{
  "best_metric": 1.4024385213851929,
  "best_model_checkpoint": "./outputs/202410/no_safetensors/checkpoint/checkpoint-110000",
  "epoch": 3.5091956039749252,
  "eval_steps": 10000,
  "global_step": 110000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01595074410221237,
      "grad_norm": 108751.9921875,
      "learning_rate": 5e-06,
      "loss": 9.707,
      "step": 500
    },
    {
      "epoch": 0.03190148820442474,
      "grad_norm": 44635.21484375,
      "learning_rate": 1e-05,
      "loss": 7.8592,
      "step": 1000
    },
    {
      "epoch": 0.047852232306637106,
      "grad_norm": 56782.453125,
      "learning_rate": 1.5e-05,
      "loss": 7.2609,
      "step": 1500
    },
    {
      "epoch": 0.06380297640884948,
      "grad_norm": 96195.9140625,
      "learning_rate": 2e-05,
      "loss": 7.1215,
      "step": 2000
    },
    {
      "epoch": 0.07975372051106185,
      "grad_norm": 108495.3828125,
      "learning_rate": 2.5e-05,
      "loss": 7.0039,
      "step": 2500
    },
    {
      "epoch": 0.09570446461327421,
      "grad_norm": 69317.0625,
      "learning_rate": 3e-05,
      "loss": 6.8924,
      "step": 3000
    },
    {
      "epoch": 0.11165520871548658,
      "grad_norm": 112126.8203125,
      "learning_rate": 3.5e-05,
      "loss": 6.7924,
      "step": 3500
    },
    {
      "epoch": 0.12760595281769896,
      "grad_norm": 94684.1640625,
      "learning_rate": 4e-05,
      "loss": 6.6991,
      "step": 4000
    },
    {
      "epoch": 0.14355669691991133,
      "grad_norm": 99549.90625,
      "learning_rate": 4.5e-05,
      "loss": 6.6077,
      "step": 4500
    },
    {
      "epoch": 0.1595074410221237,
      "grad_norm": 100152.6171875,
      "learning_rate": 5e-05,
      "loss": 6.4957,
      "step": 5000
    },
    {
      "epoch": 0.17545818512433606,
      "grad_norm": 165780.328125,
      "learning_rate": 5.500000000000001e-05,
      "loss": 6.3014,
      "step": 5500
    },
    {
      "epoch": 0.19140892922654842,
      "grad_norm": 132947.90625,
      "learning_rate": 6e-05,
      "loss": 5.9146,
      "step": 6000
    },
    {
      "epoch": 0.2073596733287608,
      "grad_norm": 146624.34375,
      "learning_rate": 6.500000000000001e-05,
      "loss": 5.5084,
      "step": 6500
    },
    {
      "epoch": 0.22331041743097316,
      "grad_norm": 145966.1875,
      "learning_rate": 7e-05,
      "loss": 5.1444,
      "step": 7000
    },
    {
      "epoch": 0.23926116153318552,
      "grad_norm": 127509.96875,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.5906,
      "step": 7500
    },
    {
      "epoch": 0.2552119056353979,
      "grad_norm": 97949.8828125,
      "learning_rate": 8e-05,
      "loss": 3.9702,
      "step": 8000
    },
    {
      "epoch": 0.2711626497376103,
      "grad_norm": 89478.4296875,
      "learning_rate": 8.5e-05,
      "loss": 3.5577,
      "step": 8500
    },
    {
      "epoch": 0.28711339383982265,
      "grad_norm": 94187.8984375,
      "learning_rate": 9e-05,
      "loss": 3.302,
      "step": 9000
    },
    {
      "epoch": 0.303064137942035,
      "grad_norm": 83401.4765625,
      "learning_rate": 9.5e-05,
      "loss": 3.122,
      "step": 9500
    },
    {
      "epoch": 0.3190148820442474,
      "grad_norm": 80432.59375,
      "learning_rate": 0.0001,
      "loss": 2.9716,
      "step": 10000
    },
    {
      "epoch": 0.3190148820442474,
      "eval_loss": 2.7994558811187744,
      "eval_runtime": 4941.5974,
      "eval_samples_per_second": 202.986,
      "eval_steps_per_second": 1.586,
      "step": 10000
    },
    {
      "epoch": 0.33496562614645975,
      "grad_norm": 71825.7421875,
      "learning_rate": 9.994949494949496e-05,
      "loss": 2.8485,
      "step": 10500
    },
    {
      "epoch": 0.3509163702486721,
      "grad_norm": 76352.0625,
      "learning_rate": 9.98989898989899e-05,
      "loss": 2.7498,
      "step": 11000
    },
    {
      "epoch": 0.3668671143508845,
      "grad_norm": 74371.5703125,
      "learning_rate": 9.984848484848486e-05,
      "loss": 2.6733,
      "step": 11500
    },
    {
      "epoch": 0.38281785845309685,
      "grad_norm": 68137.9609375,
      "learning_rate": 9.97979797979798e-05,
      "loss": 2.5987,
      "step": 12000
    },
    {
      "epoch": 0.3987686025553092,
      "grad_norm": 64699.58984375,
      "learning_rate": 9.974747474747475e-05,
      "loss": 2.5405,
      "step": 12500
    },
    {
      "epoch": 0.4147193466575216,
      "grad_norm": 69361.3046875,
      "learning_rate": 9.96969696969697e-05,
      "loss": 2.4881,
      "step": 13000
    },
    {
      "epoch": 0.43067009075973395,
      "grad_norm": 69834.671875,
      "learning_rate": 9.964646464646466e-05,
      "loss": 2.446,
      "step": 13500
    },
    {
      "epoch": 0.4466208348619463,
      "grad_norm": 57975.98828125,
      "learning_rate": 9.95959595959596e-05,
      "loss": 2.3991,
      "step": 14000
    },
    {
      "epoch": 0.4625715789641587,
