Devy1's picture
Upload checkpoint Qwen2.5-Coder-CONTROL-checkpoints_multi_language_2k-1.5B-Base-9 at epoch 9
1282af6 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 9.0,
"eval_steps": 500,
"global_step": 1206,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.007511737089201878,
"grad_norm": 1.5546875,
"learning_rate": 5e-05,
"loss": 0.7059,
"step": 1
},
{
"epoch": 0.015023474178403756,
"grad_norm": 2.046875,
"learning_rate": 4.996268656716418e-05,
"loss": 0.8614,
"step": 2
},
{
"epoch": 0.022535211267605635,
"grad_norm": 14.375,
"learning_rate": 4.992537313432836e-05,
"loss": 0.799,
"step": 3
},
{
"epoch": 0.03004694835680751,
"grad_norm": 2.421875,
"learning_rate": 4.988805970149254e-05,
"loss": 0.7599,
"step": 4
},
{
"epoch": 0.03755868544600939,
"grad_norm": 1.7890625,
"learning_rate": 4.985074626865672e-05,
"loss": 0.7254,
"step": 5
},
{
"epoch": 0.04507042253521127,
"grad_norm": 1.4375,
"learning_rate": 4.98134328358209e-05,
"loss": 0.7982,
"step": 6
},
{
"epoch": 0.05258215962441314,
"grad_norm": 1.546875,
"learning_rate": 4.977611940298508e-05,
"loss": 0.7192,
"step": 7
},
{
"epoch": 0.06009389671361502,
"grad_norm": 2.71875,
"learning_rate": 4.973880597014925e-05,
"loss": 0.8359,
"step": 8
},
{
"epoch": 0.0676056338028169,
"grad_norm": 1.4140625,
"learning_rate": 4.9701492537313436e-05,
"loss": 0.6135,
"step": 9
},
{
"epoch": 0.07511737089201878,
"grad_norm": 3.96875,
"learning_rate": 4.966417910447762e-05,
"loss": 1.0456,
"step": 10
},
{
"epoch": 0.08262910798122065,
"grad_norm": 1.6171875,
"learning_rate": 4.9626865671641794e-05,
"loss": 0.6937,
"step": 11
},
{
"epoch": 0.09014084507042254,
"grad_norm": 1.3828125,
"learning_rate": 4.9589552238805977e-05,
"loss": 0.6935,
"step": 12
},
{
"epoch": 0.09765258215962441,
"grad_norm": 1.7265625,
"learning_rate": 4.955223880597015e-05,
"loss": 0.9582,
"step": 13
},
{
"epoch": 0.10516431924882629,
"grad_norm": 1.6015625,
"learning_rate": 4.951492537313433e-05,
"loss": 0.6369,
"step": 14
},
{
"epoch": 0.11267605633802817,
"grad_norm": 1.4453125,
"learning_rate": 4.9477611940298504e-05,
"loss": 0.8523,
"step": 15
},
{
"epoch": 0.12018779342723004,
"grad_norm": 1.234375,
"learning_rate": 4.944029850746269e-05,
"loss": 0.7572,
"step": 16
},
{
"epoch": 0.12769953051643193,
"grad_norm": 1.6171875,
"learning_rate": 4.940298507462687e-05,
"loss": 0.8729,
"step": 17
},
{
"epoch": 0.1352112676056338,
"grad_norm": 1.4296875,
"learning_rate": 4.9365671641791045e-05,
"loss": 0.7657,
"step": 18
},
{
"epoch": 0.14272300469483568,
"grad_norm": 1.5546875,
"learning_rate": 4.932835820895523e-05,
"loss": 0.7701,
"step": 19
},
{
"epoch": 0.15023474178403756,
"grad_norm": 1.421875,
"learning_rate": 4.92910447761194e-05,
"loss": 0.8063,
"step": 20
},
{
"epoch": 0.15774647887323945,
"grad_norm": 1.203125,
"learning_rate": 4.9253731343283586e-05,
"loss": 0.6274,
"step": 21
},
{
"epoch": 0.1652582159624413,
"grad_norm": 1.0234375,
"learning_rate": 4.921641791044777e-05,
"loss": 0.6862,
"step": 22
},
{
"epoch": 0.1727699530516432,
"grad_norm": 1.3203125,
"learning_rate": 4.9179104477611944e-05,
"loss": 0.8265,
"step": 23
},
{
"epoch": 0.18028169014084508,
"grad_norm": 1.3671875,
"learning_rate": 4.914179104477612e-05,
"loss": 0.6659,
"step": 24
},
{
"epoch": 0.18779342723004694,
"grad_norm": 1.34375,
"learning_rate": 4.91044776119403e-05,
"loss": 0.6795,
"step": 25
},
{
"epoch": 0.19530516431924883,
"grad_norm": 3.734375,
"learning_rate": 4.906716417910448e-05,
"loss": 0.7914,
"step": 26
},
{
"epoch": 0.2028169014084507,
"grad_norm": 1.578125,
"learning_rate": 4.902985074626866e-05,
"loss": 0.7915,
"step": 27
},
{
"epoch": 0.21032863849765257,
"grad_norm": 1.078125,
"learning_rate": 4.899253731343284e-05,
"loss": 0.6433,
"step": 28
},
{
"epoch": 0.21784037558685446,
"grad_norm": 1.2265625,
"learning_rate": 4.895522388059702e-05,
"loss": 0.8444,
"step": 29
},
{
"epoch": 0.22535211267605634,
"grad_norm": 1.328125,
"learning_rate": 4.8917910447761195e-05,
"loss": 0.7353,
"step": 30
},
{
"epoch": 0.23286384976525823,
"grad_norm": 1.0859375,
"learning_rate": 4.888059701492538e-05,
"loss": 0.6133,
"step": 31
},
{
"epoch": 0.2403755868544601,
"grad_norm": 1.4375,
"learning_rate": 4.884328358208955e-05,
"loss": 0.671,
"step": 32
},
{
"epoch": 0.24788732394366197,
"grad_norm": 1.1484375,
"learning_rate": 4.8805970149253735e-05,
"loss": 0.7712,
"step": 33
},
{
"epoch": 0.25539906103286386,
"grad_norm": 1.4765625,
"learning_rate": 4.876865671641792e-05,
"loss": 0.8207,
"step": 34
},
{
"epoch": 0.26291079812206575,
"grad_norm": 1.28125,
"learning_rate": 4.8731343283582094e-05,
"loss": 0.7435,
"step": 35
},
{
"epoch": 0.2704225352112676,
"grad_norm": 1.171875,
"learning_rate": 4.869402985074627e-05,
"loss": 0.7014,
"step": 36
},
{
"epoch": 0.27793427230046946,
"grad_norm": 1.1875,
"learning_rate": 4.8656716417910445e-05,
"loss": 0.7946,
"step": 37
},
{
"epoch": 0.28544600938967135,
"grad_norm": 1.6328125,
"learning_rate": 4.861940298507463e-05,
"loss": 0.5345,
"step": 38
},
{
"epoch": 0.29295774647887324,
"grad_norm": 2.859375,
"learning_rate": 4.858208955223881e-05,
"loss": 0.8832,
"step": 39
},
{
"epoch": 0.3004694835680751,
"grad_norm": 2.09375,
"learning_rate": 4.8544776119402986e-05,
"loss": 0.8591,
"step": 40
},
{
"epoch": 0.307981220657277,
"grad_norm": 1.21875,
"learning_rate": 4.850746268656717e-05,
"loss": 0.6557,
"step": 41
},
{
"epoch": 0.3154929577464789,
"grad_norm": 0.984375,
"learning_rate": 4.8470149253731344e-05,
"loss": 0.715,
"step": 42
},
{
"epoch": 0.32300469483568073,
"grad_norm": 0.9453125,
"learning_rate": 4.843283582089552e-05,
"loss": 0.6608,
"step": 43
},
{
"epoch": 0.3305164319248826,
"grad_norm": 1.5703125,
"learning_rate": 4.83955223880597e-05,
"loss": 0.5904,
"step": 44
},
{
"epoch": 0.3380281690140845,
"grad_norm": 2.703125,
"learning_rate": 4.8358208955223885e-05,
"loss": 0.8645,
"step": 45
},
{
"epoch": 0.3455399061032864,
"grad_norm": 5.84375,
"learning_rate": 4.832089552238806e-05,
"loss": 0.9412,
"step": 46
},
{
"epoch": 0.3530516431924883,
"grad_norm": 1.2734375,
"learning_rate": 4.8283582089552244e-05,
"loss": 0.8767,
"step": 47
},
{
"epoch": 0.36056338028169016,
"grad_norm": 1.296875,
"learning_rate": 4.824626865671642e-05,
"loss": 0.8197,
"step": 48
},
{
"epoch": 0.36807511737089205,
"grad_norm": 1.0625,
"learning_rate": 4.8208955223880595e-05,
"loss": 0.6598,
"step": 49
},
{
"epoch": 0.3755868544600939,
"grad_norm": 4.0,
"learning_rate": 4.817164179104478e-05,
"loss": 1.1535,
"step": 50
},
{
"epoch": 0.38309859154929576,
"grad_norm": 1.09375,
"learning_rate": 4.813432835820896e-05,
"loss": 0.6635,
"step": 51
},
{
"epoch": 0.39061032863849765,
"grad_norm": 1.3125,
"learning_rate": 4.8097014925373136e-05,
"loss": 0.6979,
"step": 52
},
{
"epoch": 0.39812206572769954,
"grad_norm": 1.2734375,
"learning_rate": 4.805970149253732e-05,
"loss": 0.7167,
"step": 53
},
{
"epoch": 0.4056338028169014,
"grad_norm": 1.1640625,
"learning_rate": 4.8022388059701494e-05,
"loss": 0.8033,
"step": 54
},
{
"epoch": 0.4131455399061033,
"grad_norm": 1.421875,
"learning_rate": 4.798507462686567e-05,
"loss": 0.8736,
"step": 55
},
{
"epoch": 0.42065727699530514,
"grad_norm": 1.2890625,
"learning_rate": 4.794776119402985e-05,
"loss": 0.8361,
"step": 56
},
{
"epoch": 0.428169014084507,
"grad_norm": 1.1328125,
"learning_rate": 4.7910447761194035e-05,
"loss": 0.6386,
"step": 57
},
{
"epoch": 0.4356807511737089,
"grad_norm": 1.2421875,
"learning_rate": 4.787313432835821e-05,
"loss": 0.7318,
"step": 58
},
{
"epoch": 0.4431924882629108,
"grad_norm": 1.4375,
"learning_rate": 4.7835820895522394e-05,
"loss": 0.7141,
"step": 59
},
{
"epoch": 0.4507042253521127,
"grad_norm": 1.0859375,
"learning_rate": 4.779850746268657e-05,
"loss": 0.6612,
"step": 60
},
{
"epoch": 0.4582159624413146,
"grad_norm": 1.109375,
"learning_rate": 4.7761194029850745e-05,
"loss": 0.8155,
"step": 61
},
{
"epoch": 0.46572769953051646,
"grad_norm": 1.0546875,
"learning_rate": 4.772388059701493e-05,
"loss": 0.8123,
"step": 62
},
{
"epoch": 0.4732394366197183,
"grad_norm": 1.1640625,
"learning_rate": 4.768656716417911e-05,
"loss": 0.6706,
"step": 63
},
{
"epoch": 0.4807511737089202,
"grad_norm": 1.25,
"learning_rate": 4.7649253731343286e-05,
"loss": 0.8376,
"step": 64
},
{
"epoch": 0.48826291079812206,
"grad_norm": 0.98828125,
"learning_rate": 4.761194029850746e-05,
"loss": 0.7736,
"step": 65
},
{
"epoch": 0.49577464788732395,
"grad_norm": 1.296875,
"learning_rate": 4.7574626865671644e-05,
"loss": 0.777,
"step": 66
},
{
"epoch": 0.5032863849765258,
"grad_norm": 1.1328125,
"learning_rate": 4.753731343283582e-05,
"loss": 0.7517,
"step": 67
},
{
"epoch": 0.5107981220657277,
"grad_norm": 1.2578125,
"learning_rate": 4.75e-05,
"loss": 0.8422,
"step": 68
},
{
"epoch": 0.5183098591549296,
"grad_norm": 1.2109375,
"learning_rate": 4.7462686567164185e-05,
"loss": 0.6369,
"step": 69
},
{
"epoch": 0.5258215962441315,
"grad_norm": 1.0,
"learning_rate": 4.742537313432836e-05,
"loss": 0.6823,
"step": 70
},
{
"epoch": 0.5333333333333333,
"grad_norm": 1.1953125,
"learning_rate": 4.738805970149254e-05,
"loss": 0.6799,
"step": 71
},
{
"epoch": 0.5408450704225352,
"grad_norm": 1.1640625,
"learning_rate": 4.735074626865672e-05,
"loss": 0.6477,
"step": 72
},
{
"epoch": 0.5483568075117371,
"grad_norm": 1.125,
"learning_rate": 4.7313432835820895e-05,
"loss": 0.7116,
"step": 73
},
{
"epoch": 0.5558685446009389,
"grad_norm": 1.0390625,
"learning_rate": 4.727611940298508e-05,
"loss": 0.6501,
"step": 74
},
{
"epoch": 0.5633802816901409,
"grad_norm": 1.203125,
"learning_rate": 4.723880597014926e-05,
"loss": 0.8061,
"step": 75
},
{
"epoch": 0.5708920187793427,
"grad_norm": 1.203125,
"learning_rate": 4.7201492537313436e-05,
"loss": 0.7363,
"step": 76
},
{
"epoch": 0.5784037558685446,
"grad_norm": 1.15625,
"learning_rate": 4.716417910447761e-05,
"loss": 0.7949,
"step": 77
},
{
"epoch": 0.5859154929577465,
"grad_norm": 1.25,
"learning_rate": 4.7126865671641794e-05,
"loss": 0.7815,
"step": 78
},
{
"epoch": 0.5934272300469483,
"grad_norm": 1.40625,
"learning_rate": 4.708955223880597e-05,
"loss": 0.7815,
"step": 79
},
{
"epoch": 0.6009389671361502,
"grad_norm": 1.1796875,
"learning_rate": 4.705223880597015e-05,
"loss": 0.7299,
"step": 80
},
{
"epoch": 0.6084507042253521,
"grad_norm": 1.25,
"learning_rate": 4.7014925373134335e-05,
"loss": 0.5975,
"step": 81
},
{
"epoch": 0.615962441314554,
"grad_norm": 1.8984375,
"learning_rate": 4.697761194029851e-05,
"loss": 0.8056,
"step": 82
},
{
"epoch": 0.6234741784037559,
"grad_norm": 1.3671875,
"learning_rate": 4.6940298507462687e-05,
"loss": 0.8034,
"step": 83
},
{
"epoch": 0.6309859154929578,
"grad_norm": 1.078125,
"learning_rate": 4.690298507462687e-05,
"loss": 0.6472,
"step": 84
},
{
"epoch": 0.6384976525821596,
"grad_norm": 1.328125,
"learning_rate": 4.6865671641791045e-05,
"loss": 0.8561,
"step": 85
},
{
"epoch": 0.6460093896713615,
"grad_norm": 2.90625,
"learning_rate": 4.682835820895523e-05,
"loss": 0.8774,
"step": 86
},
{
"epoch": 0.6535211267605634,
"grad_norm": 1.1484375,
"learning_rate": 4.67910447761194e-05,
"loss": 0.6865,
"step": 87
},
{
"epoch": 0.6610328638497652,
"grad_norm": 1.53125,
"learning_rate": 4.6753731343283586e-05,
"loss": 0.798,
"step": 88
},
{
"epoch": 0.6685446009389672,
"grad_norm": 1.1875,
"learning_rate": 4.671641791044776e-05,
"loss": 0.7587,
"step": 89
},
{
"epoch": 0.676056338028169,
"grad_norm": 1.25,
"learning_rate": 4.667910447761194e-05,
"loss": 0.6989,
"step": 90
},
{
"epoch": 0.6835680751173709,
"grad_norm": 1.0546875,
"learning_rate": 4.664179104477612e-05,
"loss": 0.639,
"step": 91
},
{
"epoch": 0.6910798122065728,
"grad_norm": 1.453125,
"learning_rate": 4.66044776119403e-05,
"loss": 0.6844,
"step": 92
},
{
"epoch": 0.6985915492957746,
"grad_norm": 1.03125,
"learning_rate": 4.656716417910448e-05,
"loss": 0.7513,
"step": 93
},
{
"epoch": 0.7061032863849765,
"grad_norm": 1.015625,
"learning_rate": 4.652985074626866e-05,
"loss": 0.6264,
"step": 94
},
{
"epoch": 0.7136150234741784,
"grad_norm": 1.21875,
"learning_rate": 4.6492537313432837e-05,
"loss": 0.7228,
"step": 95
},
{
"epoch": 0.7211267605633803,
"grad_norm": 1.0078125,
"learning_rate": 4.645522388059701e-05,
"loss": 0.5355,
"step": 96
},
{
"epoch": 0.7286384976525822,
"grad_norm": 1.359375,
"learning_rate": 4.6417910447761195e-05,
"loss": 0.7717,
"step": 97
},
{
"epoch": 0.7361502347417841,
"grad_norm": 1.1328125,
"learning_rate": 4.638059701492538e-05,
"loss": 0.7365,
"step": 98
},
{
"epoch": 0.7436619718309859,
"grad_norm": 3.375,
"learning_rate": 4.634328358208955e-05,
"loss": 0.8382,
"step": 99
},
{
"epoch": 0.7511737089201878,
"grad_norm": 1.421875,
"learning_rate": 4.6305970149253736e-05,
"loss": 0.7674,
"step": 100
},
{
"epoch": 0.7586854460093897,
"grad_norm": 1.7265625,
"learning_rate": 4.626865671641791e-05,
"loss": 0.554,
"step": 101
},
{
"epoch": 0.7661971830985915,
"grad_norm": 1.25,
"learning_rate": 4.623134328358209e-05,
"loss": 0.7921,
"step": 102
},
{
"epoch": 0.7737089201877935,
"grad_norm": 1.2734375,
"learning_rate": 4.6194029850746277e-05,
"loss": 0.6282,
"step": 103
},
{
"epoch": 0.7812206572769953,
"grad_norm": 1.171875,
"learning_rate": 4.615671641791045e-05,
"loss": 0.7992,
"step": 104
},
{
"epoch": 0.7887323943661971,
"grad_norm": 1.0859375,
"learning_rate": 4.611940298507463e-05,
"loss": 0.7313,
"step": 105
},
{
"epoch": 0.7962441314553991,
"grad_norm": 0.9921875,
"learning_rate": 4.608208955223881e-05,
"loss": 0.7154,
"step": 106
},
{
"epoch": 0.8037558685446009,
"grad_norm": 1.0859375,
"learning_rate": 4.6044776119402986e-05,
"loss": 0.6904,
"step": 107
},
{
"epoch": 0.8112676056338028,
"grad_norm": 1.125,
"learning_rate": 4.600746268656716e-05,
"loss": 0.7075,
"step": 108
},
{
"epoch": 0.8187793427230047,
"grad_norm": 2.609375,
"learning_rate": 4.5970149253731345e-05,
"loss": 0.7362,
"step": 109
},
{
"epoch": 0.8262910798122066,
"grad_norm": 1.125,
"learning_rate": 4.593283582089553e-05,
"loss": 0.6568,
"step": 110
},
{
"epoch": 0.8338028169014085,
"grad_norm": 1.3984375,
"learning_rate": 4.58955223880597e-05,
"loss": 0.7508,
"step": 111
},
{
"epoch": 0.8413145539906103,
"grad_norm": 1.078125,
"learning_rate": 4.585820895522388e-05,
"loss": 0.8402,
"step": 112
},
{
"epoch": 0.8488262910798122,
"grad_norm": 1.2734375,
"learning_rate": 4.582089552238806e-05,
"loss": 0.6946,
"step": 113
},
{
"epoch": 0.856338028169014,
"grad_norm": 1.03125,
"learning_rate": 4.578358208955224e-05,
"loss": 0.6877,
"step": 114
},
{
"epoch": 0.863849765258216,
"grad_norm": 1.2890625,
"learning_rate": 4.574626865671642e-05,
"loss": 0.6703,
"step": 115
},
{
"epoch": 0.8713615023474178,
"grad_norm": 1.2578125,
"learning_rate": 4.57089552238806e-05,
"loss": 0.6673,
"step": 116
},
{
"epoch": 0.8788732394366198,
"grad_norm": 1.078125,
"learning_rate": 4.567164179104478e-05,
"loss": 0.8,
"step": 117
},
{
"epoch": 0.8863849765258216,
"grad_norm": 1.7734375,
"learning_rate": 4.5634328358208954e-05,
"loss": 0.7146,
"step": 118
},
{
"epoch": 0.8938967136150234,
"grad_norm": 1.1953125,
"learning_rate": 4.5597014925373136e-05,
"loss": 0.7342,
"step": 119
},
{
"epoch": 0.9014084507042254,
"grad_norm": 1.390625,
"learning_rate": 4.555970149253732e-05,
"loss": 0.865,
"step": 120
},
{
"epoch": 0.9089201877934272,
"grad_norm": 1.171875,
"learning_rate": 4.5522388059701495e-05,
"loss": 0.8743,
"step": 121
},
{
"epoch": 0.9164319248826291,
"grad_norm": 1.0625,
"learning_rate": 4.548507462686568e-05,
"loss": 0.8124,
"step": 122
},
{
"epoch": 0.923943661971831,
"grad_norm": 1.0703125,
"learning_rate": 4.544776119402985e-05,
"loss": 0.739,
"step": 123
},
{
"epoch": 0.9314553990610329,
"grad_norm": 1.109375,
"learning_rate": 4.541044776119403e-05,
"loss": 0.9343,
"step": 124
},
{
"epoch": 0.9389671361502347,
"grad_norm": 1.21875,
"learning_rate": 4.537313432835821e-05,
"loss": 0.8239,
"step": 125
},
{
"epoch": 0.9464788732394366,
"grad_norm": 1.125,
"learning_rate": 4.5335820895522394e-05,
"loss": 0.5928,
"step": 126
},
{
"epoch": 0.9539906103286385,
"grad_norm": 1.140625,
"learning_rate": 4.529850746268657e-05,
"loss": 0.6705,
"step": 127
},
{
"epoch": 0.9615023474178404,
"grad_norm": 1.5390625,
"learning_rate": 4.526119402985075e-05,
"loss": 0.7937,
"step": 128
},
{
"epoch": 0.9690140845070423,
"grad_norm": 1.0703125,
"learning_rate": 4.522388059701493e-05,
"loss": 0.7819,
"step": 129
},
{
"epoch": 0.9765258215962441,
"grad_norm": 1.2265625,
"learning_rate": 4.5186567164179104e-05,
"loss": 0.7217,
"step": 130
},
{
"epoch": 0.984037558685446,
"grad_norm": 0.97265625,
"learning_rate": 4.5149253731343286e-05,
"loss": 0.5954,
"step": 131
},
{
"epoch": 0.9915492957746479,
"grad_norm": 1.171875,
"learning_rate": 4.511194029850747e-05,
"loss": 0.6472,
"step": 132
},
{
"epoch": 0.9990610328638497,
"grad_norm": 1.078125,
"learning_rate": 4.5074626865671645e-05,
"loss": 0.6715,
"step": 133
},
{
"epoch": 1.0,
"grad_norm": 2.765625,
"learning_rate": 4.503731343283582e-05,
"loss": 0.7686,
"step": 134
},
{
"epoch": 1.007511737089202,
"grad_norm": 1.625,
"learning_rate": 4.5e-05,
"loss": 0.6494,
"step": 135
},
{
"epoch": 1.0150234741784037,
"grad_norm": 1.46875,
"learning_rate": 4.496268656716418e-05,
"loss": 0.5652,
"step": 136
},
{
"epoch": 1.0225352112676056,
"grad_norm": 0.9296875,
"learning_rate": 4.492537313432836e-05,
"loss": 0.5451,
"step": 137
},
{
"epoch": 1.0300469483568075,
"grad_norm": 1.1171875,
"learning_rate": 4.4888059701492544e-05,
"loss": 0.7535,
"step": 138
},
{
"epoch": 1.0375586854460095,
"grad_norm": 1.328125,
"learning_rate": 4.485074626865672e-05,
"loss": 0.6217,
"step": 139
},
{
"epoch": 1.0450704225352112,
"grad_norm": 1.1953125,
"learning_rate": 4.4813432835820895e-05,
"loss": 0.6696,
"step": 140
},
{
"epoch": 1.0525821596244131,
"grad_norm": 1.59375,
"learning_rate": 4.477611940298508e-05,
"loss": 0.5071,
"step": 141
},
{
"epoch": 1.060093896713615,
"grad_norm": 1.4921875,
"learning_rate": 4.4738805970149254e-05,
"loss": 0.5824,
"step": 142
},
{
"epoch": 1.0676056338028168,
"grad_norm": 1.1796875,
"learning_rate": 4.4701492537313436e-05,
"loss": 0.4513,
"step": 143
},
{
"epoch": 1.0751173708920188,
"grad_norm": 1.3671875,
"learning_rate": 4.466417910447762e-05,
"loss": 0.6003,
"step": 144
},
{
"epoch": 1.0826291079812207,
"grad_norm": 1.3515625,
"learning_rate": 4.4626865671641794e-05,
"loss": 0.6236,
"step": 145
},
{
"epoch": 1.0901408450704226,
"grad_norm": 1.0859375,
"learning_rate": 4.458955223880597e-05,
"loss": 0.5397,
"step": 146
},
{
"epoch": 1.0976525821596244,
"grad_norm": 2.0625,
"learning_rate": 4.455223880597015e-05,
"loss": 0.8009,
"step": 147
},
{
"epoch": 1.1051643192488263,
"grad_norm": 1.3125,
"learning_rate": 4.451492537313433e-05,
"loss": 0.7748,
"step": 148
},
{
"epoch": 1.1126760563380282,
"grad_norm": 3.421875,
"learning_rate": 4.447761194029851e-05,
"loss": 0.7256,
"step": 149
},
{
"epoch": 1.12018779342723,
"grad_norm": 1.296875,
"learning_rate": 4.4440298507462694e-05,
