Stewy Slocum
Add fine-tuned model
0cd24af
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 0,
"global_step": 193,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0051813471502590676,
"grad_norm": 0.5859375,
"learning_rate": 1e-05,
"loss": 2.1904,
"step": 1
},
{
"epoch": 0.010362694300518135,
"grad_norm": 0.56640625,
"learning_rate": 9.94818652849741e-06,
"loss": 2.1307,
"step": 2
},
{
"epoch": 0.015544041450777202,
"grad_norm": 0.55078125,
"learning_rate": 9.89637305699482e-06,
"loss": 2.1128,
"step": 3
},
{
"epoch": 0.02072538860103627,
"grad_norm": 0.55078125,
"learning_rate": 9.844559585492228e-06,
"loss": 2.0918,
"step": 4
},
{
"epoch": 0.025906735751295335,
"grad_norm": 0.54296875,
"learning_rate": 9.792746113989638e-06,
"loss": 2.0508,
"step": 5
},
{
"epoch": 0.031088082901554404,
"grad_norm": 0.546875,
"learning_rate": 9.740932642487048e-06,
"loss": 2.1463,
"step": 6
},
{
"epoch": 0.03626943005181347,
"grad_norm": 0.5078125,
"learning_rate": 9.689119170984456e-06,
"loss": 1.9596,
"step": 7
},
{
"epoch": 0.04145077720207254,
"grad_norm": 0.53125,
"learning_rate": 9.637305699481867e-06,
"loss": 2.112,
"step": 8
},
{
"epoch": 0.046632124352331605,
"grad_norm": 0.486328125,
"learning_rate": 9.585492227979275e-06,
"loss": 1.9563,
"step": 9
},
{
"epoch": 0.05181347150259067,
"grad_norm": 0.55078125,
"learning_rate": 9.533678756476683e-06,
"loss": 1.8997,
"step": 10
},
{
"epoch": 0.05699481865284974,
"grad_norm": 0.455078125,
"learning_rate": 9.481865284974095e-06,
"loss": 1.7939,
"step": 11
},
{
"epoch": 0.06217616580310881,
"grad_norm": 0.47265625,
"learning_rate": 9.430051813471504e-06,
"loss": 1.8679,
"step": 12
},
{
"epoch": 0.06735751295336788,
"grad_norm": 0.51171875,
"learning_rate": 9.378238341968912e-06,
"loss": 1.9434,
"step": 13
},
{
"epoch": 0.07253886010362694,
"grad_norm": 0.447265625,
"learning_rate": 9.326424870466322e-06,
"loss": 1.8658,
"step": 14
},
{
"epoch": 0.07772020725388601,
"grad_norm": 0.365234375,
"learning_rate": 9.27461139896373e-06,
"loss": 1.7418,
"step": 15
},
{
"epoch": 0.08290155440414508,
"grad_norm": 0.349609375,
"learning_rate": 9.22279792746114e-06,
"loss": 1.7164,
"step": 16
},
{
"epoch": 0.08808290155440414,
"grad_norm": 0.35546875,
"learning_rate": 9.17098445595855e-06,
"loss": 1.7372,
"step": 17
},
{
"epoch": 0.09326424870466321,
"grad_norm": 0.357421875,
"learning_rate": 9.11917098445596e-06,
"loss": 1.7713,
"step": 18
},
{
"epoch": 0.09844559585492228,
"grad_norm": 0.359375,
"learning_rate": 9.06735751295337e-06,
"loss": 1.7887,
"step": 19
},
{
"epoch": 0.10362694300518134,
"grad_norm": 0.322265625,
"learning_rate": 9.015544041450778e-06,
"loss": 1.7009,
"step": 20
},
{
"epoch": 0.10880829015544041,
"grad_norm": 0.32421875,
"learning_rate": 8.963730569948186e-06,
"loss": 1.6982,
"step": 21
},
{
"epoch": 0.11398963730569948,
"grad_norm": 0.32421875,
"learning_rate": 8.911917098445596e-06,
"loss": 1.7035,
"step": 22
},
{
"epoch": 0.11917098445595854,
"grad_norm": 0.30859375,
"learning_rate": 8.860103626943006e-06,
"loss": 1.5866,
"step": 23
},
{
"epoch": 0.12435233160621761,
"grad_norm": 0.306640625,