      "grad_norm": 67055.9375,
      "learning_rate": 9.954545454545455e-05,
      "loss": 2.3637,
      "step": 14500
    },
    {
      "epoch": 0.47852232306637105,
      "grad_norm": 62929.25390625,
      "learning_rate": 9.94949494949495e-05,
      "loss": 2.3294,
      "step": 15000
    },
    {
      "epoch": 0.4944730671685834,
      "grad_norm": 65925.8828125,
      "learning_rate": 9.944444444444446e-05,
      "loss": 2.3016,
      "step": 15500
    },
    {
      "epoch": 0.5104238112707958,
      "grad_norm": 59559.88671875,
      "learning_rate": 9.939393939393939e-05,
      "loss": 2.2717,
      "step": 16000
    },
    {
      "epoch": 0.5263745553730081,
      "grad_norm": 63280.40234375,
      "learning_rate": 9.934343434343435e-05,
      "loss": 2.2462,
      "step": 16500
    },
    {
      "epoch": 0.5423252994752206,
      "grad_norm": 61513.0859375,
      "learning_rate": 9.92929292929293e-05,
      "loss": 2.2214,
      "step": 17000
    },
    {
      "epoch": 0.5582760435774329,
      "grad_norm": 63240.92578125,
      "learning_rate": 9.924242424242425e-05,
      "loss": 2.2013,
      "step": 17500
    },
    {
      "epoch": 0.5742267876796453,
      "grad_norm": 61634.92578125,
      "learning_rate": 9.919191919191919e-05,
      "loss": 2.1798,
      "step": 18000
    },
    {
      "epoch": 0.5901775317818576,
      "grad_norm": 56590.8203125,
      "learning_rate": 9.914141414141415e-05,
      "loss": 2.1557,
      "step": 18500
    },
    {
      "epoch": 0.60612827588407,
      "grad_norm": 59655.97265625,
      "learning_rate": 9.909090909090911e-05,
      "loss": 2.14,
      "step": 19000
    },
    {
      "epoch": 0.6220790199862823,
      "grad_norm": 60380.125,
      "learning_rate": 9.904040404040404e-05,
      "loss": 2.123,
      "step": 19500
    },
    {
      "epoch": 0.6380297640884948,
      "grad_norm": 56893.875,
      "learning_rate": 9.8989898989899e-05,
      "loss": 2.1062,
      "step": 20000
    },
    {
      "epoch": 0.6380297640884948,
      "eval_loss": 2.007786512374878,
      "eval_runtime": 4985.2285,
      "eval_samples_per_second": 201.209,
      "eval_steps_per_second": 1.572,
      "step": 20000
    },
    {
      "epoch": 0.6539805081907071,
      "grad_norm": 60312.33203125,
      "learning_rate": 9.893939393939395e-05,
      "loss": 2.0889,
      "step": 20500
    },
    {
      "epoch": 0.6699312522929195,
      "grad_norm": 58157.28125,
      "learning_rate": 9.888888888888889e-05,
      "loss": 2.0776,
      "step": 21000
    },
    {
      "epoch": 0.6858819963951318,
      "grad_norm": 58377.234375,
      "learning_rate": 9.883838383838384e-05,
      "loss": 2.0646,
      "step": 21500
    },
    {
      "epoch": 0.7018327404973442,
      "grad_norm": 57768.578125,
      "learning_rate": 9.87878787878788e-05,
      "loss": 2.0493,
      "step": 22000
    },
    {
      "epoch": 0.7177834845995565,
      "grad_norm": 56948.41796875,
      "learning_rate": 9.873737373737374e-05,
      "loss": 2.0339,
      "step": 22500
    },
    {
      "epoch": 0.733734228701769,
      "grad_norm": 58923.421875,
      "learning_rate": 9.868686868686869e-05,
      "loss": 2.0256,
      "step": 23000
    },
    {
      "epoch": 0.7496849728039813,
      "grad_norm": 60381.23828125,
      "learning_rate": 9.863636363636364e-05,
      "loss": 2.0108,
      "step": 23500
    },
    {
      "epoch": 0.7656357169061937,
      "grad_norm": 55685.12890625,
      "learning_rate": 9.85858585858586e-05,
      "loss": 2.0011,
      "step": 24000
    },
    {
      "epoch": 0.781586461008406,
      "grad_norm": 55655.4609375,
      "learning_rate": 9.853535353535353e-05,
      "loss": 1.9899,
      "step": 24500
    },
    {
      "epoch": 0.7975372051106184,
      "grad_norm": 57943.70703125,
      "learning_rate": 9.848484848484849e-05,
      "loss": 1.9793,
      "step": 25000
    },
    {
      "epoch": 0.8134879492128307,
      "grad_norm": 56282.34375,
      "learning_rate": 9.843434343434344e-05,
      "loss": 1.9666,
      "step": 25500
    },
    {
      "epoch": 0.8294386933150432,
      "grad_norm": 56147.5390625,
      "learning_rate": 9.838383838383838e-05,
      "loss": 1.9575,
      "step": 26000
    },
    {
      "epoch": 0.8453894374172555,
      "grad_norm": 54766.921875,
      "learning_rate": 9.833333333333333e-05,
      "loss": 1.9508,
      "step": 26500
    },
    {
      "epoch": 0.8613401815194679,
      "grad_norm": 57243.0390625,
      "learning_rate": 9.828282828282829e-05,
      "loss": 1.9406,
      "step": 27000
    },
    {
      "epoch": 0.8772909256216802,
      "grad_norm": 57537.25,
      "learning_rate": 9.823232323232325e-05,
      "loss": 1.9295,
      "step": 27500
    },
    {
      "epoch": 0.8932416697238926,
      "grad_norm": 56535.60546875,
      "learning_rate": 9.818181818181818e-05,
      "loss": 1.9232,
      "step": 28000
    },
    {
      "epoch": 0.9091924138261049,
      "grad_norm": 60243.4375,
