{
  "best_metric": 0.9246163368225098,
  "best_model_checkpoint": "miner_id_24/checkpoint-200",
  "epoch": 1.282051282051282,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00641025641025641,
      "grad_norm": 9.957436561584473,
      "learning_rate": 1e-05,
      "loss": 7.4946,
      "step": 1
    },
    {
      "epoch": 0.00641025641025641,
      "eval_loss": 2.116502523422241,
      "eval_runtime": 27.7986,
      "eval_samples_per_second": 9.461,
      "eval_steps_per_second": 2.374,
      "step": 1
    },
    {
      "epoch": 0.01282051282051282,
      "grad_norm": 11.247956275939941,
      "learning_rate": 2e-05,
      "loss": 8.1836,
      "step": 2
    },
    {
      "epoch": 0.019230769230769232,
      "grad_norm": 11.235127449035645,
      "learning_rate": 3e-05,
      "loss": 8.2321,
      "step": 3
    },
    {
      "epoch": 0.02564102564102564,
      "grad_norm": 9.880584716796875,
      "learning_rate": 4e-05,
      "loss": 7.7768,
      "step": 4
    },
    {
      "epoch": 0.03205128205128205,
      "grad_norm": 6.761786460876465,
      "learning_rate": 5e-05,
      "loss": 7.4105,
      "step": 5
    },
    {
      "epoch": 0.038461538461538464,
      "grad_norm": 5.910149574279785,
      "learning_rate": 6e-05,
      "loss": 6.8102,
      "step": 6
    },
    {
      "epoch": 0.04487179487179487,
      "grad_norm": 7.675437927246094,
      "learning_rate": 7e-05,
      "loss": 6.6599,
      "step": 7
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 6.464653491973877,
      "learning_rate": 8e-05,
      "loss": 6.0097,
      "step": 8
    },
    {
      "epoch": 0.057692307692307696,
      "grad_norm": 6.064931392669678,
      "learning_rate": 9e-05,
      "loss": 5.4483,
      "step": 9
    },
    {
      "epoch": 0.0641025641025641,
      "grad_norm": 4.900819301605225,
      "learning_rate": 0.0001,
      "loss": 4.9754,
      "step": 10
    },
    {
      "epoch": 0.07051282051282051,
      "grad_norm": 4.617133140563965,
      "learning_rate": 9.999316524962345e-05,
      "loss": 4.7351,
      "step": 11
    },
    {
      "epoch": 0.07692307692307693,
      "grad_norm": 4.90165901184082,
      "learning_rate": 9.997266286704631e-05,
      "loss": 4.7322,
      "step": 12
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 4.873775482177734,
      "learning_rate": 9.993849845741524e-05,
      "loss": 4.3286,
      "step": 13
    },
    {
      "epoch": 0.08974358974358974,
      "grad_norm": 4.3032026290893555,
      "learning_rate": 9.989068136093873e-05,
      "loss": 4.4172,
      "step": 14
    },
    {
      "epoch": 0.09615384615384616,
      "grad_norm": 3.951387643814087,
      "learning_rate": 9.98292246503335e-05,
      "loss": 4.3254,
      "step": 15
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 3.966798782348633,
      "learning_rate": 9.975414512725057e-05,
      "loss": 4.4062,
      "step": 16
    },
    {
      "epoch": 0.10897435897435898,
      "grad_norm": 3.9771132469177246,
      "learning_rate": 9.966546331768191e-05,
      "loss": 4.2944,
      "step": 17
    },
    {
      "epoch": 0.11538461538461539,
      "grad_norm": 4.00201416015625,
      "learning_rate": 9.956320346634876e-05,
      "loss": 4.1275,
      "step": 18
    },
    {
      "epoch": 0.12179487179487179,
      "grad_norm": 4.415872573852539,
      "learning_rate": 9.944739353007344e-05,
      "loss": 4.3262,
      "step": 19
    },
    {
      "epoch": 0.1282051282051282,
      "grad_norm": 4.9452080726623535,
      "learning_rate": 9.931806517013612e-05,
      "loss": 4.0444,
      "step": 20
    },
    {
      "epoch": 0.1346153846153846,
      "grad_norm": 5.381906032562256,
      "learning_rate": 9.917525374361912e-05,
      "loss": 4.0786,
      "step": 21
    },
    {
      "epoch": 0.14102564102564102,
      "grad_norm": 5.061701774597168,
      "learning_rate": 9.901899829374047e-05,
      "loss": 3.9276,
      "step": 22
    },
    {
      "epoch": 0.14743589743589744,
      "grad_norm": 5.450504302978516,
      "learning_rate": 9.884934153917997e-05,
      "loss": 4.2544,
      "step": 23
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 4.766714096069336,
      "learning_rate": 9.86663298624003e-05,
      "loss": 4.3889,
      "step": 24
    },
    {
      "epoch": 0.16025641025641027,
      "grad_norm": 8.331812858581543,
      "learning_rate": 9.847001329696653e-05,
