{
  "best_global_step": 45000,
  "best_metric": 1.0206714868545532,
  "best_model_checkpoint": "/workspace/MT_Multilingual_En/checkpoint-45000",
  "epoch": 3.0,
  "eval_steps": 5000,
  "global_step": 84789,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003538202637287791,
      "grad_norm": 3.90625,
      "learning_rate": 4.9977515176118345e-05,
      "loss": 2.4129154205322267,
      "num_input_tokens_seen": 2861504,
      "step": 10,
      "train_runtime": 107.8109,
      "train_tokens_per_second": 26541.883
    },
    {
      "epoch": 0.0007076405274575581,
      "grad_norm": 2.21875,
      "learning_rate": 4.9952567580506e-05,
      "loss": 1.739237403869629,
      "num_input_tokens_seen": 5659264,
      "step": 20,
      "train_runtime": 201.23,
      "train_tokens_per_second": 28123.361
    },
    {
      "epoch": 0.0010614607911863373,
      "grad_norm": 2.21875,
      "learning_rate": 4.992765730738634e-05,
      "loss": 1.6574527740478515,
      "num_input_tokens_seen": 8484416,
      "step": 30,
      "train_runtime": 300.0843,
      "train_tokens_per_second": 28273.445
    },
    {
      "epoch": 0.0014152810549151163,
      "grad_norm": 1.9140625,
      "learning_rate": 4.9902784263792476e-05,
      "loss": 1.6026153564453125,
      "num_input_tokens_seen": 11342464,
      "step": 40,
      "train_runtime": 397.2987,
      "train_tokens_per_second": 28548.959
    },
    {
      "epoch": 0.0017691013186438955,
      "grad_norm": 1.9921875,
      "learning_rate": 4.987794835708133e-05,
      "loss": 1.578458309173584,
      "num_input_tokens_seen": 14208000,
      "step": 50,
      "train_runtime": 495.7456,
      "train_tokens_per_second": 28659.86
    },
    {
      "epoch": 0.0021229215823726747,
      "grad_norm": 2.0625,
      "learning_rate": 4.985314949493234e-05,
      "loss": 1.5477357864379884,
      "num_input_tokens_seen": 17070848,
      "step": 60,
      "train_runtime": 593.7889,
      "train_tokens_per_second": 28749.017
    },
    {
      "epoch": 0.0024767418461014534,
      "grad_norm": 1.8515625,
      "learning_rate": 4.982838758534584e-05,
      "loss": 1.5277509689331055,
      "num_input_tokens_seen": 19876352,
      "step": 70,
      "train_runtime": 688.806,
      "train_tokens_per_second": 28856.24
    },
    {
      "epoch": 0.0028305621098302326,
      "grad_norm": 1.953125,
      "learning_rate": 4.980366253664179e-05,
      "loss": 1.5297769546508788,
      "num_input_tokens_seen": 22738816,
      "step": 80,
      "train_runtime": 787.0004,
      "train_tokens_per_second": 28893.017
    },
    {
      "epoch": 0.0031843823735590118,
      "grad_norm": 1.8671875,
      "learning_rate": 4.977897425745825e-05,
      "loss": 1.513206386566162,
      "num_input_tokens_seen": 25550720,
      "step": 90,
      "train_runtime": 885.1696,
      "train_tokens_per_second": 28865.337
    },
    {
      "epoch": 0.003538202637287791,
      "grad_norm": 2.015625,
      "learning_rate": 4.975432265674997e-05,
      "loss": 1.5171786308288575,
      "num_input_tokens_seen": 28315520,
      "step": 100,
      "train_runtime": 980.0312,
      "train_tokens_per_second": 28892.468
    },
    {
      "epoch": 0.0038920229010165697,
      "grad_norm": 1.7421875,
      "learning_rate": 4.972970764378705e-05,
      "loss": 1.4735165596008302,
      "num_input_tokens_seen": 31176512,
      "step": 110,
      "train_runtime": 1078.185,
      "train_tokens_per_second": 28915.734
    },
    {
      "epoch": 0.004245843164745349,
      "grad_norm": 1.78125,
      "learning_rate": 4.970512912815344e-05,
      "loss": 1.4906696319580077,
      "num_input_tokens_seen": 34090624,
      "step": 120,
      "train_runtime": 1181.1928,
      "train_tokens_per_second": 28861.184
    },
    {
      "epoch": 0.004599663428474128,
      "grad_norm": 1.7265625,
      "learning_rate": 4.968058701974564e-05,
      "loss": 1.4680511474609375,
      "num_input_tokens_seen": 36877632,
      "step": 130,
      "train_runtime": 1275.3019,
      "train_tokens_per_second": 28916.785
    },
    {
      "epoch": 0.004953483692202907,
      "grad_norm": 1.8203125,
      "learning_rate": 4.96560812287712e-05,
      "loss": 1.4557507514953614,
      "num_input_tokens_seen": 39719808,
      "step": 140,
      "train_runtime": 1374.6852,
      "train_tokens_per_second": 28893.748
    },
    {
      "epoch": 0.005307303955931686,
      "grad_norm": 1.7578125,
      "learning_rate": 4.963161166574748e-05,
      "loss": 1.4658089637756349,
      "num_input_tokens_seen": 42594048,
      "step": 150,
      "train_runtime": 1474.8059,
      "train_tokens_per_second": 28881.121
    },
    {
      "epoch": 0.005661124219660465,
      "grad_norm": 1.7109375,
      "learning_rate": 4.960717824150013e-05,
      "loss": 1.4383573532104492,
      "num_input_tokens_seen": 45422080,
      "step": 160,
      "train_runtime": 1569.9766,
      "train_tokens_per_second": 28931.692
    },
    {
      "epoch": 0.006014944483389244,
      "grad_norm": 1.8359375,
      "learning_rate": 4.9582780867161893e-05,
      "loss": 1.4379766464233399,
      "num_input_tokens_seen": 48225408,
      "step": 170,
      "train_runtime": 1664.588,
      "train_tokens_per_second": 28971.378
    },
    {
      "epoch": 0.0063687647471180235,
      "grad_norm": 1.71875,
      "learning_rate": 4.955841945417105e-05,
      "loss": 1.4336433410644531,
      "num_input_tokens_seen": 51081536,
      "step": 180,
      "train_runtime": 1760.7339,
      "train_tokens_per_second": 29011.503
    },
    {
      "epoch": 0.006722585010846802,
      "grad_norm": 1.8125,
      "learning_rate": 4.953409391427024e-05,
      "loss": 1.4460283279418946,
      "num_input_tokens_seen": 53934336,
      "step": 190,
      "train_runtime": 1859.4849,
      "train_tokens_per_second": 29004.988
    },
    {
      "epoch": 0.007076405274575582,
      "grad_norm": 1.78125,
      "learning_rate": 4.950980415950502e-05,
      "loss": 1.434066390991211,
      "num_input_tokens_seen": 56792576,
      "step": 200,
      "train_runtime": 1958.0115,
      "train_tokens_per_second": 29005.231
    },
    {
      "epoch": 0.007430225538304361,
      "grad_norm": 1.703125,
      "learning_rate": 4.9485550102222575e-05,
      "loss": 1.427436637878418,
      "num_input_tokens_seen": 59683840,
      "step": 210,
      "train_runtime": 2057.4491,
      "train_tokens_per_second": 29008.66
    },
    {
      "epoch": 0.007784045802033139,
      "grad_norm": 1.7109375,
      "learning_rate": 4.946133165507037e-05,
      "loss": 1.4229135513305664,
      "num_input_tokens_seen": 62532608,
      "step": 220,
      "train_runtime": 2156.0527,
      "train_tokens_per_second": 29003.284
    },
    {
      "epoch": 0.008137866065761919,
      "grad_norm": 1.828125,
      "learning_rate": 4.943714873099483e-05,
      "loss": 1.4132097244262696,
      "num_input_tokens_seen": 65382784,
      "step": 230,
      "train_runtime": 2253.0986,
      "train_tokens_per_second": 29019.051
    },
    {
      "epoch": 0.008491686329490699,
      "grad_norm": 1.7421875,
      "learning_rate": 4.9413001243240024e-05,
      "loss": 1.418577003479004,
      "num_input_tokens_seen": 68271488,
      "step": 240,
      "train_runtime": 2348.6142,
      "train_tokens_per_second": 29068.84
    },
    {
      "epoch": 0.008845506593219477,
      "grad_norm": 1.5703125,
      "learning_rate": 4.938888910534637e-05,
      "loss": 1.398007583618164,
      "num_input_tokens_seen": 71153984,
      "step": 250,
      "train_runtime": 2447.896,
      "train_tokens_per_second": 29067.404
    },
    {
      "epoch": 0.009199326856948256,
      "grad_norm": 1.765625,
      "learning_rate": 4.936481223114932e-05,
      "loss": 1.4049840927124024,
      "num_input_tokens_seen": 73939776,
      "step": 260,
      "train_runtime": 2544.5168,
      "train_tokens_per_second": 29058.475
    },
    {
      "epoch": 0.009553147120677036,
      "grad_norm": 1.71875,
      "learning_rate": 4.934077053477808e-05,
      "loss": 1.3924064636230469,
      "num_input_tokens_seen": 76772352,
      "step": 270,
      "train_runtime": 2644.1424,
      "train_tokens_per_second": 29034.878
    },
    {
      "epoch": 0.009906967384405814,
      "grad_norm": 1.7265625,
      "learning_rate": 4.931676393065431e-05,
      "loss": 1.390452766418457,
      "num_input_tokens_seen": 79604032,
      "step": 280,
      "train_runtime": 2743.373,
      "train_tokens_per_second": 29016.846
    },
    {
      "epoch": 0.010260787648134593,
      "grad_norm": 1.671875,
      "learning_rate": 4.929279233349088e-05,
      "loss": 1.3796944618225098,
      "num_input_tokens_seen": 82418560,
      "step": 290,
      "train_runtime": 2838.2774,
      "train_tokens_per_second": 29038.233
    },
    {
      "epoch": 0.010614607911863373,
      "grad_norm": 1.640625,
      "learning_rate": 4.926885565829051e-05,
      "loss": 1.385779857635498,
      "num_input_tokens_seen": 85216128,
      "step": 300,
      "train_runtime": 2929.6,
      "train_tokens_per_second": 29087.974
    },
    {
      "epoch": 0.01096842817559215,
      "grad_norm": 1.6796875,
      "learning_rate": 4.924495382034461e-05,
      "loss": 1.3861013412475587,
      "num_input_tokens_seen": 88064064,
      "step": 310,
      "train_runtime": 3028.0671,
      "train_tokens_per_second": 29082.599
    },
    {
      "epoch": 0.01132224843932093,
      "grad_norm": 1.671875,
      "learning_rate": 4.9221086735231975e-05,
      "loss": 1.3745354652404784,
      "num_input_tokens_seen": 90948800,
      "step": 320,
      "train_runtime": 3125.891,
      "train_tokens_per_second": 29095.32
    },
    {
      "epoch": 0.01167606870304971,
      "grad_norm": 1.7265625,
      "learning_rate": 4.919725431881751e-05,
      "loss": 1.3837973594665527,
      "num_input_tokens_seen": 93845760,
      "step": 330,
      "train_runtime": 3224.7228,
      "train_tokens_per_second": 29101.962
    },
    {
      "epoch": 0.012029888966778488,
      "grad_norm": 1.7109375,
      "learning_rate": 4.917345648725101e-05,
      "loss": 1.3645482063293457,
      "num_input_tokens_seen": 96686912,
      "step": 340,
      "train_runtime": 3321.4064,
      "train_tokens_per_second": 29110.232
    },
    {
      "epoch": 0.012383709230507267,
      "grad_norm": 1.609375,
      "learning_rate": 4.914969315696596e-05,
      "loss": 1.359701156616211,
      "num_input_tokens_seen": 99527552,
      "step": 350,
      "train_runtime": 3418.69,
      "train_tokens_per_second": 29112.774
    },
    {
      "epoch": 0.012737529494236047,
      "grad_norm": 1.640625,
      "learning_rate": 4.912596424467818e-05,
      "loss": 1.3707971572875977,
      "num_input_tokens_seen": 102450560,
      "step": 360,
      "train_runtime": 3518.6186,
      "train_tokens_per_second": 29116.7
    },
    {
      "epoch": 0.013091349757964827,
      "grad_norm": 1.609375,
      "learning_rate": 4.910226966738475e-05,
      "loss": 1.3824318885803222,
      "num_input_tokens_seen": 105327808,
      "step": 370,
      "train_runtime": 3616.6336,
      "train_tokens_per_second": 29123.163
    },
    {
      "epoch": 0.013445170021693605,
      "grad_norm": 1.5859375,
      "learning_rate": 4.9078609342362666e-05,
      "loss": 1.3800084114074707,
      "num_input_tokens_seen": 108158336,
      "step": 380,
      "train_runtime": 3713.0293,
      "train_tokens_per_second": 29129.405
    },
    {
      "epoch": 0.013798990285422384,
      "grad_norm": 1.71875,
      "learning_rate": 4.905498318716775e-05,
      "loss": 1.3636469841003418,
      "num_input_tokens_seen": 111012864,
      "step": 390,
      "train_runtime": 3811.3416,
      "train_tokens_per_second": 29126.978
    },
    {
      "epoch": 0.014152810549151164,
      "grad_norm": 1.6484375,
      "learning_rate": 4.9031391119633295e-05,
      "loss": 1.3595507621765137,
      "num_input_tokens_seen": 113838336,
      "step": 400,
      "train_runtime": 3907.2664,
      "train_tokens_per_second": 29135.033
    },
    {
      "epoch": 0.014506630812879942,
      "grad_norm": 1.6484375,
      "learning_rate": 4.9007833057869e-05,
      "loss": 1.351626205444336,
      "num_input_tokens_seen": 116627008,
      "step": 410,
      "train_runtime": 4002.2816,
      "train_tokens_per_second": 29140.13
    },
    {
      "epoch": 0.014860451076608721,
      "grad_norm": 1.671875,
      "learning_rate": 4.898430892025967e-05,
      "loss": 1.3616992950439453,
      "num_input_tokens_seen": 119470080,
      "step": 420,
      "train_runtime": 4103.089,
      "train_tokens_per_second": 29117.107
    },
    {
      "epoch": 0.015214271340337501,
      "grad_norm": 1.6484375,
      "learning_rate": 4.896081862546415e-05,
      "loss": 1.3449151992797852,
      "num_input_tokens_seen": 122313024,
      "step": 430,
      "train_runtime": 4200.2387,
      "train_tokens_per_second": 29120.494
    },
    {
      "epoch": 0.015568091604066279,
      "grad_norm": 1.59375,
      "learning_rate": 4.8937362092414e-05,
      "loss": 1.3649165153503418,
      "num_input_tokens_seen": 125125248,
      "step": 440,
      "train_runtime": 4293.6594,
      "train_tokens_per_second": 29141.866
    },
    {
      "epoch": 0.01592191186779506,
      "grad_norm": 1.671875,
      "learning_rate": 4.891393924031244e-05,
      "loss": 1.3540953636169433,
      "num_input_tokens_seen": 127990208,
      "step": 450,
      "train_runtime": 4391.8149,
      "train_tokens_per_second": 29142.897
    },
    {
      "epoch": 0.016275732131523838,
      "grad_norm": 1.6328125,
      "learning_rate": 4.8890549988633095e-05,
      "loss": 1.3574003219604491,
      "num_input_tokens_seen": 130801600,
      "step": 460,
      "train_runtime": 4485.1091,
      "train_tokens_per_second": 29163.527
    },
    {
      "epoch": 0.016629552395252618,
      "grad_norm": 1.6875,
      "learning_rate": 4.8867194257118907e-05,
      "loss": 1.3498289108276367,
      "num_input_tokens_seen": 133635712,
      "step": 470,
      "train_runtime": 4584.3761,
      "train_tokens_per_second": 29150.251
    },
    {
      "epoch": 0.016983372658981397,
      "grad_norm": 1.6171875,
      "learning_rate": 4.884387196578093e-05,
      "loss": 1.3534079551696778,
      "num_input_tokens_seen": 136496704,
      "step": 480,
      "train_runtime": 4682.6935,
      "train_tokens_per_second": 29149.186
    },
    {
      "epoch": 0.017337192922710173,
      "grad_norm": 1.609375,
      "learning_rate": 4.882058303489718e-05,
      "loss": 1.3462406158447267,
      "num_input_tokens_seen": 139289984,
      "step": 490,
      "train_runtime": 4774.9382,
      "train_tokens_per_second": 29171.055
    },
    {
      "epoch": 0.017691013186438953,
      "grad_norm": 1.53125,
      "learning_rate": 4.8797327385011496e-05,
      "loss": 1.3408540725708007,
      "num_input_tokens_seen": 142138496,
      "step": 500,
      "train_runtime": 4869.0303,
      "train_tokens_per_second": 29192.362
    },
    {
      "epoch": 0.018044833450167733,
      "grad_norm": 1.5859375,
      "learning_rate": 4.8774104936932425e-05,
      "loss": 1.3498264312744142,
      "num_input_tokens_seen": 144959360,
      "step": 510,
      "train_runtime": 4965.0448,
      "train_tokens_per_second": 29195.982
    },
    {
      "epoch": 0.018398653713896512,
      "grad_norm": 1.640625,
      "learning_rate": 4.8750915611732076e-05,
      "loss": 1.3357254028320313,
      "num_input_tokens_seen": 147701312,
      "step": 520,
      "train_runtime": 5054.7796,
      "train_tokens_per_second": 29220.129
    },
    {
      "epoch": 0.018752473977625292,
      "grad_norm": 1.515625,
      "learning_rate": 4.8727759330744986e-05,
      "loss": 1.347636890411377,
      "num_input_tokens_seen": 150572416,
      "step": 530,
      "train_runtime": 5154.9794,
      "train_tokens_per_second": 29209.121
    },
    {
      "epoch": 0.01910629424135407,
      "grad_norm": 1.59375,
      "learning_rate": 4.870463601556696e-05,
      "loss": 1.3421825408935546,
      "num_input_tokens_seen": 153366080,
      "step": 540,
      "train_runtime": 5249.816,
      "train_tokens_per_second": 29213.611
    },
    {
      "epoch": 0.019460114505082848,
      "grad_norm": 1.5703125,
      "learning_rate": 4.8681545588054075e-05,
      "loss": 1.3426931381225586,
      "num_input_tokens_seen": 156225920,
      "step": 550,
      "train_runtime": 5351.1457,
      "train_tokens_per_second": 29194.855
    },
    {
      "epoch": 0.019813934768811627,
      "grad_norm": 1.5234375,
      "learning_rate": 4.8658487970321404e-05,
      "loss": 1.3237018585205078,
      "num_input_tokens_seen": 159087552,
      "step": 560,
      "train_runtime": 5450.9745,
      "train_tokens_per_second": 29185.158
    },
    {
      "epoch": 0.020167755032540407,
      "grad_norm": 1.546875,
      "learning_rate": 4.863546308474209e-05,
      "loss": 1.3331922531127929,
      "num_input_tokens_seen": 161982784,
      "step": 570,
      "train_runtime": 5553.0448,
      "train_tokens_per_second": 29170.084
    },
    {
      "epoch": 0.020521575296269187,
      "grad_norm": 1.5546875,
      "learning_rate": 4.86124708539461e-05,
      "loss": 1.3306333541870117,
      "num_input_tokens_seen": 164782400,
      "step": 580,
      "train_runtime": 5649.7766,
      "train_tokens_per_second": 29166.18
    },
    {
      "epoch": 0.020875395559997966,
      "grad_norm": 1.625,
      "learning_rate": 4.8589511200819216e-05,
      "loss": 1.3231840133666992,
      "num_input_tokens_seen": 167594880,
      "step": 590,
      "train_runtime": 5742.5619,
      "train_tokens_per_second": 29184.689
    },
    {
      "epoch": 0.021229215823726746,
      "grad_norm": 1.5234375,
      "learning_rate": 4.8566584048501926e-05,
      "loss": 1.3181431770324707,
      "num_input_tokens_seen": 170407296,
      "step": 600,
      "train_runtime": 5838.5945,
      "train_tokens_per_second": 29186.356
    },
    {
      "epoch": 0.021583036087455525,
      "grad_norm": 1.515625,
      "learning_rate": 4.854368932038835e-05,
      "loss": 1.3116433143615722,
      "num_input_tokens_seen": 173246784,
      "step": 610,
      "train_runtime": 5935.3768,
      "train_tokens_per_second": 29188.843
    },
    {
      "epoch": 0.0219368563511843,
      "grad_norm": 1.6875,
      "learning_rate": 4.8520826940125144e-05,
      "loss": 1.3395931243896484,
      "num_input_tokens_seen": 176162112,
      "step": 620,
      "train_runtime": 6036.5162,
      "train_tokens_per_second": 29182.745
    },
    {
      "epoch": 0.02229067661491308,
      "grad_norm": 1.6484375,
      "learning_rate": 4.849799683161046e-05,
      "loss": 1.3172121047973633,
      "num_input_tokens_seen": 179001984,
      "step": 630,
      "train_runtime": 6132.0013,
      "train_tokens_per_second": 29191.446
    },
    {
      "epoch": 0.02264449687864186,
      "grad_norm": 1.671875,
      "learning_rate": 4.8475198918992835e-05,
      "loss": 1.3434142112731933,
      "num_input_tokens_seen": 181931712,
      "step": 640,
      "train_runtime": 6233.6083,
      "train_tokens_per_second": 29185.618
    },
    {
      "epoch": 0.02299831714237064,
      "grad_norm": 1.5546875,
      "learning_rate": 4.845243312667023e-05,
      "loss": 1.3180923461914062,
      "num_input_tokens_seen": 184767872,
      "step": 650,
      "train_runtime": 6331.407,
      "train_tokens_per_second": 29182.751
    },
    {
      "epoch": 0.02335213740609942,
      "grad_norm": 1.5390625,
      "learning_rate": 4.842969937928884e-05,
      "loss": 1.3221427917480468,
      "num_input_tokens_seen": 187563008,
      "step": 660,
      "train_runtime": 6426.4829,
      "train_tokens_per_second": 29185.95
    },
    {
      "epoch": 0.0237059576698282,
      "grad_norm": 1.4765625,
      "learning_rate": 4.840699760174217e-05,
      "loss": 1.3036195755004882,
      "num_input_tokens_seen": 190415872,
      "step": 670,
      "train_runtime": 6523.0256,
      "train_tokens_per_second": 29191.342
    },
    {
      "epoch": 0.024059777933556976,
      "grad_norm": 1.5390625,
      "learning_rate": 4.8384327719169906e-05,
      "loss": 1.3122371673583983,
      "num_input_tokens_seen": 193276160,
      "step": 680,
      "train_runtime": 6618.4252,
      "train_tokens_per_second": 29202.741
    },
    {
      "epoch": 0.024413598197285755,
      "grad_norm": 1.5078125,
      "learning_rate": 4.836168965695694e-05,
      "loss": 1.3263204574584961,
      "num_input_tokens_seen": 196100352,
      "step": 690,
      "train_runtime": 6715.4217,
      "train_tokens_per_second": 29201.495
    },
    {
      "epoch": 0.024767418461014535,
      "grad_norm": 1.515625,
      "learning_rate": 4.8339083340732304e-05,
      "loss": 1.315943717956543,
      "num_input_tokens_seen": 198917632,
      "step": 700,
      "train_runtime": 6812.0588,
      "train_tokens_per_second": 29200.81
    },
    {
      "epoch": 0.025121238724743315,
      "grad_norm": 1.4765625,
      "learning_rate": 4.8316508696368154e-05,
      "loss": 1.3086830139160157,
      "num_input_tokens_seen": 201755584,
      "step": 710,
      "train_runtime": 6908.1598,
      "train_tokens_per_second": 29205.402
    },
    {
      "epoch": 0.025475058988472094,
      "grad_norm": 1.578125,
      "learning_rate": 4.8293965649978714e-05,
      "loss": 1.3209542274475097,
      "num_input_tokens_seen": 204637376,
      "step": 720,
      "train_runtime": 7009.7956,
      "train_tokens_per_second": 29193.059
    },
    {
      "epoch": 0.025828879252200874,
      "grad_norm": 1.578125,
      "learning_rate": 4.8271454127919364e-05,
      "loss": 1.317988395690918,
      "num_input_tokens_seen": 207481920,
      "step": 730,
      "train_runtime": 7105.0533,
      "train_tokens_per_second": 29202.021
    },
    {
      "epoch": 0.026182699515929653,
      "grad_norm": 1.53125,
      "learning_rate": 4.824897405678549e-05,
      "loss": 1.3196215629577637,
      "num_input_tokens_seen": 210324480,
      "step": 740,
      "train_runtime": 7204.7059,
      "train_tokens_per_second": 29192.653
    },
    {
      "epoch": 0.02653651977965843,
      "grad_norm": 1.53125,
      "learning_rate": 4.8226525363411576e-05,
      "loss": 1.3075403213500976,
      "num_input_tokens_seen": 213174656,
      "step": 750,
      "train_runtime": 7301.4456,
      "train_tokens_per_second": 29196.226
    },
    {
      "epoch": 0.02689034004338721,
      "grad_norm": 1.53125,
      "learning_rate": 4.820410797487017e-05,
      "loss": 1.3020206451416017,
      "num_input_tokens_seen": 216051136,
      "step": 760,
      "train_runtime": 7402.0411,
      "train_tokens_per_second": 29188.049
    },
    {
      "epoch": 0.02724416030711599,
      "grad_norm": 1.5234375,
      "learning_rate": 4.818172181847091e-05,
      "loss": 1.308267879486084,
      "num_input_tokens_seen": 218912640,
      "step": 770,
      "train_runtime": 7500.902,
      "train_tokens_per_second": 29184.842
    },
    {
      "epoch": 0.02759798057084477,
      "grad_norm": 1.53125,
      "learning_rate": 4.81593668217595e-05,
      "loss": 1.3149566650390625,
      "num_input_tokens_seen": 221661120,
      "step": 780,
      "train_runtime": 7591.8409,
      "train_tokens_per_second": 29197.282
    },
    {
      "epoch": 0.027951800834573548,
      "grad_norm": 1.59375,
      "learning_rate": 4.813704291251675e-05,
      "loss": 1.3037477493286134,
      "num_input_tokens_seen": 224521408,
      "step": 790,
      "train_runtime": 7686.6362,
      "train_tokens_per_second": 29209.319
    },
    {
      "epoch": 0.028305621098302328,
      "grad_norm": 1.59375,
      "learning_rate": 4.811475001875759e-05,
      "loss": 1.2903422355651855,
      "num_input_tokens_seen": 227384512,
      "step": 800,
      "train_runtime": 7786.7451,
      "train_tokens_per_second": 29201.484
    },
    {
      "epoch": 0.028659441362031104,
      "grad_norm": 1.4765625,
      "learning_rate": 4.8092488068730105e-05,
      "loss": 1.2953707695007324,
      "num_input_tokens_seen": 230168128,
      "step": 810,
      "train_runtime": 7881.5661,
      "train_tokens_per_second": 29203.349
    },
    {
      "epoch": 0.029013261625759883,
      "grad_norm": 1.5390625,
      "learning_rate": 4.807025699091452e-05,
      "loss": 1.3137131690979005,
      "num_input_tokens_seen": 233010944,
      "step": 820,
      "train_runtime": 7980.0157,
      "train_tokens_per_second": 29199.309
    },
    {
      "epoch": 0.029367081889488663,
      "grad_norm": 1.5703125,
      "learning_rate": 4.8048056714022325e-05,
      "loss": 1.2995559692382812,
      "num_input_tokens_seen": 235868608,
      "step": 830,
      "train_runtime": 8081.6458,
      "train_tokens_per_second": 29185.715
    },
    {
      "epoch": 0.029720902153217443,
      "grad_norm": 1.46875,
      "learning_rate": 4.802588716699519e-05,
      "loss": 1.299889373779297,
      "num_input_tokens_seen": 238670976,
      "step": 840,
      "train_runtime": 8177.168,
      "train_tokens_per_second": 29187.486
    },
    {
      "epoch": 0.030074722416946222,
      "grad_norm": 1.5234375,
      "learning_rate": 4.8003748279004156e-05,
      "loss": 1.307916259765625,
      "num_input_tokens_seen": 241592064,
      "step": 850,
      "train_runtime": 8279.211,
      "train_tokens_per_second": 29180.566
    },
    {
      "epoch": 0.030428542680675002,
      "grad_norm": 1.46875,
      "learning_rate": 4.798163997944854e-05,
      "loss": 1.2924917221069336,
      "num_input_tokens_seen": 244417792,
      "step": 860,
      "train_runtime": 8372.8013,
      "train_tokens_per_second": 29191.878
    },
    {
      "epoch": 0.030782362944403778,
      "grad_norm": 1.484375,
      "learning_rate": 4.79595621979551e-05,
      "loss": 1.3086358070373536,
      "num_input_tokens_seen": 247252096,
      "step": 870,
      "train_runtime": 8469.2832,
      "train_tokens_per_second": 29193.981
    },
    {
      "epoch": 0.031136183208132558,
      "grad_norm": 1.484375,
      "learning_rate": 4.793751486437702e-05,
      "loss": 1.2793291091918946,
      "num_input_tokens_seen": 250084480,
      "step": 880,
      "train_runtime": 8565.5624,
      "train_tokens_per_second": 29196.505
    },
    {
      "epoch": 0.03149000347186134,
      "grad_norm": 1.484375,
      "learning_rate": 4.7915497908793064e-05,
      "loss": 1.2936951637268066,
      "num_input_tokens_seen": 252907136,
      "step": 890,
      "train_runtime": 8663.0229,
      "train_tokens_per_second": 29193.867
    },
    {
      "epoch": 0.03184382373559012,
      "grad_norm": 1.4921875,
      "learning_rate": 4.7893511261506516e-05,
      "loss": 1.2788345336914062,
      "num_input_tokens_seen": 255730432,
      "step": 900,
      "train_runtime": 8760.1548,
      "train_tokens_per_second": 29192.456
    },
    {
      "epoch": 0.032197643999318896,
      "grad_norm": 1.4921875,
      "learning_rate": 4.787155485304435e-05,
      "loss": 1.2894940376281738,
      "num_input_tokens_seen": 258587072,
      "step": 910,
      "train_runtime": 8857.8314,
      "train_tokens_per_second": 29193.045
    },
    {
      "epoch": 0.032551464263047676,
      "grad_norm": 1.53125,
      "learning_rate": 4.784962861415629e-05,
      "loss": 1.2983574867248535,
      "num_input_tokens_seen": 261403456,
      "step": 920,
      "train_runtime": 8953.832,
      "train_tokens_per_second": 29194.59
    },
    {
      "epoch": 0.032905284526776456,
      "grad_norm": 1.5703125,
      "learning_rate": 4.7827732475813884e-05,
      "loss": 1.2840347290039062,
      "num_input_tokens_seen": 264245888,
      "step": 930,
      "train_runtime": 9050.8908,
      "train_tokens_per_second": 29195.567
    },
    {
      "epoch": 0.033259104790505235,
      "grad_norm": 1.4765625,
      "learning_rate": 4.7805866369209576e-05,
      "loss": 1.276268768310547,
      "num_input_tokens_seen": 267068608,
      "step": 940,
      "train_runtime": 9147.7169,
      "train_tokens_per_second": 29195.111
    },
    {
      "epoch": 0.033612925054234015,
      "grad_norm": 1.5546875,
      "learning_rate": 4.778403022575583e-05,
      "loss": 1.2826930046081544,
      "num_input_tokens_seen": 269879616,
      "step": 950,
      "train_runtime": 9241.5376,
      "train_tokens_per_second": 29202.891
    },
    {
      "epoch": 0.033966745317962795,
      "grad_norm": 1.484375,
      "learning_rate": 4.7762223977084195e-05,
      "loss": 1.287209415435791,
      "num_input_tokens_seen": 272747456,
      "step": 960,
      "train_runtime": 9342.3445,
      "train_tokens_per_second": 29194.755
    },
    {
      "epoch": 0.03432056558169157,
      "grad_norm": 1.5,
      "learning_rate": 4.774044755504444e-05,
      "loss": 1.2790203094482422,
      "num_input_tokens_seen": 275555264,
      "step": 970,
      "train_runtime": 9437.9049,
      "train_tokens_per_second": 29196.656
    },
    {
      "epoch": 0.03467438584542035,
      "grad_norm": 1.46875,
      "learning_rate": 4.7718700891703616e-05,
      "loss": 1.2881513595581056,
      "num_input_tokens_seen": 278383808,
      "step": 980,
      "train_runtime": 9532.674,
      "train_tokens_per_second": 29203.118
    },
    {
      "epoch": 0.035028206109149126,
      "grad_norm": 1.5234375,
      "learning_rate": 4.7696983919345215e-05,
      "loss": 1.2910917282104493,
      "num_input_tokens_seen": 281244672,
      "step": 990,
      "train_runtime": 9633.2162,
      "train_tokens_per_second": 29195.304
    },
    {
      "epoch": 0.035382026372877906,
      "grad_norm": 1.53125,
      "learning_rate": 4.7675296570468216e-05,
      "loss": 1.2847518920898438,
      "num_input_tokens_seen": 284070144,
      "step": 1000,
      "train_runtime": 9730.0636,
      "train_tokens_per_second": 29195.096
    },
    {
      "epoch": 0.035735846636606686,
      "grad_norm": 1.484375,
      "learning_rate": 4.76536387777863e-05,
      "loss": 1.2603843688964844,
      "num_input_tokens_seen": 286892224,
      "step": 1010,
      "train_runtime": 9825.4324,
      "train_tokens_per_second": 29198.941
    },
    {
      "epoch": 0.036089666900335465,
      "grad_norm": 1.671875,
      "learning_rate": 4.7632010474226915e-05,
      "loss": 1.273622989654541,
      "num_input_tokens_seen": 289760768,
      "step": 1020,
      "train_runtime": 9926.6568,
      "train_tokens_per_second": 29190.167
    },
    {
      "epoch": 0.036443487164064245,
      "grad_norm": 1.546875,
      "learning_rate": 4.761041159293035e-05,
      "loss": 1.2834928512573243,
      "num_input_tokens_seen": 292580992,
      "step": 1030,
      "train_runtime": 10022.8105,
      "train_tokens_per_second": 29191.512
    },
    {
      "epoch": 0.036797307427793025,
      "grad_norm": 1.4921875,
      "learning_rate": 4.7588842067249e-05,
      "loss": 1.282025146484375,
      "num_input_tokens_seen": 295430272,
      "step": 1040,
      "train_runtime": 10122.797,
      "train_tokens_per_second": 29184.648
    },
    {
      "epoch": 0.037151127691521804,
      "grad_norm": 1.53125,
      "learning_rate": 4.756730183074637e-05,
      "loss": 1.2845125198364258,
      "num_input_tokens_seen": 298248704,
      "step": 1050,
      "train_runtime": 10218.0481,
      "train_tokens_per_second": 29188.422
    },
    {
      "epoch": 0.037504947955250584,
      "grad_norm": 1.5625,
      "learning_rate": 4.7545790817196314e-05,
      "loss": 1.271329116821289,
      "num_input_tokens_seen": 301097088,
      "step": 1060,
      "train_runtime": 10317.1547,
      "train_tokens_per_second": 29184.121
    },
    {
      "epoch": 0.03785876821897936,
      "grad_norm": 1.4609375,
      "learning_rate": 4.752430896058212e-05,
      "loss": 1.27503662109375,
      "num_input_tokens_seen": 303881344,
      "step": 1070,
      "train_runtime": 10410.6854,
      "train_tokens_per_second": 29189.369
    },
    {
      "epoch": 0.03821258848270814,
      "grad_norm": 1.484375,
      "learning_rate": 4.750285619509567e-05,
      "loss": 1.2855945587158204,
      "num_input_tokens_seen": 306701696,
      "step": 1080,
      "train_runtime": 10507.778,
      "train_tokens_per_second": 29188.064
    },
    {
      "epoch": 0.03856640874643692,
      "grad_norm": 1.5078125,
      "learning_rate": 4.7481432455136644e-05,
      "loss": 1.286431884765625,
      "num_input_tokens_seen": 309561344,
      "step": 1090,
      "train_runtime": 10608.7189,
      "train_tokens_per_second": 29179.899
    },
    {
      "epoch": 0.038920229010165695,
      "grad_norm": 1.484375,
      "learning_rate": 4.7460037675311584e-05,
      "loss": 1.2837228775024414,
      "num_input_tokens_seen": 312447872,
      "step": 1100,
      "train_runtime": 10708.76,
      "train_tokens_per_second": 29176.849
    },
    {
      "epoch": 0.039274049273894475,
      "grad_norm": 1.5625,
      "learning_rate": 4.7438671790433126e-05,
      "loss": 1.2781454086303712,
      "num_input_tokens_seen": 315278400,
      "step": 1110,
      "train_runtime": 10805.9579,
      "train_tokens_per_second": 29176.349
    },
    {
      "epoch": 0.039627869537623255,
      "grad_norm": 1.5078125,
      "learning_rate": 4.741733473551915e-05,
      "loss": 1.2586235046386718,
      "num_input_tokens_seen": 318156160,
      "step": 1120,
      "train_runtime": 10904.8312,
      "train_tokens_per_second": 29175.707
    },
    {
      "epoch": 0.039981689801352034,
      "grad_norm": 1.4765625,
      "learning_rate": 4.7396026445791966e-05,
      "loss": 1.2817815780639648,
      "num_input_tokens_seen": 321007808,
      "step": 1130,
      "train_runtime": 11003.2492,
      "train_tokens_per_second": 29173.911
    },
    {
      "epoch": 0.040335510065080814,
      "grad_norm": 1.578125,
      "learning_rate": 4.737474685667742e-05,
      "loss": 1.2775043487548827,
      "num_input_tokens_seen": 323854016,
      "step": 1140,
      "train_runtime": 11101.0407,
      "train_tokens_per_second": 29173.302
    },
    {
      "epoch": 0.04068933032880959,
      "grad_norm": 1.4921875,
      "learning_rate": 4.7353495903804165e-05,
      "loss": 1.2724164962768554,
      "num_input_tokens_seen": 326739072,
      "step": 1150,
      "train_runtime": 11203.2937,
      "train_tokens_per_second": 29164.555
    },
    {
      "epoch": 0.04104315059253837,
      "grad_norm": 1.546875,
      "learning_rate": 4.733227352300277e-05,
      "loss": 1.261830711364746,
      "num_input_tokens_seen": 329584000,
      "step": 1160,
      "train_runtime": 11300.3868,
      "train_tokens_per_second": 29165.727
    },
    {
      "epoch": 0.04139697085626715,
      "grad_norm": 1.484375,
      "learning_rate": 4.731107965030496e-05,
      "loss": 1.2604832649230957,
      "num_input_tokens_seen": 332447488,
      "step": 1170,
      "train_runtime": 11398.9997,
      "train_tokens_per_second": 29164.62
    },
    {
      "epoch": 0.04175079111999593,
      "grad_norm": 1.5390625,
      "learning_rate": 4.728991422194278e-05,
      "loss": 1.2686702728271484,
      "num_input_tokens_seen": 335291008,
      "step": 1180,
      "train_runtime": 11497.3088,
      "train_tokens_per_second": 29162.564
    },
    {
      "epoch": 0.04210461138372471,
      "grad_norm": 1.4921875,
      "learning_rate": 4.726877717434773e-05,
      "loss": 1.2504941940307617,
      "num_input_tokens_seen": 338140352,
      "step": 1190,
      "train_runtime": 11596.4711,
      "train_tokens_per_second": 29158.901
    },
    {
      "epoch": 0.04245843164745349,
      "grad_norm": 1.4609375,
      "learning_rate": 4.724766844415013e-05,
      "loss": 1.2769978523254395,
      "num_input_tokens_seen": 340990272,
      "step": 1200,
      "train_runtime": 11695.6569,
      "train_tokens_per_second": 29155.29
    },
    {
      "epoch": 0.04281225191118227,
      "grad_norm": 1.4453125,
      "learning_rate": 4.722658796817813e-05,
      "loss": 1.2674144744873046,
      "num_input_tokens_seen": 343838208,
      "step": 1210,
      "train_runtime": 11793.4781,
      "train_tokens_per_second": 29154.945
    },
    {
      "epoch": 0.04316607217491105,
      "grad_norm": 1.46875,
      "learning_rate": 4.7205535683457044e-05,
      "loss": 1.258150005340576,
      "num_input_tokens_seen": 346657792,
      "step": 1220,
      "train_runtime": 11892.3837,
      "train_tokens_per_second": 29149.563
    },
    {
      "epoch": 0.04351989243863982,
      "grad_norm": 1.4765625,
      "learning_rate": 4.7184511527208484e-05,
      "loss": 1.2677743911743165,
      "num_input_tokens_seen": 349406848,
      "step": 1230,
      "train_runtime": 11984.7668,
      "train_tokens_per_second": 29154.247
    },
    {
      "epoch": 0.0438737127023686,
      "grad_norm": 1.5390625,
      "learning_rate": 4.7163515436849644e-05,
      "loss": 1.2628530502319335,
      "num_input_tokens_seen": 352205120,
      "step": 1240,
      "train_runtime": 12077.1018,
      "train_tokens_per_second": 29163.05
    },
    {
      "epoch": 0.04422753296609738,
      "grad_norm": 1.515625,
      "learning_rate": 4.714254734999245e-05,
      "loss": 1.2550325393676758,
      "num_input_tokens_seen": 355032320,
      "step": 1250,
      "train_runtime": 12174.9434,
      "train_tokens_per_second": 29160.901
    },
    {
      "epoch": 0.04458135322982616,
      "grad_norm": 1.484375,
      "learning_rate": 4.712160720444284e-05,
      "loss": 1.2668527603149413,
      "num_input_tokens_seen": 357865728,
      "step": 1260,
      "train_runtime": 12270.6258,
      "train_tokens_per_second": 29164.424
    },
    {
      "epoch": 0.04493517349355494,
      "grad_norm": 1.5,
      "learning_rate": 4.710069493819992e-05,
      "loss": 1.273119068145752,
      "num_input_tokens_seen": 360726208,
      "step": 1270,
      "train_runtime": 12367.0349,
      "train_tokens_per_second": 29168.367
    },
    {
      "epoch": 0.04528899375728372,
      "grad_norm": 1.4453125,
      "learning_rate": 4.70798104894553e-05,
      "loss": 1.272770881652832,
      "num_input_tokens_seen": 363523776,
      "step": 1280,
      "train_runtime": 12463.0456,
      "train_tokens_per_second": 29168.133
    },
    {
      "epoch": 0.0456428140210125,
      "grad_norm": 1.484375,
      "learning_rate": 4.705895379659219e-05,
      "loss": 1.2593206405639648,
      "num_input_tokens_seen": 366363840,
      "step": 1290,
      "train_runtime": 12559.5297,
      "train_tokens_per_second": 29170.188
    },
    {
      "epoch": 0.04599663428474128,
      "grad_norm": 1.453125,
      "learning_rate": 4.7038124798184766e-05,
      "loss": 1.2485363006591796,
      "num_input_tokens_seen": 369254272,
      "step": 1300,
      "train_runtime": 12658.6132,
      "train_tokens_per_second": 29170.199
    },
    {
      "epoch": 0.04635045454847006,
      "grad_norm": 1.4296875,
      "learning_rate": 4.7017323432997304e-05,
      "loss": 1.249028778076172,
      "num_input_tokens_seen": 372060416,
      "step": 1310,
      "train_runtime": 12752.3333,
      "train_tokens_per_second": 29175.87
    },
    {
      "epoch": 0.04670427481219884,
      "grad_norm": 1.484375,
      "learning_rate": 4.6996549639983506e-05,
      "loss": 1.2636095046997071,
      "num_input_tokens_seen": 374916672,
      "step": 1320,
      "train_runtime": 12850.8931,
      "train_tokens_per_second": 29174.367
    },
    {
      "epoch": 0.04705809507592762,
      "grad_norm": 1.46875,
      "learning_rate": 4.697580335828569e-05,
      "loss": 1.2756300926208497,
      "num_input_tokens_seen": 377688768,
      "step": 1330,
      "train_runtime": 12944.598,
      "train_tokens_per_second": 29177.327
    },
    {
      "epoch": 0.0474119153396564,
      "grad_norm": 1.484375,
      "learning_rate": 4.6955084527234076e-05,
      "loss": 1.270100975036621,
      "num_input_tokens_seen": 380504704,
      "step": 1340,
      "train_runtime": 13041.89,
      "train_tokens_per_second": 29175.58
    },
    {
      "epoch": 0.04776573560338518,
      "grad_norm": 1.5390625,
      "learning_rate": 4.6934393086346034e-05,
      "loss": 1.25796537399292,
      "num_input_tokens_seen": 383362752,
      "step": 1350,
      "train_runtime": 13139.651,
      "train_tokens_per_second": 29176.022
    },
    {
      "epoch": 0.04811955586711395,
      "grad_norm": 1.5390625,
      "learning_rate": 4.6913728975325324e-05,
      "loss": 1.256306266784668,
      "num_input_tokens_seen": 386168256,
      "step": 1360,
      "train_runtime": 13235.1592,
      "train_tokens_per_second": 29177.455
    },
    {
      "epoch": 0.04847337613084273,
      "grad_norm": 1.5,
      "learning_rate": 4.6893092134061393e-05,
      "loss": 1.253044891357422,
      "num_input_tokens_seen": 389013440,
      "step": 1370,
      "train_runtime": 13330.0091,
      "train_tokens_per_second": 29183.284
    },
    {
      "epoch": 0.04882719639457151,
      "grad_norm": 1.390625,
      "learning_rate": 4.687248250262859e-05,
      "loss": 1.2590097427368163,
      "num_input_tokens_seen": 391862656,
      "step": 1380,
      "train_runtime": 13427.754,
      "train_tokens_per_second": 29183.038
    },
    {
      "epoch": 0.04918101665830029,
      "grad_norm": 1.3984375,
      "learning_rate": 4.685190002128548e-05,
      "loss": 1.2540940284729003,
      "num_input_tokens_seen": 394694016,
      "step": 1390,
      "train_runtime": 13524.9475,
      "train_tokens_per_second": 29182.665
    },
    {
      "epoch": 0.04953483692202907,
      "grad_norm": 1.375,
      "learning_rate": 4.6831344630474114e-05,
      "loss": 1.2662076950073242,
      "num_input_tokens_seen": 397559168,
      "step": 1400,
      "train_runtime": 13623.6606,
      "train_tokens_per_second": 29181.523
    },
    {
      "epoch": 0.04988865718575785,
      "grad_norm": 1.4765625,
      "learning_rate": 4.6810816270819276e-05,
      "loss": 1.2607160568237306,
      "num_input_tokens_seen": 400339968,
      "step": 1410,
      "train_runtime": 13716.952,
      "train_tokens_per_second": 29185.782
    },
    {
      "epoch": 0.05024247744948663,
      "grad_norm": 1.4609375,
      "learning_rate": 4.679031488312777e-05,
      "loss": 1.2524450302124024,
      "num_input_tokens_seen": 403147712,
      "step": 1420,
      "train_runtime": 13808.9773,
      "train_tokens_per_second": 29194.61
    },
    {
      "epoch": 0.05059629771321541,
      "grad_norm": 1.3984375,
      "learning_rate": 4.6769840408387717e-05,
      "loss": 1.2521073341369628,
      "num_input_tokens_seen": 405921984,
      "step": 1430,
      "train_runtime": 13902.9365,
      "train_tokens_per_second": 29196.852
    },
    {
      "epoch": 0.05095011797694419,
      "grad_norm": 1.484375,
      "learning_rate": 4.674939278776787e-05,
      "loss": 1.254897117614746,
      "num_input_tokens_seen": 408771328,
      "step": 1440,
      "train_runtime": 14002.5319,
      "train_tokens_per_second": 29192.673
    },
    {
      "epoch": 0.05130393824067297,
      "grad_norm": 1.453125,
      "learning_rate": 4.672897196261683e-05,
      "loss": 1.2373151779174805,
      "num_input_tokens_seen": 411631360,
      "step": 1450,
      "train_runtime": 14097.8673,
      "train_tokens_per_second": 29198.13
    },
    {
      "epoch": 0.05165775850440175,
      "grad_norm": 1.4609375,
      "learning_rate": 4.670857787446238e-05,
      "loss": 1.247175407409668,
      "num_input_tokens_seen": 414472512,
      "step": 1460,
      "train_runtime": 14195.1007,
      "train_tokens_per_second": 29198.279
    },
    {
      "epoch": 0.05201157876813053,
      "grad_norm": 1.4453125,
      "learning_rate": 4.668821046501082e-05,
      "loss": 1.262812328338623,
      "num_input_tokens_seen": 417288512,
      "step": 1470,
      "train_runtime": 14289.1285,
      "train_tokens_per_second": 29203.217
    },
    {
      "epoch": 0.05236539903185931,
      "grad_norm": 1.53125,
      "learning_rate": 4.6667869676146194e-05,
      "loss": 1.2526397705078125,
      "num_input_tokens_seen": 420114432,
      "step": 1480,
      "train_runtime": 14386.311,
      "train_tokens_per_second": 29202.374
    },
    {
      "epoch": 0.05271921929558808,
      "grad_norm": 1.4140625,
      "learning_rate": 4.6647555449929645e-05,
      "loss": 1.2694456100463867,
      "num_input_tokens_seen": 423016960,
      "step": 1490,
      "train_runtime": 14486.3006,
      "train_tokens_per_second": 29201.172
    },
    {
      "epoch": 0.05307303955931686,
      "grad_norm": 1.4765625,
      "learning_rate": 4.662726772859869e-05,
      "loss": 1.2332801818847656,
      "num_input_tokens_seen": 425864448,
      "step": 1500,
      "train_runtime": 14583.1399,
      "train_tokens_per_second": 29202.521
    },
    {
      "epoch": 0.05342685982304564,
      "grad_norm": 1.5078125,
      "learning_rate": 4.660700645456655e-05,
      "loss": 1.2506831169128418,
      "num_input_tokens_seen": 428695872,
      "step": 1510,
      "train_runtime": 14681.7896,
      "train_tokens_per_second": 29199.156
    },
    {
      "epoch": 0.05378068008677442,
      "grad_norm": 1.578125,
      "learning_rate": 4.658677157042149e-05,
      "loss": 1.2596900939941407,
      "num_input_tokens_seen": 431512576,
      "step": 1520,
      "train_runtime": 14778.0889,
      "train_tokens_per_second": 29199.484
    },
    {
      "epoch": 0.0541345003505032,
      "grad_norm": 1.4296875,
      "learning_rate": 4.656656301892605e-05,
      "loss": 1.247041893005371,
      "num_input_tokens_seen": 434367744,
      "step": 1530,
      "train_runtime": 14876.8818,
      "train_tokens_per_second": 29197.499
    },
    {
      "epoch": 0.05448832061423198,
      "grad_norm": 1.53125,
      "learning_rate": 4.6546380743016465e-05,
      "loss": 1.245659637451172,
      "num_input_tokens_seen": 437205952,
      "step": 1540,
      "train_runtime": 14975.2845,
      "train_tokens_per_second": 29195.168
    },
    {
      "epoch": 0.05484214087796076,
      "grad_norm": 1.4453125,
      "learning_rate": 4.652622468580193e-05,
      "loss": 1.2528257369995117,
      "num_input_tokens_seen": 440075648,
      "step": 1550,
      "train_runtime": 15075.7843,
      "train_tokens_per_second": 29190.896
    },
    {
      "epoch": 0.05519596114168954,
      "grad_norm": 1.421875,
      "learning_rate": 4.650609479056392e-05,
      "loss": 1.244206428527832,
      "num_input_tokens_seen": 442901888,
      "step": 1560,
      "train_runtime": 15171.8307,
      "train_tokens_per_second": 29192.383
    },
    {
      "epoch": 0.055549781405418316,
      "grad_norm": 1.4765625,
      "learning_rate": 4.648599100075556e-05,
      "loss": 1.2513113975524903,
      "num_input_tokens_seen": 445732352,
      "step": 1570,
      "train_runtime": 15267.9431,
      "train_tokens_per_second": 29194.001
    },
    {
      "epoch": 0.055903601669147096,
      "grad_norm": 1.4453125,
      "learning_rate": 4.6465913260000945e-05,
      "loss": 1.2245362281799317,
      "num_input_tokens_seen": 448596480,
      "step": 1580,
      "train_runtime": 15368.0358,
      "train_tokens_per_second": 29190.229
    },
    {
      "epoch": 0.056257421932875876,
      "grad_norm": 1.4609375,
      "learning_rate": 4.644586151209444e-05,
      "loss": 1.2394739151000977,
      "num_input_tokens_seen": 451430272,
      "step": 1590,
      "train_runtime": 15465.94,
      "train_tokens_per_second": 29188.673
    },
    {
      "epoch": 0.056611242196604655,
      "grad_norm": 1.375,
      "learning_rate": 4.6425835701000084e-05,
      "loss": 1.2369486808776855,
      "num_input_tokens_seen": 454233152,
      "step": 1600,
      "train_runtime": 15558.2509,
      "train_tokens_per_second": 29195.644
    },
    {
      "epoch": 0.05696506246033343,
      "grad_norm": 1.4375,
      "learning_rate": 4.640583577085084e-05,
      "loss": 1.2486921310424806,
      "num_input_tokens_seen": 457093248,
      "step": 1610,
      "train_runtime": 15655.8197,
      "train_tokens_per_second": 29196.379
    },
    {
      "epoch": 0.05731888272406221,
      "grad_norm": 1.4375,
      "learning_rate": 4.638586166594806e-05,
      "loss": 1.2466064453125,
      "num_input_tokens_seen": 459936448,
      "step": 1620,
      "train_runtime": 15752.8374,
      "train_tokens_per_second": 29197.054
    },
    {
      "epoch": 0.05767270298779099,
      "grad_norm": 1.4921875,
      "learning_rate": 4.6365913330760726e-05,
      "loss": 1.2378973007202148,
      "num_input_tokens_seen": 462743744,
      "step": 1630,
      "train_runtime": 15849.6915,
      "train_tokens_per_second": 29195.757
    },
    {
      "epoch": 0.05802652325151977,
      "grad_norm": 1.515625,
      "learning_rate": 4.6345990709924855e-05,
      "loss": 1.240572738647461,
      "num_input_tokens_seen": 465583680,
      "step": 1640,
      "train_runtime": 15947.1139,
      "train_tokens_per_second": 29195.482
    },
    {
      "epoch": 0.058380343515248546,
      "grad_norm": 1.390625,
      "learning_rate": 4.632609374824284e-05,
      "loss": 1.255947208404541,
      "num_input_tokens_seen": 468450816,
      "step": 1650,
      "train_runtime": 16046.7169,
      "train_tokens_per_second": 29192.938
    },
    {
      "epoch": 0.058734163778977326,
      "grad_norm": 1.4921875,
      "learning_rate": 4.630622239068285e-05,
      "loss": 1.2280990600585937,
      "num_input_tokens_seen": 471258944,
      "step": 1660,
      "train_runtime": 16143.6493,
      "train_tokens_per_second": 29191.599
    },
    {
      "epoch": 0.059087984042706106,
      "grad_norm": 1.421875,
      "learning_rate": 4.628637658237808e-05,
      "loss": 1.2365451812744142,
      "num_input_tokens_seen": 474096320,
      "step": 1670,
      "train_runtime": 16242.9438,
      "train_tokens_per_second": 29187.832
    },
    {
      "epoch": 0.059441804306434885,
      "grad_norm": 1.453125,
      "learning_rate": 4.626655626862625e-05,
      "loss": 1.2225577354431152,
      "num_input_tokens_seen": 476921472,
      "step": 1680,
      "train_runtime": 16339.6803,
      "train_tokens_per_second": 29187.932
    },
    {
      "epoch": 0.059795624570163665,
      "grad_norm": 1.484375,
      "learning_rate": 4.624676139488888e-05,
      "loss": 1.2477752685546875,
      "num_input_tokens_seen": 479802176,
      "step": 1690,
      "train_runtime": 16440.5262,
      "train_tokens_per_second": 29184.113
    },
    {
      "epoch": 0.060149444833892445,
      "grad_norm": 1.4375,
      "learning_rate": 4.6226991906790686e-05,
      "loss": 1.234751319885254,
      "num_input_tokens_seen": 482621056,
      "step": 1700,
      "train_runtime": 16536.6526,
      "train_tokens_per_second": 29184.931
    },
    {
      "epoch": 0.060503265097621224,
      "grad_norm": 1.515625,
      "learning_rate": 4.620724775011897e-05,
      "loss": 1.2388036727905274,
      "num_input_tokens_seen": 485433280,
      "step": 1710,
      "train_runtime": 16630.7479,
      "train_tokens_per_second": 29188.903
    },
    {
      "epoch": 0.060857085361350004,
      "grad_norm": 1.4375,
      "learning_rate": 4.618752887082297e-05,
      "loss": 1.2334161758422852,
      "num_input_tokens_seen": 488321600,
      "step": 1720,
      "train_runtime": 16730.6618,
      "train_tokens_per_second": 29187.226
    },
    {
      "epoch": 0.06121090562507878,
      "grad_norm": 1.4609375,
      "learning_rate": 4.616783521501325e-05,
      "loss": 1.2322227478027343,
      "num_input_tokens_seen": 491185728,
      "step": 1730,
      "train_runtime": 16830.5553,
      "train_tokens_per_second": 29184.167
    },
    {
      "epoch": 0.061564725888807556,
      "grad_norm": 1.546875,
      "learning_rate": 4.614816672896108e-05,
      "loss": 1.2362937927246094,
      "num_input_tokens_seen": 494032640,
      "step": 1740,
      "train_runtime": 16928.1548,
      "train_tokens_per_second": 29184.081
    },
    {
      "epoch": 0.061918546152536336,
      "grad_norm": 1.390625,
      "learning_rate": 4.612852335909782e-05,
      "loss": 1.2363208770751952,
      "num_input_tokens_seen": 496898944,
      "step": 1750,
      "train_runtime": 17024.3112,
      "train_tokens_per_second": 29187.609
    },
    {
      "epoch": 0.062272366416265115,
      "grad_norm": 1.4453125,
      "learning_rate": 4.6108905052014323e-05,
      "loss": 1.2319842338562013,
      "num_input_tokens_seen": 499705920,
      "step": 1760,
      "train_runtime": 17117.7506,
      "train_tokens_per_second": 29192.265
    },
    {
      "epoch": 0.0626261866799939,
      "grad_norm": 1.3984375,
      "learning_rate": 4.608931175446027e-05,
      "loss": 1.2204668045043945,
      "num_input_tokens_seen": 502554560,
      "step": 1770,
      "train_runtime": 17214.5734,
      "train_tokens_per_second": 29193.553
    },
    {
      "epoch": 0.06298000694372267,
      "grad_norm": 1.46875,
      "learning_rate": 4.606974341334367e-05,
      "loss": 1.2483132362365723,
      "num_input_tokens_seen": 505327296,
      "step": 1780,
      "train_runtime": 17309.3119,
      "train_tokens_per_second": 29193.956
    },
    {
      "epoch": 0.06333382720745145,
      "grad_norm": 1.4453125,
      "learning_rate": 4.605019997573011e-05,
      "loss": 1.2371336936950683,
      "num_input_tokens_seen": 508246208,
      "step": 1790,
      "train_runtime": 17410.8137,
      "train_tokens_per_second": 29191.41
    },
    {
      "epoch": 0.06368764747118023,
      "grad_norm": 1.4453125,
      "learning_rate": 4.603068138884229e-05,
      "loss": 1.2442188262939453,
      "num_input_tokens_seen": 511120896,
      "step": 1800,
      "train_runtime": 17510.8092,
      "train_tokens_per_second": 29188.879
    },
    {
      "epoch": 0.06404146773490901,
      "grad_norm": 1.453125,
      "learning_rate": 4.6011187600059345e-05,
      "loss": 1.2285377502441406,
      "num_input_tokens_seen": 513971072,
      "step": 1810,
      "train_runtime": 17606.1918,
      "train_tokens_per_second": 29192.632
    },
    {
      "epoch": 0.06439528799863779,
      "grad_norm": 1.46875,
      "learning_rate": 4.599171855691629e-05,
      "loss": 1.2315665245056153,
      "num_input_tokens_seen": 516781632,
      "step": 1820,
      "train_runtime": 17702.6313,
      "train_tokens_per_second": 29192.363
    },
    {
      "epoch": 0.06474910826236657,
      "grad_norm": 1.4609375,
      "learning_rate": 4.597227420710335e-05,
      "loss": 1.2157657623291016,
      "num_input_tokens_seen": 519587648,
      "step": 1830,
      "train_runtime": 17798.7916,
      "train_tokens_per_second": 29192.299
    },
    {
      "epoch": 0.06510292852609535,
      "grad_norm": 1.421875,
      "learning_rate": 4.595285449846551e-05,
      "loss": 1.2247900009155273,
      "num_input_tokens_seen": 522408064,
      "step": 1840,
      "train_runtime": 17895.1288,
      "train_tokens_per_second": 29192.752
    },
    {
      "epoch": 0.06545674878982413,
      "grad_norm": 1.4453125,
      "learning_rate": 4.593345937900178e-05,
      "loss": 1.2300881385803222,
      "num_input_tokens_seen": 525223808,
      "step": 1850,
      "train_runtime": 17989.5972,
      "train_tokens_per_second": 29195.974
    },
    {
      "epoch": 0.06581056905355291,
      "grad_norm": 1.46875,
      "learning_rate": 4.591408879686472e-05,
      "loss": 1.2117149353027343,
      "num_input_tokens_seen": 527996032,
      "step": 1860,
      "train_runtime": 18081.7914,
      "train_tokens_per_second": 29200.427
    },
    {
      "epoch": 0.06616438931728169,
      "grad_norm": 1.40625,
      "learning_rate": 4.5894742700359775e-05,
      "loss": 1.2351256370544434,
      "num_input_tokens_seen": 530825152,
      "step": 1870,
      "train_runtime": 18175.6858,
      "train_tokens_per_second": 29205.234
    },
    {
      "epoch": 0.06651820958101047,
      "grad_norm": 1.4140625,
      "learning_rate": 4.587542103794477e-05,
      "loss": 1.231490135192871,
      "num_input_tokens_seen": 533647104,
      "step": 1880,
      "train_runtime": 18273.171,
      "train_tokens_per_second": 29203.859
    },
    {
      "epoch": 0.06687202984473925,
      "grad_norm": 1.4609375,
      "learning_rate": 4.5856123758229247e-05,
      "loss": 1.2345277786254882,
      "num_input_tokens_seen": 536478464,
      "step": 1890,
      "train_runtime": 18368.7573,
      "train_tokens_per_second": 29206.029
    },
    {
      "epoch": 0.06722585010846803,
      "grad_norm": 1.4453125,
      "learning_rate": 4.5836850809973993e-05,
      "loss": 1.2307114601135254,
      "num_input_tokens_seen": 539351808,
      "step": 1900,
      "train_runtime": 18467.8843,
      "train_tokens_per_second": 29204.851
    },
    {
      "epoch": 0.06757967037219681,
      "grad_norm": 1.3984375,
      "learning_rate": 4.5817602142090385e-05,
      "loss": 1.2299392700195313,
      "num_input_tokens_seen": 542161408,
      "step": 1910,
      "train_runtime": 18565.5234,
      "train_tokens_per_second": 29202.592
    },
    {
      "epoch": 0.06793349063592559,
      "grad_norm": 1.5703125,
      "learning_rate": 4.579837770363989e-05,
      "loss": 1.2268086433410645,
      "num_input_tokens_seen": 544951744,
      "step": 1920,
      "train_runtime": 18656.9272,
      "train_tokens_per_second": 29209.083
    },
    {
      "epoch": 0.06828731089965437,
      "grad_norm": 1.40625,
      "learning_rate": 4.57791774438334e-05,
      "loss": 1.2209148406982422,
      "num_input_tokens_seen": 547750400,
      "step": 1930,
      "train_runtime": 18753.1179,
      "train_tokens_per_second": 29208.498
    },
    {
      "epoch": 0.06864113116338313,
      "grad_norm": 1.484375,
      "learning_rate": 4.576000131203078e-05,
      "loss": 1.2444892883300782,
      "num_input_tokens_seen": 550594112,
      "step": 1940,
      "train_runtime": 18851.5952,
      "train_tokens_per_second": 29206.765
    },
    {
      "epoch": 0.06899495142711191,
      "grad_norm": 1.3984375,
      "learning_rate": 4.574084925774023e-05,
      "loss": 1.2348945617675782,
      "num_input_tokens_seen": 553487040,
      "step": 1950,
      "train_runtime": 18952.3784,
      "train_tokens_per_second": 29204.094
    },
    {
      "epoch": 0.0693487716908407,
      "grad_norm": 1.390625,
      "learning_rate": 4.5721721230617795e-05,
      "loss": 1.2143863677978515,
      "num_input_tokens_seen": 556323008,
      "step": 1960,
      "train_runtime": 19051.8237,
      "train_tokens_per_second": 29200.512
    },
    {
      "epoch": 0.06970259195456947,
      "grad_norm": 1.4765625,
      "learning_rate": 4.57026171804667e-05,
      "loss": 1.22979679107666,
      "num_input_tokens_seen": 559121728,
      "step": 1970,
      "train_runtime": 19148.5024,
      "train_tokens_per_second": 29199.241
    },
    {
      "epoch": 0.07005641221829825,
      "grad_norm": 1.4375,
      "learning_rate": 4.568353705723692e-05,
      "loss": 1.2112942695617677,
      "num_input_tokens_seen": 562017152,
      "step": 1980,
      "train_runtime": 19248.202,
      "train_tokens_per_second": 29198.423
    },
    {
      "epoch": 0.07041023248202703,
      "grad_norm": 1.4375,
      "learning_rate": 4.566448081102455e-05,
      "loss": 1.210357666015625,
      "num_input_tokens_seen": 564825344,
      "step": 1990,
      "train_runtime": 19342.5825,
      "train_tokens_per_second": 29201.134
    },
    {
      "epoch": 0.07076405274575581,
      "grad_norm": 1.4765625,
      "learning_rate": 4.564544839207128e-05,
      "loss": 1.2312849044799805,
      "num_input_tokens_seen": 567674176,
      "step": 2000,
      "train_runtime": 19439.7692,
      "train_tokens_per_second": 29201.693
    },
    {
      "epoch": 0.07111787300948459,
      "grad_norm": 1.515625,
      "learning_rate": 4.562643975076387e-05,
      "loss": 1.2250823974609375,
      "num_input_tokens_seen": 570516160,
      "step": 2010,
      "train_runtime": 19538.3333,
      "train_tokens_per_second": 29199.838
    },
    {
      "epoch": 0.07147169327321337,
      "grad_norm": 1.5,
      "learning_rate": 4.560745483763357e-05,
      "loss": 1.2218762397766114,
      "num_input_tokens_seen": 573346944,
      "step": 2020,
      "train_runtime": 19636.8058,
      "train_tokens_per_second": 29197.567
    },
    {
      "epoch": 0.07182551353694215,
      "grad_norm": 1.5859375,
      "learning_rate": 4.5588493603355595e-05,
      "loss": 1.230175495147705,
      "num_input_tokens_seen": 576276288,
      "step": 2030,
      "train_runtime": 19740.692,
      "train_tokens_per_second": 29192.304
    },
    {
      "epoch": 0.07217933380067093,
      "grad_norm": 1.53125,
      "learning_rate": 4.556955599874859e-05,
      "loss": 1.2221302032470702,
      "num_input_tokens_seen": 579141184,
      "step": 2040,
      "train_runtime": 19840.7192,
      "train_tokens_per_second": 29189.526
    },
    {
      "epoch": 0.07253315406439971,
      "grad_norm": 1.4296875,
      "learning_rate": 4.555064197477409e-05,
      "loss": 1.2246397972106933,
      "num_input_tokens_seen": 582017088,
      "step": 2050,
      "train_runtime": 19940.8475,
      "train_tokens_per_second": 29187.179
    },
    {
      "epoch": 0.07288697432812849,
      "grad_norm": 1.4609375,
      "learning_rate": 4.5531751482536e-05,
      "loss": 1.2272417068481445,
      "num_input_tokens_seen": 584861632,
      "step": 2060,
      "train_runtime": 20041.7056,
      "train_tokens_per_second": 29182.228
    },
    {
      "epoch": 0.07324079459185727,
      "grad_norm": 1.40625,
      "learning_rate": 4.5512884473280024e-05,
      "loss": 1.2221508979797364,
      "num_input_tokens_seen": 587725440,
      "step": 2070,
      "train_runtime": 20138.1246,
      "train_tokens_per_second": 29184.716
    },
    {
      "epoch": 0.07359461485558605,
      "grad_norm": 1.421875,
      "learning_rate": 4.549404089839322e-05,
      "loss": 1.2156543731689453,
      "num_input_tokens_seen": 590559040,
      "step": 2080,
      "train_runtime": 20235.6956,
      "train_tokens_per_second": 29184.025
    },
    {
      "epoch": 0.07394843511931483,
      "grad_norm": 1.453125,
      "learning_rate": 4.547522070940335e-05,
      "loss": 1.2300201416015626,
      "num_input_tokens_seen": 593424512,
      "step": 2090,
      "train_runtime": 20334.4965,
      "train_tokens_per_second": 29183.143
    },
    {
      "epoch": 0.07430225538304361,
      "grad_norm": 1.421875,
      "learning_rate": 4.545642385797848e-05,
      "loss": 1.2280845642089844,
      "num_input_tokens_seen": 596225088,
      "step": 2100,
      "train_runtime": 20426.1303,
      "train_tokens_per_second": 29189.331
    },
    {
      "epoch": 0.07465607564677239,
      "grad_norm": 1.4765625,
      "learning_rate": 4.543765029592637e-05,
      "loss": 1.2405645370483398,
      "num_input_tokens_seen": 599054400,
      "step": 2110,
      "train_runtime": 20519.6591,
      "train_tokens_per_second": 29194.169
    },
    {
      "epoch": 0.07500989591050117,
      "grad_norm": 1.4921875,
      "learning_rate": 4.541889997519403e-05,
      "loss": 1.2238348007202149,
      "num_input_tokens_seen": 601905792,
      "step": 2120,
      "train_runtime": 20619.7969,
      "train_tokens_per_second": 29190.675
    },
    {
      "epoch": 0.07536371617422995,
      "grad_norm": 1.40625,
      "learning_rate": 4.5400172847867095e-05,
      "loss": 1.2187747001647948,
      "num_input_tokens_seen": 604781696,
      "step": 2130,
      "train_runtime": 20719.7377,
      "train_tokens_per_second": 29188.675
    },
    {
      "epoch": 0.07571753643795873,
      "grad_norm": 1.4609375,
      "learning_rate": 4.5381468866169466e-05,
      "loss": 1.2268861770629882,
      "num_input_tokens_seen": 607602112,
      "step": 2140,
      "train_runtime": 20813.8676,
      "train_tokens_per_second": 29192.177
    },
    {
      "epoch": 0.0760713567016875,
      "grad_norm": 1.3984375,
      "learning_rate": 4.5362787982462616e-05,
      "loss": 1.2039087295532227,
      "num_input_tokens_seen": 610399360,
      "step": 2150,
      "train_runtime": 20911.6496,
      "train_tokens_per_second": 29189.441
    },
    {
      "epoch": 0.07642517696541629,
      "grad_norm": 1.4765625,
      "learning_rate": 4.5344130149245275e-05,
      "loss": 1.2154084205627442,
      "num_input_tokens_seen": 613185408,
      "step": 2160,
      "train_runtime": 21004.4077,
      "train_tokens_per_second": 29193.178
    },
    {
      "epoch": 0.07677899722914507,
      "grad_norm": 1.4375,
      "learning_rate": 4.5325495319152715e-05,
      "loss": 1.2252399444580078,
      "num_input_tokens_seen": 616021440,
      "step": 2170,
      "train_runtime": 21101.0227,
      "train_tokens_per_second": 29193.914
    },
    {
      "epoch": 0.07713281749287385,
      "grad_norm": 1.46875,
      "learning_rate": 4.530688344495644e-05,
      "loss": 1.2119600296020507,
      "num_input_tokens_seen": 618854080,
      "step": 2180,
      "train_runtime": 21196.471,
      "train_tokens_per_second": 29196.09
    },
    {
      "epoch": 0.07748663775660261,
      "grad_norm": 1.3671875,
      "learning_rate": 4.528829447956357e-05,
      "loss": 1.213577938079834,
      "num_input_tokens_seen": 621675904,
      "step": 2190,
      "train_runtime": 21292.4057,
      "train_tokens_per_second": 29197.072
    },
    {
      "epoch": 0.07784045802033139,
      "grad_norm": 1.4140625,
      "learning_rate": 4.526972837601633e-05,
      "loss": 1.2243017196655273,
      "num_input_tokens_seen": 624492288,
      "step": 2200,
      "train_runtime": 21388.1015,
      "train_tokens_per_second": 29198.117
    },
    {
      "epoch": 0.07819427828406017,
      "grad_norm": 1.4140625,
      "learning_rate": 4.525118508749165e-05,
      "loss": 1.2132570266723632,
      "num_input_tokens_seen": 627315200,
      "step": 2210,
      "train_runtime": 21484.547,
      "train_tokens_per_second": 29198.437
    },
    {
      "epoch": 0.07854809854778895,
      "grad_norm": 1.4609375,
      "learning_rate": 4.5232664567300546e-05,
      "loss": 1.1953063011169434,
      "num_input_tokens_seen": 630126080,
      "step": 2220,
      "train_runtime": 21581.9984,
      "train_tokens_per_second": 29196.837
    },
    {
      "epoch": 0.07890191881151773,
      "grad_norm": 1.4296875,
      "learning_rate": 4.521416676888773e-05,
      "loss": 1.2052556991577148,
      "num_input_tokens_seen": 632958400,
      "step": 2230,
      "train_runtime": 21677.576,
      "train_tokens_per_second": 29198.763
    },
    {
      "epoch": 0.07925573907524651,
      "grad_norm": 1.40625,
      "learning_rate": 4.519569164583107e-05,
      "loss": 1.2163087844848632,
      "num_input_tokens_seen": 635800064,
      "step": 2240,
      "train_runtime": 21777.5008,
      "train_tokens_per_second": 29195.272
    },
    {
      "epoch": 0.07960955933897529,
      "grad_norm": 1.3671875,
      "learning_rate": 4.517723915184109e-05,
      "loss": 1.2182098388671876,
      "num_input_tokens_seen": 638624768,
      "step": 2250,
      "train_runtime": 21871.5979,
      "train_tokens_per_second": 29198.816
    },
    {
      "epoch": 0.07996337960270407,
      "grad_norm": 1.5546875,
      "learning_rate": 4.5158809240760506e-05,
      "loss": 1.222600269317627,
      "num_input_tokens_seen": 641490688,
      "step": 2260,
      "train_runtime": 21971.3813,
      "train_tokens_per_second": 29196.648
    },
    {
      "epoch": 0.08031719986643285,
      "grad_norm": 1.4375,
      "learning_rate": 4.514040186656375e-05,
      "loss": 1.2230731964111328,
      "num_input_tokens_seen": 644356096,
      "step": 2270,
      "train_runtime": 22066.9376,
      "train_tokens_per_second": 29200.069
    },
    {
      "epoch": 0.08067102013016163,
      "grad_norm": 1.375,
      "learning_rate": 4.512201698335644e-05,
      "loss": 1.2082666397094726,
      "num_input_tokens_seen": 647194560,
      "step": 2280,
      "train_runtime": 22165.6287,
      "train_tokens_per_second": 29198.114
    },
    {
      "epoch": 0.08102484039389041,
      "grad_norm": 1.3984375,
      "learning_rate": 4.510365454537496e-05,
      "loss": 1.1968767166137695,
      "num_input_tokens_seen": 650039296,
      "step": 2290,
      "train_runtime": 22261.5949,
      "train_tokens_per_second": 29200.033
    },
    {
      "epoch": 0.08137866065761919,
      "grad_norm": 1.5234375,
      "learning_rate": 4.5085314506985945e-05,
      "loss": 1.2200936317443847,
      "num_input_tokens_seen": 652945088,
      "step": 2300,
      "train_runtime": 22361.7776,
      "train_tokens_per_second": 29199.158
    },
    {
      "epoch": 0.08173248092134797,
      "grad_norm": 1.453125,
      "learning_rate": 4.50669968226858e-05,
      "loss": 1.2192657470703125,
      "num_input_tokens_seen": 655788096,
      "step": 2310,
      "train_runtime": 22458.7173,
      "train_tokens_per_second": 29199.713
    },
    {
      "epoch": 0.08208630118507675,
      "grad_norm": 1.359375,
      "learning_rate": 4.504870144710027e-05,
      "loss": 1.206212043762207,
      "num_input_tokens_seen": 658622528,
      "step": 2320,
      "train_runtime": 22555.1242,
      "train_tokens_per_second": 29200.572
    },
    {
      "epoch": 0.08244012144880553,
      "grad_norm": 1.34375,
      "learning_rate": 4.5030428334983884e-05,
      "loss": 1.208874225616455,
      "num_input_tokens_seen": 661542720,
      "step": 2330,
      "train_runtime": 22658.8215,
      "train_tokens_per_second": 29195.813
    },
    {
      "epoch": 0.0827939417125343,
      "grad_norm": 1.421875,
      "learning_rate": 4.501217744121959e-05,
      "loss": 1.2202801704406738,
      "num_input_tokens_seen": 664371264,
      "step": 2340,
      "train_runtime": 22754.4931,
      "train_tokens_per_second": 29197.366
    },
    {
      "epoch": 0.08314776197626308,
      "grad_norm": 1.4296875,
      "learning_rate": 4.499394872081821e-05,
      "loss": 1.2100823402404786,
      "num_input_tokens_seen": 667226688,
      "step": 2350,
      "train_runtime": 22851.286,
      "train_tokens_per_second": 29198.649
    },
    {
      "epoch": 0.08350158223999186,
      "grad_norm": 1.5,
      "learning_rate": 4.4975742128918e-05,
      "loss": 1.2218746185302733,
      "num_input_tokens_seen": 670128512,
      "step": 2360,
      "train_runtime": 22949.9588,
      "train_tokens_per_second": 29199.552
    },
    {
      "epoch": 0.08385540250372064,
      "grad_norm": 1.5,
      "learning_rate": 4.495755762078418e-05,
      "loss": 1.2034995079040527,
      "num_input_tokens_seen": 672977984,
      "step": 2370,
      "train_runtime": 23045.0625,
      "train_tokens_per_second": 29202.697
    },
    {
      "epoch": 0.08420922276744942,
      "grad_norm": 1.4609375,
      "learning_rate": 4.49393951518085e-05,
      "loss": 1.2213037490844727,
      "num_input_tokens_seen": 675826496,
      "step": 2380,
      "train_runtime": 23142.2101,
      "train_tokens_per_second": 29203.196
    },
    {
      "epoch": 0.0845630430311782,
      "grad_norm": 1.4921875,
      "learning_rate": 4.4921254677508716e-05,
      "loss": 1.2164669990539552,
      "num_input_tokens_seen": 678657856,
      "step": 2390,
      "train_runtime": 23236.586,
      "train_tokens_per_second": 29206.436
    },
    {
      "epoch": 0.08491686329490698,
      "grad_norm": 1.453125,
      "learning_rate": 4.490313615352821e-05,
      "loss": 1.2158859252929688,
      "num_input_tokens_seen": 681497152,
      "step": 2400,
      "train_runtime": 23331.9726,
      "train_tokens_per_second": 29208.724
    },
    {
      "epoch": 0.08527068355863576,
      "grad_norm": 1.421875,
      "learning_rate": 4.48850395356355e-05,
      "loss": 1.199061393737793,
      "num_input_tokens_seen": 684355968,
      "step": 2410,
      "train_runtime": 23429.1563,
      "train_tokens_per_second": 29209.587
    },
    {
      "epoch": 0.08562450382236454,
      "grad_norm": 1.4296875,
      "learning_rate": 4.486696477972375e-05,
      "loss": 1.2099312782287597,
      "num_input_tokens_seen": 687187904,
      "step": 2420,
      "train_runtime": 23523.5488,
      "train_tokens_per_second": 29212.765
    },
    {
      "epoch": 0.08597832408609332,
      "grad_norm": 1.40625,
      "learning_rate": 4.484891184181041e-05,
      "loss": 1.2046204566955567,
      "num_input_tokens_seen": 689986048,
      "step": 2430,
      "train_runtime": 23616.1301,
      "train_tokens_per_second": 29216.728
    },
    {
      "epoch": 0.0863321443498221,
      "grad_norm": 1.421875,
      "learning_rate": 4.483088067803662e-05,
      "loss": 1.210502815246582,
      "num_input_tokens_seen": 692802496,
      "step": 2440,
      "train_runtime": 23713.0167,
      "train_tokens_per_second": 29216.127
    },
    {
      "epoch": 0.08668596461355087,
      "grad_norm": 1.390625,
      "learning_rate": 4.481287124466697e-05,
      "loss": 1.221125030517578,
      "num_input_tokens_seen": 695674432,
      "step": 2450,
      "train_runtime": 23811.4503,
      "train_tokens_per_second": 29215.962
    },
    {
      "epoch": 0.08703978487727965,
      "grad_norm": 1.3984375,
      "learning_rate": 4.479488349808885e-05,
      "loss": 1.2127570152282714,
      "num_input_tokens_seen": 698575488,
      "step": 2460,
      "train_runtime": 23911.4328,
      "train_tokens_per_second": 29215.125
    },
    {
      "epoch": 0.08739360514100843,
      "grad_norm": 1.4453125,
      "learning_rate": 4.4776917394812114e-05,
      "loss": 1.2150564193725586,
      "num_input_tokens_seen": 701434496,
      "step": 2470,
      "train_runtime": 24011.2645,
      "train_tokens_per_second": 29212.726
    },
    {
      "epoch": 0.0877474254047372,
      "grad_norm": 1.421875,
      "learning_rate": 4.475897289146862e-05,
      "loss": 1.2245460510253907,
      "num_input_tokens_seen": 704291840,
      "step": 2480,
      "train_runtime": 24111.047,
      "train_tokens_per_second": 29210.338
    },
    {
      "epoch": 0.08810124566846599,
      "grad_norm": 1.3828125,
      "learning_rate": 4.4741049944811806e-05,
      "loss": 1.198171329498291,
      "num_input_tokens_seen": 707117184,
      "step": 2490,
      "train_runtime": 24207.8934,
      "train_tokens_per_second": 29210.191
    },
    {
      "epoch": 0.08845506593219477,
      "grad_norm": 1.421875,
      "learning_rate": 4.472314851171621e-05,
      "loss": 1.2186487197875977,
      "num_input_tokens_seen": 709938944,
      "step": 2500,
      "train_runtime": 24305.3319,
      "train_tokens_per_second": 29209.185
    },
    {
      "epoch": 0.08880888619592354,
      "grad_norm": 1.421875,
      "learning_rate": 4.4705268549177084e-05,
      "loss": 1.2124378204345703,
      "num_input_tokens_seen": 712816832,
      "step": 2510,
      "train_runtime": 24403.5722,
      "train_tokens_per_second": 29209.528
    },
    {
      "epoch": 0.08916270645965232,
      "grad_norm": 1.4296875,
      "learning_rate": 4.468741001430989e-05,
      "loss": 1.2078802108764648,
      "num_input_tokens_seen": 715680704,
      "step": 2520,
      "train_runtime": 24501.8893,
      "train_tokens_per_second": 29209.205
    },
    {
      "epoch": 0.0895165267233811,
      "grad_norm": 1.4609375,
      "learning_rate": 4.466957286434997e-05,
      "loss": 1.2123603820800781,
      "num_input_tokens_seen": 718503552,
      "step": 2530,
      "train_runtime": 24596.8177,
      "train_tokens_per_second": 29211.24
    },
    {
      "epoch": 0.08987034698710988,
      "grad_norm": 1.375,
      "learning_rate": 4.4651757056652e-05,
      "loss": 1.2005475997924804,
      "num_input_tokens_seen": 721313088,
      "step": 2540,
      "train_runtime": 24693.1613,
      "train_tokens_per_second": 29211.047
    },
    {
      "epoch": 0.09022416725083866,
      "grad_norm": 1.359375,
      "learning_rate": 4.463396254868968e-05,
      "loss": 1.2158756256103516,
      "num_input_tokens_seen": 724171456,
      "step": 2550,
      "train_runtime": 24793.0683,
      "train_tokens_per_second": 29208.626
    },
    {
      "epoch": 0.09057798751456744,
      "grad_norm": 1.5078125,
      "learning_rate": 4.461618929805519e-05,
      "loss": 1.2183591842651367,
      "num_input_tokens_seen": 727007232,
      "step": 2560,
      "train_runtime": 24891.7148,
      "train_tokens_per_second": 29206.796
    },
    {
      "epoch": 0.09093180777829622,
      "grad_norm": 1.46875,
      "learning_rate": 4.459843726245888e-05,
      "loss": 1.218313503265381,
      "num_input_tokens_seen": 729885696,
      "step": 2570,
      "train_runtime": 24988.5633,
      "train_tokens_per_second": 29208.79
    },
    {
      "epoch": 0.091285628042025,
      "grad_norm": 1.421875,
      "learning_rate": 4.458070639972875e-05,
      "loss": 1.2011194229125977,
      "num_input_tokens_seen": 732750016,
      "step": 2580,
      "train_runtime": 25085.7208,
      "train_tokens_per_second": 29209.845
    },
    {
      "epoch": 0.09163944830575378,
      "grad_norm": 1.390625,
      "learning_rate": 4.456299666781007e-05,
      "loss": 1.190675926208496,
      "num_input_tokens_seen": 735551168,
      "step": 2590,
      "train_runtime": 25178.9671,
      "train_tokens_per_second": 29212.921
    },
    {
      "epoch": 0.09199326856948256,
      "grad_norm": 1.390625,
      "learning_rate": 4.4545308024764984e-05,
      "loss": 1.208780288696289,
      "num_input_tokens_seen": 738383808,
      "step": 2600,
      "train_runtime": 25279.1051,
      "train_tokens_per_second": 29209.254
    },
    {
      "epoch": 0.09234708883321134,
      "grad_norm": 1.453125,
      "learning_rate": 4.452764042877207e-05,
      "loss": 1.2048264503479005,
      "num_input_tokens_seen": 741271168,
      "step": 2610,
      "train_runtime": 25377.7877,
      "train_tokens_per_second": 29209.448
    },
    {
      "epoch": 0.09270090909694012,
      "grad_norm": 1.46875,
      "learning_rate": 4.45099938381259e-05,
      "loss": 1.2072249412536622,
      "num_input_tokens_seen": 744088896,
      "step": 2620,
      "train_runtime": 25474.1285,
      "train_tokens_per_second": 29209.592
    },
    {
      "epoch": 0.0930547293606689,
      "grad_norm": 1.453125,
      "learning_rate": 4.449236821123667e-05,
      "loss": 1.2159435272216796,
      "num_input_tokens_seen": 746930688,
      "step": 2630,
      "train_runtime": 25569.9338,
      "train_tokens_per_second": 29211.288
    },
    {
      "epoch": 0.09340854962439768,
      "grad_norm": 1.3515625,
      "learning_rate": 4.447476350662976e-05,
      "loss": 1.2045675277709962,
      "num_input_tokens_seen": 749821440,
      "step": 2640,
      "train_runtime": 25670.1256,
      "train_tokens_per_second": 29209.886
    },
    {
      "epoch": 0.09376236988812646,
      "grad_norm": 1.3359375,
      "learning_rate": 4.4457179682945346e-05,
      "loss": 1.1950159072875977,
      "num_input_tokens_seen": 752690176,
      "step": 2650,
      "train_runtime": 25769.5087,
      "train_tokens_per_second": 29208.557
    },
    {
      "epoch": 0.09411619015185524,
      "grad_norm": 1.375,
      "learning_rate": 4.443961669893798e-05,
      "loss": 1.1952871322631835,
      "num_input_tokens_seen": 755524736,
      "step": 2660,
      "train_runtime": 25866.5417,
      "train_tokens_per_second": 29208.572
    },
    {
      "epoch": 0.09447001041558402,
      "grad_norm": 1.40625,
      "learning_rate": 4.4422074513476155e-05,
      "loss": 1.217361831665039,
      "num_input_tokens_seen": 758300864,
      "step": 2670,
      "train_runtime": 25960.4008,
      "train_tokens_per_second": 29209.906
    },
    {
      "epoch": 0.0948238306793128,
      "grad_norm": 1.515625,
      "learning_rate": 4.4404553085541955e-05,
      "loss": 1.183639907836914,
      "num_input_tokens_seen": 761173376,
      "step": 2680,
      "train_runtime": 26056.1744,
      "train_tokens_per_second": 29212.783
    },
    {
      "epoch": 0.09517765094304158,
      "grad_norm": 1.4140625,
      "learning_rate": 4.438705237423063e-05,
      "loss": 1.196107769012451,
      "num_input_tokens_seen": 764039808,
      "step": 2690,
      "train_runtime": 26152.4055,
      "train_tokens_per_second": 29214.896
    },
    {
      "epoch": 0.09553147120677036,
      "grad_norm": 1.4296875,
      "learning_rate": 4.436957233875017e-05,
      "loss": 1.1997604370117188,
      "num_input_tokens_seen": 766838592,
      "step": 2700,
      "train_runtime": 26247.4442,
      "train_tokens_per_second": 29215.743
    },
    {
      "epoch": 0.09588529147049912,
      "grad_norm": 1.4140625,
      "learning_rate": 4.4352112938420956e-05,
      "loss": 1.194338035583496,
      "num_input_tokens_seen": 769722496,
      "step": 2710,
      "train_runtime": 26347.254,
      "train_tokens_per_second": 29214.524
    },
    {
      "epoch": 0.0962391117342279,
      "grad_norm": 1.359375,
      "learning_rate": 4.433467413267529e-05,
      "loss": 1.214699649810791,
      "num_input_tokens_seen": 772516544,
      "step": 2720,
      "train_runtime": 26443.1311,
      "train_tokens_per_second": 29214.261
    },
    {
      "epoch": 0.09659293199795668,
      "grad_norm": 1.453125,
      "learning_rate": 4.431725588105708e-05,
      "loss": 1.2045160293579102,
      "num_input_tokens_seen": 775288064,
      "step": 2730,
      "train_runtime": 26538.1636,
      "train_tokens_per_second": 29214.081
    },
    {
      "epoch": 0.09694675226168546,
      "grad_norm": 1.453125,
      "learning_rate": 4.4299858143221377e-05,
      "loss": 1.2014851570129395,
      "num_input_tokens_seen": 778139008,
      "step": 2740,
      "train_runtime": 26636.0213,
      "train_tokens_per_second": 29213.785
    },
    {
      "epoch": 0.09730057252541424,
      "grad_norm": 1.421875,
      "learning_rate": 4.4282480878934065e-05,
      "loss": 1.2017187118530273,
      "num_input_tokens_seen": 781009600,
      "step": 2750,
      "train_runtime": 26734.791,
      "train_tokens_per_second": 29213.23
    },
    {
      "epoch": 0.09765439278914302,
      "grad_norm": 1.4453125,
      "learning_rate": 4.4265124048071346e-05,
      "loss": 1.2163751602172852,
      "num_input_tokens_seen": 783864896,
      "step": 2760,
      "train_runtime": 26836.8976,
      "train_tokens_per_second": 29208.477
    },
    {
      "epoch": 0.0980082130528718,
      "grad_norm": 1.421875,
      "learning_rate": 4.4247787610619477e-05,
      "loss": 1.2004958152770997,
      "num_input_tokens_seen": 786664128,
      "step": 2770,
      "train_runtime": 26931.3977,
      "train_tokens_per_second": 29209.926
    },
    {
      "epoch": 0.09836203331660058,
      "grad_norm": 1.4296875,
      "learning_rate": 4.42304715266743e-05,
      "loss": 1.2016335487365724,
      "num_input_tokens_seen": 789491136,
      "step": 2780,
      "train_runtime": 27028.9694,
      "train_tokens_per_second": 29209.073
    },
    {
      "epoch": 0.09871585358032936,
      "grad_norm": 1.421875,
      "learning_rate": 4.421317575644092e-05,
      "loss": 1.202066707611084,
      "num_input_tokens_seen": 792327488,
      "step": 2790,
      "train_runtime": 27126.2188,
      "train_tokens_per_second": 29208.918
    },
    {
      "epoch": 0.09906967384405814,
      "grad_norm": 1.421875,
      "learning_rate": 4.419590026023325e-05,
      "loss": 1.1856679916381836,
      "num_input_tokens_seen": 795147904,
      "step": 2800,
      "train_runtime": 27225.5987,
      "train_tokens_per_second": 29205.892
    },
    {
      "epoch": 0.09942349410778692,
      "grad_norm": 1.390625,
      "learning_rate": 4.417864499847368e-05,
      "loss": 1.1965105056762695,
      "num_input_tokens_seen": 797988288,
      "step": 2810,
      "train_runtime": 27321.0049,
      "train_tokens_per_second": 29207.867
    },
    {
      "epoch": 0.0997773143715157,
      "grad_norm": 1.4609375,
      "learning_rate": 4.4161409931692676e-05,
      "loss": 1.1999900817871094,
      "num_input_tokens_seen": 800824704,
      "step": 2820,
      "train_runtime": 27417.1188,
      "train_tokens_per_second": 29208.93
    },
    {
      "epoch": 0.10013113463524448,
      "grad_norm": 1.40625,
      "learning_rate": 4.414419502052841e-05,
      "loss": 1.1976238250732423,
      "num_input_tokens_seen": 803713152,
      "step": 2830,
      "train_runtime": 27517.7694,
      "train_tokens_per_second": 29207.06
    },
    {
      "epoch": 0.10048495489897326,
      "grad_norm": 1.3671875,
      "learning_rate": 4.412700022572637e-05,
      "loss": 1.198695182800293,
      "num_input_tokens_seen": 806536128,
      "step": 2840,
      "train_runtime": 27614.9268,
      "train_tokens_per_second": 29206.528
    },
    {
      "epoch": 0.10083877516270204,
      "grad_norm": 1.421875,
      "learning_rate": 4.410982550813902e-05,
      "loss": 1.1939813613891601,
      "num_input_tokens_seen": 809369600,
      "step": 2850,
      "train_runtime": 27710.2314,
      "train_tokens_per_second": 29208.331
    },
    {
      "epoch": 0.10119259542643082,
      "grad_norm": 1.40625,
      "learning_rate": 4.409267082872535e-05,
      "loss": 1.1966314315795898,
      "num_input_tokens_seen": 812267648,
      "step": 2860,
      "train_runtime": 27813.2768,
      "train_tokens_per_second": 29204.313
    },
    {
      "epoch": 0.1015464156901596,
      "grad_norm": 1.4140625,
      "learning_rate": 4.407553614855059e-05,
      "loss": 1.1915521621704102,
      "num_input_tokens_seen": 815092928,
      "step": 2870,
      "train_runtime": 27910.609,
      "train_tokens_per_second": 29203.696
    },
    {
      "epoch": 0.10190023595388838,
      "grad_norm": 1.5,
      "learning_rate": 4.405842142878579e-05,
      "loss": 1.1902820587158203,
      "num_input_tokens_seen": 817994752,
      "step": 2880,
      "train_runtime": 28010.5023,
      "train_tokens_per_second": 29203.145
    },
    {
      "epoch": 0.10225405621761716,
      "grad_norm": 1.4453125,
      "learning_rate": 4.404132663070745e-05,
      "loss": 1.1870713233947754,
      "num_input_tokens_seen": 820838144,
      "step": 2890,
      "train_runtime": 28105.8878,
      "train_tokens_per_second": 29205.202
    },
    {
      "epoch": 0.10260787648134594,
      "grad_norm": 1.4921875,
      "learning_rate": 4.402425171569716e-05,
      "loss": 1.1928697586059571,
      "num_input_tokens_seen": 823684480,
      "step": 2900,
      "train_runtime": 28204.6686,
      "train_tokens_per_second": 29203.835
    },
    {
      "epoch": 0.10296169674507472,
      "grad_norm": 1.4609375,
      "learning_rate": 4.400719664524127e-05,
      "loss": 1.197272777557373,
      "num_input_tokens_seen": 826506304,
      "step": 2910,
      "train_runtime": 28301.1778,
      "train_tokens_per_second": 29203.954
    },
    {
      "epoch": 0.1033155170088035,
      "grad_norm": 1.375,
      "learning_rate": 4.399016138093044e-05,
      "loss": 1.2012823104858399,
      "num_input_tokens_seen": 829323264,
      "step": 2920,
      "train_runtime": 28398.6908,
      "train_tokens_per_second": 29202.87
    },
    {
      "epoch": 0.10366933727253227,
      "grad_norm": 1.4609375,
      "learning_rate": 4.397314588445937e-05,
      "loss": 1.2069860458374024,
      "num_input_tokens_seen": 832161984,
      "step": 2930,
      "train_runtime": 28495.2588,
      "train_tokens_per_second": 29203.524
    },
    {
      "epoch": 0.10402315753626105,
      "grad_norm": 1.375,
      "learning_rate": 4.395615011762637e-05,
      "loss": 1.195295238494873,
      "num_input_tokens_seen": 834996416,
      "step": 2940,
      "train_runtime": 28591.0724,
      "train_tokens_per_second": 29204.795
    },
    {
      "epoch": 0.10437697779998983,
      "grad_norm": 1.3828125,
      "learning_rate": 4.3939174042333057e-05,
      "loss": 1.2002138137817382,
      "num_input_tokens_seen": 837916736,
      "step": 2950,
      "train_runtime": 28691.9256,
      "train_tokens_per_second": 29203.921
    },
    {
      "epoch": 0.10473079806371861,
      "grad_norm": 1.4296875,
      "learning_rate": 4.3922217620583904e-05,
      "loss": 1.203592014312744,
      "num_input_tokens_seen": 840767040,
      "step": 2960,
      "train_runtime": 28789.0314,
      "train_tokens_per_second": 29204.423
    },
    {
      "epoch": 0.10508461832744738,
      "grad_norm": 1.453125,
      "learning_rate": 4.3905280814486025e-05,
      "loss": 1.1943778038024901,
      "num_input_tokens_seen": 843630912,
      "step": 2970,
      "train_runtime": 28889.2004,
      "train_tokens_per_second": 29202.294
    },
    {
      "epoch": 0.10543843859117616,
      "grad_norm": 1.4375,
      "learning_rate": 4.388836358624867e-05,
      "loss": 1.2080059051513672,
      "num_input_tokens_seen": 846460864,
      "step": 2980,
      "train_runtime": 28985.7047,
      "train_tokens_per_second": 29202.701
    },
    {
      "epoch": 0.10579225885490494,
      "grad_norm": 1.3984375,
      "learning_rate": 4.3871465898182976e-05,
      "loss": 1.192498779296875,
      "num_input_tokens_seen": 849315712,
      "step": 2990,
      "train_runtime": 29082.8192,
      "train_tokens_per_second": 29203.349
    },
    {
      "epoch": 0.10614607911863372,
      "grad_norm": 1.4765625,
      "learning_rate": 4.385458771270156e-05,
      "loss": 1.209206771850586,
      "num_input_tokens_seen": 852171840,
      "step": 3000,
      "train_runtime": 29180.664,
      "train_tokens_per_second": 29203.305
    },
    {
      "epoch": 0.1064998993823625,
      "grad_norm": 1.390625,
      "learning_rate": 4.3837728992318205e-05,
      "loss": 1.181245994567871,
      "num_input_tokens_seen": 855081664,
      "step": 3010,
      "train_runtime": 29282.3022,
      "train_tokens_per_second": 29201.313
    },
    {
      "epoch": 0.10685371964609128,
      "grad_norm": 1.421875,
      "learning_rate": 4.382088969964746e-05,
      "loss": 1.1841010093688964,
      "num_input_tokens_seen": 857962944,
      "step": 3020,
      "train_runtime": 29383.1457,
      "train_tokens_per_second": 29199.152
    },
    {
      "epoch": 0.10720753990982006,
      "grad_norm": 1.359375,
      "learning_rate": 4.380406979740436e-05,
      "loss": 1.1869535446166992,
      "num_input_tokens_seen": 860796160,
      "step": 3030,
      "train_runtime": 29479.4075,
      "train_tokens_per_second": 29199.914
    },
    {
      "epoch": 0.10756136017354884,
      "grad_norm": 1.4375,
      "learning_rate": 4.3787269248403994e-05,
      "loss": 1.1952959060668946,
      "num_input_tokens_seen": 863619072,
      "step": 3040,
      "train_runtime": 29577.2786,
      "train_tokens_per_second": 29198.733
    },
    {
      "epoch": 0.10791518043727762,
      "grad_norm": 1.390625,
      "learning_rate": 4.377048801556126e-05,
      "loss": 1.1918405532836913,
      "num_input_tokens_seen": 866453888,
      "step": 3050,
      "train_runtime": 29673.0985,
      "train_tokens_per_second": 29199.98
    },
    {
      "epoch": 0.1082690007010064,
      "grad_norm": 1.375,
      "learning_rate": 4.3753726061890446e-05,
      "loss": 1.189606285095215,
      "num_input_tokens_seen": 869239744,
      "step": 3060,
      "train_runtime": 29767.6504,
      "train_tokens_per_second": 29200.818
    },
    {
      "epoch": 0.10862282096473518,
      "grad_norm": 1.4375,
      "learning_rate": 4.373698335050488e-05,
      "loss": 1.1768980026245117,
      "num_input_tokens_seen": 872085568,
      "step": 3070,
      "train_runtime": 29866.9994,
      "train_tokens_per_second": 29198.968
    },
    {
      "epoch": 0.10897664122846396,
      "grad_norm": 1.4609375,
      "learning_rate": 4.372025984461667e-05,
      "loss": 1.194584274291992,
      "num_input_tokens_seen": 874937024,
      "step": 3080,
      "train_runtime": 29966.9065,
      "train_tokens_per_second": 29196.775
    },
    {
      "epoch": 0.10933046149219273,
      "grad_norm": 1.390625,
      "learning_rate": 4.370355550753629e-05,
      "loss": 1.1898836135864257,
      "num_input_tokens_seen": 877781248,
      "step": 3090,
      "train_runtime": 30063.6946,
      "train_tokens_per_second": 29197.384
    },
    {
      "epoch": 0.10968428175592151,
      "grad_norm": 1.375,
      "learning_rate": 4.368687030267226e-05,
      "loss": 1.201324462890625,
      "num_input_tokens_seen": 880572416,
      "step": 3100,
      "train_runtime": 30155.131,
      "train_tokens_per_second": 29201.412
    },
    {
      "epoch": 0.1100381020196503,
      "grad_norm": 1.484375,
      "learning_rate": 4.367020419353081e-05,
      "loss": 1.1825067520141601,
      "num_input_tokens_seen": 883425984,
      "step": 3110,
      "train_runtime": 30252.9592,
      "train_tokens_per_second": 29201.308
    },
    {
      "epoch": 0.11039192228337907,
      "grad_norm": 1.359375,
      "learning_rate": 4.365355714371558e-05,
      "loss": 1.1842081069946289,
      "num_input_tokens_seen": 886238272,
      "step": 3120,
      "train_runtime": 30347.0201,
      "train_tokens_per_second": 29203.469
    },
    {
      "epoch": 0.11074574254710785,
      "grad_norm": 1.3671875,
      "learning_rate": 4.3636929116927235e-05,
      "loss": 1.1948518753051758,
      "num_input_tokens_seen": 889061760,
      "step": 3130,
      "train_runtime": 30445.2537,
      "train_tokens_per_second": 29201.982
    },
    {
      "epoch": 0.11109956281083663,
      "grad_norm": 1.4375,
      "learning_rate": 4.362032007696314e-05,
      "loss": 1.1665071487426757,
      "num_input_tokens_seen": 891973888,
      "step": 3140,
      "train_runtime": 30546.3933,
      "train_tokens_per_second": 29200.629
    },
    {
      "epoch": 0.11145338307456541,
      "grad_norm": 1.4765625,
      "learning_rate": 4.360372998771707e-05,
      "loss": 1.1946119308471679,
      "num_input_tokens_seen": 894815232,
      "step": 3150,
      "train_runtime": 30643.8524,
      "train_tokens_per_second": 29200.481
    },
    {
      "epoch": 0.11180720333829419,
      "grad_norm": 1.4140625,
      "learning_rate": 4.358715881317884e-05,
      "loss": 1.1860280990600587,
      "num_input_tokens_seen": 897675520,
      "step": 3160,
      "train_runtime": 30741.6034,
      "train_tokens_per_second": 29200.673
    },
    {
      "epoch": 0.11216102360202297,
      "grad_norm": 1.4140625,
      "learning_rate": 4.357060651743399e-05,
      "loss": 1.1771388053894043,
      "num_input_tokens_seen": 900471808,
      "step": 3170,
      "train_runtime": 30835.7744,
      "train_tokens_per_second": 29202.179
    },
    {
      "epoch": 0.11251484386575175,
      "grad_norm": 1.34375,
      "learning_rate": 4.3554073064663454e-05,
      "loss": 1.1875066757202148,
      "num_input_tokens_seen": 903332224,
      "step": 3180,
      "train_runtime": 30933.4199,
      "train_tokens_per_second": 29202.469
    },
    {
      "epoch": 0.11286866412948053,
      "grad_norm": 1.3671875,
      "learning_rate": 4.353755841914325e-05,
      "loss": 1.1925976753234864,
      "num_input_tokens_seen": 906127424,
      "step": 3190,
      "train_runtime": 31029.297,
      "train_tokens_per_second": 29202.319
    },
    {
      "epoch": 0.11322248439320931,
      "grad_norm": 1.515625,
      "learning_rate": 4.3521062545244116e-05,
      "loss": 1.1901744842529296,
      "num_input_tokens_seen": 908971136,
      "step": 3200,
      "train_runtime": 31127.8529,
      "train_tokens_per_second": 29201.215
    },
    {
      "epoch": 0.11357630465693809,
      "grad_norm": 1.390625,
      "learning_rate": 4.350458540743126e-05,
      "loss": 1.188551902770996,
      "num_input_tokens_seen": 911782080,
      "step": 3210,
      "train_runtime": 31222.2894,
      "train_tokens_per_second": 29202.922
    },
    {
      "epoch": 0.11393012492066686,
      "grad_norm": 1.40625,
      "learning_rate": 4.3488126970263955e-05,
      "loss": 1.1836232185363769,
      "num_input_tokens_seen": 914660992,
      "step": 3220,
      "train_runtime": 31321.8772,
      "train_tokens_per_second": 29201.985
    },
    {
      "epoch": 0.11428394518439564,
      "grad_norm": 1.4140625,
      "learning_rate": 4.347168719839527e-05,
      "loss": 1.1906529426574708,
      "num_input_tokens_seen": 917527296,
      "step": 3230,
      "train_runtime": 31417.5016,
      "train_tokens_per_second": 29204.337
    },
    {
      "epoch": 0.11463776544812442,
      "grad_norm": 1.40625,
      "learning_rate": 4.345526605657173e-05,
      "loss": 1.181631851196289,
      "num_input_tokens_seen": 920384640,
      "step": 3240,
      "train_runtime": 31516.4165,
      "train_tokens_per_second": 29203.34
    },
    {
      "epoch": 0.1149915857118532,
      "grad_norm": 1.4375,
      "learning_rate": 4.343886350963304e-05,
      "loss": 1.1828688621520995,
      "num_input_tokens_seen": 923238016,
      "step": 3250,
      "train_runtime": 31615.9212,
      "train_tokens_per_second": 29201.68
    },
    {
      "epoch": 0.11534540597558197,
      "grad_norm": 1.359375,
      "learning_rate": 4.3422479522511697e-05,
      "loss": 1.1837403297424316,
      "num_input_tokens_seen": 926139264,
      "step": 3260,
      "train_runtime": 31719.5933,
      "train_tokens_per_second": 29197.703
    },
    {
      "epoch": 0.11569922623931075,
      "grad_norm": 1.46875,
      "learning_rate": 4.340611406023272e-05,
      "loss": 1.1957791328430176,
      "num_input_tokens_seen": 928941120,
      "step": 3270,
      "train_runtime": 31812.4078,
      "train_tokens_per_second": 29200.591
    },
    {
      "epoch": 0.11605304650303953,
      "grad_norm": 1.4296875,
      "learning_rate": 4.338976708791336e-05,
      "loss": 1.1935272216796875,
      "num_input_tokens_seen": 931777472,
      "step": 3280,
      "train_runtime": 31909.518,
      "train_tokens_per_second": 29200.613
    },
    {
      "epoch": 0.11640686676676831,
      "grad_norm": 1.4921875,
      "learning_rate": 4.337343857076272e-05,
      "loss": 1.1873862266540527,
      "num_input_tokens_seen": 934654080,
      "step": 3290,
      "train_runtime": 32009.69,
      "train_tokens_per_second": 29199.098
    },
    {
      "epoch": 0.11676068703049709,
      "grad_norm": 1.4453125,
      "learning_rate": 4.33571284740815e-05,
      "loss": 1.1853967666625977,
      "num_input_tokens_seen": 937466048,
      "step": 3300,
      "train_runtime": 32105.4885,
      "train_tokens_per_second": 29199.557
    },
    {
      "epoch": 0.11711450729422587,
      "grad_norm": 1.4453125,
      "learning_rate": 4.3340836763261675e-05,
      "loss": 1.1915245056152344,
      "num_input_tokens_seen": 940354688,
      "step": 3310,
      "train_runtime": 32207.2972,
      "train_tokens_per_second": 29196.945
    },
    {
      "epoch": 0.11746832755795465,
      "grad_norm": 1.4609375,
      "learning_rate": 4.332456340378618e-05,
      "loss": 1.1804960250854493,
      "num_input_tokens_seen": 943173696,
      "step": 3320,
      "train_runtime": 32303.3354,
      "train_tokens_per_second": 29197.409
    },
    {
      "epoch": 0.11782214782168343,
      "grad_norm": 1.359375,
      "learning_rate": 4.3308308361228586e-05,
      "loss": 1.18006591796875,
      "num_input_tokens_seen": 946035008,
      "step": 3330,
      "train_runtime": 32402.3813,
      "train_tokens_per_second": 29196.466
    },
    {
      "epoch": 0.11817596808541221,
      "grad_norm": 1.4453125,
      "learning_rate": 4.329207160125282e-05,
      "loss": 1.1822134017944337,
      "num_input_tokens_seen": 948837056,
      "step": 3340,
      "train_runtime": 32496.2654,
      "train_tokens_per_second": 29198.342
    },
    {
      "epoch": 0.11852978834914099,
      "grad_norm": 1.296875,
      "learning_rate": 4.327585308961287e-05,
      "loss": 1.1795909881591797,
      "num_input_tokens_seen": 951684928,
      "step": 3350,
      "train_runtime": 32594.652,
      "train_tokens_per_second": 29197.579
    },
    {
      "epoch": 0.11888360861286977,
      "grad_norm": 1.4375,
      "learning_rate": 4.325965279215243e-05,
      "loss": 1.1808343887329102,
      "num_input_tokens_seen": 954490496,
      "step": 3360,
      "train_runtime": 32687.8398,
      "train_tokens_per_second": 29200.17
    },
    {
      "epoch": 0.11923742887659855,
      "grad_norm": 1.4609375,
      "learning_rate": 4.3243470674804686e-05,
      "loss": 1.1711687088012694,
      "num_input_tokens_seen": 957301120,
      "step": 3370,
      "train_runtime": 32782.7263,
      "train_tokens_per_second": 29201.388
    },
    {
      "epoch": 0.11959124914032733,
      "grad_norm": 1.359375,
      "learning_rate": 4.3227306703591904e-05,
      "loss": 1.176078987121582,
      "num_input_tokens_seen": 960131584,
      "step": 3380,
      "train_runtime": 32878.1754,
      "train_tokens_per_second": 29202.703
    },
    {
      "epoch": 0.11994506940405611,
      "grad_norm": 1.390625,
      "learning_rate": 4.32111608446252e-05,
      "loss": 1.1693265914916993,
      "num_input_tokens_seen": 962939648,
      "step": 3390,
      "train_runtime": 32970.497,
      "train_tokens_per_second": 29206.1
    },
    {
      "epoch": 0.12029888966778489,
      "grad_norm": 1.390625,
      "learning_rate": 4.319503306410426e-05,
      "loss": 1.1904790878295899,
      "num_input_tokens_seen": 965777408,
      "step": 3400,
      "train_runtime": 33063.1117,
      "train_tokens_per_second": 29210.118
    },
    {
      "epoch": 0.12065270993151367,
      "grad_norm": 1.4921875,
      "learning_rate": 4.317892332831699e-05,
      "loss": 1.167193603515625,
      "num_input_tokens_seen": 968573504,
      "step": 3410,
      "train_runtime": 33155.8555,
      "train_tokens_per_second": 29212.744
    },
    {
      "epoch": 0.12100653019524245,
      "grad_norm": 1.4375,
      "learning_rate": 4.316283160363922e-05,
      "loss": 1.1785587310791015,
      "num_input_tokens_seen": 971386240,
      "step": 3420,
      "train_runtime": 33249.7383,
      "train_tokens_per_second": 29214.854
    },
    {
      "epoch": 0.12136035045897123,
      "grad_norm": 1.4375,
      "learning_rate": 4.314675785653447e-05,
      "loss": 1.1811996459960938,
      "num_input_tokens_seen": 974241984,
      "step": 3430,
      "train_runtime": 33349.1071,
      "train_tokens_per_second": 29213.435
    },
    {
      "epoch": 0.12171417072270001,
      "grad_norm": 1.4453125,
      "learning_rate": 4.3130702053553606e-05,
      "loss": 1.1894235610961914,
      "num_input_tokens_seen": 977055936,
      "step": 3440,
      "train_runtime": 33442.9489,
      "train_tokens_per_second": 29215.604
    },
    {
      "epoch": 0.12206799098642879,
      "grad_norm": 1.4140625,
      "learning_rate": 4.3114664161334546e-05,
      "loss": 1.1872685432434082,
      "num_input_tokens_seen": 979927168,
      "step": 3450,
      "train_runtime": 33540.5123,
      "train_tokens_per_second": 29216.225
    },
    {
      "epoch": 0.12242181125015757,
      "grad_norm": 1.4140625,
      "learning_rate": 4.3098644146601984e-05,
      "loss": 1.1752504348754882,
      "num_input_tokens_seen": 982789760,
      "step": 3460,
      "train_runtime": 33640.5354,
      "train_tokens_per_second": 29214.451
    },
    {
      "epoch": 0.12277563151388635,
      "grad_norm": 1.40625,
      "learning_rate": 4.30826419761671e-05,
      "loss": 1.1864883422851562,
      "num_input_tokens_seen": 985613760,
      "step": 3470,
      "train_runtime": 33736.1035,
      "train_tokens_per_second": 29215.4
    },
    {
      "epoch": 0.12312945177761511,
      "grad_norm": 1.3828125,
      "learning_rate": 4.30666576169273e-05,
      "loss": 1.1909018516540528,
      "num_input_tokens_seen": 988397824,
      "step": 3480,
      "train_runtime": 33826.3807,
      "train_tokens_per_second": 29219.733
    },
    {
      "epoch": 0.12348327204134389,
      "grad_norm": 1.4140625,
      "learning_rate": 4.305069103586585e-05,
      "loss": 1.1829191207885743,
      "num_input_tokens_seen": 991241024,
      "step": 3490,
      "train_runtime": 33919.963,
      "train_tokens_per_second": 29222.939
    },
    {
      "epoch": 0.12383709230507267,
      "grad_norm": 1.4765625,
      "learning_rate": 4.303474220005164e-05,
      "loss": 1.1854116439819335,
      "num_input_tokens_seen": 994065856,
      "step": 3500,
      "train_runtime": 34013.7704,
      "train_tokens_per_second": 29225.394
    },
    {
      "epoch": 0.12419091256880145,
      "grad_norm": 1.4296875,
      "learning_rate": 4.3018811076638944e-05,
      "loss": 1.1804745674133301,
      "num_input_tokens_seen": 996866560,
      "step": 3510,
      "train_runtime": 34109.8402,
      "train_tokens_per_second": 29225.19
    },
    {
      "epoch": 0.12454473283253023,
      "grad_norm": 1.34375,
      "learning_rate": 4.300289763286704e-05,
      "loss": 1.177566146850586,
      "num_input_tokens_seen": 999720064,
      "step": 3520,
      "train_runtime": 34206.0193,
      "train_tokens_per_second": 29226.437
    },
    {
      "epoch": 0.12489855309625901,
      "grad_norm": 1.3203125,
      "learning_rate": 4.298700183606e-05,
      "loss": 1.1937307357788085,
      "num_input_tokens_seen": 1002563968,
      "step": 3530,
      "train_runtime": 34304.3059,
      "train_tokens_per_second": 29225.601
    },
    {
      "epoch": 0.1252523733599878,
      "grad_norm": 1.5625,
      "learning_rate": 4.297112365362637e-05,
      "loss": 1.1904770851135253,
      "num_input_tokens_seen": 1005402176,
      "step": 3540,
      "train_runtime": 34400.0585,
      "train_tokens_per_second": 29226.758
    },
    {
      "epoch": 0.12560619362371658,
      "grad_norm": 1.328125,
      "learning_rate": 4.295526305305891e-05,
      "loss": 1.1810283660888672,
      "num_input_tokens_seen": 1008258880,
      "step": 3550,
      "train_runtime": 34496.5586,
      "train_tokens_per_second": 29227.811
    },
    {
      "epoch": 0.12596001388744535,
      "grad_norm": 1.46875,
      "learning_rate": 4.293942000193429e-05,
      "loss": 1.1796077728271483,
      "num_input_tokens_seen": 1011047872,
      "step": 3560,
      "train_runtime": 34590.6535,
      "train_tokens_per_second": 29228.932
    },
    {
      "epoch": 0.12631383415117414,
      "grad_norm": 1.3984375,
      "learning_rate": 4.2923594467912866e-05,
      "loss": 1.1729990005493165,
      "num_input_tokens_seen": 1013899392,
      "step": 3570,
      "train_runtime": 34685.7749,
      "train_tokens_per_second": 29230.986
    },
    {
      "epoch": 0.1266676544149029,
      "grad_norm": 1.390625,
      "learning_rate": 4.290778641873832e-05,
      "loss": 1.202324676513672,
      "num_input_tokens_seen": 1016776256,
      "step": 3580,
      "train_runtime": 34783.0605,
      "train_tokens_per_second": 29231.938
    },
    {
      "epoch": 0.1270214746786317,
      "grad_norm": 1.4453125,
      "learning_rate": 4.2891995822237455e-05,
      "loss": 1.173007106781006,
      "num_input_tokens_seen": 1019636224,
      "step": 3590,
      "train_runtime": 34879.8305,
      "train_tokens_per_second": 29232.832
    },
    {
      "epoch": 0.12737529494236047,
      "grad_norm": 1.3828125,
      "learning_rate": 4.28762226463199e-05,
      "loss": 1.1899112701416015,
      "num_input_tokens_seen": 1022491264,
      "step": 3600,
      "train_runtime": 34977.4571,
      "train_tokens_per_second": 29232.864
    },
    {
      "epoch": 0.12772911520608923,
      "grad_norm": 1.3515625,
      "learning_rate": 4.286046685897781e-05,
      "loss": 1.1736169815063477,
      "num_input_tokens_seen": 1025290688,
      "step": 3610,
      "train_runtime": 35070.8437,
      "train_tokens_per_second": 29234.845
    },
    {
      "epoch": 0.12808293546981803,
      "grad_norm": 1.4609375,
      "learning_rate": 4.284472842828562e-05,
      "loss": 1.1902640342712403,
      "num_input_tokens_seen": 1028080896,
      "step": 3620,
      "train_runtime": 35162.0416,
      "train_tokens_per_second": 29238.373
    },
    {
      "epoch": 0.1284367557335468,
      "grad_norm": 1.359375,
      "learning_rate": 4.282900732239977e-05,
      "loss": 1.1653921127319335,
      "num_input_tokens_seen": 1030951360,
      "step": 3630,
      "train_runtime": 35258.9416,
      "train_tokens_per_second": 29239.43
    },
    {
      "epoch": 0.12879057599727559,
      "grad_norm": 1.4140625,
      "learning_rate": 4.281330350955845e-05,
      "loss": 1.1851133346557616,
      "num_input_tokens_seen": 1033796352,
      "step": 3640,
      "train_runtime": 35356.2581,
      "train_tokens_per_second": 29239.416
    },
    {
      "epoch": 0.12914439626100435,
      "grad_norm": 1.4765625,
      "learning_rate": 4.279761695808125e-05,
      "loss": 1.1738685607910155,
      "num_input_tokens_seen": 1036626624,
      "step": 3650,
      "train_runtime": 35453.2762,
      "train_tokens_per_second": 29239.234
    },
    {
      "epoch": 0.12949821652473315,
      "grad_norm": 1.421875,
      "learning_rate": 4.278194763636904e-05,
      "loss": 1.1984460830688477,
      "num_input_tokens_seen": 1039479552,
      "step": 3660,
      "train_runtime": 35552.3888,
      "train_tokens_per_second": 29237.966
    },
    {
      "epoch": 0.1298520367884619,
      "grad_norm": 1.421875,
      "learning_rate": 4.276629551290354e-05,
      "loss": 1.1884843826293945,
      "num_input_tokens_seen": 1042291904,
      "step": 3670,
      "train_runtime": 35648.7259,
      "train_tokens_per_second": 29237.845
    },
    {
      "epoch": 0.1302058570521907,
      "grad_norm": 1.46875,
      "learning_rate": 4.2750660556247175e-05,
      "loss": 1.179736042022705,
      "num_input_tokens_seen": 1045103104,
      "step": 3680,
      "train_runtime": 35745.796,
      "train_tokens_per_second": 29237.091
    },
    {
      "epoch": 0.13055967731591947,
      "grad_norm": 1.4296875,
      "learning_rate": 4.273504273504274e-05,
      "loss": 1.1895154953002929,
      "num_input_tokens_seen": 1047985280,
      "step": 3690,
      "train_runtime": 35843.7208,
      "train_tokens_per_second": 29237.625
    },
    {
      "epoch": 0.13091349757964826,
      "grad_norm": 1.40625,
      "learning_rate": 4.271944201801317e-05,
      "loss": 1.1777228355407714,
      "num_input_tokens_seen": 1050893376,
      "step": 3700,
      "train_runtime": 35943.6029,
      "train_tokens_per_second": 29237.285
    },
    {
      "epoch": 0.13126731784337703,
      "grad_norm": 1.4375,
      "learning_rate": 4.270385837396127e-05,
      "loss": 1.182157325744629,
      "num_input_tokens_seen": 1053785536,
      "step": 3710,
      "train_runtime": 36043.3147,
      "train_tokens_per_second": 29236.643
    },
    {
      "epoch": 0.13162113810710582,
      "grad_norm": 1.3984375,
      "learning_rate": 4.268829177176945e-05,
      "loss": 1.1841708183288575,
      "num_input_tokens_seen": 1056617280,
      "step": 3720,
      "train_runtime": 36137.0049,
      "train_tokens_per_second": 29239.205
    },
    {
      "epoch": 0.1319749583708346,
      "grad_norm": 1.40625,
      "learning_rate": 4.2672742180399455e-05,
      "loss": 1.1797069549560546,
      "num_input_tokens_seen": 1059486912,
      "step": 3730,
      "train_runtime": 36235.2429,
      "train_tokens_per_second": 29239.128
    },
    {
      "epoch": 0.13232877863456338,
      "grad_norm": 1.3671875,
      "learning_rate": 4.265720956889213e-05,
      "loss": 1.1824552536010742,
      "num_input_tokens_seen": 1062342016,
      "step": 3740,
      "train_runtime": 36332.7711,
      "train_tokens_per_second": 29239.224
    },
    {
      "epoch": 0.13268259889829215,
      "grad_norm": 1.4140625,
      "learning_rate": 4.2641693906367113e-05,
      "loss": 1.1785259246826172,
      "num_input_tokens_seen": 1065209920,
      "step": 3750,
      "train_runtime": 36433.6906,
      "train_tokens_per_second": 29236.948
    },
    {
      "epoch": 0.13303641916202094,
      "grad_norm": 1.3671875,
      "learning_rate": 4.2626195162022646e-05,
      "loss": 1.1788436889648437,
      "num_input_tokens_seen": 1068011200,
      "step": 3760,
      "train_runtime": 36527.7044,
      "train_tokens_per_second": 29238.388
    },
    {
      "epoch": 0.1333902394257497,
      "grad_norm": 1.3984375,
      "learning_rate": 4.2610713305135255e-05,
      "loss": 1.1807544708251954,
      "num_input_tokens_seen": 1070900608,
      "step": 3770,
      "train_runtime": 36629.5791,
      "train_tokens_per_second": 29235.952
    },
    {
      "epoch": 0.1337440596894785,
      "grad_norm": 1.359375,
      "learning_rate": 4.2595248305059546e-05,
      "loss": 1.1695978164672851,
      "num_input_tokens_seen": 1073795328,
      "step": 3780,
      "train_runtime": 36730.9848,
      "train_tokens_per_second": 29234.047
    },
    {
      "epoch": 0.13409787995320727,
      "grad_norm": 1.4140625,
      "learning_rate": 4.2579800131227916e-05,
      "loss": 1.1728618621826172,
      "num_input_tokens_seen": 1076604416,
      "step": 3790,
      "train_runtime": 36825.2397,
      "train_tokens_per_second": 29235.503
    },
    {
      "epoch": 0.13445170021693606,
      "grad_norm": 1.375,
      "learning_rate": 4.256436875315028e-05,
      "loss": 1.1714584350585937,
      "num_input_tokens_seen": 1079443520,
      "step": 3800,
      "train_runtime": 36918.4298,
      "train_tokens_per_second": 29238.609
    },
    {
      "epoch": 0.13480552048066483,
      "grad_norm": 1.4609375,
      "learning_rate": 4.2548954140413895e-05,
      "loss": 1.1774912834167481,
      "num_input_tokens_seen": 1082304064,
      "step": 3810,
      "train_runtime": 37015.0972,
      "train_tokens_per_second": 29239.53
    },
    {
      "epoch": 0.13515934074439362,
      "grad_norm": 1.4140625,
      "learning_rate": 4.253355626268302e-05,
      "loss": 1.170922088623047,
      "num_input_tokens_seen": 1085158976,
      "step": 3820,
      "train_runtime": 37113.0647,
      "train_tokens_per_second": 29239.272
    },
    {
      "epoch": 0.13551316100812238,
      "grad_norm": 1.3828125,
      "learning_rate": 4.2518175089698716e-05,
      "loss": 1.1693132400512696,
      "num_input_tokens_seen": 1088037632,
      "step": 3830,
      "train_runtime": 37213.9649,
      "train_tokens_per_second": 29237.348
    },
    {
      "epoch": 0.13586698127185118,
      "grad_norm": 1.40625,
      "learning_rate": 4.25028105912786e-05,
      "loss": 1.1835298538208008,
      "num_input_tokens_seen": 1090901952,
      "step": 3840,
      "train_runtime": 37316.914,
      "train_tokens_per_second": 29233.445
    },
    {
      "epoch": 0.13622080153557994,
      "grad_norm": 1.390625,
      "learning_rate": 4.2487462737316565e-05,
      "loss": 1.1862130165100098,
      "num_input_tokens_seen": 1093725824,
      "step": 3850,
      "train_runtime": 37413.6944,
      "train_tokens_per_second": 29233.302
    },
    {
      "epoch": 0.13657462179930874,
      "grad_norm": 1.3515625,
      "learning_rate": 4.2472131497782555e-05,
      "loss": 1.1785076141357422,
      "num_input_tokens_seen": 1096502720,
      "step": 3860,
      "train_runtime": 37505.278,
      "train_tokens_per_second": 29235.958
    },
    {
      "epoch": 0.1369284420630375,
      "grad_norm": 1.3671875,
      "learning_rate": 4.245681684272231e-05,
      "loss": 1.181657314300537,
      "num_input_tokens_seen": 1099356800,
      "step": 3870,
      "train_runtime": 37602.0285,
      "train_tokens_per_second": 29236.635
    },
    {
      "epoch": 0.13728226232676627,
      "grad_norm": 1.3984375,
      "learning_rate": 4.244151874225712e-05,
      "loss": 1.179312038421631,
      "num_input_tokens_seen": 1102169280,
      "step": 3880,
      "train_runtime": 37696.469,
      "train_tokens_per_second": 29237.998
    },
    {
      "epoch": 0.13763608259049506,
      "grad_norm": 1.4140625,
      "learning_rate": 4.2426237166583596e-05,
      "loss": 1.1605977058410644,
      "num_input_tokens_seen": 1105003328,
      "step": 3890,
      "train_runtime": 37796.0045,
      "train_tokens_per_second": 29235.983
    },
    {
      "epoch": 0.13798990285422383,
      "grad_norm": 1.375,
      "learning_rate": 4.241097208597339e-05,
      "loss": 1.1763355255126953,
      "num_input_tokens_seen": 1107821184,
      "step": 3900,
      "train_runtime": 37890.4228,
      "train_tokens_per_second": 29237.499
    },
    {
      "epoch": 0.13834372311795262,
      "grad_norm": 1.3828125,
      "learning_rate": 4.2395723470773005e-05,
      "loss": 1.1708013534545898,
      "num_input_tokens_seen": 1110715968,
      "step": 3910,
      "train_runtime": 37989.7024,
      "train_tokens_per_second": 29237.291
    },
    {
      "epoch": 0.1386975433816814,
      "grad_norm": 1.4375,
      "learning_rate": 4.238049129140347e-05,
      "loss": 1.1769329071044923,
      "num_input_tokens_seen": 1113568000,
      "step": 3920,
      "train_runtime": 38088.3434,
      "train_tokens_per_second": 29236.451
    },
    {
      "epoch": 0.13905136364541018,
      "grad_norm": 1.4765625,
      "learning_rate": 4.236527551836022e-05,
      "loss": 1.1631412506103516,
      "num_input_tokens_seen": 1116387136,
      "step": 3930,
      "train_runtime": 38183.027,
      "train_tokens_per_second": 29237.785
    },
    {
      "epoch": 0.13940518390913895,
      "grad_norm": 1.4296875,
      "learning_rate": 4.235007612221274e-05,
      "loss": 1.172716999053955,
      "num_input_tokens_seen": 1119228928,
      "step": 3940,
      "train_runtime": 38277.3634,
      "train_tokens_per_second": 29239.969
    },
    {
      "epoch": 0.13975900417286774,
      "grad_norm": 1.390625,
      "learning_rate": 4.2334893073604386e-05,
      "loss": 1.1742752075195313,
      "num_input_tokens_seen": 1122038912,
      "step": 3950,
      "train_runtime": 38370.595,
      "train_tokens_per_second": 29242.156
    },
    {
      "epoch": 0.1401128244365965,
      "grad_norm": 1.421875,
      "learning_rate": 4.231972634325214e-05,
      "loss": 1.1919352531433105,
      "num_input_tokens_seen": 1124911232,
      "step": 3960,
      "train_runtime": 38471.2265,
      "train_tokens_per_second": 29240.327
    },
    {
      "epoch": 0.1404666447003253,
      "grad_norm": 1.3828125,
      "learning_rate": 4.230457590194635e-05,
      "loss": 1.1724810600280762,
      "num_input_tokens_seen": 1127771200,
      "step": 3970,
      "train_runtime": 38569.7353,
      "train_tokens_per_second": 29239.796
    },
    {
      "epoch": 0.14082046496405407,
      "grad_norm": 1.328125,
      "learning_rate": 4.228944172055053e-05,
      "loss": 1.1805822372436523,
      "num_input_tokens_seen": 1130658240,
      "step": 3980,
      "train_runtime": 38669.2246,
      "train_tokens_per_second": 29239.227
    },
    {
      "epoch": 0.14117428522778286,
      "grad_norm": 1.3984375,
      "learning_rate": 4.22743237700011e-05,
      "loss": 1.1816822052001954,
      "num_input_tokens_seen": 1133511744,
      "step": 3990,
      "train_runtime": 38768.2346,
      "train_tokens_per_second": 29238.157
    },
    {
      "epoch": 0.14152810549151162,
      "grad_norm": 1.4453125,
      "learning_rate": 4.225922202130716e-05,
      "loss": 1.1658548355102538,
      "num_input_tokens_seen": 1136350848,
      "step": 4000,
      "train_runtime": 38865.4396,
      "train_tokens_per_second": 29238.08
    },
    {
      "epoch": 0.14188192575524042,
      "grad_norm": 1.375,
      "learning_rate": 4.224413644555024e-05,
      "loss": 1.1686421394348145,
      "num_input_tokens_seen": 1139143808,
      "step": 4010,
      "train_runtime": 38959.2863,
      "train_tokens_per_second": 29239.34
    },
    {
      "epoch": 0.14223574601896918,
      "grad_norm": 1.46875,
      "learning_rate": 4.222906701388411e-05,
      "loss": 1.1757335662841797,
      "num_input_tokens_seen": 1141969856,
      "step": 4020,
      "train_runtime": 39058.2066,
      "train_tokens_per_second": 29237.642
    },
    {
      "epoch": 0.14258956628269798,
      "grad_norm": 1.4375,
      "learning_rate": 4.2214013697534466e-05,
      "loss": 1.1730082511901856,
      "num_input_tokens_seen": 1144803136,
      "step": 4030,
      "train_runtime": 39156.5104,
      "train_tokens_per_second": 29236.598
    },
    {
      "epoch": 0.14294338654642674,
      "grad_norm": 1.3671875,
      "learning_rate": 4.219897646779882e-05,
      "loss": 1.1709014892578125,
      "num_input_tokens_seen": 1147692672,
      "step": 4040,
      "train_runtime": 39259.2997,
      "train_tokens_per_second": 29233.651
    },
    {
      "epoch": 0.14329720681015554,
      "grad_norm": 1.3828125,
      "learning_rate": 4.2183955296046145e-05,
      "loss": 1.1871071815490724,
      "num_input_tokens_seen": 1150605952,
      "step": 4050,
      "train_runtime": 39361.974,
      "train_tokens_per_second": 29231.409
    },
    {
      "epoch": 0.1436510270738843,
      "grad_norm": 1.3828125,
      "learning_rate": 4.2168950153716746e-05,
      "loss": 1.1795658111572265,
      "num_input_tokens_seen": 1153387008,
      "step": 4060,
      "train_runtime": 39455.367,
      "train_tokens_per_second": 29232.703
    },
    {
      "epoch": 0.1440048473376131,
      "grad_norm": 1.4296875,
      "learning_rate": 4.215396101232197e-05,
      "loss": 1.1646547317504883,
      "num_input_tokens_seen": 1156206208,
      "step": 4070,
      "train_runtime": 39549.8734,
      "train_tokens_per_second": 29234.132
    },
    {
      "epoch": 0.14435866760134186,
      "grad_norm": 1.515625,
      "learning_rate": 4.213898784344398e-05,
      "loss": 1.178143310546875,
      "num_input_tokens_seen": 1159107648,
      "step": 4080,
      "train_runtime": 39651.1204,
      "train_tokens_per_second": 29232.658
    },
    {
      "epoch": 0.14471248786507065,
      "grad_norm": 1.3671875,
      "learning_rate": 4.21240306187356e-05,
      "loss": 1.1769689559936523,
      "num_input_tokens_seen": 1161944576,
      "step": 4090,
      "train_runtime": 39748.7419,
      "train_tokens_per_second": 29232.235
    },
    {
      "epoch": 0.14506630812879942,
      "grad_norm": 1.4296875,
      "learning_rate": 4.2109089309919967e-05,
      "loss": 1.176289939880371,
      "num_input_tokens_seen": 1164828992,
      "step": 4100,
      "train_runtime": 39848.5136,
      "train_tokens_per_second": 29231.429
    },
    {
      "epoch": 0.14542012839252821,
      "grad_norm": 1.46875,
      "learning_rate": 4.2094163888790445e-05,
      "loss": 1.1834224700927733,
      "num_input_tokens_seen": 1167660480,
      "step": 4110,
      "train_runtime": 39944.6555,
      "train_tokens_per_second": 29231.958
    },
    {
      "epoch": 0.14577394865625698,
      "grad_norm": 1.4765625,
      "learning_rate": 4.2079254327210294e-05,
      "loss": 1.163860034942627,
      "num_input_tokens_seen": 1170493056,
      "step": 4120,
      "train_runtime": 40043.2845,
      "train_tokens_per_second": 29230.695
    },
    {
      "epoch": 0.14612776891998575,
      "grad_norm": 1.4453125,
      "learning_rate": 4.206436059711249e-05,
      "loss": 1.1672218322753907,
      "num_input_tokens_seen": 1173303936,
      "step": 4130,
      "train_runtime": 40140.6304,
      "train_tokens_per_second": 29229.833
    },
    {
      "epoch": 0.14648158918371454,
      "grad_norm": 1.3671875,
      "learning_rate": 4.20494826704995e-05,
      "loss": 1.1857643127441406,
      "num_input_tokens_seen": 1176151616,
      "step": 4140,
      "train_runtime": 40239.7876,
      "train_tokens_per_second": 29228.574
    },
    {
      "epoch": 0.1468354094474433,
      "grad_norm": 1.421875,
      "learning_rate": 4.203462051944307e-05,
      "loss": 1.176898193359375,
      "num_input_tokens_seen": 1179087552,
      "step": 4150,
      "train_runtime": 40344.3662,
      "train_tokens_per_second": 29225.581
    },
    {
      "epoch": 0.1471892297111721,
      "grad_norm": 1.4296875,
      "learning_rate": 4.201977411608398e-05,
      "loss": 1.180149459838867,
      "num_input_tokens_seen": 1181852160,
      "step": 4160,
      "train_runtime": 40436.6452,
      "train_tokens_per_second": 29227.255
    },
    {
      "epoch": 0.14754304997490086,
      "grad_norm": 1.375,
      "learning_rate": 4.200494343263185e-05,
      "loss": 1.180349063873291,
      "num_input_tokens_seen": 1184651008,
      "step": 4170,
      "train_runtime": 40531.9268,
      "train_tokens_per_second": 29227.602
    },
    {
      "epoch": 0.14789687023862966,
      "grad_norm": 1.4296875,
      "learning_rate": 4.1990128441364914e-05,
      "loss": 1.1600811004638671,
      "num_input_tokens_seen": 1187485120,
      "step": 4180,
      "train_runtime": 40629.2827,
      "train_tokens_per_second": 29227.322
    },
    {
      "epoch": 0.14825069050235842,
      "grad_norm": 1.4296875,
      "learning_rate": 4.197532911462977e-05,
      "loss": 1.1738241195678711,
      "num_input_tokens_seen": 1190325248,
      "step": 4190,
      "train_runtime": 40729.0992,
      "train_tokens_per_second": 29225.425
    },
    {
      "epoch": 0.14860451076608722,
      "grad_norm": 1.390625,
      "learning_rate": 4.196054542484125e-05,
      "loss": 1.1638025283813476,
      "num_input_tokens_seen": 1193193088,
      "step": 4200,
      "train_runtime": 40829.218,
      "train_tokens_per_second": 29224.0
    },
    {
      "epoch": 0.14895833102981598,
      "grad_norm": 1.4453125,
      "learning_rate": 4.1945777344482084e-05,
      "loss": 1.1518236160278321,
      "num_input_tokens_seen": 1196034560,
      "step": 4210,
      "train_runtime": 40925.6326,
      "train_tokens_per_second": 29224.583
    },
    {
      "epoch": 0.14931215129354478,
      "grad_norm": 1.4296875,
      "learning_rate": 4.19310248461028e-05,
      "loss": 1.1800807952880858,
      "num_input_tokens_seen": 1198912832,
      "step": 4220,
      "train_runtime": 41028.757,
      "train_tokens_per_second": 29221.281
    },
    {
      "epoch": 0.14966597155727354,
      "grad_norm": 1.46875,
      "learning_rate": 4.1916287902321405e-05,
      "loss": 1.1695475578308105,
      "num_input_tokens_seen": 1201798272,
      "step": 4230,
      "train_runtime": 41130.2756,
      "train_tokens_per_second": 29219.31
    },
    {
      "epoch": 0.15001979182100234,
      "grad_norm": 1.4765625,
      "learning_rate": 4.190156648582328e-05,
      "loss": 1.1690372467041015,
      "num_input_tokens_seen": 1204654784,
      "step": 4240,
      "train_runtime": 41226.3142,
      "train_tokens_per_second": 29220.531
    },
    {
      "epoch": 0.1503736120847311,
      "grad_norm": 1.4296875,
      "learning_rate": 4.188686056936087e-05,
      "loss": 1.1712785720825196,
      "num_input_tokens_seen": 1207475008,
      "step": 4250,
      "train_runtime": 41321.1014,
      "train_tokens_per_second": 29221.753
    },
    {
      "epoch": 0.1507274323484599,
      "grad_norm": 1.4296875,
      "learning_rate": 4.187217012575352e-05,
      "loss": 1.1590457916259767,
      "num_input_tokens_seen": 1210316224,
      "step": 4260,
      "train_runtime": 41417.3597,
      "train_tokens_per_second": 29222.438
    },
    {
      "epoch": 0.15108125261218866,
      "grad_norm": 1.375,
      "learning_rate": 4.185749512788727e-05,
      "loss": 1.1723502159118653,
      "num_input_tokens_seen": 1213199552,
      "step": 4270,
      "train_runtime": 41515.867,
      "train_tokens_per_second": 29222.551
    },
    {
      "epoch": 0.15143507287591745,
      "grad_norm": 1.4453125,
      "learning_rate": 4.184283554871462e-05,
      "loss": 1.157613182067871,
      "num_input_tokens_seen": 1216018816,
      "step": 4280,
      "train_runtime": 41612.7361,
      "train_tokens_per_second": 29222.275
    },
    {
      "epoch": 0.15178889313964622,
      "grad_norm": 1.4296875,
      "learning_rate": 4.1828191361254344e-05,
      "loss": 1.1705541610717773,
      "num_input_tokens_seen": 1218848896,
      "step": 4290,
      "train_runtime": 41707.2296,
      "train_tokens_per_second": 29223.924
    },
    {
      "epoch": 0.152142713403375,
      "grad_norm": 1.40625,
      "learning_rate": 4.181356253859127e-05,
      "loss": 1.16650447845459,
      "num_input_tokens_seen": 1221640448,
      "step": 4300,
      "train_runtime": 41798.0608,
      "train_tokens_per_second": 29227.204
    },
    {
      "epoch": 0.15249653366710378,
      "grad_norm": 1.34375,
      "learning_rate": 4.179894905387606e-05,
      "loss": 1.1773106575012207,
      "num_input_tokens_seen": 1224492544,
      "step": 4310,
      "train_runtime": 41895.5567,
      "train_tokens_per_second": 29227.265
    },
    {
      "epoch": 0.15285035393083257,
      "grad_norm": 1.3984375,
      "learning_rate": 4.178435088032502e-05,
      "loss": 1.1660337448120117,
      "num_input_tokens_seen": 1227310592,
      "step": 4320,
      "train_runtime": 41991.7216,
      "train_tokens_per_second": 29227.442
    },
    {
      "epoch": 0.15320417419456134,
      "grad_norm": 1.453125,
      "learning_rate": 4.176976799121989e-05,
      "loss": 1.1444032669067383,
      "num_input_tokens_seen": 1230119616,
      "step": 4330,
      "train_runtime": 42088.656,
      "train_tokens_per_second": 29226.869
    },
    {
      "epoch": 0.15355799445829013,
      "grad_norm": 1.3984375,
      "learning_rate": 4.1755200359907657e-05,
      "loss": 1.1619373321533204,
      "num_input_tokens_seen": 1232923648,
      "step": 4340,
      "train_runtime": 42183.2887,
      "train_tokens_per_second": 29227.774
    },
    {
      "epoch": 0.1539118147220189,
      "grad_norm": 1.3828125,
      "learning_rate": 4.174064795980028e-05,
      "loss": 1.1633609771728515,
      "num_input_tokens_seen": 1235791296,
      "step": 4350,
      "train_runtime": 42280.2091,
      "train_tokens_per_second": 29228.599
    },
    {
      "epoch": 0.1542656349857477,
      "grad_norm": 1.3984375,
      "learning_rate": 4.17261107643746e-05,
      "loss": 1.184457015991211,
      "num_input_tokens_seen": 1238657856,
      "step": 4360,
      "train_runtime": 42381.4408,
      "train_tokens_per_second": 29226.422
    },
    {
      "epoch": 0.15461945524947646,
      "grad_norm": 1.359375,
      "learning_rate": 4.171158874717204e-05,
      "loss": 1.167654037475586,
      "num_input_tokens_seen": 1241488704,
      "step": 4370,
      "train_runtime": 42477.304,
      "train_tokens_per_second": 29227.107
    },
    {
      "epoch": 0.15497327551320522,
      "grad_norm": 1.4453125,
      "learning_rate": 4.169708188179844e-05,
      "loss": 1.156892967224121,
      "num_input_tokens_seen": 1244296576,
      "step": 4380,
      "train_runtime": 42570.8106,
      "train_tokens_per_second": 29228.867
    },
    {
      "epoch": 0.15532709577693402,
      "grad_norm": 1.5078125,
      "learning_rate": 4.1682590141923846e-05,
      "loss": 1.1702998161315918,
      "num_input_tokens_seen": 1247104320,
      "step": 4390,
      "train_runtime": 42666.2003,
      "train_tokens_per_second": 29229.327
    },
    {
      "epoch": 0.15568091604066278,
      "grad_norm": 1.296875,
      "learning_rate": 4.1668113501282335e-05,
      "loss": 1.159244918823242,
      "num_input_tokens_seen": 1249909376,
      "step": 4400,
      "train_runtime": 42762.447,
      "train_tokens_per_second": 29229.136
    },
    {
      "epoch": 0.15603473630439157,
      "grad_norm": 1.4296875,
      "learning_rate": 4.165365193367178e-05,
      "loss": 1.165069580078125,
      "num_input_tokens_seen": 1252730048,
      "step": 4410,
      "train_runtime": 42858.7268,
      "train_tokens_per_second": 29229.287
    },
    {
      "epoch": 0.15638855656812034,
      "grad_norm": 1.453125,
      "learning_rate": 4.163920541295369e-05,
      "loss": 1.1761979103088378,
      "num_input_tokens_seen": 1255548928,
      "step": 4420,
      "train_runtime": 42954.4584,
      "train_tokens_per_second": 29229.77
    },
    {
      "epoch": 0.15674237683184913,
      "grad_norm": 1.46875,
      "learning_rate": 4.1624773913052946e-05,
      "loss": 1.1730831146240235,
      "num_input_tokens_seen": 1258380608,
      "step": 4430,
      "train_runtime": 43053.2889,
      "train_tokens_per_second": 29228.443
    },
    {
      "epoch": 0.1570961970955779,
      "grad_norm": 1.4453125,
      "learning_rate": 4.161035740795769e-05,
      "loss": 1.16481351852417,
      "num_input_tokens_seen": 1261217344,
      "step": 4440,
      "train_runtime": 43149.0754,
      "train_tokens_per_second": 29229.302
    },
    {
      "epoch": 0.1574500173593067,
      "grad_norm": 1.40625,
      "learning_rate": 4.1595955871719055e-05,
      "loss": 1.1573904037475586,
      "num_input_tokens_seen": 1264081024,
      "step": 4450,
      "train_runtime": 43249.3658,
      "train_tokens_per_second": 29227.735
    },
    {
      "epoch": 0.15780383762303546,
      "grad_norm": 1.40625,
      "learning_rate": 4.158156927845101e-05,
      "loss": 1.1631442070007325,
      "num_input_tokens_seen": 1266929920,
      "step": 4460,
      "train_runtime": 43345.5208,
      "train_tokens_per_second": 29228.624
    },
    {
      "epoch": 0.15815765788676425,
      "grad_norm": 1.421875,
      "learning_rate": 4.156719760233016e-05,
      "loss": 1.1768792152404786,
      "num_input_tokens_seen": 1269772864,
      "step": 4470,
      "train_runtime": 43441.6644,
      "train_tokens_per_second": 29229.379
    },
    {
      "epoch": 0.15851147815049302,
      "grad_norm": 1.4375,
      "learning_rate": 4.155284081759552e-05,
      "loss": 1.1812875747680665,
      "num_input_tokens_seen": 1272572224,
      "step": 4480,
      "train_runtime": 43535.9244,
      "train_tokens_per_second": 29230.394
    },
    {
      "epoch": 0.1588652984142218,
      "grad_norm": 1.3984375,
      "learning_rate": 4.1538498898548356e-05,
      "loss": 1.1645915031433105,
      "num_input_tokens_seen": 1275388928,
      "step": 4490,
      "train_runtime": 43633.4048,
      "train_tokens_per_second": 29229.645
    },
    {
      "epoch": 0.15921911867795058,
      "grad_norm": 1.359375,
      "learning_rate": 4.1524171819552e-05,
      "loss": 1.163807487487793,
      "num_input_tokens_seen": 1278251456,
      "step": 4500,
      "train_runtime": 43731.3608,
      "train_tokens_per_second": 29229.629
    },
    {
      "epoch": 0.15957293894167937,
      "grad_norm": 1.390625,
      "learning_rate": 4.15098595550316e-05,
      "loss": 1.174567413330078,
      "num_input_tokens_seen": 1281085120,
      "step": 4510,
      "train_runtime": 43827.8411,
      "train_tokens_per_second": 29229.939
    },
    {
      "epoch": 0.15992675920540814,
      "grad_norm": 1.390625,
      "learning_rate": 4.1495562079474e-05,
      "loss": 1.1581344604492188,
      "num_input_tokens_seen": 1283928256,
      "step": 4520,
      "train_runtime": 43923.7854,
      "train_tokens_per_second": 29230.82
    },
    {
      "epoch": 0.16028057946913693,
      "grad_norm": 1.4765625,
      "learning_rate": 4.148127936742749e-05,
      "loss": 1.1675923347473145,
      "num_input_tokens_seen": 1286786880,
      "step": 4530,
      "train_runtime": 44023.1981,
      "train_tokens_per_second": 29229.746
    },
    {
      "epoch": 0.1606343997328657,
      "grad_norm": 1.3828125,
      "learning_rate": 4.146701139350166e-05,
      "loss": 1.1774301528930664,
      "num_input_tokens_seen": 1289581760,
      "step": 4540,
      "train_runtime": 44119.12,
      "train_tokens_per_second": 29229.544
    },
    {
      "epoch": 0.1609882199965945,
      "grad_norm": 1.4296875,
      "learning_rate": 4.1452758132367196e-05,
      "loss": 1.165812110900879,
      "num_input_tokens_seen": 1292423360,
      "step": 4550,
      "train_runtime": 44216.0546,
      "train_tokens_per_second": 29229.731
    },
    {
      "epoch": 0.16134204026032326,
      "grad_norm": 1.421875,
      "learning_rate": 4.1438519558755656e-05,
      "loss": 1.1558544158935546,
      "num_input_tokens_seen": 1295337216,
      "step": 4560,
      "train_runtime": 44317.0703,
      "train_tokens_per_second": 29228.855
    },
    {
      "epoch": 0.16169586052405205,
      "grad_norm": 1.390625,
      "learning_rate": 4.1424295647459336e-05,
      "loss": 1.1622037887573242,
      "num_input_tokens_seen": 1298182656,
      "step": 4570,
      "train_runtime": 44414.7974,
      "train_tokens_per_second": 29228.607
    },
    {
      "epoch": 0.16204968078778081,
      "grad_norm": 1.359375,
      "learning_rate": 4.141008637333106e-05,
      "loss": 1.1622723579406737,
      "num_input_tokens_seen": 1301050048,
      "step": 4580,
      "train_runtime": 44514.1041,
      "train_tokens_per_second": 29227.816
    },
    {
      "epoch": 0.1624035010515096,
      "grad_norm": 1.4296875,
      "learning_rate": 4.1395891711283974e-05,
      "loss": 1.1522689819335938,
      "num_input_tokens_seen": 1303916544,
      "step": 4590,
      "train_runtime": 44613.6419,
      "train_tokens_per_second": 29226.857
    },
    {
      "epoch": 0.16275732131523837,
      "grad_norm": 1.4375,
      "learning_rate": 4.1381711636291395e-05,
      "loss": 1.1612784385681152,
      "num_input_tokens_seen": 1306714944,
      "step": 4600,
      "train_runtime": 44708.9977,
      "train_tokens_per_second": 29227.113
    },
    {
      "epoch": 0.16311114157896717,
      "grad_norm": 1.375,
      "learning_rate": 4.1367546123386604e-05,
      "loss": 1.152998447418213,
      "num_input_tokens_seen": 1309505600,
      "step": 4610,
      "train_runtime": 44805.2476,
      "train_tokens_per_second": 29226.612
    },
    {
      "epoch": 0.16346496184269593,
      "grad_norm": 1.40625,
      "learning_rate": 4.1353395147662673e-05,
      "loss": 1.1638368606567382,
      "num_input_tokens_seen": 1312348416,
      "step": 4620,
      "train_runtime": 44903.011,
      "train_tokens_per_second": 29226.29
    },
    {
      "epoch": 0.16381878210642473,
      "grad_norm": 1.3828125,
      "learning_rate": 4.133925868427225e-05,
      "loss": 1.1757159233093262,
      "num_input_tokens_seen": 1315210752,
      "step": 4630,
      "train_runtime": 45002.394,
      "train_tokens_per_second": 29225.351
    },
    {
      "epoch": 0.1641726023701535,
      "grad_norm": 1.34375,
      "learning_rate": 4.132513670842744e-05,
      "loss": 1.1579181671142578,
      "num_input_tokens_seen": 1318022080,
      "step": 4640,
      "train_runtime": 45096.4576,
      "train_tokens_per_second": 29226.732
    },
    {
      "epoch": 0.16452642263388226,
      "grad_norm": 1.5,
      "learning_rate": 4.1311029195399534e-05,
      "loss": 1.1574539184570312,
      "num_input_tokens_seen": 1320899072,
      "step": 4650,
      "train_runtime": 45198.4939,
      "train_tokens_per_second": 29224.405
    },
    {
      "epoch": 0.16488024289761105,
      "grad_norm": 1.484375,
      "learning_rate": 4.129693612051892e-05,
      "loss": 1.1614418029785156,
      "num_input_tokens_seen": 1323750912,
      "step": 4660,
      "train_runtime": 45296.0792,
      "train_tokens_per_second": 29224.404
    },
    {
      "epoch": 0.16523406316133982,
      "grad_norm": 1.3671875,
      "learning_rate": 4.1282857459174826e-05,
      "loss": 1.1747958183288574,
      "num_input_tokens_seen": 1326532416,
      "step": 4670,
      "train_runtime": 45389.6955,
      "train_tokens_per_second": 29225.409
    },
    {
      "epoch": 0.1655878834250686,
      "grad_norm": 1.453125,
      "learning_rate": 4.1268793186815184e-05,
      "loss": 1.1685308456420898,
      "num_input_tokens_seen": 1329344384,
      "step": 4680,
      "train_runtime": 45486.4155,
      "train_tokens_per_second": 29225.086
    },
    {
      "epoch": 0.16594170368879738,
      "grad_norm": 1.4453125,
      "learning_rate": 4.1254743278946456e-05,
      "loss": 1.1820893287658691,
      "num_input_tokens_seen": 1332233664,
      "step": 4690,
      "train_runtime": 45586.4255,
      "train_tokens_per_second": 29224.35
    },
    {
      "epoch": 0.16629552395252617,
      "grad_norm": 1.40625,
      "learning_rate": 4.1240707711133394e-05,
      "loss": 1.1573176383972168,
      "num_input_tokens_seen": 1335070720,
      "step": 4700,
      "train_runtime": 45683.4818,
      "train_tokens_per_second": 29224.364
    },
    {
      "epoch": 0.16664934421625494,
      "grad_norm": 1.3828125,
      "learning_rate": 4.122668645899893e-05,
      "loss": 1.1567338943481444,
      "num_input_tokens_seen": 1338002176,
      "step": 4710,
      "train_runtime": 45785.9886,
      "train_tokens_per_second": 29222.961
    },
    {
      "epoch": 0.16700316447998373,
      "grad_norm": 1.421875,
      "learning_rate": 4.1212679498223975e-05,
      "loss": 1.1683042526245118,
      "num_input_tokens_seen": 1340848640,
      "step": 4720,
      "train_runtime": 45883.5878,
      "train_tokens_per_second": 29222.838
    },
    {
      "epoch": 0.1673569847437125,
      "grad_norm": 1.3984375,
      "learning_rate": 4.1198686804547215e-05,
      "loss": 1.1651246070861816,
      "num_input_tokens_seen": 1343707776,
      "step": 4730,
      "train_runtime": 45980.2325,
      "train_tokens_per_second": 29223.597
    },
    {
      "epoch": 0.1677108050074413,
      "grad_norm": 1.390625,
      "learning_rate": 4.118470835376499e-05,
      "loss": 1.1756913185119628,
      "num_input_tokens_seen": 1346536704,
      "step": 4740,
      "train_runtime": 46077.4068,
      "train_tokens_per_second": 29223.361
    },
    {
      "epoch": 0.16806462527117005,
      "grad_norm": 1.375,
      "learning_rate": 4.117074412173107e-05,
      "loss": 1.1566192626953125,
      "num_input_tokens_seen": 1349381632,
      "step": 4750,
      "train_runtime": 46177.208,
      "train_tokens_per_second": 29221.811
    },
    {
      "epoch": 0.16841844553489885,
      "grad_norm": 1.4140625,
      "learning_rate": 4.115679408435648e-05,
      "loss": 1.1635604858398438,
      "num_input_tokens_seen": 1352231744,
      "step": 4760,
      "train_runtime": 46275.4368,
      "train_tokens_per_second": 29221.372
    },
    {
      "epoch": 0.1687722657986276,
      "grad_norm": 1.375,
      "learning_rate": 4.114285821760937e-05,
      "loss": 1.1621339797973633,
      "num_input_tokens_seen": 1355066048,
      "step": 4770,
      "train_runtime": 46368.8854,
      "train_tokens_per_second": 29223.606
    },
    {
      "epoch": 0.1691260860623564,
      "grad_norm": 1.4609375,
      "learning_rate": 4.11289364975148e-05,
      "loss": 1.175765609741211,
      "num_input_tokens_seen": 1357933376,
      "step": 4780,
      "train_runtime": 46466.8963,
      "train_tokens_per_second": 29223.673
    },
    {
      "epoch": 0.16947990632608517,
      "grad_norm": 1.4140625,
      "learning_rate": 4.111502890015456e-05,
      "loss": 1.1585985183715821,
      "num_input_tokens_seen": 1360776320,
      "step": 4790,
      "train_runtime": 46560.4075,
      "train_tokens_per_second": 29226.04
    },
    {
      "epoch": 0.16983372658981397,
      "grad_norm": 1.4609375,
      "learning_rate": 4.1101135401667056e-05,
      "loss": 1.1796425819396972,
      "num_input_tokens_seen": 1363593088,
      "step": 4800,
      "train_runtime": 46657.2961,
      "train_tokens_per_second": 29225.72
    },
    {
      "epoch": 0.17018754685354273,
      "grad_norm": 1.3671875,
      "learning_rate": 4.108725597824708e-05,
      "loss": 1.168414306640625,
      "num_input_tokens_seen": 1366410176,
      "step": 4810,
      "train_runtime": 46752.5326,
      "train_tokens_per_second": 29226.442
    },
    {
      "epoch": 0.17054136711727153,
      "grad_norm": 1.3828125,
      "learning_rate": 4.107339060614564e-05,
      "loss": 1.1621706008911132,
      "num_input_tokens_seen": 1369257856,
      "step": 4820,
      "train_runtime": 46849.9652,
      "train_tokens_per_second": 29226.443
    },
    {
      "epoch": 0.1708951873810003,
      "grad_norm": 1.4140625,
      "learning_rate": 4.1059539261669825e-05,
      "loss": 1.1523948669433595,
      "num_input_tokens_seen": 1372139584,
      "step": 4830,
      "train_runtime": 46952.0795,
      "train_tokens_per_second": 29224.256
    },
    {
      "epoch": 0.17124900764472908,
      "grad_norm": 1.4296875,
      "learning_rate": 4.104570192118262e-05,
      "loss": 1.1553438186645508,
      "num_input_tokens_seen": 1374939520,
      "step": 4840,
      "train_runtime": 47048.903,
      "train_tokens_per_second": 29223.625
    },
    {
      "epoch": 0.17160282790845785,
      "grad_norm": 1.4296875,
      "learning_rate": 4.1031878561102714e-05,
      "loss": 1.1646602630615235,
      "num_input_tokens_seen": 1377782592,
      "step": 4850,
      "train_runtime": 47144.8875,
      "train_tokens_per_second": 29224.433
    },
    {
      "epoch": 0.17195664817218664,
      "grad_norm": 1.359375,
      "learning_rate": 4.1018069157904385e-05,
      "loss": 1.1651230812072755,
      "num_input_tokens_seen": 1380642112,
      "step": 4860,
      "train_runtime": 47242.3557,
      "train_tokens_per_second": 29224.667
    },
    {
      "epoch": 0.1723104684359154,
      "grad_norm": 1.3984375,
      "learning_rate": 4.100427368811727e-05,
      "loss": 1.1619221687316894,
      "num_input_tokens_seen": 1383498688,
      "step": 4870,
      "train_runtime": 47339.9335,
      "train_tokens_per_second": 29224.77
    },
    {
      "epoch": 0.1726642886996442,
      "grad_norm": 1.421875,
      "learning_rate": 4.099049212832622e-05,
      "loss": 1.166537380218506,
      "num_input_tokens_seen": 1386405760,
      "step": 4880,
      "train_runtime": 47440.8473,
      "train_tokens_per_second": 29223.883
    },
    {
      "epoch": 0.17301810896337297,
      "grad_norm": 1.4140625,
      "learning_rate": 4.0976724455171155e-05,
      "loss": 1.155689525604248,
      "num_input_tokens_seen": 1389235520,
      "step": 4890,
      "train_runtime": 47538.2575,
      "train_tokens_per_second": 29223.526
    },
    {
      "epoch": 0.17337192922710173,
      "grad_norm": 1.375,
      "learning_rate": 4.096297064534688e-05,
      "loss": 1.1490235328674316,
      "num_input_tokens_seen": 1392041408,
      "step": 4900,
      "train_runtime": 47634.3289,
      "train_tokens_per_second": 29223.492
    },
    {
      "epoch": 0.17372574949083053,
      "grad_norm": 1.390625,
      "learning_rate": 4.0949230675602904e-05,
      "loss": 1.1558156967163087,
      "num_input_tokens_seen": 1394892672,
      "step": 4910,
      "train_runtime": 47731.0245,
      "train_tokens_per_second": 29224.025
    },
    {
      "epoch": 0.1740795697545593,
      "grad_norm": 1.3984375,
      "learning_rate": 4.09355045227433e-05,
      "loss": 1.1501849174499512,
      "num_input_tokens_seen": 1397753408,
      "step": 4920,
      "train_runtime": 47830.6114,
      "train_tokens_per_second": 29222.989
    },
    {
      "epoch": 0.1744333900182881,
      "grad_norm": 1.359375,
      "learning_rate": 4.092179216362654e-05,
      "loss": 1.1577836990356445,
      "num_input_tokens_seen": 1400560384,
      "step": 4930,
      "train_runtime": 47924.6172,
      "train_tokens_per_second": 29224.237
    },
    {
      "epoch": 0.17478721028201685,
      "grad_norm": 1.4375,
      "learning_rate": 4.090809357516532e-05,
      "loss": 1.164453887939453,
      "num_input_tokens_seen": 1403432320,
      "step": 4940,
      "train_runtime": 48024.1259,
      "train_tokens_per_second": 29223.485
    },
    {
      "epoch": 0.17514103054574565,
      "grad_norm": 1.4140625,
      "learning_rate": 4.089440873432638e-05,
      "loss": 1.1713566780090332,
      "num_input_tokens_seen": 1406244736,
      "step": 4950,
      "train_runtime": 48116.6901,
      "train_tokens_per_second": 29225.716
    },
    {
      "epoch": 0.1754948508094744,
      "grad_norm": 1.40625,
      "learning_rate": 4.088073761813037e-05,
      "loss": 1.1553348541259765,
      "num_input_tokens_seen": 1409138176,
      "step": 4960,
      "train_runtime": 48218.5514,
      "train_tokens_per_second": 29223.984
    },
    {
      "epoch": 0.1758486710732032,
      "grad_norm": 1.3984375,
      "learning_rate": 4.086708020365172e-05,
      "loss": 1.1524312973022461,
      "num_input_tokens_seen": 1412013888,
      "step": 4970,
      "train_runtime": 48319.4241,
      "train_tokens_per_second": 29222.49
    },
    {
      "epoch": 0.17620249133693197,
      "grad_norm": 1.4296875,
      "learning_rate": 4.0853436468018354e-05,
      "loss": 1.159165382385254,
      "num_input_tokens_seen": 1414840448,
      "step": 4980,
      "train_runtime": 48416.0872,
      "train_tokens_per_second": 29222.528
    },
    {
      "epoch": 0.17655631160066076,
      "grad_norm": 1.359375,
      "learning_rate": 4.0839806388411686e-05,
      "loss": 1.158484649658203,
      "num_input_tokens_seen": 1417739520,
      "step": 4990,
      "train_runtime": 48514.9025,
      "train_tokens_per_second": 29222.763
    },
    {
      "epoch": 0.17691013186438953,
      "grad_norm": 1.3828125,
      "learning_rate": 4.0826189942066346e-05,
      "loss": 1.1729397773742676,
      "num_input_tokens_seen": 1420613056,
      "step": 5000,
      "train_runtime": 48613.5893,
      "train_tokens_per_second": 29222.55
    },
    {
      "epoch": 0.17691013186438953,
      "eval_loss": 1.0554543733596802,
      "eval_runtime": 8.4538,
      "eval_samples_per_second": 471.739,
      "eval_steps_per_second": 3.785,
      "num_input_tokens_seen": 1420613056,
      "step": 5000
    },
    {
      "epoch": 0.17726395212811832,
      "grad_norm": 1.390625,
      "learning_rate": 4.081258710627008e-05,
      "loss": 1.1454292297363282,
      "num_input_tokens_seen": 1423456576,
      "step": 5010,
      "train_runtime": 48740.9535,
      "train_tokens_per_second": 29204.529
    },
    {
      "epoch": 0.1776177723918471,
      "grad_norm": 1.3515625,
      "learning_rate": 4.0798997858363557e-05,
      "loss": 1.161700439453125,
      "num_input_tokens_seen": 1426246848,
      "step": 5020,
      "train_runtime": 48832.8141,
      "train_tokens_per_second": 29206.731
    },
    {
      "epoch": 0.17797159265557588,
      "grad_norm": 1.40625,
      "learning_rate": 4.078542217574024e-05,
      "loss": 1.1583166122436523,
      "num_input_tokens_seen": 1429053568,
      "step": 5030,
      "train_runtime": 48928.9495,
      "train_tokens_per_second": 29206.709
    },
    {
      "epoch": 0.17832541291930465,
      "grad_norm": 1.3515625,
      "learning_rate": 4.0771860035846196e-05,
      "loss": 1.1529541015625,
      "num_input_tokens_seen": 1431894464,
      "step": 5040,
      "train_runtime": 49026.0584,
      "train_tokens_per_second": 29206.804
    },
    {
      "epoch": 0.17867923318303344,
      "grad_norm": 1.3984375,
      "learning_rate": 4.0758311416179965e-05,
      "loss": 1.1603623390197755,
      "num_input_tokens_seen": 1434778752,
      "step": 5050,
      "train_runtime": 49125.9649,
      "train_tokens_per_second": 29206.118
    },
    {
      "epoch": 0.1790330534467622,
      "grad_norm": 1.421875,
      "learning_rate": 4.0744776294292386e-05,
      "loss": 1.150662899017334,
      "num_input_tokens_seen": 1437638720,
      "step": 5060,
      "train_runtime": 49225.1784,
      "train_tokens_per_second": 29205.353
    },
    {
      "epoch": 0.179386873710491,
      "grad_norm": 1.4375,
      "learning_rate": 4.073125464778646e-05,
      "loss": 1.1515050888061524,
      "num_input_tokens_seen": 1440541568,
      "step": 5070,
      "train_runtime": 49328.1591,
      "train_tokens_per_second": 29203.23
    },
    {
      "epoch": 0.17974069397421977,
      "grad_norm": 1.40625,
      "learning_rate": 4.071774645431717e-05,
      "loss": 1.1444365501403808,
      "num_input_tokens_seen": 1443293440,
      "step": 5080,
      "train_runtime": 49423.4369,
      "train_tokens_per_second": 29202.612
    },
    {
      "epoch": 0.18009451423794856,
      "grad_norm": 1.3515625,
      "learning_rate": 4.070425169159135e-05,
      "loss": 1.1678031921386718,
      "num_input_tokens_seen": 1446114368,
      "step": 5090,
      "train_runtime": 49520.6974,
      "train_tokens_per_second": 29202.221
    },
    {
      "epoch": 0.18044833450167733,
      "grad_norm": 1.359375,
      "learning_rate": 4.069077033736751e-05,
      "loss": 1.1512995719909669,
      "num_input_tokens_seen": 1448938560,
      "step": 5100,
      "train_runtime": 49618.5831,
      "train_tokens_per_second": 29201.53
    },
    {
      "epoch": 0.18080215476540612,
      "grad_norm": 1.40625,
      "learning_rate": 4.06773023694557e-05,
      "loss": 1.1586835861206055,
      "num_input_tokens_seen": 1451746496,
      "step": 5110,
      "train_runtime": 49714.3736,
      "train_tokens_per_second": 29201.746
    },
    {
      "epoch": 0.18115597502913489,
      "grad_norm": 1.3828125,
      "learning_rate": 4.066384776571732e-05,
      "loss": 1.1529558181762696,
      "num_input_tokens_seen": 1454587072,
      "step": 5120,
      "train_runtime": 49810.6538,
      "train_tokens_per_second": 29202.328
    },
    {
      "epoch": 0.18150979529286368,
      "grad_norm": 1.5078125,
      "learning_rate": 4.065040650406504e-05,
      "loss": 1.1565089225769043,
      "num_input_tokens_seen": 1457448256,
      "step": 5130,
      "train_runtime": 49910.1208,
      "train_tokens_per_second": 29201.457
    },
    {
      "epoch": 0.18186361555659245,
      "grad_norm": 1.40625,
      "learning_rate": 4.0636978562462576e-05,
      "loss": 1.161362648010254,
      "num_input_tokens_seen": 1460298880,
      "step": 5140,
      "train_runtime": 50008.7864,
      "train_tokens_per_second": 29200.846
    },
    {
      "epoch": 0.1822174358203212,
      "grad_norm": 1.3828125,
      "learning_rate": 4.062356391892456e-05,
      "loss": 1.1447731018066407,
      "num_input_tokens_seen": 1463134592,
      "step": 5150,
      "train_runtime": 50108.1207,
      "train_tokens_per_second": 29199.55
    },
    {
      "epoch": 0.18257125608405,
      "grad_norm": 1.3828125,
      "learning_rate": 4.0610162551516395e-05,
      "loss": 1.1505602836608886,
      "num_input_tokens_seen": 1466017024,
      "step": 5160,
      "train_runtime": 50209.0531,
      "train_tokens_per_second": 29198.261
    },
    {
      "epoch": 0.18292507634777877,
      "grad_norm": 1.4609375,
      "learning_rate": 4.059677443835412e-05,
      "loss": 1.1518810272216797,
      "num_input_tokens_seen": 1468844032,
      "step": 5170,
      "train_runtime": 50303.6015,
      "train_tokens_per_second": 29199.58
    },
    {
      "epoch": 0.18327889661150756,
      "grad_norm": 1.359375,
      "learning_rate": 4.058339955760423e-05,
      "loss": 1.1491867065429688,
      "num_input_tokens_seen": 1471720064,
      "step": 5180,
      "train_runtime": 50406.047,
      "train_tokens_per_second": 29197.292
    },
    {
      "epoch": 0.18363271687523633,
      "grad_norm": 1.3515625,
      "learning_rate": 4.0570037887483535e-05,
      "loss": 1.1602293014526368,
      "num_input_tokens_seen": 1474620736,
      "step": 5190,
      "train_runtime": 50507.3471,
      "train_tokens_per_second": 29196.163
    },
    {
      "epoch": 0.18398653713896512,
      "grad_norm": 1.40625,
      "learning_rate": 4.0556689406259025e-05,
      "loss": 1.1516728401184082,
      "num_input_tokens_seen": 1477467008,
      "step": 5200,
      "train_runtime": 50604.0907,
      "train_tokens_per_second": 29196.592
    },
    {
      "epoch": 0.1843403574026939,
      "grad_norm": 1.40625,
      "learning_rate": 4.054335409224771e-05,
      "loss": 1.1603678703308105,
      "num_input_tokens_seen": 1480353088,
      "step": 5210,
      "train_runtime": 50703.3004,
      "train_tokens_per_second": 29196.385
    },
    {
      "epoch": 0.18469417766642268,
      "grad_norm": 1.328125,
      "learning_rate": 4.053003192381646e-05,
      "loss": 1.1358709335327148,
      "num_input_tokens_seen": 1483264448,
      "step": 5220,
      "train_runtime": 50803.2103,
      "train_tokens_per_second": 29196.274
    },
    {
      "epoch": 0.18504799793015145,
      "grad_norm": 1.4140625,
      "learning_rate": 4.051672287938189e-05,
      "loss": 1.1461207389831543,
      "num_input_tokens_seen": 1486090944,
      "step": 5230,
      "train_runtime": 50900.4302,
      "train_tokens_per_second": 29196.039
    },
    {
      "epoch": 0.18540181819388024,
      "grad_norm": 1.40625,
      "learning_rate": 4.050342693741019e-05,
      "loss": 1.1470937728881836,
      "num_input_tokens_seen": 1488925888,
      "step": 5240,
      "train_runtime": 50996.6361,
      "train_tokens_per_second": 29196.551
    },
    {
      "epoch": 0.185755638457609,
      "grad_norm": 1.4296875,
      "learning_rate": 4.049014407641699e-05,
      "loss": 1.1562808990478515,
      "num_input_tokens_seen": 1491699968,
      "step": 5250,
      "train_runtime": 51089.9572,
      "train_tokens_per_second": 29197.518
    },
    {
      "epoch": 0.1861094587213378,
      "grad_norm": 1.4453125,
      "learning_rate": 4.047687427496717e-05,
      "loss": 1.1603093147277832,
      "num_input_tokens_seen": 1494559296,
      "step": 5260,
      "train_runtime": 51189.7178,
      "train_tokens_per_second": 29196.475
    },
    {
      "epoch": 0.18646327898506657,
      "grad_norm": 1.375,
      "learning_rate": 4.046361751167479e-05,
      "loss": 1.1542572021484374,
      "num_input_tokens_seen": 1497424320,
      "step": 5270,
      "train_runtime": 51284.273,
      "train_tokens_per_second": 29198.509
    },
    {
      "epoch": 0.18681709924879536,
      "grad_norm": 1.3828125,
      "learning_rate": 4.045037376520292e-05,
      "loss": 1.1529299736022949,
      "num_input_tokens_seen": 1500251456,
      "step": 5280,
      "train_runtime": 51382.623,
      "train_tokens_per_second": 29197.642
    },
    {
      "epoch": 0.18717091951252413,
      "grad_norm": 1.3671875,
      "learning_rate": 4.043714301426344e-05,
      "loss": 1.1605234146118164,
      "num_input_tokens_seen": 1503083520,
      "step": 5290,
      "train_runtime": 51481.3425,
      "train_tokens_per_second": 29196.665
    },
    {
      "epoch": 0.18752473977625292,
      "grad_norm": 1.3515625,
      "learning_rate": 4.042392523761696e-05,
      "loss": 1.1543375968933105,
      "num_input_tokens_seen": 1505860864,
      "step": 5300,
      "train_runtime": 51576.1011,
      "train_tokens_per_second": 29196.873
    },
    {
      "epoch": 0.18787856003998168,
      "grad_norm": 1.3828125,
      "learning_rate": 4.041072041407267e-05,
      "loss": 1.1467929840087892,
      "num_input_tokens_seen": 1508762624,
      "step": 5310,
      "train_runtime": 51676.3124,
      "train_tokens_per_second": 29196.407
    },
    {
      "epoch": 0.18823238030371048,
      "grad_norm": 1.375,
      "learning_rate": 4.039752852248815e-05,
      "loss": 1.1630261421203614,
      "num_input_tokens_seen": 1511563328,
      "step": 5320,
      "train_runtime": 51772.2489,
      "train_tokens_per_second": 29196.401
    },
    {
      "epoch": 0.18858620056743924,
      "grad_norm": 1.3671875,
      "learning_rate": 4.0384349541769286e-05,
      "loss": 1.1554012298583984,
      "num_input_tokens_seen": 1514407936,
      "step": 5330,
      "train_runtime": 51869.783,
      "train_tokens_per_second": 29196.342
    },
    {
      "epoch": 0.18894002083116804,
      "grad_norm": 1.4765625,
      "learning_rate": 4.037118345087011e-05,
      "loss": 1.1593147277832032,
      "num_input_tokens_seen": 1517231040,
      "step": 5340,
      "train_runtime": 51967.408,
      "train_tokens_per_second": 29195.819
    },
    {
      "epoch": 0.1892938410948968,
      "grad_norm": 1.3984375,
      "learning_rate": 4.0358030228792636e-05,
      "loss": 1.1548017501831054,
      "num_input_tokens_seen": 1520078656,
      "step": 5350,
      "train_runtime": 52066.7486,
      "train_tokens_per_second": 29194.807
    },
    {
      "epoch": 0.1896476613586256,
      "grad_norm": 1.3671875,
      "learning_rate": 4.034488985458673e-05,
      "loss": 1.1534326553344727,
      "num_input_tokens_seen": 1522890176,
      "step": 5360,
      "train_runtime": 52159.9773,
      "train_tokens_per_second": 29196.527
    },
    {
      "epoch": 0.19000148162235436,
      "grad_norm": 1.4609375,
      "learning_rate": 4.033176230735001e-05,
      "loss": 1.1487655639648438,
      "num_input_tokens_seen": 1525755264,
      "step": 5370,
      "train_runtime": 52257.3638,
      "train_tokens_per_second": 29196.943
    },
    {
      "epoch": 0.19035530188608316,
      "grad_norm": 1.453125,
      "learning_rate": 4.0318647566227626e-05,
      "loss": 1.15179500579834,
      "num_input_tokens_seen": 1528616832,
      "step": 5380,
      "train_runtime": 52354.8715,
      "train_tokens_per_second": 29197.222
    },
    {
      "epoch": 0.19070912214981192,
      "grad_norm": 1.359375,
      "learning_rate": 4.0305545610412205e-05,
      "loss": 1.149301528930664,
      "num_input_tokens_seen": 1531522944,
      "step": 5390,
      "train_runtime": 52458.3277,
      "train_tokens_per_second": 29195.039
    },
    {
      "epoch": 0.19106294241354072,
      "grad_norm": 1.3984375,
      "learning_rate": 4.029245641914365e-05,
      "loss": 1.163567066192627,
      "num_input_tokens_seen": 1534331328,
      "step": 5400,
      "train_runtime": 52555.1986,
      "train_tokens_per_second": 29194.663
    },
    {
      "epoch": 0.19141676267726948,
      "grad_norm": 1.3828125,
      "learning_rate": 4.027937997170904e-05,
      "loss": 1.1477647781372071,
      "num_input_tokens_seen": 1537209664,
      "step": 5410,
      "train_runtime": 52654.2983,
      "train_tokens_per_second": 29194.381
    },
    {
      "epoch": 0.19177058294099825,
      "grad_norm": 1.4375,
      "learning_rate": 4.026631624744247e-05,
      "loss": 1.1594183921813965,
      "num_input_tokens_seen": 1540037376,
      "step": 5420,
      "train_runtime": 52752.0564,
      "train_tokens_per_second": 29193.883
    },
    {
      "epoch": 0.19212440320472704,
      "grad_norm": 1.375,
      "learning_rate": 4.025326522572493e-05,
      "loss": 1.1417713165283203,
      "num_input_tokens_seen": 1542879168,
      "step": 5430,
      "train_runtime": 52849.8164,
      "train_tokens_per_second": 29193.652
    },
    {
      "epoch": 0.1924782234684558,
      "grad_norm": 1.3671875,
      "learning_rate": 4.024022688598415e-05,
      "loss": 1.165010643005371,
      "num_input_tokens_seen": 1545750912,
      "step": 5440,
      "train_runtime": 52949.0474,
      "train_tokens_per_second": 29193.177
    },
    {
      "epoch": 0.1928320437321846,
      "grad_norm": 1.390625,
      "learning_rate": 4.0227201207694494e-05,
      "loss": 1.1466317176818848,
      "num_input_tokens_seen": 1548581376,
      "step": 5450,
      "train_runtime": 53045.1953,
      "train_tokens_per_second": 29193.622
    },
    {
      "epoch": 0.19318586399591336,
      "grad_norm": 1.3984375,
      "learning_rate": 4.021418817037677e-05,
      "loss": 1.1439767837524415,
      "num_input_tokens_seen": 1551461504,
      "step": 5460,
      "train_runtime": 53144.9877,
      "train_tokens_per_second": 29192.998
    },
    {
      "epoch": 0.19353968425964216,
      "grad_norm": 1.390625,
      "learning_rate": 4.0201187753598174e-05,
      "loss": 1.1544062614440918,
      "num_input_tokens_seen": 1554299584,
      "step": 5470,
      "train_runtime": 53243.1234,
      "train_tokens_per_second": 29192.494
    },
    {
      "epoch": 0.19389350452337092,
      "grad_norm": 1.4609375,
      "learning_rate": 4.018819993697208e-05,
      "loss": 1.144437026977539,
      "num_input_tokens_seen": 1557140416,
      "step": 5480,
      "train_runtime": 53338.0593,
      "train_tokens_per_second": 29193.796
    },
    {
      "epoch": 0.19424732478709972,
      "grad_norm": 1.359375,
      "learning_rate": 4.017522470015793e-05,
      "loss": 1.1415154457092285,
      "num_input_tokens_seen": 1560041024,
      "step": 5490,
      "train_runtime": 53437.1489,
      "train_tokens_per_second": 29193.942
    },
    {
      "epoch": 0.19460114505082848,
      "grad_norm": 1.40625,
      "learning_rate": 4.0162262022861144e-05,
      "loss": 1.138638687133789,
      "num_input_tokens_seen": 1562892608,
      "step": 5500,
      "train_runtime": 53537.1356,
      "train_tokens_per_second": 29192.683
    },
    {
      "epoch": 0.19495496531455728,
      "grad_norm": 1.375,
      "learning_rate": 4.0149311884832906e-05,
      "loss": 1.1469120979309082,
      "num_input_tokens_seen": 1565761536,
      "step": 5510,
      "train_runtime": 53635.3466,
      "train_tokens_per_second": 29192.718
    },
    {
      "epoch": 0.19530878557828604,
      "grad_norm": 1.390625,
      "learning_rate": 4.0136374265870116e-05,
      "loss": 1.1435979843139648,
      "num_input_tokens_seen": 1568601984,
      "step": 5520,
      "train_runtime": 53730.6046,
      "train_tokens_per_second": 29193.827
    },
    {
      "epoch": 0.19566260584201484,
      "grad_norm": 1.3671875,
      "learning_rate": 4.0123449145815174e-05,
      "loss": 1.1436124801635743,
      "num_input_tokens_seen": 1571458304,
      "step": 5530,
      "train_runtime": 53825.1891,
      "train_tokens_per_second": 29195.593
    },
    {
      "epoch": 0.1960164261057436,
      "grad_norm": 1.46875,
      "learning_rate": 4.011053650455592e-05,
      "loss": 1.1641233444213868,
      "num_input_tokens_seen": 1574254144,
      "step": 5540,
      "train_runtime": 53919.0228,
      "train_tokens_per_second": 29196.637
    },
    {
      "epoch": 0.1963702463694724,
      "grad_norm": 1.34375,
      "learning_rate": 4.0097636322025466e-05,
      "loss": 1.1391079902648926,
      "num_input_tokens_seen": 1577121152,
      "step": 5550,
      "train_runtime": 54016.4198,
      "train_tokens_per_second": 29197.069
    },
    {
      "epoch": 0.19672406663320116,
      "grad_norm": 1.4375,
      "learning_rate": 4.008474857820206e-05,
      "loss": 1.1429768562316895,
      "num_input_tokens_seen": 1579922944,
      "step": 5560,
      "train_runtime": 54110.6774,
      "train_tokens_per_second": 29197.989
    },
    {
      "epoch": 0.19707788689692995,
      "grad_norm": 1.5078125,
      "learning_rate": 4.007187325310899e-05,
      "loss": 1.1527151107788085,
      "num_input_tokens_seen": 1582776832,
      "step": 5570,
      "train_runtime": 54207.1796,
      "train_tokens_per_second": 29198.657
    },
    {
      "epoch": 0.19743170716065872,
      "grad_norm": 1.4453125,
      "learning_rate": 4.00590103268144e-05,
      "loss": 1.1505550384521483,
      "num_input_tokens_seen": 1585641792,
      "step": 5580,
      "train_runtime": 54307.187,
      "train_tokens_per_second": 29197.642
    },
    {
      "epoch": 0.19778552742438751,
      "grad_norm": 1.3828125,
      "learning_rate": 4.004615977943124e-05,
      "loss": 1.1448429107666016,
      "num_input_tokens_seen": 1588441088,
      "step": 5590,
      "train_runtime": 54401.783,
      "train_tokens_per_second": 29198.328
    },
    {
      "epoch": 0.19813934768811628,
      "grad_norm": 1.375,
      "learning_rate": 4.0033321591117025e-05,
      "loss": 1.1348305702209474,
      "num_input_tokens_seen": 1591290368,
      "step": 5600,
      "train_runtime": 54498.4769,
      "train_tokens_per_second": 29198.804
    },
    {
      "epoch": 0.19849316795184507,
      "grad_norm": 1.2890625,
      "learning_rate": 4.002049574207381e-05,
      "loss": 1.1528627395629882,
      "num_input_tokens_seen": 1594144128,
      "step": 5610,
      "train_runtime": 54596.3287,
      "train_tokens_per_second": 29198.742
    },
    {
      "epoch": 0.19884698821557384,
      "grad_norm": 1.4375,
      "learning_rate": 4.000768221254803e-05,
      "loss": 1.1378749847412108,
      "num_input_tokens_seen": 1597000064,
      "step": 5620,
      "train_runtime": 54692.8803,
      "train_tokens_per_second": 29199.414
    },
    {
      "epoch": 0.19920080847930263,
      "grad_norm": 1.453125,
      "learning_rate": 3.999488098283034e-05,
      "loss": 1.1557339668273925,
      "num_input_tokens_seen": 1599860288,
      "step": 5630,
      "train_runtime": 54793.8956,
      "train_tokens_per_second": 29197.783
    },
    {
      "epoch": 0.1995546287430314,
      "grad_norm": 1.40625,
      "learning_rate": 3.9982092033255506e-05,
      "loss": 1.1512733459472657,
      "num_input_tokens_seen": 1602709120,
      "step": 5640,
      "train_runtime": 54891.6999,
      "train_tokens_per_second": 29197.659
    },
    {
      "epoch": 0.1999084490067602,
      "grad_norm": 1.4140625,
      "learning_rate": 3.996931534420232e-05,
      "loss": 1.1527785301208495,
      "num_input_tokens_seen": 1605536384,
      "step": 5650,
      "train_runtime": 54988.336,
      "train_tokens_per_second": 29197.763
    },
    {
      "epoch": 0.20026226927048896,
      "grad_norm": 1.3515625,
      "learning_rate": 3.995655089609339e-05,
      "loss": 1.1383662223815918,
      "num_input_tokens_seen": 1608395072,
      "step": 5660,
      "train_runtime": 55084.7358,
      "train_tokens_per_second": 29198.562
    },
    {
      "epoch": 0.20061608953421772,
      "grad_norm": 1.3984375,
      "learning_rate": 3.994379866939511e-05,
      "loss": 1.1372873306274414,
      "num_input_tokens_seen": 1611246528,
      "step": 5670,
      "train_runtime": 55182.7103,
      "train_tokens_per_second": 29198.394
    },
    {
      "epoch": 0.20096990979794652,
      "grad_norm": 1.3984375,
      "learning_rate": 3.993105864461745e-05,
      "loss": 1.1518970489501954,
      "num_input_tokens_seen": 1614097856,
      "step": 5680,
      "train_runtime": 55281.5908,
      "train_tokens_per_second": 29197.746
    },
    {
      "epoch": 0.20132373006167528,
      "grad_norm": 1.4296875,
      "learning_rate": 3.9918330802313866e-05,
      "loss": 1.1478713989257812,
      "num_input_tokens_seen": 1616895488,
      "step": 5690,
      "train_runtime": 55379.7952,
      "train_tokens_per_second": 29196.487
    },
    {
      "epoch": 0.20167755032540408,
      "grad_norm": 1.421875,
      "learning_rate": 3.9905615123081206e-05,
      "loss": 1.1519228935241699,
      "num_input_tokens_seen": 1619738624,
      "step": 5700,
      "train_runtime": 55476.9616,
      "train_tokens_per_second": 29196.599
    },
    {
      "epoch": 0.20203137058913284,
      "grad_norm": 1.4140625,
      "learning_rate": 3.989291158755953e-05,
      "loss": 1.1645353317260743,
      "num_input_tokens_seen": 1622599168,
      "step": 5710,
      "train_runtime": 55577.135,
      "train_tokens_per_second": 29195.445
    },
    {
      "epoch": 0.20238519085286164,
      "grad_norm": 1.4453125,
      "learning_rate": 3.988022017643201e-05,
      "loss": 1.1464563369750977,
      "num_input_tokens_seen": 1625486464,
      "step": 5720,
      "train_runtime": 55677.2571,
      "train_tokens_per_second": 29194.801
    },
    {
      "epoch": 0.2027390111165904,
      "grad_norm": 1.4375,
      "learning_rate": 3.9867540870424826e-05,
      "loss": 1.1449846267700194,
      "num_input_tokens_seen": 1628304704,
      "step": 5730,
      "train_runtime": 55773.7572,
      "train_tokens_per_second": 29194.818
    },
    {
      "epoch": 0.2030928313803192,
      "grad_norm": 1.4296875,
      "learning_rate": 3.985487365030702e-05,
      "loss": 1.1489128112792968,
      "num_input_tokens_seen": 1631111616,
      "step": 5740,
      "train_runtime": 55868.4489,
      "train_tokens_per_second": 29195.577
    },
    {
      "epoch": 0.20344665164404796,
      "grad_norm": 1.453125,
      "learning_rate": 3.984221849689036e-05,
      "loss": 1.1492780685424804,
      "num_input_tokens_seen": 1633982144,
      "step": 5750,
      "train_runtime": 55967.4685,
      "train_tokens_per_second": 29195.213
    },
    {
      "epoch": 0.20380047190777675,
      "grad_norm": 1.453125,
      "learning_rate": 3.982957539102927e-05,
      "loss": 1.1517362594604492,
      "num_input_tokens_seen": 1636864512,
      "step": 5760,
      "train_runtime": 56064.5572,
      "train_tokens_per_second": 29196.066
    },
    {
      "epoch": 0.20415429217150552,
      "grad_norm": 1.3515625,
      "learning_rate": 3.981694431362065e-05,
      "loss": 1.1585161209106445,
      "num_input_tokens_seen": 1639718144,
      "step": 5770,
      "train_runtime": 56163.8876,
      "train_tokens_per_second": 29195.239
    },
    {
      "epoch": 0.2045081124352343,
      "grad_norm": 1.40625,
      "learning_rate": 3.9804325245603786e-05,
      "loss": 1.1651932716369628,
      "num_input_tokens_seen": 1642537728,
      "step": 5780,
      "train_runtime": 56264.2992,
      "train_tokens_per_second": 29193.25
    },
    {
      "epoch": 0.20486193269896308,
      "grad_norm": 1.375,
      "learning_rate": 3.9791718167960226e-05,
      "loss": 1.147236156463623,
      "num_input_tokens_seen": 1645398208,
      "step": 5790,
      "train_runtime": 56362.2523,
      "train_tokens_per_second": 29193.266
    },
    {
      "epoch": 0.20521575296269187,
      "grad_norm": 1.2890625,
      "learning_rate": 3.9779123061713665e-05,
      "loss": 1.1393996238708497,
      "num_input_tokens_seen": 1648256576,
      "step": 5800,
      "train_runtime": 56458.8542,
      "train_tokens_per_second": 29193.943
    },
    {
      "epoch": 0.20556957322642064,
      "grad_norm": 1.34375,
      "learning_rate": 3.976653990792979e-05,
      "loss": 1.1316509246826172,
      "num_input_tokens_seen": 1651121344,
      "step": 5810,
      "train_runtime": 56559.0913,
      "train_tokens_per_second": 29192.855
    },
    {
      "epoch": 0.20592339349014943,
      "grad_norm": 1.3671875,
      "learning_rate": 3.9753968687716206e-05,
      "loss": 1.1508367538452149,
      "num_input_tokens_seen": 1654019904,
      "step": 5820,
      "train_runtime": 56660.667,
      "train_tokens_per_second": 29191.677
    },
    {
      "epoch": 0.2062772137538782,
      "grad_norm": 1.390625,
      "learning_rate": 3.974140938222232e-05,
      "loss": 1.163071632385254,
      "num_input_tokens_seen": 1656882560,
      "step": 5830,
      "train_runtime": 56757.9602,
      "train_tokens_per_second": 29192.074
    },
    {
      "epoch": 0.206631034017607,
      "grad_norm": 1.4453125,
      "learning_rate": 3.972886197263915e-05,
      "loss": 1.1346718788146972,
      "num_input_tokens_seen": 1659705024,
      "step": 5840,
      "train_runtime": 56855.0025,
      "train_tokens_per_second": 29191.891
    },
    {
      "epoch": 0.20698485428133576,
      "grad_norm": 1.3203125,
      "learning_rate": 3.97163264401993e-05,
      "loss": 1.1526689529418945,
      "num_input_tokens_seen": 1662524416,
      "step": 5850,
      "train_runtime": 56952.7032,
      "train_tokens_per_second": 29191.317
    },
    {
      "epoch": 0.20733867454506455,
      "grad_norm": 1.4140625,
      "learning_rate": 3.970380276617677e-05,
      "loss": 1.1438655853271484,
      "num_input_tokens_seen": 1665339712,
      "step": 5860,
      "train_runtime": 57046.7553,
      "train_tokens_per_second": 29192.54
    },
    {
      "epoch": 0.20769249480879332,
      "grad_norm": 1.4453125,
      "learning_rate": 3.96912909318869e-05,
      "loss": 1.1559438705444336,
      "num_input_tokens_seen": 1668169472,
      "step": 5870,
      "train_runtime": 57143.1243,
      "train_tokens_per_second": 29192.829
    },
    {
      "epoch": 0.2080463150725221,
      "grad_norm": 1.421875,
      "learning_rate": 3.96787909186862e-05,
      "loss": 1.159921360015869,
      "num_input_tokens_seen": 1671030400,
      "step": 5880,
      "train_runtime": 57242.653,
      "train_tokens_per_second": 29192.05
    },
    {
      "epoch": 0.20840013533625087,
      "grad_norm": 1.421875,
      "learning_rate": 3.9666302707972244e-05,
      "loss": 1.1411149978637696,
      "num_input_tokens_seen": 1673912576,
      "step": 5890,
      "train_runtime": 57342.8691,
      "train_tokens_per_second": 29191.294
    },
    {
      "epoch": 0.20875395559997967,
      "grad_norm": 1.3515625,
      "learning_rate": 3.965382628118358e-05,
      "loss": 1.1569387435913085,
      "num_input_tokens_seen": 1676753344,
      "step": 5900,
      "train_runtime": 57442.2207,
      "train_tokens_per_second": 29190.26
    },
    {
      "epoch": 0.20910777586370843,
      "grad_norm": 1.4140625,
      "learning_rate": 3.964136161979959e-05,
      "loss": 1.1489845275878907,
      "num_input_tokens_seen": 1679636032,
      "step": 5910,
      "train_runtime": 57543.6342,
      "train_tokens_per_second": 29188.911
    },
    {
      "epoch": 0.20946159612743723,
      "grad_norm": 1.40625,
      "learning_rate": 3.9628908705340406e-05,
      "loss": 1.1315176010131835,
      "num_input_tokens_seen": 1682448960,
      "step": 5920,
      "train_runtime": 57637.531,
      "train_tokens_per_second": 29190.164
    },
    {
      "epoch": 0.209815416391166,
      "grad_norm": 1.4296875,
      "learning_rate": 3.961646751936673e-05,
      "loss": 1.154404640197754,
      "num_input_tokens_seen": 1685275328,
      "step": 5930,
      "train_runtime": 57735.653,
      "train_tokens_per_second": 29189.508
    },
    {
      "epoch": 0.21016923665489476,
      "grad_norm": 1.390625,
      "learning_rate": 3.960403804347979e-05,
      "loss": 1.149032974243164,
      "num_input_tokens_seen": 1688108032,
      "step": 5940,
      "train_runtime": 57836.2769,
      "train_tokens_per_second": 29187.702
    },
    {
      "epoch": 0.21052305691862355,
      "grad_norm": 1.375,
      "learning_rate": 3.959162025932119e-05,
      "loss": 1.1340028762817382,
      "num_input_tokens_seen": 1691020608,
      "step": 5950,
      "train_runtime": 57938.5232,
      "train_tokens_per_second": 29186.464
    },
    {
      "epoch": 0.21087687718235232,
      "grad_norm": 1.3203125,
      "learning_rate": 3.95792141485728e-05,
      "loss": 1.1358987808227539,
      "num_input_tokens_seen": 1693874496,
      "step": 5960,
      "train_runtime": 58035.898,
      "train_tokens_per_second": 29186.668
    },
    {
      "epoch": 0.2112306974460811,
      "grad_norm": 1.390625,
      "learning_rate": 3.956681969295664e-05,
      "loss": 1.1353602409362793,
      "num_input_tokens_seen": 1696687552,
      "step": 5970,
      "train_runtime": 58132.2615,
      "train_tokens_per_second": 29186.677
    },
    {
      "epoch": 0.21158451770980988,
      "grad_norm": 1.40625,
      "learning_rate": 3.955443687423479e-05,
      "loss": 1.1650691032409668,
      "num_input_tokens_seen": 1699554688,
      "step": 5980,
      "train_runtime": 58228.5775,
      "train_tokens_per_second": 29187.639
    },
    {
      "epoch": 0.21193833797353867,
      "grad_norm": 1.34375,
      "learning_rate": 3.954206567420924e-05,
      "loss": 1.1413604736328125,
      "num_input_tokens_seen": 1702368448,
      "step": 5990,
      "train_runtime": 58324.341,
      "train_tokens_per_second": 29187.959
    },
    {
      "epoch": 0.21229215823726744,
      "grad_norm": 1.40625,
      "learning_rate": 3.952970607472179e-05,
      "loss": 1.1468786239624023,
      "num_input_tokens_seen": 1705224320,
      "step": 6000,
      "train_runtime": 58421.791,
      "train_tokens_per_second": 29188.156
    },
    {
      "epoch": 0.21264597850099623,
      "grad_norm": 1.4140625,
      "learning_rate": 3.951735805765399e-05,
      "loss": 1.1585137367248535,
      "num_input_tokens_seen": 1708082560,
      "step": 6010,
      "train_runtime": 58522.3005,
      "train_tokens_per_second": 29186.866
    },
    {
      "epoch": 0.212999798764725,
      "grad_norm": 1.34375,
      "learning_rate": 3.950502160492692e-05,
      "loss": 1.1556333541870116,
      "num_input_tokens_seen": 1710936896,
      "step": 6020,
      "train_runtime": 58621.1972,
      "train_tokens_per_second": 29186.318
    },
    {
      "epoch": 0.2133536190284538,
      "grad_norm": 1.3828125,
      "learning_rate": 3.9492696698501205e-05,
      "loss": 1.1288800239562988,
      "num_input_tokens_seen": 1713764544,
      "step": 6030,
      "train_runtime": 58719.1419,
      "train_tokens_per_second": 29185.79
    },
    {
      "epoch": 0.21370743929218255,
      "grad_norm": 1.359375,
      "learning_rate": 3.9480383320376784e-05,
      "loss": 1.1399528503417968,
      "num_input_tokens_seen": 1716610688,
      "step": 6040,
      "train_runtime": 58814.2339,
      "train_tokens_per_second": 29186.994
    },
    {
      "epoch": 0.21406125955591135,
      "grad_norm": 1.421875,
      "learning_rate": 3.94680814525929e-05,
      "loss": 1.1543367385864258,
      "num_input_tokens_seen": 1719404096,
      "step": 6050,
      "train_runtime": 58910.3287,
      "train_tokens_per_second": 29186.802
    },
    {
      "epoch": 0.21441507981964011,
      "grad_norm": 1.421875,
      "learning_rate": 3.945579107722792e-05,
      "loss": 1.1419769287109376,
      "num_input_tokens_seen": 1722238400,
      "step": 6060,
      "train_runtime": 59008.5208,
      "train_tokens_per_second": 29186.266
    },
    {
      "epoch": 0.2147689000833689,
      "grad_norm": 1.390625,
      "learning_rate": 3.9443512176399276e-05,
      "loss": 1.1401005744934083,
      "num_input_tokens_seen": 1725054016,
      "step": 6070,
      "train_runtime": 59108.3679,
      "train_tokens_per_second": 29184.599
    },
    {
      "epoch": 0.21512272034709767,
      "grad_norm": 1.3671875,
      "learning_rate": 3.9431244732263307e-05,
      "loss": 1.1481748580932618,
      "num_input_tokens_seen": 1727897216,
      "step": 6080,
      "train_runtime": 59205.3681,
      "train_tokens_per_second": 29184.807
    },
    {
      "epoch": 0.21547654061082647,
      "grad_norm": 1.390625,
      "learning_rate": 3.941898872701519e-05,
      "loss": 1.1427518844604492,
      "num_input_tokens_seen": 1730726784,
      "step": 6090,
      "train_runtime": 59303.4314,
      "train_tokens_per_second": 29184.26
    },
    {
      "epoch": 0.21583036087455523,
      "grad_norm": 1.4140625,
      "learning_rate": 3.940674414288882e-05,
      "loss": 1.1553242683410645,
      "num_input_tokens_seen": 1733550144,
      "step": 6100,
      "train_runtime": 59398.42,
      "train_tokens_per_second": 29185.122
    },
    {
      "epoch": 0.21618418113828403,
      "grad_norm": 1.375,
      "learning_rate": 3.939451096215668e-05,
      "loss": 1.1446781158447266,
      "num_input_tokens_seen": 1736353792,
      "step": 6110,
      "train_runtime": 59490.7245,
      "train_tokens_per_second": 29186.967
    },
    {
      "epoch": 0.2165380014020128,
      "grad_norm": 1.40625,
      "learning_rate": 3.938228916712978e-05,
      "loss": 1.1400846481323241,
      "num_input_tokens_seen": 1739209408,
      "step": 6120,
      "train_runtime": 59588.3461,
      "train_tokens_per_second": 29187.073
    },
    {
      "epoch": 0.21689182166574159,
      "grad_norm": 1.390625,
      "learning_rate": 3.937007874015748e-05,
      "loss": 1.1396926879882812,
      "num_input_tokens_seen": 1742103104,
      "step": 6130,
      "train_runtime": 59688.4129,
      "train_tokens_per_second": 29186.621
    },
    {
      "epoch": 0.21724564192947035,
      "grad_norm": 1.421875,
      "learning_rate": 3.935787966362748e-05,
      "loss": 1.1415468215942384,
      "num_input_tokens_seen": 1744954176,
      "step": 6140,
      "train_runtime": 59786.5128,
      "train_tokens_per_second": 29186.418
    },
    {
      "epoch": 0.21759946219319914,
      "grad_norm": 1.5859375,
      "learning_rate": 3.9345691919965595e-05,
      "loss": 1.1422434806823731,
      "num_input_tokens_seen": 1747763136,
      "step": 6150,
      "train_runtime": 59880.6236,
      "train_tokens_per_second": 29187.457
    },
    {
      "epoch": 0.2179532824569279,
      "grad_norm": 1.4140625,
      "learning_rate": 3.9333515491635764e-05,
      "loss": 1.127164649963379,
      "num_input_tokens_seen": 1750596096,
      "step": 6160,
      "train_runtime": 59977.0687,
      "train_tokens_per_second": 29187.757
    },
    {
      "epoch": 0.2183071027206567,
      "grad_norm": 1.3828125,
      "learning_rate": 3.932135036113987e-05,
      "loss": 1.1408446311950684,
      "num_input_tokens_seen": 1753441664,
      "step": 6170,
      "train_runtime": 60074.709,
      "train_tokens_per_second": 29187.685
    },
    {
      "epoch": 0.21866092298438547,
      "grad_norm": 1.359375,
      "learning_rate": 3.930919651101764e-05,
      "loss": 1.1441112518310548,
      "num_input_tokens_seen": 1756270976,
      "step": 6180,
      "train_runtime": 60168.8001,
      "train_tokens_per_second": 29189.064
    },
    {
      "epoch": 0.21901474324811424,
      "grad_norm": 1.4296875,
      "learning_rate": 3.9297053923846576e-05,
      "loss": 1.139028263092041,
      "num_input_tokens_seen": 1759120064,
      "step": 6190,
      "train_runtime": 60266.842,
      "train_tokens_per_second": 29188.854
    },
    {
      "epoch": 0.21936856351184303,
      "grad_norm": 1.421875,
      "learning_rate": 3.928492258224183e-05,
      "loss": 1.1424497604370116,
      "num_input_tokens_seen": 1761969408,
      "step": 6200,
      "train_runtime": 60367.2567,
      "train_tokens_per_second": 29187.502
    },
    {
      "epoch": 0.2197223837755718,
      "grad_norm": 1.390625,
      "learning_rate": 3.927280246885609e-05,
      "loss": 1.1556337356567383,
      "num_input_tokens_seen": 1764794368,
      "step": 6210,
      "train_runtime": 60461.8492,
      "train_tokens_per_second": 29188.561
    },
    {
      "epoch": 0.2200762040393006,
      "grad_norm": 1.3515625,
      "learning_rate": 3.9260693566379486e-05,
      "loss": 1.1572488784790038,
      "num_input_tokens_seen": 1767617984,
      "step": 6220,
      "train_runtime": 60556.4517,
      "train_tokens_per_second": 29189.59
    },
    {
      "epoch": 0.22043002430302935,
      "grad_norm": 1.3671875,
      "learning_rate": 3.924859585753948e-05,
      "loss": 1.1354021072387694,
      "num_input_tokens_seen": 1770441920,
      "step": 6230,
      "train_runtime": 60655.5988,
      "train_tokens_per_second": 29188.434
    },
    {
      "epoch": 0.22078384456675815,
      "grad_norm": 1.484375,
      "learning_rate": 3.923650932510079e-05,
      "loss": 1.136590576171875,
      "num_input_tokens_seen": 1773221248,
      "step": 6240,
      "train_runtime": 60751.2281,
      "train_tokens_per_second": 29188.237
    },
    {
      "epoch": 0.2211376648304869,
      "grad_norm": 1.3828125,
      "learning_rate": 3.9224433951865215e-05,
      "loss": 1.1415470123291016,
      "num_input_tokens_seen": 1776083840,
      "step": 6250,
      "train_runtime": 60851.0098,
      "train_tokens_per_second": 29187.418
    },
    {
      "epoch": 0.2214914850942157,
      "grad_norm": 1.4453125,
      "learning_rate": 3.921236972067165e-05,
      "loss": 1.1432729721069337,
      "num_input_tokens_seen": 1778896128,
      "step": 6260,
      "train_runtime": 60947.4036,
      "train_tokens_per_second": 29187.398
    },
    {
      "epoch": 0.22184530535794447,
      "grad_norm": 1.4296875,
      "learning_rate": 3.920031661439585e-05,
      "loss": 1.1537821769714356,
      "num_input_tokens_seen": 1781776256,
      "step": 6270,
      "train_runtime": 61047.4585,
      "train_tokens_per_second": 29186.739
    },
    {
      "epoch": 0.22219912562167327,
      "grad_norm": 1.3828125,
      "learning_rate": 3.918827461595045e-05,
      "loss": 1.1450191497802735,
      "num_input_tokens_seen": 1784618432,
      "step": 6280,
      "train_runtime": 61144.8827,
      "train_tokens_per_second": 29186.718
    },
    {
      "epoch": 0.22255294588540203,
      "grad_norm": 1.4453125,
      "learning_rate": 3.9176243708284746e-05,
      "loss": 1.1388998985290528,
      "num_input_tokens_seen": 1787409536,
      "step": 6290,
      "train_runtime": 61238.0544,
      "train_tokens_per_second": 29187.889
    },
    {
      "epoch": 0.22290676614913082,
      "grad_norm": 1.375,
      "learning_rate": 3.9164223874384715e-05,
      "loss": 1.1438385009765626,
      "num_input_tokens_seen": 1790285248,
      "step": 6300,
      "train_runtime": 61337.5985,
      "train_tokens_per_second": 29187.404
    },
    {
      "epoch": 0.2232605864128596,
      "grad_norm": 1.421875,
      "learning_rate": 3.91522150972728e-05,
      "loss": 1.154564094543457,
      "num_input_tokens_seen": 1793080832,
      "step": 6310,
      "train_runtime": 61431.9211,
      "train_tokens_per_second": 29188.096
    },
    {
      "epoch": 0.22361440667658838,
      "grad_norm": 1.3515625,
      "learning_rate": 3.9140217360007896e-05,
      "loss": 1.143277359008789,
      "num_input_tokens_seen": 1795923200,
      "step": 6320,
      "train_runtime": 61531.1083,
      "train_tokens_per_second": 29187.24
    },
    {
      "epoch": 0.22396822694031715,
      "grad_norm": 1.40625,
      "learning_rate": 3.912823064568521e-05,
      "loss": 1.1513311386108398,
      "num_input_tokens_seen": 1798770432,
      "step": 6330,
      "train_runtime": 61627.5978,
      "train_tokens_per_second": 29187.742
    },
    {
      "epoch": 0.22432204720404594,
      "grad_norm": 1.4453125,
      "learning_rate": 3.9116254937436155e-05,
      "loss": 1.1597996711730958,
      "num_input_tokens_seen": 1801678912,
      "step": 6340,
      "train_runtime": 61730.9808,
      "train_tokens_per_second": 29185.976
    },
    {
      "epoch": 0.2246758674677747,
      "grad_norm": 1.4296875,
      "learning_rate": 3.910429021842825e-05,
      "loss": 1.1374059677124024,
      "num_input_tokens_seen": 1804571712,
      "step": 6350,
      "train_runtime": 61833.0496,
      "train_tokens_per_second": 29184.582
    },
    {
      "epoch": 0.2250296877315035,
      "grad_norm": 1.359375,
      "learning_rate": 3.9092336471865084e-05,
      "loss": 1.1346322059631349,
      "num_input_tokens_seen": 1807458880,
      "step": 6360,
      "train_runtime": 61932.2407,
      "train_tokens_per_second": 29184.458
    },
    {
      "epoch": 0.22538350799523227,
      "grad_norm": 1.40625,
      "learning_rate": 3.908039368098611e-05,
      "loss": 1.1326444625854493,
      "num_input_tokens_seen": 1810334720,
      "step": 6370,
      "train_runtime": 62032.6656,
      "train_tokens_per_second": 29183.571
    },
    {
      "epoch": 0.22573732825896106,
      "grad_norm": 1.4296875,
      "learning_rate": 3.9068461829066633e-05,
      "loss": 1.1365474700927733,
      "num_input_tokens_seen": 1813165248,
      "step": 6380,
      "train_runtime": 62131.792,
      "train_tokens_per_second": 29182.568
    },
    {
      "epoch": 0.22609114852268983,
      "grad_norm": 1.3984375,
      "learning_rate": 3.9056540899417656e-05,
      "loss": 1.12777099609375,
      "num_input_tokens_seen": 1816047488,
      "step": 6390,
      "train_runtime": 62230.2839,
      "train_tokens_per_second": 29182.696
    },
    {
      "epoch": 0.22644496878641862,
      "grad_norm": 1.4921875,
      "learning_rate": 3.904463087538585e-05,
      "loss": 1.1430343627929687,
      "num_input_tokens_seen": 1818968000,
      "step": 6400,
      "train_runtime": 62332.1216,
      "train_tokens_per_second": 29181.872
    },
    {
      "epoch": 0.2267987890501474,
      "grad_norm": 1.3515625,
      "learning_rate": 3.903273174035336e-05,
      "loss": 1.1484623908996583,
      "num_input_tokens_seen": 1821808384,
      "step": 6410,
      "train_runtime": 62427.7789,
      "train_tokens_per_second": 29182.656
    },
    {
      "epoch": 0.22715260931387618,
      "grad_norm": 1.3359375,
      "learning_rate": 3.902084347773779e-05,
      "loss": 1.1474923133850097,
      "num_input_tokens_seen": 1824615104,
      "step": 6420,
      "train_runtime": 62518.6878,
      "train_tokens_per_second": 29185.115
    },
    {
      "epoch": 0.22750642957760495,
      "grad_norm": 1.4375,
      "learning_rate": 3.900896607099207e-05,
      "loss": 1.143539047241211,
      "num_input_tokens_seen": 1827493440,
      "step": 6430,
      "train_runtime": 62616.2699,
      "train_tokens_per_second": 29185.601
    },
    {
      "epoch": 0.2278602498413337,
      "grad_norm": 1.515625,
      "learning_rate": 3.899709950360437e-05,
      "loss": 1.1556416511535645,
      "num_input_tokens_seen": 1830364224,
      "step": 6440,
      "train_runtime": 62720.3892,
      "train_tokens_per_second": 29182.922
    },
    {
      "epoch": 0.2282140701050625,
      "grad_norm": 1.375,
      "learning_rate": 3.8985243759097997e-05,
      "loss": 1.1459407806396484,
      "num_input_tokens_seen": 1833173248,
      "step": 6450,
      "train_runtime": 62818.2893,
      "train_tokens_per_second": 29182.158
    },
    {
      "epoch": 0.22856789036879127,
      "grad_norm": 1.34375,
      "learning_rate": 3.897339882103129e-05,
      "loss": 1.1415900230407714,
      "num_input_tokens_seen": 1836004224,
      "step": 6460,
      "train_runtime": 62914.7275,
      "train_tokens_per_second": 29182.424
    },
    {
      "epoch": 0.22892171063252006,
      "grad_norm": 1.3671875,
      "learning_rate": 3.8961564672997544e-05,
      "loss": 1.1457250595092774,
      "num_input_tokens_seen": 1838892288,
      "step": 6470,
      "train_runtime": 63014.2845,
      "train_tokens_per_second": 29182.15
    },
    {
      "epoch": 0.22927553089624883,
      "grad_norm": 1.4453125,
      "learning_rate": 3.8949741298624924e-05,
      "loss": 1.138191318511963,
      "num_input_tokens_seen": 1841783296,
      "step": 6480,
      "train_runtime": 63114.5779,
      "train_tokens_per_second": 29181.583
    },
    {
      "epoch": 0.22962935115997762,
      "grad_norm": 1.4375,
      "learning_rate": 3.8937928681576305e-05,
      "loss": 1.1177082061767578,
      "num_input_tokens_seen": 1844600320,
      "step": 6490,
      "train_runtime": 63212.3698,
      "train_tokens_per_second": 29181.002
    },
    {
      "epoch": 0.2299831714237064,
      "grad_norm": 1.4375,
      "learning_rate": 3.8926126805549276e-05,
      "loss": 1.136014747619629,
      "num_input_tokens_seen": 1847412800,
      "step": 6500,
      "train_runtime": 63309.1661,
      "train_tokens_per_second": 29180.811
    },
    {
      "epoch": 0.23033699168743518,
      "grad_norm": 1.40625,
      "learning_rate": 3.891433565427596e-05,
      "loss": 1.140073013305664,
      "num_input_tokens_seen": 1850266368,
      "step": 6510,
      "train_runtime": 63405.5182,
      "train_tokens_per_second": 29181.472
    },
    {
      "epoch": 0.23069081195116395,
      "grad_norm": 1.4453125,
      "learning_rate": 3.8902555211522964e-05,
      "loss": 1.1314300537109374,
      "num_input_tokens_seen": 1853080064,
      "step": 6520,
      "train_runtime": 63502.8761,
      "train_tokens_per_second": 29181.042
    },
    {
      "epoch": 0.23104463221489274,
      "grad_norm": 1.453125,
      "learning_rate": 3.889078546109127e-05,
      "loss": 1.1261022567749024,
      "num_input_tokens_seen": 1855954496,
      "step": 6530,
      "train_runtime": 63601.115,
      "train_tokens_per_second": 29181.163
    },
    {
      "epoch": 0.2313984524786215,
      "grad_norm": 1.40625,
      "learning_rate": 3.887902638681616e-05,
      "loss": 1.1435681343078614,
      "num_input_tokens_seen": 1858839360,
      "step": 6540,
      "train_runtime": 63703.9171,
      "train_tokens_per_second": 29179.357
    },
    {
      "epoch": 0.2317522727423503,
      "grad_norm": 1.359375,
      "learning_rate": 3.886727797256707e-05,
      "loss": 1.1449981689453126,
      "num_input_tokens_seen": 1861636608,
      "step": 6550,
      "train_runtime": 63797.3175,
      "train_tokens_per_second": 29180.484
    },
    {
      "epoch": 0.23210609300607907,
      "grad_norm": 1.453125,
      "learning_rate": 3.88555402022476e-05,
      "loss": 1.1497786521911622,
      "num_input_tokens_seen": 1864463936,
      "step": 6560,
      "train_runtime": 63893.4284,
      "train_tokens_per_second": 29180.84
    },
    {
      "epoch": 0.23245991326980786,
      "grad_norm": 1.4296875,
      "learning_rate": 3.884381305979528e-05,
      "loss": 1.1577054023742677,
      "num_input_tokens_seen": 1867305792,
      "step": 6570,
      "train_runtime": 63988.8544,
      "train_tokens_per_second": 29181.735
    },
    {
      "epoch": 0.23281373353353663,
      "grad_norm": 1.34375,
      "learning_rate": 3.883209652918163e-05,
      "loss": 1.152506160736084,
      "num_input_tokens_seen": 1870197312,
      "step": 6580,
      "train_runtime": 64090.5322,
      "train_tokens_per_second": 29180.555
    },
    {
      "epoch": 0.23316755379726542,
      "grad_norm": 1.359375,
      "learning_rate": 3.8820390594411935e-05,
      "loss": 1.135176181793213,
      "num_input_tokens_seen": 1873037888,
      "step": 6590,
      "train_runtime": 64186.4843,
      "train_tokens_per_second": 29181.188
    },
    {
      "epoch": 0.23352137406099419,
      "grad_norm": 1.5234375,
      "learning_rate": 3.880869523952524e-05,
      "loss": 1.146751308441162,
      "num_input_tokens_seen": 1875862336,
      "step": 6600,
      "train_runtime": 64282.3637,
      "train_tokens_per_second": 29181.602
    },
    {
      "epoch": 0.23387519432472298,
      "grad_norm": 1.4140625,
      "learning_rate": 3.879701044859422e-05,
      "loss": 1.1365710258483888,
      "num_input_tokens_seen": 1878708736,
      "step": 6610,
      "train_runtime": 64381.5086,
      "train_tokens_per_second": 29180.875
    },
    {
      "epoch": 0.23422901458845174,
      "grad_norm": 1.4453125,
      "learning_rate": 3.87853362057251e-05,
      "loss": 1.1493534088134765,
      "num_input_tokens_seen": 1881544192,
      "step": 6620,
      "train_runtime": 64478.8465,
      "train_tokens_per_second": 29180.798
    },
    {
      "epoch": 0.23458283485218054,
      "grad_norm": 1.3984375,
      "learning_rate": 3.8773672495057576e-05,
      "loss": 1.1299819946289062,
      "num_input_tokens_seen": 1884380800,
      "step": 6630,
      "train_runtime": 64576.4644,
      "train_tokens_per_second": 29180.613
    },
    {
      "epoch": 0.2349366551159093,
      "grad_norm": 1.4453125,
      "learning_rate": 3.8762019300764674e-05,
      "loss": 1.1530756950378418,
      "num_input_tokens_seen": 1887308288,
      "step": 6640,
      "train_runtime": 64678.532,
      "train_tokens_per_second": 29179.826
    },
    {
      "epoch": 0.2352904753796381,
      "grad_norm": 1.4296875,
      "learning_rate": 3.875037660705273e-05,
      "loss": 1.141530418395996,
      "num_input_tokens_seen": 1890241536,
      "step": 6650,
      "train_runtime": 64782.7117,
      "train_tokens_per_second": 29178.179
    },
    {
      "epoch": 0.23564429564336686,
      "grad_norm": 1.3828125,
      "learning_rate": 3.873874439816127e-05,
      "loss": 1.1291374206542968,
      "num_input_tokens_seen": 1893055168,
      "step": 6660,
      "train_runtime": 64877.9561,
      "train_tokens_per_second": 29178.712
    },
    {
      "epoch": 0.23599811590709566,
      "grad_norm": 1.421875,
      "learning_rate": 3.872712265836289e-05,
      "loss": 1.1466433525085449,
      "num_input_tokens_seen": 1895939264,
      "step": 6670,
      "train_runtime": 64979.0119,
      "train_tokens_per_second": 29177.718
    },
    {
      "epoch": 0.23635193617082442,
      "grad_norm": 1.421875,
      "learning_rate": 3.8715511371963225e-05,
      "loss": 1.135545253753662,
      "num_input_tokens_seen": 1898837952,
      "step": 6680,
      "train_runtime": 65079.8874,
      "train_tokens_per_second": 29177.032
    },
    {
      "epoch": 0.23670575643455322,
      "grad_norm": 1.3828125,
      "learning_rate": 3.87039105233008e-05,
      "loss": 1.142326545715332,
      "num_input_tokens_seen": 1901653440,
      "step": 6690,
      "train_runtime": 65174.2205,
      "train_tokens_per_second": 29178.001
    },
    {
      "epoch": 0.23705957669828198,
      "grad_norm": 1.3671875,
      "learning_rate": 3.8692320096746975e-05,
      "loss": 1.1339874267578125,
      "num_input_tokens_seen": 1904521472,
      "step": 6700,
      "train_runtime": 65273.7606,
      "train_tokens_per_second": 29177.444
    },
    {
      "epoch": 0.23741339696201075,
      "grad_norm": 1.390625,
      "learning_rate": 3.868074007670589e-05,
      "loss": 1.1387247085571288,
      "num_input_tokens_seen": 1907357632,
      "step": 6710,
      "train_runtime": 65367.9752,
      "train_tokens_per_second": 29178.778
    },
    {
      "epoch": 0.23776721722573954,
      "grad_norm": 1.4375,
      "learning_rate": 3.866917044761428e-05,
      "loss": 1.1407943725585938,
      "num_input_tokens_seen": 1910141312,
      "step": 6720,
      "train_runtime": 65462.4518,
      "train_tokens_per_second": 29179.19
    },
    {
      "epoch": 0.2381210374894683,
      "grad_norm": 1.4375,
      "learning_rate": 3.8657611193941486e-05,
      "loss": 1.1545680999755858,
      "num_input_tokens_seen": 1912992640,
      "step": 6730,
      "train_runtime": 65559.5331,
      "train_tokens_per_second": 29179.473
    },
    {
      "epoch": 0.2384748577531971,
      "grad_norm": 1.4140625,
      "learning_rate": 3.8646062300189315e-05,
      "loss": 1.1428878784179688,
      "num_input_tokens_seen": 1915814976,
      "step": 6740,
      "train_runtime": 65655.9673,
      "train_tokens_per_second": 29179.602
    },
    {
      "epoch": 0.23882867801692587,
      "grad_norm": 1.4765625,
      "learning_rate": 3.8634523750891984e-05,
      "loss": 1.134803009033203,
      "num_input_tokens_seen": 1918640832,
      "step": 6750,
      "train_runtime": 65751.9303,
      "train_tokens_per_second": 29179.992
    },
    {
      "epoch": 0.23918249828065466,
      "grad_norm": 1.421875,
      "learning_rate": 3.862299553061597e-05,
      "loss": 1.1285060882568358,
      "num_input_tokens_seen": 1921455040,
      "step": 6760,
      "train_runtime": 65848.0918,
      "train_tokens_per_second": 29180.117
    },
    {
      "epoch": 0.23953631854438343,
      "grad_norm": 1.359375,
      "learning_rate": 3.861147762396e-05,
      "loss": 1.1300186157226562,
      "num_input_tokens_seen": 1924308160,
      "step": 6770,
      "train_runtime": 65945.4527,
      "train_tokens_per_second": 29180.301
    },
    {
      "epoch": 0.23989013880811222,
      "grad_norm": 1.375,
      "learning_rate": 3.859997001555494e-05,
      "loss": 1.1520641326904297,
      "num_input_tokens_seen": 1927171840,
      "step": 6780,
      "train_runtime": 66045.4698,
      "train_tokens_per_second": 29179.471
    },
    {
      "epoch": 0.24024395907184098,
      "grad_norm": 1.4140625,
      "learning_rate": 3.8588472690063676e-05,
      "loss": 1.129981231689453,
      "num_input_tokens_seen": 1930048320,
      "step": 6790,
      "train_runtime": 66143.4647,
      "train_tokens_per_second": 29179.728
    },
    {
      "epoch": 0.24059777933556978,
      "grad_norm": 1.421875,
      "learning_rate": 3.857698563218106e-05,
      "loss": 1.133086585998535,
      "num_input_tokens_seen": 1932894976,
      "step": 6800,
      "train_runtime": 66240.003,
      "train_tokens_per_second": 29180.176
    },
    {
      "epoch": 0.24095159959929854,
      "grad_norm": 1.4140625,
      "learning_rate": 3.8565508826633836e-05,
      "loss": 1.149017906188965,
      "num_input_tokens_seen": 1935687936,
      "step": 6810,
      "train_runtime": 66335.2542,
      "train_tokens_per_second": 29180.38
    },
    {
      "epoch": 0.24130541986302734,
      "grad_norm": 1.4375,
      "learning_rate": 3.855404225818049e-05,
      "loss": 1.1403033256530761,
      "num_input_tokens_seen": 1938496576,
      "step": 6820,
      "train_runtime": 66427.9314,
      "train_tokens_per_second": 29181.95
    },
    {
      "epoch": 0.2416592401267561,
      "grad_norm": 1.484375,
      "learning_rate": 3.8542585911611286e-05,
      "loss": 1.1356518745422364,
      "num_input_tokens_seen": 1941282368,
      "step": 6830,
      "train_runtime": 66524.8751,
      "train_tokens_per_second": 29181.3
    },
    {
      "epoch": 0.2420130603904849,
      "grad_norm": 1.3671875,
      "learning_rate": 3.853113977174803e-05,
      "loss": 1.1438831329345702,
      "num_input_tokens_seen": 1944067968,
      "step": 6840,
      "train_runtime": 66618.031,
      "train_tokens_per_second": 29182.309
    },
    {
      "epoch": 0.24236688065421366,
      "grad_norm": 1.3671875,
      "learning_rate": 3.851970382344411e-05,
      "loss": 1.1441171646118165,
      "num_input_tokens_seen": 1946858304,
      "step": 6850,
      "train_runtime": 66712.4292,
      "train_tokens_per_second": 29182.842
    },
    {
      "epoch": 0.24272070091794246,
      "grad_norm": 1.375,
      "learning_rate": 3.850827805158433e-05,
      "loss": 1.136497402191162,
      "num_input_tokens_seen": 1949729472,
      "step": 6860,
      "train_runtime": 66811.8681,
      "train_tokens_per_second": 29182.382
    },
    {
      "epoch": 0.24307452118167122,
      "grad_norm": 1.4140625,
      "learning_rate": 3.8496862441084896e-05,
      "loss": 1.1479606628417969,
      "num_input_tokens_seen": 1952568000,
      "step": 6870,
      "train_runtime": 66910.8616,
      "train_tokens_per_second": 29181.63
    },
    {
      "epoch": 0.24342834144540001,
      "grad_norm": 1.40625,
      "learning_rate": 3.848545697689328e-05,
      "loss": 1.1422126770019532,
      "num_input_tokens_seen": 1955436224,
      "step": 6880,
      "train_runtime": 67010.6494,
      "train_tokens_per_second": 29180.977
    },
    {
      "epoch": 0.24378216170912878,
      "grad_norm": 1.5,
      "learning_rate": 3.8474061643988136e-05,
      "loss": 1.1392714500427246,
      "num_input_tokens_seen": 1958284672,
      "step": 6890,
      "train_runtime": 67107.2396,
      "train_tokens_per_second": 29181.422
    },
    {
      "epoch": 0.24413598197285757,
      "grad_norm": 1.4375,
      "learning_rate": 3.846267642737925e-05,
      "loss": 1.1346969604492188,
      "num_input_tokens_seen": 1961151936,
      "step": 6900,
      "train_runtime": 67206.3038,
      "train_tokens_per_second": 29181.071
    },
    {
      "epoch": 0.24448980223658634,
      "grad_norm": 1.3671875,
      "learning_rate": 3.8451301312107455e-05,
      "loss": 1.1457378387451171,
      "num_input_tokens_seen": 1963977536,
      "step": 6910,
      "train_runtime": 67299.259,
      "train_tokens_per_second": 29182.751
    },
    {
      "epoch": 0.24484362250031513,
      "grad_norm": 1.4296875,
      "learning_rate": 3.843993628324451e-05,
      "loss": 1.1376886367797852,
      "num_input_tokens_seen": 1966882304,
      "step": 6920,
      "train_runtime": 67400.1047,
      "train_tokens_per_second": 29182.185
    },
    {
      "epoch": 0.2451974427640439,
      "grad_norm": 1.40625,
      "learning_rate": 3.8428581325893034e-05,
      "loss": 1.1302379608154296,
      "num_input_tokens_seen": 1969747328,
      "step": 6930,
      "train_runtime": 67499.8873,
      "train_tokens_per_second": 29181.491
    },
    {
      "epoch": 0.2455512630277727,
      "grad_norm": 1.4453125,
      "learning_rate": 3.8417236425186484e-05,
      "loss": 1.1344221115112305,
      "num_input_tokens_seen": 1972638400,
      "step": 6940,
      "train_runtime": 67599.4762,
      "train_tokens_per_second": 29181.268
    },
    {
      "epoch": 0.24590508329150146,
      "grad_norm": 1.375,
      "learning_rate": 3.840590156628895e-05,
      "loss": 1.1475934028625487,
      "num_input_tokens_seen": 1975386240,
      "step": 6950,
      "train_runtime": 67691.2636,
      "train_tokens_per_second": 29182.292
    },
    {
      "epoch": 0.24625890355523022,
      "grad_norm": 1.4296875,
      "learning_rate": 3.8394576734395205e-05,
      "loss": 1.1424145698547363,
      "num_input_tokens_seen": 1978244864,
      "step": 6960,
      "train_runtime": 67788.0498,
      "train_tokens_per_second": 29182.797
    },
    {
      "epoch": 0.24661272381895902,
      "grad_norm": 1.3515625,
      "learning_rate": 3.838326191473054e-05,
      "loss": 1.139106845855713,
      "num_input_tokens_seen": 1981100288,
      "step": 6970,
      "train_runtime": 67884.3,
      "train_tokens_per_second": 29183.483
    },
    {
      "epoch": 0.24696654408268778,
      "grad_norm": 1.3515625,
      "learning_rate": 3.837195709255069e-05,
      "loss": 1.1418012619018554,
      "num_input_tokens_seen": 1983949504,
      "step": 6980,
      "train_runtime": 67981.7282,
      "train_tokens_per_second": 29183.57
    },
    {
      "epoch": 0.24732036434641658,
      "grad_norm": 1.4140625,
      "learning_rate": 3.8360662253141796e-05,
      "loss": 1.1349398612976074,
      "num_input_tokens_seen": 1986802688,
      "step": 6990,
      "train_runtime": 68080.1139,
      "train_tokens_per_second": 29183.304
    },
    {
      "epoch": 0.24767418461014534,
      "grad_norm": 1.3828125,
      "learning_rate": 3.834937738182029e-05,
      "loss": 1.146417236328125,
      "num_input_tokens_seen": 1989645568,
      "step": 7000,
      "train_runtime": 68178.2889,
      "train_tokens_per_second": 29182.979
    },
    {
      "epoch": 0.24802800487387414,
      "grad_norm": 1.390625,
      "learning_rate": 3.833810246393281e-05,
      "loss": 1.1256877899169921,
      "num_input_tokens_seen": 1992492736,
      "step": 7010,
      "train_runtime": 68275.4144,
      "train_tokens_per_second": 29183.166
    },
    {
      "epoch": 0.2483818251376029,
      "grad_norm": 1.3828125,
      "learning_rate": 3.832683748485616e-05,
      "loss": 1.1218952178955077,
      "num_input_tokens_seen": 1995362560,
      "step": 7020,
      "train_runtime": 68376.5348,
      "train_tokens_per_second": 29181.978
    },
    {
      "epoch": 0.2487356454013317,
      "grad_norm": 1.3359375,
      "learning_rate": 3.8315582429997184e-05,
      "loss": 1.1263322830200195,
      "num_input_tokens_seen": 1998209664,
      "step": 7030,
      "train_runtime": 68473.9816,
      "train_tokens_per_second": 29182.028
    },
    {
      "epoch": 0.24908946566506046,
      "grad_norm": 1.3203125,
      "learning_rate": 3.830433728479272e-05,
      "loss": 1.1397740364074707,
      "num_input_tokens_seen": 2001065600,
      "step": 7040,
      "train_runtime": 68572.8357,
      "train_tokens_per_second": 29181.608
    },
    {
      "epoch": 0.24944328592878925,
      "grad_norm": 1.375,
      "learning_rate": 3.829310203470948e-05,
      "loss": 1.1502744674682617,
      "num_input_tokens_seen": 2003880192,
      "step": 7050,
      "train_runtime": 68669.2815,
      "train_tokens_per_second": 29181.61
    },
    {
      "epoch": 0.24979710619251802,
      "grad_norm": 1.4140625,
      "learning_rate": 3.828187666524403e-05,
      "loss": 1.131840419769287,
      "num_input_tokens_seen": 2006683904,
      "step": 7060,
      "train_runtime": 68762.6417,
      "train_tokens_per_second": 29182.763
    },
    {
      "epoch": 0.2501509264562468,
      "grad_norm": 1.46875,
      "learning_rate": 3.827066116192266e-05,
      "loss": 1.1296314239501952,
      "num_input_tokens_seen": 2009511232,
      "step": 7070,
      "train_runtime": 68859.0959,
      "train_tokens_per_second": 29182.945
    },
    {
      "epoch": 0.2505047467199756,
      "grad_norm": 1.4453125,
      "learning_rate": 3.825945551030135e-05,
      "loss": 1.134183120727539,
      "num_input_tokens_seen": 2012319744,
      "step": 7080,
      "train_runtime": 68954.6519,
      "train_tokens_per_second": 29183.234
    },
    {
      "epoch": 0.25085856698370435,
      "grad_norm": 1.4296875,
      "learning_rate": 3.824825969596561e-05,
      "loss": 1.114000415802002,
      "num_input_tokens_seen": 2015164544,
      "step": 7090,
      "train_runtime": 69052.0159,
      "train_tokens_per_second": 29183.283
    },
    {
      "epoch": 0.25121238724743317,
      "grad_norm": 1.3671875,
      "learning_rate": 3.823707370453054e-05,
      "loss": 1.157622718811035,
      "num_input_tokens_seen": 2018028928,
      "step": 7100,
      "train_runtime": 69151.1325,
      "train_tokens_per_second": 29182.876
    },
    {
      "epoch": 0.25156620751116193,
      "grad_norm": 1.3671875,
      "learning_rate": 3.8225897521640614e-05,
      "loss": 1.1390769004821777,
      "num_input_tokens_seen": 2020869120,
      "step": 7110,
      "train_runtime": 69246.1316,
      "train_tokens_per_second": 29183.856
    },
    {
      "epoch": 0.2519200277748907,
      "grad_norm": 1.40625,
      "learning_rate": 3.8214731132969675e-05,
      "loss": 1.1347352981567382,
      "num_input_tokens_seen": 2023728320,
      "step": 7120,
      "train_runtime": 69346.0722,
      "train_tokens_per_second": 29183.027
    },
    {
      "epoch": 0.25227384803861946,
      "grad_norm": 1.3515625,
      "learning_rate": 3.820357452422084e-05,
      "loss": 1.1225122451782226,
      "num_input_tokens_seen": 2026488448,
      "step": 7130,
      "train_runtime": 69439.3913,
      "train_tokens_per_second": 29183.557
    },
    {
      "epoch": 0.2526276683023483,
      "grad_norm": 1.40625,
      "learning_rate": 3.8192427681126445e-05,
      "loss": 1.1339890480041503,
      "num_input_tokens_seen": 2029323392,
      "step": 7140,
      "train_runtime": 69536.8319,
      "train_tokens_per_second": 29183.432
    },
    {
      "epoch": 0.25298148856607705,
      "grad_norm": 1.3984375,
      "learning_rate": 3.818129058944793e-05,
      "loss": 1.1264930725097657,
      "num_input_tokens_seen": 2032191488,
      "step": 7150,
      "train_runtime": 69635.3811,
      "train_tokens_per_second": 29183.318
    },
    {
      "epoch": 0.2533353088298058,
      "grad_norm": 1.4375,
      "learning_rate": 3.817016323497578e-05,
      "loss": 1.1312952041625977,
      "num_input_tokens_seen": 2035036480,
      "step": 7160,
      "train_runtime": 69732.5297,
      "train_tokens_per_second": 29183.46
    },
    {
      "epoch": 0.2536891290935346,
      "grad_norm": 1.4140625,
      "learning_rate": 3.8159045603529455e-05,
      "loss": 1.136730670928955,
      "num_input_tokens_seen": 2037872896,
      "step": 7170,
      "train_runtime": 69827.7406,
      "train_tokens_per_second": 29184.288
    },
    {
      "epoch": 0.2540429493572634,
      "grad_norm": 1.40625,
      "learning_rate": 3.8147937680957334e-05,
      "loss": 1.1294061660766601,
      "num_input_tokens_seen": 2040756736,
      "step": 7180,
      "train_runtime": 69929.5416,
      "train_tokens_per_second": 29183.042
    },
    {
      "epoch": 0.25439676962099217,
      "grad_norm": 1.484375,
      "learning_rate": 3.813683945313658e-05,
      "loss": 1.1473760604858398,
      "num_input_tokens_seen": 2043658624,
      "step": 7190,
      "train_runtime": 70032.2175,
      "train_tokens_per_second": 29181.692
    },
    {
      "epoch": 0.25475058988472093,
      "grad_norm": 1.4296875,
      "learning_rate": 3.812575090597313e-05,
      "loss": 1.1357305526733399,
      "num_input_tokens_seen": 2046480768,
      "step": 7200,
      "train_runtime": 70126.3916,
      "train_tokens_per_second": 29182.747
    },
    {
      "epoch": 0.2551044101484497,
      "grad_norm": 1.3984375,
      "learning_rate": 3.811467202540156e-05,
      "loss": 1.1149269104003907,
      "num_input_tokens_seen": 2049320192,
      "step": 7210,
      "train_runtime": 70224.2848,
      "train_tokens_per_second": 29182.5
    },
    {
      "epoch": 0.25545823041217847,
      "grad_norm": 1.390625,
      "learning_rate": 3.810360279738507e-05,
      "loss": 1.1372767448425294,
      "num_input_tokens_seen": 2052214592,
      "step": 7220,
      "train_runtime": 70325.8296,
      "train_tokens_per_second": 29181.52
    },
    {
      "epoch": 0.2558120506759073,
      "grad_norm": 1.40625,
      "learning_rate": 3.809254320791535e-05,
      "loss": 1.1226654052734375,
      "num_input_tokens_seen": 2055053696,
      "step": 7230,
      "train_runtime": 70424.4302,
      "train_tokens_per_second": 29180.977
    },
    {
      "epoch": 0.25616587093963605,
      "grad_norm": 1.4140625,
      "learning_rate": 3.808149324301256e-05,
      "loss": 1.1400375366210938,
      "num_input_tokens_seen": 2057861696,
      "step": 7240,
      "train_runtime": 70519.6069,
      "train_tokens_per_second": 29181.412
    },
    {
      "epoch": 0.2565196912033648,
      "grad_norm": 1.40625,
      "learning_rate": 3.807045288872522e-05,
      "loss": 1.1438339233398438,
      "num_input_tokens_seen": 2060795840,
      "step": 7250,
      "train_runtime": 70623.2554,
      "train_tokens_per_second": 29180.131
    },
    {
      "epoch": 0.2568735114670936,
      "grad_norm": 1.46875,
      "learning_rate": 3.805942213113015e-05,
      "loss": 1.1415992736816407,
      "num_input_tokens_seen": 2063608512,
      "step": 7260,
      "train_runtime": 70720.183,
      "train_tokens_per_second": 29179.909
    },
    {
      "epoch": 0.2572273317308224,
      "grad_norm": 1.3984375,
      "learning_rate": 3.8048400956332385e-05,
      "loss": 1.1233534812927246,
      "num_input_tokens_seen": 2066395712,
      "step": 7270,
      "train_runtime": 70813.9829,
      "train_tokens_per_second": 29180.617
    },
    {
      "epoch": 0.25758115199455117,
      "grad_norm": 1.40625,
      "learning_rate": 3.803738935046512e-05,
      "loss": 1.1389616012573243,
      "num_input_tokens_seen": 2069224768,
      "step": 7280,
      "train_runtime": 70905.7564,
      "train_tokens_per_second": 29182.747
    },
    {
      "epoch": 0.25793497225827994,
      "grad_norm": 1.421875,
      "learning_rate": 3.802638729968962e-05,
      "loss": 1.1460859298706054,
      "num_input_tokens_seen": 2072058432,
      "step": 7290,
      "train_runtime": 71001.4414,
      "train_tokens_per_second": 29183.329
    },
    {
      "epoch": 0.2582887925220087,
      "grad_norm": 1.421875,
      "learning_rate": 3.8015394790195145e-05,
      "loss": 1.1346612930297852,
      "num_input_tokens_seen": 2074911296,
      "step": 7300,
      "train_runtime": 71098.063,
      "train_tokens_per_second": 29183.795
    },
    {
      "epoch": 0.2586426127857375,
      "grad_norm": 1.390625,
      "learning_rate": 3.800441180819891e-05,
      "loss": 1.1296041488647461,
      "num_input_tokens_seen": 2077735040,
      "step": 7310,
      "train_runtime": 71191.266,
      "train_tokens_per_second": 29185.252
    },
    {
      "epoch": 0.2589964330494663,
      "grad_norm": 1.4375,
      "learning_rate": 3.7993438339945965e-05,
      "loss": 1.1356515884399414,
      "num_input_tokens_seen": 2080523264,
      "step": 7320,
      "train_runtime": 71286.4314,
      "train_tokens_per_second": 29185.403
    },
    {
      "epoch": 0.25935025331319506,
      "grad_norm": 1.46875,
      "learning_rate": 3.798247437170914e-05,
      "loss": 1.1401887893676759,
      "num_input_tokens_seen": 2083436160,
      "step": 7330,
      "train_runtime": 71385.7768,
      "train_tokens_per_second": 29185.592
    },
    {
      "epoch": 0.2597040735769238,
      "grad_norm": 1.3984375,
      "learning_rate": 3.797151988978901e-05,
      "loss": 1.1248514175415039,
      "num_input_tokens_seen": 2086317440,
      "step": 7340,
      "train_runtime": 71486.5402,
      "train_tokens_per_second": 29184.759
    },
    {
      "epoch": 0.26005789384065264,
      "grad_norm": 1.375,
      "learning_rate": 3.796057488051377e-05,
      "loss": 1.1352010726928712,
      "num_input_tokens_seen": 2089149312,
      "step": 7350,
      "train_runtime": 71583.7026,
      "train_tokens_per_second": 29184.706
    },
    {
      "epoch": 0.2604117141043814,
      "grad_norm": 1.453125,
      "learning_rate": 3.794963933023918e-05,
      "loss": 1.1512141227722168,
      "num_input_tokens_seen": 2092033920,
      "step": 7360,
      "train_runtime": 71683.8741,
      "train_tokens_per_second": 29184.164
    },
    {
      "epoch": 0.2607655343681102,
      "grad_norm": 1.3671875,
      "learning_rate": 3.79387132253485e-05,
      "loss": 1.1262611389160155,
      "num_input_tokens_seen": 2094888320,
      "step": 7370,
      "train_runtime": 71779.5244,
      "train_tokens_per_second": 29185.04
    },
    {
      "epoch": 0.26111935463183894,
      "grad_norm": 1.3984375,
      "learning_rate": 3.792779655225243e-05,
      "loss": 1.129753303527832,
      "num_input_tokens_seen": 2097696448,
      "step": 7380,
      "train_runtime": 71874.8108,
      "train_tokens_per_second": 29185.419
    },
    {
      "epoch": 0.26147317489556776,
      "grad_norm": 1.3671875,
      "learning_rate": 3.791688929738902e-05,
      "loss": 1.1443886756896973,
      "num_input_tokens_seen": 2100542080,
      "step": 7390,
      "train_runtime": 71972.3708,
      "train_tokens_per_second": 29185.395
    },
    {
      "epoch": 0.2618269951592965,
      "grad_norm": 1.453125,
      "learning_rate": 3.79059914472236e-05,
      "loss": 1.1337841033935547,
      "num_input_tokens_seen": 2103424704,
      "step": 7400,
      "train_runtime": 72072.3082,
      "train_tokens_per_second": 29184.922
    },
    {
      "epoch": 0.2621808154230253,
      "grad_norm": 1.4375,
      "learning_rate": 3.7895102988248716e-05,
      "loss": 1.1247122764587403,
      "num_input_tokens_seen": 2106209600,
      "step": 7410,
      "train_runtime": 72163.0665,
      "train_tokens_per_second": 29186.808
    },
    {
      "epoch": 0.26253463568675406,
      "grad_norm": 1.390625,
      "learning_rate": 3.7884223906984064e-05,
      "loss": 1.1288507461547852,
      "num_input_tokens_seen": 2109084864,
      "step": 7420,
      "train_runtime": 72264.5412,
      "train_tokens_per_second": 29185.612
    },
    {
      "epoch": 0.2628884559504829,
      "grad_norm": 1.3828125,
      "learning_rate": 3.787335418997641e-05,
      "loss": 1.1154647827148438,
      "num_input_tokens_seen": 2111953856,
      "step": 7430,
      "train_runtime": 72362.7297,
      "train_tokens_per_second": 29185.658
    },
    {
      "epoch": 0.26324227621421165,
      "grad_norm": 1.421875,
      "learning_rate": 3.786249382379952e-05,
      "loss": 1.1302781105041504,
      "num_input_tokens_seen": 2114753408,
      "step": 7440,
      "train_runtime": 72457.3642,
      "train_tokens_per_second": 29186.176
    },
    {
      "epoch": 0.2635960964779404,
      "grad_norm": 1.390625,
      "learning_rate": 3.785164279505411e-05,
      "loss": 1.1366804122924805,
      "num_input_tokens_seen": 2117616384,
      "step": 7450,
      "train_runtime": 72556.924,
      "train_tokens_per_second": 29185.587
    },
    {
      "epoch": 0.2639499167416692,
      "grad_norm": 1.484375,
      "learning_rate": 3.7840801090367744e-05,
      "loss": 1.137161922454834,
      "num_input_tokens_seen": 2120492864,
      "step": 7460,
      "train_runtime": 72657.0111,
      "train_tokens_per_second": 29184.972
    },
    {
      "epoch": 0.26430373700539794,
      "grad_norm": 1.4375,
      "learning_rate": 3.782996869639479e-05,
      "loss": 1.128640365600586,
      "num_input_tokens_seen": 2123302848,
      "step": 7470,
      "train_runtime": 72752.7919,
      "train_tokens_per_second": 29185.173
    },
    {
      "epoch": 0.26465755726912676,
      "grad_norm": 1.40625,
      "learning_rate": 3.7819145599816354e-05,
      "loss": 1.1331095695495605,
      "num_input_tokens_seen": 2126127488,
      "step": 7480,
      "train_runtime": 72846.8763,
      "train_tokens_per_second": 29186.255
    },
    {
      "epoch": 0.26501137753285553,
      "grad_norm": 1.421875,
      "learning_rate": 3.780833178734018e-05,
      "loss": 1.1541515350341798,
      "num_input_tokens_seen": 2129004864,
      "step": 7490,
      "train_runtime": 72946.5989,
      "train_tokens_per_second": 29185.8
    },
    {
      "epoch": 0.2653651977965843,
      "grad_norm": 1.4296875,
      "learning_rate": 3.77975272457006e-05,
      "loss": 1.1398646354675293,
      "num_input_tokens_seen": 2131798656,
      "step": 7500,
      "train_runtime": 73040.8284,
      "train_tokens_per_second": 29186.398
    },
    {
      "epoch": 0.26571901806031306,
      "grad_norm": 1.421875,
      "learning_rate": 3.778673196165851e-05,
      "loss": 1.1274892807006835,
      "num_input_tokens_seen": 2134637504,
      "step": 7510,
      "train_runtime": 73138.4172,
      "train_tokens_per_second": 29186.269
    },
    {
      "epoch": 0.2660728383240419,
      "grad_norm": 1.453125,
      "learning_rate": 3.7775945922001186e-05,
      "loss": 1.1374027252197265,
      "num_input_tokens_seen": 2137523456,
      "step": 7520,
      "train_runtime": 73238.0,
      "train_tokens_per_second": 29185.989
    },
    {
      "epoch": 0.26642665858777065,
      "grad_norm": 1.5234375,
      "learning_rate": 3.776516911354236e-05,
      "loss": 1.150265884399414,
      "num_input_tokens_seen": 2140406464,
      "step": 7530,
      "train_runtime": 73333.4629,
      "train_tokens_per_second": 29187.309
    },
    {
      "epoch": 0.2667804788514994,
      "grad_norm": 1.546875,
      "learning_rate": 3.775440152312205e-05,
      "loss": 1.1447628021240235,
      "num_input_tokens_seen": 2143232512,
      "step": 7540,
      "train_runtime": 73428.9879,
      "train_tokens_per_second": 29187.826
    },
    {
      "epoch": 0.2671342991152282,
      "grad_norm": 1.40625,
      "learning_rate": 3.774364313760652e-05,
      "loss": 1.1404863357543946,
      "num_input_tokens_seen": 2146056960,
      "step": 7550,
      "train_runtime": 73524.301,
      "train_tokens_per_second": 29188.403
    },
    {
      "epoch": 0.267488119378957,
      "grad_norm": 1.4375,
      "learning_rate": 3.7732893943888224e-05,
      "loss": 1.1331168174743653,
      "num_input_tokens_seen": 2148890048,
      "step": 7560,
      "train_runtime": 73619.8908,
      "train_tokens_per_second": 29188.987
    },
    {
      "epoch": 0.26784193964268577,
      "grad_norm": 1.3984375,
      "learning_rate": 3.772215392888574e-05,
      "loss": 1.1341447830200195,
      "num_input_tokens_seen": 2151736000,
      "step": 7570,
      "train_runtime": 73715.682,
      "train_tokens_per_second": 29189.664
    },
    {
      "epoch": 0.26819575990641453,
      "grad_norm": 1.3828125,
      "learning_rate": 3.771142307954368e-05,
      "loss": 1.122310733795166,
      "num_input_tokens_seen": 2154576640,
      "step": 7580,
      "train_runtime": 73811.3508,
      "train_tokens_per_second": 29190.316
    },
    {
      "epoch": 0.2685495801701433,
      "grad_norm": 1.375,
      "learning_rate": 3.770070138283264e-05,
      "loss": 1.1399478912353516,
      "num_input_tokens_seen": 2157471680,
      "step": 7590,
      "train_runtime": 73909.106,
      "train_tokens_per_second": 29190.878
    },
    {
      "epoch": 0.2689034004338721,
      "grad_norm": 1.3828125,
      "learning_rate": 3.768998882574915e-05,
      "loss": 1.135573387145996,
      "num_input_tokens_seen": 2160348288,
      "step": 7600,
      "train_runtime": 74011.7396,
      "train_tokens_per_second": 29189.265
    },
    {
      "epoch": 0.2692572206976009,
      "grad_norm": 1.359375,
      "learning_rate": 3.767928539531557e-05,
      "loss": 1.137821578979492,
      "num_input_tokens_seen": 2163158784,
      "step": 7610,
      "train_runtime": 74106.9851,
      "train_tokens_per_second": 29189.675
    },
    {
      "epoch": 0.26961104096132965,
      "grad_norm": 1.4140625,
      "learning_rate": 3.7668591078580055e-05,
      "loss": 1.1332132339477539,
      "num_input_tokens_seen": 2166053632,
      "step": 7620,
      "train_runtime": 74210.6799,
      "train_tokens_per_second": 29187.896
    },
    {
      "epoch": 0.2699648612250584,
      "grad_norm": 1.4296875,
      "learning_rate": 3.765790586261647e-05,
      "loss": 1.1222350120544433,
      "num_input_tokens_seen": 2168858112,
      "step": 7630,
      "train_runtime": 74306.6377,
      "train_tokens_per_second": 29187.946
    },
    {
      "epoch": 0.27031868148878724,
      "grad_norm": 1.40625,
      "learning_rate": 3.7647229734524326e-05,
      "loss": 1.1288958549499513,
      "num_input_tokens_seen": 2171655104,
      "step": 7640,
      "train_runtime": 74400.0034,
      "train_tokens_per_second": 29188.911
    },
    {
      "epoch": 0.270672501752516,
      "grad_norm": 1.3359375,
      "learning_rate": 3.7636562681428744e-05,
      "loss": 1.1227753639221192,
      "num_input_tokens_seen": 2174459328,
      "step": 7650,
      "train_runtime": 74493.1176,
      "train_tokens_per_second": 29190.07
    },
    {
      "epoch": 0.27102632201624477,
      "grad_norm": 1.3515625,
      "learning_rate": 3.7625904690480346e-05,
      "loss": 1.1272872924804687,
      "num_input_tokens_seen": 2177253312,
      "step": 7660,
      "train_runtime": 74587.6873,
      "train_tokens_per_second": 29190.519
    },
    {
      "epoch": 0.27138014227997354,
      "grad_norm": 1.359375,
      "learning_rate": 3.7615255748855224e-05,
      "loss": 1.1400781631469727,
      "num_input_tokens_seen": 2180137280,
      "step": 7670,
      "train_runtime": 74686.7472,
      "train_tokens_per_second": 29190.417
    },
    {
      "epoch": 0.27173396254370236,
      "grad_norm": 1.4296875,
      "learning_rate": 3.7604615843754845e-05,
      "loss": 1.128744888305664,
      "num_input_tokens_seen": 2182987840,
      "step": 7680,
      "train_runtime": 74785.0198,
      "train_tokens_per_second": 29190.175
    },
    {
      "epoch": 0.2720877828074311,
      "grad_norm": 1.4296875,
      "learning_rate": 3.759398496240601e-05,
      "loss": 1.1261759757995606,
      "num_input_tokens_seen": 2185845312,
      "step": 7690,
      "train_runtime": 74881.1922,
      "train_tokens_per_second": 29190.845
    },
    {
      "epoch": 0.2724416030711599,
      "grad_norm": 1.3828125,
      "learning_rate": 3.7583363092060815e-05,
      "loss": 1.1218698501586915,
      "num_input_tokens_seen": 2188683776,
      "step": 7700,
      "train_runtime": 74978.9417,
      "train_tokens_per_second": 29190.646
    },
    {
      "epoch": 0.27279542333488865,
      "grad_norm": 1.46875,
      "learning_rate": 3.757275021999649e-05,
      "loss": 1.1364570617675782,
      "num_input_tokens_seen": 2191521152,
      "step": 7710,
      "train_runtime": 75077.8458,
      "train_tokens_per_second": 29189.984
    },
    {
      "epoch": 0.2731492435986175,
      "grad_norm": 1.3984375,
      "learning_rate": 3.7562146333515445e-05,
      "loss": 1.127101230621338,
      "num_input_tokens_seen": 2194422656,
      "step": 7720,
