{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010094891984655765,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010094891984655764,
      "grad_norm": 0.944897472858429,
      "learning_rate": 1e-05,
      "loss": 2.4585,
      "step": 1
    },
    {
      "epoch": 0.00010094891984655764,
      "eval_loss": 2.663647413253784,
      "eval_runtime": 837.5363,
      "eval_samples_per_second": 9.96,
      "eval_steps_per_second": 1.245,
      "step": 1
    },
    {
      "epoch": 0.0002018978396931153,
      "grad_norm": 1.1168081760406494,
      "learning_rate": 2e-05,
      "loss": 2.614,
      "step": 2
    },
    {
      "epoch": 0.0003028467595396729,
      "grad_norm": 0.8895403742790222,
      "learning_rate": 3e-05,
      "loss": 2.5742,
      "step": 3
    },
    {
      "epoch": 0.0004037956793862306,
      "grad_norm": 1.1057639122009277,
      "learning_rate": 4e-05,
      "loss": 2.6082,
      "step": 4
    },
    {
      "epoch": 0.0005047445992327882,
      "grad_norm": 1.2985063791275024,
      "learning_rate": 5e-05,
      "loss": 2.6844,
      "step": 5
    },
    {
      "epoch": 0.0006056935190793458,
      "grad_norm": 1.2740225791931152,
      "learning_rate": 6e-05,
      "loss": 2.684,
      "step": 6
    },
    {
      "epoch": 0.0007066424389259035,
      "grad_norm": 1.1661525964736938,
      "learning_rate": 7e-05,
      "loss": 2.5458,
      "step": 7
    },
    {
      "epoch": 0.0008075913587724611,
      "grad_norm": 0.7164007425308228,
      "learning_rate": 8e-05,
      "loss": 2.447,
      "step": 8
    },
    {
      "epoch": 0.0009085402786190188,
      "grad_norm": 0.8726524710655212,
      "learning_rate": 9e-05,
      "loss": 2.4571,
      "step": 9
    },
    {
      "epoch": 0.0009085402786190188,
      "eval_loss": 2.368643283843994,
      "eval_runtime": 836.9961,
      "eval_samples_per_second": 9.967,
      "eval_steps_per_second": 1.246,
      "step": 9
    },
    {
      "epoch": 0.0010094891984655764,
      "grad_norm": 0.793461263179779,
      "learning_rate": 0.0001,
      "loss": 2.4332,
      "step": 10
    },
    {
      "epoch": 0.001110438118312134,
      "grad_norm": 0.6365218162536621,
      "learning_rate": 9.99695413509548e-05,
      "loss": 2.3091,
      "step": 11
    },
    {
      "epoch": 0.0012113870381586917,
      "grad_norm": 0.49457401037216187,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.2431,
      "step": 12
    },
    {
      "epoch": 0.0013123359580052493,
      "grad_norm": 0.7975025773048401,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.239,
      "step": 13
    },
    {
      "epoch": 0.001413284877851807,
      "grad_norm": 0.48324573040008545,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.227,
      "step": 14
    },
    {
      "epoch": 0.0015142337976983646,
      "grad_norm": 0.3696288764476776,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.2318,
      "step": 15
    },
    {
      "epoch": 0.0016151827175449223,
      "grad_norm": 0.3048635423183441,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.1899,
      "step": 16
    },
    {
      "epoch": 0.00171613163739148,
      "grad_norm": 0.3256937265396118,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.2085,
      "step": 17
    },
    {
      "epoch": 0.0018170805572380376,
      "grad_norm": 0.2600611448287964,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.1825,
      "step": 18
    },
    {
      "epoch": 0.0018170805572380376,
      "eval_loss": 2.201138734817505,
      "eval_runtime": 836.612,
      "eval_samples_per_second": 9.971,
      "eval_steps_per_second": 1.247,
      "step": 18
    },
    {
      "epoch": 0.0019180294770845953,
      "grad_norm": 0.3889247179031372,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.1976,
      "step": 19
    },
    {
      "epoch": 0.0020189783969311527,