      "loss": 4.6597,
      "step": 25
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 4.654125690460205,
      "learning_rate": 9.826044551386744e-05,
      "loss": 4.2013,
      "step": 26
    },
    {
      "epoch": 0.17307692307692307,
      "grad_norm": 4.443905830383301,
      "learning_rate": 9.803768380684242e-05,
      "loss": 4.014,
      "step": 27
    },
    {
      "epoch": 0.1794871794871795,
      "grad_norm": 4.30183744430542,
      "learning_rate": 9.780178907671789e-05,
      "loss": 3.9669,
      "step": 28
    },
    {
      "epoch": 0.1858974358974359,
      "grad_norm": 4.961958408355713,
      "learning_rate": 9.755282581475769e-05,
      "loss": 3.9399,
      "step": 29
    },
    {
      "epoch": 0.19230769230769232,
      "grad_norm": 5.458182334899902,
      "learning_rate": 9.729086208503174e-05,
      "loss": 4.163,
      "step": 30
    },
    {
      "epoch": 0.1987179487179487,
      "grad_norm": 5.726374626159668,
      "learning_rate": 9.701596950580806e-05,
      "loss": 3.965,
      "step": 31
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 4.620736122131348,
      "learning_rate": 9.672822322997305e-05,
      "loss": 3.9121,
      "step": 32
    },
    {
      "epoch": 0.21153846153846154,
      "grad_norm": 5.1553215980529785,
      "learning_rate": 9.642770192448536e-05,
      "loss": 3.8999,
      "step": 33
    },
    {
      "epoch": 0.21794871794871795,
      "grad_norm": 5.532503128051758,
      "learning_rate": 9.611448774886924e-05,
      "loss": 4.5878,
      "step": 34
    },
    {
      "epoch": 0.22435897435897437,
      "grad_norm": 4.936411380767822,
      "learning_rate": 9.578866633275288e-05,
      "loss": 3.991,
      "step": 35
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 5.254283428192139,
      "learning_rate": 9.545032675245813e-05,
      "loss": 3.7305,
      "step": 36
    },
    {
      "epoch": 0.23717948717948717,
      "grad_norm": 5.494096279144287,
      "learning_rate": 9.509956150664796e-05,
      "loss": 3.866,
      "step": 37
    },
    {
      "epoch": 0.24358974358974358,
      "grad_norm": 8.530524253845215,
      "learning_rate": 9.473646649103818e-05,
      "loss": 4.9389,
      "step": 38
    },
    {
      "epoch": 0.25,
      "grad_norm": 8.089641571044922,
      "learning_rate": 9.43611409721806e-05,
      "loss": 6.0769,
      "step": 39
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 7.604012489318848,
      "learning_rate": 9.397368756032445e-05,
      "loss": 6.0996,
      "step": 40
    },
    {
      "epoch": 0.26282051282051283,
      "grad_norm": 5.347238540649414,
      "learning_rate": 9.357421218136386e-05,
      "loss": 5.706,
      "step": 41
    },
    {
      "epoch": 0.2692307692307692,
      "grad_norm": 3.8665168285369873,
      "learning_rate": 9.316282404787871e-05,
      "loss": 5.249,
      "step": 42
    },
    {
      "epoch": 0.27564102564102566,
      "grad_norm": 3.3026998043060303,
      "learning_rate": 9.273963562927695e-05,
      "loss": 5.2123,
      "step": 43
    },
    {
      "epoch": 0.28205128205128205,
      "grad_norm": 3.3289437294006348,
      "learning_rate": 9.230476262104677e-05,
      "loss": 5.036,
      "step": 44
    },
    {
      "epoch": 0.28846153846153844,
      "grad_norm": 3.3549132347106934,
      "learning_rate": 9.185832391312644e-05,
      "loss": 5.0075,
      "step": 45
    },
    {
      "epoch": 0.2948717948717949,
      "grad_norm": 3.145491600036621,
      "learning_rate": 9.140044155740101e-05,
      "loss": 4.5827,
      "step": 46
    },
    {
      "epoch": 0.30128205128205127,
      "grad_norm": 3.2935290336608887,
      "learning_rate": 9.093124073433463e-05,
      "loss": 4.7193,
      "step": 47
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 3.1303982734680176,
      "learning_rate": 9.045084971874738e-05,
      "loss": 4.3667,
      "step": 48
    },
    {
      "epoch": 0.3141025641025641,
      "grad_norm": 2.9355759620666504,
      "learning_rate": 8.995939984474624e-05,
      "loss": 4.0385,
      "step": 49
    },
    {
      "epoch": 0.32051282051282054,
      "grad_norm": 3.22135591506958,
      "learning_rate": 8.945702546981969e-05,
      "loss": 4.1746,
      "step": 50
    },
    {
      "epoch": 0.32051282051282054,
      "eval_loss": 1.0742619037628174,
      "eval_runtime": 28.2421,