      "train_runtime": 75175.1254,
      "train_tokens_per_second": 29190.808
    },
    {
      "epoch": 0.27350306386234624,
      "grad_norm": 1.3359375,
      "learning_rate": 3.7551551419945167e-05,
      "loss": 1.1238965034484862,
      "num_input_tokens_seen": 2197244288,
      "step": 7730,
      "train_runtime": 75271.2025,
      "train_tokens_per_second": 29191.035
    },
    {
      "epoch": 0.273856884126075,
      "grad_norm": 1.4609375,
      "learning_rate": 3.7540965466638104e-05,
      "loss": 1.129817295074463,
      "num_input_tokens_seen": 2200139968,
      "step": 7740,
      "train_runtime": 75371.095,
      "train_tokens_per_second": 29190.766
    },
    {
      "epoch": 0.27421070438980377,
      "grad_norm": 1.4140625,
      "learning_rate": 3.753038846097172e-05,
      "loss": 1.1170234680175781,
      "num_input_tokens_seen": 2203025792,
      "step": 7750,
      "train_runtime": 75469.9287,
      "train_tokens_per_second": 29190.776
    },
    {
      "epoch": 0.27456452465353254,
      "grad_norm": 1.375,
      "learning_rate": 3.751982039034827e-05,
      "loss": 1.1340647697448731,
      "num_input_tokens_seen": 2205819776,
      "step": 7760,
      "train_runtime": 75564.5006,
      "train_tokens_per_second": 29191.218
    },
    {
      "epoch": 0.27491834491726136,
      "grad_norm": 1.390625,
      "learning_rate": 3.75092612421949e-05,
      "loss": 1.1377099990844726,
      "num_input_tokens_seen": 2208704192,
      "step": 7770,
      "train_runtime": 75663.8369,
      "train_tokens_per_second": 29191.015
    },
    {
      "epoch": 0.2752721651809901,
      "grad_norm": 1.484375,
      "learning_rate": 3.7498711003963475e-05,
      "loss": 1.142449188232422,
      "num_input_tokens_seen": 2211600192,
      "step": 7780,
      "train_runtime": 75765.5144,
      "train_tokens_per_second": 29190.064
    },
    {
      "epoch": 0.2756259854447189,
      "grad_norm": 1.4296875,
      "learning_rate": 3.748816966313058e-05,
      "loss": 1.1300529479980468,
      "num_input_tokens_seen": 2214473088,
      "step": 7790,
      "train_runtime": 75865.4483,
      "train_tokens_per_second": 29189.481
    },
    {
      "epoch": 0.27597980570844766,
      "grad_norm": 1.3984375,
      "learning_rate": 3.7477637207197374e-05,
      "loss": 1.1275361061096192,
      "num_input_tokens_seen": 2217345664,
      "step": 7800,
      "train_runtime": 75967.8682,
      "train_tokens_per_second": 29187.941
    },
    {
      "epoch": 0.2763336259721765,
      "grad_norm": 1.40625,
      "learning_rate": 3.7467113623689666e-05,
      "loss": 1.1317346572875977,
      "num_input_tokens_seen": 2220153792,
      "step": 7810,
      "train_runtime": 76062.9826,
      "train_tokens_per_second": 29188.361
    },
    {
      "epoch": 0.27668744623590524,
      "grad_norm": 1.3671875,
      "learning_rate": 3.745659890015768e-05,
      "loss": 1.1346624374389649,
      "num_input_tokens_seen": 2222968896,
      "step": 7820,
      "train_runtime": 76159.5033,
      "train_tokens_per_second": 29188.332
    },
    {
      "epoch": 0.277041266499634,
      "grad_norm": 1.4140625,
      "learning_rate": 3.744609302417615e-05,
      "loss": 1.1355717658996582,
      "num_input_tokens_seen": 2225786688,
      "step": 7830,
      "train_runtime": 76257.4497,
      "train_tokens_per_second": 29187.793
    },
    {
      "epoch": 0.2773950867633628,
      "grad_norm": 1.390625,
      "learning_rate": 3.7435595983344175e-05,
      "loss": 1.1183170318603515,
      "num_input_tokens_seen": 2228604288,
      "step": 7840,
      "train_runtime": 76355.7866,
      "train_tokens_per_second": 29187.104
    },
    {
      "epoch": 0.2777489070270916,
      "grad_norm": 1.453125,
      "learning_rate": 3.7425107765285155e-05,
      "loss": 1.1182866096496582,
      "num_input_tokens_seen": 2231460224,
      "step": 7850,
      "train_runtime": 76453.1884,
      "train_tokens_per_second": 29187.275
    },
    {
      "epoch": 0.27810272729082036,
      "grad_norm": 1.375,
      "learning_rate": 3.741462835764676e-05,
      "loss": 1.1316190719604493,
      "num_input_tokens_seen": 2234335488,
      "step": 7860,
      "train_runtime": 76551.7972,
      "train_tokens_per_second": 29187.238
    },
    {
      "epoch": 0.2784565475545491,
      "grad_norm": 1.4296875,
      "learning_rate": 3.740415774810088e-05,
      "loss": 1.143202018737793,
      "num_input_tokens_seen": 2237156352,
      "step": 7870,
      "train_runtime": 76646.3965,
      "train_tokens_per_second": 29188.017
    },
    {
      "epoch": 0.2788103678182779,
      "grad_norm": 1.4765625,
      "learning_rate": 3.739369592434351e-05,
      "loss": 1.1331881523132323,
      "num_input_tokens_seen": 2239989440,
      "step": 7880,
      "train_runtime": 76741.487,
      "train_tokens_per_second": 29188.768
    },
    {
      "epoch": 0.2791641880820067,
      "grad_norm": 1.40625,
      "learning_rate": 3.738324287409473e-05,
      "loss": 1.135151481628418,
      "num_input_tokens_seen": 2242795072,
      "step": 7890,
      "train_runtime": 76837.6395,
      "train_tokens_per_second": 29188.755
    },
    {
      "epoch": 0.2795180083457355,
      "grad_norm": 1.3828125,
      "learning_rate": 3.7372798585098644e-05,
      "loss": 1.1281002044677735,
      "num_input_tokens_seen": 2245659968,
      "step": 7900,
      "train_runtime": 76935.0665,
      "train_tokens_per_second": 29189.03
    },
    {
      "epoch": 0.27987182860946425,
      "grad_norm": 1.3984375,
      "learning_rate": 3.736236304512331e-05,
      "loss": 1.1266074180603027,
      "num_input_tokens_seen": 2248550016,
      "step": 7910,
      "train_runtime": 77034.3417,
      "train_tokens_per_second": 29188.93
    },
    {
      "epoch": 0.280225648873193,
      "grad_norm": 1.421875,
      "learning_rate": 3.735193624196067e-05,
      "loss": 1.1398014068603515,
      "num_input_tokens_seen": 2251377408,
      "step": 7920,
      "train_runtime": 77133.2243,
      "train_tokens_per_second": 29188.167
    },
    {
      "epoch": 0.28057946913692183,
      "grad_norm": 1.4140625,
      "learning_rate": 3.7341518163426514e-05,
      "loss": 1.1338825225830078,
      "num_input_tokens_seen": 2254267840,
      "step": 7930,
      "train_runtime": 77234.1905,
      "train_tokens_per_second": 29187.434
    },
    {
      "epoch": 0.2809332894006506,
      "grad_norm": 1.4296875,
      "learning_rate": 3.73311087973604e-05,
      "loss": 1.1300137519836426,
      "num_input_tokens_seen": 2257108288,
      "step": 7940,
      "train_runtime": 77331.5107,
      "train_tokens_per_second": 29187.433
    },
    {
      "epoch": 0.28128710966437936,
      "grad_norm": 1.375,
      "learning_rate": 3.732070813162561e-05,
      "loss": 1.132537841796875,
      "num_input_tokens_seen": 2259932288,
      "step": 7950,
      "train_runtime": 77427.511,
      "train_tokens_per_second": 29187.717
    },
    {
      "epoch": 0.28164092992810813,
      "grad_norm": 1.4453125,
      "learning_rate": 3.731031615410908e-05,
      "loss": 1.1268039703369142,
      "num_input_tokens_seen": 2262767296,
      "step": 7960,
      "train_runtime": 77526.9336,
      "train_tokens_per_second": 29186.854
    },
    {
      "epoch": 0.28199475019183695,
      "grad_norm": 1.421875,
      "learning_rate": 3.729993285272132e-05,
      "loss": 1.1363138198852538,
      "num_input_tokens_seen": 2265615168,
      "step": 7970,
      "train_runtime": 77620.9465,
      "train_tokens_per_second": 29188.193
    },
    {
      "epoch": 0.2823485704555657,
      "grad_norm": 1.4140625,
      "learning_rate": 3.7289558215396414e-05,
      "loss": 1.1310443878173828,
      "num_input_tokens_seen": 2268486528,
      "step": 7980,
      "train_runtime": 77721.9026,
      "train_tokens_per_second": 29187.223
    },
    {
      "epoch": 0.2827023907192945,
      "grad_norm": 1.46875,
      "learning_rate": 3.727919223009191e-05,
      "loss": 1.1291948318481446,
      "num_input_tokens_seen": 2271343488,
      "step": 7990,
      "train_runtime": 77819.2925,
      "train_tokens_per_second": 29187.409
    },
    {
      "epoch": 0.28305621098302325,
      "grad_norm": 1.4296875,
      "learning_rate": 3.726883488478877e-05,
      "loss": 1.1411422729492187,
      "num_input_tokens_seen": 2274239872,
      "step": 8000,
      "train_runtime": 77921.9153,
      "train_tokens_per_second": 29186.139
    },
    {
      "epoch": 0.283410031246752,
      "grad_norm": 1.546875,
      "learning_rate": 3.7258486167491323e-05,
      "loss": 1.1403490066528321,
      "num_input_tokens_seen": 2277056192,
      "step": 8010,
      "train_runtime": 78020.0687,
      "train_tokens_per_second": 29185.519
    },
    {
      "epoch": 0.28376385151048084,
      "grad_norm": 1.390625,
      "learning_rate": 3.724814606622721e-05,
      "loss": 1.124257469177246,
      "num_input_tokens_seen": 2279883712,
      "step": 8020,
      "train_runtime": 78116.5981,
      "train_tokens_per_second": 29185.65
    },
    {
      "epoch": 0.2841176717742096,
      "grad_norm": 1.46875,
      "learning_rate": 3.7237814569047294e-05,
      "loss": 1.1326744079589843,
      "num_input_tokens_seen": 2282755712,
      "step": 8030,
      "train_runtime": 78216.2185,
      "train_tokens_per_second": 29185.197
    },
    {
      "epoch": 0.28447149203793837,
      "grad_norm": 1.375,
      "learning_rate": 3.7227491664025656e-05,
      "loss": 1.13114013671875,
      "num_input_tokens_seen": 2285597504,
      "step": 8040,
      "train_runtime": 78313.1538,
      "train_tokens_per_second": 29185.359
    },
    {
      "epoch": 0.28482531230166713,
      "grad_norm": 1.4296875,
      "learning_rate": 3.721717733925948e-05,
      "loss": 1.1304126739501954,
      "num_input_tokens_seen": 2288411904,
      "step": 8050,
      "train_runtime": 78408.591,
      "train_tokens_per_second": 29185.729
    },
    {
      "epoch": 0.28517913256539595,
      "grad_norm": 1.453125,
      "learning_rate": 3.720687158286904e-05,
      "loss": 1.1453889846801757,
      "num_input_tokens_seen": 2291227200,
      "step": 8060,
      "train_runtime": 78506.5534,
      "train_tokens_per_second": 29185.171
    },
    {
      "epoch": 0.2855329528291247,
      "grad_norm": 1.3828125,
      "learning_rate": 3.719657438299762e-05,
      "loss": 1.1260215759277343,
      "num_input_tokens_seen": 2294135296,
      "step": 8070,
      "train_runtime": 78607.6359,
      "train_tokens_per_second": 29184.637
    },
    {
      "epoch": 0.2858867730928535,
      "grad_norm": 1.4140625,
      "learning_rate": 3.7186285727811446e-05,
      "loss": 1.1442317962646484,
      "num_input_tokens_seen": 2296980672,
      "step": 8080,
      "train_runtime": 78703.2757,
      "train_tokens_per_second": 29185.325
    },
    {
      "epoch": 0.28624059335658225,
      "grad_norm": 1.390625,
      "learning_rate": 3.717600560549967e-05,
      "loss": 1.1200284957885742,
      "num_input_tokens_seen": 2299847616,
      "step": 8090,
      "train_runtime": 78802.5776,
      "train_tokens_per_second": 29184.929
    },
    {
      "epoch": 0.2865944136203111,
      "grad_norm": 1.40625,
      "learning_rate": 3.716573400427426e-05,
      "loss": 1.131354522705078,
      "num_input_tokens_seen": 2302721024,
      "step": 8100,
      "train_runtime": 78900.441,
      "train_tokens_per_second": 29185.148
    },
    {
      "epoch": 0.28694823388403984,
      "grad_norm": 1.4453125,
      "learning_rate": 3.7155470912370004e-05,
      "loss": 1.128091049194336,
      "num_input_tokens_seen": 2305532864,
      "step": 8110,
      "train_runtime": 78995.9616,
      "train_tokens_per_second": 29185.452
    },
    {
      "epoch": 0.2873020541477686,
      "grad_norm": 1.4296875,
      "learning_rate": 3.714521631804439e-05,
      "loss": 1.1166316986083984,
      "num_input_tokens_seen": 2308429184,
      "step": 8120,
      "train_runtime": 79097.6061,
      "train_tokens_per_second": 29184.564
    },
    {
      "epoch": 0.28765587441149737,
      "grad_norm": 1.3984375,
      "learning_rate": 3.713497020957759e-05,
      "loss": 1.1284744262695312,
      "num_input_tokens_seen": 2311290368,
      "step": 8130,
      "train_runtime": 79195.5682,
      "train_tokens_per_second": 29184.592
    },
    {
      "epoch": 0.2880096946752262,
      "grad_norm": 1.375,
      "learning_rate": 3.712473257527238e-05,
      "loss": 1.1257888793945312,
      "num_input_tokens_seen": 2314154880,
      "step": 8140,
      "train_runtime": 79292.6667,
      "train_tokens_per_second": 29184.98
    },
    {
      "epoch": 0.28836351493895496,
      "grad_norm": 1.4453125,
      "learning_rate": 3.711450340345412e-05,
      "loss": 1.1286203384399414,
      "num_input_tokens_seen": 2316930176,
      "step": 8150,
      "train_runtime": 79385.9411,
      "train_tokens_per_second": 29185.649
    },
    {
      "epoch": 0.2887173352026837,
      "grad_norm": 1.40625,
      "learning_rate": 3.710428268247067e-05,
      "loss": 1.1332658767700194,
      "num_input_tokens_seen": 2319758464,
      "step": 8160,
      "train_runtime": 79481.6487,
      "train_tokens_per_second": 29186.089
    },
    {
      "epoch": 0.2890711554664125,
      "grad_norm": 1.390625,
      "learning_rate": 3.709407040069233e-05,
      "loss": 1.1342099189758301,
      "num_input_tokens_seen": 2322607680,
      "step": 8170,
      "train_runtime": 79576.7605,
      "train_tokens_per_second": 29187.01
    },
    {
      "epoch": 0.2894249757301413,
      "grad_norm": 1.3984375,
      "learning_rate": 3.708386654651179e-05,
      "loss": 1.1288168907165528,
      "num_input_tokens_seen": 2325455936,
      "step": 8180,
      "train_runtime": 79672.4626,
      "train_tokens_per_second": 29187.7
    },
    {
      "epoch": 0.2897787959938701,
      "grad_norm": 1.421875,
      "learning_rate": 3.707367110834409e-05,
      "loss": 1.1234468460083007,
      "num_input_tokens_seen": 2328385344,
      "step": 8190,
      "train_runtime": 79773.0415,
      "train_tokens_per_second": 29187.622
    },
    {
      "epoch": 0.29013261625759884,
      "grad_norm": 1.40625,
      "learning_rate": 3.7063484074626555e-05,
      "loss": 1.122950553894043,
      "num_input_tokens_seen": 2331216704,
      "step": 8200,
      "train_runtime": 79869.2063,
      "train_tokens_per_second": 29187.929
    },
    {
      "epoch": 0.2904864365213276,
      "grad_norm": 1.40625,
      "learning_rate": 3.7053305433818725e-05,
      "loss": 1.1147238731384277,
      "num_input_tokens_seen": 2334031296,
      "step": 8210,
      "train_runtime": 79964.6388,
      "train_tokens_per_second": 29188.293
    },
    {
      "epoch": 0.29084025678505643,
      "grad_norm": 1.40625,
      "learning_rate": 3.704313517440232e-05,
      "loss": 1.1350948333740234,
      "num_input_tokens_seen": 2336879680,
      "step": 8220,
      "train_runtime": 80061.6959,
      "train_tokens_per_second": 29188.486
    },
    {
      "epoch": 0.2911940770487852,
      "grad_norm": 1.421875,
      "learning_rate": 3.703297328488118e-05,
      "loss": 1.1406403541564942,
      "num_input_tokens_seen": 2339704960,
      "step": 8230,
      "train_runtime": 80156.6228,
      "train_tokens_per_second": 29189.166
    },
    {
      "epoch": 0.29154789731251396,
      "grad_norm": 1.421875,
      "learning_rate": 3.70228197537812e-05,
      "loss": 1.1303775787353516,
      "num_input_tokens_seen": 2342555712,
      "step": 8240,
      "train_runtime": 80254.772,
      "train_tokens_per_second": 29188.99
    },
    {
      "epoch": 0.2919017175762427,
      "grad_norm": 1.4609375,
      "learning_rate": 3.7012674569650305e-05,
      "loss": 1.123440933227539,
      "num_input_tokens_seen": 2345399232,
      "step": 8250,
      "train_runtime": 80351.869,
      "train_tokens_per_second": 29189.106
    },
    {
      "epoch": 0.2922555378399715,
      "grad_norm": 1.4296875,
      "learning_rate": 3.700253772105835e-05,
      "loss": 1.1239120483398437,
      "num_input_tokens_seen": 2348243328,
      "step": 8260,
      "train_runtime": 80450.6535,
      "train_tokens_per_second": 29188.617
    },
    {
      "epoch": 0.2926093581037003,
      "grad_norm": 1.3671875,
      "learning_rate": 3.699240919659711e-05,
      "loss": 1.111411190032959,
      "num_input_tokens_seen": 2351143808,
      "step": 8270,
      "train_runtime": 80551.2972,
      "train_tokens_per_second": 29188.156
    },
    {
      "epoch": 0.2929631783674291,
      "grad_norm": 1.484375,
      "learning_rate": 3.698228898488019e-05,
      "loss": 1.1376068115234375,
      "num_input_tokens_seen": 2354002048,
      "step": 8280,
      "train_runtime": 80649.9049,
      "train_tokens_per_second": 29187.909
    },
    {
      "epoch": 0.29331699863115784,
      "grad_norm": 1.3671875,
      "learning_rate": 3.6972177074543e-05,
      "loss": 1.1308083534240723,
      "num_input_tokens_seen": 2356863744,
      "step": 8290,
      "train_runtime": 80746.9014,
      "train_tokens_per_second": 29188.287
    },
    {
      "epoch": 0.2936708188948866,
      "grad_norm": 1.3984375,
      "learning_rate": 3.69620734542427e-05,
      "loss": 1.1193157196044923,
      "num_input_tokens_seen": 2359627648,
      "step": 8300,
      "train_runtime": 80841.8287,
      "train_tokens_per_second": 29188.202
    },
    {
      "epoch": 0.29402463915861543,
      "grad_norm": 1.375,
      "learning_rate": 3.695197811265811e-05,
      "loss": 1.115550422668457,
      "num_input_tokens_seen": 2362501568,
      "step": 8310,
      "train_runtime": 80938.7533,
      "train_tokens_per_second": 29188.757
    },
    {
      "epoch": 0.2943784594223442,
      "grad_norm": 1.359375,
      "learning_rate": 3.6941891038489694e-05,
      "loss": 1.1178993225097655,
      "num_input_tokens_seen": 2365346752,
      "step": 8320,
      "train_runtime": 81036.7459,
      "train_tokens_per_second": 29188.57
    },
    {
      "epoch": 0.29473227968607296,
      "grad_norm": 1.453125,
      "learning_rate": 3.693181222045952e-05,
      "loss": 1.1281351089477538,
      "num_input_tokens_seen": 2368080704,
      "step": 8330,
      "train_runtime": 81126.6452,
      "train_tokens_per_second": 29189.925
    },
    {
      "epoch": 0.29508609994980173,
      "grad_norm": 1.3828125,
      "learning_rate": 3.692174164731113e-05,
      "loss": 1.117399024963379,
      "num_input_tokens_seen": 2370936576,
      "step": 8340,
      "train_runtime": 81225.4357,
      "train_tokens_per_second": 29189.583
    },
    {
      "epoch": 0.29543992021353055,
      "grad_norm": 1.3984375,
      "learning_rate": 3.6911679307809595e-05,
      "loss": 1.1253440856933594,
      "num_input_tokens_seen": 2373767424,
      "step": 8350,
      "train_runtime": 81321.9177,
      "train_tokens_per_second": 29189.762
    },
    {
      "epoch": 0.2957937404772593,
      "grad_norm": 1.3828125,
      "learning_rate": 3.690162519074137e-05,
      "loss": 1.1316165924072266,
      "num_input_tokens_seen": 2376621184,
      "step": 8360,
      "train_runtime": 81419.481,
      "train_tokens_per_second": 29189.835
    },
    {
      "epoch": 0.2961475607409881,
      "grad_norm": 1.328125,
      "learning_rate": 3.689157928491431e-05,
      "loss": 1.1369115829467773,
      "num_input_tokens_seen": 2379502336,
      "step": 8370,
      "train_runtime": 81520.8032,
      "train_tokens_per_second": 29188.897
    },
    {
      "epoch": 0.29650138100471685,
      "grad_norm": 1.40625,
      "learning_rate": 3.6881541579157566e-05,
      "loss": 1.1128883361816406,
      "num_input_tokens_seen": 2382356224,
      "step": 8380,
      "train_runtime": 81616.7019,
      "train_tokens_per_second": 29189.567
    },
    {
      "epoch": 0.29685520126844567,
      "grad_norm": 1.3359375,
      "learning_rate": 3.687151206232154e-05,
      "loss": 1.120544147491455,
      "num_input_tokens_seen": 2385200640,
      "step": 8390,
      "train_runtime": 81713.5745,
      "train_tokens_per_second": 29189.772
    },
    {
      "epoch": 0.29720902153217443,
      "grad_norm": 1.390625,
      "learning_rate": 3.686149072327788e-05,
      "loss": 1.1094697952270507,
      "num_input_tokens_seen": 2388069312,
      "step": 8400,
      "train_runtime": 81816.5612,
      "train_tokens_per_second": 29188.092
    },
    {
      "epoch": 0.2975628417959032,
      "grad_norm": 1.40625,
      "learning_rate": 3.685147755091937e-05,
      "loss": 1.1189895629882813,
      "num_input_tokens_seen": 2390887552,
      "step": 8410,
      "train_runtime": 81910.9535,
      "train_tokens_per_second": 29188.862
    },
    {
      "epoch": 0.29791666205963196,
      "grad_norm": 1.3828125,
      "learning_rate": 3.684147253415992e-05,
      "loss": 1.1353343963623046,
      "num_input_tokens_seen": 2393791232,
      "step": 8420,
      "train_runtime": 82011.9706,
      "train_tokens_per_second": 29188.315
    },
    {
      "epoch": 0.2982704823233608,
      "grad_norm": 1.46875,
      "learning_rate": 3.683147566193448e-05,
      "loss": 1.1186967849731446,
      "num_input_tokens_seen": 2396629440,
      "step": 8430,
      "train_runtime": 82109.6732,
      "train_tokens_per_second": 29188.15
    },
    {
      "epoch": 0.29862430258708955,
      "grad_norm": 1.3125,
      "learning_rate": 3.6821486923199025e-05,
      "loss": 1.1169426918029786,
      "num_input_tokens_seen": 2399512128,
      "step": 8440,
      "train_runtime": 82206.5495,
      "train_tokens_per_second": 29188.819
    },
    {
      "epoch": 0.2989781228508183,
      "grad_norm": 1.4140625,
      "learning_rate": 3.681150630693046e-05,
      "loss": 1.1447039604187013,
      "num_input_tokens_seen": 2402339072,
      "step": 8450,
      "train_runtime": 82301.8774,
      "train_tokens_per_second": 29189.359
    },
    {
      "epoch": 0.2993319431145471,
      "grad_norm": 1.3984375,
      "learning_rate": 3.6801533802126615e-05,
      "loss": 1.12135009765625,
      "num_input_tokens_seen": 2405264896,
      "step": 8460,
      "train_runtime": 82401.4541,
      "train_tokens_per_second": 29189.593
    },
    {
      "epoch": 0.2996857633782759,
      "grad_norm": 1.4921875,
      "learning_rate": 3.679156939780617e-05,
      "loss": 1.1173569679260253,
      "num_input_tokens_seen": 2408088704,
      "step": 8470,
      "train_runtime": 82497.6881,
      "train_tokens_per_second": 29189.772
    },
    {
      "epoch": 0.30003958364200467,
      "grad_norm": 1.3984375,
      "learning_rate": 3.6781613083008594e-05,
      "loss": 1.1180392265319825,
      "num_input_tokens_seen": 2410963584,
      "step": 8480,
      "train_runtime": 82597.6625,
      "train_tokens_per_second": 29189.247
    },
    {
      "epoch": 0.30039340390573344,
      "grad_norm": 1.5078125,
      "learning_rate": 3.677166484679412e-05,
      "loss": 1.114876651763916,
      "num_input_tokens_seen": 2413775104,
      "step": 8490,
      "train_runtime": 82696.8962,
      "train_tokens_per_second": 29188.219
    },
    {
      "epoch": 0.3007472241694622,
      "grad_norm": 1.390625,
      "learning_rate": 3.676172467824368e-05,
      "loss": 1.1401662826538086,
      "num_input_tokens_seen": 2416579520,
      "step": 8500,
      "train_runtime": 82792.1291,
      "train_tokens_per_second": 29188.518
    },
    {
      "epoch": 0.30110104443319097,
      "grad_norm": 1.40625,
      "learning_rate": 3.675179256645885e-05,
      "loss": 1.115629291534424,
      "num_input_tokens_seen": 2419437504,
      "step": 8510,
      "train_runtime": 82889.3571,
      "train_tokens_per_second": 29188.759
    },
    {
      "epoch": 0.3014548646969198,
      "grad_norm": 1.3984375,
      "learning_rate": 3.674186850056181e-05,
      "loss": 1.1329103469848634,
      "num_input_tokens_seen": 2422266048,
      "step": 8520,
      "train_runtime": 82986.0424,
      "train_tokens_per_second": 29188.837
    },
    {
      "epoch": 0.30180868496064855,
      "grad_norm": 1.4921875,
      "learning_rate": 3.67319524696953e-05,
      "loss": 1.1320242881774902,
      "num_input_tokens_seen": 2425138624,
      "step": 8530,
      "train_runtime": 83084.2092,
      "train_tokens_per_second": 29188.923
    },
    {
      "epoch": 0.3021625052243773,
      "grad_norm": 1.4453125,
      "learning_rate": 3.6722044463022536e-05,
      "loss": 1.136598777770996,
      "num_input_tokens_seen": 2427948672,
      "step": 8540,
      "train_runtime": 83180.1683,
      "train_tokens_per_second": 29189.033
    },
    {
      "epoch": 0.3025163254881061,
      "grad_norm": 1.46875,
      "learning_rate": 3.6712144469727214e-05,
      "loss": 1.150098705291748,
      "num_input_tokens_seen": 2430787840,
      "step": 8550,
      "train_runtime": 83276.9682,
      "train_tokens_per_second": 29189.197
    },
    {
      "epoch": 0.3028701457518349,
      "grad_norm": 1.484375,
      "learning_rate": 3.67022524790134e-05,
      "loss": 1.1031455993652344,
      "num_input_tokens_seen": 2433624896,
      "step": 8560,
      "train_runtime": 83375.0654,
      "train_tokens_per_second": 29188.881
    },
    {
      "epoch": 0.3032239660155637,
      "grad_norm": 1.4921875,
      "learning_rate": 3.6692368480105546e-05,
      "loss": 1.130989170074463,
      "num_input_tokens_seen": 2436540992,
      "step": 8570,
      "train_runtime": 83479.2561,
      "train_tokens_per_second": 29187.383
    },
    {
      "epoch": 0.30357778627929244,
      "grad_norm": 1.4296875,
      "learning_rate": 3.6682492462248374e-05,
      "loss": 1.1278568267822267,
      "num_input_tokens_seen": 2439352320,
      "step": 8580,
      "train_runtime": 83574.551,
      "train_tokens_per_second": 29187.741
    },
    {
      "epoch": 0.3039316065430212,
      "grad_norm": 1.5078125,
      "learning_rate": 3.667262441470689e-05,
      "loss": 1.1163878440856934,
      "num_input_tokens_seen": 2442149504,
      "step": 8590,
      "train_runtime": 83670.1516,
      "train_tokens_per_second": 29187.822
    },
    {
      "epoch": 0.30428542680675,
      "grad_norm": 1.4140625,
      "learning_rate": 3.6662764326766255e-05,
      "loss": 1.1244693756103517,
      "num_input_tokens_seen": 2445011904,
      "step": 8600,
      "train_runtime": 83766.4121,
      "train_tokens_per_second": 29188.452
    },
    {
      "epoch": 0.3046392470704788,
      "grad_norm": 1.453125,
      "learning_rate": 3.665291218773185e-05,
      "loss": 1.1290009498596192,
      "num_input_tokens_seen": 2447813440,
      "step": 8610,
      "train_runtime": 83862.9885,
      "train_tokens_per_second": 29188.245
    },
    {
      "epoch": 0.30499306733420756,
      "grad_norm": 1.5,
      "learning_rate": 3.664306798692912e-05,
      "loss": 1.1371442794799804,
      "num_input_tokens_seen": 2450714688,
      "step": 8620,
      "train_runtime": 83962.659,
      "train_tokens_per_second": 29188.15
    },
    {
      "epoch": 0.3053468875979363,
      "grad_norm": 1.421875,
      "learning_rate": 3.6633231713703576e-05,
      "loss": 1.121608352661133,
      "num_input_tokens_seen": 2453575680,
      "step": 8630,
      "train_runtime": 84057.6491,
      "train_tokens_per_second": 29189.202
    },
    {
      "epoch": 0.30570070786166514,
      "grad_norm": 1.3671875,
      "learning_rate": 3.6623403357420745e-05,
      "loss": 1.1213171005249023,
      "num_input_tokens_seen": 2456404864,
      "step": 8640,
      "train_runtime": 84154.0283,
      "train_tokens_per_second": 29189.391
    },
    {
      "epoch": 0.3060545281253939,
      "grad_norm": 1.4296875,
      "learning_rate": 3.661358290746611e-05,
      "loss": 1.1265426635742188,
      "num_input_tokens_seen": 2459235200,
      "step": 8650,
      "train_runtime": 84248.5045,
      "train_tokens_per_second": 29190.253
    },
    {
      "epoch": 0.3064083483891227,
      "grad_norm": 1.4375,
      "learning_rate": 3.6603770353245056e-05,
      "loss": 1.1187304496765136,
      "num_input_tokens_seen": 2462055168,
      "step": 8660,
      "train_runtime": 84344.5661,
      "train_tokens_per_second": 29190.442
    },
    {
      "epoch": 0.30676216865285144,
      "grad_norm": 1.4140625,
      "learning_rate": 3.659396568418286e-05,
      "loss": 1.1444374084472657,
      "num_input_tokens_seen": 2464862528,
      "step": 8670,
      "train_runtime": 84440.05,
      "train_tokens_per_second": 29190.681
    },
    {
      "epoch": 0.30711598891658026,
      "grad_norm": 1.3671875,
      "learning_rate": 3.658416888972459e-05,
      "loss": 1.1160392761230469,
      "num_input_tokens_seen": 2467719744,
      "step": 8680,
      "train_runtime": 84540.8057,
      "train_tokens_per_second": 29189.688
    },
    {
      "epoch": 0.30746980918030903,
      "grad_norm": 1.3671875,
      "learning_rate": 3.6574379959335106e-05,
      "loss": 1.1155062675476075,
      "num_input_tokens_seen": 2470527360,
      "step": 8690,
      "train_runtime": 84638.3805,
      "train_tokens_per_second": 29189.209
    },
    {
      "epoch": 0.3078236294440378,
      "grad_norm": 1.4609375,
      "learning_rate": 3.6564598882498976e-05,
      "loss": 1.1218263626098632,
      "num_input_tokens_seen": 2473384512,
      "step": 8700,
      "train_runtime": 84736.0005,
      "train_tokens_per_second": 29189.3
    },
    {
      "epoch": 0.30817744970776656,
      "grad_norm": 1.4375,
      "learning_rate": 3.655482564872043e-05,
      "loss": 1.1300183296203614,
      "num_input_tokens_seen": 2476265920,
      "step": 8710,
      "train_runtime": 84836.943,
      "train_tokens_per_second": 29188.533
    },
    {
      "epoch": 0.3085312699714954,
      "grad_norm": 1.4296875,
      "learning_rate": 3.654506024752336e-05,
      "loss": 1.1353984832763673,
      "num_input_tokens_seen": 2479082048,
      "step": 8720,
      "train_runtime": 84934.0182,
      "train_tokens_per_second": 29188.329
    },
    {
      "epoch": 0.30888509023522415,
      "grad_norm": 1.4140625,
      "learning_rate": 3.653530266845121e-05,
      "loss": 1.1258880615234375,
      "num_input_tokens_seen": 2481906176,
      "step": 8730,
      "train_runtime": 85032.9337,
      "train_tokens_per_second": 29187.587
    },
    {
      "epoch": 0.3092389104989529,
      "grad_norm": 1.3828125,
      "learning_rate": 3.652555290106696e-05,
      "loss": 1.1230047225952149,
      "num_input_tokens_seen": 2484805632,
      "step": 8740,
      "train_runtime": 85134.2736,
      "train_tokens_per_second": 29186.901
    },
    {
      "epoch": 0.3095927307626817,
      "grad_norm": 1.40625,
      "learning_rate": 3.6515810934953084e-05,
      "loss": 1.1328210830688477,
      "num_input_tokens_seen": 2487667264,
      "step": 8750,
      "train_runtime": 85233.1649,
      "train_tokens_per_second": 29186.611
    },
    {
      "epoch": 0.30994655102641044,
      "grad_norm": 1.390625,
      "learning_rate": 3.650607675971151e-05,
      "loss": 1.134385108947754,
      "num_input_tokens_seen": 2490510976,
      "step": 8760,
      "train_runtime": 85329.2609,
      "train_tokens_per_second": 29187.068
    },
    {
      "epoch": 0.31030037129013927,
      "grad_norm": 1.4609375,
      "learning_rate": 3.649635036496351e-05,
      "loss": 1.119410228729248,
      "num_input_tokens_seen": 2493334080,
      "step": 8770,
      "train_runtime": 85426.077,
      "train_tokens_per_second": 29187.037
    },
    {
      "epoch": 0.31065419155386803,
      "grad_norm": 1.40625,
      "learning_rate": 3.6486631740349746e-05,
      "loss": 1.12426700592041,
      "num_input_tokens_seen": 2496189760,
      "step": 8780,
      "train_runtime": 85524.5292,
      "train_tokens_per_second": 29186.828
    },
    {
      "epoch": 0.3110080118175968,
      "grad_norm": 1.3984375,
      "learning_rate": 3.647692087553018e-05,
      "loss": 1.1201671600341796,
      "num_input_tokens_seen": 2499008640,
      "step": 8790,
      "train_runtime": 85621.1868,
      "train_tokens_per_second": 29186.802
    },
    {
      "epoch": 0.31136183208132556,
      "grad_norm": 1.4296875,
      "learning_rate": 3.6467217760184005e-05,
      "loss": 1.1179556846618652,
      "num_input_tokens_seen": 2501886848,
      "step": 8800,
      "train_runtime": 85719.996,
      "train_tokens_per_second": 29186.735
    },
    {
      "epoch": 0.3117156523450544,
      "grad_norm": 1.390625,
      "learning_rate": 3.6457522384009625e-05,
      "loss": 1.1338930130004883,
      "num_input_tokens_seen": 2504794944,
      "step": 8810,
      "train_runtime": 85821.2233,
      "train_tokens_per_second": 29186.195
    },
    {
      "epoch": 0.31206947260878315,
      "grad_norm": 1.453125,
      "learning_rate": 3.644783473672462e-05,
      "loss": 1.1311001777648926,
      "num_input_tokens_seen": 2507562112,
      "step": 8820,
      "train_runtime": 85912.1665,
      "train_tokens_per_second": 29187.509
    },
    {
      "epoch": 0.3124232928725119,
      "grad_norm": 1.4609375,
      "learning_rate": 3.643815480806568e-05,
      "loss": 1.1240288734436035,
      "num_input_tokens_seen": 2510362944,
      "step": 8830,
      "train_runtime": 86007.2102,
      "train_tokens_per_second": 29187.82
    },
    {
      "epoch": 0.3127771131362407,
      "grad_norm": 1.4453125,
      "learning_rate": 3.6428482587788555e-05,
      "loss": 1.1163619995117187,
      "num_input_tokens_seen": 2513173952,
      "step": 8840,
      "train_runtime": 86103.1347,
      "train_tokens_per_second": 29187.95
    },
    {
      "epoch": 0.3131309333999695,
      "grad_norm": 1.3984375,
      "learning_rate": 3.641881806566803e-05,
      "loss": 1.1362246513366698,
      "num_input_tokens_seen": 2515977600,
      "step": 8850,
      "train_runtime": 86198.5096,
      "train_tokens_per_second": 29188.18
    },
    {
      "epoch": 0.31348475366369827,
      "grad_norm": 1.359375,
      "learning_rate": 3.640916123149788e-05,
      "loss": 1.1329086303710938,
      "num_input_tokens_seen": 2518817344,
      "step": 8860,
      "train_runtime": 86292.4068,
      "train_tokens_per_second": 29189.328
    },
    {
      "epoch": 0.31383857392742703,
      "grad_norm": 1.453125,
      "learning_rate": 3.639951207509079e-05,
      "loss": 1.129981231689453,
      "num_input_tokens_seen": 2521707904,
      "step": 8870,
      "train_runtime": 86390.7016,
      "train_tokens_per_second": 29189.575
    },
    {
      "epoch": 0.3141923941911558,
      "grad_norm": 1.4296875,
      "learning_rate": 3.6389870586278333e-05,
      "loss": 1.1341193199157715,
      "num_input_tokens_seen": 2524563456,
      "step": 8880,
      "train_runtime": 86491.7242,
      "train_tokens_per_second": 29188.497
    },
    {
      "epoch": 0.3145462144548846,
      "grad_norm": 1.3828125,
      "learning_rate": 3.6380236754910965e-05,
      "loss": 1.1225038528442384,
      "num_input_tokens_seen": 2527402176,
      "step": 8890,
      "train_runtime": 86589.1681,
      "train_tokens_per_second": 29188.434
    },
    {
      "epoch": 0.3149000347186134,
      "grad_norm": 1.46875,
      "learning_rate": 3.6370610570857897e-05,
      "loss": 1.1302080154418945,
      "num_input_tokens_seen": 2530241984,
      "step": 8900,
      "train_runtime": 86685.1822,
      "train_tokens_per_second": 29188.864
    },
    {
      "epoch": 0.31525385498234215,
      "grad_norm": 1.4609375,
      "learning_rate": 3.6360992024007114e-05,
      "loss": 1.12758150100708,
      "num_input_tokens_seen": 2533102720,
      "step": 8910,
      "train_runtime": 86782.279,
      "train_tokens_per_second": 29189.17
    },
    {
      "epoch": 0.3156076752460709,
      "grad_norm": 1.4296875,
      "learning_rate": 3.6351381104265304e-05,
      "loss": 1.1178728103637696,
      "num_input_tokens_seen": 2535987776,
      "step": 8920,
      "train_runtime": 86885.0562,
      "train_tokens_per_second": 29187.848
    },
    {
      "epoch": 0.31596149550979974,
      "grad_norm": 1.40625,
      "learning_rate": 3.634177780155783e-05,
      "loss": 1.122505283355713,
      "num_input_tokens_seen": 2538791680,
      "step": 8930,
      "train_runtime": 86980.0486,
      "train_tokens_per_second": 29188.207
    },
    {
      "epoch": 0.3163153157735285,
      "grad_norm": 1.421875,
      "learning_rate": 3.633218210582867e-05,
      "loss": 1.1400506019592285,
      "num_input_tokens_seen": 2541619776,
      "step": 8940,
      "train_runtime": 87074.3543,
      "train_tokens_per_second": 29189.074
    },
    {
      "epoch": 0.31666913603725727,
      "grad_norm": 1.421875,
      "learning_rate": 3.6322594007040376e-05,
      "loss": 1.122921085357666,
      "num_input_tokens_seen": 2544407552,
      "step": 8950,
      "train_runtime": 87166.7046,
      "train_tokens_per_second": 29190.131
    },
    {
      "epoch": 0.31702295630098604,
      "grad_norm": 1.390625,
      "learning_rate": 3.631301349517403e-05,
      "loss": 1.1329333305358886,
      "num_input_tokens_seen": 2547242816,
      "step": 8960,
      "train_runtime": 87263.6965,
      "train_tokens_per_second": 29190.178
    },
    {
      "epoch": 0.31737677656471486,
      "grad_norm": 1.46875,
      "learning_rate": 3.6303440560229216e-05,
      "loss": 1.1296253204345703,
      "num_input_tokens_seen": 2550115904,
      "step": 8970,
      "train_runtime": 87363.8625,
      "train_tokens_per_second": 29189.597
    },
    {
      "epoch": 0.3177305968284436,
      "grad_norm": 1.3828125,
      "learning_rate": 3.629387519222395e-05,
      "loss": 1.1210012435913086,
      "num_input_tokens_seen": 2552975104,
      "step": 8980,
      "train_runtime": 87462.7185,
      "train_tokens_per_second": 29189.295
    },
    {
      "epoch": 0.3180844170921724,
      "grad_norm": 1.3359375,
      "learning_rate": 3.628431738119464e-05,
      "loss": 1.1072532653808593,
      "num_input_tokens_seen": 2555840832,
      "step": 8990,
      "train_runtime": 87562.6784,
      "train_tokens_per_second": 29188.701
    },
    {
      "epoch": 0.31843823735590115,
      "grad_norm": 1.3984375,
      "learning_rate": 3.62747671171961e-05,
      "loss": 1.1240053176879883,
      "num_input_tokens_seen": 2558715456,
      "step": 9000,
      "train_runtime": 87662.0483,
      "train_tokens_per_second": 29188.406
    },
    {
      "epoch": 0.3187920576196299,
      "grad_norm": 1.34375,
      "learning_rate": 3.626522439030138e-05,
      "loss": 1.1330659866333008,
      "num_input_tokens_seen": 2561515072,
      "step": 9010,
      "train_runtime": 87757.2908,
      "train_tokens_per_second": 29188.63
    },
    {
      "epoch": 0.31914587788335874,
      "grad_norm": 1.4609375,
      "learning_rate": 3.6255689190601863e-05,
      "loss": 1.1192876815795898,
      "num_input_tokens_seen": 2564361216,
      "step": 9020,
      "train_runtime": 87856.4234,
      "train_tokens_per_second": 29188.09
    },
    {
      "epoch": 0.3194996981470875,
      "grad_norm": 1.3671875,
      "learning_rate": 3.624616150820714e-05,
      "loss": 1.1350156784057617,
      "num_input_tokens_seen": 2567278592,
      "step": 9030,
      "train_runtime": 87956.0313,
      "train_tokens_per_second": 29188.204
    },
    {
      "epoch": 0.3198535184108163,
      "grad_norm": 1.421875,
      "learning_rate": 3.623664133324499e-05,
      "loss": 1.0994648933410645,
      "num_input_tokens_seen": 2570106688,
      "step": 9040,
      "train_runtime": 88053.7493,
      "train_tokens_per_second": 29187.93
    },
    {
      "epoch": 0.32020733867454504,
      "grad_norm": 1.3828125,
      "learning_rate": 3.622712865586131e-05,
      "loss": 1.1128053665161133,
      "num_input_tokens_seen": 2572995136,
      "step": 9050,
      "train_runtime": 88156.7578,
      "train_tokens_per_second": 29186.59
    },
    {
      "epoch": 0.32056115893827386,
      "grad_norm": 1.3671875,
      "learning_rate": 3.621762346622014e-05,
      "loss": 1.1269713401794434,
      "num_input_tokens_seen": 2575895040,
      "step": 9060,
      "train_runtime": 88256.7919,
      "train_tokens_per_second": 29186.366
    },
    {
      "epoch": 0.3209149792020026,
      "grad_norm": 1.421875,
      "learning_rate": 3.620812575450352e-05,
      "loss": 1.120786476135254,
      "num_input_tokens_seen": 2578794624,
      "step": 9070,
      "train_runtime": 88353.8809,
      "train_tokens_per_second": 29187.112
    },
    {
      "epoch": 0.3212687994657314,
      "grad_norm": 1.4140625,
      "learning_rate": 3.6198635510911556e-05,
      "loss": 1.1182626724243163,
      "num_input_tokens_seen": 2581654976,
      "step": 9080,
      "train_runtime": 88449.8693,
      "train_tokens_per_second": 29187.776
    },
    {
      "epoch": 0.32162261972946016,
      "grad_norm": 1.421875,
      "learning_rate": 3.618915272566228e-05,
      "loss": 1.100466251373291,
      "num_input_tokens_seen": 2584450176,
      "step": 9090,
      "train_runtime": 88541.801,
      "train_tokens_per_second": 29189.04
    },
    {
      "epoch": 0.321976439993189,
      "grad_norm": 1.3984375,
      "learning_rate": 3.6179677388991694e-05,
      "loss": 1.1356571197509766,
      "num_input_tokens_seen": 2587310016,
      "step": 9100,
      "train_runtime": 88639.0941,
      "train_tokens_per_second": 29189.265
    },
    {
      "epoch": 0.32233026025691774,
      "grad_norm": 1.4140625,
      "learning_rate": 3.617020949115366e-05,
      "loss": 1.1236122131347657,
      "num_input_tokens_seen": 2590123008,
      "step": 9110,
      "train_runtime": 88737.388,
      "train_tokens_per_second": 29188.632
    },
    {
      "epoch": 0.3226840805206465,
      "grad_norm": 1.3515625,
      "learning_rate": 3.6160749022419886e-05,
      "loss": 1.1182680130004883,
      "num_input_tokens_seen": 2592997760,
      "step": 9120,
      "train_runtime": 88835.5397,
      "train_tokens_per_second": 29188.743
    },
    {
      "epoch": 0.3230379007843753,
      "grad_norm": 1.4140625,
      "learning_rate": 3.6151295973079887e-05,
      "loss": 1.1226987838745117,
      "num_input_tokens_seen": 2595862784,
      "step": 9130,
      "train_runtime": 88934.7602,
      "train_tokens_per_second": 29188.394
    },
    {
      "epoch": 0.3233917210481041,
      "grad_norm": 1.4453125,
      "learning_rate": 3.6141850333440934e-05,
      "loss": 1.1207016944885253,
      "num_input_tokens_seen": 2598674112,
      "step": 9140,
      "train_runtime": 89028.5047,
      "train_tokens_per_second": 29189.237
    },
    {
      "epoch": 0.32374554131183286,
      "grad_norm": 1.4296875,
      "learning_rate": 3.613241209382803e-05,
      "loss": 1.1185750007629394,
      "num_input_tokens_seen": 2601500736,
      "step": 9150,
      "train_runtime": 89125.5605,
      "train_tokens_per_second": 29189.165
    },
    {
      "epoch": 0.32409936157556163,
      "grad_norm": 1.421875,
      "learning_rate": 3.6122981244583834e-05,
      "loss": 1.1150111198425292,
      "num_input_tokens_seen": 2604376704,
      "step": 9160,
      "train_runtime": 89225.5478,
      "train_tokens_per_second": 29188.688
    },
    {
      "epoch": 0.3244531818392904,
      "grad_norm": 1.4296875,
      "learning_rate": 3.6113557776068644e-05,
      "loss": 1.1338795661926269,
      "num_input_tokens_seen": 2607175040,
      "step": 9170,
      "train_runtime": 89320.727,
      "train_tokens_per_second": 29188.914
    },
    {
      "epoch": 0.3248070021030192,
      "grad_norm": 1.375,
      "learning_rate": 3.6104141678660386e-05,
      "loss": 1.1259471893310546,
      "num_input_tokens_seen": 2610071488,
      "step": 9180,
      "train_runtime": 89421.624,
      "train_tokens_per_second": 29188.37
    },
    {
      "epoch": 0.325160822366748,
      "grad_norm": 1.40625,
      "learning_rate": 3.6094732942754487e-05,
      "loss": 1.124881649017334,
      "num_input_tokens_seen": 2612900480,
      "step": 9190,
      "train_runtime": 89518.85,
      "train_tokens_per_second": 29188.271
    },
    {
      "epoch": 0.32551464263047675,
      "grad_norm": 1.4375,
      "learning_rate": 3.60853315587639e-05,
      "loss": 1.1124618530273438,
      "num_input_tokens_seen": 2615733952,
      "step": 9200,
      "train_runtime": 89615.4092,
      "train_tokens_per_second": 29188.44
    },
    {
      "epoch": 0.3258684628942055,
      "grad_norm": 1.34375,
      "learning_rate": 3.607593751711909e-05,
      "loss": 1.1181381225585938,
      "num_input_tokens_seen": 2618562688,
      "step": 9210,
      "train_runtime": 89712.4193,
      "train_tokens_per_second": 29188.408
    },
    {
      "epoch": 0.32622228315793433,
      "grad_norm": 1.3671875,
      "learning_rate": 3.60665508082679e-05,
      "loss": 1.1356059074401856,
      "num_input_tokens_seen": 2621396928,
      "step": 9220,
      "train_runtime": 89809.972,
      "train_tokens_per_second": 29188.261
    },
    {
      "epoch": 0.3265761034216631,
      "grad_norm": 1.4296875,
      "learning_rate": 3.6057171422675585e-05,
      "loss": 1.1214991569519044,
      "num_input_tokens_seen": 2624207232,
      "step": 9230,
      "train_runtime": 89902.9859,
      "train_tokens_per_second": 29189.322
    },
    {
      "epoch": 0.32692992368539187,
      "grad_norm": 1.40625,
      "learning_rate": 3.604779935082474e-05,
      "loss": 1.1198180198669434,
      "num_input_tokens_seen": 2627099328,
      "step": 9240,
      "train_runtime": 90003.0246,
      "train_tokens_per_second": 29189.012
    },
    {
      "epoch": 0.32728374394912063,
      "grad_norm": 1.4453125,
      "learning_rate": 3.603843458321526e-05,
      "loss": 1.1245351791381837,
      "num_input_tokens_seen": 2629939328,
      "step": 9250,
      "train_runtime": 90099.1411,
      "train_tokens_per_second": 29189.394
    },
    {
      "epoch": 0.32763756421284945,
      "grad_norm": 1.4921875,
      "learning_rate": 3.6029077110364355e-05,
      "loss": 1.1235692977905274,
      "num_input_tokens_seen": 2632770752,
      "step": 9260,
      "train_runtime": 90191.611,
      "train_tokens_per_second": 29190.861
    },
    {
      "epoch": 0.3279913844765782,
      "grad_norm": 1.4453125,
      "learning_rate": 3.60197269228064e-05,
      "loss": 1.1284940719604493,
      "num_input_tokens_seen": 2635556544,
      "step": 9270,
      "train_runtime": 90285.9312,
      "train_tokens_per_second": 29191.221
    },
    {
      "epoch": 0.328345204740307,
      "grad_norm": 1.3984375,
      "learning_rate": 3.601038401109299e-05,
      "loss": 1.120694351196289,
      "num_input_tokens_seen": 2638380544,
      "step": 9280,
      "train_runtime": 90380.0654,
      "train_tokens_per_second": 29192.063
    },
    {
      "epoch": 0.32869902500403575,
      "grad_norm": 1.4375,
      "learning_rate": 3.6001048365792846e-05,
      "loss": 1.1235492706298829,
      "num_input_tokens_seen": 2641256448,
      "step": 9290,
      "train_runtime": 90479.0775,
      "train_tokens_per_second": 29191.903
    },
    {
      "epoch": 0.3290528452677645,
      "grad_norm": 1.3671875,
      "learning_rate": 3.599171997749182e-05,
      "loss": 1.1138433456420898,
      "num_input_tokens_seen": 2644147904,
      "step": 9300,
      "train_runtime": 90578.304,
      "train_tokens_per_second": 29191.846
    },
    {
      "epoch": 0.32940666553149334,
      "grad_norm": 1.484375,
      "learning_rate": 3.598239883679281e-05,
      "loss": 1.1388039588928223,
      "num_input_tokens_seen": 2646989184,
      "step": 9310,
      "train_runtime": 90676.41,
      "train_tokens_per_second": 29191.597
    },
    {
      "epoch": 0.3297604857952221,
      "grad_norm": 1.4375,
      "learning_rate": 3.597308493431576e-05,
      "loss": 1.1168378829956054,
      "num_input_tokens_seen": 2649807872,
      "step": 9320,
      "train_runtime": 90772.6098,
      "train_tokens_per_second": 29191.712
    },
    {
      "epoch": 0.33011430605895087,
      "grad_norm": 1.4140625,
      "learning_rate": 3.596377826069758e-05,
      "loss": 1.1381750106811523,
      "num_input_tokens_seen": 2652620224,
      "step": 9330,
      "train_runtime": 90869.2288,
      "train_tokens_per_second": 29191.623
    },
    {
      "epoch": 0.33046812632267963,
      "grad_norm": 1.4375,
      "learning_rate": 3.5954478806592155e-05,
      "loss": 1.108255386352539,
      "num_input_tokens_seen": 2655494400,
      "step": 9340,
      "train_runtime": 90968.2157,
      "train_tokens_per_second": 29191.453
    },
    {
      "epoch": 0.33082194658640846,
      "grad_norm": 1.40625,
      "learning_rate": 3.594518656267024e-05,
      "loss": 1.1222249031066895,
      "num_input_tokens_seen": 2658351552,
      "step": 9350,
      "train_runtime": 91066.7924,
      "train_tokens_per_second": 29191.229
    },
    {
      "epoch": 0.3311757668501372,
      "grad_norm": 1.4296875,
      "learning_rate": 3.5935901519619496e-05,
      "loss": 1.124747085571289,
      "num_input_tokens_seen": 2661200768,
      "step": 9360,
      "train_runtime": 91161.5182,
      "train_tokens_per_second": 29192.151
    },
    {
      "epoch": 0.331529587113866,
      "grad_norm": 1.359375,
      "learning_rate": 3.5926623668144385e-05,
      "loss": 1.112786102294922,
      "num_input_tokens_seen": 2664068544,
      "step": 9370,
      "train_runtime": 91260.3555,
      "train_tokens_per_second": 29191.959
    },
    {
      "epoch": 0.33188340737759475,
      "grad_norm": 1.375,
      "learning_rate": 3.5917352998966194e-05,
      "loss": 1.1267093658447265,
      "num_input_tokens_seen": 2666974464,
      "step": 9380,
      "train_runtime": 91362.8286,
      "train_tokens_per_second": 29191.023
    },
    {
      "epoch": 0.3322372276413236,
      "grad_norm": 1.4453125,
      "learning_rate": 3.5908089502822914e-05,
      "loss": 1.1222867965698242,
      "num_input_tokens_seen": 2669785344,
      "step": 9390,
      "train_runtime": 91459.8959,
      "train_tokens_per_second": 29190.776
    },
    {
      "epoch": 0.33259104790505234,
      "grad_norm": 1.421875,
      "learning_rate": 3.589883317046929e-05,
      "loss": 1.1301656723022462,
      "num_input_tokens_seen": 2672659712,
      "step": 9400,
      "train_runtime": 91559.0917,
      "train_tokens_per_second": 29190.544
    },
    {
      "epoch": 0.3329448681687811,
      "grad_norm": 1.46875,
      "learning_rate": 3.5889583992676715e-05,
      "loss": 1.1311653137207032,
      "num_input_tokens_seen": 2675633856,
      "step": 9410,
      "train_runtime": 91667.8424,
      "train_tokens_per_second": 29188.359
    },
    {
      "epoch": 0.33329868843250987,
      "grad_norm": 1.4609375,
      "learning_rate": 3.5880341960233244e-05,
      "loss": 1.1145493507385253,
      "num_input_tokens_seen": 2678472576,
      "step": 9420,
      "train_runtime": 91764.2578,
      "train_tokens_per_second": 29188.626
    },
    {
      "epoch": 0.3336525086962387,
      "grad_norm": 1.4609375,
      "learning_rate": 3.58711070639435e-05,
      "loss": 1.1212147712707519,
      "num_input_tokens_seen": 2681330496,
      "step": 9430,
      "train_runtime": 91863.4098,
      "train_tokens_per_second": 29188.232
    },
    {
      "epoch": 0.33400632895996746,
      "grad_norm": 1.4140625,
      "learning_rate": 3.586187929462869e-05,
      "loss": 1.1153898239135742,
      "num_input_tokens_seen": 2684185664,
      "step": 9440,
      "train_runtime": 91960.56,
      "train_tokens_per_second": 29188.444
    },
    {
      "epoch": 0.3343601492236962,
      "grad_norm": 1.484375,
      "learning_rate": 3.585265864312651e-05,
      "loss": 1.1192108154296876,
      "num_input_tokens_seen": 2687038656,
      "step": 9450,
      "train_runtime": 92059.6866,
      "train_tokens_per_second": 29188.006
    },
    {
      "epoch": 0.334713969487425,
      "grad_norm": 1.40625,
      "learning_rate": 3.584344510029118e-05,
      "loss": 1.1284709930419923,
      "num_input_tokens_seen": 2689887424,
      "step": 9460,
      "train_runtime": 92162.6313,
      "train_tokens_per_second": 29186.313
    },
    {
      "epoch": 0.3350677897511538,
      "grad_norm": 1.4453125,
      "learning_rate": 3.583423865699333e-05,
      "loss": 1.1181785583496093,
      "num_input_tokens_seen": 2692676672,
      "step": 9470,
      "train_runtime": 92257.3222,
      "train_tokens_per_second": 29186.59
    },
    {
      "epoch": 0.3354216100148826,
      "grad_norm": 1.3828125,
      "learning_rate": 3.5825039304119994e-05,
      "loss": 1.1325632095336915,
      "num_input_tokens_seen": 2695477440,
      "step": 9480,
      "train_runtime": 92351.5195,
      "train_tokens_per_second": 29187.148
    },
    {
      "epoch": 0.33577543027861134,
      "grad_norm": 1.4375,
      "learning_rate": 3.581584703257461e-05,
      "loss": 1.1161925315856933,
      "num_input_tokens_seen": 2698277824,
      "step": 9490,
      "train_runtime": 92446.6004,
      "train_tokens_per_second": 29187.421
    },
    {
      "epoch": 0.3361292505423401,
      "grad_norm": 1.390625,
      "learning_rate": 3.580666183327689e-05,
      "loss": 1.116877555847168,
      "num_input_tokens_seen": 2701066624,
      "step": 9500,
      "train_runtime": 92542.0271,
      "train_tokens_per_second": 29187.459
    },
    {
      "epoch": 0.33648307080606893,
      "grad_norm": 1.40625,
      "learning_rate": 3.5797483697162906e-05,
      "loss": 1.1289949417114258,
      "num_input_tokens_seen": 2703923072,
      "step": 9510,
      "train_runtime": 92640.5825,
      "train_tokens_per_second": 29187.242
    },
    {
      "epoch": 0.3368368910697977,
      "grad_norm": 1.4609375,
      "learning_rate": 3.5788312615184936e-05,
      "loss": 1.1240201950073243,
      "num_input_tokens_seen": 2706712320,
      "step": 9520,
      "train_runtime": 92733.6628,
      "train_tokens_per_second": 29188.023
    },
    {
      "epoch": 0.33719071133352646,
      "grad_norm": 1.4375,
      "learning_rate": 3.5779148578311476e-05,
      "loss": 1.1112796783447265,
      "num_input_tokens_seen": 2709565248,
      "step": 9530,
      "train_runtime": 92832.2292,
      "train_tokens_per_second": 29187.765
    },
    {
      "epoch": 0.3375445315972552,
      "grad_norm": 1.3984375,
      "learning_rate": 3.5769991577527236e-05,
      "loss": 1.1177736282348634,
      "num_input_tokens_seen": 2712431488,
      "step": 9540,
      "train_runtime": 92932.2426,
      "train_tokens_per_second": 29187.195
    },
    {
      "epoch": 0.337898351860984,
      "grad_norm": 1.3984375,
      "learning_rate": 3.5760841603833034e-05,
      "loss": 1.1261808395385742,
      "num_input_tokens_seen": 2715215744,
      "step": 9550,
      "train_runtime": 93026.3533,
      "train_tokens_per_second": 29187.597
    },
    {
      "epoch": 0.3382521721247128,
      "grad_norm": 1.4375,
      "learning_rate": 3.5751698648245814e-05,
      "loss": 1.1256035804748534,
      "num_input_tokens_seen": 2718075904,
      "step": 9560,
      "train_runtime": 93123.8424,
      "train_tokens_per_second": 29187.755
    },
    {
      "epoch": 0.3386059923884416,
      "grad_norm": 1.390625,
      "learning_rate": 3.574256270179857e-05,
      "loss": 1.1279800415039063,
      "num_input_tokens_seen": 2720922240,
      "step": 9570,
      "train_runtime": 93219.2374,
      "train_tokens_per_second": 29188.42
    },
    {
      "epoch": 0.33895981265217034,
      "grad_norm": 1.3984375,
      "learning_rate": 3.573343375554037e-05,
      "loss": 1.1151175498962402,
      "num_input_tokens_seen": 2723745536,
      "step": 9580,
      "train_runtime": 93316.8135,
      "train_tokens_per_second": 29188.154
    },
    {
      "epoch": 0.3393136329158991,
      "grad_norm": 1.34375,
      "learning_rate": 3.572431180053621e-05,
      "loss": 1.1193756103515624,
      "num_input_tokens_seen": 2726585024,
      "step": 9590,
      "train_runtime": 93412.8625,
      "train_tokens_per_second": 29188.539
    },
    {
      "epoch": 0.33966745317962793,
      "grad_norm": 1.4453125,
      "learning_rate": 3.571519682786711e-05,
      "loss": 1.1256680488586426,
      "num_input_tokens_seen": 2729407232,
      "step": 9600,
      "train_runtime": 93508.067,
      "train_tokens_per_second": 29189.003
    },
    {
      "epoch": 0.3400212734433567,
      "grad_norm": 1.40625,
      "learning_rate": 3.570608882862996e-05,
      "loss": 1.1174805641174317,
      "num_input_tokens_seen": 2732339136,
      "step": 9610,
      "train_runtime": 93610.8376,
      "train_tokens_per_second": 29188.278
    },
    {
      "epoch": 0.34037509370708546,
      "grad_norm": 1.4296875,
      "learning_rate": 3.569698779393757e-05,
      "loss": 1.118931198120117,
      "num_input_tokens_seen": 2735181952,
      "step": 9620,
      "train_runtime": 93707.8034,
      "train_tokens_per_second": 29188.412
    },
    {
      "epoch": 0.34072891397081423,
      "grad_norm": 1.484375,
      "learning_rate": 3.568789371491859e-05,
      "loss": 1.1140660285949706,
      "num_input_tokens_seen": 2738008576,
      "step": 9630,
      "train_runtime": 93802.7169,
      "train_tokens_per_second": 29189.011
    },
    {
      "epoch": 0.34108273423454305,
      "grad_norm": 1.40625,
      "learning_rate": 3.567880658271748e-05,
      "loss": 1.1254289627075196,
      "num_input_tokens_seen": 2740840448,
      "step": 9640,
      "train_runtime": 93900.1881,
      "train_tokens_per_second": 29188.871
    },
    {
      "epoch": 0.3414365544982718,
      "grad_norm": 1.4140625,
      "learning_rate": 3.566972638849445e-05,
      "loss": 1.1219924926757812,
      "num_input_tokens_seen": 2743672448,
      "step": 9650,
      "train_runtime": 93997.6323,
      "train_tokens_per_second": 29188.74
    },
    {
      "epoch": 0.3417903747620006,
      "grad_norm": 1.390625,
      "learning_rate": 3.566065312342551e-05,
      "loss": 1.1299943923950195,
      "num_input_tokens_seen": 2746535680,
      "step": 9660,
      "train_runtime": 94095.8508,
      "train_tokens_per_second": 29188.701
    },
    {
      "epoch": 0.34214419502572935,
      "grad_norm": 1.4609375,
      "learning_rate": 3.565158677870231e-05,
      "loss": 1.1233320236206055,
      "num_input_tokens_seen": 2749366528,
      "step": 9670,
      "train_runtime": 94192.1831,
      "train_tokens_per_second": 29188.903
    },
    {
      "epoch": 0.34249801528945817,
      "grad_norm": 1.4453125,
      "learning_rate": 3.564252734553221e-05,
      "loss": 1.1325451850891113,
      "num_input_tokens_seen": 2752208512,
      "step": 9680,
      "train_runtime": 94290.1794,
      "train_tokens_per_second": 29188.708
    },
    {
      "epoch": 0.34285183555318693,
      "grad_norm": 1.40625,
      "learning_rate": 3.563347481513818e-05,
      "loss": 1.1063970565795898,
      "num_input_tokens_seen": 2755070656,
      "step": 9690,
      "train_runtime": 94386.5634,
      "train_tokens_per_second": 29189.225
    },
    {
      "epoch": 0.3432056558169157,
      "grad_norm": 1.3515625,
      "learning_rate": 3.56244291787588e-05,
      "loss": 1.1268686294555663,
      "num_input_tokens_seen": 2757961664,
      "step": 9700,
      "train_runtime": 94487.0331,
      "train_tokens_per_second": 29188.785
    },
    {
      "epoch": 0.34355947608064447,
      "grad_norm": 1.4140625,
      "learning_rate": 3.5615390427648216e-05,
      "loss": 1.121345329284668,
      "num_input_tokens_seen": 2760823872,
      "step": 9710,
      "train_runtime": 94585.5189,
      "train_tokens_per_second": 29188.653
    },
    {
      "epoch": 0.3439132963443733,
      "grad_norm": 1.40625,
      "learning_rate": 3.5606358553076075e-05,
      "loss": 1.1318540573120117,
      "num_input_tokens_seen": 2763666752,
      "step": 9720,
      "train_runtime": 94682.2458,
      "train_tokens_per_second": 29188.859
    },
    {
      "epoch": 0.34426711660810205,
      "grad_norm": 1.4140625,
      "learning_rate": 3.5597333546327526e-05,
      "loss": 1.1212841033935548,
      "num_input_tokens_seen": 2766528320,
      "step": 9730,
      "train_runtime": 94780.4467,
      "train_tokens_per_second": 29188.809
    },
    {
      "epoch": 0.3446209368718308,
      "grad_norm": 1.40625,
      "learning_rate": 3.5588315398703186e-05,
      "loss": 1.1235257148742677,
      "num_input_tokens_seen": 2769368640,
      "step": 9740,
      "train_runtime": 94879.2997,
      "train_tokens_per_second": 29188.333
    },
    {
      "epoch": 0.3449747571355596,
      "grad_norm": 1.3984375,
      "learning_rate": 3.557930410151907e-05,
      "loss": 1.125667190551758,
      "num_input_tokens_seen": 2772225664,
      "step": 9750,
      "train_runtime": 94977.6614,
      "train_tokens_per_second": 29188.186
    },
    {
      "epoch": 0.3453285773992884,
      "grad_norm": 1.4453125,
      "learning_rate": 3.5570299646106606e-05,
      "loss": 1.126353931427002,
      "num_input_tokens_seen": 2775066944,
      "step": 9760,
      "train_runtime": 95074.0334,
      "train_tokens_per_second": 29188.484
    },
    {
      "epoch": 0.34568239766301717,
      "grad_norm": 1.4921875,
      "learning_rate": 3.556130202381253e-05,
      "loss": 1.1292800903320312,
      "num_input_tokens_seen": 2777946752,
      "step": 9770,
      "train_runtime": 95173.1995,
      "train_tokens_per_second": 29188.33
    },
    {
      "epoch": 0.34603621792674594,
      "grad_norm": 1.3984375,
      "learning_rate": 3.555231122599892e-05,
      "loss": 1.1255942344665528,
      "num_input_tokens_seen": 2780791680,
      "step": 9780,
      "train_runtime": 95271.4153,
      "train_tokens_per_second": 29188.101
    },
    {
      "epoch": 0.3463900381904747,
      "grad_norm": 1.421875,
      "learning_rate": 3.554332724404313e-05,
      "loss": 1.1063140869140624,
      "num_input_tokens_seen": 2783628736,
      "step": 9790,
      "train_runtime": 95365.7914,
      "train_tokens_per_second": 29188.965
    },
    {
      "epoch": 0.34674385845420347,
      "grad_norm": 1.4375,
      "learning_rate": 3.553435006933777e-05,
      "loss": 1.1084149360656739,
      "num_input_tokens_seen": 2786429696,
      "step": 9800,
      "train_runtime": 95458.7135,
      "train_tokens_per_second": 29189.894
    },
    {
      "epoch": 0.3470976787179323,
      "grad_norm": 1.4375,
      "learning_rate": 3.5525379693290626e-05,
      "loss": 1.1316360473632812,
      "num_input_tokens_seen": 2789282624,
      "step": 9810,
      "train_runtime": 95558.3865,
      "train_tokens_per_second": 29189.302
    },
    {
      "epoch": 0.34745149898166106,
      "grad_norm": 1.359375,
      "learning_rate": 3.551641610732469e-05,
      "loss": 1.1189855575561523,
      "num_input_tokens_seen": 2792052992,
      "step": 9820,
      "train_runtime": 95649.9851,
      "train_tokens_per_second": 29190.313
    },
    {
      "epoch": 0.3478053192453898,
      "grad_norm": 1.4296875,
      "learning_rate": 3.55074593028781e-05,
      "loss": 1.1084105491638183,
      "num_input_tokens_seen": 2794906496,
      "step": 9830,
      "train_runtime": 95748.6092,
      "train_tokens_per_second": 29190.048
    },
    {
      "epoch": 0.3481591395091186,
      "grad_norm": 1.375,
      "learning_rate": 3.5498509271404065e-05,
      "loss": 1.1247610092163085,
      "num_input_tokens_seen": 2797787136,
      "step": 9840,
      "train_runtime": 95847.4016,
      "train_tokens_per_second": 29190.015
    },
    {
      "epoch": 0.3485129597728474,
      "grad_norm": 1.5234375,
      "learning_rate": 3.5489566004370893e-05,
      "loss": 1.1253646850585937,
      "num_input_tokens_seen": 2800681280,
      "step": 9850,
      "train_runtime": 95948.7665,
      "train_tokens_per_second": 29189.341
    },
    {
      "epoch": 0.3488667800365762,
      "grad_norm": 1.4453125,
      "learning_rate": 3.548062949326194e-05,
      "loss": 1.1148176193237305,
      "num_input_tokens_seen": 2803524800,
      "step": 9860,
      "train_runtime": 96044.6662,
      "train_tokens_per_second": 29189.802
    },
    {
      "epoch": 0.34922060030030494,
      "grad_norm": 1.390625,
      "learning_rate": 3.547169972957554e-05,
      "loss": 1.1202608108520509,
      "num_input_tokens_seen": 2806324992,
      "step": 9870,
      "train_runtime": 96140.6759,
      "train_tokens_per_second": 29189.778
    },
    {
      "epoch": 0.3495744205640337,
      "grad_norm": 1.3984375,
      "learning_rate": 3.5462776704825e-05,
      "loss": 1.1176113128662108,
      "num_input_tokens_seen": 2809198208,
      "step": 9880,
      "train_runtime": 96238.0425,
      "train_tokens_per_second": 29190.101
    },
    {
      "epoch": 0.3499282408277625,
      "grad_norm": 1.4609375,
      "learning_rate": 3.5453860410538594e-05,
      "loss": 1.109024429321289,
      "num_input_tokens_seen": 2812001408,
      "step": 9890,
      "train_runtime": 96332.733,
      "train_tokens_per_second": 29190.508
    },
    {
      "epoch": 0.3502820610914913,
      "grad_norm": 1.5703125,
      "learning_rate": 3.5444950838259455e-05,
      "loss": 1.109194278717041,
      "num_input_tokens_seen": 2814878784,
      "step": 9900,
      "train_runtime": 96431.8684,
      "train_tokens_per_second": 29190.337
    },
    {
      "epoch": 0.35063588135522006,
      "grad_norm": 1.4140625,
      "learning_rate": 3.543604797954563e-05,
      "loss": 1.112288761138916,
      "num_input_tokens_seen": 2817671616,
      "step": 9910,
      "train_runtime": 96526.1892,
      "train_tokens_per_second": 29190.747
    },
    {
      "epoch": 0.3509897016189488,
      "grad_norm": 1.4375,
      "learning_rate": 3.542715182596996e-05,
      "loss": 1.1129362106323242,
      "num_input_tokens_seen": 2820527872,
      "step": 9920,
      "train_runtime": 96624.0564,
      "train_tokens_per_second": 29190.742
    },
    {
      "epoch": 0.35134352188267765,
      "grad_norm": 1.421875,
      "learning_rate": 3.5418262369120115e-05,
      "loss": 1.1146570205688477,
      "num_input_tokens_seen": 2823372928,
      "step": 9930,
      "train_runtime": 96720.6889,
      "train_tokens_per_second": 29190.993
    },
    {
      "epoch": 0.3516973421464064,
      "grad_norm": 1.4296875,
      "learning_rate": 3.5409379600598526e-05,
      "loss": 1.1188179969787597,
      "num_input_tokens_seen": 2826218944,
      "step": 9940,
      "train_runtime": 96817.8747,
      "train_tokens_per_second": 29191.086
    },
    {
      "epoch": 0.3520511624101352,
      "grad_norm": 1.359375,
      "learning_rate": 3.540050351202235e-05,
      "loss": 1.1275922775268554,
      "num_input_tokens_seen": 2829055168,
      "step": 9950,
      "train_runtime": 96913.0701,
      "train_tokens_per_second": 29191.678
    },
    {
      "epoch": 0.35240498267386394,
      "grad_norm": 1.3984375,
      "learning_rate": 3.539163409502347e-05,
      "loss": 1.113216018676758,
      "num_input_tokens_seen": 2831964224,
      "step": 9960,
      "train_runtime": 97015.5726,
      "train_tokens_per_second": 29190.821
    },
    {
      "epoch": 0.35275880293759276,
      "grad_norm": 1.4375,
      "learning_rate": 3.5382771341248416e-05,
      "loss": 1.1188175201416015,
      "num_input_tokens_seen": 2834815616,
      "step": 9970,
      "train_runtime": 97112.6245,
      "train_tokens_per_second": 29191.01
    },
    {
      "epoch": 0.35311262320132153,
      "grad_norm": 1.4609375,
      "learning_rate": 3.537391524235835e-05,
      "loss": 1.1246353149414063,
      "num_input_tokens_seen": 2837725056,
      "step": 9980,
      "train_runtime": 97213.7987,
      "train_tokens_per_second": 29190.558
    },
    {
      "epoch": 0.3534664434650503,
      "grad_norm": 1.515625,
      "learning_rate": 3.5365065790029055e-05,
      "loss": 1.130160140991211,
      "num_input_tokens_seen": 2840564416,
      "step": 9990,
      "train_runtime": 97312.3622,
      "train_tokens_per_second": 29190.17
    },
    {
      "epoch": 0.35382026372877906,
      "grad_norm": 1.4296875,
      "learning_rate": 3.535622297595087e-05,
      "loss": 1.115757942199707,
      "num_input_tokens_seen": 2843412288,
      "step": 10000,
      "train_runtime": 97411.5268,
      "train_tokens_per_second": 29189.69
    },
    {
      "epoch": 0.35382026372877906,
      "eval_loss": 1.0372706651687622,
      "eval_runtime": 8.4453,
      "eval_samples_per_second": 472.214,
      "eval_steps_per_second": 3.789,
      "num_input_tokens_seen": 2843412288,
      "step": 10000
    },
    {
      "epoch": 0.3541740839925079,
      "grad_norm": 1.390625,
      "learning_rate": 3.534738679182869e-05,
      "loss": 1.1269047737121582,
      "num_input_tokens_seen": 2846261632,
      "step": 10010,
      "train_runtime": 97536.7678,
      "train_tokens_per_second": 29181.423
    },
    {
      "epoch": 0.35452790425623665,
      "grad_norm": 1.3828125,
      "learning_rate": 3.533855722938188e-05,
      "loss": 1.1177932739257812,
      "num_input_tokens_seen": 2849122752,
      "step": 10020,
      "train_runtime": 97633.9783,
      "train_tokens_per_second": 29181.672
    },
    {
      "epoch": 0.3548817245199654,
      "grad_norm": 1.4453125,
      "learning_rate": 3.5329734280344325e-05,
      "loss": 1.113227653503418,
      "num_input_tokens_seen": 2851970688,
      "step": 10030,
      "train_runtime": 97731.4603,
      "train_tokens_per_second": 29181.705
    },
    {
      "epoch": 0.3552355447836942,
      "grad_norm": 1.484375,
      "learning_rate": 3.5320917936464294e-05,
      "loss": 1.1225366592407227,
      "num_input_tokens_seen": 2854831552,
      "step": 10040,
      "train_runtime": 97831.2638,
      "train_tokens_per_second": 29181.178
    },
    {
      "epoch": 0.35558936504742295,
      "grad_norm": 1.3828125,
      "learning_rate": 3.5312108189504505e-05,
      "loss": 1.1237954139709472,
      "num_input_tokens_seen": 2857663424,
      "step": 10050,
      "train_runtime": 97927.6764,
      "train_tokens_per_second": 29181.367
    },
    {
      "epoch": 0.35594318531115177,
      "grad_norm": 1.3515625,
      "learning_rate": 3.530330503124204e-05,
      "loss": 1.1268199920654296,
      "num_input_tokens_seen": 2860553920,
      "step": 10060,
      "train_runtime": 98027.2536,
      "train_tokens_per_second": 29181.21
    },
    {
      "epoch": 0.35629700557488053,
      "grad_norm": 1.46875,
      "learning_rate": 3.5294508453468325e-05,
      "loss": 1.1216670989990234,
      "num_input_tokens_seen": 2863390528,
      "step": 10070,
      "train_runtime": 98127.5918,
      "train_tokens_per_second": 29180.279
    },
    {
      "epoch": 0.3566508258386093,
      "grad_norm": 1.4140625,
      "learning_rate": 3.528571844798908e-05,
      "loss": 1.1175540924072265,
      "num_input_tokens_seen": 2866238080,
      "step": 10080,
      "train_runtime": 98225.8852,
      "train_tokens_per_second": 29180.069
    },
    {
      "epoch": 0.35700464610233806,
      "grad_norm": 1.3515625,
      "learning_rate": 3.527693500662431e-05,
      "loss": 1.1122797012329102,
      "num_input_tokens_seen": 2869066944,
      "step": 10090,
      "train_runtime": 98321.6796,
      "train_tokens_per_second": 29180.41
    },
    {
      "epoch": 0.3573584663660669,
      "grad_norm": 1.4296875,
      "learning_rate": 3.5268158121208294e-05,
      "loss": 1.1270309448242188,
      "num_input_tokens_seen": 2871896960,
      "step": 10100,
      "train_runtime": 98419.4466,
      "train_tokens_per_second": 29180.178
    },
    {
      "epoch": 0.35771228662979565,
      "grad_norm": 1.4375,
      "learning_rate": 3.525938778358949e-05,
      "loss": 1.1095788955688477,
      "num_input_tokens_seen": 2874711360,
      "step": 10110,
      "train_runtime": 98513.7977,
      "train_tokens_per_second": 29180.799
    },
    {
      "epoch": 0.3580661068935244,
      "grad_norm": 1.40625,
      "learning_rate": 3.5250623985630537e-05,
      "loss": 1.1010171890258789,
      "num_input_tokens_seen": 2877534400,
      "step": 10120,
      "train_runtime": 98609.1326,
      "train_tokens_per_second": 29181.216
    },
    {
      "epoch": 0.3584199271572532,
      "grad_norm": 1.4609375,
      "learning_rate": 3.524186671920826e-05,
      "loss": 1.1162256240844726,
      "num_input_tokens_seen": 2880340160,
      "step": 10130,
      "train_runtime": 98706.5543,
      "train_tokens_per_second": 29180.84
    },
    {
      "epoch": 0.358773747420982,
      "grad_norm": 1.4453125,
      "learning_rate": 3.523311597621358e-05,
      "loss": 1.130044937133789,
      "num_input_tokens_seen": 2883145024,
      "step": 10140,
      "train_runtime": 98800.7358,
      "train_tokens_per_second": 29181.412
    },
    {
      "epoch": 0.35912756768471077,
      "grad_norm": 1.4609375,
      "learning_rate": 3.5224371748551505e-05,
      "loss": 1.1327491760253907,
      "num_input_tokens_seen": 2885943040,
      "step": 10150,
      "train_runtime": 98894.9224,
      "train_tokens_per_second": 29181.913
    },
    {
      "epoch": 0.35948138794843953,
      "grad_norm": 1.4375,
      "learning_rate": 3.521563402814109e-05,
      "loss": 1.1092525482177735,
      "num_input_tokens_seen": 2888792000,
      "step": 10160,
      "train_runtime": 98991.1651,
      "train_tokens_per_second": 29182.321
    },
    {
      "epoch": 0.3598352082121683,
      "grad_norm": 1.390625,
      "learning_rate": 3.5206902806915436e-05,
      "loss": 1.110850715637207,
      "num_input_tokens_seen": 2891615552,
      "step": 10170,
      "train_runtime": 99087.6242,
      "train_tokens_per_second": 29182.409
    },
    {
      "epoch": 0.3601890284758971,
      "grad_norm": 1.453125,
      "learning_rate": 3.5198178076821644e-05,
      "loss": 1.1072074890136718,
      "num_input_tokens_seen": 2894430336,
      "step": 10180,
      "train_runtime": 99186.4886,
      "train_tokens_per_second": 29181.7
    },
    {
      "epoch": 0.3605428487396259,
      "grad_norm": 1.4765625,
      "learning_rate": 3.5189459829820743e-05,
      "loss": 1.115060043334961,
      "num_input_tokens_seen": 2897246656,
      "step": 10190,
      "train_runtime": 99280.7205,
      "train_tokens_per_second": 29182.369
    },
    {
      "epoch": 0.36089666900335465,
      "grad_norm": 1.53125,
      "learning_rate": 3.5180748057887714e-05,
      "loss": 1.1040501594543457,
      "num_input_tokens_seen": 2900098944,
      "step": 10200,
      "train_runtime": 99378.4639,
      "train_tokens_per_second": 29182.368
    },
    {
      "epoch": 0.3612504892670834,
      "grad_norm": 1.4921875,
      "learning_rate": 3.517204275301144e-05,
      "loss": 1.1283758163452149,
      "num_input_tokens_seen": 2902918144,
      "step": 10210,
      "train_runtime": 99475.7019,
      "train_tokens_per_second": 29182.183
    },
    {
      "epoch": 0.36160430953081224,
      "grad_norm": 1.4375,
      "learning_rate": 3.5163343907194676e-05,
      "loss": 1.1114299774169922,
      "num_input_tokens_seen": 2905770432,
      "step": 10220,
      "train_runtime": 99571.0069,
      "train_tokens_per_second": 29182.897
    },
    {
      "epoch": 0.361958129794541,
      "grad_norm": 1.4296875,
      "learning_rate": 3.5154651512453995e-05,
      "loss": 1.1151932716369628,
      "num_input_tokens_seen": 2908571584,
      "step": 10230,
      "train_runtime": 99667.5395,
      "train_tokens_per_second": 29182.737
    },
    {
      "epoch": 0.36231195005826977,
      "grad_norm": 1.5078125,
      "learning_rate": 3.514596556081981e-05,
      "loss": 1.117941665649414,
      "num_input_tokens_seen": 2911423872,
      "step": 10240,
      "train_runtime": 99764.4732,
      "train_tokens_per_second": 29182.972
    },
    {
      "epoch": 0.36266577032199854,
      "grad_norm": 1.46875,
      "learning_rate": 3.513728604433628e-05,
      "loss": 1.1198583602905274,
      "num_input_tokens_seen": 2914283584,
      "step": 10250,
      "train_runtime": 99863.5919,
      "train_tokens_per_second": 29182.643
    },
    {
      "epoch": 0.36301959058572736,
      "grad_norm": 1.421875,
      "learning_rate": 3.5128612955061334e-05,
      "loss": 1.1151424407958985,
      "num_input_tokens_seen": 2917172096,
      "step": 10260,
      "train_runtime": 99964.7304,
      "train_tokens_per_second": 29182.013
    },
    {
      "epoch": 0.3633734108494561,
      "grad_norm": 1.4296875,
      "learning_rate": 3.5119946285066595e-05,
      "loss": 1.120326328277588,
      "num_input_tokens_seen": 2919902656,
      "step": 10270,
      "train_runtime": 100055.147,
      "train_tokens_per_second": 29182.933
    },
    {
      "epoch": 0.3637272311131849,
      "grad_norm": 1.421875,
      "learning_rate": 3.511128602643739e-05,
      "loss": 1.11312894821167,
      "num_input_tokens_seen": 2922714496,
      "step": 10280,
      "train_runtime": 100152.1783,
      "train_tokens_per_second": 29182.735
    },
    {
      "epoch": 0.36408105137691366,
      "grad_norm": 1.40625,
      "learning_rate": 3.510263217127269e-05,
      "loss": 1.1357854843139648,
      "num_input_tokens_seen": 2925525888,
      "step": 10290,
      "train_runtime": 100248.7699,
      "train_tokens_per_second": 29182.661
    },
    {
      "epoch": 0.3644348716406424,
      "grad_norm": 1.421875,
      "learning_rate": 3.50939847116851e-05,
      "loss": 1.122338104248047,
      "num_input_tokens_seen": 2928375872,
      "step": 10300,
      "train_runtime": 100345.9146,
      "train_tokens_per_second": 29182.811
    },
    {
      "epoch": 0.36478869190437124,
      "grad_norm": 1.484375,
      "learning_rate": 3.508534363980081e-05,
      "loss": 1.1127201080322267,
      "num_input_tokens_seen": 2931220864,
      "step": 10310,
      "train_runtime": 100443.8697,
      "train_tokens_per_second": 29182.676
    },
    {
      "epoch": 0.3651425121681,
      "grad_norm": 1.390625,
      "learning_rate": 3.507670894775958e-05,
      "loss": 1.1078279495239258,
      "num_input_tokens_seen": 2934116352,
      "step": 10320,
      "train_runtime": 100543.7415,
      "train_tokens_per_second": 29182.486
    },
    {
      "epoch": 0.3654963324318288,
      "grad_norm": 1.4375,
      "learning_rate": 3.506808062771471e-05,
      "loss": 1.1126413345336914,
      "num_input_tokens_seen": 2936979328,
      "step": 10330,
      "train_runtime": 100643.5748,
      "train_tokens_per_second": 29181.985
    },
    {
      "epoch": 0.36585015269555754,
      "grad_norm": 1.484375,
      "learning_rate": 3.505945867183298e-05,
      "loss": 1.1108901023864746,
      "num_input_tokens_seen": 2939864704,
      "step": 10340,
      "train_runtime": 100741.6459,
      "train_tokens_per_second": 29182.218
    },
    {
      "epoch": 0.36620397295928636,
      "grad_norm": 1.421875,
      "learning_rate": 3.505084307229468e-05,
      "loss": 1.1100027084350585,
      "num_input_tokens_seen": 2942764864,
      "step": 10350,
      "train_runtime": 100840.7667,
      "train_tokens_per_second": 29182.294
    },
    {
      "epoch": 0.3665577932230151,
      "grad_norm": 1.4765625,
      "learning_rate": 3.5042233821293525e-05,
      "loss": 1.1167325973510742,
      "num_input_tokens_seen": 2945659584,
      "step": 10360,
      "train_runtime": 100940.8964,
      "train_tokens_per_second": 29182.023
    },
    {
      "epoch": 0.3669116134867439,
      "grad_norm": 1.375,
      "learning_rate": 3.503363091103664e-05,
      "loss": 1.1093772888183593,
      "num_input_tokens_seen": 2948521152,
      "step": 10370,
      "train_runtime": 101039.091,
      "train_tokens_per_second": 29181.984
    },
    {
      "epoch": 0.36726543375047266,
      "grad_norm": 1.390625,
      "learning_rate": 3.5025034333744545e-05,
      "loss": 1.1222831726074218,
      "num_input_tokens_seen": 2951408384,
      "step": 10380,
      "train_runtime": 101140.5089,
      "train_tokens_per_second": 29181.269
    },
    {
      "epoch": 0.3676192540142015,
      "grad_norm": 1.4375,
      "learning_rate": 3.501644408165112e-05,
      "loss": 1.1212279319763183,
      "num_input_tokens_seen": 2954215808,
      "step": 10390,
      "train_runtime": 101236.67,
      "train_tokens_per_second": 29181.282
    },
    {
      "epoch": 0.36797307427793025,
      "grad_norm": 1.4375,
      "learning_rate": 3.500786014700357e-05,
      "loss": 1.1134011268615722,
      "num_input_tokens_seen": 2957086144,
      "step": 10400,
      "train_runtime": 101334.7644,
      "train_tokens_per_second": 29181.359
    },
    {
      "epoch": 0.368326894541659,
      "grad_norm": 1.375,
      "learning_rate": 3.499928252206237e-05,
      "loss": 1.1200634002685548,
      "num_input_tokens_seen": 2959937472,
      "step": 10410,
      "train_runtime": 101432.1888,
      "train_tokens_per_second": 29181.441
    },
    {
      "epoch": 0.3686807148053878,
      "grad_norm": 1.46875,
      "learning_rate": 3.499071119910131e-05,
      "loss": 1.1210924148559571,
      "num_input_tokens_seen": 2962776128,
      "step": 10420,
      "train_runtime": 101529.5345,
      "train_tokens_per_second": 29181.421
    },
    {
      "epoch": 0.3690345350691166,
      "grad_norm": 1.4453125,
      "learning_rate": 3.498214617040739e-05,
      "loss": 1.1227343559265137,
      "num_input_tokens_seen": 2965612416,
      "step": 10430,
      "train_runtime": 101625.5937,
      "train_tokens_per_second": 29181.748
    },
    {
      "epoch": 0.36938835533284536,
      "grad_norm": 1.421875,
      "learning_rate": 3.49735874282808e-05,
      "loss": 1.117354965209961,
      "num_input_tokens_seen": 2968451008,
      "step": 10440,
      "train_runtime": 101722.8542,
      "train_tokens_per_second": 29181.751
    },
    {
      "epoch": 0.36974217559657413,
      "grad_norm": 1.5859375,
      "learning_rate": 3.4965034965034965e-05,
      "loss": 1.1092388153076171,
      "num_input_tokens_seen": 2971281600,
      "step": 10450,
      "train_runtime": 101816.8755,
      "train_tokens_per_second": 29182.604
    },
    {
      "epoch": 0.3700959958603029,
      "grad_norm": 1.3984375,
      "learning_rate": 3.495648877299642e-05,
      "loss": 1.1116914749145508,
      "num_input_tokens_seen": 2974099712,
      "step": 10460,
      "train_runtime": 101912.5863,
      "train_tokens_per_second": 29182.85
    },
    {
      "epoch": 0.3704498161240317,
      "grad_norm": 1.484375,
      "learning_rate": 3.494794884450483e-05,
      "loss": 1.1130853652954102,
      "num_input_tokens_seen": 2976928896,
      "step": 10470,
      "train_runtime": 102009.0156,
      "train_tokens_per_second": 29182.998
    },
    {
      "epoch": 0.3708036363877605,
      "grad_norm": 1.4453125,
      "learning_rate": 3.4939415171912954e-05,
      "loss": 1.1183357238769531,
      "num_input_tokens_seen": 2979790336,
      "step": 10480,
      "train_runtime": 102107.4453,
      "train_tokens_per_second": 29182.89
    },
    {
      "epoch": 0.37115745665148925,
      "grad_norm": 1.3828125,
      "learning_rate": 3.4930887747586616e-05,
      "loss": 1.1139404296875,
      "num_input_tokens_seen": 2982652160,
      "step": 10490,
      "train_runtime": 102204.8376,
      "train_tokens_per_second": 29183.082
    },
    {
      "epoch": 0.371511276915218,
      "grad_norm": 1.421875,
      "learning_rate": 3.492236656390469e-05,
      "loss": 1.112145233154297,
      "num_input_tokens_seen": 2985514176,
      "step": 10500,
      "train_runtime": 102305.1865,
      "train_tokens_per_second": 29182.432
    },
    {
      "epoch": 0.37186509717894684,
      "grad_norm": 1.4375,
      "learning_rate": 3.4913851613259034e-05,
      "loss": 1.1100782394409179,
      "num_input_tokens_seen": 2988309056,
      "step": 10510,
      "train_runtime": 102398.8311,
      "train_tokens_per_second": 29183.039
    },
    {
      "epoch": 0.3722189174426756,
      "grad_norm": 1.4375,
      "learning_rate": 3.490534288805452e-05,
      "loss": 1.117668342590332,
      "num_input_tokens_seen": 2991174400,
      "step": 10520,
      "train_runtime": 102494.5793,
      "train_tokens_per_second": 29183.733
    },
    {
      "epoch": 0.37257273770640437,
      "grad_norm": 1.4296875,
      "learning_rate": 3.489684038070891e-05,
      "loss": 1.1157140731811523,
      "num_input_tokens_seen": 2993989824,
      "step": 10530,
      "train_runtime": 102591.1933,
      "train_tokens_per_second": 29183.692
    },
    {
      "epoch": 0.37292655797013313,
      "grad_norm": 1.40625,
      "learning_rate": 3.488834408365296e-05,
      "loss": 1.114221954345703,
      "num_input_tokens_seen": 2996803968,
      "step": 10540,
      "train_runtime": 102686.4276,
      "train_tokens_per_second": 29184.032
    },
    {
      "epoch": 0.37328037823386195,
      "grad_norm": 1.4609375,
      "learning_rate": 3.487985398933027e-05,
      "loss": 1.098709487915039,
      "num_input_tokens_seen": 2999637952,
      "step": 10550,
      "train_runtime": 102782.4254,
      "train_tokens_per_second": 29184.347
    },
    {
      "epoch": 0.3736341984975907,
      "grad_norm": 1.4609375,
      "learning_rate": 3.4871370090197324e-05,
      "loss": 1.1089361190795899,
      "num_input_tokens_seen": 3002435456,
      "step": 10560,
      "train_runtime": 102877.1071,
      "train_tokens_per_second": 29184.68
    },
    {
      "epoch": 0.3739880187613195,
      "grad_norm": 1.4453125,
      "learning_rate": 3.486289237872343e-05,
      "loss": 1.106496238708496,
      "num_input_tokens_seen": 3005268288,
      "step": 10570,
      "train_runtime": 102976.853,
      "train_tokens_per_second": 29183.92
    },
    {
      "epoch": 0.37434183902504825,
      "grad_norm": 1.53125,
      "learning_rate": 3.485442084739075e-05,
      "loss": 1.1061769485473634,
      "num_input_tokens_seen": 3008101568,
      "step": 10580,
      "train_runtime": 103075.6469,
      "train_tokens_per_second": 29183.436
    },
    {
      "epoch": 0.374695659288777,
      "grad_norm": 1.4140625,
      "learning_rate": 3.484595548869416e-05,
      "loss": 1.1253287315368652,
      "num_input_tokens_seen": 3010975040,
      "step": 10590,
      "train_runtime": 103173.0554,
      "train_tokens_per_second": 29183.734
    },
    {
      "epoch": 0.37504947955250584,
      "grad_norm": 1.40625,
      "learning_rate": 3.4837496295141335e-05,
      "loss": 1.1121050834655761,
      "num_input_tokens_seen": 3013859904,
      "step": 10600,
      "train_runtime": 103276.3622,
      "train_tokens_per_second": 29182.475
    },
    {
      "epoch": 0.3754032998162346,
      "grad_norm": 1.4921875,
      "learning_rate": 3.482904325925266e-05,
      "loss": 1.1130998611450196,
      "num_input_tokens_seen": 3016678976,
      "step": 10610,
      "train_runtime": 103374.5373,
      "train_tokens_per_second": 29182.031
    },
    {
      "epoch": 0.37575712007996337,
      "grad_norm": 1.4296875,
      "learning_rate": 3.482059637356124e-05,
      "loss": 1.1177041053771972,
      "num_input_tokens_seen": 3019452544,
      "step": 10620,
      "train_runtime": 103465.8853,
      "train_tokens_per_second": 29183.074
    },
    {
      "epoch": 0.37611094034369214,
      "grad_norm": 1.3984375,
      "learning_rate": 3.481215563061281e-05,
      "loss": 1.106947422027588,
      "num_input_tokens_seen": 3022247808,
      "step": 10630,
      "train_runtime": 103562.3545,
      "train_tokens_per_second": 29182.88
    },
    {
      "epoch": 0.37646476060742096,
      "grad_norm": 1.3984375,
      "learning_rate": 3.4803721022965785e-05,
      "loss": 1.126286506652832,
      "num_input_tokens_seen": 3025134272,
      "step": 10640,
      "train_runtime": 103661.2286,
      "train_tokens_per_second": 29182.89
    },
    {
      "epoch": 0.3768185808711497,
      "grad_norm": 1.4453125,
      "learning_rate": 3.479529254319117e-05,
      "loss": 1.1151983261108398,
      "num_input_tokens_seen": 3027994880,
      "step": 10650,
      "train_runtime": 103759.258,
      "train_tokens_per_second": 29182.889
    },
    {
      "epoch": 0.3771724011348785,
      "grad_norm": 1.421875,
      "learning_rate": 3.478687018387257e-05,
      "loss": 1.1072070121765136,
      "num_input_tokens_seen": 3030848064,
      "step": 10660,
      "train_runtime": 103855.3804,
      "train_tokens_per_second": 29183.351
    },
    {
      "epoch": 0.37752622139860725,
      "grad_norm": 1.390625,
      "learning_rate": 3.477845393760616e-05,
      "loss": 1.0979772567749024,
      "num_input_tokens_seen": 3033682752,
      "step": 10670,
      "train_runtime": 103953.7931,
      "train_tokens_per_second": 29182.992
    },
    {
      "epoch": 0.3778800416623361,
      "grad_norm": 1.421875,
      "learning_rate": 3.4770043797000614e-05,
      "loss": 1.1147751808166504,
      "num_input_tokens_seen": 3036544128,
      "step": 10680,
      "train_runtime": 104050.3975,
      "train_tokens_per_second": 29183.398
    },
    {
      "epoch": 0.37823386192606484,
      "grad_norm": 1.453125,
      "learning_rate": 3.4761639754677146e-05,
      "loss": 1.126236915588379,
      "num_input_tokens_seen": 3039454016,
      "step": 10690,
      "train_runtime": 104154.0514,
      "train_tokens_per_second": 29182.293
    },
    {
      "epoch": 0.3785876821897936,
      "grad_norm": 1.453125,
      "learning_rate": 3.4753241803269435e-05,
      "loss": 1.0952476501464843,
      "num_input_tokens_seen": 3042330880,
      "step": 10700,
      "train_runtime": 104253.2228,
      "train_tokens_per_second": 29182.128
    },
    {
      "epoch": 0.37894150245352237,
      "grad_norm": 1.515625,
      "learning_rate": 3.474484993542361e-05,
      "loss": 1.1179283142089844,
      "num_input_tokens_seen": 3045096960,
      "step": 10710,
      "train_runtime": 104346.4105,
      "train_tokens_per_second": 29182.575
    },
    {
      "epoch": 0.3792953227172512,
      "grad_norm": 1.4765625,
      "learning_rate": 3.473646414379822e-05,
      "loss": 1.1073570251464844,
      "num_input_tokens_seen": 3047948800,
      "step": 10720,
      "train_runtime": 104445.4612,
      "train_tokens_per_second": 29182.204
    },
    {
      "epoch": 0.37964914298097996,
      "grad_norm": 1.4375,
      "learning_rate": 3.472808442106422e-05,
      "loss": 1.10926513671875,
      "num_input_tokens_seen": 3050755584,
      "step": 10730,
      "train_runtime": 104541.3125,
      "train_tokens_per_second": 29182.297
    },
    {
      "epoch": 0.3800029632447087,
      "grad_norm": 1.4375,
      "learning_rate": 3.4719710759904936e-05,
      "loss": 1.1258193016052247,
      "num_input_tokens_seen": 3053615808,
      "step": 10740,
      "train_runtime": 104640.1521,
      "train_tokens_per_second": 29182.066
    },
    {
      "epoch": 0.3803567835084375,
      "grad_norm": 1.4140625,
      "learning_rate": 3.471134315301603e-05,
      "loss": 1.1104583740234375,
      "num_input_tokens_seen": 3056458816,
      "step": 10750,
      "train_runtime": 104738.2197,
      "train_tokens_per_second": 29181.886
    },
    {
      "epoch": 0.3807106037721663,
      "grad_norm": 1.3515625,
      "learning_rate": 3.470298159310549e-05,
      "loss": 1.1088730812072753,
      "num_input_tokens_seen": 3059267264,
      "step": 10760,
      "train_runtime": 104835.5516,
      "train_tokens_per_second": 29181.582
    },
    {
      "epoch": 0.3810644240358951,
      "grad_norm": 1.421875,
      "learning_rate": 3.4694626072893585e-05,
      "loss": 1.1143556594848634,
      "num_input_tokens_seen": 3062082304,
      "step": 10770,
      "train_runtime": 104931.0495,
      "train_tokens_per_second": 29181.852
    },
    {
      "epoch": 0.38141824429962384,
      "grad_norm": 1.453125,
      "learning_rate": 3.468627658511285e-05,
      "loss": 1.106454849243164,
      "num_input_tokens_seen": 3064864640,
      "step": 10780,
      "train_runtime": 105023.3036,
      "train_tokens_per_second": 29182.71
    },
    {
      "epoch": 0.3817720645633526,
      "grad_norm": 1.390625,
      "learning_rate": 3.467793312250806e-05,
      "loss": 1.1209445953369142,
      "num_input_tokens_seen": 3067711424,
      "step": 10790,
      "train_runtime": 105119.7186,
      "train_tokens_per_second": 29183.025
    },
    {
      "epoch": 0.38212588482708143,
      "grad_norm": 1.3984375,
      "learning_rate": 3.466959567783619e-05,
      "loss": 1.1158806800842285,
      "num_input_tokens_seen": 3070594560,
      "step": 10800,
      "train_runtime": 105218.3736,
      "train_tokens_per_second": 29183.064
    },
    {
      "epoch": 0.3824797050908102,
      "grad_norm": 1.3671875,
      "learning_rate": 3.466126424386642e-05,
      "loss": 1.1121633529663086,
      "num_input_tokens_seen": 3073427264,
      "step": 10810,
      "train_runtime": 105315.0952,
      "train_tokens_per_second": 29183.16
    },
    {
      "epoch": 0.38283352535453896,
      "grad_norm": 1.375,
      "learning_rate": 3.4652938813380056e-05,
      "loss": 1.100991916656494,
      "num_input_tokens_seen": 3076311168,
      "step": 10820,
      "train_runtime": 105412.7109,
      "train_tokens_per_second": 29183.494
    },
    {
      "epoch": 0.3831873456182677,
      "grad_norm": 1.4140625,
      "learning_rate": 3.464461937917057e-05,
      "loss": 1.1089619636535644,
      "num_input_tokens_seen": 3079126784,
      "step": 10830,
      "train_runtime": 105508.0077,
      "train_tokens_per_second": 29183.821
    },
    {
      "epoch": 0.3835411658819965,
      "grad_norm": 1.3984375,
      "learning_rate": 3.4636305934043525e-05,
      "loss": 1.1244887351989745,
      "num_input_tokens_seen": 3082002240,
      "step": 10840,
      "train_runtime": 105609.4925,
      "train_tokens_per_second": 29183.004
    },
    {
      "epoch": 0.3838949861457253,
      "grad_norm": 1.40625,
      "learning_rate": 3.4627998470816544e-05,
      "loss": 1.1102939605712892,
      "num_input_tokens_seen": 3084901440,
      "step": 10850,
      "train_runtime": 105706.2378,
      "train_tokens_per_second": 29183.722
    },
    {
      "epoch": 0.3842488064094541,
      "grad_norm": 1.3984375,
      "learning_rate": 3.4619696982319334e-05,
      "loss": 1.1122724533081054,
      "num_input_tokens_seen": 3087681536,
      "step": 10860,
      "train_runtime": 105800.493,
      "train_tokens_per_second": 29184.0
    },
    {
      "epoch": 0.38460262667318285,
      "grad_norm": 1.4296875,
      "learning_rate": 3.461140146139361e-05,
      "loss": 1.1118152618408204,
      "num_input_tokens_seen": 3090515008,
      "step": 10870,
      "train_runtime": 105897.9605,
      "train_tokens_per_second": 29183.895
    },
    {
      "epoch": 0.3849564469369116,
      "grad_norm": 1.4375,
      "learning_rate": 3.460311190089309e-05,
      "loss": 1.118225383758545,
      "num_input_tokens_seen": 3093318016,
      "step": 10880,
      "train_runtime": 105994.1743,
      "train_tokens_per_second": 29183.849
    },
    {
      "epoch": 0.38531026720064043,
      "grad_norm": 1.3671875,
      "learning_rate": 3.459482829368348e-05,
      "loss": 1.1051155090332032,
      "num_input_tokens_seen": 3096163776,
      "step": 10890,
      "train_runtime": 106091.6422,
      "train_tokens_per_second": 29183.861
    },
    {
      "epoch": 0.3856640874643692,
      "grad_norm": 1.4609375,
      "learning_rate": 3.4586550632642425e-05,
      "loss": 1.1158140182495118,
      "num_input_tokens_seen": 3099002176,
      "step": 10900,
      "train_runtime": 106188.8231,
      "train_tokens_per_second": 29183.883
    },
    {
      "epoch": 0.38601790772809796,
      "grad_norm": 1.4765625,
      "learning_rate": 3.457827891065949e-05,
      "loss": 1.1205942153930664,
      "num_input_tokens_seen": 3101874688,
      "step": 10910,
      "train_runtime": 106287.4492,
      "train_tokens_per_second": 29183.828
    },
    {
      "epoch": 0.38637172799182673,
      "grad_norm": 1.3984375,
      "learning_rate": 3.457001312063614e-05,
      "loss": 1.1110269546508789,
      "num_input_tokens_seen": 3104693824,
      "step": 10920,
      "train_runtime": 106382.5153,
      "train_tokens_per_second": 29184.249
    },
    {
      "epoch": 0.38672554825555555,
      "grad_norm": 1.34375,
      "learning_rate": 3.45617532554857e-05,
      "loss": 1.1043720245361328,
      "num_input_tokens_seen": 3107511360,
      "step": 10930,
      "train_runtime": 106480.3539,
      "train_tokens_per_second": 29183.894
    },
    {
      "epoch": 0.3870793685192843,
      "grad_norm": 1.546875,
      "learning_rate": 3.455349930813339e-05,
      "loss": 1.1182670593261719,
      "num_input_tokens_seen": 3110319744,
      "step": 10940,
      "train_runtime": 106574.8559,
      "train_tokens_per_second": 29184.367
    },
    {
      "epoch": 0.3874331887830131,
      "grad_norm": 1.359375,
      "learning_rate": 3.45452512715162e-05,
      "loss": 1.1050334930419923,
      "num_input_tokens_seen": 3113139328,
      "step": 10950,
      "train_runtime": 106672.0311,
      "train_tokens_per_second": 29184.213
    },
    {
      "epoch": 0.38778700904674185,
      "grad_norm": 1.421875,
      "learning_rate": 3.4537009138582935e-05,
      "loss": 1.1165643692016602,
      "num_input_tokens_seen": 3116035456,
      "step": 10960,
      "train_runtime": 106773.0437,
      "train_tokens_per_second": 29183.728
    },
    {
      "epoch": 0.38814082931047067,
      "grad_norm": 1.46875,
      "learning_rate": 3.4528772902294174e-05,
      "loss": 1.1053705215454102,
      "num_input_tokens_seen": 3118861248,
      "step": 10970,
      "train_runtime": 106866.9227,
      "train_tokens_per_second": 29184.533
    },
    {
      "epoch": 0.38849464957419944,
      "grad_norm": 1.390625,
      "learning_rate": 3.452054255562222e-05,
      "loss": 1.116770076751709,
      "num_input_tokens_seen": 3121694144,
      "step": 10980,
      "train_runtime": 106963.6725,
      "train_tokens_per_second": 29184.62
    },
    {
      "epoch": 0.3888484698379282,
      "grad_norm": 1.4296875,
      "learning_rate": 3.451231809155115e-05,
      "loss": 1.1107559204101562,
      "num_input_tokens_seen": 3124662464,
      "step": 10990,
      "train_runtime": 107073.9523,
      "train_tokens_per_second": 29182.284
    },
    {
      "epoch": 0.38920229010165697,
      "grad_norm": 1.4140625,
      "learning_rate": 3.450409950307666e-05,
      "loss": 1.113471508026123,
      "num_input_tokens_seen": 3127486208,
      "step": 11000,
      "train_runtime": 107171.0941,
      "train_tokens_per_second": 29182.18
    },
    {
      "epoch": 0.3895561103653858,
      "grad_norm": 1.4296875,
      "learning_rate": 3.449588678320619e-05,
      "loss": 1.1239524841308595,
      "num_input_tokens_seen": 3130333248,
      "step": 11010,
      "train_runtime": 107268.318,
      "train_tokens_per_second": 29182.272
    },
    {
      "epoch": 0.38990993062911455,
      "grad_norm": 1.4609375,
      "learning_rate": 3.4487679924958767e-05,
      "loss": 1.1235685348510742,
      "num_input_tokens_seen": 3133211840,
      "step": 11020,
      "train_runtime": 107368.3632,
      "train_tokens_per_second": 29181.891
    },
    {
      "epoch": 0.3902637508928433,
      "grad_norm": 1.4375,
      "learning_rate": 3.4479478921365076e-05,
      "loss": 1.1143548965454102,
      "num_input_tokens_seen": 3136050176,
      "step": 11030,
      "train_runtime": 107463.9093,
      "train_tokens_per_second": 29182.357
    },
    {
      "epoch": 0.3906175711565721,
      "grad_norm": 1.484375,
      "learning_rate": 3.447128376546738e-05,
      "loss": 1.1043270111083985,
      "num_input_tokens_seen": 3138931008,
      "step": 11040,
      "train_runtime": 107563.1158,
      "train_tokens_per_second": 29182.225
    },
    {
      "epoch": 0.3909713914203009,
      "grad_norm": 1.3828125,
      "learning_rate": 3.4463094450319505e-05,
      "loss": 1.1129372596740723,
      "num_input_tokens_seen": 3141796864,
      "step": 11050,
      "train_runtime": 107664.4772,
      "train_tokens_per_second": 29181.369
    },
    {
      "epoch": 0.3913252116840297,
      "grad_norm": 1.4140625,
      "learning_rate": 3.4454910968986855e-05,
      "loss": 1.1184050559997558,
      "num_input_tokens_seen": 3144613824,
      "step": 11060,
      "train_runtime": 107761.4763,
      "train_tokens_per_second": 29181.243
    },
    {
      "epoch": 0.39167903194775844,
      "grad_norm": 1.3828125,
      "learning_rate": 3.4446733314546336e-05,
      "loss": 1.1175203323364258,
      "num_input_tokens_seen": 3147476032,
      "step": 11070,
      "train_runtime": 107862.5838,
      "train_tokens_per_second": 29180.425
    },
    {
      "epoch": 0.3920328522114872,
      "grad_norm": 1.359375,
      "learning_rate": 3.443856148008633e-05,
      "loss": 1.104756736755371,
      "num_input_tokens_seen": 3150305600,
      "step": 11080,
      "train_runtime": 107958.7977,
      "train_tokens_per_second": 29180.629
    },
    {
      "epoch": 0.39238667247521597,
      "grad_norm": 1.4609375,
      "learning_rate": 3.443039545870672e-05,
      "loss": 1.1070931434631348,
      "num_input_tokens_seen": 3153158784,
      "step": 11090,
      "train_runtime": 108055.595,
      "train_tokens_per_second": 29180.893
    },
    {
      "epoch": 0.3927404927389448,
      "grad_norm": 1.4609375,
      "learning_rate": 3.442223524351883e-05,
      "loss": 1.1171310424804688,
      "num_input_tokens_seen": 3156049984,
      "step": 11100,
      "train_runtime": 108157.7549,
      "train_tokens_per_second": 29180.062
    },
    {
      "epoch": 0.39309431300267356,
      "grad_norm": 1.4453125,
      "learning_rate": 3.44140808276454e-05,
      "loss": 1.1156272888183594,
      "num_input_tokens_seen": 3158898944,
      "step": 11110,
      "train_runtime": 108255.6249,
      "train_tokens_per_second": 29179.998
    },
    {
      "epoch": 0.3934481332664023,
      "grad_norm": 1.4453125,
      "learning_rate": 3.4405932204220575e-05,
      "loss": 1.0975558280944824,
      "num_input_tokens_seen": 3161758976,
      "step": 11120,
      "train_runtime": 108353.6674,
      "train_tokens_per_second": 29179.99
    },
    {
      "epoch": 0.3938019535301311,
      "grad_norm": 1.453125,
      "learning_rate": 3.4397789366389876e-05,
      "loss": 1.113433265686035,
      "num_input_tokens_seen": 3164592256,
      "step": 11130,
      "train_runtime": 108448.5117,
      "train_tokens_per_second": 29180.596
    },
    {
      "epoch": 0.3941557737938599,
      "grad_norm": 1.4296875,
      "learning_rate": 3.438965230731016e-05,
      "loss": 1.1086791038513184,
      "num_input_tokens_seen": 3167391680,
      "step": 11140,
      "train_runtime": 108541.7124,
      "train_tokens_per_second": 29181.331
    },
    {
      "epoch": 0.3945095940575887,
      "grad_norm": 1.453125,
      "learning_rate": 3.438152102014964e-05,
      "loss": 1.1120376586914062,
      "num_input_tokens_seen": 3170208256,
      "step": 11150,
      "train_runtime": 108638.0519,
      "train_tokens_per_second": 29181.38
    },
    {
      "epoch": 0.39486341432131744,
      "grad_norm": 1.453125,
      "learning_rate": 3.437339549808778e-05,
      "loss": 1.1136640548706054,
      "num_input_tokens_seen": 3173073088,
      "step": 11160,
      "train_runtime": 108737.0464,
      "train_tokens_per_second": 29181.159
    },
    {
      "epoch": 0.3952172345850462,
      "grad_norm": 1.40625,
      "learning_rate": 3.43652757343154e-05,
      "loss": 1.1128786087036133,
      "num_input_tokens_seen": 3175926528,
      "step": 11170,
      "train_runtime": 108834.7908,
      "train_tokens_per_second": 29181.17
    },
    {
      "epoch": 0.39557105484877503,
      "grad_norm": 1.359375,
      "learning_rate": 3.435716172203449e-05,
      "loss": 1.1115937232971191,
      "num_input_tokens_seen": 3178719680,
      "step": 11180,
      "train_runtime": 108928.2575,
      "train_tokens_per_second": 29181.773
    },
    {
      "epoch": 0.3959248751125038,
      "grad_norm": 1.484375,
      "learning_rate": 3.434905345445833e-05,
      "loss": 1.1214506149291992,
      "num_input_tokens_seen": 3181518912,
      "step": 11190,
      "train_runtime": 109024.9094,
      "train_tokens_per_second": 29181.578
    },
    {
      "epoch": 0.39627869537623256,
      "grad_norm": 1.4375,
      "learning_rate": 3.4340950924811374e-05,
      "loss": 1.1053207397460938,
      "num_input_tokens_seen": 3184423232,
      "step": 11200,
      "train_runtime": 109122.9601,
      "train_tokens_per_second": 29181.973
    },
    {
      "epoch": 0.3966325156399613,
      "grad_norm": 1.4140625,
      "learning_rate": 3.433285412632927e-05,
      "loss": 1.1215445518493652,
      "num_input_tokens_seen": 3187193344,
      "step": 11210,
      "train_runtime": 109214.2455,
      "train_tokens_per_second": 29182.945
    },
    {
      "epoch": 0.39698633590369015,
      "grad_norm": 1.484375,
      "learning_rate": 3.4324763052258835e-05,
      "loss": 1.1018836975097657,
      "num_input_tokens_seen": 3190018944,
      "step": 11220,
      "train_runtime": 109308.5314,
      "train_tokens_per_second": 29183.623
    },
    {
      "epoch": 0.3973401561674189,
      "grad_norm": 1.4140625,
      "learning_rate": 3.4316677695858003e-05,
      "loss": 1.1190860748291016,
      "num_input_tokens_seen": 3192876288,
      "step": 11230,
      "train_runtime": 109408.6708,
      "train_tokens_per_second": 29183.028
    },
    {
      "epoch": 0.3976939764311477,
      "grad_norm": 1.40625,
      "learning_rate": 3.430859805039583e-05,
      "loss": 1.1159124374389648,
      "num_input_tokens_seen": 3195720640,
      "step": 11240,
      "train_runtime": 109507.207,
      "train_tokens_per_second": 29182.743
    },
    {
      "epoch": 0.39804779669487644,
      "grad_norm": 1.484375,
      "learning_rate": 3.430052410915246e-05,
      "loss": 1.104234218597412,
      "num_input_tokens_seen": 3198522880,
      "step": 11250,
      "train_runtime": 109600.578,
      "train_tokens_per_second": 29183.449
    },
    {
      "epoch": 0.39840161695860526,
      "grad_norm": 1.3828125,
      "learning_rate": 3.4292455865419086e-05,
      "loss": 1.1040767669677733,
      "num_input_tokens_seen": 3201374656,
      "step": 11260,
      "train_runtime": 109698.3929,
      "train_tokens_per_second": 29183.423
    },
    {
      "epoch": 0.39875543722233403,
      "grad_norm": 1.46875,
      "learning_rate": 3.4284393312497973e-05,
      "loss": 1.101394271850586,
      "num_input_tokens_seen": 3204221120,
      "step": 11270,
      "train_runtime": 109800.7182,
      "train_tokens_per_second": 29182.151
    },
    {
      "epoch": 0.3991092574860628,
      "grad_norm": 1.3984375,
      "learning_rate": 3.427633644370238e-05,
      "loss": 1.112740707397461,
      "num_input_tokens_seen": 3207060992,
      "step": 11280,
      "train_runtime": 109895.8818,
      "train_tokens_per_second": 29182.722
    },
    {
      "epoch": 0.39946307774979156,
      "grad_norm": 1.4296875,
      "learning_rate": 3.4268285252356564e-05,
      "loss": 1.1246959686279296,
      "num_input_tokens_seen": 3209919680,
      "step": 11290,
      "train_runtime": 109993.9784,
      "train_tokens_per_second": 29182.686
    },
    {
      "epoch": 0.3998168980135204,
      "grad_norm": 1.4609375,
      "learning_rate": 3.426023973179575e-05,
      "loss": 1.1174297332763672,
      "num_input_tokens_seen": 3212786368,
      "step": 11300,
      "train_runtime": 110095.7435,
      "train_tokens_per_second": 29181.749
    },
    {
      "epoch": 0.40017071827724915,
      "grad_norm": 1.390625,
      "learning_rate": 3.425219987536614e-05,
      "loss": 1.1124868392944336,
      "num_input_tokens_seen": 3215634944,
      "step": 11310,
      "train_runtime": 110192.6136,
      "train_tokens_per_second": 29181.946
    },
    {
      "epoch": 0.4005245385409779,
      "grad_norm": 1.3984375,
      "learning_rate": 3.4244165676424815e-05,
      "loss": 1.1201066970825195,
      "num_input_tokens_seen": 3218476672,
      "step": 11320,
      "train_runtime": 110287.328,
      "train_tokens_per_second": 29182.652
    },
    {
      "epoch": 0.4008783588047067,
      "grad_norm": 1.3984375,
      "learning_rate": 3.423613712833979e-05,
      "loss": 1.1139363288879394,
      "num_input_tokens_seen": 3221314432,
      "step": 11330,
      "train_runtime": 110384.8241,
      "train_tokens_per_second": 29182.584
    },
    {
      "epoch": 0.40123217906843545,
      "grad_norm": 1.4921875,
      "learning_rate": 3.422811422448995e-05,
      "loss": 1.109142780303955,
      "num_input_tokens_seen": 3224176704,
      "step": 11340,
      "train_runtime": 110484.0339,
      "train_tokens_per_second": 29182.286
    },
    {
      "epoch": 0.40158599933216427,
      "grad_norm": 1.5,
      "learning_rate": 3.422009695826503e-05,
      "loss": 1.1031388282775878,
      "num_input_tokens_seen": 3226992384,
      "step": 11350,
      "train_runtime": 110580.8312,
      "train_tokens_per_second": 29182.204
    },
    {
      "epoch": 0.40193981959589303,
      "grad_norm": 1.4453125,
      "learning_rate": 3.4212085323065626e-05,
      "loss": 1.1194723129272461,
      "num_input_tokens_seen": 3229866496,
      "step": 11360,
      "train_runtime": 110680.3498,
      "train_tokens_per_second": 29181.932
    },
    {
      "epoch": 0.4022936398596218,
      "grad_norm": 1.4140625,
      "learning_rate": 3.4204079312303103e-05,
      "loss": 1.1056083679199218,
      "num_input_tokens_seen": 3232696320,
      "step": 11370,
      "train_runtime": 110773.0782,
      "train_tokens_per_second": 29183.05
    },
    {
      "epoch": 0.40264746012335056,
      "grad_norm": 1.3984375,
      "learning_rate": 3.419607891939964e-05,
      "loss": 1.1169441223144532,
      "num_input_tokens_seen": 3235577024,
      "step": 11380,
      "train_runtime": 110872.7255,
      "train_tokens_per_second": 29182.804
    },
    {
      "epoch": 0.4030012803870794,
      "grad_norm": 1.421875,
      "learning_rate": 3.4188084137788166e-05,
      "loss": 1.1078732490539551,
      "num_input_tokens_seen": 3238419904,
      "step": 11390,
      "train_runtime": 110969.1995,
      "train_tokens_per_second": 29183.052
    },
    {
      "epoch": 0.40335510065080815,
      "grad_norm": 1.4296875,
      "learning_rate": 3.418009496091238e-05,
      "loss": 1.1268056869506835,
      "num_input_tokens_seen": 3241216512,
      "step": 11400,
      "train_runtime": 111062.2152,
      "train_tokens_per_second": 29183.791
    },
    {
      "epoch": 0.4037089209145369,
      "grad_norm": 1.546875,
      "learning_rate": 3.417211138222666e-05,
      "loss": 1.1081307411193848,
      "num_input_tokens_seen": 3244043904,
      "step": 11410,
      "train_runtime": 111158.0072,
      "train_tokens_per_second": 29184.078
    },
    {
      "epoch": 0.4040627411782657,
      "grad_norm": 1.390625,
      "learning_rate": 3.416413339519612e-05,
      "loss": 1.109385871887207,
      "num_input_tokens_seen": 3246944704,
      "step": 11420,
      "train_runtime": 111261.0448,
      "train_tokens_per_second": 29183.123
    },
    {
      "epoch": 0.4044165614419945,
      "grad_norm": 1.421875,
      "learning_rate": 3.4156160993296524e-05,
      "loss": 1.1223718643188476,
      "num_input_tokens_seen": 3249768064,
      "step": 11430,
      "train_runtime": 111357.2481,
      "train_tokens_per_second": 29183.265
    },
    {
      "epoch": 0.40477038170572327,
      "grad_norm": 1.4453125,
      "learning_rate": 3.4148194170014295e-05,
      "loss": 1.121194076538086,
      "num_input_tokens_seen": 3252589824,
      "step": 11440,
      "train_runtime": 111453.6271,
      "train_tokens_per_second": 29183.347
    },
    {
      "epoch": 0.40512420196945204,
      "grad_norm": 1.5546875,
      "learning_rate": 3.4140232918846484e-05,
      "loss": 1.1094854354858399,
      "num_input_tokens_seen": 3255463808,
      "step": 11450,
      "train_runtime": 111551.4368,
      "train_tokens_per_second": 29183.522
    },
    {
      "epoch": 0.4054780222331808,
      "grad_norm": 1.4140625,
      "learning_rate": 3.4132277233300753e-05,
      "loss": 1.088420295715332,
      "num_input_tokens_seen": 3258240768,
      "step": 11460,
      "train_runtime": 111642.6468,
      "train_tokens_per_second": 29184.553
    },
    {
      "epoch": 0.4058318424969096,
      "grad_norm": 1.4453125,
      "learning_rate": 3.4124327106895356e-05,
      "loss": 1.1078187942504882,
      "num_input_tokens_seen": 3261076992,
      "step": 11470,
      "train_runtime": 111739.1433,
      "train_tokens_per_second": 29184.732
    },
    {
      "epoch": 0.4061856627606384,
      "grad_norm": 1.40625,
      "learning_rate": 3.4116382533159097e-05,
      "loss": 1.1171884536743164,
      "num_input_tokens_seen": 3263949568,
      "step": 11480,
      "train_runtime": 111837.8026,
      "train_tokens_per_second": 29184.672
    },
    {
      "epoch": 0.40653948302436715,
      "grad_norm": 1.390625,
      "learning_rate": 3.4108443505631335e-05,
      "loss": 1.1110849380493164,
      "num_input_tokens_seen": 3266796544,
      "step": 11490,
      "train_runtime": 111935.1078,
      "train_tokens_per_second": 29184.736
    },
    {
      "epoch": 0.4068933032880959,
      "grad_norm": 1.4453125,
      "learning_rate": 3.410051001786192e-05,
      "loss": 1.1107412338256837,
      "num_input_tokens_seen": 3269649216,
      "step": 11500,
      "train_runtime": 112035.4055,
      "train_tokens_per_second": 29184.071
    },
    {
      "epoch": 0.40724712355182474,
      "grad_norm": 1.421875,
      "learning_rate": 3.409258206341124e-05,
      "loss": 1.110093116760254,
      "num_input_tokens_seen": 3272512320,
      "step": 11510,
      "train_runtime": 112134.7425,
      "train_tokens_per_second": 29183.75
    },
    {
      "epoch": 0.4076009438155535,
      "grad_norm": 1.4296875,
      "learning_rate": 3.4084659635850134e-05,
      "loss": 1.112485980987549,
      "num_input_tokens_seen": 3275336384,
      "step": 11520,
      "train_runtime": 112231.8412,
      "train_tokens_per_second": 29183.664
    },
    {
      "epoch": 0.4079547640792823,
      "grad_norm": 1.4453125,
      "learning_rate": 3.40767427287599e-05,
      "loss": 1.1065649032592773,
      "num_input_tokens_seen": 3278275648,
      "step": 11530,
      "train_runtime": 112334.4729,
      "train_tokens_per_second": 29183.167
    },
    {
      "epoch": 0.40830858434301104,
      "grad_norm": 1.3984375,
      "learning_rate": 3.406883133573224e-05,
      "loss": 1.0992963790893555,
      "num_input_tokens_seen": 3281109184,
      "step": 11540,
      "train_runtime": 112432.9488,
      "train_tokens_per_second": 29182.808
    },
    {
      "epoch": 0.40866240460673986,
      "grad_norm": 1.421875,
      "learning_rate": 3.406092545036932e-05,
      "loss": 1.1040657043457032,
      "num_input_tokens_seen": 3283960064,
      "step": 11550,
      "train_runtime": 112529.3883,
      "train_tokens_per_second": 29183.133
    },
    {
      "epoch": 0.4090162248704686,
      "grad_norm": 1.375,
      "learning_rate": 3.405302506628365e-05,
      "loss": 1.1051065444946289,
      "num_input_tokens_seen": 3286808128,
      "step": 11560,
      "train_runtime": 112627.3287,
      "train_tokens_per_second": 29183.043
    },
    {
      "epoch": 0.4093700451341974,
      "grad_norm": 1.453125,
      "learning_rate": 3.404513017709813e-05,
      "loss": 1.1185232162475587,
      "num_input_tokens_seen": 3289673792,
      "step": 11570,
      "train_runtime": 112726.0757,
      "train_tokens_per_second": 29182.9
    },
    {
      "epoch": 0.40972386539792616,
      "grad_norm": 1.5,
      "learning_rate": 3.403724077644598e-05,
      "loss": 1.0939390182495117,
      "num_input_tokens_seen": 3292509696,
      "step": 11580,
      "train_runtime": 112821.094,
      "train_tokens_per_second": 29183.458
    },
    {
      "epoch": 0.4100776856616549,
      "grad_norm": 1.40625,
      "learning_rate": 3.402935685797077e-05,
      "loss": 1.1304559707641602,
      "num_input_tokens_seen": 3295443840,
      "step": 11590,
      "train_runtime": 112925.871,
      "train_tokens_per_second": 29182.364
    },
    {
      "epoch": 0.41043150592538374,
      "grad_norm": 1.4296875,
      "learning_rate": 3.4021478415326355e-05,
      "loss": 1.1220402717590332,
      "num_input_tokens_seen": 3298356224,
      "step": 11600,
      "train_runtime": 113029.5744,
      "train_tokens_per_second": 29181.356
    },
    {
      "epoch": 0.4107853261891125,
      "grad_norm": 1.4609375,
      "learning_rate": 3.401360544217687e-05,
      "loss": 1.110680389404297,
      "num_input_tokens_seen": 3301193152,
      "step": 11610,
      "train_runtime": 113126.6515,
      "train_tokens_per_second": 29181.392
    },
    {
      "epoch": 0.4111391464528413,
      "grad_norm": 1.421875,
      "learning_rate": 3.400573793219672e-05,
      "loss": 1.1259288787841797,
      "num_input_tokens_seen": 3304026112,
      "step": 11620,
      "train_runtime": 113223.8508,
      "train_tokens_per_second": 29181.361
    },
    {
      "epoch": 0.41149296671657004,
      "grad_norm": 1.390625,
      "learning_rate": 3.3997875879070546e-05,
      "loss": 1.1169405937194825,
      "num_input_tokens_seen": 3306898304,
      "step": 11630,
      "train_runtime": 113321.0037,
      "train_tokens_per_second": 29181.689
    },
    {
      "epoch": 0.41184678698029886,
      "grad_norm": 1.375,
      "learning_rate": 3.399001927649318e-05,
      "loss": 1.113192653656006,
      "num_input_tokens_seen": 3309742208,
      "step": 11640,
      "train_runtime": 113420.4835,
      "train_tokens_per_second": 29181.168
    },
    {
      "epoch": 0.41220060724402763,
      "grad_norm": 1.4140625,
      "learning_rate": 3.398216811816968e-05,
      "loss": 1.1123380661010742,
      "num_input_tokens_seen": 3312578688,
      "step": 11650,
      "train_runtime": 113516.7655,
      "train_tokens_per_second": 29181.405
    },
    {
      "epoch": 0.4125544275077564,
      "grad_norm": 1.4453125,
      "learning_rate": 3.397432239781527e-05,
      "loss": 1.10406494140625,
      "num_input_tokens_seen": 3315393024,
      "step": 11660,
      "train_runtime": 113613.3214,
      "train_tokens_per_second": 29181.376
    },
    {
      "epoch": 0.41290824777148516,
      "grad_norm": 1.3828125,
      "learning_rate": 3.396648210915531e-05,
      "loss": 1.1108510971069336,
      "num_input_tokens_seen": 3318191872,
      "step": 11670,
      "train_runtime": 113711.055,
      "train_tokens_per_second": 29180.908
    },
    {
      "epoch": 0.413262068035214,
      "grad_norm": 1.4140625,
      "learning_rate": 3.3958647245925315e-05,
      "loss": 1.1249521255493165,
      "num_input_tokens_seen": 3321021888,
      "step": 11680,
      "train_runtime": 113809.5832,
      "train_tokens_per_second": 29180.512
    },
    {
      "epoch": 0.41361588829894275,
      "grad_norm": 1.3984375,
      "learning_rate": 3.3950817801870885e-05,
      "loss": 1.1151761054992675,
      "num_input_tokens_seen": 3323904960,
      "step": 11690,
      "train_runtime": 113911.4632,
      "train_tokens_per_second": 29179.723
    },
    {
      "epoch": 0.4139697085626715,
      "grad_norm": 1.421875,
      "learning_rate": 3.3942993770747735e-05,
      "loss": 1.1033821105957031,
      "num_input_tokens_seen": 3326796480,
      "step": 11700,
      "train_runtime": 114009.9968,
      "train_tokens_per_second": 29179.866
    },
    {
      "epoch": 0.4143235288264003,
      "grad_norm": 1.390625,
      "learning_rate": 3.3935175146321626e-05,
      "loss": 1.1209312438964845,
      "num_input_tokens_seen": 3329629056,
      "step": 11710,
      "train_runtime": 114106.7787,
      "train_tokens_per_second": 29179.941
    },
    {
      "epoch": 0.4146773490901291,
      "grad_norm": 1.4453125,
      "learning_rate": 3.392736192236839e-05,
      "loss": 1.1134897232055665,
      "num_input_tokens_seen": 3332476864,
      "step": 11720,
      "train_runtime": 114202.394,
      "train_tokens_per_second": 29180.447
    },
    {
      "epoch": 0.41503116935385787,
      "grad_norm": 1.421875,
      "learning_rate": 3.391955409267387e-05,
      "loss": 1.0991153717041016,
      "num_input_tokens_seen": 3335266304,
      "step": 11730,
      "train_runtime": 114295.592,
      "train_tokens_per_second": 29181.058
    },
    {
      "epoch": 0.41538498961758663,
      "grad_norm": 1.359375,
      "learning_rate": 3.3911751651033896e-05,
      "loss": 1.1115594863891602,
      "num_input_tokens_seen": 3338176256,
      "step": 11740,
      "train_runtime": 114398.5276,
      "train_tokens_per_second": 29180.238
    },
    {
      "epoch": 0.4157388098813154,
      "grad_norm": 1.4375,
      "learning_rate": 3.3903954591254334e-05,
      "loss": 1.1000202178955079,
      "num_input_tokens_seen": 3341021696,
      "step": 11750,
      "train_runtime": 114496.1818,
      "train_tokens_per_second": 29180.202
    },
    {
      "epoch": 0.4160926301450442,
      "grad_norm": 1.4453125,
      "learning_rate": 3.389616290715097e-05,
      "loss": 1.1059999465942383,
      "num_input_tokens_seen": 3343843200,
      "step": 11760,
      "train_runtime": 114593.8566,
      "train_tokens_per_second": 29179.952
    },
    {
      "epoch": 0.416446450408773,
      "grad_norm": 1.40625,
      "learning_rate": 3.388837659254955e-05,
      "loss": 1.1151594161987304,
      "num_input_tokens_seen": 3346653568,
      "step": 11770,
      "train_runtime": 114688.3758,
      "train_tokens_per_second": 29180.408
    },
    {
      "epoch": 0.41680027067250175,
      "grad_norm": 1.4296875,
      "learning_rate": 3.3880595641285746e-05,
      "loss": 1.1014064788818358,
      "num_input_tokens_seen": 3349494080,
      "step": 11780,
      "train_runtime": 114784.602,
      "train_tokens_per_second": 29180.692
    },
    {
      "epoch": 0.4171540909362305,
      "grad_norm": 1.40625,
      "learning_rate": 3.387282004720513e-05,
      "loss": 1.1034460067749023,
      "num_input_tokens_seen": 3352347968,
      "step": 11790,
      "train_runtime": 114882.7868,
      "train_tokens_per_second": 29180.594
    },
    {
      "epoch": 0.41750791119995934,
      "grad_norm": 1.3984375,
      "learning_rate": 3.386504980416316e-05,
      "loss": 1.1088354110717773,
      "num_input_tokens_seen": 3355214848,
      "step": 11800,
      "train_runtime": 114980.2265,
      "train_tokens_per_second": 29180.799
    },
    {
      "epoch": 0.4178617314636881,
      "grad_norm": 1.3671875,
      "learning_rate": 3.385728490602515e-05,
      "loss": 1.100706195831299,
      "num_input_tokens_seen": 3358055872,
      "step": 11810,
      "train_runtime": 115076.5158,
      "train_tokens_per_second": 29181.07
    },
    {
      "epoch": 0.41821555172741687,
      "grad_norm": 1.3984375,
      "learning_rate": 3.384952534666625e-05,
      "loss": 1.0944582939147949,
      "num_input_tokens_seen": 3360913728,
      "step": 11820,
      "train_runtime": 115174.112,
      "train_tokens_per_second": 29181.156
    },
    {
      "epoch": 0.41856937199114563,
      "grad_norm": 1.4609375,
      "learning_rate": 3.3841771119971455e-05,
      "loss": 1.111971092224121,
      "num_input_tokens_seen": 3363813568,
      "step": 11830,
      "train_runtime": 115276.4956,
      "train_tokens_per_second": 29180.394
    },
    {
      "epoch": 0.41892319225487445,
      "grad_norm": 1.4296875,
      "learning_rate": 3.383402221983554e-05,
      "loss": 1.1079582214355468,
      "num_input_tokens_seen": 3366657472,
      "step": 11840,
      "train_runtime": 115376.0608,
      "train_tokens_per_second": 29179.861
    },
    {
      "epoch": 0.4192770125186032,
      "grad_norm": 1.4375,
      "learning_rate": 3.3826278640163064e-05,
      "loss": 1.106375026702881,
      "num_input_tokens_seen": 3369497024,
      "step": 11850,
      "train_runtime": 115473.2668,
      "train_tokens_per_second": 29179.888
    },
    {
      "epoch": 0.419630832782332,
      "grad_norm": 1.484375,
      "learning_rate": 3.3818540374868354e-05,
      "loss": 1.093511199951172,
      "num_input_tokens_seen": 3372334208,
      "step": 11860,
      "train_runtime": 115569.4025,
      "train_tokens_per_second": 29180.165
    },
    {
      "epoch": 0.41998465304606075,
      "grad_norm": 1.4140625,
      "learning_rate": 3.381080741787547e-05,
      "loss": 1.119515323638916,
      "num_input_tokens_seen": 3375107712,
      "step": 11870,
      "train_runtime": 115662.963,
      "train_tokens_per_second": 29180.54
    },
    {
      "epoch": 0.4203384733097895,
      "grad_norm": 1.40625,
      "learning_rate": 3.38030797631182e-05,
      "loss": 1.1166337966918944,
      "num_input_tokens_seen": 3377940096,
      "step": 11880,
      "train_runtime": 115758.0986,
      "train_tokens_per_second": 29181.026
    },
    {
      "epoch": 0.42069229357351834,
      "grad_norm": 1.453125,
      "learning_rate": 3.379535740454003e-05,
      "loss": 1.0954187393188477,
      "num_input_tokens_seen": 3380774976,
      "step": 11890,
      "train_runtime": 115855.3595,
      "train_tokens_per_second": 29180.998
    },
    {
      "epoch": 0.4210461138372471,
      "grad_norm": 1.3984375,
      "learning_rate": 3.3787640336094126e-05,
      "loss": 1.1123652458190918,
      "num_input_tokens_seen": 3383618432,
      "step": 11900,
      "train_runtime": 115955.4603,
      "train_tokens_per_second": 29180.329
    },
    {
      "epoch": 0.42139993410097587,
      "grad_norm": 1.5,
      "learning_rate": 3.3779928551743325e-05,
      "loss": 1.0995706558227538,
      "num_input_tokens_seen": 3386487296,
      "step": 11910,
      "train_runtime": 116054.4774,
      "train_tokens_per_second": 29180.152
    },
    {
      "epoch": 0.42175375436470464,
      "grad_norm": 1.40625,
      "learning_rate": 3.3772222045460084e-05,
      "loss": 1.106417465209961,
      "num_input_tokens_seen": 3389325760,
      "step": 11920,
      "train_runtime": 116152.1057,
      "train_tokens_per_second": 29180.063
    },
    {
      "epoch": 0.42210757462843346,
      "grad_norm": 1.40625,
      "learning_rate": 3.37645208112265e-05,
      "loss": 1.1005504608154297,
      "num_input_tokens_seen": 3392209920,
      "step": 11930,
      "train_runtime": 116253.6662,
      "train_tokens_per_second": 29179.38
    },
    {
      "epoch": 0.4224613948921622,
      "grad_norm": 1.421875,
      "learning_rate": 3.3756824843034255e-05,
      "loss": 1.1013697624206542,
      "num_input_tokens_seen": 3395060672,
      "step": 11940,
      "train_runtime": 116349.4207,
      "train_tokens_per_second": 29179.867
    },
    {
      "epoch": 0.422815215155891,
      "grad_norm": 1.5390625,
      "learning_rate": 3.374913413488464e-05,
      "loss": 1.0898906707763671,
      "num_input_tokens_seen": 3397972864,
      "step": 11950,
      "train_runtime": 116451.2907,
      "train_tokens_per_second": 29179.349
    },
    {
      "epoch": 0.42316903541961975,
      "grad_norm": 1.453125,
      "learning_rate": 3.374144868078848e-05,
      "loss": 1.1230120658874512,
      "num_input_tokens_seen": 3400848320,
      "step": 11960,
      "train_runtime": 116552.5891,
      "train_tokens_per_second": 29178.66
    },
    {
      "epoch": 0.4235228556833486,
      "grad_norm": 1.421875,
      "learning_rate": 3.373376847476615e-05,
      "loss": 1.1154045104980468,
      "num_input_tokens_seen": 3403706240,
      "step": 11970,
      "train_runtime": 116652.2168,
      "train_tokens_per_second": 29178.239
    },
    {
      "epoch": 0.42387667594707734,
      "grad_norm": 1.375,
      "learning_rate": 3.3726093510847566e-05,
      "loss": 1.108010196685791,
      "num_input_tokens_seen": 3406595200,
      "step": 11980,
      "train_runtime": 116750.1437,
      "train_tokens_per_second": 29178.51
    },
    {
      "epoch": 0.4242304962108061,
      "grad_norm": 1.4453125,
      "learning_rate": 3.371842378307212e-05,
      "loss": 1.1087597846984862,
      "num_input_tokens_seen": 3409425088,
      "step": 11990,
      "train_runtime": 116845.3764,
      "train_tokens_per_second": 29178.947
    },
    {
      "epoch": 0.4245843164745349,
      "grad_norm": 1.375,
      "learning_rate": 3.371075928548872e-05,
      "loss": 1.1004678726196289,
      "num_input_tokens_seen": 3412251712,
      "step": 12000,
      "train_runtime": 116940.6255,
      "train_tokens_per_second": 29179.352
    },
    {
      "epoch": 0.4249381367382637,
      "grad_norm": 1.40625,
      "learning_rate": 3.37031000121557e-05,
      "loss": 1.1028223037719727,
      "num_input_tokens_seen": 3415124224,
      "step": 12010,
      "train_runtime": 117040.982,
      "train_tokens_per_second": 29178.875
    },
    {
      "epoch": 0.42529195700199246,
      "grad_norm": 1.34375,
      "learning_rate": 3.369544595714088e-05,
      "loss": 1.1159469604492187,
      "num_input_tokens_seen": 3417996992,
      "step": 12020,
      "train_runtime": 117138.9986,
      "train_tokens_per_second": 29178.984
    },
    {
      "epoch": 0.4256457772657212,
      "grad_norm": 1.5,
      "learning_rate": 3.368779711452148e-05,
      "loss": 1.1111854553222655,
      "num_input_tokens_seen": 3420820992,
      "step": 12030,
      "train_runtime": 117236.6156,
      "train_tokens_per_second": 29178.776
    },
    {
      "epoch": 0.42599959752945,
      "grad_norm": 1.4453125,
      "learning_rate": 3.368015347838413e-05,
      "loss": 1.107831859588623,
      "num_input_tokens_seen": 3423679168,
      "step": 12040,
      "train_runtime": 117333.9721,
      "train_tokens_per_second": 29178.925
    },
    {
      "epoch": 0.4263534177931788,
      "grad_norm": 1.515625,
      "learning_rate": 3.3672515042824855e-05,
      "loss": 1.1108792304992676,
      "num_input_tokens_seen": 3426460544,
      "step": 12050,
      "train_runtime": 117427.5155,
      "train_tokens_per_second": 29179.367
    },
    {
      "epoch": 0.4267072380569076,
      "grad_norm": 1.390625,
      "learning_rate": 3.366488180194904e-05,
      "loss": 1.1164531707763672,
      "num_input_tokens_seen": 3429307456,
      "step": 12060,
      "train_runtime": 117527.3214,
      "train_tokens_per_second": 29178.811
    },
    {
      "epoch": 0.42706105832063634,
      "grad_norm": 1.453125,
      "learning_rate": 3.365725374987143e-05,
      "loss": 1.1068065643310547,
      "num_input_tokens_seen": 3432160064,
      "step": 12070,
      "train_runtime": 117626.5912,
      "train_tokens_per_second": 29178.437
    },
    {
      "epoch": 0.4274148785843651,
      "grad_norm": 1.3828125,
      "learning_rate": 3.36496308807161e-05,
      "loss": 1.1161949157714843,
      "num_input_tokens_seen": 3434977472,
      "step": 12080,
      "train_runtime": 117723.264,
      "train_tokens_per_second": 29178.408
    },
    {
      "epoch": 0.42776869884809393,
      "grad_norm": 1.421875,
      "learning_rate": 3.3642013188616426e-05,
      "loss": 1.096306324005127,
      "num_input_tokens_seen": 3437811840,
      "step": 12090,
      "train_runtime": 117819.2614,
      "train_tokens_per_second": 29178.691
    },
    {
      "epoch": 0.4281225191118227,
      "grad_norm": 1.4921875,
      "learning_rate": 3.3634400667715074e-05,
      "loss": 1.1094569206237792,
      "num_input_tokens_seen": 3440651072,
      "step": 12100,
      "train_runtime": 117915.9225,
      "train_tokens_per_second": 29178.85
    },
    {
      "epoch": 0.42847633937555146,
      "grad_norm": 1.484375,
      "learning_rate": 3.3626793312164013e-05,
      "loss": 1.1037714958190918,
      "num_input_tokens_seen": 3443467200,
      "step": 12110,
      "train_runtime": 118012.8431,
      "train_tokens_per_second": 29178.75
    },
    {
      "epoch": 0.42883015963928023,
      "grad_norm": 1.453125,
      "learning_rate": 3.361919111612443e-05,
      "loss": 1.1099245071411132,
      "num_input_tokens_seen": 3446304064,
      "step": 12120,
      "train_runtime": 118111.6404,
      "train_tokens_per_second": 29178.361
    },
    {
      "epoch": 0.429183979903009,
      "grad_norm": 1.4375,
      "learning_rate": 3.361159407376678e-05,
      "loss": 1.1102795600891113,
      "num_input_tokens_seen": 3449141056,
      "step": 12130,
      "train_runtime": 118208.4289,
      "train_tokens_per_second": 29178.47
    },
    {
      "epoch": 0.4295378001667378,
      "grad_norm": 1.390625,
      "learning_rate": 3.3604002179270685e-05,
      "loss": 1.1166166305541991,
      "num_input_tokens_seen": 3451978496,
      "step": 12140,
      "train_runtime": 118305.8349,
      "train_tokens_per_second": 29178.43
    },
    {
      "epoch": 0.4298916204304666,
      "grad_norm": 1.421875,
      "learning_rate": 3.359641542682504e-05,
      "loss": 1.1043574333190918,
      "num_input_tokens_seen": 3454860928,
      "step": 12150,
      "train_runtime": 118404.6085,
      "train_tokens_per_second": 29178.433
    },
    {
      "epoch": 0.43024544069419535,
      "grad_norm": 1.5234375,
      "learning_rate": 3.3588833810627854e-05,
      "loss": 1.1016742706298828,
      "num_input_tokens_seen": 3457707904,
      "step": 12160,
      "train_runtime": 118500.8332,
      "train_tokens_per_second": 29178.764
    },
    {
      "epoch": 0.4305992609579241,
      "grad_norm": 1.40625,
      "learning_rate": 3.358125732488632e-05,
      "loss": 1.121287727355957,
      "num_input_tokens_seen": 3460558272,
      "step": 12170,
      "train_runtime": 118595.6527,
      "train_tokens_per_second": 29179.47
    },
    {
      "epoch": 0.43095308122165293,
      "grad_norm": 1.390625,
      "learning_rate": 3.357368596381679e-05,
      "loss": 1.1062000274658204,
      "num_input_tokens_seen": 3463387392,
      "step": 12180,
      "train_runtime": 118693.8105,
      "train_tokens_per_second": 29179.174
    },
    {
      "epoch": 0.4313069014853817,
      "grad_norm": 1.375,
      "learning_rate": 3.356611972164471e-05,
      "loss": 1.1084465026855468,
      "num_input_tokens_seen": 3466219328,
      "step": 12190,
      "train_runtime": 118787.3174,
      "train_tokens_per_second": 29180.046
    },
    {
      "epoch": 0.43166072174911047,
      "grad_norm": 1.453125,
      "learning_rate": 3.355855859260466e-05,
      "loss": 1.1182991981506347,
      "num_input_tokens_seen": 3469031360,
      "step": 12200,
      "train_runtime": 118880.7301,
      "train_tokens_per_second": 29180.771
    },
    {
      "epoch": 0.43201454201283923,
      "grad_norm": 1.4375,
      "learning_rate": 3.3551002570940285e-05,
      "loss": 1.116539764404297,
      "num_input_tokens_seen": 3471901376,
      "step": 12210,
      "train_runtime": 118980.6469,
      "train_tokens_per_second": 29180.387
    },
    {
      "epoch": 0.43236836227656805,
      "grad_norm": 1.4375,
      "learning_rate": 3.354345165090431e-05,
      "loss": 1.104250144958496,
      "num_input_tokens_seen": 3474786368,
      "step": 12220,
      "train_runtime": 119080.1139,
      "train_tokens_per_second": 29180.241
    },
    {
      "epoch": 0.4327221825402968,
      "grad_norm": 1.359375,
      "learning_rate": 3.3535905826758515e-05,
      "loss": 1.111336612701416,
      "num_input_tokens_seen": 3477614976,
      "step": 12230,
      "train_runtime": 119173.9197,
      "train_tokens_per_second": 29181.007
    },
    {
      "epoch": 0.4330760028040256,
      "grad_norm": 1.390625,
      "learning_rate": 3.352836509277369e-05,
      "loss": 1.1017717361450194,
      "num_input_tokens_seen": 3480460416,
      "step": 12240,
      "train_runtime": 119271.689,
      "train_tokens_per_second": 29180.943
    },
    {
      "epoch": 0.43342982306775435,
      "grad_norm": 1.4765625,
      "learning_rate": 3.352082944322966e-05,
      "loss": 1.116755485534668,
      "num_input_tokens_seen": 3483293248,
      "step": 12250,
      "train_runtime": 119369.2244,
      "train_tokens_per_second": 29180.832
    },
    {
      "epoch": 0.43378364333148317,
      "grad_norm": 1.453125,
      "learning_rate": 3.351329887241524e-05,
      "loss": 1.1216218948364258,
      "num_input_tokens_seen": 3486146176,
      "step": 12260,
      "train_runtime": 119466.2761,
      "train_tokens_per_second": 29181.006
    },
    {
      "epoch": 0.43413746359521194,
      "grad_norm": 1.453125,
      "learning_rate": 3.3505773374628225e-05,
      "loss": 1.1049503326416015,
      "num_input_tokens_seen": 3488975744,
      "step": 12270,
      "train_runtime": 119564.6136,
      "train_tokens_per_second": 29180.672
    },
    {
      "epoch": 0.4344912838589407,
      "grad_norm": 1.59375,
      "learning_rate": 3.3498252944175354e-05,
      "loss": 1.1079347610473633,
      "num_input_tokens_seen": 3491848384,
      "step": 12280,
      "train_runtime": 119665.4068,
      "train_tokens_per_second": 29180.099
    },
    {
      "epoch": 0.43484510412266947,
      "grad_norm": 1.40625,
      "learning_rate": 3.3490737575372326e-05,
      "loss": 1.1060548782348634,
      "num_input_tokens_seen": 3494671616,
      "step": 12290,
      "train_runtime": 119759.7638,
      "train_tokens_per_second": 29180.682
    },
    {
      "epoch": 0.4351989243863983,
      "grad_norm": 1.4765625,
      "learning_rate": 3.348322726254375e-05,
      "loss": 1.0926141738891602,
      "num_input_tokens_seen": 3497450944,
      "step": 12300,
      "train_runtime": 119853.4357,
      "train_tokens_per_second": 29181.065
    },
    {
      "epoch": 0.43555274465012705,
      "grad_norm": 1.4765625,
      "learning_rate": 3.347572200002315e-05,
      "loss": 1.103368091583252,
      "num_input_tokens_seen": 3500264704,
      "step": 12310,
      "train_runtime": 119950.3479,
      "train_tokens_per_second": 29180.947
    },
    {
      "epoch": 0.4359065649138558,
      "grad_norm": 1.421875,
      "learning_rate": 3.3468221782152924e-05,
      "loss": 1.1038829803466796,
      "num_input_tokens_seen": 3503073856,
      "step": 12320,
      "train_runtime": 120045.978,
      "train_tokens_per_second": 29181.101
    },
    {
      "epoch": 0.4362603851775846,
      "grad_norm": 1.4921875,
      "learning_rate": 3.346072660328435e-05,
      "loss": 1.1046785354614257,
      "num_input_tokens_seen": 3505961728,
      "step": 12330,
      "train_runtime": 120145.5582,
      "train_tokens_per_second": 29180.952
    },
    {
      "epoch": 0.4366142054413134,
      "grad_norm": 1.4140625,
      "learning_rate": 3.345323645777756e-05,
      "loss": 1.0987144470214845,
      "num_input_tokens_seen": 3508781760,
      "step": 12340,
      "train_runtime": 120240.3128,
      "train_tokens_per_second": 29181.409
    },
    {
      "epoch": 0.4369680257050422,
      "grad_norm": 1.4375,
      "learning_rate": 3.34457513400015e-05,
      "loss": 1.1068971633911133,
      "num_input_tokens_seen": 3511625344,
      "step": 12350,
      "train_runtime": 120336.6888,
      "train_tokens_per_second": 29181.668
    },
    {
      "epoch": 0.43732184596877094,
      "grad_norm": 1.4140625,
      "learning_rate": 3.343827124433396e-05,
      "loss": 1.1072772979736327,
      "num_input_tokens_seen": 3514470144,
      "step": 12360,
      "train_runtime": 120433.2515,
      "train_tokens_per_second": 29181.892
    },
    {
      "epoch": 0.4376756662324997,
      "grad_norm": 1.453125,
      "learning_rate": 3.343079616516151e-05,
      "loss": 1.1110486030578612,
      "num_input_tokens_seen": 3517244992,
      "step": 12370,
      "train_runtime": 120527.002,
      "train_tokens_per_second": 29182.216
    },
    {
      "epoch": 0.43802948649622847,
      "grad_norm": 1.3984375,
      "learning_rate": 3.3423326096879495e-05,
      "loss": 1.1143271446228027,
      "num_input_tokens_seen": 3520055808,
      "step": 12380,
      "train_runtime": 120623.1121,
      "train_tokens_per_second": 29182.267
    },
    {
      "epoch": 0.4383833067599573,
      "grad_norm": 1.5625,
      "learning_rate": 3.341586103389203e-05,
      "loss": 1.1165136337280273,
      "num_input_tokens_seen": 3522888384,
      "step": 12390,
      "train_runtime": 120719.4697,
      "train_tokens_per_second": 29182.438
    },
    {
      "epoch": 0.43873712702368606,
      "grad_norm": 1.4921875,
      "learning_rate": 3.3408400970611995e-05,
      "loss": 1.097696876525879,
      "num_input_tokens_seen": 3525718848,
      "step": 12400,
      "train_runtime": 120816.8061,
      "train_tokens_per_second": 29182.354
    },
    {
      "epoch": 0.4390909472874148,
      "grad_norm": 1.46875,
      "learning_rate": 3.340094590146095e-05,
      "loss": 1.112516212463379,
      "num_input_tokens_seen": 3528588416,
      "step": 12410,
      "train_runtime": 120913.7276,
      "train_tokens_per_second": 29182.695
    },
    {
      "epoch": 0.4394447675511436,
      "grad_norm": 1.4375,
      "learning_rate": 3.3393495820869215e-05,
      "loss": 1.1050718307495118,
      "num_input_tokens_seen": 3531412928,
      "step": 12420,
      "train_runtime": 121012.495,
      "train_tokens_per_second": 29182.217
    },
    {
      "epoch": 0.4397985878148724,
      "grad_norm": 1.453125,
      "learning_rate": 3.338605072327576e-05,
      "loss": 1.0926527023315429,
      "num_input_tokens_seen": 3534187904,
      "step": 12430,
      "train_runtime": 121106.9302,
      "train_tokens_per_second": 29182.375
    },
    {
      "epoch": 0.4401524080786012,
      "grad_norm": 1.4375,
      "learning_rate": 3.337861060312827e-05,
      "loss": 1.1018476486206055,
      "num_input_tokens_seen": 3537046400,
      "step": 12440,
      "train_runtime": 121202.5157,
      "train_tokens_per_second": 29182.945
    },
    {
      "epoch": 0.44050622834232994,
      "grad_norm": 1.46875,
      "learning_rate": 3.337117545488306e-05,
      "loss": 1.0933261871337892,
      "num_input_tokens_seen": 3539862400,
      "step": 12450,
      "train_runtime": 121299.602,
      "train_tokens_per_second": 29182.803
    },
    {
      "epoch": 0.4408600486060587,
      "grad_norm": 1.484375,
      "learning_rate": 3.33637452730051e-05,
      "loss": 1.1149778366088867,
      "num_input_tokens_seen": 3542731776,
      "step": 12460,
      "train_runtime": 121398.7915,
      "train_tokens_per_second": 29182.595
    },
    {
      "epoch": 0.44121386886978753,
      "grad_norm": 1.4140625,
      "learning_rate": 3.335632005196796e-05,
      "loss": 1.1093759536743164,
      "num_input_tokens_seen": 3545568832,
      "step": 12470,
      "train_runtime": 121496.1293,
      "train_tokens_per_second": 29182.566
    },
    {
      "epoch": 0.4415676891335163,
      "grad_norm": 1.453125,
      "learning_rate": 3.334889978625383e-05,
      "loss": 1.1053879737854004,
      "num_input_tokens_seen": 3548391872,
      "step": 12480,
      "train_runtime": 121591.375,
      "train_tokens_per_second": 29182.924
    },
    {
      "epoch": 0.44192150939724506,
      "grad_norm": 1.4296875,
      "learning_rate": 3.3341484470353515e-05,
      "loss": 1.1148277282714845,
      "num_input_tokens_seen": 3551287488,
      "step": 12490,
      "train_runtime": 121694.1541,
      "train_tokens_per_second": 29182.071
    },
    {
      "epoch": 0.4422753296609738,
      "grad_norm": 1.40625,
      "learning_rate": 3.333407409876635e-05,
      "loss": 1.1003576278686524,
      "num_input_tokens_seen": 3554146688,
      "step": 12500,
      "train_runtime": 121791.0818,
      "train_tokens_per_second": 29182.323
    },
    {
      "epoch": 0.44262914992470265,
      "grad_norm": 1.421875,
      "learning_rate": 3.332666866600024e-05,
      "loss": 1.0955620765686036,
      "num_input_tokens_seen": 3556976192,
      "step": 12510,
      "train_runtime": 121890.3274,
      "train_tokens_per_second": 29181.776
    },
    {
      "epoch": 0.4429829701884314,
      "grad_norm": 1.421875,
      "learning_rate": 3.331926816657162e-05,
      "loss": 1.1010419845581054,
      "num_input_tokens_seen": 3559771392,
      "step": 12520,
      "train_runtime": 121984.1789,
      "train_tokens_per_second": 29182.238
    },
    {
      "epoch": 0.4433367904521602,
      "grad_norm": 1.53125,
      "learning_rate": 3.331187259500546e-05,
      "loss": 1.1269894599914552,
      "num_input_tokens_seen": 3562673984,
      "step": 12530,
      "train_runtime": 122086.2689,
      "train_tokens_per_second": 29181.611
    },
    {
      "epoch": 0.44369061071588894,
      "grad_norm": 1.390625,
      "learning_rate": 3.3304481945835235e-05,
      "loss": 1.1217117309570312,
      "num_input_tokens_seen": 3565495808,
      "step": 12540,
      "train_runtime": 122181.82,
      "train_tokens_per_second": 29181.885
    },
    {
      "epoch": 0.44404443097961777,
      "grad_norm": 1.5546875,
      "learning_rate": 3.329709621360288e-05,
      "loss": 1.1079509735107422,
      "num_input_tokens_seen": 3568296192,
      "step": 12550,
      "train_runtime": 122274.8907,
      "train_tokens_per_second": 29182.575
    },
    {
      "epoch": 0.44439825124334653,
      "grad_norm": 1.515625,
      "learning_rate": 3.328971539285882e-05,
      "loss": 1.104273223876953,
      "num_input_tokens_seen": 3571137408,
      "step": 12560,
      "train_runtime": 122372.7173,
      "train_tokens_per_second": 29182.464
    },
    {
      "epoch": 0.4447520715070753,
      "grad_norm": 1.3828125,
      "learning_rate": 3.3282339478161935e-05,
      "loss": 1.0957395553588867,
      "num_input_tokens_seen": 3573937216,
      "step": 12570,
      "train_runtime": 122465.9734,
      "train_tokens_per_second": 29183.104
    },
    {
      "epoch": 0.44510589177080406,
      "grad_norm": 1.421875,
      "learning_rate": 3.327496846407953e-05,
      "loss": 1.1060129165649415,
      "num_input_tokens_seen": 3576755136,
      "step": 12580,
      "train_runtime": 122559.9881,
      "train_tokens_per_second": 29183.71
    },
    {
      "epoch": 0.4454597120345329,
      "grad_norm": 1.421875,
      "learning_rate": 3.3267602345187304e-05,
      "loss": 1.110853385925293,
      "num_input_tokens_seen": 3579593728,
      "step": 12590,
      "train_runtime": 122655.6954,
      "train_tokens_per_second": 29184.081
    },
    {
      "epoch": 0.44581353229826165,
      "grad_norm": 1.3984375,
      "learning_rate": 3.326024111606942e-05,
      "loss": 1.0923341751098632,
      "num_input_tokens_seen": 3582422016,
      "step": 12600,
      "train_runtime": 122751.342,
      "train_tokens_per_second": 29184.382
    },
    {
      "epoch": 0.4461673525619904,
      "grad_norm": 1.40625,
      "learning_rate": 3.325288477131839e-05,
      "loss": 1.1202333450317383,
      "num_input_tokens_seen": 3585311552,
      "step": 12610,
      "train_runtime": 122851.3861,
      "train_tokens_per_second": 29184.136
    },
    {
      "epoch": 0.4465211728257192,
      "grad_norm": 1.4140625,
      "learning_rate": 3.324553330553507e-05,
      "loss": 1.0907839775085448,
      "num_input_tokens_seen": 3588124352,
      "step": 12620,
      "train_runtime": 122945.8911,
      "train_tokens_per_second": 29184.581
    },
    {
      "epoch": 0.44687499308944795,
      "grad_norm": 1.484375,
      "learning_rate": 3.323818671332871e-05,
      "loss": 1.0993354797363282,
      "num_input_tokens_seen": 3590967936,
      "step": 12630,
      "train_runtime": 123043.7959,
      "train_tokens_per_second": 29184.47
    },
    {
      "epoch": 0.44722881335317677,
      "grad_norm": 1.4609375,
      "learning_rate": 3.323084498931687e-05,
      "loss": 1.1179710388183595,
      "num_input_tokens_seen": 3593794752,
      "step": 12640,
      "train_runtime": 123139.9277,
      "train_tokens_per_second": 29184.642
    },
    {
      "epoch": 0.44758263361690553,
      "grad_norm": 1.4765625,
      "learning_rate": 3.322350812812545e-05,
      "loss": 1.118307113647461,
      "num_input_tokens_seen": 3596652736,
      "step": 12650,
      "train_runtime": 123238.6684,
      "train_tokens_per_second": 29184.45
    },
    {
      "epoch": 0.4479364538806343,
      "grad_norm": 1.421875,
      "learning_rate": 3.321617612438862e-05,
      "loss": 1.0977344512939453,
      "num_input_tokens_seen": 3599468672,
      "step": 12660,
      "train_runtime": 123334.8485,
      "train_tokens_per_second": 29184.523
    },
    {
      "epoch": 0.44829027414436307,
      "grad_norm": 1.4453125,
      "learning_rate": 3.320884897274886e-05,
      "loss": 1.1174657821655274,
      "num_input_tokens_seen": 3602314176,
      "step": 12670,
      "train_runtime": 123432.5231,
      "train_tokens_per_second": 29184.481
    },
    {
      "epoch": 0.4486440944080919,
      "grad_norm": 1.4453125,
      "learning_rate": 3.320152666785692e-05,
      "loss": 1.1217931747436523,
      "num_input_tokens_seen": 3605160320,
      "step": 12680,
      "train_runtime": 123527.7602,
      "train_tokens_per_second": 29185.021
    },
    {
      "epoch": 0.44899791467182065,
      "grad_norm": 1.4296875,
      "learning_rate": 3.319420920437179e-05,
      "loss": 1.0929196357727051,
      "num_input_tokens_seen": 3608000448,
      "step": 12690,
      "train_runtime": 123624.1875,
      "train_tokens_per_second": 29185.231
    },
    {
      "epoch": 0.4493517349355494,
      "grad_norm": 1.453125,
      "learning_rate": 3.31868965769607e-05,
      "loss": 1.1016122817993164,
      "num_input_tokens_seen": 3610869056,
      "step": 12700,
      "train_runtime": 123723.7021,
      "train_tokens_per_second": 29184.942
    },
    {
      "epoch": 0.4497055551992782,
      "grad_norm": 1.3828125,
      "learning_rate": 3.317958878029911e-05,
      "loss": 1.1059175491333009,
      "num_input_tokens_seen": 3613746304,
      "step": 12710,
      "train_runtime": 123822.6971,
      "train_tokens_per_second": 29184.846
    },
    {
      "epoch": 0.450059375463007,
      "grad_norm": 1.40625,
      "learning_rate": 3.3172285809070665e-05,
      "loss": 1.0970277786254883,
      "num_input_tokens_seen": 3616641600,
      "step": 12720,
      "train_runtime": 123921.8178,
      "train_tokens_per_second": 29184.866
    },
    {
      "epoch": 0.45041319572673577,
      "grad_norm": 1.421875,
      "learning_rate": 3.3164987657967214e-05,
      "loss": 1.1279159545898438,
      "num_input_tokens_seen": 3619544960,
      "step": 12730,
      "train_runtime": 124024.9816,
      "train_tokens_per_second": 29183.999
    },
    {
      "epoch": 0.45076701599046454,
      "grad_norm": 1.453125,
      "learning_rate": 3.315769432168877e-05,
      "loss": 1.1084771156311035,
      "num_input_tokens_seen": 3622380864,
      "step": 12740,
      "train_runtime": 124120.043,
      "train_tokens_per_second": 29184.496
    },
    {
      "epoch": 0.4511208362541933,
      "grad_norm": 1.4375,
      "learning_rate": 3.315040579494349e-05,
      "loss": 1.1145353317260742,
      "num_input_tokens_seen": 3625226368,
      "step": 12750,
      "train_runtime": 124217.7388,
      "train_tokens_per_second": 29184.45
    },
    {
      "epoch": 0.4514746565179221,
      "grad_norm": 1.4453125,
      "learning_rate": 3.31431220724477e-05,
      "loss": 1.1009464263916016,
      "num_input_tokens_seen": 3628066688,
      "step": 12760,
      "train_runtime": 124312.7124,
      "train_tokens_per_second": 29185.001
    },
    {
      "epoch": 0.4518284767816509,
      "grad_norm": 1.421875,
      "learning_rate": 3.3135843148925834e-05,
      "loss": 1.1143318176269532,
      "num_input_tokens_seen": 3630867584,
      "step": 12770,
      "train_runtime": 124405.4721,
      "train_tokens_per_second": 29185.755
    },
    {
      "epoch": 0.45218229704537966,
      "grad_norm": 1.421875,
      "learning_rate": 3.3128569019110414e-05,
      "loss": 1.1067062377929688,
      "num_input_tokens_seen": 3633722176,
      "step": 12780,
      "train_runtime": 124504.1755,
      "train_tokens_per_second": 29185.545
    },
    {
      "epoch": 0.4525361173091084,
      "grad_norm": 1.3671875,
      "learning_rate": 3.312129967774207e-05,
      "loss": 1.100377655029297,
      "num_input_tokens_seen": 3636590208,
      "step": 12790,
      "train_runtime": 124604.4635,
      "train_tokens_per_second": 29185.072
    },
    {
      "epoch": 0.45288993757283724,
      "grad_norm": 1.4296875,
      "learning_rate": 3.311403511956952e-05,
      "loss": 1.0981801986694335,
      "num_input_tokens_seen": 3639380736,
      "step": 12800,
      "train_runtime": 124698.4002,
      "train_tokens_per_second": 29185.465
    },
    {
      "epoch": 0.453243757836566,
      "grad_norm": 1.4375,
      "learning_rate": 3.310677533934952e-05,
      "loss": 1.1047271728515624,
      "num_input_tokens_seen": 3642170816,
      "step": 12810,
      "train_runtime": 124793.4465,
      "train_tokens_per_second": 29185.594
    },
    {
      "epoch": 0.4535975781002948,
      "grad_norm": 1.453125,
      "learning_rate": 3.309952033184686e-05,
      "loss": 1.0958417892456054,
      "num_input_tokens_seen": 3644998592,
      "step": 12820,
      "train_runtime": 124888.3737,
      "train_tokens_per_second": 29186.052
    },
    {
      "epoch": 0.45395139836402354,
      "grad_norm": 1.3671875,
      "learning_rate": 3.309227009183439e-05,
      "loss": 1.0978492736816405,
      "num_input_tokens_seen": 3647778752,
      "step": 12830,
      "train_runtime": 124981.2006,
      "train_tokens_per_second": 29186.62
    },
    {
      "epoch": 0.45430521862775236,
      "grad_norm": 1.390625,
      "learning_rate": 3.308502461409295e-05,
      "loss": 1.1000548362731934,
      "num_input_tokens_seen": 3650677312,
      "step": 12840,
      "train_runtime": 125080.1836,
      "train_tokens_per_second": 29186.696
    },
    {
      "epoch": 0.4546590388914811,
      "grad_norm": 1.390625,
      "learning_rate": 3.3077783893411386e-05,
      "loss": 1.1006376266479492,
      "num_input_tokens_seen": 3653550912,
      "step": 12850,
      "train_runtime": 125180.1601,
      "train_tokens_per_second": 29186.342
    },
    {
      "epoch": 0.4550128591552099,
      "grad_norm": 1.390625,
      "learning_rate": 3.30705479245865e-05,
      "loss": 1.0956745147705078,
      "num_input_tokens_seen": 3656410176,
      "step": 12860,
      "train_runtime": 125278.1578,
      "train_tokens_per_second": 29186.334
    },
    {
      "epoch": 0.45536667941893866,
      "grad_norm": 1.40625,
      "learning_rate": 3.3063316702423094e-05,
      "loss": 1.10784969329834,
      "num_input_tokens_seen": 3659304768,
      "step": 12870,
      "train_runtime": 125379.2257,
      "train_tokens_per_second": 29185.894
    },
    {
      "epoch": 0.4557204996826674,
      "grad_norm": 1.3984375,
      "learning_rate": 3.305609022173388e-05,
      "loss": 1.1130596160888673,
      "num_input_tokens_seen": 3662148672,
      "step": 12880,
      "train_runtime": 125475.826,
      "train_tokens_per_second": 29186.089
    },
    {
      "epoch": 0.45607431994639624,
      "grad_norm": 1.4140625,
      "learning_rate": 3.304886847733954e-05,
      "loss": 1.1128378868103028,
      "num_input_tokens_seen": 3665006976,
      "step": 12890,
      "train_runtime": 125573.8038,
      "train_tokens_per_second": 29186.079
    },
    {
      "epoch": 0.456428140210125,
      "grad_norm": 1.3984375,
      "learning_rate": 3.304165146406865e-05,
      "loss": 1.0901856422424316,
      "num_input_tokens_seen": 3667843008,
      "step": 12900,
      "train_runtime": 125671.5831,
      "train_tokens_per_second": 29185.938
    },
    {
      "epoch": 0.4567819604738538,
      "grad_norm": 1.453125,
      "learning_rate": 3.30344391767577e-05,
      "loss": 1.1052507400512694,
      "num_input_tokens_seen": 3670698688,
      "step": 12910,
      "train_runtime": 125770.1597,
      "train_tokens_per_second": 29185.768
    },
    {
      "epoch": 0.45713578073758254,
      "grad_norm": 1.390625,
      "learning_rate": 3.302723161025104e-05,
      "loss": 1.1128118515014649,
      "num_input_tokens_seen": 3673513344,
      "step": 12920,
      "train_runtime": 125863.9831,
      "train_tokens_per_second": 29186.374
    },
    {
      "epoch": 0.45748960100131136,
      "grad_norm": 1.3828125,
      "learning_rate": 3.302002875940093e-05,
      "loss": 1.0914009094238282,
      "num_input_tokens_seen": 3676334272,
      "step": 12930,
      "train_runtime": 125958.9702,
      "train_tokens_per_second": 29186.76
    },
    {
      "epoch": 0.45784342126504013,
      "grad_norm": 1.453125,
      "learning_rate": 3.3012830619067466e-05,
      "loss": 1.1091476440429688,
      "num_input_tokens_seen": 3679143232,
      "step": 12940,
      "train_runtime": 126054.9094,
      "train_tokens_per_second": 29186.83
    },
    {
      "epoch": 0.4581972415287689,
      "grad_norm": 1.5078125,
      "learning_rate": 3.300563718411857e-05,
      "loss": 1.1056535720825196,
      "num_input_tokens_seen": 3681976512,
      "step": 12950,
      "train_runtime": 126151.729,
      "train_tokens_per_second": 29186.889
    },
    {
      "epoch": 0.45855106179249766,
      "grad_norm": 1.4140625,
      "learning_rate": 3.299844844943e-05,
      "loss": 1.1109651565551757,
      "num_input_tokens_seen": 3684819072,
      "step": 12960,
      "train_runtime": 126249.13,
      "train_tokens_per_second": 29186.887
    },
    {
      "epoch": 0.4589048820562265,
      "grad_norm": 1.3984375,
      "learning_rate": 3.299126440988535e-05,
      "loss": 1.1065553665161132,
      "num_input_tokens_seen": 3687670720,
      "step": 12970,
      "train_runtime": 126347.254,
      "train_tokens_per_second": 29186.79
    },
    {
      "epoch": 0.45925870231995525,
      "grad_norm": 1.390625,
      "learning_rate": 3.298408506037596e-05,
      "loss": 1.1015348434448242,
      "num_input_tokens_seen": 3690532032,
      "step": 12980,
      "train_runtime": 126446.7523,
      "train_tokens_per_second": 29186.452
    },
    {
      "epoch": 0.459612522583684,
      "grad_norm": 1.4296875,
      "learning_rate": 3.297691039580097e-05,
      "loss": 1.0998037338256836,
      "num_input_tokens_seen": 3693374976,
      "step": 12990,
      "train_runtime": 126544.4817,
      "train_tokens_per_second": 29186.377
    },
    {
      "epoch": 0.4599663428474128,
      "grad_norm": 1.3671875,
      "learning_rate": 3.29697404110673e-05,
      "loss": 1.1078229904174806,
      "num_input_tokens_seen": 3696248128,
      "step": 13000,
      "train_runtime": 126644.827,
      "train_tokens_per_second": 29185.938
    },
    {
      "epoch": 0.4603201631111416,
      "grad_norm": 1.4375,
      "learning_rate": 3.2962575101089594e-05,
      "loss": 1.095658302307129,
      "num_input_tokens_seen": 3699071680,
      "step": 13010,
      "train_runtime": 126740.3667,
      "train_tokens_per_second": 29186.216
    },
    {
      "epoch": 0.46067398337487037,
      "grad_norm": 1.5,
      "learning_rate": 3.295541446079024e-05,
      "loss": 1.103954029083252,
      "num_input_tokens_seen": 3701891648,
      "step": 13020,
      "train_runtime": 126836.2823,
      "train_tokens_per_second": 29186.378
    },
    {
      "epoch": 0.46102780363859913,
      "grad_norm": 1.40625,
      "learning_rate": 3.2948258485099336e-05,
      "loss": 1.1082317352294921,
      "num_input_tokens_seen": 3704756032,
      "step": 13030,
      "train_runtime": 126935.4757,
      "train_tokens_per_second": 29186.136
    },
    {
      "epoch": 0.4613816239023279,
      "grad_norm": 1.4609375,
      "learning_rate": 3.29411071689547e-05,
      "loss": 1.1182458877563477,
      "num_input_tokens_seen": 3707661952,
      "step": 13040,
      "train_runtime": 127037.1749,
      "train_tokens_per_second": 29185.646
    },
    {
      "epoch": 0.4617354441660567,
      "grad_norm": 1.40625,
      "learning_rate": 3.2933960507301826e-05,
      "loss": 1.0974594116210938,
      "num_input_tokens_seen": 3710518912,
      "step": 13050,
      "train_runtime": 127136.1297,
      "train_tokens_per_second": 29185.401
    },
    {
      "epoch": 0.4620892644297855,
      "grad_norm": 1.484375,
      "learning_rate": 3.292681849509387e-05,
      "loss": 1.104828453063965,
      "num_input_tokens_seen": 3713319168,
      "step": 13060,
      "train_runtime": 127233.9407,
      "train_tokens_per_second": 29184.973
    },
    {
      "epoch": 0.46244308469351425,
      "grad_norm": 1.4609375,
      "learning_rate": 3.291968112729166e-05,
      "loss": 1.107470417022705,
      "num_input_tokens_seen": 3716157248,
      "step": 13070,
      "train_runtime": 127331.0211,
      "train_tokens_per_second": 29185.011
    },
    {
      "epoch": 0.462796904957243,
      "grad_norm": 1.4453125,
      "learning_rate": 3.291254839886367e-05,
      "loss": 1.0845415115356445,
      "num_input_tokens_seen": 3718953728,
      "step": 13080,
      "train_runtime": 127428.3045,
      "train_tokens_per_second": 29184.676
    },
    {
      "epoch": 0.46315072522097184,
      "grad_norm": 1.4609375,
      "learning_rate": 3.2905420304785995e-05,
      "loss": 1.1077667236328126,
      "num_input_tokens_seen": 3721783488,
      "step": 13090,
      "train_runtime": 127524.09,
      "train_tokens_per_second": 29184.944
    },
    {
      "epoch": 0.4635045454847006,
      "grad_norm": 1.3515625,
      "learning_rate": 3.289829684004235e-05,
      "loss": 1.1112678527832032,
      "num_input_tokens_seen": 3724641792,
      "step": 13100,
      "train_runtime": 127621.7913,
      "train_tokens_per_second": 29184.999
    },
    {
      "epoch": 0.46385836574842937,
      "grad_norm": 1.5078125,
      "learning_rate": 3.289117799962402e-05,
      "loss": 1.1067995071411132,
      "num_input_tokens_seen": 3727474368,
      "step": 13110,
      "train_runtime": 127718.4072,
      "train_tokens_per_second": 29185.099
    },
    {
      "epoch": 0.46421218601215813,
      "grad_norm": 1.390625,
      "learning_rate": 3.2884063778529914e-05,
      "loss": 1.1009221076965332,
      "num_input_tokens_seen": 3730300608,
      "step": 13120,
      "train_runtime": 127813.8751,
      "train_tokens_per_second": 29185.412
    },
    {
      "epoch": 0.4645660062758869,
      "grad_norm": 1.4765625,
      "learning_rate": 3.28769541717665e-05,
      "loss": 1.111198616027832,
      "num_input_tokens_seen": 3733139328,
      "step": 13130,
      "train_runtime": 127910.1621,
      "train_tokens_per_second": 29185.635
    },
    {
      "epoch": 0.4649198265396157,
      "grad_norm": 1.3359375,
      "learning_rate": 3.2869849174347775e-05,
      "loss": 1.0902486801147462,
      "num_input_tokens_seen": 3736004480,
      "step": 13140,
      "train_runtime": 128007.7307,
      "train_tokens_per_second": 29185.772
    },
    {
      "epoch": 0.4652736468033445,
      "grad_norm": 1.421875,
      "learning_rate": 3.2862748781295294e-05,
      "loss": 1.0935636520385743,
      "num_input_tokens_seen": 3738816960,
      "step": 13150,
      "train_runtime": 128101.2633,
      "train_tokens_per_second": 29186.418
    },
    {
      "epoch": 0.46562746706707325,
      "grad_norm": 1.4140625,
      "learning_rate": 3.2855652987638146e-05,
      "loss": 1.1180343627929688,
      "num_input_tokens_seen": 3741696896,
      "step": 13160,
      "train_runtime": 128202.7701,
      "train_tokens_per_second": 29185.773
    },
    {
      "epoch": 0.465981287330802,
      "grad_norm": 1.453125,
      "learning_rate": 3.284856178841291e-05,
      "loss": 1.0981327056884767,
      "num_input_tokens_seen": 3744501888,
      "step": 13170,
      "train_runtime": 128297.2485,
      "train_tokens_per_second": 29186.143
    },
    {
      "epoch": 0.46633510759453084,
      "grad_norm": 1.4453125,
      "learning_rate": 3.284147517866367e-05,
      "loss": 1.1091805458068849,
      "num_input_tokens_seen": 3747355968,
      "step": 13180,
      "train_runtime": 128396.3945,
      "train_tokens_per_second": 29185.835
    },
    {
      "epoch": 0.4666889278582596,
      "grad_norm": 1.4453125,
      "learning_rate": 3.2834393153441976e-05,
      "loss": 1.1088296890258789,
      "num_input_tokens_seen": 3750236160,
      "step": 13190,
      "train_runtime": 128493.5587,
      "train_tokens_per_second": 29186.18
    },
    {
      "epoch": 0.46704274812198837,
      "grad_norm": 1.421875,
      "learning_rate": 3.282731570780689e-05,
      "loss": 1.101529312133789,
      "num_input_tokens_seen": 3753081600,
      "step": 13200,
      "train_runtime": 128589.8262,
      "train_tokens_per_second": 29186.458
    },
    {
      "epoch": 0.46739656838571714,
      "grad_norm": 1.4453125,
      "learning_rate": 3.2820242836824875e-05,
      "loss": 1.112099838256836,
      "num_input_tokens_seen": 3755909056,
      "step": 13210,
      "train_runtime": 128686.5275,
      "train_tokens_per_second": 29186.498
    },
    {
      "epoch": 0.46775038864944596,
      "grad_norm": 1.4453125,
      "learning_rate": 3.2813174535569854e-05,
      "loss": 1.1053627967834472,
      "num_input_tokens_seen": 3758709056,
      "step": 13220,
      "train_runtime": 128783.3692,
      "train_tokens_per_second": 29186.292
    },
    {
      "epoch": 0.4681042089131747,
      "grad_norm": 1.40625,
      "learning_rate": 3.280611079912318e-05,
      "loss": 1.0999862670898437,
      "num_input_tokens_seen": 3761523904,
      "step": 13230,
      "train_runtime": 128878.2107,
      "train_tokens_per_second": 29186.655
    },
    {
      "epoch": 0.4684580291769035,
      "grad_norm": 1.4453125,
      "learning_rate": 3.279905162257358e-05,
      "loss": 1.1103971481323243,
      "num_input_tokens_seen": 3764351680,
      "step": 13240,
      "train_runtime": 128972.5885,
      "train_tokens_per_second": 29187.223
    },
    {
      "epoch": 0.46881184944063226,
      "grad_norm": 1.375,
      "learning_rate": 3.279199700101723e-05,
      "loss": 1.1121068954467774,
      "num_input_tokens_seen": 3767180096,
      "step": 13250,
      "train_runtime": 129067.1242,
      "train_tokens_per_second": 29187.759
    },
    {
      "epoch": 0.4691656697043611,
      "grad_norm": 1.46875,
      "learning_rate": 3.2784946929557644e-05,
      "loss": 1.0980195999145508,
      "num_input_tokens_seen": 3769964480,
      "step": 13260,
      "train_runtime": 129162.6615,
      "train_tokens_per_second": 29187.727
    },
    {
      "epoch": 0.46951948996808984,
      "grad_norm": 1.484375,
      "learning_rate": 3.277790140330571e-05,
      "loss": 1.1119718551635742,
      "num_input_tokens_seen": 3772865984,
      "step": 13270,
      "train_runtime": 129261.9751,
      "train_tokens_per_second": 29187.748
    },
    {
      "epoch": 0.4698733102318186,
      "grad_norm": 1.4296875,
      "learning_rate": 3.277086041737968e-05,
      "loss": 1.1151845932006836,
      "num_input_tokens_seen": 3775689600,
      "step": 13280,
      "train_runtime": 129356.0989,
      "train_tokens_per_second": 29188.338
    },
    {
      "epoch": 0.4702271304955474,
      "grad_norm": 1.5234375,
      "learning_rate": 3.276382396690513e-05,
      "loss": 1.1176087379455566,
      "num_input_tokens_seen": 3778486464,
      "step": 13290,
      "train_runtime": 129452.96,
      "train_tokens_per_second": 29188.104
    },
    {
      "epoch": 0.4705809507592762,
      "grad_norm": 1.453125,
      "learning_rate": 3.275679204701496e-05,
      "loss": 1.1205736160278321,
      "num_input_tokens_seen": 3781317632,
      "step": 13300,
      "train_runtime": 129549.2862,
      "train_tokens_per_second": 29188.255
    },
    {
      "epoch": 0.47093477102300496,
      "grad_norm": 1.4453125,
      "learning_rate": 3.274976465284939e-05,
      "loss": 1.104206657409668,
      "num_input_tokens_seen": 3784164480,
      "step": 13310,
      "train_runtime": 129645.5724,
      "train_tokens_per_second": 29188.536
    },
    {
      "epoch": 0.4712885912867337,
      "grad_norm": 1.421875,
      "learning_rate": 3.274274177955593e-05,
      "loss": 1.1073772430419921,
      "num_input_tokens_seen": 3786995392,
      "step": 13320,
      "train_runtime": 129741.2091,
      "train_tokens_per_second": 29188.84
    },
    {
      "epoch": 0.4716424115504625,
      "grad_norm": 1.53125,
      "learning_rate": 3.273572342228937e-05,
      "loss": 1.09786376953125,
      "num_input_tokens_seen": 3789813440,
      "step": 13330,
      "train_runtime": 129837.2074,
      "train_tokens_per_second": 29188.963
    },
    {
      "epoch": 0.4719962318141913,
      "grad_norm": 1.4296875,
      "learning_rate": 3.272870957621176e-05,
      "loss": 1.09412841796875,
      "num_input_tokens_seen": 3792692928,
      "step": 13340,
      "train_runtime": 129934.5841,
      "train_tokens_per_second": 29189.249
    },
    {
      "epoch": 0.4723500520779201,
      "grad_norm": 1.4921875,
      "learning_rate": 3.2721700236492414e-05,
      "loss": 1.1130117416381835,
      "num_input_tokens_seen": 3795596096,
      "step": 13350,
      "train_runtime": 130037.7027,
      "train_tokens_per_second": 29188.428
    },
    {
      "epoch": 0.47270387234164885,
      "grad_norm": 1.4140625,
      "learning_rate": 3.271469539830788e-05,
      "loss": 1.1061529159545898,
      "num_input_tokens_seen": 3798444096,
      "step": 13360,
      "train_runtime": 130137.1313,
      "train_tokens_per_second": 29188.012
    },
    {
      "epoch": 0.4730576926053776,
      "grad_norm": 1.4765625,
      "learning_rate": 3.270769505684193e-05,
      "loss": 1.1145133018493651,
      "num_input_tokens_seen": 3801311488,
      "step": 13370,
      "train_runtime": 130236.6232,
      "train_tokens_per_second": 29187.731
    },
    {
      "epoch": 0.47341151286910643,
      "grad_norm": 1.4296875,
      "learning_rate": 3.2700699207285544e-05,
      "loss": 1.1082937240600585,
      "num_input_tokens_seen": 3804162368,
      "step": 13380,
      "train_runtime": 130333.3685,
      "train_tokens_per_second": 29187.939
    },
    {
      "epoch": 0.4737653331328352,
      "grad_norm": 1.46875,
      "learning_rate": 3.269370784483691e-05,
      "loss": 1.1077110290527343,
      "num_input_tokens_seen": 3806985664,
      "step": 13390,
      "train_runtime": 130429.0111,
      "train_tokens_per_second": 29188.182
    },
    {
      "epoch": 0.47411915339656396,
      "grad_norm": 1.3515625,
      "learning_rate": 3.268672096470138e-05,
      "loss": 1.110721492767334,
      "num_input_tokens_seen": 3809798528,
      "step": 13400,
      "train_runtime": 130524.2093,
      "train_tokens_per_second": 29188.444
    },
    {
      "epoch": 0.47447297366029273,
      "grad_norm": 1.4609375,
      "learning_rate": 3.2679738562091506e-05,
      "loss": 1.103311824798584,
      "num_input_tokens_seen": 3812646720,
      "step": 13410,
      "train_runtime": 130621.2615,
      "train_tokens_per_second": 29188.561
    },
    {
      "epoch": 0.4748267939240215,
      "grad_norm": 1.484375,
      "learning_rate": 3.2672760632226964e-05,
      "loss": 1.1058692932128906,
      "num_input_tokens_seen": 3815474560,
      "step": 13420,
      "train_runtime": 130719.991,
      "train_tokens_per_second": 29188.149
    },
    {
      "epoch": 0.4751806141877503,
      "grad_norm": 1.4609375,
      "learning_rate": 3.266578717033458e-05,
      "loss": 1.1080438613891601,
      "num_input_tokens_seen": 3818355968,
      "step": 13430,
      "train_runtime": 130820.6469,
      "train_tokens_per_second": 29187.717
    },
    {
      "epoch": 0.4755344344514791,
      "grad_norm": 1.3671875,
      "learning_rate": 3.265881817164833e-05,
      "loss": 1.0981053352355956,
      "num_input_tokens_seen": 3821149376,
      "step": 13440,
      "train_runtime": 130913.3979,
      "train_tokens_per_second": 29188.375
    },
    {
      "epoch": 0.47588825471520785,
      "grad_norm": 1.4921875,
      "learning_rate": 3.265185363140928e-05,
      "loss": 1.1091983795166016,
      "num_input_tokens_seen": 3824011584,
      "step": 13450,
      "train_runtime": 131011.044,
      "train_tokens_per_second": 29188.467
    },
    {
      "epoch": 0.4762420749789366,
      "grad_norm": 1.421875,
      "learning_rate": 3.26448935448656e-05,
      "loss": 1.0971981048583985,
      "num_input_tokens_seen": 3826835904,
      "step": 13460,
      "train_runtime": 131106.8447,
      "train_tokens_per_second": 29188.681
    },
    {
      "epoch": 0.47659589524266543,
      "grad_norm": 1.4609375,
      "learning_rate": 3.263793790727256e-05,
      "loss": 1.101974105834961,
      "num_input_tokens_seen": 3829707968,
      "step": 13470,
      "train_runtime": 131205.7862,
      "train_tokens_per_second": 29188.56
    },
    {
      "epoch": 0.4769497155063942,
      "grad_norm": 1.4765625,
      "learning_rate": 3.2630986713892495e-05,
      "loss": 1.0923451423645019,
      "num_input_tokens_seen": 3832545344,
      "step": 13480,
      "train_runtime": 131302.558,
      "train_tokens_per_second": 29188.657
    },
    {
      "epoch": 0.47730353577012297,
      "grad_norm": 1.3828125,
      "learning_rate": 3.26240399599948e-05,
      "loss": 1.1004320144653321,
      "num_input_tokens_seen": 3835377728,
      "step": 13490,
      "train_runtime": 131400.4682,
      "train_tokens_per_second": 29188.463
    },
    {
      "epoch": 0.47765735603385173,
      "grad_norm": 1.4609375,
      "learning_rate": 3.2617097640855914e-05,
      "loss": 1.1029982566833496,
      "num_input_tokens_seen": 3838192448,
      "step": 13500,
      "train_runtime": 131497.0135,
      "train_tokens_per_second": 29188.438
    },
    {
      "epoch": 0.47801117629758055,
      "grad_norm": 1.40625,
      "learning_rate": 3.2610159751759314e-05,
      "loss": 1.0987348556518555,
      "num_input_tokens_seen": 3841070848,
      "step": 13510,
      "train_runtime": 131596.9178,
      "train_tokens_per_second": 29188.152
    },
    {
      "epoch": 0.4783649965613093,
      "grad_norm": 1.4765625,
      "learning_rate": 3.26032262879955e-05,
      "loss": 1.114363956451416,
      "num_input_tokens_seen": 3843858048,
      "step": 13520,
      "train_runtime": 131691.8696,
      "train_tokens_per_second": 29188.272
    },
    {
      "epoch": 0.4787188168250381,
      "grad_norm": 1.40625,
      "learning_rate": 3.259629724486198e-05,
      "loss": 1.1138381958007812,
      "num_input_tokens_seen": 3846663040,
      "step": 13530,
      "train_runtime": 131787.4145,
      "train_tokens_per_second": 29188.394
    },
    {
      "epoch": 0.47907263708876685,
      "grad_norm": 1.390625,
      "learning_rate": 3.258937261766323e-05,
      "loss": 1.0999014854431153,
      "num_input_tokens_seen": 3849578240,
      "step": 13540,
      "train_runtime": 131889.5612,
      "train_tokens_per_second": 29187.892
    },
    {
      "epoch": 0.47942645735249567,
      "grad_norm": 1.53125,
      "learning_rate": 3.258245240171074e-05,
      "loss": 1.1082172393798828,
      "num_input_tokens_seen": 3852476672,
      "step": 13550,
      "train_runtime": 131989.0194,
      "train_tokens_per_second": 29187.857
    },
    {
      "epoch": 0.47978027761622444,
      "grad_norm": 1.453125,
      "learning_rate": 3.2575536592322935e-05,
      "loss": 1.1088698387145997,
      "num_input_tokens_seen": 3855333952,
      "step": 13560,
      "train_runtime": 132085.8598,
      "train_tokens_per_second": 29188.09
    },
    {
      "epoch": 0.4801340978799532,
      "grad_norm": 1.4296875,
      "learning_rate": 3.256862518482523e-05,
      "loss": 1.0957657814025878,
      "num_input_tokens_seen": 3858135808,
      "step": 13570,
      "train_runtime": 132180.017,
      "train_tokens_per_second": 29188.495
    },
    {
      "epoch": 0.48048791814368197,
      "grad_norm": 1.4765625,
      "learning_rate": 3.256171817454994e-05,
      "loss": 1.1019087791442872,
      "num_input_tokens_seen": 3860974400,
      "step": 13580,
      "train_runtime": 132276.8632,
      "train_tokens_per_second": 29188.585
    },
    {
      "epoch": 0.4808417384074108,
      "grad_norm": 1.40625,
      "learning_rate": 3.255481555683633e-05,
      "loss": 1.1147951126098632,
      "num_input_tokens_seen": 3863829120,
      "step": 13590,
      "train_runtime": 132375.8881,
      "train_tokens_per_second": 29188.315
    },
    {
      "epoch": 0.48119555867113956,
      "grad_norm": 1.421875,
      "learning_rate": 3.254791732703057e-05,
      "loss": 1.1057777404785156,
      "num_input_tokens_seen": 3866681408,
      "step": 13600,
      "train_runtime": 132474.6392,
      "train_tokens_per_second": 29188.088
    },
    {
      "epoch": 0.4815493789348683,
      "grad_norm": 1.4765625,
      "learning_rate": 3.254102348048575e-05,
      "loss": 1.1031816482543946,
      "num_input_tokens_seen": 3869484160,
      "step": 13610,
      "train_runtime": 132569.6644,
      "train_tokens_per_second": 29188.308
    },
    {
      "epoch": 0.4819031991985971,
      "grad_norm": 1.453125,
      "learning_rate": 3.25341340125618e-05,
      "loss": 1.102052879333496,
      "num_input_tokens_seen": 3872334656,
      "step": 13620,
      "train_runtime": 132665.444,
      "train_tokens_per_second": 29188.721
    },
    {
      "epoch": 0.4822570194623259,
      "grad_norm": 1.40625,
      "learning_rate": 3.2527248918625575e-05,
      "loss": 1.1104936599731445,
      "num_input_tokens_seen": 3875176384,
      "step": 13630,
      "train_runtime": 132761.4324,
      "train_tokens_per_second": 29189.022
    },
    {
      "epoch": 0.4826108397260547,
      "grad_norm": 1.4609375,
      "learning_rate": 3.252036819405075e-05,
      "loss": 1.1074193954467773,
      "num_input_tokens_seen": 3877983360,
      "step": 13640,
      "train_runtime": 132856.1478,
      "train_tokens_per_second": 29189.341
    },
    {
      "epoch": 0.48296465998978344,
      "grad_norm": 1.4765625,
      "learning_rate": 3.251349183421788e-05,
      "loss": 1.103062057495117,
      "num_input_tokens_seen": 3880825280,
      "step": 13650,
      "train_runtime": 132953.0926,
      "train_tokens_per_second": 29189.432
    },
    {
      "epoch": 0.4833184802535122,
      "grad_norm": 1.484375,
      "learning_rate": 3.250661983451434e-05,
      "loss": 1.101047897338867,
      "num_input_tokens_seen": 3883634624,
      "step": 13660,
      "train_runtime": 133047.7782,
      "train_tokens_per_second": 29189.774
    },
    {
      "epoch": 0.48367230051724097,
      "grad_norm": 1.453125,
      "learning_rate": 3.2499752190334326e-05,
      "loss": 1.1017118453979493,
      "num_input_tokens_seen": 3886481728,
      "step": 13670,
      "train_runtime": 133148.9144,
      "train_tokens_per_second": 29188.985
    },
    {
      "epoch": 0.4840261207809698,
      "grad_norm": 1.4140625,
      "learning_rate": 3.2492888897078834e-05,
      "loss": 1.1198915481567382,
      "num_input_tokens_seen": 3889359232,
      "step": 13680,
      "train_runtime": 133248.3306,
      "train_tokens_per_second": 29188.803
    },
    {
      "epoch": 0.48437994104469856,
      "grad_norm": 1.4453125,
      "learning_rate": 3.248602995015567e-05,
      "loss": 1.0979561805725098,
      "num_input_tokens_seen": 3892185280,
      "step": 13690,
      "train_runtime": 133343.6889,
      "train_tokens_per_second": 29189.123
    },
    {
      "epoch": 0.4847337613084273,
      "grad_norm": 1.3984375,
      "learning_rate": 3.247917534497943e-05,
      "loss": 1.0981789588928224,
      "num_input_tokens_seen": 3895009856,
      "step": 13700,
      "train_runtime": 133441.3657,
      "train_tokens_per_second": 29188.924
    },
    {
      "epoch": 0.4850875815721561,
      "grad_norm": 1.4609375,
      "learning_rate": 3.247232507697145e-05,
      "loss": 1.1070235252380372,
      "num_input_tokens_seen": 3897859200,
      "step": 13710,
      "train_runtime": 133540.0506,
      "train_tokens_per_second": 29188.69
    },
    {
      "epoch": 0.4854414018358849,
      "grad_norm": 1.4921875,
      "learning_rate": 3.246547914155985e-05,
      "loss": 1.1151971817016602,
      "num_input_tokens_seen": 3900682816,
      "step": 13720,
      "train_runtime": 133633.4897,
      "train_tokens_per_second": 29189.411
    },
    {
      "epoch": 0.4857952220996137,
      "grad_norm": 1.421875,
      "learning_rate": 3.245863753417949e-05,
      "loss": 1.124067783355713,
      "num_input_tokens_seen": 3903496256,
      "step": 13730,
      "train_runtime": 133727.4919,
      "train_tokens_per_second": 29189.931
    },
    {
      "epoch": 0.48614904236334244,
      "grad_norm": 1.40625,
      "learning_rate": 3.2451800250271944e-05,
      "loss": 1.11301851272583,
      "num_input_tokens_seen": 3906388864,
      "step": 13740,
      "train_runtime": 133828.7377,
      "train_tokens_per_second": 29189.462
    },
    {
      "epoch": 0.4865028626270712,
      "grad_norm": 1.5390625,
      "learning_rate": 3.244496728528553e-05,
      "loss": 1.1062323570251464,
      "num_input_tokens_seen": 3909218240,
      "step": 13750,
      "train_runtime": 133927.0602,
      "train_tokens_per_second": 29189.159
    },
    {
      "epoch": 0.48685668289080003,
      "grad_norm": 1.3984375,
      "learning_rate": 3.243813863467525e-05,
      "loss": 1.0976166725158691,
      "num_input_tokens_seen": 3912107584,
      "step": 13760,
      "train_runtime": 134027.7196,
      "train_tokens_per_second": 29188.795
    },
    {
      "epoch": 0.4872105031545288,
      "grad_norm": 1.421875,
      "learning_rate": 3.243131429390281e-05,
      "loss": 1.102048683166504,
      "num_input_tokens_seen": 3914896384,
      "step": 13770,
      "train_runtime": 134120.97,
      "train_tokens_per_second": 29189.294
    },
    {
      "epoch": 0.48756432341825756,
      "grad_norm": 1.40625,
      "learning_rate": 3.2424494258436594e-05,
      "loss": 1.0953975677490235,
      "num_input_tokens_seen": 3917735680,
      "step": 13780,
      "train_runtime": 134220.2986,
      "train_tokens_per_second": 29188.846
    },
    {
      "epoch": 0.4879181436819863,
      "grad_norm": 1.453125,
      "learning_rate": 3.241767852375166e-05,
      "loss": 1.0973093032836914,
      "num_input_tokens_seen": 3920528640,
      "step": 13790,
      "train_runtime": 134315.0908,
      "train_tokens_per_second": 29189.041
    },
    {
      "epoch": 0.48827196394571515,
      "grad_norm": 1.4609375,
      "learning_rate": 3.241086708532971e-05,
      "loss": 1.0930806159973145,
      "num_input_tokens_seen": 3923366016,
      "step": 13800,
      "train_runtime": 134411.4754,
      "train_tokens_per_second": 29189.219
    },
    {
      "epoch": 0.4886257842094439,
      "grad_norm": 1.375,
      "learning_rate": 3.24040599386591e-05,
      "loss": 1.1080178260803222,
      "num_input_tokens_seen": 3926291648,
      "step": 13810,
      "train_runtime": 134510.1931,
      "train_tokens_per_second": 29189.547
    },
    {
      "epoch": 0.4889796044731727,
      "grad_norm": 1.453125,
      "learning_rate": 3.23972570792348e-05,
      "loss": 1.096669578552246,
      "num_input_tokens_seen": 3929174336,
      "step": 13820,
      "train_runtime": 134609.8358,
      "train_tokens_per_second": 29189.355
    },
    {
      "epoch": 0.48933342473690145,
      "grad_norm": 1.4765625,
      "learning_rate": 3.239045850255842e-05,
      "loss": 1.1071681022644042,
      "num_input_tokens_seen": 3932069312,
      "step": 13830,
      "train_runtime": 134709.4532,
      "train_tokens_per_second": 29189.26
    },
    {
      "epoch": 0.48968724500063027,
      "grad_norm": 1.484375,
      "learning_rate": 3.238366420413817e-05,
      "loss": 1.1096026420593261,
      "num_input_tokens_seen": 3934879616,
      "step": 13840,
      "train_runtime": 134803.0882,
      "train_tokens_per_second": 29189.833
    },
    {
      "epoch": 0.49004106526435903,
      "grad_norm": 1.453125,
      "learning_rate": 3.237687417948882e-05,
      "loss": 1.1094367980957032,
      "num_input_tokens_seen": 3937755456,
      "step": 13850,
      "train_runtime": 134900.8932,
      "train_tokens_per_second": 29189.988
    },
    {
      "epoch": 0.4903948855280878,
      "grad_norm": 1.4140625,
      "learning_rate": 3.2370088424131776e-05,
      "loss": 1.1118120193481444,
      "num_input_tokens_seen": 3940664064,
      "step": 13860,
      "train_runtime": 135002.1294,
      "train_tokens_per_second": 29189.644
    },
    {
      "epoch": 0.49074870579181656,
      "grad_norm": 1.484375,
      "learning_rate": 3.236330693359497e-05,
      "loss": 1.0917236328125,
      "num_input_tokens_seen": 3943483520,
      "step": 13870,
      "train_runtime": 135097.2743,
      "train_tokens_per_second": 29189.956
    },
    {
      "epoch": 0.4911025260555454,
      "grad_norm": 1.453125,
      "learning_rate": 3.2356529703412894e-05,
      "loss": 1.1113127708435058,
      "num_input_tokens_seen": 3946334144,
      "step": 13880,
      "train_runtime": 135195.1216,
      "train_tokens_per_second": 29189.915
    },
    {
      "epoch": 0.49145634631927415,
      "grad_norm": 1.4921875,
      "learning_rate": 3.234975672912661e-05,
      "loss": 1.121194076538086,
      "num_input_tokens_seen": 3949208896,
      "step": 13890,
      "train_runtime": 135293.4259,
      "train_tokens_per_second": 29189.954
    },
    {
      "epoch": 0.4918101665830029,
      "grad_norm": 1.515625,
      "learning_rate": 3.234298800628368e-05,
      "loss": 1.107191276550293,
      "num_input_tokens_seen": 3952040192,
      "step": 13900,
      "train_runtime": 135390.6827,
      "train_tokens_per_second": 29189.898
    },
    {
      "epoch": 0.4921639868467317,
      "grad_norm": 1.4296875,
      "learning_rate": 3.2336223530438195e-05,
      "loss": 1.09014949798584,
      "num_input_tokens_seen": 3954881216,
      "step": 13910,
      "train_runtime": 135488.2664,
      "train_tokens_per_second": 29189.843
    },
    {
      "epoch": 0.49251780711046045,
      "grad_norm": 1.3828125,
      "learning_rate": 3.232946329715076e-05,
      "loss": 1.0901865005493163,
      "num_input_tokens_seen": 3957707456,
      "step": 13920,
      "train_runtime": 135583.9987,
      "train_tokens_per_second": 29190.078
    },
    {
      "epoch": 0.49287162737418927,
      "grad_norm": 1.484375,
      "learning_rate": 3.2322707301988456e-05,
      "loss": 1.1042044639587403,
      "num_input_tokens_seen": 3960528768,
      "step": 13930,
      "train_runtime": 135676.7127,
      "train_tokens_per_second": 29190.925
    },
    {
      "epoch": 0.49322544763791804,
      "grad_norm": 1.4921875,
      "learning_rate": 3.231595554052488e-05,
      "loss": 1.0973613739013672,
      "num_input_tokens_seen": 3963380224,
      "step": 13940,
      "train_runtime": 135774.1198,
      "train_tokens_per_second": 29190.984
    },
    {
      "epoch": 0.4935792679016468,
      "grad_norm": 1.375,
      "learning_rate": 3.230920800834005e-05,
      "loss": 1.109498882293701,
      "num_input_tokens_seen": 3966185728,
      "step": 13950,
      "train_runtime": 135870.4554,
      "train_tokens_per_second": 29190.936
    },
    {
      "epoch": 0.49393308816537557,
      "grad_norm": 1.46875,
      "learning_rate": 3.2302464701020486e-05,
      "loss": 1.118125820159912,
      "num_input_tokens_seen": 3968997120,
      "step": 13960,
      "train_runtime": 135964.7497,
      "train_tokens_per_second": 29191.369
    },
    {
      "epoch": 0.4942869084291044,
      "grad_norm": 1.4765625,
      "learning_rate": 3.2295725614159126e-05,
      "loss": 1.0873123168945313,
      "num_input_tokens_seen": 3971827776,
      "step": 13970,
      "train_runtime": 136060.5239,
      "train_tokens_per_second": 29191.625
    },
    {
      "epoch": 0.49464072869283315,
      "grad_norm": 1.453125,
      "learning_rate": 3.228899074335536e-05,
      "loss": 1.0985291481018067,
      "num_input_tokens_seen": 3974702400,
      "step": 13980,
      "train_runtime": 136162.2762,
      "train_tokens_per_second": 29190.922
    },
    {
      "epoch": 0.4949945489565619,
      "grad_norm": 1.4453125,
      "learning_rate": 3.228226008421498e-05,
      "loss": 1.109107780456543,
      "num_input_tokens_seen": 3977531136,
      "step": 13990,
      "train_runtime": 136257.5528,
      "train_tokens_per_second": 29191.271
    },
    {
      "epoch": 0.4953483692202907,
      "grad_norm": 1.4453125,
      "learning_rate": 3.2275533632350193e-05,
      "loss": 1.0951703071594239,
      "num_input_tokens_seen": 3980384000,
      "step": 14000,
      "train_runtime": 136356.6963,
      "train_tokens_per_second": 29190.968
    },
    {
      "epoch": 0.4957021894840195,
      "grad_norm": 1.421875,
      "learning_rate": 3.226881138337963e-05,
      "loss": 1.1000097274780274,
      "num_input_tokens_seen": 3983229632,
      "step": 14010,
      "train_runtime": 136454.7301,
      "train_tokens_per_second": 29190.851
    },
    {
      "epoch": 0.49605600974774827,
      "grad_norm": 1.4375,
      "learning_rate": 3.2262093332928256e-05,
      "loss": 1.0987120628356934,
      "num_input_tokens_seen": 3986041472,
      "step": 14020,
      "train_runtime": 136550.3243,
      "train_tokens_per_second": 29191.007
    },
    {
      "epoch": 0.49640983001147704,
      "grad_norm": 1.4765625,
      "learning_rate": 3.225537947662746e-05,
      "loss": 1.0936863899230957,
      "num_input_tokens_seen": 3988832896,
      "step": 14030,
      "train_runtime": 136641.373,
      "train_tokens_per_second": 29191.985
    },
    {
      "epoch": 0.4967636502752058,
      "grad_norm": 1.4609375,
      "learning_rate": 3.224866981011494e-05,
      "loss": 1.1051401138305663,
      "num_input_tokens_seen": 3991680640,
      "step": 14040,
      "train_runtime": 136737.4792,
      "train_tokens_per_second": 29192.294
    },
    {
      "epoch": 0.4971174705389346,
      "grad_norm": 1.46875,
      "learning_rate": 3.22419643290348e-05,
      "loss": 1.1136377334594727,
      "num_input_tokens_seen": 3994563456,
      "step": 14050,
      "train_runtime": 136835.8252,
      "train_tokens_per_second": 29192.38
    },
    {
      "epoch": 0.4974712908026634,
      "grad_norm": 1.4140625,
      "learning_rate": 3.2235263029037446e-05,
      "loss": 1.1218993186950683,
      "num_input_tokens_seen": 3997392256,
      "step": 14060,
      "train_runtime": 136935.7313,
      "train_tokens_per_second": 29191.74
    },
    {
      "epoch": 0.49782511106639216,
      "grad_norm": 1.4375,
      "learning_rate": 3.222856590577962e-05,
      "loss": 1.1009552001953125,
      "num_input_tokens_seen": 4000232832,
      "step": 14070,
      "train_runtime": 137032.8476,
      "train_tokens_per_second": 29191.781
    },
    {
      "epoch": 0.4981789313301209,
      "grad_norm": 1.4296875,
      "learning_rate": 3.222187295492436e-05,
      "loss": 1.0966402053833009,
      "num_input_tokens_seen": 4003073536,
      "step": 14080,
      "train_runtime": 137128.9667,
      "train_tokens_per_second": 29192.035
    },
    {
      "epoch": 0.49853275159384974,
      "grad_norm": 1.46875,
      "learning_rate": 3.221518417214104e-05,
      "loss": 1.1095767974853517,
      "num_input_tokens_seen": 4005809600,
      "step": 14090,
      "train_runtime": 137220.6063,
      "train_tokens_per_second": 29192.479
    },
    {
      "epoch": 0.4988865718575785,
      "grad_norm": 1.4296875,
      "learning_rate": 3.22084995531053e-05,
      "loss": 1.106474018096924,
      "num_input_tokens_seen": 4008653568,
      "step": 14100,
      "train_runtime": 137318.9791,
      "train_tokens_per_second": 29192.276
    },
    {
      "epoch": 0.4992403921213073,
      "grad_norm": 1.4140625,
      "learning_rate": 3.220181909349907e-05,
      "loss": 1.1004980087280274,
      "num_input_tokens_seen": 4011502592,
      "step": 14110,
      "train_runtime": 137417.7579,
      "train_tokens_per_second": 29192.025
    },
    {
      "epoch": 0.49959421238503604,
      "grad_norm": 1.4609375,
      "learning_rate": 3.219514278901053e-05,
      "loss": 1.0978187561035155,
      "num_input_tokens_seen": 4014291200,
      "step": 14120,
      "train_runtime": 137511.4612,
      "train_tokens_per_second": 29192.412
    },
    {
      "epoch": 0.49994803264876486,
      "grad_norm": 1.4375,
      "learning_rate": 3.218847063533413e-05,
      "loss": 1.097608757019043,
      "num_input_tokens_seen": 4017122112,
      "step": 14130,
      "train_runtime": 137606.7558,
      "train_tokens_per_second": 29192.768
    },
    {
      "epoch": 0.5003018529124936,
      "grad_norm": 1.453125,
      "learning_rate": 3.218180262817055e-05,
      "loss": 1.0966375350952149,
      "num_input_tokens_seen": 4019970816,
      "step": 14140,
      "train_runtime": 137704.9447,
      "train_tokens_per_second": 29192.64
    },
    {
      "epoch": 0.5006556731762224,
      "grad_norm": 1.4375,
      "learning_rate": 3.217513876322674e-05,
      "loss": 1.089796257019043,
      "num_input_tokens_seen": 4022749120,
      "step": 14150,
      "train_runtime": 137801.0757,
      "train_tokens_per_second": 29192.436
    },
    {
      "epoch": 0.5010094934399512,
      "grad_norm": 1.4453125,
      "learning_rate": 3.216847903621581e-05,
      "loss": 1.1036855697631835,
      "num_input_tokens_seen": 4025592000,
      "step": 14160,
      "train_runtime": 137897.3888,
      "train_tokens_per_second": 29192.663
    },
    {
      "epoch": 0.5013633137036799,
      "grad_norm": 1.40625,
      "learning_rate": 3.216182344285713e-05,
      "loss": 1.1118246078491212,
      "num_input_tokens_seen": 4028470080,
      "step": 14170,
      "train_runtime": 137996.0792,
      "train_tokens_per_second": 29192.642
    },
    {
      "epoch": 0.5017171339674087,
      "grad_norm": 1.453125,
      "learning_rate": 3.215517197887625e-05,
      "loss": 1.1060211181640625,
      "num_input_tokens_seen": 4031278400,
      "step": 14180,
      "train_runtime": 138091.492,
      "train_tokens_per_second": 29192.808
    },
    {
      "epoch": 0.5020709542311375,
      "grad_norm": 1.515625,
      "learning_rate": 3.214852464000488e-05,
      "loss": 1.0942562103271485,
      "num_input_tokens_seen": 4034128192,
      "step": 14190,
      "train_runtime": 138186.4638,
      "train_tokens_per_second": 29193.367
    },
    {
      "epoch": 0.5024247744948663,
      "grad_norm": 1.515625,
      "learning_rate": 3.2141881421980945e-05,
      "loss": 1.0967092514038086,
      "num_input_tokens_seen": 4036948608,
      "step": 14200,
      "train_runtime": 138282.0724,
      "train_tokens_per_second": 29193.579
    },
    {
      "epoch": 0.5027785947585951,
      "grad_norm": 1.46875,
      "learning_rate": 3.213524232054851e-05,
      "loss": 1.0930200576782227,
      "num_input_tokens_seen": 4039743232,
      "step": 14210,
      "train_runtime": 138375.0017,
      "train_tokens_per_second": 29194.169
    },
    {
      "epoch": 0.5031324150223239,
      "grad_norm": 1.46875,
      "learning_rate": 3.21286073314578e-05,
      "loss": 1.105172348022461,
      "num_input_tokens_seen": 4042558016,
      "step": 14220,
      "train_runtime": 138473.5501,
      "train_tokens_per_second": 29193.72
    },
    {
      "epoch": 0.5034862352860526,
      "grad_norm": 1.453125,
      "learning_rate": 3.2121976450465155e-05,
      "loss": 1.1135007858276367,
      "num_input_tokens_seen": 4045371264,
      "step": 14230,
      "train_runtime": 138568.2037,
      "train_tokens_per_second": 29194.08
    },
    {
      "epoch": 0.5038400555497814,
      "grad_norm": 1.484375,
      "learning_rate": 3.211534967333308e-05,
      "loss": 1.08929443359375,
      "num_input_tokens_seen": 4048218176,
      "step": 14240,
      "train_runtime": 138665.5178,
      "train_tokens_per_second": 29194.123
    },
    {
      "epoch": 0.5041938758135102,
      "grad_norm": 1.40625,
      "learning_rate": 3.210872699583019e-05,
      "loss": 1.0952016830444335,
      "num_input_tokens_seen": 4051051456,
      "step": 14250,
      "train_runtime": 138761.9769,
      "train_tokens_per_second": 29194.247
    },
    {
      "epoch": 0.5045476960772389,
      "grad_norm": 1.4453125,
      "learning_rate": 3.210210841373118e-05,
      "loss": 1.1050315856933595,
      "num_input_tokens_seen": 4053911744,
      "step": 14260,
      "train_runtime": 138861.051,
      "train_tokens_per_second": 29194.016
    },
    {
      "epoch": 0.5049015163409677,
      "grad_norm": 1.4609375,
      "learning_rate": 3.2095493922816855e-05,
      "loss": 1.1054222106933593,
      "num_input_tokens_seen": 4056795584,
      "step": 14270,
      "train_runtime": 138959.7546,
      "train_tokens_per_second": 29194.032
    },
    {
      "epoch": 0.5052553366046966,
      "grad_norm": 1.4375,
      "learning_rate": 3.2088883518874105e-05,
      "loss": 1.1054767608642577,
      "num_input_tokens_seen": 4059580480,
      "step": 14280,
      "train_runtime": 139055.2549,
      "train_tokens_per_second": 29194.01
    },
    {
      "epoch": 0.5056091568684253,
      "grad_norm": 1.4609375,
      "learning_rate": 3.208227719769589e-05,
      "loss": 1.0909000396728517,
      "num_input_tokens_seen": 4062394432,
      "step": 14290,
      "train_runtime": 139151.5203,
      "train_tokens_per_second": 29194.036
    },
    {
      "epoch": 0.5059629771321541,
      "grad_norm": 1.4375,
      "learning_rate": 3.207567495508124e-05,
      "loss": 1.104444408416748,
      "num_input_tokens_seen": 4065237184,
      "step": 14300,
      "train_runtime": 139248.055,
      "train_tokens_per_second": 29194.212
    },
    {
      "epoch": 0.5063167973958829,
      "grad_norm": 1.53125,
      "learning_rate": 3.2069076786835205e-05,
      "loss": 1.1105491638183593,
      "num_input_tokens_seen": 4068040320,
      "step": 14310,
      "train_runtime": 139344.5755,
      "train_tokens_per_second": 29194.106
    },
    {
      "epoch": 0.5066706176596116,
      "grad_norm": 1.4375,
      "learning_rate": 3.2062482688768904e-05,
      "loss": 1.100996971130371,
      "num_input_tokens_seen": 4070913536,
      "step": 14320,
      "train_runtime": 139445.4364,
      "train_tokens_per_second": 29193.595
    },
    {
      "epoch": 0.5070244379233404,
      "grad_norm": 1.3984375,
      "learning_rate": 3.205589265669947e-05,
      "loss": 1.0908689498901367,
      "num_input_tokens_seen": 4073779840,
      "step": 14330,
      "train_runtime": 139544.2297,
      "train_tokens_per_second": 29193.467
    },
    {
      "epoch": 0.5073782581870692,
      "grad_norm": 1.4296875,
      "learning_rate": 3.204930668645005e-05,
      "loss": 1.116949462890625,
      "num_input_tokens_seen": 4076619840,
      "step": 14340,
      "train_runtime": 139640.4344,
      "train_tokens_per_second": 29193.692
    },
    {
      "epoch": 0.5077320784507979,
      "grad_norm": 1.4140625,
      "learning_rate": 3.20427247738498e-05,
      "loss": 1.0988884925842286,
      "num_input_tokens_seen": 4079465216,
      "step": 14350,
      "train_runtime": 139739.5916,
      "train_tokens_per_second": 29193.339
    },
    {
      "epoch": 0.5080858987145268,
      "grad_norm": 1.46875,
      "learning_rate": 3.2036146914733854e-05,
      "loss": 1.1020221710205078,
      "num_input_tokens_seen": 4082283904,
      "step": 14360,
      "train_runtime": 139835.7909,
      "train_tokens_per_second": 29193.412
    },
    {
      "epoch": 0.5084397189782556,
      "grad_norm": 1.375,
      "learning_rate": 3.202957310494336e-05,
      "loss": 1.1072748184204102,
      "num_input_tokens_seen": 4085162240,
      "step": 14370,
      "train_runtime": 139933.813,
      "train_tokens_per_second": 29193.532
    },
    {
      "epoch": 0.5087935392419843,
      "grad_norm": 1.5,
      "learning_rate": 3.202300334032542e-05,
      "loss": 1.0912253379821777,
      "num_input_tokens_seen": 4088018432,
      "step": 14380,
      "train_runtime": 140031.6413,
      "train_tokens_per_second": 29193.534
    },
    {
      "epoch": 0.5091473595057131,
      "grad_norm": 1.453125,
      "learning_rate": 3.201643761673308e-05,
      "loss": 1.114656925201416,
      "num_input_tokens_seen": 4090857408,
      "step": 14390,
      "train_runtime": 140130.7342,
      "train_tokens_per_second": 29193.149
    },
    {
      "epoch": 0.5095011797694419,
      "grad_norm": 1.4609375,
      "learning_rate": 3.200987593002536e-05,
      "loss": 1.1161548614501953,
      "num_input_tokens_seen": 4093682816,
      "step": 14400,
      "train_runtime": 140227.1308,
      "train_tokens_per_second": 29193.23
    },
    {
      "epoch": 0.5098550000331706,
      "grad_norm": 1.3984375,
      "learning_rate": 3.200331827606721e-05,
      "loss": 1.0994593620300293,
      "num_input_tokens_seen": 4096522432,
      "step": 14410,
      "train_runtime": 140324.8795,
      "train_tokens_per_second": 29193.13
    },
    {
      "epoch": 0.5102088202968994,
      "grad_norm": 1.359375,
      "learning_rate": 3.199676465072951e-05,
      "loss": 1.0772233963012696,
      "num_input_tokens_seen": 4099334656,
      "step": 14420,
      "train_runtime": 140420.6714,
      "train_tokens_per_second": 29193.242
    },
    {
      "epoch": 0.5105626405606282,
      "grad_norm": 1.46875,
      "learning_rate": 3.1990215049889046e-05,
      "loss": 1.0929615020751953,
      "num_input_tokens_seen": 4102225472,
      "step": 14430,
      "train_runtime": 140520.7501,
      "train_tokens_per_second": 29193.023
    },
    {
      "epoch": 0.5109164608243569,
      "grad_norm": 1.46875,
      "learning_rate": 3.198366946942851e-05,
      "loss": 1.106859016418457,
      "num_input_tokens_seen": 4105131328,
      "step": 14440,
      "train_runtime": 140622.0598,
      "train_tokens_per_second": 29192.655
    },
    {
      "epoch": 0.5112702810880858,
      "grad_norm": 1.4375,
      "learning_rate": 3.1977127905236514e-05,
      "loss": 1.10336275100708,
      "num_input_tokens_seen": 4107939968,
      "step": 14450,
      "train_runtime": 140716.6683,
      "train_tokens_per_second": 29192.988
    },
    {
      "epoch": 0.5116241013518146,
      "grad_norm": 1.4296875,
      "learning_rate": 3.197059035320752e-05,
      "loss": 1.1046796798706056,
      "num_input_tokens_seen": 4110789568,
      "step": 14460,
      "train_runtime": 140816.2927,
      "train_tokens_per_second": 29192.571
    },
    {
      "epoch": 0.5119779216155433,
      "grad_norm": 1.4140625,
      "learning_rate": 3.196405680924189e-05,
      "loss": 1.0953731536865234,
      "num_input_tokens_seen": 4113665408,
      "step": 14470,
      "train_runtime": 140915.3778,
      "train_tokens_per_second": 29192.452
    },
    {
      "epoch": 0.5123317418792721,
      "grad_norm": 1.4453125,
      "learning_rate": 3.195752726924582e-05,
      "loss": 1.106933879852295,
      "num_input_tokens_seen": 4116458560,
      "step": 14480,
      "train_runtime": 141010.5413,
      "train_tokens_per_second": 29192.559
    },
    {
      "epoch": 0.5126855621430009,
      "grad_norm": 1.484375,
      "learning_rate": 3.195100172913139e-05,
      "loss": 1.1035601615905761,
      "num_input_tokens_seen": 4119314880,
      "step": 14490,
      "train_runtime": 141110.1157,
      "train_tokens_per_second": 29192.201
    },
    {
      "epoch": 0.5130393824067296,
      "grad_norm": 1.4140625,
      "learning_rate": 3.19444801848165e-05,
      "loss": 1.1016318321228027,
      "num_input_tokens_seen": 4122162112,
      "step": 14500,
      "train_runtime": 141207.486,
      "train_tokens_per_second": 29192.235
    },
    {
      "epoch": 0.5133932026704584,
      "grad_norm": 1.4453125,
      "learning_rate": 3.1937962632224885e-05,
      "loss": 1.100595188140869,
      "num_input_tokens_seen": 4125037696,
      "step": 14510,
      "train_runtime": 141307.1723,
      "train_tokens_per_second": 29191.991
    },
    {
      "epoch": 0.5137470229341872,
      "grad_norm": 1.4609375,
      "learning_rate": 3.193144906728609e-05,
      "loss": 1.089040756225586,
      "num_input_tokens_seen": 4127887424,
      "step": 14520,
      "train_runtime": 141403.0502,
      "train_tokens_per_second": 29192.351
    },
    {
      "epoch": 0.514100843197916,
      "grad_norm": 1.3984375,
      "learning_rate": 3.1924939485935494e-05,
      "loss": 1.1045886993408203,
      "num_input_tokens_seen": 4130725888,
      "step": 14530,
      "train_runtime": 141499.7567,
      "train_tokens_per_second": 29192.459
    },
    {
      "epoch": 0.5144546634616448,
      "grad_norm": 1.5,
      "learning_rate": 3.1918433884114253e-05,
      "loss": 1.0892650604248046,
      "num_input_tokens_seen": 4133562560,
      "step": 14540,
      "train_runtime": 141596.0992,
      "train_tokens_per_second": 29192.63
    },
    {
      "epoch": 0.5148084837253736,
      "grad_norm": 1.453125,
      "learning_rate": 3.191193225776931e-05,
      "loss": 1.1099250793457032,
      "num_input_tokens_seen": 4136477056,
      "step": 14550,
      "train_runtime": 141698.2785,
      "train_tokens_per_second": 29192.148
    },
    {
      "epoch": 0.5151623039891023,
      "grad_norm": 1.5390625,
      "learning_rate": 3.190543460285339e-05,
      "loss": 1.1154672622680664,
      "num_input_tokens_seen": 4139378048,
      "step": 14560,
      "train_runtime": 141801.1784,
      "train_tokens_per_second": 29191.422
    },
    {
      "epoch": 0.5155161242528311,
      "grad_norm": 1.46875,
      "learning_rate": 3.189894091532499e-05,
      "loss": 1.1032766342163085,
      "num_input_tokens_seen": 4142189568,
      "step": 14570,
      "train_runtime": 141896.8435,
      "train_tokens_per_second": 29191.555
    },
    {
      "epoch": 0.5158699445165599,
      "grad_norm": 1.4375,
      "learning_rate": 3.1892451191148346e-05,
      "loss": 1.1020416259765624,
      "num_input_tokens_seen": 4144996480,
      "step": 14580,
      "train_runtime": 141991.6749,
      "train_tokens_per_second": 29191.827
    },
    {
      "epoch": 0.5162237647802886,
      "grad_norm": 1.453125,
      "learning_rate": 3.1885965426293465e-05,
      "loss": 1.0892604827880858,
      "num_input_tokens_seen": 4147858752,
      "step": 14590,
      "train_runtime": 142092.2194,
      "train_tokens_per_second": 29191.315
    },
    {
      "epoch": 0.5165775850440174,
      "grad_norm": 1.453125,
      "learning_rate": 3.187948361673606e-05,
      "loss": 1.0985610961914063,
      "num_input_tokens_seen": 4150731072,
      "step": 14600,
      "train_runtime": 142193.5765,
      "train_tokens_per_second": 29190.707
    },
    {
      "epoch": 0.5169314053077463,
      "grad_norm": 1.4296875,
      "learning_rate": 3.187300575845759e-05,
      "loss": 1.1001857757568358,
      "num_input_tokens_seen": 4153606400,
      "step": 14610,
      "train_runtime": 142295.3933,
      "train_tokens_per_second": 29190.027
    },
    {
      "epoch": 0.517285225571475,
      "grad_norm": 1.4375,
      "learning_rate": 3.186653184744521e-05,
      "loss": 1.0890081405639649,
      "num_input_tokens_seen": 4156454976,
      "step": 14620,
      "train_runtime": 142397.1467,
      "train_tokens_per_second": 29189.173
    },
    {
      "epoch": 0.5176390458352038,
      "grad_norm": 1.4921875,
      "learning_rate": 3.18600618796918e-05,
      "loss": 1.1146483421325684,
      "num_input_tokens_seen": 4159297856,
      "step": 14630,
      "train_runtime": 142495.3299,
      "train_tokens_per_second": 29189.012
    },
    {
      "epoch": 0.5179928660989326,
      "grad_norm": 1.3984375,
      "learning_rate": 3.185359585119591e-05,
      "loss": 1.0927743911743164,
      "num_input_tokens_seen": 4162070592,
      "step": 14640,
      "train_runtime": 142588.3126,
      "train_tokens_per_second": 29189.423
    },
    {
      "epoch": 0.5183466863626613,
      "grad_norm": 1.484375,
      "learning_rate": 3.184713375796178e-05,
      "loss": 1.112596321105957,
      "num_input_tokens_seen": 4164963520,
      "step": 14650,
      "train_runtime": 142687.2477,
      "train_tokens_per_second": 29189.459
    },
    {
      "epoch": 0.5187005066263901,
      "grad_norm": 1.3828125,
      "learning_rate": 3.1840675595999344e-05,
      "loss": 1.1020581245422363,
      "num_input_tokens_seen": 4167799616,
      "step": 14660,
      "train_runtime": 142783.4036,
      "train_tokens_per_second": 29189.664
    },
    {
      "epoch": 0.5190543268901189,
      "grad_norm": 1.4921875,
      "learning_rate": 3.1834221361324155e-05,
      "loss": 1.1092158317565919,
      "num_input_tokens_seen": 4170638912,
      "step": 14670,
      "train_runtime": 142882.0459,
      "train_tokens_per_second": 29189.384
    },
    {
      "epoch": 0.5194081471538476,
      "grad_norm": 1.4921875,
      "learning_rate": 3.182777104995744e-05,
      "loss": 1.1136004447937011,
      "num_input_tokens_seen": 4173507968,
      "step": 14680,
      "train_runtime": 142982.6465,
      "train_tokens_per_second": 29188.913
    },
    {
      "epoch": 0.5197619674175764,
      "grad_norm": 1.4375,
      "learning_rate": 3.182132465792609e-05,
      "loss": 1.1088988304138183,
      "num_input_tokens_seen": 4176281024,
      "step": 14690,
      "train_runtime": 143076.736,
      "train_tokens_per_second": 29189.099
    },
    {
      "epoch": 0.5201157876813053,
      "grad_norm": 1.421875,
      "learning_rate": 3.181488218126259e-05,
      "loss": 1.0977745056152344,
      "num_input_tokens_seen": 4179121664,
      "step": 14700,
      "train_runtime": 143173.1139,
      "train_tokens_per_second": 29189.291
    },
    {
      "epoch": 0.520469607945034,
      "grad_norm": 1.4296875,
      "learning_rate": 3.180844361600506e-05,
      "loss": 1.0890690803527832,
      "num_input_tokens_seen": 4181968960,
      "step": 14710,
      "train_runtime": 143271.9115,
      "train_tokens_per_second": 29189.036
    },
    {
      "epoch": 0.5208234282087628,
      "grad_norm": 1.421875,
      "learning_rate": 3.180200895819722e-05,
      "loss": 1.0961807250976563,
      "num_input_tokens_seen": 4184813760,
      "step": 14720,
      "train_runtime": 143372.0938,
      "train_tokens_per_second": 29188.482
    },
    {
      "epoch": 0.5211772484724916,
      "grad_norm": 1.4609375,
      "learning_rate": 3.1795578203888424e-05,
      "loss": 1.1000530242919921,
      "num_input_tokens_seen": 4187652480,
      "step": 14730,
      "train_runtime": 143467.6217,
      "train_tokens_per_second": 29188.833
    },
    {
      "epoch": 0.5215310687362203,
      "grad_norm": 1.4296875,
      "learning_rate": 3.178915134913357e-05,
      "loss": 1.0909713745117187,
      "num_input_tokens_seen": 4190458368,
      "step": 14740,
      "train_runtime": 143563.7702,
      "train_tokens_per_second": 29188.829
    },
    {
      "epoch": 0.5218848889999491,
      "grad_norm": 1.453125,
      "learning_rate": 3.178272838999316e-05,
      "loss": 1.109012985229492,
      "num_input_tokens_seen": 4193264512,
      "step": 14750,
      "train_runtime": 143656.0229,
      "train_tokens_per_second": 29189.619
    },
    {
      "epoch": 0.5222387092636779,
      "grad_norm": 1.4453125,
      "learning_rate": 3.1776309322533274e-05,
      "loss": 1.1129315376281739,
      "num_input_tokens_seen": 4196158144,
      "step": 14760,
      "train_runtime": 143756.3909,
      "train_tokens_per_second": 29189.368
    },
    {
      "epoch": 0.5225925295274066,
      "grad_norm": 1.4453125,
      "learning_rate": 3.1769894142825536e-05,
      "loss": 1.0914870262145997,
      "num_input_tokens_seen": 4199005248,
      "step": 14770,
      "train_runtime": 143853.7149,
      "train_tokens_per_second": 29189.411
    },
    {
      "epoch": 0.5229463497911355,
      "grad_norm": 1.421875,
      "learning_rate": 3.176348284694712e-05,
      "loss": 1.095636749267578,
      "num_input_tokens_seen": 4201899904,
      "step": 14780,
      "train_runtime": 143951.7153,
      "train_tokens_per_second": 29189.648
    },
    {
      "epoch": 0.5233001700548643,
      "grad_norm": 1.4609375,
      "learning_rate": 3.175707543098075e-05,
      "loss": 1.086642074584961,
      "num_input_tokens_seen": 4204755200,
      "step": 14790,
      "train_runtime": 144048.8902,
      "train_tokens_per_second": 29189.779
    },
    {
      "epoch": 0.523653990318593,
      "grad_norm": 1.4375,
      "learning_rate": 3.1750671891014653e-05,
      "loss": 1.0990318298339843,
      "num_input_tokens_seen": 4207601856,
      "step": 14800,
      "train_runtime": 144144.9564,
      "train_tokens_per_second": 29190.073
    },
    {
      "epoch": 0.5240078105823218,
      "grad_norm": 1.4375,
      "learning_rate": 3.174427222314262e-05,
      "loss": 1.101422119140625,
      "num_input_tokens_seen": 4210502592,
      "step": 14810,
      "train_runtime": 144248.4526,
      "train_tokens_per_second": 29189.239
    },
    {
      "epoch": 0.5243616308460506,
      "grad_norm": 1.421875,
      "learning_rate": 3.173787642346391e-05,
      "loss": 1.101428508758545,
      "num_input_tokens_seen": 4213360320,
      "step": 14820,
      "train_runtime": 144346.3457,
      "train_tokens_per_second": 29189.241
    },
    {
      "epoch": 0.5247154511097794,
      "grad_norm": 1.3984375,
      "learning_rate": 3.173148448808331e-05,
      "loss": 1.1023262977600097,
      "num_input_tokens_seen": 4216256576,
      "step": 14830,
      "train_runtime": 144448.5691,
      "train_tokens_per_second": 29188.635
    },
    {
      "epoch": 0.5250692713735081,
      "grad_norm": 1.3828125,
      "learning_rate": 3.172509641311107e-05,
      "loss": 1.0945629119873046,
      "num_input_tokens_seen": 4219089728,
      "step": 14840,
      "train_runtime": 144545.1205,
      "train_tokens_per_second": 29188.739
    },
    {
      "epoch": 0.5254230916372369,
      "grad_norm": 1.4609375,
      "learning_rate": 3.171871219466293e-05,
      "loss": 1.0991458892822266,
      "num_input_tokens_seen": 4221922816,
      "step": 14850,
      "train_runtime": 144643.6275,
      "train_tokens_per_second": 29188.447
    },
    {
      "epoch": 0.5257769119009658,
      "grad_norm": 1.4921875,
      "learning_rate": 3.171233182886011e-05,
      "loss": 1.0987175941467284,
      "num_input_tokens_seen": 4224739520,
      "step": 14860,
      "train_runtime": 144738.0802,
      "train_tokens_per_second": 29188.86
    },
    {
      "epoch": 0.5261307321646945,
      "grad_norm": 1.4609375,
      "learning_rate": 3.170595531182928e-05,
      "loss": 1.086920928955078,
      "num_input_tokens_seen": 4227567616,
      "step": 14870,
      "train_runtime": 144834.4178,
      "train_tokens_per_second": 29188.971
    },
    {
      "epoch": 0.5264845524284233,
      "grad_norm": 1.4296875,
      "learning_rate": 3.169958263970256e-05,
      "loss": 1.097539520263672,
      "num_input_tokens_seen": 4230410944,
      "step": 14880,
      "train_runtime": 144931.2304,
      "train_tokens_per_second": 29189.091
    },
    {
      "epoch": 0.5268383726921521,
      "grad_norm": 1.5078125,
      "learning_rate": 3.169321380861751e-05,
      "loss": 1.0943305969238282,
      "num_input_tokens_seen": 4233268416,
      "step": 14890,
      "train_runtime": 145029.8779,
      "train_tokens_per_second": 29188.94
    },
    {
      "epoch": 0.5271921929558808,
      "grad_norm": 1.421875,
      "learning_rate": 3.168684881471711e-05,
      "loss": 1.114631175994873,
      "num_input_tokens_seen": 4236136320,
      "step": 14900,
      "train_runtime": 145126.9686,
      "train_tokens_per_second": 29189.174
    },
    {
      "epoch": 0.5275460132196096,
      "grad_norm": 1.484375,
      "learning_rate": 3.168048765414979e-05,
      "loss": 1.1044181823730468,
      "num_input_tokens_seen": 4238955776,
      "step": 14910,
      "train_runtime": 145223.7081,
      "train_tokens_per_second": 29189.144
    },
    {
      "epoch": 0.5278998334833384,
      "grad_norm": 1.5234375,
      "learning_rate": 3.167413032306936e-05,
      "loss": 1.1040070533752442,
      "num_input_tokens_seen": 4241815808,
      "step": 14920,
      "train_runtime": 145319.6209,
      "train_tokens_per_second": 29189.56
    },
    {
      "epoch": 0.5282536537470671,
      "grad_norm": 1.5234375,
      "learning_rate": 3.166777681763504e-05,
      "loss": 1.100289535522461,
      "num_input_tokens_seen": 4244648448,
      "step": 14930,
      "train_runtime": 145416.3322,
      "train_tokens_per_second": 29189.627
    },
    {
      "epoch": 0.5286074740107959,
      "grad_norm": 1.3828125,
      "learning_rate": 3.166142713401144e-05,
      "loss": 1.0983248710632325,
      "num_input_tokens_seen": 4247458240,
      "step": 14940,
      "train_runtime": 145510.117,
      "train_tokens_per_second": 29190.123
    },
    {
      "epoch": 0.5289612942745248,
      "grad_norm": 1.3984375,
      "learning_rate": 3.165508126836857e-05,
      "loss": 1.0990144729614257,
      "num_input_tokens_seen": 4250291904,
      "step": 14950,
      "train_runtime": 145607.518,
      "train_tokens_per_second": 29190.058
    },
    {
      "epoch": 0.5293151145382535,
      "grad_norm": 1.4609375,
      "learning_rate": 3.164873921688177e-05,
      "loss": 1.1041632652282716,
      "num_input_tokens_seen": 4253113856,
      "step": 14960,
      "train_runtime": 145703.5849,
      "train_tokens_per_second": 29190.18
    },
    {
      "epoch": 0.5296689348019823,
      "grad_norm": 1.5234375,
      "learning_rate": 3.164240097573178e-05,
      "loss": 1.106937789916992,
      "num_input_tokens_seen": 4255949760,
      "step": 14970,
      "train_runtime": 145800.3951,
      "train_tokens_per_second": 29190.248
    },
    {
      "epoch": 0.5300227550657111,
      "grad_norm": 1.4765625,
      "learning_rate": 3.163606654110467e-05,
      "loss": 1.0933317184448241,
      "num_input_tokens_seen": 4258822784,
      "step": 14980,
      "train_runtime": 145897.9241,
      "train_tokens_per_second": 29190.428
    },
    {
      "epoch": 0.5303765753294398,
      "grad_norm": 1.5234375,
      "learning_rate": 3.162973590919187e-05,
      "loss": 1.0996970176696776,
      "num_input_tokens_seen": 4261609088,
      "step": 14990,
      "train_runtime": 145991.9843,
      "train_tokens_per_second": 29190.706
    },
    {
      "epoch": 0.5307303955931686,
      "grad_norm": 1.40625,
      "learning_rate": 3.162340907619012e-05,
      "loss": 1.094344425201416,
      "num_input_tokens_seen": 4264439296,
      "step": 15000,
      "train_runtime": 146089.4406,
      "train_tokens_per_second": 29190.606
    },
    {
      "epoch": 0.5307303955931686,
      "eval_loss": 1.027906060218811,
      "eval_runtime": 8.4623,
      "eval_samples_per_second": 471.266,
      "eval_steps_per_second": 3.781,
      "num_input_tokens_seen": 4264439296,
      "step": 15000
    },
    {
      "epoch": 0.5310842158568974,
      "grad_norm": 1.453125,
      "learning_rate": 3.1617086038301516e-05,
      "loss": 1.1061349868774415,
      "num_input_tokens_seen": 4267301248,
      "step": 15010,
      "train_runtime": 146216.081,
      "train_tokens_per_second": 29184.897
    },
    {
      "epoch": 0.5314380361206261,
      "grad_norm": 1.5078125,
      "learning_rate": 3.161076679173344e-05,
      "loss": 1.093703842163086,
      "num_input_tokens_seen": 4270196416,
      "step": 15020,
      "train_runtime": 146316.0665,
      "train_tokens_per_second": 29184.74
    },
    {
      "epoch": 0.531791856384355,
      "grad_norm": 1.453125,
      "learning_rate": 3.1604451332698575e-05,
      "loss": 1.1053047180175781,
      "num_input_tokens_seen": 4273007872,
      "step": 15030,
      "train_runtime": 146412.4309,
      "train_tokens_per_second": 29184.734
    },
    {
      "epoch": 0.5321456766480838,
      "grad_norm": 1.5078125,
      "learning_rate": 3.1598139657414923e-05,
      "loss": 1.1073984146118163,
      "num_input_tokens_seen": 4275906944,
      "step": 15040,
      "train_runtime": 146512.5482,
      "train_tokens_per_second": 29184.578
    },
    {
      "epoch": 0.5324994969118125,
      "grad_norm": 1.421875,
      "learning_rate": 3.159183176210574e-05,
      "loss": 1.0986339569091796,
      "num_input_tokens_seen": 4278740224,
      "step": 15050,
      "train_runtime": 146609.0843,
      "train_tokens_per_second": 29184.687
    },
    {
      "epoch": 0.5328533171755413,
      "grad_norm": 1.5078125,
      "learning_rate": 3.1585527642999595e-05,
      "loss": 1.1029499053955079,
      "num_input_tokens_seen": 4281597824,
      "step": 15060,
      "train_runtime": 146706.8816,
      "train_tokens_per_second": 29184.71
    },
    {
      "epoch": 0.5332071374392701,
      "grad_norm": 1.46875,
      "learning_rate": 3.1579227296330294e-05,
      "loss": 1.1047273635864259,
      "num_input_tokens_seen": 4284404224,
      "step": 15070,
      "train_runtime": 146800.5694,
      "train_tokens_per_second": 29185.202
    },
    {
      "epoch": 0.5335609577029988,
      "grad_norm": 1.4765625,
      "learning_rate": 3.157293071833691e-05,
      "loss": 1.102030372619629,
      "num_input_tokens_seen": 4287281280,
      "step": 15080,
      "train_runtime": 146898.8729,
      "train_tokens_per_second": 29185.256
    },
    {
      "epoch": 0.5339147779667276,
      "grad_norm": 1.515625,
      "learning_rate": 3.156663790526375e-05,
      "loss": 1.1135922431945802,
      "num_input_tokens_seen": 4290095232,
      "step": 15090,
      "train_runtime": 146992.6547,
      "train_tokens_per_second": 29185.78
    },
    {
      "epoch": 0.5342685982304564,
      "grad_norm": 1.4140625,
      "learning_rate": 3.156034885336039e-05,
      "loss": 1.0953948020935058,
      "num_input_tokens_seen": 4292953728,
      "step": 15100,
      "train_runtime": 147090.8563,
      "train_tokens_per_second": 29185.728
    },
    {
      "epoch": 0.5346224184941852,
      "grad_norm": 1.484375,
      "learning_rate": 3.155406355888161e-05,
      "loss": 1.1062522888183595,
      "num_input_tokens_seen": 4295809728,
      "step": 15110,
      "train_runtime": 147187.2885,
      "train_tokens_per_second": 29186.01
    },
    {
      "epoch": 0.534976238757914,
      "grad_norm": 1.4765625,
      "learning_rate": 3.1547782018087407e-05,
      "loss": 1.1058372497558593,
      "num_input_tokens_seen": 4298643584,
      "step": 15120,
      "train_runtime": 147284.5594,
      "train_tokens_per_second": 29185.976
    },
    {
      "epoch": 0.5353300590216428,
      "grad_norm": 1.5,
      "learning_rate": 3.154150422724299e-05,
      "loss": 1.1000194549560547,
      "num_input_tokens_seen": 4301509632,
      "step": 15130,
      "train_runtime": 147381.6765,
      "train_tokens_per_second": 29186.19
    },
    {
      "epoch": 0.5356838792853715,
      "grad_norm": 1.453125,
      "learning_rate": 3.1535230182618783e-05,
      "loss": 1.094675350189209,
      "num_input_tokens_seen": 4304355904,
      "step": 15140,
      "train_runtime": 147480.4402,
      "train_tokens_per_second": 29185.944
    },
    {
      "epoch": 0.5360376995491003,
      "grad_norm": 1.3984375,
      "learning_rate": 3.1528959880490387e-05,
      "loss": 1.1069917678833008,
      "num_input_tokens_seen": 4307218112,
      "step": 15150,
      "train_runtime": 147576.8599,
      "train_tokens_per_second": 29186.27
    },
    {
      "epoch": 0.5363915198128291,
      "grad_norm": 1.421875,
      "learning_rate": 3.152269331713859e-05,
      "loss": 1.106736946105957,
      "num_input_tokens_seen": 4310026432,
      "step": 15160,
      "train_runtime": 147671.2128,
      "train_tokens_per_second": 29186.639
    },
    {
      "epoch": 0.5367453400765578,
      "grad_norm": 1.4296875,
      "learning_rate": 3.151643048884935e-05,
      "loss": 1.1010101318359375,
      "num_input_tokens_seen": 4312905856,
      "step": 15170,
      "train_runtime": 147769.9418,
      "train_tokens_per_second": 29186.625
    },
    {
      "epoch": 0.5370991603402866,
      "grad_norm": 1.3671875,
      "learning_rate": 3.151017139191379e-05,
      "loss": 1.103235912322998,
      "num_input_tokens_seen": 4315747840,
      "step": 15180,
      "train_runtime": 147870.437,
      "train_tokens_per_second": 29186.009
    },
    {
      "epoch": 0.5374529806040154,
      "grad_norm": 1.4140625,
      "learning_rate": 3.150391602262818e-05,
      "loss": 1.10398588180542,
      "num_input_tokens_seen": 4318558848,
      "step": 15190,
      "train_runtime": 147965.1964,
      "train_tokens_per_second": 29186.315
    },
    {
      "epoch": 0.5378068008677442,
      "grad_norm": 1.4375,
      "learning_rate": 3.149766437729394e-05,
      "loss": 1.1043699264526368,
      "num_input_tokens_seen": 4321412352,
      "step": 15200,
      "train_runtime": 148063.7926,
      "train_tokens_per_second": 29186.152
    },
    {
      "epoch": 0.538160621131473,
      "grad_norm": 1.40625,
      "learning_rate": 3.1491416452217635e-05,
      "loss": 1.10097074508667,
      "num_input_tokens_seen": 4324212544,
      "step": 15210,
      "train_runtime": 148157.9549,
      "train_tokens_per_second": 29186.503
    },
    {
      "epoch": 0.5385144413952018,
      "grad_norm": 1.4765625,
      "learning_rate": 3.1485172243710954e-05,
      "loss": 1.0952075958251952,
      "num_input_tokens_seen": 4327046656,
      "step": 15220,
      "train_runtime": 148255.6018,
      "train_tokens_per_second": 29186.396
    },
    {
      "epoch": 0.5388682616589305,
      "grad_norm": 1.5,
      "learning_rate": 3.1478931748090676e-05,
      "loss": 1.0879972457885743,
      "num_input_tokens_seen": 4329853184,
      "step": 15230,
      "train_runtime": 148354.2467,
      "train_tokens_per_second": 29185.907
    },
    {
      "epoch": 0.5392220819226593,
      "grad_norm": 1.3984375,
      "learning_rate": 3.147269496167873e-05,
      "loss": 1.0896201133728027,
      "num_input_tokens_seen": 4332705792,
      "step": 15240,
      "train_runtime": 148452.9075,
      "train_tokens_per_second": 29185.725
    },
    {
      "epoch": 0.5395759021863881,
      "grad_norm": 1.390625,
      "learning_rate": 3.1466461880802105e-05,
      "loss": 1.0955044746398925,
      "num_input_tokens_seen": 4335562112,
      "step": 15250,
      "train_runtime": 148553.5202,
      "train_tokens_per_second": 29185.186
    },
    {
      "epoch": 0.5399297224501168,
      "grad_norm": 1.4765625,
      "learning_rate": 3.146023250179291e-05,
      "loss": 1.10261869430542,
      "num_input_tokens_seen": 4338357376,
      "step": 15260,
      "train_runtime": 148648.5591,
      "train_tokens_per_second": 29185.331
    },
    {
      "epoch": 0.5402835427138456,
      "grad_norm": 1.46875,
      "learning_rate": 3.145400682098833e-05,
      "loss": 1.1063451766967773,
      "num_input_tokens_seen": 4341228736,
      "step": 15270,
      "train_runtime": 148747.7484,
      "train_tokens_per_second": 29185.173
    },
    {
      "epoch": 0.5406373629775745,
      "grad_norm": 1.453125,
      "learning_rate": 3.14477848347306e-05,
      "loss": 1.1046052932739259,
      "num_input_tokens_seen": 4344086976,
      "step": 15280,
      "train_runtime": 148845.5232,
      "train_tokens_per_second": 29185.204
    },
    {
      "epoch": 0.5409911832413032,
      "grad_norm": 1.4921875,
      "learning_rate": 3.144156653936703e-05,
      "loss": 1.0952974319458009,
      "num_input_tokens_seen": 4346898432,
      "step": 15290,
      "train_runtime": 148941.6375,
      "train_tokens_per_second": 29185.247
    },
    {
      "epoch": 0.541345003505032,
      "grad_norm": 1.453125,
      "learning_rate": 3.1435351931250004e-05,
      "loss": 1.0998014450073241,
      "num_input_tokens_seen": 4349809920,
      "step": 15300,
      "train_runtime": 149044.8744,
      "train_tokens_per_second": 29184.566
    },
    {
      "epoch": 0.5416988237687608,
      "grad_norm": 1.4140625,
      "learning_rate": 3.142914100673692e-05,
      "loss": 1.1016740798950195,
      "num_input_tokens_seen": 4352621696,
      "step": 15310,
      "train_runtime": 149141.073,
      "train_tokens_per_second": 29184.594
    },
    {
      "epoch": 0.5420526440324895,
      "grad_norm": 1.46875,
      "learning_rate": 3.1422933762190235e-05,
      "loss": 1.1036070823669433,
      "num_input_tokens_seen": 4355470784,
      "step": 15320,
      "train_runtime": 149235.5375,
      "train_tokens_per_second": 29185.212
    },
    {
      "epoch": 0.5424064642962183,
      "grad_norm": 1.515625,
      "learning_rate": 3.141673019397741e-05,
      "loss": 1.0816612243652344,
      "num_input_tokens_seen": 4358257216,
      "step": 15330,
      "train_runtime": 149328.6573,
      "train_tokens_per_second": 29185.672
    },
    {
      "epoch": 0.5427602845599471,
      "grad_norm": 1.4921875,
      "learning_rate": 3.141053029847095e-05,
      "loss": 1.0864892959594727,
      "num_input_tokens_seen": 4361099712,
      "step": 15340,
      "train_runtime": 149425.9335,
      "train_tokens_per_second": 29185.695
    },
    {
      "epoch": 0.5431141048236758,
      "grad_norm": 1.484375,
      "learning_rate": 3.140433407204835e-05,
      "loss": 1.0936277389526368,
      "num_input_tokens_seen": 4363925120,
      "step": 15350,
      "train_runtime": 149521.6484,
      "train_tokens_per_second": 29185.908
    },
    {
      "epoch": 0.5434679250874047,
      "grad_norm": 1.421875,
      "learning_rate": 3.1398141511092124e-05,
      "loss": 1.095210647583008,
      "num_input_tokens_seen": 4366730752,
      "step": 15360,
      "train_runtime": 149618.5187,
      "train_tokens_per_second": 29185.764
    },
    {
      "epoch": 0.5438217453511335,
      "grad_norm": 1.484375,
      "learning_rate": 3.1391952611989736e-05,
      "loss": 1.1034278869628906,
      "num_input_tokens_seen": 4369636992,
      "step": 15370,
      "train_runtime": 149719.1889,
      "train_tokens_per_second": 29185.551
    },
    {
      "epoch": 0.5441755656148622,
      "grad_norm": 1.4609375,
      "learning_rate": 3.138576737113369e-05,
      "loss": 1.097421360015869,
      "num_input_tokens_seen": 4372542848,
      "step": 15380,
      "train_runtime": 149821.2154,
      "train_tokens_per_second": 29185.071
    },
    {
      "epoch": 0.544529385878591,
      "grad_norm": 1.4765625,
      "learning_rate": 3.137958578492143e-05,
      "loss": 1.091389274597168,
      "num_input_tokens_seen": 4375380224,
      "step": 15390,
      "train_runtime": 149918.6079,
      "train_tokens_per_second": 29185.038
    },
    {
      "epoch": 0.5448832061423198,
      "grad_norm": 1.421875,
