{
  "best_metric": 10.302141189575195,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.047267355982274745,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002363367799113737,
      "grad_norm": 0.7017511129379272,
      "learning_rate": 1e-05,
      "loss": 41.5264,
      "step": 1
    },
    {
      "epoch": 0.0002363367799113737,
      "eval_loss": 10.377434730529785,
      "eval_runtime": 14.2612,
      "eval_samples_per_second": 499.747,
      "eval_steps_per_second": 124.954,
      "step": 1
    },
    {
      "epoch": 0.0004726735598227474,
      "grad_norm": 0.768441379070282,
      "learning_rate": 2e-05,
      "loss": 41.5087,
      "step": 2
    },
    {
      "epoch": 0.0007090103397341211,
      "grad_norm": 0.7134986519813538,
      "learning_rate": 3e-05,
      "loss": 41.5091,
      "step": 3
    },
    {
      "epoch": 0.0009453471196454948,
      "grad_norm": 0.92826908826828,
      "learning_rate": 4e-05,
      "loss": 41.4964,
      "step": 4
    },
    {
      "epoch": 0.0011816838995568684,
      "grad_norm": 0.8108736276626587,
      "learning_rate": 5e-05,
      "loss": 41.5004,
      "step": 5
    },
    {
      "epoch": 0.0014180206794682422,
      "grad_norm": 0.8229092955589294,
      "learning_rate": 6e-05,
      "loss": 41.5036,
      "step": 6
    },
    {
      "epoch": 0.001654357459379616,
      "grad_norm": 0.7677971720695496,
      "learning_rate": 7e-05,
      "loss": 41.4944,
      "step": 7
    },
    {
      "epoch": 0.0018906942392909896,
      "grad_norm": 0.8452812433242798,
      "learning_rate": 8e-05,
      "loss": 41.4958,
      "step": 8
    },
    {
      "epoch": 0.0021270310192023634,
      "grad_norm": 0.7085577249526978,
      "learning_rate": 9e-05,
      "loss": 41.5001,
      "step": 9
    },
    {
      "epoch": 0.002363367799113737,
      "grad_norm": 0.7536247968673706,
      "learning_rate": 0.0001,
      "loss": 41.4768,
      "step": 10
    },
    {
      "epoch": 0.002599704579025111,
      "grad_norm": 0.7905914187431335,
      "learning_rate": 9.999316524962345e-05,
      "loss": 41.4779,
      "step": 11
    },
    {
      "epoch": 0.0028360413589364844,
      "grad_norm": 0.81048583984375,
      "learning_rate": 9.997266286704631e-05,
      "loss": 41.4992,
      "step": 12
    },
    {
      "epoch": 0.0030723781388478583,
      "grad_norm": 0.8617708086967468,
      "learning_rate": 9.993849845741524e-05,
      "loss": 41.4757,
      "step": 13
    },
    {
      "epoch": 0.003308714918759232,
      "grad_norm": 0.8749671578407288,
      "learning_rate": 9.989068136093873e-05,
      "loss": 41.4582,
      "step": 14
    },
    {
      "epoch": 0.0035450516986706058,
      "grad_norm": 1.1751662492752075,
      "learning_rate": 9.98292246503335e-05,
      "loss": 41.4465,
      "step": 15
    },
    {
      "epoch": 0.0037813884785819793,
      "grad_norm": 1.051166296005249,
      "learning_rate": 9.975414512725057e-05,
      "loss": 41.467,
      "step": 16
    },
    {
      "epoch": 0.004017725258493353,
      "grad_norm": 1.0199294090270996,
      "learning_rate": 9.966546331768191e-05,
      "loss": 41.472,
      "step": 17
    },
    {
      "epoch": 0.004254062038404727,
      "grad_norm": 1.2211377620697021,
      "learning_rate": 9.956320346634876e-05,
      "loss": 41.4589,
      "step": 18
    },
    {
      "epoch": 0.0044903988183161,
      "grad_norm": 1.030989408493042,
      "learning_rate": 9.944739353007344e-05,
      "loss": 41.433,
      "step": 19
    },
    {
      "epoch": 0.004726735598227474,
      "grad_norm": 1.3730398416519165,
      "learning_rate": 9.931806517013612e-05,
      "loss": 41.4433,
      "step": 20
    },
    {
      "epoch": 0.004963072378138848,
      "grad_norm": 1.4557560682296753,
      "learning_rate": 9.917525374361912e-05,
      "loss": 41.4162,
      "step": 21
    },
    {
      "epoch": 0.005199409158050222,
      "grad_norm": 1.5338850021362305,
      "learning_rate": 9.901899829374047e-05,
      "loss": 41.4223,
      "step": 22
    },
    {
      "epoch": 0.005435745937961595,
      "grad_norm": 1.4582769870758057,
      "learning_rate": 9.884934153917997e-05,
      "loss": 41.4285,
      "step": 23
    },
    {
      "epoch": 0.005672082717872969,
      "grad_norm": 1.5451937913894653,
      "learning_rate": 9.86663298624003e-05,
      "loss": 41.4217,
      "step": 24
    },
    {
      "epoch": 0.005908419497784343,
      "grad_norm": 1.3850833177566528,