      "eval_samples_per_second": 9.312,
      "eval_steps_per_second": 2.337,
      "step": 50
    },
    {
      "epoch": 0.3269230769230769,
      "grad_norm": 3.3093056678771973,
      "learning_rate": 8.894386393810563e-05,
      "loss": 3.9733,
      "step": 51
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 3.6032257080078125,
      "learning_rate": 8.842005554284296e-05,
      "loss": 4.1736,
      "step": 52
    },
    {
      "epoch": 0.33974358974358976,
      "grad_norm": 3.5169215202331543,
      "learning_rate": 8.788574348801675e-05,
      "loss": 4.7065,
      "step": 53
    },
    {
      "epoch": 0.34615384615384615,
      "grad_norm": 3.892195463180542,
      "learning_rate": 8.73410738492077e-05,
      "loss": 3.6555,
      "step": 54
    },
    {
      "epoch": 0.3525641025641026,
      "grad_norm": 3.566694736480713,
      "learning_rate": 8.678619553365659e-05,
      "loss": 3.4694,
      "step": 55
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 3.5258185863494873,
      "learning_rate": 8.622126023955446e-05,
      "loss": 4.0258,
      "step": 56
    },
    {
      "epoch": 0.36538461538461536,
      "grad_norm": 3.711472988128662,
      "learning_rate": 8.564642241456986e-05,
      "loss": 3.9599,
      "step": 57
    },
    {
      "epoch": 0.3717948717948718,
      "grad_norm": 3.8064444065093994,
      "learning_rate": 8.506183921362443e-05,
      "loss": 4.0288,
      "step": 58
    },
    {
      "epoch": 0.3782051282051282,
      "grad_norm": 4.256228446960449,
      "learning_rate": 8.44676704559283e-05,
      "loss": 4.2489,
      "step": 59
    },
    {
      "epoch": 0.38461538461538464,
      "grad_norm": 3.41007924079895,
      "learning_rate": 8.386407858128706e-05,
      "loss": 3.6778,
      "step": 60
    },
    {
      "epoch": 0.391025641025641,
      "grad_norm": 4.161782264709473,
      "learning_rate": 8.32512286056924e-05,
      "loss": 3.8408,
      "step": 61
    },
    {
      "epoch": 0.3974358974358974,
      "grad_norm": 4.120133876800537,
      "learning_rate": 8.262928807620843e-05,
      "loss": 3.8373,
      "step": 62
    },
    {
      "epoch": 0.40384615384615385,
      "grad_norm": 3.7649734020233154,
      "learning_rate": 8.199842702516583e-05,
      "loss": 3.8083,
      "step": 63
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 3.989408016204834,
      "learning_rate": 8.135881792367686e-05,
      "loss": 3.7964,
      "step": 64
    },
    {
      "epoch": 0.4166666666666667,
      "grad_norm": 4.099987030029297,
      "learning_rate": 8.07106356344834e-05,
      "loss": 3.8704,
      "step": 65
    },
    {
      "epoch": 0.4230769230769231,
      "grad_norm": 4.085524082183838,
      "learning_rate": 8.005405736415126e-05,
      "loss": 3.7143,
      "step": 66
    },
    {
      "epoch": 0.42948717948717946,
      "grad_norm": 5.65880823135376,
      "learning_rate": 7.938926261462366e-05,
      "loss": 3.625,
      "step": 67
    },
    {
      "epoch": 0.4358974358974359,
      "grad_norm": 4.0476393699646,
      "learning_rate": 7.871643313414718e-05,
      "loss": 3.6684,
      "step": 68
    },
    {
      "epoch": 0.4423076923076923,
      "grad_norm": 4.744653224945068,
      "learning_rate": 7.803575286758364e-05,
      "loss": 3.4566,
      "step": 69
    },
    {
      "epoch": 0.44871794871794873,
      "grad_norm": 4.958125114440918,
      "learning_rate": 7.734740790612136e-05,
      "loss": 4.0852,
      "step": 70
    },
    {
      "epoch": 0.4551282051282051,
      "grad_norm": 6.67598819732666,
      "learning_rate": 7.66515864363997e-05,
      "loss": 3.5015,
      "step": 71
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 5.2367706298828125,
      "learning_rate": 7.594847868906076e-05,
      "loss": 3.952,
      "step": 72
    },
    {
      "epoch": 0.46794871794871795,
      "grad_norm": 4.691414833068848,
      "learning_rate": 7.52382768867422e-05,
      "loss": 3.2776,
      "step": 73
    },
    {
      "epoch": 0.47435897435897434,
      "grad_norm": 5.058370113372803,
      "learning_rate": 7.452117519152542e-05,
      "loss": 3.6019,
      "step": 74
    },
    {
      "epoch": 0.4807692307692308,
      "grad_norm": 5.959715843200684,
      "learning_rate": 7.379736965185368e-05,
      "loss": 3.5346,
      "step": 75
    },
    {
      "epoch": 0.48717948717948717,