"learning_rate": 8.808290155440415e-06,
"loss": 1.6257,
"step": 24
},
{
"epoch": 0.12953367875647667,
"grad_norm": 0.34375,
"learning_rate": 8.756476683937825e-06,
"loss": 1.6452,
"step": 25
},
{
"epoch": 0.13471502590673576,
"grad_norm": 0.31640625,
"learning_rate": 8.704663212435233e-06,
"loss": 1.639,
"step": 26
},
{
"epoch": 0.13989637305699482,
"grad_norm": 0.314453125,
"learning_rate": 8.652849740932643e-06,
"loss": 1.6445,
"step": 27
},
{
"epoch": 0.14507772020725387,
"grad_norm": 0.333984375,
"learning_rate": 8.601036269430052e-06,
"loss": 1.5961,
"step": 28
},
{
"epoch": 0.15025906735751296,
"grad_norm": 0.296875,
"learning_rate": 8.549222797927462e-06,
"loss": 1.5829,
"step": 29
},
{
"epoch": 0.15544041450777202,
"grad_norm": 0.296875,
"learning_rate": 8.497409326424872e-06,
"loss": 1.5735,
"step": 30
},
{
"epoch": 0.16062176165803108,
"grad_norm": 0.298828125,
"learning_rate": 8.44559585492228e-06,
"loss": 1.5644,
"step": 31
},
{
"epoch": 0.16580310880829016,
"grad_norm": 0.33203125,
"learning_rate": 8.393782383419689e-06,
"loss": 1.5304,
"step": 32
},
{
"epoch": 0.17098445595854922,
"grad_norm": 0.28125,
"learning_rate": 8.341968911917099e-06,
"loss": 1.5284,
"step": 33
},
{
"epoch": 0.17616580310880828,
"grad_norm": 0.3046875,
"learning_rate": 8.290155440414507e-06,
"loss": 1.561,
"step": 34
},
{
"epoch": 0.18134715025906736,
"grad_norm": 0.265625,
"learning_rate": 8.238341968911918e-06,
"loss": 1.4904,
"step": 35
},
{
"epoch": 0.18652849740932642,
"grad_norm": 0.3203125,
"learning_rate": 8.186528497409328e-06,
"loss": 1.4777,
"step": 36
},
{
"epoch": 0.19170984455958548,
"grad_norm": 0.30078125,
"learning_rate": 8.134715025906736e-06,
"loss": 1.5864,
"step": 37
},
{
"epoch": 0.19689119170984457,
"grad_norm": 0.267578125,
"learning_rate": 8.082901554404146e-06,
"loss": 1.4958,
"step": 38
},
{
"epoch": 0.20207253886010362,
"grad_norm": 0.26953125,
"learning_rate": 8.031088082901555e-06,
"loss": 1.4746,
"step": 39
},
{
"epoch": 0.20725388601036268,
"grad_norm": 0.275390625,
"learning_rate": 7.979274611398965e-06,
"loss": 1.4437,
"step": 40
},
{
"epoch": 0.21243523316062177,
"grad_norm": 0.251953125,
"learning_rate": 7.927461139896375e-06,
"loss": 1.5036,
"step": 41
},
{
"epoch": 0.21761658031088082,
"grad_norm": 0.283203125,
"learning_rate": 7.875647668393783e-06,
"loss": 1.5222,
"step": 42
},
{
"epoch": 0.22279792746113988,
"grad_norm": 0.236328125,
"learning_rate": 7.823834196891192e-06,
"loss": 1.4365,
"step": 43
},
{
"epoch": 0.22797927461139897,
"grad_norm": 0.251953125,
"learning_rate": 7.772020725388602e-06,
"loss": 1.4751,
"step": 44
},
{
"epoch": 0.23316062176165803,
"grad_norm": 0.267578125,
"learning_rate": 7.72020725388601e-06,
"loss": 1.5108,
"step": 45
},
{
"epoch": 0.23834196891191708,
"grad_norm": 0.234375,
"learning_rate": 7.66839378238342e-06,
"loss": 1.4059,
"step": 46
},
{
"epoch": 0.24352331606217617,
"grad_norm": 0.310546875,
"learning_rate": 7.61658031088083e-06,
"loss": 1.4012,
"step": 47
},
{
"epoch": 0.24870466321243523,
"grad_norm": 0.2392578125,
"learning_rate": 7.564766839378239e-06,
"loss": 1.4273,
"step": 48
},
{
"epoch": 0.2538860103626943,