      "learning_rate": 9.847001329696653e-05,
      "loss": 41.4297,
      "step": 25
    },
    {
      "epoch": 0.006144756277695717,
      "grad_norm": 1.7164242267608643,
      "learning_rate": 9.826044551386744e-05,
      "loss": 41.3928,
      "step": 26
    },
    {
      "epoch": 0.00638109305760709,
      "grad_norm": 1.753216028213501,
      "learning_rate": 9.803768380684242e-05,
      "loss": 41.3906,
      "step": 27
    },
    {
      "epoch": 0.006617429837518464,
      "grad_norm": 1.7551887035369873,
      "learning_rate": 9.780178907671789e-05,
      "loss": 41.4036,
      "step": 28
    },
    {
      "epoch": 0.006853766617429837,
      "grad_norm": 2.0399880409240723,
      "learning_rate": 9.755282581475769e-05,
      "loss": 41.4044,
      "step": 29
    },
    {
      "epoch": 0.0070901033973412115,
      "grad_norm": 1.8561136722564697,
      "learning_rate": 9.729086208503174e-05,
      "loss": 41.3591,
      "step": 30
    },
    {
      "epoch": 0.007326440177252585,
      "grad_norm": 1.7218948602676392,
      "learning_rate": 9.701596950580806e-05,
      "loss": 41.3757,
      "step": 31
    },
    {
      "epoch": 0.0075627769571639586,
      "grad_norm": 1.8805934190750122,
      "learning_rate": 9.672822322997305e-05,
      "loss": 41.3346,
      "step": 32
    },
    {
      "epoch": 0.007799113737075332,
      "grad_norm": 1.6052335500717163,
      "learning_rate": 9.642770192448536e-05,
      "loss": 41.3369,
      "step": 33
    },
    {
      "epoch": 0.008035450516986706,
      "grad_norm": 1.7732124328613281,
      "learning_rate": 9.611448774886924e-05,
      "loss": 41.3233,
      "step": 34
    },
    {
      "epoch": 0.00827178729689808,
      "grad_norm": 1.5795286893844604,
      "learning_rate": 9.578866633275288e-05,
      "loss": 41.307,
      "step": 35
    },
    {
      "epoch": 0.008508124076809453,
      "grad_norm": 1.5525028705596924,
      "learning_rate": 9.545032675245813e-05,
      "loss": 41.3207,
      "step": 36
    },
    {
      "epoch": 0.008744460856720827,
      "grad_norm": 1.5069037675857544,
      "learning_rate": 9.509956150664796e-05,
      "loss": 41.2767,
      "step": 37
    },
    {
      "epoch": 0.0089807976366322,
      "grad_norm": 1.269014596939087,
      "learning_rate": 9.473646649103818e-05,
      "loss": 41.3,
      "step": 38
    },
    {
      "epoch": 0.009217134416543574,
      "grad_norm": 1.3924968242645264,
      "learning_rate": 9.43611409721806e-05,
      "loss": 41.285,
      "step": 39
    },
    {
      "epoch": 0.009453471196454948,
      "grad_norm": 1.2203623056411743,
      "learning_rate": 9.397368756032445e-05,
      "loss": 41.2927,
      "step": 40
    },
    {
      "epoch": 0.009689807976366323,
      "grad_norm": 1.1147902011871338,
      "learning_rate": 9.357421218136386e-05,
      "loss": 41.2915,
      "step": 41
    },
    {
      "epoch": 0.009926144756277696,
      "grad_norm": 1.1098339557647705,
      "learning_rate": 9.316282404787871e-05,
      "loss": 41.2562,
      "step": 42
    },
    {
      "epoch": 0.01016248153618907,
      "grad_norm": 1.074512243270874,
      "learning_rate": 9.273963562927695e-05,
      "loss": 41.2381,
      "step": 43
    },
    {
      "epoch": 0.010398818316100443,
      "grad_norm": 0.9971290230751038,
      "learning_rate": 9.230476262104677e-05,
      "loss": 41.2457,
      "step": 44
    },
    {
      "epoch": 0.010635155096011817,
      "grad_norm": 0.9822519421577454,
      "learning_rate": 9.185832391312644e-05,
      "loss": 41.2439,
      "step": 45
    },
    {
      "epoch": 0.01087149187592319,
      "grad_norm": 0.899904191493988,
      "learning_rate": 9.140044155740101e-05,
      "loss": 41.2459,
      "step": 46
    },
    {
      "epoch": 0.011107828655834564,
      "grad_norm": 0.9511874318122864,
      "learning_rate": 9.093124073433463e-05,
      "loss": 41.2397,
      "step": 47
    },
    {
      "epoch": 0.011344165435745937,
      "grad_norm": 0.6701773405075073,
      "learning_rate": 9.045084971874738e-05,
      "loss": 41.2834,
      "step": 48
    },
    {
      "epoch": 0.011580502215657311,
      "grad_norm": 0.9111840128898621,
      "learning_rate": 8.995939984474624e-05,
      "loss": 41.2605,
      "step": 49
    },
    {
      "epoch": 0.011816838995568686,
      "grad_norm": 0.9969452619552612,
      "learning_rate": 8.945702546981969e-05,
      "loss": 41.2156,
      "step": 50
    },
    {
