{
  "best_metric": 0.8114216923713684,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.0067727161131382226,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.3863580565691114e-05,
      "grad_norm": 2.0441832542419434,
      "learning_rate": 1e-05,
      "loss": 1.0181,
      "step": 1
    },
    {
      "epoch": 3.3863580565691114e-05,
      "eval_loss": 1.1343133449554443,
      "eval_runtime": 4284.1245,
      "eval_samples_per_second": 11.609,
      "eval_steps_per_second": 2.902,
      "step": 1
    },
    {
      "epoch": 6.772716113138223e-05,
      "grad_norm": 3.6331210136413574,
      "learning_rate": 2e-05,
      "loss": 1.1313,
      "step": 2
    },
    {
      "epoch": 0.00010159074169707334,
      "grad_norm": 1.9606194496154785,
      "learning_rate": 3e-05,
      "loss": 1.2072,
      "step": 3
    },
    {
      "epoch": 0.00013545432226276446,
      "grad_norm": 1.545116662979126,
      "learning_rate": 4e-05,
      "loss": 1.189,
      "step": 4
    },
    {
      "epoch": 0.00016931790282845557,
      "grad_norm": 1.599936842918396,
      "learning_rate": 5e-05,
      "loss": 1.2607,
      "step": 5
    },
    {
      "epoch": 0.00020318148339414668,
      "grad_norm": 1.529877781867981,
      "learning_rate": 6e-05,
      "loss": 1.2322,
      "step": 6
    },
    {
      "epoch": 0.0002370450639598378,
      "grad_norm": 1.2671633958816528,
      "learning_rate": 7e-05,
      "loss": 0.9866,
      "step": 7
    },
    {
      "epoch": 0.0002709086445255289,
      "grad_norm": 1.5841752290725708,
      "learning_rate": 8e-05,
      "loss": 0.9674,
      "step": 8
    },
    {
      "epoch": 0.00030477222509122,
      "grad_norm": 1.4465010166168213,
      "learning_rate": 9e-05,
      "loss": 0.9905,
      "step": 9
    },
    {
      "epoch": 0.00033863580565691114,
      "grad_norm": 1.454184889793396,
      "learning_rate": 0.0001,
      "loss": 1.0279,
      "step": 10
    },
    {
      "epoch": 0.0003724993862226022,
      "grad_norm": 1.490474820137024,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.0434,
      "step": 11
    },
    {
      "epoch": 0.00040636296678829337,
      "grad_norm": 1.3123879432678223,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.9873,
      "step": 12
    },
    {
      "epoch": 0.00044022654735398445,
      "grad_norm": 1.3003586530685425,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9404,
      "step": 13
    },
    {
      "epoch": 0.0004740901279196756,
      "grad_norm": 1.2886568307876587,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.9071,
      "step": 14
    },
    {
      "epoch": 0.0005079537084853667,
      "grad_norm": 1.1523945331573486,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.9002,
      "step": 15
    },
    {
      "epoch": 0.0005418172890510578,
      "grad_norm": 1.161170482635498,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.8016,
      "step": 16
    },
    {
      "epoch": 0.0005756808696167489,
      "grad_norm": 1.1345629692077637,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.893,
      "step": 17
    },
    {
      "epoch": 0.00060954445018244,
      "grad_norm": 1.166721224784851,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.8097,
      "step": 18
    },
    {
      "epoch": 0.0006434080307481312,
      "grad_norm": 1.2668547630310059,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8576,
      "step": 19
    },
    {
      "epoch": 0.0006772716113138223,
      "grad_norm": 1.161539912223816,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.9148,
      "step": 20
    },
    {
      "epoch": 0.0007111351918795134,
      "grad_norm": 1.2676417827606201,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.919,
      "step": 21
    },
    {
      "epoch": 0.0007449987724452045,
      "grad_norm": 1.009020447731018,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8214,
      "step": 22
    },
    {
      "epoch": 0.0007788623530108956,
      "grad_norm": 1.0390195846557617,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.6965,
      "step": 23
    },
    {
      "epoch": 0.0008127259335765867,
      "grad_norm": 1.2287013530731201,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.818,
      "step": 24
    },
    {
      "epoch": 0.0008465895141422778,
      "grad_norm": 1.1437411308288574,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.6158,
      "step": 25
    },
    {
      "epoch": 0.0008804530947079689,
      "grad_norm": 1.088263988494873,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.6778,
      "step": 26
    },
    {
      "epoch": 0.0009143166752736601,
      "grad_norm": 1.1476519107818604,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7442,
      "step": 27
    },
    {
      "epoch": 0.0009481802558393512,
      "grad_norm": 1.0394822359085083,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6852,
      "step": 28
    },
    {