"grad_norm": 0.2265625,
"learning_rate": 7.512953367875648e-06,
"loss": 1.3553,
"step": 49
},
{
"epoch": 0.25906735751295334,
"grad_norm": 0.28125,
"learning_rate": 7.461139896373057e-06,
"loss": 1.5213,
"step": 50
},
{
"epoch": 0.26424870466321243,
"grad_norm": 0.21484375,
"learning_rate": 7.409326424870467e-06,
"loss": 1.3887,
"step": 51
},
{
"epoch": 0.2694300518134715,
"grad_norm": 0.2177734375,
"learning_rate": 7.357512953367876e-06,
"loss": 1.3657,
"step": 52
},
{
"epoch": 0.27461139896373055,
"grad_norm": 0.224609375,
"learning_rate": 7.305699481865286e-06,
"loss": 1.391,
"step": 53
},
{
"epoch": 0.27979274611398963,
"grad_norm": 0.2578125,
"learning_rate": 7.253886010362695e-06,
"loss": 1.395,
"step": 54
},
{
"epoch": 0.2849740932642487,
"grad_norm": 0.2099609375,
"learning_rate": 7.2020725388601045e-06,
"loss": 1.3452,
"step": 55
},
{
"epoch": 0.29015544041450775,
"grad_norm": 0.2080078125,
"learning_rate": 7.150259067357514e-06,
"loss": 1.3142,
"step": 56
},
{
"epoch": 0.29533678756476683,
"grad_norm": 0.2275390625,
"learning_rate": 7.098445595854922e-06,
"loss": 1.4131,
"step": 57
},
{
"epoch": 0.3005181347150259,
"grad_norm": 0.26953125,
"learning_rate": 7.0466321243523315e-06,
"loss": 1.3867,
"step": 58
},
{
"epoch": 0.30569948186528495,
"grad_norm": 0.205078125,
"learning_rate": 6.994818652849742e-06,
"loss": 1.3463,
"step": 59
},
{
"epoch": 0.31088082901554404,
"grad_norm": 0.216796875,
"learning_rate": 6.943005181347151e-06,
"loss": 1.4282,
"step": 60
},
{
"epoch": 0.3160621761658031,
"grad_norm": 0.193359375,
"learning_rate": 6.89119170984456e-06,
"loss": 1.3243,
"step": 61
},
{
"epoch": 0.32124352331606215,
"grad_norm": 0.220703125,
"learning_rate": 6.839378238341969e-06,
"loss": 1.3298,
"step": 62
},
{
"epoch": 0.32642487046632124,
"grad_norm": 0.2265625,
"learning_rate": 6.787564766839379e-06,
"loss": 1.3915,
"step": 63
},
{
"epoch": 0.3316062176165803,
"grad_norm": 0.2158203125,
"learning_rate": 6.735751295336788e-06,
"loss": 1.4065,
"step": 64
},
{
"epoch": 0.33678756476683935,
"grad_norm": 0.193359375,
"learning_rate": 6.683937823834198e-06,
"loss": 1.3088,
"step": 65
},
{
"epoch": 0.34196891191709844,
"grad_norm": 0.337890625,
"learning_rate": 6.632124352331607e-06,
"loss": 1.2932,
"step": 66
},
{
"epoch": 0.3471502590673575,
"grad_norm": 0.1904296875,
"learning_rate": 6.5803108808290166e-06,
"loss": 1.2824,
"step": 67
},
{
"epoch": 0.35233160621761656,
"grad_norm": 0.267578125,
"learning_rate": 6.528497409326425e-06,
"loss": 1.3223,
"step": 68
},
{
"epoch": 0.35751295336787564,
"grad_norm": 0.251953125,
"learning_rate": 6.476683937823834e-06,
"loss": 1.2771,
"step": 69
},
{
"epoch": 0.3626943005181347,
"grad_norm": 0.26953125,
"learning_rate": 6.4248704663212435e-06,
"loss": 1.2777,
"step": 70
},
{
"epoch": 0.36787564766839376,
"grad_norm": 0.2158203125,
"learning_rate": 6.373056994818654e-06,
"loss": 1.3134,
"step": 71
},
{
"epoch": 0.37305699481865284,
"grad_norm": 0.1806640625,
"learning_rate": 6.321243523316063e-06,
"loss": 1.2717,
"step": 72
},
{
"epoch": 0.37823834196891193,
"grad_norm": 0.19140625,
"learning_rate": 6.269430051813472e-06,
