R1_Qwen1.5B_0.1_Hard / trainer_state.json
a-F1's picture
Model save
966a09e verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 20.0,
"eval_steps": 500,
"global_step": 640,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.03125,
"grad_norm": 46.110501381920706,
"learning_rate": 3.125e-07,
"loss": 12.2656,
"step": 1
},
{
"epoch": 0.0625,
"grad_norm": 44.3840095403182,
"learning_rate": 6.25e-07,
"loss": 12.25,
"step": 2
},
{
"epoch": 0.09375,
"grad_norm": 45.08551841682328,
"learning_rate": 9.375000000000001e-07,
"loss": 12.2344,
"step": 3
},
{
"epoch": 0.125,
"grad_norm": 45.1316287538876,
"learning_rate": 1.25e-06,
"loss": 12.2344,
"step": 4
},
{
"epoch": 0.15625,
"grad_norm": 46.41560905837161,
"learning_rate": 1.5625e-06,
"loss": 12.2031,
"step": 5
},
{
"epoch": 0.1875,
"grad_norm": 45.99984421115488,
"learning_rate": 1.8750000000000003e-06,
"loss": 12.2188,
"step": 6
},
{
"epoch": 0.21875,
"grad_norm": 46.38339519477593,
"learning_rate": 2.1875000000000002e-06,
"loss": 12.1406,
"step": 7
},
{
"epoch": 0.25,
"grad_norm": 46.40529439389694,
"learning_rate": 2.5e-06,
"loss": 12.1719,
"step": 8
},
{
"epoch": 0.28125,
"grad_norm": 43.65578500040681,
"learning_rate": 2.8125e-06,
"loss": 12.0156,
"step": 9
},
{
"epoch": 0.3125,
"grad_norm": 44.68853723233476,
"learning_rate": 3.125e-06,
"loss": 11.9688,
"step": 10
},
{
"epoch": 0.34375,
"grad_norm": 44.78101790123477,
"learning_rate": 3.4375e-06,
"loss": 11.9219,
"step": 11
},
{
"epoch": 0.375,
"grad_norm": 46.09518551380032,
"learning_rate": 3.7500000000000005e-06,
"loss": 11.2031,
"step": 12
},
{
"epoch": 0.40625,
"grad_norm": 43.314408501134345,
"learning_rate": 4.0625000000000005e-06,
"loss": 11.1406,
"step": 13
},
{
"epoch": 0.4375,
"grad_norm": 43.67395224267264,
"learning_rate": 4.3750000000000005e-06,
"loss": 10.9844,
"step": 14
},
{
"epoch": 0.46875,
"grad_norm": 44.942577210615966,
"learning_rate": 4.6875000000000004e-06,
"loss": 10.9062,
"step": 15
},
{
"epoch": 0.5,
"grad_norm": 39.795501724737136,
"learning_rate": 5e-06,
"loss": 9.2031,
"step": 16
},
{
"epoch": 0.53125,
"grad_norm": 36.85445424560905,
"learning_rate": 5.3125e-06,
"loss": 9.25,
"step": 17
},
{
"epoch": 0.5625,
"grad_norm": 36.386407981382206,
"learning_rate": 5.625e-06,
"loss": 9.0,
"step": 18
},
{
"epoch": 0.59375,
"grad_norm": 31.01202194392733,
"learning_rate": 5.9375e-06,
"loss": 8.4844,
"step": 19
},
{
"epoch": 0.625,
"grad_norm": 29.63788066305587,
"learning_rate": 6.25e-06,
"loss": 8.4062,
"step": 20
},
{
"epoch": 0.65625,
"grad_norm": 26.180432188386177,
"learning_rate": 6.5625e-06,
"loss": 8.2969,
"step": 21
},
{
"epoch": 0.6875,
"grad_norm": 19.359932695283444,
"learning_rate": 6.875e-06,
"loss": 7.7578,
"step": 22
},
{
"epoch": 0.71875,
"grad_norm": 16.80095311236084,
"learning_rate": 7.1875e-06,
"loss": 7.6016,
"step": 23
},
{
"epoch": 0.75,
"grad_norm": 12.119680802563018,
"learning_rate": 7.500000000000001e-06,
"loss": 7.3125,
"step": 24
},
{
"epoch": 0.78125,
"grad_norm": 12.600638957374223,
"learning_rate": 7.8125e-06,
"loss": 7.4453,
"step": 25
},
{
"epoch": 0.8125,
"grad_norm": 19.42990002822014,
"learning_rate": 8.125000000000001e-06,
"loss": 7.5469,
"step": 26
},
{
"epoch": 0.84375,
"grad_norm": 22.374131848811093,
"learning_rate": 8.4375e-06,
"loss": 7.375,
"step": 27
},
{
"epoch": 0.875,
"grad_norm": 19.57930909452537,
"learning_rate": 8.750000000000001e-06,
"loss": 7.2109,
"step": 28
},
{
"epoch": 0.90625,
"grad_norm": 20.324224063135294,
"learning_rate": 9.0625e-06,
"loss": 7.0781,
"step": 29
},
{
"epoch": 0.9375,
"grad_norm": 18.50485383281225,
"learning_rate": 9.375000000000001e-06,
"loss": 7.1016,
"step": 30
},
{
"epoch": 0.96875,
"grad_norm": 19.282887599812298,
"learning_rate": 9.6875e-06,
"loss": 6.7734,
"step": 31
},
{
"epoch": 1.0,
"grad_norm": 13.922627090211678,
"learning_rate": 1e-05,
"loss": 6.7344,
"step": 32
},
{
"epoch": 1.03125,
"grad_norm": 13.050915366974877,
"learning_rate": 9.983552631578947e-06,
"loss": 6.6406,
"step": 33
},
{
"epoch": 1.0625,
"grad_norm": 9.21367695459411,
"learning_rate": 9.967105263157895e-06,
"loss": 6.1484,
"step": 34
},
{
"epoch": 1.09375,
"grad_norm": 7.469938122435962,
"learning_rate": 9.950657894736842e-06,
"loss": 6.2891,
"step": 35
},
{
"epoch": 1.125,
"grad_norm": 6.322117149479666,
"learning_rate": 9.93421052631579e-06,
"loss": 6.0703,
"step": 36
},
{
"epoch": 1.15625,
"grad_norm": 6.067036130357828,
"learning_rate": 9.917763157894738e-06,
"loss": 6.2734,
"step": 37
},
{
"epoch": 1.1875,
"grad_norm": 6.159787369412575,
"learning_rate": 9.901315789473686e-06,
"loss": 6.0703,
"step": 38
},
{
"epoch": 1.21875,
"grad_norm": 6.0713071098842395,
"learning_rate": 9.884868421052633e-06,
"loss": 6.0,
"step": 39
},
{
"epoch": 1.25,
"grad_norm": 6.592393486649236,
"learning_rate": 9.868421052631579e-06,
"loss": 5.6641,
"step": 40
},
{
"epoch": 1.28125,
"grad_norm": 7.035653985047366,
"learning_rate": 9.851973684210527e-06,
"loss": 5.6016,
"step": 41
},
{
"epoch": 1.3125,
"grad_norm": 6.717323149397708,
"learning_rate": 9.835526315789474e-06,
"loss": 5.5469,
"step": 42
},
{
"epoch": 1.34375,
"grad_norm": 5.970768286182251,
"learning_rate": 9.819078947368422e-06,
"loss": 5.4297,
"step": 43
},
{
"epoch": 1.375,
"grad_norm": 5.723626744044176,
"learning_rate": 9.80263157894737e-06,
"loss": 5.7734,
"step": 44
},
{
"epoch": 1.40625,
"grad_norm": 5.1471050746329485,
"learning_rate": 9.786184210526316e-06,
"loss": 5.2812,
"step": 45
},
{
"epoch": 1.4375,
"grad_norm": 4.323727754176942,
"learning_rate": 9.769736842105264e-06,
"loss": 5.3047,
"step": 46
},
{
"epoch": 1.46875,
"grad_norm": 3.9055527444416493,
"learning_rate": 9.753289473684211e-06,
"loss": 5.3906,
"step": 47
},
{
"epoch": 1.5,
"grad_norm": 4.228742611105712,
"learning_rate": 9.736842105263159e-06,
"loss": 5.0391,
"step": 48
},
{
"epoch": 1.53125,
"grad_norm": 4.066259863295825,
"learning_rate": 9.720394736842105e-06,
"loss": 4.9141,
"step": 49
},
{
"epoch": 1.5625,
"grad_norm": 4.649487456233776,
"learning_rate": 9.703947368421054e-06,
"loss": 4.7344,
"step": 50
},
{
"epoch": 1.59375,
"grad_norm": 4.284492602425991,
"learning_rate": 9.6875e-06,
"loss": 4.7891,
"step": 51
},
{
"epoch": 1.625,
"grad_norm": 4.255834421159205,
"learning_rate": 9.671052631578948e-06,
"loss": 4.7656,
"step": 52
},
{
"epoch": 1.65625,
"grad_norm": 3.3905156951443787,
"learning_rate": 9.654605263157896e-06,
"loss": 4.8203,
"step": 53
},
{
"epoch": 1.6875,
"grad_norm": 3.372000616668671,
"learning_rate": 9.638157894736843e-06,
"loss": 4.6562,
"step": 54
},
{
"epoch": 1.71875,
"grad_norm": 3.3716451672730043,
"learning_rate": 9.62171052631579e-06,
"loss": 4.5703,
"step": 55
},
{
"epoch": 1.75,
"grad_norm": 3.4701893070848757,
"learning_rate": 9.605263157894737e-06,
"loss": 4.5469,
"step": 56
},
{
"epoch": 1.78125,
"grad_norm": 3.160350331885458,
"learning_rate": 9.588815789473685e-06,
"loss": 4.2344,
"step": 57
},
{
"epoch": 1.8125,
"grad_norm": 3.3967526879578323,
"learning_rate": 9.572368421052632e-06,
"loss": 4.3828,
"step": 58
},
{
"epoch": 1.84375,
"grad_norm": 3.0675497190805037,
"learning_rate": 9.55592105263158e-06,
"loss": 4.1836,
"step": 59
},
{
"epoch": 1.875,
"grad_norm": 3.2209407679699535,
"learning_rate": 9.539473684210528e-06,
"loss": 4.5391,
"step": 60
},
{
"epoch": 1.90625,
"grad_norm": 3.0374784801495185,
"learning_rate": 9.523026315789474e-06,
"loss": 4.5234,
"step": 61
},
{
"epoch": 1.9375,
"grad_norm": 3.1584530825465893,
"learning_rate": 9.506578947368423e-06,
"loss": 4.3125,
"step": 62
},
{
"epoch": 1.96875,
"grad_norm": 2.71281632857147,
"learning_rate": 9.490131578947369e-06,
"loss": 3.8281,
"step": 63
},
{
"epoch": 2.0,
"grad_norm": 2.7121073900509622,
"learning_rate": 9.473684210526315e-06,
"loss": 4.1562,
"step": 64
},
{
"epoch": 2.03125,
"grad_norm": 2.7419832449346178,
"learning_rate": 9.457236842105264e-06,
"loss": 3.6016,
"step": 65
},
{
"epoch": 2.0625,
"grad_norm": 2.822322918514082,
"learning_rate": 9.440789473684212e-06,
"loss": 3.8555,
"step": 66
},
{
"epoch": 2.09375,
"grad_norm": 2.6876019984970316,
"learning_rate": 9.424342105263158e-06,
"loss": 4.2031,
"step": 67
},
{
"epoch": 2.125,
"grad_norm": 2.7014572688765037,
"learning_rate": 9.407894736842106e-06,
"loss": 3.9922,
"step": 68
},
{
"epoch": 2.15625,
"grad_norm": 2.5749081557210487,
"learning_rate": 9.391447368421054e-06,
"loss": 4.0,
"step": 69
},
{
"epoch": 2.1875,
"grad_norm": 2.5094384154907816,
"learning_rate": 9.375000000000001e-06,
"loss": 3.5703,
"step": 70
},
{
"epoch": 2.21875,
"grad_norm": 2.3759939616387262,
"learning_rate": 9.358552631578947e-06,
"loss": 3.5703,
"step": 71
},
{
"epoch": 2.25,
"grad_norm": 2.396832813190029,
"learning_rate": 9.342105263157895e-06,
"loss": 3.5039,
"step": 72
},
{
"epoch": 2.28125,
"grad_norm": 2.2974057602228353,
"learning_rate": 9.325657894736842e-06,
"loss": 3.6836,
"step": 73
},
{
"epoch": 2.3125,
"grad_norm": 2.299078356511566,
"learning_rate": 9.30921052631579e-06,
"loss": 3.6328,
"step": 74
},
{
"epoch": 2.34375,
"grad_norm": 2.2167536329414,
"learning_rate": 9.292763157894738e-06,
"loss": 3.6289,
"step": 75
},
{
"epoch": 2.375,
"grad_norm": 2.291424274819479,
"learning_rate": 9.276315789473686e-06,
"loss": 3.5898,
"step": 76
},
{
"epoch": 2.40625,
"grad_norm": 2.0711161335212536,
"learning_rate": 9.259868421052633e-06,
"loss": 3.3398,
"step": 77
},
{
"epoch": 2.4375,
"grad_norm": 2.168829352719516,
"learning_rate": 9.243421052631579e-06,
"loss": 3.6367,
"step": 78
},
{
"epoch": 2.46875,
"grad_norm": 2.0050888506256443,
"learning_rate": 9.226973684210527e-06,
"loss": 3.3594,
"step": 79
},
{
"epoch": 2.5,
"grad_norm": 2.213218342065591,
"learning_rate": 9.210526315789474e-06,
"loss": 3.4688,
"step": 80
},
{
"epoch": 2.53125,
"grad_norm": 2.1783865648233567,
"learning_rate": 9.194078947368422e-06,
"loss": 3.5781,
"step": 81
},
{
"epoch": 2.5625,
"grad_norm": 1.8789106547226722,
"learning_rate": 9.17763157894737e-06,