      "epoch": 0.011816838995568686,
      "eval_loss": 10.308880805969238,
      "eval_runtime": 14.2383,
      "eval_samples_per_second": 500.551,
      "eval_steps_per_second": 125.155,
      "step": 50
    },
    {
      "epoch": 0.01205317577548006,
      "grad_norm": 0.7181535959243774,
      "learning_rate": 8.894386393810563e-05,
      "loss": 41.2843,
      "step": 51
    },
    {
      "epoch": 0.012289512555391433,
      "grad_norm": 0.656765341758728,
      "learning_rate": 8.842005554284296e-05,
      "loss": 41.252,
      "step": 52
    },
    {
      "epoch": 0.012525849335302807,
      "grad_norm": 1.0173224210739136,
      "learning_rate": 8.788574348801675e-05,
      "loss": 41.2316,
      "step": 53
    },
    {
      "epoch": 0.01276218611521418,
      "grad_norm": 0.7584019899368286,
      "learning_rate": 8.73410738492077e-05,
      "loss": 41.26,
      "step": 54
    },
    {
      "epoch": 0.012998522895125554,
      "grad_norm": 0.7002210021018982,
      "learning_rate": 8.678619553365659e-05,
      "loss": 41.2448,
      "step": 55
    },
    {
      "epoch": 0.013234859675036927,
      "grad_norm": 0.9506973624229431,
      "learning_rate": 8.622126023955446e-05,
      "loss": 41.226,
      "step": 56
    },
    {
      "epoch": 0.0134711964549483,
      "grad_norm": 1.0385700464248657,
      "learning_rate": 8.564642241456986e-05,
      "loss": 41.2578,
      "step": 57
    },
    {
      "epoch": 0.013707533234859674,
      "grad_norm": 0.620910108089447,
      "learning_rate": 8.506183921362443e-05,
      "loss": 41.2346,
      "step": 58
    },
    {
      "epoch": 0.01394387001477105,
      "grad_norm": 0.5517739653587341,
      "learning_rate": 8.44676704559283e-05,
      "loss": 41.222,
      "step": 59
    },
    {
      "epoch": 0.014180206794682423,
      "grad_norm": 0.7472225427627563,
      "learning_rate": 8.386407858128706e-05,
      "loss": 41.2452,
      "step": 60
    },
    {
      "epoch": 0.014416543574593797,
      "grad_norm": 0.5741201043128967,
      "learning_rate": 8.32512286056924e-05,
      "loss": 41.2203,
      "step": 61
    },
    {
      "epoch": 0.01465288035450517,
      "grad_norm": 0.5387749075889587,
      "learning_rate": 8.262928807620843e-05,
      "loss": 41.2097,
      "step": 62
    },
    {
      "epoch": 0.014889217134416544,
      "grad_norm": 0.7165069580078125,
      "learning_rate": 8.199842702516583e-05,
      "loss": 41.2417,
      "step": 63
    },
    {
      "epoch": 0.015125553914327917,
      "grad_norm": 0.5952112674713135,
      "learning_rate": 8.135881792367686e-05,
      "loss": 41.2155,
      "step": 64
    },
    {
      "epoch": 0.01536189069423929,
      "grad_norm": 0.726498544216156,
      "learning_rate": 8.07106356344834e-05,
      "loss": 41.2175,
      "step": 65
    },
    {
      "epoch": 0.015598227474150664,
      "grad_norm": 0.5219938158988953,
      "learning_rate": 8.005405736415126e-05,
      "loss": 41.2036,
      "step": 66
    },
    {
      "epoch": 0.015834564254062038,
      "grad_norm": 0.8299499154090881,
      "learning_rate": 7.938926261462366e-05,
      "loss": 41.2478,
      "step": 67
    },
    {
      "epoch": 0.016070901033973413,
      "grad_norm": 0.6959971785545349,
      "learning_rate": 7.871643313414718e-05,
      "loss": 41.2315,
      "step": 68
    },
    {
      "epoch": 0.016307237813884785,
      "grad_norm": 0.5263533592224121,
      "learning_rate": 7.803575286758364e-05,
      "loss": 41.2372,
      "step": 69
    },
    {
      "epoch": 0.01654357459379616,
      "grad_norm": 0.6296979784965515,
      "learning_rate": 7.734740790612136e-05,
      "loss": 41.2239,
      "step": 70
    },
    {
      "epoch": 0.01677991137370753,
      "grad_norm": 0.536000669002533,
      "learning_rate": 7.66515864363997e-05,
      "loss": 41.1904,
      "step": 71
    },
    {
      "epoch": 0.017016248153618907,
      "grad_norm": 0.7077313661575317,
      "learning_rate": 7.594847868906076e-05,
      "loss": 41.1963,
      "step": 72
    },
    {
      "epoch": 0.017252584933530282,
      "grad_norm": 0.7770552635192871,
      "learning_rate": 7.52382768867422e-05,
      "loss": 41.1966,
      "step": 73
    },
    {
      "epoch": 0.017488921713441654,
      "grad_norm": 0.4142221212387085,
      "learning_rate": 7.452117519152542e-05,
      "loss": 41.2344,
      "step": 74
    },
    {
      "epoch": 0.01772525849335303,
      "grad_norm": 0.6962189078330994,
