{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.38095238095238093,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0038095238095238095,
      "grad_norm": 0.8425641655921936,
      "learning_rate": 1e-05,
      "loss": 2.9022,
      "step": 1
    },
    {
      "epoch": 0.0038095238095238095,
      "eval_loss": 3.012644052505493,
      "eval_runtime": 23.3161,
      "eval_samples_per_second": 37.914,
      "eval_steps_per_second": 1.201,
      "step": 1
    },
    {
      "epoch": 0.007619047619047619,
      "grad_norm": 0.8923664689064026,
      "learning_rate": 2e-05,
      "loss": 2.8666,
      "step": 2
    },
    {
      "epoch": 0.011428571428571429,
      "grad_norm": 0.8885706067085266,
      "learning_rate": 3e-05,
      "loss": 2.9939,
      "step": 3
    },
    {
      "epoch": 0.015238095238095238,
      "grad_norm": 0.7595656514167786,
      "learning_rate": 4e-05,
      "loss": 2.7863,
      "step": 4
    },
    {
      "epoch": 0.01904761904761905,
      "grad_norm": 0.7122583985328674,
      "learning_rate": 5e-05,
      "loss": 2.8128,
      "step": 5
    },
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 0.89375901222229,
      "learning_rate": 6e-05,
      "loss": 3.0086,
      "step": 6
    },
    {
      "epoch": 0.02666666666666667,
      "grad_norm": 0.8725149035453796,
      "learning_rate": 7e-05,
      "loss": 2.8897,
      "step": 7
    },
    {
      "epoch": 0.030476190476190476,
      "grad_norm": 0.8501432538032532,
      "learning_rate": 8e-05,
      "loss": 2.9326,
      "step": 8
    },
    {
      "epoch": 0.03428571428571429,
      "grad_norm": 0.9583824872970581,
      "learning_rate": 9e-05,
      "loss": 3.0583,
      "step": 9
    },
    {
      "epoch": 0.03428571428571429,
      "eval_loss": 2.7582240104675293,
      "eval_runtime": 23.3379,
      "eval_samples_per_second": 37.878,
      "eval_steps_per_second": 1.2,
      "step": 9
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 0.7377868890762329,
      "learning_rate": 0.0001,
      "loss": 2.6929,
      "step": 10
    },
    {
      "epoch": 0.0419047619047619,
      "grad_norm": 0.7336325645446777,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.5914,
      "step": 11
    },
    {
      "epoch": 0.045714285714285714,
      "grad_norm": 0.8724717497825623,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.6152,
      "step": 12
    },
    {
      "epoch": 0.049523809523809526,
      "grad_norm": 0.9832696914672852,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.453,
      "step": 13
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 0.9889651536941528,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.6524,
      "step": 14
    },
    {
      "epoch": 0.05714285714285714,
      "grad_norm": 0.952361524105072,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.4998,
      "step": 15
    },
    {
      "epoch": 0.06095238095238095,
      "grad_norm": 0.7652778029441833,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.4316,
      "step": 16
    },
    {
      "epoch": 0.06476190476190476,
      "grad_norm": 0.7523125410079956,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.4392,
      "step": 17
    },
    {
      "epoch": 0.06857142857142857,
      "grad_norm": 0.7820950150489807,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.4528,
      "step": 18
    },
    {
      "epoch": 0.06857142857142857,
      "eval_loss": 2.4456119537353516,
      "eval_runtime": 23.2826,
      "eval_samples_per_second": 37.968,
      "eval_steps_per_second": 1.203,
      "step": 18
    },
    {
      "epoch": 0.07238095238095238,
      "grad_norm": 0.6220594048500061,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.2962,
      "step": 19
    },
    {
      "epoch": 0.0761904761904762,
      "grad_norm": 0.8074927926063538,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.2276,
      "step": 20
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.7311758995056152,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.392,
      "step": 21
    },
    {
      "epoch": 0.0838095238095238,
      "grad_norm": 0.6732069849967957,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.3772,
      "step": 22
    },
    {
      "epoch": 0.08761904761904762,
      "grad_norm": 0.6739742755889893,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.263,
      "step": 23
    },
    {
      "epoch": 0.09142857142857143,
      "grad_norm": 0.7148386240005493,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.2541,
      "step": 24
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.7360737323760986,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.4418,
      "step": 25
