm": 3.109375,
"learning_rate": 3.4661483641075484e-05,
"loss": 2.2281,
"step": 2361
},
{
"epoch": 4.820408163265306,
"grad_norm": 3.0625,
"learning_rate": 3.462908973113055e-05,
"loss": 2.3204,
"step": 2362
},
{
"epoch": 4.822448979591837,
"grad_norm": 3.3125,
"learning_rate": 3.459669582118562e-05,
"loss": 2.2264,
"step": 2363
},
{
"epoch": 4.8244897959183675,
"grad_norm": 3.265625,
"learning_rate": 3.456430191124069e-05,
"loss": 2.1892,
"step": 2364
},
{
"epoch": 4.826530612244898,
"grad_norm": 3.21875,
"learning_rate": 3.453190800129576e-05,
"loss": 2.2977,
"step": 2365
},
{
"epoch": 4.828571428571428,
"grad_norm": 3.21875,
"learning_rate": 3.4499514091350825e-05,
"loss": 2.2118,
"step": 2366
},
{
"epoch": 4.830612244897959,
"grad_norm": 3.234375,
"learning_rate": 3.44671201814059e-05,
"loss": 2.2924,
"step": 2367
},
{
"epoch": 4.83265306122449,
"grad_norm": 3.390625,
"learning_rate": 3.443472627146096e-05,
"loss": 2.2891,
"step": 2368
},
{
"epoch": 4.83469387755102,
"grad_norm": 3.25,
"learning_rate": 3.4402332361516035e-05,
"loss": 2.3386,
"step": 2369
},
{
"epoch": 4.836734693877551,
"grad_norm": 3.4375,
"learning_rate": 3.43699384515711e-05,
"loss": 2.223,
"step": 2370
},
{
"epoch": 4.838775510204082,
"grad_norm": 3.328125,
"learning_rate": 3.433754454162617e-05,
"loss": 2.2674,
"step": 2371
},
{
"epoch": 4.840816326530613,
"grad_norm": 3.1875,
"learning_rate": 3.4305150631681246e-05,
"loss": 2.1608,
"step": 2372
},
{
"epoch": 4.8428571428571425,
"grad_norm": 3.359375,
"learning_rate": 3.427275672173632e-05,
"loss": 2.2654,
"step": 2373
},
{
"epoch": 4.844897959183673,
"grad_norm": 3.53125,
"learning_rate": 3.4240362811791384e-05,
"loss": 2.3037,
"step": 2374
},
{
"epoch": 4.846938775510204,
"grad_norm": 3.34375,
"learning_rate": 3.4207968901846456e-05,
"loss": 2.2059,
"step": 2375
},
{
"epoch": 4.848979591836734,
"grad_norm": 3.1875,
"learning_rate": 3.417557499190153e-05,
"loss": 2.4384,
"step": 2376
},
{
"epoch": 4.851020408163265,
"grad_norm": 3.265625,
"learning_rate": 3.4143181081956594e-05,
"loss": 2.2846,
"step": 2377
},
{
"epoch": 4.853061224489796,
"grad_norm": 3.140625,
"learning_rate": 3.4110787172011666e-05,
"loss": 2.302,
"step": 2378
},
{
"epoch": 4.855102040816327,
"grad_norm": 3.265625,
"learning_rate": 3.407839326206673e-05,
"loss": 2.1633,
"step": 2379
},
{
"epoch": 4.857142857142857,
"grad_norm": 3.328125,
"learning_rate": 3.4045999352121804e-05,
"loss": 2.4568,
"step": 2380
},
{
"epoch": 4.859183673469388,
"grad_norm": 3.28125,
"learning_rate": 3.401360544217687e-05,
"loss": 2.2892,
"step": 2381
},
{
"epoch": 4.8612244897959185,
"grad_norm": 3.265625,
"learning_rate": 3.398121153223194e-05,
"loss": 2.2423,
"step": 2382
},
{
"epoch": 4.863265306122449,
"grad_norm": 3.109375,
"learning_rate": 3.394881762228701e-05,
"loss": 2.327,
"step": 2383
},
{
"epoch": 4.865306122448979,
"grad_norm": 3.359375,
"learning_rate": 3.391642371234208e-05,
"loss": 2.3123,
"step": 2384
},
{
"epoch": 4.86734693877551,
"grad_norm": 3.234375,
"learning_rate": 3.388402980239715e-05,
"loss": 2.325,
"step": 2385
},
{
"epoch": 4.869387755102041,
"grad_norm": 3.328125,
"learning_rate": 3.3851635892452225e-05,
"loss": 2.219,
"step": 2386
},
{
"epoch": 4.871428571428572,
"grad_norm": 3.15625,
"learning_rate": 3.381924198250729e-05,
"loss": 2.2718,
"step": 2387
},
{
"epoch": 4.873469387755102,
"grad_norm": 3.125,
"learning_rate": 3.378684807256236e-05,
"loss": 2.1891,
"step": 2388
},
{
"epoch": 4.875510204081633,
"grad_norm": 3.71875,
"learning_rate": 3.375445416261743e-05,
"loss": 2.1534,
"step": 2389
},
{
"epoch": 4.877551020408164,
"grad_norm": 3.4375,
"learning_rate": 3.37220602526725e-05,
"loss": 2.1839,
"step": 2390
},
{
"epoch": 4.8795918367346935,
"grad_norm": 2.984375,
"learning_rate": 3.368966634272757e-05,
"loss": 2.2352,
"step": 2391
},
{
"epoch": 4.881632653061224,
"grad_norm": 3.125,
"learning_rate": 3.365727243278264e-05,
"loss": 2.2637,
"step": 2392
},
{
"epoch": 4.883673469387755,
"grad_norm": 3.109375,
"learning_rate": 3.362487852283771e-05,
"loss": 2.224,
"step": 2393
},
{
"epoch": 4.885714285714286,
"grad_norm": 3.28125,
"learning_rate": 3.3592484612892776e-05,
"loss": 2.2607,
"step": 2394
},
{
"epoch": 4.887755102040816,
"grad_norm": 2.984375,
"learning_rate": 3.356009070294785e-05,
"loss": 2.2591,
"step": 2395
},
{
"epoch": 4.889795918367347,
"grad_norm": 3.453125,
"learning_rate": 3.3527696793002914e-05,
"loss": 2.148,
"step": 2396
},
{
"epoch": 4.891836734693878,
"grad_norm": 3.328125,
"learning_rate": 3.349530288305799e-05,
"loss": 2.2852,
"step": 2397
},
{
"epoch": 4.893877551020408,
"grad_norm": 3.1875,
"learning_rate": 3.346290897311305e-05,
"loss": 2.2815,
"step": 2398
},
{
"epoch": 4.895918367346939,
"grad_norm": 3.359375,
"learning_rate": 3.3430515063168125e-05,
"loss": 2.2226,
"step": 2399
},
{
"epoch": 4.8979591836734695,
"grad_norm": 3.484375,
"learning_rate": 3.33981211532232e-05,
"loss": 2.2872,
"step": 2400
},
{
"epoch": 4.9,
"grad_norm": 3.09375,
"learning_rate": 3.336572724327827e-05,
"loss": 2.2194,
"step": 2401
},
{
"epoch": 4.90204081632653,
"grad_norm": 3.09375,
"learning_rate": 3.3333333333333335e-05,
"loss": 2.2766,
"step": 2402
},
{
"epoch": 4.904081632653061,
"grad_norm": 3.25,
"learning_rate": 3.330093942338841e-05,
"loss": 2.3379,
"step": 2403
},
{
"epoch": 4.906122448979592,
"grad_norm": 3.265625,
"learning_rate": 3.326854551344347e-05,
"loss": 2.3337,
"step": 2404
},
{
"epoch": 4.908163265306122,
"grad_norm": 3.453125,
"learning_rate": 3.3236151603498545e-05,
"loss": 2.1913,
"step": 2405
},
{
"epoch": 4.910204081632653,
"grad_norm": 3.125,
"learning_rate": 3.320375769355361e-05,
"loss": 2.1398,
"step": 2406
},
{
"epoch": 4.912244897959184,
"grad_norm": 3.25,
"learning_rate": 3.317136378360868e-05,
"loss": 2.2357,
"step": 2407
},
{
"epoch": 4.914285714285715,
"grad_norm": 3.40625,
"learning_rate": 3.3138969873663755e-05,
"loss": 2.2259,
"step": 2408
},
{
"epoch": 4.916326530612245,
"grad_norm": 3.34375,
"learning_rate": 3.310657596371882e-05,
"loss": 2.2266,
"step": 2409
},
{
"epoch": 4.918367346938775,
"grad_norm": 3.25,
"learning_rate": 3.3074182053773893e-05,
"loss": 2.3298,
"step": 2410
},
{
"epoch": 4.920408163265306,
"grad_norm": 3.296875,
"learning_rate": 3.304178814382896e-05,
"loss": 2.2387,
"step": 2411
},
{
"epoch": 4.922448979591836,
"grad_norm": 3.3125,
"learning_rate": 3.300939423388403e-05,
"loss": 2.3771,
"step": 2412
},
{
"epoch": 4.924489795918367,
"grad_norm": 3.453125,
"learning_rate": 3.29770003239391e-05,
"loss": 2.3574,
"step": 2413
},
{
"epoch": 4.926530612244898,
"grad_norm": 3.3125,
"learning_rate": 3.294460641399417e-05,
"loss": 2.2177,
"step": 2414
},
{
"epoch": 4.928571428571429,
"grad_norm": 3.40625,
"learning_rate": 3.291221250404924e-05,
"loss": 2.2503,
"step": 2415
},
{
"epoch": 4.930612244897959,
"grad_norm": 3.234375,
"learning_rate": 3.2879818594104314e-05,
"loss": 2.2052,
"step": 2416
},
{
"epoch": 4.93265306122449,
"grad_norm": 3.375,
"learning_rate": 3.284742468415938e-05,
"loss": 2.2203,
"step": 2417
},
{
"epoch": 4.9346938775510205,
"grad_norm": 3.296875,
"learning_rate": 3.281503077421445e-05,
"loss": 2.2509,
"step": 2418
},
{
"epoch": 4.936734693877551,
"grad_norm": 3.640625,
"learning_rate": 3.278263686426952e-05,
"loss": 2.1775,
"step": 2419
},
{
"epoch": 4.938775510204081,
"grad_norm": 3.5625,
"learning_rate": 3.275024295432459e-05,
"loss": 2.2827,
"step": 2420
},
{
"epoch": 4.940816326530612,
"grad_norm": 3.421875,
"learning_rate": 3.2717849044379655e-05,
"loss": 2.3511,
"step": 2421
},
{
"epoch": 4.942857142857143,
"grad_norm": 3.234375,
"learning_rate": 3.268545513443473e-05,
"loss": 2.1787,
"step": 2422
},
{
"epoch": 4.944897959183674,
"grad_norm": 3.328125,
"learning_rate": 3.265306122448979e-05,
"loss": 2.26,
"step": 2423
},
{
"epoch": 4.946938775510204,
"grad_norm": 3.15625,
"learning_rate": 3.2620667314544866e-05,
"loss": 2.1622,
"step": 2424
},
{
"epoch": 4.948979591836735,
"grad_norm": 3.125,
"learning_rate": 3.258827340459994e-05,
"loss": 2.2123,
"step": 2425
},
{
"epoch": 4.951020408163266,
"grad_norm": 3.359375,
"learning_rate": 3.2555879494655004e-05,
"loss": 2.2126,
"step": 2426
},
{
"epoch": 4.953061224489796,
"grad_norm": 3.0625,
"learning_rate": 3.2523485584710076e-05,
"loss": 2.2455,
"step": 2427
},
{
"epoch": 4.955102040816326,
"grad_norm": 3.234375,
"learning_rate": 3.249109167476515e-05,
"loss": 2.2028,
"step": 2428
},
{
"epoch": 4.957142857142857,
"grad_norm": 3.40625,
"learning_rate": 3.245869776482022e-05,
"loss": 2.2122,
"step": 2429
},
{
"epoch": 4.959183673469388,
"grad_norm": 3.21875,
"learning_rate": 3.2426303854875286e-05,
"loss": 2.2116,
"step": 2430
},
{
"epoch": 4.961224489795918,
"grad_norm": 3.53125,
"learning_rate": 3.239390994493036e-05,
"loss": 2.2569,
"step": 2431
},
{
"epoch": 4.963265306122449,
"grad_norm": 3.578125,
"learning_rate": 3.2361516034985424e-05,
"loss": 2.279,
"step": 2432
},
{
"epoch": 4.96530612244898,
"grad_norm": 3.46875,
"learning_rate": 3.2329122125040497e-05,
"loss": 2.1409,
"step": 2433
},
{
"epoch": 4.96734693877551,
"grad_norm": 3.390625,
"learning_rate": 3.229672821509556e-05,
"loss": 2.0971,
"step": 2434
},
{
"epoch": 4.969387755102041,
"grad_norm": 3.078125,
"learning_rate": 3.2264334305150634e-05,
"loss": 2.2182,
"step": 2435
},
{
"epoch": 4.9714285714285715,
"grad_norm": 3.328125,
"learning_rate": 3.22319403952057e-05,
"loss": 2.1926,
"step": 2436
},
{
"epoch": 4.973469387755102,
"grad_norm": 3.0625,
"learning_rate": 3.219954648526077e-05,
"loss": 2.2095,
"step": 2437
},
{
"epoch": 4.975510204081632,
"grad_norm": 3.40625,
"learning_rate": 3.216715257531584e-05,
"loss": 2.1011,
"step": 2438
},
{
"epoch": 4.977551020408163,
"grad_norm": 3.5625,
"learning_rate": 3.213475866537091e-05,
"loss": 2.2053,
"step": 2439
},
{
"epoch": 4.979591836734694,
"grad_norm": 3.390625,
"learning_rate": 3.2102364755425976e-05,
"loss": 2.3191,
"step": 2440
},
{
"epoch": 4.981632653061224,
"grad_norm": 3.421875,
"learning_rate": 3.206997084548105e-05,
"loss": 2.2113,
"step": 2441
},
{
"epoch": 4.983673469387755,
"grad_norm": 3.25,
"learning_rate": 3.203757693553612e-05,
"loss": 2.2451,
"step": 2442
},
{
"epoch": 4.985714285714286,
"grad_norm": 3.5,
"learning_rate": 3.200518302559119e-05,
"loss": 2.1749,
"step": 2443
},
{
"epoch": 4.987755102040817,
"grad_norm": 3.28125,
"learning_rate": 3.1972789115646265e-05,
"loss": 2.3021,
"step": 2444
},
{
"epoch": 4.989795918367347,
"grad_norm": 3.296875,
"learning_rate": 3.194039520570133e-05,
"loss": 2.2249,
"step": 2445
},
{
"epoch": 4.9918367346938775,
"grad_norm": 3.15625,
"learning_rate": 3.19080012957564e-05,
"loss": 2.2093,
"step": 2446
},
{
"epoch": 4.993877551020408,
"grad_norm": 3.171875,
"learning_rate": 3.187560738581147e-05,
"loss": 2.3097,
"step": 2447
},
{
"epoch": 4.995918367346938,
"grad_norm": 3.359375,
"learning_rate": 3.184321347586654e-05,
"loss": 2.2224,
"step": 2448
},
{
"epoch": 4.997959183673469,
"grad_norm": 3.421875,
"learning_rate": 3.181081956592161e-05,
"loss": 2.2375,
"step": 2449
},
{
"epoch": 5.0,
"grad_norm": 3.203125,
"learning_rate": 3.177842565597668e-05,
"loss": 2.3735,
"step": 2450
},
{
"epoch": 5.002040816326531,
"grad_norm": 5.96875,
"learning_rate": 3.1746031746031745e-05,
"loss": 1.4798,
"step": 2451
},
{
"epoch": 5.004081632653061,
"grad_norm": 4.9375,
"learning_rate": 3.171363783608682e-05,
"loss": 1.4348,
"step": 2452
},
{
"epoch": 5.006122448979592,
"grad_norm": 4.3125,
"learning_rate": 3.168124392614188e-05,
"loss": 1.362,
"step": 2453
},
{
"epoch": 5.0081632653061225,
"grad_norm": 3.3125,
"learning_rate": 3.1648850016196955e-05,
"loss": 1.3075,
"step": 2454
},
{
"epoch": 5.010204081632653,
"grad_norm": 3.765625,
"learning_rate": 3.161645610625202e-05,
"loss": 1.4149,
"step": 2455
},
{
"epoch": 5.012244897959183,
"grad_norm": 5.09375,
"learning_rate": 3.158406219630709e-05,
"loss": 1.3337,
"step": 2456
},
{
"epoch": 5.014285714285714,
"grad_norm": 5.28125,
"learning_rate": 3.1551668286362165e-05,
"loss": 1.3751,
"step": 2457
},
{
"epoch": 5.016326530612245,
"grad_norm": 4.90625,
"learning_rate": 3.151927437641724e-05,
"loss": 1.4134,
"step": 2458
},
{
"epoch": 5.018367346938776,
"grad_norm": 3.6875,
"learning_rate": 3.148688046647231e-05,
"loss": 1.3381,
"step": 2459
},
{
"epoch": 5.020408163265306,
"grad_norm": 3.765625,
"learning_rate": 3.1454486556527375e-05,
"loss": 1.3398,
"step": 2460
},
{
"epoch": 5.022448979591837,
"grad_norm": 3.921875,
"learning_rate": 3.142209264658245e-05,
"loss": 1.4066,
"step": 2461
},
{
"epoch": 5.024489795918368,
"grad_norm": 3.328125,
"learning_rate": 3.1389698736637513e-05,
"loss": 1.4493,
"step": 2462
},
{
"epoch": 5.026530612244898,
"grad_norm": 3.546875,
"learning_rate": 3.1357304826692586e-05,
"loss": 1.3063,
"step": 2463
},
{
"epoch": 5.0285714285714285,
"grad_norm": 3.46875,
"learning_rate": 3.132491091674765e-05,
"loss": 1.3651,
"step": 2464
},
{
"epoch": 5.030612244897959,
"grad_norm": 3.203125,
"learning_rate": 3.1292517006802724e-05,
"loss": 1.3223,
"step": 2465
},
{
"epoch": 5.03265306122449,
"grad_norm": 2.96875,
"learning_rate": 3.126012309685779e-05,
"loss": 1.3707,
"step": 2466
},
{
"epoch": 5.03469387755102,
"grad_norm": 3.203125,
"learning_rate": 3.122772918691286e-05,
"loss": 1.3801,
"step": 2467
},
{
"epoch": 5.036734693877551,
"grad_norm": 3.09375,
"learning_rate": 3.119533527696793e-05,
"loss": 1.3314,
"step": 2468
},
{
"epoch": 5.038775510204082,
"grad_norm": 3.234375,
"learning_rate": 3.1162941367023e-05,
"loss": 1.3628,
"step": 2469
},
{
"epoch": 5.040816326530612,
"grad_norm": 3.203125,
"learning_rate": 3.113054745707807e-05,
"loss": 1.2826,
"step": 2470
},
{
"epoch": 5.042857142857143,
"grad_norm": 2.984375,
"learning_rate": 3.1098153547133144e-05,
"loss": 1.3343,
"step": 2471
},
{
"epoch": 5.044897959183674,
"grad_norm": 3.109375,
"learning_rate": 3.106575963718821e-05,
"loss": 1.3592,
"step": 2472
},
{
"epoch": 5.046938775510204,
"grad_norm": 3.0,
"learning_rate": 3.103336572724328e-05,
"loss": 1.3149,
"step": 2473
},
{
"epoch": 5.048979591836734,
"grad_norm": 2.96875,
"learning_rate": 3.1000971817298355e-05,
"loss": 1.2427,
"step": 2474
},
{
"epoch": 5.051020408163265,
"grad_norm": 3.109375,
"learning_rate": 3.096857790735342e-05,
"loss": 1.3504,
"step": 2475
},
{
"epoch": 5.053061224489796,
"grad_norm": 3.125,
"learning_rate": 3.093618399740849e-05,
"loss": 1.4345,
"step": 2476
},
{
"epoch": 5.055102040816327,
"grad_norm": 3.140625,
"learning_rate": 3.090379008746356e-05,
"loss": 1.3201,
"step": 2477
},
{
"epoch": 5.057142857142857,
"grad_norm": 3.015625,
"learning_rate": 3.087139617751863e-05,
"loss": 1.3356,
"step": 2478
},
{
"epoch": 5.059183673469388,
"grad_norm": 2.96875,
"learning_rate": 3.0839002267573696e-05,
"loss": 1.234,
"step": 2479
},
{
"epoch": 5.061224489795919,
"grad_norm": 3.0,
"learning_rate": 3.080660835762877e-05,
"loss": 1.3,
"step": 2480
},
{
"epoch": 5.063265306122449,
"grad_norm": 3.09375,
"learning_rate": 3.0774214447683834e-05,
"loss": 1.3716,
"step": 2481
},
{
"epoch": 5.0653061224489795,
"grad_norm": 2.984375,
"learning_rate": 3.0741820537738906e-05,
"loss": 1.246,
"step": 2482
},
{
"epoch": 5.06734693877551,
"grad_norm": 2.9375,
"learning_rate": 3.070942662779397e-05,
"loss": 1.2669,
"step": 2483
},
{
"epoch": 5.069387755102041,
"grad_norm": 2.828125,
"learning_rate": 3.0677032717849044e-05,
"loss": 1.2663,
"step": 2484
},
{
"epoch": 5.071428571428571,
"grad_norm": 3.09375,
"learning_rate": 3.0644638807904117e-05,
"loss": 1.3593,
"step": 2485
},
{
"epoch": 5.073469387755102,
"grad_norm": 2.953125,
"learning_rate": 3.061224489795919e-05,
"loss": 1.3974,
"step": 2486
},
{
"epoch": 5.075510204081633,
"grad_norm": 2.96875,
"learning_rate": 3.0579850988014254e-05,
"loss": 1.2995,
"step": 2487
},
{
"epoch": 5.077551020408163,
"grad_norm": 3.015625,
"learning_rate": 3.054745707806933e-05,
"loss": 1.2868,
"step": 2488
},
{
"epoch": 5.079591836734694,
"grad_norm": 3.140625,
"learning_rate": 3.0515063168124392e-05,
"loss": 1.3213,
"step": 2489
},
{
"epoch": 5.081632653061225,
"grad_norm": 3.0,
"learning_rate": 3.0482669258179465e-05,
"loss": 1.2516,
"step": 2490
},
{
"epoch": 5.083673469387755,
"grad_norm": 3.0,
"learning_rate": 3.0450275348234537e-05,
"loss": 1.4025,
"step": 2491
},
{
"epoch": 5.085714285714285,
"grad_norm": 3.21875,
"learning_rate": 3.0417881438289603e-05,
"loss": 1.3199,
"step": 2492
},
{
"epoch": 5.087755102040816,
"grad_norm": 3.265625,
"learning_rate": 3.0385487528344675e-05,
"loss": 1.2432,
"step": 2493
},
{
"epoch": 5.089795918367347,
"grad_norm": 3.0625,
"learning_rate": 3.035309361839974e-05,
"loss": 1.3356,
"step": 2494
},
{
"epoch": 5.091836734693878,
"grad_norm": 2.859375,
"learning_rate": 3.0320699708454813e-05,