"loss": 1.2838,
"step": 73
},
{
"epoch": 0.38341968911917096,
"grad_norm": 0.19140625,
"learning_rate": 6.217616580310881e-06,
"loss": 1.3106,
"step": 74
},
{
"epoch": 0.38860103626943004,
"grad_norm": 0.2041015625,
"learning_rate": 6.165803108808291e-06,
"loss": 1.3315,
"step": 75
},
{
"epoch": 0.39378238341968913,
"grad_norm": 0.1787109375,
"learning_rate": 6.113989637305699e-06,
"loss": 1.2833,
"step": 76
},
{
"epoch": 0.39896373056994816,
"grad_norm": 0.1728515625,
"learning_rate": 6.06217616580311e-06,
"loss": 1.2527,
"step": 77
},
{
"epoch": 0.40414507772020725,
"grad_norm": 0.236328125,
"learning_rate": 6.0103626943005185e-06,
"loss": 1.3637,
"step": 78
},
{
"epoch": 0.40932642487046633,
"grad_norm": 0.171875,
"learning_rate": 5.958549222797928e-06,
"loss": 1.2618,
"step": 79
},
{
"epoch": 0.41450777202072536,
"grad_norm": 0.1826171875,
"learning_rate": 5.906735751295337e-06,
"loss": 1.2929,
"step": 80
},
{
"epoch": 0.41968911917098445,
"grad_norm": 0.1875,
"learning_rate": 5.854922279792746e-06,
"loss": 1.3042,
"step": 81
},
{
"epoch": 0.42487046632124353,
"grad_norm": 0.2080078125,
"learning_rate": 5.8031088082901555e-06,
"loss": 1.3224,
"step": 82
},
{
"epoch": 0.43005181347150256,
"grad_norm": 0.19921875,
"learning_rate": 5.751295336787566e-06,
"loss": 1.312,
"step": 83
},
{
"epoch": 0.43523316062176165,
"grad_norm": 0.255859375,
"learning_rate": 5.699481865284975e-06,
"loss": 1.2953,
"step": 84
},
{
"epoch": 0.44041450777202074,
"grad_norm": 0.1943359375,
"learning_rate": 5.647668393782384e-06,
"loss": 1.26,
"step": 85
},
{
"epoch": 0.44559585492227977,
"grad_norm": 0.279296875,
"learning_rate": 5.5958549222797934e-06,
"loss": 1.2324,
"step": 86
},
{
"epoch": 0.45077720207253885,
"grad_norm": 0.1787109375,
"learning_rate": 5.544041450777202e-06,
"loss": 1.207,
"step": 87
},
{
"epoch": 0.45595854922279794,
"grad_norm": 0.1865234375,
"learning_rate": 5.492227979274611e-06,
"loss": 1.2599,
"step": 88
},
{
"epoch": 0.46113989637305697,
"grad_norm": 0.1806640625,
"learning_rate": 5.440414507772021e-06,
"loss": 1.2447,
"step": 89
},
{
"epoch": 0.46632124352331605,
"grad_norm": 0.1953125,
"learning_rate": 5.3886010362694305e-06,
"loss": 1.1624,
"step": 90
},
{
"epoch": 0.47150259067357514,
"grad_norm": 0.1796875,
"learning_rate": 5.33678756476684e-06,
"loss": 1.2802,
"step": 91
},
{
"epoch": 0.47668393782383417,
"grad_norm": 0.28515625,
"learning_rate": 5.284974093264249e-06,
"loss": 1.2723,
"step": 92
},
{
"epoch": 0.48186528497409326,
"grad_norm": 0.32421875,
"learning_rate": 5.233160621761658e-06,
"loss": 1.2746,
"step": 93
},
{
"epoch": 0.48704663212435234,
"grad_norm": 0.212890625,
"learning_rate": 5.1813471502590676e-06,
"loss": 1.2925,
"step": 94
},
{
"epoch": 0.49222797927461137,
"grad_norm": 0.17578125,
"learning_rate": 5.129533678756478e-06,
"loss": 1.2142,
"step": 95
},
{
"epoch": 0.49740932642487046,
"grad_norm": 0.19921875,
"learning_rate": 5.077720207253887e-06,
"loss": 1.2779,
"step": 96
},
{
"epoch": 0.5025906735751295,
"grad_norm": 0.18359375,
"learning_rate": 5.025906735751296e-06,
"loss": 1.243,
"step": 97
},
{
"epoch": 0.5077720207253886,
