{
  "best_metric": 0.10843601077795029,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 0.06396418005916686,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003198209002958343,
      "grad_norm": 0.733355700969696,
      "learning_rate": 1e-05,
      "loss": 0.8424,
      "step": 1
    },
    {
      "epoch": 0.0003198209002958343,
      "eval_loss": 0.41758644580841064,
      "eval_runtime": 700.4829,
      "eval_samples_per_second": 7.518,
      "eval_steps_per_second": 1.88,
      "step": 1
    },
    {
      "epoch": 0.0006396418005916686,
      "grad_norm": 0.7232412695884705,
      "learning_rate": 2e-05,
      "loss": 0.892,
      "step": 2
    },
    {
      "epoch": 0.000959462700887503,
      "grad_norm": 0.7371528148651123,
      "learning_rate": 3e-05,
      "loss": 0.9308,
      "step": 3
    },
    {
      "epoch": 0.0012792836011833373,
      "grad_norm": 0.6977390646934509,
      "learning_rate": 4e-05,
      "loss": 0.857,
      "step": 4
    },
    {
      "epoch": 0.0015991045014791716,
      "grad_norm": 0.513538122177124,
      "learning_rate": 5e-05,
      "loss": 0.7975,
      "step": 5
    },
    {
      "epoch": 0.001918925401775006,
      "grad_norm": 0.3662252128124237,
      "learning_rate": 6e-05,
      "loss": 0.6456,
      "step": 6
    },
    {
      "epoch": 0.0022387463020708404,
      "grad_norm": 0.26116642355918884,
      "learning_rate": 7e-05,
      "loss": 0.5514,
      "step": 7
    },
    {
      "epoch": 0.0025585672023666745,
      "grad_norm": 0.2631494402885437,
      "learning_rate": 8e-05,
      "loss": 0.4995,
      "step": 8
    },
    {
      "epoch": 0.002878388102662509,
      "grad_norm": 0.2916277348995209,
      "learning_rate": 9e-05,
      "loss": 0.4514,
      "step": 9
    },
    {
      "epoch": 0.0031982090029583432,
      "grad_norm": 0.39282315969467163,
      "learning_rate": 0.0001,
      "loss": 0.5483,
      "step": 10
    },
    {
      "epoch": 0.003518029903254178,
      "grad_norm": 0.5647358894348145,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.5357,
      "step": 11
    },
    {
      "epoch": 0.003837850803550012,
      "grad_norm": 0.43796467781066895,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.5543,
      "step": 12
    },
    {
      "epoch": 0.004157671703845846,
      "grad_norm": 0.3381921052932739,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.5419,
      "step": 13
    },
    {
      "epoch": 0.004477492604141681,
      "grad_norm": 0.28958505392074585,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.5034,
      "step": 14
    },
    {
      "epoch": 0.004797313504437515,
      "grad_norm": 0.25872281193733215,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.4969,
      "step": 15
    },
    {
      "epoch": 0.005117134404733349,
      "grad_norm": 0.2884986400604248,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.5669,
      "step": 16
    },
    {
      "epoch": 0.005436955305029184,
      "grad_norm": 0.24532407522201538,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.4266,
      "step": 17
    },
    {
      "epoch": 0.005756776205325018,
      "grad_norm": 0.23512235283851624,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.3983,
      "step": 18
    },
    {
      "epoch": 0.006076597105620852,
      "grad_norm": 0.28063926100730896,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.535,
      "step": 19
    },
    {
      "epoch": 0.0063964180059166865,
      "grad_norm": 0.3638555705547333,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.4705,
      "step": 20
    },
    {
      "epoch": 0.006716238906212521,
      "grad_norm": 0.2459528148174286,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.4986,
      "step": 21
    },
    {
      "epoch": 0.007036059806508356,
      "grad_norm": 0.24128219485282898,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.4247,
      "step": 22
    },
    {
      "epoch": 0.007355880706804189,
      "grad_norm": 0.3016946613788605,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.4983,
      "step": 23
    },
    {
      "epoch": 0.007675701607100024,
      "grad_norm": 0.2684149146080017,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.4159,
      "step": 24
    },
    {
      "epoch": 0.007995522507395858,
      "grad_norm": 0.327891081571579,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.4267,