    },
    {
      "epoch": 0.09904761904761905,
      "grad_norm": 0.679867684841156,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.2185,
      "step": 26
    },
    {
      "epoch": 0.10285714285714286,
      "grad_norm": 0.7640732526779175,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.1802,
      "step": 27
    },
    {
      "epoch": 0.10285714285714286,
      "eval_loss": 2.3157849311828613,
      "eval_runtime": 23.2875,
      "eval_samples_per_second": 37.96,
      "eval_steps_per_second": 1.202,
      "step": 27
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 0.654911994934082,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.2952,
      "step": 28
    },
    {
      "epoch": 0.11047619047619048,
      "grad_norm": 0.6312480568885803,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.2159,
      "step": 29
    },
    {
      "epoch": 0.11428571428571428,
      "grad_norm": 0.6264930963516235,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.1769,
      "step": 30
    },
    {
      "epoch": 0.1180952380952381,
      "grad_norm": 0.62114018201828,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.3689,
      "step": 31
    },
    {
      "epoch": 0.1219047619047619,
      "grad_norm": 0.7079157829284668,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.282,
      "step": 32
    },
    {
      "epoch": 0.12571428571428572,
      "grad_norm": 0.6873489022254944,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.2897,
      "step": 33
    },
    {
      "epoch": 0.1295238095238095,
      "grad_norm": 0.7113760709762573,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.2389,
      "step": 34
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.620746374130249,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.2117,
      "step": 35
    },
    {
      "epoch": 0.13714285714285715,
      "grad_norm": 0.6419087648391724,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.3821,
      "step": 36
    },
    {
      "epoch": 0.13714285714285715,
      "eval_loss": 2.264549493789673,
      "eval_runtime": 23.3065,
      "eval_samples_per_second": 37.929,
      "eval_steps_per_second": 1.201,
      "step": 36
    },
    {
      "epoch": 0.14095238095238094,
      "grad_norm": 0.5768018960952759,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.1495,
      "step": 37
    },
    {
      "epoch": 0.14476190476190476,
      "grad_norm": 0.6271620988845825,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.1974,
      "step": 38
    },
    {
      "epoch": 0.14857142857142858,
      "grad_norm": 0.713019847869873,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.1833,
      "step": 39
    },
    {
      "epoch": 0.1523809523809524,
      "grad_norm": 0.5771420001983643,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.2127,
      "step": 40
    },
    {
      "epoch": 0.15619047619047619,
      "grad_norm": 0.5620035529136658,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.2167,
      "step": 41
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.6497955918312073,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.322,
      "step": 42
    },
    {
      "epoch": 0.16380952380952382,
      "grad_norm": 0.7585984468460083,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.1695,
      "step": 43
    },
    {
      "epoch": 0.1676190476190476,
      "grad_norm": 1.7383661270141602,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.3977,
      "step": 44
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.5274875164031982,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.9752,
      "step": 45
    },
    {
      "epoch": 0.17142857142857143,
      "eval_loss": 2.2403390407562256,
      "eval_runtime": 23.2833,
      "eval_samples_per_second": 37.967,
      "eval_steps_per_second": 1.203,
      "step": 45
    },
    {
      "epoch": 0.17523809523809525,
      "grad_norm": 0.528351366519928,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1741,
      "step": 46
    },
    {
      "epoch": 0.17904761904761904,
      "grad_norm": 0.6983162760734558,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.323,
      "step": 47
    },
    {
      "epoch": 0.18285714285714286,
      "grad_norm": 0.5931514501571655,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.2507,
      "step": 48
    },
    {
      "epoch": 0.18666666666666668,
      "grad_norm": 0.6230358481407166,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.2536,
      "step": 49
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.5384048819541931,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.1278,
      "step": 50
    },
    {