      "grad_norm": 0.30169251561164856,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.2119,
      "step": 20
    },
    {
      "epoch": 0.0021199273167777106,
      "grad_norm": 0.24492594599723816,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.2028,
      "step": 21
    },
    {
      "epoch": 0.002220876236624268,
      "grad_norm": 0.2256334125995636,
      "learning_rate": 9.567727288213005e-05,
      "loss": 2.158,
      "step": 22
    },
    {
      "epoch": 0.002321825156470826,
      "grad_norm": 0.299275279045105,
      "learning_rate": 9.493970231495835e-05,
      "loss": 2.1862,
      "step": 23
    },
    {
      "epoch": 0.0024227740763173833,
      "grad_norm": 0.2614262104034424,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.1995,
      "step": 24
    },
    {
      "epoch": 0.002523722996163941,
      "grad_norm": 0.36414486169815063,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.1961,
      "step": 25
    },
    {
      "epoch": 0.0026246719160104987,
      "grad_norm": 0.279491662979126,
      "learning_rate": 9.24024048078213e-05,
      "loss": 2.1918,
      "step": 26
    },
    {
      "epoch": 0.0027256208358570565,
      "grad_norm": 0.4121980369091034,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.1888,
      "step": 27
    },
    {
      "epoch": 0.0027256208358570565,
      "eval_loss": 2.1801180839538574,
      "eval_runtime": 837.0562,
      "eval_samples_per_second": 9.966,
      "eval_steps_per_second": 1.246,
      "step": 27
    },
    {
      "epoch": 0.002826569755703614,
      "grad_norm": 0.2528911828994751,
      "learning_rate": 9.045084971874738e-05,
      "loss": 2.1625,
      "step": 28
    },
    {
      "epoch": 0.0029275186755501714,
      "grad_norm": 0.30560562014579773,
      "learning_rate": 8.940053768033609e-05,
      "loss": 2.1744,
      "step": 29
    },
    {
      "epoch": 0.0030284675953967293,
      "grad_norm": 0.5374148488044739,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.212,
      "step": 30
    },
    {
      "epoch": 0.0031294165152432867,
      "grad_norm": 0.2979753911495209,
      "learning_rate": 8.715724127386972e-05,
      "loss": 2.161,
      "step": 31
    },
    {
      "epoch": 0.0032303654350898446,
      "grad_norm": 0.23406262695789337,
      "learning_rate": 8.596699001693255e-05,
      "loss": 2.149,
      "step": 32
    },
    {
      "epoch": 0.003331314354936402,
      "grad_norm": 0.28936153650283813,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.1734,
      "step": 33
    },
    {
      "epoch": 0.00343226327478296,
      "grad_norm": 0.3578174412250519,
      "learning_rate": 8.345653031794292e-05,
      "loss": 2.193,
      "step": 34
    },
    {
      "epoch": 0.0035332121946295173,
      "grad_norm": 0.33021020889282227,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.1804,
      "step": 35
    },
    {
      "epoch": 0.0036341611144760752,
      "grad_norm": 0.2678793966770172,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.2016,
      "step": 36
    },
    {
      "epoch": 0.0036341611144760752,
      "eval_loss": 2.1783008575439453,
      "eval_runtime": 836.5111,
      "eval_samples_per_second": 9.972,
      "eval_steps_per_second": 1.247,
      "step": 36
    },
    {
      "epoch": 0.0037351100343226327,
      "grad_norm": 0.285946249961853,
      "learning_rate": 7.938926261462366e-05,
      "loss": 2.1862,
      "step": 37
    },
    {
      "epoch": 0.0038360589541691905,
      "grad_norm": 0.32445332407951355,
      "learning_rate": 7.795964517353735e-05,
      "loss": 2.1826,
      "step": 38
    },
    {
      "epoch": 0.003937007874015748,
      "grad_norm": 0.33953049778938293,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.1831,
      "step": 39
    },
    {
      "epoch": 0.004037956793862305,
      "grad_norm": 0.22985900938510895,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.1897,
      "step": 40