      "step": 25
    },
    {
      "epoch": 0.008315343407691692,
      "grad_norm": 0.3018912971019745,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.3276,
      "step": 26
    },
    {
      "epoch": 0.008635164307987527,
      "grad_norm": 0.3946612775325775,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.4075,
      "step": 27
    },
    {
      "epoch": 0.008954985208283361,
      "grad_norm": 0.34061896800994873,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.2974,
      "step": 28
    },
    {
      "epoch": 0.009274806108579196,
      "grad_norm": 0.6930350661277771,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.4981,
      "step": 29
    },
    {
      "epoch": 0.00959462700887503,
      "grad_norm": 0.5890650153160095,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.5368,
      "step": 30
    },
    {
      "epoch": 0.009914447909170865,
      "grad_norm": 0.6804101467132568,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.6569,
      "step": 31
    },
    {
      "epoch": 0.010234268809466698,
      "grad_norm": 0.6683328747749329,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.5618,
      "step": 32
    },
    {
      "epoch": 0.010554089709762533,
      "grad_norm": 0.6280273795127869,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.5284,
      "step": 33
    },
    {
      "epoch": 0.010873910610058367,
      "grad_norm": 0.7099074721336365,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.5627,
      "step": 34
    },
    {
      "epoch": 0.011193731510354202,
      "grad_norm": 0.8341547250747681,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.7536,
      "step": 35
    },
    {
      "epoch": 0.011513552410650036,
      "grad_norm": 1.0870885848999023,
      "learning_rate": 9.545032675245813e-05,
      "loss": 1.0291,
      "step": 36
    },
    {
      "epoch": 0.011833373310945871,
      "grad_norm": 0.9681828022003174,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8318,
      "step": 37
    },
    {
      "epoch": 0.012153194211241704,
      "grad_norm": 1.0672504901885986,
      "learning_rate": 9.473646649103818e-05,
      "loss": 1.0472,
      "step": 38
    },
    {
      "epoch": 0.012473015111537538,
      "grad_norm": 1.0365281105041504,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.8252,
      "step": 39
    },
    {
      "epoch": 0.012792836011833373,
      "grad_norm": 1.1480456590652466,
      "learning_rate": 9.397368756032445e-05,
      "loss": 1.0432,
      "step": 40
    },
    {
      "epoch": 0.013112656912129208,
      "grad_norm": 1.205892562866211,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8711,
      "step": 41
    },
    {
      "epoch": 0.013432477812425042,
      "grad_norm": 1.3959020376205444,
      "learning_rate": 9.316282404787871e-05,
      "loss": 1.0566,
      "step": 42
    },
    {
      "epoch": 0.013752298712720877,
      "grad_norm": 1.5852802991867065,
      "learning_rate": 9.273963562927695e-05,
      "loss": 1.0596,
      "step": 43
    },
    {
      "epoch": 0.014072119613016711,
      "grad_norm": 1.57753586769104,
      "learning_rate": 9.230476262104677e-05,
      "loss": 1.0618,
      "step": 44
    },
    {
      "epoch": 0.014391940513312544,
      "grad_norm": 1.8437082767486572,
      "learning_rate": 9.185832391312644e-05,
      "loss": 1.2583,
      "step": 45
    },
    {
      "epoch": 0.014711761413608379,
      "grad_norm": 1.7808903455734253,
      "learning_rate": 9.140044155740101e-05,
      "loss": 1.1523,
      "step": 46
    },
    {
      "epoch": 0.015031582313904213,
      "grad_norm": 2.2847094535827637,
      "learning_rate": 9.093124073433463e-05,
      "loss": 1.5351,
      "step": 47
    },
    {
      "epoch": 0.015351403214200048,
      "grad_norm": 2.603990316390991,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.6839,
      "step": 48
    },
    {
      "epoch": 0.015671224114495882,
      "grad_norm": 3.1308672428131104,
      "learning_rate": 8.995939984474624e-05,
      "loss": 1.7368,
      "step": 49
    },
    {
      "epoch": 0.015991045014791715,
      "grad_norm": 4.260708808898926,
      "learning_rate": 8.945702546981969e-05,
      "loss": 1.7424,
      "step": 50
    },
    {
      "epoch": 0.015991045014791715,
      "eval_loss": 0.1714501827955246,
      "eval_runtime": 707.5921,