"loss": 1.2234,
"step": 2495
},
{
"epoch": 5.093877551020408,
"grad_norm": 2.859375,
"learning_rate": 3.0288305798509882e-05,
"loss": 1.2547,
"step": 2496
},
{
"epoch": 5.095918367346939,
"grad_norm": 3.234375,
"learning_rate": 3.0255911888564954e-05,
"loss": 1.2307,
"step": 2497
},
{
"epoch": 5.09795918367347,
"grad_norm": 3.078125,
"learning_rate": 3.022351797862002e-05,
"loss": 1.4016,
"step": 2498
},
{
"epoch": 5.1,
"grad_norm": 2.65625,
"learning_rate": 3.0191124068675092e-05,
"loss": 1.2774,
"step": 2499
},
{
"epoch": 5.1020408163265305,
"grad_norm": 2.96875,
"learning_rate": 3.0158730158730158e-05,
"loss": 1.2827,
"step": 2500
},
{
"epoch": 5.1020408163265305,
"eval_loss": 4.719367504119873,
"eval_runtime": 5.3749,
"eval_samples_per_second": 29.768,
"eval_steps_per_second": 7.442,
"step": 2500
},
{
"epoch": 5.104081632653061,
"grad_norm": 2.953125,
"learning_rate": 3.012633624878523e-05,
"loss": 1.3462,
"step": 2501
},
{
"epoch": 5.106122448979592,
"grad_norm": 3.140625,
"learning_rate": 3.00939423388403e-05,
"loss": 1.2936,
"step": 2502
},
{
"epoch": 5.108163265306122,
"grad_norm": 2.921875,
"learning_rate": 3.0061548428895368e-05,
"loss": 1.2707,
"step": 2503
},
{
"epoch": 5.110204081632653,
"grad_norm": 2.9375,
"learning_rate": 3.0029154518950437e-05,
"loss": 1.2565,
"step": 2504
},
{
"epoch": 5.112244897959184,
"grad_norm": 3.09375,
"learning_rate": 2.999676060900551e-05,
"loss": 1.3035,
"step": 2505
},
{
"epoch": 5.114285714285714,
"grad_norm": 2.96875,
"learning_rate": 2.9964366699060575e-05,
"loss": 1.2588,
"step": 2506
},
{
"epoch": 5.116326530612245,
"grad_norm": 2.953125,
"learning_rate": 2.9931972789115647e-05,
"loss": 1.3161,
"step": 2507
},
{
"epoch": 5.118367346938776,
"grad_norm": 2.96875,
"learning_rate": 2.989957887917072e-05,
"loss": 1.2483,
"step": 2508
},
{
"epoch": 5.1204081632653065,
"grad_norm": 3.0625,
"learning_rate": 2.9867184969225785e-05,
"loss": 1.2803,
"step": 2509
},
{
"epoch": 5.122448979591836,
"grad_norm": 3.046875,
"learning_rate": 2.9834791059280858e-05,
"loss": 1.3361,
"step": 2510
},
{
"epoch": 5.124489795918367,
"grad_norm": 3.328125,
"learning_rate": 2.9802397149335927e-05,
"loss": 1.2656,
"step": 2511
},
{
"epoch": 5.126530612244898,
"grad_norm": 3.21875,
"learning_rate": 2.9770003239391e-05,
"loss": 1.2914,
"step": 2512
},
{
"epoch": 5.128571428571428,
"grad_norm": 3.015625,
"learning_rate": 2.9737609329446064e-05,
"loss": 1.2585,
"step": 2513
},
{
"epoch": 5.130612244897959,
"grad_norm": 3.0625,
"learning_rate": 2.9705215419501137e-05,
"loss": 1.3023,
"step": 2514
},
{
"epoch": 5.13265306122449,
"grad_norm": 3.015625,
"learning_rate": 2.9672821509556202e-05,
"loss": 1.3097,
"step": 2515
},
{
"epoch": 5.134693877551021,
"grad_norm": 2.953125,
"learning_rate": 2.9640427599611275e-05,
"loss": 1.2385,
"step": 2516
},
{
"epoch": 5.136734693877551,
"grad_norm": 3.046875,
"learning_rate": 2.9608033689666344e-05,
"loss": 1.278,
"step": 2517
},
{
"epoch": 5.1387755102040815,
"grad_norm": 3.03125,
"learning_rate": 2.9575639779721416e-05,
"loss": 1.2768,
"step": 2518
},
{
"epoch": 5.140816326530612,
"grad_norm": 2.96875,
"learning_rate": 2.954324586977648e-05,
"loss": 1.3356,
"step": 2519
},
{
"epoch": 5.142857142857143,
"grad_norm": 3.09375,
"learning_rate": 2.9510851959831554e-05,
"loss": 1.2872,
"step": 2520
},
{
"epoch": 5.144897959183673,
"grad_norm": 3.203125,
"learning_rate": 2.947845804988662e-05,
"loss": 1.2726,
"step": 2521
},
{
"epoch": 5.146938775510204,
"grad_norm": 2.84375,
"learning_rate": 2.9446064139941692e-05,
"loss": 1.217,
"step": 2522
},
{
"epoch": 5.148979591836735,
"grad_norm": 3.1875,
"learning_rate": 2.941367022999676e-05,
"loss": 1.3373,
"step": 2523
},
{
"epoch": 5.151020408163265,
"grad_norm": 3.015625,
"learning_rate": 2.938127632005183e-05,
"loss": 1.2756,
"step": 2524
},
{
"epoch": 5.153061224489796,
"grad_norm": 2.828125,
"learning_rate": 2.9348882410106902e-05,
"loss": 1.3123,
"step": 2525
},
{
"epoch": 5.155102040816327,
"grad_norm": 2.859375,
"learning_rate": 2.931648850016197e-05,
"loss": 1.337,
"step": 2526
},
{
"epoch": 5.1571428571428575,
"grad_norm": 2.71875,
"learning_rate": 2.9284094590217043e-05,
"loss": 1.1954,
"step": 2527
},
{
"epoch": 5.159183673469387,
"grad_norm": 2.875,
"learning_rate": 2.925170068027211e-05,
"loss": 1.2323,
"step": 2528
},
{
"epoch": 5.161224489795918,
"grad_norm": 2.921875,
"learning_rate": 2.921930677032718e-05,
"loss": 1.2635,
"step": 2529
},
{
"epoch": 5.163265306122449,
"grad_norm": 2.96875,
"learning_rate": 2.9186912860382247e-05,
"loss": 1.2961,
"step": 2530
},
{
"epoch": 5.16530612244898,
"grad_norm": 2.90625,
"learning_rate": 2.915451895043732e-05,
"loss": 1.2753,
"step": 2531
},
{
"epoch": 5.16734693877551,
"grad_norm": 3.078125,
"learning_rate": 2.912212504049239e-05,
"loss": 1.2558,
"step": 2532
},
{
"epoch": 5.169387755102041,
"grad_norm": 3.078125,
"learning_rate": 2.908973113054746e-05,
"loss": 1.2745,
"step": 2533
},
{
"epoch": 5.171428571428572,
"grad_norm": 3.15625,
"learning_rate": 2.9057337220602526e-05,
"loss": 1.3212,
"step": 2534
},
{
"epoch": 5.173469387755102,
"grad_norm": 3.0,
"learning_rate": 2.90249433106576e-05,
"loss": 1.2592,
"step": 2535
},
{
"epoch": 5.1755102040816325,
"grad_norm": 3.078125,
"learning_rate": 2.8992549400712664e-05,
"loss": 1.4014,
"step": 2536
},
{
"epoch": 5.177551020408163,
"grad_norm": 3.109375,
"learning_rate": 2.8960155490767737e-05,
"loss": 1.2215,
"step": 2537
},
{
"epoch": 5.179591836734694,
"grad_norm": 3.0,
"learning_rate": 2.8927761580822805e-05,
"loss": 1.3057,
"step": 2538
},
{
"epoch": 5.181632653061224,
"grad_norm": 2.78125,
"learning_rate": 2.8895367670877878e-05,
"loss": 1.2552,
"step": 2539
},
{
"epoch": 5.183673469387755,
"grad_norm": 3.140625,
"learning_rate": 2.886297376093295e-05,
"loss": 1.3197,
"step": 2540
},
{
"epoch": 5.185714285714286,
"grad_norm": 2.984375,
"learning_rate": 2.8830579850988016e-05,
"loss": 1.2869,
"step": 2541
},
{
"epoch": 5.187755102040816,
"grad_norm": 3.203125,
"learning_rate": 2.8798185941043088e-05,
"loss": 1.2774,
"step": 2542
},
{
"epoch": 5.189795918367347,
"grad_norm": 3.109375,
"learning_rate": 2.8765792031098154e-05,
"loss": 1.2502,
"step": 2543
},
{
"epoch": 5.191836734693878,
"grad_norm": 3.15625,
"learning_rate": 2.8733398121153226e-05,
"loss": 1.2839,
"step": 2544
},
{
"epoch": 5.1938775510204085,
"grad_norm": 3.09375,
"learning_rate": 2.870100421120829e-05,
"loss": 1.2122,
"step": 2545
},
{
"epoch": 5.1959183673469385,
"grad_norm": 3.0,
"learning_rate": 2.8668610301263364e-05,
"loss": 1.207,
"step": 2546
},
{
"epoch": 5.197959183673469,
"grad_norm": 3.078125,
"learning_rate": 2.8636216391318433e-05,
"loss": 1.3652,
"step": 2547
},
{
"epoch": 5.2,
"grad_norm": 3.078125,
"learning_rate": 2.8603822481373505e-05,
"loss": 1.3008,
"step": 2548
},
{
"epoch": 5.202040816326531,
"grad_norm": 3.015625,
"learning_rate": 2.857142857142857e-05,
"loss": 1.3019,
"step": 2549
},
{
"epoch": 5.204081632653061,
"grad_norm": 3.015625,
"learning_rate": 2.8539034661483643e-05,
"loss": 1.3005,
"step": 2550
},
{
"epoch": 5.206122448979592,
"grad_norm": 2.984375,
"learning_rate": 2.850664075153871e-05,
"loss": 1.2774,
"step": 2551
},
{
"epoch": 5.208163265306123,
"grad_norm": 3.09375,
"learning_rate": 2.847424684159378e-05,
"loss": 1.2344,
"step": 2552
},
{
"epoch": 5.210204081632653,
"grad_norm": 3.0625,
"learning_rate": 2.844185293164885e-05,
"loss": 1.2982,
"step": 2553
},
{
"epoch": 5.2122448979591836,
"grad_norm": 3.09375,
"learning_rate": 2.8409459021703922e-05,
"loss": 1.3391,
"step": 2554
},
{
"epoch": 5.214285714285714,
"grad_norm": 3.109375,
"learning_rate": 2.8377065111758988e-05,
"loss": 1.2379,
"step": 2555
},
{
"epoch": 5.216326530612245,
"grad_norm": 2.84375,
"learning_rate": 2.834467120181406e-05,
"loss": 1.3052,
"step": 2556
},
{
"epoch": 5.218367346938775,
"grad_norm": 2.828125,
"learning_rate": 2.8312277291869133e-05,
"loss": 1.1821,
"step": 2557
},
{
"epoch": 5.220408163265306,
"grad_norm": 2.984375,
"learning_rate": 2.82798833819242e-05,
"loss": 1.3911,
"step": 2558
},
{
"epoch": 5.222448979591837,
"grad_norm": 3.078125,
"learning_rate": 2.824748947197927e-05,
"loss": 1.3909,
"step": 2559
},
{
"epoch": 5.224489795918367,
"grad_norm": 3.09375,
"learning_rate": 2.821509556203434e-05,
"loss": 1.4739,
"step": 2560
},
{
"epoch": 5.226530612244898,
"grad_norm": 3.28125,
"learning_rate": 2.8182701652089412e-05,
"loss": 1.4383,
"step": 2561
},
{
"epoch": 5.228571428571429,
"grad_norm": 3.015625,
"learning_rate": 2.8150307742144478e-05,
"loss": 1.3313,
"step": 2562
},
{
"epoch": 5.2306122448979595,
"grad_norm": 3.25,
"learning_rate": 2.811791383219955e-05,
"loss": 1.317,
"step": 2563
},
{
"epoch": 5.2326530612244895,
"grad_norm": 3.1875,
"learning_rate": 2.8085519922254615e-05,
"loss": 1.3413,
"step": 2564
},
{
"epoch": 5.23469387755102,
"grad_norm": 2.96875,
"learning_rate": 2.8053126012309688e-05,
"loss": 1.2729,
"step": 2565
},
{
"epoch": 5.236734693877551,
"grad_norm": 3.046875,
"learning_rate": 2.8020732102364753e-05,
"loss": 1.2535,
"step": 2566
},
{
"epoch": 5.238775510204082,
"grad_norm": 3.046875,
"learning_rate": 2.7988338192419826e-05,
"loss": 1.2459,
"step": 2567
},
{
"epoch": 5.240816326530612,
"grad_norm": 3.5625,
"learning_rate": 2.7955944282474895e-05,
"loss": 1.4328,
"step": 2568
},
{
"epoch": 5.242857142857143,
"grad_norm": 3.046875,
"learning_rate": 2.7923550372529967e-05,
"loss": 1.187,
"step": 2569
},
{
"epoch": 5.244897959183674,
"grad_norm": 3.0,
"learning_rate": 2.7891156462585033e-05,
"loss": 1.2302,
"step": 2570
},
{
"epoch": 5.246938775510204,
"grad_norm": 3.421875,
"learning_rate": 2.7858762552640105e-05,
"loss": 1.3545,
"step": 2571
},
{
"epoch": 5.248979591836735,
"grad_norm": 3.21875,
"learning_rate": 2.782636864269517e-05,
"loss": 1.352,
"step": 2572
},
{
"epoch": 5.251020408163265,
"grad_norm": 3.296875,
"learning_rate": 2.7793974732750243e-05,
"loss": 1.3513,
"step": 2573
},
{
"epoch": 5.253061224489796,
"grad_norm": 3.171875,
"learning_rate": 2.7761580822805315e-05,
"loss": 1.3107,
"step": 2574
},
{
"epoch": 5.255102040816326,
"grad_norm": 2.8125,
"learning_rate": 2.7729186912860384e-05,
"loss": 1.2053,
"step": 2575
},
{
"epoch": 5.257142857142857,
"grad_norm": 3.046875,
"learning_rate": 2.7696793002915457e-05,
"loss": 1.2961,
"step": 2576
},
{
"epoch": 5.259183673469388,
"grad_norm": 3.3125,
"learning_rate": 2.7664399092970522e-05,
"loss": 1.2129,
"step": 2577
},
{
"epoch": 5.261224489795918,
"grad_norm": 3.453125,
"learning_rate": 2.7632005183025595e-05,
"loss": 1.3549,
"step": 2578
},
{
"epoch": 5.263265306122449,
"grad_norm": 3.0625,
"learning_rate": 2.759961127308066e-05,
"loss": 1.2307,
"step": 2579
},
{
"epoch": 5.26530612244898,
"grad_norm": 3.015625,
"learning_rate": 2.7567217363135732e-05,
"loss": 1.2692,
"step": 2580
},
{
"epoch": 5.2673469387755105,
"grad_norm": 3.1875,
"learning_rate": 2.75348234531908e-05,
"loss": 1.2675,
"step": 2581
},
{
"epoch": 5.2693877551020405,
"grad_norm": 3.109375,
"learning_rate": 2.7502429543245874e-05,
"loss": 1.2751,
"step": 2582
},
{
"epoch": 5.271428571428571,
"grad_norm": 3.015625,
"learning_rate": 2.747003563330094e-05,
"loss": 1.2809,
"step": 2583
},
{
"epoch": 5.273469387755102,
"grad_norm": 3.171875,
"learning_rate": 2.7437641723356012e-05,
"loss": 1.3195,
"step": 2584
},
{
"epoch": 5.275510204081632,
"grad_norm": 2.96875,
"learning_rate": 2.7405247813411077e-05,
"loss": 1.2886,
"step": 2585
},
{
"epoch": 5.277551020408163,
"grad_norm": 3.046875,
"learning_rate": 2.737285390346615e-05,
"loss": 1.3073,
"step": 2586
},
{
"epoch": 5.279591836734694,
"grad_norm": 2.828125,
"learning_rate": 2.734045999352122e-05,
"loss": 1.1732,
"step": 2587
},
{
"epoch": 5.281632653061225,
"grad_norm": 3.390625,
"learning_rate": 2.7308066083576288e-05,
"loss": 1.358,
"step": 2588
},
{
"epoch": 5.283673469387755,
"grad_norm": 3.15625,
"learning_rate": 2.7275672173631357e-05,
"loss": 1.3808,
"step": 2589
},
{
"epoch": 5.285714285714286,
"grad_norm": 3.1875,
"learning_rate": 2.724327826368643e-05,
"loss": 1.2223,
"step": 2590
},
{
"epoch": 5.2877551020408164,
"grad_norm": 3.125,
"learning_rate": 2.72108843537415e-05,
"loss": 1.2423,
"step": 2591
},
{
"epoch": 5.289795918367347,
"grad_norm": 3.28125,
"learning_rate": 2.7178490443796567e-05,
"loss": 1.1799,
"step": 2592
},
{
"epoch": 5.291836734693877,
"grad_norm": 2.890625,
"learning_rate": 2.714609653385164e-05,
"loss": 1.2236,
"step": 2593
},
{
"epoch": 5.293877551020408,
"grad_norm": 2.8125,
"learning_rate": 2.7113702623906705e-05,
"loss": 1.2508,
"step": 2594
},
{
"epoch": 5.295918367346939,
"grad_norm": 3.015625,
"learning_rate": 2.7081308713961777e-05,
"loss": 1.2263,
"step": 2595
},
{
"epoch": 5.29795918367347,
"grad_norm": 2.84375,
"learning_rate": 2.7048914804016846e-05,
"loss": 1.2133,
"step": 2596
},
{
"epoch": 5.3,
"grad_norm": 3.15625,
"learning_rate": 2.701652089407192e-05,
"loss": 1.3155,
"step": 2597
},
{
"epoch": 5.302040816326531,
"grad_norm": 3.125,
"learning_rate": 2.6984126984126984e-05,
"loss": 1.3233,
"step": 2598
},
{
"epoch": 5.3040816326530615,
"grad_norm": 2.96875,
"learning_rate": 2.6951733074182056e-05,
"loss": 1.2423,
"step": 2599
},
{
"epoch": 5.3061224489795915,
"grad_norm": 3.0625,
"learning_rate": 2.6919339164237122e-05,
"loss": 1.2229,
"step": 2600
},
{
"epoch": 5.308163265306122,
"grad_norm": 2.859375,
"learning_rate": 2.6886945254292194e-05,
"loss": 1.2479,
"step": 2601
},
{
"epoch": 5.310204081632653,
"grad_norm": 3.046875,
"learning_rate": 2.6854551344347263e-05,
"loss": 1.2388,
"step": 2602
},
{
"epoch": 5.312244897959184,
"grad_norm": 3.09375,
"learning_rate": 2.6822157434402336e-05,
"loss": 1.2301,
"step": 2603
},
{
"epoch": 5.314285714285714,
"grad_norm": 2.921875,
"learning_rate": 2.67897635244574e-05,
"loss": 1.3326,
"step": 2604
},
{
"epoch": 5.316326530612245,
"grad_norm": 2.9375,
"learning_rate": 2.6757369614512473e-05,
"loss": 1.2315,
"step": 2605
},
{
"epoch": 5.318367346938776,
"grad_norm": 3.03125,
"learning_rate": 2.6724975704567546e-05,
"loss": 1.3211,
"step": 2606
},
{
"epoch": 5.320408163265306,
"grad_norm": 2.96875,
"learning_rate": 2.669258179462261e-05,
"loss": 1.241,
"step": 2607
},
{
"epoch": 5.322448979591837,
"grad_norm": 3.03125,
"learning_rate": 2.6660187884677684e-05,
"loss": 1.2148,
"step": 2608
},
{
"epoch": 5.3244897959183675,
"grad_norm": 3.21875,
"learning_rate": 2.662779397473275e-05,
"loss": 1.2036,
"step": 2609
},
{
"epoch": 5.326530612244898,
"grad_norm": 3.1875,
"learning_rate": 2.6595400064787822e-05,
"loss": 1.2828,
"step": 2610
},
{
"epoch": 5.328571428571428,
"grad_norm": 3.09375,
"learning_rate": 2.656300615484289e-05,
"loss": 1.2156,
"step": 2611
},
{
"epoch": 5.330612244897959,
"grad_norm": 3.15625,
"learning_rate": 2.6530612244897963e-05,
"loss": 1.2831,
"step": 2612
},
{
"epoch": 5.33265306122449,
"grad_norm": 2.96875,
"learning_rate": 2.649821833495303e-05,
"loss": 1.2035,
"step": 2613
},
{
"epoch": 5.33469387755102,
"grad_norm": 3.171875,
"learning_rate": 2.64658244250081e-05,
"loss": 1.3654,
"step": 2614
},
{
"epoch": 5.336734693877551,
"grad_norm": 3.15625,
"learning_rate": 2.6433430515063167e-05,
"loss": 1.2816,
"step": 2615
},
{
"epoch": 5.338775510204082,
"grad_norm": 3.03125,
"learning_rate": 2.640103660511824e-05,
"loss": 1.307,
"step": 2616
},
{
"epoch": 5.340816326530613,
"grad_norm": 3.15625,
"learning_rate": 2.6368642695173308e-05,
"loss": 1.2355,
"step": 2617
},
{
"epoch": 5.3428571428571425,
"grad_norm": 3.109375,
"learning_rate": 2.633624878522838e-05,
"loss": 1.2479,
"step": 2618
},
{
"epoch": 5.344897959183673,
"grad_norm": 2.984375,
"learning_rate": 2.6303854875283446e-05,
"loss": 1.3011,
"step": 2619
},
{
"epoch": 5.346938775510204,
"grad_norm": 3.046875,
"learning_rate": 2.6271460965338518e-05,
"loss": 1.3397,
"step": 2620
},
{
"epoch": 5.348979591836735,
"grad_norm": 2.96875,
"learning_rate": 2.6239067055393584e-05,
"loss": 1.2757,
"step": 2621
},
{
"epoch": 5.351020408163265,
"grad_norm": 3.09375,
"learning_rate": 2.6206673145448656e-05,
"loss": 1.2729,
"step": 2622
},
{
"epoch": 5.353061224489796,
"grad_norm": 3.0,
"learning_rate": 2.617427923550373e-05,
"loss": 1.2668,
"step": 2623
},
{
"epoch": 5.355102040816327,
"grad_norm": 3.125,
"learning_rate": 2.6141885325558797e-05,
"loss": 1.321,
"step": 2624
},
{
"epoch": 5.357142857142857,
"grad_norm": 3.09375,
"learning_rate": 2.610949141561387e-05,
"loss": 1.307,
"step": 2625
},
{
"epoch": 5.359183673469388,
"grad_norm": 3.0625,
"learning_rate": 2.6077097505668935e-05,
"loss": 1.2168,
"step": 2626
},
{
"epoch": 5.3612244897959185,
"grad_norm": 3.03125,
"learning_rate": 2.6044703595724008e-05,
"loss": 1.1955,
"step": 2627
},
{
"epoch": 5.363265306122449,