"loss": 3.2969,
"step": 82
},
{
"epoch": 2.59375,
"grad_norm": 2.197246298703413,
"learning_rate": 9.161184210526316e-06,
"loss": 3.3203,
"step": 83
},
{
"epoch": 2.625,
"grad_norm": 1.9163387667758176,
"learning_rate": 9.144736842105264e-06,
"loss": 3.1172,
"step": 84
},
{
"epoch": 2.65625,
"grad_norm": 2.0702491303544193,
"learning_rate": 9.128289473684211e-06,
"loss": 3.0586,
"step": 85
},
{
"epoch": 2.6875,
"grad_norm": 1.8964079143443917,
"learning_rate": 9.111842105263159e-06,
"loss": 2.9219,
"step": 86
},
{
"epoch": 2.71875,
"grad_norm": 1.9913389941190272,
"learning_rate": 9.095394736842105e-06,
"loss": 3.3828,
"step": 87
},
{
"epoch": 2.75,
"grad_norm": 1.9481029459662997,
"learning_rate": 9.078947368421054e-06,
"loss": 2.8828,
"step": 88
},
{
"epoch": 2.78125,
"grad_norm": 1.897304436878228,
"learning_rate": 9.0625e-06,
"loss": 2.8633,
"step": 89
},
{
"epoch": 2.8125,
"grad_norm": 1.7962340916408015,
"learning_rate": 9.046052631578948e-06,
"loss": 3.0625,
"step": 90
},
{
"epoch": 2.84375,
"grad_norm": 1.8381297453196523,
"learning_rate": 9.029605263157896e-06,
"loss": 3.1094,
"step": 91
},
{
"epoch": 2.875,
"grad_norm": 1.7794526602162275,
"learning_rate": 9.013157894736843e-06,
"loss": 2.8594,
"step": 92
},
{
"epoch": 2.90625,
"grad_norm": 1.8047121766254635,
"learning_rate": 8.996710526315791e-06,
"loss": 3.1406,
"step": 93
},
{
"epoch": 2.9375,
"grad_norm": 1.9699073388267623,
"learning_rate": 8.980263157894737e-06,
"loss": 3.0078,
"step": 94
},
{
"epoch": 2.96875,
"grad_norm": 1.8731129484295872,
"learning_rate": 8.963815789473685e-06,
"loss": 2.875,
"step": 95
},
{
"epoch": 3.0,
"grad_norm": 1.6982200970791388,
"learning_rate": 8.947368421052632e-06,
"loss": 2.5625,
"step": 96
},
{
"epoch": 3.03125,
"grad_norm": 1.9031029201560958,
"learning_rate": 8.93092105263158e-06,
"loss": 2.9844,
"step": 97
},
{
"epoch": 3.0625,
"grad_norm": 1.6695451188240085,
"learning_rate": 8.914473684210528e-06,
"loss": 2.6523,
"step": 98
},
{
"epoch": 3.09375,
"grad_norm": 1.730680102186145,
"learning_rate": 8.898026315789475e-06,
"loss": 3.0859,
"step": 99
},
{
"epoch": 3.125,
"grad_norm": 1.6884819836662068,
"learning_rate": 8.881578947368423e-06,
"loss": 2.7148,
"step": 100
},
{
"epoch": 3.15625,
"grad_norm": 1.728765765557413,
"learning_rate": 8.865131578947369e-06,
"loss": 3.0,
"step": 101
},
{
"epoch": 3.1875,
"grad_norm": 1.8602197774702887,
"learning_rate": 8.848684210526316e-06,
"loss": 2.75,
"step": 102
},
{
"epoch": 3.21875,
"grad_norm": 1.7228141108566688,
"learning_rate": 8.832236842105264e-06,
"loss": 2.5664,
"step": 103
},
{
"epoch": 3.25,
"grad_norm": 1.810657852919142,
"learning_rate": 8.81578947368421e-06,
"loss": 2.7617,
"step": 104
},
{
"epoch": 3.28125,
"grad_norm": 1.649528540621614,
"learning_rate": 8.799342105263158e-06,
"loss": 2.9102,
"step": 105
},
{
"epoch": 3.3125,
"grad_norm": 1.6281918056322846,
"learning_rate": 8.782894736842106e-06,
"loss": 2.7109,
"step": 106
},
{
"epoch": 3.34375,
"grad_norm": 1.6464336351267892,
"learning_rate": 8.766447368421054e-06,
"loss": 2.6055,
"step": 107
},
{
"epoch": 3.375,
"grad_norm": 1.8980671641413749,
"learning_rate": 8.750000000000001e-06,
"loss": 2.8438,
"step": 108
},
{
"epoch": 3.40625,
"grad_norm": 1.8109357611137384,
"learning_rate": 8.733552631578947e-06,
"loss": 2.8516,
"step": 109
},
{
"epoch": 3.4375,
"grad_norm": 1.7292602276559284,
"learning_rate": 8.717105263157895e-06,
"loss": 2.8945,
"step": 110
},
{
"epoch": 3.46875,
"grad_norm": 1.5948507175911883,
"learning_rate": 8.700657894736842e-06,
"loss": 2.5156,
"step": 111
},
{
"epoch": 3.5,
"grad_norm": 1.806808364445775,
"learning_rate": 8.68421052631579e-06,
"loss": 2.7656,
"step": 112
},
{
"epoch": 3.53125,
"grad_norm": 1.5695807259145398,
"learning_rate": 8.667763157894738e-06,
"loss": 2.4023,
"step": 113
},
{
"epoch": 3.5625,
"grad_norm": 1.5483755852685912,
"learning_rate": 8.651315789473685e-06,
"loss": 2.543,
"step": 114
},
{
"epoch": 3.59375,
"grad_norm": 1.6190500817619615,
"learning_rate": 8.634868421052633e-06,
"loss": 2.4062,
"step": 115
},
{
"epoch": 3.625,
"grad_norm": 1.725081555813222,
"learning_rate": 8.61842105263158e-06,
"loss": 2.668,
"step": 116
},
{
"epoch": 3.65625,
"grad_norm": 1.5223857347255458,
"learning_rate": 8.601973684210527e-06,
"loss": 2.582,
"step": 117
},
{
"epoch": 3.6875,
"grad_norm": 1.4573586184299665,
"learning_rate": 8.585526315789474e-06,
"loss": 2.1621,
"step": 118
},
{
"epoch": 3.71875,
"grad_norm": 1.551630975643171,
"learning_rate": 8.569078947368422e-06,
"loss": 2.25,
"step": 119
},
{
"epoch": 3.75,
"grad_norm": 1.7115247638697302,
"learning_rate": 8.552631578947368e-06,
"loss": 2.5078,
"step": 120
},
{
"epoch": 3.78125,
"grad_norm": 1.5161089621031751,
"learning_rate": 8.536184210526316e-06,
"loss": 2.4844,
"step": 121
},
{
"epoch": 3.8125,
"grad_norm": 1.5463172048875915,
"learning_rate": 8.519736842105265e-06,
"loss": 2.3594,
"step": 122
},
{
"epoch": 3.84375,
"grad_norm": 1.632449509289891,
"learning_rate": 8.503289473684211e-06,
"loss": 2.3711,
"step": 123
},
{
"epoch": 3.875,
"grad_norm": 1.5220532463788692,
"learning_rate": 8.486842105263159e-06,
"loss": 2.5781,
"step": 124
},
{
"epoch": 3.90625,
"grad_norm": 1.4018744182292626,
"learning_rate": 8.470394736842106e-06,
"loss": 2.125,
"step": 125
},
{
"epoch": 3.9375,
"grad_norm": 1.452042757407898,
"learning_rate": 8.453947368421054e-06,
"loss": 2.2168,
"step": 126
},
{
"epoch": 3.96875,
"grad_norm": 1.5840590841632787,
"learning_rate": 8.4375e-06,
"loss": 2.375,
"step": 127
},
{
"epoch": 4.0,
"grad_norm": 1.6041264843039755,
"learning_rate": 8.421052631578948e-06,
"loss": 2.5898,
"step": 128
},
{
"epoch": 4.03125,
"grad_norm": 1.5449529169706775,
"learning_rate": 8.404605263157896e-06,
"loss": 2.1406,
"step": 129
},
{
"epoch": 4.0625,
"grad_norm": 1.4114794133075035,
"learning_rate": 8.388157894736843e-06,
"loss": 2.3242,
"step": 130
},
{
"epoch": 4.09375,
"grad_norm": 1.4120631432352837,
"learning_rate": 8.371710526315791e-06,
"loss": 2.4492,
"step": 131
},
{
"epoch": 4.125,
"grad_norm": 1.611229701046415,
"learning_rate": 8.355263157894737e-06,
"loss": 2.4121,
"step": 132
},
{
"epoch": 4.15625,
"grad_norm": 1.342411831838034,
"learning_rate": 8.338815789473685e-06,
"loss": 1.9609,
"step": 133
},
{
"epoch": 4.1875,
"grad_norm": 1.841969844503565,
"learning_rate": 8.322368421052632e-06,
"loss": 2.5645,
"step": 134
},
{
"epoch": 4.21875,
"grad_norm": 1.5185920240220854,
"learning_rate": 8.30592105263158e-06,
"loss": 2.2754,
"step": 135
},
{
"epoch": 4.25,
"grad_norm": 1.7834691967758824,
"learning_rate": 8.289473684210526e-06,
"loss": 2.4453,
"step": 136
},
{
"epoch": 4.28125,
"grad_norm": 1.5536983087480682,
"learning_rate": 8.273026315789475e-06,
"loss": 2.3867,
"step": 137
},
{
"epoch": 4.3125,
"grad_norm": 1.6713110707162413,
"learning_rate": 8.256578947368423e-06,
"loss": 2.5352,
"step": 138
},
{
"epoch": 4.34375,
"grad_norm": 1.4508550182948057,
"learning_rate": 8.24013157894737e-06,
"loss": 2.0938,
"step": 139
},
{
"epoch": 4.375,
"grad_norm": 1.5433665435103934,
"learning_rate": 8.223684210526316e-06,
"loss": 2.3633,
"step": 140
},
{
"epoch": 4.40625,
"grad_norm": 1.4646130800229755,
"learning_rate": 8.207236842105264e-06,
"loss": 2.1895,
"step": 141
},
{
"epoch": 4.4375,
"grad_norm": 1.2612998058796774,
"learning_rate": 8.19078947368421e-06,
"loss": 1.8887,
"step": 142
},
{
"epoch": 4.46875,
"grad_norm": 1.4242229934206938,
"learning_rate": 8.174342105263158e-06,
"loss": 2.248,
"step": 143
},
{
"epoch": 4.5,
"grad_norm": 1.3568311619256344,
"learning_rate": 8.157894736842106e-06,
"loss": 2.2656,
"step": 144
},
{
"epoch": 4.53125,
"grad_norm": 1.5675469731233866,
"learning_rate": 8.141447368421055e-06,
"loss": 2.3906,
"step": 145
},
{
"epoch": 4.5625,
"grad_norm": 1.4677734689265398,
"learning_rate": 8.125000000000001e-06,
"loss": 2.166,
"step": 146
},
{
"epoch": 4.59375,
"grad_norm": 1.4095494134291513,
"learning_rate": 8.108552631578947e-06,
"loss": 2.0801,
"step": 147
},
{
"epoch": 4.625,
"grad_norm": 1.2878578828666303,
"learning_rate": 8.092105263157896e-06,
"loss": 1.9707,
"step": 148
},
{
"epoch": 4.65625,
"grad_norm": 1.3374208950735806,
"learning_rate": 8.075657894736842e-06,
"loss": 2.0273,
"step": 149
},
{
"epoch": 4.6875,
"grad_norm": 1.3729371606088205,
"learning_rate": 8.05921052631579e-06,
"loss": 2.1289,
"step": 150
},
{
"epoch": 4.71875,
"grad_norm": 1.3241742252417898,
"learning_rate": 8.042763157894737e-06,
"loss": 2.0879,
"step": 151
},
{
"epoch": 4.75,
"grad_norm": 1.3471247242485715,
"learning_rate": 8.026315789473685e-06,
"loss": 1.8652,
"step": 152
},
{
"epoch": 4.78125,
"grad_norm": 1.4796814241372787,
"learning_rate": 8.009868421052633e-06,
"loss": 2.0898,
"step": 153
},
{
"epoch": 4.8125,
"grad_norm": 1.495355734738571,
"learning_rate": 7.99342105263158e-06,
"loss": 2.2305,
"step": 154
},
{
"epoch": 4.84375,
"grad_norm": 1.5568481473400642,
"learning_rate": 7.976973684210527e-06,
"loss": 2.0957,
"step": 155
},
{
"epoch": 4.875,
"grad_norm": 1.418950047941357,
"learning_rate": 7.960526315789474e-06,
"loss": 2.0879,
"step": 156
},
{
"epoch": 4.90625,
"grad_norm": 1.2150012585524623,
"learning_rate": 7.944078947368422e-06,
"loss": 1.7637,
"step": 157
},
{
"epoch": 4.9375,
"grad_norm": 1.5502099489754206,
"learning_rate": 7.927631578947368e-06,
"loss": 2.3086,
"step": 158
},
{
"epoch": 4.96875,
"grad_norm": 1.4300086207532696,
"learning_rate": 7.911184210526316e-06,
"loss": 1.7852,
"step": 159
},
{
"epoch": 5.0,
"grad_norm": 1.348782645249337,
"learning_rate": 7.894736842105265e-06,
"loss": 1.8965,
"step": 160
},
{
"epoch": 5.03125,
"grad_norm": 1.345313969026504,
"learning_rate": 7.878289473684211e-06,
"loss": 2.0703,
"step": 161
},
{
"epoch": 5.0625,
"grad_norm": 1.3410519038383748,
"learning_rate": 7.86184210526316e-06,
"loss": 1.9863,
"step": 162
},
{
"epoch": 5.09375,
"grad_norm": 1.3415275737905352,
"learning_rate": 7.845394736842106e-06,