      "eval_samples_per_second": 7.442,
      "eval_steps_per_second": 1.861,
      "step": 50
    },
    {
      "epoch": 0.01631086591508755,
      "grad_norm": 3.0255730152130127,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.6125,
      "step": 51
    },
    {
      "epoch": 0.016630686815383385,
      "grad_norm": 1.856024146080017,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.5058,
      "step": 52
    },
    {
      "epoch": 0.01695050771567922,
      "grad_norm": 0.7605986595153809,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.3023,
      "step": 53
    },
    {
      "epoch": 0.017270328615975054,
      "grad_norm": 0.37644797563552856,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.2905,
      "step": 54
    },
    {
      "epoch": 0.01759014951627089,
      "grad_norm": 0.46010029315948486,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.3047,
      "step": 55
    },
    {
      "epoch": 0.017909970416566723,
      "grad_norm": 0.4566298723220825,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.2718,
      "step": 56
    },
    {
      "epoch": 0.018229791316862556,
      "grad_norm": 0.37460243701934814,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.2255,
      "step": 57
    },
    {
      "epoch": 0.018549612217158392,
      "grad_norm": 0.39128974080085754,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.2072,
      "step": 58
    },
    {
      "epoch": 0.018869433117454225,
      "grad_norm": 0.3821653723716736,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.2479,
      "step": 59
    },
    {
      "epoch": 0.01918925401775006,
      "grad_norm": 0.40521425008773804,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.2804,
      "step": 60
    },
    {
      "epoch": 0.019509074918045894,
      "grad_norm": 0.337826132774353,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.2472,
      "step": 61
    },
    {
      "epoch": 0.01982889581834173,
      "grad_norm": 0.3585914969444275,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.3281,
      "step": 62
    },
    {
      "epoch": 0.020148716718637563,
      "grad_norm": 0.3059711158275604,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.2471,
      "step": 63
    },
    {
      "epoch": 0.020468537618933396,
      "grad_norm": 0.252555251121521,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.2368,
      "step": 64
    },
    {
      "epoch": 0.020788358519229232,
      "grad_norm": 0.28456854820251465,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.2326,
      "step": 65
    },
    {
      "epoch": 0.021108179419525065,
      "grad_norm": 0.30199140310287476,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.2877,
      "step": 66
    },
    {
      "epoch": 0.0214280003198209,
      "grad_norm": 0.3159363269805908,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.2488,
      "step": 67
    },
    {
      "epoch": 0.021747821220116734,
      "grad_norm": 0.308321088552475,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.2174,
      "step": 68
    },
    {
      "epoch": 0.022067642120412567,
      "grad_norm": 0.36082711815834045,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.2816,
      "step": 69
    },
    {
      "epoch": 0.022387463020708404,
      "grad_norm": 0.2793419659137726,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.2147,
      "step": 70
    },
    {
      "epoch": 0.022707283921004236,
      "grad_norm": 0.292595237493515,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.2611,
      "step": 71
    },
    {
      "epoch": 0.023027104821300073,
      "grad_norm": 0.3361249566078186,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.3039,
      "step": 72
    },
    {
      "epoch": 0.023346925721595906,
      "grad_norm": 0.35229048132896423,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.362,
      "step": 73
    },
    {
      "epoch": 0.023666746621891742,
      "grad_norm": 0.2868785560131073,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.2409,
      "step": 74
    },
    {
      "epoch": 0.023986567522187575,
      "grad_norm": 0.3366268277168274,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.3118,
      "step": 75
    },
    {
      "epoch": 0.024306388422483408,
      "grad_norm": 0.34326082468032837,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.2568,