      "learning_rate": 7.379736965185368e-05,
      "loss": 41.2208,
      "step": 75
    },
    {
      "epoch": 0.0179615952732644,
      "grad_norm": 0.4926377236843109,
      "learning_rate": 7.30670581489344e-05,
      "loss": 41.2277,
      "step": 76
    },
    {
      "epoch": 0.018197932053175776,
      "grad_norm": 0.48527052998542786,
      "learning_rate": 7.233044034264034e-05,
      "loss": 41.2387,
      "step": 77
    },
    {
      "epoch": 0.018434268833087148,
      "grad_norm": 0.8539275527000427,
      "learning_rate": 7.158771761692464e-05,
      "loss": 41.2181,
      "step": 78
    },
    {
      "epoch": 0.018670605612998523,
      "grad_norm": 0.591537356376648,
      "learning_rate": 7.083909302476453e-05,
      "loss": 41.1969,
      "step": 79
    },
    {
      "epoch": 0.018906942392909895,
      "grad_norm": 0.4562430679798126,
      "learning_rate": 7.008477123264848e-05,
      "loss": 41.2178,
      "step": 80
    },
    {
      "epoch": 0.01914327917282127,
      "grad_norm": 0.6759952902793884,
      "learning_rate": 6.932495846462261e-05,
      "loss": 41.2081,
      "step": 81
    },
    {
      "epoch": 0.019379615952732646,
      "grad_norm": 0.4287702739238739,
      "learning_rate": 6.855986244591104e-05,
      "loss": 41.2085,
      "step": 82
    },
    {
      "epoch": 0.019615952732644017,
      "grad_norm": 0.5619176626205444,
      "learning_rate": 6.778969234612584e-05,
      "loss": 41.1882,
      "step": 83
    },
    {
      "epoch": 0.019852289512555393,
      "grad_norm": 0.5078598856925964,
      "learning_rate": 6.701465872208216e-05,
      "loss": 41.2125,
      "step": 84
    },
    {
      "epoch": 0.020088626292466764,
      "grad_norm": 0.5129840970039368,
      "learning_rate": 6.623497346023418e-05,
      "loss": 41.2206,
      "step": 85
    },
    {
      "epoch": 0.02032496307237814,
      "grad_norm": 0.4230496287345886,
      "learning_rate": 6.545084971874738e-05,
      "loss": 41.2112,
      "step": 86
    },
    {
      "epoch": 0.02056129985228951,
      "grad_norm": 0.5913252234458923,
      "learning_rate": 6.466250186922325e-05,
      "loss": 41.1912,
      "step": 87
    },
    {
      "epoch": 0.020797636632200887,
      "grad_norm": 0.4400564432144165,
      "learning_rate": 6.387014543809223e-05,
      "loss": 41.2222,
      "step": 88
    },
    {
      "epoch": 0.02103397341211226,
      "grad_norm": 0.4668077230453491,
      "learning_rate": 6.307399704769099e-05,
      "loss": 41.2382,
      "step": 89
    },
    {
      "epoch": 0.021270310192023634,
      "grad_norm": 0.4134087562561035,
      "learning_rate": 6.227427435703997e-05,
      "loss": 41.2253,
      "step": 90
    },
    {
      "epoch": 0.02150664697193501,
      "grad_norm": 0.510674238204956,
      "learning_rate": 6.147119600233758e-05,
      "loss": 41.2252,
      "step": 91
    },
    {
      "epoch": 0.02174298375184638,
      "grad_norm": 0.5037128925323486,
      "learning_rate": 6.066498153718735e-05,
      "loss": 41.2131,
      "step": 92
    },
    {
      "epoch": 0.021979320531757756,
      "grad_norm": 0.41048845648765564,
      "learning_rate": 5.985585137257401e-05,
      "loss": 41.2349,
      "step": 93
    },
    {
      "epoch": 0.022215657311669128,
      "grad_norm": 0.5764169096946716,
      "learning_rate": 5.90440267166055e-05,
      "loss": 41.2414,
      "step": 94
    },
    {
      "epoch": 0.022451994091580503,
      "grad_norm": 0.6956310272216797,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 41.1853,
      "step": 95
    },
    {
      "epoch": 0.022688330871491875,
      "grad_norm": 0.5462573766708374,
      "learning_rate": 5.74131823855921e-05,
      "loss": 41.2128,
      "step": 96
    },
    {
      "epoch": 0.02292466765140325,
      "grad_norm": 0.7207971811294556,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 41.2486,
      "step": 97
    },
    {
      "epoch": 0.023161004431314622,
      "grad_norm": 0.6430618762969971,
      "learning_rate": 5.577423184847932e-05,
      "loss": 41.2549,
      "step": 98
    },
    {
      "epoch": 0.023397341211225997,
      "grad_norm": 0.8826752305030823,
      "learning_rate": 5.495227651252315e-05,
      "loss": 41.2182,
      "step": 99
    },
    {
      "epoch": 0.023633677991137372,
      "grad_norm": 1.2225955724716187,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 41.1814,
      "step": 100
    },
    {
      "epoch": 0.023633677991137372,