"loss": 1.9258,
"step": 163
},
{
"epoch": 5.125,
"grad_norm": 1.4042294952658152,
"learning_rate": 7.828947368421054e-06,
"loss": 2.125,
"step": 164
},
{
"epoch": 5.15625,
"grad_norm": 1.3663594348069061,
"learning_rate": 7.8125e-06,
"loss": 2.0352,
"step": 165
},
{
"epoch": 5.1875,
"grad_norm": 1.5744500230349077,
"learning_rate": 7.796052631578948e-06,
"loss": 2.2285,
"step": 166
},
{
"epoch": 5.21875,
"grad_norm": 1.3562739084585815,
"learning_rate": 7.779605263157895e-06,
"loss": 2.0586,
"step": 167
},
{
"epoch": 5.25,
"grad_norm": 1.2277460241295945,
"learning_rate": 7.763157894736843e-06,
"loss": 1.7441,
"step": 168
},
{
"epoch": 5.28125,
"grad_norm": 1.3433735977540853,
"learning_rate": 7.746710526315791e-06,
"loss": 2.043,
"step": 169
},
{
"epoch": 5.3125,
"grad_norm": 1.5745506941777736,
"learning_rate": 7.730263157894737e-06,
"loss": 2.041,
"step": 170
},
{
"epoch": 5.34375,
"grad_norm": 1.466403250520866,
"learning_rate": 7.713815789473686e-06,
"loss": 2.1289,
"step": 171
},
{
"epoch": 5.375,
"grad_norm": 1.3116428932247919,
"learning_rate": 7.697368421052632e-06,
"loss": 1.9102,
"step": 172
},
{
"epoch": 5.40625,
"grad_norm": 1.41620004981607,
"learning_rate": 7.680921052631578e-06,
"loss": 1.9766,
"step": 173
},
{
"epoch": 5.4375,
"grad_norm": 1.2068214874535954,
"learning_rate": 7.664473684210527e-06,
"loss": 1.7871,
"step": 174
},
{
"epoch": 5.46875,
"grad_norm": 1.3520693075990964,
"learning_rate": 7.648026315789475e-06,
"loss": 1.9141,
"step": 175
},
{
"epoch": 5.5,
"grad_norm": 1.2305509194591682,
"learning_rate": 7.631578947368423e-06,
"loss": 1.8008,
"step": 176
},
{
"epoch": 5.53125,
"grad_norm": 1.349983596276008,
"learning_rate": 7.615131578947369e-06,
"loss": 1.7227,
"step": 177
},
{
"epoch": 5.5625,
"grad_norm": 1.4158833046390478,
"learning_rate": 7.598684210526316e-06,
"loss": 2.002,
"step": 178
},
{
"epoch": 5.59375,
"grad_norm": 1.2163070728239471,
"learning_rate": 7.582236842105264e-06,
"loss": 1.918,
"step": 179
},
{
"epoch": 5.625,
"grad_norm": 1.2891781817034034,
"learning_rate": 7.565789473684211e-06,
"loss": 1.752,
"step": 180
},
{
"epoch": 5.65625,
"grad_norm": 1.2873813695474143,
"learning_rate": 7.549342105263159e-06,
"loss": 1.8574,
"step": 181
},
{
"epoch": 5.6875,
"grad_norm": 1.4129403193981556,
"learning_rate": 7.532894736842106e-06,
"loss": 2.1094,
"step": 182
},
{
"epoch": 5.71875,
"grad_norm": 1.272823109386593,
"learning_rate": 7.516447368421054e-06,
"loss": 1.7344,
"step": 183
},
{
"epoch": 5.75,
"grad_norm": 1.4755129897251515,
"learning_rate": 7.500000000000001e-06,
"loss": 2.0078,
"step": 184
},
{
"epoch": 5.78125,
"grad_norm": 1.2740980855037742,
"learning_rate": 7.4835526315789475e-06,
"loss": 1.873,
"step": 185
},
{
"epoch": 5.8125,
"grad_norm": 1.23447908173342,
"learning_rate": 7.467105263157896e-06,
"loss": 1.8242,
"step": 186
},
{
"epoch": 5.84375,
"grad_norm": 1.3585314479888622,
"learning_rate": 7.450657894736842e-06,
"loss": 1.8633,
"step": 187
},
{
"epoch": 5.875,
"grad_norm": 1.2678054921308055,
"learning_rate": 7.43421052631579e-06,
"loss": 1.8125,
"step": 188
},
{
"epoch": 5.90625,
"grad_norm": 1.3108222757243544,
"learning_rate": 7.4177631578947374e-06,
"loss": 1.6895,
"step": 189
},
{
"epoch": 5.9375,
"grad_norm": 1.4562794514992154,
"learning_rate": 7.4013157894736856e-06,
"loss": 1.9023,
"step": 190
},
{
"epoch": 5.96875,
"grad_norm": 1.2807964774559686,
"learning_rate": 7.384868421052632e-06,
"loss": 1.9629,
"step": 191
},
{
"epoch": 6.0,
"grad_norm": 1.340863110638616,
"learning_rate": 7.368421052631579e-06,
"loss": 1.9531,
"step": 192
},
{
"epoch": 6.03125,
"grad_norm": 1.2127416869589702,
"learning_rate": 7.351973684210527e-06,
"loss": 1.8223,
"step": 193
},
{
"epoch": 6.0625,
"grad_norm": 1.3467940572703827,
"learning_rate": 7.335526315789474e-06,
"loss": 2.0371,
"step": 194
},
{
"epoch": 6.09375,
"grad_norm": 1.1536204273784294,
"learning_rate": 7.319078947368422e-06,
"loss": 1.584,
"step": 195
},
{
"epoch": 6.125,
"grad_norm": 1.2729596706853674,
"learning_rate": 7.302631578947369e-06,
"loss": 1.8203,
"step": 196
},
{
"epoch": 6.15625,
"grad_norm": 1.1709559405981904,
"learning_rate": 7.286184210526316e-06,
"loss": 1.6777,
"step": 197
},
{
"epoch": 6.1875,
"grad_norm": 1.352052761699238,
"learning_rate": 7.269736842105264e-06,
"loss": 1.9102,
"step": 198
},
{
"epoch": 6.21875,
"grad_norm": 1.2750580445285065,
"learning_rate": 7.253289473684211e-06,
"loss": 1.7734,
"step": 199
},
{
"epoch": 6.25,
"grad_norm": 1.2939217003267616,
"learning_rate": 7.236842105263158e-06,
"loss": 1.791,
"step": 200
},
{
"epoch": 6.28125,
"grad_norm": 1.2650695751339902,
"learning_rate": 7.220394736842106e-06,
"loss": 1.6094,
"step": 201
},
{
"epoch": 6.3125,
"grad_norm": 1.25464131412363,
"learning_rate": 7.203947368421054e-06,
"loss": 1.7402,
"step": 202
},
{
"epoch": 6.34375,
"grad_norm": 1.5497524942602627,
"learning_rate": 7.1875e-06,
"loss": 1.7734,
"step": 203
},
{
"epoch": 6.375,
"grad_norm": 1.2160427199624535,
"learning_rate": 7.1710526315789475e-06,
"loss": 1.7285,
"step": 204
},
{
"epoch": 6.40625,
"grad_norm": 1.3487818927806237,
"learning_rate": 7.154605263157896e-06,
"loss": 1.7402,
"step": 205
},
{
"epoch": 6.4375,
"grad_norm": 1.107072434898807,
"learning_rate": 7.138157894736842e-06,
"loss": 1.6641,
"step": 206
},
{
"epoch": 6.46875,
"grad_norm": 1.4016573341641314,
"learning_rate": 7.12171052631579e-06,
"loss": 2.1387,
"step": 207
},
{
"epoch": 6.5,
"grad_norm": 1.3392867039415794,
"learning_rate": 7.1052631578947375e-06,
"loss": 1.7852,
"step": 208
},
{
"epoch": 6.53125,
"grad_norm": 1.344829225483593,
"learning_rate": 7.088815789473686e-06,
"loss": 1.8262,
"step": 209
},
{
"epoch": 6.5625,
"grad_norm": 1.2901220099849333,
"learning_rate": 7.072368421052632e-06,
"loss": 1.7832,
"step": 210
},
{
"epoch": 6.59375,
"grad_norm": 1.2583202389216346,
"learning_rate": 7.055921052631579e-06,
"loss": 1.625,
"step": 211
},
{
"epoch": 6.625,
"grad_norm": 1.2024207284992958,
"learning_rate": 7.0394736842105274e-06,
"loss": 1.7324,
"step": 212
},
{
"epoch": 6.65625,
"grad_norm": 1.574981670155728,
"learning_rate": 7.023026315789474e-06,
"loss": 1.8496,
"step": 213
},
{
"epoch": 6.6875,
"grad_norm": 1.2969168811442906,
"learning_rate": 7.006578947368422e-06,
"loss": 1.5938,
"step": 214
},
{
"epoch": 6.71875,
"grad_norm": 1.1616206155336706,
"learning_rate": 6.990131578947369e-06,
"loss": 1.4629,
"step": 215
},
{
"epoch": 6.75,
"grad_norm": 1.365223546599706,
"learning_rate": 6.973684210526316e-06,
"loss": 1.8008,
"step": 216
},
{
"epoch": 6.78125,
"grad_norm": 1.3510596482406705,
"learning_rate": 6.957236842105264e-06,
"loss": 1.8281,
"step": 217
},
{
"epoch": 6.8125,
"grad_norm": 1.4694592813286227,
"learning_rate": 6.940789473684211e-06,
"loss": 1.7637,
"step": 218
},
{
"epoch": 6.84375,
"grad_norm": 1.4286299323547051,
"learning_rate": 6.924342105263158e-06,
"loss": 1.7031,
"step": 219
},
{
"epoch": 6.875,
"grad_norm": 1.5197759621356106,
"learning_rate": 6.907894736842106e-06,
"loss": 1.5879,
"step": 220
},
{
"epoch": 6.90625,
"grad_norm": 1.1308149311661615,
"learning_rate": 6.891447368421054e-06,
"loss": 1.666,
"step": 221
},
{
"epoch": 6.9375,
"grad_norm": 1.290793747756769,
"learning_rate": 6.875e-06,
"loss": 1.7852,
"step": 222
},
{
"epoch": 6.96875,
"grad_norm": 1.4260685025654767,
"learning_rate": 6.8585526315789475e-06,
"loss": 1.8496,
"step": 223
},
{
"epoch": 7.0,
"grad_norm": 1.2591429399622196,
"learning_rate": 6.842105263157896e-06,
"loss": 1.6543,
"step": 224
},
{
"epoch": 7.03125,
"grad_norm": 1.3838081743754846,
"learning_rate": 6.825657894736842e-06,
"loss": 1.8633,
"step": 225
},
{
"epoch": 7.0625,
"grad_norm": 1.3226514168347299,
"learning_rate": 6.80921052631579e-06,
"loss": 1.918,
"step": 226
},
{
"epoch": 7.09375,
"grad_norm": 1.119759607546033,
"learning_rate": 6.7927631578947375e-06,
"loss": 1.3574,
"step": 227
},
{
"epoch": 7.125,
"grad_norm": 1.1770895940221853,
"learning_rate": 6.776315789473686e-06,
"loss": 1.5879,
"step": 228
},
{
"epoch": 7.15625,
"grad_norm": 1.4013517475514878,
"learning_rate": 6.759868421052632e-06,
"loss": 1.916,
"step": 229
},
{
"epoch": 7.1875,
"grad_norm": 1.2035057060414645,
"learning_rate": 6.743421052631579e-06,
"loss": 1.4551,
"step": 230
},
{
"epoch": 7.21875,
"grad_norm": 1.3524206532170369,
"learning_rate": 6.7269736842105275e-06,
"loss": 1.5488,
"step": 231
},
{
"epoch": 7.25,
"grad_norm": 1.3000002404533175,
"learning_rate": 6.710526315789474e-06,
"loss": 1.6367,
"step": 232
},
{
"epoch": 7.28125,
"grad_norm": 1.3002929917889723,
"learning_rate": 6.694078947368422e-06,
"loss": 1.6387,
"step": 233
},
{
"epoch": 7.3125,
"grad_norm": 1.3198740119814931,
"learning_rate": 6.677631578947369e-06,
"loss": 1.6973,
"step": 234
},
{
"epoch": 7.34375,
"grad_norm": 1.3505488242950343,
"learning_rate": 6.661184210526316e-06,
"loss": 1.7246,
"step": 235
},
{
"epoch": 7.375,
"grad_norm": 1.087590027191493,
"learning_rate": 6.644736842105264e-06,
"loss": 1.3516,
"step": 236
},
{
"epoch": 7.40625,
"grad_norm": 1.2635273727752099,
"learning_rate": 6.62828947368421e-06,
"loss": 1.5234,
"step": 237
},
{
"epoch": 7.4375,
"grad_norm": 1.2982082251620062,
"learning_rate": 6.6118421052631584e-06,
"loss": 1.6328,
"step": 238
},
{
"epoch": 7.46875,
"grad_norm": 1.194402347892603,
"learning_rate": 6.595394736842106e-06,
"loss": 1.5547,
"step": 239
},
{
"epoch": 7.5,
"grad_norm": 1.3089950328485123,
"learning_rate": 6.578947368421054e-06,
"loss": 1.7637,
"step": 240
},
{
"epoch": 7.53125,
"grad_norm": 1.2762780422661464,
"learning_rate": 6.5625e-06,
"loss": 1.5586,
"step": 241
},
{
"epoch": 7.5625,
"grad_norm": 1.1284842098871226,
"learning_rate": 6.5460526315789476e-06,
"loss": 1.4492,
"step": 242
},
{
"epoch": 7.59375,
"grad_norm": 1.529655443376855,
"learning_rate": 6.529605263157896e-06,
"loss": 1.7422,
"step": 243
},
{
"epoch": 7.625,
"grad_norm": 1.1665841904157732,