    },
    {
      "epoch": 0.004138905713708864,
      "grad_norm": 0.22906559705734253,
      "learning_rate": 7.347357813929454e-05,
      "loss": 2.1724,
      "step": 41
    },
    {
      "epoch": 0.004239854633555421,
      "grad_norm": 0.23222745954990387,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.1808,
      "step": 42
    },
    {
      "epoch": 0.004340803553401979,
      "grad_norm": 0.2707752585411072,
      "learning_rate": 7.033683215379002e-05,
      "loss": 2.1431,
      "step": 43
    },
    {
      "epoch": 0.004441752473248536,
      "grad_norm": 0.4225059449672699,
      "learning_rate": 6.873032967079561e-05,
      "loss": 2.1715,
      "step": 44
    },
    {
      "epoch": 0.0045427013930950935,
      "grad_norm": 0.2372809201478958,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.159,
      "step": 45
    },
    {
      "epoch": 0.0045427013930950935,
      "eval_loss": 2.1703410148620605,
      "eval_runtime": 836.4728,
      "eval_samples_per_second": 9.973,
      "eval_steps_per_second": 1.247,
      "step": 45
    },
    {
      "epoch": 0.004643650312941652,
      "grad_norm": 0.2771320641040802,
      "learning_rate": 6.545084971874738e-05,
      "loss": 2.1876,
      "step": 46
    },
    {
      "epoch": 0.004744599232788209,
      "grad_norm": 0.25997450947761536,
      "learning_rate": 6.378186779084995e-05,
      "loss": 2.1687,
      "step": 47
    },
    {
      "epoch": 0.004845548152634767,
      "grad_norm": 0.23976390063762665,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.1836,
      "step": 48
    },
    {
      "epoch": 0.004946497072481324,
      "grad_norm": 0.23776023089885712,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 2.168,
      "step": 49
    },
    {
      "epoch": 0.005047445992327882,
      "grad_norm": 0.2904040813446045,
      "learning_rate": 5.868240888334653e-05,
      "loss": 2.1617,
      "step": 50
    },
    {
      "epoch": 0.00514839491217444,
      "grad_norm": 0.34431248903274536,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.1716,
      "step": 51
    },
    {
      "epoch": 0.005249343832020997,
      "grad_norm": 0.2910543382167816,
      "learning_rate": 5.522642316338268e-05,
      "loss": 2.1826,
      "step": 52
    },
    {
      "epoch": 0.005350292751867555,
      "grad_norm": 0.21696153283119202,
      "learning_rate": 5.348782368720626e-05,
      "loss": 2.164,
      "step": 53
    },
    {
      "epoch": 0.005451241671714113,
      "grad_norm": 0.2520364224910736,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.178,
      "step": 54
    },
    {
      "epoch": 0.005451241671714113,
      "eval_loss": 2.168518543243408,
      "eval_runtime": 836.9008,
      "eval_samples_per_second": 9.968,
      "eval_steps_per_second": 1.246,
      "step": 54
    },
    {
      "epoch": 0.0055521905915606705,
      "grad_norm": 0.23974812030792236,
      "learning_rate": 5e-05,
      "loss": 2.168,
      "step": 55
    },
    {
      "epoch": 0.005653139511407228,
      "grad_norm": 0.2293047308921814,
      "learning_rate": 4.825502516487497e-05,
      "loss": 2.1621,
      "step": 56
    },
    {
      "epoch": 0.005754088431253785,
      "grad_norm": 0.19091089069843292,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.1491,
      "step": 57
    },
    {
      "epoch": 0.005855037351100343,
      "grad_norm": 0.23644797503948212,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.1517,
      "step": 58
    },
    {
      "epoch": 0.005955986270946901,
      "grad_norm": 0.20270752906799316,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 2.1575,
      "step": 59
    },
    {
      "epoch": 0.0060569351907934586,
      "grad_norm": 0.3651578724384308,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.1877,
      "step": 60
    },
    {
      "epoch": 0.006157884110640016,
      "grad_norm": 0.2750738859176636,