      "eval_loss": 10.304475784301758,
      "eval_runtime": 14.2094,
      "eval_samples_per_second": 501.569,
      "eval_steps_per_second": 125.41,
      "step": 100
    },
    {
      "epoch": 0.023870014771048744,
      "grad_norm": 0.5683258175849915,
      "learning_rate": 5.330452921628497e-05,
      "loss": 41.2639,
      "step": 101
    },
    {
      "epoch": 0.02410635155096012,
      "grad_norm": 0.6116344332695007,
      "learning_rate": 5.247918773366112e-05,
      "loss": 41.2569,
      "step": 102
    },
    {
      "epoch": 0.02434268833087149,
      "grad_norm": 0.7886593341827393,
      "learning_rate": 5.165316846586541e-05,
      "loss": 41.2623,
      "step": 103
    },
    {
      "epoch": 0.024579025110782866,
      "grad_norm": 0.5637018084526062,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 41.2561,
      "step": 104
    },
    {
      "epoch": 0.024815361890694238,
      "grad_norm": 0.5537078976631165,
      "learning_rate": 5e-05,
      "loss": 41.2528,
      "step": 105
    },
    {
      "epoch": 0.025051698670605613,
      "grad_norm": 0.8540703654289246,
      "learning_rate": 4.917330276168208e-05,
      "loss": 41.2307,
      "step": 106
    },
    {
      "epoch": 0.025288035450516985,
      "grad_norm": 0.6901519298553467,
      "learning_rate": 4.834683153413459e-05,
      "loss": 41.2618,
      "step": 107
    },
    {
      "epoch": 0.02552437223042836,
      "grad_norm": 0.8774058818817139,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 41.2425,
      "step": 108
    },
    {
      "epoch": 0.025760709010339736,
      "grad_norm": 0.5206881165504456,
      "learning_rate": 4.669547078371504e-05,
      "loss": 41.2331,
      "step": 109
    },
    {
      "epoch": 0.025997045790251107,
      "grad_norm": 0.5892984867095947,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 41.2217,
      "step": 110
    },
    {
      "epoch": 0.026233382570162483,
      "grad_norm": 0.4885897636413574,
      "learning_rate": 4.504772348747687e-05,
      "loss": 41.2286,
      "step": 111
    },
    {
      "epoch": 0.026469719350073855,
      "grad_norm": 0.4280990660190582,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 41.249,
      "step": 112
    },
    {
      "epoch": 0.02670605612998523,
      "grad_norm": 0.511814534664154,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 41.1789,
      "step": 113
    },
    {
      "epoch": 0.0269423929098966,
      "grad_norm": 0.6043238639831543,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 41.2006,
      "step": 114
    },
    {
      "epoch": 0.027178729689807977,
      "grad_norm": 0.6983438730239868,
      "learning_rate": 4.17702704859633e-05,
      "loss": 41.2285,
      "step": 115
    },
    {
      "epoch": 0.02741506646971935,
      "grad_norm": 0.4473256468772888,
      "learning_rate": 4.095597328339452e-05,
      "loss": 41.2161,
      "step": 116
    },
    {
      "epoch": 0.027651403249630724,
      "grad_norm": 0.7691261172294617,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 41.235,
      "step": 117
    },
    {
      "epoch": 0.0278877400295421,
      "grad_norm": 0.7613927721977234,
      "learning_rate": 3.933501846281267e-05,
      "loss": 41.2039,
      "step": 118
    },
    {
      "epoch": 0.02812407680945347,
      "grad_norm": 0.4714309275150299,
      "learning_rate": 3.852880399766243e-05,
      "loss": 41.2043,
      "step": 119
    },
    {
      "epoch": 0.028360413589364846,
      "grad_norm": 0.5756589770317078,
      "learning_rate": 3.772572564296005e-05,
      "loss": 41.236,
      "step": 120
    },
    {
      "epoch": 0.028596750369276218,
      "grad_norm": 0.6995598077774048,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 41.2093,
      "step": 121
    },
    {
      "epoch": 0.028833087149187593,
      "grad_norm": 0.6448226571083069,
      "learning_rate": 3.612985456190778e-05,
      "loss": 41.212,
      "step": 122
    },
    {
      "epoch": 0.029069423929098965,
      "grad_norm": 0.4924877882003784,
      "learning_rate": 3.533749813077677e-05,
      "loss": 41.1863,
      "step": 123
    },
    {
      "epoch": 0.02930576070901034,
      "grad_norm": 0.5269948840141296,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 41.1971,
      "step": 124
    },
    {
      "epoch": 0.029542097488921712,
      "grad_norm": 0.39500701427459717,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 41.2065,
      "step": 125
    },
    {