"loss": 0.6101,
"step": 150
},
{
"epoch": 1.127699530516432,
"grad_norm": 1.109375,
"learning_rate": 4.440298507462687e-05,
"loss": 0.4897,
"step": 151
},
{
"epoch": 1.1352112676056338,
"grad_norm": 1.0703125,
"learning_rate": 4.4365671641791045e-05,
"loss": 0.7608,
"step": 152
},
{
"epoch": 1.1427230046948358,
"grad_norm": 1.1171875,
"learning_rate": 4.432835820895523e-05,
"loss": 0.6389,
"step": 153
},
{
"epoch": 1.1502347417840375,
"grad_norm": 0.98828125,
"learning_rate": 4.4291044776119403e-05,
"loss": 0.4912,
"step": 154
},
{
"epoch": 1.1577464788732394,
"grad_norm": 1.1171875,
"learning_rate": 4.4253731343283586e-05,
"loss": 0.6865,
"step": 155
},
{
"epoch": 1.1652582159624414,
"grad_norm": 1.0078125,
"learning_rate": 4.421641791044777e-05,
"loss": 0.4687,
"step": 156
},
{
"epoch": 1.172769953051643,
"grad_norm": 1.6484375,
"learning_rate": 4.4179104477611944e-05,
"loss": 0.6835,
"step": 157
},
{
"epoch": 1.180281690140845,
"grad_norm": 1.015625,
"learning_rate": 4.414179104477612e-05,
"loss": 0.4748,
"step": 158
},
{
"epoch": 1.187793427230047,
"grad_norm": 1.1015625,
"learning_rate": 4.4104477611940296e-05,
"loss": 0.556,
"step": 159
},
{
"epoch": 1.1953051643192487,
"grad_norm": 1.0390625,
"learning_rate": 4.406716417910448e-05,
"loss": 0.4781,
"step": 160
},
{
"epoch": 1.2028169014084507,
"grad_norm": 0.87890625,
"learning_rate": 4.402985074626866e-05,
"loss": 0.4693,
"step": 161
},
{
"epoch": 1.2103286384976526,
"grad_norm": 1.1171875,
"learning_rate": 4.399253731343284e-05,
"loss": 0.5578,
"step": 162
},
{
"epoch": 1.2178403755868545,
"grad_norm": 1.2890625,
"learning_rate": 4.395522388059702e-05,
"loss": 0.6094,
"step": 163
},
{
"epoch": 1.2253521126760563,
"grad_norm": 1.671875,
"learning_rate": 4.3917910447761195e-05,
"loss": 0.6457,
"step": 164
},
{
"epoch": 1.2328638497652582,
"grad_norm": 0.96875,
"learning_rate": 4.388059701492537e-05,
"loss": 0.5279,
"step": 165
},
{
"epoch": 1.2403755868544601,
"grad_norm": 1.0234375,
"learning_rate": 4.384328358208955e-05,
"loss": 0.5519,
"step": 166
},
{
"epoch": 1.247887323943662,
"grad_norm": 0.97265625,
"learning_rate": 4.3805970149253736e-05,
"loss": 0.4328,
"step": 167
},
{
"epoch": 1.2553990610328638,
"grad_norm": 1.6484375,
"learning_rate": 4.376865671641791e-05,
"loss": 0.6765,
"step": 168
},
{
"epoch": 1.2629107981220657,
"grad_norm": 0.953125,
"learning_rate": 4.3731343283582094e-05,
"loss": 0.4776,
"step": 169
},
{
"epoch": 1.2704225352112677,
"grad_norm": 1.125,
"learning_rate": 4.369402985074627e-05,
"loss": 0.4864,
"step": 170
},
{
"epoch": 1.2779342723004694,
"grad_norm": 1.2421875,
"learning_rate": 4.3656716417910446e-05,
"loss": 0.5458,
"step": 171
},
{
"epoch": 1.2854460093896714,
"grad_norm": 1.046875,
"learning_rate": 4.361940298507463e-05,
"loss": 0.5282,
"step": 172
},
{
"epoch": 1.2929577464788733,
"grad_norm": 1.0703125,
"learning_rate": 4.358208955223881e-05,
"loss": 0.5868,
"step": 173
},
{
"epoch": 1.300469483568075,
"grad_norm": 0.94921875,
"learning_rate": 4.354477611940299e-05,
"loss": 0.5913,
"step": 174
},
{
"epoch": 1.307981220657277,
"grad_norm": 1.1953125,
"learning_rate": 4.350746268656717e-05,
"loss": 0.6012,
"step": 175
},
{
"epoch": 1.315492957746479,
"grad_norm": 1.578125,
"learning_rate": 4.3470149253731345e-05,
"loss": 0.7648,
"step": 176
},
{
"epoch": 1.3230046948356806,
"grad_norm": 1.09375,
"learning_rate": 4.343283582089552e-05,
"loss": 0.5035,
"step": 177
},
{
"epoch": 1.3305164319248826,
"grad_norm": 0.98046875,
"learning_rate": 4.33955223880597e-05,
"loss": 0.6096,
"step": 178
},
{
"epoch": 1.3380281690140845,
"grad_norm": 1.1875,
"learning_rate": 4.3358208955223886e-05,
"loss": 0.6028,
"step": 179
},
{
"epoch": 1.3455399061032864,
"grad_norm": 1.046875,
"learning_rate": 4.332089552238806e-05,
"loss": 0.4301,
"step": 180
},
{
"epoch": 1.3530516431924884,
"grad_norm": 0.875,
"learning_rate": 4.328358208955224e-05,
"loss": 0.4578,
"step": 181
},
{
"epoch": 1.36056338028169,
"grad_norm": 1.2734375,
"learning_rate": 4.324626865671642e-05,
"loss": 0.6293,
"step": 182
},
{
"epoch": 1.368075117370892,
"grad_norm": 1.09375,
"learning_rate": 4.3208955223880596e-05,
"loss": 0.6577,
"step": 183
},
{
"epoch": 1.375586854460094,
"grad_norm": 1.0,
"learning_rate": 4.317164179104478e-05,
"loss": 0.5545,
"step": 184
},
{
"epoch": 1.3830985915492957,
"grad_norm": 1.28125,
"learning_rate": 4.313432835820896e-05,
"loss": 0.6445,
"step": 185
},
{
"epoch": 1.3906103286384977,
"grad_norm": 0.9609375,
"learning_rate": 4.3097014925373137e-05,
"loss": 0.3414,
"step": 186
},
{
"epoch": 1.3981220657276996,
"grad_norm": 1.1328125,
"learning_rate": 4.305970149253731e-05,
"loss": 0.6948,
"step": 187
},
{
"epoch": 1.4056338028169013,
"grad_norm": 1.15625,
"learning_rate": 4.3022388059701495e-05,
"loss": 0.4784,
"step": 188
},
{
"epoch": 1.4131455399061033,
"grad_norm": 1.140625,
"learning_rate": 4.298507462686567e-05,
"loss": 0.665,
"step": 189
},
{
"epoch": 1.4206572769953052,
"grad_norm": 1.0703125,
"learning_rate": 4.294776119402985e-05,
"loss": 0.5881,
"step": 190
},
{
"epoch": 1.428169014084507,
"grad_norm": 0.98046875,
"learning_rate": 4.2910447761194036e-05,
"loss": 0.4298,
"step": 191
},
{
"epoch": 1.4356807511737089,
"grad_norm": 1.2578125,
"learning_rate": 4.287313432835821e-05,
"loss": 0.6543,
"step": 192
},
{
"epoch": 1.4431924882629108,
"grad_norm": 1.09375,
"learning_rate": 4.283582089552239e-05,
"loss": 0.4931,
"step": 193
},
{
"epoch": 1.4507042253521127,
"grad_norm": 1.2265625,
"learning_rate": 4.279850746268657e-05,
"loss": 0.5279,
"step": 194
},
{
"epoch": 1.4582159624413147,
"grad_norm": 1.015625,
"learning_rate": 4.2761194029850746e-05,
"loss": 0.5347,
"step": 195
},
{
"epoch": 1.4657276995305164,
"grad_norm": 1.15625,
"learning_rate": 4.272388059701493e-05,
"loss": 0.48,
"step": 196
},
{
"epoch": 1.4732394366197183,
"grad_norm": 1.25,
"learning_rate": 4.268656716417911e-05,
"loss": 0.6988,
"step": 197
},
{
"epoch": 1.4807511737089203,
"grad_norm": 1.421875,
"learning_rate": 4.2649253731343286e-05,
"loss": 0.5859,
"step": 198
},
{
"epoch": 1.488262910798122,
"grad_norm": 1.1796875,
"learning_rate": 4.261194029850746e-05,
"loss": 0.5283,
"step": 199
},
{
"epoch": 1.495774647887324,
"grad_norm": 1.0703125,
"learning_rate": 4.2574626865671645e-05,
"loss": 0.4631,
"step": 200
},
{
"epoch": 1.503286384976526,
"grad_norm": 0.9921875,
"learning_rate": 4.253731343283582e-05,
"loss": 0.5231,
"step": 201
},
{
"epoch": 1.5107981220657276,
"grad_norm": 1.0625,
"learning_rate": 4.25e-05,
"loss": 0.5583,
"step": 202
},
{
"epoch": 1.5183098591549296,
"grad_norm": 0.9453125,
"learning_rate": 4.2462686567164186e-05,
"loss": 0.4876,
"step": 203
},
{
"epoch": 1.5258215962441315,
"grad_norm": 1.2265625,
"learning_rate": 4.242537313432836e-05,
"loss": 0.4504,
"step": 204
},
{
"epoch": 1.5333333333333332,
"grad_norm": 0.93359375,
"learning_rate": 4.238805970149254e-05,
"loss": 0.4757,
"step": 205
},
{
"epoch": 1.5408450704225352,
"grad_norm": 1.0703125,
"learning_rate": 4.235074626865671e-05,
"loss": 0.5933,
"step": 206
},
{
"epoch": 1.548356807511737,
"grad_norm": 1.0078125,
"learning_rate": 4.2313432835820895e-05,
"loss": 0.5415,
"step": 207
},
{
"epoch": 1.5558685446009388,
"grad_norm": 1.1953125,
"learning_rate": 4.227611940298508e-05,
"loss": 0.7041,
"step": 208
},
{
"epoch": 1.563380281690141,
"grad_norm": 1.109375,
"learning_rate": 4.2238805970149254e-05,
"loss": 0.5753,
"step": 209
},
{
"epoch": 1.5708920187793427,
"grad_norm": 1.1640625,
"learning_rate": 4.2201492537313436e-05,
"loss": 0.552,
"step": 210
},
{
"epoch": 1.5784037558685446,
"grad_norm": 1.0,
"learning_rate": 4.216417910447761e-05,
"loss": 0.5549,
"step": 211
},
{
"epoch": 1.5859154929577466,
"grad_norm": 1.1328125,
"learning_rate": 4.212686567164179e-05,
"loss": 0.6679,
"step": 212
},
{
"epoch": 1.5934272300469483,
"grad_norm": 2.015625,
"learning_rate": 4.208955223880597e-05,
"loss": 0.796,
"step": 213
},
{
"epoch": 1.6009389671361502,
"grad_norm": 2.953125,
"learning_rate": 4.205223880597015e-05,
"loss": 0.6427,
"step": 214
},
{
"epoch": 1.6084507042253522,
"grad_norm": 0.90625,
"learning_rate": 4.201492537313433e-05,
"loss": 0.466,
"step": 215
},
{
"epoch": 1.615962441314554,
"grad_norm": 0.94140625,
"learning_rate": 4.197761194029851e-05,
"loss": 0.4242,
"step": 216
},
{
"epoch": 1.6234741784037559,
"grad_norm": 3.0,
"learning_rate": 4.194029850746269e-05,
"loss": 0.6968,
"step": 217
},
{
"epoch": 1.6309859154929578,
"grad_norm": 0.9765625,
"learning_rate": 4.190298507462686e-05,
"loss": 0.5988,
"step": 218
},
{
"epoch": 1.6384976525821595,
"grad_norm": 1.203125,
"learning_rate": 4.186567164179105e-05,
"loss": 0.4979,
"step": 219
},
{
"epoch": 1.6460093896713615,
"grad_norm": 0.83203125,
"learning_rate": 4.182835820895523e-05,
"loss": 0.3527,
"step": 220
},
{
"epoch": 1.6535211267605634,
"grad_norm": 1.09375,
"learning_rate": 4.1791044776119404e-05,
"loss": 0.5743,
"step": 221
},
{
"epoch": 1.6610328638497651,
"grad_norm": 1.3203125,
"learning_rate": 4.1753731343283586e-05,
"loss": 0.6427,
"step": 222
},
{
"epoch": 1.6685446009389673,
"grad_norm": 1.2109375,
"learning_rate": 4.171641791044776e-05,
"loss": 0.6496,
"step": 223
},
{
"epoch": 1.676056338028169,
"grad_norm": 0.8515625,
"learning_rate": 4.167910447761194e-05,
"loss": 0.3463,
"step": 224
},
{
"epoch": 1.683568075117371,
"grad_norm": 1.34375,
"learning_rate": 4.164179104477613e-05,
"loss": 0.6243,
"step": 225
},
{
"epoch": 1.6910798122065729,
"grad_norm": 0.98828125,
"learning_rate": 4.16044776119403e-05,
"loss": 0.5389,
"step": 226
},
{
"epoch": 1.6985915492957746,
"grad_norm": 1.0,
"learning_rate": 4.156716417910448e-05,
"loss": 0.5515,
"step": 227
},
{
"epoch": 1.7061032863849765,
"grad_norm": 1.2890625,
"learning_rate": 4.152985074626866e-05,
"loss": 0.6783,
"step": 228
},
{
"epoch": 1.7136150234741785,
"grad_norm": 1.0390625,
"learning_rate": 4.149253731343284e-05,
"loss": 0.5099,
"step": 229
},
{
"epoch": 1.7211267605633802,
"grad_norm": 1.078125,
"learning_rate": 4.145522388059702e-05,
"loss": 0.461,
"step": 230
},
{
"epoch": 1.7286384976525822,
"grad_norm": 1.0703125,
"learning_rate": 4.1417910447761195e-05,
"loss": 0.4953,
"step": 231
},
{
"epoch": 1.736150234741784,
"grad_norm": 1.1484375,
"learning_rate": 4.138059701492538e-05,
"loss": 0.5662,
"step": 232
},
{
"epoch": 1.7436619718309858,
"grad_norm": 1.1171875,
"learning_rate": 4.1343283582089554e-05,
"loss": 0.524,
"step": 233
},
{
"epoch": 1.7511737089201878,
"grad_norm": 1.1328125,
"learning_rate": 4.130597014925373e-05,
"loss": 0.424,
"step": 234
},
{
"epoch": 1.7586854460093897,
"grad_norm": 1.5625,
"learning_rate": 4.126865671641791e-05,
"loss": 0.5042,
"step": 235
},
{
"epoch": 1.7661971830985914,
"grad_norm": 0.9765625,
"learning_rate": 4.1231343283582094e-05,
"loss": 0.5515,
"step": 236
},
{
"epoch": 1.7737089201877936,
"grad_norm": 1.0703125,
"learning_rate": 4.119402985074627e-05,
"loss": 0.6026,
"step": 237
},
{
"epoch": 1.7812206572769953,
"grad_norm": 1.171875,
"learning_rate": 4.115671641791045e-05,
"loss": 0.6206,
"step": 238
},
{
"epoch": 1.788732394366197,
"grad_norm": 1.96875,
"learning_rate": 4.111940298507463e-05,
"loss": 0.6904,
"step": 239
},
{
"epoch": 1.7962441314553992,
"grad_norm": 1.0703125,
"learning_rate": 4.1082089552238804e-05,
"loss": 0.4693,
"step": 240
},
{
"epoch": 1.803755868544601,
"grad_norm": 0.8984375,
"learning_rate": 4.104477611940299e-05,
"loss": 0.3648,
"step": 241
},
{
"epoch": 1.8112676056338028,
"grad_norm": 1.2734375,
"learning_rate": 4.100746268656717e-05,
"loss": 0.6071,
"step": 242
},
{
"epoch": 1.8187793427230048,
"grad_norm": 1.1015625,
"learning_rate": 4.0970149253731345e-05,
"loss": 0.4936,
"step": 243
},
{
"epoch": 1.8262910798122065,
"grad_norm": 1.0625,
"learning_rate": 4.093283582089553e-05,
"loss": 0.6627,
"step": 244
},
{
"epoch": 1.8338028169014085,
"grad_norm": 1.0625,
"learning_rate": 4.0895522388059703e-05,
"loss": 0.4625,
"step": 245
},
{
"epoch": 1.8413145539906104,
"grad_norm": 1.2890625,
"learning_rate": 4.085820895522388e-05,
"loss": 0.5132,
"step": 246
},
{
"epoch": 1.8488262910798121,
"grad_norm": 0.91796875,
"learning_rate": 4.082089552238806e-05,
"loss": 0.5464,
"step": 247
},
{
"epoch": 1.856338028169014,
"grad_norm": 1.5390625,
"learning_rate": 4.0783582089552244e-05,
"loss": 0.6268,
"step": 248
},
{
"epoch": 1.863849765258216,
"grad_norm": 1.1015625,
"learning_rate": 4.074626865671642e-05,
"loss": 0.4702,
"step": 249
},
{
"epoch": 1.8713615023474177,
"grad_norm": 1.21875,
"learning_rate": 4.07089552238806e-05,
"loss": 0.6875,
"step": 250
},
{
"epoch": 1.8788732394366199,
"grad_norm": 1.828125,
"learning_rate": 4.067164179104478e-05,
"loss": 0.5994,
"step": 251
},
{
"epoch": 1.8863849765258216,
"grad_norm": 1.1015625,
"learning_rate": 4.0634328358208954e-05,
"loss": 0.513,
"step": 252
},
{
"epoch": 1.8938967136150233,
"grad_norm": 0.99609375,
"learning_rate": 4.059701492537314e-05,
"loss": 0.5234,
"step": 253
},
{
"epoch": 1.9014084507042255,
"grad_norm": 1.03125,
"learning_rate": 4.055970149253732e-05,
"loss": 0.3845,
"step": 254
},
{
"epoch": 1.9089201877934272,
"grad_norm": 0.8515625,
"learning_rate": 4.0522388059701495e-05,
"loss": 0.5088,
"step": 255
},
{
"epoch": 1.9164319248826291,
"grad_norm": 1.3359375,
"learning_rate": 4.048507462686567e-05,
"loss": 0.5853,
"step": 256
},
{
"epoch": 1.923943661971831,
"grad_norm": 1.0859375,
"learning_rate": 4.044776119402985e-05,
"loss": 0.5691,
"step": 257
},
{
"epoch": 1.9314553990610328,
"grad_norm": 1.2890625,
"learning_rate": 4.041044776119403e-05,
"loss": 0.5251,
"step": 258
},
{
"epoch": 1.9389671361502347,
"grad_norm": 1.0390625,
"learning_rate": 4.037313432835821e-05,
"loss": 0.5245,
"step": 259
},
{
"epoch": 1.9464788732394367,
"grad_norm": 1.078125,
"learning_rate": 4.0335820895522394e-05,
"loss": 0.5217,
"step": 260
},
{
"epoch": 1.9539906103286384,
"grad_norm": 1.078125,
"learning_rate": 4.029850746268657e-05,
"loss": 0.4795,
"step": 261
},
{
"epoch": 1.9615023474178404,
"grad_norm": 1.109375,
"learning_rate": 4.0261194029850746e-05,
"loss": 0.5037,
"step": 262
},
{
"epoch": 1.9690140845070423,
"grad_norm": 1.0,
"learning_rate": 4.022388059701493e-05,
"loss": 0.5489,
"step": 263
},
{
"epoch": 1.976525821596244,
"grad_norm": 1.078125,
"learning_rate": 4.0186567164179104e-05,
"loss": 0.6005,
"step": 264
},
{
"epoch": 1.984037558685446,
"grad_norm": 0.96875,
"learning_rate": 4.014925373134329e-05,
"loss": 0.4849,
"step": 265
},
{
"epoch": 1.991549295774648,
"grad_norm": 1.1171875,
"learning_rate": 4.011194029850747e-05,
"loss": 0.541,
"step": 266
},
{
"epoch": 1.9990610328638496,
"grad_norm": 1.109375,
"learning_rate": 4.0074626865671645e-05,
"loss": 0.5955,
"step": 267
},
{
"epoch": 2.0,
"grad_norm": 3.390625,
"learning_rate": 4.003731343283582e-05,
"loss": 0.4322,
"step": 268
},
{
"epoch": 2.0075117370892017,
"grad_norm": 1.1171875,
"learning_rate": 4e-05,
"loss": 0.4255,
"step": 269
},
{
"epoch": 2.015023474178404,
"grad_norm": 1.140625,
"learning_rate": 3.996268656716418e-05,
"loss": 0.4638,
"step": 270
},
{
"epoch": 2.0225352112676056,
"grad_norm": 1.046875,
"learning_rate": 3.992537313432836e-05,
"loss": 0.4727,
"step": 271
},
{
"epoch": 2.0300469483568073,
"grad_norm": 0.94921875,
"learning_rate": 3.9888059701492544e-05,
"loss": 0.3631,
"step": 272
},
{
"epoch": 2.0375586854460095,
"grad_norm": 1.234375,
"learning_rate": 3.985074626865672e-05,
"loss": 0.4291,
"step": 273
},
{
"epoch": 2.045070422535211,
"grad_norm": 1.3125,
"learning_rate": 3.9813432835820896e-05,
"loss": 0.4012,
"step": 274
},
{
"epoch": 2.052582159624413,
"grad_norm": 1.453125,
"learning_rate": 3.977611940298508e-05,
"loss": 0.5699,
"step": 275
},
{
"epoch": 2.060093896713615,
"grad_norm": 1.546875,
"learning_rate": 3.9738805970149254e-05,
"loss": 0.4192,
"step": 276
},
{
"epoch": 2.067605633802817,
"grad_norm": 1.5078125,
"learning_rate": 3.9701492537313437e-05,
"loss": 0.442,
"step": 277
},
{
"epoch": 2.075117370892019,
"grad_norm": 1.078125,
"learning_rate": 3.966417910447761e-05,
"loss": 0.3812,
"step": 278
},
{
"epoch": 2.0826291079812207,
"grad_norm": 0.9609375,
"learning_rate": 3.9626865671641795e-05,
"loss": 0.3047,
"step": 279
},
{
"epoch": 2.0901408450704224,
"grad_norm": 1.1640625,
"learning_rate": 3.958955223880597e-05,
"loss": 0.474,
"step": 280
},
{
"epoch": 2.0976525821596246,
"grad_norm": 1.1484375,
"learning_rate": 3.9552238805970146e-05,
"loss": 0.4265,
"step": 281
},
{
"epoch": 2.1051643192488263,
"grad_norm": 1.0234375,
"learning_rate": 3.951492537313433e-05,
"loss": 0.4247,
"step": 282
},
{
"epoch": 2.112676056338028,
"grad_norm": 1.125,
"learning_rate": 3.947761194029851e-05,
"loss": 0.4229,
"step": 283
},
{
"epoch": 2.12018779342723,
"grad_norm": 1.03125,
"learning_rate": 3.944029850746269e-05,
"loss": 0.585,
"step": 284
},
{
"epoch": 2.127699530516432,
"grad_norm": 0.9921875,
"learning_rate": 3.940298507462687e-05,
"loss": 0.4583,
"step": 285
},
{
"epoch": 2.1352112676056336,
"grad_norm": 1.0859375,
"learning_rate": 3.9365671641791046e-05,
"loss": 0.4564,
"step": 286
},
{
"epoch": 2.142723004694836,
"grad_norm": 1.1484375,
"learning_rate": 3.932835820895522e-05,
"loss": 0.4242,
"step": 287
},
{
"epoch": 2.1502347417840375,
"grad_norm": 1.0625,
"learning_rate": 3.9291044776119404e-05,
"loss": 0.492,
"step": 288
},
{
"epoch": 2.1577464788732392,
"grad_norm": 1.109375,
"learning_rate": 3.9253731343283586e-05,
"loss": 0.389,
"step": 289
},
{
"epoch": 2.1652582159624414,
"grad_norm": 0.9765625,
"learning_rate": 3.921641791044776e-05,
"loss": 0.382,
"step": 290
},
{
"epoch": 2.172769953051643,
"grad_norm": 1.21875,
"learning_rate": 3.9179104477611945e-05,
"loss": 0.422,
"step": 291
},
{
"epoch": 2.1802816901408453,
"grad_norm": 1.2734375,
"learning_rate": 3.914179104477612e-05,
"loss": 0.4392,
"step": 292
},
{
"epoch": 2.187793427230047,
"grad_norm": 1.234375,
"learning_rate": 3.9104477611940296e-05,
"loss": 0.5264,
"step": 293
},
{
"epoch": 2.1953051643192487,
"grad_norm": 1.046875,
"learning_rate": 3.906716417910448e-05,
"loss": 0.3301,
"step": 294
},
{
"epoch": 2.202816901408451,
"grad_norm": 0.96875,
"learning_rate": 3.902985074626866e-05,
"loss": 0.4047,
"step": 295
},
{
"epoch": 2.2103286384976526,
"grad_norm": 1.328125,
"learning_rate": 3.899253731343284e-05,
"loss": 0.4317,
"step": 296
},
{
"epoch": 2.2178403755868543,
"grad_norm": 1.3359375,
"learning_rate": 3.895522388059702e-05,
"loss": 0.4581,
"step": 297
},
{
"epoch": 2.2253521126760565,
"grad_norm": 1.296875,
"learning_rate": 3.8917910447761195e-05,
"loss": 0.4516,
"step": 298
},
{
"epoch": 2.232863849765258,
"grad_norm": 0.9140625,
"learning_rate": 3.888059701492537e-05,
"loss": 0.2895,
"step": 299
},
{
"epoch": 2.24037558685446,
"grad_norm": 1.1640625,
"learning_rate": 3.8843283582089554e-05,
"loss": 0.4794,
"step": 300
},
{
"epoch": 2.247887323943662,
"grad_norm": 1.0859375,
"learning_rate": 3.8805970149253736e-05,