"learning_rate": 6.513157894736842e-06,
"loss": 1.5293,
"step": 244
},
{
"epoch": 7.65625,
"grad_norm": 1.1960803290051991,
"learning_rate": 6.49671052631579e-06,
"loss": 1.498,
"step": 245
},
{
"epoch": 7.6875,
"grad_norm": 1.03923554987526,
"learning_rate": 6.4802631578947375e-06,
"loss": 1.3477,
"step": 246
},
{
"epoch": 7.71875,
"grad_norm": 1.3337104732841285,
"learning_rate": 6.463815789473686e-06,
"loss": 1.918,
"step": 247
},
{
"epoch": 7.75,
"grad_norm": 1.2816634472422972,
"learning_rate": 6.447368421052632e-06,
"loss": 1.7285,
"step": 248
},
{
"epoch": 7.78125,
"grad_norm": 1.3927598479283319,
"learning_rate": 6.430921052631579e-06,
"loss": 1.7148,
"step": 249
},
{
"epoch": 7.8125,
"grad_norm": 1.1575457380088763,
"learning_rate": 6.4144736842105275e-06,
"loss": 1.4395,
"step": 250
},
{
"epoch": 7.84375,
"grad_norm": 1.3948540383365446,
"learning_rate": 6.398026315789474e-06,
"loss": 1.7207,
"step": 251
},
{
"epoch": 7.875,
"grad_norm": 1.1846914337228318,
"learning_rate": 6.381578947368422e-06,
"loss": 1.6621,
"step": 252
},
{
"epoch": 7.90625,
"grad_norm": 1.3729206538265337,
"learning_rate": 6.3651315789473685e-06,
"loss": 1.8105,
"step": 253
},
{
"epoch": 7.9375,
"grad_norm": 1.092566362043007,
"learning_rate": 6.348684210526316e-06,
"loss": 1.5332,
"step": 254
},
{
"epoch": 7.96875,
"grad_norm": 1.1938075771886005,
"learning_rate": 6.332236842105264e-06,
"loss": 1.5332,
"step": 255
},
{
"epoch": 8.0,
"grad_norm": 1.1884574116970386,
"learning_rate": 6.31578947368421e-06,
"loss": 1.6016,
"step": 256
},
{
"epoch": 8.03125,
"grad_norm": 1.2323040477702536,
"learning_rate": 6.2993421052631585e-06,
"loss": 1.7051,
"step": 257
},
{
"epoch": 8.0625,
"grad_norm": 1.1826155398481955,
"learning_rate": 6.282894736842106e-06,
"loss": 1.4453,
"step": 258
},
{
"epoch": 8.09375,
"grad_norm": 1.4256490905240415,
"learning_rate": 6.266447368421054e-06,
"loss": 2.0039,
"step": 259
},
{
"epoch": 8.125,
"grad_norm": 1.137042790902281,
"learning_rate": 6.25e-06,
"loss": 1.4004,
"step": 260
},
{
"epoch": 8.15625,
"grad_norm": 1.1547256937707602,
"learning_rate": 6.233552631578948e-06,
"loss": 1.4336,
"step": 261
},
{
"epoch": 8.1875,
"grad_norm": 1.3234819920803873,
"learning_rate": 6.217105263157896e-06,
"loss": 1.7266,
"step": 262
},
{
"epoch": 8.21875,
"grad_norm": 1.1223848680889128,
"learning_rate": 6.200657894736842e-06,
"loss": 1.4199,
"step": 263
},
{
"epoch": 8.25,
"grad_norm": 1.1469925068381117,
"learning_rate": 6.18421052631579e-06,
"loss": 1.4414,
"step": 264
},
{
"epoch": 8.28125,
"grad_norm": 1.2977669850108717,
"learning_rate": 6.1677631578947376e-06,
"loss": 1.6523,
"step": 265
},
{
"epoch": 8.3125,
"grad_norm": 1.4735184954231604,
"learning_rate": 6.151315789473685e-06,
"loss": 1.8223,
"step": 266
},
{
"epoch": 8.34375,
"grad_norm": 1.040621746376745,
"learning_rate": 6.134868421052632e-06,
"loss": 1.4766,
"step": 267
},
{
"epoch": 8.375,
"grad_norm": 1.34186018093504,
"learning_rate": 6.118421052631579e-06,
"loss": 1.8047,
"step": 268
},
{
"epoch": 8.40625,
"grad_norm": 1.1839311529004948,
"learning_rate": 6.101973684210527e-06,
"loss": 1.4316,
"step": 269
},
{
"epoch": 8.4375,
"grad_norm": 1.2199376693433344,
"learning_rate": 6.085526315789474e-06,
"loss": 1.543,
"step": 270
},
{
"epoch": 8.46875,
"grad_norm": 1.2316121100991364,
"learning_rate": 6.069078947368422e-06,
"loss": 1.5156,
"step": 271
},
{
"epoch": 8.5,
"grad_norm": 1.3823753070802702,
"learning_rate": 6.0526315789473685e-06,
"loss": 1.5879,
"step": 272
},
{
"epoch": 8.53125,
"grad_norm": 1.32128273050164,
"learning_rate": 6.036184210526316e-06,
"loss": 1.5781,
"step": 273
},
{
"epoch": 8.5625,
"grad_norm": 1.3424113003624236,
"learning_rate": 6.019736842105264e-06,
"loss": 1.748,
"step": 274
},
{
"epoch": 8.59375,
"grad_norm": 1.1466546955884545,
"learning_rate": 6.00328947368421e-06,
"loss": 1.3809,
"step": 275
},
{
"epoch": 8.625,
"grad_norm": 1.2076133131499247,
"learning_rate": 5.9868421052631585e-06,
"loss": 1.6699,
"step": 276
},
{
"epoch": 8.65625,
"grad_norm": 1.2213610720940913,
"learning_rate": 5.970394736842106e-06,
"loss": 1.3398,
"step": 277
},
{
"epoch": 8.6875,
"grad_norm": 0.9935233872059256,
"learning_rate": 5.953947368421054e-06,
"loss": 1.2568,
"step": 278
},
{
"epoch": 8.71875,
"grad_norm": 1.2865221082169063,
"learning_rate": 5.9375e-06,
"loss": 1.4844,
"step": 279
},
{
"epoch": 8.75,
"grad_norm": 1.3289498848746482,
"learning_rate": 5.921052631578948e-06,
"loss": 1.6348,
"step": 280
},
{
"epoch": 8.78125,
"grad_norm": 1.1164359514707043,
"learning_rate": 5.904605263157896e-06,
"loss": 1.3809,
"step": 281
},
{
"epoch": 8.8125,
"grad_norm": 1.2970501761466038,
"learning_rate": 5.888157894736842e-06,
"loss": 1.4102,
"step": 282
},
{
"epoch": 8.84375,
"grad_norm": 1.3343317408525743,
"learning_rate": 5.87171052631579e-06,
"loss": 1.6523,
"step": 283
},
{
"epoch": 8.875,
"grad_norm": 1.2378422677250207,
"learning_rate": 5.855263157894738e-06,
"loss": 1.3047,
"step": 284
},
{
"epoch": 8.90625,
"grad_norm": 1.119983613468547,
"learning_rate": 5.838815789473685e-06,
"loss": 1.4043,
"step": 285
},
{
"epoch": 8.9375,
"grad_norm": 1.1996702075618084,
"learning_rate": 5.822368421052632e-06,
"loss": 1.5703,
"step": 286
},
{
"epoch": 8.96875,
"grad_norm": 1.0778663070491803,
"learning_rate": 5.805921052631579e-06,
"loss": 1.3828,
"step": 287
},
{
"epoch": 9.0,
"grad_norm": 1.068292333670538,
"learning_rate": 5.789473684210527e-06,
"loss": 1.4727,
"step": 288
},
{
"epoch": 9.03125,
"grad_norm": 1.2192159062465524,
"learning_rate": 5.773026315789474e-06,
"loss": 1.5195,
"step": 289
},
{
"epoch": 9.0625,
"grad_norm": 1.3481737413765114,
"learning_rate": 5.756578947368422e-06,
"loss": 1.6465,
"step": 290
},
{
"epoch": 9.09375,
"grad_norm": 1.3284157045718723,
"learning_rate": 5.7401315789473685e-06,
"loss": 1.668,
"step": 291
},
{
"epoch": 9.125,
"grad_norm": 1.1523606928804837,
"learning_rate": 5.723684210526316e-06,
"loss": 1.3711,
"step": 292
},
{
"epoch": 9.15625,
"grad_norm": 1.2624009140169858,
"learning_rate": 5.707236842105264e-06,
"loss": 1.4805,
"step": 293
},
{
"epoch": 9.1875,
"grad_norm": 1.1974249834174664,
"learning_rate": 5.69078947368421e-06,
"loss": 1.416,
"step": 294
},
{
"epoch": 9.21875,
"grad_norm": 1.0880104341393793,
"learning_rate": 5.6743421052631585e-06,
"loss": 1.416,
"step": 295
},
{
"epoch": 9.25,
"grad_norm": 1.0648083314607524,
"learning_rate": 5.657894736842106e-06,
"loss": 1.4922,
"step": 296
},
{
"epoch": 9.28125,
"grad_norm": 1.3924241155835761,
"learning_rate": 5.641447368421054e-06,
"loss": 1.8535,
"step": 297
},
{
"epoch": 9.3125,
"grad_norm": 1.1997511105605825,
"learning_rate": 5.625e-06,
"loss": 1.5508,
"step": 298
},
{
"epoch": 9.34375,
"grad_norm": 0.9991377489525408,
"learning_rate": 5.608552631578948e-06,
"loss": 1.2793,
"step": 299
},
{
"epoch": 9.375,
"grad_norm": 0.9245773551113274,
"learning_rate": 5.592105263157896e-06,
"loss": 1.1406,
"step": 300
},
{
"epoch": 9.40625,
"grad_norm": 1.3441639892433364,
"learning_rate": 5.575657894736842e-06,
"loss": 1.8691,
"step": 301
},
{
"epoch": 9.4375,
"grad_norm": 1.2026188224693601,
"learning_rate": 5.55921052631579e-06,
"loss": 1.3486,
"step": 302
},
{
"epoch": 9.46875,
"grad_norm": 1.1016342505763965,
"learning_rate": 5.542763157894737e-06,
"loss": 1.3008,
"step": 303
},
{
"epoch": 9.5,
"grad_norm": 1.0605253903830034,
"learning_rate": 5.526315789473685e-06,
"loss": 1.3301,
"step": 304
},
{
"epoch": 9.53125,
"grad_norm": 1.2775271089840106,
"learning_rate": 5.509868421052632e-06,
"loss": 1.5605,
"step": 305
},
{
"epoch": 9.5625,
"grad_norm": 1.1104372435375556,
"learning_rate": 5.493421052631579e-06,
"loss": 1.3984,
"step": 306
},
{
"epoch": 9.59375,
"grad_norm": 1.1918158892068837,
"learning_rate": 5.476973684210527e-06,
"loss": 1.3594,
"step": 307
},
{
"epoch": 9.625,
"grad_norm": 1.06273551473133,
"learning_rate": 5.460526315789474e-06,
"loss": 1.3809,
"step": 308
},
{
"epoch": 9.65625,
"grad_norm": 1.2788595464616823,
"learning_rate": 5.444078947368422e-06,
"loss": 1.6016,
"step": 309
},
{
"epoch": 9.6875,
"grad_norm": 1.2042036204677522,
"learning_rate": 5.4276315789473686e-06,
"loss": 1.334,
"step": 310
},
{
"epoch": 9.71875,
"grad_norm": 1.118364091577098,
"learning_rate": 5.411184210526316e-06,
"loss": 1.4043,
"step": 311
},
{
"epoch": 9.75,
"grad_norm": 1.2565371105509984,
"learning_rate": 5.394736842105264e-06,
"loss": 1.4629,
"step": 312
},
{
"epoch": 9.78125,
"grad_norm": 1.1689553385554297,
"learning_rate": 5.37828947368421e-06,
"loss": 1.5547,
"step": 313
},
{
"epoch": 9.8125,
"grad_norm": 1.0306781671470933,
"learning_rate": 5.3618421052631585e-06,
"loss": 1.3008,
"step": 314
},
{
"epoch": 9.84375,
"grad_norm": 1.1832250443460393,
"learning_rate": 5.345394736842106e-06,
"loss": 1.6035,
"step": 315
},
{
"epoch": 9.875,
"grad_norm": 1.204745943784607,
"learning_rate": 5.328947368421054e-06,
"loss": 1.3887,
"step": 316
},
{
"epoch": 9.90625,
"grad_norm": 1.1435805601154991,
"learning_rate": 5.3125e-06,
"loss": 1.3242,
"step": 317
},
{
"epoch": 9.9375,
"grad_norm": 1.1279236877871361,
"learning_rate": 5.296052631578948e-06,
"loss": 1.3496,
"step": 318
},
{
"epoch": 9.96875,
"grad_norm": 1.206055707255631,
"learning_rate": 5.279605263157895e-06,
"loss": 1.4844,
"step": 319
},
{
"epoch": 10.0,
"grad_norm": 1.0754848156346868,
"learning_rate": 5.263157894736842e-06,
"loss": 1.3359,
"step": 320
},
{
"epoch": 10.03125,
"grad_norm": 1.2154135689523968,
"learning_rate": 5.24671052631579e-06,
"loss": 1.5293,
"step": 321
},
{
"epoch": 10.0625,
"grad_norm": 1.129676688837292,
"learning_rate": 5.230263157894737e-06,
"loss": 1.3799,
"step": 322
},
{
"epoch": 10.09375,
"grad_norm": 1.1816669829377744,
"learning_rate": 5.213815789473685e-06,
"loss": 1.4102,
"step": 323
},
{
"epoch": 10.125,
"grad_norm": 1.2594276176240513,
"learning_rate": 5.197368421052632e-06,
"loss": 1.377,
"step": 324
},
{
"epoch": 10.15625,