"grad_norm": 0.185546875,
"learning_rate": 4.974093264248705e-06,
"loss": 1.2286,
"step": 98
},
{
"epoch": 0.5129533678756477,
"grad_norm": 0.181640625,
"learning_rate": 4.922279792746114e-06,
"loss": 1.2651,
"step": 99
},
{
"epoch": 0.5181347150259067,
"grad_norm": 0.2001953125,
"learning_rate": 4.870466321243524e-06,
"loss": 1.2102,
"step": 100
},
{
"epoch": 0.5233160621761658,
"grad_norm": 0.177734375,
"learning_rate": 4.818652849740933e-06,
"loss": 1.2121,
"step": 101
},
{
"epoch": 0.5284974093264249,
"grad_norm": 0.1865234375,
"learning_rate": 4.766839378238342e-06,
"loss": 1.2662,
"step": 102
},
{
"epoch": 0.533678756476684,
"grad_norm": 0.173828125,
"learning_rate": 4.715025906735752e-06,
"loss": 1.2483,
"step": 103
},
{
"epoch": 0.538860103626943,
"grad_norm": 0.271484375,
"learning_rate": 4.663212435233161e-06,
"loss": 1.1849,
"step": 104
},
{
"epoch": 0.5440414507772021,
"grad_norm": 0.1767578125,
"learning_rate": 4.61139896373057e-06,
"loss": 1.2014,
"step": 105
},
{
"epoch": 0.5492227979274611,
"grad_norm": 0.1845703125,
"learning_rate": 4.55958549222798e-06,
"loss": 1.2394,
"step": 106
},
{
"epoch": 0.5544041450777202,
"grad_norm": 0.26953125,
"learning_rate": 4.507772020725389e-06,
"loss": 1.2432,
"step": 107
},
{
"epoch": 0.5595854922279793,
"grad_norm": 0.2470703125,
"learning_rate": 4.455958549222798e-06,
"loss": 1.3076,
"step": 108
},
{
"epoch": 0.5647668393782384,
"grad_norm": 0.169921875,
"learning_rate": 4.404145077720207e-06,
"loss": 1.1779,
"step": 109
},
{
"epoch": 0.5699481865284974,
"grad_norm": 0.1875,
"learning_rate": 4.352331606217617e-06,
"loss": 1.2862,
"step": 110
},
{
"epoch": 0.5751295336787565,
"grad_norm": 0.1669921875,
"learning_rate": 4.300518134715026e-06,
"loss": 1.2241,
"step": 111
},
{
"epoch": 0.5803108808290155,
"grad_norm": 0.1708984375,
"learning_rate": 4.248704663212436e-06,
"loss": 1.2024,
"step": 112
},
{
"epoch": 0.5854922279792746,
"grad_norm": 0.1572265625,
"learning_rate": 4.1968911917098444e-06,
"loss": 1.1879,
"step": 113
},
{
"epoch": 0.5906735751295337,
"grad_norm": 0.166015625,
"learning_rate": 4.145077720207254e-06,
"loss": 1.2018,
"step": 114
},
{
"epoch": 0.5958549222797928,
"grad_norm": 0.1884765625,
"learning_rate": 4.093264248704664e-06,
"loss": 1.2372,
"step": 115
},
{
"epoch": 0.6010362694300518,
"grad_norm": 0.2734375,
"learning_rate": 4.041450777202073e-06,
"loss": 1.215,
"step": 116
},
{
"epoch": 0.6062176165803109,
"grad_norm": 0.1962890625,
"learning_rate": 3.989637305699482e-06,
"loss": 1.266,
"step": 117
},
{
"epoch": 0.6113989637305699,
"grad_norm": 0.185546875,
"learning_rate": 3.937823834196892e-06,
"loss": 1.2359,
"step": 118
},
{
"epoch": 0.616580310880829,
"grad_norm": 0.2177734375,
"learning_rate": 3.886010362694301e-06,
"loss": 1.3115,
"step": 119
},
{
"epoch": 0.6217616580310881,
"grad_norm": 0.1728515625,
"learning_rate": 3.83419689119171e-06,
"loss": 1.2321,
"step": 120
},
{
"epoch": 0.6269430051813472,
"grad_norm": 0.17578125,
"learning_rate": 3.7823834196891194e-06,
"loss": 1.218,
"step": 121
},
{
"epoch": 0.6321243523316062,
"grad_norm": 0.208984375,
