{
  "best_metric": 0.5165769457817078,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.03746721618583739,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00018733608092918696,
      "grad_norm": 0.42080265283584595,
      "learning_rate": 1e-05,
      "loss": 0.4969,
      "step": 1
    },
    {
      "epoch": 0.00018733608092918696,
      "eval_loss": 0.8705017566680908,
      "eval_runtime": 858.7263,
      "eval_samples_per_second": 10.469,
      "eval_steps_per_second": 2.618,
      "step": 1
    },
    {
      "epoch": 0.0003746721618583739,
      "grad_norm": 0.45967909693717957,
      "learning_rate": 2e-05,
      "loss": 0.5082,
      "step": 2
    },
    {
      "epoch": 0.0005620082427875609,
      "grad_norm": 0.5537425875663757,
      "learning_rate": 3e-05,
      "loss": 0.6617,
      "step": 3
    },
    {
      "epoch": 0.0007493443237167478,
      "grad_norm": 0.5181278586387634,
      "learning_rate": 4e-05,
      "loss": 0.6112,
      "step": 4
    },
    {
      "epoch": 0.0009366804046459348,
      "grad_norm": 0.5044459104537964,
      "learning_rate": 5e-05,
      "loss": 0.623,
      "step": 5
    },
    {
      "epoch": 0.0011240164855751218,
      "grad_norm": 0.44043049216270447,
      "learning_rate": 6e-05,
      "loss": 0.6518,
      "step": 6
    },
    {
      "epoch": 0.0013113525665043087,
      "grad_norm": 0.4129781424999237,
      "learning_rate": 7e-05,
      "loss": 0.6967,
      "step": 7
    },
    {
      "epoch": 0.0014986886474334957,
      "grad_norm": 0.4499181807041168,
      "learning_rate": 8e-05,
      "loss": 0.644,
      "step": 8
    },
    {
      "epoch": 0.0016860247283626826,
      "grad_norm": 0.5048525333404541,
      "learning_rate": 9e-05,
      "loss": 0.7024,
      "step": 9
    },
    {
      "epoch": 0.0018733608092918695,
      "grad_norm": 0.45464831590652466,
      "learning_rate": 0.0001,
      "loss": 0.6282,
      "step": 10
    },
    {
      "epoch": 0.0020606968902210565,
      "grad_norm": 0.4535512328147888,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.6226,
      "step": 11
    },
    {
      "epoch": 0.0022480329711502436,
      "grad_norm": 0.4109664261341095,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.6397,
      "step": 12
    },
    {
      "epoch": 0.0024353690520794303,
      "grad_norm": 0.3601583242416382,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.6826,
      "step": 13
    },
    {
      "epoch": 0.0026227051330086175,
      "grad_norm": 0.3060451149940491,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.5616,
      "step": 14
    },
    {
      "epoch": 0.002810041213937804,
      "grad_norm": 0.2901949882507324,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.5684,
      "step": 15
    },
    {
      "epoch": 0.0029973772948669914,
      "grad_norm": 0.3803945779800415,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.607,
      "step": 16
    },
    {
      "epoch": 0.0031847133757961785,
      "grad_norm": 0.36635759472846985,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.5908,
      "step": 17
    },
    {
      "epoch": 0.0033720494567253652,
      "grad_norm": 0.3936110734939575,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.6501,
      "step": 18
    },
    {
      "epoch": 0.0035593855376545524,
      "grad_norm": 0.39425206184387207,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7399,
      "step": 19
    },
    {
      "epoch": 0.003746721618583739,
      "grad_norm": 0.383055716753006,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6677,
      "step": 20
    },
    {
      "epoch": 0.003934057699512926,
      "grad_norm": 0.4156208336353302,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.7399,
      "step": 21
    },
    {
      "epoch": 0.004121393780442113,
      "grad_norm": 0.4110686779022217,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.6558,
      "step": 22
    },
    {
      "epoch": 0.0043087298613713005,
      "grad_norm": 0.4925207793712616,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.7393,
      "step": 23
    },
    {
      "epoch": 0.004496065942300487,
      "grad_norm": 0.39587220549583435,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.7053,
      "step": 24
    },
    {
      "epoch": 0.004683402023229674,
      "grad_norm": 0.34142959117889404,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.5991,
      "step": 25
    },
    {
      "epoch": 0.004870738104158861,
      "grad_norm": 0.42330533266067505,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.6839,
      "step": 26
    },
    {
      "epoch": 0.005058074185088048,
      "grad_norm": 0.43851202726364136,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.7177,
      "step": 27
    },
    {
      "epoch": 0.005245410266017235,
      "grad_norm": 0.433656245470047,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.6886,