"grad_norm": 3.03125,
"learning_rate": 2.6012309685779073e-05,
"loss": 1.2429,
"step": 2628
},
{
"epoch": 5.365306122448979,
"grad_norm": 3.078125,
"learning_rate": 2.5979915775834146e-05,
"loss": 1.3035,
"step": 2629
},
{
"epoch": 5.36734693877551,
"grad_norm": 3.296875,
"learning_rate": 2.594752186588921e-05,
"loss": 1.2768,
"step": 2630
},
{
"epoch": 5.369387755102041,
"grad_norm": 3.109375,
"learning_rate": 2.5915127955944283e-05,
"loss": 1.2711,
"step": 2631
},
{
"epoch": 5.371428571428572,
"grad_norm": 3.1875,
"learning_rate": 2.5882734045999352e-05,
"loss": 1.2826,
"step": 2632
},
{
"epoch": 5.373469387755102,
"grad_norm": 3.015625,
"learning_rate": 2.5850340136054425e-05,
"loss": 1.2569,
"step": 2633
},
{
"epoch": 5.375510204081633,
"grad_norm": 3.125,
"learning_rate": 2.581794622610949e-05,
"loss": 1.2456,
"step": 2634
},
{
"epoch": 5.377551020408164,
"grad_norm": 3.296875,
"learning_rate": 2.5785552316164563e-05,
"loss": 1.3074,
"step": 2635
},
{
"epoch": 5.3795918367346935,
"grad_norm": 3.15625,
"learning_rate": 2.575315840621963e-05,
"loss": 1.1916,
"step": 2636
},
{
"epoch": 5.381632653061224,
"grad_norm": 3.21875,
"learning_rate": 2.57207644962747e-05,
"loss": 1.2701,
"step": 2637
},
{
"epoch": 5.383673469387755,
"grad_norm": 3.140625,
"learning_rate": 2.568837058632977e-05,
"loss": 1.3189,
"step": 2638
},
{
"epoch": 5.385714285714286,
"grad_norm": 2.953125,
"learning_rate": 2.5655976676384842e-05,
"loss": 1.1504,
"step": 2639
},
{
"epoch": 5.387755102040816,
"grad_norm": 2.96875,
"learning_rate": 2.5623582766439914e-05,
"loss": 1.2828,
"step": 2640
},
{
"epoch": 5.389795918367347,
"grad_norm": 3.171875,
"learning_rate": 2.559118885649498e-05,
"loss": 1.2665,
"step": 2641
},
{
"epoch": 5.391836734693878,
"grad_norm": 2.90625,
"learning_rate": 2.5558794946550052e-05,
"loss": 1.2238,
"step": 2642
},
{
"epoch": 5.393877551020408,
"grad_norm": 3.1875,
"learning_rate": 2.5526401036605118e-05,
"loss": 1.2773,
"step": 2643
},
{
"epoch": 5.395918367346939,
"grad_norm": 2.921875,
"learning_rate": 2.549400712666019e-05,
"loss": 1.2124,
"step": 2644
},
{
"epoch": 5.3979591836734695,
"grad_norm": 3.359375,
"learning_rate": 2.546161321671526e-05,
"loss": 1.229,
"step": 2645
},
{
"epoch": 5.4,
"grad_norm": 3.0625,
"learning_rate": 2.542921930677033e-05,
"loss": 1.201,
"step": 2646
},
{
"epoch": 5.40204081632653,
"grad_norm": 3.046875,
"learning_rate": 2.5396825396825397e-05,
"loss": 1.2548,
"step": 2647
},
{
"epoch": 5.404081632653061,
"grad_norm": 3.40625,
"learning_rate": 2.536443148688047e-05,
"loss": 1.3183,
"step": 2648
},
{
"epoch": 5.406122448979592,
"grad_norm": 3.0625,
"learning_rate": 2.5332037576935535e-05,
"loss": 1.2614,
"step": 2649
},
{
"epoch": 5.408163265306122,
"grad_norm": 3.09375,
"learning_rate": 2.5299643666990607e-05,
"loss": 1.2114,
"step": 2650
},
{
"epoch": 5.410204081632653,
"grad_norm": 3.28125,
"learning_rate": 2.5267249757045673e-05,
"loss": 1.2715,
"step": 2651
},
{
"epoch": 5.412244897959184,
"grad_norm": 3.078125,
"learning_rate": 2.5234855847100745e-05,
"loss": 1.2997,
"step": 2652
},
{
"epoch": 5.414285714285715,
"grad_norm": 3.125,
"learning_rate": 2.5202461937155814e-05,
"loss": 1.233,
"step": 2653
},
{
"epoch": 5.416326530612245,
"grad_norm": 3.078125,
"learning_rate": 2.5170068027210887e-05,
"loss": 1.272,
"step": 2654
},
{
"epoch": 5.418367346938775,
"grad_norm": 3.234375,
"learning_rate": 2.5137674117265952e-05,
"loss": 1.2805,
"step": 2655
},
{
"epoch": 5.420408163265306,
"grad_norm": 3.0625,
"learning_rate": 2.5105280207321025e-05,
"loss": 1.2602,
"step": 2656
},
{
"epoch": 5.422448979591837,
"grad_norm": 3.078125,
"learning_rate": 2.5072886297376097e-05,
"loss": 1.2643,
"step": 2657
},
{
"epoch": 5.424489795918367,
"grad_norm": 3.109375,
"learning_rate": 2.5040492387431162e-05,
"loss": 1.3085,
"step": 2658
},
{
"epoch": 5.426530612244898,
"grad_norm": 2.890625,
"learning_rate": 2.5008098477486235e-05,
"loss": 1.2143,
"step": 2659
},
{
"epoch": 5.428571428571429,
"grad_norm": 3.203125,
"learning_rate": 2.4975704567541304e-05,
"loss": 1.2469,
"step": 2660
},
{
"epoch": 5.430612244897959,
"grad_norm": 3.234375,
"learning_rate": 2.4943310657596373e-05,
"loss": 1.2228,
"step": 2661
},
{
"epoch": 5.43265306122449,
"grad_norm": 3.15625,
"learning_rate": 2.4910916747651442e-05,
"loss": 1.2322,
"step": 2662
},
{
"epoch": 5.4346938775510205,
"grad_norm": 3.09375,
"learning_rate": 2.487852283770651e-05,
"loss": 1.2408,
"step": 2663
},
{
"epoch": 5.436734693877551,
"grad_norm": 2.984375,
"learning_rate": 2.4846128927761583e-05,
"loss": 1.2469,
"step": 2664
},
{
"epoch": 5.438775510204081,
"grad_norm": 3.0,
"learning_rate": 2.4813735017816652e-05,
"loss": 1.2626,
"step": 2665
},
{
"epoch": 5.440816326530612,
"grad_norm": 3.109375,
"learning_rate": 2.478134110787172e-05,
"loss": 1.2825,
"step": 2666
},
{
"epoch": 5.442857142857143,
"grad_norm": 3.25,
"learning_rate": 2.4748947197926793e-05,
"loss": 1.3149,
"step": 2667
},
{
"epoch": 5.444897959183674,
"grad_norm": 3.0625,
"learning_rate": 2.4716553287981862e-05,
"loss": 1.293,
"step": 2668
},
{
"epoch": 5.446938775510204,
"grad_norm": 2.9375,
"learning_rate": 2.468415937803693e-05,
"loss": 1.2099,
"step": 2669
},
{
"epoch": 5.448979591836735,
"grad_norm": 3.3125,
"learning_rate": 2.4651765468092e-05,
"loss": 1.3086,
"step": 2670
},
{
"epoch": 5.451020408163266,
"grad_norm": 3.046875,
"learning_rate": 2.461937155814707e-05,
"loss": 1.2285,
"step": 2671
},
{
"epoch": 5.453061224489796,
"grad_norm": 3.21875,
"learning_rate": 2.4586977648202138e-05,
"loss": 1.1502,
"step": 2672
},
{
"epoch": 5.455102040816326,
"grad_norm": 2.84375,
"learning_rate": 2.4554583738257207e-05,
"loss": 1.1806,
"step": 2673
},
{
"epoch": 5.457142857142857,
"grad_norm": 3.15625,
"learning_rate": 2.452218982831228e-05,
"loss": 1.2674,
"step": 2674
},
{
"epoch": 5.459183673469388,
"grad_norm": 3.109375,
"learning_rate": 2.448979591836735e-05,
"loss": 1.2469,
"step": 2675
},
{
"epoch": 5.461224489795918,
"grad_norm": 3.1875,
"learning_rate": 2.4457402008422417e-05,
"loss": 1.3458,
"step": 2676
},
{
"epoch": 5.463265306122449,
"grad_norm": 3.3125,
"learning_rate": 2.4425008098477486e-05,
"loss": 1.2549,
"step": 2677
},
{
"epoch": 5.46530612244898,
"grad_norm": 3.078125,
"learning_rate": 2.4392614188532555e-05,
"loss": 1.1858,
"step": 2678
},
{
"epoch": 5.46734693877551,
"grad_norm": 3.109375,
"learning_rate": 2.4360220278587624e-05,
"loss": 1.257,
"step": 2679
},
{
"epoch": 5.469387755102041,
"grad_norm": 3.203125,
"learning_rate": 2.4327826368642697e-05,
"loss": 1.2456,
"step": 2680
},
{
"epoch": 5.4714285714285715,
"grad_norm": 3.1875,
"learning_rate": 2.4295432458697766e-05,
"loss": 1.2215,
"step": 2681
},
{
"epoch": 5.473469387755102,
"grad_norm": 3.078125,
"learning_rate": 2.4263038548752838e-05,
"loss": 1.1833,
"step": 2682
},
{
"epoch": 5.475510204081632,
"grad_norm": 3.109375,
"learning_rate": 2.4230644638807907e-05,
"loss": 1.2712,
"step": 2683
},
{
"epoch": 5.477551020408163,
"grad_norm": 3.03125,
"learning_rate": 2.4198250728862976e-05,
"loss": 1.3041,
"step": 2684
},
{
"epoch": 5.479591836734694,
"grad_norm": 2.859375,
"learning_rate": 2.4165856818918045e-05,
"loss": 1.2469,
"step": 2685
},
{
"epoch": 5.481632653061224,
"grad_norm": 3.375,
"learning_rate": 2.4133462908973114e-05,
"loss": 1.2514,
"step": 2686
},
{
"epoch": 5.483673469387755,
"grad_norm": 3.4375,
"learning_rate": 2.4101068999028183e-05,
"loss": 1.3624,
"step": 2687
},
{
"epoch": 5.485714285714286,
"grad_norm": 3.328125,
"learning_rate": 2.4068675089083255e-05,
"loss": 1.2516,
"step": 2688
},
{
"epoch": 5.487755102040817,
"grad_norm": 3.109375,
"learning_rate": 2.4036281179138324e-05,
"loss": 1.2092,
"step": 2689
},
{
"epoch": 5.489795918367347,
"grad_norm": 3.140625,
"learning_rate": 2.4003887269193393e-05,
"loss": 1.2426,
"step": 2690
},
{
"epoch": 5.4918367346938775,
"grad_norm": 3.15625,
"learning_rate": 2.3971493359248462e-05,
"loss": 1.3379,
"step": 2691
},
{
"epoch": 5.493877551020408,
"grad_norm": 3.34375,
"learning_rate": 2.393909944930353e-05,
"loss": 1.2527,
"step": 2692
},
{
"epoch": 5.495918367346939,
"grad_norm": 3.171875,
"learning_rate": 2.39067055393586e-05,
"loss": 1.2275,
"step": 2693
},
{
"epoch": 5.497959183673469,
"grad_norm": 3.15625,
"learning_rate": 2.387431162941367e-05,
"loss": 1.2257,
"step": 2694
},
{
"epoch": 5.5,
"grad_norm": 3.265625,
"learning_rate": 2.384191771946874e-05,
"loss": 1.2692,
"step": 2695
},
{
"epoch": 5.502040816326531,
"grad_norm": 3.203125,
"learning_rate": 2.380952380952381e-05,
"loss": 1.2592,
"step": 2696
},
{
"epoch": 5.504081632653062,
"grad_norm": 3.328125,
"learning_rate": 2.3777129899578883e-05,
"loss": 1.3027,
"step": 2697
},
{
"epoch": 5.506122448979592,
"grad_norm": 3.140625,
"learning_rate": 2.374473598963395e-05,
"loss": 1.1708,
"step": 2698
},
{
"epoch": 5.5081632653061225,
"grad_norm": 3.125,
"learning_rate": 2.371234207968902e-05,
"loss": 1.2265,
"step": 2699
},
{
"epoch": 5.510204081632653,
"grad_norm": 3.203125,
"learning_rate": 2.367994816974409e-05,
"loss": 1.1826,
"step": 2700
},
{
"epoch": 5.512244897959183,
"grad_norm": 2.984375,
"learning_rate": 2.364755425979916e-05,
"loss": 1.2291,
"step": 2701
},
{
"epoch": 5.514285714285714,
"grad_norm": 3.21875,
"learning_rate": 2.3615160349854227e-05,
"loss": 1.1737,
"step": 2702
},
{
"epoch": 5.516326530612245,
"grad_norm": 3.25,
"learning_rate": 2.35827664399093e-05,
"loss": 1.2176,
"step": 2703
},
{
"epoch": 5.518367346938776,
"grad_norm": 3.40625,
"learning_rate": 2.355037252996437e-05,
"loss": 1.2538,
"step": 2704
},
{
"epoch": 5.520408163265306,
"grad_norm": 3.03125,
"learning_rate": 2.3517978620019438e-05,
"loss": 1.2886,
"step": 2705
},
{
"epoch": 5.522448979591837,
"grad_norm": 3.078125,
"learning_rate": 2.3485584710074507e-05,
"loss": 1.3369,
"step": 2706
},
{
"epoch": 5.524489795918368,
"grad_norm": 3.28125,
"learning_rate": 2.3453190800129576e-05,
"loss": 1.256,
"step": 2707
},
{
"epoch": 5.526530612244898,
"grad_norm": 3.265625,
"learning_rate": 2.3420796890184645e-05,
"loss": 1.4306,
"step": 2708
},
{
"epoch": 5.5285714285714285,
"grad_norm": 3.203125,
"learning_rate": 2.3388402980239717e-05,
"loss": 1.3173,
"step": 2709
},
{
"epoch": 5.530612244897959,
"grad_norm": 3.25,
"learning_rate": 2.3356009070294786e-05,
"loss": 1.2163,
"step": 2710
},
{
"epoch": 5.53265306122449,
"grad_norm": 2.953125,
"learning_rate": 2.3323615160349855e-05,
"loss": 1.2397,
"step": 2711
},
{
"epoch": 5.53469387755102,
"grad_norm": 3.140625,
"learning_rate": 2.3291221250404924e-05,
"loss": 1.3248,
"step": 2712
},
{
"epoch": 5.536734693877551,
"grad_norm": 3.1875,
"learning_rate": 2.3258827340459996e-05,
"loss": 1.2536,
"step": 2713
},
{
"epoch": 5.538775510204082,
"grad_norm": 3.0625,
"learning_rate": 2.3226433430515065e-05,
"loss": 1.2132,
"step": 2714
},
{
"epoch": 5.540816326530612,
"grad_norm": 3.09375,
"learning_rate": 2.3194039520570134e-05,
"loss": 1.1531,
"step": 2715
},
{
"epoch": 5.542857142857143,
"grad_norm": 3.4375,
"learning_rate": 2.3161645610625203e-05,
"loss": 1.2792,
"step": 2716
},
{
"epoch": 5.544897959183674,
"grad_norm": 3.265625,
"learning_rate": 2.3129251700680275e-05,
"loss": 1.3612,
"step": 2717
},
{
"epoch": 5.546938775510204,
"grad_norm": 2.859375,
"learning_rate": 2.3096857790735344e-05,
"loss": 1.2006,
"step": 2718
},
{
"epoch": 5.548979591836734,
"grad_norm": 3.0,
"learning_rate": 2.3064463880790413e-05,
"loss": 1.1972,
"step": 2719
},
{
"epoch": 5.551020408163265,
"grad_norm": 3.09375,
"learning_rate": 2.3032069970845482e-05,
"loss": 1.3005,
"step": 2720
},
{
"epoch": 5.553061224489796,
"grad_norm": 3.109375,
"learning_rate": 2.299967606090055e-05,
"loss": 1.2761,
"step": 2721
},
{
"epoch": 5.555102040816326,
"grad_norm": 3.015625,
"learning_rate": 2.296728215095562e-05,
"loss": 1.1637,
"step": 2722
},
{
"epoch": 5.557142857142857,
"grad_norm": 3.0625,
"learning_rate": 2.293488824101069e-05,
"loss": 1.2125,
"step": 2723
},
{
"epoch": 5.559183673469388,
"grad_norm": 2.875,
"learning_rate": 2.290249433106576e-05,
"loss": 1.2649,
"step": 2724
},
{
"epoch": 5.561224489795919,
"grad_norm": 3.03125,
"learning_rate": 2.287010042112083e-05,
"loss": 1.276,
"step": 2725
},
{
"epoch": 5.563265306122449,
"grad_norm": 3.25,
"learning_rate": 2.28377065111759e-05,
"loss": 1.1763,
"step": 2726
},
{
"epoch": 5.5653061224489795,
"grad_norm": 3.0,
"learning_rate": 2.280531260123097e-05,
"loss": 1.1999,
"step": 2727
},
{
"epoch": 5.56734693877551,
"grad_norm": 3.15625,
"learning_rate": 2.2772918691286037e-05,
"loss": 1.2151,
"step": 2728
},
{
"epoch": 5.569387755102041,
"grad_norm": 3.0,
"learning_rate": 2.2740524781341106e-05,
"loss": 1.2183,
"step": 2729
},
{
"epoch": 5.571428571428571,
"grad_norm": 2.859375,
"learning_rate": 2.270813087139618e-05,
"loss": 1.1797,
"step": 2730
},
{
"epoch": 5.573469387755102,
"grad_norm": 3.109375,
"learning_rate": 2.267573696145125e-05,
"loss": 1.2448,
"step": 2731
},
{
"epoch": 5.575510204081633,
"grad_norm": 2.984375,
"learning_rate": 2.264334305150632e-05,
"loss": 1.256,
"step": 2732
},
{
"epoch": 5.577551020408164,
"grad_norm": 3.0625,
"learning_rate": 2.261094914156139e-05,
"loss": 1.1961,
"step": 2733
},
{
"epoch": 5.579591836734694,
"grad_norm": 3.328125,
"learning_rate": 2.2578555231616458e-05,
"loss": 1.2582,
"step": 2734
},
{
"epoch": 5.581632653061225,
"grad_norm": 2.890625,
"learning_rate": 2.2546161321671527e-05,
"loss": 1.1469,
"step": 2735
},
{
"epoch": 5.583673469387755,
"grad_norm": 3.015625,
"learning_rate": 2.2513767411726596e-05,
"loss": 1.1698,
"step": 2736
},
{
"epoch": 5.585714285714285,
"grad_norm": 2.921875,
"learning_rate": 2.2481373501781665e-05,
"loss": 1.2056,
"step": 2737
},
{
"epoch": 5.587755102040816,
"grad_norm": 3.171875,
"learning_rate": 2.2448979591836737e-05,
"loss": 1.2016,
"step": 2738
},
{
"epoch": 5.589795918367347,
"grad_norm": 3.28125,
"learning_rate": 2.2416585681891806e-05,
"loss": 1.2957,
"step": 2739
},
{
"epoch": 5.591836734693878,
"grad_norm": 3.25,
"learning_rate": 2.2384191771946875e-05,
"loss": 1.3345,
"step": 2740
},
{
"epoch": 5.593877551020408,
"grad_norm": 3.203125,
"learning_rate": 2.2351797862001944e-05,
"loss": 1.2666,
"step": 2741
},
{
"epoch": 5.595918367346939,
"grad_norm": 3.28125,
"learning_rate": 2.2319403952057013e-05,
"loss": 1.2584,
"step": 2742
},
{
"epoch": 5.59795918367347,
"grad_norm": 2.734375,
"learning_rate": 2.2287010042112082e-05,
"loss": 1.1868,
"step": 2743
},
{
"epoch": 5.6,
"grad_norm": 3.328125,
"learning_rate": 2.225461613216715e-05,
"loss": 1.2462,
"step": 2744
},
{
"epoch": 5.6020408163265305,
"grad_norm": 3.265625,
"learning_rate": 2.2222222222222223e-05,
"loss": 1.2716,
"step": 2745
},
{
"epoch": 5.604081632653061,
"grad_norm": 3.0,
"learning_rate": 2.2189828312277296e-05,
"loss": 1.265,
"step": 2746
},
{
"epoch": 5.606122448979592,
"grad_norm": 3.203125,
"learning_rate": 2.2157434402332365e-05,
"loss": 1.3144,
"step": 2747
},
{
"epoch": 5.608163265306122,
"grad_norm": 3.03125,
"learning_rate": 2.2125040492387434e-05,
"loss": 1.1966,
"step": 2748
},
{
"epoch": 5.610204081632653,
"grad_norm": 3.046875,
"learning_rate": 2.2092646582442503e-05,
"loss": 1.1719,
"step": 2749
},
{
"epoch": 5.612244897959184,
"grad_norm": 3.09375,
"learning_rate": 2.206025267249757e-05,
"loss": 1.2491,
"step": 2750
},
{
"epoch": 5.614285714285714,
"grad_norm": 3.0,
"learning_rate": 2.202785876255264e-05,
"loss": 1.2147,
"step": 2751
},
{
"epoch": 5.616326530612245,
"grad_norm": 2.859375,
"learning_rate": 2.1995464852607713e-05,
"loss": 1.235,
"step": 2752
},
{
"epoch": 5.618367346938776,
"grad_norm": 3.15625,
"learning_rate": 2.1963070942662782e-05,
"loss": 1.1965,
"step": 2753
},
{
"epoch": 5.6204081632653065,
"grad_norm": 3.265625,
"learning_rate": 2.193067703271785e-05,
"loss": 1.2848,
"step": 2754
},
{
"epoch": 5.622448979591836,
"grad_norm": 3.0,
"learning_rate": 2.189828312277292e-05,
"loss": 1.2666,
"step": 2755
},
{
"epoch": 5.624489795918367,
"grad_norm": 3.109375,
"learning_rate": 2.186588921282799e-05,
"loss": 1.1873,
"step": 2756
},
{
"epoch": 5.626530612244898,
"grad_norm": 3.3125,
"learning_rate": 2.1833495302883058e-05,
"loss": 1.3085,
"step": 2757
},
{
"epoch": 5.628571428571428,
"grad_norm": 3.1875,
"learning_rate": 2.1801101392938127e-05,
"loss": 1.2045,
"step": 2758
},
{
"epoch": 5.630612244897959,
"grad_norm": 3.15625,
"learning_rate": 2.17687074829932e-05,
"loss": 1.234,
"step": 2759
},
{
"epoch": 5.63265306122449,
"grad_norm": 3.0625,
"learning_rate": 2.1736313573048268e-05,
"loss": 1.1806,
"step": 2760
},
{
"epoch": 5.634693877551021,
"grad_norm": 2.921875,
"learning_rate": 2.1703919663103337e-05,
"loss": 1.2263,
"step": 2761
},
{
"epoch": 5.636734693877551,
"grad_norm": 3.078125,