"learning_rate": 3.7305699481865287e-06,
"loss": 1.2228,
"step": 122
},
{
"epoch": 0.6373056994818653,
"grad_norm": 0.337890625,
"learning_rate": 3.678756476683938e-06,
"loss": 1.1292,
"step": 123
},
{
"epoch": 0.6424870466321243,
"grad_norm": 0.30859375,
"learning_rate": 3.6269430051813476e-06,
"loss": 1.2333,
"step": 124
},
{
"epoch": 0.6476683937823834,
"grad_norm": 0.173828125,
"learning_rate": 3.575129533678757e-06,
"loss": 1.1676,
"step": 125
},
{
"epoch": 0.6528497409326425,
"grad_norm": 0.193359375,
"learning_rate": 3.5233160621761657e-06,
"loss": 1.2409,
"step": 126
},
{
"epoch": 0.6580310880829016,
"grad_norm": 0.255859375,
"learning_rate": 3.4715025906735754e-06,
"loss": 1.1751,
"step": 127
},
{
"epoch": 0.6632124352331606,
"grad_norm": 0.16796875,
"learning_rate": 3.4196891191709847e-06,
"loss": 1.1823,
"step": 128
},
{
"epoch": 0.6683937823834197,
"grad_norm": 0.2021484375,
"learning_rate": 3.367875647668394e-06,
"loss": 1.244,
"step": 129
},
{
"epoch": 0.6735751295336787,
"grad_norm": 0.203125,
"learning_rate": 3.3160621761658036e-06,
"loss": 1.244,
"step": 130
},
{
"epoch": 0.6787564766839378,
"grad_norm": 0.294921875,
"learning_rate": 3.2642487046632125e-06,
"loss": 1.2113,
"step": 131
},
{
"epoch": 0.6839378238341969,
"grad_norm": 0.2197265625,
"learning_rate": 3.2124352331606218e-06,
"loss": 1.2801,
"step": 132
},
{
"epoch": 0.689119170984456,
"grad_norm": 0.2353515625,
"learning_rate": 3.1606217616580314e-06,
"loss": 1.1404,
"step": 133
},
{
"epoch": 0.694300518134715,
"grad_norm": 0.16015625,
"learning_rate": 3.1088082901554407e-06,
"loss": 1.1907,
"step": 134
},
{
"epoch": 0.6994818652849741,
"grad_norm": 0.189453125,
"learning_rate": 3.0569948186528495e-06,
"loss": 1.2261,
"step": 135
},
{
"epoch": 0.7046632124352331,
"grad_norm": 0.1982421875,
"learning_rate": 3.0051813471502592e-06,
"loss": 1.215,
"step": 136
},
{
"epoch": 0.7098445595854922,
"grad_norm": 0.212890625,
"learning_rate": 2.9533678756476685e-06,
"loss": 1.205,
"step": 137
},
{
"epoch": 0.7150259067357513,
"grad_norm": 0.1865234375,
"learning_rate": 2.9015544041450778e-06,
"loss": 1.1383,
"step": 138
},
{
"epoch": 0.7202072538860104,
"grad_norm": 0.185546875,
"learning_rate": 2.8497409326424875e-06,
"loss": 1.147,
"step": 139
},
{
"epoch": 0.7253886010362695,
"grad_norm": 0.19140625,
"learning_rate": 2.7979274611398967e-06,
"loss": 1.1653,
"step": 140
},
{
"epoch": 0.7305699481865285,
"grad_norm": 0.1630859375,
"learning_rate": 2.7461139896373056e-06,
"loss": 1.1968,
"step": 141
},
{
"epoch": 0.7357512953367875,
"grad_norm": 0.1875,
"learning_rate": 2.6943005181347152e-06,
"loss": 1.1995,
"step": 142
},
{
"epoch": 0.7409326424870466,
"grad_norm": 0.169921875,
"learning_rate": 2.6424870466321245e-06,
"loss": 1.1571,
"step": 143
},
{
"epoch": 0.7461139896373057,
"grad_norm": 0.26171875,
"learning_rate": 2.5906735751295338e-06,
"loss": 1.1923,
"step": 144
},
{
"epoch": 0.7512953367875648,
"grad_norm": 0.189453125,
"learning_rate": 2.5388601036269435e-06,
"loss": 1.1903,
"step": 145
},
{
"epoch": 0.7564766839378239,
"grad_norm": 0.30859375,
"learning_rate": 2.4870466321243523e-06,
"loss": 1.3161,