      "learning_rate": 3.137340784975535e-05,
      "loss": 1.0843572616577148,
      "num_input_tokens_seen": 4378217408,
      "step": 15400,
      "train_runtime": 150012.6016,
      "train_tokens_per_second": 29185.664
    },
    {
      "epoch": 0.5452370264060485,
      "grad_norm": 1.4921875,
      "learning_rate": 3.136723356204285e-05,
      "loss": 1.1028470039367675,
      "num_input_tokens_seen": 4381097920,
      "step": 15410,
      "train_runtime": 150111.8547,
      "train_tokens_per_second": 29185.556
    },
    {
      "epoch": 0.5455908466697773,
      "grad_norm": 1.453125,
      "learning_rate": 3.136106291819622e-05,
      "loss": 1.087200927734375,
      "num_input_tokens_seen": 4383983232,
      "step": 15420,
      "train_runtime": 150210.6582,
      "train_tokens_per_second": 29185.567
    },
    {
      "epoch": 0.5459446669335061,
      "grad_norm": 1.4453125,
      "learning_rate": 3.1354895914632736e-05,
      "loss": 1.0797155380249024,
      "num_input_tokens_seen": 4386808896,
      "step": 15430,
      "train_runtime": 150306.5815,
      "train_tokens_per_second": 29185.741
    },
    {
      "epoch": 0.546298487197235,
      "grad_norm": 1.40625,
      "learning_rate": 3.1348732547774575e-05,
      "loss": 1.1075575828552247,
      "num_input_tokens_seen": 4389618368,
      "step": 15440,
      "train_runtime": 150398.0833,
      "train_tokens_per_second": 29186.664
    },
    {
      "epoch": 0.5466523074609637,
      "grad_norm": 1.5078125,
      "learning_rate": 3.134257281404883e-05,
      "loss": 1.0977468490600586,
      "num_input_tokens_seen": 4392389376,
      "step": 15450,
      "train_runtime": 150491.3618,
      "train_tokens_per_second": 29186.987
    },
    {
      "epoch": 0.5470061277246925,
      "grad_norm": 1.5234375,
      "learning_rate": 3.133641670988755e-05,
      "loss": 1.1008666038513184,
      "num_input_tokens_seen": 4395211200,
      "step": 15460,
      "train_runtime": 150589.836,
      "train_tokens_per_second": 29186.639
    },
    {
      "epoch": 0.5473599479884212,
      "grad_norm": 1.3828125,
      "learning_rate": 3.133026423172764e-05,
      "loss": 1.0695835113525392,
      "num_input_tokens_seen": 4398042880,
      "step": 15470,
      "train_runtime": 150686.2214,
      "train_tokens_per_second": 29186.762
    },
    {
      "epoch": 0.54771376825215,
      "grad_norm": 1.5,
      "learning_rate": 3.1324115376010897e-05,
      "loss": 1.1110475540161133,
      "num_input_tokens_seen": 4400883648,
      "step": 15480,
      "train_runtime": 150783.6344,
      "train_tokens_per_second": 29186.746
    },
    {
      "epoch": 0.5480675885158788,
      "grad_norm": 1.4296875,
      "learning_rate": 3.131797013918406e-05,
      "loss": 1.1030634880065917,
      "num_input_tokens_seen": 4403774336,
      "step": 15490,
      "train_runtime": 150883.8632,
      "train_tokens_per_second": 29186.516
    },
    {
      "epoch": 0.5484214087796075,
      "grad_norm": 1.453125,
      "learning_rate": 3.13118285176987e-05,
      "loss": 1.0888117790222167,
      "num_input_tokens_seen": 4406650432,
      "step": 15500,
      "train_runtime": 150985.6229,
      "train_tokens_per_second": 29185.894
    },
    {
      "epoch": 0.5487752290433363,
      "grad_norm": 1.421875,
      "learning_rate": 3.130569050801126e-05,
      "loss": 1.1040544509887695,
      "num_input_tokens_seen": 4409492992,
      "step": 15510,
      "train_runtime": 151088.099,
      "train_tokens_per_second": 29184.913
    },
    {
      "epoch": 0.5491290493070651,
      "grad_norm": 1.40625,
      "learning_rate": 3.129955610658306e-05,
      "loss": 1.0858856201171876,
      "num_input_tokens_seen": 4412328704,
      "step": 15520,
      "train_runtime": 151185.1827,
      "train_tokens_per_second": 29184.928
    },
    {
      "epoch": 0.549482869570794,
      "grad_norm": 1.421875,
      "learning_rate": 3.129342530988025e-05,
      "loss": 1.1064414978027344,
      "num_input_tokens_seen": 4415215616,
      "step": 15530,
      "train_runtime": 151285.3065,
      "train_tokens_per_second": 29184.696
    },
    {
      "epoch": 0.5498366898345227,
      "grad_norm": 1.40625,
      "learning_rate": 3.128729811437385e-05,
      "loss": 1.096492862701416,
      "num_input_tokens_seen": 4418009344,
      "step": 15540,
      "train_runtime": 151378.4056,
      "train_tokens_per_second": 29185.202
    },
    {
      "epoch": 0.5501905100982515,
      "grad_norm": 1.4375,
      "learning_rate": 3.12811745165397e-05,
      "loss": 1.0954319000244142,
      "num_input_tokens_seen": 4420809344,
      "step": 15550,
      "train_runtime": 151474.0058,
      "train_tokens_per_second": 29185.267
    },
    {
      "epoch": 0.5505443303619802,
      "grad_norm": 1.4453125,
      "learning_rate": 3.127505451285846e-05,
      "loss": 1.0932269096374512,
      "num_input_tokens_seen": 4423656192,
      "step": 15560,
      "train_runtime": 151569.806,
      "train_tokens_per_second": 29185.603
    },
    {
      "epoch": 0.550898150625709,
      "grad_norm": 1.5,
      "learning_rate": 3.126893809981563e-05,
      "loss": 1.0970354080200195,
      "num_input_tokens_seen": 4426493120,
      "step": 15570,
      "train_runtime": 151665.5511,
      "train_tokens_per_second": 29185.884
    },
    {
      "epoch": 0.5512519708894378,
      "grad_norm": 1.4609375,
      "learning_rate": 3.126282527390149e-05,
      "loss": 1.087992286682129,
      "num_input_tokens_seen": 4429351104,
      "step": 15580,
      "train_runtime": 151763.6139,
      "train_tokens_per_second": 29185.857
    },
    {
      "epoch": 0.5516057911531665,
      "grad_norm": 1.4609375,
      "learning_rate": 3.1256716031611146e-05,
      "loss": 1.10123872756958,
      "num_input_tokens_seen": 4432209088,
      "step": 15590,
      "train_runtime": 151862.7628,
      "train_tokens_per_second": 29185.621
    },
    {
      "epoch": 0.5519596114168953,
      "grad_norm": 1.5234375,
      "learning_rate": 3.1250610369444475e-05,
      "loss": 1.0992961883544923,
      "num_input_tokens_seen": 4435005440,
      "step": 15600,
      "train_runtime": 151957.2331,
      "train_tokens_per_second": 29185.879
    },
    {
      "epoch": 0.5523134316806242,
      "grad_norm": 1.3984375,
      "learning_rate": 3.124450828390616e-05,
      "loss": 1.0977477073669433,
      "num_input_tokens_seen": 4437808960,
      "step": 15610,
      "train_runtime": 152051.4416,
      "train_tokens_per_second": 29186.234
    },
    {
      "epoch": 0.552667251944353,
      "grad_norm": 1.46875,
      "learning_rate": 3.123840977150566e-05,
      "loss": 1.0966440200805665,
      "num_input_tokens_seen": 4440682112,
      "step": 15620,
      "train_runtime": 152150.0325,
      "train_tokens_per_second": 29186.205
    },
    {
      "epoch": 0.5530210722080817,
      "grad_norm": 1.453125,
      "learning_rate": 3.123231482875717e-05,
      "loss": 1.1073192596435546,
      "num_input_tokens_seen": 4443432064,
      "step": 15630,
      "train_runtime": 152243.4503,
      "train_tokens_per_second": 29186.359
    },
    {
      "epoch": 0.5533748924718105,
      "grad_norm": 1.4765625,
      "learning_rate": 3.122622345217967e-05,
      "loss": 1.101778793334961,
      "num_input_tokens_seen": 4446262656,
      "step": 15640,
      "train_runtime": 152338.9995,
      "train_tokens_per_second": 29186.634
    },
    {
      "epoch": 0.5537287127355393,
      "grad_norm": 1.4140625,
      "learning_rate": 3.12201356382969e-05,
      "loss": 1.100726318359375,
      "num_input_tokens_seen": 4449059968,
      "step": 15650,
      "train_runtime": 152431.9496,
      "train_tokens_per_second": 29187.188
    },
    {
      "epoch": 0.554082532999268,
      "grad_norm": 1.3984375,
      "learning_rate": 3.1214051383637304e-05,
      "loss": 1.0887067794799805,
      "num_input_tokens_seen": 4451883072,
      "step": 15660,
      "train_runtime": 152529.2713,
      "train_tokens_per_second": 29187.074
    },
    {
      "epoch": 0.5544363532629968,
      "grad_norm": 1.4765625,
      "learning_rate": 3.1207970684734104e-05,
      "loss": 1.1054166793823241,
      "num_input_tokens_seen": 4454731648,
      "step": 15670,
      "train_runtime": 152627.8194,
      "train_tokens_per_second": 29186.892
    },
    {
      "epoch": 0.5547901735267255,
      "grad_norm": 1.484375,
      "learning_rate": 3.120189353812521e-05,
      "loss": 1.1081710815429688,
      "num_input_tokens_seen": 4457504576,
      "step": 15680,
      "train_runtime": 152722.3296,
      "train_tokens_per_second": 29186.987
    },
    {
      "epoch": 0.5551439937904544,
      "grad_norm": 1.484375,
      "learning_rate": 3.1195819940353294e-05,
      "loss": 1.1078763961791993,
      "num_input_tokens_seen": 4460403072,
      "step": 15690,
      "train_runtime": 152823.112,
      "train_tokens_per_second": 29186.705
    },
    {
      "epoch": 0.5554978140541832,
      "grad_norm": 1.359375,
      "learning_rate": 3.1189749887965684e-05,
      "loss": 1.0896400451660155,
      "num_input_tokens_seen": 4463253248,
      "step": 15700,
      "train_runtime": 152920.9078,
      "train_tokens_per_second": 29186.678
    },
    {
      "epoch": 0.555851634317912,
      "grad_norm": 1.5,
      "learning_rate": 3.118368337751443e-05,
      "loss": 1.0881017684936523,
      "num_input_tokens_seen": 4466122112,
      "step": 15710,
      "train_runtime": 153019.3007,
      "train_tokens_per_second": 29186.659
    },
    {
      "epoch": 0.5562054545816407,
      "grad_norm": 1.5,
      "learning_rate": 3.1177620405556305e-05,
      "loss": 1.0928945541381836,
      "num_input_tokens_seen": 4468945472,
      "step": 15720,
      "train_runtime": 153112.8285,
      "train_tokens_per_second": 29187.27
    },
    {
      "epoch": 0.5565592748453695,
      "grad_norm": 1.4765625,
      "learning_rate": 3.117156096865272e-05,
      "loss": 1.083473014831543,
      "num_input_tokens_seen": 4471820544,
      "step": 15730,
      "train_runtime": 153210.3466,
      "train_tokens_per_second": 29187.458
    },
    {
      "epoch": 0.5569130951090983,
      "grad_norm": 1.546875,
      "learning_rate": 3.116550506336979e-05,
      "loss": 1.0952303886413575,
      "num_input_tokens_seen": 4474630848,
      "step": 15740,
      "train_runtime": 153304.2605,
      "train_tokens_per_second": 29187.909
    },
    {
      "epoch": 0.557266915372827,
      "grad_norm": 1.40625,
      "learning_rate": 3.11594526862783e-05,
      "loss": 1.093082809448242,
      "num_input_tokens_seen": 4477449344,
      "step": 15750,
      "train_runtime": 153400.8369,
      "train_tokens_per_second": 29187.907
    },
    {
      "epoch": 0.5576207356365558,
      "grad_norm": 1.4453125,
      "learning_rate": 3.115340383395367e-05,
      "loss": 1.1097824096679687,
      "num_input_tokens_seen": 4480296448,
      "step": 15760,
      "train_runtime": 153498.266,
      "train_tokens_per_second": 29187.929
    },
    {
      "epoch": 0.5579745559002846,
      "grad_norm": 1.46875,
      "learning_rate": 3.1147358502975995e-05,
      "loss": 1.090419387817383,
      "num_input_tokens_seen": 4483132544,
      "step": 15770,
      "train_runtime": 153593.2888,
      "train_tokens_per_second": 29188.336
    },
    {
      "epoch": 0.5583283761640134,
      "grad_norm": 1.453125,
      "learning_rate": 3.114131668993e-05,
      "loss": 1.0836040496826171,
      "num_input_tokens_seen": 4486022528,
      "step": 15780,
      "train_runtime": 153694.966,
      "train_tokens_per_second": 29187.83
    },
    {
      "epoch": 0.5586821964277422,
      "grad_norm": 1.421875,
      "learning_rate": 3.113527839140507e-05,
      "loss": 1.0928377151489257,
      "num_input_tokens_seen": 4488831680,
      "step": 15790,
      "train_runtime": 153789.6718,
      "train_tokens_per_second": 29188.122
    },
    {
      "epoch": 0.559036016691471,
      "grad_norm": 1.5,
      "learning_rate": 3.112924360399517e-05,
      "loss": 1.0948768615722657,
      "num_input_tokens_seen": 4491701632,
      "step": 15800,
      "train_runtime": 153885.8063,
      "train_tokens_per_second": 29188.538
    },
    {
      "epoch": 0.5593898369551997,
      "grad_norm": 1.4140625,
      "learning_rate": 3.112321232429894e-05,
      "loss": 1.0950164794921875,
      "num_input_tokens_seen": 4494555328,
      "step": 15810,
      "train_runtime": 153984.9977,
      "train_tokens_per_second": 29188.268
    },
    {
      "epoch": 0.5597436572189285,
      "grad_norm": 1.4296875,
      "learning_rate": 3.11171845489196e-05,
      "loss": 1.1019578933715821,
      "num_input_tokens_seen": 4497396288,
      "step": 15820,
      "train_runtime": 154085.0991,
      "train_tokens_per_second": 29187.743
    },
    {
      "epoch": 0.5600974774826573,
      "grad_norm": 1.4921875,
      "learning_rate": 3.1111160274464965e-05,
      "loss": 1.1111499786376953,
      "num_input_tokens_seen": 4500270336,
      "step": 15830,
      "train_runtime": 154182.4537,
      "train_tokens_per_second": 29187.954
    },
    {
      "epoch": 0.560451297746386,
      "grad_norm": 1.4609375,
      "learning_rate": 3.1105139497547466e-05,
      "loss": 1.0959906578063965,
      "num_input_tokens_seen": 4503136000,
      "step": 15840,
      "train_runtime": 154281.0117,
      "train_tokens_per_second": 29187.882
    },
    {
      "epoch": 0.5608051180101148,
      "grad_norm": 1.3828125,
      "learning_rate": 3.109912221478411e-05,
      "loss": 1.1004793167114257,
      "num_input_tokens_seen": 4505967552,
      "step": 15850,
      "train_runtime": 154374.0107,
      "train_tokens_per_second": 29188.641
    },
    {
      "epoch": 0.5611589382738437,
      "grad_norm": 1.421875,
      "learning_rate": 3.10931084227965e-05,
      "loss": 1.111363983154297,
      "num_input_tokens_seen": 4508822272,
      "step": 15860,
      "train_runtime": 154472.6551,
      "train_tokens_per_second": 29188.482
    },
    {
      "epoch": 0.5615127585375724,
      "grad_norm": 1.3984375,
      "learning_rate": 3.108709811821079e-05,
      "loss": 1.093797492980957,
      "num_input_tokens_seen": 4511687872,
      "step": 15870,
      "train_runtime": 154568.6383,
      "train_tokens_per_second": 29188.896
    },
    {
      "epoch": 0.5618665788013012,
      "grad_norm": 1.5,
      "learning_rate": 3.1081091297657696e-05,
      "loss": 1.102625560760498,
      "num_input_tokens_seen": 4514513728,
      "step": 15880,
      "train_runtime": 154664.7529,
      "train_tokens_per_second": 29189.028
    },
    {
      "epoch": 0.56222039906503,
      "grad_norm": 1.421875,
      "learning_rate": 3.107508795777251e-05,
      "loss": 1.1006938934326171,
      "num_input_tokens_seen": 4517418432,
      "step": 15890,
      "train_runtime": 154765.1946,
      "train_tokens_per_second": 29188.852
    },
    {
      "epoch": 0.5625742193287587,
      "grad_norm": 1.421875,
      "learning_rate": 3.1069088095195056e-05,
      "loss": 1.0954530715942383,
      "num_input_tokens_seen": 4520242240,
      "step": 15900,
      "train_runtime": 154861.7181,
      "train_tokens_per_second": 29188.894
    },
    {
      "epoch": 0.5629280395924875,
      "grad_norm": 1.4375,
      "learning_rate": 3.1063091706569703e-05,
      "loss": 1.1035541534423827,
      "num_input_tokens_seen": 4523114112,
      "step": 15910,
      "train_runtime": 154961.8216,
      "train_tokens_per_second": 29188.571
    },
    {
      "epoch": 0.5632818598562163,
      "grad_norm": 1.453125,
      "learning_rate": 3.105709878854535e-05,
      "loss": 1.0915435791015624,
      "num_input_tokens_seen": 4525934080,
      "step": 15920,
      "train_runtime": 155055.8094,
      "train_tokens_per_second": 29189.065
    },
    {
      "epoch": 0.563635680119945,
      "grad_norm": 1.4375,
      "learning_rate": 3.105110933777541e-05,
      "loss": 1.1024755477905273,
      "num_input_tokens_seen": 4528804608,
      "step": 15930,
      "train_runtime": 155155.5647,
      "train_tokens_per_second": 29188.799
    },
    {
      "epoch": 0.5639895003836739,
      "grad_norm": 1.4375,
      "learning_rate": 3.104512335091783e-05,
      "loss": 1.0822784423828125,
      "num_input_tokens_seen": 4531621824,
      "step": 15940,
      "train_runtime": 155251.2849,
      "train_tokens_per_second": 29188.949
    },
    {
      "epoch": 0.5643433206474027,
      "grad_norm": 1.4375,
      "learning_rate": 3.1039140824635074e-05,
      "loss": 1.100897216796875,
      "num_input_tokens_seen": 4534456960,
      "step": 15950,
      "train_runtime": 155347.3771,
      "train_tokens_per_second": 29189.144
    },
    {
      "epoch": 0.5646971409111314,
      "grad_norm": 1.4375,
      "learning_rate": 3.103316175559406e-05,
      "loss": 1.0912737846374512,
      "num_input_tokens_seen": 4537251712,
      "step": 15960,
      "train_runtime": 155439.4289,
      "train_tokens_per_second": 29189.838
    },
    {
      "epoch": 0.5650509611748602,
      "grad_norm": 1.4140625,
      "learning_rate": 3.102718614046624e-05,
      "loss": 1.0967851638793946,
      "num_input_tokens_seen": 4540102528,
      "step": 15970,
      "train_runtime": 155539.6172,
      "train_tokens_per_second": 29189.364
    },
    {
      "epoch": 0.565404781438589,
      "grad_norm": 1.484375,
      "learning_rate": 3.1021213975927546e-05,
      "loss": 1.0907953262329102,
      "num_input_tokens_seen": 4542922176,
      "step": 15980,
      "train_runtime": 155635.8547,
      "train_tokens_per_second": 29189.432
    },
    {
      "epoch": 0.5657586017023177,
      "grad_norm": 1.4453125,
      "learning_rate": 3.1015245258658374e-05,
      "loss": 1.0972389221191405,
      "num_input_tokens_seen": 4545801856,
      "step": 15990,
      "train_runtime": 155735.5036,
      "train_tokens_per_second": 29189.246
    },
    {
      "epoch": 0.5661124219660465,
      "grad_norm": 1.46875,
      "learning_rate": 3.1009279985343606e-05,
      "loss": 1.1026800155639649,
      "num_input_tokens_seen": 4548607936,
      "step": 16000,
      "train_runtime": 155829.477,
      "train_tokens_per_second": 29189.65
    },
    {
      "epoch": 0.5664662422297753,
      "grad_norm": 1.4609375,
      "learning_rate": 3.100331815267255e-05,
      "loss": 1.083327865600586,
      "num_input_tokens_seen": 4551433344,
      "step": 16010,
      "train_runtime": 155925.7021,
      "train_tokens_per_second": 29189.757
    },
    {
      "epoch": 0.566820062493504,
      "grad_norm": 1.4375,
      "learning_rate": 3.099735975733902e-05,
      "loss": 1.103782844543457,
      "num_input_tokens_seen": 4554319296,
      "step": 16020,
      "train_runtime": 156024.8979,
      "train_tokens_per_second": 29189.696
    },
    {
      "epoch": 0.5671738827572329,
      "grad_norm": 1.4765625,
      "learning_rate": 3.099140479604123e-05,
      "loss": 1.1188199996948243,
      "num_input_tokens_seen": 4557161024,
      "step": 16030,
      "train_runtime": 156122.2412,
      "train_tokens_per_second": 29189.698
    },
    {
      "epoch": 0.5675277030209617,
      "grad_norm": 1.4375,
      "learning_rate": 3.098545326548186e-05,
      "loss": 1.0935213088989257,
      "num_input_tokens_seen": 4559967424,
      "step": 16040,
      "train_runtime": 156219.2943,
      "train_tokens_per_second": 29189.528
    },
    {
      "epoch": 0.5678815232846904,
      "grad_norm": 1.4140625,
      "learning_rate": 3.0979505162368014e-05,
      "loss": 1.0943670272827148,
      "num_input_tokens_seen": 4562896704,
      "step": 16050,
      "train_runtime": 156322.85,
      "train_tokens_per_second": 29188.93
    },
    {
      "epoch": 0.5682353435484192,
      "grad_norm": 1.4140625,
      "learning_rate": 3.097356048341121e-05,
      "loss": 1.091106128692627,
      "num_input_tokens_seen": 4565749120,
      "step": 16060,
      "train_runtime": 156421.1992,
      "train_tokens_per_second": 29188.813
    },
    {
      "epoch": 0.568589163812148,
      "grad_norm": 1.4296875,
      "learning_rate": 3.0967619225327396e-05,
      "loss": 1.089901065826416,
      "num_input_tokens_seen": 4568584384,
      "step": 16070,
      "train_runtime": 156516.5518,
      "train_tokens_per_second": 29189.145
    },
    {
      "epoch": 0.5689429840758767,
      "grad_norm": 1.4453125,
      "learning_rate": 3.0961681384836924e-05,
      "loss": 1.1129552841186523,
      "num_input_tokens_seen": 4571418688,
      "step": 16080,
      "train_runtime": 156610.8427,
      "train_tokens_per_second": 29189.669
    },
    {
      "epoch": 0.5692968043396055,
      "grad_norm": 1.4296875,
      "learning_rate": 3.095574695866453e-05,
      "loss": 1.0970922470092774,
      "num_input_tokens_seen": 4574281664,
      "step": 16090,
      "train_runtime": 156709.3855,
      "train_tokens_per_second": 29189.583
    },
    {
      "epoch": 0.5696506246033343,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0949815943539355e-05,
      "loss": 1.0968297004699707,
      "num_input_tokens_seen": 4577187776,
      "step": 16100,
      "train_runtime": 156811.5678,
      "train_tokens_per_second": 29189.095
    },
    {
      "epoch": 0.5700044448670631,
      "grad_norm": 1.46875,
      "learning_rate": 3.094388833619495e-05,
      "loss": 1.0999921798706054,
      "num_input_tokens_seen": 4580032448,
      "step": 16110,
      "train_runtime": 156907.1198,
      "train_tokens_per_second": 29189.449
    },
    {
      "epoch": 0.5703582651307919,
      "grad_norm": 1.484375,
      "learning_rate": 3.0937964133369196e-05,
      "loss": 1.1031403541564941,
      "num_input_tokens_seen": 4582878016,
      "step": 16120,
      "train_runtime": 157004.9988,
      "train_tokens_per_second": 29189.376
    },
    {
      "epoch": 0.5707120853945207,
      "grad_norm": 1.46875,
      "learning_rate": 3.093204333180437e-05,
      "loss": 1.0962789535522461,
      "num_input_tokens_seen": 4585753088,
      "step": 16130,
      "train_runtime": 157102.9379,
      "train_tokens_per_second": 29189.48
    },
    {
      "epoch": 0.5710659056582494,
      "grad_norm": 1.4765625,
      "learning_rate": 3.0926125928247114e-05,
      "loss": 1.0988807678222656,
      "num_input_tokens_seen": 4588563328,
      "step": 16140,
      "train_runtime": 157195.551,
      "train_tokens_per_second": 29190.16
    },
    {
      "epoch": 0.5714197259219782,
      "grad_norm": 1.5234375,
      "learning_rate": 3.092021191944842e-05,
      "loss": 1.0988398551940919,
      "num_input_tokens_seen": 4591463744,
      "step": 16150,
      "train_runtime": 157295.0003,
      "train_tokens_per_second": 29190.144
    },
    {
      "epoch": 0.571773546185707,
      "grad_norm": 1.4609375,
      "learning_rate": 3.091430130216363e-05,
      "loss": 1.122174072265625,
      "num_input_tokens_seen": 4594273024,
      "step": 16160,
      "train_runtime": 157391.4572,
      "train_tokens_per_second": 29190.104
    },
    {
      "epoch": 0.5721273664494357,
      "grad_norm": 1.453125,
      "learning_rate": 3.090839407315242e-05,
      "loss": 1.0839764595031738,
      "num_input_tokens_seen": 4597126080,
      "step": 16170,
      "train_runtime": 157490.7133,
      "train_tokens_per_second": 29189.823
    },
    {
      "epoch": 0.5724811867131645,
      "grad_norm": 1.4453125,
      "learning_rate": 3.0902490229178794e-05,
      "loss": 1.0895937919616698,
      "num_input_tokens_seen": 4600000640,
      "step": 16180,
      "train_runtime": 157588.204,
      "train_tokens_per_second": 29190.006
    },
    {
      "epoch": 0.5728350069768934,
      "grad_norm": 1.4765625,
      "learning_rate": 3.0896589767011104e-05,
      "loss": 1.1022708892822266,
      "num_input_tokens_seen": 4602910592,
      "step": 16190,
      "train_runtime": 157690.9027,
      "train_tokens_per_second": 29189.449
    },
    {
      "epoch": 0.5731888272406221,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0890692683421985e-05,
      "loss": 1.0977823257446289,
      "num_input_tokens_seen": 4605728704,
      "step": 16200,
      "train_runtime": 157788.1273,
      "train_tokens_per_second": 29189.324
    },
    {
      "epoch": 0.5735426475043509,
      "grad_norm": 1.453125,
      "learning_rate": 3.088479897518843e-05,
      "loss": 1.0876147270202636,
      "num_input_tokens_seen": 4608575232,
      "step": 16210,
      "train_runtime": 157887.3794,
      "train_tokens_per_second": 29189.003
    },
    {
      "epoch": 0.5738964677680797,
      "grad_norm": 1.4140625,
      "learning_rate": 3.087890863909168e-05,
      "loss": 1.0891738891601563,
      "num_input_tokens_seen": 4611442048,
      "step": 16220,
      "train_runtime": 157986.347,
      "train_tokens_per_second": 29188.864
    },
    {
      "epoch": 0.5742502880318084,
      "grad_norm": 1.4140625,
      "learning_rate": 3.087302167191732e-05,
      "loss": 1.0904061317443847,
      "num_input_tokens_seen": 4614256512,
      "step": 16230,
      "train_runtime": 158081.2465,
      "train_tokens_per_second": 29189.146
    },
    {
      "epoch": 0.5746041082955372,
      "grad_norm": 1.484375,
      "learning_rate": 3.086713807045518e-05,
      "loss": 1.0983211517333984,
      "num_input_tokens_seen": 4617124736,
      "step": 16240,
      "train_runtime": 158178.841,
      "train_tokens_per_second": 29189.269
    },
    {
      "epoch": 0.574957928559266,
      "grad_norm": 1.40625,
      "learning_rate": 3.086125783149941e-05,
      "loss": 1.1054360389709472,
      "num_input_tokens_seen": 4620004160,
      "step": 16250,
      "train_runtime": 158280.7379,
      "train_tokens_per_second": 29188.67
    },
    {
      "epoch": 0.5753117488229947,
      "grad_norm": 1.453125,
      "learning_rate": 3.0855380951848404e-05,
      "loss": 1.0865482330322265,
      "num_input_tokens_seen": 4622785792,
      "step": 16260,
      "train_runtime": 158373.3303,
      "train_tokens_per_second": 29189.168
    },
    {
      "epoch": 0.5756655690867235,
      "grad_norm": 1.4375,
      "learning_rate": 3.084950742830484e-05,
      "loss": 1.0817226409912108,
      "num_input_tokens_seen": 4625604160,
      "step": 16270,
      "train_runtime": 158468.545,
      "train_tokens_per_second": 29189.415
    },
    {
      "epoch": 0.5760193893504524,
      "grad_norm": 1.4140625,
      "learning_rate": 3.0843637257675654e-05,
      "loss": 1.0987147331237792,
      "num_input_tokens_seen": 4628437632,
      "step": 16280,
      "train_runtime": 158565.669,
      "train_tokens_per_second": 29189.406
    },
    {
      "epoch": 0.5763732096141811,
      "grad_norm": 1.4375,
      "learning_rate": 3.083777043677202e-05,
      "loss": 1.0940322875976562,
      "num_input_tokens_seen": 4631296000,
      "step": 16290,
      "train_runtime": 158666.2514,
      "train_tokens_per_second": 29188.917
    },
    {
      "epoch": 0.5767270298779099,
      "grad_norm": 1.4609375,
      "learning_rate": 3.083190696240936e-05,
      "loss": 1.0987180709838866,
      "num_input_tokens_seen": 4634136512,
      "step": 16300,
      "train_runtime": 158762.912,
      "train_tokens_per_second": 29189.037
    },
    {
      "epoch": 0.5770808501416387,
      "grad_norm": 1.4375,
      "learning_rate": 3.082604683140735e-05,
      "loss": 1.104232406616211,
      "num_input_tokens_seen": 4636912320,
      "step": 16310,
      "train_runtime": 158856.2223,
      "train_tokens_per_second": 29189.365
    },
    {
      "epoch": 0.5774346704053674,
      "grad_norm": 1.421875,
      "learning_rate": 3.082019004058987e-05,
      "loss": 1.091866683959961,
      "num_input_tokens_seen": 4639789184,
      "step": 16320,
      "train_runtime": 158954.7447,
      "train_tokens_per_second": 29189.372
    },
    {
      "epoch": 0.5777884906690962,
      "grad_norm": 1.453125,
      "learning_rate": 3.081433658678505e-05,
      "loss": 1.1110514640808105,
      "num_input_tokens_seen": 4642627456,
      "step": 16330,
      "train_runtime": 159054.1179,
      "train_tokens_per_second": 29188.98
    },
    {
      "epoch": 0.578142310932825,
      "grad_norm": 1.5,
      "learning_rate": 3.080848646682521e-05,
      "loss": 1.0920642852783202,
      "num_input_tokens_seen": 4645507840,
      "step": 16340,
      "train_runtime": 159154.262,
      "train_tokens_per_second": 29188.712
    },
    {
      "epoch": 0.5784961311965537,
      "grad_norm": 1.5625,
      "learning_rate": 3.080263967754689e-05,
      "loss": 1.0935344696044922,
      "num_input_tokens_seen": 4648344960,
      "step": 16350,
      "train_runtime": 159250.2561,
      "train_tokens_per_second": 29188.932
    },
    {
      "epoch": 0.5788499514602826,
      "grad_norm": 1.515625,
      "learning_rate": 3.079679621579083e-05,
      "loss": 1.0941923141479493,
      "num_input_tokens_seen": 4651201088,
      "step": 16360,
      "train_runtime": 159346.0958,
      "train_tokens_per_second": 29189.301
    },
    {
      "epoch": 0.5792037717240114,
      "grad_norm": 1.3828125,
      "learning_rate": 3.079095607840197e-05,
      "loss": 1.1140329360961914,
      "num_input_tokens_seen": 4654067008,
      "step": 16370,
      "train_runtime": 159444.6865,
      "train_tokens_per_second": 29189.226
    },
    {
      "epoch": 0.5795575919877402,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0785119262229416e-05,
      "loss": 1.1076531410217285,
      "num_input_tokens_seen": 4656871680,
      "step": 16380,
      "train_runtime": 159537.9012,
      "train_tokens_per_second": 29189.751
    },
    {
      "epoch": 0.5799114122514689,
      "grad_norm": 1.40625,
      "learning_rate": 3.0779285764126485e-05,
      "loss": 1.0871011734008789,
      "num_input_tokens_seen": 4659745472,
      "step": 16390,
      "train_runtime": 159634.5113,
      "train_tokens_per_second": 29190.088
    },
    {
      "epoch": 0.5802652325151977,
      "grad_norm": 1.484375,
      "learning_rate": 3.077345558095064e-05,
      "loss": 1.082573699951172,
      "num_input_tokens_seen": 4662502656,
      "step": 16400,
      "train_runtime": 159724.0189,
      "train_tokens_per_second": 29190.993
    },
    {
      "epoch": 0.5806190527789264,
      "grad_norm": 1.46875,
      "learning_rate": 3.076762870956352e-05,
      "loss": 1.092704963684082,
      "num_input_tokens_seen": 4665291584,
      "step": 16410,
      "train_runtime": 159819.8018,
      "train_tokens_per_second": 29190.948
    },
    {
      "epoch": 0.5809728730426552,
      "grad_norm": 1.46875,
      "learning_rate": 3.076180514683092e-05,
      "loss": 1.0958224296569825,
      "num_input_tokens_seen": 4668126080,
      "step": 16420,
      "train_runtime": 159918.4421,
      "train_tokens_per_second": 29190.668
    },
    {
      "epoch": 0.581326693306384,
      "grad_norm": 1.3984375,
      "learning_rate": 3.075598488962278e-05,
      "loss": 1.0964084625244142,
      "num_input_tokens_seen": 4670958656,
      "step": 16430,
      "train_runtime": 160015.9544,
      "train_tokens_per_second": 29190.581
    },
    {
      "epoch": 0.5816805135701129,
      "grad_norm": 1.4921875,
      "learning_rate": 3.0750167934813207e-05,
      "loss": 1.0976393699645997,
      "num_input_tokens_seen": 4673823552,
      "step": 16440,
      "train_runtime": 160116.9374,
      "train_tokens_per_second": 29190.063
    },
    {
      "epoch": 0.5820343338338416,
      "grad_norm": 1.4296875,
      "learning_rate": 3.074435427928041e-05,
      "loss": 1.1124701499938965,
      "num_input_tokens_seen": 4676659520,
      "step": 16450,
      "train_runtime": 160213.6744,
      "train_tokens_per_second": 29190.14
    },
    {
      "epoch": 0.5823881540975704,
      "grad_norm": 1.4765625,
      "learning_rate": 3.073854391990675e-05,
      "loss": 1.0831924438476563,
      "num_input_tokens_seen": 4679561536,
      "step": 16460,
      "train_runtime": 160312.8935,
      "train_tokens_per_second": 29190.176
    },
    {
      "epoch": 0.5827419743612992,
      "grad_norm": 1.4140625,
      "learning_rate": 3.073273685357871e-05,
      "loss": 1.0927404403686523,
      "num_input_tokens_seen": 4682363072,
      "step": 16470,
      "train_runtime": 160407.3232,
      "train_tokens_per_second": 29190.457
    },
    {
      "epoch": 0.5830957946250279,
      "grad_norm": 1.4453125,
      "learning_rate": 3.072693307718689e-05,
      "loss": 1.0950761795043946,
      "num_input_tokens_seen": 4685215616,
      "step": 16480,
      "train_runtime": 160505.6131,
      "train_tokens_per_second": 29190.354
    },
    {
      "epoch": 0.5834496148887567,
      "grad_norm": 1.3984375,
      "learning_rate": 3.0721132587626e-05,
      "loss": 1.1046653747558595,
      "num_input_tokens_seen": 4687993344,
      "step": 16490,
      "train_runtime": 160598.0263,
      "train_tokens_per_second": 29190.853
    },
    {
      "epoch": 0.5838034351524855,
      "grad_norm": 1.4140625,
      "learning_rate": 3.071533538179482e-05,
      "loss": 1.113405418395996,
      "num_input_tokens_seen": 4690838592,
      "step": 16500,
      "train_runtime": 160697.2545,
      "train_tokens_per_second": 29190.534
    },
    {
      "epoch": 0.5841572554162142,
      "grad_norm": 1.4375,
      "learning_rate": 3.070954145659627e-05,
      "loss": 1.0783203125,
      "num_input_tokens_seen": 4693651456,
      "step": 16510,
      "train_runtime": 160792.1861,
      "train_tokens_per_second": 29190.793
    },
    {
      "epoch": 0.584511075679943,
      "grad_norm": 1.4453125,
      "learning_rate": 3.070375080893734e-05,
      "loss": 1.1018409729003906,
      "num_input_tokens_seen": 4696469440,
      "step": 16520,
      "train_runtime": 160884.5834,
      "train_tokens_per_second": 29191.544
    },
    {
      "epoch": 0.5848648959436719,
      "grad_norm": 1.4375,
      "learning_rate": 3.06979634357291e-05,
      "loss": 1.0934564590454101,
      "num_input_tokens_seen": 4699296576,
      "step": 16530,
      "train_runtime": 160981.4188,
      "train_tokens_per_second": 29191.547
    },
    {
      "epoch": 0.5852187162074006,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0692179333886686e-05,
      "loss": 1.0985864639282226,
      "num_input_tokens_seen": 4702138112,
      "step": 16540,
      "train_runtime": 161076.2394,
      "train_tokens_per_second": 29192.003
    },
    {
      "epoch": 0.5855725364711294,
      "grad_norm": 1.4140625,
      "learning_rate": 3.068639850032933e-05,
      "loss": 1.0992287635803222,
      "num_input_tokens_seen": 4705041280,
      "step": 16550,
      "train_runtime": 161177.5383,
      "train_tokens_per_second": 29191.669
    },
    {
      "epoch": 0.5859263567348582,
      "grad_norm": 1.5078125,
      "learning_rate": 3.068062093198028e-05,
      "loss": 1.0850433349609374,
      "num_input_tokens_seen": 4707861184,
      "step": 16560,
      "train_runtime": 161274.4075,
      "train_tokens_per_second": 29191.62
    },
    {
      "epoch": 0.5862801769985869,
      "grad_norm": 1.4765625,
      "learning_rate": 3.067484662576687e-05,
      "loss": 1.0919729232788087,
      "num_input_tokens_seen": 4710654208,
      "step": 16570,
      "train_runtime": 161368.3874,
      "train_tokens_per_second": 29191.927
    },
    {
      "epoch": 0.5866339972623157,
      "grad_norm": 1.4921875,
      "learning_rate": 3.066907557862048e-05,
      "loss": 1.1082036972045899,
      "num_input_tokens_seen": 4713473728,
      "step": 16580,
      "train_runtime": 161465.2313,
      "train_tokens_per_second": 29191.88
    },
    {
      "epoch": 0.5869878175260445,
      "grad_norm": 1.421875,
      "learning_rate": 3.066330778747651e-05,
      "loss": 1.0777200698852538,
      "num_input_tokens_seen": 4716275520,
      "step": 16590,
      "train_runtime": 161561.6525,
      "train_tokens_per_second": 29191.8
    },
    {
      "epoch": 0.5873416377897732,
      "grad_norm": 1.453125,
      "learning_rate": 3.065754324927441e-05,
      "loss": 1.0964981079101563,
      "num_input_tokens_seen": 4719098112,
      "step": 16600,
      "train_runtime": 161659.212,
      "train_tokens_per_second": 29191.644
    },
    {
      "epoch": 0.5876954580535021,
      "grad_norm": 1.4921875,
      "learning_rate": 3.065178196095765e-05,
      "loss": 1.0978200912475586,
      "num_input_tokens_seen": 4721976000,
      "step": 16610,
      "train_runtime": 161758.1394,
      "train_tokens_per_second": 29191.582
    },
    {
      "epoch": 0.5880492783172309,
      "grad_norm": 1.53125,
      "learning_rate": 3.064602391947372e-05,
      "loss": 1.0874610900878907,
      "num_input_tokens_seen": 4724850880,
      "step": 16620,
      "train_runtime": 161857.3038,
      "train_tokens_per_second": 29191.459
    },
    {
      "epoch": 0.5884030985809596,
      "grad_norm": 1.5859375,
      "learning_rate": 3.0640269121774126e-05,
      "loss": 1.103624153137207,
      "num_input_tokens_seen": 4727732864,
      "step": 16630,
      "train_runtime": 161957.2067,
      "train_tokens_per_second": 29191.247
    },
    {
      "epoch": 0.5887569188446884,
      "grad_norm": 1.4609375,
      "learning_rate": 3.063451756481437e-05,
      "loss": 1.096430778503418,
      "num_input_tokens_seen": 4730596480,
      "step": 16640,
      "train_runtime": 162056.1642,
      "train_tokens_per_second": 29191.092
    },
    {
      "epoch": 0.5891107391084172,
      "grad_norm": 1.40625,
      "learning_rate": 3.062876924555396e-05,
      "loss": 1.0871400833129883,
      "num_input_tokens_seen": 4733436416,
      "step": 16650,
      "train_runtime": 162152.2593,
      "train_tokens_per_second": 29191.307
    },
    {
      "epoch": 0.5894645593721459,
      "grad_norm": 1.421875,
      "learning_rate": 3.06230241609564e-05,
      "loss": 1.0895965576171875,
      "num_input_tokens_seen": 4736315712,
      "step": 16660,
      "train_runtime": 162250.9113,
      "train_tokens_per_second": 29191.304
    },
    {
      "epoch": 0.5898183796358747,
      "grad_norm": 1.4609375,
      "learning_rate": 3.061728230798916e-05,
      "loss": 1.0916547775268555,
      "num_input_tokens_seen": 4739207104,
      "step": 16670,
      "train_runtime": 162350.2769,
      "train_tokens_per_second": 29191.247
    },
    {
      "epoch": 0.5901721998996035,
      "grad_norm": 1.4375,
      "learning_rate": 3.061154368362373e-05,
      "loss": 1.102214527130127,
      "num_input_tokens_seen": 4742024256,
      "step": 16680,
      "train_runtime": 162447.3676,
      "train_tokens_per_second": 29191.143
    },
    {
      "epoch": 0.5905260201633323,
      "grad_norm": 1.4296875,
      "learning_rate": 3.060580828483552e-05,
      "loss": 1.1019763946533203,
      "num_input_tokens_seen": 4744898496,
      "step": 16690,
      "train_runtime": 162547.0219,
      "train_tokens_per_second": 29190.929
    },
    {
      "epoch": 0.5908798404270611,
      "grad_norm": 1.3828125,
      "learning_rate": 3.060007610860395e-05,
      "loss": 1.0941965103149414,
      "num_input_tokens_seen": 4747769280,
      "step": 16700,
      "train_runtime": 162644.4956,
      "train_tokens_per_second": 29191.085
    },
    {
      "epoch": 0.5912336606907899,
      "grad_norm": 1.5,
      "learning_rate": 3.059434715191236e-05,
      "loss": 1.0862497329711913,
      "num_input_tokens_seen": 4750639936,
      "step": 16710,
      "train_runtime": 162743.4136,
      "train_tokens_per_second": 29190.981
    },
    {
      "epoch": 0.5915874809545186,
      "grad_norm": 1.4921875,
      "learning_rate": 3.0588621411748074e-05,
      "loss": 1.0978269577026367,
      "num_input_tokens_seen": 4753437632,
      "step": 16720,
      "train_runtime": 162835.5379,
      "train_tokens_per_second": 29191.648
    },
    {
      "epoch": 0.5919413012182474,
      "grad_norm": 1.40625,
      "learning_rate": 3.0582898885102344e-05,
      "loss": 1.0986330032348632,
      "num_input_tokens_seen": 4756237120,
      "step": 16730,
      "train_runtime": 162926.9518,
      "train_tokens_per_second": 29192.451
    },
    {
      "epoch": 0.5922951214819762,
      "grad_norm": 1.5625,
      "learning_rate": 3.0577179568970366e-05,
      "loss": 1.0953177452087401,
      "num_input_tokens_seen": 4759045184,
      "step": 16740,
      "train_runtime": 163022.3496,
      "train_tokens_per_second": 29192.594
    },
    {
      "epoch": 0.5926489417457049,
      "grad_norm": 1.5,
      "learning_rate": 3.057146346035127e-05,
      "loss": 1.0803657531738282,
      "num_input_tokens_seen": 4761911616,
      "step": 16750,
      "train_runtime": 163120.1687,
      "train_tokens_per_second": 29192.66
    },
    {
      "epoch": 0.5930027620094337,
      "grad_norm": 1.40625,
      "learning_rate": 3.056575055624811e-05,
      "loss": 1.0998851776123046,
      "num_input_tokens_seen": 4764743872,
      "step": 16760,
      "train_runtime": 163215.051,
      "train_tokens_per_second": 29193.042
    },
    {
      "epoch": 0.5933565822731625,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0560040853667846e-05,
      "loss": 1.0969873428344727,
      "num_input_tokens_seen": 4767652416,
      "step": 16770,
      "train_runtime": 163319.6484,
      "train_tokens_per_second": 29192.155
    },
    {
      "epoch": 0.5937104025368913,
      "grad_norm": 1.3515625,
      "learning_rate": 3.0554334349621366e-05,
      "loss": 1.092568302154541,
      "num_input_tokens_seen": 4770495296,
      "step": 16780,
      "train_runtime": 163417.5826,
      "train_tokens_per_second": 29192.056
    },
    {
      "epoch": 0.5940642228006201,
      "grad_norm": 1.453125,
      "learning_rate": 3.054863104112347e-05,
      "loss": 1.0889858245849608,
      "num_input_tokens_seen": 4773229056,
      "step": 16790,
      "train_runtime": 163511.1766,
      "train_tokens_per_second": 29192.066
    },
    {
      "epoch": 0.5944180430643489,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0542930925192835e-05,
      "loss": 1.0896934509277343,
      "num_input_tokens_seen": 4776024960,
      "step": 16800,
      "train_runtime": 163605.1201,
      "train_tokens_per_second": 29192.393
    },
    {
      "epoch": 0.5947718633280776,
      "grad_norm": 1.53125,
      "learning_rate": 3.053723399885205e-05,
      "loss": 1.1006757736206054,
      "num_input_tokens_seen": 4778855936,
      "step": 16810,
      "train_runtime": 163703.3256,
      "train_tokens_per_second": 29192.174
    },
    {
      "epoch": 0.5951256835918064,
      "grad_norm": 1.5078125,
      "learning_rate": 3.0531540259127565e-05,
      "loss": 1.0932408332824708,
      "num_input_tokens_seen": 4781725888,
      "step": 16820,
      "train_runtime": 163800.7865,
      "train_tokens_per_second": 29192.326
    },
    {
      "epoch": 0.5954795038555352,
      "grad_norm": 1.546875,
      "learning_rate": 3.052584970304976e-05,
      "loss": 1.103687858581543,
      "num_input_tokens_seen": 4784632384,
      "step": 16830,
      "train_runtime": 163902.5704,
      "train_tokens_per_second": 29191.93
    },
    {
      "epoch": 0.5958333241192639,
      "grad_norm": 1.4609375,
      "learning_rate": 3.052016232765282e-05,
      "loss": 1.0926210403442382,
      "num_input_tokens_seen": 4787526400,
      "step": 16840,
      "train_runtime": 164003.5975,
      "train_tokens_per_second": 29191.594
    },
    {
      "epoch": 0.5961871443829927,
      "grad_norm": 1.5390625,
      "learning_rate": 3.0514478129974845e-05,
      "loss": 1.1001875877380372,
      "num_input_tokens_seen": 4790408000,
      "step": 16850,
      "train_runtime": 164104.3717,
      "train_tokens_per_second": 29191.227
    },
    {
      "epoch": 0.5965409646467216,
      "grad_norm": 1.4296875,
      "learning_rate": 3.0508797107057785e-05,
      "loss": 1.1003700256347657,
      "num_input_tokens_seen": 4793291904,
      "step": 16860,
      "train_runtime": 164202.677,
      "train_tokens_per_second": 29191.314
    },
    {
      "epoch": 0.5968947849104503,
      "grad_norm": 1.4921875,
      "learning_rate": 3.0503119255947432e-05,
      "loss": 1.0925004005432128,
      "num_input_tokens_seen": 4796120448,
      "step": 16870,
      "train_runtime": 164300.2393,
      "train_tokens_per_second": 29191.196
    },
    {
      "epoch": 0.5972486051741791,
      "grad_norm": 1.5234375,
      "learning_rate": 3.049744457369344e-05,
      "loss": 1.0863349914550782,
      "num_input_tokens_seen": 4798935680,
      "step": 16880,
      "train_runtime": 164397.9617,
      "train_tokens_per_second": 29190.968
    },
    {
      "epoch": 0.5976024254379079,
      "grad_norm": 1.40625,
      "learning_rate": 3.049177305734929e-05,
      "loss": 1.1031753540039062,
      "num_input_tokens_seen": 4801809088,
      "step": 16890,
      "train_runtime": 164499.0426,
      "train_tokens_per_second": 29190.499
    },
    {
      "epoch": 0.5979562457016366,
      "grad_norm": 1.5,
      "learning_rate": 3.04861047039723e-05,
      "loss": 1.0945579528808593,
      "num_input_tokens_seen": 4804642752,
      "step": 16900,
      "train_runtime": 164595.3738,
      "train_tokens_per_second": 29190.631
    },
    {
      "epoch": 0.5983100659653654,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0480439510623638e-05,
      "loss": 1.0884976387023926,
      "num_input_tokens_seen": 4807497472,
      "step": 16910,
      "train_runtime": 164691.6342,
      "train_tokens_per_second": 29190.903
    },
    {
      "epoch": 0.5986638862290942,
      "grad_norm": 1.484375,
      "learning_rate": 3.0474777474368255e-05,
      "loss": 1.0983901977539063,
      "num_input_tokens_seen": 4810281792,
      "step": 16920,
      "train_runtime": 164783.4129,
      "train_tokens_per_second": 29191.541
    },
    {
      "epoch": 0.5990177064928229,
      "grad_norm": 1.421875,
      "learning_rate": 3.046911859227495e-05,
      "loss": 1.0942093849182128,
      "num_input_tokens_seen": 4813188032,
      "step": 16930,
      "train_runtime": 164881.0774,
      "train_tokens_per_second": 29191.876
    },
    {
      "epoch": 0.5993715267565518,
      "grad_norm": 1.5,
      "learning_rate": 3.0463462861416302e-05,
      "loss": 1.102155876159668,
      "num_input_tokens_seen": 4816004416,
      "step": 16940,
      "train_runtime": 164976.999,
      "train_tokens_per_second": 29191.975
    },
    {
      "epoch": 0.5997253470202806,
      "grad_norm": 1.453125,
      "learning_rate": 3.045781027886873e-05,
      "loss": 1.1043055534362793,
      "num_input_tokens_seen": 4818798528,
      "step": 16950,
      "train_runtime": 165069.2818,
      "train_tokens_per_second": 29192.582
    },
    {
      "epoch": 0.6000791672840093,
      "grad_norm": 1.4453125,
      "learning_rate": 3.0452160841712408e-05,
      "loss": 1.0920918464660645,
      "num_input_tokens_seen": 4821652480,
      "step": 16960,
      "train_runtime": 165170.3979,
      "train_tokens_per_second": 29191.989
    },
    {
      "epoch": 0.6004329875477381,
      "grad_norm": 1.4609375,
      "learning_rate": 3.044651454703133e-05,
      "loss": 1.0912130355834961,
      "num_input_tokens_seen": 4824476672,
      "step": 16970,
      "train_runtime": 165268.614,
      "train_tokens_per_second": 29191.729
    },
    {
      "epoch": 0.6007868078114669,
      "grad_norm": 1.5078125,
      "learning_rate": 3.0440871391913257e-05,
      "loss": 1.0945262908935547,
      "num_input_tokens_seen": 4827343616,
      "step": 16980,
      "train_runtime": 165365.0015,
      "train_tokens_per_second": 29192.051
    },
    {
      "epoch": 0.6011406280751956,
      "grad_norm": 1.421875,
      "learning_rate": 3.043523137344973e-05,
      "loss": 1.0904662132263183,
      "num_input_tokens_seen": 4830190848,
      "step": 16990,
      "train_runtime": 165462.0301,
      "train_tokens_per_second": 29192.141
    },
    {
      "epoch": 0.6014944483389244,
      "grad_norm": 1.4765625,
      "learning_rate": 3.0429594488736074e-05,
      "loss": 1.0914529800415038,
      "num_input_tokens_seen": 4833028416,
      "step": 17000,
      "train_runtime": 165559.2298,
      "train_tokens_per_second": 29192.141
    },
    {
      "epoch": 0.6018482686026532,
      "grad_norm": 1.453125,
      "learning_rate": 3.0423960734871348e-05,
      "loss": 1.0862038612365723,
      "num_input_tokens_seen": 4835902656,
      "step": 17010,
      "train_runtime": 165657.6504,
      "train_tokens_per_second": 29192.148
    },
    {
      "epoch": 0.6022020888663819,
      "grad_norm": 1.4921875,
      "learning_rate": 3.0418330108958404e-05,
      "loss": 1.1011293411254883,
      "num_input_tokens_seen": 4838743168,
      "step": 17020,
      "train_runtime": 165754.348,
      "train_tokens_per_second": 29192.255
    },
    {
      "epoch": 0.6025559091301108,
      "grad_norm": 1.5234375,
      "learning_rate": 3.0412702608103828e-05,
      "loss": 1.0982834815979003,
      "num_input_tokens_seen": 4841615808,
      "step": 17030,
      "train_runtime": 165853.4018,
      "train_tokens_per_second": 29192.14
    },
    {
      "epoch": 0.6029097293938396,
      "grad_norm": 1.4453125,
      "learning_rate": 3.0407078229417944e-05,
      "loss": 1.0963294982910157,
      "num_input_tokens_seen": 4844434816,
      "step": 17040,
      "train_runtime": 165949.2732,
      "train_tokens_per_second": 29192.263
    },
    {
      "epoch": 0.6032635496575683,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0401456970014836e-05,
      "loss": 1.1030233383178711,
      "num_input_tokens_seen": 4847282624,
      "step": 17050,
      "train_runtime": 166046.9135,
      "train_tokens_per_second": 29192.248
    },
    {
      "epoch": 0.6036173699212971,
      "grad_norm": 1.4609375,
      "learning_rate": 3.039583882701231e-05,
      "loss": 1.101303768157959,
      "num_input_tokens_seen": 4850112192,
      "step": 17060,
      "train_runtime": 166145.1997,
      "train_tokens_per_second": 29192.009
    },
    {
      "epoch": 0.6039711901850259,
      "grad_norm": 1.4140625,
      "learning_rate": 3.0390223797531887e-05,
      "loss": 1.0827056884765625,
      "num_input_tokens_seen": 4852995648,
      "step": 17070,
      "train_runtime": 166245.0838,
      "train_tokens_per_second": 29191.815
    },
    {
      "epoch": 0.6043250104487546,
      "grad_norm": 1.46875,
      "learning_rate": 3.0384611878698837e-05,
      "loss": 1.0955751419067383,
      "num_input_tokens_seen": 4855845952,
      "step": 17080,
      "train_runtime": 166343.3742,
      "train_tokens_per_second": 29191.7
    },
    {
      "epoch": 0.6046788307124834,
      "grad_norm": 1.46875,
      "learning_rate": 3.0379003067642113e-05,
      "loss": 1.1060341835021972,
      "num_input_tokens_seen": 4858639744,
      "step": 17090,
      "train_runtime": 166436.3358,
      "train_tokens_per_second": 29192.182
    },
    {
      "epoch": 0.6050326509762122,
      "grad_norm": 1.4453125,
      "learning_rate": 3.037339736149441e-05,
      "loss": 1.0828195571899415,
      "num_input_tokens_seen": 4861526848,
      "step": 17100,
      "train_runtime": 166536.1505,
      "train_tokens_per_second": 29192.021
    },
    {
      "epoch": 0.605386471239941,
      "grad_norm": 1.4765625,
      "learning_rate": 3.0367794757392092e-05,
      "loss": 1.0872723579406738,
      "num_input_tokens_seen": 4864316736,
      "step": 17110,
      "train_runtime": 166630.3133,
      "train_tokens_per_second": 29192.268
    },
    {
      "epoch": 0.6057402915036698,
      "grad_norm": 1.453125,
      "learning_rate": 3.0362195252475245e-05,
      "loss": 1.0839508056640625,
      "num_input_tokens_seen": 4867139456,
      "step": 17120,
      "train_runtime": 166726.4425,
      "train_tokens_per_second": 29192.367
    },
    {
      "epoch": 0.6060941117673986,
      "grad_norm": 1.4921875,
      "learning_rate": 3.0356598843887634e-05,
      "loss": 1.0889789581298828,
      "num_input_tokens_seen": 4869951104,
      "step": 17130,
      "train_runtime": 166822.0911,
      "train_tokens_per_second": 29192.483
    },
    {
      "epoch": 0.6064479320311273,
      "grad_norm": 1.4765625,
      "learning_rate": 3.03510055287767e-05,
      "loss": 1.097985076904297,
      "num_input_tokens_seen": 4872733760,
      "step": 17140,
      "train_runtime": 166915.5678,
      "train_tokens_per_second": 29192.806
    },
    {
      "epoch": 0.6068017522948561,
      "grad_norm": 1.4921875,
      "learning_rate": 3.0345415304293578e-05,
      "loss": 1.0952084541320801,
      "num_input_tokens_seen": 4875590400,
      "step": 17150,
      "train_runtime": 167014.2401,
      "train_tokens_per_second": 29192.663
    },
    {
      "epoch": 0.6071555725585849,
      "grad_norm": 1.4921875,
      "learning_rate": 3.0339828167593065e-05,
      "loss": 1.0912042617797852,
      "num_input_tokens_seen": 4878444224,
      "step": 17160,
      "train_runtime": 167114.136,
      "train_tokens_per_second": 29192.289
    },
    {
      "epoch": 0.6075093928223136,
      "grad_norm": 1.515625,
      "learning_rate": 3.033424411583363e-05,
      "loss": 1.0914927482604981,
      "num_input_tokens_seen": 4881299392,
      "step": 17170,
      "train_runtime": 167209.6986,
      "train_tokens_per_second": 29192.681
    },
    {
      "epoch": 0.6078632130860424,
      "grad_norm": 1.4921875,
      "learning_rate": 3.0328663146177387e-05,
      "loss": 1.1041365623474122,
      "num_input_tokens_seen": 4884182528,
      "step": 17180,
      "train_runtime": 167309.9021,
      "train_tokens_per_second": 29192.43
    },
    {
      "epoch": 0.6082170333497713,
      "grad_norm": 1.484375,
      "learning_rate": 3.032308525579013e-05,
      "loss": 1.0896267890930176,
      "num_input_tokens_seen": 4887034048,
      "step": 17190,
      "train_runtime": 167410.0078,
      "train_tokens_per_second": 29192.007
    },
    {
      "epoch": 0.6085708536135,
      "grad_norm": 1.484375,
      "learning_rate": 3.031751044184127e-05,
      "loss": 1.076206588745117,
      "num_input_tokens_seen": 4889851008,
      "step": 17200,
      "train_runtime": 167506.114,
      "train_tokens_per_second": 29192.075
    },
    {
      "epoch": 0.6089246738772288,
      "grad_norm": 1.4375,
      "learning_rate": 3.0311938701503872e-05,
      "loss": 1.0827105522155762,
      "num_input_tokens_seen": 4892737344,
      "step": 17210,
      "train_runtime": 167604.1311,
      "train_tokens_per_second": 29192.224
    },
    {
      "epoch": 0.6092784941409576,
      "grad_norm": 1.4453125,
      "learning_rate": 3.0306370031954646e-05,
      "loss": 1.0833229064941405,
      "num_input_tokens_seen": 4895623744,
      "step": 17220,
      "train_runtime": 167704.6688,
      "train_tokens_per_second": 29191.935
    },
    {
      "epoch": 0.6096323144046863,
      "grad_norm": 1.4921875,
      "learning_rate": 3.030080443037393e-05,
      "loss": 1.0984199523925782,
      "num_input_tokens_seen": 4898499072,
      "step": 17230,
      "train_runtime": 167801.7973,
      "train_tokens_per_second": 29192.173
    },
    {
      "epoch": 0.6099861346684151,
      "grad_norm": 1.4453125,
      "learning_rate": 3.0295241893945663e-05,
      "loss": 1.1059236526489258,
      "num_input_tokens_seen": 4901417472,
      "step": 17240,
      "train_runtime": 167905.4916,
      "train_tokens_per_second": 29191.526
    },
    {
      "epoch": 0.6103399549321439,
      "grad_norm": 1.453125,
      "learning_rate": 3.028968241985743e-05,
      "loss": 1.0986146926879883,
      "num_input_tokens_seen": 4904288448,
      "step": 17250,
      "train_runtime": 168004.9424,
      "train_tokens_per_second": 29191.334
    },
    {
      "epoch": 0.6106937751958726,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0284126005300405e-05,
      "loss": 1.0951709747314453,
      "num_input_tokens_seen": 4907094080,
      "step": 17260,
      "train_runtime": 168102.0963,
      "train_tokens_per_second": 29191.153
    },
    {
      "epoch": 0.6110475954596014,
      "grad_norm": 1.4140625,
      "learning_rate": 3.0278572647469385e-05,
      "loss": 1.0993926048278808,
      "num_input_tokens_seen": 4909941952,
      "step": 17270,
      "train_runtime": 168202.1115,
      "train_tokens_per_second": 29190.727
    },
    {
      "epoch": 0.6114014157233303,
      "grad_norm": 1.5234375,
      "learning_rate": 3.027302234356275e-05,
      "loss": 1.0908631324768066,
      "num_input_tokens_seen": 4912768192,
      "step": 17280,
      "train_runtime": 168297.2355,
      "train_tokens_per_second": 29191.021
    },
    {
      "epoch": 0.611755235987059,
      "grad_norm": 1.4453125,
      "learning_rate": 3.0267475090782494e-05,
      "loss": 1.0866449356079102,
      "num_input_tokens_seen": 4915623744,
      "step": 17290,
      "train_runtime": 168393.6697,
      "train_tokens_per_second": 29191.262
    },
    {
      "epoch": 0.6121090562507878,
      "grad_norm": 1.5,
      "learning_rate": 3.026193088633418e-05,
      "loss": 1.1042341232299804,
      "num_input_tokens_seen": 4918438208,
      "step": 17300,
      "train_runtime": 168488.9128,
      "train_tokens_per_second": 29191.465
    },
    {
      "epoch": 0.6124628765145166,
      "grad_norm": 1.4375,
      "learning_rate": 3.0256389727426952e-05,
      "loss": 1.0890140533447266,
      "num_input_tokens_seen": 4921316352,
      "step": 17310,
      "train_runtime": 168588.1916,
      "train_tokens_per_second": 29191.347
    },
    {
      "epoch": 0.6128166967782454,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0250851611273555e-05,
      "loss": 1.096203899383545,
      "num_input_tokens_seen": 4924200896,
      "step": 17320,
      "train_runtime": 168688.9609,
      "train_tokens_per_second": 29191.009
    },
    {
      "epoch": 0.6131705170419741,
      "grad_norm": 1.4296875,
      "learning_rate": 3.0245316535090273e-05,
      "loss": 1.0928457260131836,
      "num_input_tokens_seen": 4927030016,
      "step": 17330,
      "train_runtime": 168783.2432,
      "train_tokens_per_second": 29191.464
    },
    {
      "epoch": 0.6135243373057029,
      "grad_norm": 1.4765625,
      "learning_rate": 3.023978449609697e-05,
      "loss": 1.0842462539672852,
      "num_input_tokens_seen": 4929834496,
      "step": 17340,
      "train_runtime": 168878.6244,
      "train_tokens_per_second": 29191.584
    },
    {
      "epoch": 0.6138781575694316,
      "grad_norm": 1.4609375,
      "learning_rate": 3.023425549151707e-05,
      "loss": 1.1089102745056152,
      "num_input_tokens_seen": 4932647296,
      "step": 17350,
      "train_runtime": 168974.7087,
      "train_tokens_per_second": 29191.631
    },
    {
      "epoch": 0.6142319778331605,
      "grad_norm": 1.4609375,
      "learning_rate": 3.022872951857754e-05,
      "loss": 1.0797795295715331,
      "num_input_tokens_seen": 4935509440,
      "step": 17360,
      "train_runtime": 169075.2307,
      "train_tokens_per_second": 29191.203
    },
    {
      "epoch": 0.6145857980968893,
      "grad_norm": 1.5078125,
      "learning_rate": 3.0223206574508904e-05,
      "loss": 1.089653491973877,
      "num_input_tokens_seen": 4938350144,
      "step": 17370,
      "train_runtime": 169171.783,
      "train_tokens_per_second": 29191.335
    },
    {
      "epoch": 0.6149396183606181,
      "grad_norm": 1.453125,
      "learning_rate": 3.0217686656545224e-05,
      "loss": 1.0938947677612305,
      "num_input_tokens_seen": 4941242176,
      "step": 17380,
      "train_runtime": 169272.5752,
      "train_tokens_per_second": 29191.038
    },
    {
      "epoch": 0.6152934386243468,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0212169761924077e-05,
      "loss": 1.0758726119995117,
      "num_input_tokens_seen": 4944175168,
      "step": 17390,
      "train_runtime": 169375.4072,
      "train_tokens_per_second": 29190.632
    },
    {
      "epoch": 0.6156472588880756,
      "grad_norm": 1.390625,
      "learning_rate": 3.0206655887886604e-05,
      "loss": 1.1010332107543945,
      "num_input_tokens_seen": 4947047616,
      "step": 17400,
      "train_runtime": 169474.9204,
      "train_tokens_per_second": 29190.441
    },
    {
      "epoch": 0.6160010791518044,
      "grad_norm": 1.765625,
      "learning_rate": 3.0201145031677448e-05,
      "loss": 1.1021709442138672,
      "num_input_tokens_seen": 4949891200,
      "step": 17410,
      "train_runtime": 169572.5651,
      "train_tokens_per_second": 29190.401
    },
    {
      "epoch": 0.6163548994155331,
      "grad_norm": 1.46875,
      "learning_rate": 3.019563719054477e-05,
      "loss": 1.092070960998535,
      "num_input_tokens_seen": 4952743552,
      "step": 17420,
      "train_runtime": 169671.376,
      "train_tokens_per_second": 29190.213
    },
    {
      "epoch": 0.6167087196792619,
      "grad_norm": 1.4609375,
      "learning_rate": 3.019013236174025e-05,
      "loss": 1.092387580871582,
      "num_input_tokens_seen": 4955594368,
      "step": 17430,
      "train_runtime": 169770.9245,
      "train_tokens_per_second": 29189.889
    },
    {
      "epoch": 0.6170625399429908,
      "grad_norm": 1.4453125,
      "learning_rate": 3.018463054251906e-05,
      "loss": 1.0892486572265625,
      "num_input_tokens_seen": 4958432448,
      "step": 17440,
      "train_runtime": 169865.4199,
      "train_tokens_per_second": 29190.358
    },
    {
      "epoch": 0.6174163602067195,
      "grad_norm": 1.40625,
      "learning_rate": 3.017913173013989e-05,
      "loss": 1.0922076225280761,
      "num_input_tokens_seen": 4961316288,
      "step": 17450,
      "train_runtime": 169963.4036,
      "train_tokens_per_second": 29190.497
    },
    {
      "epoch": 0.6177701804704483,
      "grad_norm": 1.4765625,
      "learning_rate": 3.017363592186491e-05,
      "loss": 1.0945773124694824,
      "num_input_tokens_seen": 4964150016,
      "step": 17460,
      "train_runtime": 170060.7718,
      "train_tokens_per_second": 29190.447
    },
    {
      "epoch": 0.6181240007341771,
      "grad_norm": 1.40625,
      "learning_rate": 3.0168143114959797e-05,
      "loss": 1.083472728729248,
      "num_input_tokens_seen": 4966970816,
      "step": 17470,
      "train_runtime": 170157.728,
      "train_tokens_per_second": 29190.392
    },
    {
      "epoch": 0.6184778209979058,
      "grad_norm": 1.4296875,
      "learning_rate": 3.016265330669369e-05,
      "loss": 1.1022187232971192,
      "num_input_tokens_seen": 4969811584,
      "step": 17480,
      "train_runtime": 170254.9485,
      "train_tokens_per_second": 29190.409
    },
    {
      "epoch": 0.6188316412616346,
      "grad_norm": 1.453125,
      "learning_rate": 3.0157166494339223e-05,
      "loss": 1.1012327194213867,
      "num_input_tokens_seen": 4972673536,
      "step": 17490,
      "train_runtime": 170354.5556,
      "train_tokens_per_second": 29190.141
    },
    {
      "epoch": 0.6191854615253634,
      "grad_norm": 1.4296875,
      "learning_rate": 3.0151682675172482e-05,
      "loss": 1.0924217224121093,
      "num_input_tokens_seen": 4975483200,
      "step": 17500,
      "train_runtime": 170451.3342,
      "train_tokens_per_second": 29190.051
    },
    {
      "epoch": 0.6195392817890921,
      "grad_norm": 1.4921875,
      "learning_rate": 3.0146201846473034e-05,
      "loss": 1.072235679626465,
      "num_input_tokens_seen": 4978340736,
      "step": 17510,
      "train_runtime": 170550.1157,
      "train_tokens_per_second": 29189.899
    },
    {
      "epoch": 0.6198931020528209,
      "grad_norm": 1.4375,
      "learning_rate": 3.01407240055239e-05,
      "loss": 1.1102373123168945,
      "num_input_tokens_seen": 4981153600,
      "step": 17520,
      "train_runtime": 170645.6815,
      "train_tokens_per_second": 29190.036
    },
    {
      "epoch": 0.6202469223165498,
      "grad_norm": 1.46875,
      "learning_rate": 3.013524914961157e-05,
      "loss": 1.0981882095336915,
      "num_input_tokens_seen": 4983947264,
      "step": 17530,
      "train_runtime": 170738.3057,
      "train_tokens_per_second": 29190.563
    },
    {
      "epoch": 0.6206007425802785,
      "grad_norm": 1.4765625,
      "learning_rate": 3.012977727602596e-05,
      "loss": 1.085178756713867,
      "num_input_tokens_seen": 4986762560,
      "step": 17540,
      "train_runtime": 170832.8027,
      "train_tokens_per_second": 29190.896
    },
    {
      "epoch": 0.6209545628440073,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0124308382060446e-05,
      "loss": 1.1066741943359375,
      "num_input_tokens_seen": 4989534656,
      "step": 17550,
      "train_runtime": 170928.6516,
      "train_tokens_per_second": 29190.745
    },
    {
      "epoch": 0.6213083831077361,
      "grad_norm": 1.4609375,
      "learning_rate": 3.011884246501183e-05,
      "loss": 1.0930465698242187,
      "num_input_tokens_seen": 4992401984,
      "step": 17560,
      "train_runtime": 171028.0332,
      "train_tokens_per_second": 29190.548
    },
    {
      "epoch": 0.6216622033714648,
      "grad_norm": 1.4921875,
      "learning_rate": 3.0113379522180363e-05,
      "loss": 1.1016223907470704,
      "num_input_tokens_seen": 4995281408,
      "step": 17570,
      "train_runtime": 171127.275,
      "train_tokens_per_second": 29190.446
    },
    {
      "epoch": 0.6220160236351936,
      "grad_norm": 1.5078125,
      "learning_rate": 3.0107919550869702e-05,
      "loss": 1.092971134185791,
      "num_input_tokens_seen": 4998074432,
      "step": 17580,
      "train_runtime": 171218.8557,
      "train_tokens_per_second": 29191.145
    },
    {
      "epoch": 0.6223698438989224,
      "grad_norm": 1.4765625,
      "learning_rate": 3.0102462548386933e-05,
      "loss": 1.0873563766479493,
      "num_input_tokens_seen": 5000884480,
      "step": 17590,
      "train_runtime": 171313.6407,
      "train_tokens_per_second": 29191.397
    },
    {
      "epoch": 0.6227236641626511,
      "grad_norm": 1.4140625,
      "learning_rate": 3.0097008512042572e-05,
      "loss": 1.093904685974121,
      "num_input_tokens_seen": 5003696768,
      "step": 17600,
      "train_runtime": 171409.448,
      "train_tokens_per_second": 29191.488
    },
    {
      "epoch": 0.62307748442638,
      "grad_norm": 1.453125,
      "learning_rate": 3.009155743915052e-05,
      "loss": 1.1052436828613281,
      "num_input_tokens_seen": 5006511936,
      "step": 17610,
      "train_runtime": 171505.8189,
      "train_tokens_per_second": 29191.499
    },
    {
      "epoch": 0.6234313046901088,
      "grad_norm": 1.4296875,
      "learning_rate": 3.00861093270281e-05,
      "loss": 1.0873170852661134,
      "num_input_tokens_seen": 5009304512,
      "step": 17620,
      "train_runtime": 171601.1368,
      "train_tokens_per_second": 29191.558
    },
    {
      "epoch": 0.6237851249538375,
      "grad_norm": 1.453125,
      "learning_rate": 3.008066417299602e-05,
      "loss": 1.08282527923584,
      "num_input_tokens_seen": 5012144896,
      "step": 17630,
      "train_runtime": 171695.8218,
      "train_tokens_per_second": 29192.003
    },
    {
      "epoch": 0.6241389452175663,
      "grad_norm": 1.515625,
      "learning_rate": 3.00752219743784e-05,
      "loss": 1.0912040710449218,
      "num_input_tokens_seen": 5015010432,
      "step": 17640,
      "train_runtime": 171793.8096,
      "train_tokens_per_second": 29192.032
    },
    {
      "epoch": 0.6244927654812951,
      "grad_norm": 1.515625,
      "learning_rate": 3.0069782728502737e-05,
      "loss": 1.0895211219787597,
      "num_input_tokens_seen": 5017832512,
      "step": 17650,
      "train_runtime": 171889.4482,
      "train_tokens_per_second": 29192.208
    },
    {
      "epoch": 0.6248465857450238,
      "grad_norm": 1.4375,
      "learning_rate": 3.00643464326999e-05,
      "loss": 1.0778526306152343,
      "num_input_tokens_seen": 5020703808,
      "step": 17660,
      "train_runtime": 171988.6396,
      "train_tokens_per_second": 29192.067
    },
    {
      "epoch": 0.6252004060087526,
      "grad_norm": 1.4921875,
      "learning_rate": 3.0058913084304146e-05,
      "loss": 1.0848018646240234,
      "num_input_tokens_seen": 5023488640,
      "step": 17670,
      "train_runtime": 172082.5195,
      "train_tokens_per_second": 29192.324
    },
    {
      "epoch": 0.6255542262724814,
      "grad_norm": 1.4375,
      "learning_rate": 3.0053482680653112e-05,
      "loss": 1.0912198066711425,
      "num_input_tokens_seen": 5026346880,
      "step": 17680,
      "train_runtime": 172180.1147,
      "train_tokens_per_second": 29192.377
    },
    {
      "epoch": 0.6259080465362102,
      "grad_norm": 1.484375,
      "learning_rate": 3.0048055219087777e-05,
      "loss": 1.0929868698120118,
      "num_input_tokens_seen": 5029180480,
      "step": 17690,
      "train_runtime": 172276.9616,
      "train_tokens_per_second": 29192.415
    },
    {
      "epoch": 0.626261866799939,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0042630696952507e-05,
      "loss": 1.0932377815246581,
      "num_input_tokens_seen": 5032037952,
      "step": 17700,
      "train_runtime": 172373.6311,
      "train_tokens_per_second": 29192.62
    },
    {
      "epoch": 0.6266156870636678,
      "grad_norm": 1.453125,
      "learning_rate": 3.0037209111594994e-05,
      "loss": 1.1029495239257812,
      "num_input_tokens_seen": 5034930752,
      "step": 17710,
      "train_runtime": 172474.0978,
      "train_tokens_per_second": 29192.388
    },
    {
      "epoch": 0.6269695073273965,
      "grad_norm": 1.484375,
      "learning_rate": 3.0031790460366305e-05,
      "loss": 1.090860939025879,
      "num_input_tokens_seen": 5037810368,
      "step": 17720,
      "train_runtime": 172572.479,
      "train_tokens_per_second": 29192.432
    },
    {
      "epoch": 0.6273233275911253,
      "grad_norm": 1.5,
      "learning_rate": 3.002637474062083e-05,
      "loss": 1.101734733581543,
      "num_input_tokens_seen": 5040589760,
      "step": 17730,
      "train_runtime": 172664.3444,
      "train_tokens_per_second": 29192.997
    },
    {
      "epoch": 0.6276771478548541,
      "grad_norm": 1.4609375,
      "learning_rate": 3.0020961949716325e-05,
      "loss": 1.0864606857299806,
      "num_input_tokens_seen": 5043435904,
      "step": 17740,
      "train_runtime": 172763.5063,
      "train_tokens_per_second": 29192.716
    },
    {
      "epoch": 0.6280309681185828,
      "grad_norm": 1.484375,
      "learning_rate": 3.0015552085013847e-05,
      "loss": 1.093165683746338,
      "num_input_tokens_seen": 5046189184,
      "step": 17750,
      "train_runtime": 172854.2283,
      "train_tokens_per_second": 29193.322
    },
    {
      "epoch": 0.6283847883823116,
      "grad_norm": 1.4375,
      "learning_rate": 3.0010145143877805e-05,
      "loss": 1.1060758590698243,
      "num_input_tokens_seen": 5048981696,
      "step": 17760,
      "train_runtime": 172947.7576,
      "train_tokens_per_second": 29193.681
    },
    {
      "epoch": 0.6287386086460404,
      "grad_norm": 1.3984375,
      "learning_rate": 3.0004741123675907e-05,
      "loss": 1.0958579063415528,
      "num_input_tokens_seen": 5051770688,
      "step": 17770,
      "train_runtime": 173043.1493,
      "train_tokens_per_second": 29193.705
    },
    {
      "epoch": 0.6290924289097692,
      "grad_norm": 1.484375,
      "learning_rate": 2.9999340021779205e-05,
      "loss": 1.0740983963012696,
      "num_input_tokens_seen": 5054588800,
      "step": 17780,
      "train_runtime": 173139.303,
      "train_tokens_per_second": 29193.769
    },
    {
      "epoch": 0.629446249173498,
      "grad_norm": 1.3828125,
      "learning_rate": 2.999394183556204e-05,
      "loss": 1.0861684799194335,
      "num_input_tokens_seen": 5057500672,
      "step": 17790,
      "train_runtime": 173239.8046,
      "train_tokens_per_second": 29193.641
    },
    {
      "epoch": 0.6298000694372268,
      "grad_norm": 1.4921875,
      "learning_rate": 2.998854656240207e-05,
      "loss": 1.094163990020752,
      "num_input_tokens_seen": 5060324160,
      "step": 17800,
      "train_runtime": 173334.4305,
      "train_tokens_per_second": 29193.993
    },
    {
      "epoch": 0.6301538897009555,
      "grad_norm": 1.4609375,
      "learning_rate": 2.9983154199680257e-05,
      "loss": 1.1063013076782227,
      "num_input_tokens_seen": 5063190336,
      "step": 17810,
      "train_runtime": 173431.0982,
      "train_tokens_per_second": 29194.247
    },
    {
      "epoch": 0.6305077099646843,
      "grad_norm": 1.4296875,
      "learning_rate": 2.9977764744780845e-05,
      "loss": 1.0933140754699706,
      "num_input_tokens_seen": 5065999168,
      "step": 17820,
      "train_runtime": 173527.565,
      "train_tokens_per_second": 29194.204
    },
    {
      "epoch": 0.6308615302284131,
      "grad_norm": 1.578125,
      "learning_rate": 2.9972378195091384e-05,
      "loss": 1.0691737174987792,
      "num_input_tokens_seen": 5068796416,
      "step": 17830,
      "train_runtime": 173625.1881,
      "train_tokens_per_second": 29193.9
    },
    {
      "epoch": 0.6312153504921418,
      "grad_norm": 1.390625,
      "learning_rate": 2.996699454800269e-05,
      "loss": 1.1059783935546874,
      "num_input_tokens_seen": 5071733952,
      "step": 17840,
      "train_runtime": 173726.4859,
      "train_tokens_per_second": 29193.787
    },
    {
      "epoch": 0.6315691707558706,
      "grad_norm": 1.453125,
      "learning_rate": 2.9961613800908883e-05,
      "loss": 1.0885400772094727,
      "num_input_tokens_seen": 5074574912,
      "step": 17850,
      "train_runtime": 173823.5559,
      "train_tokens_per_second": 29193.828
    },
    {
      "epoch": 0.6319229910195995,
      "grad_norm": 1.390625,
      "learning_rate": 2.995623595120733e-05,
      "loss": 1.0917795181274415,
      "num_input_tokens_seen": 5077408448,
      "step": 17860,
      "train_runtime": 173921.5166,
      "train_tokens_per_second": 29193.676
    },
    {
      "epoch": 0.6322768112833282,
      "grad_norm": 1.4296875,
      "learning_rate": 2.995086099629869e-05,
      "loss": 1.1009288787841798,
      "num_input_tokens_seen": 5080244672,
      "step": 17870,
      "train_runtime": 174018.047,
      "train_tokens_per_second": 29193.781
    },
    {
      "epoch": 0.632630631547057,
      "grad_norm": 1.5,
      "learning_rate": 2.9945488933586867e-05,
      "loss": 1.0865049362182617,
      "num_input_tokens_seen": 5083104384,
      "step": 17880,
      "train_runtime": 174118.5249,
      "train_tokens_per_second": 29193.358
    },
    {
      "epoch": 0.6329844518107858,
      "grad_norm": 1.4375,
      "learning_rate": 2.9940119760479045e-05,
      "loss": 1.0965476036071777,
      "num_input_tokens_seen": 5085932736,
      "step": 17890,
      "train_runtime": 174214.2296,
      "train_tokens_per_second": 29193.555
    },
    {
      "epoch": 0.6333382720745145,
      "grad_norm": 1.484375,
      "learning_rate": 2.9934753474385635e-05,
      "loss": 1.0934578895568847,
      "num_input_tokens_seen": 5088743936,
      "step": 17900,
      "train_runtime": 174309.3472,
      "train_tokens_per_second": 29193.752
    },
    {
      "epoch": 0.6336920923382433,
      "grad_norm": 1.515625,
      "learning_rate": 2.9929390072720314e-05,
      "loss": 1.0994976043701172,
      "num_input_tokens_seen": 5091568960,
      "step": 17910,
      "train_runtime": 174406.7168,
      "train_tokens_per_second": 29193.652
    },
    {
      "epoch": 0.6340459126019721,
      "grad_norm": 1.40625,
      "learning_rate": 2.99240295529e-05,
      "loss": 1.0884819030761719,
      "num_input_tokens_seen": 5094457088,
      "step": 17920,
      "train_runtime": 174503.6363,
      "train_tokens_per_second": 29193.988
    },
    {
      "epoch": 0.6343997328657008,
      "grad_norm": 1.4609375,
      "learning_rate": 2.991867191234484e-05,
      "loss": 1.0861394882202149,
      "num_input_tokens_seen": 5097324736,
      "step": 17930,
      "train_runtime": 174603.033,
      "train_tokens_per_second": 29193.793
    },
    {
      "epoch": 0.6347535531294297,
      "grad_norm": 1.421875,
      "learning_rate": 2.991331714847822e-05,
      "loss": 1.0968965530395507,
      "num_input_tokens_seen": 5100176512,
      "step": 17940,
      "train_runtime": 174699.976,
      "train_tokens_per_second": 29193.916
    },
    {
      "epoch": 0.6351073733931585,
      "grad_norm": 1.4765625,
      "learning_rate": 2.990796525872675e-05,
      "loss": 1.1063126564025878,
      "num_input_tokens_seen": 5103029248,
      "step": 17950,
      "train_runtime": 174796.4361,
      "train_tokens_per_second": 29194.126
    },
    {
      "epoch": 0.6354611936568872,
      "grad_norm": 1.4921875,
      "learning_rate": 2.990261624052027e-05,
      "loss": 1.1037614822387696,
      "num_input_tokens_seen": 5105830400,
      "step": 17960,
      "train_runtime": 174892.5169,
      "train_tokens_per_second": 29194.104
    },
    {
      "epoch": 0.635815013920616,
      "grad_norm": 1.453125,
      "learning_rate": 2.989727009129182e-05,
      "loss": 1.0944622039794922,
      "num_input_tokens_seen": 5108736064,
      "step": 17970,
      "train_runtime": 174988.7355,
      "train_tokens_per_second": 29194.657
    },
    {
      "epoch": 0.6361688341843448,
      "grad_norm": 1.46875,
      "learning_rate": 2.989192680847766e-05,
      "loss": 1.1029019355773926,
      "num_input_tokens_seen": 5111624448,
      "step": 17980,
      "train_runtime": 175089.8964,
      "train_tokens_per_second": 29194.286
    },
    {
      "epoch": 0.6365226544480735,
      "grad_norm": 1.421875,
      "learning_rate": 2.9886586389517267e-05,
      "loss": 1.0914192199707031,
      "num_input_tokens_seen": 5114494144,
      "step": 17990,
      "train_runtime": 175187.3023,
      "train_tokens_per_second": 29194.434
    },
    {
      "epoch": 0.6368764747118023,
      "grad_norm": 1.4140625,
      "learning_rate": 2.98812488318533e-05,
      "loss": 1.091372013092041,
      "num_input_tokens_seen": 5117328640,
      "step": 18000,
      "train_runtime": 175283.8196,
      "train_tokens_per_second": 29194.529
    },
    {
      "epoch": 0.6372302949755311,
      "grad_norm": 1.484375,
      "learning_rate": 2.987591413293162e-05,
      "loss": 1.0850393295288085,
      "num_input_tokens_seen": 5120165696,
      "step": 18010,
      "train_runtime": 175379.0616,
      "train_tokens_per_second": 29194.852
    },
    {
      "epoch": 0.6375841152392598,
      "grad_norm": 1.4921875,
      "learning_rate": 2.98705822902013e-05,
      "loss": 1.0896478652954102,
      "num_input_tokens_seen": 5123009728,
      "step": 18020,
      "train_runtime": 175478.2863,
      "train_tokens_per_second": 29194.551
    },
    {
      "epoch": 0.6379379355029887,
      "grad_norm": 1.4375,
      "learning_rate": 2.9865253301114553e-05,
      "loss": 1.088956642150879,
      "num_input_tokens_seen": 5125901824,
      "step": 18030,
      "train_runtime": 175578.9358,
      "train_tokens_per_second": 29194.287
    },
    {
      "epoch": 0.6382917557667175,
      "grad_norm": 1.5078125,
      "learning_rate": 2.985992716312683e-05,
      "loss": 1.0927720069885254,
      "num_input_tokens_seen": 5128786752,
      "step": 18040,
      "train_runtime": 175677.101,
      "train_tokens_per_second": 29194.395
    },
    {
      "epoch": 0.6386455760304462,
      "grad_norm": 1.3984375,
      "learning_rate": 2.9854603873696703e-05,
      "loss": 1.0811944961547852,
      "num_input_tokens_seen": 5131620736,
      "step": 18050,
      "train_runtime": 175773.3321,
      "train_tokens_per_second": 29194.535
    },
    {
      "epoch": 0.638999396294175,
      "grad_norm": 1.4609375,
      "learning_rate": 2.9849283430285947e-05,
      "loss": 1.10753173828125,
      "num_input_tokens_seen": 5134488384,
      "step": 18060,
      "train_runtime": 175873.4498,
      "train_tokens_per_second": 29194.221
    },
    {
      "epoch": 0.6393532165579038,
      "grad_norm": 1.515625,
      "learning_rate": 2.98439658303595e-05,
      "loss": 1.0945836067199708,
      "num_input_tokens_seen": 5137327488,
      "step": 18070,
      "train_runtime": 175970.9049,
      "train_tokens_per_second": 29194.187
    },
    {
      "epoch": 0.6397070368216325,
      "grad_norm": 1.5,
      "learning_rate": 2.9838651071385442e-05,
      "loss": 1.0856395721435548,
      "num_input_tokens_seen": 5140219712,
      "step": 18080,
      "train_runtime": 176073.6686,
      "train_tokens_per_second": 29193.574
    },
    {
      "epoch": 0.6400608570853613,
      "grad_norm": 1.484375,
      "learning_rate": 2.9833339150835037e-05,
      "loss": 1.0879490852355957,
      "num_input_tokens_seen": 5143062656,
      "step": 18090,
      "train_runtime": 176171.1003,
      "train_tokens_per_second": 29193.566
    },
    {
      "epoch": 0.6404146773490901,
      "grad_norm": 1.4921875,
      "learning_rate": 2.982803006618267e-05,
      "loss": 1.095631217956543,
      "num_input_tokens_seen": 5145871104,
      "step": 18100,
      "train_runtime": 176266.9958,
      "train_tokens_per_second": 29193.617
    },
    {
      "epoch": 0.640768497612819,
      "grad_norm": 1.484375,
      "learning_rate": 2.982272381490588e-05,
      "loss": 1.093402099609375,
      "num_input_tokens_seen": 5148714880,
      "step": 18110,
      "train_runtime": 176362.3532,
      "train_tokens_per_second": 29193.957
    },
    {
      "epoch": 0.6411223178765477,
      "grad_norm": 1.5078125,
      "learning_rate": 2.9817420394485363e-05,
      "loss": 1.076893138885498,
      "num_input_tokens_seen": 5151576832,
      "step": 18120,
      "train_runtime": 176458.5029,
      "train_tokens_per_second": 29194.268
    },
    {
      "epoch": 0.6414761381402765,
      "grad_norm": 1.484375,
      "learning_rate": 2.9812119802404927e-05,
      "loss": 1.0914627075195313,
      "num_input_tokens_seen": 5154438400,
      "step": 18130,
      "train_runtime": 176556.9636,
      "train_tokens_per_second": 29194.195
    },
    {
      "epoch": 0.6418299584040053,
      "grad_norm": 1.4296875,
      "learning_rate": 2.9806822036151523e-05,
      "loss": 1.090593147277832,
      "num_input_tokens_seen": 5157314816,
      "step": 18140,
      "train_runtime": 176655.4461,
      "train_tokens_per_second": 29194.202
    },
    {
      "epoch": 0.642183778667734,
      "grad_norm": 1.4609375,
      "learning_rate": 2.980152709321522e-05,
      "loss": 1.1043086051940918,
      "num_input_tokens_seen": 5160157824,
      "step": 18150,
      "train_runtime": 176750.9139,
      "train_tokens_per_second": 29194.518
    },
    {
      "epoch": 0.6425375989314628,
      "grad_norm": 1.421875,
      "learning_rate": 2.9796234971089214e-05,
      "loss": 1.0932493209838867,
      "num_input_tokens_seen": 5163078912,
      "step": 18160,
      "train_runtime": 176851.2355,
      "train_tokens_per_second": 29194.475
    },
    {
      "epoch": 0.6428914191951915,
      "grad_norm": 1.484375,
      "learning_rate": 2.979094566726981e-05,
      "loss": 1.0833987236022948,
      "num_input_tokens_seen": 5165915968,
      "step": 18170,
      "train_runtime": 176948.6607,
      "train_tokens_per_second": 29194.434
    },
    {
      "epoch": 0.6432452394589203,
      "grad_norm": 1.4296875,
      "learning_rate": 2.9785659179256427e-05,
      "loss": 1.0705631256103516,
      "num_input_tokens_seen": 5168756928,
      "step": 18180,
      "train_runtime": 177045.3861,
      "train_tokens_per_second": 29194.531
    },
    {
      "epoch": 0.6435990597226492,
      "grad_norm": 1.59375,
      "learning_rate": 2.978037550455159e-05,
      "loss": 1.0914487838745117,
      "num_input_tokens_seen": 5171592320,
      "step": 18190,
      "train_runtime": 177143.7771,
      "train_tokens_per_second": 29194.321
    },
    {
      "epoch": 0.643952879986378,
      "grad_norm": 1.421875,
      "learning_rate": 2.977509464066091e-05,
      "loss": 1.0922799110412598,
      "num_input_tokens_seen": 5174435520,
      "step": 18200,
      "train_runtime": 177242.0846,
      "train_tokens_per_second": 29194.17
    },
    {
      "epoch": 0.6443067002501067,
      "grad_norm": 1.5,
      "learning_rate": 2.9769816585093126e-05,
      "loss": 1.0937393188476563,
      "num_input_tokens_seen": 5177222080,
      "step": 18210,
      "train_runtime": 177338.4738,
      "train_tokens_per_second": 29194.015
    },
    {
      "epoch": 0.6446605205138355,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9764541335360024e-05,
      "loss": 1.0992071151733398,
      "num_input_tokens_seen": 5180071744,
      "step": 18220,
      "train_runtime": 177435.6535,
      "train_tokens_per_second": 29194.086
    },
    {
      "epoch": 0.6450143407775643,
      "grad_norm": 1.3984375,
      "learning_rate": 2.9759268888976505e-05,
      "loss": 1.0768861770629883,
      "num_input_tokens_seen": 5182936768,
      "step": 18230,
      "train_runtime": 177537.2114,
      "train_tokens_per_second": 29193.524
    },
    {
      "epoch": 0.645368161041293,
      "grad_norm": 1.4609375,
      "learning_rate": 2.9753999243460546e-05,
      "loss": 1.0919095993041992,
      "num_input_tokens_seen": 5185806016,
      "step": 18240,
      "train_runtime": 177635.9218,
      "train_tokens_per_second": 29193.453
    },
    {
      "epoch": 0.6457219813050218,
      "grad_norm": 1.5390625,
      "learning_rate": 2.974873239633319e-05,
      "loss": 1.0921977043151856,
      "num_input_tokens_seen": 5188599488,
      "step": 18250,
      "train_runtime": 177730.9001,
      "train_tokens_per_second": 29193.57
    },
    {
      "epoch": 0.6460758015687506,
      "grad_norm": 1.46875,
      "learning_rate": 2.9743468345118563e-05,
      "loss": 1.0843795776367187,
      "num_input_tokens_seen": 5191436992,
      "step": 18260,
      "train_runtime": 177829.7727,
      "train_tokens_per_second": 29193.295
    },
    {
      "epoch": 0.6464296218324794,
      "grad_norm": 1.5078125,
      "learning_rate": 2.9738207087343844e-05,
      "loss": 1.1045127868652345,
      "num_input_tokens_seen": 5194292288,
      "step": 18270,
      "train_runtime": 177927.1568,
      "train_tokens_per_second": 29193.364
    },
    {
      "epoch": 0.6467834420962082,
      "grad_norm": 1.3828125,
      "learning_rate": 2.9732948620539287e-05,
      "loss": 1.0811529159545898,
      "num_input_tokens_seen": 5197122944,
      "step": 18280,
      "train_runtime": 178022.2839,
      "train_tokens_per_second": 29193.665
    },
    {
      "epoch": 0.647137262359937,
      "grad_norm": 1.515625,
      "learning_rate": 2.9727692942238188e-05,
      "loss": 1.0792274475097656,
      "num_input_tokens_seen": 5199970304,
      "step": 18290,
      "train_runtime": 178115.6842,
      "train_tokens_per_second": 29194.343
    },
    {
      "epoch": 0.6474910826236657,
      "grad_norm": 1.4375,
      "learning_rate": 2.97224400499769e-05,
      "loss": 1.1003503799438477,
      "num_input_tokens_seen": 5202848960,
      "step": 18300,
      "train_runtime": 178216.2598,
      "train_tokens_per_second": 29194.019
    },
    {
      "epoch": 0.6478449028873945,
      "grad_norm": 1.4140625,
      "learning_rate": 2.9717189941294826e-05,
      "loss": 1.0977008819580079,
      "num_input_tokens_seen": 5205752704,
      "step": 18310,
      "train_runtime": 178316.5849,
      "train_tokens_per_second": 29193.878
    },
    {
      "epoch": 0.6481987231511233,
      "grad_norm": 1.53125,
      "learning_rate": 2.97119426137344e-05,
      "loss": 1.0840436935424804,
      "num_input_tokens_seen": 5208582144,
      "step": 18320,
      "train_runtime": 178414.9225,
      "train_tokens_per_second": 29193.646
    },
    {
      "epoch": 0.648552543414852,
      "grad_norm": 1.4453125,
      "learning_rate": 2.9706698064841103e-05,
      "loss": 1.0948871612548827,
      "num_input_tokens_seen": 5211359552,
      "step": 18330,
      "train_runtime": 178507.3672,
      "train_tokens_per_second": 29194.087
    },
    {
      "epoch": 0.6489063636785808,
      "grad_norm": 1.5078125,
      "learning_rate": 2.970145629216345e-05,
      "loss": 1.1049657821655274,
      "num_input_tokens_seen": 5214195008,
      "step": 18340,
      "train_runtime": 178603.9511,
      "train_tokens_per_second": 29194.175
    },
    {
      "epoch": 0.6492601839423096,
      "grad_norm": 1.46875,
      "learning_rate": 2.969621729325296e-05,
      "loss": 1.0939626693725586,
      "num_input_tokens_seen": 5217021248,
      "step": 18350,
      "train_runtime": 178701.0722,
      "train_tokens_per_second": 29194.124
    },
    {
      "epoch": 0.6496140042060384,
      "grad_norm": 1.4375,
      "learning_rate": 2.969098106566421e-05,
      "loss": 1.092513370513916,
      "num_input_tokens_seen": 5219914240,
      "step": 18360,
      "train_runtime": 178803.0361,
      "train_tokens_per_second": 29193.656
    },
    {
      "epoch": 0.6499678244697672,
      "grad_norm": 1.46875,
      "learning_rate": 2.968574760695476e-05,
      "loss": 1.0998994827270507,
      "num_input_tokens_seen": 5222842560,
      "step": 18370,
      "train_runtime": 178906.5538,
      "train_tokens_per_second": 29193.132
    },
    {
      "epoch": 0.650321644733496,
      "grad_norm": 1.46875,
      "learning_rate": 2.9680516914685206e-05,
      "loss": 1.0877735137939453,
      "num_input_tokens_seen": 5225691136,
      "step": 18380,
      "train_runtime": 179003.2837,
      "train_tokens_per_second": 29193.27
    },
    {
      "epoch": 0.6506754649972247,
      "grad_norm": 1.515625,
      "learning_rate": 2.9675288986419148e-05,
      "loss": 1.0872085571289063,
      "num_input_tokens_seen": 5228528256,
      "step": 18390,
      "train_runtime": 179100.9875,
      "train_tokens_per_second": 29193.185
    },
    {
      "epoch": 0.6510292852609535,
      "grad_norm": 1.453125,
      "learning_rate": 2.967006381972317e-05,
      "loss": 1.0903966903686524,
      "num_input_tokens_seen": 5231359040,
      "step": 18400,
      "train_runtime": 179199.3576,
      "train_tokens_per_second": 29192.956
    },
    {
      "epoch": 0.6513831055246823,
      "grad_norm": 1.4375,
      "learning_rate": 2.9664841412166882e-05,
      "loss": 1.089061450958252,
      "num_input_tokens_seen": 5234193408,
      "step": 18410,
      "train_runtime": 179297.6035,
      "train_tokens_per_second": 29192.768
    },
    {
      "epoch": 0.651736925788411,
      "grad_norm": 1.421875,
      "learning_rate": 2.965962176132287e-05,
      "loss": 1.0873963356018066,
      "num_input_tokens_seen": 5237039872,
      "step": 18420,
      "train_runtime": 179395.3124,
      "train_tokens_per_second": 29192.735
    },
    {
      "epoch": 0.6520907460521398,
      "grad_norm": 1.4375,
      "learning_rate": 2.9654404864766706e-05,
      "loss": 1.0846607208251953,
      "num_input_tokens_seen": 5239866176,
      "step": 18430,
      "train_runtime": 179490.4234,
      "train_tokens_per_second": 29193.013
    },
    {
      "epoch": 0.6524445663158687,
      "grad_norm": 1.484375,
      "learning_rate": 2.9649190720076962e-05,
      "loss": 1.0934024810791017,
      "num_input_tokens_seen": 5242772352,
      "step": 18440,
      "train_runtime": 179592.2532,
      "train_tokens_per_second": 29192.642
    },
    {
      "epoch": 0.6527983865795974,
      "grad_norm": 1.4921875,
      "learning_rate": 2.9643979324835176e-05,
      "loss": 1.0942916870117188,
      "num_input_tokens_seen": 5245648320,
      "step": 18450,
      "train_runtime": 179693.6135,
      "train_tokens_per_second": 29192.18
    },
    {
      "epoch": 0.6531522068433262,
      "grad_norm": 1.484375,
      "learning_rate": 2.9638770676625866e-05,
      "loss": 1.081151294708252,
      "num_input_tokens_seen": 5248480512,
      "step": 18460,
      "train_runtime": 179794.2649,
      "train_tokens_per_second": 29191.59
    },
    {
      "epoch": 0.653506027107055,
      "grad_norm": 1.484375,
      "learning_rate": 2.9633564773036517e-05,
      "loss": 1.0827617645263672,
      "num_input_tokens_seen": 5251268608,
      "step": 18470,
      "train_runtime": 179887.5313,
      "train_tokens_per_second": 29191.954
    },
    {
      "epoch": 0.6538598473707837,
      "grad_norm": 1.4140625,
      "learning_rate": 2.9628361611657578e-05,
      "loss": 1.0874143600463868,
      "num_input_tokens_seen": 5254129984,
      "step": 18480,
      "train_runtime": 179988.4168,
      "train_tokens_per_second": 29191.49
    },
    {
      "epoch": 0.6542136676345125,
      "grad_norm": 1.484375,
      "learning_rate": 2.9623161190082472e-05,
      "loss": 1.1064335823059082,
      "num_input_tokens_seen": 5256959360,
      "step": 18490,
      "train_runtime": 180088.4742,
      "train_tokens_per_second": 29190.982
    },
    {
      "epoch": 0.6545674878982413,
      "grad_norm": 1.4921875,
      "learning_rate": 2.9617963505907554e-05,
      "loss": 1.0842641830444335,
      "num_input_tokens_seen": 5259849216,
      "step": 18500,
      "train_runtime": 180191.5962,
      "train_tokens_per_second": 29190.314
    },
    {
      "epoch": 0.65492130816197,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9612768556732145e-05,
      "loss": 1.0885549545288087,
      "num_input_tokens_seen": 5262726208,
      "step": 18510,
      "train_runtime": 180289.508,
      "train_tokens_per_second": 29190.419
    },
    {
      "epoch": 0.6552751284256989,
      "grad_norm": 1.4609375,
      "learning_rate": 2.960757634015852e-05,
      "loss": 1.081289291381836,
      "num_input_tokens_seen": 5265541184,
      "step": 18520,
      "train_runtime": 180385.9793,
      "train_tokens_per_second": 29190.413
    },
    {
      "epoch": 0.6556289486894277,
      "grad_norm": 1.390625,
      "learning_rate": 2.9602386853791885e-05,
      "loss": 1.0903072357177734,
      "num_input_tokens_seen": 5268363008,
      "step": 18530,
      "train_runtime": 180478.5022,
      "train_tokens_per_second": 29191.083
    },
    {
      "epoch": 0.6559827689531564,
      "grad_norm": 1.4609375,
      "learning_rate": 2.959720009524038e-05,
      "loss": 1.0963611602783203,
      "num_input_tokens_seen": 5271242496,
      "step": 18540,
      "train_runtime": 180579.5244,
      "train_tokens_per_second": 29190.699
    },
    {
      "epoch": 0.6563365892168852,
      "grad_norm": 1.484375,
      "learning_rate": 2.9592016062115085e-05,
      "loss": 1.0904500961303711,
      "num_input_tokens_seen": 5274129024,
      "step": 18550,
      "train_runtime": 180676.8974,
      "train_tokens_per_second": 29190.943
    },
    {
      "epoch": 0.656690409480614,
      "grad_norm": 1.484375,
      "learning_rate": 2.9586834752030002e-05,
      "loss": 1.0924099922180175,
      "num_input_tokens_seen": 5277002112,
      "step": 18560,
      "train_runtime": 180774.8022,
      "train_tokens_per_second": 29191.027
    },
    {
      "epoch": 0.6570442297443427,
      "grad_norm": 1.453125,
      "learning_rate": 2.958165616260206e-05,
      "loss": 1.0979349136352539,
      "num_input_tokens_seen": 5279807488,
      "step": 18570,
      "train_runtime": 180867.7661,
      "train_tokens_per_second": 29191.534
    },
    {
      "epoch": 0.6573980500080715,
      "grad_norm": 1.4453125,
      "learning_rate": 2.9576480291451114e-05,
      "loss": 1.0780704498291016,
      "num_input_tokens_seen": 5282667136,
      "step": 18580,
      "train_runtime": 180965.3503,
      "train_tokens_per_second": 29191.595
    },
    {
      "epoch": 0.6577518702718003,
      "grad_norm": 1.4375,
      "learning_rate": 2.957130713619991e-05,
      "loss": 1.080467414855957,
      "num_input_tokens_seen": 5285451392,
      "step": 18590,
      "train_runtime": 181059.2849,
      "train_tokens_per_second": 29191.827
    },
    {
      "epoch": 0.658105690535529,
      "grad_norm": 1.4609375,
      "learning_rate": 2.9566136694474138e-05,
      "loss": 1.0925837516784669,
      "num_input_tokens_seen": 5288344704,
      "step": 18600,
      "train_runtime": 181157.395,
      "train_tokens_per_second": 29191.989
    },
    {
      "epoch": 0.6584595107992579,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9560968963902365e-05,
      "loss": 1.0902776718139648,
      "num_input_tokens_seen": 5291221376,
      "step": 18610,
      "train_runtime": 181255.453,
      "train_tokens_per_second": 29192.067
    },
    {
      "epoch": 0.6588133310629867,
      "grad_norm": 1.4921875,
      "learning_rate": 2.9555803942116062e-05,
      "loss": 1.0930139541625976,
      "num_input_tokens_seen": 5294061632,
      "step": 18620,
      "train_runtime": 181349.5866,
      "train_tokens_per_second": 29192.576
    },
    {
      "epoch": 0.6591671513267154,
      "grad_norm": 1.453125,
      "learning_rate": 2.955064162674961e-05,
      "loss": 1.0928016662597657,
      "num_input_tokens_seen": 5296885440,
      "step": 18630,
      "train_runtime": 181445.2004,
      "train_tokens_per_second": 29192.756
    },
    {
      "epoch": 0.6595209715904442,
      "grad_norm": 1.546875,
      "learning_rate": 2.9545482015440266e-05,
      "loss": 1.0867008209228515,
      "num_input_tokens_seen": 5299739584,
      "step": 18640,
      "train_runtime": 181543.1924,
      "train_tokens_per_second": 29192.72
    },
    {
      "epoch": 0.659874791854173,
      "grad_norm": 1.4765625,
      "learning_rate": 2.954032510582819e-05,
      "loss": 1.0938479423522949,
      "num_input_tokens_seen": 5302608896,
      "step": 18650,
      "train_runtime": 181644.1586,
      "train_tokens_per_second": 29192.29
    },
    {
      "epoch": 0.6602286121179017,
      "grad_norm": 1.421875,
      "learning_rate": 2.95351708955564e-05,
      "loss": 1.0895544052124024,
      "num_input_tokens_seen": 5305451584,
      "step": 18660,
      "train_runtime": 181739.5908,
      "train_tokens_per_second": 29192.602
    },
    {
      "epoch": 0.6605824323816305,
      "grad_norm": 1.4609375,
      "learning_rate": 2.9530019382270823e-05,
      "loss": 1.0963059425354005,
      "num_input_tokens_seen": 5308258240,
      "step": 18670,
      "train_runtime": 181835.071,
      "train_tokens_per_second": 29192.709
    },
    {
      "epoch": 0.6609362526453593,
      "grad_norm": 1.4296875,
      "learning_rate": 2.9524870563620233e-05,
      "loss": 1.0789520263671875,
      "num_input_tokens_seen": 5311137216,
      "step": 18680,
      "train_runtime": 181936.6169,
      "train_tokens_per_second": 29192.239
    },
    {
      "epoch": 0.6612900729090881,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9519724437256287e-05,
      "loss": 1.1076924324035644,
      "num_input_tokens_seen": 5314011520,
      "step": 18690,
      "train_runtime": 182036.1582,
      "train_tokens_per_second": 29192.066
    },
    {
      "epoch": 0.6616438931728169,
      "grad_norm": 1.390625,
      "learning_rate": 2.9514581000833496e-05,
      "loss": 1.0936838150024415,
      "num_input_tokens_seen": 5316814848,
      "step": 18700,
      "train_runtime": 182129.8169,
      "train_tokens_per_second": 29192.446
    },
    {
      "epoch": 0.6619977134365457,
      "grad_norm": 1.46875,
      "learning_rate": 2.950944025200924e-05,
      "loss": 1.0819818496704101,
      "num_input_tokens_seen": 5319664256,
      "step": 18710,
      "train_runtime": 182226.0389,
      "train_tokens_per_second": 29192.668
    },
    {
      "epoch": 0.6623515337002744,
      "grad_norm": 1.5390625,
      "learning_rate": 2.950430218844375e-05,
      "loss": 1.0942863464355468,
      "num_input_tokens_seen": 5322458624,
      "step": 18720,
      "train_runtime": 182319.1659,
      "train_tokens_per_second": 29193.083
    },
    {
      "epoch": 0.6627053539640032,
      "grad_norm": 1.40625,
      "learning_rate": 2.9499166807800106e-05,
      "loss": 1.0859619140625,
      "num_input_tokens_seen": 5325399872,
      "step": 18730,
      "train_runtime": 182422.1745,
      "train_tokens_per_second": 29192.722
    },
    {
      "epoch": 0.663059174227732,
      "grad_norm": 1.453125,
      "learning_rate": 2.949403410774424e-05,
      "loss": 1.0927477836608888,
      "num_input_tokens_seen": 5328314432,
      "step": 18740,
      "train_runtime": 182524.5124,
      "train_tokens_per_second": 29192.323
    },
    {
      "epoch": 0.6634129944914607,
      "grad_norm": 1.3828125,
      "learning_rate": 2.948890408594492e-05,
      "loss": 1.0970878601074219,
      "num_input_tokens_seen": 5331233920,
      "step": 18750,
      "train_runtime": 182626.7291,
      "train_tokens_per_second": 29191.97
    },
    {
      "epoch": 0.6637668147551895,
      "grad_norm": 1.46875,
      "learning_rate": 2.9483776740073748e-05,
      "loss": 1.0828668594360351,
      "num_input_tokens_seen": 5334099904,
      "step": 18760,
      "train_runtime": 182725.1574,
      "train_tokens_per_second": 29191.929
    },
    {
      "epoch": 0.6641206350189184,
      "grad_norm": 1.4609375,
      "learning_rate": 2.947865206780518e-05,
      "loss": 1.097357177734375,
      "num_input_tokens_seen": 5336928320,
      "step": 18770,
      "train_runtime": 182823.5492,
      "train_tokens_per_second": 29191.69
    },
    {
      "epoch": 0.6644744552826471,
      "grad_norm": 1.4609375,
      "learning_rate": 2.947353006681647e-05,
      "loss": 1.0987221717834472,
      "num_input_tokens_seen": 5339757504,
      "step": 18780,
      "train_runtime": 182921.9824,
      "train_tokens_per_second": 29191.448
    },
    {
      "epoch": 0.6648282755463759,
      "grad_norm": 1.5,
      "learning_rate": 2.9468410734787717e-05,
      "loss": 1.0904268264770507,
      "num_input_tokens_seen": 5342539648,
      "step": 18790,
      "train_runtime": 183015.0258,
      "train_tokens_per_second": 29191.809
    },
    {
      "epoch": 0.6651820958101047,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9463294069401838e-05,
      "loss": 1.0936807632446288,
      "num_input_tokens_seen": 5345349760,
      "step": 18800,
      "train_runtime": 183112.2276,
      "train_tokens_per_second": 29191.659
    },
    {
      "epoch": 0.6655359160738334,
      "grad_norm": 1.5,
      "learning_rate": 2.9458180068344555e-05,
      "loss": 1.0877982139587403,
      "num_input_tokens_seen": 5348219840,
      "step": 18810,
      "train_runtime": 183209.4026,
      "train_tokens_per_second": 29191.841
    },
    {
      "epoch": 0.6658897363375622,
      "grad_norm": 1.453125,
      "learning_rate": 2.9453068729304407e-05,
      "loss": 1.1054519653320312,
      "num_input_tokens_seen": 5351087040,
      "step": 18820,
      "train_runtime": 183307.6863,
      "train_tokens_per_second": 29191.831
    },
    {
      "epoch": 0.666243556601291,
      "grad_norm": 1.4765625,
      "learning_rate": 2.944796004997274e-05,
      "loss": 1.085451316833496,
      "num_input_tokens_seen": 5353951744,
      "step": 18830,
      "train_runtime": 183407.224,
      "train_tokens_per_second": 29191.608
    },
    {
      "epoch": 0.6665973768650197,
      "grad_norm": 1.4609375,
      "learning_rate": 2.94428540280437e-05,
      "loss": 1.0862783432006835,
      "num_input_tokens_seen": 5356777280,
      "step": 18840,
      "train_runtime": 183503.9527,
      "train_tokens_per_second": 29191.618
    },
    {
      "epoch": 0.6669511971287485,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9437750661214242e-05,
      "loss": 1.101036548614502,
      "num_input_tokens_seen": 5359628992,
      "step": 18850,
      "train_runtime": 183602.508,
      "train_tokens_per_second": 29191.48
    },
    {
      "epoch": 0.6673050173924774,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9432649947184094e-05,
      "loss": 1.0907785415649414,
      "num_input_tokens_seen": 5362466496,
      "step": 18860,
      "train_runtime": 183699.7633,
      "train_tokens_per_second": 29191.472
    },
    {
      "epoch": 0.6676588376562061,
      "grad_norm": 1.4765625,
      "learning_rate": 2.942755188365579e-05,
      "loss": 1.0816029548645019,
      "num_input_tokens_seen": 5365309760,
      "step": 18870,
      "train_runtime": 183794.2455,
      "train_tokens_per_second": 29191.935
    },
    {
      "epoch": 0.6680126579199349,
      "grad_norm": 1.4921875,
      "learning_rate": 2.9422456468334635e-05,
      "loss": 1.0955357551574707,
      "num_input_tokens_seen": 5368185728,
      "step": 18880,
      "train_runtime": 183893.2717,
      "train_tokens_per_second": 29191.855
    },
    {
      "epoch": 0.6683664781836637,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9417363698928734e-05,
      "loss": 1.0994853019714355,
      "num_input_tokens_seen": 5371068544,
      "step": 18890,
      "train_runtime": 183992.0101,
      "train_tokens_per_second": 29191.858
    },
    {
      "epoch": 0.6687202984473924,
      "grad_norm": 1.484375,
      "learning_rate": 2.9412273573148946e-05,
      "loss": 1.0925383567810059,
      "num_input_tokens_seen": 5373968000,
      "step": 18900,
      "train_runtime": 184090.5312,
      "train_tokens_per_second": 29191.985
    },
    {
      "epoch": 0.6690741187111212,
      "grad_norm": 1.46875,
      "learning_rate": 2.940718608870891e-05,
      "loss": 1.0968799591064453,
      "num_input_tokens_seen": 5376826432,
      "step": 18910,
      "train_runtime": 184186.995,
      "train_tokens_per_second": 29192.215
    },
    {
      "epoch": 0.66942793897485,
      "grad_norm": 1.453125,
      "learning_rate": 2.940210124332504e-05,
      "loss": 1.0887353897094727,
      "num_input_tokens_seen": 5379688192,
      "step": 18920,
      "train_runtime": 184284.8861,
      "train_tokens_per_second": 29192.238
    },
    {
      "epoch": 0.6697817592385787,
      "grad_norm": 1.484375,
      "learning_rate": 2.9397019034716504e-05,
      "loss": 1.084455966949463,
      "num_input_tokens_seen": 5382474368,
      "step": 18930,
      "train_runtime": 184377.7708,
      "train_tokens_per_second": 29192.643
    },
    {
      "epoch": 0.6701355795023076,
      "grad_norm": 1.4609375,
      "learning_rate": 2.9391939460605233e-05,
      "loss": 1.1016748428344727,
      "num_input_tokens_seen": 5385377792,
      "step": 18940,
      "train_runtime": 184479.4524,
      "train_tokens_per_second": 29192.291
    },
    {
      "epoch": 0.6704893997660364,
      "grad_norm": 1.40625,
      "learning_rate": 2.9386862518715914e-05,
      "loss": 1.0882539749145508,
      "num_input_tokens_seen": 5388224832,
      "step": 18950,
      "train_runtime": 184576.7722,
      "train_tokens_per_second": 29192.323
    },
    {
      "epoch": 0.6708432200297652,
      "grad_norm": 1.4921875,
      "learning_rate": 2.9381788206775966e-05,
      "loss": 1.0915789604187012,
      "num_input_tokens_seen": 5391128576,
      "step": 18960,
      "train_runtime": 184676.4331,
      "train_tokens_per_second": 29192.293
    },
    {
      "epoch": 0.6711970402934939,
      "grad_norm": 1.4375,
      "learning_rate": 2.937671652251559e-05,
      "loss": 1.0947673797607422,
      "num_input_tokens_seen": 5393952960,
      "step": 18970,
      "train_runtime": 184772.0976,
      "train_tokens_per_second": 29192.465
    },
    {
      "epoch": 0.6715508605572227,
      "grad_norm": 1.4375,
      "learning_rate": 2.9371647463667696e-05,
      "loss": 1.09671049118042,
      "num_input_tokens_seen": 5396779968,
      "step": 18980,
      "train_runtime": 184867.6518,
      "train_tokens_per_second": 29192.668
    },
    {
      "epoch": 0.6719046808209514,
      "grad_norm": 1.4140625,
      "learning_rate": 2.9366581027967943e-05,
      "loss": 1.091103458404541,
      "num_input_tokens_seen": 5399650560,
      "step": 18990,
      "train_runtime": 184966.3119,
      "train_tokens_per_second": 29192.616
    },
    {
      "epoch": 0.6722585010846802,
      "grad_norm": 1.4375,
      "learning_rate": 2.9361517213154726e-05,
      "loss": 1.0908233642578125,
      "num_input_tokens_seen": 5402479168,
      "step": 19000,
      "train_runtime": 185063.7875,
      "train_tokens_per_second": 29192.525
    },
    {
      "epoch": 0.672612321348409,
      "grad_norm": 1.5234375,
      "learning_rate": 2.935645601696917e-05,
      "loss": 1.091437530517578,
      "num_input_tokens_seen": 5405312896,
      "step": 19010,
      "train_runtime": 185160.0886,
      "train_tokens_per_second": 29192.646
    },
    {
      "epoch": 0.6729661416121379,
      "grad_norm": 1.4453125,
      "learning_rate": 2.9351397437155114e-05,
      "loss": 1.0892853736877441,
      "num_input_tokens_seen": 5408159488,
      "step": 19020,
      "train_runtime": 185259.0436,
      "train_tokens_per_second": 29192.418
    },
    {
      "epoch": 0.6733199618758666,
      "grad_norm": 1.4140625,
      "learning_rate": 2.934634147145913e-05,
      "loss": 1.0914436340332032,
      "num_input_tokens_seen": 5411064832,
      "step": 19030,
      "train_runtime": 185362.7922,
      "train_tokens_per_second": 29191.753
    },
    {
      "epoch": 0.6736737821395954,
      "grad_norm": 1.5390625,
      "learning_rate": 2.9341288117630495e-05,
      "loss": 1.089668083190918,
      "num_input_tokens_seen": 5413963968,
      "step": 19040,
      "train_runtime": 185465.6532,
      "train_tokens_per_second": 29191.195
    },
    {
      "epoch": 0.6740276024033242,
      "grad_norm": 1.4609375,
      "learning_rate": 2.933623737342121e-05,
      "loss": 1.099471092224121,
      "num_input_tokens_seen": 5416799744,
      "step": 19050,
      "train_runtime": 185562.9908,
      "train_tokens_per_second": 29191.164
    },
    {
      "epoch": 0.6743814226670529,
      "grad_norm": 1.421875,
      "learning_rate": 2.9331189236585977e-05,
      "loss": 1.0768820762634277,
      "num_input_tokens_seen": 5419656768,
      "step": 19060,
      "train_runtime": 185661.2006,
      "train_tokens_per_second": 29191.111
    },
    {
      "epoch": 0.6747352429307817,
      "grad_norm": 1.421875,
      "learning_rate": 2.9326143704882192e-05,
      "loss": 1.0833656311035156,
      "num_input_tokens_seen": 5422565120,
      "step": 19070,
      "train_runtime": 185761.9342,
      "train_tokens_per_second": 29190.938
    },
    {
      "epoch": 0.6750890631945105,
      "grad_norm": 1.484375,
      "learning_rate": 2.932110077606997e-05,
      "loss": 1.1005870819091796,
      "num_input_tokens_seen": 5425444800,
      "step": 19080,
      "train_runtime": 185858.9366,
      "train_tokens_per_second": 29191.197
    },
    {
      "epoch": 0.6754428834582392,
      "grad_norm": 1.46875,
      "learning_rate": 2.931606044791212e-05,
      "loss": 1.0951419830322267,
      "num_input_tokens_seen": 5428307008,
      "step": 19090,
      "train_runtime": 185955.8984,
      "train_tokens_per_second": 29191.368
    },
    {
      "epoch": 0.675796703721968,
      "grad_norm": 1.46875,
      "learning_rate": 2.9311022718174114e-05,
      "loss": 1.0833753585815429,
      "num_input_tokens_seen": 5431148672,
      "step": 19100,
      "train_runtime": 186051.9164,
      "train_tokens_per_second": 29191.576
    },
    {
      "epoch": 0.6761505239856969,
      "grad_norm": 1.46875,
      "learning_rate": 2.930598758462415e-05,
      "loss": 1.0919424057006837,
      "num_input_tokens_seen": 5433984128,
      "step": 19110,
      "train_runtime": 186148.4115,
      "train_tokens_per_second": 29191.676
    },
    {
      "epoch": 0.6765043442494256,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9300955045033072e-05,
      "loss": 1.091560173034668,
      "num_input_tokens_seen": 5436845760,
      "step": 19120,
      "train_runtime": 186246.6845,
      "train_tokens_per_second": 29191.638
    },
    {
      "epoch": 0.6768581645131544,
      "grad_norm": 1.5078125,
      "learning_rate": 2.9295925097174435e-05,
      "loss": 1.092702865600586,
      "num_input_tokens_seen": 5439687872,
      "step": 19130,
      "train_runtime": 186343.686,
      "train_tokens_per_second": 29191.694
    },
    {
      "epoch": 0.6772119847768832,
      "grad_norm": 1.484375,
      "learning_rate": 2.929089773882445e-05,
      "loss": 1.0795379638671876,
      "num_input_tokens_seen": 5442598016,
      "step": 19140,
      "train_runtime": 186443.5976,
      "train_tokens_per_second": 29191.659
    },
    {
      "epoch": 0.6775658050406119,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9285872967762007e-05,
      "loss": 1.0872017860412597,
      "num_input_tokens_seen": 5445430784,
      "step": 19150,
      "train_runtime": 186541.2136,
      "train_tokens_per_second": 29191.569
    },
    {
      "epoch": 0.6779196253043407,
      "grad_norm": 1.4453125,
      "learning_rate": 2.9280850781768638e-05,
      "loss": 1.0945188522338867,
      "num_input_tokens_seen": 5448254016,
      "step": 19160,
      "train_runtime": 186636.6447,
      "train_tokens_per_second": 29191.77
    },
    {
      "epoch": 0.6782734455680695,
      "grad_norm": 1.484375,
      "learning_rate": 2.9275831178628576e-05,
      "loss": 1.1001896858215332,
      "num_input_tokens_seen": 5451079232,
      "step": 19170,
      "train_runtime": 186734.4365,
      "train_tokens_per_second": 29191.612
    },
    {
      "epoch": 0.6786272658317982,
      "grad_norm": 1.359375,
      "learning_rate": 2.927081415612869e-05,
      "loss": 1.0868235588073731,
      "num_input_tokens_seen": 5453943552,
      "step": 19180,
      "train_runtime": 186831.1071,
      "train_tokens_per_second": 29191.839
    },
    {
      "epoch": 0.6789810860955271,
      "grad_norm": 1.4609375,
      "learning_rate": 2.9265799712058505e-05,
      "loss": 1.0899572372436523,
      "num_input_tokens_seen": 5456769984,
      "step": 19190,
      "train_runtime": 186928.818,
      "train_tokens_per_second": 29191.7
    },
    {
      "epoch": 0.6793349063592559,
      "grad_norm": 1.40625,
      "learning_rate": 2.926078784421019e-05,
      "loss": 1.088314151763916,
      "num_input_tokens_seen": 5459565120,
      "step": 19200,
      "train_runtime": 187025.1999,
      "train_tokens_per_second": 29191.602
    },
    {
      "epoch": 0.6796887266229846,
      "grad_norm": 1.4296875,
      "learning_rate": 2.9255778550378575e-05,
      "loss": 1.09413423538208,
      "num_input_tokens_seen": 5462365376,
      "step": 19210,
      "train_runtime": 187119.7468,
      "train_tokens_per_second": 29191.817
    },
    {
      "epoch": 0.6800425468867134,
      "grad_norm": 1.484375,
      "learning_rate": 2.9250771828361118e-05,
      "loss": 1.099820899963379,
      "num_input_tokens_seen": 5465167104,
      "step": 19220,
      "train_runtime": 187214.3196,
      "train_tokens_per_second": 29192.036
    },
    {
      "epoch": 0.6803963671504422,
      "grad_norm": 1.4609375,
      "learning_rate": 2.9245767675957923e-05,
      "loss": 1.088345432281494,
      "num_input_tokens_seen": 5468045760,
      "step": 19230,
      "train_runtime": 187315.3967,
      "train_tokens_per_second": 29191.651
    },
    {
      "epoch": 0.6807501874141709,
      "grad_norm": 1.5,
      "learning_rate": 2.924076609097172e-05,
      "loss": 1.0848025321960448,
      "num_input_tokens_seen": 5470898304,
      "step": 19240,
      "train_runtime": 187412.0854,
      "train_tokens_per_second": 29191.812
    },
    {
      "epoch": 0.6811040076778997,
      "grad_norm": 1.390625,
      "learning_rate": 2.9235767071207876e-05,
      "loss": 1.0876169204711914,
      "num_input_tokens_seen": 5473720128,
      "step": 19250,
      "train_runtime": 187510.3437,
      "train_tokens_per_second": 29191.564
    },
    {
      "epoch": 0.6814578279416285,
      "grad_norm": 1.3984375,
      "learning_rate": 2.9230770614474383e-05,
      "loss": 1.083964729309082,
      "num_input_tokens_seen": 5476543296,
      "step": 19260,
      "train_runtime": 187604.4355,
      "train_tokens_per_second": 29191.971
    },
    {
      "epoch": 0.6818116482053573,
      "grad_norm": 1.4296875,
      "learning_rate": 2.9225776718581842e-05,
      "loss": 1.0896371841430663,
      "num_input_tokens_seen": 5479396800,
      "step": 19270,
      "train_runtime": 187704.9121,
      "train_tokens_per_second": 29191.547
    },
    {
      "epoch": 0.6821654684690861,
      "grad_norm": 1.578125,
      "learning_rate": 2.9220785381343495e-05,
      "loss": 1.082411003112793,
      "num_input_tokens_seen": 5482251968,
      "step": 19280,
      "train_runtime": 187800.92,
      "train_tokens_per_second": 29191.827
    },
    {
      "epoch": 0.6825192887328149,
      "grad_norm": 1.4375,
      "learning_rate": 2.9215796600575174e-05,
      "loss": 1.100215530395508,
      "num_input_tokens_seen": 5485147520,
      "step": 19290,
      "train_runtime": 187900.1281,
      "train_tokens_per_second": 29191.824
    },
    {
      "epoch": 0.6828731089965436,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9210810374095332e-05,
      "loss": 1.0939317703247071,
      "num_input_tokens_seen": 5488081408,
      "step": 19300,
      "train_runtime": 188004.1669,
      "train_tokens_per_second": 29191.275
    },
    {
      "epoch": 0.6832269292602724,
      "grad_norm": 1.46875,
      "learning_rate": 2.9205826699725026e-05,
      "loss": 1.0846552848815918,
      "num_input_tokens_seen": 5490922368,
      "step": 19310,
      "train_runtime": 188101.1667,
      "train_tokens_per_second": 29191.325
    },
    {
      "epoch": 0.6835807495240012,
      "grad_norm": 1.3984375,
      "learning_rate": 2.920084557528791e-05,
      "loss": 1.0832067489624024,
      "num_input_tokens_seen": 5493779520,
      "step": 19320,
      "train_runtime": 188199.2343,
      "train_tokens_per_second": 29191.296
    },
    {
      "epoch": 0.6839345697877299,
      "grad_norm": 1.46875,
      "learning_rate": 2.9195866998610245e-05,
      "loss": 1.0840791702270507,
      "num_input_tokens_seen": 5496683584,
      "step": 19330,
      "train_runtime": 188299.4467,
      "train_tokens_per_second": 29191.183
    },
    {
      "epoch": 0.6842883900514587,
      "grad_norm": 1.453125,
      "learning_rate": 2.9190890967520878e-05,
      "loss": 1.1022411346435548,
      "num_input_tokens_seen": 5499504832,
      "step": 19340,
      "train_runtime": 188395.2866,
      "train_tokens_per_second": 29191.308
    },
    {
      "epoch": 0.6846422103151875,
      "grad_norm": 1.421875,
      "learning_rate": 2.9185917479851243e-05,
      "loss": 1.0856489181518554,
      "num_input_tokens_seen": 5502320448,
      "step": 19350,
      "train_runtime": 188489.1529,
      "train_tokens_per_second": 29191.709
    },
    {
      "epoch": 0.6849960305789163,
      "grad_norm": 1.4375,
      "learning_rate": 2.9180946533435366e-05,
      "loss": 1.0901593208312987,
      "num_input_tokens_seen": 5505159232,
      "step": 19360,
      "train_runtime": 188587.6478,
      "train_tokens_per_second": 29191.515
    },
    {
      "epoch": 0.6853498508426451,
      "grad_norm": 1.453125,
      "learning_rate": 2.9175978126109853e-05,
      "loss": 1.0906315803527833,
      "num_input_tokens_seen": 5508060096,
      "step": 19370,
      "train_runtime": 188686.6545,
      "train_tokens_per_second": 29191.572
    },
    {
      "epoch": 0.6857036711063739,
      "grad_norm": 1.515625,
      "learning_rate": 2.9171012255713885e-05,
      "loss": 1.0797996520996094,
      "num_input_tokens_seen": 5510877184,
      "step": 19380,
      "train_runtime": 188781.1867,
      "train_tokens_per_second": 29191.877
    },
    {
      "epoch": 0.6860574913701026,
      "grad_norm": 1.46875,
      "learning_rate": 2.9166048920089217e-05,
      "loss": 1.0906700134277343,
      "num_input_tokens_seen": 5513754944,
      "step": 19390,
      "train_runtime": 188880.392,
      "train_tokens_per_second": 29191.781
    },
    {
      "epoch": 0.6864113116338314,
      "grad_norm": 1.421875,
      "learning_rate": 2.9161088117080175e-05,
      "loss": 1.08398494720459,
      "num_input_tokens_seen": 5516608448,
      "step": 19400,
      "train_runtime": 188977.526,
      "train_tokens_per_second": 29191.876
    },
    {
      "epoch": 0.6867651318975602,
      "grad_norm": 1.4609375,
      "learning_rate": 2.9156129844533658e-05,
      "loss": 1.1016504287719726,
      "num_input_tokens_seen": 5519425216,
      "step": 19410,
      "train_runtime": 189073.5648,
      "train_tokens_per_second": 29191.946
    },
    {
      "epoch": 0.6871189521612889,
      "grad_norm": 1.5,
      "learning_rate": 2.9151174100299104e-05,
      "loss": 1.0955078125,
      "num_input_tokens_seen": 5522282560,
      "step": 19420,
      "train_runtime": 189171.022,
      "train_tokens_per_second": 29192.011
    },
    {
      "epoch": 0.6874727724250177,
      "grad_norm": 1.4453125,
      "learning_rate": 2.9146220882228535e-05,
      "loss": 1.092181396484375,
      "num_input_tokens_seen": 5525120704,
      "step": 19430,
      "train_runtime": 189267.205,
      "train_tokens_per_second": 29192.171
    },
    {
      "epoch": 0.6878265926887466,
      "grad_norm": 1.421875,
      "learning_rate": 2.914127018817651e-05,
      "loss": 1.0844809532165527,
      "num_input_tokens_seen": 5527968768,
      "step": 19440,
      "train_runtime": 189363.597,
      "train_tokens_per_second": 29192.352
    },
    {
      "epoch": 0.6881804129524753,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9136322016000152e-05,
      "loss": 1.094071388244629,
      "num_input_tokens_seen": 5530816640,
      "step": 19450,
      "train_runtime": 189460.134,
      "train_tokens_per_second": 29192.509
    },
    {
      "epoch": 0.6885342332162041,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9131376363559116e-05,
      "loss": 1.0853330612182617,
      "num_input_tokens_seen": 5533670784,
      "step": 19460,
      "train_runtime": 189558.8665,
      "train_tokens_per_second": 29192.361
    },
    {
      "epoch": 0.6888880534799329,
      "grad_norm": 1.3828125,
      "learning_rate": 2.9126433228715606e-05,
      "loss": 1.0917522430419921,
      "num_input_tokens_seen": 5536528192,
      "step": 19470,
      "train_runtime": 189656.5566,
      "train_tokens_per_second": 29192.39
    },
    {
      "epoch": 0.6892418737436616,
      "grad_norm": 1.453125,
      "learning_rate": 2.9121492609334354e-05,
      "loss": 1.0888936996459961,
      "num_input_tokens_seen": 5539371584,
      "step": 19480,
      "train_runtime": 189755.0936,
      "train_tokens_per_second": 29192.215
    },
    {
      "epoch": 0.6895956940073904,
      "grad_norm": 1.53125,
      "learning_rate": 2.9116554503282656e-05,
      "loss": 1.1009056091308593,
      "num_input_tokens_seen": 5542197632,
      "step": 19490,
      "train_runtime": 189852.9602,
      "train_tokens_per_second": 29192.053
    },
    {
      "epoch": 0.6899495142711192,
      "grad_norm": 1.4375,
      "learning_rate": 2.9111618908430303e-05,
      "loss": 1.1005096435546875,
      "num_input_tokens_seen": 5545063616,
      "step": 19500,
      "train_runtime": 189950.3237,
      "train_tokens_per_second": 29192.178
    },
    {
      "epoch": 0.6903033345348479,
      "grad_norm": 1.4765625,
      "learning_rate": 2.9106685822649643e-05,
      "loss": 1.0799062728881836,
      "num_input_tokens_seen": 5547930752,
      "step": 19510,
      "train_runtime": 190050.5956,
      "train_tokens_per_second": 29191.862
    },
    {
      "epoch": 0.6906571547985768,
      "grad_norm": 1.5078125,
      "learning_rate": 2.910175524381552e-05,
      "loss": 1.0904115676879882,
      "num_input_tokens_seen": 5550838656,
      "step": 19520,
      "train_runtime": 190152.5324,
      "train_tokens_per_second": 29191.505
    },
    {
      "epoch": 0.6910109750623056,
      "grad_norm": 1.4453125,
      "learning_rate": 2.9096827169805318e-05,
      "loss": 1.1013668060302735,
      "num_input_tokens_seen": 5553703552,
      "step": 19530,
      "train_runtime": 190249.9517,
      "train_tokens_per_second": 29191.616
    },
    {
      "epoch": 0.6913647953260343,
      "grad_norm": 1.3984375,
      "learning_rate": 2.9091901598498923e-05,
      "loss": 1.0842442512512207,
      "num_input_tokens_seen": 5556544960,
      "step": 19540,
      "train_runtime": 190345.4545,
      "train_tokens_per_second": 29191.897
    },
    {
      "epoch": 0.6917186155897631,
      "grad_norm": 1.515625,
      "learning_rate": 2.9086978527778736e-05,
      "loss": 1.0904832839965821,
      "num_input_tokens_seen": 5559399936,
      "step": 19550,
      "train_runtime": 190445.6296,
      "train_tokens_per_second": 29191.533
    },
    {
      "epoch": 0.6920724358534919,
      "grad_norm": 1.5078125,
      "learning_rate": 2.9082057955529668e-05,
      "loss": 1.0956499099731445,
      "num_input_tokens_seen": 5562200832,
      "step": 19560,
      "train_runtime": 190541.0884,
      "train_tokens_per_second": 29191.608
    },
    {
      "epoch": 0.6924262561172206,
      "grad_norm": 1.453125,
      "learning_rate": 2.907713987963914e-05,
      "loss": 1.0887033462524414,
      "num_input_tokens_seen": 5565021952,
      "step": 19570,
      "train_runtime": 190636.6222,
      "train_tokens_per_second": 29191.778
    },
    {
      "epoch": 0.6927800763809494,
      "grad_norm": 1.4453125,
      "learning_rate": 2.9072224297997058e-05,
      "loss": 1.0784814834594727,
      "num_input_tokens_seen": 5567839552,
      "step": 19580,
      "train_runtime": 190731.9377,
      "train_tokens_per_second": 29191.962
    },
    {
      "epoch": 0.6931338966446782,
      "grad_norm": 1.4921875,
      "learning_rate": 2.9067311208495834e-05,
      "loss": 1.096353530883789,
      "num_input_tokens_seen": 5570708480,
      "step": 19590,
      "train_runtime": 190830.4026,
      "train_tokens_per_second": 29191.934
    },
    {
      "epoch": 0.6934877169084069,
      "grad_norm": 1.578125,
      "learning_rate": 2.9062400609030372e-05,
      "loss": 1.0887290954589843,
      "num_input_tokens_seen": 5573613440,
      "step": 19600,
      "train_runtime": 190935.4069,
      "train_tokens_per_second": 29191.094
    },
    {
      "epoch": 0.6938415371721358,
      "grad_norm": 1.5390625,
      "learning_rate": 2.905749249749806e-05,
      "loss": 1.0947599411010742,
      "num_input_tokens_seen": 5576448704,
      "step": 19610,
      "train_runtime": 191031.4505,
      "train_tokens_per_second": 29191.26
    },
    {
      "epoch": 0.6941953574358646,
      "grad_norm": 1.5078125,
      "learning_rate": 2.905258687179878e-05,
      "loss": 1.0950462341308593,
      "num_input_tokens_seen": 5579299264,
      "step": 19620,
      "train_runtime": 191129.8609,
      "train_tokens_per_second": 29191.144
    },
    {
      "epoch": 0.6945491776995933,
      "grad_norm": 1.4140625,
      "learning_rate": 2.904768372983488e-05,
      "loss": 1.0760307312011719,
      "num_input_tokens_seen": 5582173632,
      "step": 19630,
      "train_runtime": 191229.0088,
      "train_tokens_per_second": 29191.04
    },
    {
      "epoch": 0.6949029979633221,
      "grad_norm": 1.4609375,
      "learning_rate": 2.90427830695112e-05,
      "loss": 1.0803937911987305,
      "num_input_tokens_seen": 5585031104,
      "step": 19640,
      "train_runtime": 191325.9687,
      "train_tokens_per_second": 29191.182
    },
    {
      "epoch": 0.6952568182270509,
      "grad_norm": 1.46875,
      "learning_rate": 2.9037884888735044e-05,
      "loss": 1.0880586624145507,
      "num_input_tokens_seen": 5587897024,
      "step": 19650,
      "train_runtime": 191423.5523,
      "train_tokens_per_second": 29191.272
    },
    {
      "epoch": 0.6956106384907796,
      "grad_norm": 1.4921875,
      "learning_rate": 2.9032989185416194e-05,
      "loss": 1.0889060020446777,
      "num_input_tokens_seen": 5590733440,
      "step": 19660,
      "train_runtime": 191518.7222,
      "train_tokens_per_second": 29191.577
    },
    {
      "epoch": 0.6959644587545084,
      "grad_norm": 1.484375,
      "learning_rate": 2.9028095957466888e-05,
      "loss": 1.0846498489379883,
      "num_input_tokens_seen": 5593578688,
      "step": 19670,
      "train_runtime": 191618.6324,
      "train_tokens_per_second": 29191.205
    },
    {
      "epoch": 0.6963182790182372,
      "grad_norm": 1.4296875,
      "learning_rate": 2.9023205202801833e-05,
      "loss": 1.1014820098876954,
      "num_input_tokens_seen": 5596428224,
      "step": 19680,
      "train_runtime": 191718.9395,
      "train_tokens_per_second": 29190.795
    },
    {
      "epoch": 0.696672099281966,
      "grad_norm": 1.4453125,
      "learning_rate": 2.90183169193382e-05,
      "loss": 1.086155891418457,
      "num_input_tokens_seen": 5599307520,
      "step": 19690,
      "train_runtime": 191818.0104,
      "train_tokens_per_second": 29190.729
    },
    {
      "epoch": 0.6970259195456948,
      "grad_norm": 1.4453125,
      "learning_rate": 2.90134311049956e-05,
      "loss": 1.0921913146972657,
      "num_input_tokens_seen": 5602154304,
      "step": 19700,
      "train_runtime": 191916.7749,
      "train_tokens_per_second": 29190.54
    },
    {
      "epoch": 0.6973797398094236,
      "grad_norm": 1.4765625,
      "learning_rate": 2.90085477576961e-05,
      "loss": 1.0807540893554688,
      "num_input_tokens_seen": 5605031168,
      "step": 19710,
      "train_runtime": 192016.6811,
      "train_tokens_per_second": 29190.335
    },
    {
      "epoch": 0.6977335600731523,
      "grad_norm": 1.4375,
      "learning_rate": 2.9003666875364226e-05,
      "loss": 1.087117862701416,
      "num_input_tokens_seen": 5607879552,
      "step": 19720,
      "train_runtime": 192117.1118,
      "train_tokens_per_second": 29189.901
    },
    {
      "epoch": 0.6980873803368811,
      "grad_norm": 1.484375,
      "learning_rate": 2.899878845592694e-05,
      "loss": 1.0962993621826171,
      "num_input_tokens_seen": 5610736960,
      "step": 19730,
      "train_runtime": 192214.2101,
      "train_tokens_per_second": 29190.022
    },
    {
      "epoch": 0.6984412006006099,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8993912497313636e-05,
      "loss": 1.1015631675720214,
      "num_input_tokens_seen": 5613547520,
      "step": 19740,
      "train_runtime": 192309.7418,
      "train_tokens_per_second": 29190.136
    },
    {
      "epoch": 0.6987950208643386,
      "grad_norm": 1.5234375,
      "learning_rate": 2.8989038997456153e-05,
      "loss": 1.1008919715881347,
      "num_input_tokens_seen": 5616413824,
      "step": 19750,
      "train_runtime": 192409.5395,
      "train_tokens_per_second": 29189.893
    },
    {
      "epoch": 0.6991488411280674,
      "grad_norm": 1.5234375,
      "learning_rate": 2.898416795428876e-05,
      "loss": 1.0842368125915527,
      "num_input_tokens_seen": 5619273088,
      "step": 19760,
      "train_runtime": 192508.2407,
      "train_tokens_per_second": 29189.779
    },
    {
      "epoch": 0.6995026613917963,
      "grad_norm": 1.4453125,
      "learning_rate": 2.897929936574816e-05,
      "loss": 1.0945915222167968,
      "num_input_tokens_seen": 5622143360,
      "step": 19770,
      "train_runtime": 192607.0722,
      "train_tokens_per_second": 29189.704
    },
    {
      "epoch": 0.699856481655525,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8974433229773478e-05,
      "loss": 1.0760332107543946,
      "num_input_tokens_seen": 5624978304,
      "step": 19780,
      "train_runtime": 192704.4175,
      "train_tokens_per_second": 29189.67
    },
    {
      "epoch": 0.7002103019192538,
      "grad_norm": 1.484375,
      "learning_rate": 2.896956954430625e-05,
      "loss": 1.0991595268249512,
      "num_input_tokens_seen": 5627826944,
      "step": 19790,
      "train_runtime": 192800.5018,
      "train_tokens_per_second": 29189.898
    },
    {
      "epoch": 0.7005641221829826,
      "grad_norm": 1.484375,
      "learning_rate": 2.896470830729045e-05,
      "loss": 1.0913871765136718,
      "num_input_tokens_seen": 5630693376,
      "step": 19800,
      "train_runtime": 192899.3496,
      "train_tokens_per_second": 29189.8
    },
    {
      "epoch": 0.7009179424467114,
      "grad_norm": 1.4453125,
      "learning_rate": 2.895984951667245e-05,
      "loss": 1.074981689453125,
      "num_input_tokens_seen": 5633505024,
      "step": 19810,
      "train_runtime": 192995.857,
      "train_tokens_per_second": 29189.772
    },
    {
      "epoch": 0.7012717627104401,
      "grad_norm": 1.4453125,
      "learning_rate": 2.8954993170401047e-05,
      "loss": 1.103561019897461,
      "num_input_tokens_seen": 5636371072,
      "step": 19820,
      "train_runtime": 193095.3345,
      "train_tokens_per_second": 29189.577
    },
    {
      "epoch": 0.7016255829741689,
      "grad_norm": 1.546875,
      "learning_rate": 2.8950139266427423e-05,
      "loss": 1.0803226470947265,
      "num_input_tokens_seen": 5639171712,
      "step": 19830,
      "train_runtime": 193195.1816,
      "train_tokens_per_second": 29188.987
    },
    {
      "epoch": 0.7019794032378976,
      "grad_norm": 1.453125,
      "learning_rate": 2.8945287802705186e-05,
      "loss": 1.0966381072998046,
      "num_input_tokens_seen": 5642090560,
      "step": 19840,
      "train_runtime": 193299.5293,
      "train_tokens_per_second": 29188.331
    },
    {
      "epoch": 0.7023332235016264,
      "grad_norm": 1.4921875,
      "learning_rate": 2.8940438777190336e-05,
      "loss": 1.0877382278442382,
      "num_input_tokens_seen": 5644966464,
      "step": 19850,
      "train_runtime": 193397.4449,
      "train_tokens_per_second": 29188.423
    },
    {
      "epoch": 0.7026870437653553,
      "grad_norm": 1.5234375,
      "learning_rate": 2.8935592187841265e-05,
      "loss": 1.0996005058288574,
      "num_input_tokens_seen": 5647789632,
      "step": 19860,
      "train_runtime": 193493.9888,
      "train_tokens_per_second": 29188.45
    },
    {
      "epoch": 0.7030408640290841,
      "grad_norm": 1.4765625,
      "learning_rate": 2.893074803261876e-05,
      "loss": 1.1107070922851563,
      "num_input_tokens_seen": 5650654400,
      "step": 19870,
      "train_runtime": 193592.5673,
      "train_tokens_per_second": 29188.385
    },
    {
      "epoch": 0.7033946842928128,
      "grad_norm": 1.453125,
      "learning_rate": 2.8925906309485995e-05,
      "loss": 1.1060708999633788,
      "num_input_tokens_seen": 5653547328,
      "step": 19880,
      "train_runtime": 193691.9477,
      "train_tokens_per_second": 29188.345
    },
    {
      "epoch": 0.7037485045565416,
      "grad_norm": 1.46875,
      "learning_rate": 2.8921067016408532e-05,
      "loss": 1.0840373992919923,
      "num_input_tokens_seen": 5656377152,
      "step": 19890,
      "train_runtime": 193786.0592,
      "train_tokens_per_second": 29188.772
    },
    {
      "epoch": 0.7041023248202704,
      "grad_norm": 1.46875,
      "learning_rate": 2.8916230151354316e-05,
      "loss": 1.09478816986084,
      "num_input_tokens_seen": 5659159808,
      "step": 19900,
      "train_runtime": 193880.5657,
      "train_tokens_per_second": 29188.897
    },
    {
      "epoch": 0.7044561450839991,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8911395712293677e-05,
      "loss": 1.0978190422058105,
      "num_input_tokens_seen": 5661991040,
      "step": 19910,
      "train_runtime": 193977.3448,
      "train_tokens_per_second": 29188.929
    },
    {
      "epoch": 0.7048099653477279,
      "grad_norm": 1.515625,
      "learning_rate": 2.8906563697199294e-05,
      "loss": 1.0917061805725097,
      "num_input_tokens_seen": 5664812992,
      "step": 19920,
      "train_runtime": 194072.7129,
      "train_tokens_per_second": 29189.127
    },
    {
      "epoch": 0.7051637856114567,
      "grad_norm": 1.4375,
      "learning_rate": 2.8901734104046245e-05,
      "loss": 1.0856008529663086,
      "num_input_tokens_seen": 5667594496,
      "step": 19930,
      "train_runtime": 194167.5294,
      "train_tokens_per_second": 29189.198
    },
    {
      "epoch": 0.7055176058751855,
      "grad_norm": 1.4921875,
      "learning_rate": 2.8896906930811964e-05,
      "loss": 1.0891366958618165,
      "num_input_tokens_seen": 5670416896,
      "step": 19940,
      "train_runtime": 194261.7956,
      "train_tokens_per_second": 29189.563
    },
    {
      "epoch": 0.7058714261389143,
      "grad_norm": 1.53125,
      "learning_rate": 2.8892082175476243e-05,
      "loss": 1.0832382202148438,
      "num_input_tokens_seen": 5673184896,
      "step": 19950,
      "train_runtime": 194353.1425,
      "train_tokens_per_second": 29190.086
    },
    {
      "epoch": 0.7062252464026431,
      "grad_norm": 1.484375,
      "learning_rate": 2.8887259836021246e-05,
      "loss": 1.07581787109375,
      "num_input_tokens_seen": 5676008320,
      "step": 19960,
      "train_runtime": 194448.4622,
      "train_tokens_per_second": 29190.297
    },
    {
      "epoch": 0.7065790666663718,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8882439910431493e-05,
      "loss": 1.0983402252197265,
      "num_input_tokens_seen": 5678878592,
      "step": 19970,
      "train_runtime": 194548.7966,
      "train_tokens_per_second": 29189.996
    },
    {
      "epoch": 0.7069328869301006,
      "grad_norm": 1.46875,
      "learning_rate": 2.8877622396693843e-05,
      "loss": 1.0802966117858888,
      "num_input_tokens_seen": 5681686336,
      "step": 19980,
      "train_runtime": 194643.0368,
      "train_tokens_per_second": 29190.288
    },
    {
      "epoch": 0.7072867071938294,
      "grad_norm": 1.4375,
      "learning_rate": 2.8872807292797516e-05,
      "loss": 1.0902936935424805,
      "num_input_tokens_seen": 5684484224,
      "step": 19990,
      "train_runtime": 194736.8987,
      "train_tokens_per_second": 29190.586
    },
    {
      "epoch": 0.7076405274575581,
      "grad_norm": 1.3984375,
      "learning_rate": 2.8867994596734084e-05,
      "loss": 1.0697978019714356,
      "num_input_tokens_seen": 5687337600,
      "step": 20000,
      "train_runtime": 194834.3094,
      "train_tokens_per_second": 29190.637
    },
    {
      "epoch": 0.7076405274575581,
      "eval_loss": 1.0228816270828247,
      "eval_runtime": 8.4427,
      "eval_samples_per_second": 472.363,
      "eval_steps_per_second": 3.79,
      "num_input_tokens_seen": 5687337600,
      "step": 20000
    },
    {
      "epoch": 0.7079943477212869,
      "grad_norm": 1.4296875,
      "learning_rate": 2.8863184306497437e-05,
      "loss": 1.0925306320190429,
      "num_input_tokens_seen": 5690213376,
      "step": 20010,
      "train_runtime": 194965.6015,
      "train_tokens_per_second": 29185.73
    },
    {
      "epoch": 0.7083481679850158,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8858376420083848e-05,
      "loss": 1.0952974319458009,
      "num_input_tokens_seen": 5693051008,
      "step": 20020,
      "train_runtime": 195061.0169,
      "train_tokens_per_second": 29186.001
    },
    {
      "epoch": 0.7087019882487445,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8853570935491873e-05,
      "loss": 1.0926799774169922,
      "num_input_tokens_seen": 5695909696,
      "step": 20030,
      "train_runtime": 195158.4023,
      "train_tokens_per_second": 29186.085
    },
    {
      "epoch": 0.7090558085124733,
      "grad_norm": 1.4453125,
      "learning_rate": 2.8848767850722447e-05,
      "loss": 1.0882314682006835,
      "num_input_tokens_seen": 5698707008,
      "step": 20040,
      "train_runtime": 195251.1642,
      "train_tokens_per_second": 29186.546
    },
    {
      "epoch": 0.7094096287762021,
      "grad_norm": 1.4921875,
      "learning_rate": 2.88439671637788e-05,
      "loss": 1.0749954223632812,
      "num_input_tokens_seen": 5701546880,
      "step": 20050,
      "train_runtime": 195345.0275,
      "train_tokens_per_second": 29187.059
    },
    {
      "epoch": 0.7097634490399308,
      "grad_norm": 1.453125,
      "learning_rate": 2.8839168872666505e-05,
      "loss": 1.0942911148071288,
      "num_input_tokens_seen": 5704427968,
      "step": 20060,
      "train_runtime": 195444.3986,
      "train_tokens_per_second": 29186.961
    },
    {
      "epoch": 0.7101172693036596,
      "grad_norm": 1.46875,
      "learning_rate": 2.8834372975393448e-05,
      "loss": 1.0947986602783204,
      "num_input_tokens_seen": 5707261696,
      "step": 20070,
      "train_runtime": 195543.1737,
      "train_tokens_per_second": 29186.709
    },
    {
      "epoch": 0.7104710895673884,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8829579469969843e-05,
      "loss": 1.0881196975708007,
      "num_input_tokens_seen": 5710143360,
      "step": 20080,
      "train_runtime": 195644.2279,
      "train_tokens_per_second": 29186.363
    },
    {
      "epoch": 0.7108249098311171,
      "grad_norm": 1.5,
      "learning_rate": 2.88247883544082e-05,
      "loss": 1.0811176300048828,
      "num_input_tokens_seen": 5712987712,
      "step": 20090,
      "train_runtime": 195739.4787,
      "train_tokens_per_second": 29186.691
    },
    {
      "epoch": 0.7111787300948459,
      "grad_norm": 1.46875,
      "learning_rate": 2.8819999626723366e-05,
      "loss": 1.0837835311889648,
      "num_input_tokens_seen": 5715797888,
      "step": 20100,
      "train_runtime": 195837.1104,
      "train_tokens_per_second": 29186.49
    },
    {
      "epoch": 0.7115325503585748,
      "grad_norm": 1.5,
      "learning_rate": 2.881521328493248e-05,
      "loss": 1.094403076171875,
      "num_input_tokens_seen": 5718698624,
      "step": 20110,
      "train_runtime": 195940.1735,
      "train_tokens_per_second": 29185.942
    },
    {
      "epoch": 0.7118863706223035,
      "grad_norm": 1.4921875,
      "learning_rate": 2.881042932705499e-05,
      "loss": 1.0817872047424317,
      "num_input_tokens_seen": 5721542016,
      "step": 20120,
      "train_runtime": 196038.5884,
      "train_tokens_per_second": 29185.795
    },
    {
      "epoch": 0.7122401908860323,
      "grad_norm": 1.4375,
      "learning_rate": 2.8805647751112635e-05,
      "loss": 1.0949193954467773,
      "num_input_tokens_seen": 5724366592,
      "step": 20130,
      "train_runtime": 196134.4216,
      "train_tokens_per_second": 29185.936
    },
    {
      "epoch": 0.7125940111497611,
      "grad_norm": 1.515625,
      "learning_rate": 2.8800868555129462e-05,
      "loss": 1.080448818206787,
      "num_input_tokens_seen": 5727242496,
      "step": 20140,
      "train_runtime": 196233.8922,
      "train_tokens_per_second": 29185.797
    },
    {
      "epoch": 0.7129478314134898,
      "grad_norm": 1.5,
      "learning_rate": 2.8796091737131814e-05,
      "loss": 1.0960376739501954,
      "num_input_tokens_seen": 5730071552,
      "step": 20150,
      "train_runtime": 196334.6362,
      "train_tokens_per_second": 29185.23
    },
    {
      "epoch": 0.7133016516772186,
      "grad_norm": 1.453125,
      "learning_rate": 2.8791317295148322e-05,
      "loss": 1.0841053009033204,
      "num_input_tokens_seen": 5732937792,
      "step": 20160,
      "train_runtime": 196432.9402,
      "train_tokens_per_second": 29185.216
    },
    {
      "epoch": 0.7136554719409474,
      "grad_norm": 1.40625,
      "learning_rate": 2.8786545227209893e-05,
      "loss": 1.0891578674316407,
      "num_input_tokens_seen": 5735873920,
      "step": 20170,
      "train_runtime": 196535.513,
      "train_tokens_per_second": 29184.924
    },
    {
      "epoch": 0.7140092922046761,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8781775531349742e-05,
      "loss": 1.0758840560913085,
      "num_input_tokens_seen": 5738691328,
      "step": 20180,
      "train_runtime": 196632.2626,
      "train_tokens_per_second": 29184.892
    },
    {
      "epoch": 0.714363112468405,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8777008205603334e-05,
      "loss": 1.080224609375,
      "num_input_tokens_seen": 5741575872,
      "step": 20190,
      "train_runtime": 196731.0299,
      "train_tokens_per_second": 29184.902
    },
    {
      "epoch": 0.7147169327321338,
      "grad_norm": 1.5078125,
      "learning_rate": 2.877224324800844e-05,
      "loss": 1.0910663604736328,
      "num_input_tokens_seen": 5744369344,
      "step": 20200,
      "train_runtime": 196826.0572,
      "train_tokens_per_second": 29185.004
    },
    {
      "epoch": 0.7150707529958625,
      "grad_norm": 1.53125,
      "learning_rate": 2.8767480656605078e-05,
      "loss": 1.0980361938476562,
      "num_input_tokens_seen": 5747209984,
      "step": 20210,
      "train_runtime": 196921.5211,
      "train_tokens_per_second": 29185.281
    },
    {
      "epoch": 0.7154245732595913,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8762720429435556e-05,
      "loss": 1.0987638473510741,
      "num_input_tokens_seen": 5750020864,
      "step": 20220,
      "train_runtime": 197017.2893,
      "train_tokens_per_second": 29185.362
    },
    {
      "epoch": 0.7157783935233201,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8757962564544448e-05,
      "loss": 1.0891666412353516,
      "num_input_tokens_seen": 5752873536,
      "step": 20230,
      "train_runtime": 197115.1965,
      "train_tokens_per_second": 29185.338
    },
    {
      "epoch": 0.7161322137870488,
      "grad_norm": 1.4296875,
      "learning_rate": 2.8753207059978586e-05,
      "loss": 1.0760698318481445,
      "num_input_tokens_seen": 5755677440,
      "step": 20240,
      "train_runtime": 197209.8521,
      "train_tokens_per_second": 29185.547
    },
    {
      "epoch": 0.7164860340507776,
      "grad_norm": 1.4296875,
      "learning_rate": 2.874845391378706e-05,
      "loss": 1.0904196739196776,
      "num_input_tokens_seen": 5758570688,
      "step": 20250,
      "train_runtime": 197309.8637,
      "train_tokens_per_second": 29185.417
    },
    {
      "epoch": 0.7168398543145064,
      "grad_norm": 1.4375,
      "learning_rate": 2.874370312402121e-05,
      "loss": 1.0977852821350098,
      "num_input_tokens_seen": 5761387904,
      "step": 20260,
      "train_runtime": 197404.6991,
      "train_tokens_per_second": 29185.667
    },
    {
      "epoch": 0.7171936745782352,
      "grad_norm": 1.4921875,
      "learning_rate": 2.8738954688734647e-05,
      "loss": 1.0906200408935547,
      "num_input_tokens_seen": 5764247104,
      "step": 20270,
      "train_runtime": 197505.1961,
      "train_tokens_per_second": 29185.293
    },
    {
      "epoch": 0.717547494841964,
      "grad_norm": 1.4375,
      "learning_rate": 2.8734208605983226e-05,
      "loss": 1.0951306343078613,
      "num_input_tokens_seen": 5767154432,
      "step": 20280,
      "train_runtime": 197608.0578,
      "train_tokens_per_second": 29184.814
    },
    {
      "epoch": 0.7179013151056928,
      "grad_norm": 1.5,
      "learning_rate": 2.8729464873825035e-05,
      "loss": 1.0831586837768554,
      "num_input_tokens_seen": 5769997696,
      "step": 20290,
      "train_runtime": 197708.2035,
      "train_tokens_per_second": 29184.412
    },
    {
      "epoch": 0.7182551353694215,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8724723490320427e-05,
      "loss": 1.0909561157226562,
      "num_input_tokens_seen": 5772786240,
      "step": 20300,
      "train_runtime": 197802.7165,
      "train_tokens_per_second": 29184.565
    },
    {
      "epoch": 0.7186089556331503,
      "grad_norm": 1.3984375,
      "learning_rate": 2.8719984453531983e-05,
      "loss": 1.0886833190917968,
      "num_input_tokens_seen": 5775593920,
      "step": 20310,
      "train_runtime": 197896.3895,
      "train_tokens_per_second": 29184.938
    },
    {
      "epoch": 0.7189627758968791,
      "grad_norm": 1.4375,
      "learning_rate": 2.871524776152452e-05,
      "loss": 1.0860897064208985,
      "num_input_tokens_seen": 5778514880,
      "step": 20320,
      "train_runtime": 198000.1728,
      "train_tokens_per_second": 29184.393
    },
    {
      "epoch": 0.7193165961606078,
      "grad_norm": 1.4453125,
      "learning_rate": 2.8710513412365093e-05,
      "loss": 1.1019561767578125,
      "num_input_tokens_seen": 5781344768,
      "step": 20330,
      "train_runtime": 198097.5728,
      "train_tokens_per_second": 29184.329
    },
    {
      "epoch": 0.7196704164243366,
      "grad_norm": 1.4453125,
      "learning_rate": 2.8705781404122977e-05,
      "loss": 1.0983673095703126,
      "num_input_tokens_seen": 5784193728,
      "step": 20340,
      "train_runtime": 198196.4053,
      "train_tokens_per_second": 29184.151
    },
    {
      "epoch": 0.7200242366880654,
      "grad_norm": 1.4921875,
      "learning_rate": 2.87010517348697e-05,
      "loss": 1.0921268463134766,
      "num_input_tokens_seen": 5787004928,
      "step": 20350,
      "train_runtime": 198289.2752,
      "train_tokens_per_second": 29184.659
    },
    {
      "epoch": 0.7203780569517942,
      "grad_norm": 1.5234375,
      "learning_rate": 2.8696324402678976e-05,
      "loss": 1.0820493698120117,
      "num_input_tokens_seen": 5789859136,
      "step": 20360,
      "train_runtime": 198387.9519,
      "train_tokens_per_second": 29184.53
    },
    {
      "epoch": 0.720731877215523,
      "grad_norm": 1.453125,
      "learning_rate": 2.8691599405626764e-05,
      "loss": 1.0730117797851562,
      "num_input_tokens_seen": 5792650304,
      "step": 20370,
      "train_runtime": 198480.455,
      "train_tokens_per_second": 29184.991
    },
    {
      "epoch": 0.7210856974792518,
      "grad_norm": 1.5078125,
      "learning_rate": 2.8686876741791234e-05,
      "loss": 1.075141143798828,
      "num_input_tokens_seen": 5795493184,
      "step": 20380,
      "train_runtime": 198575.8295,
      "train_tokens_per_second": 29185.29
    },
    {
      "epoch": 0.7214395177429805,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8682156409252775e-05,
      "loss": 1.0916683197021484,
      "num_input_tokens_seen": 5798369408,
      "step": 20390,
      "train_runtime": 198678.0561,
      "train_tokens_per_second": 29184.75
    },
    {
      "epoch": 0.7217933380067093,
      "grad_norm": 1.4140625,
      "learning_rate": 2.8677438406093976e-05,
      "loss": 1.0880443572998046,
      "num_input_tokens_seen": 5801295872,
      "step": 20400,
      "train_runtime": 198780.1186,
      "train_tokens_per_second": 29184.487
    },
    {
      "epoch": 0.7221471582704381,
      "grad_norm": 1.4375,
      "learning_rate": 2.867272273039964e-05,
      "loss": 1.0962202072143554,
      "num_input_tokens_seen": 5804118912,
      "step": 20410,
      "train_runtime": 198878.4957,
      "train_tokens_per_second": 29184.246
    },
    {
      "epoch": 0.7225009785341668,
      "grad_norm": 1.46875,
      "learning_rate": 2.8668009380256765e-05,
      "loss": 1.0831769943237304,
      "num_input_tokens_seen": 5806953088,
      "step": 20420,
      "train_runtime": 198975.6041,
      "train_tokens_per_second": 29184.247
    },
    {
      "epoch": 0.7228547987978956,
      "grad_norm": 1.46875,
      "learning_rate": 2.8663298353754574e-05,
      "loss": 1.0717395782470702,
      "num_input_tokens_seen": 5809839424,
      "step": 20430,
      "train_runtime": 199073.4705,
      "train_tokens_per_second": 29184.398
    },
    {
      "epoch": 0.7232086190616245,
      "grad_norm": 1.5078125,
      "learning_rate": 2.865858964898445e-05,
      "loss": 1.067544651031494,
      "num_input_tokens_seen": 5812671488,
      "step": 20440,
      "train_runtime": 199171.2854,
      "train_tokens_per_second": 29184.285
    },
    {
      "epoch": 0.7235624393253532,
      "grad_norm": 1.5234375,
      "learning_rate": 2.8653883264040004e-05,
      "loss": 1.0977293014526368,
      "num_input_tokens_seen": 5815518528,
      "step": 20450,
      "train_runtime": 199270.2613,
      "train_tokens_per_second": 29184.076
    },
    {
      "epoch": 0.723916259589082,
      "grad_norm": 1.4375,
      "learning_rate": 2.8649179197017017e-05,
      "loss": 1.074941349029541,
      "num_input_tokens_seen": 5818345600,
      "step": 20460,
      "train_runtime": 199364.8499,
      "train_tokens_per_second": 29184.41
    },
    {
      "epoch": 0.7242700798528108,
      "grad_norm": 1.484375,
      "learning_rate": 2.864447744601347e-05,
      "loss": 1.0839223861694336,
      "num_input_tokens_seen": 5821212608,
      "step": 20470,
      "train_runtime": 199465.5614,
      "train_tokens_per_second": 29184.048
    },
    {
      "epoch": 0.7246239001165395,
      "grad_norm": 1.453125,
      "learning_rate": 2.8639778009129507e-05,
      "loss": 1.0871542930603026,
      "num_input_tokens_seen": 5824051264,
      "step": 20480,
      "train_runtime": 199561.9693,
      "train_tokens_per_second": 29184.174
    },
    {
      "epoch": 0.7249777203802683,
      "grad_norm": 1.5546875,
      "learning_rate": 2.8635080884467492e-05,
      "loss": 1.1037616729736328,
      "num_input_tokens_seen": 5826942080,
      "step": 20490,
      "train_runtime": 199662.534,
      "train_tokens_per_second": 29183.953
    },
    {
      "epoch": 0.7253315406439971,
      "grad_norm": 1.546875,
      "learning_rate": 2.8630386070131927e-05,
      "loss": 1.0879095077514649,
      "num_input_tokens_seen": 5829822528,
      "step": 20500,
      "train_runtime": 199760.2839,
      "train_tokens_per_second": 29184.092
    },
    {
      "epoch": 0.7256853609077258,
      "grad_norm": 1.4453125,
      "learning_rate": 2.8625693564229507e-05,
      "loss": 1.0806976318359376,
      "num_input_tokens_seen": 5832641408,
      "step": 20510,
      "train_runtime": 199856.8314,
      "train_tokens_per_second": 29184.098
    },
    {
      "epoch": 0.7260391811714547,
      "grad_norm": 1.46875,
      "learning_rate": 2.8621003364869102e-05,
      "loss": 1.1008872985839844,
      "num_input_tokens_seen": 5835486976,
      "step": 20520,
      "train_runtime": 199955.4398,
      "train_tokens_per_second": 29183.937
    },
    {
      "epoch": 0.7263930014351835,
      "grad_norm": 1.5078125,
      "learning_rate": 2.8616315470161738e-05,
      "loss": 1.0980289459228516,
      "num_input_tokens_seen": 5838337664,
      "step": 20530,
      "train_runtime": 200049.8944,
      "train_tokens_per_second": 29184.408
    },
    {
      "epoch": 0.7267468216989122,
      "grad_norm": 1.4375,
      "learning_rate": 2.8611629878220624e-05,
      "loss": 1.0838214874267578,
      "num_input_tokens_seen": 5841176896,
      "step": 20540,
      "train_runtime": 200143.8794,
      "train_tokens_per_second": 29184.889
    },
    {
      "epoch": 0.727100641962641,
      "grad_norm": 1.5234375,
      "learning_rate": 2.8606946587161116e-05,
      "loss": 1.0899641036987304,
      "num_input_tokens_seen": 5844045184,
      "step": 20550,
      "train_runtime": 200239.7846,
      "train_tokens_per_second": 29185.235
    },
    {
      "epoch": 0.7274544622263698,
      "grad_norm": 1.484375,
      "learning_rate": 2.860226559510072e-05,
      "loss": 1.086819839477539,
      "num_input_tokens_seen": 5846909568,
      "step": 20560,
      "train_runtime": 200337.0593,
      "train_tokens_per_second": 29185.362
    },
    {
      "epoch": 0.7278082824900985,
      "grad_norm": 1.4296875,
      "learning_rate": 2.859758690015913e-05,
      "loss": 1.0753935813903808,
      "num_input_tokens_seen": 5849704832,
      "step": 20570,
      "train_runtime": 200433.6118,
      "train_tokens_per_second": 29185.249
    },
    {
      "epoch": 0.7281621027538273,
      "grad_norm": 1.4453125,
      "learning_rate": 2.8592910500458154e-05,
      "loss": 1.0973416328430177,
      "num_input_tokens_seen": 5852570432,
      "step": 20580,
      "train_runtime": 200529.0901,
      "train_tokens_per_second": 29185.643
    },
    {
      "epoch": 0.7285159230175561,
      "grad_norm": 1.421875,
      "learning_rate": 2.858823639412178e-05,
      "loss": 1.0996490478515626,
      "num_input_tokens_seen": 5855476864,
      "step": 20590,
      "train_runtime": 200631.3745,
      "train_tokens_per_second": 29185.25
    },
    {
      "epoch": 0.7288697432812848,
      "grad_norm": 1.4453125,
      "learning_rate": 2.858356457927613e-05,
      "loss": 1.0959861755371094,
      "num_input_tokens_seen": 5858295936,
      "step": 20600,
      "train_runtime": 200727.9582,
      "train_tokens_per_second": 29185.251
    },
    {
      "epoch": 0.7292235635450137,
      "grad_norm": 1.5,
      "learning_rate": 2.857889505404946e-05,
      "loss": 1.094660186767578,
      "num_input_tokens_seen": 5861133632,
      "step": 20610,
      "train_runtime": 200827.9127,
      "train_tokens_per_second": 29184.856
    },
    {
      "epoch": 0.7295773838087425,
      "grad_norm": 1.390625,
      "learning_rate": 2.8574227816572184e-05,
      "loss": 1.070242214202881,
      "num_input_tokens_seen": 5863989568,
      "step": 20620,
      "train_runtime": 200927.2653,
      "train_tokens_per_second": 29184.638
    },
    {
      "epoch": 0.7299312040724713,
      "grad_norm": 1.53125,
      "learning_rate": 2.856956286497684e-05,
      "loss": 1.0797122955322265,
      "num_input_tokens_seen": 5866803392,
      "step": 20630,
      "train_runtime": 201021.5821,
      "train_tokens_per_second": 29184.943
    },
    {
      "epoch": 0.7302850243362,
      "grad_norm": 1.421875,
      "learning_rate": 2.85649001973981e-05,
      "loss": 1.0852837562561035,
      "num_input_tokens_seen": 5869583616,
      "step": 20640,
      "train_runtime": 201116.799,
      "train_tokens_per_second": 29184.949
    },
    {
      "epoch": 0.7306388445999288,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8560239811972754e-05,
      "loss": 1.0829025268554688,
      "num_input_tokens_seen": 5872449152,
      "step": 20650,
      "train_runtime": 201214.4393,
      "train_tokens_per_second": 29185.029
    },
    {
      "epoch": 0.7309926648636575,
      "grad_norm": 1.4375,
      "learning_rate": 2.855558170683976e-05,
      "loss": 1.085296630859375,
      "num_input_tokens_seen": 5875205056,
      "step": 20660,
      "train_runtime": 201305.5004,
      "train_tokens_per_second": 29185.517
    },
    {
      "epoch": 0.7313464851273863,
      "grad_norm": 1.3984375,
      "learning_rate": 2.855092588014017e-05,
      "loss": 1.0773494720458985,
      "num_input_tokens_seen": 5878038464,
      "step": 20670,
      "train_runtime": 201401.1528,
      "train_tokens_per_second": 29185.724
    },
    {
      "epoch": 0.7317003053911151,
      "grad_norm": 1.4609375,
      "learning_rate": 2.854627233001715e-05,
      "loss": 1.0850372314453125,
      "num_input_tokens_seen": 5880880256,
      "step": 20680,
      "train_runtime": 201498.3317,
      "train_tokens_per_second": 29185.752
    },
    {
      "epoch": 0.732054125654844,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8541621054615992e-05,
      "loss": 1.090677261352539,
      "num_input_tokens_seen": 5883739392,
      "step": 20690,
      "train_runtime": 201596.9171,
      "train_tokens_per_second": 29185.662
    },
    {
      "epoch": 0.7324079459185727,
      "grad_norm": 1.4921875,
      "learning_rate": 2.8536972052084122e-05,
      "loss": 1.087679100036621,
      "num_input_tokens_seen": 5886572544,
      "step": 20700,
      "train_runtime": 201692.7934,
      "train_tokens_per_second": 29185.835
    },
    {
      "epoch": 0.7327617661823015,
      "grad_norm": 1.4765625,
      "learning_rate": 2.853232532057104e-05,
      "loss": 1.0921354293823242,
      "num_input_tokens_seen": 5889413760,
      "step": 20710,
      "train_runtime": 201793.1629,
      "train_tokens_per_second": 29185.398
    },
    {
      "epoch": 0.7331155864460303,
      "grad_norm": 1.4921875,
      "learning_rate": 2.8527680858228395e-05,
      "loss": 1.083078956604004,
      "num_input_tokens_seen": 5892251136,
      "step": 20720,
      "train_runtime": 201890.0336,
      "train_tokens_per_second": 29185.448
    },
    {
      "epoch": 0.733469406709759,
      "grad_norm": 1.4375,
      "learning_rate": 2.8523038663209906e-05,
      "loss": 1.1056851387023925,
      "num_input_tokens_seen": 5895028096,
      "step": 20730,
      "train_runtime": 201982.8335,
      "train_tokens_per_second": 29185.788
    },
    {
      "epoch": 0.7338232269734878,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8518398733671427e-05,
      "loss": 1.0864974975585937,
      "num_input_tokens_seen": 5897904192,
      "step": 20740,
      "train_runtime": 202081.8973,
      "train_tokens_per_second": 29185.713
    },
    {
      "epoch": 0.7341770472372166,
      "grad_norm": 1.5078125,
      "learning_rate": 2.8513761067770877e-05,
      "loss": 1.0926448822021484,
      "num_input_tokens_seen": 5900780160,
      "step": 20750,
      "train_runtime": 202179.4711,
      "train_tokens_per_second": 29185.852
    },
    {
      "epoch": 0.7345308675009453,
      "grad_norm": 1.453125,
      "learning_rate": 2.85091256636683e-05,
      "loss": 1.0929207801818848,
      "num_input_tokens_seen": 5903594944,
      "step": 20760,
      "train_runtime": 202275.0756,
      "train_tokens_per_second": 29185.973
    },
    {
      "epoch": 0.7348846877646742,
      "grad_norm": 1.4375,
      "learning_rate": 2.850449251952582e-05,
      "loss": 1.104050064086914,
      "num_input_tokens_seen": 5906506368,
      "step": 20770,
      "train_runtime": 202375.6254,
      "train_tokens_per_second": 29185.858
    },
    {
      "epoch": 0.735238508028403,
      "grad_norm": 1.5234375,
      "learning_rate": 2.849986163350766e-05,
      "loss": 1.086974811553955,
      "num_input_tokens_seen": 5909345856,
      "step": 20780,
      "train_runtime": 202473.9834,
      "train_tokens_per_second": 29185.705
    },
    {
      "epoch": 0.7355923282921317,
      "grad_norm": 1.5625,
      "learning_rate": 2.8495233003780103e-05,
      "loss": 1.0867299079895019,
      "num_input_tokens_seen": 5912204480,
      "step": 20790,
      "train_runtime": 202570.7248,
      "train_tokens_per_second": 29185.878
    },
    {
      "epoch": 0.7359461485558605,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8490606628511557e-05,
      "loss": 1.0714550971984864,
      "num_input_tokens_seen": 5915059072,
      "step": 20800,
      "train_runtime": 202669.4962,
      "train_tokens_per_second": 29185.739
    },
    {
      "epoch": 0.7362999688195893,
      "grad_norm": 1.5,
      "learning_rate": 2.8485982505872476e-05,
      "loss": 1.0838314056396485,
      "num_input_tokens_seen": 5917924608,
      "step": 20810,
      "train_runtime": 202768.8889,
      "train_tokens_per_second": 29185.565
    },
    {
      "epoch": 0.736653789083318,
      "grad_norm": 1.4375,
      "learning_rate": 2.8481360634035415e-05,
      "loss": 1.0970909118652343,
      "num_input_tokens_seen": 5920770944,
      "step": 20820,
      "train_runtime": 202865.3995,
      "train_tokens_per_second": 29185.711
    },
    {
      "epoch": 0.7370076093470468,
      "grad_norm": 1.453125,
      "learning_rate": 2.847674101117499e-05,
      "loss": 1.087839698791504,
      "num_input_tokens_seen": 5923643264,
      "step": 20830,
      "train_runtime": 202961.5031,
      "train_tokens_per_second": 29186.044
    },
    {
      "epoch": 0.7373614296107756,
      "grad_norm": 1.4375,
      "learning_rate": 2.8472123635467896e-05,
      "loss": 1.0966964721679688,
      "num_input_tokens_seen": 5926487104,
      "step": 20840,
      "train_runtime": 203058.9049,
      "train_tokens_per_second": 29186.049
    },
    {
      "epoch": 0.7377152498745044,
      "grad_norm": 1.4609375,
      "learning_rate": 2.846750850509289e-05,
      "loss": 1.094930362701416,
      "num_input_tokens_seen": 5929334592,
      "step": 20850,
      "train_runtime": 203153.8148,
      "train_tokens_per_second": 29186.43
    },
    {
      "epoch": 0.7380690701382332,
      "grad_norm": 1.46875,
      "learning_rate": 2.8462895618230813e-05,
      "loss": 1.092931079864502,
      "num_input_tokens_seen": 5932241536,
      "step": 20860,
      "train_runtime": 203253.7407,
      "train_tokens_per_second": 29186.383
    },
    {
      "epoch": 0.738422890401962,
      "grad_norm": 1.453125,
      "learning_rate": 2.845828497306453e-05,
      "loss": 1.082656478881836,
      "num_input_tokens_seen": 5935053632,
      "step": 20870,
      "train_runtime": 203350.7096,
      "train_tokens_per_second": 29186.294
    },
    {
      "epoch": 0.7387767106656907,
      "grad_norm": 1.515625,
      "learning_rate": 2.8453676567779018e-05,
      "loss": 1.0924680709838868,
      "num_input_tokens_seen": 5937934784,
      "step": 20880,
      "train_runtime": 203448.0758,
      "train_tokens_per_second": 29186.488
    },
    {
      "epoch": 0.7391305309294195,
      "grad_norm": 1.5078125,
      "learning_rate": 2.8449070400561267e-05,
      "loss": 1.0883349418640136,
      "num_input_tokens_seen": 5940800320,
      "step": 20890,
      "train_runtime": 203547.7452,
      "train_tokens_per_second": 29186.274
    },
    {
      "epoch": 0.7394843511931483,
      "grad_norm": 1.4453125,
      "learning_rate": 2.8444466469600343e-05,
      "loss": 1.089867115020752,
      "num_input_tokens_seen": 5943635072,
      "step": 20900,
      "train_runtime": 203644.7724,
      "train_tokens_per_second": 29186.288
    },
    {
      "epoch": 0.739838171456877,
      "grad_norm": 1.4921875,
      "learning_rate": 2.8439864773087354e-05,
      "loss": 1.0746932983398438,
      "num_input_tokens_seen": 5946503040,
      "step": 20910,
      "train_runtime": 203744.6279,
      "train_tokens_per_second": 29186.061
    },
    {
      "epoch": 0.7401919917206058,
      "grad_norm": 1.484375,
      "learning_rate": 2.8435265309215465e-05,
      "loss": 1.0746275901794433,
      "num_input_tokens_seen": 5949331712,
      "step": 20920,
      "train_runtime": 203841.3424,
      "train_tokens_per_second": 29186.09
    },
    {
      "epoch": 0.7405458119843346,
      "grad_norm": 1.390625,
      "learning_rate": 2.843066807617987e-05,
      "loss": 1.1065662384033204,
      "num_input_tokens_seen": 5952235008,
      "step": 20930,
      "train_runtime": 203941.7084,
      "train_tokens_per_second": 29185.962
    },
    {
      "epoch": 0.7408996322480634,
      "grad_norm": 1.4453125,
      "learning_rate": 2.8426073072177827e-05,
      "loss": 1.102370548248291,
      "num_input_tokens_seen": 5955103680,
      "step": 20940,
      "train_runtime": 204038.711,
      "train_tokens_per_second": 29186.146
    },
    {
      "epoch": 0.7412534525117922,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8421480295408616e-05,
      "loss": 1.0794326782226562,
      "num_input_tokens_seen": 5957967168,
      "step": 20950,
      "train_runtime": 204138.396,
      "train_tokens_per_second": 29185.921
    },
    {
      "epoch": 0.741607272775521,
      "grad_norm": 1.5390625,
      "learning_rate": 2.841688974407355e-05,
      "loss": 1.0891324996948242,
      "num_input_tokens_seen": 5960793536,
      "step": 20960,
      "train_runtime": 204235.9234,
      "train_tokens_per_second": 29185.823
    },
    {
      "epoch": 0.7419610930392497,
      "grad_norm": 1.4140625,
      "learning_rate": 2.8412301416375984e-05,
      "loss": 1.0865235328674316,
      "num_input_tokens_seen": 5963631616,
      "step": 20970,
      "train_runtime": 204332.9588,
      "train_tokens_per_second": 29185.853
    },
    {
      "epoch": 0.7423149133029785,
      "grad_norm": 1.4765625,
      "learning_rate": 2.840771531052131e-05,
      "loss": 1.0937984466552735,
      "num_input_tokens_seen": 5966481920,
      "step": 20980,
      "train_runtime": 204433.6912,
      "train_tokens_per_second": 29185.414
    },
    {
      "epoch": 0.7426687335667073,
      "grad_norm": 1.4375,
      "learning_rate": 2.840313142471694e-05,
      "loss": 1.0782765388488769,
      "num_input_tokens_seen": 5969371072,
      "step": 20990,
      "train_runtime": 204536.4966,
      "train_tokens_per_second": 29184.87
    },
    {
      "epoch": 0.743022553830436,
      "grad_norm": 1.4609375,
      "learning_rate": 2.83985497571723e-05,
      "loss": 1.095046615600586,
      "num_input_tokens_seen": 5972228032,
      "step": 21000,
      "train_runtime": 204632.5437,
      "train_tokens_per_second": 29185.133
    },
    {
      "epoch": 0.7433763740941648,
      "grad_norm": 1.40625,
      "learning_rate": 2.8393970306098843e-05,
      "loss": 1.0785394668579102,
      "num_input_tokens_seen": 5975085504,
      "step": 21010,
      "train_runtime": 204729.9215,
      "train_tokens_per_second": 29185.209
    },
    {
      "epoch": 0.7437301943578937,
      "grad_norm": 1.46875,
      "learning_rate": 2.8389393069710053e-05,
      "loss": 1.1014423370361328,
      "num_input_tokens_seen": 5977922240,
      "step": 21020,
      "train_runtime": 204828.4314,
      "train_tokens_per_second": 29185.022
    },
    {
      "epoch": 0.7440840146216224,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8384818046221418e-05,
      "loss": 1.0986970901489257,
      "num_input_tokens_seen": 5980802240,
      "step": 21030,
      "train_runtime": 204932.0416,
      "train_tokens_per_second": 29184.32
    },
    {
      "epoch": 0.7444378348853512,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8380245233850434e-05,
      "loss": 1.1003684997558594,
      "num_input_tokens_seen": 5983692864,
      "step": 21040,
      "train_runtime": 205031.3093,
      "train_tokens_per_second": 29184.288
    },
    {
      "epoch": 0.74479165514908,
      "grad_norm": 1.4609375,
      "learning_rate": 2.837567463081662e-05,
      "loss": 1.0922761917114259,
      "num_input_tokens_seen": 5986513920,
      "step": 21050,
      "train_runtime": 205128.0219,
      "train_tokens_per_second": 29184.281
    },
    {
      "epoch": 0.7451454754128087,
      "grad_norm": 1.421875,
      "learning_rate": 2.8371106235341477e-05,
      "loss": 1.0713348388671875,
      "num_input_tokens_seen": 5989338944,
      "step": 21060,
      "train_runtime": 205222.2288,
      "train_tokens_per_second": 29184.65
    },
    {
      "epoch": 0.7454992956765375,
      "grad_norm": 1.5546875,
      "learning_rate": 2.836654004564855e-05,
      "loss": 1.0853272438049317,
      "num_input_tokens_seen": 5992180160,
      "step": 21070,
      "train_runtime": 205319.2402,
      "train_tokens_per_second": 29184.699
    },
    {
      "epoch": 0.7458531159402663,
      "grad_norm": 1.4921875,
      "learning_rate": 2.8361976059963348e-05,
      "loss": 1.090385913848877,
      "num_input_tokens_seen": 5995003712,
      "step": 21080,
      "train_runtime": 205413.8481,
      "train_tokens_per_second": 29185.003
    },
    {
      "epoch": 0.746206936203995,
      "grad_norm": 1.4375,
      "learning_rate": 2.835741427651339e-05,
      "loss": 1.093421745300293,
      "num_input_tokens_seen": 5997859648,
      "step": 21090,
      "train_runtime": 205514.2558,
      "train_tokens_per_second": 29184.64
    },
    {
      "epoch": 0.7465607564677239,
      "grad_norm": 1.390625,
      "learning_rate": 2.8352854693528197e-05,
      "loss": 1.0894065856933595,
      "num_input_tokens_seen": 6000715712,
      "step": 21100,
      "train_runtime": 205612.4937,
      "train_tokens_per_second": 29184.587
    },
    {
      "epoch": 0.7469145767314527,
      "grad_norm": 1.4296875,
      "learning_rate": 2.8348297309239274e-05,
      "loss": 1.0839420318603517,
      "num_input_tokens_seen": 6003573504,
      "step": 21110,
      "train_runtime": 205708.5214,
      "train_tokens_per_second": 29184.856
    },
    {
      "epoch": 0.7472683969951814,
      "grad_norm": 1.46875,
      "learning_rate": 2.834374212188012e-05,
      "loss": 1.081197166442871,
      "num_input_tokens_seen": 6006483328,
      "step": 21120,
      "train_runtime": 205808.8246,
      "train_tokens_per_second": 29184.771
    },
    {
      "epoch": 0.7476222172589102,
      "grad_norm": 1.421875,
      "learning_rate": 2.833918912968621e-05,
      "loss": 1.0791766166687011,
      "num_input_tokens_seen": 6009366272,
      "step": 21130,
      "train_runtime": 205908.9856,
      "train_tokens_per_second": 29184.575
    },
    {
      "epoch": 0.747976037522639,
      "grad_norm": 1.5078125,
      "learning_rate": 2.833463833089502e-05,
      "loss": 1.0813014030456543,
      "num_input_tokens_seen": 6012217152,
      "step": 21140,
      "train_runtime": 206007.2449,
      "train_tokens_per_second": 29184.494
    },
    {
      "epoch": 0.7483298577863677,
      "grad_norm": 1.5078125,
      "learning_rate": 2.8330089723745985e-05,
      "loss": 1.0820041656494142,
      "num_input_tokens_seen": 6015078784,
      "step": 21150,
      "train_runtime": 206107.3156,
      "train_tokens_per_second": 29184.208
    },
    {
      "epoch": 0.7486836780500965,
      "grad_norm": 1.421875,
      "learning_rate": 2.8325543306480538e-05,
      "loss": 1.0813280105590821,
      "num_input_tokens_seen": 6017903040,
      "step": 21160,
      "train_runtime": 206204.9631,
      "train_tokens_per_second": 29184.084
    },
    {
      "epoch": 0.7490374983138253,
      "grad_norm": 1.4140625,
      "learning_rate": 2.832099907734208e-05,
      "loss": 1.0904282569885253,
      "num_input_tokens_seen": 6020737728,
      "step": 21170,
      "train_runtime": 206299.6566,
      "train_tokens_per_second": 29184.429
    },
    {
      "epoch": 0.749391318577554,
      "grad_norm": 1.46875,
      "learning_rate": 2.831645703457598e-05,
      "loss": 1.0923046112060546,
      "num_input_tokens_seen": 6023592192,
      "step": 21180,
      "train_runtime": 206398.8206,
      "train_tokens_per_second": 29184.237
    },
    {
      "epoch": 0.7497451388412829,
      "grad_norm": 1.390625,
      "learning_rate": 2.8311917176429582e-05,
      "loss": 1.0897808074951172,
      "num_input_tokens_seen": 6026465792,
      "step": 21190,
      "train_runtime": 206496.9128,
      "train_tokens_per_second": 29184.29
    },
    {
      "epoch": 0.7500989591050117,
      "grad_norm": 1.4765625,
      "learning_rate": 2.830737950115218e-05,
      "loss": 1.0916244506835937,
      "num_input_tokens_seen": 6029296384,
      "step": 21200,
      "train_runtime": 206590.9171,
      "train_tokens_per_second": 29184.712
    },
    {
      "epoch": 0.7504527793687404,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8302844006995062e-05,
      "loss": 1.0757956504821777,
      "num_input_tokens_seen": 6032204928,
      "step": 21210,
      "train_runtime": 206692.8857,
      "train_tokens_per_second": 29184.386
    },
    {
      "epoch": 0.7508065996324692,
      "grad_norm": 1.46875,
      "learning_rate": 2.829831069221145e-05,
      "loss": 1.0937291145324708,
      "num_input_tokens_seen": 6035024960,
      "step": 21220,
      "train_runtime": 206786.3884,
      "train_tokens_per_second": 29184.827
    },
    {
      "epoch": 0.751160419896198,
      "grad_norm": 1.515625,
      "learning_rate": 2.8293779555056532e-05,
      "loss": 1.0911020278930663,
      "num_input_tokens_seen": 6037872512,
      "step": 21230,
      "train_runtime": 206887.2391,
      "train_tokens_per_second": 29184.364
    },
    {
      "epoch": 0.7515142401599267,
      "grad_norm": 1.5,
      "learning_rate": 2.8289250593787454e-05,
      "loss": 1.090523910522461,
      "num_input_tokens_seen": 6040666880,
      "step": 21240,
      "train_runtime": 206979.7239,
      "train_tokens_per_second": 29184.824
    },
    {
      "epoch": 0.7518680604236555,
      "grad_norm": 1.453125,
      "learning_rate": 2.8284723806663316e-05,
      "loss": 1.0765873908996582,
      "num_input_tokens_seen": 6043495232,
      "step": 21250,
      "train_runtime": 207077.159,
      "train_tokens_per_second": 29184.751
    },
    {
      "epoch": 0.7522218806873843,
      "grad_norm": 1.5078125,
      "learning_rate": 2.828019919194515e-05,
      "loss": 1.08115234375,
      "num_input_tokens_seen": 6046314368,
      "step": 21260,
      "train_runtime": 207175.0045,
      "train_tokens_per_second": 29184.575
    },
    {
      "epoch": 0.7525757009511131,
      "grad_norm": 1.4140625,
      "learning_rate": 2.827567674789597e-05,
      "loss": 1.0994600296020507,
      "num_input_tokens_seen": 6049228096,
      "step": 21270,
      "train_runtime": 207273.7765,
      "train_tokens_per_second": 29184.725
    },
    {
      "epoch": 0.7529295212148419,
      "grad_norm": 1.5,
      "learning_rate": 2.8271156472780697e-05,
      "loss": 1.0828849792480468,
      "num_input_tokens_seen": 6052079168,
      "step": 21280,
      "train_runtime": 207374.6388,
      "train_tokens_per_second": 29184.278
    },
    {
      "epoch": 0.7532833414785707,
      "grad_norm": 1.46875,
      "learning_rate": 2.826663836486621e-05,
      "loss": 1.0879409790039063,
      "num_input_tokens_seen": 6054953216,
      "step": 21290,
      "train_runtime": 207473.6822,
      "train_tokens_per_second": 29184.199
    },
    {
      "epoch": 0.7536371617422994,
      "grad_norm": 1.4609375,
      "learning_rate": 2.8262122422421326e-05,
      "loss": 1.093393898010254,
      "num_input_tokens_seen": 6057801984,
      "step": 21300,
      "train_runtime": 207569.5803,
      "train_tokens_per_second": 29184.44
    },
    {
      "epoch": 0.7539909820060282,
      "grad_norm": 1.3828125,
      "learning_rate": 2.8257608643716797e-05,
      "loss": 1.06944580078125,
      "num_input_tokens_seen": 6060640320,
      "step": 21310,
      "train_runtime": 207667.5081,
      "train_tokens_per_second": 29184.346
    },
    {
      "epoch": 0.754344802269757,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8253097027025312e-05,
      "loss": 1.0926382064819335,
      "num_input_tokens_seen": 6063462656,
      "step": 21320,
      "train_runtime": 207762.4624,
      "train_tokens_per_second": 29184.592
    },
    {
      "epoch": 0.7546986225334857,
      "grad_norm": 1.4921875,
      "learning_rate": 2.8248587570621472e-05,
      "loss": 1.0897224426269532,
      "num_input_tokens_seen": 6066305152,
      "step": 21330,
      "train_runtime": 207859.2088,
      "train_tokens_per_second": 29184.683
    },
    {
      "epoch": 0.7550524427972145,
      "grad_norm": 1.546875,
      "learning_rate": 2.824408027278182e-05,
      "loss": 1.0880735397338868,
      "num_input_tokens_seen": 6069158208,
      "step": 21340,
      "train_runtime": 207955.7887,
      "train_tokens_per_second": 29184.849
    },
    {
      "epoch": 0.7554062630609434,
      "grad_norm": 1.5234375,
      "learning_rate": 2.823957513178483e-05,
      "loss": 1.0897762298583984,
      "num_input_tokens_seen": 6071980864,
      "step": 21350,
      "train_runtime": 208049.9718,
      "train_tokens_per_second": 29185.204
    },
    {
      "epoch": 0.7557600833246721,
      "grad_norm": 1.40625,
      "learning_rate": 2.8235072145910878e-05,
      "loss": 1.0912284851074219,
      "num_input_tokens_seen": 6074852992,
      "step": 21360,
      "train_runtime": 208150.3177,
      "train_tokens_per_second": 29184.933
    },
    {
      "epoch": 0.7561139035884009,
      "grad_norm": 1.5234375,
      "learning_rate": 2.8230571313442273e-05,
      "loss": 1.0704248428344727,
      "num_input_tokens_seen": 6077675520,
      "step": 21370,
      "train_runtime": 208246.0597,
      "train_tokens_per_second": 29185.069
    },
    {
      "epoch": 0.7564677238521297,
      "grad_norm": 1.46875,
      "learning_rate": 2.822607263266324e-05,
      "loss": 1.083498191833496,
      "num_input_tokens_seen": 6080512448,
      "step": 21380,
      "train_runtime": 208340.9109,
      "train_tokens_per_second": 29185.398
    },
    {
      "epoch": 0.7568215441158584,
      "grad_norm": 1.4296875,
      "learning_rate": 2.822157610185991e-05,
      "loss": 1.0689991950988769,
      "num_input_tokens_seen": 6083380992,
      "step": 21390,
      "train_runtime": 208436.9376,
      "train_tokens_per_second": 29185.715
    },
    {
      "epoch": 0.7571753643795872,
      "grad_norm": 1.484375,
      "learning_rate": 2.821708171932032e-05,
      "loss": 1.090031623840332,
      "num_input_tokens_seen": 6086255040,
      "step": 21400,
      "train_runtime": 208536.4264,
      "train_tokens_per_second": 29185.573
    },
    {
      "epoch": 0.757529184643316,
      "grad_norm": 1.421875,
      "learning_rate": 2.821258948333444e-05,
      "loss": 1.0873319625854492,
      "num_input_tokens_seen": 6089119296,
      "step": 21410,
      "train_runtime": 208635.2545,
      "train_tokens_per_second": 29185.476
    },
    {
      "epoch": 0.7578830049070447,
      "grad_norm": 1.4375,
      "learning_rate": 2.8208099392194116e-05,
      "loss": 1.0775225639343262,
      "num_input_tokens_seen": 6091926080,
      "step": 21420,
      "train_runtime": 208730.6425,
      "train_tokens_per_second": 29185.586
    },
    {
      "epoch": 0.7582368251707735,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8203611444193113e-05,
      "loss": 1.0895069122314454,
      "num_input_tokens_seen": 6094779584,
      "step": 21430,
      "train_runtime": 208826.5034,
      "train_tokens_per_second": 29185.853
    },
    {
      "epoch": 0.7585906454345024,
      "grad_norm": 1.4296875,
      "learning_rate": 2.8199125637627084e-05,
      "loss": 1.0830517768859864,
      "num_input_tokens_seen": 6097571456,
      "step": 21440,
      "train_runtime": 208920.5238,
      "train_tokens_per_second": 29186.082
    },
    {
      "epoch": 0.7589444656982312,
      "grad_norm": 1.546875,
      "learning_rate": 2.8194641970793593e-05,
      "loss": 1.0836994171142578,
      "num_input_tokens_seen": 6100396672,
      "step": 21450,
      "train_runtime": 209015.4517,
      "train_tokens_per_second": 29186.343
    },
    {
      "epoch": 0.7592982859619599,
      "grad_norm": 1.5390625,
      "learning_rate": 2.8190160441992092e-05,
      "loss": 1.106247329711914,
      "num_input_tokens_seen": 6103225152,
      "step": 21460,
      "train_runtime": 209113.6944,
      "train_tokens_per_second": 29186.157
    },
    {
      "epoch": 0.7596521062256887,
      "grad_norm": 1.46875,
      "learning_rate": 2.818568104952392e-05,
      "loss": 1.0901400566101074,
      "num_input_tokens_seen": 6106011520,
      "step": 21470,
      "train_runtime": 209205.4401,
      "train_tokens_per_second": 29186.677
    },
    {
      "epoch": 0.7600059264894174,
      "grad_norm": 1.5390625,
      "learning_rate": 2.8181203791692306e-05,
      "loss": 1.080908966064453,
      "num_input_tokens_seen": 6108848960,
      "step": 21480,
      "train_runtime": 209300.4021,
      "train_tokens_per_second": 29186.991
    },
    {
      "epoch": 0.7603597467531462,
      "grad_norm": 1.53125,
      "learning_rate": 2.8176728666802375e-05,
      "loss": 1.082099723815918,
      "num_input_tokens_seen": 6111702336,
      "step": 21490,
      "train_runtime": 209399.0236,
      "train_tokens_per_second": 29186.871
    },
    {
      "epoch": 0.760713567016875,
      "grad_norm": 1.4375,
      "learning_rate": 2.8172255673161124e-05,
      "loss": 1.083989429473877,
      "num_input_tokens_seen": 6114556160,
      "step": 21500,
      "train_runtime": 209496.3187,
      "train_tokens_per_second": 29186.938
    },
    {
      "epoch": 0.7610673872806037,
      "grad_norm": 1.5078125,
      "learning_rate": 2.8167784809077436e-05,
      "loss": 1.0908090591430664,
      "num_input_tokens_seen": 6117416192,
      "step": 21510,
      "train_runtime": 209592.5871,
      "train_tokens_per_second": 29187.178
    },
    {
      "epoch": 0.7614212075443326,
      "grad_norm": 1.390625,
      "learning_rate": 2.816331607286207e-05,
      "loss": 1.0711624145507812,
      "num_input_tokens_seen": 6120260224,
      "step": 21520,
      "train_runtime": 209690.4009,
      "train_tokens_per_second": 29187.126
    },
    {
      "epoch": 0.7617750278080614,
      "grad_norm": 1.4765625,
      "learning_rate": 2.815884946282766e-05,
      "loss": 1.091764545440674,
      "num_input_tokens_seen": 6123067136,
      "step": 21530,
      "train_runtime": 209786.4549,
      "train_tokens_per_second": 29187.142
    },
    {
      "epoch": 0.7621288480717902,
      "grad_norm": 1.484375,
      "learning_rate": 2.815438497728871e-05,
      "loss": 1.085133171081543,
      "num_input_tokens_seen": 6125931520,
      "step": 21540,
      "train_runtime": 209887.4066,
      "train_tokens_per_second": 29186.751
    },
    {
      "epoch": 0.7624826683355189,
      "grad_norm": 1.5078125,
      "learning_rate": 2.8149922614561607e-05,
      "loss": 1.0899795532226562,
      "num_input_tokens_seen": 6128745536,
      "step": 21550,
      "train_runtime": 209985.8777,
      "train_tokens_per_second": 29186.465
    },
    {
      "epoch": 0.7628364885992477,
      "grad_norm": 1.4921875,
      "learning_rate": 2.8145462372964588e-05,
      "loss": 1.0814544677734375,
      "num_input_tokens_seen": 6131573312,
      "step": 21560,
      "train_runtime": 210083.2531,
      "train_tokens_per_second": 29186.397
    },
    {
      "epoch": 0.7631903088629765,
      "grad_norm": 1.5078125,
      "learning_rate": 2.814100425081777e-05,
      "loss": 1.0850869178771974,
      "num_input_tokens_seen": 6134375040,
      "step": 21570,
      "train_runtime": 210178.8549,
      "train_tokens_per_second": 29186.452
    },
    {
      "epoch": 0.7635441291267052,
      "grad_norm": 1.421875,
      "learning_rate": 2.8136548246443117e-05,
      "loss": 1.0924762725830077,
      "num_input_tokens_seen": 6137264960,
      "step": 21580,
      "train_runtime": 210280.1616,
      "train_tokens_per_second": 29186.134
    },
    {
      "epoch": 0.763897949390434,
      "grad_norm": 1.4453125,
      "learning_rate": 2.8132094358164468e-05,
      "loss": 1.0981695175170898,
      "num_input_tokens_seen": 6140138816,
      "step": 21590,
      "train_runtime": 210377.8484,
      "train_tokens_per_second": 29186.242
    },
    {
      "epoch": 0.7642517696541629,
      "grad_norm": 1.453125,
      "learning_rate": 2.8127642584307508e-05,
      "loss": 1.0990865707397461,
      "num_input_tokens_seen": 6142984064,
      "step": 21600,
      "train_runtime": 210476.3098,
      "train_tokens_per_second": 29186.107
    },
    {
      "epoch": 0.7646055899178916,
      "grad_norm": 1.5,
      "learning_rate": 2.8123192923199776e-05,
      "loss": 1.0925244331359862,
      "num_input_tokens_seen": 6145847488,
      "step": 21610,
      "train_runtime": 210573.3467,
      "train_tokens_per_second": 29186.255
    },
    {
      "epoch": 0.7649594101816204,
      "grad_norm": 1.5234375,
      "learning_rate": 2.8118745373170667e-05,
      "loss": 1.0959525108337402,
      "num_input_tokens_seen": 6148713792,
      "step": 21620,
      "train_runtime": 210672.2077,
      "train_tokens_per_second": 29186.165
    },
    {
      "epoch": 0.7653132304453492,
      "grad_norm": 1.46875,
      "learning_rate": 2.8114299932551423e-05,
      "loss": 1.0885591506958008,
      "num_input_tokens_seen": 6151501696,
      "step": 21630,
      "train_runtime": 210765.0913,
      "train_tokens_per_second": 29186.53
    },
    {
      "epoch": 0.7656670507090779,
      "grad_norm": 1.5078125,
      "learning_rate": 2.8109856599675145e-05,
      "loss": 1.0907438278198243,
      "num_input_tokens_seen": 6154360064,
      "step": 21640,
      "train_runtime": 210864.698,
      "train_tokens_per_second": 29186.299
    },
    {
      "epoch": 0.7660208709728067,
      "grad_norm": 1.5234375,
      "learning_rate": 2.8105415372876742e-05,
      "loss": 1.0830144882202148,
      "num_input_tokens_seen": 6157238080,
      "step": 21650,
      "train_runtime": 210964.4834,
      "train_tokens_per_second": 29186.136
    },
    {
      "epoch": 0.7663746912365355,
      "grad_norm": 1.5625,
      "learning_rate": 2.8100976250493e-05,
      "loss": 1.0706307411193847,
      "num_input_tokens_seen": 6160097728,
      "step": 21660,
      "train_runtime": 211065.0002,
      "train_tokens_per_second": 29185.785
    },
    {
      "epoch": 0.7667285115002642,
      "grad_norm": 1.4140625,
      "learning_rate": 2.8096539230862527e-05,
      "loss": 1.1098913192749023,
      "num_input_tokens_seen": 6162970048,
      "step": 21670,
      "train_runtime": 211164.9839,
      "train_tokens_per_second": 29185.568
    },
    {
      "epoch": 0.767082331763993,
      "grad_norm": 1.453125,
      "learning_rate": 2.809210431232578e-05,
      "loss": 1.0804973602294923,
      "num_input_tokens_seen": 6165827072,
      "step": 21680,
      "train_runtime": 211263.4865,
      "train_tokens_per_second": 29185.484
    },
    {
      "epoch": 0.7674361520277219,
      "grad_norm": 1.515625,
      "learning_rate": 2.8087671493225025e-05,
      "loss": 1.0761798858642577,
      "num_input_tokens_seen": 6168667520,
      "step": 21690,
      "train_runtime": 211359.9955,
      "train_tokens_per_second": 29185.596
    },
    {
      "epoch": 0.7677899722914506,
      "grad_norm": 1.4296875,
      "learning_rate": 2.808324077190438e-05,
      "loss": 1.088958168029785,
      "num_input_tokens_seen": 6171544384,
      "step": 21700,
      "train_runtime": 211460.2329,
      "train_tokens_per_second": 29185.366
    },
    {
      "epoch": 0.7681437925551794,
      "grad_norm": 1.4921875,
      "learning_rate": 2.807881214670978e-05,
      "loss": 1.0673308372497559,
      "num_input_tokens_seen": 6174348288,
      "step": 21710,
      "train_runtime": 211554.6896,
      "train_tokens_per_second": 29185.589
    },
    {
      "epoch": 0.7684976128189082,
      "grad_norm": 1.453125,
      "learning_rate": 2.8074385615988996e-05,
      "loss": 1.089615249633789,
      "num_input_tokens_seen": 6177181760,
      "step": 21720,
      "train_runtime": 211651.3135,
      "train_tokens_per_second": 29185.653
    },
    {
      "epoch": 0.7688514330826369,
      "grad_norm": 1.515625,
      "learning_rate": 2.8069961178091602e-05,
      "loss": 1.0905158996582032,
      "num_input_tokens_seen": 6180022592,
      "step": 21730,
      "train_runtime": 211748.0846,
      "train_tokens_per_second": 29185.731
    },
    {
      "epoch": 0.7692052533463657,
      "grad_norm": 1.5078125,
      "learning_rate": 2.806553883136901e-05,
      "loss": 1.0859285354614259,
      "num_input_tokens_seen": 6182888576,
      "step": 21740,
      "train_runtime": 211847.3082,
      "train_tokens_per_second": 29185.59
    },
    {
      "epoch": 0.7695590736100945,
      "grad_norm": 1.453125,
      "learning_rate": 2.806111857417445e-05,
      "loss": 1.0836685180664063,
      "num_input_tokens_seen": 6185731200,
      "step": 21750,
      "train_runtime": 211944.7372,
      "train_tokens_per_second": 29185.585
    },
    {
      "epoch": 0.7699128938738232,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8056700404862957e-05,
      "loss": 1.0907863616943358,
      "num_input_tokens_seen": 6188538752,
      "step": 21760,
      "train_runtime": 212039.7668,
      "train_tokens_per_second": 29185.746
    },
    {
      "epoch": 0.7702667141375521,
      "grad_norm": 1.484375,
      "learning_rate": 2.8052284321791383e-05,
      "loss": 1.0798266410827637,
      "num_input_tokens_seen": 6191344448,
      "step": 21770,
      "train_runtime": 212134.0477,
      "train_tokens_per_second": 29186.001
    },
    {
      "epoch": 0.7706205344012809,
      "grad_norm": 1.484375,
      "learning_rate": 2.8047870323318382e-05,
      "loss": 1.0769691467285156,
      "num_input_tokens_seen": 6194210752,
      "step": 21780,
      "train_runtime": 212233.3352,
      "train_tokens_per_second": 29185.852
    },
    {
      "epoch": 0.7709743546650096,
      "grad_norm": 1.46875,
      "learning_rate": 2.8043458407804428e-05,
      "loss": 1.0874345779418946,
      "num_input_tokens_seen": 6197046656,
      "step": 21790,
      "train_runtime": 212330.7806,
      "train_tokens_per_second": 29185.814
    },
    {
      "epoch": 0.7713281749287384,
      "grad_norm": 1.5390625,
      "learning_rate": 2.8039048573611805e-05,
      "loss": 1.0784727096557618,
      "num_input_tokens_seen": 6199852800,
      "step": 21800,
      "train_runtime": 212426.4179,
      "train_tokens_per_second": 29185.884
    },
    {
      "epoch": 0.7716819951924672,
      "grad_norm": 1.4765625,
      "learning_rate": 2.8034640819104574e-05,
      "loss": 1.0917928695678711,
      "num_input_tokens_seen": 6202663808,
      "step": 21810,
      "train_runtime": 212521.0331,
      "train_tokens_per_second": 29186.117
    },
    {
      "epoch": 0.7720358154561959,
      "grad_norm": 1.5546875,
      "learning_rate": 2.803023514264861e-05,
      "loss": 1.0851006507873535,
      "num_input_tokens_seen": 6205479296,
      "step": 21820,
      "train_runtime": 212619.0134,
      "train_tokens_per_second": 29185.91
    },
    {
      "epoch": 0.7723896357199247,
      "grad_norm": 1.515625,
      "learning_rate": 2.8025831542611596e-05,
      "loss": 1.0765792846679687,
      "num_input_tokens_seen": 6208357056,
      "step": 21830,
      "train_runtime": 212717.6969,
      "train_tokens_per_second": 29185.898
    },
    {
      "epoch": 0.7727434559836535,
      "grad_norm": 1.5234375,
      "learning_rate": 2.8021430017362994e-05,
      "loss": 1.0935245513916017,
      "num_input_tokens_seen": 6211215936,
      "step": 21840,
      "train_runtime": 212814.3643,
      "train_tokens_per_second": 29186.075
    },
    {
      "epoch": 0.7730972762473823,
      "grad_norm": 1.5390625,
      "learning_rate": 2.801703056527406e-05,
      "loss": 1.092359733581543,
      "num_input_tokens_seen": 6214038720,
      "step": 21850,
      "train_runtime": 212909.657,
      "train_tokens_per_second": 29186.27
    },
    {
      "epoch": 0.7734510965111111,
      "grad_norm": 1.5625,
      "learning_rate": 2.801263318471784e-05,
      "loss": 1.0896340370178224,
      "num_input_tokens_seen": 6216856064,
      "step": 21860,
      "train_runtime": 213002.9695,
      "train_tokens_per_second": 29186.711
    },
    {
      "epoch": 0.7738049167748399,
      "grad_norm": 1.5234375,
      "learning_rate": 2.800823787406917e-05,
      "loss": 1.0854398727416992,
      "num_input_tokens_seen": 6219774528,
      "step": 21870,
      "train_runtime": 213105.0584,
      "train_tokens_per_second": 29186.424
    },
    {
      "epoch": 0.7741587370385686,
      "grad_norm": 1.5234375,
      "learning_rate": 2.8003844631704678e-05,
      "loss": 1.0930980682373046,
      "num_input_tokens_seen": 6222680512,
      "step": 21880,
      "train_runtime": 213206.1058,
      "train_tokens_per_second": 29186.221
    },
    {
      "epoch": 0.7745125573022974,
      "grad_norm": 1.5,
      "learning_rate": 2.7999453456002755e-05,
      "loss": 1.1009612083435059,
      "num_input_tokens_seen": 6225528896,
      "step": 21890,
      "train_runtime": 213304.4556,
      "train_tokens_per_second": 29186.117
    },
    {
      "epoch": 0.7748663775660262,
      "grad_norm": 1.4140625,
      "learning_rate": 2.799506434534359e-05,
      "loss": 1.0871479034423828,
      "num_input_tokens_seen": 6228382528,
      "step": 21900,
      "train_runtime": 213403.6381,
      "train_tokens_per_second": 29185.925
    },
    {
      "epoch": 0.7752201978297549,
      "grad_norm": 1.5,
      "learning_rate": 2.7990677298109136e-05,
      "loss": 1.088340950012207,
      "num_input_tokens_seen": 6231212864,
      "step": 21910,
      "train_runtime": 213500.2966,
      "train_tokens_per_second": 29185.968
    },
    {
      "epoch": 0.7755740180934837,
      "grad_norm": 1.5546875,
      "learning_rate": 2.7986292312683125e-05,
      "loss": 1.0889883041381836,
      "num_input_tokens_seen": 6233996096,
      "step": 21920,
      "train_runtime": 213592.3052,
      "train_tokens_per_second": 29186.426
    },
    {
      "epoch": 0.7759278383572125,
      "grad_norm": 1.453125,
      "learning_rate": 2.798190938745106e-05,
      "loss": 1.0929086685180665,
      "num_input_tokens_seen": 6236845568,
      "step": 21930,
      "train_runtime": 213687.8018,
      "train_tokens_per_second": 29186.718
    },
    {
      "epoch": 0.7762816586209413,
      "grad_norm": 1.453125,
      "learning_rate": 2.7977528520800218e-05,
      "loss": 1.0870466232299805,
      "num_input_tokens_seen": 6239686912,
      "step": 21940,
      "train_runtime": 213782.4399,
      "train_tokens_per_second": 29187.088
    },
    {
      "epoch": 0.7766354788846701,
      "grad_norm": 1.4375,
      "learning_rate": 2.7973149711119635e-05,
      "loss": 1.0926259994506835,
      "num_input_tokens_seen": 6242501824,
      "step": 21950,
      "train_runtime": 213877.7648,
      "train_tokens_per_second": 29187.241
    },
    {
      "epoch": 0.7769892991483989,
      "grad_norm": 1.515625,
      "learning_rate": 2.7968772956800115e-05,
      "loss": 1.0902044296264648,
      "num_input_tokens_seen": 6245323904,
      "step": 21960,
      "train_runtime": 213973.7852,
      "train_tokens_per_second": 29187.332
    },
    {
      "epoch": 0.7773431194121276,
      "grad_norm": 1.53125,
      "learning_rate": 2.796439825623423e-05,
      "loss": 1.0715646743774414,
      "num_input_tokens_seen": 6248202496,
      "step": 21970,
      "train_runtime": 214076.1497,
      "train_tokens_per_second": 29186.822
    },
    {
      "epoch": 0.7776969396758564,
      "grad_norm": 1.421875,
      "learning_rate": 2.79600256078163e-05,
      "loss": 1.0818517684936524,
      "num_input_tokens_seen": 6251015872,
      "step": 21980,
      "train_runtime": 214173.7298,
      "train_tokens_per_second": 29186.66
    },
    {
      "epoch": 0.7780507599395852,
      "grad_norm": 1.4453125,
      "learning_rate": 2.7955655009942416e-05,
      "loss": 1.0870773315429687,
      "num_input_tokens_seen": 6253897536,
      "step": 21990,
      "train_runtime": 214273.0143,
      "train_tokens_per_second": 29186.585
    },
    {
      "epoch": 0.7784045802033139,
      "grad_norm": 1.5,
      "learning_rate": 2.79512864610104e-05,
      "loss": 1.0889597892761231,
      "num_input_tokens_seen": 6256718016,
      "step": 22000,
      "train_runtime": 214369.8021,
      "train_tokens_per_second": 29186.564
    },
    {
      "epoch": 0.7787584004670427,
      "grad_norm": 1.4765625,
      "learning_rate": 2.794691995941986e-05,
      "loss": 1.0722615242004394,
      "num_input_tokens_seen": 6259563648,
      "step": 22010,
      "train_runtime": 214467.1256,
      "train_tokens_per_second": 29186.588
    },
    {
      "epoch": 0.7791122207307716,
      "grad_norm": 1.5234375,
      "learning_rate": 2.7942555503572115e-05,
      "loss": 1.089272403717041,
      "num_input_tokens_seen": 6262393408,
      "step": 22020,
      "train_runtime": 214564.61,
      "train_tokens_per_second": 29186.516
    },
    {
      "epoch": 0.7794660409945003,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7938193091870268e-05,
      "loss": 1.0903002738952636,
      "num_input_tokens_seen": 6265231040,
      "step": 22030,
      "train_runtime": 214661.4457,
      "train_tokens_per_second": 29186.569
    },
    {
      "epoch": 0.7798198612582291,
      "grad_norm": 1.5078125,
      "learning_rate": 2.793383272271914e-05,
      "loss": 1.0818592071533204,
      "num_input_tokens_seen": 6268078272,
      "step": 22040,
      "train_runtime": 214758.0991,
      "train_tokens_per_second": 29186.691
    },
    {
      "epoch": 0.7801736815219579,
      "grad_norm": 1.4921875,
      "learning_rate": 2.7929474394525307e-05,
      "loss": 1.088098907470703,
      "num_input_tokens_seen": 6270969152,
      "step": 22050,
      "train_runtime": 214858.8045,
      "train_tokens_per_second": 29186.466
    },
    {
      "epoch": 0.7805275017856866,
      "grad_norm": 1.46875,
      "learning_rate": 2.7925118105697078e-05,
      "loss": 1.0991410255432128,
      "num_input_tokens_seen": 6273804032,
      "step": 22060,
      "train_runtime": 214955.2365,
      "train_tokens_per_second": 29186.561
    },
    {
      "epoch": 0.7808813220494154,
      "grad_norm": 1.5078125,
      "learning_rate": 2.792076385464451e-05,
      "loss": 1.094899559020996,
      "num_input_tokens_seen": 6276699200,
      "step": 22070,
      "train_runtime": 215055.5087,
      "train_tokens_per_second": 29186.414
    },
    {
      "epoch": 0.7812351423131442,
      "grad_norm": 1.46875,
      "learning_rate": 2.7916411639779383e-05,
      "loss": 1.0877613067626952,
      "num_input_tokens_seen": 6279558528,
      "step": 22080,
      "train_runtime": 215156.2774,
      "train_tokens_per_second": 29186.034
    },
    {
      "epoch": 0.7815889625768729,
      "grad_norm": 1.4296875,
      "learning_rate": 2.7912061459515215e-05,
      "loss": 1.0898740768432618,
      "num_input_tokens_seen": 6282408320,
      "step": 22090,
      "train_runtime": 215256.6063,
      "train_tokens_per_second": 29185.67
    },
    {
      "epoch": 0.7819427828406018,
      "grad_norm": 1.5,
      "learning_rate": 2.7907713312267247e-05,
      "loss": 1.0837122917175293,
      "num_input_tokens_seen": 6285253888,
      "step": 22100,
      "train_runtime": 215353.7608,
      "train_tokens_per_second": 29185.717
    },
    {
      "epoch": 0.7822966031043306,
      "grad_norm": 1.4765625,
      "learning_rate": 2.7903367196452457e-05,
      "loss": 1.1006884574890137,
      "num_input_tokens_seen": 6288175424,
      "step": 22110,
      "train_runtime": 215453.8621,
      "train_tokens_per_second": 29185.717
    },
    {
      "epoch": 0.7826504233680593,
      "grad_norm": 1.46875,
      "learning_rate": 2.7899023110489554e-05,
      "loss": 1.0890989303588867,
      "num_input_tokens_seen": 6291064832,
      "step": 22120,
      "train_runtime": 215552.3823,
      "train_tokens_per_second": 29185.782
    },
    {
      "epoch": 0.7830042436317881,
      "grad_norm": 1.421875,
      "learning_rate": 2.789468105279895e-05,
      "loss": 1.0702329635620118,
      "num_input_tokens_seen": 6293907776,
      "step": 22130,
      "train_runtime": 215649.1166,
      "train_tokens_per_second": 29185.873
    },
    {
      "epoch": 0.7833580638955169,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7890341021802786e-05,
      "loss": 1.089697265625,
      "num_input_tokens_seen": 6296731904,
      "step": 22140,
      "train_runtime": 215745.7221,
      "train_tokens_per_second": 29185.895
    },
    {
      "epoch": 0.7837118841592456,
      "grad_norm": 1.484375,
      "learning_rate": 2.7886003015924933e-05,
      "loss": 1.0803797721862793,
      "num_input_tokens_seen": 6299597952,
      "step": 22150,
      "train_runtime": 215843.66,
      "train_tokens_per_second": 29185.93
    },
    {
      "epoch": 0.7840657044229744,
      "grad_norm": 1.4453125,
      "learning_rate": 2.788166703359096e-05,
      "loss": 1.0752176284790038,
      "num_input_tokens_seen": 6302420160,
      "step": 22160,
      "train_runtime": 215937.9367,
      "train_tokens_per_second": 29186.257
    },
    {
      "epoch": 0.7844195246867032,
      "grad_norm": 1.3984375,
      "learning_rate": 2.787733307322816e-05,
      "loss": 1.1016907691955566,
      "num_input_tokens_seen": 6305252352,
      "step": 22170,
      "train_runtime": 216033.4285,
      "train_tokens_per_second": 29186.466
    },
    {
      "epoch": 0.7847733449504319,
      "grad_norm": 1.46875,
      "learning_rate": 2.7873001133265518e-05,
      "loss": 1.0844686508178711,
      "num_input_tokens_seen": 6308094464,
      "step": 22180,
      "train_runtime": 216130.7985,
      "train_tokens_per_second": 29186.467
    },
    {
      "epoch": 0.7851271652141608,
      "grad_norm": 1.4375,
      "learning_rate": 2.7868671212133768e-05,
      "loss": 1.0852106094360352,
      "num_input_tokens_seen": 6311009408,
      "step": 22190,
      "train_runtime": 216233.3525,
      "train_tokens_per_second": 29186.105
    },
    {
      "epoch": 0.7854809854778896,
      "grad_norm": 1.390625,
      "learning_rate": 2.7864343308265313e-05,
      "loss": 1.0717653274536132,
      "num_input_tokens_seen": 6313870208,
      "step": 22200,
      "train_runtime": 216330.0587,
      "train_tokens_per_second": 29186.283
    },
    {
      "epoch": 0.7858348057416183,
      "grad_norm": 1.375,
      "learning_rate": 2.7860017420094258e-05,
      "loss": 1.0739994049072266,
      "num_input_tokens_seen": 6316758400,
      "step": 22210,
      "train_runtime": 216429.0445,
      "train_tokens_per_second": 29186.279
    },
    {
      "epoch": 0.7861886260053471,
      "grad_norm": 1.484375,
      "learning_rate": 2.7855693546056445e-05,
      "loss": 1.0957128524780273,
      "num_input_tokens_seen": 6319635136,
      "step": 22220,
      "train_runtime": 216528.6347,
      "train_tokens_per_second": 29186.14
    },
    {
      "epoch": 0.7865424462690759,
      "grad_norm": 1.421875,
      "learning_rate": 2.785137168458937e-05,
      "loss": 1.0915746688842773,
      "num_input_tokens_seen": 6322477056,
      "step": 22230,
      "train_runtime": 216623.0773,
      "train_tokens_per_second": 29186.535
    },
    {
      "epoch": 0.7868962665328046,
      "grad_norm": 1.46875,
      "learning_rate": 2.7847051834132265e-05,
      "loss": 1.0820093154907227,
      "num_input_tokens_seen": 6325317824,
      "step": 22240,
      "train_runtime": 216720.5364,
      "train_tokens_per_second": 29186.518
    },
    {
      "epoch": 0.7872500867965334,
      "grad_norm": 1.4921875,
      "learning_rate": 2.784273399312603e-05,
      "loss": 1.0895115852355957,
      "num_input_tokens_seen": 6328111424,
      "step": 22250,
      "train_runtime": 216813.8603,
      "train_tokens_per_second": 29186.84
    },
    {
      "epoch": 0.7876039070602622,
      "grad_norm": 1.4765625,
      "learning_rate": 2.783841816001326e-05,
      "loss": 1.0801700592041015,
      "num_input_tokens_seen": 6330975616,
      "step": 22260,
      "train_runtime": 216913.1992,
      "train_tokens_per_second": 29186.678
    },
    {
      "epoch": 0.787957727323991,
      "grad_norm": 1.5,
      "learning_rate": 2.7834104333238255e-05,
      "loss": 1.0837890625,
      "num_input_tokens_seen": 6333824768,
      "step": 22270,
      "train_runtime": 217009.3876,
      "train_tokens_per_second": 29186.87
    },
    {
      "epoch": 0.7883115475877198,
      "grad_norm": 1.421875,
      "learning_rate": 2.7829792511246987e-05,
      "loss": 1.087213897705078,
      "num_input_tokens_seen": 6336694208,
      "step": 22280,
      "train_runtime": 217109.4294,
      "train_tokens_per_second": 29186.637
    },
    {
      "epoch": 0.7886653678514486,
      "grad_norm": 1.484375,
      "learning_rate": 2.7825482692487114e-05,
      "loss": 1.0931692123413086,
      "num_input_tokens_seen": 6339521664,
      "step": 22290,
      "train_runtime": 217205.5884,
      "train_tokens_per_second": 29186.734
    },
    {
      "epoch": 0.7890191881151774,
      "grad_norm": 1.5,
      "learning_rate": 2.7821174875407985e-05,
      "loss": 1.0911617279052734,
      "num_input_tokens_seen": 6342405632,
      "step": 22300,
      "train_runtime": 217307.167,
      "train_tokens_per_second": 29186.362
    },
    {
      "epoch": 0.7893730083789061,
      "grad_norm": 1.515625,
      "learning_rate": 2.781686905846062e-05,
      "loss": 1.0833774566650392,
      "num_input_tokens_seen": 6345213056,
      "step": 22310,
      "train_runtime": 217402.6911,
      "train_tokens_per_second": 29186.451
    },
    {
      "epoch": 0.7897268286426349,
      "grad_norm": 1.5078125,
      "learning_rate": 2.7812565240097716e-05,
      "loss": 1.0764126777648926,
      "num_input_tokens_seen": 6348006400,
      "step": 22320,
      "train_runtime": 217497.343,
      "train_tokens_per_second": 29186.593
    },
    {
      "epoch": 0.7900806489063636,
      "grad_norm": 1.3828125,
      "learning_rate": 2.7808263418773656e-05,
      "loss": 1.092008113861084,
      "num_input_tokens_seen": 6350875264,
      "step": 22330,
      "train_runtime": 217594.684,
      "train_tokens_per_second": 29186.721
    },
    {
      "epoch": 0.7904344691700924,
      "grad_norm": 1.4921875,
      "learning_rate": 2.7803963592944482e-05,
      "loss": 1.0686561584472656,
      "num_input_tokens_seen": 6353698624,
      "step": 22340,
      "train_runtime": 217690.405,
      "train_tokens_per_second": 29186.857
    },
    {
      "epoch": 0.7907882894338213,
      "grad_norm": 1.5,
      "learning_rate": 2.779966576106792e-05,
      "loss": 1.0854507446289063,
      "num_input_tokens_seen": 6356481472,
      "step": 22350,
      "train_runtime": 217783.5379,
      "train_tokens_per_second": 29187.153
    },
    {
      "epoch": 0.7911421096975501,
      "grad_norm": 1.453125,
      "learning_rate": 2.779536992160336e-05,
      "loss": 1.0927342414855956,
      "num_input_tokens_seen": 6359324096,
      "step": 22360,
      "train_runtime": 217881.4989,
      "train_tokens_per_second": 29187.077
    },
    {
      "epoch": 0.7914959299612788,
      "grad_norm": 1.5078125,
      "learning_rate": 2.7791076073011845e-05,
      "loss": 1.08468017578125,
      "num_input_tokens_seen": 6362175808,
      "step": 22370,
      "train_runtime": 217980.0217,
      "train_tokens_per_second": 29186.967
    },
    {
      "epoch": 0.7918497502250076,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7786784213756102e-05,
      "loss": 1.0837465286254884,
      "num_input_tokens_seen": 6365002496,
      "step": 22380,
      "train_runtime": 218076.8825,
      "train_tokens_per_second": 29186.966
    },
    {
      "epoch": 0.7922035704887364,
      "grad_norm": 1.5390625,
      "learning_rate": 2.7782494342300502e-05,
      "loss": 1.092539405822754,
      "num_input_tokens_seen": 6367800384,
      "step": 22390,
      "train_runtime": 218167.685,
      "train_tokens_per_second": 29187.642
    },
    {
      "epoch": 0.7925573907524651,
      "grad_norm": 1.4765625,
      "learning_rate": 2.777820645711109e-05,
      "loss": 1.0881843566894531,
      "num_input_tokens_seen": 6370698624,
      "step": 22400,
      "train_runtime": 218268.0469,
      "train_tokens_per_second": 29187.5
    },
    {
      "epoch": 0.7929112110161939,
      "grad_norm": 1.5234375,
      "learning_rate": 2.777392055665556e-05,
      "loss": 1.0867594718933105,
      "num_input_tokens_seen": 6373549824,
      "step": 22410,
      "train_runtime": 218366.4292,
      "train_tokens_per_second": 29187.407
    },
    {
      "epoch": 0.7932650312799226,
      "grad_norm": 1.46875,
      "learning_rate": 2.7769636639403252e-05,
      "loss": 1.0758161544799805,
      "num_input_tokens_seen": 6376342400,
      "step": 22420,
      "train_runtime": 218460.7629,
      "train_tokens_per_second": 29187.586
    },
    {
      "epoch": 0.7936188515436514,
      "grad_norm": 1.5234375,
      "learning_rate": 2.776535470382518e-05,
      "loss": 1.0880653381347656,
      "num_input_tokens_seen": 6379187776,
      "step": 22430,
      "train_runtime": 218559.0245,
      "train_tokens_per_second": 29187.483
    },
    {
      "epoch": 0.7939726718073803,
      "grad_norm": 1.4609375,
      "learning_rate": 2.776107474839399e-05,
      "loss": 1.0953195571899415,
      "num_input_tokens_seen": 6382054144,
      "step": 22440,
      "train_runtime": 218659.6236,
      "train_tokens_per_second": 29187.163
    },
    {
      "epoch": 0.7943264920711091,
      "grad_norm": 1.421875,
      "learning_rate": 2.7756796771583976e-05,
      "loss": 1.0886566162109375,
      "num_input_tokens_seen": 6384900416,
      "step": 22450,
      "train_runtime": 218755.672,
      "train_tokens_per_second": 29187.359
    },
    {
      "epoch": 0.7946803123348378,
      "grad_norm": 1.4453125,
      "learning_rate": 2.775252077187109e-05,
      "loss": 1.073645782470703,
      "num_input_tokens_seen": 6387747456,
      "step": 22460,
      "train_runtime": 218852.7602,
      "train_tokens_per_second": 29187.42
    },
    {
      "epoch": 0.7950341325985666,
      "grad_norm": 1.5,
      "learning_rate": 2.7748246747732902e-05,
      "loss": 1.100697135925293,
      "num_input_tokens_seen": 6390513600,
      "step": 22470,
      "train_runtime": 218947.0941,
      "train_tokens_per_second": 29187.478
    },
    {
      "epoch": 0.7953879528622954,
      "grad_norm": 1.46875,
      "learning_rate": 2.774397469764866e-05,
      "loss": 1.0823389053344727,
      "num_input_tokens_seen": 6393333760,
      "step": 22480,
      "train_runtime": 219041.902,
      "train_tokens_per_second": 29187.72
    },
    {
      "epoch": 0.7957417731260241,
      "grad_norm": 1.453125,
      "learning_rate": 2.7739704620099226e-05,
      "loss": 1.0799068450927733,
      "num_input_tokens_seen": 6396174656,
      "step": 22490,
      "train_runtime": 219141.017,
      "train_tokens_per_second": 29187.483
    },
    {
      "epoch": 0.7960955933897529,
      "grad_norm": 1.5,
      "learning_rate": 2.7735436513567098e-05,
      "loss": 1.0778932571411133,
      "num_input_tokens_seen": 6399009600,
      "step": 22500,
      "train_runtime": 219239.3533,
      "train_tokens_per_second": 29187.322
    },
    {
      "epoch": 0.7964494136534817,
      "grad_norm": 1.4296875,
      "learning_rate": 2.7731170376536402e-05,
      "loss": 1.0846778869628906,
      "num_input_tokens_seen": 6401880448,
      "step": 22510,
      "train_runtime": 219337.5787,
      "train_tokens_per_second": 29187.34
    },
    {
      "epoch": 0.7968032339172105,
      "grad_norm": 1.46875,
      "learning_rate": 2.7726906207492925e-05,
      "loss": 1.0940632820129395,
      "num_input_tokens_seen": 6404782144,
      "step": 22520,
      "train_runtime": 219438.7903,
      "train_tokens_per_second": 29187.101
    },
    {
      "epoch": 0.7971570541809393,
      "grad_norm": 1.5859375,
      "learning_rate": 2.7722644004924048e-05,
      "loss": 1.0905357360839845,
      "num_input_tokens_seen": 6407612544,
      "step": 22530,
      "train_runtime": 219536.8433,
      "train_tokens_per_second": 29186.958
    },
    {
      "epoch": 0.7975108744446681,
      "grad_norm": 1.5078125,
      "learning_rate": 2.77183837673188e-05,
      "loss": 1.079473876953125,
      "num_input_tokens_seen": 6410450176,
      "step": 22540,
      "train_runtime": 219635.56,
      "train_tokens_per_second": 29186.759
    },
    {
      "epoch": 0.7978646947083968,
      "grad_norm": 1.4296875,
      "learning_rate": 2.7714125493167835e-05,
      "loss": 1.0797595977783203,
      "num_input_tokens_seen": 6413332416,
      "step": 22550,
      "train_runtime": 219738.0091,
      "train_tokens_per_second": 29186.268
    },
    {
      "epoch": 0.7982185149721256,
      "grad_norm": 1.515625,
      "learning_rate": 2.770986918096342e-05,
      "loss": 1.0850589752197266,
      "num_input_tokens_seen": 6416186432,
      "step": 22560,
      "train_runtime": 219836.6644,
      "train_tokens_per_second": 29186.153
    },
    {
      "epoch": 0.7985723352358544,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7705614829199454e-05,
      "loss": 1.08462495803833,
      "num_input_tokens_seen": 6418982848,
      "step": 22570,
      "train_runtime": 219931.623,
      "train_tokens_per_second": 29186.266
    },
    {
      "epoch": 0.7989261554995831,
      "grad_norm": 1.4375,
      "learning_rate": 2.7701362436371437e-05,
      "loss": 1.0859682083129882,
      "num_input_tokens_seen": 6421845056,
      "step": 22580,
      "train_runtime": 220031.0337,
      "train_tokens_per_second": 29186.088
    },
    {
      "epoch": 0.7992799757633119,
      "grad_norm": 1.5078125,
      "learning_rate": 2.7697112000976492e-05,
      "loss": 1.060536766052246,
      "num_input_tokens_seen": 6424694080,
      "step": 22590,
      "train_runtime": 220127.394,
      "train_tokens_per_second": 29186.254
    },
    {
      "epoch": 0.7996337960270408,
      "grad_norm": 1.4140625,
      "learning_rate": 2.769286352151338e-05,
      "loss": 1.0825712203979492,
      "num_input_tokens_seen": 6427556096,
      "step": 22600,
      "train_runtime": 220225.7843,
      "train_tokens_per_second": 29186.21
    },
    {
      "epoch": 0.7999876162907695,
      "grad_norm": 1.46875,
      "learning_rate": 2.768861699648243e-05,
      "loss": 1.0818939208984375,
      "num_input_tokens_seen": 6430488064,
      "step": 22610,
      "train_runtime": 220325.6519,
      "train_tokens_per_second": 29186.289
    },
    {
      "epoch": 0.8003414365544983,
      "grad_norm": 1.4453125,
      "learning_rate": 2.7684372424385613e-05,
      "loss": 1.0833845138549805,
      "num_input_tokens_seen": 6433337280,
      "step": 22620,
      "train_runtime": 220422.4011,
      "train_tokens_per_second": 29186.404
    },
    {
      "epoch": 0.8006952568182271,
      "grad_norm": 1.5,
      "learning_rate": 2.7680129803726496e-05,
      "loss": 1.0743524551391601,
      "num_input_tokens_seen": 6436162176,
      "step": 22630,
      "train_runtime": 220520.1282,
      "train_tokens_per_second": 29186.28
    },
    {
      "epoch": 0.8010490770819558,
      "grad_norm": 1.4453125,
      "learning_rate": 2.767588913301025e-05,
      "loss": 1.0982215881347657,
      "num_input_tokens_seen": 6439001344,
      "step": 22640,
      "train_runtime": 220616.3687,
      "train_tokens_per_second": 29186.417
    },
    {
      "epoch": 0.8014028973456846,
      "grad_norm": 1.5,
      "learning_rate": 2.767165041074365e-05,
      "loss": 1.0816495895385743,
      "num_input_tokens_seen": 6441841536,
      "step": 22650,
      "train_runtime": 220712.0151,
      "train_tokens_per_second": 29186.637
    },
    {
      "epoch": 0.8017567176094134,
      "grad_norm": 1.4296875,
      "learning_rate": 2.766741363543507e-05,
      "loss": 1.0748140335083007,
      "num_input_tokens_seen": 6444707584,
      "step": 22660,
      "train_runtime": 220810.6789,
      "train_tokens_per_second": 29186.576
    },
    {
      "epoch": 0.8021105378731421,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7663178805594482e-05,
      "loss": 1.068247413635254,
      "num_input_tokens_seen": 6447578112,
      "step": 22670,
      "train_runtime": 220908.3467,
      "train_tokens_per_second": 29186.666
    },
    {
      "epoch": 0.8024643581368709,
      "grad_norm": 1.484375,
      "learning_rate": 2.7658945919733463e-05,
      "loss": 1.0890165328979493,
      "num_input_tokens_seen": 6450483520,
      "step": 22680,
      "train_runtime": 221011.6993,
      "train_tokens_per_second": 29186.163
    },
    {
      "epoch": 0.8028181784005998,
      "grad_norm": 1.4765625,
      "learning_rate": 2.7654714976365164e-05,
      "loss": 1.075960350036621,
      "num_input_tokens_seen": 6453366400,
      "step": 22690,
      "train_runtime": 221109.0118,
      "train_tokens_per_second": 29186.356
    },
    {
      "epoch": 0.8031719986643285,
      "grad_norm": 1.4375,
      "learning_rate": 2.765048597400436e-05,
      "loss": 1.0807207107543946,
      "num_input_tokens_seen": 6456204928,
      "step": 22700,
      "train_runtime": 221205.2463,
      "train_tokens_per_second": 29186.491
    },
    {
      "epoch": 0.8035258189280573,
      "grad_norm": 1.453125,
      "learning_rate": 2.7646258911167373e-05,
      "loss": 1.0858779907226563,
      "num_input_tokens_seen": 6459031936,
      "step": 22710,
      "train_runtime": 221302.3505,
      "train_tokens_per_second": 29186.459
    },
    {
      "epoch": 0.8038796391917861,
      "grad_norm": 1.4453125,
      "learning_rate": 2.7642033786372145e-05,
      "loss": 1.0899287223815919,
      "num_input_tokens_seen": 6461922624,
      "step": 22720,
      "train_runtime": 221399.4719,
      "train_tokens_per_second": 29186.712
    },
    {
      "epoch": 0.8042334594555148,
      "grad_norm": 1.53125,
      "learning_rate": 2.7637810598138193e-05,
      "loss": 1.078603172302246,
      "num_input_tokens_seen": 6464810112,
      "step": 22730,
      "train_runtime": 221496.2168,
      "train_tokens_per_second": 29187.0
    },
    {
      "epoch": 0.8045872797192436,
      "grad_norm": 1.5,
      "learning_rate": 2.7633589344986615e-05,
      "loss": 1.0724714279174805,
      "num_input_tokens_seen": 6467718464,
      "step": 22740,
      "train_runtime": 221598.5992,
      "train_tokens_per_second": 29186.64
    },
    {
      "epoch": 0.8049410999829724,
      "grad_norm": 1.5,
      "learning_rate": 2.7629370025440087e-05,
      "loss": 1.0867698669433594,
      "num_input_tokens_seen": 6470567360,
      "step": 22750,
      "train_runtime": 221698.3856,
      "train_tokens_per_second": 29186.353
    },
    {
      "epoch": 0.8052949202467011,
      "grad_norm": 1.4296875,
      "learning_rate": 2.762515263802287e-05,
      "loss": 1.0704718589782716,
      "num_input_tokens_seen": 6473497920,
      "step": 22760,
      "train_runtime": 221798.8459,
      "train_tokens_per_second": 29186.346
    },
    {
      "epoch": 0.80564874051043,
      "grad_norm": 1.453125,
      "learning_rate": 2.762093718126081e-05,
      "loss": 1.0814133644104005,
      "num_input_tokens_seen": 6476327488,
      "step": 22770,
      "train_runtime": 221891.8858,
      "train_tokens_per_second": 29186.86
    },
    {
      "epoch": 0.8060025607741588,
      "grad_norm": 1.4765625,
      "learning_rate": 2.7616723653681298e-05,
      "loss": 1.0889326095581056,
      "num_input_tokens_seen": 6479164608,
      "step": 22780,
      "train_runtime": 221988.188,
      "train_tokens_per_second": 29186.979
    },
    {
      "epoch": 0.8063563810378875,
      "grad_norm": 1.4921875,
      "learning_rate": 2.761251205381332e-05,
      "loss": 1.0868659973144532,
      "num_input_tokens_seen": 6482004800,
      "step": 22790,
      "train_runtime": 222085.1636,
      "train_tokens_per_second": 29187.023
    },
    {
      "epoch": 0.8067102013016163,
      "grad_norm": 1.5234375,
      "learning_rate": 2.760830238018744e-05,
      "loss": 1.084191131591797,
      "num_input_tokens_seen": 6484838592,
      "step": 22800,
      "train_runtime": 222183.111,
      "train_tokens_per_second": 29186.911
    },
    {
      "epoch": 0.8070640215653451,
      "grad_norm": 1.453125,
      "learning_rate": 2.760409463133576e-05,
      "loss": 1.0698507308959961,
      "num_input_tokens_seen": 6487655488,
      "step": 22810,
      "train_runtime": 222276.9424,
      "train_tokens_per_second": 29187.263
    },
    {
      "epoch": 0.8074178418290738,
      "grad_norm": 1.625,
      "learning_rate": 2.7599888805791967e-05,
      "loss": 1.086565113067627,
      "num_input_tokens_seen": 6490529792,
      "step": 22820,
      "train_runtime": 222378.5886,
      "train_tokens_per_second": 29186.847
    },
    {
      "epoch": 0.8077716620928026,
      "grad_norm": 1.4453125,
      "learning_rate": 2.759568490209132e-05,
      "loss": 1.0623001098632812,
      "num_input_tokens_seen": 6493384512,
      "step": 22830,
      "train_runtime": 222476.3897,
      "train_tokens_per_second": 29186.848
    },
    {
      "epoch": 0.8081254823565314,
      "grad_norm": 1.46875,
      "learning_rate": 2.7591482918770613e-05,
      "loss": 1.0803041458129883,
      "num_input_tokens_seen": 6496235776,
      "step": 22840,
      "train_runtime": 222573.3827,
      "train_tokens_per_second": 29186.939
    },
    {
      "epoch": 0.8084793026202602,
      "grad_norm": 1.5078125,
      "learning_rate": 2.7587282854368222e-05,
      "loss": 1.0806642532348634,
      "num_input_tokens_seen": 6499074240,
      "step": 22850,
      "train_runtime": 222671.9021,
      "train_tokens_per_second": 29186.773
    },
    {
      "epoch": 0.808833122883989,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7583084707424072e-05,
      "loss": 1.069394874572754,
      "num_input_tokens_seen": 6501894272,
      "step": 22860,
      "train_runtime": 222768.0564,
      "train_tokens_per_second": 29186.834
    },
    {
      "epoch": 0.8091869431477178,
      "grad_norm": 1.53125,
      "learning_rate": 2.7578888476479643e-05,
      "loss": 1.086017894744873,
      "num_input_tokens_seen": 6504719232,
      "step": 22870,
      "train_runtime": 222865.6993,
      "train_tokens_per_second": 29186.722
    },
    {
      "epoch": 0.8095407634114465,
      "grad_norm": 1.609375,
      "learning_rate": 2.7574694160077964e-05,
      "loss": 1.0745489120483398,
      "num_input_tokens_seen": 6507529088,
      "step": 22880,
      "train_runtime": 222961.0441,
      "train_tokens_per_second": 29186.843
    },
    {
      "epoch": 0.8098945836751753,
      "grad_norm": 1.4296875,
      "learning_rate": 2.757050175676362e-05,
      "loss": 1.0779829025268555,
      "num_input_tokens_seen": 6510378048,
      "step": 22890,
      "train_runtime": 223060.7285,
      "train_tokens_per_second": 29186.572
    },
    {
      "epoch": 0.8102484039389041,
      "grad_norm": 1.484375,
      "learning_rate": 2.756631126508274e-05,
      "loss": 1.0801769256591798,
      "num_input_tokens_seen": 6513212288,
      "step": 22900,
      "train_runtime": 223154.846,
      "train_tokens_per_second": 29186.963
    },
    {
      "epoch": 0.8106022242026328,
      "grad_norm": 1.5078125,
      "learning_rate": 2.7562122683583004e-05,
      "loss": 1.0808786392211913,
      "num_input_tokens_seen": 6516022976,
      "step": 22910,
      "train_runtime": 223253.5888,
      "train_tokens_per_second": 29186.644
    },
    {
      "epoch": 0.8109560444663616,
      "grad_norm": 1.484375,
      "learning_rate": 2.7557936010813634e-05,
      "loss": 1.0762039184570313,
      "num_input_tokens_seen": 6518820352,
      "step": 22920,
      "train_runtime": 223348.5547,
      "train_tokens_per_second": 29186.759
    },
    {
      "epoch": 0.8113098647300904,
      "grad_norm": 1.4453125,
      "learning_rate": 2.75537512453254e-05,
      "loss": 1.0891626358032227,
      "num_input_tokens_seen": 6521648768,
      "step": 22930,
      "train_runtime": 223447.3114,
      "train_tokens_per_second": 29186.517
    },
    {
      "epoch": 0.8116636849938192,
      "grad_norm": 1.5390625,
      "learning_rate": 2.7549568385670595e-05,
      "loss": 1.0772696495056153,
      "num_input_tokens_seen": 6524491072,
      "step": 22940,
      "train_runtime": 223545.5487,
      "train_tokens_per_second": 29186.406
    },
    {
      "epoch": 0.812017505257548,
      "grad_norm": 1.5546875,
      "learning_rate": 2.754538743040307e-05,
      "loss": 1.0925559043884276,
      "num_input_tokens_seen": 6527338176,
      "step": 22950,
      "train_runtime": 223642.946,
      "train_tokens_per_second": 29186.425
    },
    {
      "epoch": 0.8123713255212768,
      "grad_norm": 1.5234375,
      "learning_rate": 2.75412083780782e-05,
      "loss": 1.0778794288635254,
      "num_input_tokens_seen": 6530195456,
      "step": 22960,
      "train_runtime": 223740.4807,
      "train_tokens_per_second": 29186.473
    },
    {
      "epoch": 0.8127251457850055,
      "grad_norm": 1.46875,
      "learning_rate": 2.7537031227252898e-05,
      "loss": 1.082054328918457,
      "num_input_tokens_seen": 6533060800,
      "step": 22970,
      "train_runtime": 223840.7978,
      "train_tokens_per_second": 29186.193
    },
    {
      "epoch": 0.8130789660487343,
      "grad_norm": 1.421875,
      "learning_rate": 2.75328559764856e-05,
      "loss": 1.0906583786010742,
      "num_input_tokens_seen": 6535907968,
      "step": 22980,
      "train_runtime": 223936.8598,
      "train_tokens_per_second": 29186.388
    },
    {
      "epoch": 0.8134327863124631,
      "grad_norm": 1.453125,
      "learning_rate": 2.752868262433629e-05,
      "loss": 1.0815360069274902,
      "num_input_tokens_seen": 6538782976,
      "step": 22990,
      "train_runtime": 224036.8667,
      "train_tokens_per_second": 29186.192
    },
    {
      "epoch": 0.8137866065761918,
      "grad_norm": 1.46875,
      "learning_rate": 2.752451116936646e-05,
      "loss": 1.075191116333008,
      "num_input_tokens_seen": 6541612096,
      "step": 23000,
      "train_runtime": 224132.5556,
      "train_tokens_per_second": 29186.354
    },
    {
      "epoch": 0.8141404268399206,
      "grad_norm": 1.5234375,
      "learning_rate": 2.752034161013915e-05,
      "loss": 1.0768547058105469,
      "num_input_tokens_seen": 6544474112,
      "step": 23010,
      "train_runtime": 224233.1456,
      "train_tokens_per_second": 29186.025
    },
    {
      "epoch": 0.8144942471036495,
      "grad_norm": 1.4921875,
      "learning_rate": 2.7516173945218888e-05,
      "loss": 1.0830118179321289,
      "num_input_tokens_seen": 6547316608,
      "step": 23020,
      "train_runtime": 224327.398,
      "train_tokens_per_second": 29186.433
    },
    {
      "epoch": 0.8148480673673782,
      "grad_norm": 1.53125,
      "learning_rate": 2.751200817317176e-05,
      "loss": 1.0963520050048827,
      "num_input_tokens_seen": 6550139776,
      "step": 23030,
      "train_runtime": 224424.3539,
      "train_tokens_per_second": 29186.404
    },
    {
      "epoch": 0.815201887631107,
      "grad_norm": 1.4375,
      "learning_rate": 2.7507844292565354e-05,
      "loss": 1.068218994140625,
      "num_input_tokens_seen": 6552959808,
      "step": 23040,
      "train_runtime": 224521.6797,
      "train_tokens_per_second": 29186.312
    },
    {
      "epoch": 0.8155557078948358,
      "grad_norm": 1.5078125,
      "learning_rate": 2.7503682301968763e-05,
      "loss": 1.0791427612304687,
      "num_input_tokens_seen": 6555845696,
      "step": 23050,
      "train_runtime": 224622.7318,
      "train_tokens_per_second": 29186.03
    },
    {
      "epoch": 0.8159095281585645,
      "grad_norm": 1.546875,
      "learning_rate": 2.7499522199952627e-05,
      "loss": 1.0884111404418946,
      "num_input_tokens_seen": 6558741824,
      "step": 23060,
      "train_runtime": 224725.9057,
      "train_tokens_per_second": 29185.517
    },
    {
      "epoch": 0.8162633484222933,
      "grad_norm": 1.5,
      "learning_rate": 2.7495363985089072e-05,
      "loss": 1.080415630340576,
      "num_input_tokens_seen": 6561577408,
      "step": 23070,
      "train_runtime": 224823.8569,
      "train_tokens_per_second": 29185.414
    },
    {
      "epoch": 0.8166171686860221,
      "grad_norm": 1.5,
      "learning_rate": 2.7491207655951745e-05,