"loss": 0.5919,
"step": 301
},
{
"epoch": 2.255399061032864,
"grad_norm": 1.015625,
"learning_rate": 3.876865671641791e-05,
"loss": 0.4234,
"step": 302
},
{
"epoch": 2.262910798122066,
"grad_norm": 1.8203125,
"learning_rate": 3.873134328358209e-05,
"loss": 0.4109,
"step": 303
},
{
"epoch": 2.2704225352112677,
"grad_norm": 1.109375,
"learning_rate": 3.869402985074627e-05,
"loss": 0.465,
"step": 304
},
{
"epoch": 2.2779342723004694,
"grad_norm": 1.21875,
"learning_rate": 3.8656716417910446e-05,
"loss": 0.4098,
"step": 305
},
{
"epoch": 2.2854460093896716,
"grad_norm": 1.109375,
"learning_rate": 3.861940298507463e-05,
"loss": 0.4484,
"step": 306
},
{
"epoch": 2.2929577464788733,
"grad_norm": 1.171875,
"learning_rate": 3.858208955223881e-05,
"loss": 0.4225,
"step": 307
},
{
"epoch": 2.300469483568075,
"grad_norm": 1.4296875,
"learning_rate": 3.854477611940299e-05,
"loss": 0.5249,
"step": 308
},
{
"epoch": 2.307981220657277,
"grad_norm": 0.96484375,
"learning_rate": 3.850746268656716e-05,
"loss": 0.376,
"step": 309
},
{
"epoch": 2.315492957746479,
"grad_norm": 1.28125,
"learning_rate": 3.8470149253731345e-05,
"loss": 0.4915,
"step": 310
},
{
"epoch": 2.3230046948356806,
"grad_norm": 0.98046875,
"learning_rate": 3.843283582089552e-05,
"loss": 0.3064,
"step": 311
},
{
"epoch": 2.330516431924883,
"grad_norm": 0.953125,
"learning_rate": 3.8395522388059704e-05,
"loss": 0.2775,
"step": 312
},
{
"epoch": 2.3380281690140845,
"grad_norm": 1.2421875,
"learning_rate": 3.8358208955223886e-05,
"loss": 0.4981,
"step": 313
},
{
"epoch": 2.345539906103286,
"grad_norm": 0.9375,
"learning_rate": 3.832089552238806e-05,
"loss": 0.3448,
"step": 314
},
{
"epoch": 2.3530516431924884,
"grad_norm": 0.953125,
"learning_rate": 3.828358208955224e-05,
"loss": 0.3782,
"step": 315
},
{
"epoch": 2.36056338028169,
"grad_norm": 1.4453125,
"learning_rate": 3.824626865671642e-05,
"loss": 0.6991,
"step": 316
},
{
"epoch": 2.368075117370892,
"grad_norm": 1.0234375,
"learning_rate": 3.8208955223880596e-05,
"loss": 0.3665,
"step": 317
},
{
"epoch": 2.375586854460094,
"grad_norm": 1.21875,
"learning_rate": 3.817164179104478e-05,
"loss": 0.4168,
"step": 318
},
{
"epoch": 2.3830985915492957,
"grad_norm": 1.1796875,
"learning_rate": 3.813432835820896e-05,
"loss": 0.4422,
"step": 319
},
{
"epoch": 2.3906103286384974,
"grad_norm": 1.0234375,
"learning_rate": 3.809701492537314e-05,
"loss": 0.3613,
"step": 320
},
{
"epoch": 2.3981220657276996,
"grad_norm": 1.0703125,
"learning_rate": 3.805970149253731e-05,
"loss": 0.4135,
"step": 321
},
{
"epoch": 2.4056338028169013,
"grad_norm": 0.91015625,
"learning_rate": 3.8022388059701495e-05,
"loss": 0.3028,
"step": 322
},
{
"epoch": 2.4131455399061035,
"grad_norm": 1.0625,
"learning_rate": 3.798507462686567e-05,
"loss": 0.3747,
"step": 323
},
{
"epoch": 2.420657276995305,
"grad_norm": 0.8671875,
"learning_rate": 3.7947761194029854e-05,
"loss": 0.2747,
"step": 324
},
{
"epoch": 2.428169014084507,
"grad_norm": 0.8984375,
"learning_rate": 3.791044776119403e-05,
"loss": 0.3254,
"step": 325
},
{
"epoch": 2.435680751173709,
"grad_norm": 0.984375,
"learning_rate": 3.787313432835821e-05,
"loss": 0.4222,
"step": 326
},
{
"epoch": 2.443192488262911,
"grad_norm": 0.96484375,
"learning_rate": 3.783582089552239e-05,
"loss": 0.3116,
"step": 327
},
{
"epoch": 2.4507042253521125,
"grad_norm": 4.25,
"learning_rate": 3.7798507462686563e-05,
"loss": 0.4996,
"step": 328
},
{
"epoch": 2.4582159624413147,
"grad_norm": 1.15625,
"learning_rate": 3.776119402985075e-05,
"loss": 0.4413,
"step": 329
},
{
"epoch": 2.4657276995305164,
"grad_norm": 1.1484375,
"learning_rate": 3.772388059701493e-05,
"loss": 0.4048,
"step": 330
},
{
"epoch": 2.473239436619718,
"grad_norm": 0.96484375,
"learning_rate": 3.7686567164179104e-05,
"loss": 0.4141,
"step": 331
},
{
"epoch": 2.4807511737089203,
"grad_norm": 1.1640625,
"learning_rate": 3.764925373134329e-05,
"loss": 0.358,
"step": 332
},
{
"epoch": 2.488262910798122,
"grad_norm": 1.0390625,
"learning_rate": 3.761194029850746e-05,
"loss": 0.358,
"step": 333
},
{
"epoch": 2.495774647887324,
"grad_norm": 1.3046875,
"learning_rate": 3.757462686567164e-05,
"loss": 0.5101,
"step": 334
},
{
"epoch": 2.503286384976526,
"grad_norm": 1.125,
"learning_rate": 3.753731343283583e-05,
"loss": 0.4161,
"step": 335
},
{
"epoch": 2.5107981220657276,
"grad_norm": 1.15625,
"learning_rate": 3.7500000000000003e-05,
"loss": 0.4621,
"step": 336
},
{
"epoch": 2.5183098591549298,
"grad_norm": 0.99609375,
"learning_rate": 3.746268656716418e-05,
"loss": 0.4423,
"step": 337
},
{
"epoch": 2.5258215962441315,
"grad_norm": 0.921875,
"learning_rate": 3.742537313432836e-05,
"loss": 0.3696,
"step": 338
},
{
"epoch": 2.533333333333333,
"grad_norm": 0.97265625,
"learning_rate": 3.738805970149254e-05,
"loss": 0.3723,
"step": 339
},
{
"epoch": 2.5408450704225354,
"grad_norm": 1.1875,
"learning_rate": 3.735074626865671e-05,
"loss": 0.478,
"step": 340
},
{
"epoch": 2.548356807511737,
"grad_norm": 1.0625,
"learning_rate": 3.73134328358209e-05,
"loss": 0.4382,
"step": 341
},
{
"epoch": 2.555868544600939,
"grad_norm": 1.03125,
"learning_rate": 3.727611940298508e-05,
"loss": 0.3668,
"step": 342
},
{
"epoch": 2.563380281690141,
"grad_norm": 1.1796875,
"learning_rate": 3.7238805970149254e-05,
"loss": 0.4139,
"step": 343
},
{
"epoch": 2.5708920187793427,
"grad_norm": 1.0625,
"learning_rate": 3.720149253731344e-05,
"loss": 0.4257,
"step": 344
},
{
"epoch": 2.5784037558685444,
"grad_norm": 1.0703125,
"learning_rate": 3.716417910447761e-05,
"loss": 0.49,
"step": 345
},
{
"epoch": 2.5859154929577466,
"grad_norm": 1.1015625,
"learning_rate": 3.7126865671641795e-05,
"loss": 0.4485,
"step": 346
},
{
"epoch": 2.5934272300469483,
"grad_norm": 1.1875,
"learning_rate": 3.708955223880598e-05,
"loss": 0.451,
"step": 347
},
{
"epoch": 2.60093896713615,
"grad_norm": 1.078125,
"learning_rate": 3.7052238805970153e-05,
"loss": 0.4173,
"step": 348
},
{
"epoch": 2.608450704225352,
"grad_norm": 1.140625,
"learning_rate": 3.701492537313433e-05,
"loss": 0.3067,
"step": 349
},
{
"epoch": 2.615962441314554,
"grad_norm": 1.171875,
"learning_rate": 3.6977611940298505e-05,
"loss": 0.3344,
"step": 350
},
{
"epoch": 2.6234741784037556,
"grad_norm": 1.0,
"learning_rate": 3.694029850746269e-05,
"loss": 0.3942,
"step": 351
},
{
"epoch": 2.630985915492958,
"grad_norm": 1.359375,
"learning_rate": 3.690298507462687e-05,
"loss": 0.5222,
"step": 352
},
{
"epoch": 2.6384976525821595,
"grad_norm": 1.03125,
"learning_rate": 3.6865671641791046e-05,
"loss": 0.2982,
"step": 353
},
{
"epoch": 2.6460093896713612,
"grad_norm": 1.828125,
"learning_rate": 3.682835820895523e-05,
"loss": 0.4765,
"step": 354
},
{
"epoch": 2.6535211267605634,
"grad_norm": 0.9921875,
"learning_rate": 3.6791044776119404e-05,
"loss": 0.3604,
"step": 355
},
{
"epoch": 2.661032863849765,
"grad_norm": 1.2109375,
"learning_rate": 3.675373134328358e-05,
"loss": 0.4295,
"step": 356
},
{
"epoch": 2.6685446009389673,
"grad_norm": 1.09375,
"learning_rate": 3.671641791044776e-05,
"loss": 0.3636,
"step": 357
},
{
"epoch": 2.676056338028169,
"grad_norm": 1.1640625,
"learning_rate": 3.6679104477611945e-05,
"loss": 0.4205,
"step": 358
},
{
"epoch": 2.683568075117371,
"grad_norm": 1.2578125,
"learning_rate": 3.664179104477612e-05,
"loss": 0.6766,
"step": 359
},
{
"epoch": 2.691079812206573,
"grad_norm": 0.94921875,
"learning_rate": 3.66044776119403e-05,
"loss": 0.3813,
"step": 360
},
{
"epoch": 2.6985915492957746,
"grad_norm": 1.09375,
"learning_rate": 3.656716417910448e-05,
"loss": 0.4775,
"step": 361
},
{
"epoch": 2.7061032863849768,
"grad_norm": 1.3359375,
"learning_rate": 3.6529850746268655e-05,
"loss": 0.4854,
"step": 362
},
{
"epoch": 2.7136150234741785,
"grad_norm": 1.5625,
"learning_rate": 3.649253731343284e-05,
"loss": 0.5122,
"step": 363
},
{
"epoch": 2.72112676056338,
"grad_norm": 1.0234375,
"learning_rate": 3.645522388059702e-05,
"loss": 0.389,
"step": 364
},
{
"epoch": 2.7286384976525824,
"grad_norm": 1.0546875,
"learning_rate": 3.6417910447761196e-05,
"loss": 0.4442,
"step": 365
},
{
"epoch": 2.736150234741784,
"grad_norm": 1.0390625,
"learning_rate": 3.638059701492538e-05,
"loss": 0.3946,
"step": 366
},
{
"epoch": 2.743661971830986,
"grad_norm": 1.2578125,
"learning_rate": 3.6343283582089554e-05,
"loss": 0.3582,
"step": 367
},
{
"epoch": 2.751173708920188,
"grad_norm": 1.15625,
"learning_rate": 3.630597014925373e-05,
"loss": 0.4962,
"step": 368
},
{
"epoch": 2.7586854460093897,
"grad_norm": 1.140625,
"learning_rate": 3.626865671641791e-05,
"loss": 0.4519,
"step": 369
},
{
"epoch": 2.7661971830985914,
"grad_norm": 1.046875,
"learning_rate": 3.6231343283582095e-05,
"loss": 0.4805,
"step": 370
},
{
"epoch": 2.7737089201877936,
"grad_norm": 1.203125,
"learning_rate": 3.619402985074627e-05,
"loss": 0.3858,
"step": 371
},
{
"epoch": 2.7812206572769953,
"grad_norm": 1.25,
"learning_rate": 3.6156716417910446e-05,
"loss": 0.3975,
"step": 372
},
{
"epoch": 2.788732394366197,
"grad_norm": 1.2109375,
"learning_rate": 3.611940298507463e-05,
"loss": 0.5112,
"step": 373
},
{
"epoch": 2.796244131455399,
"grad_norm": 1.0625,
"learning_rate": 3.6082089552238805e-05,
"loss": 0.4478,
"step": 374
},
{
"epoch": 2.803755868544601,
"grad_norm": 1.2265625,
"learning_rate": 3.604477611940299e-05,
"loss": 0.3357,
"step": 375
},
{
"epoch": 2.8112676056338026,
"grad_norm": 1.0859375,
"learning_rate": 3.600746268656717e-05,
"loss": 0.3859,
"step": 376
},
{
"epoch": 2.818779342723005,
"grad_norm": 0.921875,
"learning_rate": 3.5970149253731346e-05,
"loss": 0.3302,
"step": 377
},
{
"epoch": 2.8262910798122065,
"grad_norm": 1.0703125,
"learning_rate": 3.593283582089552e-05,
"loss": 0.4415,
"step": 378
},
{
"epoch": 2.8338028169014082,
"grad_norm": 1.0703125,
"learning_rate": 3.5895522388059704e-05,
"loss": 0.322,
"step": 379
},
{
"epoch": 2.8413145539906104,
"grad_norm": 1.09375,
"learning_rate": 3.585820895522388e-05,
"loss": 0.3689,
"step": 380
},
{
"epoch": 2.848826291079812,
"grad_norm": 1.1484375,
"learning_rate": 3.582089552238806e-05,
"loss": 0.4491,
"step": 381
},
{
"epoch": 2.856338028169014,
"grad_norm": 1.1171875,
"learning_rate": 3.5783582089552245e-05,
"loss": 0.5455,
"step": 382
},
{
"epoch": 2.863849765258216,
"grad_norm": 1.625,
"learning_rate": 3.574626865671642e-05,
"loss": 0.4963,
"step": 383
},
{
"epoch": 2.8713615023474177,
"grad_norm": 1.140625,
"learning_rate": 3.5708955223880596e-05,
"loss": 0.5053,
"step": 384
},
{
"epoch": 2.87887323943662,
"grad_norm": 1.0,
"learning_rate": 3.567164179104478e-05,
"loss": 0.4466,
"step": 385
},
{
"epoch": 2.8863849765258216,
"grad_norm": 0.9375,
"learning_rate": 3.5634328358208955e-05,
"loss": 0.3599,
"step": 386
},
{
"epoch": 2.8938967136150233,
"grad_norm": 1.390625,
"learning_rate": 3.559701492537314e-05,
"loss": 0.4515,
"step": 387
},
{
"epoch": 2.9014084507042255,
"grad_norm": 1.0390625,
"learning_rate": 3.555970149253732e-05,
"loss": 0.4526,
"step": 388
},
{
"epoch": 2.908920187793427,
"grad_norm": 1.2890625,
"learning_rate": 3.5522388059701495e-05,
"loss": 0.4239,
"step": 389
},
{
"epoch": 2.9164319248826294,
"grad_norm": 1.046875,
"learning_rate": 3.548507462686567e-05,
"loss": 0.3883,
"step": 390
},
{
"epoch": 2.923943661971831,
"grad_norm": 1.2578125,
"learning_rate": 3.5447761194029854e-05,
"loss": 0.486,
"step": 391
},
{
"epoch": 2.931455399061033,
"grad_norm": 1.109375,
"learning_rate": 3.541044776119403e-05,
"loss": 0.502,
"step": 392
},
{
"epoch": 2.938967136150235,
"grad_norm": 1.0703125,
"learning_rate": 3.537313432835821e-05,
"loss": 0.5833,
"step": 393
},
{
"epoch": 2.9464788732394367,
"grad_norm": 1.1015625,
"learning_rate": 3.5335820895522395e-05,
"loss": 0.3583,
"step": 394
},
{
"epoch": 2.9539906103286384,
"grad_norm": 1.078125,
"learning_rate": 3.529850746268657e-05,
"loss": 0.3327,
"step": 395
},
{
"epoch": 2.9615023474178406,
"grad_norm": 1.2265625,
"learning_rate": 3.5261194029850746e-05,
"loss": 0.4078,
"step": 396
},
{
"epoch": 2.9690140845070423,
"grad_norm": 0.97265625,
"learning_rate": 3.522388059701492e-05,
"loss": 0.3805,
"step": 397
},
{
"epoch": 2.976525821596244,
"grad_norm": 0.953125,
"learning_rate": 3.5186567164179105e-05,
"loss": 0.3543,
"step": 398
},
{
"epoch": 2.984037558685446,
"grad_norm": 1.03125,
"learning_rate": 3.514925373134329e-05,
"loss": 0.3794,
"step": 399
},
{
"epoch": 2.991549295774648,
"grad_norm": 1.1015625,
"learning_rate": 3.511194029850746e-05,
"loss": 0.4541,
"step": 400
},
{
"epoch": 2.9990610328638496,
"grad_norm": 1.0625,
"learning_rate": 3.5074626865671645e-05,
"loss": 0.4267,
"step": 401
},
{
"epoch": 3.0,
"grad_norm": 3.6875,
"learning_rate": 3.503731343283582e-05,
"loss": 0.3003,
"step": 402
},
{
"epoch": 3.0075117370892017,
"grad_norm": 1.1796875,
"learning_rate": 3.5e-05,
"loss": 0.3058,
"step": 403
},
{
"epoch": 3.015023474178404,
"grad_norm": 0.984375,
"learning_rate": 3.496268656716418e-05,
"loss": 0.234,
"step": 404
},
{
"epoch": 3.0225352112676056,
"grad_norm": 1.0859375,
"learning_rate": 3.492537313432836e-05,
"loss": 0.3378,
"step": 405
},
{
"epoch": 3.0300469483568073,
"grad_norm": 0.94921875,
"learning_rate": 3.488805970149254e-05,
"loss": 0.2556,
"step": 406
},
{
"epoch": 3.0375586854460095,
"grad_norm": 1.1015625,
"learning_rate": 3.485074626865672e-05,
"loss": 0.2731,
"step": 407
},
{
"epoch": 3.045070422535211,
"grad_norm": 1.25,
"learning_rate": 3.4813432835820896e-05,
"loss": 0.2886,
"step": 408
},
{
"epoch": 3.052582159624413,
"grad_norm": 2.171875,
"learning_rate": 3.477611940298507e-05,
"loss": 0.3671,
"step": 409
},
{
"epoch": 3.060093896713615,
"grad_norm": 1.8125,
"learning_rate": 3.4738805970149254e-05,
"loss": 0.3331,
"step": 410
},
{
"epoch": 3.067605633802817,
"grad_norm": 1.7421875,
"learning_rate": 3.470149253731344e-05,
"loss": 0.3577,
"step": 411
},
{
"epoch": 3.075117370892019,
"grad_norm": 1.890625,
"learning_rate": 3.466417910447761e-05,
"loss": 0.2809,
"step": 412
},
{
"epoch": 3.0826291079812207,
"grad_norm": 1.4609375,
"learning_rate": 3.4626865671641795e-05,
"loss": 0.3122,
"step": 413
},
{
"epoch": 3.0901408450704224,
"grad_norm": 1.125,
"learning_rate": 3.458955223880597e-05,
"loss": 0.2599,
"step": 414
},
{
"epoch": 3.0976525821596246,
"grad_norm": 1.2734375,
"learning_rate": 3.455223880597015e-05,
"loss": 0.3066,
"step": 415
},
{
"epoch": 3.1051643192488263,
"grad_norm": 1.125,
"learning_rate": 3.451492537313433e-05,
"loss": 0.266,
"step": 416
},
{
"epoch": 3.112676056338028,
"grad_norm": 1.0859375,
"learning_rate": 3.447761194029851e-05,
"loss": 0.3201,
"step": 417
},
{
"epoch": 3.12018779342723,
"grad_norm": 0.89453125,
"learning_rate": 3.444029850746269e-05,
"loss": 0.1919,
"step": 418
},
{
"epoch": 3.127699530516432,
"grad_norm": 1.1640625,
"learning_rate": 3.440298507462687e-05,
"loss": 0.3906,
"step": 419
},
{
"epoch": 3.1352112676056336,
"grad_norm": 1.078125,
"learning_rate": 3.4365671641791046e-05,
"loss": 0.2502,
"step": 420
},
{
"epoch": 3.142723004694836,
"grad_norm": 1.1171875,
"learning_rate": 3.432835820895522e-05,
"loss": 0.2846,
"step": 421
},
{
"epoch": 3.1502347417840375,
"grad_norm": 1.0703125,
"learning_rate": 3.4291044776119404e-05,
"loss": 0.3431,
"step": 422
},
{
"epoch": 3.1577464788732392,
"grad_norm": 1.0859375,
"learning_rate": 3.425373134328359e-05,
"loss": 0.2536,
"step": 423
},
{
"epoch": 3.1652582159624414,
"grad_norm": 1.296875,
"learning_rate": 3.421641791044776e-05,
"loss": 0.2595,
"step": 424
},
{
"epoch": 3.172769953051643,
"grad_norm": 1.25,
"learning_rate": 3.417910447761194e-05,
"loss": 0.3605,
"step": 425
},
{
"epoch": 3.1802816901408453,
"grad_norm": 1.59375,
"learning_rate": 3.414179104477612e-05,
"loss": 0.4784,
"step": 426
},
{
"epoch": 3.187793427230047,
"grad_norm": 1.203125,
"learning_rate": 3.41044776119403e-05,
"loss": 0.2589,
"step": 427
},
{
"epoch": 3.1953051643192487,
"grad_norm": 1.328125,
"learning_rate": 3.406716417910448e-05,
"loss": 0.2985,
"step": 428
},
{
"epoch": 3.202816901408451,
"grad_norm": 1.4375,
"learning_rate": 3.402985074626866e-05,
"loss": 0.2615,
"step": 429
},
{
"epoch": 3.2103286384976526,
"grad_norm": 1.140625,
"learning_rate": 3.399253731343284e-05,
"loss": 0.2181,
"step": 430
},
{
"epoch": 3.2178403755868543,
"grad_norm": 1.2109375,
"learning_rate": 3.395522388059701e-05,
"loss": 0.3046,
"step": 431
},
{
"epoch": 3.2253521126760565,
"grad_norm": 1.1171875,
"learning_rate": 3.3917910447761196e-05,
"loss": 0.2563,
"step": 432
},
{
"epoch": 3.232863849765258,
"grad_norm": 0.98046875,
"learning_rate": 3.388059701492537e-05,
"loss": 0.2574,
"step": 433
},
{
"epoch": 3.24037558685446,
"grad_norm": 1.0625,
"learning_rate": 3.3843283582089554e-05,
"loss": 0.2544,
"step": 434
},
{
"epoch": 3.247887323943662,
"grad_norm": 1.0078125,
"learning_rate": 3.380597014925374e-05,
"loss": 0.2205,
"step": 435
},
{
"epoch": 3.255399061032864,
"grad_norm": 0.9453125,
"learning_rate": 3.376865671641791e-05,
"loss": 0.2099,
"step": 436
},
{
"epoch": 3.262910798122066,
"grad_norm": 1.0703125,
"learning_rate": 3.373134328358209e-05,
"loss": 0.3441,
"step": 437
},
{
"epoch": 3.2704225352112677,
"grad_norm": 1.1484375,
"learning_rate": 3.369402985074627e-05,
"loss": 0.2991,
"step": 438
},
{
"epoch": 3.2779342723004694,
"grad_norm": 1.1953125,
"learning_rate": 3.365671641791045e-05,
"loss": 0.2694,
"step": 439
},
{
"epoch": 3.2854460093896716,
"grad_norm": 0.9765625,
"learning_rate": 3.361940298507463e-05,
"loss": 0.2535,
"step": 440
},
{
"epoch": 3.2929577464788733,
"grad_norm": 1.4375,
"learning_rate": 3.358208955223881e-05,
"loss": 0.3394,
"step": 441
},
{
"epoch": 3.300469483568075,
"grad_norm": 1.3984375,
"learning_rate": 3.354477611940299e-05,
"loss": 0.4334,
"step": 442
},
{
"epoch": 3.307981220657277,
"grad_norm": 1.1875,
"learning_rate": 3.350746268656716e-05,
"loss": 0.3504,
"step": 443
},
{
"epoch": 3.315492957746479,
"grad_norm": 1.1953125,
"learning_rate": 3.347014925373134e-05,
"loss": 0.3178,
"step": 444
},
{
"epoch": 3.3230046948356806,
"grad_norm": 1.140625,
"learning_rate": 3.343283582089553e-05,
"loss": 0.4878,
"step": 445
},
{
"epoch": 3.330516431924883,
"grad_norm": 1.1328125,
"learning_rate": 3.3395522388059704e-05,
"loss": 0.3015,
"step": 446
},
{
"epoch": 3.3380281690140845,
"grad_norm": 1.3203125,
"learning_rate": 3.335820895522388e-05,
"loss": 0.2809,
"step": 447
},
{
"epoch": 3.345539906103286,
"grad_norm": 1.234375,
"learning_rate": 3.332089552238806e-05,
"loss": 0.2838,
"step": 448
},
{
"epoch": 3.3530516431924884,
"grad_norm": 1.1015625,
"learning_rate": 3.328358208955224e-05,
"loss": 0.2251,
"step": 449
},
{
"epoch": 3.36056338028169,
"grad_norm": 1.203125,
"learning_rate": 3.3246268656716414e-05,
"loss": 0.3665,
"step": 450
},
{
"epoch": 3.368075117370892,
"grad_norm": 1.203125,
"learning_rate": 3.32089552238806e-05,
"loss": 0.3966,
"step": 451
},
{
"epoch": 3.375586854460094,
"grad_norm": 1.296875,
"learning_rate": 3.317164179104478e-05,
"loss": 0.2999,
"step": 452
},