"step": 146
},
{
"epoch": 0.7616580310880829,
"grad_norm": 0.18359375,
"learning_rate": 2.435233160621762e-06,
"loss": 1.1498,
"step": 147
},
{
"epoch": 0.7668393782383419,
"grad_norm": 0.1689453125,
"learning_rate": 2.383419689119171e-06,
"loss": 1.1664,
"step": 148
},
{
"epoch": 0.772020725388601,
"grad_norm": 0.2578125,
"learning_rate": 2.3316062176165805e-06,
"loss": 1.1965,
"step": 149
},
{
"epoch": 0.7772020725388601,
"grad_norm": 0.267578125,
"learning_rate": 2.27979274611399e-06,
"loss": 1.1897,
"step": 150
},
{
"epoch": 0.7823834196891192,
"grad_norm": 0.267578125,
"learning_rate": 2.227979274611399e-06,
"loss": 1.2007,
"step": 151
},
{
"epoch": 0.7875647668393783,
"grad_norm": 0.1640625,
"learning_rate": 2.1761658031088083e-06,
"loss": 1.1804,
"step": 152
},
{
"epoch": 0.7927461139896373,
"grad_norm": 0.1669921875,
"learning_rate": 2.124352331606218e-06,
"loss": 1.1773,
"step": 153
},
{
"epoch": 0.7979274611398963,
"grad_norm": 0.294921875,
"learning_rate": 2.072538860103627e-06,
"loss": 1.2459,
"step": 154
},
{
"epoch": 0.8031088082901554,
"grad_norm": 0.1982421875,
"learning_rate": 2.0207253886010365e-06,
"loss": 1.2608,
"step": 155
},
{
"epoch": 0.8082901554404145,
"grad_norm": 0.220703125,
"learning_rate": 1.968911917098446e-06,
"loss": 1.1368,
"step": 156
},
{
"epoch": 0.8134715025906736,
"grad_norm": 0.220703125,
"learning_rate": 1.917098445595855e-06,
"loss": 1.1361,
"step": 157
},
{
"epoch": 0.8186528497409327,
"grad_norm": 0.185546875,
"learning_rate": 1.8652849740932643e-06,
"loss": 1.175,
"step": 158
},
{
"epoch": 0.8238341968911918,
"grad_norm": 0.1767578125,
"learning_rate": 1.8134715025906738e-06,
"loss": 1.1436,
"step": 159
},
{
"epoch": 0.8290155440414507,
"grad_norm": 0.390625,
"learning_rate": 1.7616580310880829e-06,
"loss": 1.2755,
"step": 160
},
{
"epoch": 0.8341968911917098,
"grad_norm": 0.1845703125,
"learning_rate": 1.7098445595854923e-06,
"loss": 1.2285,
"step": 161
},
{
"epoch": 0.8393782383419689,
"grad_norm": 0.2890625,
"learning_rate": 1.6580310880829018e-06,
"loss": 1.2302,
"step": 162
},
{
"epoch": 0.844559585492228,
"grad_norm": 0.2470703125,
"learning_rate": 1.6062176165803109e-06,
"loss": 1.1622,
"step": 163
},
{
"epoch": 0.8497409326424871,
"grad_norm": 0.369140625,
"learning_rate": 1.5544041450777204e-06,
"loss": 1.1747,
"step": 164
},
{
"epoch": 0.8549222797927462,
"grad_norm": 0.1728515625,
"learning_rate": 1.5025906735751296e-06,
"loss": 1.1839,
"step": 165
},
{
"epoch": 0.8601036269430051,
"grad_norm": 0.2353515625,
"learning_rate": 1.4507772020725389e-06,
"loss": 1.1777,
"step": 166
},
{
"epoch": 0.8652849740932642,
"grad_norm": 0.171875,
"learning_rate": 1.3989637305699484e-06,
"loss": 1.1679,
"step": 167
},
{
"epoch": 0.8704663212435233,
"grad_norm": 0.1875,
"learning_rate": 1.3471502590673576e-06,
"loss": 1.1815,
"step": 168
},
{
"epoch": 0.8756476683937824,
"grad_norm": 0.1767578125,
"learning_rate": 1.2953367875647669e-06,
"loss": 1.2012,
"step": 169
},
{
"epoch": 0.8808290155440415,
"grad_norm": 0.203125,
"learning_rate": 1.2435233160621762e-06,
"loss": 1.1577,
"step": 170
},
{
"epoch": 0.8860103626943006,