      "step": 76
    },
    {
      "epoch": 0.024626209322779244,
      "grad_norm": 0.29759883880615234,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.2492,
      "step": 77
    },
    {
      "epoch": 0.024946030223075077,
      "grad_norm": 0.3078097701072693,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.2608,
      "step": 78
    },
    {
      "epoch": 0.025265851123370913,
      "grad_norm": 0.4492635428905487,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.3267,
      "step": 79
    },
    {
      "epoch": 0.025585672023666746,
      "grad_norm": 0.5370021462440491,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.4138,
      "step": 80
    },
    {
      "epoch": 0.025905492923962582,
      "grad_norm": 0.548529863357544,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.4897,
      "step": 81
    },
    {
      "epoch": 0.026225313824258415,
      "grad_norm": 0.42671453952789307,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.2967,
      "step": 82
    },
    {
      "epoch": 0.026545134724554248,
      "grad_norm": 0.4900617301464081,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.3634,
      "step": 83
    },
    {
      "epoch": 0.026864955624850084,
      "grad_norm": 0.720504879951477,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.4668,
      "step": 84
    },
    {
      "epoch": 0.027184776525145917,
      "grad_norm": 0.8631587624549866,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.6065,
      "step": 85
    },
    {
      "epoch": 0.027504597425441753,
      "grad_norm": 0.7580759525299072,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.5634,
      "step": 86
    },
    {
      "epoch": 0.027824418325737586,
      "grad_norm": 0.9472992420196533,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.6912,
      "step": 87
    },
    {
      "epoch": 0.028144239226033423,
      "grad_norm": 0.8876928687095642,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.738,
      "step": 88
    },
    {
      "epoch": 0.028464060126329255,
      "grad_norm": 0.9907633662223816,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7004,
      "step": 89
    },
    {
      "epoch": 0.02878388102662509,
      "grad_norm": 0.9504837989807129,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.5916,
      "step": 90
    },
    {
      "epoch": 0.029103701926920925,
      "grad_norm": 1.2986513376235962,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.8868,
      "step": 91
    },
    {
      "epoch": 0.029423522827216757,
      "grad_norm": 1.048391342163086,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.7267,
      "step": 92
    },
    {
      "epoch": 0.029743343727512594,
      "grad_norm": 1.5032157897949219,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.9489,
      "step": 93
    },
    {
      "epoch": 0.030063164627808427,
      "grad_norm": 1.5255554914474487,
      "learning_rate": 5.90440267166055e-05,
      "loss": 1.1125,
      "step": 94
    },
    {
      "epoch": 0.030382985528104263,
      "grad_norm": 1.3697547912597656,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.859,
      "step": 95
    },
    {
      "epoch": 0.030702806428400096,
      "grad_norm": 1.6299450397491455,
      "learning_rate": 5.74131823855921e-05,
      "loss": 1.0489,
      "step": 96
    },
    {
      "epoch": 0.03102262732869593,
      "grad_norm": 2.0556132793426514,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 1.121,
      "step": 97
    },
    {
      "epoch": 0.031342448228991765,
      "grad_norm": 1.9002476930618286,
      "learning_rate": 5.577423184847932e-05,
      "loss": 1.0666,
      "step": 98
    },
    {
      "epoch": 0.0316622691292876,
      "grad_norm": 2.442599296569824,
      "learning_rate": 5.495227651252315e-05,
      "loss": 1.5068,
      "step": 99
    },
    {
      "epoch": 0.03198209002958343,
      "grad_norm": 3.024186372756958,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 1.662,
      "step": 100
    },
    {
      "epoch": 0.03198209002958343,
      "eval_loss": 0.1231631189584732,
      "eval_runtime": 707.7718,
      "eval_samples_per_second": 7.44,
      "eval_steps_per_second": 1.861,
      "step": 100
    },
    {
      "epoch": 0.03230191092987927,
      "grad_norm": 0.33594822883605957,
      "learning_rate": 5.330452921628497e-05,
      "loss": 0.2608,