{
"epoch": 3.3830985915492957,
"grad_norm": 1.0625,
"learning_rate": 3.3134328358208955e-05,
"loss": 0.2774,
"step": 453
},
{
"epoch": 3.3906103286384974,
"grad_norm": 1.2109375,
"learning_rate": 3.309701492537314e-05,
"loss": 0.4075,
"step": 454
},
{
"epoch": 3.3981220657276996,
"grad_norm": 1.171875,
"learning_rate": 3.305970149253731e-05,
"loss": 0.2425,
"step": 455
},
{
"epoch": 3.4056338028169013,
"grad_norm": 1.1328125,
"learning_rate": 3.302238805970149e-05,
"loss": 0.3725,
"step": 456
},
{
"epoch": 3.4131455399061035,
"grad_norm": 1.1328125,
"learning_rate": 3.298507462686568e-05,
"loss": 0.2723,
"step": 457
},
{
"epoch": 3.420657276995305,
"grad_norm": 1.15625,
"learning_rate": 3.2947761194029854e-05,
"loss": 0.3451,
"step": 458
},
{
"epoch": 3.428169014084507,
"grad_norm": 1.0078125,
"learning_rate": 3.291044776119403e-05,
"loss": 0.251,
"step": 459
},
{
"epoch": 3.435680751173709,
"grad_norm": 1.1953125,
"learning_rate": 3.287313432835821e-05,
"loss": 0.3167,
"step": 460
},
{
"epoch": 3.443192488262911,
"grad_norm": 1.140625,
"learning_rate": 3.283582089552239e-05,
"loss": 0.2979,
"step": 461
},
{
"epoch": 3.4507042253521125,
"grad_norm": 1.203125,
"learning_rate": 3.279850746268657e-05,
"loss": 0.2733,
"step": 462
},
{
"epoch": 3.4582159624413147,
"grad_norm": 1.140625,
"learning_rate": 3.276119402985075e-05,
"loss": 0.5612,
"step": 463
},
{
"epoch": 3.4657276995305164,
"grad_norm": 1.1640625,
"learning_rate": 3.272388059701493e-05,
"loss": 0.3,
"step": 464
},
{
"epoch": 3.473239436619718,
"grad_norm": 1.09375,
"learning_rate": 3.2686567164179105e-05,
"loss": 0.3114,
"step": 465
},
{
"epoch": 3.4807511737089203,
"grad_norm": 1.9609375,
"learning_rate": 3.264925373134329e-05,
"loss": 0.4609,
"step": 466
},
{
"epoch": 3.488262910798122,
"grad_norm": 1.40625,
"learning_rate": 3.261194029850746e-05,
"loss": 0.3911,
"step": 467
},
{
"epoch": 3.495774647887324,
"grad_norm": 1.265625,
"learning_rate": 3.2574626865671646e-05,
"loss": 0.3526,
"step": 468
},
{
"epoch": 3.503286384976526,
"grad_norm": 1.1328125,
"learning_rate": 3.253731343283582e-05,
"loss": 0.2948,
"step": 469
},
{
"epoch": 3.5107981220657276,
"grad_norm": 1.2890625,
"learning_rate": 3.2500000000000004e-05,
"loss": 0.3205,
"step": 470
},
{
"epoch": 3.5183098591549298,
"grad_norm": 0.95703125,
"learning_rate": 3.246268656716418e-05,
"loss": 0.2793,
"step": 471
},
{
"epoch": 3.5258215962441315,
"grad_norm": 1.390625,
"learning_rate": 3.2425373134328355e-05,
"loss": 0.2795,
"step": 472
},
{
"epoch": 3.533333333333333,
"grad_norm": 0.859375,
"learning_rate": 3.238805970149254e-05,
"loss": 0.2497,
"step": 473
},
{
"epoch": 3.5408450704225354,
"grad_norm": 1.125,
"learning_rate": 3.235074626865672e-05,
"loss": 0.2743,
"step": 474
},
{
"epoch": 3.548356807511737,
"grad_norm": 0.94140625,
"learning_rate": 3.2313432835820896e-05,
"loss": 0.2061,
"step": 475
},
{
"epoch": 3.555868544600939,
"grad_norm": 1.3203125,
"learning_rate": 3.227611940298508e-05,
"loss": 0.3852,
"step": 476
},
{
"epoch": 3.563380281690141,
"grad_norm": 1.1015625,
"learning_rate": 3.2238805970149255e-05,
"loss": 0.2777,
"step": 477
},
{
"epoch": 3.5708920187793427,
"grad_norm": 1.140625,
"learning_rate": 3.220149253731343e-05,
"loss": 0.2988,
"step": 478
},
{
"epoch": 3.5784037558685444,
"grad_norm": 1.1015625,
"learning_rate": 3.216417910447761e-05,
"loss": 0.2646,
"step": 479
},
{
"epoch": 3.5859154929577466,
"grad_norm": 1.125,
"learning_rate": 3.2126865671641796e-05,
"loss": 0.2648,
"step": 480
},
{
"epoch": 3.5934272300469483,
"grad_norm": 1.2421875,
"learning_rate": 3.208955223880597e-05,
"loss": 0.3574,
"step": 481
},
{
"epoch": 3.60093896713615,
"grad_norm": 1.21875,
"learning_rate": 3.2052238805970154e-05,
"loss": 0.2751,
"step": 482
},
{
"epoch": 3.608450704225352,
"grad_norm": 1.2265625,
"learning_rate": 3.201492537313433e-05,
"loss": 0.2955,
"step": 483
},
{
"epoch": 3.615962441314554,
"grad_norm": 0.99609375,
"learning_rate": 3.1977611940298505e-05,
"loss": 0.2677,
"step": 484
},
{
"epoch": 3.6234741784037556,
"grad_norm": 1.2421875,
"learning_rate": 3.194029850746269e-05,
"loss": 0.3071,
"step": 485
},
{
"epoch": 3.630985915492958,
"grad_norm": 1.25,
"learning_rate": 3.190298507462687e-05,
"loss": 0.3171,
"step": 486
},
{
"epoch": 3.6384976525821595,
"grad_norm": 1.296875,
"learning_rate": 3.1865671641791046e-05,
"loss": 0.2817,
"step": 487
},
{
"epoch": 3.6460093896713612,
"grad_norm": 6.4375,
"learning_rate": 3.182835820895523e-05,
"loss": 0.4779,
"step": 488
},
{
"epoch": 3.6535211267605634,
"grad_norm": 1.0,
"learning_rate": 3.1791044776119405e-05,
"loss": 0.2539,
"step": 489
},
{
"epoch": 3.661032863849765,
"grad_norm": 1.0859375,
"learning_rate": 3.175373134328358e-05,
"loss": 0.2517,
"step": 490
},
{
"epoch": 3.6685446009389673,
"grad_norm": 1.1875,
"learning_rate": 3.171641791044776e-05,
"loss": 0.2995,
"step": 491
},
{
"epoch": 3.676056338028169,
"grad_norm": 1.40625,
"learning_rate": 3.1679104477611945e-05,
"loss": 0.3996,
"step": 492
},
{
"epoch": 3.683568075117371,
"grad_norm": 1.21875,
"learning_rate": 3.164179104477612e-05,
"loss": 0.367,
"step": 493
},
{
"epoch": 3.691079812206573,
"grad_norm": 1.2265625,
"learning_rate": 3.16044776119403e-05,
"loss": 0.216,
"step": 494
},
{
"epoch": 3.6985915492957746,
"grad_norm": 1.234375,
"learning_rate": 3.156716417910448e-05,
"loss": 0.3269,
"step": 495
},
{
"epoch": 3.7061032863849768,
"grad_norm": 1.421875,
"learning_rate": 3.1529850746268655e-05,
"loss": 0.3337,
"step": 496
},
{
"epoch": 3.7136150234741785,
"grad_norm": 1.265625,
"learning_rate": 3.149253731343284e-05,
"loss": 0.3343,
"step": 497
},
{
"epoch": 3.72112676056338,
"grad_norm": 1.796875,
"learning_rate": 3.145522388059702e-05,
"loss": 0.3311,
"step": 498
},
{
"epoch": 3.7286384976525824,
"grad_norm": 1.1015625,
"learning_rate": 3.1417910447761196e-05,
"loss": 0.3231,
"step": 499
},
{
"epoch": 3.736150234741784,
"grad_norm": 1.2578125,
"learning_rate": 3.138059701492537e-05,
"loss": 0.226,
"step": 500
},
{
"epoch": 3.743661971830986,
"grad_norm": 1.09375,
"learning_rate": 3.1343283582089554e-05,
"loss": 0.2367,
"step": 501
},
{
"epoch": 3.751173708920188,
"grad_norm": 1.28125,
"learning_rate": 3.130597014925373e-05,
"loss": 0.3148,
"step": 502
},
{
"epoch": 3.7586854460093897,
"grad_norm": 1.0390625,
"learning_rate": 3.126865671641791e-05,
"loss": 0.4082,
"step": 503
},
{
"epoch": 3.7661971830985914,
"grad_norm": 1.1484375,
"learning_rate": 3.1231343283582095e-05,
"loss": 0.3441,
"step": 504
},
{
"epoch": 3.7737089201877936,
"grad_norm": 1.203125,
"learning_rate": 3.119402985074627e-05,
"loss": 0.3403,
"step": 505
},
{
"epoch": 3.7812206572769953,
"grad_norm": 1.109375,
"learning_rate": 3.115671641791045e-05,
"loss": 0.303,
"step": 506
},
{
"epoch": 3.788732394366197,
"grad_norm": 1.1015625,
"learning_rate": 3.111940298507463e-05,
"loss": 0.2613,
"step": 507
},
{
"epoch": 3.796244131455399,
"grad_norm": 1.1328125,
"learning_rate": 3.1082089552238805e-05,
"loss": 0.2781,
"step": 508
},
{
"epoch": 3.803755868544601,
"grad_norm": 1.0625,
"learning_rate": 3.104477611940299e-05,
"loss": 0.268,
"step": 509
},
{
"epoch": 3.8112676056338026,
"grad_norm": 1.0234375,
"learning_rate": 3.100746268656717e-05,
"loss": 0.2663,
"step": 510
},
{
"epoch": 3.818779342723005,
"grad_norm": 1.1484375,
"learning_rate": 3.0970149253731346e-05,
"loss": 0.3102,
"step": 511
},
{
"epoch": 3.8262910798122065,
"grad_norm": 1.1953125,
"learning_rate": 3.093283582089552e-05,
"loss": 0.4035,
"step": 512
},
{
"epoch": 3.8338028169014082,
"grad_norm": 1.1015625,
"learning_rate": 3.0895522388059704e-05,
"loss": 0.2987,
"step": 513
},
{
"epoch": 3.8413145539906104,
"grad_norm": 1.15625,
"learning_rate": 3.085820895522388e-05,
"loss": 0.2892,
"step": 514
},
{
"epoch": 3.848826291079812,
"grad_norm": 1.03125,
"learning_rate": 3.082089552238806e-05,
"loss": 0.4299,
"step": 515
},
{
"epoch": 3.856338028169014,
"grad_norm": 1.171875,
"learning_rate": 3.078358208955224e-05,
"loss": 0.3571,
"step": 516
},
{
"epoch": 3.863849765258216,
"grad_norm": 1.421875,
"learning_rate": 3.074626865671642e-05,
"loss": 0.4082,
"step": 517
},
{
"epoch": 3.8713615023474177,
"grad_norm": 1.109375,
"learning_rate": 3.07089552238806e-05,
"loss": 0.3317,
"step": 518
},
{
"epoch": 3.87887323943662,
"grad_norm": 1.375,
"learning_rate": 3.067164179104477e-05,
"loss": 0.3549,
"step": 519
},
{
"epoch": 3.8863849765258216,
"grad_norm": 1.1171875,
"learning_rate": 3.0634328358208955e-05,
"loss": 0.2538,
"step": 520
},
{
"epoch": 3.8938967136150233,
"grad_norm": 1.0703125,
"learning_rate": 3.059701492537314e-05,
"loss": 0.2683,
"step": 521
},
{
"epoch": 3.9014084507042255,
"grad_norm": 1.21875,
"learning_rate": 3.055970149253731e-05,
"loss": 0.3572,
"step": 522
},
{
"epoch": 3.908920187793427,
"grad_norm": 1.125,
"learning_rate": 3.0522388059701496e-05,
"loss": 0.2967,
"step": 523
},
{
"epoch": 3.9164319248826294,
"grad_norm": 1.390625,
"learning_rate": 3.0485074626865672e-05,
"loss": 0.3288,
"step": 524
},
{
"epoch": 3.923943661971831,
"grad_norm": 1.1796875,
"learning_rate": 3.044776119402985e-05,
"loss": 0.2934,
"step": 525
},
{
"epoch": 3.931455399061033,
"grad_norm": 1.125,
"learning_rate": 3.0410447761194033e-05,
"loss": 0.3035,
"step": 526
},
{
"epoch": 3.938967136150235,
"grad_norm": 1.0390625,
"learning_rate": 3.037313432835821e-05,
"loss": 0.2851,
"step": 527
},
{
"epoch": 3.9464788732394367,
"grad_norm": 0.9765625,
"learning_rate": 3.033582089552239e-05,
"loss": 0.2385,
"step": 528
},
{
"epoch": 3.9539906103286384,
"grad_norm": 1.0859375,
"learning_rate": 3.029850746268657e-05,
"loss": 0.2407,
"step": 529
},
{
"epoch": 3.9615023474178406,
"grad_norm": 1.140625,
"learning_rate": 3.0261194029850747e-05,
"loss": 0.273,
"step": 530
},
{
"epoch": 3.9690140845070423,
"grad_norm": 1.140625,
"learning_rate": 3.0223880597014926e-05,
"loss": 0.4011,
"step": 531
},
{
"epoch": 3.976525821596244,
"grad_norm": 1.09375,
"learning_rate": 3.018656716417911e-05,
"loss": 0.2457,
"step": 532
},
{
"epoch": 3.984037558685446,
"grad_norm": 1.2421875,
"learning_rate": 3.0149253731343284e-05,
"loss": 0.3084,
"step": 533
},
{
"epoch": 3.991549295774648,
"grad_norm": 1.1328125,
"learning_rate": 3.0111940298507463e-05,
"loss": 0.2906,
"step": 534
},
{
"epoch": 3.9990610328638496,
"grad_norm": 1.1953125,
"learning_rate": 3.0074626865671646e-05,
"loss": 0.3793,
"step": 535
},
{
"epoch": 4.0,
"grad_norm": 4.125,
"learning_rate": 3.003731343283582e-05,
"loss": 0.3955,
"step": 536
},
{
"epoch": 4.007511737089202,
"grad_norm": 1.21875,
"learning_rate": 3e-05,
"loss": 0.2192,
"step": 537
},
{
"epoch": 4.015023474178403,
"grad_norm": 1.125,
"learning_rate": 2.9962686567164183e-05,
"loss": 0.2237,
"step": 538
},
{
"epoch": 4.022535211267606,
"grad_norm": 1.0546875,
"learning_rate": 2.992537313432836e-05,
"loss": 0.2136,
"step": 539
},
{
"epoch": 4.030046948356808,
"grad_norm": 1.078125,
"learning_rate": 2.9888059701492538e-05,
"loss": 0.1825,
"step": 540
},
{
"epoch": 4.037558685446009,
"grad_norm": 1.0546875,
"learning_rate": 2.9850746268656714e-05,
"loss": 0.1888,
"step": 541
},
{
"epoch": 4.045070422535211,
"grad_norm": 1.296875,
"learning_rate": 2.9813432835820897e-05,
"loss": 0.2012,
"step": 542
},
{
"epoch": 4.052582159624413,
"grad_norm": 1.5,
"learning_rate": 2.9776119402985076e-05,
"loss": 0.1892,
"step": 543
},
{
"epoch": 4.060093896713615,
"grad_norm": 1.8671875,
"learning_rate": 2.973880597014925e-05,
"loss": 0.2194,
"step": 544
},
{
"epoch": 4.067605633802817,
"grad_norm": 1.390625,
"learning_rate": 2.9701492537313434e-05,
"loss": 0.2948,
"step": 545
},
{
"epoch": 4.075117370892019,
"grad_norm": 1.7578125,
"learning_rate": 2.9664179104477613e-05,
"loss": 0.2072,
"step": 546
},
{
"epoch": 4.08262910798122,
"grad_norm": 1.890625,
"learning_rate": 2.962686567164179e-05,
"loss": 0.2474,
"step": 547
},
{
"epoch": 4.090140845070422,
"grad_norm": 1.5859375,
"learning_rate": 2.958955223880597e-05,
"loss": 0.2302,
"step": 548
},
{
"epoch": 4.097652582159625,
"grad_norm": 1.3203125,
"learning_rate": 2.955223880597015e-05,
"loss": 0.2129,
"step": 549
},
{
"epoch": 4.105164319248826,
"grad_norm": 1.1796875,
"learning_rate": 2.9514925373134326e-05,
"loss": 0.2074,
"step": 550
},
{
"epoch": 4.112676056338028,
"grad_norm": 1.1875,
"learning_rate": 2.9477611940298512e-05,
"loss": 0.206,
"step": 551
},
{
"epoch": 4.12018779342723,
"grad_norm": 1.0625,
"learning_rate": 2.9440298507462688e-05,
"loss": 0.1677,
"step": 552
},
{
"epoch": 4.127699530516432,
"grad_norm": 1.078125,
"learning_rate": 2.9402985074626864e-05,
"loss": 0.1773,
"step": 553
},
{
"epoch": 4.135211267605634,
"grad_norm": 1.1328125,
"learning_rate": 2.936567164179105e-05,
"loss": 0.1995,
"step": 554
},
{
"epoch": 4.142723004694836,
"grad_norm": 1.5625,
"learning_rate": 2.9328358208955226e-05,
"loss": 0.283,
"step": 555
},
{
"epoch": 4.150234741784038,
"grad_norm": 1.4296875,
"learning_rate": 2.92910447761194e-05,
"loss": 0.3608,
"step": 556
},
{
"epoch": 4.157746478873239,
"grad_norm": 1.1015625,
"learning_rate": 2.9253731343283587e-05,
"loss": 0.2016,
"step": 557
},
{
"epoch": 4.165258215962441,
"grad_norm": 1.28125,
"learning_rate": 2.9216417910447763e-05,
"loss": 0.2631,
"step": 558
},
{
"epoch": 4.1727699530516436,
"grad_norm": 1.171875,
"learning_rate": 2.917910447761194e-05,
"loss": 0.1979,
"step": 559
},
{
"epoch": 4.180281690140845,
"grad_norm": 1.3515625,
"learning_rate": 2.9141791044776125e-05,
"loss": 0.2198,
"step": 560
},
{
"epoch": 4.187793427230047,
"grad_norm": 1.25,
"learning_rate": 2.91044776119403e-05,
"loss": 0.1828,
"step": 561
},
{
"epoch": 4.195305164319249,
"grad_norm": 1.546875,
"learning_rate": 2.9067164179104476e-05,
"loss": 0.2584,
"step": 562
},
{
"epoch": 4.20281690140845,
"grad_norm": 1.21875,
"learning_rate": 2.9029850746268662e-05,
"loss": 0.1783,
"step": 563
},
{
"epoch": 4.210328638497653,
"grad_norm": 1.3203125,
"learning_rate": 2.8992537313432838e-05,
"loss": 0.2071,
"step": 564
},
{
"epoch": 4.217840375586855,
"grad_norm": 1.2890625,
"learning_rate": 2.8955223880597017e-05,
"loss": 0.2298,
"step": 565
},
{
"epoch": 4.225352112676056,
"grad_norm": 1.0859375,
"learning_rate": 2.8917910447761193e-05,
"loss": 0.1265,
"step": 566
},
{
"epoch": 4.232863849765258,
"grad_norm": 1.390625,
"learning_rate": 2.8880597014925376e-05,
"loss": 0.2881,
"step": 567
},
{
"epoch": 4.24037558685446,
"grad_norm": 1.265625,
"learning_rate": 2.8843283582089555e-05,
"loss": 0.2023,
"step": 568
},
{
"epoch": 4.247887323943662,
"grad_norm": 1.1328125,
"learning_rate": 2.880597014925373e-05,
"loss": 0.1748,
"step": 569
},
{
"epoch": 4.255399061032864,
"grad_norm": 1.078125,
"learning_rate": 2.8768656716417913e-05,
"loss": 0.1945,
"step": 570
},
{
"epoch": 4.262910798122066,
"grad_norm": 1.2109375,
"learning_rate": 2.8731343283582092e-05,
"loss": 0.249,
"step": 571
},
{
"epoch": 4.270422535211267,
"grad_norm": 5.15625,
"learning_rate": 2.8694029850746268e-05,
"loss": 0.2944,
"step": 572
},
{
"epoch": 4.277934272300469,
"grad_norm": 1.2109375,
"learning_rate": 2.865671641791045e-05,
"loss": 0.268,
"step": 573
},
{
"epoch": 4.285446009389672,
"grad_norm": 1.15625,
"learning_rate": 2.861940298507463e-05,
"loss": 0.2261,
"step": 574
},
{
"epoch": 4.292957746478873,
"grad_norm": 1.2421875,
"learning_rate": 2.8582089552238805e-05,
"loss": 0.2299,
"step": 575
},
{
"epoch": 4.300469483568075,
"grad_norm": 1.4140625,
"learning_rate": 2.8544776119402988e-05,
"loss": 0.2149,
"step": 576
},
{
"epoch": 4.307981220657277,
"grad_norm": 2.265625,
"learning_rate": 2.8507462686567167e-05,
"loss": 0.3157,
"step": 577
},
{
"epoch": 4.3154929577464785,
"grad_norm": 2.546875,
"learning_rate": 2.8470149253731343e-05,
"loss": 0.3262,
"step": 578
},
{
"epoch": 4.323004694835681,
"grad_norm": 1.171875,
"learning_rate": 2.8432835820895525e-05,
"loss": 0.2183,
"step": 579
},
{
"epoch": 4.330516431924883,
"grad_norm": 1.1875,
"learning_rate": 2.8395522388059705e-05,
"loss": 0.1779,
"step": 580
},
{
"epoch": 4.338028169014084,
"grad_norm": 1.171875,
"learning_rate": 2.835820895522388e-05,
"loss": 0.1742,
"step": 581
},
{
"epoch": 4.345539906103286,
"grad_norm": 1.15625,
"learning_rate": 2.8320895522388063e-05,
"loss": 0.191,
"step": 582
},
{
"epoch": 4.353051643192488,
"grad_norm": 1.453125,
"learning_rate": 2.8283582089552242e-05,
"loss": 0.3915,
"step": 583
},
{
"epoch": 4.3605633802816905,
"grad_norm": 1.3984375,
"learning_rate": 2.8246268656716418e-05,
"loss": 0.2613,
"step": 584
},
{
"epoch": 4.368075117370892,
"grad_norm": 1.2421875,
"learning_rate": 2.82089552238806e-05,
"loss": 0.2701,
"step": 585
},
{
"epoch": 4.375586854460094,
"grad_norm": 1.21875,
"learning_rate": 2.817164179104478e-05,
"loss": 0.2133,
"step": 586
},
{
"epoch": 4.383098591549296,
"grad_norm": 1.3203125,
"learning_rate": 2.8134328358208955e-05,
"loss": 0.2844,
"step": 587
},
{
"epoch": 4.390610328638497,
"grad_norm": 1.2109375,
"learning_rate": 2.8097014925373134e-05,
"loss": 0.2141,
"step": 588
},
{
"epoch": 4.3981220657277,
"grad_norm": 1.265625,
"learning_rate": 2.8059701492537317e-05,
"loss": 0.184,
"step": 589
},
{
"epoch": 4.405633802816902,
"grad_norm": 1.09375,
"learning_rate": 2.8022388059701493e-05,
"loss": 0.1307,
"step": 590
},
{
"epoch": 4.413145539906103,
"grad_norm": 1.25,
"learning_rate": 2.7985074626865672e-05,
"loss": 0.3037,
"step": 591
},
{
"epoch": 4.420657276995305,
"grad_norm": 0.96484375,
"learning_rate": 2.7947761194029854e-05,
"loss": 0.1229,
"step": 592
},
{
"epoch": 4.428169014084507,
"grad_norm": 1.203125,
"learning_rate": 2.791044776119403e-05,
"loss": 0.1999,
"step": 593
},
{
"epoch": 4.435680751173709,
"grad_norm": 1.21875,
"learning_rate": 2.787313432835821e-05,
"loss": 0.2231,
"step": 594
},
{
"epoch": 4.443192488262911,
"grad_norm": 1.171875,
"learning_rate": 2.7835820895522392e-05,
"loss": 0.1836,
"step": 595
},
{
"epoch": 4.450704225352113,
"grad_norm": 1.171875,
"learning_rate": 2.7798507462686568e-05,
"loss": 0.2028,
"step": 596
},
{
"epoch": 4.458215962441314,
"grad_norm": 3.40625,
"learning_rate": 2.7761194029850747e-05,
"loss": 0.3321,
"step": 597
},
{
"epoch": 4.465727699530516,
"grad_norm": 2.390625,
"learning_rate": 2.772388059701493e-05,
"loss": 0.285,
"step": 598
},
{
"epoch": 4.473239436619719,
"grad_norm": 1.2109375,
"learning_rate": 2.7686567164179105e-05,
"loss": 0.2116,
"step": 599
},
{
"epoch": 4.48075117370892,
"grad_norm": 1.1796875,
"learning_rate": 2.7649253731343284e-05,
"loss": 0.1738,
"step": 600
},
{
"epoch": 4.488262910798122,
"grad_norm": 1.1171875,
"learning_rate": 2.7611940298507467e-05,
"loss": 0.1857,
"step": 601
},
{
"epoch": 4.495774647887324,
"grad_norm": 1.1640625,
"learning_rate": 2.7574626865671643e-05,
"loss": 0.1895,
"step": 602
},
{
"epoch": 4.5032863849765254,
"grad_norm": 1.15625,
"learning_rate": 2.7537313432835822e-05,
"loss": 0.1901,
"step": 603
},
{
"epoch": 4.510798122065728,
"grad_norm": 1.2734375,