      "epoch": 0.029778434268833087,
      "grad_norm": 0.5846647620201111,
      "learning_rate": 3.298534127791785e-05,
      "loss": 41.2433,
      "step": 126
    },
    {
      "epoch": 0.030014771048744462,
      "grad_norm": 0.5672599077224731,
      "learning_rate": 3.221030765387417e-05,
      "loss": 41.2302,
      "step": 127
    },
    {
      "epoch": 0.030251107828655834,
      "grad_norm": 0.666126549243927,
      "learning_rate": 3.144013755408895e-05,
      "loss": 41.23,
      "step": 128
    },
    {
      "epoch": 0.03048744460856721,
      "grad_norm": 0.5294464230537415,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 41.1618,
      "step": 129
    },
    {
      "epoch": 0.03072378138847858,
      "grad_norm": 0.5049988031387329,
      "learning_rate": 2.991522876735154e-05,
      "loss": 41.1871,
      "step": 130
    },
    {
      "epoch": 0.030960118168389957,
      "grad_norm": 0.4904077649116516,
      "learning_rate": 2.916090697523549e-05,
      "loss": 41.221,
      "step": 131
    },
    {
      "epoch": 0.03119645494830133,
      "grad_norm": 0.690887987613678,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 41.2017,
      "step": 132
    },
    {
      "epoch": 0.0314327917282127,
      "grad_norm": 0.5043950080871582,
      "learning_rate": 2.766955965735968e-05,
      "loss": 41.2255,
      "step": 133
    },
    {
      "epoch": 0.031669128508124075,
      "grad_norm": 0.5043528079986572,
      "learning_rate": 2.693294185106562e-05,
      "loss": 41.2038,
      "step": 134
    },
    {
      "epoch": 0.03190546528803545,
      "grad_norm": 0.45125049352645874,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 41.2188,
      "step": 135
    },
    {
      "epoch": 0.032141802067946826,
      "grad_norm": 0.5066573023796082,
      "learning_rate": 2.547882480847461e-05,
      "loss": 41.2102,
      "step": 136
    },
    {
      "epoch": 0.0323781388478582,
      "grad_norm": 0.43378594517707825,
      "learning_rate": 2.476172311325783e-05,
      "loss": 41.2007,
      "step": 137
    },
    {
      "epoch": 0.03261447562776957,
      "grad_norm": 0.5496785640716553,
      "learning_rate": 2.405152131093926e-05,
      "loss": 41.1984,
      "step": 138
    },
    {
      "epoch": 0.032850812407680945,
      "grad_norm": 0.5256023406982422,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 41.2067,
      "step": 139
    },
    {
      "epoch": 0.03308714918759232,
      "grad_norm": 0.4560036361217499,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 41.2223,
      "step": 140
    },
    {
      "epoch": 0.033323485967503695,
      "grad_norm": 0.45323535799980164,
      "learning_rate": 2.196424713241637e-05,
      "loss": 41.2171,
      "step": 141
    },
    {
      "epoch": 0.03355982274741506,
      "grad_norm": 0.5921773314476013,
      "learning_rate": 2.128356686585282e-05,
      "loss": 41.1751,
      "step": 142
    },
    {
      "epoch": 0.03379615952732644,
      "grad_norm": 0.4303775131702423,
      "learning_rate": 2.061073738537635e-05,
      "loss": 41.2136,
      "step": 143
    },
    {
      "epoch": 0.034032496307237814,
      "grad_norm": 0.4436986446380615,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 41.2185,
      "step": 144
    },
    {
      "epoch": 0.03426883308714919,
      "grad_norm": 0.5888164043426514,
      "learning_rate": 1.928936436551661e-05,
      "loss": 41.2181,
      "step": 145
    },
    {
      "epoch": 0.034505169867060564,
      "grad_norm": 0.5130054354667664,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 41.2302,
      "step": 146
    },
    {
      "epoch": 0.03474150664697193,
      "grad_norm": 0.535312294960022,
      "learning_rate": 1.800157297483417e-05,
      "loss": 41.2168,
      "step": 147
    },
    {
      "epoch": 0.03497784342688331,
      "grad_norm": 0.5531200170516968,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 41.1973,
      "step": 148
    },
    {
      "epoch": 0.03521418020679468,
      "grad_norm": 0.7230327725410461,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 41.1891,
      "step": 149
    },
    {
      "epoch": 0.03545051698670606,
      "grad_norm": 1.0734859704971313,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 41.1475,
      "step": 150
    },
    {
      "epoch": 0.03545051698670606,
      "eval_loss": 10.302660942077637,
      "eval_runtime": 14.2196,
      "eval_samples_per_second": 501.21,
      "eval_steps_per_second": 125.32,