      "epoch": 0.0009820438364050424,
      "grad_norm": 1.2543938159942627,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8076,
      "step": 29
    },
    {
      "epoch": 0.0010159074169707335,
      "grad_norm": 1.225186824798584,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.7627,
      "step": 30
    },
    {
      "epoch": 0.0010497709975364246,
      "grad_norm": 1.2618635892868042,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6439,
      "step": 31
    },
    {
      "epoch": 0.0010836345781021156,
      "grad_norm": 1.4580321311950684,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.7065,
      "step": 32
    },
    {
      "epoch": 0.0011174981586678067,
      "grad_norm": 1.4413307905197144,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.7158,
      "step": 33
    },
    {
      "epoch": 0.0011513617392334978,
      "grad_norm": 1.4636950492858887,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6476,
      "step": 34
    },
    {
      "epoch": 0.001185225319799189,
      "grad_norm": 1.8687407970428467,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7728,
      "step": 35
    },
    {
      "epoch": 0.00121908890036488,
      "grad_norm": 1.716018557548523,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.762,
      "step": 36
    },
    {
      "epoch": 0.0012529524809305713,
      "grad_norm": 1.642137885093689,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.9424,
      "step": 37
    },
    {
      "epoch": 0.0012868160614962624,
      "grad_norm": 1.6538066864013672,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8565,
      "step": 38
    },
    {
      "epoch": 0.0013206796420619535,
      "grad_norm": 1.763176679611206,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8803,
      "step": 39
    },
    {
      "epoch": 0.0013545432226276446,
      "grad_norm": 1.8091034889221191,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7763,
      "step": 40
    },
    {
      "epoch": 0.0013884068031933356,
      "grad_norm": 2.060272216796875,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.9599,
      "step": 41
    },
    {
      "epoch": 0.0014222703837590267,
      "grad_norm": 2.222691059112549,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8838,
      "step": 42
    },
    {
      "epoch": 0.0014561339643247178,
      "grad_norm": 2.226693868637085,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7283,
      "step": 43
    },
    {
      "epoch": 0.001489997544890409,
      "grad_norm": 2.7375259399414062,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7829,
      "step": 44
    },
    {
      "epoch": 0.0015238611254561002,
      "grad_norm": 2.421783924102783,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.8352,
      "step": 45
    },
    {
      "epoch": 0.0015577247060217913,
      "grad_norm": 2.5380146503448486,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.7635,
      "step": 46
    },
    {
      "epoch": 0.0015915882865874824,
      "grad_norm": 2.992722988128662,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8715,
      "step": 47
    },
    {
      "epoch": 0.0016254518671531735,
      "grad_norm": 2.938319683074951,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.723,
      "step": 48
    },
    {
      "epoch": 0.0016593154477188646,
      "grad_norm": 3.285334825515747,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.5857,
      "step": 49
    },
    {
      "epoch": 0.0016931790282845556,
      "grad_norm": 6.651454925537109,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7282,
      "step": 50
    },
    {
      "epoch": 0.0016931790282845556,
      "eval_loss": 0.9169284701347351,
      "eval_runtime": 4379.7698,
      "eval_samples_per_second": 11.356,
      "eval_steps_per_second": 2.839,
      "step": 50
    },
    {
      "epoch": 0.0017270426088502467,
      "grad_norm": 1.4602924585342407,
      "learning_rate": 8.894386393810563e-05,
      "loss": 1.1179,
      "step": 51
    },
    {
      "epoch": 0.0017609061894159378,
      "grad_norm": 1.7842880487442017,
      "learning_rate": 8.842005554284296e-05,
      "loss": 1.0612,
      "step": 52
    },
    {
      "epoch": 0.0017947697699816291,
      "grad_norm": 0.9636514782905579,
      "learning_rate": 8.788574348801675e-05,
      "loss": 1.0375,
      "step": 53
    },
    {
      "epoch": 0.0018286333505473202,
      "grad_norm": 0.778742790222168,
      "learning_rate": 8.73410738492077e-05,
      "loss": 1.1209,
      "step": 54
    },
    {
      "epoch": 0.0018624969311130113,
      "grad_norm": 0.7997629642486572,
      "learning_rate": 8.678619553365659e-05,
      "loss": 1.1201,
      "step": 55
    },
    {
      "epoch": 0.0018963605116787024,
      "grad_norm": 0.8073371052742004,
      "learning_rate": 8.622126023955446e-05,
      "loss": 1.055,
      "step": 56
    },
    {
      "epoch": 0.0019302240922443935,