"learning_rate": 2.1671525753158406e-05,
"loss": 1.3201,
"step": 2762
},
{
"epoch": 5.6387755102040815,
"grad_norm": 3.53125,
"learning_rate": 2.1639131843213478e-05,
"loss": 1.3456,
"step": 2763
},
{
"epoch": 5.640816326530612,
"grad_norm": 2.84375,
"learning_rate": 2.1606737933268547e-05,
"loss": 1.1707,
"step": 2764
},
{
"epoch": 5.642857142857143,
"grad_norm": 3.125,
"learning_rate": 2.1574344023323616e-05,
"loss": 1.2462,
"step": 2765
},
{
"epoch": 5.644897959183673,
"grad_norm": 2.96875,
"learning_rate": 2.1541950113378685e-05,
"loss": 1.2354,
"step": 2766
},
{
"epoch": 5.646938775510204,
"grad_norm": 3.234375,
"learning_rate": 2.1509556203433757e-05,
"loss": 1.2973,
"step": 2767
},
{
"epoch": 5.648979591836735,
"grad_norm": 3.203125,
"learning_rate": 2.1477162293488826e-05,
"loss": 1.2441,
"step": 2768
},
{
"epoch": 5.651020408163266,
"grad_norm": 3.140625,
"learning_rate": 2.1444768383543895e-05,
"loss": 1.2074,
"step": 2769
},
{
"epoch": 5.653061224489796,
"grad_norm": 2.96875,
"learning_rate": 2.1412374473598964e-05,
"loss": 1.253,
"step": 2770
},
{
"epoch": 5.655102040816327,
"grad_norm": 3.21875,
"learning_rate": 2.1379980563654033e-05,
"loss": 1.2768,
"step": 2771
},
{
"epoch": 5.6571428571428575,
"grad_norm": 3.234375,
"learning_rate": 2.1347586653709102e-05,
"loss": 1.2561,
"step": 2772
},
{
"epoch": 5.659183673469387,
"grad_norm": 3.203125,
"learning_rate": 2.1315192743764175e-05,
"loss": 1.3059,
"step": 2773
},
{
"epoch": 5.661224489795918,
"grad_norm": 3.03125,
"learning_rate": 2.1282798833819244e-05,
"loss": 1.2636,
"step": 2774
},
{
"epoch": 5.663265306122449,
"grad_norm": 3.25,
"learning_rate": 2.1250404923874313e-05,
"loss": 1.3502,
"step": 2775
},
{
"epoch": 5.66530612244898,
"grad_norm": 3.234375,
"learning_rate": 2.121801101392938e-05,
"loss": 1.2512,
"step": 2776
},
{
"epoch": 5.66734693877551,
"grad_norm": 3.296875,
"learning_rate": 2.118561710398445e-05,
"loss": 1.2711,
"step": 2777
},
{
"epoch": 5.669387755102041,
"grad_norm": 3.359375,
"learning_rate": 2.115322319403952e-05,
"loss": 1.2799,
"step": 2778
},
{
"epoch": 5.671428571428572,
"grad_norm": 3.203125,
"learning_rate": 2.1120829284094592e-05,
"loss": 1.268,
"step": 2779
},
{
"epoch": 5.673469387755102,
"grad_norm": 3.046875,
"learning_rate": 2.108843537414966e-05,
"loss": 1.2214,
"step": 2780
},
{
"epoch": 5.6755102040816325,
"grad_norm": 2.96875,
"learning_rate": 2.1056041464204733e-05,
"loss": 1.1798,
"step": 2781
},
{
"epoch": 5.677551020408163,
"grad_norm": 3.171875,
"learning_rate": 2.1023647554259802e-05,
"loss": 1.327,
"step": 2782
},
{
"epoch": 5.679591836734694,
"grad_norm": 3.3125,
"learning_rate": 2.099125364431487e-05,
"loss": 1.3423,
"step": 2783
},
{
"epoch": 5.681632653061224,
"grad_norm": 3.171875,
"learning_rate": 2.095885973436994e-05,
"loss": 1.3002,
"step": 2784
},
{
"epoch": 5.683673469387755,
"grad_norm": 3.421875,
"learning_rate": 2.092646582442501e-05,
"loss": 1.2442,
"step": 2785
},
{
"epoch": 5.685714285714286,
"grad_norm": 3.15625,
"learning_rate": 2.0894071914480078e-05,
"loss": 1.2736,
"step": 2786
},
{
"epoch": 5.687755102040816,
"grad_norm": 3.0625,
"learning_rate": 2.0861678004535147e-05,
"loss": 1.219,
"step": 2787
},
{
"epoch": 5.689795918367347,
"grad_norm": 3.15625,
"learning_rate": 2.082928409459022e-05,
"loss": 1.2294,
"step": 2788
},
{
"epoch": 5.691836734693878,
"grad_norm": 2.90625,
"learning_rate": 2.0796890184645288e-05,
"loss": 1.2175,
"step": 2789
},
{
"epoch": 5.6938775510204085,
"grad_norm": 3.28125,
"learning_rate": 2.0764496274700357e-05,
"loss": 1.3087,
"step": 2790
},
{
"epoch": 5.6959183673469385,
"grad_norm": 3.265625,
"learning_rate": 2.0732102364755426e-05,
"loss": 1.253,
"step": 2791
},
{
"epoch": 5.697959183673469,
"grad_norm": 3.109375,
"learning_rate": 2.0699708454810495e-05,
"loss": 1.2021,
"step": 2792
},
{
"epoch": 5.7,
"grad_norm": 3.21875,
"learning_rate": 2.0667314544865564e-05,
"loss": 1.2321,
"step": 2793
},
{
"epoch": 5.70204081632653,
"grad_norm": 3.109375,
"learning_rate": 2.0634920634920636e-05,
"loss": 1.2805,
"step": 2794
},
{
"epoch": 5.704081632653061,
"grad_norm": 3.171875,
"learning_rate": 2.0602526724975705e-05,
"loss": 1.2208,
"step": 2795
},
{
"epoch": 5.706122448979592,
"grad_norm": 3.265625,
"learning_rate": 2.0570132815030778e-05,
"loss": 1.2811,
"step": 2796
},
{
"epoch": 5.708163265306123,
"grad_norm": 3.0,
"learning_rate": 2.0537738905085847e-05,
"loss": 1.275,
"step": 2797
},
{
"epoch": 5.710204081632653,
"grad_norm": 2.984375,
"learning_rate": 2.0505344995140916e-05,
"loss": 1.2855,
"step": 2798
},
{
"epoch": 5.7122448979591836,
"grad_norm": 2.859375,
"learning_rate": 2.0472951085195985e-05,
"loss": 1.2407,
"step": 2799
},
{
"epoch": 5.714285714285714,
"grad_norm": 3.15625,
"learning_rate": 2.0440557175251054e-05,
"loss": 1.2118,
"step": 2800
},
{
"epoch": 5.716326530612245,
"grad_norm": 2.890625,
"learning_rate": 2.0408163265306123e-05,
"loss": 1.1587,
"step": 2801
},
{
"epoch": 5.718367346938775,
"grad_norm": 2.984375,
"learning_rate": 2.0375769355361195e-05,
"loss": 1.2031,
"step": 2802
},
{
"epoch": 5.720408163265306,
"grad_norm": 3.234375,
"learning_rate": 2.0343375445416264e-05,
"loss": 1.2401,
"step": 2803
},
{
"epoch": 5.722448979591837,
"grad_norm": 3.296875,
"learning_rate": 2.0310981535471333e-05,
"loss": 1.3242,
"step": 2804
},
{
"epoch": 5.724489795918368,
"grad_norm": 3.3125,
"learning_rate": 2.0278587625526402e-05,
"loss": 1.2476,
"step": 2805
},
{
"epoch": 5.726530612244898,
"grad_norm": 3.21875,
"learning_rate": 2.024619371558147e-05,
"loss": 1.2432,
"step": 2806
},
{
"epoch": 5.728571428571429,
"grad_norm": 2.984375,
"learning_rate": 2.021379980563654e-05,
"loss": 1.1582,
"step": 2807
},
{
"epoch": 5.7306122448979595,
"grad_norm": 3.296875,
"learning_rate": 2.018140589569161e-05,
"loss": 1.3297,
"step": 2808
},
{
"epoch": 5.7326530612244895,
"grad_norm": 3.109375,
"learning_rate": 2.014901198574668e-05,
"loss": 1.2052,
"step": 2809
},
{
"epoch": 5.73469387755102,
"grad_norm": 3.3125,
"learning_rate": 2.011661807580175e-05,
"loss": 1.2611,
"step": 2810
},
{
"epoch": 5.736734693877551,
"grad_norm": 3.28125,
"learning_rate": 2.008422416585682e-05,
"loss": 1.2746,
"step": 2811
},
{
"epoch": 5.738775510204082,
"grad_norm": 3.0625,
"learning_rate": 2.005183025591189e-05,
"loss": 1.2039,
"step": 2812
},
{
"epoch": 5.740816326530612,
"grad_norm": 2.890625,
"learning_rate": 2.001943634596696e-05,
"loss": 1.328,
"step": 2813
},
{
"epoch": 5.742857142857143,
"grad_norm": 3.046875,
"learning_rate": 1.998704243602203e-05,
"loss": 1.2215,
"step": 2814
},
{
"epoch": 5.744897959183674,
"grad_norm": 3.078125,
"learning_rate": 1.9954648526077098e-05,
"loss": 1.2248,
"step": 2815
},
{
"epoch": 5.746938775510204,
"grad_norm": 2.8125,
"learning_rate": 1.9922254616132167e-05,
"loss": 1.2771,
"step": 2816
},
{
"epoch": 5.748979591836735,
"grad_norm": 2.65625,
"learning_rate": 1.988986070618724e-05,
"loss": 1.1868,
"step": 2817
},
{
"epoch": 5.751020408163265,
"grad_norm": 3.203125,
"learning_rate": 1.985746679624231e-05,
"loss": 1.3052,
"step": 2818
},
{
"epoch": 5.753061224489796,
"grad_norm": 3.0,
"learning_rate": 1.9825072886297377e-05,
"loss": 1.1971,
"step": 2819
},
{
"epoch": 5.755102040816326,
"grad_norm": 2.734375,
"learning_rate": 1.9792678976352446e-05,
"loss": 1.141,
"step": 2820
},
{
"epoch": 5.757142857142857,
"grad_norm": 3.140625,
"learning_rate": 1.9760285066407515e-05,
"loss": 1.2447,
"step": 2821
},
{
"epoch": 5.759183673469388,
"grad_norm": 3.421875,
"learning_rate": 1.9727891156462584e-05,
"loss": 1.268,
"step": 2822
},
{
"epoch": 5.761224489795918,
"grad_norm": 3.34375,
"learning_rate": 1.9695497246517657e-05,
"loss": 1.2611,
"step": 2823
},
{
"epoch": 5.763265306122449,
"grad_norm": 3.0625,
"learning_rate": 1.9663103336572726e-05,
"loss": 1.1749,
"step": 2824
},
{
"epoch": 5.76530612244898,
"grad_norm": 2.9375,
"learning_rate": 1.9630709426627795e-05,
"loss": 1.2165,
"step": 2825
},
{
"epoch": 5.7673469387755105,
"grad_norm": 2.984375,
"learning_rate": 1.9598315516682864e-05,
"loss": 1.2059,
"step": 2826
},
{
"epoch": 5.7693877551020405,
"grad_norm": 2.8125,
"learning_rate": 1.9565921606737933e-05,
"loss": 1.2934,
"step": 2827
},
{
"epoch": 5.771428571428571,
"grad_norm": 3.140625,
"learning_rate": 1.9533527696793e-05,
"loss": 1.2186,
"step": 2828
},
{
"epoch": 5.773469387755102,
"grad_norm": 3.0625,
"learning_rate": 1.9501133786848074e-05,
"loss": 1.2513,
"step": 2829
},
{
"epoch": 5.775510204081632,
"grad_norm": 2.9375,
"learning_rate": 1.9468739876903143e-05,
"loss": 1.1902,
"step": 2830
},
{
"epoch": 5.777551020408163,
"grad_norm": 3.34375,
"learning_rate": 1.9436345966958215e-05,
"loss": 1.2883,
"step": 2831
},
{
"epoch": 5.779591836734694,
"grad_norm": 3.0,
"learning_rate": 1.9403952057013284e-05,
"loss": 1.2001,
"step": 2832
},
{
"epoch": 5.781632653061225,
"grad_norm": 3.171875,
"learning_rate": 1.9371558147068353e-05,
"loss": 1.2628,
"step": 2833
},
{
"epoch": 5.783673469387755,
"grad_norm": 3.171875,
"learning_rate": 1.9339164237123422e-05,
"loss": 1.3101,
"step": 2834
},
{
"epoch": 5.785714285714286,
"grad_norm": 3.125,
"learning_rate": 1.930677032717849e-05,
"loss": 1.1929,
"step": 2835
},
{
"epoch": 5.7877551020408164,
"grad_norm": 3.125,
"learning_rate": 1.927437641723356e-05,
"loss": 1.2051,
"step": 2836
},
{
"epoch": 5.789795918367347,
"grad_norm": 3.21875,
"learning_rate": 1.924198250728863e-05,
"loss": 1.2006,
"step": 2837
},
{
"epoch": 5.791836734693877,
"grad_norm": 2.921875,
"learning_rate": 1.92095885973437e-05,
"loss": 1.2658,
"step": 2838
},
{
"epoch": 5.793877551020408,
"grad_norm": 3.265625,
"learning_rate": 1.917719468739877e-05,
"loss": 1.2296,
"step": 2839
},
{
"epoch": 5.795918367346939,
"grad_norm": 2.953125,
"learning_rate": 1.914480077745384e-05,
"loss": 1.3115,
"step": 2840
},
{
"epoch": 5.79795918367347,
"grad_norm": 3.21875,
"learning_rate": 1.9112406867508908e-05,
"loss": 1.2223,
"step": 2841
},
{
"epoch": 5.8,
"grad_norm": 3.03125,
"learning_rate": 1.9080012957563977e-05,
"loss": 1.2849,
"step": 2842
},
{
"epoch": 5.802040816326531,
"grad_norm": 3.171875,
"learning_rate": 1.9047619047619046e-05,
"loss": 1.2273,
"step": 2843
},
{
"epoch": 5.8040816326530615,
"grad_norm": 3.21875,
"learning_rate": 1.901522513767412e-05,
"loss": 1.2796,
"step": 2844
},
{
"epoch": 5.8061224489795915,
"grad_norm": 3.5,
"learning_rate": 1.898283122772919e-05,
"loss": 1.3178,
"step": 2845
},
{
"epoch": 5.808163265306122,
"grad_norm": 3.421875,
"learning_rate": 1.895043731778426e-05,
"loss": 1.2445,
"step": 2846
},
{
"epoch": 5.810204081632653,
"grad_norm": 3.1875,
"learning_rate": 1.891804340783933e-05,
"loss": 1.2467,
"step": 2847
},
{
"epoch": 5.812244897959184,
"grad_norm": 3.46875,
"learning_rate": 1.8885649497894398e-05,
"loss": 1.3362,
"step": 2848
},
{
"epoch": 5.814285714285714,
"grad_norm": 3.109375,
"learning_rate": 1.8853255587949467e-05,
"loss": 1.1668,
"step": 2849
},
{
"epoch": 5.816326530612245,
"grad_norm": 2.90625,
"learning_rate": 1.8820861678004536e-05,
"loss": 1.1725,
"step": 2850
},
{
"epoch": 5.818367346938776,
"grad_norm": 3.328125,
"learning_rate": 1.8788467768059605e-05,
"loss": 1.2395,
"step": 2851
},
{
"epoch": 5.820408163265306,
"grad_norm": 3.171875,
"learning_rate": 1.8756073858114677e-05,
"loss": 1.2228,
"step": 2852
},
{
"epoch": 5.822448979591837,
"grad_norm": 3.203125,
"learning_rate": 1.8723679948169746e-05,
"loss": 1.1749,
"step": 2853
},
{
"epoch": 5.8244897959183675,
"grad_norm": 3.3125,
"learning_rate": 1.8691286038224815e-05,
"loss": 1.3145,
"step": 2854
},
{
"epoch": 5.826530612244898,
"grad_norm": 3.171875,
"learning_rate": 1.8658892128279884e-05,
"loss": 1.208,
"step": 2855
},
{
"epoch": 5.828571428571428,
"grad_norm": 3.203125,
"learning_rate": 1.8626498218334953e-05,
"loss": 1.2749,
"step": 2856
},
{
"epoch": 5.830612244897959,
"grad_norm": 3.265625,
"learning_rate": 1.8594104308390022e-05,
"loss": 1.2417,
"step": 2857
},
{
"epoch": 5.83265306122449,
"grad_norm": 3.0625,
"learning_rate": 1.856171039844509e-05,
"loss": 1.1816,
"step": 2858
},
{
"epoch": 5.83469387755102,
"grad_norm": 3.28125,
"learning_rate": 1.8529316488500163e-05,
"loss": 1.2868,
"step": 2859
},
{
"epoch": 5.836734693877551,
"grad_norm": 3.09375,
"learning_rate": 1.8496922578555232e-05,
"loss": 1.2198,
"step": 2860
},
{
"epoch": 5.838775510204082,
"grad_norm": 3.21875,
"learning_rate": 1.84645286686103e-05,
"loss": 1.1583,
"step": 2861
},
{
"epoch": 5.840816326530613,
"grad_norm": 2.953125,
"learning_rate": 1.8432134758665373e-05,
"loss": 1.2859,
"step": 2862
},
{
"epoch": 5.8428571428571425,
"grad_norm": 2.96875,
"learning_rate": 1.8399740848720442e-05,
"loss": 1.2469,
"step": 2863
},
{
"epoch": 5.844897959183673,
"grad_norm": 2.90625,
"learning_rate": 1.836734693877551e-05,
"loss": 1.1606,
"step": 2864
},
{
"epoch": 5.846938775510204,
"grad_norm": 3.15625,
"learning_rate": 1.833495302883058e-05,
"loss": 1.1958,
"step": 2865
},
{
"epoch": 5.848979591836734,
"grad_norm": 3.0,
"learning_rate": 1.8302559118885653e-05,
"loss": 1.1338,
"step": 2866
},
{
"epoch": 5.851020408163265,
"grad_norm": 2.984375,
"learning_rate": 1.827016520894072e-05,
"loss": 1.1981,
"step": 2867
},
{
"epoch": 5.853061224489796,
"grad_norm": 2.984375,
"learning_rate": 1.823777129899579e-05,
"loss": 1.1742,
"step": 2868
},
{
"epoch": 5.855102040816327,
"grad_norm": 3.203125,
"learning_rate": 1.820537738905086e-05,
"loss": 1.2914,
"step": 2869
},
{
"epoch": 5.857142857142857,
"grad_norm": 3.09375,
"learning_rate": 1.817298347910593e-05,
"loss": 1.2752,
"step": 2870
},
{
"epoch": 5.859183673469388,
"grad_norm": 3.609375,
"learning_rate": 1.8140589569160997e-05,
"loss": 1.3222,
"step": 2871
},
{
"epoch": 5.8612244897959185,
"grad_norm": 3.171875,
"learning_rate": 1.8108195659216066e-05,
"loss": 1.2279,
"step": 2872
},
{
"epoch": 5.863265306122449,
"grad_norm": 3.171875,
"learning_rate": 1.807580174927114e-05,
"loss": 1.3103,
"step": 2873
},
{
"epoch": 5.865306122448979,
"grad_norm": 3.03125,
"learning_rate": 1.8043407839326208e-05,
"loss": 1.2451,
"step": 2874
},
{
"epoch": 5.86734693877551,
"grad_norm": 2.953125,
"learning_rate": 1.8011013929381277e-05,
"loss": 1.218,
"step": 2875
},
{
"epoch": 5.869387755102041,
"grad_norm": 3.09375,
"learning_rate": 1.7978620019436346e-05,
"loss": 1.2622,
"step": 2876
},
{
"epoch": 5.871428571428572,
"grad_norm": 3.171875,
"learning_rate": 1.7946226109491415e-05,
"loss": 1.2416,
"step": 2877
},
{
"epoch": 5.873469387755102,
"grad_norm": 3.0,
"learning_rate": 1.7913832199546487e-05,
"loss": 1.2002,
"step": 2878
},
{
"epoch": 5.875510204081633,
"grad_norm": 3.015625,
"learning_rate": 1.7881438289601556e-05,
"loss": 1.1628,
"step": 2879
},
{
"epoch": 5.877551020408164,
"grad_norm": 3.28125,
"learning_rate": 1.7849044379656625e-05,
"loss": 1.2519,
"step": 2880
},
{
"epoch": 5.8795918367346935,
"grad_norm": 3.0625,
"learning_rate": 1.7816650469711697e-05,
"loss": 1.1872,
"step": 2881
},
{
"epoch": 5.881632653061224,
"grad_norm": 3.03125,
"learning_rate": 1.7784256559766766e-05,
"loss": 1.2487,
"step": 2882
},
{
"epoch": 5.883673469387755,
"grad_norm": 2.9375,
"learning_rate": 1.7751862649821835e-05,
"loss": 1.2244,
"step": 2883
},
{
"epoch": 5.885714285714286,
"grad_norm": 3.265625,
"learning_rate": 1.7719468739876904e-05,
"loss": 1.16,
"step": 2884
},
{
"epoch": 5.887755102040816,
"grad_norm": 3.109375,
"learning_rate": 1.7687074829931973e-05,
"loss": 1.1544,
"step": 2885
},
{
"epoch": 5.889795918367347,
"grad_norm": 3.0,
"learning_rate": 1.7654680919987042e-05,
"loss": 1.1915,
"step": 2886
},
{
"epoch": 5.891836734693878,
"grad_norm": 3.125,
"learning_rate": 1.7622287010042114e-05,
"loss": 1.2063,
"step": 2887
},
{
"epoch": 5.893877551020408,
"grad_norm": 3.109375,
"learning_rate": 1.7589893100097183e-05,
"loss": 1.2283,
"step": 2888
},
{
"epoch": 5.895918367346939,
"grad_norm": 3.015625,
"learning_rate": 1.7557499190152252e-05,
"loss": 1.2957,
"step": 2889
},
{
"epoch": 5.8979591836734695,
"grad_norm": 2.734375,
"learning_rate": 1.752510528020732e-05,
"loss": 1.1526,
"step": 2890
},
{
"epoch": 5.9,
"grad_norm": 3.375,
"learning_rate": 1.749271137026239e-05,
"loss": 1.1852,
"step": 2891
},
{
"epoch": 5.90204081632653,
"grad_norm": 3.015625,
"learning_rate": 1.746031746031746e-05,
"loss": 1.2384,
"step": 2892
},
{
"epoch": 5.904081632653061,
"grad_norm": 3.0625,
"learning_rate": 1.7427923550372528e-05,
"loss": 1.2186,
"step": 2893
},
{
"epoch": 5.906122448979592,
"grad_norm": 3.0625,
"learning_rate": 1.73955296404276e-05,
"loss": 1.1204,
"step": 2894
},
{
"epoch": 5.908163265306122,
"grad_norm": 3.515625,
"learning_rate": 1.7363135730482673e-05,
"loss": 1.2538,
"step": 2895
},
{
"epoch": 5.910204081632653,
"grad_norm": 3.203125,