      "learning_rate": 9.813131313131314e-05,
      "loss": 1.9139,
      "step": 28500
    },
    {
      "epoch": 0.9251431579283174,
      "grad_norm": 54113.95703125,
      "learning_rate": 9.808080808080809e-05,
      "loss": 1.9067,
      "step": 29000
    },
    {
      "epoch": 0.9410939020305297,
      "grad_norm": 56388.44921875,
      "learning_rate": 9.803030303030303e-05,
      "loss": 1.8986,
      "step": 29500
    },
    {
      "epoch": 0.9570446461327421,
      "grad_norm": 55065.8203125,
      "learning_rate": 9.797979797979798e-05,
      "loss": 1.8912,
      "step": 30000
    },
    {
      "epoch": 0.9570446461327421,
      "eval_loss": 1.7991323471069336,
      "eval_runtime": 4913.8629,
      "eval_samples_per_second": 204.132,
      "eval_steps_per_second": 1.595,
      "step": 30000
    },
    {
      "epoch": 0.9729953902349545,
      "grad_norm": 55303.02734375,
      "learning_rate": 9.792929292929294e-05,
      "loss": 1.8815,
      "step": 30500
    },
    {
      "epoch": 0.9889461343371668,
      "grad_norm": 61240.37109375,
      "learning_rate": 9.787878787878789e-05,
      "loss": 1.876,
      "step": 31000
    },
    {
      "epoch": 1.0048968784393792,
      "grad_norm": 54453.8359375,
      "learning_rate": 9.782828282828283e-05,
      "loss": 1.8677,
      "step": 31500
    },
    {
      "epoch": 1.0208476225415917,
      "grad_norm": 53728.48828125,
      "learning_rate": 9.777777777777778e-05,
      "loss": 1.8582,
      "step": 32000
    },
    {
      "epoch": 1.0367983666438039,
      "grad_norm": 57865.578125,
      "learning_rate": 9.772727272727274e-05,
      "loss": 1.8532,
      "step": 32500
    },
    {
      "epoch": 1.0527491107460163,
      "grad_norm": 57046.4609375,
      "learning_rate": 9.767676767676767e-05,
      "loss": 1.8473,
      "step": 33000
    },
    {
      "epoch": 1.0686998548482287,
      "grad_norm": 57173.7265625,
      "learning_rate": 9.762626262626263e-05,
      "loss": 1.8394,
      "step": 33500
    },
    {
      "epoch": 1.0846505989504411,
      "grad_norm": 55721.00390625,
      "learning_rate": 9.757575757575758e-05,
      "loss": 1.8346,
      "step": 34000
    },
    {
      "epoch": 1.1006013430526533,
      "grad_norm": 56324.05859375,
      "learning_rate": 9.752525252525253e-05,
      "loss": 1.8319,
      "step": 34500
    },
    {
      "epoch": 1.1165520871548658,
      "grad_norm": 55807.09765625,
      "learning_rate": 9.747474747474747e-05,
      "loss": 1.8231,
      "step": 35000
    },
    {
      "epoch": 1.1325028312570782,
      "grad_norm": 53290.69140625,
      "learning_rate": 9.742424242424243e-05,
      "loss": 1.815,
      "step": 35500
    },
    {
      "epoch": 1.1484535753592906,
      "grad_norm": 55672.96875,
      "learning_rate": 9.737373737373738e-05,
      "loss": 1.8117,
      "step": 36000
    },
    {
      "epoch": 1.1644043194615028,
      "grad_norm": 53640.85546875,
      "learning_rate": 9.732323232323232e-05,
      "loss": 1.8069,
      "step": 36500
    },
    {
      "epoch": 1.1803550635637152,
      "grad_norm": 58046.828125,
      "learning_rate": 9.727272727272728e-05,
      "loss": 1.801,
      "step": 37000
    },
    {
      "epoch": 1.1963058076659276,
      "grad_norm": 57318.890625,
      "learning_rate": 9.722222222222223e-05,
      "loss": 1.7943,
      "step": 37500
    },
    {
      "epoch": 1.21225655176814,
      "grad_norm": 57652.68359375,
      "learning_rate": 9.717171717171718e-05,
      "loss": 1.7907,
      "step": 38000
    },
    {
      "epoch": 1.2282072958703523,
      "grad_norm": 54140.81640625,
      "learning_rate": 9.712121212121212e-05,
      "loss": 1.7837,
      "step": 38500
    },
    {
      "epoch": 1.2441580399725647,
      "grad_norm": 55963.265625,
      "learning_rate": 9.707070707070708e-05,
      "loss": 1.7804,
      "step": 39000
    },
    {
      "epoch": 1.260108784074777,
      "grad_norm": 56717.23828125,
      "learning_rate": 9.702020202020202e-05,
      "loss": 1.7779,
      "step": 39500
    },
    {
      "epoch": 1.2760595281769895,
      "grad_norm": 54491.91796875,
      "learning_rate": 9.696969696969698e-05,
      "loss": 1.7704,
      "step": 40000
    },
    {
      "epoch": 1.2760595281769895,
      "eval_loss": 1.684906005859375,
      "eval_runtime": 4951.5896,
      "eval_samples_per_second": 202.576,
      "eval_steps_per_second": 1.583,
      "step": 40000
    },
    {
      "epoch": 1.2920262230233042,
      "grad_norm": 53837.6640625,
      "learning_rate": 9.691919191919192e-05,
      "loss": 1.7651,
      "step": 40500
    },
    {
      "epoch": 1.3079769671255164,
      "grad_norm": 54601.4765625,
      "learning_rate": 9.686868686868688e-05,
      "loss": 1.759,
      "step": 41000
    },
    {
      "epoch": 1.3239277112277288,
      "grad_norm": 52770.5078125,
      "learning_rate": 9.681818181818181e-05,
      "loss": 1.7568,
      "step": 41500
    },
    {
      "epoch": 1.3398784553299412,