      "step": 28
    },
    {
      "epoch": 0.005432746346946422,
      "grad_norm": 0.4120844304561615,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.6562,
      "step": 29
    },
    {
      "epoch": 0.005620082427875608,
      "grad_norm": 0.3945956826210022,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.5192,
      "step": 30
    },
    {
      "epoch": 0.005807418508804796,
      "grad_norm": 0.5734912753105164,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.7187,
      "step": 31
    },
    {
      "epoch": 0.005994754589733983,
      "grad_norm": 0.4779996871948242,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.6509,
      "step": 32
    },
    {
      "epoch": 0.006182090670663169,
      "grad_norm": 0.48496487736701965,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.6189,
      "step": 33
    },
    {
      "epoch": 0.006369426751592357,
      "grad_norm": 0.500619113445282,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.6168,
      "step": 34
    },
    {
      "epoch": 0.006556762832521544,
      "grad_norm": 0.48954758048057556,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.6362,
      "step": 35
    },
    {
      "epoch": 0.0067440989134507304,
      "grad_norm": 0.462784081697464,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.717,
      "step": 36
    },
    {
      "epoch": 0.006931434994379917,
      "grad_norm": 0.49576225876808167,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.708,
      "step": 37
    },
    {
      "epoch": 0.007118771075309105,
      "grad_norm": 0.5154783725738525,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.7356,
      "step": 38
    },
    {
      "epoch": 0.0073061071562382915,
      "grad_norm": 0.47215205430984497,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.6353,
      "step": 39
    },
    {
      "epoch": 0.007493443237167478,
      "grad_norm": 0.46207132935523987,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.6345,
      "step": 40
    },
    {
      "epoch": 0.007680779318096666,
      "grad_norm": 0.4675160050392151,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.6768,
      "step": 41
    },
    {
      "epoch": 0.007868115399025852,
      "grad_norm": 0.5246294140815735,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.6912,
      "step": 42
    },
    {
      "epoch": 0.00805545147995504,
      "grad_norm": 0.5424666404724121,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.6923,
      "step": 43
    },
    {
      "epoch": 0.008242787560884226,
      "grad_norm": 0.5615256428718567,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.6484,
      "step": 44
    },
    {
      "epoch": 0.008430123641813413,
      "grad_norm": 0.5460834503173828,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.6547,
      "step": 45
    },
    {
      "epoch": 0.008617459722742601,
      "grad_norm": 0.5864610075950623,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.6528,
      "step": 46
    },
    {
      "epoch": 0.008804795803671788,
      "grad_norm": 0.5872603058815002,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7014,
      "step": 47
    },
    {
      "epoch": 0.008992131884600974,
      "grad_norm": 0.5060229897499084,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.5756,
      "step": 48
    },
    {
      "epoch": 0.009179467965530161,
      "grad_norm": 0.5722307562828064,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.6031,
      "step": 49
    },
    {
      "epoch": 0.009366804046459348,
      "grad_norm": 0.6936435103416443,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.5627,
      "step": 50
    },
    {
      "epoch": 0.009366804046459348,
      "eval_loss": 0.6191325187683105,
      "eval_runtime": 864.1279,
      "eval_samples_per_second": 10.404,
      "eval_steps_per_second": 2.601,
      "step": 50
    },
    {
      "epoch": 0.009554140127388535,
      "grad_norm": 0.37449517846107483,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.4748,
      "step": 51
    },
    {
      "epoch": 0.009741476208317721,
      "grad_norm": 0.32919132709503174,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.4336,
      "step": 52
    },
    {
      "epoch": 0.00992881228924691,
      "grad_norm": 0.3035586178302765,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.5157,
      "step": 53
    },
    {
      "epoch": 0.010116148370176097,
      "grad_norm": 0.32444432377815247,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.527,
      "step": 54
    },
    {
      "epoch": 0.010303484451105283,
      "grad_norm": 0.28885287046432495,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.5447,
      "step": 55
    },
    {
      "epoch": 0.01049082053203447,
      "grad_norm": 0.3308047652244568,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.6171,
      "step": 56
    },
    {
      "epoch": 0.010678156612963657,