      "grad_norm": 10.346742630004883,
      "learning_rate": 7.30670581489344e-05,
      "loss": 4.6809,
      "step": 76
    },
    {
      "epoch": 0.4935897435897436,
      "grad_norm": 11.073515892028809,
      "learning_rate": 7.233044034264034e-05,
      "loss": 6.4677,
      "step": 77
    },
    {
      "epoch": 0.5,
      "grad_norm": 9.660663604736328,
      "learning_rate": 7.158771761692464e-05,
      "loss": 5.9138,
      "step": 78
    },
    {
      "epoch": 0.5064102564102564,
      "grad_norm": 7.799278259277344,
      "learning_rate": 7.083909302476453e-05,
      "loss": 5.3653,
      "step": 79
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 7.223135471343994,
      "learning_rate": 7.008477123264848e-05,
      "loss": 5.1873,
      "step": 80
    },
    {
      "epoch": 0.5192307692307693,
      "grad_norm": 5.180141925811768,
      "learning_rate": 6.932495846462261e-05,
      "loss": 4.6571,
      "step": 81
    },
    {
      "epoch": 0.5256410256410257,
      "grad_norm": 3.5540072917938232,
      "learning_rate": 6.855986244591104e-05,
      "loss": 4.1324,
      "step": 82
    },
    {
      "epoch": 0.532051282051282,
      "grad_norm": 2.854039430618286,
      "learning_rate": 6.778969234612584e-05,
      "loss": 4.1329,
      "step": 83
    },
    {
      "epoch": 0.5384615384615384,
      "grad_norm": 3.3957605361938477,
      "learning_rate": 6.701465872208216e-05,
      "loss": 4.7686,
      "step": 84
    },
    {
      "epoch": 0.5448717948717948,
      "grad_norm": 3.0800118446350098,
      "learning_rate": 6.623497346023418e-05,
      "loss": 4.3467,
      "step": 85
    },
    {
      "epoch": 0.5512820512820513,
      "grad_norm": 3.383251428604126,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.4548,
      "step": 86
    },
    {
      "epoch": 0.5576923076923077,
      "grad_norm": 3.3952181339263916,
      "learning_rate": 6.466250186922325e-05,
      "loss": 4.0999,
      "step": 87
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 3.5181736946105957,
      "learning_rate": 6.387014543809223e-05,
      "loss": 4.7229,
      "step": 88
    },
    {
      "epoch": 0.5705128205128205,
      "grad_norm": 3.4152626991271973,
      "learning_rate": 6.307399704769099e-05,
      "loss": 3.8945,
      "step": 89
    },
    {
      "epoch": 0.5769230769230769,
      "grad_norm": 3.2614777088165283,
      "learning_rate": 6.227427435703997e-05,
      "loss": 3.7917,
      "step": 90
    },
    {
      "epoch": 0.5833333333333334,
      "grad_norm": 3.2620959281921387,
      "learning_rate": 6.147119600233758e-05,
      "loss": 3.7493,
      "step": 91
    },
    {
      "epoch": 0.5897435897435898,
      "grad_norm": 3.280299186706543,
      "learning_rate": 6.066498153718735e-05,
      "loss": 3.8057,
      "step": 92
    },
    {
      "epoch": 0.5961538461538461,
      "grad_norm": 3.3490095138549805,
      "learning_rate": 5.985585137257401e-05,
      "loss": 4.0438,
      "step": 93
    },
    {
      "epoch": 0.6025641025641025,
      "grad_norm": 3.555368423461914,
      "learning_rate": 5.90440267166055e-05,
      "loss": 3.5393,
      "step": 94
    },
    {
      "epoch": 0.6089743589743589,
      "grad_norm": 3.605402946472168,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 3.8683,
      "step": 95
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 3.5116748809814453,
      "learning_rate": 5.74131823855921e-05,
      "loss": 3.9831,
      "step": 96
    },
    {
      "epoch": 0.6217948717948718,
      "grad_norm": 3.322603702545166,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 3.9772,
      "step": 97
    },
    {
      "epoch": 0.6282051282051282,
      "grad_norm": 3.720085620880127,
      "learning_rate": 5.577423184847932e-05,
      "loss": 3.6853,
      "step": 98
    },
    {
      "epoch": 0.6346153846153846,
      "grad_norm": 3.5957906246185303,
      "learning_rate": 5.495227651252315e-05,
      "loss": 3.8104,
      "step": 99
    },
    {
      "epoch": 0.6410256410256411,
      "grad_norm": 3.5254197120666504,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 3.6103,
      "step": 100
    },
    {
      "epoch": 0.6410256410256411,
      "eval_loss": 0.9980463981628418,
      "eval_runtime": 28.245,
      "eval_samples_per_second": 9.311,
      "eval_steps_per_second": 2.337,
      "step": 100
    },
    {