      "grad_norm": 0.7069865465164185,
      "learning_rate": 8.564642241456986e-05,
      "loss": 1.1197,
      "step": 57
    },
    {
      "epoch": 0.0019640876728100848,
      "grad_norm": 0.8875919580459595,
      "learning_rate": 8.506183921362443e-05,
      "loss": 1.051,
      "step": 58
    },
    {
      "epoch": 0.0019979512533757756,
      "grad_norm": 0.8637341856956482,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.9375,
      "step": 59
    },
    {
      "epoch": 0.002031814833941467,
      "grad_norm": 0.9806546568870544,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8921,
      "step": 60
    },
    {
      "epoch": 0.002065678414507158,
      "grad_norm": 1.0685687065124512,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.9015,
      "step": 61
    },
    {
      "epoch": 0.002099541995072849,
      "grad_norm": 1.091840147972107,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.8015,
      "step": 62
    },
    {
      "epoch": 0.00213340557563854,
      "grad_norm": 1.2013441324234009,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.9462,
      "step": 63
    },
    {
      "epoch": 0.0021672691562042313,
      "grad_norm": 1.0091452598571777,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.989,
      "step": 64
    },
    {
      "epoch": 0.002201132736769922,
      "grad_norm": 0.8565776944160461,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.7666,
      "step": 65
    },
    {
      "epoch": 0.0022349963173356135,
      "grad_norm": 0.8313263058662415,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.772,
      "step": 66
    },
    {
      "epoch": 0.0022688598979013048,
      "grad_norm": 0.8839550614356995,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.8793,
      "step": 67
    },
    {
      "epoch": 0.0023027234784669956,
      "grad_norm": 0.9040988087654114,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.8448,
      "step": 68
    },
    {
      "epoch": 0.002336587059032687,
      "grad_norm": 0.9890454411506653,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.8529,
      "step": 69
    },
    {
      "epoch": 0.002370450639598378,
      "grad_norm": 0.9348019361495972,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.8252,
      "step": 70
    },
    {
      "epoch": 0.002404314220164069,
      "grad_norm": 0.877582311630249,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.818,
      "step": 71
    },
    {
      "epoch": 0.00243817780072976,
      "grad_norm": 0.9090872406959534,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.738,
      "step": 72
    },
    {
      "epoch": 0.0024720413812954513,
      "grad_norm": 0.9891653656959534,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7846,
      "step": 73
    },
    {
      "epoch": 0.0025059049618611426,
      "grad_norm": 0.8998435735702515,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.7636,
      "step": 74
    },
    {
      "epoch": 0.0025397685424268335,
      "grad_norm": 0.9262997508049011,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.801,
      "step": 75
    },
    {
      "epoch": 0.0025736321229925248,
      "grad_norm": 0.9769306778907776,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.8211,
      "step": 76
    },
    {
      "epoch": 0.0026074957035582156,
      "grad_norm": 0.8825656771659851,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.6619,
      "step": 77
    },
    {
      "epoch": 0.002641359284123907,
      "grad_norm": 0.8876908421516418,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.686,
      "step": 78
    },
    {
      "epoch": 0.002675222864689598,
      "grad_norm": 1.0735276937484741,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7434,
      "step": 79
    },
    {
      "epoch": 0.002709086445255289,
      "grad_norm": 1.1962286233901978,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.7853,
      "step": 80
    },
    {
      "epoch": 0.00274295002582098,
      "grad_norm": 1.2984271049499512,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.8267,
      "step": 81
    },
    {
      "epoch": 0.0027768136063866713,
      "grad_norm": 1.2141095399856567,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7199,
      "step": 82
    },
    {
      "epoch": 0.0028106771869523626,
      "grad_norm": 1.3065780401229858,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.7869,
      "step": 83
    },
    {
      "epoch": 0.0028445407675180535,
      "grad_norm": 1.307120680809021,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.8337,
      "step": 84
    },
    {
      "epoch": 0.0028784043480837448,
      "grad_norm": 1.4318408966064453,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7498,
      "step": 85
    },
    {
      "epoch": 0.0029122679286494356,
      "grad_norm": 1.4361746311187744,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.775,
      "step": 86
    },