"learning_rate": 1.7330741820537742e-05,
"loss": 1.2511,
"step": 2896
},
{
"epoch": 5.912244897959184,
"grad_norm": 3.109375,
"learning_rate": 1.729834791059281e-05,
"loss": 1.1657,
"step": 2897
},
{
"epoch": 5.914285714285715,
"grad_norm": 3.21875,
"learning_rate": 1.726595400064788e-05,
"loss": 1.2993,
"step": 2898
},
{
"epoch": 5.916326530612245,
"grad_norm": 3.03125,
"learning_rate": 1.723356009070295e-05,
"loss": 1.2253,
"step": 2899
},
{
"epoch": 5.918367346938775,
"grad_norm": 3.0625,
"learning_rate": 1.7201166180758018e-05,
"loss": 1.2353,
"step": 2900
},
{
"epoch": 5.920408163265306,
"grad_norm": 3.0,
"learning_rate": 1.7168772270813087e-05,
"loss": 1.1807,
"step": 2901
},
{
"epoch": 5.922448979591836,
"grad_norm": 3.171875,
"learning_rate": 1.713637836086816e-05,
"loss": 1.2498,
"step": 2902
},
{
"epoch": 5.924489795918367,
"grad_norm": 2.84375,
"learning_rate": 1.7103984450923228e-05,
"loss": 1.2032,
"step": 2903
},
{
"epoch": 5.926530612244898,
"grad_norm": 3.140625,
"learning_rate": 1.7071590540978297e-05,
"loss": 1.2513,
"step": 2904
},
{
"epoch": 5.928571428571429,
"grad_norm": 3.015625,
"learning_rate": 1.7039196631033366e-05,
"loss": 1.1338,
"step": 2905
},
{
"epoch": 5.930612244897959,
"grad_norm": 3.203125,
"learning_rate": 1.7006802721088435e-05,
"loss": 1.2836,
"step": 2906
},
{
"epoch": 5.93265306122449,
"grad_norm": 3.015625,
"learning_rate": 1.6974408811143504e-05,
"loss": 1.1464,
"step": 2907
},
{
"epoch": 5.9346938775510205,
"grad_norm": 3.1875,
"learning_rate": 1.6942014901198576e-05,
"loss": 1.2553,
"step": 2908
},
{
"epoch": 5.936734693877551,
"grad_norm": 3.328125,
"learning_rate": 1.6909620991253645e-05,
"loss": 1.2389,
"step": 2909
},
{
"epoch": 5.938775510204081,
"grad_norm": 2.9375,
"learning_rate": 1.6877227081308714e-05,
"loss": 1.1838,
"step": 2910
},
{
"epoch": 5.940816326530612,
"grad_norm": 2.875,
"learning_rate": 1.6844833171363786e-05,
"loss": 1.2261,
"step": 2911
},
{
"epoch": 5.942857142857143,
"grad_norm": 3.28125,
"learning_rate": 1.6812439261418855e-05,
"loss": 1.2513,
"step": 2912
},
{
"epoch": 5.944897959183674,
"grad_norm": 3.09375,
"learning_rate": 1.6780045351473924e-05,
"loss": 1.1899,
"step": 2913
},
{
"epoch": 5.946938775510204,
"grad_norm": 3.171875,
"learning_rate": 1.6747651441528993e-05,
"loss": 1.1846,
"step": 2914
},
{
"epoch": 5.948979591836735,
"grad_norm": 3.125,
"learning_rate": 1.6715257531584062e-05,
"loss": 1.2158,
"step": 2915
},
{
"epoch": 5.951020408163266,
"grad_norm": 3.171875,
"learning_rate": 1.6682863621639135e-05,
"loss": 1.1559,
"step": 2916
},
{
"epoch": 5.953061224489796,
"grad_norm": 3.078125,
"learning_rate": 1.6650469711694204e-05,
"loss": 1.2196,
"step": 2917
},
{
"epoch": 5.955102040816326,
"grad_norm": 2.953125,
"learning_rate": 1.6618075801749273e-05,
"loss": 1.1806,
"step": 2918
},
{
"epoch": 5.957142857142857,
"grad_norm": 2.921875,
"learning_rate": 1.658568189180434e-05,
"loss": 1.2208,
"step": 2919
},
{
"epoch": 5.959183673469388,
"grad_norm": 3.203125,
"learning_rate": 1.655328798185941e-05,
"loss": 1.1838,
"step": 2920
},
{
"epoch": 5.961224489795918,
"grad_norm": 2.921875,
"learning_rate": 1.652089407191448e-05,
"loss": 1.2051,
"step": 2921
},
{
"epoch": 5.963265306122449,
"grad_norm": 2.9375,
"learning_rate": 1.648850016196955e-05,
"loss": 1.1878,
"step": 2922
},
{
"epoch": 5.96530612244898,
"grad_norm": 3.0625,
"learning_rate": 1.645610625202462e-05,
"loss": 1.1922,
"step": 2923
},
{
"epoch": 5.96734693877551,
"grad_norm": 3.125,
"learning_rate": 1.642371234207969e-05,
"loss": 1.2626,
"step": 2924
},
{
"epoch": 5.969387755102041,
"grad_norm": 3.03125,
"learning_rate": 1.639131843213476e-05,
"loss": 1.1681,
"step": 2925
},
{
"epoch": 5.9714285714285715,
"grad_norm": 3.0625,
"learning_rate": 1.6358924522189828e-05,
"loss": 1.1942,
"step": 2926
},
{
"epoch": 5.973469387755102,
"grad_norm": 2.9375,
"learning_rate": 1.6326530612244897e-05,
"loss": 1.154,
"step": 2927
},
{
"epoch": 5.975510204081632,
"grad_norm": 3.203125,
"learning_rate": 1.629413670229997e-05,
"loss": 1.2901,
"step": 2928
},
{
"epoch": 5.977551020408163,
"grad_norm": 3.03125,
"learning_rate": 1.6261742792355038e-05,
"loss": 1.1879,
"step": 2929
},
{
"epoch": 5.979591836734694,
"grad_norm": 3.03125,
"learning_rate": 1.622934888241011e-05,
"loss": 1.1324,
"step": 2930
},
{
"epoch": 5.981632653061224,
"grad_norm": 3.046875,
"learning_rate": 1.619695497246518e-05,
"loss": 1.1803,
"step": 2931
},
{
"epoch": 5.983673469387755,
"grad_norm": 3.1875,
"learning_rate": 1.6164561062520248e-05,
"loss": 1.2525,
"step": 2932
},
{
"epoch": 5.985714285714286,
"grad_norm": 3.25,
"learning_rate": 1.6132167152575317e-05,
"loss": 1.2814,
"step": 2933
},
{
"epoch": 5.987755102040817,
"grad_norm": 2.796875,
"learning_rate": 1.6099773242630386e-05,
"loss": 1.2598,
"step": 2934
},
{
"epoch": 5.989795918367347,
"grad_norm": 2.9375,
"learning_rate": 1.6067379332685455e-05,
"loss": 1.228,
"step": 2935
},
{
"epoch": 5.9918367346938775,
"grad_norm": 3.265625,
"learning_rate": 1.6034985422740524e-05,
"loss": 1.2529,
"step": 2936
},
{
"epoch": 5.993877551020408,
"grad_norm": 2.96875,
"learning_rate": 1.6002591512795596e-05,
"loss": 1.1624,
"step": 2937
},
{
"epoch": 5.995918367346938,
"grad_norm": 3.046875,
"learning_rate": 1.5970197602850665e-05,
"loss": 1.2116,
"step": 2938
},
{
"epoch": 5.997959183673469,
"grad_norm": 3.078125,
"learning_rate": 1.5937803692905734e-05,
"loss": 1.1998,
"step": 2939
},
{
"epoch": 6.0,
"grad_norm": 3.171875,
"learning_rate": 1.5905409782960803e-05,
"loss": 1.3831,
"step": 2940
},
{
"epoch": 6.002040816326531,
"grad_norm": 3.3125,
"learning_rate": 1.5873015873015872e-05,
"loss": 0.761,
"step": 2941
},
{
"epoch": 6.004081632653061,
"grad_norm": 3.625,
"learning_rate": 1.584062196307094e-05,
"loss": 0.8392,
"step": 2942
},
{
"epoch": 6.006122448979592,
"grad_norm": 2.828125,
"learning_rate": 1.580822805312601e-05,
"loss": 0.8606,
"step": 2943
},
{
"epoch": 6.0081632653061225,
"grad_norm": 2.625,
"learning_rate": 1.5775834143181083e-05,
"loss": 0.8263,
"step": 2944
},
{
"epoch": 6.010204081632653,
"grad_norm": 2.8125,
"learning_rate": 1.5743440233236155e-05,
"loss": 0.8967,
"step": 2945
},
{
"epoch": 6.012244897959183,
"grad_norm": 2.8125,
"learning_rate": 1.5711046323291224e-05,
"loss": 0.8156,
"step": 2946
},
{
"epoch": 6.014285714285714,
"grad_norm": 3.15625,
"learning_rate": 1.5678652413346293e-05,
"loss": 0.822,
"step": 2947
},
{
"epoch": 6.016326530612245,
"grad_norm": 3.21875,
"learning_rate": 1.5646258503401362e-05,
"loss": 0.7984,
"step": 2948
},
{
"epoch": 6.018367346938776,
"grad_norm": 3.03125,
"learning_rate": 1.561386459345643e-05,
"loss": 0.8284,
"step": 2949
},
{
"epoch": 6.020408163265306,
"grad_norm": 3.171875,
"learning_rate": 1.55814706835115e-05,
"loss": 0.8283,
"step": 2950
},
{
"epoch": 6.022448979591837,
"grad_norm": 3.25,
"learning_rate": 1.5549076773566572e-05,
"loss": 0.8782,
"step": 2951
},
{
"epoch": 6.024489795918368,
"grad_norm": 2.703125,
"learning_rate": 1.551668286362164e-05,
"loss": 0.7678,
"step": 2952
},
{
"epoch": 6.026530612244898,
"grad_norm": 3.109375,
"learning_rate": 1.548428895367671e-05,
"loss": 0.8459,
"step": 2953
},
{
"epoch": 6.0285714285714285,
"grad_norm": 2.734375,
"learning_rate": 1.545189504373178e-05,
"loss": 0.7841,
"step": 2954
},
{
"epoch": 6.030612244897959,
"grad_norm": 2.71875,
"learning_rate": 1.5419501133786848e-05,
"loss": 0.8327,
"step": 2955
},
{
"epoch": 6.03265306122449,
"grad_norm": 2.453125,
"learning_rate": 1.5387107223841917e-05,
"loss": 0.7798,
"step": 2956
},
{
"epoch": 6.03469387755102,
"grad_norm": 2.546875,
"learning_rate": 1.5354713313896986e-05,
"loss": 0.8799,
"step": 2957
},
{
"epoch": 6.036734693877551,
"grad_norm": 2.734375,
"learning_rate": 1.5322319403952058e-05,
"loss": 0.8675,
"step": 2958
},
{
"epoch": 6.038775510204082,
"grad_norm": 2.5625,
"learning_rate": 1.5289925494007127e-05,
"loss": 0.8609,
"step": 2959
},
{
"epoch": 6.040816326530612,
"grad_norm": 2.84375,
"learning_rate": 1.5257531584062196e-05,
"loss": 0.852,
"step": 2960
},
{
"epoch": 6.042857142857143,
"grad_norm": 2.796875,
"learning_rate": 1.5225137674117269e-05,
"loss": 0.8492,
"step": 2961
},
{
"epoch": 6.044897959183674,
"grad_norm": 2.390625,
"learning_rate": 1.5192743764172338e-05,
"loss": 0.7995,
"step": 2962
},
{
"epoch": 6.046938775510204,
"grad_norm": 2.5,
"learning_rate": 1.5160349854227406e-05,
"loss": 0.8649,
"step": 2963
},
{
"epoch": 6.048979591836734,
"grad_norm": 2.578125,
"learning_rate": 1.5127955944282477e-05,
"loss": 0.8594,
"step": 2964
},
{
"epoch": 6.051020408163265,
"grad_norm": 2.671875,
"learning_rate": 1.5095562034337546e-05,
"loss": 0.8616,
"step": 2965
},
{
"epoch": 6.053061224489796,
"grad_norm": 2.453125,
"learning_rate": 1.5063168124392615e-05,
"loss": 0.8027,
"step": 2966
},
{
"epoch": 6.055102040816327,
"grad_norm": 2.453125,
"learning_rate": 1.5030774214447684e-05,
"loss": 0.848,
"step": 2967
},
{
"epoch": 6.057142857142857,
"grad_norm": 2.578125,
"learning_rate": 1.4998380304502755e-05,
"loss": 0.8681,
"step": 2968
},
{
"epoch": 6.059183673469388,
"grad_norm": 2.390625,
"learning_rate": 1.4965986394557824e-05,
"loss": 0.7891,
"step": 2969
},
{
"epoch": 6.061224489795919,
"grad_norm": 2.40625,
"learning_rate": 1.4933592484612893e-05,
"loss": 0.8457,
"step": 2970
},
{
"epoch": 6.063265306122449,
"grad_norm": 2.546875,
"learning_rate": 1.4901198574667963e-05,
"loss": 0.848,
"step": 2971
},
{
"epoch": 6.0653061224489795,
"grad_norm": 2.15625,
"learning_rate": 1.4868804664723032e-05,
"loss": 0.7444,
"step": 2972
},
{
"epoch": 6.06734693877551,
"grad_norm": 2.46875,
"learning_rate": 1.4836410754778101e-05,
"loss": 0.805,
"step": 2973
},
{
"epoch": 6.069387755102041,
"grad_norm": 2.390625,
"learning_rate": 1.4804016844833172e-05,
"loss": 0.7989,
"step": 2974
},
{
"epoch": 6.071428571428571,
"grad_norm": 2.359375,
"learning_rate": 1.477162293488824e-05,
"loss": 0.8871,
"step": 2975
},
{
"epoch": 6.073469387755102,
"grad_norm": 2.375,
"learning_rate": 1.473922902494331e-05,
"loss": 0.8073,
"step": 2976
},
{
"epoch": 6.075510204081633,
"grad_norm": 2.34375,
"learning_rate": 1.470683511499838e-05,
"loss": 0.8147,
"step": 2977
},
{
"epoch": 6.077551020408163,
"grad_norm": 2.46875,
"learning_rate": 1.4674441205053451e-05,
"loss": 0.8723,
"step": 2978
},
{
"epoch": 6.079591836734694,
"grad_norm": 2.5,
"learning_rate": 1.4642047295108522e-05,
"loss": 0.782,
"step": 2979
},
{
"epoch": 6.081632653061225,
"grad_norm": 2.34375,
"learning_rate": 1.460965338516359e-05,
"loss": 0.7644,
"step": 2980
},
{
"epoch": 6.083673469387755,
"grad_norm": 2.40625,
"learning_rate": 1.457725947521866e-05,
"loss": 0.7837,
"step": 2981
},
{
"epoch": 6.085714285714285,
"grad_norm": 2.65625,
"learning_rate": 1.454486556527373e-05,
"loss": 0.9348,
"step": 2982
},
{
"epoch": 6.087755102040816,
"grad_norm": 2.359375,
"learning_rate": 1.45124716553288e-05,
"loss": 0.8375,
"step": 2983
},
{
"epoch": 6.089795918367347,
"grad_norm": 2.390625,
"learning_rate": 1.4480077745383868e-05,
"loss": 0.836,
"step": 2984
},
{
"epoch": 6.091836734693878,
"grad_norm": 2.578125,
"learning_rate": 1.4447683835438939e-05,
"loss": 0.8358,
"step": 2985
},
{
"epoch": 6.093877551020408,
"grad_norm": 2.546875,
"learning_rate": 1.4415289925494008e-05,
"loss": 0.8669,
"step": 2986
},
{
"epoch": 6.095918367346939,
"grad_norm": 2.421875,
"learning_rate": 1.4382896015549077e-05,
"loss": 0.8169,
"step": 2987
},
{
"epoch": 6.09795918367347,
"grad_norm": 2.390625,
"learning_rate": 1.4350502105604146e-05,
"loss": 0.7987,
"step": 2988
},
{
"epoch": 6.1,
"grad_norm": 2.53125,
"learning_rate": 1.4318108195659216e-05,
"loss": 0.8178,
"step": 2989
},
{
"epoch": 6.1020408163265305,
"grad_norm": 2.359375,
"learning_rate": 1.4285714285714285e-05,
"loss": 0.8416,
"step": 2990
},
{
"epoch": 6.104081632653061,
"grad_norm": 2.25,
"learning_rate": 1.4253320375769354e-05,
"loss": 0.7499,
"step": 2991
},
{
"epoch": 6.106122448979592,
"grad_norm": 2.5,
"learning_rate": 1.4220926465824425e-05,
"loss": 0.7517,
"step": 2992
},
{
"epoch": 6.108163265306122,
"grad_norm": 2.5625,
"learning_rate": 1.4188532555879494e-05,
"loss": 0.8423,
"step": 2993
},
{
"epoch": 6.110204081632653,
"grad_norm": 2.359375,
"learning_rate": 1.4156138645934566e-05,
"loss": 0.7365,
"step": 2994
},
{
"epoch": 6.112244897959184,
"grad_norm": 2.34375,
"learning_rate": 1.4123744735989635e-05,
"loss": 0.7947,
"step": 2995
},
{
"epoch": 6.114285714285714,
"grad_norm": 2.46875,
"learning_rate": 1.4091350826044706e-05,
"loss": 0.8661,
"step": 2996
},
{
"epoch": 6.116326530612245,
"grad_norm": 2.71875,
"learning_rate": 1.4058956916099775e-05,
"loss": 0.8921,
"step": 2997
},
{
"epoch": 6.118367346938776,
"grad_norm": 2.46875,
"learning_rate": 1.4026563006154844e-05,
"loss": 0.8112,
"step": 2998
},
{
"epoch": 6.1204081632653065,
"grad_norm": 2.53125,
"learning_rate": 1.3994169096209913e-05,
"loss": 0.798,
"step": 2999
},
{
"epoch": 6.122448979591836,
"grad_norm": 2.671875,
"learning_rate": 1.3961775186264984e-05,
"loss": 0.8557,
"step": 3000
},
{
"epoch": 6.122448979591836,
"eval_loss": 4.991698265075684,
"eval_runtime": 5.364,
"eval_samples_per_second": 29.828,
"eval_steps_per_second": 7.457,
"step": 3000
},
{
"epoch": 6.124489795918367,
"grad_norm": 2.46875,
"learning_rate": 1.3929381276320053e-05,
"loss": 0.8544,
"step": 3001
},
{
"epoch": 6.126530612244898,
"grad_norm": 2.59375,
"learning_rate": 1.3896987366375121e-05,
"loss": 0.8821,
"step": 3002
},
{
"epoch": 6.128571428571428,
"grad_norm": 2.3125,
"learning_rate": 1.3864593456430192e-05,
"loss": 0.8304,
"step": 3003
},
{
"epoch": 6.130612244897959,
"grad_norm": 2.5,
"learning_rate": 1.3832199546485261e-05,
"loss": 0.7474,
"step": 3004
},
{
"epoch": 6.13265306122449,
"grad_norm": 2.84375,
"learning_rate": 1.379980563654033e-05,
"loss": 0.8452,
"step": 3005
},
{
"epoch": 6.134693877551021,
"grad_norm": 2.34375,
"learning_rate": 1.37674117265954e-05,
"loss": 0.7788,
"step": 3006
},
{
"epoch": 6.136734693877551,
"grad_norm": 2.5625,
"learning_rate": 1.373501781665047e-05,
"loss": 0.8852,
"step": 3007
},
{
"epoch": 6.1387755102040815,
"grad_norm": 2.5,
"learning_rate": 1.3702623906705539e-05,
"loss": 0.8137,
"step": 3008
},
{
"epoch": 6.140816326530612,
"grad_norm": 2.515625,
"learning_rate": 1.367022999676061e-05,
"loss": 0.8416,
"step": 3009
},
{
"epoch": 6.142857142857143,
"grad_norm": 2.46875,
"learning_rate": 1.3637836086815678e-05,
"loss": 0.7968,
"step": 3010
},
{
"epoch": 6.144897959183673,
"grad_norm": 2.359375,
"learning_rate": 1.360544217687075e-05,
"loss": 0.843,
"step": 3011
},
{
"epoch": 6.146938775510204,
"grad_norm": 2.40625,
"learning_rate": 1.357304826692582e-05,
"loss": 0.8465,
"step": 3012
},
{
"epoch": 6.148979591836735,
"grad_norm": 2.40625,
"learning_rate": 1.3540654356980889e-05,
"loss": 0.7731,
"step": 3013
},
{
"epoch": 6.151020408163265,
"grad_norm": 2.46875,
"learning_rate": 1.350826044703596e-05,
"loss": 0.813,
"step": 3014
},
{
"epoch": 6.153061224489796,
"grad_norm": 2.59375,
"learning_rate": 1.3475866537091028e-05,
"loss": 0.7976,
"step": 3015
},
{
"epoch": 6.155102040816327,
"grad_norm": 2.34375,
"learning_rate": 1.3443472627146097e-05,
"loss": 0.8235,
"step": 3016
},
{
"epoch": 6.1571428571428575,
"grad_norm": 2.3125,
"learning_rate": 1.3411078717201168e-05,
"loss": 0.8262,
"step": 3017
},
{
"epoch": 6.159183673469387,
"grad_norm": 2.53125,
"learning_rate": 1.3378684807256237e-05,
"loss": 0.8519,
"step": 3018
},
{
"epoch": 6.161224489795918,
"grad_norm": 2.515625,
"learning_rate": 1.3346290897311306e-05,
"loss": 0.8816,
"step": 3019
},
{
"epoch": 6.163265306122449,
"grad_norm": 2.390625,
"learning_rate": 1.3313896987366375e-05,
"loss": 0.8324,
"step": 3020
},
{
"epoch": 6.16530612244898,
"grad_norm": 2.703125,
"learning_rate": 1.3281503077421445e-05,
"loss": 0.7992,
"step": 3021
},
{
"epoch": 6.16734693877551,
"grad_norm": 2.4375,
"learning_rate": 1.3249109167476514e-05,
"loss": 0.7889,
"step": 3022
},
{
"epoch": 6.169387755102041,
"grad_norm": 2.375,
"learning_rate": 1.3216715257531583e-05,
"loss": 0.7467,
"step": 3023
},
{
"epoch": 6.171428571428572,
"grad_norm": 2.4375,
"learning_rate": 1.3184321347586654e-05,
"loss": 0.8538,
"step": 3024
},
{
"epoch": 6.173469387755102,
"grad_norm": 2.34375,
"learning_rate": 1.3151927437641723e-05,
"loss": 0.8073,
"step": 3025
},
{
"epoch": 6.1755102040816325,
"grad_norm": 2.578125,
"learning_rate": 1.3119533527696792e-05,
"loss": 0.8491,
"step": 3026
},
{
"epoch": 6.177551020408163,
"grad_norm": 2.296875,
"learning_rate": 1.3087139617751864e-05,
"loss": 0.816,
"step": 3027
},
{
"epoch": 6.179591836734694,
"grad_norm": 2.625,
"learning_rate": 1.3054745707806935e-05,
"loss": 0.7944,
"step": 3028
},
{