      "step": 150
    },
    {
      "epoch": 0.03568685376661743,
      "grad_norm": 0.5952106714248657,
      "learning_rate": 1.553232954407171e-05,
      "loss": 41.2393,
      "step": 151
    },
    {
      "epoch": 0.0359231905465288,
      "grad_norm": 0.7109106183052063,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 41.2423,
      "step": 152
    },
    {
      "epoch": 0.03615952732644018,
      "grad_norm": 0.5527380704879761,
      "learning_rate": 1.435357758543015e-05,
      "loss": 41.2416,
      "step": 153
    },
    {
      "epoch": 0.03639586410635155,
      "grad_norm": 0.6840224266052246,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 41.2288,
      "step": 154
    },
    {
      "epoch": 0.03663220088626293,
      "grad_norm": 0.5231875777244568,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 41.2239,
      "step": 155
    },
    {
      "epoch": 0.036868537666174296,
      "grad_norm": 0.7598364949226379,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 41.2286,
      "step": 156
    },
    {
      "epoch": 0.03710487444608567,
      "grad_norm": 0.6023375391960144,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 41.2491,
      "step": 157
    },
    {
      "epoch": 0.03734121122599705,
      "grad_norm": 0.8281338214874268,
      "learning_rate": 1.157994445715706e-05,
      "loss": 41.2193,
      "step": 158
    },
    {
      "epoch": 0.03757754800590842,
      "grad_norm": 0.5209323167800903,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 41.2312,
      "step": 159
    },
    {
      "epoch": 0.03781388478581979,
      "grad_norm": 0.4611285626888275,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 41.2075,
      "step": 160
    },
    {
      "epoch": 0.038050221565731165,
      "grad_norm": 0.5764565467834473,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 41.216,
      "step": 161
    },
    {
      "epoch": 0.03828655834564254,
      "grad_norm": 0.44899246096611023,
      "learning_rate": 9.549150281252633e-06,
      "loss": 41.1963,
      "step": 162
    },
    {
      "epoch": 0.038522895125553916,
      "grad_norm": 0.32884252071380615,
      "learning_rate": 9.068759265665384e-06,
      "loss": 41.195,
      "step": 163
    },
    {
      "epoch": 0.03875923190546529,
      "grad_norm": 0.5130680203437805,
      "learning_rate": 8.599558442598998e-06,
      "loss": 41.1739,
      "step": 164
    },
    {
      "epoch": 0.03899556868537666,
      "grad_norm": 0.46964457631111145,
      "learning_rate": 8.141676086873572e-06,
      "loss": 41.217,
      "step": 165
    },
    {
      "epoch": 0.039231905465288035,
      "grad_norm": 0.4942385256290436,
      "learning_rate": 7.695237378953223e-06,
      "loss": 41.206,
      "step": 166
    },
    {
      "epoch": 0.03946824224519941,
      "grad_norm": 0.4457976520061493,
      "learning_rate": 7.260364370723044e-06,
      "loss": 41.1872,
      "step": 167
    },
    {
      "epoch": 0.039704579025110785,
      "grad_norm": 0.6863199472427368,
      "learning_rate": 6.837175952121306e-06,
      "loss": 41.205,
      "step": 168
    },
    {
      "epoch": 0.039940915805022154,
      "grad_norm": 0.6692585349082947,
      "learning_rate": 6.425787818636131e-06,
      "loss": 41.1909,
      "step": 169
    },
    {
      "epoch": 0.04017725258493353,
      "grad_norm": 0.7875409126281738,
      "learning_rate": 6.026312439675552e-06,
      "loss": 41.1849,
      "step": 170
    },
    {
      "epoch": 0.040413589364844904,
      "grad_norm": 0.662039577960968,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 41.1509,
      "step": 171
    },
    {
      "epoch": 0.04064992614475628,
      "grad_norm": 0.511557400226593,
      "learning_rate": 5.263533508961827e-06,
      "loss": 41.1996,
      "step": 172
    },
    {
      "epoch": 0.040886262924667655,
      "grad_norm": 0.7464421987533569,
      "learning_rate": 4.900438493352055e-06,
      "loss": 41.2006,
      "step": 173
    },
    {
      "epoch": 0.04112259970457902,
      "grad_norm": 0.38620132207870483,
      "learning_rate": 4.549673247541875e-06,
      "loss": 41.2137,
      "step": 174
    },
    {
      "epoch": 0.0413589364844904,
      "grad_norm": 0.5495768785476685,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 41.2167,
      "step": 175
    },
    {
      "epoch": 0.04159527326440177,
      "grad_norm": 0.5984005928039551,
      "learning_rate": 3.885512251130763e-06,