    {
      "epoch": 0.002946131509215127,
      "grad_norm": 1.5540616512298584,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.7581,
      "step": 87
    },
    {
      "epoch": 0.002979995089780818,
      "grad_norm": 2.339376926422119,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7285,
      "step": 88
    },
    {
      "epoch": 0.003013858670346509,
      "grad_norm": 1.6438493728637695,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.8313,
      "step": 89
    },
    {
      "epoch": 0.0030477222509122004,
      "grad_norm": 1.7021400928497314,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7428,
      "step": 90
    },
    {
      "epoch": 0.0030815858314778913,
      "grad_norm": 1.669267177581787,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6981,
      "step": 91
    },
    {
      "epoch": 0.0031154494120435826,
      "grad_norm": 1.642217993736267,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7507,
      "step": 92
    },
    {
      "epoch": 0.0031493129926092735,
      "grad_norm": 1.6944239139556885,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7556,
      "step": 93
    },
    {
      "epoch": 0.0031831765731749648,
      "grad_norm": 2.803438901901245,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.7637,
      "step": 94
    },
    {
      "epoch": 0.0032170401537406556,
      "grad_norm": 2.991342067718506,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7315,
      "step": 95
    },
    {
      "epoch": 0.003250903734306347,
      "grad_norm": 2.2428009510040283,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7676,
      "step": 96
    },
    {
      "epoch": 0.003284767314872038,
      "grad_norm": 2.6103129386901855,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7777,
      "step": 97
    },
    {
      "epoch": 0.003318630895437729,
      "grad_norm": 2.7896811962127686,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.8251,
      "step": 98
    },
    {
      "epoch": 0.0033524944760034204,
      "grad_norm": 3.8848860263824463,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.7392,
      "step": 99
    },
    {
      "epoch": 0.0033863580565691113,
      "grad_norm": 4.235522270202637,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.8175,
      "step": 100
    },
    {
      "epoch": 0.0033863580565691113,
      "eval_loss": 0.8521695733070374,
      "eval_runtime": 4374.0654,
      "eval_samples_per_second": 11.37,
      "eval_steps_per_second": 2.843,
      "step": 100
    },
    {
      "epoch": 0.0034202216371348026,
      "grad_norm": 1.1458899974822998,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.8591,
      "step": 101
    },
    {
      "epoch": 0.0034540852177004935,
      "grad_norm": 1.172037959098816,
      "learning_rate": 5.247918773366112e-05,
      "loss": 1.327,
      "step": 102
    },
    {
      "epoch": 0.0034879487982661848,
      "grad_norm": 0.9343804717063904,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.9444,
      "step": 103
    },
    {
      "epoch": 0.0035218123788318756,
      "grad_norm": 0.7813839316368103,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 1.0259,
      "step": 104
    },
    {
      "epoch": 0.003555675959397567,
      "grad_norm": 0.7565736770629883,
      "learning_rate": 5e-05,
      "loss": 1.041,
      "step": 105
    },
    {
      "epoch": 0.0035895395399632582,
      "grad_norm": 0.8008309006690979,
      "learning_rate": 4.917330276168208e-05,
      "loss": 1.0422,
      "step": 106
    },
    {
      "epoch": 0.003623403120528949,
      "grad_norm": 0.7426912784576416,
      "learning_rate": 4.834683153413459e-05,
      "loss": 1.0826,
      "step": 107
    },
    {
      "epoch": 0.0036572667010946404,
      "grad_norm": 0.936414361000061,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.9141,
      "step": 108
    },
    {
      "epoch": 0.0036911302816603313,
      "grad_norm": 0.8418607115745544,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.9935,
      "step": 109
    },
    {
      "epoch": 0.0037249938622260226,
      "grad_norm": 0.920128345489502,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.8894,
      "step": 110
    },
    {
      "epoch": 0.0037588574427917134,
      "grad_norm": 1.1256664991378784,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.9296,
      "step": 111
    },
    {
      "epoch": 0.0037927210233574048,
      "grad_norm": 0.9914236664772034,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.8955,
      "step": 112
    },
    {
      "epoch": 0.0038265846039230956,
      "grad_norm": 0.86021488904953,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 1.1076,
      "step": 113
    },
    {
      "epoch": 0.003860448184488787,
      "grad_norm": 0.8354436159133911,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.9834,
      "step": 114
    },
    {
      "epoch": 0.0038943117650544782,