"epoch": 6.181632653061224,
"grad_norm": 2.546875,
"learning_rate": 1.3022351797862004e-05,
"loss": 0.8029,
"step": 3029
},
{
"epoch": 6.183673469387755,
"grad_norm": 2.40625,
"learning_rate": 1.2989957887917073e-05,
"loss": 0.7615,
"step": 3030
},
{
"epoch": 6.185714285714286,
"grad_norm": 2.640625,
"learning_rate": 1.2957563977972142e-05,
"loss": 0.8891,
"step": 3031
},
{
"epoch": 6.187755102040816,
"grad_norm": 2.84375,
"learning_rate": 1.2925170068027212e-05,
"loss": 0.9069,
"step": 3032
},
{
"epoch": 6.189795918367347,
"grad_norm": 2.578125,
"learning_rate": 1.2892776158082281e-05,
"loss": 0.8789,
"step": 3033
},
{
"epoch": 6.191836734693878,
"grad_norm": 2.484375,
"learning_rate": 1.286038224813735e-05,
"loss": 0.8501,
"step": 3034
},
{
"epoch": 6.1938775510204085,
"grad_norm": 2.46875,
"learning_rate": 1.2827988338192421e-05,
"loss": 0.82,
"step": 3035
},
{
"epoch": 6.1959183673469385,
"grad_norm": 2.296875,
"learning_rate": 1.279559442824749e-05,
"loss": 0.7979,
"step": 3036
},
{
"epoch": 6.197959183673469,
"grad_norm": 2.46875,
"learning_rate": 1.2763200518302559e-05,
"loss": 0.7961,
"step": 3037
},
{
"epoch": 6.2,
"grad_norm": 2.359375,
"learning_rate": 1.273080660835763e-05,
"loss": 0.7912,
"step": 3038
},
{
"epoch": 6.202040816326531,
"grad_norm": 2.3125,
"learning_rate": 1.2698412698412699e-05,
"loss": 0.7595,
"step": 3039
},
{
"epoch": 6.204081632653061,
"grad_norm": 2.390625,
"learning_rate": 1.2666018788467768e-05,
"loss": 0.8133,
"step": 3040
},
{
"epoch": 6.206122448979592,
"grad_norm": 2.53125,
"learning_rate": 1.2633624878522836e-05,
"loss": 0.8362,
"step": 3041
},
{
"epoch": 6.208163265306123,
"grad_norm": 2.28125,
"learning_rate": 1.2601230968577907e-05,
"loss": 0.767,
"step": 3042
},
{
"epoch": 6.210204081632653,
"grad_norm": 2.65625,
"learning_rate": 1.2568837058632976e-05,
"loss": 0.8336,
"step": 3043
},
{
"epoch": 6.2122448979591836,
"grad_norm": 2.25,
"learning_rate": 1.2536443148688048e-05,
"loss": 0.821,
"step": 3044
},
{
"epoch": 6.214285714285714,
"grad_norm": 2.4375,
"learning_rate": 1.2504049238743117e-05,
"loss": 0.7919,
"step": 3045
},
{
"epoch": 6.216326530612245,
"grad_norm": 2.421875,
"learning_rate": 1.2471655328798186e-05,
"loss": 0.8154,
"step": 3046
},
{
"epoch": 6.218367346938775,
"grad_norm": 2.484375,
"learning_rate": 1.2439261418853255e-05,
"loss": 0.7772,
"step": 3047
},
{
"epoch": 6.220408163265306,
"grad_norm": 2.46875,
"learning_rate": 1.2406867508908326e-05,
"loss": 0.852,
"step": 3048
},
{
"epoch": 6.222448979591837,
"grad_norm": 2.359375,
"learning_rate": 1.2374473598963397e-05,
"loss": 0.7787,
"step": 3049
},
{
"epoch": 6.224489795918367,
"grad_norm": 2.546875,
"learning_rate": 1.2342079689018466e-05,
"loss": 0.7517,
"step": 3050
},
{
"epoch": 6.226530612244898,
"grad_norm": 2.5625,
"learning_rate": 1.2309685779073535e-05,
"loss": 0.8715,
"step": 3051
},
{
"epoch": 6.228571428571429,
"grad_norm": 2.453125,
"learning_rate": 1.2277291869128604e-05,
"loss": 0.8348,
"step": 3052
},
{
"epoch": 6.2306122448979595,
"grad_norm": 2.34375,
"learning_rate": 1.2244897959183674e-05,
"loss": 0.8242,
"step": 3053
},
{
"epoch": 6.2326530612244895,
"grad_norm": 2.390625,
"learning_rate": 1.2212504049238743e-05,
"loss": 0.7916,
"step": 3054
},
{
"epoch": 6.23469387755102,
"grad_norm": 2.3125,
"learning_rate": 1.2180110139293812e-05,
"loss": 0.7629,
"step": 3055
},
{
"epoch": 6.236734693877551,
"grad_norm": 2.546875,
"learning_rate": 1.2147716229348883e-05,
"loss": 0.8209,
"step": 3056
},
{
"epoch": 6.238775510204082,
"grad_norm": 2.46875,
"learning_rate": 1.2115322319403953e-05,
"loss": 0.8332,
"step": 3057
},
{
"epoch": 6.240816326530612,
"grad_norm": 2.390625,
"learning_rate": 1.2082928409459022e-05,
"loss": 0.7971,
"step": 3058
},
{
"epoch": 6.242857142857143,
"grad_norm": 2.359375,
"learning_rate": 1.2050534499514091e-05,
"loss": 0.7935,
"step": 3059
},
{
"epoch": 6.244897959183674,
"grad_norm": 2.390625,
"learning_rate": 1.2018140589569162e-05,
"loss": 0.8895,
"step": 3060
},
{
"epoch": 6.246938775510204,
"grad_norm": 2.40625,
"learning_rate": 1.1985746679624231e-05,
"loss": 0.882,
"step": 3061
},
{
"epoch": 6.248979591836735,
"grad_norm": 2.671875,
"learning_rate": 1.19533527696793e-05,
"loss": 0.8206,
"step": 3062
},
{
"epoch": 6.251020408163265,
"grad_norm": 2.40625,
"learning_rate": 1.192095885973437e-05,
"loss": 0.8074,
"step": 3063
},
{
"epoch": 6.253061224489796,
"grad_norm": 2.40625,
"learning_rate": 1.1888564949789441e-05,
"loss": 0.7785,
"step": 3064
},
{
"epoch": 6.255102040816326,
"grad_norm": 2.375,
"learning_rate": 1.185617103984451e-05,
"loss": 0.7863,
"step": 3065
},
{
"epoch": 6.257142857142857,
"grad_norm": 2.3125,
"learning_rate": 1.182377712989958e-05,
"loss": 0.7716,
"step": 3066
},
{
"epoch": 6.259183673469388,
"grad_norm": 2.4375,
"learning_rate": 1.179138321995465e-05,
"loss": 0.7988,
"step": 3067
},
{
"epoch": 6.261224489795918,
"grad_norm": 2.484375,
"learning_rate": 1.1758989310009719e-05,
"loss": 0.8253,
"step": 3068
},
{
"epoch": 6.263265306122449,
"grad_norm": 2.5625,
"learning_rate": 1.1726595400064788e-05,
"loss": 0.7901,
"step": 3069
},
{
"epoch": 6.26530612244898,
"grad_norm": 2.53125,
"learning_rate": 1.1694201490119858e-05,
"loss": 0.8628,
"step": 3070
},
{
"epoch": 6.2673469387755105,
"grad_norm": 2.515625,
"learning_rate": 1.1661807580174927e-05,
"loss": 0.8475,
"step": 3071
},
{
"epoch": 6.2693877551020405,
"grad_norm": 2.609375,
"learning_rate": 1.1629413670229998e-05,
"loss": 0.7617,
"step": 3072
},
{
"epoch": 6.271428571428571,
"grad_norm": 2.25,
"learning_rate": 1.1597019760285067e-05,
"loss": 0.7973,
"step": 3073
},
{
"epoch": 6.273469387755102,
"grad_norm": 2.640625,
"learning_rate": 1.1564625850340138e-05,
"loss": 0.7726,
"step": 3074
},
{
"epoch": 6.275510204081632,
"grad_norm": 2.53125,
"learning_rate": 1.1532231940395207e-05,
"loss": 0.7822,
"step": 3075
},
{
"epoch": 6.277551020408163,
"grad_norm": 2.5625,
"learning_rate": 1.1499838030450276e-05,
"loss": 0.9039,
"step": 3076
},
{
"epoch": 6.279591836734694,
"grad_norm": 2.546875,
"learning_rate": 1.1467444120505345e-05,
"loss": 0.8531,
"step": 3077
},
{
"epoch": 6.281632653061225,
"grad_norm": 2.8125,
"learning_rate": 1.1435050210560415e-05,
"loss": 0.894,
"step": 3078
},
{
"epoch": 6.283673469387755,
"grad_norm": 2.609375,
"learning_rate": 1.1402656300615484e-05,
"loss": 0.8102,
"step": 3079
},
{
"epoch": 6.285714285714286,
"grad_norm": 2.453125,
"learning_rate": 1.1370262390670553e-05,
"loss": 0.8188,
"step": 3080
},
{
"epoch": 6.2877551020408164,
"grad_norm": 2.5,
"learning_rate": 1.1337868480725626e-05,
"loss": 0.8201,
"step": 3081
},
{
"epoch": 6.289795918367347,
"grad_norm": 2.53125,
"learning_rate": 1.1305474570780694e-05,
"loss": 0.8298,
"step": 3082
},
{
"epoch": 6.291836734693877,
"grad_norm": 2.53125,
"learning_rate": 1.1273080660835763e-05,
"loss": 0.7766,
"step": 3083
},
{
"epoch": 6.293877551020408,
"grad_norm": 2.5,
"learning_rate": 1.1240686750890832e-05,
"loss": 0.8098,
"step": 3084
},
{
"epoch": 6.295918367346939,
"grad_norm": 2.53125,
"learning_rate": 1.1208292840945903e-05,
"loss": 0.7918,
"step": 3085
},
{
"epoch": 6.29795918367347,
"grad_norm": 2.46875,
"learning_rate": 1.1175898931000972e-05,
"loss": 0.8648,
"step": 3086
},
{
"epoch": 6.3,
"grad_norm": 2.453125,
"learning_rate": 1.1143505021056041e-05,
"loss": 0.8067,
"step": 3087
},
{
"epoch": 6.302040816326531,
"grad_norm": 2.484375,
"learning_rate": 1.1111111111111112e-05,
"loss": 0.8346,
"step": 3088
},
{
"epoch": 6.3040816326530615,
"grad_norm": 2.5,
"learning_rate": 1.1078717201166182e-05,
"loss": 0.7401,
"step": 3089
},
{
"epoch": 6.3061224489795915,
"grad_norm": 2.640625,
"learning_rate": 1.1046323291221251e-05,
"loss": 0.8474,
"step": 3090
},
{
"epoch": 6.308163265306122,
"grad_norm": 2.5,
"learning_rate": 1.101392938127632e-05,
"loss": 0.8069,
"step": 3091
},
{
"epoch": 6.310204081632653,
"grad_norm": 2.5625,
"learning_rate": 1.0981535471331391e-05,
"loss": 0.8522,
"step": 3092
},
{
"epoch": 6.312244897959184,
"grad_norm": 2.515625,
"learning_rate": 1.094914156138646e-05,
"loss": 0.7717,
"step": 3093
},
{
"epoch": 6.314285714285714,
"grad_norm": 2.421875,
"learning_rate": 1.0916747651441529e-05,
"loss": 0.8352,
"step": 3094
},
{
"epoch": 6.316326530612245,
"grad_norm": 2.34375,
"learning_rate": 1.08843537414966e-05,
"loss": 0.7743,
"step": 3095
},
{
"epoch": 6.318367346938776,
"grad_norm": 2.75,
"learning_rate": 1.0851959831551668e-05,
"loss": 0.857,
"step": 3096
},
{
"epoch": 6.320408163265306,
"grad_norm": 2.625,
"learning_rate": 1.0819565921606739e-05,
"loss": 0.8793,
"step": 3097
},
{
"epoch": 6.322448979591837,
"grad_norm": 2.40625,
"learning_rate": 1.0787172011661808e-05,
"loss": 0.7947,
"step": 3098
},
{
"epoch": 6.3244897959183675,
"grad_norm": 2.3125,
"learning_rate": 1.0754778101716879e-05,
"loss": 0.7887,
"step": 3099
},
{
"epoch": 6.326530612244898,
"grad_norm": 2.421875,
"learning_rate": 1.0722384191771948e-05,
"loss": 0.8215,
"step": 3100
},
{
"epoch": 6.328571428571428,
"grad_norm": 2.546875,
"learning_rate": 1.0689990281827017e-05,
"loss": 0.7912,
"step": 3101
},
{
"epoch": 6.330612244897959,
"grad_norm": 2.609375,
"learning_rate": 1.0657596371882087e-05,
"loss": 0.8136,
"step": 3102
},
{
"epoch": 6.33265306122449,
"grad_norm": 2.375,
"learning_rate": 1.0625202461937156e-05,
"loss": 0.8157,
"step": 3103
},
{
"epoch": 6.33469387755102,
"grad_norm": 2.328125,
"learning_rate": 1.0592808551992225e-05,
"loss": 0.7969,
"step": 3104
},
{
"epoch": 6.336734693877551,
"grad_norm": 2.265625,
"learning_rate": 1.0560414642047296e-05,
"loss": 0.7621,
"step": 3105
},
{
"epoch": 6.338775510204082,
"grad_norm": 2.390625,
"learning_rate": 1.0528020732102367e-05,
"loss": 0.8642,
"step": 3106
},
{
"epoch": 6.340816326530613,
"grad_norm": 2.53125,
"learning_rate": 1.0495626822157436e-05,
"loss": 0.8744,
"step": 3107
},
{
"epoch": 6.3428571428571425,
"grad_norm": 2.703125,
"learning_rate": 1.0463232912212504e-05,
"loss": 0.8444,
"step": 3108
},
{
"epoch": 6.344897959183673,
"grad_norm": 2.28125,
"learning_rate": 1.0430839002267573e-05,
"loss": 0.791,
"step": 3109
},
{
"epoch": 6.346938775510204,
"grad_norm": 2.40625,
"learning_rate": 1.0398445092322644e-05,
"loss": 0.8152,
"step": 3110
},
{
"epoch": 6.348979591836735,
"grad_norm": 2.40625,
"learning_rate": 1.0366051182377713e-05,
"loss": 0.8108,
"step": 3111
},
{
"epoch": 6.351020408163265,
"grad_norm": 2.65625,
"learning_rate": 1.0333657272432782e-05,
"loss": 0.8797,
"step": 3112
},
{
"epoch": 6.353061224489796,
"grad_norm": 2.609375,
"learning_rate": 1.0301263362487853e-05,
"loss": 0.803,
"step": 3113
},
{
"epoch": 6.355102040816327,
"grad_norm": 2.5,
"learning_rate": 1.0268869452542923e-05,
"loss": 0.8266,
"step": 3114
},
{
"epoch": 6.357142857142857,
"grad_norm": 2.921875,
"learning_rate": 1.0236475542597992e-05,
"loss": 0.8791,
"step": 3115
},
{
"epoch": 6.359183673469388,
"grad_norm": 2.5625,
"learning_rate": 1.0204081632653061e-05,
"loss": 0.7947,
"step": 3116
},
{
"epoch": 6.3612244897959185,
"grad_norm": 2.53125,
"learning_rate": 1.0171687722708132e-05,
"loss": 0.8718,
"step": 3117
},
{
"epoch": 6.363265306122449,
"grad_norm": 2.53125,
"learning_rate": 1.0139293812763201e-05,
"loss": 0.7808,
"step": 3118
},
{
"epoch": 6.365306122448979,
"grad_norm": 2.296875,
"learning_rate": 1.010689990281827e-05,
"loss": 0.8579,
"step": 3119
},
{
"epoch": 6.36734693877551,
"grad_norm": 2.25,
"learning_rate": 1.007450599287334e-05,
"loss": 0.7282,
"step": 3120
},
{
"epoch": 6.369387755102041,
"grad_norm": 2.765625,
"learning_rate": 1.004211208292841e-05,
"loss": 0.8556,
"step": 3121
},
{
"epoch": 6.371428571428572,
"grad_norm": 2.65625,
"learning_rate": 1.000971817298348e-05,
"loss": 0.8057,
"step": 3122
},
{
"epoch": 6.373469387755102,
"grad_norm": 2.578125,
"learning_rate": 9.977324263038549e-06,
"loss": 0.798,
"step": 3123
},
{
"epoch": 6.375510204081633,
"grad_norm": 2.53125,
"learning_rate": 9.94493035309362e-06,
"loss": 0.8284,
"step": 3124
},
{
"epoch": 6.377551020408164,
"grad_norm": 2.484375,
"learning_rate": 9.912536443148689e-06,
"loss": 0.8091,
"step": 3125
},
{
"epoch": 6.3795918367346935,
"grad_norm": 2.515625,
"learning_rate": 9.880142533203758e-06,
"loss": 0.834,
"step": 3126
},
{
"epoch": 6.381632653061224,
"grad_norm": 2.296875,
"learning_rate": 9.847748623258828e-06,
"loss": 0.8147,
"step": 3127
},
{
"epoch": 6.383673469387755,
"grad_norm": 2.234375,
"learning_rate": 9.815354713313897e-06,
"loss": 0.7288,
"step": 3128
},
{
"epoch": 6.385714285714286,
"grad_norm": 2.421875,
"learning_rate": 9.782960803368966e-06,
"loss": 0.8257,
"step": 3129
},
{
"epoch": 6.387755102040816,
"grad_norm": 2.640625,
"learning_rate": 9.750566893424037e-06,
"loss": 0.8032,
"step": 3130
},
{
"epoch": 6.389795918367347,
"grad_norm": 2.296875,
"learning_rate": 9.718172983479108e-06,
"loss": 0.7995,
"step": 3131
},
{
"epoch": 6.391836734693878,
"grad_norm": 2.4375,
"learning_rate": 9.685779073534177e-06,
"loss": 0.7743,
"step": 3132
},
{
"epoch": 6.393877551020408,
"grad_norm": 2.59375,
"learning_rate": 9.653385163589246e-06,
"loss": 0.8109,
"step": 3133
},
{
"epoch": 6.395918367346939,
"grad_norm": 2.4375,
"learning_rate": 9.620991253644314e-06,
"loss": 0.7975,
"step": 3134
},
{
"epoch": 6.3979591836734695,
"grad_norm": 2.46875,
"learning_rate": 9.588597343699385e-06,
"loss": 0.809,
"step": 3135
},
{
"epoch": 6.4,
"grad_norm": 2.546875,
"learning_rate": 9.556203433754454e-06,
"loss": 0.833,
"step": 3136
},
{
"epoch": 6.40204081632653,
"grad_norm": 2.421875,
"learning_rate": 9.523809523809523e-06,
"loss": 0.859,
"step": 3137
},
{
"epoch": 6.404081632653061,
"grad_norm": 2.40625,
"learning_rate": 9.491415613864595e-06,
"loss": 0.7756,
"step": 3138
},
{
"epoch": 6.406122448979592,
"grad_norm": 2.515625,
"learning_rate": 9.459021703919664e-06,
"loss": 0.8029,
"step": 3139
},
{
"epoch": 6.408163265306122,
"grad_norm": 2.46875,
"learning_rate": 9.426627793974733e-06,
"loss": 0.7622,
"step": 3140
},
{
"epoch": 6.410204081632653,
"grad_norm": 2.359375,
"learning_rate": 9.394233884029802e-06,
"loss": 0.8132,
"step": 3141
},
{
"epoch": 6.412244897959184,
"grad_norm": 2.46875,
"learning_rate": 9.361839974084873e-06,
"loss": 0.8315,
"step": 3142
},
{
"epoch": 6.414285714285715,
"grad_norm": 2.484375,
"learning_rate": 9.329446064139942e-06,
"loss": 0.8266,
"step": 3143
},
{
"epoch": 6.416326530612245,
"grad_norm": 2.40625,
"learning_rate": 9.297052154195011e-06,
"loss": 0.7522,
"step": 3144
},
{
"epoch": 6.418367346938775,
"grad_norm": 2.671875,
"learning_rate": 9.264658244250082e-06,
"loss": 0.7832,
"step": 3145
},
{
"epoch": 6.420408163265306,
"grad_norm": 2.390625,
"learning_rate": 9.23226433430515e-06,
"loss": 0.7991,
"step": 3146
},
{
"epoch": 6.422448979591837,
"grad_norm": 2.359375,
"learning_rate": 9.199870424360221e-06,
"loss": 0.8581,
"step": 3147
},
{
"epoch": 6.424489795918367,
"grad_norm": 2.453125,
"learning_rate": 9.16747651441529e-06,
"loss": 0.817,
"step": 3148
},
{
"epoch": 6.426530612244898,
"grad_norm": 2.328125,
"learning_rate": 9.13508260447036e-06,
"loss": 0.7831,
"step": 3149
},
{
"epoch": 6.428571428571429,
"grad_norm": 2.1875,
"learning_rate": 9.10268869452543e-06,
"loss": 0.7685,
"step": 3150
},
{
"epoch": 6.430612244897959,
"grad_norm": 2.421875,
"learning_rate": 9.070294784580499e-06,
"loss": 0.789,
"step": 3151
},
{
"epoch": 6.43265306122449,
"grad_norm": 2.53125,
"learning_rate": 9.03790087463557e-06,
"loss": 0.8112,
"step": 3152
},
{
"epoch": 6.4346938775510205,
"grad_norm": 2.59375,
"learning_rate": 9.005506964690638e-06,
"loss": 0.8298,
"step": 3153
},
{
"epoch": 6.436734693877551,
"grad_norm": 2.390625,
"learning_rate": 8.973113054745707e-06,
"loss": 0.8014,
"step": 3154
},
{
"epoch": 6.438775510204081,
"grad_norm": 2.609375,
"learning_rate": 8.940719144800778e-06,
"loss": 0.8091,
"step": 3155
},
{
"epoch": 6.440816326530612,
"grad_norm": 2.3125,
"learning_rate": 8.908325234855849e-06,
"loss": 0.7423,
"step": 3156
},
{
"epoch": 6.442857142857143,
"grad_norm": 2.28125,
"learning_rate": 8.875931324910918e-06,
"loss": 0.8788,
"step": 3157
},
{
"epoch": 6.444897959183674,
"grad_norm": 2.4375,
"learning_rate": 8.843537414965987e-06,
"loss": 0.7966,
"step": 3158
},
{
"epoch": 6.446938775510204,
"grad_norm": 2.3125,
"learning_rate": 8.811143505021057e-06,
"loss": 0.8059,
"step": 3159
},
{
"epoch": 6.448979591836735,
"grad_norm": 2.5,
"learning_rate": 8.778749595076126e-06,
"loss": 0.8892,
"step": 3160
},
{
"epoch": 6.451020408163266,
"grad_norm": 2.40625,
"learning_rate": 8.746355685131195e-06,
"loss": 0.7999,
"step": 3161
},
{
"epoch": 6.453061224489796,
"grad_norm": 2.390625,
"learning_rate": 8.713961775186264e-06,
"loss": 0.853,
"step": 3162
},
{
"epoch": 6.455102040816326,