      "epoch": 0.19428571428571428,
      "grad_norm": 0.523990273475647,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.1908,
      "step": 51
    },
    {
      "epoch": 0.1980952380952381,
      "grad_norm": 0.695479691028595,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.1215,
      "step": 52
    },
    {
      "epoch": 0.2019047619047619,
      "grad_norm": 0.6540449261665344,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.1393,
      "step": 53
    },
    {
      "epoch": 0.2057142857142857,
      "grad_norm": 1.415208101272583,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.2981,
      "step": 54
    },
    {
      "epoch": 0.2057142857142857,
      "eval_loss": 2.2233521938323975,
      "eval_runtime": 23.2756,
      "eval_samples_per_second": 37.98,
      "eval_steps_per_second": 1.203,
      "step": 54
    },
    {
      "epoch": 0.20952380952380953,
      "grad_norm": 0.6257505416870117,
      "learning_rate": 5e-05,
      "loss": 2.2164,
      "step": 55
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 0.5463209748268127,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.1594,
      "step": 56
    },
    {
      "epoch": 0.21714285714285714,
      "grad_norm": 0.552152156829834,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.2046,
      "step": 57
    },
    {
      "epoch": 0.22095238095238096,
      "grad_norm": 0.8017885684967041,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.0353,
      "step": 58
    },
    {
      "epoch": 0.22476190476190477,
      "grad_norm": 0.6089012622833252,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.2432,
      "step": 59
    },
    {
      "epoch": 0.22857142857142856,
      "grad_norm": 0.644237220287323,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.2391,
      "step": 60
    },
    {
      "epoch": 0.23238095238095238,
      "grad_norm": 0.5924395322799683,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.1539,
      "step": 61
    },
    {
      "epoch": 0.2361904761904762,
      "grad_norm": 0.66671222448349,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.2696,
      "step": 62
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.6097422242164612,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.1888,
      "step": 63
    },
    {
      "epoch": 0.24,
      "eval_loss": 2.220935106277466,
      "eval_runtime": 23.2877,
      "eval_samples_per_second": 37.96,
      "eval_steps_per_second": 1.202,
      "step": 63
    },
    {
      "epoch": 0.2438095238095238,
      "grad_norm": 0.684579074382782,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.2123,
      "step": 64
    },
    {
      "epoch": 0.24761904761904763,
      "grad_norm": 0.7317588925361633,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.1611,
      "step": 65
    },
    {
      "epoch": 0.25142857142857145,
      "grad_norm": 0.6265579462051392,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.1573,
      "step": 66
    },
    {
      "epoch": 0.25523809523809526,
      "grad_norm": 0.6284566521644592,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.1642,
      "step": 67
    },
    {
      "epoch": 0.259047619047619,
      "grad_norm": 0.6570642590522766,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.1743,
      "step": 68
    },
    {
      "epoch": 0.26285714285714284,
      "grad_norm": 0.6028674840927124,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.2979,
      "step": 69
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 2.3493614196777344,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.1998,
      "step": 70
    },
    {
      "epoch": 0.2704761904761905,
      "grad_norm": 0.5517127513885498,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.2335,
      "step": 71
    },
    {
      "epoch": 0.2742857142857143,
      "grad_norm": 0.5958511233329773,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.2773,
      "step": 72
    },
    {
      "epoch": 0.2742857142857143,
      "eval_loss": 2.2107913494110107,
      "eval_runtime": 23.2929,
      "eval_samples_per_second": 37.951,
      "eval_steps_per_second": 1.202,
      "step": 72
    },
    {
      "epoch": 0.2780952380952381,
      "grad_norm": 0.5674335956573486,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.1722,
      "step": 73
    },
    {
      "epoch": 0.2819047619047619,
      "grad_norm": 8.10051155090332,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.1072,
      "step": 74
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.5924919247627258,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.1822,
      "step": 75
    },
    {
      "epoch": 0.2895238095238095,