"learning_rate": 2.7500000000000004e-05,
"loss": 0.2366,
"step": 604
},
{
"epoch": 4.51830985915493,
"grad_norm": 1.2734375,
"learning_rate": 2.746268656716418e-05,
"loss": 0.206,
"step": 605
},
{
"epoch": 4.525821596244132,
"grad_norm": 1.2265625,
"learning_rate": 2.742537313432836e-05,
"loss": 0.379,
"step": 606
},
{
"epoch": 4.533333333333333,
"grad_norm": 1.2265625,
"learning_rate": 2.7388059701492542e-05,
"loss": 0.5791,
"step": 607
},
{
"epoch": 4.540845070422535,
"grad_norm": 1.25,
"learning_rate": 2.7350746268656718e-05,
"loss": 0.1957,
"step": 608
},
{
"epoch": 4.5483568075117375,
"grad_norm": 1.140625,
"learning_rate": 2.7313432835820897e-05,
"loss": 0.2482,
"step": 609
},
{
"epoch": 4.555868544600939,
"grad_norm": 1.109375,
"learning_rate": 2.727611940298508e-05,
"loss": 0.1431,
"step": 610
},
{
"epoch": 4.563380281690141,
"grad_norm": 1.296875,
"learning_rate": 2.7238805970149255e-05,
"loss": 0.2122,
"step": 611
},
{
"epoch": 4.570892018779343,
"grad_norm": 1.2265625,
"learning_rate": 2.7201492537313434e-05,
"loss": 0.1462,
"step": 612
},
{
"epoch": 4.578403755868544,
"grad_norm": 1.3359375,
"learning_rate": 2.716417910447761e-05,
"loss": 0.2386,
"step": 613
},
{
"epoch": 4.585915492957747,
"grad_norm": 1.2421875,
"learning_rate": 2.7126865671641793e-05,
"loss": 0.2615,
"step": 614
},
{
"epoch": 4.593427230046949,
"grad_norm": 1.2421875,
"learning_rate": 2.7089552238805972e-05,
"loss": 0.2149,
"step": 615
},
{
"epoch": 4.60093896713615,
"grad_norm": 1.234375,
"learning_rate": 2.7052238805970147e-05,
"loss": 0.2781,
"step": 616
},
{
"epoch": 4.608450704225352,
"grad_norm": 1.4140625,
"learning_rate": 2.701492537313433e-05,
"loss": 0.2847,
"step": 617
},
{
"epoch": 4.615962441314554,
"grad_norm": 1.1328125,
"learning_rate": 2.697761194029851e-05,
"loss": 0.179,
"step": 618
},
{
"epoch": 4.623474178403756,
"grad_norm": 1.171875,
"learning_rate": 2.6940298507462685e-05,
"loss": 0.1893,
"step": 619
},
{
"epoch": 4.630985915492958,
"grad_norm": 1.1875,
"learning_rate": 2.6902985074626868e-05,
"loss": 0.2808,
"step": 620
},
{
"epoch": 4.63849765258216,
"grad_norm": 1.1796875,
"learning_rate": 2.6865671641791047e-05,
"loss": 0.2442,
"step": 621
},
{
"epoch": 4.646009389671361,
"grad_norm": 1.34375,
"learning_rate": 2.6828358208955222e-05,
"loss": 0.203,
"step": 622
},
{
"epoch": 4.653521126760563,
"grad_norm": 1.171875,
"learning_rate": 2.6791044776119405e-05,
"loss": 0.1833,
"step": 623
},
{
"epoch": 4.661032863849766,
"grad_norm": 1.296875,
"learning_rate": 2.6753731343283584e-05,
"loss": 0.2138,
"step": 624
},
{
"epoch": 4.668544600938967,
"grad_norm": 1.3046875,
"learning_rate": 2.671641791044776e-05,
"loss": 0.2239,
"step": 625
},
{
"epoch": 4.676056338028169,
"grad_norm": 0.99609375,
"learning_rate": 2.6679104477611942e-05,
"loss": 0.1641,
"step": 626
},
{
"epoch": 4.683568075117371,
"grad_norm": 1.015625,
"learning_rate": 2.664179104477612e-05,
"loss": 0.1532,
"step": 627
},
{
"epoch": 4.691079812206572,
"grad_norm": 1.34375,
"learning_rate": 2.6604477611940297e-05,
"loss": 0.2429,
"step": 628
},
{
"epoch": 4.698591549295775,
"grad_norm": 1.1484375,
"learning_rate": 2.656716417910448e-05,
"loss": 0.1719,
"step": 629
},
{
"epoch": 4.706103286384977,
"grad_norm": 1.265625,
"learning_rate": 2.652985074626866e-05,
"loss": 0.1938,
"step": 630
},
{
"epoch": 4.713615023474178,
"grad_norm": 0.94140625,
"learning_rate": 2.6492537313432835e-05,
"loss": 0.1406,
"step": 631
},
{
"epoch": 4.72112676056338,
"grad_norm": 1.109375,
"learning_rate": 2.6455223880597017e-05,
"loss": 0.2237,
"step": 632
},
{
"epoch": 4.728638497652582,
"grad_norm": 1.1875,
"learning_rate": 2.6417910447761197e-05,
"loss": 0.1949,
"step": 633
},
{
"epoch": 4.736150234741784,
"grad_norm": 1.078125,
"learning_rate": 2.6380597014925372e-05,
"loss": 0.1467,
"step": 634
},
{
"epoch": 4.743661971830986,
"grad_norm": 1.3359375,
"learning_rate": 2.6343283582089555e-05,
"loss": 0.3206,
"step": 635
},
{
"epoch": 4.751173708920188,
"grad_norm": 1.234375,
"learning_rate": 2.6305970149253734e-05,
"loss": 0.2237,
"step": 636
},
{
"epoch": 4.758685446009389,
"grad_norm": 1.265625,
"learning_rate": 2.626865671641791e-05,
"loss": 0.215,
"step": 637
},
{
"epoch": 4.766197183098591,
"grad_norm": 1.265625,
"learning_rate": 2.623134328358209e-05,
"loss": 0.2284,
"step": 638
},
{
"epoch": 4.773708920187794,
"grad_norm": 1.40625,
"learning_rate": 2.619402985074627e-05,
"loss": 0.2274,
"step": 639
},
{
"epoch": 4.781220657276995,
"grad_norm": 1.078125,
"learning_rate": 2.6156716417910447e-05,
"loss": 0.1719,
"step": 640
},
{
"epoch": 4.788732394366197,
"grad_norm": 1.15625,
"learning_rate": 2.6119402985074626e-05,
"loss": 0.247,
"step": 641
},
{
"epoch": 4.796244131455399,
"grad_norm": 1.1171875,
"learning_rate": 2.608208955223881e-05,
"loss": 0.2167,
"step": 642
},
{
"epoch": 4.8037558685446005,
"grad_norm": 0.97265625,
"learning_rate": 2.6044776119402985e-05,
"loss": 0.1554,
"step": 643
},
{
"epoch": 4.811267605633803,
"grad_norm": 1.25,
"learning_rate": 2.6007462686567164e-05,
"loss": 0.2615,
"step": 644
},
{
"epoch": 4.818779342723005,
"grad_norm": 1.0546875,
"learning_rate": 2.5970149253731346e-05,
"loss": 0.1838,
"step": 645
},
{
"epoch": 4.826291079812207,
"grad_norm": 1.34375,
"learning_rate": 2.5932835820895522e-05,
"loss": 0.2121,
"step": 646
},
{
"epoch": 4.833802816901408,
"grad_norm": 1.4765625,
"learning_rate": 2.58955223880597e-05,
"loss": 0.2578,
"step": 647
},
{
"epoch": 4.84131455399061,
"grad_norm": 1.140625,
"learning_rate": 2.5858208955223884e-05,
"loss": 0.1684,
"step": 648
},
{
"epoch": 4.848826291079813,
"grad_norm": 1.2421875,
"learning_rate": 2.582089552238806e-05,
"loss": 0.267,
"step": 649
},
{
"epoch": 4.856338028169014,
"grad_norm": 1.5078125,
"learning_rate": 2.578358208955224e-05,
"loss": 0.2862,
"step": 650
},
{
"epoch": 4.863849765258216,
"grad_norm": 1.3671875,
"learning_rate": 2.574626865671642e-05,
"loss": 0.2479,
"step": 651
},
{
"epoch": 4.871361502347418,
"grad_norm": 1.1328125,
"learning_rate": 2.5708955223880597e-05,
"loss": 0.1498,
"step": 652
},
{
"epoch": 4.878873239436619,
"grad_norm": 1.078125,
"learning_rate": 2.5671641791044776e-05,
"loss": 0.1611,
"step": 653
},
{
"epoch": 4.886384976525822,
"grad_norm": 1.3671875,
"learning_rate": 2.563432835820896e-05,
"loss": 0.3195,
"step": 654
},
{
"epoch": 4.893896713615024,
"grad_norm": 1.28125,
"learning_rate": 2.5597014925373135e-05,
"loss": 0.1946,
"step": 655
},
{
"epoch": 4.901408450704225,
"grad_norm": 0.98828125,
"learning_rate": 2.5559701492537314e-05,
"loss": 0.1978,
"step": 656
},
{
"epoch": 4.908920187793427,
"grad_norm": 1.25,
"learning_rate": 2.5522388059701496e-05,
"loss": 0.2309,
"step": 657
},
{
"epoch": 4.916431924882629,
"grad_norm": 1.25,
"learning_rate": 2.5485074626865672e-05,
"loss": 0.2294,
"step": 658
},
{
"epoch": 4.923943661971831,
"grad_norm": 1.3046875,
"learning_rate": 2.544776119402985e-05,
"loss": 0.2133,
"step": 659
},
{
"epoch": 4.931455399061033,
"grad_norm": 1.3046875,
"learning_rate": 2.5410447761194027e-05,
"loss": 0.2004,
"step": 660
},
{
"epoch": 4.938967136150235,
"grad_norm": 1.1640625,
"learning_rate": 2.537313432835821e-05,
"loss": 0.1762,
"step": 661
},
{
"epoch": 4.946478873239436,
"grad_norm": 1.1796875,
"learning_rate": 2.533582089552239e-05,
"loss": 0.1554,
"step": 662
},
{
"epoch": 4.953990610328638,
"grad_norm": 1.203125,
"learning_rate": 2.5298507462686565e-05,
"loss": 0.2101,
"step": 663
},
{
"epoch": 4.961502347417841,
"grad_norm": 1.125,
"learning_rate": 2.526119402985075e-05,
"loss": 0.2066,
"step": 664
},
{
"epoch": 4.969014084507043,
"grad_norm": 1.21875,
"learning_rate": 2.5223880597014926e-05,
"loss": 0.2379,
"step": 665
},
{
"epoch": 4.976525821596244,
"grad_norm": 1.140625,
"learning_rate": 2.5186567164179102e-05,
"loss": 0.2164,
"step": 666
},
{
"epoch": 4.984037558685446,
"grad_norm": 1.40625,
"learning_rate": 2.5149253731343288e-05,
"loss": 0.2609,
"step": 667
},
{
"epoch": 4.991549295774648,
"grad_norm": 1.28125,
"learning_rate": 2.5111940298507464e-05,
"loss": 0.2104,
"step": 668
},
{
"epoch": 4.99906103286385,
"grad_norm": 1.3671875,
"learning_rate": 2.507462686567164e-05,
"loss": 0.2784,
"step": 669
},
{
"epoch": 5.0,
"grad_norm": 12.5,
"learning_rate": 2.5037313432835825e-05,
"loss": 0.371,
"step": 670
},
{
"epoch": 5.007511737089202,
"grad_norm": 0.9609375,
"learning_rate": 2.5e-05,
"loss": 0.112,
"step": 671
},
{
"epoch": 5.015023474178403,
"grad_norm": 0.9765625,
"learning_rate": 2.496268656716418e-05,
"loss": 0.1188,
"step": 672
},
{
"epoch": 5.022535211267606,
"grad_norm": 1.1328125,
"learning_rate": 2.492537313432836e-05,
"loss": 0.1617,
"step": 673
},
{
"epoch": 5.030046948356808,
"grad_norm": 1.0078125,
"learning_rate": 2.488805970149254e-05,
"loss": 0.1524,
"step": 674
},
{
"epoch": 5.037558685446009,
"grad_norm": 1.109375,
"learning_rate": 2.4850746268656718e-05,
"loss": 0.1798,
"step": 675
},
{
"epoch": 5.045070422535211,
"grad_norm": 1.3671875,
"learning_rate": 2.4813432835820897e-05,
"loss": 0.1401,
"step": 676
},
{
"epoch": 5.052582159624413,
"grad_norm": 1.4140625,
"learning_rate": 2.4776119402985076e-05,
"loss": 0.1516,
"step": 677
},
{
"epoch": 5.060093896713615,
"grad_norm": 1.375,
"learning_rate": 2.4738805970149252e-05,
"loss": 0.1901,
"step": 678
},
{
"epoch": 5.067605633802817,
"grad_norm": 1.5,
"learning_rate": 2.4701492537313434e-05,
"loss": 0.1306,
"step": 679
},
{
"epoch": 5.075117370892019,
"grad_norm": 1.4765625,
"learning_rate": 2.4664179104477614e-05,
"loss": 0.1139,
"step": 680
},
{
"epoch": 5.08262910798122,
"grad_norm": 0.8984375,
"learning_rate": 2.4626865671641793e-05,
"loss": 0.0696,
"step": 681
},
{
"epoch": 5.090140845070422,
"grad_norm": 1.4453125,
"learning_rate": 2.4589552238805972e-05,
"loss": 0.1845,
"step": 682
},
{
"epoch": 5.097652582159625,
"grad_norm": 1.5390625,
"learning_rate": 2.455223880597015e-05,
"loss": 0.1631,
"step": 683
},
{
"epoch": 5.105164319248826,
"grad_norm": 1.0390625,
"learning_rate": 2.451492537313433e-05,
"loss": 0.1209,
"step": 684
},
{
"epoch": 5.112676056338028,
"grad_norm": 1.03125,
"learning_rate": 2.447761194029851e-05,
"loss": 0.1213,
"step": 685
},
{
"epoch": 5.12018779342723,
"grad_norm": 1.2421875,
"learning_rate": 2.444029850746269e-05,
"loss": 0.159,
"step": 686
},
{
"epoch": 5.127699530516432,
"grad_norm": 1.28125,
"learning_rate": 2.4402985074626868e-05,
"loss": 0.2102,
"step": 687
},
{
"epoch": 5.135211267605634,
"grad_norm": 1.09375,
"learning_rate": 2.4365671641791047e-05,
"loss": 0.136,
"step": 688
},
{
"epoch": 5.142723004694836,
"grad_norm": 1.28125,
"learning_rate": 2.4328358208955223e-05,
"loss": 0.1773,
"step": 689
},
{
"epoch": 5.150234741784038,
"grad_norm": 0.9140625,
"learning_rate": 2.4291044776119405e-05,
"loss": 0.1019,
"step": 690
},
{
"epoch": 5.157746478873239,
"grad_norm": 1.2421875,
"learning_rate": 2.4253731343283584e-05,
"loss": 0.1439,
"step": 691
},
{
"epoch": 5.165258215962441,
"grad_norm": 1.1875,
"learning_rate": 2.421641791044776e-05,
"loss": 0.2064,
"step": 692
},
{
"epoch": 5.1727699530516436,
"grad_norm": 1.1328125,
"learning_rate": 2.4179104477611943e-05,
"loss": 0.1546,
"step": 693
},
{
"epoch": 5.180281690140845,
"grad_norm": 1.3359375,
"learning_rate": 2.4141791044776122e-05,
"loss": 0.1733,
"step": 694
},
{
"epoch": 5.187793427230047,
"grad_norm": 1.1875,
"learning_rate": 2.4104477611940298e-05,
"loss": 0.1166,
"step": 695
},
{
"epoch": 5.195305164319249,
"grad_norm": 1.3046875,
"learning_rate": 2.406716417910448e-05,
"loss": 0.1439,
"step": 696
},
{
"epoch": 5.20281690140845,
"grad_norm": 1.140625,
"learning_rate": 2.402985074626866e-05,
"loss": 0.113,
"step": 697
},
{
"epoch": 5.210328638497653,
"grad_norm": 1.3125,
"learning_rate": 2.3992537313432835e-05,
"loss": 0.12,
"step": 698
},
{
"epoch": 5.217840375586855,
"grad_norm": 1.515625,
"learning_rate": 2.3955223880597018e-05,
"loss": 0.2058,
"step": 699
},
{
"epoch": 5.225352112676056,
"grad_norm": 1.125,
"learning_rate": 2.3917910447761197e-05,
"loss": 0.184,
"step": 700
},
{
"epoch": 5.232863849765258,
"grad_norm": 1.1484375,
"learning_rate": 2.3880597014925373e-05,
"loss": 0.1627,
"step": 701
},
{
"epoch": 5.24037558685446,
"grad_norm": 1.015625,
"learning_rate": 2.3843283582089555e-05,
"loss": 0.1321,
"step": 702
},
{
"epoch": 5.247887323943662,
"grad_norm": 0.9375,
"learning_rate": 2.380597014925373e-05,
"loss": 0.1394,
"step": 703
},
{
"epoch": 5.255399061032864,
"grad_norm": 1.2890625,
"learning_rate": 2.376865671641791e-05,
"loss": 0.3624,
"step": 704
},
{
"epoch": 5.262910798122066,
"grad_norm": 1.03125,
"learning_rate": 2.3731343283582093e-05,
"loss": 0.1044,
"step": 705
},
{
"epoch": 5.270422535211267,
"grad_norm": 1.4453125,
"learning_rate": 2.369402985074627e-05,
"loss": 0.174,
"step": 706
},
{
"epoch": 5.277934272300469,
"grad_norm": 1.1875,
"learning_rate": 2.3656716417910448e-05,
"loss": 0.1257,
"step": 707
},
{
"epoch": 5.285446009389672,
"grad_norm": 1.0703125,
"learning_rate": 2.361940298507463e-05,
"loss": 0.1612,
"step": 708
},
{
"epoch": 5.292957746478873,
"grad_norm": 1.2421875,
"learning_rate": 2.3582089552238806e-05,
"loss": 0.2154,
"step": 709
},
{
"epoch": 5.300469483568075,
"grad_norm": 0.94140625,
"learning_rate": 2.3544776119402985e-05,
"loss": 0.1267,
"step": 710
},
{
"epoch": 5.307981220657277,
"grad_norm": 1.1484375,
"learning_rate": 2.3507462686567168e-05,
"loss": 0.1396,
"step": 711
},
{
"epoch": 5.3154929577464785,
"grad_norm": 1.484375,
"learning_rate": 2.3470149253731343e-05,
"loss": 0.149,
"step": 712
},
{
"epoch": 5.323004694835681,
"grad_norm": 1.2265625,
"learning_rate": 2.3432835820895522e-05,
"loss": 0.1184,
"step": 713
},
{
"epoch": 5.330516431924883,
"grad_norm": 1.1015625,
"learning_rate": 2.33955223880597e-05,
"loss": 0.1294,
"step": 714
},
{
"epoch": 5.338028169014084,
"grad_norm": 1.234375,
"learning_rate": 2.335820895522388e-05,
"loss": 0.1485,
"step": 715
},
{
"epoch": 5.345539906103286,
"grad_norm": 1.25,
"learning_rate": 2.332089552238806e-05,
"loss": 0.1923,
"step": 716
},
{
"epoch": 5.353051643192488,
"grad_norm": 1.125,
"learning_rate": 2.328358208955224e-05,
"loss": 0.1342,
"step": 717
},
{
"epoch": 5.3605633802816905,
"grad_norm": 1.3046875,
"learning_rate": 2.3246268656716418e-05,
"loss": 0.1401,
"step": 718
},
{
"epoch": 5.368075117370892,
"grad_norm": 1.1015625,
"learning_rate": 2.3208955223880597e-05,
"loss": 0.1073,
"step": 719
},
{
"epoch": 5.375586854460094,
"grad_norm": 1.2109375,
"learning_rate": 2.3171641791044777e-05,
"loss": 0.1687,
"step": 720
},
{
"epoch": 5.383098591549296,
"grad_norm": 1.171875,
"learning_rate": 2.3134328358208956e-05,
"loss": 0.1367,
"step": 721
},
{
"epoch": 5.390610328638497,
"grad_norm": 1.0390625,
"learning_rate": 2.3097014925373138e-05,
"loss": 0.0987,
"step": 722
},
{
"epoch": 5.3981220657277,
"grad_norm": 1.09375,
"learning_rate": 2.3059701492537314e-05,
"loss": 0.1261,
"step": 723
},
{
"epoch": 5.405633802816902,
"grad_norm": 1.5078125,
"learning_rate": 2.3022388059701493e-05,
"loss": 0.3792,
"step": 724
},
{
"epoch": 5.413145539906103,
"grad_norm": 1.265625,
"learning_rate": 2.2985074626865672e-05,
"loss": 0.2143,
"step": 725
},
{
"epoch": 5.420657276995305,
"grad_norm": 1.2734375,
"learning_rate": 2.294776119402985e-05,
"loss": 0.2339,
"step": 726
},
{
"epoch": 5.428169014084507,
"grad_norm": 1.3359375,
"learning_rate": 2.291044776119403e-05,
"loss": 0.1666,
"step": 727
},
{
"epoch": 5.435680751173709,
"grad_norm": 1.2421875,
"learning_rate": 2.287313432835821e-05,
"loss": 0.1587,
"step": 728
},
{
"epoch": 5.443192488262911,
"grad_norm": 1.2265625,
"learning_rate": 2.283582089552239e-05,
"loss": 0.151,
"step": 729
},
{
"epoch": 5.450704225352113,
"grad_norm": 1.3828125,
"learning_rate": 2.2798507462686568e-05,
"loss": 0.1418,
"step": 730
},
{
"epoch": 5.458215962441314,
"grad_norm": 1.4765625,
"learning_rate": 2.2761194029850747e-05,
"loss": 0.1868,
"step": 731
},
{
"epoch": 5.465727699530516,
"grad_norm": 1.3828125,
"learning_rate": 2.2723880597014926e-05,
"loss": 0.1495,
"step": 732
},
{
"epoch": 5.473239436619719,
"grad_norm": 1.296875,
"learning_rate": 2.2686567164179106e-05,
"loss": 0.2444,
"step": 733
},
{
"epoch": 5.48075117370892,
"grad_norm": 1.0234375,
"learning_rate": 2.2649253731343285e-05,
"loss": 0.1009,
"step": 734
},
{
"epoch": 5.488262910798122,
"grad_norm": 1.03125,
"learning_rate": 2.2611940298507464e-05,
"loss": 0.1102,
"step": 735
},
{
"epoch": 5.495774647887324,
"grad_norm": 1.0625,
"learning_rate": 2.2574626865671643e-05,
"loss": 0.1591,
"step": 736
},
{
"epoch": 5.5032863849765254,
"grad_norm": 1.375,
"learning_rate": 2.2537313432835822e-05,
"loss": 0.18,
"step": 737
},
{
"epoch": 5.510798122065728,
"grad_norm": 1.3515625,
"learning_rate": 2.25e-05,
"loss": 0.1313,
"step": 738
},
{
"epoch": 5.51830985915493,
"grad_norm": 0.81640625,
"learning_rate": 2.246268656716418e-05,
"loss": 0.171,
"step": 739
},
{
"epoch": 5.525821596244132,
"grad_norm": 1.1796875,
"learning_rate": 2.242537313432836e-05,
"loss": 0.1132,
"step": 740
},
{
"epoch": 5.533333333333333,
"grad_norm": 1.3046875,
"learning_rate": 2.238805970149254e-05,
"loss": 0.2318,
"step": 741
},
{
"epoch": 5.540845070422535,
"grad_norm": 1.0390625,
"learning_rate": 2.2350746268656718e-05,
"loss": 0.1041,
"step": 742
},
{
"epoch": 5.5483568075117375,
"grad_norm": 1.2890625,
"learning_rate": 2.2313432835820897e-05,
"loss": 0.1265,
"step": 743
},
{
"epoch": 5.555868544600939,
"grad_norm": 1.625,
"learning_rate": 2.2276119402985076e-05,
"loss": 0.1973,
"step": 744
},
{
"epoch": 5.563380281690141,
"grad_norm": 1.3515625,
"learning_rate": 2.2238805970149256e-05,
"loss": 0.245,
"step": 745
},
{
"epoch": 5.570892018779343,
"grad_norm": 1.40625,
"learning_rate": 2.2201492537313435e-05,
"loss": 0.1469,
"step": 746
},
{
"epoch": 5.578403755868544,
"grad_norm": 1.28125,
"learning_rate": 2.2164179104477614e-05,
"loss": 0.168,
"step": 747
},
{
"epoch": 5.585915492957747,
"grad_norm": 1.3203125,
"learning_rate": 2.2126865671641793e-05,
"loss": 0.158,
"step": 748
},
{
"epoch": 5.593427230046949,
"grad_norm": 1.03125,
"learning_rate": 2.2089552238805972e-05,
"loss": 0.1159,
"step": 749
},
{
"epoch": 5.60093896713615,
"grad_norm": 1.453125,
"learning_rate": 2.2052238805970148e-05,
"loss": 0.2124,
"step": 750
},
{
"epoch": 5.608450704225352,
"grad_norm": 1.21875,
"learning_rate": 2.201492537313433e-05,
"loss": 0.181,
"step": 751
},
{
"epoch": 5.615962441314554,
"grad_norm": 1.171875,
"learning_rate": 2.197761194029851e-05,
"loss": 0.2086,
"step": 752
},
{
"epoch": 5.623474178403756,
"grad_norm": 1.125,
"learning_rate": 2.1940298507462685e-05,
"loss": 0.1678,
"step": 753
},
{
"epoch": 5.630985915492958,
"grad_norm": 1.0546875,
"learning_rate": 2.1902985074626868e-05,
"loss": 0.1135,
"step": 754
},
{
"epoch": 5.63849765258216,
"grad_norm": 1.21875,
"learning_rate": 2.1865671641791047e-05,
"loss": 0.1659,
"step": 755
},
{
"epoch": 5.646009389671361,