      "epoch": 0.6474358974358975,
      "grad_norm": 3.6587297916412354,
      "learning_rate": 5.330452921628497e-05,
      "loss": 3.918,
      "step": 101
    },
    {
      "epoch": 0.6538461538461539,
      "grad_norm": 3.831242084503174,
      "learning_rate": 5.247918773366112e-05,
      "loss": 3.7586,
      "step": 102
    },
    {
      "epoch": 0.6602564102564102,
      "grad_norm": 3.78513503074646,
      "learning_rate": 5.165316846586541e-05,
      "loss": 3.5943,
      "step": 103
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 3.6787242889404297,
      "learning_rate": 5.0826697238317935e-05,
      "loss": 3.4123,
      "step": 104
    },
    {
      "epoch": 0.6730769230769231,
      "grad_norm": 3.7676947116851807,
      "learning_rate": 5e-05,
      "loss": 3.1584,
      "step": 105
    },
    {
      "epoch": 0.6794871794871795,
      "grad_norm": 4.073101043701172,
      "learning_rate": 4.917330276168208e-05,
      "loss": 3.45,
      "step": 106
    },
    {
      "epoch": 0.6858974358974359,
      "grad_norm": 4.140744209289551,
      "learning_rate": 4.834683153413459e-05,
      "loss": 3.5452,
      "step": 107
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 4.776129722595215,
      "learning_rate": 4.7520812266338885e-05,
      "loss": 3.7265,
      "step": 108
    },
    {
      "epoch": 0.6987179487179487,
      "grad_norm": 4.0117506980896,
      "learning_rate": 4.669547078371504e-05,
      "loss": 3.2593,
      "step": 109
    },
    {
      "epoch": 0.7051282051282052,
      "grad_norm": 4.677291393280029,
      "learning_rate": 4.5871032726383386e-05,
      "loss": 3.1475,
      "step": 110
    },
    {
      "epoch": 0.7115384615384616,
      "grad_norm": 5.10119104385376,
      "learning_rate": 4.504772348747687e-05,
      "loss": 3.3635,
      "step": 111
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 5.42010498046875,
      "learning_rate": 4.4225768151520694e-05,
      "loss": 4.0145,
      "step": 112
    },
    {
      "epoch": 0.7243589743589743,
      "grad_norm": 5.240736484527588,
      "learning_rate": 4.3405391432896555e-05,
      "loss": 4.2514,
      "step": 113
    },
    {
      "epoch": 0.7307692307692307,
      "grad_norm": 7.772806167602539,
      "learning_rate": 4.2586817614407895e-05,
      "loss": 4.5696,
      "step": 114
    },
    {
      "epoch": 0.7371794871794872,
      "grad_norm": 8.802128791809082,
      "learning_rate": 4.17702704859633e-05,
      "loss": 5.8478,
      "step": 115
    },
    {
      "epoch": 0.7435897435897436,
      "grad_norm": 7.847908020019531,
      "learning_rate": 4.095597328339452e-05,
      "loss": 5.0477,
      "step": 116
    },
    {
      "epoch": 0.75,
      "grad_norm": 7.966437816619873,
      "learning_rate": 4.0144148627425993e-05,
      "loss": 5.0813,
      "step": 117
    },
    {
      "epoch": 0.7564102564102564,
      "grad_norm": 8.309389114379883,
      "learning_rate": 3.933501846281267e-05,
      "loss": 5.3415,
      "step": 118
    },
    {
      "epoch": 0.7628205128205128,
      "grad_norm": 6.793262958526611,
      "learning_rate": 3.852880399766243e-05,
      "loss": 4.9559,
      "step": 119
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 6.368189334869385,
      "learning_rate": 3.772572564296005e-05,
      "loss": 4.708,
      "step": 120
    },
    {
      "epoch": 0.7756410256410257,
      "grad_norm": 4.444794654846191,
      "learning_rate": 3.6926002952309016e-05,
      "loss": 4.6569,
      "step": 121
    },
    {
      "epoch": 0.782051282051282,
      "grad_norm": 5.020304203033447,
      "learning_rate": 3.612985456190778e-05,
      "loss": 4.4671,
      "step": 122
    },
    {
      "epoch": 0.7884615384615384,
      "grad_norm": 4.116661071777344,
      "learning_rate": 3.533749813077677e-05,
      "loss": 4.1168,
      "step": 123
    },
    {
      "epoch": 0.7948717948717948,
      "grad_norm": 3.835765838623047,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 4.2167,
      "step": 124
    },
    {
      "epoch": 0.8012820512820513,
      "grad_norm": 3.623770236968994,
      "learning_rate": 3.3765026539765834e-05,
      "loss": 4.1236,
      "step": 125
    },
    {
      "epoch": 0.8076923076923077,
      "grad_norm": 3.4973554611206055,
      "learning_rate": 3.298534127791785e-05,
      "loss": 4.2815,
      "step": 126
    },
    {