      "grad_norm": 0.30128827691078186,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.4781,
      "step": 57
    },
    {
      "epoch": 0.010865492693892843,
      "grad_norm": 0.36715951561927795,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.6087,
      "step": 58
    },
    {
      "epoch": 0.01105282877482203,
      "grad_norm": 0.3732537627220154,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.5109,
      "step": 59
    },
    {
      "epoch": 0.011240164855751217,
      "grad_norm": 0.3901432752609253,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.6546,
      "step": 60
    },
    {
      "epoch": 0.011427500936680405,
      "grad_norm": 0.397430419921875,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.5201,
      "step": 61
    },
    {
      "epoch": 0.011614837017609592,
      "grad_norm": 0.3561963140964508,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.6574,
      "step": 62
    },
    {
      "epoch": 0.011802173098538779,
      "grad_norm": 0.3552945554256439,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.5902,
      "step": 63
    },
    {
      "epoch": 0.011989509179467965,
      "grad_norm": 0.3475552499294281,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.5658,
      "step": 64
    },
    {
      "epoch": 0.012176845260397152,
      "grad_norm": 0.36502939462661743,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.5651,
      "step": 65
    },
    {
      "epoch": 0.012364181341326339,
      "grad_norm": 0.4349987208843231,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.6653,
      "step": 66
    },
    {
      "epoch": 0.012551517422255526,
      "grad_norm": 0.3665624260902405,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.6457,
      "step": 67
    },
    {
      "epoch": 0.012738853503184714,
      "grad_norm": 0.368875652551651,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.615,
      "step": 68
    },
    {
      "epoch": 0.0129261895841139,
      "grad_norm": 0.34342971444129944,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.5418,
      "step": 69
    },
    {
      "epoch": 0.013113525665043087,
      "grad_norm": 0.34940338134765625,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.5764,
      "step": 70
    },
    {
      "epoch": 0.013300861745972274,
      "grad_norm": 0.36036354303359985,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.6491,
      "step": 71
    },
    {
      "epoch": 0.013488197826901461,
      "grad_norm": 0.37648874521255493,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.6055,
      "step": 72
    },
    {
      "epoch": 0.013675533907830648,
      "grad_norm": 0.38907724618911743,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.5236,
      "step": 73
    },
    {
      "epoch": 0.013862869988759834,
      "grad_norm": 0.4091130793094635,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.6689,
      "step": 74
    },
    {
      "epoch": 0.014050206069689023,
      "grad_norm": 0.3916974365711212,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.6061,
      "step": 75
    },
    {
      "epoch": 0.01423754215061821,
      "grad_norm": 0.3526623547077179,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.5073,
      "step": 76
    },
    {
      "epoch": 0.014424878231547396,
      "grad_norm": 0.3583081066608429,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.5815,
      "step": 77
    },
    {
      "epoch": 0.014612214312476583,
      "grad_norm": 0.42418238520622253,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.5992,
      "step": 78
    },
    {
      "epoch": 0.01479955039340577,
      "grad_norm": 0.49305421113967896,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.6266,
      "step": 79
    },
    {
      "epoch": 0.014986886474334956,
      "grad_norm": 0.4837939739227295,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.6285,
      "step": 80
    },
    {
      "epoch": 0.015174222555264143,
      "grad_norm": 0.41280192136764526,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.596,
      "step": 81
    },
    {
      "epoch": 0.015361558636193332,
      "grad_norm": 0.4788668751716614,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.5841,
      "step": 82
    },
    {
      "epoch": 0.015548894717122518,
      "grad_norm": 0.4837977886199951,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.5759,
      "step": 83
    },
    {
      "epoch": 0.015736230798051705,
      "grad_norm": 0.47581222653388977,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.57,
      "step": 84
    },
    {
      "epoch": 0.01592356687898089,
      "grad_norm": 0.4152592420578003,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.563,
      "step": 85
    },
    {
      "epoch": 0.01611090295991008,
      "grad_norm": 0.5010339617729187,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5835,
      "step": 86
    },
    {