      "learning_rate": 3.960441545911204e-05,
      "loss": 2.1686,
      "step": 61
    },
    {
      "epoch": 0.0062588330304865734,
      "grad_norm": 0.23219722509384155,
      "learning_rate": 3.790390522001662e-05,
      "loss": 2.1544,
      "step": 62
    },
    {
      "epoch": 0.006359781950333132,
      "grad_norm": 0.26596349477767944,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.1497,
      "step": 63
    },
    {
      "epoch": 0.006359781950333132,
      "eval_loss": 2.166980743408203,
      "eval_runtime": 837.3556,
      "eval_samples_per_second": 9.962,
      "eval_steps_per_second": 1.246,
      "step": 63
    },
    {
      "epoch": 0.006460730870179689,
      "grad_norm": 0.23465655744075775,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.1973,
      "step": 64
    },
    {
      "epoch": 0.006561679790026247,
      "grad_norm": 0.226127028465271,
      "learning_rate": 3.289899283371657e-05,
      "loss": 2.1708,
      "step": 65
    },
    {
      "epoch": 0.006662628709872804,
      "grad_norm": 0.23844251036643982,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.177,
      "step": 66
    },
    {
      "epoch": 0.006763577629719362,
      "grad_norm": 0.31955665349960327,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 2.1675,
      "step": 67
    },
    {
      "epoch": 0.00686452654956592,
      "grad_norm": 0.2359679788351059,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 2.1804,
      "step": 68
    },
    {
      "epoch": 0.006965475469412477,
      "grad_norm": 0.2088335007429123,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.1771,
      "step": 69
    },
    {
      "epoch": 0.007066424389259035,
      "grad_norm": 0.21319451928138733,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.1654,
      "step": 70
    },
    {
      "epoch": 0.007167373309105592,
      "grad_norm": 0.22512580454349518,
      "learning_rate": 2.350403678833976e-05,
      "loss": 2.1664,
      "step": 71
    },
    {
      "epoch": 0.0072683222289521504,
      "grad_norm": 0.23601970076560974,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.1307,
      "step": 72
    },
    {
      "epoch": 0.0072683222289521504,
      "eval_loss": 2.1660921573638916,
      "eval_runtime": 836.8568,
      "eval_samples_per_second": 9.968,
      "eval_steps_per_second": 1.246,
      "step": 72
    },
    {
      "epoch": 0.007369271148798708,
      "grad_norm": 0.27343568205833435,
      "learning_rate": 2.061073738537635e-05,
      "loss": 2.1712,
      "step": 73
    },
    {
      "epoch": 0.007470220068645265,
      "grad_norm": 0.2502886950969696,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 2.1687,
      "step": 74
    },
    {
      "epoch": 0.007571168988491823,
      "grad_norm": 0.25393420457839966,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.1572,
      "step": 75
    },
    {
      "epoch": 0.007672117908338381,
      "grad_norm": 0.23516961932182312,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 2.1657,
      "step": 76
    },
    {
      "epoch": 0.0077730668281849385,
      "grad_norm": 0.22615772485733032,
      "learning_rate": 1.526708147705013e-05,
      "loss": 2.1423,
      "step": 77
    },
    {
      "epoch": 0.007874015748031496,
      "grad_norm": 0.25158652663230896,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.1857,
      "step": 78
    },
    {
      "epoch": 0.007974964667878054,
      "grad_norm": 0.24187257885932922,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 2.155,
      "step": 79
    },
    {
      "epoch": 0.00807591358772461,
      "grad_norm": 0.2316223829984665,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 2.176,
      "step": 80
    },
    {
      "epoch": 0.00817686250757117,
      "grad_norm": 0.2663958668708801,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.175,
      "step": 81
    },
    {
      "epoch": 0.00817686250757117,