"grad_norm": 1.008987196838564,
"learning_rate": 5.180921052631579e-06,
"loss": 1.2754,
"step": 325
},
{
"epoch": 10.1875,
"grad_norm": 1.0077078292816104,
"learning_rate": 5.164473684210527e-06,
"loss": 1.2441,
"step": 326
},
{
"epoch": 10.21875,
"grad_norm": 1.1493149526564261,
"learning_rate": 5.148026315789474e-06,
"loss": 1.5977,
"step": 327
},
{
"epoch": 10.25,
"grad_norm": 1.21245285652362,
"learning_rate": 5.131578947368422e-06,
"loss": 1.2969,
"step": 328
},
{
"epoch": 10.28125,
"grad_norm": 1.1945879462228663,
"learning_rate": 5.115131578947369e-06,
"loss": 1.5371,
"step": 329
},
{
"epoch": 10.3125,
"grad_norm": 1.2197917228914175,
"learning_rate": 5.098684210526316e-06,
"loss": 1.5391,
"step": 330
},
{
"epoch": 10.34375,
"grad_norm": 1.3025833566173235,
"learning_rate": 5.082236842105264e-06,
"loss": 1.5586,
"step": 331
},
{
"epoch": 10.375,
"grad_norm": 1.186750044727453,
"learning_rate": 5.0657894736842104e-06,
"loss": 1.4277,
"step": 332
},
{
"epoch": 10.40625,
"grad_norm": 1.3934048340733807,
"learning_rate": 5.0493421052631586e-06,
"loss": 1.6484,
"step": 333
},
{
"epoch": 10.4375,
"grad_norm": 1.1105348891949298,
"learning_rate": 5.032894736842106e-06,
"loss": 1.2539,
"step": 334
},
{
"epoch": 10.46875,
"grad_norm": 1.1506739890579292,
"learning_rate": 5.016447368421053e-06,
"loss": 1.2949,
"step": 335
},
{
"epoch": 10.5,
"grad_norm": 1.0957711868381537,
"learning_rate": 5e-06,
"loss": 1.2129,
"step": 336
},
{
"epoch": 10.53125,
"grad_norm": 1.1175328217521991,
"learning_rate": 4.983552631578948e-06,
"loss": 1.5078,
"step": 337
},
{
"epoch": 10.5625,
"grad_norm": 1.1896931608496566,
"learning_rate": 4.967105263157895e-06,
"loss": 1.418,
"step": 338
},
{
"epoch": 10.59375,
"grad_norm": 1.1953282095258284,
"learning_rate": 4.950657894736843e-06,
"loss": 1.4043,
"step": 339
},
{
"epoch": 10.625,
"grad_norm": 1.0534650726069181,
"learning_rate": 4.9342105263157895e-06,
"loss": 1.1973,
"step": 340
},
{
"epoch": 10.65625,
"grad_norm": 1.0926845658185267,
"learning_rate": 4.917763157894737e-06,
"loss": 1.3262,
"step": 341
},
{
"epoch": 10.6875,
"grad_norm": 1.1569298118442002,
"learning_rate": 4.901315789473685e-06,
"loss": 1.3516,
"step": 342
},
{
"epoch": 10.71875,
"grad_norm": 1.118753536452266,
"learning_rate": 4.884868421052632e-06,
"loss": 1.2559,
"step": 343
},
{
"epoch": 10.75,
"grad_norm": 1.165228582996436,
"learning_rate": 4.8684210526315795e-06,
"loss": 1.377,
"step": 344
},
{
"epoch": 10.78125,
"grad_norm": 1.2039659932149558,
"learning_rate": 4.851973684210527e-06,
"loss": 1.3125,
"step": 345
},
{
"epoch": 10.8125,
"grad_norm": 1.1220609308798875,
"learning_rate": 4.835526315789474e-06,
"loss": 1.4238,
"step": 346
},
{
"epoch": 10.84375,
"grad_norm": 1.2507059658078532,
"learning_rate": 4.819078947368421e-06,
"loss": 1.4609,
"step": 347
},
{
"epoch": 10.875,
"grad_norm": 1.3271056298248607,
"learning_rate": 4.802631578947369e-06,
"loss": 1.6504,
"step": 348
},
{
"epoch": 10.90625,
"grad_norm": 1.0787012990106282,
"learning_rate": 4.786184210526316e-06,
"loss": 1.2803,
"step": 349
},
{
"epoch": 10.9375,
"grad_norm": 1.154705302242999,
"learning_rate": 4.769736842105264e-06,
"loss": 1.3359,
"step": 350
},
{
"epoch": 10.96875,
"grad_norm": 1.0937048750337814,
"learning_rate": 4.753289473684211e-06,
"loss": 1.2041,
"step": 351
},
{
"epoch": 11.0,
"grad_norm": 1.1617527213309744,
"learning_rate": 4.736842105263158e-06,
"loss": 1.3711,
"step": 352
},
{
"epoch": 11.03125,
"grad_norm": 1.1883830201473682,
"learning_rate": 4.720394736842106e-06,
"loss": 1.5977,
"step": 353
},
{
"epoch": 11.0625,
"grad_norm": 1.0139784705048083,
"learning_rate": 4.703947368421053e-06,
"loss": 1.2891,
"step": 354
},
{
"epoch": 11.09375,
"grad_norm": 1.2579898083868604,
"learning_rate": 4.6875000000000004e-06,
"loss": 1.5254,
"step": 355
},
{
"epoch": 11.125,
"grad_norm": 1.1725513734302704,
"learning_rate": 4.671052631578948e-06,
"loss": 1.373,
"step": 356
},
{
"epoch": 11.15625,
"grad_norm": 1.1987413898195225,
"learning_rate": 4.654605263157895e-06,
"loss": 1.4863,
"step": 357
},
{
"epoch": 11.1875,
"grad_norm": 1.093239113754782,
"learning_rate": 4.638157894736843e-06,
"loss": 1.4727,
"step": 358
},
{
"epoch": 11.21875,
"grad_norm": 1.1208003088492746,
"learning_rate": 4.6217105263157896e-06,
"loss": 1.332,
"step": 359
},
{
"epoch": 11.25,
"grad_norm": 1.3151133748590742,
"learning_rate": 4.605263157894737e-06,
"loss": 1.5781,
"step": 360
},
{
"epoch": 11.28125,
"grad_norm": 1.0342040777680257,
"learning_rate": 4.588815789473685e-06,
"loss": 1.3066,
"step": 361
},
{
"epoch": 11.3125,
"grad_norm": 1.040927136579576,
"learning_rate": 4.572368421052632e-06,
"loss": 1.377,
"step": 362
},
{
"epoch": 11.34375,
"grad_norm": 1.1625272195538854,
"learning_rate": 4.5559210526315795e-06,
"loss": 1.4863,
"step": 363
},
{
"epoch": 11.375,
"grad_norm": 1.2739101469375733,
"learning_rate": 4.539473684210527e-06,
"loss": 1.418,
"step": 364
},
{
"epoch": 11.40625,
"grad_norm": 0.9656151744390092,
"learning_rate": 4.523026315789474e-06,
"loss": 1.0996,
"step": 365
},
{
"epoch": 11.4375,
"grad_norm": 1.1015967438212477,
"learning_rate": 4.506578947368421e-06,
"loss": 1.2646,
"step": 366
},
{
"epoch": 11.46875,
"grad_norm": 1.2010035878113032,
"learning_rate": 4.490131578947369e-06,
"loss": 1.3281,
"step": 367
},
{
"epoch": 11.5,
"grad_norm": 1.1519349789068691,
"learning_rate": 4.473684210526316e-06,
"loss": 1.2158,
"step": 368
},
{
"epoch": 11.53125,
"grad_norm": 1.1196243544282645,
"learning_rate": 4.457236842105264e-06,
"loss": 1.2852,
"step": 369
},
{
"epoch": 11.5625,
"grad_norm": 1.0907715090076417,
"learning_rate": 4.440789473684211e-06,
"loss": 1.2773,
"step": 370
},
{
"epoch": 11.59375,
"grad_norm": 0.9841441198723676,
"learning_rate": 4.424342105263158e-06,
"loss": 1.2598,
"step": 371
},
{
"epoch": 11.625,
"grad_norm": 1.1345770150297678,
"learning_rate": 4.407894736842105e-06,
"loss": 1.4023,
"step": 372
},
{
"epoch": 11.65625,
"grad_norm": 1.1185447421477923,
"learning_rate": 4.391447368421053e-06,
"loss": 1.3691,
"step": 373
},
{
"epoch": 11.6875,
"grad_norm": 1.1540730230879181,
"learning_rate": 4.3750000000000005e-06,
"loss": 1.3203,
"step": 374
},
{
"epoch": 11.71875,
"grad_norm": 1.184669271964522,
"learning_rate": 4.358552631578948e-06,
"loss": 1.1768,
"step": 375
},
{
"epoch": 11.75,
"grad_norm": 1.1637275265772447,
"learning_rate": 4.342105263157895e-06,
"loss": 1.4512,
"step": 376
},
{
"epoch": 11.78125,
"grad_norm": 1.0358827548745186,
"learning_rate": 4.325657894736842e-06,
"loss": 1.2461,
"step": 377
},
{
"epoch": 11.8125,
"grad_norm": 1.1128314718491639,
"learning_rate": 4.30921052631579e-06,
"loss": 1.3018,
"step": 378
},
{
"epoch": 11.84375,
"grad_norm": 1.0161634189398387,
"learning_rate": 4.292763157894737e-06,
"loss": 1.1387,
"step": 379
},
{
"epoch": 11.875,
"grad_norm": 1.4521991968396184,
"learning_rate": 4.276315789473684e-06,
"loss": 1.5,
"step": 380
},
{
"epoch": 11.90625,
"grad_norm": 1.1899659944122705,
"learning_rate": 4.259868421052632e-06,
"loss": 1.3926,
"step": 381
},
{
"epoch": 11.9375,
"grad_norm": 1.1121528138192258,
"learning_rate": 4.2434210526315796e-06,
"loss": 1.207,
"step": 382
},
{
"epoch": 11.96875,
"grad_norm": 1.0588783355137454,
"learning_rate": 4.226973684210527e-06,
"loss": 1.1055,
"step": 383
},
{
"epoch": 12.0,
"grad_norm": 1.1614232418764687,
"learning_rate": 4.210526315789474e-06,
"loss": 1.4883,
"step": 384
},
{
"epoch": 12.03125,
"grad_norm": 1.0746097740254226,
"learning_rate": 4.194078947368421e-06,
"loss": 1.2393,
"step": 385
},
{
"epoch": 12.0625,
"grad_norm": 0.9854229757382881,
"learning_rate": 4.177631578947369e-06,
"loss": 1.123,
"step": 386
},
{
"epoch": 12.09375,
"grad_norm": 1.1065232705122436,
"learning_rate": 4.161184210526316e-06,
"loss": 1.3027,
"step": 387
},
{
"epoch": 12.125,
"grad_norm": 1.2394820431877753,
"learning_rate": 4.144736842105263e-06,
"loss": 1.4453,
"step": 388
},
{
"epoch": 12.15625,
"grad_norm": 1.283661056628274,
"learning_rate": 4.128289473684211e-06,
"loss": 1.416,
"step": 389
},
{
"epoch": 12.1875,
"grad_norm": 0.9969260727592318,
"learning_rate": 4.111842105263158e-06,
"loss": 1.1445,
"step": 390
},
{
"epoch": 12.21875,
"grad_norm": 1.1882926090414414,
"learning_rate": 4.095394736842105e-06,
"loss": 1.4688,
"step": 391
},
{
"epoch": 12.25,
"grad_norm": 1.0949407531874138,
"learning_rate": 4.078947368421053e-06,
"loss": 1.1846,
"step": 392
},
{
"epoch": 12.28125,
"grad_norm": 1.1279581192159158,
"learning_rate": 4.0625000000000005e-06,
"loss": 1.4238,
"step": 393
},
{
"epoch": 12.3125,
"grad_norm": 1.0976208579632025,
"learning_rate": 4.046052631578948e-06,
"loss": 1.2354,
"step": 394
},
{
"epoch": 12.34375,
"grad_norm": 1.047171336883935,
"learning_rate": 4.029605263157895e-06,
"loss": 1.1592,
"step": 395
},
{
"epoch": 12.375,
"grad_norm": 1.0235369257101183,
"learning_rate": 4.013157894736842e-06,
"loss": 1.1787,
"step": 396
},
{
"epoch": 12.40625,
"grad_norm": 1.1017349959377196,
"learning_rate": 3.99671052631579e-06,
"loss": 1.1836,
"step": 397
},
{
"epoch": 12.4375,
"grad_norm": 1.2601490910061588,
"learning_rate": 3.980263157894737e-06,
"loss": 1.5059,
"step": 398
},
{
"epoch": 12.46875,
"grad_norm": 1.1846034199737945,
"learning_rate": 3.963815789473684e-06,
"loss": 1.4277,
"step": 399
},
{
"epoch": 12.5,
"grad_norm": 1.1414440302505462,
"learning_rate": 3.947368421052632e-06,
"loss": 1.3496,
"step": 400
},
{
"epoch": 12.53125,
"grad_norm": 1.1382135616662248,
"learning_rate": 3.93092105263158e-06,
"loss": 1.3652,
"step": 401
},
{
"epoch": 12.5625,
"grad_norm": 1.0393915037961405,
"learning_rate": 3.914473684210527e-06,
"loss": 1.21,
"step": 402
},
{
"epoch": 12.59375,
"grad_norm": 1.1448568792854905,
"learning_rate": 3.898026315789474e-06,
"loss": 1.3174,
"step": 403
},
{
"epoch": 12.625,
"grad_norm": 1.0592051048429247,
"learning_rate": 3.8815789473684214e-06,
"loss": 1.2021,
"step": 404
},
{
"epoch": 12.65625,