      "epoch": 0.016298239040839265,
      "grad_norm": 0.5072130560874939,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6536,
      "step": 87
    },
    {
      "epoch": 0.016485575121768452,
      "grad_norm": 0.46855559945106506,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.6424,
      "step": 88
    },
    {
      "epoch": 0.01667291120269764,
      "grad_norm": 0.5350022315979004,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.641,
      "step": 89
    },
    {
      "epoch": 0.016860247283626825,
      "grad_norm": 0.5057423710823059,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5698,
      "step": 90
    },
    {
      "epoch": 0.017047583364556012,
      "grad_norm": 0.5755689740180969,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.5891,
      "step": 91
    },
    {
      "epoch": 0.017234919445485202,
      "grad_norm": 0.5369793772697449,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.6112,
      "step": 92
    },
    {
      "epoch": 0.01742225552641439,
      "grad_norm": 0.5031367540359497,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.5595,
      "step": 93
    },
    {
      "epoch": 0.017609591607343576,
      "grad_norm": 0.5147919654846191,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6253,
      "step": 94
    },
    {
      "epoch": 0.017796927688272762,
      "grad_norm": 0.4553160071372986,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.5102,
      "step": 95
    },
    {
      "epoch": 0.01798426376920195,
      "grad_norm": 0.5461573004722595,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.5889,
      "step": 96
    },
    {
      "epoch": 0.018171599850131136,
      "grad_norm": 0.48324018716812134,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.5526,
      "step": 97
    },
    {
      "epoch": 0.018358935931060322,
      "grad_norm": 0.545119047164917,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.5491,
      "step": 98
    },
    {
      "epoch": 0.01854627201198951,
      "grad_norm": 0.6584556102752686,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.5615,
      "step": 99
    },
    {
      "epoch": 0.018733608092918696,
      "grad_norm": 0.6728478670120239,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.4033,
      "step": 100
    },
    {
      "epoch": 0.018733608092918696,
      "eval_loss": 0.5584664940834045,
      "eval_runtime": 864.7582,
      "eval_samples_per_second": 10.396,
      "eval_steps_per_second": 2.6,
      "step": 100
    },
    {
      "epoch": 0.018920944173847883,
      "grad_norm": 0.2538839280605316,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.3803,
      "step": 101
    },
    {
      "epoch": 0.01910828025477707,
      "grad_norm": 0.2640833854675293,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.4428,
      "step": 102
    },
    {
      "epoch": 0.019295616335706256,
      "grad_norm": 0.3113883137702942,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.524,
      "step": 103
    },
    {
      "epoch": 0.019482952416635443,
      "grad_norm": 0.31153520941734314,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.5101,
      "step": 104
    },
    {
      "epoch": 0.01967028849756463,
      "grad_norm": 0.2953944802284241,
      "learning_rate": 5e-05,
      "loss": 0.4476,
      "step": 105
    },
    {
      "epoch": 0.01985762457849382,
      "grad_norm": 0.356200248003006,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.5153,
      "step": 106
    },
    {
      "epoch": 0.020044960659423006,
      "grad_norm": 0.33625417947769165,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.551,
      "step": 107
    },
    {
      "epoch": 0.020232296740352193,
      "grad_norm": 0.3744712769985199,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.5789,
      "step": 108
    },
    {
      "epoch": 0.02041963282128138,
      "grad_norm": 0.3471558094024658,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.5941,
      "step": 109
    },
    {
      "epoch": 0.020606968902210566,
      "grad_norm": 0.37143242359161377,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.6131,
      "step": 110
    },
    {
      "epoch": 0.020794304983139753,
      "grad_norm": 0.3376232981681824,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.563,
      "step": 111
    },
    {
      "epoch": 0.02098164106406894,
      "grad_norm": 0.3566010296344757,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.5164,
      "step": 112
    },
    {
      "epoch": 0.021168977144998127,
      "grad_norm": 0.3177107870578766,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.4854,
      "step": 113
    },
    {
      "epoch": 0.021356313225927313,
      "grad_norm": 0.36092278361320496,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.591,
      "step": 114
    },
    {
      "epoch": 0.0215436493068565,