"grad_norm": 0.17578125,
"learning_rate": 1.1917098445595854e-06,
"loss": 1.145,
"step": 171
},
{
"epoch": 0.8911917098445595,
"grad_norm": 0.17578125,
"learning_rate": 1.139896373056995e-06,
"loss": 1.1748,
"step": 172
},
{
"epoch": 0.8963730569948186,
"grad_norm": 0.2373046875,
"learning_rate": 1.0880829015544042e-06,
"loss": 1.1703,
"step": 173
},
{
"epoch": 0.9015544041450777,
"grad_norm": 0.291015625,
"learning_rate": 1.0362694300518134e-06,
"loss": 1.25,
"step": 174
},
{
"epoch": 0.9067357512953368,
"grad_norm": 0.189453125,
"learning_rate": 9.84455958549223e-07,
"loss": 1.1705,
"step": 175
},
{
"epoch": 0.9119170984455959,
"grad_norm": 0.181640625,
"learning_rate": 9.326424870466322e-07,
"loss": 1.1529,
"step": 176
},
{
"epoch": 0.917098445595855,
"grad_norm": 0.1689453125,
"learning_rate": 8.808290155440414e-07,
"loss": 1.1649,
"step": 177
},
{
"epoch": 0.9222797927461139,
"grad_norm": 0.224609375,
"learning_rate": 8.290155440414509e-07,
"loss": 1.2016,
"step": 178
},
{
"epoch": 0.927461139896373,
"grad_norm": 0.1943359375,
"learning_rate": 7.772020725388602e-07,
"loss": 1.2224,
"step": 179
},
{
"epoch": 0.9326424870466321,
"grad_norm": 0.2890625,
"learning_rate": 7.253886010362694e-07,
"loss": 1.1401,
"step": 180
},
{
"epoch": 0.9378238341968912,
"grad_norm": 0.2236328125,
"learning_rate": 6.735751295336788e-07,
"loss": 1.1787,
"step": 181
},
{
"epoch": 0.9430051813471503,
"grad_norm": 0.32421875,
"learning_rate": 6.217616580310881e-07,
"loss": 1.2108,
"step": 182
},
{
"epoch": 0.9481865284974094,
"grad_norm": 0.1845703125,
"learning_rate": 5.699481865284974e-07,
"loss": 1.1799,
"step": 183
},
{
"epoch": 0.9533678756476683,
"grad_norm": 0.283203125,
"learning_rate": 5.181347150259067e-07,
"loss": 1.1576,
"step": 184
},
{
"epoch": 0.9585492227979274,
"grad_norm": 0.19921875,
"learning_rate": 4.663212435233161e-07,
"loss": 1.1976,
"step": 185
},
{
"epoch": 0.9637305699481865,
"grad_norm": 0.1943359375,
"learning_rate": 4.1450777202072546e-07,
"loss": 1.1638,
"step": 186
},
{
"epoch": 0.9689119170984456,
"grad_norm": 0.1787109375,
"learning_rate": 3.626943005181347e-07,
"loss": 1.1646,
"step": 187
},
{
"epoch": 0.9740932642487047,
"grad_norm": 0.1748046875,
"learning_rate": 3.1088082901554404e-07,
"loss": 1.1893,
"step": 188
},
{
"epoch": 0.9792746113989638,
"grad_norm": 0.1865234375,
"learning_rate": 2.5906735751295336e-07,
"loss": 1.19,
"step": 189
},
{
"epoch": 0.9844559585492227,
"grad_norm": 0.298828125,
"learning_rate": 2.0725388601036273e-07,
"loss": 1.1957,
"step": 190
},
{
"epoch": 0.9896373056994818,
"grad_norm": 0.173828125,
"learning_rate": 1.5544041450777202e-07,
"loss": 1.1617,
"step": 191
},
{
"epoch": 0.9948186528497409,
"grad_norm": 0.197265625,
"learning_rate": 1.0362694300518136e-07,
"loss": 1.1923,
"step": 192
},
{
"epoch": 1.0,
"grad_norm": 0.2255859375,
"learning_rate": 5.181347150259068e-08,
"loss": 1.3158,
"step": 193
}
],
"logging_steps": 1.0,
"max_steps": 193,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 0,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 6.264235809927332e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}