"grad_norm": 2.59375,
"learning_rate": 8.681567865241336e-06,
"loss": 0.8077,
"step": 3163
},
{
"epoch": 6.457142857142857,
"grad_norm": 2.25,
"learning_rate": 8.649173955296405e-06,
"loss": 0.8016,
"step": 3164
},
{
"epoch": 6.459183673469388,
"grad_norm": 2.3125,
"learning_rate": 8.616780045351474e-06,
"loss": 0.7455,
"step": 3165
},
{
"epoch": 6.461224489795918,
"grad_norm": 2.421875,
"learning_rate": 8.584386135406543e-06,
"loss": 0.8458,
"step": 3166
},
{
"epoch": 6.463265306122449,
"grad_norm": 2.5,
"learning_rate": 8.551992225461614e-06,
"loss": 0.8079,
"step": 3167
},
{
"epoch": 6.46530612244898,
"grad_norm": 2.5625,
"learning_rate": 8.519598315516683e-06,
"loss": 0.7935,
"step": 3168
},
{
"epoch": 6.46734693877551,
"grad_norm": 2.3125,
"learning_rate": 8.487204405571752e-06,
"loss": 0.8373,
"step": 3169
},
{
"epoch": 6.469387755102041,
"grad_norm": 2.59375,
"learning_rate": 8.454810495626823e-06,
"loss": 0.8089,
"step": 3170
},
{
"epoch": 6.4714285714285715,
"grad_norm": 2.484375,
"learning_rate": 8.422416585681893e-06,
"loss": 0.8119,
"step": 3171
},
{
"epoch": 6.473469387755102,
"grad_norm": 2.515625,
"learning_rate": 8.390022675736962e-06,
"loss": 0.9165,
"step": 3172
},
{
"epoch": 6.475510204081632,
"grad_norm": 2.515625,
"learning_rate": 8.357628765792031e-06,
"loss": 0.7549,
"step": 3173
},
{
"epoch": 6.477551020408163,
"grad_norm": 2.578125,
"learning_rate": 8.325234855847102e-06,
"loss": 0.8911,
"step": 3174
},
{
"epoch": 6.479591836734694,
"grad_norm": 2.53125,
"learning_rate": 8.29284094590217e-06,
"loss": 0.8601,
"step": 3175
},
{
"epoch": 6.481632653061224,
"grad_norm": 2.5,
"learning_rate": 8.26044703595724e-06,
"loss": 0.8139,
"step": 3176
},
{
"epoch": 6.483673469387755,
"grad_norm": 2.53125,
"learning_rate": 8.22805312601231e-06,
"loss": 0.8243,
"step": 3177
},
{
"epoch": 6.485714285714286,
"grad_norm": 2.46875,
"learning_rate": 8.19565921606738e-06,
"loss": 0.7648,
"step": 3178
},
{
"epoch": 6.487755102040817,
"grad_norm": 2.609375,
"learning_rate": 8.163265306122448e-06,
"loss": 0.8437,
"step": 3179
},
{
"epoch": 6.489795918367347,
"grad_norm": 2.609375,
"learning_rate": 8.130871396177519e-06,
"loss": 0.8532,
"step": 3180
},
{
"epoch": 6.4918367346938775,
"grad_norm": 2.25,
"learning_rate": 8.09847748623259e-06,
"loss": 0.7887,
"step": 3181
},
{
"epoch": 6.493877551020408,
"grad_norm": 2.296875,
"learning_rate": 8.066083576287659e-06,
"loss": 0.7737,
"step": 3182
},
{
"epoch": 6.495918367346939,
"grad_norm": 2.515625,
"learning_rate": 8.033689666342728e-06,
"loss": 0.7514,
"step": 3183
},
{
"epoch": 6.497959183673469,
"grad_norm": 2.71875,
"learning_rate": 8.001295756397798e-06,
"loss": 0.8424,
"step": 3184
},
{
"epoch": 6.5,
"grad_norm": 2.296875,
"learning_rate": 7.968901846452867e-06,
"loss": 0.7592,
"step": 3185
},
{
"epoch": 6.502040816326531,
"grad_norm": 2.375,
"learning_rate": 7.936507936507936e-06,
"loss": 0.7765,
"step": 3186
},
{
"epoch": 6.504081632653062,
"grad_norm": 2.484375,
"learning_rate": 7.904114026563005e-06,
"loss": 0.7909,
"step": 3187
},
{
"epoch": 6.506122448979592,
"grad_norm": 2.546875,
"learning_rate": 7.871720116618077e-06,
"loss": 0.8351,
"step": 3188
},
{
"epoch": 6.5081632653061225,
"grad_norm": 2.546875,
"learning_rate": 7.839326206673146e-06,
"loss": 0.8427,
"step": 3189
},
{
"epoch": 6.510204081632653,
"grad_norm": 2.40625,
"learning_rate": 7.806932296728215e-06,
"loss": 0.8148,
"step": 3190
},
{
"epoch": 6.512244897959183,
"grad_norm": 2.296875,
"learning_rate": 7.774538386783286e-06,
"loss": 0.847,
"step": 3191
},
{
"epoch": 6.514285714285714,
"grad_norm": 2.484375,
"learning_rate": 7.742144476838355e-06,
"loss": 0.7621,
"step": 3192
},
{
"epoch": 6.516326530612245,
"grad_norm": 2.421875,
"learning_rate": 7.709750566893424e-06,
"loss": 0.8186,
"step": 3193
},
{
"epoch": 6.518367346938776,
"grad_norm": 2.3125,
"learning_rate": 7.677356656948493e-06,
"loss": 0.8107,
"step": 3194
},
{
"epoch": 6.520408163265306,
"grad_norm": 2.546875,
"learning_rate": 7.644962747003564e-06,
"loss": 0.8685,
"step": 3195
},
{
"epoch": 6.522448979591837,
"grad_norm": 2.4375,
"learning_rate": 7.612568837058634e-06,
"loss": 0.7544,
"step": 3196
},
{
"epoch": 6.524489795918368,
"grad_norm": 2.484375,
"learning_rate": 7.580174927113703e-06,
"loss": 0.8385,
"step": 3197
},
{
"epoch": 6.526530612244898,
"grad_norm": 2.390625,
"learning_rate": 7.547781017168773e-06,
"loss": 0.7223,
"step": 3198
},
{
"epoch": 6.5285714285714285,
"grad_norm": 2.4375,
"learning_rate": 7.515387107223842e-06,
"loss": 0.7613,
"step": 3199
},
{
"epoch": 6.530612244897959,
"grad_norm": 2.5,
"learning_rate": 7.482993197278912e-06,
"loss": 0.7926,
"step": 3200
},
{
"epoch": 6.53265306122449,
"grad_norm": 2.453125,
"learning_rate": 7.450599287333982e-06,
"loss": 0.7643,
"step": 3201
},
{
"epoch": 6.53469387755102,
"grad_norm": 2.640625,
"learning_rate": 7.418205377389051e-06,
"loss": 0.8568,
"step": 3202
},
{
"epoch": 6.536734693877551,
"grad_norm": 2.34375,
"learning_rate": 7.38581146744412e-06,
"loss": 0.7992,
"step": 3203
},
{
"epoch": 6.538775510204082,
"grad_norm": 2.359375,
"learning_rate": 7.35341755749919e-06,
"loss": 0.7878,
"step": 3204
},
{
"epoch": 6.540816326530612,
"grad_norm": 2.375,
"learning_rate": 7.321023647554261e-06,
"loss": 0.7886,
"step": 3205
},
{
"epoch": 6.542857142857143,
"grad_norm": 2.53125,
"learning_rate": 7.28862973760933e-06,
"loss": 0.8078,
"step": 3206
},
{
"epoch": 6.544897959183674,
"grad_norm": 2.65625,
"learning_rate": 7.2562358276644e-06,
"loss": 0.8891,
"step": 3207
},
{
"epoch": 6.546938775510204,
"grad_norm": 2.640625,
"learning_rate": 7.2238419177194695e-06,
"loss": 0.8695,
"step": 3208
},
{
"epoch": 6.548979591836734,
"grad_norm": 2.515625,
"learning_rate": 7.191448007774538e-06,
"loss": 0.8001,
"step": 3209
},
{
"epoch": 6.551020408163265,
"grad_norm": 2.484375,
"learning_rate": 7.159054097829608e-06,
"loss": 0.7508,
"step": 3210
},
{
"epoch": 6.553061224489796,
"grad_norm": 2.421875,
"learning_rate": 7.126660187884677e-06,
"loss": 0.8383,
"step": 3211
},
{
"epoch": 6.555102040816326,
"grad_norm": 2.296875,
"learning_rate": 7.094266277939747e-06,
"loss": 0.838,
"step": 3212
},
{
"epoch": 6.557142857142857,
"grad_norm": 2.4375,
"learning_rate": 7.061872367994818e-06,
"loss": 0.802,
"step": 3213
},
{
"epoch": 6.559183673469388,
"grad_norm": 2.375,
"learning_rate": 7.0294784580498875e-06,
"loss": 0.7898,
"step": 3214
},
{
"epoch": 6.561224489795919,
"grad_norm": 2.484375,
"learning_rate": 6.9970845481049564e-06,
"loss": 0.7663,
"step": 3215
},
{
"epoch": 6.563265306122449,
"grad_norm": 2.359375,
"learning_rate": 6.964690638160026e-06,
"loss": 0.7638,
"step": 3216
},
{
"epoch": 6.5653061224489795,
"grad_norm": 2.34375,
"learning_rate": 6.932296728215096e-06,
"loss": 0.7664,
"step": 3217
},
{
"epoch": 6.56734693877551,
"grad_norm": 2.25,
"learning_rate": 6.899902818270165e-06,
"loss": 0.7741,
"step": 3218
},
{
"epoch": 6.569387755102041,
"grad_norm": 2.453125,
"learning_rate": 6.867508908325235e-06,
"loss": 0.8285,
"step": 3219
},
{
"epoch": 6.571428571428571,
"grad_norm": 2.515625,
"learning_rate": 6.835114998380305e-06,
"loss": 0.7725,
"step": 3220
},
{
"epoch": 6.573469387755102,
"grad_norm": 2.546875,
"learning_rate": 6.802721088435375e-06,
"loss": 0.7967,
"step": 3221
},
{
"epoch": 6.575510204081633,
"grad_norm": 2.40625,
"learning_rate": 6.770327178490444e-06,
"loss": 0.8043,
"step": 3222
},
{
"epoch": 6.577551020408164,
"grad_norm": 2.53125,
"learning_rate": 6.737933268545514e-06,
"loss": 0.8327,
"step": 3223
},
{
"epoch": 6.579591836734694,
"grad_norm": 2.125,
"learning_rate": 6.705539358600584e-06,
"loss": 0.7573,
"step": 3224
},
{
"epoch": 6.581632653061225,
"grad_norm": 2.203125,
"learning_rate": 6.673145448655653e-06,
"loss": 0.7698,
"step": 3225
},
{
"epoch": 6.583673469387755,
"grad_norm": 2.46875,
"learning_rate": 6.640751538710723e-06,
"loss": 0.87,
"step": 3226
},
{
"epoch": 6.585714285714285,
"grad_norm": 2.40625,
"learning_rate": 6.608357628765792e-06,
"loss": 0.8061,
"step": 3227
},
{
"epoch": 6.587755102040816,
"grad_norm": 2.796875,
"learning_rate": 6.5759637188208614e-06,
"loss": 0.9108,
"step": 3228
},
{
"epoch": 6.589795918367347,
"grad_norm": 2.609375,
"learning_rate": 6.543569808875932e-06,
"loss": 0.8008,
"step": 3229
},
{
"epoch": 6.591836734693878,
"grad_norm": 2.390625,
"learning_rate": 6.511175898931002e-06,
"loss": 0.8727,
"step": 3230
},
{
"epoch": 6.593877551020408,
"grad_norm": 2.328125,
"learning_rate": 6.478781988986071e-06,
"loss": 0.8308,
"step": 3231
},
{
"epoch": 6.595918367346939,
"grad_norm": 2.5,
"learning_rate": 6.446388079041141e-06,
"loss": 0.8273,
"step": 3232
},
{
"epoch": 6.59795918367347,
"grad_norm": 2.625,
"learning_rate": 6.4139941690962105e-06,
"loss": 0.8319,
"step": 3233
},
{
"epoch": 6.6,
"grad_norm": 2.46875,
"learning_rate": 6.3816002591512795e-06,
"loss": 0.8239,
"step": 3234
},
{
"epoch": 6.6020408163265305,
"grad_norm": 2.546875,
"learning_rate": 6.349206349206349e-06,
"loss": 0.8057,
"step": 3235
},
{
"epoch": 6.604081632653061,
"grad_norm": 2.375,
"learning_rate": 6.316812439261418e-06,
"loss": 0.794,
"step": 3236
},
{
"epoch": 6.606122448979592,
"grad_norm": 2.734375,
"learning_rate": 6.284418529316488e-06,
"loss": 0.9053,
"step": 3237
},
{
"epoch": 6.608163265306122,
"grad_norm": 2.421875,
"learning_rate": 6.252024619371559e-06,
"loss": 0.7992,
"step": 3238
},
{
"epoch": 6.610204081632653,
"grad_norm": 2.46875,
"learning_rate": 6.219630709426628e-06,
"loss": 0.862,
"step": 3239
},
{
"epoch": 6.612244897959184,
"grad_norm": 2.34375,
"learning_rate": 6.187236799481698e-06,
"loss": 0.816,
"step": 3240
},
{
"epoch": 6.614285714285714,
"grad_norm": 2.234375,
"learning_rate": 6.154842889536767e-06,
"loss": 0.8024,
"step": 3241
},
{
"epoch": 6.616326530612245,
"grad_norm": 2.65625,
"learning_rate": 6.122448979591837e-06,
"loss": 0.8232,
"step": 3242
},
{
"epoch": 6.618367346938776,
"grad_norm": 2.484375,
"learning_rate": 6.090055069646906e-06,
"loss": 0.8025,
"step": 3243
},
{
"epoch": 6.6204081632653065,
"grad_norm": 2.65625,
"learning_rate": 6.057661159701977e-06,
"loss": 0.8248,
"step": 3244
},
{
"epoch": 6.622448979591836,
"grad_norm": 2.328125,
"learning_rate": 6.025267249757046e-06,
"loss": 0.8003,
"step": 3245
},
{
"epoch": 6.624489795918367,
"grad_norm": 2.453125,
"learning_rate": 5.9928733398121155e-06,
"loss": 0.8715,
"step": 3246
},
{
"epoch": 6.626530612244898,
"grad_norm": 2.4375,
"learning_rate": 5.960479429867185e-06,
"loss": 0.7995,
"step": 3247
},
{
"epoch": 6.628571428571428,
"grad_norm": 2.53125,
"learning_rate": 5.928085519922255e-06,
"loss": 0.8677,
"step": 3248
},
{
"epoch": 6.630612244897959,
"grad_norm": 2.28125,
"learning_rate": 5.895691609977325e-06,
"loss": 0.777,
"step": 3249
},
{
"epoch": 6.63265306122449,
"grad_norm": 2.09375,
"learning_rate": 5.863297700032394e-06,
"loss": 0.8114,
"step": 3250
},
{
"epoch": 6.634693877551021,
"grad_norm": 2.421875,
"learning_rate": 5.830903790087464e-06,
"loss": 0.8321,
"step": 3251
},
{
"epoch": 6.636734693877551,
"grad_norm": 2.3125,
"learning_rate": 5.7985098801425335e-06,
"loss": 0.8757,
"step": 3252
},
{
"epoch": 6.6387755102040815,
"grad_norm": 2.34375,
"learning_rate": 5.766115970197603e-06,
"loss": 0.7658,
"step": 3253
},
{
"epoch": 6.640816326530612,
"grad_norm": 2.390625,
"learning_rate": 5.733722060252672e-06,
"loss": 0.7093,
"step": 3254
},
{
"epoch": 6.642857142857143,
"grad_norm": 2.53125,
"learning_rate": 5.701328150307742e-06,
"loss": 0.8227,
"step": 3255
},
{
"epoch": 6.644897959183673,
"grad_norm": 2.28125,
"learning_rate": 5.668934240362813e-06,
"loss": 0.7419,
"step": 3256
},
{
"epoch": 6.646938775510204,
"grad_norm": 2.46875,
"learning_rate": 5.636540330417882e-06,
"loss": 0.8162,
"step": 3257
},
{
"epoch": 6.648979591836735,
"grad_norm": 2.703125,
"learning_rate": 5.6041464204729515e-06,
"loss": 0.8695,
"step": 3258
},
{
"epoch": 6.651020408163266,
"grad_norm": 2.640625,
"learning_rate": 5.5717525105280205e-06,
"loss": 0.9011,
"step": 3259
},
{
"epoch": 6.653061224489796,
"grad_norm": 2.546875,
"learning_rate": 5.539358600583091e-06,
"loss": 0.7929,
"step": 3260
},
{
"epoch": 6.655102040816327,
"grad_norm": 2.3125,
"learning_rate": 5.50696469063816e-06,
"loss": 0.7634,
"step": 3261
},
{
"epoch": 6.6571428571428575,
"grad_norm": 2.25,
"learning_rate": 5.47457078069323e-06,
"loss": 0.7489,
"step": 3262
},
{
"epoch": 6.659183673469387,
"grad_norm": 2.46875,
"learning_rate": 5.4421768707483e-06,
"loss": 0.8152,
"step": 3263
},
{
"epoch": 6.661224489795918,
"grad_norm": 2.34375,
"learning_rate": 5.4097829608033695e-06,
"loss": 0.7356,
"step": 3264
},
{
"epoch": 6.663265306122449,
"grad_norm": 2.515625,
"learning_rate": 5.377389050858439e-06,
"loss": 0.7876,
"step": 3265
},
{
"epoch": 6.66530612244898,
"grad_norm": 2.578125,
"learning_rate": 5.344995140913508e-06,
"loss": 0.7798,
"step": 3266
},
{
"epoch": 6.66734693877551,
"grad_norm": 2.421875,
"learning_rate": 5.312601230968578e-06,
"loss": 0.7442,
"step": 3267
},
{
"epoch": 6.669387755102041,
"grad_norm": 2.390625,
"learning_rate": 5.280207321023648e-06,
"loss": 0.8275,
"step": 3268
},
{
"epoch": 6.671428571428572,
"grad_norm": 2.734375,
"learning_rate": 5.247813411078718e-06,
"loss": 0.8946,
"step": 3269
},
{
"epoch": 6.673469387755102,
"grad_norm": 2.3125,
"learning_rate": 5.215419501133787e-06,
"loss": 0.87,
"step": 3270
},
{
"epoch": 6.6755102040816325,
"grad_norm": 2.40625,
"learning_rate": 5.1830255911888565e-06,
"loss": 0.8487,
"step": 3271
},
{
"epoch": 6.677551020408163,
"grad_norm": 2.421875,
"learning_rate": 5.150631681243926e-06,
"loss": 0.8483,
"step": 3272
},
{
"epoch": 6.679591836734694,
"grad_norm": 2.375,
"learning_rate": 5.118237771298996e-06,
"loss": 0.8666,
"step": 3273
},
{
"epoch": 6.681632653061224,
"grad_norm": 2.5,
"learning_rate": 5.085843861354066e-06,
"loss": 0.8191,
"step": 3274
},
{
"epoch": 6.683673469387755,
"grad_norm": 2.875,
"learning_rate": 5.053449951409135e-06,
"loss": 0.8965,
"step": 3275
},
{
"epoch": 6.685714285714286,
"grad_norm": 2.359375,
"learning_rate": 5.021056041464205e-06,
"loss": 0.8196,
"step": 3276
},
{
"epoch": 6.687755102040816,
"grad_norm": 2.375,
"learning_rate": 4.9886621315192745e-06,
"loss": 0.8078,
"step": 3277
},
{
"epoch": 6.689795918367347,
"grad_norm": 2.4375,
"learning_rate": 4.956268221574344e-06,
"loss": 0.7917,
"step": 3278
},
{
"epoch": 6.691836734693878,
"grad_norm": 2.453125,
"learning_rate": 4.923874311629414e-06,
"loss": 0.8491,
"step": 3279
},
{
"epoch": 6.6938775510204085,
"grad_norm": 2.609375,
"learning_rate": 4.891480401684483e-06,
"loss": 0.7846,
"step": 3280
},
{
"epoch": 6.6959183673469385,
"grad_norm": 2.40625,
"learning_rate": 4.859086491739554e-06,
"loss": 0.7881,
"step": 3281
},
{
"epoch": 6.697959183673469,
"grad_norm": 2.75,
"learning_rate": 4.826692581794623e-06,
"loss": 0.9012,
"step": 3282
},
{
"epoch": 6.7,
"grad_norm": 2.46875,
"learning_rate": 4.7942986718496926e-06,
"loss": 0.8185,
"step": 3283
},
{
"epoch": 6.70204081632653,
"grad_norm": 2.34375,
"learning_rate": 4.7619047619047615e-06,
"loss": 0.7944,
"step": 3284
},
{
"epoch": 6.704081632653061,
"grad_norm": 2.375,
"learning_rate": 4.729510851959832e-06,
"loss": 0.8205,
"step": 3285
},
{
"epoch": 6.706122448979592,
"grad_norm": 2.671875,
"learning_rate": 4.697116942014901e-06,
"loss": 0.8723,
"step": 3286
},
{
"epoch": 6.708163265306123,
"grad_norm": 2.5,
"learning_rate": 4.664723032069971e-06,
"loss": 0.8153,
"step": 3287
},
{
"epoch": 6.710204081632653,
"grad_norm": 2.4375,
"learning_rate": 4.632329122125041e-06,
"loss": 0.8019,
"step": 3288
},
{
"epoch": 6.7122448979591836,
"grad_norm": 2.390625,
"learning_rate": 4.599935212180111e-06,
"loss": 0.8282,
"step": 3289
},
{
"epoch": 6.714285714285714,
"grad_norm": 2.546875,
"learning_rate": 4.56754130223518e-06,
"loss": 0.8162,
"step": 3290
},
{
"epoch": 6.716326530612245,
"grad_norm": 2.53125,
"learning_rate": 4.535147392290249e-06,
"loss": 0.8267,
"step": 3291
},
{
"epoch": 6.718367346938775,
"grad_norm": 2.5,
"learning_rate": 4.502753482345319e-06,
"loss": 0.8133,
"step": 3292
},
{
"epoch": 6.720408163265306,
"grad_norm": 2.375,
"learning_rate": 4.470359572400389e-06,
"loss": 0.8336,
"step": 3293
},
{
"epoch": 6.722448979591837,
"grad_norm": 2.609375,
"learning_rate": 4.437965662455459e-06,
"loss": 0.9122,
"step": 3294
},
{
"epoch": 6.724489795918368,
"grad_norm": 2.46875,
"learning_rate": 4.405571752510529e-06,
"loss": 0.8662,
"step": 3295
},
{
"epoch": 6.726530612244898,
"grad_norm": 2.375,
"learning_rate": 4.3731778425655976e-06,
"loss": 0.7482,
"step": 3296
},
{
"epoch": 6.728571428571429,
"grad_norm": 2.328125,
"learning_rate": 4.340783932620668e-06,
"loss": 0.8384,
"step": 3297
},
{
"epoch": 6.7306122448979595,