      "grad_norm": 56085.59765625,
      "learning_rate": 9.676767676767677e-05,
      "loss": 1.7522,
      "step": 42000
    },
    {
      "epoch": 1.3558291994321534,
      "grad_norm": 55068.359375,
      "learning_rate": 9.671717171717172e-05,
      "loss": 1.7506,
      "step": 42500
    },
    {
      "epoch": 1.3717799435343658,
      "grad_norm": 57091.0546875,
      "learning_rate": 9.666666666666667e-05,
      "loss": 1.7419,
      "step": 43000
    },
    {
      "epoch": 1.3877306876365783,
      "grad_norm": 52158.63671875,
      "learning_rate": 9.661616161616161e-05,
      "loss": 1.7395,
      "step": 43500
    },
    {
      "epoch": 1.4036814317387907,
      "grad_norm": 54727.2890625,
      "learning_rate": 9.656565656565657e-05,
      "loss": 1.7351,
      "step": 44000
    },
    {
      "epoch": 1.419632175841003,
      "grad_norm": 59289.56640625,
      "learning_rate": 9.651515151515152e-05,
      "loss": 1.731,
      "step": 44500
    },
    {
      "epoch": 1.4355829199432153,
      "grad_norm": 57592.5546875,
      "learning_rate": 9.646464646464647e-05,
      "loss": 1.7268,
      "step": 45000
    },
    {
      "epoch": 1.4515336640454277,
      "grad_norm": 56016.44921875,
      "learning_rate": 9.641414141414143e-05,
      "loss": 1.723,
      "step": 45500
    },
    {
      "epoch": 1.4674844081476401,
      "grad_norm": 55521.9765625,
      "learning_rate": 9.636363636363637e-05,
      "loss": 1.7171,
      "step": 46000
    },
    {
      "epoch": 1.4834351522498523,
      "grad_norm": 56532.88671875,
      "learning_rate": 9.631313131313132e-05,
      "loss": 1.7146,
      "step": 46500
    },
    {
      "epoch": 1.4993858963520648,
      "grad_norm": 53762.78515625,
      "learning_rate": 9.626262626262627e-05,
      "loss": 1.7107,
      "step": 47000
    },
    {
      "epoch": 1.5153366404542772,
      "grad_norm": 54982.08203125,
      "learning_rate": 9.621212121212123e-05,
      "loss": 1.7085,
      "step": 47500
    },
    {
      "epoch": 1.5312873845564896,
      "grad_norm": 57135.71484375,
      "learning_rate": 9.616161616161616e-05,
      "loss": 1.7063,
      "step": 48000
    },
    {
      "epoch": 1.547238128658702,
      "grad_norm": 55469.52734375,
      "learning_rate": 9.611111111111112e-05,
      "loss": 1.7021,
      "step": 48500
    },
    {
      "epoch": 1.5631888727609144,
      "grad_norm": 55527.140625,
      "learning_rate": 9.606060606060606e-05,
      "loss": 1.6959,
      "step": 49000
    },
    {
      "epoch": 1.5791396168631266,
      "grad_norm": 55039.515625,
      "learning_rate": 9.601010101010101e-05,
      "loss": 1.6953,
      "step": 49500
    },
    {
      "epoch": 1.595090360965339,
      "grad_norm": 58584.22265625,
      "learning_rate": 9.595959595959596e-05,
      "loss": 1.6916,
      "step": 50000
    },
    {
      "epoch": 1.595090360965339,
      "eval_loss": 1.60930597782135,
      "eval_runtime": 4918.9878,
      "eval_samples_per_second": 203.919,
      "eval_steps_per_second": 1.593,
      "step": 50000
    },
    {
      "epoch": 1.6110411050675513,
      "grad_norm": 55009.78125,
      "learning_rate": 9.590909090909092e-05,
      "loss": 1.685,
      "step": 50500
    },
    {
      "epoch": 1.6269918491697637,
      "grad_norm": 53817.55078125,
      "learning_rate": 9.585858585858586e-05,
      "loss": 1.684,
      "step": 51000
    },
    {
      "epoch": 1.6429425932719761,
      "grad_norm": 53155.3359375,
      "learning_rate": 9.580808080808081e-05,
      "loss": 1.6813,
      "step": 51500
    },
    {
      "epoch": 1.6588933373741885,
      "grad_norm": 55288.33984375,
      "learning_rate": 9.575757575757576e-05,
      "loss": 1.6776,
      "step": 52000
    },
    {
      "epoch": 1.674844081476401,
      "grad_norm": 58538.25,
      "learning_rate": 9.570707070707072e-05,
      "loss": 1.6746,
      "step": 52500
    },
    {
      "epoch": 1.6907948255786134,
      "grad_norm": 54227.25390625,
      "learning_rate": 9.565656565656566e-05,
      "loss": 1.6715,
      "step": 53000
    },
    {
      "epoch": 1.7067455696808256,
      "grad_norm": 56011.28125,
      "learning_rate": 9.560606060606061e-05,
      "loss": 1.6701,
      "step": 53500
    },
    {
      "epoch": 1.722696313783038,
      "grad_norm": 51203.140625,
      "learning_rate": 9.555555555555557e-05,
      "loss": 1.6695,
      "step": 54000
    },
    {
      "epoch": 1.7386470578852502,
      "grad_norm": 53641.3203125,
      "learning_rate": 9.550505050505051e-05,
      "loss": 1.6613,
      "step": 54500
    },
    {
      "epoch": 1.7545978019874626,
      "grad_norm": 55869.0234375,
      "learning_rate": 9.545454545454546e-05,
      "loss": 1.6598,
      "step": 55000
    },
    {
      "epoch": 1.770548546089675,
      "grad_norm": 54982.5546875,
      "learning_rate": 9.540404040404041e-05,
      "loss": 1.6595,
      "step": 55500
    },
    {
      "epoch": 1.7864992901918875,