      "loss": 41.1902,
      "step": 176
    },
    {
      "epoch": 0.04183161004431315,
      "grad_norm": 0.4261760413646698,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 41.1947,
      "step": 177
    },
    {
      "epoch": 0.04206794682422452,
      "grad_norm": 0.5816600322723389,
      "learning_rate": 3.271776770026963e-06,
      "loss": 41.2046,
      "step": 178
    },
    {
      "epoch": 0.04230428360413589,
      "grad_norm": 0.456093430519104,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 41.1863,
      "step": 179
    },
    {
      "epoch": 0.04254062038404727,
      "grad_norm": 0.43328291177749634,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 41.2001,
      "step": 180
    },
    {
      "epoch": 0.04277695716395864,
      "grad_norm": 0.5691746473312378,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 41.1685,
      "step": 181
    },
    {
      "epoch": 0.04301329394387002,
      "grad_norm": 0.5189961791038513,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 41.2279,
      "step": 182
    },
    {
      "epoch": 0.043249630723781386,
      "grad_norm": 0.47839346528053284,
      "learning_rate": 1.962316193157593e-06,
      "loss": 41.2119,
      "step": 183
    },
    {
      "epoch": 0.04348596750369276,
      "grad_norm": 0.5730328559875488,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 41.1881,
      "step": 184
    },
    {
      "epoch": 0.04372230428360414,
      "grad_norm": 0.3865632116794586,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 41.2054,
      "step": 185
    },
    {
      "epoch": 0.04395864106351551,
      "grad_norm": 0.5237383842468262,
      "learning_rate": 1.333670137599713e-06,
      "loss": 41.2109,
      "step": 186
    },
    {
      "epoch": 0.04419497784342688,
      "grad_norm": 0.6009936332702637,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 41.2325,
      "step": 187
    },
    {
      "epoch": 0.044431314623338256,
      "grad_norm": 0.5030163526535034,
      "learning_rate": 9.810017062595322e-07,
      "loss": 41.2093,
      "step": 188
    },
    {
      "epoch": 0.04466765140324963,
      "grad_norm": 0.4723687469959259,
      "learning_rate": 8.247462563808817e-07,
      "loss": 41.2163,
      "step": 189
    },
    {
      "epoch": 0.044903988183161006,
      "grad_norm": 0.4294276833534241,
      "learning_rate": 6.819348298638839e-07,
      "loss": 41.2236,
      "step": 190
    },
    {
      "epoch": 0.04514032496307238,
      "grad_norm": 0.4475322365760803,
      "learning_rate": 5.526064699265753e-07,
      "loss": 41.2278,
      "step": 191
    },
    {
      "epoch": 0.04537666174298375,
      "grad_norm": 0.47935032844543457,
      "learning_rate": 4.367965336512403e-07,
      "loss": 41.223,
      "step": 192
    },
    {
      "epoch": 0.045612998522895125,
      "grad_norm": 0.4120992422103882,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 41.2327,
      "step": 193
    },
    {
      "epoch": 0.0458493353028065,
      "grad_norm": 0.4597708582878113,
      "learning_rate": 2.458548727494292e-07,
      "loss": 41.1928,
      "step": 194
    },
    {
      "epoch": 0.046085672082717875,
      "grad_norm": 0.5746362209320068,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 41.2173,
      "step": 195
    },
    {
      "epoch": 0.046322008862629244,
      "grad_norm": 0.5305614471435547,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 41.214,
      "step": 196
    },
    {
      "epoch": 0.04655834564254062,
      "grad_norm": 0.6036120653152466,
      "learning_rate": 6.150154258476315e-08,
      "loss": 41.2042,
      "step": 197
    },
    {
      "epoch": 0.046794682422451994,
      "grad_norm": 0.5383595824241638,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 41.1988,
      "step": 198
    },
    {
      "epoch": 0.04703101920236337,
      "grad_norm": 0.815504252910614,
      "learning_rate": 6.834750376549792e-09,
      "loss": 41.1883,
      "step": 199
    },
    {
      "epoch": 0.047267355982274745,
      "grad_norm": 1.1346863508224487,
      "learning_rate": 0.0,
      "loss": 41.1836,
      "step": 200
    },
    {
      "epoch": 0.047267355982274745,
      "eval_loss": 10.302141189575195,
      "eval_runtime": 14.1976,
      "eval_samples_per_second": 501.986,
      "eval_steps_per_second": 125.514,
      "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": 43445157101568.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}