      "loss": 1.0804697036743165,
      "num_input_tokens_seen": 6564394368,
      "step": 23080,
      "train_runtime": 224919.485,
      "train_tokens_per_second": 29185.53
    },
    {
      "epoch": 0.8169709889497508,
      "grad_norm": 1.4921875,
      "learning_rate": 2.7487053211115797e-05,
      "loss": 1.077825927734375,
      "num_input_tokens_seen": 6567258048,
      "step": 23090,
      "train_runtime": 225020.8964,
      "train_tokens_per_second": 29185.103
    },
    {
      "epoch": 0.8173248092134797,
      "grad_norm": 1.5234375,
      "learning_rate": 2.748290064915789e-05,
      "loss": 1.0958138465881349,
      "num_input_tokens_seen": 6570109760,
      "step": 23100,
      "train_runtime": 225118.6605,
      "train_tokens_per_second": 29185.096
    },
    {
      "epoch": 0.8176786294772085,
      "grad_norm": 1.5078125,
      "learning_rate": 2.747874996865619e-05,
      "loss": 1.0759672164916991,
      "num_input_tokens_seen": 6572910400,
      "step": 23110,
      "train_runtime": 225214.9084,
      "train_tokens_per_second": 29185.059
    },
    {
      "epoch": 0.8180324497409373,
      "grad_norm": 1.4765625,
      "learning_rate": 2.747460116819037e-05,
      "loss": 1.0935222625732421,
      "num_input_tokens_seen": 6575717312,
      "step": 23120,
      "train_runtime": 225308.3959,
      "train_tokens_per_second": 29185.407
    },
    {
      "epoch": 0.818386270004666,
      "grad_norm": 1.46875,
      "learning_rate": 2.7470454246341597e-05,
      "loss": 1.0940135955810546,
      "num_input_tokens_seen": 6578460416,
      "step": 23130,
      "train_runtime": 225400.0272,
      "train_tokens_per_second": 29185.713
    },
    {
      "epoch": 0.8187400902683948,
      "grad_norm": 1.4765625,
      "learning_rate": 2.746630920169254e-05,
      "loss": 1.078403854370117,
      "num_input_tokens_seen": 6581277248,
      "step": 23140,
      "train_runtime": 225498.2749,
      "train_tokens_per_second": 29185.488
    },
    {
      "epoch": 0.8190939105321235,
      "grad_norm": 1.5,
      "learning_rate": 2.7462166032827358e-05,
      "loss": 1.0915197372436523,
      "num_input_tokens_seen": 6584125312,
      "step": 23150,
      "train_runtime": 225597.8471,
      "train_tokens_per_second": 29185.231
    },
    {
      "epoch": 0.8194477307958523,
      "grad_norm": 1.4609375,
      "learning_rate": 2.745802473833171e-05,
      "loss": 1.0811795234680175,
      "num_input_tokens_seen": 6586948032,
      "step": 23160,
      "train_runtime": 225693.9878,
      "train_tokens_per_second": 29185.306
    },
    {
      "epoch": 0.8198015510595811,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7453885316792755e-05,
      "loss": 1.0730777740478517,
      "num_input_tokens_seen": 6589785408,
      "step": 23170,
      "train_runtime": 225791.104,
      "train_tokens_per_second": 29185.319
    },
    {
      "epoch": 0.8201553713233098,
      "grad_norm": 1.4765625,
      "learning_rate": 2.7449747766799135e-05,
      "loss": 1.0770389556884765,
      "num_input_tokens_seen": 6592632320,
      "step": 23180,
      "train_runtime": 225890.8482,
      "train_tokens_per_second": 29185.035
    },
    {
      "epoch": 0.8205091915870387,
      "grad_norm": 1.46875,
      "learning_rate": 2.744561208694097e-05,
      "loss": 1.0897814750671386,
      "num_input_tokens_seen": 6595490112,
      "step": 23190,
      "train_runtime": 225987.8959,
      "train_tokens_per_second": 29185.148
    },
    {
      "epoch": 0.8208630118507675,
      "grad_norm": 1.4921875,
      "learning_rate": 2.7441478275809884e-05,
      "loss": 1.0790255546569825,
      "num_input_tokens_seen": 6598388416,
      "step": 23200,
      "train_runtime": 226089.1662,
      "train_tokens_per_second": 29184.894
    },
    {
      "epoch": 0.8212168321144963,
      "grad_norm": 1.453125,
      "learning_rate": 2.743734633199898e-05,
      "loss": 1.0959592819213868,
      "num_input_tokens_seen": 6601239296,
      "step": 23210,
      "train_runtime": 226187.6752,
      "train_tokens_per_second": 29184.788
    },
    {
      "epoch": 0.821570652378225,
      "grad_norm": 1.4921875,
      "learning_rate": 2.743321625410284e-05,
      "loss": 1.0892959594726563,
      "num_input_tokens_seen": 6604035840,
      "step": 23220,
      "train_runtime": 226280.6314,
      "train_tokens_per_second": 29185.157
    },
    {
      "epoch": 0.8219244726419538,
      "grad_norm": 1.4765625,
      "learning_rate": 2.7429088040717526e-05,
      "loss": 1.096724796295166,
      "num_input_tokens_seen": 6606898432,
      "step": 23230,
      "train_runtime": 226378.024,
      "train_tokens_per_second": 29185.246
    },
    {
      "epoch": 0.8222782929056826,
      "grad_norm": 1.4921875,
      "learning_rate": 2.7424961690440586e-05,
      "loss": 1.0844781875610352,
      "num_input_tokens_seen": 6609739008,
      "step": 23240,
      "train_runtime": 226472.1124,
      "train_tokens_per_second": 29185.664
    },
    {
      "epoch": 0.8226321131694113,
      "grad_norm": 1.4921875,
      "learning_rate": 2.742083720187103e-05,
      "loss": 1.0861766815185547,
      "num_input_tokens_seen": 6612523008,
      "step": 23250,
      "train_runtime": 226564.1338,
      "train_tokens_per_second": 29186.098
    },
    {
      "epoch": 0.8229859334331401,
      "grad_norm": 1.5234375,
      "learning_rate": 2.7416714573609363e-05,
      "loss": 1.076883316040039,
      "num_input_tokens_seen": 6615339584,
      "step": 23260,
      "train_runtime": 226660.995,
      "train_tokens_per_second": 29186.052
    },
    {
      "epoch": 0.823339753696869,
      "grad_norm": 1.4765625,
      "learning_rate": 2.7412593804257543e-05,
      "loss": 1.0979621887207032,
      "num_input_tokens_seen": 6618179392,
      "step": 23270,
      "train_runtime": 226755.7336,
      "train_tokens_per_second": 29186.382
    },
    {
      "epoch": 0.8236935739605977,
      "grad_norm": 1.453125,
      "learning_rate": 2.740847489241901e-05,
      "loss": 1.0813051223754884,
      "num_input_tokens_seen": 6621007104,
      "step": 23280,
      "train_runtime": 226853.9951,
      "train_tokens_per_second": 29186.205
    },
    {
      "epoch": 0.8240473942243265,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7404357836698668e-05,
      "loss": 1.0965773582458496,
      "num_input_tokens_seen": 6623822912,
      "step": 23290,
      "train_runtime": 226949.1809,
      "train_tokens_per_second": 29186.371
    },
    {
      "epoch": 0.8244012144880553,
      "grad_norm": 1.4609375,
      "learning_rate": 2.740024263570289e-05,
      "loss": 1.0745887756347656,
      "num_input_tokens_seen": 6626688576,
      "step": 23300,
      "train_runtime": 227047.2126,
      "train_tokens_per_second": 29186.39
    },
    {
      "epoch": 0.824755034751784,
      "grad_norm": 1.484375,
      "learning_rate": 2.7396129288039503e-05,
      "loss": 1.0811769485473632,
      "num_input_tokens_seen": 6629458304,
      "step": 23310,
      "train_runtime": 227139.6555,
      "train_tokens_per_second": 29186.706
    },
    {
      "epoch": 0.8251088550155128,
      "grad_norm": 1.453125,
      "learning_rate": 2.739201779231782e-05,
      "loss": 1.0905887603759765,
      "num_input_tokens_seen": 6632267136,
      "step": 23320,
      "train_runtime": 227233.2296,
      "train_tokens_per_second": 29187.048
    },
    {
      "epoch": 0.8254626752792416,
      "grad_norm": 1.5,
      "learning_rate": 2.7387908147148587e-05,
      "loss": 1.0939032554626464,
      "num_input_tokens_seen": 6635163584,
      "step": 23330,
      "train_runtime": 227333.4696,
      "train_tokens_per_second": 29186.919
    },
    {
      "epoch": 0.8258164955429703,
      "grad_norm": 1.546875,
      "learning_rate": 2.7383800351144027e-05,
      "loss": 1.088741397857666,
      "num_input_tokens_seen": 6638039808,
      "step": 23340,
      "train_runtime": 227429.2755,
      "train_tokens_per_second": 29187.271
    },
    {
      "epoch": 0.8261703158066992,
      "grad_norm": 1.453125,
      "learning_rate": 2.737969440291782e-05,
      "loss": 1.0957265853881837,
      "num_input_tokens_seen": 6640829056,
      "step": 23350,
      "train_runtime": 227523.7353,
      "train_tokens_per_second": 29187.412
    },
    {
      "epoch": 0.826524136070428,
      "grad_norm": 1.4453125,
      "learning_rate": 2.7375590301085087e-05,
      "loss": 1.070406723022461,
      "num_input_tokens_seen": 6643602688,
      "step": 23360,
      "train_runtime": 227618.3698,
      "train_tokens_per_second": 29187.463
    },
    {
      "epoch": 0.8268779563341567,
      "grad_norm": 1.53125,
      "learning_rate": 2.7371488044262406e-05,
      "loss": 1.0714908599853517,
      "num_input_tokens_seen": 6646403584,
      "step": 23370,
      "train_runtime": 227710.793,
      "train_tokens_per_second": 29187.916
    },
    {
      "epoch": 0.8272317765978855,
      "grad_norm": 1.4765625,
      "learning_rate": 2.7367387631067816e-05,
      "loss": 1.0696182250976562,
      "num_input_tokens_seen": 6649190208,
      "step": 23380,
      "train_runtime": 227805.6425,
      "train_tokens_per_second": 29187.996
    },
    {
      "epoch": 0.8275855968616143,
      "grad_norm": 1.4765625,
      "learning_rate": 2.73632890601208e-05,
      "loss": 1.0714986801147461,
      "num_input_tokens_seen": 6651995392,
      "step": 23390,
      "train_runtime": 227900.7377,
      "train_tokens_per_second": 29188.126
    },
    {
      "epoch": 0.827939417125343,
      "grad_norm": 1.453125,
      "learning_rate": 2.7359192330042277e-05,
      "loss": 1.0810748100280763,
      "num_input_tokens_seen": 6654835136,
      "step": 23400,
      "train_runtime": 227998.3007,
      "train_tokens_per_second": 29188.091
    },
    {
      "epoch": 0.8282932373890718,
      "grad_norm": 1.53125,
      "learning_rate": 2.7355097439454625e-05,
      "loss": 1.106581211090088,
      "num_input_tokens_seen": 6657648832,
      "step": 23410,
      "train_runtime": 228092.8054,
      "train_tokens_per_second": 29188.333
    },
    {
      "epoch": 0.8286470576528006,
      "grad_norm": 1.46875,
      "learning_rate": 2.735100438698166e-05,
      "loss": 1.0827984809875488,
      "num_input_tokens_seen": 6660510272,
      "step": 23420,
      "train_runtime": 228192.2342,
      "train_tokens_per_second": 29188.155
    },
    {
      "epoch": 0.8290008779165293,
      "grad_norm": 1.65625,
      "learning_rate": 2.7346913171248635e-05,
      "loss": 1.074754810333252,
      "num_input_tokens_seen": 6663379200,
      "step": 23430,
      "train_runtime": 228294.8726,
      "train_tokens_per_second": 29187.599
    },
    {
      "epoch": 0.8293546981802582,
      "grad_norm": 1.4609375,
      "learning_rate": 2.734282379088225e-05,
      "loss": 1.0844354629516602,
      "num_input_tokens_seen": 6666237120,
      "step": 23440,
      "train_runtime": 228395.6905,
      "train_tokens_per_second": 29187.228
    },
    {
      "epoch": 0.829708518443987,
      "grad_norm": 1.453125,
      "learning_rate": 2.733873624451063e-05,
      "loss": 1.081937026977539,
      "num_input_tokens_seen": 6669092544,
      "step": 23450,
      "train_runtime": 228494.4185,
      "train_tokens_per_second": 29187.114
    },
    {
      "epoch": 0.8300623387077157,
      "grad_norm": 1.5546875,
      "learning_rate": 2.733465053076335e-05,
      "loss": 1.07940673828125,
      "num_input_tokens_seen": 6671894848,
      "step": 23460,
      "train_runtime": 228590.2873,
      "train_tokens_per_second": 29187.132
    },
    {
      "epoch": 0.8304161589714445,
      "grad_norm": 1.4453125,
      "learning_rate": 2.733056664827141e-05,
      "loss": 1.0755454063415528,
      "num_input_tokens_seen": 6674719872,
      "step": 23470,
      "train_runtime": 228684.5172,
      "train_tokens_per_second": 29187.459
    },
    {
      "epoch": 0.8307699792351733,
      "grad_norm": 1.53125,
      "learning_rate": 2.732648459566724e-05,
      "loss": 1.0861963272094726,
      "num_input_tokens_seen": 6677592960,
      "step": 23480,
      "train_runtime": 228784.5293,
      "train_tokens_per_second": 29187.257
    },
    {
      "epoch": 0.831123799498902,
      "grad_norm": 1.5390625,
      "learning_rate": 2.73224043715847e-05,
      "loss": 1.0914776802062989,
      "num_input_tokens_seen": 6680380736,
      "step": 23490,
      "train_runtime": 228877.2885,
      "train_tokens_per_second": 29187.609
    },
    {
      "epoch": 0.8314776197626308,
      "grad_norm": 1.453125,
      "learning_rate": 2.731832597465908e-05,
      "loss": 1.0868388175964356,
      "num_input_tokens_seen": 6683200000,
      "step": 23500,
      "train_runtime": 228974.4052,
      "train_tokens_per_second": 29187.542
    },
    {
      "epoch": 0.8318314400263596,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7314249403527097e-05,
      "loss": 1.0788534164428711,
      "num_input_tokens_seen": 6686038400,
      "step": 23510,
      "train_runtime": 229073.8299,
      "train_tokens_per_second": 29187.264
    },
    {
      "epoch": 0.8321852602900884,
      "grad_norm": 1.5,
      "learning_rate": 2.731017465682689e-05,
      "loss": 1.0865266799926758,
      "num_input_tokens_seen": 6688851328,
      "step": 23520,
      "train_runtime": 229169.6674,
      "train_tokens_per_second": 29187.333
    },
    {
      "epoch": 0.8325390805538172,
      "grad_norm": 1.484375,
      "learning_rate": 2.730610173319802e-05,
      "loss": 1.0864070892333983,
      "num_input_tokens_seen": 6691664960,
      "step": 23530,
      "train_runtime": 229264.0118,
      "train_tokens_per_second": 29187.594
    },
    {
      "epoch": 0.832892900817546,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7302030631281454e-05,
      "loss": 1.0914388656616212,
      "num_input_tokens_seen": 6694520128,
      "step": 23540,
      "train_runtime": 229361.4796,
      "train_tokens_per_second": 29187.639
    },
    {
      "epoch": 0.8332467210812747,
      "grad_norm": 1.4765625,
      "learning_rate": 2.7297961349719608e-05,
      "loss": 1.0835803985595702,
      "num_input_tokens_seen": 6697419392,
      "step": 23550,
      "train_runtime": 229463.8819,
      "train_tokens_per_second": 29187.249
    },
    {
      "epoch": 0.8336005413450035,
      "grad_norm": 1.5234375,
      "learning_rate": 2.729389388715628e-05,
      "loss": 1.0846891403198242,
      "num_input_tokens_seen": 6700298176,
      "step": 23560,
      "train_runtime": 229564.6438,
      "train_tokens_per_second": 29186.978
    },
    {
      "epoch": 0.8339543616087323,
      "grad_norm": 1.5625,
      "learning_rate": 2.728982824223671e-05,
      "loss": 1.0953842163085938,
      "num_input_tokens_seen": 6703155264,
      "step": 23570,
      "train_runtime": 229660.6212,
      "train_tokens_per_second": 29187.221
    },
    {
      "epoch": 0.834308181872461,
      "grad_norm": 1.4921875,
      "learning_rate": 2.7285764413607527e-05,
      "loss": 1.0790843963623047,
      "num_input_tokens_seen": 6706059072,
      "step": 23580,
      "train_runtime": 229759.6279,
      "train_tokens_per_second": 29187.282
    },
    {
      "epoch": 0.8346620021361898,
      "grad_norm": 1.4765625,
      "learning_rate": 2.7281702399916786e-05,
      "loss": 1.0800951957702636,
      "num_input_tokens_seen": 6708845440,
      "step": 23590,
      "train_runtime": 229853.7703,
      "train_tokens_per_second": 29187.45
    },
    {
      "epoch": 0.8350158223999187,
      "grad_norm": 1.5546875,
      "learning_rate": 2.7277642199813954e-05,
      "loss": 1.0798261642456055,
      "num_input_tokens_seen": 6711675456,
      "step": 23600,
      "train_runtime": 229950.7569,
      "train_tokens_per_second": 29187.447
    },
    {
      "epoch": 0.8353696426636474,
      "grad_norm": 1.5390625,
      "learning_rate": 2.7273583811949882e-05,
      "loss": 1.0819452285766602,
      "num_input_tokens_seen": 6714522112,
      "step": 23610,
      "train_runtime": 230046.4123,
      "train_tokens_per_second": 29187.685
    },
    {
      "epoch": 0.8357234629273762,
      "grad_norm": 1.4921875,
      "learning_rate": 2.7269527234976844e-05,
      "loss": 1.0799477577209473,
      "num_input_tokens_seen": 6717364800,
      "step": 23620,
      "train_runtime": 230142.4622,
      "train_tokens_per_second": 29187.855
    },
    {
      "epoch": 0.836077283191105,
      "grad_norm": 1.46875,
      "learning_rate": 2.726547246754852e-05,
      "loss": 1.0844985961914062,
      "num_input_tokens_seen": 6720234496,
      "step": 23630,
      "train_runtime": 230242.8303,
      "train_tokens_per_second": 29187.595
    },
    {
      "epoch": 0.8364311034548337,
      "grad_norm": 1.4921875,
      "learning_rate": 2.726141950831998e-05,
      "loss": 1.0818479537963868,
      "num_input_tokens_seen": 6723101184,
      "step": 23640,
      "train_runtime": 230337.4883,
      "train_tokens_per_second": 29188.046
    },
    {
      "epoch": 0.8367849237185625,
      "grad_norm": 1.484375,
      "learning_rate": 2.7257368355947686e-05,
      "loss": 1.0719627380371093,
      "num_input_tokens_seen": 6725948544,
      "step": 23650,
      "train_runtime": 230435.5083,
      "train_tokens_per_second": 29187.987
    },
    {
      "epoch": 0.8371387439822913,
      "grad_norm": 1.484375,
      "learning_rate": 2.7253319009089528e-05,
      "loss": 1.1059932708740234,
      "num_input_tokens_seen": 6728794496,
      "step": 23660,
      "train_runtime": 230530.8522,
      "train_tokens_per_second": 29188.26
    },
    {
      "epoch": 0.83749256424602,
      "grad_norm": 1.453125,
      "learning_rate": 2.7249271466404758e-05,
      "loss": 1.0806312561035156,
      "num_input_tokens_seen": 6731619392,
      "step": 23670,
      "train_runtime": 230628.1144,
      "train_tokens_per_second": 29188.199
    },
    {
      "epoch": 0.8378463845097489,
      "grad_norm": 1.4453125,
      "learning_rate": 2.724522572655403e-05,
      "loss": 1.0931632041931152,
      "num_input_tokens_seen": 6734455360,
      "step": 23680,
      "train_runtime": 230727.0472,
      "train_tokens_per_second": 29187.975
    },
    {
      "epoch": 0.8382002047734777,
      "grad_norm": 1.5,
      "learning_rate": 2.7241181788199405e-05,
      "loss": 1.0595630645751952,
      "num_input_tokens_seen": 6737257792,
      "step": 23690,
      "train_runtime": 230820.5579,
      "train_tokens_per_second": 29188.292
    },
    {
      "epoch": 0.8385540250372064,
      "grad_norm": 1.453125,
      "learning_rate": 2.7237139650004316e-05,
      "loss": 1.0887943267822267,
      "num_input_tokens_seen": 6740072256,
      "step": 23700,
      "train_runtime": 230915.9002,
      "train_tokens_per_second": 29188.429
    },
    {
      "epoch": 0.8389078453009352,
      "grad_norm": 1.4375,
      "learning_rate": 2.7233099310633598e-05,
      "loss": 1.0827318191528321,
      "num_input_tokens_seen": 6742937472,
      "step": 23710,
      "train_runtime": 231014.1756,
      "train_tokens_per_second": 29188.414
    },
    {
      "epoch": 0.839261665564664,
      "grad_norm": 1.46875,
      "learning_rate": 2.722906076875345e-05,
      "loss": 1.091862678527832,
      "num_input_tokens_seen": 6745802560,
      "step": 23720,
      "train_runtime": 231110.8685,
      "train_tokens_per_second": 29188.599
    },
    {
      "epoch": 0.8396154858283927,
      "grad_norm": 1.5546875,
      "learning_rate": 2.7225024023031487e-05,
      "loss": 1.0906465530395508,
      "num_input_tokens_seen": 6748624448,
      "step": 23730,
      "train_runtime": 231206.9539,
      "train_tokens_per_second": 29188.674
    },
    {
      "epoch": 0.8399693060921215,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7220989072136676e-05,
      "loss": 1.0838644981384278,
      "num_input_tokens_seen": 6751487104,
      "step": 23740,
      "train_runtime": 231304.6279,
      "train_tokens_per_second": 29188.725
    },
    {
      "epoch": 0.8403231263558503,
      "grad_norm": 1.5078125,
      "learning_rate": 2.7216955914739385e-05,
      "loss": 1.091843032836914,
      "num_input_tokens_seen": 6754324864,
      "step": 23750,
      "train_runtime": 231402.0658,
      "train_tokens_per_second": 29188.697
    },
    {
      "epoch": 0.840676946619579,
      "grad_norm": 1.4765625,
      "learning_rate": 2.7212924549511348e-05,
      "loss": 1.0811660766601563,
      "num_input_tokens_seen": 6757160064,
      "step": 23760,
      "train_runtime": 231499.0573,
      "train_tokens_per_second": 29188.715
    },
    {
      "epoch": 0.8410307668833079,
      "grad_norm": 1.4453125,
      "learning_rate": 2.7208894975125688e-05,
      "loss": 1.1039216995239258,
      "num_input_tokens_seen": 6759985152,
      "step": 23770,
      "train_runtime": 231595.025,
      "train_tokens_per_second": 29188.819
    },
    {
      "epoch": 0.8413845871470367,
      "grad_norm": 1.4765625,
      "learning_rate": 2.720486719025689e-05,
      "loss": 1.0820953369140625,
      "num_input_tokens_seen": 6762899520,
      "step": 23780,
      "train_runtime": 231698.0318,
      "train_tokens_per_second": 29188.42
    },
    {
      "epoch": 0.8417384074107654,
      "grad_norm": 1.5390625,
      "learning_rate": 2.7200841193580816e-05,
      "loss": 1.0918209075927734,
      "num_input_tokens_seen": 6765737088,
      "step": 23790,
      "train_runtime": 231793.7778,
      "train_tokens_per_second": 29188.605
    },
    {
      "epoch": 0.8420922276744942,
      "grad_norm": 1.4453125,
      "learning_rate": 2.7196816983774708e-05,
      "loss": 1.0905494689941406,
      "num_input_tokens_seen": 6768535104,
      "step": 23800,
      "train_runtime": 231889.6833,
      "train_tokens_per_second": 29188.6
    },
    {
      "epoch": 0.842446047938223,
      "grad_norm": 1.4921875,
      "learning_rate": 2.7192794559517166e-05,
      "loss": 1.0850044250488282,
      "num_input_tokens_seen": 6771360384,
      "step": 23810,
      "train_runtime": 231985.3505,
      "train_tokens_per_second": 29188.741
    },
    {
      "epoch": 0.8427998682019517,
      "grad_norm": 1.453125,
      "learning_rate": 2.7188773919488165e-05,
      "loss": 1.0747900009155273,
      "num_input_tokens_seen": 6774220352,
      "step": 23820,
      "train_runtime": 232085.2691,
      "train_tokens_per_second": 29188.498
    },
    {
      "epoch": 0.8431536884656805,
      "grad_norm": 1.484375,
      "learning_rate": 2.7184755062369043e-05,
      "loss": 1.0913869857788085,
      "num_input_tokens_seen": 6777075840,
      "step": 23830,
      "train_runtime": 232185.0854,
      "train_tokens_per_second": 29188.248
    },
    {
      "epoch": 0.8435075087294093,
      "grad_norm": 1.484375,
      "learning_rate": 2.7180737986842498e-05,
      "loss": 1.0834657669067382,
      "num_input_tokens_seen": 6779957440,
      "step": 23840,
      "train_runtime": 232283.3646,
      "train_tokens_per_second": 29188.304
    },
    {
      "epoch": 0.8438613289931381,
      "grad_norm": 1.4921875,
      "learning_rate": 2.71767226915926e-05,
      "loss": 1.0889476776123046,
      "num_input_tokens_seen": 6782824192,
      "step": 23850,
      "train_runtime": 232382.1699,
      "train_tokens_per_second": 29188.23
    },
    {
      "epoch": 0.8442151492568669,
      "grad_norm": 1.4296875,
      "learning_rate": 2.7172709175304767e-05,
      "loss": 1.0833987236022948,
      "num_input_tokens_seen": 6785715776,
      "step": 23860,
      "train_runtime": 232479.9756,
      "train_tokens_per_second": 29188.388
    },
    {
      "epoch": 0.8445689695205957,
      "grad_norm": 1.5546875,
      "learning_rate": 2.716869743666579e-05,
      "loss": 1.0783214569091797,
      "num_input_tokens_seen": 6788554176,
      "step": 23870,
      "train_runtime": 232574.2907,
      "train_tokens_per_second": 29188.756
    },
    {
      "epoch": 0.8449227897843244,
      "grad_norm": 1.4453125,
      "learning_rate": 2.7164687474363803e-05,
      "loss": 1.0737434387207032,
      "num_input_tokens_seen": 6791387200,
      "step": 23880,
      "train_runtime": 232672.5081,
      "train_tokens_per_second": 29188.61
    },
    {
      "epoch": 0.8452766100480532,
      "grad_norm": 1.4765625,
      "learning_rate": 2.7160679287088307e-05,
      "loss": 1.0815143585205078,
      "num_input_tokens_seen": 6794182400,
      "step": 23890,
      "train_runtime": 232768.1337,
      "train_tokens_per_second": 29188.628
    },
    {
      "epoch": 0.845630430311782,
      "grad_norm": 1.5234375,
      "learning_rate": 2.7156672873530147e-05,
      "loss": 1.072005844116211,
      "num_input_tokens_seen": 6797066368,
      "step": 23900,
      "train_runtime": 232869.1749,
      "train_tokens_per_second": 29188.347
    },
    {
      "epoch": 0.8459842505755107,
      "grad_norm": 1.484375,
      "learning_rate": 2.715266823238152e-05,
      "loss": 1.0908548355102539,
      "num_input_tokens_seen": 6799884352,
      "step": 23910,
      "train_runtime": 232965.8717,
      "train_tokens_per_second": 29188.328
    },
    {
      "epoch": 0.8463380708392395,
      "grad_norm": 1.5390625,
      "learning_rate": 2.714866536233598e-05,
      "loss": 1.0767156600952148,
      "num_input_tokens_seen": 6802746560,
      "step": 23920,
      "train_runtime": 233064.4784,
      "train_tokens_per_second": 29188.26
    },
    {
      "epoch": 0.8466918911029684,
      "grad_norm": 1.4140625,
      "learning_rate": 2.7144664262088422e-05,
      "loss": 1.0972530364990234,
      "num_input_tokens_seen": 6805556800,
      "step": 23930,
      "train_runtime": 233159.2158,
      "train_tokens_per_second": 29188.453
    },
    {
      "epoch": 0.8470457113666972,
      "grad_norm": 1.4453125,
      "learning_rate": 2.7140664930335084e-05,
      "loss": 1.0831727027893066,
      "num_input_tokens_seen": 6808367872,
      "step": 23940,
      "train_runtime": 233254.4973,
      "train_tokens_per_second": 29188.581
    },
    {
      "epoch": 0.8473995316304259,
      "grad_norm": 1.46875,
      "learning_rate": 2.713666736577356e-05,
      "loss": 1.0744585037231444,
      "num_input_tokens_seen": 6811223296,
      "step": 23950,
      "train_runtime": 233352.4767,
      "train_tokens_per_second": 29188.562
    },
    {
      "epoch": 0.8477533518941547,
      "grad_norm": 1.546875,
      "learning_rate": 2.713267156710278e-05,
      "loss": 1.0840402603149415,
      "num_input_tokens_seen": 6814095104,
      "step": 23960,
      "train_runtime": 233450.3355,
      "train_tokens_per_second": 29188.628
    },
    {
      "epoch": 0.8481071721578834,
      "grad_norm": 1.4453125,
      "learning_rate": 2.712867753302301e-05,
      "loss": 1.081430149078369,
      "num_input_tokens_seen": 6816930432,
      "step": 23970,
      "train_runtime": 233547.7574,
      "train_tokens_per_second": 29188.593
    },
    {
      "epoch": 0.8484609924216122,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7124685262235865e-05,
      "loss": 1.0756324768066405,
      "num_input_tokens_seen": 6819820480,
      "step": 23980,
      "train_runtime": 233649.2415,
      "train_tokens_per_second": 29188.284
    },
    {
      "epoch": 0.848814812685341,
      "grad_norm": 1.546875,
      "learning_rate": 2.7120694753444287e-05,
      "loss": 1.0659494400024414,
      "num_input_tokens_seen": 6822655680,
      "step": 23990,
      "train_runtime": 233747.7772,
      "train_tokens_per_second": 29188.109
    },
    {
      "epoch": 0.8491686329490697,
      "grad_norm": 1.5703125,
      "learning_rate": 2.7116706005352547e-05,
      "loss": 1.0928373336791992,
      "num_input_tokens_seen": 6825531264,
      "step": 24000,
      "train_runtime": 233846.7193,
      "train_tokens_per_second": 29188.057
    },
    {
      "epoch": 0.8495224532127985,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7112719016666282e-05,
      "loss": 1.0766069412231445,
      "num_input_tokens_seen": 6828340608,
      "step": 24010,
      "train_runtime": 233943.377,
      "train_tokens_per_second": 29188.006
    },
    {
      "epoch": 0.8498762734765274,
      "grad_norm": 1.453125,
      "learning_rate": 2.7108733786092427e-05,
      "loss": 1.0779426574707032,
      "num_input_tokens_seen": 6831119424,
      "step": 24020,
      "train_runtime": 234038.7183,
      "train_tokens_per_second": 29187.989
    },
    {
      "epoch": 0.8502300937402562,
      "grad_norm": 1.4375,
      "learning_rate": 2.7104750312339254e-05,
      "loss": 1.0757341384887695,
      "num_input_tokens_seen": 6833910272,
      "step": 24030,
      "train_runtime": 234129.4955,
      "train_tokens_per_second": 29188.592
    },
    {
      "epoch": 0.8505839140039849,
      "grad_norm": 1.515625,
      "learning_rate": 2.7100768594116382e-05,
      "loss": 1.0879364013671875,
      "num_input_tokens_seen": 6836786432,
      "step": 24040,
      "train_runtime": 234226.2272,
      "train_tokens_per_second": 29188.817
    },
    {
      "epoch": 0.8509377342677137,
      "grad_norm": 1.4921875,
      "learning_rate": 2.709678863013473e-05,
      "loss": 1.0813230514526366,
      "num_input_tokens_seen": 6839663232,
      "step": 24050,
      "train_runtime": 234324.8211,
      "train_tokens_per_second": 29188.812
    },
    {
      "epoch": 0.8512915545314425,
      "grad_norm": 1.5,
      "learning_rate": 2.7092810419106562e-05,
      "loss": 1.0850580215454102,
      "num_input_tokens_seen": 6842474688,
      "step": 24060,
      "train_runtime": 234421.1302,
      "train_tokens_per_second": 29188.814
    },
    {
      "epoch": 0.8516453747951712,
      "grad_norm": 1.4453125,
      "learning_rate": 2.7088833959745457e-05,
      "loss": 1.068478775024414,
      "num_input_tokens_seen": 6845340864,
      "step": 24070,
      "train_runtime": 234521.1324,
      "train_tokens_per_second": 29188.589
    },
    {
      "epoch": 0.8519991950589,
      "grad_norm": 1.5,
      "learning_rate": 2.708485925076631e-05,
      "loss": 1.079576301574707,
      "num_input_tokens_seen": 6848187072,
      "step": 24080,
      "train_runtime": 234618.5427,
      "train_tokens_per_second": 29188.601
    },
    {
      "epoch": 0.8523530153226287,
      "grad_norm": 1.4609375,
      "learning_rate": 2.708088629088535e-05,
      "loss": 1.0959550857543945,
      "num_input_tokens_seen": 6851030336,
      "step": 24090,
      "train_runtime": 234714.019,
      "train_tokens_per_second": 29188.842
    },
    {
      "epoch": 0.8527068355863576,
      "grad_norm": 1.5703125,
      "learning_rate": 2.7076915078820115e-05,
      "loss": 1.0947162628173828,
      "num_input_tokens_seen": 6853932416,
      "step": 24100,
      "train_runtime": 234812.7552,
      "train_tokens_per_second": 29188.927
    },
    {
      "epoch": 0.8530606558500864,
      "grad_norm": 1.46875,
      "learning_rate": 2.707294561328945e-05,
      "loss": 1.0949834823608398,
      "num_input_tokens_seen": 6856750656,
      "step": 24110,
      "train_runtime": 234908.6978,
      "train_tokens_per_second": 29189.003
    },
    {
      "epoch": 0.8534144761138152,
      "grad_norm": 1.46875,
      "learning_rate": 2.706897789301353e-05,
      "loss": 1.0991998672485352,
      "num_input_tokens_seen": 6859575616,
      "step": 24120,
      "train_runtime": 235006.471,
      "train_tokens_per_second": 29188.88
    },
    {
      "epoch": 0.8537682963775439,
      "grad_norm": 1.4921875,
      "learning_rate": 2.706501191671384e-05,
      "loss": 1.0824554443359375,
      "num_input_tokens_seen": 6862452608,
      "step": 24130,
      "train_runtime": 235109.2691,
      "train_tokens_per_second": 29188.354
    },
    {
      "epoch": 0.8541221166412727,
      "grad_norm": 1.5078125,
      "learning_rate": 2.7061047683113165e-05,
      "loss": 1.075168991088867,
      "num_input_tokens_seen": 6865240064,
      "step": 24140,
      "train_runtime": 235203.2334,
      "train_tokens_per_second": 29188.545
    },
    {
      "epoch": 0.8544759369050015,
      "grad_norm": 1.46875,
      "learning_rate": 2.705708519093561e-05,
      "loss": 1.0751630783081054,
      "num_input_tokens_seen": 6868096128,
      "step": 24150,
      "train_runtime": 235298.3579,
      "train_tokens_per_second": 29188.883
    },
    {
      "epoch": 0.8548297571687302,
      "grad_norm": 1.4921875,
      "learning_rate": 2.705312443890658e-05,
      "loss": 1.0913986206054687,
      "num_input_tokens_seen": 6870921280,
      "step": 24160,
      "train_runtime": 235394.4129,
      "train_tokens_per_second": 29188.974
    },
    {
      "epoch": 0.855183577432459,
      "grad_norm": 1.4765625,
      "learning_rate": 2.70491654257528e-05,
      "loss": 1.0760330200195312,
      "num_input_tokens_seen": 6873722496,
      "step": 24170,
      "train_runtime": 235488.1594,
      "train_tokens_per_second": 29189.249
    },
    {
      "epoch": 0.8555373976961879,
      "grad_norm": 1.4609375,
      "learning_rate": 2.7045208150202274e-05,
      "loss": 1.0862226486206055,
      "num_input_tokens_seen": 6876630144,
      "step": 24180,
      "train_runtime": 235588.1074,
      "train_tokens_per_second": 29189.207
    },
    {
      "epoch": 0.8558912179599166,
      "grad_norm": 1.484375,
      "learning_rate": 2.704125261098433e-05,
      "loss": 1.0711069107055664,
      "num_input_tokens_seen": 6879503168,
      "step": 24190,
      "train_runtime": 235686.1825,
      "train_tokens_per_second": 29189.251
    },
    {
      "epoch": 0.8562450382236454,
      "grad_norm": 1.4921875,
      "learning_rate": 2.7037298806829586e-05,
      "loss": 1.0709022521972655,
      "num_input_tokens_seen": 6882324928,
      "step": 24200,
      "train_runtime": 235783.2484,
      "train_tokens_per_second": 29189.202
    },
    {
      "epoch": 0.8565988584873742,
      "grad_norm": 1.484375,
      "learning_rate": 2.7033346736469967e-05,
      "loss": 1.0856159210205079,
      "num_input_tokens_seen": 6885142784,
      "step": 24210,
      "train_runtime": 235879.7707,
      "train_tokens_per_second": 29189.204
    },
    {
      "epoch": 0.8569526787511029,
      "grad_norm": 1.484375,
      "learning_rate": 2.702939639863869e-05,
      "loss": 1.098006820678711,
      "num_input_tokens_seen": 6888005184,
      "step": 24220,
      "train_runtime": 235978.0144,
      "train_tokens_per_second": 29189.182
    },
    {
      "epoch": 0.8573064990148317,
      "grad_norm": 1.4453125,
      "learning_rate": 2.7025447792070262e-05,
      "loss": 1.0786596298217774,
      "num_input_tokens_seen": 6890802816,
      "step": 24230,
      "train_runtime": 236072.4919,
      "train_tokens_per_second": 29189.351
    },
    {
      "epoch": 0.8576603192785605,
      "grad_norm": 1.484375,
      "learning_rate": 2.7021500915500493e-05,
      "loss": 1.0907440185546875,
      "num_input_tokens_seen": 6893650624,
      "step": 24240,
      "train_runtime": 236168.2666,
      "train_tokens_per_second": 29189.572
    },
    {
      "epoch": 0.8580141395422892,
      "grad_norm": 1.5,
      "learning_rate": 2.701755576766648e-05,
      "loss": 1.0735344886779785,
      "num_input_tokens_seen": 6896463104,
      "step": 24250,
      "train_runtime": 236263.0594,
      "train_tokens_per_second": 29189.765
    },
    {
      "epoch": 0.858367959806018,
      "grad_norm": 1.4609375,
      "learning_rate": 2.701361234730661e-05,
      "loss": 1.0826171875,
      "num_input_tokens_seen": 6899282112,
      "step": 24260,
      "train_runtime": 236360.0342,
      "train_tokens_per_second": 29189.715
    },
    {
      "epoch": 0.8587217800697469,
      "grad_norm": 1.4296875,
      "learning_rate": 2.700967065316056e-05,
      "loss": 1.0902681350708008,
      "num_input_tokens_seen": 6902066688,
      "step": 24270,
      "train_runtime": 236452.9146,
      "train_tokens_per_second": 29190.026
    },
    {
      "epoch": 0.8590756003334756,
      "grad_norm": 1.4921875,
      "learning_rate": 2.70057306839693e-05,
      "loss": 1.0699932098388671,
      "num_input_tokens_seen": 6904942080,
      "step": 24280,
      "train_runtime": 236549.7838,
      "train_tokens_per_second": 29190.228
    },
    {
      "epoch": 0.8594294205972044,
      "grad_norm": 1.421875,
      "learning_rate": 2.7001792438475076e-05,
      "loss": 1.081153678894043,
      "num_input_tokens_seen": 6907759808,
      "step": 24290,
      "train_runtime": 236647.7366,
      "train_tokens_per_second": 29190.052
    },
    {
      "epoch": 0.8597832408609332,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6997855915421416e-05,
      "loss": 1.088338565826416,
      "num_input_tokens_seen": 6910643456,
      "step": 24300,
      "train_runtime": 236747.3366,
      "train_tokens_per_second": 29189.952
    },
    {
      "epoch": 0.8601370611246619,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6993921113553145e-05,
      "loss": 1.0780616760253907,
      "num_input_tokens_seen": 6913510976,
      "step": 24310,
      "train_runtime": 236847.6791,
      "train_tokens_per_second": 29189.693
    },
    {
      "epoch": 0.8604908813883907,
      "grad_norm": 1.5234375,
      "learning_rate": 2.6989988031616343e-05,
      "loss": 1.092308521270752,
      "num_input_tokens_seen": 6916365952,
      "step": 24320,
      "train_runtime": 236946.1861,
      "train_tokens_per_second": 29189.607
    },
    {
      "epoch": 0.8608447016521195,
      "grad_norm": 1.59375,
      "learning_rate": 2.6986056668358396e-05,
      "loss": 1.082712745666504,
      "num_input_tokens_seen": 6919160512,
      "step": 24330,
      "train_runtime": 237039.8672,
      "train_tokens_per_second": 29189.86
    },
    {
      "epoch": 0.8611985219158482,
      "grad_norm": 1.4765625,
      "learning_rate": 2.6982127022527947e-05,
      "loss": 1.086615753173828,
      "num_input_tokens_seen": 6921967232,
      "step": 24340,
      "train_runtime": 237133.169,
      "train_tokens_per_second": 29190.211
    },
    {
      "epoch": 0.8615523421795771,
      "grad_norm": 1.5078125,
      "learning_rate": 2.697819909287493e-05,
      "loss": 1.0909248352050782,
      "num_input_tokens_seen": 6924779200,
      "step": 24350,
      "train_runtime": 237228.649,
      "train_tokens_per_second": 29190.316
    },
    {
      "epoch": 0.8619061624433059,
      "grad_norm": 1.515625,
      "learning_rate": 2.697427287815053e-05,
      "loss": 1.0873506546020508,
      "num_input_tokens_seen": 6927630272,
      "step": 24360,
      "train_runtime": 237326.2851,
      "train_tokens_per_second": 29190.32
    },
    {
      "epoch": 0.8622599827070346,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6970348377107236e-05,
      "loss": 1.0783419609069824,
      "num_input_tokens_seen": 6930432384,
      "step": 24370,
      "train_runtime": 237421.5578,
      "train_tokens_per_second": 29190.409
    },
    {
      "epoch": 0.8626138029707634,
      "grad_norm": 1.4609375,
      "learning_rate": 2.696642558849877e-05,
      "loss": 1.0671567916870117,
      "num_input_tokens_seen": 6933254400,
      "step": 24380,
      "train_runtime": 237518.7061,
      "train_tokens_per_second": 29190.351
    },
    {
      "epoch": 0.8629676232344922,
      "grad_norm": 1.5703125,
      "learning_rate": 2.696250451108016e-05,
      "loss": 1.0788722038269043,
      "num_input_tokens_seen": 6936082688,
      "step": 24390,
      "train_runtime": 237614.6022,
      "train_tokens_per_second": 29190.473
    },
    {
      "epoch": 0.8633214434982209,
      "grad_norm": 1.46875,
      "learning_rate": 2.6958585143607662e-05,
      "loss": 1.0786075592041016,
      "num_input_tokens_seen": 6938952640,
      "step": 24400,
      "train_runtime": 237714.6555,
      "train_tokens_per_second": 29190.26
    },
    {
      "epoch": 0.8636752637619497,
      "grad_norm": 1.53125,
      "learning_rate": 2.695466748483883e-05,
      "loss": 1.0840526580810548,
      "num_input_tokens_seen": 6941816064,
      "step": 24410,
      "train_runtime": 237813.728,
      "train_tokens_per_second": 29190.14
    },
    {
      "epoch": 0.8640290840256785,
      "grad_norm": 1.5,
      "learning_rate": 2.695075153353247e-05,
      "loss": 1.0835630416870117,
      "num_input_tokens_seen": 6944680640,
      "step": 24420,
      "train_runtime": 237912.617,
      "train_tokens_per_second": 29190.048
    },
    {
      "epoch": 0.8643829042894073,
      "grad_norm": 1.546875,
      "learning_rate": 2.6946837288448646e-05,
      "loss": 1.098896598815918,
      "num_input_tokens_seen": 6947518400,
      "step": 24430,
      "train_runtime": 238010.1948,
      "train_tokens_per_second": 29190.003
    },
    {
      "epoch": 0.8647367245531361,
      "grad_norm": 1.515625,
      "learning_rate": 2.6942924748348684e-05,
      "loss": 1.069491481781006,
      "num_input_tokens_seen": 6950360640,
      "step": 24440,
      "train_runtime": 238108.9322,
      "train_tokens_per_second": 29189.836
    },
    {
      "epoch": 0.8650905448168649,
      "grad_norm": 1.4921875,
      "learning_rate": 2.693901391199517e-05,
      "loss": 1.087900733947754,
      "num_input_tokens_seen": 6953204544,
      "step": 24450,
      "train_runtime": 238208.6282,
      "train_tokens_per_second": 29189.558
    },
    {
      "epoch": 0.8654443650805936,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6935104778151943e-05,
      "loss": 1.0837324142456055,
      "num_input_tokens_seen": 6956102976,
      "step": 24460,
      "train_runtime": 238308.1457,
      "train_tokens_per_second": 29189.531
    },
    {
      "epoch": 0.8657981853443224,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6931197345584102e-05,
      "loss": 1.0930782318115235,
      "num_input_tokens_seen": 6958895232,
      "step": 24470,
      "train_runtime": 238402.9365,
      "train_tokens_per_second": 29189.637
    },
    {
      "epoch": 0.8661520056080512,
      "grad_norm": 1.4375,
      "learning_rate": 2.6927291613058003e-05,
      "loss": 1.0754700660705567,
      "num_input_tokens_seen": 6961713088,
      "step": 24480,
      "train_runtime": 238498.4904,
      "train_tokens_per_second": 29189.757
    },
    {
      "epoch": 0.8665058258717799,
      "grad_norm": 1.484375,
      "learning_rate": 2.6923387579341254e-05,
      "loss": 1.074538516998291,
      "num_input_tokens_seen": 6964551872,
      "step": 24490,
      "train_runtime": 238592.1189,
      "train_tokens_per_second": 29190.201
    },
    {
      "epoch": 0.8668596461355087,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6919485243202693e-05,
      "loss": 1.075462245941162,
      "num_input_tokens_seen": 6967388480,
      "step": 24500,
      "train_runtime": 238689.6123,
      "train_tokens_per_second": 29190.162
    },
    {
      "epoch": 0.8672134663992375,
      "grad_norm": 1.4140625,
      "learning_rate": 2.6915584603412434e-05,
      "loss": 1.0740318298339844,
      "num_input_tokens_seen": 6970218048,
      "step": 24510,
      "train_runtime": 238785.345,
      "train_tokens_per_second": 29190.309
    },
    {
      "epoch": 0.8675672866629663,
      "grad_norm": 1.5234375,
      "learning_rate": 2.6911685658741827e-05,
      "loss": 1.092128086090088,
      "num_input_tokens_seen": 6973067072,
      "step": 24520,
      "train_runtime": 238884.1443,
      "train_tokens_per_second": 29190.163
    },
    {
      "epoch": 0.8679211069266951,
      "grad_norm": 1.4765625,
      "learning_rate": 2.690778840796346e-05,
      "loss": 1.0855809211730958,
      "num_input_tokens_seen": 6975971712,
      "step": 24530,
      "train_runtime": 238983.7427,
      "train_tokens_per_second": 29190.152
    },
    {
      "epoch": 0.8682749271904239,
      "grad_norm": 1.46875,
      "learning_rate": 2.6903892849851175e-05,
      "loss": 1.0914899826049804,
      "num_input_tokens_seen": 6978857408,
      "step": 24540,
      "train_runtime": 239082.9346,
      "train_tokens_per_second": 29190.111
    },
    {
      "epoch": 0.8686287474541526,
      "grad_norm": 1.46875,
      "learning_rate": 2.6899998983180057e-05,
      "loss": 1.0806451797485352,
      "num_input_tokens_seen": 6981693952,
      "step": 24550,
      "train_runtime": 239179.7049,
      "train_tokens_per_second": 29190.16
    },
    {
      "epoch": 0.8689825677178814,
      "grad_norm": 1.5078125,
      "learning_rate": 2.689610680672642e-05,
      "loss": 1.0807291984558105,
      "num_input_tokens_seen": 6984531072,
      "step": 24560,
      "train_runtime": 239276.1369,
      "train_tokens_per_second": 29190.253
    },
    {
      "epoch": 0.8693363879816102,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6892216319267843e-05,
      "loss": 1.0879636764526368,
      "num_input_tokens_seen": 6987390016,
      "step": 24570,
      "train_runtime": 239374.7435,
      "train_tokens_per_second": 29190.172
    },
    {
      "epoch": 0.8696902082453389,
      "grad_norm": 1.515625,
      "learning_rate": 2.6888327519583107e-05,
      "loss": 1.0862504959106445,
      "num_input_tokens_seen": 6990256832,
      "step": 24580,
      "train_runtime": 239474.2903,
      "train_tokens_per_second": 29190.01
    },
    {
      "epoch": 0.8700440285090677,
      "grad_norm": 1.46875,
      "learning_rate": 2.688444040645225e-05,
      "loss": 1.0749689102172852,
      "num_input_tokens_seen": 6993125056,
      "step": 24590,
      "train_runtime": 239573.6276,
      "train_tokens_per_second": 29189.878
    },
    {
      "epoch": 0.8703978487727966,
      "grad_norm": 1.4140625,
      "learning_rate": 2.688055497865654e-05,
      "loss": 1.09580078125,
      "num_input_tokens_seen": 6995943936,
      "step": 24600,
      "train_runtime": 239668.9823,
      "train_tokens_per_second": 29190.026
    },
    {
      "epoch": 0.8707516690365253,
      "grad_norm": 1.484375,
      "learning_rate": 2.6876671234978483e-05,
      "loss": 1.0815733909606933,
      "num_input_tokens_seen": 6998836736,
      "step": 24610,
      "train_runtime": 239771.7174,
      "train_tokens_per_second": 29189.584
    },
    {
      "epoch": 0.8711054893002541,
      "grad_norm": 1.4453125,
      "learning_rate": 2.6872789174201807e-05,
      "loss": 1.0890100479125977,
      "num_input_tokens_seen": 7001703360,
      "step": 24620,
      "train_runtime": 239871.773,
      "train_tokens_per_second": 29189.359
    },
    {
      "epoch": 0.8714593095639829,
      "grad_norm": 1.53125,
      "learning_rate": 2.686890879511147e-05,
      "loss": 1.0821913719177245,
      "num_input_tokens_seen": 7004562624,
      "step": 24630,
      "train_runtime": 239972.4569,
      "train_tokens_per_second": 29189.027
    },
    {
      "epoch": 0.8718131298277116,
      "grad_norm": 1.5,
      "learning_rate": 2.6865030096493665e-05,
      "loss": 1.0964225769042968,
      "num_input_tokens_seen": 7007431616,
      "step": 24640,
      "train_runtime": 240071.8713,
      "train_tokens_per_second": 29188.891
    },
    {
      "epoch": 0.8721669500914404,
      "grad_norm": 1.5390625,
      "learning_rate": 2.6861153077135815e-05,
      "loss": 1.0850180625915526,
      "num_input_tokens_seen": 7010275584,
      "step": 24650,
      "train_runtime": 240169.036,
      "train_tokens_per_second": 29188.923
    },
    {
      "epoch": 0.8725207703551692,
      "grad_norm": 1.484375,
      "learning_rate": 2.6857277735826545e-05,
      "loss": 1.0880144119262696,
      "num_input_tokens_seen": 7013106304,
      "step": 24660,
      "train_runtime": 240265.1603,
      "train_tokens_per_second": 29189.027
    },
    {
      "epoch": 0.8728745906188979,
      "grad_norm": 1.46875,
      "learning_rate": 2.685340407135573e-05,
      "loss": 1.080960178375244,
      "num_input_tokens_seen": 7016033600,
      "step": 24670,
      "train_runtime": 240368.0185,
      "train_tokens_per_second": 29188.715
    },
    {
      "epoch": 0.8732284108826268,
      "grad_norm": 1.515625,
      "learning_rate": 2.6849532082514445e-05,
      "loss": 1.076182746887207,
      "num_input_tokens_seen": 7018875776,
      "step": 24680,
      "train_runtime": 240465.6459,
      "train_tokens_per_second": 29188.684
    },
    {
      "epoch": 0.8735822311463556,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6845661768095005e-05,
      "loss": 1.075659942626953,
      "num_input_tokens_seen": 7021816512,
      "step": 24690,
      "train_runtime": 240568.7628,
      "train_tokens_per_second": 29188.397
    },
    {
      "epoch": 0.8739360514100843,
      "grad_norm": 1.5,
      "learning_rate": 2.6841793126890925e-05,
      "loss": 1.0824756622314453,
      "num_input_tokens_seen": 7024625344,
      "step": 24700,
      "train_runtime": 240661.7039,
      "train_tokens_per_second": 29188.796
    },
    {
      "epoch": 0.8742898716738131,
      "grad_norm": 1.4609375,
      "learning_rate": 2.6837926157696946e-05,
      "loss": 1.0706636428833007,
      "num_input_tokens_seen": 7027444544,
      "step": 24710,
      "train_runtime": 240760.9186,
      "train_tokens_per_second": 29188.477
    },
    {
      "epoch": 0.8746436919375419,
      "grad_norm": 1.53125,
      "learning_rate": 2.6834060859309018e-05,
      "loss": 1.0804738044738769,
      "num_input_tokens_seen": 7030291968,
      "step": 24720,
      "train_runtime": 240857.1844,
      "train_tokens_per_second": 29188.633
    },
    {
      "epoch": 0.8749975122012706,
      "grad_norm": 1.4375,
      "learning_rate": 2.6830197230524317e-05,
      "loss": 1.0731182098388672,
      "num_input_tokens_seen": 7033122624,
      "step": 24730,
      "train_runtime": 240950.6518,
      "train_tokens_per_second": 29189.058
    },
    {
      "epoch": 0.8753513324649994,
      "grad_norm": 1.453125,
      "learning_rate": 2.6826335270141216e-05,
      "loss": 1.0789525985717774,
      "num_input_tokens_seen": 7036029120,
      "step": 24740,
      "train_runtime": 241053.5898,
      "train_tokens_per_second": 29188.651
    },
    {
      "epoch": 0.8757051527287282,
      "grad_norm": 1.46875,
      "learning_rate": 2.6822474976959312e-05,
      "loss": 1.0889410018920898,
      "num_input_tokens_seen": 7038888256,
      "step": 24750,
      "train_runtime": 241152.9983,
      "train_tokens_per_second": 29188.475
    },
    {
      "epoch": 0.8760589729924569,
      "grad_norm": 1.515625,
      "learning_rate": 2.6818616349779397e-05,
      "loss": 1.0873723030090332,
      "num_input_tokens_seen": 7041737792,
      "step": 24760,
      "train_runtime": 241250.3633,
      "train_tokens_per_second": 29188.506
    },
    {
      "epoch": 0.8764127932561858,
      "grad_norm": 1.515625,
      "learning_rate": 2.6814759387403482e-05,
      "loss": 1.0853837966918944,
      "num_input_tokens_seen": 7044557952,
      "step": 24770,
      "train_runtime": 241349.1278,
      "train_tokens_per_second": 29188.247
    },
    {
      "epoch": 0.8767666135199146,
      "grad_norm": 1.5078125,
      "learning_rate": 2.681090408863477e-05,
      "loss": 1.0883296966552733,
      "num_input_tokens_seen": 7047406528,
      "step": 24780,
      "train_runtime": 241449.3234,
      "train_tokens_per_second": 29187.932
    },
    {
      "epoch": 0.8771204337836433,
      "grad_norm": 1.4765625,
      "learning_rate": 2.6807050452277694e-05,
      "loss": 1.0750125885009765,
      "num_input_tokens_seen": 7050232384,
      "step": 24790,
      "train_runtime": 241544.1102,
      "train_tokens_per_second": 29188.178
    },
    {
      "epoch": 0.8774742540473721,
      "grad_norm": 1.5,
      "learning_rate": 2.6803198477137853e-05,
      "loss": 1.073841667175293,
      "num_input_tokens_seen": 7053055232,
      "step": 24800,
      "train_runtime": 241639.5396,
      "train_tokens_per_second": 29188.333
    },
    {
      "epoch": 0.8778280743111009,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6799348162022082e-05,
      "loss": 1.0776921272277833,
      "num_input_tokens_seen": 7055884096,
      "step": 24810,
      "train_runtime": 241735.9141,
      "train_tokens_per_second": 29188.398
    },
    {
      "epoch": 0.8781818945748296,
      "grad_norm": 1.46875,
      "learning_rate": 2.6795499505738397e-05,
      "loss": 1.0809947013854981,
      "num_input_tokens_seen": 7058721152,
      "step": 24820,
      "train_runtime": 241832.6971,
      "train_tokens_per_second": 29188.448
    },
    {
      "epoch": 0.8785357148385584,
      "grad_norm": 1.546875,
      "learning_rate": 2.679165250709601e-05,
      "loss": 1.0843608856201172,
      "num_input_tokens_seen": 7061523712,
      "step": 24830,
      "train_runtime": 241929.2114,
      "train_tokens_per_second": 29188.388
    },
    {
      "epoch": 0.8788895351022872,
      "grad_norm": 1.4765625,
      "learning_rate": 2.678780716490533e-05,
      "loss": 1.083354377746582,
      "num_input_tokens_seen": 7064400064,
      "step": 24840,
      "train_runtime": 242030.1901,
      "train_tokens_per_second": 29188.095
    },
    {
      "epoch": 0.879243355366016,
      "grad_norm": 1.484375,
      "learning_rate": 2.678396347797798e-05,
      "loss": 1.0801756858825684,
      "num_input_tokens_seen": 7067241536,
      "step": 24850,
      "train_runtime": 242125.585,
      "train_tokens_per_second": 29188.33
    },
    {
      "epoch": 0.8795971756297448,
      "grad_norm": 1.453125,
      "learning_rate": 2.6780121445126756e-05,
      "loss": 1.083262825012207,
      "num_input_tokens_seen": 7070086080,
      "step": 24860,
      "train_runtime": 242222.8888,
      "train_tokens_per_second": 29188.348
    },
    {
      "epoch": 0.8799509958934736,
      "grad_norm": 1.484375,
      "learning_rate": 2.6776281065165644e-05,
      "loss": 1.0719333648681642,
      "num_input_tokens_seen": 7072959040,
      "step": 24870,
      "train_runtime": 242321.6707,
      "train_tokens_per_second": 29188.306
    },
    {
      "epoch": 0.8803048161572024,
      "grad_norm": 1.4453125,
      "learning_rate": 2.677244233690983e-05,
      "loss": 1.083949661254883,
      "num_input_tokens_seen": 7075815808,
      "step": 24880,
      "train_runtime": 242420.6619,
      "train_tokens_per_second": 29188.171
    },
    {
      "epoch": 0.8806586364209311,
      "grad_norm": 1.53125,
      "learning_rate": 2.6768605259175694e-05,
      "loss": 1.080158805847168,
      "num_input_tokens_seen": 7078660800,
      "step": 24890,
      "train_runtime": 242520.2304,
      "train_tokens_per_second": 29187.919
    },
    {
      "epoch": 0.8810124566846599,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6764769830780784e-05,
      "loss": 1.0854487419128418,
      "num_input_tokens_seen": 7081475520,
      "step": 24900,
      "train_runtime": 242613.439,
      "train_tokens_per_second": 29188.307
    },
    {
      "epoch": 0.8813662769483886,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6760936050543857e-05,
      "loss": 1.0771869659423827,
      "num_input_tokens_seen": 7084299776,
      "step": 24910,
      "train_runtime": 242708.6528,
      "train_tokens_per_second": 29188.493
    },
    {
      "epoch": 0.8817200972121174,
      "grad_norm": 1.5,
      "learning_rate": 2.675710391728483e-05,
      "loss": 1.0804795265197753,
      "num_input_tokens_seen": 7087195264,
      "step": 24920,
      "train_runtime": 242808.9221,
      "train_tokens_per_second": 29188.364
    },
    {
      "epoch": 0.8820739174758463,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6753273429824822e-05,
      "loss": 1.090805435180664,
      "num_input_tokens_seen": 7090094592,
      "step": 24930,
      "train_runtime": 242907.5836,
      "train_tokens_per_second": 29188.445
    },
    {
      "epoch": 0.8824277377395751,
      "grad_norm": 1.5,
      "learning_rate": 2.6749444586986127e-05,
      "loss": 1.086817455291748,
      "num_input_tokens_seen": 7092936384,
      "step": 24940,
      "train_runtime": 243004.393,
      "train_tokens_per_second": 29188.511
    },
    {
      "epoch": 0.8827815580033038,
      "grad_norm": 1.515625,
      "learning_rate": 2.6745617387592214e-05,
      "loss": 1.081374168395996,
      "num_input_tokens_seen": 7095776448,
      "step": 24950,
      "train_runtime": 243099.6345,
      "train_tokens_per_second": 29188.758
    },
    {
      "epoch": 0.8831353782670326,
      "grad_norm": 1.515625,
      "learning_rate": 2.6741791830467728e-05,
      "loss": 1.0765195846557618,
      "num_input_tokens_seen": 7098612160,
      "step": 24960,
      "train_runtime": 243196.0411,
      "train_tokens_per_second": 29188.848
    },
    {
      "epoch": 0.8834891985307614,
      "grad_norm": 1.4140625,
      "learning_rate": 2.67379679144385e-05,
      "loss": 1.066823959350586,
      "num_input_tokens_seen": 7101494464,
      "step": 24970,
      "train_runtime": 243294.953,
      "train_tokens_per_second": 29188.828
    },
    {
      "epoch": 0.8838430187944901,
      "grad_norm": 1.453125,
      "learning_rate": 2.6734145638331536e-05,
      "loss": 1.0808423995971679,
      "num_input_tokens_seen": 7104353216,
      "step": 24980,
      "train_runtime": 243394.3763,
      "train_tokens_per_second": 29188.65
    },
    {
      "epoch": 0.8841968390582189,
      "grad_norm": 1.4765625,
      "learning_rate": 2.673032500097501e-05,
      "loss": 1.0944605827331544,
      "num_input_tokens_seen": 7107186624,
      "step": 24990,
      "train_runtime": 243490.1142,
      "train_tokens_per_second": 29188.81
    },
    {
      "epoch": 0.8845506593219477,
      "grad_norm": 1.5078125,
      "learning_rate": 2.672650600119826e-05,
      "loss": 1.0927881240844726,
      "num_input_tokens_seen": 7110093696,
      "step": 25000,
      "train_runtime": 243591.6987,
      "train_tokens_per_second": 29188.571
    },
    {
      "epoch": 0.8845506593219477,
      "eval_loss": 1.023461103439331,
      "eval_runtime": 8.4538,
      "eval_samples_per_second": 471.741,
      "eval_steps_per_second": 3.785,
      "num_input_tokens_seen": 7110093696,
      "step": 25000
    },
    {
      "epoch": 0.8849044795856764,
      "grad_norm": 1.515625,
      "learning_rate": 2.672268863783181e-05,
      "loss": 1.0820868492126465,
      "num_input_tokens_seen": 7112954752,
      "step": 25010,
      "train_runtime": 243720.1139,
      "train_tokens_per_second": 29184.931
    },
    {
      "epoch": 0.8852582998494053,
      "grad_norm": 1.46875,
      "learning_rate": 2.6718872909707347e-05,
      "loss": 1.0855422019958496,
      "num_input_tokens_seen": 7115726848,
      "step": 25020,
      "train_runtime": 243811.1186,
      "train_tokens_per_second": 29185.407
    },
    {
      "epoch": 0.8856121201131341,
      "grad_norm": 1.5,
      "learning_rate": 2.671505881565772e-05,
      "loss": 1.0735036849975585,
      "num_input_tokens_seen": 7118565376,
      "step": 25030,
      "train_runtime": 243909.476,
      "train_tokens_per_second": 29185.276
    },
    {
      "epoch": 0.8859659403768628,
      "grad_norm": 1.5390625,
      "learning_rate": 2.671124635451696e-05,
      "loss": 1.0760697364807128,
      "num_input_tokens_seen": 7121407552,
      "step": 25040,
      "train_runtime": 244005.8084,
      "train_tokens_per_second": 29185.402
    },
    {
      "epoch": 0.8863197606405916,
      "grad_norm": 1.4765625,
      "learning_rate": 2.6707435525120237e-05,
      "loss": 1.087644386291504,
      "num_input_tokens_seen": 7124235968,
      "step": 25050,
      "train_runtime": 244103.4799,
      "train_tokens_per_second": 29185.311
    },
    {
      "epoch": 0.8866735809043204,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6703626326303906e-05,
      "loss": 1.0907632827758789,
      "num_input_tokens_seen": 7127074624,
      "step": 25060,
      "train_runtime": 244201.7598,
      "train_tokens_per_second": 29185.189
    },
    {
      "epoch": 0.8870274011680491,
      "grad_norm": 1.515625,
      "learning_rate": 2.669981875690547e-05,
      "loss": 1.084065055847168,
      "num_input_tokens_seen": 7129976704,
      "step": 25070,
      "train_runtime": 244301.3048,
      "train_tokens_per_second": 29185.177
    },
    {
      "epoch": 0.8873812214317779,
      "grad_norm": 1.453125,
      "learning_rate": 2.6696012815763604e-05,
      "loss": 1.0855453491210938,
      "num_input_tokens_seen": 7132845120,
      "step": 25080,
      "train_runtime": 244402.9778,
      "train_tokens_per_second": 29184.772
    },
    {
      "epoch": 0.8877350416955067,
      "grad_norm": 1.4921875,
      "learning_rate": 2.669220850171813e-05,
      "loss": 1.0917444229125977,
      "num_input_tokens_seen": 7135742464,
      "step": 25090,
      "train_runtime": 244502.0565,
      "train_tokens_per_second": 29184.795
    },
    {
      "epoch": 0.8880888619592355,
      "grad_norm": 1.5,
      "learning_rate": 2.668840581361003e-05,
      "loss": 1.0945510864257812,
      "num_input_tokens_seen": 7138578432,
      "step": 25100,
      "train_runtime": 244597.8626,
      "train_tokens_per_second": 29184.958
    },
    {
      "epoch": 0.8884426822229643,
      "grad_norm": 1.4921875,
      "learning_rate": 2.668460475028145e-05,
      "loss": 1.0809709548950195,
      "num_input_tokens_seen": 7141411008,
      "step": 25110,
      "train_runtime": 244694.9135,
      "train_tokens_per_second": 29184.959
    },
    {
      "epoch": 0.8887965024866931,
      "grad_norm": 1.546875,
      "learning_rate": 2.6680805310575686e-05,
      "loss": 1.0810720443725585,
      "num_input_tokens_seen": 7144279872,
      "step": 25120,
      "train_runtime": 244795.5105,
      "train_tokens_per_second": 29184.685
    },
    {
      "epoch": 0.8891503227504218,
      "grad_norm": 1.515625,
      "learning_rate": 2.6677007493337164e-05,
      "loss": 1.075914192199707,
      "num_input_tokens_seen": 7147075776,
      "step": 25130,
      "train_runtime": 244889.5229,
      "train_tokens_per_second": 29184.898
    },
    {
      "epoch": 0.8895041430141506,
      "grad_norm": 1.5,
      "learning_rate": 2.6673211297411503e-05,
      "loss": 1.0719465255737304,
      "num_input_tokens_seen": 7149911360,
      "step": 25140,
      "train_runtime": 244986.1548,
      "train_tokens_per_second": 29184.961
    },
    {
      "epoch": 0.8898579632778794,
      "grad_norm": 1.546875,
      "learning_rate": 2.6669416721645447e-05,
      "loss": 1.0775411605834961,
      "num_input_tokens_seen": 7152746304,
      "step": 25150,
      "train_runtime": 245081.8446,
      "train_tokens_per_second": 29185.133
    },
    {
      "epoch": 0.8902117835416081,
      "grad_norm": 1.484375,
      "learning_rate": 2.6665623764886876e-05,
      "loss": 1.0747762680053712,
      "num_input_tokens_seen": 7155609408,
      "step": 25160,
      "train_runtime": 245181.4255,
      "train_tokens_per_second": 29184.957
    },
    {
      "epoch": 0.8905656038053369,
      "grad_norm": 1.546875,
      "learning_rate": 2.6661832425984847e-05,
      "loss": 1.0630716323852538,
      "num_input_tokens_seen": 7158470784,
      "step": 25170,
      "train_runtime": 245281.5406,
      "train_tokens_per_second": 29184.711
    },
    {
      "epoch": 0.8909194240690658,
      "grad_norm": 1.4921875,
      "learning_rate": 2.665804270378953e-05,
      "loss": 1.0947274208068847,
      "num_input_tokens_seen": 7161297344,
      "step": 25180,
      "train_runtime": 245379.6795,
      "train_tokens_per_second": 29184.557
    },
    {
      "epoch": 0.8912732443327945,
      "grad_norm": 1.4609375,
      "learning_rate": 2.665425459715228e-05,
      "loss": 1.0680038452148437,
      "num_input_tokens_seen": 7164144192,
      "step": 25190,
      "train_runtime": 245478.0936,
      "train_tokens_per_second": 29184.454
    },
    {
      "epoch": 0.8916270645965233,
      "grad_norm": 1.4140625,
      "learning_rate": 2.6650468104925547e-05,
      "loss": 1.0844810485839844,
      "num_input_tokens_seen": 7167005376,
      "step": 25200,
      "train_runtime": 245575.9154,
      "train_tokens_per_second": 29184.48
    },
    {
      "epoch": 0.8919808848602521,
      "grad_norm": 1.4453125,
      "learning_rate": 2.664668322596295e-05,
      "loss": 1.0924552917480468,
      "num_input_tokens_seen": 7169872000,
      "step": 25210,
      "train_runtime": 245676.5425,
      "train_tokens_per_second": 29184.194
    },
    {
      "epoch": 0.8923347051239808,
      "grad_norm": 1.4609375,
      "learning_rate": 2.664289995911925e-05,
      "loss": 1.0814663887023925,
      "num_input_tokens_seen": 7172743232,
      "step": 25220,
      "train_runtime": 245774.7289,
      "train_tokens_per_second": 29184.218
    },
    {
      "epoch": 0.8926885253877096,
      "grad_norm": 1.5,
      "learning_rate": 2.6639118303250328e-05,
      "loss": 1.0901309967041015,
      "num_input_tokens_seen": 7175549440,
      "step": 25230,
      "train_runtime": 245870.464,
      "train_tokens_per_second": 29184.268
    },
    {
      "epoch": 0.8930423456514384,
      "grad_norm": 1.484375,
      "learning_rate": 2.663533825721321e-05,
      "loss": 1.0798226356506349,
      "num_input_tokens_seen": 7178427264,
      "step": 25240,
      "train_runtime": 245973.191,
      "train_tokens_per_second": 29183.779
    },
    {
      "epoch": 0.8933961659151671,
      "grad_norm": 1.5234375,
      "learning_rate": 2.6631559819866065e-05,
      "loss": 1.0817352294921876,
      "num_input_tokens_seen": 7181239232,
      "step": 25250,
      "train_runtime": 246068.3741,
      "train_tokens_per_second": 29183.918
    },
    {
      "epoch": 0.8937499861788959,
      "grad_norm": 1.4921875,
      "learning_rate": 2.662778299006819e-05,
      "loss": 1.0886592864990234,
      "num_input_tokens_seen": 7184113536,
      "step": 25260,
      "train_runtime": 246166.7593,
      "train_tokens_per_second": 29183.93
    },
    {
      "epoch": 0.8941038064426248,
      "grad_norm": 1.515625,
      "learning_rate": 2.6624007766680004e-05,
      "loss": 1.0795515060424805,
      "num_input_tokens_seen": 7186963200,
      "step": 25270,
      "train_runtime": 246262.8267,
      "train_tokens_per_second": 29184.117
    },
    {
      "epoch": 0.8944576267063535,
      "grad_norm": 1.4765625,
      "learning_rate": 2.6620234148563066e-05,
      "loss": 1.0838384628295898,
      "num_input_tokens_seen": 7189763328,
      "step": 25280,
      "train_runtime": 246357.9389,
      "train_tokens_per_second": 29184.216
    },
    {
      "epoch": 0.8948114469700823,
      "grad_norm": 1.4140625,
      "learning_rate": 2.6616462134580072e-05,
      "loss": 1.065964698791504,
      "num_input_tokens_seen": 7192593280,
      "step": 25290,
      "train_runtime": 246455.5212,
      "train_tokens_per_second": 29184.143
    },
    {
      "epoch": 0.8951652672338111,
      "grad_norm": 1.46875,
      "learning_rate": 2.6612691723594835e-05,
      "loss": 1.0664762496948241,
      "num_input_tokens_seen": 7195397888,
      "step": 25300,
      "train_runtime": 246550.8968,
      "train_tokens_per_second": 29184.229
    },
    {
      "epoch": 0.8955190874975398,
      "grad_norm": 1.484375,
      "learning_rate": 2.6608922914472283e-05,
      "loss": 1.0739008903503418,
      "num_input_tokens_seen": 7198229056,
      "step": 25310,
      "train_runtime": 246647.4637,
      "train_tokens_per_second": 29184.282
    },
    {
      "epoch": 0.8958729077612686,
      "grad_norm": 1.453125,
      "learning_rate": 2.66051557060785e-05,
      "loss": 1.0971456527709962,
      "num_input_tokens_seen": 7200989056,
      "step": 25320,
      "train_runtime": 246739.0074,
      "train_tokens_per_second": 29184.64
    },
    {
      "epoch": 0.8962267280249974,
      "grad_norm": 1.484375,
      "learning_rate": 2.6601390097280665e-05,
      "loss": 1.0726150512695312,
      "num_input_tokens_seen": 7203796608,
      "step": 25330,
      "train_runtime": 246835.5655,
      "train_tokens_per_second": 29184.597
    },
    {
      "epoch": 0.8965805482887261,
      "grad_norm": 1.4453125,
      "learning_rate": 2.6597626086947097e-05,
      "loss": 1.0842613220214843,
      "num_input_tokens_seen": 7206658048,
      "step": 25340,
      "train_runtime": 246934.1662,
      "train_tokens_per_second": 29184.532
    },
    {
      "epoch": 0.896934368552455,
      "grad_norm": 1.4765625,
      "learning_rate": 2.659386367394722e-05,
      "loss": 1.0856489181518554,
      "num_input_tokens_seen": 7209520704,
      "step": 25350,
      "train_runtime": 247032.273,
      "train_tokens_per_second": 29184.53
    },
    {
      "epoch": 0.8972881888161838,
      "grad_norm": 1.5,
      "learning_rate": 2.65901028571516e-05,
      "loss": 1.0777853012084961,
      "num_input_tokens_seen": 7212382976,
      "step": 25360,
      "train_runtime": 247130.7074,
      "train_tokens_per_second": 29184.487
    },
    {
      "epoch": 0.8976420090799125,
      "grad_norm": 1.46875,
      "learning_rate": 2.6586343635431887e-05,
      "loss": 1.0753351211547852,
      "num_input_tokens_seen": 7215223936,
      "step": 25370,
      "train_runtime": 247226.8554,
      "train_tokens_per_second": 29184.629
    },
    {
      "epoch": 0.8979958293436413,
      "grad_norm": 1.5390625,
      "learning_rate": 2.658258600766088e-05,
      "loss": 1.0863506317138671,
      "num_input_tokens_seen": 7218056128,
      "step": 25380,
      "train_runtime": 247322.1342,
      "train_tokens_per_second": 29184.837
    },
    {
      "epoch": 0.8983496496073701,
      "grad_norm": 1.515625,
      "learning_rate": 2.657882997271247e-05,
      "loss": 1.0970540046691895,
      "num_input_tokens_seen": 7220825728,
      "step": 25390,
      "train_runtime": 247413.596,
      "train_tokens_per_second": 29185.242
    },
    {
      "epoch": 0.8987034698710988,
      "grad_norm": 1.453125,
      "learning_rate": 2.6575075529461685e-05,
      "loss": 1.0809480667114257,
      "num_input_tokens_seen": 7223679360,
      "step": 25400,
      "train_runtime": 247513.4826,
      "train_tokens_per_second": 29184.993
    },
    {
      "epoch": 0.8990572901348276,
      "grad_norm": 1.5,
      "learning_rate": 2.657132267678464e-05,
      "loss": 1.0871879577636718,
      "num_input_tokens_seen": 7226557696,
      "step": 25410,
      "train_runtime": 247613.1079,
      "train_tokens_per_second": 29184.875
    },
    {
      "epoch": 0.8994111103985564,
      "grad_norm": 1.484375,
      "learning_rate": 2.656757141355857e-05,
      "loss": 1.0866841316223144,
      "num_input_tokens_seen": 7229419072,
      "step": 25420,
      "train_runtime": 247713.6701,
      "train_tokens_per_second": 29184.579
    },
    {
      "epoch": 0.8997649306622852,
      "grad_norm": 1.4375,
      "learning_rate": 2.6563821738661833e-05,
      "loss": 1.076329803466797,
      "num_input_tokens_seen": 7232323200,
      "step": 25430,
      "train_runtime": 247812.5539,
      "train_tokens_per_second": 29184.652
    },
    {
      "epoch": 0.900118750926014,
      "grad_norm": 1.4296875,
      "learning_rate": 2.6560073650973873e-05,
      "loss": 1.0857110023498535,
      "num_input_tokens_seen": 7235181440,
      "step": 25440,
      "train_runtime": 247908.9608,
      "train_tokens_per_second": 29184.832
    },
    {
      "epoch": 0.9004725711897428,
      "grad_norm": 1.484375,
      "learning_rate": 2.655632714937525e-05,
      "loss": 1.0765920639038087,
      "num_input_tokens_seen": 7238069568,
      "step": 25450,
      "train_runtime": 248008.5125,
      "train_tokens_per_second": 29184.763
    },
    {
      "epoch": 0.9008263914534715,
      "grad_norm": 1.5234375,
      "learning_rate": 2.6552582232747637e-05,
      "loss": 1.0810518264770508,
      "num_input_tokens_seen": 7240984192,
      "step": 25460,
      "train_runtime": 248109.8195,
      "train_tokens_per_second": 29184.593
    },
    {
      "epoch": 0.9011802117172003,
      "grad_norm": 1.53125,
      "learning_rate": 2.6548838899973794e-05,
      "loss": 1.082456398010254,
      "num_input_tokens_seen": 7243801856,
      "step": 25470,
      "train_runtime": 248205.6738,
      "train_tokens_per_second": 29184.675
    },
    {
      "epoch": 0.9015340319809291,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6545097149937598e-05,
      "loss": 1.0678675651550293,
      "num_input_tokens_seen": 7246685504,
      "step": 25480,
      "train_runtime": 248307.6994,
      "train_tokens_per_second": 29184.296
    },
    {
      "epoch": 0.9018878522446578,
      "grad_norm": 1.53125,
      "learning_rate": 2.6541356981524018e-05,
      "loss": 1.082634162902832,
      "num_input_tokens_seen": 7249484288,
      "step": 25490,
      "train_runtime": 248403.2319,
      "train_tokens_per_second": 29184.34
    },
    {
      "epoch": 0.9022416725083866,
      "grad_norm": 1.5703125,
      "learning_rate": 2.653761839361913e-05,
      "loss": 1.079379940032959,
      "num_input_tokens_seen": 7252360000,
      "step": 25500,
      "train_runtime": 248502.5914,
      "train_tokens_per_second": 29184.243
    },
    {
      "epoch": 0.9025954927721154,
      "grad_norm": 1.5,
      "learning_rate": 2.6533881385110097e-05,
      "loss": 1.076802635192871,
      "num_input_tokens_seen": 7255188736,
      "step": 25510,
      "train_runtime": 248598.4963,
      "train_tokens_per_second": 29184.363
    },
    {
      "epoch": 0.9029493130358442,
      "grad_norm": 1.5546875,
      "learning_rate": 2.6530145954885187e-05,
      "loss": 1.0867416381835937,
      "num_input_tokens_seen": 7258065280,
      "step": 25520,
      "train_runtime": 248697.0814,
      "train_tokens_per_second": 29184.361
    },
    {
      "epoch": 0.903303133299573,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6526412101833764e-05,
      "loss": 1.087068748474121,
      "num_input_tokens_seen": 7260926016,
      "step": 25530,
      "train_runtime": 248794.1386,
      "train_tokens_per_second": 29184.474
    },
    {
      "epoch": 0.9036569535633018,
      "grad_norm": 1.46875,
      "learning_rate": 2.6522679824846287e-05,
      "loss": 1.0725414276123046,
      "num_input_tokens_seen": 7263808640,
      "step": 25540,
      "train_runtime": 248892.3637,
      "train_tokens_per_second": 29184.538
    },
    {
      "epoch": 0.9040107738270305,
      "grad_norm": 1.4609375,
      "learning_rate": 2.6518949122814297e-05,
      "loss": 1.064630889892578,
      "num_input_tokens_seen": 7266746560,
      "step": 25550,
      "train_runtime": 248993.3164,
      "train_tokens_per_second": 29184.504
    },
    {
      "epoch": 0.9043645940907593,
      "grad_norm": 1.4609375,
      "learning_rate": 2.651521999463043e-05,
      "loss": 1.0855447769165039,
      "num_input_tokens_seen": 7269593280,
      "step": 25560,
      "train_runtime": 249093.0018,
      "train_tokens_per_second": 29184.253
    },
    {
      "epoch": 0.9047184143544881,
      "grad_norm": 1.5234375,
      "learning_rate": 2.651149243918842e-05,
      "loss": 1.0834228515625,
      "num_input_tokens_seen": 7272358272,
      "step": 25570,
      "train_runtime": 249183.6601,
      "train_tokens_per_second": 29184.732
    },
    {
      "epoch": 0.9050722346182168,
      "grad_norm": 1.453125,
      "learning_rate": 2.650776645538308e-05,
      "loss": 1.083333396911621,
      "num_input_tokens_seen": 7275191680,
      "step": 25580,
      "train_runtime": 249279.9882,
      "train_tokens_per_second": 29184.82
    },
    {
      "epoch": 0.9054260548819456,
      "grad_norm": 1.46875,
      "learning_rate": 2.650404204211032e-05,
      "loss": 1.0843095779418945,
      "num_input_tokens_seen": 7278065728,
      "step": 25590,
      "train_runtime": 249378.1278,
      "train_tokens_per_second": 29184.86
    },
    {
      "epoch": 0.9057798751456745,
      "grad_norm": 1.484375,
      "learning_rate": 2.6500319198267126e-05,
      "loss": 1.0793691635131837,
      "num_input_tokens_seen": 7280872960,
      "step": 25600,
      "train_runtime": 249474.7743,
      "train_tokens_per_second": 29184.806
    },
    {
      "epoch": 0.9061336954094033,
      "grad_norm": 1.5625,
      "learning_rate": 2.6496597922751572e-05,
      "loss": 1.091477394104004,
      "num_input_tokens_seen": 7283647360,
      "step": 25610,
      "train_runtime": 249567.9253,
      "train_tokens_per_second": 29185.03
    },
    {
      "epoch": 0.906487515673132,
      "grad_norm": 1.5234375,
      "learning_rate": 2.6492878214462818e-05,
      "loss": 1.077634048461914,
      "num_input_tokens_seen": 7286489344,
      "step": 25620,
      "train_runtime": 249666.6195,
      "train_tokens_per_second": 29184.876
    },
    {
      "epoch": 0.9068413359368608,
      "grad_norm": 1.453125,
      "learning_rate": 2.648916007230109e-05,
      "loss": 1.0741587638854981,
      "num_input_tokens_seen": 7289338816,
      "step": 25630,
      "train_runtime": 249760.3702,
      "train_tokens_per_second": 29185.33
    },
    {
      "epoch": 0.9071951562005895,
      "grad_norm": 1.53125,
      "learning_rate": 2.6485443495167722e-05,
      "loss": 1.0661139488220215,
      "num_input_tokens_seen": 7292164416,
      "step": 25640,
      "train_runtime": 249855.4223,
      "train_tokens_per_second": 29185.536
    },
    {
      "epoch": 0.9075489764643183,
      "grad_norm": 1.53125,
      "learning_rate": 2.6481728481965102e-05,
      "loss": 1.0773960113525392,
      "num_input_tokens_seen": 7295053952,
      "step": 25650,
      "train_runtime": 249957.271,
      "train_tokens_per_second": 29185.204
    },
    {
      "epoch": 0.9079027967280471,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6478015031596705e-05,
      "loss": 1.0822235107421876,
      "num_input_tokens_seen": 7297896512,
      "step": 25660,
      "train_runtime": 250054.115,
      "train_tokens_per_second": 29185.269
    },
    {
      "epoch": 0.9082566169917758,
      "grad_norm": 1.515625,
      "learning_rate": 2.6474303142967076e-05,
      "loss": 1.0850409507751464,
      "num_input_tokens_seen": 7300728320,
      "step": 25670,
      "train_runtime": 250150.6804,
      "train_tokens_per_second": 29185.323
    },
    {
      "epoch": 0.9086104372555047,
      "grad_norm": 1.46875,
      "learning_rate": 2.6470592814981852e-05,
      "loss": 1.0878046989440917,
      "num_input_tokens_seen": 7303594368,
      "step": 25680,
      "train_runtime": 250250.4739,
      "train_tokens_per_second": 29185.137
    },
    {
      "epoch": 0.9089642575192335,
      "grad_norm": 1.5390625,
      "learning_rate": 2.6466884046547725e-05,
      "loss": 1.0865326881408692,
      "num_input_tokens_seen": 7306414336,
      "step": 25690,
      "train_runtime": 250346.8912,
      "train_tokens_per_second": 29185.161
    },
    {
      "epoch": 0.9093180777829623,
      "grad_norm": 1.46875,
      "learning_rate": 2.646317683657247e-05,
      "loss": 1.087425708770752,
      "num_input_tokens_seen": 7309275328,
      "step": 25700,
      "train_runtime": 250445.6595,
      "train_tokens_per_second": 29185.075
    },
    {
      "epoch": 0.909671898046691,
      "grad_norm": 1.546875,
      "learning_rate": 2.645947118396491e-05,
      "loss": 1.0775270462036133,
      "num_input_tokens_seen": 7312084864,
      "step": 25710,
      "train_runtime": 250540.256,
      "train_tokens_per_second": 29185.269
    },
    {
      "epoch": 0.9100257183104198,
      "grad_norm": 1.5703125,
      "learning_rate": 2.6455767087634982e-05,
      "loss": 1.0788516998291016,
      "num_input_tokens_seen": 7314917504,
      "step": 25720,
      "train_runtime": 250638.7772,
      "train_tokens_per_second": 29185.099
    },
    {
      "epoch": 0.9103795385741486,
      "grad_norm": 1.5625,
      "learning_rate": 2.6452064546493642e-05,
      "loss": 1.0912677764892578,
      "num_input_tokens_seen": 7317741568,
      "step": 25730,
      "train_runtime": 250736.0017,
      "train_tokens_per_second": 29185.045
    },
    {
      "epoch": 0.9107333588378773,
      "grad_norm": 1.4765625,
      "learning_rate": 2.644836355945295e-05,
      "loss": 1.0868235588073731,
      "num_input_tokens_seen": 7320575360,
      "step": 25740,
      "train_runtime": 250831.9924,
      "train_tokens_per_second": 29185.174
    },
    {
      "epoch": 0.9110871791016061,
      "grad_norm": 1.453125,
      "learning_rate": 2.6444664125426012e-05,
      "loss": 1.0838855743408202,
      "num_input_tokens_seen": 7323435072,
      "step": 25750,
      "train_runtime": 250929.8307,
      "train_tokens_per_second": 29185.191
    },
    {
      "epoch": 0.9114409993653348,
      "grad_norm": 1.515625,
      "learning_rate": 2.6440966243326985e-05,
      "loss": 1.0764616966247558,
      "num_input_tokens_seen": 7326340928,
      "step": 25760,
      "train_runtime": 251029.6234,
      "train_tokens_per_second": 29185.165
    },
    {
      "epoch": 0.9117948196290637,
      "grad_norm": 1.4296875,
      "learning_rate": 2.6437269912071132e-05,
      "loss": 1.0859882354736328,
      "num_input_tokens_seen": 7329211904,
      "step": 25770,
      "train_runtime": 251130.7837,
      "train_tokens_per_second": 29184.841
    },
    {
      "epoch": 0.9121486398927925,
      "grad_norm": 1.3984375,
      "learning_rate": 2.6433575130574732e-05,
      "loss": 1.0698867797851563,
      "num_input_tokens_seen": 7332064704,
      "step": 25780,
      "train_runtime": 251230.9046,
      "train_tokens_per_second": 29184.565
    },
    {
      "epoch": 0.9125024601565213,
      "grad_norm": 1.4453125,
      "learning_rate": 2.6429881897755154e-05,
      "loss": 1.0742000579833983,
      "num_input_tokens_seen": 7334932160,
      "step": 25790,
      "train_runtime": 251327.6775,
      "train_tokens_per_second": 29184.737
    },
    {
      "epoch": 0.91285628042025,
      "grad_norm": 1.453125,
      "learning_rate": 2.6426190212530806e-05,
      "loss": 1.0767349243164062,
      "num_input_tokens_seen": 7337747072,
      "step": 25800,
      "train_runtime": 251422.4495,
      "train_tokens_per_second": 29184.932
    },
    {
      "epoch": 0.9132101006839788,
      "grad_norm": 1.4609375,
      "learning_rate": 2.6422500073821168e-05,
      "loss": 1.0791378021240234,
      "num_input_tokens_seen": 7340579904,
      "step": 25810,
      "train_runtime": 251518.8808,
      "train_tokens_per_second": 29185.005
    },
    {
      "epoch": 0.9135639209477076,
      "grad_norm": 1.515625,
      "learning_rate": 2.6418811480546757e-05,
      "loss": 1.0746797561645507,
      "num_input_tokens_seen": 7343382400,
      "step": 25820,
      "train_runtime": 251615.3851,
      "train_tokens_per_second": 29184.95
    },
    {
      "epoch": 0.9139177412114363,
      "grad_norm": 1.46875,
      "learning_rate": 2.641512443162917e-05,
      "loss": 1.083230209350586,
      "num_input_tokens_seen": 7346285056,
      "step": 25830,
      "train_runtime": 251716.8142,
      "train_tokens_per_second": 29184.721
    },
    {
      "epoch": 0.9142715614751651,
      "grad_norm": 1.4765625,
      "learning_rate": 2.6411438925991034e-05,
      "loss": 1.0928114891052245,
      "num_input_tokens_seen": 7349125248,
      "step": 25840,
      "train_runtime": 251815.6639,
      "train_tokens_per_second": 29184.544
    },
    {
      "epoch": 0.914625381738894,
      "grad_norm": 1.5390625,
      "learning_rate": 2.6407754962556046e-05,
      "loss": 1.0763283729553224,
      "num_input_tokens_seen": 7351978560,
      "step": 25850,
      "train_runtime": 251910.7933,
      "train_tokens_per_second": 29184.849
    },
    {
      "epoch": 0.9149792020026227,
      "grad_norm": 1.5390625,
      "learning_rate": 2.640407254024894e-05,
      "loss": 1.0778742790222169,
      "num_input_tokens_seen": 7354887424,
      "step": 25860,
      "train_runtime": 252011.3396,
      "train_tokens_per_second": 29184.748
    },
    {
      "epoch": 0.9153330222663515,
      "grad_norm": 1.5546875,
      "learning_rate": 2.640039165799551e-05,
      "loss": 1.0742226600646974,
      "num_input_tokens_seen": 7357754112,
      "step": 25870,
      "train_runtime": 252109.3592,
      "train_tokens_per_second": 29184.772
    },
    {
      "epoch": 0.9156868425300803,
      "grad_norm": 1.5546875,
      "learning_rate": 2.6396712314722586e-05,
      "loss": 1.0778573989868163,
      "num_input_tokens_seen": 7360567936,
      "step": 25880,
      "train_runtime": 252206.5726,
      "train_tokens_per_second": 29184.679
    },
    {
      "epoch": 0.916040662793809,
      "grad_norm": 1.453125,
      "learning_rate": 2.6393034509358054e-05,
      "loss": 1.076102066040039,
      "num_input_tokens_seen": 7363417344,
      "step": 25890,
      "train_runtime": 252305.5533,
      "train_tokens_per_second": 29184.523
    },
    {
      "epoch": 0.9163944830575378,
      "grad_norm": 1.46875,
      "learning_rate": 2.6389358240830854e-05,
      "loss": 1.0896738052368165,
      "num_input_tokens_seen": 7366247552,
      "step": 25900,
      "train_runtime": 252400.7703,
      "train_tokens_per_second": 29184.727
    },
    {
      "epoch": 0.9167483033212666,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6385683508070942e-05,
      "loss": 1.0849623680114746,
      "num_input_tokens_seen": 7369084736,
      "step": 25910,
      "train_runtime": 252497.4335,
      "train_tokens_per_second": 29184.791
    },
    {
      "epoch": 0.9171021235849953,
      "grad_norm": 1.4609375,
      "learning_rate": 2.6382010310009335e-05,
      "loss": 1.0704755783081055,
      "num_input_tokens_seen": 7371948800,
      "step": 25920,
      "train_runtime": 252596.0576,
      "train_tokens_per_second": 29184.734
    },
    {
      "epoch": 0.9174559438487242,
      "grad_norm": 1.46875,
      "learning_rate": 2.63783386455781e-05,
      "loss": 1.0822740554809571,
      "num_input_tokens_seen": 7374769472,
      "step": 25930,
      "train_runtime": 252690.7873,
      "train_tokens_per_second": 29184.956
    },
    {
      "epoch": 0.917809764112453,
      "grad_norm": 1.5546875,
      "learning_rate": 2.637466851371032e-05,
      "loss": 1.0856513023376464,
      "num_input_tokens_seen": 7377641152,
      "step": 25940,
      "train_runtime": 252790.7288,
      "train_tokens_per_second": 29184.777
    },
    {
      "epoch": 0.9181635843761817,
      "grad_norm": 1.5,
      "learning_rate": 2.637099991334015e-05,
      "loss": 1.0730134963989257,
      "num_input_tokens_seen": 7380539456,
      "step": 25950,
      "train_runtime": 252891.9438,
      "train_tokens_per_second": 29184.557
    },
    {
      "epoch": 0.9185174046399105,
      "grad_norm": 1.5078125,
      "learning_rate": 2.636733284340275e-05,
      "loss": 1.0824790000915527,
      "num_input_tokens_seen": 7383350272,
      "step": 25960,
      "train_runtime": 252986.7885,
      "train_tokens_per_second": 29184.727
    },
    {
      "epoch": 0.9188712249036393,
      "grad_norm": 1.40625,
      "learning_rate": 2.6363667302834326e-05,
      "loss": 1.071113681793213,
      "num_input_tokens_seen": 7386183232,
      "step": 25970,
      "train_runtime": 253083.3117,
      "train_tokens_per_second": 29184.79
    },
    {
      "epoch": 0.919225045167368,
      "grad_norm": 1.515625,
      "learning_rate": 2.636000329057214e-05,
      "loss": 1.0770376205444336,
      "num_input_tokens_seen": 7389062656,
      "step": 25980,
      "train_runtime": 253183.5693,
      "train_tokens_per_second": 29184.606
    },
    {
      "epoch": 0.9195788654310968,
      "grad_norm": 1.46875,
      "learning_rate": 2.6356340805554452e-05,
      "loss": 1.0821327209472655,
      "num_input_tokens_seen": 7391905792,
      "step": 25990,
      "train_runtime": 253281.6365,
      "train_tokens_per_second": 29184.531
    },
    {
      "epoch": 0.9199326856948256,
      "grad_norm": 1.53125,
      "learning_rate": 2.635267984672058e-05,
      "loss": 1.0727310180664062,
      "num_input_tokens_seen": 7394704704,
      "step": 26000,
      "train_runtime": 253375.7886,
      "train_tokens_per_second": 29184.733
    },
    {
      "epoch": 0.9202865059585543,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6349020413010862e-05,
      "loss": 1.085969829559326,
      "num_input_tokens_seen": 7397520192,
      "step": 26010,
      "train_runtime": 253472.108,
      "train_tokens_per_second": 29184.75
    },
    {
      "epoch": 0.9206403262222832,
      "grad_norm": 1.4453125,
      "learning_rate": 2.6345362503366676e-05,
      "loss": 1.0866451263427734,
      "num_input_tokens_seen": 7400370176,
      "step": 26020,
      "train_runtime": 253572.4413,
      "train_tokens_per_second": 29184.442
    },
    {
      "epoch": 0.920994146486012,
      "grad_norm": 1.546875,
      "learning_rate": 2.634170611673042e-05,
      "loss": 1.0759344100952148,
      "num_input_tokens_seen": 7403118144,
      "step": 26030,
      "train_runtime": 253665.2455,
      "train_tokens_per_second": 29184.598
    },
    {
      "epoch": 0.9213479667497407,
      "grad_norm": 1.546875,
      "learning_rate": 2.6338051252045516e-05,
      "loss": 1.064386749267578,
      "num_input_tokens_seen": 7405969792,
      "step": 26040,
      "train_runtime": 253764.8145,
      "train_tokens_per_second": 29184.384
    },
    {
      "epoch": 0.9217017870134695,
      "grad_norm": 1.4609375,
      "learning_rate": 2.6334397908256412e-05,
      "loss": 1.0717890739440918,
      "num_input_tokens_seen": 7408837952,
      "step": 26050,
      "train_runtime": 253861.1274,
      "train_tokens_per_second": 29184.61
    },
    {
      "epoch": 0.9220556072771983,
      "grad_norm": 1.5390625,
      "learning_rate": 2.63307460843086e-05,
      "loss": 1.0824569702148437,
      "num_input_tokens_seen": 7411620864,
      "step": 26060,
      "train_runtime": 253954.7688,
      "train_tokens_per_second": 29184.807
    },
    {
      "epoch": 0.922409427540927,
      "grad_norm": 1.4140625,
      "learning_rate": 2.6327095779148576e-05,
      "loss": 1.0916525840759277,
      "num_input_tokens_seen": 7414539200,
      "step": 26070,
      "train_runtime": 254057.2273,
      "train_tokens_per_second": 29184.524
    },
    {
      "epoch": 0.9227632478046558,
      "grad_norm": 1.5,
      "learning_rate": 2.6323446991723856e-05,
      "loss": 1.0695180892944336,
      "num_input_tokens_seen": 7417369856,
      "step": 26080,
      "train_runtime": 254150.8479,
      "train_tokens_per_second": 29184.911
    },
    {
      "epoch": 0.9231170680683846,
      "grad_norm": 1.5390625,
      "learning_rate": 2.6319799720982985e-05,
      "loss": 1.0762442588806151,
      "num_input_tokens_seen": 7420172992,
      "step": 26090,
      "train_runtime": 254246.8087,
      "train_tokens_per_second": 29184.921
    },
    {
      "epoch": 0.9234708883321134,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6316153965875527e-05,
      "loss": 1.0815706253051758,
      "num_input_tokens_seen": 7422991104,
      "step": 26100,
      "train_runtime": 254342.3119,
      "train_tokens_per_second": 29185.042
    },
    {
      "epoch": 0.9238247085958422,
      "grad_norm": 1.5234375,
      "learning_rate": 2.6312509725352074e-05,
      "loss": 1.082437515258789,
      "num_input_tokens_seen": 7425821120,
      "step": 26110,
      "train_runtime": 254440.5942,
      "train_tokens_per_second": 29184.891
    },
    {
      "epoch": 0.924178528859571,
      "grad_norm": 1.46875,
      "learning_rate": 2.6308866998364208e-05,
      "loss": 1.0699711799621583,
      "num_input_tokens_seen": 7428651392,
      "step": 26120,
      "train_runtime": 254535.9423,
      "train_tokens_per_second": 29185.078
    },
    {
      "epoch": 0.9245323491232997,
      "grad_norm": 1.484375,
      "learning_rate": 2.6305225783864556e-05,
      "loss": 1.0834810256958007,
      "num_input_tokens_seen": 7431515456,
      "step": 26130,
      "train_runtime": 254633.8743,
      "train_tokens_per_second": 29185.101
    },
    {
      "epoch": 0.9248861693870285,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6301586080806734e-05,
      "loss": 1.0833247184753418,
      "num_input_tokens_seen": 7434345792,
      "step": 26140,
      "train_runtime": 254733.6062,
      "train_tokens_per_second": 29184.786
    },
    {
      "epoch": 0.9252399896507573,
      "grad_norm": 1.546875,
      "learning_rate": 2.6297947888145395e-05,
      "loss": 1.0645605087280274,
      "num_input_tokens_seen": 7437112960,
      "step": 26150,
      "train_runtime": 254826.4131,
      "train_tokens_per_second": 29185.016
    },
    {
      "epoch": 0.925593809914486,
      "grad_norm": 1.4609375,
      "learning_rate": 2.6294311204836185e-05,
      "loss": 1.080024814605713,
      "num_input_tokens_seen": 7440015104,
      "step": 26160,
      "train_runtime": 254926.1042,
      "train_tokens_per_second": 29184.987
    },
    {
      "epoch": 0.9259476301782148,
      "grad_norm": 1.4765625,
      "learning_rate": 2.6290676029835777e-05,
      "loss": 1.0686896324157715,
      "num_input_tokens_seen": 7442824320,
      "step": 26170,
      "train_runtime": 255021.3657,
      "train_tokens_per_second": 29185.101
    },
    {
      "epoch": 0.9263014504419437,
      "grad_norm": 1.4609375,
      "learning_rate": 2.6287042362101834e-05,
      "loss": 1.0828365325927733,
      "num_input_tokens_seen": 7445649280,
      "step": 26180,
      "train_runtime": 255116.0164,
      "train_tokens_per_second": 29185.346
    },
    {
      "epoch": 0.9266552707056724,
      "grad_norm": 1.3984375,
      "learning_rate": 2.628341020059304e-05,
      "loss": 1.0752599716186524,
      "num_input_tokens_seen": 7448544256,
      "step": 26190,
      "train_runtime": 255218.2302,
      "train_tokens_per_second": 29185.001
    },
    {
      "epoch": 0.9270090909694012,
      "grad_norm": 1.484375,
      "learning_rate": 2.627977954426909e-05,
      "loss": 1.0848546981811524,
      "num_input_tokens_seen": 7451411648,
      "step": 26200,
      "train_runtime": 255317.9095,
      "train_tokens_per_second": 29184.837
    },
    {
      "epoch": 0.92736291123313,
      "grad_norm": 1.515625,
      "learning_rate": 2.627615039209067e-05,
      "loss": 1.085745906829834,
      "num_input_tokens_seen": 7454233792,
      "step": 26210,
      "train_runtime": 255413.6951,
      "train_tokens_per_second": 29184.942
    },
    {
      "epoch": 0.9277167314968587,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6272522743019483e-05,
      "loss": 1.0798236846923828,
      "num_input_tokens_seen": 7457067968,
      "step": 26220,
      "train_runtime": 255512.8286,
      "train_tokens_per_second": 29184.711
    },
    {
      "epoch": 0.9280705517605875,
      "grad_norm": 1.4609375,
      "learning_rate": 2.6268896596018234e-05,
      "loss": 1.068924903869629,
      "num_input_tokens_seen": 7459882048,
      "step": 26230,
      "train_runtime": 255606.4221,
      "train_tokens_per_second": 29185.034
    },
    {
      "epoch": 0.9284243720243163,
      "grad_norm": 1.484375,
      "learning_rate": 2.6265271950050624e-05,
      "loss": 1.0713335990905761,
      "num_input_tokens_seen": 7462726464,
      "step": 26240,
      "train_runtime": 255703.6777,
      "train_tokens_per_second": 29185.057
    },
    {
      "epoch": 0.928778192288045,
      "grad_norm": 1.5,
      "learning_rate": 2.626164880408136e-05,
      "loss": 1.073418426513672,
      "num_input_tokens_seen": 7465592512,
      "step": 26250,
      "train_runtime": 255801.7036,
      "train_tokens_per_second": 29185.077
    },
    {
      "epoch": 0.9291320125517738,
      "grad_norm": 1.484375,
      "learning_rate": 2.6258027157076137e-05,
      "loss": 1.078279685974121,
      "num_input_tokens_seen": 7468436288,
      "step": 26260,
      "train_runtime": 255900.3095,
      "train_tokens_per_second": 29184.944
    },
    {
      "epoch": 0.9294858328155027,
      "grad_norm": 1.53125,
      "learning_rate": 2.625440700800167e-05,
      "loss": 1.0788238525390625,
      "num_input_tokens_seen": 7471270400,
      "step": 26270,
      "train_runtime": 255998.3517,
      "train_tokens_per_second": 29184.838
    },
    {
      "epoch": 0.9298396530792314,
      "grad_norm": 1.5,
      "learning_rate": 2.6250788355825646e-05,
      "loss": 1.0796710968017578,
      "num_input_tokens_seen": 7474175040,
      "step": 26280,
      "train_runtime": 256099.8839,
      "train_tokens_per_second": 29184.609
    },
    {
      "epoch": 0.9301934733429602,
      "grad_norm": 1.4765625,
      "learning_rate": 2.6247171199516767e-05,
      "loss": 1.0876428604125976,
      "num_input_tokens_seen": 7477086272,
      "step": 26290,
      "train_runtime": 256201.0517,
      "train_tokens_per_second": 29184.448
    },
    {
      "epoch": 0.930547293606689,
      "grad_norm": 1.4296875,
      "learning_rate": 2.6243555538044717e-05,
      "loss": 1.081110382080078,
      "num_input_tokens_seen": 7479947072,
      "step": 26300,
      "train_runtime": 256299.7458,
      "train_tokens_per_second": 29184.372
    },
    {
      "epoch": 0.9309011138704177,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6239941370380184e-05,
      "loss": 1.0841760635375977,
      "num_input_tokens_seen": 7482773952,
      "step": 26310,
      "train_runtime": 256396.3876,
      "train_tokens_per_second": 29184.397
    },
    {
      "epoch": 0.9312549341341465,
      "grad_norm": 1.5546875,
      "learning_rate": 2.6236328695494834e-05,
      "loss": 1.0706096649169923,
      "num_input_tokens_seen": 7485591360,
      "step": 26320,
      "train_runtime": 256490.795,
      "train_tokens_per_second": 29184.639
    },
    {
      "epoch": 0.9316087543978753,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6232717512361343e-05,
      "loss": 1.0788137435913085,
      "num_input_tokens_seen": 7488479360,
      "step": 26330,
      "train_runtime": 256590.7314,
      "train_tokens_per_second": 29184.528
    },
    {
      "epoch": 0.931962574661604,
      "grad_norm": 1.5234375,
      "learning_rate": 2.6229107819953357e-05,
      "loss": 1.0879730224609374,
      "num_input_tokens_seen": 7491326208,
      "step": 26340,
      "train_runtime": 256687.8165,
      "train_tokens_per_second": 29184.58
    },
    {
      "epoch": 0.9323163949253329,
      "grad_norm": 1.46875,
      "learning_rate": 2.6225499617245525e-05,
      "loss": 1.0781933784484863,
      "num_input_tokens_seen": 7494171328,
      "step": 26350,
      "train_runtime": 256782.7283,
      "train_tokens_per_second": 29184.873
    },
    {
      "epoch": 0.9326702151890617,
      "grad_norm": 1.4609375,
      "learning_rate": 2.6221892903213473e-05,
      "loss": 1.0975550651550292,
      "num_input_tokens_seen": 7496991168,
      "step": 26360,
      "train_runtime": 256878.9263,
      "train_tokens_per_second": 29184.921
    },
    {
      "epoch": 0.9330240354527904,
      "grad_norm": 1.5859375,
      "learning_rate": 2.621828767683382e-05,
      "loss": 1.0849864959716797,
      "num_input_tokens_seen": 7499831552,
      "step": 26370,
      "train_runtime": 256977.6567,
      "train_tokens_per_second": 29184.761
    },
    {
      "epoch": 0.9333778557165192,
      "grad_norm": 1.515625,
      "learning_rate": 2.6214683937084162e-05,
      "loss": 1.0859233856201171,
      "num_input_tokens_seen": 7502663936,
      "step": 26380,
      "train_runtime": 257073.1286,
      "train_tokens_per_second": 29184.94
    },
    {
      "epoch": 0.933731675980248,
      "grad_norm": 1.53125,
      "learning_rate": 2.621108168294309e-05,
      "loss": 1.0787812232971192,
      "num_input_tokens_seen": 7505471744,
      "step": 26390,
      "train_runtime": 257167.4091,
      "train_tokens_per_second": 29185.159
    },
    {
      "epoch": 0.9340854962439767,
      "grad_norm": 1.46875,
      "learning_rate": 2.620748091339016e-05,
      "loss": 1.0715045928955078,
      "num_input_tokens_seen": 7508353152,
      "step": 26400,
      "train_runtime": 257261.9127,
      "train_tokens_per_second": 29185.638
    },
    {
      "epoch": 0.9344393165077055,
      "grad_norm": 1.5390625,
      "learning_rate": 2.620388162740593e-05,
      "loss": 1.0859477043151855,
      "num_input_tokens_seen": 7511148928,
      "step": 26410,
      "train_runtime": 257356.6009,
      "train_tokens_per_second": 29185.764
    },
    {
      "epoch": 0.9347931367714343,
      "grad_norm": 1.5234375,
      "learning_rate": 2.620028382397192e-05,
      "loss": 1.0769970893859864,
      "num_input_tokens_seen": 7514030912,
      "step": 26420,
      "train_runtime": 257455.7774,
      "train_tokens_per_second": 29185.715
    },
    {
      "epoch": 0.9351469570351632,
      "grad_norm": 1.515625,
      "learning_rate": 2.6196687502070645e-05,
      "loss": 1.0977009773254394,
      "num_input_tokens_seen": 7516908224,
      "step": 26430,
      "train_runtime": 257553.8307,
      "train_tokens_per_second": 29185.775
    },
    {
      "epoch": 0.9355007772988919,
      "grad_norm": 1.453125,
      "learning_rate": 2.6193092660685577e-05,
      "loss": 1.0683977127075195,
      "num_input_tokens_seen": 7519726528,
      "step": 26440,
      "train_runtime": 257646.3918,
      "train_tokens_per_second": 29186.229
    },
    {
      "epoch": 0.9358545975626207,
      "grad_norm": 1.6484375,
      "learning_rate": 2.618949929880118e-05,
      "loss": 1.076093578338623,
      "num_input_tokens_seen": 7522534016,
      "step": 26450,
      "train_runtime": 257742.7845,
      "train_tokens_per_second": 29186.206
    },
    {
      "epoch": 0.9362084178263494,
      "grad_norm": 1.46875,
      "learning_rate": 2.618590741540289e-05,
      "loss": 1.0674578666687011,
      "num_input_tokens_seen": 7525328512,
      "step": 26460,
      "train_runtime": 257835.0832,
      "train_tokens_per_second": 29186.596
    },
    {
      "epoch": 0.9365622380900782,
      "grad_norm": 1.453125,
      "learning_rate": 2.6182317009477104e-05,
      "loss": 1.0867802619934082,
      "num_input_tokens_seen": 7528202048,
      "step": 26470,
      "train_runtime": 257933.6429,
      "train_tokens_per_second": 29186.584
    },
    {
      "epoch": 0.936916058353807,
      "grad_norm": 1.5,
      "learning_rate": 2.617872808001122e-05,
      "loss": 1.0810303688049316,
      "num_input_tokens_seen": 7531066304,
      "step": 26480,
      "train_runtime": 258031.5273,
      "train_tokens_per_second": 29186.613
    },
    {
      "epoch": 0.9372698786175357,
      "grad_norm": 1.4765625,
      "learning_rate": 2.6175140625993583e-05,
      "loss": 1.077030849456787,
      "num_input_tokens_seen": 7533873984,
      "step": 26490,
      "train_runtime": 258126.6617,
      "train_tokens_per_second": 29186.733
    },
    {
      "epoch": 0.9376236988812645,
      "grad_norm": 1.4453125,
      "learning_rate": 2.6171554646413508e-05,
      "loss": 1.067174243927002,
      "num_input_tokens_seen": 7536732416,
      "step": 26500,
      "train_runtime": 258224.9788,
      "train_tokens_per_second": 29186.69
    },
    {
      "epoch": 0.9379775191449934,
      "grad_norm": 1.5234375,
      "learning_rate": 2.61679701402613e-05,
      "loss": 1.080540084838867,
      "num_input_tokens_seen": 7539570496,
      "step": 26510,
      "train_runtime": 258323.5943,
      "train_tokens_per_second": 29186.534
    },
    {
      "epoch": 0.9383313394087222,
      "grad_norm": 1.546875,
      "learning_rate": 2.6164387106528197e-05,
      "loss": 1.0905363082885742,
      "num_input_tokens_seen": 7542419776,
      "step": 26520,
      "train_runtime": 258423.1647,
      "train_tokens_per_second": 29186.315
    },
    {
      "epoch": 0.9386851596724509,
      "grad_norm": 1.46875,
      "learning_rate": 2.6160805544206447e-05,
      "loss": 1.076739501953125,
      "num_input_tokens_seen": 7545247616,
      "step": 26530,
      "train_runtime": 258520.7841,
      "train_tokens_per_second": 29186.232
    },
    {
      "epoch": 0.9390389799361797,
      "grad_norm": 1.5390625,
      "learning_rate": 2.6157225452289223e-05,
      "loss": 1.0900687217712401,
      "num_input_tokens_seen": 7548103680,
      "step": 26540,
      "train_runtime": 258616.2377,
      "train_tokens_per_second": 29186.503
    },
    {
      "epoch": 0.9393928001999085,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6153646829770696e-05,
      "loss": 1.064324188232422,
      "num_input_tokens_seen": 7550937152,
      "step": 26550,
      "train_runtime": 258713.8921,
      "train_tokens_per_second": 29186.439
    },
    {
      "epoch": 0.9397466204636372,
      "grad_norm": 1.4609375,
      "learning_rate": 2.6150069675645972e-05,
      "loss": 1.0771010398864747,
      "num_input_tokens_seen": 7553826304,
      "step": 26560,
      "train_runtime": 258814.7094,
      "train_tokens_per_second": 29186.233
    },
    {
      "epoch": 0.940100440727366,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6146493988911137e-05,
      "loss": 1.0769364356994628,
      "num_input_tokens_seen": 7556638656,
      "step": 26570,
      "train_runtime": 258909.1224,
      "train_tokens_per_second": 29186.452
    },
    {
      "epoch": 0.9404542609910947,
      "grad_norm": 1.5625,
      "learning_rate": 2.6142919768563224e-05,
      "loss": 1.0838316917419433,
      "num_input_tokens_seen": 7559477248,
      "step": 26580,
      "train_runtime": 259005.4121,
      "train_tokens_per_second": 29186.561
    },
    {
      "epoch": 0.9408080812548235,
      "grad_norm": 1.421875,
      "learning_rate": 2.613934701360024e-05,
      "loss": 1.085238552093506,
      "num_input_tokens_seen": 7562282368,
      "step": 26590,
      "train_runtime": 259098.7449,
      "train_tokens_per_second": 29186.874
    },
    {
      "epoch": 0.9411619015185524,
      "grad_norm": 1.546875,
      "learning_rate": 2.6135775723021143e-05,
      "loss": 1.077366542816162,
      "num_input_tokens_seen": 7565127424,
      "step": 26600,
      "train_runtime": 259195.1194,
      "train_tokens_per_second": 29186.998
    },
    {
      "epoch": 0.9415157217822812,
      "grad_norm": 1.546875,
      "learning_rate": 2.613220589582585e-05,
      "loss": 1.0844367027282715,
      "num_input_tokens_seen": 7568018496,
      "step": 26610,
      "train_runtime": 259295.2024,
      "train_tokens_per_second": 29186.882
    },
    {
      "epoch": 0.9418695420460099,
      "grad_norm": 1.5546875,
      "learning_rate": 2.612863753101522e-05,
      "loss": 1.0768617630004882,
      "num_input_tokens_seen": 7570843008,
      "step": 26620,
      "train_runtime": 259389.3927,
      "train_tokens_per_second": 29187.173
    },
    {
      "epoch": 0.9422233623097387,
      "grad_norm": 1.421875,
      "learning_rate": 2.612507062759109e-05,
      "loss": 1.08292236328125,
      "num_input_tokens_seen": 7573606592,
      "step": 26630,
      "train_runtime": 259480.588,
      "train_tokens_per_second": 29187.565
    },
    {
      "epoch": 0.9425771825734675,
      "grad_norm": 1.453125,
      "learning_rate": 2.612150518455625e-05,
      "loss": 1.0820573806762694,
      "num_input_tokens_seen": 7576424576,
      "step": 26640,
      "train_runtime": 259578.2444,
      "train_tokens_per_second": 29187.441
    },
    {
      "epoch": 0.9429310028371962,
      "grad_norm": 1.4609375,
      "learning_rate": 2.6117941200914407e-05,
      "loss": 1.085733985900879,
      "num_input_tokens_seen": 7579285376,
      "step": 26650,
      "train_runtime": 259673.528,
      "train_tokens_per_second": 29187.748
    },
    {
      "epoch": 0.943284823100925,
      "grad_norm": 1.46875,
      "learning_rate": 2.6114378675670266e-05,
      "loss": 1.0861295700073241,
      "num_input_tokens_seen": 7582086912,
      "step": 26660,
      "train_runtime": 259767.0666,
      "train_tokens_per_second": 29188.022
    },
    {
      "epoch": 0.9436386433646538,
      "grad_norm": 1.5,
      "learning_rate": 2.611081760782944e-05,
      "loss": 1.0760425567626952,
      "num_input_tokens_seen": 7584917376,
      "step": 26670,
      "train_runtime": 259863.2204,
      "train_tokens_per_second": 29188.114
    },
    {
      "epoch": 0.9439924636283826,
      "grad_norm": 1.5,
      "learning_rate": 2.6107257996398533e-05,
      "loss": 1.0788305282592774,
      "num_input_tokens_seen": 7587733568,
      "step": 26680,
      "train_runtime": 259959.7449,
      "train_tokens_per_second": 29188.11
    },
    {
      "epoch": 0.9443462838921114,
      "grad_norm": 1.46875,
      "learning_rate": 2.610369984038506e-05,
      "loss": 1.0764963150024414,
      "num_input_tokens_seen": 7590547328,
      "step": 26690,
      "train_runtime": 260053.8163,
      "train_tokens_per_second": 29188.371
    },
    {
      "epoch": 0.9447001041558402,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6100143138797508e-05,
      "loss": 1.0734793663024902,
      "num_input_tokens_seen": 7593391104,
      "step": 26700,
      "train_runtime": 260150.3458,
      "train_tokens_per_second": 29188.472
    },
    {
      "epoch": 0.9450539244195689,
      "grad_norm": 1.484375,
      "learning_rate": 2.6096587890645286e-05,
      "loss": 1.0645111083984375,
      "num_input_tokens_seen": 7596243136,
      "step": 26710,
      "train_runtime": 260248.8905,
      "train_tokens_per_second": 29188.379
    },
    {
      "epoch": 0.9454077446832977,
      "grad_norm": 1.5234375,
      "learning_rate": 2.6093034094938772e-05,
      "loss": 1.0891409873962403,
      "num_input_tokens_seen": 7599072192,
      "step": 26720,
      "train_runtime": 260345.6814,
      "train_tokens_per_second": 29188.393
    },
    {
      "epoch": 0.9457615649470265,
      "grad_norm": 1.46875,
      "learning_rate": 2.608948175068927e-05,
      "loss": 1.0813072204589844,
      "num_input_tokens_seen": 7601949120,
      "step": 26730,
      "train_runtime": 260442.8863,
      "train_tokens_per_second": 29188.546
    },
    {
      "epoch": 0.9461153852107552,
      "grad_norm": 1.5625,
      "learning_rate": 2.6085930856909035e-05,
      "loss": 1.0803549766540528,
      "num_input_tokens_seen": 7604805952,
      "step": 26740,
      "train_runtime": 260538.8755,
      "train_tokens_per_second": 29188.757
    },
    {
      "epoch": 0.946469205474484,
      "grad_norm": 1.515625,
      "learning_rate": 2.608238141261126e-05,
      "loss": 1.0850915908813477,
      "num_input_tokens_seen": 7607641280,
      "step": 26750,
      "train_runtime": 260634.0829,
      "train_tokens_per_second": 29188.973
    },
    {
      "epoch": 0.9468230257382129,
      "grad_norm": 1.5390625,
      "learning_rate": 2.6078833416810072e-05,
      "loss": 1.0891590118408203,
      "num_input_tokens_seen": 7610425536,
      "step": 26760,
      "train_runtime": 260727.9224,
      "train_tokens_per_second": 29189.147
    },
    {
      "epoch": 0.9471768460019416,
      "grad_norm": 1.46875,
      "learning_rate": 2.6075286868520543e-05,
      "loss": 1.0819381713867187,
      "num_input_tokens_seen": 7613237632,
      "step": 26770,
      "train_runtime": 260821.5482,
      "train_tokens_per_second": 29189.45
    },
    {
      "epoch": 0.9475306662656704,
      "grad_norm": 1.484375,
      "learning_rate": 2.6071741766758678e-05,
      "loss": 1.0874982833862306,
      "num_input_tokens_seen": 7616021312,
      "step": 26780,
      "train_runtime": 260916.3586,
      "train_tokens_per_second": 29189.512
    },
    {
      "epoch": 0.9478844865293992,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6068198110541432e-05,
      "loss": 1.0767423629760742,
      "num_input_tokens_seen": 7618848512,
      "step": 26790,
      "train_runtime": 261013.4491,
      "train_tokens_per_second": 29189.486
    },
    {
      "epoch": 0.9482383067931279,
      "grad_norm": 1.53125,
      "learning_rate": 2.606465589888667e-05,
      "loss": 1.092358112335205,
      "num_input_tokens_seen": 7621735040,
      "step": 26800,
      "train_runtime": 261112.5893,
      "train_tokens_per_second": 29189.458
    },
    {
      "epoch": 0.9485921270568567,
      "grad_norm": 1.484375,
      "learning_rate": 2.606111513081321e-05,
      "loss": 1.074544906616211,
      "num_input_tokens_seen": 7624568320,
      "step": 26810,
      "train_runtime": 261208.4494,
      "train_tokens_per_second": 29189.593
    },
    {
      "epoch": 0.9489459473205855,
      "grad_norm": 1.5625,
      "learning_rate": 2.60575758053408e-05,
      "loss": 1.0646194458007812,
      "num_input_tokens_seen": 7627436160,
      "step": 26820,
      "train_runtime": 261307.5589,
      "train_tokens_per_second": 29189.497
    },
    {
      "epoch": 0.9492997675843142,
      "grad_norm": 1.5,
      "learning_rate": 2.605403792149012e-05,
      "loss": 1.079594326019287,
      "num_input_tokens_seen": 7630342400,
      "step": 26830,
      "train_runtime": 261407.989,
      "train_tokens_per_second": 29189.4
    },
    {
      "epoch": 0.949653587848043,
      "grad_norm": 1.4921875,
      "learning_rate": 2.6050501478282775e-05,
      "loss": 1.072446346282959,
      "num_input_tokens_seen": 7633210560,
      "step": 26840,
      "train_runtime": 261507.8011,
      "train_tokens_per_second": 29189.227
    },
    {
      "epoch": 0.9500074081117719,
      "grad_norm": 1.46875,
      "learning_rate": 2.6046966474741293e-05,
      "loss": 1.0824260711669922,
      "num_input_tokens_seen": 7636083072,
      "step": 26850,
      "train_runtime": 261604.1435,
      "train_tokens_per_second": 29189.458
    },
    {
      "epoch": 0.9503612283755006,
      "grad_norm": 1.453125,
      "learning_rate": 2.6043432909889148e-05,
      "loss": 1.088757038116455,
      "num_input_tokens_seen": 7638949888,
      "step": 26860,
      "train_runtime": 261700.4961,
      "train_tokens_per_second": 29189.665
    },
    {
      "epoch": 0.9507150486392294,
      "grad_norm": 1.46875,
      "learning_rate": 2.6039900782750737e-05,
      "loss": 1.0757373809814452,
      "num_input_tokens_seen": 7641783168,
      "step": 26870,
      "train_runtime": 261796.748,
      "train_tokens_per_second": 29189.756
    },
    {
      "epoch": 0.9510688689029582,
      "grad_norm": 1.5234375,
      "learning_rate": 2.6036370092351377e-05,
      "loss": 1.071635913848877,
      "num_input_tokens_seen": 7644615424,
      "step": 26880,
      "train_runtime": 261894.8357,
      "train_tokens_per_second": 29189.638
    },
    {
      "epoch": 0.9514226891666869,
      "grad_norm": 1.546875,
      "learning_rate": 2.6032840837717298e-05,
      "loss": 1.0655144691467284,
      "num_input_tokens_seen": 7647469376,
      "step": 26890,
      "train_runtime": 261993.1857,
      "train_tokens_per_second": 29189.574
    },
    {
      "epoch": 0.9517765094304157,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6029313017875682e-05,
      "loss": 1.0876749992370605,
      "num_input_tokens_seen": 7650284608,
      "step": 26900,
      "train_runtime": 262087.5444,
      "train_tokens_per_second": 29189.806
    },
    {
      "epoch": 0.9521303296941445,
      "grad_norm": 1.484375,
      "learning_rate": 2.602578663185461e-05,
      "loss": 1.0852800369262696,
      "num_input_tokens_seen": 7653107456,
      "step": 26910,
      "train_runtime": 262186.8198,
      "train_tokens_per_second": 29189.52
    },
    {
      "epoch": 0.9524841499578732,
      "grad_norm": 1.5,
      "learning_rate": 2.6022261678683102e-05,
      "loss": 1.077920913696289,
      "num_input_tokens_seen": 7655948864,
      "step": 26920,
      "train_runtime": 262284.6289,
      "train_tokens_per_second": 29189.468
    },
    {
      "epoch": 0.9528379702216021,
      "grad_norm": 1.5078125,
      "learning_rate": 2.601873815739108e-05,
      "loss": 1.0815540313720704,
      "num_input_tokens_seen": 7658779392,
      "step": 26930,
      "train_runtime": 262381.8249,
      "train_tokens_per_second": 29189.443
    },
    {
      "epoch": 0.9531917904853309,
      "grad_norm": 1.46875,
      "learning_rate": 2.6015216067009395e-05,
      "loss": 1.0645343780517578,
      "num_input_tokens_seen": 7661614784,
      "step": 26940,
      "train_runtime": 262476.6997,
      "train_tokens_per_second": 29189.695
    },
    {
      "epoch": 0.9535456107490596,
      "grad_norm": 1.5078125,
      "learning_rate": 2.6011695406569824e-05,
      "loss": 1.0704078674316406,
      "num_input_tokens_seen": 7664483008,
      "step": 26950,
      "train_runtime": 262575.5553,
      "train_tokens_per_second": 29189.629
    },
    {
      "epoch": 0.9538994310127884,
      "grad_norm": 1.484375,
      "learning_rate": 2.6008176175105048e-05,
      "loss": 1.0725948333740234,
      "num_input_tokens_seen": 7667332416,
      "step": 26960,
      "train_runtime": 262670.3161,
      "train_tokens_per_second": 29189.946
    },
    {
      "epoch": 0.9542532512765172,
      "grad_norm": 1.5,
      "learning_rate": 2.6004658371648672e-05,
      "loss": 1.0794626235961915,
      "num_input_tokens_seen": 7670159680,
      "step": 26970,
      "train_runtime": 262766.5782,
      "train_tokens_per_second": 29190.012
    },
    {
      "epoch": 0.9546070715402459,
      "grad_norm": 1.515625,
      "learning_rate": 2.6001141995235195e-05,
      "loss": 1.0818564414978027,
      "num_input_tokens_seen": 7673056704,
      "step": 26980,
      "train_runtime": 262865.6503,
      "train_tokens_per_second": 29190.032
    },
    {
      "epoch": 0.9549608918039747,
      "grad_norm": 1.4453125,
      "learning_rate": 2.599762704490007e-05,
      "loss": 1.0796282768249512,
      "num_input_tokens_seen": 7675956352,
      "step": 26990,
      "train_runtime": 262967.2762,
      "train_tokens_per_second": 29189.778
    },
    {
      "epoch": 0.9553147120677035,
      "grad_norm": 1.53125,
      "learning_rate": 2.599411351967963e-05,
      "loss": 1.0778749465942383,
      "num_input_tokens_seen": 7678770112,
      "step": 27000,
      "train_runtime": 263064.2965,
      "train_tokens_per_second": 29189.708
    },
    {
      "epoch": 0.9556685323314323,
      "grad_norm": 1.4765625,
      "learning_rate": 2.5990601418611127e-05,
      "loss": 1.0656103134155273,
      "num_input_tokens_seen": 7681633920,
      "step": 27010,
      "train_runtime": 263164.3479,
      "train_tokens_per_second": 29189.493
    },
    {
      "epoch": 0.9560223525951611,
      "grad_norm": 1.5078125,
      "learning_rate": 2.598709074073272e-05,
      "loss": 1.0797760009765625,
      "num_input_tokens_seen": 7684447104,
      "step": 27020,
      "train_runtime": 263258.8387,
      "train_tokens_per_second": 29189.702
    },
    {
      "epoch": 0.9563761728588899,
      "grad_norm": 1.4765625,
      "learning_rate": 2.5983581485083498e-05,
      "loss": 1.0836926460266114,
      "num_input_tokens_seen": 7687253632,
      "step": 27030,
      "train_runtime": 263355.3457,
      "train_tokens_per_second": 29189.662
    },
    {
      "epoch": 0.9567299931226186,
      "grad_norm": 1.484375,
      "learning_rate": 2.598007365070343e-05,
      "loss": 1.084663200378418,
      "num_input_tokens_seen": 7690112640,
      "step": 27040,
      "train_runtime": 263455.25,
      "train_tokens_per_second": 29189.445
    },
    {
      "epoch": 0.9570838133863474,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5976567236633403e-05,
      "loss": 1.0982830047607421,
      "num_input_tokens_seen": 7692974400,
      "step": 27050,
      "train_runtime": 263554.4651,
      "train_tokens_per_second": 29189.315
    },
    {
      "epoch": 0.9574376336500762,
      "grad_norm": 1.5,
      "learning_rate": 2.5973062241915225e-05,
      "loss": 1.0604990005493165,
      "num_input_tokens_seen": 7695779648,
      "step": 27060,
      "train_runtime": 263651.545,
      "train_tokens_per_second": 29189.207
    },
    {
      "epoch": 0.9577914539138049,
      "grad_norm": 1.4609375,
      "learning_rate": 2.5969558665591576e-05,
      "loss": 1.0921756744384765,
      "num_input_tokens_seen": 7698627264,
      "step": 27070,
      "train_runtime": 263749.4617,
      "train_tokens_per_second": 29189.168
    },
    {
      "epoch": 0.9581452741775337,
      "grad_norm": 1.546875,
      "learning_rate": 2.5966056506706078e-05,
      "loss": 1.0763803482055665,
      "num_input_tokens_seen": 7701469120,
      "step": 27080,
      "train_runtime": 263848.0735,
      "train_tokens_per_second": 29189.029
    },
    {
      "epoch": 0.9584990944412625,
      "grad_norm": 1.4609375,
      "learning_rate": 2.596255576430322e-05,
      "loss": 1.0933831214904786,
      "num_input_tokens_seen": 7704293632,
      "step": 27090,
      "train_runtime": 263943.1038,
      "train_tokens_per_second": 29189.221
    },
    {
      "epoch": 0.9588529147049913,
      "grad_norm": 1.4609375,
      "learning_rate": 2.5959056437428414e-05,
      "loss": 1.08085298538208,
      "num_input_tokens_seen": 7707106816,
      "step": 27100,
      "train_runtime": 264039.1825,
      "train_tokens_per_second": 29189.254
    },
    {
      "epoch": 0.9592067349687201,
      "grad_norm": 1.5625,
      "learning_rate": 2.5955558525127977e-05,
      "loss": 1.0727056503295898,
      "num_input_tokens_seen": 7709932096,
      "step": 27110,
      "train_runtime": 264134.0475,
      "train_tokens_per_second": 29189.467
    },
    {
      "epoch": 0.9595605552324489,
      "grad_norm": 1.4375,
      "learning_rate": 2.5952062026449096e-05,
      "loss": 1.0823779106140137,
      "num_input_tokens_seen": 7712776768,
      "step": 27120,
      "train_runtime": 264232.0709,
      "train_tokens_per_second": 29189.404
    },
    {
      "epoch": 0.9599143754961776,
      "grad_norm": 1.546875,
      "learning_rate": 2.59485669404399e-05,
      "loss": 1.0806731224060058,
      "num_input_tokens_seen": 7715607616,
      "step": 27130,
      "train_runtime": 264327.6129,
      "train_tokens_per_second": 29189.563
    },
    {
      "epoch": 0.9602681957599064,
      "grad_norm": 1.546875,
      "learning_rate": 2.5945073266149366e-05,
      "loss": 1.0666584014892577,
      "num_input_tokens_seen": 7718424512,
      "step": 27140,
      "train_runtime": 264422.9603,
      "train_tokens_per_second": 29189.691
    },
    {
      "epoch": 0.9606220160236352,
      "grad_norm": 1.484375,
      "learning_rate": 2.594158100262741e-05,
      "loss": 1.0793862342834473,
      "num_input_tokens_seen": 7721271360,
      "step": 27150,
      "train_runtime": 264519.1368,
      "train_tokens_per_second": 29189.84
    },
    {
      "epoch": 0.9609758362873639,
      "grad_norm": 1.4609375,
      "learning_rate": 2.5938090148924815e-05,
      "loss": 1.0912773132324218,
      "num_input_tokens_seen": 7724100992,
      "step": 27160,
      "train_runtime": 264615.4779,
      "train_tokens_per_second": 29189.906
    },
    {
      "epoch": 0.9613296565510927,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5934600704093282e-05,
      "loss": 1.0855581283569335,
      "num_input_tokens_seen": 7726932160,
      "step": 27170,
      "train_runtime": 264711.61,
      "train_tokens_per_second": 29190.001
    },
    {
      "epoch": 0.9616834768148216,
      "grad_norm": 1.5703125,
      "learning_rate": 2.5931112667185365e-05,
      "loss": 1.084220790863037,
      "num_input_tokens_seen": 7729738432,
      "step": 27180,
      "train_runtime": 264807.2364,
      "train_tokens_per_second": 29190.057
    },
    {
      "epoch": 0.9620372970785503,
      "grad_norm": 1.53125,
      "learning_rate": 2.592762603725456e-05,
      "loss": 1.0891904830932617,
      "num_input_tokens_seen": 7732588608,
      "step": 27190,
      "train_runtime": 264903.1288,
      "train_tokens_per_second": 29190.25
    },
    {
      "epoch": 0.9623911173422791,
      "grad_norm": 1.4921875,
      "learning_rate": 2.592414081335522e-05,
      "loss": 1.0743358612060547,
      "num_input_tokens_seen": 7735442176,
      "step": 27200,
      "train_runtime": 264998.4065,
      "train_tokens_per_second": 29190.523
    },
    {
      "epoch": 0.9627449376060079,
      "grad_norm": 1.4296875,
      "learning_rate": 2.592065699454259e-05,
      "loss": 1.083421802520752,
      "num_input_tokens_seen": 7738321792,
      "step": 27210,
      "train_runtime": 265098.3717,
      "train_tokens_per_second": 29190.378
    },
    {
      "epoch": 0.9630987578697366,
      "grad_norm": 1.421875,
      "learning_rate": 2.5917174579872815e-05,
      "loss": 1.0821763038635255,
      "num_input_tokens_seen": 7741176000,
      "step": 27220,
      "train_runtime": 265194.8742,
      "train_tokens_per_second": 29190.519
    },
    {
      "epoch": 0.9634525781334654,
      "grad_norm": 1.5,
      "learning_rate": 2.5913693568402926e-05,
      "loss": 1.067593765258789,
      "num_input_tokens_seen": 7744038848,
      "step": 27230,
      "train_runtime": 265293.0473,
      "train_tokens_per_second": 29190.508
    },
    {
      "epoch": 0.9638063983971942,
      "grad_norm": 1.53125,
      "learning_rate": 2.5910213959190833e-05,
      "loss": 1.0845775604248047,
      "num_input_tokens_seen": 7746888704,
      "step": 27240,
      "train_runtime": 265391.857,
      "train_tokens_per_second": 29190.378
    },
    {
      "epoch": 0.9641602186609229,
      "grad_norm": 1.4765625,
      "learning_rate": 2.590673575129534e-05,
      "loss": 1.0790922164916992,
      "num_input_tokens_seen": 7749687296,
      "step": 27250,
      "train_runtime": 265485.8201,
      "train_tokens_per_second": 29190.588
    },
    {
      "epoch": 0.9645140389246518,
      "grad_norm": 1.46875,
      "learning_rate": 2.5903258943776116e-05,
      "loss": 1.0659368515014649,
      "num_input_tokens_seen": 7752568768,
      "step": 27260,
      "train_runtime": 265587.6225,
      "train_tokens_per_second": 29190.249
    },
    {
      "epoch": 0.9648678591883806,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5899783535693745e-05,
      "loss": 1.051686668395996,
      "num_input_tokens_seen": 7755390336,
      "step": 27270,
      "train_runtime": 265683.4082,
      "train_tokens_per_second": 29190.345
    },
    {
      "epoch": 0.9652216794521093,
      "grad_norm": 1.5,
      "learning_rate": 2.5896309526109663e-05,
      "loss": 1.0772632598876952,
      "num_input_tokens_seen": 7758272320,
      "step": 27280,
      "train_runtime": 265783.898,
      "train_tokens_per_second": 29190.152
    },
    {
      "epoch": 0.9655754997158381,
      "grad_norm": 1.515625,
      "learning_rate": 2.589283691408621e-05,
      "loss": 1.0933277130126953,
      "num_input_tokens_seen": 7761131648,
      "step": 27290,
      "train_runtime": 265882.2405,
      "train_tokens_per_second": 29190.109
    },
    {
      "epoch": 0.9659293199795669,
      "grad_norm": 1.5078125,
      "learning_rate": 2.588936569868658e-05,
      "loss": 1.0769664764404296,
      "num_input_tokens_seen": 7763973760,
      "step": 27300,
      "train_runtime": 265980.3944,
      "train_tokens_per_second": 29190.023
    },
    {
      "epoch": 0.9662831402432956,
      "grad_norm": 1.421875,
      "learning_rate": 2.5885895878974877e-05,
      "loss": 1.0858171463012696,
      "num_input_tokens_seen": 7766862464,
      "step": 27310,
      "train_runtime": 266081.2809,
      "train_tokens_per_second": 29189.812
    },
    {
      "epoch": 0.9666369605070244,
      "grad_norm": 1.4375,
      "learning_rate": 2.5882427454016055e-05,
      "loss": 1.0894524574279785,
      "num_input_tokens_seen": 7769708480,
      "step": 27320,
      "train_runtime": 266180.0344,
      "train_tokens_per_second": 29189.674
    },
    {
      "epoch": 0.9669907807707532,
      "grad_norm": 1.5078125,
      "learning_rate": 2.587896042287596e-05,
      "loss": 1.0776158332824708,
      "num_input_tokens_seen": 7772516544,
      "step": 27330,
      "train_runtime": 266276.6718,
      "train_tokens_per_second": 29189.626
    },
    {
      "epoch": 0.9673446010344819,
      "grad_norm": 1.484375,
      "learning_rate": 2.5875494784621317e-05,
      "loss": 1.069560718536377,
      "num_input_tokens_seen": 7775338240,
      "step": 27340,
      "train_runtime": 266372.8184,
      "train_tokens_per_second": 29189.683
    },
    {
      "epoch": 0.9676984212982108,
      "grad_norm": 1.5703125,
      "learning_rate": 2.587203053831971e-05,
      "loss": 1.0834737777709962,
      "num_input_tokens_seen": 7778188160,
      "step": 27350,
      "train_runtime": 266471.8531,
      "train_tokens_per_second": 29189.53
    },
    {
      "epoch": 0.9680522415619396,
      "grad_norm": 1.4609375,
      "learning_rate": 2.586856768303961e-05,
      "loss": 1.085575485229492,
      "num_input_tokens_seen": 7781007616,
      "step": 27360,
      "train_runtime": 266568.9186,
      "train_tokens_per_second": 29189.478
    },
    {
      "epoch": 0.9684060618256684,
      "grad_norm": 1.5234375,
      "learning_rate": 2.586510621785036e-05,
      "loss": 1.0810811996459961,
      "num_input_tokens_seen": 7783851840,
      "step": 27370,
      "train_runtime": 266663.3712,
      "train_tokens_per_second": 29189.805
    },
    {
      "epoch": 0.9687598820893971,
      "grad_norm": 1.546875,
      "learning_rate": 2.5861646141822164e-05,
      "loss": 1.0886645317077637,
      "num_input_tokens_seen": 7786691392,
      "step": 27380,
      "train_runtime": 266763.4786,
      "train_tokens_per_second": 29189.496
    },
    {
      "epoch": 0.9691137023531259,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5858187454026106e-05,
      "loss": 1.0835071563720704,
      "num_input_tokens_seen": 7789517312,
      "step": 27390,
      "train_runtime": 266858.215,
      "train_tokens_per_second": 29189.723
    },
    {
      "epoch": 0.9694675226168546,
      "grad_norm": 1.4765625,
      "learning_rate": 2.5854730153534134e-05,
      "loss": 1.0840339660644531,
      "num_input_tokens_seen": 7792367616,
      "step": 27400,
      "train_runtime": 266957.3884,
      "train_tokens_per_second": 29189.556
    },
    {
      "epoch": 0.9698213428805834,
      "grad_norm": 1.53125,
      "learning_rate": 2.585127423941907e-05,
      "loss": 1.0763545989990235,
      "num_input_tokens_seen": 7795244736,
      "step": 27410,
      "train_runtime": 267058.4155,
      "train_tokens_per_second": 29189.287
    },
    {
      "epoch": 0.9701751631443122,
      "grad_norm": 1.5078125,
      "learning_rate": 2.58478197107546e-05,
      "loss": 1.0793272018432618,
      "num_input_tokens_seen": 7798101888,
      "step": 27420,
      "train_runtime": 267155.1714,
      "train_tokens_per_second": 29189.41
    },
    {
      "epoch": 0.9705289834080411,
      "grad_norm": 1.53125,
      "learning_rate": 2.5844366566615273e-05,
      "loss": 1.080540657043457,
      "num_input_tokens_seen": 7801014976,
      "step": 27430,
      "train_runtime": 267255.7067,
      "train_tokens_per_second": 29189.33
    },
    {
      "epoch": 0.9708828036717698,
      "grad_norm": 1.5234375,
      "learning_rate": 2.584091480607651e-05,
      "loss": 1.0805315017700194,
      "num_input_tokens_seen": 7803891904,
      "step": 27440,
      "train_runtime": 267355.6663,
      "train_tokens_per_second": 29189.177
    },
    {
      "epoch": 0.9712366239354986,
      "grad_norm": 1.4375,
      "learning_rate": 2.5837464428214592e-05,
      "loss": 1.0856252670288087,
      "num_input_tokens_seen": 7806784704,
      "step": 27450,
      "train_runtime": 267456.3388,
      "train_tokens_per_second": 29189.006
    },
    {
      "epoch": 0.9715904441992274,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5834015432106666e-05,
      "loss": 1.0732501983642577,
      "num_input_tokens_seen": 7809631744,
      "step": 27460,
      "train_runtime": 267552.8006,
      "train_tokens_per_second": 29189.124
    },
    {
      "epoch": 0.9719442644629561,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5830567816830737e-05,
      "loss": 1.0684146881103516,
      "num_input_tokens_seen": 7812457856,
      "step": 27470,
      "train_runtime": 267649.2058,
      "train_tokens_per_second": 29189.169
    },
    {
      "epoch": 0.9722980847266849,
      "grad_norm": 1.4609375,
      "learning_rate": 2.5827121581465668e-05,
      "loss": 1.0824934005737306,
      "num_input_tokens_seen": 7815289536,
      "step": 27480,
      "train_runtime": 267748.0132,
      "train_tokens_per_second": 29188.973
    },
    {
      "epoch": 0.9726519049904137,
      "grad_norm": 1.4609375,
      "learning_rate": 2.5823676725091193e-05,
      "loss": 1.0845535278320313,
      "num_input_tokens_seen": 7818122176,
      "step": 27490,
      "train_runtime": 267845.5235,
      "train_tokens_per_second": 29188.922
    },
    {
      "epoch": 0.9730057252541424,
      "grad_norm": 1.5,
      "learning_rate": 2.5820233246787902e-05,
      "loss": 1.0888787269592286,
      "num_input_tokens_seen": 7820980032,
      "step": 27500,
      "train_runtime": 267942.3272,
      "train_tokens_per_second": 29189.043
    },
    {
      "epoch": 0.9733595455178713,
      "grad_norm": 1.53125,
      "learning_rate": 2.581679114563723e-05,
      "loss": 1.074323844909668,
      "num_input_tokens_seen": 7823928128,
      "step": 27510,
      "train_runtime": 268046.6643,
      "train_tokens_per_second": 29188.679
    },
    {
      "epoch": 0.9737133657816001,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5813350420721488e-05,
      "loss": 1.0770124435424804,
      "num_input_tokens_seen": 7826748928,
      "step": 27520,
      "train_runtime": 268141.2039,
      "train_tokens_per_second": 29188.908
    },
    {
      "epoch": 0.9740671860453288,
      "grad_norm": 1.4765625,
      "learning_rate": 2.5809911071123834e-05,
      "loss": 1.0684118270874023,
      "num_input_tokens_seen": 7829627584,
      "step": 27530,
      "train_runtime": 268241.1902,
      "train_tokens_per_second": 29188.759
    },
    {
      "epoch": 0.9744210063090576,
      "grad_norm": 1.5625,
      "learning_rate": 2.5806473095928274e-05,
      "loss": 1.0669201850891112,
      "num_input_tokens_seen": 7832470336,
      "step": 27540,
      "train_runtime": 268336.2613,
      "train_tokens_per_second": 29189.012
    },
    {
      "epoch": 0.9747748265727864,
      "grad_norm": 1.546875,
      "learning_rate": 2.5803036494219678e-05,
      "loss": 1.066395378112793,
      "num_input_tokens_seen": 7835371520,
      "step": 27550,
      "train_runtime": 268437.6271,
      "train_tokens_per_second": 29188.797
    },
    {
      "epoch": 0.9751286468365151,
      "grad_norm": 1.5,
      "learning_rate": 2.5799601265083767e-05,
      "loss": 1.0989919662475587,
      "num_input_tokens_seen": 7838242752,
      "step": 27560,
      "train_runtime": 268536.3828,
      "train_tokens_per_second": 29188.755
    },
    {
      "epoch": 0.9754824671002439,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5796167407607113e-05,
      "loss": 1.0709043502807618,
      "num_input_tokens_seen": 7841110848,
      "step": 27570,
      "train_runtime": 268633.4605,
      "train_tokens_per_second": 29188.884
    },
    {
      "epoch": 0.9758362873639727,
      "grad_norm": 1.515625,
      "learning_rate": 2.5792734920877138e-05,
      "loss": 1.0698806762695312,
      "num_input_tokens_seen": 7843947392,
      "step": 27580,
      "train_runtime": 268730.1294,
      "train_tokens_per_second": 29188.939
    },
    {
      "epoch": 0.9761901076277014,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5789303803982114e-05,
      "loss": 1.0741756439208985,
      "num_input_tokens_seen": 7846760832,
      "step": 27590,
      "train_runtime": 268825.3028,
      "train_tokens_per_second": 29189.071
    },
    {
      "epoch": 0.9765439278914303,
      "grad_norm": 1.53125,
      "learning_rate": 2.578587405601115e-05,
      "loss": 1.0901464462280273,
      "num_input_tokens_seen": 7849578048,
      "step": 27600,
      "train_runtime": 268921.4639,
      "train_tokens_per_second": 29189.109
    },
    {
      "epoch": 0.9768977481551591,
      "grad_norm": 1.5,
      "learning_rate": 2.5782445676054233e-05,
      "loss": 1.0760123252868652,
      "num_input_tokens_seen": 7852493312,
      "step": 27610,
      "train_runtime": 269021.685,
      "train_tokens_per_second": 29189.072
    },
    {
      "epoch": 0.9772515684188878,
      "grad_norm": 1.5,
      "learning_rate": 2.577901866320217e-05,
      "loss": 1.0806961059570312,
      "num_input_tokens_seen": 7855302656,
      "step": 27620,
      "train_runtime": 269116.7043,
      "train_tokens_per_second": 29189.205
    },
    {
      "epoch": 0.9776053886826166,
      "grad_norm": 1.53125,
      "learning_rate": 2.5775593016546618e-05,
      "loss": 1.0667445182800293,
      "num_input_tokens_seen": 7858197760,
      "step": 27630,
      "train_runtime": 269217.8684,
      "train_tokens_per_second": 29188.99
    },
    {
      "epoch": 0.9779592089463454,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5772168735180084e-05,
      "loss": 1.0754318237304688,
      "num_input_tokens_seen": 7861040896,
      "step": 27640,
      "train_runtime": 269315.9781,
      "train_tokens_per_second": 29188.914
    },
    {
      "epoch": 0.9783130292100741,
      "grad_norm": 1.4765625,
      "learning_rate": 2.5768745818195927e-05,
      "loss": 1.0721765518188477,
      "num_input_tokens_seen": 7863913856,
      "step": 27650,
      "train_runtime": 269414.8174,
      "train_tokens_per_second": 29188.869
    },
    {
      "epoch": 0.9786668494738029,
      "grad_norm": 1.4453125,
      "learning_rate": 2.5765324264688327e-05,
      "loss": 1.0786039352416992,
      "num_input_tokens_seen": 7866820160,
      "step": 27660,
      "train_runtime": 269514.7675,
      "train_tokens_per_second": 29188.828
    },
    {
      "epoch": 0.9790206697375317,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5761904073752323e-05,
      "loss": 1.0736366271972657,
      "num_input_tokens_seen": 7869606464,
      "step": 27670,
      "train_runtime": 269607.0216,
      "train_tokens_per_second": 29189.175
    },
    {
      "epoch": 0.9793744900012605,
      "grad_norm": 1.515625,
      "learning_rate": 2.5758485244483788e-05,
      "loss": 1.079141616821289,
      "num_input_tokens_seen": 7872438336,
      "step": 27680,
      "train_runtime": 269704.4539,
      "train_tokens_per_second": 29189.13
    },
    {
      "epoch": 0.9797283102649893,
      "grad_norm": 1.5,
      "learning_rate": 2.5755067775979443e-05,
      "loss": 1.0794377326965332,
      "num_input_tokens_seen": 7875197248,
      "step": 27690,
      "train_runtime": 269795.6957,
      "train_tokens_per_second": 29189.484
    },
    {
      "epoch": 0.9800821305287181,
      "grad_norm": 1.53125,
      "learning_rate": 2.5751651667336824e-05,
      "loss": 1.0809971809387207,
      "num_input_tokens_seen": 7878105984,
      "step": 27700,
      "train_runtime": 269896.9846,
      "train_tokens_per_second": 29189.307
    },
    {
      "epoch": 0.9804359507924468,
      "grad_norm": 1.484375,
      "learning_rate": 2.5748236917654333e-05,
      "loss": 1.0715396881103516,
      "num_input_tokens_seen": 7880935232,
      "step": 27710,
      "train_runtime": 269990.5836,
      "train_tokens_per_second": 29189.667
    },
    {
      "epoch": 0.9807897710561756,
      "grad_norm": 1.5390625,
      "learning_rate": 2.5744823526031202e-05,
      "loss": 1.0838909149169922,
      "num_input_tokens_seen": 7883814720,
      "step": 27720,
      "train_runtime": 270088.4354,
      "train_tokens_per_second": 29189.753
    },
    {
      "epoch": 0.9811435913199044,
      "grad_norm": 1.4765625,
      "learning_rate": 2.5741411491567484e-05,
      "loss": 1.0846062660217286,
      "num_input_tokens_seen": 7886692032,
      "step": 27730,
      "train_runtime": 270187.4806,
      "train_tokens_per_second": 29189.702
    },
    {
      "epoch": 0.9814974115836331,
      "grad_norm": 1.4609375,
      "learning_rate": 2.573800081336408e-05,
      "loss": 1.077780532836914,
      "num_input_tokens_seen": 7889550912,
      "step": 27740,
      "train_runtime": 270285.32,
      "train_tokens_per_second": 29189.713
    },
    {
      "epoch": 0.9818512318473619,
      "grad_norm": 1.5546875,
      "learning_rate": 2.573459149052272e-05,
      "loss": 1.0764476776123046,
      "num_input_tokens_seen": 7892358528,
      "step": 27750,
      "train_runtime": 270378.5473,
      "train_tokens_per_second": 29190.032
    },
    {
      "epoch": 0.9822050521110908,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5731183522145968e-05,
      "loss": 1.0945233345031737,
      "num_input_tokens_seen": 7895227200,
      "step": 27760,
      "train_runtime": 270479.5364,
      "train_tokens_per_second": 29189.739
    },
    {
      "epoch": 0.9825588723748195,
      "grad_norm": 1.4140625,
      "learning_rate": 2.5727776907337226e-05,
      "loss": 1.0698240280151368,
      "num_input_tokens_seen": 7898030208,
      "step": 27770,
      "train_runtime": 270573.2773,
      "train_tokens_per_second": 29189.986
    },
    {
      "epoch": 0.9829126926385483,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5724371645200708e-05,
      "loss": 1.0922103881835938,
      "num_input_tokens_seen": 7900816960,
      "step": 27780,
      "train_runtime": 270670.7337,
      "train_tokens_per_second": 29189.772
    },
    {
      "epoch": 0.9832665129022771,
      "grad_norm": 1.53125,
      "learning_rate": 2.572096773484147e-05,
      "loss": 1.0953201293945312,
      "num_input_tokens_seen": 7903646848,
      "step": 27790,
      "train_runtime": 270766.7707,
      "train_tokens_per_second": 29189.87
    },
    {
      "epoch": 0.9836203331660058,
      "grad_norm": 1.5,
      "learning_rate": 2.5717565175365416e-05,
      "loss": 1.0674108505249023,
      "num_input_tokens_seen": 7906475520,
      "step": 27800,
      "train_runtime": 270861.5972,
      "train_tokens_per_second": 29190.094
    },
    {
      "epoch": 0.9839741534297346,
      "grad_norm": 1.53125,
      "learning_rate": 2.571416396587924e-05,
      "loss": 1.0883499145507813,
      "num_input_tokens_seen": 7909321216,
      "step": 27810,
      "train_runtime": 270959.919,
      "train_tokens_per_second": 29190.004
    },
    {
      "epoch": 0.9843279736934634,
      "grad_norm": 1.5703125,
      "learning_rate": 2.5710764105490486e-05,
      "loss": 1.0881172180175782,
      "num_input_tokens_seen": 7912120320,
      "step": 27820,
      "train_runtime": 271053.8938,
      "train_tokens_per_second": 29190.211
    },
    {
      "epoch": 0.9846817939571921,
      "grad_norm": 1.46875,
      "learning_rate": 2.570736559330752e-05,
      "loss": 1.0804701805114747,
      "num_input_tokens_seen": 7914969536,
      "step": 27830,
      "train_runtime": 271151.2861,
      "train_tokens_per_second": 29190.234
    },
    {
      "epoch": 0.9850356142209209,
      "grad_norm": 1.5390625,
      "learning_rate": 2.570396842843953e-05,
      "loss": 1.0784674644470216,
      "num_input_tokens_seen": 7917792064,
      "step": 27840,
      "train_runtime": 271247.0839,
      "train_tokens_per_second": 29190.331
    },
    {
      "epoch": 0.9853894344846498,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5700572609996526e-05,
      "loss": 1.0708795547485352,
      "num_input_tokens_seen": 7920633152,
      "step": 27850,
      "train_runtime": 271345.5165,
      "train_tokens_per_second": 29190.212
    },
    {
      "epoch": 0.9857432547483785,
      "grad_norm": 1.4765625,
      "learning_rate": 2.5697178137089357e-05,
      "loss": 1.068554973602295,
      "num_input_tokens_seen": 7923523520,
      "step": 27860,
      "train_runtime": 271443.0465,
      "train_tokens_per_second": 29190.372
    },
    {
      "epoch": 0.9860970750121073,
      "grad_norm": 1.390625,
      "learning_rate": 2.569378500882966e-05,
      "loss": 1.077509880065918,
      "num_input_tokens_seen": 7926298176,
      "step": 27870,
      "train_runtime": 271539.0512,
      "train_tokens_per_second": 29190.27
    },
    {
      "epoch": 0.9864508952758361,
      "grad_norm": 1.5078125,
      "learning_rate": 2.569039322432994e-05,
      "loss": 1.0904461860656738,
      "num_input_tokens_seen": 7929133824,
      "step": 27880,
      "train_runtime": 271634.703,
      "train_tokens_per_second": 29190.43
    },
    {
      "epoch": 0.9868047155395648,
      "grad_norm": 1.5546875,
      "learning_rate": 2.5687002782703474e-05,
      "loss": 1.0774654388427733,
      "num_input_tokens_seen": 7931983168,
      "step": 27890,
      "train_runtime": 271733.0054,
      "train_tokens_per_second": 29190.356
    },
    {
      "epoch": 0.9871585358032936,
      "grad_norm": 1.53125,
      "learning_rate": 2.568361368306439e-05,
      "loss": 1.0760505676269532,
      "num_input_tokens_seen": 7934843328,
      "step": 27900,
      "train_runtime": 271832.6524,
      "train_tokens_per_second": 29190.177
    },
    {
      "epoch": 0.9875123560670224,
      "grad_norm": 1.515625,
      "learning_rate": 2.5680225924527623e-05,
      "loss": 1.0733545303344727,
      "num_input_tokens_seen": 7937700352,
      "step": 27910,
      "train_runtime": 271930.15,
      "train_tokens_per_second": 29190.218
    },
    {
      "epoch": 0.9878661763307511,
      "grad_norm": 1.609375,
      "learning_rate": 2.5676839506208927e-05,
      "loss": 1.0811322212219239,
      "num_input_tokens_seen": 7940547648,
      "step": 27920,
      "train_runtime": 272027.0864,
      "train_tokens_per_second": 29190.283
    },
    {
      "epoch": 0.98821999659448,
      "grad_norm": 1.5078125,
      "learning_rate": 2.567345442722487e-05,
      "loss": 1.0765664100646972,
      "num_input_tokens_seen": 7943389504,
      "step": 27930,
      "train_runtime": 272122.5577,
      "train_tokens_per_second": 29190.485
    },
    {
      "epoch": 0.9885738168582088,
      "grad_norm": 1.484375,
      "learning_rate": 2.567007068669283e-05,
      "loss": 1.0716974258422851,
      "num_input_tokens_seen": 7946204800,
      "step": 27940,
      "train_runtime": 272216.2076,
      "train_tokens_per_second": 29190.785
    },
    {
      "epoch": 0.9889276371219375,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5666688283731016e-05,
      "loss": 1.074761199951172,
      "num_input_tokens_seen": 7948974080,
      "step": 27950,
      "train_runtime": 272306.8401,
      "train_tokens_per_second": 29191.239
    },
    {
      "epoch": 0.9892814573856663,
      "grad_norm": 1.421875,
      "learning_rate": 2.5663307217458428e-05,
      "loss": 1.0852390289306642,
      "num_input_tokens_seen": 7951878912,
      "step": 27960,
      "train_runtime": 272406.1756,
      "train_tokens_per_second": 29191.258
    },
    {
      "epoch": 0.9896352776493951,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5659927486994893e-05,
      "loss": 1.075189971923828,
      "num_input_tokens_seen": 7954701824,
      "step": 27970,
      "train_runtime": 272502.0673,
      "train_tokens_per_second": 29191.345
    },
    {
      "epoch": 0.9899890979131238,
      "grad_norm": 1.515625,
      "learning_rate": 2.565654909146105e-05,
      "loss": 1.0853957176208495,
      "num_input_tokens_seen": 7957524096,
      "step": 27980,
      "train_runtime": 272599.2147,
      "train_tokens_per_second": 29191.295
    },
    {
      "epoch": 0.9903429181768526,
      "grad_norm": 1.609375,
      "learning_rate": 2.5653172029978346e-05,
      "loss": 1.094355010986328,
      "num_input_tokens_seen": 7960404800,
      "step": 27990,
      "train_runtime": 272696.3696,
      "train_tokens_per_second": 29191.459
    },
    {
      "epoch": 0.9906967384405814,
      "grad_norm": 1.453125,
      "learning_rate": 2.5649796301669014e-05,
      "loss": 1.0694226264953612,
      "num_input_tokens_seen": 7963204224,
      "step": 28000,
      "train_runtime": 272792.0419,
      "train_tokens_per_second": 29191.483
    },
    {
      "epoch": 0.9910505587043102,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5646421905656148e-05,
      "loss": 1.0809826850891113,
      "num_input_tokens_seen": 7966060928,
      "step": 28010,
      "train_runtime": 272888.7173,
      "train_tokens_per_second": 29191.61
    },
    {
      "epoch": 0.991404378968039,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5643048841063587e-05,
      "loss": 1.0588871955871582,
      "num_input_tokens_seen": 7968937280,
      "step": 28020,
      "train_runtime": 272987.0521,
      "train_tokens_per_second": 29191.631
    },
    {
      "epoch": 0.9917581992317678,
      "grad_norm": 1.5234375,
      "learning_rate": 2.563967710701603e-05,
      "loss": 1.0705137252807617,
      "num_input_tokens_seen": 7971751104,
      "step": 28030,
      "train_runtime": 273082.9606,
      "train_tokens_per_second": 29191.683
    },
    {
      "epoch": 0.9921120194954965,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5636306702638946e-05,
      "loss": 1.0820624351501464,
      "num_input_tokens_seen": 7974506944,
      "step": 28040,
      "train_runtime": 273175.4305,
      "train_tokens_per_second": 29191.889
    },
    {
      "epoch": 0.9924658397592253,
      "grad_norm": 1.515625,
      "learning_rate": 2.5632937627058624e-05,
      "loss": 1.0849373817443848,
      "num_input_tokens_seen": 7977336320,
      "step": 28050,
      "train_runtime": 273271.1204,
      "train_tokens_per_second": 29192.021
    },
    {
      "epoch": 0.9928196600229541,
      "grad_norm": 1.546875,
      "learning_rate": 2.562956987940216e-05,
      "loss": 1.0767066955566407,
      "num_input_tokens_seen": 7980157952,
      "step": 28060,
      "train_runtime": 273366.2609,
      "train_tokens_per_second": 29192.183
    },
    {
      "epoch": 0.9931734802866828,
      "grad_norm": 1.515625,
      "learning_rate": 2.5626203458797432e-05,
      "loss": 1.081617546081543,
      "num_input_tokens_seen": 7983067456,
      "step": 28070,
      "train_runtime": 273467.7376,
      "train_tokens_per_second": 29191.99
    },
    {
      "epoch": 0.9935273005504116,
      "grad_norm": 1.4453125,
      "learning_rate": 2.562283836437315e-05,
      "loss": 1.0542971611022949,
      "num_input_tokens_seen": 7985969856,
      "step": 28080,
      "train_runtime": 273567.9491,
      "train_tokens_per_second": 29191.906
    },
    {
      "epoch": 0.9938811208141404,
      "grad_norm": 1.5546875,
      "learning_rate": 2.561947459525879e-05,
      "loss": 1.0764500617980957,
      "num_input_tokens_seen": 7988810048,
      "step": 28090,
      "train_runtime": 273663.805,
      "train_tokens_per_second": 29192.059
    },
    {
      "epoch": 0.9942349410778692,
      "grad_norm": 1.546875,
      "learning_rate": 2.561611215058466e-05,
      "loss": 1.0756690979003907,
      "num_input_tokens_seen": 7991675072,
      "step": 28100,
      "train_runtime": 273762.467,
      "train_tokens_per_second": 29192.004
    },
    {
      "epoch": 0.994588761341598,
      "grad_norm": 1.453125,
      "learning_rate": 2.5612751029481845e-05,
      "loss": 1.0747888565063477,
      "num_input_tokens_seen": 7994518144,
      "step": 28110,
      "train_runtime": 273858.9846,
      "train_tokens_per_second": 29192.097
    },
    {
      "epoch": 0.9949425816053268,
      "grad_norm": 1.4765625,
      "learning_rate": 2.560939123108225e-05,
      "loss": 1.064966583251953,
      "num_input_tokens_seen": 7997373312,
      "step": 28120,
      "train_runtime": 273959.6891,
      "train_tokens_per_second": 29191.789
    },
    {
      "epoch": 0.9952964018690555,
      "grad_norm": 1.5078125,
      "learning_rate": 2.560603275451855e-05,
      "loss": 1.0838247299194337,
      "num_input_tokens_seen": 8000276352,
      "step": 28130,
      "train_runtime": 274061.7482,
      "train_tokens_per_second": 29191.51
    },
    {
      "epoch": 0.9956502221327843,
      "grad_norm": 1.5703125,
      "learning_rate": 2.5602675598924227e-05,
      "loss": 1.0842864036560058,
      "num_input_tokens_seen": 8003102528,
      "step": 28140,
      "train_runtime": 274154.7946,
      "train_tokens_per_second": 29191.912
    },
    {
      "epoch": 0.9960040423965131,
      "grad_norm": 1.515625,
      "learning_rate": 2.5599319763433566e-05,
      "loss": 1.0867082595825195,
      "num_input_tokens_seen": 8005923840,
      "step": 28150,
      "train_runtime": 274252.3358,
      "train_tokens_per_second": 29191.816
    },
    {
      "epoch": 0.9963578626602418,
      "grad_norm": 1.515625,
      "learning_rate": 2.559596524718164e-05,
      "loss": 1.0674554824829101,
      "num_input_tokens_seen": 8008785664,
      "step": 28160,
      "train_runtime": 274349.5547,
      "train_tokens_per_second": 29191.903
    },
    {
      "epoch": 0.9967116829239706,
      "grad_norm": 1.4609375,
      "learning_rate": 2.559261204930431e-05,
      "loss": 1.091507911682129,
      "num_input_tokens_seen": 8011625856,
      "step": 28170,
      "train_runtime": 274446.9892,
      "train_tokens_per_second": 29191.888
    },
    {
      "epoch": 0.9970655031876995,
      "grad_norm": 1.4765625,
      "learning_rate": 2.558926016893824e-05,
      "loss": 1.0768211364746094,
      "num_input_tokens_seen": 8014461440,
      "step": 28180,
      "train_runtime": 274542.2935,
      "train_tokens_per_second": 29192.083
    },
    {
      "epoch": 0.9974193234514283,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5585909605220877e-05,
      "loss": 1.0855039596557616,
      "num_input_tokens_seen": 8017315840,
      "step": 28190,
      "train_runtime": 274641.2073,
      "train_tokens_per_second": 29191.963
    },
    {
      "epoch": 0.997773143715157,
      "grad_norm": 1.5078125,
      "learning_rate": 2.558256035729046e-05,
      "loss": 1.0816872596740723,
      "num_input_tokens_seen": 8020148032,
      "step": 28200,
      "train_runtime": 274736.4116,
      "train_tokens_per_second": 29192.155
    },
    {
      "epoch": 0.9981269639788858,
      "grad_norm": 1.453125,
      "learning_rate": 2.557921242428602e-05,
      "loss": 1.086631679534912,
      "num_input_tokens_seen": 8022949056,
      "step": 28210,
      "train_runtime": 274831.3067,
      "train_tokens_per_second": 29192.268
    },
    {
      "epoch": 0.9984807842426145,
      "grad_norm": 1.4765625,
      "learning_rate": 2.557586580534737e-05,
      "loss": 1.056513500213623,
      "num_input_tokens_seen": 8025749568,
      "step": 28220,
      "train_runtime": 274925.6151,
      "train_tokens_per_second": 29192.44
    },
    {
      "epoch": 0.9988346045063433,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5572520499615127e-05,
      "loss": 1.0795278549194336,
      "num_input_tokens_seen": 8028631680,
      "step": 28230,
      "train_runtime": 275025.6763,
      "train_tokens_per_second": 29192.299
    },
    {
      "epoch": 0.9991884247700721,
      "grad_norm": 1.4609375,
      "learning_rate": 2.5569176506230667e-05,
      "loss": 1.08691463470459,
      "num_input_tokens_seen": 8031430592,
      "step": 28240,
      "train_runtime": 275121.853,
      "train_tokens_per_second": 29192.267
    },
    {
      "epoch": 0.9995422450338008,
      "grad_norm": 1.390625,
      "learning_rate": 2.5565833824336183e-05,
      "loss": 1.0855924606323242,
      "num_input_tokens_seen": 8034253696,
      "step": 28250,
      "train_runtime": 275215.4158,
      "train_tokens_per_second": 29192.601
    },
    {
      "epoch": 0.9998960652975297,
      "grad_norm": 1.5,
      "learning_rate": 2.5562492453074633e-05,
      "loss": 1.0761659622192383,
      "num_input_tokens_seen": 8037056512,
      "step": 28260,
      "train_runtime": 275307.6235,
      "train_tokens_per_second": 29193.004
    },
    {
      "epoch": 1.0002476741846102,
      "grad_norm": 1.5078125,
      "learning_rate": 2.555915239158976e-05,
      "loss": 1.0461535453796387,
      "num_input_tokens_seen": 8039909376,
      "step": 28270,
      "train_runtime": 275416.9825,
      "train_tokens_per_second": 29191.771
    },
    {
      "epoch": 1.000601494448339,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5555813639026093e-05,
      "loss": 1.0417590141296387,
      "num_input_tokens_seen": 8042756800,
      "step": 28280,
      "train_runtime": 275517.5656,
      "train_tokens_per_second": 29191.448
    },
    {
      "epoch": 1.0009553147120678,
      "grad_norm": 1.4375,
      "learning_rate": 2.5552476194528947e-05,
      "loss": 1.0575657844543458,
      "num_input_tokens_seen": 8045619328,
      "step": 28290,
      "train_runtime": 275616.865,
      "train_tokens_per_second": 29191.317
    },
    {
      "epoch": 1.0013091349757965,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5549140057244413e-05,
      "loss": 1.0269801139831543,
      "num_input_tokens_seen": 8048455744,
      "step": 28300,
      "train_runtime": 275715.9639,
      "train_tokens_per_second": 29191.113
    },
    {
      "epoch": 1.0016629552395253,
      "grad_norm": 1.484375,
      "learning_rate": 2.5545805226319362e-05,
      "loss": 1.0488599777221679,
      "num_input_tokens_seen": 8051281152,
      "step": 28310,
      "train_runtime": 275813.2384,
      "train_tokens_per_second": 29191.061
    },
    {
      "epoch": 1.002016775503254,
      "grad_norm": 1.4609375,
      "learning_rate": 2.5542471700901453e-05,
      "loss": 1.0414800643920898,
      "num_input_tokens_seen": 8054102272,
      "step": 28320,
      "train_runtime": 275908.1793,
      "train_tokens_per_second": 29191.241
    },
    {
      "epoch": 1.0023705957669828,
      "grad_norm": 1.5859375,
      "learning_rate": 2.5539139480139113e-05,
      "loss": 1.052264404296875,
      "num_input_tokens_seen": 8056987648,
      "step": 28330,
      "train_runtime": 276008.6164,
      "train_tokens_per_second": 29191.073
    },
    {
      "epoch": 1.0027244160307116,
      "grad_norm": 1.4609375,
      "learning_rate": 2.5535808563181546e-05,
      "loss": 1.049784278869629,
      "num_input_tokens_seen": 8059853504,
      "step": 28340,
      "train_runtime": 276105.2063,
      "train_tokens_per_second": 29191.241
    },
    {
      "epoch": 1.0030782362944404,
      "grad_norm": 1.4296875,
      "learning_rate": 2.553247894917874e-05,
      "loss": 1.041153335571289,
      "num_input_tokens_seen": 8062724288,
      "step": 28350,
      "train_runtime": 276203.152,
      "train_tokens_per_second": 29191.283
    },
    {
      "epoch": 1.0034320565581691,
      "grad_norm": 1.4765625,
      "learning_rate": 2.5529150637281453e-05,
      "loss": 1.0391952514648437,
      "num_input_tokens_seen": 8065563840,
      "step": 28360,
      "train_runtime": 276302.6845,
      "train_tokens_per_second": 29191.044
    },
    {
      "epoch": 1.003785876821898,
      "grad_norm": 1.484375,
      "learning_rate": 2.552582362664122e-05,
      "loss": 1.0343010902404786,
      "num_input_tokens_seen": 8068325568,
      "step": 28370,
      "train_runtime": 276395.1137,
      "train_tokens_per_second": 29191.274
    },
    {
      "epoch": 1.0041396970856267,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5522497916410353e-05,
      "loss": 1.0336405754089355,
      "num_input_tokens_seen": 8071166848,
      "step": 28380,
      "train_runtime": 276491.7165,
      "train_tokens_per_second": 29191.351
    },
    {
      "epoch": 1.0044935173493554,
      "grad_norm": 1.46875,
      "learning_rate": 2.5519173505741933e-05,
      "loss": 1.0573418617248536,
      "num_input_tokens_seen": 8074037760,
      "step": 28390,
      "train_runtime": 276592.852,
      "train_tokens_per_second": 29191.057
    },
    {
      "epoch": 1.0048473376130842,
      "grad_norm": 1.546875,
      "learning_rate": 2.551585039378981e-05,
      "loss": 1.048826026916504,
      "num_input_tokens_seen": 8076849536,
      "step": 28400,
      "train_runtime": 276688.5907,
      "train_tokens_per_second": 29191.119
    },
    {
      "epoch": 1.005201157876813,
      "grad_norm": 1.5078125,
      "learning_rate": 2.551252857970861e-05,
      "loss": 1.0556368827819824,
      "num_input_tokens_seen": 8079745472,
      "step": 28410,
      "train_runtime": 276788.3542,
      "train_tokens_per_second": 29191.06
    },
    {
      "epoch": 1.0055549781405417,
      "grad_norm": 1.6171875,
      "learning_rate": 2.5509208062653734e-05,
      "loss": 1.046487045288086,
      "num_input_tokens_seen": 8082548672,
      "step": 28420,
      "train_runtime": 276883.6851,
      "train_tokens_per_second": 29191.134
    },
    {
      "epoch": 1.0059087984042707,
      "grad_norm": 1.4765625,
      "learning_rate": 2.5505888841781333e-05,
      "loss": 1.0456127166748046,
      "num_input_tokens_seen": 8085400384,
      "step": 28430,
      "train_runtime": 276981.9673,
      "train_tokens_per_second": 29191.071
    },
    {
      "epoch": 1.0062626186679995,
      "grad_norm": 1.546875,
      "learning_rate": 2.5502570916248353e-05,
      "loss": 1.0565091133117677,
      "num_input_tokens_seen": 8088302272,
      "step": 28440,
      "train_runtime": 277083.7319,
      "train_tokens_per_second": 29190.823
    },
    {
      "epoch": 1.0066164389317283,
      "grad_norm": 1.5390625,
      "learning_rate": 2.5499254285212486e-05,
      "loss": 1.0428768157958985,
      "num_input_tokens_seen": 8091105088,
      "step": 28450,
      "train_runtime": 277177.3537,
      "train_tokens_per_second": 29191.076
    },
    {
      "epoch": 1.006970259195457,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5495938947832204e-05,
      "loss": 1.0437034606933593,
      "num_input_tokens_seen": 8093894528,
      "step": 28460,
      "train_runtime": 277273.3659,
      "train_tokens_per_second": 29191.028
    },
    {
      "epoch": 1.0073240794591858,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5492624903266732e-05,
      "loss": 1.0500662803649903,
      "num_input_tokens_seen": 8096779008,
      "step": 28470,
      "train_runtime": 277371.8951,
      "train_tokens_per_second": 29191.058
    },
    {
      "epoch": 1.0076778997229145,
      "grad_norm": 1.515625,
      "learning_rate": 2.548931215067607e-05,
      "loss": 1.058894157409668,
      "num_input_tokens_seen": 8099626048,
      "step": 28480,
      "train_runtime": 277469.7007,
      "train_tokens_per_second": 29191.029
    },
    {
      "epoch": 1.0080317199866433,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5486000689220985e-05,
      "loss": 1.0497917175292968,
      "num_input_tokens_seen": 8102472448,
      "step": 28490,
      "train_runtime": 277565.7006,
      "train_tokens_per_second": 29191.188
    },
    {
      "epoch": 1.008385540250372,
      "grad_norm": 1.5625,
      "learning_rate": 2.5482690518062994e-05,
      "loss": 1.0561471939086915,
      "num_input_tokens_seen": 8105298176,
      "step": 28500,
      "train_runtime": 277663.5394,
      "train_tokens_per_second": 29191.078
    },
    {
      "epoch": 1.0087393605141008,
      "grad_norm": 1.578125,
      "learning_rate": 2.547938163636439e-05,
      "loss": 1.034977912902832,
      "num_input_tokens_seen": 8108137024,
      "step": 28510,
      "train_runtime": 277760.1941,
      "train_tokens_per_second": 29191.141
    },
    {
      "epoch": 1.0090931807778296,
      "grad_norm": 1.46875,
      "learning_rate": 2.5476074043288212e-05,
      "loss": 1.0483784675598145,
      "num_input_tokens_seen": 8110957248,
      "step": 28520,
      "train_runtime": 277854.8922,
      "train_tokens_per_second": 29191.342
    },
    {
      "epoch": 1.0094470010415584,
      "grad_norm": 1.5390625,
      "learning_rate": 2.547276773799827e-05,
      "loss": 1.052114486694336,
      "num_input_tokens_seen": 8113789056,
      "step": 28530,
      "train_runtime": 277949.4019,
      "train_tokens_per_second": 29191.605
    },
    {
      "epoch": 1.0098008213052871,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5469462719659138e-05,
      "loss": 1.0433934211730957,
      "num_input_tokens_seen": 8116633408,
      "step": 28540,
      "train_runtime": 278049.5238,
      "train_tokens_per_second": 29191.323
    },
    {
      "epoch": 1.010154641569016,
      "grad_norm": 1.53125,
      "learning_rate": 2.5466158987436135e-05,
      "loss": 1.0439754486083985,
      "num_input_tokens_seen": 8119549888,
      "step": 28550,
      "train_runtime": 278151.2818,
      "train_tokens_per_second": 29191.129
    },
    {
      "epoch": 1.0105084618327447,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5462856540495345e-05,
      "loss": 1.0415685653686524,
      "num_input_tokens_seen": 8122393088,
      "step": 28560,
      "train_runtime": 278248.9951,
      "train_tokens_per_second": 29191.096
    },
    {
      "epoch": 1.0108622820964734,
      "grad_norm": 1.5390625,
      "learning_rate": 2.5459555378003607e-05,
      "loss": 1.0535131454467774,
      "num_input_tokens_seen": 8125268992,
      "step": 28570,
      "train_runtime": 278351.2624,
      "train_tokens_per_second": 29190.703
    },
    {
      "epoch": 1.0112161023602022,
      "grad_norm": 1.4453125,
      "learning_rate": 2.545625549912853e-05,
      "loss": 1.0525379180908203,
      "num_input_tokens_seen": 8128035648,
      "step": 28580,
      "train_runtime": 278445.0144,
      "train_tokens_per_second": 29190.81
    },
    {
      "epoch": 1.011569922623931,
      "grad_norm": 1.53125,
      "learning_rate": 2.5452956903038445e-05,
      "loss": 1.047139549255371,
      "num_input_tokens_seen": 8130815040,
      "step": 28590,
      "train_runtime": 278538.075,
      "train_tokens_per_second": 29191.036
    },
    {
      "epoch": 1.01192374288766,
      "grad_norm": 1.5,
      "learning_rate": 2.5449659588902468e-05,
      "loss": 1.043433952331543,
      "num_input_tokens_seen": 8133671872,
      "step": 28600,
      "train_runtime": 278637.0429,
      "train_tokens_per_second": 29190.921
    },
    {
      "epoch": 1.0122775631513887,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5446363555890464e-05,
      "loss": 1.0490514755249023,
      "num_input_tokens_seen": 8136553088,
      "step": 28610,
      "train_runtime": 278734.772,
      "train_tokens_per_second": 29191.023
    },
    {
      "epoch": 1.0126313834151175,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5443068803173025e-05,
      "loss": 1.0465084075927735,
      "num_input_tokens_seen": 8139360896,
      "step": 28620,
      "train_runtime": 278829.9859,
      "train_tokens_per_second": 29191.125
    },
    {
      "epoch": 1.0129852036788463,
      "grad_norm": 1.453125,
      "learning_rate": 2.5439775329921533e-05,
      "loss": 1.0498362541198731,
      "num_input_tokens_seen": 8142155072,
      "step": 28630,
      "train_runtime": 278923.2515,
      "train_tokens_per_second": 29191.382
    },
    {
      "epoch": 1.013339023942575,
      "grad_norm": 1.6015625,
      "learning_rate": 2.5436483135308092e-05,
      "loss": 1.0487951278686523,
      "num_input_tokens_seen": 8144966400,
      "step": 28640,
      "train_runtime": 279019.0008,
      "train_tokens_per_second": 29191.44
    },
    {
      "epoch": 1.0136928442063038,
      "grad_norm": 1.453125,
      "learning_rate": 2.543319221850557e-05,
      "loss": 1.0545931816101075,
      "num_input_tokens_seen": 8147819264,
      "step": 28650,
      "train_runtime": 279115.6656,
      "train_tokens_per_second": 29191.551
    },
    {
      "epoch": 1.0140466644700326,
      "grad_norm": 1.5390625,
      "learning_rate": 2.542990257868757e-05,
      "loss": 1.0500198364257813,
      "num_input_tokens_seen": 8150625984,
      "step": 28660,
      "train_runtime": 279211.676,
      "train_tokens_per_second": 29191.566
    },
    {
      "epoch": 1.0144004847337613,
      "grad_norm": 1.5,
      "learning_rate": 2.542661421502846e-05,
      "loss": 1.0482884407043458,
      "num_input_tokens_seen": 8153499264,
      "step": 28670,
      "train_runtime": 279309.5145,
      "train_tokens_per_second": 29191.627
    },
    {
      "epoch": 1.01475430499749,
      "grad_norm": 1.5,
      "learning_rate": 2.5423327126703344e-05,
      "loss": 1.048494529724121,
      "num_input_tokens_seen": 8156353152,
      "step": 28680,
      "train_runtime": 279406.7758,
      "train_tokens_per_second": 29191.68
    },
    {
      "epoch": 1.0151081252612189,
      "grad_norm": 1.5,
      "learning_rate": 2.5420041312888078e-05,
      "loss": 1.0693546295166017,
      "num_input_tokens_seen": 8159211072,
      "step": 28690,
      "train_runtime": 279503.9132,
      "train_tokens_per_second": 29191.76
    },
    {
      "epoch": 1.0154619455249476,
      "grad_norm": 1.5703125,
      "learning_rate": 2.5416756772759254e-05,
      "loss": 1.04472074508667,
      "num_input_tokens_seen": 8162032448,
      "step": 28700,
      "train_runtime": 279597.2143,
      "train_tokens_per_second": 29192.109
    },
    {
      "epoch": 1.0158157657886764,
      "grad_norm": 1.5390625,
      "learning_rate": 2.5413473505494222e-05,
      "loss": 1.05493221282959,
      "num_input_tokens_seen": 8164826816,
      "step": 28710,
      "train_runtime": 279694.5835,
      "train_tokens_per_second": 29191.938
    },
    {
      "epoch": 1.0161695860524051,
      "grad_norm": 1.4609375,
      "learning_rate": 2.5410191510271063e-05,
      "loss": 1.036782455444336,
      "num_input_tokens_seen": 8167666688,
      "step": 28720,
      "train_runtime": 279790.8071,
      "train_tokens_per_second": 29192.048
    },
    {
      "epoch": 1.016523406316134,
      "grad_norm": 1.484375,
      "learning_rate": 2.5406910786268613e-05,
      "loss": 1.0539432525634767,
      "num_input_tokens_seen": 8170509952,
      "step": 28730,
      "train_runtime": 279889.4772,
      "train_tokens_per_second": 29191.915
    },
    {
      "epoch": 1.0168772265798627,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5403631332666444e-05,
      "loss": 1.06082763671875,
      "num_input_tokens_seen": 8173393088,
      "step": 28740,
      "train_runtime": 279987.6446,
      "train_tokens_per_second": 29191.978
    },
    {
      "epoch": 1.0172310468435914,
      "grad_norm": 1.5546875,
      "learning_rate": 2.5400353148644863e-05,
      "loss": 1.0518483161926269,
      "num_input_tokens_seen": 8176212416,
      "step": 28750,
      "train_runtime": 280084.6557,
      "train_tokens_per_second": 29191.933
    },
    {
      "epoch": 1.0175848671073202,
      "grad_norm": 1.546875,
      "learning_rate": 2.5397076233384925e-05,
      "loss": 1.0547897338867187,
      "num_input_tokens_seen": 8179049152,
      "step": 28760,
      "train_runtime": 280180.7249,
      "train_tokens_per_second": 29192.048
    },
    {
      "epoch": 1.0179386873710492,
      "grad_norm": 1.5,
      "learning_rate": 2.539380058606843e-05,
      "loss": 1.0515294075012207,
      "num_input_tokens_seen": 8181930752,
      "step": 28770,
      "train_runtime": 280279.034,
      "train_tokens_per_second": 29192.09
    },
    {
      "epoch": 1.018292507634778,
      "grad_norm": 1.5703125,
      "learning_rate": 2.5390526205877895e-05,
      "loss": 1.0550987243652343,
      "num_input_tokens_seen": 8184747072,
      "step": 28780,
      "train_runtime": 280374.1012,
      "train_tokens_per_second": 29192.237
    },
    {
      "epoch": 1.0186463278985067,
      "grad_norm": 1.546875,
      "learning_rate": 2.53872530919966e-05,
      "loss": 1.0469552993774414,
      "num_input_tokens_seen": 8187612480,
      "step": 28790,
      "train_runtime": 280474.4117,
      "train_tokens_per_second": 29192.012
    },
    {
      "epoch": 1.0190001481622355,
      "grad_norm": 1.46875,
      "learning_rate": 2.5383981243608547e-05,
      "loss": 1.0461732864379882,
      "num_input_tokens_seen": 8190449536,
      "step": 28800,
      "train_runtime": 280571.5129,
      "train_tokens_per_second": 29192.021
    },
    {
      "epoch": 1.0193539684259643,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5380710659898476e-05,
      "loss": 1.0500362396240235,
      "num_input_tokens_seen": 8193309440,
      "step": 28810,
      "train_runtime": 280669.6368,
      "train_tokens_per_second": 29192.005
    },
    {
      "epoch": 1.019707788689693,
      "grad_norm": 1.4765625,
      "learning_rate": 2.537744134005187e-05,
      "loss": 1.0477670669555663,
      "num_input_tokens_seen": 8196130880,
      "step": 28820,
      "train_runtime": 280766.7364,
      "train_tokens_per_second": 29191.958
    },
    {
      "epoch": 1.0200616089534218,
      "grad_norm": 1.5859375,
      "learning_rate": 2.537417328325493e-05,
      "loss": 1.0487887382507324,
      "num_input_tokens_seen": 8198935744,
      "step": 28830,
      "train_runtime": 280860.5953,
      "train_tokens_per_second": 29192.19
    },
    {
      "epoch": 1.0204154292171506,
      "grad_norm": 1.453125,
      "learning_rate": 2.5370906488694606e-05,
      "loss": 1.0366425514221191,
      "num_input_tokens_seen": 8201811456,
      "step": 28840,
      "train_runtime": 280959.9854,
      "train_tokens_per_second": 29192.098
    },
    {
      "epoch": 1.0207692494808793,
      "grad_norm": 1.5,
      "learning_rate": 2.536764095555857e-05,
      "loss": 1.043288803100586,
      "num_input_tokens_seen": 8204692032,
      "step": 28850,
      "train_runtime": 281059.1685,
      "train_tokens_per_second": 29192.045
    },
    {
      "epoch": 1.021123069744608,
      "grad_norm": 1.5546875,
      "learning_rate": 2.536437668303524e-05,
      "loss": 1.0415903091430665,
      "num_input_tokens_seen": 8207528256,
      "step": 28860,
      "train_runtime": 281157.7158,
      "train_tokens_per_second": 29191.901
    },
    {
      "epoch": 1.0214768900083369,
      "grad_norm": 1.46875,
      "learning_rate": 2.5361113670313745e-05,
      "loss": 1.0549073219299316,
      "num_input_tokens_seen": 8210386176,
      "step": 28870,
      "train_runtime": 281256.8691,
      "train_tokens_per_second": 29191.771
    },
    {
      "epoch": 1.0218307102720656,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5357851916583964e-05,
      "loss": 1.052191162109375,
      "num_input_tokens_seen": 8213194304,
      "step": 28880,
      "train_runtime": 281351.9924,
      "train_tokens_per_second": 29191.883
    },
    {
      "epoch": 1.0221845305357944,
      "grad_norm": 1.5703125,
      "learning_rate": 2.5354591421036485e-05,
      "loss": 1.042929458618164,
      "num_input_tokens_seen": 8216071488,
      "step": 28890,
      "train_runtime": 281450.8002,
      "train_tokens_per_second": 29191.857
    },
    {
      "epoch": 1.0225383507995232,
      "grad_norm": 1.5390625,
      "learning_rate": 2.5351332182862643e-05,
      "loss": 1.049736785888672,
      "num_input_tokens_seen": 8218899968,
      "step": 28900,
      "train_runtime": 281546.6597,
      "train_tokens_per_second": 29191.964
    },
    {
      "epoch": 1.022892171063252,
      "grad_norm": 1.5625,
      "learning_rate": 2.5348074201254484e-05,
      "loss": 1.0518577575683594,
      "num_input_tokens_seen": 8221649344,
      "step": 28910,
      "train_runtime": 281637.9698,
      "train_tokens_per_second": 29192.262
    },
    {
      "epoch": 1.0232459913269807,
      "grad_norm": 1.5390625,
      "learning_rate": 2.53448174754048e-05,
      "loss": 1.0536100387573242,
      "num_input_tokens_seen": 8224446976,
      "step": 28920,
      "train_runtime": 281731.1291,
      "train_tokens_per_second": 29192.539
    },
    {
      "epoch": 1.0235998115907097,
      "grad_norm": 1.5703125,
      "learning_rate": 2.5341562004507087e-05,
      "loss": 1.0543691635131835,
      "num_input_tokens_seen": 8227288704,
      "step": 28930,
      "train_runtime": 281826.1467,
      "train_tokens_per_second": 29192.78
    },
    {
      "epoch": 1.0239536318544384,
      "grad_norm": 1.6171875,
      "learning_rate": 2.5338307787755583e-05,
      "loss": 1.0539840698242187,
      "num_input_tokens_seen": 8230196608,
      "step": 28940,
      "train_runtime": 281927.6811,
      "train_tokens_per_second": 29192.581
    },
    {
      "epoch": 1.0243074521181672,
      "grad_norm": 1.53125,
      "learning_rate": 2.533505482434524e-05,
      "loss": 1.0509790420532226,
      "num_input_tokens_seen": 8233026688,
      "step": 28950,
      "train_runtime": 282024.9214,
      "train_tokens_per_second": 29192.55
    },
    {
      "epoch": 1.024661272381896,
      "grad_norm": 1.5546875,
      "learning_rate": 2.533180311347174e-05,
      "loss": 1.049030876159668,
      "num_input_tokens_seen": 8235850176,
      "step": 28960,
      "train_runtime": 282119.1461,
      "train_tokens_per_second": 29192.808
    },
    {
      "epoch": 1.0250150926456247,
      "grad_norm": 1.5390625,
      "learning_rate": 2.532855265433149e-05,
      "loss": 1.0446240425109863,
      "num_input_tokens_seen": 8238641280,
      "step": 28970,
      "train_runtime": 282215.9284,
      "train_tokens_per_second": 29192.687
    },
    {
      "epoch": 1.0253689129093535,
      "grad_norm": 1.515625,
      "learning_rate": 2.5325303446121602e-05,
      "loss": 1.0574220657348632,
      "num_input_tokens_seen": 8241520448,
      "step": 28980,
      "train_runtime": 282317.7652,
      "train_tokens_per_second": 29192.355
    },
    {
      "epoch": 1.0257227331730823,
      "grad_norm": 1.515625,
      "learning_rate": 2.532205548803992e-05,
      "loss": 1.0444223403930664,
      "num_input_tokens_seen": 8244379776,
      "step": 28990,
      "train_runtime": 282416.3548,
      "train_tokens_per_second": 29192.289
    },
    {
      "epoch": 1.026076553436811,
      "grad_norm": 1.4609375,
      "learning_rate": 2.531880877928502e-05,
      "loss": 1.0516919136047362,
      "num_input_tokens_seen": 8247211264,
      "step": 29000,
      "train_runtime": 282511.9789,
      "train_tokens_per_second": 29192.43
    },
    {
      "epoch": 1.0264303737005398,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5315563319056173e-05,
      "loss": 1.0510659217834473,
      "num_input_tokens_seen": 8250072320,
      "step": 29010,
      "train_runtime": 282611.1781,
      "train_tokens_per_second": 29192.307
    },
    {
      "epoch": 1.0267841939642686,
      "grad_norm": 1.4375,
      "learning_rate": 2.5312319106553384e-05,
      "loss": 1.04381103515625,
      "num_input_tokens_seen": 8252970432,
      "step": 29020,
      "train_runtime": 282709.0952,
      "train_tokens_per_second": 29192.448
    },
    {
      "epoch": 1.0271380142279973,
      "grad_norm": 1.5390625,
      "learning_rate": 2.5309076140977378e-05,
      "loss": 1.0518154144287108,
      "num_input_tokens_seen": 8255750656,
      "step": 29030,
      "train_runtime": 282802.0084,
      "train_tokens_per_second": 29192.688
    },
    {
      "epoch": 1.027491834491726,
      "grad_norm": 1.5,
      "learning_rate": 2.530583442152958e-05,
      "loss": 1.0532559394836425,
      "num_input_tokens_seen": 8258627008,
      "step": 29040,
      "train_runtime": 282902.0275,
      "train_tokens_per_second": 29192.534
    },
    {
      "epoch": 1.0278456547554549,
      "grad_norm": 1.515625,
      "learning_rate": 2.5302593947412147e-05,
      "loss": 1.0552700996398925,
      "num_input_tokens_seen": 8261513408,
      "step": 29050,
      "train_runtime": 283000.5129,
      "train_tokens_per_second": 29192.574
    },
    {
      "epoch": 1.0281994750191836,
      "grad_norm": 1.609375,
      "learning_rate": 2.529935471782794e-05,
      "loss": 1.0474486351013184,
      "num_input_tokens_seen": 8264319104,
      "step": 29060,
      "train_runtime": 283097.2607,
      "train_tokens_per_second": 29192.508
    },
    {
      "epoch": 1.0285532952829124,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5296116731980547e-05,
      "loss": 1.046504020690918,
      "num_input_tokens_seen": 8267183424,
      "step": 29070,
      "train_runtime": 283196.3407,
      "train_tokens_per_second": 29192.409
    },
    {
      "epoch": 1.0289071155466412,
      "grad_norm": 1.546875,
      "learning_rate": 2.529287998907426e-05,
      "loss": 1.0457409858703612,
      "num_input_tokens_seen": 8270033920,
      "step": 29080,
      "train_runtime": 283293.893,
      "train_tokens_per_second": 29192.419
    },
    {
      "epoch": 1.02926093581037,
      "grad_norm": 1.515625,
      "learning_rate": 2.528964448831408e-05,
      "loss": 1.04161376953125,
      "num_input_tokens_seen": 8272901376,
      "step": 29090,
      "train_runtime": 283388.9958,
      "train_tokens_per_second": 29192.74
    },
    {
      "epoch": 1.029614756074099,
      "grad_norm": 1.5625,
      "learning_rate": 2.5286410228905727e-05,
      "loss": 1.0571967124938966,
      "num_input_tokens_seen": 8275804544,
      "step": 29100,
      "train_runtime": 283490.7586,
      "train_tokens_per_second": 29192.502
    },
    {
      "epoch": 1.0299685763378277,
      "grad_norm": 1.421875,
      "learning_rate": 2.5283177210055632e-05,
      "loss": 1.057651901245117,
      "num_input_tokens_seen": 8278685440,
      "step": 29110,
      "train_runtime": 283588.2622,
      "train_tokens_per_second": 29192.624
    },
    {
      "epoch": 1.0303223966015564,
      "grad_norm": 1.53125,
      "learning_rate": 2.527994543097093e-05,
      "loss": 1.0562969207763673,
      "num_input_tokens_seen": 8281519168,
      "step": 29120,
      "train_runtime": 283682.8297,
      "train_tokens_per_second": 29192.881
    },
    {
      "epoch": 1.0306762168652852,
      "grad_norm": 1.53125,
      "learning_rate": 2.5276714890859472e-05,
      "loss": 1.033643913269043,
      "num_input_tokens_seen": 8284398976,
      "step": 29130,
      "train_runtime": 283781.6278,
      "train_tokens_per_second": 29192.866
    },
    {
      "epoch": 1.031030037129014,
      "grad_norm": 1.4609375,
      "learning_rate": 2.527348558892981e-05,
      "loss": 1.0283584594726562,
      "num_input_tokens_seen": 8287274432,
      "step": 29140,
      "train_runtime": 283881.0966,
      "train_tokens_per_second": 29192.766
    },
    {
      "epoch": 1.0313838573927427,
      "grad_norm": 1.515625,
      "learning_rate": 2.5270257524391223e-05,
      "loss": 1.0556285858154297,
      "num_input_tokens_seen": 8290079808,
      "step": 29150,
      "train_runtime": 283977.7187,
      "train_tokens_per_second": 29192.712
    },
    {
      "epoch": 1.0317376776564715,
      "grad_norm": 1.53125,
      "learning_rate": 2.526703069645366e-05,
      "loss": 1.054032325744629,
      "num_input_tokens_seen": 8292949888,
      "step": 29160,
      "train_runtime": 284077.3842,
      "train_tokens_per_second": 29192.573
    },
    {
      "epoch": 1.0320914979202003,
      "grad_norm": 1.453125,
      "learning_rate": 2.5263805104327815e-05,
      "loss": 1.0340589523315429,
      "num_input_tokens_seen": 8295789568,
      "step": 29170,
      "train_runtime": 284174.5491,
      "train_tokens_per_second": 29192.585
    },
    {
      "epoch": 1.032445318183929,
      "grad_norm": 1.4921875,
      "learning_rate": 2.526058074722506e-05,
      "loss": 1.0599351882934571,
      "num_input_tokens_seen": 8298608576,
      "step": 29180,
      "train_runtime": 284268.5552,
      "train_tokens_per_second": 29192.847
    },
    {
      "epoch": 1.0327991384476578,
      "grad_norm": 1.453125,
      "learning_rate": 2.5257357624357485e-05,
      "loss": 1.0520073890686035,
      "num_input_tokens_seen": 8301422400,
      "step": 29190,
      "train_runtime": 284364.9755,
      "train_tokens_per_second": 29192.844
    },
    {
      "epoch": 1.0331529587113866,
      "grad_norm": 1.484375,
      "learning_rate": 2.525413573493788e-05,
      "loss": 1.0312509536743164,
      "num_input_tokens_seen": 8304241792,
      "step": 29200,
      "train_runtime": 284460.9569,
      "train_tokens_per_second": 29192.905
    },
    {
      "epoch": 1.0335067789751153,
      "grad_norm": 1.4921875,
      "learning_rate": 2.525091507817974e-05,
      "loss": 1.0496007919311523,
      "num_input_tokens_seen": 8307077248,
      "step": 29210,
      "train_runtime": 284557.768,
      "train_tokens_per_second": 29192.938
    },
    {
      "epoch": 1.033860599238844,
      "grad_norm": 1.5234375,
      "learning_rate": 2.524769565329725e-05,
      "loss": 1.0554866790771484,
      "num_input_tokens_seen": 8309927040,
      "step": 29220,
      "train_runtime": 284655.4133,
      "train_tokens_per_second": 29192.935
    },
    {
      "epoch": 1.0342144195025729,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5244477459505317e-05,
      "loss": 1.055649185180664,
      "num_input_tokens_seen": 8312778944,
      "step": 29230,
      "train_runtime": 284756.1336,
      "train_tokens_per_second": 29192.625
    },
    {
      "epoch": 1.0345682397663016,
      "grad_norm": 1.5234375,
      "learning_rate": 2.524126049601953e-05,
      "loss": 1.0521562576293946,
      "num_input_tokens_seen": 8315668160,
      "step": 29240,
      "train_runtime": 284855.8212,
      "train_tokens_per_second": 29192.551
    },
    {
      "epoch": 1.0349220600300304,
      "grad_norm": 1.6015625,
      "learning_rate": 2.523804476205619e-05,
      "loss": 1.048072910308838,
      "num_input_tokens_seen": 8318459328,
      "step": 29250,
      "train_runtime": 284949.3712,
      "train_tokens_per_second": 29192.763
    },
    {
      "epoch": 1.0352758802937592,
      "grad_norm": 1.5625,
      "learning_rate": 2.5234830256832292e-05,
      "loss": 1.048440933227539,
      "num_input_tokens_seen": 8321299904,
      "step": 29260,
      "train_runtime": 285048.8669,
      "train_tokens_per_second": 29192.538
    },
    {
      "epoch": 1.0356297005574882,
      "grad_norm": 1.46875,
      "learning_rate": 2.523161697956552e-05,
      "loss": 1.0441511154174805,
      "num_input_tokens_seen": 8324117120,
      "step": 29270,
      "train_runtime": 285143.902,
      "train_tokens_per_second": 29192.689
    },
    {
      "epoch": 1.035983520821217,
      "grad_norm": 1.53125,
      "learning_rate": 2.522840492947427e-05,
      "loss": 1.0370633125305175,
      "num_input_tokens_seen": 8326990528,
      "step": 29280,
      "train_runtime": 285243.335,
      "train_tokens_per_second": 29192.586
    },
    {
      "epoch": 1.0363373410849457,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5225194105777628e-05,
      "loss": 1.0461969375610352,
      "num_input_tokens_seen": 8329845760,
      "step": 29290,
      "train_runtime": 285341.7318,
      "train_tokens_per_second": 29192.525
    },
    {
      "epoch": 1.0366911613486745,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5221984507695367e-05,
      "loss": 1.0469532012939453,
      "num_input_tokens_seen": 8332707136,
      "step": 29300,
      "train_runtime": 285437.741,
      "train_tokens_per_second": 29192.731
    },
    {
      "epoch": 1.0370449816124032,
      "grad_norm": 1.53125,
      "learning_rate": 2.5218776134447975e-05,
      "loss": 1.0551328659057617,
      "num_input_tokens_seen": 8335544064,
      "step": 29310,
      "train_runtime": 285535.4016,
      "train_tokens_per_second": 29192.682
    },
    {
      "epoch": 1.037398801876132,
      "grad_norm": 1.4609375,
      "learning_rate": 2.5215568985256617e-05,
      "loss": 1.0431121826171874,
      "num_input_tokens_seen": 8338327616,
      "step": 29320,
      "train_runtime": 285628.1199,
      "train_tokens_per_second": 29192.951
    },
    {
      "epoch": 1.0377526221398607,
      "grad_norm": 1.484375,
      "learning_rate": 2.5212363059343154e-05,
      "loss": 1.0485538482666015,
      "num_input_tokens_seen": 8341245440,
      "step": 29330,
      "train_runtime": 285729.3202,
      "train_tokens_per_second": 29192.823
    },
    {
      "epoch": 1.0381064424035895,
      "grad_norm": 1.5859375,
      "learning_rate": 2.520915835593014e-05,
      "loss": 1.0576911926269532,
      "num_input_tokens_seen": 8344038784,
      "step": 29340,
      "train_runtime": 285822.911,
      "train_tokens_per_second": 29193.037
    },
    {
      "epoch": 1.0384602626673183,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5205954874240828e-05,
      "loss": 1.0524527549743652,
      "num_input_tokens_seen": 8346882368,
      "step": 29350,
      "train_runtime": 285918.9176,
      "train_tokens_per_second": 29193.18
    },
    {
      "epoch": 1.038814082931047,
      "grad_norm": 1.4375,
      "learning_rate": 2.5202752613499154e-05,
      "loss": 1.0630861282348634,
      "num_input_tokens_seen": 8349779264,
      "step": 29360,
      "train_runtime": 286018.5129,
      "train_tokens_per_second": 29193.143
    },
    {
      "epoch": 1.0391679031947758,
      "grad_norm": 1.4609375,
      "learning_rate": 2.5199551572929743e-05,
      "loss": 1.0630492210388183,
      "num_input_tokens_seen": 8352670208,
      "step": 29370,
      "train_runtime": 286119.9668,
      "train_tokens_per_second": 29192.895
    },
    {
      "epoch": 1.0395217234585046,
      "grad_norm": 1.6015625,
      "learning_rate": 2.5196351751757913e-05,
      "loss": 1.0535256385803222,
      "num_input_tokens_seen": 8355529344,
      "step": 29380,
      "train_runtime": 286217.5474,
      "train_tokens_per_second": 29192.932
    },
    {
      "epoch": 1.0398755437222333,
      "grad_norm": 1.640625,
      "learning_rate": 2.5193153149209664e-05,
      "loss": 1.048048210144043,
      "num_input_tokens_seen": 8358456000,
      "step": 29390,
      "train_runtime": 286322.1492,
      "train_tokens_per_second": 29192.488
    },
    {
      "epoch": 1.040229363985962,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5189955764511702e-05,
      "loss": 1.034145450592041,
      "num_input_tokens_seen": 8361291264,
      "step": 29400,
      "train_runtime": 286419.7113,
      "train_tokens_per_second": 29192.444
    },
    {
      "epoch": 1.0405831842496909,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5186759596891398e-05,
      "loss": 1.0371543884277343,
      "num_input_tokens_seen": 8364111616,
      "step": 29410,
      "train_runtime": 286516.0903,
      "train_tokens_per_second": 29192.467
    },
    {
      "epoch": 1.0409370045134196,
      "grad_norm": 1.546875,
      "learning_rate": 2.518356464557682e-05,
      "loss": 1.0476859092712403,
      "num_input_tokens_seen": 8366962112,
      "step": 29420,
      "train_runtime": 286613.6514,
      "train_tokens_per_second": 29192.476
    },
    {
      "epoch": 1.0412908247771484,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5180370909796718e-05,
      "loss": 1.0342678070068358,
      "num_input_tokens_seen": 8369782848,
      "step": 29430,
      "train_runtime": 286707.073,
      "train_tokens_per_second": 29192.802
    },
    {
      "epoch": 1.0416446450408774,
      "grad_norm": 1.5,
      "learning_rate": 2.5177178388780527e-05,
      "loss": 1.0435821533203125,
      "num_input_tokens_seen": 8372579840,
      "step": 29440,
      "train_runtime": 286799.8777,
      "train_tokens_per_second": 29193.108
    },
    {
      "epoch": 1.0419984653046062,
      "grad_norm": 1.515625,
      "learning_rate": 2.5173987081758372e-05,
      "loss": 1.055179977416992,
      "num_input_tokens_seen": 8375406144,
      "step": 29450,
      "train_runtime": 286895.2872,
      "train_tokens_per_second": 29193.251
    },
    {
      "epoch": 1.042352285568335,
      "grad_norm": 1.5390625,
      "learning_rate": 2.5170796987961044e-05,
      "loss": 1.054011344909668,
      "num_input_tokens_seen": 8378244928,
      "step": 29460,
      "train_runtime": 286990.2973,
      "train_tokens_per_second": 29193.478
    },
    {
      "epoch": 1.0427061058320637,
      "grad_norm": 1.5625,
      "learning_rate": 2.516760810662004e-05,
      "loss": 1.041065788269043,
      "num_input_tokens_seen": 8381078592,
      "step": 29470,
      "train_runtime": 287087.1308,
      "train_tokens_per_second": 29193.502
    },
    {
      "epoch": 1.0430599260957925,
      "grad_norm": 1.4765625,
      "learning_rate": 2.5164420436967517e-05,
      "loss": 1.044297218322754,
      "num_input_tokens_seen": 8383939776,
      "step": 29480,
      "train_runtime": 287185.443,
      "train_tokens_per_second": 29193.471
    },
    {
      "epoch": 1.0434137463595212,
      "grad_norm": 1.4765625,
      "learning_rate": 2.516123397823632e-05,
      "loss": 1.046547031402588,
      "num_input_tokens_seen": 8386789760,
      "step": 29490,
      "train_runtime": 287283.4915,
      "train_tokens_per_second": 29193.427
    },
    {
      "epoch": 1.04376756662325,
      "grad_norm": 1.5,
      "learning_rate": 2.5158048729659988e-05,
      "loss": 1.0549219131469727,
      "num_input_tokens_seen": 8389647168,
      "step": 29500,
      "train_runtime": 287381.562,
      "train_tokens_per_second": 29193.408
    },
    {
      "epoch": 1.0441213868869788,
      "grad_norm": 1.5234375,
      "learning_rate": 2.5154864690472714e-05,
      "loss": 1.0541885375976563,
      "num_input_tokens_seen": 8392480128,
      "step": 29510,
      "train_runtime": 287478.7503,
      "train_tokens_per_second": 29193.393
    },
    {
      "epoch": 1.0444752071507075,
      "grad_norm": 1.53125,
      "learning_rate": 2.5151681859909383e-05,
      "loss": 1.0468287467956543,
      "num_input_tokens_seen": 8395303808,
      "step": 29520,
      "train_runtime": 287575.499,
      "train_tokens_per_second": 29193.39
    },
    {
      "epoch": 1.0448290274144363,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5148500237205564e-05,
      "loss": 1.047328567504883,
      "num_input_tokens_seen": 8398207104,
      "step": 29530,
      "train_runtime": 287677.9103,
      "train_tokens_per_second": 29193.09
    },
    {
      "epoch": 1.045182847678165,
      "grad_norm": 1.5,
      "learning_rate": 2.514531982159748e-05,
      "loss": 1.0507135391235352,
      "num_input_tokens_seen": 8401092352,
      "step": 29540,
      "train_runtime": 287777.3632,
      "train_tokens_per_second": 29193.027
    },
    {
      "epoch": 1.0455366679418938,
      "grad_norm": 1.546875,
      "learning_rate": 2.5142140612322056e-05,
      "loss": 1.042203712463379,
      "num_input_tokens_seen": 8403973376,
      "step": 29550,
      "train_runtime": 287876.823,
      "train_tokens_per_second": 29192.949
    },
    {
      "epoch": 1.0458904882056226,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5138962608616883e-05,
      "loss": 1.0546101570129394,
      "num_input_tokens_seen": 8406783168,
      "step": 29560,
      "train_runtime": 287970.1057,
      "train_tokens_per_second": 29193.25
    },
    {
      "epoch": 1.0462443084693513,
      "grad_norm": 1.5390625,
      "learning_rate": 2.513578580972022e-05,
      "loss": 1.0395442962646484,
      "num_input_tokens_seen": 8409632128,
      "step": 29570,
      "train_runtime": 288066.8315,
      "train_tokens_per_second": 29193.337
    },
    {
      "epoch": 1.0465981287330801,
      "grad_norm": 1.5390625,
      "learning_rate": 2.5132610214871e-05,
      "loss": 1.0510801315307616,
      "num_input_tokens_seen": 8412488576,
      "step": 29580,
      "train_runtime": 288164.4564,
      "train_tokens_per_second": 29193.36
    },
    {
      "epoch": 1.0469519489968089,
      "grad_norm": 1.53125,
      "learning_rate": 2.5129435823308835e-05,
      "loss": 1.0485179901123047,
      "num_input_tokens_seen": 8415376256,
      "step": 29590,
      "train_runtime": 288262.9087,
      "train_tokens_per_second": 29193.406
    },
    {
      "epoch": 1.0473057692605379,
      "grad_norm": 1.46875,
      "learning_rate": 2.5126262634274012e-05,
      "loss": 1.0595196723937987,
      "num_input_tokens_seen": 8418174016,
      "step": 29600,
      "train_runtime": 288359.3351,
      "train_tokens_per_second": 29193.347
    },
    {
      "epoch": 1.0476595895242666,
      "grad_norm": 1.5703125,
      "learning_rate": 2.512309064700748e-05,
      "loss": 1.042276954650879,
      "num_input_tokens_seen": 8420998912,
      "step": 29610,
      "train_runtime": 288456.3795,
      "train_tokens_per_second": 29193.318
    },
    {
      "epoch": 1.0480134097879954,
      "grad_norm": 1.4609375,
      "learning_rate": 2.511991986075086e-05,
      "loss": 1.0346954345703125,
      "num_input_tokens_seen": 8423861184,
      "step": 29620,
      "train_runtime": 288553.7079,
      "train_tokens_per_second": 29193.391
    },
    {
      "epoch": 1.0483672300517242,
      "grad_norm": 1.546875,
      "learning_rate": 2.511675027474645e-05,
      "loss": 1.0535845756530762,
      "num_input_tokens_seen": 8426761344,
      "step": 29630,
      "train_runtime": 288652.5121,
      "train_tokens_per_second": 29193.445
    },
    {
      "epoch": 1.048721050315453,
      "grad_norm": 1.578125,
      "learning_rate": 2.5113581888237215e-05,
      "loss": 1.0491786003112793,
      "num_input_tokens_seen": 8429587008,
      "step": 29640,
      "train_runtime": 288748.2343,
      "train_tokens_per_second": 29193.553
    },
    {
      "epoch": 1.0490748705791817,
      "grad_norm": 1.5703125,
      "learning_rate": 2.5110414700466782e-05,
      "loss": 1.0429922103881837,
      "num_input_tokens_seen": 8432394048,
      "step": 29650,
      "train_runtime": 288844.8743,
      "train_tokens_per_second": 29193.504
    },
    {
      "epoch": 1.0494286908429105,
      "grad_norm": 1.515625,
      "learning_rate": 2.5107248710679447e-05,
      "loss": 1.041240119934082,
      "num_input_tokens_seen": 8435300096,
      "step": 29660,
      "train_runtime": 288944.605,
      "train_tokens_per_second": 29193.485
    },
    {
      "epoch": 1.0497825111066392,
      "grad_norm": 1.5703125,
      "learning_rate": 2.5104083918120187e-05,
      "loss": 1.0659772872924804,
      "num_input_tokens_seen": 8438190336,
      "step": 29670,
      "train_runtime": 289045.2337,
      "train_tokens_per_second": 29193.321
    },
    {
      "epoch": 1.050136331370368,
      "grad_norm": 1.484375,
      "learning_rate": 2.5100920322034615e-05,
      "loss": 1.0506914138793946,
      "num_input_tokens_seen": 8441038080,
      "step": 29680,
      "train_runtime": 289144.1649,
      "train_tokens_per_second": 29193.181
    },
    {
      "epoch": 1.0504901516340968,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5097757921669047e-05,
      "loss": 1.0402145385742188,
      "num_input_tokens_seen": 8443878784,
      "step": 29690,
      "train_runtime": 289242.1086,
      "train_tokens_per_second": 29193.117
    },
    {
      "epoch": 1.0508439718978255,
      "grad_norm": 1.5546875,
      "learning_rate": 2.509459671627043e-05,
      "loss": 1.0512310028076173,
      "num_input_tokens_seen": 8446693824,
      "step": 29700,
      "train_runtime": 289336.745,
      "train_tokens_per_second": 29193.298
    },
    {
      "epoch": 1.0511977921615543,
      "grad_norm": 1.4296875,
      "learning_rate": 2.50914367050864e-05,
      "loss": 1.048554039001465,
      "num_input_tokens_seen": 8449562112,
      "step": 29710,
      "train_runtime": 289434.8572,
      "train_tokens_per_second": 29193.312
    },
    {
      "epoch": 1.051551612425283,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5088277887365236e-05,
      "loss": 1.0454522132873536,
      "num_input_tokens_seen": 8452375104,
      "step": 29720,
      "train_runtime": 289529.9637,
      "train_tokens_per_second": 29193.438
    },
    {
      "epoch": 1.0519054326890118,
      "grad_norm": 1.515625,
      "learning_rate": 2.5085120262355895e-05,
      "loss": 1.0414667129516602,
      "num_input_tokens_seen": 8455174848,
      "step": 29730,
      "train_runtime": 289623.5498,
      "train_tokens_per_second": 29193.672
    },
    {
      "epoch": 1.0522592529527406,
      "grad_norm": 1.453125,
      "learning_rate": 2.5081963829307987e-05,
      "loss": 1.0501920700073242,
      "num_input_tokens_seen": 8458032256,
      "step": 29740,
      "train_runtime": 289723.9768,
      "train_tokens_per_second": 29193.415
    },
    {
      "epoch": 1.0526130732164694,
      "grad_norm": 1.546875,
      "learning_rate": 2.507880858747178e-05,
      "loss": 1.0454265594482421,
      "num_input_tokens_seen": 8460895680,
      "step": 29750,
      "train_runtime": 289820.1731,
      "train_tokens_per_second": 29193.605
    },
    {
      "epoch": 1.0529668934801983,
      "grad_norm": 1.6015625,
      "learning_rate": 2.5075654536098213e-05,
      "loss": 1.0526483535766602,
      "num_input_tokens_seen": 8463737536,
      "step": 29760,
      "train_runtime": 289916.4064,
      "train_tokens_per_second": 29193.717
    },
    {
      "epoch": 1.053320713743927,
      "grad_norm": 1.5703125,
      "learning_rate": 2.5072501674438875e-05,
      "loss": 1.0564079284667969,
      "num_input_tokens_seen": 8466601408,
      "step": 29770,
      "train_runtime": 290016.9172,
      "train_tokens_per_second": 29193.474
    },
    {
      "epoch": 1.0536745340076559,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5069350001746017e-05,
      "loss": 1.054703140258789,
      "num_input_tokens_seen": 8469489536,
      "step": 29780,
      "train_runtime": 290119.8698,
      "train_tokens_per_second": 29193.07
    },
    {
      "epoch": 1.0540283542713846,
      "grad_norm": 1.5625,
      "learning_rate": 2.506619951727255e-05,
      "loss": 1.0509763717651368,
      "num_input_tokens_seen": 8472355136,
      "step": 29790,
      "train_runtime": 290220.2752,
      "train_tokens_per_second": 29192.844
    },
    {
      "epoch": 1.0543821745351134,
      "grad_norm": 1.515625,
      "learning_rate": 2.5063050220272033e-05,
      "loss": 1.0431835174560546,
      "num_input_tokens_seen": 8475185664,
      "step": 29800,
      "train_runtime": 290315.7879,
      "train_tokens_per_second": 29192.989
    },
    {
      "epoch": 1.0547359947988422,
      "grad_norm": 1.5390625,
      "learning_rate": 2.5059902109998696e-05,
      "loss": 1.039987564086914,
      "num_input_tokens_seen": 8478013504,
      "step": 29810,
      "train_runtime": 290410.6227,
      "train_tokens_per_second": 29193.194
    },
    {
      "epoch": 1.055089815062571,
      "grad_norm": 1.484375,
      "learning_rate": 2.505675518570741e-05,
      "loss": 1.03611421585083,
      "num_input_tokens_seen": 8480837376,
      "step": 29820,
      "train_runtime": 290507.0359,
      "train_tokens_per_second": 29193.225
    },
    {
      "epoch": 1.0554436353262997,
      "grad_norm": 1.5703125,
      "learning_rate": 2.505360944665371e-05,
      "loss": 1.0449862480163574,
      "num_input_tokens_seen": 8483714496,
      "step": 29830,
      "train_runtime": 290607.6559,
      "train_tokens_per_second": 29193.018
    },
    {
      "epoch": 1.0557974555900285,
      "grad_norm": 1.53125,
      "learning_rate": 2.5050464892093777e-05,
      "loss": 1.0410438537597657,
      "num_input_tokens_seen": 8486601152,
      "step": 29840,
      "train_runtime": 290707.6858,
      "train_tokens_per_second": 29192.903
    },
    {
      "epoch": 1.0561512758537572,
      "grad_norm": 1.625,
      "learning_rate": 2.5047321521284463e-05,
      "loss": 1.053577995300293,
      "num_input_tokens_seen": 8489445376,
      "step": 29850,
      "train_runtime": 290806.0966,
      "train_tokens_per_second": 29192.804
    },
    {
      "epoch": 1.056505096117486,
      "grad_norm": 1.5703125,
      "learning_rate": 2.5044179333483243e-05,
      "loss": 1.0501842498779297,
      "num_input_tokens_seen": 8492256192,
      "step": 29860,
      "train_runtime": 290901.0884,
      "train_tokens_per_second": 29192.934
    },
    {
      "epoch": 1.0568589163812148,
      "grad_norm": 1.4921875,
      "learning_rate": 2.5041038327948274e-05,
      "loss": 1.038751220703125,
      "num_input_tokens_seen": 8495081984,
      "step": 29870,
      "train_runtime": 290997.3531,
      "train_tokens_per_second": 29192.987
    },
    {
      "epoch": 1.0572127366449435,
      "grad_norm": 1.53125,
      "learning_rate": 2.5037898503938346e-05,
      "loss": 1.0530385017395019,
      "num_input_tokens_seen": 8497885824,
      "step": 29880,
      "train_runtime": 291092.1869,
      "train_tokens_per_second": 29193.109
    },
    {
      "epoch": 1.0575665569086723,
      "grad_norm": 1.5390625,
      "learning_rate": 2.5034759860712903e-05,
      "loss": 1.0458839416503907,
      "num_input_tokens_seen": 8500759808,
      "step": 29890,
      "train_runtime": 291190.678,
      "train_tokens_per_second": 29193.104
    },
    {
      "epoch": 1.057920377172401,
      "grad_norm": 1.5078125,
      "learning_rate": 2.5031622397532047e-05,
      "loss": 1.0505592346191406,
      "num_input_tokens_seen": 8503626176,
      "step": 29900,
      "train_runtime": 291286.2858,
      "train_tokens_per_second": 29193.363
    },
    {
      "epoch": 1.0582741974361298,
      "grad_norm": 1.5,
      "learning_rate": 2.502848611365651e-05,
      "loss": 1.0517515182495116,
      "num_input_tokens_seen": 8506471488,
      "step": 29910,
      "train_runtime": 291386.256,
      "train_tokens_per_second": 29193.112
    },
    {
      "epoch": 1.0586280176998586,
      "grad_norm": 1.4765625,
      "learning_rate": 2.50253510083477e-05,
      "loss": 1.0337539672851563,
      "num_input_tokens_seen": 8509321664,
      "step": 29920,
      "train_runtime": 291481.034,
      "train_tokens_per_second": 29193.397
    },
    {
      "epoch": 1.0589818379635876,
      "grad_norm": 1.53125,
      "learning_rate": 2.502221708086765e-05,
      "loss": 1.0613242149353028,
      "num_input_tokens_seen": 8512201600,
      "step": 29930,
      "train_runtime": 291579.3382,
      "train_tokens_per_second": 29193.432
    },
    {
      "epoch": 1.0593356582273163,
      "grad_norm": 1.5859375,
      "learning_rate": 2.501908433047904e-05,
      "loss": 1.0454280853271485,
      "num_input_tokens_seen": 8515051712,
      "step": 29940,
      "train_runtime": 291677.0492,
      "train_tokens_per_second": 29193.424
    },
    {
      "epoch": 1.0596894784910451,
      "grad_norm": 1.5234375,
      "learning_rate": 2.501595275644521e-05,
      "loss": 1.0531499862670899,
      "num_input_tokens_seen": 8517857344,
      "step": 29950,
      "train_runtime": 291771.1597,
      "train_tokens_per_second": 29193.623
    },
    {
      "epoch": 1.0600432987547739,
      "grad_norm": 1.484375,
      "learning_rate": 2.5012822358030136e-05,
      "loss": 1.0593780517578124,
      "num_input_tokens_seen": 8520674944,
      "step": 29960,
      "train_runtime": 291865.3755,
      "train_tokens_per_second": 29193.853
    },
    {
      "epoch": 1.0603971190185026,
      "grad_norm": 1.5078125,
      "learning_rate": 2.500969313449844e-05,
      "loss": 1.0549972534179688,
      "num_input_tokens_seen": 8523534848,
      "step": 29970,
      "train_runtime": 291964.1425,
      "train_tokens_per_second": 29193.773
    },
    {
      "epoch": 1.0607509392822314,
      "grad_norm": 1.546875,
      "learning_rate": 2.500656508511539e-05,
      "loss": 1.040264892578125,
      "num_input_tokens_seen": 8526372224,
      "step": 29980,
      "train_runtime": 292060.5278,
      "train_tokens_per_second": 29193.853
    },
    {
      "epoch": 1.0611047595459602,
      "grad_norm": 1.5546875,
      "learning_rate": 2.500343820914689e-05,
      "loss": 1.0484054565429688,
      "num_input_tokens_seen": 8529185856,
      "step": 29990,
      "train_runtime": 292157.4674,
      "train_tokens_per_second": 29193.797
    },
    {
      "epoch": 1.061458579809689,
      "grad_norm": 1.5625,
      "learning_rate": 2.5000312505859502e-05,
      "loss": 1.046640968322754,
      "num_input_tokens_seen": 8532056576,
      "step": 30000,
      "train_runtime": 292257.5228,
      "train_tokens_per_second": 29193.625
    },
    {
      "epoch": 1.061458579809689,
      "eval_loss": 1.0210896730422974,
      "eval_runtime": 8.447,
      "eval_samples_per_second": 472.12,
      "eval_steps_per_second": 3.788,
      "num_input_tokens_seen": 8532056576,
      "step": 30000
    },
    {
      "epoch": 1.0618124000734177,
      "grad_norm": 1.5625,
      "learning_rate": 2.4997187974520408e-05,
      "loss": 1.0460805892944336,
      "num_input_tokens_seen": 8534891904,
      "step": 30010,
      "train_runtime": 292386.7088,
      "train_tokens_per_second": 29190.424
    },
    {
      "epoch": 1.0621662203371465,
      "grad_norm": 1.4765625,
      "learning_rate": 2.4994064614397442e-05,
      "loss": 1.0540008544921875,
      "num_input_tokens_seen": 8537737984,
      "step": 30020,
      "train_runtime": 292484.2251,
      "train_tokens_per_second": 29190.422
    },
    {
      "epoch": 1.0625200406008752,
      "grad_norm": 1.59375,
      "learning_rate": 2.499094242475909e-05,
      "loss": 1.0457609176635743,
      "num_input_tokens_seen": 8540617600,
      "step": 30030,
      "train_runtime": 292585.6751,
      "train_tokens_per_second": 29190.143
    },
    {
      "epoch": 1.062873860864604,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4987821404874463e-05,
      "loss": 1.05477933883667,
      "num_input_tokens_seen": 8543440512,
      "step": 30040,
      "train_runtime": 292683.0358,
      "train_tokens_per_second": 29190.078
    },
    {
      "epoch": 1.0632276811283328,
      "grad_norm": 1.53125,
      "learning_rate": 2.49847015540133e-05,
      "loss": 1.0480039596557618,
      "num_input_tokens_seen": 8546294080,
      "step": 30050,
      "train_runtime": 292780.3147,
      "train_tokens_per_second": 29190.125
    },
    {
      "epoch": 1.0635815013920615,
      "grad_norm": 1.5390625,
      "learning_rate": 2.498158287144601e-05,
      "loss": 1.0439905166625976,
      "num_input_tokens_seen": 8549108480,
      "step": 30060,
      "train_runtime": 292875.7644,
      "train_tokens_per_second": 29190.222
    },
    {
      "epoch": 1.0639353216557903,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4978465356443613e-05,
      "loss": 1.0514918327331544,
      "num_input_tokens_seen": 8551931200,
      "step": 30070,
      "train_runtime": 292972.628,
      "train_tokens_per_second": 29190.205
    },
    {
      "epoch": 1.064289141919519,
      "grad_norm": 1.4765625,
      "learning_rate": 2.4975349008277774e-05,
      "loss": 1.037200927734375,
      "num_input_tokens_seen": 8554742592,
      "step": 30080,
      "train_runtime": 293069.8207,
      "train_tokens_per_second": 29190.118
    },
    {
      "epoch": 1.0646429621832478,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4972233826220794e-05,
      "loss": 1.0489699363708496,
      "num_input_tokens_seen": 8557563520,
      "step": 30090,
      "train_runtime": 293167.6382,
      "train_tokens_per_second": 29190.001
    },
    {
      "epoch": 1.0649967824469768,
      "grad_norm": 1.5390625,
      "learning_rate": 2.496911980954561e-05,
      "loss": 1.038052749633789,
      "num_input_tokens_seen": 8560374208,
      "step": 30100,
      "train_runtime": 293263.1792,
      "train_tokens_per_second": 29190.075
    },
    {
      "epoch": 1.0653506027107056,
      "grad_norm": 1.53125,
      "learning_rate": 2.496600695752579e-05,
      "loss": 1.0519622802734374,
      "num_input_tokens_seen": 8563199168,
      "step": 30110,
      "train_runtime": 293359.5516,
      "train_tokens_per_second": 29190.115
    },
    {
      "epoch": 1.0657044229744344,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4962895269435543e-05,
      "loss": 1.0428800582885742,
      "num_input_tokens_seen": 8566012160,
      "step": 30120,
      "train_runtime": 293456.0629,
      "train_tokens_per_second": 29190.101
    },
    {
      "epoch": 1.0660582432381631,
      "grad_norm": 1.5234375,
      "learning_rate": 2.49597847445497e-05,
      "loss": 1.0345462799072265,
      "num_input_tokens_seen": 8568842368,
      "step": 30130,
      "train_runtime": 293553.8092,
      "train_tokens_per_second": 29190.023
    },
    {
      "epoch": 1.0664120635018919,
      "grad_norm": 1.46875,
      "learning_rate": 2.495667538214374e-05,
      "loss": 1.047976303100586,
      "num_input_tokens_seen": 8571620096,
      "step": 30140,
      "train_runtime": 293646.1542,
      "train_tokens_per_second": 29190.303
    },
    {
      "epoch": 1.0667658837656206,
      "grad_norm": 1.5859375,
      "learning_rate": 2.4953567181493754e-05,
      "loss": 1.05532808303833,
      "num_input_tokens_seen": 8574470656,
      "step": 30150,
      "train_runtime": 293745.2682,
      "train_tokens_per_second": 29190.158
    },
    {
      "epoch": 1.0671197040293494,
      "grad_norm": 1.53125,
      "learning_rate": 2.495046014187648e-05,
      "loss": 1.0400854110717774,
      "num_input_tokens_seen": 8577330752,
      "step": 30160,
      "train_runtime": 293846.441,
      "train_tokens_per_second": 29189.841
    },
    {
      "epoch": 1.0674735242930782,
      "grad_norm": 1.5078125,
      "learning_rate": 2.494735426256928e-05,
      "loss": 1.0402067184448243,
      "num_input_tokens_seen": 8580153856,
      "step": 30170,
      "train_runtime": 293941.7454,
      "train_tokens_per_second": 29189.981
    },
    {
      "epoch": 1.067827344556807,
      "grad_norm": 1.4765625,
      "learning_rate": 2.4944249542850143e-05,
      "loss": 1.0450834274291991,
      "num_input_tokens_seen": 8582978368,
      "step": 30180,
      "train_runtime": 294038.6103,
      "train_tokens_per_second": 29189.971
    },
    {
      "epoch": 1.0681811648205357,
      "grad_norm": 1.5078125,
      "learning_rate": 2.494114598199769e-05,
      "loss": 1.0636441230773925,
      "num_input_tokens_seen": 8585800064,
      "step": 30190,
      "train_runtime": 294131.6847,
      "train_tokens_per_second": 29190.327
    },
    {
      "epoch": 1.0685349850842645,
      "grad_norm": 1.46875,
      "learning_rate": 2.493804357929118e-05,
      "loss": 1.0470794677734374,
      "num_input_tokens_seen": 8588638464,
      "step": 30200,
      "train_runtime": 294228.8358,
      "train_tokens_per_second": 29190.336
    },
    {
      "epoch": 1.0688888053479932,
      "grad_norm": 1.515625,
      "learning_rate": 2.4934942334010474e-05,
      "loss": 1.0458884239196777,
      "num_input_tokens_seen": 8591515776,
      "step": 30210,
      "train_runtime": 294326.0642,
      "train_tokens_per_second": 29190.469
    },
    {
      "epoch": 1.069242625611722,
      "grad_norm": 1.4921875,
      "learning_rate": 2.493184224543609e-05,
      "loss": 1.0448594093322754,
      "num_input_tokens_seen": 8594383872,
      "step": 30220,
      "train_runtime": 294426.1964,
      "train_tokens_per_second": 29190.283
    },
    {
      "epoch": 1.0695964458754508,
      "grad_norm": 1.609375,
      "learning_rate": 2.4928743312849144e-05,
      "loss": 1.038890266418457,
      "num_input_tokens_seen": 8597279040,
      "step": 30230,
      "train_runtime": 294525.4017,
      "train_tokens_per_second": 29190.28
    },
    {
      "epoch": 1.0699502661391795,
      "grad_norm": 1.5,
      "learning_rate": 2.4925645535531404e-05,
      "loss": 1.0495343208312988,
      "num_input_tokens_seen": 8600124544,
      "step": 30240,
      "train_runtime": 294623.5399,
      "train_tokens_per_second": 29190.215
    },
    {
      "epoch": 1.0703040864029083,
      "grad_norm": 1.515625,
      "learning_rate": 2.4922548912765234e-05,
      "loss": 1.0418855667114257,
      "num_input_tokens_seen": 8603017472,
      "step": 30250,
      "train_runtime": 294722.653,
      "train_tokens_per_second": 29190.215
    },
    {
      "epoch": 1.070657906666637,
      "grad_norm": 1.484375,
      "learning_rate": 2.4919453443833642e-05,
      "loss": 1.0531468391418457,
      "num_input_tokens_seen": 8605882240,
      "step": 30260,
      "train_runtime": 294819.7566,
      "train_tokens_per_second": 29190.317
    },
    {
      "epoch": 1.071011726930366,
      "grad_norm": 1.53125,
      "learning_rate": 2.4916359128020264e-05,
      "loss": 1.0358877182006836,
      "num_input_tokens_seen": 8608732864,
      "step": 30270,
      "train_runtime": 294920.114,
      "train_tokens_per_second": 29190.05
    },
    {
      "epoch": 1.0713655471940948,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4913265964609342e-05,
      "loss": 1.0475775718688964,
      "num_input_tokens_seen": 8611570944,
      "step": 30280,
      "train_runtime": 295016.8556,
      "train_tokens_per_second": 29190.098
    },
    {
      "epoch": 1.0717193674578236,
      "grad_norm": 1.546875,
      "learning_rate": 2.4910173952885737e-05,
      "loss": 1.0310024261474608,
      "num_input_tokens_seen": 8614446272,
      "step": 30290,
      "train_runtime": 295114.1289,
      "train_tokens_per_second": 29190.22
    },
    {
      "epoch": 1.0720731877215524,
      "grad_norm": 1.5390625,
      "learning_rate": 2.490708309213496e-05,
      "loss": 1.0560443878173829,
      "num_input_tokens_seen": 8617270976,
      "step": 30300,
      "train_runtime": 295210.7714,
      "train_tokens_per_second": 29190.232
    },
    {
      "epoch": 1.0724270079852811,
      "grad_norm": 1.53125,
      "learning_rate": 2.4903993381643107e-05,
      "loss": 1.038797378540039,
      "num_input_tokens_seen": 8620095744,
      "step": 30310,
      "train_runtime": 295306.9363,
      "train_tokens_per_second": 29190.292
    },
    {
      "epoch": 1.0727808282490099,
      "grad_norm": 1.484375,
      "learning_rate": 2.4900904820696916e-05,
      "loss": 1.0457059860229492,
      "num_input_tokens_seen": 8622953920,
      "step": 30320,
      "train_runtime": 295406.7993,
      "train_tokens_per_second": 29190.1
    },
    {
      "epoch": 1.0731346485127387,
      "grad_norm": 1.515625,
      "learning_rate": 2.489781740858374e-05,
      "loss": 1.0438735961914063,
      "num_input_tokens_seen": 8625767808,
      "step": 30330,
      "train_runtime": 295503.9469,
      "train_tokens_per_second": 29190.026
    },
    {
      "epoch": 1.0734884687764674,
      "grad_norm": 1.546875,
      "learning_rate": 2.4894731144591545e-05,
      "loss": 1.0542779922485352,
      "num_input_tokens_seen": 8628583552,
      "step": 30340,
      "train_runtime": 295599.7813,
      "train_tokens_per_second": 29190.088
    },
    {
      "epoch": 1.0738422890401962,
      "grad_norm": 1.4921875,
      "learning_rate": 2.4891646028008923e-05,
      "loss": 1.0325572967529297,
      "num_input_tokens_seen": 8631424640,
      "step": 30350,
      "train_runtime": 295698.3045,
      "train_tokens_per_second": 29189.97
    },
    {
      "epoch": 1.074196109303925,
      "grad_norm": 1.5,
      "learning_rate": 2.4888562058125068e-05,
      "loss": 1.0446797370910645,
      "num_input_tokens_seen": 8634254720,
      "step": 30360,
      "train_runtime": 295794.5655,
      "train_tokens_per_second": 29190.038
    },
    {
      "epoch": 1.0745499295676537,
      "grad_norm": 1.484375,
      "learning_rate": 2.488547923422981e-05,
      "loss": 1.0506183624267578,
      "num_input_tokens_seen": 8637137792,
      "step": 30370,
      "train_runtime": 295894.3293,
      "train_tokens_per_second": 29189.94
    },
    {
      "epoch": 1.0749037498313825,
      "grad_norm": 1.5625,
      "learning_rate": 2.4882397555613582e-05,
      "loss": 1.0563552856445313,
      "num_input_tokens_seen": 8639975552,
      "step": 30380,
      "train_runtime": 295990.1277,
      "train_tokens_per_second": 29190.08
    },
    {
      "epoch": 1.0752575700951112,
      "grad_norm": 1.4765625,
      "learning_rate": 2.487931702156743e-05,
      "loss": 1.04453763961792,
      "num_input_tokens_seen": 8642767680,
      "step": 30390,
      "train_runtime": 296085.1998,
      "train_tokens_per_second": 29190.137
    },
    {
      "epoch": 1.07561139035884,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4876237631383026e-05,
      "loss": 1.047821617126465,
      "num_input_tokens_seen": 8645595200,
      "step": 30400,
      "train_runtime": 296180.1265,
      "train_tokens_per_second": 29190.329
    },
    {
      "epoch": 1.0759652106225688,
      "grad_norm": 1.5,
      "learning_rate": 2.4873159384352647e-05,
      "loss": 1.051121139526367,
      "num_input_tokens_seen": 8648428928,
      "step": 30410,
      "train_runtime": 296275.8518,
      "train_tokens_per_second": 29190.462
    },
    {
      "epoch": 1.0763190308862975,
      "grad_norm": 1.5078125,
      "learning_rate": 2.487008227976918e-05,
      "loss": 1.0485450744628906,
      "num_input_tokens_seen": 8651207872,
      "step": 30420,
      "train_runtime": 296368.2732,
      "train_tokens_per_second": 29190.735
    },
    {
      "epoch": 1.0766728511500263,
      "grad_norm": 1.5625,
      "learning_rate": 2.486700631692613e-05,
      "loss": 1.0437174797058106,
      "num_input_tokens_seen": 8654055616,
      "step": 30430,
      "train_runtime": 296465.1544,
      "train_tokens_per_second": 29190.802
    },
    {
      "epoch": 1.0770266714137553,
      "grad_norm": 1.5546875,
      "learning_rate": 2.486393149511762e-05,
      "loss": 1.056033992767334,
      "num_input_tokens_seen": 8656875840,
      "step": 30440,
      "train_runtime": 296561.5934,
      "train_tokens_per_second": 29190.819
    },
    {
      "epoch": 1.077380491677484,
      "grad_norm": 1.5625,
      "learning_rate": 2.4860857813638365e-05,
      "loss": 1.0636586189270019,
      "num_input_tokens_seen": 8659703808,
      "step": 30450,
      "train_runtime": 296658.6774,
      "train_tokens_per_second": 29190.799
    },
    {
      "epoch": 1.0777343119412128,
      "grad_norm": 1.5078125,
      "learning_rate": 2.485778527178371e-05,
      "loss": 1.042108154296875,
      "num_input_tokens_seen": 8662570112,
      "step": 30460,
      "train_runtime": 296756.5371,
      "train_tokens_per_second": 29190.832
    },
    {
      "epoch": 1.0780881322049416,
      "grad_norm": 1.484375,
      "learning_rate": 2.48547138688496e-05,
      "loss": 1.0412103652954101,
      "num_input_tokens_seen": 8665451456,
      "step": 30470,
      "train_runtime": 296858.6448,
      "train_tokens_per_second": 29190.497
    },
    {
      "epoch": 1.0784419524686704,
      "grad_norm": 1.5703125,
      "learning_rate": 2.485164360413258e-05,
      "loss": 1.0650873184204102,
      "num_input_tokens_seen": 8668232768,
      "step": 30480,
      "train_runtime": 296954.7419,
      "train_tokens_per_second": 29190.417
    },
    {
      "epoch": 1.0787957727323991,
      "grad_norm": 1.5390625,
      "learning_rate": 2.4848574476929823e-05,
      "loss": 1.0396809577941895,
      "num_input_tokens_seen": 8671091072,
      "step": 30490,
      "train_runtime": 297055.7673,
      "train_tokens_per_second": 29190.112
    },
    {
      "epoch": 1.079149592996128,
      "grad_norm": 1.5625,
      "learning_rate": 2.484550648653909e-05,
      "loss": 1.0381423950195312,
      "num_input_tokens_seen": 8673882240,
      "step": 30500,
      "train_runtime": 297148.834,
      "train_tokens_per_second": 29190.363
    },
    {
      "epoch": 1.0795034132598567,
      "grad_norm": 1.4609375,
      "learning_rate": 2.484243963225877e-05,
      "loss": 1.047877597808838,
      "num_input_tokens_seen": 8676791552,
      "step": 30510,
      "train_runtime": 297248.4347,
      "train_tokens_per_second": 29190.369
    },
    {
      "epoch": 1.0798572335235854,
      "grad_norm": 1.46875,
      "learning_rate": 2.4839373913387835e-05,
      "loss": 1.0318588256835937,
      "num_input_tokens_seen": 8679678208,
      "step": 30520,
      "train_runtime": 297345.8992,
      "train_tokens_per_second": 29190.509
    },
    {
      "epoch": 1.0802110537873142,
      "grad_norm": 1.4609375,
      "learning_rate": 2.4836309329225873e-05,
      "loss": 1.0531158447265625,
      "num_input_tokens_seen": 8682504064,
      "step": 30530,
      "train_runtime": 297444.989,
      "train_tokens_per_second": 29190.285
    },
    {
      "epoch": 1.080564874051043,
      "grad_norm": 1.484375,
      "learning_rate": 2.483324587907309e-05,
      "loss": 1.0509878158569337,
      "num_input_tokens_seen": 8685337408,
      "step": 30540,
      "train_runtime": 297543.294,
      "train_tokens_per_second": 29190.164
    },
    {
      "epoch": 1.0809186943147717,
      "grad_norm": 1.59375,
      "learning_rate": 2.483018356223027e-05,
      "loss": 1.0492218017578125,
      "num_input_tokens_seen": 8688214592,
      "step": 30550,
      "train_runtime": 297641.9107,
      "train_tokens_per_second": 29190.159
    },
    {
      "epoch": 1.0812725145785005,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4827122377998815e-05,
      "loss": 1.0370466232299804,
      "num_input_tokens_seen": 8691076224,
      "step": 30560,
      "train_runtime": 297738.7063,
      "train_tokens_per_second": 29190.28
    },
    {
      "epoch": 1.0816263348422293,
      "grad_norm": 1.5703125,
      "learning_rate": 2.4824062325680737e-05,
      "loss": 1.038159465789795,
      "num_input_tokens_seen": 8693898432,
      "step": 30570,
      "train_runtime": 297835.8317,
      "train_tokens_per_second": 29190.237
    },
    {
      "epoch": 1.081980155105958,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4821003404578623e-05,
      "loss": 1.0451680183410645,
      "num_input_tokens_seen": 8696720704,
      "step": 30580,
      "train_runtime": 297930.6687,
      "train_tokens_per_second": 29190.418
    },
    {
      "epoch": 1.082333975369687,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4817945613995703e-05,
      "loss": 1.0363076210021973,
      "num_input_tokens_seen": 8699545408,
      "step": 30590,
      "train_runtime": 298024.4018,
      "train_tokens_per_second": 29190.715
    },
    {
      "epoch": 1.0826877956334158,
      "grad_norm": 1.515625,
      "learning_rate": 2.481488895323577e-05,
      "loss": 1.0608390808105468,
      "num_input_tokens_seen": 8702389504,
      "step": 30600,
      "train_runtime": 298119.8471,
      "train_tokens_per_second": 29190.91
    },
    {
      "epoch": 1.0830416158971445,
      "grad_norm": 1.5,
      "learning_rate": 2.481183342160324e-05,
      "loss": 1.0562709808349608,
      "num_input_tokens_seen": 8705240000,
      "step": 30610,
      "train_runtime": 298218.1932,
      "train_tokens_per_second": 29190.841
    },
    {
      "epoch": 1.0833954361608733,
      "grad_norm": 1.578125,
      "learning_rate": 2.4808779018403107e-05,
      "loss": 1.044337844848633,
      "num_input_tokens_seen": 8708054656,
      "step": 30620,
      "train_runtime": 298315.3686,
      "train_tokens_per_second": 29190.768
    },
    {
      "epoch": 1.083749256424602,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4805725742940987e-05,
      "loss": 1.0405929565429688,
      "num_input_tokens_seen": 8710902016,
      "step": 30630,
      "train_runtime": 298413.6176,
      "train_tokens_per_second": 29190.699
    },
    {
      "epoch": 1.0841030766883308,
      "grad_norm": 1.5390625,
      "learning_rate": 2.4802673594523086e-05,
      "loss": 1.0613485336303712,
      "num_input_tokens_seen": 8713767680,
      "step": 30640,
      "train_runtime": 298515.1001,
      "train_tokens_per_second": 29190.375
    },
    {
      "epoch": 1.0844568969520596,
      "grad_norm": 1.4765625,
      "learning_rate": 2.4799622572456198e-05,
      "loss": 1.0447149276733398,
      "num_input_tokens_seen": 8716583552,
      "step": 30650,
      "train_runtime": 298609.1483,
      "train_tokens_per_second": 29190.611
    },
    {
      "epoch": 1.0848107172157884,
      "grad_norm": 1.515625,
      "learning_rate": 2.479657267604772e-05,
      "loss": 1.0446485519409179,
      "num_input_tokens_seen": 8719445056,
      "step": 30660,
      "train_runtime": 298705.5966,
      "train_tokens_per_second": 29190.766
    },
    {
      "epoch": 1.0851645374795171,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4793523904605657e-05,
      "loss": 1.0459712028503418,
      "num_input_tokens_seen": 8722262400,
      "step": 30670,
      "train_runtime": 298800.0204,
      "train_tokens_per_second": 29190.97
    },
    {
      "epoch": 1.085518357743246,
      "grad_norm": 1.46875,
      "learning_rate": 2.479047625743859e-05,
      "loss": 1.0515359878540038,
      "num_input_tokens_seen": 8725083008,
      "step": 30680,
      "train_runtime": 298896.4016,
      "train_tokens_per_second": 29190.994
    },
    {
      "epoch": 1.0858721780069747,
      "grad_norm": 1.546875,
      "learning_rate": 2.4787429733855697e-05,
      "loss": 1.0492181777954102,
      "num_input_tokens_seen": 8727941952,
      "step": 30690,
      "train_runtime": 298994.9556,
      "train_tokens_per_second": 29190.934
    },
    {
      "epoch": 1.0862259982707034,
      "grad_norm": 1.5,
      "learning_rate": 2.478438433316677e-05,
      "loss": 1.0382863998413085,
      "num_input_tokens_seen": 8730815872,
      "step": 30700,
      "train_runtime": 299094.5214,
      "train_tokens_per_second": 29190.825
    },
    {
      "epoch": 1.0865798185344322,
      "grad_norm": 1.4609375,
      "learning_rate": 2.478134005468217e-05,
      "loss": 1.0530181884765626,
      "num_input_tokens_seen": 8733630720,
      "step": 30710,
      "train_runtime": 299190.7199,
      "train_tokens_per_second": 29190.848
    },
    {
      "epoch": 1.086933638798161,
      "grad_norm": 1.53125,
      "learning_rate": 2.4778296897712865e-05,
      "loss": 1.044699001312256,
      "num_input_tokens_seen": 8736459968,
      "step": 30720,
      "train_runtime": 299286.1103,
      "train_tokens_per_second": 29190.997
    },
    {
      "epoch": 1.0872874590618897,
      "grad_norm": 1.578125,
      "learning_rate": 2.4775254861570422e-05,
      "loss": 1.0501251220703125,
      "num_input_tokens_seen": 8739337600,
      "step": 30730,
      "train_runtime": 299384.3463,
      "train_tokens_per_second": 29191.031
    },
    {
      "epoch": 1.0876412793256185,
      "grad_norm": 1.5625,
      "learning_rate": 2.4772213945566974e-05,
      "loss": 1.0486842155456544,
      "num_input_tokens_seen": 8742197120,
      "step": 30740,
      "train_runtime": 299482.7554,
      "train_tokens_per_second": 29190.987
    },
    {
      "epoch": 1.0879950995893473,
      "grad_norm": 1.5703125,
      "learning_rate": 2.4769174149015266e-05,
      "loss": 1.0486906051635743,
      "num_input_tokens_seen": 8745038464,
      "step": 30750,
      "train_runtime": 299578.9517,
      "train_tokens_per_second": 29191.098