      "grad_norm": 55537.86328125,
      "learning_rate": 9.535353535353537e-05,
      "loss": 1.6544,
      "step": 56000
    },
    {
      "epoch": 1.8024500342941,
      "grad_norm": 52897.34375,
      "learning_rate": 9.53030303030303e-05,
      "loss": 1.6512,
      "step": 56500
    },
    {
      "epoch": 1.8184007783963123,
      "grad_norm": 55306.94921875,
      "learning_rate": 9.525252525252526e-05,
      "loss": 1.6493,
      "step": 57000
    },
    {
      "epoch": 1.8343515224985245,
      "grad_norm": 55051.29296875,
      "learning_rate": 9.52020202020202e-05,
      "loss": 1.6453,
      "step": 57500
    },
    {
      "epoch": 1.850302266600737,
      "grad_norm": 54118.21484375,
      "learning_rate": 9.515151515151515e-05,
      "loss": 1.6441,
      "step": 58000
    },
    {
      "epoch": 1.8662530107029491,
      "grad_norm": 56088.76171875,
      "learning_rate": 9.51010101010101e-05,
      "loss": 1.6429,
      "step": 58500
    },
    {
      "epoch": 1.8822037548051616,
      "grad_norm": 52600.8359375,
      "learning_rate": 9.505050505050506e-05,
      "loss": 1.636,
      "step": 59000
    },
    {
      "epoch": 1.898154498907374,
      "grad_norm": 55023.9375,
      "learning_rate": 9.5e-05,
      "loss": 1.6333,
      "step": 59500
    },
    {
      "epoch": 1.9141052430095864,
      "grad_norm": 54295.30859375,
      "learning_rate": 9.494949494949495e-05,
      "loss": 1.6335,
      "step": 60000
    },
    {
      "epoch": 1.9141052430095864,
      "eval_loss": 1.5532509088516235,
      "eval_runtime": 4919.5325,
      "eval_samples_per_second": 203.896,
      "eval_steps_per_second": 1.593,
      "step": 60000
    },
    {
      "epoch": 1.9300559871117988,
      "grad_norm": 55173.84765625,
      "learning_rate": 9.48989898989899e-05,
      "loss": 1.63,
      "step": 60500
    },
    {
      "epoch": 1.9460067312140112,
      "grad_norm": 53612.4921875,
      "learning_rate": 9.484848484848486e-05,
      "loss": 1.6286,
      "step": 61000
    },
    {
      "epoch": 1.9619574753162237,
      "grad_norm": 55060.9140625,
      "learning_rate": 9.47979797979798e-05,
      "loss": 1.6263,
      "step": 61500
    },
    {
      "epoch": 1.9779082194184359,
      "grad_norm": 54993.5625,
      "learning_rate": 9.474747474747475e-05,
      "loss": 1.6231,
      "step": 62000
    },
    {
      "epoch": 1.9938589635206483,
      "grad_norm": 55949.11328125,
      "learning_rate": 9.469696969696971e-05,
      "loss": 1.6228,
      "step": 62500
    },
    {
      "epoch": 2.0098097076228605,
      "grad_norm": 54883.53515625,
      "learning_rate": 9.464646464646464e-05,
      "loss": 1.6197,
      "step": 63000
    },
    {
      "epoch": 2.025760451725073,
      "grad_norm": 57476.609375,
      "learning_rate": 9.45959595959596e-05,
      "loss": 1.6145,
      "step": 63500
    },
    {
      "epoch": 2.0417111958272853,
      "grad_norm": 55516.81640625,
      "learning_rate": 9.454545454545455e-05,
      "loss": 1.6126,
      "step": 64000
    },
    {
      "epoch": 2.0576619399294978,
      "grad_norm": 53755.71484375,
      "learning_rate": 9.449494949494951e-05,
      "loss": 1.6109,
      "step": 64500
    },
    {
      "epoch": 2.07361268403171,
      "grad_norm": 54177.87890625,
      "learning_rate": 9.444444444444444e-05,
      "loss": 1.6105,
      "step": 65000
    },
    {
      "epoch": 2.0895634281339226,
      "grad_norm": 56828.4765625,
      "learning_rate": 9.43939393939394e-05,
      "loss": 1.6075,
      "step": 65500
    },
    {
      "epoch": 2.105514172236135,
      "grad_norm": 55464.76171875,
      "learning_rate": 9.434343434343435e-05,
      "loss": 1.606,
      "step": 66000
    },
    {
      "epoch": 2.121464916338347,
      "grad_norm": 56928.1015625,
      "learning_rate": 9.42929292929293e-05,
      "loss": 1.6023,
      "step": 66500
    },
    {
      "epoch": 2.1374156604405594,
      "grad_norm": 51041.0,
      "learning_rate": 9.424242424242424e-05,
      "loss": 1.6,
      "step": 67000
    },
    {
      "epoch": 2.153366404542772,
      "grad_norm": 56379.828125,
      "learning_rate": 9.41919191919192e-05,
      "loss": 1.6003,
      "step": 67500
    },
    {
      "epoch": 2.1693171486449843,
      "grad_norm": 55763.93359375,
      "learning_rate": 9.414141414141415e-05,
      "loss": 1.596,
      "step": 68000
    },
    {
      "epoch": 2.1852678927471967,
      "grad_norm": 53785.359375,
      "learning_rate": 9.40909090909091e-05,
      "loss": 1.5932,
      "step": 68500
    },
    {
      "epoch": 2.201218636849409,
      "grad_norm": 56003.0703125,
      "learning_rate": 9.404040404040404e-05,
      "loss": 1.5928,
      "step": 69000
    },
    {
      "epoch": 2.2171693809516215,
      "grad_norm": 55811.99609375,
      "learning_rate": 9.3989898989899e-05,
      "loss": 1.5919,
      "step": 69500
    },
    {
      "epoch": 2.233120125053834,
      "grad_norm": 56307.57421875,