      "grad_norm": 0.3421477973461151,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.514,
      "step": 115
    },
    {
      "epoch": 0.021730985387785687,
      "grad_norm": 0.35613057017326355,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.4944,
      "step": 116
    },
    {
      "epoch": 0.021918321468714873,
      "grad_norm": 0.3736391067504883,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.5164,
      "step": 117
    },
    {
      "epoch": 0.02210565754964406,
      "grad_norm": 0.3712262511253357,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.4989,
      "step": 118
    },
    {
      "epoch": 0.022292993630573247,
      "grad_norm": 0.5579050779342651,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.5055,
      "step": 119
    },
    {
      "epoch": 0.022480329711502434,
      "grad_norm": 0.3797934353351593,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.5869,
      "step": 120
    },
    {
      "epoch": 0.022667665792431624,
      "grad_norm": 0.3670457601547241,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.415,
      "step": 121
    },
    {
      "epoch": 0.02285500187336081,
      "grad_norm": 0.41976362466812134,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.5708,
      "step": 122
    },
    {
      "epoch": 0.023042337954289997,
      "grad_norm": 0.40332919359207153,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.5098,
      "step": 123
    },
    {
      "epoch": 0.023229674035219184,
      "grad_norm": 0.3828362822532654,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.518,
      "step": 124
    },
    {
      "epoch": 0.02341701011614837,
      "grad_norm": 0.3352470099925995,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.4949,
      "step": 125
    },
    {
      "epoch": 0.023604346197077557,
      "grad_norm": 0.44147586822509766,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.6338,
      "step": 126
    },
    {
      "epoch": 0.023791682278006744,
      "grad_norm": 0.4130827486515045,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.5187,
      "step": 127
    },
    {
      "epoch": 0.02397901835893593,
      "grad_norm": 0.4177480936050415,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.5869,
      "step": 128
    },
    {
      "epoch": 0.024166354439865118,
      "grad_norm": 0.4028020203113556,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.5911,
      "step": 129
    },
    {
      "epoch": 0.024353690520794304,
      "grad_norm": 0.3950989544391632,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.5111,
      "step": 130
    },
    {
      "epoch": 0.02454102660172349,
      "grad_norm": 0.4779664874076843,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.6617,
      "step": 131
    },
    {
      "epoch": 0.024728362682652678,
      "grad_norm": 0.402166485786438,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.5413,
      "step": 132
    },
    {
      "epoch": 0.024915698763581864,
      "grad_norm": 0.4281097948551178,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.5187,
      "step": 133
    },
    {
      "epoch": 0.02510303484451105,
      "grad_norm": 0.4947041869163513,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.5406,
      "step": 134
    },
    {
      "epoch": 0.02529037092544024,
      "grad_norm": 0.47548750042915344,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.6042,
      "step": 135
    },
    {
      "epoch": 0.025477707006369428,
      "grad_norm": 0.4392681121826172,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.5197,
      "step": 136
    },
    {
      "epoch": 0.025665043087298615,
      "grad_norm": 0.45879611372947693,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.5063,
      "step": 137
    },
    {
      "epoch": 0.0258523791682278,
      "grad_norm": 0.5270653367042542,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.6409,
      "step": 138
    },
    {
      "epoch": 0.026039715249156988,
      "grad_norm": 0.5170595645904541,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.5655,
      "step": 139
    },
    {
      "epoch": 0.026227051330086175,
      "grad_norm": 0.5222468972206116,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.5845,
      "step": 140
    },
    {
      "epoch": 0.02641438741101536,
      "grad_norm": 0.4840741753578186,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5542,
      "step": 141
    },
    {
      "epoch": 0.02660172349194455,
      "grad_norm": 0.48176074028015137,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.526,
      "step": 142
    },
    {
      "epoch": 0.026789059572873735,
      "grad_norm": 0.5765575170516968,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5653,
      "step": 143
    },
    {
      "epoch": 0.026976395653802922,
      "grad_norm": 0.4946809709072113,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.4856,
      "step": 144
    },
    {