    },
    {
      "epoch": 1.0883489198530762,
      "grad_norm": 1.5234375,
      "learning_rate": 2.476613547122863e-05,
      "loss": 1.039016056060791,
      "num_input_tokens_seen": 8747859200,
      "step": 30760,
      "train_runtime": 299672.0653,
      "train_tokens_per_second": 29191.44
    },
    {
      "epoch": 1.088702740116805,
      "grad_norm": 1.5,
      "learning_rate": 2.476309791152098e-05,
      "loss": 1.0504534721374512,
      "num_input_tokens_seen": 8750696064,
      "step": 30770,
      "train_runtime": 299770.9669,
      "train_tokens_per_second": 29191.273
    },
    {
      "epoch": 1.0890565603805338,
      "grad_norm": 1.5625,
      "learning_rate": 2.4760061469206827e-05,
      "loss": 1.0460838317871093,
      "num_input_tokens_seen": 8753561088,
      "step": 30780,
      "train_runtime": 299870.4998,
      "train_tokens_per_second": 29191.138
    },
    {
      "epoch": 1.0894103806442625,
      "grad_norm": 1.53125,
      "learning_rate": 2.4757026143601268e-05,
      "loss": 1.0525848388671875,
      "num_input_tokens_seen": 8756371328,
      "step": 30790,
      "train_runtime": 299962.3874,
      "train_tokens_per_second": 29191.564
    },
    {
      "epoch": 1.0897642009079913,
      "grad_norm": 1.484375,
      "learning_rate": 2.475399193401998e-05,
      "loss": 1.05786190032959,
      "num_input_tokens_seen": 8759267776,
      "step": 30800,
      "train_runtime": 300063.1715,
      "train_tokens_per_second": 29191.412
    },
    {
      "epoch": 1.09011802117172,
      "grad_norm": 1.5234375,
      "learning_rate": 2.475095883977924e-05,
      "loss": 1.0509421348571777,
      "num_input_tokens_seen": 8762098944,
      "step": 30810,
      "train_runtime": 300160.8754,
      "train_tokens_per_second": 29191.343
    },
    {
      "epoch": 1.0904718414354488,
      "grad_norm": 1.5625,
      "learning_rate": 2.474792686019591e-05,
      "loss": 1.058945083618164,
      "num_input_tokens_seen": 8764981312,
      "step": 30820,
      "train_runtime": 300261.7557,
      "train_tokens_per_second": 29191.135
    },
    {
      "epoch": 1.0908256616991776,
      "grad_norm": 1.5,
      "learning_rate": 2.474489599458742e-05,
      "loss": 1.0421622276306153,
      "num_input_tokens_seen": 8767852096,
      "step": 30830,
      "train_runtime": 300359.1119,
      "train_tokens_per_second": 29191.231
    },
    {
      "epoch": 1.0911794819629064,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4741866242271804e-05,
      "loss": 1.0410686492919923,
      "num_input_tokens_seen": 8770695360,
      "step": 30840,
      "train_runtime": 300456.183,
      "train_tokens_per_second": 29191.263
    },
    {
      "epoch": 1.0915333022266351,
      "grad_norm": 1.5625,
      "learning_rate": 2.473883760256767e-05,
      "loss": 1.0436766624450684,
      "num_input_tokens_seen": 8773544896,
      "step": 30850,
      "train_runtime": 300554.7256,
      "train_tokens_per_second": 29191.173
    },
    {
      "epoch": 1.091887122490364,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4735810074794217e-05,
      "loss": 1.0514400482177735,
      "num_input_tokens_seen": 8776427072,
      "step": 30860,
      "train_runtime": 300656.3635,
      "train_tokens_per_second": 29190.891
    },
    {
      "epoch": 1.0922409427540927,
      "grad_norm": 1.578125,
      "learning_rate": 2.473278365827123e-05,
      "loss": 1.0523329734802247,
      "num_input_tokens_seen": 8779285632,
      "step": 30870,
      "train_runtime": 300754.7594,
      "train_tokens_per_second": 29190.845
    },
    {
      "epoch": 1.0925947630178214,
      "grad_norm": 1.46875,
      "learning_rate": 2.472975835231906e-05,
      "loss": 1.03155574798584,
      "num_input_tokens_seen": 8782105792,
      "step": 30880,
      "train_runtime": 300850.7221,
      "train_tokens_per_second": 29190.908
    },
    {
      "epoch": 1.0929485832815502,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4726734156258647e-05,
      "loss": 1.0517875671386718,
      "num_input_tokens_seen": 8784940160,
      "step": 30890,
      "train_runtime": 300948.0247,
      "train_tokens_per_second": 29190.888
    },
    {
      "epoch": 1.093302403545279,
      "grad_norm": 1.453125,
      "learning_rate": 2.4723711069411526e-05,
      "loss": 1.045181655883789,
      "num_input_tokens_seen": 8787793280,
      "step": 30900,
      "train_runtime": 301045.5653,
      "train_tokens_per_second": 29190.908
    },
    {
      "epoch": 1.0936562238090077,
      "grad_norm": 1.5390625,
      "learning_rate": 2.472068909109979e-05,
      "loss": 1.0326014518737794,
      "num_input_tokens_seen": 8790602368,
      "step": 30910,
      "train_runtime": 301143.3034,
      "train_tokens_per_second": 29190.762
    },
    {
      "epoch": 1.0940100440727365,
      "grad_norm": 1.4609375,
      "learning_rate": 2.471766822064614e-05,
      "loss": 1.0526304244995117,
      "num_input_tokens_seen": 8793475968,
      "step": 30920,
      "train_runtime": 301242.9576,
      "train_tokens_per_second": 29190.644
    },
    {
      "epoch": 1.0943638643364655,
      "grad_norm": 1.4921875,
      "learning_rate": 2.4714648457373824e-05,
      "loss": 1.061772918701172,
      "num_input_tokens_seen": 8796281344,
      "step": 30930,
      "train_runtime": 301338.0831,
      "train_tokens_per_second": 29190.739
    },
    {
      "epoch": 1.0947176846001943,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4711629800606694e-05,
      "loss": 1.0545734405517577,
      "num_input_tokens_seen": 8799133248,
      "step": 30940,
      "train_runtime": 301435.9162,
      "train_tokens_per_second": 29190.726
    },
    {
      "epoch": 1.095071504863923,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4708612249669157e-05,
      "loss": 1.029511070251465,
      "num_input_tokens_seen": 8801989376,
      "step": 30950,
      "train_runtime": 301534.5957,
      "train_tokens_per_second": 29190.645
    },
    {
      "epoch": 1.0954253251276518,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4705595803886223e-05,
      "loss": 1.0471227645874024,
      "num_input_tokens_seen": 8804858112,
      "step": 30960,
      "train_runtime": 301634.612,
      "train_tokens_per_second": 29190.477
    },
    {
      "epoch": 1.0957791453913805,
      "grad_norm": 1.515625,
      "learning_rate": 2.4702580462583468e-05,
      "loss": 1.0468629837036132,
      "num_input_tokens_seen": 8807736384,
      "step": 30970,
      "train_runtime": 301732.889,
      "train_tokens_per_second": 29190.508
    },
    {
      "epoch": 1.0961329656551093,
      "grad_norm": 1.5,
      "learning_rate": 2.4699566225087032e-05,
      "loss": 1.0527093887329102,
      "num_input_tokens_seen": 8810558976,
      "step": 30980,
      "train_runtime": 301826.8997,
      "train_tokens_per_second": 29190.768
    },
    {
      "epoch": 1.096486785918838,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4696553090723644e-05,
      "loss": 1.04113826751709,
      "num_input_tokens_seen": 8813443392,
      "step": 30990,
      "train_runtime": 301925.9443,
      "train_tokens_per_second": 29190.745
    },
    {
      "epoch": 1.0968406061825668,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4693541058820606e-05,
      "loss": 1.054214096069336,
      "num_input_tokens_seen": 8816337728,
      "step": 31000,
      "train_runtime": 302025.6837,
      "train_tokens_per_second": 29190.689
    },
    {
      "epoch": 1.0971944264462956,
      "grad_norm": 1.53125,
      "learning_rate": 2.4690530128705798e-05,
      "loss": 1.045550537109375,
      "num_input_tokens_seen": 8819114624,
      "step": 31010,
      "train_runtime": 302117.1336,
      "train_tokens_per_second": 29191.044
    },
    {
      "epoch": 1.0975482467100244,
      "grad_norm": 1.53125,
      "learning_rate": 2.4687520299707655e-05,
      "loss": 1.0659130096435547,
      "num_input_tokens_seen": 8821949056,
      "step": 31020,
      "train_runtime": 302214.9256,
      "train_tokens_per_second": 29190.977
    },
    {
      "epoch": 1.0979020669737531,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4684511571155208e-05,
      "loss": 1.0533631324768067,
      "num_input_tokens_seen": 8824721216,
      "step": 31030,
      "train_runtime": 302310.5652,
      "train_tokens_per_second": 29190.912
    },
    {
      "epoch": 1.098255887237482,
      "grad_norm": 1.578125,
      "learning_rate": 2.4681503942378048e-05,
      "loss": 1.0494016647338866,
      "num_input_tokens_seen": 8827554688,
      "step": 31040,
      "train_runtime": 302407.507,
      "train_tokens_per_second": 29190.924
    },
    {
      "epoch": 1.0986097075012107,
      "grad_norm": 1.515625,
      "learning_rate": 2.4678497412706344e-05,
      "loss": 1.0470052719116212,
      "num_input_tokens_seen": 8830366976,
      "step": 31050,
      "train_runtime": 302505.6869,
      "train_tokens_per_second": 29190.747
    },
    {
      "epoch": 1.0989635277649394,
      "grad_norm": 1.515625,
      "learning_rate": 2.4675491981470825e-05,
      "loss": 1.0486572265625,
      "num_input_tokens_seen": 8833177664,
      "step": 31060,
      "train_runtime": 302600.7043,
      "train_tokens_per_second": 29190.869
    },
    {
      "epoch": 1.0993173480286682,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4672487648002803e-05,
      "loss": 1.0364870071411132,
      "num_input_tokens_seen": 8835960448,
      "step": 31070,
      "train_runtime": 302697.3773,
      "train_tokens_per_second": 29190.74
    },
    {
      "epoch": 1.099671168292397,
      "grad_norm": 1.578125,
      "learning_rate": 2.4669484411634147e-05,
      "loss": 1.0433317184448243,
      "num_input_tokens_seen": 8838765440,
      "step": 31080,
      "train_runtime": 302794.6868,
      "train_tokens_per_second": 29190.623
    },
    {
      "epoch": 1.1000249885561257,
      "grad_norm": 1.5390625,
      "learning_rate": 2.466648227169731e-05,
      "loss": 1.0406436920166016,
      "num_input_tokens_seen": 8841659136,
      "step": 31090,
      "train_runtime": 302894.5805,
      "train_tokens_per_second": 29190.549
    },
    {
      "epoch": 1.1003788088198547,
      "grad_norm": 1.53125,
      "learning_rate": 2.4663481227525304e-05,
      "loss": 1.0454859733581543,
      "num_input_tokens_seen": 8844499712,
      "step": 31100,
      "train_runtime": 302992.4831,
      "train_tokens_per_second": 29190.492
    },
    {
      "epoch": 1.1007326290835835,
      "grad_norm": 1.4296875,
      "learning_rate": 2.4660481278451704e-05,
      "loss": 1.041936492919922,
      "num_input_tokens_seen": 8847438720,
      "step": 31110,
      "train_runtime": 303096.5202,
      "train_tokens_per_second": 29190.169
    },
    {
      "epoch": 1.1010864493473123,
      "grad_norm": 1.546875,
      "learning_rate": 2.465748242381067e-05,
      "loss": 1.0427564620971679,
      "num_input_tokens_seen": 8850241344,
      "step": 31120,
      "train_runtime": 303191.1789,
      "train_tokens_per_second": 29190.3
    },
    {
      "epoch": 1.101440269611041,
      "grad_norm": 1.5390625,
      "learning_rate": 2.4654484662936915e-05,
      "loss": 1.0541624069213866,
      "num_input_tokens_seen": 8853025600,
      "step": 31130,
      "train_runtime": 303286.0314,
      "train_tokens_per_second": 29190.351
    },
    {
      "epoch": 1.1017940898747698,
      "grad_norm": 1.4921875,
      "learning_rate": 2.4651487995165712e-05,
      "loss": 1.0453739166259766,
      "num_input_tokens_seen": 8855847872,
      "step": 31140,
      "train_runtime": 303381.8347,
      "train_tokens_per_second": 29190.435
    },
    {
      "epoch": 1.1021479101384986,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4648492419832915e-05,
      "loss": 1.0470635414123535,
      "num_input_tokens_seen": 8858661760,
      "step": 31150,
      "train_runtime": 303477.5497,
      "train_tokens_per_second": 29190.501
    },
    {
      "epoch": 1.1025017304022273,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4645497936274937e-05,
      "loss": 1.0383598327636718,
      "num_input_tokens_seen": 8861430016,
      "step": 31160,
      "train_runtime": 303569.942,
      "train_tokens_per_second": 29190.736
    },
    {
      "epoch": 1.102855550665956,
      "grad_norm": 1.5390625,
      "learning_rate": 2.4642504543828753e-05,
      "loss": 1.0553249359130858,
      "num_input_tokens_seen": 8864291968,
      "step": 31170,
      "train_runtime": 303667.1459,
      "train_tokens_per_second": 29190.817
    },
    {
      "epoch": 1.1032093709296849,
      "grad_norm": 1.484375,
      "learning_rate": 2.4639512241831904e-05,
      "loss": 1.0555017471313477,
      "num_input_tokens_seen": 8867147392,
      "step": 31180,
      "train_runtime": 303767.6686,
      "train_tokens_per_second": 29190.557
    },
    {
      "epoch": 1.1035631911934136,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4636521029622485e-05,
      "loss": 1.049258041381836,
      "num_input_tokens_seen": 8869901376,
      "step": 31190,
      "train_runtime": 303858.6513,
      "train_tokens_per_second": 29190.88
    },
    {
      "epoch": 1.1039170114571424,
      "grad_norm": 1.5078125,
      "learning_rate": 2.463353090653917e-05,
      "loss": 1.0552886962890624,
      "num_input_tokens_seen": 8872737920,
      "step": 31200,
      "train_runtime": 303955.9923,
      "train_tokens_per_second": 29190.864
    },
    {
      "epoch": 1.1042708317208711,
      "grad_norm": 1.5,
      "learning_rate": 2.4630541871921187e-05,
      "loss": 1.0535228729248047,
      "num_input_tokens_seen": 8875596736,
      "step": 31210,
      "train_runtime": 304055.1752,
      "train_tokens_per_second": 29190.744
    },
    {
      "epoch": 1.1046246519846,
      "grad_norm": 1.484375,
      "learning_rate": 2.4627553925108313e-05,
      "loss": 1.0456931114196777,
      "num_input_tokens_seen": 8878420480,
      "step": 31220,
      "train_runtime": 304152.9035,
      "train_tokens_per_second": 29190.648
    },
    {
      "epoch": 1.1049784722483287,
      "grad_norm": 1.53125,
      "learning_rate": 2.4624567065440906e-05,
      "loss": 1.0231801986694335,
      "num_input_tokens_seen": 8881234816,
      "step": 31230,
      "train_runtime": 304248.3569,
      "train_tokens_per_second": 29190.74
    },
    {
      "epoch": 1.1053322925120574,
      "grad_norm": 1.5625,
      "learning_rate": 2.4621581292259868e-05,
      "loss": 1.0556482315063476,
      "num_input_tokens_seen": 8883989888,
      "step": 31240,
      "train_runtime": 304342.0799,
      "train_tokens_per_second": 29190.804
    },
    {
      "epoch": 1.1056861127757862,
      "grad_norm": 1.5,
      "learning_rate": 2.4618596604906673e-05,
      "loss": 1.0458615303039551,
      "num_input_tokens_seen": 8886794368,
      "step": 31250,
      "train_runtime": 304437.0651,
      "train_tokens_per_second": 29190.908
    },
    {
      "epoch": 1.106039933039515,
      "grad_norm": 1.53125,
      "learning_rate": 2.4615613002723347e-05,
      "loss": 1.0497917175292968,
      "num_input_tokens_seen": 8889625600,
      "step": 31260,
      "train_runtime": 304530.4194,
      "train_tokens_per_second": 29191.257
    },
    {
      "epoch": 1.106393753303244,
      "grad_norm": 1.515625,
      "learning_rate": 2.4612630485052466e-05,
      "loss": 1.067885398864746,
      "num_input_tokens_seen": 8892476480,
      "step": 31270,
      "train_runtime": 304628.6883,
      "train_tokens_per_second": 29191.198
    },
    {
      "epoch": 1.1067475735669727,
      "grad_norm": 1.5625,
      "learning_rate": 2.4609649051237175e-05,
      "loss": 1.0575736045837403,
      "num_input_tokens_seen": 8895300608,
      "step": 31280,
      "train_runtime": 304722.7593,
      "train_tokens_per_second": 29191.455
    },
    {
      "epoch": 1.1071013938307015,
      "grad_norm": 1.5703125,
      "learning_rate": 2.460666870062118e-05,
      "loss": 1.0464168548583985,
      "num_input_tokens_seen": 8898108736,
      "step": 31290,
      "train_runtime": 304818.0323,
      "train_tokens_per_second": 29191.543
    },
    {
      "epoch": 1.1074552140944303,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4603689432548728e-05,
      "loss": 1.0408933639526368,
      "num_input_tokens_seen": 8900946240,
      "step": 31300,
      "train_runtime": 304915.5895,
      "train_tokens_per_second": 29191.509
    },
    {
      "epoch": 1.107809034358159,
      "grad_norm": 1.5234375,
      "learning_rate": 2.460071124636463e-05,
      "loss": 1.0459248542785644,
      "num_input_tokens_seen": 8903786752,
      "step": 31310,
      "train_runtime": 305013.361,
      "train_tokens_per_second": 29191.465
    },
    {
      "epoch": 1.1081628546218878,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4597734141414254e-05,
      "loss": 1.0534470558166504,
      "num_input_tokens_seen": 8906625472,
      "step": 31320,
      "train_runtime": 305111.6807,
      "train_tokens_per_second": 29191.362
    },
    {
      "epoch": 1.1085166748856166,
      "grad_norm": 1.5390625,
      "learning_rate": 2.4594758117043516e-05,
      "loss": 1.0427116394042968,
      "num_input_tokens_seen": 8909447808,
      "step": 31330,
      "train_runtime": 305207.5283,
      "train_tokens_per_second": 29191.442
    },
    {
      "epoch": 1.1088704951493453,
      "grad_norm": 1.4609375,
      "learning_rate": 2.4591783172598898e-05,
      "loss": 1.0386438369750977,
      "num_input_tokens_seen": 8912378432,
      "step": 31340,
      "train_runtime": 305312.2238,
      "train_tokens_per_second": 29191.03
    },
    {
      "epoch": 1.109224315413074,
      "grad_norm": 1.484375,
      "learning_rate": 2.458880930742742e-05,
      "loss": 1.0455702781677245,
      "num_input_tokens_seen": 8915198144,
      "step": 31350,
      "train_runtime": 305407.68,
      "train_tokens_per_second": 29191.139
    },
    {
      "epoch": 1.1095781356768029,
      "grad_norm": 1.5,
      "learning_rate": 2.458583652087666e-05,
      "loss": 1.04412841796875,
      "num_input_tokens_seen": 8918044992,
      "step": 31360,
      "train_runtime": 305503.5699,
      "train_tokens_per_second": 29191.296
    },
    {
      "epoch": 1.1099319559405316,
      "grad_norm": 1.4765625,
      "learning_rate": 2.4582864812294757e-05,
      "loss": 1.044855499267578,
      "num_input_tokens_seen": 8920859072,
      "step": 31370,
      "train_runtime": 305599.4905,
      "train_tokens_per_second": 29191.341
    },
    {
      "epoch": 1.1102857762042604,
      "grad_norm": 1.578125,
      "learning_rate": 2.4579894181030387e-05,
      "loss": 1.0475560188293458,
      "num_input_tokens_seen": 8923675840,
      "step": 31380,
      "train_runtime": 305694.711,
      "train_tokens_per_second": 29191.463
    },
    {
      "epoch": 1.1106395964679892,
      "grad_norm": 1.484375,
      "learning_rate": 2.457692462643279e-05,
      "loss": 1.0380531311035157,
      "num_input_tokens_seen": 8926519936,
      "step": 31390,
      "train_runtime": 305791.9212,
      "train_tokens_per_second": 29191.484
    },
    {
      "epoch": 1.110993416731718,
      "grad_norm": 1.5625,
      "learning_rate": 2.4573956147851734e-05,
      "loss": 1.046290969848633,
      "num_input_tokens_seen": 8929360768,
      "step": 31400,
      "train_runtime": 305889.2544,
      "train_tokens_per_second": 29191.482
    },
    {
      "epoch": 1.1113472369954467,
      "grad_norm": 1.546875,
      "learning_rate": 2.4570988744637573e-05,
      "loss": 1.0340972900390626,
      "num_input_tokens_seen": 8932176064,
      "step": 31410,
      "train_runtime": 305983.6071,
      "train_tokens_per_second": 29191.682
    },
    {
      "epoch": 1.1117010572591755,
      "grad_norm": 1.546875,
      "learning_rate": 2.4568022416141178e-05,
      "loss": 1.0471845626831056,
      "num_input_tokens_seen": 8935036928,
      "step": 31420,
      "train_runtime": 306080.1689,
      "train_tokens_per_second": 29191.819
    },
    {
      "epoch": 1.1120548775229042,
      "grad_norm": 1.4375,
      "learning_rate": 2.4565057161713987e-05,
      "loss": 1.0552879333496095,
      "num_input_tokens_seen": 8937931264,
      "step": 31430,
      "train_runtime": 306181.0071,
      "train_tokens_per_second": 29191.658
    },
    {
      "epoch": 1.1124086977866332,
      "grad_norm": 1.53125,
      "learning_rate": 2.4562092980707975e-05,
      "loss": 1.0414106369018554,
      "num_input_tokens_seen": 8940802240,
      "step": 31440,
      "train_runtime": 306278.2142,
      "train_tokens_per_second": 29191.767
    },
    {
      "epoch": 1.112762518050362,
      "grad_norm": 1.546875,
      "learning_rate": 2.455912987247566e-05,
      "loss": 1.047684383392334,
      "num_input_tokens_seen": 8943665088,
      "step": 31450,
      "train_runtime": 306376.259,
      "train_tokens_per_second": 29191.769
    },
    {
      "epoch": 1.1131163383140907,
      "grad_norm": 1.4921875,
      "learning_rate": 2.455616783637013e-05,
      "loss": 1.0307809829711914,
      "num_input_tokens_seen": 8946493184,
      "step": 31460,
      "train_runtime": 306475.0425,
      "train_tokens_per_second": 29191.588
    },
    {
      "epoch": 1.1134701585778195,
      "grad_norm": 1.53125,
      "learning_rate": 2.4553206871745e-05,
      "loss": 1.0528751373291017,
      "num_input_tokens_seen": 8949372224,
      "step": 31470,
      "train_runtime": 306574.6036,
      "train_tokens_per_second": 29191.499
    },
    {
      "epoch": 1.1138239788415483,
      "grad_norm": 1.4765625,
      "learning_rate": 2.4550246977954422e-05,
      "loss": 1.0489970207214356,
      "num_input_tokens_seen": 8952211392,
      "step": 31480,
      "train_runtime": 306671.4842,
      "train_tokens_per_second": 29191.535
    },
    {
      "epoch": 1.114177799105277,
      "grad_norm": 1.5703125,
      "learning_rate": 2.454728815435312e-05,
      "loss": 1.0605897903442383,
      "num_input_tokens_seen": 8955083968,
      "step": 31490,
      "train_runtime": 306771.9897,
      "train_tokens_per_second": 29191.335
    },
    {
      "epoch": 1.1145316193690058,
      "grad_norm": 1.546875,
      "learning_rate": 2.4544330400296333e-05,
      "loss": 1.061956787109375,
      "num_input_tokens_seen": 8957897152,
      "step": 31500,
      "train_runtime": 306866.4948,
      "train_tokens_per_second": 29191.513
    },
    {
      "epoch": 1.1148854396327346,
      "grad_norm": 1.5625,
      "learning_rate": 2.4541373715139876e-05,
      "loss": 1.0594853401184081,
      "num_input_tokens_seen": 8960745408,
      "step": 31510,
      "train_runtime": 306966.8663,
      "train_tokens_per_second": 29191.246
    },
    {
      "epoch": 1.1152392598964633,
      "grad_norm": 1.5390625,
      "learning_rate": 2.453841809824007e-05,
      "loss": 1.0405210494995116,
      "num_input_tokens_seen": 8963585856,
      "step": 31520,
      "train_runtime": 307065.1845,
      "train_tokens_per_second": 29191.15
    },
    {
      "epoch": 1.115593080160192,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4535463548953808e-05,
      "loss": 1.0429888725280763,
      "num_input_tokens_seen": 8966380032,
      "step": 31530,
      "train_runtime": 307158.5428,
      "train_tokens_per_second": 29191.374
    },
    {
      "epoch": 1.1159469004239209,
      "grad_norm": 1.5,
      "learning_rate": 2.4532510066638515e-05,
      "loss": 1.0548622131347656,
      "num_input_tokens_seen": 8969227840,
      "step": 31540,
      "train_runtime": 307259.5212,
      "train_tokens_per_second": 29191.049
    },
    {
      "epoch": 1.1163007206876496,
      "grad_norm": 1.5234375,
      "learning_rate": 2.452955765065216e-05,
      "loss": 1.044530487060547,
      "num_input_tokens_seen": 8972045184,
      "step": 31550,
      "train_runtime": 307355.1375,
      "train_tokens_per_second": 29191.135
    },
    {
      "epoch": 1.1166545409513784,
      "grad_norm": 1.53125,
      "learning_rate": 2.4526606300353234e-05,
      "loss": 1.0411452293395995,
      "num_input_tokens_seen": 8974774208,
      "step": 31560,
      "train_runtime": 307444.1593,
      "train_tokens_per_second": 29191.559
    },
    {
      "epoch": 1.1170083612151072,
      "grad_norm": 1.5390625,
      "learning_rate": 2.4523656015100795e-05,
      "loss": 1.0385894775390625,
      "num_input_tokens_seen": 8977614272,
      "step": 31570,
      "train_runtime": 307543.0173,
      "train_tokens_per_second": 29191.41
    },
    {
      "epoch": 1.117362181478836,
      "grad_norm": 1.4921875,
      "learning_rate": 2.4520706794254433e-05,
      "loss": 1.0645389556884766,
      "num_input_tokens_seen": 8980489344,
      "step": 31580,
      "train_runtime": 307643.2607,
      "train_tokens_per_second": 29191.244
    },
    {
      "epoch": 1.117716001742565,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4517758637174266e-05,
      "loss": 1.0459966659545898,
      "num_input_tokens_seen": 8983301248,
      "step": 31590,
      "train_runtime": 307735.8503,
      "train_tokens_per_second": 29191.598
    },
    {
      "epoch": 1.1180698220062937,
      "grad_norm": 1.4921875,
      "learning_rate": 2.4514811543220957e-05,
      "loss": 1.0456958770751954,
      "num_input_tokens_seen": 8986166976,
      "step": 31600,
      "train_runtime": 307833.4767,
      "train_tokens_per_second": 29191.65
    },
    {
      "epoch": 1.1184236422700224,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4511865511755717e-05,
      "loss": 1.048631477355957,
      "num_input_tokens_seen": 8989008256,
      "step": 31610,
      "train_runtime": 307929.248,
      "train_tokens_per_second": 29191.798
    },
    {
      "epoch": 1.1187774625337512,
      "grad_norm": 1.59375,
      "learning_rate": 2.4508920542140266e-05,
      "loss": 1.06162109375,
      "num_input_tokens_seen": 8991880064,
      "step": 31620,
      "train_runtime": 308026.4464,
      "train_tokens_per_second": 29191.909
    },
    {
      "epoch": 1.11913128279748,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4505976633736905e-05,
      "loss": 1.049001407623291,
      "num_input_tokens_seen": 8994712896,
      "step": 31630,
      "train_runtime": 308122.6184,
      "train_tokens_per_second": 29191.992
    },
    {
      "epoch": 1.1194851030612087,
      "grad_norm": 1.515625,
      "learning_rate": 2.4503033785908423e-05,
      "loss": 1.0532272338867188,
      "num_input_tokens_seen": 8997562816,
      "step": 31640,
      "train_runtime": 308220.5335,
      "train_tokens_per_second": 29191.964
    },
    {
      "epoch": 1.1198389233249375,
      "grad_norm": 1.515625,
      "learning_rate": 2.4500091998018178e-05,
      "loss": 1.0328126907348634,
      "num_input_tokens_seen": 9000375744,
      "step": 31650,
      "train_runtime": 308315.0323,
      "train_tokens_per_second": 29192.141
    },
    {
      "epoch": 1.1201927435886663,
      "grad_norm": 1.578125,
      "learning_rate": 2.4497151269430056e-05,
      "loss": 1.0480571746826173,
      "num_input_tokens_seen": 9003194944,
      "step": 31660,
      "train_runtime": 308409.0779,
      "train_tokens_per_second": 29192.38
    },
    {
      "epoch": 1.120546563852395,
      "grad_norm": 1.5703125,
      "learning_rate": 2.4494211599508456e-05,
      "loss": 1.0557334899902344,
      "num_input_tokens_seen": 9006043008,
      "step": 31670,
      "train_runtime": 308506.3339,
      "train_tokens_per_second": 29192.409
    },
    {
      "epoch": 1.1209003841161238,
      "grad_norm": 1.5,
      "learning_rate": 2.4491272987618343e-05,
      "loss": 1.0364778518676758,
      "num_input_tokens_seen": 9008929856,
      "step": 31680,
      "train_runtime": 308608.2548,
      "train_tokens_per_second": 29192.122
    },
    {
      "epoch": 1.1212542043798526,
      "grad_norm": 1.5234375,
      "learning_rate": 2.44883354331252e-05,
      "loss": 1.0408843994140624,
      "num_input_tokens_seen": 9011756992,
      "step": 31690,
      "train_runtime": 308704.7115,
      "train_tokens_per_second": 29192.159
    },
    {
      "epoch": 1.1216080246435813,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4485398935395037e-05,
      "loss": 1.041062068939209,
      "num_input_tokens_seen": 9014561344,
      "step": 31700,
      "train_runtime": 308802.1414,
      "train_tokens_per_second": 29192.03
    },
    {
      "epoch": 1.12196184490731,
      "grad_norm": 1.5,
      "learning_rate": 2.44824634937944e-05,
      "loss": 1.0443008422851563,
      "num_input_tokens_seen": 9017416320,
      "step": 31710,
      "train_runtime": 308898.6514,
      "train_tokens_per_second": 29192.152
    },
    {
      "epoch": 1.1223156651710389,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4479529107690374e-05,
      "loss": 1.0452661514282227,
      "num_input_tokens_seen": 9020226688,
      "step": 31720,
      "train_runtime": 308992.2753,
      "train_tokens_per_second": 29192.402
    },
    {
      "epoch": 1.1226694854347676,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4476595776450564e-05,
      "loss": 1.0426406860351562,
      "num_input_tokens_seen": 9023073728,
      "step": 31730,
      "train_runtime": 309090.8384,
      "train_tokens_per_second": 29192.304
    },
    {
      "epoch": 1.1230233056984964,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4473663499443112e-05,
      "loss": 1.0516764640808105,
      "num_input_tokens_seen": 9025939264,
      "step": 31740,
      "train_runtime": 309189.0717,
      "train_tokens_per_second": 29192.297
    },
    {
      "epoch": 1.1233771259622252,
      "grad_norm": 1.484375,
      "learning_rate": 2.4470732276036698e-05,
      "loss": 1.0516112327575684,
      "num_input_tokens_seen": 9028742144,
      "step": 31750,
      "train_runtime": 309283.5716,
      "train_tokens_per_second": 29192.44
    },
    {
      "epoch": 1.1237309462259542,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4467802105600504e-05,
      "loss": 1.0575088500976562,
      "num_input_tokens_seen": 9031582592,
      "step": 31760,
      "train_runtime": 309381.4844,
      "train_tokens_per_second": 29192.382
    },
    {
      "epoch": 1.124084766489683,
      "grad_norm": 1.515625,
      "learning_rate": 2.4464872987504275e-05,
      "loss": 1.0502893447875976,
      "num_input_tokens_seen": 9034511360,
      "step": 31770,
      "train_runtime": 309484.4073,
      "train_tokens_per_second": 29192.137
    },
    {
      "epoch": 1.1244385867534117,
      "grad_norm": 1.5546875,
      "learning_rate": 2.446194492111825e-05,
      "loss": 1.0474067687988282,
      "num_input_tokens_seen": 9037327936,
      "step": 31780,
      "train_runtime": 309580.808,
      "train_tokens_per_second": 29192.145
    },
    {
      "epoch": 1.1247924070171404,
      "grad_norm": 1.6171875,
      "learning_rate": 2.445901790581323e-05,
      "loss": 1.0419821739196777,
      "num_input_tokens_seen": 9040213888,
      "step": 31790,
      "train_runtime": 309678.1126,
      "train_tokens_per_second": 29192.292
    },
    {
      "epoch": 1.1251462272808692,
      "grad_norm": 1.5546875,
      "learning_rate": 2.445609194096051e-05,
      "loss": 1.0498111724853516,
      "num_input_tokens_seen": 9043037632,
      "step": 31800,
      "train_runtime": 309772.7052,
      "train_tokens_per_second": 29192.493
    },
    {
      "epoch": 1.125500047544598,
      "grad_norm": 1.625,
      "learning_rate": 2.4453167025931932e-05,
      "loss": 1.050590419769287,
      "num_input_tokens_seen": 9045867008,
      "step": 31810,
      "train_runtime": 309867.4145,
      "train_tokens_per_second": 29192.702
    },
    {
      "epoch": 1.1258538678083267,
      "grad_norm": 1.4453125,
      "learning_rate": 2.445024316009987e-05,
      "loss": 1.0657878875732423,
      "num_input_tokens_seen": 9048692928,
      "step": 31820,
      "train_runtime": 309964.4458,
      "train_tokens_per_second": 29192.68
    },
    {
      "epoch": 1.1262076880720555,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4447320342837192e-05,
      "loss": 1.0538702964782716,
      "num_input_tokens_seen": 9051539264,
      "step": 31830,
      "train_runtime": 310060.8247,
      "train_tokens_per_second": 29192.786
    },
    {
      "epoch": 1.1265615083357843,
      "grad_norm": 1.515625,
      "learning_rate": 2.444439857351732e-05,
      "loss": 1.0472599983215332,
      "num_input_tokens_seen": 9054397632,
      "step": 31840,
      "train_runtime": 310159.7546,
      "train_tokens_per_second": 29192.69
    },
    {
      "epoch": 1.126915328599513,
      "grad_norm": 1.53125,
      "learning_rate": 2.4441477851514195e-05,
      "loss": 1.0469745635986327,
      "num_input_tokens_seen": 9057182848,
      "step": 31850,
      "train_runtime": 310255.0787,
      "train_tokens_per_second": 29192.698
    },
    {
      "epoch": 1.1272691488632418,
      "grad_norm": 1.5,
      "learning_rate": 2.443855817620227e-05,
      "loss": 1.0439446449279786,
      "num_input_tokens_seen": 9060000320,
      "step": 31860,
      "train_runtime": 310354.0321,
      "train_tokens_per_second": 29192.469
    },
    {
      "epoch": 1.1276229691269706,
      "grad_norm": 1.4921875,
      "learning_rate": 2.4435639546956534e-05,
      "loss": 1.0508008003234863,
      "num_input_tokens_seen": 9062860096,
      "step": 31870,
      "train_runtime": 310452.7968,
      "train_tokens_per_second": 29192.393
    },
    {
      "epoch": 1.1279767893906993,
      "grad_norm": 1.5625,
      "learning_rate": 2.4432721963152482e-05,
      "loss": 1.0317928314208984,
      "num_input_tokens_seen": 9065692160,
      "step": 31880,
      "train_runtime": 310547.8618,
      "train_tokens_per_second": 29192.576
    },
    {
      "epoch": 1.128330609654428,
      "grad_norm": 1.5234375,
      "learning_rate": 2.442980542416615e-05,
      "loss": 1.0434582710266114,
      "num_input_tokens_seen": 9068529280,
      "step": 31890,
      "train_runtime": 310641.0875,
      "train_tokens_per_second": 29192.949
    },
    {
      "epoch": 1.1286844299181569,
      "grad_norm": 1.53125,
      "learning_rate": 2.4426889929374085e-05,
      "loss": 1.0450094223022461,
      "num_input_tokens_seen": 9071363904,
      "step": 31900,
      "train_runtime": 310734.785,
      "train_tokens_per_second": 29193.268
    },
    {
      "epoch": 1.1290382501818856,
      "grad_norm": 1.5625,
      "learning_rate": 2.442397547815336e-05,
      "loss": 1.034642219543457,
      "num_input_tokens_seen": 9074169152,
      "step": 31910,
      "train_runtime": 310830.9006,
      "train_tokens_per_second": 29193.266
    },
    {
      "epoch": 1.1293920704456144,
      "grad_norm": 1.6171875,
      "learning_rate": 2.4421062069881545e-05,
      "loss": 1.0458524703979493,
      "num_input_tokens_seen": 9077015808,
      "step": 31920,
      "train_runtime": 310930.3143,
      "train_tokens_per_second": 29193.087
    },
    {
      "epoch": 1.1297458907093434,
      "grad_norm": 1.5390625,
      "learning_rate": 2.4418149703936773e-05,
      "loss": 1.0533014297485352,
      "num_input_tokens_seen": 9079837120,
      "step": 31930,
      "train_runtime": 311028.1308,
      "train_tokens_per_second": 29192.977
    },
    {
      "epoch": 1.1300997109730722,
      "grad_norm": 1.59375,
      "learning_rate": 2.4415238379697657e-05,
      "loss": 1.0463518142700194,
      "num_input_tokens_seen": 9082718400,
      "step": 31940,
      "train_runtime": 311126.8154,
      "train_tokens_per_second": 29192.978
    },
    {
      "epoch": 1.130453531236801,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4412328096543355e-05,
      "loss": 1.056227207183838,
      "num_input_tokens_seen": 9085524160,
      "step": 31950,
      "train_runtime": 311222.8179,
      "train_tokens_per_second": 29192.989
    },
    {
      "epoch": 1.1308073515005297,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4409418853853517e-05,
      "loss": 1.050007438659668,
      "num_input_tokens_seen": 9088371776,
      "step": 31960,
      "train_runtime": 311321.4328,
      "train_tokens_per_second": 29192.888
    },
    {
      "epoch": 1.1311611717642585,
      "grad_norm": 1.5859375,
      "learning_rate": 2.440651065100833e-05,
      "loss": 1.049050521850586,
      "num_input_tokens_seen": 9091224704,
      "step": 31970,
      "train_runtime": 311420.5427,
      "train_tokens_per_second": 29192.759
    },
    {
      "epoch": 1.1315149920279872,
      "grad_norm": 1.53125,
      "learning_rate": 2.44036034873885e-05,
      "loss": 1.0518720626831055,
      "num_input_tokens_seen": 9094091584,
      "step": 31980,
      "train_runtime": 311518.9739,
      "train_tokens_per_second": 29192.737
    },
    {
      "epoch": 1.131868812291716,
      "grad_norm": 1.5625,
      "learning_rate": 2.440069736237523e-05,
      "loss": 1.0541970252990722,
      "num_input_tokens_seen": 9096930752,
      "step": 31990,
      "train_runtime": 311612.7942,
      "train_tokens_per_second": 29193.059
    },
    {
      "epoch": 1.1322226325554448,
      "grad_norm": 1.515625,
      "learning_rate": 2.439779227535026e-05,
      "loss": 1.0437821388244628,
      "num_input_tokens_seen": 9099779968,
      "step": 32000,
      "train_runtime": 311709.8301,
      "train_tokens_per_second": 29193.112
    },
    {
      "epoch": 1.1325764528191735,
      "grad_norm": 1.5078125,
      "learning_rate": 2.439488822569583e-05,
      "loss": 1.0526975631713866,
      "num_input_tokens_seen": 9102639104,
      "step": 32010,
      "train_runtime": 311805.9603,
      "train_tokens_per_second": 29193.281
    },
    {
      "epoch": 1.1329302730829023,
      "grad_norm": 1.5625,
      "learning_rate": 2.4391985212794695e-05,
      "loss": 1.0390093803405762,
      "num_input_tokens_seen": 9105475008,
      "step": 32020,
      "train_runtime": 311904.7411,
      "train_tokens_per_second": 29193.128
    },
    {
      "epoch": 1.133284093346631,
      "grad_norm": 1.609375,
      "learning_rate": 2.4389083236030146e-05,
      "loss": 1.0508566856384278,
      "num_input_tokens_seen": 9108276032,
      "step": 32030,
      "train_runtime": 312000.297,
      "train_tokens_per_second": 29193.165
    },
    {
      "epoch": 1.1336379136103598,
      "grad_norm": 1.515625,
      "learning_rate": 2.4386182294785952e-05,
      "loss": 1.0429948806762694,
      "num_input_tokens_seen": 9111154176,
      "step": 32040,
      "train_runtime": 312100.3361,
      "train_tokens_per_second": 29193.029
    },
    {
      "epoch": 1.1339917338740886,
      "grad_norm": 1.5390625,
      "learning_rate": 2.438328238844642e-05,
      "loss": 1.0432381629943848,
      "num_input_tokens_seen": 9113959488,
      "step": 32050,
      "train_runtime": 312193.8207,
      "train_tokens_per_second": 29193.273
    },
    {
      "epoch": 1.1343455541378173,
      "grad_norm": 1.5390625,
      "learning_rate": 2.4380383516396372e-05,
      "loss": 1.0511786460876464,
      "num_input_tokens_seen": 9116817472,
      "step": 32060,
      "train_runtime": 312289.3377,
      "train_tokens_per_second": 29193.496
    },
    {
      "epoch": 1.1346993744015461,
      "grad_norm": 1.578125,
      "learning_rate": 2.4377485678021113e-05,
      "loss": 1.0442041397094726,
      "num_input_tokens_seen": 9119695808,
      "step": 32070,
      "train_runtime": 312387.1321,
      "train_tokens_per_second": 29193.571
    },
    {
      "epoch": 1.1350531946652749,
      "grad_norm": 1.46875,
      "learning_rate": 2.4374588872706498e-05,
      "loss": 1.0452404022216797,
      "num_input_tokens_seen": 9122551872,
      "step": 32080,
      "train_runtime": 312485.8575,
      "train_tokens_per_second": 29193.487
    },
    {
      "epoch": 1.1354070149290036,
      "grad_norm": 1.5,
      "learning_rate": 2.4371693099838865e-05,
      "loss": 1.0455184936523438,
      "num_input_tokens_seen": 9125410176,
      "step": 32090,
      "train_runtime": 312587.1207,
      "train_tokens_per_second": 29193.174
    },
    {
      "epoch": 1.1357608351927326,
      "grad_norm": 1.59375,
      "learning_rate": 2.4368798358805075e-05,
      "loss": 1.055732536315918,
      "num_input_tokens_seen": 9128252480,
      "step": 32100,
      "train_runtime": 312684.294,
      "train_tokens_per_second": 29193.192
    },
    {
      "epoch": 1.1361146554564614,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4365904648992495e-05,
      "loss": 1.0638261795043946,
      "num_input_tokens_seen": 9131125248,
      "step": 32110,
      "train_runtime": 312779.8344,
      "train_tokens_per_second": 29193.459
    },
    {
      "epoch": 1.1364684757201902,
      "grad_norm": 1.578125,
      "learning_rate": 2.436301196978899e-05,
      "loss": 1.0604118347167968,
      "num_input_tokens_seen": 9133973888,
      "step": 32120,
      "train_runtime": 312878.9014,
      "train_tokens_per_second": 29193.32
    },
    {
      "epoch": 1.136822295983919,
      "grad_norm": 1.546875,
      "learning_rate": 2.436012032058296e-05,
      "loss": 1.048573875427246,
      "num_input_tokens_seen": 9136808640,
      "step": 32130,
      "train_runtime": 312974.9982,
      "train_tokens_per_second": 29193.414
    },
    {
      "epoch": 1.1371761162476477,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4357229700763283e-05,
      "loss": 1.048323631286621,
      "num_input_tokens_seen": 9139679488,
      "step": 32140,
      "train_runtime": 313071.3479,
      "train_tokens_per_second": 29193.599
    },
    {
      "epoch": 1.1375299365113765,
      "grad_norm": 1.53125,
      "learning_rate": 2.435434010971937e-05,
      "loss": 1.0625919342041015,
      "num_input_tokens_seen": 9142476992,
      "step": 32150,
      "train_runtime": 313165.4838,
      "train_tokens_per_second": 29193.757
    },
    {
      "epoch": 1.1378837567751052,
      "grad_norm": 1.515625,
      "learning_rate": 2.4351451546841118e-05,
      "loss": 1.050563907623291,
      "num_input_tokens_seen": 9145374272,
      "step": 32160,
      "train_runtime": 313266.4301,
      "train_tokens_per_second": 29193.598
    },
    {
      "epoch": 1.138237577038834,
      "grad_norm": 1.578125,
      "learning_rate": 2.434856401151895e-05,
      "loss": 1.063033390045166,
      "num_input_tokens_seen": 9148207488,
      "step": 32170,
      "train_runtime": 313364.9698,
      "train_tokens_per_second": 29193.459
    },
    {
      "epoch": 1.1385913973025628,
      "grad_norm": 1.5,
      "learning_rate": 2.4345677503143778e-05,
      "loss": 1.0455703735351562,
      "num_input_tokens_seen": 9151062912,
      "step": 32180,
      "train_runtime": 313463.3372,
      "train_tokens_per_second": 29193.407
    },
    {
      "epoch": 1.1389452175662915,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4342792021107033e-05,
      "loss": 1.0594691276550292,
      "num_input_tokens_seen": 9153943872,
      "step": 32190,
      "train_runtime": 313561.4083,
      "train_tokens_per_second": 29193.465
    },
    {
      "epoch": 1.1392990378300203,
      "grad_norm": 1.4765625,
      "learning_rate": 2.433990756480064e-05,
      "loss": 1.0457569122314454,
      "num_input_tokens_seen": 9156787648,
      "step": 32200,
      "train_runtime": 313658.5607,
      "train_tokens_per_second": 29193.489
    },
    {
      "epoch": 1.139652858093749,
      "grad_norm": 1.5625,
      "learning_rate": 2.433702413361703e-05,
      "loss": 1.054711151123047,
      "num_input_tokens_seen": 9159608000,
      "step": 32210,
      "train_runtime": 313754.6676,
      "train_tokens_per_second": 29193.535
    },
    {
      "epoch": 1.1400066783574778,
      "grad_norm": 1.515625,
      "learning_rate": 2.4334141726949147e-05,
      "loss": 1.0411535263061524,
      "num_input_tokens_seen": 9162429568,
      "step": 32220,
      "train_runtime": 313850.3719,
      "train_tokens_per_second": 29193.623
    },
    {
      "epoch": 1.1403604986212066,
      "grad_norm": 1.546875,
      "learning_rate": 2.433126034419042e-05,
      "loss": 1.041477108001709,
      "num_input_tokens_seen": 9165374848,
      "step": 32230,
      "train_runtime": 313952.8415,
      "train_tokens_per_second": 29193.476
    },
    {
      "epoch": 1.1407143188849354,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4328379984734804e-05,
      "loss": 1.0271110534667969,
      "num_input_tokens_seen": 9168251840,
      "step": 32240,
      "train_runtime": 314053.0184,
      "train_tokens_per_second": 29193.325
    },
    {
      "epoch": 1.1410681391486643,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4325500647976738e-05,
      "loss": 1.0625797271728517,
      "num_input_tokens_seen": 9171082368,
      "step": 32250,
      "train_runtime": 314148.7918,
      "train_tokens_per_second": 29193.435
    },
    {
      "epoch": 1.1414219594123929,
      "grad_norm": 1.5625,
      "learning_rate": 2.4322622333311165e-05,
      "loss": 1.0457557678222655,
      "num_input_tokens_seen": 9173994176,
      "step": 32260,
      "train_runtime": 314247.5124,
      "train_tokens_per_second": 29193.53
    },
    {
      "epoch": 1.1417757796761219,
      "grad_norm": 1.484375,
      "learning_rate": 2.4319745040133543e-05,
      "loss": 1.0398128509521485,
      "num_input_tokens_seen": 9176779456,
      "step": 32270,
      "train_runtime": 314343.5929,
      "train_tokens_per_second": 29193.467
    },
    {
      "epoch": 1.1421295999398506,
      "grad_norm": 1.515625,
      "learning_rate": 2.431686876783981e-05,
      "loss": 1.0560508728027345,
      "num_input_tokens_seen": 9179582464,
      "step": 32280,
      "train_runtime": 314440.686,
      "train_tokens_per_second": 29193.367
    },
    {
      "epoch": 1.1424834202035794,
      "grad_norm": 1.5078125,
      "learning_rate": 2.431399351582642e-05,
      "loss": 1.0500800132751464,
      "num_input_tokens_seen": 9182380544,
      "step": 32290,
      "train_runtime": 314536.8008,
      "train_tokens_per_second": 29193.342
    },
    {
      "epoch": 1.1428372404673082,
      "grad_norm": 1.4453125,
      "learning_rate": 2.431111928349032e-05,
      "loss": 1.035835075378418,
      "num_input_tokens_seen": 9185219008,
      "step": 32300,
      "train_runtime": 314635.0955,
      "train_tokens_per_second": 29193.244
    },
    {
      "epoch": 1.143191060731037,
      "grad_norm": 1.5625,
      "learning_rate": 2.4308246070228956e-05,
      "loss": 1.0359127044677734,
      "num_input_tokens_seen": 9188072448,
      "step": 32310,
      "train_runtime": 314733.1277,
      "train_tokens_per_second": 29193.217
    },
    {
      "epoch": 1.1435448809947657,
      "grad_norm": 1.5703125,
      "learning_rate": 2.430537387544027e-05,
      "loss": 1.0430099487304687,
      "num_input_tokens_seen": 9190898560,
      "step": 32320,
      "train_runtime": 314830.6093,
      "train_tokens_per_second": 29193.154
    },
    {
      "epoch": 1.1438987012584945,
      "grad_norm": 1.5859375,
      "learning_rate": 2.4302502698522707e-05,
      "loss": 1.0741775512695313,
      "num_input_tokens_seen": 9193738752,
      "step": 32330,
      "train_runtime": 314928.9703,
      "train_tokens_per_second": 29193.055
    },
    {
      "epoch": 1.1442525215222232,
      "grad_norm": 1.5859375,
      "learning_rate": 2.429963253887521e-05,
      "loss": 1.0395607948303223,
      "num_input_tokens_seen": 9196551616,
      "step": 32340,
      "train_runtime": 315024.8354,
      "train_tokens_per_second": 29193.1
    },
    {
      "epoch": 1.144606341785952,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4296763395897212e-05,
      "loss": 1.032814884185791,
      "num_input_tokens_seen": 9199440448,
      "step": 32350,
      "train_runtime": 315123.9614,
      "train_tokens_per_second": 29193.085
    },
    {
      "epoch": 1.1449601620496808,
      "grad_norm": 1.5390625,
      "learning_rate": 2.4293895268988646e-05,
      "loss": 1.0513600349426269,
      "num_input_tokens_seen": 9202239616,
      "step": 32360,
      "train_runtime": 315218.7343,
      "train_tokens_per_second": 29193.188
    },
    {
      "epoch": 1.1453139823134095,
      "grad_norm": 1.5625,
      "learning_rate": 2.429102815754994e-05,
      "loss": 1.0378034591674805,
      "num_input_tokens_seen": 9205112192,
      "step": 32370,
      "train_runtime": 315319.4919,
      "train_tokens_per_second": 29192.969
    },
    {
      "epoch": 1.1456678025771383,
      "grad_norm": 1.5625,
      "learning_rate": 2.428816206098202e-05,
      "loss": 1.036593246459961,
      "num_input_tokens_seen": 9208002176,
      "step": 32380,
      "train_runtime": 315418.946,
      "train_tokens_per_second": 29192.927
    },
    {
      "epoch": 1.146021622840867,
      "grad_norm": 1.484375,
      "learning_rate": 2.42852969786863e-05,
      "loss": 1.0576810836791992,
      "num_input_tokens_seen": 9210931712,
      "step": 32390,
      "train_runtime": 315520.4814,
      "train_tokens_per_second": 29192.817
    },
    {
      "epoch": 1.1463754431045958,
      "grad_norm": 1.5625,
      "learning_rate": 2.42824329100647e-05,
      "loss": 1.0560544967651366,
      "num_input_tokens_seen": 9213806912,
      "step": 32400,
      "train_runtime": 315618.1033,
      "train_tokens_per_second": 29192.897
    },
    {
      "epoch": 1.1467292633683246,
      "grad_norm": 1.5703125,
      "learning_rate": 2.4279569854519623e-05,
      "loss": 1.0520299911499023,
      "num_input_tokens_seen": 9216752256,
      "step": 32410,
      "train_runtime": 315726.149,
      "train_tokens_per_second": 29192.236
    },
    {
      "epoch": 1.1470830836320536,
      "grad_norm": 1.5234375,
      "learning_rate": 2.427670781145397e-05,
      "loss": 1.0443252563476562,
      "num_input_tokens_seen": 9219542528,
      "step": 32420,
      "train_runtime": 315819.6952,
      "train_tokens_per_second": 29192.424
    },
    {
      "epoch": 1.1474369038957821,
      "grad_norm": 1.53125,
      "learning_rate": 2.4273846780271132e-05,
      "loss": 1.0557531356811523,
      "num_input_tokens_seen": 9222449664,
      "step": 32430,
      "train_runtime": 315922.045,
      "train_tokens_per_second": 29192.169
    },
    {
      "epoch": 1.147790724159511,
      "grad_norm": 1.671875,
      "learning_rate": 2.4270986760374985e-05,
      "loss": 1.0323116302490234,
      "num_input_tokens_seen": 9225259136,
      "step": 32440,
      "train_runtime": 316018.7977,
      "train_tokens_per_second": 29192.121
    },
    {
      "epoch": 1.1481445444232399,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4268127751169922e-05,
      "loss": 1.0515762329101563,
      "num_input_tokens_seen": 9228095808,
      "step": 32450,
      "train_runtime": 316116.1598,
      "train_tokens_per_second": 29192.104
    },
    {
      "epoch": 1.1484983646869686,
      "grad_norm": 1.4921875,
      "learning_rate": 2.4265269752060792e-05,
      "loss": 1.0592628479003907,
      "num_input_tokens_seen": 9230960960,
      "step": 32460,
      "train_runtime": 316215.0486,
      "train_tokens_per_second": 29192.036
    },
    {
      "epoch": 1.1488521849506974,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4262412762452966e-05,
      "loss": 1.037183952331543,
      "num_input_tokens_seen": 9233762240,
      "step": 32470,
      "train_runtime": 316308.8794,
      "train_tokens_per_second": 29192.232
    },
    {
      "epoch": 1.1492060052144262,
      "grad_norm": 1.5703125,
      "learning_rate": 2.4259556781752288e-05,
      "loss": 1.046483039855957,
      "num_input_tokens_seen": 9236616256,
      "step": 32480,
      "train_runtime": 316405.4809,
      "train_tokens_per_second": 29192.34
    },
    {
      "epoch": 1.149559825478155,
      "grad_norm": 1.59375,
      "learning_rate": 2.4256701809365084e-05,
      "loss": 1.0437725067138672,
      "num_input_tokens_seen": 9239468160,
      "step": 32490,
      "train_runtime": 316504.3086,
      "train_tokens_per_second": 29192.235
    },
    {
      "epoch": 1.1499136457418837,
      "grad_norm": 1.53125,
      "learning_rate": 2.4253847844698192e-05,
      "loss": 1.037636947631836,
      "num_input_tokens_seen": 9242305792,
      "step": 32500,
      "train_runtime": 316598.0295,
      "train_tokens_per_second": 29192.556
    },
    {
      "epoch": 1.1502674660056125,
      "grad_norm": 1.53125,
      "learning_rate": 2.4250994887158923e-05,
      "loss": 1.0476924896240234,
      "num_input_tokens_seen": 9245208512,
      "step": 32510,
      "train_runtime": 316699.04,
      "train_tokens_per_second": 29192.411
    },
    {
      "epoch": 1.1506212862693412,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4248142936155078e-05,
      "loss": 1.0538250923156738,
      "num_input_tokens_seen": 9248095040,
      "step": 32520,
      "train_runtime": 316799.6536,
      "train_tokens_per_second": 29192.251
    },
    {
      "epoch": 1.15097510653307,
      "grad_norm": 1.546875,
      "learning_rate": 2.424529199109494e-05,
      "loss": 1.0363734245300293,
      "num_input_tokens_seen": 9250908736,
      "step": 32530,
      "train_runtime": 316893.853,
      "train_tokens_per_second": 29192.452
    },
    {
      "epoch": 1.1513289267967988,
      "grad_norm": 1.4609375,
      "learning_rate": 2.42424420513873e-05,
      "loss": 1.0496133804321288,
      "num_input_tokens_seen": 9253798272,
      "step": 32540,
      "train_runtime": 316993.2595,
      "train_tokens_per_second": 29192.413
    },
    {
      "epoch": 1.1516827470605275,
      "grad_norm": 1.484375,
      "learning_rate": 2.4239593116441407e-05,
      "loss": 1.055825901031494,
      "num_input_tokens_seen": 9256601152,
      "step": 32550,
      "train_runtime": 317089.6771,
      "train_tokens_per_second": 29192.376
    },
    {
      "epoch": 1.1520365673242563,
      "grad_norm": 1.5078125,
      "learning_rate": 2.423674518566701e-05,
      "loss": 1.0431286811828613,
      "num_input_tokens_seen": 9259409984,
      "step": 32560,
      "train_runtime": 317184.306,
      "train_tokens_per_second": 29192.522
    },
    {
      "epoch": 1.152390387587985,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4233898258474347e-05,
      "loss": 1.0527082443237306,
      "num_input_tokens_seen": 9262257600,
      "step": 32570,
      "train_runtime": 317283.6518,
      "train_tokens_per_second": 29192.357
    },
    {
      "epoch": 1.1527442078517138,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4231052334274144e-05,
      "loss": 1.0527776718139648,
      "num_input_tokens_seen": 9265102848,
      "step": 32580,
      "train_runtime": 317379.1271,
      "train_tokens_per_second": 29192.54
    },
    {
      "epoch": 1.1530980281154428,
      "grad_norm": 1.578125,
      "learning_rate": 2.4228207412477587e-05,
      "loss": 1.0542076110839844,
      "num_input_tokens_seen": 9267959744,
      "step": 32590,
      "train_runtime": 317476.6132,
      "train_tokens_per_second": 29192.575
    },
    {
      "epoch": 1.1534518483791714,
      "grad_norm": 1.515625,
      "learning_rate": 2.4225363492496376e-05,
      "loss": 1.0584444046020507,
      "num_input_tokens_seen": 9270835776,
      "step": 32600,
      "train_runtime": 317576.4598,
      "train_tokens_per_second": 29192.453
    },
    {
      "epoch": 1.1538056686429004,
      "grad_norm": 1.5390625,
      "learning_rate": 2.422252057374267e-05,
      "loss": 1.0436830520629883,
      "num_input_tokens_seen": 9273656704,
      "step": 32610,
      "train_runtime": 317671.6494,
      "train_tokens_per_second": 29192.585
    },
    {
      "epoch": 1.1541594889066291,
      "grad_norm": 1.4921875,
      "learning_rate": 2.421967865562914e-05,
      "loss": 1.0404401779174806,
      "num_input_tokens_seen": 9276506176,
      "step": 32620,
      "train_runtime": 317770.5632,
      "train_tokens_per_second": 29192.465
    },
    {
      "epoch": 1.1545133091703579,
      "grad_norm": 1.609375,
      "learning_rate": 2.42168377375689e-05,
      "loss": 1.041179370880127,
      "num_input_tokens_seen": 9279303040,
      "step": 32630,
      "train_runtime": 317866.0312,
      "train_tokens_per_second": 29192.497
    },
    {
      "epoch": 1.1548671294340866,
      "grad_norm": 1.484375,
      "learning_rate": 2.421399781897558e-05,
      "loss": 1.0554627418518066,
      "num_input_tokens_seen": 9282128768,
      "step": 32640,
      "train_runtime": 317961.729,
      "train_tokens_per_second": 29192.597
    },
    {
      "epoch": 1.1552209496978154,
      "grad_norm": 1.5859375,
      "learning_rate": 2.421115889926327e-05,
      "loss": 1.0332971572875977,
      "num_input_tokens_seen": 9284994944,
      "step": 32650,
      "train_runtime": 318057.4652,
      "train_tokens_per_second": 29192.822
    },
    {
      "epoch": 1.1555747699615442,
      "grad_norm": 1.578125,
      "learning_rate": 2.4208320977846555e-05,
      "loss": 1.0540093421936034,
      "num_input_tokens_seen": 9287864128,
      "step": 32660,
      "train_runtime": 318160.2763,
      "train_tokens_per_second": 29192.407
    },
    {
      "epoch": 1.155928590225273,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4205484054140493e-05,
      "loss": 1.0434331893920898,
      "num_input_tokens_seen": 9290722688,
      "step": 32670,
      "train_runtime": 318254.7732,
      "train_tokens_per_second": 29192.721
    },
    {
      "epoch": 1.1562824104890017,
      "grad_norm": 1.5390625,
      "learning_rate": 2.4202648127560616e-05,
      "loss": 1.0429251670837403,
      "num_input_tokens_seen": 9293619328,
      "step": 32680,
      "train_runtime": 318354.5927,
      "train_tokens_per_second": 29192.666
    },
    {
      "epoch": 1.1566362307527305,
      "grad_norm": 1.4921875,
      "learning_rate": 2.4199813197522947e-05,
      "loss": 1.0462181091308593,
      "num_input_tokens_seen": 9296439552,
      "step": 32690,
      "train_runtime": 318449.3515,
      "train_tokens_per_second": 29192.836
    },
    {
      "epoch": 1.1569900510164592,
      "grad_norm": 1.546875,
      "learning_rate": 2.4196979263443985e-05,
      "loss": 1.0607258796691894,
      "num_input_tokens_seen": 9299260096,
      "step": 32700,
      "train_runtime": 318544.6935,
      "train_tokens_per_second": 29192.952
    },
    {
      "epoch": 1.157343871280188,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4194146324740697e-05,
      "loss": 1.0570894241333009,
      "num_input_tokens_seen": 9302155392,
      "step": 32710,
      "train_runtime": 318643.9295,
      "train_tokens_per_second": 29192.947
    },
    {
      "epoch": 1.1576976915439168,
      "grad_norm": 1.53125,
      "learning_rate": 2.4191314380830545e-05,
      "loss": 1.0498271942138673,
      "num_input_tokens_seen": 9305032704,
      "step": 32720,
      "train_runtime": 318744.065,
      "train_tokens_per_second": 29192.803
    },
    {
      "epoch": 1.1580515118076455,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4188483431131453e-05,
      "loss": 1.03955135345459,
      "num_input_tokens_seen": 9307922176,
      "step": 32730,
      "train_runtime": 318844.0745,
      "train_tokens_per_second": 29192.709
    },
    {
      "epoch": 1.1584053320713743,
      "grad_norm": 1.5625,
      "learning_rate": 2.4185653475061826e-05,
      "loss": 1.0597930908203126,
      "num_input_tokens_seen": 9310772928,
      "step": 32740,
      "train_runtime": 318942.0228,
      "train_tokens_per_second": 29192.682
    },
    {
      "epoch": 1.158759152335103,
      "grad_norm": 1.53125,
      "learning_rate": 2.418282451204055e-05,
      "loss": 1.0491201400756835,
      "num_input_tokens_seen": 9313617920,
      "step": 32750,
      "train_runtime": 319038.0671,
      "train_tokens_per_second": 29192.811
    },
    {
      "epoch": 1.159112972598832,
      "grad_norm": 1.5703125,
      "learning_rate": 2.417999654148698e-05,
      "loss": 1.0376638412475585,
      "num_input_tokens_seen": 9316380864,
      "step": 32760,
      "train_runtime": 319132.1817,
      "train_tokens_per_second": 29192.859
    },
    {
      "epoch": 1.1594667928625608,
      "grad_norm": 1.4921875,
      "learning_rate": 2.4177169562820957e-05,
      "loss": 1.0466375350952148,
      "num_input_tokens_seen": 9319236608,
      "step": 32770,
      "train_runtime": 319228.6595,
      "train_tokens_per_second": 29192.982
    },
    {
      "epoch": 1.1598206131262896,
      "grad_norm": 1.5625,
      "learning_rate": 2.417434357546278e-05,
      "loss": 1.048301601409912,
      "num_input_tokens_seen": 9322090112,
      "step": 32780,
      "train_runtime": 319327.5124,
      "train_tokens_per_second": 29192.881
    },
    {
      "epoch": 1.1601744333900184,
      "grad_norm": 1.53125,
      "learning_rate": 2.417151857883324e-05,
      "loss": 1.0443024635314941,
      "num_input_tokens_seen": 9324975552,
      "step": 32790,
      "train_runtime": 319428.1631,
      "train_tokens_per_second": 29192.716
    },
    {
      "epoch": 1.1605282536537471,
      "grad_norm": 1.53125,
      "learning_rate": 2.416869457235358e-05,
      "loss": 1.0508749961853028,
      "num_input_tokens_seen": 9327805440,
      "step": 32800,
      "train_runtime": 319527.3024,
      "train_tokens_per_second": 29192.515
    },
    {
      "epoch": 1.1608820739174759,
      "grad_norm": 1.5078125,
      "learning_rate": 2.416587155544554e-05,
      "loss": 1.042680549621582,
      "num_input_tokens_seen": 9330690368,
      "step": 32810,
      "train_runtime": 319629.8267,
      "train_tokens_per_second": 29192.177
    },
    {
      "epoch": 1.1612358941812047,
      "grad_norm": 1.46875,
      "learning_rate": 2.416304952753132e-05,
      "loss": 1.0420875549316406,
      "num_input_tokens_seen": 9333535360,
      "step": 32820,
      "train_runtime": 319729.4394,
      "train_tokens_per_second": 29191.98
    },
    {
      "epoch": 1.1615897144449334,
      "grad_norm": 1.53125,
      "learning_rate": 2.4160228488033597e-05,
      "loss": 1.0510334014892577,
      "num_input_tokens_seen": 9336407552,
      "step": 32830,
      "train_runtime": 319827.0853,
      "train_tokens_per_second": 29192.048
    },
    {
      "epoch": 1.1619435347086622,
      "grad_norm": 1.546875,
      "learning_rate": 2.415740843637551e-05,
      "loss": 1.0462615966796875,
      "num_input_tokens_seen": 9339243968,
      "step": 32840,
      "train_runtime": 319923.506,
      "train_tokens_per_second": 29192.116
    },
    {
      "epoch": 1.162297354972391,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4154589371980672e-05,
      "loss": 1.0432231903076172,
      "num_input_tokens_seen": 9342061376,
      "step": 32850,
      "train_runtime": 320020.392,
      "train_tokens_per_second": 29192.082
    },
    {
      "epoch": 1.1626511752361197,
      "grad_norm": 1.4765625,
      "learning_rate": 2.415177129427319e-05,
      "loss": 1.0435205459594727,
      "num_input_tokens_seen": 9344861312,
      "step": 32860,
      "train_runtime": 320114.5634,
      "train_tokens_per_second": 29192.24
    },
    {
      "epoch": 1.1630049954998485,
      "grad_norm": 1.5234375,
      "learning_rate": 2.414895420267761e-05,
      "loss": 1.037504291534424,
      "num_input_tokens_seen": 9347685952,
      "step": 32870,
      "train_runtime": 320211.7764,
      "train_tokens_per_second": 29192.199
    },
    {
      "epoch": 1.1633588157635772,
      "grad_norm": 1.5078125,
      "learning_rate": 2.414613809661895e-05,
      "loss": 1.037369728088379,
      "num_input_tokens_seen": 9350535936,
      "step": 32880,
      "train_runtime": 320306.1323,
      "train_tokens_per_second": 29192.497
    },
    {
      "epoch": 1.163712636027306,
      "grad_norm": 1.59375,
      "learning_rate": 2.4143322975522726e-05,
      "loss": 1.0578983306884766,
      "num_input_tokens_seen": 9353344832,
      "step": 32890,
      "train_runtime": 320402.3921,
      "train_tokens_per_second": 29192.494
    },
    {
      "epoch": 1.1640664562910348,
      "grad_norm": 1.5234375,
      "learning_rate": 2.414050883881489e-05,
      "loss": 1.0586021423339844,
      "num_input_tokens_seen": 9356229248,
      "step": 32900,
      "train_runtime": 320501.8902,
      "train_tokens_per_second": 29192.431
    },
    {
      "epoch": 1.1644202765547635,
      "grad_norm": 1.5390625,
      "learning_rate": 2.413769568592188e-05,
      "loss": 1.0394105911254883,
      "num_input_tokens_seen": 9359088832,
      "step": 32910,
      "train_runtime": 320599.3888,
      "train_tokens_per_second": 29192.472
    },
    {
      "epoch": 1.1647740968184923,
      "grad_norm": 1.53125,
      "learning_rate": 2.41348835162706e-05,
      "loss": 1.0404560089111328,
      "num_input_tokens_seen": 9361896832,
      "step": 32920,
      "train_runtime": 320690.9863,
      "train_tokens_per_second": 29192.89
    },
    {
      "epoch": 1.1651279170822213,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4132072329288414e-05,
      "loss": 1.0524593353271485,
      "num_input_tokens_seen": 9364762048,
      "step": 32930,
      "train_runtime": 320789.2124,
      "train_tokens_per_second": 29192.883
    },
    {
      "epoch": 1.16548173734595,
      "grad_norm": 1.484375,
      "learning_rate": 2.4129262124403165e-05,
      "loss": 1.0528087615966797,
      "num_input_tokens_seen": 9367664576,
      "step": 32940,
      "train_runtime": 320892.2813,
      "train_tokens_per_second": 29192.552
    },
    {
      "epoch": 1.1658355576096788,
      "grad_norm": 1.5703125,
      "learning_rate": 2.4126452901043155e-05,
      "loss": 1.0578031539916992,
      "num_input_tokens_seen": 9370459584,
      "step": 32950,
      "train_runtime": 320988.6864,
      "train_tokens_per_second": 29192.492
    },
    {
      "epoch": 1.1661893778734076,
      "grad_norm": 1.5234375,
      "learning_rate": 2.412364465863714e-05,
      "loss": 1.0421407699584961,
      "num_input_tokens_seen": 9373308352,
      "step": 32960,
      "train_runtime": 321087.833,
      "train_tokens_per_second": 29192.35
    },
    {
      "epoch": 1.1665431981371364,
      "grad_norm": 1.546875,
      "learning_rate": 2.4120837396614367e-05,
      "loss": 1.0504817008972167,
      "num_input_tokens_seen": 9376113856,
      "step": 32970,
      "train_runtime": 321181.8857,
      "train_tokens_per_second": 29192.536
    },
    {
      "epoch": 1.1668970184008651,
      "grad_norm": 1.53125,
      "learning_rate": 2.4118031114404525e-05,
      "loss": 1.0418380737304687,
      "num_input_tokens_seen": 9378983360,
      "step": 32980,
      "train_runtime": 321279.8609,
      "train_tokens_per_second": 29192.565
    },
    {
      "epoch": 1.167250838664594,
      "grad_norm": 1.5234375,
      "learning_rate": 2.411522581143778e-05,
      "loss": 1.0419570922851562,
      "num_input_tokens_seen": 9381851328,
      "step": 32990,
      "train_runtime": 321378.0665,
      "train_tokens_per_second": 29192.569
    },
    {
      "epoch": 1.1676046589283227,
      "grad_norm": 1.515625,
      "learning_rate": 2.4112421487144762e-05,
      "loss": 1.0477673530578613,
      "num_input_tokens_seen": 9384704960,
      "step": 33000,
      "train_runtime": 321476.0676,
      "train_tokens_per_second": 29192.546
    },
    {
      "epoch": 1.1679584791920514,
      "grad_norm": 1.5390625,
      "learning_rate": 2.410961814095655e-05,
      "loss": 1.0445474624633788,
      "num_input_tokens_seen": 9387591232,
      "step": 33010,
      "train_runtime": 321575.4434,
      "train_tokens_per_second": 29192.5
    },
    {
      "epoch": 1.1683122994557802,
      "grad_norm": 1.4765625,
      "learning_rate": 2.410681577230471e-05,
      "loss": 1.0470449447631835,
      "num_input_tokens_seen": 9390438848,
      "step": 33020,
      "train_runtime": 321674.6138,
      "train_tokens_per_second": 29192.353
    },
    {
      "epoch": 1.168666119719509,
      "grad_norm": 1.546875,
      "learning_rate": 2.410401438062125e-05,
      "loss": 1.0504799842834474,
      "num_input_tokens_seen": 9393268608,
      "step": 33030,
      "train_runtime": 321771.5331,
      "train_tokens_per_second": 29192.354
    },
    {
      "epoch": 1.1690199399832377,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4101213965338647e-05,
      "loss": 1.052176284790039,
      "num_input_tokens_seen": 9396069120,
      "step": 33040,
      "train_runtime": 321865.3779,
      "train_tokens_per_second": 29192.544
    },
    {
      "epoch": 1.1693737602469665,
      "grad_norm": 1.5,
      "learning_rate": 2.4098414525889836e-05,
      "loss": 1.0376056671142577,
      "num_input_tokens_seen": 9398898688,
      "step": 33050,
      "train_runtime": 321962.7058,
      "train_tokens_per_second": 29192.507
    },
    {
      "epoch": 1.1697275805106953,
      "grad_norm": 1.5390625,
      "learning_rate": 2.4095616061708218e-05,
      "loss": 1.0475838661193848,
      "num_input_tokens_seen": 9401752448,
      "step": 33060,
      "train_runtime": 322059.1035,
      "train_tokens_per_second": 29192.631
    },
    {
      "epoch": 1.170081400774424,
      "grad_norm": 1.59375,
      "learning_rate": 2.4092818572227663e-05,
      "loss": 1.049431610107422,
      "num_input_tokens_seen": 9404559936,
      "step": 33070,
      "train_runtime": 322157.2328,
      "train_tokens_per_second": 29192.453
    },
    {
      "epoch": 1.1704352210381528,
      "grad_norm": 1.46875,
      "learning_rate": 2.4090022056882475e-05,
      "loss": 1.0546879768371582,
      "num_input_tokens_seen": 9407359360,
      "step": 33080,
      "train_runtime": 322253.326,
      "train_tokens_per_second": 29192.435
    },
    {
      "epoch": 1.1707890413018816,
      "grad_norm": 1.5859375,
      "learning_rate": 2.408722651510744e-05,
      "loss": 1.056777286529541,
      "num_input_tokens_seen": 9410227264,
      "step": 33090,
      "train_runtime": 322354.4818,
      "train_tokens_per_second": 29192.171
    },
    {
      "epoch": 1.1711428615656105,
      "grad_norm": 1.5390625,
      "learning_rate": 2.40844319463378e-05,
      "loss": 1.061662769317627,
      "num_input_tokens_seen": 9413071936,
      "step": 33100,
      "train_runtime": 322453.3029,
      "train_tokens_per_second": 29192.047
    },
    {
      "epoch": 1.1714966818293393,
      "grad_norm": 1.5859375,
      "learning_rate": 2.4081638350009247e-05,
      "loss": 1.047011947631836,
      "num_input_tokens_seen": 9415914944,
      "step": 33110,
      "train_runtime": 322548.9801,
      "train_tokens_per_second": 29192.202
    },
    {
      "epoch": 1.171850502093068,
      "grad_norm": 1.578125,
      "learning_rate": 2.407884572555794e-05,
      "loss": 1.0410253524780273,
      "num_input_tokens_seen": 9418758016,
      "step": 33120,
      "train_runtime": 322647.6684,
      "train_tokens_per_second": 29192.085
    },
    {
      "epoch": 1.1722043223567968,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4076054072420486e-05,
      "loss": 1.045882511138916,
      "num_input_tokens_seen": 9421605568,
      "step": 33130,
      "train_runtime": 322744.6669,
      "train_tokens_per_second": 29192.134
    },
    {
      "epoch": 1.1725581426205256,
      "grad_norm": 1.515625,
      "learning_rate": 2.4073263390033957e-05,
      "loss": 1.044580078125,
      "num_input_tokens_seen": 9424470656,
      "step": 33140,
      "train_runtime": 322841.5336,
      "train_tokens_per_second": 29192.25
    },
    {
      "epoch": 1.1729119628842544,
      "grad_norm": 1.6015625,
      "learning_rate": 2.407047367783588e-05,
      "loss": 1.0418977737426758,
      "num_input_tokens_seen": 9427328064,
      "step": 33150,
      "train_runtime": 322939.5539,
      "train_tokens_per_second": 29192.237
    },
    {
      "epoch": 1.1732657831479831,
      "grad_norm": 1.53125,
      "learning_rate": 2.406768493526424e-05,
      "loss": 1.0422359466552735,
      "num_input_tokens_seen": 9430267776,
      "step": 33160,
      "train_runtime": 323041.8965,
      "train_tokens_per_second": 29192.089
    },
    {
      "epoch": 1.173619603411712,
      "grad_norm": 1.484375,
      "learning_rate": 2.4064897161757468e-05,
      "loss": 1.0466090202331544,
      "num_input_tokens_seen": 9433076864,
      "step": 33170,
      "train_runtime": 323134.5161,
      "train_tokens_per_second": 29192.415
    },
    {
      "epoch": 1.1739734236754407,
      "grad_norm": 1.484375,
      "learning_rate": 2.4062110356754464e-05,
      "loss": 1.0432160377502442,
      "num_input_tokens_seen": 9435879104,
      "step": 33180,
      "train_runtime": 323229.2541,
      "train_tokens_per_second": 29192.528
    },
    {
      "epoch": 1.1743272439391694,
      "grad_norm": 1.5,
      "learning_rate": 2.4059324519694572e-05,
      "loss": 1.041322898864746,
      "num_input_tokens_seen": 9438735936,
      "step": 33190,
      "train_runtime": 323325.9152,
      "train_tokens_per_second": 29192.637
    },
    {
      "epoch": 1.1746810642028982,
      "grad_norm": 1.53125,
      "learning_rate": 2.40565396500176e-05,
      "loss": 1.0426311492919922,
      "num_input_tokens_seen": 9441674880,
      "step": 33200,
      "train_runtime": 323428.9636,
      "train_tokens_per_second": 29192.422
    },
    {
      "epoch": 1.175034884466627,
      "grad_norm": 1.515625,
      "learning_rate": 2.40537557471638e-05,
      "loss": 1.0483665466308594,
      "num_input_tokens_seen": 9444507392,
      "step": 33210,
      "train_runtime": 323526.1822,
      "train_tokens_per_second": 29192.405
    },
    {
      "epoch": 1.1753887047303557,
      "grad_norm": 1.609375,
      "learning_rate": 2.4050972810573875e-05,
      "loss": 1.054740810394287,
      "num_input_tokens_seen": 9447403584,
      "step": 33220,
      "train_runtime": 323628.1224,
      "train_tokens_per_second": 29192.159
    },
    {
      "epoch": 1.1757425249940845,
      "grad_norm": 1.5234375,
      "learning_rate": 2.4048190839689003e-05,
      "loss": 1.0511341094970703,
      "num_input_tokens_seen": 9450276032,
      "step": 33230,
      "train_runtime": 323725.6822,
      "train_tokens_per_second": 29192.235
    },
    {
      "epoch": 1.1760963452578133,
      "grad_norm": 1.5625,
      "learning_rate": 2.404540983395078e-05,
      "loss": 1.061384677886963,
      "num_input_tokens_seen": 9453128704,
      "step": 33240,
      "train_runtime": 323822.7719,
      "train_tokens_per_second": 29192.291
    },
    {
      "epoch": 1.1764501655215422,
      "grad_norm": 1.546875,
      "learning_rate": 2.404262979280129e-05,
      "loss": 1.0401178359985352,
      "num_input_tokens_seen": 9455938816,
      "step": 33250,
      "train_runtime": 323919.1172,
      "train_tokens_per_second": 29192.284
    },
    {
      "epoch": 1.1768039857852708,
      "grad_norm": 1.5625,
      "learning_rate": 2.403985071568304e-05,
      "loss": 1.0605267524719237,
      "num_input_tokens_seen": 9458846912,
      "step": 33260,
      "train_runtime": 324021.0063,
      "train_tokens_per_second": 29192.079
    },
    {
      "epoch": 1.1771578060489998,
      "grad_norm": 1.515625,
      "learning_rate": 2.4037072602039002e-05,
      "loss": 1.038251781463623,
      "num_input_tokens_seen": 9461655808,
      "step": 33270,
      "train_runtime": 324117.2406,
      "train_tokens_per_second": 29192.078
    },
    {
      "epoch": 1.1775116263127285,
      "grad_norm": 1.53125,
      "learning_rate": 2.4034295451312596e-05,
      "loss": 1.038266944885254,
      "num_input_tokens_seen": 9464510336,
      "step": 33280,
      "train_runtime": 324214.811,
      "train_tokens_per_second": 29192.097
    },
    {
      "epoch": 1.1778654465764573,
      "grad_norm": 1.4765625,
      "learning_rate": 2.403151926294769e-05,
      "loss": 1.0397583961486816,
      "num_input_tokens_seen": 9467379904,
      "step": 33290,
      "train_runtime": 324311.7911,
      "train_tokens_per_second": 29192.216
    },
    {
      "epoch": 1.178219266840186,
      "grad_norm": 1.5625,
      "learning_rate": 2.4028744036388606e-05,
      "loss": 1.0602401733398437,
      "num_input_tokens_seen": 9470173248,
      "step": 33300,
      "train_runtime": 324405.4836,
      "train_tokens_per_second": 29192.396
    },
    {
      "epoch": 1.1785730871039148,
      "grad_norm": 1.5078125,
      "learning_rate": 2.4025969771080115e-05,
      "loss": 1.051076889038086,
      "num_input_tokens_seen": 9473054848,
      "step": 33310,
      "train_runtime": 324505.9537,
      "train_tokens_per_second": 29192.237
    },
    {
      "epoch": 1.1789269073676436,
      "grad_norm": 1.5390625,
      "learning_rate": 2.402319646646742e-05,
      "loss": 1.0372862815856934,
      "num_input_tokens_seen": 9475877696,
      "step": 33320,
      "train_runtime": 324601.8597,
      "train_tokens_per_second": 29192.309
    },
    {
      "epoch": 1.1792807276313724,
      "grad_norm": 1.5625,
      "learning_rate": 2.40204241219962e-05,
      "loss": 1.0379487991333007,
      "num_input_tokens_seen": 9478680000,
      "step": 33330,
      "train_runtime": 324695.7327,
      "train_tokens_per_second": 29192.499
    },
    {
      "epoch": 1.1796345478951011,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4017652737112568e-05,
      "loss": 1.0590753555297852,
      "num_input_tokens_seen": 9481559616,
      "step": 33340,
      "train_runtime": 324795.5859,
      "train_tokens_per_second": 29192.391
    },
    {
      "epoch": 1.17998836815883,
      "grad_norm": 1.5546875,
      "learning_rate": 2.4014882311263073e-05,
      "loss": 1.0555908203125,
      "num_input_tokens_seen": 9484425536,
      "step": 33350,
      "train_runtime": 324895.0845,
      "train_tokens_per_second": 29192.272
    },
    {
      "epoch": 1.1803421884225587,
      "grad_norm": 1.5859375,
      "learning_rate": 2.4012112843894734e-05,
      "loss": 1.065989112854004,
      "num_input_tokens_seen": 9487289024,
      "step": 33360,
      "train_runtime": 324993.0493,
      "train_tokens_per_second": 29192.283
    },
    {
      "epoch": 1.1806960086862874,
      "grad_norm": 1.5703125,
      "learning_rate": 2.400934433445499e-05,
      "loss": 1.0564004898071289,
      "num_input_tokens_seen": 9490138112,
      "step": 33370,
      "train_runtime": 325089.9557,
      "train_tokens_per_second": 29192.345
    },
    {
      "epoch": 1.1810498289500162,
      "grad_norm": 1.609375,
      "learning_rate": 2.4006576782391752e-05,
      "loss": 1.0383302688598632,
      "num_input_tokens_seen": 9492945728,
      "step": 33380,
      "train_runtime": 325183.3903,
      "train_tokens_per_second": 29192.591
    },
    {
      "epoch": 1.181403649213745,
      "grad_norm": 1.4921875,
      "learning_rate": 2.400381018715336e-05,
      "loss": 1.044392204284668,
      "num_input_tokens_seen": 9495778368,
      "step": 33390,
      "train_runtime": 325279.0154,
      "train_tokens_per_second": 29192.717
    },
    {
      "epoch": 1.1817574694774737,
      "grad_norm": 1.5234375,
      "learning_rate": 2.40010445481886e-05,
      "loss": 1.0480578422546387,
      "num_input_tokens_seen": 9498635840,
      "step": 33400,
      "train_runtime": 325376.9453,
      "train_tokens_per_second": 29192.713
    },
    {
      "epoch": 1.1821112897412025,
      "grad_norm": 1.6015625,
      "learning_rate": 2.399827986494671e-05,
      "loss": 1.0429742813110352,
      "num_input_tokens_seen": 9501464128,
      "step": 33410,
      "train_runtime": 325471.5144,
      "train_tokens_per_second": 29192.921
    },
    {
      "epoch": 1.1824651100049315,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3995516136877368e-05,
      "loss": 1.0429563522338867,
      "num_input_tokens_seen": 9504287872,
      "step": 33420,
      "train_runtime": 325566.4248,
      "train_tokens_per_second": 29193.084
    },
    {
      "epoch": 1.18281893026866,
      "grad_norm": 1.5703125,
      "learning_rate": 2.3992753363430694e-05,
      "loss": 1.049850082397461,
      "num_input_tokens_seen": 9507071424,
      "step": 33430,
      "train_runtime": 325659.1939,
      "train_tokens_per_second": 29193.315
    },
    {
      "epoch": 1.183172750532389,
      "grad_norm": 1.4921875,
      "learning_rate": 2.3989991544057252e-05,
      "loss": 1.0475232124328613,
      "num_input_tokens_seen": 9509908096,
      "step": 33440,
      "train_runtime": 325753.2426,
      "train_tokens_per_second": 29193.595
    },
    {
      "epoch": 1.1835265707961178,
      "grad_norm": 1.515625,
      "learning_rate": 2.3987230678208044e-05,
      "loss": 1.0477602005004882,
      "num_input_tokens_seen": 9512749568,
      "step": 33450,
      "train_runtime": 325850.2626,
      "train_tokens_per_second": 29193.623
    },
    {
      "epoch": 1.1838803910598465,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3984470765334527e-05,
      "loss": 1.0219315528869628,
      "num_input_tokens_seen": 9515630272,
      "step": 33460,
      "train_runtime": 325950.0632,
      "train_tokens_per_second": 29193.522
    },
    {
      "epoch": 1.1842342113235753,
      "grad_norm": 1.5390625,
      "learning_rate": 2.398171180488859e-05,
      "loss": 1.0671205520629883,
      "num_input_tokens_seen": 9518488256,
      "step": 33470,
      "train_runtime": 326049.4024,
      "train_tokens_per_second": 29193.393
    },
    {
      "epoch": 1.184588031587304,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3978953796322565e-05,
      "loss": 1.0545934677124023,
      "num_input_tokens_seen": 9521336768,
      "step": 33480,
      "train_runtime": 326147.5605,
      "train_tokens_per_second": 29193.34
    },
    {
      "epoch": 1.1849418518510328,
      "grad_norm": 1.546875,
      "learning_rate": 2.3976196739089218e-05,
      "loss": 1.0505924224853516,
      "num_input_tokens_seen": 9524181696,
      "step": 33490,
      "train_runtime": 326246.1526,
      "train_tokens_per_second": 29193.238
    },
    {
      "epoch": 1.1852956721147616,
      "grad_norm": 1.53125,
      "learning_rate": 2.397344063264177e-05,
      "loss": 1.0547115325927734,
      "num_input_tokens_seen": 9527027968,
      "step": 33500,
      "train_runtime": 326344.0253,
      "train_tokens_per_second": 29193.205
    },
    {
      "epoch": 1.1856494923784904,
      "grad_norm": 1.6015625,
      "learning_rate": 2.3970685476433867e-05,
      "loss": 1.0371501922607422,
      "num_input_tokens_seen": 9529800960,
      "step": 33510,
      "train_runtime": 326436.5714,
      "train_tokens_per_second": 29193.423
    },
    {
      "epoch": 1.1860033126422191,
      "grad_norm": 1.5078125,
      "learning_rate": 2.396793126991961e-05,
      "loss": 1.048904800415039,
      "num_input_tokens_seen": 9532695360,
      "step": 33520,
      "train_runtime": 326537.0411,
      "train_tokens_per_second": 29193.305
    },
    {
      "epoch": 1.186357132905948,
      "grad_norm": 1.5546875,
      "learning_rate": 2.396517801255352e-05,
      "loss": 1.0349294662475585,
      "num_input_tokens_seen": 9535536512,
      "step": 33530,
      "train_runtime": 326633.3564,
      "train_tokens_per_second": 29193.395
    },
    {
      "epoch": 1.1867109531696767,
      "grad_norm": 1.53125,
      "learning_rate": 2.3962425703790577e-05,
      "loss": 1.0505560874938964,
      "num_input_tokens_seen": 9538409280,
      "step": 33540,
      "train_runtime": 326730.6436,
      "train_tokens_per_second": 29193.495
    },
    {
      "epoch": 1.1870647734334054,
      "grad_norm": 1.5234375,
      "learning_rate": 2.395967434308618e-05,
      "loss": 1.040046501159668,
      "num_input_tokens_seen": 9541272320,
      "step": 33550,
      "train_runtime": 326827.5586,
      "train_tokens_per_second": 29193.598
    },
    {
      "epoch": 1.1874185936971342,
      "grad_norm": 1.546875,
      "learning_rate": 2.395692392989619e-05,
      "loss": 1.0439062118530273,
      "num_input_tokens_seen": 9544064320,
      "step": 33560,
      "train_runtime": 326922.8118,
      "train_tokens_per_second": 29193.632
    },
    {
      "epoch": 1.187772413960863,
      "grad_norm": 1.59375,
      "learning_rate": 2.3954174463676868e-05,
      "loss": 1.0508002281188964,
      "num_input_tokens_seen": 9546886080,
      "step": 33570,
      "train_runtime": 327020.9833,
      "train_tokens_per_second": 29193.497
    },
    {
      "epoch": 1.1881262342245917,
      "grad_norm": 1.484375,
      "learning_rate": 2.395142594388495e-05,
      "loss": 1.0431723594665527,
      "num_input_tokens_seen": 9549726336,
      "step": 33580,
      "train_runtime": 327115.9228,
      "train_tokens_per_second": 29193.707
    },
    {
      "epoch": 1.1884800544883207,
      "grad_norm": 1.546875,
      "learning_rate": 2.3948678369977577e-05,
      "loss": 1.0509469985961915,
      "num_input_tokens_seen": 9552575936,
      "step": 33590,
      "train_runtime": 327214.1763,
      "train_tokens_per_second": 29193.649
    },
    {
      "epoch": 1.1888338747520493,
      "grad_norm": 1.5078125,
      "learning_rate": 2.3945931741412362e-05,
      "loss": 1.0630071640014649,
      "num_input_tokens_seen": 9555412928,
      "step": 33600,
      "train_runtime": 327312.2521,
      "train_tokens_per_second": 29193.569
    },
    {
      "epoch": 1.1891876950157783,
      "grad_norm": 1.578125,
      "learning_rate": 2.394318605764731e-05,
      "loss": 1.0547370910644531,
      "num_input_tokens_seen": 9558267328,
      "step": 33610,
      "train_runtime": 327410.8004,
      "train_tokens_per_second": 29193.5
    },
    {
      "epoch": 1.189541515279507,
      "grad_norm": 1.53125,
      "learning_rate": 2.3940441318140893e-05,
      "loss": 1.0457229614257812,
      "num_input_tokens_seen": 9561136192,
      "step": 33620,
      "train_runtime": 327510.9084,
      "train_tokens_per_second": 29193.337
    },
    {
      "epoch": 1.1898953355432358,
      "grad_norm": 1.515625,
      "learning_rate": 2.3937697522352013e-05,
      "loss": 1.0475440979003907,
      "num_input_tokens_seen": 9564021504,
      "step": 33630,
      "train_runtime": 327612.2147,
      "train_tokens_per_second": 29193.116
    },
    {
      "epoch": 1.1902491558069646,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3934954669739984e-05,
      "loss": 1.0458075523376464,
      "num_input_tokens_seen": 9566898944,
      "step": 33640,
      "train_runtime": 327712.4137,
      "train_tokens_per_second": 29192.971
    },
    {
      "epoch": 1.1906029760706933,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3932212759764587e-05,
      "loss": 1.0440912246704102,
      "num_input_tokens_seen": 9569715968,
      "step": 33650,
      "train_runtime": 327807.2247,
      "train_tokens_per_second": 29193.121
    },
    {
      "epoch": 1.190956796334422,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3929471791886006e-05,
      "loss": 1.043346118927002,
      "num_input_tokens_seen": 9572561984,
      "step": 33660,
      "train_runtime": 327905.26,
      "train_tokens_per_second": 29193.072
    },
    {
      "epoch": 1.1913106165981509,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3926731765564872e-05,
      "loss": 1.0547977447509767,
      "num_input_tokens_seen": 9575418432,
      "step": 33670,
      "train_runtime": 328004.6034,
      "train_tokens_per_second": 29192.939
    },
    {
      "epoch": 1.1916644368618796,
      "grad_norm": 1.4609375,
      "learning_rate": 2.3923992680262258e-05,
      "loss": 1.064218521118164,
      "num_input_tokens_seen": 9578277056,
      "step": 33680,
      "train_runtime": 328103.3864,
      "train_tokens_per_second": 29192.863
    },
    {
      "epoch": 1.1920182571256084,
      "grad_norm": 1.546875,
      "learning_rate": 2.3921254535439645e-05,
      "loss": 1.0444768905639648,
      "num_input_tokens_seen": 9581097408,
      "step": 33690,
      "train_runtime": 328197.9103,
      "train_tokens_per_second": 29193.048
    },
    {
      "epoch": 1.1923720773893371,
      "grad_norm": 1.5,
      "learning_rate": 2.391851733055896e-05,
      "loss": 1.0381498336791992,
      "num_input_tokens_seen": 9583940608,
      "step": 33700,
      "train_runtime": 328296.3157,
      "train_tokens_per_second": 29192.958
    },
    {
      "epoch": 1.192725897653066,
      "grad_norm": 1.59375,
      "learning_rate": 2.3915781065082566e-05,
      "loss": 1.036000633239746,
      "num_input_tokens_seen": 9586741440,
      "step": 33710,
      "train_runtime": 328389.3966,
      "train_tokens_per_second": 29193.213
    },
    {
      "epoch": 1.1930797179167947,
      "grad_norm": 1.515625,
      "learning_rate": 2.391304573847324e-05,
      "loss": 1.0411787033081055,
      "num_input_tokens_seen": 9589594176,
      "step": 33720,
      "train_runtime": 328487.2119,
      "train_tokens_per_second": 29193.204
    },
    {
      "epoch": 1.1934335381805234,
      "grad_norm": 1.484375,
      "learning_rate": 2.3910311350194205e-05,
      "loss": 1.0503351211547851,
      "num_input_tokens_seen": 9592433600,
      "step": 33730,
      "train_runtime": 328585.6562,
      "train_tokens_per_second": 29193.099
    },
    {
      "epoch": 1.1937873584442522,
      "grad_norm": 1.5234375,
      "learning_rate": 2.39075778997091e-05,
      "loss": 1.046432876586914,
      "num_input_tokens_seen": 9595292032,
      "step": 33740,
      "train_runtime": 328682.0973,
      "train_tokens_per_second": 29193.23
    },
    {
      "epoch": 1.194141178707981,
      "grad_norm": 1.5546875,
      "learning_rate": 2.390484538648201e-05,
      "loss": 1.0224493026733399,
      "num_input_tokens_seen": 9598131072,
      "step": 33750,
      "train_runtime": 328779.624,
      "train_tokens_per_second": 29193.205
    },
    {
      "epoch": 1.19449499897171,
      "grad_norm": 1.5,
      "learning_rate": 2.3902113809977433e-05,
      "loss": 1.0521577835083007,
      "num_input_tokens_seen": 9601000896,
      "step": 33760,
      "train_runtime": 328879.157,
      "train_tokens_per_second": 29193.096
    },
    {
      "epoch": 1.1948488192354387,
      "grad_norm": 1.59375,
      "learning_rate": 2.3899383169660297e-05,
      "loss": 1.0468816757202148,
      "num_input_tokens_seen": 9603877632,
      "step": 33770,
      "train_runtime": 328977.2869,
      "train_tokens_per_second": 29193.133
    },
    {
      "epoch": 1.1952026394991675,
      "grad_norm": 1.515625,
      "learning_rate": 2.3896653464995968e-05,
      "loss": 1.0482233047485352,
      "num_input_tokens_seen": 9606686784,
      "step": 33780,
      "train_runtime": 329069.321,
      "train_tokens_per_second": 29193.505
    },
    {
      "epoch": 1.1955564597628963,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3893924695450232e-05,
      "loss": 1.0563304901123047,
      "num_input_tokens_seen": 9609472128,
      "step": 33790,
      "train_runtime": 329164.4276,
      "train_tokens_per_second": 29193.532
    },
    {
      "epoch": 1.195910280026625,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3891196860489297e-05,
      "loss": 1.0408262252807616,
      "num_input_tokens_seen": 9612316480,
      "step": 33800,
      "train_runtime": 329259.2368,
      "train_tokens_per_second": 29193.764
    },
    {
      "epoch": 1.1962641002903538,
      "grad_norm": 1.6640625,
      "learning_rate": 2.3888469959579813e-05,
      "loss": 1.0598806381225585,
      "num_input_tokens_seen": 9615149248,
      "step": 33810,
      "train_runtime": 329355.2162,
      "train_tokens_per_second": 29193.857
    },
    {
      "epoch": 1.1966179205540826,
      "grad_norm": 1.5546875,
      "learning_rate": 2.388574399218883e-05,
      "loss": 1.058354377746582,
      "num_input_tokens_seen": 9618028096,
      "step": 33820,
      "train_runtime": 329453.7767,
      "train_tokens_per_second": 29193.862
    },
    {
      "epoch": 1.1969717408178113,
      "grad_norm": 1.546875,
      "learning_rate": 2.3883018957783854e-05,
      "loss": 1.040217399597168,
      "num_input_tokens_seen": 9620882880,
      "step": 33830,
      "train_runtime": 329553.3623,
      "train_tokens_per_second": 29193.703
    },
    {
      "epoch": 1.19732556108154,
      "grad_norm": 1.6875,
      "learning_rate": 2.3880294855832802e-05,
      "loss": 1.0426069259643556,
      "num_input_tokens_seen": 9623748352,
      "step": 33840,
      "train_runtime": 329652.7941,
      "train_tokens_per_second": 29193.59
    },
    {
      "epoch": 1.1976793813452689,
      "grad_norm": 1.5625,
      "learning_rate": 2.387757168580401e-05,
      "loss": 1.0550308227539062,
      "num_input_tokens_seen": 9626657536,
      "step": 33850,
      "train_runtime": 329755.987,
      "train_tokens_per_second": 29193.276
    },
    {
      "epoch": 1.1980332016089976,
      "grad_norm": 1.546875,
      "learning_rate": 2.387484944716625e-05,
      "loss": 1.043130874633789,
      "num_input_tokens_seen": 9629524736,
      "step": 33860,
      "train_runtime": 329853.5976,
      "train_tokens_per_second": 29193.329
    },
    {
      "epoch": 1.1983870218727264,
      "grad_norm": 1.546875,
      "learning_rate": 2.387212813938871e-05,
      "loss": 1.0468429565429687,
      "num_input_tokens_seen": 9632425664,
      "step": 33870,
      "train_runtime": 329953.3697,
      "train_tokens_per_second": 29193.294
    },
    {
      "epoch": 1.1987408421364552,
      "grad_norm": 1.4921875,
      "learning_rate": 2.3869407761940998e-05,
      "loss": 1.053243637084961,
      "num_input_tokens_seen": 9635266304,
      "step": 33880,
      "train_runtime": 330049.0357,
      "train_tokens_per_second": 29193.439
    },
    {
      "epoch": 1.199094662400184,
      "grad_norm": 1.546875,
      "learning_rate": 2.3866688314293158e-05,
      "loss": 1.0454025268554688,
      "num_input_tokens_seen": 9638069824,
      "step": 33890,
      "train_runtime": 330142.561,
      "train_tokens_per_second": 29193.66
    },
    {
      "epoch": 1.1994484826639127,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3863969795915643e-05,
      "loss": 1.035744857788086,
      "num_input_tokens_seen": 9640934016,
      "step": 33900,
      "train_runtime": 330241.7728,
      "train_tokens_per_second": 29193.563
    },
    {
      "epoch": 1.1998023029276415,
      "grad_norm": 1.4921875,
      "learning_rate": 2.3861252206279336e-05,
      "loss": 1.0417303085327148,
      "num_input_tokens_seen": 9643792320,
      "step": 33910,
      "train_runtime": 330339.474,
      "train_tokens_per_second": 29193.581
    },
    {
      "epoch": 1.2001561231913702,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3858535544855544e-05,
      "loss": 1.0378734588623046,
      "num_input_tokens_seen": 9646623424,
      "step": 33920,
      "train_runtime": 330436.9759,
      "train_tokens_per_second": 29193.535
    },
    {
      "epoch": 1.2005099434550992,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3855819811115987e-05,
      "loss": 1.0467106819152832,
      "num_input_tokens_seen": 9649468544,
      "step": 33930,
      "train_runtime": 330531.9018,
      "train_tokens_per_second": 29193.759
    },
    {
      "epoch": 1.200863763718828,
      "grad_norm": 1.546875,
      "learning_rate": 2.385310500453281e-05,
      "loss": 1.060910129547119,
      "num_input_tokens_seen": 9652265792,
      "step": 33940,
      "train_runtime": 330629.3641,
      "train_tokens_per_second": 29193.613
    },
    {
      "epoch": 1.2012175839825567,
      "grad_norm": 1.4609375,
      "learning_rate": 2.3850391124578573e-05,
      "loss": 1.044386100769043,
      "num_input_tokens_seen": 9655174464,
      "step": 33950,
      "train_runtime": 330728.319,
      "train_tokens_per_second": 29193.673
    },
    {
      "epoch": 1.2015714042462855,
      "grad_norm": 1.5625,
      "learning_rate": 2.3847678170726275e-05,
      "loss": 1.0542067527770995,
      "num_input_tokens_seen": 9658019648,
      "step": 33960,
      "train_runtime": 330824.7249,
      "train_tokens_per_second": 29193.766
    },
    {
      "epoch": 1.2019252245100143,
      "grad_norm": 1.46875,
      "learning_rate": 2.3844966142449312e-05,
      "loss": 1.0422491073608398,
      "num_input_tokens_seen": 9660785984,
      "step": 33970,
      "train_runtime": 330917.4801,
      "train_tokens_per_second": 29193.943
    },
    {
      "epoch": 1.202279044773743,
      "grad_norm": 1.5,
      "learning_rate": 2.384225503922151e-05,
      "loss": 1.0566981315612793,
      "num_input_tokens_seen": 9663646464,
      "step": 33980,
      "train_runtime": 331015.419,
      "train_tokens_per_second": 29193.947
    },
    {
      "epoch": 1.2026328650374718,
      "grad_norm": 1.546875,
      "learning_rate": 2.3839544860517103e-05,
      "loss": 1.0488442420959472,
      "num_input_tokens_seen": 9666481280,
      "step": 33990,
      "train_runtime": 331112.3314,
      "train_tokens_per_second": 29193.963
    },
    {
      "epoch": 1.2029866853012006,
      "grad_norm": 1.578125,
      "learning_rate": 2.3836835605810765e-05,
      "loss": 1.0545729637145995,
      "num_input_tokens_seen": 9669289216,
      "step": 34000,
      "train_runtime": 331208.864,
      "train_tokens_per_second": 29193.932
    },
    {
      "epoch": 1.2033405055649293,
      "grad_norm": 1.4765625,
      "learning_rate": 2.3834127274577564e-05,
      "loss": 1.0484482765197753,
      "num_input_tokens_seen": 9672089728,
      "step": 34010,
      "train_runtime": 331302.0211,
      "train_tokens_per_second": 29194.177
    },
    {
      "epoch": 1.203694325828658,
      "grad_norm": 1.453125,
      "learning_rate": 2.3831419866293005e-05,
      "loss": 1.0506410598754883,
      "num_input_tokens_seen": 9674950272,
      "step": 34020,
      "train_runtime": 331399.6784,
      "train_tokens_per_second": 29194.205
    },
    {
      "epoch": 1.2040481460923869,
      "grad_norm": 1.609375,
      "learning_rate": 2.3828713380432997e-05,
      "loss": 1.046139907836914,
      "num_input_tokens_seen": 9677808448,
      "step": 34030,
      "train_runtime": 331498.9901,
      "train_tokens_per_second": 29194.081
    },
    {
      "epoch": 1.2044019663561156,
      "grad_norm": 1.5703125,
      "learning_rate": 2.3826007816473866e-05,
      "loss": 1.0537068367004394,
      "num_input_tokens_seen": 9680670464,
      "step": 34040,
      "train_runtime": 331599.0792,
      "train_tokens_per_second": 29193.9
    },
    {
      "epoch": 1.2047557866198444,
      "grad_norm": 1.6015625,
      "learning_rate": 2.3823303173892365e-05,
      "loss": 1.0411800384521483,
      "num_input_tokens_seen": 9683566656,
      "step": 34050,
      "train_runtime": 331699.4626,
      "train_tokens_per_second": 29193.797
    },
    {
      "epoch": 1.2051096068835732,
      "grad_norm": 1.5546875,
      "learning_rate": 2.382059945216565e-05,
      "loss": 1.04378662109375,
      "num_input_tokens_seen": 9686376832,
      "step": 34060,
      "train_runtime": 331795.0556,
      "train_tokens_per_second": 29193.855
    },
    {
      "epoch": 1.205463427147302,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3817896650771297e-05,
      "loss": 1.050713348388672,
      "num_input_tokens_seen": 9689171392,
      "step": 34070,
      "train_runtime": 331889.7397,
      "train_tokens_per_second": 29193.947
    },
    {
      "epoch": 1.205817247411031,
      "grad_norm": 1.5625,
      "learning_rate": 2.38151947691873e-05,
      "loss": 1.0462234497070313,
      "num_input_tokens_seen": 9692054784,
      "step": 34080,
      "train_runtime": 331987.3721,
      "train_tokens_per_second": 29194.047
    },
    {
      "epoch": 1.2061710676747595,
      "grad_norm": 1.5703125,
      "learning_rate": 2.3812493806892066e-05,
      "loss": 1.0486331939697267,
      "num_input_tokens_seen": 9694916736,
      "step": 34090,
      "train_runtime": 332085.5828,
      "train_tokens_per_second": 29194.031
    },
    {
      "epoch": 1.2065248879384884,
      "grad_norm": 1.5625,
      "learning_rate": 2.3809793763364406e-05,
      "loss": 1.0600369453430176,
      "num_input_tokens_seen": 9697683648,
      "step": 34100,
      "train_runtime": 332176.848,
      "train_tokens_per_second": 29194.339
    },
    {
      "epoch": 1.2068787082022172,
      "grad_norm": 1.46875,
      "learning_rate": 2.3807094638083575e-05,
      "loss": 1.037211799621582,
      "num_input_tokens_seen": 9700529856,
      "step": 34110,
      "train_runtime": 332276.0993,
      "train_tokens_per_second": 29194.185
    },
    {
      "epoch": 1.207232528465946,
      "grad_norm": 1.6484375,
      "learning_rate": 2.3804396430529196e-05,
      "loss": 1.0461621284484863,
      "num_input_tokens_seen": 9703314112,
      "step": 34120,
      "train_runtime": 332366.0512,
      "train_tokens_per_second": 29194.661
    },
    {
      "epoch": 1.2075863487296747,
      "grad_norm": 1.5390625,
      "learning_rate": 2.380169914018134e-05,
      "loss": 1.0311933517456056,
      "num_input_tokens_seen": 9706138560,
      "step": 34130,
      "train_runtime": 332461.4211,
      "train_tokens_per_second": 29194.782
    },
    {
      "epoch": 1.2079401689934035,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3799002766520473e-05,
      "loss": 1.060780906677246,
      "num_input_tokens_seen": 9708987008,
      "step": 34140,
      "train_runtime": 332557.2372,
      "train_tokens_per_second": 29194.935
    },
    {
      "epoch": 1.2082939892571323,
      "grad_norm": 1.484375,
      "learning_rate": 2.379630730902749e-05,
      "loss": 1.0365987777709962,
      "num_input_tokens_seen": 9711806784,
      "step": 34150,
      "train_runtime": 332655.1865,
      "train_tokens_per_second": 29194.815
    },
    {
      "epoch": 1.208647809520861,
      "grad_norm": 1.5,
      "learning_rate": 2.3793612767183668e-05,
      "loss": 1.0393068313598632,
      "num_input_tokens_seen": 9714642624,
      "step": 34160,
      "train_runtime": 332750.8299,
      "train_tokens_per_second": 29194.946
    },
    {
      "epoch": 1.2090016297845898,
      "grad_norm": 1.5078125,
      "learning_rate": 2.3790919140470726e-05,
      "loss": 1.0314400672912598,
      "num_input_tokens_seen": 9717448704,
      "step": 34170,
      "train_runtime": 332844.9093,
      "train_tokens_per_second": 29195.125
    },
    {
      "epoch": 1.2093554500483186,
      "grad_norm": 1.53125,
      "learning_rate": 2.3788226428370774e-05,
      "loss": 1.0527836799621582,
      "num_input_tokens_seen": 9720349056,
      "step": 34180,
      "train_runtime": 332945.3032,
      "train_tokens_per_second": 29195.033
    },
    {
      "epoch": 1.2097092703120473,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3785534630366355e-05,
      "loss": 1.0481876373291015,
      "num_input_tokens_seen": 9723184512,
      "step": 34190,
      "train_runtime": 333040.602,
      "train_tokens_per_second": 29195.193
    },
    {
      "epoch": 1.210063090575776,
      "grad_norm": 1.5,
      "learning_rate": 2.378284374594038e-05,
      "loss": 1.0418161392211913,
      "num_input_tokens_seen": 9726001856,
      "step": 34200,
      "train_runtime": 333135.529,
      "train_tokens_per_second": 29195.33
    },
    {
      "epoch": 1.2104169108395049,
      "grad_norm": 1.515625,
      "learning_rate": 2.3780153774576215e-05,
      "loss": 1.0523595809936523,
      "num_input_tokens_seen": 9728830720,
      "step": 34210,
      "train_runtime": 333228.02,
      "train_tokens_per_second": 29195.716
    },
    {
      "epoch": 1.2107707311032336,
      "grad_norm": 1.515625,
      "learning_rate": 2.3777464715757608e-05,
      "loss": 1.055731201171875,
      "num_input_tokens_seen": 9731613632,
      "step": 34220,
      "train_runtime": 333322.0123,
      "train_tokens_per_second": 29195.832
    },
    {
      "epoch": 1.2111245513669624,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3774776568968716e-05,
      "loss": 1.0354131698608398,
      "num_input_tokens_seen": 9734413504,
      "step": 34230,
      "train_runtime": 333417.2383,
      "train_tokens_per_second": 29195.891
    },
    {
      "epoch": 1.2114783716306912,
      "grad_norm": 1.4921875,
      "learning_rate": 2.377208933369413e-05,
      "loss": 1.0449087142944335,
      "num_input_tokens_seen": 9737197568,
      "step": 34240,
      "train_runtime": 333511.4503,
      "train_tokens_per_second": 29195.992
    },
    {
      "epoch": 1.2118321918944202,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3769403009418808e-05,
      "loss": 1.0436315536499023,
      "num_input_tokens_seen": 9740070400,
      "step": 34250,
      "train_runtime": 333611.026,
      "train_tokens_per_second": 29195.889
    },
    {
      "epoch": 1.2121860121581487,
      "grad_norm": 1.6015625,
      "learning_rate": 2.3766717595628145e-05,
      "loss": 1.0474668502807618,
      "num_input_tokens_seen": 9742856832,
      "step": 34260,
      "train_runtime": 333706.7563,
      "train_tokens_per_second": 29195.863
    },
    {
      "epoch": 1.2125398324218777,
      "grad_norm": 1.5859375,
      "learning_rate": 2.376403309180794e-05,
      "loss": 1.0425712585449218,
      "num_input_tokens_seen": 9745677376,
      "step": 34270,
      "train_runtime": 333801.7284,
      "train_tokens_per_second": 29196.006
    },
    {
      "epoch": 1.2128936526856064,
      "grad_norm": 1.5,
      "learning_rate": 2.3761349497444387e-05,
      "loss": 1.0322124481201171,
      "num_input_tokens_seen": 9748482816,
      "step": 34280,
      "train_runtime": 333896.7713,
      "train_tokens_per_second": 29196.098
    },
    {
      "epoch": 1.2132474729493352,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3758666812024093e-05,
      "loss": 1.0425240516662597,
      "num_input_tokens_seen": 9751270656,
      "step": 34290,
      "train_runtime": 333988.7433,
      "train_tokens_per_second": 29196.405
    },
    {
      "epoch": 1.213601293213064,
      "grad_norm": 1.5859375,
      "learning_rate": 2.3755985035034072e-05,
      "loss": 1.04284610748291,
      "num_input_tokens_seen": 9754067584,
      "step": 34300,
      "train_runtime": 334080.6888,
      "train_tokens_per_second": 29196.742
    },
    {
      "epoch": 1.2139551134767927,
      "grad_norm": 1.5703125,
      "learning_rate": 2.3753304165961733e-05,
      "loss": 1.0384990692138671,
      "num_input_tokens_seen": 9756888192,
      "step": 34310,
      "train_runtime": 334178.4749,
      "train_tokens_per_second": 29196.639
    },
    {
      "epoch": 1.2143089337405215,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3750624204294913e-05,
      "loss": 1.0635936737060547,
      "num_input_tokens_seen": 9759714240,
      "step": 34320,
      "train_runtime": 334276.0436,
      "train_tokens_per_second": 29196.571
    },
    {
      "epoch": 1.2146627540042503,
      "grad_norm": 1.515625,
      "learning_rate": 2.3747945149521823e-05,
      "loss": 1.0456748962402345,
      "num_input_tokens_seen": 9762568192,
      "step": 34330,
      "train_runtime": 334372.9975,
      "train_tokens_per_second": 29196.64
    },
    {
      "epoch": 1.215016574267979,
      "grad_norm": 1.5703125,
      "learning_rate": 2.374526700113111e-05,
      "loss": 1.0479136466979981,
      "num_input_tokens_seen": 9765409216,
      "step": 34340,
      "train_runtime": 334470.4833,
      "train_tokens_per_second": 29196.625
    },
    {
      "epoch": 1.2153703945317078,
      "grad_norm": 1.484375,
      "learning_rate": 2.374258975861179e-05,
      "loss": 1.0496002197265626,
      "num_input_tokens_seen": 9768232192,
      "step": 34350,
      "train_runtime": 334563.6324,
      "train_tokens_per_second": 29196.934
    },
    {
      "epoch": 1.2157242147954366,
      "grad_norm": 1.484375,
      "learning_rate": 2.3739913421453303e-05,
      "loss": 1.050473117828369,
      "num_input_tokens_seen": 9771099072,
      "step": 34360,
      "train_runtime": 334660.7355,
      "train_tokens_per_second": 29197.029
    },
    {
      "epoch": 1.2160780350591653,
      "grad_norm": 1.515625,
      "learning_rate": 2.37372379891455e-05,
      "loss": 1.0564163208007813,
      "num_input_tokens_seen": 9773976512,
      "step": 34370,
      "train_runtime": 334763.2741,
      "train_tokens_per_second": 29196.681
    },
    {
      "epoch": 1.216431855322894,
      "grad_norm": 1.546875,
      "learning_rate": 2.3734563461178615e-05,
      "loss": 1.0495073318481445,
      "num_input_tokens_seen": 9776848576,
      "step": 34380,
      "train_runtime": 334866.4662,
      "train_tokens_per_second": 29196.26
    },
    {
      "epoch": 1.2167856755866229,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3731889837043294e-05,
      "loss": 1.0609786987304688,
      "num_input_tokens_seen": 9779679808,
      "step": 34390,
      "train_runtime": 334964.1719,
      "train_tokens_per_second": 29196.197
    },
    {
      "epoch": 1.2171394958503516,
      "grad_norm": 1.609375,
      "learning_rate": 2.3729217116230586e-05,
      "loss": 1.0397884368896484,
      "num_input_tokens_seen": 9782507968,
      "step": 34400,
      "train_runtime": 335059.0737,
      "train_tokens_per_second": 29196.368
    },
    {
      "epoch": 1.2174933161140804,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3726545298231932e-05,
      "loss": 1.0494367599487304,
      "num_input_tokens_seen": 9785377728,
      "step": 34410,
      "train_runtime": 335159.231,
      "train_tokens_per_second": 29196.205
    },
    {
      "epoch": 1.2178471363778094,
      "grad_norm": 1.4609375,
      "learning_rate": 2.3723874382539182e-05,
      "loss": 1.0413763046264648,
      "num_input_tokens_seen": 9788234496,
      "step": 34420,
      "train_runtime": 335255.7368,
      "train_tokens_per_second": 29196.322
    },
    {
      "epoch": 1.218200956641538,
      "grad_norm": 1.5625,
      "learning_rate": 2.3721204368644585e-05,
      "loss": 1.0489760398864747,
      "num_input_tokens_seen": 9791061312,
      "step": 34430,
      "train_runtime": 335353.8568,
      "train_tokens_per_second": 29196.209
    },
    {
      "epoch": 1.218554776905267,
      "grad_norm": 1.5234375,
      "learning_rate": 2.371853525604079e-05,
      "loss": 1.0461412429809571,
      "num_input_tokens_seen": 9793960000,
      "step": 34440,
      "train_runtime": 335455.0368,
      "train_tokens_per_second": 29196.044
    },
    {
      "epoch": 1.2189085971689957,
      "grad_norm": 1.5,
      "learning_rate": 2.371586704422084e-05,
      "loss": 1.0428497314453125,
      "num_input_tokens_seen": 9796792448,
      "step": 34450,
      "train_runtime": 335553.8787,
      "train_tokens_per_second": 29195.885
    },
    {
      "epoch": 1.2192624174327245,
      "grad_norm": 1.5703125,
      "learning_rate": 2.3713199732678183e-05,
      "loss": 1.0350074768066406,
      "num_input_tokens_seen": 9799579008,
      "step": 34460,
      "train_runtime": 335647.6225,
      "train_tokens_per_second": 29196.033
    },
    {
      "epoch": 1.2196162376964532,
      "grad_norm": 1.515625,
      "learning_rate": 2.371053332090666e-05,
      "loss": 1.0548994064331054,
      "num_input_tokens_seen": 9802470912,
      "step": 34470,
      "train_runtime": 335747.8525,
      "train_tokens_per_second": 29195.93
    },
    {
      "epoch": 1.219970057960182,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3707867808400527e-05,
      "loss": 1.049970817565918,
      "num_input_tokens_seen": 9805286080,
      "step": 34480,
      "train_runtime": 335842.2428,
      "train_tokens_per_second": 29196.107
    },
    {
      "epoch": 1.2203238782239108,
      "grad_norm": 1.5859375,
      "learning_rate": 2.370520319465442e-05,
      "loss": 1.0524154663085938,
      "num_input_tokens_seen": 9808145920,
      "step": 34490,
      "train_runtime": 335940.4863,
      "train_tokens_per_second": 29196.082
    },
    {
      "epoch": 1.2206776984876395,
      "grad_norm": 1.515625,
      "learning_rate": 2.370253947916337e-05,
      "loss": 1.0469653129577636,
      "num_input_tokens_seen": 9810961536,
      "step": 34500,
      "train_runtime": 336040.5577,
      "train_tokens_per_second": 29195.766
    },
    {
      "epoch": 1.2210315187513683,
      "grad_norm": 1.453125,
      "learning_rate": 2.369987666142282e-05,
      "loss": 1.041243553161621,
      "num_input_tokens_seen": 9813835456,
      "step": 34510,
      "train_runtime": 336139.8792,
      "train_tokens_per_second": 29195.689
    },
    {
      "epoch": 1.221385339015097,
      "grad_norm": 1.5859375,
      "learning_rate": 2.36972147409286e-05,
      "loss": 1.0468326568603517,
      "num_input_tokens_seen": 9816663680,
      "step": 34520,
      "train_runtime": 336235.8066,
      "train_tokens_per_second": 29195.771
    },
    {
      "epoch": 1.2217391592788258,
      "grad_norm": 1.546875,
      "learning_rate": 2.3694553717176945e-05,
      "loss": 1.0382003784179688,
      "num_input_tokens_seen": 9819550080,
      "step": 34530,
      "train_runtime": 336337.7512,
      "train_tokens_per_second": 29195.504
    },
    {
      "epoch": 1.2220929795425546,
      "grad_norm": 1.5,
      "learning_rate": 2.369189358966447e-05,
      "loss": 1.0429319381713866,
      "num_input_tokens_seen": 9822366336,
      "step": 34540,
      "train_runtime": 336433.0374,
      "train_tokens_per_second": 29195.606
    },
    {
      "epoch": 1.2224467998062833,
      "grad_norm": 1.5,
      "learning_rate": 2.3689234357888205e-05,
      "loss": 1.061648178100586,
      "num_input_tokens_seen": 9825223488,
      "step": 34550,
      "train_runtime": 336530.9466,
      "train_tokens_per_second": 29195.602
    },
    {
      "epoch": 1.2228006200700121,
      "grad_norm": 1.5390625,
      "learning_rate": 2.368657602134556e-05,
      "loss": 1.0461462020874024,
      "num_input_tokens_seen": 9828064064,
      "step": 34560,
      "train_runtime": 336625.9852,
      "train_tokens_per_second": 29195.797
    },
    {
      "epoch": 1.2231544403337409,
      "grad_norm": 1.515625,
      "learning_rate": 2.3683918579534347e-05,
      "loss": 1.0494418144226074,
      "num_input_tokens_seen": 9830890048,
      "step": 34570,
      "train_runtime": 336723.6422,
      "train_tokens_per_second": 29195.723
    },
    {
      "epoch": 1.2235082605974696,
      "grad_norm": 1.515625,
      "learning_rate": 2.368126203195277e-05,
      "loss": 1.0356925964355468,
      "num_input_tokens_seen": 9833731520,
      "step": 34580,
      "train_runtime": 336821.0276,
      "train_tokens_per_second": 29195.717
    },
    {
      "epoch": 1.2238620808611986,
      "grad_norm": 1.4765625,
      "learning_rate": 2.3678606378099428e-05,
      "loss": 1.0287874221801758,
      "num_input_tokens_seen": 9836584960,
      "step": 34590,
      "train_runtime": 336921.9186,
      "train_tokens_per_second": 29195.444
    },
    {
      "epoch": 1.2242159011249274,
      "grad_norm": 1.53125,
      "learning_rate": 2.3675951617473315e-05,
      "loss": 1.051163387298584,
      "num_input_tokens_seen": 9839436032,
      "step": 34600,
      "train_runtime": 337019.341,
      "train_tokens_per_second": 29195.464
    },
    {
      "epoch": 1.2245697213886562,
      "grad_norm": 1.4921875,
      "learning_rate": 2.3673297749573805e-05,
      "loss": 1.038036823272705,
      "num_input_tokens_seen": 9842257152,
      "step": 34610,
      "train_runtime": 337114.8367,
      "train_tokens_per_second": 29195.562
    },
    {
      "epoch": 1.224923541652385,
      "grad_norm": 1.5078125,
      "learning_rate": 2.3670644773900692e-05,
      "loss": 1.048990821838379,
      "num_input_tokens_seen": 9845072128,
      "step": 34620,
      "train_runtime": 337210.96,
      "train_tokens_per_second": 29195.588
    },
    {
      "epoch": 1.2252773619161137,
      "grad_norm": 1.59375,
      "learning_rate": 2.3667992689954135e-05,
      "loss": 1.0513466835021972,
      "num_input_tokens_seen": 9847911808,
      "step": 34630,
      "train_runtime": 337307.029,
      "train_tokens_per_second": 29195.691
    },
    {
      "epoch": 1.2256311821798425,
      "grad_norm": 1.53125,
      "learning_rate": 2.3665341497234704e-05,
      "loss": 1.0437068939208984,
      "num_input_tokens_seen": 9850730624,
      "step": 34640,
      "train_runtime": 337404.3879,
      "train_tokens_per_second": 29195.621
    },
    {
      "epoch": 1.2259850024435712,
      "grad_norm": 1.53125,
      "learning_rate": 2.3662691195243346e-05,
      "loss": 1.04404296875,
      "num_input_tokens_seen": 9853537408,
      "step": 34650,
      "train_runtime": 337498.7256,
      "train_tokens_per_second": 29195.777
    },
    {
      "epoch": 1.2263388227073,
      "grad_norm": 1.515625,
      "learning_rate": 2.3660041783481403e-05,
      "loss": 1.0487115859985352,
      "num_input_tokens_seen": 9856290560,
      "step": 34660,
      "train_runtime": 337588.2097,
      "train_tokens_per_second": 29196.193
    },
    {
      "epoch": 1.2266926429710288,
      "grad_norm": 1.484375,
      "learning_rate": 2.365739326145062e-05,
      "loss": 1.041053009033203,
      "num_input_tokens_seen": 9859116416,
      "step": 34670,
      "train_runtime": 337685.1457,
      "train_tokens_per_second": 29196.18
    },
    {
      "epoch": 1.2270464632347575,
      "grad_norm": 1.6171875,
      "learning_rate": 2.3654745628653117e-05,
      "loss": 1.0450716018676758,
      "num_input_tokens_seen": 9861939776,
      "step": 34680,
      "train_runtime": 337782.3199,
      "train_tokens_per_second": 29196.14
    },
    {
      "epoch": 1.2274002834984863,
      "grad_norm": 1.4765625,
      "learning_rate": 2.3652098884591413e-05,
      "loss": 1.0455732345581055,
      "num_input_tokens_seen": 9864776704,
      "step": 34690,
      "train_runtime": 337879.0092,
      "train_tokens_per_second": 29196.181
    },
    {
      "epoch": 1.227754103762215,
      "grad_norm": 1.546875,
      "learning_rate": 2.3649453028768406e-05,
      "loss": 1.0550278663635253,
      "num_input_tokens_seen": 9867605056,
      "step": 34700,
      "train_runtime": 337973.0465,
      "train_tokens_per_second": 29196.426
    },
    {
      "epoch": 1.2281079240259438,
      "grad_norm": 1.53125,
      "learning_rate": 2.3646808060687397e-05,
      "loss": 1.0549308776855468,
      "num_input_tokens_seen": 9870411776,
      "step": 34710,
      "train_runtime": 338066.6367,
      "train_tokens_per_second": 29196.646
    },
    {
      "epoch": 1.2284617442896726,
      "grad_norm": 1.5625,
      "learning_rate": 2.364416397985207e-05,
      "loss": 1.0530141830444335,
      "num_input_tokens_seen": 9873246208,
      "step": 34720,
      "train_runtime": 338162.2504,
      "train_tokens_per_second": 29196.772
    },
    {
      "epoch": 1.2288155645534014,
      "grad_norm": 1.53125,
      "learning_rate": 2.3641520785766487e-05,
      "loss": 1.0283068656921386,
      "num_input_tokens_seen": 9876161920,
      "step": 34730,
      "train_runtime": 338265.1522,
      "train_tokens_per_second": 29196.51
    },
    {
      "epoch": 1.2291693848171301,
      "grad_norm": 1.5078125,
      "learning_rate": 2.363887847793512e-05,
      "loss": 1.052764892578125,
      "num_input_tokens_seen": 9878980416,
      "step": 34740,
      "train_runtime": 338361.4464,
      "train_tokens_per_second": 29196.531
    },
    {
      "epoch": 1.2295232050808589,
      "grad_norm": 1.5234375,
      "learning_rate": 2.363623705586281e-05,
      "loss": 1.0538837432861328,
      "num_input_tokens_seen": 9881828992,
      "step": 34750,
      "train_runtime": 338460.6894,
      "train_tokens_per_second": 29196.386
    },
    {
      "epoch": 1.2298770253445879,
      "grad_norm": 1.546875,
      "learning_rate": 2.363359651905479e-05,
      "loss": 1.0590595245361327,
      "num_input_tokens_seen": 9884673792,
      "step": 34760,
      "train_runtime": 338557.5671,
      "train_tokens_per_second": 29196.434
    },
    {
      "epoch": 1.2302308456083166,
      "grad_norm": 1.546875,
      "learning_rate": 2.3630956867016688e-05,
      "loss": 1.0451095581054688,
      "num_input_tokens_seen": 9887490688,
      "step": 34770,
      "train_runtime": 338652.4789,
      "train_tokens_per_second": 29196.57
    },
    {
      "epoch": 1.2305846658720454,
      "grad_norm": 1.546875,
      "learning_rate": 2.3628318099254506e-05,
      "loss": 1.0444417953491212,
      "num_input_tokens_seen": 9890319040,
      "step": 34780,
      "train_runtime": 338747.0135,
      "train_tokens_per_second": 29196.771
    },
    {
      "epoch": 1.2309384861357742,
      "grad_norm": 1.46875,
      "learning_rate": 2.3625680215274635e-05,
      "loss": 1.0326299667358398,
      "num_input_tokens_seen": 9893143104,
      "step": 34790,
      "train_runtime": 338845.4517,
      "train_tokens_per_second": 29196.624
    },
    {
      "epoch": 1.231292306399503,
      "grad_norm": 1.5625,
      "learning_rate": 2.362304321458386e-05,
      "loss": 1.0454606056213378,
      "num_input_tokens_seen": 9896034752,
      "step": 34800,
      "train_runtime": 338947.182,
      "train_tokens_per_second": 29196.392
    },
    {
      "epoch": 1.2316461266632317,
      "grad_norm": 1.578125,
      "learning_rate": 2.362040709668934e-05,
      "loss": 1.054949951171875,
      "num_input_tokens_seen": 9898863040,
      "step": 34810,
      "train_runtime": 339044.6517,
      "train_tokens_per_second": 29196.34
    },
    {
      "epoch": 1.2319999469269605,
      "grad_norm": 1.5546875,
      "learning_rate": 2.361777186109863e-05,
      "loss": 1.0335612297058105,
      "num_input_tokens_seen": 9901685696,
      "step": 34820,
      "train_runtime": 339138.9828,
      "train_tokens_per_second": 29196.542
    },
    {
      "epoch": 1.2323537671906892,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3615137507319672e-05,
      "loss": 1.044585609436035,
      "num_input_tokens_seen": 9904598208,
      "step": 34830,
      "train_runtime": 339240.9308,
      "train_tokens_per_second": 29196.354
    },
    {
      "epoch": 1.232707587454418,
      "grad_norm": 1.5546875,
      "learning_rate": 2.361250403486076e-05,
      "loss": 1.04913272857666,
      "num_input_tokens_seen": 9907452864,
      "step": 34840,
      "train_runtime": 339338.5954,
      "train_tokens_per_second": 29196.363
    },
    {
      "epoch": 1.2330614077181468,
      "grad_norm": 1.5625,
      "learning_rate": 2.360987144323062e-05,
      "loss": 1.0436088562011718,
      "num_input_tokens_seen": 9910414720,
      "step": 34850,
      "train_runtime": 339441.2594,
      "train_tokens_per_second": 29196.258
    },
    {
      "epoch": 1.2334152279818755,
      "grad_norm": 1.578125,
      "learning_rate": 2.3607239731938324e-05,
      "loss": 1.0461825370788573,
      "num_input_tokens_seen": 9913257856,
      "step": 34860,
      "train_runtime": 339539.4414,
      "train_tokens_per_second": 29196.189
    },
    {
      "epoch": 1.2337690482456043,
      "grad_norm": 1.609375,
      "learning_rate": 2.3604608900493343e-05,
      "loss": 1.0470144271850585,
      "num_input_tokens_seen": 9916116224,
      "step": 34870,
      "train_runtime": 339638.044,
      "train_tokens_per_second": 29196.129
    },
    {
      "epoch": 1.234122868509333,
      "grad_norm": 1.46875,
      "learning_rate": 2.360197894840553e-05,
      "loss": 1.0448129653930665,
      "num_input_tokens_seen": 9918965312,
      "step": 34880,
      "train_runtime": 339735.0607,
      "train_tokens_per_second": 29196.178
    },
    {
      "epoch": 1.2344766887730618,
      "grad_norm": 1.5625,
      "learning_rate": 2.3599349875185117e-05,
      "loss": 1.0460649490356446,
      "num_input_tokens_seen": 9921834944,
      "step": 34890,
      "train_runtime": 339833.411,
      "train_tokens_per_second": 29196.173
    },
    {
      "epoch": 1.2348305090367906,
      "grad_norm": 1.53125,
      "learning_rate": 2.359672168034272e-05,
      "loss": 1.0505395889282227,
      "num_input_tokens_seen": 9924674240,
      "step": 34900,
      "train_runtime": 339932.6594,
      "train_tokens_per_second": 29196.001
    },
    {
      "epoch": 1.2351843293005194,
      "grad_norm": 1.4765625,
      "learning_rate": 2.3594094363389327e-05,
      "loss": 1.0440752029418945,
      "num_input_tokens_seen": 9927486080,
      "step": 34910,
      "train_runtime": 340026.9274,
      "train_tokens_per_second": 29196.176
    },
    {
      "epoch": 1.2355381495642481,
      "grad_norm": 1.6171875,
      "learning_rate": 2.3591467923836324e-05,
      "loss": 1.0381940841674804,
      "num_input_tokens_seen": 9930325312,
      "step": 34920,
      "train_runtime": 340127.4052,
      "train_tokens_per_second": 29195.899
    },
    {
      "epoch": 1.235891969827977,
      "grad_norm": 1.484375,
      "learning_rate": 2.3588842361195467e-05,
      "loss": 1.0517271041870118,
      "num_input_tokens_seen": 9933175360,
      "step": 34930,
      "train_runtime": 340224.5636,
      "train_tokens_per_second": 29195.938
    },
    {
      "epoch": 1.2362457900917059,
      "grad_norm": 1.4609375,
      "learning_rate": 2.3586217674978893e-05,
      "loss": 1.0489501953125,
      "num_input_tokens_seen": 9936098560,
      "step": 34940,
      "train_runtime": 340326.6596,
      "train_tokens_per_second": 29195.769
    },
    {
      "epoch": 1.2365996103554346,
      "grad_norm": 1.53125,
      "learning_rate": 2.358359386469912e-05,
      "loss": 1.0448589324951172,
      "num_input_tokens_seen": 9938961792,
      "step": 34950,
      "train_runtime": 340424.5394,
      "train_tokens_per_second": 29195.785
    },
    {
      "epoch": 1.2369534306191634,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3580970929869047e-05,
      "loss": 1.0518791198730468,
      "num_input_tokens_seen": 9941761600,
      "step": 34960,
      "train_runtime": 340517.3195,
      "train_tokens_per_second": 29196.053
    },
    {
      "epoch": 1.2373072508828922,
      "grad_norm": 1.609375,
      "learning_rate": 2.3578348870001952e-05,
      "loss": 1.0555269241333007,
      "num_input_tokens_seen": 9944624256,
      "step": 34970,
      "train_runtime": 340616.7984,
      "train_tokens_per_second": 29195.93
    },
    {
      "epoch": 1.237661071146621,
      "grad_norm": 1.6015625,
      "learning_rate": 2.357572768461149e-05,
      "loss": 1.042059326171875,
      "num_input_tokens_seen": 9947495936,
      "step": 34980,
      "train_runtime": 340717.5742,
      "train_tokens_per_second": 29195.723
    },
    {
      "epoch": 1.2380148914103497,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3573107373211687e-05,
      "loss": 1.0555862426757812,
      "num_input_tokens_seen": 9950286144,
      "step": 34990,
      "train_runtime": 340808.4745,
      "train_tokens_per_second": 29196.123
    },
    {
      "epoch": 1.2383687116740785,
      "grad_norm": 1.5,
      "learning_rate": 2.3570487935316964e-05,
      "loss": 1.050098991394043,
      "num_input_tokens_seen": 9953103872,
      "step": 35000,
      "train_runtime": 340906.0818,
      "train_tokens_per_second": 29196.029
    },
    {
      "epoch": 1.2383687116740785,
      "eval_loss": 1.022186517715454,
      "eval_runtime": 8.4373,
      "eval_samples_per_second": 472.662,
      "eval_steps_per_second": 3.793,
      "num_input_tokens_seen": 9953103872,
      "step": 35000
    },
    {
      "epoch": 1.2387225319378072,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3567869370442104e-05,
      "loss": 1.0379037857055664,
      "num_input_tokens_seen": 9955961216,
      "step": 35010,
      "train_runtime": 341033.8247,
      "train_tokens_per_second": 29193.471
    },
    {
      "epoch": 1.239076352201536,
      "grad_norm": 1.5,
      "learning_rate": 2.356525167810228e-05,
      "loss": 1.0494878768920899,
      "num_input_tokens_seen": 9958810304,
      "step": 35020,
      "train_runtime": 341134.6746,
      "train_tokens_per_second": 29193.193
    },
    {
      "epoch": 1.2394301724652648,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3562634857813034e-05,
      "loss": 1.0683238983154297,
      "num_input_tokens_seen": 9961596352,
      "step": 35030,
      "train_runtime": 341229.4685,
      "train_tokens_per_second": 29193.248
    },
    {
      "epoch": 1.2397839927289935,
      "grad_norm": 1.53125,
      "learning_rate": 2.3560018909090288e-05,
      "loss": 1.0537175178527831,
      "num_input_tokens_seen": 9964467392,
      "step": 35040,
      "train_runtime": 341328.333,
      "train_tokens_per_second": 29193.203
    },
    {
      "epoch": 1.2401378129927223,
      "grad_norm": 1.6015625,
      "learning_rate": 2.355740383145033e-05,
      "loss": 1.0476181030273437,
      "num_input_tokens_seen": 9967367488,
      "step": 35050,
      "train_runtime": 341429.2103,
      "train_tokens_per_second": 29193.072
    },
    {
      "epoch": 1.240491633256451,
      "grad_norm": 1.4765625,
      "learning_rate": 2.3554789624409836e-05,
      "loss": 1.063364315032959,
      "num_input_tokens_seen": 9970211264,
      "step": 35060,
      "train_runtime": 341525.4929,
      "train_tokens_per_second": 29193.169
    },
    {
      "epoch": 1.2408454535201798,
      "grad_norm": 1.5234375,
      "learning_rate": 2.355217628748586e-05,
      "loss": 1.0372730255126954,
      "num_input_tokens_seen": 9973072000,
      "step": 35070,
      "train_runtime": 341621.9655,
      "train_tokens_per_second": 29193.298
    },
    {
      "epoch": 1.2411992737839088,
      "grad_norm": 1.6484375,
      "learning_rate": 2.354956382019581e-05,
      "loss": 1.051537322998047,
      "num_input_tokens_seen": 9975927488,
      "step": 35080,
      "train_runtime": 341718.711,
      "train_tokens_per_second": 29193.39
    },
    {
      "epoch": 1.2415530940476374,
      "grad_norm": 1.578125,
      "learning_rate": 2.35469522220575e-05,
      "loss": 1.05850191116333,
      "num_input_tokens_seen": 9978769408,
      "step": 35090,
      "train_runtime": 341812.6127,
      "train_tokens_per_second": 29193.684
    },
    {
      "epoch": 1.2419069143113664,
      "grad_norm": 1.53125,
      "learning_rate": 2.3544341492589096e-05,
      "loss": 1.057568359375,
      "num_input_tokens_seen": 9981646080,
      "step": 35100,
      "train_runtime": 341912.2972,
      "train_tokens_per_second": 29193.586
    },
    {
      "epoch": 1.2422607345750951,
      "grad_norm": 1.5625,
      "learning_rate": 2.3541731631309126e-05,
      "loss": 1.0560384750366212,
      "num_input_tokens_seen": 9984491392,
      "step": 35110,
      "train_runtime": 342010.5964,
      "train_tokens_per_second": 29193.515
    },
    {
      "epoch": 1.2426145548388239,
      "grad_norm": 1.515625,
      "learning_rate": 2.3539122637736537e-05,
      "loss": 1.0476004600524902,
      "num_input_tokens_seen": 9987369216,
      "step": 35120,
      "train_runtime": 342108.8054,
      "train_tokens_per_second": 29193.546
    },
    {
      "epoch": 1.2429683751025526,
      "grad_norm": 1.5234375,
      "learning_rate": 2.35365145113906e-05,
      "loss": 1.0363781929016114,
      "num_input_tokens_seen": 9990212224,
      "step": 35130,
      "train_runtime": 342205.7277,
      "train_tokens_per_second": 29193.586
    },
    {
      "epoch": 1.2433221953662814,
      "grad_norm": 1.6171875,
      "learning_rate": 2.3533907251790983e-05,
      "loss": 1.0540312767028808,
      "num_input_tokens_seen": 9993065216,
      "step": 35140,
      "train_runtime": 342304.8287,
      "train_tokens_per_second": 29193.468
    },
    {
      "epoch": 1.2436760156300102,
      "grad_norm": 1.4921875,
      "learning_rate": 2.3531300858457727e-05,
      "loss": 1.0373088836669921,
      "num_input_tokens_seen": 9995957056,
      "step": 35150,
      "train_runtime": 342407.4004,
      "train_tokens_per_second": 29193.169
    },
    {
      "epoch": 1.244029835893739,
      "grad_norm": 1.546875,
      "learning_rate": 2.352869533091124e-05,
      "loss": 1.050804901123047,
      "num_input_tokens_seen": 9998854080,
      "step": 35160,
      "train_runtime": 342508.3408,
      "train_tokens_per_second": 29193.024
    },
    {
      "epoch": 1.2443836561574677,
      "grad_norm": 1.609375,
      "learning_rate": 2.3526090668672306e-05,
      "loss": 1.0617940902709961,
      "num_input_tokens_seen": 10001740096,
      "step": 35170,
      "train_runtime": 342609.6539,
      "train_tokens_per_second": 29192.815
    },
    {
      "epoch": 1.2447374764211965,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3523486871262068e-05,
      "loss": 1.0579568862915039,
      "num_input_tokens_seen": 10004669440,
      "step": 35180,
      "train_runtime": 342710.4438,
      "train_tokens_per_second": 29192.777
    },
    {
      "epoch": 1.2450912966849252,
      "grad_norm": 1.578125,
      "learning_rate": 2.3520883938202048e-05,
      "loss": 1.0430191993713378,
      "num_input_tokens_seen": 10007498176,
      "step": 35190,
      "train_runtime": 342806.8788,
      "train_tokens_per_second": 29192.816
    },
    {
      "epoch": 1.245445116948654,
      "grad_norm": 1.6484375,
      "learning_rate": 2.3518281869014153e-05,
      "loss": 1.0434306144714356,
      "num_input_tokens_seen": 10010338560,
      "step": 35200,
      "train_runtime": 342902.2307,
      "train_tokens_per_second": 29192.982
    },
    {
      "epoch": 1.2457989372123828,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3515680663220632e-05,
      "loss": 1.056950283050537,
      "num_input_tokens_seen": 10013225984,
      "step": 35210,
      "train_runtime": 343004.834,
      "train_tokens_per_second": 29192.667
    },
    {
      "epoch": 1.2461527574761115,
      "grad_norm": 1.53125,
      "learning_rate": 2.351308032034413e-05,
      "loss": 1.0369938850402831,
      "num_input_tokens_seen": 10016053440,
      "step": 35220,
      "train_runtime": 343101.0257,
      "train_tokens_per_second": 29192.724
    },
    {
      "epoch": 1.2465065777398403,
      "grad_norm": 1.59375,
      "learning_rate": 2.3510480839907635e-05,
      "loss": 1.0479074478149415,
      "num_input_tokens_seen": 10018930112,
      "step": 35230,
      "train_runtime": 343202.489,
      "train_tokens_per_second": 29192.475
    },
    {
      "epoch": 1.246860398003569,
      "grad_norm": 1.578125,
      "learning_rate": 2.350788222143453e-05,
      "loss": 1.0474456787109374,
      "num_input_tokens_seen": 10021760448,
      "step": 35240,
      "train_runtime": 343299.6052,
      "train_tokens_per_second": 29192.461
    },
    {
      "epoch": 1.247214218267298,
      "grad_norm": 1.5,
      "learning_rate": 2.3505284464448558e-05,
      "loss": 1.0391267776489257,
      "num_input_tokens_seen": 10024582720,
      "step": 35250,
      "train_runtime": 343396.3395,
      "train_tokens_per_second": 29192.457
    },
    {
      "epoch": 1.2475680385310266,
      "grad_norm": 1.5625,
      "learning_rate": 2.3502687568473815e-05,
      "loss": 1.060915756225586,
      "num_input_tokens_seen": 10027407872,
      "step": 35260,
      "train_runtime": 343493.3662,
      "train_tokens_per_second": 29192.435
    },
    {
      "epoch": 1.2479218587947556,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3500091533034785e-05,
      "loss": 1.0523077964782714,
      "num_input_tokens_seen": 10030243520,
      "step": 35270,
      "train_runtime": 343590.4599,
      "train_tokens_per_second": 29192.439
    },
    {
      "epoch": 1.2482756790584844,
      "grad_norm": 1.546875,
      "learning_rate": 2.3497496357656313e-05,
      "loss": 1.0498737335205077,
      "num_input_tokens_seen": 10033080960,
      "step": 35280,
      "train_runtime": 343688.3072,
      "train_tokens_per_second": 29192.384
    },
    {
      "epoch": 1.2486294993222131,
      "grad_norm": 1.6015625,
      "learning_rate": 2.3494902041863607e-05,
      "loss": 1.0472888946533203,
      "num_input_tokens_seen": 10035942016,
      "step": 35290,
      "train_runtime": 343785.0122,
      "train_tokens_per_second": 29192.494
    },
    {
      "epoch": 1.2489833195859419,
      "grad_norm": 1.5703125,
      "learning_rate": 2.349230858518225e-05,
      "loss": 1.0496798515319825,
      "num_input_tokens_seen": 10038792768,
      "step": 35300,
      "train_runtime": 343881.9716,
      "train_tokens_per_second": 29192.553
    },
    {
      "epoch": 1.2493371398496707,
      "grad_norm": 1.53125,
      "learning_rate": 2.3489715987138178e-05,
      "loss": 1.0443727493286132,
      "num_input_tokens_seen": 10041574528,
      "step": 35310,
      "train_runtime": 343976.7355,
      "train_tokens_per_second": 29192.598
    },
    {
      "epoch": 1.2496909601133994,
      "grad_norm": 1.515625,
      "learning_rate": 2.348712424725771e-05,
      "loss": 1.051421546936035,
      "num_input_tokens_seen": 10044415808,
      "step": 35320,
      "train_runtime": 344075.6255,
      "train_tokens_per_second": 29192.465
    },
    {
      "epoch": 1.2500447803771282,
      "grad_norm": 1.546875,
      "learning_rate": 2.3484533365067526e-05,
      "loss": 1.0535319328308106,
      "num_input_tokens_seen": 10047284864,
      "step": 35330,
      "train_runtime": 344177.6259,
      "train_tokens_per_second": 29192.15
    },
    {
      "epoch": 1.250398600640857,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3481943340094656e-05,
      "loss": 1.0444052696228028,
      "num_input_tokens_seen": 10050130944,
      "step": 35340,
      "train_runtime": 344273.7368,
      "train_tokens_per_second": 29192.267
    },
    {
      "epoch": 1.2507524209045857,
      "grad_norm": 1.484375,
      "learning_rate": 2.3479354171866517e-05,
      "loss": 1.0486770629882813,
      "num_input_tokens_seen": 10052974080,
      "step": 35350,
      "train_runtime": 344369.9278,
      "train_tokens_per_second": 29192.369
    },
    {
      "epoch": 1.2511062411683145,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3476765859910877e-05,
      "loss": 1.0445372581481933,
      "num_input_tokens_seen": 10055788288,
      "step": 35360,
      "train_runtime": 344464.3196,
      "train_tokens_per_second": 29192.54
    },
    {
      "epoch": 1.2514600614320432,
      "grad_norm": 1.5078125,
      "learning_rate": 2.347417840375587e-05,
      "loss": 1.046097183227539,
      "num_input_tokens_seen": 10058621248,
      "step": 35370,
      "train_runtime": 344562.4226,
      "train_tokens_per_second": 29192.45
    },
    {
      "epoch": 1.251813881695772,
      "grad_norm": 1.6015625,
      "learning_rate": 2.347159180293e-05,
      "loss": 1.0351703643798829,
      "num_input_tokens_seen": 10061456640,
      "step": 35380,
      "train_runtime": 344658.0097,
      "train_tokens_per_second": 29192.58
    },
    {
      "epoch": 1.2521677019595008,
      "grad_norm": 1.6015625,
      "learning_rate": 2.346900605696213e-05,
      "loss": 1.0489368438720703,
      "num_input_tokens_seen": 10064292736,
      "step": 35390,
      "train_runtime": 344752.9148,
      "train_tokens_per_second": 29192.771
    },
    {
      "epoch": 1.2525215222232295,
      "grad_norm": 1.5078125,
      "learning_rate": 2.3466421165381486e-05,
      "loss": 1.0433351516723632,
      "num_input_tokens_seen": 10067125568,
      "step": 35400,
      "train_runtime": 344849.2694,
      "train_tokens_per_second": 29192.828
    },
    {
      "epoch": 1.2528753424869583,
      "grad_norm": 1.5859375,
      "learning_rate": 2.346383712771766e-05,
      "loss": 1.0557622909545898,
      "num_input_tokens_seen": 10069973440,
      "step": 35410,
      "train_runtime": 344945.6496,
      "train_tokens_per_second": 29192.928
    },
    {
      "epoch": 1.2532291627506873,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3461253943500598e-05,
      "loss": 1.0483509063720704,
      "num_input_tokens_seen": 10072860544,
      "step": 35420,
      "train_runtime": 345044.9417,
      "train_tokens_per_second": 29192.894
    },
    {
      "epoch": 1.2535829830144158,
      "grad_norm": 1.53125,
      "learning_rate": 2.345867161226062e-05,
      "loss": 1.0492051124572754,
      "num_input_tokens_seen": 10075716096,
      "step": 35430,
      "train_runtime": 345142.7525,
      "train_tokens_per_second": 29192.895
    },
    {
      "epoch": 1.2539368032781448,
      "grad_norm": 1.6171875,
      "learning_rate": 2.34560901335284e-05,
      "loss": 1.0399688720703124,
      "num_input_tokens_seen": 10078532096,
      "step": 35440,
      "train_runtime": 345238.5874,
      "train_tokens_per_second": 29192.948
    },
    {
      "epoch": 1.2542906235418736,
      "grad_norm": 1.53125,
      "learning_rate": 2.3453509506834984e-05,
      "loss": 1.0498522758483886,
      "num_input_tokens_seen": 10081347968,
      "step": 35450,
      "train_runtime": 345337.7363,
      "train_tokens_per_second": 29192.72
    },
    {
      "epoch": 1.2546444438056024,
      "grad_norm": 1.53125,
      "learning_rate": 2.345092973171176e-05,
      "loss": 1.035527515411377,
      "num_input_tokens_seen": 10084213888,
      "step": 35460,
      "train_runtime": 345437.4566,
      "train_tokens_per_second": 29192.59
    },
    {
      "epoch": 1.2549982640693311,
      "grad_norm": 1.6171875,
      "learning_rate": 2.3448350807690487e-05,
      "loss": 1.0342901229858399,
      "num_input_tokens_seen": 10087038336,
      "step": 35470,
      "train_runtime": 345534.2121,
      "train_tokens_per_second": 29192.589
    },
    {
      "epoch": 1.25535208433306,
      "grad_norm": 1.4921875,
      "learning_rate": 2.3445772734303292e-05,
      "loss": 1.0608578681945802,
      "num_input_tokens_seen": 10089841024,
      "step": 35480,
      "train_runtime": 345629.5796,
      "train_tokens_per_second": 29192.643
    },
    {
      "epoch": 1.2557059045967887,
      "grad_norm": 1.6015625,
      "learning_rate": 2.344319551108265e-05,
      "loss": 1.050887107849121,
      "num_input_tokens_seen": 10092678848,
      "step": 35490,
      "train_runtime": 345722.2101,
      "train_tokens_per_second": 29193.03
    },
    {
      "epoch": 1.2560597248605174,
      "grad_norm": 1.53125,
      "learning_rate": 2.3440619137561402e-05,
      "loss": 1.0496967315673829,
      "num_input_tokens_seen": 10095558208,
      "step": 35500,
      "train_runtime": 345825.52,
      "train_tokens_per_second": 29192.635
    },
    {
      "epoch": 1.2564135451242462,
      "grad_norm": 1.546875,
      "learning_rate": 2.343804361327275e-05,
      "loss": 1.0381778717041015,
      "num_input_tokens_seen": 10098391104,
      "step": 35510,
      "train_runtime": 345920.4675,
      "train_tokens_per_second": 29192.812
    },
    {
      "epoch": 1.256767365387975,
      "grad_norm": 1.6171875,
      "learning_rate": 2.3435468937750252e-05,
      "loss": 1.0526269912719726,
      "num_input_tokens_seen": 10101243008,
      "step": 35520,
      "train_runtime": 346016.4749,
      "train_tokens_per_second": 29192.954
    },
    {
      "epoch": 1.2571211856517037,
      "grad_norm": 1.5703125,
      "learning_rate": 2.3432895110527815e-05,
      "loss": 1.052810287475586,
      "num_input_tokens_seen": 10104065792,
      "step": 35530,
      "train_runtime": 346112.1064,
      "train_tokens_per_second": 29193.044
    },
    {
      "epoch": 1.2574750059154325,
      "grad_norm": 1.5078125,
      "learning_rate": 2.3430322131139726e-05,
      "loss": 1.040468978881836,
      "num_input_tokens_seen": 10106898368,
      "step": 35540,
      "train_runtime": 346210.5427,
      "train_tokens_per_second": 29192.925
    },
    {
      "epoch": 1.2578288261791613,
      "grad_norm": 1.5625,
      "learning_rate": 2.342774999912061e-05,
      "loss": 1.0462255477905273,
      "num_input_tokens_seen": 10109664512,
      "step": 35550,
      "train_runtime": 346302.423,
      "train_tokens_per_second": 29193.167
    },
    {
      "epoch": 1.25818264644289,
      "grad_norm": 1.5703125,
      "learning_rate": 2.342517871400546e-05,
      "loss": 1.0593046188354491,
      "num_input_tokens_seen": 10112520512,
      "step": 35560,
      "train_runtime": 346399.8001,
      "train_tokens_per_second": 29193.205
    },
    {
      "epoch": 1.258536466706619,
      "grad_norm": 1.546875,
      "learning_rate": 2.342260827532962e-05,
      "loss": 1.048978614807129,
      "num_input_tokens_seen": 10115328000,
      "step": 35570,
      "train_runtime": 346497.4929,
      "train_tokens_per_second": 29193.077
    },
    {
      "epoch": 1.2588902869703475,
      "grad_norm": 1.5859375,
      "learning_rate": 2.34200386826288e-05,
      "loss": 1.0493156433105468,
      "num_input_tokens_seen": 10118209472,
      "step": 35580,
      "train_runtime": 346596.438,
      "train_tokens_per_second": 29193.057
    },
    {
      "epoch": 1.2592441072340765,
      "grad_norm": 1.5703125,
      "learning_rate": 2.3417469935439052e-05,
      "loss": 1.0535624504089356,
      "num_input_tokens_seen": 10121055488,
      "step": 35590,
      "train_runtime": 346694.5435,
      "train_tokens_per_second": 29193.005
    },
    {
      "epoch": 1.259597927497805,
      "grad_norm": 1.5234375,
      "learning_rate": 2.34149020332968e-05,
      "loss": 1.0508821487426758,
      "num_input_tokens_seen": 10123917824,
      "step": 35600,
      "train_runtime": 346793.3066,
      "train_tokens_per_second": 29192.945
    },
    {
      "epoch": 1.259951747761534,
      "grad_norm": 1.6015625,
      "learning_rate": 2.3412334975738813e-05,
      "loss": 1.0557462692260742,
      "num_input_tokens_seen": 10126750016,
      "step": 35610,
      "train_runtime": 346891.1305,
      "train_tokens_per_second": 29192.877
    },
    {
      "epoch": 1.2603055680252628,
      "grad_norm": 1.5078125,
      "learning_rate": 2.3409768762302222e-05,
      "loss": 1.033669662475586,
      "num_input_tokens_seen": 10129580608,
      "step": 35620,
      "train_runtime": 346989.5281,
      "train_tokens_per_second": 29192.756
    },
    {
      "epoch": 1.2606593882889916,
      "grad_norm": 1.6015625,
      "learning_rate": 2.340720339252451e-05,
      "loss": 1.0552188873291015,
      "num_input_tokens_seen": 10132420992,
      "step": 35630,
      "train_runtime": 347087.1683,
      "train_tokens_per_second": 29192.727
    },
    {
      "epoch": 1.2610132085527204,
      "grad_norm": 1.515625,
      "learning_rate": 2.3404638865943507e-05,
      "loss": 1.0387256622314454,
      "num_input_tokens_seen": 10135264512,
      "step": 35640,
      "train_runtime": 347182.6921,
      "train_tokens_per_second": 29192.885
    },
    {
      "epoch": 1.2613670288164491,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3402075182097412e-05,
      "loss": 1.0667291641235352,
      "num_input_tokens_seen": 10138134912,
      "step": 35650,
      "train_runtime": 347282.4493,
      "train_tokens_per_second": 29192.765
    },
    {
      "epoch": 1.261720849080178,
      "grad_norm": 1.484375,
      "learning_rate": 2.339951234052477e-05,
      "loss": 1.0387666702270508,
      "num_input_tokens_seen": 10140988224,
      "step": 35660,
      "train_runtime": 347382.1504,
      "train_tokens_per_second": 29192.6
    },
    {
      "epoch": 1.2620746693439067,
      "grad_norm": 1.546875,
      "learning_rate": 2.3396950340764478e-05,
      "loss": 1.0389020919799805,
      "num_input_tokens_seen": 10143858304,
      "step": 35670,
      "train_runtime": 347483.5017,
      "train_tokens_per_second": 29192.345
    },
    {
      "epoch": 1.2624284896076354,
      "grad_norm": 1.5625,
      "learning_rate": 2.3394389182355793e-05,
      "loss": 1.0320611953735352,
      "num_input_tokens_seen": 10146706752,
      "step": 35680,
      "train_runtime": 347582.7934,
      "train_tokens_per_second": 29192.201
    },
    {
      "epoch": 1.2627823098713642,
      "grad_norm": 1.5234375,
      "learning_rate": 2.339182886483832e-05,
      "loss": 1.0480488777160644,
      "num_input_tokens_seen": 10149506048,
      "step": 35690,
      "train_runtime": 347676.9738,
      "train_tokens_per_second": 29192.345
    },
    {
      "epoch": 1.263136130135093,
      "grad_norm": 1.546875,
      "learning_rate": 2.3389269387752017e-05,
      "loss": 1.0477913856506347,
      "num_input_tokens_seen": 10152397888,
      "step": 35700,
      "train_runtime": 347776.5258,
      "train_tokens_per_second": 29192.303
    },
    {
      "epoch": 1.2634899503988217,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3386710750637194e-05,
      "loss": 1.0533632278442382,
      "num_input_tokens_seen": 10155230208,
      "step": 35710,
      "train_runtime": 347873.7436,
      "train_tokens_per_second": 29192.287
    },
    {
      "epoch": 1.2638437706625505,
      "grad_norm": 1.5078125,
      "learning_rate": 2.3384152953034514e-05,
      "loss": 1.0542146682739257,
      "num_input_tokens_seen": 10158070912,
      "step": 35720,
      "train_runtime": 347972.5801,
      "train_tokens_per_second": 29192.159
    },
    {
      "epoch": 1.2641975909262793,
      "grad_norm": 1.453125,
      "learning_rate": 2.338159599448499e-05,
      "loss": 1.0429905891418456,
      "num_input_tokens_seen": 10160917056,
      "step": 35730,
      "train_runtime": 348069.8664,
      "train_tokens_per_second": 29192.177
    },
    {
      "epoch": 1.2645514111900082,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3379039874529996e-05,
      "loss": 1.040936279296875,
      "num_input_tokens_seen": 10163797952,
      "step": 35740,
      "train_runtime": 348168.0129,
      "train_tokens_per_second": 29192.222
    },
    {
      "epoch": 1.2649052314537368,
      "grad_norm": 1.515625,
      "learning_rate": 2.337648459271124e-05,
      "loss": 1.035550880432129,
      "num_input_tokens_seen": 10166626048,
      "step": 35750,
      "train_runtime": 348265.7225,
      "train_tokens_per_second": 29192.152
    },
    {
      "epoch": 1.2652590517174658,
      "grad_norm": 1.5859375,
      "learning_rate": 2.3373930148570787e-05,
      "loss": 1.0582223892211915,
      "num_input_tokens_seen": 10169436416,
      "step": 35760,
      "train_runtime": 348362.2433,
      "train_tokens_per_second": 29192.132
    },
    {
      "epoch": 1.2656128719811943,
      "grad_norm": 1.6171875,
      "learning_rate": 2.3371376541651063e-05,
      "loss": 1.0647600173950196,
      "num_input_tokens_seen": 10172264768,
      "step": 35770,
      "train_runtime": 348457.3947,
      "train_tokens_per_second": 29192.277
    },
    {
      "epoch": 1.2659666922449233,
      "grad_norm": 1.5625,
      "learning_rate": 2.336882377149483e-05,
      "loss": 1.052362823486328,
      "num_input_tokens_seen": 10175120896,
      "step": 35780,
      "train_runtime": 348555.5991,
      "train_tokens_per_second": 29192.246
    },
    {
      "epoch": 1.266320512508652,
      "grad_norm": 1.53125,
      "learning_rate": 2.3366271837645207e-05,
      "loss": 1.0560431480407715,
      "num_input_tokens_seen": 10178012672,
      "step": 35790,
      "train_runtime": 348654.2094,
      "train_tokens_per_second": 29192.284
    },
    {
      "epoch": 1.2666743327723808,
      "grad_norm": 1.5859375,
      "learning_rate": 2.3363720739645652e-05,
      "loss": 1.0467076301574707,
      "num_input_tokens_seen": 10180854720,
      "step": 35800,
      "train_runtime": 348751.3984,
      "train_tokens_per_second": 29192.298
    },
    {
      "epoch": 1.2670281530361096,
      "grad_norm": 1.515625,
      "learning_rate": 2.3361170477039995e-05,
      "loss": 1.0449387550354003,
      "num_input_tokens_seen": 10183678464,
      "step": 35810,
      "train_runtime": 348847.0621,
      "train_tokens_per_second": 29192.387
    },
    {
      "epoch": 1.2673819732998384,
      "grad_norm": 1.5859375,
      "learning_rate": 2.3358621049372383e-05,
      "loss": 1.0527238845825195,
      "num_input_tokens_seen": 10186474624,
      "step": 35820,
      "train_runtime": 348943.7547,
      "train_tokens_per_second": 29192.311
    },
    {
      "epoch": 1.2677357935635671,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3356072456187336e-05,
      "loss": 1.0483879089355468,
      "num_input_tokens_seen": 10189268608,
      "step": 35830,
      "train_runtime": 349037.7649,
      "train_tokens_per_second": 29192.453
    },
    {
      "epoch": 1.268089613827296,
      "grad_norm": 1.5,
      "learning_rate": 2.335352469702972e-05,
      "loss": 1.0454856872558593,
      "num_input_tokens_seen": 10192053568,
      "step": 35840,
      "train_runtime": 349132.9995,
      "train_tokens_per_second": 29192.467
    },
    {
      "epoch": 1.2684434340910247,
      "grad_norm": 1.5703125,
      "learning_rate": 2.3350977771444724e-05,
      "loss": 1.0411387443542481,
      "num_input_tokens_seen": 10194905920,
      "step": 35850,
      "train_runtime": 349233.1365,
      "train_tokens_per_second": 29192.264
    },
    {
      "epoch": 1.2687972543547534,
      "grad_norm": 1.5078125,
      "learning_rate": 2.3348431678977914e-05,
      "loss": 1.045221710205078,
      "num_input_tokens_seen": 10197752832,
      "step": 35860,
      "train_runtime": 349330.1158,
      "train_tokens_per_second": 29192.309
    },
    {
      "epoch": 1.2691510746184822,
      "grad_norm": 1.546875,
      "learning_rate": 2.334588641917519e-05,
      "loss": 1.0437467575073243,
      "num_input_tokens_seen": 10200570048,
      "step": 35870,
      "train_runtime": 349423.947,
      "train_tokens_per_second": 29192.533
    },
    {
      "epoch": 1.269504894882211,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3343341991582792e-05,
      "loss": 1.047953987121582,
      "num_input_tokens_seen": 10203438656,
      "step": 35880,
      "train_runtime": 349524.4337,
      "train_tokens_per_second": 29192.347
    },
    {
      "epoch": 1.2698587151459397,
      "grad_norm": 1.4609375,
      "learning_rate": 2.334079839574732e-05,
      "loss": 1.0267410278320312,
      "num_input_tokens_seen": 10206278592,
      "step": 35890,
      "train_runtime": 349619.6906,
      "train_tokens_per_second": 29192.517
    },
    {
      "epoch": 1.2702125354096685,
      "grad_norm": 1.5859375,
      "learning_rate": 2.333825563121571e-05,
      "loss": 1.0556390762329102,
      "num_input_tokens_seen": 10209164416,
      "step": 35900,
      "train_runtime": 349718.3815,
      "train_tokens_per_second": 29192.53
    },
    {
      "epoch": 1.2705663556733975,
      "grad_norm": 1.53125,
      "learning_rate": 2.333571369753525e-05,
      "loss": 1.047159194946289,
      "num_input_tokens_seen": 10212010368,
      "step": 35910,
      "train_runtime": 349816.9482,
      "train_tokens_per_second": 29192.44
    },
    {
      "epoch": 1.270920175937126,
      "grad_norm": 1.59375,
      "learning_rate": 2.3333172594253564e-05,
      "loss": 1.0545637130737304,
      "num_input_tokens_seen": 10214850176,
      "step": 35920,
      "train_runtime": 349914.0217,
      "train_tokens_per_second": 29192.457
    },
    {
      "epoch": 1.271273996200855,
      "grad_norm": 1.4765625,
      "learning_rate": 2.3330632320918626e-05,
      "loss": 1.057828426361084,
      "num_input_tokens_seen": 10217684864,
      "step": 35930,
      "train_runtime": 350011.3174,
      "train_tokens_per_second": 29192.441
    },
    {
      "epoch": 1.2716278164645836,
      "grad_norm": 1.578125,
      "learning_rate": 2.3328092877078757e-05,
      "loss": 1.0525793075561523,
      "num_input_tokens_seen": 10220489984,
      "step": 35940,
      "train_runtime": 350106.7227,
      "train_tokens_per_second": 29192.499
    },
    {
      "epoch": 1.2719816367283125,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3325554262282617e-05,
      "loss": 1.0531472206115722,
      "num_input_tokens_seen": 10223374272,
      "step": 35950,
      "train_runtime": 350205.037,
      "train_tokens_per_second": 29192.539
    },
    {
      "epoch": 1.2723354569920413,
      "grad_norm": 1.53125,
      "learning_rate": 2.332301647607922e-05,
      "loss": 1.0415127754211426,
      "num_input_tokens_seen": 10226270016,
      "step": 35960,
      "train_runtime": 350304.5862,
      "train_tokens_per_second": 29192.51
    },
    {
      "epoch": 1.27268927725577,
      "grad_norm": 1.4609375,
      "learning_rate": 2.3320479518017907e-05,
      "loss": 1.0368799209594726,
      "num_input_tokens_seen": 10229135040,
      "step": 35970,
      "train_runtime": 350400.8981,
      "train_tokens_per_second": 29192.662
    },
    {
      "epoch": 1.2730430975194988,
      "grad_norm": 1.53125,
      "learning_rate": 2.3317943387648372e-05,
      "loss": 1.0461764335632324,
      "num_input_tokens_seen": 10232022784,
      "step": 35980,
      "train_runtime": 350503.8323,
      "train_tokens_per_second": 29192.328
    },
    {
      "epoch": 1.2733969177832276,
      "grad_norm": 1.546875,
      "learning_rate": 2.3315408084520653e-05,
      "loss": 1.0449687957763671,
      "num_input_tokens_seen": 10234852992,
      "step": 35990,
      "train_runtime": 350601.298,
      "train_tokens_per_second": 29192.285
    },
    {
      "epoch": 1.2737507380469564,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3312873608185128e-05,
      "loss": 1.031435203552246,
      "num_input_tokens_seen": 10237701504,
      "step": 36000,
      "train_runtime": 350699.1236,
      "train_tokens_per_second": 29192.264
    },
    {
      "epoch": 1.2741045583106851,
      "grad_norm": 1.4765625,
      "learning_rate": 2.3310339958192516e-05,
      "loss": 1.0394020080566406,
      "num_input_tokens_seen": 10240542208,
      "step": 36010,
      "train_runtime": 350796.3553,
      "train_tokens_per_second": 29192.271
    },
    {
      "epoch": 1.274458378574414,
      "grad_norm": 1.453125,
      "learning_rate": 2.3307807134093877e-05,
      "loss": 1.035683822631836,
      "num_input_tokens_seen": 10243427712,
      "step": 36020,
      "train_runtime": 350896.4206,
      "train_tokens_per_second": 29192.169
    },
    {
      "epoch": 1.2748121988381427,
      "grad_norm": 1.59375,
      "learning_rate": 2.3305275135440616e-05,
      "loss": 1.0510623931884766,
      "num_input_tokens_seen": 10246277184,
      "step": 36030,
      "train_runtime": 350993.8491,
      "train_tokens_per_second": 29192.184
    },
    {
      "epoch": 1.2751660191018714,
      "grad_norm": 1.53125,
      "learning_rate": 2.3302743961784472e-05,
      "loss": 1.0356892585754394,
      "num_input_tokens_seen": 10249089600,
      "step": 36040,
      "train_runtime": 351089.4252,
      "train_tokens_per_second": 29192.248
    },
    {
      "epoch": 1.2755198393656002,
      "grad_norm": 1.4765625,
      "learning_rate": 2.3300213612677545e-05,
      "loss": 1.0561676025390625,
      "num_input_tokens_seen": 10252022528,
      "step": 36050,
      "train_runtime": 351190.5342,
      "train_tokens_per_second": 29192.195
    },
    {
      "epoch": 1.275873659629329,
      "grad_norm": 1.5,
      "learning_rate": 2.3297684087672242e-05,
      "loss": 1.0552453994750977,
      "num_input_tokens_seen": 10254893120,
      "step": 36060,
      "train_runtime": 351286.5997,
      "train_tokens_per_second": 29192.383
    },
    {
      "epoch": 1.2762274798930577,
      "grad_norm": 1.640625,
      "learning_rate": 2.3295155386321336e-05,
      "loss": 1.049654197692871,
      "num_input_tokens_seen": 10257762624,
      "step": 36070,
      "train_runtime": 351384.6384,
      "train_tokens_per_second": 29192.405
    },
    {
      "epoch": 1.2765813001567867,
      "grad_norm": 1.4765625,
      "learning_rate": 2.3292627508177933e-05,
      "loss": 1.0412948608398438,
      "num_input_tokens_seen": 10260627968,
      "step": 36080,
      "train_runtime": 351481.0546,
      "train_tokens_per_second": 29192.549
    },
    {
      "epoch": 1.2769351204205153,
      "grad_norm": 1.53125,
      "learning_rate": 2.3290100452795474e-05,
      "loss": 1.060901165008545,
      "num_input_tokens_seen": 10263424576,
      "step": 36090,
      "train_runtime": 351576.484,
      "train_tokens_per_second": 29192.58
    },
    {
      "epoch": 1.2772889406842443,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3287574219727752e-05,
      "loss": 1.0422266960144042,
      "num_input_tokens_seen": 10266299072,
      "step": 36100,
      "train_runtime": 351679.023,
      "train_tokens_per_second": 29192.242
    },
    {
      "epoch": 1.277642760947973,
      "grad_norm": 1.609375,
      "learning_rate": 2.3285048808528872e-05,
      "loss": 1.0456802368164062,
      "num_input_tokens_seen": 10269100928,
      "step": 36110,
      "train_runtime": 351774.3474,
      "train_tokens_per_second": 29192.296
    },
    {
      "epoch": 1.2779965812117018,
      "grad_norm": 1.53125,
      "learning_rate": 2.3282524218753308e-05,
      "loss": 1.0575891494750977,
      "num_input_tokens_seen": 10271921792,
      "step": 36120,
      "train_runtime": 351870.0429,
      "train_tokens_per_second": 29192.374
    },
    {
      "epoch": 1.2783504014754306,
      "grad_norm": 1.5234375,
      "learning_rate": 2.328000044995586e-05,
      "loss": 1.046957302093506,
      "num_input_tokens_seen": 10274797312,
      "step": 36130,
      "train_runtime": 351966.9009,
      "train_tokens_per_second": 29192.51
    },
    {
      "epoch": 1.2787042217391593,
      "grad_norm": 1.625,
      "learning_rate": 2.3277477501691647e-05,
      "loss": 1.0440662384033204,
      "num_input_tokens_seen": 10277620416,
      "step": 36140,
      "train_runtime": 352063.2155,
      "train_tokens_per_second": 29192.543
    },
    {
      "epoch": 1.279058042002888,
      "grad_norm": 1.515625,
      "learning_rate": 2.3274955373516163e-05,
      "loss": 1.0550686836242675,
      "num_input_tokens_seen": 10280484224,
      "step": 36150,
      "train_runtime": 352160.464,
      "train_tokens_per_second": 29192.613
    },
    {
      "epoch": 1.2794118622666169,
      "grad_norm": 1.53125,
      "learning_rate": 2.3272434064985205e-05,
      "loss": 1.050411319732666,
      "num_input_tokens_seen": 10283366336,
      "step": 36160,
      "train_runtime": 352258.4835,
      "train_tokens_per_second": 29192.672
    },
    {
      "epoch": 1.2797656825303456,
      "grad_norm": 1.46875,
      "learning_rate": 2.3269913575654932e-05,
      "loss": 1.0474621772766113,
      "num_input_tokens_seen": 10286268288,
      "step": 36170,
      "train_runtime": 352358.5875,
      "train_tokens_per_second": 29192.614
    },
    {
      "epoch": 1.2801195027940744,
      "grad_norm": 1.5078125,
      "learning_rate": 2.326739390508182e-05,
      "loss": 1.0358003616333007,
      "num_input_tokens_seen": 10289162304,
      "step": 36180,
      "train_runtime": 352460.982,
      "train_tokens_per_second": 29192.344
    },
    {
      "epoch": 1.2804733230578031,
      "grad_norm": 1.6171875,
      "learning_rate": 2.326487505282269e-05,
      "loss": 1.0526773452758789,
      "num_input_tokens_seen": 10291963072,
      "step": 36190,
      "train_runtime": 352554.5786,
      "train_tokens_per_second": 29192.538
    },
    {
      "epoch": 1.280827143321532,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3262357018434698e-05,
      "loss": 1.0549711227416991,
      "num_input_tokens_seen": 10294793920,
      "step": 36200,
      "train_runtime": 352650.8065,
      "train_tokens_per_second": 29192.6
    },
    {
      "epoch": 1.2811809635852607,
      "grad_norm": 1.578125,
      "learning_rate": 2.3259839801475338e-05,
      "loss": 1.0471868515014648,
      "num_input_tokens_seen": 10297646528,
      "step": 36210,
      "train_runtime": 352748.7297,
      "train_tokens_per_second": 29192.583
    },
    {
      "epoch": 1.2815347838489894,
      "grad_norm": 1.4765625,
      "learning_rate": 2.325732340150243e-05,
      "loss": 1.0624814987182618,
      "num_input_tokens_seen": 10300463360,
      "step": 36220,
      "train_runtime": 352845.0855,
      "train_tokens_per_second": 29192.594
    },
    {
      "epoch": 1.2818886041127182,
      "grad_norm": 1.5859375,
      "learning_rate": 2.325480781807415e-05,
      "loss": 1.05201416015625,
      "num_input_tokens_seen": 10303317952,
      "step": 36230,
      "train_runtime": 352945.8606,
      "train_tokens_per_second": 29192.347
    },
    {
      "epoch": 1.282242424376447,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3252293050748975e-05,
      "loss": 1.0428884506225586,
      "num_input_tokens_seen": 10306168768,
      "step": 36240,
      "train_runtime": 353042.5725,
      "train_tokens_per_second": 29192.425
    },
    {
      "epoch": 1.282596244640176,
      "grad_norm": 1.5390625,
      "learning_rate": 2.324977909908575e-05,
      "loss": 1.0578889846801758,
      "num_input_tokens_seen": 10308941952,
      "step": 36250,
      "train_runtime": 353137.9522,
      "train_tokens_per_second": 29192.393
    },
    {
      "epoch": 1.2829500649039045,
      "grad_norm": 1.546875,
      "learning_rate": 2.3247265962643632e-05,
      "loss": 1.0350717544555663,
      "num_input_tokens_seen": 10311799040,
      "step": 36260,
      "train_runtime": 353237.1889,
      "train_tokens_per_second": 29192.28
    },
    {
      "epoch": 1.2833038851676335,
      "grad_norm": 1.484375,
      "learning_rate": 2.3244753640982106e-05,
      "loss": 1.0512584686279296,
      "num_input_tokens_seen": 10314670976,
      "step": 36270,
      "train_runtime": 353337.8415,
      "train_tokens_per_second": 29192.093
    },
    {
      "epoch": 1.2836577054313623,
      "grad_norm": 1.5078125,
      "learning_rate": 2.324224213366102e-05,
      "loss": 1.0635036468505858,
      "num_input_tokens_seen": 10317556096,
      "step": 36280,
      "train_runtime": 353437.9517,
      "train_tokens_per_second": 29191.987
    },
    {
      "epoch": 1.284011525695091,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3239731440240538e-05,
      "loss": 1.0386905670166016,
      "num_input_tokens_seen": 10320370240,
      "step": 36290,
      "train_runtime": 353533.8443,
      "train_tokens_per_second": 29192.029
    },
    {
      "epoch": 1.2843653459588198,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3237221560281143e-05,
      "loss": 1.0551176071166992,
      "num_input_tokens_seen": 10323213696,
      "step": 36300,
      "train_runtime": 353633.8103,
      "train_tokens_per_second": 29191.818
    },
    {
      "epoch": 1.2847191662225486,
      "grad_norm": 1.53125,
      "learning_rate": 2.3234712493343673e-05,
      "loss": 1.0369672775268555,
      "num_input_tokens_seen": 10326142016,
      "step": 36310,
      "train_runtime": 353734.0188,
      "train_tokens_per_second": 29191.826
    },
    {
      "epoch": 1.2850729864862773,
      "grad_norm": 1.5859375,
      "learning_rate": 2.323220423898928e-05,
      "loss": 1.0476274490356445,
      "num_input_tokens_seen": 10329028416,
      "step": 36320,
      "train_runtime": 353833.0712,
      "train_tokens_per_second": 29191.812
    },
    {
      "epoch": 1.285426806750006,
      "grad_norm": 1.515625,
      "learning_rate": 2.3229696796779456e-05,
      "loss": 1.0520745277404786,
      "num_input_tokens_seen": 10331877632,
      "step": 36330,
      "train_runtime": 353929.8137,
      "train_tokens_per_second": 29191.883
    },
    {
      "epoch": 1.2857806270137349,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3227190166276033e-05,
      "loss": 1.064095687866211,
      "num_input_tokens_seen": 10334730560,
      "step": 36340,
      "train_runtime": 354025.2963,
      "train_tokens_per_second": 29192.068
    },
    {
      "epoch": 1.2861344472774636,
      "grad_norm": 1.5625,
      "learning_rate": 2.3224684347041153e-05,
      "loss": 1.0499074935913086,
      "num_input_tokens_seen": 10337580928,
      "step": 36350,
      "train_runtime": 354122.5456,
      "train_tokens_per_second": 29192.1
    },
    {
      "epoch": 1.2864882675411924,
      "grad_norm": 1.59375,
      "learning_rate": 2.3222179338637306e-05,
      "loss": 1.0515209197998048,
      "num_input_tokens_seen": 10340425472,
      "step": 36360,
      "train_runtime": 354219.5206,
      "train_tokens_per_second": 29192.139
    },
    {
      "epoch": 1.2868420878049212,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3219675140627302e-05,
      "loss": 1.0561207771301269,
      "num_input_tokens_seen": 10343287040,
      "step": 36370,
      "train_runtime": 354315.9595,
      "train_tokens_per_second": 29192.27
    },
    {
      "epoch": 1.28719590806865,
      "grad_norm": 1.5703125,
      "learning_rate": 2.3217171752574292e-05,
      "loss": 1.0493478775024414,
      "num_input_tokens_seen": 10346137920,
      "step": 36380,
      "train_runtime": 354413.1693,
      "train_tokens_per_second": 29192.307
    },
    {
      "epoch": 1.2875497283323787,
      "grad_norm": 1.5,
      "learning_rate": 2.3214669174041745e-05,
      "loss": 1.0583698272705078,
      "num_input_tokens_seen": 10348913664,
      "step": 36390,
      "train_runtime": 354505.3245,
      "train_tokens_per_second": 29192.548
    },
    {
      "epoch": 1.2879035485961077,
      "grad_norm": 1.5625,
      "learning_rate": 2.321216740459346e-05,
      "loss": 1.0367016792297363,
      "num_input_tokens_seen": 10351740544,
      "step": 36400,
      "train_runtime": 354600.6063,
      "train_tokens_per_second": 29192.676
    },
    {
      "epoch": 1.2882573688598362,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3209666443793578e-05,
      "loss": 1.0508742332458496,
      "num_input_tokens_seen": 10354564224,
      "step": 36410,
      "train_runtime": 354698.6685,
      "train_tokens_per_second": 29192.566
    },
    {
      "epoch": 1.2886111891235652,
      "grad_norm": 1.59375,
      "learning_rate": 2.3207166291206553e-05,
      "loss": 1.041246223449707,
      "num_input_tokens_seen": 10357410304,
      "step": 36420,
      "train_runtime": 354796.1143,
      "train_tokens_per_second": 29192.57
    },
    {
      "epoch": 1.2889650093872937,
      "grad_norm": 1.59375,
      "learning_rate": 2.3204666946397175e-05,
      "loss": 1.0406181335449218,
      "num_input_tokens_seen": 10360279296,
      "step": 36430,
      "train_runtime": 354894.7119,
      "train_tokens_per_second": 29192.543
    },
    {
      "epoch": 1.2893188296510227,
      "grad_norm": 1.65625,
      "learning_rate": 2.3202168408930565e-05,
      "loss": 1.0501867294311524,
      "num_input_tokens_seen": 10363111616,
      "step": 36440,
      "train_runtime": 354991.2767,
      "train_tokens_per_second": 29192.581
    },
    {
      "epoch": 1.2896726499147515,
      "grad_norm": 1.5703125,
      "learning_rate": 2.3199670678372166e-05,
      "loss": 1.051297950744629,
      "num_input_tokens_seen": 10365997312,
      "step": 36450,
      "train_runtime": 355090.3381,
      "train_tokens_per_second": 29192.564
    },
    {
      "epoch": 1.2900264701784803,
      "grad_norm": 1.484375,
      "learning_rate": 2.3197173754287747e-05,
      "loss": 1.0366804122924804,
      "num_input_tokens_seen": 10368827776,
      "step": 36460,
      "train_runtime": 355183.6405,
      "train_tokens_per_second": 29192.864
    },
    {
      "epoch": 1.290380290442209,
      "grad_norm": 1.59375,
      "learning_rate": 2.319467763624341e-05,
      "loss": 1.041246223449707,
      "num_input_tokens_seen": 10371667456,
      "step": 36470,
      "train_runtime": 355279.7515,
      "train_tokens_per_second": 29192.96
    },
    {
      "epoch": 1.2907341107059378,
      "grad_norm": 1.5625,
      "learning_rate": 2.3192182323805577e-05,
      "loss": 1.0443979263305665,
      "num_input_tokens_seen": 10374532864,
      "step": 36480,
      "train_runtime": 355379.2188,
      "train_tokens_per_second": 29192.852
    },
    {
      "epoch": 1.2910879309696666,
      "grad_norm": 1.59375,
      "learning_rate": 2.318968781654101e-05,
      "loss": 1.0467546463012696,
      "num_input_tokens_seen": 10377353600,
      "step": 36490,
      "train_runtime": 355473.3924,
      "train_tokens_per_second": 29193.053
    },
    {
      "epoch": 1.2914417512333953,
      "grad_norm": 1.5859375,
      "learning_rate": 2.3187194114016778e-05,
      "loss": 1.0610313415527344,
      "num_input_tokens_seen": 10380203328,
      "step": 36500,
      "train_runtime": 355569.8065,
      "train_tokens_per_second": 29193.152
    },
    {
      "epoch": 1.291795571497124,
      "grad_norm": 1.515625,
      "learning_rate": 2.318470121580029e-05,
      "loss": 1.048283004760742,
      "num_input_tokens_seen": 10383002688,
      "step": 36510,
      "train_runtime": 355665.7253,
      "train_tokens_per_second": 29193.149
    },
    {
      "epoch": 1.2921493917608529,
      "grad_norm": 1.4609375,
      "learning_rate": 2.318220912145927e-05,
      "loss": 1.0514901161193848,
      "num_input_tokens_seen": 10385819840,
      "step": 36520,
      "train_runtime": 355762.9526,
      "train_tokens_per_second": 29193.09
    },
    {
      "epoch": 1.2925032120245816,
      "grad_norm": 1.5625,
      "learning_rate": 2.3179717830561783e-05,
      "loss": 1.0465136528015138,
      "num_input_tokens_seen": 10388652800,
      "step": 36530,
      "train_runtime": 355857.989,
      "train_tokens_per_second": 29193.254
    },
    {
      "epoch": 1.2928570322883104,
      "grad_norm": 1.59375,
      "learning_rate": 2.3177227342676204e-05,
      "loss": 1.0370139122009276,
      "num_input_tokens_seen": 10391493696,
      "step": 36540,
      "train_runtime": 355955.8484,
      "train_tokens_per_second": 29193.21
    },
    {
      "epoch": 1.2932108525520392,
      "grad_norm": 1.5,
      "learning_rate": 2.317473765737124e-05,
      "loss": 1.0567922592163086,
      "num_input_tokens_seen": 10394314816,
      "step": 36550,
      "train_runtime": 356052.06,
      "train_tokens_per_second": 29193.244
    },
    {
      "epoch": 1.293564672815768,
      "grad_norm": 1.4609375,
      "learning_rate": 2.317224877421591e-05,
      "loss": 1.0522394180297852,
      "num_input_tokens_seen": 10397156672,
      "step": 36560,
      "train_runtime": 356148.7977,
      "train_tokens_per_second": 29193.294
    },
    {
      "epoch": 1.293918493079497,
      "grad_norm": 1.484375,
      "learning_rate": 2.3169760692779578e-05,
      "loss": 1.0532241821289063,
      "num_input_tokens_seen": 10400008960,
      "step": 36570,
      "train_runtime": 356247.167,
      "train_tokens_per_second": 29193.24
    },
    {
      "epoch": 1.2942723133432255,
      "grad_norm": 1.5703125,
      "learning_rate": 2.316727341263191e-05,
      "loss": 1.0459787368774414,
      "num_input_tokens_seen": 10402812224,
      "step": 36580,
      "train_runtime": 356344.7186,
      "train_tokens_per_second": 29193.115
    },
    {
      "epoch": 1.2946261336069544,
      "grad_norm": 1.578125,
      "learning_rate": 2.3164786933342915e-05,
      "loss": 1.0656368255615234,
      "num_input_tokens_seen": 10405665600,
      "step": 36590,
      "train_runtime": 356442.5288,
      "train_tokens_per_second": 29193.109
    },
    {
      "epoch": 1.294979953870683,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3162301254482914e-05,
      "loss": 1.0501174926757812,
      "num_input_tokens_seen": 10408514944,
      "step": 36600,
      "train_runtime": 356540.2004,
      "train_tokens_per_second": 29193.103
    },
    {
      "epoch": 1.295333774134412,
      "grad_norm": 1.515625,
      "learning_rate": 2.3159816375622546e-05,
      "loss": 1.0399152755737304,
      "num_input_tokens_seen": 10411365760,
      "step": 36610,
      "train_runtime": 356638.1673,
      "train_tokens_per_second": 29193.078
    },
    {
      "epoch": 1.2956875943981407,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3157332296332783e-05,
      "loss": 1.056624698638916,
      "num_input_tokens_seen": 10414225920,
      "step": 36620,
      "train_runtime": 356736.4946,
      "train_tokens_per_second": 29193.049
    },
    {
      "epoch": 1.2960414146618695,
      "grad_norm": 1.4765625,
      "learning_rate": 2.3154849016184914e-05,
      "loss": 1.0495917320251464,
      "num_input_tokens_seen": 10417155072,
      "step": 36630,
      "train_runtime": 356839.1533,
      "train_tokens_per_second": 29192.859
    },
    {
      "epoch": 1.2963952349255983,
      "grad_norm": 1.546875,
      "learning_rate": 2.3152366534750554e-05,
      "loss": 1.0446695327758788,
      "num_input_tokens_seen": 10420005760,
      "step": 36640,
      "train_runtime": 356936.3959,
      "train_tokens_per_second": 29192.892
    },
    {
      "epoch": 1.296749055189327,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3149884851601633e-05,
      "loss": 1.0270333290100098,
      "num_input_tokens_seen": 10422820672,
      "step": 36650,
      "train_runtime": 357033.1975,
      "train_tokens_per_second": 29192.861
    },
    {
      "epoch": 1.2971028754530558,
      "grad_norm": 1.5625,
      "learning_rate": 2.31474039663104e-05,
      "loss": 1.0441347122192384,
      "num_input_tokens_seen": 10425622016,
      "step": 36660,
      "train_runtime": 357126.8002,
      "train_tokens_per_second": 29193.054
    },
    {
      "epoch": 1.2974566957167846,
      "grad_norm": 1.625,
      "learning_rate": 2.314492387844944e-05,
      "loss": 1.0503193855285644,
      "num_input_tokens_seen": 10428388224,
      "step": 36670,
      "train_runtime": 357223.9592,
      "train_tokens_per_second": 29192.858
    },
    {
      "epoch": 1.2978105159805133,
      "grad_norm": 1.5703125,
      "learning_rate": 2.314244458759163e-05,
      "loss": 1.052667999267578,
      "num_input_tokens_seen": 10431217152,
      "step": 36680,
      "train_runtime": 357322.8441,
      "train_tokens_per_second": 29192.696
    },
    {
      "epoch": 1.298164336244242,
      "grad_norm": 1.53125,
      "learning_rate": 2.3139966093310202e-05,
      "loss": 1.0420839309692382,
      "num_input_tokens_seen": 10434115456,
      "step": 36690,
      "train_runtime": 357419.7419,
      "train_tokens_per_second": 29192.891
    },
    {
      "epoch": 1.2985181565079709,
      "grad_norm": 1.59375,
      "learning_rate": 2.3137488395178695e-05,
      "loss": 1.0467926025390626,
      "num_input_tokens_seen": 10436962176,
      "step": 36700,
      "train_runtime": 357516.5408,
      "train_tokens_per_second": 29192.949
    },
    {
      "epoch": 1.2988719767716996,
      "grad_norm": 1.5078125,
      "learning_rate": 2.313501149277095e-05,
      "loss": 1.0565263748168945,
      "num_input_tokens_seen": 10439813568,
      "step": 36710,
      "train_runtime": 357612.4305,
      "train_tokens_per_second": 29193.095
    },
    {
      "epoch": 1.2992257970354284,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3132535385661143e-05,
      "loss": 1.0378105163574218,
      "num_input_tokens_seen": 10442624128,
      "step": 36720,
      "train_runtime": 357708.4198,
      "train_tokens_per_second": 29193.118
    },
    {
      "epoch": 1.2995796172991572,
      "grad_norm": 1.578125,
      "learning_rate": 2.313006007342377e-05,
      "loss": 1.0547441482543944,
      "num_input_tokens_seen": 10445464384,
      "step": 36730,
      "train_runtime": 357804.4516,
      "train_tokens_per_second": 29193.221
    },
    {
      "epoch": 1.2999334375628862,
      "grad_norm": 1.5546875,
      "learning_rate": 2.312758555563365e-05,
      "loss": 1.0556913375854493,
      "num_input_tokens_seen": 10448279744,
      "step": 36740,
      "train_runtime": 357900.0712,
      "train_tokens_per_second": 29193.288
    },
    {
      "epoch": 1.3002872578266147,
      "grad_norm": 1.515625,
      "learning_rate": 2.3125111831865908e-05,
      "loss": 1.0528488159179688,
      "num_input_tokens_seen": 10451154112,
      "step": 36750,
      "train_runtime": 357999.7628,
      "train_tokens_per_second": 29193.187
    },
    {
      "epoch": 1.3006410780903437,
      "grad_norm": 1.578125,
      "learning_rate": 2.3122638901695983e-05,
      "loss": 1.0508752822875977,
      "num_input_tokens_seen": 10454018944,
      "step": 36760,
      "train_runtime": 358100.6159,
      "train_tokens_per_second": 29192.966
    },
    {
      "epoch": 1.3009948983540722,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3120166764699654e-05,
      "loss": 1.0481758117675781,
      "num_input_tokens_seen": 10456844672,
      "step": 36770,
      "train_runtime": 358198.2409,
      "train_tokens_per_second": 29192.898
    },
    {
      "epoch": 1.3013487186178012,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3117695420453e-05,
      "loss": 1.0499849319458008,
      "num_input_tokens_seen": 10459667520,
      "step": 36780,
      "train_runtime": 358294.4614,
      "train_tokens_per_second": 29192.937
    },
    {
      "epoch": 1.30170253888153,
      "grad_norm": 1.515625,
      "learning_rate": 2.3115224868532416e-05,
      "loss": 1.0536531448364257,
      "num_input_tokens_seen": 10462504000,
      "step": 36790,
      "train_runtime": 358389.767,
      "train_tokens_per_second": 29193.088
    },
    {
      "epoch": 1.3020563591452587,
      "grad_norm": 1.53125,
      "learning_rate": 2.3112755108514628e-05,
      "loss": 1.0406072616577149,
      "num_input_tokens_seen": 10465319296,
      "step": 36800,
      "train_runtime": 358484.5859,
      "train_tokens_per_second": 29193.22
    },
    {
      "epoch": 1.3024101794089875,
      "grad_norm": 1.5546875,
      "learning_rate": 2.311028613997666e-05,
      "loss": 1.0578908920288086,
      "num_input_tokens_seen": 10468055424,
      "step": 36810,
      "train_runtime": 358576.4696,
      "train_tokens_per_second": 29193.37
    },
    {
      "epoch": 1.3027639996727163,
      "grad_norm": 1.609375,
      "learning_rate": 2.3107817962495873e-05,
      "loss": 1.0372175216674804,
      "num_input_tokens_seen": 10470895104,
      "step": 36820,
      "train_runtime": 358672.9144,
      "train_tokens_per_second": 29193.437
    },
    {
      "epoch": 1.303117819936445,
      "grad_norm": 1.546875,
      "learning_rate": 2.3105350575649924e-05,
      "loss": 1.0335363388061523,
      "num_input_tokens_seen": 10473714944,
      "step": 36830,
      "train_runtime": 358768.3805,
      "train_tokens_per_second": 29193.529
    },
    {
      "epoch": 1.3034716402001738,
      "grad_norm": 1.5234375,
      "learning_rate": 2.31028839790168e-05,
      "loss": 1.0454877853393554,
      "num_input_tokens_seen": 10476587264,
      "step": 36840,
      "train_runtime": 358864.2343,
      "train_tokens_per_second": 29193.735
    },
    {
      "epoch": 1.3038254604639026,
      "grad_norm": 1.515625,
      "learning_rate": 2.310041817217479e-05,
      "loss": 1.0510156631469727,
      "num_input_tokens_seen": 10479458496,
      "step": 36850,
      "train_runtime": 358961.9824,
      "train_tokens_per_second": 29193.784
    },
    {
      "epoch": 1.3041792807276313,
      "grad_norm": 1.515625,
      "learning_rate": 2.3097953154702514e-05,
      "loss": 1.037264347076416,
      "num_input_tokens_seen": 10482322368,
      "step": 36860,
      "train_runtime": 359059.1948,
      "train_tokens_per_second": 29193.856
    },
    {
      "epoch": 1.30453310099136,
      "grad_norm": 1.53125,
      "learning_rate": 2.3095488926178896e-05,
      "loss": 1.0494277954101563,
      "num_input_tokens_seen": 10485198720,
      "step": 36870,
      "train_runtime": 359157.6535,
      "train_tokens_per_second": 29193.861
    },
    {
      "epoch": 1.3048869212550889,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3093025486183175e-05,
      "loss": 1.0465604782104492,
      "num_input_tokens_seen": 10488079168,
      "step": 36880,
      "train_runtime": 359255.2734,
      "train_tokens_per_second": 29193.946
    },
    {
      "epoch": 1.3052407415188176,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3090562834294908e-05,
      "loss": 1.0376805305480956,
      "num_input_tokens_seen": 10490917376,
      "step": 36890,
      "train_runtime": 359353.3229,
      "train_tokens_per_second": 29193.879
    },
    {
      "epoch": 1.3055945617825464,
      "grad_norm": 1.5,
      "learning_rate": 2.3088100970093966e-05,
      "loss": 1.0495441436767579,
      "num_input_tokens_seen": 10493685440,
      "step": 36900,
      "train_runtime": 359447.878,
      "train_tokens_per_second": 29193.9
    },
    {
      "epoch": 1.3059483820462754,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3085639893160527e-05,
      "loss": 1.0380681037902832,
      "num_input_tokens_seen": 10496578880,
      "step": 36910,
      "train_runtime": 359549.4819,
      "train_tokens_per_second": 29193.698
    },
    {
      "epoch": 1.306302202310004,
      "grad_norm": 1.609375,
      "learning_rate": 2.3083179603075084e-05,
      "loss": 1.0462970733642578,
      "num_input_tokens_seen": 10499381056,
      "step": 36920,
      "train_runtime": 359645.8663,
      "train_tokens_per_second": 29193.665
    },
    {
      "epoch": 1.306656022573733,
      "grad_norm": 1.484375,
      "learning_rate": 2.308072009941845e-05,
      "loss": 1.0414505004882812,
      "num_input_tokens_seen": 10502223168,
      "step": 36930,
      "train_runtime": 359742.3527,
      "train_tokens_per_second": 29193.736
    },
    {
      "epoch": 1.3070098428374615,
      "grad_norm": 1.53125,
      "learning_rate": 2.3078261381771748e-05,
      "loss": 1.0640272140502929,
      "num_input_tokens_seen": 10505056384,
      "step": 36940,
      "train_runtime": 359841.468,
      "train_tokens_per_second": 29193.568
    },
    {
      "epoch": 1.3073636631011905,
      "grad_norm": 1.453125,
      "learning_rate": 2.3075803449716407e-05,
      "loss": 1.0454618453979492,
      "num_input_tokens_seen": 10507953088,
      "step": 36950,
      "train_runtime": 359942.0,
      "train_tokens_per_second": 29193.462
    },
    {
      "epoch": 1.3077174833649192,
      "grad_norm": 1.53125,
      "learning_rate": 2.3073346302834174e-05,
      "loss": 1.0460451126098633,
      "num_input_tokens_seen": 10510797760,
      "step": 36960,
      "train_runtime": 360038.7672,
      "train_tokens_per_second": 29193.517
    },
    {
      "epoch": 1.308071303628648,
      "grad_norm": 1.5078125,
      "learning_rate": 2.3070889940707103e-05,
      "loss": 1.0400960922241211,
      "num_input_tokens_seen": 10513629440,
      "step": 36970,
      "train_runtime": 360133.4219,
      "train_tokens_per_second": 29193.707
    },
    {
      "epoch": 1.3084251238923768,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3068434362917562e-05,
      "loss": 1.0526330947875977,
      "num_input_tokens_seen": 10516463040,
      "step": 36980,
      "train_runtime": 360231.1379,
      "train_tokens_per_second": 29193.654
    },
    {
      "epoch": 1.3087789441561055,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3065979569048235e-05,
      "loss": 1.0522574424743651,
      "num_input_tokens_seen": 10519315840,
      "step": 36990,
      "train_runtime": 360330.1459,
      "train_tokens_per_second": 29193.549
    },
    {
      "epoch": 1.3091327644198343,
      "grad_norm": 1.5703125,
      "learning_rate": 2.306352555868211e-05,
      "loss": 1.0494985580444336,
      "num_input_tokens_seen": 10522161280,
      "step": 37000,
      "train_runtime": 360431.9766,
      "train_tokens_per_second": 29193.196
    },
    {
      "epoch": 1.309486584683563,
      "grad_norm": 1.578125,
      "learning_rate": 2.3061072331402486e-05,
      "loss": 1.0393866539001464,
      "num_input_tokens_seen": 10525001856,
      "step": 37010,
      "train_runtime": 360529.6753,
      "train_tokens_per_second": 29193.164
    },
    {
      "epoch": 1.3098404049472918,
      "grad_norm": 1.484375,
      "learning_rate": 2.3058619886792977e-05,
      "loss": 1.056252670288086,
      "num_input_tokens_seen": 10527894912,
      "step": 37020,
      "train_runtime": 360631.0474,
      "train_tokens_per_second": 29192.98
    },
    {
      "epoch": 1.3101942252110206,
      "grad_norm": 1.5234375,
      "learning_rate": 2.30561682244375e-05,
      "loss": 1.0535904884338378,
      "num_input_tokens_seen": 10530746304,
      "step": 37030,
      "train_runtime": 360728.3462,
      "train_tokens_per_second": 29193.01
    },
    {
      "epoch": 1.3105480454747493,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3053717343920285e-05,
      "loss": 1.0243169784545898,
      "num_input_tokens_seen": 10533536064,
      "step": 37040,
      "train_runtime": 360820.2445,
      "train_tokens_per_second": 29193.307
    },
    {
      "epoch": 1.3109018657384781,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3051267244825882e-05,
      "loss": 1.0444095611572266,
      "num_input_tokens_seen": 10536402112,
      "step": 37050,
      "train_runtime": 360920.2751,
      "train_tokens_per_second": 29193.157
    },
    {
      "epoch": 1.3112556860022069,
      "grad_norm": 1.5546875,
      "learning_rate": 2.3048817926739122e-05,
      "loss": 1.0551862716674805,
      "num_input_tokens_seen": 10539198208,
      "step": 37060,
      "train_runtime": 361015.5745,
      "train_tokens_per_second": 29193.195
    },
    {
      "epoch": 1.3116095062659356,
      "grad_norm": 1.609375,
      "learning_rate": 2.3046369389245177e-05,
      "loss": 1.0470331192016602,
      "num_input_tokens_seen": 10542040704,
      "step": 37070,
      "train_runtime": 361112.5169,
      "train_tokens_per_second": 29193.23
    },
    {
      "epoch": 1.3119633265296646,
      "grad_norm": 1.53125,
      "learning_rate": 2.3043921631929502e-05,
      "loss": 1.0484514236450195,
      "num_input_tokens_seen": 10544857600,
      "step": 37080,
      "train_runtime": 361207.7265,
      "train_tokens_per_second": 29193.333
    },
    {
      "epoch": 1.3123171467933932,
      "grad_norm": 1.546875,
      "learning_rate": 2.304147465437788e-05,
      "loss": 1.0424309730529786,
      "num_input_tokens_seen": 10547648128,
      "step": 37090,
      "train_runtime": 361304.6019,
      "train_tokens_per_second": 29193.229
    },
    {
      "epoch": 1.3126709670571222,
      "grad_norm": 1.46875,
      "learning_rate": 2.3039028456176388e-05,
      "loss": 1.060536003112793,
      "num_input_tokens_seen": 10550496320,
      "step": 37100,
      "train_runtime": 361403.2622,
      "train_tokens_per_second": 29193.141
    },
    {
      "epoch": 1.313024787320851,
      "grad_norm": 1.515625,
      "learning_rate": 2.3036583036911418e-05,
      "loss": 1.049647331237793,
      "num_input_tokens_seen": 10553359488,
      "step": 37110,
      "train_runtime": 361502.7992,
      "train_tokens_per_second": 29193.023
    },
    {
      "epoch": 1.3133786075845797,
      "grad_norm": 1.53125,
      "learning_rate": 2.3034138396169667e-05,
      "loss": 1.0355438232421874,
      "num_input_tokens_seen": 10556238080,
      "step": 37120,
      "train_runtime": 361603.0356,
      "train_tokens_per_second": 29192.891
    },
    {
      "epoch": 1.3137324278483085,
      "grad_norm": 1.5625,
      "learning_rate": 2.3031694533538127e-05,
      "loss": 1.0470772743225099,
      "num_input_tokens_seen": 10559099584,
      "step": 37130,
      "train_runtime": 361699.7392,
      "train_tokens_per_second": 29192.998
    },
    {
      "epoch": 1.3140862481120372,
      "grad_norm": 1.453125,
      "learning_rate": 2.302925144860413e-05,
      "loss": 1.0470949172973634,
      "num_input_tokens_seen": 10561887616,
      "step": 37140,
      "train_runtime": 361791.5918,
      "train_tokens_per_second": 29193.292
    },
    {
      "epoch": 1.314440068375766,
      "grad_norm": 1.53125,
      "learning_rate": 2.302680914095527e-05,
      "loss": 1.0452104568481446,
      "num_input_tokens_seen": 10564708288,
      "step": 37150,
      "train_runtime": 361887.7339,
      "train_tokens_per_second": 29193.331
    },
    {
      "epoch": 1.3147938886394948,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3024367610179485e-05,
      "loss": 1.0486051559448242,
      "num_input_tokens_seen": 10567546368,
      "step": 37160,
      "train_runtime": 361984.4615,
      "train_tokens_per_second": 29193.37
    },
    {
      "epoch": 1.3151477089032235,
      "grad_norm": 1.5390625,
      "learning_rate": 2.3021926855864995e-05,
      "loss": 1.0471332550048829,
      "num_input_tokens_seen": 10570346432,
      "step": 37170,
      "train_runtime": 362078.2656,
      "train_tokens_per_second": 29193.54
    },
    {
      "epoch": 1.3155015291669523,
      "grad_norm": 1.5234375,
      "learning_rate": 2.3019486877600337e-05,
      "loss": 1.0480123519897462,
      "num_input_tokens_seen": 10573251008,
      "step": 37180,
      "train_runtime": 362180.6668,
      "train_tokens_per_second": 29193.306
    },
    {
      "epoch": 1.315855349430681,
      "grad_norm": 1.6015625,
      "learning_rate": 2.3017047674974354e-05,
      "loss": 1.0487049102783204,
      "num_input_tokens_seen": 10576018752,
      "step": 37190,
      "train_runtime": 362275.3999,
      "train_tokens_per_second": 29193.312
    },
    {
      "epoch": 1.3162091696944098,
      "grad_norm": 1.5859375,
      "learning_rate": 2.301460924757618e-05,
      "loss": 1.040346622467041,
      "num_input_tokens_seen": 10578802304,
      "step": 37200,
      "train_runtime": 362367.6879,
      "train_tokens_per_second": 29193.559
    },
    {
      "epoch": 1.3165629899581386,
      "grad_norm": 1.6015625,
      "learning_rate": 2.3012171594995272e-05,
      "loss": 1.059952735900879,
      "num_input_tokens_seen": 10581651136,
      "step": 37210,
      "train_runtime": 362466.1534,
      "train_tokens_per_second": 29193.488
    },
    {
      "epoch": 1.3169168102218674,
      "grad_norm": 1.5625,
      "learning_rate": 2.3009734716821385e-05,
      "loss": 1.0498506546020507,
      "num_input_tokens_seen": 10584571264,
      "step": 37220,
      "train_runtime": 362567.7144,
      "train_tokens_per_second": 29193.364
    },
    {
      "epoch": 1.3172706304855961,
      "grad_norm": 1.5625,
      "learning_rate": 2.3007298612644562e-05,
      "loss": 1.0539627075195312,
      "num_input_tokens_seen": 10587413376,
      "step": 37230,
      "train_runtime": 362663.781,
      "train_tokens_per_second": 29193.468
    },
    {
      "epoch": 1.3176244507493249,
      "grad_norm": 1.515625,
      "learning_rate": 2.3004863282055178e-05,
      "loss": 1.0466215133666992,
      "num_input_tokens_seen": 10590196160,
      "step": 37240,
      "train_runtime": 362758.2299,
      "train_tokens_per_second": 29193.538
    },
    {
      "epoch": 1.3179782710130539,
      "grad_norm": 1.5546875,
      "learning_rate": 2.300242872464389e-05,
      "loss": 1.0482284545898437,
      "num_input_tokens_seen": 10593082240,
      "step": 37250,
      "train_runtime": 362857.7112,
      "train_tokens_per_second": 29193.488
    },
    {
      "epoch": 1.3183320912767824,
      "grad_norm": 1.484375,
      "learning_rate": 2.299999494000167e-05,
      "loss": 1.0472142219543457,
      "num_input_tokens_seen": 10595914944,
      "step": 37260,
      "train_runtime": 362955.8532,
      "train_tokens_per_second": 29193.399
    },
    {
      "epoch": 1.3186859115405114,
      "grad_norm": 1.5,
      "learning_rate": 2.299756192771979e-05,
      "loss": 1.039475917816162,
      "num_input_tokens_seen": 10598733952,
      "step": 37270,
      "train_runtime": 363050.1718,
      "train_tokens_per_second": 29193.579
    },
    {
      "epoch": 1.3190397318042402,
      "grad_norm": 1.5546875,
      "learning_rate": 2.299512968738981e-05,
      "loss": 1.0451589584350587,
      "num_input_tokens_seen": 10601590592,
      "step": 37280,
      "train_runtime": 363149.8771,
      "train_tokens_per_second": 29193.43
    },
    {
      "epoch": 1.319393552067969,
      "grad_norm": 1.625,
      "learning_rate": 2.2992698218603617e-05,
      "loss": 1.0418299674987792,
      "num_input_tokens_seen": 10604454208,
      "step": 37290,
      "train_runtime": 363247.5556,
      "train_tokens_per_second": 29193.463
    },
    {
      "epoch": 1.3197473723316977,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2990267520953383e-05,
      "loss": 1.0479687690734862,
      "num_input_tokens_seen": 10607281792,
      "step": 37300,
      "train_runtime": 363345.4716,
      "train_tokens_per_second": 29193.378
    },
    {
      "epoch": 1.3201011925954265,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2987837594031587e-05,
      "loss": 1.0511348724365235,
      "num_input_tokens_seen": 10610142208,
      "step": 37310,
      "train_runtime": 363444.6193,
      "train_tokens_per_second": 29193.285
    },
    {
      "epoch": 1.3204550128591552,
      "grad_norm": 1.5,
      "learning_rate": 2.2985408437431016e-05,
      "loss": 1.0417060852050781,
      "num_input_tokens_seen": 10613000000,
      "step": 37320,
      "train_runtime": 363540.8964,
      "train_tokens_per_second": 29193.414
    },
    {
      "epoch": 1.320808833122884,
      "grad_norm": 1.4609375,
      "learning_rate": 2.2982980050744743e-05,
      "loss": 1.0559803009033204,
      "num_input_tokens_seen": 10615812480,
      "step": 37330,
      "train_runtime": 363637.1474,
      "train_tokens_per_second": 29193.421
    },
    {
      "epoch": 1.3211626533866128,
      "grad_norm": 1.4765625,
      "learning_rate": 2.2980552433566154e-05,
      "loss": 1.0329368591308594,
      "num_input_tokens_seen": 10618701824,
      "step": 37340,
      "train_runtime": 363738.4774,
      "train_tokens_per_second": 29193.232
    },
    {
      "epoch": 1.3215164736503415,
      "grad_norm": 1.53125,
      "learning_rate": 2.297812558548893e-05,
      "loss": 1.04880952835083,
      "num_input_tokens_seen": 10621494208,
      "step": 37350,
      "train_runtime": 363831.1856,
      "train_tokens_per_second": 29193.468
    },
    {
      "epoch": 1.3218702939140703,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2975699506107056e-05,
      "loss": 1.067913818359375,
      "num_input_tokens_seen": 10624335168,
      "step": 37360,
      "train_runtime": 363930.6256,
      "train_tokens_per_second": 29193.298
    },
    {
      "epoch": 1.322224114177799,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2973274195014816e-05,
      "loss": 1.0308109283447267,
      "num_input_tokens_seen": 10627284608,
      "step": 37370,
      "train_runtime": 364035.4673,
      "train_tokens_per_second": 29192.992
    },
    {
      "epoch": 1.3225779344415278,
      "grad_norm": 1.484375,
      "learning_rate": 2.2970849651806796e-05,
      "loss": 1.049750518798828,
      "num_input_tokens_seen": 10630163712,
      "step": 37380,
      "train_runtime": 364132.7308,
      "train_tokens_per_second": 29193.101
    },
    {
      "epoch": 1.3229317547052566,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2968425876077866e-05,
      "loss": 1.049171543121338,
      "num_input_tokens_seen": 10633005760,
      "step": 37390,
      "train_runtime": 364229.1151,
      "train_tokens_per_second": 29193.179
    },
    {
      "epoch": 1.3232855749689856,
      "grad_norm": 1.578125,
      "learning_rate": 2.2966002867423225e-05,
      "loss": 1.0560935974121093,
      "num_input_tokens_seen": 10635808064,
      "step": 37400,
      "train_runtime": 364326.6627,
      "train_tokens_per_second": 29193.054
    },
    {
      "epoch": 1.3236393952327141,
      "grad_norm": 1.53125,
      "learning_rate": 2.296358062543834e-05,
      "loss": 1.0479181289672852,
      "num_input_tokens_seen": 10638664576,
      "step": 37410,
      "train_runtime": 364426.5396,
      "train_tokens_per_second": 29192.892
    },
    {
      "epoch": 1.323993215496443,
      "grad_norm": 1.53125,
      "learning_rate": 2.2961159149718993e-05,
      "loss": 1.0485272407531738,
      "num_input_tokens_seen": 10641406976,
      "step": 37420,
      "train_runtime": 364518.9866,
      "train_tokens_per_second": 29193.012
    },
    {
      "epoch": 1.3243470357601717,
      "grad_norm": 1.625,
      "learning_rate": 2.295873843986126e-05,
      "loss": 1.052652931213379,
      "num_input_tokens_seen": 10644213824,
      "step": 37430,
      "train_runtime": 364615.4912,
      "train_tokens_per_second": 29192.983
    },
    {
      "epoch": 1.3247008560239006,
      "grad_norm": 1.5703125,
      "learning_rate": 2.2956318495461526e-05,
      "loss": 1.0435104370117188,
      "num_input_tokens_seen": 10647067776,
      "step": 37440,
      "train_runtime": 364714.4911,
      "train_tokens_per_second": 29192.884
    },
    {
      "epoch": 1.3250546762876294,
      "grad_norm": 1.5859375,
      "learning_rate": 2.295389931611645e-05,
      "loss": 1.0460174560546875,
      "num_input_tokens_seen": 10649914880,
      "step": 37450,
      "train_runtime": 364810.0318,
      "train_tokens_per_second": 29193.043
    },
    {
      "epoch": 1.3254084965513582,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2951480901423017e-05,
      "loss": 1.0481403350830079,
      "num_input_tokens_seen": 10652834368,
      "step": 37460,
      "train_runtime": 364912.1996,
      "train_tokens_per_second": 29192.87
    },
    {
      "epoch": 1.325762316815087,
      "grad_norm": 1.5625,
      "learning_rate": 2.294906325097848e-05,
      "loss": 1.0586639404296876,
      "num_input_tokens_seen": 10655695232,
      "step": 37470,
      "train_runtime": 365009.8971,
      "train_tokens_per_second": 29192.894
    },
    {
      "epoch": 1.3261161370788157,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2946646364380415e-05,
      "loss": 1.0358417510986329,
      "num_input_tokens_seen": 10658500800,
      "step": 37480,
      "train_runtime": 365106.6769,
      "train_tokens_per_second": 29192.84
    },
    {
      "epoch": 1.3264699573425445,
      "grad_norm": 1.5859375,
      "learning_rate": 2.294423024122668e-05,
      "loss": 1.0429515838623047,
      "num_input_tokens_seen": 10661347136,
      "step": 37490,
      "train_runtime": 365204.6142,
      "train_tokens_per_second": 29192.805
    },
    {
      "epoch": 1.3268237776062732,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2941814881115428e-05,
      "loss": 1.0570093154907227,
      "num_input_tokens_seen": 10664161344,
      "step": 37500,
      "train_runtime": 365301.5558,
      "train_tokens_per_second": 29192.762
    },
    {
      "epoch": 1.327177597870002,
      "grad_norm": 1.46875,
      "learning_rate": 2.293940028364512e-05,
      "loss": 1.0468643188476563,
      "num_input_tokens_seen": 10666978752,
      "step": 37510,
      "train_runtime": 365399.3638,
      "train_tokens_per_second": 29192.658
    },
    {
      "epoch": 1.3275314181337308,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2936986448414498e-05,
      "loss": 1.0379514694213867,
      "num_input_tokens_seen": 10669854080,
      "step": 37520,
      "train_runtime": 365496.4374,
      "train_tokens_per_second": 29192.772
    },
    {
      "epoch": 1.3278852383974595,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2934573375022613e-05,
      "loss": 1.0594658851623535,
      "num_input_tokens_seen": 10672654272,
      "step": 37530,
      "train_runtime": 365593.325,
      "train_tokens_per_second": 29192.695
    },
    {
      "epoch": 1.3282390586611883,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2932161063068803e-05,
      "loss": 1.0419137954711915,
      "num_input_tokens_seen": 10675512896,
      "step": 37540,
      "train_runtime": 365691.8176,
      "train_tokens_per_second": 29192.649
    },
    {
      "epoch": 1.328592878924917,
      "grad_norm": 1.59375,
      "learning_rate": 2.29297495121527e-05,
      "loss": 1.0442682266235352,
      "num_input_tokens_seen": 10678393792,
      "step": 37550,
      "train_runtime": 365790.8259,
      "train_tokens_per_second": 29192.623
    },
    {
      "epoch": 1.3289466991886458,
      "grad_norm": 1.5078125,
      "learning_rate": 2.2927338721874245e-05,
      "loss": 1.0362014770507812,
      "num_input_tokens_seen": 10681257408,
      "step": 37560,
      "train_runtime": 365889.998,
      "train_tokens_per_second": 29192.537
    },
    {
      "epoch": 1.3293005194523748,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2924928691833646e-05,
      "loss": 1.0445623397827148,
      "num_input_tokens_seen": 10684109248,
      "step": 37570,
      "train_runtime": 365986.626,
      "train_tokens_per_second": 29192.622
    },
    {
      "epoch": 1.3296543397161034,
      "grad_norm": 1.5625,
      "learning_rate": 2.292251942163143e-05,
      "loss": 1.0484098434448241,
      "num_input_tokens_seen": 10686949504,
      "step": 37580,
      "train_runtime": 366087.4075,
      "train_tokens_per_second": 29192.344
    },
    {
      "epoch": 1.3300081599798323,
      "grad_norm": 1.4921875,
      "learning_rate": 2.292011091086841e-05,
      "loss": 1.0334796905517578,
      "num_input_tokens_seen": 10689757504,
      "step": 37590,
      "train_runtime": 366181.5396,
      "train_tokens_per_second": 29192.508
    },
    {
      "epoch": 1.330361980243561,
      "grad_norm": 1.5078125,
      "learning_rate": 2.291770315914569e-05,
      "loss": 1.0423398971557618,
      "num_input_tokens_seen": 10692563456,
      "step": 37600,
      "train_runtime": 366277.8288,
      "train_tokens_per_second": 29192.494
    },
    {
      "epoch": 1.3307158005072899,
      "grad_norm": 1.4921875,
      "learning_rate": 2.291529616606466e-05,
      "loss": 1.0493038177490235,
      "num_input_tokens_seen": 10695440576,
      "step": 37610,
      "train_runtime": 366376.3963,
      "train_tokens_per_second": 29192.494
    },
    {
      "epoch": 1.3310696207710186,
      "grad_norm": 1.4921875,
      "learning_rate": 2.291288993122703e-05,
      "loss": 1.0501667976379394,
      "num_input_tokens_seen": 10698309440,
      "step": 37620,
      "train_runtime": 366472.7048,
      "train_tokens_per_second": 29192.65
    },
    {
      "epoch": 1.3314234410347474,
      "grad_norm": 1.5625,
      "learning_rate": 2.291048445423477e-05,
      "loss": 1.048077392578125,
      "num_input_tokens_seen": 10701123648,
      "step": 37630,
      "train_runtime": 366568.6515,
      "train_tokens_per_second": 29192.686
    },
    {
      "epoch": 1.3317772612984762,
      "grad_norm": 1.484375,
      "learning_rate": 2.2908079734690165e-05,
      "loss": 1.0443392753601075,
      "num_input_tokens_seen": 10704008128,
      "step": 37640,
      "train_runtime": 366670.0941,
      "train_tokens_per_second": 29192.477
    },
    {
      "epoch": 1.332131081562205,
      "grad_norm": 1.6171875,
      "learning_rate": 2.290567577219578e-05,
      "loss": 1.0704610824584961,
      "num_input_tokens_seen": 10706837312,
      "step": 37650,
      "train_runtime": 366769.1874,
      "train_tokens_per_second": 29192.303
    },
    {
      "epoch": 1.3324849018259337,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2903272566354474e-05,
      "loss": 1.042983627319336,
      "num_input_tokens_seen": 10709667584,
      "step": 37660,
      "train_runtime": 366865.0044,
      "train_tokens_per_second": 29192.394
    },
    {
      "epoch": 1.3328387220896625,
      "grad_norm": 1.46875,
      "learning_rate": 2.2900870116769398e-05,
      "loss": 1.0343786239624024,
      "num_input_tokens_seen": 10712546048,
      "step": 37670,
      "train_runtime": 366964.9715,
      "train_tokens_per_second": 29192.285
    },
    {
      "epoch": 1.3331925423533912,
      "grad_norm": 1.5546875,
      "learning_rate": 2.289846842304401e-05,
      "loss": 1.043423557281494,
      "num_input_tokens_seen": 10715385920,
      "step": 37680,
      "train_runtime": 367057.8568,
      "train_tokens_per_second": 29192.635
    },
    {
      "epoch": 1.33354636261712,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2896067484782027e-05,
      "loss": 1.050009822845459,
      "num_input_tokens_seen": 10718208256,
      "step": 37690,
      "train_runtime": 367154.1342,
      "train_tokens_per_second": 29192.667
    },
    {
      "epoch": 1.3339001828808488,
      "grad_norm": 1.578125,
      "learning_rate": 2.2893667301587484e-05,
      "loss": 1.0511722564697266,
      "num_input_tokens_seen": 10721053248,
      "step": 37700,
      "train_runtime": 367249.7636,
      "train_tokens_per_second": 29192.812
    },
    {
      "epoch": 1.3342540031445775,
      "grad_norm": 1.5078125,
      "learning_rate": 2.28912678730647e-05,
      "loss": 1.0508247375488282,
      "num_input_tokens_seen": 10723918528,
      "step": 37710,
      "train_runtime": 367347.8904,
      "train_tokens_per_second": 29192.814
    },
    {
      "epoch": 1.3346078234083063,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2888869198818276e-05,
      "loss": 1.0328415870666503,
      "num_input_tokens_seen": 10726782400,
      "step": 37720,
      "train_runtime": 367446.9201,
      "train_tokens_per_second": 29192.74
    },
    {
      "epoch": 1.334961643672035,
      "grad_norm": 1.578125,
      "learning_rate": 2.288647127845311e-05,
      "loss": 1.0424562454223634,
      "num_input_tokens_seen": 10729592704,
      "step": 37730,
      "train_runtime": 367541.9129,
      "train_tokens_per_second": 29192.841
    },
    {
      "epoch": 1.335315463935764,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2884074111574384e-05,
      "loss": 1.0430944442749024,
      "num_input_tokens_seen": 10732409408,
      "step": 37740,
      "train_runtime": 367636.6224,
      "train_tokens_per_second": 29192.982
    },
    {
      "epoch": 1.3356692841994926,
      "grad_norm": 1.515625,
      "learning_rate": 2.2881677697787584e-05,
      "loss": 1.0337045669555665,
      "num_input_tokens_seen": 10735275520,
      "step": 37750,
      "train_runtime": 367736.6107,
      "train_tokens_per_second": 29192.839
    },
    {
      "epoch": 1.3360231044632216,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2879282036698465e-05,
      "loss": 1.049667739868164,
      "num_input_tokens_seen": 10738120000,
      "step": 37760,
      "train_runtime": 367832.9363,
      "train_tokens_per_second": 29192.927
    },
    {
      "epoch": 1.3363769247269501,
      "grad_norm": 1.5703125,
      "learning_rate": 2.2876887127913084e-05,
      "loss": 1.0456581115722656,
      "num_input_tokens_seen": 10740943936,
      "step": 37770,
      "train_runtime": 367931.2216,
      "train_tokens_per_second": 29192.804
    },
    {
      "epoch": 1.3367307449906791,
      "grad_norm": 1.6015625,
      "learning_rate": 2.2874492971037785e-05,
      "loss": 1.0321878433227538,
      "num_input_tokens_seen": 10743787392,
      "step": 37780,
      "train_runtime": 368027.5706,
      "train_tokens_per_second": 29192.887
    },
    {
      "epoch": 1.3370845652544079,
      "grad_norm": 1.515625,
      "learning_rate": 2.2872099565679195e-05,
      "loss": 1.0337953567504883,
      "num_input_tokens_seen": 10746590016,
      "step": 37790,
      "train_runtime": 368121.1745,
      "train_tokens_per_second": 29193.078
    },
    {
      "epoch": 1.3374383855181367,
      "grad_norm": 1.5625,
      "learning_rate": 2.2869706911444235e-05,
      "loss": 1.0514656066894532,
      "num_input_tokens_seen": 10749435136,
      "step": 37800,
      "train_runtime": 368216.9394,
      "train_tokens_per_second": 29193.212
    },
    {
      "epoch": 1.3377922057818654,
      "grad_norm": 1.5625,
      "learning_rate": 2.286731500794011e-05,
      "loss": 1.0550714492797852,
      "num_input_tokens_seen": 10752276416,
      "step": 37810,
      "train_runtime": 368317.9765,
      "train_tokens_per_second": 29192.918
    },
    {
      "epoch": 1.3381460260455942,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2864923854774315e-05,
      "loss": 1.0470369338989258,
      "num_input_tokens_seen": 10755136384,
      "step": 37820,
      "train_runtime": 368413.7625,
      "train_tokens_per_second": 29193.091
    },
    {
      "epoch": 1.338499846309323,
      "grad_norm": 1.5859375,
      "learning_rate": 2.286253345155463e-05,
      "loss": 1.053567886352539,
      "num_input_tokens_seen": 10758000256,
      "step": 37830,
      "train_runtime": 368510.5016,
      "train_tokens_per_second": 29193.199
    },
    {
      "epoch": 1.3388536665730517,
      "grad_norm": 1.484375,
      "learning_rate": 2.286014379788912e-05,
      "loss": 1.0579944610595704,
      "num_input_tokens_seen": 10760865920,
      "step": 37840,
      "train_runtime": 368609.1138,
      "train_tokens_per_second": 29193.163
    },
    {
      "epoch": 1.3392074868367805,
      "grad_norm": 1.53125,
      "learning_rate": 2.285775489338615e-05,
      "loss": 1.0434446334838867,
      "num_input_tokens_seen": 10763731520,
      "step": 37850,
      "train_runtime": 368709.1949,
      "train_tokens_per_second": 29193.011
    },
    {
      "epoch": 1.3395613071005092,
      "grad_norm": 1.5625,
      "learning_rate": 2.285536673765435e-05,
      "loss": 1.0287858963012695,
      "num_input_tokens_seen": 10766653312,
      "step": 37860,
      "train_runtime": 368811.8285,
      "train_tokens_per_second": 29192.809
    },
    {
      "epoch": 1.339915127364238,
      "grad_norm": 1.546875,
      "learning_rate": 2.285297933030265e-05,
      "loss": 1.0378787994384766,
      "num_input_tokens_seen": 10769527616,
      "step": 37870,
      "train_runtime": 368910.9243,
      "train_tokens_per_second": 29192.759
    },
    {
      "epoch": 1.3402689476279668,
      "grad_norm": 1.6015625,
      "learning_rate": 2.2850592670940272e-05,
      "loss": 1.0429025650024415,
      "num_input_tokens_seen": 10772364544,
      "step": 37880,
      "train_runtime": 369007.365,
      "train_tokens_per_second": 29192.817
    },
    {
      "epoch": 1.3406227678916955,
      "grad_norm": 1.53125,
      "learning_rate": 2.2848206759176703e-05,
      "loss": 1.0434407234191894,
      "num_input_tokens_seen": 10775186496,
      "step": 37890,
      "train_runtime": 369100.4314,
      "train_tokens_per_second": 29193.102
    },
    {
      "epoch": 1.3409765881554243,
      "grad_norm": 1.5078125,
      "learning_rate": 2.284582159462173e-05,
      "loss": 1.0480441093444823,
      "num_input_tokens_seen": 10778001152,
      "step": 37900,
      "train_runtime": 369195.2968,
      "train_tokens_per_second": 29193.224
    },
    {
      "epoch": 1.3413304084191533,
      "grad_norm": 1.546875,
      "learning_rate": 2.284343717688543e-05,
      "loss": 1.0453269958496094,
      "num_input_tokens_seen": 10780771584,
      "step": 37910,
      "train_runtime": 369287.2883,
      "train_tokens_per_second": 29193.454
    },
    {
      "epoch": 1.3416842286828818,
      "grad_norm": 1.5078125,
      "learning_rate": 2.284105350557815e-05,
      "loss": 1.0328609466552734,
      "num_input_tokens_seen": 10783595904,
      "step": 37920,
      "train_runtime": 369383.1361,
      "train_tokens_per_second": 29193.525
    },
    {
      "epoch": 1.3420380489466108,
      "grad_norm": 1.515625,
      "learning_rate": 2.2838670580310526e-05,
      "loss": 1.039613914489746,
      "num_input_tokens_seen": 10786434432,
      "step": 37930,
      "train_runtime": 369481.2058,
      "train_tokens_per_second": 29193.459
    },
    {
      "epoch": 1.3423918692103396,
      "grad_norm": 1.5546875,
      "learning_rate": 2.283628840069349e-05,
      "loss": 1.0377912521362305,
      "num_input_tokens_seen": 10789229440,
      "step": 37940,
      "train_runtime": 369579.1883,
      "train_tokens_per_second": 29193.282
    },
    {
      "epoch": 1.3427456894740684,
      "grad_norm": 1.53125,
      "learning_rate": 2.2833906966338237e-05,
      "loss": 1.0440091133117675,
      "num_input_tokens_seen": 10792035136,
      "step": 37950,
      "train_runtime": 369672.9616,
      "train_tokens_per_second": 29193.466
    },
    {
      "epoch": 1.3430995097377971,
      "grad_norm": 1.578125,
      "learning_rate": 2.2831526276856274e-05,
      "loss": 1.037813663482666,
      "num_input_tokens_seen": 10794873920,
      "step": 37960,
      "train_runtime": 369770.0977,
      "train_tokens_per_second": 29193.475
    },
    {
      "epoch": 1.343453330001526,
      "grad_norm": 1.5,
      "learning_rate": 2.282914633185936e-05,
      "loss": 1.061992359161377,
      "num_input_tokens_seen": 10797723776,
      "step": 37970,
      "train_runtime": 369866.8627,
      "train_tokens_per_second": 29193.542
    },
    {
      "epoch": 1.3438071502652547,
      "grad_norm": 1.6015625,
      "learning_rate": 2.282676713095956e-05,
      "loss": 1.044581127166748,
      "num_input_tokens_seen": 10800582464,
      "step": 37980,
      "train_runtime": 369964.185,
      "train_tokens_per_second": 29193.589
    },
    {
      "epoch": 1.3441609705289834,
      "grad_norm": 1.59375,
      "learning_rate": 2.2824388673769212e-05,
      "loss": 1.0455829620361328,
      "num_input_tokens_seen": 10803405056,
      "step": 37990,
      "train_runtime": 370061.1766,
      "train_tokens_per_second": 29193.565
    },
    {
      "epoch": 1.3445147907927122,
      "grad_norm": 1.5234375,
      "learning_rate": 2.282201095990094e-05,
      "loss": 1.0459413528442383,
      "num_input_tokens_seen": 10806262080,
      "step": 38000,
      "train_runtime": 370157.6813,
      "train_tokens_per_second": 29193.672
    },
    {
      "epoch": 1.344868611056441,
      "grad_norm": 1.546875,
      "learning_rate": 2.281963398896765e-05,
      "loss": 1.048223114013672,
      "num_input_tokens_seen": 10809123968,
      "step": 38010,
      "train_runtime": 370256.9081,
      "train_tokens_per_second": 29193.578
    },
    {
      "epoch": 1.3452224313201697,
      "grad_norm": 1.6015625,
      "learning_rate": 2.281725776058253e-05,
      "loss": 1.0246917724609375,
      "num_input_tokens_seen": 10812005120,
      "step": 38020,
      "train_runtime": 370357.3558,
      "train_tokens_per_second": 29193.44
    },
    {
      "epoch": 1.3455762515838985,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2814882274359045e-05,
      "loss": 1.0537096977233886,
      "num_input_tokens_seen": 10814812608,
      "step": 38030,
      "train_runtime": 370452.8941,
      "train_tokens_per_second": 29193.489
    },
    {
      "epoch": 1.3459300718476273,
      "grad_norm": 1.46875,
      "learning_rate": 2.2812507529910955e-05,
      "loss": 1.0459613800048828,
      "num_input_tokens_seen": 10817676160,
      "step": 38040,
      "train_runtime": 370554.17,
      "train_tokens_per_second": 29193.238
    },
    {
      "epoch": 1.346283892111356,
      "grad_norm": 1.5,
      "learning_rate": 2.2810133526852288e-05,
      "loss": 1.0511150360107422,
      "num_input_tokens_seen": 10820531584,
      "step": 38050,
      "train_runtime": 370649.4579,
      "train_tokens_per_second": 29193.437
    },
    {
      "epoch": 1.3466377123750848,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2807760264797352e-05,
      "loss": 1.0667016983032227,
      "num_input_tokens_seen": 10823374656,
      "step": 38060,
      "train_runtime": 370744.4697,
      "train_tokens_per_second": 29193.624
    },
    {
      "epoch": 1.3469915326388135,
      "grad_norm": 1.4921875,
      "learning_rate": 2.280538774336075e-05,
      "loss": 1.0343782424926757,
      "num_input_tokens_seen": 10826221568,
      "step": 38070,
      "train_runtime": 370840.817,
      "train_tokens_per_second": 29193.716
    },
    {
      "epoch": 1.3473453529025425,
      "grad_norm": 1.5859375,
      "learning_rate": 2.280301596215735e-05,
      "loss": 1.0547415733337402,
      "num_input_tokens_seen": 10829106240,
      "step": 38080,
      "train_runtime": 370939.8092,
      "train_tokens_per_second": 29193.702
    },
    {
      "epoch": 1.347699173166271,
      "grad_norm": 1.53125,
      "learning_rate": 2.280064492080231e-05,
      "loss": 1.0488555908203125,
      "num_input_tokens_seen": 10831973376,
      "step": 38090,
      "train_runtime": 371041.1952,
      "train_tokens_per_second": 29193.452
    },
    {
      "epoch": 1.34805299343,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2798274618911075e-05,
      "loss": 1.0483903884887695,
      "num_input_tokens_seen": 10834827968,
      "step": 38100,
      "train_runtime": 371140.0945,
      "train_tokens_per_second": 29193.364
    },
    {
      "epoch": 1.3484068136937288,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2795905056099345e-05,
      "loss": 1.051621913909912,
      "num_input_tokens_seen": 10837663360,
      "step": 38110,
      "train_runtime": 371233.7794,
      "train_tokens_per_second": 29193.635
    },
    {
      "epoch": 1.3487606339574576,
      "grad_norm": 1.546875,
      "learning_rate": 2.2793536231983123e-05,
      "loss": 1.0459112167358398,
      "num_input_tokens_seen": 10840504384,
      "step": 38120,
      "train_runtime": 371331.5169,
      "train_tokens_per_second": 29193.602
    },
    {
      "epoch": 1.3491144542211864,
      "grad_norm": 1.59375,
      "learning_rate": 2.279116814617868e-05,
      "loss": 1.0426649093627929,
      "num_input_tokens_seen": 10843375552,
      "step": 38130,
      "train_runtime": 371430.7151,
      "train_tokens_per_second": 29193.535
    },
    {
      "epoch": 1.3494682744849151,
      "grad_norm": 1.578125,
      "learning_rate": 2.278880079830257e-05,
      "loss": 1.0565378189086914,
      "num_input_tokens_seen": 10846235072,
      "step": 38140,
      "train_runtime": 371525.0632,
      "train_tokens_per_second": 29193.818
    },
    {
      "epoch": 1.349822094748644,
      "grad_norm": 1.578125,
      "learning_rate": 2.278643418797163e-05,
      "loss": 1.0484249114990234,
      "num_input_tokens_seen": 10849056384,
      "step": 38150,
      "train_runtime": 371619.5522,
      "train_tokens_per_second": 29193.987
    },
    {
      "epoch": 1.3501759150123727,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2784068314802963e-05,
      "loss": 1.0410048484802246,
      "num_input_tokens_seen": 10851937984,
      "step": 38160,
      "train_runtime": 371721.2599,
      "train_tokens_per_second": 29193.751
    },
    {
      "epoch": 1.3505297352761014,
      "grad_norm": 1.5546875,
      "learning_rate": 2.278170317841396e-05,
      "loss": 1.0485618591308594,
      "num_input_tokens_seen": 10854759168,
      "step": 38170,
      "train_runtime": 371816.2537,
      "train_tokens_per_second": 29193.88
    },
    {
      "epoch": 1.3508835555398302,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2779338778422287e-05,
      "loss": 1.0510879516601563,
      "num_input_tokens_seen": 10857565568,
      "step": 38180,
      "train_runtime": 371913.2779,
      "train_tokens_per_second": 29193.81
    },
    {
      "epoch": 1.351237375803559,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2776975114445885e-05,
      "loss": 1.0606042861938476,
      "num_input_tokens_seen": 10860431872,
      "step": 38190,
      "train_runtime": 372013.3595,
      "train_tokens_per_second": 29193.661
    },
    {
      "epoch": 1.3515911960672877,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2774612186102988e-05,
      "loss": 1.0492417335510253,
      "num_input_tokens_seen": 10863265536,
      "step": 38200,
      "train_runtime": 372109.4626,
      "train_tokens_per_second": 29193.736
    },
    {
      "epoch": 1.3519450163310165,
      "grad_norm": 1.578125,
      "learning_rate": 2.277224999301208e-05,
      "loss": 1.0515697479248047,
      "num_input_tokens_seen": 10866100608,
      "step": 38210,
      "train_runtime": 372207.8186,
      "train_tokens_per_second": 29193.639
    },
    {
      "epoch": 1.3522988365947453,
      "grad_norm": 1.5078125,
      "learning_rate": 2.276988853479194e-05,
      "loss": 1.0494285583496095,
      "num_input_tokens_seen": 10868931328,
      "step": 38220,
      "train_runtime": 372308.2573,
      "train_tokens_per_second": 29193.366
    },
    {
      "epoch": 1.352652656858474,
      "grad_norm": 1.6484375,
      "learning_rate": 2.2767527811061636e-05,
      "loss": 1.0398226737976075,
      "num_input_tokens_seen": 10871714048,
      "step": 38230,
      "train_runtime": 372401.8912,
      "train_tokens_per_second": 29193.498
    },
    {
      "epoch": 1.3530064771222028,
      "grad_norm": 1.5625,
      "learning_rate": 2.2765167821440473e-05,
      "loss": 1.0515054702758788,
      "num_input_tokens_seen": 10874593664,
      "step": 38240,
      "train_runtime": 372500.9422,
      "train_tokens_per_second": 29193.466
    },
    {
      "epoch": 1.3533602973859318,
      "grad_norm": 1.5625,
      "learning_rate": 2.2762808565548063e-05,
      "loss": 1.0365448951721192,
      "num_input_tokens_seen": 10877424960,
      "step": 38250,
      "train_runtime": 372598.4795,
      "train_tokens_per_second": 29193.423
    },
    {
      "epoch": 1.3537141176496603,
      "grad_norm": 1.484375,
      "learning_rate": 2.2760450043004303e-05,
      "loss": 1.0534202575683593,
      "num_input_tokens_seen": 10880254464,
      "step": 38260,
      "train_runtime": 372696.0432,
      "train_tokens_per_second": 29193.373
    },
    {
      "epoch": 1.3540679379133893,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2758092253429327e-05,
      "loss": 1.0417467117309571,
      "num_input_tokens_seen": 10883046016,
      "step": 38270,
      "train_runtime": 372789.3301,
      "train_tokens_per_second": 29193.556
    },
    {
      "epoch": 1.354421758177118,
      "grad_norm": 1.5,
      "learning_rate": 2.2755735196443585e-05,
      "loss": 1.0656957626342773,
      "num_input_tokens_seen": 10885894336,
      "step": 38280,
      "train_runtime": 372887.323,
      "train_tokens_per_second": 29193.522
    },
    {
      "epoch": 1.3547755784408468,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2753378871667773e-05,
      "loss": 1.0613719940185546,
      "num_input_tokens_seen": 10888731584,
      "step": 38290,
      "train_runtime": 372984.4191,
      "train_tokens_per_second": 29193.529
    },
    {
      "epoch": 1.3551293987045756,
      "grad_norm": 1.6171875,
      "learning_rate": 2.275102327872288e-05,
      "loss": 1.0681971549987792,
      "num_input_tokens_seen": 10891600512,
      "step": 38300,
      "train_runtime": 373082.1422,
      "train_tokens_per_second": 29193.572
    },
    {
      "epoch": 1.3554832189683044,
      "grad_norm": 1.5234375,
      "learning_rate": 2.274866841723015e-05,
      "loss": 1.0517045974731445,
      "num_input_tokens_seen": 10894444864,
      "step": 38310,
      "train_runtime": 373176.4523,
      "train_tokens_per_second": 29193.816
    },
    {
      "epoch": 1.3558370392320331,
      "grad_norm": 1.515625,
      "learning_rate": 2.2746314286811134e-05,
      "loss": 1.052298355102539,
      "num_input_tokens_seen": 10897268608,
      "step": 38320,
      "train_runtime": 373274.0634,
      "train_tokens_per_second": 29193.747
    },
    {
      "epoch": 1.356190859495762,
      "grad_norm": 1.5703125,
      "learning_rate": 2.2743960887087616e-05,
      "loss": 1.0525511741638183,
      "num_input_tokens_seen": 10900054720,
      "step": 38330,
      "train_runtime": 373368.1292,
      "train_tokens_per_second": 29193.854
    },
    {
      "epoch": 1.3565446797594907,
      "grad_norm": 1.625,
      "learning_rate": 2.274160821768169e-05,
      "loss": 1.053469181060791,
      "num_input_tokens_seen": 10902898240,
      "step": 38340,
      "train_runtime": 373467.0976,
      "train_tokens_per_second": 29193.732
    },
    {
      "epoch": 1.3568985000232194,
      "grad_norm": 1.6328125,
      "learning_rate": 2.2739256278215697e-05,
      "loss": 1.0391500473022461,
      "num_input_tokens_seen": 10905727360,
      "step": 38350,
      "train_runtime": 373564.9207,
      "train_tokens_per_second": 29193.66
    },
    {
      "epoch": 1.3572523202869482,
      "grad_norm": 1.609375,
      "learning_rate": 2.273690506831227e-05,
      "loss": 1.0450399398803711,
      "num_input_tokens_seen": 10908560768,
      "step": 38360,
      "train_runtime": 373663.0007,
      "train_tokens_per_second": 29193.58
    },
    {
      "epoch": 1.357606140550677,
      "grad_norm": 1.53125,
      "learning_rate": 2.273455458759431e-05,
      "loss": 1.0413854598999024,
      "num_input_tokens_seen": 10911420800,
      "step": 38370,
      "train_runtime": 373759.5785,
      "train_tokens_per_second": 29193.689
    },
    {
      "epoch": 1.3579599608144057,
      "grad_norm": 1.5703125,
      "learning_rate": 2.2732204835684982e-05,
      "loss": 1.0510250091552735,
      "num_input_tokens_seen": 10914297472,
      "step": 38380,
      "train_runtime": 373858.6826,
      "train_tokens_per_second": 29193.644
    },
    {
      "epoch": 1.3583137810781345,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2729855812207737e-05,
      "loss": 1.0506999015808105,
      "num_input_tokens_seen": 10917116480,
      "step": 38390,
      "train_runtime": 373955.0688,
      "train_tokens_per_second": 29193.658
    },
    {
      "epoch": 1.3586676013418635,
      "grad_norm": 1.5703125,
      "learning_rate": 2.272750751678628e-05,
      "loss": 1.0377120971679688,
      "num_input_tokens_seen": 10919937344,
      "step": 38400,
      "train_runtime": 374051.3085,
      "train_tokens_per_second": 29193.688
    },
    {
      "epoch": 1.359021421605592,
      "grad_norm": 1.5,
      "learning_rate": 2.2725159949044613e-05,
      "loss": 1.047859001159668,
      "num_input_tokens_seen": 10922721856,
      "step": 38410,
      "train_runtime": 374145.1381,
      "train_tokens_per_second": 29193.809
    },
    {
      "epoch": 1.359375241869321,
      "grad_norm": 1.515625,
      "learning_rate": 2.2722813108606992e-05,
      "loss": 1.0343412399291991,
      "num_input_tokens_seen": 10925587264,
      "step": 38420,
      "train_runtime": 374242.3586,
      "train_tokens_per_second": 29193.882
    },
    {
      "epoch": 1.3597290621330496,
      "grad_norm": 1.4921875,
      "learning_rate": 2.2720466995097943e-05,
      "loss": 1.0416072845458983,
      "num_input_tokens_seen": 10928521728,
      "step": 38430,
      "train_runtime": 374347.2622,
      "train_tokens_per_second": 29193.54