      "grad_norm": 0.6240224242210388,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.2588,
      "step": 76
    },
    {
      "epoch": 0.29333333333333333,
      "grad_norm": 0.5227974057197571,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.092,
      "step": 77
    },
    {
      "epoch": 0.29714285714285715,
      "grad_norm": 0.5892701148986816,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.0542,
      "step": 78
    },
    {
      "epoch": 0.30095238095238097,
      "grad_norm": 0.6080027222633362,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.1877,
      "step": 79
    },
    {
      "epoch": 0.3047619047619048,
      "grad_norm": 0.5509330034255981,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.1802,
      "step": 80
    },
    {
      "epoch": 0.30857142857142855,
      "grad_norm": 0.6087760925292969,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.1623,
      "step": 81
    },
    {
      "epoch": 0.30857142857142855,
      "eval_loss": 2.2086734771728516,
      "eval_runtime": 23.2822,
      "eval_samples_per_second": 37.969,
      "eval_steps_per_second": 1.203,
      "step": 81
    },
    {
      "epoch": 0.31238095238095237,
      "grad_norm": 0.6101416349411011,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.1315,
      "step": 82
    },
    {
      "epoch": 0.3161904761904762,
      "grad_norm": 0.7591520547866821,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.3257,
      "step": 83
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.5862055420875549,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.1308,
      "step": 84
    },
    {
      "epoch": 0.3238095238095238,
      "grad_norm": 0.9785626530647278,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.221,
      "step": 85
    },
    {
      "epoch": 0.32761904761904764,
      "grad_norm": 0.5859477519989014,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.2224,
      "step": 86
    },
    {
      "epoch": 0.3314285714285714,
      "grad_norm": 0.600614070892334,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.0754,
      "step": 87
    },
    {
      "epoch": 0.3352380952380952,
      "grad_norm": 0.581584632396698,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.2861,
      "step": 88
    },
    {
      "epoch": 0.33904761904761904,
      "grad_norm": 0.8023515343666077,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.1617,
      "step": 89
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.6560883522033691,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.2529,
      "step": 90
    },
    {
      "epoch": 0.34285714285714286,
      "eval_loss": 2.207376718521118,
      "eval_runtime": 23.2641,
      "eval_samples_per_second": 37.999,
      "eval_steps_per_second": 1.204,
      "step": 90
    },
    {
      "epoch": 0.3466666666666667,
      "grad_norm": 0.5743101835250854,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.1292,
      "step": 91
    },
    {
      "epoch": 0.3504761904761905,
      "grad_norm": 0.6466842293739319,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.1413,
      "step": 92
    },
    {
      "epoch": 0.35428571428571426,
      "grad_norm": 0.5407741069793701,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.1141,
      "step": 93
    },
    {
      "epoch": 0.3580952380952381,
      "grad_norm": 0.5799128413200378,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.2612,
      "step": 94
    },
    {
      "epoch": 0.3619047619047619,
      "grad_norm": 0.7486923933029175,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.1326,
      "step": 95
    },
    {
      "epoch": 0.3657142857142857,
      "grad_norm": 0.5356907248497009,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.172,
      "step": 96
    },
    {
      "epoch": 0.36952380952380953,
      "grad_norm": 0.6150782704353333,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.2271,
      "step": 97
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 0.601334810256958,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.1812,
      "step": 98
    },
    {
      "epoch": 0.37714285714285717,
      "grad_norm": 0.5893957018852234,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.1482,
      "step": 99
    },
    {
      "epoch": 0.37714285714285717,
      "eval_loss": 2.2071611881256104,
      "eval_runtime": 23.2788,
      "eval_samples_per_second": 37.974,
      "eval_steps_per_second": 1.203,
      "step": 99
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.588111400604248,
      "learning_rate": 0.0,
      "loss": 2.2722,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.935098268483584e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}