"grad_norm": 1.3125,
"learning_rate": 2.1828358208955223e-05,
"loss": 0.1873,
"step": 756
},
{
"epoch": 5.653521126760563,
"grad_norm": 1.046875,
"learning_rate": 2.1791044776119405e-05,
"loss": 0.1422,
"step": 757
},
{
"epoch": 5.661032863849766,
"grad_norm": 1.0625,
"learning_rate": 2.1753731343283585e-05,
"loss": 0.1386,
"step": 758
},
{
"epoch": 5.668544600938967,
"grad_norm": 1.34375,
"learning_rate": 2.171641791044776e-05,
"loss": 0.1323,
"step": 759
},
{
"epoch": 5.676056338028169,
"grad_norm": 0.984375,
"learning_rate": 2.1679104477611943e-05,
"loss": 0.1868,
"step": 760
},
{
"epoch": 5.683568075117371,
"grad_norm": 1.25,
"learning_rate": 2.164179104477612e-05,
"loss": 0.1392,
"step": 761
},
{
"epoch": 5.691079812206572,
"grad_norm": 0.9921875,
"learning_rate": 2.1604477611940298e-05,
"loss": 0.2694,
"step": 762
},
{
"epoch": 5.698591549295775,
"grad_norm": 1.1640625,
"learning_rate": 2.156716417910448e-05,
"loss": 0.1435,
"step": 763
},
{
"epoch": 5.706103286384977,
"grad_norm": 1.4453125,
"learning_rate": 2.1529850746268656e-05,
"loss": 0.1606,
"step": 764
},
{
"epoch": 5.713615023474178,
"grad_norm": 1.4296875,
"learning_rate": 2.1492537313432835e-05,
"loss": 0.4702,
"step": 765
},
{
"epoch": 5.72112676056338,
"grad_norm": 1.2734375,
"learning_rate": 2.1455223880597018e-05,
"loss": 0.1787,
"step": 766
},
{
"epoch": 5.728638497652582,
"grad_norm": 1.1875,
"learning_rate": 2.1417910447761194e-05,
"loss": 0.385,
"step": 767
},
{
"epoch": 5.736150234741784,
"grad_norm": 1.125,
"learning_rate": 2.1380597014925373e-05,
"loss": 0.1831,
"step": 768
},
{
"epoch": 5.743661971830986,
"grad_norm": 1.078125,
"learning_rate": 2.1343283582089555e-05,
"loss": 0.1037,
"step": 769
},
{
"epoch": 5.751173708920188,
"grad_norm": 1.34375,
"learning_rate": 2.130597014925373e-05,
"loss": 0.2022,
"step": 770
},
{
"epoch": 5.758685446009389,
"grad_norm": 1.203125,
"learning_rate": 2.126865671641791e-05,
"loss": 0.1255,
"step": 771
},
{
"epoch": 5.766197183098591,
"grad_norm": 1.3515625,
"learning_rate": 2.1231343283582093e-05,
"loss": 0.145,
"step": 772
},
{
"epoch": 5.773708920187794,
"grad_norm": 1.09375,
"learning_rate": 2.119402985074627e-05,
"loss": 0.1445,
"step": 773
},
{
"epoch": 5.781220657276995,
"grad_norm": 1.140625,
"learning_rate": 2.1156716417910448e-05,
"loss": 0.1954,
"step": 774
},
{
"epoch": 5.788732394366197,
"grad_norm": 1.3203125,
"learning_rate": 2.1119402985074627e-05,
"loss": 0.2458,
"step": 775
},
{
"epoch": 5.796244131455399,
"grad_norm": 1.21875,
"learning_rate": 2.1082089552238806e-05,
"loss": 0.1457,
"step": 776
},
{
"epoch": 5.8037558685446005,
"grad_norm": 1.03125,
"learning_rate": 2.1044776119402985e-05,
"loss": 0.2193,
"step": 777
},
{
"epoch": 5.811267605633803,
"grad_norm": 1.109375,
"learning_rate": 2.1007462686567164e-05,
"loss": 0.1347,
"step": 778
},
{
"epoch": 5.818779342723005,
"grad_norm": 1.1640625,
"learning_rate": 2.0970149253731344e-05,
"loss": 0.134,
"step": 779
},
{
"epoch": 5.826291079812207,
"grad_norm": 1.140625,
"learning_rate": 2.0932835820895526e-05,
"loss": 0.1581,
"step": 780
},
{
"epoch": 5.833802816901408,
"grad_norm": 1.0078125,
"learning_rate": 2.0895522388059702e-05,
"loss": 0.1612,
"step": 781
},
{
"epoch": 5.84131455399061,
"grad_norm": 1.296875,
"learning_rate": 2.085820895522388e-05,
"loss": 0.1703,
"step": 782
},
{
"epoch": 5.848826291079813,
"grad_norm": 1.125,
"learning_rate": 2.0820895522388064e-05,
"loss": 0.1335,
"step": 783
},
{
"epoch": 5.856338028169014,
"grad_norm": 1.2421875,
"learning_rate": 2.078358208955224e-05,
"loss": 0.2009,
"step": 784
},
{
"epoch": 5.863849765258216,
"grad_norm": 1.0546875,
"learning_rate": 2.074626865671642e-05,
"loss": 0.1669,
"step": 785
},
{
"epoch": 5.871361502347418,
"grad_norm": 1.1015625,
"learning_rate": 2.0708955223880598e-05,
"loss": 0.1377,
"step": 786
},
{
"epoch": 5.878873239436619,
"grad_norm": 1.3515625,
"learning_rate": 2.0671641791044777e-05,
"loss": 0.1486,
"step": 787
},
{
"epoch": 5.886384976525822,
"grad_norm": 0.99609375,
"learning_rate": 2.0634328358208956e-05,
"loss": 0.1162,
"step": 788
},
{
"epoch": 5.893896713615024,
"grad_norm": 1.140625,
"learning_rate": 2.0597014925373135e-05,
"loss": 0.1297,
"step": 789
},
{
"epoch": 5.901408450704225,
"grad_norm": 1.1796875,
"learning_rate": 2.0559701492537314e-05,
"loss": 0.1896,
"step": 790
},
{
"epoch": 5.908920187793427,
"grad_norm": 1.3671875,
"learning_rate": 2.0522388059701493e-05,
"loss": 0.1604,
"step": 791
},
{
"epoch": 5.916431924882629,
"grad_norm": 1.34375,
"learning_rate": 2.0485074626865673e-05,
"loss": 0.236,
"step": 792
},
{
"epoch": 5.923943661971831,
"grad_norm": 1.1953125,
"learning_rate": 2.0447761194029852e-05,
"loss": 0.1211,
"step": 793
},
{
"epoch": 5.931455399061033,
"grad_norm": 1.296875,
"learning_rate": 2.041044776119403e-05,
"loss": 0.131,
"step": 794
},
{
"epoch": 5.938967136150235,
"grad_norm": 1.03125,
"learning_rate": 2.037313432835821e-05,
"loss": 0.1394,
"step": 795
},
{
"epoch": 5.946478873239436,
"grad_norm": 1.046875,
"learning_rate": 2.033582089552239e-05,
"loss": 0.1314,
"step": 796
},
{
"epoch": 5.953990610328638,
"grad_norm": 1.3203125,
"learning_rate": 2.029850746268657e-05,
"loss": 0.134,
"step": 797
},
{
"epoch": 5.961502347417841,
"grad_norm": 1.2421875,
"learning_rate": 2.0261194029850748e-05,
"loss": 0.2297,
"step": 798
},
{
"epoch": 5.969014084507043,
"grad_norm": 1.390625,
"learning_rate": 2.0223880597014927e-05,
"loss": 0.1523,
"step": 799
},
{
"epoch": 5.976525821596244,
"grad_norm": 1.2265625,
"learning_rate": 2.0186567164179106e-05,
"loss": 0.1851,
"step": 800
},
{
"epoch": 5.984037558685446,
"grad_norm": 1.03125,
"learning_rate": 2.0149253731343285e-05,
"loss": 0.1212,
"step": 801
},
{
"epoch": 5.991549295774648,
"grad_norm": 0.9140625,
"learning_rate": 2.0111940298507464e-05,
"loss": 0.1094,
"step": 802
},
{
"epoch": 5.99906103286385,
"grad_norm": 1.234375,
"learning_rate": 2.0074626865671643e-05,
"loss": 0.1579,
"step": 803
},
{
"epoch": 6.0,
"grad_norm": 2.71875,
"learning_rate": 2.0037313432835822e-05,
"loss": 0.0278,
"step": 804
},
{
"epoch": 6.007511737089202,
"grad_norm": 1.0390625,
"learning_rate": 2e-05,
"loss": 0.1042,
"step": 805
},
{
"epoch": 6.015023474178403,
"grad_norm": 0.92578125,
"learning_rate": 1.996268656716418e-05,
"loss": 0.0914,
"step": 806
},
{
"epoch": 6.022535211267606,
"grad_norm": 0.94140625,
"learning_rate": 1.992537313432836e-05,
"loss": 0.1609,
"step": 807
},
{
"epoch": 6.030046948356808,
"grad_norm": 1.078125,
"learning_rate": 1.988805970149254e-05,
"loss": 0.1108,
"step": 808
},
{
"epoch": 6.037558685446009,
"grad_norm": 0.75390625,
"learning_rate": 1.9850746268656718e-05,
"loss": 0.063,
"step": 809
},
{
"epoch": 6.045070422535211,
"grad_norm": 0.88671875,
"learning_rate": 1.9813432835820897e-05,
"loss": 0.0672,
"step": 810
},
{
"epoch": 6.052582159624413,
"grad_norm": 1.234375,
"learning_rate": 1.9776119402985073e-05,
"loss": 0.1158,
"step": 811
},
{
"epoch": 6.060093896713615,
"grad_norm": 1.203125,
"learning_rate": 1.9738805970149256e-05,
"loss": 0.1054,
"step": 812
},
{
"epoch": 6.067605633802817,
"grad_norm": 1.109375,
"learning_rate": 1.9701492537313435e-05,
"loss": 0.181,
"step": 813
},
{
"epoch": 6.075117370892019,
"grad_norm": 1.6875,
"learning_rate": 1.966417910447761e-05,
"loss": 0.1623,
"step": 814
},
{
"epoch": 6.08262910798122,
"grad_norm": 1.34375,
"learning_rate": 1.9626865671641793e-05,
"loss": 0.0979,
"step": 815
},
{
"epoch": 6.090140845070422,
"grad_norm": 1.578125,
"learning_rate": 1.9589552238805972e-05,
"loss": 0.1489,
"step": 816
},
{
"epoch": 6.097652582159625,
"grad_norm": 1.2578125,
"learning_rate": 1.9552238805970148e-05,
"loss": 0.1104,
"step": 817
},
{
"epoch": 6.105164319248826,
"grad_norm": 1.5078125,
"learning_rate": 1.951492537313433e-05,
"loss": 0.0942,
"step": 818
},
{
"epoch": 6.112676056338028,
"grad_norm": 1.3203125,
"learning_rate": 1.947761194029851e-05,
"loss": 0.0802,
"step": 819
},
{
"epoch": 6.12018779342723,
"grad_norm": 1.109375,
"learning_rate": 1.9440298507462686e-05,
"loss": 0.1709,
"step": 820
},
{
"epoch": 6.127699530516432,
"grad_norm": 1.2265625,
"learning_rate": 1.9402985074626868e-05,
"loss": 0.1592,
"step": 821
},
{
"epoch": 6.135211267605634,
"grad_norm": 1.328125,
"learning_rate": 1.9365671641791044e-05,
"loss": 0.1145,
"step": 822
},
{
"epoch": 6.142723004694836,
"grad_norm": 1.09375,
"learning_rate": 1.9328358208955223e-05,
"loss": 0.2294,
"step": 823
},
{
"epoch": 6.150234741784038,
"grad_norm": 1.234375,
"learning_rate": 1.9291044776119406e-05,
"loss": 0.0945,
"step": 824
},
{
"epoch": 6.157746478873239,
"grad_norm": 0.88671875,
"learning_rate": 1.925373134328358e-05,
"loss": 0.0607,
"step": 825
},
{
"epoch": 6.165258215962441,
"grad_norm": 1.0234375,
"learning_rate": 1.921641791044776e-05,
"loss": 0.1006,
"step": 826
},
{
"epoch": 6.1727699530516436,
"grad_norm": 1.015625,
"learning_rate": 1.9179104477611943e-05,
"loss": 0.1101,
"step": 827
},
{
"epoch": 6.180281690140845,
"grad_norm": 1.0703125,
"learning_rate": 1.914179104477612e-05,
"loss": 0.0858,
"step": 828
},
{
"epoch": 6.187793427230047,
"grad_norm": 1.0703125,
"learning_rate": 1.9104477611940298e-05,
"loss": 0.1218,
"step": 829
},
{
"epoch": 6.195305164319249,
"grad_norm": 0.8984375,
"learning_rate": 1.906716417910448e-05,
"loss": 0.0886,
"step": 830
},
{
"epoch": 6.20281690140845,
"grad_norm": 1.078125,
"learning_rate": 1.9029850746268656e-05,
"loss": 0.0836,
"step": 831
},
{
"epoch": 6.210328638497653,
"grad_norm": 1.359375,
"learning_rate": 1.8992537313432836e-05,
"loss": 0.0915,
"step": 832
},
{
"epoch": 6.217840375586855,
"grad_norm": 0.8671875,
"learning_rate": 1.8955223880597015e-05,
"loss": 0.084,
"step": 833
},
{
"epoch": 6.225352112676056,
"grad_norm": 0.87109375,
"learning_rate": 1.8917910447761194e-05,
"loss": 0.0764,
"step": 834
},
{
"epoch": 6.232863849765258,
"grad_norm": 1.21875,
"learning_rate": 1.8880597014925376e-05,
"loss": 0.1105,
"step": 835
},
{
"epoch": 6.24037558685446,
"grad_norm": 1.3046875,
"learning_rate": 1.8843283582089552e-05,
"loss": 0.108,
"step": 836
},
{
"epoch": 6.247887323943662,
"grad_norm": 1.1015625,
"learning_rate": 1.880597014925373e-05,
"loss": 0.079,
"step": 837
},
{
"epoch": 6.255399061032864,
"grad_norm": 1.109375,
"learning_rate": 1.8768656716417914e-05,
"loss": 0.0765,
"step": 838
},
{
"epoch": 6.262910798122066,
"grad_norm": 1.0625,
"learning_rate": 1.873134328358209e-05,
"loss": 0.2507,
"step": 839
},
{
"epoch": 6.270422535211267,
"grad_norm": 1.3671875,
"learning_rate": 1.869402985074627e-05,
"loss": 0.1335,
"step": 840
},
{
"epoch": 6.277934272300469,
"grad_norm": 1.015625,
"learning_rate": 1.865671641791045e-05,
"loss": 0.0873,
"step": 841
},
{
"epoch": 6.285446009389672,
"grad_norm": 2.015625,
"learning_rate": 1.8619402985074627e-05,
"loss": 0.09,
"step": 842
},
{
"epoch": 6.292957746478873,
"grad_norm": 1.09375,
"learning_rate": 1.8582089552238806e-05,
"loss": 0.104,
"step": 843
},
{
"epoch": 6.300469483568075,
"grad_norm": 1.0703125,
"learning_rate": 1.854477611940299e-05,
"loss": 0.1005,
"step": 844
},
{
"epoch": 6.307981220657277,
"grad_norm": 1.1015625,
"learning_rate": 1.8507462686567165e-05,
"loss": 0.125,
"step": 845
},
{
"epoch": 6.3154929577464785,
"grad_norm": 1.1953125,
"learning_rate": 1.8470149253731344e-05,
"loss": 0.1096,
"step": 846
},
{
"epoch": 6.323004694835681,
"grad_norm": 1.125,
"learning_rate": 1.8432835820895523e-05,
"loss": 0.1391,
"step": 847
},
{
"epoch": 6.330516431924883,
"grad_norm": 1.1328125,
"learning_rate": 1.8395522388059702e-05,
"loss": 0.1566,
"step": 848
},
{
"epoch": 6.338028169014084,
"grad_norm": 1.1171875,
"learning_rate": 1.835820895522388e-05,
"loss": 0.0975,
"step": 849
},
{
"epoch": 6.345539906103286,
"grad_norm": 1.09375,
"learning_rate": 1.832089552238806e-05,
"loss": 0.1701,
"step": 850
},
{
"epoch": 6.353051643192488,
"grad_norm": 1.2734375,
"learning_rate": 1.828358208955224e-05,
"loss": 0.0989,
"step": 851
},
{
"epoch": 6.3605633802816905,
"grad_norm": 1.234375,
"learning_rate": 1.824626865671642e-05,
"loss": 0.181,
"step": 852
},
{
"epoch": 6.368075117370892,
"grad_norm": 1.0703125,
"learning_rate": 1.8208955223880598e-05,
"loss": 0.2529,
"step": 853
},
{
"epoch": 6.375586854460094,
"grad_norm": 0.79296875,
"learning_rate": 1.8171641791044777e-05,
"loss": 0.0699,
"step": 854
},
{
"epoch": 6.383098591549296,
"grad_norm": 1.375,
"learning_rate": 1.8134328358208956e-05,
"loss": 0.1345,
"step": 855
},
{
"epoch": 6.390610328638497,
"grad_norm": 1.109375,
"learning_rate": 1.8097014925373135e-05,
"loss": 0.1229,
"step": 856
},
{
"epoch": 6.3981220657277,
"grad_norm": 1.046875,
"learning_rate": 1.8059701492537314e-05,
"loss": 0.0892,
"step": 857
},
{
"epoch": 6.405633802816902,
"grad_norm": 1.203125,
"learning_rate": 1.8022388059701494e-05,
"loss": 0.0911,
"step": 858
},
{
"epoch": 6.413145539906103,
"grad_norm": 1.1484375,
"learning_rate": 1.7985074626865673e-05,
"loss": 0.1399,
"step": 859
},
{
"epoch": 6.420657276995305,
"grad_norm": 1.0859375,
"learning_rate": 1.7947761194029852e-05,
"loss": 0.0993,
"step": 860
},
{
"epoch": 6.428169014084507,
"grad_norm": 1.1484375,
"learning_rate": 1.791044776119403e-05,
"loss": 0.102,
"step": 861
},
{
"epoch": 6.435680751173709,
"grad_norm": 1.0390625,
"learning_rate": 1.787313432835821e-05,
"loss": 0.1405,
"step": 862
},
{
"epoch": 6.443192488262911,
"grad_norm": 1.03125,
"learning_rate": 1.783582089552239e-05,
"loss": 0.0976,
"step": 863
},
{
"epoch": 6.450704225352113,
"grad_norm": 1.078125,
"learning_rate": 1.779850746268657e-05,
"loss": 0.1315,
"step": 864
},
{
"epoch": 6.458215962441314,
"grad_norm": 1.2421875,
"learning_rate": 1.7761194029850748e-05,
"loss": 0.1021,
"step": 865
},
{
"epoch": 6.465727699530516,
"grad_norm": 0.984375,
"learning_rate": 1.7723880597014927e-05,
"loss": 0.0776,
"step": 866
},
{
"epoch": 6.473239436619719,
"grad_norm": 1.0546875,
"learning_rate": 1.7686567164179106e-05,
"loss": 0.0788,
"step": 867
},
{
"epoch": 6.48075117370892,
"grad_norm": 1.046875,
"learning_rate": 1.7649253731343285e-05,
"loss": 0.0883,
"step": 868
},
{
"epoch": 6.488262910798122,
"grad_norm": 1.265625,
"learning_rate": 1.761194029850746e-05,
"loss": 0.1038,
"step": 869
},
{
"epoch": 6.495774647887324,
"grad_norm": 1.234375,
"learning_rate": 1.7574626865671644e-05,
"loss": 0.1022,
"step": 870
},
{
"epoch": 6.5032863849765254,
"grad_norm": 1.109375,
"learning_rate": 1.7537313432835823e-05,
"loss": 0.0873,
"step": 871
},
{
"epoch": 6.510798122065728,
"grad_norm": 0.90234375,
"learning_rate": 1.75e-05,
"loss": 0.1352,
"step": 872
},
{
"epoch": 6.51830985915493,
"grad_norm": 0.98828125,
"learning_rate": 1.746268656716418e-05,
"loss": 0.1704,
"step": 873
},
{
"epoch": 6.525821596244132,
"grad_norm": 1.0625,
"learning_rate": 1.742537313432836e-05,
"loss": 0.0876,
"step": 874
},
{
"epoch": 6.533333333333333,
"grad_norm": 1.265625,
"learning_rate": 1.7388059701492536e-05,
"loss": 0.1051,
"step": 875
},
{
"epoch": 6.540845070422535,
"grad_norm": 1.2109375,
"learning_rate": 1.735074626865672e-05,
"loss": 0.1042,
"step": 876
},
{
"epoch": 6.5483568075117375,
"grad_norm": 1.140625,
"learning_rate": 1.7313432835820898e-05,
"loss": 0.1321,
"step": 877
},
{
"epoch": 6.555868544600939,
"grad_norm": 1.3515625,
"learning_rate": 1.7276119402985073e-05,
"loss": 0.1019,
"step": 878
},
{
"epoch": 6.563380281690141,
"grad_norm": 0.99609375,
"learning_rate": 1.7238805970149256e-05,
"loss": 0.1456,
"step": 879
},
{
"epoch": 6.570892018779343,
"grad_norm": 1.25,
"learning_rate": 1.7201492537313435e-05,
"loss": 0.1061,
"step": 880
},
{
"epoch": 6.578403755868544,
"grad_norm": 1.0546875,
"learning_rate": 1.716417910447761e-05,
"loss": 0.0982,
"step": 881
},
{
"epoch": 6.585915492957747,
"grad_norm": 0.89453125,
"learning_rate": 1.7126865671641793e-05,
"loss": 0.102,
"step": 882
},
{
"epoch": 6.593427230046949,
"grad_norm": 1.1328125,
"learning_rate": 1.708955223880597e-05,
"loss": 0.1385,
"step": 883
},
{
"epoch": 6.60093896713615,
"grad_norm": 0.9921875,
"learning_rate": 1.705223880597015e-05,
"loss": 0.1456,
"step": 884
},
{
"epoch": 6.608450704225352,
"grad_norm": 0.9453125,
"learning_rate": 1.701492537313433e-05,
"loss": 0.0805,
"step": 885
},
{
"epoch": 6.615962441314554,
"grad_norm": 1.5390625,
"learning_rate": 1.6977611940298507e-05,
"loss": 0.1905,
"step": 886
},
{
"epoch": 6.623474178403756,
"grad_norm": 1.1015625,
"learning_rate": 1.6940298507462686e-05,
"loss": 0.0896,
"step": 887
},
{
"epoch": 6.630985915492958,
"grad_norm": 1.1171875,
"learning_rate": 1.690298507462687e-05,
"loss": 0.0715,
"step": 888
},
{
"epoch": 6.63849765258216,
"grad_norm": 1.0703125,
"learning_rate": 1.6865671641791044e-05,
"loss": 0.1723,
"step": 889
},
{
"epoch": 6.646009389671361,
"grad_norm": 1.078125,
"learning_rate": 1.6828358208955223e-05,
"loss": 0.1806,
"step": 890
},
{
"epoch": 6.653521126760563,
"grad_norm": 1.1015625,
"learning_rate": 1.6791044776119406e-05,
"loss": 0.1232,
"step": 891
},
{
"epoch": 6.661032863849766,
"grad_norm": 1.09375,
"learning_rate": 1.675373134328358e-05,
"loss": 0.1032,
"step": 892
},
{
"epoch": 6.668544600938967,
"grad_norm": 0.984375,
"learning_rate": 1.6716417910447764e-05,
"loss": 0.0722,
"step": 893
},
{
"epoch": 6.676056338028169,
"grad_norm": 1.515625,
"learning_rate": 1.667910447761194e-05,
"loss": 0.1131,
"step": 894
},
{
"epoch": 6.683568075117371,
"grad_norm": 1.2421875,
"learning_rate": 1.664179104477612e-05,
"loss": 0.1406,
"step": 895
},
{
"epoch": 6.691079812206572,
"grad_norm": 0.98046875,
"learning_rate": 1.66044776119403e-05,
"loss": 0.1566,
"step": 896
},
{
"epoch": 6.698591549295775,
"grad_norm": 1.171875,
"learning_rate": 1.6567164179104477e-05,
"loss": 0.15,
"step": 897
},
{
"epoch": 6.706103286384977,
"grad_norm": 1.109375,
"learning_rate": 1.6529850746268657e-05,
"loss": 0.129,
"step": 898
},
{
"epoch": 6.713615023474178,
"grad_norm": 0.90625,
"learning_rate": 1.649253731343284e-05,
"loss": 0.0799,
"step": 899
},
{
"epoch": 6.72112676056338,
"grad_norm": 0.953125,
"learning_rate": 1.6455223880597015e-05,
"loss": 0.0734,
"step": 900
},
{
"epoch": 6.728638497652582,
"grad_norm": 1.0625,
"learning_rate": 1.6417910447761194e-05,
"loss": 0.2714,
"step": 901
},
{
"epoch": 6.736150234741784,
"grad_norm": 1.140625,
"learning_rate": 1.6380597014925377e-05,
"loss": 0.1555,
"step": 902
},
{
"epoch": 6.743661971830986,
"grad_norm": 0.98046875,
"learning_rate": 1.6343283582089552e-05,
"loss": 0.0953,
"step": 903
},
{
"epoch": 6.751173708920188,
"grad_norm": 1.140625,
"learning_rate": 1.630597014925373e-05,
"loss": 0.3822,
"step": 904
},
{
"epoch": 6.758685446009389,
"grad_norm": 0.96484375,
"learning_rate": 1.626865671641791e-05,
"loss": 0.0733,
"step": 905
},
{
"epoch": 6.766197183098591,
"grad_norm": 1.0234375,
"learning_rate": 1.623134328358209e-05,
"loss": 0.0707,
"step": 906
},
{
"epoch": 6.773708920187794,
"grad_norm": 1.078125,
"learning_rate": 1.619402985074627e-05,