      "learning_rate": 9.393939393939395e-05,
      "loss": 1.5869,
      "step": 70000
    },
    {
      "epoch": 2.233120125053834,
      "eval_loss": 1.5101096630096436,
      "eval_runtime": 4917.8928,
      "eval_samples_per_second": 203.964,
      "eval_steps_per_second": 1.594,
      "step": 70000
    },
    {
      "epoch": 2.249070869156046,
      "grad_norm": 53560.9296875,
      "learning_rate": 9.388888888888889e-05,
      "loss": 1.5883,
      "step": 70500
    },
    {
      "epoch": 2.2650216132582583,
      "grad_norm": 56536.40625,
      "learning_rate": 9.383838383838385e-05,
      "loss": 1.585,
      "step": 71000
    },
    {
      "epoch": 2.2809723573604708,
      "grad_norm": 54454.96875,
      "learning_rate": 9.378787878787879e-05,
      "loss": 1.582,
      "step": 71500
    },
    {
      "epoch": 2.296923101462683,
      "grad_norm": 55888.09375,
      "learning_rate": 9.373737373737375e-05,
      "loss": 1.5776,
      "step": 72000
    },
    {
      "epoch": 2.3128738455648956,
      "grad_norm": 55370.46484375,
      "learning_rate": 9.368686868686869e-05,
      "loss": 1.5781,
      "step": 72500
    },
    {
      "epoch": 2.328824589667108,
      "grad_norm": 56668.328125,
      "learning_rate": 9.363636363636364e-05,
      "loss": 1.5779,
      "step": 73000
    },
    {
      "epoch": 2.3447753337693205,
      "grad_norm": 56674.85546875,
      "learning_rate": 9.358585858585858e-05,
      "loss": 1.5724,
      "step": 73500
    },
    {
      "epoch": 2.360726077871533,
      "grad_norm": 59070.734375,
      "learning_rate": 9.353535353535354e-05,
      "loss": 1.5737,
      "step": 74000
    },
    {
      "epoch": 2.376676821973745,
      "grad_norm": 55701.37109375,
      "learning_rate": 9.348484848484849e-05,
      "loss": 1.5702,
      "step": 74500
    },
    {
      "epoch": 2.3926275660759573,
      "grad_norm": 54837.890625,
      "learning_rate": 9.343434343434344e-05,
      "loss": 1.5691,
      "step": 75000
    },
    {
      "epoch": 2.4085783101781697,
      "grad_norm": 55847.98046875,
      "learning_rate": 9.338383838383838e-05,
      "loss": 1.5692,
      "step": 75500
    },
    {
      "epoch": 2.424529054280382,
      "grad_norm": 53633.03125,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.5639,
      "step": 76000
    },
    {
      "epoch": 2.4404797983825945,
      "grad_norm": 55944.12890625,
      "learning_rate": 9.328282828282829e-05,
      "loss": 1.5664,
      "step": 76500
    },
    {
      "epoch": 2.456430542484807,
      "grad_norm": 53979.30859375,
      "learning_rate": 9.323232323232324e-05,
      "loss": 1.5635,
      "step": 77000
    },
    {
      "epoch": 2.4723812865870194,
      "grad_norm": 56014.97265625,
      "learning_rate": 9.318181818181818e-05,
      "loss": 1.5601,
      "step": 77500
    },
    {
      "epoch": 2.488332030689232,
      "grad_norm": 55291.9140625,
      "learning_rate": 9.313131313131314e-05,
      "loss": 1.5618,
      "step": 78000
    },
    {
      "epoch": 2.5042827747914442,
      "grad_norm": 53215.24609375,
      "learning_rate": 9.308080808080809e-05,
      "loss": 1.5576,
      "step": 78500
    },
    {
      "epoch": 2.520233518893656,
      "grad_norm": 56197.3203125,
      "learning_rate": 9.303030303030303e-05,
      "loss": 1.554,
      "step": 79000
    },
    {
      "epoch": 2.5361842629958686,
      "grad_norm": 55106.9765625,
      "learning_rate": 9.2979797979798e-05,
      "loss": 1.5545,
      "step": 79500
    },
    {
      "epoch": 2.552135007098081,
      "grad_norm": 54552.08984375,
      "learning_rate": 9.292929292929293e-05,
      "loss": 1.5529,
      "step": 80000
    },
    {
      "epoch": 2.552135007098081,
      "eval_loss": 1.4744161367416382,
      "eval_runtime": 4899.8032,
      "eval_samples_per_second": 204.717,
      "eval_steps_per_second": 1.599,
      "step": 80000
    },
    {
      "epoch": 2.5681017019443955,
      "grad_norm": 56671.71875,
      "learning_rate": 9.287878787878789e-05,
      "loss": 1.5516,
      "step": 80500
    },
    {
      "epoch": 2.5840524460466083,
      "grad_norm": 54676.5078125,
      "learning_rate": 9.282828282828283e-05,
      "loss": 1.5501,
      "step": 81000
    },
    {
      "epoch": 2.6000031901488203,
      "grad_norm": 56587.88671875,
      "learning_rate": 9.277777777777778e-05,
      "loss": 1.549,
      "step": 81500
    },
    {
      "epoch": 2.6159539342510327,
      "grad_norm": 56696.6484375,
      "learning_rate": 9.272727272727273e-05,
      "loss": 1.5448,
      "step": 82000
    },
    {
      "epoch": 2.631904678353245,
      "grad_norm": 55145.359375,
      "learning_rate": 9.267676767676769e-05,
      "loss": 1.5439,
      "step": 82500
    },
    {
      "epoch": 2.6478554224554576,
      "grad_norm": 55258.8828125,
      "learning_rate": 9.262626262626263e-05,
      "loss": 1.5461,
      "step": 83000
    },
    {
      "epoch": 2.66380616655767,
      "grad_norm": 55989.4921875,