      "epoch": 0.02716373173473211,
      "grad_norm": 0.562139093875885,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.5423,
      "step": 145
    },
    {
      "epoch": 0.027351067815661295,
      "grad_norm": 0.5321676731109619,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.4844,
      "step": 146
    },
    {
      "epoch": 0.027538403896590482,
      "grad_norm": 0.5954334735870361,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.4415,
      "step": 147
    },
    {
      "epoch": 0.02772573997751967,
      "grad_norm": 0.5740236639976501,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 0.5534,
      "step": 148
    },
    {
      "epoch": 0.02791307605844886,
      "grad_norm": 0.5329805612564087,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 0.4563,
      "step": 149
    },
    {
      "epoch": 0.028100412139378046,
      "grad_norm": 0.8162520527839661,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 0.3259,
      "step": 150
    },
    {
      "epoch": 0.028100412139378046,
      "eval_loss": 0.5239449143409729,
      "eval_runtime": 863.9955,
      "eval_samples_per_second": 10.405,
      "eval_steps_per_second": 2.602,
      "step": 150
    },
    {
      "epoch": 0.028287748220307232,
      "grad_norm": 0.2185271978378296,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.3959,
      "step": 151
    },
    {
      "epoch": 0.02847508430123642,
      "grad_norm": 0.2499614655971527,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.4484,
      "step": 152
    },
    {
      "epoch": 0.028662420382165606,
      "grad_norm": 0.30417028069496155,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.5521,
      "step": 153
    },
    {
      "epoch": 0.028849756463094792,
      "grad_norm": 0.29717206954956055,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.3527,
      "step": 154
    },
    {
      "epoch": 0.02903709254402398,
      "grad_norm": 0.44893911480903625,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4939,
      "step": 155
    },
    {
      "epoch": 0.029224428624953166,
      "grad_norm": 0.3228415548801422,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.4924,
      "step": 156
    },
    {
      "epoch": 0.029411764705882353,
      "grad_norm": 0.41260698437690735,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.4795,
      "step": 157
    },
    {
      "epoch": 0.02959910078681154,
      "grad_norm": 0.36818867921829224,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.4674,
      "step": 158
    },
    {
      "epoch": 0.029786436867740726,
      "grad_norm": 0.6487616300582886,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.5059,
      "step": 159
    },
    {
      "epoch": 0.029973772948669913,
      "grad_norm": 0.3940207064151764,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.5665,
      "step": 160
    },
    {
      "epoch": 0.0301611090295991,
      "grad_norm": 0.404619961977005,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.4904,
      "step": 161
    },
    {
      "epoch": 0.030348445110528286,
      "grad_norm": 0.33328792452812195,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.4922,
      "step": 162
    },
    {
      "epoch": 0.030535781191457476,
      "grad_norm": 0.3360675573348999,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.4651,
      "step": 163
    },
    {
      "epoch": 0.030723117272386663,
      "grad_norm": 0.33444592356681824,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.4711,
      "step": 164
    },
    {
      "epoch": 0.03091045335331585,
      "grad_norm": 0.34084513783454895,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.5694,
      "step": 165
    },
    {
      "epoch": 0.031097789434245036,
      "grad_norm": 0.3488391637802124,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.5116,
      "step": 166
    },
    {
      "epoch": 0.03128512551517422,
      "grad_norm": 0.34621378779411316,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.4571,
      "step": 167
    },
    {
      "epoch": 0.03147246159610341,
      "grad_norm": 0.3867354094982147,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.5472,
      "step": 168
    },
    {
      "epoch": 0.03165979767703259,
      "grad_norm": 0.41999396681785583,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.5396,
      "step": 169
    },
    {
      "epoch": 0.03184713375796178,
      "grad_norm": 0.34793877601623535,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.4683,
      "step": 170
    },
    {
      "epoch": 0.032034469838890973,
      "grad_norm": 0.39462634921073914,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.5228,
      "step": 171
    },
    {
      "epoch": 0.03222180591982016,
      "grad_norm": 0.3997817933559418,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.5927,
      "step": 172
    },
    {
      "epoch": 0.03240914200074935,