"loss": 0.1384,
"step": 907
},
{
"epoch": 6.781220657276995,
"grad_norm": 1.2734375,
"learning_rate": 1.6156716417910448e-05,
"loss": 0.1339,
"step": 908
},
{
"epoch": 6.788732394366197,
"grad_norm": 1.46875,
"learning_rate": 1.6119402985074627e-05,
"loss": 0.1535,
"step": 909
},
{
"epoch": 6.796244131455399,
"grad_norm": 1.09375,
"learning_rate": 1.6082089552238806e-05,
"loss": 0.104,
"step": 910
},
{
"epoch": 6.8037558685446005,
"grad_norm": 1.2109375,
"learning_rate": 1.6044776119402986e-05,
"loss": 0.1296,
"step": 911
},
{
"epoch": 6.811267605633803,
"grad_norm": 1.1328125,
"learning_rate": 1.6007462686567165e-05,
"loss": 0.1004,
"step": 912
},
{
"epoch": 6.818779342723005,
"grad_norm": 1.140625,
"learning_rate": 1.5970149253731344e-05,
"loss": 0.0807,
"step": 913
},
{
"epoch": 6.826291079812207,
"grad_norm": 0.8359375,
"learning_rate": 1.5932835820895523e-05,
"loss": 0.0643,
"step": 914
},
{
"epoch": 6.833802816901408,
"grad_norm": 1.1015625,
"learning_rate": 1.5895522388059702e-05,
"loss": 0.0884,
"step": 915
},
{
"epoch": 6.84131455399061,
"grad_norm": 1.0703125,
"learning_rate": 1.585820895522388e-05,
"loss": 0.1034,
"step": 916
},
{
"epoch": 6.848826291079813,
"grad_norm": 1.3046875,
"learning_rate": 1.582089552238806e-05,
"loss": 0.109,
"step": 917
},
{
"epoch": 6.856338028169014,
"grad_norm": 1.2109375,
"learning_rate": 1.578358208955224e-05,
"loss": 0.1407,
"step": 918
},
{
"epoch": 6.863849765258216,
"grad_norm": 1.0546875,
"learning_rate": 1.574626865671642e-05,
"loss": 0.1072,
"step": 919
},
{
"epoch": 6.871361502347418,
"grad_norm": 1.4140625,
"learning_rate": 1.5708955223880598e-05,
"loss": 0.1552,
"step": 920
},
{
"epoch": 6.878873239436619,
"grad_norm": 0.875,
"learning_rate": 1.5671641791044777e-05,
"loss": 0.0638,
"step": 921
},
{
"epoch": 6.886384976525822,
"grad_norm": 1.3828125,
"learning_rate": 1.5634328358208956e-05,
"loss": 0.3367,
"step": 922
},
{
"epoch": 6.893896713615024,
"grad_norm": 1.0078125,
"learning_rate": 1.5597014925373136e-05,
"loss": 0.0858,
"step": 923
},
{
"epoch": 6.901408450704225,
"grad_norm": 1.4375,
"learning_rate": 1.5559701492537315e-05,
"loss": 0.1229,
"step": 924
},
{
"epoch": 6.908920187793427,
"grad_norm": 1.3671875,
"learning_rate": 1.5522388059701494e-05,
"loss": 0.1057,
"step": 925
},
{
"epoch": 6.916431924882629,
"grad_norm": 1.2890625,
"learning_rate": 1.5485074626865673e-05,
"loss": 0.1322,
"step": 926
},
{
"epoch": 6.923943661971831,
"grad_norm": 1.09375,
"learning_rate": 1.5447761194029852e-05,
"loss": 0.0927,
"step": 927
},
{
"epoch": 6.931455399061033,
"grad_norm": 1.0625,
"learning_rate": 1.541044776119403e-05,
"loss": 0.1138,
"step": 928
},
{
"epoch": 6.938967136150235,
"grad_norm": 1.21875,
"learning_rate": 1.537313432835821e-05,
"loss": 0.1005,
"step": 929
},
{
"epoch": 6.946478873239436,
"grad_norm": 1.046875,
"learning_rate": 1.5335820895522386e-05,
"loss": 0.0835,
"step": 930
},
{
"epoch": 6.953990610328638,
"grad_norm": 1.1796875,
"learning_rate": 1.529850746268657e-05,
"loss": 0.1771,
"step": 931
},
{
"epoch": 6.961502347417841,
"grad_norm": 1.109375,
"learning_rate": 1.5261194029850748e-05,
"loss": 0.2269,
"step": 932
},
{
"epoch": 6.969014084507043,
"grad_norm": 1.140625,
"learning_rate": 1.5223880597014925e-05,
"loss": 0.0912,
"step": 933
},
{
"epoch": 6.976525821596244,
"grad_norm": 1.2265625,
"learning_rate": 1.5186567164179105e-05,
"loss": 0.0928,
"step": 934
},
{
"epoch": 6.984037558685446,
"grad_norm": 1.0703125,
"learning_rate": 1.5149253731343285e-05,
"loss": 0.0892,
"step": 935
},
{
"epoch": 6.991549295774648,
"grad_norm": 1.140625,
"learning_rate": 1.5111940298507463e-05,
"loss": 0.1125,
"step": 936
},
{
"epoch": 6.99906103286385,
"grad_norm": 1.0859375,
"learning_rate": 1.5074626865671642e-05,
"loss": 0.1949,
"step": 937
},
{
"epoch": 7.0,
"grad_norm": 4.34375,
"learning_rate": 1.5037313432835823e-05,
"loss": 0.1053,
"step": 938
},
{
"epoch": 7.007511737089202,
"grad_norm": 0.8671875,
"learning_rate": 1.5e-05,
"loss": 0.0748,
"step": 939
},
{
"epoch": 7.015023474178403,
"grad_norm": 0.8515625,
"learning_rate": 1.496268656716418e-05,
"loss": 0.1079,
"step": 940
},
{
"epoch": 7.022535211267606,
"grad_norm": 0.890625,
"learning_rate": 1.4925373134328357e-05,
"loss": 0.1529,
"step": 941
},
{
"epoch": 7.030046948356808,
"grad_norm": 0.86328125,
"learning_rate": 1.4888059701492538e-05,
"loss": 0.0722,
"step": 942
},
{
"epoch": 7.037558685446009,
"grad_norm": 0.9375,
"learning_rate": 1.4850746268656717e-05,
"loss": 0.0882,
"step": 943
},
{
"epoch": 7.045070422535211,
"grad_norm": 0.91015625,
"learning_rate": 1.4813432835820894e-05,
"loss": 0.0768,
"step": 944
},
{
"epoch": 7.052582159624413,
"grad_norm": 0.93359375,
"learning_rate": 1.4776119402985075e-05,
"loss": 0.0893,
"step": 945
},
{
"epoch": 7.060093896713615,
"grad_norm": 0.87109375,
"learning_rate": 1.4738805970149256e-05,
"loss": 0.1348,
"step": 946
},
{
"epoch": 7.067605633802817,
"grad_norm": 1.203125,
"learning_rate": 1.4701492537313432e-05,
"loss": 0.1082,
"step": 947
},
{
"epoch": 7.075117370892019,
"grad_norm": 0.94140625,
"learning_rate": 1.4664179104477613e-05,
"loss": 0.0673,
"step": 948
},
{
"epoch": 7.08262910798122,
"grad_norm": 1.09375,
"learning_rate": 1.4626865671641794e-05,
"loss": 0.0769,
"step": 949
},
{
"epoch": 7.090140845070422,
"grad_norm": 0.99609375,
"learning_rate": 1.458955223880597e-05,
"loss": 0.0804,
"step": 950
},
{
"epoch": 7.097652582159625,
"grad_norm": 1.03125,
"learning_rate": 1.455223880597015e-05,
"loss": 0.0566,
"step": 951
},
{
"epoch": 7.105164319248826,
"grad_norm": 1.0546875,
"learning_rate": 1.4514925373134331e-05,
"loss": 0.0637,
"step": 952
},
{
"epoch": 7.112676056338028,
"grad_norm": 1.1484375,
"learning_rate": 1.4477611940298509e-05,
"loss": 0.1605,
"step": 953
},
{
"epoch": 7.12018779342723,
"grad_norm": 1.046875,
"learning_rate": 1.4440298507462688e-05,
"loss": 0.0685,
"step": 954
},
{
"epoch": 7.127699530516432,
"grad_norm": 1.1171875,
"learning_rate": 1.4402985074626865e-05,
"loss": 0.0671,
"step": 955
},
{
"epoch": 7.135211267605634,
"grad_norm": 1.1484375,
"learning_rate": 1.4365671641791046e-05,
"loss": 0.0758,
"step": 956
},
{
"epoch": 7.142723004694836,
"grad_norm": 1.0234375,
"learning_rate": 1.4328358208955225e-05,
"loss": 0.0638,
"step": 957
},
{
"epoch": 7.150234741784038,
"grad_norm": 0.87109375,
"learning_rate": 1.4291044776119403e-05,
"loss": 0.0945,
"step": 958
},
{
"epoch": 7.157746478873239,
"grad_norm": 1.1171875,
"learning_rate": 1.4253731343283584e-05,
"loss": 0.0805,
"step": 959
},
{
"epoch": 7.165258215962441,
"grad_norm": 0.93359375,
"learning_rate": 1.4216417910447763e-05,
"loss": 0.0854,
"step": 960
},
{
"epoch": 7.1727699530516436,
"grad_norm": 0.796875,
"learning_rate": 1.417910447761194e-05,
"loss": 0.0552,
"step": 961
},
{
"epoch": 7.180281690140845,
"grad_norm": 0.96484375,
"learning_rate": 1.4141791044776121e-05,
"loss": 0.0761,
"step": 962
},
{
"epoch": 7.187793427230047,
"grad_norm": 0.86328125,
"learning_rate": 1.41044776119403e-05,
"loss": 0.0668,
"step": 963
},
{
"epoch": 7.195305164319249,
"grad_norm": 0.87890625,
"learning_rate": 1.4067164179104478e-05,
"loss": 0.1175,
"step": 964
},
{
"epoch": 7.20281690140845,
"grad_norm": 1.0859375,
"learning_rate": 1.4029850746268658e-05,
"loss": 0.0752,
"step": 965
},
{
"epoch": 7.210328638497653,
"grad_norm": 0.79296875,
"learning_rate": 1.3992537313432836e-05,
"loss": 0.0608,
"step": 966
},
{
"epoch": 7.217840375586855,
"grad_norm": 0.8359375,
"learning_rate": 1.3955223880597015e-05,
"loss": 0.0559,
"step": 967
},
{
"epoch": 7.225352112676056,
"grad_norm": 0.68359375,
"learning_rate": 1.3917910447761196e-05,
"loss": 0.0429,
"step": 968
},
{
"epoch": 7.232863849765258,
"grad_norm": 0.9453125,
"learning_rate": 1.3880597014925373e-05,
"loss": 0.0705,
"step": 969
},
{
"epoch": 7.24037558685446,
"grad_norm": 0.99609375,
"learning_rate": 1.3843283582089553e-05,
"loss": 0.0865,
"step": 970
},
{
"epoch": 7.247887323943662,
"grad_norm": 0.79296875,
"learning_rate": 1.3805970149253733e-05,
"loss": 0.058,
"step": 971
},
{
"epoch": 7.255399061032864,
"grad_norm": 0.984375,
"learning_rate": 1.3768656716417911e-05,
"loss": 0.2233,
"step": 972
},
{
"epoch": 7.262910798122066,
"grad_norm": 0.9453125,
"learning_rate": 1.373134328358209e-05,
"loss": 0.1417,
"step": 973
},
{
"epoch": 7.270422535211267,
"grad_norm": 0.86328125,
"learning_rate": 1.3694029850746271e-05,
"loss": 0.0668,
"step": 974
},
{
"epoch": 7.277934272300469,
"grad_norm": 0.953125,
"learning_rate": 1.3656716417910448e-05,
"loss": 0.0577,
"step": 975
},
{
"epoch": 7.285446009389672,
"grad_norm": 0.95703125,
"learning_rate": 1.3619402985074628e-05,
"loss": 0.0804,
"step": 976
},
{
"epoch": 7.292957746478873,
"grad_norm": 1.0,
"learning_rate": 1.3582089552238805e-05,
"loss": 0.0654,
"step": 977
},
{
"epoch": 7.300469483568075,
"grad_norm": 1.0546875,
"learning_rate": 1.3544776119402986e-05,
"loss": 0.1187,
"step": 978
},
{
"epoch": 7.307981220657277,
"grad_norm": 1.1015625,
"learning_rate": 1.3507462686567165e-05,
"loss": 0.0901,
"step": 979
},
{
"epoch": 7.3154929577464785,
"grad_norm": 1.140625,
"learning_rate": 1.3470149253731342e-05,
"loss": 0.1741,
"step": 980
},
{
"epoch": 7.323004694835681,
"grad_norm": 0.88671875,
"learning_rate": 1.3432835820895523e-05,
"loss": 0.1421,
"step": 981
},
{
"epoch": 7.330516431924883,
"grad_norm": 1.0703125,
"learning_rate": 1.3395522388059702e-05,
"loss": 0.4088,
"step": 982
},
{
"epoch": 7.338028169014084,
"grad_norm": 0.90234375,
"learning_rate": 1.335820895522388e-05,
"loss": 0.0642,
"step": 983
},
{
"epoch": 7.345539906103286,
"grad_norm": 0.984375,
"learning_rate": 1.332089552238806e-05,
"loss": 0.1351,
"step": 984
},
{
"epoch": 7.353051643192488,
"grad_norm": 0.80859375,
"learning_rate": 1.328358208955224e-05,
"loss": 0.0533,
"step": 985
},
{
"epoch": 7.3605633802816905,
"grad_norm": 0.87890625,
"learning_rate": 1.3246268656716417e-05,
"loss": 0.0787,
"step": 986
},
{
"epoch": 7.368075117370892,
"grad_norm": 1.0390625,
"learning_rate": 1.3208955223880598e-05,
"loss": 0.1437,
"step": 987
},
{
"epoch": 7.375586854460094,
"grad_norm": 0.93359375,
"learning_rate": 1.3171641791044777e-05,
"loss": 0.0807,
"step": 988
},
{
"epoch": 7.383098591549296,
"grad_norm": 0.98046875,
"learning_rate": 1.3134328358208955e-05,
"loss": 0.0661,
"step": 989
},
{
"epoch": 7.390610328638497,
"grad_norm": 1.21875,
"learning_rate": 1.3097014925373136e-05,
"loss": 0.1727,
"step": 990
},
{
"epoch": 7.3981220657277,
"grad_norm": 0.84765625,
"learning_rate": 1.3059701492537313e-05,
"loss": 0.0578,
"step": 991
},
{
"epoch": 7.405633802816902,
"grad_norm": 0.84375,
"learning_rate": 1.3022388059701492e-05,
"loss": 0.0626,
"step": 992
},
{
"epoch": 7.413145539906103,
"grad_norm": 0.67578125,
"learning_rate": 1.2985074626865673e-05,
"loss": 0.0612,
"step": 993
},
{
"epoch": 7.420657276995305,
"grad_norm": 0.9921875,
"learning_rate": 1.294776119402985e-05,
"loss": 0.0803,
"step": 994
},
{
"epoch": 7.428169014084507,
"grad_norm": 0.91796875,
"learning_rate": 1.291044776119403e-05,
"loss": 0.07,
"step": 995
},
{
"epoch": 7.435680751173709,
"grad_norm": 1.203125,
"learning_rate": 1.287313432835821e-05,
"loss": 0.1505,
"step": 996
},
{
"epoch": 7.443192488262911,
"grad_norm": 0.97265625,
"learning_rate": 1.2835820895522388e-05,
"loss": 0.0874,
"step": 997
},
{
"epoch": 7.450704225352113,
"grad_norm": 1.0078125,
"learning_rate": 1.2798507462686567e-05,
"loss": 0.0789,
"step": 998
},
{
"epoch": 7.458215962441314,
"grad_norm": 0.984375,
"learning_rate": 1.2761194029850748e-05,
"loss": 0.0566,
"step": 999
},
{
"epoch": 7.465727699530516,
"grad_norm": 1.109375,
"learning_rate": 1.2723880597014926e-05,
"loss": 0.0765,
"step": 1000
},
{
"epoch": 7.473239436619719,
"grad_norm": 0.875,
"learning_rate": 1.2686567164179105e-05,
"loss": 0.0576,
"step": 1001
},
{
"epoch": 7.48075117370892,
"grad_norm": 0.91015625,
"learning_rate": 1.2649253731343282e-05,
"loss": 0.1435,
"step": 1002
},
{
"epoch": 7.488262910798122,
"grad_norm": 0.88671875,
"learning_rate": 1.2611940298507463e-05,
"loss": 0.0823,
"step": 1003
},
{
"epoch": 7.495774647887324,
"grad_norm": 0.8984375,
"learning_rate": 1.2574626865671644e-05,
"loss": 0.0556,
"step": 1004
},
{
"epoch": 7.5032863849765254,
"grad_norm": 0.77734375,
"learning_rate": 1.253731343283582e-05,
"loss": 0.0613,
"step": 1005
},
{
"epoch": 7.510798122065728,
"grad_norm": 0.84375,
"learning_rate": 1.25e-05,
"loss": 0.0621,
"step": 1006
},
{
"epoch": 7.51830985915493,
"grad_norm": 0.80859375,
"learning_rate": 1.246268656716418e-05,
"loss": 0.102,
"step": 1007
},
{
"epoch": 7.525821596244132,
"grad_norm": 0.953125,
"learning_rate": 1.2425373134328359e-05,
"loss": 0.0977,
"step": 1008
},
{
"epoch": 7.533333333333333,
"grad_norm": 1.421875,
"learning_rate": 1.2388059701492538e-05,
"loss": 0.1226,
"step": 1009
},
{
"epoch": 7.540845070422535,
"grad_norm": 1.109375,
"learning_rate": 1.2350746268656717e-05,
"loss": 0.0997,
"step": 1010
},
{
"epoch": 7.5483568075117375,
"grad_norm": 0.95703125,
"learning_rate": 1.2313432835820896e-05,
"loss": 0.0797,
"step": 1011
},
{
"epoch": 7.555868544600939,
"grad_norm": 1.0390625,
"learning_rate": 1.2276119402985076e-05,
"loss": 0.0802,
"step": 1012
},
{
"epoch": 7.563380281690141,
"grad_norm": 0.90234375,
"learning_rate": 1.2238805970149255e-05,
"loss": 0.0623,
"step": 1013
},
{
"epoch": 7.570892018779343,
"grad_norm": 0.9609375,
"learning_rate": 1.2201492537313434e-05,
"loss": 0.2565,
"step": 1014
},
{
"epoch": 7.578403755868544,
"grad_norm": 0.921875,
"learning_rate": 1.2164179104477611e-05,
"loss": 0.1013,
"step": 1015
},
{
"epoch": 7.585915492957747,
"grad_norm": 1.3203125,
"learning_rate": 1.2126865671641792e-05,
"loss": 0.0742,
"step": 1016
},
{
"epoch": 7.593427230046949,
"grad_norm": 0.98046875,
"learning_rate": 1.2089552238805971e-05,
"loss": 0.0605,
"step": 1017
},
{
"epoch": 7.60093896713615,
"grad_norm": 1.0625,
"learning_rate": 1.2052238805970149e-05,
"loss": 0.0787,
"step": 1018
},
{
"epoch": 7.608450704225352,
"grad_norm": 0.86328125,
"learning_rate": 1.201492537313433e-05,
"loss": 0.0869,
"step": 1019
},
{
"epoch": 7.615962441314554,
"grad_norm": 1.015625,
"learning_rate": 1.1977611940298509e-05,
"loss": 0.1106,
"step": 1020
},
{
"epoch": 7.623474178403756,
"grad_norm": 1.0859375,
"learning_rate": 1.1940298507462686e-05,
"loss": 0.0982,
"step": 1021
},
{
"epoch": 7.630985915492958,
"grad_norm": 1.3671875,
"learning_rate": 1.1902985074626865e-05,
"loss": 0.0962,
"step": 1022
},
{
"epoch": 7.63849765258216,
"grad_norm": 1.015625,
"learning_rate": 1.1865671641791046e-05,
"loss": 0.0855,
"step": 1023
},
{
"epoch": 7.646009389671361,
"grad_norm": 1.21875,
"learning_rate": 1.1828358208955224e-05,
"loss": 0.0704,
"step": 1024
},
{
"epoch": 7.653521126760563,
"grad_norm": 0.81640625,
"learning_rate": 1.1791044776119403e-05,
"loss": 0.0643,
"step": 1025
},
{
"epoch": 7.661032863849766,
"grad_norm": 1.015625,
"learning_rate": 1.1753731343283584e-05,
"loss": 0.1014,
"step": 1026
},
{
"epoch": 7.668544600938967,
"grad_norm": 1.0078125,
"learning_rate": 1.1716417910447761e-05,
"loss": 0.0815,
"step": 1027
},
{
"epoch": 7.676056338028169,
"grad_norm": 0.91796875,
"learning_rate": 1.167910447761194e-05,
"loss": 0.0736,
"step": 1028
},
{
"epoch": 7.683568075117371,
"grad_norm": 0.86328125,
"learning_rate": 1.164179104477612e-05,
"loss": 0.0611,
"step": 1029
},
{
"epoch": 7.691079812206572,
"grad_norm": 1.015625,
"learning_rate": 1.1604477611940299e-05,
"loss": 0.0968,
"step": 1030
},
{
"epoch": 7.698591549295775,
"grad_norm": 0.9765625,
"learning_rate": 1.1567164179104478e-05,
"loss": 0.0842,
"step": 1031
},
{
"epoch": 7.706103286384977,
"grad_norm": 0.9140625,
"learning_rate": 1.1529850746268657e-05,
"loss": 0.2258,
"step": 1032
},
{
"epoch": 7.713615023474178,
"grad_norm": 1.078125,
"learning_rate": 1.1492537313432836e-05,
"loss": 0.0836,
"step": 1033
},
{
"epoch": 7.72112676056338,
"grad_norm": 1.125,
"learning_rate": 1.1455223880597015e-05,
"loss": 0.1969,
"step": 1034
},
{
"epoch": 7.728638497652582,
"grad_norm": 0.8984375,
"learning_rate": 1.1417910447761194e-05,
"loss": 0.1295,
"step": 1035
},
{
"epoch": 7.736150234741784,
"grad_norm": 1.0234375,
"learning_rate": 1.1380597014925374e-05,
"loss": 0.0627,
"step": 1036
},
{
"epoch": 7.743661971830986,
"grad_norm": 0.88671875,
"learning_rate": 1.1343283582089553e-05,
"loss": 0.0576,
"step": 1037
},
{
"epoch": 7.751173708920188,
"grad_norm": 1.1328125,
"learning_rate": 1.1305970149253732e-05,
"loss": 0.051,
"step": 1038
},
{
"epoch": 7.758685446009389,
"grad_norm": 1.1484375,
"learning_rate": 1.1268656716417911e-05,
"loss": 0.0813,
"step": 1039
},
{
"epoch": 7.766197183098591,
"grad_norm": 0.921875,
"learning_rate": 1.123134328358209e-05,
"loss": 0.0688,
"step": 1040
},
{
"epoch": 7.773708920187794,
"grad_norm": 0.78515625,
"learning_rate": 1.119402985074627e-05,
"loss": 0.0581,
"step": 1041
},
{
"epoch": 7.781220657276995,
"grad_norm": 0.98046875,
"learning_rate": 1.1156716417910449e-05,
"loss": 0.0747,
"step": 1042
},
{
"epoch": 7.788732394366197,
"grad_norm": 0.796875,
"learning_rate": 1.1119402985074628e-05,
"loss": 0.0874,
"step": 1043
},
{
"epoch": 7.796244131455399,
"grad_norm": 0.96875,
"learning_rate": 1.1082089552238807e-05,
"loss": 0.145,
"step": 1044
},
{
"epoch": 7.8037558685446005,
"grad_norm": 0.89453125,
"learning_rate": 1.1044776119402986e-05,
"loss": 0.0587,
"step": 1045
},
{
"epoch": 7.811267605633803,
"grad_norm": 1.3203125,
"learning_rate": 1.1007462686567165e-05,
"loss": 0.0909,
"step": 1046
},
{
"epoch": 7.818779342723005,
"grad_norm": 1.25,
"learning_rate": 1.0970149253731343e-05,
"loss": 0.3541,
"step": 1047
},
{
"epoch": 7.826291079812207,
"grad_norm": 1.1484375,
"learning_rate": 1.0932835820895524e-05,
"loss": 0.2692,
"step": 1048
},
{
"epoch": 7.833802816901408,
"grad_norm": 0.94921875,
"learning_rate": 1.0895522388059703e-05,
"loss": 0.0783,
"step": 1049
},
{
"epoch": 7.84131455399061,
"grad_norm": 0.9453125,
"learning_rate": 1.085820895522388e-05,
"loss": 0.0664,
"step": 1050
},
{
"epoch": 7.848826291079813,
"grad_norm": 0.890625,
"learning_rate": 1.082089552238806e-05,
"loss": 0.0535,
"step": 1051
},
{
"epoch": 7.856338028169014,
"grad_norm": 0.984375,
"learning_rate": 1.078358208955224e-05,
"loss": 0.066,
"step": 1052
},
{
"epoch": 7.863849765258216,
"grad_norm": 1.0234375,
"learning_rate": 1.0746268656716418e-05,
"loss": 0.0756,
"step": 1053
},
{
"epoch": 7.871361502347418,
"grad_norm": 0.953125,
"learning_rate": 1.0708955223880597e-05,
"loss": 0.0674,
"step": 1054
},
{
"epoch": 7.878873239436619,
"grad_norm": 0.93359375,
"learning_rate": 1.0671641791044778e-05,
"loss": 0.0733,
"step": 1055
},
{
"epoch": 7.886384976525822,
"grad_norm": 1.0546875,
"learning_rate": 1.0634328358208955e-05,
"loss": 0.0814,
"step": 1056
},
{
"epoch": 7.893896713615024,
"grad_norm": 0.9140625,
"learning_rate": 1.0597014925373134e-05,
"loss": 0.0812,