      "eval_loss": 2.1655943393707275,
      "eval_runtime": 836.7406,
      "eval_samples_per_second": 9.97,
      "eval_steps_per_second": 1.247,
      "step": 81
    },
    {
      "epoch": 0.008277811427417727,
      "grad_norm": 0.287240207195282,
      "learning_rate": 9.549150281252633e-06,
      "loss": 2.1805,
      "step": 82
    },
    {
      "epoch": 0.008378760347264284,
      "grad_norm": 0.2595893144607544,
      "learning_rate": 8.548121372247918e-06,
      "loss": 2.1463,
      "step": 83
    },
    {
      "epoch": 0.008479709267110842,
      "grad_norm": 0.23999683558940887,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.1788,
      "step": 84
    },
    {
      "epoch": 0.008580658186957399,
      "grad_norm": 0.27363473176956177,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.145,
      "step": 85
    },
    {
      "epoch": 0.008681607106803957,
      "grad_norm": 0.2818804979324341,
      "learning_rate": 5.852620357053651e-06,
      "loss": 2.1733,
      "step": 86
    },
    {
      "epoch": 0.008782556026650516,
      "grad_norm": 0.2009168416261673,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.1748,
      "step": 87
    },
    {
      "epoch": 0.008883504946497072,
      "grad_norm": 0.26735901832580566,
      "learning_rate": 4.322727117869951e-06,
      "loss": 2.176,
      "step": 88
    },
    {
      "epoch": 0.00898445386634363,
      "grad_norm": 0.2693656384944916,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 2.1828,
      "step": 89
    },
    {
      "epoch": 0.009085402786190187,
      "grad_norm": 0.20952469110488892,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.1511,
      "step": 90
    },
    {
      "epoch": 0.009085402786190187,
      "eval_loss": 2.1652722358703613,
      "eval_runtime": 836.531,
      "eval_samples_per_second": 9.972,
      "eval_steps_per_second": 1.247,
      "step": 90
    },
    {
      "epoch": 0.009186351706036745,
      "grad_norm": 0.21097005903720856,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.1736,
      "step": 91
    },
    {
      "epoch": 0.009287300625883304,
      "grad_norm": 0.25543177127838135,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 2.1668,
      "step": 92
    },
    {
      "epoch": 0.00938824954572986,
      "grad_norm": 0.25192975997924805,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.1451,
      "step": 93
    },
    {
      "epoch": 0.009489198465576418,
      "grad_norm": 0.2307412028312683,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.1588,
      "step": 94
    },
    {
      "epoch": 0.009590147385422977,
      "grad_norm": 0.2313176393508911,
      "learning_rate": 7.596123493895991e-07,
      "loss": 2.16,
      "step": 95
    },
    {
      "epoch": 0.009691096305269533,
      "grad_norm": 0.23625782132148743,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.1843,
      "step": 96
    },
    {
      "epoch": 0.009792045225116092,
      "grad_norm": 0.2403765767812729,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 2.1836,
      "step": 97
    },
    {
      "epoch": 0.009892994144962648,
      "grad_norm": 0.2410961240530014,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 2.1562,
      "step": 98
    },
    {
      "epoch": 0.009993943064809207,
      "grad_norm": 0.2312341183423996,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.1613,
      "step": 99
    },
    {
      "epoch": 0.009993943064809207,
      "eval_loss": 2.1652092933654785,
      "eval_runtime": 836.931,
      "eval_samples_per_second": 9.967,
      "eval_steps_per_second": 1.246,
      "step": 99
    },
    {
      "epoch": 0.010094891984655765,
      "grad_norm": 0.20589391887187958,
      "learning_rate": 0.0,
      "loss": 2.1687,
      "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": 1.4244483234476851e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}