"grad_norm": 2.484375,
"learning_rate": 4.308390022675737e-06,
"loss": 0.7669,
"step": 3298
},
{
"epoch": 6.7326530612244895,
"grad_norm": 2.640625,
"learning_rate": 4.275996112730807e-06,
"loss": 0.8645,
"step": 3299
},
{
"epoch": 6.73469387755102,
"grad_norm": 2.328125,
"learning_rate": 4.243602202785876e-06,
"loss": 0.8026,
"step": 3300
},
{
"epoch": 6.736734693877551,
"grad_norm": 2.4375,
"learning_rate": 4.211208292840947e-06,
"loss": 0.8471,
"step": 3301
},
{
"epoch": 6.738775510204082,
"grad_norm": 2.578125,
"learning_rate": 4.178814382896016e-06,
"loss": 0.8891,
"step": 3302
},
{
"epoch": 6.740816326530612,
"grad_norm": 2.671875,
"learning_rate": 4.146420472951085e-06,
"loss": 0.824,
"step": 3303
},
{
"epoch": 6.742857142857143,
"grad_norm": 2.5625,
"learning_rate": 4.114026563006155e-06,
"loss": 0.8246,
"step": 3304
},
{
"epoch": 6.744897959183674,
"grad_norm": 2.484375,
"learning_rate": 4.081632653061224e-06,
"loss": 0.8093,
"step": 3305
},
{
"epoch": 6.746938775510204,
"grad_norm": 2.734375,
"learning_rate": 4.049238743116295e-06,
"loss": 0.8453,
"step": 3306
},
{
"epoch": 6.748979591836735,
"grad_norm": 2.34375,
"learning_rate": 4.016844833171364e-06,
"loss": 0.7437,
"step": 3307
},
{
"epoch": 6.751020408163265,
"grad_norm": 2.40625,
"learning_rate": 3.984450923226434e-06,
"loss": 0.853,
"step": 3308
},
{
"epoch": 6.753061224489796,
"grad_norm": 2.25,
"learning_rate": 3.9520570132815026e-06,
"loss": 0.771,
"step": 3309
},
{
"epoch": 6.755102040816326,
"grad_norm": 2.5,
"learning_rate": 3.919663103336573e-06,
"loss": 0.8485,
"step": 3310
},
{
"epoch": 6.757142857142857,
"grad_norm": 2.328125,
"learning_rate": 3.887269193391643e-06,
"loss": 0.7745,
"step": 3311
},
{
"epoch": 6.759183673469388,
"grad_norm": 2.4375,
"learning_rate": 3.854875283446712e-06,
"loss": 0.86,
"step": 3312
},
{
"epoch": 6.761224489795918,
"grad_norm": 2.671875,
"learning_rate": 3.822481373501782e-06,
"loss": 0.8632,
"step": 3313
},
{
"epoch": 6.763265306122449,
"grad_norm": 2.3125,
"learning_rate": 3.7900874635568516e-06,
"loss": 0.7821,
"step": 3314
},
{
"epoch": 6.76530612244898,
"grad_norm": 2.4375,
"learning_rate": 3.757693553611921e-06,
"loss": 0.7944,
"step": 3315
},
{
"epoch": 6.7673469387755105,
"grad_norm": 2.78125,
"learning_rate": 3.725299643666991e-06,
"loss": 0.9161,
"step": 3316
},
{
"epoch": 6.7693877551020405,
"grad_norm": 2.421875,
"learning_rate": 3.69290573372206e-06,
"loss": 0.8084,
"step": 3317
},
{
"epoch": 6.771428571428571,
"grad_norm": 2.28125,
"learning_rate": 3.6605118237771304e-06,
"loss": 0.7925,
"step": 3318
},
{
"epoch": 6.773469387755102,
"grad_norm": 2.46875,
"learning_rate": 3.6281179138322e-06,
"loss": 0.8479,
"step": 3319
},
{
"epoch": 6.775510204081632,
"grad_norm": 2.25,
"learning_rate": 3.595724003887269e-06,
"loss": 0.7686,
"step": 3320
},
{
"epoch": 6.777551020408163,
"grad_norm": 2.390625,
"learning_rate": 3.5633300939423386e-06,
"loss": 0.82,
"step": 3321
},
{
"epoch": 6.779591836734694,
"grad_norm": 2.640625,
"learning_rate": 3.530936183997409e-06,
"loss": 0.8676,
"step": 3322
},
{
"epoch": 6.781632653061225,
"grad_norm": 2.265625,
"learning_rate": 3.4985422740524782e-06,
"loss": 0.8016,
"step": 3323
},
{
"epoch": 6.783673469387755,
"grad_norm": 2.484375,
"learning_rate": 3.466148364107548e-06,
"loss": 0.7916,
"step": 3324
},
{
"epoch": 6.785714285714286,
"grad_norm": 2.53125,
"learning_rate": 3.4337544541626174e-06,
"loss": 0.8089,
"step": 3325
},
{
"epoch": 6.7877551020408164,
"grad_norm": 2.625,
"learning_rate": 3.4013605442176877e-06,
"loss": 0.8226,
"step": 3326
},
{
"epoch": 6.789795918367347,
"grad_norm": 2.46875,
"learning_rate": 3.368966634272757e-06,
"loss": 0.8101,
"step": 3327
},
{
"epoch": 6.791836734693877,
"grad_norm": 2.453125,
"learning_rate": 3.3365727243278264e-06,
"loss": 0.8383,
"step": 3328
},
{
"epoch": 6.793877551020408,
"grad_norm": 2.203125,
"learning_rate": 3.304178814382896e-06,
"loss": 0.7322,
"step": 3329
},
{
"epoch": 6.795918367346939,
"grad_norm": 2.40625,
"learning_rate": 3.271784904437966e-06,
"loss": 0.7632,
"step": 3330
},
{
"epoch": 6.79795918367347,
"grad_norm": 2.46875,
"learning_rate": 3.2393909944930354e-06,
"loss": 0.8714,
"step": 3331
},
{
"epoch": 6.8,
"grad_norm": 2.546875,
"learning_rate": 3.2069970845481052e-06,
"loss": 0.8458,
"step": 3332
},
{
"epoch": 6.802040816326531,
"grad_norm": 2.359375,
"learning_rate": 3.1746031746031746e-06,
"loss": 0.8663,
"step": 3333
},
{
"epoch": 6.8040816326530615,
"grad_norm": 2.5625,
"learning_rate": 3.142209264658244e-06,
"loss": 0.8691,
"step": 3334
},
{
"epoch": 6.8061224489795915,
"grad_norm": 2.625,
"learning_rate": 3.109815354713314e-06,
"loss": 0.8029,
"step": 3335
},
{
"epoch": 6.808163265306122,
"grad_norm": 2.421875,
"learning_rate": 3.0774214447683836e-06,
"loss": 0.8763,
"step": 3336
},
{
"epoch": 6.810204081632653,
"grad_norm": 2.625,
"learning_rate": 3.045027534823453e-06,
"loss": 0.7908,
"step": 3337
},
{
"epoch": 6.812244897959184,
"grad_norm": 2.28125,
"learning_rate": 3.012633624878523e-06,
"loss": 0.7283,
"step": 3338
},
{
"epoch": 6.814285714285714,
"grad_norm": 2.578125,
"learning_rate": 2.9802397149335927e-06,
"loss": 0.8298,
"step": 3339
},
{
"epoch": 6.816326530612245,
"grad_norm": 2.28125,
"learning_rate": 2.9478458049886625e-06,
"loss": 0.7913,
"step": 3340
},
{
"epoch": 6.818367346938776,
"grad_norm": 2.265625,
"learning_rate": 2.915451895043732e-06,
"loss": 0.7501,
"step": 3341
},
{
"epoch": 6.820408163265306,
"grad_norm": 2.3125,
"learning_rate": 2.8830579850988017e-06,
"loss": 0.7858,
"step": 3342
},
{
"epoch": 6.822448979591837,
"grad_norm": 2.46875,
"learning_rate": 2.850664075153871e-06,
"loss": 0.8025,
"step": 3343
},
{
"epoch": 6.8244897959183675,
"grad_norm": 2.546875,
"learning_rate": 2.818270165208941e-06,
"loss": 0.7896,
"step": 3344
},
{
"epoch": 6.826530612244898,
"grad_norm": 2.5,
"learning_rate": 2.7858762552640102e-06,
"loss": 0.8735,
"step": 3345
},
{
"epoch": 6.828571428571428,
"grad_norm": 2.390625,
"learning_rate": 2.75348234531908e-06,
"loss": 0.7765,
"step": 3346
},
{
"epoch": 6.830612244897959,
"grad_norm": 2.296875,
"learning_rate": 2.72108843537415e-06,
"loss": 0.7669,
"step": 3347
},
{
"epoch": 6.83265306122449,
"grad_norm": 2.578125,
"learning_rate": 2.6886945254292197e-06,
"loss": 0.8444,
"step": 3348
},
{
"epoch": 6.83469387755102,
"grad_norm": 2.625,
"learning_rate": 2.656300615484289e-06,
"loss": 0.8611,
"step": 3349
},
{
"epoch": 6.836734693877551,
"grad_norm": 2.578125,
"learning_rate": 2.623906705539359e-06,
"loss": 0.7838,
"step": 3350
},
{
"epoch": 6.838775510204082,
"grad_norm": 2.234375,
"learning_rate": 2.5915127955944283e-06,
"loss": 0.7828,
"step": 3351
},
{
"epoch": 6.840816326530613,
"grad_norm": 2.28125,
"learning_rate": 2.559118885649498e-06,
"loss": 0.7854,
"step": 3352
},
{
"epoch": 6.8428571428571425,
"grad_norm": 2.421875,
"learning_rate": 2.5267249757045675e-06,
"loss": 0.7977,
"step": 3353
},
{
"epoch": 6.844897959183673,
"grad_norm": 2.484375,
"learning_rate": 2.4943310657596373e-06,
"loss": 0.7652,
"step": 3354
},
{
"epoch": 6.846938775510204,
"grad_norm": 2.328125,
"learning_rate": 2.461937155814707e-06,
"loss": 0.7696,
"step": 3355
},
{
"epoch": 6.848979591836734,
"grad_norm": 2.15625,
"learning_rate": 2.429543245869777e-06,
"loss": 0.8339,
"step": 3356
},
{
"epoch": 6.851020408163265,
"grad_norm": 2.4375,
"learning_rate": 2.3971493359248463e-06,
"loss": 0.7937,
"step": 3357
},
{
"epoch": 6.853061224489796,
"grad_norm": 2.40625,
"learning_rate": 2.364755425979916e-06,
"loss": 0.825,
"step": 3358
},
{
"epoch": 6.855102040816327,
"grad_norm": 2.46875,
"learning_rate": 2.3323615160349855e-06,
"loss": 0.7848,
"step": 3359
},
{
"epoch": 6.857142857142857,
"grad_norm": 2.640625,
"learning_rate": 2.2999676060900553e-06,
"loss": 0.8695,
"step": 3360
},
{
"epoch": 6.859183673469388,
"grad_norm": 2.46875,
"learning_rate": 2.2675736961451247e-06,
"loss": 0.7602,
"step": 3361
},
{
"epoch": 6.8612244897959185,
"grad_norm": 2.40625,
"learning_rate": 2.2351797862001945e-06,
"loss": 0.8322,
"step": 3362
},
{
"epoch": 6.863265306122449,
"grad_norm": 2.578125,
"learning_rate": 2.2027858762552643e-06,
"loss": 0.8178,
"step": 3363
},
{
"epoch": 6.865306122448979,
"grad_norm": 2.359375,
"learning_rate": 2.170391966310334e-06,
"loss": 0.7774,
"step": 3364
},
{
"epoch": 6.86734693877551,
"grad_norm": 2.40625,
"learning_rate": 2.1379980563654035e-06,
"loss": 0.7743,
"step": 3365
},
{
"epoch": 6.869387755102041,
"grad_norm": 2.4375,
"learning_rate": 2.1056041464204733e-06,
"loss": 0.7883,
"step": 3366
},
{
"epoch": 6.871428571428572,
"grad_norm": 2.59375,
"learning_rate": 2.0732102364755427e-06,
"loss": 0.8688,
"step": 3367
},
{
"epoch": 6.873469387755102,
"grad_norm": 2.234375,
"learning_rate": 2.040816326530612e-06,
"loss": 0.7091,
"step": 3368
},
{
"epoch": 6.875510204081633,
"grad_norm": 2.453125,
"learning_rate": 2.008422416585682e-06,
"loss": 0.8402,
"step": 3369
},
{
"epoch": 6.877551020408164,
"grad_norm": 2.1875,
"learning_rate": 1.9760285066407513e-06,
"loss": 0.7653,
"step": 3370
},
{
"epoch": 6.8795918367346935,
"grad_norm": 2.3125,
"learning_rate": 1.9436345966958215e-06,
"loss": 0.7588,
"step": 3371
},
{
"epoch": 6.881632653061224,
"grad_norm": 2.265625,
"learning_rate": 1.911240686750891e-06,
"loss": 0.7664,
"step": 3372
},
{
"epoch": 6.883673469387755,
"grad_norm": 2.578125,
"learning_rate": 1.8788467768059605e-06,
"loss": 0.8108,
"step": 3373
},
{
"epoch": 6.885714285714286,
"grad_norm": 2.359375,
"learning_rate": 1.84645286686103e-06,
"loss": 0.8603,
"step": 3374
},
{
"epoch": 6.887755102040816,
"grad_norm": 2.359375,
"learning_rate": 1.8140589569161e-06,
"loss": 0.7905,
"step": 3375
},
{
"epoch": 6.889795918367347,
"grad_norm": 2.296875,
"learning_rate": 1.7816650469711693e-06,
"loss": 0.767,
"step": 3376
},
{
"epoch": 6.891836734693878,
"grad_norm": 2.3125,
"learning_rate": 1.7492711370262391e-06,
"loss": 0.8304,
"step": 3377
},
{
"epoch": 6.893877551020408,
"grad_norm": 2.4375,
"learning_rate": 1.7168772270813087e-06,
"loss": 0.7503,
"step": 3378
},
{
"epoch": 6.895918367346939,
"grad_norm": 2.421875,
"learning_rate": 1.6844833171363785e-06,
"loss": 0.831,
"step": 3379
},
{
"epoch": 6.8979591836734695,
"grad_norm": 2.359375,
"learning_rate": 1.652089407191448e-06,
"loss": 0.7488,
"step": 3380
},
{
"epoch": 6.9,
"grad_norm": 2.4375,
"learning_rate": 1.6196954972465177e-06,
"loss": 0.7855,
"step": 3381
},
{
"epoch": 6.90204081632653,
"grad_norm": 2.53125,
"learning_rate": 1.5873015873015873e-06,
"loss": 0.838,
"step": 3382
},
{
"epoch": 6.904081632653061,
"grad_norm": 2.34375,
"learning_rate": 1.554907677356657e-06,
"loss": 0.8058,
"step": 3383
},
{
"epoch": 6.906122448979592,
"grad_norm": 2.390625,
"learning_rate": 1.5225137674117265e-06,
"loss": 0.8049,
"step": 3384
},
{
"epoch": 6.908163265306122,
"grad_norm": 2.1875,
"learning_rate": 1.4901198574667963e-06,
"loss": 0.7409,
"step": 3385
},
{
"epoch": 6.910204081632653,
"grad_norm": 2.78125,
"learning_rate": 1.457725947521866e-06,
"loss": 0.8607,
"step": 3386
},
{
"epoch": 6.912244897959184,
"grad_norm": 2.40625,
"learning_rate": 1.4253320375769355e-06,
"loss": 0.856,
"step": 3387
},
{
"epoch": 6.914285714285715,
"grad_norm": 2.453125,
"learning_rate": 1.3929381276320051e-06,
"loss": 0.738,
"step": 3388
},
{
"epoch": 6.916326530612245,
"grad_norm": 2.25,
"learning_rate": 1.360544217687075e-06,
"loss": 0.7383,
"step": 3389
},
{
"epoch": 6.918367346938775,
"grad_norm": 2.546875,
"learning_rate": 1.3281503077421445e-06,
"loss": 0.7855,
"step": 3390
},
{
"epoch": 6.920408163265306,
"grad_norm": 2.578125,
"learning_rate": 1.2957563977972141e-06,
"loss": 0.841,
"step": 3391
},
{
"epoch": 6.922448979591836,
"grad_norm": 2.265625,
"learning_rate": 1.2633624878522837e-06,
"loss": 0.7723,
"step": 3392
},
{
"epoch": 6.924489795918367,
"grad_norm": 2.34375,
"learning_rate": 1.2309685779073535e-06,
"loss": 0.7689,
"step": 3393
},
{
"epoch": 6.926530612244898,
"grad_norm": 2.40625,
"learning_rate": 1.1985746679624231e-06,
"loss": 0.7993,
"step": 3394
},
{
"epoch": 6.928571428571429,
"grad_norm": 2.625,
"learning_rate": 1.1661807580174927e-06,
"loss": 0.8413,
"step": 3395
},
{
"epoch": 6.930612244897959,
"grad_norm": 2.25,
"learning_rate": 1.1337868480725623e-06,
"loss": 0.8014,
"step": 3396
},
{
"epoch": 6.93265306122449,
"grad_norm": 2.578125,
"learning_rate": 1.1013929381276321e-06,
"loss": 0.8613,
"step": 3397
},
{
"epoch": 6.9346938775510205,
"grad_norm": 2.296875,
"learning_rate": 1.0689990281827017e-06,
"loss": 0.8238,
"step": 3398
},
{
"epoch": 6.936734693877551,
"grad_norm": 2.421875,
"learning_rate": 1.0366051182377713e-06,
"loss": 0.8114,
"step": 3399
},
{
"epoch": 6.938775510204081,
"grad_norm": 2.59375,
"learning_rate": 1.004211208292841e-06,
"loss": 0.7968,
"step": 3400
},
{
"epoch": 6.940816326530612,
"grad_norm": 2.390625,
"learning_rate": 9.718172983479108e-07,
"loss": 0.7894,
"step": 3401
},
{
"epoch": 6.942857142857143,
"grad_norm": 2.265625,
"learning_rate": 9.394233884029803e-07,
"loss": 0.7437,
"step": 3402
},
{
"epoch": 6.944897959183674,
"grad_norm": 2.53125,
"learning_rate": 9.0702947845805e-07,
"loss": 0.8233,
"step": 3403
},
{
"epoch": 6.946938775510204,
"grad_norm": 2.46875,
"learning_rate": 8.746355685131196e-07,
"loss": 0.7742,
"step": 3404
},
{
"epoch": 6.948979591836735,
"grad_norm": 2.40625,
"learning_rate": 8.422416585681893e-07,
"loss": 0.8311,
"step": 3405
},
{
"epoch": 6.951020408163266,
"grad_norm": 2.359375,
"learning_rate": 8.098477486232589e-07,
"loss": 0.8189,
"step": 3406
},
{
"epoch": 6.953061224489796,
"grad_norm": 2.3125,
"learning_rate": 7.774538386783285e-07,
"loss": 0.7435,
"step": 3407
},
{
"epoch": 6.955102040816326,
"grad_norm": 2.5625,
"learning_rate": 7.450599287333982e-07,
"loss": 0.8108,
"step": 3408
},
{
"epoch": 6.957142857142857,
"grad_norm": 2.515625,
"learning_rate": 7.126660187884678e-07,
"loss": 0.7694,
"step": 3409
},
{
"epoch": 6.959183673469388,
"grad_norm": 2.28125,
"learning_rate": 6.802721088435375e-07,
"loss": 0.8291,
"step": 3410
},
{
"epoch": 6.961224489795918,
"grad_norm": 2.546875,
"learning_rate": 6.478781988986071e-07,
"loss": 0.8302,
"step": 3411
},
{
"epoch": 6.963265306122449,
"grad_norm": 2.46875,
"learning_rate": 6.154842889536768e-07,
"loss": 0.8729,
"step": 3412
},
{
"epoch": 6.96530612244898,
"grad_norm": 2.53125,
"learning_rate": 5.830903790087464e-07,
"loss": 0.7484,
"step": 3413
},
{
"epoch": 6.96734693877551,
"grad_norm": 2.28125,
"learning_rate": 5.506964690638161e-07,
"loss": 0.7746,
"step": 3414
},
{
"epoch": 6.969387755102041,
"grad_norm": 2.515625,
"learning_rate": 5.183025591188857e-07,
"loss": 0.8473,
"step": 3415
},
{
"epoch": 6.9714285714285715,
"grad_norm": 2.421875,
"learning_rate": 4.859086491739554e-07,
"loss": 0.8695,
"step": 3416
},
{
"epoch": 6.973469387755102,
"grad_norm": 2.421875,
"learning_rate": 4.53514739229025e-07,
"loss": 0.8249,
"step": 3417
},
{
"epoch": 6.975510204081632,
"grad_norm": 2.359375,
"learning_rate": 4.2112082928409463e-07,
"loss": 0.7749,
"step": 3418
},
{
"epoch": 6.977551020408163,
"grad_norm": 2.21875,
"learning_rate": 3.8872691933916423e-07,
"loss": 0.7507,
"step": 3419
},
{
"epoch": 6.979591836734694,
"grad_norm": 2.421875,
"learning_rate": 3.563330093942339e-07,
"loss": 0.7236,
"step": 3420
},
{
"epoch": 6.981632653061224,
"grad_norm": 2.484375,
"learning_rate": 3.2393909944930353e-07,
"loss": 0.8538,
"step": 3421
},
{
"epoch": 6.983673469387755,
"grad_norm": 2.5,
"learning_rate": 2.915451895043732e-07,
"loss": 0.8119,
"step": 3422
},
{
"epoch": 6.985714285714286,
"grad_norm": 2.375,
"learning_rate": 2.5915127955944284e-07,
"loss": 0.9002,
"step": 3423
},
{
"epoch": 6.987755102040817,
"grad_norm": 2.34375,
"learning_rate": 2.267573696145125e-07,
"loss": 0.8106,
"step": 3424
},
{
"epoch": 6.989795918367347,
"grad_norm": 2.53125,
"learning_rate": 1.9436345966958211e-07,
"loss": 0.7706,
"step": 3425
},
{
"epoch": 6.9918367346938775,
"grad_norm": 2.328125,
"learning_rate": 1.6196954972465177e-07,
"loss": 0.8167,
"step": 3426
},
{
"epoch": 6.993877551020408,
"grad_norm": 2.5,
"learning_rate": 1.2957563977972142e-07,
"loss": 0.8576,
"step": 3427
},
{
"epoch": 6.995918367346938,
"grad_norm": 2.53125,
"learning_rate": 9.718172983479106e-08,
"loss": 0.797,
"step": 3428
},
{
"epoch": 6.997959183673469,
"grad_norm": 2.359375,
"learning_rate": 6.478781988986071e-08,
"loss": 0.7789,
"step": 3429
},
{
"epoch": 7.0,
"grad_norm": 2.421875,
"learning_rate": 3.2393909944930355e-08,
"loss": 0.7793,
"step": 3430
}
],
"logging_steps": 1,
"max_steps": 3430,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.377162808135254e+18,
"train_batch_size": 32,
"trial_name": null,
"trial_params": null
}