      "grad_norm": 0.8657628893852234,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.8908,
      "step": 115
    },
    {
      "epoch": 0.0039281753456201695,
      "grad_norm": 0.855169415473938,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.8587,
      "step": 116
    },
    {
      "epoch": 0.00396203892618586,
      "grad_norm": 0.9482845067977905,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.9064,
      "step": 117
    },
    {
      "epoch": 0.003995902506751551,
      "grad_norm": 0.8780611753463745,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.77,
      "step": 118
    },
    {
      "epoch": 0.004029766087317243,
      "grad_norm": 0.843481719493866,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.7907,
      "step": 119
    },
    {
      "epoch": 0.004063629667882934,
      "grad_norm": 0.817581832408905,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.7699,
      "step": 120
    },
    {
      "epoch": 0.004097493248448624,
      "grad_norm": 0.9872439503669739,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.7838,
      "step": 121
    },
    {
      "epoch": 0.004131356829014316,
      "grad_norm": 0.8429522514343262,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.7741,
      "step": 122
    },
    {
      "epoch": 0.004165220409580007,
      "grad_norm": 0.8456198573112488,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.8308,
      "step": 123
    },
    {
      "epoch": 0.004199083990145698,
      "grad_norm": 0.836810290813446,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.7197,
      "step": 124
    },
    {
      "epoch": 0.0042329475707113895,
      "grad_norm": 0.8510724306106567,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.7817,
      "step": 125
    },
    {
      "epoch": 0.00426681115127708,
      "grad_norm": 0.9283472299575806,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.7639,
      "step": 126
    },
    {
      "epoch": 0.004300674731842771,
      "grad_norm": 0.9334129095077515,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.7159,
      "step": 127
    },
    {
      "epoch": 0.004334538312408463,
      "grad_norm": 0.8882057666778564,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.7146,
      "step": 128
    },
    {
      "epoch": 0.004368401892974154,
      "grad_norm": 1.0052096843719482,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.7436,
      "step": 129
    },
    {
      "epoch": 0.004402265473539844,
      "grad_norm": 1.036095380783081,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.7443,
      "step": 130
    },
    {
      "epoch": 0.004436129054105536,
      "grad_norm": 1.1256189346313477,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.7056,
      "step": 131
    },
    {
      "epoch": 0.004469992634671227,
      "grad_norm": 1.1841328144073486,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.7057,
      "step": 132
    },
    {
      "epoch": 0.004503856215236918,
      "grad_norm": 1.177301287651062,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.7923,
      "step": 133
    },
    {
      "epoch": 0.0045377197958026095,
      "grad_norm": 1.3304249048233032,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.7732,
      "step": 134
    },
    {
      "epoch": 0.0045715833763683,
      "grad_norm": 1.3118896484375,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.7544,
      "step": 135
    },
    {
      "epoch": 0.004605446956933991,
      "grad_norm": 1.5514614582061768,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.8029,
      "step": 136
    },
    {
      "epoch": 0.004639310537499683,
      "grad_norm": 1.2711803913116455,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.753,
      "step": 137
    },
    {
      "epoch": 0.004673174118065374,
      "grad_norm": 1.4091942310333252,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.8104,
      "step": 138
    },
    {
      "epoch": 0.004707037698631065,
      "grad_norm": 1.648789405822754,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.763,
      "step": 139
    },
    {
      "epoch": 0.004740901279196756,
      "grad_norm": 1.9252206087112427,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.7113,
      "step": 140
    },
    {
      "epoch": 0.004774764859762447,
      "grad_norm": 1.8625355958938599,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.7801,
      "step": 141
    },
    {
      "epoch": 0.004808628440328138,
      "grad_norm": 1.736893653869629,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7988,
      "step": 142
    },
    {
      "epoch": 0.0048424920208938295,
      "grad_norm": 1.6877861022949219,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.7038,
      "step": 143
    },
    {
      "epoch": 0.00487635560145952,
      "grad_norm": 2.2004785537719727,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.8114,
      "step": 144
    },
    {