"grad_norm": 1.0218252432617492,
"learning_rate": 3.865131578947369e-06,
"loss": 1.1309,
"step": 405
},
{
"epoch": 12.6875,
"grad_norm": 1.19885665360683,
"learning_rate": 3.848684210526316e-06,
"loss": 1.4141,
"step": 406
},
{
"epoch": 12.71875,
"grad_norm": 1.2686967780371439,
"learning_rate": 3.832236842105263e-06,
"loss": 1.4121,
"step": 407
},
{
"epoch": 12.75,
"grad_norm": 1.209271788347019,
"learning_rate": 3.815789473684211e-06,
"loss": 1.3906,
"step": 408
},
{
"epoch": 12.78125,
"grad_norm": 1.0673063533229126,
"learning_rate": 3.799342105263158e-06,
"loss": 1.2637,
"step": 409
},
{
"epoch": 12.8125,
"grad_norm": 0.9011876750636091,
"learning_rate": 3.7828947368421055e-06,
"loss": 1.0303,
"step": 410
},
{
"epoch": 12.84375,
"grad_norm": 1.082837212073044,
"learning_rate": 3.766447368421053e-06,
"loss": 1.2461,
"step": 411
},
{
"epoch": 12.875,
"grad_norm": 1.100263665438574,
"learning_rate": 3.7500000000000005e-06,
"loss": 1.249,
"step": 412
},
{
"epoch": 12.90625,
"grad_norm": 1.0885744676023275,
"learning_rate": 3.733552631578948e-06,
"loss": 1.3848,
"step": 413
},
{
"epoch": 12.9375,
"grad_norm": 1.3329324019634943,
"learning_rate": 3.717105263157895e-06,
"loss": 1.4492,
"step": 414
},
{
"epoch": 12.96875,
"grad_norm": 1.3882784181575505,
"learning_rate": 3.7006578947368428e-06,
"loss": 1.6699,
"step": 415
},
{
"epoch": 13.0,
"grad_norm": 1.0716251354423374,
"learning_rate": 3.6842105263157896e-06,
"loss": 1.2139,
"step": 416
},
{
"epoch": 13.03125,
"grad_norm": 1.287986851928492,
"learning_rate": 3.667763157894737e-06,
"loss": 1.5117,
"step": 417
},
{
"epoch": 13.0625,
"grad_norm": 1.0840412540341369,
"learning_rate": 3.6513157894736846e-06,
"loss": 1.3145,
"step": 418
},
{
"epoch": 13.09375,
"grad_norm": 1.1037476377552207,
"learning_rate": 3.634868421052632e-06,
"loss": 1.2344,
"step": 419
},
{
"epoch": 13.125,
"grad_norm": 1.0800076547795563,
"learning_rate": 3.618421052631579e-06,
"loss": 1.2266,
"step": 420
},
{
"epoch": 13.15625,
"grad_norm": 0.9998065477775393,
"learning_rate": 3.601973684210527e-06,
"loss": 1.2285,
"step": 421
},
{
"epoch": 13.1875,
"grad_norm": 1.175154093974312,
"learning_rate": 3.5855263157894737e-06,
"loss": 1.2109,
"step": 422
},
{
"epoch": 13.21875,
"grad_norm": 1.0116582403798422,
"learning_rate": 3.569078947368421e-06,
"loss": 1.2529,
"step": 423
},
{
"epoch": 13.25,
"grad_norm": 1.202897202439205,
"learning_rate": 3.5526315789473687e-06,
"loss": 1.4688,
"step": 424
},
{
"epoch": 13.28125,
"grad_norm": 1.004145952160525,
"learning_rate": 3.536184210526316e-06,
"loss": 1.1387,
"step": 425
},
{
"epoch": 13.3125,
"grad_norm": 1.0297417125754638,
"learning_rate": 3.5197368421052637e-06,
"loss": 1.1719,
"step": 426
},
{
"epoch": 13.34375,
"grad_norm": 1.07787501319166,
"learning_rate": 3.503289473684211e-06,
"loss": 1.3145,
"step": 427
},
{
"epoch": 13.375,
"grad_norm": 1.150503122039903,
"learning_rate": 3.486842105263158e-06,
"loss": 1.2793,
"step": 428
},
{
"epoch": 13.40625,
"grad_norm": 1.1739991668311942,
"learning_rate": 3.4703947368421056e-06,
"loss": 1.4102,
"step": 429
},
{
"epoch": 13.4375,
"grad_norm": 1.2153703174808637,
"learning_rate": 3.453947368421053e-06,
"loss": 1.2109,
"step": 430
},
{
"epoch": 13.46875,
"grad_norm": 1.1554295615769916,
"learning_rate": 3.4375e-06,
"loss": 1.3301,
"step": 431
},
{
"epoch": 13.5,
"grad_norm": 1.2893469286620574,
"learning_rate": 3.421052631578948e-06,
"loss": 1.3027,
"step": 432
},
{
"epoch": 13.53125,
"grad_norm": 1.0075597242681218,
"learning_rate": 3.404605263157895e-06,
"loss": 1.1182,
"step": 433
},
{
"epoch": 13.5625,
"grad_norm": 1.3509099608240223,
"learning_rate": 3.388157894736843e-06,
"loss": 1.3809,
"step": 434
},
{
"epoch": 13.59375,
"grad_norm": 1.069498050149035,
"learning_rate": 3.3717105263157897e-06,
"loss": 1.1846,
"step": 435
},
{
"epoch": 13.625,
"grad_norm": 1.114890453198544,
"learning_rate": 3.355263157894737e-06,
"loss": 1.1875,
"step": 436
},
{
"epoch": 13.65625,
"grad_norm": 1.129765979380437,
"learning_rate": 3.3388157894736847e-06,
"loss": 1.3633,
"step": 437
},
{
"epoch": 13.6875,
"grad_norm": 1.0998066220104334,
"learning_rate": 3.322368421052632e-06,
"loss": 1.2539,
"step": 438
},
{
"epoch": 13.71875,
"grad_norm": 0.9304831734458692,
"learning_rate": 3.3059210526315792e-06,
"loss": 1.0859,
"step": 439
},
{
"epoch": 13.75,
"grad_norm": 1.0694382341833957,
"learning_rate": 3.289473684210527e-06,
"loss": 1.3496,
"step": 440
},
{
"epoch": 13.78125,
"grad_norm": 1.1708315245441043,
"learning_rate": 3.2730263157894738e-06,
"loss": 1.3828,
"step": 441
},
{
"epoch": 13.8125,
"grad_norm": 1.0656716652628695,
"learning_rate": 3.256578947368421e-06,
"loss": 1.4023,
"step": 442
},
{
"epoch": 13.84375,
"grad_norm": 1.0607375221223125,
"learning_rate": 3.2401315789473688e-06,
"loss": 1.2344,
"step": 443
},
{
"epoch": 13.875,
"grad_norm": 1.2210966070357725,
"learning_rate": 3.223684210526316e-06,
"loss": 1.3945,
"step": 444
},
{
"epoch": 13.90625,
"grad_norm": 0.9014517324691765,
"learning_rate": 3.2072368421052637e-06,
"loss": 0.998,
"step": 445
},
{
"epoch": 13.9375,
"grad_norm": 1.125188484311246,
"learning_rate": 3.190789473684211e-06,
"loss": 1.2012,
"step": 446
},
{
"epoch": 13.96875,
"grad_norm": 1.0457511830501967,
"learning_rate": 3.174342105263158e-06,
"loss": 1.1953,
"step": 447
},
{
"epoch": 14.0,
"grad_norm": 1.2950505608894367,
"learning_rate": 3.157894736842105e-06,
"loss": 1.457,
"step": 448
},
{
"epoch": 14.03125,
"grad_norm": 1.170056852408912,
"learning_rate": 3.141447368421053e-06,
"loss": 1.3926,
"step": 449
},
{
"epoch": 14.0625,
"grad_norm": 1.2493616975451318,
"learning_rate": 3.125e-06,
"loss": 1.5918,
"step": 450
},
{
"epoch": 14.09375,
"grad_norm": 0.8888799675990482,
"learning_rate": 3.108552631578948e-06,
"loss": 0.9805,
"step": 451
},
{
"epoch": 14.125,
"grad_norm": 1.204210154016948,
"learning_rate": 3.092105263157895e-06,
"loss": 1.4355,
"step": 452
},
{
"epoch": 14.15625,
"grad_norm": 1.054523469321179,
"learning_rate": 3.0756578947368424e-06,
"loss": 1.2363,
"step": 453
},
{
"epoch": 14.1875,
"grad_norm": 0.9613996471643123,
"learning_rate": 3.0592105263157897e-06,
"loss": 1.1055,
"step": 454
},
{
"epoch": 14.21875,
"grad_norm": 1.0551733236211187,
"learning_rate": 3.042763157894737e-06,
"loss": 1.2793,
"step": 455
},
{
"epoch": 14.25,
"grad_norm": 0.9152832465100885,
"learning_rate": 3.0263157894736843e-06,
"loss": 0.9717,
"step": 456
},
{
"epoch": 14.28125,
"grad_norm": 0.9987134923379365,
"learning_rate": 3.009868421052632e-06,
"loss": 1.1562,
"step": 457
},
{
"epoch": 14.3125,
"grad_norm": 0.9956381989955094,
"learning_rate": 2.9934210526315792e-06,
"loss": 1.0273,
"step": 458
},
{
"epoch": 14.34375,
"grad_norm": 1.0938183028544668,
"learning_rate": 2.976973684210527e-06,
"loss": 1.25,
"step": 459
},
{
"epoch": 14.375,
"grad_norm": 1.1362098980479445,
"learning_rate": 2.960526315789474e-06,
"loss": 1.1943,
"step": 460
},
{
"epoch": 14.40625,
"grad_norm": 1.2643759923619813,
"learning_rate": 2.944078947368421e-06,
"loss": 1.4707,
"step": 461
},
{
"epoch": 14.4375,
"grad_norm": 0.9737358507532656,
"learning_rate": 2.927631578947369e-06,
"loss": 1.1211,
"step": 462
},
{
"epoch": 14.46875,
"grad_norm": 1.0496208877927968,
"learning_rate": 2.911184210526316e-06,
"loss": 1.1504,
"step": 463
},
{
"epoch": 14.5,
"grad_norm": 1.2256958010679917,
"learning_rate": 2.8947368421052634e-06,
"loss": 1.5234,
"step": 464
},
{
"epoch": 14.53125,
"grad_norm": 1.173766625463973,
"learning_rate": 2.878289473684211e-06,
"loss": 1.2148,
"step": 465
},
{
"epoch": 14.5625,
"grad_norm": 0.9930757226403226,
"learning_rate": 2.861842105263158e-06,
"loss": 1.1084,
"step": 466
},
{
"epoch": 14.59375,
"grad_norm": 0.8924636979654819,
"learning_rate": 2.845394736842105e-06,
"loss": 1.0645,
"step": 467
},
{
"epoch": 14.625,
"grad_norm": 1.0071866945186874,
"learning_rate": 2.828947368421053e-06,
"loss": 1.0977,
"step": 468
},
{
"epoch": 14.65625,
"grad_norm": 1.161231836469243,
"learning_rate": 2.8125e-06,
"loss": 1.2852,
"step": 469
},
{
"epoch": 14.6875,
"grad_norm": 1.1586427690801844,
"learning_rate": 2.796052631578948e-06,
"loss": 1.4531,
"step": 470
},
{
"epoch": 14.71875,
"grad_norm": 1.0735965447794522,
"learning_rate": 2.779605263157895e-06,
"loss": 1.1904,
"step": 471
},
{
"epoch": 14.75,
"grad_norm": 1.1132905570623621,
"learning_rate": 2.7631578947368424e-06,
"loss": 1.416,
"step": 472
},
{
"epoch": 14.78125,
"grad_norm": 1.159521186004377,
"learning_rate": 2.7467105263157893e-06,
"loss": 1.2432,
"step": 473
},
{
"epoch": 14.8125,
"grad_norm": 1.0656935107635523,
"learning_rate": 2.730263157894737e-06,
"loss": 1.2812,
"step": 474
},
{
"epoch": 14.84375,
"grad_norm": 1.0011066736142082,
"learning_rate": 2.7138157894736843e-06,
"loss": 1.1523,
"step": 475
},
{
"epoch": 14.875,
"grad_norm": 1.14999073916424,
"learning_rate": 2.697368421052632e-06,
"loss": 1.4043,
"step": 476
},
{
"epoch": 14.90625,
"grad_norm": 1.2325422262223233,
"learning_rate": 2.6809210526315793e-06,
"loss": 1.2559,
"step": 477
},
{
"epoch": 14.9375,
"grad_norm": 0.9847559909054264,
"learning_rate": 2.664473684210527e-06,
"loss": 1.1162,
"step": 478
},
{
"epoch": 14.96875,
"grad_norm": 1.3310005724561664,
"learning_rate": 2.648026315789474e-06,
"loss": 1.5029,
"step": 479
},
{
"epoch": 15.0,
"grad_norm": 1.1154233561514635,
"learning_rate": 2.631578947368421e-06,
"loss": 1.2266,
"step": 480
},
{
"epoch": 15.03125,
"grad_norm": 1.2563971886551109,
"learning_rate": 2.6151315789473684e-06,
"loss": 1.3633,
"step": 481
},
{
"epoch": 15.0625,
"grad_norm": 1.105742026406257,
"learning_rate": 2.598684210526316e-06,
"loss": 1.2539,
"step": 482
},
{
"epoch": 15.09375,
"grad_norm": 1.0780836881301994,
"learning_rate": 2.5822368421052634e-06,
"loss": 1.1729,
"step": 483
},
{
"epoch": 15.125,
"grad_norm": 1.1413296775014503,
"learning_rate": 2.565789473684211e-06,
"loss": 1.2656,
"step": 484
},
{