    },
    {
      "epoch": 1.3600828823967785,
      "grad_norm": 1.59375,
      "learning_rate": 2.271812160814228e-05,
      "loss": 1.0476009368896484,
      "num_input_tokens_seen": 10931379456,
      "step": 38440,
      "train_runtime": 374447.9188,
      "train_tokens_per_second": 29193.324
    },
    {
      "epoch": 1.3604367026605073,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2715776947365065e-05,
      "loss": 1.0585382461547852,
      "num_input_tokens_seen": 10934192128,
      "step": 38450,
      "train_runtime": 374539.358,
      "train_tokens_per_second": 29193.707
    },
    {
      "epoch": 1.360790522924236,
      "grad_norm": 1.4921875,
      "learning_rate": 2.2713433012391654e-05,
      "loss": 1.0478019714355469,
      "num_input_tokens_seen": 10936995136,
      "step": 38460,
      "train_runtime": 374633.7215,
      "train_tokens_per_second": 29193.835
    },
    {
      "epoch": 1.3611443431879648,
      "grad_norm": 1.5625,
      "learning_rate": 2.2711089802847657e-05,
      "loss": 1.0317276000976563,
      "num_input_tokens_seen": 10939837696,
      "step": 38470,
      "train_runtime": 374732.4047,
      "train_tokens_per_second": 29193.733
    },
    {
      "epoch": 1.3614981634516936,
      "grad_norm": 1.5859375,
      "learning_rate": 2.270874731835896e-05,
      "loss": 1.0454461097717285,
      "num_input_tokens_seen": 10942637888,
      "step": 38480,
      "train_runtime": 374828.7685,
      "train_tokens_per_second": 29193.698
    },
    {
      "epoch": 1.3618519837154224,
      "grad_norm": 1.609375,
      "learning_rate": 2.270640555855172e-05,
      "loss": 1.0558258056640626,
      "num_input_tokens_seen": 10945469248,
      "step": 38490,
      "train_runtime": 374925.7918,
      "train_tokens_per_second": 29193.695
    },
    {
      "epoch": 1.3622058039791511,
      "grad_norm": 1.578125,
      "learning_rate": 2.2704064523052372e-05,
      "loss": 1.0441680908203126,
      "num_input_tokens_seen": 10948361600,
      "step": 38500,
      "train_runtime": 375029.288,
      "train_tokens_per_second": 29193.351
    },
    {
      "epoch": 1.36255962424288,
      "grad_norm": 1.59375,
      "learning_rate": 2.270172421148759e-05,
      "loss": 1.0511001586914062,
      "num_input_tokens_seen": 10951189440,
      "step": 38510,
      "train_runtime": 375126.0481,
      "train_tokens_per_second": 29193.359
    },
    {
      "epoch": 1.3629134445066087,
      "grad_norm": 1.5625,
      "learning_rate": 2.269938462348436e-05,
      "loss": 1.056480598449707,
      "num_input_tokens_seen": 10954091712,
      "step": 38520,
      "train_runtime": 375224.5522,
      "train_tokens_per_second": 29193.43
    },
    {
      "epoch": 1.3632672647703374,
      "grad_norm": 1.5390625,
      "learning_rate": 2.26970457586699e-05,
      "loss": 1.0521228790283204,
      "num_input_tokens_seen": 10956958592,
      "step": 38530,
      "train_runtime": 375321.4768,
      "train_tokens_per_second": 29193.529
    },
    {
      "epoch": 1.3636210850340662,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2694707616671726e-05,
      "loss": 1.0505373001098632,
      "num_input_tokens_seen": 10959828992,
      "step": 38540,
      "train_runtime": 375419.0815,
      "train_tokens_per_second": 29193.585
    },
    {
      "epoch": 1.363974905297795,
      "grad_norm": 1.609375,
      "learning_rate": 2.2692370197117605e-05,
      "loss": 1.0515336990356445,
      "num_input_tokens_seen": 10962646848,
      "step": 38550,
      "train_runtime": 375515.2586,
      "train_tokens_per_second": 29193.612
    },
    {
      "epoch": 1.3643287255615237,
      "grad_norm": 1.5,
      "learning_rate": 2.269003349963557e-05,
      "loss": 1.0415372848510742,
      "num_input_tokens_seen": 10965488256,
      "step": 38560,
      "train_runtime": 375609.6036,
      "train_tokens_per_second": 29193.844
    },
    {
      "epoch": 1.3646825458252527,
      "grad_norm": 1.53125,
      "learning_rate": 2.268769752385393e-05,
      "loss": 1.0393760681152344,
      "num_input_tokens_seen": 10968309696,
      "step": 38570,
      "train_runtime": 375704.4204,
      "train_tokens_per_second": 29193.986
    },
    {
      "epoch": 1.3650363660889813,
      "grad_norm": 1.578125,
      "learning_rate": 2.2685362269401272e-05,
      "loss": 1.0394875526428222,
      "num_input_tokens_seen": 10971198272,
      "step": 38580,
      "train_runtime": 375801.7905,
      "train_tokens_per_second": 29194.109
    },
    {
      "epoch": 1.3653901863527103,
      "grad_norm": 1.53125,
      "learning_rate": 2.268302773590643e-05,
      "loss": 1.0530092239379882,
      "num_input_tokens_seen": 10974057664,
      "step": 38590,
      "train_runtime": 375900.1359,
      "train_tokens_per_second": 29194.077
    },
    {
      "epoch": 1.3657440066164388,
      "grad_norm": 1.4921875,
      "learning_rate": 2.268069392299851e-05,
      "loss": 1.0489792823791504,
      "num_input_tokens_seen": 10976914496,
      "step": 38600,
      "train_runtime": 375998.6722,
      "train_tokens_per_second": 29194.025
    },
    {
      "epoch": 1.3660978268801678,
      "grad_norm": 1.59375,
      "learning_rate": 2.267836083030689e-05,
      "loss": 1.0627403259277344,
      "num_input_tokens_seen": 10979768960,
      "step": 38610,
      "train_runtime": 376097.7373,
      "train_tokens_per_second": 29193.925
    },
    {
      "epoch": 1.3664516471438966,
      "grad_norm": 1.484375,
      "learning_rate": 2.2676028457461225e-05,
      "loss": 1.0449098587036132,
      "num_input_tokens_seen": 10982613952,
      "step": 38620,
      "train_runtime": 376194.9781,
      "train_tokens_per_second": 29193.941
    },
    {
      "epoch": 1.3668054674076253,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2673696804091418e-05,
      "loss": 1.0404308319091797,
      "num_input_tokens_seen": 10985410048,
      "step": 38630,
      "train_runtime": 376288.0843,
      "train_tokens_per_second": 29194.148
    },
    {
      "epoch": 1.367159287671354,
      "grad_norm": 1.546875,
      "learning_rate": 2.267136586982764e-05,
      "loss": 1.0431385040283203,
      "num_input_tokens_seen": 10988300032,
      "step": 38640,
      "train_runtime": 376386.8052,
      "train_tokens_per_second": 29194.169
    },
    {
      "epoch": 1.3675131079350829,
      "grad_norm": 1.625,
      "learning_rate": 2.2669035654300346e-05,
      "loss": 1.0358546257019043,
      "num_input_tokens_seen": 10991144128,
      "step": 38650,
      "train_runtime": 376486.0268,
      "train_tokens_per_second": 29194.029
    },
    {
      "epoch": 1.3678669281988116,
      "grad_norm": 1.5625,
      "learning_rate": 2.2666706157140242e-05,
      "loss": 1.027207374572754,
      "num_input_tokens_seen": 10994020800,
      "step": 38660,
      "train_runtime": 376585.362,
      "train_tokens_per_second": 29193.967
    },
    {
      "epoch": 1.3682207484625404,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2664377377978295e-05,
      "loss": 1.0363803863525392,
      "num_input_tokens_seen": 10996851072,
      "step": 38670,
      "train_runtime": 376682.111,
      "train_tokens_per_second": 29193.983
    },
    {
      "epoch": 1.3685745687262691,
      "grad_norm": 1.59375,
      "learning_rate": 2.2662049316445754e-05,
      "loss": 1.0493412017822266,
      "num_input_tokens_seen": 10999660864,
      "step": 38680,
      "train_runtime": 376776.5831,
      "train_tokens_per_second": 29194.12
    },
    {
      "epoch": 1.368928388989998,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2659721972174117e-05,
      "loss": 1.0513843536376952,
      "num_input_tokens_seen": 11002482368,
      "step": 38690,
      "train_runtime": 376873.9076,
      "train_tokens_per_second": 29194.068
    },
    {
      "epoch": 1.3692822092537267,
      "grad_norm": 1.546875,
      "learning_rate": 2.2657395344795153e-05,
      "loss": 1.055150604248047,
      "num_input_tokens_seen": 11005339264,
      "step": 38700,
      "train_runtime": 376971.9183,
      "train_tokens_per_second": 29194.056
    },
    {
      "epoch": 1.3696360295174554,
      "grad_norm": 1.53125,
      "learning_rate": 2.265506943394091e-05,
      "loss": 1.0429594039916992,
      "num_input_tokens_seen": 11008131072,
      "step": 38710,
      "train_runtime": 377063.3051,
      "train_tokens_per_second": 29194.384
    },
    {
      "epoch": 1.3699898497811842,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2652744239243668e-05,
      "loss": 1.0332805633544921,
      "num_input_tokens_seen": 11010988160,
      "step": 38720,
      "train_runtime": 377160.7785,
      "train_tokens_per_second": 29194.415
    },
    {
      "epoch": 1.370343670044913,
      "grad_norm": 1.578125,
      "learning_rate": 2.2650419760336006e-05,
      "loss": 1.0375531196594239,
      "num_input_tokens_seen": 11013866176,
      "step": 38730,
      "train_runtime": 377260.9304,
      "train_tokens_per_second": 29194.293
    },
    {
      "epoch": 1.370697490308642,
      "grad_norm": 1.609375,
      "learning_rate": 2.2648095996850735e-05,
      "loss": 1.0343402862548827,
      "num_input_tokens_seen": 11016722496,
      "step": 38740,
      "train_runtime": 377358.7664,
      "train_tokens_per_second": 29194.293
    },
    {
      "epoch": 1.3710513105723705,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2645772948420957e-05,
      "loss": 1.0320053100585938,
      "num_input_tokens_seen": 11019531904,
      "step": 38750,
      "train_runtime": 377453.6236,
      "train_tokens_per_second": 29194.4
    },
    {
      "epoch": 1.3714051308360995,
      "grad_norm": 1.5078125,
      "learning_rate": 2.264345061468003e-05,
      "loss": 1.0510149002075195,
      "num_input_tokens_seen": 11022393792,
      "step": 38760,
      "train_runtime": 377553.0145,
      "train_tokens_per_second": 29194.294
    },
    {
      "epoch": 1.371758951099828,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2641128995261554e-05,
      "loss": 1.0567310333251954,
      "num_input_tokens_seen": 11025283008,
      "step": 38770,
      "train_runtime": 377653.4506,
      "train_tokens_per_second": 29194.181
    },
    {
      "epoch": 1.372112771363557,
      "grad_norm": 1.6015625,
      "learning_rate": 2.2638808089799417e-05,
      "loss": 1.0332561492919923,
      "num_input_tokens_seen": 11028088128,
      "step": 38780,
      "train_runtime": 377749.0305,
      "train_tokens_per_second": 29194.22
    },
    {
      "epoch": 1.3724665916272858,
      "grad_norm": 1.4609375,
      "learning_rate": 2.2636487897927773e-05,
      "loss": 1.0421150207519532,
      "num_input_tokens_seen": 11030944000,
      "step": 38790,
      "train_runtime": 377849.8904,
      "train_tokens_per_second": 29193.985
    },
    {
      "epoch": 1.3728204118910146,
      "grad_norm": 1.53125,
      "learning_rate": 2.2634168419281007e-05,
      "loss": 1.0385971069335938,
      "num_input_tokens_seen": 11033770048,
      "step": 38800,
      "train_runtime": 377945.4882,
      "train_tokens_per_second": 29194.078
    },
    {
      "epoch": 1.3731742321547433,
      "grad_norm": 1.4765625,
      "learning_rate": 2.2631849653493803e-05,
      "loss": 1.0461700439453125,
      "num_input_tokens_seen": 11036662784,
      "step": 38810,
      "train_runtime": 378042.208,
      "train_tokens_per_second": 29194.261
    },
    {
      "epoch": 1.373528052418472,
      "grad_norm": 1.546875,
      "learning_rate": 2.2629531600201077e-05,
      "loss": 1.052126407623291,
      "num_input_tokens_seen": 11039528064,
      "step": 38820,
      "train_runtime": 378139.5734,
      "train_tokens_per_second": 29194.321
    },
    {
      "epoch": 1.3738818726822009,
      "grad_norm": 1.546875,
      "learning_rate": 2.2627214259038028e-05,
      "loss": 1.052404022216797,
      "num_input_tokens_seen": 11042412992,
      "step": 38830,
      "train_runtime": 378238.8953,
      "train_tokens_per_second": 29194.282
    },
    {
      "epoch": 1.3742356929459296,
      "grad_norm": 1.4765625,
      "learning_rate": 2.2624897629640108e-05,
      "loss": 1.0393418312072753,
      "num_input_tokens_seen": 11045297216,
      "step": 38840,
      "train_runtime": 378338.4779,
      "train_tokens_per_second": 29194.221
    },
    {
      "epoch": 1.3745895132096584,
      "grad_norm": 1.53125,
      "learning_rate": 2.2622581711643022e-05,
      "loss": 1.054104995727539,
      "num_input_tokens_seen": 11048189056,
      "step": 38850,
      "train_runtime": 378438.9056,
      "train_tokens_per_second": 29194.115
    },
    {
      "epoch": 1.3749433334733872,
      "grad_norm": 1.5390625,
      "learning_rate": 2.262026650468275e-05,
      "loss": 1.0449606895446777,
      "num_input_tokens_seen": 11051043840,
      "step": 38860,
      "train_runtime": 378536.9587,
      "train_tokens_per_second": 29194.095
    },
    {
      "epoch": 1.375297153737116,
      "grad_norm": 1.59375,
      "learning_rate": 2.261795200839553e-05,
      "loss": 1.0522755622863769,
      "num_input_tokens_seen": 11053920512,
      "step": 38870,
      "train_runtime": 378637.2655,
      "train_tokens_per_second": 29193.958
    },
    {
      "epoch": 1.3756509740008447,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2615638222417856e-05,
      "loss": 1.0605039596557617,
      "num_input_tokens_seen": 11056773632,
      "step": 38880,
      "train_runtime": 378739.0313,
      "train_tokens_per_second": 29193.647
    },
    {
      "epoch": 1.3760047942645734,
      "grad_norm": 1.5390625,
      "learning_rate": 2.261332514638648e-05,
      "loss": 1.042280387878418,
      "num_input_tokens_seen": 11059602944,
      "step": 38890,
      "train_runtime": 378835.7355,
      "train_tokens_per_second": 29193.663
    },
    {
      "epoch": 1.3763586145283022,
      "grad_norm": 1.5234375,
      "learning_rate": 2.261101277993842e-05,
      "loss": 1.044830894470215,
      "num_input_tokens_seen": 11062481856,
      "step": 38900,
      "train_runtime": 378934.7615,
      "train_tokens_per_second": 29193.632
    },
    {
      "epoch": 1.3767124347920312,
      "grad_norm": 1.53125,
      "learning_rate": 2.2608701122710953e-05,
      "loss": 1.0554269790649413,
      "num_input_tokens_seen": 11065335296,
      "step": 38910,
      "train_runtime": 379031.0473,
      "train_tokens_per_second": 29193.744
    },
    {
      "epoch": 1.3770662550557597,
      "grad_norm": 1.5,
      "learning_rate": 2.2606390174341617e-05,
      "loss": 1.0572389602661132,
      "num_input_tokens_seen": 11068160768,
      "step": 38920,
      "train_runtime": 379126.8252,
      "train_tokens_per_second": 29193.821
    },
    {
      "epoch": 1.3774200753194887,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2604079934468193e-05,
      "loss": 1.049103355407715,
      "num_input_tokens_seen": 11070971520,
      "step": 38930,
      "train_runtime": 379222.0315,
      "train_tokens_per_second": 29193.904
    },
    {
      "epoch": 1.3777738955832175,
      "grad_norm": 1.4921875,
      "learning_rate": 2.260177040272875e-05,
      "loss": 1.0430784225463867,
      "num_input_tokens_seen": 11073798144,
      "step": 38940,
      "train_runtime": 379317.8006,
      "train_tokens_per_second": 29193.985
    },
    {
      "epoch": 1.3781277158469463,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2599461578761593e-05,
      "loss": 1.043807315826416,
      "num_input_tokens_seen": 11076636224,
      "step": 38950,
      "train_runtime": 379415.225,
      "train_tokens_per_second": 29193.969
    },
    {
      "epoch": 1.378481536110675,
      "grad_norm": 1.578125,
      "learning_rate": 2.2597153462205292e-05,
      "loss": 1.0592025756835937,
      "num_input_tokens_seen": 11079494464,
      "step": 38960,
      "train_runtime": 379513.8802,
      "train_tokens_per_second": 29193.911
    },
    {
      "epoch": 1.3788353563744038,
      "grad_norm": 1.4921875,
      "learning_rate": 2.259484605269868e-05,
      "loss": 1.0388696670532227,
      "num_input_tokens_seen": 11082340352,
      "step": 38970,
      "train_runtime": 379612.4336,
      "train_tokens_per_second": 29193.829
    },
    {
      "epoch": 1.3791891766381326,
      "grad_norm": 1.5234375,
      "learning_rate": 2.259253934988084e-05,
      "loss": 1.0601749420166016,
      "num_input_tokens_seen": 11085170816,
      "step": 38980,
      "train_runtime": 379710.0881,
      "train_tokens_per_second": 29193.775
    },
    {
      "epoch": 1.3795429969018613,
      "grad_norm": 1.5078125,
      "learning_rate": 2.2590233353391124e-05,
      "loss": 1.040640163421631,
      "num_input_tokens_seen": 11087992192,
      "step": 38990,
      "train_runtime": 379805.6008,
      "train_tokens_per_second": 29193.862
    },
    {
      "epoch": 1.37989681716559,
      "grad_norm": 1.4765625,
      "learning_rate": 2.2587928062869124e-05,
      "loss": 1.0615262031555175,
      "num_input_tokens_seen": 11090834624,
      "step": 39000,
      "train_runtime": 379902.6594,
      "train_tokens_per_second": 29193.885
    },
    {
      "epoch": 1.3802506374293189,
      "grad_norm": 1.484375,
      "learning_rate": 2.258562347795471e-05,
      "loss": 1.0302799224853516,
      "num_input_tokens_seen": 11093671168,
      "step": 39010,
      "train_runtime": 380000.3997,
      "train_tokens_per_second": 29193.841
    },
    {
      "epoch": 1.3806044576930476,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2583319598287993e-05,
      "loss": 1.037026596069336,
      "num_input_tokens_seen": 11096512000,
      "step": 39020,
      "train_runtime": 380101.6439,
      "train_tokens_per_second": 29193.539
    },
    {
      "epoch": 1.3809582779567764,
      "grad_norm": 1.484375,
      "learning_rate": 2.258101642350935e-05,
      "loss": 1.0541017532348633,
      "num_input_tokens_seen": 11099313280,
      "step": 39030,
      "train_runtime": 380195.1016,
      "train_tokens_per_second": 29193.73
    },
    {
      "epoch": 1.3813120982205052,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2578713953259414e-05,
      "loss": 1.0390743255615233,
      "num_input_tokens_seen": 11102135744,
      "step": 39040,
      "train_runtime": 380292.3038,
      "train_tokens_per_second": 29193.69
    },
    {
      "epoch": 1.381665918484234,
      "grad_norm": 1.6015625,
      "learning_rate": 2.2576412187179074e-05,
      "loss": 1.0446849822998048,
      "num_input_tokens_seen": 11104966592,
      "step": 39050,
      "train_runtime": 380390.5681,
      "train_tokens_per_second": 29193.591
    },
    {
      "epoch": 1.3820197387479627,
      "grad_norm": 1.4921875,
      "learning_rate": 2.257411112490946e-05,
      "loss": 1.0373998641967774,
      "num_input_tokens_seen": 11107825536,
      "step": 39060,
      "train_runtime": 380490.4442,
      "train_tokens_per_second": 29193.442
    },
    {
      "epoch": 1.3823735590116915,
      "grad_norm": 1.4921875,
      "learning_rate": 2.257181076609199e-05,
      "loss": 1.0539454460144042,
      "num_input_tokens_seen": 11110701056,
      "step": 39070,
      "train_runtime": 380588.8607,
      "train_tokens_per_second": 29193.448
    },
    {
      "epoch": 1.3827273792754204,
      "grad_norm": 1.5078125,
      "learning_rate": 2.2569511110368306e-05,
      "loss": 1.0503253936767578,
      "num_input_tokens_seen": 11113572480,
      "step": 39080,
      "train_runtime": 380685.1271,
      "train_tokens_per_second": 29193.608
    },
    {
      "epoch": 1.383081199539149,
      "grad_norm": 1.578125,
      "learning_rate": 2.256721215738032e-05,
      "loss": 1.0612279891967773,
      "num_input_tokens_seen": 11116431744,
      "step": 39090,
      "train_runtime": 380785.1104,
      "train_tokens_per_second": 29193.452
    },
    {
      "epoch": 1.383435019802878,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2564913906770207e-05,
      "loss": 1.0342654228210448,
      "num_input_tokens_seen": 11119239296,
      "step": 39100,
      "train_runtime": 380878.4819,
      "train_tokens_per_second": 29193.666
    },
    {
      "epoch": 1.3837888400666067,
      "grad_norm": 1.5625,
      "learning_rate": 2.2562616358180384e-05,
      "loss": 1.0499846458435058,
      "num_input_tokens_seen": 11122072192,
      "step": 39110,
      "train_runtime": 380972.6946,
      "train_tokens_per_second": 29193.883
    },
    {
      "epoch": 1.3841426603303355,
      "grad_norm": 1.4921875,
      "learning_rate": 2.2560319511253522e-05,
      "loss": 1.0567741394042969,
      "num_input_tokens_seen": 11124964864,
      "step": 39120,
      "train_runtime": 381072.3018,
      "train_tokens_per_second": 29193.843
    },
    {
      "epoch": 1.3844964805940643,
      "grad_norm": 1.515625,
      "learning_rate": 2.255802336563256e-05,
      "loss": 1.0532445907592773,
      "num_input_tokens_seen": 11127832384,
      "step": 39130,
      "train_runtime": 381169.9882,
      "train_tokens_per_second": 29193.884
    },
    {
      "epoch": 1.384850300857793,
      "grad_norm": 1.5703125,
      "learning_rate": 2.255572792096067e-05,
      "loss": 1.04498291015625,
      "num_input_tokens_seen": 11130690944,
      "step": 39140,
      "train_runtime": 381272.0187,
      "train_tokens_per_second": 29193.569
    },
    {
      "epoch": 1.3852041211215218,
      "grad_norm": 1.546875,
      "learning_rate": 2.2553433176881303e-05,
      "loss": 1.0420803070068358,
      "num_input_tokens_seen": 11133547840,
      "step": 39150,
      "train_runtime": 381371.2767,
      "train_tokens_per_second": 29193.462
    },
    {
      "epoch": 1.3855579413852506,
      "grad_norm": 1.5,
      "learning_rate": 2.2551139133038147e-05,
      "loss": 1.040702724456787,
      "num_input_tokens_seen": 11136403328,
      "step": 39160,
      "train_runtime": 381469.9362,
      "train_tokens_per_second": 29193.397
    },
    {
      "epoch": 1.3859117616489793,
      "grad_norm": 1.4921875,
      "learning_rate": 2.2548845789075145e-05,
      "loss": 1.045588493347168,
      "num_input_tokens_seen": 11139264832,
      "step": 39170,
      "train_runtime": 381568.4827,
      "train_tokens_per_second": 29193.357
    },
    {
      "epoch": 1.386265581912708,
      "grad_norm": 1.53125,
      "learning_rate": 2.2546553144636503e-05,
      "loss": 1.042722797393799,
      "num_input_tokens_seen": 11142194368,
      "step": 39180,
      "train_runtime": 381673.7176,
      "train_tokens_per_second": 29192.983
    },
    {
      "epoch": 1.3866194021764369,
      "grad_norm": 1.5390625,
      "learning_rate": 2.254426119936668e-05,
      "loss": 1.0345090866088866,
      "num_input_tokens_seen": 11145013632,
      "step": 39190,
      "train_runtime": 381769.42,
      "train_tokens_per_second": 29193.05
    },
    {
      "epoch": 1.3869732224401656,
      "grad_norm": 1.515625,
      "learning_rate": 2.2541969952910365e-05,
      "loss": 1.0423244476318358,
      "num_input_tokens_seen": 11147898752,
      "step": 39200,
      "train_runtime": 381868.4082,
      "train_tokens_per_second": 29193.037
    },
    {
      "epoch": 1.3873270427038944,
      "grad_norm": 1.5,
      "learning_rate": 2.2539679404912533e-05,
      "loss": 1.0376026153564453,
      "num_input_tokens_seen": 11150699776,
      "step": 39210,
      "train_runtime": 381964.6975,
      "train_tokens_per_second": 29193.011
    },
    {
      "epoch": 1.3876808629676232,
      "grad_norm": 1.53125,
      "learning_rate": 2.253738955501838e-05,
      "loss": 1.0511850357055663,
      "num_input_tokens_seen": 11153533632,
      "step": 39220,
      "train_runtime": 382061.8244,
      "train_tokens_per_second": 29193.007
    },
    {
      "epoch": 1.3880346832313522,
      "grad_norm": 1.9140625,
      "learning_rate": 2.2535100402873383e-05,
      "loss": 1.0417304992675782,
      "num_input_tokens_seen": 11156396864,
      "step": 39230,
      "train_runtime": 382158.705,
      "train_tokens_per_second": 29193.099
    },
    {
      "epoch": 1.3883885034950807,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2532811948123252e-05,
      "loss": 1.0417596817016601,
      "num_input_tokens_seen": 11159236160,
      "step": 39240,
      "train_runtime": 382258.1862,
      "train_tokens_per_second": 29192.929
    },
    {
      "epoch": 1.3887423237588097,
      "grad_norm": 1.6484375,
      "learning_rate": 2.2530524190413955e-05,
      "loss": 1.0316246032714844,
      "num_input_tokens_seen": 11162052224,
      "step": 39250,
      "train_runtime": 382352.4595,
      "train_tokens_per_second": 29193.096
    },
    {
      "epoch": 1.3890961440225382,
      "grad_norm": 1.6015625,
      "learning_rate": 2.2528237129391706e-05,
      "loss": 1.0439836502075195,
      "num_input_tokens_seen": 11164892736,
      "step": 39260,
      "train_runtime": 382451.4834,
      "train_tokens_per_second": 29192.965
    },
    {
      "epoch": 1.3894499642862672,
      "grad_norm": 1.5,
      "learning_rate": 2.2525950764702985e-05,
      "loss": 1.0512356758117676,
      "num_input_tokens_seen": 11167730112,
      "step": 39270,
      "train_runtime": 382548.1049,
      "train_tokens_per_second": 29193.009
    },
    {
      "epoch": 1.389803784549996,
      "grad_norm": 1.5625,
      "learning_rate": 2.2523665095994505e-05,
      "loss": 1.0410776138305664,
      "num_input_tokens_seen": 11170539264,
      "step": 39280,
      "train_runtime": 382642.4035,
      "train_tokens_per_second": 29193.156
    },
    {
      "epoch": 1.3901576048137247,
      "grad_norm": 1.6015625,
      "learning_rate": 2.252138012291324e-05,
      "loss": 1.0410516738891602,
      "num_input_tokens_seen": 11173406528,
      "step": 39290,
      "train_runtime": 382743.2944,
      "train_tokens_per_second": 29192.952
    },
    {
      "epoch": 1.3905114250774535,
      "grad_norm": 1.4921875,
      "learning_rate": 2.2519095845106414e-05,
      "loss": 1.051633358001709,
      "num_input_tokens_seen": 11176267392,
      "step": 39300,
      "train_runtime": 382841.2982,
      "train_tokens_per_second": 29192.951
    },
    {
      "epoch": 1.3908652453411823,
      "grad_norm": 1.5,
      "learning_rate": 2.25168122622215e-05,
      "loss": 1.0403926849365235,
      "num_input_tokens_seen": 11179142976,
      "step": 39310,
      "train_runtime": 382940.4189,
      "train_tokens_per_second": 29192.904
    },
    {
      "epoch": 1.391219065604911,
      "grad_norm": 1.515625,
      "learning_rate": 2.2514529373906217e-05,
      "loss": 1.0471771240234375,
      "num_input_tokens_seen": 11181973504,
      "step": 39320,
      "train_runtime": 383034.965,
      "train_tokens_per_second": 29193.088
    },
    {
      "epoch": 1.3915728858686398,
      "grad_norm": 1.59375,
      "learning_rate": 2.251224717980855e-05,
      "loss": 1.049705696105957,
      "num_input_tokens_seen": 11184771456,
      "step": 39330,
      "train_runtime": 383127.6075,
      "train_tokens_per_second": 29193.332
    },
    {
      "epoch": 1.3919267061323686,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2509965679576713e-05,
      "loss": 1.0376442909240722,
      "num_input_tokens_seen": 11187658048,
      "step": 39340,
      "train_runtime": 383227.958,
      "train_tokens_per_second": 29193.22
    },
    {
      "epoch": 1.3922805263960973,
      "grad_norm": 1.578125,
      "learning_rate": 2.250768487285918e-05,
      "loss": 1.0393450736999512,
      "num_input_tokens_seen": 11190528448,
      "step": 39350,
      "train_runtime": 383327.0196,
      "train_tokens_per_second": 29193.164
    },
    {
      "epoch": 1.392634346659826,
      "grad_norm": 1.546875,
      "learning_rate": 2.250540475930467e-05,
      "loss": 1.0546005249023438,
      "num_input_tokens_seen": 11193331648,
      "step": 39360,
      "train_runtime": 383422.5045,
      "train_tokens_per_second": 29193.205
    },
    {
      "epoch": 1.3929881669235549,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2503125338562166e-05,
      "loss": 1.0360166549682617,
      "num_input_tokens_seen": 11196209024,
      "step": 39370,
      "train_runtime": 383521.4834,
      "train_tokens_per_second": 29193.173
    },
    {
      "epoch": 1.3933419871872836,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2500846610280868e-05,
      "loss": 1.056164264678955,
      "num_input_tokens_seen": 11199065536,
      "step": 39380,
      "train_runtime": 383621.9867,
      "train_tokens_per_second": 29192.971
    },
    {
      "epoch": 1.3936958074510124,
      "grad_norm": 1.5625,
      "learning_rate": 2.2498568574110262e-05,
      "loss": 1.043155574798584,
      "num_input_tokens_seen": 11201837056,
      "step": 39390,
      "train_runtime": 383714.7791,
      "train_tokens_per_second": 29193.134
    },
    {
      "epoch": 1.3940496277147414,
      "grad_norm": 1.546875,
      "learning_rate": 2.249629122970006e-05,
      "loss": 1.0327795028686524,
      "num_input_tokens_seen": 11204617408,
      "step": 39400,
      "train_runtime": 383808.2285,
      "train_tokens_per_second": 29193.27
    },
    {
      "epoch": 1.39440344797847,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2494014576700217e-05,
      "loss": 1.048772144317627,
      "num_input_tokens_seen": 11207412032,
      "step": 39410,
      "train_runtime": 383902.789,
      "train_tokens_per_second": 29193.359
    },
    {
      "epoch": 1.394757268242199,
      "grad_norm": 1.5625,
      "learning_rate": 2.2491738614760956e-05,
      "loss": 1.0413206100463868,
      "num_input_tokens_seen": 11210267648,
      "step": 39420,
      "train_runtime": 384001.4965,
      "train_tokens_per_second": 29193.292
    },
    {
      "epoch": 1.3951110885059275,
      "grad_norm": 1.5625,
      "learning_rate": 2.2489463343532742e-05,
      "loss": 1.048126792907715,
      "num_input_tokens_seen": 11213072064,
      "step": 39430,
      "train_runtime": 384096.7809,
      "train_tokens_per_second": 29193.351
    },
    {
      "epoch": 1.3954649087696565,
      "grad_norm": 1.546875,
      "learning_rate": 2.2487188762666268e-05,
      "loss": 1.0392765998840332,
      "num_input_tokens_seen": 11215926144,
      "step": 39440,
      "train_runtime": 384195.716,
      "train_tokens_per_second": 29193.262
    },
    {
      "epoch": 1.3958187290333852,
      "grad_norm": 1.5,
      "learning_rate": 2.2484914871812504e-05,
      "loss": 1.035966396331787,
      "num_input_tokens_seen": 11218763200,
      "step": 39450,
      "train_runtime": 384293.2613,
      "train_tokens_per_second": 29193.234
    },
    {
      "epoch": 1.396172549297114,
      "grad_norm": 1.515625,
      "learning_rate": 2.248264167062264e-05,
      "loss": 1.0366376876831054,
      "num_input_tokens_seen": 11221601472,
      "step": 39460,
      "train_runtime": 384387.848,
      "train_tokens_per_second": 29193.435
    },
    {
      "epoch": 1.3965263695608428,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2480369158748138e-05,
      "loss": 1.0312374114990235,
      "num_input_tokens_seen": 11224429952,
      "step": 39470,
      "train_runtime": 384486.1267,
      "train_tokens_per_second": 29193.329
    },
    {
      "epoch": 1.3968801898245715,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2478097335840682e-05,
      "loss": 1.0563644409179687,
      "num_input_tokens_seen": 11227295360,
      "step": 39480,
      "train_runtime": 384586.6823,
      "train_tokens_per_second": 29193.147
    },
    {
      "epoch": 1.3972340100883003,
      "grad_norm": 1.515625,
      "learning_rate": 2.2475826201552215e-05,
      "loss": 1.0611684799194336,
      "num_input_tokens_seen": 11230140864,
      "step": 39490,
      "train_runtime": 384683.5924,
      "train_tokens_per_second": 29193.189
    },
    {
      "epoch": 1.397587830352029,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2473555755534935e-05,
      "loss": 1.0420080184936524,
      "num_input_tokens_seen": 11232961856,
      "step": 39500,
      "train_runtime": 384780.3619,
      "train_tokens_per_second": 29193.179
    },
    {
      "epoch": 1.3979416506157578,
      "grad_norm": 1.515625,
      "learning_rate": 2.2471285997441267e-05,
      "loss": 1.0478855133056642,
      "num_input_tokens_seen": 11235836672,
      "step": 39510,
      "train_runtime": 384879.253,
      "train_tokens_per_second": 29193.147
    },
    {
      "epoch": 1.3982954708794866,
      "grad_norm": 1.625,
      "learning_rate": 2.246901692692389e-05,
      "loss": 1.0322057723999023,
      "num_input_tokens_seen": 11238604864,
      "step": 39520,
      "train_runtime": 384971.9265,
      "train_tokens_per_second": 29193.31
    },
    {
      "epoch": 1.3986492911432153,
      "grad_norm": 1.484375,
      "learning_rate": 2.2466748543635735e-05,
      "loss": 1.0475372314453124,
      "num_input_tokens_seen": 11241440704,
      "step": 39530,
      "train_runtime": 385066.7152,
      "train_tokens_per_second": 29193.488
    },
    {
      "epoch": 1.399003111406944,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2464480847229967e-05,
      "loss": 1.0377182006835937,
      "num_input_tokens_seen": 11244246336,
      "step": 39540,
      "train_runtime": 385162.9319,
      "train_tokens_per_second": 29193.48
    },
    {
      "epoch": 1.3993569316706729,
      "grad_norm": 1.6015625,
      "learning_rate": 2.2462213837360003e-05,
      "loss": 1.0449495315551758,
      "num_input_tokens_seen": 11247100608,
      "step": 39550,
      "train_runtime": 385257.5317,
      "train_tokens_per_second": 29193.72
    },
    {
      "epoch": 1.3997107519344016,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2459947513679502e-05,
      "loss": 1.0441871643066407,
      "num_input_tokens_seen": 11249952448,
      "step": 39560,
      "train_runtime": 385355.4952,
      "train_tokens_per_second": 29193.699
    },
    {
      "epoch": 1.4000645721981306,
      "grad_norm": 1.53125,
      "learning_rate": 2.2457681875842372e-05,
      "loss": 1.033175563812256,
      "num_input_tokens_seen": 11252786880,
      "step": 39570,
      "train_runtime": 385450.6222,
      "train_tokens_per_second": 29193.848
    },
    {
      "epoch": 1.4004183924618592,
      "grad_norm": 1.4921875,
      "learning_rate": 2.245541692350276e-05,
      "loss": 1.0449872970581056,
      "num_input_tokens_seen": 11255565824,
      "step": 39580,
      "train_runtime": 385542.9018,
      "train_tokens_per_second": 29194.068
    },
    {
      "epoch": 1.4007722127255882,
      "grad_norm": 1.515625,
      "learning_rate": 2.245315265631506e-05,
      "loss": 1.060658073425293,
      "num_input_tokens_seen": 11258436608,
      "step": 39590,
      "train_runtime": 385643.1489,
      "train_tokens_per_second": 29193.924
    },
    {
      "epoch": 1.4011260329893167,
      "grad_norm": 1.5625,
      "learning_rate": 2.2450889073933906e-05,
      "loss": 1.0500158309936523,
      "num_input_tokens_seen": 11261232640,
      "step": 39600,
      "train_runtime": 385735.9626,
      "train_tokens_per_second": 29194.148
    },
    {
      "epoch": 1.4014798532530457,
      "grad_norm": 1.546875,
      "learning_rate": 2.2448626176014187e-05,
      "loss": 1.0530572891235352,
      "num_input_tokens_seen": 11264059072,
      "step": 39610,
      "train_runtime": 385833.6685,
      "train_tokens_per_second": 29194.08
    },
    {
      "epoch": 1.4018336735167745,
      "grad_norm": 1.6796875,
      "learning_rate": 2.2446363962211015e-05,
      "loss": 1.0422932624816894,
      "num_input_tokens_seen": 11266859392,
      "step": 39620,
      "train_runtime": 385929.9726,
      "train_tokens_per_second": 29194.051
    },
    {
      "epoch": 1.4021874937805032,
      "grad_norm": 1.4921875,
      "learning_rate": 2.244410243217976e-05,
      "loss": 1.0377328872680665,
      "num_input_tokens_seen": 11269693120,
      "step": 39630,
      "train_runtime": 386026.231,
      "train_tokens_per_second": 29194.112
    },
    {
      "epoch": 1.402541314044232,
      "grad_norm": 1.5078125,
      "learning_rate": 2.2441841585576043e-05,
      "loss": 1.0665373802185059,
      "num_input_tokens_seen": 11272529792,
      "step": 39640,
      "train_runtime": 386124.0272,
      "train_tokens_per_second": 29194.065
    },
    {
      "epoch": 1.4028951343079608,
      "grad_norm": 1.546875,
      "learning_rate": 2.2439581422055703e-05,
      "loss": 1.052358627319336,
      "num_input_tokens_seen": 11275426048,
      "step": 39650,
      "train_runtime": 386224.7586,
      "train_tokens_per_second": 29193.949
    },
    {
      "epoch": 1.4032489545716895,
      "grad_norm": 1.546875,
      "learning_rate": 2.2437321941274843e-05,
      "loss": 1.0522232055664062,
      "num_input_tokens_seen": 11278256192,
      "step": 39660,
      "train_runtime": 386323.3386,
      "train_tokens_per_second": 29193.826
    },
    {
      "epoch": 1.4036027748354183,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2435063142889803e-05,
      "loss": 1.0450531005859376,
      "num_input_tokens_seen": 11281119616,
      "step": 39670,
      "train_runtime": 386421.988,
      "train_tokens_per_second": 29193.783
    },
    {
      "epoch": 1.403956595099147,
      "grad_norm": 1.5703125,
      "learning_rate": 2.2432805026557163e-05,
      "loss": 1.0515355110168456,
      "num_input_tokens_seen": 11284013440,
      "step": 39680,
      "train_runtime": 386523.1815,
      "train_tokens_per_second": 29193.627
    },
    {
      "epoch": 1.4043104153628758,
      "grad_norm": 1.5390625,
      "learning_rate": 2.243054759193374e-05,
      "loss": 1.0554115295410156,
      "num_input_tokens_seen": 11286918848,
      "step": 39690,
      "train_runtime": 386626.38,
      "train_tokens_per_second": 29193.349
    },
    {
      "epoch": 1.4046642356266046,
      "grad_norm": 1.578125,
      "learning_rate": 2.2428290838676597e-05,
      "loss": 1.0513277053833008,
      "num_input_tokens_seen": 11289822400,
      "step": 39700,
      "train_runtime": 386724.9854,
      "train_tokens_per_second": 29193.413
    },
    {
      "epoch": 1.4050180558903334,
      "grad_norm": 1.53125,
      "learning_rate": 2.2426034766443042e-05,
      "loss": 1.0250278472900392,
      "num_input_tokens_seen": 11292672064,
      "step": 39710,
      "train_runtime": 386822.1631,
      "train_tokens_per_second": 29193.446
    },
    {
      "epoch": 1.4053718761540621,
      "grad_norm": 1.640625,
      "learning_rate": 2.2423779374890626e-05,
      "loss": 1.0511338233947753,
      "num_input_tokens_seen": 11295548544,
      "step": 39720,
      "train_runtime": 386924.1449,
      "train_tokens_per_second": 29193.186
    },
    {
      "epoch": 1.4057256964177909,
      "grad_norm": 1.578125,
      "learning_rate": 2.2421524663677132e-05,
      "loss": 1.0543429374694824,
      "num_input_tokens_seen": 11298352256,
      "step": 39730,
      "train_runtime": 387019.0663,
      "train_tokens_per_second": 29193.27
    },
    {
      "epoch": 1.4060795166815199,
      "grad_norm": 1.6796875,
      "learning_rate": 2.2419270632460588e-05,
      "loss": 1.0396318435668945,
      "num_input_tokens_seen": 11301168896,
      "step": 39740,
      "train_runtime": 387114.4175,
      "train_tokens_per_second": 29193.356
    },
    {
      "epoch": 1.4064333369452484,
      "grad_norm": 1.5,
      "learning_rate": 2.2417017280899265e-05,
      "loss": 1.0545123100280762,
      "num_input_tokens_seen": 11303974528,
      "step": 39750,
      "train_runtime": 387211.2257,
      "train_tokens_per_second": 29193.303
    },
    {
      "epoch": 1.4067871572089774,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2414764608651668e-05,
      "loss": 1.0452911376953125,
      "num_input_tokens_seen": 11306792128,
      "step": 39760,
      "train_runtime": 387309.9705,
      "train_tokens_per_second": 29193.135
    },
    {
      "epoch": 1.407140977472706,
      "grad_norm": 1.5234375,
      "learning_rate": 2.241251261537655e-05,
      "loss": 1.0543917655944823,
      "num_input_tokens_seen": 11309587840,
      "step": 39770,
      "train_runtime": 387404.476,
      "train_tokens_per_second": 29193.23
    },
    {
      "epoch": 1.407494797736435,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2410261300732903e-05,
      "loss": 1.0523942947387694,
      "num_input_tokens_seen": 11312487232,
      "step": 39780,
      "train_runtime": 387507.5437,
      "train_tokens_per_second": 29192.947
    },
    {
      "epoch": 1.4078486180001637,
      "grad_norm": 1.53125,
      "learning_rate": 2.240801066437995e-05,
      "loss": 1.0520904541015625,
      "num_input_tokens_seen": 11315314880,
      "step": 39790,
      "train_runtime": 387602.246,
      "train_tokens_per_second": 29193.11
    },
    {
      "epoch": 1.4082024382638925,
      "grad_norm": 1.515625,
      "learning_rate": 2.2405760705977166e-05,
      "loss": 1.0449533462524414,
      "num_input_tokens_seen": 11318206912,
      "step": 39800,
      "train_runtime": 387701.5398,
      "train_tokens_per_second": 29193.092
    },
    {
      "epoch": 1.4085562585276212,
      "grad_norm": 1.546875,
      "learning_rate": 2.240351142518425e-05,
      "loss": 1.047023868560791,
      "num_input_tokens_seen": 11321046528,
      "step": 39810,
      "train_runtime": 387798.3967,
      "train_tokens_per_second": 29193.124
    },
    {
      "epoch": 1.40891007879135,
      "grad_norm": 1.5390625,
      "learning_rate": 2.240126282166116e-05,
      "loss": 1.0461925506591796,
      "num_input_tokens_seen": 11323874880,
      "step": 39820,
      "train_runtime": 387896.454,
      "train_tokens_per_second": 29193.035
    },
    {
      "epoch": 1.4092638990550788,
      "grad_norm": 1.5390625,
      "learning_rate": 2.239901489506808e-05,
      "loss": 1.0345829010009766,
      "num_input_tokens_seen": 11326753280,
      "step": 39830,
      "train_runtime": 387997.3316,
      "train_tokens_per_second": 29192.864
    },
    {
      "epoch": 1.4096177193188075,
      "grad_norm": 1.5703125,
      "learning_rate": 2.2396767645065424e-05,
      "loss": 1.054257869720459,
      "num_input_tokens_seen": 11329605440,
      "step": 39840,
      "train_runtime": 388094.6909,
      "train_tokens_per_second": 29192.89
    },
    {
      "epoch": 1.4099715395825363,
      "grad_norm": 1.5625,
      "learning_rate": 2.239452107131387e-05,
      "loss": 1.047704315185547,
      "num_input_tokens_seen": 11332447360,
      "step": 39850,
      "train_runtime": 388191.5665,
      "train_tokens_per_second": 29192.925
    },
    {
      "epoch": 1.410325359846265,
      "grad_norm": 1.5859375,
      "learning_rate": 2.239227517347431e-05,
      "loss": 1.0488602638244628,
      "num_input_tokens_seen": 11335302336,
      "step": 39860,
      "train_runtime": 388289.6492,
      "train_tokens_per_second": 29192.904
    },
    {
      "epoch": 1.4106791801099938,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2390029951207876e-05,
      "loss": 1.0532964706420898,
      "num_input_tokens_seen": 11338120000,
      "step": 39870,
      "train_runtime": 388383.1738,
      "train_tokens_per_second": 29193.129
    },
    {
      "epoch": 1.4110330003737226,
      "grad_norm": 1.59375,
      "learning_rate": 2.2387785404175965e-05,
      "loss": 1.0511537551879884,
      "num_input_tokens_seen": 11340983232,
      "step": 39880,
      "train_runtime": 388482.0117,
      "train_tokens_per_second": 29193.072
    },
    {
      "epoch": 1.4113868206374514,
      "grad_norm": 1.546875,
      "learning_rate": 2.2385541532040178e-05,
      "loss": 1.0491630554199218,
      "num_input_tokens_seen": 11343874368,
      "step": 39890,
      "train_runtime": 388582.4644,
      "train_tokens_per_second": 29192.965
    },
    {
      "epoch": 1.4117406409011801,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2383298334462368e-05,
      "loss": 1.0500043869018554,
      "num_input_tokens_seen": 11346669056,
      "step": 39900,
      "train_runtime": 388676.998,
      "train_tokens_per_second": 29193.055
    },
    {
      "epoch": 1.412094461164909,
      "grad_norm": 1.5625,
      "learning_rate": 2.2381055811104627e-05,
      "loss": 1.043359375,
      "num_input_tokens_seen": 11349581440,
      "step": 39910,
      "train_runtime": 388779.1986,
      "train_tokens_per_second": 29192.872
    },
    {
      "epoch": 1.4124482814286377,
      "grad_norm": 1.59375,
      "learning_rate": 2.2378813961629274e-05,
      "loss": 1.0477094650268555,
      "num_input_tokens_seen": 11352445824,
      "step": 39920,
      "train_runtime": 388879.0793,
      "train_tokens_per_second": 29192.74
    },
    {
      "epoch": 1.4128021016923666,
      "grad_norm": 1.578125,
      "learning_rate": 2.2376572785698884e-05,
      "loss": 1.0501890182495117,
      "num_input_tokens_seen": 11355256192,
      "step": 39930,
      "train_runtime": 388974.0483,
      "train_tokens_per_second": 29192.838
    },
    {
      "epoch": 1.4131559219560954,
      "grad_norm": 1.5390625,
      "learning_rate": 2.237433228297625e-05,
      "loss": 1.0471805572509765,
      "num_input_tokens_seen": 11358158912,
      "step": 39940,
      "train_runtime": 389073.1656,
      "train_tokens_per_second": 29192.861
    },
    {
      "epoch": 1.4135097422198242,
      "grad_norm": 1.4921875,
      "learning_rate": 2.2372092453124402e-05,
      "loss": 1.0440771102905273,
      "num_input_tokens_seen": 11360970368,
      "step": 39950,
      "train_runtime": 389169.0617,
      "train_tokens_per_second": 29192.892
    },
    {
      "epoch": 1.413863562483553,
      "grad_norm": 1.546875,
      "learning_rate": 2.236985329580662e-05,
      "loss": 1.0517522811889648,
      "num_input_tokens_seen": 11363792768,
      "step": 39960,
      "train_runtime": 389262.7078,
      "train_tokens_per_second": 29193.12
    },
    {
      "epoch": 1.4142173827472817,
      "grad_norm": 1.609375,
      "learning_rate": 2.236761481068641e-05,
      "loss": 1.0224111557006836,
      "num_input_tokens_seen": 11366586624,
      "step": 39970,
      "train_runtime": 389358.9769,
      "train_tokens_per_second": 29193.077
    },
    {
      "epoch": 1.4145712030110105,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2365376997427508e-05,
      "loss": 1.049896240234375,
      "num_input_tokens_seen": 11369383424,
      "step": 39980,
      "train_runtime": 389452.3435,
      "train_tokens_per_second": 29193.26
    },
    {
      "epoch": 1.4149250232747392,
      "grad_norm": 1.5625,
      "learning_rate": 2.2363139855693906e-05,
      "loss": 1.0384031295776368,
      "num_input_tokens_seen": 11372213504,
      "step": 39990,
      "train_runtime": 389550.512,
      "train_tokens_per_second": 29193.168
    },
    {
      "epoch": 1.415278843538468,
      "grad_norm": 1.546875,
      "learning_rate": 2.2360903385149807e-05,
      "loss": 1.0415538787841796,
      "num_input_tokens_seen": 11374996992,
      "step": 40000,
      "train_runtime": 389643.852,
      "train_tokens_per_second": 29193.318
    },
    {
      "epoch": 1.415278843538468,
      "eval_loss": 1.0212212800979614,
      "eval_runtime": 8.4446,
      "eval_samples_per_second": 472.254,
      "eval_steps_per_second": 3.789,
      "num_input_tokens_seen": 11374996992,
      "step": 40000
    },
    {
      "epoch": 1.4156326638021968,
      "grad_norm": 1.53125,
      "learning_rate": 2.2358667585459662e-05,
      "loss": 1.044675636291504,
      "num_input_tokens_seen": 11377803456,
      "step": 40010,
      "train_runtime": 389770.1984,
      "train_tokens_per_second": 29191.055
    },
    {
      "epoch": 1.4159864840659255,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2356432456288154e-05,
      "loss": 1.0501034736633301,
      "num_input_tokens_seen": 11380581760,
      "step": 40020,
      "train_runtime": 389862.1276,
      "train_tokens_per_second": 29191.299
    },
    {
      "epoch": 1.4163403043296543,
      "grad_norm": 1.5234375,
      "learning_rate": 2.235419799730021e-05,
      "loss": 1.0443290710449218,
      "num_input_tokens_seen": 11383398080,
      "step": 40030,
      "train_runtime": 389957.4993,
      "train_tokens_per_second": 29191.381
    },
    {
      "epoch": 1.416694124593383,
      "grad_norm": 1.53125,
      "learning_rate": 2.2351964208160966e-05,
      "loss": 1.05822811126709,
      "num_input_tokens_seen": 11386258048,
      "step": 40040,
      "train_runtime": 390054.6812,
      "train_tokens_per_second": 29191.441
    },
    {
      "epoch": 1.4170479448571118,
      "grad_norm": 1.578125,
      "learning_rate": 2.2349731088535826e-05,
      "loss": 1.0480676651000977,
      "num_input_tokens_seen": 11389134464,
      "step": 40050,
      "train_runtime": 390152.9132,
      "train_tokens_per_second": 29191.463
    },
    {
      "epoch": 1.4174017651208406,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2347498638090404e-05,
      "loss": 1.046462631225586,
      "num_input_tokens_seen": 11391962304,
      "step": 40060,
      "train_runtime": 390248.5152,
      "train_tokens_per_second": 29191.558
    },
    {
      "epoch": 1.4177555853845694,
      "grad_norm": 1.546875,
      "learning_rate": 2.234526685649055e-05,
      "loss": 1.0428226470947266,
      "num_input_tokens_seen": 11394846720,
      "step": 40070,
      "train_runtime": 390346.881,
      "train_tokens_per_second": 29191.592
    },
    {
      "epoch": 1.4181094056482983,
      "grad_norm": 1.5390625,
      "learning_rate": 2.234303574340235e-05,
      "loss": 1.055576992034912,
      "num_input_tokens_seen": 11397669696,
      "step": 40080,
      "train_runtime": 390442.264,
      "train_tokens_per_second": 29191.69
    },
    {
      "epoch": 1.418463225912027,
      "grad_norm": 1.53125,
      "learning_rate": 2.234080529849214e-05,
      "loss": 1.044771385192871,
      "num_input_tokens_seen": 11400518080,
      "step": 40090,
      "train_runtime": 390541.7946,
      "train_tokens_per_second": 29191.544
    },
    {
      "epoch": 1.4188170461757559,
      "grad_norm": 1.59375,
      "learning_rate": 2.2338575521426467e-05,
      "loss": 1.045384120941162,
      "num_input_tokens_seen": 11403364352,
      "step": 40100,
      "train_runtime": 390640.9999,
      "train_tokens_per_second": 29191.417
    },
    {
      "epoch": 1.4191708664394846,
      "grad_norm": 1.546875,
      "learning_rate": 2.2336346411872113e-05,
      "loss": 1.0332416534423827,
      "num_input_tokens_seen": 11406277248,
      "step": 40110,
      "train_runtime": 390740.7292,
      "train_tokens_per_second": 29191.421
    },
    {
      "epoch": 1.4195246867032134,
      "grad_norm": 1.515625,
      "learning_rate": 2.2334117969496103e-05,
      "loss": 1.05528564453125,
      "num_input_tokens_seen": 11409132672,
      "step": 40120,
      "train_runtime": 390835.6925,
      "train_tokens_per_second": 29191.634
    },
    {
      "epoch": 1.4198785069669422,
      "grad_norm": 1.5,
      "learning_rate": 2.2331890193965688e-05,
      "loss": 1.0416860580444336,
      "num_input_tokens_seen": 11411977280,
      "step": 40130,
      "train_runtime": 390934.7157,
      "train_tokens_per_second": 29191.517
    },
    {
      "epoch": 1.420232327230671,
      "grad_norm": 1.46875,
      "learning_rate": 2.2329663084948358e-05,
      "loss": 1.0484854698181152,
      "num_input_tokens_seen": 11414848768,
      "step": 40140,
      "train_runtime": 391032.0986,
      "train_tokens_per_second": 29191.59
    },
    {
      "epoch": 1.4205861474943997,
      "grad_norm": 1.578125,
      "learning_rate": 2.2327436642111822e-05,
      "loss": 1.037376308441162,
      "num_input_tokens_seen": 11417682944,
      "step": 40150,
      "train_runtime": 391127.4374,
      "train_tokens_per_second": 29191.721
    },
    {
      "epoch": 1.4209399677581285,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2325210865124034e-05,
      "loss": 1.057407760620117,
      "num_input_tokens_seen": 11420514240,
      "step": 40160,
      "train_runtime": 391225.2514,
      "train_tokens_per_second": 29191.659
    },
    {
      "epoch": 1.4212937880218572,
      "grad_norm": 1.546875,
      "learning_rate": 2.2322985753653177e-05,
      "loss": 1.050730323791504,
      "num_input_tokens_seen": 11423375296,
      "step": 40170,
      "train_runtime": 391320.5525,
      "train_tokens_per_second": 29191.861
    },
    {
      "epoch": 1.421647608285586,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2320761307367658e-05,
      "loss": 1.0421464920043946,
      "num_input_tokens_seen": 11426219264,
      "step": 40180,
      "train_runtime": 391418.6507,
      "train_tokens_per_second": 29191.811
    },
    {
      "epoch": 1.4220014285493148,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2318537525936124e-05,
      "loss": 1.0467681884765625,
      "num_input_tokens_seen": 11429033600,
      "step": 40190,
      "train_runtime": 391515.2475,
      "train_tokens_per_second": 29191.797
    },
    {
      "epoch": 1.4223552488130435,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2316314409027443e-05,
      "loss": 1.0425706863403321,
      "num_input_tokens_seen": 11431858624,
      "step": 40200,
      "train_runtime": 391613.4077,
      "train_tokens_per_second": 29191.694
    },
    {
      "epoch": 1.4227090690767723,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2314091956310723e-05,
      "loss": 1.0442602157592773,
      "num_input_tokens_seen": 11434702080,
      "step": 40210,
      "train_runtime": 391711.022,
      "train_tokens_per_second": 29191.678
    },
    {
      "epoch": 1.423062889340501,
      "grad_norm": 1.5078125,
      "learning_rate": 2.231187016745531e-05,
      "loss": 1.051041316986084,
      "num_input_tokens_seen": 11437572544,
      "step": 40220,
      "train_runtime": 391812.1681,
      "train_tokens_per_second": 29191.468
    },
    {
      "epoch": 1.42341670960423,
      "grad_norm": 1.5078125,
      "learning_rate": 2.2309649042130753e-05,
      "loss": 1.0279705047607421,
      "num_input_tokens_seen": 11440431808,
      "step": 40230,
      "train_runtime": 391911.6743,
      "train_tokens_per_second": 29191.352
    },
    {
      "epoch": 1.4237705298679586,
      "grad_norm": 1.5703125,
      "learning_rate": 2.2307428580006863e-05,
      "loss": 1.034186553955078,
      "num_input_tokens_seen": 11443291968,
      "step": 40240,
      "train_runtime": 392009.7479,
      "train_tokens_per_second": 29191.345
    },
    {
      "epoch": 1.4241243501316876,
      "grad_norm": 1.5390625,
      "learning_rate": 2.230520878075366e-05,
      "loss": 1.0449962615966797,
      "num_input_tokens_seen": 11446056000,
      "step": 40250,
      "train_runtime": 392101.4276,
      "train_tokens_per_second": 29191.569
    },
    {
      "epoch": 1.4244781703954161,
      "grad_norm": 1.5078125,
      "learning_rate": 2.2302989644041396e-05,
      "loss": 1.0418746948242188,
      "num_input_tokens_seen": 11448894656,
      "step": 40260,
      "train_runtime": 392197.0003,
      "train_tokens_per_second": 29191.694
    },
    {
      "epoch": 1.4248319906591451,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2300771169540562e-05,
      "loss": 1.0475712776184083,
      "num_input_tokens_seen": 11451740096,
      "step": 40270,
      "train_runtime": 392292.4986,
      "train_tokens_per_second": 29191.841
    },
    {
      "epoch": 1.4251858109228739,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2298553356921874e-05,
      "loss": 1.0458477020263672,
      "num_input_tokens_seen": 11454567040,
      "step": 40280,
      "train_runtime": 392386.8516,
      "train_tokens_per_second": 29192.026
    },
    {
      "epoch": 1.4255396311866027,
      "grad_norm": 1.6484375,
      "learning_rate": 2.2296336205856278e-05,
      "loss": 1.0575248718261718,
      "num_input_tokens_seen": 11457382976,
      "step": 40290,
      "train_runtime": 392481.4958,
      "train_tokens_per_second": 29192.161
    },
    {
      "epoch": 1.4258934514503314,
      "grad_norm": 1.5078125,
      "learning_rate": 2.2294119716014944e-05,
      "loss": 1.038258171081543,
      "num_input_tokens_seen": 11460279872,
      "step": 40300,
      "train_runtime": 392585.1201,
      "train_tokens_per_second": 29191.835
    },
    {
      "epoch": 1.4262472717140602,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2291903887069275e-05,
      "loss": 1.0444435119628905,
      "num_input_tokens_seen": 11463110400,
      "step": 40310,
      "train_runtime": 392680.752,
      "train_tokens_per_second": 29191.934
    },
    {
      "epoch": 1.426601091977789,
      "grad_norm": 1.5390625,
      "learning_rate": 2.22896887186909e-05,
      "loss": 1.0557172775268555,
      "num_input_tokens_seen": 11465984384,
      "step": 40320,
      "train_runtime": 392781.1389,
      "train_tokens_per_second": 29191.79
    },
    {
      "epoch": 1.4269549122415177,
      "grad_norm": 1.53125,
      "learning_rate": 2.2287474210551678e-05,
      "loss": 1.0416687965393066,
      "num_input_tokens_seen": 11468849600,
      "step": 40330,
      "train_runtime": 392881.5545,
      "train_tokens_per_second": 29191.621
    },
    {
      "epoch": 1.4273087325052465,
      "grad_norm": 1.5859375,
      "learning_rate": 2.22852603623237e-05,
      "loss": 1.0503323554992676,
      "num_input_tokens_seen": 11471715584,
      "step": 40340,
      "train_runtime": 392979.2461,
      "train_tokens_per_second": 29191.658
    },
    {
      "epoch": 1.4276625527689752,
      "grad_norm": 1.515625,
      "learning_rate": 2.2283047173679276e-05,
      "loss": 1.0425731658935546,
      "num_input_tokens_seen": 11474555008,
      "step": 40350,
      "train_runtime": 393076.632,
      "train_tokens_per_second": 29191.649
    },
    {
      "epoch": 1.428016373032704,
      "grad_norm": 1.46875,
      "learning_rate": 2.2280834644290958e-05,
      "loss": 1.035398292541504,
      "num_input_tokens_seen": 11477404096,
      "step": 40360,
      "train_runtime": 393175.0416,
      "train_tokens_per_second": 29191.589
    },
    {
      "epoch": 1.4283701932964328,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2278622773831507e-05,
      "loss": 1.04400691986084,
      "num_input_tokens_seen": 11480238592,
      "step": 40370,
      "train_runtime": 393270.5724,
      "train_tokens_per_second": 29191.705
    },
    {
      "epoch": 1.4287240135601615,
      "grad_norm": 1.5703125,
      "learning_rate": 2.227641156197392e-05,
      "loss": 1.0421079635620116,
      "num_input_tokens_seen": 11483001536,
      "step": 40380,
      "train_runtime": 393362.1955,
      "train_tokens_per_second": 29191.93
    },
    {
      "epoch": 1.4290778338238903,
      "grad_norm": 1.609375,
      "learning_rate": 2.227420100839143e-05,
      "loss": 1.0457950592041017,
      "num_input_tokens_seen": 11485833152,
      "step": 40390,
      "train_runtime": 393458.233,
      "train_tokens_per_second": 29192.001
    },
    {
      "epoch": 1.4294316540876193,
      "grad_norm": 1.5,
      "learning_rate": 2.227199111275749e-05,
      "loss": 1.0480183601379394,
      "num_input_tokens_seen": 11488681728,
      "step": 40400,
      "train_runtime": 393556.1217,
      "train_tokens_per_second": 29191.978
    },
    {
      "epoch": 1.4297854743513478,
      "grad_norm": 1.625,
      "learning_rate": 2.226978187474577e-05,
      "loss": 1.0503217697143554,
      "num_input_tokens_seen": 11491614080,
      "step": 40410,
      "train_runtime": 393658.2634,
      "train_tokens_per_second": 29191.853
    },
    {
      "epoch": 1.4301392946150768,
      "grad_norm": 1.578125,
      "learning_rate": 2.226757329403018e-05,
      "loss": 1.0462230682373046,
      "num_input_tokens_seen": 11494459264,
      "step": 40420,
      "train_runtime": 393754.8116,
      "train_tokens_per_second": 29191.921
    },
    {
      "epoch": 1.4304931148788054,
      "grad_norm": 1.5703125,
      "learning_rate": 2.226536537028485e-05,
      "loss": 1.050889778137207,
      "num_input_tokens_seen": 11497338880,
      "step": 40430,
      "train_runtime": 393854.2034,
      "train_tokens_per_second": 29191.865
    },
    {
      "epoch": 1.4308469351425344,
      "grad_norm": 1.5,
      "learning_rate": 2.2263158103184143e-05,
      "loss": 1.0412408828735351,
      "num_input_tokens_seen": 11500204352,
      "step": 40440,
      "train_runtime": 393951.8686,
      "train_tokens_per_second": 29191.902
    },
    {
      "epoch": 1.4312007554062631,
      "grad_norm": 1.515625,
      "learning_rate": 2.2260951492402636e-05,
      "loss": 1.0434948921203613,
      "num_input_tokens_seen": 11502991680,
      "step": 40450,
      "train_runtime": 394045.4041,
      "train_tokens_per_second": 29192.046
    },
    {
      "epoch": 1.431554575669992,
      "grad_norm": 1.5234375,
      "learning_rate": 2.225874553761514e-05,
      "loss": 1.0416189193725587,
      "num_input_tokens_seen": 11505850112,
      "step": 40460,
      "train_runtime": 394140.8536,
      "train_tokens_per_second": 29192.229
    },
    {
      "epoch": 1.4319083959337207,
      "grad_norm": 1.6015625,
      "learning_rate": 2.2256540238496687e-05,
      "loss": 1.0286125183105468,
      "num_input_tokens_seen": 11508674048,
      "step": 40470,
      "train_runtime": 394236.8393,
      "train_tokens_per_second": 29192.285
    },
    {
      "epoch": 1.4322622161974494,
      "grad_norm": 1.5390625,
      "learning_rate": 2.225433559472255e-05,
      "loss": 1.0434803009033202,
      "num_input_tokens_seen": 11511497024,
      "step": 40480,
      "train_runtime": 394334.5857,
      "train_tokens_per_second": 29192.207
    },
    {
      "epoch": 1.4326160364611782,
      "grad_norm": 1.578125,
      "learning_rate": 2.22521316059682e-05,
      "loss": 1.037852954864502,
      "num_input_tokens_seen": 11514339264,
      "step": 40490,
      "train_runtime": 394430.6602,
      "train_tokens_per_second": 29192.303
    },
    {
      "epoch": 1.432969856724907,
      "grad_norm": 1.4921875,
      "learning_rate": 2.224992827190935e-05,
      "loss": 1.0581388473510742,
      "num_input_tokens_seen": 11517171136,
      "step": 40500,
      "train_runtime": 394527.5537,
      "train_tokens_per_second": 29192.311
    },
    {
      "epoch": 1.4333236769886357,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2247725592221942e-05,
      "loss": 1.0539109230041503,
      "num_input_tokens_seen": 11520055104,
      "step": 40510,
      "train_runtime": 394627.7421,
      "train_tokens_per_second": 29192.208
    },
    {
      "epoch": 1.4336774972523645,
      "grad_norm": 1.5703125,
      "learning_rate": 2.224552356658213e-05,
      "loss": 1.0471458435058594,
      "num_input_tokens_seen": 11522938176,
      "step": 40520,
      "train_runtime": 394729.7138,
      "train_tokens_per_second": 29191.971
    },
    {
      "epoch": 1.4340313175160933,
      "grad_norm": 1.546875,
      "learning_rate": 2.2243322194666296e-05,
      "loss": 1.0536922454833983,
      "num_input_tokens_seen": 11525780544,
      "step": 40530,
      "train_runtime": 394826.9752,
      "train_tokens_per_second": 29191.978
    },
    {
      "epoch": 1.434385137779822,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2241121476151057e-05,
      "loss": 1.0487850189208985,
      "num_input_tokens_seen": 11528624000,
      "step": 40540,
      "train_runtime": 394922.7891,
      "train_tokens_per_second": 29192.096
    },
    {
      "epoch": 1.4347389580435508,
      "grad_norm": 1.4921875,
      "learning_rate": 2.2238921410713234e-05,
      "loss": 1.0326763153076173,
      "num_input_tokens_seen": 11531470016,
      "step": 40550,
      "train_runtime": 395019.6787,
      "train_tokens_per_second": 29192.141
    },
    {
      "epoch": 1.4350927783072795,
      "grad_norm": 1.546875,
      "learning_rate": 2.223672199802989e-05,
      "loss": 1.0505352020263672,
      "num_input_tokens_seen": 11534291712,
      "step": 40560,
      "train_runtime": 395117.1501,
      "train_tokens_per_second": 29192.081
    },
    {
      "epoch": 1.4354465985710085,
      "grad_norm": 1.5625,
      "learning_rate": 2.2234523237778308e-05,
      "loss": 1.0437631607055664,
      "num_input_tokens_seen": 11537152192,
      "step": 40570,
      "train_runtime": 395218.1203,
      "train_tokens_per_second": 29191.86
    },
    {
      "epoch": 1.435800418834737,
      "grad_norm": 1.609375,
      "learning_rate": 2.2232325129635972e-05,
      "loss": 1.0477143287658692,
      "num_input_tokens_seen": 11539980224,
      "step": 40580,
      "train_runtime": 395315.0069,
      "train_tokens_per_second": 29191.86
    },
    {
      "epoch": 1.436154239098466,
      "grad_norm": 1.546875,
      "learning_rate": 2.2230127673280628e-05,
      "loss": 1.0545995712280274,
      "num_input_tokens_seen": 11542885888,
      "step": 40590,
      "train_runtime": 395417.5701,
      "train_tokens_per_second": 29191.636
    },
    {
      "epoch": 1.4365080593621946,
      "grad_norm": 1.515625,
      "learning_rate": 2.222793086839022e-05,
      "loss": 1.0390766143798829,
      "num_input_tokens_seen": 11545725440,
      "step": 40600,
      "train_runtime": 395518.1609,
      "train_tokens_per_second": 29191.391
    },
    {
      "epoch": 1.4368618796259236,
      "grad_norm": 1.6328125,
      "learning_rate": 2.222573471464291e-05,
      "loss": 1.0442255020141602,
      "num_input_tokens_seen": 11548548416,
      "step": 40610,
      "train_runtime": 395616.5321,
      "train_tokens_per_second": 29191.269
    },
    {
      "epoch": 1.4372156998896524,
      "grad_norm": 1.546875,
      "learning_rate": 2.22235392117171e-05,
      "loss": 1.0517688751220704,
      "num_input_tokens_seen": 11551403648,
      "step": 40620,
      "train_runtime": 395714.6795,
      "train_tokens_per_second": 29191.244
    },
    {
      "epoch": 1.4375695201533811,
      "grad_norm": 1.59375,
      "learning_rate": 2.22213443592914e-05,
      "loss": 1.0470075607299805,
      "num_input_tokens_seen": 11554256640,
      "step": 40630,
      "train_runtime": 395813.0091,
      "train_tokens_per_second": 29191.2
    },
    {
      "epoch": 1.43792334041711,
      "grad_norm": 1.5625,
      "learning_rate": 2.221915015704465e-05,
      "loss": 1.049504280090332,
      "num_input_tokens_seen": 11557072000,
      "step": 40640,
      "train_runtime": 395907.3491,
      "train_tokens_per_second": 29191.355
    },
    {
      "epoch": 1.4382771606808387,
      "grad_norm": 1.546875,
      "learning_rate": 2.221695660465592e-05,
      "loss": 1.0337453842163087,
      "num_input_tokens_seen": 11559902336,
      "step": 40650,
      "train_runtime": 396006.9965,
      "train_tokens_per_second": 29191.157
    },
    {
      "epoch": 1.4386309809445674,
      "grad_norm": 1.5703125,
      "learning_rate": 2.2214763701804485e-05,
      "loss": 1.0419260025024415,
      "num_input_tokens_seen": 11562712000,
      "step": 40660,
      "train_runtime": 396102.2832,
      "train_tokens_per_second": 29191.228
    },
    {
      "epoch": 1.4389848012082962,
      "grad_norm": 1.5078125,
      "learning_rate": 2.221257144816984e-05,
      "loss": 1.0503210067749023,
      "num_input_tokens_seen": 11565586112,
      "step": 40670,
      "train_runtime": 396199.855,
      "train_tokens_per_second": 29191.293
    },
    {
      "epoch": 1.439338621472025,
      "grad_norm": 1.4609375,
      "learning_rate": 2.2210379843431728e-05,
      "loss": 1.038141632080078,
      "num_input_tokens_seen": 11568444672,
      "step": 40680,
      "train_runtime": 396296.8045,
      "train_tokens_per_second": 29191.365
    },
    {
      "epoch": 1.4396924417357537,
      "grad_norm": 1.515625,
      "learning_rate": 2.220818888727008e-05,
      "loss": 1.054074764251709,
      "num_input_tokens_seen": 11571286464,
      "step": 40690,
      "train_runtime": 396393.1427,
      "train_tokens_per_second": 29191.44
    },
    {
      "epoch": 1.4400462619994825,
      "grad_norm": 1.578125,
      "learning_rate": 2.2205998579365066e-05,
      "loss": 1.0525421142578124,
      "num_input_tokens_seen": 11574163904,
      "step": 40700,
      "train_runtime": 396490.5742,
      "train_tokens_per_second": 29191.523
    },
    {
      "epoch": 1.4404000822632113,
      "grad_norm": 1.5078125,
      "learning_rate": 2.220380891939708e-05,
      "loss": 1.0468564987182618,
      "num_input_tokens_seen": 11577004992,
      "step": 40710,
      "train_runtime": 396585.6953,
      "train_tokens_per_second": 29191.686
    },
    {
      "epoch": 1.44075390252694,
      "grad_norm": 1.53125,
      "learning_rate": 2.220161990704673e-05,
      "loss": 1.0383939743041992,
      "num_input_tokens_seen": 11579829248,
      "step": 40720,
      "train_runtime": 396681.9254,
      "train_tokens_per_second": 29191.724
    },
    {
      "epoch": 1.4411077227906688,
      "grad_norm": 1.578125,
      "learning_rate": 2.2199431541994836e-05,
      "loss": 1.0423402786254883,
      "num_input_tokens_seen": 11582653632,
      "step": 40730,
      "train_runtime": 396779.8476,
      "train_tokens_per_second": 29191.638
    },
    {
      "epoch": 1.4414615430543978,
      "grad_norm": 1.5625,
      "learning_rate": 2.2197243823922452e-05,
      "loss": 1.0414833068847655,
      "num_input_tokens_seen": 11585477120,
      "step": 40740,
      "train_runtime": 396876.5162,
      "train_tokens_per_second": 29191.642
    },
    {
      "epoch": 1.4418153633181263,
      "grad_norm": 1.6875,
      "learning_rate": 2.2195056752510847e-05,
      "loss": 1.0374091148376465,
      "num_input_tokens_seen": 11588314752,
      "step": 40750,
      "train_runtime": 396973.5863,
      "train_tokens_per_second": 29191.652
    },
    {
      "epoch": 1.4421691835818553,
      "grad_norm": 1.546875,
      "learning_rate": 2.2192870327441508e-05,
      "loss": 1.051079559326172,
      "num_input_tokens_seen": 11591223168,
      "step": 40760,
      "train_runtime": 397074.504,
      "train_tokens_per_second": 29191.557
    },
    {
      "epoch": 1.442523003845584,
      "grad_norm": 1.5,
      "learning_rate": 2.219068454839615e-05,
      "loss": 1.0459545135498047,
      "num_input_tokens_seen": 11594067584,
      "step": 40770,
      "train_runtime": 397169.5584,
      "train_tokens_per_second": 29191.733
    },
    {
      "epoch": 1.4428768241093128,
      "grad_norm": 1.578125,
      "learning_rate": 2.218849941505669e-05,
      "loss": 1.0319475173950194,
      "num_input_tokens_seen": 11596892352,
      "step": 40780,
      "train_runtime": 397266.2794,
      "train_tokens_per_second": 29191.736
    },
    {
      "epoch": 1.4432306443730416,
      "grad_norm": 1.4921875,
      "learning_rate": 2.2186314927105285e-05,
      "loss": 1.0504606246948243,
      "num_input_tokens_seen": 11599698048,
      "step": 40790,
      "train_runtime": 397360.5588,
      "train_tokens_per_second": 29191.871
    },
    {
      "epoch": 1.4435844646367704,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2184131084224292e-05,
      "loss": 1.0436793327331544,
      "num_input_tokens_seen": 11602548928,
      "step": 40800,
      "train_runtime": 397458.9574,
      "train_tokens_per_second": 29191.816
    },
    {
      "epoch": 1.4439382849004991,
      "grad_norm": 1.484375,
      "learning_rate": 2.2181947886096305e-05,
      "loss": 1.0282968521118163,
      "num_input_tokens_seen": 11605396096,
      "step": 40810,
      "train_runtime": 397555.4879,
      "train_tokens_per_second": 29191.89
    },
    {
      "epoch": 1.444292105164228,
      "grad_norm": 1.53125,
      "learning_rate": 2.217976533240412e-05,
      "loss": 1.0415470123291015,
      "num_input_tokens_seen": 11608202496,
      "step": 40820,
      "train_runtime": 397650.8477,
      "train_tokens_per_second": 29191.947
    },
    {
      "epoch": 1.4446459254279567,
      "grad_norm": 1.5390625,
      "learning_rate": 2.217758342283076e-05,
      "loss": 1.0513572692871094,
      "num_input_tokens_seen": 11611019392,
      "step": 40830,
      "train_runtime": 397746.4464,
      "train_tokens_per_second": 29192.013
    },
    {
      "epoch": 1.4449997456916854,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2175402157059465e-05,
      "loss": 1.0468131065368653,
      "num_input_tokens_seen": 11613865792,
      "step": 40840,
      "train_runtime": 397843.95,
      "train_tokens_per_second": 29192.013
    },
    {
      "epoch": 1.4453535659554142,
      "grad_norm": 1.4921875,
      "learning_rate": 2.2173221534773696e-05,
      "loss": 1.0407327651977538,
      "num_input_tokens_seen": 11616688384,
      "step": 40850,
      "train_runtime": 397937.9655,
      "train_tokens_per_second": 29192.209
    },
    {
      "epoch": 1.445707386219143,
      "grad_norm": 1.625,
      "learning_rate": 2.217104155565713e-05,
      "loss": 1.0378256797790528,
      "num_input_tokens_seen": 11619584704,
      "step": 40860,
      "train_runtime": 398041.1481,
      "train_tokens_per_second": 29191.918
    },
    {
      "epoch": 1.4460612064828717,
      "grad_norm": 1.53125,
      "learning_rate": 2.2168862219393656e-05,
      "loss": 1.0306124687194824,
      "num_input_tokens_seen": 11622397504,
      "step": 40870,
      "train_runtime": 398135.42,
      "train_tokens_per_second": 29192.071
    },
    {
      "epoch": 1.4464150267466005,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2166683525667382e-05,
      "loss": 1.0399761199951172,
      "num_input_tokens_seen": 11625274112,
      "step": 40880,
      "train_runtime": 398234.7382,
      "train_tokens_per_second": 29192.014
    },
    {
      "epoch": 1.4467688470103293,
      "grad_norm": 1.609375,
      "learning_rate": 2.2164505474162645e-05,
      "loss": 1.054448127746582,
      "num_input_tokens_seen": 11628109952,
      "step": 40890,
      "train_runtime": 398330.0975,
      "train_tokens_per_second": 29192.145
    },
    {
      "epoch": 1.447122667274058,
      "grad_norm": 1.5625,
      "learning_rate": 2.216232806456398e-05,
      "loss": 1.0595831871032715,
      "num_input_tokens_seen": 11630886720,
      "step": 40900,
      "train_runtime": 398422.5725,
      "train_tokens_per_second": 29192.339
    },
    {
      "epoch": 1.447476487537787,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2160151296556163e-05,
      "loss": 1.046468162536621,
      "num_input_tokens_seen": 11633691392,
      "step": 40910,
      "train_runtime": 398517.3564,
      "train_tokens_per_second": 29192.433
    },
    {
      "epoch": 1.4478303078015156,
      "grad_norm": 1.546875,
      "learning_rate": 2.2157975169824165e-05,
      "loss": 1.0486946105957031,
      "num_input_tokens_seen": 11636556800,
      "step": 40920,
      "train_runtime": 398615.812,
      "train_tokens_per_second": 29192.411
    },
    {
      "epoch": 1.4481841280652445,
      "grad_norm": 1.578125,
      "learning_rate": 2.2155799684053176e-05,
      "loss": 1.056875991821289,
      "num_input_tokens_seen": 11639413632,
      "step": 40930,
      "train_runtime": 398713.7253,
      "train_tokens_per_second": 29192.408
    },
    {
      "epoch": 1.4485379483289733,
      "grad_norm": 1.5625,
      "learning_rate": 2.215362483892862e-05,
      "loss": 1.0640172958374023,
      "num_input_tokens_seen": 11642220480,
      "step": 40940,
      "train_runtime": 398808.0418,
      "train_tokens_per_second": 29192.542
    },
    {
      "epoch": 1.448891768592702,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2151450634136108e-05,
      "loss": 1.0391796112060547,
      "num_input_tokens_seen": 11645031872,
      "step": 40950,
      "train_runtime": 398904.0311,
      "train_tokens_per_second": 29192.565
    },
    {
      "epoch": 1.4492455888564308,
      "grad_norm": 1.5703125,
      "learning_rate": 2.2149277069361504e-05,
      "loss": 1.0368310928344726,
      "num_input_tokens_seen": 11647837376,
      "step": 40960,
      "train_runtime": 398999.1426,
      "train_tokens_per_second": 29192.638
    },
    {
      "epoch": 1.4495994091201596,
      "grad_norm": 1.609375,
      "learning_rate": 2.2147104144290857e-05,
      "loss": 1.0468981742858887,
      "num_input_tokens_seen": 11650645696,
      "step": 40970,
      "train_runtime": 399095.3002,
      "train_tokens_per_second": 29192.641
    },
    {
      "epoch": 1.4499532293838884,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2144931858610438e-05,
      "loss": 1.0457931518554688,
      "num_input_tokens_seen": 11653494912,
      "step": 40980,
      "train_runtime": 399195.3604,
      "train_tokens_per_second": 29192.461
    },
    {
      "epoch": 1.4503070496476171,
      "grad_norm": 1.5546875,
      "learning_rate": 2.214276021200674e-05,
      "loss": 1.0330873489379884,
      "num_input_tokens_seen": 11656305984,
      "step": 40990,
      "train_runtime": 399291.6867,
      "train_tokens_per_second": 29192.458
    },
    {
      "epoch": 1.450660869911346,
      "grad_norm": 1.65625,
      "learning_rate": 2.2140589204166476e-05,
      "loss": 1.0439936637878418,
      "num_input_tokens_seen": 11659153792,
      "step": 41000,
      "train_runtime": 399388.3846,
      "train_tokens_per_second": 29192.521
    },
    {
      "epoch": 1.4510146901750747,
      "grad_norm": 1.515625,
      "learning_rate": 2.2138418834776557e-05,
      "loss": 1.0346403121948242,
      "num_input_tokens_seen": 11661997248,
      "step": 41010,
      "train_runtime": 399487.5561,
      "train_tokens_per_second": 29192.392
    },
    {
      "epoch": 1.4513685104388034,
      "grad_norm": 1.5,
      "learning_rate": 2.213624910352413e-05,
      "loss": 1.0374399185180665,
      "num_input_tokens_seen": 11664893056,
      "step": 41020,
      "train_runtime": 399588.6646,
      "train_tokens_per_second": 29192.252
    },
    {
      "epoch": 1.4517223307025322,
      "grad_norm": 1.546875,
      "learning_rate": 2.2134080010096532e-05,
      "loss": 1.0471195220947265,
      "num_input_tokens_seen": 11667749184,
      "step": 41030,
      "train_runtime": 399689.934,
      "train_tokens_per_second": 29192.002
    },
    {
      "epoch": 1.452076150966261,
      "grad_norm": 1.609375,
      "learning_rate": 2.213191155418133e-05,
      "loss": 1.0537670135498047,
      "num_input_tokens_seen": 11670609856,
      "step": 41040,
      "train_runtime": 399788.5285,
      "train_tokens_per_second": 29191.958
    },
    {
      "epoch": 1.4524299712299897,
      "grad_norm": 1.5234375,
      "learning_rate": 2.212974373546631e-05,
      "loss": 1.0435978889465332,
      "num_input_tokens_seen": 11673447424,
      "step": 41050,
      "train_runtime": 399886.7424,
      "train_tokens_per_second": 29191.884
    },
    {
      "epoch": 1.4527837914937185,
      "grad_norm": 1.59375,
      "learning_rate": 2.212757655363946e-05,
      "loss": 1.0325845718383788,
      "num_input_tokens_seen": 11676262784,
      "step": 41060,
      "train_runtime": 399981.5869,
      "train_tokens_per_second": 29192.001
    },
    {
      "epoch": 1.4531376117574473,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2125410008388984e-05,
      "loss": 1.0372783660888671,
      "num_input_tokens_seen": 11679105472,
      "step": 41070,
      "train_runtime": 400080.8304,
      "train_tokens_per_second": 29191.865
    },
    {
      "epoch": 1.4534914320211763,
      "grad_norm": 1.6015625,
      "learning_rate": 2.2123244099403306e-05,
      "loss": 1.0257381439208983,
      "num_input_tokens_seen": 11681939456,
      "step": 41080,
      "train_runtime": 400176.7445,
      "train_tokens_per_second": 29191.95
    },
    {
      "epoch": 1.4538452522849048,
      "grad_norm": 1.609375,
      "learning_rate": 2.2121078826371056e-05,
      "loss": 1.0472345352172852,
      "num_input_tokens_seen": 11684796032,
      "step": 41090,
      "train_runtime": 400273.4513,
      "train_tokens_per_second": 29192.034
    },
    {
      "epoch": 1.4541990725486338,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2118914188981088e-05,
      "loss": 1.0358465194702149,
      "num_input_tokens_seen": 11687639744,
      "step": 41100,
      "train_runtime": 400371.9194,
      "train_tokens_per_second": 29191.957
    },
    {
      "epoch": 1.4545528928123626,
      "grad_norm": 1.515625,
      "learning_rate": 2.2116750186922453e-05,
      "loss": 1.0474271774291992,
      "num_input_tokens_seen": 11690419520,
      "step": 41110,
      "train_runtime": 400465.3486,
      "train_tokens_per_second": 29192.088
    },
    {
      "epoch": 1.4549067130760913,
      "grad_norm": 1.5703125,
      "learning_rate": 2.2114586819884432e-05,
      "loss": 1.0510454177856445,
      "num_input_tokens_seen": 11693284544,
      "step": 41120,
      "train_runtime": 400566.0689,
      "train_tokens_per_second": 29191.9
    },
    {
      "epoch": 1.45526053333982,
      "grad_norm": 1.546875,
      "learning_rate": 2.21124240875565e-05,
      "loss": 1.0660600662231445,
      "num_input_tokens_seen": 11696187968,
      "step": 41130,
      "train_runtime": 400667.5123,
      "train_tokens_per_second": 29191.755
    },
    {
      "epoch": 1.4556143536035488,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2110261989628366e-05,
      "loss": 1.0360647201538087,
      "num_input_tokens_seen": 11699114240,
      "step": 41140,
      "train_runtime": 400772.8859,
      "train_tokens_per_second": 29191.382
    },
    {
      "epoch": 1.4559681738672776,
      "grad_norm": 1.5078125,
      "learning_rate": 2.210810052578994e-05,
      "loss": 1.044085693359375,
      "num_input_tokens_seen": 11701960832,
      "step": 41150,
      "train_runtime": 400871.1346,
      "train_tokens_per_second": 29191.328
    },
    {
      "epoch": 1.4563219941310064,
      "grad_norm": 1.5078125,
      "learning_rate": 2.2105939695731333e-05,
      "loss": 1.0406719207763673,
      "num_input_tokens_seen": 11704807872,
      "step": 41160,
      "train_runtime": 400968.2915,
      "train_tokens_per_second": 29191.355
    },
    {
      "epoch": 1.4566758143947351,
      "grad_norm": 1.59375,
      "learning_rate": 2.210377949914289e-05,
      "loss": 1.0352442741394043,
      "num_input_tokens_seen": 11707594944,
      "step": 41170,
      "train_runtime": 401062.0598,
      "train_tokens_per_second": 29191.48
    },
    {
      "epoch": 1.457029634658464,
      "grad_norm": 1.4921875,
      "learning_rate": 2.2101619935715153e-05,
      "loss": 1.0453128814697266,
      "num_input_tokens_seen": 11710382912,
      "step": 41180,
      "train_runtime": 401154.8746,
      "train_tokens_per_second": 29191.675
    },
    {
      "epoch": 1.4573834549221927,
      "grad_norm": 1.4765625,
      "learning_rate": 2.2099461005138885e-05,
      "loss": 1.0396349906921387,
      "num_input_tokens_seen": 11713193856,
      "step": 41190,
      "train_runtime": 401250.8707,
      "train_tokens_per_second": 29191.697
    },
    {
      "epoch": 1.4577372751859214,
      "grad_norm": 1.5625,
      "learning_rate": 2.2097302707105054e-05,
      "loss": 1.037434196472168,
      "num_input_tokens_seen": 11715963584,
      "step": 41200,
      "train_runtime": 401342.6474,
      "train_tokens_per_second": 29191.923
    },
    {
      "epoch": 1.4580910954496502,
      "grad_norm": 1.5703125,
      "learning_rate": 2.209514504130483e-05,
      "loss": 1.0567068099975585,
      "num_input_tokens_seen": 11718841600,
      "step": 41210,
      "train_runtime": 401443.7862,
      "train_tokens_per_second": 29191.737
    },
    {
      "epoch": 1.458444915713379,
      "grad_norm": 1.609375,
      "learning_rate": 2.2092988007429625e-05,
      "loss": 1.0624927520751952,
      "num_input_tokens_seen": 11721698304,
      "step": 41220,
      "train_runtime": 401542.7923,
      "train_tokens_per_second": 29191.654
    },
    {
      "epoch": 1.458798735977108,
      "grad_norm": 1.5703125,
      "learning_rate": 2.209083160517102e-05,
      "loss": 1.046692180633545,
      "num_input_tokens_seen": 11724616320,
      "step": 41230,
      "train_runtime": 401646.6804,
      "train_tokens_per_second": 29191.369
    },
    {
      "epoch": 1.4591525562408365,
      "grad_norm": 1.578125,
      "learning_rate": 2.208867583422084e-05,
      "loss": 1.0482171058654786,
      "num_input_tokens_seen": 11727516416,
      "step": 41240,
      "train_runtime": 401747.6655,
      "train_tokens_per_second": 29191.25
    },
    {
      "epoch": 1.4595063765045655,
      "grad_norm": 1.59375,
      "learning_rate": 2.2086520694271108e-05,
      "loss": 1.0550015449523926,
      "num_input_tokens_seen": 11730358784,
      "step": 41250,
      "train_runtime": 401846.8133,
      "train_tokens_per_second": 29191.121
    },
    {
      "epoch": 1.459860196768294,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2084366185014058e-05,
      "loss": 1.0345678329467773,
      "num_input_tokens_seen": 11733238336,
      "step": 41260,
      "train_runtime": 401946.5463,
      "train_tokens_per_second": 29191.042
    },
    {
      "epoch": 1.460214017032023,
      "grad_norm": 1.53125,
      "learning_rate": 2.208221230614213e-05,
      "loss": 1.0363618850708007,
      "num_input_tokens_seen": 11736064640,
      "step": 41270,
      "train_runtime": 402042.9497,
      "train_tokens_per_second": 29191.072
    },
    {
      "epoch": 1.4605678372957518,
      "grad_norm": 1.6171875,
      "learning_rate": 2.208005905734798e-05,
      "loss": 1.0393327713012694,
      "num_input_tokens_seen": 11738981952,
      "step": 41280,
      "train_runtime": 402142.2306,
      "train_tokens_per_second": 29191.12
    },
    {
      "epoch": 1.4609216575594806,
      "grad_norm": 1.734375,
      "learning_rate": 2.2077906438324474e-05,
      "loss": 1.061495876312256,
      "num_input_tokens_seen": 11741814272,
      "step": 41290,
      "train_runtime": 402237.8789,
      "train_tokens_per_second": 29191.22
    },
    {
      "epoch": 1.4612754778232093,
      "grad_norm": 1.578125,
      "learning_rate": 2.2075754448764683e-05,
      "loss": 1.0450518608093262,
      "num_input_tokens_seen": 11744600640,
      "step": 41300,
      "train_runtime": 402331.7763,
      "train_tokens_per_second": 29191.332
    },
    {
      "epoch": 1.461629298086938,
      "grad_norm": 1.546875,
      "learning_rate": 2.2073603088361887e-05,
      "loss": 1.052476406097412,
      "num_input_tokens_seen": 11747479040,
      "step": 41310,
      "train_runtime": 402431.6748,
      "train_tokens_per_second": 29191.239
    },
    {
      "epoch": 1.4619831183506669,
      "grad_norm": 1.625,
      "learning_rate": 2.2071452356809586e-05,
      "loss": 1.0523114204406738,
      "num_input_tokens_seen": 11750318720,
      "step": 41320,
      "train_runtime": 402527.7311,
      "train_tokens_per_second": 29191.327
    },
    {
      "epoch": 1.4623369386143956,
      "grad_norm": 1.5703125,
      "learning_rate": 2.2069302253801474e-05,
      "loss": 1.046518898010254,
      "num_input_tokens_seen": 11753198720,
      "step": 41330,
      "train_runtime": 402624.8541,
      "train_tokens_per_second": 29191.439
    },
    {
      "epoch": 1.4626907588781244,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2067152779031465e-05,
      "loss": 1.0492050170898437,
      "num_input_tokens_seen": 11756035008,
      "step": 41340,
      "train_runtime": 402719.6634,
      "train_tokens_per_second": 29191.609
    },
    {
      "epoch": 1.4630445791418532,
      "grad_norm": 1.5546875,
      "learning_rate": 2.206500393219367e-05,
      "loss": 1.0442693710327149,
      "num_input_tokens_seen": 11758838976,
      "step": 41350,
      "train_runtime": 402814.2002,
      "train_tokens_per_second": 29191.719
    },
    {
      "epoch": 1.463398399405582,
      "grad_norm": 1.5859375,
      "learning_rate": 2.206285571298242e-05,
      "loss": 1.0590126037597656,
      "num_input_tokens_seen": 11761715328,
      "step": 41360,
      "train_runtime": 402912.9124,
      "train_tokens_per_second": 29191.706
    },
    {
      "epoch": 1.4637522196693107,
      "grad_norm": 1.5234375,
      "learning_rate": 2.206070812109226e-05,
      "loss": 1.0465780258178712,
      "num_input_tokens_seen": 11764582592,
      "step": 41370,
      "train_runtime": 403010.6777,
      "train_tokens_per_second": 29191.739
    },
    {
      "epoch": 1.4641060399330394,
      "grad_norm": 1.578125,
      "learning_rate": 2.2058561156217913e-05,
      "loss": 1.0461875915527343,
      "num_input_tokens_seen": 11767450752,
      "step": 41380,
      "train_runtime": 403108.3868,
      "train_tokens_per_second": 29191.779
    },
    {
      "epoch": 1.4644598601967682,
      "grad_norm": 1.5078125,
      "learning_rate": 2.2056414818054347e-05,
      "loss": 1.025762939453125,
      "num_input_tokens_seen": 11770238464,
      "step": 41390,
      "train_runtime": 403200.3197,
      "train_tokens_per_second": 29192.037
    },
    {
      "epoch": 1.4648136804604972,
      "grad_norm": 1.53125,
      "learning_rate": 2.2054269106296714e-05,
      "loss": 1.0426716804504395,
      "num_input_tokens_seen": 11773071424,
      "step": 41400,
      "train_runtime": 403296.76,
      "train_tokens_per_second": 29192.08
    },
    {
      "epoch": 1.4651675007242257,
      "grad_norm": 1.6796875,
      "learning_rate": 2.205212402064038e-05,
      "loss": 1.0465368270874023,
      "num_input_tokens_seen": 11775928576,
      "step": 41410,
      "train_runtime": 403392.0175,
      "train_tokens_per_second": 29192.27
    },
    {
      "epoch": 1.4655213209879547,
      "grad_norm": 1.5703125,
      "learning_rate": 2.204997956078092e-05,
      "loss": 1.0456119537353517,
      "num_input_tokens_seen": 11778787136,
      "step": 41420,
      "train_runtime": 403489.5029,
      "train_tokens_per_second": 29192.301
    },
    {
      "epoch": 1.4658751412516833,
      "grad_norm": 1.6171875,
      "learning_rate": 2.2047835726414116e-05,
      "loss": 1.044627857208252,
      "num_input_tokens_seen": 11781597376,
      "step": 41430,
      "train_runtime": 403584.7964,
      "train_tokens_per_second": 29192.372
    },
    {
      "epoch": 1.4662289615154123,
      "grad_norm": 1.515625,
      "learning_rate": 2.2045692517235952e-05,
      "loss": 1.0564058303833008,
      "num_input_tokens_seen": 11784486528,
      "step": 41440,
      "train_runtime": 403687.0094,
      "train_tokens_per_second": 29192.137
    },
    {
      "epoch": 1.466582781779141,
      "grad_norm": 1.5703125,
      "learning_rate": 2.204354993294263e-05,
      "loss": 1.025999164581299,
      "num_input_tokens_seen": 11787246976,
      "step": 41450,
      "train_runtime": 403780.8217,
      "train_tokens_per_second": 29192.191
    },
    {
      "epoch": 1.4669366020428698,
      "grad_norm": 1.59375,
      "learning_rate": 2.2041407973230548e-05,
      "loss": 1.0323284149169922,
      "num_input_tokens_seen": 11790027328,
      "step": 41460,
      "train_runtime": 403874.8085,
      "train_tokens_per_second": 29192.282
    },
    {
      "epoch": 1.4672904223065986,
      "grad_norm": 1.546875,
      "learning_rate": 2.203926663779631e-05,
      "loss": 1.0368988037109375,
      "num_input_tokens_seen": 11792876288,
      "step": 41470,
      "train_runtime": 403971.8962,
      "train_tokens_per_second": 29192.319
    },
    {
      "epoch": 1.4676442425703273,
      "grad_norm": 1.515625,
      "learning_rate": 2.2037125926336733e-05,
      "loss": 1.0433948516845704,
      "num_input_tokens_seen": 11795772096,
      "step": 41480,
      "train_runtime": 404074.3439,
      "train_tokens_per_second": 29192.084
    },
    {
      "epoch": 1.467998062834056,
      "grad_norm": 1.515625,
      "learning_rate": 2.2034985838548835e-05,
      "loss": 1.0308919906616212,
      "num_input_tokens_seen": 11798590080,
      "step": 41490,
      "train_runtime": 404171.8253,
      "train_tokens_per_second": 29192.015
    },
    {
      "epoch": 1.4683518830977849,
      "grad_norm": 1.578125,
      "learning_rate": 2.2032846374129848e-05,
      "loss": 1.0398931503295898,
      "num_input_tokens_seen": 11801416064,
      "step": 41500,
      "train_runtime": 404269.4697,
      "train_tokens_per_second": 29191.955
    },
    {
      "epoch": 1.4687057033615136,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2030707532777196e-05,
      "loss": 1.0588146209716798,
      "num_input_tokens_seen": 11804203456,
      "step": 41510,
      "train_runtime": 404363.6303,
      "train_tokens_per_second": 29192.05
    },
    {
      "epoch": 1.4690595236252424,
      "grad_norm": 1.5390625,
      "learning_rate": 2.2028569314188528e-05,
      "loss": 1.0482805252075196,
      "num_input_tokens_seen": 11807072768,
      "step": 41520,
      "train_runtime": 404462.0527,
      "train_tokens_per_second": 29192.041
    },
    {
      "epoch": 1.4694133438889712,
      "grad_norm": 1.578125,
      "learning_rate": 2.2026431718061676e-05,
      "loss": 1.039259433746338,
      "num_input_tokens_seen": 11809909504,
      "step": 41530,
      "train_runtime": 404559.8033,
      "train_tokens_per_second": 29191.999
    },
    {
      "epoch": 1.4697671641527,
      "grad_norm": 1.5859375,
      "learning_rate": 2.202429474409469e-05,
      "loss": 1.0508792877197266,
      "num_input_tokens_seen": 11812725696,
      "step": 41540,
      "train_runtime": 404655.2554,
      "train_tokens_per_second": 29192.073
    },
    {
      "epoch": 1.4701209844164287,
      "grad_norm": 1.53125,
      "learning_rate": 2.202215839198583e-05,
      "loss": 1.0438759803771973,
      "num_input_tokens_seen": 11815580224,
      "step": 41550,
      "train_runtime": 404752.9507,
      "train_tokens_per_second": 29192.079
    },
    {
      "epoch": 1.4704748046801575,
      "grad_norm": 1.546875,
      "learning_rate": 2.2020022661433544e-05,
      "loss": 1.0374098777770997,
      "num_input_tokens_seen": 11818447168,
      "step": 41560,
      "train_runtime": 404850.7085,
      "train_tokens_per_second": 29192.112
    },
    {
      "epoch": 1.4708286249438864,
      "grad_norm": 1.546875,
      "learning_rate": 2.20178875521365e-05,
      "loss": 1.040067768096924,
      "num_input_tokens_seen": 11821257664,
      "step": 41570,
      "train_runtime": 404948.0684,
      "train_tokens_per_second": 29192.034
    },
    {
      "epoch": 1.471182445207615,
      "grad_norm": 1.59375,
      "learning_rate": 2.2015753063793566e-05,
      "loss": 1.0494681358337403,
      "num_input_tokens_seen": 11824069248,
      "step": 41580,
      "train_runtime": 405040.4456,
      "train_tokens_per_second": 29192.317
    },
    {
      "epoch": 1.471536265471344,
      "grad_norm": 1.5703125,
      "learning_rate": 2.2013619196103812e-05,
      "loss": 1.0467537879943847,
      "num_input_tokens_seen": 11826916096,
      "step": 41590,
      "train_runtime": 405138.9522,
      "train_tokens_per_second": 29192.246
    },
    {
      "epoch": 1.4718900857350725,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2011485948766514e-05,
      "loss": 1.0413759231567383,
      "num_input_tokens_seen": 11829774080,
      "step": 41600,
      "train_runtime": 405236.7062,
      "train_tokens_per_second": 29192.257
    },
    {
      "epoch": 1.4722439059988015,
      "grad_norm": 1.5859375,
      "learning_rate": 2.2009353321481148e-05,
      "loss": 1.031088924407959,
      "num_input_tokens_seen": 11832622592,
      "step": 41610,
      "train_runtime": 405332.2654,
      "train_tokens_per_second": 29192.402
    },
    {
      "epoch": 1.4725977262625303,
      "grad_norm": 1.59375,
      "learning_rate": 2.2007221313947404e-05,
      "loss": 1.0509910583496094,
      "num_input_tokens_seen": 11835515584,
      "step": 41620,
      "train_runtime": 405432.1363,
      "train_tokens_per_second": 29192.347
    },
    {
      "epoch": 1.472951546526259,
      "grad_norm": 1.625,
      "learning_rate": 2.2005089925865162e-05,
      "loss": 1.042337131500244,
      "num_input_tokens_seen": 11838331520,
      "step": 41630,
      "train_runtime": 405529.0386,
      "train_tokens_per_second": 29192.315
    },
    {
      "epoch": 1.4733053667899878,
      "grad_norm": 1.5234375,
      "learning_rate": 2.2002959156934518e-05,
      "loss": 1.042196273803711,
      "num_input_tokens_seen": 11841169152,
      "step": 41640,
      "train_runtime": 405623.1734,
      "train_tokens_per_second": 29192.536
    },
    {
      "epoch": 1.4736591870537166,
      "grad_norm": 1.5546875,
      "learning_rate": 2.2000829006855763e-05,
      "loss": 1.0566818237304687,
      "num_input_tokens_seen": 11844018688,
      "step": 41650,
      "train_runtime": 405720.1591,
      "train_tokens_per_second": 29192.581
    },
    {
      "epoch": 1.4740130073174453,
      "grad_norm": 1.53125,
      "learning_rate": 2.199869947532939e-05,
      "loss": 1.0388776779174804,
      "num_input_tokens_seen": 11846870592,
      "step": 41660,
      "train_runtime": 405815.9284,
      "train_tokens_per_second": 29192.72
    },
    {
      "epoch": 1.474366827581174,
      "grad_norm": 1.5625,
      "learning_rate": 2.199657056205611e-05,
      "loss": 1.0442949295043946,
      "num_input_tokens_seen": 11849697280,
      "step": 41670,
      "train_runtime": 405911.6893,
      "train_tokens_per_second": 29192.796
    },
    {
      "epoch": 1.4747206478449029,
      "grad_norm": 1.53125,
      "learning_rate": 2.1994442266736807e-05,
      "loss": 1.0557119369506835,
      "num_input_tokens_seen": 11852599104,
      "step": 41680,
      "train_runtime": 406010.1776,
      "train_tokens_per_second": 29192.862
    },
    {
      "epoch": 1.4750744681086316,
      "grad_norm": 1.59375,
      "learning_rate": 2.1992314589072605e-05,
      "loss": 1.0498502731323243,
      "num_input_tokens_seen": 11855496576,
      "step": 41690,
      "train_runtime": 406112.1147,
      "train_tokens_per_second": 29192.669
    },
    {
      "epoch": 1.4754282883723604,
      "grad_norm": 1.453125,
      "learning_rate": 2.1990187528764796e-05,
      "loss": 1.0423704147338868,
      "num_input_tokens_seen": 11858326784,
      "step": 41700,
      "train_runtime": 406207.4612,
      "train_tokens_per_second": 29192.784
    },
    {
      "epoch": 1.4757821086360892,
      "grad_norm": 1.609375,
      "learning_rate": 2.19880610855149e-05,
      "loss": 1.0341442108154297,
      "num_input_tokens_seen": 11861230528,
      "step": 41710,
      "train_runtime": 406304.5466,
      "train_tokens_per_second": 29192.955
    },
    {
      "epoch": 1.476135928899818,
      "grad_norm": 1.5625,
      "learning_rate": 2.1985935259024618e-05,
      "loss": 1.0339225769042968,
      "num_input_tokens_seen": 11864121472,
      "step": 41720,
      "train_runtime": 406404.3474,
      "train_tokens_per_second": 29192.9
    },
    {
      "epoch": 1.4764897491635467,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1983810048995874e-05,
      "loss": 1.0435525894165039,
      "num_input_tokens_seen": 11866918208,
      "step": 41730,
      "train_runtime": 406499.6782,
      "train_tokens_per_second": 29192.934
    },
    {
      "epoch": 1.4768435694272757,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1981685455130778e-05,
      "loss": 1.062387180328369,
      "num_input_tokens_seen": 11869772224,
      "step": 41740,
      "train_runtime": 406599.945,
      "train_tokens_per_second": 29192.754
    },
    {
      "epoch": 1.4771973896910042,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1979561477131642e-05,
      "loss": 1.0386247634887695,
      "num_input_tokens_seen": 11872650752,
      "step": 41750,
      "train_runtime": 406700.3702,
      "train_tokens_per_second": 29192.623
    },
    {
      "epoch": 1.4775512099547332,
      "grad_norm": 1.59375,
      "learning_rate": 2.197743811470099e-05,
      "loss": 1.0492256164550782,
      "num_input_tokens_seen": 11875491328,
      "step": 41760,
      "train_runtime": 406796.9918,
      "train_tokens_per_second": 29192.672
    },
    {
      "epoch": 1.477905030218462,
      "grad_norm": 1.5703125,
      "learning_rate": 2.197531536754154e-05,
      "loss": 1.0409231185913086,
      "num_input_tokens_seen": 11878366272,
      "step": 41770,
      "train_runtime": 406897.0638,
      "train_tokens_per_second": 29192.558
    },
    {
      "epoch": 1.4782588504821907,
      "grad_norm": 1.546875,
      "learning_rate": 2.1973193235356205e-05,
      "loss": 1.037760353088379,
      "num_input_tokens_seen": 11881177856,
      "step": 41780,
      "train_runtime": 406994.199,
      "train_tokens_per_second": 29192.499
    },
    {
      "epoch": 1.4786126707459195,
      "grad_norm": 1.59375,
      "learning_rate": 2.197107171784811e-05,
      "loss": 1.0423807144165038,
      "num_input_tokens_seen": 11884000640,
      "step": 41790,
      "train_runtime": 407086.5214,
      "train_tokens_per_second": 29192.813
    },
    {
      "epoch": 1.4789664910096483,
      "grad_norm": 1.53125,
      "learning_rate": 2.196895081472058e-05,
      "loss": 1.032763671875,
      "num_input_tokens_seen": 11886802112,
      "step": 41800,
      "train_runtime": 407183.9525,
      "train_tokens_per_second": 29192.708
    },
    {
      "epoch": 1.479320311273377,
      "grad_norm": 1.578125,
      "learning_rate": 2.196683052567713e-05,
      "loss": 1.034012794494629,
      "num_input_tokens_seen": 11889605760,
      "step": 41810,
      "train_runtime": 407281.2312,
      "train_tokens_per_second": 29192.619
    },
    {
      "epoch": 1.4796741315371058,
      "grad_norm": 1.59375,
      "learning_rate": 2.1964710850421486e-05,
      "loss": 1.0540048599243164,
      "num_input_tokens_seen": 11892479424,
      "step": 41820,
      "train_runtime": 407377.7839,
      "train_tokens_per_second": 29192.754
    },
    {
      "epoch": 1.4800279518008346,
      "grad_norm": 1.546875,
      "learning_rate": 2.196259178865757e-05,
      "loss": 1.047801399230957,
      "num_input_tokens_seen": 11895332288,
      "step": 41830,
      "train_runtime": 407475.0464,
      "train_tokens_per_second": 29192.787
    },
    {
      "epoch": 1.4803817720645633,
      "grad_norm": 1.6328125,
      "learning_rate": 2.1960473340089502e-05,
      "loss": 1.0426290512084961,
      "num_input_tokens_seen": 11898161408,
      "step": 41840,
      "train_runtime": 407572.7828,
      "train_tokens_per_second": 29192.728
    },
    {
      "epoch": 1.480735592328292,
      "grad_norm": 1.5703125,
      "learning_rate": 2.19583555044216e-05,
      "loss": 1.0480476379394532,
      "num_input_tokens_seen": 11900976064,
      "step": 41850,
      "train_runtime": 407668.7041,
      "train_tokens_per_second": 29192.763
    },
    {
      "epoch": 1.4810894125920209,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1956238281358394e-05,
      "loss": 1.0446859359741212,
      "num_input_tokens_seen": 11903796608,
      "step": 41860,
      "train_runtime": 407762.2055,
      "train_tokens_per_second": 29192.987
    },
    {
      "epoch": 1.4814432328557496,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1954121670604595e-05,
      "loss": 1.0473766326904297,
      "num_input_tokens_seen": 11906668864,
      "step": 41870,
      "train_runtime": 407861.1203,
      "train_tokens_per_second": 29192.949
    },
    {
      "epoch": 1.4817970531194784,
      "grad_norm": 1.578125,
      "learning_rate": 2.1952005671865124e-05,
      "loss": 1.0395652770996093,
      "num_input_tokens_seen": 11909509120,
      "step": 41880,
      "train_runtime": 407957.0914,
      "train_tokens_per_second": 29193.044
    },
    {
      "epoch": 1.4821508733832072,
      "grad_norm": 1.59375,
      "learning_rate": 2.194989028484511e-05,
      "loss": 1.0352354049682617,
      "num_input_tokens_seen": 11912281088,
      "step": 41890,
      "train_runtime": 408051.088,
      "train_tokens_per_second": 29193.112
    },
    {
      "epoch": 1.482504693646936,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1947775509249857e-05,
      "loss": 1.0341602325439454,
      "num_input_tokens_seen": 11915101440,
      "step": 41900,
      "train_runtime": 408147.8931,
      "train_tokens_per_second": 29193.098
    },
    {
      "epoch": 1.482858513910665,
      "grad_norm": 1.5,
      "learning_rate": 2.194566134478489e-05,
      "loss": 1.0491454124450683,
      "num_input_tokens_seen": 11917887168,
      "step": 41910,
      "train_runtime": 408239.6565,
      "train_tokens_per_second": 29193.36
    },
    {
      "epoch": 1.4832123341743935,
      "grad_norm": 1.625,
      "learning_rate": 2.1943547791155918e-05,
      "loss": 1.0488490104675292,
      "num_input_tokens_seen": 11920766592,
      "step": 41920,
      "train_runtime": 408336.6398,
      "train_tokens_per_second": 29193.478
    },
    {
      "epoch": 1.4835661544381225,
      "grad_norm": 1.5625,
      "learning_rate": 2.1941434848068865e-05,
      "loss": 1.0422578811645509,
      "num_input_tokens_seen": 11923626560,
      "step": 41930,
      "train_runtime": 408432.5021,
      "train_tokens_per_second": 29193.628
    },
    {
      "epoch": 1.4839199747018512,
      "grad_norm": 1.5546875,
      "learning_rate": 2.193932251522983e-05,
      "loss": 1.026353359222412,
      "num_input_tokens_seen": 11926494080,
      "step": 41940,
      "train_runtime": 408533.287,
      "train_tokens_per_second": 29193.445
    },
    {
      "epoch": 1.48427379496558,
      "grad_norm": 1.578125,
      "learning_rate": 2.1937210792345127e-05,
      "loss": 1.0463303565979003,
      "num_input_tokens_seen": 11929369280,
      "step": 41950,
      "train_runtime": 408633.6282,
      "train_tokens_per_second": 29193.313
    },
    {
      "epoch": 1.4846276152293088,
      "grad_norm": 1.578125,
      "learning_rate": 2.193509967912126e-05,
      "loss": 1.0381989479064941,
      "num_input_tokens_seen": 11932191616,
      "step": 41960,
      "train_runtime": 408730.6604,
      "train_tokens_per_second": 29193.287
    },
    {
      "epoch": 1.4849814354930375,
      "grad_norm": 1.5546875,
      "learning_rate": 2.193298917526494e-05,
      "loss": 1.0350196838378907,
      "num_input_tokens_seen": 11935069632,
      "step": 41970,
      "train_runtime": 408829.5725,
      "train_tokens_per_second": 29193.264
    },
    {
      "epoch": 1.4853352557567663,
      "grad_norm": 1.5,
      "learning_rate": 2.1930879280483068e-05,
      "loss": 1.0481773376464845,
      "num_input_tokens_seen": 11937905984,
      "step": 41980,
      "train_runtime": 408926.3808,
      "train_tokens_per_second": 29193.289
    },
    {
      "epoch": 1.485689076020495,
      "grad_norm": 1.5,
      "learning_rate": 2.1928769994482743e-05,
      "loss": 1.0512334823608398,
      "num_input_tokens_seen": 11940753536,
      "step": 41990,
      "train_runtime": 409024.4082,
      "train_tokens_per_second": 29193.254
    },
    {
      "epoch": 1.4860428962842238,
      "grad_norm": 1.5078125,
      "learning_rate": 2.1926661316971257e-05,
      "loss": 1.0553668975830077,
      "num_input_tokens_seen": 11943568640,
      "step": 42000,
      "train_runtime": 409117.9687,
      "train_tokens_per_second": 29193.459
    },
    {
      "epoch": 1.4863967165479526,
      "grad_norm": 1.5859375,
      "learning_rate": 2.192455324765611e-05,
      "loss": 1.0476322174072266,
      "num_input_tokens_seen": 11946471296,
      "step": 42010,
      "train_runtime": 409222.609,
      "train_tokens_per_second": 29193.087
    },
    {
      "epoch": 1.4867505368116813,
      "grad_norm": 1.6171875,
      "learning_rate": 2.192244578624499e-05,
      "loss": 1.047531509399414,
      "num_input_tokens_seen": 11949288896,
      "step": 42020,
      "train_runtime": 409318.3913,
      "train_tokens_per_second": 29193.139
    },
    {
      "epoch": 1.48710435707541,
      "grad_norm": 1.546875,
      "learning_rate": 2.1920338932445783e-05,
      "loss": 1.0479537963867187,
      "num_input_tokens_seen": 11952160768,
      "step": 42030,
      "train_runtime": 409417.4394,
      "train_tokens_per_second": 29193.091
    },
    {
      "epoch": 1.4874581773391389,
      "grad_norm": 1.5078125,
      "learning_rate": 2.191823268596658e-05,
      "loss": 1.0573183059692384,
      "num_input_tokens_seen": 11955001600,
      "step": 42040,
      "train_runtime": 409515.7302,
      "train_tokens_per_second": 29193.022
    },
    {
      "epoch": 1.4878119976028676,
      "grad_norm": 1.625,
      "learning_rate": 2.191612704651565e-05,
      "loss": 1.0413215637207032,
      "num_input_tokens_seen": 11957859520,
      "step": 42050,
      "train_runtime": 409614.7208,
      "train_tokens_per_second": 29192.944
    },
    {
      "epoch": 1.4881658178665966,
      "grad_norm": 1.625,
      "learning_rate": 2.191402201380148e-05,
      "loss": 1.047816848754883,
      "num_input_tokens_seen": 11960717312,
      "step": 42060,
      "train_runtime": 409711.0821,
      "train_tokens_per_second": 29193.053
    },
    {
      "epoch": 1.4885196381303252,
      "grad_norm": 1.5390625,
      "learning_rate": 2.191191758753273e-05,
      "loss": 1.0452162742614746,
      "num_input_tokens_seen": 11963604416,
      "step": 42070,
      "train_runtime": 409808.7145,
      "train_tokens_per_second": 29193.143
    },
    {
      "epoch": 1.4888734583940542,
      "grad_norm": 1.5625,
      "learning_rate": 2.190981376741828e-05,
      "loss": 1.034780502319336,
      "num_input_tokens_seen": 11966445696,
      "step": 42080,
      "train_runtime": 409906.2744,
      "train_tokens_per_second": 29193.126
    },
    {
      "epoch": 1.4892272786577827,
      "grad_norm": 1.53125,
      "learning_rate": 2.190771055316719e-05,
      "loss": 1.0443185806274413,
      "num_input_tokens_seen": 11969239296,
      "step": 42090,
      "train_runtime": 410000.8354,
      "train_tokens_per_second": 29193.207
    },
    {
      "epoch": 1.4895810989215117,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1905607944488718e-05,
      "loss": 1.056391143798828,
      "num_input_tokens_seen": 11972024704,
      "step": 42100,
      "train_runtime": 410095.1891,
      "train_tokens_per_second": 29193.282
    },
    {
      "epoch": 1.4899349191852405,
      "grad_norm": 1.53125,
      "learning_rate": 2.1903505941092315e-05,
      "loss": 1.0540189743041992,
      "num_input_tokens_seen": 11974864512,
      "step": 42110,
      "train_runtime": 410196.259,
      "train_tokens_per_second": 29193.012
    },
    {
      "epoch": 1.4902887394489692,
      "grad_norm": 1.5078125,
      "learning_rate": 2.1901404542687634e-05,
      "loss": 1.036434268951416,
      "num_input_tokens_seen": 11977747904,
      "step": 42120,
      "train_runtime": 410294.9798,
      "train_tokens_per_second": 29193.016
    },
    {
      "epoch": 1.490642559712698,
      "grad_norm": 1.6015625,
      "learning_rate": 2.189930374898452e-05,
      "loss": 1.0434698104858398,
      "num_input_tokens_seen": 11980582336,
      "step": 42130,
      "train_runtime": 410390.9941,
      "train_tokens_per_second": 29193.093
    },
    {
      "epoch": 1.4909963799764268,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1897203559693018e-05,
      "loss": 1.0390192031860352,
      "num_input_tokens_seen": 11983450432,
      "step": 42140,
      "train_runtime": 410492.5106,
      "train_tokens_per_second": 29192.86
    },
    {
      "epoch": 1.4913502002401555,
      "grad_norm": 1.46875,
      "learning_rate": 2.1895103974523347e-05,
      "loss": 1.0304597854614257,
      "num_input_tokens_seen": 11986294720,
      "step": 42150,
      "train_runtime": 410590.6493,
      "train_tokens_per_second": 29192.81
    },
    {
      "epoch": 1.4917040205038843,
      "grad_norm": 1.5625,
      "learning_rate": 2.1893004993185944e-05,
      "loss": 1.0278430938720704,
      "num_input_tokens_seen": 11989119424,
      "step": 42160,
      "train_runtime": 410684.979,
      "train_tokens_per_second": 29192.983
    },
    {
      "epoch": 1.492057840767613,
      "grad_norm": 1.59375,
      "learning_rate": 2.189090661539144e-05,
      "loss": 1.0518048286437989,
      "num_input_tokens_seen": 11991940736,
      "step": 42170,
      "train_runtime": 410781.3006,
      "train_tokens_per_second": 29193.005
    },
    {
      "epoch": 1.4924116610313418,
      "grad_norm": 1.6171875,
      "learning_rate": 2.188880884085063e-05,
      "loss": 1.0379878997802734,
      "num_input_tokens_seen": 11994823424,
      "step": 42180,
      "train_runtime": 410879.0538,
      "train_tokens_per_second": 29193.076
    },
    {
      "epoch": 1.4927654812950706,
      "grad_norm": 1.515625,
      "learning_rate": 2.1886711669274547e-05,
      "loss": 1.0607930183410645,
      "num_input_tokens_seen": 11997691712,
      "step": 42190,
      "train_runtime": 410977.6487,
      "train_tokens_per_second": 29193.052
    },
    {
      "epoch": 1.4931193015587994,
      "grad_norm": 1.6953125,
      "learning_rate": 2.188461510037438e-05,
      "loss": 1.0382171630859376,
      "num_input_tokens_seen": 12000527232,
      "step": 42200,
      "train_runtime": 411073.165,
      "train_tokens_per_second": 29193.166
    },
    {
      "epoch": 1.4934731218225281,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1882519133861538e-05,
      "loss": 1.053349208831787,
      "num_input_tokens_seen": 12003381312,
      "step": 42210,
      "train_runtime": 411171.334,
      "train_tokens_per_second": 29193.138
    },
    {
      "epoch": 1.4938269420862569,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1880423769447607e-05,
      "loss": 1.0464336395263671,
      "num_input_tokens_seen": 12006237440,
      "step": 42220,
      "train_runtime": 411268.7057,
      "train_tokens_per_second": 29193.17
    },
    {
      "epoch": 1.4941807623499859,
      "grad_norm": 1.4609375,
      "learning_rate": 2.1878329006844368e-05,
      "loss": 1.0412126541137696,
      "num_input_tokens_seen": 12009064128,
      "step": 42230,
      "train_runtime": 411367.4846,
      "train_tokens_per_second": 29193.032
    },
    {
      "epoch": 1.4945345826137144,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1876234845763806e-05,
      "loss": 1.0450308799743653,
      "num_input_tokens_seen": 12011854592,
      "step": 42240,
      "train_runtime": 411463.0188,
      "train_tokens_per_second": 29193.036
    },
    {
      "epoch": 1.4948884028774434,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1874141285918086e-05,
      "loss": 1.0267714500427245,
      "num_input_tokens_seen": 12014750016,
      "step": 42250,
      "train_runtime": 411565.5982,
      "train_tokens_per_second": 29192.795
    },
    {
      "epoch": 1.495242223141172,
      "grad_norm": 1.578125,
      "learning_rate": 2.1872048327019575e-05,
      "loss": 1.0476985931396485,
      "num_input_tokens_seen": 12017579008,
      "step": 42260,
      "train_runtime": 411661.1129,
      "train_tokens_per_second": 29192.893
    },
    {
      "epoch": 1.495596043404901,
      "grad_norm": 1.578125,
      "learning_rate": 2.1869955968780834e-05,
      "loss": 1.0531655311584474,
      "num_input_tokens_seen": 12020409536,
      "step": 42270,
      "train_runtime": 411755.668,
      "train_tokens_per_second": 29193.064
    },
    {
      "epoch": 1.4959498636686297,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1867864210914605e-05,
      "loss": 1.044987106323242,
      "num_input_tokens_seen": 12023295872,
      "step": 42280,
      "train_runtime": 411857.4663,
      "train_tokens_per_second": 29192.856
    },
    {
      "epoch": 1.4963036839323585,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1865773053133827e-05,
      "loss": 1.0359729766845702,
      "num_input_tokens_seen": 12026124864,
      "step": 42290,
      "train_runtime": 411953.7778,
      "train_tokens_per_second": 29192.899
    },
    {
      "epoch": 1.4966575041960872,
      "grad_norm": 1.640625,
      "learning_rate": 2.186368249515164e-05,
      "loss": 1.0432865142822265,
      "num_input_tokens_seen": 12028913472,
      "step": 42300,
      "train_runtime": 412048.1428,
      "train_tokens_per_second": 29192.981
    },
    {
      "epoch": 1.497011324459816,
      "grad_norm": 1.53125,
      "learning_rate": 2.1861592536681362e-05,
      "loss": 1.0423819541931152,
      "num_input_tokens_seen": 12031675968,
      "step": 42310,
      "train_runtime": 412142.3687,
      "train_tokens_per_second": 29193.009
    },
    {
      "epoch": 1.4973651447235448,
      "grad_norm": 1.515625,
      "learning_rate": 2.1859503177436517e-05,
      "loss": 1.0461089134216308,
      "num_input_tokens_seen": 12034532864,
      "step": 42320,
      "train_runtime": 412242.3,
      "train_tokens_per_second": 29192.863
    },
    {
      "epoch": 1.4977189649872735,
      "grad_norm": 1.546875,
      "learning_rate": 2.1857414417130808e-05,
      "loss": 1.0397977828979492,
      "num_input_tokens_seen": 12037375104,
      "step": 42330,
      "train_runtime": 412340.1499,
      "train_tokens_per_second": 29192.828
    },
    {
      "epoch": 1.4980727852510023,
      "grad_norm": 1.546875,
      "learning_rate": 2.1855326255478136e-05,
      "loss": 1.047746467590332,
      "num_input_tokens_seen": 12040229696,
      "step": 42340,
      "train_runtime": 412438.9995,
      "train_tokens_per_second": 29192.753
    },
    {
      "epoch": 1.498426605514731,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1853238692192597e-05,
      "loss": 1.0540481567382813,
      "num_input_tokens_seen": 12043131968,
      "step": 42350,
      "train_runtime": 412541.087,
      "train_tokens_per_second": 29192.564
    },
    {
      "epoch": 1.4987804257784598,
      "grad_norm": 1.59375,
      "learning_rate": 2.185115172698846e-05,
      "loss": 1.0551654815673828,
      "num_input_tokens_seen": 12045978368,
      "step": 42360,
      "train_runtime": 412638.3751,
      "train_tokens_per_second": 29192.579
    },
    {
      "epoch": 1.4991342460421886,
      "grad_norm": 1.6328125,
      "learning_rate": 2.1849065359580216e-05,
      "loss": 1.056142234802246,
      "num_input_tokens_seen": 12048829120,
      "step": 42370,
      "train_runtime": 412736.0112,
      "train_tokens_per_second": 29192.58
    },
    {
      "epoch": 1.4994880663059174,
      "grad_norm": 1.609375,
      "learning_rate": 2.1846979589682517e-05,
      "loss": 1.042633056640625,
      "num_input_tokens_seen": 12051688192,
      "step": 42380,
      "train_runtime": 412833.8281,
      "train_tokens_per_second": 29192.589
    },
    {
      "epoch": 1.4998418865696461,
      "grad_norm": 1.59375,
      "learning_rate": 2.184489441701022e-05,
      "loss": 1.0316919326782226,
      "num_input_tokens_seen": 12054501504,
      "step": 42390,
      "train_runtime": 412929.5533,
      "train_tokens_per_second": 29192.634
    },
    {
      "epoch": 1.500195706833375,
      "grad_norm": 1.578125,
      "learning_rate": 2.1842809841278376e-05,
      "loss": 1.0452521324157715,
      "num_input_tokens_seen": 12057332352,
      "step": 42400,
      "train_runtime": 413025.816,
      "train_tokens_per_second": 29192.685
    },
    {
      "epoch": 1.5005495270971037,
      "grad_norm": 1.578125,
      "learning_rate": 2.1840725862202214e-05,
      "loss": 1.037149429321289,
      "num_input_tokens_seen": 12060198464,
      "step": 42410,
      "train_runtime": 413125.1564,
      "train_tokens_per_second": 29192.602
    },
    {
      "epoch": 1.5009033473608326,
      "grad_norm": 1.484375,
      "learning_rate": 2.183864247949716e-05,
      "loss": 1.0300870895385743,
      "num_input_tokens_seen": 12063074496,
      "step": 42420,
      "train_runtime": 413226.9285,
      "train_tokens_per_second": 29192.373
    },
    {
      "epoch": 1.5012571676245612,
      "grad_norm": 1.609375,
      "learning_rate": 2.183655969287883e-05,
      "loss": 1.0460521697998046,
      "num_input_tokens_seen": 12065890304,
      "step": 42430,
      "train_runtime": 413321.5463,
      "train_tokens_per_second": 29192.503
    },
    {
      "epoch": 1.5016109878882902,
      "grad_norm": 1.609375,
      "learning_rate": 2.1834477502063034e-05,
      "loss": 1.0378887176513671,
      "num_input_tokens_seen": 12068698816,
      "step": 42440,
      "train_runtime": 413417.8118,
      "train_tokens_per_second": 29192.498
    },
    {
      "epoch": 1.5019648081520187,
      "grad_norm": 1.5546875,
      "learning_rate": 2.183239590676576e-05,
      "loss": 1.037282371520996,
      "num_input_tokens_seen": 12071541632,
      "step": 42450,
      "train_runtime": 413516.8409,
      "train_tokens_per_second": 29192.382
    },
    {
      "epoch": 1.5023186284157477,
      "grad_norm": 1.546875,
      "learning_rate": 2.1830314906703198e-05,
      "loss": 1.0383455276489257,
      "num_input_tokens_seen": 12074359232,
      "step": 42460,
      "train_runtime": 413611.3353,
      "train_tokens_per_second": 29192.525
    },
    {
      "epoch": 1.5026724486794765,
      "grad_norm": 1.5078125,
      "learning_rate": 2.1828234501591717e-05,
      "loss": 1.0513297080993653,
      "num_input_tokens_seen": 12077214400,
      "step": 42470,
      "train_runtime": 413710.0004,
      "train_tokens_per_second": 29192.464
    },
    {
      "epoch": 1.5030262689432052,
      "grad_norm": 1.5390625,
      "learning_rate": 2.182615469114789e-05,
      "loss": 1.0450010299682617,
      "num_input_tokens_seen": 12079984256,
      "step": 42480,
      "train_runtime": 413803.1038,
      "train_tokens_per_second": 29192.59
    },
    {
      "epoch": 1.503380089206934,
      "grad_norm": 1.546875,
      "learning_rate": 2.182407547508846e-05,
      "loss": 1.065173053741455,
      "num_input_tokens_seen": 12082777152,
      "step": 42490,
      "train_runtime": 413896.2561,
      "train_tokens_per_second": 29192.767
    },
    {
      "epoch": 1.5037339094706628,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1821996853130363e-05,
      "loss": 1.04293212890625,
      "num_input_tokens_seen": 12085594880,
      "step": 42500,
      "train_runtime": 413990.9459,
      "train_tokens_per_second": 29192.897
    },
    {
      "epoch": 1.5040877297343915,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1819918824990745e-05,
      "loss": 1.0379575729370116,
      "num_input_tokens_seen": 12088394176,
      "step": 42510,
      "train_runtime": 414086.6367,
      "train_tokens_per_second": 29192.911
    },
    {
      "epoch": 1.5044415499981203,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1817841390386913e-05,
      "loss": 1.0347934722900392,
      "num_input_tokens_seen": 12091286464,
      "step": 42520,
      "train_runtime": 414189.0236,
      "train_tokens_per_second": 29192.677
    },
    {
      "epoch": 1.504795370261849,
      "grad_norm": 1.515625,
      "learning_rate": 2.1815764549036372e-05,
      "loss": 1.0424234390258789,
      "num_input_tokens_seen": 12094099776,
      "step": 42530,
      "train_runtime": 414283.7345,
      "train_tokens_per_second": 29192.794
    },
    {
      "epoch": 1.5051491905255778,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1813688300656823e-05,
      "loss": 1.0475288391113282,
      "num_input_tokens_seen": 12096892544,
      "step": 42540,
      "train_runtime": 414377.4291,
      "train_tokens_per_second": 29192.933
    },
    {
      "epoch": 1.5055030107893068,
      "grad_norm": 1.578125,
      "learning_rate": 2.181161264496615e-05,
      "loss": 1.0440555572509767,
      "num_input_tokens_seen": 12099722304,
      "step": 42550,
      "train_runtime": 414476.7732,
      "train_tokens_per_second": 29192.763
    },
    {
      "epoch": 1.5058568310530354,
      "grad_norm": 1.5625,
      "learning_rate": 2.1809537581682414e-05,
      "loss": 1.0527608871459961,
      "num_input_tokens_seen": 12102568576,
      "step": 42560,
      "train_runtime": 414576.9224,
      "train_tokens_per_second": 29192.577
    },
    {
      "epoch": 1.5062106513167643,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1807463110523877e-05,
      "loss": 1.0559452056884766,
      "num_input_tokens_seen": 12105425984,
      "step": 42570,
      "train_runtime": 414676.4146,
      "train_tokens_per_second": 29192.463
    },
    {
      "epoch": 1.506564471580493,
      "grad_norm": 1.640625,
      "learning_rate": 2.1805389231208993e-05,
      "loss": 1.045664405822754,
      "num_input_tokens_seen": 12108240576,
      "step": 42580,
      "train_runtime": 414771.4796,
      "train_tokens_per_second": 29192.558
    },
    {
      "epoch": 1.5069182918442219,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1803315943456386e-05,
      "loss": 1.0540199279785156,
      "num_input_tokens_seen": 12111070208,
      "step": 42590,
      "train_runtime": 414870.1096,
      "train_tokens_per_second": 29192.439
    },
    {
      "epoch": 1.5072721121079504,
      "grad_norm": 1.59375,
      "learning_rate": 2.180124324698488e-05,
      "loss": 1.0544292449951171,
      "num_input_tokens_seen": 12113892736,
      "step": 42600,
      "train_runtime": 414965.3684,
      "train_tokens_per_second": 29192.539
    },
    {
      "epoch": 1.5076259323716794,
      "grad_norm": 1.609375,
      "learning_rate": 2.1799171141513476e-05,
      "loss": 1.046010684967041,
      "num_input_tokens_seen": 12116740160,
      "step": 42610,
      "train_runtime": 415063.8281,
      "train_tokens_per_second": 29192.474
    },
    {
      "epoch": 1.507979752635408,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1797099626761385e-05,
      "loss": 1.047665786743164,
      "num_input_tokens_seen": 12119576064,
      "step": 42620,
      "train_runtime": 415161.2845,
      "train_tokens_per_second": 29192.452
    },
    {
      "epoch": 1.508333572899137,
      "grad_norm": 1.53125,
      "learning_rate": 2.179502870244797e-05,
      "loss": 1.0463827133178711,
      "num_input_tokens_seen": 12122361472,
      "step": 42630,
      "train_runtime": 415256.5711,
      "train_tokens_per_second": 29192.462
    },
    {
      "epoch": 1.5086873931628657,
      "grad_norm": 1.53125,
      "learning_rate": 2.1792958368292814e-05,
      "loss": 1.0368387222290039,
      "num_input_tokens_seen": 12125185728,
      "step": 42640,
      "train_runtime": 415350.7856,
      "train_tokens_per_second": 29192.639
    },
    {
      "epoch": 1.5090412134265945,
      "grad_norm": 1.53125,
      "learning_rate": 2.1790888624015656e-05,
      "loss": 1.047996711730957,
      "num_input_tokens_seen": 12128054336,
      "step": 42650,
      "train_runtime": 415446.6081,
      "train_tokens_per_second": 29192.811
    },
    {
      "epoch": 1.5093950336903232,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1788819469336452e-05,
      "loss": 1.036382293701172,
      "num_input_tokens_seen": 12130873984,
      "step": 42660,
      "train_runtime": 415541.5522,
      "train_tokens_per_second": 29192.926
    },
    {
      "epoch": 1.509748853954052,
      "grad_norm": 1.53125,
      "learning_rate": 2.1786750903975316e-05,
      "loss": 1.0466689109802245,
      "num_input_tokens_seen": 12133724032,
      "step": 42670,
      "train_runtime": 415639.8312,
      "train_tokens_per_second": 29192.881
    },
    {
      "epoch": 1.5101026742177808,
      "grad_norm": 1.5546875,
      "learning_rate": 2.178468292765257e-05,
      "loss": 1.0254417419433595,
      "num_input_tokens_seen": 12136596352,
      "step": 42680,
      "train_runtime": 415738.4127,
      "train_tokens_per_second": 29192.867
    },
    {
      "epoch": 1.5104564944815095,
      "grad_norm": 1.6640625,
      "learning_rate": 2.1782615540088703e-05,
      "loss": 1.034085178375244,
      "num_input_tokens_seen": 12139420544,
      "step": 42690,
      "train_runtime": 415836.4486,
      "train_tokens_per_second": 29192.777
    },
    {
      "epoch": 1.5108103147452383,
      "grad_norm": 1.546875,
      "learning_rate": 2.178054874100441e-05,
      "loss": 1.0588154792785645,
      "num_input_tokens_seen": 12142253632,
      "step": 42700,
      "train_runtime": 415933.7704,
      "train_tokens_per_second": 29192.757
    },
    {
      "epoch": 1.511164135008967,
      "grad_norm": 1.4921875,
      "learning_rate": 2.177848253012055e-05,
      "loss": 1.046395492553711,
      "num_input_tokens_seen": 12145089920,
      "step": 42710,
      "train_runtime": 416030.6338,
      "train_tokens_per_second": 29192.778
    },
    {
      "epoch": 1.511517955272696,
      "grad_norm": 1.5859375,
      "learning_rate": 2.177641690715819e-05,
      "loss": 1.0572474479675293,
      "num_input_tokens_seen": 12148039232,
      "step": 42720,
      "train_runtime": 416134.5092,
      "train_tokens_per_second": 29192.578
    },
    {
      "epoch": 1.5118717755364246,
      "grad_norm": 1.609375,
      "learning_rate": 2.1774351871838557e-05,
      "loss": 1.0362068176269532,
      "num_input_tokens_seen": 12150827264,
      "step": 42730,
      "train_runtime": 416228.3345,
      "train_tokens_per_second": 29192.696
    },
    {
      "epoch": 1.5122255958001536,
      "grad_norm": 1.5234375,
      "learning_rate": 2.177228742388308e-05,
      "loss": 1.0352916717529297,
      "num_input_tokens_seen": 12153618240,
      "step": 42740,
      "train_runtime": 416323.82,
      "train_tokens_per_second": 29192.704
    },
    {
      "epoch": 1.5125794160638821,
      "grad_norm": 1.5078125,
      "learning_rate": 2.1770223563013374e-05,
      "loss": 1.0551420211791993,
      "num_input_tokens_seen": 12156494272,
      "step": 42750,
      "train_runtime": 416422.5607,
      "train_tokens_per_second": 29192.689
    },
    {
      "epoch": 1.5129332363276111,
      "grad_norm": 1.5,
      "learning_rate": 2.176816028895123e-05,
      "loss": 1.0372543334960938,
      "num_input_tokens_seen": 12159317760,
      "step": 42760,
      "train_runtime": 416516.8143,
      "train_tokens_per_second": 29192.862
    },
    {
      "epoch": 1.5132870565913397,
      "grad_norm": 1.4765625,
      "learning_rate": 2.1766097601418624e-05,
      "loss": 1.062789535522461,
      "num_input_tokens_seen": 12162160128,
      "step": 42770,
      "train_runtime": 416612.76,
      "train_tokens_per_second": 29192.961
    },
    {
      "epoch": 1.5136408768550687,
      "grad_norm": 1.7734375,
      "learning_rate": 2.176403550013773e-05,
      "loss": 1.0416414260864257,
      "num_input_tokens_seen": 12164983872,
      "step": 42780,
      "train_runtime": 416709.5207,
      "train_tokens_per_second": 29192.959
    },
    {
      "epoch": 1.5139946971187974,
      "grad_norm": 1.5078125,
      "learning_rate": 2.176197398483088e-05,
      "loss": 1.0398242950439454,
      "num_input_tokens_seen": 12167836288,
      "step": 42790,
      "train_runtime": 416806.3917,
      "train_tokens_per_second": 29193.017
    },
    {
      "epoch": 1.5143485173825262,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1759913055220623e-05,
      "loss": 1.040786361694336,
      "num_input_tokens_seen": 12170711296,
      "step": 42800,
      "train_runtime": 416903.1154,
      "train_tokens_per_second": 29193.141
    },
    {
      "epoch": 1.514702337646255,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1757852711029664e-05,
      "loss": 1.0440271377563477,
      "num_input_tokens_seen": 12173560000,
      "step": 42810,
      "train_runtime": 417001.5546,
      "train_tokens_per_second": 29193.081
    },
    {
      "epoch": 1.5150561579099837,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1755792951980896e-05,
      "loss": 1.0461885452270507,
      "num_input_tokens_seen": 12176367744,
      "step": 42820,
      "train_runtime": 417098.556,
      "train_tokens_per_second": 29193.023
    },
    {
      "epoch": 1.5154099781737125,
      "grad_norm": 1.578125,
      "learning_rate": 2.175373377779742e-05,
      "loss": 1.0404053688049317,
      "num_input_tokens_seen": 12179276928,
      "step": 42830,
      "train_runtime": 417198.6669,
      "train_tokens_per_second": 29192.991
    },
    {
      "epoch": 1.5157637984374412,
      "grad_norm": 1.53125,
      "learning_rate": 2.1751675188202493e-05,
      "loss": 1.0439472198486328,
      "num_input_tokens_seen": 12182130112,
      "step": 42840,
      "train_runtime": 417293.7685,
      "train_tokens_per_second": 29193.175
    },
    {
      "epoch": 1.51611761870117,
      "grad_norm": 1.59375,
      "learning_rate": 2.174961718291956e-05,
      "loss": 1.0283014297485351,
      "num_input_tokens_seen": 12184963072,
      "step": 42850,
      "train_runtime": 417389.1862,
      "train_tokens_per_second": 29193.289
    },
    {
      "epoch": 1.5164714389648988,
      "grad_norm": 1.5234375,
      "learning_rate": 2.174755976167226e-05,
      "loss": 1.0475403785705566,
      "num_input_tokens_seen": 12187821696,
      "step": 42860,
      "train_runtime": 417486.1684,
      "train_tokens_per_second": 29193.354
    },
    {
      "epoch": 1.5168252592286275,
      "grad_norm": 1.53125,
      "learning_rate": 2.1745502924184407e-05,
      "loss": 1.058966064453125,
      "num_input_tokens_seen": 12190711616,
      "step": 42870,
      "train_runtime": 417582.581,
      "train_tokens_per_second": 29193.535
    },
    {
      "epoch": 1.5171790794923563,
      "grad_norm": 1.5,
      "learning_rate": 2.1743446670180005e-05,
      "loss": 1.0328614234924316,
      "num_input_tokens_seen": 12193600256,
      "step": 42880,
      "train_runtime": 417678.5843,
      "train_tokens_per_second": 29193.741
    },
    {
      "epoch": 1.5175328997560853,
      "grad_norm": 1.59375,
      "learning_rate": 2.1741390999383225e-05,
      "loss": 1.0563753128051758,
      "num_input_tokens_seen": 12196479168,
      "step": 42890,
      "train_runtime": 417777.2178,
      "train_tokens_per_second": 29193.739
    },
    {
      "epoch": 1.5178867200198138,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1739335911518432e-05,
      "loss": 1.0326037406921387,
      "num_input_tokens_seen": 12199325632,
      "step": 42900,
      "train_runtime": 417872.28,
      "train_tokens_per_second": 29193.91
    },
    {
      "epoch": 1.5182405402835428,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1737281406310186e-05,
      "loss": 1.0542548179626465,
      "num_input_tokens_seen": 12202148992,
      "step": 42910,
      "train_runtime": 417970.6545,
      "train_tokens_per_second": 29193.794
    },
    {
      "epoch": 1.5185943605472714,
      "grad_norm": 1.53125,
      "learning_rate": 2.17352274834832e-05,
      "loss": 1.0400730133056642,
      "num_input_tokens_seen": 12204924544,
      "step": 42920,
      "train_runtime": 418064.755,
      "train_tokens_per_second": 29193.861
    },
    {
      "epoch": 1.5189481808110004,
      "grad_norm": 1.546875,
      "learning_rate": 2.1733174142762388e-05,
      "loss": 1.0398210525512694,
      "num_input_tokens_seen": 12207786432,
      "step": 42930,
      "train_runtime": 418162.5356,
      "train_tokens_per_second": 29193.879
    },
    {
      "epoch": 1.519302001074729,
      "grad_norm": 1.59375,
      "learning_rate": 2.1731121383872852e-05,
      "loss": 1.0391586303710938,
      "num_input_tokens_seen": 12210541632,
      "step": 42940,
      "train_runtime": 418253.9241,
      "train_tokens_per_second": 29194.087
    },
    {
      "epoch": 1.519655821338458,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1729069206539847e-05,
      "loss": 1.0596964836120606,
      "num_input_tokens_seen": 12213365440,
      "step": 42950,
      "train_runtime": 418351.5407,
      "train_tokens_per_second": 29194.025
    },
    {
      "epoch": 1.5200096416021867,
      "grad_norm": 1.5703125,
      "learning_rate": 2.172701761048885e-05,
      "loss": 1.040212059020996,
      "num_input_tokens_seen": 12216205056,
      "step": 42960,
      "train_runtime": 418450.0997,
      "train_tokens_per_second": 29193.935
    },
    {
      "epoch": 1.5203634618659154,
      "grad_norm": 1.515625,
      "learning_rate": 2.1724966595445483e-05,
      "loss": 1.0396663665771484,
      "num_input_tokens_seen": 12219023168,
      "step": 42970,
      "train_runtime": 418545.2175,
      "train_tokens_per_second": 29194.034
    },
    {
      "epoch": 1.5207172821296442,
      "grad_norm": 1.5625,
      "learning_rate": 2.172291616113557e-05,
      "loss": 1.0443694114685058,
      "num_input_tokens_seen": 12221892480,
      "step": 42980,
      "train_runtime": 418645.7244,
      "train_tokens_per_second": 29193.879
    },
    {
      "epoch": 1.521071102393373,
      "grad_norm": 1.4609375,
      "learning_rate": 2.172086630728511e-05,
      "loss": 1.0352608680725097,
      "num_input_tokens_seen": 12224784640,
      "step": 42990,
      "train_runtime": 418745.8379,
      "train_tokens_per_second": 29193.806
    },
    {
      "epoch": 1.5214249226571017,
      "grad_norm": 1.515625,
      "learning_rate": 2.171881703362028e-05,
      "loss": 1.0279292106628417,
      "num_input_tokens_seen": 12227680960,
      "step": 43000,
      "train_runtime": 418846.1632,
      "train_tokens_per_second": 29193.728
    },
    {
      "epoch": 1.5217787429208305,
      "grad_norm": 1.515625,
      "learning_rate": 2.1716768339867445e-05,
      "loss": 1.0479794502258302,
      "num_input_tokens_seen": 12230492544,
      "step": 43010,
      "train_runtime": 418940.6561,
      "train_tokens_per_second": 29193.854
    },
    {
      "epoch": 1.5221325631845593,
      "grad_norm": 1.5625,
      "learning_rate": 2.1714720225753148e-05,
      "loss": 1.051537036895752,
      "num_input_tokens_seen": 12233338944,
      "step": 43020,
      "train_runtime": 419035.3543,
      "train_tokens_per_second": 29194.05
    },
    {
      "epoch": 1.522486383448288,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1712672691004098e-05,
      "loss": 1.0505584716796874,
      "num_input_tokens_seen": 12236178880,
      "step": 43030,
      "train_runtime": 419134.3926,
      "train_tokens_per_second": 29193.927
    },
    {
      "epoch": 1.522840203712017,
      "grad_norm": 1.5390625,
      "learning_rate": 2.171062573534722e-05,
      "loss": 1.0368742942810059,
      "num_input_tokens_seen": 12238977280,
      "step": 43040,
      "train_runtime": 419229.5784,
      "train_tokens_per_second": 29193.974
    },
    {
      "epoch": 1.5231940239757455,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1708579358509578e-05,
      "loss": 1.0479641914367677,
      "num_input_tokens_seen": 12241750400,
      "step": 43050,
      "train_runtime": 419324.152,
      "train_tokens_per_second": 29194.003
    },
    {
      "epoch": 1.5235478442394745,
      "grad_norm": 1.5,
      "learning_rate": 2.1706533560218447e-05,
      "loss": 1.042159080505371,
      "num_input_tokens_seen": 12244605504,
      "step": 43060,
      "train_runtime": 419421.5721,
      "train_tokens_per_second": 29194.029
    },
    {
      "epoch": 1.523901664503203,
      "grad_norm": 1.59375,
      "learning_rate": 2.1704488340201262e-05,
      "loss": 1.0577176094055176,
      "num_input_tokens_seen": 12247415680,
      "step": 43070,
      "train_runtime": 419517.9375,
      "train_tokens_per_second": 29194.021
    },
    {
      "epoch": 1.524255484766932,
      "grad_norm": 1.5,
      "learning_rate": 2.170244369818564e-05,
      "loss": 1.031463050842285,
      "num_input_tokens_seen": 12250276096,
      "step": 43080,
      "train_runtime": 419613.7672,
      "train_tokens_per_second": 29194.171
    },
    {
      "epoch": 1.5246093050306606,
      "grad_norm": 1.546875,
      "learning_rate": 2.17003996338994e-05,
      "loss": 1.034702682495117,
      "num_input_tokens_seen": 12253115968,
      "step": 43090,
      "train_runtime": 419711.2986,
      "train_tokens_per_second": 29194.153
    },
    {
      "epoch": 1.5249631252943896,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1698356147070515e-05,
      "loss": 1.0415021896362304,
      "num_input_tokens_seen": 12255938880,
      "step": 43100,
      "train_runtime": 419804.6666,
      "train_tokens_per_second": 29194.385
    },
    {
      "epoch": 1.5253169455581181,
      "grad_norm": 1.546875,
      "learning_rate": 2.169631323742714e-05,
      "loss": 1.0493538856506348,
      "num_input_tokens_seen": 12258805568,
      "step": 43110,
      "train_runtime": 419900.5082,
      "train_tokens_per_second": 29194.548
    },
    {
      "epoch": 1.5256707658218471,
      "grad_norm": 1.5625,
      "learning_rate": 2.1694270904697623e-05,
      "loss": 1.04089412689209,
      "num_input_tokens_seen": 12261658944,
      "step": 43120,
      "train_runtime": 419996.967,
      "train_tokens_per_second": 29194.637
    },
    {
      "epoch": 1.526024586085576,
      "grad_norm": 1.625,
      "learning_rate": 2.169222914861048e-05,
      "loss": 1.0408832550048828,
      "num_input_tokens_seen": 12264533888,
      "step": 43130,
      "train_runtime": 420095.2484,
      "train_tokens_per_second": 29194.65
    },
    {
      "epoch": 1.5263784063493047,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1690187968894404e-05,
      "loss": 1.0360333442687988,
      "num_input_tokens_seen": 12267309504,
      "step": 43140,
      "train_runtime": 420187.6432,
      "train_tokens_per_second": 29194.836
    },
    {
      "epoch": 1.5267322266130334,
      "grad_norm": 1.546875,
      "learning_rate": 2.168814736527828e-05,
      "loss": 1.0442935943603515,
      "num_input_tokens_seen": 12270153472,
      "step": 43150,
      "train_runtime": 420285.7195,
      "train_tokens_per_second": 29194.79
    },
    {
      "epoch": 1.5270860468767622,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1686107337491155e-05,
      "loss": 1.0598824501037598,
      "num_input_tokens_seen": 12272988096,
      "step": 43160,
      "train_runtime": 420381.7686,
      "train_tokens_per_second": 29194.863
    },
    {
      "epoch": 1.527439867140491,
      "grad_norm": 1.515625,
      "learning_rate": 2.1684067885262266e-05,
      "loss": 1.0544626235961914,
      "num_input_tokens_seen": 12275819520,
      "step": 43170,
      "train_runtime": 420478.0983,
      "train_tokens_per_second": 29194.908
    },
    {
      "epoch": 1.5277936874042197,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1682029008321024e-05,
      "loss": 1.0444058418273925,
      "num_input_tokens_seen": 12278695552,
      "step": 43180,
      "train_runtime": 420577.9048,
      "train_tokens_per_second": 29194.818
    },
    {
      "epoch": 1.5281475076679485,
      "grad_norm": 1.59375,
      "learning_rate": 2.167999070639702e-05,
      "loss": 1.0490710258483886,
      "num_input_tokens_seen": 12281526208,
      "step": 43190,
      "train_runtime": 420676.5867,
      "train_tokens_per_second": 29194.699
    },
    {
      "epoch": 1.5285013279316773,
      "grad_norm": 1.53125,
      "learning_rate": 2.1677952979220015e-05,
      "loss": 1.0391048431396483,
      "num_input_tokens_seen": 12284343616,
      "step": 43200,
      "train_runtime": 420772.9571,
      "train_tokens_per_second": 29194.708
    },
    {
      "epoch": 1.5288551481954062,
      "grad_norm": 1.53125,
      "learning_rate": 2.167591582651996e-05,
      "loss": 1.0537946701049805,
      "num_input_tokens_seen": 12287138176,
      "step": 43210,
      "train_runtime": 420868.9598,
      "train_tokens_per_second": 29194.688
    },
    {
      "epoch": 1.5292089684591348,
      "grad_norm": 1.5625,
      "learning_rate": 2.1673879248026977e-05,
      "loss": 1.0563127517700195,
      "num_input_tokens_seen": 12289980992,
      "step": 43220,
      "train_runtime": 420966.0616,
      "train_tokens_per_second": 29194.707
    },
    {
      "epoch": 1.5295627887228638,
      "grad_norm": 1.640625,
      "learning_rate": 2.1671843243471366e-05,
      "loss": 1.0555213928222655,
      "num_input_tokens_seen": 12292877440,
      "step": 43230,
      "train_runtime": 421065.1127,
      "train_tokens_per_second": 29194.719
    },
    {
      "epoch": 1.5299166089865923,
      "grad_norm": 1.578125,
      "learning_rate": 2.1669807812583602e-05,
      "loss": 1.0501736640930175,
      "num_input_tokens_seen": 12295747712,
      "step": 43240,
      "train_runtime": 421165.1097,
      "train_tokens_per_second": 29194.602
    },
    {
      "epoch": 1.5302704292503213,
      "grad_norm": 1.65625,
      "learning_rate": 2.1667772955094347e-05,
      "loss": 1.0316579818725586,
      "num_input_tokens_seen": 12298618496,
      "step": 43250,
      "train_runtime": 421262.419,
      "train_tokens_per_second": 29194.673
    },
    {
      "epoch": 1.5306242495140499,
      "grad_norm": 1.6328125,
      "learning_rate": 2.1665738670734422e-05,
      "loss": 1.0505202293395997,
      "num_input_tokens_seen": 12301503552,
      "step": 43260,
      "train_runtime": 421364.4653,
      "train_tokens_per_second": 29194.449
    },
    {
      "epoch": 1.5309780697777788,
      "grad_norm": 1.5859375,
      "learning_rate": 2.166370495923485e-05,
      "loss": 1.0442238807678224,
      "num_input_tokens_seen": 12304304192,
      "step": 43270,
      "train_runtime": 421457.8542,
      "train_tokens_per_second": 29194.625
    },
    {
      "epoch": 1.5313318900415074,
      "grad_norm": 1.5078125,
      "learning_rate": 2.16616718203268e-05,
      "loss": 1.0508591651916503,
      "num_input_tokens_seen": 12307178752,
      "step": 43280,
      "train_runtime": 421555.7308,
      "train_tokens_per_second": 29194.666
    },
    {
      "epoch": 1.5316857103052364,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1659639253741637e-05,
      "loss": 1.0491396903991699,
      "num_input_tokens_seen": 12310115008,
      "step": 43290,
      "train_runtime": 421660.404,
      "train_tokens_per_second": 29194.382
    },
    {
      "epoch": 1.5320395305689651,
      "grad_norm": 1.5,
      "learning_rate": 2.1657607259210906e-05,
      "loss": 1.0359157562255858,
      "num_input_tokens_seen": 12312915904,
      "step": 43300,
      "train_runtime": 421754.138,
      "train_tokens_per_second": 29194.535
    },
    {
      "epoch": 1.532393350832694,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1655575836466328e-05,
      "loss": 1.0286699295043946,
      "num_input_tokens_seen": 12315801152,
      "step": 43310,
      "train_runtime": 421850.7504,
      "train_tokens_per_second": 29194.688
    },
    {
      "epoch": 1.5327471710964227,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1653544985239775e-05,
      "loss": 1.0502691268920898,
      "num_input_tokens_seen": 12318612608,
      "step": 43320,
      "train_runtime": 421946.4108,
      "train_tokens_per_second": 29194.733
    },
    {
      "epoch": 1.5331009913601514,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1651514705263324e-05,
      "loss": 1.0324738502502442,
      "num_input_tokens_seen": 12321439360,
      "step": 43330,
      "train_runtime": 422043.3891,
      "train_tokens_per_second": 29194.722
    },
    {
      "epoch": 1.5334548116238802,
      "grad_norm": 1.4921875,
      "learning_rate": 2.164948499626922e-05,
      "loss": 1.0371762275695802,
      "num_input_tokens_seen": 12324267840,
      "step": 43340,
      "train_runtime": 422139.3144,
      "train_tokens_per_second": 29194.788
    },
    {
      "epoch": 1.533808631887609,
      "grad_norm": 1.53125,
      "learning_rate": 2.1647455857989867e-05,
      "loss": 1.0468305587768554,
      "num_input_tokens_seen": 12327083776,
      "step": 43350,
      "train_runtime": 422237.1323,
      "train_tokens_per_second": 29194.694
    },
    {
      "epoch": 1.5341624521513377,
      "grad_norm": 1.515625,
      "learning_rate": 2.164542729015788e-05,
      "loss": 1.0604291915893556,
      "num_input_tokens_seen": 12329918656,
      "step": 43360,
      "train_runtime": 422332.4121,
      "train_tokens_per_second": 29194.82
    },
    {
      "epoch": 1.5345162724150665,
      "grad_norm": 1.546875,
      "learning_rate": 2.1643399292506014e-05,
      "loss": 1.041202926635742,
      "num_input_tokens_seen": 12332732800,
      "step": 43370,
      "train_runtime": 422427.1519,
      "train_tokens_per_second": 29194.934
    },
    {
      "epoch": 1.5348700926787955,
      "grad_norm": 1.5390625,
      "learning_rate": 2.164137186476722e-05,
      "loss": 1.0472566604614257,
      "num_input_tokens_seen": 12335606464,
      "step": 43380,
      "train_runtime": 422524.3422,
      "train_tokens_per_second": 29195.02
    },
    {
      "epoch": 1.535223912942524,
      "grad_norm": 1.59375,
      "learning_rate": 2.1639345006674607e-05,
      "loss": 1.0419801712036132,
      "num_input_tokens_seen": 12338514496,
      "step": 43390,
      "train_runtime": 422624.1145,
      "train_tokens_per_second": 29195.008
    },
    {
      "epoch": 1.535577733206253,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1637318717961477e-05,
      "loss": 1.0485687255859375,
      "num_input_tokens_seen": 12341371840,
      "step": 43400,
      "train_runtime": 422721.5974,
      "train_tokens_per_second": 29195.035
    },
    {
      "epoch": 1.5359315534699816,
      "grad_norm": 1.5625,
      "learning_rate": 2.16352929983613e-05,
      "loss": 1.04600248336792,
      "num_input_tokens_seen": 12344204800,
      "step": 43410,
      "train_runtime": 422816.7219,
      "train_tokens_per_second": 29195.167
    },
    {
      "epoch": 1.5362853737337105,
      "grad_norm": 1.53125,
      "learning_rate": 2.1633267847607718e-05,
      "loss": 1.0444555282592773,
      "num_input_tokens_seen": 12347099648,
      "step": 43420,
      "train_runtime": 422918.9801,
      "train_tokens_per_second": 29194.953
    },
    {
      "epoch": 1.536639193997439,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1631243265434543e-05,
      "loss": 1.0559234619140625,
      "num_input_tokens_seen": 12349994944,
      "step": 43430,
      "train_runtime": 423016.1553,
      "train_tokens_per_second": 29195.091
    },
    {
      "epoch": 1.536993014261168,
      "grad_norm": 1.609375,
      "learning_rate": 2.1629219251575783e-05,
      "loss": 1.056288719177246,
      "num_input_tokens_seen": 12352848384,
      "step": 43440,
      "train_runtime": 423112.3279,
      "train_tokens_per_second": 29195.198
    },
    {
      "epoch": 1.5373468345248966,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1627195805765592e-05,
      "loss": 1.0437440872192383,
      "num_input_tokens_seen": 12355717632,
      "step": 43450,
      "train_runtime": 423211.9966,
      "train_tokens_per_second": 29195.103
    },
    {
      "epoch": 1.5377006547886256,
      "grad_norm": 1.5234375,
      "learning_rate": 2.162517292773831e-05,
      "loss": 1.0504669189453124,
      "num_input_tokens_seen": 12358574016,
      "step": 43460,
      "train_runtime": 423309.1987,
      "train_tokens_per_second": 29195.146
    },
    {
      "epoch": 1.5380544750523544,
      "grad_norm": 1.4921875,
      "learning_rate": 2.1623150617228456e-05,
      "loss": 1.0412670135498048,
      "num_input_tokens_seen": 12361382976,
      "step": 43470,
      "train_runtime": 423404.9539,
      "train_tokens_per_second": 29195.178
    },
    {
      "epoch": 1.5384082953160831,
      "grad_norm": 1.59375,
      "learning_rate": 2.1621128873970715e-05,
      "loss": 1.0383896827697754,
      "num_input_tokens_seen": 12364179456,
      "step": 43480,
      "train_runtime": 423499.5818,
      "train_tokens_per_second": 29195.258
    },
    {
      "epoch": 1.538762115579812,
      "grad_norm": 1.4453125,
      "learning_rate": 2.1619107697699955e-05,
      "loss": 1.0356176376342774,
      "num_input_tokens_seen": 12367064192,
      "step": 43490,
      "train_runtime": 423598.0425,
      "train_tokens_per_second": 29195.282
    },
    {
      "epoch": 1.5391159358435407,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1617087088151208e-05,
      "loss": 1.0627592086791993,
      "num_input_tokens_seen": 12369846336,
      "step": 43500,
      "train_runtime": 423689.4189,
      "train_tokens_per_second": 29195.552
    },
    {
      "epoch": 1.5394697561072694,
      "grad_norm": 1.578125,
      "learning_rate": 2.1615067045059685e-05,
      "loss": 1.0589136123657226,
      "num_input_tokens_seen": 12372748672,
      "step": 43510,
      "train_runtime": 423792.5135,
      "train_tokens_per_second": 29195.298
    },
    {
      "epoch": 1.5398235763709982,
      "grad_norm": 1.5546875,
      "learning_rate": 2.161304756816076e-05,
      "loss": 1.0461523056030273,
      "num_input_tokens_seen": 12375564032,
      "step": 43520,
      "train_runtime": 423886.8529,
      "train_tokens_per_second": 29195.442
    },
    {
      "epoch": 1.540177396634727,
      "grad_norm": 1.578125,
      "learning_rate": 2.1611028657189997e-05,
      "loss": 1.0475812911987306,
      "num_input_tokens_seen": 12378426496,
      "step": 43530,
      "train_runtime": 423984.8066,
      "train_tokens_per_second": 29195.448
    },
    {
      "epoch": 1.5405312168984557,
      "grad_norm": 1.578125,
      "learning_rate": 2.160901031188312e-05,
      "loss": 1.0542695999145508,
      "num_input_tokens_seen": 12381221568,
      "step": 43540,
      "train_runtime": 424078.8232,
      "train_tokens_per_second": 29195.567
    },
    {
      "epoch": 1.5408850371621847,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1606992531976027e-05,
      "loss": 1.042238140106201,
      "num_input_tokens_seen": 12384109184,
      "step": 43550,
      "train_runtime": 424179.319,
      "train_tokens_per_second": 29195.457
    },
    {
      "epoch": 1.5412388574259133,
      "grad_norm": 1.546875,
      "learning_rate": 2.1604975317204805e-05,
      "loss": 1.0426836013793945,
      "num_input_tokens_seen": 12386943936,
      "step": 43560,
      "train_runtime": 424275.723,
      "train_tokens_per_second": 29195.505
    },
    {
      "epoch": 1.5415926776896423,
      "grad_norm": 1.5234375,
      "learning_rate": 2.160295866730568e-05,
      "loss": 1.0295053482055665,
      "num_input_tokens_seen": 12389767488,
      "step": 43570,
      "train_runtime": 424372.8634,
      "train_tokens_per_second": 29195.475
    },
    {
      "epoch": 1.5419464979533708,
      "grad_norm": 1.5703125,
      "learning_rate": 2.160094258201508e-05,
      "loss": 1.0637248039245606,
      "num_input_tokens_seen": 12392641280,
      "step": 43580,
      "train_runtime": 424472.3734,
      "train_tokens_per_second": 29195.401
    },
    {
      "epoch": 1.5423003182170998,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1598927061069596e-05,
      "loss": 1.0461264610290528,
      "num_input_tokens_seen": 12395480384,
      "step": 43590,
      "train_runtime": 424568.6398,
      "train_tokens_per_second": 29195.469
    },
    {
      "epoch": 1.5426541384808283,
      "grad_norm": 1.5390625,
      "learning_rate": 2.159691210420599e-05,
      "loss": 1.0489859580993652,
      "num_input_tokens_seen": 12398313600,
      "step": 43600,
      "train_runtime": 424666.1858,
      "train_tokens_per_second": 29195.434
    },
    {
      "epoch": 1.5430079587445573,
      "grad_norm": 1.5625,
      "learning_rate": 2.1594897711161196e-05,
      "loss": 1.0430309295654296,
      "num_input_tokens_seen": 12401137984,
      "step": 43610,
      "train_runtime": 424763.7164,
      "train_tokens_per_second": 29195.38
    },
    {
      "epoch": 1.543361779008286,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1592883881672317e-05,
      "loss": 1.0336658477783203,
      "num_input_tokens_seen": 12403944384,
      "step": 43620,
      "train_runtime": 424859.5892,
      "train_tokens_per_second": 29195.397
    },
    {
      "epoch": 1.5437155992720148,
      "grad_norm": 1.609375,
      "learning_rate": 2.1590870615476628e-05,
      "loss": 1.0417205810546875,
      "num_input_tokens_seen": 12406708288,
      "step": 43630,
      "train_runtime": 424951.5157,
      "train_tokens_per_second": 29195.585
    },
    {
      "epoch": 1.5440694195357436,
      "grad_norm": 1.484375,
      "learning_rate": 2.158885791231158e-05,
      "loss": 1.0469600677490234,
      "num_input_tokens_seen": 12409582400,
      "step": 43640,
      "train_runtime": 425052.6828,
      "train_tokens_per_second": 29195.398
    },
    {
      "epoch": 1.5444232397994724,
      "grad_norm": 1.6015625,
      "learning_rate": 2.15868457719148e-05,
      "loss": 1.0430903434753418,
      "num_input_tokens_seen": 12412413120,
      "step": 43650,
      "train_runtime": 425149.8215,
      "train_tokens_per_second": 29195.386
    },
    {
      "epoch": 1.5447770600632011,
      "grad_norm": 1.546875,
      "learning_rate": 2.158483419402407e-05,
      "loss": 1.0475128173828125,
      "num_input_tokens_seen": 12415259136,
      "step": 43660,
      "train_runtime": 425245.5321,
      "train_tokens_per_second": 29195.508
    },
    {
      "epoch": 1.54513088032693,
      "grad_norm": 1.5546875,
      "learning_rate": 2.158282317837736e-05,
      "loss": 1.0455371856689453,
      "num_input_tokens_seen": 12418113728,
      "step": 43670,
      "train_runtime": 425344.4959,
      "train_tokens_per_second": 29195.426
    },
    {
      "epoch": 1.5454847005906587,
      "grad_norm": 1.5078125,
      "learning_rate": 2.1580812724712792e-05,
      "loss": 1.0389822006225586,
      "num_input_tokens_seen": 12420983232,
      "step": 43680,
      "train_runtime": 425442.5918,
      "train_tokens_per_second": 29195.439
    },
    {
      "epoch": 1.5458385208543874,
      "grad_norm": 1.4296875,
      "learning_rate": 2.157880283276868e-05,
      "loss": 1.0300063133239745,
      "num_input_tokens_seen": 12423910528,
      "step": 43690,
      "train_runtime": 425547.5032,
      "train_tokens_per_second": 29195.12
    },
    {
      "epoch": 1.5461923411181162,
      "grad_norm": 1.5625,
      "learning_rate": 2.1576793502283494e-05,
      "loss": 1.0402565956115724,
      "num_input_tokens_seen": 12426757504,
      "step": 43700,
      "train_runtime": 425646.2978,
      "train_tokens_per_second": 29195.033
    },
    {
      "epoch": 1.546546161381845,
      "grad_norm": 1.578125,
      "learning_rate": 2.1574784732995884e-05,
      "loss": 1.0457696914672852,
      "num_input_tokens_seen": 12429555392,
      "step": 43710,
      "train_runtime": 425740.1585,
      "train_tokens_per_second": 29195.168
    },
    {
      "epoch": 1.546899981645574,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1572776524644658e-05,
      "loss": 1.039921188354492,
      "num_input_tokens_seen": 12432411840,
      "step": 43720,
      "train_runtime": 425841.5584,
      "train_tokens_per_second": 29194.924
    },
    {
      "epoch": 1.5472538019093025,
      "grad_norm": 1.59375,
      "learning_rate": 2.1570768876968802e-05,
      "loss": 1.039276695251465,
      "num_input_tokens_seen": 12435229312,
      "step": 43730,
      "train_runtime": 425936.6784,
      "train_tokens_per_second": 29195.019
    },
    {
      "epoch": 1.5476076221730315,
      "grad_norm": 1.546875,
      "learning_rate": 2.1568761789707474e-05,
      "loss": 1.0489606857299805,
      "num_input_tokens_seen": 12438057088,
      "step": 43740,
      "train_runtime": 426032.5596,
      "train_tokens_per_second": 29195.086
    },
    {
      "epoch": 1.54796144243676,
      "grad_norm": 1.5859375,
      "learning_rate": 2.15667552626e-05,
      "loss": 1.0413787841796875,
      "num_input_tokens_seen": 12440882112,
      "step": 43750,
      "train_runtime": 426129.7919,
      "train_tokens_per_second": 29195.054
    },
    {
      "epoch": 1.548315262700489,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1564749295385872e-05,
      "loss": 1.051457977294922,
      "num_input_tokens_seen": 12443744384,
      "step": 43760,
      "train_runtime": 426228.2363,
      "train_tokens_per_second": 29195.026
    },
    {
      "epoch": 1.5486690829642176,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1562743887804757e-05,
      "loss": 1.053226852416992,
      "num_input_tokens_seen": 12446624256,
      "step": 43770,
      "train_runtime": 426328.5979,
      "train_tokens_per_second": 29194.908
    },
    {
      "epoch": 1.5490229032279466,
      "grad_norm": 1.4765625,
      "learning_rate": 2.1560739039596485e-05,
      "loss": 1.0394094467163086,
      "num_input_tokens_seen": 12449464896,
      "step": 43780,
      "train_runtime": 426426.9263,
      "train_tokens_per_second": 29194.838
    },
    {
      "epoch": 1.5493767234916753,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1558734750501068e-05,
      "loss": 1.039376449584961,
      "num_input_tokens_seen": 12452267776,
      "step": 43790,
      "train_runtime": 426522.3152,
      "train_tokens_per_second": 29194.88
    },
    {
      "epoch": 1.549730543755404,
      "grad_norm": 1.5625,
      "learning_rate": 2.1556731020258664e-05,
      "loss": 1.0416500091552734,
      "num_input_tokens_seen": 12455164288,
      "step": 43800,
      "train_runtime": 426622.3669,
      "train_tokens_per_second": 29194.823
    },
    {
      "epoch": 1.5500843640191329,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1554727848609627e-05,
      "loss": 1.039046287536621,
      "num_input_tokens_seen": 12458012544,
      "step": 43810,
      "train_runtime": 426718.4193,
      "train_tokens_per_second": 29194.926
    },
    {
      "epoch": 1.5504381842828616,
      "grad_norm": 1.578125,
      "learning_rate": 2.155272523529446e-05,
      "loss": 1.0542257308959961,
      "num_input_tokens_seen": 12460797376,
      "step": 43820,
      "train_runtime": 426814.9971,
      "train_tokens_per_second": 29194.844
    },
    {
      "epoch": 1.5507920045465904,
      "grad_norm": 1.59375,
      "learning_rate": 2.1550723180053844e-05,
      "loss": 1.0441154479980468,
      "num_input_tokens_seen": 12463622784,
      "step": 43830,
      "train_runtime": 426913.4158,
      "train_tokens_per_second": 29194.732
    },
    {
      "epoch": 1.5511458248103192,
      "grad_norm": 1.5859375,
      "learning_rate": 2.154872168262863e-05,
      "loss": 1.0531270980834961,
      "num_input_tokens_seen": 12466459840,
      "step": 43840,
      "train_runtime": 427010.8291,
      "train_tokens_per_second": 29194.716
    },
    {
      "epoch": 1.551499645074048,
      "grad_norm": 1.59375,
      "learning_rate": 2.1546720742759827e-05,
      "loss": 1.0457523345947266,
      "num_input_tokens_seen": 12469283840,
      "step": 43850,
      "train_runtime": 427110.183,
      "train_tokens_per_second": 29194.537
    },
    {
      "epoch": 1.5518534653377767,
      "grad_norm": 1.59375,
      "learning_rate": 2.1544720360188627e-05,
      "loss": 1.0378005027770996,
      "num_input_tokens_seen": 12472106944,
      "step": 43860,
      "train_runtime": 427206.7736,
      "train_tokens_per_second": 29194.544
    },
    {
      "epoch": 1.5522072856015057,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1542720534656376e-05,
      "loss": 1.0333465576171874,
      "num_input_tokens_seen": 12474971072,
      "step": 43870,
      "train_runtime": 427307.1717,
      "train_tokens_per_second": 29194.387
    },
    {
      "epoch": 1.5525611058652342,
      "grad_norm": 1.546875,
      "learning_rate": 2.1540721265904594e-05,
      "loss": 1.0362982749938965,
      "num_input_tokens_seen": 12477812096,
      "step": 43880,
      "train_runtime": 427403.432,
      "train_tokens_per_second": 29194.459
    },
    {
      "epoch": 1.5529149261289632,
      "grad_norm": 1.515625,
      "learning_rate": 2.153872255367498e-05,
      "loss": 1.0396611213684082,
      "num_input_tokens_seen": 12480686400,
      "step": 43890,
      "train_runtime": 427502.2978,
      "train_tokens_per_second": 29194.431
    },
    {
      "epoch": 1.5532687463926917,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1536724397709374e-05,
      "loss": 1.0510746002197267,
      "num_input_tokens_seen": 12483482560,
      "step": 43900,
      "train_runtime": 427596.3897,
      "train_tokens_per_second": 29194.546
    },
    {
      "epoch": 1.5536225666564207,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1534726797749813e-05,
      "loss": 1.0677972793579102,
      "num_input_tokens_seen": 12486327744,
      "step": 43910,
      "train_runtime": 427691.4493,
      "train_tokens_per_second": 29194.71
    },
    {
      "epoch": 1.5539763869201493,
      "grad_norm": 1.5703125,
      "learning_rate": 2.153272975353848e-05,
      "loss": 1.0305341720581054,
      "num_input_tokens_seen": 12489117760,
      "step": 43920,
      "train_runtime": 427786.8053,
      "train_tokens_per_second": 29194.724
    },
    {
      "epoch": 1.5543302071838783,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1530733264817737e-05,
      "loss": 1.0405635833740234,
      "num_input_tokens_seen": 12491962432,
      "step": 43930,
      "train_runtime": 427884.0641,
      "train_tokens_per_second": 29194.736
    },
    {
      "epoch": 1.5546840274476068,
      "grad_norm": 1.515625,
      "learning_rate": 2.152873733133011e-05,
      "loss": 1.0432016372680664,
      "num_input_tokens_seen": 12494818688,
      "step": 43940,
      "train_runtime": 427982.7358,
      "train_tokens_per_second": 29194.679
    },
    {
      "epoch": 1.5550378477113358,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1526741952818296e-05,
      "loss": 1.0429587364196777,
      "num_input_tokens_seen": 12497623616,
      "step": 43950,
      "train_runtime": 428078.8085,
      "train_tokens_per_second": 29194.68
    },
    {
      "epoch": 1.5553916679750646,
      "grad_norm": 1.53125,
      "learning_rate": 2.152474712902514e-05,
      "loss": 1.0428516387939453,
      "num_input_tokens_seen": 12500495488,
      "step": 43960,
      "train_runtime": 428177.0438,
      "train_tokens_per_second": 29194.689
    },
    {
      "epoch": 1.5557454882387933,
      "grad_norm": 1.546875,
      "learning_rate": 2.1522752859693686e-05,
      "loss": 1.0450689315795898,
      "num_input_tokens_seen": 12503396544,
      "step": 43970,
      "train_runtime": 428275.3307,
      "train_tokens_per_second": 29194.762
    },
    {
      "epoch": 1.556099308502522,
      "grad_norm": 1.4296875,
      "learning_rate": 2.152075914456711e-05,
      "loss": 1.0359740257263184,
      "num_input_tokens_seen": 12506165056,
      "step": 43980,
      "train_runtime": 428369.0549,
      "train_tokens_per_second": 29194.838
    },
    {
      "epoch": 1.5564531287662509,
      "grad_norm": 1.53125,
      "learning_rate": 2.1518765983388788e-05,
      "loss": 1.0476415634155274,
      "num_input_tokens_seen": 12508950272,
      "step": 43990,
      "train_runtime": 428463.596,
      "train_tokens_per_second": 29194.896
    },
    {
      "epoch": 1.5568069490299796,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1516773375902238e-05,
      "loss": 1.0386534690856934,
      "num_input_tokens_seen": 12511763648,
      "step": 44000,
      "train_runtime": 428559.0501,
      "train_tokens_per_second": 29194.958
    },
    {
      "epoch": 1.5571607692937084,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1514781321851152e-05,
      "loss": 1.0571907997131347,
      "num_input_tokens_seen": 12514606592,
      "step": 44010,
      "train_runtime": 428653.7401,
      "train_tokens_per_second": 29195.141
    },
    {
      "epoch": 1.5575145895574372,
      "grad_norm": 1.46875,
      "learning_rate": 2.1512789820979384e-05,
      "loss": 1.0358988761901855,
      "num_input_tokens_seen": 12517426304,
      "step": 44020,
      "train_runtime": 428748.709,
      "train_tokens_per_second": 29195.251
    },
    {
      "epoch": 1.557868409821166,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1510798873030965e-05,
      "loss": 1.056374740600586,
      "num_input_tokens_seen": 12520287168,
      "step": 44030,
      "train_runtime": 428845.5862,
      "train_tokens_per_second": 29195.327
    },
    {
      "epoch": 1.558222230084895,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1508808477750084e-05,
      "loss": 1.0577253341674804,
      "num_input_tokens_seen": 12523135232,
      "step": 44040,
      "train_runtime": 428941.2479,
      "train_tokens_per_second": 29195.456
    },
    {
      "epoch": 1.5585760503486235,
      "grad_norm": 1.515625,
      "learning_rate": 2.1506818634881096e-05,
      "loss": 1.0331825256347655,
      "num_input_tokens_seen": 12525946816,
      "step": 44050,
      "train_runtime": 429035.8043,
      "train_tokens_per_second": 29195.575
    },
    {
      "epoch": 1.5589298706123524,
      "grad_norm": 1.5625,
      "learning_rate": 2.1504829344168518e-05,
      "loss": 1.0354949951171875,
      "num_input_tokens_seen": 12528793280,
      "step": 44060,
      "train_runtime": 429134.8158,
      "train_tokens_per_second": 29195.471
    },
    {
      "epoch": 1.559283690876081,
      "grad_norm": 1.5078125,
      "learning_rate": 2.1502840605357042e-05,
      "loss": 1.0373895645141602,
      "num_input_tokens_seen": 12531591424,
      "step": 44070,
      "train_runtime": 429230.4733,
      "train_tokens_per_second": 29195.484
    },
    {
      "epoch": 1.55963751113981,
      "grad_norm": 1.578125,
      "learning_rate": 2.1500852418191518e-05,
      "loss": 1.0414798736572266,
      "num_input_tokens_seen": 12534477184,
      "step": 44080,
      "train_runtime": 429332.8976,
      "train_tokens_per_second": 29195.24
    },
    {
      "epoch": 1.5599913314035385,
      "grad_norm": 1.578125,
      "learning_rate": 2.1498864782416958e-05,
      "loss": 1.0361026763916015,
      "num_input_tokens_seen": 12537293888,
      "step": 44090,
      "train_runtime": 429427.1601,
      "train_tokens_per_second": 29195.391
    },
    {
      "epoch": 1.5603451516672675,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1496877697778547e-05,
      "loss": 1.045965576171875,
      "num_input_tokens_seen": 12540124032,
      "step": 44100,
      "train_runtime": 429522.7224,
      "train_tokens_per_second": 29195.485
    },
    {
      "epoch": 1.560698971930996,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1494891164021637e-05,
      "loss": 1.0534655570983886,
      "num_input_tokens_seen": 12542967296,
      "step": 44110,
      "train_runtime": 429620.2897,
      "train_tokens_per_second": 29195.472
    },
    {
      "epoch": 1.561052792194725,
      "grad_norm": 1.5546875,
      "learning_rate": 2.149290518089173e-05,
      "loss": 1.0562336921691895,
      "num_input_tokens_seen": 12545837312,
      "step": 44120,
      "train_runtime": 429719.3938,
      "train_tokens_per_second": 29195.418
    },
    {
      "epoch": 1.5614066124584538,
      "grad_norm": 1.6328125,
      "learning_rate": 2.1490919748134512e-05,
      "loss": 1.0469095230102539,
      "num_input_tokens_seen": 12548620288,
      "step": 44130,
      "train_runtime": 429814.3738,
      "train_tokens_per_second": 29195.441
    },
    {
      "epoch": 1.5617604327221826,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1488934865495812e-05,
      "loss": 1.0596696853637695,
      "num_input_tokens_seen": 12551454720,
      "step": 44140,
      "train_runtime": 429908.59,
      "train_tokens_per_second": 29195.636
    },
    {
      "epoch": 1.5621142529859113,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1486950532721642e-05,
      "loss": 1.047023391723633,
      "num_input_tokens_seen": 12554275392,
      "step": 44150,
      "train_runtime": 430004.0307,
      "train_tokens_per_second": 29195.716
    },
    {
      "epoch": 1.56246807324964,
      "grad_norm": 1.546875,
      "learning_rate": 2.1484966749558173e-05,
      "loss": 1.0512585639953613,
      "num_input_tokens_seen": 12557107904,
      "step": 44160,
      "train_runtime": 430098.3346,
      "train_tokens_per_second": 29195.9
    },
    {
      "epoch": 1.5628218935133689,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1482983515751732e-05,
      "loss": 1.0472970962524415,
      "num_input_tokens_seen": 12559961920,
      "step": 44170,
      "train_runtime": 430194.6214,
      "train_tokens_per_second": 29195.999
    },
    {
      "epoch": 1.5631757137770976,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1481000831048812e-05,
      "loss": 1.061131477355957,
      "num_input_tokens_seen": 12562849856,
      "step": 44180,
      "train_runtime": 430289.7902,
      "train_tokens_per_second": 29196.254
    },
    {
      "epoch": 1.5635295340408264,
      "grad_norm": 1.515625,
      "learning_rate": 2.147901869519609e-05,
      "loss": 1.0481048583984376,
      "num_input_tokens_seen": 12565730240,
      "step": 44190,
      "train_runtime": 430390.6847,
      "train_tokens_per_second": 29196.102
    },
    {
      "epoch": 1.5638833543045552,
      "grad_norm": 1.5,
      "learning_rate": 2.147703710794037e-05,
      "loss": 1.0524595260620118,
      "num_input_tokens_seen": 12568560064,
      "step": 44200,
      "train_runtime": 430484.8898,
      "train_tokens_per_second": 29196.286
    },
    {
      "epoch": 1.5642371745682841,
      "grad_norm": 1.59375,
      "learning_rate": 2.147505606902865e-05,
      "loss": 1.0452356338500977,
      "num_input_tokens_seen": 12571387584,
      "step": 44210,
      "train_runtime": 430580.361,
      "train_tokens_per_second": 29196.379
    },
    {
      "epoch": 1.5645909948320127,
      "grad_norm": 1.5625,
      "learning_rate": 2.147307557820808e-05,
      "loss": 1.036658477783203,
      "num_input_tokens_seen": 12574206720,
      "step": 44220,
      "train_runtime": 430676.4645,
      "train_tokens_per_second": 29196.41
    },
    {
      "epoch": 1.5649448150957417,
      "grad_norm": 1.59375,
      "learning_rate": 2.147109563522597e-05,
      "loss": 1.0526797294616699,
      "num_input_tokens_seen": 12577028288,
      "step": 44230,
      "train_runtime": 430769.3209,
      "train_tokens_per_second": 29196.667
    },
    {
      "epoch": 1.5652986353594702,
      "grad_norm": 1.546875,
      "learning_rate": 2.1469116239829804e-05,
      "loss": 1.046884250640869,
      "num_input_tokens_seen": 12579834816,
      "step": 44240,
      "train_runtime": 430862.5779,
      "train_tokens_per_second": 29196.861
    },
    {
      "epoch": 1.5656524556231992,
      "grad_norm": 1.640625,
      "learning_rate": 2.1467137391767213e-05,
      "loss": 1.0525732040405273,
      "num_input_tokens_seen": 12582689984,
      "step": 44250,
      "train_runtime": 430959.7349,
      "train_tokens_per_second": 29196.904
    },
    {
      "epoch": 1.5660062758869278,
      "grad_norm": 1.515625,
      "learning_rate": 2.146515909078601e-05,
      "loss": 1.0342742919921875,
      "num_input_tokens_seen": 12585563968,
      "step": 44260,
      "train_runtime": 431061.0219,
      "train_tokens_per_second": 29196.711
    },
    {
      "epoch": 1.5663600961506567,
      "grad_norm": 1.515625,
      "learning_rate": 2.1463181336634156e-05,
      "loss": 1.0630790710449218,
      "num_input_tokens_seen": 12588414528,
      "step": 44270,
      "train_runtime": 431158.3226,
      "train_tokens_per_second": 29196.733
    },
    {
      "epoch": 1.5667139164143853,
      "grad_norm": 1.515625,
      "learning_rate": 2.1461204129059776e-05,
      "loss": 1.057823657989502,
      "num_input_tokens_seen": 12591275648,
      "step": 44280,
      "train_runtime": 431256.6585,
      "train_tokens_per_second": 29196.71
    },
    {
      "epoch": 1.5670677366781143,
      "grad_norm": 1.5625,
      "learning_rate": 2.145922746781116e-05,
      "loss": 1.0354292869567872,
      "num_input_tokens_seen": 12594127680,
      "step": 44290,
      "train_runtime": 431352.0516,
      "train_tokens_per_second": 29196.865
    },
    {
      "epoch": 1.567421556941843,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1457251352636765e-05,
      "loss": 1.039517879486084,
      "num_input_tokens_seen": 12596940032,
      "step": 44300,
      "train_runtime": 431444.7041,
      "train_tokens_per_second": 29197.114
    },
    {
      "epoch": 1.5677753772055718,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1455275783285203e-05,
      "loss": 1.0428491592407227,
      "num_input_tokens_seen": 12599772992,
      "step": 44310,
      "train_runtime": 431542.2623,
      "train_tokens_per_second": 29197.078
    },
    {
      "epoch": 1.5681291974693006,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1453300759505255e-05,
      "loss": 1.0480964660644532,
      "num_input_tokens_seen": 12602666496,
      "step": 44320,
      "train_runtime": 431640.9839,
      "train_tokens_per_second": 29197.104
    },
    {
      "epoch": 1.5684830177330293,
      "grad_norm": 1.5390625,
      "learning_rate": 2.145132628104585e-05,
      "loss": 1.0417550086975098,
      "num_input_tokens_seen": 12605518912,
      "step": 44330,
      "train_runtime": 431738.8117,
      "train_tokens_per_second": 29197.095
    },
    {
      "epoch": 1.568836837996758,
      "grad_norm": 1.65625,
      "learning_rate": 2.1449352347656098e-05,
      "loss": 1.043064785003662,
      "num_input_tokens_seen": 12608373696,
      "step": 44340,
      "train_runtime": 431838.3409,
      "train_tokens_per_second": 29196.976
    },
    {
      "epoch": 1.5691906582604869,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1447378959085256e-05,
      "loss": 1.0404104232788085,
      "num_input_tokens_seen": 12611231296,
      "step": 44350,
      "train_runtime": 431935.6324,
      "train_tokens_per_second": 29197.015
    },
    {
      "epoch": 1.5695444785242156,
      "grad_norm": 1.546875,
      "learning_rate": 2.1445406115082747e-05,
      "loss": 1.0478376388549804,
      "num_input_tokens_seen": 12614064960,
      "step": 44360,
      "train_runtime": 432033.5355,
      "train_tokens_per_second": 29196.958
    },
    {
      "epoch": 1.5698982987879444,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1443433815398163e-05,
      "loss": 1.0358861923217773,
      "num_input_tokens_seen": 12616857728,
      "step": 44370,
      "train_runtime": 432129.3037,
      "train_tokens_per_second": 29196.95
    },
    {
      "epoch": 1.5702521190516734,
      "grad_norm": 1.515625,
      "learning_rate": 2.1441462059781238e-05,
      "loss": 1.0468219757080077,
      "num_input_tokens_seen": 12619720000,
      "step": 44380,
      "train_runtime": 432228.1974,
      "train_tokens_per_second": 29196.892
    },
    {
      "epoch": 1.570605939315402,
      "grad_norm": 1.640625,
      "learning_rate": 2.1439490847981885e-05,
      "loss": 1.0535453796386718,
      "num_input_tokens_seen": 12622584512,
      "step": 44390,
      "train_runtime": 432327.7116,
      "train_tokens_per_second": 29196.797
    },
    {
      "epoch": 1.570959759579131,
      "grad_norm": 1.59375,
      "learning_rate": 2.1437520179750174e-05,
      "loss": 1.0479585647583007,
      "num_input_tokens_seen": 12625504576,
      "step": 44400,
      "train_runtime": 432430.632,
      "train_tokens_per_second": 29196.601
    },
    {
      "epoch": 1.5713135798428595,
      "grad_norm": 1.5625,
      "learning_rate": 2.1435550054836332e-05,
      "loss": 1.0353968620300293,
      "num_input_tokens_seen": 12628376768,
      "step": 44410,
      "train_runtime": 432531.4068,
      "train_tokens_per_second": 29196.439
    },
    {
      "epoch": 1.5716674001065885,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1433580472990743e-05,
      "loss": 1.0461334228515624,
      "num_input_tokens_seen": 12631232192,
      "step": 44420,
      "train_runtime": 432628.817,
      "train_tokens_per_second": 29196.465
    },
    {
      "epoch": 1.572021220370317,
      "grad_norm": 1.515625,
      "learning_rate": 2.1431611433963964e-05,
      "loss": 1.0468220710754395,
      "num_input_tokens_seen": 12634029568,
      "step": 44430,
      "train_runtime": 432724.5745,
      "train_tokens_per_second": 29196.469
    },
    {
      "epoch": 1.572375040634046,
      "grad_norm": 1.578125,
      "learning_rate": 2.14296429375067e-05,
      "loss": 1.0458183288574219,
      "num_input_tokens_seen": 12636909120,
      "step": 44440,
      "train_runtime": 432825.2015,
      "train_tokens_per_second": 29196.334
    },
    {
      "epoch": 1.5727288608977745,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1427674983369826e-05,
      "loss": 1.0403324127197267,
      "num_input_tokens_seen": 12639779136,
      "step": 44450,
      "train_runtime": 432926.1433,
      "train_tokens_per_second": 29196.156
    },
    {
      "epoch": 1.5730826811615035,
      "grad_norm": 1.5,
      "learning_rate": 2.1425707571304366e-05,
      "loss": 1.0453529357910156,
      "num_input_tokens_seen": 12642660672,
      "step": 44460,
      "train_runtime": 433027.1443,
      "train_tokens_per_second": 29196.0
    },
    {
      "epoch": 1.5734365014252323,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1423740701061512e-05,
      "loss": 1.0526577949523925,
      "num_input_tokens_seen": 12645494208,
      "step": 44470,
      "train_runtime": 433125.2304,
      "train_tokens_per_second": 29195.931
    },
    {
      "epoch": 1.573790321688961,
      "grad_norm": 1.4921875,
      "learning_rate": 2.1421774372392622e-05,
      "loss": 1.052344512939453,
      "num_input_tokens_seen": 12648281280,
      "step": 44480,
      "train_runtime": 433218.0439,
      "train_tokens_per_second": 29196.109
    },
    {
      "epoch": 1.5741441419526898,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1419808585049194e-05,
      "loss": 1.041238784790039,
      "num_input_tokens_seen": 12651189952,
      "step": 44490,
      "train_runtime": 433317.8228,
      "train_tokens_per_second": 29196.099
    },
    {
      "epoch": 1.5744979622164186,
      "grad_norm": 1.5625,
      "learning_rate": 2.1417843338782907e-05,
      "loss": 1.0470590591430664,
      "num_input_tokens_seen": 12654037952,
      "step": 44500,
      "train_runtime": 433415.2045,
      "train_tokens_per_second": 29196.11
    },
    {
      "epoch": 1.5748517824801473,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1415878633345592e-05,
      "loss": 1.0562950134277345,
      "num_input_tokens_seen": 12656910592,
      "step": 44510,
      "train_runtime": 433516.133,
      "train_tokens_per_second": 29195.939
    },
    {
      "epoch": 1.575205602743876,
      "grad_norm": 1.53125,
      "learning_rate": 2.1413914468489227e-05,
      "loss": 1.0463618278503417,
      "num_input_tokens_seen": 12659733376,
      "step": 44520,
      "train_runtime": 433614.0243,
      "train_tokens_per_second": 29195.858
    },
    {
      "epoch": 1.5755594230076049,
      "grad_norm": 1.5390625,
      "learning_rate": 2.141195084396597e-05,
      "loss": 1.0385541915893555,
      "num_input_tokens_seen": 12662600768,
      "step": 44530,
      "train_runtime": 433709.9989,
      "train_tokens_per_second": 29196.008
    },
    {
      "epoch": 1.5759132432713336,
      "grad_norm": 1.6328125,
      "learning_rate": 2.140998775952812e-05,
      "loss": 1.0457186698913574,
      "num_input_tokens_seen": 12665407296,
      "step": 44540,
      "train_runtime": 433806.3701,
      "train_tokens_per_second": 29195.992
    },
    {
      "epoch": 1.5762670635350626,
      "grad_norm": 1.5859375,
      "learning_rate": 2.140802521492814e-05,
      "loss": 1.044708824157715,
      "num_input_tokens_seen": 12668250752,
      "step": 44550,
      "train_runtime": 433902.7786,
      "train_tokens_per_second": 29196.058
    },
    {
      "epoch": 1.5766208837987912,
      "grad_norm": 1.546875,
      "learning_rate": 2.140606320991867e-05,
      "loss": 1.0513051986694335,
      "num_input_tokens_seen": 12671056320,
      "step": 44560,
      "train_runtime": 434000.8048,
      "train_tokens_per_second": 29195.928
    },
    {
      "epoch": 1.5769747040625202,
      "grad_norm": 1.515625,
      "learning_rate": 2.140410174425248e-05,
      "loss": 1.0528629302978516,
      "num_input_tokens_seen": 12673875200,
      "step": 44570,
      "train_runtime": 434097.1981,
      "train_tokens_per_second": 29195.939
    },
    {
      "epoch": 1.5773285243262487,
      "grad_norm": 1.5,
      "learning_rate": 2.140214081768251e-05,
      "loss": 1.031651496887207,
      "num_input_tokens_seen": 12676647872,
      "step": 44580,
      "train_runtime": 434193.0344,
      "train_tokens_per_second": 29195.88
    },
    {
      "epoch": 1.5776823445899777,
      "grad_norm": 1.6015625,
      "learning_rate": 2.140018042996187e-05,
      "loss": 1.0336088180541991,
      "num_input_tokens_seen": 12679409024,
      "step": 44590,
      "train_runtime": 434284.7739,
      "train_tokens_per_second": 29196.071
    },
    {
      "epoch": 1.5780361648537062,
      "grad_norm": 1.546875,
      "learning_rate": 2.1398220580843807e-05,
      "loss": 1.0407217025756836,
      "num_input_tokens_seen": 12682261504,
      "step": 44600,
      "train_runtime": 434382.3721,
      "train_tokens_per_second": 29196.078
    },
    {
      "epoch": 1.5783899851174352,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1396261270081748e-05,
      "loss": 1.0556010246276855,
      "num_input_tokens_seen": 12685153856,
      "step": 44610,
      "train_runtime": 434483.1764,
      "train_tokens_per_second": 29195.961
    },
    {
      "epoch": 1.578743805381164,
      "grad_norm": 1.515625,
      "learning_rate": 2.1394302497429258e-05,
      "loss": 1.052020263671875,
      "num_input_tokens_seen": 12688015296,
      "step": 44620,
      "train_runtime": 434580.4244,
      "train_tokens_per_second": 29196.012
    },
    {
      "epoch": 1.5790976256448928,
      "grad_norm": 1.6328125,
      "learning_rate": 2.1392344262640077e-05,
      "loss": 1.0391345977783204,
      "num_input_tokens_seen": 12690933824,
      "step": 44630,
      "train_runtime": 434680.5884,
      "train_tokens_per_second": 29195.999
    },
    {
      "epoch": 1.5794514459086215,
      "grad_norm": 1.609375,
      "learning_rate": 2.139038656546809e-05,
      "loss": 1.0532212257385254,
      "num_input_tokens_seen": 12693750144,
      "step": 44640,
      "train_runtime": 434773.5827,
      "train_tokens_per_second": 29196.231
    },
    {
      "epoch": 1.5798052661723503,
      "grad_norm": 1.6015625,
      "learning_rate": 2.138842940566735e-05,
      "loss": 1.0623306274414062,
      "num_input_tokens_seen": 12696573056,
      "step": 44650,
      "train_runtime": 434868.2404,
      "train_tokens_per_second": 29196.368
    },
    {
      "epoch": 1.580159086436079,
      "grad_norm": 1.578125,
      "learning_rate": 2.1386472782992055e-05,
      "loss": 1.0404582977294923,
      "num_input_tokens_seen": 12699389568,
      "step": 44660,
      "train_runtime": 434964.2352,
      "train_tokens_per_second": 29196.399
    },
    {
      "epoch": 1.5805129066998078,
      "grad_norm": 1.609375,
      "learning_rate": 2.138451669719658e-05,
      "loss": 1.0526749610900878,
      "num_input_tokens_seen": 12702281792,
      "step": 44670,
      "train_runtime": 435065.79,
      "train_tokens_per_second": 29196.232
    },
    {
      "epoch": 1.5808667269635366,
      "grad_norm": 1.5546875,
      "learning_rate": 2.138256114803543e-05,
      "loss": 1.054495620727539,
      "num_input_tokens_seen": 12705152832,
      "step": 44680,
      "train_runtime": 435163.372,
      "train_tokens_per_second": 29196.283
    },
    {
      "epoch": 1.5812205472272653,
      "grad_norm": 1.5625,
      "learning_rate": 2.138060613526329e-05,
      "loss": 1.0472589492797852,
      "num_input_tokens_seen": 12707983872,
      "step": 44690,
      "train_runtime": 435260.9977,
      "train_tokens_per_second": 29196.238
    },
    {
      "epoch": 1.5815743674909941,
      "grad_norm": 1.609375,
      "learning_rate": 2.1378651658634993e-05,
      "loss": 1.0411848068237304,
      "num_input_tokens_seen": 12710842048,
      "step": 44700,
      "train_runtime": 435360.6603,
      "train_tokens_per_second": 29196.12
    },
    {
      "epoch": 1.5819281877547229,
      "grad_norm": 1.59375,
      "learning_rate": 2.137669771790553e-05,
      "loss": 1.0305139541625976,
      "num_input_tokens_seen": 12713751936,
      "step": 44710,
      "train_runtime": 435461.5363,
      "train_tokens_per_second": 29196.039
    },
    {
      "epoch": 1.5822820080184519,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1374744312830048e-05,
      "loss": 1.042025375366211,
      "num_input_tokens_seen": 12716627776,
      "step": 44720,
      "train_runtime": 435561.7119,
      "train_tokens_per_second": 29195.927
    },
    {
      "epoch": 1.5826358282821804,
      "grad_norm": 1.5859375,
      "learning_rate": 2.137279144316385e-05,
      "loss": 1.0512571334838867,
      "num_input_tokens_seen": 12719462592,
      "step": 44730,
      "train_runtime": 435654.7801,
      "train_tokens_per_second": 29196.197
    },
    {
      "epoch": 1.5829896485459094,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1370839108662393e-05,
      "loss": 1.0432860374450683,
      "num_input_tokens_seen": 12722289728,
      "step": 44740,
      "train_runtime": 435751.0818,
      "train_tokens_per_second": 29196.232
    },
    {
      "epoch": 1.583343468809638,
      "grad_norm": 1.578125,
      "learning_rate": 2.1368887309081305e-05,
      "loss": 1.0352720260620116,
      "num_input_tokens_seen": 12725142528,
      "step": 44750,
      "train_runtime": 435849.0201,
      "train_tokens_per_second": 29196.217
    },
    {
      "epoch": 1.583697289073367,
      "grad_norm": 1.6875,
      "learning_rate": 2.136693604417635e-05,
      "loss": 1.041702651977539,
      "num_input_tokens_seen": 12727975808,
      "step": 44760,
      "train_runtime": 435946.7291,
      "train_tokens_per_second": 29196.172
    },
    {
      "epoch": 1.5840511093370955,
      "grad_norm": 1.5625,
      "learning_rate": 2.1364985313703465e-05,
      "loss": 1.0502321243286132,
      "num_input_tokens_seen": 12730808960,
      "step": 44770,
      "train_runtime": 436042.5893,
      "train_tokens_per_second": 29196.251
    },
    {
      "epoch": 1.5844049296008245,
      "grad_norm": 1.5625,
      "learning_rate": 2.1363035117418724e-05,
      "loss": 1.042138671875,
      "num_input_tokens_seen": 12733634816,
      "step": 44780,
      "train_runtime": 436138.6279,
      "train_tokens_per_second": 29196.301
    },
    {
      "epoch": 1.5847587498645532,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1361085455078375e-05,
      "loss": 1.0468841552734376,
      "num_input_tokens_seen": 12736443904,
      "step": 44790,
      "train_runtime": 436235.0886,
      "train_tokens_per_second": 29196.285
    },
    {
      "epoch": 1.585112570128282,
      "grad_norm": 1.546875,
      "learning_rate": 2.1359136326438812e-05,
      "loss": 1.054422950744629,
      "num_input_tokens_seen": 12739237568,
      "step": 44800,
      "train_runtime": 436329.1128,
      "train_tokens_per_second": 29196.396
    },
    {
      "epoch": 1.5854663903920108,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1357187731256588e-05,
      "loss": 1.0375128746032716,
      "num_input_tokens_seen": 12742100800,
      "step": 44810,
      "train_runtime": 436428.0668,
      "train_tokens_per_second": 29196.337
    },
    {
      "epoch": 1.5858202106557395,
      "grad_norm": 1.5078125,
      "learning_rate": 2.1355239669288418e-05,
      "loss": 1.0519845962524415,
      "num_input_tokens_seen": 12745032448,
      "step": 44820,
      "train_runtime": 436528.0433,
      "train_tokens_per_second": 29196.366
    },
    {
      "epoch": 1.5861740309194683,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1353292140291152e-05,
      "loss": 1.056899070739746,
      "num_input_tokens_seen": 12747848768,
      "step": 44830,
      "train_runtime": 436625.8006,
      "train_tokens_per_second": 29196.279
    },
    {
      "epoch": 1.586527851183197,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1351345144021818e-05,
      "loss": 1.0399456024169922,
      "num_input_tokens_seen": 12750732672,
      "step": 44840,
      "train_runtime": 436727.8906,
      "train_tokens_per_second": 29196.058
    },
    {
      "epoch": 1.5868816714469258,
      "grad_norm": 1.5625,
      "learning_rate": 2.1349398680237585e-05,
      "loss": 1.0559812545776368,
      "num_input_tokens_seen": 12753564352,
      "step": 44850,
      "train_runtime": 436824.6898,
      "train_tokens_per_second": 29196.07
    },
    {
      "epoch": 1.5872354917106546,
      "grad_norm": 1.5078125,
      "learning_rate": 2.1347452748695784e-05,
      "loss": 1.040593433380127,
      "num_input_tokens_seen": 12756367616,
      "step": 44860,
      "train_runtime": 436920.0619,
      "train_tokens_per_second": 29196.113
    },
    {
      "epoch": 1.5875893119743836,
      "grad_norm": 1.484375,
      "learning_rate": 2.1345507349153896e-05,
      "loss": 1.052777099609375,
      "num_input_tokens_seen": 12759225088,
      "step": 44870,
      "train_runtime": 437015.2269,
      "train_tokens_per_second": 29196.294
    },
    {
      "epoch": 1.5879431322381121,
      "grad_norm": 1.546875,
      "learning_rate": 2.1343562481369555e-05,
      "loss": 1.0363547325134277,
      "num_input_tokens_seen": 12762026688,
      "step": 44880,
      "train_runtime": 437109.7645,
      "train_tokens_per_second": 29196.389
    },
    {
      "epoch": 1.588296952501841,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1341618145100557e-05,
      "loss": 1.042843723297119,
      "num_input_tokens_seen": 12764949504,
      "step": 44890,
      "train_runtime": 437211.5973,
      "train_tokens_per_second": 29196.274
    },
    {
      "epoch": 1.5886507727655697,
      "grad_norm": 1.6171875,
      "learning_rate": 2.133967434010485e-05,
      "loss": 1.041438102722168,
      "num_input_tokens_seen": 12767798144,
      "step": 44900,
      "train_runtime": 437311.1767,
      "train_tokens_per_second": 29196.14
    },
    {
      "epoch": 1.5890045930292986,
      "grad_norm": 1.53125,
      "learning_rate": 2.1337731066140536e-05,
      "loss": 1.0319658279418946,
      "num_input_tokens_seen": 12770677440,
      "step": 44910,
      "train_runtime": 437407.631,
      "train_tokens_per_second": 29196.284
    },
    {
      "epoch": 1.5893584132930272,
      "grad_norm": 1.546875,
      "learning_rate": 2.1335788322965864e-05,
      "loss": 1.0552289962768555,
      "num_input_tokens_seen": 12773505792,
      "step": 44920,
      "train_runtime": 437500.2493,
      "train_tokens_per_second": 29196.568
    },
    {
      "epoch": 1.5897122335567562,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1333846110339246e-05,
      "loss": 1.0312393188476563,
      "num_input_tokens_seen": 12776366080,
      "step": 44930,
      "train_runtime": 437597.2159,
      "train_tokens_per_second": 29196.635
    },
    {
      "epoch": 1.5900660538204847,
      "grad_norm": 1.5078125,
      "learning_rate": 2.133190442801925e-05,
      "loss": 1.0461433410644532,
      "num_input_tokens_seen": 12779222592,
      "step": 44940,
      "train_runtime": 437696.5461,
      "train_tokens_per_second": 29196.535
    },
    {
      "epoch": 1.5904198740842137,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1329963275764586e-05,
      "loss": 1.0408315658569336,
      "num_input_tokens_seen": 12782075776,
      "step": 44950,
      "train_runtime": 437792.9036,
      "train_tokens_per_second": 29196.626
    },
    {
      "epoch": 1.5907736943479425,
      "grad_norm": 1.5078125,
      "learning_rate": 2.1328022653334127e-05,
      "loss": 1.067591953277588,
      "num_input_tokens_seen": 12784884160,
      "step": 44960,
      "train_runtime": 437884.9429,
      "train_tokens_per_second": 29196.903
    },
    {
      "epoch": 1.5911275146116712,
      "grad_norm": 1.609375,
      "learning_rate": 2.1326082560486895e-05,
      "loss": 1.0391206741333008,
      "num_input_tokens_seen": 12787754624,
      "step": 44970,
      "train_runtime": 437979.7424,
      "train_tokens_per_second": 29197.137
    },
    {
      "epoch": 1.5914813348754,
      "grad_norm": 1.6328125,
      "learning_rate": 2.132414299698207e-05,
      "loss": 1.0396652221679688,
      "num_input_tokens_seen": 12790593216,
      "step": 44980,
      "train_runtime": 438075.4153,
      "train_tokens_per_second": 29197.24
    },
    {
      "epoch": 1.5918351551391288,
      "grad_norm": 1.59375,
      "learning_rate": 2.1322203962578984e-05,
      "loss": 1.0236476898193358,
      "num_input_tokens_seen": 12793465920,
      "step": 44990,
      "train_runtime": 438173.0949,
      "train_tokens_per_second": 29197.288
    },
    {
      "epoch": 1.5921889754028575,
      "grad_norm": 1.640625,
      "learning_rate": 2.1320265457037115e-05,
      "loss": 1.0456605911254884,
      "num_input_tokens_seen": 12796284416,
      "step": 45000,
      "train_runtime": 438271.6469,
      "train_tokens_per_second": 29197.153
    },
    {
      "epoch": 1.5921889754028575,
      "eval_loss": 1.0206714868545532,
      "eval_runtime": 8.4397,
      "eval_samples_per_second": 472.531,
      "eval_steps_per_second": 3.792,
      "num_input_tokens_seen": 12796284416,
      "step": 45000
    },
    {
      "epoch": 1.5925427956665863,
      "grad_norm": 1.609375,
      "learning_rate": 2.1318327480116112e-05,
      "loss": 1.045743751525879,
      "num_input_tokens_seen": 12799080832,
      "step": 45010,
      "train_runtime": 438394.532,
      "train_tokens_per_second": 29195.348
    },
    {
      "epoch": 1.592896615930315,
      "grad_norm": 1.5546875,
      "learning_rate": 2.131639003157575e-05,
      "loss": 1.0450422286987304,
      "num_input_tokens_seen": 12801917888,
      "step": 45020,
      "train_runtime": 438493.4646,
      "train_tokens_per_second": 29195.231
    },
    {
      "epoch": 1.5932504361940438,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1314453111175983e-05,
      "loss": 1.0441603660583496,
      "num_input_tokens_seen": 12804813248,
      "step": 45030,
      "train_runtime": 438591.8902,
      "train_tokens_per_second": 29195.28
    },
    {
      "epoch": 1.5936042564577728,
      "grad_norm": 1.4453125,
      "learning_rate": 2.13125167186769e-05,
      "loss": 1.044929027557373,
      "num_input_tokens_seen": 12807639168,
      "step": 45040,
      "train_runtime": 438686.5846,
      "train_tokens_per_second": 29195.42
    },
    {
      "epoch": 1.5939580767215014,
      "grad_norm": 1.578125,
      "learning_rate": 2.131058085383875e-05,
      "loss": 1.0534921646118165,
      "num_input_tokens_seen": 12810487744,
      "step": 45050,
      "train_runtime": 438785.8513,
      "train_tokens_per_second": 29195.307
    },
    {
      "epoch": 1.5943118969852303,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1308645516421935e-05,
      "loss": 1.041093349456787,
      "num_input_tokens_seen": 12813344448,
      "step": 45060,
      "train_runtime": 438882.017,
      "train_tokens_per_second": 29195.419
    },
    {
      "epoch": 1.594665717248959,
      "grad_norm": 1.6328125,
      "learning_rate": 2.1306710706187006e-05,
      "loss": 1.0549644470214843,
      "num_input_tokens_seen": 12816212480,
      "step": 45070,
      "train_runtime": 438980.089,
      "train_tokens_per_second": 29195.43
    },
    {
      "epoch": 1.5950195375126879,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1304776422894667e-05,
      "loss": 1.055319595336914,
      "num_input_tokens_seen": 12819068672,
      "step": 45080,
      "train_runtime": 439075.8093,
      "train_tokens_per_second": 29195.57
    },
    {
      "epoch": 1.5953733577764164,
      "grad_norm": 1.546875,
      "learning_rate": 2.1302842666305776e-05,
      "loss": 1.0458061218261718,
      "num_input_tokens_seen": 12821913664,
      "step": 45090,
      "train_runtime": 439171.1883,
      "train_tokens_per_second": 29195.708
    },
    {
      "epoch": 1.5957271780401454,
      "grad_norm": 1.53125,
      "learning_rate": 2.1300909436181343e-05,
      "loss": 1.050140953063965,
      "num_input_tokens_seen": 12824738816,
      "step": 45100,
      "train_runtime": 439268.5403,
      "train_tokens_per_second": 29195.669
    },
    {
      "epoch": 1.596080998303874,
      "grad_norm": 1.515625,
      "learning_rate": 2.129897673228253e-05,
      "loss": 1.0492334365844727,
      "num_input_tokens_seen": 12827594304,
      "step": 45110,
      "train_runtime": 439368.4347,
      "train_tokens_per_second": 29195.53
    },
    {
      "epoch": 1.596434818567603,
      "grad_norm": 1.53125,
      "learning_rate": 2.1297044554370643e-05,
      "loss": 1.0443814277648926,
      "num_input_tokens_seen": 12830426944,
      "step": 45120,
      "train_runtime": 439464.7386,
      "train_tokens_per_second": 29195.578
    },
    {
      "epoch": 1.5967886388313317,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1295112902207147e-05,
      "loss": 1.0439817428588867,
      "num_input_tokens_seen": 12833234624,
      "step": 45130,
      "train_runtime": 439558.9835,
      "train_tokens_per_second": 29195.705
    },
    {
      "epoch": 1.5971424590950605,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1293181775553662e-05,
      "loss": 1.033648681640625,
      "num_input_tokens_seen": 12836122624,
      "step": 45140,
      "train_runtime": 439659.0337,
      "train_tokens_per_second": 29195.63
    },
    {
      "epoch": 1.5974962793587892,
      "grad_norm": 1.546875,
      "learning_rate": 2.1291251174171946e-05,
      "loss": 1.0342557907104493,
      "num_input_tokens_seen": 12838963712,
      "step": 45150,
      "train_runtime": 439756.2228,
      "train_tokens_per_second": 29195.639
    },
    {
      "epoch": 1.597850099622518,
      "grad_norm": 1.6328125,
      "learning_rate": 2.128932109782393e-05,
      "loss": 1.0384085655212403,
      "num_input_tokens_seen": 12841800960,
      "step": 45160,
      "train_runtime": 439849.7728,
      "train_tokens_per_second": 29195.879
    },
    {
      "epoch": 1.5982039198862468,
      "grad_norm": 1.5390625,
      "learning_rate": 2.128739154627167e-05,
      "loss": 1.0540500640869142,
      "num_input_tokens_seen": 12844650624,
      "step": 45170,
      "train_runtime": 439948.3787,
      "train_tokens_per_second": 29195.813
    },
    {
      "epoch": 1.5985577401499755,
      "grad_norm": 1.5859375,
      "learning_rate": 2.128546251927739e-05,
      "loss": 1.0372386932373048,
      "num_input_tokens_seen": 12847525312,
      "step": 45180,
      "train_runtime": 440045.3117,
      "train_tokens_per_second": 29195.915
    },
    {
      "epoch": 1.5989115604137043,
      "grad_norm": 1.6328125,
      "learning_rate": 2.128353401660346e-05,
      "loss": 1.0490705490112304,
      "num_input_tokens_seen": 12850308864,
      "step": 45190,
      "train_runtime": 440138.7147,
      "train_tokens_per_second": 29196.043
    },
    {
      "epoch": 1.599265380677433,
      "grad_norm": 1.484375,
      "learning_rate": 2.1281606038012402e-05,
      "loss": 1.0497625350952149,
      "num_input_tokens_seen": 12853207808,
      "step": 45200,
      "train_runtime": 440240.0119,
      "train_tokens_per_second": 29195.91
    },
    {
      "epoch": 1.599619200941162,
      "grad_norm": 1.515625,
      "learning_rate": 2.1279678583266886e-05,
      "loss": 1.0485101699829102,
      "num_input_tokens_seen": 12856019520,
      "step": 45210,
      "train_runtime": 440337.7613,
      "train_tokens_per_second": 29195.814
    },
    {
      "epoch": 1.5999730212048906,
      "grad_norm": 1.5625,
      "learning_rate": 2.127775165212974e-05,
      "loss": 1.0389598846435546,
      "num_input_tokens_seen": 12858788544,
      "step": 45220,
      "train_runtime": 440428.9636,
      "train_tokens_per_second": 29196.056
    },
    {
      "epoch": 1.6003268414686196,
      "grad_norm": 1.546875,
      "learning_rate": 2.1275825244363922e-05,
      "loss": 1.053035831451416,
      "num_input_tokens_seen": 12861605056,
      "step": 45230,
      "train_runtime": 440526.4916,
      "train_tokens_per_second": 29195.985
    },
    {
      "epoch": 1.6006806617323481,
      "grad_norm": 1.546875,
      "learning_rate": 2.127389935973257e-05,
      "loss": 1.0308696746826171,
      "num_input_tokens_seen": 12864459136,
      "step": 45240,
      "train_runtime": 440624.6148,
      "train_tokens_per_second": 29195.961
    },
    {
      "epoch": 1.6010344819960771,
      "grad_norm": 1.59375,
      "learning_rate": 2.1271973997998947e-05,
      "loss": 1.045677375793457,
      "num_input_tokens_seen": 12867307072,
      "step": 45250,
      "train_runtime": 440720.9821,
      "train_tokens_per_second": 29196.039
    },
    {
      "epoch": 1.6013883022598057,
      "grad_norm": 1.578125,
      "learning_rate": 2.1270049158926483e-05,
      "loss": 1.057631492614746,
      "num_input_tokens_seen": 12870160896,
      "step": 45260,
      "train_runtime": 440816.523,
      "train_tokens_per_second": 29196.185
    },
    {
      "epoch": 1.6017421225235347,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1268124842278744e-05,
      "loss": 1.057645034790039,
      "num_input_tokens_seen": 12873036864,
      "step": 45270,
      "train_runtime": 440915.43,
      "train_tokens_per_second": 29196.159
    },
    {
      "epoch": 1.6020959427872632,
      "grad_norm": 1.625,
      "learning_rate": 2.1266201047819458e-05,
      "loss": 1.042458724975586,
      "num_input_tokens_seen": 12875860800,
      "step": 45280,
      "train_runtime": 441011.1517,
      "train_tokens_per_second": 29196.225
    },
    {
      "epoch": 1.6024497630509922,
      "grad_norm": 1.5625,
      "learning_rate": 2.126427777531249e-05,
      "loss": 1.0422024726867676,
      "num_input_tokens_seen": 12878672064,
      "step": 45290,
      "train_runtime": 441108.1195,
      "train_tokens_per_second": 29196.18
    },
    {
      "epoch": 1.602803583314721,
      "grad_norm": 1.5625,
      "learning_rate": 2.126235502452186e-05,
      "loss": 1.0468622207641602,
      "num_input_tokens_seen": 12881511680,
      "step": 45300,
      "train_runtime": 441206.624,
      "train_tokens_per_second": 29196.098
    },
    {
      "epoch": 1.6031574035784497,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1260432795211747e-05,
      "loss": 1.0394622802734375,
      "num_input_tokens_seen": 12884358464,
      "step": 45310,
      "train_runtime": 441302.012,
      "train_tokens_per_second": 29196.238
    },
    {
      "epoch": 1.6035112238421785,
      "grad_norm": 1.6328125,
      "learning_rate": 2.1258511087146463e-05,
      "loss": 1.0437772750854493,
      "num_input_tokens_seen": 12887202048,
      "step": 45320,
      "train_runtime": 441399.7289,
      "train_tokens_per_second": 29196.217
    },
    {
      "epoch": 1.6038650441059072,
      "grad_norm": 1.5625,
      "learning_rate": 2.125658990009048e-05,
      "loss": 1.0609143257141114,
      "num_input_tokens_seen": 12890055360,
      "step": 45330,
      "train_runtime": 441497.0485,
      "train_tokens_per_second": 29196.244
    },
    {
      "epoch": 1.604218864369636,
      "grad_norm": 1.5625,
      "learning_rate": 2.125466923380842e-05,
      "loss": 1.0305564880371094,
      "num_input_tokens_seen": 12892913984,
      "step": 45340,
      "train_runtime": 441590.8471,
      "train_tokens_per_second": 29196.515
    },
    {
      "epoch": 1.6045726846333648,
      "grad_norm": 1.53125,
      "learning_rate": 2.1252749088065038e-05,
      "loss": 1.0546951293945312,
      "num_input_tokens_seen": 12895766784,
      "step": 45350,
      "train_runtime": 441687.4746,
      "train_tokens_per_second": 29196.587
    },
    {
      "epoch": 1.6049265048970935,
      "grad_norm": 1.5546875,
      "learning_rate": 2.125082946262526e-05,
      "loss": 1.0414019584655763,
      "num_input_tokens_seen": 12898648448,
      "step": 45360,
      "train_runtime": 441787.5486,
      "train_tokens_per_second": 29196.496
    },
    {
      "epoch": 1.6052803251608223,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1248910357254146e-05,
      "loss": 1.0513697624206544,
      "num_input_tokens_seen": 12901506176,
      "step": 45370,
      "train_runtime": 441884.5443,
      "train_tokens_per_second": 29196.554
    },
    {
      "epoch": 1.6056341454245513,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1246991771716913e-05,
      "loss": 1.052490234375,
      "num_input_tokens_seen": 12904395392,
      "step": 45380,
      "train_runtime": 441984.7823,
      "train_tokens_per_second": 29196.47
    },
    {
      "epoch": 1.6059879656882798,
      "grad_norm": 1.515625,
      "learning_rate": 2.124507370577891e-05,
      "loss": 1.0545053482055664,
      "num_input_tokens_seen": 12907297152,
      "step": 45390,
      "train_runtime": 442085.4629,
      "train_tokens_per_second": 29196.384
    },
    {
      "epoch": 1.6063417859520088,
      "grad_norm": 1.4765625,
      "learning_rate": 2.1243156159205653e-05,
      "loss": 1.0311254501342773,
      "num_input_tokens_seen": 12910122304,
      "step": 45400,
      "train_runtime": 442181.2968,
      "train_tokens_per_second": 29196.446
    },
    {
      "epoch": 1.6066956062157374,
      "grad_norm": 1.625,
      "learning_rate": 2.1241239131762808e-05,
      "loss": 1.0413692474365235,
      "num_input_tokens_seen": 12912981696,
      "step": 45410,
      "train_runtime": 442276.7025,
      "train_tokens_per_second": 29196.613
    },
    {
      "epoch": 1.6070494264794664,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1239322623216165e-05,
      "loss": 1.0384191513061523,
      "num_input_tokens_seen": 12915846144,
      "step": 45420,
      "train_runtime": 442375.2362,
      "train_tokens_per_second": 29196.585
    },
    {
      "epoch": 1.607403246743195,
      "grad_norm": 1.578125,
      "learning_rate": 2.1237406633331682e-05,
      "loss": 1.044264030456543,
      "num_input_tokens_seen": 12918590592,
      "step": 45430,
      "train_runtime": 442468.7083,
      "train_tokens_per_second": 29196.62
    },
    {
      "epoch": 1.607757067006924,
      "grad_norm": 1.609375,
      "learning_rate": 2.1235491161875466e-05,
      "loss": 1.0461427688598632,
      "num_input_tokens_seen": 12921430848,
      "step": 45440,
      "train_runtime": 442565.912,
      "train_tokens_per_second": 29196.625
    },
    {
      "epoch": 1.6081108872706524,
      "grad_norm": 1.546875,
      "learning_rate": 2.123357620861376e-05,
      "loss": 1.0455726623535155,
      "num_input_tokens_seen": 12924311040,
      "step": 45450,
      "train_runtime": 442665.4921,
      "train_tokens_per_second": 29196.563
    },
    {
      "epoch": 1.6084647075343814,
      "grad_norm": 1.4921875,
      "learning_rate": 2.1231661773312958e-05,
      "loss": 1.046687126159668,
      "num_input_tokens_seen": 12927140416,
      "step": 45460,
      "train_runtime": 442760.9398,
      "train_tokens_per_second": 29196.66
    },
    {
      "epoch": 1.6088185277981102,
      "grad_norm": 1.5546875,
      "learning_rate": 2.122974785573961e-05,
      "loss": 1.0214195251464844,
      "num_input_tokens_seen": 12929985536,
      "step": 45470,
      "train_runtime": 442857.8228,
      "train_tokens_per_second": 29196.697
    },
    {
      "epoch": 1.609172348061839,
      "grad_norm": 1.59375,
      "learning_rate": 2.12278344556604e-05,
      "loss": 1.0417657852172852,
      "num_input_tokens_seen": 12932874688,
      "step": 45480,
      "train_runtime": 442959.2239,
      "train_tokens_per_second": 29196.535
    },
    {
      "epoch": 1.6095261683255677,
      "grad_norm": 1.5,
      "learning_rate": 2.1225921572842165e-05,
      "loss": 1.0569036483764649,
      "num_input_tokens_seen": 12935733760,
      "step": 45490,
      "train_runtime": 443057.4794,
      "train_tokens_per_second": 29196.514
    },
    {
      "epoch": 1.6098799885892965,
      "grad_norm": 1.5,
      "learning_rate": 2.12240092070519e-05,
      "loss": 1.044008445739746,
      "num_input_tokens_seen": 12938590528,
      "step": 45500,
      "train_runtime": 443154.2466,
      "train_tokens_per_second": 29196.585
    },
    {
      "epoch": 1.6102338088530253,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1222097358056727e-05,
      "loss": 1.0410192489624024,
      "num_input_tokens_seen": 12941407296,
      "step": 45510,
      "train_runtime": 443249.8895,
      "train_tokens_per_second": 29196.64
    },
    {
      "epoch": 1.610587629116754,
      "grad_norm": 1.4921875,
      "learning_rate": 2.122018602562393e-05,
      "loss": 1.0308902740478516,
      "num_input_tokens_seen": 12944279360,
      "step": 45520,
      "train_runtime": 443345.8522,
      "train_tokens_per_second": 29196.798
    },
    {
      "epoch": 1.6109414493804828,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1218275209520926e-05,
      "loss": 1.0359943389892579,
      "num_input_tokens_seen": 12947076288,
      "step": 45530,
      "train_runtime": 443440.7642,
      "train_tokens_per_second": 29196.856
    },
    {
      "epoch": 1.6112952696442115,
      "grad_norm": 1.5625,
      "learning_rate": 2.1216364909515306e-05,
      "loss": 1.042301559448242,
      "num_input_tokens_seen": 12949908672,
      "step": 45540,
      "train_runtime": 443536.9233,
      "train_tokens_per_second": 29196.912
    },
    {
      "epoch": 1.6116490899079405,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1214455125374763e-05,
      "loss": 1.04135160446167,
      "num_input_tokens_seen": 12952833728,
      "step": 45550,
      "train_runtime": 443640.0693,
      "train_tokens_per_second": 29196.717
    },
    {
      "epoch": 1.612002910171669,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1212545856867176e-05,
      "loss": 1.0375239372253418,
      "num_input_tokens_seen": 12955658368,
      "step": 45560,
      "train_runtime": 443735.2554,
      "train_tokens_per_second": 29196.82
    },
    {
      "epoch": 1.612356730435398,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1210637103760558e-05,
      "loss": 1.0502585411071776,
      "num_input_tokens_seen": 12958541632,
      "step": 45570,
      "train_runtime": 443836.5436,
      "train_tokens_per_second": 29196.653
    },
    {
      "epoch": 1.6127105506991266,
      "grad_norm": 1.53125,
      "learning_rate": 2.1208728865823054e-05,
      "loss": 1.0434927940368652,
      "num_input_tokens_seen": 12961378560,
      "step": 45580,
      "train_runtime": 443930.8658,
      "train_tokens_per_second": 29196.84
    },
    {
      "epoch": 1.6130643709628556,
      "grad_norm": 1.5625,
      "learning_rate": 2.120682114282298e-05,
      "loss": 1.0383832931518555,
      "num_input_tokens_seen": 12964219904,
      "step": 45590,
      "train_runtime": 444026.9219,
      "train_tokens_per_second": 29196.923
    },
    {
      "epoch": 1.6134181912265841,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1204913934528784e-05,
      "loss": 1.041362190246582,
      "num_input_tokens_seen": 12967115520,
      "step": 45600,
      "train_runtime": 444127.4128,
      "train_tokens_per_second": 29196.837
    },
    {
      "epoch": 1.6137720114903131,
      "grad_norm": 1.578125,
      "learning_rate": 2.120300724070905e-05,
      "loss": 1.0473427772521973,
      "num_input_tokens_seen": 12969981824,
      "step": 45610,
      "train_runtime": 444223.7077,
      "train_tokens_per_second": 29196.96
    },
    {
      "epoch": 1.614125831754042,
      "grad_norm": 1.640625,
      "learning_rate": 2.1201101061132525e-05,
      "loss": 1.0513710021972655,
      "num_input_tokens_seen": 12972808768,
      "step": 45620,
      "train_runtime": 444317.9338,
      "train_tokens_per_second": 29197.131
    },
    {
      "epoch": 1.6144796520177707,
      "grad_norm": 1.6640625,
      "learning_rate": 2.1199195395568095e-05,
      "loss": 1.0483999252319336,
      "num_input_tokens_seen": 12975654144,
      "step": 45630,
      "train_runtime": 444413.245,
      "train_tokens_per_second": 29197.271
    },
    {
      "epoch": 1.6148334722814994,
      "grad_norm": 1.5546875,
      "learning_rate": 2.119729024378479e-05,
      "loss": 1.061457061767578,
      "num_input_tokens_seen": 12978517376,
      "step": 45640,
      "train_runtime": 444510.4704,
      "train_tokens_per_second": 29197.327
    },
    {
      "epoch": 1.6151872925452282,
      "grad_norm": 1.4453125,
      "learning_rate": 2.119538560555179e-05,
      "loss": 1.0518308639526368,
      "num_input_tokens_seen": 12981345408,
      "step": 45650,
      "train_runtime": 444606.4216,
      "train_tokens_per_second": 29197.386
    },
    {
      "epoch": 1.615541112808957,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1193481480638405e-05,
      "loss": 1.0580204963684081,
      "num_input_tokens_seen": 12984199744,
      "step": 45660,
      "train_runtime": 444704.5574,
      "train_tokens_per_second": 29197.362
    },
    {
      "epoch": 1.6158949330726857,
      "grad_norm": 1.5078125,
      "learning_rate": 2.119157786881411e-05,
      "loss": 1.035477066040039,
      "num_input_tokens_seen": 12986996160,
      "step": 45670,
      "train_runtime": 444799.7774,
      "train_tokens_per_second": 29197.398
    },
    {
      "epoch": 1.6162487533364145,
      "grad_norm": 1.6484375,
      "learning_rate": 2.118967476984852e-05,
      "loss": 1.0476390838623046,
      "num_input_tokens_seen": 12989805504,
      "step": 45680,
      "train_runtime": 444897.2758,
      "train_tokens_per_second": 29197.314
    },
    {
      "epoch": 1.6166025736001433,
      "grad_norm": 1.5703125,
      "learning_rate": 2.118777218351139e-05,
      "loss": 1.043496322631836,
      "num_input_tokens_seen": 12992623296,
      "step": 45690,
      "train_runtime": 444994.6827,
      "train_tokens_per_second": 29197.255
    },
    {
      "epoch": 1.616956393863872,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1185870109572614e-05,
      "loss": 1.0510296821594238,
      "num_input_tokens_seen": 12995437504,
      "step": 45700,
      "train_runtime": 445090.2523,
      "train_tokens_per_second": 29197.309
    },
    {
      "epoch": 1.6173102141276008,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1183968547802243e-05,
      "loss": 1.0419703483581544,
      "num_input_tokens_seen": 12998207936,
      "step": 45710,
      "train_runtime": 445187.3383,
      "train_tokens_per_second": 29197.164
    },
    {
      "epoch": 1.6176640343913298,
      "grad_norm": 1.546875,
      "learning_rate": 2.1182067497970464e-05,
      "loss": 1.047741413116455,
      "num_input_tokens_seen": 13001048000,
      "step": 45720,
      "train_runtime": 445285.3991,
      "train_tokens_per_second": 29197.113
    },
    {
      "epoch": 1.6180178546550583,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1180166959847613e-05,
      "loss": 1.027329444885254,
      "num_input_tokens_seen": 13003955456,
      "step": 45730,
      "train_runtime": 445389.5992,
      "train_tokens_per_second": 29196.81
    },
    {
      "epoch": 1.6183716749187873,
      "grad_norm": 1.53125,
      "learning_rate": 2.1178266933204168e-05,
      "loss": 1.0437131881713868,
      "num_input_tokens_seen": 13006771584,
      "step": 45740,
      "train_runtime": 445486.4624,
      "train_tokens_per_second": 29196.783
    },
    {
      "epoch": 1.6187254951825158,
      "grad_norm": 1.5,
      "learning_rate": 2.1176367417810754e-05,
      "loss": 1.059103012084961,
      "num_input_tokens_seen": 13009608512,
      "step": 45750,
      "train_runtime": 445583.934,
      "train_tokens_per_second": 29196.763
    },
    {
      "epoch": 1.6190793154462448,
      "grad_norm": 1.5625,
      "learning_rate": 2.1174468413438138e-05,
      "loss": 1.058873748779297,
      "num_input_tokens_seen": 13012532928,
      "step": 45760,
      "train_runtime": 445687.3452,
      "train_tokens_per_second": 29196.55
    },
    {
      "epoch": 1.6194331357099734,
      "grad_norm": 1.609375,
      "learning_rate": 2.1172569919857225e-05,
      "loss": 1.04759521484375,
      "num_input_tokens_seen": 13015375424,
      "step": 45770,
      "train_runtime": 445784.3132,
      "train_tokens_per_second": 29196.576
    },
    {
      "epoch": 1.6197869559737024,
      "grad_norm": 1.5625,
      "learning_rate": 2.117067193683907e-05,
      "loss": 1.0393503189086915,
      "num_input_tokens_seen": 13018198976,
      "step": 45780,
      "train_runtime": 445879.6933,
      "train_tokens_per_second": 29196.663
    },
    {
      "epoch": 1.6201407762374311,
      "grad_norm": 1.578125,
      "learning_rate": 2.1168774464154877e-05,
      "loss": 1.0540716171264648,
      "num_input_tokens_seen": 13021067456,
      "step": 45790,
      "train_runtime": 445978.0124,
      "train_tokens_per_second": 29196.658
    },
    {
      "epoch": 1.62049459650116,
      "grad_norm": 1.6171875,
      "learning_rate": 2.116687750157598e-05,
      "loss": 1.0280941009521485,
      "num_input_tokens_seen": 13023915008,
      "step": 45800,
      "train_runtime": 446077.9779,
      "train_tokens_per_second": 29196.498
    },
    {
      "epoch": 1.6208484167648887,
      "grad_norm": 1.5703125,
      "learning_rate": 2.116498104887387e-05,
      "loss": 1.0313157081604003,
      "num_input_tokens_seen": 13026771648,
      "step": 45810,
      "train_runtime": 446176.6892,
      "train_tokens_per_second": 29196.442
    },
    {
      "epoch": 1.6212022370286174,
      "grad_norm": 1.5078125,
      "learning_rate": 2.1163085105820175e-05,
      "loss": 1.0493535041809081,
      "num_input_tokens_seen": 13029592256,
      "step": 45820,
      "train_runtime": 446272.2649,
      "train_tokens_per_second": 29196.509
    },
    {
      "epoch": 1.6215560572923462,
      "grad_norm": 1.53125,
      "learning_rate": 2.116118967218666e-05,
      "loss": 1.041722297668457,
      "num_input_tokens_seen": 13032440768,
      "step": 45830,
      "train_runtime": 446369.6234,
      "train_tokens_per_second": 29196.523
    },
    {
      "epoch": 1.621909877556075,
      "grad_norm": 1.59375,
      "learning_rate": 2.115929474774525e-05,
      "loss": 1.0371341705322266,
      "num_input_tokens_seen": 13035298816,
      "step": 45840,
      "train_runtime": 446465.2198,
      "train_tokens_per_second": 29196.673
    },
    {
      "epoch": 1.6222636978198037,
      "grad_norm": 1.59375,
      "learning_rate": 2.1157400332267988e-05,
      "loss": 1.0379834175109863,
      "num_input_tokens_seen": 13038126784,
      "step": 45850,
      "train_runtime": 446561.3237,
      "train_tokens_per_second": 29196.722
    },
    {
      "epoch": 1.6226175180835325,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1155506425527083e-05,
      "loss": 1.0553869247436523,
      "num_input_tokens_seen": 13040989568,
      "step": 45860,
      "train_runtime": 446657.7286,
      "train_tokens_per_second": 29196.83
    },
    {
      "epoch": 1.6229713383472615,
      "grad_norm": 1.5625,
      "learning_rate": 2.115361302729488e-05,
      "loss": 1.0496926307678223,
      "num_input_tokens_seen": 13043850432,
      "step": 45870,
      "train_runtime": 446756.7032,
      "train_tokens_per_second": 29196.765
    },
    {
      "epoch": 1.62332515861099,
      "grad_norm": 1.5625,
      "learning_rate": 2.115172013734386e-05,
      "loss": 1.0443217277526855,
      "num_input_tokens_seen": 13046672512,
      "step": 45880,
      "train_runtime": 446851.6897,
      "train_tokens_per_second": 29196.874
    },
    {
      "epoch": 1.623678978874719,
      "grad_norm": 1.515625,
      "learning_rate": 2.1149827755446652e-05,
      "loss": 1.028960609436035,
      "num_input_tokens_seen": 13049484224,
      "step": 45890,
      "train_runtime": 446950.2868,
      "train_tokens_per_second": 29196.724
    },
    {
      "epoch": 1.6240327991384476,
      "grad_norm": 1.59375,
      "learning_rate": 2.1147935881376024e-05,
      "loss": 1.0520562171936034,
      "num_input_tokens_seen": 13052268352,
      "step": 45900,
      "train_runtime": 447041.0164,
      "train_tokens_per_second": 29197.026
    },
    {
      "epoch": 1.6243866194021765,
      "grad_norm": 1.546875,
      "learning_rate": 2.114604451490489e-05,
      "loss": 1.043747901916504,
      "num_input_tokens_seen": 13055154752,
      "step": 45910,
      "train_runtime": 447139.1045,
      "train_tokens_per_second": 29197.077
    },
    {
      "epoch": 1.624740439665905,
      "grad_norm": 1.546875,
      "learning_rate": 2.1144153655806313e-05,
      "loss": 1.0399864196777344,
      "num_input_tokens_seen": 13058002880,
      "step": 45920,
      "train_runtime": 447235.7241,
      "train_tokens_per_second": 29197.137
    },
    {
      "epoch": 1.625094259929634,
      "grad_norm": 1.5234375,
      "learning_rate": 2.114226330385347e-05,
      "loss": 1.0345932006835938,
      "num_input_tokens_seen": 13060896256,
      "step": 45930,
      "train_runtime": 447337.6349,
      "train_tokens_per_second": 29196.954
    },
    {
      "epoch": 1.6254480801933626,
      "grad_norm": 1.5,
      "learning_rate": 2.1140373458819724e-05,
      "loss": 1.0480596542358398,
      "num_input_tokens_seen": 13063714752,
      "step": 45940,
      "train_runtime": 447437.0597,
      "train_tokens_per_second": 29196.765
    },
    {
      "epoch": 1.6258019004570916,
      "grad_norm": 1.5625,
      "learning_rate": 2.1138484120478535e-05,
      "loss": 1.0573106765747071,
      "num_input_tokens_seen": 13066550336,
      "step": 45950,
      "train_runtime": 447531.6258,
      "train_tokens_per_second": 29196.932
    },
    {
      "epoch": 1.6261557207208204,
      "grad_norm": 1.5625,
      "learning_rate": 2.1136595288603532e-05,
      "loss": 1.046173667907715,
      "num_input_tokens_seen": 13069404032,
      "step": 45960,
      "train_runtime": 447633.7344,
      "train_tokens_per_second": 29196.647
    },
    {
      "epoch": 1.6265095409845491,
      "grad_norm": 1.6015625,
      "learning_rate": 2.113470696296849e-05,
      "loss": 1.0373607635498048,
      "num_input_tokens_seen": 13072281472,
      "step": 45970,
      "train_runtime": 447731.9296,
      "train_tokens_per_second": 29196.67
    },
    {
      "epoch": 1.626863361248278,
      "grad_norm": 1.65625,
      "learning_rate": 2.1132819143347296e-05,
      "loss": 1.0497488975524902,
      "num_input_tokens_seen": 13075117376,
      "step": 45980,
      "train_runtime": 447830.3899,
      "train_tokens_per_second": 29196.584
    },
    {
      "epoch": 1.6272171815120067,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1130931829514005e-05,
      "loss": 1.043372344970703,
      "num_input_tokens_seen": 13077915200,
      "step": 45990,
      "train_runtime": 447924.3973,
      "train_tokens_per_second": 29196.702
    },
    {
      "epoch": 1.6275710017757354,
      "grad_norm": 1.59375,
      "learning_rate": 2.112904502124281e-05,
      "loss": 1.0511838912963867,
      "num_input_tokens_seen": 13080718592,
      "step": 46000,
      "train_runtime": 448018.6169,
      "train_tokens_per_second": 29196.819
    },
    {
      "epoch": 1.6279248220394642,
      "grad_norm": 1.5390625,
      "learning_rate": 2.112715871830803e-05,
      "loss": 1.0444914817810058,
      "num_input_tokens_seen": 13083587968,
      "step": 46010,
      "train_runtime": 448117.3861,
      "train_tokens_per_second": 29196.787
    },
    {
      "epoch": 1.628278642303193,
      "grad_norm": 1.5625,
      "learning_rate": 2.112527292048414e-05,
      "loss": 1.068752384185791,
      "num_input_tokens_seen": 13086399744,
      "step": 46020,
      "train_runtime": 448213.4201,
      "train_tokens_per_second": 29196.805
    },
    {
      "epoch": 1.6286324625669217,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1123387627545748e-05,
      "loss": 1.0460834503173828,
      "num_input_tokens_seen": 13089255104,
      "step": 46030,
      "train_runtime": 448311.5016,
      "train_tokens_per_second": 29196.786
    },
    {
      "epoch": 1.6289862828306507,
      "grad_norm": 1.5703125,
      "learning_rate": 2.112150283926761e-05,
      "loss": 1.0375429153442384,
      "num_input_tokens_seen": 13092094592,
      "step": 46040,
      "train_runtime": 448409.7565,
      "train_tokens_per_second": 29196.721
    },
    {
      "epoch": 1.6293401030943793,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1119618555424612e-05,
      "loss": 1.054412841796875,
      "num_input_tokens_seen": 13094937920,
      "step": 46050,
      "train_runtime": 448506.6047,
      "train_tokens_per_second": 29196.756
    },
    {
      "epoch": 1.6296939233581083,
      "grad_norm": 1.53125,
      "learning_rate": 2.1117734775791794e-05,
      "loss": 1.041779136657715,
      "num_input_tokens_seen": 13097787008,
      "step": 46060,
      "train_runtime": 448606.8987,
      "train_tokens_per_second": 29196.58
    },
    {
      "epoch": 1.6300477436218368,
      "grad_norm": 1.609375,
      "learning_rate": 2.1115851500144324e-05,
      "loss": 1.0425216674804687,
      "num_input_tokens_seen": 13100669632,
      "step": 46070,
      "train_runtime": 448708.8638,
      "train_tokens_per_second": 29196.369
    },
    {
      "epoch": 1.6304015638855658,
      "grad_norm": 1.546875,
      "learning_rate": 2.1113968728257516e-05,
      "loss": 1.0390350341796875,
      "num_input_tokens_seen": 13103485440,
      "step": 46080,
      "train_runtime": 448802.4448,
      "train_tokens_per_second": 29196.555
    },
    {
      "epoch": 1.6307553841492943,
      "grad_norm": 1.546875,
      "learning_rate": 2.1112086459906828e-05,
      "loss": 1.0471569061279298,
      "num_input_tokens_seen": 13106362880,
      "step": 46090,
      "train_runtime": 448900.8036,