      "step": 101
    },
    {
      "epoch": 0.0326217318301751,
      "grad_norm": 0.3474246561527252,
      "learning_rate": 5.247918773366112e-05,
      "loss": 0.2597,
      "step": 102
    },
    {
      "epoch": 0.03294155273047094,
      "grad_norm": 0.277812123298645,
      "learning_rate": 5.165316846586541e-05,
      "loss": 0.2435,
      "step": 103
    },
    {
      "epoch": 0.03326137363076677,
      "grad_norm": 0.30479344725608826,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 0.249,
      "step": 104
    },
    {
      "epoch": 0.033581194531062605,
      "grad_norm": 0.34273555874824524,
      "learning_rate": 5e-05,
      "loss": 0.2653,
      "step": 105
    },
    {
      "epoch": 0.03390101543135844,
      "grad_norm": 0.32153844833374023,
      "learning_rate": 4.917330276168208e-05,
      "loss": 0.2075,
      "step": 106
    },
    {
      "epoch": 0.03422083633165427,
      "grad_norm": 0.36128899455070496,
      "learning_rate": 4.834683153413459e-05,
      "loss": 0.2087,
      "step": 107
    },
    {
      "epoch": 0.03454065723195011,
      "grad_norm": 0.4501410126686096,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 0.2204,
      "step": 108
    },
    {
      "epoch": 0.034860478132245944,
      "grad_norm": 0.26083818078041077,
      "learning_rate": 4.669547078371504e-05,
      "loss": 0.1565,
      "step": 109
    },
    {
      "epoch": 0.03518029903254178,
      "grad_norm": 0.28071239590644836,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 0.1908,
      "step": 110
    },
    {
      "epoch": 0.03550011993283761,
      "grad_norm": 0.3036470115184784,
      "learning_rate": 4.504772348747687e-05,
      "loss": 0.2239,
      "step": 111
    },
    {
      "epoch": 0.035819940833133446,
      "grad_norm": 0.3025403618812561,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 0.2086,
      "step": 112
    },
    {
      "epoch": 0.03613976173342928,
      "grad_norm": 0.3334406316280365,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 0.2382,
      "step": 113
    },
    {
      "epoch": 0.03645958263372511,
      "grad_norm": 0.36945047974586487,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 0.2561,
      "step": 114
    },
    {
      "epoch": 0.03677940353402095,
      "grad_norm": 0.34640777111053467,
      "learning_rate": 4.17702704859633e-05,
      "loss": 0.2271,
      "step": 115
    },
    {
      "epoch": 0.037099224434316784,
      "grad_norm": 0.3813648223876953,
      "learning_rate": 4.095597328339452e-05,
      "loss": 0.265,
      "step": 116
    },
    {
      "epoch": 0.03741904533461262,
      "grad_norm": 0.32037341594696045,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 0.1715,
      "step": 117
    },
    {
      "epoch": 0.03773886623490845,
      "grad_norm": 0.36896005272865295,
      "learning_rate": 3.933501846281267e-05,
      "loss": 0.3049,
      "step": 118
    },
    {
      "epoch": 0.038058687135204286,
      "grad_norm": 0.29940271377563477,
      "learning_rate": 3.852880399766243e-05,
      "loss": 0.1969,
      "step": 119
    },
    {
      "epoch": 0.03837850803550012,
      "grad_norm": 0.36412161588668823,
      "learning_rate": 3.772572564296005e-05,
      "loss": 0.2573,
      "step": 120
    },
    {
      "epoch": 0.03869832893579595,
      "grad_norm": 0.35847535729408264,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 0.2533,
      "step": 121
    },
    {
      "epoch": 0.03901814983609179,
      "grad_norm": 0.4879471957683563,
      "learning_rate": 3.612985456190778e-05,
      "loss": 0.4432,
      "step": 122
    },
    {
      "epoch": 0.039337970736387624,
      "grad_norm": 0.3185747563838959,
      "learning_rate": 3.533749813077677e-05,
      "loss": 0.2221,
      "step": 123
    },
    {
      "epoch": 0.03965779163668346,
      "grad_norm": 0.30086520314216614,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2175,
      "step": 124
    },
    {
      "epoch": 0.03997761253697929,
      "grad_norm": 0.30397024750709534,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 0.2589,
      "step": 125
    },
    {
      "epoch": 0.040297433437275126,
      "grad_norm": 0.37038129568099976,
      "learning_rate": 3.298534127791785e-05,
      "loss": 0.2608,
      "step": 126
    },
    {
      "epoch": 0.04061725433757096,
      "grad_norm": 0.3764711916446686,