      "learning_rate": 9.257575757575758e-05,
      "loss": 1.5423,
      "step": 83500
    },
    {
      "epoch": 2.6797569106598824,
      "grad_norm": 54569.66015625,
      "learning_rate": 9.252525252525253e-05,
      "loss": 1.5432,
      "step": 84000
    },
    {
      "epoch": 2.695707654762095,
      "grad_norm": 56487.32421875,
      "learning_rate": 9.247474747474749e-05,
      "loss": 1.5406,
      "step": 84500
    },
    {
      "epoch": 2.711658398864307,
      "grad_norm": 55735.38671875,
      "learning_rate": 9.242424242424242e-05,
      "loss": 1.5385,
      "step": 85000
    },
    {
      "epoch": 2.7276091429665192,
      "grad_norm": 55246.734375,
      "learning_rate": 9.237373737373738e-05,
      "loss": 1.5385,
      "step": 85500
    },
    {
      "epoch": 2.7435598870687317,
      "grad_norm": 54426.76171875,
      "learning_rate": 9.232323232323232e-05,
      "loss": 1.5354,
      "step": 86000
    },
    {
      "epoch": 2.759510631170944,
      "grad_norm": 56496.05859375,
      "learning_rate": 9.227272727272727e-05,
      "loss": 1.5354,
      "step": 86500
    },
    {
      "epoch": 2.7754613752731565,
      "grad_norm": 54483.66796875,
      "learning_rate": 9.222222222222223e-05,
      "loss": 1.5314,
      "step": 87000
    },
    {
      "epoch": 2.791412119375369,
      "grad_norm": 56842.0,
      "learning_rate": 9.217171717171718e-05,
      "loss": 1.5307,
      "step": 87500
    },
    {
      "epoch": 2.8073628634775813,
      "grad_norm": 55707.21875,
      "learning_rate": 9.212121212121214e-05,
      "loss": 1.5299,
      "step": 88000
    },
    {
      "epoch": 2.8233136075797933,
      "grad_norm": 54965.58984375,
      "learning_rate": 9.207070707070707e-05,
      "loss": 1.5292,
      "step": 88500
    },
    {
      "epoch": 2.839264351682006,
      "grad_norm": 54280.4140625,
      "learning_rate": 9.202020202020203e-05,
      "loss": 1.5281,
      "step": 89000
    },
    {
      "epoch": 2.855215095784218,
      "grad_norm": 56317.328125,
      "learning_rate": 9.196969696969698e-05,
      "loss": 1.5292,
      "step": 89500
    },
    {
      "epoch": 2.8711658398864306,
      "grad_norm": 56429.265625,
      "learning_rate": 9.191919191919192e-05,
      "loss": 1.5248,
      "step": 90000
    },
    {
      "epoch": 2.8711658398864306,
      "eval_loss": 1.4486085176467896,
      "eval_runtime": 4949.3767,
      "eval_samples_per_second": 202.667,
      "eval_steps_per_second": 1.583,
      "step": 90000
    },
    {
      "epoch": 2.887116583988643,
      "grad_norm": 60500.609375,
      "learning_rate": 9.186868686868687e-05,
      "loss": 1.5244,
      "step": 90500
    },
    {
      "epoch": 2.9030673280908554,
      "grad_norm": 56278.77734375,
      "learning_rate": 9.181818181818183e-05,
      "loss": 1.5228,
      "step": 91000
    },
    {
      "epoch": 2.919018072193068,
      "grad_norm": 55179.0859375,
      "learning_rate": 9.176767676767677e-05,
      "loss": 1.5228,
      "step": 91500
    },
    {
      "epoch": 2.9349688162952803,
      "grad_norm": 58535.69140625,
      "learning_rate": 9.171717171717172e-05,
      "loss": 1.5207,
      "step": 92000
    },
    {
      "epoch": 2.9509195603974927,
      "grad_norm": 56315.96484375,
      "learning_rate": 9.166666666666667e-05,
      "loss": 1.5205,
      "step": 92500
    },
    {
      "epoch": 2.9668703044997047,
      "grad_norm": 57173.87109375,
      "learning_rate": 9.161616161616163e-05,
      "loss": 1.5165,
      "step": 93000
    },
    {
      "epoch": 2.9828210486019175,
      "grad_norm": 58435.5,
      "learning_rate": 9.156565656565656e-05,
      "loss": 1.516,
      "step": 93500
    },
    {
      "epoch": 2.9987717927041295,
      "grad_norm": 55689.07421875,
      "learning_rate": 9.151515151515152e-05,
      "loss": 1.5155,
      "step": 94000
    },
    {
      "epoch": 3.014722536806342,
      "grad_norm": 55691.28515625,
      "learning_rate": 9.146464646464647e-05,
      "loss": 1.5124,
      "step": 94500
    },
    {
      "epoch": 3.0306732809085544,
      "grad_norm": 55951.5546875,
      "learning_rate": 9.141414141414141e-05,
      "loss": 1.5098,
      "step": 95000
    },
    {
      "epoch": 3.046624025010767,
      "grad_norm": 56781.6328125,
      "learning_rate": 9.136363636363637e-05,
      "loss": 1.5107,
      "step": 95500
    },
    {
      "epoch": 3.062574769112979,
      "grad_norm": 56111.234375,
      "learning_rate": 9.131313131313132e-05,
      "loss": 1.5072,
      "step": 96000
    },
    {
      "epoch": 3.0785255132151916,
      "grad_norm": 55225.51171875,
      "learning_rate": 9.126262626262627e-05,
      "loss": 1.5089,
      "step": 96500
    },
    {
      "epoch": 3.094476257317404,
      "grad_norm": 57983.26171875,
      "learning_rate": 9.121212121212121e-05,
      "loss": 1.5068,
      "step": 97000
    },
    {
      "epoch": 3.110427001419616,
      "grad_norm": 55611.953125,