      "train_tokens_per_second": 29196.568
    },
    {
      "epoch": 1.6311092044130233,
      "grad_norm": 1.53125,
      "learning_rate": 2.1110204694867846e-05,
      "loss": 1.041170310974121,
      "num_input_tokens_seen": 13109184320,
      "step": 46100,
      "train_runtime": 448997.5476,
      "train_tokens_per_second": 29196.561
    },
    {
      "epoch": 1.6314630246767519,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1108323432916305e-05,
      "loss": 1.040970802307129,
      "num_input_tokens_seen": 13111998528,
      "step": 46110,
      "train_runtime": 449092.1592,
      "train_tokens_per_second": 29196.677
    },
    {
      "epoch": 1.6318168449404808,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1106442673828086e-05,
      "loss": 1.028834915161133,
      "num_input_tokens_seen": 13114796928,
      "step": 46120,
      "train_runtime": 449188.2111,
      "train_tokens_per_second": 29196.663
    },
    {
      "epoch": 1.6321706652042096,
      "grad_norm": 1.578125,
      "learning_rate": 2.1104562417379202e-05,
      "loss": 1.0417366981506349,
      "num_input_tokens_seen": 13117667904,
      "step": 46130,
      "train_runtime": 449286.4307,
      "train_tokens_per_second": 29196.671
    },
    {
      "epoch": 1.6325244854679384,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1102682663345797e-05,
      "loss": 1.0517852783203125,
      "num_input_tokens_seen": 13120485824,
      "step": 46140,
      "train_runtime": 449385.0701,
      "train_tokens_per_second": 29196.533
    },
    {
      "epoch": 1.6328783057316671,
      "grad_norm": 1.5625,
      "learning_rate": 2.110080341150417e-05,
      "loss": 1.0380425453186035,
      "num_input_tokens_seen": 13123296384,
      "step": 46150,
      "train_runtime": 449481.9051,
      "train_tokens_per_second": 29196.495
    },
    {
      "epoch": 1.633232125995396,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1098924661630748e-05,
      "loss": 1.0318406105041504,
      "num_input_tokens_seen": 13126158592,
      "step": 46160,
      "train_runtime": 449579.8944,
      "train_tokens_per_second": 29196.498
    },
    {
      "epoch": 1.6335859462591247,
      "grad_norm": 1.5390625,
      "learning_rate": 2.109704641350211e-05,
      "loss": 1.0515216827392577,
      "num_input_tokens_seen": 13128961920,
      "step": 46170,
      "train_runtime": 449675.1117,
      "train_tokens_per_second": 29196.55
    },
    {
      "epoch": 1.6339397665228534,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1095168666894962e-05,
      "loss": 1.0501476287841798,
      "num_input_tokens_seen": 13131829312,
      "step": 46180,
      "train_runtime": 449771.1415,
      "train_tokens_per_second": 29196.692
    },
    {
      "epoch": 1.6342935867865822,
      "grad_norm": 1.546875,
      "learning_rate": 2.1093291421586156e-05,
      "loss": 1.0344221115112304,
      "num_input_tokens_seen": 13134680704,
      "step": 46190,
      "train_runtime": 449870.5922,
      "train_tokens_per_second": 29196.575
    },
    {
      "epoch": 1.634647407050311,
      "grad_norm": 1.578125,
      "learning_rate": 2.1091414677352676e-05,
      "loss": 1.0517990112304687,
      "num_input_tokens_seen": 13137536192,
      "step": 46200,
      "train_runtime": 449969.798,
      "train_tokens_per_second": 29196.484
    },
    {
      "epoch": 1.63500122731404,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1089538433971655e-05,
      "loss": 1.0370164871215821,
      "num_input_tokens_seen": 13140289920,
      "step": 46210,
      "train_runtime": 450059.3008,
      "train_tokens_per_second": 29196.797
    },
    {
      "epoch": 1.6353550475777685,
      "grad_norm": 1.546875,
      "learning_rate": 2.1087662691220356e-05,
      "loss": 1.0414294242858886,
      "num_input_tokens_seen": 13143133696,
      "step": 46220,
      "train_runtime": 450159.3889,
      "train_tokens_per_second": 29196.622
    },
    {
      "epoch": 1.6357088678414975,
      "grad_norm": 1.5625,
      "learning_rate": 2.1085787448876184e-05,
      "loss": 1.0402842521667481,
      "num_input_tokens_seen": 13145959488,
      "step": 46230,
      "train_runtime": 450254.5317,
      "train_tokens_per_second": 29196.729
    },
    {
      "epoch": 1.636062688105226,
      "grad_norm": 1.546875,
      "learning_rate": 2.1083912706716684e-05,
      "loss": 1.0508570671081543,
      "num_input_tokens_seen": 13148823552,
      "step": 46240,
      "train_runtime": 450353.4895,
      "train_tokens_per_second": 29196.673
    },
    {
      "epoch": 1.636416508368955,
      "grad_norm": 1.609375,
      "learning_rate": 2.108203846451954e-05,
      "loss": 1.0438257217407227,
      "num_input_tokens_seen": 13151654272,
      "step": 46250,
      "train_runtime": 450448.7057,
      "train_tokens_per_second": 29196.786
    },
    {
      "epoch": 1.6367703286326836,
      "grad_norm": 1.5703125,
      "learning_rate": 2.1080164722062563e-05,
      "loss": 1.0453462600708008,
      "num_input_tokens_seen": 13154499264,
      "step": 46260,
      "train_runtime": 450547.2926,
      "train_tokens_per_second": 29196.711
    },
    {
      "epoch": 1.6371241488964126,
      "grad_norm": 1.4921875,
      "learning_rate": 2.107829147912372e-05,
      "loss": 1.0453277587890626,
      "num_input_tokens_seen": 13157342336,
      "step": 46270,
      "train_runtime": 450641.8004,
      "train_tokens_per_second": 29196.897
    },
    {
      "epoch": 1.637477969160141,
      "grad_norm": 1.5234375,
      "learning_rate": 2.1076418735481103e-05,
      "loss": 1.0486770629882813,
      "num_input_tokens_seen": 13160202240,
      "step": 46280,
      "train_runtime": 450739.1009,
      "train_tokens_per_second": 29196.939
    },
    {
      "epoch": 1.63783178942387,
      "grad_norm": 1.5625,
      "learning_rate": 2.1074546490912953e-05,
      "loss": 1.0393259048461914,
      "num_input_tokens_seen": 13163059008,
      "step": 46290,
      "train_runtime": 450833.7334,
      "train_tokens_per_second": 29197.147
    },
    {
      "epoch": 1.6381856096875989,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1072674745197633e-05,
      "loss": 1.0415185928344726,
      "num_input_tokens_seen": 13165887680,
      "step": 46300,
      "train_runtime": 450929.4295,
      "train_tokens_per_second": 29197.224
    },
    {
      "epoch": 1.6385394299513276,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1070803498113666e-05,
      "loss": 1.0281451225280762,
      "num_input_tokens_seen": 13168763136,
      "step": 46310,
      "train_runtime": 451026.1118,
      "train_tokens_per_second": 29197.341
    },
    {
      "epoch": 1.6388932502150564,
      "grad_norm": 1.53125,
      "learning_rate": 2.1068932749439683e-05,
      "loss": 1.040757942199707,
      "num_input_tokens_seen": 13171664704,
      "step": 46320,
      "train_runtime": 451125.7541,
      "train_tokens_per_second": 29197.324
    },
    {
      "epoch": 1.6392470704787852,
      "grad_norm": 1.578125,
      "learning_rate": 2.106706249895448e-05,
      "loss": 1.0481891632080078,
      "num_input_tokens_seen": 13174498368,
      "step": 46330,
      "train_runtime": 451219.4048,
      "train_tokens_per_second": 29197.544
    },
    {
      "epoch": 1.639600890742514,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1065192746436978e-05,
      "loss": 1.0490798950195312,
      "num_input_tokens_seen": 13177369472,
      "step": 46340,
      "train_runtime": 451318.3687,
      "train_tokens_per_second": 29197.503
    },
    {
      "epoch": 1.6399547110062427,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1063323491666236e-05,
      "loss": 1.0412813186645509,
      "num_input_tokens_seen": 13180198144,
      "step": 46350,
      "train_runtime": 451414.4927,
      "train_tokens_per_second": 29197.552
    },
    {
      "epoch": 1.6403085312699714,
      "grad_norm": 1.484375,
      "learning_rate": 2.1061454734421454e-05,
      "loss": 1.0397573471069337,
      "num_input_tokens_seen": 13183083840,
      "step": 46360,
      "train_runtime": 451515.9887,
      "train_tokens_per_second": 29197.38
    },
    {
      "epoch": 1.6406623515337002,
      "grad_norm": 1.6171875,
      "learning_rate": 2.1059586474481964e-05,
      "loss": 1.0464710235595702,
      "num_input_tokens_seen": 13185916928,
      "step": 46370,
      "train_runtime": 451614.328,
      "train_tokens_per_second": 29197.295
    },
    {
      "epoch": 1.6410161717974292,
      "grad_norm": 1.484375,
      "learning_rate": 2.1057718711627242e-05,
      "loss": 1.0438583374023438,
      "num_input_tokens_seen": 13188786176,
      "step": 46380,
      "train_runtime": 451712.3017,
      "train_tokens_per_second": 29197.315
    },
    {
      "epoch": 1.6413699920611577,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1055851445636883e-05,
      "loss": 1.0410429000854493,
      "num_input_tokens_seen": 13191628032,
      "step": 46390,
      "train_runtime": 451815.1615,
      "train_tokens_per_second": 29196.957
    },
    {
      "epoch": 1.6417238123248867,
      "grad_norm": 1.5390625,
      "learning_rate": 2.105398467629065e-05,
      "loss": 1.058316993713379,
      "num_input_tokens_seen": 13194503104,
      "step": 46400,
      "train_runtime": 451913.9365,
      "train_tokens_per_second": 29196.938
    },
    {
      "epoch": 1.6420776325886153,
      "grad_norm": 1.625,
      "learning_rate": 2.105211840336841e-05,
      "loss": 1.0347240447998047,
      "num_input_tokens_seen": 13197430976,
      "step": 46410,
      "train_runtime": 452019.206,
      "train_tokens_per_second": 29196.616
    },
    {
      "epoch": 1.6424314528523443,
      "grad_norm": 1.75,
      "learning_rate": 2.1050252626650186e-05,
      "loss": 1.0519929885864259,
      "num_input_tokens_seen": 13200295744,
      "step": 46420,
      "train_runtime": 452118.3533,
      "train_tokens_per_second": 29196.549
    },
    {
      "epoch": 1.6427852731160728,
      "grad_norm": 1.5078125,
      "learning_rate": 2.104838734591614e-05,
      "loss": 1.0457836151123048,
      "num_input_tokens_seen": 13203172032,
      "step": 46430,
      "train_runtime": 452217.7775,
      "train_tokens_per_second": 29196.49
    },
    {
      "epoch": 1.6431390933798018,
      "grad_norm": 1.546875,
      "learning_rate": 2.1046522560946552e-05,
      "loss": 1.051173210144043,
      "num_input_tokens_seen": 13206040256,
      "step": 46440,
      "train_runtime": 452317.5407,
      "train_tokens_per_second": 29196.392
    },
    {
      "epoch": 1.6434929136435306,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1044658271521856e-05,
      "loss": 1.0393603324890137,
      "num_input_tokens_seen": 13208871616,
      "step": 46450,
      "train_runtime": 452413.4982,
      "train_tokens_per_second": 29196.458
    },
    {
      "epoch": 1.6438467339072593,
      "grad_norm": 1.5625,
      "learning_rate": 2.1042794477422607e-05,
      "loss": 1.0537090301513672,
      "num_input_tokens_seen": 13211724224,
      "step": 46460,
      "train_runtime": 452511.737,
      "train_tokens_per_second": 29196.423
    },
    {
      "epoch": 1.644200554170988,
      "grad_norm": 1.578125,
      "learning_rate": 2.104093117842952e-05,
      "loss": 1.0456012725830077,
      "num_input_tokens_seen": 13214587840,
      "step": 46470,
      "train_runtime": 452610.323,
      "train_tokens_per_second": 29196.391
    },
    {
      "epoch": 1.6445543744347169,
      "grad_norm": 1.609375,
      "learning_rate": 2.1039068374323418e-05,
      "loss": 1.0417285919189454,
      "num_input_tokens_seen": 13217446528,
      "step": 46480,
      "train_runtime": 452708.1493,
      "train_tokens_per_second": 29196.396
    },
    {
      "epoch": 1.6449081946984456,
      "grad_norm": 1.53125,
      "learning_rate": 2.1037206064885274e-05,
      "loss": 1.050992202758789,
      "num_input_tokens_seen": 13220312960,
      "step": 46490,
      "train_runtime": 452808.3346,
      "train_tokens_per_second": 29196.267
    },
    {
      "epoch": 1.6452620149621744,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1035344249896195e-05,
      "loss": 1.0359968185424804,
      "num_input_tokens_seen": 13223205056,
      "step": 46500,
      "train_runtime": 452907.9758,
      "train_tokens_per_second": 29196.229
    },
    {
      "epoch": 1.6456158352259032,
      "grad_norm": 1.5859375,
      "learning_rate": 2.1033482929137428e-05,
      "loss": 1.0434438705444335,
      "num_input_tokens_seen": 13226083584,
      "step": 46510,
      "train_runtime": 453009.1769,
      "train_tokens_per_second": 29196.061
    },
    {
      "epoch": 1.645969655489632,
      "grad_norm": 1.578125,
      "learning_rate": 2.1031622102390343e-05,
      "loss": 1.0472466468811035,
      "num_input_tokens_seen": 13228925952,
      "step": 46520,
      "train_runtime": 453105.2479,
      "train_tokens_per_second": 29196.144
    },
    {
      "epoch": 1.6463234757533607,
      "grad_norm": 1.5546875,
      "learning_rate": 2.1029761769436462e-05,
      "loss": 1.054567527770996,
      "num_input_tokens_seen": 13231716608,
      "step": 46530,
      "train_runtime": 453200.4771,
      "train_tokens_per_second": 29196.167
    },
    {
      "epoch": 1.6466772960170895,
      "grad_norm": 1.609375,
      "learning_rate": 2.1027901930057424e-05,
      "loss": 1.0405843734741211,
      "num_input_tokens_seen": 13234541632,
      "step": 46540,
      "train_runtime": 453296.6358,
      "train_tokens_per_second": 29196.205
    },
    {
      "epoch": 1.6470311162808184,
      "grad_norm": 1.5625,
      "learning_rate": 2.1026042584035024e-05,
      "loss": 1.0536142349243165,
      "num_input_tokens_seen": 13237397568,
      "step": 46550,
      "train_runtime": 453394.6308,
      "train_tokens_per_second": 29196.194
    },
    {
      "epoch": 1.647384936544547,
      "grad_norm": 1.546875,
      "learning_rate": 2.102418373115117e-05,
      "loss": 1.0409521102905273,
      "num_input_tokens_seen": 13240272896,
      "step": 46560,
      "train_runtime": 453493.6649,
      "train_tokens_per_second": 29196.158
    },
    {
      "epoch": 1.647738756808276,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1022325371187922e-05,
      "loss": 1.03292236328125,
      "num_input_tokens_seen": 13243127168,
      "step": 46570,
      "train_runtime": 453590.7672,
      "train_tokens_per_second": 29196.201
    },
    {
      "epoch": 1.6480925770720045,
      "grad_norm": 1.53125,
      "learning_rate": 2.102046750392747e-05,
      "loss": 1.0524033546447753,
      "num_input_tokens_seen": 13245971712,
      "step": 46580,
      "train_runtime": 453687.8774,
      "train_tokens_per_second": 29196.221
    },
    {
      "epoch": 1.6484463973357335,
      "grad_norm": 1.53125,
      "learning_rate": 2.1018610129152124e-05,
      "loss": 1.0444852828979492,
      "num_input_tokens_seen": 13248825600,
      "step": 46590,
      "train_runtime": 453788.1898,
      "train_tokens_per_second": 29196.056
    },
    {
      "epoch": 1.648800217599462,
      "grad_norm": 1.4921875,
      "learning_rate": 2.101675324664436e-05,
      "loss": 1.035674476623535,
      "num_input_tokens_seen": 13251676864,
      "step": 46600,
      "train_runtime": 453883.6559,
      "train_tokens_per_second": 29196.198
    },
    {
      "epoch": 1.649154037863191,
      "grad_norm": 1.6171875,
      "learning_rate": 2.101489685618676e-05,
      "loss": 1.042851448059082,
      "num_input_tokens_seen": 13254531008,
      "step": 46610,
      "train_runtime": 453981.2854,
      "train_tokens_per_second": 29196.206
    },
    {
      "epoch": 1.6495078581269198,
      "grad_norm": 1.578125,
      "learning_rate": 2.1013040957562053e-05,
      "loss": 1.0516764640808105,
      "num_input_tokens_seen": 13257378880,
      "step": 46620,
      "train_runtime": 454078.885,
      "train_tokens_per_second": 29196.202
    },
    {
      "epoch": 1.6498616783906486,
      "grad_norm": 1.578125,
      "learning_rate": 2.1011185550553098e-05,
      "loss": 1.0474960327148437,
      "num_input_tokens_seen": 13260264704,
      "step": 46630,
      "train_runtime": 454176.3858,
      "train_tokens_per_second": 29196.288
    },
    {
      "epoch": 1.6502154986543773,
      "grad_norm": 1.6015625,
      "learning_rate": 2.1009330634942888e-05,
      "loss": 1.0495420455932618,
      "num_input_tokens_seen": 13263092864,
      "step": 46640,
      "train_runtime": 454271.7108,
      "train_tokens_per_second": 29196.387
    },
    {
      "epoch": 1.650569318918106,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1007476210514558e-05,
      "loss": 1.0578771591186524,
      "num_input_tokens_seen": 13265986880,
      "step": 46650,
      "train_runtime": 454371.0557,
      "train_tokens_per_second": 29196.373
    },
    {
      "epoch": 1.6509231391818349,
      "grad_norm": 1.59375,
      "learning_rate": 2.1005622277051373e-05,
      "loss": 1.0405420303344726,
      "num_input_tokens_seen": 13268831936,
      "step": 46660,
      "train_runtime": 454468.2262,
      "train_tokens_per_second": 29196.391
    },
    {
      "epoch": 1.6512769594455636,
      "grad_norm": 1.578125,
      "learning_rate": 2.1003768834336722e-05,
      "loss": 1.034939956665039,
      "num_input_tokens_seen": 13271678208,
      "step": 46670,
      "train_runtime": 454567.1969,
      "train_tokens_per_second": 29196.296
    },
    {
      "epoch": 1.6516307797092924,
      "grad_norm": 1.6015625,
      "learning_rate": 2.100191588215414e-05,
      "loss": 1.042933177947998,
      "num_input_tokens_seen": 13274531392,
      "step": 46680,
      "train_runtime": 454666.3151,
      "train_tokens_per_second": 29196.206
    },
    {
      "epoch": 1.6519845999730212,
      "grad_norm": 1.5390625,
      "learning_rate": 2.1000063420287294e-05,
      "loss": 1.048354148864746,
      "num_input_tokens_seen": 13277452096,
      "step": 46690,
      "train_runtime": 454767.5276,
      "train_tokens_per_second": 29196.131
    },
    {
      "epoch": 1.6523384202367501,
      "grad_norm": 1.53125,
      "learning_rate": 2.0998211448519977e-05,
      "loss": 1.0457612991333007,
      "num_input_tokens_seen": 13280262400,
      "step": 46700,
      "train_runtime": 454862.6518,
      "train_tokens_per_second": 29196.203
    },
    {
      "epoch": 1.6526922405004787,
      "grad_norm": 1.53125,
      "learning_rate": 2.0996359966636126e-05,
      "loss": 1.0481047630310059,
      "num_input_tokens_seen": 13283095104,
      "step": 46710,
      "train_runtime": 454959.1776,
      "train_tokens_per_second": 29196.235
    },
    {
      "epoch": 1.6530460607642077,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0994508974419803e-05,
      "loss": 1.0480422019958495,
      "num_input_tokens_seen": 13285955648,
      "step": 46720,
      "train_runtime": 455059.003,
      "train_tokens_per_second": 29196.116
    },
    {
      "epoch": 1.6533998810279362,
      "grad_norm": 1.578125,
      "learning_rate": 2.0992658471655204e-05,
      "loss": 1.0436612129211427,
      "num_input_tokens_seen": 13288854080,
      "step": 46730,
      "train_runtime": 455158.672,
      "train_tokens_per_second": 29196.091
    },
    {
      "epoch": 1.6537537012916652,
      "grad_norm": 1.609375,
      "learning_rate": 2.099080845812666e-05,
      "loss": 1.034919261932373,
      "num_input_tokens_seen": 13291678272,
      "step": 46740,
      "train_runtime": 455255.1077,
      "train_tokens_per_second": 29196.11
    },
    {
      "epoch": 1.6541075215553938,
      "grad_norm": 1.59375,
      "learning_rate": 2.0988958933618644e-05,
      "loss": 1.0450848579406737,
      "num_input_tokens_seen": 13294490624,
      "step": 46750,
      "train_runtime": 455348.9459,
      "train_tokens_per_second": 29196.27
    },
    {
      "epoch": 1.6544613418191227,
      "grad_norm": 1.5625,
      "learning_rate": 2.0987109897915743e-05,
      "loss": 1.0262994766235352,
      "num_input_tokens_seen": 13297313344,
      "step": 46760,
      "train_runtime": 455443.0541,
      "train_tokens_per_second": 29196.435
    },
    {
      "epoch": 1.6548151620828513,
      "grad_norm": 1.5625,
      "learning_rate": 2.098526135080269e-05,
      "loss": 1.043727970123291,
      "num_input_tokens_seen": 13300200448,
      "step": 46770,
      "train_runtime": 455545.7237,
      "train_tokens_per_second": 29196.192
    },
    {
      "epoch": 1.6551689823465803,
      "grad_norm": 1.6796875,
      "learning_rate": 2.098341329206435e-05,
      "loss": 1.0367565155029297,
      "num_input_tokens_seen": 13303008704,
      "step": 46780,
      "train_runtime": 455642.1439,
      "train_tokens_per_second": 29196.177
    },
    {
      "epoch": 1.655522802610309,
      "grad_norm": 1.6171875,
      "learning_rate": 2.0981565721485717e-05,
      "loss": 1.0436342239379883,
      "num_input_tokens_seen": 13305876544,
      "step": 46790,
      "train_runtime": 455741.123,
      "train_tokens_per_second": 29196.129
    },
    {
      "epoch": 1.6558766228740378,
      "grad_norm": 1.5625,
      "learning_rate": 2.097971863885191e-05,
      "loss": 1.049390697479248,
      "num_input_tokens_seen": 13308730368,
      "step": 46800,
      "train_runtime": 455839.0035,
      "train_tokens_per_second": 29196.12
    },
    {
      "epoch": 1.6562304431377666,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0977872043948204e-05,
      "loss": 1.043410873413086,
      "num_input_tokens_seen": 13311532672,
      "step": 46810,
      "train_runtime": 455933.5458,
      "train_tokens_per_second": 29196.212
    },
    {
      "epoch": 1.6565842634014953,
      "grad_norm": 1.53125,
      "learning_rate": 2.0976025936559985e-05,
      "loss": 1.050224494934082,
      "num_input_tokens_seen": 13314393216,
      "step": 46820,
      "train_runtime": 456031.7654,
      "train_tokens_per_second": 29196.197
    },
    {
      "epoch": 1.656938083665224,
      "grad_norm": 1.578125,
      "learning_rate": 2.0974180316472775e-05,
      "loss": 1.0492095947265625,
      "num_input_tokens_seen": 13317245120,
      "step": 46830,
      "train_runtime": 456129.9987,
      "train_tokens_per_second": 29196.162
    },
    {
      "epoch": 1.6572919039289529,
      "grad_norm": 1.6484375,
      "learning_rate": 2.097233518347223e-05,
      "loss": 1.0414523124694823,
      "num_input_tokens_seen": 13320087360,
      "step": 46840,
      "train_runtime": 456224.6387,
      "train_tokens_per_second": 29196.335
    },
    {
      "epoch": 1.6576457241926816,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0970490537344147e-05,
      "loss": 1.041114616394043,
      "num_input_tokens_seen": 13322951360,
      "step": 46850,
      "train_runtime": 456323.3271,
      "train_tokens_per_second": 29196.297
    },
    {
      "epoch": 1.6579995444564104,
      "grad_norm": 1.546875,
      "learning_rate": 2.096864637787444e-05,
      "loss": 1.0383722305297851,
      "num_input_tokens_seen": 13325792384,
      "step": 46860,
      "train_runtime": 456423.3829,
      "train_tokens_per_second": 29196.121
    },
    {
      "epoch": 1.6583533647201394,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0966802704849163e-05,
      "loss": 1.044740867614746,
      "num_input_tokens_seen": 13328666816,
      "step": 46870,
      "train_runtime": 456523.1392,
      "train_tokens_per_second": 29196.038
    },
    {
      "epoch": 1.658707184983868,
      "grad_norm": 1.609375,
      "learning_rate": 2.0964959518054493e-05,
      "loss": 1.0436692237854004,
      "num_input_tokens_seen": 13331439104,
      "step": 46880,
      "train_runtime": 456615.544,
      "train_tokens_per_second": 29196.201
    },
    {
      "epoch": 1.659061005247597,
      "grad_norm": 1.515625,
      "learning_rate": 2.0963116817276757e-05,
      "loss": 1.0431354522705079,
      "num_input_tokens_seen": 13334280384,
      "step": 46890,
      "train_runtime": 456714.6153,
      "train_tokens_per_second": 29196.089
    },
    {
      "epoch": 1.6594148255113255,
      "grad_norm": 1.578125,
      "learning_rate": 2.09612746023024e-05,
      "loss": 1.055609893798828,
      "num_input_tokens_seen": 13337033728,
      "step": 46900,
      "train_runtime": 456805.7556,
      "train_tokens_per_second": 29196.291
    },
    {
      "epoch": 1.6597686457750545,
      "grad_norm": 1.5625,
      "learning_rate": 2.095943287291799e-05,
      "loss": 1.0302774429321289,
      "num_input_tokens_seen": 13339911232,
      "step": 46910,
      "train_runtime": 456905.6602,
      "train_tokens_per_second": 29196.205
    },
    {
      "epoch": 1.660122466038783,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0957591628910243e-05,
      "loss": 1.0479881286621093,
      "num_input_tokens_seen": 13342779200,
      "step": 46920,
      "train_runtime": 457004.0384,
      "train_tokens_per_second": 29196.195
    },
    {
      "epoch": 1.660476286302512,
      "grad_norm": 1.578125,
      "learning_rate": 2.0955750870066006e-05,
      "loss": 1.0544830322265626,
      "num_input_tokens_seen": 13345669440,
      "step": 46930,
      "train_runtime": 457102.9238,
      "train_tokens_per_second": 29196.202
    },
    {
      "epoch": 1.6608301065662405,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0953910596172238e-05,
      "loss": 1.0262856483459473,
      "num_input_tokens_seen": 13348459328,
      "step": 46940,
      "train_runtime": 457197.9955,
      "train_tokens_per_second": 29196.233
    },
    {
      "epoch": 1.6611839268299695,
      "grad_norm": 1.515625,
      "learning_rate": 2.095207080701605e-05,
      "loss": 1.0338899612426757,
      "num_input_tokens_seen": 13351299712,
      "step": 46950,
      "train_runtime": 457298.2516,
      "train_tokens_per_second": 29196.044
    },
    {
      "epoch": 1.6615377470936983,
      "grad_norm": 1.546875,
      "learning_rate": 2.095023150238468e-05,
      "loss": 1.0509410858154298,
      "num_input_tokens_seen": 13354214464,
      "step": 46960,
      "train_runtime": 457397.4501,
      "train_tokens_per_second": 29196.084
    },
    {
      "epoch": 1.661891567357427,
      "grad_norm": 1.609375,
      "learning_rate": 2.094839268206548e-05,
      "loss": 1.047112274169922,
      "num_input_tokens_seen": 13357048896,
      "step": 46970,
      "train_runtime": 457493.0668,
      "train_tokens_per_second": 29196.178
    },
    {
      "epoch": 1.6622453876211558,
      "grad_norm": 1.5078125,
      "learning_rate": 2.094655434584595e-05,
      "loss": 1.0434722900390625,
      "num_input_tokens_seen": 13359905216,
      "step": 46980,
      "train_runtime": 457589.1288,
      "train_tokens_per_second": 29196.291
    },
    {
      "epoch": 1.6625992078848846,
      "grad_norm": 1.5625,
      "learning_rate": 2.0944716493513714e-05,
      "loss": 1.0429104804992675,
      "num_input_tokens_seen": 13362752320,
      "step": 46990,
      "train_runtime": 457689.6381,
      "train_tokens_per_second": 29196.1
    },
    {
      "epoch": 1.6629530281486133,
      "grad_norm": 1.59375,
      "learning_rate": 2.0942879124856534e-05,
      "loss": 1.0438237190246582,
      "num_input_tokens_seen": 13365596352,
      "step": 47000,
      "train_runtime": 457787.0839,
      "train_tokens_per_second": 29196.098
    },
    {
      "epoch": 1.663306848412342,
      "grad_norm": 1.5234375,
      "learning_rate": 2.094104223966229e-05,
      "loss": 1.05397367477417,
      "num_input_tokens_seen": 13368435264,
      "step": 47010,
      "train_runtime": 457887.3056,
      "train_tokens_per_second": 29195.907
    },
    {
      "epoch": 1.6636606686760709,
      "grad_norm": 1.546875,
      "learning_rate": 2.0939205837719e-05,
      "loss": 1.0470624923706056,
      "num_input_tokens_seen": 13371336128,
      "step": 47020,
      "train_runtime": 457988.023,
      "train_tokens_per_second": 29195.821
    },
    {
      "epoch": 1.6640144889397996,
      "grad_norm": 1.625,
      "learning_rate": 2.093736991881481e-05,
      "loss": 1.0530908584594727,
      "num_input_tokens_seen": 13374194624,
      "step": 47030,
      "train_runtime": 458085.4751,
      "train_tokens_per_second": 29195.85
    },
    {
      "epoch": 1.6643683092035286,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0935534482737994e-05,
      "loss": 1.0404083251953125,
      "num_input_tokens_seen": 13377049408,
      "step": 47040,
      "train_runtime": 458184.6808,
      "train_tokens_per_second": 29195.759
    },
    {
      "epoch": 1.6647221294672572,
      "grad_norm": 1.609375,
      "learning_rate": 2.0933699529276963e-05,
      "loss": 1.0439571380615233,
      "num_input_tokens_seen": 13379879360,
      "step": 47050,
      "train_runtime": 458283.6731,
      "train_tokens_per_second": 29195.627
    },
    {
      "epoch": 1.6650759497309862,
      "grad_norm": 1.6015625,
      "learning_rate": 2.093186505822025e-05,
      "loss": 1.0417221069335938,
      "num_input_tokens_seen": 13382698880,
      "step": 47060,
      "train_runtime": 458378.27,
      "train_tokens_per_second": 29195.753
    },
    {
      "epoch": 1.6654297699947147,
      "grad_norm": 1.59375,
      "learning_rate": 2.093003106935652e-05,
      "loss": 1.0277709007263183,
      "num_input_tokens_seen": 13385529024,
      "step": 47070,
      "train_runtime": 458472.769,
      "train_tokens_per_second": 29195.909
    },
    {
      "epoch": 1.6657835902584437,
      "grad_norm": 1.578125,
      "learning_rate": 2.0928197562474576e-05,
      "loss": 1.0528524398803711,
      "num_input_tokens_seen": 13388344192,
      "step": 47080,
      "train_runtime": 458568.8932,
      "train_tokens_per_second": 29195.928
    },
    {
      "epoch": 1.6661374105221722,
      "grad_norm": 1.5625,
      "learning_rate": 2.0926364537363328e-05,
      "loss": 1.0390199661254882,
      "num_input_tokens_seen": 13391186560,
      "step": 47090,
      "train_runtime": 458665.013,
      "train_tokens_per_second": 29196.006
    },
    {
      "epoch": 1.6664912307859012,
      "grad_norm": 1.578125,
      "learning_rate": 2.0924531993811842e-05,
      "loss": 1.0489742279052734,
      "num_input_tokens_seen": 13393996416,
      "step": 47100,
      "train_runtime": 458758.5445,
      "train_tokens_per_second": 29196.179
    },
    {
      "epoch": 1.6668450510496298,
      "grad_norm": 1.578125,
      "learning_rate": 2.0922699931609298e-05,
      "loss": 1.0449716567993164,
      "num_input_tokens_seen": 13396853760,
      "step": 47110,
      "train_runtime": 458858.2973,
      "train_tokens_per_second": 29196.059
    },
    {
      "epoch": 1.6671988713133588,
      "grad_norm": 1.6484375,
      "learning_rate": 2.092086835054501e-05,
      "loss": 1.0386228561401367,
      "num_input_tokens_seen": 13399712064,
      "step": 47120,
      "train_runtime": 458959.7016,
      "train_tokens_per_second": 29195.836
    },
    {
      "epoch": 1.6675526915770875,
      "grad_norm": 1.5625,
      "learning_rate": 2.0919037250408417e-05,
      "loss": 1.061539649963379,
      "num_input_tokens_seen": 13402605056,
      "step": 47130,
      "train_runtime": 459062.1069,
      "train_tokens_per_second": 29195.625
    },
    {
      "epoch": 1.6679065118408163,
      "grad_norm": 1.53125,
      "learning_rate": 2.0917206630989093e-05,
      "loss": 1.0274774551391601,
      "num_input_tokens_seen": 13405434112,
      "step": 47140,
      "train_runtime": 459157.6139,
      "train_tokens_per_second": 29195.713
    },
    {
      "epoch": 1.668260332104545,
      "grad_norm": 1.625,
      "learning_rate": 2.0915376492076734e-05,
      "loss": 1.0601457595825194,
      "num_input_tokens_seen": 13408317248,
      "step": 47150,
      "train_runtime": 459257.1859,
      "train_tokens_per_second": 29195.661
    },
    {
      "epoch": 1.6686141523682738,
      "grad_norm": 1.59375,
      "learning_rate": 2.0913546833461167e-05,
      "loss": 1.0459922790527343,
      "num_input_tokens_seen": 13411214528,
      "step": 47160,
      "train_runtime": 459355.9211,
      "train_tokens_per_second": 29195.693
    },
    {
      "epoch": 1.6689679726320026,
      "grad_norm": 1.546875,
      "learning_rate": 2.0911717654932358e-05,
      "loss": 1.0506868362426758,
      "num_input_tokens_seen": 13414142848,
      "step": 47170,
      "train_runtime": 459457.6723,
      "train_tokens_per_second": 29195.601
    },
    {
      "epoch": 1.6693217928957313,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0909888956280382e-05,
      "loss": 1.0442222595214843,
      "num_input_tokens_seen": 13416974656,
      "step": 47180,
      "train_runtime": 459556.2284,
      "train_tokens_per_second": 29195.502
    },
    {
      "epoch": 1.6696756131594601,
      "grad_norm": 1.578125,
      "learning_rate": 2.0908060737295463e-05,
      "loss": 1.0459659576416016,
      "num_input_tokens_seen": 13419807360,
      "step": 47190,
      "train_runtime": 459654.922,
      "train_tokens_per_second": 29195.396
    },
    {
      "epoch": 1.6700294334231889,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0906232997767933e-05,
      "loss": 1.046407127380371,
      "num_input_tokens_seen": 13422652160,
      "step": 47200,
      "train_runtime": 459753.5346,
      "train_tokens_per_second": 29195.321
    },
    {
      "epoch": 1.6703832536869179,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0904405737488273e-05,
      "loss": 1.0499863624572754,
      "num_input_tokens_seen": 13425501952,
      "step": 47210,
      "train_runtime": 459852.2304,
      "train_tokens_per_second": 29195.252
    },
    {
      "epoch": 1.6707370739506464,
      "grad_norm": 1.59375,
      "learning_rate": 2.0902578956247073e-05,
      "loss": 1.0427212715148926,
      "num_input_tokens_seen": 13428351808,
      "step": 47220,
      "train_runtime": 459948.4449,
      "train_tokens_per_second": 29195.341
    },
    {
      "epoch": 1.6710908942143754,
      "grad_norm": 1.5390625,
      "learning_rate": 2.090075265383507e-05,
      "loss": 1.0481599807739257,
      "num_input_tokens_seen": 13431173376,
      "step": 47230,
      "train_runtime": 460043.0176,
      "train_tokens_per_second": 29195.473
    },
    {
      "epoch": 1.671444714478104,
      "grad_norm": 1.578125,
      "learning_rate": 2.0898926830043105e-05,
      "loss": 1.0492734909057617,
      "num_input_tokens_seen": 13434019200,
      "step": 47240,
      "train_runtime": 460143.0516,
      "train_tokens_per_second": 29195.31
    },
    {
      "epoch": 1.671798534741833,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0897101484662172e-05,
      "loss": 1.0275311470031738,
      "num_input_tokens_seen": 13436852224,
      "step": 47250,
      "train_runtime": 460239.3385,
      "train_tokens_per_second": 29195.358
    },
    {
      "epoch": 1.6721523550055615,
      "grad_norm": 1.546875,
      "learning_rate": 2.0895276617483384e-05,
      "loss": 1.0409951210021973,
      "num_input_tokens_seen": 13439749248,
      "step": 47260,
      "train_runtime": 460340.9623,
      "train_tokens_per_second": 29195.206
    },
    {
      "epoch": 1.6725061752692905,
      "grad_norm": 1.5625,
      "learning_rate": 2.089345222829797e-05,
      "loss": 1.0670215606689453,
      "num_input_tokens_seen": 13442612416,
      "step": 47270,
      "train_runtime": 460443.593,
      "train_tokens_per_second": 29194.917
    },
    {
      "epoch": 1.672859995533019,
      "grad_norm": 1.484375,
      "learning_rate": 2.0891628316897297e-05,
      "loss": 1.0492310523986816,
      "num_input_tokens_seen": 13445467136,
      "step": 47280,
      "train_runtime": 460541.1391,
      "train_tokens_per_second": 29194.932
    },
    {
      "epoch": 1.673213815796748,
      "grad_norm": 1.59375,
      "learning_rate": 2.0889804883072863e-05,
      "loss": 1.0431037902832032,
      "num_input_tokens_seen": 13448285184,
      "step": 47290,
      "train_runtime": 460634.195,
      "train_tokens_per_second": 29195.152
    },
    {
      "epoch": 1.6735676360604768,
      "grad_norm": 1.53125,
      "learning_rate": 2.088798192661629e-05,
      "loss": 1.0487661361694336,
      "num_input_tokens_seen": 13451164352,
      "step": 47300,
      "train_runtime": 460735.4841,
      "train_tokens_per_second": 29194.982
    },
    {
      "epoch": 1.6739214563242055,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0886159447319314e-05,
      "loss": 1.0385402679443358,
      "num_input_tokens_seen": 13453996416,
      "step": 47310,
      "train_runtime": 460828.8895,
      "train_tokens_per_second": 29195.21
    },
    {
      "epoch": 1.6742752765879343,
      "grad_norm": 1.609375,
      "learning_rate": 2.0884337444973824e-05,
      "loss": 1.0444768905639648,
      "num_input_tokens_seen": 13456834240,
      "step": 47320,
      "train_runtime": 460928.5045,
      "train_tokens_per_second": 29195.058
    },
    {
      "epoch": 1.674629096851663,
      "grad_norm": 1.5859375,
      "learning_rate": 2.088251591937182e-05,
      "loss": 1.04348783493042,
      "num_input_tokens_seen": 13459677824,
      "step": 47330,
      "train_runtime": 461023.3058,
      "train_tokens_per_second": 29195.222
    },
    {
      "epoch": 1.6749829171153918,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0880694870305427e-05,
      "loss": 1.0553012847900392,
      "num_input_tokens_seen": 13462523200,
      "step": 47340,
      "train_runtime": 461118.4519,
      "train_tokens_per_second": 29195.369
    },
    {
      "epoch": 1.6753367373791206,
      "grad_norm": 1.5625,
      "learning_rate": 2.08788742975669e-05,
      "loss": 1.0575847625732422,
      "num_input_tokens_seen": 13465363840,
      "step": 47350,
      "train_runtime": 461214.9731,
      "train_tokens_per_second": 29195.418
    },
    {
      "epoch": 1.6756905576428494,
      "grad_norm": 1.515625,
      "learning_rate": 2.0877054200948624e-05,
      "loss": 1.0414051055908202,
      "num_input_tokens_seen": 13468191488,
      "step": 47360,
      "train_runtime": 461310.5018,
      "train_tokens_per_second": 29195.502
    },
    {
      "epoch": 1.6760443779065781,
      "grad_norm": 1.5,
      "learning_rate": 2.08752345802431e-05,
      "loss": 1.0467647552490233,
      "num_input_tokens_seen": 13471042048,
      "step": 47370,
      "train_runtime": 461408.0476,
      "train_tokens_per_second": 29195.507
    },
    {
      "epoch": 1.676398198170307,
      "grad_norm": 1.5625,
      "learning_rate": 2.0873415435242988e-05,
      "loss": 1.0510597229003906,
      "num_input_tokens_seen": 13473888448,
      "step": 47380,
      "train_runtime": 461504.9358,
      "train_tokens_per_second": 29195.546
    },
    {
      "epoch": 1.6767520184340357,
      "grad_norm": 1.5390625,
      "learning_rate": 2.087159676574102e-05,
      "loss": 1.0448269844055176,
      "num_input_tokens_seen": 13476737984,
      "step": 47390,
      "train_runtime": 461602.18,
      "train_tokens_per_second": 29195.568
    },
    {
      "epoch": 1.6771058386977646,
      "grad_norm": 1.5390625,
      "learning_rate": 2.086977857153011e-05,
      "loss": 1.0441213607788087,
      "num_input_tokens_seen": 13479566400,
      "step": 47400,
      "train_runtime": 461699.0362,
      "train_tokens_per_second": 29195.57
    },
    {
      "epoch": 1.6774596589614932,
      "grad_norm": 1.53125,
      "learning_rate": 2.086796085240326e-05,
      "loss": 1.02572603225708,
      "num_input_tokens_seen": 13482357696,
      "step": 47410,
      "train_runtime": 461794.9778,
      "train_tokens_per_second": 29195.549
    },
    {
      "epoch": 1.6778134792252222,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0866143608153614e-05,
      "loss": 1.0397144317626954,
      "num_input_tokens_seen": 13485198336,
      "step": 47420,
      "train_runtime": 461893.4857,
      "train_tokens_per_second": 29195.472
    },
    {
      "epoch": 1.6781672994889507,
      "grad_norm": 1.6015625,
      "learning_rate": 2.086432683857444e-05,
      "loss": 1.0513761520385743,
      "num_input_tokens_seen": 13488037952,
      "step": 47430,
      "train_runtime": 461990.7485,
      "train_tokens_per_second": 29195.472
    },
    {
      "epoch": 1.6785211197526797,
      "grad_norm": 1.5625,
      "learning_rate": 2.0862510543459127e-05,
      "loss": 1.040067195892334,
      "num_input_tokens_seen": 13490893952,
      "step": 47440,
      "train_runtime": 462087.104,
      "train_tokens_per_second": 29195.565
    },
    {
      "epoch": 1.6788749400164085,
      "grad_norm": 1.546875,
      "learning_rate": 2.0860694722601197e-05,
      "loss": 1.0471364974975585,
      "num_input_tokens_seen": 13493688384,
      "step": 47450,
      "train_runtime": 462182.0053,
      "train_tokens_per_second": 29195.616
    },
    {
      "epoch": 1.6792287602801372,
      "grad_norm": 1.515625,
      "learning_rate": 2.0858879375794306e-05,
      "loss": 1.0379494667053222,
      "num_input_tokens_seen": 13496522752,
      "step": 47460,
      "train_runtime": 462279.2851,
      "train_tokens_per_second": 29195.604
    },
    {
      "epoch": 1.679582580543866,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0857064502832207e-05,
      "loss": 1.056376838684082,
      "num_input_tokens_seen": 13499400384,
      "step": 47470,
      "train_runtime": 462381.2319,
      "train_tokens_per_second": 29195.39
    },
    {
      "epoch": 1.6799364008075948,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0855250103508805e-05,
      "loss": 1.0333965301513672,
      "num_input_tokens_seen": 13502198976,
      "step": 47480,
      "train_runtime": 462474.8422,
      "train_tokens_per_second": 29195.532
    },
    {
      "epoch": 1.6802902210713235,
      "grad_norm": 1.5859375,
      "learning_rate": 2.085343617761812e-05,
      "loss": 1.0535968780517577,
      "num_input_tokens_seen": 13505095424,
      "step": 47490,
      "train_runtime": 462576.4348,
      "train_tokens_per_second": 29195.381
    },
    {
      "epoch": 1.6806440413350523,
      "grad_norm": 1.5703125,
      "learning_rate": 2.08516227249543e-05,
      "loss": 1.0447009086608887,
      "num_input_tokens_seen": 13507979072,
      "step": 47500,
      "train_runtime": 462675.6046,
      "train_tokens_per_second": 29195.356
    },
    {
      "epoch": 1.680997861598781,
      "grad_norm": 1.5859375,
      "learning_rate": 2.084980974531162e-05,
      "loss": 1.0551579475402832,
      "num_input_tokens_seen": 13510811264,
      "step": 47510,
      "train_runtime": 462774.2356,
      "train_tokens_per_second": 29195.254
    },
    {
      "epoch": 1.6813516818625098,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0847997238484477e-05,
      "loss": 1.04492244720459,
      "num_input_tokens_seen": 13513655808,
      "step": 47520,
      "train_runtime": 462867.9451,
      "train_tokens_per_second": 29195.489
    },
    {
      "epoch": 1.6817055021262386,
      "grad_norm": 1.5546875,
      "learning_rate": 2.084618520426739e-05,
      "loss": 1.0321231842041017,
      "num_input_tokens_seen": 13516457088,
      "step": 47530,
      "train_runtime": 462963.576,
      "train_tokens_per_second": 29195.509
    },
    {
      "epoch": 1.6820593223899674,
      "grad_norm": 1.6328125,
      "learning_rate": 2.0844373642455005e-05,
      "loss": 1.0554420471191406,
      "num_input_tokens_seen": 13519269760,
      "step": 47540,
      "train_runtime": 463061.5658,
      "train_tokens_per_second": 29195.405
    },
    {
      "epoch": 1.6824131426536963,
      "grad_norm": 1.515625,
      "learning_rate": 2.0842562552842103e-05,
      "loss": 1.0388916015625,
      "num_input_tokens_seen": 13522149376,
      "step": 47550,
      "train_runtime": 463158.9585,
      "train_tokens_per_second": 29195.483
    },
    {
      "epoch": 1.682766962917425,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0840751935223573e-05,
      "loss": 1.0513490676879882,
      "num_input_tokens_seen": 13525025600,
      "step": 47560,
      "train_runtime": 463256.1095,
      "train_tokens_per_second": 29195.569
    },
    {
      "epoch": 1.6831207831811539,
      "grad_norm": 1.53125,
      "learning_rate": 2.0838941789394442e-05,
      "loss": 1.0462310791015625,
      "num_input_tokens_seen": 13527870528,
      "step": 47570,
      "train_runtime": 463352.1806,
      "train_tokens_per_second": 29195.655
    },
    {
      "epoch": 1.6834746034448824,
      "grad_norm": 1.5234375,
      "learning_rate": 2.083713211514986e-05,
      "loss": 1.0376806259155273,
      "num_input_tokens_seen": 13530731712,
      "step": 47580,
      "train_runtime": 463452.7968,
      "train_tokens_per_second": 29195.49
    },
    {
      "epoch": 1.6838284237086114,
      "grad_norm": 1.5546875,
      "learning_rate": 2.083532291228509e-05,
      "loss": 1.0448654174804688,
      "num_input_tokens_seen": 13533541440,
      "step": 47590,
      "train_runtime": 463547.5185,
      "train_tokens_per_second": 29195.586
    },
    {
      "epoch": 1.68418224397234,
      "grad_norm": 1.53125,
      "learning_rate": 2.0833514180595527e-05,
      "loss": 1.0375941276550293,
      "num_input_tokens_seen": 13536369920,
      "step": 47600,
      "train_runtime": 463645.8791,
      "train_tokens_per_second": 29195.493
    },
    {
      "epoch": 1.684536064236069,
      "grad_norm": 1.515625,
      "learning_rate": 2.08317059198767e-05,
      "loss": 1.0529433250427247,
      "num_input_tokens_seen": 13539229248,
      "step": 47610,
      "train_runtime": 463743.4026,
      "train_tokens_per_second": 29195.519
    },
    {
      "epoch": 1.6848898844997977,
      "grad_norm": 1.53125,
      "learning_rate": 2.0829898129924246e-05,
      "loss": 1.0403919219970703,
      "num_input_tokens_seen": 13542116416,
      "step": 47620,
      "train_runtime": 463843.9651,
      "train_tokens_per_second": 29195.414
    },
    {
      "epoch": 1.6852437047635265,
      "grad_norm": 1.6484375,
      "learning_rate": 2.0828090810533936e-05,
      "loss": 1.0451854705810546,
      "num_input_tokens_seen": 13544968064,
      "step": 47630,
      "train_runtime": 463942.5191,
      "train_tokens_per_second": 29195.358
    },
    {
      "epoch": 1.6855975250272552,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0826283961501665e-05,
      "loss": 1.0454134941101074,
      "num_input_tokens_seen": 13547780288,
      "step": 47640,
      "train_runtime": 464038.7261,
      "train_tokens_per_second": 29195.366
    },
    {
      "epoch": 1.685951345290984,
      "grad_norm": 1.546875,
      "learning_rate": 2.0824477582623445e-05,
      "loss": 1.0439224243164062,
      "num_input_tokens_seen": 13550642496,
      "step": 47650,
      "train_runtime": 464136.1614,
      "train_tokens_per_second": 29195.403
    },
    {
      "epoch": 1.6863051655547128,
      "grad_norm": 1.5625,
      "learning_rate": 2.0822671673695414e-05,
      "loss": 1.054850196838379,
      "num_input_tokens_seen": 13553570048,
      "step": 47660,
      "train_runtime": 464236.5271,
      "train_tokens_per_second": 29195.398
    },
    {
      "epoch": 1.6866589858184415,
      "grad_norm": 1.5,
      "learning_rate": 2.0820866234513844e-05,
      "loss": 1.0565918922424316,
      "num_input_tokens_seen": 13556407616,
      "step": 47670,
      "train_runtime": 464335.1491,
      "train_tokens_per_second": 29195.308
    },
    {
      "epoch": 1.6870128060821703,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0819061264875116e-05,
      "loss": 1.0543604850769044,
      "num_input_tokens_seen": 13559210688,
      "step": 47680,
      "train_runtime": 464427.835,
      "train_tokens_per_second": 29195.517
    },
    {
      "epoch": 1.687366626345899,
      "grad_norm": 1.4921875,
      "learning_rate": 2.0817256764575738e-05,
      "loss": 1.0420949935913086,
      "num_input_tokens_seen": 13561989696,
      "step": 47690,
      "train_runtime": 464523.2772,
      "train_tokens_per_second": 29195.501
    },
    {
      "epoch": 1.687720446609628,
      "grad_norm": 1.5,
      "learning_rate": 2.0815452733412354e-05,
      "loss": 1.0442051887512207,
      "num_input_tokens_seen": 13564833792,
      "step": 47700,
      "train_runtime": 464618.5704,
      "train_tokens_per_second": 29195.634
    },
    {
      "epoch": 1.6880742668733566,
      "grad_norm": 1.5625,
      "learning_rate": 2.081364917118171e-05,
      "loss": 1.0418291091918945,
      "num_input_tokens_seen": 13567649856,
      "step": 47710,
      "train_runtime": 464712.9509,
      "train_tokens_per_second": 29195.764
    },
    {
      "epoch": 1.6884280871370856,
      "grad_norm": 1.5390625,
      "learning_rate": 2.08118460776807e-05,
      "loss": 1.0447476387023926,
      "num_input_tokens_seen": 13570492544,
      "step": 47720,
      "train_runtime": 464808.5861,
      "train_tokens_per_second": 29195.873
    },
    {
      "epoch": 1.6887819074008141,
      "grad_norm": 1.546875,
      "learning_rate": 2.0810043452706317e-05,
      "loss": 1.0467083930969239,
      "num_input_tokens_seen": 13573312896,
      "step": 47730,
      "train_runtime": 464903.8846,
      "train_tokens_per_second": 29195.955
    },
    {
      "epoch": 1.6891357276645431,
      "grad_norm": 1.53125,
      "learning_rate": 2.08082412960557e-05,
      "loss": 1.0457755088806153,
      "num_input_tokens_seen": 13576127424,
      "step": 47740,
      "train_runtime": 464998.157,
      "train_tokens_per_second": 29196.089
    },
    {
      "epoch": 1.6894895479282717,
      "grad_norm": 1.6171875,
      "learning_rate": 2.0806439607526085e-05,
      "loss": 1.0554765701293944,
      "num_input_tokens_seen": 13578962368,
      "step": 47750,
      "train_runtime": 465092.9708,
      "train_tokens_per_second": 29196.232
    },
    {
      "epoch": 1.6898433681920006,
      "grad_norm": 1.6328125,
      "learning_rate": 2.0804638386914853e-05,
      "loss": 1.0475746154785157,
      "num_input_tokens_seen": 13581805696,
      "step": 47760,
      "train_runtime": 465190.6014,
      "train_tokens_per_second": 29196.217
    },
    {
      "epoch": 1.6901971884557292,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0802837634019497e-05,
      "loss": 1.0468786239624024,
      "num_input_tokens_seen": 13584596864,
      "step": 47770,
      "train_runtime": 465285.636,
      "train_tokens_per_second": 29196.252
    },
    {
      "epoch": 1.6905510087194582,
      "grad_norm": 1.5546875,
      "learning_rate": 2.080103734863764e-05,
      "loss": 1.0477848052978516,
      "num_input_tokens_seen": 13587456064,
      "step": 47780,
      "train_runtime": 465384.5809,
      "train_tokens_per_second": 29196.189
    },
    {
      "epoch": 1.690904828983187,
      "grad_norm": 1.546875,
      "learning_rate": 2.0799237530567022e-05,
      "loss": 1.0498855590820313,
      "num_input_tokens_seen": 13590344512,
      "step": 47790,
      "train_runtime": 465481.9338,
      "train_tokens_per_second": 29196.288
    },
    {
      "epoch": 1.6912586492469157,
      "grad_norm": 1.5078125,
      "learning_rate": 2.079743817960551e-05,
      "loss": 1.0415288925170898,
      "num_input_tokens_seen": 13593122368,
      "step": 47800,
      "train_runtime": 465578.3119,
      "train_tokens_per_second": 29196.21
    },
    {
      "epoch": 1.6916124695106445,
      "grad_norm": 1.5,
      "learning_rate": 2.0795639295551074e-05,
      "loss": 1.0545483589172364,
      "num_input_tokens_seen": 13596015680,
      "step": 47810,
      "train_runtime": 465677.1929,
      "train_tokens_per_second": 29196.224
    },
    {
      "epoch": 1.6919662897743732,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0793840878201835e-05,
      "loss": 1.0294765472412108,
      "num_input_tokens_seen": 13598832384,
      "step": 47820,
      "train_runtime": 465772.1076,
      "train_tokens_per_second": 29196.322
    },
    {
      "epoch": 1.692320110038102,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0792042927356023e-05,
      "loss": 1.0374161720275878,
      "num_input_tokens_seen": 13601646720,
      "step": 47830,
      "train_runtime": 465868.358,
      "train_tokens_per_second": 29196.331
    },
    {
      "epoch": 1.6926739303018308,
      "grad_norm": 1.53125,
      "learning_rate": 2.079024544281199e-05,
      "loss": 1.0482377052307128,
      "num_input_tokens_seen": 13604438848,
      "step": 47840,
      "train_runtime": 465963.5646,
      "train_tokens_per_second": 29196.358
    },
    {
      "epoch": 1.6930277505655595,
      "grad_norm": 1.65625,
      "learning_rate": 2.078844842436821e-05,
      "loss": 1.0437973022460938,
      "num_input_tokens_seen": 13607228928,
      "step": 47850,
      "train_runtime": 466057.9138,
      "train_tokens_per_second": 29196.434
    },
    {
      "epoch": 1.6933815708292883,
      "grad_norm": 1.625,
      "learning_rate": 2.0786651871823272e-05,
      "loss": 1.038986587524414,
      "num_input_tokens_seen": 13610089280,
      "step": 47860,
      "train_runtime": 466157.8318,
      "train_tokens_per_second": 29196.312
    },
    {
      "epoch": 1.6937353910930173,
      "grad_norm": 1.59375,
      "learning_rate": 2.0784855784975907e-05,
      "loss": 1.0401915550231933,
      "num_input_tokens_seen": 13612907328,
      "step": 47870,
      "train_runtime": 466252.4636,
      "train_tokens_per_second": 29196.43
    },
    {
      "epoch": 1.6940892113567458,
      "grad_norm": 1.546875,
      "learning_rate": 2.078306016362495e-05,
      "loss": 1.0373383522033692,
      "num_input_tokens_seen": 13615737856,
      "step": 47880,
      "train_runtime": 466349.3174,
      "train_tokens_per_second": 29196.436
    },
    {
      "epoch": 1.6944430316204748,
      "grad_norm": 1.59375,
      "learning_rate": 2.0781265007569355e-05,
      "loss": 1.0413772583007812,
      "num_input_tokens_seen": 13618588352,
      "step": 47890,
      "train_runtime": 466446.225,
      "train_tokens_per_second": 29196.481
    },
    {
      "epoch": 1.6947968518842034,
      "grad_norm": 1.5625,
      "learning_rate": 2.0779470316608218e-05,
      "loss": 1.0577576637268067,
      "num_input_tokens_seen": 13621466304,
      "step": 47900,
      "train_runtime": 466544.1411,
      "train_tokens_per_second": 29196.522
    },
    {
      "epoch": 1.6951506721479324,
      "grad_norm": 1.53125,
      "learning_rate": 2.0777676090540738e-05,
      "loss": 1.0431707382202149,
      "num_input_tokens_seen": 13624274496,
      "step": 47910,
      "train_runtime": 466638.1767,
      "train_tokens_per_second": 29196.656
    },
    {
      "epoch": 1.695504492411661,
      "grad_norm": 1.6171875,
      "learning_rate": 2.0775882329166235e-05,
      "loss": 1.059424877166748,
      "num_input_tokens_seen": 13627144192,
      "step": 47920,
      "train_runtime": 466733.9718,
      "train_tokens_per_second": 29196.812
    },
    {
      "epoch": 1.69585831267539,
      "grad_norm": 1.6484375,
      "learning_rate": 2.0774089032284164e-05,
      "loss": 1.0579084396362304,
      "num_input_tokens_seen": 13629971648,
      "step": 47930,
      "train_runtime": 466827.3692,
      "train_tokens_per_second": 29197.028
    },
    {
      "epoch": 1.6962121329391184,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0772296199694092e-05,
      "loss": 1.0509796142578125,
      "num_input_tokens_seen": 13632793792,
      "step": 47940,
      "train_runtime": 466923.5463,
      "train_tokens_per_second": 29197.058
    },
    {
      "epoch": 1.6965659532028474,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0770503831195703e-05,
      "loss": 1.039320182800293,
      "num_input_tokens_seen": 13635600512,
      "step": 47950,
      "train_runtime": 467019.4387,
      "train_tokens_per_second": 29197.073
    },
    {
      "epoch": 1.6969197734665762,
      "grad_norm": 1.515625,
      "learning_rate": 2.0768711926588813e-05,
      "loss": 1.071627140045166,
      "num_input_tokens_seen": 13638457728,
      "step": 47960,
      "train_runtime": 467120.5229,
      "train_tokens_per_second": 29196.871
    },
    {
      "epoch": 1.697273593730305,
      "grad_norm": 1.5078125,
      "learning_rate": 2.076692048567335e-05,
      "loss": 1.0387510299682616,
      "num_input_tokens_seen": 13641345664,
      "step": 47970,
      "train_runtime": 467217.7414,
      "train_tokens_per_second": 29196.977
    },
    {
      "epoch": 1.6976274139940337,
      "grad_norm": 1.546875,
      "learning_rate": 2.076512950824937e-05,
      "loss": 1.0363213539123535,
      "num_input_tokens_seen": 13644170176,
      "step": 47980,
      "train_runtime": 467312.4609,
      "train_tokens_per_second": 29197.103
    },
    {
      "epoch": 1.6979812342577625,
      "grad_norm": 1.59375,
      "learning_rate": 2.0763338994117043e-05,
      "loss": 1.0325971603393556,
      "num_input_tokens_seen": 13647034688,
      "step": 47990,
      "train_runtime": 467408.4893,
      "train_tokens_per_second": 29197.233
    },
    {
      "epoch": 1.6983350545214912,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0761548943076657e-05,
      "loss": 1.0379398345947266,
      "num_input_tokens_seen": 13649907456,
      "step": 48000,
      "train_runtime": 467509.9631,
      "train_tokens_per_second": 29197.041
    },
    {
      "epoch": 1.69868887478522,
      "grad_norm": 1.53125,
      "learning_rate": 2.0759759354928637e-05,
      "loss": 1.0252336502075194,
      "num_input_tokens_seen": 13652747200,
      "step": 48010,
      "train_runtime": 467608.1638,
      "train_tokens_per_second": 29196.982
    },
    {
      "epoch": 1.6990426950489488,
      "grad_norm": 1.53125,
      "learning_rate": 2.0757970229473512e-05,
      "loss": 1.0471942901611329,
      "num_input_tokens_seen": 13655570176,
      "step": 48020,
      "train_runtime": 467705.199,
      "train_tokens_per_second": 29196.96
    },
    {
      "epoch": 1.6993965153126775,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0756181566511933e-05,
      "loss": 1.0526710510253907,
      "num_input_tokens_seen": 13658403008,
      "step": 48030,
      "train_runtime": 467801.0439,
      "train_tokens_per_second": 29197.034
    },
    {
      "epoch": 1.6997503355764065,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0754393365844677e-05,
      "loss": 1.0546140670776367,
      "num_input_tokens_seen": 13661246656,
      "step": 48040,
      "train_runtime": 467899.1564,
      "train_tokens_per_second": 29196.989
    },
    {
      "epoch": 1.700104155840135,
      "grad_norm": 1.6015625,
      "learning_rate": 2.075260562727264e-05,
      "loss": 1.0283187866210937,
      "num_input_tokens_seen": 13664068160,
      "step": 48050,
      "train_runtime": 467994.4987,
      "train_tokens_per_second": 29197.07
    },
    {
      "epoch": 1.700457976103864,
      "grad_norm": 1.5625,
      "learning_rate": 2.0750818350596838e-05,
      "loss": 1.0443769454956056,
      "num_input_tokens_seen": 13666918592,
      "step": 48060,
      "train_runtime": 468094.2825,
      "train_tokens_per_second": 29196.936
    },
    {
      "epoch": 1.7008117963675926,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0749031535618403e-05,
      "loss": 1.039093017578125,
      "num_input_tokens_seen": 13669768384,
      "step": 48070,
      "train_runtime": 468188.6178,
      "train_tokens_per_second": 29197.139
    },
    {
      "epoch": 1.7011656166313216,
      "grad_norm": 1.5546875,
      "learning_rate": 2.074724518213859e-05,
      "loss": 1.0362802505493165,
      "num_input_tokens_seen": 13672655936,
      "step": 48080,
      "train_runtime": 468290.0713,
      "train_tokens_per_second": 29196.98
    },
    {
      "epoch": 1.7015194368950501,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0745459289958773e-05,
      "loss": 1.0392768859863282,
      "num_input_tokens_seen": 13675506176,
      "step": 48090,
      "train_runtime": 468388.0911,
      "train_tokens_per_second": 29196.955
    },
    {
      "epoch": 1.7018732571587791,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0743673858880447e-05,
      "loss": 1.047902488708496,
      "num_input_tokens_seen": 13678392192,
      "step": 48100,
      "train_runtime": 468488.9157,
      "train_tokens_per_second": 29196.832
    },
    {
      "epoch": 1.7022270774225077,
      "grad_norm": 1.625,
      "learning_rate": 2.074188888870523e-05,
      "loss": 1.040693759918213,
      "num_input_tokens_seen": 13681223040,
      "step": 48110,
      "train_runtime": 468586.7138,
      "train_tokens_per_second": 29196.78
    },
    {
      "epoch": 1.7025808976862367,
      "grad_norm": 1.546875,
      "learning_rate": 2.0740104379234847e-05,
      "loss": 1.0504280090332032,
      "num_input_tokens_seen": 13684064896,
      "step": 48120,
      "train_runtime": 468683.9512,
      "train_tokens_per_second": 29196.786
    },
    {
      "epoch": 1.7029347179499654,
      "grad_norm": 1.546875,
      "learning_rate": 2.073832033027116e-05,
      "loss": 1.04351806640625,
      "num_input_tokens_seen": 13686884928,
      "step": 48130,
      "train_runtime": 468778.3339,
      "train_tokens_per_second": 29196.923
    },
    {
      "epoch": 1.7032885382136942,
      "grad_norm": 1.5,
      "learning_rate": 2.0736536741616128e-05,
      "loss": 1.0345563888549805,
      "num_input_tokens_seen": 13689754880,
      "step": 48140,
      "train_runtime": 468874.4155,
      "train_tokens_per_second": 29197.061
    },
    {
      "epoch": 1.703642358477423,
      "grad_norm": 1.5703125,
      "learning_rate": 2.073475361307185e-05,
      "loss": 1.0466058731079102,
      "num_input_tokens_seen": 13692595840,
      "step": 48150,
      "train_runtime": 468970.2353,
      "train_tokens_per_second": 29197.153
    },
    {
      "epoch": 1.7039961787411517,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0732970944440534e-05,
      "loss": 1.038508415222168,
      "num_input_tokens_seen": 13695499712,
      "step": 48160,
      "train_runtime": 469069.2391,
      "train_tokens_per_second": 29197.182
    },
    {
      "epoch": 1.7043499990048805,
      "grad_norm": 1.546875,
      "learning_rate": 2.073118873552452e-05,
      "loss": 1.032989501953125,
      "num_input_tokens_seen": 13698357888,
      "step": 48170,
      "train_runtime": 469168.1216,
      "train_tokens_per_second": 29197.12
    },
    {
      "epoch": 1.7047038192686093,
      "grad_norm": 1.546875,
      "learning_rate": 2.0729406986126238e-05,
      "loss": 1.0547128677368165,
      "num_input_tokens_seen": 13701224064,
      "step": 48180,
      "train_runtime": 469267.1181,
      "train_tokens_per_second": 29197.068
    },
    {
      "epoch": 1.705057639532338,
      "grad_norm": 1.546875,
      "learning_rate": 2.0727625696048264e-05,
      "loss": 1.0474655151367187,
      "num_input_tokens_seen": 13704029888,
      "step": 48190,
      "train_runtime": 469363.4881,
      "train_tokens_per_second": 29197.051
    },
    {
      "epoch": 1.7054114597960668,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0725844865093287e-05,
      "loss": 1.0476907730102538,
      "num_input_tokens_seen": 13706867200,
      "step": 48200,
      "train_runtime": 469458.5914,
      "train_tokens_per_second": 29197.18
    },
    {
      "epoch": 1.7057652800597958,
      "grad_norm": 1.5390625,
      "learning_rate": 2.07240644930641e-05,
      "loss": 1.040272045135498,
      "num_input_tokens_seen": 13709739264,
      "step": 48210,
      "train_runtime": 469557.7052,
      "train_tokens_per_second": 29197.134
    },
    {
      "epoch": 1.7061191003235243,
      "grad_norm": 1.6171875,
      "learning_rate": 2.0722284579763633e-05,
      "loss": 1.0462236404418945,
      "num_input_tokens_seen": 13712579456,
      "step": 48220,
      "train_runtime": 469655.1765,
      "train_tokens_per_second": 29197.122
    },
    {
      "epoch": 1.7064729205872533,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0720505124994934e-05,
      "loss": 1.0380185127258301,
      "num_input_tokens_seen": 13715411648,
      "step": 48230,
      "train_runtime": 469751.9403,
      "train_tokens_per_second": 29197.137
    },
    {
      "epoch": 1.7068267408509818,
      "grad_norm": 1.5,
      "learning_rate": 2.0718726128561156e-05,
      "loss": 1.0448797225952149,
      "num_input_tokens_seen": 13718270848,
      "step": 48240,
      "train_runtime": 469848.8401,
      "train_tokens_per_second": 29197.201
    },
    {
      "epoch": 1.7071805611147108,
      "grad_norm": 1.484375,
      "learning_rate": 2.0716947590265572e-05,
      "loss": 1.0532607078552245,
      "num_input_tokens_seen": 13721091776,
      "step": 48250,
      "train_runtime": 469944.8196,
      "train_tokens_per_second": 29197.24
    },
    {
      "epoch": 1.7075343813784394,
      "grad_norm": 1.4921875,
      "learning_rate": 2.0715169509911588e-05,
      "loss": 1.0432819366455077,
      "num_input_tokens_seen": 13723950912,
      "step": 48260,
      "train_runtime": 470042.6813,
      "train_tokens_per_second": 29197.244
    },
    {
      "epoch": 1.7078882016421684,
      "grad_norm": 1.4765625,
      "learning_rate": 2.0713391887302706e-05,
      "loss": 1.0455898284912108,
      "num_input_tokens_seen": 13726796736,
      "step": 48270,
      "train_runtime": 470141.4976,
      "train_tokens_per_second": 29197.16
    },
    {
      "epoch": 1.708242021905897,
      "grad_norm": 1.578125,
      "learning_rate": 2.0711614722242566e-05,
      "loss": 1.054796314239502,
      "num_input_tokens_seen": 13729610496,
      "step": 48280,
      "train_runtime": 470238.4266,
      "train_tokens_per_second": 29197.126
    },
    {
      "epoch": 1.708595842169626,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0709838014534923e-05,
      "loss": 1.040621566772461,
      "num_input_tokens_seen": 13732433536,
      "step": 48290,
      "train_runtime": 470335.3354,
      "train_tokens_per_second": 29197.112
    },
    {
      "epoch": 1.7089496624333547,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0708061763983633e-05,
      "loss": 1.0442960739135743,
      "num_input_tokens_seen": 13735299264,
      "step": 48300,
      "train_runtime": 470433.6907,
      "train_tokens_per_second": 29197.099
    },
    {
      "epoch": 1.7093034826970834,
      "grad_norm": 1.609375,
      "learning_rate": 2.070628597039269e-05,
      "loss": 1.0369464874267578,
      "num_input_tokens_seen": 13738148736,
      "step": 48310,
      "train_runtime": 470527.0862,
      "train_tokens_per_second": 29197.36
    },
    {
      "epoch": 1.7096573029608122,
      "grad_norm": 1.5859375,
      "learning_rate": 2.07045106335662e-05,
      "loss": 1.0347278594970704,
      "num_input_tokens_seen": 13741024576,
      "step": 48320,
      "train_runtime": 470625.9429,
      "train_tokens_per_second": 29197.338
    },
    {
      "epoch": 1.710011123224541,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0702735753308372e-05,
      "loss": 1.0356561660766601,
      "num_input_tokens_seen": 13743871680,
      "step": 48330,
      "train_runtime": 470721.5453,
      "train_tokens_per_second": 29197.456
    },
    {
      "epoch": 1.7103649434882697,
      "grad_norm": 1.515625,
      "learning_rate": 2.0700961329423558e-05,
      "loss": 1.04902925491333,
      "num_input_tokens_seen": 13746730624,
      "step": 48340,
      "train_runtime": 470820.0719,
      "train_tokens_per_second": 29197.418
    },
    {
      "epoch": 1.7107187637519985,
      "grad_norm": 1.578125,
      "learning_rate": 2.06991873617162e-05,
      "loss": 1.0557451248168945,
      "num_input_tokens_seen": 13749591872,
      "step": 48350,
      "train_runtime": 470919.8034,
      "train_tokens_per_second": 29197.311
    },
    {
      "epoch": 1.7110725840157273,
      "grad_norm": 1.5625,
      "learning_rate": 2.0697413849990883e-05,
      "loss": 1.0538095474243163,
      "num_input_tokens_seen": 13752402496,
      "step": 48360,
      "train_runtime": 471015.599,
      "train_tokens_per_second": 29197.34
    },
    {
      "epoch": 1.711426404279456,
      "grad_norm": 1.59375,
      "learning_rate": 2.0695640794052288e-05,
      "loss": 1.0530920028686523,
      "num_input_tokens_seen": 13755270592,
      "step": 48370,
      "train_runtime": 471117.4845,
      "train_tokens_per_second": 29197.113
    },
    {
      "epoch": 1.711780224543185,
      "grad_norm": 1.6328125,
      "learning_rate": 2.0693868193705228e-05,
      "loss": 1.0418710708618164,
      "num_input_tokens_seen": 13758136064,
      "step": 48380,
      "train_runtime": 471218.2489,
      "train_tokens_per_second": 29196.951
    },
    {
      "epoch": 1.7121340448069136,
      "grad_norm": 1.5234375,
      "learning_rate": 2.069209604875463e-05,
      "loss": 1.0257854461669922,
      "num_input_tokens_seen": 13761048000,
      "step": 48390,
      "train_runtime": 471319.6827,
      "train_tokens_per_second": 29196.846
    },
    {
      "epoch": 1.7124878650706425,
      "grad_norm": 1.5625,
      "learning_rate": 2.069032435900553e-05,
      "loss": 1.0533125877380372,
      "num_input_tokens_seen": 13763955520,
      "step": 48400,
      "train_runtime": 471423.1266,
      "train_tokens_per_second": 29196.606
    },
    {
      "epoch": 1.712841685334371,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0688553124263086e-05,
      "loss": 1.0532243728637696,
      "num_input_tokens_seen": 13766769280,
      "step": 48410,
      "train_runtime": 471519.0769,
      "train_tokens_per_second": 29196.633
    },
    {
      "epoch": 1.7131955055981,
      "grad_norm": 1.546875,
      "learning_rate": 2.068678234433257e-05,
      "loss": 1.035375213623047,
      "num_input_tokens_seen": 13769620032,
      "step": 48420,
      "train_runtime": 471616.5294,
      "train_tokens_per_second": 29196.644
    },
    {
      "epoch": 1.7135493258618286,
      "grad_norm": 1.625,
      "learning_rate": 2.0685012019019385e-05,
      "loss": 1.0479228019714355,
      "num_input_tokens_seen": 13772479168,
      "step": 48430,
      "train_runtime": 471713.0964,
      "train_tokens_per_second": 29196.728
    },
    {
      "epoch": 1.7139031461255576,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0683242148129027e-05,
      "loss": 1.0387092590332032,
      "num_input_tokens_seen": 13775317824,
      "step": 48440,
      "train_runtime": 471808.4508,
      "train_tokens_per_second": 29196.844
    },
    {
      "epoch": 1.7142569663892864,
      "grad_norm": 1.5390625,
      "learning_rate": 2.068147273146712e-05,
      "loss": 1.0448718070983887,
      "num_input_tokens_seen": 13778182400,
      "step": 48450,
      "train_runtime": 471906.4376,
      "train_tokens_per_second": 29196.852
    },
    {
      "epoch": 1.7146107866530151,
      "grad_norm": 1.546875,
      "learning_rate": 2.067970376883942e-05,
      "loss": 1.0333721160888671,
      "num_input_tokens_seen": 13781024832,
      "step": 48460,
      "train_runtime": 472004.4178,
      "train_tokens_per_second": 29196.813
    },
    {
      "epoch": 1.714964606916744,
      "grad_norm": 1.578125,
      "learning_rate": 2.0677935260051766e-05,
      "loss": 1.0551851272583008,
      "num_input_tokens_seen": 13783832896,
      "step": 48470,
      "train_runtime": 472098.437,
      "train_tokens_per_second": 29196.947
    },
    {
      "epoch": 1.7153184271804727,
      "grad_norm": 1.546875,
      "learning_rate": 2.0676167204910145e-05,
      "loss": 1.0528467178344727,
      "num_input_tokens_seen": 13786695424,
      "step": 48480,
      "train_runtime": 472194.4309,
      "train_tokens_per_second": 29197.073
    },
    {
      "epoch": 1.7156722474442014,
      "grad_norm": 1.609375,
      "learning_rate": 2.067439960322063e-05,
      "loss": 1.0395853996276856,
      "num_input_tokens_seen": 13789540672,
      "step": 48490,
      "train_runtime": 472292.3232,
      "train_tokens_per_second": 29197.046
    },
    {
      "epoch": 1.7160260677079302,
      "grad_norm": 1.59375,
      "learning_rate": 2.067263245478945e-05,
      "loss": 1.050419235229492,
      "num_input_tokens_seen": 13792359680,
      "step": 48500,
      "train_runtime": 472389.6654,
      "train_tokens_per_second": 29196.997
    },
    {
      "epoch": 1.716379887971659,
      "grad_norm": 1.5546875,
      "learning_rate": 2.06708657594229e-05,
      "loss": 1.0478198051452636,
      "num_input_tokens_seen": 13795189312,
      "step": 48510,
      "train_runtime": 472485.0945,
      "train_tokens_per_second": 29197.089
    },
    {
      "epoch": 1.7167337082353877,
      "grad_norm": 1.640625,
      "learning_rate": 2.066909951692744e-05,
      "loss": 1.050819206237793,
      "num_input_tokens_seen": 13798056320,
      "step": 48520,
      "train_runtime": 472585.2177,
      "train_tokens_per_second": 29196.97
    },
    {
      "epoch": 1.7170875284991165,
      "grad_norm": 1.59375,
      "learning_rate": 2.0667333727109607e-05,
      "loss": 1.0315229415893554,
      "num_input_tokens_seen": 13800873792,
      "step": 48530,
      "train_runtime": 472680.8053,
      "train_tokens_per_second": 29197.026
    },
    {
      "epoch": 1.7174413487628453,
      "grad_norm": 1.5703125,
      "learning_rate": 2.066556838977608e-05,
      "loss": 1.0307050704956056,
      "num_input_tokens_seen": 13803753728,
      "step": 48540,
      "train_runtime": 472781.4947,
      "train_tokens_per_second": 29196.899
    },
    {
      "epoch": 1.7177951690265743,
      "grad_norm": 1.625,
      "learning_rate": 2.0663803504733643e-05,
      "loss": 1.0403037071228027,
      "num_input_tokens_seen": 13806596224,
      "step": 48550,
      "train_runtime": 472877.2343,
      "train_tokens_per_second": 29196.999
    },
    {
      "epoch": 1.7181489892903028,
      "grad_norm": 1.53125,
      "learning_rate": 2.0662039071789186e-05,
      "loss": 1.0480350494384765,
      "num_input_tokens_seen": 13809494848,
      "step": 48560,
      "train_runtime": 472978.7893,
      "train_tokens_per_second": 29196.859
    },
    {
      "epoch": 1.7185028095540318,
      "grad_norm": 1.5859375,
      "learning_rate": 2.066027509074973e-05,
      "loss": 1.0463435173034668,
      "num_input_tokens_seen": 13812316224,
      "step": 48570,
      "train_runtime": 473072.4371,
      "train_tokens_per_second": 29197.043
    },
    {
      "epoch": 1.7188566298177603,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0658511561422408e-05,
      "loss": 1.0436429977416992,
      "num_input_tokens_seen": 13815134080,
      "step": 48580,
      "train_runtime": 473168.8854,
      "train_tokens_per_second": 29197.047
    },
    {
      "epoch": 1.7192104500814893,
      "grad_norm": 1.578125,
      "learning_rate": 2.0656748483614464e-05,
      "loss": 1.041421890258789,
      "num_input_tokens_seen": 13818018304,
      "step": 48590,
      "train_runtime": 473267.7718,
      "train_tokens_per_second": 29197.041
    },
    {
      "epoch": 1.7195642703452179,
      "grad_norm": 1.546875,
      "learning_rate": 2.0654985857133256e-05,
      "loss": 1.051570224761963,
      "num_input_tokens_seen": 13820798656,
      "step": 48600,
      "train_runtime": 473361.4137,
      "train_tokens_per_second": 29197.138
    },
    {
      "epoch": 1.7199180906089468,
      "grad_norm": 1.625,
      "learning_rate": 2.065322368178626e-05,
      "loss": 1.0513435363769532,
      "num_input_tokens_seen": 13823666880,
      "step": 48610,
      "train_runtime": 473458.1954,
      "train_tokens_per_second": 29197.228
    },
    {
      "epoch": 1.7202719108726756,
      "grad_norm": 1.515625,
      "learning_rate": 2.0651461957381073e-05,
      "loss": 1.051394271850586,
      "num_input_tokens_seen": 13826486272,
      "step": 48620,
      "train_runtime": 473553.8688,
      "train_tokens_per_second": 29197.283
    },
    {
      "epoch": 1.7206257311364044,
      "grad_norm": 1.53125,
      "learning_rate": 2.064970068372539e-05,
      "loss": 1.0701923370361328,
      "num_input_tokens_seen": 13829337600,
      "step": 48630,
      "train_runtime": 473651.6269,
      "train_tokens_per_second": 29197.277
    },
    {
      "epoch": 1.7209795514001331,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0647939860627043e-05,
      "loss": 1.0580183029174806,
      "num_input_tokens_seen": 13832139200,
      "step": 48640,
      "train_runtime": 473747.1725,
      "train_tokens_per_second": 29197.302
    },
    {
      "epoch": 1.721333371663862,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0646179487893964e-05,
      "loss": 1.053616428375244,
      "num_input_tokens_seen": 13835023680,
      "step": 48650,
      "train_runtime": 473847.3854,
      "train_tokens_per_second": 29197.214
    },
    {
      "epoch": 1.7216871919275907,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0644419565334194e-05,
      "loss": 1.0409774780273438,
      "num_input_tokens_seen": 13837870400,
      "step": 48660,
      "train_runtime": 473946.4473,
      "train_tokens_per_second": 29197.118
    },
    {
      "epoch": 1.7220410121913194,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0642660092755907e-05,
      "loss": 1.0438819885253907,
      "num_input_tokens_seen": 13840713216,
      "step": 48670,
      "train_runtime": 474042.677,
      "train_tokens_per_second": 29197.188
    },
    {
      "epoch": 1.7223948324550482,
      "grad_norm": 1.5625,
      "learning_rate": 2.0640901069967375e-05,
      "loss": 1.042196273803711,
      "num_input_tokens_seen": 13843563264,
      "step": 48680,
      "train_runtime": 474138.3577,
      "train_tokens_per_second": 29197.307
    },
    {
      "epoch": 1.722748652718777,
      "grad_norm": 1.546875,
      "learning_rate": 2.0639142496777e-05,
      "loss": 1.0360612869262695,
      "num_input_tokens_seen": 13846371072,
      "step": 48690,
      "train_runtime": 474234.5726,
      "train_tokens_per_second": 29197.304
    },
    {
      "epoch": 1.723102472982506,
      "grad_norm": 1.6171875,
      "learning_rate": 2.0637384372993275e-05,
      "loss": 1.0482637405395507,
      "num_input_tokens_seen": 13849165696,
      "step": 48700,
      "train_runtime": 474327.5951,
      "train_tokens_per_second": 29197.47
    },
    {
      "epoch": 1.7234562932462345,
      "grad_norm": 1.515625,
      "learning_rate": 2.0635626698424836e-05,
      "loss": 1.036379051208496,
      "num_input_tokens_seen": 13851974848,
      "step": 48710,
      "train_runtime": 474423.1242,
      "train_tokens_per_second": 29197.512
    },
    {
      "epoch": 1.7238101135099635,
      "grad_norm": 1.59375,
      "learning_rate": 2.0633869472880413e-05,
      "loss": 1.0425637245178223,
      "num_input_tokens_seen": 13854800512,
      "step": 48720,
      "train_runtime": 474516.87,
      "train_tokens_per_second": 29197.699
    },
    {
      "epoch": 1.724163933773692,
      "grad_norm": 1.53125,
      "learning_rate": 2.0632112696168856e-05,
      "loss": 1.0267884254455566,
      "num_input_tokens_seen": 13857649536,
      "step": 48730,
      "train_runtime": 474613.8739,
      "train_tokens_per_second": 29197.734
    },
    {
      "epoch": 1.724517754037421,
      "grad_norm": 1.609375,
      "learning_rate": 2.0630356368099127e-05,
      "loss": 1.0543734550476074,
      "num_input_tokens_seen": 13860484224,
      "step": 48740,
      "train_runtime": 474708.1315,
      "train_tokens_per_second": 29197.908
    },
    {
      "epoch": 1.7248715743011496,
      "grad_norm": 1.53125,
      "learning_rate": 2.06286004884803e-05,
      "loss": 1.0459514617919923,
      "num_input_tokens_seen": 13863294144,
      "step": 48750,
      "train_runtime": 474802.2797,
      "train_tokens_per_second": 29198.036
    },
    {
      "epoch": 1.7252253945648786,
      "grad_norm": 1.5703125,
      "learning_rate": 2.062684505712157e-05,
      "loss": 1.0446882247924805,
      "num_input_tokens_seen": 13866109632,
      "step": 48760,
      "train_runtime": 474895.8284,
      "train_tokens_per_second": 29198.213
    },
    {
      "epoch": 1.725579214828607,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0625090073832243e-05,
      "loss": 1.0386396408081056,
      "num_input_tokens_seen": 13868989440,
      "step": 48770,
      "train_runtime": 474995.8105,
      "train_tokens_per_second": 29198.13
    },
    {
      "epoch": 1.725933035092336,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0623335538421733e-05,
      "loss": 1.0466388702392577,
      "num_input_tokens_seen": 13871900992,
      "step": 48780,
      "train_runtime": 475096.573,
      "train_tokens_per_second": 29198.066
    },
    {
      "epoch": 1.7262868553560649,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0621581450699574e-05,
      "loss": 1.0408769607543946,
      "num_input_tokens_seen": 13874715264,
      "step": 48790,
      "train_runtime": 475193.8519,
      "train_tokens_per_second": 29198.011
    },
    {
      "epoch": 1.7266406756197936,
      "grad_norm": 1.578125,
      "learning_rate": 2.0619827810475418e-05,
      "loss": 1.0410490036010742,
      "num_input_tokens_seen": 13877607872,
      "step": 48800,
      "train_runtime": 475292.2553,
      "train_tokens_per_second": 29198.052
    },
    {
      "epoch": 1.7269944958835224,
      "grad_norm": 1.609375,
      "learning_rate": 2.0618074617559007e-05,
      "loss": 1.0360124588012696,
      "num_input_tokens_seen": 13880471104,
      "step": 48810,
      "train_runtime": 475390.8144,
      "train_tokens_per_second": 29198.021
    },
    {
      "epoch": 1.7273483161472512,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0616321871760226e-05,
      "loss": 1.0540721893310547,
      "num_input_tokens_seen": 13883314176,
      "step": 48820,
      "train_runtime": 475486.6453,
      "train_tokens_per_second": 29198.116
    },
    {
      "epoch": 1.72770213641098,
      "grad_norm": 1.546875,
      "learning_rate": 2.0614569572889056e-05,
      "loss": 1.0346625328063965,
      "num_input_tokens_seen": 13886184000,
      "step": 48830,
      "train_runtime": 475584.162,
      "train_tokens_per_second": 29198.163
    },
    {
      "epoch": 1.7280559566747087,
      "grad_norm": 1.515625,
      "learning_rate": 2.061281772075559e-05,
      "loss": 1.0431413650512695,
      "num_input_tokens_seen": 13888998912,
      "step": 48840,
      "train_runtime": 475680.1868,
      "train_tokens_per_second": 29198.187
    },
    {
      "epoch": 1.7284097769384374,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0611066315170047e-05,
      "loss": 1.024100399017334,
      "num_input_tokens_seen": 13891844032,
      "step": 48850,
      "train_runtime": 475777.1041,
      "train_tokens_per_second": 29198.219
    },
    {
      "epoch": 1.7287635972021662,
      "grad_norm": 1.578125,
      "learning_rate": 2.0609315355942744e-05,
      "loss": 1.0514487266540526,
      "num_input_tokens_seen": 13894653056,
      "step": 48860,
      "train_runtime": 475871.2165,
      "train_tokens_per_second": 29198.347
    },
    {
      "epoch": 1.7291174174658952,
      "grad_norm": 1.546875,
      "learning_rate": 2.0607564842884116e-05,
      "loss": 1.0382627487182616,
      "num_input_tokens_seen": 13897499200,
      "step": 48870,
      "train_runtime": 475968.1835,
      "train_tokens_per_second": 29198.379
    },
    {
      "epoch": 1.7294712377296237,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0605814775804717e-05,
      "loss": 1.0404762268066405,
      "num_input_tokens_seen": 13900315904,
      "step": 48880,
      "train_runtime": 476065.678,
      "train_tokens_per_second": 29198.316
    },
    {
      "epoch": 1.7298250579933527,
      "grad_norm": 1.53125,
      "learning_rate": 2.0604065154515207e-05,
      "loss": 1.0355974197387696,
      "num_input_tokens_seen": 13903188096,
      "step": 48890,
      "train_runtime": 476169.0108,
      "train_tokens_per_second": 29198.011
    },
    {
      "epoch": 1.7301788782570813,
      "grad_norm": 1.484375,
      "learning_rate": 2.0602315978826363e-05,
      "loss": 1.0339536666870117,
      "num_input_tokens_seen": 13906031168,
      "step": 48900,
      "train_runtime": 476264.6223,
      "train_tokens_per_second": 29198.119
    },
    {
      "epoch": 1.7305326985208103,
      "grad_norm": 1.53125,
      "learning_rate": 2.0600567248549062e-05,
      "loss": 1.0224604606628418,
      "num_input_tokens_seen": 13908900416,
      "step": 48910,
      "train_runtime": 476363.9456,
      "train_tokens_per_second": 29198.054
    },
    {
      "epoch": 1.7308865187845388,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0598818963494312e-05,
      "loss": 1.041419506072998,
      "num_input_tokens_seen": 13911761984,
      "step": 48920,
      "train_runtime": 476461.9537,
      "train_tokens_per_second": 29198.054
    },
    {
      "epoch": 1.7312403390482678,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0597071123473223e-05,
      "loss": 1.0342070579528808,
      "num_input_tokens_seen": 13914586048,
      "step": 48930,
      "train_runtime": 476558.9906,
      "train_tokens_per_second": 29198.035
    },
    {
      "epoch": 1.7315941593119963,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0595323728297013e-05,
      "loss": 1.0391162872314452,
      "num_input_tokens_seen": 13917437120,
      "step": 48940,
      "train_runtime": 476657.0566,
      "train_tokens_per_second": 29198.009
    },
    {
      "epoch": 1.7319479795757253,
      "grad_norm": 1.59375,
      "learning_rate": 2.059357677777702e-05,
      "loss": 1.0502416610717773,
      "num_input_tokens_seen": 13920332864,
      "step": 48950,
      "train_runtime": 476758.4667,
      "train_tokens_per_second": 29197.872
    },
    {
      "epoch": 1.732301799839454,
      "grad_norm": 1.546875,
      "learning_rate": 2.0591830271724687e-05,
      "loss": 1.0514039039611816,
      "num_input_tokens_seen": 13923163072,
      "step": 48960,
      "train_runtime": 476853.3703,
      "train_tokens_per_second": 29197.997
    },
    {
      "epoch": 1.7326556201031829,
      "grad_norm": 1.4921875,
      "learning_rate": 2.0590084209951588e-05,
      "loss": 1.0414766311645507,
      "num_input_tokens_seen": 13926025600,
      "step": 48970,
      "train_runtime": 476949.5068,
      "train_tokens_per_second": 29198.113
    },
    {
      "epoch": 1.7330094403669116,
      "grad_norm": 1.5625,
      "learning_rate": 2.0588338592269375e-05,
      "loss": 1.048966121673584,
      "num_input_tokens_seen": 13928862016,
      "step": 48980,
      "train_runtime": 477046.0383,
      "train_tokens_per_second": 29198.15
    },
    {
      "epoch": 1.7333632606306404,
      "grad_norm": 1.5,
      "learning_rate": 2.0586593418489846e-05,
      "loss": 1.0327461242675782,
      "num_input_tokens_seen": 13931706304,
      "step": 48990,
      "train_runtime": 477142.4779,
      "train_tokens_per_second": 29198.21
    },
    {
      "epoch": 1.7337170808943692,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0584848688424894e-05,
      "loss": 1.0469164848327637,
      "num_input_tokens_seen": 13934492032,
      "step": 49000,
      "train_runtime": 477235.8661,
      "train_tokens_per_second": 29198.334
    },
    {
      "epoch": 1.734070901158098,
      "grad_norm": 1.515625,
      "learning_rate": 2.0583104401886512e-05,
      "loss": 1.0373330116271973,
      "num_input_tokens_seen": 13937352640,
      "step": 49010,
      "train_runtime": 477333.1974,
      "train_tokens_per_second": 29198.373
    },
    {
      "epoch": 1.7344247214218267,
      "grad_norm": 1.6171875,
      "learning_rate": 2.0581360558686828e-05,
      "loss": 1.0462541580200195,
      "num_input_tokens_seen": 13940169664,
      "step": 49020,
      "train_runtime": 477430.5141,
      "train_tokens_per_second": 29198.322
    },
    {
      "epoch": 1.7347785416855555,
      "grad_norm": 1.53125,
      "learning_rate": 2.057961715863807e-05,
      "loss": 1.0577322006225587,
      "num_input_tokens_seen": 13942974080,
      "step": 49030,
      "train_runtime": 477528.1572,
      "train_tokens_per_second": 29198.224
    },
    {
      "epoch": 1.7351323619492844,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0577874201552578e-05,
      "loss": 1.0335983276367187,
      "num_input_tokens_seen": 13945876096,
      "step": 49040,
      "train_runtime": 477628.4343,
      "train_tokens_per_second": 29198.17
    },
    {
      "epoch": 1.735486182213013,
      "grad_norm": 1.609375,
      "learning_rate": 2.0576131687242803e-05,
      "loss": 1.052004623413086,
      "num_input_tokens_seen": 13948727552,
      "step": 49050,
      "train_runtime": 477725.0005,
      "train_tokens_per_second": 29198.237
    },
    {
      "epoch": 1.735840002476742,
      "grad_norm": 1.53125,
      "learning_rate": 2.0574389615521303e-05,
      "loss": 1.0471911430358887,
      "num_input_tokens_seen": 13951510016,
      "step": 49060,
      "train_runtime": 477819.1865,
      "train_tokens_per_second": 29198.304
    },
    {
      "epoch": 1.7361938227404705,
      "grad_norm": 1.53125,
      "learning_rate": 2.0572647986200757e-05,
      "loss": 1.0375133514404298,
      "num_input_tokens_seen": 13954370496,
      "step": 49070,
      "train_runtime": 477917.0954,
      "train_tokens_per_second": 29198.308
    },
    {
      "epoch": 1.7365476430041995,
      "grad_norm": 1.546875,
      "learning_rate": 2.057090679909395e-05,
      "loss": 1.0506306648254395,
      "num_input_tokens_seen": 13957226688,
      "step": 49080,
      "train_runtime": 478014.419,
      "train_tokens_per_second": 29198.338
    },
    {
      "epoch": 1.736901463267928,
      "grad_norm": 1.578125,
      "learning_rate": 2.056916605401378e-05,
      "loss": 1.0379024505615235,
      "num_input_tokens_seen": 13960103168,
      "step": 49090,
      "train_runtime": 478110.9201,
      "train_tokens_per_second": 29198.461
    },
    {
      "epoch": 1.737255283531657,
      "grad_norm": 1.6328125,
      "learning_rate": 2.0567425750773247e-05,
      "loss": 1.0387723922729493,
      "num_input_tokens_seen": 13962869504,
      "step": 49100,
      "train_runtime": 478204.8248,
      "train_tokens_per_second": 29198.512
    },
    {
      "epoch": 1.7376091037953856,
      "grad_norm": 1.515625,
      "learning_rate": 2.056568588918547e-05,
      "loss": 1.0447329521179198,
      "num_input_tokens_seen": 13965735744,
      "step": 49110,
      "train_runtime": 478301.3469,
      "train_tokens_per_second": 29198.613
    },
    {
      "epoch": 1.7379629240591146,
      "grad_norm": 1.5625,
      "learning_rate": 2.056394646906368e-05,
      "loss": 1.0494123458862306,
      "num_input_tokens_seen": 13968618560,
      "step": 49120,
      "train_runtime": 478401.7977,
      "train_tokens_per_second": 29198.508
    },
    {
      "epoch": 1.7383167443228433,
      "grad_norm": 1.59375,
      "learning_rate": 2.0562207490221216e-05,
      "loss": 1.056183433532715,
      "num_input_tokens_seen": 13971409984,
      "step": 49130,
      "train_runtime": 478498.0476,
      "train_tokens_per_second": 29198.468
    },
    {
      "epoch": 1.738670564586572,
      "grad_norm": 1.53125,
      "learning_rate": 2.056046895247152e-05,
      "loss": 1.0337942123413086,
      "num_input_tokens_seen": 13974325824,
      "step": 49140,
      "train_runtime": 478600.5157,
      "train_tokens_per_second": 29198.309
    },
    {
      "epoch": 1.7390243848503009,
      "grad_norm": 1.546875,
      "learning_rate": 2.0558730855628155e-05,
      "loss": 1.0294963836669921,
      "num_input_tokens_seen": 13977164992,
      "step": 49150,
      "train_runtime": 478698.1206,
      "train_tokens_per_second": 29198.287
    },
    {
      "epoch": 1.7393782051140296,
      "grad_norm": 1.546875,
      "learning_rate": 2.055699319950479e-05,
      "loss": 1.0346454620361327,
      "num_input_tokens_seen": 13980006592,
      "step": 49160,
      "train_runtime": 478795.8667,
      "train_tokens_per_second": 29198.261
    },
    {
      "epoch": 1.7397320253777584,
      "grad_norm": 1.625,
      "learning_rate": 2.055525598391521e-05,
      "loss": 1.0476339340209961,
      "num_input_tokens_seen": 13982844032,
      "step": 49170,
      "train_runtime": 478890.139,
      "train_tokens_per_second": 29198.438
    },
    {
      "epoch": 1.7400858456414872,
      "grad_norm": 1.59375,
      "learning_rate": 2.0553519208673293e-05,
      "loss": 1.0363340377807617,
      "num_input_tokens_seen": 13985742656,
      "step": 49180,
      "train_runtime": 478990.0942,
      "train_tokens_per_second": 29198.396
    },
    {
      "epoch": 1.740439665905216,
      "grad_norm": 1.53125,
      "learning_rate": 2.0551782873593057e-05,
      "loss": 1.0457462310791015,
      "num_input_tokens_seen": 13988579712,
      "step": 49190,
      "train_runtime": 479086.5108,
      "train_tokens_per_second": 29198.442
    },
    {
      "epoch": 1.7407934861689447,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0550046978488592e-05,
      "loss": 1.0352367401123046,
      "num_input_tokens_seen": 13991383168,
      "step": 49200,
      "train_runtime": 479183.0376,
      "train_tokens_per_second": 29198.411
    },
    {
      "epoch": 1.7411473064326737,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0548311523174133e-05,
      "loss": 1.0488887786865235,
      "num_input_tokens_seen": 13994221952,
      "step": 49210,
      "train_runtime": 479282.2296,
      "train_tokens_per_second": 29198.291
    },
    {
      "epoch": 1.7415011266964022,
      "grad_norm": 1.625,
      "learning_rate": 2.0546576507464003e-05,
      "loss": 1.0279927253723145,
      "num_input_tokens_seen": 13997047232,
      "step": 49220,
      "train_runtime": 479377.0136,
      "train_tokens_per_second": 29198.411
    },
    {
      "epoch": 1.7418549469601312,
      "grad_norm": 1.578125,
      "learning_rate": 2.054484193117264e-05,
      "loss": 1.0450519561767577,
      "num_input_tokens_seen": 13999908032,
      "step": 49230,
      "train_runtime": 479476.7231,
      "train_tokens_per_second": 29198.306
    },
    {
      "epoch": 1.7422087672238598,
      "grad_norm": 1.546875,
      "learning_rate": 2.0543107794114597e-05,
      "loss": 1.0506264686584472,
      "num_input_tokens_seen": 14002766016,
      "step": 49240,
      "train_runtime": 479574.9874,
      "train_tokens_per_second": 29198.283
    },
    {
      "epoch": 1.7425625874875887,
      "grad_norm": 1.6953125,
      "learning_rate": 2.0541374096104523e-05,
      "loss": 1.0401939392089843,
      "num_input_tokens_seen": 14005568576,
      "step": 49250,
      "train_runtime": 479669.4077,
      "train_tokens_per_second": 29198.378
    },
    {
      "epoch": 1.7429164077513173,
      "grad_norm": 1.5390625,
      "learning_rate": 2.05396408369572e-05,
      "loss": 1.0356176376342774,
      "num_input_tokens_seen": 14008406912,
      "step": 49260,
      "train_runtime": 479766.9693,
      "train_tokens_per_second": 29198.356
    },
    {
      "epoch": 1.7432702280150463,
      "grad_norm": 1.6015625,
      "learning_rate": 2.05379080164875e-05,
      "loss": 1.0442070007324218,
      "num_input_tokens_seen": 14011195456,
      "step": 49270,
      "train_runtime": 479861.6656,
      "train_tokens_per_second": 29198.405
    },
    {
      "epoch": 1.743624048278775,
      "grad_norm": 1.578125,
      "learning_rate": 2.053617563451041e-05,
      "loss": 1.0491275787353516,
      "num_input_tokens_seen": 14014009280,
      "step": 49280,
      "train_runtime": 479957.0554,
      "train_tokens_per_second": 29198.465
    },
    {
      "epoch": 1.7439778685425038,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0534443690841026e-05,
      "loss": 1.051888656616211,
      "num_input_tokens_seen": 14016871680,
      "step": 49290,
      "train_runtime": 480053.2705,
      "train_tokens_per_second": 29198.576
    },
    {
      "epoch": 1.7443316888062326,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0532712185294546e-05,
      "loss": 1.0419275283813476,
      "num_input_tokens_seen": 14019706496,
      "step": 49300,
      "train_runtime": 480149.7696,
      "train_tokens_per_second": 29198.611
    },
    {
      "epoch": 1.7446855090699613,
      "grad_norm": 1.546875,
      "learning_rate": 2.0530981117686292e-05,
      "loss": 1.0337262153625488,
      "num_input_tokens_seen": 14022544512,
      "step": 49310,
      "train_runtime": 480246.7632,
      "train_tokens_per_second": 29198.624
    },
    {
      "epoch": 1.74503932933369,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0529250487831685e-05,
      "loss": 1.0391016960144044,
      "num_input_tokens_seen": 14025402624,
      "step": 49320,
      "train_runtime": 480344.1786,
      "train_tokens_per_second": 29198.652
    },
    {
      "epoch": 1.7453931495974189,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0527520295546256e-05,
      "loss": 1.046268844604492,
      "num_input_tokens_seen": 14028195008,
      "step": 49330,
      "train_runtime": 480439.1016,
      "train_tokens_per_second": 29198.695
    },
    {
      "epoch": 1.7457469698611476,
      "grad_norm": 1.484375,
      "learning_rate": 2.052579054064565e-05,
      "loss": 1.0352148056030273,
      "num_input_tokens_seen": 14031070592,
      "step": 49340,
      "train_runtime": 480538.318,
      "train_tokens_per_second": 29198.651
    },
    {
      "epoch": 1.7461007901248764,
      "grad_norm": 1.59375,
      "learning_rate": 2.052406122294561e-05,
      "loss": 1.0393878936767578,
      "num_input_tokens_seen": 14033917056,
      "step": 49350,
      "train_runtime": 480636.8911,
      "train_tokens_per_second": 29198.585
    },
    {
      "epoch": 1.7464546103886052,
      "grad_norm": 1.546875,
      "learning_rate": 2.0522332342261998e-05,
      "loss": 1.0309988975524902,
      "num_input_tokens_seen": 14036744256,
      "step": 49360,
      "train_runtime": 480733.268,
      "train_tokens_per_second": 29198.612
    },
    {
      "epoch": 1.746808430652334,
      "grad_norm": 1.5859375,
      "learning_rate": 2.052060389841078e-05,
      "loss": 1.0485136032104492,
      "num_input_tokens_seen": 14039614784,
      "step": 49370,
      "train_runtime": 480831.881,
      "train_tokens_per_second": 29198.594
    },
    {
      "epoch": 1.747162250916063,
      "grad_norm": 1.6640625,
      "learning_rate": 2.0518875891208032e-05,
      "loss": 1.0527847290039063,
      "num_input_tokens_seen": 14042505024,
      "step": 49380,
      "train_runtime": 480929.443,
      "train_tokens_per_second": 29198.68
    },
    {
      "epoch": 1.7475160711797915,
      "grad_norm": 1.609375,
      "learning_rate": 2.051714832046994e-05,
      "loss": 1.0364698410034179,
      "num_input_tokens_seen": 14045327680,
      "step": 49390,
      "train_runtime": 481024.0881,
      "train_tokens_per_second": 29198.803
    },
    {
      "epoch": 1.7478698914435205,
      "grad_norm": 1.5703125,
      "learning_rate": 2.051542118601279e-05,
      "loss": 1.0604217529296875,
      "num_input_tokens_seen": 14048168320,
      "step": 49400,
      "train_runtime": 481121.7219,
      "train_tokens_per_second": 29198.782
    },
    {
      "epoch": 1.748223711707249,
      "grad_norm": 1.640625,
      "learning_rate": 2.0513694487652985e-05,
      "loss": 1.0384990692138671,
      "num_input_tokens_seen": 14050945984,
      "step": 49410,
      "train_runtime": 481215.2371,
      "train_tokens_per_second": 29198.88
    },
    {
      "epoch": 1.748577531970978,
      "grad_norm": 1.59375,
      "learning_rate": 2.051196822520703e-05,
      "loss": 1.0549892425537108,
      "num_input_tokens_seen": 14053775424,
      "step": 49420,
      "train_runtime": 481309.2135,
      "train_tokens_per_second": 29199.058
    },
    {
      "epoch": 1.7489313522347065,
      "grad_norm": 1.546875,
      "learning_rate": 2.0510242398491553e-05,
      "loss": 1.0484639167785645,
      "num_input_tokens_seen": 14056553600,
      "step": 49430,
      "train_runtime": 481404.3522,
      "train_tokens_per_second": 29199.058
    },
    {
      "epoch": 1.7492851724984355,
      "grad_norm": 1.65625,
      "learning_rate": 2.0508517007323266e-05,
      "loss": 1.0476638793945312,
      "num_input_tokens_seen": 14059430400,
      "step": 49440,
      "train_runtime": 481502.6083,
      "train_tokens_per_second": 29199.074
    },
    {
      "epoch": 1.7496389927621643,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0506792051519007e-05,
      "loss": 1.0458457946777344,
      "num_input_tokens_seen": 14062304448,
      "step": 49450,
      "train_runtime": 481602.3122,
      "train_tokens_per_second": 29198.997
    },
    {
      "epoch": 1.749992813025893,
      "grad_norm": 1.5234375,
      "learning_rate": 2.050506753089571e-05,
      "loss": 1.044095516204834,
      "num_input_tokens_seen": 14065174720,
      "step": 49460,
      "train_runtime": 481702.3966,
      "train_tokens_per_second": 29198.889
    },
    {
      "epoch": 1.7503466332896218,
      "grad_norm": 1.6171875,
      "learning_rate": 2.050334344527043e-05,
      "loss": 1.0397148132324219,
      "num_input_tokens_seen": 14067993536,
      "step": 49470,
      "train_runtime": 481797.0595,
      "train_tokens_per_second": 29199.002
    },
    {
      "epoch": 1.7507004535533506,
      "grad_norm": 1.5,
      "learning_rate": 2.0501619794460322e-05,
      "loss": 1.0371423721313477,
      "num_input_tokens_seen": 14070812992,
      "step": 49480,
      "train_runtime": 481891.877,
      "train_tokens_per_second": 29199.108
    },
    {
      "epoch": 1.7510542738170793,
      "grad_norm": 1.5625,
      "learning_rate": 2.0499896578282647e-05,
      "loss": 1.0353283882141113,
      "num_input_tokens_seen": 14073621120,
      "step": 49490,
      "train_runtime": 481987.1479,
      "train_tokens_per_second": 29199.163
    },
    {
      "epoch": 1.751408094080808,
      "grad_norm": 1.5859375,
      "learning_rate": 2.049817379655477e-05,
      "loss": 1.0405938148498535,
      "num_input_tokens_seen": 14076485120,
      "step": 49500,
      "train_runtime": 482085.399,
      "train_tokens_per_second": 29199.153
    },
    {
      "epoch": 1.7517619143445369,
      "grad_norm": 1.5,
      "learning_rate": 2.049645144909418e-05,
      "loss": 1.0486406326293944,
      "num_input_tokens_seen": 14079344448,
      "step": 49510,
      "train_runtime": 482183.186,
      "train_tokens_per_second": 29199.161
    },
    {
      "epoch": 1.7521157346082656,
      "grad_norm": 1.5625,
      "learning_rate": 2.0494729535718454e-05,
      "loss": 1.054590892791748,
      "num_input_tokens_seen": 14082116544,
      "step": 49520,
      "train_runtime": 482278.4688,
      "train_tokens_per_second": 29199.14
    },
    {
      "epoch": 1.7524695548719946,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0493008056245292e-05,
      "loss": 1.0536883354187012,
      "num_input_tokens_seen": 14085002496,
      "step": 49530,
      "train_runtime": 482377.502,
      "train_tokens_per_second": 29199.128
    },
    {
      "epoch": 1.7528233751357232,
      "grad_norm": 1.53125,
      "learning_rate": 2.0491287010492484e-05,
      "loss": 1.040531063079834,
      "num_input_tokens_seen": 14087823168,
      "step": 49540,
      "train_runtime": 482474.1638,
      "train_tokens_per_second": 29199.124
    },
    {
      "epoch": 1.7531771953994522,
      "grad_norm": 1.640625,
      "learning_rate": 2.0489566398277943e-05,
      "loss": 1.0404985427856446,
      "num_input_tokens_seen": 14090702016,
      "step": 49550,
      "train_runtime": 482571.7636,
      "train_tokens_per_second": 29199.185
    },
    {
      "epoch": 1.7535310156631807,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0487846219419683e-05,
      "loss": 1.0284334182739259,
      "num_input_tokens_seen": 14093561536,
      "step": 49560,
      "train_runtime": 482668.1857,
      "train_tokens_per_second": 29199.276
    },
    {
      "epoch": 1.7538848359269097,
      "grad_norm": 1.5390625,
      "learning_rate": 2.048612647373583e-05,
      "loss": 1.0421756744384765,
      "num_input_tokens_seen": 14096403200,
      "step": 49570,
      "train_runtime": 482764.1746,
      "train_tokens_per_second": 29199.356
    },
    {
      "epoch": 1.7542386561906382,
      "grad_norm": 1.59375,
      "learning_rate": 2.0484407161044598e-05,
      "loss": 1.0391937255859376,
      "num_input_tokens_seen": 14099277248,
      "step": 49580,
      "train_runtime": 482868.2732,
      "train_tokens_per_second": 29199.014
    },
    {
      "epoch": 1.7545924764543672,
      "grad_norm": 1.4921875,
      "learning_rate": 2.0482688281164333e-05,
      "loss": 1.029792594909668,
      "num_input_tokens_seen": 14102163968,
      "step": 49590,
      "train_runtime": 482966.4412,
      "train_tokens_per_second": 29199.056
    },
    {
      "epoch": 1.7549462967180958,
      "grad_norm": 1.6328125,
      "learning_rate": 2.048096983391347e-05,
      "loss": 1.0432671546936034,
      "num_input_tokens_seen": 14104997632,
      "step": 49600,
      "train_runtime": 483061.3176,
      "train_tokens_per_second": 29199.187
    },
    {
      "epoch": 1.7553001169818248,
      "grad_norm": 1.53125,
      "learning_rate": 2.047925181911056e-05,
      "loss": 1.035003089904785,
      "num_input_tokens_seen": 14107825920,
      "step": 49610,
      "train_runtime": 483157.8585,
      "train_tokens_per_second": 29199.206
    },
    {
      "epoch": 1.7556539372455535,
      "grad_norm": 1.546875,
      "learning_rate": 2.0477534236574254e-05,
      "loss": 1.0351346969604491,
      "num_input_tokens_seen": 14110684672,
      "step": 49620,
      "train_runtime": 483255.226,
      "train_tokens_per_second": 29199.239
    },
    {
      "epoch": 1.7560077575092823,
      "grad_norm": 1.59375,
      "learning_rate": 2.0475817086123313e-05,
      "loss": 1.035903549194336,
      "num_input_tokens_seen": 14113532736,
      "step": 49630,
      "train_runtime": 483354.7374,
      "train_tokens_per_second": 29199.119
    },
    {
      "epoch": 1.756361577773011,
      "grad_norm": 1.546875,
      "learning_rate": 2.047410036757661e-05,
      "loss": 1.0369736671447753,
      "num_input_tokens_seen": 14116398912,
      "step": 49640,
      "train_runtime": 483452.6755,
      "train_tokens_per_second": 29199.133
    },
    {
      "epoch": 1.7567153980367398,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0472384080753113e-05,
      "loss": 1.0273098945617676,
      "num_input_tokens_seen": 14119203904,
      "step": 49650,
      "train_runtime": 483547.0572,
      "train_tokens_per_second": 29199.234
    },
    {
      "epoch": 1.7570692183004686,
      "grad_norm": 1.625,
      "learning_rate": 2.04706682254719e-05,
      "loss": 1.035970687866211,
      "num_input_tokens_seen": 14122062720,
      "step": 49660,
      "train_runtime": 483645.8289,
      "train_tokens_per_second": 29199.182
    },
    {
      "epoch": 1.7574230385641973,
      "grad_norm": 1.609375,
      "learning_rate": 2.0468952801552166e-05,
      "loss": 1.0512178421020508,
      "num_input_tokens_seen": 14124929664,
      "step": 49670,
      "train_runtime": 483745.8198,
      "train_tokens_per_second": 29199.073
    },
    {
      "epoch": 1.7577768588279261,
      "grad_norm": 1.6015625,
      "learning_rate": 2.046723780881319e-05,
      "loss": 1.046142864227295,
      "num_input_tokens_seen": 14127732224,
      "step": 49680,
      "train_runtime": 483843.2025,
      "train_tokens_per_second": 29198.989
    },
    {
      "epoch": 1.7581306790916549,
      "grad_norm": 1.515625,
      "learning_rate": 2.0465523247074376e-05,
      "loss": 1.026993179321289,
      "num_input_tokens_seen": 14130582720,
      "step": 49690,
      "train_runtime": 483939.0294,
      "train_tokens_per_second": 29199.097
    },
    {
      "epoch": 1.7584844993553839,
      "grad_norm": 1.484375,
      "learning_rate": 2.046380911615523e-05,
      "loss": 1.0374319076538085,
      "num_input_tokens_seen": 14133457536,
      "step": 49700,
      "train_runtime": 484037.0433,
      "train_tokens_per_second": 29199.124
    },
    {
      "epoch": 1.7588383196191124,
      "grad_norm": 1.671875,
      "learning_rate": 2.0462095415875357e-05,
      "loss": 1.0421133041381836,
      "num_input_tokens_seen": 14136300352,
      "step": 49710,
      "train_runtime": 484133.5263,
      "train_tokens_per_second": 29199.177
    },
    {
      "epoch": 1.7591921398828414,
      "grad_norm": 1.4765625,
      "learning_rate": 2.046038214605448e-05,
      "loss": 1.0453826904296875,
      "num_input_tokens_seen": 14139115072,
      "step": 49720,
      "train_runtime": 484227.5369,
      "train_tokens_per_second": 29199.321
    },
    {
      "epoch": 1.75954596014657,
      "grad_norm": 1.53125,
      "learning_rate": 2.0458669306512404e-05,
      "loss": 1.0337961196899415,
      "num_input_tokens_seen": 14141986880,
      "step": 49730,
      "train_runtime": 484327.0461,
      "train_tokens_per_second": 29199.251
    },
    {
      "epoch": 1.759899780410299,
      "grad_norm": 1.65625,
      "learning_rate": 2.045695689706907e-05,
      "loss": 1.0395074844360352,
      "num_input_tokens_seen": 14144775616,
      "step": 49740,
      "train_runtime": 484419.9994,
      "train_tokens_per_second": 29199.405
    },
    {
      "epoch": 1.7602536006740275,
      "grad_norm": 1.5625,
      "learning_rate": 2.0455244917544507e-05,
      "loss": 1.0431678771972657,
      "num_input_tokens_seen": 14147649088,
      "step": 49750,
      "train_runtime": 484516.88,
      "train_tokens_per_second": 29199.497
    },
    {
      "epoch": 1.7606074209377565,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0453533367758846e-05,
      "loss": 1.056477165222168,
      "num_input_tokens_seen": 14150497472,
      "step": 49760,
      "train_runtime": 484615.4264,
      "train_tokens_per_second": 29199.437
    },
    {
      "epoch": 1.760961241201485,
      "grad_norm": 1.546875,
      "learning_rate": 2.0451822247532338e-05,
      "loss": 1.0475886344909668,
      "num_input_tokens_seen": 14153397504,
      "step": 49770,
      "train_runtime": 484715.4174,
      "train_tokens_per_second": 29199.396
    },
    {
      "epoch": 1.761315061465214,
      "grad_norm": 1.59375,
      "learning_rate": 2.0450111556685323e-05,
      "loss": 1.037252426147461,
      "num_input_tokens_seen": 14156242496,
      "step": 49780,
      "train_runtime": 484813.4751,
      "train_tokens_per_second": 29199.359
    },
    {
      "epoch": 1.7616688817289428,
      "grad_norm": 1.609375,
      "learning_rate": 2.0448401295038257e-05,
      "loss": 1.0535497665405273,
      "num_input_tokens_seen": 14159148352,
      "step": 49790,
      "train_runtime": 484910.6163,
      "train_tokens_per_second": 29199.502
    },
    {
      "epoch": 1.7620227019926715,
      "grad_norm": 1.59375,
      "learning_rate": 2.04466914624117e-05,
      "loss": 1.0464811325073242,
      "num_input_tokens_seen": 14162018816,
      "step": 49800,
      "train_runtime": 485006.7762,
      "train_tokens_per_second": 29199.631
    },
    {
      "epoch": 1.7623765222564003,
      "grad_norm": 1.578125,
      "learning_rate": 2.0444982058626314e-05,
      "loss": 1.0456256866455078,
      "num_input_tokens_seen": 14164775744,
      "step": 49810,
      "train_runtime": 485097.5514,
      "train_tokens_per_second": 29199.85
    },
    {
      "epoch": 1.762730342520129,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0443273083502863e-05,
      "loss": 1.048194122314453,
      "num_input_tokens_seen": 14167685312,
      "step": 49820,
      "train_runtime": 485196.9786,
      "train_tokens_per_second": 29199.863
    },
    {
      "epoch": 1.7630841627838578,
      "grad_norm": 1.546875,
      "learning_rate": 2.044156453686223e-05,
      "loss": 1.0465474128723145,
      "num_input_tokens_seen": 14170503936,
      "step": 49830,
      "train_runtime": 485291.1105,
      "train_tokens_per_second": 29200.007
    },
    {
      "epoch": 1.7634379830475866,
      "grad_norm": 1.65625,
      "learning_rate": 2.0439856418525386e-05,
      "loss": 1.0460803985595704,
      "num_input_tokens_seen": 14173361536,
      "step": 49840,
      "train_runtime": 485386.4781,
      "train_tokens_per_second": 29200.157
    },
    {
      "epoch": 1.7637918033113154,
      "grad_norm": 1.515625,
      "learning_rate": 2.043814872831341e-05,
      "loss": 1.0394889831542968,
      "num_input_tokens_seen": 14176290624,
      "step": 49850,
      "train_runtime": 485486.2268,
      "train_tokens_per_second": 29200.191
    },
    {
      "epoch": 1.7641456235750441,
      "grad_norm": 1.609375,
      "learning_rate": 2.0436441466047494e-05,
      "loss": 1.0546134948730468,
      "num_input_tokens_seen": 14179099648,
      "step": 49860,
      "train_runtime": 485580.1396,
      "train_tokens_per_second": 29200.329
    },
    {
      "epoch": 1.764499443838773,
      "grad_norm": 1.578125,
      "learning_rate": 2.0434734631548927e-05,
      "loss": 1.0247303009033204,
      "num_input_tokens_seen": 14181980544,
      "step": 49870,
      "train_runtime": 485683.2143,
      "train_tokens_per_second": 29200.063
    },
    {
      "epoch": 1.7648532641025017,
      "grad_norm": 1.578125,
      "learning_rate": 2.0433028224639106e-05,
      "loss": 1.0453105926513673,
      "num_input_tokens_seen": 14184771008,
      "step": 49880,
      "train_runtime": 485774.5797,
      "train_tokens_per_second": 29200.316
    },
    {
      "epoch": 1.7652070843662306,
      "grad_norm": 1.53125,
      "learning_rate": 2.0431322245139533e-05,
      "loss": 1.03680419921875,
      "num_input_tokens_seen": 14187629440,
      "step": 49890,
      "train_runtime": 485872.6208,
      "train_tokens_per_second": 29200.306
    },
    {
      "epoch": 1.7655609046299592,
      "grad_norm": 1.5625,
      "learning_rate": 2.0429616692871808e-05,
      "loss": 1.0536304473876954,
      "num_input_tokens_seen": 14190438336,
      "step": 49900,
      "train_runtime": 485969.4994,
      "train_tokens_per_second": 29200.265
    },
    {
      "epoch": 1.7659147248936882,
      "grad_norm": 1.546875,
      "learning_rate": 2.0427911567657644e-05,
      "loss": 1.0393367767333985,
      "num_input_tokens_seen": 14193285184,
      "step": 49910,
      "train_runtime": 486068.9931,
      "train_tokens_per_second": 29200.145
    },
    {
      "epoch": 1.7662685451574167,
      "grad_norm": 1.625,
      "learning_rate": 2.0426206869318852e-05,
      "loss": 1.0441725730895997,
      "num_input_tokens_seen": 14196087936,
      "step": 49920,
      "train_runtime": 486162.6151,
      "train_tokens_per_second": 29200.287
    },
    {
      "epoch": 1.7666223654211457,
      "grad_norm": 1.59375,
      "learning_rate": 2.0424502597677357e-05,
      "loss": 1.0534631729125976,
      "num_input_tokens_seen": 14198965376,
      "step": 49930,
      "train_runtime": 486264.5689,
      "train_tokens_per_second": 29200.082
    },
    {
      "epoch": 1.7669761856848742,
      "grad_norm": 1.578125,
      "learning_rate": 2.042279875255517e-05,
      "loss": 1.0427358627319336,
      "num_input_tokens_seen": 14201795712,
      "step": 49940,
      "train_runtime": 486362.7876,
      "train_tokens_per_second": 29200.005
    },
    {
      "epoch": 1.7673300059486032,
      "grad_norm": 1.609375,
      "learning_rate": 2.0421095333774413e-05,
      "loss": 1.0370229721069335,
      "num_input_tokens_seen": 14204625984,
      "step": 49950,
      "train_runtime": 486458.8386,
      "train_tokens_per_second": 29200.057
    },
    {
      "epoch": 1.767683826212332,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0419392341157327e-05,
      "loss": 1.0327394485473633,
      "num_input_tokens_seen": 14207496960,
      "step": 49960,
      "train_runtime": 486560.3849,
      "train_tokens_per_second": 29199.864
    },
    {
      "epoch": 1.7680376464760608,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0417689774526235e-05,
      "loss": 1.02719087600708,
      "num_input_tokens_seen": 14210322496,
      "step": 49970,
      "train_runtime": 486657.8858,
      "train_tokens_per_second": 29199.82
    },
    {
      "epoch": 1.7683914667397895,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0415987633703583e-05,
      "loss": 1.0395299911499023,
      "num_input_tokens_seen": 14213167616,
      "step": 49980,
      "train_runtime": 486756.5346,
      "train_tokens_per_second": 29199.747
    },
    {
      "epoch": 1.7687452870035183,
      "grad_norm": 1.609375,
      "learning_rate": 2.04142859185119e-05,
      "loss": 1.0352636337280274,
      "num_input_tokens_seen": 14216049408,
      "step": 49990,
      "train_runtime": 486856.4982,
      "train_tokens_per_second": 29199.671
    },
    {
      "epoch": 1.769099107267247,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0412584628773835e-05,
      "loss": 1.056472110748291,
      "num_input_tokens_seen": 14218881984,
      "step": 50000,
      "train_runtime": 486955.1314,
      "train_tokens_per_second": 29199.573
    },
    {
      "epoch": 1.769099107267247,
      "eval_loss": 1.0212867259979248,
      "eval_runtime": 8.4506,
      "eval_samples_per_second": 471.917,
      "eval_steps_per_second": 3.787,
      "num_input_tokens_seen": 14218881984,
      "step": 50000
    },
    {
      "epoch": 1.7694529275309758,
      "grad_norm": 1.609375,
      "learning_rate": 2.0410883764312135e-05,
      "loss": 1.0360840797424316,
      "num_input_tokens_seen": 14221693248,
      "step": 50010,
      "train_runtime": 487078.4178,
      "train_tokens_per_second": 29197.954
    },
    {
      "epoch": 1.7698067477947046,
      "grad_norm": 1.6171875,
      "learning_rate": 2.0409183324949646e-05,
      "loss": 1.0517303466796875,
      "num_input_tokens_seen": 14224536320,
      "step": 50020,
      "train_runtime": 487178.398,
      "train_tokens_per_second": 29197.798
    },
    {
      "epoch": 1.7701605680584334,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0407483310509333e-05,
      "loss": 1.049877643585205,
      "num_input_tokens_seen": 14227418304,
      "step": 50030,
      "train_runtime": 487280.2087,
      "train_tokens_per_second": 29197.612
    },
    {
      "epoch": 1.7705143883221623,
      "grad_norm": 1.640625,
      "learning_rate": 2.040578372081424e-05,
      "loss": 1.0502395629882812,
      "num_input_tokens_seen": 14230233536,
      "step": 50040,
      "train_runtime": 487375.8501,
      "train_tokens_per_second": 29197.658
    },
    {
      "epoch": 1.770868208585891,
      "grad_norm": 1.625,
      "learning_rate": 2.0404084555687525e-05,
      "loss": 1.0314266204833984,
      "num_input_tokens_seen": 14233023552,
      "step": 50050,
      "train_runtime": 487468.8366,
      "train_tokens_per_second": 29197.812
    },
    {
      "epoch": 1.7712220288496199,
      "grad_norm": 1.578125,
      "learning_rate": 2.0402385814952464e-05,
      "loss": 1.0299631118774415,
      "num_input_tokens_seen": 14235863680,
      "step": 50060,
      "train_runtime": 487565.0515,
      "train_tokens_per_second": 29197.876
    },
    {
      "epoch": 1.7715758491133484,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0400687498432415e-05,
      "loss": 1.035188865661621,
      "num_input_tokens_seen": 14238697344,
      "step": 50070,
      "train_runtime": 487661.3434,
      "train_tokens_per_second": 29197.921
    },
    {
      "epoch": 1.7719296693770774,
      "grad_norm": 1.65625,
      "learning_rate": 2.039898960595085e-05,
      "loss": 1.037077045440674,
      "num_input_tokens_seen": 14241492992,
      "step": 50080,
      "train_runtime": 487757.6321,
      "train_tokens_per_second": 29197.889
    },
    {
      "epoch": 1.772283489640806,
      "grad_norm": 1.546875,
      "learning_rate": 2.039729213733134e-05,
      "loss": 1.0450297355651856,
      "num_input_tokens_seen": 14244341760,
      "step": 50090,
      "train_runtime": 487856.6919,
      "train_tokens_per_second": 29197.799
    },
    {
      "epoch": 1.772637309904535,
      "grad_norm": 1.546875,
      "learning_rate": 2.0395595092397554e-05,
      "loss": 1.0408285140991211,
      "num_input_tokens_seen": 14247171968,
      "step": 50100,
      "train_runtime": 487955.9187,
      "train_tokens_per_second": 29197.662
    },
    {
      "epoch": 1.7729911301682635,
      "grad_norm": 1.640625,
      "learning_rate": 2.0393898470973276e-05,
      "loss": 1.0585382461547852,
      "num_input_tokens_seen": 14249991808,
      "step": 50110,
      "train_runtime": 488054.7777,
      "train_tokens_per_second": 29197.525
    },
    {
      "epoch": 1.7733449504319925,
      "grad_norm": 1.609375,
      "learning_rate": 2.0392202272882384e-05,
      "loss": 1.044197177886963,
      "num_input_tokens_seen": 14252898176,
      "step": 50120,
      "train_runtime": 488155.5534,
      "train_tokens_per_second": 29197.452
    },
    {
      "epoch": 1.7736987706957212,
      "grad_norm": 1.53125,
      "learning_rate": 2.0390506497948854e-05,
      "loss": 1.0573487281799316,
      "num_input_tokens_seen": 14255738752,
      "step": 50130,
      "train_runtime": 488254.153,
      "train_tokens_per_second": 29197.373
    },
    {
      "epoch": 1.77405259095945,
      "grad_norm": 1.5546875,
      "learning_rate": 2.038881114599678e-05,
      "loss": 1.0294795036315918,
      "num_input_tokens_seen": 14258539840,
      "step": 50140,
      "train_runtime": 488347.9311,
      "train_tokens_per_second": 29197.502
    },
    {
      "epoch": 1.7744064112231788,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0387116216850345e-05,
      "loss": 1.0442691802978517,
      "num_input_tokens_seen": 14261400064,
      "step": 50150,
      "train_runtime": 488443.5884,
      "train_tokens_per_second": 29197.64
    },
    {
      "epoch": 1.7747602314869075,
      "grad_norm": 1.53125,
      "learning_rate": 2.0385421710333838e-05,
      "loss": 1.038187313079834,
      "num_input_tokens_seen": 14264280128,
      "step": 50160,
      "train_runtime": 488540.8907,
      "train_tokens_per_second": 29197.72
    },
    {
      "epoch": 1.7751140517506363,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0383727626271648e-05,
      "loss": 1.0440409660339356,
      "num_input_tokens_seen": 14267157120,
      "step": 50170,
      "train_runtime": 488639.6854,
      "train_tokens_per_second": 29197.704
    },
    {
      "epoch": 1.775467872014365,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0382033964488274e-05,
      "loss": 1.0581318855285644,
      "num_input_tokens_seen": 14270035136,
      "step": 50180,
      "train_runtime": 488737.846,
      "train_tokens_per_second": 29197.729
    },
    {
      "epoch": 1.7758216922780938,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0380340724808307e-05,
      "loss": 1.0410472869873046,
      "num_input_tokens_seen": 14272912768,
      "step": 50190,
      "train_runtime": 488838.2035,
      "train_tokens_per_second": 29197.621
    },
    {
      "epoch": 1.7761755125418226,
      "grad_norm": 1.578125,
      "learning_rate": 2.0378647907056447e-05,
      "loss": 1.0410990715026855,
      "num_input_tokens_seen": 14275817984,
      "step": 50200,
      "train_runtime": 488938.441,
      "train_tokens_per_second": 29197.577
    },
    {
      "epoch": 1.7765293328055516,
      "grad_norm": 1.546875,
      "learning_rate": 2.0376955511057493e-05,
      "loss": 1.034639835357666,
      "num_input_tokens_seen": 14278631360,
      "step": 50210,
      "train_runtime": 489037.1933,
      "train_tokens_per_second": 29197.434
    },
    {
      "epoch": 1.7768831530692801,
      "grad_norm": 1.53125,
      "learning_rate": 2.0375263536636348e-05,
      "loss": 1.039046859741211,
      "num_input_tokens_seen": 14281497792,
      "step": 50220,
      "train_runtime": 489134.6329,
      "train_tokens_per_second": 29197.478
    },
    {
      "epoch": 1.7772369733330091,
      "grad_norm": 1.609375,
      "learning_rate": 2.0373571983618014e-05,
      "loss": 1.049449348449707,
      "num_input_tokens_seen": 14284357120,
      "step": 50230,
      "train_runtime": 489234.1636,
      "train_tokens_per_second": 29197.383
    },
    {
      "epoch": 1.7775907935967377,
      "grad_norm": 1.5625,
      "learning_rate": 2.0371880851827597e-05,
      "loss": 1.0400571823120117,
      "num_input_tokens_seen": 14287188160,
      "step": 50240,
      "train_runtime": 489329.9614,
      "train_tokens_per_second": 29197.452
    },
    {
      "epoch": 1.7779446138604666,
      "grad_norm": 1.6171875,
      "learning_rate": 2.0370190141090298e-05,
      "loss": 1.0454938888549805,
      "num_input_tokens_seen": 14290047232,
      "step": 50250,
      "train_runtime": 489426.2897,
      "train_tokens_per_second": 29197.547
    },
    {
      "epoch": 1.7782984341241952,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0368499851231433e-05,
      "loss": 1.0445655822753905,
      "num_input_tokens_seen": 14292963264,
      "step": 50260,
      "train_runtime": 489526.9316,
      "train_tokens_per_second": 29197.501
    },
    {
      "epoch": 1.7786522543879242,
      "grad_norm": 1.578125,
      "learning_rate": 2.0366809982076404e-05,
      "loss": 1.0426286697387694,
      "num_input_tokens_seen": 14295811392,
      "step": 50270,
      "train_runtime": 489626.293,
      "train_tokens_per_second": 29197.393
    },
    {
      "epoch": 1.779006074651653,
      "grad_norm": 1.578125,
      "learning_rate": 2.0365120533450732e-05,
      "loss": 1.0470451354980468,
      "num_input_tokens_seen": 14298666560,
      "step": 50280,
      "train_runtime": 489722.6788,
      "train_tokens_per_second": 29197.477
    },
    {
      "epoch": 1.7793598949153817,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0363431505180018e-05,
      "loss": 1.0330720901489259,
      "num_input_tokens_seen": 14301523264,
      "step": 50290,
      "train_runtime": 489824.2876,
      "train_tokens_per_second": 29197.252
    },
    {
      "epoch": 1.7797137151791105,
      "grad_norm": 1.5234375,
      "learning_rate": 2.036174289708998e-05,
      "loss": 1.044950294494629,
      "num_input_tokens_seen": 14304374016,
      "step": 50300,
      "train_runtime": 489923.0941,
      "train_tokens_per_second": 29197.183
    },
    {
      "epoch": 1.7800675354428392,
      "grad_norm": 1.5390625,
      "learning_rate": 2.036005470900643e-05,
      "loss": 1.0390226364135742,
      "num_input_tokens_seen": 14307237504,
      "step": 50310,
      "train_runtime": 490021.6151,
      "train_tokens_per_second": 29197.156
    },
    {
      "epoch": 1.780421355706568,
      "grad_norm": 1.6015625,
      "learning_rate": 2.035836694075529e-05,
      "loss": 1.0313528060913086,
      "num_input_tokens_seen": 14310040896,
      "step": 50320,
      "train_runtime": 490113.7838,
      "train_tokens_per_second": 29197.385
    },
    {
      "epoch": 1.7807751759702968,
      "grad_norm": 1.578125,
      "learning_rate": 2.0356679592162574e-05,
      "loss": 1.0422174453735351,
      "num_input_tokens_seen": 14312854592,
      "step": 50330,
      "train_runtime": 490208.6826,
      "train_tokens_per_second": 29197.473
    },
    {
      "epoch": 1.7811289962340255,
      "grad_norm": 1.546875,
      "learning_rate": 2.0354992663054395e-05,
      "loss": 1.0405973434448241,
      "num_input_tokens_seen": 14315676736,
      "step": 50340,
      "train_runtime": 490305.6438,
      "train_tokens_per_second": 29197.455
    },
    {
      "epoch": 1.7814828164977543,
      "grad_norm": 1.6171875,
      "learning_rate": 2.0353306153256975e-05,
      "loss": 1.0566287994384767,
      "num_input_tokens_seen": 14318516544,
      "step": 50350,
      "train_runtime": 490408.1881,
      "train_tokens_per_second": 29197.14
    },
    {
      "epoch": 1.781836636761483,
      "grad_norm": 1.4921875,
      "learning_rate": 2.0351620062596634e-05,
      "loss": 1.043938446044922,
      "num_input_tokens_seen": 14321402944,
      "step": 50360,
      "train_runtime": 490508.768,
      "train_tokens_per_second": 29197.038
    },
    {
      "epoch": 1.7821904570252118,
      "grad_norm": 1.5625,
      "learning_rate": 2.0349934390899796e-05,
      "loss": 1.0397371292114257,
      "num_input_tokens_seen": 14324217408,
      "step": 50370,
      "train_runtime": 490603.3791,
      "train_tokens_per_second": 29197.144
    },
    {
      "epoch": 1.7825442772889408,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0348249137992967e-05,
      "loss": 1.0405067443847655,
      "num_input_tokens_seen": 14327077504,
      "step": 50380,
      "train_runtime": 490700.4536,
      "train_tokens_per_second": 29197.196
    },
    {
      "epoch": 1.7828980975526694,
      "grad_norm": 1.640625,
      "learning_rate": 2.034656430370278e-05,
      "loss": 1.0518203735351563,
      "num_input_tokens_seen": 14329920000,
      "step": 50390,
      "train_runtime": 490798.0187,
      "train_tokens_per_second": 29197.184
    },
    {
      "epoch": 1.7832519178163984,
      "grad_norm": 1.5625,
      "learning_rate": 2.0344879887855952e-05,
      "loss": 1.0539262771606446,
      "num_input_tokens_seen": 14332805952,
      "step": 50400,
      "train_runtime": 490897.486,
      "train_tokens_per_second": 29197.147
    },
    {
      "epoch": 1.783605738080127,
      "grad_norm": 1.640625,
      "learning_rate": 2.0343195890279314e-05,
      "loss": 1.0491648674011231,
      "num_input_tokens_seen": 14335667776,
      "step": 50410,
      "train_runtime": 490995.3454,
      "train_tokens_per_second": 29197.156
    },
    {
      "epoch": 1.783959558343856,
      "grad_norm": 1.5078125,
      "learning_rate": 2.034151231079977e-05,
      "loss": 1.0401899337768554,
      "num_input_tokens_seen": 14338499456,
      "step": 50420,
      "train_runtime": 491092.1586,
      "train_tokens_per_second": 29197.166
    },
    {
      "epoch": 1.7843133786075844,
      "grad_norm": 1.546875,
      "learning_rate": 2.033982914924436e-05,
      "loss": 1.0654169082641602,
      "num_input_tokens_seen": 14341356736,
      "step": 50430,
      "train_runtime": 491192.26,
      "train_tokens_per_second": 29197.033
    },
    {
      "epoch": 1.7846671988713134,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0338146405440198e-05,
      "loss": 1.0430665016174316,
      "num_input_tokens_seen": 14344204160,
      "step": 50440,
      "train_runtime": 491289.4995,
      "train_tokens_per_second": 29197.05
    },
    {
      "epoch": 1.7850210191350422,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0336464079214507e-05,
      "loss": 1.0326311111450195,
      "num_input_tokens_seen": 14347045632,
      "step": 50450,
      "train_runtime": 491386.7174,
      "train_tokens_per_second": 29197.056
    },
    {
      "epoch": 1.785374839398771,
      "grad_norm": 1.5546875,
      "learning_rate": 2.033478217039461e-05,
      "loss": 1.0404419898986816,
      "num_input_tokens_seen": 14349957440,
      "step": 50460,
      "train_runtime": 491488.7559,
      "train_tokens_per_second": 29196.919
    },
    {
      "epoch": 1.7857286596624997,
      "grad_norm": 1.515625,
      "learning_rate": 2.033310067880794e-05,
      "loss": 1.0385892868041993,
      "num_input_tokens_seen": 14352851520,
      "step": 50470,
      "train_runtime": 491587.4846,
      "train_tokens_per_second": 29196.942
    },
    {
      "epoch": 1.7860824799262285,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0331419604282e-05,
      "loss": 1.0431005477905273,
      "num_input_tokens_seen": 14355658304,
      "step": 50480,
      "train_runtime": 491682.3156,
      "train_tokens_per_second": 29197.02
    },
    {
      "epoch": 1.7864363001899572,
      "grad_norm": 1.6328125,
      "learning_rate": 2.0329738946644425e-05,
      "loss": 1.0313123703002929,
      "num_input_tokens_seen": 14358490496,
      "step": 50490,
      "train_runtime": 491780.2141,
      "train_tokens_per_second": 29196.967
    },
    {
      "epoch": 1.786790120453686,
      "grad_norm": 1.59375,
      "learning_rate": 2.0328058705722937e-05,
      "loss": 1.045037841796875,
      "num_input_tokens_seen": 14361369600,
      "step": 50500,
      "train_runtime": 491879.5976,
      "train_tokens_per_second": 29196.921
    },
    {
      "epoch": 1.7871439407174148,
      "grad_norm": 1.53125,
      "learning_rate": 2.0326378881345356e-05,
      "loss": 1.0443553924560547,
      "num_input_tokens_seen": 14364233472,
      "step": 50510,
      "train_runtime": 491975.6469,
      "train_tokens_per_second": 29197.042
    },
    {
      "epoch": 1.7874977609811435,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0324699473339605e-05,
      "loss": 1.0371468544006348,
      "num_input_tokens_seen": 14367140736,
      "step": 50520,
      "train_runtime": 492076.3174,
      "train_tokens_per_second": 29196.977
    },
    {
      "epoch": 1.7878515812448725,
      "grad_norm": 1.53125,
      "learning_rate": 2.0323020481533697e-05,
      "loss": 1.0320363998413087,
      "num_input_tokens_seen": 14369975680,
      "step": 50530,
      "train_runtime": 492177.9953,
      "train_tokens_per_second": 29196.705
    },
    {
      "epoch": 1.788205401508601,
      "grad_norm": 1.625,
      "learning_rate": 2.0321341905755763e-05,
      "loss": 1.0426502227783203,
      "num_input_tokens_seen": 14372866816,
      "step": 50540,
      "train_runtime": 492277.3846,
      "train_tokens_per_second": 29196.683
    },
    {
      "epoch": 1.78855922177233,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0319663745834018e-05,
      "loss": 1.0454934120178223,
      "num_input_tokens_seen": 14375748352,
      "step": 50550,
      "train_runtime": 492378.0506,
      "train_tokens_per_second": 29196.566
    },
    {
      "epoch": 1.7889130420360586,
      "grad_norm": 1.5546875,
      "learning_rate": 2.031798600159678e-05,
      "loss": 1.042333984375,
      "num_input_tokens_seen": 14378604800,
      "step": 50560,
      "train_runtime": 492476.263,
      "train_tokens_per_second": 29196.544
    },
    {
      "epoch": 1.7892668622997876,
      "grad_norm": 1.59375,
      "learning_rate": 2.0316308672872466e-05,
      "loss": 1.042057991027832,
      "num_input_tokens_seen": 14381446144,
      "step": 50570,
      "train_runtime": 492571.2659,
      "train_tokens_per_second": 29196.681
    },
    {
      "epoch": 1.7896206825635161,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0314631759489597e-05,
      "loss": 1.0495368003845216,
      "num_input_tokens_seen": 14384275968,
      "step": 50580,
      "train_runtime": 492668.7761,
      "train_tokens_per_second": 29196.646
    },
    {
      "epoch": 1.7899745028272451,
      "grad_norm": 1.515625,
      "learning_rate": 2.0312955261276783e-05,
      "loss": 1.0322505950927734,
      "num_input_tokens_seen": 14387086464,
      "step": 50590,
      "train_runtime": 492764.3369,
      "train_tokens_per_second": 29196.688
    },
    {
      "epoch": 1.7903283230909737,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0311279178062754e-05,
      "loss": 1.048440933227539,
      "num_input_tokens_seen": 14389862144,
      "step": 50600,
      "train_runtime": 492855.9002,
      "train_tokens_per_second": 29196.895
    },
    {
      "epoch": 1.7906821433547027,
      "grad_norm": 1.6328125,
      "learning_rate": 2.0309603509676307e-05,
      "loss": 1.056524658203125,
      "num_input_tokens_seen": 14392652352,
      "step": 50610,
      "train_runtime": 492948.3348,
      "train_tokens_per_second": 29197.081
    },
    {
      "epoch": 1.7910359636184314,
      "grad_norm": 1.6328125,
      "learning_rate": 2.0307928255946362e-05,
      "loss": 1.0436988830566407,
      "num_input_tokens_seen": 14395532992,
      "step": 50620,
      "train_runtime": 493046.2876,
      "train_tokens_per_second": 29197.123
    },
    {
      "epoch": 1.7913897838821602,
      "grad_norm": 1.5625,
      "learning_rate": 2.0306253416701935e-05,
      "loss": 1.0413457870483398,
      "num_input_tokens_seen": 14398337088,
      "step": 50630,
      "train_runtime": 493140.4398,
      "train_tokens_per_second": 29197.235
    },
    {
      "epoch": 1.791743604145889,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0304578991772127e-05,
      "loss": 1.0323431968688965,
      "num_input_tokens_seen": 14401125888,
      "step": 50640,
      "train_runtime": 493233.4919,
      "train_tokens_per_second": 29197.38
    },
    {
      "epoch": 1.7920974244096177,
      "grad_norm": 1.5703125,
      "learning_rate": 2.030290498098616e-05,
      "loss": 1.0564096450805665,
      "num_input_tokens_seen": 14403993088,
      "step": 50650,
      "train_runtime": 493332.5436,
      "train_tokens_per_second": 29197.33
    },
    {
      "epoch": 1.7924512446733465,
      "grad_norm": 1.5625,
      "learning_rate": 2.0301231384173324e-05,
      "loss": 1.0411944389343262,
      "num_input_tokens_seen": 14406857472,
      "step": 50660,
      "train_runtime": 493429.6924,
      "train_tokens_per_second": 29197.387
    },
    {
      "epoch": 1.7928050649370753,
      "grad_norm": 1.625,
      "learning_rate": 2.0299558201163047e-05,
      "loss": 1.0244243621826172,
      "num_input_tokens_seen": 14409669824,
      "step": 50670,
      "train_runtime": 493525.059,
      "train_tokens_per_second": 29197.443
    },
    {
      "epoch": 1.793158885200804,
      "grad_norm": 1.578125,
      "learning_rate": 2.0297885431784816e-05,
      "loss": 1.0476810455322265,
      "num_input_tokens_seen": 14412567104,
      "step": 50680,
      "train_runtime": 493623.7596,
      "train_tokens_per_second": 29197.474
    },
    {
      "epoch": 1.7935127054645328,
      "grad_norm": 1.546875,
      "learning_rate": 2.0296213075868243e-05,
      "loss": 1.0351078987121582,
      "num_input_tokens_seen": 14415413184,
      "step": 50690,
      "train_runtime": 493721.2109,
      "train_tokens_per_second": 29197.476
    },
    {
      "epoch": 1.7938665257282618,
      "grad_norm": 1.625,
      "learning_rate": 2.0294541133243025e-05,
      "loss": 1.0443912506103517,
      "num_input_tokens_seen": 14418257472,
      "step": 50700,
      "train_runtime": 493817.1349,
      "train_tokens_per_second": 29197.564
    },
    {
      "epoch": 1.7942203459919903,
      "grad_norm": 1.484375,
      "learning_rate": 2.0292869603738964e-05,
      "loss": 1.045097827911377,
      "num_input_tokens_seen": 14421087296,
      "step": 50710,
      "train_runtime": 493914.0543,
      "train_tokens_per_second": 29197.564
    },
    {
      "epoch": 1.7945741662557193,
      "grad_norm": 1.5,
      "learning_rate": 2.0291198487185956e-05,
      "loss": 1.0387515068054198,
      "num_input_tokens_seen": 14423951360,
      "step": 50720,
      "train_runtime": 494012.137,
      "train_tokens_per_second": 29197.565
    },
    {
      "epoch": 1.7949279865194478,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0289527783413993e-05,
      "loss": 1.0363192558288574,
      "num_input_tokens_seen": 14426803840,
      "step": 50730,
      "train_runtime": 494106.9869,
      "train_tokens_per_second": 29197.733
    },
    {
      "epoch": 1.7952818067831768,
      "grad_norm": 1.53125,
      "learning_rate": 2.0287857492253182e-05,
      "loss": 1.065131950378418,
      "num_input_tokens_seen": 14429652032,
      "step": 50740,
      "train_runtime": 494202.8229,
      "train_tokens_per_second": 29197.834
    },
    {
      "epoch": 1.7956356270469054,
      "grad_norm": 1.546875,
      "learning_rate": 2.0286187613533696e-05,
      "loss": 1.0385104179382325,
      "num_input_tokens_seen": 14432463744,
      "step": 50750,
      "train_runtime": 494297.6439,
      "train_tokens_per_second": 29197.921
    },
    {
      "epoch": 1.7959894473106344,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0284518147085836e-05,
      "loss": 1.0438802719116211,
      "num_input_tokens_seen": 14435292544,
      "step": 50760,
      "train_runtime": 494395.0652,
      "train_tokens_per_second": 29197.89
    },
    {
      "epoch": 1.796343267574363,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0282849092739986e-05,
      "loss": 1.0564435958862304,
      "num_input_tokens_seen": 14438149312,
      "step": 50770,
      "train_runtime": 494494.0064,
      "train_tokens_per_second": 29197.825
    },
    {
      "epoch": 1.796697087838092,
      "grad_norm": 1.5625,
      "learning_rate": 2.0281180450326632e-05,
      "loss": 1.0487442016601562,
      "num_input_tokens_seen": 14441028352,
      "step": 50780,
      "train_runtime": 494595.1058,
      "train_tokens_per_second": 29197.677
    },
    {
      "epoch": 1.7970509081018207,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0279512219676352e-05,
      "loss": 1.055472183227539,
      "num_input_tokens_seen": 14443823424,
      "step": 50790,
      "train_runtime": 494688.4535,
      "train_tokens_per_second": 29197.818
    },
    {
      "epoch": 1.7974047283655494,
      "grad_norm": 1.4921875,
      "learning_rate": 2.027784440061983e-05,
      "loss": 1.0422065734863282,
      "num_input_tokens_seen": 14446639488,
      "step": 50800,
      "train_runtime": 494785.9472,
      "train_tokens_per_second": 29197.756
    },
    {
      "epoch": 1.7977585486292782,
      "grad_norm": 1.59375,
      "learning_rate": 2.0276176992987846e-05,
      "loss": 1.0303110122680663,
      "num_input_tokens_seen": 14449491200,
      "step": 50810,
      "train_runtime": 494884.7099,
      "train_tokens_per_second": 29197.692
    },
    {
      "epoch": 1.798112368893007,
      "grad_norm": 1.5703125,
      "learning_rate": 2.027450999661126e-05,
      "loss": 1.0373829841613769,
      "num_input_tokens_seen": 14452334592,
      "step": 50820,
      "train_runtime": 494980.2948,
      "train_tokens_per_second": 29197.798
    },
    {
      "epoch": 1.7984661891567357,
      "grad_norm": 1.546875,
      "learning_rate": 2.027284341132106e-05,
      "loss": 1.0487239837646485,
      "num_input_tokens_seen": 14455210944,
      "step": 50830,
      "train_runtime": 495080.7379,
      "train_tokens_per_second": 29197.684
    },
    {
      "epoch": 1.7988200094204645,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0271177236948313e-05,
      "loss": 1.0419292449951172,
      "num_input_tokens_seen": 14458058048,
      "step": 50840,
      "train_runtime": 495177.8516,
      "train_tokens_per_second": 29197.707
    },
    {
      "epoch": 1.7991738296841933,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0269511473324176e-05,
      "loss": 1.0383618354797364,
      "num_input_tokens_seen": 14460942528,
      "step": 50850,
      "train_runtime": 495278.0757,
      "train_tokens_per_second": 29197.623
    },
    {
      "epoch": 1.799527649947922,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0267846120279927e-05,
      "loss": 1.0358762741088867,
      "num_input_tokens_seen": 14463786432,
      "step": 50860,
      "train_runtime": 495373.7086,
      "train_tokens_per_second": 29197.727
    },
    {
      "epoch": 1.799881470211651,
      "grad_norm": 1.578125,
      "learning_rate": 2.0266181177646913e-05,
      "loss": 1.0555421829223632,
      "num_input_tokens_seen": 14466568000,
      "step": 50870,
      "train_runtime": 495466.2406,
      "train_tokens_per_second": 29197.888
    },
    {
      "epoch": 1.8002352904753796,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0264516645256593e-05,
      "loss": 1.0385346412658691,
      "num_input_tokens_seen": 14469439616,
      "step": 50880,
      "train_runtime": 495565.1752,
      "train_tokens_per_second": 29197.854
    },
    {
      "epoch": 1.8005891107391085,
      "grad_norm": 1.515625,
      "learning_rate": 2.0262852522940528e-05,
      "loss": 1.0360372543334961,
      "num_input_tokens_seen": 14472290816,
      "step": 50890,
      "train_runtime": 495657.9219,
      "train_tokens_per_second": 29198.143
    },
    {
      "epoch": 1.800942931002837,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0261188810530366e-05,
      "loss": 1.0383338928222656,
      "num_input_tokens_seen": 14475117760,
      "step": 50900,
      "train_runtime": 495755.2593,
      "train_tokens_per_second": 29198.112
    },
    {
      "epoch": 1.801296751266566,
      "grad_norm": 1.5234375,
      "learning_rate": 2.025952550785785e-05,
      "loss": 1.0498991012573242,
      "num_input_tokens_seen": 14478041856,
      "step": 50910,
      "train_runtime": 495859.7928,
      "train_tokens_per_second": 29197.854
    },
    {
      "epoch": 1.8016505715302946,
      "grad_norm": 1.5625,
      "learning_rate": 2.0257862614754837e-05,
      "loss": 1.043105697631836,
      "num_input_tokens_seen": 14480872128,
      "step": 50920,
      "train_runtime": 495958.8654,
      "train_tokens_per_second": 29197.728
    },
    {
      "epoch": 1.8020043917940236,
      "grad_norm": 1.6484375,
      "learning_rate": 2.0256200131053257e-05,
      "loss": 1.0473910331726075,
      "num_input_tokens_seen": 14483709056,
      "step": 50930,
      "train_runtime": 496054.5917,
      "train_tokens_per_second": 29197.813
    },
    {
      "epoch": 1.8023582120577522,
      "grad_norm": 1.5546875,
      "learning_rate": 2.025453805658515e-05,
      "loss": 1.0524008750915528,
      "num_input_tokens_seen": 14486550784,
      "step": 50940,
      "train_runtime": 496151.7081,
      "train_tokens_per_second": 29197.825
    },
    {
      "epoch": 1.8027120323214811,
      "grad_norm": 1.5625,
      "learning_rate": 2.0252876391182653e-05,
      "loss": 1.0378385543823243,
      "num_input_tokens_seen": 14489419584,
      "step": 50950,
      "train_runtime": 496248.831,
      "train_tokens_per_second": 29197.892
    },
    {
      "epoch": 1.80306585258521,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0251215134677996e-05,
      "loss": 1.0409759521484374,
      "num_input_tokens_seen": 14492228352,
      "step": 50960,
      "train_runtime": 496342.7554,
      "train_tokens_per_second": 29198.025
    },
    {
      "epoch": 1.8034196728489387,
      "grad_norm": 1.6015625,
      "learning_rate": 2.02495542869035e-05,
      "loss": 1.0407875061035157,
      "num_input_tokens_seen": 14495119616,
      "step": 50970,
      "train_runtime": 496441.3516,
      "train_tokens_per_second": 29198.05
    },
    {
      "epoch": 1.8037734931126674,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0247893847691597e-05,
      "loss": 1.0456952095031737,
      "num_input_tokens_seen": 14497977664,
      "step": 50980,
      "train_runtime": 496540.1198,
      "train_tokens_per_second": 29197.998
    },
    {
      "epoch": 1.8041273133763962,
      "grad_norm": 1.59375,
      "learning_rate": 2.02462338168748e-05,
      "loss": 1.0488187789916992,
      "num_input_tokens_seen": 14500845632,
      "step": 50990,
      "train_runtime": 496638.3003,
      "train_tokens_per_second": 29198.001
    },
    {
      "epoch": 1.804481133640125,
      "grad_norm": 1.625,
      "learning_rate": 2.0244574194285724e-05,
      "loss": 1.0329582214355468,
      "num_input_tokens_seen": 14503726720,
      "step": 51000,
      "train_runtime": 496737.2443,
      "train_tokens_per_second": 29197.985
    },
    {
      "epoch": 1.8048349539038537,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0242914979757085e-05,
      "loss": 1.0491451263427733,
      "num_input_tokens_seen": 14506607104,
      "step": 51010,
      "train_runtime": 496837.1653,
      "train_tokens_per_second": 29197.911
    },
    {
      "epoch": 1.8051887741675825,
      "grad_norm": 1.5390625,
      "learning_rate": 2.024125617312169e-05,
      "loss": 1.0352978706359863,
      "num_input_tokens_seen": 14509458560,
      "step": 51020,
      "train_runtime": 496934.1051,
      "train_tokens_per_second": 29197.953
    },
    {
      "epoch": 1.8055425944313113,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0239597774212434e-05,
      "loss": 1.0428482055664063,
      "num_input_tokens_seen": 14512300352,
      "step": 51030,
      "train_runtime": 497031.4295,
      "train_tokens_per_second": 29197.953
    },
    {
      "epoch": 1.8058964146950403,
      "grad_norm": 1.578125,
      "learning_rate": 2.023793978286233e-05,
      "loss": 1.044601058959961,
      "num_input_tokens_seen": 14515180032,
      "step": 51040,
      "train_runtime": 497130.9174,
      "train_tokens_per_second": 29197.902
    },
    {
      "epoch": 1.8062502349587688,
      "grad_norm": 1.5625,
      "learning_rate": 2.023628219890446e-05,
      "loss": 1.042293167114258,
      "num_input_tokens_seen": 14518073408,
      "step": 51050,
      "train_runtime": 497231.1661,
      "train_tokens_per_second": 29197.835
    },
    {
      "epoch": 1.8066040552224978,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0234625022172022e-05,
      "loss": 1.0376708984375,
      "num_input_tokens_seen": 14520882176,
      "step": 51060,
      "train_runtime": 497327.4748,
      "train_tokens_per_second": 29197.828
    },
    {
      "epoch": 1.8069578754862263,
      "grad_norm": 1.5625,
      "learning_rate": 2.0232968252498296e-05,
      "loss": 1.0467042922973633,
      "num_input_tokens_seen": 14523785792,
      "step": 51070,
      "train_runtime": 497428.378,
      "train_tokens_per_second": 29197.743
    },
    {
      "epoch": 1.8073116957499553,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0231311889716673e-05,
      "loss": 1.0369575500488282,
      "num_input_tokens_seen": 14526678976,
      "step": 51080,
      "train_runtime": 497529.6735,
      "train_tokens_per_second": 29197.613
    },
    {
      "epoch": 1.8076655160136839,
      "grad_norm": 1.59375,
      "learning_rate": 2.022965593366062e-05,
      "loss": 1.048073959350586,
      "num_input_tokens_seen": 14529515904,
      "step": 51090,
      "train_runtime": 497626.6446,
      "train_tokens_per_second": 29197.624
    },
    {
      "epoch": 1.8080193362774128,
      "grad_norm": 1.609375,
      "learning_rate": 2.0228000384163716e-05,
      "loss": 1.0357088088989257,
      "num_input_tokens_seen": 14532425728,
      "step": 51100,
      "train_runtime": 497725.6107,
      "train_tokens_per_second": 29197.665
    },
    {
      "epoch": 1.8083731565411414,
      "grad_norm": 1.59375,
      "learning_rate": 2.0226345241059623e-05,
      "loss": 1.0365728378295898,
      "num_input_tokens_seen": 14535256000,
      "step": 51110,
      "train_runtime": 497820.8259,
      "train_tokens_per_second": 29197.766
    },
    {
      "epoch": 1.8087269768048704,
      "grad_norm": 1.5625,
      "learning_rate": 2.022469050418211e-05,
      "loss": 1.0466348648071289,
      "num_input_tokens_seen": 14538068928,
      "step": 51120,
      "train_runtime": 497916.0634,
      "train_tokens_per_second": 29197.831
    },
    {
      "epoch": 1.8090807970685991,
      "grad_norm": 1.578125,
      "learning_rate": 2.0223036173365033e-05,
      "loss": 1.0418018341064452,
      "num_input_tokens_seen": 14540915776,
      "step": 51130,
      "train_runtime": 498013.094,
      "train_tokens_per_second": 29197.858
    },
    {
      "epoch": 1.809434617332328,
      "grad_norm": 1.578125,
      "learning_rate": 2.0221382248442346e-05,
      "loss": 1.0480876922607423,
      "num_input_tokens_seen": 14543712704,
      "step": 51140,
      "train_runtime": 498107.8148,
      "train_tokens_per_second": 29197.921
    },
    {
      "epoch": 1.8097884375960567,
      "grad_norm": 1.703125,
      "learning_rate": 2.0219728729248095e-05,
      "loss": 1.0362838745117187,
      "num_input_tokens_seen": 14546570112,
      "step": 51150,
      "train_runtime": 498205.8487,
      "train_tokens_per_second": 29197.911
    },
    {
      "epoch": 1.8101422578597854,
      "grad_norm": 1.4921875,
      "learning_rate": 2.0218075615616425e-05,
      "loss": 1.05155029296875,
      "num_input_tokens_seen": 14549390400,
      "step": 51160,
      "train_runtime": 498301.9508,
      "train_tokens_per_second": 29197.94
    },
    {
      "epoch": 1.8104960781235142,
      "grad_norm": 1.53125,
      "learning_rate": 2.0216422907381577e-05,
      "loss": 1.056875228881836,
      "num_input_tokens_seen": 14552233984,
      "step": 51170,
      "train_runtime": 498398.7393,
      "train_tokens_per_second": 29197.975
    },
    {
      "epoch": 1.810849898387243,
      "grad_norm": 1.53125,
      "learning_rate": 2.021477060437788e-05,
      "loss": 1.0404655456542968,
      "num_input_tokens_seen": 14555083712,
      "step": 51180,
      "train_runtime": 498496.2025,
      "train_tokens_per_second": 29197.983
    },
    {
      "epoch": 1.8112037186509717,
      "grad_norm": 1.8203125,
      "learning_rate": 2.021311870643976e-05,
      "loss": 1.0440263748168945,
      "num_input_tokens_seen": 14557916544,
      "step": 51190,
      "train_runtime": 498591.8218,
      "train_tokens_per_second": 29198.065
    },
    {
      "epoch": 1.8115575389147005,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0211467213401743e-05,
      "loss": 1.0642189025878905,
      "num_input_tokens_seen": 14560795200,
      "step": 51200,
      "train_runtime": 498692.8226,
      "train_tokens_per_second": 29197.924
    },
    {
      "epoch": 1.8119113591784295,
      "grad_norm": 1.515625,
      "learning_rate": 2.0209816125098453e-05,
      "loss": 1.0294891357421876,
      "num_input_tokens_seen": 14563599168,
      "step": 51210,
      "train_runtime": 498787.5493,
      "train_tokens_per_second": 29198.001
    },
    {
      "epoch": 1.812265179442158,
      "grad_norm": 1.5703125,
      "learning_rate": 2.020816544136459e-05,
      "loss": 1.0365999221801758,
      "num_input_tokens_seen": 14566429632,
      "step": 51220,
      "train_runtime": 498883.0826,
      "train_tokens_per_second": 29198.083
    },
    {
      "epoch": 1.812618999705887,
      "grad_norm": 1.5546875,
      "learning_rate": 2.0206515162034965e-05,
      "loss": 1.0311760902404785,
      "num_input_tokens_seen": 14569262720,
      "step": 51230,
      "train_runtime": 498979.4813,
      "train_tokens_per_second": 29198.12
    },
    {
      "epoch": 1.8129728199696156,
      "grad_norm": 1.5625,
      "learning_rate": 2.0204865286944477e-05,
      "loss": 1.0443012237548828,
      "num_input_tokens_seen": 14572097408,
      "step": 51240,
      "train_runtime": 499078.6412,
      "train_tokens_per_second": 29197.998
    },
    {
      "epoch": 1.8133266402333446,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0203215815928123e-05,
      "loss": 1.0509981155395507,
      "num_input_tokens_seen": 14574926208,
      "step": 51250,
      "train_runtime": 499175.7432,
      "train_tokens_per_second": 29197.986
    },
    {
      "epoch": 1.813680460497073,
      "grad_norm": 1.625,
      "learning_rate": 2.0201566748820995e-05,
      "loss": 1.038629913330078,
      "num_input_tokens_seen": 14577741888,
      "step": 51260,
      "train_runtime": 499270.9927,
      "train_tokens_per_second": 29198.055
    },
    {
      "epoch": 1.814034280760802,
      "grad_norm": 1.5390625,
      "learning_rate": 2.019991808545827e-05,
      "loss": 1.0356837272644044,
      "num_input_tokens_seen": 14580565376,
      "step": 51270,
      "train_runtime": 499368.2589,
      "train_tokens_per_second": 29198.022
    },
    {
      "epoch": 1.8143881010245309,
      "grad_norm": 1.5859375,
      "learning_rate": 2.019826982567523e-05,
      "loss": 1.0412332534790039,
      "num_input_tokens_seen": 14583456704,
      "step": 51280,
      "train_runtime": 499469.7744,
      "train_tokens_per_second": 29197.876
    },
    {
      "epoch": 1.8147419212882596,
      "grad_norm": 1.5390625,
      "learning_rate": 2.019662196930725e-05,
      "loss": 1.0636192321777345,
      "num_input_tokens_seen": 14586282368,
      "step": 51290,
      "train_runtime": 499569.1937,
      "train_tokens_per_second": 29197.722
    },
    {
      "epoch": 1.8150957415519884,
      "grad_norm": 1.5625,
      "learning_rate": 2.0194974516189784e-05,
      "loss": 1.038242721557617,
      "num_input_tokens_seen": 14589166144,
      "step": 51300,
      "train_runtime": 499669.0478,
      "train_tokens_per_second": 29197.658
    },
    {
      "epoch": 1.8154495618157171,
      "grad_norm": 1.640625,
      "learning_rate": 2.019332746615841e-05,
      "loss": 1.0383970260620117,
      "num_input_tokens_seen": 14592027904,
      "step": 51310,
      "train_runtime": 499767.3185,
      "train_tokens_per_second": 29197.643
    },
    {
      "epoch": 1.815803382079446,
      "grad_norm": 1.640625,
      "learning_rate": 2.0191680819048758e-05,
      "loss": 1.0508296966552735,
      "num_input_tokens_seen": 14594885632,
      "step": 51320,
      "train_runtime": 499864.944,
      "train_tokens_per_second": 29197.658
    },
    {
      "epoch": 1.8161572023431747,
      "grad_norm": 1.6953125,
      "learning_rate": 2.0190034574696592e-05,
      "loss": 1.0378774642944335,
      "num_input_tokens_seen": 14597692416,
      "step": 51330,
      "train_runtime": 499959.606,
      "train_tokens_per_second": 29197.744
    },
    {
      "epoch": 1.8165110226069034,
      "grad_norm": 1.5625,
      "learning_rate": 2.0188388732937753e-05,
      "loss": 1.0439323425292968,
      "num_input_tokens_seen": 14600551936,
      "step": 51340,
      "train_runtime": 500059.1372,
      "train_tokens_per_second": 29197.651
    },
    {
      "epoch": 1.8168648428706322,
      "grad_norm": 1.609375,
      "learning_rate": 2.0186743293608164e-05,
      "loss": 1.057363510131836,
      "num_input_tokens_seen": 14603393216,
      "step": 51350,
      "train_runtime": 500155.0712,
      "train_tokens_per_second": 29197.731
    },
    {
      "epoch": 1.817218663134361,
      "grad_norm": 1.625,
      "learning_rate": 2.0185098256543866e-05,
      "loss": 1.0470507621765137,
      "num_input_tokens_seen": 14606230912,
      "step": 51360,
      "train_runtime": 500253.918,
      "train_tokens_per_second": 29197.634
    },
    {
      "epoch": 1.8175724833980897,
      "grad_norm": 1.6015625,
      "learning_rate": 2.018345362158098e-05,
      "loss": 1.052962875366211,
      "num_input_tokens_seen": 14609116672,
      "step": 51370,
      "train_runtime": 500351.9405,
      "train_tokens_per_second": 29197.682
    },
    {
      "epoch": 1.8179263036618187,
      "grad_norm": 1.5078125,
      "learning_rate": 2.018180938855571e-05,
      "loss": 1.0452037811279298,
      "num_input_tokens_seen": 14611964800,
      "step": 51380,
      "train_runtime": 500449.6435,
      "train_tokens_per_second": 29197.673
    },
    {
      "epoch": 1.8182801239255473,
      "grad_norm": 1.625,
      "learning_rate": 2.0180165557304377e-05,
      "loss": 1.0401094436645508,
      "num_input_tokens_seen": 14614870656,
      "step": 51390,
      "train_runtime": 500548.4537,
      "train_tokens_per_second": 29197.714
    },
    {
      "epoch": 1.8186339441892763,
      "grad_norm": 1.59375,
      "learning_rate": 2.0178522127663373e-05,
      "loss": 1.0510944366455077,
      "num_input_tokens_seen": 14617749760,
      "step": 51400,
      "train_runtime": 500646.2984,
      "train_tokens_per_second": 29197.759
    },
    {
      "epoch": 1.8189877644530048,
      "grad_norm": 1.46875,
      "learning_rate": 2.0176879099469196e-05,
      "loss": 1.0417635917663575,
      "num_input_tokens_seen": 14620598784,
      "step": 51410,
      "train_runtime": 500744.27,
      "train_tokens_per_second": 29197.736
    },
    {
      "epoch": 1.8193415847167338,
      "grad_norm": 1.5625,
      "learning_rate": 2.0175236472558443e-05,
      "loss": 1.0548954963684083,
      "num_input_tokens_seen": 14623430720,
      "step": 51420,
      "train_runtime": 500840.5475,
      "train_tokens_per_second": 29197.777
    },
    {
      "epoch": 1.8196954049804623,
      "grad_norm": 1.578125,
      "learning_rate": 2.017359424676778e-05,
      "loss": 1.0520763397216797,
      "num_input_tokens_seen": 14626291456,
      "step": 51430,
      "train_runtime": 500938.8916,
      "train_tokens_per_second": 29197.756
    },
    {
      "epoch": 1.8200492252441913,
      "grad_norm": 1.578125,
      "learning_rate": 2.0171952421933997e-05,
      "loss": 1.0492498397827148,
      "num_input_tokens_seen": 14629185536,
      "step": 51440,
      "train_runtime": 501039.4479,
      "train_tokens_per_second": 29197.672
    },
    {
      "epoch": 1.82040304550792,
      "grad_norm": 1.5,
      "learning_rate": 2.017031099789395e-05,
      "loss": 1.0346683502197265,
      "num_input_tokens_seen": 14631982272,
      "step": 51450,
      "train_runtime": 501136.2791,
      "train_tokens_per_second": 29197.611
    },
    {
      "epoch": 1.8207568657716489,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0168669974484606e-05,
      "loss": 1.0459463119506835,
      "num_input_tokens_seen": 14634767872,
      "step": 51460,
      "train_runtime": 501227.8464,
      "train_tokens_per_second": 29197.835
    },
    {
      "epoch": 1.8211106860353776,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0167029351543015e-05,
      "loss": 1.0462090492248535,
      "num_input_tokens_seen": 14637595008,
      "step": 51470,
      "train_runtime": 501324.8891,
      "train_tokens_per_second": 29197.822
    },
    {
      "epoch": 1.8214645062991064,
      "grad_norm": 1.546875,
      "learning_rate": 2.0165389128906324e-05,
      "loss": 1.0340088844299316,
      "num_input_tokens_seen": 14640451712,
      "step": 51480,
      "train_runtime": 501422.454,
      "train_tokens_per_second": 29197.838
    },
    {
      "epoch": 1.8218183265628352,
      "grad_norm": 1.5625,
      "learning_rate": 2.0163749306411775e-05,
      "loss": 1.0535844802856444,
      "num_input_tokens_seen": 14643309056,
      "step": 51490,
      "train_runtime": 501523.8447,
      "train_tokens_per_second": 29197.633
    },
    {
      "epoch": 1.822172146826564,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0162109883896694e-05,
      "loss": 1.0409570693969727,
      "num_input_tokens_seen": 14646130432,
      "step": 51500,
      "train_runtime": 501621.4637,
      "train_tokens_per_second": 29197.575
    },
    {
      "epoch": 1.8225259670902927,
      "grad_norm": 1.5,
      "learning_rate": 2.016047086119851e-05,
      "loss": 1.0397847175598145,
      "num_input_tokens_seen": 14649022720,
      "step": 51510,
      "train_runtime": 501721.2547,
      "train_tokens_per_second": 29197.533
    },
    {
      "epoch": 1.8228797873540215,
      "grad_norm": 1.546875,
      "learning_rate": 2.015883223815473e-05,
      "loss": 1.0342705726623536,
      "num_input_tokens_seen": 14651866240,
      "step": 51520,
      "train_runtime": 501818.1134,
      "train_tokens_per_second": 29197.564
    },
    {
      "epoch": 1.8232336076177504,
      "grad_norm": 1.53125,
      "learning_rate": 2.0157194014602974e-05,
      "loss": 1.0436864852905274,
      "num_input_tokens_seen": 14654656192,
      "step": 51530,
      "train_runtime": 501913.8893,
      "train_tokens_per_second": 29197.551
    },
    {
      "epoch": 1.823587427881479,
      "grad_norm": 1.5,
      "learning_rate": 2.0155556190380938e-05,
      "loss": 1.0517480850219727,
      "num_input_tokens_seen": 14657508992,
      "step": 51540,
      "train_runtime": 502012.2289,
      "train_tokens_per_second": 29197.514
    },
    {
      "epoch": 1.823941248145208,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0153918765326414e-05,
      "loss": 1.0439971923828124,
      "num_input_tokens_seen": 14660358720,
      "step": 51550,
      "train_runtime": 502112.3169,
      "train_tokens_per_second": 29197.369
    },
    {
      "epoch": 1.8242950684089365,
      "grad_norm": 1.65625,
      "learning_rate": 2.0152281739277286e-05,
      "loss": 1.0467494964599608,
      "num_input_tokens_seen": 14663172096,
      "step": 51560,
      "train_runtime": 502207.7565,
      "train_tokens_per_second": 29197.423
    },
    {
      "epoch": 1.8246488886726655,
      "grad_norm": 1.6171875,
      "learning_rate": 2.0150645112071542e-05,
      "loss": 1.0431316375732422,
      "num_input_tokens_seen": 14666016192,
      "step": 51570,
      "train_runtime": 502305.9387,
      "train_tokens_per_second": 29197.378
    },
    {
      "epoch": 1.825002708936394,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0149008883547245e-05,
      "loss": 1.0314371109008789,
      "num_input_tokens_seen": 14668849408,
      "step": 51580,
      "train_runtime": 502403.4196,
      "train_tokens_per_second": 29197.352
    },
    {
      "epoch": 1.825356529200123,
      "grad_norm": 1.59375,
      "learning_rate": 2.0147373053542558e-05,
      "loss": 1.028524112701416,
      "num_input_tokens_seen": 14671720320,
      "step": 51590,
      "train_runtime": 502502.6348,
      "train_tokens_per_second": 29197.3
    },
    {
      "epoch": 1.8257103494638516,
      "grad_norm": 1.5859375,
      "learning_rate": 2.014573762189573e-05,
      "loss": 1.0491708755493163,
      "num_input_tokens_seen": 14674547072,
      "step": 51600,
      "train_runtime": 502597.6644,
      "train_tokens_per_second": 29197.404
    },
    {
      "epoch": 1.8260641697275806,
      "grad_norm": 1.578125,
      "learning_rate": 2.0144102588445116e-05,
      "loss": 1.0468650817871095,
      "num_input_tokens_seen": 14677419392,
      "step": 51610,
      "train_runtime": 502697.9296,
      "train_tokens_per_second": 29197.294
    },
    {
      "epoch": 1.8264179899913093,
      "grad_norm": 1.5703125,
      "learning_rate": 2.014246795302915e-05,
      "loss": 1.0587779998779296,
      "num_input_tokens_seen": 14680263424,
      "step": 51620,
      "train_runtime": 502797.2572,
      "train_tokens_per_second": 29197.183
    },
    {
      "epoch": 1.826771810255038,
      "grad_norm": 1.53125,
      "learning_rate": 2.0140833715486358e-05,
      "loss": 1.0538188934326171,
      "num_input_tokens_seen": 14683072576,
      "step": 51630,
      "train_runtime": 502891.4476,
      "train_tokens_per_second": 29197.3
    },
    {
      "epoch": 1.8271256305187669,
      "grad_norm": 1.5703125,
      "learning_rate": 2.013919987565536e-05,
      "loss": 1.0453543663024902,
      "num_input_tokens_seen": 14685962816,
      "step": 51640,
      "train_runtime": 502992.8032,
      "train_tokens_per_second": 29197.163
    },
    {
      "epoch": 1.8274794507824956,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0137566433374875e-05,
      "loss": 1.0611413955688476,
      "num_input_tokens_seen": 14688814784,
      "step": 51650,
      "train_runtime": 503089.3726,
      "train_tokens_per_second": 29197.227
    },
    {
      "epoch": 1.8278332710462244,
      "grad_norm": 1.6484375,
      "learning_rate": 2.0135933388483708e-05,
      "loss": 1.0337538719177246,
      "num_input_tokens_seen": 14691624512,
      "step": 51660,
      "train_runtime": 503184.4293,
      "train_tokens_per_second": 29197.296
    },
    {
      "epoch": 1.8281870913099532,
      "grad_norm": 1.453125,
      "learning_rate": 2.0134300740820746e-05,
      "loss": 1.0425182342529298,
      "num_input_tokens_seen": 14694446016,
      "step": 51670,
      "train_runtime": 503280.003,
      "train_tokens_per_second": 29197.357
    },
    {
      "epoch": 1.828540911573682,
      "grad_norm": 1.5625,
      "learning_rate": 2.0132668490224984e-05,
      "loss": 1.034316635131836,
      "num_input_tokens_seen": 14697304640,
      "step": 51680,
      "train_runtime": 503377.4958,
      "train_tokens_per_second": 29197.381
    },
    {
      "epoch": 1.8288947318374107,
      "grad_norm": 1.484375,
      "learning_rate": 2.0131036636535498e-05,
      "loss": 1.0368898391723633,
      "num_input_tokens_seen": 14700168192,
      "step": 51690,
      "train_runtime": 503476.3983,
      "train_tokens_per_second": 29197.333
    },
    {
      "epoch": 1.8292485521011397,
      "grad_norm": 1.5625,
      "learning_rate": 2.012940517959146e-05,
      "loss": 1.0418512344360351,
      "num_input_tokens_seen": 14703018816,
      "step": 51700,
      "train_runtime": 503571.9849,
      "train_tokens_per_second": 29197.452
    },
    {
      "epoch": 1.8296023723648682,
      "grad_norm": 1.609375,
      "learning_rate": 2.0127774119232128e-05,
      "loss": 1.0547548294067384,
      "num_input_tokens_seen": 14705870720,
      "step": 51710,
      "train_runtime": 503668.7778,
      "train_tokens_per_second": 29197.503
    },
    {
      "epoch": 1.8299561926285972,
      "grad_norm": 1.59375,
      "learning_rate": 2.0126143455296853e-05,
      "loss": 1.0333142280578613,
      "num_input_tokens_seen": 14708772032,
      "step": 51720,
      "train_runtime": 503769.4174,
      "train_tokens_per_second": 29197.429
    },
    {
      "epoch": 1.8303100128923258,
      "grad_norm": 1.609375,
      "learning_rate": 2.012451318762508e-05,
      "loss": 1.0409263610839843,
      "num_input_tokens_seen": 14711634496,
      "step": 51730,
      "train_runtime": 503867.1251,
      "train_tokens_per_second": 29197.449
    },
    {
      "epoch": 1.8306638331560547,
      "grad_norm": 1.546875,
      "learning_rate": 2.0122883316056348e-05,
      "loss": 1.04263916015625,
      "num_input_tokens_seen": 14714460160,
      "step": 51740,
      "train_runtime": 503963.4873,
      "train_tokens_per_second": 29197.473
    },
    {
      "epoch": 1.8310176534197833,
      "grad_norm": 1.5,
      "learning_rate": 2.0121253840430276e-05,
      "loss": 1.0307008743286132,
      "num_input_tokens_seen": 14717380800,
      "step": 51750,
      "train_runtime": 504065.9683,
      "train_tokens_per_second": 29197.331
    },
    {
      "epoch": 1.8313714736835123,
      "grad_norm": 1.5234375,
      "learning_rate": 2.0119624760586583e-05,
      "loss": 1.047711181640625,
      "num_input_tokens_seen": 14720253952,
      "step": 51760,
      "train_runtime": 504164.8552,
      "train_tokens_per_second": 29197.303
    },
    {
      "epoch": 1.8317252939472408,
      "grad_norm": 1.5625,
      "learning_rate": 2.0117996076365077e-05,
      "loss": 1.0437042236328125,
      "num_input_tokens_seen": 14723105536,
      "step": 51770,
      "train_runtime": 504262.3586,
      "train_tokens_per_second": 29197.312
    },
    {
      "epoch": 1.8320791142109698,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0116367787605653e-05,
      "loss": 1.0339778900146483,
      "num_input_tokens_seen": 14725951360,
      "step": 51780,
      "train_runtime": 504360.3145,
      "train_tokens_per_second": 29197.284
    },
    {
      "epoch": 1.8324329344746986,
      "grad_norm": 1.6171875,
      "learning_rate": 2.01147398941483e-05,
      "loss": 1.0321468353271483,
      "num_input_tokens_seen": 14728826624,
      "step": 51790,
      "train_runtime": 504458.8143,
      "train_tokens_per_second": 29197.283
    },
    {
      "epoch": 1.8327867547384273,
      "grad_norm": 1.6015625,
      "learning_rate": 2.01131123958331e-05,
      "loss": 1.0399364471435546,
      "num_input_tokens_seen": 14731645760,
      "step": 51800,
      "train_runtime": 504551.2647,
      "train_tokens_per_second": 29197.52
    },
    {
      "epoch": 1.833140575002156,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0111485292500217e-05,
      "loss": 1.0426036834716796,
      "num_input_tokens_seen": 14734529472,
      "step": 51810,
      "train_runtime": 504649.8135,
      "train_tokens_per_second": 29197.533
    },
    {
      "epoch": 1.8334943952658849,
      "grad_norm": 1.5390625,
      "learning_rate": 2.010985858398992e-05,
      "loss": 1.043788528442383,
      "num_input_tokens_seen": 14737382208,
      "step": 51820,
      "train_runtime": 504746.6455,
      "train_tokens_per_second": 29197.583
    },
    {
      "epoch": 1.8338482155296136,
      "grad_norm": 1.6640625,
      "learning_rate": 2.0108232270142547e-05,
      "loss": 1.0479053497314452,
      "num_input_tokens_seen": 14740214656,
      "step": 51830,
      "train_runtime": 504844.2525,
      "train_tokens_per_second": 29197.549
    },
    {
      "epoch": 1.8342020357933424,
      "grad_norm": 1.546875,
      "learning_rate": 2.0106606350798547e-05,
      "loss": 1.0432571411132812,
      "num_input_tokens_seen": 14743062976,
      "step": 51840,
      "train_runtime": 504943.255,
      "train_tokens_per_second": 29197.465
    },
    {
      "epoch": 1.8345558560570712,
      "grad_norm": 1.53125,
      "learning_rate": 2.0104980825798458e-05,
      "loss": 1.0279623985290527,
      "num_input_tokens_seen": 14745890688,
      "step": 51850,
      "train_runtime": 505036.816,
      "train_tokens_per_second": 29197.655
    },
    {
      "epoch": 1.8349096763208,
      "grad_norm": 1.609375,
      "learning_rate": 2.0103355694982888e-05,
      "loss": 1.045193576812744,
      "num_input_tokens_seen": 14748708992,
      "step": 51860,
      "train_runtime": 505131.4694,
      "train_tokens_per_second": 29197.763
    },
    {
      "epoch": 1.835263496584529,
      "grad_norm": 1.5234375,
      "learning_rate": 2.010173095819256e-05,
      "loss": 1.0485448837280273,
      "num_input_tokens_seen": 14751567872,
      "step": 51870,
      "train_runtime": 505232.1501,
      "train_tokens_per_second": 29197.603
    },
    {
      "epoch": 1.8356173168482575,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0100106615268267e-05,
      "loss": 1.0435639381408692,
      "num_input_tokens_seen": 14754377344,
      "step": 51880,
      "train_runtime": 505328.7227,
      "train_tokens_per_second": 29197.583
    },
    {
      "epoch": 1.8359711371119865,
      "grad_norm": 1.578125,
      "learning_rate": 2.0098482666050902e-05,
      "loss": 1.048586368560791,
      "num_input_tokens_seen": 14757212480,
      "step": 51890,
      "train_runtime": 505428.6674,
      "train_tokens_per_second": 29197.419
    },
    {
      "epoch": 1.836324957375715,
      "grad_norm": 1.5625,
      "learning_rate": 2.009685911038145e-05,
      "loss": 1.0303977966308593,
      "num_input_tokens_seen": 14760058624,
      "step": 51900,
      "train_runtime": 505525.2278,
      "train_tokens_per_second": 29197.472
    },
    {
      "epoch": 1.836678777639444,
      "grad_norm": 1.5625,
      "learning_rate": 2.0095235948100982e-05,
      "loss": 1.0451906204223633,
      "num_input_tokens_seen": 14762878976,
      "step": 51910,
      "train_runtime": 505619.859,
      "train_tokens_per_second": 29197.585
    },
    {
      "epoch": 1.8370325979031725,
      "grad_norm": 1.6484375,
      "learning_rate": 2.0093613179050662e-05,
      "loss": 1.046688938140869,
      "num_input_tokens_seen": 14765716864,
      "step": 51920,
      "train_runtime": 505716.7726,
      "train_tokens_per_second": 29197.602
    },
    {
      "epoch": 1.8373864181669015,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0091990803071733e-05,
      "loss": 1.0450884819030761,
      "num_input_tokens_seen": 14768661952,
      "step": 51930,
      "train_runtime": 505820.8839,
      "train_tokens_per_second": 29197.414
    },
    {
      "epoch": 1.83774023843063,
      "grad_norm": 1.6015625,
      "learning_rate": 2.009036882000554e-05,
      "loss": 1.0423538208007812,
      "num_input_tokens_seen": 14771459328,
      "step": 51940,
      "train_runtime": 505914.1719,
      "train_tokens_per_second": 29197.56
    },
    {
      "epoch": 1.838094058694359,
      "grad_norm": 1.5859375,
      "learning_rate": 2.008874722969352e-05,
      "loss": 1.0451613426208497,
      "num_input_tokens_seen": 14774306688,
      "step": 51950,
      "train_runtime": 506014.2802,
      "train_tokens_per_second": 29197.411
    },
    {
      "epoch": 1.8384478789580878,
      "grad_norm": 1.5625,
      "learning_rate": 2.0087126031977192e-05,
      "loss": 1.05203218460083,
      "num_input_tokens_seen": 14777162176,
      "step": 51960,
      "train_runtime": 506111.3558,
      "train_tokens_per_second": 29197.452
    },
    {
      "epoch": 1.8388016992218166,
      "grad_norm": 1.5625,
      "learning_rate": 2.008550522669815e-05,
      "loss": 1.0339105606079102,
      "num_input_tokens_seen": 14779979264,
      "step": 51970,
      "train_runtime": 506208.0553,
      "train_tokens_per_second": 29197.44
    },
    {
      "epoch": 1.8391555194855453,
      "grad_norm": 1.640625,
      "learning_rate": 2.0083884813698114e-05,
      "loss": 1.0527472496032715,
      "num_input_tokens_seen": 14782824768,
      "step": 51980,
      "train_runtime": 506304.6854,
      "train_tokens_per_second": 29197.488
    },
    {
      "epoch": 1.839509339749274,
      "grad_norm": 1.578125,
      "learning_rate": 2.008226479281886e-05,
      "loss": 1.0303709983825684,
      "num_input_tokens_seen": 14785633472,
      "step": 51990,
      "train_runtime": 506400.5495,
      "train_tokens_per_second": 29197.507
    },
    {
      "epoch": 1.8398631600130029,
      "grad_norm": 1.5625,
      "learning_rate": 2.008064516390227e-05,
      "loss": 1.0445036888122559,
      "num_input_tokens_seen": 14788486272,
      "step": 52000,
      "train_runtime": 506497.2499,
      "train_tokens_per_second": 29197.565
    },
    {
      "epoch": 1.8402169802767316,
      "grad_norm": 1.578125,
      "learning_rate": 2.0079025926790312e-05,
      "loss": 1.0370040893554688,
      "num_input_tokens_seen": 14791354112,
      "step": 52010,
      "train_runtime": 506595.112,
      "train_tokens_per_second": 29197.586
    },
    {
      "epoch": 1.8405708005404604,
      "grad_norm": 1.625,
      "learning_rate": 2.007740708132504e-05,
      "loss": 1.0363029479980468,
      "num_input_tokens_seen": 14794183552,
      "step": 52020,
      "train_runtime": 506694.5507,
      "train_tokens_per_second": 29197.44
    },
    {
      "epoch": 1.8409246208041892,
      "grad_norm": 1.640625,
      "learning_rate": 2.0075788627348595e-05,
      "loss": 1.0445004463195802,
      "num_input_tokens_seen": 14797066048,
      "step": 52030,
      "train_runtime": 506793.5188,
      "train_tokens_per_second": 29197.426
    },
    {
      "epoch": 1.8412784410679182,
      "grad_norm": 1.5859375,
      "learning_rate": 2.007417056470322e-05,
      "loss": 1.0487873077392578,
      "num_input_tokens_seen": 14799977664,
      "step": 52040,
      "train_runtime": 506894.0107,
      "train_tokens_per_second": 29197.381
    },
    {
      "epoch": 1.8416322613316467,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0072552893231236e-05,
      "loss": 1.0380552291870118,
      "num_input_tokens_seen": 14802843776,
      "step": 52050,
      "train_runtime": 506992.4511,
      "train_tokens_per_second": 29197.365
    },
    {
      "epoch": 1.8419860815953757,
      "grad_norm": 1.53125,
      "learning_rate": 2.0070935612775056e-05,
      "loss": 1.0303022384643554,
      "num_input_tokens_seen": 14805666496,
      "step": 52060,
      "train_runtime": 507088.0139,
      "train_tokens_per_second": 29197.429
    },
    {
      "epoch": 1.8423399018591042,
      "grad_norm": 1.578125,
      "learning_rate": 2.006931872317718e-05,
      "loss": 1.045656108856201,
      "num_input_tokens_seen": 14808541888,
      "step": 52070,
      "train_runtime": 507189.2107,
      "train_tokens_per_second": 29197.273
    },
    {
      "epoch": 1.8426937221228332,
      "grad_norm": 1.640625,
      "learning_rate": 2.0067702224280192e-05,
      "loss": 1.043748950958252,
      "num_input_tokens_seen": 14811345728,
      "step": 52080,
      "train_runtime": 507282.502,
      "train_tokens_per_second": 29197.431
    },
    {
      "epoch": 1.8430475423865618,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0066086115926782e-05,
      "loss": 1.034750747680664,
      "num_input_tokens_seen": 14814217152,
      "step": 52090,
      "train_runtime": 507380.3484,
      "train_tokens_per_second": 29197.459
    },
    {
      "epoch": 1.8434013626502908,
      "grad_norm": 1.625,
      "learning_rate": 2.0064470397959713e-05,
      "loss": 1.0458473205566405,
      "num_input_tokens_seen": 14817025984,
      "step": 52100,
      "train_runtime": 507475.8014,
      "train_tokens_per_second": 29197.503
    },
    {
      "epoch": 1.8437551829140195,
      "grad_norm": 1.5625,
      "learning_rate": 2.0062855070221834e-05,
      "loss": 1.0320871353149415,
      "num_input_tokens_seen": 14819859648,
      "step": 52110,
      "train_runtime": 507572.8711,
      "train_tokens_per_second": 29197.501
    },
    {
      "epoch": 1.8441090031777483,
      "grad_norm": 1.578125,
      "learning_rate": 2.0061240132556102e-05,
      "loss": 1.0385744094848632,
      "num_input_tokens_seen": 14822672128,
      "step": 52120,
      "train_runtime": 507669.1589,
      "train_tokens_per_second": 29197.504
    },
    {
      "epoch": 1.844462823441477,
      "grad_norm": 1.515625,
      "learning_rate": 2.0059625584805542e-05,
      "loss": 1.0346109390258789,
      "num_input_tokens_seen": 14825601920,
      "step": 52130,
      "train_runtime": 507772.9094,
      "train_tokens_per_second": 29197.308
    },
    {
      "epoch": 1.8448166437052058,
      "grad_norm": 1.546875,
      "learning_rate": 2.0058011426813275e-05,
      "loss": 1.0366310119628905,
      "num_input_tokens_seen": 14828473088,
      "step": 52140,
      "train_runtime": 507874.2741,
      "train_tokens_per_second": 29197.134
    },
    {
      "epoch": 1.8451704639689346,
      "grad_norm": 1.59375,
      "learning_rate": 2.0056397658422517e-05,
      "loss": 1.0524778366088867,
      "num_input_tokens_seen": 14831337536,
      "step": 52150,
      "train_runtime": 507973.2337,
      "train_tokens_per_second": 29197.085
    },
    {
      "epoch": 1.8455242842326633,
      "grad_norm": 1.625,
      "learning_rate": 2.005478427947656e-05,
      "loss": 1.0503826141357422,
      "num_input_tokens_seen": 14834190336,
      "step": 52160,
      "train_runtime": 508070.3556,
      "train_tokens_per_second": 29197.118
    },
    {
      "epoch": 1.8458781044963921,
      "grad_norm": 1.5390625,
      "learning_rate": 2.005317128981879e-05,
      "loss": 1.0673009872436523,
      "num_input_tokens_seen": 14837054976,
      "step": 52170,
      "train_runtime": 508171.5615,
      "train_tokens_per_second": 29196.941
    },
    {
      "epoch": 1.8462319247601209,
      "grad_norm": 1.6015625,
      "learning_rate": 2.005155868929269e-05,
      "loss": 1.0425497055053712,
      "num_input_tokens_seen": 14839866816,
      "step": 52180,
      "train_runtime": 508267.3256,
      "train_tokens_per_second": 29196.972
    },
    {
      "epoch": 1.8465857450238496,
      "grad_norm": 1.5859375,
      "learning_rate": 2.0049946477741817e-05,
      "loss": 1.037805938720703,
      "num_input_tokens_seen": 14842770944,
      "step": 52190,
      "train_runtime": 508368.043,
      "train_tokens_per_second": 29196.9
    },
    {
      "epoch": 1.8469395652875784,
      "grad_norm": 1.53125,
      "learning_rate": 2.0048334655009818e-05,
      "loss": 1.0417848587036134,
      "num_input_tokens_seen": 14845628288,
      "step": 52200,
      "train_runtime": 508463.0235,
      "train_tokens_per_second": 29197.066
    },
    {
      "epoch": 1.8472933855513074,
      "grad_norm": 1.5625,
      "learning_rate": 2.004672322094043e-05,
      "loss": 1.0489841461181642,
      "num_input_tokens_seen": 14848459520,
      "step": 52210,
      "train_runtime": 508557.2734,
      "train_tokens_per_second": 29197.222
    },
    {
      "epoch": 1.847647205815036,
      "grad_norm": 1.6171875,
      "learning_rate": 2.00451121753775e-05,
      "loss": 1.0454236030578614,
      "num_input_tokens_seen": 14851264192,
      "step": 52220,
      "train_runtime": 508652.0865,
      "train_tokens_per_second": 29197.293
    },
    {
      "epoch": 1.848001026078765,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0043501518164916e-05,
      "loss": 1.0397187232971192,
      "num_input_tokens_seen": 14854066368,
      "step": 52230,
      "train_runtime": 508745.8713,
      "train_tokens_per_second": 29197.419
    },
    {
      "epoch": 1.8483548463424935,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0041891249146692e-05,
      "loss": 1.0382884979248046,
      "num_input_tokens_seen": 14856942720,
      "step": 52240,
      "train_runtime": 508845.8719,
      "train_tokens_per_second": 29197.334
    },
    {
      "epoch": 1.8487086666062225,
      "grad_norm": 1.6328125,
      "learning_rate": 2.0040281368166923e-05,
      "loss": 1.0552717208862306,
      "num_input_tokens_seen": 14859740992,
      "step": 52250,
      "train_runtime": 508940.7851,
      "train_tokens_per_second": 29197.387
    },
    {
      "epoch": 1.849062486869951,
      "grad_norm": 1.609375,
      "learning_rate": 2.0038671875069774e-05,
      "loss": 1.0455099105834962,
      "num_input_tokens_seen": 14862599808,
      "step": 52260,
      "train_runtime": 509041.1939,
      "train_tokens_per_second": 29197.244
    },
    {
      "epoch": 1.84941630713368,
      "grad_norm": 1.59375,
      "learning_rate": 2.0037062769699525e-05,
      "loss": 1.0445660591125487,
      "num_input_tokens_seen": 14865442304,
      "step": 52270,
      "train_runtime": 509139.4289,
      "train_tokens_per_second": 29197.193
    },
    {
      "epoch": 1.8497701273974088,
      "grad_norm": 1.546875,
      "learning_rate": 2.0035454051900516e-05,
      "loss": 1.0431885719299316,
      "num_input_tokens_seen": 14868314304,
      "step": 52280,
      "train_runtime": 509238.0069,
      "train_tokens_per_second": 29197.181
    },
    {
      "epoch": 1.8501239476611375,
      "grad_norm": 1.5234375,
      "learning_rate": 2.003384572151719e-05,
      "loss": 1.0481454849243164,
      "num_input_tokens_seen": 14871239232,
      "step": 52290,
      "train_runtime": 509338.6177,
      "train_tokens_per_second": 29197.156
    },
    {
      "epoch": 1.8504777679248663,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0032237778394082e-05,
      "loss": 1.0423768997192382,
      "num_input_tokens_seen": 14874111104,
      "step": 52300,
      "train_runtime": 509435.6785,
      "train_tokens_per_second": 29197.231
    },
    {
      "epoch": 1.850831588188595,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0030630222375794e-05,
      "loss": 1.0550924301147462,
      "num_input_tokens_seen": 14876953088,
      "step": 52310,
      "train_runtime": 509533.6353,
      "train_tokens_per_second": 29197.195
    },
    {
      "epoch": 1.8511854084523238,
      "grad_norm": 1.5625,
      "learning_rate": 2.0029023053307043e-05,
      "loss": 1.0483924865722656,
      "num_input_tokens_seen": 14879821632,
      "step": 52320,
      "train_runtime": 509633.4089,
      "train_tokens_per_second": 29197.108
    },
    {
      "epoch": 1.8515392287160526,
      "grad_norm": 1.4765625,
      "learning_rate": 2.0027416271032604e-05,
      "loss": 1.0359944343566894,
      "num_input_tokens_seen": 14882681024,
      "step": 52330,
      "train_runtime": 509730.7759,
      "train_tokens_per_second": 29197.14
    },
    {
      "epoch": 1.8518930489797814,
      "grad_norm": 1.6015625,
      "learning_rate": 2.0025809875397362e-05,
      "loss": 1.0570131301879884,
      "num_input_tokens_seen": 14885498688,
      "step": 52340,
      "train_runtime": 509828.037,
      "train_tokens_per_second": 29197.097
    },
    {
      "epoch": 1.8522468692435101,
      "grad_norm": 1.53125,
      "learning_rate": 2.002420386624628e-05,
      "loss": 1.064437198638916,
      "num_input_tokens_seen": 14888316288,
      "step": 52350,
      "train_runtime": 509923.4993,
      "train_tokens_per_second": 29197.157
    },
    {
      "epoch": 1.852600689507239,
      "grad_norm": 1.625,
      "learning_rate": 2.0022598243424406e-05,
      "loss": 1.0421026229858399,
      "num_input_tokens_seen": 14891132864,
      "step": 52360,
      "train_runtime": 510018.5921,
      "train_tokens_per_second": 29197.235
    },
    {
      "epoch": 1.8529545097709677,
      "grad_norm": 1.578125,
      "learning_rate": 2.0020993006776878e-05,
      "loss": 1.0399102210998534,
      "num_input_tokens_seen": 14893995456,
      "step": 52370,
      "train_runtime": 510117.2599,
      "train_tokens_per_second": 29197.2
    },
    {
      "epoch": 1.8533083300346966,
      "grad_norm": 1.4921875,
      "learning_rate": 2.0019388156148922e-05,
      "loss": 1.0542527198791505,
      "num_input_tokens_seen": 14896844864,
      "step": 52380,
      "train_runtime": 510213.3919,
      "train_tokens_per_second": 29197.283
    },
    {
      "epoch": 1.8536621502984252,
      "grad_norm": 1.5625,
      "learning_rate": 2.001778369138585e-05,
      "loss": 1.0476877212524414,
      "num_input_tokens_seen": 14899698176,
      "step": 52390,
      "train_runtime": 510310.4664,
      "train_tokens_per_second": 29197.32
    },
    {
      "epoch": 1.8540159705621542,
      "grad_norm": 1.53125,
      "learning_rate": 2.001617961233306e-05,
      "loss": 1.0468734741210937,
      "num_input_tokens_seen": 14902509760,
      "step": 52400,
      "train_runtime": 510408.6807,
      "train_tokens_per_second": 29197.211
    },
    {
      "epoch": 1.8543697908258827,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0014575918836026e-05,
      "loss": 1.0497058868408202,
      "num_input_tokens_seen": 14905346752,
      "step": 52410,
      "train_runtime": 510503.2478,
      "train_tokens_per_second": 29197.359
    },
    {
      "epoch": 1.8547236110896117,
      "grad_norm": 1.5625,
      "learning_rate": 2.0012972610740336e-05,
      "loss": 1.0388196945190429,
      "num_input_tokens_seen": 14908187008,
      "step": 52420,
      "train_runtime": 510599.4398,
      "train_tokens_per_second": 29197.421
    },
    {
      "epoch": 1.8550774313533402,
      "grad_norm": 1.5703125,
      "learning_rate": 2.001136968789164e-05,
      "loss": 1.0317584037780763,
      "num_input_tokens_seen": 14911065536,
      "step": 52430,
      "train_runtime": 510697.828,
      "train_tokens_per_second": 29197.433
    },
    {
      "epoch": 1.8554312516170692,
      "grad_norm": 1.5390625,
      "learning_rate": 2.000976715013568e-05,
      "loss": 1.0462995529174806,
      "num_input_tokens_seen": 14913905792,
      "step": 52440,
      "train_runtime": 510793.649,
      "train_tokens_per_second": 29197.516
    },
    {
      "epoch": 1.855785071880798,
      "grad_norm": 1.53125,
      "learning_rate": 2.0008164997318294e-05,
      "loss": 1.0523185729980469,
      "num_input_tokens_seen": 14916731520,
      "step": 52450,
      "train_runtime": 510889.9194,
      "train_tokens_per_second": 29197.545
    },
    {
      "epoch": 1.8561388921445268,
      "grad_norm": 1.5625,
      "learning_rate": 2.000656322928539e-05,
      "loss": 1.0413409233093263,
      "num_input_tokens_seen": 14919531776,
      "step": 52460,
      "train_runtime": 510985.1243,
      "train_tokens_per_second": 29197.585
    },
    {
      "epoch": 1.8564927124082555,
      "grad_norm": 1.5390625,
      "learning_rate": 2.000496184588298e-05,
      "loss": 1.043079662322998,
      "num_input_tokens_seen": 14922358592,
      "step": 52470,
      "train_runtime": 511084.2011,
      "train_tokens_per_second": 29197.456
    },
    {
      "epoch": 1.8568465326719843,
      "grad_norm": 1.5703125,
      "learning_rate": 2.0003360846957154e-05,
      "loss": 1.0452932357788085,
      "num_input_tokens_seen": 14925212928,
      "step": 52480,
      "train_runtime": 511182.4988,
      "train_tokens_per_second": 29197.426
    },
    {
      "epoch": 1.857200352935713,
      "grad_norm": 1.5390625,
      "learning_rate": 2.0001760232354076e-05,
      "loss": 1.0442402839660645,
      "num_input_tokens_seen": 14928026944,
      "step": 52490,
      "train_runtime": 511275.7474,
      "train_tokens_per_second": 29197.604
    },
    {
      "epoch": 1.8575541731994418,
      "grad_norm": 1.5078125,
      "learning_rate": 2.0000160001920026e-05,
      "loss": 1.0527508735656739,
      "num_input_tokens_seen": 14930867008,
      "step": 52500,
      "train_runtime": 511372.3867,
      "train_tokens_per_second": 29197.64
    },
    {
      "epoch": 1.8579079934631706,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9998560155501343e-05,
      "loss": 1.0397061347961425,
      "num_input_tokens_seen": 14933773568,
      "step": 52510,
      "train_runtime": 511476.2425,
      "train_tokens_per_second": 29197.394
    },
    {
      "epoch": 1.8582618137268994,
      "grad_norm": 1.53125,
      "learning_rate": 1.9996960692944456e-05,
      "loss": 1.044118881225586,
      "num_input_tokens_seen": 14936665216,
      "step": 52520,
      "train_runtime": 511577.123,
      "train_tokens_per_second": 29197.289
    },
    {
      "epoch": 1.8586156339906283,
      "grad_norm": 1.59375,
      "learning_rate": 1.9995361614095893e-05,
      "loss": 1.0353090286254882,
      "num_input_tokens_seen": 14939450240,
      "step": 52530,
      "train_runtime": 511672.7221,
      "train_tokens_per_second": 29197.277
    },
    {
      "epoch": 1.858969454254357,
      "grad_norm": 1.546875,
      "learning_rate": 1.9993762918802263e-05,
      "loss": 1.0530210494995118,
      "num_input_tokens_seen": 14942286464,
      "step": 52540,
      "train_runtime": 511769.1059,
      "train_tokens_per_second": 29197.32
    },
    {
      "epoch": 1.8593232745180859,
      "grad_norm": 1.59375,
      "learning_rate": 1.9992164606910253e-05,
      "loss": 1.0539814949035644,
      "num_input_tokens_seen": 14945110144,
      "step": 52550,
      "train_runtime": 511863.0419,
      "train_tokens_per_second": 29197.478
    },
    {
      "epoch": 1.8596770947818144,
      "grad_norm": 1.6015625,
      "learning_rate": 1.999056667826664e-05,
      "loss": 1.0307307243347168,
      "num_input_tokens_seen": 14947939904,
      "step": 52560,
      "train_runtime": 511958.7727,
      "train_tokens_per_second": 29197.546
    },
    {
      "epoch": 1.8600309150455434,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9988969132718285e-05,
      "loss": 1.0452447891235352,
      "num_input_tokens_seen": 14950793920,
      "step": 52570,
      "train_runtime": 512055.261,
      "train_tokens_per_second": 29197.618
    },
    {
      "epoch": 1.860384735309272,
      "grad_norm": 1.5234375,
      "learning_rate": 1.9987371970112145e-05,
      "loss": 1.034015941619873,
      "num_input_tokens_seen": 14953684864,
      "step": 52580,
      "train_runtime": 512154.8245,
      "train_tokens_per_second": 29197.587
    },
    {
      "epoch": 1.860738555573001,
      "grad_norm": 1.5625,
      "learning_rate": 1.998577519029525e-05,
      "loss": 1.0378585815429688,
      "num_input_tokens_seen": 14956571904,
      "step": 52590,
      "train_runtime": 512255.173,
      "train_tokens_per_second": 29197.503
    },
    {
      "epoch": 1.8610923758367295,
      "grad_norm": 1.625,
      "learning_rate": 1.9984178793114727e-05,
      "loss": 1.0414339065551759,
      "num_input_tokens_seen": 14959440576,
      "step": 52600,
      "train_runtime": 512353.9287,
      "train_tokens_per_second": 29197.474
    },
    {
      "epoch": 1.8614461961004585,
      "grad_norm": 1.546875,
      "learning_rate": 1.9982582778417768e-05,
      "loss": 1.0509407997131348,
      "num_input_tokens_seen": 14962240768,
      "step": 52610,
      "train_runtime": 512449.1819,
      "train_tokens_per_second": 29197.511
    },
    {
      "epoch": 1.8618000163641872,
      "grad_norm": 1.5234375,
      "learning_rate": 1.9980987146051677e-05,
      "loss": 1.0383895874023437,
      "num_input_tokens_seen": 14965126656,
      "step": 52620,
      "train_runtime": 512550.815,
      "train_tokens_per_second": 29197.352
    },
    {
      "epoch": 1.862153836627916,
      "grad_norm": 1.5625,
      "learning_rate": 1.9979391895863827e-05,
      "loss": 1.0555732727050782,
      "num_input_tokens_seen": 14967964416,
      "step": 52630,
      "train_runtime": 512645.8905,
      "train_tokens_per_second": 29197.473
    },
    {
      "epoch": 1.8625076568916448,
      "grad_norm": 1.5703125,
      "learning_rate": 1.997779702770168e-05,
      "loss": 1.040258026123047,
      "num_input_tokens_seen": 14970794816,
      "step": 52640,
      "train_runtime": 512741.7674,
      "train_tokens_per_second": 29197.533
    },
    {
      "epoch": 1.8628614771553735,
      "grad_norm": 1.53125,
      "learning_rate": 1.997620254141278e-05,
      "loss": 1.0489641189575196,
      "num_input_tokens_seen": 14973588160,
      "step": 52650,
      "train_runtime": 512835.02,
      "train_tokens_per_second": 29197.671
    },
    {
      "epoch": 1.8632152974191023,
      "grad_norm": 1.578125,
      "learning_rate": 1.997460843684476e-05,
      "loss": 1.0352008819580079,
      "num_input_tokens_seen": 14976479104,
      "step": 52660,
      "train_runtime": 512935.4777,
      "train_tokens_per_second": 29197.589
    },
    {
      "epoch": 1.863569117682831,
      "grad_norm": 1.5703125,
      "learning_rate": 1.997301471384534e-05,
      "loss": 1.0511030197143554,
      "num_input_tokens_seen": 14979315392,
      "step": 52670,
      "train_runtime": 513032.6538,
      "train_tokens_per_second": 29197.587
    },
    {
      "epoch": 1.8639229379465598,
      "grad_norm": 1.59375,
      "learning_rate": 1.997142137226232e-05,
      "loss": 1.0293703079223633,
      "num_input_tokens_seen": 14982132672,
      "step": 52680,
      "train_runtime": 513126.0189,
      "train_tokens_per_second": 29197.765
    },
    {
      "epoch": 1.8642767582102886,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9969828411943588e-05,
      "loss": 1.0369377136230469,
      "num_input_tokens_seen": 14984967808,
      "step": 52690,
      "train_runtime": 513221.2946,
      "train_tokens_per_second": 29197.868
    },
    {
      "epoch": 1.8646305784740176,
      "grad_norm": 1.609375,
      "learning_rate": 1.9968235832737117e-05,
      "loss": 1.0452211380004883,
      "num_input_tokens_seen": 14987848256,
      "step": 52700,
      "train_runtime": 513320.2832,
      "train_tokens_per_second": 29197.849
    },
    {
      "epoch": 1.8649843987377461,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9966643634490965e-05,
      "loss": 1.0504636764526367,
      "num_input_tokens_seen": 14990697344,
      "step": 52710,
      "train_runtime": 513417.8358,
      "train_tokens_per_second": 29197.851
    },
    {
      "epoch": 1.8653382190014751,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9965051817053272e-05,
      "loss": 1.0321514129638671,
      "num_input_tokens_seen": 14993497344,
      "step": 52720,
      "train_runtime": 513515.5204,
      "train_tokens_per_second": 29197.749
    },
    {
      "epoch": 1.8656920392652037,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9963460380272264e-05,
      "loss": 1.0420095443725585,
      "num_input_tokens_seen": 14996344832,
      "step": 52730,
      "train_runtime": 513612.8711,
      "train_tokens_per_second": 29197.759
    },
    {
      "epoch": 1.8660458595289326,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9961869323996253e-05,
      "loss": 1.0237188339233398,
      "num_input_tokens_seen": 14999178816,
      "step": 52740,
      "train_runtime": 513708.1459,
      "train_tokens_per_second": 29197.861
    },
    {
      "epoch": 1.8663996797926612,
      "grad_norm": 1.65625,
      "learning_rate": 1.996027864807364e-05,
      "loss": 1.0382715225219727,
      "num_input_tokens_seen": 15002017408,
      "step": 52750,
      "train_runtime": 513804.4794,
      "train_tokens_per_second": 29197.911
    },
    {
      "epoch": 1.8667535000563902,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9958688352352895e-05,
      "loss": 1.0614127159118651,
      "num_input_tokens_seen": 15004853824,
      "step": 52760,
      "train_runtime": 513902.6096,
      "train_tokens_per_second": 29197.855
    },
    {
      "epoch": 1.8671073203201187,
      "grad_norm": 1.578125,
      "learning_rate": 1.995709843668259e-05,
      "loss": 1.0335342407226562,
      "num_input_tokens_seen": 15007682048,
      "step": 52770,
      "train_runtime": 513999.3624,
      "train_tokens_per_second": 29197.861
    },
    {
      "epoch": 1.8674611405838477,
      "grad_norm": 1.5390625,
      "learning_rate": 1.995550890091138e-05,
      "loss": 1.0511831283569335,
      "num_input_tokens_seen": 15010514304,
      "step": 52780,
      "train_runtime": 514095.1809,
      "train_tokens_per_second": 29197.928
    },
    {
      "epoch": 1.8678149608475765,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9953919744887985e-05,
      "loss": 1.055367660522461,
      "num_input_tokens_seen": 15013325632,
      "step": 52790,
      "train_runtime": 514191.6865,
      "train_tokens_per_second": 29197.916
    },
    {
      "epoch": 1.8681687811113052,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9952330968461233e-05,
      "loss": 1.0340347290039062,
      "num_input_tokens_seen": 15016185792,
      "step": 52800,
      "train_runtime": 514289.1651,
      "train_tokens_per_second": 29197.943
    },
    {
      "epoch": 1.868522601375034,
      "grad_norm": 1.65625,
      "learning_rate": 1.995074257148002e-05,
      "loss": 1.0472915649414063,
      "num_input_tokens_seen": 15019031040,
      "step": 52810,
      "train_runtime": 514385.8,
      "train_tokens_per_second": 29197.989
    },
    {
      "epoch": 1.8688764216387628,
      "grad_norm": 1.59375,
      "learning_rate": 1.9949154553793342e-05,
      "loss": 1.033731746673584,
      "num_input_tokens_seen": 15021916736,
      "step": 52820,
      "train_runtime": 514486.3398,
      "train_tokens_per_second": 29197.892
    },
    {
      "epoch": 1.8692302419024915,
      "grad_norm": 1.5546875,
      "learning_rate": 1.994756691525026e-05,
      "loss": 1.0458511352539062,
      "num_input_tokens_seen": 15024798208,
      "step": 52830,
      "train_runtime": 514587.1763,
      "train_tokens_per_second": 29197.77
    },
    {
      "epoch": 1.8695840621662203,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9945979655699932e-05,
      "loss": 1.0440725326538085,
      "num_input_tokens_seen": 15027600960,
      "step": 52840,
      "train_runtime": 514678.7218,
      "train_tokens_per_second": 29198.023
    },
    {
      "epoch": 1.869937882429949,
      "grad_norm": 1.5703125,
      "learning_rate": 1.99443927749916e-05,
      "loss": 1.0341585159301758,
      "num_input_tokens_seen": 15030380544,
      "step": 52850,
      "train_runtime": 514775.4708,
      "train_tokens_per_second": 29197.935
    },
    {
      "epoch": 1.8702917026936778,
      "grad_norm": 1.53125,
      "learning_rate": 1.994280627297458e-05,
      "loss": 1.0424995422363281,
      "num_input_tokens_seen": 15033159424,
      "step": 52860,
      "train_runtime": 514868.1487,
      "train_tokens_per_second": 29198.076
    },
    {
      "epoch": 1.8706455229574068,
      "grad_norm": 1.5625,
      "learning_rate": 1.9941220149498282e-05,
      "loss": 1.0405799865722656,
      "num_input_tokens_seen": 15035982464,
      "step": 52870,
      "train_runtime": 514966.2047,
      "train_tokens_per_second": 29197.998
    },
    {
      "epoch": 1.8709993432211354,
      "grad_norm": 1.5390625,
      "learning_rate": 1.99396344044122e-05,
      "loss": 1.04142427444458,
      "num_input_tokens_seen": 15038833600,
      "step": 52880,
      "train_runtime": 515063.2978,
      "train_tokens_per_second": 29198.03
    },
    {
      "epoch": 1.8713531634848644,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9938049037565903e-05,
      "loss": 1.0353654861450194,
      "num_input_tokens_seen": 15041661824,
      "step": 52890,
      "train_runtime": 515160.172,
      "train_tokens_per_second": 29198.029
    },
    {
      "epoch": 1.871706983748593,
      "grad_norm": 1.59375,
      "learning_rate": 1.993646404880905e-05,
      "loss": 1.0471607208251954,
      "num_input_tokens_seen": 15044500672,
      "step": 52900,
      "train_runtime": 515258.2459,
      "train_tokens_per_second": 29197.981
    },
    {
      "epoch": 1.8720608040123219,
      "grad_norm": 1.5546875,
      "learning_rate": 1.993487943799139e-05,
      "loss": 1.0443610191345214,
      "num_input_tokens_seen": 15047343552,
      "step": 52910,
      "train_runtime": 515353.1297,
      "train_tokens_per_second": 29198.122
    },
    {
      "epoch": 1.8724146242760504,
      "grad_norm": 1.578125,
      "learning_rate": 1.9933295204962733e-05,
      "loss": 1.039942741394043,
      "num_input_tokens_seen": 15050183808,
      "step": 52920,
      "train_runtime": 515450.7645,
      "train_tokens_per_second": 29198.102
    },
    {
      "epoch": 1.8727684445397794,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9931711349572995e-05,
      "loss": 1.0339216232299804,
      "num_input_tokens_seen": 15053017280,
      "step": 52930,
      "train_runtime": 515548.5573,
      "train_tokens_per_second": 29198.059
    },
    {
      "epoch": 1.873122264803508,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9930127871672175e-05,
      "loss": 1.0475444793701172,
      "num_input_tokens_seen": 15055880320,
      "step": 52940,
      "train_runtime": 515647.6823,
      "train_tokens_per_second": 29197.999
    },
    {
      "epoch": 1.873476085067237,
      "grad_norm": 1.578125,
      "learning_rate": 1.992854477111034e-05,
      "loss": 1.0461475372314453,
      "num_input_tokens_seen": 15058738560,
      "step": 52950,
      "train_runtime": 515744.4016,
      "train_tokens_per_second": 29198.065
    },
    {
      "epoch": 1.8738299053309657,
      "grad_norm": 1.59375,
      "learning_rate": 1.9926962047737652e-05,
      "loss": 1.0350165367126465,
      "num_input_tokens_seen": 15061586240,
      "step": 52960,
      "train_runtime": 515842.3738,
      "train_tokens_per_second": 29198.04
    },
    {
      "epoch": 1.8741837255946945,
      "grad_norm": 1.5,
      "learning_rate": 1.992537970140435e-05,
      "loss": 1.0413796424865722,
      "num_input_tokens_seen": 15064406464,
      "step": 52970,
      "train_runtime": 515935.6584,
      "train_tokens_per_second": 29198.227
    },
    {
      "epoch": 1.8745375458584232,
      "grad_norm": 1.578125,
      "learning_rate": 1.9923797731960762e-05,
      "loss": 1.046365737915039,
      "num_input_tokens_seen": 15067219712,
      "step": 52980,
      "train_runtime": 516030.0879,
      "train_tokens_per_second": 29198.336
    },
    {
      "epoch": 1.874891366122152,
      "grad_norm": 1.578125,
      "learning_rate": 1.9922216139257303e-05,
      "loss": 1.0428776741027832,
      "num_input_tokens_seen": 15070048576,
      "step": 52990,
      "train_runtime": 516127.3372,
      "train_tokens_per_second": 29198.315
    },
    {
      "epoch": 1.8752451863858808,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9920634923144448e-05,
      "loss": 1.0358384132385254,
      "num_input_tokens_seen": 15072914944,
      "step": 53000,
      "train_runtime": 516223.6377,
      "train_tokens_per_second": 29198.421
    },
    {
      "epoch": 1.8755990066496095,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9919054083472788e-05,
      "loss": 1.0324202537536622,
      "num_input_tokens_seen": 15075765440,
      "step": 53010,
      "train_runtime": 516320.3123,
      "train_tokens_per_second": 29198.474
    },
    {
      "epoch": 1.8759528269133383,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9917473620092976e-05,
      "loss": 1.039243507385254,
      "num_input_tokens_seen": 15078580992,
      "step": 53020,
      "train_runtime": 516413.5367,
      "train_tokens_per_second": 29198.656
    },
    {
      "epoch": 1.876306647177067,
      "grad_norm": 1.578125,
      "learning_rate": 1.9915893532855746e-05,
      "loss": 1.0500545501708984,
      "num_input_tokens_seen": 15081389120,
      "step": 53030,
      "train_runtime": 516507.62,
      "train_tokens_per_second": 29198.774
    },
    {
      "epoch": 1.876660467440796,
      "grad_norm": 1.5,
      "learning_rate": 1.9914313821611926e-05,
      "loss": 1.0438434600830078,
      "num_input_tokens_seen": 15084214336,
      "step": 53040,
      "train_runtime": 516601.3371,
      "train_tokens_per_second": 29198.946
    },
    {
      "epoch": 1.8770142877045246,
      "grad_norm": 1.578125,
      "learning_rate": 1.9912734486212426e-05,
      "loss": 1.0411837577819825,
      "num_input_tokens_seen": 15087038464,
      "step": 53050,
      "train_runtime": 516699.1081,
      "train_tokens_per_second": 29198.886
    },
    {
      "epoch": 1.8773681079682536,
      "grad_norm": 1.578125,
      "learning_rate": 1.9911155526508233e-05,
      "loss": 1.0391999244689942,
      "num_input_tokens_seen": 15089893760,
      "step": 53060,
      "train_runtime": 516796.3658,
      "train_tokens_per_second": 29198.916
    },
    {
      "epoch": 1.8777219282319821,
      "grad_norm": 1.484375,
      "learning_rate": 1.9909576942350416e-05,
      "loss": 1.0618062973022462,
      "num_input_tokens_seen": 15092741632,
      "step": 53070,
      "train_runtime": 516896.2887,
      "train_tokens_per_second": 29198.781
    },
    {
      "epoch": 1.8780757484957111,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9907998733590127e-05,
      "loss": 1.039078140258789,
      "num_input_tokens_seen": 15095558784,
      "step": 53080,
      "train_runtime": 516991.705,
      "train_tokens_per_second": 29198.841
    },
    {
      "epoch": 1.8784295687594397,
      "grad_norm": 1.484375,
      "learning_rate": 1.9906420900078614e-05,
      "loss": 1.0455076217651367,
      "num_input_tokens_seen": 15098389696,
      "step": 53090,
      "train_runtime": 517086.6485,
      "train_tokens_per_second": 29198.955
    },
    {
      "epoch": 1.8787833890231687,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9904843441667184e-05,
      "loss": 1.044952964782715,
      "num_input_tokens_seen": 15101230144,
      "step": 53100,
      "train_runtime": 517186.691,
      "train_tokens_per_second": 29198.799
    },
    {
      "epoch": 1.8791372092868974,
      "grad_norm": 1.6015625,
      "learning_rate": 1.990326635820725e-05,
      "loss": 1.0527901649475098,
      "num_input_tokens_seen": 15104124416,
      "step": 53110,
      "train_runtime": 517285.0234,
      "train_tokens_per_second": 29198.843
    },
    {
      "epoch": 1.8794910295506262,
      "grad_norm": 1.515625,
      "learning_rate": 1.9901689649550285e-05,
      "loss": 1.038181972503662,
      "num_input_tokens_seen": 15106953216,
      "step": 53120,
      "train_runtime": 517381.4692,
      "train_tokens_per_second": 29198.868
    },
    {
      "epoch": 1.879844849814355,
      "grad_norm": 1.546875,
      "learning_rate": 1.9900113315547862e-05,
      "loss": 1.0390201568603517,
      "num_input_tokens_seen": 15109785728,
      "step": 53130,
      "train_runtime": 517477.6137,
      "train_tokens_per_second": 29198.917
    },
    {
      "epoch": 1.8801986700780837,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9898537356051635e-05,
      "loss": 1.0423640251159667,
      "num_input_tokens_seen": 15112611712,
      "step": 53140,
      "train_runtime": 517576.8188,
      "train_tokens_per_second": 29198.78
    },
    {
      "epoch": 1.8805524903418125,
      "grad_norm": 1.6640625,
      "learning_rate": 1.9896961770913325e-05,
      "loss": 1.0438544273376464,
      "num_input_tokens_seen": 15115498368,
      "step": 53150,
      "train_runtime": 517679.5134,
      "train_tokens_per_second": 29198.564
    },
    {
      "epoch": 1.8809063106055413,
      "grad_norm": 1.578125,
      "learning_rate": 1.989538655998475e-05,
      "loss": 1.0327787399291992,
      "num_input_tokens_seen": 15118345792,
      "step": 53160,
      "train_runtime": 517778.4665,
      "train_tokens_per_second": 29198.483
    },
    {
      "epoch": 1.88126013086927,
      "grad_norm": 1.609375,
      "learning_rate": 1.989381172311781e-05,
      "loss": 1.031819725036621,
      "num_input_tokens_seen": 15121195328,
      "step": 53170,
      "train_runtime": 517873.3254,
      "train_tokens_per_second": 29198.637
    },
    {
      "epoch": 1.8816139511329988,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9892237260164473e-05,
      "loss": 1.041791820526123,
      "num_input_tokens_seen": 15123988544,
      "step": 53180,
      "train_runtime": 517967.9132,
      "train_tokens_per_second": 29198.698
    },
    {
      "epoch": 1.8819677713967276,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9890663170976807e-05,
      "loss": 1.0493701934814452,
      "num_input_tokens_seen": 15126827200,
      "step": 53190,
      "train_runtime": 518063.8658,
      "train_tokens_per_second": 29198.769
    },
    {
      "epoch": 1.8823215916604563,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9889089455406948e-05,
      "loss": 1.043891716003418,
      "num_input_tokens_seen": 15129682240,
      "step": 53200,
      "train_runtime": 518159.7581,
      "train_tokens_per_second": 29198.875
    },
    {
      "epoch": 1.8826754119241853,
      "grad_norm": 1.5625,
      "learning_rate": 1.9887516113307126e-05,
      "loss": 1.0514963150024415,
      "num_input_tokens_seen": 15132541760,
      "step": 53210,
      "train_runtime": 518257.9663,
      "train_tokens_per_second": 29198.86
    },
    {
      "epoch": 1.8830292321879138,
      "grad_norm": 1.5625,
      "learning_rate": 1.9885943144529635e-05,
      "loss": 1.0334545135498048,
      "num_input_tokens_seen": 15135366592,
      "step": 53220,
      "train_runtime": 518353.1064,
      "train_tokens_per_second": 29198.95
    },
    {
      "epoch": 1.8833830524516428,
      "grad_norm": 1.609375,
      "learning_rate": 1.9884370548926874e-05,
      "loss": 1.0295021057128906,
      "num_input_tokens_seen": 15138289152,
      "step": 53230,
      "train_runtime": 518453.5214,
      "train_tokens_per_second": 29198.932
    },
    {
      "epoch": 1.8837368727153714,
      "grad_norm": 1.53125,
      "learning_rate": 1.9882798326351305e-05,
      "loss": 1.0414121627807618,
      "num_input_tokens_seen": 15141172672,
      "step": 53240,
      "train_runtime": 518554.6762,
      "train_tokens_per_second": 29198.797
    },
    {
      "epoch": 1.8840906929791004,
      "grad_norm": 1.578125,
      "learning_rate": 1.9881226476655475e-05,
      "loss": 1.0378078460693358,
      "num_input_tokens_seen": 15144026176,
      "step": 53250,
      "train_runtime": 518651.7549,
      "train_tokens_per_second": 29198.833
    },
    {
      "epoch": 1.884444513242829,
      "grad_norm": 1.5234375,
      "learning_rate": 1.9879654999692028e-05,
      "loss": 1.0480581283569337,
      "num_input_tokens_seen": 15146872384,
      "step": 53260,
      "train_runtime": 518752.6084,
      "train_tokens_per_second": 29198.643
    },
    {
      "epoch": 1.884798333506558,
      "grad_norm": 1.6171875,
      "learning_rate": 1.987808389531366e-05,
      "loss": 1.0405941009521484,
      "num_input_tokens_seen": 15149702272,
      "step": 53270,
      "train_runtime": 518850.0919,
      "train_tokens_per_second": 29198.612
    },
    {
      "epoch": 1.8851521537702867,
      "grad_norm": 1.5625,
      "learning_rate": 1.987651316337318e-05,
      "loss": 1.0401514053344727,
      "num_input_tokens_seen": 15152548288,
      "step": 53280,
      "train_runtime": 518947.6243,
      "train_tokens_per_second": 29198.608
    },
    {
      "epoch": 1.8855059740340154,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9874942803723465e-05,
      "loss": 1.0519044876098633,
      "num_input_tokens_seen": 15155368576,
      "step": 53290,
      "train_runtime": 519040.4972,
      "train_tokens_per_second": 29198.817
    },
    {
      "epoch": 1.8858597942977442,
      "grad_norm": 1.5390625,
      "learning_rate": 1.987337281621746e-05,
      "loss": 1.0356197357177734,
      "num_input_tokens_seen": 15158285760,
      "step": 53300,
      "train_runtime": 519138.1145,
      "train_tokens_per_second": 29198.946
    },
    {
      "epoch": 1.886213614561473,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9871803200708214e-05,
      "loss": 1.0419928550720214,
      "num_input_tokens_seen": 15161112320,
      "step": 53310,
      "train_runtime": 519231.2866,
      "train_tokens_per_second": 29199.15
    },
    {
      "epoch": 1.8865674348252017,
      "grad_norm": 1.5625,
      "learning_rate": 1.9870233957048844e-05,
      "loss": 1.0307758331298829,
      "num_input_tokens_seen": 15163967936,
      "step": 53320,
      "train_runtime": 519328.7672,
      "train_tokens_per_second": 29199.168
    },
    {
      "epoch": 1.8869212550889305,
      "grad_norm": 1.5,
      "learning_rate": 1.9868665085092556e-05,
      "loss": 1.0403764724731446,
      "num_input_tokens_seen": 15166826496,
      "step": 53330,
      "train_runtime": 519427.3639,
      "train_tokens_per_second": 29199.129
    },
    {
      "epoch": 1.8872750753526593,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9867096584692624e-05,
      "loss": 1.042405891418457,
      "num_input_tokens_seen": 15169662656,
      "step": 53340,
      "train_runtime": 519523.3621,
      "train_tokens_per_second": 29199.192
    },
    {
      "epoch": 1.887628895616388,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9865528455702416e-05,
      "loss": 1.0508646965026855,
      "num_input_tokens_seen": 15172499712,
      "step": 53350,
      "train_runtime": 519621.0718,
      "train_tokens_per_second": 29199.162
    },
    {
      "epoch": 1.887982715880117,
      "grad_norm": 1.546875,
      "learning_rate": 1.9863960697975378e-05,
      "loss": 1.0372345924377442,
      "num_input_tokens_seen": 15175370112,
      "step": 53360,
      "train_runtime": 519720.6627,
      "train_tokens_per_second": 29199.089
    },
    {
      "epoch": 1.8883365361438456,
      "grad_norm": 1.5234375,
      "learning_rate": 1.986239331136503e-05,
      "loss": 1.0476030349731444,
      "num_input_tokens_seen": 15178147008,
      "step": 53370,
      "train_runtime": 519813.0948,
      "train_tokens_per_second": 29199.239
    },
    {
      "epoch": 1.8886903564075745,
      "grad_norm": 1.59375,
      "learning_rate": 1.9860826295724985e-05,
      "loss": 1.026973819732666,
      "num_input_tokens_seen": 15181014080,
      "step": 53380,
      "train_runtime": 519915.1026,
      "train_tokens_per_second": 29199.025
    },
    {
      "epoch": 1.889044176671303,
      "grad_norm": 1.53125,
      "learning_rate": 1.985925965090893e-05,
      "loss": 1.0540546417236327,
      "num_input_tokens_seen": 15183882944,
      "step": 53390,
      "train_runtime": 520012.9325,
      "train_tokens_per_second": 29199.049
    },
    {
      "epoch": 1.889397996935032,
      "grad_norm": 1.609375,
      "learning_rate": 1.9857693376770625e-05,
      "loss": 1.050197219848633,
      "num_input_tokens_seen": 15186685824,
      "step": 53400,
      "train_runtime": 520108.8119,
      "train_tokens_per_second": 29199.055
    },
    {
      "epoch": 1.8897518171987606,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9856127473163922e-05,
      "loss": 1.049802017211914,
      "num_input_tokens_seen": 15189505536,
      "step": 53410,
      "train_runtime": 520203.7912,
      "train_tokens_per_second": 29199.144
    },
    {
      "epoch": 1.8901056374624896,
      "grad_norm": 1.5625,
      "learning_rate": 1.9854561939942756e-05,
      "loss": 1.032862091064453,
      "num_input_tokens_seen": 15192307968,
      "step": 53420,
      "train_runtime": 520300.9281,
      "train_tokens_per_second": 29199.079
    },
    {
      "epoch": 1.8904594577262182,
      "grad_norm": 1.5625,
      "learning_rate": 1.985299677696113e-05,
      "loss": 1.0359228134155274,
      "num_input_tokens_seen": 15195184448,
      "step": 53430,
      "train_runtime": 520398.7095,
      "train_tokens_per_second": 29199.12
    },
    {
      "epoch": 1.8908132779899471,
      "grad_norm": 1.546875,
      "learning_rate": 1.9851431984073143e-05,
      "loss": 1.0315203666687012,
      "num_input_tokens_seen": 15198006784,
      "step": 53440,
      "train_runtime": 520493.2648,
      "train_tokens_per_second": 29199.238
    },
    {
      "epoch": 1.891167098253676,
      "grad_norm": 1.640625,
      "learning_rate": 1.9849867561132955e-05,
      "loss": 1.0527069091796875,
      "num_input_tokens_seen": 15200875904,
      "step": 53450,
      "train_runtime": 520590.3136,
      "train_tokens_per_second": 29199.306
    },
    {
      "epoch": 1.8915209185174047,
      "grad_norm": 1.578125,
      "learning_rate": 1.9848303507994826e-05,
      "loss": 1.0399028778076171,
      "num_input_tokens_seen": 15203784192,
      "step": 53460,
      "train_runtime": 520692.5356,
      "train_tokens_per_second": 29199.159
    },
    {
      "epoch": 1.8918747387811334,
      "grad_norm": 1.5625,
      "learning_rate": 1.9846739824513087e-05,
      "loss": 1.0577550888061524,
      "num_input_tokens_seen": 15206600512,
      "step": 53470,
      "train_runtime": 520786.9983,
      "train_tokens_per_second": 29199.271
    },
    {
      "epoch": 1.8922285590448622,
      "grad_norm": 1.578125,
      "learning_rate": 1.9845176510542145e-05,
      "loss": 1.0266995429992676,
      "num_input_tokens_seen": 15209420352,
      "step": 53480,
      "train_runtime": 520881.8668,
      "train_tokens_per_second": 29199.366
    },
    {
      "epoch": 1.892582379308591,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9843613565936495e-05,
      "loss": 1.0459341049194335,
      "num_input_tokens_seen": 15212237376,
      "step": 53490,
      "train_runtime": 520977.2835,
      "train_tokens_per_second": 29199.425
    },
    {
      "epoch": 1.8929361995723197,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9842050990550707e-05,
      "loss": 1.031562900543213,
      "num_input_tokens_seen": 15215105664,
      "step": 53500,
      "train_runtime": 521076.1249,
      "train_tokens_per_second": 29199.391
    },
    {
      "epoch": 1.8932900198360485,
      "grad_norm": 1.546875,
      "learning_rate": 1.9840488784239442e-05,
      "loss": 1.0388352394104003,
      "num_input_tokens_seen": 15217921088,
      "step": 53510,
      "train_runtime": 521170.3275,
      "train_tokens_per_second": 29199.516
    },
    {
      "epoch": 1.8936438400997773,
      "grad_norm": 1.5859375,
      "learning_rate": 1.983892694685743e-05,
      "loss": 1.0502792358398438,
      "num_input_tokens_seen": 15220754240,
      "step": 53520,
      "train_runtime": 521267.1786,
      "train_tokens_per_second": 29199.525
    },
    {
      "epoch": 1.8939976603635063,
      "grad_norm": 1.609375,
      "learning_rate": 1.983736547825947e-05,
      "loss": 1.0360902786254882,
      "num_input_tokens_seen": 15223586240,
      "step": 53530,
      "train_runtime": 521363.5944,
      "train_tokens_per_second": 29199.557
    },
    {
      "epoch": 1.8943514806272348,
      "grad_norm": 1.546875,
      "learning_rate": 1.983580437830047e-05,
      "loss": 1.0490608215332031,
      "num_input_tokens_seen": 15226450176,
      "step": 53540,
      "train_runtime": 521461.5897,
      "train_tokens_per_second": 29199.562
    },
    {
      "epoch": 1.8947053008909638,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9834243646835407e-05,
      "loss": 1.0239006996154785,
      "num_input_tokens_seen": 15229264320,
      "step": 53550,
      "train_runtime": 521557.3554,
      "train_tokens_per_second": 29199.596
    },
    {
      "epoch": 1.8950591211546923,
      "grad_norm": 1.5625,
      "learning_rate": 1.9832683283719318e-05,
      "loss": 1.0635089874267578,
      "num_input_tokens_seen": 15232128128,
      "step": 53560,
      "train_runtime": 521658.1878,
      "train_tokens_per_second": 29199.442
    },
    {
      "epoch": 1.8954129414184213,
      "grad_norm": 1.484375,
      "learning_rate": 1.9831123288807342e-05,
      "loss": 1.0329875946044922,
      "num_input_tokens_seen": 15234941632,
      "step": 53570,
      "train_runtime": 521755.8698,
      "train_tokens_per_second": 29199.368
    },
    {
      "epoch": 1.8957667616821499,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9829563661954696e-05,
      "loss": 1.02885160446167,
      "num_input_tokens_seen": 15237821568,
      "step": 53580,
      "train_runtime": 521857.0135,
      "train_tokens_per_second": 29199.227
    },
    {
      "epoch": 1.8961205819458788,
      "grad_norm": 1.5625,
      "learning_rate": 1.9828004403016665e-05,
      "loss": 1.0391828536987304,
      "num_input_tokens_seen": 15240696384,
      "step": 53590,
      "train_runtime": 521955.9789,
      "train_tokens_per_second": 29199.199
    },
    {
      "epoch": 1.8964744022096074,
      "grad_norm": 1.5625,
      "learning_rate": 1.9826445511848627e-05,
      "loss": 1.060126781463623,
      "num_input_tokens_seen": 15243539328,
      "step": 53600,
      "train_runtime": 522051.0271,
      "train_tokens_per_second": 29199.328
    },
    {
      "epoch": 1.8968282224733364,
      "grad_norm": 1.5625,
      "learning_rate": 1.9824886988306024e-05,
      "loss": 1.0260886192321776,
      "num_input_tokens_seen": 15246413888,
      "step": 53610,
      "train_runtime": 522148.9507,
      "train_tokens_per_second": 29199.358
    },
    {
      "epoch": 1.8971820427370651,
      "grad_norm": 1.5625,
      "learning_rate": 1.9823328832244396e-05,
      "loss": 1.039914608001709,
      "num_input_tokens_seen": 15249245376,
      "step": 53620,
      "train_runtime": 522246.9005,
      "train_tokens_per_second": 29199.303
    },
    {
      "epoch": 1.897535863000794,
      "grad_norm": 1.546875,
      "learning_rate": 1.9821771043519348e-05,
      "loss": 1.041110897064209,
      "num_input_tokens_seen": 15252124224,
      "step": 53630,
      "train_runtime": 522346.4513,
      "train_tokens_per_second": 29199.249
    },
    {
      "epoch": 1.8978896832645227,
      "grad_norm": 1.578125,
      "learning_rate": 1.9820213621986572e-05,
      "loss": 1.0495532035827637,
      "num_input_tokens_seen": 15254925440,
      "step": 53640,
      "train_runtime": 522440.3372,
      "train_tokens_per_second": 29199.364
    },
    {
      "epoch": 1.8982435035282514,
      "grad_norm": 1.625,
      "learning_rate": 1.9818656567501832e-05,
      "loss": 1.037358283996582,
      "num_input_tokens_seen": 15257742528,
      "step": 53650,
      "train_runtime": 522537.3361,
      "train_tokens_per_second": 29199.335
    },
    {
      "epoch": 1.8985973237919802,
      "grad_norm": 1.5625,
      "learning_rate": 1.9817099879920984e-05,
      "loss": 1.0442892074584962,
      "num_input_tokens_seen": 15260600320,
      "step": 53660,
      "train_runtime": 522634.9213,
      "train_tokens_per_second": 29199.351
    },
    {
      "epoch": 1.898951144055709,
      "grad_norm": 1.5625,
      "learning_rate": 1.981554355909995e-05,
      "loss": 1.046921157836914,
      "num_input_tokens_seen": 15263387648,
      "step": 53670,
      "train_runtime": 522730.0105,
      "train_tokens_per_second": 29199.371
    },
    {
      "epoch": 1.8993049643194377,
      "grad_norm": 1.546875,
      "learning_rate": 1.9813987604894733e-05,
      "loss": 1.0375445365905762,
      "num_input_tokens_seen": 15266260160,
      "step": 53680,
      "train_runtime": 522830.4441,
      "train_tokens_per_second": 29199.256
    },
    {
      "epoch": 1.8996587845831665,
      "grad_norm": 1.6015625,
      "learning_rate": 1.981243201716143e-05,
      "loss": 1.0256319999694825,
      "num_input_tokens_seen": 15269102656,
      "step": 53690,
      "train_runtime": 522928.4416,
      "train_tokens_per_second": 29199.22
    },
    {
      "epoch": 1.9000126048468955,
      "grad_norm": 1.546875,
      "learning_rate": 1.98108767957562e-05,
      "loss": 1.0496192932128907,
      "num_input_tokens_seen": 15271902464,
      "step": 53700,
      "train_runtime": 523020.8395,
      "train_tokens_per_second": 29199.415
    },
    {
      "epoch": 1.900366425110624,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9809321940535282e-05,
      "loss": 1.0359999656677246,
      "num_input_tokens_seen": 15274761856,
      "step": 53710,
      "train_runtime": 523119.2567,
      "train_tokens_per_second": 29199.387
    },
    {
      "epoch": 1.900720245374353,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9807767451355004e-05,
      "loss": 1.0280059814453124,
      "num_input_tokens_seen": 15277596800,
      "step": 53720,
      "train_runtime": 523215.2255,
      "train_tokens_per_second": 29199.45
    },
    {
      "epoch": 1.9010740656380816,
      "grad_norm": 1.609375,
      "learning_rate": 1.9806213328071767e-05,
      "loss": 1.0353303909301759,
      "num_input_tokens_seen": 15280457344,
      "step": 53730,
      "train_runtime": 523311.9963,
      "train_tokens_per_second": 29199.517
    },
    {
      "epoch": 1.9014278859018106,
      "grad_norm": 1.640625,
      "learning_rate": 1.980465957054205e-05,
      "loss": 1.0233169555664063,
      "num_input_tokens_seen": 15283255808,
      "step": 53740,
      "train_runtime": 523408.078,
      "train_tokens_per_second": 29199.503
    },
    {
      "epoch": 1.901781706165539,
      "grad_norm": 1.609375,
      "learning_rate": 1.980310617862242e-05,
      "loss": 1.0535359382629395,
      "num_input_tokens_seen": 15286074816,
      "step": 53750,
      "train_runtime": 523506.028,
      "train_tokens_per_second": 29199.425
    },
    {
      "epoch": 1.902135526429268,
      "grad_norm": 1.6171875,
      "learning_rate": 1.98015531521695e-05,
      "loss": 1.0434648513793945,
      "num_input_tokens_seen": 15288933504,
      "step": 53760,