      "learning_rate": 3.221030765387417e-05,
      "loss": 0.2366,
      "step": 127
    },
    {
      "epoch": 0.04093707523786679,
      "grad_norm": 0.40300023555755615,
      "learning_rate": 3.144013755408895e-05,
      "loss": 0.3038,
      "step": 128
    },
    {
      "epoch": 0.04125689613816263,
      "grad_norm": 0.5505624413490295,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 0.3437,
      "step": 129
    },
    {
      "epoch": 0.041576717038458465,
      "grad_norm": 0.4119115173816681,
      "learning_rate": 2.991522876735154e-05,
      "loss": 0.3183,
      "step": 130
    },
    {
      "epoch": 0.0418965379387543,
      "grad_norm": 0.5014015436172485,
      "learning_rate": 2.916090697523549e-05,
      "loss": 0.3946,
      "step": 131
    },
    {
      "epoch": 0.04221635883905013,
      "grad_norm": 0.5232303142547607,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 0.3443,
      "step": 132
    },
    {
      "epoch": 0.04253617973934597,
      "grad_norm": 0.5242652893066406,
      "learning_rate": 2.766955965735968e-05,
      "loss": 0.3455,
      "step": 133
    },
    {
      "epoch": 0.0428560006396418,
      "grad_norm": 0.6080648303031921,
      "learning_rate": 2.693294185106562e-05,
      "loss": 0.389,
      "step": 134
    },
    {
      "epoch": 0.04317582153993763,
      "grad_norm": 0.808191180229187,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 0.5288,
      "step": 135
    },
    {
      "epoch": 0.04349564244023347,
      "grad_norm": 0.7360102534294128,
      "learning_rate": 2.547882480847461e-05,
      "loss": 0.5251,
      "step": 136
    },
    {
      "epoch": 0.043815463340529305,
      "grad_norm": 0.8850722908973694,
      "learning_rate": 2.476172311325783e-05,
      "loss": 0.6886,
      "step": 137
    },
    {
      "epoch": 0.044135284240825134,
      "grad_norm": 0.9609745740890503,
      "learning_rate": 2.405152131093926e-05,
      "loss": 0.7781,
      "step": 138
    },
    {
      "epoch": 0.04445510514112097,
      "grad_norm": 0.9895976185798645,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 0.5235,
      "step": 139
    },
    {
      "epoch": 0.04477492604141681,
      "grad_norm": 1.0348330736160278,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 0.6453,
      "step": 140
    },
    {
      "epoch": 0.04509474694171264,
      "grad_norm": 1.077602505683899,
      "learning_rate": 2.196424713241637e-05,
      "loss": 0.5987,
      "step": 141
    },
    {
      "epoch": 0.04541456784200847,
      "grad_norm": 1.0914020538330078,
      "learning_rate": 2.128356686585282e-05,
      "loss": 0.7573,
      "step": 142
    },
    {
      "epoch": 0.04573438874230431,
      "grad_norm": 1.4008575677871704,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.8901,
      "step": 143
    },
    {
      "epoch": 0.046054209642600145,
      "grad_norm": 1.513798475265503,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 0.988,
      "step": 144
    },
    {
      "epoch": 0.046374030542895975,
      "grad_norm": 1.3358558416366577,
      "learning_rate": 1.928936436551661e-05,
      "loss": 0.7208,
      "step": 145
    },
    {
      "epoch": 0.04669385144319181,
      "grad_norm": 1.3631783723831177,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 0.8042,
      "step": 146
    },
    {
      "epoch": 0.04701367234348765,
      "grad_norm": 1.5463505983352661,
      "learning_rate": 1.800157297483417e-05,
      "loss": 0.9349,
      "step": 147
    },
    {
      "epoch": 0.047333493243783484,
      "grad_norm": 1.9204987287521362,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 1.0789,
      "step": 148
    },
    {
      "epoch": 0.04765331414407931,
      "grad_norm": 2.9544529914855957,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 1.6101,
      "step": 149
    },
    {
      "epoch": 0.04797313504437515,
      "grad_norm": 4.241387844085693,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 1.8563,
      "step": 150
    },
    {
      "epoch": 0.04797313504437515,
      "eval_loss": 0.11033383011817932,
      "eval_runtime": 707.3098,
      "eval_samples_per_second": 7.445,
      "eval_steps_per_second": 1.862,
      "step": 150
    },
    {
      "epoch": 0.048292955944670986,
      "grad_norm": 0.2228386104106903,
      "learning_rate": 1.553232954407171e-05,