      "epoch": 0.004910219182025211,
      "grad_norm": 2.4584996700286865,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7978,
      "step": 145
    },
    {
      "epoch": 0.004944082762590903,
      "grad_norm": 2.3921878337860107,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.8769,
      "step": 146
    },
    {
      "epoch": 0.004977946343156594,
      "grad_norm": 2.814528465270996,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.6822,
      "step": 147
    },
    {
      "epoch": 0.005011809923722285,
      "grad_norm": 2.679048538208008,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.7034,
      "step": 148
    },
    {
      "epoch": 0.005045673504287976,
      "grad_norm": 4.924661636352539,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.4983,
      "step": 149
    },
    {
      "epoch": 0.005079537084853667,
      "grad_norm": 3.6667542457580566,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.5527,
      "step": 150
    },
    {
      "epoch": 0.005079537084853667,
      "eval_loss": 0.8154168128967285,
      "eval_runtime": 4334.8234,
      "eval_samples_per_second": 11.473,
      "eval_steps_per_second": 2.868,
      "step": 150
    },
    {
      "epoch": 0.005113400665419358,
      "grad_norm": 1.0565838813781738,
      "learning_rate": 1.553232954407171e-05,
      "loss": 1.0765,
      "step": 151
    },
    {
      "epoch": 0.0051472642459850495,
      "grad_norm": 1.207249641418457,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 1.1139,
      "step": 152
    },
    {
      "epoch": 0.00518112782655074,
      "grad_norm": 1.2924115657806396,
      "learning_rate": 1.435357758543015e-05,
      "loss": 1.1912,
      "step": 153
    },
    {
      "epoch": 0.005214991407116431,
      "grad_norm": 0.8060011267662048,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 1.075,
      "step": 154
    },
    {
      "epoch": 0.005248854987682123,
      "grad_norm": 0.6935968995094299,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 1.0861,
      "step": 155
    },
    {
      "epoch": 0.005282718568247814,
      "grad_norm": 0.6611942052841187,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 1.0816,
      "step": 156
    },
    {
      "epoch": 0.005316582148813505,
      "grad_norm": 0.755397617816925,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 1.1044,
      "step": 157
    },
    {
      "epoch": 0.005350445729379196,
      "grad_norm": 0.8729384541511536,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.9407,
      "step": 158
    },
    {
      "epoch": 0.005384309309944887,
      "grad_norm": 0.7903375029563904,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.9133,
      "step": 159
    },
    {
      "epoch": 0.005418172890510578,
      "grad_norm": 0.9189381003379822,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.7667,
      "step": 160
    },
    {
      "epoch": 0.0054520364710762695,
      "grad_norm": 1.0420712232589722,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.8161,
      "step": 161
    },
    {
      "epoch": 0.00548590005164196,
      "grad_norm": 0.9024725556373596,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.9087,
      "step": 162
    },
    {
      "epoch": 0.005519763632207651,
      "grad_norm": 1.2544010877609253,
      "learning_rate": 9.068759265665384e-06,
      "loss": 1.013,
      "step": 163
    },
    {
      "epoch": 0.0055536272127733426,
      "grad_norm": 0.9686055183410645,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.9438,
      "step": 164
    },
    {
      "epoch": 0.005587490793339034,
      "grad_norm": 0.9056728482246399,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.894,
      "step": 165
    },
    {
      "epoch": 0.005621354373904725,
      "grad_norm": 0.8981388211250305,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.8378,
      "step": 166
    },
    {
      "epoch": 0.005655217954470416,
      "grad_norm": 0.9021278619766235,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.7337,
      "step": 167
    },
    {
      "epoch": 0.005689081535036107,
      "grad_norm": 0.788145899772644,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.844,
      "step": 168
    },
    {
      "epoch": 0.005722945115601798,
      "grad_norm": 0.8900693655014038,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.8219,
      "step": 169
    },
    {
      "epoch": 0.0057568086961674895,
      "grad_norm": 0.9927849173545837,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.9027,
      "step": 170
    },
    {
      "epoch": 0.00579067227673318,
      "grad_norm": 0.9730656743049622,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.7991,
      "step": 171
    },
    {
      "epoch": 0.005824535857298871,
      "grad_norm": 0.8259562253952026,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.8266,
      "step": 172
    },
    {
      "epoch": 0.0058583994378645626,