      "learning_rate": 9.116161616161617e-05,
      "loss": 1.5039,
      "step": 97500
    },
    {
      "epoch": 3.1263777455218285,
      "grad_norm": 56500.25390625,
      "learning_rate": 9.111111111111112e-05,
      "loss": 1.5023,
      "step": 98000
    },
    {
      "epoch": 3.142328489624041,
      "grad_norm": 55070.7578125,
      "learning_rate": 9.106060606060606e-05,
      "loss": 1.5025,
      "step": 98500
    },
    {
      "epoch": 3.1582792337262533,
      "grad_norm": 56306.3203125,
      "learning_rate": 9.101010101010101e-05,
      "loss": 1.501,
      "step": 99000
    },
    {
      "epoch": 3.1742299778284657,
      "grad_norm": 56296.40234375,
      "learning_rate": 9.095959595959597e-05,
      "loss": 1.4999,
      "step": 99500
    },
    {
      "epoch": 3.190180721930678,
      "grad_norm": 56137.7265625,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.5015,
      "step": 100000
    },
    {
      "epoch": 3.190180721930678,
      "eval_loss": 1.4243189096450806,
      "eval_runtime": 4946.6072,
      "eval_samples_per_second": 202.78,
      "eval_steps_per_second": 1.584,
      "step": 100000
    },
    {
      "epoch": 3.2061314660328906,
      "grad_norm": 57145.66796875,
      "learning_rate": 9.085858585858586e-05,
      "loss": 1.4976,
      "step": 100500
    },
    {
      "epoch": 3.222082210135103,
      "grad_norm": 55889.25,
      "learning_rate": 9.080808080808081e-05,
      "loss": 1.4946,
      "step": 101000
    },
    {
      "epoch": 3.238032954237315,
      "grad_norm": 54433.96875,
      "learning_rate": 9.075757575757577e-05,
      "loss": 1.4985,
      "step": 101500
    },
    {
      "epoch": 3.2539836983395274,
      "grad_norm": 59956.953125,
      "learning_rate": 9.07070707070707e-05,
      "loss": 1.4926,
      "step": 102000
    },
    {
      "epoch": 3.26993444244174,
      "grad_norm": 55148.5703125,
      "learning_rate": 9.065656565656566e-05,
      "loss": 1.4935,
      "step": 102500
    },
    {
      "epoch": 3.2858851865439522,
      "grad_norm": 58131.62890625,
      "learning_rate": 9.060606060606061e-05,
      "loss": 1.4936,
      "step": 103000
    },
    {
      "epoch": 3.3018359306461647,
      "grad_norm": 61794.17578125,
      "learning_rate": 9.055555555555556e-05,
      "loss": 1.4922,
      "step": 103500
    },
    {
      "epoch": 3.317786674748377,
      "grad_norm": 56916.46875,
      "learning_rate": 9.050505050505052e-05,
      "loss": 1.4915,
      "step": 104000
    },
    {
      "epoch": 3.3337374188505895,
      "grad_norm": 56791.9765625,
      "learning_rate": 9.045454545454546e-05,
      "loss": 1.4885,
      "step": 104500
    },
    {
      "epoch": 3.349688162952802,
      "grad_norm": 59157.26171875,
      "learning_rate": 9.040404040404041e-05,
      "loss": 1.4892,
      "step": 105000
    },
    {
      "epoch": 3.365638907055014,
      "grad_norm": 57222.37890625,
      "learning_rate": 9.035353535353535e-05,
      "loss": 1.4896,
      "step": 105500
    },
    {
      "epoch": 3.3815896511572263,
      "grad_norm": 59154.6171875,
      "learning_rate": 9.030303030303031e-05,
      "loss": 1.4846,
      "step": 106000
    },
    {
      "epoch": 3.3975403952594387,
      "grad_norm": 55996.48046875,
      "learning_rate": 9.025252525252526e-05,
      "loss": 1.4866,
      "step": 106500
    },
    {
      "epoch": 3.413491139361651,
      "grad_norm": 58967.2578125,
      "learning_rate": 9.02020202020202e-05,
      "loss": 1.4846,
      "step": 107000
    },
    {
      "epoch": 3.4294418834638636,
      "grad_norm": 58440.421875,
      "learning_rate": 9.015151515151515e-05,
      "loss": 1.4851,
      "step": 107500
    },
    {
      "epoch": 3.445392627566076,
      "grad_norm": 55482.94140625,
      "learning_rate": 9.010101010101011e-05,
      "loss": 1.4862,
      "step": 108000
    },
    {
      "epoch": 3.4613433716682884,
      "grad_norm": 59205.22265625,
      "learning_rate": 9.005050505050505e-05,
      "loss": 1.4829,
      "step": 108500
    },
    {
      "epoch": 3.477294115770501,
      "grad_norm": 54196.10546875,
      "learning_rate": 9e-05,
      "loss": 1.482,
      "step": 109000
    },
    {
      "epoch": 3.4932448598727133,
      "grad_norm": 54923.30078125,
      "learning_rate": 8.994949494949495e-05,
      "loss": 1.4797,
      "step": 109500
    },
    {
      "epoch": 3.5091956039749252,
      "grad_norm": 54844.94140625,
      "learning_rate": 8.98989898989899e-05,
      "loss": 1.4788,
      "step": 110000
    },
    {
      "epoch": 3.5091956039749252,
      "eval_loss": 1.4024385213851929,
      "eval_runtime": 4946.3399,
      "eval_samples_per_second": 202.791,
      "eval_steps_per_second": 1.584,
      "step": 110000
    }
  ],
  "logging_steps": 500,
  "max_steps": 1000000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 32,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.413478046369151e+18,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}