      "loss": 0.1531,
      "step": 151
    },
    {
      "epoch": 0.048612776844966815,
      "grad_norm": 0.2362639605998993,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 0.2018,
      "step": 152
    },
    {
      "epoch": 0.04893259774526265,
      "grad_norm": 0.22419358789920807,
      "learning_rate": 1.435357758543015e-05,
      "loss": 0.1784,
      "step": 153
    },
    {
      "epoch": 0.04925241864555849,
      "grad_norm": 0.2462545484304428,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 0.185,
      "step": 154
    },
    {
      "epoch": 0.049572239545854324,
      "grad_norm": 0.3680232763290405,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 0.4665,
      "step": 155
    },
    {
      "epoch": 0.049892060446150154,
      "grad_norm": 0.21650643646717072,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 0.1792,
      "step": 156
    },
    {
      "epoch": 0.05021188134644599,
      "grad_norm": 0.2441571205854416,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 0.15,
      "step": 157
    },
    {
      "epoch": 0.050531702246741826,
      "grad_norm": 0.21878522634506226,
      "learning_rate": 1.157994445715706e-05,
      "loss": 0.1351,
      "step": 158
    },
    {
      "epoch": 0.050851523147037656,
      "grad_norm": 0.2482927143573761,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 0.2009,
      "step": 159
    },
    {
      "epoch": 0.05117134404733349,
      "grad_norm": 0.28437334299087524,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 0.1998,
      "step": 160
    },
    {
      "epoch": 0.05149116494762933,
      "grad_norm": 0.2629641890525818,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 0.2242,
      "step": 161
    },
    {
      "epoch": 0.051810985847925164,
      "grad_norm": 0.27468302845954895,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.2566,
      "step": 162
    },
    {
      "epoch": 0.052130806748220994,
      "grad_norm": 0.26547741889953613,
      "learning_rate": 9.068759265665384e-06,
      "loss": 0.1975,
      "step": 163
    },
    {
      "epoch": 0.05245062764851683,
      "grad_norm": 0.24738812446594238,
      "learning_rate": 8.599558442598998e-06,
      "loss": 0.1941,
      "step": 164
    },
    {
      "epoch": 0.052770448548812667,
      "grad_norm": 0.26750150322914124,
      "learning_rate": 8.141676086873572e-06,
      "loss": 0.1902,
      "step": 165
    },
    {
      "epoch": 0.053090269449108496,
      "grad_norm": 0.252927303314209,
      "learning_rate": 7.695237378953223e-06,
      "loss": 0.2015,
      "step": 166
    },
    {
      "epoch": 0.05341009034940433,
      "grad_norm": 0.3349028527736664,
      "learning_rate": 7.260364370723044e-06,
      "loss": 0.2644,
      "step": 167
    },
    {
      "epoch": 0.05372991124970017,
      "grad_norm": 0.3417888879776001,
      "learning_rate": 6.837175952121306e-06,
      "loss": 0.2973,
      "step": 168
    },
    {
      "epoch": 0.054049732149996005,
      "grad_norm": 0.2248062938451767,
      "learning_rate": 6.425787818636131e-06,
      "loss": 0.1836,
      "step": 169
    },
    {
      "epoch": 0.054369553050291834,
      "grad_norm": 0.33683446049690247,
      "learning_rate": 6.026312439675552e-06,
      "loss": 0.2674,
      "step": 170
    },
    {
      "epoch": 0.05468937395058767,
      "grad_norm": 0.2953754961490631,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 0.2396,
      "step": 171
    },
    {
      "epoch": 0.05500919485088351,
      "grad_norm": 0.384050577878952,
      "learning_rate": 5.263533508961827e-06,
      "loss": 0.3138,
      "step": 172
    },
    {
      "epoch": 0.055329015751179336,
      "grad_norm": 0.2819671034812927,
      "learning_rate": 4.900438493352055e-06,
      "loss": 0.2099,
      "step": 173
    },
    {
      "epoch": 0.05564883665147517,
      "grad_norm": 0.35484397411346436,
      "learning_rate": 4.549673247541875e-06,
      "loss": 0.2666,
      "step": 174
    },
    {
      "epoch": 0.05596865755177101,
      "grad_norm": 0.3796851336956024,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 0.3234,
      "step": 175
    },
    {
      "epoch": 0.056288478452066845,
      "grad_norm": 0.38910889625549316,
      "learning_rate": 3.885512251130763e-06,
      "loss": 0.3426,
      "step": 176
    },
    {
      "epoch": 0.056608299352362675,