"step": 1057
},
{
"epoch": 7.901408450704225,
"grad_norm": 1.03125,
"learning_rate": 1.0559701492537313e-05,
"loss": 0.0647,
"step": 1058
},
{
"epoch": 7.908920187793427,
"grad_norm": 1.0703125,
"learning_rate": 1.0522388059701493e-05,
"loss": 0.0693,
"step": 1059
},
{
"epoch": 7.916431924882629,
"grad_norm": 0.92578125,
"learning_rate": 1.0485074626865672e-05,
"loss": 0.0854,
"step": 1060
},
{
"epoch": 7.923943661971831,
"grad_norm": 1.046875,
"learning_rate": 1.0447761194029851e-05,
"loss": 0.0713,
"step": 1061
},
{
"epoch": 7.931455399061033,
"grad_norm": 1.0078125,
"learning_rate": 1.0410447761194032e-05,
"loss": 0.0831,
"step": 1062
},
{
"epoch": 7.938967136150235,
"grad_norm": 0.78515625,
"learning_rate": 1.037313432835821e-05,
"loss": 0.0989,
"step": 1063
},
{
"epoch": 7.946478873239436,
"grad_norm": 1.125,
"learning_rate": 1.0335820895522388e-05,
"loss": 0.0841,
"step": 1064
},
{
"epoch": 7.953990610328638,
"grad_norm": 0.8828125,
"learning_rate": 1.0298507462686568e-05,
"loss": 0.0708,
"step": 1065
},
{
"epoch": 7.961502347417841,
"grad_norm": 0.875,
"learning_rate": 1.0261194029850747e-05,
"loss": 0.0678,
"step": 1066
},
{
"epoch": 7.969014084507043,
"grad_norm": 0.87890625,
"learning_rate": 1.0223880597014926e-05,
"loss": 0.1114,
"step": 1067
},
{
"epoch": 7.976525821596244,
"grad_norm": 1.0625,
"learning_rate": 1.0186567164179105e-05,
"loss": 0.1616,
"step": 1068
},
{
"epoch": 7.984037558685446,
"grad_norm": 1.515625,
"learning_rate": 1.0149253731343284e-05,
"loss": 0.1148,
"step": 1069
},
{
"epoch": 7.991549295774648,
"grad_norm": 0.9375,
"learning_rate": 1.0111940298507463e-05,
"loss": 0.1345,
"step": 1070
},
{
"epoch": 7.99906103286385,
"grad_norm": 0.828125,
"learning_rate": 1.0074626865671643e-05,
"loss": 0.0762,
"step": 1071
},
{
"epoch": 8.0,
"grad_norm": 4.875,
"learning_rate": 1.0037313432835822e-05,
"loss": 0.096,
"step": 1072
},
{
"epoch": 8.007511737089201,
"grad_norm": 0.76171875,
"learning_rate": 1e-05,
"loss": 0.065,
"step": 1073
},
{
"epoch": 8.015023474178404,
"grad_norm": 0.9765625,
"learning_rate": 9.96268656716418e-06,
"loss": 0.0765,
"step": 1074
},
{
"epoch": 8.022535211267606,
"grad_norm": 0.765625,
"learning_rate": 9.925373134328359e-06,
"loss": 0.0771,
"step": 1075
},
{
"epoch": 8.030046948356807,
"grad_norm": 0.84375,
"learning_rate": 9.888059701492537e-06,
"loss": 0.0781,
"step": 1076
},
{
"epoch": 8.03755868544601,
"grad_norm": 0.76171875,
"learning_rate": 9.850746268656717e-06,
"loss": 0.1106,
"step": 1077
},
{
"epoch": 8.045070422535211,
"grad_norm": 0.73828125,
"learning_rate": 9.813432835820897e-06,
"loss": 0.0486,
"step": 1078
},
{
"epoch": 8.052582159624412,
"grad_norm": 0.86328125,
"learning_rate": 9.776119402985074e-06,
"loss": 0.0738,
"step": 1079
},
{
"epoch": 8.060093896713616,
"grad_norm": 0.68359375,
"learning_rate": 9.738805970149255e-06,
"loss": 0.1404,
"step": 1080
},
{
"epoch": 8.067605633802817,
"grad_norm": 0.859375,
"learning_rate": 9.701492537313434e-06,
"loss": 0.0582,
"step": 1081
},
{
"epoch": 8.075117370892018,
"grad_norm": 0.7109375,
"learning_rate": 9.664179104477612e-06,
"loss": 0.0573,
"step": 1082
},
{
"epoch": 8.082629107981221,
"grad_norm": 0.7578125,
"learning_rate": 9.62686567164179e-06,
"loss": 0.059,
"step": 1083
},
{
"epoch": 8.090140845070422,
"grad_norm": 0.6953125,
"learning_rate": 9.589552238805972e-06,
"loss": 0.0718,
"step": 1084
},
{
"epoch": 8.097652582159624,
"grad_norm": 0.74609375,
"learning_rate": 9.552238805970149e-06,
"loss": 0.061,
"step": 1085
},
{
"epoch": 8.105164319248827,
"grad_norm": 1.015625,
"learning_rate": 9.514925373134328e-06,
"loss": 0.0836,
"step": 1086
},
{
"epoch": 8.112676056338028,
"grad_norm": 0.6953125,
"learning_rate": 9.477611940298507e-06,
"loss": 0.1013,
"step": 1087
},
{
"epoch": 8.12018779342723,
"grad_norm": 0.8671875,
"learning_rate": 9.440298507462688e-06,
"loss": 0.0704,
"step": 1088
},
{
"epoch": 8.127699530516432,
"grad_norm": 0.98828125,
"learning_rate": 9.402985074626866e-06,
"loss": 0.105,
"step": 1089
},
{
"epoch": 8.135211267605634,
"grad_norm": 0.84765625,
"learning_rate": 9.365671641791045e-06,
"loss": 0.0978,
"step": 1090
},
{
"epoch": 8.142723004694835,
"grad_norm": 0.85546875,
"learning_rate": 9.328358208955226e-06,
"loss": 0.0566,
"step": 1091
},
{
"epoch": 8.150234741784038,
"grad_norm": 0.76171875,
"learning_rate": 9.291044776119403e-06,
"loss": 0.0561,
"step": 1092
},
{
"epoch": 8.15774647887324,
"grad_norm": 0.8203125,
"learning_rate": 9.253731343283582e-06,
"loss": 0.0724,
"step": 1093
},
{
"epoch": 8.16525821596244,
"grad_norm": 0.8515625,
"learning_rate": 9.216417910447761e-06,
"loss": 0.1062,
"step": 1094
},
{
"epoch": 8.172769953051644,
"grad_norm": 0.80078125,
"learning_rate": 9.17910447761194e-06,
"loss": 0.0567,
"step": 1095
},
{
"epoch": 8.180281690140845,
"grad_norm": 0.6796875,
"learning_rate": 9.14179104477612e-06,
"loss": 0.0381,
"step": 1096
},
{
"epoch": 8.187793427230046,
"grad_norm": 0.78125,
"learning_rate": 9.104477611940299e-06,
"loss": 0.0573,
"step": 1097
},
{
"epoch": 8.19530516431925,
"grad_norm": 1.015625,
"learning_rate": 9.067164179104478e-06,
"loss": 0.0583,
"step": 1098
},
{
"epoch": 8.20281690140845,
"grad_norm": 0.77734375,
"learning_rate": 9.029850746268657e-06,
"loss": 0.285,
"step": 1099
},
{
"epoch": 8.210328638497652,
"grad_norm": 0.8515625,
"learning_rate": 8.992537313432836e-06,
"loss": 0.0665,
"step": 1100
},
{
"epoch": 8.217840375586855,
"grad_norm": 0.8671875,
"learning_rate": 8.955223880597016e-06,
"loss": 0.0757,
"step": 1101
},
{
"epoch": 8.225352112676056,
"grad_norm": 0.83203125,
"learning_rate": 8.917910447761195e-06,
"loss": 0.1241,
"step": 1102
},
{
"epoch": 8.232863849765259,
"grad_norm": 0.8359375,
"learning_rate": 8.880597014925374e-06,
"loss": 0.0499,
"step": 1103
},
{
"epoch": 8.24037558685446,
"grad_norm": 0.81640625,
"learning_rate": 8.843283582089553e-06,
"loss": 0.0598,
"step": 1104
},
{
"epoch": 8.247887323943662,
"grad_norm": 0.99609375,
"learning_rate": 8.80597014925373e-06,
"loss": 0.1412,
"step": 1105
},
{
"epoch": 8.255399061032865,
"grad_norm": 0.87890625,
"learning_rate": 8.768656716417911e-06,
"loss": 0.0834,
"step": 1106
},
{
"epoch": 8.262910798122066,
"grad_norm": 0.7734375,
"learning_rate": 8.73134328358209e-06,
"loss": 0.0492,
"step": 1107
},
{
"epoch": 8.270422535211267,
"grad_norm": 0.80859375,
"learning_rate": 8.694029850746268e-06,
"loss": 0.056,
"step": 1108
},
{
"epoch": 8.27793427230047,
"grad_norm": 1.0078125,
"learning_rate": 8.656716417910449e-06,
"loss": 0.0581,
"step": 1109
},
{
"epoch": 8.285446009389672,
"grad_norm": 0.8671875,
"learning_rate": 8.619402985074628e-06,
"loss": 0.1181,
"step": 1110
},
{
"epoch": 8.292957746478873,
"grad_norm": 0.8125,
"learning_rate": 8.582089552238805e-06,
"loss": 0.0851,
"step": 1111
},
{
"epoch": 8.300469483568076,
"grad_norm": 0.76171875,
"learning_rate": 8.544776119402985e-06,
"loss": 0.0675,
"step": 1112
},
{
"epoch": 8.307981220657277,
"grad_norm": 0.66796875,
"learning_rate": 8.507462686567165e-06,
"loss": 0.0617,
"step": 1113
},
{
"epoch": 8.315492957746478,
"grad_norm": 0.9453125,
"learning_rate": 8.470149253731343e-06,
"loss": 0.0609,
"step": 1114
},
{
"epoch": 8.323004694835682,
"grad_norm": 1.0,
"learning_rate": 8.432835820895522e-06,
"loss": 0.076,
"step": 1115
},
{
"epoch": 8.330516431924883,
"grad_norm": 0.8125,
"learning_rate": 8.395522388059703e-06,
"loss": 0.0518,
"step": 1116
},
{
"epoch": 8.338028169014084,
"grad_norm": 0.85546875,
"learning_rate": 8.358208955223882e-06,
"loss": 0.0686,
"step": 1117
},
{
"epoch": 8.345539906103287,
"grad_norm": 0.734375,
"learning_rate": 8.32089552238806e-06,
"loss": 0.0692,
"step": 1118
},
{
"epoch": 8.353051643192488,
"grad_norm": 0.6796875,
"learning_rate": 8.283582089552239e-06,
"loss": 0.1845,
"step": 1119
},
{
"epoch": 8.36056338028169,
"grad_norm": 0.69921875,
"learning_rate": 8.24626865671642e-06,
"loss": 0.0576,
"step": 1120
},
{
"epoch": 8.368075117370893,
"grad_norm": 0.69921875,
"learning_rate": 8.208955223880597e-06,
"loss": 0.066,
"step": 1121
},
{
"epoch": 8.375586854460094,
"grad_norm": 0.7734375,
"learning_rate": 8.171641791044776e-06,
"loss": 0.0591,
"step": 1122
},
{
"epoch": 8.383098591549295,
"grad_norm": 0.92578125,
"learning_rate": 8.134328358208955e-06,
"loss": 0.0721,
"step": 1123
},
{
"epoch": 8.390610328638498,
"grad_norm": 0.7421875,
"learning_rate": 8.097014925373135e-06,
"loss": 0.0516,
"step": 1124
},
{
"epoch": 8.3981220657277,
"grad_norm": 0.84765625,
"learning_rate": 8.059701492537314e-06,
"loss": 0.2,
"step": 1125
},
{
"epoch": 8.4056338028169,
"grad_norm": 0.74609375,
"learning_rate": 8.022388059701493e-06,
"loss": 0.0527,
"step": 1126
},
{
"epoch": 8.413145539906104,
"grad_norm": 0.7890625,
"learning_rate": 7.985074626865672e-06,
"loss": 0.0615,
"step": 1127
},
{
"epoch": 8.420657276995305,
"grad_norm": 0.78125,
"learning_rate": 7.947761194029851e-06,
"loss": 0.0638,
"step": 1128
},
{
"epoch": 8.428169014084506,
"grad_norm": 0.7421875,
"learning_rate": 7.91044776119403e-06,
"loss": 0.0674,
"step": 1129
},
{
"epoch": 8.43568075117371,
"grad_norm": 0.765625,
"learning_rate": 7.87313432835821e-06,
"loss": 0.0734,
"step": 1130
},
{
"epoch": 8.44319248826291,
"grad_norm": 0.79296875,
"learning_rate": 7.835820895522389e-06,
"loss": 0.0555,
"step": 1131
},
{
"epoch": 8.450704225352112,
"grad_norm": 0.765625,
"learning_rate": 7.798507462686568e-06,
"loss": 0.0447,
"step": 1132
},
{
"epoch": 8.458215962441315,
"grad_norm": 0.67578125,
"learning_rate": 7.761194029850747e-06,
"loss": 0.0473,
"step": 1133
},
{
"epoch": 8.465727699530516,
"grad_norm": 0.75,
"learning_rate": 7.723880597014926e-06,
"loss": 0.0518,
"step": 1134
},
{
"epoch": 8.473239436619718,
"grad_norm": 0.73046875,
"learning_rate": 7.686567164179105e-06,
"loss": 0.116,
"step": 1135
},
{
"epoch": 8.48075117370892,
"grad_norm": 0.6875,
"learning_rate": 7.649253731343284e-06,
"loss": 0.0429,
"step": 1136
},
{
"epoch": 8.488262910798122,
"grad_norm": 0.76171875,
"learning_rate": 7.611940298507463e-06,
"loss": 0.142,
"step": 1137
},
{
"epoch": 8.495774647887323,
"grad_norm": 0.8515625,
"learning_rate": 7.574626865671643e-06,
"loss": 0.1261,
"step": 1138
},
{
"epoch": 8.503286384976526,
"grad_norm": 0.81640625,
"learning_rate": 7.537313432835821e-06,
"loss": 0.0771,
"step": 1139
},
{
"epoch": 8.510798122065728,
"grad_norm": 0.7578125,
"learning_rate": 7.5e-06,
"loss": 0.0456,
"step": 1140
},
{
"epoch": 8.518309859154929,
"grad_norm": 0.8515625,
"learning_rate": 7.4626865671641785e-06,
"loss": 0.0576,
"step": 1141
},
{
"epoch": 8.525821596244132,
"grad_norm": 0.94140625,
"learning_rate": 7.4253731343283585e-06,
"loss": 0.1538,
"step": 1142
},
{
"epoch": 8.533333333333333,
"grad_norm": 1.03125,
"learning_rate": 7.388059701492538e-06,
"loss": 0.1073,
"step": 1143
},
{
"epoch": 8.540845070422534,
"grad_norm": 0.84765625,
"learning_rate": 7.350746268656716e-06,
"loss": 0.0872,
"step": 1144
},
{
"epoch": 8.548356807511738,
"grad_norm": 0.71484375,
"learning_rate": 7.313432835820897e-06,
"loss": 0.1269,
"step": 1145
},
{
"epoch": 8.555868544600939,
"grad_norm": 0.703125,
"learning_rate": 7.276119402985075e-06,
"loss": 0.1001,
"step": 1146
},
{
"epoch": 8.56338028169014,
"grad_norm": 0.70703125,
"learning_rate": 7.238805970149254e-06,
"loss": 0.0347,
"step": 1147
},
{
"epoch": 8.570892018779343,
"grad_norm": 0.95703125,
"learning_rate": 7.201492537313433e-06,
"loss": 0.0626,
"step": 1148
},
{
"epoch": 8.578403755868544,
"grad_norm": 0.828125,
"learning_rate": 7.164179104477613e-06,
"loss": 0.1187,
"step": 1149
},
{
"epoch": 8.585915492957746,
"grad_norm": 0.78515625,
"learning_rate": 7.126865671641792e-06,
"loss": 0.0416,
"step": 1150
},
{
"epoch": 8.593427230046949,
"grad_norm": 0.72265625,
"learning_rate": 7.08955223880597e-06,
"loss": 0.434,
"step": 1151
},
{
"epoch": 8.60093896713615,
"grad_norm": 0.92578125,
"learning_rate": 7.05223880597015e-06,
"loss": 0.062,
"step": 1152
},
{
"epoch": 8.608450704225351,
"grad_norm": 0.859375,
"learning_rate": 7.014925373134329e-06,
"loss": 0.0502,
"step": 1153
},
{
"epoch": 8.615962441314554,
"grad_norm": 0.78125,
"learning_rate": 6.9776119402985076e-06,
"loss": 0.0479,
"step": 1154
},
{
"epoch": 8.623474178403756,
"grad_norm": 0.7734375,
"learning_rate": 6.940298507462687e-06,
"loss": 0.0694,
"step": 1155
},
{
"epoch": 8.630985915492957,
"grad_norm": 0.859375,
"learning_rate": 6.902985074626867e-06,
"loss": 0.2435,
"step": 1156
},
{
"epoch": 8.63849765258216,
"grad_norm": 0.7421875,
"learning_rate": 6.865671641791045e-06,
"loss": 0.0441,
"step": 1157
},
{
"epoch": 8.646009389671361,
"grad_norm": 0.6640625,
"learning_rate": 6.828358208955224e-06,
"loss": 0.034,
"step": 1158
},
{
"epoch": 8.653521126760563,
"grad_norm": 0.8828125,
"learning_rate": 6.7910447761194025e-06,
"loss": 0.1374,
"step": 1159
},
{
"epoch": 8.661032863849766,
"grad_norm": 0.7578125,
"learning_rate": 6.7537313432835825e-06,
"loss": 0.1291,
"step": 1160
},
{
"epoch": 8.668544600938967,
"grad_norm": 0.921875,
"learning_rate": 6.716417910447762e-06,
"loss": 0.0784,
"step": 1161
},
{
"epoch": 8.676056338028168,
"grad_norm": 0.7265625,
"learning_rate": 6.67910447761194e-06,
"loss": 0.0514,
"step": 1162
},
{
"epoch": 8.683568075117371,
"grad_norm": 0.8203125,
"learning_rate": 6.64179104477612e-06,
"loss": 0.1404,
"step": 1163
},
{
"epoch": 8.691079812206572,
"grad_norm": 0.73828125,
"learning_rate": 6.604477611940299e-06,
"loss": 0.0629,
"step": 1164
},
{
"epoch": 8.698591549295774,
"grad_norm": 0.859375,
"learning_rate": 6.5671641791044775e-06,
"loss": 0.1048,
"step": 1165
},
{
"epoch": 8.706103286384977,
"grad_norm": 0.79296875,
"learning_rate": 6.529850746268657e-06,
"loss": 0.0687,
"step": 1166
},
{
"epoch": 8.713615023474178,
"grad_norm": 0.78515625,
"learning_rate": 6.492537313432837e-06,
"loss": 0.0383,
"step": 1167
},
{
"epoch": 8.721126760563381,
"grad_norm": 0.84765625,
"learning_rate": 6.455223880597015e-06,
"loss": 0.0602,
"step": 1168
},
{
"epoch": 8.728638497652582,
"grad_norm": 0.828125,
"learning_rate": 6.417910447761194e-06,
"loss": 0.1421,
"step": 1169
},
{
"epoch": 8.736150234741784,
"grad_norm": 1.0078125,
"learning_rate": 6.380597014925374e-06,
"loss": 0.0555,
"step": 1170
},
{
"epoch": 8.743661971830987,
"grad_norm": 0.71484375,
"learning_rate": 6.343283582089552e-06,
"loss": 0.0483,
"step": 1171
},
{
"epoch": 8.751173708920188,
"grad_norm": 0.80859375,
"learning_rate": 6.3059701492537316e-06,
"loss": 0.0666,
"step": 1172
},
{
"epoch": 8.75868544600939,
"grad_norm": 0.77734375,
"learning_rate": 6.26865671641791e-06,
"loss": 0.0635,
"step": 1173
},
{
"epoch": 8.766197183098592,
"grad_norm": 0.87109375,
"learning_rate": 6.23134328358209e-06,
"loss": 0.0584,
"step": 1174
},
{
"epoch": 8.773708920187794,
"grad_norm": 0.890625,
"learning_rate": 6.194029850746269e-06,
"loss": 0.0926,
"step": 1175
},
{
"epoch": 8.781220657276995,
"grad_norm": 0.84765625,
"learning_rate": 6.156716417910448e-06,
"loss": 0.0707,
"step": 1176
},
{
"epoch": 8.788732394366198,
"grad_norm": 0.953125,
"learning_rate": 6.119402985074627e-06,
"loss": 0.0703,
"step": 1177
},
{
"epoch": 8.7962441314554,
"grad_norm": 0.84375,
"learning_rate": 6.082089552238806e-06,
"loss": 0.0757,
"step": 1178
},
{
"epoch": 8.8037558685446,
"grad_norm": 0.8046875,
"learning_rate": 6.044776119402986e-06,
"loss": 0.1032,
"step": 1179
},
{
"epoch": 8.811267605633804,
"grad_norm": 0.828125,
"learning_rate": 6.007462686567165e-06,
"loss": 0.0616,
"step": 1180
},
{
"epoch": 8.818779342723005,
"grad_norm": 0.69921875,
"learning_rate": 5.970149253731343e-06,
"loss": 0.0463,
"step": 1181
},
{
"epoch": 8.826291079812206,
"grad_norm": 0.76171875,
"learning_rate": 5.932835820895523e-06,
"loss": 0.134,
"step": 1182
},
{
"epoch": 8.83380281690141,
"grad_norm": 0.78125,
"learning_rate": 5.8955223880597015e-06,
"loss": 0.0561,
"step": 1183
},
{
"epoch": 8.84131455399061,
"grad_norm": 0.765625,
"learning_rate": 5.858208955223881e-06,
"loss": 0.0546,
"step": 1184
},
{
"epoch": 8.848826291079812,
"grad_norm": 0.74609375,
"learning_rate": 5.82089552238806e-06,
"loss": 0.0528,
"step": 1185
},
{
"epoch": 8.856338028169015,
"grad_norm": 0.6640625,
"learning_rate": 5.783582089552239e-06,
"loss": 0.0404,
"step": 1186
},
{
"epoch": 8.863849765258216,
"grad_norm": 0.97265625,
"learning_rate": 5.746268656716418e-06,
"loss": 0.1005,
"step": 1187
},
{
"epoch": 8.871361502347417,
"grad_norm": 0.74609375,
"learning_rate": 5.708955223880597e-06,
"loss": 0.0627,
"step": 1188
},
{
"epoch": 8.87887323943662,
"grad_norm": 0.7578125,
"learning_rate": 5.671641791044776e-06,
"loss": 0.068,
"step": 1189
},
{
"epoch": 8.886384976525822,
"grad_norm": 0.7578125,
"learning_rate": 5.6343283582089556e-06,
"loss": 0.0471,
"step": 1190
},
{
"epoch": 8.893896713615023,
"grad_norm": 0.81640625,
"learning_rate": 5.597014925373135e-06,
"loss": 0.1057,
"step": 1191
},
{
"epoch": 8.901408450704226,
"grad_norm": 0.83984375,
"learning_rate": 5.559701492537314e-06,
"loss": 0.0565,
"step": 1192
},
{
"epoch": 8.908920187793427,
"grad_norm": 0.73828125,
"learning_rate": 5.522388059701493e-06,
"loss": 0.053,
"step": 1193
},
{
"epoch": 8.916431924882628,
"grad_norm": 0.6953125,
"learning_rate": 5.485074626865671e-06,
"loss": 0.0463,
"step": 1194
},
{
"epoch": 8.923943661971832,
"grad_norm": 0.76171875,
"learning_rate": 5.447761194029851e-06,
"loss": 0.0489,
"step": 1195
},
{
"epoch": 8.931455399061033,
"grad_norm": 0.83984375,
"learning_rate": 5.41044776119403e-06,
"loss": 0.0766,
"step": 1196
},
{
"epoch": 8.938967136150234,
"grad_norm": 0.67578125,
"learning_rate": 5.373134328358209e-06,
"loss": 0.0414,
"step": 1197
},
{
"epoch": 8.946478873239437,
"grad_norm": 0.93359375,
"learning_rate": 5.335820895522389e-06,
"loss": 0.0675,
"step": 1198
},
{
"epoch": 8.953990610328638,
"grad_norm": 0.8359375,
"learning_rate": 5.298507462686567e-06,
"loss": 0.055,
"step": 1199
},
{
"epoch": 8.96150234741784,
"grad_norm": 0.90625,
"learning_rate": 5.261194029850746e-06,
"loss": 0.2729,
"step": 1200
},
{
"epoch": 8.969014084507043,
"grad_norm": 0.78515625,
"learning_rate": 5.2238805970149255e-06,
"loss": 0.0525,
"step": 1201
},
{
"epoch": 8.976525821596244,
"grad_norm": 0.9296875,
"learning_rate": 5.186567164179105e-06,
"loss": 0.1535,
"step": 1202
},
{
"epoch": 8.984037558685445,
"grad_norm": 0.8125,
"learning_rate": 5.149253731343284e-06,
"loss": 0.0609,
"step": 1203
},
{
"epoch": 8.991549295774648,
"grad_norm": 0.7890625,
"learning_rate": 5.111940298507463e-06,
"loss": 0.0616,
"step": 1204
},
{
"epoch": 8.99906103286385,
"grad_norm": 0.74609375,
"learning_rate": 5.074626865671642e-06,
"loss": 0.0545,
"step": 1205
},
{
"epoch": 9.0,
"grad_norm": 2.234375,
"learning_rate": 5.037313432835821e-06,
"loss": 0.0613,
"step": 1206
}
],
"logging_steps": 1,
"max_steps": 1340,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.170403567178875e+17,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}