      "epoch": 0.8141025641025641,
      "grad_norm": 3.046509027481079,
      "learning_rate": 3.221030765387417e-05,
      "loss": 4.2196,
      "step": 127
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 2.9827661514282227,
      "learning_rate": 3.144013755408895e-05,
      "loss": 4.0768,
      "step": 128
    },
    {
      "epoch": 0.8269230769230769,
      "grad_norm": 2.907933235168457,
      "learning_rate": 3.0675041535377405e-05,
      "loss": 3.9771,
      "step": 129
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 3.1948816776275635,
      "learning_rate": 2.991522876735154e-05,
      "loss": 4.0728,
      "step": 130
    },
    {
      "epoch": 0.8397435897435898,
      "grad_norm": 3.368992805480957,
      "learning_rate": 2.916090697523549e-05,
      "loss": 4.0119,
      "step": 131
    },
    {
      "epoch": 0.8461538461538461,
      "grad_norm": 3.3085951805114746,
      "learning_rate": 2.8412282383075363e-05,
      "loss": 3.6765,
      "step": 132
    },
    {
      "epoch": 0.8525641025641025,
      "grad_norm": 3.207343816757202,
      "learning_rate": 2.766955965735968e-05,
      "loss": 3.6675,
      "step": 133
    },
    {
      "epoch": 0.8589743589743589,
      "grad_norm": 3.4521420001983643,
      "learning_rate": 2.693294185106562e-05,
      "loss": 3.7139,
      "step": 134
    },
    {
      "epoch": 0.8653846153846154,
      "grad_norm": 3.430363655090332,
      "learning_rate": 2.6202630348146324e-05,
      "loss": 3.9139,
      "step": 135
    },
    {
      "epoch": 0.8717948717948718,
      "grad_norm": 3.638237237930298,
      "learning_rate": 2.547882480847461e-05,
      "loss": 3.9763,
      "step": 136
    },
    {
      "epoch": 0.8782051282051282,
      "grad_norm": 3.6488420963287354,
      "learning_rate": 2.476172311325783e-05,
      "loss": 3.6282,
      "step": 137
    },
    {
      "epoch": 0.8846153846153846,
      "grad_norm": 3.8091797828674316,
      "learning_rate": 2.405152131093926e-05,
      "loss": 3.75,
      "step": 138
    },
    {
      "epoch": 0.8910256410256411,
      "grad_norm": 4.3403706550598145,
      "learning_rate": 2.3348413563600325e-05,
      "loss": 3.7878,
      "step": 139
    },
    {
      "epoch": 0.8974358974358975,
      "grad_norm": 3.413701295852661,
      "learning_rate": 2.2652592093878666e-05,
      "loss": 3.7514,
      "step": 140
    },
    {
      "epoch": 0.9038461538461539,
      "grad_norm": 3.869084596633911,
      "learning_rate": 2.196424713241637e-05,
      "loss": 3.8538,
      "step": 141
    },
    {
      "epoch": 0.9102564102564102,
      "grad_norm": 3.5061874389648438,
      "learning_rate": 2.128356686585282e-05,
      "loss": 3.4699,
      "step": 142
    },
    {
      "epoch": 0.9166666666666666,
      "grad_norm": 3.533756971359253,
      "learning_rate": 2.061073738537635e-05,
      "loss": 3.6468,
      "step": 143
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 3.7761576175689697,
      "learning_rate": 1.9945942635848748e-05,
      "loss": 3.6921,
      "step": 144
    },
    {
      "epoch": 0.9294871794871795,
      "grad_norm": 3.948042154312134,
      "learning_rate": 1.928936436551661e-05,
      "loss": 3.6487,
      "step": 145
    },
    {
      "epoch": 0.9358974358974359,
      "grad_norm": 3.8867499828338623,
      "learning_rate": 1.8641182076323148e-05,
      "loss": 3.178,
      "step": 146
    },
    {
      "epoch": 0.9423076923076923,
      "grad_norm": 4.0144782066345215,
      "learning_rate": 1.800157297483417e-05,
      "loss": 3.2615,
      "step": 147
    },
    {
      "epoch": 0.9487179487179487,
      "grad_norm": 3.983966112136841,
      "learning_rate": 1.7370711923791567e-05,
      "loss": 3.024,
      "step": 148
    },
    {
      "epoch": 0.9551282051282052,
      "grad_norm": 4.11751651763916,
      "learning_rate": 1.6748771394307585e-05,
      "loss": 3.3496,
      "step": 149
    },
    {
      "epoch": 0.9615384615384616,
      "grad_norm": 4.289830207824707,
      "learning_rate": 1.6135921418712956e-05,
      "loss": 3.9751,
      "step": 150
    },
    {
      "epoch": 0.9615384615384616,
      "eval_loss": 0.955227792263031,
      "eval_runtime": 28.2085,
      "eval_samples_per_second": 9.323,
      "eval_steps_per_second": 2.34,
      "step": 150
    },
    {
      "epoch": 0.967948717948718,
      "grad_norm": 4.591463565826416,