"epoch": 15.15625,
"grad_norm": 1.2881008284721613,
"learning_rate": 2.549342105263158e-06,
"loss": 1.3848,
"step": 485
},
{
"epoch": 15.1875,
"grad_norm": 0.976527781645127,
"learning_rate": 2.5328947368421052e-06,
"loss": 1.2031,
"step": 486
},
{
"epoch": 15.21875,
"grad_norm": 0.9358594834433476,
"learning_rate": 2.516447368421053e-06,
"loss": 1.0771,
"step": 487
},
{
"epoch": 15.25,
"grad_norm": 1.1081336222960927,
"learning_rate": 2.5e-06,
"loss": 1.1973,
"step": 488
},
{
"epoch": 15.28125,
"grad_norm": 0.9289762234227542,
"learning_rate": 2.4835526315789475e-06,
"loss": 0.9883,
"step": 489
},
{
"epoch": 15.3125,
"grad_norm": 0.9842240371852441,
"learning_rate": 2.4671052631578948e-06,
"loss": 1.0938,
"step": 490
},
{
"epoch": 15.34375,
"grad_norm": 1.2307196149704511,
"learning_rate": 2.4506578947368425e-06,
"loss": 1.1777,
"step": 491
},
{
"epoch": 15.375,
"grad_norm": 1.0986796436184,
"learning_rate": 2.4342105263157898e-06,
"loss": 1.1787,
"step": 492
},
{
"epoch": 15.40625,
"grad_norm": 1.1798771532584746,
"learning_rate": 2.417763157894737e-06,
"loss": 1.3105,
"step": 493
},
{
"epoch": 15.4375,
"grad_norm": 1.2256001371386596,
"learning_rate": 2.4013157894736843e-06,
"loss": 1.3604,
"step": 494
},
{
"epoch": 15.46875,
"grad_norm": 1.021954952646941,
"learning_rate": 2.384868421052632e-06,
"loss": 1.2246,
"step": 495
},
{
"epoch": 15.5,
"grad_norm": 1.299346493712266,
"learning_rate": 2.368421052631579e-06,
"loss": 1.3535,
"step": 496
},
{
"epoch": 15.53125,
"grad_norm": 1.336121635352978,
"learning_rate": 2.3519736842105266e-06,
"loss": 1.6211,
"step": 497
},
{
"epoch": 15.5625,
"grad_norm": 0.9520793848137924,
"learning_rate": 2.335526315789474e-06,
"loss": 0.957,
"step": 498
},
{
"epoch": 15.59375,
"grad_norm": 1.0898192526364332,
"learning_rate": 2.3190789473684216e-06,
"loss": 1.2246,
"step": 499
},
{
"epoch": 15.625,
"grad_norm": 1.1748821308428201,
"learning_rate": 2.3026315789473684e-06,
"loss": 1.0957,
"step": 500
},
{
"epoch": 15.65625,
"grad_norm": 1.0083430893858323,
"learning_rate": 2.286184210526316e-06,
"loss": 1.1348,
"step": 501
},
{
"epoch": 15.6875,
"grad_norm": 1.2608117651126283,
"learning_rate": 2.2697368421052634e-06,
"loss": 1.4043,
"step": 502
},
{
"epoch": 15.71875,
"grad_norm": 1.0733128080248424,
"learning_rate": 2.2532894736842107e-06,
"loss": 1.3398,
"step": 503
},
{
"epoch": 15.75,
"grad_norm": 1.0173381426456558,
"learning_rate": 2.236842105263158e-06,
"loss": 1.1191,
"step": 504
},
{
"epoch": 15.78125,
"grad_norm": 0.9976139576050151,
"learning_rate": 2.2203947368421057e-06,
"loss": 1.0898,
"step": 505
},
{
"epoch": 15.8125,
"grad_norm": 1.0432828287429723,
"learning_rate": 2.2039473684210525e-06,
"loss": 1.1582,
"step": 506
},
{
"epoch": 15.84375,
"grad_norm": 1.3471757738180266,
"learning_rate": 2.1875000000000002e-06,
"loss": 1.4473,
"step": 507
},
{
"epoch": 15.875,
"grad_norm": 1.0421236696424703,
"learning_rate": 2.1710526315789475e-06,
"loss": 1.1934,
"step": 508
},
{
"epoch": 15.90625,
"grad_norm": 0.952901790435728,
"learning_rate": 2.154605263157895e-06,
"loss": 1.0947,
"step": 509
},
{
"epoch": 15.9375,
"grad_norm": 1.090112867461769,
"learning_rate": 2.138157894736842e-06,
"loss": 1.2266,
"step": 510
},
{
"epoch": 15.96875,
"grad_norm": 1.0259764617752856,
"learning_rate": 2.1217105263157898e-06,
"loss": 1.1895,
"step": 511
},
{
"epoch": 16.0,
"grad_norm": 1.0780860545017692,
"learning_rate": 2.105263157894737e-06,
"loss": 1.2773,
"step": 512
},
{
"epoch": 16.03125,
"grad_norm": 1.192598478720439,
"learning_rate": 2.0888157894736843e-06,
"loss": 1.1406,
"step": 513
},
{
"epoch": 16.0625,
"grad_norm": 1.0157090658357621,
"learning_rate": 2.0723684210526316e-06,
"loss": 1.1953,
"step": 514
},
{
"epoch": 16.09375,
"grad_norm": 1.1696332490676487,
"learning_rate": 2.055921052631579e-06,
"loss": 1.2686,
"step": 515
},
{
"epoch": 16.125,
"grad_norm": 0.8971977511377294,
"learning_rate": 2.0394736842105266e-06,
"loss": 0.9502,
"step": 516
},
{
"epoch": 16.15625,
"grad_norm": 1.1312500938030132,
"learning_rate": 2.023026315789474e-06,
"loss": 1.2422,
"step": 517
},
{
"epoch": 16.1875,
"grad_norm": 1.2149617401537083,
"learning_rate": 2.006578947368421e-06,
"loss": 1.3496,
"step": 518
},
{
"epoch": 16.21875,
"grad_norm": 1.2223065264663917,
"learning_rate": 1.9901315789473684e-06,
"loss": 1.4199,
"step": 519
},
{
"epoch": 16.25,
"grad_norm": 1.1257780879283918,
"learning_rate": 1.973684210526316e-06,
"loss": 1.3555,
"step": 520
},
{
"epoch": 16.28125,
"grad_norm": 1.1391743777442347,
"learning_rate": 1.9572368421052634e-06,
"loss": 1.3047,
"step": 521
},
{
"epoch": 16.3125,
"grad_norm": 1.0831660200474136,
"learning_rate": 1.9407894736842107e-06,
"loss": 1.25,
"step": 522
},
{
"epoch": 16.34375,
"grad_norm": 1.0567996107762117,
"learning_rate": 1.924342105263158e-06,
"loss": 1.1465,
"step": 523
},
{
"epoch": 16.375,
"grad_norm": 1.1628482634546986,
"learning_rate": 1.9078947368421057e-06,
"loss": 1.2549,
"step": 524
},
{
"epoch": 16.40625,
"grad_norm": 0.9482355578709101,
"learning_rate": 1.8914473684210528e-06,
"loss": 1.1299,
"step": 525
},
{
"epoch": 16.4375,
"grad_norm": 0.9628299682769264,
"learning_rate": 1.8750000000000003e-06,
"loss": 1.0742,
"step": 526
},
{
"epoch": 16.46875,
"grad_norm": 1.107300320497425,
"learning_rate": 1.8585526315789475e-06,
"loss": 1.2012,
"step": 527
},
{
"epoch": 16.5,
"grad_norm": 1.0287657590791992,
"learning_rate": 1.8421052631578948e-06,
"loss": 1.2949,
"step": 528
},
{
"epoch": 16.53125,
"grad_norm": 0.9567055660381166,
"learning_rate": 1.8256578947368423e-06,
"loss": 1.1904,
"step": 529
},
{
"epoch": 16.5625,
"grad_norm": 1.0002030531549826,
"learning_rate": 1.8092105263157896e-06,
"loss": 1.0918,
"step": 530
},
{
"epoch": 16.59375,
"grad_norm": 1.0750461930124113,
"learning_rate": 1.7927631578947369e-06,
"loss": 1.123,
"step": 531
},
{
"epoch": 16.625,
"grad_norm": 1.0587518347896514,
"learning_rate": 1.7763157894736844e-06,
"loss": 1.2207,
"step": 532
},
{
"epoch": 16.65625,
"grad_norm": 1.2056106418322352,
"learning_rate": 1.7598684210526319e-06,
"loss": 1.2188,
"step": 533
},
{
"epoch": 16.6875,
"grad_norm": 1.140280544591844,
"learning_rate": 1.743421052631579e-06,
"loss": 1.2119,
"step": 534
},
{
"epoch": 16.71875,
"grad_norm": 1.2106066605287251,
"learning_rate": 1.7269736842105264e-06,
"loss": 1.4746,
"step": 535
},
{
"epoch": 16.75,
"grad_norm": 1.077182787791311,
"learning_rate": 1.710526315789474e-06,
"loss": 1.2598,
"step": 536
},
{
"epoch": 16.78125,
"grad_norm": 0.9360280704539896,
"learning_rate": 1.6940789473684214e-06,
"loss": 1.0205,
"step": 537
},
{
"epoch": 16.8125,
"grad_norm": 1.177830582531183,
"learning_rate": 1.6776315789473685e-06,
"loss": 1.165,
"step": 538
},
{
"epoch": 16.84375,
"grad_norm": 0.9833377707764928,
"learning_rate": 1.661184210526316e-06,
"loss": 0.9775,
"step": 539
},
{
"epoch": 16.875,
"grad_norm": 1.020582698769153,
"learning_rate": 1.6447368421052635e-06,
"loss": 1.2578,
"step": 540
},
{
"epoch": 16.90625,
"grad_norm": 0.8580065921387311,
"learning_rate": 1.6282894736842105e-06,
"loss": 0.9551,
"step": 541
},
{
"epoch": 16.9375,
"grad_norm": 1.3268669487142282,
"learning_rate": 1.611842105263158e-06,
"loss": 1.373,
"step": 542
},
{
"epoch": 16.96875,
"grad_norm": 1.1004982029921277,
"learning_rate": 1.5953947368421055e-06,
"loss": 1.3125,
"step": 543
},
{
"epoch": 17.0,
"grad_norm": 1.000229419328728,
"learning_rate": 1.5789473684210526e-06,
"loss": 1.0898,
"step": 544
},
{
"epoch": 17.03125,
"grad_norm": 0.9935344747918229,
"learning_rate": 1.5625e-06,
"loss": 1.1025,
"step": 545
},
{
"epoch": 17.0625,
"grad_norm": 1.0543671143937776,
"learning_rate": 1.5460526315789476e-06,
"loss": 1.2422,
"step": 546
},
{
"epoch": 17.09375,
"grad_norm": 1.0267873484315073,
"learning_rate": 1.5296052631578948e-06,
"loss": 1.0781,
"step": 547
},
{
"epoch": 17.125,
"grad_norm": 1.1249613526875928,
"learning_rate": 1.5131578947368421e-06,
"loss": 1.1729,
"step": 548
},
{
"epoch": 17.15625,
"grad_norm": 1.0314777193884443,
"learning_rate": 1.4967105263157896e-06,
"loss": 1.0635,
"step": 549
},
{
"epoch": 17.1875,
"grad_norm": 0.9142765714159412,
"learning_rate": 1.480263157894737e-06,
"loss": 0.9785,
"step": 550
},
{
"epoch": 17.21875,
"grad_norm": 0.9901266850655975,
"learning_rate": 1.4638157894736844e-06,
"loss": 1.168,
"step": 551
},
{
"epoch": 17.25,
"grad_norm": 1.0319109364032018,
"learning_rate": 1.4473684210526317e-06,
"loss": 1.1641,
"step": 552
},
{
"epoch": 17.28125,
"grad_norm": 1.0709685127822617,
"learning_rate": 1.430921052631579e-06,
"loss": 1.2012,
"step": 553
},
{
"epoch": 17.3125,
"grad_norm": 1.0250829611009873,
"learning_rate": 1.4144736842105264e-06,
"loss": 1.125,
"step": 554
},
{
"epoch": 17.34375,
"grad_norm": 1.2173412186529595,
"learning_rate": 1.398026315789474e-06,
"loss": 1.3848,
"step": 555
},
{
"epoch": 17.375,
"grad_norm": 1.1661265073694773,
"learning_rate": 1.3815789473684212e-06,
"loss": 1.3242,
"step": 556
},
{
"epoch": 17.40625,
"grad_norm": 1.0121306619298118,
"learning_rate": 1.3651315789473685e-06,
"loss": 1.1172,
"step": 557
},
{
"epoch": 17.4375,
"grad_norm": 1.145353023757232,
"learning_rate": 1.348684210526316e-06,
"loss": 1.0859,
"step": 558
},
{
"epoch": 17.46875,
"grad_norm": 1.1543024421121426,
"learning_rate": 1.3322368421052635e-06,
"loss": 1.2773,
"step": 559
},
{
"epoch": 17.5,
"grad_norm": 1.1931114578200357,
"learning_rate": 1.3157894736842106e-06,
"loss": 1.4395,
"step": 560
},
{
"epoch": 17.53125,
"grad_norm": 1.0823108980476308,
"learning_rate": 1.299342105263158e-06,
"loss": 1.291,
"step": 561
},
{
"epoch": 17.5625,
"grad_norm": 1.2958777300604947,
"learning_rate": 1.2828947368421055e-06,
"loss": 1.5244,
"step": 562
},
{
"epoch": 17.59375,
"grad_norm": 1.0958459267557619,
"learning_rate": 1.2664473684210526e-06,
"loss": 1.2695,
"step": 563
},
{
"epoch": 17.625,
"grad_norm": 1.0560505531646338,
"learning_rate": 1.25e-06,