      "grad_norm": 0.42673397064208984,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 0.3263,
      "step": 177
    },
    {
      "epoch": 0.05692812025265851,
      "grad_norm": 0.4127025008201599,
      "learning_rate": 3.271776770026963e-06,
      "loss": 0.3375,
      "step": 178
    },
    {
      "epoch": 0.05724794115295435,
      "grad_norm": 0.46750637888908386,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 0.3369,
      "step": 179
    },
    {
      "epoch": 0.05756776205325018,
      "grad_norm": 0.503231406211853,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 0.3603,
      "step": 180
    },
    {
      "epoch": 0.05788758295354601,
      "grad_norm": 0.4760417640209198,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.3226,
      "step": 181
    },
    {
      "epoch": 0.05820740385384185,
      "grad_norm": 0.5485504269599915,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 0.3469,
      "step": 182
    },
    {
      "epoch": 0.058527224754137686,
      "grad_norm": 0.7601380944252014,
      "learning_rate": 1.962316193157593e-06,
      "loss": 0.3536,
      "step": 183
    },
    {
      "epoch": 0.058847045654433515,
      "grad_norm": 0.8731808662414551,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 0.5925,
      "step": 184
    },
    {
      "epoch": 0.05916686655472935,
      "grad_norm": 0.8889862895011902,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 0.553,
      "step": 185
    },
    {
      "epoch": 0.05948668745502519,
      "grad_norm": 0.8766216039657593,
      "learning_rate": 1.333670137599713e-06,
      "loss": 0.5783,
      "step": 186
    },
    {
      "epoch": 0.05980650835532102,
      "grad_norm": 1.0591824054718018,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 0.6292,
      "step": 187
    },
    {
      "epoch": 0.06012632925561685,
      "grad_norm": 1.1191264390945435,
      "learning_rate": 9.810017062595322e-07,
      "loss": 0.816,
      "step": 188
    },
    {
      "epoch": 0.06044615015591269,
      "grad_norm": 1.0949547290802002,
      "learning_rate": 8.247462563808817e-07,
      "loss": 0.7502,
      "step": 189
    },
    {
      "epoch": 0.060765971056208526,
      "grad_norm": 1.1341993808746338,
      "learning_rate": 6.819348298638839e-07,
      "loss": 0.7309,
      "step": 190
    },
    {
      "epoch": 0.061085791956504355,
      "grad_norm": 0.8800665736198425,
      "learning_rate": 5.526064699265753e-07,
      "loss": 0.5343,
      "step": 191
    },
    {
      "epoch": 0.06140561285680019,
      "grad_norm": 1.0097521543502808,
      "learning_rate": 4.367965336512403e-07,
      "loss": 0.5193,
      "step": 192
    },
    {
      "epoch": 0.06172543375709603,
      "grad_norm": 1.3267039060592651,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 0.9686,
      "step": 193
    },
    {
      "epoch": 0.06204525465739186,
      "grad_norm": 1.4617061614990234,
      "learning_rate": 2.458548727494292e-07,
      "loss": 0.9521,
      "step": 194
    },
    {
      "epoch": 0.062365075557687694,
      "grad_norm": 1.2641453742980957,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 0.8236,
      "step": 195
    },
    {
      "epoch": 0.06268489645798353,
      "grad_norm": 1.5959171056747437,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 0.9695,
      "step": 196
    },
    {
      "epoch": 0.06300471735827937,
      "grad_norm": 1.66757333278656,
      "learning_rate": 6.150154258476315e-08,
      "loss": 1.1264,
      "step": 197
    },
    {
      "epoch": 0.0633245382585752,
      "grad_norm": 1.9533088207244873,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 1.2251,
      "step": 198
    },
    {
      "epoch": 0.06364435915887104,
      "grad_norm": 2.112776756286621,
      "learning_rate": 6.834750376549792e-09,
      "loss": 1.115,
      "step": 199
    },
    {
      "epoch": 0.06396418005916686,
      "grad_norm": 3.199683666229248,
      "learning_rate": 0.0,
      "loss": 1.6626,
      "step": 200
    },
    {
      "epoch": 0.06396418005916686,
      "eval_loss": 0.10843601077795029,
      "eval_runtime": 707.1978,
      "eval_samples_per_second": 7.446,
      "eval_steps_per_second": 1.862,
      "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": 6.383939109676646e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}