      "grad_norm": 0.39693257212638855,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.596,
      "step": 173
    },
    {
      "epoch": 0.03259647808167853,
      "grad_norm": 0.39077872037887573,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.5139,
      "step": 174
    },
    {
      "epoch": 0.03278381416260772,
      "grad_norm": 0.4743327498435974,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.5722,
      "step": 175
    },
    {
      "epoch": 0.032971150243536904,
      "grad_norm": 0.4428120255470276,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.5466,
      "step": 176
    },
    {
      "epoch": 0.033158486324466094,
      "grad_norm": 0.5132465958595276,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.6216,
      "step": 177
    },
    {
      "epoch": 0.03334582240539528,
      "grad_norm": 0.4739689826965332,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.5981,
      "step": 178
    },
    {
      "epoch": 0.03353315848632447,
      "grad_norm": 0.5152813196182251,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.5671,
      "step": 179
    },
    {
      "epoch": 0.03372049456725365,
      "grad_norm": 0.5225147008895874,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.6041,
      "step": 180
    },
    {
      "epoch": 0.03390783064818284,
      "grad_norm": 0.4620915353298187,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.6427,
      "step": 181
    },
    {
      "epoch": 0.034095166729112024,
      "grad_norm": 0.5414467453956604,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.6167,
      "step": 182
    },
    {
      "epoch": 0.034282502810041214,
      "grad_norm": 0.5329951643943787,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.6315,
      "step": 183
    },
    {
      "epoch": 0.034469838890970404,
      "grad_norm": 0.559242308139801,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.6565,
      "step": 184
    },
    {
      "epoch": 0.03465717497189959,
      "grad_norm": 0.47660553455352783,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.5972,
      "step": 185
    },
    {
      "epoch": 0.03484451105282878,
      "grad_norm": 0.5575544238090515,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.5576,
      "step": 186
    },
    {
      "epoch": 0.03503184713375796,
      "grad_norm": 0.48290976881980896,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.4504,
      "step": 187
    },
    {
      "epoch": 0.03521918321468715,
      "grad_norm": 0.5106654763221741,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.5295,
      "step": 188
    },
    {
      "epoch": 0.035406519295616334,
      "grad_norm": 0.5468314290046692,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.6196,
      "step": 189
    },
    {
      "epoch": 0.035593855376545525,
      "grad_norm": 0.5401754975318909,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.5487,
      "step": 190
    },
    {
      "epoch": 0.03578119145747471,
      "grad_norm": 0.5291981101036072,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.4944,
      "step": 191
    },
    {
      "epoch": 0.0359685275384039,
      "grad_norm": 0.47721654176712036,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.481,
      "step": 192
    },
    {
      "epoch": 0.03615586361933308,
      "grad_norm": 0.48018309473991394,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.4536,
      "step": 193
    },
    {
      "epoch": 0.03634319970026227,
      "grad_norm": 0.5186752080917358,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.4623,
      "step": 194
    },
    {
      "epoch": 0.036530535781191455,
      "grad_norm": 0.5705375671386719,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.5524,
      "step": 195
    },
    {
      "epoch": 0.036717871862120645,
      "grad_norm": 0.6157158017158508,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.4775,
      "step": 196
    },
    {
      "epoch": 0.03690520794304983,
      "grad_norm": 0.6278684735298157,
      "learning_rate": 6.150154258476315e-08,
      "loss": 0.5011,
      "step": 197
    },
    {
      "epoch": 0.03709254402397902,
      "grad_norm": 0.5518689155578613,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 0.5323,
      "step": 198
    },
    {
      "epoch": 0.03727988010490821,
      "grad_norm": 0.5932864546775818,
      "learning_rate": 6.834750376549792e-09,
      "loss": 0.4244,
      "step": 199
    },
    {
      "epoch": 0.03746721618583739,
      "grad_norm": 0.6906148791313171,
      "learning_rate": 0.0,
      "loss": 0.3854,
      "step": 200
    },
    {
      "epoch": 0.03746721618583739,
      "eval_loss": 0.5165769457817078,
      "eval_runtime": 863.2863,
      "eval_samples_per_second": 10.414,
      "eval_steps_per_second": 2.604,
      "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": 3.763741378970911e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}