      "learning_rate": 1.553232954407171e-05,
      "loss": 3.9584,
      "step": 151
    },
    {
      "epoch": 0.9743589743589743,
      "grad_norm": 5.648409366607666,
      "learning_rate": 1.4938160786375572e-05,
      "loss": 4.2609,
      "step": 152
    },
    {
      "epoch": 0.9807692307692307,
      "grad_norm": 4.4022626876831055,
      "learning_rate": 1.435357758543015e-05,
      "loss": 4.1401,
      "step": 153
    },
    {
      "epoch": 0.9871794871794872,
      "grad_norm": 5.345084190368652,
      "learning_rate": 1.3778739760445552e-05,
      "loss": 4.2286,
      "step": 154
    },
    {
      "epoch": 0.9935897435897436,
      "grad_norm": 5.210896015167236,
      "learning_rate": 1.3213804466343421e-05,
      "loss": 3.9715,
      "step": 155
    },
    {
      "epoch": 1.0,
      "grad_norm": 3.929900884628296,
      "learning_rate": 1.2658926150792322e-05,
      "loss": 3.0495,
      "step": 156
    },
    {
      "epoch": 1.0064102564102564,
      "grad_norm": 4.236484527587891,
      "learning_rate": 1.2114256511983274e-05,
      "loss": 4.6819,
      "step": 157
    },
    {
      "epoch": 1.0128205128205128,
      "grad_norm": 3.853949546813965,
      "learning_rate": 1.157994445715706e-05,
      "loss": 4.0865,
      "step": 158
    },
    {
      "epoch": 1.0192307692307692,
      "grad_norm": 3.554014205932617,
      "learning_rate": 1.1056136061894384e-05,
      "loss": 4.0489,
      "step": 159
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 3.6991374492645264,
      "learning_rate": 1.0542974530180327e-05,
      "loss": 3.924,
      "step": 160
    },
    {
      "epoch": 1.032051282051282,
      "grad_norm": 3.5622589588165283,
      "learning_rate": 1.0040600155253765e-05,
      "loss": 4.0894,
      "step": 161
    },
    {
      "epoch": 1.0384615384615385,
      "grad_norm": 3.4620320796966553,
      "learning_rate": 9.549150281252633e-06,
      "loss": 3.7762,
      "step": 162
    },
    {
      "epoch": 1.044871794871795,
      "grad_norm": 3.3992860317230225,
      "learning_rate": 9.068759265665384e-06,
      "loss": 3.9119,
      "step": 163
    },
    {
      "epoch": 1.0512820512820513,
      "grad_norm": 3.1045048236846924,
      "learning_rate": 8.599558442598998e-06,
      "loss": 3.7437,
      "step": 164
    },
    {
      "epoch": 1.0576923076923077,
      "grad_norm": 2.8266994953155518,
      "learning_rate": 8.141676086873572e-06,
      "loss": 3.463,
      "step": 165
    },
    {
      "epoch": 1.064102564102564,
      "grad_norm": 3.1378540992736816,
      "learning_rate": 7.695237378953223e-06,
      "loss": 3.5233,
      "step": 166
    },
    {
      "epoch": 1.0705128205128205,
      "grad_norm": 3.657463788986206,
      "learning_rate": 7.260364370723044e-06,
      "loss": 3.4232,
      "step": 167
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 3.7112457752227783,
      "learning_rate": 6.837175952121306e-06,
      "loss": 3.4753,
      "step": 168
    },
    {
      "epoch": 1.0833333333333333,
      "grad_norm": 3.6645636558532715,
      "learning_rate": 6.425787818636131e-06,
      "loss": 3.591,
      "step": 169
    },
    {
      "epoch": 1.0897435897435896,
      "grad_norm": 3.244757652282715,
      "learning_rate": 6.026312439675552e-06,
      "loss": 3.1395,
      "step": 170
    },
    {
      "epoch": 1.0961538461538463,
      "grad_norm": 3.295900821685791,
      "learning_rate": 5.6388590278194096e-06,
      "loss": 3.1197,
      "step": 171
    },
    {
      "epoch": 1.1025641025641026,
      "grad_norm": 3.2848477363586426,
      "learning_rate": 5.263533508961827e-06,
      "loss": 3.3495,
      "step": 172
    },
    {
      "epoch": 1.108974358974359,
      "grad_norm": 3.1829655170440674,
      "learning_rate": 4.900438493352055e-06,
      "loss": 3.1142,
      "step": 173
    },
    {
      "epoch": 1.1153846153846154,
      "grad_norm": 3.0936052799224854,
      "learning_rate": 4.549673247541875e-06,
      "loss": 3.0715,
      "step": 174
    },
    {
      "epoch": 1.1217948717948718,
      "grad_norm": 3.2432892322540283,
      "learning_rate": 4.2113336672471245e-06,
      "loss": 2.9327,
      "step": 175
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 3.018561840057373,
      "learning_rate": 3.885512251130763e-06,
      "loss": 2.9124,
      "step": 176
    },
    {