      "grad_norm": 0.9437413215637207,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.8283,
      "step": 173
    },
    {
      "epoch": 0.005892263018430254,
      "grad_norm": 0.9569439888000488,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.6487,
      "step": 174
    },
    {
      "epoch": 0.005926126598995945,
      "grad_norm": 0.8946563005447388,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.8629,
      "step": 175
    },
    {
      "epoch": 0.005959990179561636,
      "grad_norm": 0.8732927441596985,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.7516,
      "step": 176
    },
    {
      "epoch": 0.005993853760127327,
      "grad_norm": 0.9670328497886658,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.7137,
      "step": 177
    },
    {
      "epoch": 0.006027717340693018,
      "grad_norm": 1.0360735654830933,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.7385,
      "step": 178
    },
    {
      "epoch": 0.0060615809212587095,
      "grad_norm": 1.0376851558685303,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.7262,
      "step": 179
    },
    {
      "epoch": 0.006095444501824401,
      "grad_norm": 0.9631625413894653,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6803,
      "step": 180
    },
    {
      "epoch": 0.006129308082390091,
      "grad_norm": 1.240159034729004,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6486,
      "step": 181
    },
    {
      "epoch": 0.0061631716629557826,
      "grad_norm": 1.1967631578445435,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.7372,
      "step": 182
    },
    {
      "epoch": 0.006197035243521474,
      "grad_norm": 1.4236044883728027,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.8388,
      "step": 183
    },
    {
      "epoch": 0.006230898824087165,
      "grad_norm": 1.1505696773529053,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.7553,
      "step": 184
    },
    {
      "epoch": 0.006264762404652856,
      "grad_norm": 1.3848652839660645,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.7939,
      "step": 185
    },
    {
      "epoch": 0.006298625985218547,
      "grad_norm": 1.3290842771530151,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.6618,
      "step": 186
    },
    {
      "epoch": 0.006332489565784238,
      "grad_norm": 1.3564484119415283,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.8309,
      "step": 187
    },
    {
      "epoch": 0.0063663531463499295,
      "grad_norm": 1.5110307931900024,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.7548,
      "step": 188
    },
    {
      "epoch": 0.006400216726915621,
      "grad_norm": 1.6180833578109741,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.836,
      "step": 189
    },
    {
      "epoch": 0.006434080307481311,
      "grad_norm": 1.8504395484924316,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.7747,
      "step": 190
    },
    {
      "epoch": 0.0064679438880470026,
      "grad_norm": 1.5028947591781616,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.6571,
      "step": 191
    },
    {
      "epoch": 0.006501807468612694,
      "grad_norm": 1.753167748451233,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.7481,
      "step": 192
    },
    {
      "epoch": 0.006535671049178385,
      "grad_norm": 2.1419565677642822,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.7669,
      "step": 193
    },
    {
      "epoch": 0.006569534629744076,
      "grad_norm": 2.0370125770568848,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.8954,
      "step": 194
    },
    {
      "epoch": 0.006603398210309767,
      "grad_norm": 1.958778738975525,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.6744,
      "step": 195
    },
    {
      "epoch": 0.006637261790875458,
      "grad_norm": 3.0325088500976562,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.7835,
      "step": 196
    },
    {
      "epoch": 0.0066711253714411495,
      "grad_norm": 2.31496262550354,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.7993,
      "step": 197
    },
    {
      "epoch": 0.006704988952006841,
      "grad_norm": 2.6766602993011475,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.7699,
      "step": 198
    },
    {
      "epoch": 0.006738852532572531,
      "grad_norm": 2.8966171741485596,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.6275,
      "step": 199
    },
    {
      "epoch": 0.0067727161131382226,
      "grad_norm": 3.670168876647949,
      "learning_rate": 0.0,
      "loss": 0.5824,
      "step": 200
    },
    {
      "epoch": 0.0067727161131382226,
      "eval_loss": 0.8114216923713684,
      "eval_runtime": 4340.9349,
      "eval_samples_per_second": 11.457,
      "eval_steps_per_second": 2.864,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.0737300270874624e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}