"loss": 1.127,
"step": 564
},
{
"epoch": 17.65625,
"grad_norm": 0.9502701291758148,
"learning_rate": 1.2335526315789474e-06,
"loss": 1.042,
"step": 565
},
{
"epoch": 17.6875,
"grad_norm": 1.167107395596191,
"learning_rate": 1.2171052631578949e-06,
"loss": 1.3281,
"step": 566
},
{
"epoch": 17.71875,
"grad_norm": 1.0014573626532628,
"learning_rate": 1.2006578947368422e-06,
"loss": 1.2539,
"step": 567
},
{
"epoch": 17.75,
"grad_norm": 1.0590612632945187,
"learning_rate": 1.1842105263157894e-06,
"loss": 1.1602,
"step": 568
},
{
"epoch": 17.78125,
"grad_norm": 1.1056440658535576,
"learning_rate": 1.167763157894737e-06,
"loss": 1.2578,
"step": 569
},
{
"epoch": 17.8125,
"grad_norm": 0.9707174845773445,
"learning_rate": 1.1513157894736842e-06,
"loss": 1.0381,
"step": 570
},
{
"epoch": 17.84375,
"grad_norm": 0.9319534550891547,
"learning_rate": 1.1348684210526317e-06,
"loss": 1.0469,
"step": 571
},
{
"epoch": 17.875,
"grad_norm": 1.07640867533832,
"learning_rate": 1.118421052631579e-06,
"loss": 1.2539,
"step": 572
},
{
"epoch": 17.90625,
"grad_norm": 1.0562839901611762,
"learning_rate": 1.1019736842105263e-06,
"loss": 1.1445,
"step": 573
},
{
"epoch": 17.9375,
"grad_norm": 0.9476515587217543,
"learning_rate": 1.0855263157894738e-06,
"loss": 0.9941,
"step": 574
},
{
"epoch": 17.96875,
"grad_norm": 1.243227986698938,
"learning_rate": 1.069078947368421e-06,
"loss": 1.4209,
"step": 575
},
{
"epoch": 18.0,
"grad_norm": 1.0047531189502914,
"learning_rate": 1.0526315789473685e-06,
"loss": 1.168,
"step": 576
},
{
"epoch": 18.03125,
"grad_norm": 1.145263566255281,
"learning_rate": 1.0361842105263158e-06,
"loss": 1.1484,
"step": 577
},
{
"epoch": 18.0625,
"grad_norm": 1.0227699125913654,
"learning_rate": 1.0197368421052633e-06,
"loss": 1.1543,
"step": 578
},
{
"epoch": 18.09375,
"grad_norm": 1.0023191716319868,
"learning_rate": 1.0032894736842106e-06,
"loss": 1.1289,
"step": 579
},
{
"epoch": 18.125,
"grad_norm": 1.184064441667458,
"learning_rate": 9.86842105263158e-07,
"loss": 1.3711,
"step": 580
},
{
"epoch": 18.15625,
"grad_norm": 0.9164067698376666,
"learning_rate": 9.703947368421054e-07,
"loss": 1.0156,
"step": 581
},
{
"epoch": 18.1875,
"grad_norm": 1.068057644565925,
"learning_rate": 9.539473684210528e-07,
"loss": 1.2002,
"step": 582
},
{
"epoch": 18.21875,
"grad_norm": 0.9402667674389827,
"learning_rate": 9.375000000000001e-07,
"loss": 1.0391,
"step": 583
},
{
"epoch": 18.25,
"grad_norm": 1.0724473831725843,
"learning_rate": 9.210526315789474e-07,
"loss": 1.1973,
"step": 584
},
{
"epoch": 18.28125,
"grad_norm": 0.899157164043245,
"learning_rate": 9.046052631578948e-07,
"loss": 1.0166,
"step": 585
},
{
"epoch": 18.3125,
"grad_norm": 1.1592644941231875,
"learning_rate": 8.881578947368422e-07,
"loss": 1.2871,
"step": 586
},
{
"epoch": 18.34375,
"grad_norm": 1.1279497041498054,
"learning_rate": 8.717105263157895e-07,
"loss": 1.1748,
"step": 587
},
{
"epoch": 18.375,
"grad_norm": 1.0947637178030056,
"learning_rate": 8.55263157894737e-07,
"loss": 1.1621,
"step": 588
},
{
"epoch": 18.40625,
"grad_norm": 0.971340645847889,
"learning_rate": 8.388157894736842e-07,
"loss": 1.042,
"step": 589
},
{
"epoch": 18.4375,
"grad_norm": 1.135852458781184,
"learning_rate": 8.223684210526317e-07,
"loss": 1.3008,
"step": 590
},
{
"epoch": 18.46875,
"grad_norm": 1.0277173173937963,
"learning_rate": 8.05921052631579e-07,
"loss": 1.2139,
"step": 591
},
{
"epoch": 18.5,
"grad_norm": 0.9587889530985669,
"learning_rate": 7.894736842105263e-07,
"loss": 1.1016,
"step": 592
},
{
"epoch": 18.53125,
"grad_norm": 0.9531093861419058,
"learning_rate": 7.730263157894738e-07,
"loss": 1.0674,
"step": 593
},
{
"epoch": 18.5625,
"grad_norm": 1.1666257762014436,
"learning_rate": 7.565789473684211e-07,
"loss": 1.1885,
"step": 594
},
{
"epoch": 18.59375,
"grad_norm": 1.0813604792585834,
"learning_rate": 7.401315789473685e-07,
"loss": 1.2129,
"step": 595
},
{
"epoch": 18.625,
"grad_norm": 1.1302000825187128,
"learning_rate": 7.236842105263158e-07,
"loss": 1.2676,
"step": 596
},
{
"epoch": 18.65625,
"grad_norm": 0.9312416313068738,
"learning_rate": 7.072368421052632e-07,
"loss": 1.0625,
"step": 597
},
{
"epoch": 18.6875,
"grad_norm": 1.1066387434686906,
"learning_rate": 6.907894736842106e-07,
"loss": 1.1797,
"step": 598
},
{
"epoch": 18.71875,
"grad_norm": 1.1853531130328365,
"learning_rate": 6.74342105263158e-07,
"loss": 1.4082,
"step": 599
},
{
"epoch": 18.75,
"grad_norm": 1.208353836982986,
"learning_rate": 6.578947368421053e-07,
"loss": 1.3457,
"step": 600
},
{
"epoch": 18.78125,
"grad_norm": 1.0980397009903324,
"learning_rate": 6.414473684210528e-07,
"loss": 1.2666,
"step": 601
},
{
"epoch": 18.8125,
"grad_norm": 1.3324274671780056,
"learning_rate": 6.25e-07,
"loss": 1.4922,
"step": 602
},
{
"epoch": 18.84375,
"grad_norm": 1.0217051090320044,
"learning_rate": 6.085526315789474e-07,
"loss": 1.1758,
"step": 603
},
{
"epoch": 18.875,
"grad_norm": 1.1832208524104049,
"learning_rate": 5.921052631578947e-07,
"loss": 1.2168,
"step": 604
},
{
"epoch": 18.90625,
"grad_norm": 1.138472364101582,
"learning_rate": 5.756578947368421e-07,
"loss": 1.1719,
"step": 605
},
{
"epoch": 18.9375,
"grad_norm": 0.9489909061618802,
"learning_rate": 5.592105263157895e-07,
"loss": 1.0996,
"step": 606
},
{
"epoch": 18.96875,
"grad_norm": 1.0800080525984865,
"learning_rate": 5.427631578947369e-07,
"loss": 1.0498,
"step": 607
},
{
"epoch": 19.0,
"grad_norm": 1.1052351881529183,
"learning_rate": 5.263157894736843e-07,
"loss": 1.1875,
"step": 608
},
{
"epoch": 19.03125,
"grad_norm": 0.9529877481968042,
"learning_rate": 5.098684210526317e-07,
"loss": 1.0557,
"step": 609
},
{
"epoch": 19.0625,
"grad_norm": 1.2147697421430195,
"learning_rate": 4.93421052631579e-07,
"loss": 1.3379,
"step": 610
},
{
"epoch": 19.09375,
"grad_norm": 1.1820998596909449,
"learning_rate": 4.769736842105264e-07,
"loss": 1.2344,
"step": 611
},
{
"epoch": 19.125,
"grad_norm": 1.0063229019805375,
"learning_rate": 4.605263157894737e-07,
"loss": 1.2012,
"step": 612
},
{
"epoch": 19.15625,
"grad_norm": 1.2778895444138885,
"learning_rate": 4.440789473684211e-07,
"loss": 1.3174,
"step": 613
},
{
"epoch": 19.1875,
"grad_norm": 1.2037019784132217,
"learning_rate": 4.276315789473685e-07,
"loss": 1.3789,
"step": 614
},
{
"epoch": 19.21875,
"grad_norm": 1.1854865563566213,
"learning_rate": 4.1118421052631586e-07,
"loss": 1.3145,
"step": 615
},
{
"epoch": 19.25,
"grad_norm": 1.0783877288786168,
"learning_rate": 3.9473684210526315e-07,
"loss": 1.1973,
"step": 616
},
{
"epoch": 19.28125,
"grad_norm": 1.0345740226249058,
"learning_rate": 3.7828947368421053e-07,
"loss": 1.2031,
"step": 617
},
{
"epoch": 19.3125,
"grad_norm": 1.156444902840872,
"learning_rate": 3.618421052631579e-07,
"loss": 1.3125,
"step": 618
},
{
"epoch": 19.34375,
"grad_norm": 1.2384005537624165,
"learning_rate": 3.453947368421053e-07,
"loss": 1.293,
"step": 619
},
{
"epoch": 19.375,
"grad_norm": 1.0524947955888673,
"learning_rate": 3.2894736842105264e-07,
"loss": 1.2129,
"step": 620
},
{
"epoch": 19.40625,
"grad_norm": 0.9648764915337302,
"learning_rate": 3.125e-07,
"loss": 1.2207,
"step": 621
},
{
"epoch": 19.4375,
"grad_norm": 0.9444957798556137,
"learning_rate": 2.9605263157894736e-07,
"loss": 1.1064,
"step": 622
},
{
"epoch": 19.46875,
"grad_norm": 1.0658323116370334,
"learning_rate": 2.7960526315789475e-07,
"loss": 1.2363,
"step": 623
},
{
"epoch": 19.5,
"grad_norm": 0.885475098072067,
"learning_rate": 2.6315789473684213e-07,
"loss": 1.0254,
"step": 624
},
{
"epoch": 19.53125,
"grad_norm": 1.0065666057958396,
"learning_rate": 2.467105263157895e-07,
"loss": 1.0156,
"step": 625
},
{
"epoch": 19.5625,
"grad_norm": 0.921909489715102,
"learning_rate": 2.3026315789473685e-07,
"loss": 1.0195,
"step": 626
},
{
"epoch": 19.59375,
"grad_norm": 0.9649682488701493,
"learning_rate": 2.1381578947368424e-07,
"loss": 1.1338,
"step": 627
},
{
"epoch": 19.625,
"grad_norm": 1.053086822564824,
"learning_rate": 1.9736842105263157e-07,
"loss": 1.1055,
"step": 628
},
{
"epoch": 19.65625,
"grad_norm": 0.8521740297213248,
"learning_rate": 1.8092105263157896e-07,
"loss": 0.9922,
"step": 629
},
{
"epoch": 19.6875,
"grad_norm": 0.8978034476299945,
"learning_rate": 1.6447368421052632e-07,
"loss": 1.041,
"step": 630
},
{
"epoch": 19.71875,
"grad_norm": 1.2331631454932384,
"learning_rate": 1.4802631578947368e-07,
"loss": 1.334,
"step": 631
},
{
"epoch": 19.75,
"grad_norm": 1.1387006974305094,
"learning_rate": 1.3157894736842107e-07,
"loss": 1.2686,
"step": 632
},
{
"epoch": 19.78125,
"grad_norm": 1.032056506324884,
"learning_rate": 1.1513157894736843e-07,
"loss": 1.166,
"step": 633
},
{
"epoch": 19.8125,
"grad_norm": 1.0941401119246281,
"learning_rate": 9.868421052631579e-08,
"loss": 1.2197,
"step": 634
},
{
"epoch": 19.84375,
"grad_norm": 1.0184179316050685,
"learning_rate": 8.223684210526316e-08,
"loss": 1.123,
"step": 635
},
{
"epoch": 19.875,
"grad_norm": 1.014831481795213,
"learning_rate": 6.578947368421053e-08,
"loss": 1.1279,
"step": 636
},
{
"epoch": 19.90625,
"grad_norm": 1.044195891863528,
"learning_rate": 4.934210526315789e-08,
"loss": 1.0684,
"step": 637
},
{
"epoch": 19.9375,
"grad_norm": 0.980659591323473,
"learning_rate": 3.2894736842105267e-08,
"loss": 1.1396,
"step": 638
},
{
"epoch": 19.96875,
"grad_norm": 1.0564637321806472,
"learning_rate": 1.6447368421052633e-08,
"loss": 1.2861,
"step": 639
},
{
"epoch": 20.0,
"grad_norm": 0.9521578921532778,
"learning_rate": 0.0,
"loss": 1.1064,
"step": 640
},
{
"epoch": 20.0,
"step": 640,
"total_flos": 7749606014976.0,
"train_loss": 2.1912933349609376,
"train_runtime": 187.775,
"train_samples_per_second": 53.255,
"train_steps_per_second": 3.408
}
],
"logging_steps": 1,
"max_steps": 640,
"num_input_tokens_seen": 0,
"num_train_epochs": 20,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": false,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 7749606014976.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}