      "epoch": 1.1346153846153846,
      "grad_norm": 3.1902072429656982,
      "learning_rate": 3.5722980755146517e-06,
      "loss": 3.1011,
      "step": 177
    },
    {
      "epoch": 1.141025641025641,
      "grad_norm": 2.785959482192993,
      "learning_rate": 3.271776770026963e-06,
      "loss": 2.6754,
      "step": 178
    },
    {
      "epoch": 1.1474358974358974,
      "grad_norm": 3.0718090534210205,
      "learning_rate": 2.9840304941919415e-06,
      "loss": 2.74,
      "step": 179
    },
    {
      "epoch": 1.1538461538461537,
      "grad_norm": 2.9900436401367188,
      "learning_rate": 2.7091379149682685e-06,
      "loss": 3.1063,
      "step": 180
    },
    {
      "epoch": 1.1602564102564104,
      "grad_norm": 3.383514642715454,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 2.7704,
      "step": 181
    },
    {
      "epoch": 1.1666666666666667,
      "grad_norm": 3.5119516849517822,
      "learning_rate": 2.1982109232821178e-06,
      "loss": 3.0024,
      "step": 182
    },
    {
      "epoch": 1.1730769230769231,
      "grad_norm": 3.368537664413452,
      "learning_rate": 1.962316193157593e-06,
      "loss": 2.7953,
      "step": 183
    },
    {
      "epoch": 1.1794871794871795,
      "grad_norm": 3.695169687271118,
      "learning_rate": 1.7395544861325718e-06,
      "loss": 2.7724,
      "step": 184
    },
    {
      "epoch": 1.185897435897436,
      "grad_norm": 3.565120220184326,
      "learning_rate": 1.5299867030334814e-06,
      "loss": 2.7346,
      "step": 185
    },
    {
      "epoch": 1.1923076923076923,
      "grad_norm": 3.947197914123535,
      "learning_rate": 1.333670137599713e-06,
      "loss": 2.7733,
      "step": 186
    },
    {
      "epoch": 1.1987179487179487,
      "grad_norm": 4.036811828613281,
      "learning_rate": 1.1506584608200367e-06,
      "loss": 2.5709,
      "step": 187
    },
    {
      "epoch": 1.205128205128205,
      "grad_norm": 4.229754447937012,
      "learning_rate": 9.810017062595322e-07,
      "loss": 3.0155,
      "step": 188
    },
    {
      "epoch": 1.2115384615384615,
      "grad_norm": 5.230818271636963,
      "learning_rate": 8.247462563808817e-07,
      "loss": 2.9224,
      "step": 189
    },
    {
      "epoch": 1.217948717948718,
      "grad_norm": 5.559238910675049,
      "learning_rate": 6.819348298638839e-07,
      "loss": 2.8385,
      "step": 190
    },
    {
      "epoch": 1.2243589743589745,
      "grad_norm": 6.622501850128174,
      "learning_rate": 5.526064699265753e-07,
      "loss": 2.9826,
      "step": 191
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 7.27756929397583,
      "learning_rate": 4.367965336512403e-07,
      "loss": 3.3821,
      "step": 192
    },
    {
      "epoch": 1.2371794871794872,
      "grad_norm": 8.405569076538086,
      "learning_rate": 3.3453668231809286e-07,
      "loss": 3.6505,
      "step": 193
    },
    {
      "epoch": 1.2435897435897436,
      "grad_norm": 12.843352317810059,
      "learning_rate": 2.458548727494292e-07,
      "loss": 4.6761,
      "step": 194
    },
    {
      "epoch": 1.25,
      "grad_norm": 2.2034640312194824,
      "learning_rate": 1.7077534966650766e-07,
      "loss": 4.4309,
      "step": 195
    },
    {
      "epoch": 1.2564102564102564,
      "grad_norm": 2.317612409591675,
      "learning_rate": 1.0931863906127327e-07,
      "loss": 4.0386,
      "step": 196
    },
    {
      "epoch": 1.2628205128205128,
      "grad_norm": 2.2056784629821777,
      "learning_rate": 6.150154258476315e-08,
      "loss": 3.7649,
      "step": 197
    },
    {
      "epoch": 1.2692307692307692,
      "grad_norm": 2.3508360385894775,
      "learning_rate": 2.7337132953697554e-08,
      "loss": 3.9771,
      "step": 198
    },
    {
      "epoch": 1.2756410256410255,
      "grad_norm": 2.234356641769409,
      "learning_rate": 6.834750376549792e-09,
      "loss": 3.7029,
      "step": 199
    },
    {
      "epoch": 1.282051282051282,
      "grad_norm": 2.4603159427642822,
      "learning_rate": 0.0,
      "loss": 3.7426,
      "step": 200
    },
    {
      "epoch": 1.282051282051282,
      "eval_loss": 0.9246163368225098,
      "eval_runtime": 28.1649,
      "eval_samples_per_second": 9.338,
      "eval_steps_per_second": 2.343,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 4.639644277486387e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}