      "train_runtime": 523602.7554,
      "train_tokens_per_second": 29199.49
    },
    {
      "epoch": 1.9024893466929966,
      "grad_norm": 1.625,
      "learning_rate": 1.980000049104002e-05,
      "loss": 1.035345458984375,
      "num_input_tokens_seen": 15291791680,
      "step": 53770,
      "train_runtime": 523701.4095,
      "train_tokens_per_second": 29199.447
    },
    {
      "epoch": 1.9028431669567256,
      "grad_norm": 1.578125,
      "learning_rate": 1.979844819509077e-05,
      "loss": 1.03832950592041,
      "num_input_tokens_seen": 15294617856,
      "step": 53780,
      "train_runtime": 523798.8669,
      "train_tokens_per_second": 29199.41
    },
    {
      "epoch": 1.9031969872204544,
      "grad_norm": 1.6015625,
      "learning_rate": 1.979689626417863e-05,
      "loss": 1.0421913146972657,
      "num_input_tokens_seen": 15297405056,
      "step": 53790,
      "train_runtime": 523892.8754,
      "train_tokens_per_second": 29199.491
    },
    {
      "epoch": 1.9035508074841831,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9795344698160537e-05,
      "loss": 1.0433399200439453,
      "num_input_tokens_seen": 15300277568,
      "step": 53800,
      "train_runtime": 523990.7901,
      "train_tokens_per_second": 29199.516
    },
    {
      "epoch": 1.903904627747912,
      "grad_norm": 1.578125,
      "learning_rate": 1.979379349689354e-05,
      "loss": 1.0185476303100587,
      "num_input_tokens_seen": 15303062272,
      "step": 53810,
      "train_runtime": 524084.3701,
      "train_tokens_per_second": 29199.616
    },
    {
      "epoch": 1.9042584480116407,
      "grad_norm": 1.5703125,
      "learning_rate": 1.979224266023474e-05,
      "loss": 1.0528945922851562,
      "num_input_tokens_seen": 15305852416,
      "step": 53820,
      "train_runtime": 524180.7343,
      "train_tokens_per_second": 29199.571
    },
    {
      "epoch": 1.9046122682753694,
      "grad_norm": 1.546875,
      "learning_rate": 1.9790692188041323e-05,
      "loss": 1.0445027351379395,
      "num_input_tokens_seen": 15308687872,
      "step": 53830,
      "train_runtime": 524276.4618,
      "train_tokens_per_second": 29199.647
    },
    {
      "epoch": 1.9049660885390982,
      "grad_norm": 1.5625,
      "learning_rate": 1.9789142080170562e-05,
      "loss": 1.0530653953552247,
      "num_input_tokens_seen": 15311520832,
      "step": 53840,
      "train_runtime": 524372.1716,
      "train_tokens_per_second": 29199.72
    },
    {
      "epoch": 1.905319908802827,
      "grad_norm": 1.5625,
      "learning_rate": 1.9787592336479794e-05,
      "loss": 1.0464700698852538,
      "num_input_tokens_seen": 15314368448,
      "step": 53850,
      "train_runtime": 524468.5014,
      "train_tokens_per_second": 29199.787
    },
    {
      "epoch": 1.9056737290665557,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9786042956826444e-05,
      "loss": 1.0527534484863281,
      "num_input_tokens_seen": 15317277248,
      "step": 53860,
      "train_runtime": 524570.3946,
      "train_tokens_per_second": 29199.66
    },
    {
      "epoch": 1.9060275493302847,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9784493941068015e-05,
      "loss": 1.0427188873291016,
      "num_input_tokens_seen": 15320099968,
      "step": 53870,
      "train_runtime": 524664.1774,
      "train_tokens_per_second": 29199.821
    },
    {
      "epoch": 1.9063813695940133,
      "grad_norm": 1.5,
      "learning_rate": 1.9782945289062085e-05,
      "loss": 1.0574268341064452,
      "num_input_tokens_seen": 15322939968,
      "step": 53880,
      "train_runtime": 524761.0812,
      "train_tokens_per_second": 29199.841
    },
    {
      "epoch": 1.9067351898577423,
      "grad_norm": 1.625,
      "learning_rate": 1.978139700066631e-05,
      "loss": 1.049966049194336,
      "num_input_tokens_seen": 15325730816,
      "step": 53890,
      "train_runtime": 524853.7516,
      "train_tokens_per_second": 29200.002
    },
    {
      "epoch": 1.9070890101214708,
      "grad_norm": 1.53125,
      "learning_rate": 1.977984907573842e-05,
      "loss": 1.0292572021484374,
      "num_input_tokens_seen": 15328558592,
      "step": 53900,
      "train_runtime": 524949.196,
      "train_tokens_per_second": 29200.08
    },
    {
      "epoch": 1.9074428303851998,
      "grad_norm": 1.515625,
      "learning_rate": 1.9778301514136232e-05,
      "loss": 1.031935214996338,
      "num_input_tokens_seen": 15331444736,
      "step": 53910,
      "train_runtime": 525049.891,
      "train_tokens_per_second": 29199.977
    },
    {
      "epoch": 1.9077966506489283,
      "grad_norm": 1.5859375,
      "learning_rate": 1.977675431571764e-05,
      "loss": 1.0459724426269532,
      "num_input_tokens_seen": 15334280256,
      "step": 53920,
      "train_runtime": 525148.384,
      "train_tokens_per_second": 29199.9
    },
    {
      "epoch": 1.9081504709126573,
      "grad_norm": 1.5546875,
      "learning_rate": 1.977520748034061e-05,
      "loss": 1.0390378952026367,
      "num_input_tokens_seen": 15337088064,
      "step": 53930,
      "train_runtime": 525244.154,
      "train_tokens_per_second": 29199.921
    },
    {
      "epoch": 1.9085042911763859,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9773661007863183e-05,
      "loss": 1.0487327575683594,
      "num_input_tokens_seen": 15339925120,
      "step": 53940,
      "train_runtime": 525343.7616,
      "train_tokens_per_second": 29199.785
    },
    {
      "epoch": 1.9088581114401149,
      "grad_norm": 1.6171875,
      "learning_rate": 1.977211489814349e-05,
      "loss": 1.0404623031616211,
      "num_input_tokens_seen": 15342791616,
      "step": 53950,
      "train_runtime": 525444.0114,
      "train_tokens_per_second": 29199.67
    },
    {
      "epoch": 1.9092119317038436,
      "grad_norm": 1.5859375,
      "learning_rate": 1.977056915103973e-05,
      "loss": 1.0452077865600586,
      "num_input_tokens_seen": 15345632192,
      "step": 53960,
      "train_runtime": 525539.9678,
      "train_tokens_per_second": 29199.743
    },
    {
      "epoch": 1.9095657519675724,
      "grad_norm": 1.53125,
      "learning_rate": 1.9769023766410176e-05,
      "loss": 1.0267130851745605,
      "num_input_tokens_seen": 15348445056,
      "step": 53970,
      "train_runtime": 525637.3096,
      "train_tokens_per_second": 29199.687
    },
    {
      "epoch": 1.9099195722313012,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9767478744113192e-05,
      "loss": 1.0535240173339844,
      "num_input_tokens_seen": 15351364864,
      "step": 53980,
      "train_runtime": 525738.2552,
      "train_tokens_per_second": 29199.634
    },
    {
      "epoch": 1.91027339249503,
      "grad_norm": 1.5625,
      "learning_rate": 1.976593408400721e-05,
      "loss": 1.0603821754455567,
      "num_input_tokens_seen": 15354176640,
      "step": 53990,
      "train_runtime": 525833.4837,
      "train_tokens_per_second": 29199.694
    },
    {
      "epoch": 1.9106272127587587,
      "grad_norm": 1.625,
      "learning_rate": 1.976438978595074e-05,
      "loss": 1.0571113586425782,
      "num_input_tokens_seen": 15357006080,
      "step": 54000,
      "train_runtime": 525929.4374,
      "train_tokens_per_second": 29199.746
    },
    {
      "epoch": 1.9109810330224875,
      "grad_norm": 1.4140625,
      "learning_rate": 1.9762845849802375e-05,
      "loss": 1.0201444625854492,
      "num_input_tokens_seen": 15359838528,
      "step": 54010,
      "train_runtime": 526024.6252,
      "train_tokens_per_second": 29199.847
    },
    {
      "epoch": 1.9113348532862162,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9761302275420775e-05,
      "loss": 1.033356285095215,
      "num_input_tokens_seen": 15362698240,
      "step": 54020,
      "train_runtime": 526122.158,
      "train_tokens_per_second": 29199.869
    },
    {
      "epoch": 1.911688673549945,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9759759062664685e-05,
      "loss": 1.0496872901916503,
      "num_input_tokens_seen": 15365653056,
      "step": 54030,
      "train_runtime": 526227.7252,
      "train_tokens_per_second": 29199.627
    },
    {
      "epoch": 1.912042493813674,
      "grad_norm": 1.671875,
      "learning_rate": 1.9758216211392925e-05,
      "loss": 1.04419002532959,
      "num_input_tokens_seen": 15368471552,
      "step": 54040,
      "train_runtime": 526324.9727,
      "train_tokens_per_second": 29199.586
    },
    {
      "epoch": 1.9123963140774025,
      "grad_norm": 1.5,
      "learning_rate": 1.97566737214644e-05,
      "loss": 1.0562522888183594,
      "num_input_tokens_seen": 15371287040,
      "step": 54050,
      "train_runtime": 526418.7078,
      "train_tokens_per_second": 29199.736
    },
    {
      "epoch": 1.9127501343411315,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9755131592738073e-05,
      "loss": 1.0433542251586914,
      "num_input_tokens_seen": 15374138880,
      "step": 54060,
      "train_runtime": 526516.3015,
      "train_tokens_per_second": 29199.74
    },
    {
      "epoch": 1.91310395460486,
      "grad_norm": 1.53125,
      "learning_rate": 1.9753589825073005e-05,
      "loss": 1.0321563720703124,
      "num_input_tokens_seen": 15376968384,
      "step": 54070,
      "train_runtime": 526610.0617,
      "train_tokens_per_second": 29199.914
    },
    {
      "epoch": 1.913457774868589,
      "grad_norm": 1.546875,
      "learning_rate": 1.975204841832832e-05,
      "loss": 1.0385703086853026,
      "num_input_tokens_seen": 15379848192,
      "step": 54080,
      "train_runtime": 526708.8071,
      "train_tokens_per_second": 29199.907
    },
    {
      "epoch": 1.9138115951323176,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9750507372363228e-05,
      "loss": 1.0447673797607422,
      "num_input_tokens_seen": 15382733440,
      "step": 54090,
      "train_runtime": 526806.7673,
      "train_tokens_per_second": 29199.954
    },
    {
      "epoch": 1.9141654153960466,
      "grad_norm": 1.5625,
      "learning_rate": 1.9748966687037003e-05,
      "loss": 1.0399428367614747,
      "num_input_tokens_seen": 15385608064,
      "step": 54100,
      "train_runtime": 526907.595,
      "train_tokens_per_second": 29199.822
    },
    {
      "epoch": 1.9145192356597753,
      "grad_norm": 1.578125,
      "learning_rate": 1.974742636220902e-05,
      "loss": 1.036163902282715,
      "num_input_tokens_seen": 15388443712,
      "step": 54110,
      "train_runtime": 527004.8683,
      "train_tokens_per_second": 29199.813
    },
    {
      "epoch": 1.914873055923504,
      "grad_norm": 1.5859375,
      "learning_rate": 1.97458863977387e-05,
      "loss": 1.0516206741333007,
      "num_input_tokens_seen": 15391288576,
      "step": 54120,
      "train_runtime": 527099.9639,
      "train_tokens_per_second": 29199.942
    },
    {
      "epoch": 1.9152268761872329,
      "grad_norm": 1.5625,
      "learning_rate": 1.9744346793485567e-05,
      "loss": 1.0406282424926758,
      "num_input_tokens_seen": 15394125504,
      "step": 54130,
      "train_runtime": 527195.6601,
      "train_tokens_per_second": 29200.023
    },
    {
      "epoch": 1.9155806964509616,
      "grad_norm": 1.578125,
      "learning_rate": 1.97428075493092e-05,
      "loss": 1.0409584045410156,
      "num_input_tokens_seen": 15396968256,
      "step": 54140,
      "train_runtime": 527294.3409,
      "train_tokens_per_second": 29199.95
    },
    {
      "epoch": 1.9159345167146904,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9741268665069273e-05,
      "loss": 1.049799346923828,
      "num_input_tokens_seen": 15399818176,
      "step": 54150,
      "train_runtime": 527390.1053,
      "train_tokens_per_second": 29200.051
    },
    {
      "epoch": 1.9162883369784192,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9739730140625527e-05,
      "loss": 1.037711238861084,
      "num_input_tokens_seen": 15402693504,
      "step": 54160,
      "train_runtime": 527488.3814,
      "train_tokens_per_second": 29200.062
    },
    {
      "epoch": 1.916642157242148,
      "grad_norm": 1.53125,
      "learning_rate": 1.9738191975837777e-05,
      "loss": 1.0408974647521974,
      "num_input_tokens_seen": 15405510592,
      "step": 54170,
      "train_runtime": 527583.3279,
      "train_tokens_per_second": 29200.147
    },
    {
      "epoch": 1.9169959775058767,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9736654170565928e-05,
      "loss": 1.0330016136169433,
      "num_input_tokens_seen": 15408342016,
      "step": 54180,
      "train_runtime": 527679.6672,
      "train_tokens_per_second": 29200.181
    },
    {
      "epoch": 1.9173497977696055,
      "grad_norm": 1.546875,
      "learning_rate": 1.9735116724669948e-05,
      "loss": 1.0335532188415528,
      "num_input_tokens_seen": 15411184448,
      "step": 54190,
      "train_runtime": 527779.5017,
      "train_tokens_per_second": 29200.044
    },
    {
      "epoch": 1.9177036180333342,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9733579638009878e-05,
      "loss": 1.0513883590698243,
      "num_input_tokens_seen": 15414026560,
      "step": 54200,
      "train_runtime": 527875.6176,
      "train_tokens_per_second": 29200.111
    },
    {
      "epoch": 1.9180574382970632,
      "grad_norm": 1.6640625,
      "learning_rate": 1.973204291044585e-05,
      "loss": 1.0368818283081054,
      "num_input_tokens_seen": 15416833152,
      "step": 54210,
      "train_runtime": 527970.2881,
      "train_tokens_per_second": 29200.191
    },
    {
      "epoch": 1.9184112585607918,
      "grad_norm": 1.6015625,
      "learning_rate": 1.973050654183807e-05,
      "loss": 1.0405729293823243,
      "num_input_tokens_seen": 15419706752,
      "step": 54220,
      "train_runtime": 528069.3507,
      "train_tokens_per_second": 29200.155
    },
    {
      "epoch": 1.9187650788245207,
      "grad_norm": 1.6484375,
      "learning_rate": 1.97289705320468e-05,
      "loss": 1.041118049621582,
      "num_input_tokens_seen": 15422575872,
      "step": 54230,
      "train_runtime": 528166.6873,
      "train_tokens_per_second": 29200.206
    },
    {
      "epoch": 1.9191188990882493,
      "grad_norm": 1.515625,
      "learning_rate": 1.9727434880932412e-05,
      "loss": 1.0453954696655274,
      "num_input_tokens_seen": 15425396160,
      "step": 54240,
      "train_runtime": 528264.8222,
      "train_tokens_per_second": 29200.12
    },
    {
      "epoch": 1.9194727193519783,
      "grad_norm": 1.59375,
      "learning_rate": 1.972589958835532e-05,
      "loss": 1.0476540565490722,
      "num_input_tokens_seen": 15428272832,
      "step": 54250,
      "train_runtime": 528364.7472,
      "train_tokens_per_second": 29200.042
    },
    {
      "epoch": 1.9198265396157068,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9724364654176036e-05,
      "loss": 1.0476078987121582,
      "num_input_tokens_seen": 15431049664,
      "step": 54260,
      "train_runtime": 528458.1459,
      "train_tokens_per_second": 29200.136
    },
    {
      "epoch": 1.9201803598794358,
      "grad_norm": 1.6640625,
      "learning_rate": 1.9722830078255144e-05,
      "loss": 1.050948715209961,
      "num_input_tokens_seen": 15433842304,
      "step": 54270,
      "train_runtime": 528553.3546,
      "train_tokens_per_second": 29200.16
    },
    {
      "epoch": 1.9205341801431646,
      "grad_norm": 1.53125,
      "learning_rate": 1.9721295860453297e-05,
      "loss": 1.0488189697265624,
      "num_input_tokens_seen": 15436725376,
      "step": 54280,
      "train_runtime": 528654.9709,
      "train_tokens_per_second": 29200.0
    },
    {
      "epoch": 1.9208880004068933,
      "grad_norm": 1.59375,
      "learning_rate": 1.971976200063123e-05,
      "loss": 1.0513479232788085,
      "num_input_tokens_seen": 15439570304,
      "step": 54290,
      "train_runtime": 528751.1134,
      "train_tokens_per_second": 29200.071
    },
    {
      "epoch": 1.921241820670622,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9718228498649746e-05,
      "loss": 1.0436861038208007,
      "num_input_tokens_seen": 15442452736,
      "step": 54300,
      "train_runtime": 528853.5105,
      "train_tokens_per_second": 29199.868
    },
    {
      "epoch": 1.9215956409343509,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9716695354369742e-05,
      "loss": 1.0611928939819335,
      "num_input_tokens_seen": 15445309888,
      "step": 54310,
      "train_runtime": 528951.8121,
      "train_tokens_per_second": 29199.843
    },
    {
      "epoch": 1.9219494611980796,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9715162567652167e-05,
      "loss": 1.0502029418945313,
      "num_input_tokens_seen": 15448118336,
      "step": 54320,
      "train_runtime": 529048.528,
      "train_tokens_per_second": 29199.813
    },
    {
      "epoch": 1.9223032814618084,
      "grad_norm": 1.578125,
      "learning_rate": 1.9713630138358067e-05,
      "loss": 1.0395776748657226,
      "num_input_tokens_seen": 15450951168,
      "step": 54330,
      "train_runtime": 529147.3706,
      "train_tokens_per_second": 29199.713
    },
    {
      "epoch": 1.9226571017255372,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9712098066348543e-05,
      "loss": 1.055473804473877,
      "num_input_tokens_seen": 15453823552,
      "step": 54340,
      "train_runtime": 529246.3711,
      "train_tokens_per_second": 29199.678
    },
    {
      "epoch": 1.923010921989266,
      "grad_norm": 1.6171875,
      "learning_rate": 1.971056635148479e-05,
      "loss": 1.0320868492126465,
      "num_input_tokens_seen": 15456641280,
      "step": 54350,
      "train_runtime": 529342.9127,
      "train_tokens_per_second": 29199.676
    },
    {
      "epoch": 1.923364742252995,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9709034993628065e-05,
      "loss": 1.0372796058654785,
      "num_input_tokens_seen": 15459451392,
      "step": 54360,
      "train_runtime": 529438.65,
      "train_tokens_per_second": 29199.703
    },
    {
      "epoch": 1.9237185625167235,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9707503992639716e-05,
      "loss": 1.046279525756836,
      "num_input_tokens_seen": 15462280512,
      "step": 54370,
      "train_runtime": 529535.5227,
      "train_tokens_per_second": 29199.704
    },
    {
      "epoch": 1.9240723827804525,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9705973348381145e-05,
      "loss": 1.0353227615356446,
      "num_input_tokens_seen": 15465139904,
      "step": 54380,
      "train_runtime": 529632.2458,
      "train_tokens_per_second": 29199.77
    },
    {
      "epoch": 1.924426203044181,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9704443060713846e-05,
      "loss": 1.029578971862793,
      "num_input_tokens_seen": 15467953216,
      "step": 54390,
      "train_runtime": 529728.088,
      "train_tokens_per_second": 29199.798
    },
    {
      "epoch": 1.92478002330791,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9702913129499384e-05,
      "loss": 1.056861972808838,
      "num_input_tokens_seen": 15470823872,
      "step": 54400,
      "train_runtime": 529823.2767,
      "train_tokens_per_second": 29199.97
    },
    {
      "epoch": 1.9251338435716385,
      "grad_norm": 1.59375,
      "learning_rate": 1.9701383554599397e-05,
      "loss": 1.0509902954101562,
      "num_input_tokens_seen": 15473629376,
      "step": 54410,
      "train_runtime": 529921.9003,
      "train_tokens_per_second": 29199.83
    },
    {
      "epoch": 1.9254876638353675,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9699854335875603e-05,
      "loss": 1.0375782012939454,
      "num_input_tokens_seen": 15476444864,
      "step": 54420,
      "train_runtime": 530016.9905,
      "train_tokens_per_second": 29199.903
    },
    {
      "epoch": 1.925841484099096,
      "grad_norm": 1.546875,
      "learning_rate": 1.9698325473189788e-05,
      "loss": 1.0370683670043945,
      "num_input_tokens_seen": 15479297408,
      "step": 54430,
      "train_runtime": 530114.1425,
      "train_tokens_per_second": 29199.933
    },
    {
      "epoch": 1.926195304362825,
      "grad_norm": 1.5859375,
      "learning_rate": 1.969679696640382e-05,
      "loss": 1.0302406311035157,
      "num_input_tokens_seen": 15482150528,
      "step": 54440,
      "train_runtime": 530210.5908,
      "train_tokens_per_second": 29200.002
    },
    {
      "epoch": 1.9265491246265538,
      "grad_norm": 1.59375,
      "learning_rate": 1.9695268815379634e-05,
      "loss": 1.02738676071167,
      "num_input_tokens_seen": 15485021312,
      "step": 54450,
      "train_runtime": 530311.4203,
      "train_tokens_per_second": 29199.864
    },
    {
      "epoch": 1.9269029448902826,
      "grad_norm": 1.640625,
      "learning_rate": 1.9693741019979244e-05,
      "loss": 1.0425247192382812,
      "num_input_tokens_seen": 15487830080,
      "step": 54460,
      "train_runtime": 530405.2893,
      "train_tokens_per_second": 29199.992
    },
    {
      "epoch": 1.9272567651540113,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9692213580064744e-05,
      "loss": 1.04449520111084,
      "num_input_tokens_seen": 15490663424,
      "step": 54470,
      "train_runtime": 530505.3813,
      "train_tokens_per_second": 29199.823
    },
    {
      "epoch": 1.92761058541774,
      "grad_norm": 1.609375,
      "learning_rate": 1.9690686495498302e-05,
      "loss": 1.0304500579833984,
      "num_input_tokens_seen": 15493534464,
      "step": 54480,
      "train_runtime": 530604.8153,
      "train_tokens_per_second": 29199.762
    },
    {
      "epoch": 1.9279644056814689,
      "grad_norm": 1.625,
      "learning_rate": 1.9689159766142147e-05,
      "loss": 1.0417848587036134,
      "num_input_tokens_seen": 15496378368,
      "step": 54490,
      "train_runtime": 530701.6709,
      "train_tokens_per_second": 29199.792
    },
    {
      "epoch": 1.9283182259451976,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9687633391858605e-05,
      "loss": 1.0525657653808593,
      "num_input_tokens_seen": 15499240064,
      "step": 54500,
      "train_runtime": 530800.8593,
      "train_tokens_per_second": 29199.727
    },
    {
      "epoch": 1.9286720462089264,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9686107372510057e-05,
      "loss": 1.0589433670043946,
      "num_input_tokens_seen": 15502129664,
      "step": 54510,
      "train_runtime": 530898.5879,
      "train_tokens_per_second": 29199.794
    },
    {
      "epoch": 1.9290258664726552,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9684581707958966e-05,
      "loss": 1.0395743370056152,
      "num_input_tokens_seen": 15504955584,
      "step": 54520,
      "train_runtime": 530994.2147,
      "train_tokens_per_second": 29199.858
    },
    {
      "epoch": 1.9293796867363842,
      "grad_norm": 1.59375,
      "learning_rate": 1.9683056398067875e-05,
      "loss": 1.0612245559692384,
      "num_input_tokens_seen": 15507822912,
      "step": 54530,
      "train_runtime": 531094.5644,
      "train_tokens_per_second": 29199.739
    },
    {
      "epoch": 1.9297335070001127,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9681531442699394e-05,
      "loss": 1.0379860877990723,
      "num_input_tokens_seen": 15510617088,
      "step": 54540,
      "train_runtime": 531191.8027,
      "train_tokens_per_second": 29199.654
    },
    {
      "epoch": 1.9300873272638417,
      "grad_norm": 1.578125,
      "learning_rate": 1.9680006841716207e-05,
      "loss": 1.0390233993530273,
      "num_input_tokens_seen": 15513424640,
      "step": 54550,
      "train_runtime": 531289.7801,
      "train_tokens_per_second": 29199.554
    },
    {
      "epoch": 1.9304411475275702,
      "grad_norm": 1.515625,
      "learning_rate": 1.967848259498108e-05,
      "loss": 1.0409663200378418,
      "num_input_tokens_seen": 15516254272,
      "step": 54560,
      "train_runtime": 531385.5698,
      "train_tokens_per_second": 29199.615
    },
    {
      "epoch": 1.9307949677912992,
      "grad_norm": 1.59375,
      "learning_rate": 1.967695870235685e-05,
      "loss": 1.0425911903381349,
      "num_input_tokens_seen": 15519045440,
      "step": 54570,
      "train_runtime": 531482.8683,
      "train_tokens_per_second": 29199.521
    },
    {
      "epoch": 1.9311487880550278,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9675435163706427e-05,
      "loss": 1.0364057540893554,
      "num_input_tokens_seen": 15521874368,
      "step": 54580,
      "train_runtime": 531577.8382,
      "train_tokens_per_second": 29199.627
    },
    {
      "epoch": 1.9315026083187568,
      "grad_norm": 1.59375,
      "learning_rate": 1.967391197889279e-05,
      "loss": 1.0448822021484374,
      "num_input_tokens_seen": 15524670592,
      "step": 54590,
      "train_runtime": 531671.6045,
      "train_tokens_per_second": 29199.736
    },
    {
      "epoch": 1.9318564285824853,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9672389147779e-05,
      "loss": 1.0451793670654297,
      "num_input_tokens_seen": 15527475904,
      "step": 54600,
      "train_runtime": 531765.824,
      "train_tokens_per_second": 29199.838
    },
    {
      "epoch": 1.9322102488462143,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9670866670228194e-05,
      "loss": 1.0351902008056642,
      "num_input_tokens_seen": 15530364736,
      "step": 54610,
      "train_runtime": 531863.4297,
      "train_tokens_per_second": 29199.911
    },
    {
      "epoch": 1.932564069109943,
      "grad_norm": 1.59375,
      "learning_rate": 1.9669344546103576e-05,
      "loss": 1.0437545776367188,
      "num_input_tokens_seen": 15533226624,
      "step": 54620,
      "train_runtime": 531963.3311,
      "train_tokens_per_second": 29199.807
    },
    {
      "epoch": 1.9329178893736718,
      "grad_norm": 1.578125,
      "learning_rate": 1.9667822775268428e-05,
      "loss": 1.0456543922424317,
      "num_input_tokens_seen": 15536062208,
      "step": 54630,
      "train_runtime": 532057.6358,
      "train_tokens_per_second": 29199.961
    },
    {
      "epoch": 1.9332717096374006,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9666301357586107e-05,
      "loss": 1.0550376892089843,
      "num_input_tokens_seen": 15538880256,
      "step": 54640,
      "train_runtime": 532152.8703,
      "train_tokens_per_second": 29200.031
    },
    {
      "epoch": 1.9336255299011293,
      "grad_norm": 1.4921875,
      "learning_rate": 1.9664780292920036e-05,
      "loss": 1.0527334213256836,
      "num_input_tokens_seen": 15541767296,
      "step": 54650,
      "train_runtime": 532253.1634,
      "train_tokens_per_second": 29199.953
    },
    {
      "epoch": 1.9339793501648581,
      "grad_norm": 1.640625,
      "learning_rate": 1.9663259581133726e-05,
      "loss": 1.039912796020508,
      "num_input_tokens_seen": 15544632128,
      "step": 54660,
      "train_runtime": 532350.7064,
      "train_tokens_per_second": 29199.984
    },
    {
      "epoch": 1.9343331704285869,
      "grad_norm": 1.546875,
      "learning_rate": 1.9661739222090753e-05,
      "loss": 1.0293249130249023,
      "num_input_tokens_seen": 15547487360,
      "step": 54670,
      "train_runtime": 532448.8058,
      "train_tokens_per_second": 29199.967
    },
    {
      "epoch": 1.9346869906923156,
      "grad_norm": 1.6171875,
      "learning_rate": 1.966021921565476e-05,
      "loss": 1.0374914169311524,
      "num_input_tokens_seen": 15550336384,
      "step": 54680,
      "train_runtime": 532546.7905,
      "train_tokens_per_second": 29199.944
    },
    {
      "epoch": 1.9350408109560444,
      "grad_norm": 1.59375,
      "learning_rate": 1.965869956168948e-05,
      "loss": 1.0398994445800782,
      "num_input_tokens_seen": 15553125504,
      "step": 54690,
      "train_runtime": 532639.3779,
      "train_tokens_per_second": 29200.105
    },
    {
      "epoch": 1.9353946312197734,
      "grad_norm": 1.6171875,
      "learning_rate": 1.965718026005871e-05,
      "loss": 1.0417970657348632,
      "num_input_tokens_seen": 15555997760,
      "step": 54700,
      "train_runtime": 532737.1151,
      "train_tokens_per_second": 29200.139
    },
    {
      "epoch": 1.935748451483502,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9655661310626317e-05,
      "loss": 1.045709991455078,
      "num_input_tokens_seen": 15558850560,
      "step": 54710,
      "train_runtime": 532835.0994,
      "train_tokens_per_second": 29200.123
    },
    {
      "epoch": 1.936102271747231,
      "grad_norm": 1.5078125,
      "learning_rate": 1.965414271325625e-05,
      "loss": 1.0322181701660156,
      "num_input_tokens_seen": 15561740672,
      "step": 54720,
      "train_runtime": 532933.5401,
      "train_tokens_per_second": 29200.153
    },
    {
      "epoch": 1.9364560920109595,
      "grad_norm": 1.609375,
      "learning_rate": 1.9652624467812534e-05,
      "loss": 1.048725414276123,
      "num_input_tokens_seen": 15564547840,
      "step": 54730,
      "train_runtime": 533029.1909,
      "train_tokens_per_second": 29200.179
    },
    {
      "epoch": 1.9368099122746885,
      "grad_norm": 1.5703125,
      "learning_rate": 1.965110657415925e-05,
      "loss": 1.0480867385864259,
      "num_input_tokens_seen": 15567381760,
      "step": 54740,
      "train_runtime": 533124.1841,
      "train_tokens_per_second": 29200.292
    },
    {
      "epoch": 1.937163732538417,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9649589032160576e-05,
      "loss": 1.0289634704589843,
      "num_input_tokens_seen": 15570193216,
      "step": 54750,
      "train_runtime": 533219.1935,
      "train_tokens_per_second": 29200.362
    },
    {
      "epoch": 1.937517552802146,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9648071841680746e-05,
      "loss": 1.0393794059753418,
      "num_input_tokens_seen": 15573023872,
      "step": 54760,
      "train_runtime": 533315.0343,
      "train_tokens_per_second": 29200.422
    },
    {
      "epoch": 1.9378713730658745,
      "grad_norm": 1.609375,
      "learning_rate": 1.964655500258407e-05,
      "loss": 1.029646873474121,
      "num_input_tokens_seen": 15575857152,
      "step": 54770,
      "train_runtime": 533410.6613,
      "train_tokens_per_second": 29200.498
    },
    {
      "epoch": 1.9382251933296035,
      "grad_norm": 1.609375,
      "learning_rate": 1.964503851473494e-05,
      "loss": 1.0473951339721679,
      "num_input_tokens_seen": 15578714112,
      "step": 54780,
      "train_runtime": 533511.6268,
      "train_tokens_per_second": 29200.327
    },
    {
      "epoch": 1.9385790135933323,
      "grad_norm": 1.546875,
      "learning_rate": 1.9643522377997807e-05,
      "loss": 1.0294897079467773,
      "num_input_tokens_seen": 15581578688,
      "step": 54790,
      "train_runtime": 533612.7742,
      "train_tokens_per_second": 29200.161
    },
    {
      "epoch": 1.938932833857061,
      "grad_norm": 1.546875,
      "learning_rate": 1.9642006592237216e-05,
      "loss": 1.0482364654541017,
      "num_input_tokens_seen": 15584446336,
      "step": 54800,
      "train_runtime": 533716.7361,
      "train_tokens_per_second": 29199.846
    },
    {
      "epoch": 1.9392866541207898,
      "grad_norm": 1.5625,
      "learning_rate": 1.9640491157317767e-05,
      "loss": 1.0503828048706054,
      "num_input_tokens_seen": 15587297472,
      "step": 54810,
      "train_runtime": 533814.4477,
      "train_tokens_per_second": 29199.842
    },
    {
      "epoch": 1.9396404743845186,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9638976073104138e-05,
      "loss": 1.0451245307922363,
      "num_input_tokens_seen": 15590176064,
      "step": 54820,
      "train_runtime": 533916.127,
      "train_tokens_per_second": 29199.673
    },
    {
      "epoch": 1.9399942946482474,
      "grad_norm": 1.609375,
      "learning_rate": 1.9637461339461084e-05,
      "loss": 1.0450533866882323,
      "num_input_tokens_seen": 15593021568,
      "step": 54830,
      "train_runtime": 534014.5382,
      "train_tokens_per_second": 29199.62
    },
    {
      "epoch": 1.9403481149119761,
      "grad_norm": 1.5625,
      "learning_rate": 1.9635946956253426e-05,
      "loss": 1.0469465255737305,
      "num_input_tokens_seen": 15595863488,
      "step": 54840,
      "train_runtime": 534111.7495,
      "train_tokens_per_second": 29199.626
    },
    {
      "epoch": 1.9407019351757049,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9634432923346063e-05,
      "loss": 1.0235488891601563,
      "num_input_tokens_seen": 15598663552,
      "step": 54850,
      "train_runtime": 534206.8058,
      "train_tokens_per_second": 29199.672
    },
    {
      "epoch": 1.9410557554394336,
      "grad_norm": 1.6015625,
      "learning_rate": 1.963291924060397e-05,
      "loss": 1.0349287033081054,
      "num_input_tokens_seen": 15601518336,
      "step": 54860,
      "train_runtime": 534306.1896,
      "train_tokens_per_second": 29199.584
    },
    {
      "epoch": 1.9414095757031626,
      "grad_norm": 1.6171875,
      "learning_rate": 1.963140590789219e-05,
      "loss": 1.0345143318176269,
      "num_input_tokens_seen": 15604354688,
      "step": 54870,
      "train_runtime": 534401.8732,
      "train_tokens_per_second": 29199.663
    },
    {
      "epoch": 1.9417633959668912,
      "grad_norm": 1.609375,
      "learning_rate": 1.9629892925075834e-05,
      "loss": 1.0430522918701173,
      "num_input_tokens_seen": 15607185728,
      "step": 54880,
      "train_runtime": 534498.5598,
      "train_tokens_per_second": 29199.678
    },
    {
      "epoch": 1.9421172162306202,
      "grad_norm": 1.609375,
      "learning_rate": 1.9628380292020093e-05,
      "loss": 1.0457717895507812,
      "num_input_tokens_seen": 15609983744,
      "step": 54890,
      "train_runtime": 534592.0577,
      "train_tokens_per_second": 29199.805
    },
    {
      "epoch": 1.9424710364943487,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9626868008590238e-05,
      "loss": 1.0413256645202638,
      "num_input_tokens_seen": 15612857152,
      "step": 54900,
      "train_runtime": 534690.5749,
      "train_tokens_per_second": 29199.799
    },
    {
      "epoch": 1.9428248567580777,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9625356074651595e-05,
      "loss": 1.0460908889770508,
      "num_input_tokens_seen": 15615759808,
      "step": 54910,
      "train_runtime": 534790.8535,
      "train_tokens_per_second": 29199.751
    },
    {
      "epoch": 1.9431786770218062,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9623844490069577e-05,
      "loss": 1.0443761825561524,
      "num_input_tokens_seen": 15618584640,
      "step": 54920,
      "train_runtime": 534886.3594,
      "train_tokens_per_second": 29199.819
    },
    {
      "epoch": 1.9435324972855352,
      "grad_norm": 1.6640625,
      "learning_rate": 1.9622333254709655e-05,
      "loss": 1.0493027687072753,
      "num_input_tokens_seen": 15621465664,
      "step": 54930,
      "train_runtime": 534985.6484,
      "train_tokens_per_second": 29199.785
    },
    {
      "epoch": 1.943886317549264,
      "grad_norm": 1.609375,
      "learning_rate": 1.9620822368437388e-05,
      "loss": 1.0479966163635255,
      "num_input_tokens_seen": 15624342592,
      "step": 54940,
      "train_runtime": 535084.5082,
      "train_tokens_per_second": 29199.766
    },
    {
      "epoch": 1.9442401378129928,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9619311831118405e-05,
      "loss": 1.0443848609924316,
      "num_input_tokens_seen": 15627171520,
      "step": 54950,
      "train_runtime": 535181.5305,
      "train_tokens_per_second": 29199.759
    },
    {
      "epoch": 1.9445939580767215,
      "grad_norm": 1.609375,
      "learning_rate": 1.961780164261839e-05,
      "loss": 1.0547679901123046,
      "num_input_tokens_seen": 15629987008,
      "step": 54960,
      "train_runtime": 535276.2349,
      "train_tokens_per_second": 29199.852
    },
    {
      "epoch": 1.9449477783404503,
      "grad_norm": 1.5703125,
      "learning_rate": 1.961629180280313e-05,
      "loss": 1.0513189315795899,
      "num_input_tokens_seen": 15632884096,
      "step": 54970,
      "train_runtime": 535379.0372,
      "train_tokens_per_second": 29199.657
    },
    {
      "epoch": 1.945301598604179,
      "grad_norm": 1.59375,
      "learning_rate": 1.9614782311538455e-05,
      "loss": 1.0418792724609376,
      "num_input_tokens_seen": 15635758080,
      "step": 54980,
      "train_runtime": 535476.3452,
      "train_tokens_per_second": 29199.718
    },
    {
      "epoch": 1.9456554188679078,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9613273168690278e-05,
      "loss": 1.0422185897827148,
      "num_input_tokens_seen": 15638642944,
      "step": 54990,
      "train_runtime": 535574.2466,
      "train_tokens_per_second": 29199.766
    },
    {
      "epoch": 1.9460092391316366,
      "grad_norm": 1.515625,
      "learning_rate": 1.9611764374124592e-05,
      "loss": 1.0568193435668944,
      "num_input_tokens_seen": 15641534336,
      "step": 55000,
      "train_runtime": 535675.691,
      "train_tokens_per_second": 29199.634
    },
    {
      "epoch": 1.9460092391316366,
      "eval_loss": 1.0222429037094116,
      "eval_runtime": 8.4352,
      "eval_samples_per_second": 472.781,
      "eval_steps_per_second": 3.794,
      "num_input_tokens_seen": 15641534336,
      "step": 55000
    },
    {
      "epoch": 1.9463630593953654,
      "grad_norm": 1.515625,
      "learning_rate": 1.9610255927707456e-05,
      "loss": 1.0446903228759765,
      "num_input_tokens_seen": 15644404544,
      "step": 55010,
      "train_runtime": 535803.417,
      "train_tokens_per_second": 29198.031
    },
    {
      "epoch": 1.9467168796590941,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9608747829304998e-05,
      "loss": 1.0423757553100585,
      "num_input_tokens_seen": 15647263296,
      "step": 55020,
      "train_runtime": 535903.3634,
      "train_tokens_per_second": 29197.92
    },
    {
      "epoch": 1.947070699922823,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9607240078783416e-05,
      "loss": 1.034714126586914,
      "num_input_tokens_seen": 15650120320,
      "step": 55030,
      "train_runtime": 536000.7648,
      "train_tokens_per_second": 29197.944
    },
    {
      "epoch": 1.9474245201865519,
      "grad_norm": 1.5546875,
      "learning_rate": 1.960573267600899e-05,
      "loss": 1.029018020629883,
      "num_input_tokens_seen": 15652989696,
      "step": 55040,
      "train_runtime": 536099.7843,
      "train_tokens_per_second": 29197.903
    },
    {
      "epoch": 1.9477783404502804,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9604225620848072e-05,
      "loss": 1.0611921310424806,
      "num_input_tokens_seen": 15655835264,
      "step": 55050,
      "train_runtime": 536198.6656,
      "train_tokens_per_second": 29197.826
    },
    {
      "epoch": 1.9481321607140094,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9602718913167075e-05,
      "loss": 1.04208345413208,
      "num_input_tokens_seen": 15658645696,
      "step": 55060,
      "train_runtime": 536293.97,
      "train_tokens_per_second": 29197.878
    },
    {
      "epoch": 1.948485980977738,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9601212552832483e-05,
      "loss": 1.031881046295166,
      "num_input_tokens_seen": 15661494656,
      "step": 55070,
      "train_runtime": 536393.4246,
      "train_tokens_per_second": 29197.775
    },
    {
      "epoch": 1.948839801241467,
      "grad_norm": 1.59375,
      "learning_rate": 1.959970653971087e-05,
      "loss": 1.0476322174072266,
      "num_input_tokens_seen": 15664384128,
      "step": 55080,
      "train_runtime": 536494.1733,
      "train_tokens_per_second": 29197.678
    },
    {
      "epoch": 1.9491936215051955,
      "grad_norm": 1.625,
      "learning_rate": 1.9598200873668862e-05,
      "loss": 1.0531925201416015,
      "num_input_tokens_seen": 15667203200,
      "step": 55090,
      "train_runtime": 536589.4855,
      "train_tokens_per_second": 29197.745
    },
    {
      "epoch": 1.9495474417689245,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9596695554573167e-05,
      "loss": 1.0471609115600586,
      "num_input_tokens_seen": 15670068224,
      "step": 55100,
      "train_runtime": 536691.9341,
      "train_tokens_per_second": 29197.51
    },
    {
      "epoch": 1.9499012620326532,
      "grad_norm": 1.5546875,
      "learning_rate": 1.959519058229056e-05,
      "loss": 1.0371974945068358,
      "num_input_tokens_seen": 15672869056,
      "step": 55110,
      "train_runtime": 536787.8014,
      "train_tokens_per_second": 29197.513
    },
    {
      "epoch": 1.950255082296382,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9593685956687895e-05,
      "loss": 1.0472349166870116,
      "num_input_tokens_seen": 15675753984,
      "step": 55120,
      "train_runtime": 536885.7258,
      "train_tokens_per_second": 29197.561
    },
    {
      "epoch": 1.9506089025601108,
      "grad_norm": 1.6796875,
      "learning_rate": 1.9592181677632094e-05,
      "loss": 1.04056978225708,
      "num_input_tokens_seen": 15678597760,
      "step": 55130,
      "train_runtime": 536984.1014,
      "train_tokens_per_second": 29197.508
    },
    {
      "epoch": 1.9509627228238395,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9590677744990145e-05,
      "loss": 1.0431629180908204,
      "num_input_tokens_seen": 15681442496,
      "step": 55140,
      "train_runtime": 537082.4304,
      "train_tokens_per_second": 29197.459
    },
    {
      "epoch": 1.9513165430875683,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9589174158629106e-05,
      "loss": 1.0493209838867188,
      "num_input_tokens_seen": 15684275456,
      "step": 55150,
      "train_runtime": 537179.8813,
      "train_tokens_per_second": 29197.436
    },
    {
      "epoch": 1.951670363351297,
      "grad_norm": 1.546875,
      "learning_rate": 1.958767091841612e-05,
      "loss": 1.0450294494628907,
      "num_input_tokens_seen": 15687186944,
      "step": 55160,
      "train_runtime": 537278.8794,
      "train_tokens_per_second": 29197.476
    },
    {
      "epoch": 1.9520241836150258,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9586168024218395e-05,
      "loss": 1.0342535972595215,
      "num_input_tokens_seen": 15690080128,
      "step": 55170,
      "train_runtime": 537379.6619,
      "train_tokens_per_second": 29197.384
    },
    {
      "epoch": 1.9523780038787546,
      "grad_norm": 1.5078125,
      "learning_rate": 1.9584665475903198e-05,
      "loss": 1.0479907989501953,
      "num_input_tokens_seen": 15692963840,
      "step": 55180,
      "train_runtime": 537480.3119,
      "train_tokens_per_second": 29197.281
    },
    {
      "epoch": 1.9527318241424836,
      "grad_norm": 1.578125,
      "learning_rate": 1.9583163273337892e-05,
      "loss": 1.050635528564453,
      "num_input_tokens_seen": 15695856960,
      "step": 55190,
      "train_runtime": 537581.3326,
      "train_tokens_per_second": 29197.176
    },
    {
      "epoch": 1.9530856444062121,
      "grad_norm": 1.578125,
      "learning_rate": 1.9581661416389887e-05,
      "loss": 1.0435422897338866,
      "num_input_tokens_seen": 15698729088,
      "step": 55200,
      "train_runtime": 537681.9812,
      "train_tokens_per_second": 29197.053
    },
    {
      "epoch": 1.9534394646699411,
      "grad_norm": 1.59375,
      "learning_rate": 1.9580159904926674e-05,
      "loss": 1.0374542236328126,
      "num_input_tokens_seen": 15701555520,
      "step": 55210,
      "train_runtime": 537776.408,
      "train_tokens_per_second": 29197.182
    },
    {
      "epoch": 1.9537932849336697,
      "grad_norm": 1.59375,
      "learning_rate": 1.9578658738815823e-05,
      "loss": 1.0452468872070313,
      "num_input_tokens_seen": 15704386112,
      "step": 55220,
      "train_runtime": 537875.098,
      "train_tokens_per_second": 29197.087
    },
    {
      "epoch": 1.9541471051973986,
      "grad_norm": 1.53125,
      "learning_rate": 1.957715791792496e-05,
      "loss": 1.0392741203308105,
      "num_input_tokens_seen": 15707238720,
      "step": 55230,
      "train_runtime": 537974.4391,
      "train_tokens_per_second": 29196.998
    },
    {
      "epoch": 1.9545009254611272,
      "grad_norm": 1.5234375,
      "learning_rate": 1.9575657442121788e-05,
      "loss": 1.0332864761352538,
      "num_input_tokens_seen": 15710040640,
      "step": 55240,
      "train_runtime": 538069.3769,
      "train_tokens_per_second": 29197.054
    },
    {
      "epoch": 1.9548547457248562,
      "grad_norm": 1.640625,
      "learning_rate": 1.957415731127409e-05,
      "loss": 1.0490318298339845,
      "num_input_tokens_seen": 15712885248,
      "step": 55250,
      "train_runtime": 538167.692,
      "train_tokens_per_second": 29197.006
    },
    {
      "epoch": 1.9552085659885847,
      "grad_norm": 1.6328125,
      "learning_rate": 1.957265752524971e-05,
      "loss": 1.0403959274291992,
      "num_input_tokens_seen": 15715707648,
      "step": 55260,
      "train_runtime": 538262.7725,
      "train_tokens_per_second": 29197.092
    },
    {
      "epoch": 1.9555623862523137,
      "grad_norm": 1.578125,
      "learning_rate": 1.9571158083916562e-05,
      "loss": 1.0560995101928712,
      "num_input_tokens_seen": 15718585024,
      "step": 55270,
      "train_runtime": 538362.5059,
      "train_tokens_per_second": 29197.028
    },
    {
      "epoch": 1.9559162065160425,
      "grad_norm": 1.578125,
      "learning_rate": 1.9569658987142637e-05,
      "loss": 1.0561267852783203,
      "num_input_tokens_seen": 15721424576,
      "step": 55280,
      "train_runtime": 538458.573,
      "train_tokens_per_second": 29197.092
    },
    {
      "epoch": 1.9562700267797712,
      "grad_norm": 1.515625,
      "learning_rate": 1.9568160234795992e-05,
      "loss": 1.051699447631836,
      "num_input_tokens_seen": 15724310208,
      "step": 55290,
      "train_runtime": 538558.7796,
      "train_tokens_per_second": 29197.018
    },
    {
      "epoch": 1.9566238470435,
      "grad_norm": 1.546875,
      "learning_rate": 1.956666182674476e-05,
      "loss": 1.0442497253417968,
      "num_input_tokens_seen": 15727165312,
      "step": 55300,
      "train_runtime": 538658.3119,
      "train_tokens_per_second": 29196.923
    },
    {
      "epoch": 1.9569776673072288,
      "grad_norm": 1.546875,
      "learning_rate": 1.9565163762857133e-05,
      "loss": 1.049232578277588,
      "num_input_tokens_seen": 15730059968,
      "step": 55310,
      "train_runtime": 538759.7281,
      "train_tokens_per_second": 29196.8
    },
    {
      "epoch": 1.9573314875709575,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9563666043001394e-05,
      "loss": 1.037040901184082,
      "num_input_tokens_seen": 15732864960,
      "step": 55320,
      "train_runtime": 538855.9043,
      "train_tokens_per_second": 29196.794
    },
    {
      "epoch": 1.9576853078346863,
      "grad_norm": 1.546875,
      "learning_rate": 1.9562168667045876e-05,
      "loss": 1.042534351348877,
      "num_input_tokens_seen": 15735718464,
      "step": 55330,
      "train_runtime": 538953.0891,
      "train_tokens_per_second": 29196.824
    },
    {
      "epoch": 1.958039128098415,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9560671634858988e-05,
      "loss": 1.0477263450622558,
      "num_input_tokens_seen": 15738593088,
      "step": 55340,
      "train_runtime": 539051.3222,
      "train_tokens_per_second": 29196.836
    },
    {
      "epoch": 1.9583929483621438,
      "grad_norm": 1.5625,
      "learning_rate": 1.9559174946309216e-05,
      "loss": 1.0423012733459474,
      "num_input_tokens_seen": 15741446784,
      "step": 55350,
      "train_runtime": 539146.8776,
      "train_tokens_per_second": 29196.954
    },
    {
      "epoch": 1.9587467686258728,
      "grad_norm": 1.53125,
      "learning_rate": 1.955767860126512e-05,
      "loss": 1.0428354263305664,
      "num_input_tokens_seen": 15744336704,
      "step": 55360,
      "train_runtime": 539245.6882,
      "train_tokens_per_second": 29196.964
    },
    {
      "epoch": 1.9591005888896014,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9556182599595313e-05,
      "loss": 1.045893096923828,
      "num_input_tokens_seen": 15747229056,
      "step": 55370,
      "train_runtime": 539343.7466,
      "train_tokens_per_second": 29197.018
    },
    {
      "epoch": 1.9594544091533304,
      "grad_norm": 1.515625,
      "learning_rate": 1.95546869411685e-05,
      "loss": 1.0294374465942382,
      "num_input_tokens_seen": 15750091136,
      "step": 55380,
      "train_runtime": 539440.1005,
      "train_tokens_per_second": 29197.108
    },
    {
      "epoch": 1.959808229417059,
      "grad_norm": 1.609375,
      "learning_rate": 1.9553191625853427e-05,
      "loss": 1.0479812622070312,
      "num_input_tokens_seen": 15752914624,
      "step": 55390,
      "train_runtime": 539537.1526,
      "train_tokens_per_second": 29197.09
    },
    {
      "epoch": 1.9601620496807879,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9551696653518943e-05,
      "loss": 1.0463621139526367,
      "num_input_tokens_seen": 15755769664,
      "step": 55400,
      "train_runtime": 539635.544,
      "train_tokens_per_second": 29197.057
    },
    {
      "epoch": 1.9605158699445164,
      "grad_norm": 1.59375,
      "learning_rate": 1.9550202024033947e-05,
      "loss": 1.0471301078796387,
      "num_input_tokens_seen": 15758620224,
      "step": 55410,
      "train_runtime": 539731.7235,
      "train_tokens_per_second": 29197.135
    },
    {
      "epoch": 1.9608696902082454,
      "grad_norm": 1.59375,
      "learning_rate": 1.9548707737267412e-05,
      "loss": 1.0317166328430176,
      "num_input_tokens_seen": 15761456640,
      "step": 55420,
      "train_runtime": 539828.2251,
      "train_tokens_per_second": 29197.17
    },
    {
      "epoch": 1.961223510471974,
      "grad_norm": 1.609375,
      "learning_rate": 1.9547213793088384e-05,
      "loss": 1.0495126724243165,
      "num_input_tokens_seen": 15764266944,
      "step": 55430,
      "train_runtime": 539923.5763,
      "train_tokens_per_second": 29197.219
    },
    {
      "epoch": 1.961577330735703,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9545720191365983e-05,
      "loss": 1.0511842727661134,
      "num_input_tokens_seen": 15767081344,
      "step": 55440,
      "train_runtime": 540018.5058,
      "train_tokens_per_second": 29197.298
    },
    {
      "epoch": 1.9619311509994317,
      "grad_norm": 1.578125,
      "learning_rate": 1.9544226931969382e-05,
      "loss": 1.0500625610351562,
      "num_input_tokens_seen": 15769919872,
      "step": 55450,
      "train_runtime": 540115.8197,
      "train_tokens_per_second": 29197.293
    },
    {
      "epoch": 1.9622849712631605,
      "grad_norm": 1.5078125,
      "learning_rate": 1.9542734014767848e-05,
      "loss": 1.0513444900512696,
      "num_input_tokens_seen": 15772834752,
      "step": 55460,
      "train_runtime": 540216.8062,
      "train_tokens_per_second": 29197.231
    },
    {
      "epoch": 1.9626387915268892,
      "grad_norm": 1.578125,
      "learning_rate": 1.9541241439630693e-05,
      "loss": 1.0314319610595704,
      "num_input_tokens_seen": 15775712128,
      "step": 55470,
      "train_runtime": 540318.655,
      "train_tokens_per_second": 29197.052
    },
    {
      "epoch": 1.962992611790618,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9539749206427322e-05,
      "loss": 1.0449155807495116,
      "num_input_tokens_seen": 15778560000,
      "step": 55480,
      "train_runtime": 540416.6275,
      "train_tokens_per_second": 29197.029
    },
    {
      "epoch": 1.9633464320543468,
      "grad_norm": 1.5234375,
      "learning_rate": 1.9538257315027194e-05,
      "loss": 1.0404851913452149,
      "num_input_tokens_seen": 15781436992,
      "step": 55490,
      "train_runtime": 540517.0907,
      "train_tokens_per_second": 29196.925
    },
    {
      "epoch": 1.9637002523180755,
      "grad_norm": 1.59375,
      "learning_rate": 1.953676576529984e-05,
      "loss": 1.042249870300293,
      "num_input_tokens_seen": 15784325056,
      "step": 55500,
      "train_runtime": 540616.8595,
      "train_tokens_per_second": 29196.879
    },
    {
      "epoch": 1.9640540725818043,
      "grad_norm": 1.5546875,
      "learning_rate": 1.953527455711487e-05,
      "loss": 1.037540817260742,
      "num_input_tokens_seen": 15787178496,
      "step": 55510,
      "train_runtime": 540713.8364,
      "train_tokens_per_second": 29196.92
    },
    {
      "epoch": 1.964407892845533,
      "grad_norm": 1.453125,
      "learning_rate": 1.9533783690341955e-05,
      "loss": 1.035866641998291,
      "num_input_tokens_seen": 15790024832,
      "step": 55520,
      "train_runtime": 540810.4558,
      "train_tokens_per_second": 29196.967
    },
    {
      "epoch": 1.964761713109262,
      "grad_norm": 1.59375,
      "learning_rate": 1.9532293164850833e-05,
      "loss": 1.0474421501159668,
      "num_input_tokens_seen": 15792909888,
      "step": 55530,
      "train_runtime": 540909.689,
      "train_tokens_per_second": 29196.944
    },
    {
      "epoch": 1.9651155333729906,
      "grad_norm": 1.59375,
      "learning_rate": 1.9530802980511325e-05,
      "loss": 1.044530200958252,
      "num_input_tokens_seen": 15795838272,
      "step": 55540,
      "train_runtime": 541011.2952,
      "train_tokens_per_second": 29196.873
    },
    {
      "epoch": 1.9654693536367196,
      "grad_norm": 1.53125,
      "learning_rate": 1.95293131371933e-05,
      "loss": 1.0464086532592773,
      "num_input_tokens_seen": 15798662848,
      "step": 55550,
      "train_runtime": 541106.3148,
      "train_tokens_per_second": 29196.966
    },
    {
      "epoch": 1.9658231739004481,
      "grad_norm": 1.5625,
      "learning_rate": 1.9527823634766724e-05,
      "loss": 1.048734474182129,
      "num_input_tokens_seen": 15801563648,
      "step": 55560,
      "train_runtime": 541206.6832,
      "train_tokens_per_second": 29196.912
    },
    {
      "epoch": 1.9661769941641771,
      "grad_norm": 1.4765625,
      "learning_rate": 1.952633447310161e-05,
      "loss": 1.039445972442627,
      "num_input_tokens_seen": 15804382336,
      "step": 55570,
      "train_runtime": 541302.5859,
      "train_tokens_per_second": 29196.946
    },
    {
      "epoch": 1.9665308144279057,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9524845652068046e-05,
      "loss": 1.044840145111084,
      "num_input_tokens_seen": 15807244096,
      "step": 55580,
      "train_runtime": 541399.3088,
      "train_tokens_per_second": 29197.016
    },
    {
      "epoch": 1.9668846346916347,
      "grad_norm": 1.578125,
      "learning_rate": 1.9523357171536195e-05,
      "loss": 1.0635669708251954,
      "num_input_tokens_seen": 15810162048,
      "step": 55590,
      "train_runtime": 541502.2489,
      "train_tokens_per_second": 29196.854
    },
    {
      "epoch": 1.9672384549553632,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9521869031376288e-05,
      "loss": 1.0399156570434571,
      "num_input_tokens_seen": 15813060352,
      "step": 55600,
      "train_runtime": 541601.0209,
      "train_tokens_per_second": 29196.881
    },
    {
      "epoch": 1.9675922752190922,
      "grad_norm": 1.578125,
      "learning_rate": 1.9520381231458616e-05,
      "loss": 1.0474230766296386,
      "num_input_tokens_seen": 15815886656,
      "step": 55610,
      "train_runtime": 541696.1407,
      "train_tokens_per_second": 29196.971
    },
    {
      "epoch": 1.967946095482821,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9518893771653555e-05,
      "loss": 1.062067985534668,
      "num_input_tokens_seen": 15818718272,
      "step": 55620,
      "train_runtime": 541790.6724,
      "train_tokens_per_second": 29197.103
    },
    {
      "epoch": 1.9682999157465497,
      "grad_norm": 1.5078125,
      "learning_rate": 1.951740665183153e-05,
      "loss": 1.0537633895874023,
      "num_input_tokens_seen": 15821595008,
      "step": 55630,
      "train_runtime": 541891.3751,
      "train_tokens_per_second": 29196.986
    },
    {
      "epoch": 1.9686537360102785,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9515919871863057e-05,
      "loss": 1.0433271408081055,
      "num_input_tokens_seen": 15824438784,
      "step": 55640,
      "train_runtime": 541990.594,
      "train_tokens_per_second": 29196.888
    },
    {
      "epoch": 1.9690075562740073,
      "grad_norm": 1.515625,
      "learning_rate": 1.9514433431618707e-05,
      "loss": 1.0533550262451172,
      "num_input_tokens_seen": 15827281600,
      "step": 55650,
      "train_runtime": 542086.8524,
      "train_tokens_per_second": 29196.948
    },
    {
      "epoch": 1.969361376537736,
      "grad_norm": 1.5625,
      "learning_rate": 1.951294733096912e-05,
      "loss": 1.0477264404296875,
      "num_input_tokens_seen": 15830160896,
      "step": 55660,
      "train_runtime": 542187.4931,
      "train_tokens_per_second": 29196.839
    },
    {
      "epoch": 1.9697151968014648,
      "grad_norm": 1.59375,
      "learning_rate": 1.951146156978501e-05,
      "loss": 1.0417309761047364,
      "num_input_tokens_seen": 15833006400,
      "step": 55670,
      "train_runtime": 542286.2506,
      "train_tokens_per_second": 29196.769
    },
    {
      "epoch": 1.9700690170651936,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9509976147937163e-05,
      "loss": 1.0411740303039552,
      "num_input_tokens_seen": 15835852608,
      "step": 55680,
      "train_runtime": 542381.8543,
      "train_tokens_per_second": 29196.87
    },
    {
      "epoch": 1.9704228373289223,
      "grad_norm": 1.6171875,
      "learning_rate": 1.950849106529642e-05,
      "loss": 1.0576465606689454,
      "num_input_tokens_seen": 15838724736,
      "step": 55690,
      "train_runtime": 542481.6922,
      "train_tokens_per_second": 29196.791
    },
    {
      "epoch": 1.9707766575926513,
      "grad_norm": 1.5234375,
      "learning_rate": 1.950700632173371e-05,
      "loss": 1.0506330490112306,
      "num_input_tokens_seen": 15841599232,
      "step": 55700,
      "train_runtime": 542582.2559,
      "train_tokens_per_second": 29196.678
    },
    {
      "epoch": 1.9711304778563798,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9505521917120013e-05,
      "loss": 1.0375028610229493,
      "num_input_tokens_seen": 15844439424,
      "step": 55710,
      "train_runtime": 542680.5209,
      "train_tokens_per_second": 29196.625
    },
    {
      "epoch": 1.9714842981201088,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9504037851326387e-05,
      "loss": 1.0327905654907226,
      "num_input_tokens_seen": 15847310976,
      "step": 55720,
      "train_runtime": 542781.644,
      "train_tokens_per_second": 29196.476
    },
    {
      "epoch": 1.9718381183838374,
      "grad_norm": 1.5703125,
      "learning_rate": 1.950255412422396e-05,
      "loss": 1.0480710983276367,
      "num_input_tokens_seen": 15850160768,
      "step": 55730,
      "train_runtime": 542877.7406,
      "train_tokens_per_second": 29196.557
    },
    {
      "epoch": 1.9721919386475664,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9501070735683924e-05,
      "loss": 1.0358631134033203,
      "num_input_tokens_seen": 15853018368,
      "step": 55740,
      "train_runtime": 542973.9981,
      "train_tokens_per_second": 29196.644
    },
    {
      "epoch": 1.972545758911295,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9499587685577537e-05,
      "loss": 1.0422815322875976,
      "num_input_tokens_seen": 15855846528,
      "step": 55750,
      "train_runtime": 543069.1942,
      "train_tokens_per_second": 29196.733
    },
    {
      "epoch": 1.972899579175024,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9498104973776137e-05,
      "loss": 1.0407340049743652,
      "num_input_tokens_seen": 15858727552,
      "step": 55760,
      "train_runtime": 543169.008,
      "train_tokens_per_second": 29196.672
    },
    {
      "epoch": 1.9732533994387524,
      "grad_norm": 1.59375,
      "learning_rate": 1.949662260015112e-05,
      "loss": 1.0303277969360352,
      "num_input_tokens_seen": 15861522944,
      "step": 55770,
      "train_runtime": 543263.7616,
      "train_tokens_per_second": 29196.726
    },
    {
      "epoch": 1.9736072197024814,
      "grad_norm": 1.578125,
      "learning_rate": 1.9495140564573953e-05,
      "loss": 1.0293807983398438,
      "num_input_tokens_seen": 15864311616,
      "step": 55780,
      "train_runtime": 543357.7736,
      "train_tokens_per_second": 29196.806
    },
    {
      "epoch": 1.9739610399662102,
      "grad_norm": 1.625,
      "learning_rate": 1.9493658866916166e-05,
      "loss": 1.044095230102539,
      "num_input_tokens_seen": 15867128704,
      "step": 55790,
      "train_runtime": 543453.9254,
      "train_tokens_per_second": 29196.824
    },
    {
      "epoch": 1.974314860229939,
      "grad_norm": 1.5078125,
      "learning_rate": 1.9492177507049375e-05,
      "loss": 1.0370759963989258,
      "num_input_tokens_seen": 15869987776,
      "step": 55800,
      "train_runtime": 543549.5924,
      "train_tokens_per_second": 29196.945
    },
    {
      "epoch": 1.9746686804936677,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9490696484845252e-05,
      "loss": 1.0403377532958984,
      "num_input_tokens_seen": 15872832768,
      "step": 55810,
      "train_runtime": 543645.4228,
      "train_tokens_per_second": 29197.032
    },
    {
      "epoch": 1.9750225007573965,
      "grad_norm": 1.578125,
      "learning_rate": 1.948921580017553e-05,
      "loss": 1.0487008094787598,
      "num_input_tokens_seen": 15875630080,
      "step": 55820,
      "train_runtime": 543742.1569,
      "train_tokens_per_second": 29196.982
    },
    {
      "epoch": 1.9753763210211253,
      "grad_norm": 1.5703125,
      "learning_rate": 1.948773545291202e-05,
      "loss": 1.0314671516418457,
      "num_input_tokens_seen": 15878497024,
      "step": 55830,
      "train_runtime": 543840.2257,
      "train_tokens_per_second": 29196.989
    },
    {
      "epoch": 1.975730141284854,
      "grad_norm": 1.6015625,
      "learning_rate": 1.94862554429266e-05,
      "loss": 1.0417680740356445,
      "num_input_tokens_seen": 15881281920,
      "step": 55840,
      "train_runtime": 543934.4551,
      "train_tokens_per_second": 29197.051
    },
    {
      "epoch": 1.9760839615485828,
      "grad_norm": 1.609375,
      "learning_rate": 1.9484775770091214e-05,
      "loss": 1.0384207725524903,
      "num_input_tokens_seen": 15884091584,
      "step": 55850,
      "train_runtime": 544030.114,
      "train_tokens_per_second": 29197.082
    },
    {
      "epoch": 1.9764377818123116,
      "grad_norm": 1.609375,
      "learning_rate": 1.9483296434277877e-05,
      "loss": 1.0393089294433593,
      "num_input_tokens_seen": 15886903616,
      "step": 55860,
      "train_runtime": 544126.3737,
      "train_tokens_per_second": 29197.084
    },
    {
      "epoch": 1.9767916020760405,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9481817435358675e-05,
      "loss": 1.0491540908813477,
      "num_input_tokens_seen": 15889770048,
      "step": 55870,
      "train_runtime": 544224.3946,
      "train_tokens_per_second": 29197.093
    },
    {
      "epoch": 1.977145422339769,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9480338773205753e-05,
      "loss": 1.0505325317382812,
      "num_input_tokens_seen": 15892611776,
      "step": 55880,
      "train_runtime": 544320.5325,
      "train_tokens_per_second": 29197.157
    },
    {
      "epoch": 1.977499242603498,
      "grad_norm": 1.5078125,
      "learning_rate": 1.9478860447691327e-05,
      "loss": 1.0428837776184081,
      "num_input_tokens_seen": 15895480896,
      "step": 55890,
      "train_runtime": 544417.8169,
      "train_tokens_per_second": 29197.209
    },
    {
      "epoch": 1.9778530628672266,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9477382458687682e-05,
      "loss": 1.0344646453857422,
      "num_input_tokens_seen": 15898312192,
      "step": 55900,
      "train_runtime": 544512.0031,
      "train_tokens_per_second": 29197.359
    },
    {
      "epoch": 1.9782068831309556,
      "grad_norm": 1.546875,
      "learning_rate": 1.9475904806067173e-05,
      "loss": 1.0549846649169923,
      "num_input_tokens_seen": 15901135168,
      "step": 55910,
      "train_runtime": 544607.7994,
      "train_tokens_per_second": 29197.406
    },
    {
      "epoch": 1.9785607033946842,
      "grad_norm": 1.5078125,
      "learning_rate": 1.947442748970222e-05,
      "loss": 1.0392529487609863,
      "num_input_tokens_seen": 15904008320,
      "step": 55920,
      "train_runtime": 544708.3466,
      "train_tokens_per_second": 29197.291
    },
    {
      "epoch": 1.9789145236584131,
      "grad_norm": 1.6171875,
      "learning_rate": 1.947295050946531e-05,
      "loss": 1.045662021636963,
      "num_input_tokens_seen": 15906858176,
      "step": 55930,
      "train_runtime": 544806.8257,
      "train_tokens_per_second": 29197.245
    },
    {
      "epoch": 1.979268343922142,
      "grad_norm": 1.578125,
      "learning_rate": 1.9471473865229005e-05,
      "loss": 1.0393863677978517,
      "num_input_tokens_seen": 15909717376,
      "step": 55940,
      "train_runtime": 544904.19,
      "train_tokens_per_second": 29197.275
    },
    {
      "epoch": 1.9796221641858707,
      "grad_norm": 1.6171875,
      "learning_rate": 1.946999755686592e-05,
      "loss": 1.0470576286315918,
      "num_input_tokens_seen": 15912560960,
      "step": 55950,
      "train_runtime": 545000.6249,
      "train_tokens_per_second": 29197.326
    },
    {
      "epoch": 1.9799759844495994,
      "grad_norm": 1.609375,
      "learning_rate": 1.9468521584248754e-05,
      "loss": 1.04337739944458,
      "num_input_tokens_seen": 15915391488,
      "step": 55960,
      "train_runtime": 545096.8298,
      "train_tokens_per_second": 29197.366
    },
    {
      "epoch": 1.9803298047133282,
      "grad_norm": 1.5078125,
      "learning_rate": 1.9467045947250262e-05,
      "loss": 1.0404128074645995,
      "num_input_tokens_seen": 15918301120,
      "step": 55970,
      "train_runtime": 545200.5664,
      "train_tokens_per_second": 29197.147
    },
    {
      "epoch": 1.980683624977057,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9465570645743265e-05,
      "loss": 1.0403247833251954,
      "num_input_tokens_seen": 15921138688,
      "step": 55980,
      "train_runtime": 545296.0549,
      "train_tokens_per_second": 29197.238
    },
    {
      "epoch": 1.9810374452407857,
      "grad_norm": 1.578125,
      "learning_rate": 1.946409567960067e-05,
      "loss": 1.0466753959655761,
      "num_input_tokens_seen": 15923974144,
      "step": 55990,
      "train_runtime": 545391.797,
      "train_tokens_per_second": 29197.311
    },
    {
      "epoch": 1.9813912655045145,
      "grad_norm": 1.5625,
      "learning_rate": 1.9462621048695433e-05,
      "loss": 1.0458283424377441,
      "num_input_tokens_seen": 15926836800,
      "step": 56000,
      "train_runtime": 545490.4467,
      "train_tokens_per_second": 29197.279
    },
    {
      "epoch": 1.9817450857682433,
      "grad_norm": 1.5078125,
      "learning_rate": 1.9461146752900578e-05,
      "loss": 1.0453773498535157,
      "num_input_tokens_seen": 15929623360,
      "step": 56010,
      "train_runtime": 545585.0222,
      "train_tokens_per_second": 29197.325
    },
    {
      "epoch": 1.982098906031972,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9459672792089206e-05,
      "loss": 1.0351547241210937,
      "num_input_tokens_seen": 15932404736,
      "step": 56020,
      "train_runtime": 545678.5278,
      "train_tokens_per_second": 29197.419
    },
    {
      "epoch": 1.9824527262957008,
      "grad_norm": 1.53125,
      "learning_rate": 1.9458199166134474e-05,
      "loss": 1.0419797897338867,
      "num_input_tokens_seen": 15935241664,
      "step": 56030,
      "train_runtime": 545776.2353,
      "train_tokens_per_second": 29197.39
    },
    {
      "epoch": 1.9828065465594298,
      "grad_norm": 1.5625,
      "learning_rate": 1.945672587490962e-05,
      "loss": 1.0385124206542968,
      "num_input_tokens_seen": 15938158144,
      "step": 56040,
      "train_runtime": 545876.9029,
      "train_tokens_per_second": 29197.348
    },
    {
      "epoch": 1.9831603668231583,
      "grad_norm": 1.6484375,
      "learning_rate": 1.945525291828794e-05,
      "loss": 1.0410585403442383,
      "num_input_tokens_seen": 15941030912,
      "step": 56050,
      "train_runtime": 545975.4885,
      "train_tokens_per_second": 29197.338
    },
    {
      "epoch": 1.9835141870868873,
      "grad_norm": 1.625,
      "learning_rate": 1.945378029614279e-05,
      "loss": 1.0410298347473144,
      "num_input_tokens_seen": 15943890688,
      "step": 56060,
      "train_runtime": 546073.4605,
      "train_tokens_per_second": 29197.337
    },
    {
      "epoch": 1.9838680073506159,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9452308008347617e-05,
      "loss": 1.0405838012695312,
      "num_input_tokens_seen": 15946700800,
      "step": 56070,
      "train_runtime": 546166.4823,
      "train_tokens_per_second": 29197.509
    },
    {
      "epoch": 1.9842218276143448,
      "grad_norm": 1.5546875,
      "learning_rate": 1.945083605477591e-05,
      "loss": 1.036156177520752,
      "num_input_tokens_seen": 15949568640,
      "step": 56080,
      "train_runtime": 546265.0942,
      "train_tokens_per_second": 29197.488
    },
    {
      "epoch": 1.9845756478780734,
      "grad_norm": 1.609375,
      "learning_rate": 1.9449364435301235e-05,
      "loss": 1.0450976371765137,
      "num_input_tokens_seen": 15952373440,
      "step": 56090,
      "train_runtime": 546360.5179,
      "train_tokens_per_second": 29197.522
    },
    {
      "epoch": 1.9849294681418024,
      "grad_norm": 1.6171875,
      "learning_rate": 1.944789314979723e-05,
      "loss": 1.0563013076782226,
      "num_input_tokens_seen": 15955251264,
      "step": 56100,
      "train_runtime": 546457.5223,
      "train_tokens_per_second": 29197.606
    },
    {
      "epoch": 1.9852832884055311,
      "grad_norm": 1.578125,
      "learning_rate": 1.944642219813759e-05,
      "loss": 1.041473960876465,
      "num_input_tokens_seen": 15958147520,
      "step": 56110,
      "train_runtime": 546557.2619,
      "train_tokens_per_second": 29197.577
    },
    {
      "epoch": 1.98563710866926,
      "grad_norm": 1.609375,
      "learning_rate": 1.944495158019608e-05,
      "loss": 1.0570634841918944,
      "num_input_tokens_seen": 15960998592,
      "step": 56120,
      "train_runtime": 546655.9929,
      "train_tokens_per_second": 29197.519
    },
    {
      "epoch": 1.9859909289329887,
      "grad_norm": 1.546875,
      "learning_rate": 1.9443481295846537e-05,
      "loss": 1.047287368774414,
      "num_input_tokens_seen": 15963850880,
      "step": 56130,
      "train_runtime": 546753.0485,
      "train_tokens_per_second": 29197.553
    },
    {
      "epoch": 1.9863447491967174,
      "grad_norm": 1.609375,
      "learning_rate": 1.9442011344962863e-05,
      "loss": 1.0553226470947266,
      "num_input_tokens_seen": 15966651520,
      "step": 56140,
      "train_runtime": 546846.0797,
      "train_tokens_per_second": 29197.707
    },
    {
      "epoch": 1.9866985694604462,
      "grad_norm": 1.515625,
      "learning_rate": 1.9440541727419024e-05,
      "loss": 1.0430308341979981,
      "num_input_tokens_seen": 15969476416,
      "step": 56150,
      "train_runtime": 546942.4513,
      "train_tokens_per_second": 29197.727
    },
    {
      "epoch": 1.987052389724175,
      "grad_norm": 1.546875,
      "learning_rate": 1.9439072443089045e-05,
      "loss": 1.0419475555419921,
      "num_input_tokens_seen": 15972270208,
      "step": 56160,
      "train_runtime": 547038.0483,
      "train_tokens_per_second": 29197.732
    },
    {
      "epoch": 1.9874062099879037,
      "grad_norm": 1.515625,
      "learning_rate": 1.9437603491847038e-05,
      "loss": 1.0381108283996583,
      "num_input_tokens_seen": 15975082880,
      "step": 56170,
      "train_runtime": 547131.3434,
      "train_tokens_per_second": 29197.894
    },
    {
      "epoch": 1.9877600302516325,
      "grad_norm": 1.625,
      "learning_rate": 1.943613487356717e-05,
      "loss": 1.0550914764404298,
      "num_input_tokens_seen": 15977881472,
      "step": 56180,
      "train_runtime": 547226.4726,
      "train_tokens_per_second": 29197.932
    },
    {
      "epoch": 1.9881138505153615,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9434666588123665e-05,
      "loss": 1.0478021621704101,
      "num_input_tokens_seen": 15980732160,
      "step": 56190,
      "train_runtime": 547325.1695,
      "train_tokens_per_second": 29197.876
    },
    {
      "epoch": 1.98846767077909,
      "grad_norm": 1.546875,
      "learning_rate": 1.943319863539083e-05,
      "loss": 1.043342399597168,
      "num_input_tokens_seen": 15983606720,
      "step": 56200,
      "train_runtime": 547425.2793,
      "train_tokens_per_second": 29197.787
    },
    {
      "epoch": 1.988821491042819,
      "grad_norm": 1.5625,
      "learning_rate": 1.9431731015243026e-05,
      "loss": 1.0441316604614257,
      "num_input_tokens_seen": 15986437888,
      "step": 56210,
      "train_runtime": 547522.4892,
      "train_tokens_per_second": 29197.774
    },
    {
      "epoch": 1.9891753113065476,
      "grad_norm": 1.4921875,
      "learning_rate": 1.943026372755469e-05,
      "loss": 1.0373734474182128,
      "num_input_tokens_seen": 15989271872,
      "step": 56220,
      "train_runtime": 547616.5274,
      "train_tokens_per_second": 29197.935
    },
    {
      "epoch": 1.9895291315702766,
      "grad_norm": 1.640625,
      "learning_rate": 1.942879677220032e-05,
      "loss": 1.0415738105773926,
      "num_input_tokens_seen": 15992126080,
      "step": 56230,
      "train_runtime": 547714.4012,
      "train_tokens_per_second": 29197.929
    },
    {
      "epoch": 1.989882951834005,
      "grad_norm": 1.5703125,
      "learning_rate": 1.942733014905448e-05,
      "loss": 1.0319334030151368,
      "num_input_tokens_seen": 15994999744,
      "step": 56240,
      "train_runtime": 547813.5996,
      "train_tokens_per_second": 29197.887
    },
    {
      "epoch": 1.990236772097734,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9425863857991804e-05,
      "loss": 1.0422107696533203,
      "num_input_tokens_seen": 15997838912,
      "step": 56250,
      "train_runtime": 547909.9279,
      "train_tokens_per_second": 29197.936
    },
    {
      "epoch": 1.9905905923614626,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9424397898886988e-05,
      "loss": 1.0517634391784667,
      "num_input_tokens_seen": 16000681920,
      "step": 56260,
      "train_runtime": 548008.3448,
      "train_tokens_per_second": 29197.88
    },
    {
      "epoch": 1.9909444126251916,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9422932271614797e-05,
      "loss": 1.0335149765014648,
      "num_input_tokens_seen": 16003485632,
      "step": 56270,
      "train_runtime": 548104.7475,
      "train_tokens_per_second": 29197.86
    },
    {
      "epoch": 1.9912982328889204,
      "grad_norm": 1.5625,
      "learning_rate": 1.942146697605006e-05,
      "loss": 1.0403701782226562,
      "num_input_tokens_seen": 16006271936,
      "step": 56280,
      "train_runtime": 548197.6742,
      "train_tokens_per_second": 29197.993
    },
    {
      "epoch": 1.9916520531526491,
      "grad_norm": 1.5234375,
      "learning_rate": 1.9420002012067674e-05,
      "loss": 1.0422462463378905,
      "num_input_tokens_seen": 16009110784,
      "step": 56290,
      "train_runtime": 548293.7827,
      "train_tokens_per_second": 29198.053
    },
    {
      "epoch": 1.992005873416378,
      "grad_norm": 1.59375,
      "learning_rate": 1.94185373795426e-05,
      "loss": 1.0433788299560547,
      "num_input_tokens_seen": 16011932416,
      "step": 56300,
      "train_runtime": 548389.1728,
      "train_tokens_per_second": 29198.119
    },
    {
      "epoch": 1.9923596936801067,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9417073078349874e-05,
      "loss": 1.033375358581543,
      "num_input_tokens_seen": 16014766144,
      "step": 56310,
      "train_runtime": 548486.6901,
      "train_tokens_per_second": 29198.094
    },
    {
      "epoch": 1.9927135139438354,
      "grad_norm": 1.625,
      "learning_rate": 1.9415609108364576e-05,
      "loss": 1.0364065170288086,
      "num_input_tokens_seen": 16017600256,
      "step": 56320,
      "train_runtime": 548583.3324,
      "train_tokens_per_second": 29198.117
    },
    {
      "epoch": 1.9930673342075642,
      "grad_norm": 1.5625,
      "learning_rate": 1.941414546946188e-05,
      "loss": 1.0341419219970702,
      "num_input_tokens_seen": 16020442688,
      "step": 56330,
      "train_runtime": 548677.9724,
      "train_tokens_per_second": 29198.261
    },
    {
      "epoch": 1.993421154471293,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9412682161517005e-05,
      "loss": 1.0380456924438477,
      "num_input_tokens_seen": 16023284992,
      "step": 56340,
      "train_runtime": 548777.9175,
      "train_tokens_per_second": 29198.123
    },
    {
      "epoch": 1.9937749747350217,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9411219184405246e-05,
      "loss": 1.0330841064453125,
      "num_input_tokens_seen": 16026120832,
      "step": 56350,
      "train_runtime": 548874.6847,
      "train_tokens_per_second": 29198.142
    },
    {
      "epoch": 1.9941287949987507,
      "grad_norm": 1.578125,
      "learning_rate": 1.9409756538001956e-05,
      "loss": 1.0528324127197266,
      "num_input_tokens_seen": 16028994240,
      "step": 56360,
      "train_runtime": 548972.4027,
      "train_tokens_per_second": 29198.179
    },
    {
      "epoch": 1.9944826152624793,
      "grad_norm": 1.609375,
      "learning_rate": 1.940829422218256e-05,
      "loss": 1.0527910232543944,
      "num_input_tokens_seen": 16031783040,
      "step": 56370,
      "train_runtime": 549065.4786,
      "train_tokens_per_second": 29198.308
    },
    {
      "epoch": 1.9948364355262083,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9406832236822554e-05,
      "loss": 1.042885971069336,
      "num_input_tokens_seen": 16034585152,
      "step": 56380,
      "train_runtime": 549161.7927,
      "train_tokens_per_second": 29198.29
    },
    {
      "epoch": 1.9951902557899368,
      "grad_norm": 1.609375,
      "learning_rate": 1.940537058179749e-05,
      "loss": 1.0451224327087403,
      "num_input_tokens_seen": 16037380736,
      "step": 56390,
      "train_runtime": 549257.346,
      "train_tokens_per_second": 29198.3
    },
    {
      "epoch": 1.9955440760536658,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9403909256982976e-05,
      "loss": 1.0402108192443849,
      "num_input_tokens_seen": 16040219648,
      "step": 56400,
      "train_runtime": 549355.3627,
      "train_tokens_per_second": 29198.258
    },
    {
      "epoch": 1.9958978963173943,
      "grad_norm": 1.609375,
      "learning_rate": 1.9402448262254713e-05,
      "loss": 1.0390225410461427,
      "num_input_tokens_seen": 16043105216,
      "step": 56410,
      "train_runtime": 549453.8141,
      "train_tokens_per_second": 29198.278
    },
    {
      "epoch": 1.9962517165811233,
      "grad_norm": 1.5234375,
      "learning_rate": 1.940098759748845e-05,
      "loss": 1.033859634399414,
      "num_input_tokens_seen": 16045917184,
      "step": 56420,
      "train_runtime": 549547.277,
      "train_tokens_per_second": 29198.429
    },
    {
      "epoch": 1.9966055368448519,
      "grad_norm": 1.609375,
      "learning_rate": 1.9399527262559997e-05,
      "loss": 1.0577059745788575,
      "num_input_tokens_seen": 16048747712,
      "step": 56430,
      "train_runtime": 549645.693,
      "train_tokens_per_second": 29198.351
    },
    {
      "epoch": 1.9969593571085809,
      "grad_norm": 1.6484375,
      "learning_rate": 1.939806725734524e-05,
      "loss": 1.0487089157104492,
      "num_input_tokens_seen": 16051591232,
      "step": 56440,
      "train_runtime": 549745.537,
      "train_tokens_per_second": 29198.22
    },
    {
      "epoch": 1.9973131773723096,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9396607581720126e-05,
      "loss": 1.0381735801696776,
      "num_input_tokens_seen": 16054406464,
      "step": 56450,
      "train_runtime": 549843.2844,
      "train_tokens_per_second": 29198.15
    },
    {
      "epoch": 1.9976669976360384,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9395148235560674e-05,
      "loss": 1.043528175354004,
      "num_input_tokens_seen": 16057303168,
      "step": 56460,
      "train_runtime": 549945.068,
      "train_tokens_per_second": 29198.013
    },
    {
      "epoch": 1.9980208178997672,
      "grad_norm": 1.59375,
      "learning_rate": 1.9393689218742955e-05,
      "loss": 1.0393731117248535,
      "num_input_tokens_seen": 16060162496,
      "step": 56470,
      "train_runtime": 550041.6147,
      "train_tokens_per_second": 29198.086
    },
    {
      "epoch": 1.998374638163496,
      "grad_norm": 1.546875,
      "learning_rate": 1.939223053114311e-05,
      "loss": 1.0188589096069336,
      "num_input_tokens_seen": 16062997696,
      "step": 56480,
      "train_runtime": 550138.5908,
      "train_tokens_per_second": 29198.093
    },
    {
      "epoch": 1.9987284584272247,
      "grad_norm": 1.5703125,
      "learning_rate": 1.939077217263736e-05,
      "loss": 1.0475128173828125,
      "num_input_tokens_seen": 16065828288,
      "step": 56490,
      "train_runtime": 550236.3908,
      "train_tokens_per_second": 29198.048
    },
    {
      "epoch": 1.9990822786909535,
      "grad_norm": 1.640625,
      "learning_rate": 1.9389314143101967e-05,
      "loss": 1.0484414100646973,
      "num_input_tokens_seen": 16068675392,
      "step": 56500,
      "train_runtime": 550333.4164,
      "train_tokens_per_second": 29198.073
    },
    {
      "epoch": 1.9994360989546822,
      "grad_norm": 1.578125,
      "learning_rate": 1.938785644241327e-05,
      "loss": 1.0566619873046874,
      "num_input_tokens_seen": 16071454080,
      "step": 56510,
      "train_runtime": 550426.6337,
      "train_tokens_per_second": 29198.177
    },
    {
      "epoch": 1.999789919218411,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9386399070447685e-05,
      "loss": 1.0367640495300292,
      "num_input_tokens_seen": 16074315392,
      "step": 56520,
      "train_runtime": 550525.4524,
      "train_tokens_per_second": 29198.133
    },
    {
      "epoch": 2.0001415281054915,
      "grad_norm": 1.5546875,
      "learning_rate": 1.938494202708167e-05,
      "loss": 1.039323616027832,
      "num_input_tokens_seen": 16077140928,
      "step": 56530,
      "train_runtime": 550630.6014,
      "train_tokens_per_second": 29197.689
    },
    {
      "epoch": 2.0004953483692205,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9383485312191764e-05,
      "loss": 1.030522918701172,
      "num_input_tokens_seen": 16079929728,
      "step": 56540,
      "train_runtime": 550724.896,
      "train_tokens_per_second": 29197.753
    },
    {
      "epoch": 2.000849168632949,
      "grad_norm": 1.546875,
      "learning_rate": 1.9382028925654567e-05,
      "loss": 1.0193578720092773,
      "num_input_tokens_seen": 16082804608,
      "step": 56550,
      "train_runtime": 550822.946,
      "train_tokens_per_second": 29197.775
    },
    {
      "epoch": 2.001202988896678,
      "grad_norm": 1.5234375,
      "learning_rate": 1.9380572867346734e-05,
      "loss": 1.02852783203125,
      "num_input_tokens_seen": 16085644544,
      "step": 56560,
      "train_runtime": 550920.2209,
      "train_tokens_per_second": 29197.775
    },
    {
      "epoch": 2.0015568091604066,
      "grad_norm": 1.578125,
      "learning_rate": 1.9379117137145007e-05,
      "loss": 1.0394320487976074,
      "num_input_tokens_seen": 16088528128,
      "step": 56570,
      "train_runtime": 551017.9164,
      "train_tokens_per_second": 29197.831
    },
    {
      "epoch": 2.0019106294241356,
      "grad_norm": 1.5390625,
      "learning_rate": 1.937766173492617e-05,
      "loss": 1.0304534912109375,
      "num_input_tokens_seen": 16091350208,
      "step": 56580,
      "train_runtime": 551114.9839,
      "train_tokens_per_second": 29197.809
    },
    {
      "epoch": 2.002264449687864,
      "grad_norm": 1.5234375,
      "learning_rate": 1.9376206660567083e-05,
      "loss": 1.0398508071899415,
      "num_input_tokens_seen": 16094200960,
      "step": 56590,
      "train_runtime": 551213.9996,
      "train_tokens_per_second": 29197.736
    },
    {
      "epoch": 2.002618269951593,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9374751913944676e-05,
      "loss": 1.0114702224731444,
      "num_input_tokens_seen": 16097080832,
      "step": 56600,
      "train_runtime": 551316.3104,
      "train_tokens_per_second": 29197.541
    },
    {
      "epoch": 2.0029720902153216,
      "grad_norm": 1.5625,
      "learning_rate": 1.9373297494935928e-05,
      "loss": 1.034390640258789,
      "num_input_tokens_seen": 16099895808,
      "step": 56610,
      "train_runtime": 551411.5785,
      "train_tokens_per_second": 29197.602
    },
    {
      "epoch": 2.0033259104790506,
      "grad_norm": 1.515625,
      "learning_rate": 1.9371843403417894e-05,
      "loss": 1.0322214126586915,
      "num_input_tokens_seen": 16102718208,
      "step": 56620,
      "train_runtime": 551506.9541,
      "train_tokens_per_second": 29197.67
    },
    {
      "epoch": 2.003679730742779,
      "grad_norm": 1.53125,
      "learning_rate": 1.937038963926769e-05,
      "loss": 1.0309642791748046,
      "num_input_tokens_seen": 16105603008,
      "step": 56630,
      "train_runtime": 551606.8051,
      "train_tokens_per_second": 29197.615
    },
    {
      "epoch": 2.004033551006508,
      "grad_norm": 1.5625,
      "learning_rate": 1.93689362023625e-05,
      "loss": 1.049201202392578,
      "num_input_tokens_seen": 16108478784,
      "step": 56640,
      "train_runtime": 551707.6332,
      "train_tokens_per_second": 29197.491
    },
    {
      "epoch": 2.0043873712702367,
      "grad_norm": 1.609375,
      "learning_rate": 1.936748309257957e-05,
      "loss": 1.0523618698120116,
      "num_input_tokens_seen": 16111278848,
      "step": 56650,
      "train_runtime": 551800.2233,
      "train_tokens_per_second": 29197.666
    },
    {
      "epoch": 2.0047411915339657,
      "grad_norm": 1.53125,
      "learning_rate": 1.9366030309796208e-05,
      "loss": 1.0334495544433593,
      "num_input_tokens_seen": 16114109696,
      "step": 56660,
      "train_runtime": 551892.9402,
      "train_tokens_per_second": 29197.891
    },
    {
      "epoch": 2.0050950117976942,
      "grad_norm": 1.5078125,
      "learning_rate": 1.936457785388979e-05,
      "loss": 1.018702507019043,
      "num_input_tokens_seen": 16116990336,
      "step": 56670,
      "train_runtime": 551992.7113,
      "train_tokens_per_second": 29197.832
    },
    {
      "epoch": 2.005448832061423,
      "grad_norm": 1.609375,
      "learning_rate": 1.9363125724737757e-05,
      "loss": 1.0243990898132325,
      "num_input_tokens_seen": 16119840448,
      "step": 56680,
      "train_runtime": 552089.1057,
      "train_tokens_per_second": 29197.896
    },
    {
      "epoch": 2.0058026523251518,
      "grad_norm": 1.546875,
      "learning_rate": 1.9361673922217612e-05,
      "loss": 1.0367053985595702,
      "num_input_tokens_seen": 16122732800,
      "step": 56690,
      "train_runtime": 552187.1841,
      "train_tokens_per_second": 29197.948
    },
    {
      "epoch": 2.0061564725888807,
      "grad_norm": 1.59375,
      "learning_rate": 1.9360222446206923e-05,
      "loss": 1.0436555862426757,
      "num_input_tokens_seen": 16125596480,
      "step": 56700,
      "train_runtime": 552285.5299,
      "train_tokens_per_second": 29197.934
    },
    {
      "epoch": 2.0065102928526097,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9358771296583317e-05,
      "loss": 1.0321487426757812,
      "num_input_tokens_seen": 16128472704,
      "step": 56710,
      "train_runtime": 552384.5975,
      "train_tokens_per_second": 29197.904
    },
    {
      "epoch": 2.0068641131163383,
      "grad_norm": 1.5546875,
      "learning_rate": 1.935732047322449e-05,
      "loss": 1.0434242248535157,
      "num_input_tokens_seen": 16131364864,
      "step": 56720,
      "train_runtime": 552484.1659,
      "train_tokens_per_second": 29197.877
    },
    {
      "epoch": 2.0072179333800673,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9355869976008212e-05,
      "loss": 1.0419513702392578,
      "num_input_tokens_seen": 16134208448,
      "step": 56730,
      "train_runtime": 552582.9572,
      "train_tokens_per_second": 29197.803
    },
    {
      "epoch": 2.007571753643796,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9354419804812303e-05,
      "loss": 1.0251714706420898,
      "num_input_tokens_seen": 16137034688,
      "step": 56740,
      "train_runtime": 552679.6126,
      "train_tokens_per_second": 29197.811
    },
    {
      "epoch": 2.007925573907525,
      "grad_norm": 1.578125,
      "learning_rate": 1.935296995951465e-05,
      "loss": 1.0267827987670899,
      "num_input_tokens_seen": 16139858944,
      "step": 56750,
      "train_runtime": 552774.4816,
      "train_tokens_per_second": 29197.909
    },
    {
      "epoch": 2.0082793941712533,
      "grad_norm": 1.5625,
      "learning_rate": 1.9351520439993207e-05,
      "loss": 1.039373016357422,
      "num_input_tokens_seen": 16142652160,
      "step": 56760,
      "train_runtime": 552870.8323,
      "train_tokens_per_second": 29197.873
    },
    {
      "epoch": 2.0086332144349823,
      "grad_norm": 1.53125,
      "learning_rate": 1.935007124612599e-05,
      "loss": 1.0390923500061036,
      "num_input_tokens_seen": 16145533824,
      "step": 56770,
      "train_runtime": 552969.5437,
      "train_tokens_per_second": 29197.872
    },
    {
      "epoch": 2.008987034698711,
      "grad_norm": 1.59375,
      "learning_rate": 1.9348622377791077e-05,
      "loss": 1.0399500846862793,
      "num_input_tokens_seen": 16148411392,
      "step": 56780,
      "train_runtime": 553066.7294,
      "train_tokens_per_second": 29197.944
    },
    {
      "epoch": 2.00934085496244,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9347173834866616e-05,
      "loss": 1.0342112541198731,
      "num_input_tokens_seen": 16151261248,
      "step": 56790,
      "train_runtime": 553166.2346,
      "train_tokens_per_second": 29197.844
    },
    {
      "epoch": 2.0096946752261684,
      "grad_norm": 1.671875,
      "learning_rate": 1.9345725617230813e-05,
      "loss": 1.0423255920410157,
      "num_input_tokens_seen": 16154109568,
      "step": 56800,
      "train_runtime": 553264.4239,
      "train_tokens_per_second": 29197.81
    },
    {
      "epoch": 2.0100484954898974,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9344277724761943e-05,
      "loss": 1.0389098167419433,
      "num_input_tokens_seen": 16156944128,
      "step": 56810,
      "train_runtime": 553364.1404,
      "train_tokens_per_second": 29197.671
    },
    {
      "epoch": 2.010402315753626,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9342830157338338e-05,
      "loss": 1.0416364669799805,
      "num_input_tokens_seen": 16159769408,
      "step": 56820,
      "train_runtime": 553459.4295,
      "train_tokens_per_second": 29197.749
    },
    {
      "epoch": 2.010756136017355,
      "grad_norm": 1.5703125,
      "learning_rate": 1.93413829148384e-05,
      "loss": 1.0283872604370117,
      "num_input_tokens_seen": 16162587264,
      "step": 56830,
      "train_runtime": 553555.7524,
      "train_tokens_per_second": 29197.759
    },
    {
      "epoch": 2.0111099562810835,
      "grad_norm": 1.546875,
      "learning_rate": 1.9339935997140592e-05,
      "loss": 1.0338361740112305,
      "num_input_tokens_seen": 16165395328,
      "step": 56840,
      "train_runtime": 553650.6382,
      "train_tokens_per_second": 29197.827
    },
    {
      "epoch": 2.0114637765448125,
      "grad_norm": 1.578125,
      "learning_rate": 1.9338489404123445e-05,
      "loss": 1.0248441696166992,
      "num_input_tokens_seen": 16168253568,
      "step": 56850,
      "train_runtime": 553751.2029,
      "train_tokens_per_second": 29197.686
    },
    {
      "epoch": 2.0118175968085414,
      "grad_norm": 1.609375,
      "learning_rate": 1.933704313566554e-05,
      "loss": 1.0317646980285644,
      "num_input_tokens_seen": 16171069824,
      "step": 56860,
      "train_runtime": 553846.7515,
      "train_tokens_per_second": 29197.733
    },
    {
      "epoch": 2.01217141707227,
      "grad_norm": 1.5625,
      "learning_rate": 1.9335597191645538e-05,
      "loss": 1.0321277618408202,
      "num_input_tokens_seen": 16173874944,
      "step": 56870,
      "train_runtime": 553943.4209,
      "train_tokens_per_second": 29197.702
    },
    {
      "epoch": 2.012525237335999,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9334151571942157e-05,
      "loss": 1.0297174453735352,
      "num_input_tokens_seen": 16176671680,
      "step": 56880,
      "train_runtime": 554037.8833,
      "train_tokens_per_second": 29197.772
    },
    {
      "epoch": 2.0128790575997275,
      "grad_norm": 1.5703125,
      "learning_rate": 1.933270627643417e-05,
      "loss": 1.03871431350708,
      "num_input_tokens_seen": 16179527232,
      "step": 56890,
      "train_runtime": 554136.3095,
      "train_tokens_per_second": 29197.739
    },
    {
      "epoch": 2.0132328778634565,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9331261305000432e-05,
      "loss": 1.041410255432129,
      "num_input_tokens_seen": 16182371008,
      "step": 56900,
      "train_runtime": 554233.2251,
      "train_tokens_per_second": 29197.764
    },
    {
      "epoch": 2.013586698127185,
      "grad_norm": 1.53125,
      "learning_rate": 1.9329816657519845e-05,
      "loss": 1.0393573760986328,
      "num_input_tokens_seen": 16185209088,
      "step": 56910,
      "train_runtime": 554328.0916,
      "train_tokens_per_second": 29197.887
    },
    {
      "epoch": 2.013940518390914,
      "grad_norm": 1.546875,
      "learning_rate": 1.9328372333871378e-05,
      "loss": 1.0407936096191406,
      "num_input_tokens_seen": 16187992576,
      "step": 56920,
      "train_runtime": 554423.2398,
      "train_tokens_per_second": 29197.897
    },
    {
      "epoch": 2.0142943386546426,
      "grad_norm": 1.53125,
      "learning_rate": 1.9326928333934072e-05,
      "loss": 1.0164061546325684,
      "num_input_tokens_seen": 16190857664,
      "step": 56930,
      "train_runtime": 554521.8496,
      "train_tokens_per_second": 29197.871
    },
    {
      "epoch": 2.0146481589183716,
      "grad_norm": 1.5625,
      "learning_rate": 1.9325484657587018e-05,
      "loss": 1.035902976989746,
      "num_input_tokens_seen": 16193695104,
      "step": 56940,
      "train_runtime": 554619.6086,
      "train_tokens_per_second": 29197.841
    },
    {
      "epoch": 2.0150019791821,
      "grad_norm": 1.5703125,
      "learning_rate": 1.932404130470938e-05,
      "loss": 1.0491472244262696,
      "num_input_tokens_seen": 16196511360,
      "step": 56950,
      "train_runtime": 554714.288,
      "train_tokens_per_second": 29197.934
    },
    {
      "epoch": 2.015355799445829,
      "grad_norm": 1.59375,
      "learning_rate": 1.9322598275180383e-05,
      "loss": 1.058040237426758,
      "num_input_tokens_seen": 16199365248,
      "step": 56960,
      "train_runtime": 554813.2757,
      "train_tokens_per_second": 29197.869
    },
    {
      "epoch": 2.0157096197095576,
      "grad_norm": 1.53125,
      "learning_rate": 1.9321155568879315e-05,
      "loss": 1.031581497192383,
      "num_input_tokens_seen": 16202188288,
      "step": 56970,
      "train_runtime": 554910.0131,
      "train_tokens_per_second": 29197.866
    },
    {
      "epoch": 2.0160634399732866,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9319713185685522e-05,
      "loss": 1.0329961776733398,
      "num_input_tokens_seen": 16205015936,
      "step": 56980,
      "train_runtime": 555008.627,
      "train_tokens_per_second": 29197.773
    },
    {
      "epoch": 2.016417260237015,
      "grad_norm": 1.53125,
      "learning_rate": 1.9318271125478422e-05,
      "loss": 1.0511350631713867,
      "num_input_tokens_seen": 16207861376,
      "step": 56990,
      "train_runtime": 555103.3151,
      "train_tokens_per_second": 29197.919
    },
    {
      "epoch": 2.016771080500744,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9316829388137487e-05,
      "loss": 1.0269742965698243,
      "num_input_tokens_seen": 16210714240,
      "step": 57000,
      "train_runtime": 555201.9953,
      "train_tokens_per_second": 29197.867
    },
    {
      "epoch": 2.0171249007644727,
      "grad_norm": 1.6171875,
      "learning_rate": 1.931538797354226e-05,
      "loss": 1.0312090873718263,
      "num_input_tokens_seen": 16213538688,
      "step": 57010,
      "train_runtime": 555298.8778,
      "train_tokens_per_second": 29197.86
    },
    {
      "epoch": 2.0174787210282017,
      "grad_norm": 1.546875,
      "learning_rate": 1.931394688157234e-05,
      "loss": 1.0363161087036132,
      "num_input_tokens_seen": 16216409728,
      "step": 57020,
      "train_runtime": 555398.7132,
      "train_tokens_per_second": 29197.781
    },
    {
      "epoch": 2.0178325412919307,
      "grad_norm": 1.609375,
      "learning_rate": 1.9312506112107394e-05,
      "loss": 1.0370423316955566,
      "num_input_tokens_seen": 16219295360,
      "step": 57030,
      "train_runtime": 555498.6534,
      "train_tokens_per_second": 29197.722
    },
    {
      "epoch": 2.0181863615556592,
      "grad_norm": 1.6953125,
      "learning_rate": 1.931106566502715e-05,
      "loss": 1.0489347457885743,
      "num_input_tokens_seen": 16222161216,
      "step": 57040,
      "train_runtime": 555601.7965,
      "train_tokens_per_second": 29197.46
    },
    {
      "epoch": 2.018540181819388,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9309625540211397e-05,
      "loss": 1.027577018737793,
      "num_input_tokens_seen": 16224984512,
      "step": 57050,
      "train_runtime": 555699.4019,
      "train_tokens_per_second": 29197.412
    },
    {
      "epoch": 2.0188940020831168,
      "grad_norm": 1.609375,
      "learning_rate": 1.9308185737539988e-05,
      "loss": 1.0412328720092774,
      "num_input_tokens_seen": 16227826048,
      "step": 57060,
      "train_runtime": 555796.663,
      "train_tokens_per_second": 29197.415
    },
    {
      "epoch": 2.0192478223468457,
      "grad_norm": 1.5390625,
      "learning_rate": 1.930674625689284e-05,
      "loss": 1.0316909790039062,
      "num_input_tokens_seen": 16230663616,
      "step": 57070,
      "train_runtime": 555893.2895,
      "train_tokens_per_second": 29197.445
    },
    {
      "epoch": 2.0196016426105743,
      "grad_norm": 1.671875,
      "learning_rate": 1.9305307098149935e-05,
      "loss": 1.030612087249756,
      "num_input_tokens_seen": 16233473984,
      "step": 57080,
      "train_runtime": 555988.4967,
      "train_tokens_per_second": 29197.5
    },
    {
      "epoch": 2.0199554628743033,
      "grad_norm": 1.59375,
      "learning_rate": 1.930386826119131e-05,
      "loss": 1.0328634262084961,
      "num_input_tokens_seen": 16236298688,
      "step": 57090,
      "train_runtime": 556082.9147,
      "train_tokens_per_second": 29197.622
    },
    {
      "epoch": 2.020309283138032,
      "grad_norm": 1.5546875,
      "learning_rate": 1.930242974589707e-05,
      "loss": 1.0448840141296387,
      "num_input_tokens_seen": 16239094976,
      "step": 57100,
      "train_runtime": 556177.5589,
      "train_tokens_per_second": 29197.681
    },
    {
      "epoch": 2.020663103401761,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9300991552147384e-05,
      "loss": 1.0360559463500976,
      "num_input_tokens_seen": 16241963392,
      "step": 57110,
      "train_runtime": 556277.8862,
      "train_tokens_per_second": 29197.572
    },
    {
      "epoch": 2.0210169236654894,
      "grad_norm": 1.609375,
      "learning_rate": 1.9299553679822472e-05,
      "loss": 1.0412565231323243,
      "num_input_tokens_seen": 16244818176,
      "step": 57120,
      "train_runtime": 556375.2239,
      "train_tokens_per_second": 29197.595
    },
    {
      "epoch": 2.0213707439292183,
      "grad_norm": 1.5390625,
      "learning_rate": 1.929811612880264e-05,
      "loss": 1.0242237091064452,
      "num_input_tokens_seen": 16247708736,
      "step": 57130,
      "train_runtime": 556475.4151,
      "train_tokens_per_second": 29197.532
    },
    {
      "epoch": 2.021724564192947,
      "grad_norm": 1.5625,
      "learning_rate": 1.929667889896823e-05,
      "loss": 1.0251242637634277,
      "num_input_tokens_seen": 16250485120,
      "step": 57140,
      "train_runtime": 556568.6974,
      "train_tokens_per_second": 29197.627
    },
    {
      "epoch": 2.022078384456676,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9295241990199666e-05,
      "loss": 1.0256052017211914,
      "num_input_tokens_seen": 16253317120,
      "step": 57150,
      "train_runtime": 556664.351,
      "train_tokens_per_second": 29197.697
    },
    {
      "epoch": 2.0224322047204044,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9293805402377416e-05,
      "loss": 1.0394763946533203,
      "num_input_tokens_seen": 16256130560,
      "step": 57160,
      "train_runtime": 556757.7506,
      "train_tokens_per_second": 29197.852
    },
    {
      "epoch": 2.0227860249841334,
      "grad_norm": 1.578125,
      "learning_rate": 1.9292369135382035e-05,
      "loss": 1.0331123352050782,
      "num_input_tokens_seen": 16258945856,
      "step": 57170,
      "train_runtime": 556854.5002,
      "train_tokens_per_second": 29197.835
    },
    {
      "epoch": 2.023139845247862,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9290933189094114e-05,
      "loss": 1.0376168251037599,
      "num_input_tokens_seen": 16261732672,
      "step": 57180,
      "train_runtime": 556948.3211,
      "train_tokens_per_second": 29197.92
    },
    {
      "epoch": 2.023493665511591,
      "grad_norm": 1.6015625,
      "learning_rate": 1.928949756339432e-05,
      "loss": 1.0413609504699708,
      "num_input_tokens_seen": 16264601152,
      "step": 57190,
      "train_runtime": 557048.6956,
      "train_tokens_per_second": 29197.809
    },
    {
      "epoch": 2.02384748577532,
      "grad_norm": 1.625,
      "learning_rate": 1.9288062258163386e-05,
      "loss": 1.0321037292480468,
      "num_input_tokens_seen": 16267415296,
      "step": 57200,
      "train_runtime": 557142.8497,
      "train_tokens_per_second": 29197.925
    },
    {
      "epoch": 2.0242013060390485,
      "grad_norm": 1.5859375,
      "learning_rate": 1.92866272732821e-05,
      "loss": 1.0269018173217774,
      "num_input_tokens_seen": 16270270080,
      "step": 57210,
      "train_runtime": 557242.4565,
      "train_tokens_per_second": 29197.829
    },
    {
      "epoch": 2.0245551263027775,
      "grad_norm": 1.5703125,
      "learning_rate": 1.928519260863131e-05,
      "loss": 1.0355012893676758,
      "num_input_tokens_seen": 16273134592,
      "step": 57220,
      "train_runtime": 557340.7299,
      "train_tokens_per_second": 29197.821
    },
    {
      "epoch": 2.024908946566506,
      "grad_norm": 1.609375,
      "learning_rate": 1.9283758264091932e-05,
      "loss": 1.0505844116210938,
      "num_input_tokens_seen": 16275985856,
      "step": 57230,
      "train_runtime": 557437.0142,
      "train_tokens_per_second": 29197.892
    },
    {
      "epoch": 2.025262766830235,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9282324239544938e-05,
      "loss": 1.0407686233520508,
      "num_input_tokens_seen": 16278872896,
      "step": 57240,
      "train_runtime": 557538.8864,
      "train_tokens_per_second": 29197.735
    },
    {
      "epoch": 2.0256165870939635,
      "grad_norm": 1.625,
      "learning_rate": 1.9280890534871375e-05,
      "loss": 1.03466854095459,
      "num_input_tokens_seen": 16281744064,
      "step": 57250,
      "train_runtime": 557637.7775,
      "train_tokens_per_second": 29197.706
    },
    {
      "epoch": 2.0259704073576925,
      "grad_norm": 1.59375,
      "learning_rate": 1.9279457149952333e-05,
      "loss": 1.0320151329040528,
      "num_input_tokens_seen": 16284558848,
      "step": 57260,
      "train_runtime": 557733.7053,
      "train_tokens_per_second": 29197.731
    },
    {
      "epoch": 2.026324227621421,
      "grad_norm": 1.578125,
      "learning_rate": 1.9278024084668976e-05,
      "loss": 1.0376224517822266,
      "num_input_tokens_seen": 16287411648,
      "step": 57270,
      "train_runtime": 557832.0414,
      "train_tokens_per_second": 29197.698
    },
    {
      "epoch": 2.02667804788515,
      "grad_norm": 1.5234375,
      "learning_rate": 1.9276591338902524e-05,
      "loss": 1.0234363555908204,
      "num_input_tokens_seen": 16290273344,
      "step": 57280,
      "train_runtime": 557930.2274,
      "train_tokens_per_second": 29197.689
    },
    {
      "epoch": 2.0270318681488786,
      "grad_norm": 1.578125,
      "learning_rate": 1.9275158912534273e-05,
      "loss": 1.0486383438110352,
      "num_input_tokens_seen": 16293120320,
      "step": 57290,
      "train_runtime": 558027.9399,
      "train_tokens_per_second": 29197.678
    },
    {
      "epoch": 2.0273856884126076,
      "grad_norm": 1.625,
      "learning_rate": 1.9273726805445557e-05,
      "loss": 1.0428855895996094,
      "num_input_tokens_seen": 16295982912,
      "step": 57300,
      "train_runtime": 558125.3116,
      "train_tokens_per_second": 29197.713
    },
    {
      "epoch": 2.027739508676336,
      "grad_norm": 1.5625,
      "learning_rate": 1.927229501751779e-05,
      "loss": 1.0253484725952149,
      "num_input_tokens_seen": 16298892096,
      "step": 57310,
      "train_runtime": 558227.8805,
      "train_tokens_per_second": 29197.56
    },
    {
      "epoch": 2.028093328940065,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9270863548632443e-05,
      "loss": 1.0397038459777832,
      "num_input_tokens_seen": 16301703744,
      "step": 57320,
      "train_runtime": 558320.2741,
      "train_tokens_per_second": 29197.764
    },
    {
      "epoch": 2.0284471492037937,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9269432398671045e-05,
      "loss": 1.0432754516601563,
      "num_input_tokens_seen": 16304540672,
      "step": 57330,
      "train_runtime": 558419.0604,
      "train_tokens_per_second": 29197.679
    },
    {
      "epoch": 2.0288009694675226,
      "grad_norm": 1.5703125,
      "learning_rate": 1.926800156751519e-05,
      "loss": 1.038361167907715,
      "num_input_tokens_seen": 16307324480,
      "step": 57340,
      "train_runtime": 558513.3936,
      "train_tokens_per_second": 29197.732
    },
    {
      "epoch": 2.029154789731251,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9266571055046537e-05,
      "loss": 1.0277355194091797,
      "num_input_tokens_seen": 16310174400,
      "step": 57350,
      "train_runtime": 558611.3636,
      "train_tokens_per_second": 29197.713
    },
    {
      "epoch": 2.02950860999498,
      "grad_norm": 1.71875,
      "learning_rate": 1.9265140861146795e-05,
      "loss": 1.0390813827514649,
      "num_input_tokens_seen": 16313056256,
      "step": 57360,
      "train_runtime": 558712.2934,
      "train_tokens_per_second": 29197.597
    },
    {
      "epoch": 2.029862430258709,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9263710985697744e-05,
      "loss": 1.0354751586914062,
      "num_input_tokens_seen": 16315897216,
      "step": 57370,
      "train_runtime": 558808.464,
      "train_tokens_per_second": 29197.656
    },
    {
      "epoch": 2.0302162505224377,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9262281428581227e-05,
      "loss": 1.0366113662719727,
      "num_input_tokens_seen": 16318746432,
      "step": 57380,
      "train_runtime": 558905.2477,
      "train_tokens_per_second": 29197.698
    },
    {
      "epoch": 2.0305700707861667,
      "grad_norm": 1.578125,
      "learning_rate": 1.926085218967914e-05,
      "loss": 1.0358667373657227,
      "num_input_tokens_seen": 16321615360,
      "step": 57390,
      "train_runtime": 559002.1008,
      "train_tokens_per_second": 29197.771
    },
    {
      "epoch": 2.0309238910498952,
      "grad_norm": 1.546875,
      "learning_rate": 1.925942326887345e-05,
      "loss": 1.0259176254272462,
      "num_input_tokens_seen": 16324460160,
      "step": 57400,
      "train_runtime": 559102.5191,
      "train_tokens_per_second": 29197.615
    },
    {
      "epoch": 2.0312777113136242,
      "grad_norm": 1.59375,
      "learning_rate": 1.925799466604617e-05,
      "loss": 1.0319955825805665,
      "num_input_tokens_seen": 16327308032,
      "step": 57410,
      "train_runtime": 559200.3824,
      "train_tokens_per_second": 29197.598
    },
    {
      "epoch": 2.0316315315773528,
      "grad_norm": 1.609375,
      "learning_rate": 1.9256566381079393e-05,
      "loss": 1.0251970291137695,
      "num_input_tokens_seen": 16330159360,
      "step": 57420,
      "train_runtime": 559298.9444,
      "train_tokens_per_second": 29197.551
    },
    {
      "epoch": 2.0319853518410818,
      "grad_norm": 1.609375,
      "learning_rate": 1.9255138413855265e-05,
      "loss": 1.0355701446533203,
      "num_input_tokens_seen": 16333020608,
      "step": 57430,
      "train_runtime": 559398.6009,
      "train_tokens_per_second": 29197.464
    },
    {
      "epoch": 2.0323391721048103,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9253710764255987e-05,
      "loss": 1.0507987976074218,
      "num_input_tokens_seen": 16335876224,
      "step": 57440,
      "train_runtime": 559494.5774,
      "train_tokens_per_second": 29197.56
    },
    {
      "epoch": 2.0326929923685393,
      "grad_norm": 1.625,
      "learning_rate": 1.925228343216383e-05,
      "loss": 1.041071319580078,
      "num_input_tokens_seen": 16338737920,
      "step": 57450,
      "train_runtime": 559591.3703,
      "train_tokens_per_second": 29197.623
    },
    {
      "epoch": 2.033046812632268,
      "grad_norm": 1.609375,
      "learning_rate": 1.925085641746113e-05,
      "loss": 1.029276466369629,
      "num_input_tokens_seen": 16341589632,
      "step": 57460,
      "train_runtime": 559685.3211,
      "train_tokens_per_second": 29197.817
    },
    {
      "epoch": 2.033400632895997,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9249429720030262e-05,
      "loss": 1.0252897262573242,
      "num_input_tokens_seen": 16344415744,
      "step": 57470,
      "train_runtime": 559779.3407,
      "train_tokens_per_second": 29197.962
    },
    {
      "epoch": 2.0337544531597254,
      "grad_norm": 1.59375,
      "learning_rate": 1.9248003339753688e-05,
      "loss": 1.0281572341918945,
      "num_input_tokens_seen": 16347214720,
      "step": 57480,
      "train_runtime": 559874.0953,
      "train_tokens_per_second": 29198.019
    },
    {
      "epoch": 2.0341082734234543,
      "grad_norm": 1.578125,
      "learning_rate": 1.9246577276513916e-05,
      "loss": 1.0357099533081056,
      "num_input_tokens_seen": 16350015872,
      "step": 57490,
      "train_runtime": 559972.4165,
      "train_tokens_per_second": 29197.895
    },
    {
      "epoch": 2.034462093687183,
      "grad_norm": 1.703125,
      "learning_rate": 1.9245151530193517e-05,
      "loss": 1.030306625366211,
      "num_input_tokens_seen": 16352839488,
      "step": 57500,
      "train_runtime": 560069.9038,
      "train_tokens_per_second": 29197.854
    },
    {
      "epoch": 2.034815913950912,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9243726100675132e-05,
      "loss": 1.0379362106323242,
      "num_input_tokens_seen": 16355633728,
      "step": 57510,
      "train_runtime": 560164.9437,
      "train_tokens_per_second": 29197.889
    },
    {
      "epoch": 2.0351697342146404,
      "grad_norm": 1.671875,
      "learning_rate": 1.924230098784145e-05,
      "loss": 1.0375543594360352,
      "num_input_tokens_seen": 16358462400,
      "step": 57520,
      "train_runtime": 560261.2931,
      "train_tokens_per_second": 29197.916
    },
    {
      "epoch": 2.0355235544783694,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9240876191575226e-05,
      "loss": 1.0434162139892578,
      "num_input_tokens_seen": 16361296448,
      "step": 57530,
      "train_runtime": 560356.6113,
      "train_tokens_per_second": 29198.007
    },
    {
      "epoch": 2.0358773747420984,
      "grad_norm": 1.578125,
      "learning_rate": 1.923945171175928e-05,
      "loss": 1.042367935180664,
      "num_input_tokens_seen": 16364104640,
      "step": 57540,
      "train_runtime": 560453.6306,
      "train_tokens_per_second": 29197.963
    },
    {
      "epoch": 2.036231195005827,
      "grad_norm": 1.6875,
      "learning_rate": 1.9238027548276487e-05,
      "loss": 1.0249635696411132,
      "num_input_tokens_seen": 16366969344,
      "step": 57550,
      "train_runtime": 560550.7113,
      "train_tokens_per_second": 29198.017
    },
    {
      "epoch": 2.036585015269556,
      "grad_norm": 1.6171875,
      "learning_rate": 1.923660370100978e-05,
      "loss": 1.0290655136108398,
      "num_input_tokens_seen": 16369761984,
      "step": 57560,
      "train_runtime": 560644.8206,
      "train_tokens_per_second": 29198.097
    },
    {
      "epoch": 2.0369388355332845,
      "grad_norm": 1.578125,
      "learning_rate": 1.9235180169842168e-05,
      "loss": 1.0353506088256836,
      "num_input_tokens_seen": 16372637952,
      "step": 57570,
      "train_runtime": 560743.8269,
      "train_tokens_per_second": 29198.071
    },
    {
      "epoch": 2.0372926557970135,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9233756954656694e-05,
      "loss": 1.0397926330566407,
      "num_input_tokens_seen": 16375454912,
      "step": 57580,
      "train_runtime": 560840.2624,
      "train_tokens_per_second": 29198.073
    },
    {
      "epoch": 2.037646476060742,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9232334055336495e-05,
      "loss": 1.0434465408325195,
      "num_input_tokens_seen": 16378272576,
      "step": 57590,
      "train_runtime": 560936.6753,
      "train_tokens_per_second": 29198.078
    },
    {
      "epoch": 2.038000296324471,
      "grad_norm": 1.609375,
      "learning_rate": 1.923091147176474e-05,
      "loss": 1.0623882293701172,
      "num_input_tokens_seen": 16381104576,
      "step": 57600,
      "train_runtime": 561034.3121,
      "train_tokens_per_second": 29198.044
    },
    {
      "epoch": 2.0383541165881995,
      "grad_norm": 1.6875,
      "learning_rate": 1.9229489203824668e-05,
      "loss": 1.0376337051391602,
      "num_input_tokens_seen": 16383972736,
      "step": 57610,
      "train_runtime": 561134.5172,
      "train_tokens_per_second": 29197.941
    },
    {
      "epoch": 2.0387079368519285,
      "grad_norm": 1.59375,
      "learning_rate": 1.9228067251399588e-05,
      "loss": 1.0407288551330567,
      "num_input_tokens_seen": 16386880320,
      "step": 57620,
      "train_runtime": 561239.1045,
      "train_tokens_per_second": 29197.681
    },
    {
      "epoch": 2.039061757115657,
      "grad_norm": 1.609375,
      "learning_rate": 1.9226645614372854e-05,
      "loss": 1.0470693588256836,
      "num_input_tokens_seen": 16389696512,
      "step": 57630,
      "train_runtime": 561336.9563,
      "train_tokens_per_second": 29197.608
    },
    {
      "epoch": 2.039415577379386,
      "grad_norm": 1.6015625,
      "learning_rate": 1.922522429262789e-05,
      "loss": 1.0495182991027832,
      "num_input_tokens_seen": 16392534016,
      "step": 57640,
      "train_runtime": 561432.6841,
      "train_tokens_per_second": 29197.684
    },
    {
      "epoch": 2.0397693976431146,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9223803286048182e-05,
      "loss": 1.037602996826172,
      "num_input_tokens_seen": 16395392576,
      "step": 57650,
      "train_runtime": 561532.3332,
      "train_tokens_per_second": 29197.593
    },
    {
      "epoch": 2.0401232179068436,
      "grad_norm": 1.59375,
      "learning_rate": 1.9222382594517262e-05,
      "loss": 1.0308095932006835,
      "num_input_tokens_seen": 16398186176,
      "step": 57660,
      "train_runtime": 561624.0543,
      "train_tokens_per_second": 29197.799
    },
    {
      "epoch": 2.040477038170572,
      "grad_norm": 1.59375,
      "learning_rate": 1.9220962217918742e-05,
      "loss": 1.0377174377441407,
      "num_input_tokens_seen": 16400999424,
      "step": 57670,
      "train_runtime": 561719.6221,
      "train_tokens_per_second": 29197.84
    },
    {
      "epoch": 2.040830858434301,
      "grad_norm": 1.6484375,
      "learning_rate": 1.921954215613628e-05,
      "loss": 1.0292688369750977,
      "num_input_tokens_seen": 16403853632,
      "step": 57680,
      "train_runtime": 561813.395,
      "train_tokens_per_second": 29198.047
    },
    {
      "epoch": 2.0411846786980297,
      "grad_norm": 1.4921875,
      "learning_rate": 1.92181224090536e-05,
      "loss": 1.0292903900146484,
      "num_input_tokens_seen": 16406737536,
      "step": 57690,
      "train_runtime": 561913.0241,
      "train_tokens_per_second": 29198.002
    },
    {
      "epoch": 2.0415384989617587,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9216702976554487e-05,
      "loss": 1.0307950973510742,
      "num_input_tokens_seen": 16409616320,
      "step": 57700,
      "train_runtime": 562012.5703,
      "train_tokens_per_second": 29197.952
    },
    {
      "epoch": 2.0418923192254876,
      "grad_norm": 1.515625,
      "learning_rate": 1.9215283858522782e-05,
      "loss": 1.0250868797302246,
      "num_input_tokens_seen": 16412478848,
      "step": 57710,
      "train_runtime": 562110.8505,
      "train_tokens_per_second": 29197.94
    },
    {
      "epoch": 2.042246139489216,
      "grad_norm": 1.5625,
      "learning_rate": 1.9213865054842385e-05,
      "loss": 1.0454872131347657,
      "num_input_tokens_seen": 16415389632,
      "step": 57720,
      "train_runtime": 562211.0865,
      "train_tokens_per_second": 29197.912
    },
    {
      "epoch": 2.042599959752945,
      "grad_norm": 1.6171875,
      "learning_rate": 1.921244656539726e-05,
      "loss": 1.0276055335998535,
      "num_input_tokens_seen": 16418210240,
      "step": 57730,
      "train_runtime": 562306.2075,
      "train_tokens_per_second": 29197.989
    },
    {
      "epoch": 2.0429537800166737,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9211028390071435e-05,
      "loss": 1.0251496315002442,
      "num_input_tokens_seen": 16421070208,
      "step": 57740,
      "train_runtime": 562405.7733,
      "train_tokens_per_second": 29197.905
    },
    {
      "epoch": 2.0433076002804027,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9209610528748988e-05,
      "loss": 1.0321998596191406,
      "num_input_tokens_seen": 16423968064,
      "step": 57750,
      "train_runtime": 562506.5226,
      "train_tokens_per_second": 29197.827
    },
    {
      "epoch": 2.0436614205441312,
      "grad_norm": 1.546875,
      "learning_rate": 1.9208192981314058e-05,
      "loss": 1.0351585388183593,
      "num_input_tokens_seen": 16426784896,
      "step": 57760,
      "train_runtime": 562604.0032,
      "train_tokens_per_second": 29197.775
    },
    {
      "epoch": 2.0440152408078602,
      "grad_norm": 1.65625,
      "learning_rate": 1.9206775747650858e-05,
      "loss": 1.0321237564086914,
      "num_input_tokens_seen": 16429569536,
      "step": 57770,
      "train_runtime": 562697.5344,
      "train_tokens_per_second": 29197.87
    },
    {
      "epoch": 2.0443690610715888,
      "grad_norm": 1.65625,
      "learning_rate": 1.9205358827643647e-05,
      "loss": 1.0443476676940917,
      "num_input_tokens_seen": 16432386752,
      "step": 57780,
      "train_runtime": 562790.9124,
      "train_tokens_per_second": 29198.031
    },
    {
      "epoch": 2.0447228813353178,
      "grad_norm": 1.578125,
      "learning_rate": 1.9203942221176744e-05,
      "loss": 1.0332571029663087,
      "num_input_tokens_seen": 16435227136,
      "step": 57790,
      "train_runtime": 562887.3073,
      "train_tokens_per_second": 29198.077
    },
    {
      "epoch": 2.0450767015990463,
      "grad_norm": 1.578125,
      "learning_rate": 1.9202525928134525e-05,
      "loss": 1.0320326805114746,
      "num_input_tokens_seen": 16438072832,
      "step": 57800,
      "train_runtime": 562986.6099,
      "train_tokens_per_second": 29197.982
    },
    {
      "epoch": 2.0454305218627753,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9201109948401445e-05,
      "loss": 1.027937889099121,
      "num_input_tokens_seen": 16440924416,
      "step": 57810,
      "train_runtime": 563085.3359,
      "train_tokens_per_second": 29197.927
    },
    {
      "epoch": 2.045784342126504,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9199694281861996e-05,
      "loss": 1.0226592063903808,
      "num_input_tokens_seen": 16443785088,
      "step": 57820,
      "train_runtime": 563182.799,
      "train_tokens_per_second": 29197.953
    },
    {
      "epoch": 2.046138162390233,
      "grad_norm": 1.65625,
      "learning_rate": 1.9198278928400747e-05,
      "loss": 1.0281595230102538,
      "num_input_tokens_seen": 16446580032,
      "step": 57830,
      "train_runtime": 563277.8071,
      "train_tokens_per_second": 29197.99
    },
    {
      "epoch": 2.0464919826539614,
      "grad_norm": 1.5625,
      "learning_rate": 1.9196863887902305e-05,
      "loss": 1.0325189590454102,
      "num_input_tokens_seen": 16449394368,
      "step": 57840,
      "train_runtime": 563373.0008,
      "train_tokens_per_second": 29198.052
    },
    {
      "epoch": 2.0468458029176904,
      "grad_norm": 1.53125,
      "learning_rate": 1.919544916025136e-05,
      "loss": 1.0355110168457031,
      "num_input_tokens_seen": 16452250240,
      "step": 57850,
      "train_runtime": 563469.5077,
      "train_tokens_per_second": 29198.12
    },
    {
      "epoch": 2.0471996231814193,
      "grad_norm": 1.59375,
      "learning_rate": 1.919403474533265e-05,
      "loss": 1.0211763381958008,
      "num_input_tokens_seen": 16455117440,
      "step": 57860,
      "train_runtime": 563569.5881,
      "train_tokens_per_second": 29198.022
    },
    {
      "epoch": 2.047553443445148,
      "grad_norm": 1.609375,
      "learning_rate": 1.919262064303097e-05,
      "loss": 1.0576353073120117,
      "num_input_tokens_seen": 16457974784,
      "step": 57870,
      "train_runtime": 563667.7081,
      "train_tokens_per_second": 29198.009
    },
    {
      "epoch": 2.047907263708877,
      "grad_norm": 1.578125,
      "learning_rate": 1.9191206853231182e-05,
      "loss": 1.0389991760253907,
      "num_input_tokens_seen": 16460806592,
      "step": 57880,
      "train_runtime": 563763.3907,
      "train_tokens_per_second": 29198.076
    },
    {
      "epoch": 2.0482610839726054,
      "grad_norm": 1.53125,
      "learning_rate": 1.9189793375818203e-05,
      "loss": 1.0339197158813476,
      "num_input_tokens_seen": 16463637056,
      "step": 57890,
      "train_runtime": 563864.2336,
      "train_tokens_per_second": 29197.874
    },
    {
      "epoch": 2.0486149042363344,
      "grad_norm": 1.546875,
      "learning_rate": 1.9188380210677005e-05,
      "loss": 1.04565372467041,
      "num_input_tokens_seen": 16466482944,
      "step": 57900,
      "train_runtime": 563959.4225,
      "train_tokens_per_second": 29197.992
    },
    {
      "epoch": 2.048968724500063,
      "grad_norm": 1.53125,
      "learning_rate": 1.9186967357692633e-05,
      "loss": 1.043147659301758,
      "num_input_tokens_seen": 16469398272,
      "step": 57910,
      "train_runtime": 564062.497,
      "train_tokens_per_second": 29197.825
    },
    {
      "epoch": 2.049322544763792,
      "grad_norm": 1.5625,
      "learning_rate": 1.918555481675017e-05,
      "loss": 1.0221847534179687,
      "num_input_tokens_seen": 16472209088,
      "step": 57920,
      "train_runtime": 564159.9423,
      "train_tokens_per_second": 29197.764
    },
    {
      "epoch": 2.0496763650275205,
      "grad_norm": 1.625,
      "learning_rate": 1.9184142587734786e-05,
      "loss": 1.0383444786071778,
      "num_input_tokens_seen": 16475035968,
      "step": 57930,
      "train_runtime": 564258.0903,
      "train_tokens_per_second": 29197.696
    },
    {
      "epoch": 2.0500301852912495,
      "grad_norm": 1.5859375,
      "learning_rate": 1.918273067053168e-05,
      "loss": 1.0323399543762206,
      "num_input_tokens_seen": 16477834560,
      "step": 57940,
      "train_runtime": 564352.4261,
      "train_tokens_per_second": 29197.774
    },
    {
      "epoch": 2.050384005554978,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9181319065026137e-05,
      "loss": 1.0297275543212892,
      "num_input_tokens_seen": 16480694144,
      "step": 57950,
      "train_runtime": 564450.7869,
      "train_tokens_per_second": 29197.752
    },
    {
      "epoch": 2.050737825818707,
      "grad_norm": 1.5625,
      "learning_rate": 1.9179907771103482e-05,
      "loss": 1.049105453491211,
      "num_input_tokens_seen": 16483574144,
      "step": 57960,
      "train_runtime": 564553.6352,
      "train_tokens_per_second": 29197.534
    },
    {
      "epoch": 2.0510916460824355,
      "grad_norm": 1.53125,
      "learning_rate": 1.9178496788649106e-05,
      "loss": 1.026939868927002,
      "num_input_tokens_seen": 16486465920,
      "step": 57970,
      "train_runtime": 564650.3181,
      "train_tokens_per_second": 29197.656
    },
    {
      "epoch": 2.0514454663461645,
      "grad_norm": 1.5625,
      "learning_rate": 1.9177086117548462e-05,
      "loss": 1.0285067558288574,
      "num_input_tokens_seen": 16489395392,
      "step": 57980,
      "train_runtime": 564754.1466,
      "train_tokens_per_second": 29197.476
    },
    {
      "epoch": 2.051799286609893,
      "grad_norm": 1.609375,
      "learning_rate": 1.917567575768706e-05,
      "loss": 1.0358930587768556,
      "num_input_tokens_seen": 16492230464,
      "step": 57990,
      "train_runtime": 564850.5637,
      "train_tokens_per_second": 29197.511
    },
    {
      "epoch": 2.052153106873622,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9174265708950457e-05,
      "loss": 1.0296175956726075,
      "num_input_tokens_seen": 16495102592,
      "step": 58000,
      "train_runtime": 564951.1727,
      "train_tokens_per_second": 29197.395
    },
    {
      "epoch": 2.0525069271373506,
      "grad_norm": 1.5859375,
      "learning_rate": 1.91728559712243e-05,
      "loss": 1.0306512832641601,
      "num_input_tokens_seen": 16497938880,
      "step": 58010,
      "train_runtime": 565049.7448,
      "train_tokens_per_second": 29197.321
    },
    {
      "epoch": 2.0528607474010796,
      "grad_norm": 1.609375,
      "learning_rate": 1.9171446544394252e-05,
      "loss": 1.0348872184753417,
      "num_input_tokens_seen": 16500778368,
      "step": 58020,
      "train_runtime": 565146.3757,
      "train_tokens_per_second": 29197.353
    },
    {
      "epoch": 2.0532145676648086,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9170037428346075e-05,
      "loss": 1.026598072052002,
      "num_input_tokens_seen": 16503592896,
      "step": 58030,
      "train_runtime": 565243.7715,
      "train_tokens_per_second": 29197.302
    },
    {
      "epoch": 2.053568387928537,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9168628622965565e-05,
      "loss": 1.0263011932373047,
      "num_input_tokens_seen": 16506471616,
      "step": 58040,
      "train_runtime": 565343.6128,
      "train_tokens_per_second": 29197.237
    },
    {
      "epoch": 2.053922208192266,
      "grad_norm": 1.609375,
      "learning_rate": 1.916722012813858e-05,
      "loss": 1.040518569946289,
      "num_input_tokens_seen": 16509271680,
      "step": 58050,
      "train_runtime": 565439.2616,
      "train_tokens_per_second": 29197.25
    },
    {
      "epoch": 2.0542760284559947,
      "grad_norm": 1.6328125,
      "learning_rate": 1.916581194375105e-05,
      "loss": 1.0373828887939454,
      "num_input_tokens_seen": 16512101888,
      "step": 58060,
      "train_runtime": 565531.5951,
      "train_tokens_per_second": 29197.488
    },
    {
      "epoch": 2.0546298487197237,
      "grad_norm": 1.5625,
      "learning_rate": 1.916440406968895e-05,
      "loss": 1.0361350059509278,
      "num_input_tokens_seen": 16514964032,
      "step": 58070,
      "train_runtime": 565629.402,
      "train_tokens_per_second": 29197.499
    },
    {
      "epoch": 2.054983668983452,
      "grad_norm": 1.546875,
      "learning_rate": 1.9162996505838317e-05,
      "loss": 1.0231544494628906,
      "num_input_tokens_seen": 16517902080,
      "step": 58080,
      "train_runtime": 565731.6661,
      "train_tokens_per_second": 29197.415
    },
    {
      "epoch": 2.055337489247181,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9161589252085248e-05,
      "loss": 1.029248046875,
      "num_input_tokens_seen": 16520802944,
      "step": 58090,
      "train_runtime": 565833.4604,
      "train_tokens_per_second": 29197.289
    },
    {
      "epoch": 2.0556913095109097,
      "grad_norm": 1.515625,
      "learning_rate": 1.9160182308315897e-05,
      "loss": 1.0270279884338378,
      "num_input_tokens_seen": 16523652480,
      "step": 58100,
      "train_runtime": 565932.863,
      "train_tokens_per_second": 29197.196
    },
    {
      "epoch": 2.0560451297746387,
      "grad_norm": 1.59375,
      "learning_rate": 1.9158775674416478e-05,
      "loss": 1.0436508178710937,
      "num_input_tokens_seen": 16526456192,
      "step": 58110,
      "train_runtime": 566024.6098,
      "train_tokens_per_second": 29197.416
    },
    {
      "epoch": 2.0563989500383673,
      "grad_norm": 1.65625,
      "learning_rate": 1.9157369350273266e-05,
      "loss": 1.043671226501465,
      "num_input_tokens_seen": 16529326656,
      "step": 58120,
      "train_runtime": 566124.6475,
      "train_tokens_per_second": 29197.327
    },
    {
      "epoch": 2.0567527703020962,
      "grad_norm": 1.6171875,
      "learning_rate": 1.9155963335772588e-05,
      "loss": 1.0381614685058593,
      "num_input_tokens_seen": 16532169472,
      "step": 58130,
      "train_runtime": 566220.7078,
      "train_tokens_per_second": 29197.395
    },
    {
      "epoch": 2.057106590565825,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9154557630800835e-05,
      "loss": 1.0427223205566407,
      "num_input_tokens_seen": 16535058240,
      "step": 58140,
      "train_runtime": 566319.8123,
      "train_tokens_per_second": 29197.386
    },
    {
      "epoch": 2.0574604108295538,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9153152235244455e-05,
      "loss": 1.020967674255371,
      "num_input_tokens_seen": 16537861632,
      "step": 58150,
      "train_runtime": 566416.8155,
      "train_tokens_per_second": 29197.335
    },
    {
      "epoch": 2.0578142310932823,
      "grad_norm": 1.5625,
      "learning_rate": 1.9151747148989955e-05,
      "loss": 1.0378662109375,
      "num_input_tokens_seen": 16540702272,
      "step": 58160,
      "train_runtime": 566514.8055,
      "train_tokens_per_second": 29197.299
    },
    {
      "epoch": 2.0581680513570113,
      "grad_norm": 1.671875,
      "learning_rate": 1.915034237192389e-05,
      "loss": 1.0468915939331054,
      "num_input_tokens_seen": 16543565632,
      "step": 58170,
      "train_runtime": 566613.8922,
      "train_tokens_per_second": 29197.247
    },
    {
      "epoch": 2.05852187162074,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9148937903932894e-05,
      "loss": 1.0389482498168945,
      "num_input_tokens_seen": 16546400960,
      "step": 58180,
      "train_runtime": 566710.1844,
      "train_tokens_per_second": 29197.289
    },
    {
      "epoch": 2.058875691884469,
      "grad_norm": 1.625,
      "learning_rate": 1.9147533744903633e-05,
      "loss": 1.0334646224975585,
      "num_input_tokens_seen": 16549215936,
      "step": 58190,
      "train_runtime": 566804.0591,
      "train_tokens_per_second": 29197.42
    },
    {
      "epoch": 2.059229512148198,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9146129894722863e-05,
      "loss": 1.0363191604614257,
      "num_input_tokens_seen": 16552081728,
      "step": 58200,
      "train_runtime": 566901.0766,
      "train_tokens_per_second": 29197.478
    },
    {
      "epoch": 2.0595833324119264,
      "grad_norm": 1.65625,
      "learning_rate": 1.9144726353277365e-05,
      "loss": 1.0166563034057616,
      "num_input_tokens_seen": 16554895168,
      "step": 58210,
      "train_runtime": 566998.4619,
      "train_tokens_per_second": 29197.425
    },
    {
      "epoch": 2.0599371526756554,
      "grad_norm": 1.53125,
      "learning_rate": 1.9143323120453997e-05,
      "loss": 1.0348012924194336,
      "num_input_tokens_seen": 16557778880,
      "step": 58220,
      "train_runtime": 567100.7628,
      "train_tokens_per_second": 29197.243
    },
    {
      "epoch": 2.060290972939384,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9141920196139683e-05,
      "loss": 1.045072364807129,
      "num_input_tokens_seen": 16560576960,
      "step": 58230,
      "train_runtime": 567195.5528,
      "train_tokens_per_second": 29197.297
    },
    {
      "epoch": 2.060644793203113,
      "grad_norm": 1.5859375,
      "learning_rate": 1.914051758022138e-05,
      "loss": 1.0280696868896484,
      "num_input_tokens_seen": 16563413696,
      "step": 58240,
      "train_runtime": 567294.7905,
      "train_tokens_per_second": 29197.19
    },
    {
      "epoch": 2.0609986134668414,
      "grad_norm": 1.5625,
      "learning_rate": 1.9139115272586125e-05,
      "loss": 1.0366331100463868,
      "num_input_tokens_seen": 16566302912,
      "step": 58250,
      "train_runtime": 567392.6032,
      "train_tokens_per_second": 29197.249
    },
    {
      "epoch": 2.0613524337305704,
      "grad_norm": 1.59375,
      "learning_rate": 1.9137713273121004e-05,
      "loss": 1.0313226699829101,
      "num_input_tokens_seen": 16569132608,
      "step": 58260,
      "train_runtime": 567488.8508,
      "train_tokens_per_second": 29197.283
    },
    {
      "epoch": 2.061706253994299,
      "grad_norm": 1.5625,
      "learning_rate": 1.913631158171315e-05,
      "loss": 1.0396224021911622,
      "num_input_tokens_seen": 16571966016,
      "step": 58270,
      "train_runtime": 567585.9006,
      "train_tokens_per_second": 29197.283
    },
    {
      "epoch": 2.062060074258028,
      "grad_norm": 1.609375,
      "learning_rate": 1.9134910198249782e-05,
      "loss": 1.0302993774414062,
      "num_input_tokens_seen": 16574814464,
      "step": 58280,
      "train_runtime": 567685.1079,
      "train_tokens_per_second": 29197.198
    },
    {
      "epoch": 2.0624138945217565,
      "grad_norm": 1.609375,
      "learning_rate": 1.9133509122618147e-05,
      "loss": 1.0295278549194335,
      "num_input_tokens_seen": 16577656832,
      "step": 58290,
      "train_runtime": 567782.8833,
      "train_tokens_per_second": 29197.176
    },
    {
      "epoch": 2.0627677147854855,
      "grad_norm": 1.5625,
      "learning_rate": 1.913210835470557e-05,
      "loss": 1.030609703063965,
      "num_input_tokens_seen": 16580464512,
      "step": 58300,
      "train_runtime": 567879.5413,
      "train_tokens_per_second": 29197.151
    },
    {
      "epoch": 2.063121535049214,
      "grad_norm": 1.59375,
      "learning_rate": 1.9130707894399428e-05,
      "loss": 1.0418007850646973,
      "num_input_tokens_seen": 16583327232,
      "step": 58310,
      "train_runtime": 567978.6074,
      "train_tokens_per_second": 29197.098
    },
    {
      "epoch": 2.063475355312943,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9129307741587146e-05,
      "loss": 1.039077377319336,
      "num_input_tokens_seen": 16586220096,
      "step": 58320,
      "train_runtime": 568079.5673,
      "train_tokens_per_second": 29197.002
    },
    {
      "epoch": 2.0638291755766716,
      "grad_norm": 1.625,
      "learning_rate": 1.9127907896156226e-05,
      "loss": 1.0387752532958985,
      "num_input_tokens_seen": 16589100800,
      "step": 58330,
      "train_runtime": 568179.6997,
      "train_tokens_per_second": 29196.926
    },
    {
      "epoch": 2.0641829958404005,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9126508357994205e-05,
      "loss": 1.0419276237487793,
      "num_input_tokens_seen": 16591993792,
      "step": 58340,
      "train_runtime": 568280.2712,
      "train_tokens_per_second": 29196.85
    },
    {
      "epoch": 2.064536816104129,
      "grad_norm": 1.578125,
      "learning_rate": 1.9125109126988696e-05,
      "loss": 1.0233539581298827,
      "num_input_tokens_seen": 16594866560,
      "step": 58350,
      "train_runtime": 568378.7984,
      "train_tokens_per_second": 29196.843
    },
    {
      "epoch": 2.064890636367858,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9123710203027365e-05,
      "loss": 1.0337127685546874,
      "num_input_tokens_seen": 16597712704,
      "step": 58360,
      "train_runtime": 568477.5158,
      "train_tokens_per_second": 29196.78
    },
    {
      "epoch": 2.065244456631587,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9122311585997927e-05,
      "loss": 1.030392837524414,
      "num_input_tokens_seen": 16600563392,
      "step": 58370,
      "train_runtime": 568574.7859,
      "train_tokens_per_second": 29196.798
    },
    {
      "epoch": 2.0655982768953156,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9120913275788162e-05,
      "loss": 1.0501530647277832,
      "num_input_tokens_seen": 16603433600,
      "step": 58380,
      "train_runtime": 568674.0587,
      "train_tokens_per_second": 29196.749
    },
    {
      "epoch": 2.0659520971590446,
      "grad_norm": 1.578125,
      "learning_rate": 1.9119515272285913e-05,
      "loss": 1.0417156219482422,
      "num_input_tokens_seen": 16606308032,
      "step": 58390,
      "train_runtime": 568775.1947,
      "train_tokens_per_second": 29196.611
    },
    {
      "epoch": 2.066305917422773,
      "grad_norm": 1.59375,
      "learning_rate": 1.9118117575379065e-05,
      "loss": 1.0251537322998048,
      "num_input_tokens_seen": 16609180992,
      "step": 58400,
      "train_runtime": 568874.5186,
      "train_tokens_per_second": 29196.563
    },
    {
      "epoch": 2.066659737686502,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9116720184955574e-05,
      "loss": 1.0392258644104004,
      "num_input_tokens_seen": 16612066880,
      "step": 58410,
      "train_runtime": 568973.5894,
      "train_tokens_per_second": 29196.552
    },
    {
      "epoch": 2.0670135579502307,
      "grad_norm": 1.5625,
      "learning_rate": 1.9115323100903446e-05,
      "loss": 1.0334272384643555,
      "num_input_tokens_seen": 16614880960,
      "step": 58420,
      "train_runtime": 569070.7166,
      "train_tokens_per_second": 29196.514
    },
    {
      "epoch": 2.0673673782139597,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9113926323110748e-05,
      "loss": 1.032242774963379,
      "num_input_tokens_seen": 16617709824,
      "step": 58430,
      "train_runtime": 569165.8198,
      "train_tokens_per_second": 29196.605
    },
    {
      "epoch": 2.067721198477688,
      "grad_norm": 1.59375,
      "learning_rate": 1.9112529851465603e-05,
      "loss": 1.023686122894287,
      "num_input_tokens_seen": 16620580800,
      "step": 58440,
      "train_runtime": 569262.9724,
      "train_tokens_per_second": 29196.666
    },
    {
      "epoch": 2.068075018741417,
      "grad_norm": 1.6015625,
      "learning_rate": 1.911113368585619e-05,
      "loss": 1.0176047325134276,
      "num_input_tokens_seen": 16623380800,
      "step": 58450,
      "train_runtime": 569357.8083,
      "train_tokens_per_second": 29196.721
    },
    {
      "epoch": 2.0684288390051457,
      "grad_norm": 1.546875,
      "learning_rate": 1.910973782617074e-05,
      "loss": 1.0211217880249024,
      "num_input_tokens_seen": 16626224128,
      "step": 58460,
      "train_runtime": 569457.7301,
      "train_tokens_per_second": 29196.59
    },
    {
      "epoch": 2.0687826592688747,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9108342272297558e-05,
      "loss": 1.0257566452026368,
      "num_input_tokens_seen": 16629075392,
      "step": 58470,
      "train_runtime": 569555.6044,
      "train_tokens_per_second": 29196.579
    },
    {
      "epoch": 2.0691364795326033,
      "grad_norm": 1.6171875,
      "learning_rate": 1.910694702412499e-05,
      "loss": 1.0228387832641601,
      "num_input_tokens_seen": 16631960256,
      "step": 58480,
      "train_runtime": 569654.5486,
      "train_tokens_per_second": 29196.572
    },
    {
      "epoch": 2.0694902997963323,
      "grad_norm": 1.6484375,
      "learning_rate": 1.9105552081541444e-05,
      "loss": 1.0398197174072266,
      "num_input_tokens_seen": 16634859328,
      "step": 58490,
      "train_runtime": 569754.8445,
      "train_tokens_per_second": 29196.521
    },
    {
      "epoch": 2.069844120060061,
      "grad_norm": 1.6328125,
      "learning_rate": 1.910415744443539e-05,
      "loss": 1.0222100257873534,
      "num_input_tokens_seen": 16637724160,
      "step": 58500,
      "train_runtime": 569852.2777,
      "train_tokens_per_second": 29196.556
    },
    {
      "epoch": 2.07019794032379,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9102763112695343e-05,
      "loss": 1.0228023529052734,
      "num_input_tokens_seen": 16640587520,
      "step": 58510,
      "train_runtime": 569953.1059,
      "train_tokens_per_second": 29196.415
    },
    {
      "epoch": 2.0705517605875183,
      "grad_norm": 1.5546875,
      "learning_rate": 1.910136908620989e-05,
      "loss": 1.039698600769043,
      "num_input_tokens_seen": 16643402432,
      "step": 58520,
      "train_runtime": 570048.6619,
      "train_tokens_per_second": 29196.459
    },
    {
      "epoch": 2.0709055808512473,
      "grad_norm": 1.5625,
      "learning_rate": 1.9099975364867663e-05,
      "loss": 1.0320343017578124,
      "num_input_tokens_seen": 16646235200,
      "step": 58530,
      "train_runtime": 570147.7393,
      "train_tokens_per_second": 29196.354
    },
    {
      "epoch": 2.0712594011149763,
      "grad_norm": 1.625,
      "learning_rate": 1.9098581948557356e-05,
      "loss": 1.0392239570617676,
      "num_input_tokens_seen": 16649072384,
      "step": 58540,
      "train_runtime": 570244.9086,
      "train_tokens_per_second": 29196.354
    },
    {
      "epoch": 2.071613221378705,
      "grad_norm": 1.625,
      "learning_rate": 1.909718883716772e-05,
      "loss": 1.0333748817443849,
      "num_input_tokens_seen": 16651890624,
      "step": 58550,
      "train_runtime": 570342.9052,
      "train_tokens_per_second": 29196.279
    },
    {
      "epoch": 2.071967041642434,
      "grad_norm": 1.65625,
      "learning_rate": 1.9095796030587556e-05,
      "loss": 1.0344162940979005,
      "num_input_tokens_seen": 16654746560,
      "step": 58560,
      "train_runtime": 570442.2426,
      "train_tokens_per_second": 29196.201
    },
    {
      "epoch": 2.0723208619061624,
      "grad_norm": 1.53125,
      "learning_rate": 1.9094403528705734e-05,
      "loss": 1.0420707702636718,
      "num_input_tokens_seen": 16657629760,
      "step": 58570,
      "train_runtime": 570544.2953,
      "train_tokens_per_second": 29196.032
    },
    {
      "epoch": 2.0726746821698914,
      "grad_norm": 1.65625,
      "learning_rate": 1.9093011331411173e-05,
      "loss": 1.0428474426269532,
      "num_input_tokens_seen": 16660483520,
      "step": 58580,
      "train_runtime": 570641.5384,
      "train_tokens_per_second": 29196.058
    },
    {
      "epoch": 2.07302850243362,
      "grad_norm": 1.546875,
      "learning_rate": 1.9091619438592854e-05,
      "loss": 1.0476306915283202,
      "num_input_tokens_seen": 16663353984,
      "step": 58590,
      "train_runtime": 570739.6821,
      "train_tokens_per_second": 29196.067
    },
    {
      "epoch": 2.073382322697349,
      "grad_norm": 1.5390625,
      "learning_rate": 1.90902278501398e-05,
      "loss": 1.0440097808837892,
      "num_input_tokens_seen": 16666182080,
      "step": 58600,
      "train_runtime": 570833.441,
      "train_tokens_per_second": 29196.226
    },
    {
      "epoch": 2.0737361429610774,
      "grad_norm": 1.65625,
      "learning_rate": 1.908883656594111e-05,
      "loss": 1.0377010345458983,
      "num_input_tokens_seen": 16669053312,
      "step": 58610,
      "train_runtime": 570932.1076,
      "train_tokens_per_second": 29196.209
    },
    {
      "epoch": 2.0740899632248064,
      "grad_norm": 1.59375,
      "learning_rate": 1.9087445585885926e-05,
      "loss": 1.0255504608154298,
      "num_input_tokens_seen": 16671956672,
      "step": 58620,
      "train_runtime": 571034.4507,
      "train_tokens_per_second": 29196.061
    },
    {
      "epoch": 2.074443783488535,
      "grad_norm": 1.59375,
      "learning_rate": 1.9086054909863457e-05,
      "loss": 1.038637924194336,
      "num_input_tokens_seen": 16674774464,
      "step": 58630,
      "train_runtime": 571130.2524,
      "train_tokens_per_second": 29196.097
    },
    {
      "epoch": 2.074797603752264,
      "grad_norm": 1.625,
      "learning_rate": 1.9084664537762958e-05,
      "loss": 1.0371227264404297,
      "num_input_tokens_seen": 16677654784,
      "step": 58640,
      "train_runtime": 571230.3412,
      "train_tokens_per_second": 29196.024
    },
    {
      "epoch": 2.0751514240159925,
      "grad_norm": 1.5703125,
      "learning_rate": 1.9083274469473747e-05,
      "loss": 1.0381196975708007,
      "num_input_tokens_seen": 16680489984,
      "step": 58650,
      "train_runtime": 571328.8064,
      "train_tokens_per_second": 29195.955
    },
    {
      "epoch": 2.0755052442797215,
      "grad_norm": 1.578125,
      "learning_rate": 1.9081884704885193e-05,
      "loss": 1.0182079315185546,
      "num_input_tokens_seen": 16683313088,
      "step": 58660,
      "train_runtime": 571425.517,
      "train_tokens_per_second": 29195.954
    },
    {
      "epoch": 2.07585906454345,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9080495243886733e-05,
      "loss": 1.0345094680786133,
      "num_input_tokens_seen": 16686174720,
      "step": 58670,
      "train_runtime": 571525.4325,
      "train_tokens_per_second": 29195.857
    },
    {
      "epoch": 2.076212884807179,
      "grad_norm": 1.5234375,
      "learning_rate": 1.9079106086367845e-05,
      "loss": 1.0424606323242187,
      "num_input_tokens_seen": 16689068864,
      "step": 58680,
      "train_runtime": 571626.147,
      "train_tokens_per_second": 29195.776
    },
    {
      "epoch": 2.076566705070908,
      "grad_norm": 1.671875,
      "learning_rate": 1.9077717232218072e-05,
      "loss": 1.0309646606445313,
      "num_input_tokens_seen": 16691909440,
      "step": 58690,
      "train_runtime": 571724.3104,
      "train_tokens_per_second": 29195.731
    },
    {
      "epoch": 2.0769205253346366,
      "grad_norm": 1.546875,
      "learning_rate": 1.9076328681327017e-05,
      "loss": 1.040402317047119,
      "num_input_tokens_seen": 16694771648,
      "step": 58700,
      "train_runtime": 571822.3247,
      "train_tokens_per_second": 29195.733
    },
    {
      "epoch": 2.0772743455983655,
      "grad_norm": 1.640625,
      "learning_rate": 1.907494043358433e-05,
      "loss": 1.0152390480041504,
      "num_input_tokens_seen": 16697627008,
      "step": 58710,
      "train_runtime": 571919.9663,
      "train_tokens_per_second": 29195.741
    },
    {
      "epoch": 2.077628165862094,
      "grad_norm": 1.53125,
      "learning_rate": 1.9073552488879724e-05,
      "loss": 1.0357354164123536,
      "num_input_tokens_seen": 16700488768,
      "step": 58720,
      "train_runtime": 572019.5804,
      "train_tokens_per_second": 29195.659
    },
    {
      "epoch": 2.077981986125823,
      "grad_norm": 1.640625,
      "learning_rate": 1.907216484710296e-05,
      "loss": 1.0501632690429688,
      "num_input_tokens_seen": 16703329920,
      "step": 58730,
      "train_runtime": 572114.3139,
      "train_tokens_per_second": 29195.791
    },
    {
      "epoch": 2.0783358063895516,
      "grad_norm": 1.609375,
      "learning_rate": 1.9070777508143868e-05,
      "loss": 1.0495062828063966,
      "num_input_tokens_seen": 16706194816,
      "step": 58740,
      "train_runtime": 572214.6387,
      "train_tokens_per_second": 29195.679
    },
    {
      "epoch": 2.0786896266532806,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9069390471892324e-05,
      "loss": 1.0361085891723634,
      "num_input_tokens_seen": 16708993728,
      "step": 58750,
      "train_runtime": 572308.581,
      "train_tokens_per_second": 29195.777
    },
    {
      "epoch": 2.079043446917009,
      "grad_norm": 1.640625,
      "learning_rate": 1.9068003738238263e-05,
      "loss": 1.045902919769287,
      "num_input_tokens_seen": 16711879168,
      "step": 58760,
      "train_runtime": 572406.8268,
      "train_tokens_per_second": 29195.807
    },
    {
      "epoch": 2.079397267180738,
      "grad_norm": 1.609375,
      "learning_rate": 1.9066617307071674e-05,
      "loss": 1.0319135665893555,
      "num_input_tokens_seen": 16714695232,
      "step": 58770,
      "train_runtime": 572505.9832,
      "train_tokens_per_second": 29195.669
    },
    {
      "epoch": 2.0797510874444667,
      "grad_norm": 1.546875,
      "learning_rate": 1.9065231178282607e-05,
      "loss": 1.0334832191467285,
      "num_input_tokens_seen": 16717574208,
      "step": 58780,
      "train_runtime": 572603.3838,
      "train_tokens_per_second": 29195.731
    },
    {
      "epoch": 2.0801049077081957,
      "grad_norm": 1.7109375,
      "learning_rate": 1.906384535176116e-05,
      "loss": 1.0423397064208983,
      "num_input_tokens_seen": 16720437760,
      "step": 58790,
      "train_runtime": 572703.1353,
      "train_tokens_per_second": 29195.646
    },
    {
      "epoch": 2.080458727971924,
      "grad_norm": 1.59375,
      "learning_rate": 1.90624598273975e-05,
      "loss": 1.0292854309082031,
      "num_input_tokens_seen": 16723306368,
      "step": 58800,
      "train_runtime": 572803.1776,
      "train_tokens_per_second": 29195.554
    },
    {
      "epoch": 2.080812548235653,
      "grad_norm": 1.546875,
      "learning_rate": 1.9061074605081837e-05,
      "loss": 1.0343957901000977,
      "num_input_tokens_seen": 16726129088,
      "step": 58810,
      "train_runtime": 572898.5029,
      "train_tokens_per_second": 29195.624
    },
    {
      "epoch": 2.0811663684993817,
      "grad_norm": 1.5,
      "learning_rate": 1.905968968470444e-05,
      "loss": 1.0237627029418945,
      "num_input_tokens_seen": 16728959232,
      "step": 58820,
      "train_runtime": 572993.7791,
      "train_tokens_per_second": 29195.708
    },
    {
      "epoch": 2.0815201887631107,
      "grad_norm": 1.609375,
      "learning_rate": 1.9058305066155632e-05,
      "loss": 1.0353080749511718,
      "num_input_tokens_seen": 16731800960,
      "step": 58830,
      "train_runtime": 573091.854,
      "train_tokens_per_second": 29195.671
    },
    {
      "epoch": 2.0818740090268393,
      "grad_norm": 1.59375,
      "learning_rate": 1.9056920749325805e-05,
      "loss": 1.0300054550170898,
      "num_input_tokens_seen": 16734670592,
      "step": 58840,
      "train_runtime": 573191.0311,
      "train_tokens_per_second": 29195.625
    },
    {
      "epoch": 2.0822278292905683,
      "grad_norm": 1.578125,
      "learning_rate": 1.905553673410539e-05,
      "loss": 1.0317919731140137,
      "num_input_tokens_seen": 16737600256,
      "step": 58850,
      "train_runtime": 573293.6328,
      "train_tokens_per_second": 29195.51
    },
    {
      "epoch": 2.082581649554297,
      "grad_norm": 1.6015625,
      "learning_rate": 1.905415302038488e-05,
      "loss": 1.0526699066162108,
      "num_input_tokens_seen": 16740470080,
      "step": 58860,
      "train_runtime": 573394.1052,
      "train_tokens_per_second": 29195.4
    },
    {
      "epoch": 2.082935469818026,
      "grad_norm": 1.546875,
      "learning_rate": 1.905276960805483e-05,
      "loss": 1.0458488464355469,
      "num_input_tokens_seen": 16743316864,
      "step": 58870,
      "train_runtime": 573491.6808,
      "train_tokens_per_second": 29195.396
    },
    {
      "epoch": 2.083289290081755,
      "grad_norm": 1.546875,
      "learning_rate": 1.9051386497005842e-05,
      "loss": 1.0391807556152344,
      "num_input_tokens_seen": 16746192640,
      "step": 58880,
      "train_runtime": 573591.0269,
      "train_tokens_per_second": 29195.353
    },
    {
      "epoch": 2.0836431103454833,
      "grad_norm": 1.578125,
      "learning_rate": 1.9050003687128574e-05,
      "loss": 1.0295869827270507,
      "num_input_tokens_seen": 16749062784,
      "step": 58890,
      "train_runtime": 573690.7322,
      "train_tokens_per_second": 29195.282
    },
    {
      "epoch": 2.0839969306092123,
      "grad_norm": 1.53125,
      "learning_rate": 1.9048621178313737e-05,
      "loss": 1.0254077911376953,
      "num_input_tokens_seen": 16751884544,
      "step": 58900,
      "train_runtime": 573789.1677,
      "train_tokens_per_second": 29195.191
    },
    {
      "epoch": 2.084350750872941,
      "grad_norm": 1.59375,
      "learning_rate": 1.9047238970452116e-05,
      "loss": 1.032361125946045,
      "num_input_tokens_seen": 16754719872,
      "step": 58910,
      "train_runtime": 573886.5541,
      "train_tokens_per_second": 29195.178
    },
    {
      "epoch": 2.08470457113667,
      "grad_norm": 1.5859375,
      "learning_rate": 1.904585706343453e-05,
      "loss": 1.0383284568786622,
      "num_input_tokens_seen": 16757534656,
      "step": 58920,
      "train_runtime": 573983.0281,
      "train_tokens_per_second": 29195.174
    },
    {
      "epoch": 2.0850583914003984,
      "grad_norm": 1.46875,
      "learning_rate": 1.904447545715186e-05,
      "loss": 1.0260854721069337,
      "num_input_tokens_seen": 16760392192,
      "step": 58930,
      "train_runtime": 574081.5183,
      "train_tokens_per_second": 29195.143
    },
    {
      "epoch": 2.0854122116641274,
      "grad_norm": 1.625,
      "learning_rate": 1.9043094151495045e-05,
      "loss": 1.0292816162109375,
      "num_input_tokens_seen": 16763251072,
      "step": 58940,
      "train_runtime": 574177.3014,
      "train_tokens_per_second": 29195.252
    },
    {
      "epoch": 2.085766031927856,
      "grad_norm": 1.6796875,
      "learning_rate": 1.904171314635508e-05,
      "loss": 1.0356107711791993,
      "num_input_tokens_seen": 16766037888,
      "step": 58950,
      "train_runtime": 574270.7905,
      "train_tokens_per_second": 29195.352
    },
    {
      "epoch": 2.086119852191585,
      "grad_norm": 1.5859375,
      "learning_rate": 1.904033244162301e-05,
      "loss": 1.0431496620178222,
      "num_input_tokens_seen": 16768900480,
      "step": 58960,
      "train_runtime": 574369.2007,
      "train_tokens_per_second": 29195.334
    },
    {
      "epoch": 2.0864736724553135,
      "grad_norm": 1.546875,
      "learning_rate": 1.903895203718994e-05,
      "loss": 1.0342815399169922,
      "num_input_tokens_seen": 16771760064,
      "step": 58970,
      "train_runtime": 574464.9016,
      "train_tokens_per_second": 29195.448
    },
    {
      "epoch": 2.0868274927190424,
      "grad_norm": 1.5859375,
      "learning_rate": 1.903757193294703e-05,
      "loss": 1.042623805999756,
      "num_input_tokens_seen": 16774568384,
      "step": 58980,
      "train_runtime": 574559.2281,
      "train_tokens_per_second": 29195.543
    },
    {
      "epoch": 2.087181312982771,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9036192128785495e-05,
      "loss": 1.0449088096618653,
      "num_input_tokens_seen": 16777428352,
      "step": 58990,
      "train_runtime": 574660.3652,
      "train_tokens_per_second": 29195.381
    },
    {
      "epoch": 2.0875351332465,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9034812624596605e-05,
      "loss": 1.0398799896240234,
      "num_input_tokens_seen": 16780237632,
      "step": 59000,
      "train_runtime": 574756.5396,
      "train_tokens_per_second": 29195.384
    },
    {
      "epoch": 2.0878889535102285,
      "grad_norm": 1.5703125,
      "learning_rate": 1.903343342027168e-05,
      "loss": 1.0310200691223144,
      "num_input_tokens_seen": 16783086208,
      "step": 59010,
      "train_runtime": 574853.7615,
      "train_tokens_per_second": 29195.401
    },
    {
      "epoch": 2.0882427737739575,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9032054515702103e-05,
      "loss": 1.037808609008789,
      "num_input_tokens_seen": 16785940544,
      "step": 59020,
      "train_runtime": 574951.6936,
      "train_tokens_per_second": 29195.393
    },
    {
      "epoch": 2.0885965940376865,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9030675910779307e-05,
      "loss": 1.0465572357177735,
      "num_input_tokens_seen": 16788787776,
      "step": 59030,
      "train_runtime": 575051.6673,
      "train_tokens_per_second": 29195.268
    },
    {
      "epoch": 2.088950414301415,
      "grad_norm": 1.578125,
      "learning_rate": 1.9029297605394782e-05,
      "loss": 1.0396917343139649,
      "num_input_tokens_seen": 16791682304,
      "step": 59040,
      "train_runtime": 575152.9535,
      "train_tokens_per_second": 29195.16
    },
    {
      "epoch": 2.089304234565144,
      "grad_norm": 1.640625,
      "learning_rate": 1.9027919599440077e-05,
      "loss": 1.039310836791992,
      "num_input_tokens_seen": 16794538944,
      "step": 59050,
      "train_runtime": 575252.5118,
      "train_tokens_per_second": 29195.073
    },
    {
      "epoch": 2.0896580548288726,
      "grad_norm": 1.5234375,
      "learning_rate": 1.9026541892806784e-05,
      "loss": 1.0404403686523438,
      "num_input_tokens_seen": 16797344256,
      "step": 59060,
      "train_runtime": 575346.4316,
      "train_tokens_per_second": 29195.183
    },
    {
      "epoch": 2.0900118750926016,
      "grad_norm": 1.59375,
      "learning_rate": 1.9025164485386562e-05,
      "loss": 1.0368450164794922,
      "num_input_tokens_seen": 16800192256,
      "step": 59070,
      "train_runtime": 575442.6378,
      "train_tokens_per_second": 29195.251
    },
    {
      "epoch": 2.09036569535633,
      "grad_norm": 1.5390625,
      "learning_rate": 1.9023787377071123e-05,
      "loss": 1.0284730911254882,
      "num_input_tokens_seen": 16803091072,
      "step": 59080,
      "train_runtime": 575543.1738,
      "train_tokens_per_second": 29195.188
    },
    {
      "epoch": 2.090719515620059,
      "grad_norm": 1.6328125,
      "learning_rate": 1.902241056775223e-05,
      "loss": 1.0286778450012206,
      "num_input_tokens_seen": 16805860032,
      "step": 59090,
      "train_runtime": 575638.3303,
      "train_tokens_per_second": 29195.172
    },
    {
      "epoch": 2.0910733358837876,
      "grad_norm": 1.515625,
      "learning_rate": 1.9021034057321694e-05,
      "loss": 1.0246595382690429,
      "num_input_tokens_seen": 16808715520,
      "step": 59100,
      "train_runtime": 575735.3968,
      "train_tokens_per_second": 29195.209
    },
    {
      "epoch": 2.0914271561475166,
      "grad_norm": 1.6484375,
      "learning_rate": 1.90196578456714e-05,
      "loss": 1.0300943374633789,
      "num_input_tokens_seen": 16811623104,
      "step": 59110,
      "train_runtime": 575835.7643,
      "train_tokens_per_second": 29195.17
    },
    {
      "epoch": 2.091780976411245,
      "grad_norm": 1.6328125,
      "learning_rate": 1.9018281932693273e-05,
      "loss": 1.0270252227783203,
      "num_input_tokens_seen": 16814509888,
      "step": 59120,
      "train_runtime": 575934.569,
      "train_tokens_per_second": 29195.174
    },
    {
      "epoch": 2.092134796674974,
      "grad_norm": 1.59375,
      "learning_rate": 1.9016906318279295e-05,
      "loss": 1.036483383178711,
      "num_input_tokens_seen": 16817333248,
      "step": 59130,
      "train_runtime": 576030.7045,
      "train_tokens_per_second": 29195.203
    },
    {
      "epoch": 2.0924886169387027,
      "grad_norm": 1.5859375,
      "learning_rate": 1.9015531002321503e-05,
      "loss": 1.0350326538085937,
      "num_input_tokens_seen": 16820180224,
      "step": 59140,
      "train_runtime": 576129.2538,
      "train_tokens_per_second": 29195.15
    },
    {
      "epoch": 2.0928424372024317,
      "grad_norm": 1.6875,
      "learning_rate": 1.9014155984711995e-05,
      "loss": 1.0415462493896483,
      "num_input_tokens_seen": 16823024000,
      "step": 59150,
      "train_runtime": 576227.6183,
      "train_tokens_per_second": 29195.102
    },
    {
      "epoch": 2.0931962574661602,
      "grad_norm": 1.6015625,
      "learning_rate": 1.9012781265342913e-05,
      "loss": 1.0399368286132813,
      "num_input_tokens_seen": 16825902592,
      "step": 59160,
      "train_runtime": 576328.4074,
      "train_tokens_per_second": 29194.991
    },
    {
      "epoch": 2.093550077729889,
      "grad_norm": 1.5234375,
      "learning_rate": 1.9011406844106467e-05,
      "loss": 1.044339942932129,
      "num_input_tokens_seen": 16828736576,
      "step": 59170,
      "train_runtime": 576424.9429,
      "train_tokens_per_second": 29195.018
    },
    {
      "epoch": 2.0939038979936178,
      "grad_norm": 1.5390625,
      "learning_rate": 1.90100327208949e-05,
      "loss": 1.0350798606872558,
      "num_input_tokens_seen": 16831600000,
      "step": 59180,
      "train_runtime": 576523.1295,
      "train_tokens_per_second": 29195.013
    },
    {
      "epoch": 2.0942577182573467,
      "grad_norm": 1.578125,
      "learning_rate": 1.9008658895600537e-05,
      "loss": 1.034314250946045,
      "num_input_tokens_seen": 16834408512,
      "step": 59190,
      "train_runtime": 576616.9104,
      "train_tokens_per_second": 29195.135
    },
    {
      "epoch": 2.0946115385210757,
      "grad_norm": 1.6796875,
      "learning_rate": 1.9007285368115737e-05,
      "loss": 1.0465892791748046,
      "num_input_tokens_seen": 16837252480,
      "step": 59200,
      "train_runtime": 576714.7084,
      "train_tokens_per_second": 29195.115
    },
    {
      "epoch": 2.0949653587848043,
      "grad_norm": 1.5546875,
      "learning_rate": 1.9005912138332918e-05,
      "loss": 1.0424636840820312,
      "num_input_tokens_seen": 16840087232,
      "step": 59210,
      "train_runtime": 576813.504,
      "train_tokens_per_second": 29195.029
    },
    {
      "epoch": 2.0953191790485333,
      "grad_norm": 1.609375,
      "learning_rate": 1.9004539206144557e-05,
      "loss": 1.038732147216797,
      "num_input_tokens_seen": 16842959360,
      "step": 59220,
      "train_runtime": 576914.6727,
      "train_tokens_per_second": 29194.888
    },
    {
      "epoch": 2.095672999312262,
      "grad_norm": 1.5078125,
      "learning_rate": 1.9003166571443183e-05,
      "loss": 1.044095802307129,
      "num_input_tokens_seen": 16845817536,
      "step": 59230,
      "train_runtime": 577015.9457,
      "train_tokens_per_second": 29194.718
    },
    {
      "epoch": 2.096026819575991,
      "grad_norm": 1.59375,
      "learning_rate": 1.900179423412138e-05,
      "loss": 1.0454885482788085,
      "num_input_tokens_seen": 16848680640,
      "step": 59240,
      "train_runtime": 577115.5509,
      "train_tokens_per_second": 29194.64
    },
    {
      "epoch": 2.0963806398397193,
      "grad_norm": 1.5859375,
      "learning_rate": 1.900042219407178e-05,
      "loss": 1.0347824096679688,
      "num_input_tokens_seen": 16851506560,
      "step": 59250,
      "train_runtime": 577210.9167,
      "train_tokens_per_second": 29194.712
    },
    {
      "epoch": 2.0967344601034483,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8999050451187084e-05,
      "loss": 1.0254575729370117,
      "num_input_tokens_seen": 16854356672,
      "step": 59260,
      "train_runtime": 577308.2093,
      "train_tokens_per_second": 29194.729
    },
    {
      "epoch": 2.097088280367177,
      "grad_norm": 1.515625,
      "learning_rate": 1.8997679005360026e-05,
      "loss": 1.0408082008361816,
      "num_input_tokens_seen": 16857248256,
      "step": 59270,
      "train_runtime": 577410.2266,
      "train_tokens_per_second": 29194.579
    },
    {
      "epoch": 2.097442100630906,
      "grad_norm": 1.609375,
      "learning_rate": 1.8996307856483418e-05,
      "loss": 1.0188914299011231,
      "num_input_tokens_seen": 16860063168,
      "step": 59280,
      "train_runtime": 577505.2504,
      "train_tokens_per_second": 29194.649
    },
    {
      "epoch": 2.0977959208946344,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8994937004450106e-05,
      "loss": 1.0434076309204101,
      "num_input_tokens_seen": 16862879744,
      "step": 59290,
      "train_runtime": 577600.5797,
      "train_tokens_per_second": 29194.707
    },
    {
      "epoch": 2.0981497411583634,
      "grad_norm": 1.640625,
      "learning_rate": 1.8993566449153e-05,
      "loss": 1.04630765914917,
      "num_input_tokens_seen": 16865706624,
      "step": 59300,
      "train_runtime": 577695.1115,
      "train_tokens_per_second": 29194.823
    },
    {
      "epoch": 2.098503561422092,
      "grad_norm": 1.640625,
      "learning_rate": 1.8992196190485065e-05,
      "loss": 1.0474128723144531,
      "num_input_tokens_seen": 16868554560,
      "step": 59310,
      "train_runtime": 577793.9304,
      "train_tokens_per_second": 29194.759
    },
    {
      "epoch": 2.098857381685821,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8990826228339316e-05,
      "loss": 1.0336784362792968,
      "num_input_tokens_seen": 16871385536,
      "step": 59320,
      "train_runtime": 577888.6582,
      "train_tokens_per_second": 29194.872
    },
    {
      "epoch": 2.0992112019495495,
      "grad_norm": 1.5546875,
      "learning_rate": 1.898945656260882e-05,
      "loss": 1.0314553260803223,
      "num_input_tokens_seen": 16874222016,
      "step": 59330,
      "train_runtime": 577986.4545,
      "train_tokens_per_second": 29194.84
    },
    {
      "epoch": 2.0995650222132785,
      "grad_norm": 1.546875,
      "learning_rate": 1.89880871931867e-05,
      "loss": 1.0358341217041016,
      "num_input_tokens_seen": 16877072512,
      "step": 59340,
      "train_runtime": 578086.9856,
      "train_tokens_per_second": 29194.694
    },
    {
      "epoch": 2.099918842477007,
      "grad_norm": 1.5625,
      "learning_rate": 1.8986718119966142e-05,
      "loss": 1.0321263313293456,
      "num_input_tokens_seen": 16879917504,
      "step": 59350,
      "train_runtime": 578185.0649,
      "train_tokens_per_second": 29194.662
    },
    {
      "epoch": 2.100272662740736,
      "grad_norm": 1.5234375,
      "learning_rate": 1.898534934284038e-05,
      "loss": 1.0339673042297364,
      "num_input_tokens_seen": 16882767488,
      "step": 59360,
      "train_runtime": 578283.917,
      "train_tokens_per_second": 29194.6
    },
    {
      "epoch": 2.100626483004465,
      "grad_norm": 1.6875,
      "learning_rate": 1.8983980861702692e-05,
      "loss": 1.0358073234558105,
      "num_input_tokens_seen": 16885574272,
      "step": 59370,
      "train_runtime": 578377.2593,
      "train_tokens_per_second": 29194.741
    },
    {
      "epoch": 2.1009803032681935,
      "grad_norm": 1.609375,
      "learning_rate": 1.8982612676446417e-05,
      "loss": 1.0256349563598632,
      "num_input_tokens_seen": 16888400384,
      "step": 59380,
      "train_runtime": 578470.7366,
      "train_tokens_per_second": 29194.909
    },
    {
      "epoch": 2.1013341235319225,
      "grad_norm": 1.5546875,
      "learning_rate": 1.898124478696496e-05,
      "loss": 1.029093360900879,
      "num_input_tokens_seen": 16891245568,
      "step": 59390,
      "train_runtime": 578568.7671,
      "train_tokens_per_second": 29194.88
    },
    {
      "epoch": 2.101687943795651,
      "grad_norm": 1.640625,
      "learning_rate": 1.897987719315175e-05,
      "loss": 1.038186740875244,
      "num_input_tokens_seen": 16894094848,
      "step": 59400,
      "train_runtime": 578667.0468,
      "train_tokens_per_second": 29194.845
    },
    {
      "epoch": 2.10204176405938,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8978509894900306e-05,
      "loss": 1.0382584571838378,
      "num_input_tokens_seen": 16896904000,
      "step": 59410,
      "train_runtime": 578763.1531,
      "train_tokens_per_second": 29194.851
    },
    {
      "epoch": 2.1023955843231086,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8977142892104177e-05,
      "loss": 1.0443181991577148,
      "num_input_tokens_seen": 16899750528,
      "step": 59420,
      "train_runtime": 578859.9888,
      "train_tokens_per_second": 29194.885
    },
    {
      "epoch": 2.1027494045868376,
      "grad_norm": 1.6328125,
      "learning_rate": 1.897577618465697e-05,
      "loss": 1.035562801361084,
      "num_input_tokens_seen": 16902604160,
      "step": 59430,
      "train_runtime": 578959.9191,
      "train_tokens_per_second": 29194.774
    },
    {
      "epoch": 2.103103224850566,
      "grad_norm": 1.625,
      "learning_rate": 1.8974409772452347e-05,
      "loss": 1.0553621292114257,
      "num_input_tokens_seen": 16905459840,
      "step": 59440,
      "train_runtime": 579055.3283,
      "train_tokens_per_second": 29194.896
    },
    {
      "epoch": 2.103457045114295,
      "grad_norm": 1.640625,
      "learning_rate": 1.8973043655384025e-05,
      "loss": 1.0500066757202149,
      "num_input_tokens_seen": 16908293312,
      "step": 59450,
      "train_runtime": 579150.6751,
      "train_tokens_per_second": 29194.982
    },
    {
      "epoch": 2.1038108653780236,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8971677833345776e-05,
      "loss": 1.0355939865112305,
      "num_input_tokens_seen": 16911197632,
      "step": 59460,
      "train_runtime": 579248.7042,
      "train_tokens_per_second": 29195.055
    },
    {
      "epoch": 2.1041646856417526,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8970312306231413e-05,
      "loss": 1.0279977798461915,
      "num_input_tokens_seen": 16914028416,
      "step": 59470,
      "train_runtime": 579345.8018,
      "train_tokens_per_second": 29195.048
    },
    {
      "epoch": 2.104518505905481,
      "grad_norm": 1.609375,
      "learning_rate": 1.896894707393483e-05,
      "loss": 1.0282773971557617,
      "num_input_tokens_seen": 16916836288,
      "step": 59480,
      "train_runtime": 579443.559,
      "train_tokens_per_second": 29194.968
    },
    {
      "epoch": 2.10487232616921,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8967582136349938e-05,
      "loss": 1.028620433807373,
      "num_input_tokens_seen": 16919666560,
      "step": 59490,
      "train_runtime": 579540.791,
      "train_tokens_per_second": 29194.954
    },
    {
      "epoch": 2.1052261464329387,
      "grad_norm": 1.6640625,
      "learning_rate": 1.8966217493370726e-05,
      "loss": 1.0447427749633789,
      "num_input_tokens_seen": 16922553664,
      "step": 59500,
      "train_runtime": 579639.8299,
      "train_tokens_per_second": 29194.946
    },
    {
      "epoch": 2.1055799666966677,
      "grad_norm": 1.578125,
      "learning_rate": 1.896485314489124e-05,
      "loss": 1.0220476150512696,
      "num_input_tokens_seen": 16925391424,
      "step": 59510,
      "train_runtime": 579737.14,
      "train_tokens_per_second": 29194.941
    },
    {
      "epoch": 2.1059337869603967,
      "grad_norm": 1.578125,
      "learning_rate": 1.8963489090805563e-05,
      "loss": 1.0251884460449219,
      "num_input_tokens_seen": 16928190656,
      "step": 59520,
      "train_runtime": 579831.0236,
      "train_tokens_per_second": 29195.041
    },
    {
      "epoch": 2.1062876072241252,
      "grad_norm": 1.5859375,
      "learning_rate": 1.896212533100784e-05,
      "loss": 1.047891616821289,
      "num_input_tokens_seen": 16931077696,
      "step": 59530,
      "train_runtime": 579929.1273,
      "train_tokens_per_second": 29195.081
    },
    {
      "epoch": 2.106641427487854,
      "grad_norm": 1.625,
      "learning_rate": 1.8960761865392257e-05,
      "loss": 1.0365489959716796,
      "num_input_tokens_seen": 16933905408,
      "step": 59540,
      "train_runtime": 580025.0696,
      "train_tokens_per_second": 29195.127
    },
    {
      "epoch": 2.1069952477515828,
      "grad_norm": 1.546875,
      "learning_rate": 1.895939869385308e-05,
      "loss": 1.0453784942626954,
      "num_input_tokens_seen": 16936739008,
      "step": 59550,
      "train_runtime": 580123.1494,
      "train_tokens_per_second": 29195.075
    },
    {
      "epoch": 2.1073490680153117,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8958035816284607e-05,
      "loss": 1.039588737487793,
      "num_input_tokens_seen": 16939603072,
      "step": 59560,
      "train_runtime": 580219.9101,
      "train_tokens_per_second": 29195.143
    },
    {
      "epoch": 2.1077028882790403,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8956673232581184e-05,
      "loss": 1.0341199874877929,
      "num_input_tokens_seen": 16942526144,
      "step": 59570,
      "train_runtime": 580322.1203,
      "train_tokens_per_second": 29195.038
    },
    {
      "epoch": 2.1080567085427693,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8955310942637233e-05,
      "loss": 1.0413262367248535,
      "num_input_tokens_seen": 16945340224,
      "step": 59580,
      "train_runtime": 580417.2322,
      "train_tokens_per_second": 29195.102
    },
    {
      "epoch": 2.108410528806498,
      "grad_norm": 1.59375,
      "learning_rate": 1.8953948946347214e-05,
      "loss": 1.0448229789733887,
      "num_input_tokens_seen": 16948140032,
      "step": 59590,
      "train_runtime": 580511.4575,
      "train_tokens_per_second": 29195.186
    },
    {
      "epoch": 2.108764349070227,
      "grad_norm": 1.546875,
      "learning_rate": 1.895258724360564e-05,
      "loss": 1.0257333755493163,
      "num_input_tokens_seen": 16950946176,
      "step": 59600,
      "train_runtime": 580605.4592,
      "train_tokens_per_second": 29195.292
    },
    {
      "epoch": 2.1091181693339554,
      "grad_norm": 1.5625,
      "learning_rate": 1.8951225834307078e-05,
      "loss": 1.024862575531006,
      "num_input_tokens_seen": 16953736832,
      "step": 59610,
      "train_runtime": 580698.4687,
      "train_tokens_per_second": 29195.422
    },
    {
      "epoch": 2.1094719895976843,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8949864718346153e-05,
      "loss": 1.028562068939209,
      "num_input_tokens_seen": 16956575488,
      "step": 59620,
      "train_runtime": 580792.5507,
      "train_tokens_per_second": 29195.58
    },
    {
      "epoch": 2.109825809861413,
      "grad_norm": 1.515625,
      "learning_rate": 1.894850389561754e-05,
      "loss": 1.0362640380859376,
      "num_input_tokens_seen": 16959433536,
      "step": 59630,
      "train_runtime": 580889.4839,
      "train_tokens_per_second": 29195.628
    },
    {
      "epoch": 2.110179630125142,
      "grad_norm": 1.609375,
      "learning_rate": 1.8947143366015962e-05,
      "loss": 1.0382478713989258,
      "num_input_tokens_seen": 16962239424,
      "step": 59640,
      "train_runtime": 580986.0247,
      "train_tokens_per_second": 29195.607
    },
    {
      "epoch": 2.1105334503888704,
      "grad_norm": 1.6328125,
      "learning_rate": 1.89457831294362e-05,
      "loss": 1.0340330123901367,
      "num_input_tokens_seen": 16965117632,
      "step": 59650,
      "train_runtime": 581086.3062,
      "train_tokens_per_second": 29195.521
    },
    {
      "epoch": 2.1108872706525994,
      "grad_norm": 1.6796875,
      "learning_rate": 1.8944423185773093e-05,
      "loss": 1.0391199111938476,
      "num_input_tokens_seen": 16967958464,
      "step": 59660,
      "train_runtime": 581182.2244,
      "train_tokens_per_second": 29195.591
    },
    {
      "epoch": 2.111241090916328,
      "grad_norm": 1.640625,
      "learning_rate": 1.894306353492153e-05,
      "loss": 1.0306358337402344,
      "num_input_tokens_seen": 16970785600,
      "step": 59670,
      "train_runtime": 581280.4201,
      "train_tokens_per_second": 29195.523
    },
    {
      "epoch": 2.111594911180057,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8941704176776433e-05,
      "loss": 1.0408948898315429,
      "num_input_tokens_seen": 16973653568,
      "step": 59680,
      "train_runtime": 581380.1447,
      "train_tokens_per_second": 29195.448
    },
    {
      "epoch": 2.1119487314437855,
      "grad_norm": 1.578125,
      "learning_rate": 1.8940345111232806e-05,
      "loss": 1.027516746520996,
      "num_input_tokens_seen": 16976514752,
      "step": 59690,
      "train_runtime": 581477.1185,
      "train_tokens_per_second": 29195.499
    },
    {
      "epoch": 2.1123025517075145,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8938986338185695e-05,
      "loss": 1.032382869720459,
      "num_input_tokens_seen": 16979358528,
      "step": 59700,
      "train_runtime": 581576.2154,
      "train_tokens_per_second": 29195.414
    },
    {
      "epoch": 2.1126563719712435,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8937627857530196e-05,
      "loss": 1.0356276512145997,
      "num_input_tokens_seen": 16982169344,
      "step": 59710,
      "train_runtime": 581673.0412,
      "train_tokens_per_second": 29195.387
    },
    {
      "epoch": 2.113010192234972,
      "grad_norm": 1.53125,
      "learning_rate": 1.8936269669161455e-05,
      "loss": 1.0315041542053223,
      "num_input_tokens_seen": 16985047168,
      "step": 59720,
      "train_runtime": 581772.1088,
      "train_tokens_per_second": 29195.362
    },
    {
      "epoch": 2.113364012498701,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8934911772974672e-05,
      "loss": 1.0270893096923828,
      "num_input_tokens_seen": 16987827264,
      "step": 59730,
      "train_runtime": 581865.1144,
      "train_tokens_per_second": 29195.473
    },
    {
      "epoch": 2.1137178327624295,
      "grad_norm": 1.6484375,
      "learning_rate": 1.893355416886511e-05,
      "loss": 1.0246037483215331,
      "num_input_tokens_seen": 16990676416,
      "step": 59740,
      "train_runtime": 581963.3627,
      "train_tokens_per_second": 29195.44
    },
    {
      "epoch": 2.1140716530261585,
      "grad_norm": 1.609375,
      "learning_rate": 1.893219685672807e-05,
      "loss": 1.032501220703125,
      "num_input_tokens_seen": 16993544704,
      "step": 59750,
      "train_runtime": 582059.3393,
      "train_tokens_per_second": 29195.554
    },
    {
      "epoch": 2.114425473289887,
      "grad_norm": 1.59375,
      "learning_rate": 1.893083983645892e-05,
      "loss": 1.0422328948974608,
      "num_input_tokens_seen": 16996417024,
      "step": 59760,
      "train_runtime": 582155.2642,
      "train_tokens_per_second": 29195.677
    },
    {
      "epoch": 2.114779293553616,
      "grad_norm": 1.609375,
      "learning_rate": 1.8929483107953064e-05,
      "loss": 1.0315608978271484,
      "num_input_tokens_seen": 16999229504,
      "step": 59770,
      "train_runtime": 582251.1196,
      "train_tokens_per_second": 29195.701
    },
    {
      "epoch": 2.1151331138173446,
      "grad_norm": 1.6875,
      "learning_rate": 1.892812667110597e-05,
      "loss": 1.0280136108398437,
      "num_input_tokens_seen": 17002028224,
      "step": 59780,
      "train_runtime": 582347.6279,
      "train_tokens_per_second": 29195.668
    },
    {
      "epoch": 2.1154869340810736,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8926770525813152e-05,
      "loss": 1.024853801727295,
      "num_input_tokens_seen": 17004890368,
      "step": 59790,
      "train_runtime": 582448.7428,
      "train_tokens_per_second": 29195.514
    },
    {
      "epoch": 2.115840754344802,
      "grad_norm": 1.546875,
      "learning_rate": 1.892541467197019e-05,
      "loss": 1.0388214111328125,
      "num_input_tokens_seen": 17007705856,
      "step": 59800,
      "train_runtime": 582545.1479,
      "train_tokens_per_second": 29195.515
    },
    {
      "epoch": 2.116194574608531,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8924059109472695e-05,
      "loss": 1.0264229774475098,
      "num_input_tokens_seen": 17010587200,
      "step": 59810,
      "train_runtime": 582648.6507,
      "train_tokens_per_second": 29195.274
    },
    {
      "epoch": 2.1165483948722597,
      "grad_norm": 1.5859375,
      "learning_rate": 1.892270383821635e-05,
      "loss": 1.0387274742126464,
      "num_input_tokens_seen": 17013437824,
      "step": 59820,
      "train_runtime": 582745.7073,
      "train_tokens_per_second": 29195.304
    },
    {
      "epoch": 2.1169022151359886,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8921348858096877e-05,
      "loss": 1.0293859481811523,
      "num_input_tokens_seen": 17016261568,
      "step": 59830,
      "train_runtime": 582842.5682,
      "train_tokens_per_second": 29195.296
    },
    {
      "epoch": 2.117256035399717,
      "grad_norm": 1.625,
      "learning_rate": 1.8919994169010055e-05,
      "loss": 1.0324931144714355,
      "num_input_tokens_seen": 17019096064,
      "step": 59840,
      "train_runtime": 582938.1752,
      "train_tokens_per_second": 29195.371
    },
    {
      "epoch": 2.117609855663446,
      "grad_norm": 1.6484375,
      "learning_rate": 1.891863977085172e-05,
      "loss": 1.0334905624389648,
      "num_input_tokens_seen": 17021946176,
      "step": 59850,
      "train_runtime": 583032.7487,
      "train_tokens_per_second": 29195.523
    },
    {
      "epoch": 2.117963675927175,
      "grad_norm": 1.5078125,
      "learning_rate": 1.8917285663517752e-05,
      "loss": 1.024088478088379,
      "num_input_tokens_seen": 17024808960,
      "step": 59860,
      "train_runtime": 583129.6919,
      "train_tokens_per_second": 29195.579
    },
    {
      "epoch": 2.1183174961909037,
      "grad_norm": 1.625,
      "learning_rate": 1.8915931846904088e-05,
      "loss": 1.0294410705566406,
      "num_input_tokens_seen": 17027647168,
      "step": 59870,
      "train_runtime": 583223.8663,
      "train_tokens_per_second": 29195.731
    },
    {
      "epoch": 2.1186713164546327,
      "grad_norm": 1.625,
      "learning_rate": 1.8914578320906713e-05,
      "loss": 1.0182849884033203,
      "num_input_tokens_seen": 17030481664,
      "step": 59880,
      "train_runtime": 583321.0908,
      "train_tokens_per_second": 29195.724
    },
    {
      "epoch": 2.1190251367183612,
      "grad_norm": 1.640625,
      "learning_rate": 1.8913225085421666e-05,
      "loss": 1.0368324279785157,
      "num_input_tokens_seen": 17033372480,
      "step": 59890,
      "train_runtime": 583423.8645,
      "train_tokens_per_second": 29195.536
    },
    {
      "epoch": 2.1193789569820902,
      "grad_norm": 1.609375,
      "learning_rate": 1.8911872140345043e-05,
      "loss": 1.02109375,
      "num_input_tokens_seen": 17036237568,
      "step": 59900,
      "train_runtime": 583523.0967,
      "train_tokens_per_second": 29195.481
    },
    {
      "epoch": 2.1197327772458188,
      "grad_norm": 1.578125,
      "learning_rate": 1.891051948557299e-05,
      "loss": 1.0203328132629395,
      "num_input_tokens_seen": 17039136448,
      "step": 59910,
      "train_runtime": 583625.2006,
      "train_tokens_per_second": 29195.34
    },
    {
      "epoch": 2.1200865975095478,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8909167121001694e-05,
      "loss": 1.037367343902588,
      "num_input_tokens_seen": 17042093504,
      "step": 59920,
      "train_runtime": 583732.9881,
      "train_tokens_per_second": 29195.015
    },
    {
      "epoch": 2.1204404177732763,
      "grad_norm": 1.53125,
      "learning_rate": 1.8907815046527415e-05,
      "loss": 1.0321079254150392,
      "num_input_tokens_seen": 17044966144,
      "step": 59930,
      "train_runtime": 583830.0612,
      "train_tokens_per_second": 29195.081
    },
    {
      "epoch": 2.1207942380370053,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8906463262046445e-05,
      "loss": 1.0249567031860352,
      "num_input_tokens_seen": 17047717120,
      "step": 59940,
      "train_runtime": 583921.5587,
      "train_tokens_per_second": 29195.218
    },
    {
      "epoch": 2.121148058300734,
      "grad_norm": 1.609375,
      "learning_rate": 1.8905111767455133e-05,
      "loss": 1.035243606567383,
      "num_input_tokens_seen": 17050561792,
      "step": 59950,
      "train_runtime": 584019.2148,
      "train_tokens_per_second": 29195.207
    },
    {
      "epoch": 2.121501878564463,
      "grad_norm": 1.671875,
      "learning_rate": 1.890376056264989e-05,
      "loss": 1.032937240600586,
      "num_input_tokens_seen": 17053431360,
      "step": 59960,
      "train_runtime": 584116.7294,
      "train_tokens_per_second": 29195.246
    },
    {
      "epoch": 2.1218556988281914,
      "grad_norm": 1.65625,
      "learning_rate": 1.890240964752717e-05,
      "loss": 1.0399270057678223,
      "num_input_tokens_seen": 17056203904,
      "step": 59970,
      "train_runtime": 584209.6004,
      "train_tokens_per_second": 29195.35
    },
    {
      "epoch": 2.1222095190919203,
      "grad_norm": 1.59375,
      "learning_rate": 1.890105902198348e-05,
      "loss": 1.032931137084961,
      "num_input_tokens_seen": 17059085696,
      "step": 59980,
      "train_runtime": 584307.5793,
      "train_tokens_per_second": 29195.387
    },
    {
      "epoch": 2.122563339355649,
      "grad_norm": 1.6015625,
      "learning_rate": 1.889970868591537e-05,
      "loss": 1.0395191192626954,
      "num_input_tokens_seen": 17061870464,
      "step": 59990,
      "train_runtime": 584402.029,
      "train_tokens_per_second": 29195.433
    },
    {
      "epoch": 2.122917159619378,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8898358639219462e-05,
      "loss": 1.0294286727905273,
      "num_input_tokens_seen": 17064681856,
      "step": 60000,
      "train_runtime": 584496.9519,
      "train_tokens_per_second": 29195.502
    },
    {
      "epoch": 2.122917159619378,
      "eval_loss": 1.0220143795013428,
      "eval_runtime": 8.4515,
      "eval_samples_per_second": 471.871,
      "eval_steps_per_second": 3.786,
      "num_input_tokens_seen": 17064681856,
      "step": 60000
    },
    {
      "epoch": 2.1232709798831064,
      "grad_norm": 1.625,
      "learning_rate": 1.8897008881792415e-05,
      "loss": 1.0294008255004883,
      "num_input_tokens_seen": 17067488128,
      "step": 60010,
      "train_runtime": 584623.352,
      "train_tokens_per_second": 29193.99
    },
    {
      "epoch": 2.1236248001468354,
      "grad_norm": 1.5234375,
      "learning_rate": 1.889565941353094e-05,
      "loss": 1.03782377243042,
      "num_input_tokens_seen": 17070313344,
      "step": 60020,
      "train_runtime": 584719.4914,
      "train_tokens_per_second": 29194.021
    },
    {
      "epoch": 2.1239786204105644,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8894310234331808e-05,
      "loss": 1.034225845336914,
      "num_input_tokens_seen": 17073132480,
      "step": 60030,
      "train_runtime": 584815.5585,
      "train_tokens_per_second": 29194.046
    },
    {
      "epoch": 2.124332440674293,
      "grad_norm": 1.609375,
      "learning_rate": 1.889296134409183e-05,
      "loss": 1.0413177490234375,
      "num_input_tokens_seen": 17075946112,
      "step": 60040,
      "train_runtime": 584911.8036,
      "train_tokens_per_second": 29194.053
    },
    {
      "epoch": 2.124686260938022,
      "grad_norm": 1.546875,
      "learning_rate": 1.8891612742707884e-05,
      "loss": 1.0224228858947755,
      "num_input_tokens_seen": 17078730368,
      "step": 60050,
      "train_runtime": 585006.9283,
      "train_tokens_per_second": 29194.065
    },
    {
      "epoch": 2.1250400812017505,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8890264430076882e-05,
      "loss": 1.0457534790039062,
      "num_input_tokens_seen": 17081572864,
      "step": 60060,
      "train_runtime": 585103.6931,
      "train_tokens_per_second": 29194.095
    },
    {
      "epoch": 2.1253939014654795,
      "grad_norm": 1.609375,
      "learning_rate": 1.8888916406095796e-05,
      "loss": 1.0485193252563476,
      "num_input_tokens_seen": 17084360576,
      "step": 60070,
      "train_runtime": 585196.32,
      "train_tokens_per_second": 29194.238
    },
    {
      "epoch": 2.125747721729208,
      "grad_norm": 1.5625,
      "learning_rate": 1.8887568670661654e-05,
      "loss": 1.0248265266418457,
      "num_input_tokens_seen": 17087122496,
      "step": 60080,
      "train_runtime": 585286.8037,
      "train_tokens_per_second": 29194.443
    },
    {
      "epoch": 2.126101541992937,
      "grad_norm": 1.6015625,
      "learning_rate": 1.888622122367153e-05,
      "loss": 1.0254801750183105,
      "num_input_tokens_seen": 17089951680,
      "step": 60090,
      "train_runtime": 585385.0402,
      "train_tokens_per_second": 29194.377
    },
    {
      "epoch": 2.1264553622566655,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8884874065022547e-05,
      "loss": 1.0297637939453126,
      "num_input_tokens_seen": 17092807680,
      "step": 60100,
      "train_runtime": 585485.743,
      "train_tokens_per_second": 29194.234
    },
    {
      "epoch": 2.1268091825203945,
      "grad_norm": 1.625,
      "learning_rate": 1.888352719461188e-05,
      "loss": 1.032573127746582,
      "num_input_tokens_seen": 17095697664,
      "step": 60110,
      "train_runtime": 585587.9775,
      "train_tokens_per_second": 29194.072
    },
    {
      "epoch": 2.127163002784123,
      "grad_norm": 1.578125,
      "learning_rate": 1.8882180612336762e-05,
      "loss": 1.0472108840942382,
      "num_input_tokens_seen": 17098565440,
      "step": 60120,
      "train_runtime": 585686.6931,
      "train_tokens_per_second": 29194.048
    },
    {
      "epoch": 2.127516823047852,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8880834318094482e-05,
      "loss": 1.047338104248047,
      "num_input_tokens_seen": 17101441408,
      "step": 60130,
      "train_runtime": 585783.481,
      "train_tokens_per_second": 29194.134
    },
    {
      "epoch": 2.1278706433115806,
      "grad_norm": 1.640625,
      "learning_rate": 1.8879488311782353e-05,
      "loss": 1.0444744110107422,
      "num_input_tokens_seen": 17104317184,
      "step": 60140,
      "train_runtime": 585880.8157,
      "train_tokens_per_second": 29194.192
    },
    {
      "epoch": 2.1282244635753096,
      "grad_norm": 1.609375,
      "learning_rate": 1.887814259329777e-05,
      "loss": 1.0517255783081054,
      "num_input_tokens_seen": 17107165504,
      "step": 60150,
      "train_runtime": 585977.8256,
      "train_tokens_per_second": 29194.22
    },
    {
      "epoch": 2.128578283839038,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8876797162538166e-05,
      "loss": 1.040097141265869,
      "num_input_tokens_seen": 17110032832,
      "step": 60160,
      "train_runtime": 586075.9761,
      "train_tokens_per_second": 29194.223
    },
    {
      "epoch": 2.128932104102767,
      "grad_norm": 1.5859375,
      "learning_rate": 1.887545201940102e-05,
      "loss": 1.0317014694213866,
      "num_input_tokens_seen": 17112893568,
      "step": 60170,
      "train_runtime": 586172.4602,
      "train_tokens_per_second": 29194.298
    },
    {
      "epoch": 2.1292859243664957,
      "grad_norm": 1.5859375,
      "learning_rate": 1.887410716378387e-05,
      "loss": 1.029020404815674,
      "num_input_tokens_seen": 17115758336,
      "step": 60180,
      "train_runtime": 586271.8137,
      "train_tokens_per_second": 29194.237
    },
    {
      "epoch": 2.1296397446302247,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8872762595584308e-05,
      "loss": 1.0479400634765625,
      "num_input_tokens_seen": 17118615232,
      "step": 60190,
      "train_runtime": 586371.0,
      "train_tokens_per_second": 29194.171
    },
    {
      "epoch": 2.1299935648939536,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8871418314699966e-05,
      "loss": 1.0370405197143555,
      "num_input_tokens_seen": 17121483968,
      "step": 60200,
      "train_runtime": 586470.1494,
      "train_tokens_per_second": 29194.127
    },
    {
      "epoch": 2.130347385157682,
      "grad_norm": 1.5546875,
      "learning_rate": 1.887007432102854e-05,
      "loss": 1.0422412872314453,
      "num_input_tokens_seen": 17124333696,
      "step": 60210,
      "train_runtime": 586567.8927,
      "train_tokens_per_second": 29194.12
    },
    {
      "epoch": 2.130701205421411,
      "grad_norm": 1.5625,
      "learning_rate": 1.8868730614467763e-05,
      "loss": 1.0444755554199219,
      "num_input_tokens_seen": 17127250240,
      "step": 60220,
      "train_runtime": 586666.4418,
      "train_tokens_per_second": 29194.188
    },
    {
      "epoch": 2.1310550256851397,
      "grad_norm": 1.6796875,
      "learning_rate": 1.886738719491543e-05,
      "loss": 1.0309707641601562,
      "num_input_tokens_seen": 17130068096,
      "step": 60230,
      "train_runtime": 586763.969,
      "train_tokens_per_second": 29194.138
    },
    {
      "epoch": 2.1314088459488687,
      "grad_norm": 1.59375,
      "learning_rate": 1.8866044062269382e-05,
      "loss": 1.0333799362182616,
      "num_input_tokens_seen": 17132911360,
      "step": 60240,
      "train_runtime": 586861.278,
      "train_tokens_per_second": 29194.142
    },
    {
      "epoch": 2.1317626662125972,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8864701216427515e-05,
      "loss": 1.0232383728027343,
      "num_input_tokens_seen": 17135699264,
      "step": 60250,
      "train_runtime": 586953.6545,
      "train_tokens_per_second": 29194.297
    },
    {
      "epoch": 2.1321164864763262,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8863358657287767e-05,
      "loss": 1.0357827186584472,
      "num_input_tokens_seen": 17138549440,
      "step": 60260,
      "train_runtime": 587051.1554,
      "train_tokens_per_second": 29194.303
    },
    {
      "epoch": 2.1324703067400548,
      "grad_norm": 1.609375,
      "learning_rate": 1.886201638474814e-05,
      "loss": 1.0332340240478515,
      "num_input_tokens_seen": 17141375680,
      "step": 60270,
      "train_runtime": 587147.8294,
      "train_tokens_per_second": 29194.31
    },
    {
      "epoch": 2.1328241270037838,
      "grad_norm": 1.5625,
      "learning_rate": 1.886067439870667e-05,
      "loss": 1.0334027290344239,
      "num_input_tokens_seen": 17144211968,
      "step": 60280,
      "train_runtime": 587245.9747,
      "train_tokens_per_second": 29194.261
    },
    {
      "epoch": 2.1331779472675123,
      "grad_norm": 1.515625,
      "learning_rate": 1.8859332699061463e-05,
      "loss": 1.0290438652038574,
      "num_input_tokens_seen": 17147082240,
      "step": 60290,
      "train_runtime": 587343.0096,
      "train_tokens_per_second": 29194.324
    },
    {
      "epoch": 2.1335317675312413,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8857991285710668e-05,
      "loss": 1.0250091552734375,
      "num_input_tokens_seen": 17149895104,
      "step": 60300,
      "train_runtime": 587439.7316,
      "train_tokens_per_second": 29194.306
    },
    {
      "epoch": 2.13388558779497,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8856650158552467e-05,
      "loss": 1.047140121459961,
      "num_input_tokens_seen": 17152704384,
      "step": 60310,
      "train_runtime": 587533.97,
      "train_tokens_per_second": 29194.405
    },
    {
      "epoch": 2.134239408058699,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8855309317485123e-05,
      "loss": 1.0425759315490724,
      "num_input_tokens_seen": 17155585408,
      "step": 60320,
      "train_runtime": 587633.8234,
      "train_tokens_per_second": 29194.346
    },
    {
      "epoch": 2.1345932283224274,
      "grad_norm": 1.609375,
      "learning_rate": 1.8853968762406928e-05,
      "loss": 1.0268064498901368,
      "num_input_tokens_seen": 17158439360,
      "step": 60330,
      "train_runtime": 587730.1773,
      "train_tokens_per_second": 29194.416
    },
    {
      "epoch": 2.1349470485861564,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8852628493216236e-05,
      "loss": 1.0200824737548828,
      "num_input_tokens_seen": 17161269120,
      "step": 60340,
      "train_runtime": 587826.7326,
      "train_tokens_per_second": 29194.435
    },
    {
      "epoch": 2.1353008688498853,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8851288509811446e-05,
      "loss": 1.0430803298950195,
      "num_input_tokens_seen": 17164128000,
      "step": 60350,
      "train_runtime": 587924.0665,
      "train_tokens_per_second": 29194.464
    },
    {
      "epoch": 2.135654689113614,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8849948812091007e-05,
      "loss": 1.0370073318481445,
      "num_input_tokens_seen": 17166980032,
      "step": 60360,
      "train_runtime": 588021.5634,
      "train_tokens_per_second": 29194.474
    },
    {
      "epoch": 2.136008509377343,
      "grad_norm": 1.546875,
      "learning_rate": 1.884860939995342e-05,
      "loss": 1.044865608215332,
      "num_input_tokens_seen": 17169832896,
      "step": 60370,
      "train_runtime": 588119.6852,
      "train_tokens_per_second": 29194.454
    },
    {
      "epoch": 2.1363623296410714,
      "grad_norm": 1.5390625,
      "learning_rate": 1.884727027329724e-05,
      "loss": 1.0488460540771485,
      "num_input_tokens_seen": 17172664512,
      "step": 60380,
      "train_runtime": 588215.9092,
      "train_tokens_per_second": 29194.492
    },
    {
      "epoch": 2.1367161499048004,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8845931432021067e-05,
      "loss": 1.0419288635253907,
      "num_input_tokens_seen": 17175466560,
      "step": 60390,
      "train_runtime": 588309.3258,
      "train_tokens_per_second": 29194.619
    },
    {
      "epoch": 2.137069970168529,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8844592876023555e-05,
      "loss": 1.0288740158081056,
      "num_input_tokens_seen": 17178302656,
      "step": 60400,
      "train_runtime": 588406.2827,
      "train_tokens_per_second": 29194.628
    },
    {
      "epoch": 2.137423790432258,
      "grad_norm": 1.5859375,
      "learning_rate": 1.88432546052034e-05,
      "loss": 1.0271461486816407,
      "num_input_tokens_seen": 17181206528,
      "step": 60410,
      "train_runtime": 588505.7937,
      "train_tokens_per_second": 29194.626
    },
    {
      "epoch": 2.1377776106959865,
      "grad_norm": 1.640625,
      "learning_rate": 1.884191661945937e-05,
      "loss": 1.0140506744384765,
      "num_input_tokens_seen": 17184034752,
      "step": 60420,
      "train_runtime": 588600.3113,
      "train_tokens_per_second": 29194.743
    },
    {
      "epoch": 2.1381314309597155,
      "grad_norm": 1.6640625,
      "learning_rate": 1.884057891869025e-05,
      "loss": 1.039503288269043,
      "num_input_tokens_seen": 17186925248,
      "step": 60430,
      "train_runtime": 588701.6915,
      "train_tokens_per_second": 29194.625
    },
    {
      "epoch": 2.138485251223444,
      "grad_norm": 1.5234375,
      "learning_rate": 1.883924150279491e-05,
      "loss": 1.0446317672729493,
      "num_input_tokens_seen": 17189764032,
      "step": 60440,
      "train_runtime": 588796.5169,
      "train_tokens_per_second": 29194.745
    },
    {
      "epoch": 2.138839071487173,
      "grad_norm": 1.59375,
      "learning_rate": 1.8837904371672252e-05,
      "loss": 1.035522747039795,
      "num_input_tokens_seen": 17192595904,
      "step": 60450,
      "train_runtime": 588893.5035,
      "train_tokens_per_second": 29194.745
    },
    {
      "epoch": 2.1391928917509015,
      "grad_norm": 1.5625,
      "learning_rate": 1.8836567525221222e-05,
      "loss": 1.0260725021362305,
      "num_input_tokens_seen": 17195496768,
      "step": 60460,
      "train_runtime": 588993.2992,
      "train_tokens_per_second": 29194.724
    },
    {
      "epoch": 2.1395467120146305,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8835230963340828e-05,
      "loss": 1.043486976623535,
      "num_input_tokens_seen": 17198369216,
      "step": 60470,
      "train_runtime": 589092.1673,
      "train_tokens_per_second": 29194.7
    },
    {
      "epoch": 2.139900532278359,
      "grad_norm": 1.59375,
      "learning_rate": 1.883389468593013e-05,
      "loss": 1.026930809020996,
      "num_input_tokens_seen": 17201179520,
      "step": 60480,
      "train_runtime": 589186.3199,
      "train_tokens_per_second": 29194.805
    },
    {
      "epoch": 2.140254352542088,
      "grad_norm": 1.640625,
      "learning_rate": 1.8832558692888226e-05,
      "loss": 1.0295698165893554,
      "num_input_tokens_seen": 17204054720,
      "step": 60490,
      "train_runtime": 589287.0263,
      "train_tokens_per_second": 29194.695
    },
    {
      "epoch": 2.1406081728058166,
      "grad_norm": 1.625,
      "learning_rate": 1.8831222984114276e-05,
      "loss": 1.0314491271972657,
      "num_input_tokens_seen": 17206879424,
      "step": 60500,
      "train_runtime": 589383.3367,
      "train_tokens_per_second": 29194.716
    },
    {
      "epoch": 2.1409619930695456,
      "grad_norm": 1.6015625,
      "learning_rate": 1.882988755950748e-05,
      "loss": 1.0502490997314453,
      "num_input_tokens_seen": 17209693952,
      "step": 60510,
      "train_runtime": 589478.6433,
      "train_tokens_per_second": 29194.771
    },
    {
      "epoch": 2.141315813333274,
      "grad_norm": 1.53125,
      "learning_rate": 1.88285524189671e-05,
      "loss": 1.040369415283203,
      "num_input_tokens_seen": 17212594368,
      "step": 60520,
      "train_runtime": 589584.5704,
      "train_tokens_per_second": 29194.445
    },
    {
      "epoch": 2.141669633597003,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8827217562392433e-05,
      "loss": 1.029594326019287,
      "num_input_tokens_seen": 17215391488,
      "step": 60530,
      "train_runtime": 589678.9546,
      "train_tokens_per_second": 29194.516
    },
    {
      "epoch": 2.142023453860732,
      "grad_norm": 1.578125,
      "learning_rate": 1.8825882989682843e-05,
      "loss": 1.0330682754516602,
      "num_input_tokens_seen": 17218271232,
      "step": 60540,
      "train_runtime": 589778.9255,
      "train_tokens_per_second": 29194.45
    },
    {
      "epoch": 2.1423772741244607,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8824548700737723e-05,
      "loss": 1.0306315422058105,
      "num_input_tokens_seen": 17221112832,
      "step": 60550,
      "train_runtime": 589874.5459,
      "train_tokens_per_second": 29194.535
    },
    {
      "epoch": 2.1427310943881896,
      "grad_norm": 1.578125,
      "learning_rate": 1.8823214695456538e-05,
      "loss": 1.031066608428955,
      "num_input_tokens_seen": 17223947904,
      "step": 60560,
      "train_runtime": 589969.13,
      "train_tokens_per_second": 29194.66
    },
    {
      "epoch": 2.143084914651918,
      "grad_norm": 1.5625,
      "learning_rate": 1.8821880973738792e-05,
      "loss": 1.035140609741211,
      "num_input_tokens_seen": 17226748480,
      "step": 60570,
      "train_runtime": 590062.9687,
      "train_tokens_per_second": 29194.763
    },
    {
      "epoch": 2.143438734915647,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8820547535484033e-05,
      "loss": 1.0229914665222168,
      "num_input_tokens_seen": 17229556736,
      "step": 60580,
      "train_runtime": 590158.6114,
      "train_tokens_per_second": 29194.79
    },
    {
      "epoch": 2.1437925551793757,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8819214380591876e-05,
      "loss": 1.0418058395385743,
      "num_input_tokens_seen": 17232463680,
      "step": 60590,
      "train_runtime": 590258.8674,
      "train_tokens_per_second": 29194.756
    },
    {
      "epoch": 2.1441463754431047,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8817881508961965e-05,
      "loss": 1.033818244934082,
      "num_input_tokens_seen": 17235324608,
      "step": 60600,
      "train_runtime": 590354.603,
      "train_tokens_per_second": 29194.868
    },
    {
      "epoch": 2.1445001957068333,
      "grad_norm": 1.5,
      "learning_rate": 1.881654892049401e-05,
      "loss": 1.047764205932617,
      "num_input_tokens_seen": 17238223424,
      "step": 60610,
      "train_runtime": 590457.9582,
      "train_tokens_per_second": 29194.667
    },
    {
      "epoch": 2.1448540159705622,
      "grad_norm": 1.5625,
      "learning_rate": 1.881521661508776e-05,
      "loss": 1.042230987548828,
      "num_input_tokens_seen": 17241020416,
      "step": 60620,
      "train_runtime": 590552.4922,
      "train_tokens_per_second": 29194.73
    },
    {
      "epoch": 2.145207836234291,
      "grad_norm": 1.625,
      "learning_rate": 1.8813884592643023e-05,
      "loss": 1.0310903549194337,
      "num_input_tokens_seen": 17243888512,
      "step": 60630,
      "train_runtime": 590654.682,
      "train_tokens_per_second": 29194.535
    },
    {
      "epoch": 2.1455616564980198,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8812552853059646e-05,
      "loss": 1.0413289070129395,
      "num_input_tokens_seen": 17246744000,
      "step": 60640,
      "train_runtime": 590750.5089,
      "train_tokens_per_second": 29194.632
    },
    {
      "epoch": 2.1459154767617483,
      "grad_norm": 1.59375,
      "learning_rate": 1.881122139623754e-05,
      "loss": 1.0297426223754882,
      "num_input_tokens_seen": 17249580224,
      "step": 60650,
      "train_runtime": 590849.7268,
      "train_tokens_per_second": 29194.53
    },
    {
      "epoch": 2.1462692970254773,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8809890222076647e-05,
      "loss": 1.031959056854248,
      "num_input_tokens_seen": 17252459328,
      "step": 60660,
      "train_runtime": 590947.3147,
      "train_tokens_per_second": 29194.581
    },
    {
      "epoch": 2.146623117289206,
      "grad_norm": 1.5625,
      "learning_rate": 1.8808559330476978e-05,
      "loss": 1.0241632461547852,
      "num_input_tokens_seen": 17255289664,
      "step": 60670,
      "train_runtime": 591043.233,
      "train_tokens_per_second": 29194.632
    },
    {
      "epoch": 2.146976937552935,
      "grad_norm": 1.6328125,
      "learning_rate": 1.880722872133858e-05,
      "loss": 1.037790298461914,
      "num_input_tokens_seen": 17258201984,
      "step": 60680,
      "train_runtime": 591140.567,
      "train_tokens_per_second": 29194.752
    },
    {
      "epoch": 2.147330757816664,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8805898394561554e-05,
      "loss": 1.0330011367797851,
      "num_input_tokens_seen": 17261048000,
      "step": 60690,
      "train_runtime": 591237.7499,
      "train_tokens_per_second": 29194.766
    },
    {
      "epoch": 2.1476845780803924,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8804568350046047e-05,
      "loss": 1.0419105529785155,
      "num_input_tokens_seen": 17263837120,
      "step": 60700,
      "train_runtime": 591332.8345,
      "train_tokens_per_second": 29194.789
    },
    {
      "epoch": 2.1480383983441214,
      "grad_norm": 1.53125,
      "learning_rate": 1.8803238587692266e-05,
      "loss": 1.034127902984619,
      "num_input_tokens_seen": 17266761024,
      "step": 60710,
      "train_runtime": 591436.6215,
      "train_tokens_per_second": 29194.609
    },
    {
      "epoch": 2.14839221860785,
      "grad_norm": 1.6484375,
      "learning_rate": 1.880190910740045e-05,
      "loss": 1.0453107833862305,
      "num_input_tokens_seen": 17269636992,
      "step": 60720,
      "train_runtime": 591536.7214,
      "train_tokens_per_second": 29194.531
    },
    {
      "epoch": 2.148746038871579,
      "grad_norm": 1.578125,
      "learning_rate": 1.8800579909070908e-05,
      "loss": 1.0241546630859375,
      "num_input_tokens_seen": 17272521472,
      "step": 60730,
      "train_runtime": 591635.9415,
      "train_tokens_per_second": 29194.51
    },
    {
      "epoch": 2.1490998591353074,
      "grad_norm": 1.625,
      "learning_rate": 1.879925099260398e-05,
      "loss": 1.04627685546875,
      "num_input_tokens_seen": 17275307584,
      "step": 60740,
      "train_runtime": 591727.1324,
      "train_tokens_per_second": 29194.719
    },
    {
      "epoch": 2.1494536793990364,
      "grad_norm": 1.5234375,
      "learning_rate": 1.879792235790007e-05,
      "loss": 1.0326631546020508,
      "num_input_tokens_seen": 17278189248,
      "step": 60750,
      "train_runtime": 591828.7098,
      "train_tokens_per_second": 29194.578
    },
    {
      "epoch": 2.149807499662765,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8796594004859614e-05,
      "loss": 1.0478696823120117,
      "num_input_tokens_seen": 17281056064,
      "step": 60760,
      "train_runtime": 591925.9749,
      "train_tokens_per_second": 29194.624
    },
    {
      "epoch": 2.150161319926494,
      "grad_norm": 1.625,
      "learning_rate": 1.8795265933383115e-05,
      "loss": 1.028242301940918,
      "num_input_tokens_seen": 17283865152,
      "step": 60770,
      "train_runtime": 592023.2569,
      "train_tokens_per_second": 29194.571
    },
    {
      "epoch": 2.1505151401902225,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8793938143371118e-05,
      "loss": 1.0257099151611329,
      "num_input_tokens_seen": 17286665344,
      "step": 60780,
      "train_runtime": 592116.8968,
      "train_tokens_per_second": 29194.683
    },
    {
      "epoch": 2.1508689604539515,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8792610634724215e-05,
      "loss": 1.0289459228515625,
      "num_input_tokens_seen": 17289489664,
      "step": 60790,
      "train_runtime": 592212.4486,
      "train_tokens_per_second": 29194.742
    },
    {
      "epoch": 2.15122278071768,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8791283407343048e-05,
      "loss": 1.0328706741333007,
      "num_input_tokens_seen": 17292283776,
      "step": 60800,
      "train_runtime": 592306.1958,
      "train_tokens_per_second": 29194.839
    },
    {
      "epoch": 2.151576600981409,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8789956461128312e-05,
      "loss": 1.044647789001465,
      "num_input_tokens_seen": 17295177216,
      "step": 60810,
      "train_runtime": 592405.4072,
      "train_tokens_per_second": 29194.833
    },
    {
      "epoch": 2.1519304212451376,
      "grad_norm": 1.5546875,
      "learning_rate": 1.878862979598074e-05,
      "loss": 1.034940528869629,
      "num_input_tokens_seen": 17297993216,
      "step": 60820,
      "train_runtime": 592501.2542,
      "train_tokens_per_second": 29194.863
    },
    {
      "epoch": 2.1522842415088665,
      "grad_norm": 1.578125,
      "learning_rate": 1.8787303411801134e-05,
      "loss": 1.0383743286132812,
      "num_input_tokens_seen": 17300816320,
      "step": 60830,
      "train_runtime": 592595.4851,
      "train_tokens_per_second": 29194.985
    },
    {
      "epoch": 2.152638061772595,
      "grad_norm": 1.5234375,
      "learning_rate": 1.8785977308490328e-05,
      "loss": 1.0318321228027343,
      "num_input_tokens_seen": 17303713856,
      "step": 60840,
      "train_runtime": 592692.7197,
      "train_tokens_per_second": 29195.084
    },
    {
      "epoch": 2.152991882036324,
      "grad_norm": 1.59375,
      "learning_rate": 1.8784651485949205e-05,
      "loss": 1.0455472946166993,
      "num_input_tokens_seen": 17306572992,
      "step": 60850,
      "train_runtime": 592790.6347,
      "train_tokens_per_second": 29195.085
    },
    {
      "epoch": 2.1533457023000526,
      "grad_norm": 1.546875,
      "learning_rate": 1.8783325944078713e-05,
      "loss": 1.0372384071350098,
      "num_input_tokens_seen": 17309422016,
      "step": 60860,
      "train_runtime": 592888.006,
      "train_tokens_per_second": 29195.096
    },
    {
      "epoch": 2.1536995225637816,
      "grad_norm": 1.5859375,
      "learning_rate": 1.878200068277983e-05,
      "loss": 1.040329360961914,
      "num_input_tokens_seen": 17312235456,
      "step": 60870,
      "train_runtime": 592983.7445,
      "train_tokens_per_second": 29195.127
    },
    {
      "epoch": 2.1540533428275106,
      "grad_norm": 1.5625,
      "learning_rate": 1.8780675701953594e-05,
      "loss": 1.032847023010254,
      "num_input_tokens_seen": 17315097280,
      "step": 60880,
      "train_runtime": 593081.83,
      "train_tokens_per_second": 29195.124
    },
    {
      "epoch": 2.154407163091239,
      "grad_norm": 1.6015625,
      "learning_rate": 1.877935100150109e-05,
      "loss": 1.0489488601684571,
      "num_input_tokens_seen": 17317914176,
      "step": 60890,
      "train_runtime": 593179.1501,
      "train_tokens_per_second": 29195.082
    },
    {
      "epoch": 2.154760983354968,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8778026581323445e-05,
      "loss": 1.038891315460205,
      "num_input_tokens_seen": 17320673664,
      "step": 60900,
      "train_runtime": 593272.0842,
      "train_tokens_per_second": 29195.16
    },
    {
      "epoch": 2.1551148036186967,
      "grad_norm": 1.59375,
      "learning_rate": 1.8776702441321843e-05,
      "loss": 1.036592674255371,
      "num_input_tokens_seen": 17323522560,
      "step": 60910,
      "train_runtime": 593367.3689,
      "train_tokens_per_second": 29195.273
    },
    {
      "epoch": 2.1554686238824257,
      "grad_norm": 1.578125,
      "learning_rate": 1.8775378581397523e-05,
      "loss": 1.033740234375,
      "num_input_tokens_seen": 17326356480,
      "step": 60920,
      "train_runtime": 593467.4587,
      "train_tokens_per_second": 29195.125
    },
    {
      "epoch": 2.155822444146154,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8774055001451754e-05,
      "loss": 1.0454917907714845,
      "num_input_tokens_seen": 17329271552,
      "step": 60930,
      "train_runtime": 593569.4911,
      "train_tokens_per_second": 29195.017
    },
    {
      "epoch": 2.156176264409883,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8772731701385865e-05,
      "loss": 1.0318553924560547,
      "num_input_tokens_seen": 17332025280,
      "step": 60940,
      "train_runtime": 593661.9173,
      "train_tokens_per_second": 29195.111
    },
    {
      "epoch": 2.1565300846736117,
      "grad_norm": 1.625,
      "learning_rate": 1.8771408681101236e-05,
      "loss": 1.0262277603149415,
      "num_input_tokens_seen": 17334866112,
      "step": 60950,
      "train_runtime": 593759.0774,
      "train_tokens_per_second": 29195.118
    },
    {
      "epoch": 2.1568839049373407,
      "grad_norm": 1.625,
      "learning_rate": 1.877008594049929e-05,
      "loss": 1.0352832794189453,
      "num_input_tokens_seen": 17337678848,
      "step": 60960,
      "train_runtime": 593854.144,
      "train_tokens_per_second": 29195.18
    },
    {
      "epoch": 2.1572377252010693,
      "grad_norm": 1.578125,
      "learning_rate": 1.87687634794815e-05,
      "loss": 1.0220256805419923,
      "num_input_tokens_seen": 17340461952,
      "step": 60970,
      "train_runtime": 593948.8721,
      "train_tokens_per_second": 29195.21
    },
    {
      "epoch": 2.1575915454647983,
      "grad_norm": 1.640625,
      "learning_rate": 1.876744129794939e-05,
      "loss": 1.0388761520385743,
      "num_input_tokens_seen": 17343278528,
      "step": 60980,
      "train_runtime": 594044.9947,
      "train_tokens_per_second": 29195.227
    },
    {
      "epoch": 2.157945365728527,
      "grad_norm": 1.515625,
      "learning_rate": 1.8766119395804525e-05,
      "loss": 1.0292222023010253,
      "num_input_tokens_seen": 17346139328,
      "step": 60990,
      "train_runtime": 594144.7204,
      "train_tokens_per_second": 29195.142
    },
    {
      "epoch": 2.158299185992256,
      "grad_norm": 1.6796875,
      "learning_rate": 1.8764797772948537e-05,
      "loss": 1.0289913177490235,
      "num_input_tokens_seen": 17348953856,
      "step": 61000,
      "train_runtime": 594240.53,
      "train_tokens_per_second": 29195.171
    },
    {
      "epoch": 2.1586530062559843,
      "grad_norm": 1.578125,
      "learning_rate": 1.8763476429283083e-05,
      "loss": 1.0367042541503906,
      "num_input_tokens_seen": 17351814208,
      "step": 61010,
      "train_runtime": 594337.8807,
      "train_tokens_per_second": 29195.202
    },
    {
      "epoch": 2.1590068265197133,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8762155364709885e-05,
      "loss": 1.0466423034667969,
      "num_input_tokens_seen": 17354639808,
      "step": 61020,
      "train_runtime": 594435.2993,
      "train_tokens_per_second": 29195.17
    },
    {
      "epoch": 2.1593606467834423,
      "grad_norm": 1.7109375,
      "learning_rate": 1.8760834579130705e-05,
      "loss": 1.0350506782531739,
      "num_input_tokens_seen": 17357488192,
      "step": 61030,
      "train_runtime": 594531.7547,
      "train_tokens_per_second": 29195.225
    },
    {
      "epoch": 2.159714467047171,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8759514072447352e-05,
      "loss": 1.023944091796875,
      "num_input_tokens_seen": 17360398464,
      "step": 61040,
      "train_runtime": 594630.5037,
      "train_tokens_per_second": 29195.271
    },
    {
      "epoch": 2.1600682873109,
      "grad_norm": 1.6953125,
      "learning_rate": 1.8758193844561695e-05,
      "loss": 1.026142406463623,
      "num_input_tokens_seen": 17363253888,
      "step": 61050,
      "train_runtime": 594730.2848,
      "train_tokens_per_second": 29195.174
    },
    {
      "epoch": 2.1604221075746284,
      "grad_norm": 1.6640625,
      "learning_rate": 1.875687389537564e-05,
      "loss": 1.0328672409057618,
      "num_input_tokens_seen": 17366058752,
      "step": 61060,
      "train_runtime": 594824.3712,
      "train_tokens_per_second": 29195.271
    },
    {
      "epoch": 2.1607759278383574,
      "grad_norm": 1.515625,
      "learning_rate": 1.8755554224791144e-05,
      "loss": 1.035115623474121,
      "num_input_tokens_seen": 17368965504,
      "step": 61070,
      "train_runtime": 594925.4221,
      "train_tokens_per_second": 29195.198
    },
    {
      "epoch": 2.161129748102086,
      "grad_norm": 1.578125,
      "learning_rate": 1.8754234832710217e-05,
      "loss": 1.037948226928711,
      "num_input_tokens_seen": 17371842752,
      "step": 61080,
      "train_runtime": 595025.418,
      "train_tokens_per_second": 29195.127
    },
    {
      "epoch": 2.161483568365815,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8752915719034914e-05,
      "loss": 1.0561432838439941,
      "num_input_tokens_seen": 17374629824,
      "step": 61090,
      "train_runtime": 595118.8783,
      "train_tokens_per_second": 29195.225
    },
    {
      "epoch": 2.1618373886295434,
      "grad_norm": 1.578125,
      "learning_rate": 1.8751596883667337e-05,
      "loss": 1.0417718887329102,
      "num_input_tokens_seen": 17377418176,
      "step": 61100,
      "train_runtime": 595214.0814,
      "train_tokens_per_second": 29195.24
    },
    {
      "epoch": 2.1621912088932724,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8750278326509628e-05,
      "loss": 1.0338545799255372,
      "num_input_tokens_seen": 17380196800,
      "step": 61110,
      "train_runtime": 595304.4671,
      "train_tokens_per_second": 29195.475
    },
    {
      "epoch": 2.162545029157001,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8748960047464e-05,
      "loss": 1.0371318817138673,
      "num_input_tokens_seen": 17383017792,
      "step": 61120,
      "train_runtime": 595399.7906,
      "train_tokens_per_second": 29195.539
    },
    {
      "epoch": 2.16289884942073,
      "grad_norm": 1.5625,
      "learning_rate": 1.8747642046432698e-05,
      "loss": 1.0294586181640626,
      "num_input_tokens_seen": 17385819328,
      "step": 61130,
      "train_runtime": 595491.7098,
      "train_tokens_per_second": 29195.737
    },
    {
      "epoch": 2.1632526696844585,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8746324323318008e-05,
      "loss": 1.0414617538452149,
      "num_input_tokens_seen": 17388649984,
      "step": 61140,
      "train_runtime": 595587.2955,
      "train_tokens_per_second": 29195.804
    },
    {
      "epoch": 2.1636064899481875,
      "grad_norm": 1.578125,
      "learning_rate": 1.8745006878022285e-05,
      "loss": 1.050356960296631,
      "num_input_tokens_seen": 17391516032,
      "step": 61150,
      "train_runtime": 595684.9374,
      "train_tokens_per_second": 29195.83
    },
    {
      "epoch": 2.163960310211916,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8743689710447914e-05,
      "loss": 1.0338499069213867,
      "num_input_tokens_seen": 17394293696,
      "step": 61160,
      "train_runtime": 595780.9742,
      "train_tokens_per_second": 29195.786
    },
    {
      "epoch": 2.164314130475645,
      "grad_norm": 1.578125,
      "learning_rate": 1.8742372820497335e-05,
      "loss": 1.041832160949707,
      "num_input_tokens_seen": 17397146880,
      "step": 61170,
      "train_runtime": 595878.7888,
      "train_tokens_per_second": 29195.781
    },
    {
      "epoch": 2.164667950739374,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8741056208073036e-05,
      "loss": 1.0438559532165528,
      "num_input_tokens_seen": 17400026752,
      "step": 61180,
      "train_runtime": 595978.3858,
      "train_tokens_per_second": 29195.735
    },
    {
      "epoch": 2.1650217710031026,
      "grad_norm": 1.6015625,
      "learning_rate": 1.873973987307755e-05,
      "loss": 1.032145118713379,
      "num_input_tokens_seen": 17402869504,
      "step": 61190,
      "train_runtime": 596076.1336,
      "train_tokens_per_second": 29195.716
    },
    {
      "epoch": 2.1653755912668315,
      "grad_norm": 1.65625,
      "learning_rate": 1.8738423815413468e-05,
      "loss": 1.0353187561035155,
      "num_input_tokens_seen": 17405652992,
      "step": 61200,
      "train_runtime": 596169.6968,
      "train_tokens_per_second": 29195.803
    },
    {
      "epoch": 2.16572941153056,
      "grad_norm": 1.5234375,
      "learning_rate": 1.8737108034983415e-05,
      "loss": 1.0613261222839356,
      "num_input_tokens_seen": 17408465152,
      "step": 61210,
      "train_runtime": 596265.5133,
      "train_tokens_per_second": 29195.828
    },
    {
      "epoch": 2.166083231794289,
      "grad_norm": 1.53125,
      "learning_rate": 1.873579253169007e-05,
      "loss": 1.0227901458740234,
      "num_input_tokens_seen": 17411338880,
      "step": 61220,
      "train_runtime": 596360.5625,
      "train_tokens_per_second": 29195.993
    },
    {
      "epoch": 2.1664370520580176,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8734477305436166e-05,
      "loss": 1.029444122314453,
      "num_input_tokens_seen": 17414242496,
      "step": 61230,
      "train_runtime": 596461.5299,
      "train_tokens_per_second": 29195.919
    },
    {
      "epoch": 2.1667908723217466,
      "grad_norm": 1.5390625,
      "learning_rate": 1.873316235612447e-05,
      "loss": 1.0498411178588867,
      "num_input_tokens_seen": 17417080704,
      "step": 61240,
      "train_runtime": 596559.581,
      "train_tokens_per_second": 29195.878
    },
    {
      "epoch": 2.167144692585475,
      "grad_norm": 1.6171875,
      "learning_rate": 1.873184768365781e-05,
      "loss": 1.0404541015625,
      "num_input_tokens_seen": 17419943680,
      "step": 61250,
      "train_runtime": 596660.6015,
      "train_tokens_per_second": 29195.733
    },
    {
      "epoch": 2.167498512849204,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8730533287939052e-05,
      "loss": 1.034581184387207,
      "num_input_tokens_seen": 17422755584,
      "step": 61260,
      "train_runtime": 596754.5567,
      "train_tokens_per_second": 29195.848
    },
    {
      "epoch": 2.1678523331129327,
      "grad_norm": 1.5625,
      "learning_rate": 1.8729219168871118e-05,
      "loss": 1.0320608139038085,
      "num_input_tokens_seen": 17425571776,
      "step": 61270,
      "train_runtime": 596850.6508,
      "train_tokens_per_second": 29195.866
    },
    {
      "epoch": 2.1682061533766617,
      "grad_norm": 1.625,
      "learning_rate": 1.872790532635697e-05,
      "loss": 1.0320653915405273,
      "num_input_tokens_seen": 17428384256,
      "step": 61280,
      "train_runtime": 596947.4963,
      "train_tokens_per_second": 29195.841
    },
    {
      "epoch": 2.16855997364039,
      "grad_norm": 1.609375,
      "learning_rate": 1.8726591760299626e-05,
      "loss": 1.0348188400268554,
      "num_input_tokens_seen": 17431207488,
      "step": 61290,
      "train_runtime": 597041.4685,
      "train_tokens_per_second": 29195.974
    },
    {
      "epoch": 2.168913793904119,
      "grad_norm": 1.4921875,
      "learning_rate": 1.8725278470602142e-05,
      "loss": 1.0393118858337402,
      "num_input_tokens_seen": 17434045888,
      "step": 61300,
      "train_runtime": 597139.1483,
      "train_tokens_per_second": 29195.952
    },
    {
      "epoch": 2.1692676141678477,
      "grad_norm": 1.5859375,
      "learning_rate": 1.872396545716763e-05,
      "loss": 1.0466660499572753,
      "num_input_tokens_seen": 17436891264,
      "step": 61310,
      "train_runtime": 597236.5743,
      "train_tokens_per_second": 29195.954
    },
    {
      "epoch": 2.1696214344315767,
      "grad_norm": 1.53125,
      "learning_rate": 1.8722652719899246e-05,
      "loss": 1.023768997192383,
      "num_input_tokens_seen": 17439702144,
      "step": 61320,
      "train_runtime": 597332.8739,
      "train_tokens_per_second": 29195.952
    },
    {
      "epoch": 2.1699752546953053,
      "grad_norm": 1.5625,
      "learning_rate": 1.872134025870019e-05,
      "loss": 1.0210708618164062,
      "num_input_tokens_seen": 17442579904,
      "step": 61330,
      "train_runtime": 597432.2863,
      "train_tokens_per_second": 29195.911
    },
    {
      "epoch": 2.1703290749590343,
      "grad_norm": 1.5625,
      "learning_rate": 1.872002807347371e-05,
      "loss": 1.0349971771240234,
      "num_input_tokens_seen": 17445395392,
      "step": 61340,
      "train_runtime": 597526.7302,
      "train_tokens_per_second": 29196.008
    },
    {
      "epoch": 2.170682895222763,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8718716164123114e-05,
      "loss": 1.0319562911987306,
      "num_input_tokens_seen": 17448275072,
      "step": 61350,
      "train_runtime": 597626.7326,
      "train_tokens_per_second": 29195.941
    },
    {
      "epoch": 2.171036715486492,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8717404530551747e-05,
      "loss": 1.0223904609680177,
      "num_input_tokens_seen": 17451117248,
      "step": 61360,
      "train_runtime": 597724.7231,
      "train_tokens_per_second": 29195.91
    },
    {
      "epoch": 2.171390535750221,
      "grad_norm": 1.671875,
      "learning_rate": 1.8716093172662993e-05,
      "loss": 1.0331365585327148,
      "num_input_tokens_seen": 17453973312,
      "step": 61370,
      "train_runtime": 597823.239,
      "train_tokens_per_second": 29195.876
    },
    {
      "epoch": 2.1717443560139493,
      "grad_norm": 1.6171875,
      "learning_rate": 1.87147820903603e-05,
      "loss": 1.0322481155395509,
      "num_input_tokens_seen": 17456835520,
      "step": 61380,
      "train_runtime": 597923.9263,
      "train_tokens_per_second": 29195.747
    },
    {
      "epoch": 2.1720981762776783,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8713471283547156e-05,
      "loss": 1.0435593605041504,
      "num_input_tokens_seen": 17459705216,
      "step": 61390,
      "train_runtime": 598024.8863,
      "train_tokens_per_second": 29195.616
    },
    {
      "epoch": 2.172451996541407,
      "grad_norm": 1.515625,
      "learning_rate": 1.8712160752127094e-05,
      "loss": 1.036268424987793,
      "num_input_tokens_seen": 17462594880,
      "step": 61400,
      "train_runtime": 598125.1853,
      "train_tokens_per_second": 29195.552
    },
    {
      "epoch": 2.172805816805136,
      "grad_norm": 1.640625,
      "learning_rate": 1.8710850496003697e-05,
      "loss": 1.0414047241210938,
      "num_input_tokens_seen": 17465466816,
      "step": 61410,
      "train_runtime": 598225.2157,
      "train_tokens_per_second": 29195.471
    },
    {
      "epoch": 2.1731596370688644,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8709540515080597e-05,
      "loss": 1.0279056549072265,
      "num_input_tokens_seen": 17468312512,
      "step": 61420,
      "train_runtime": 598323.0584,
      "train_tokens_per_second": 29195.453
    },
    {
      "epoch": 2.1735134573325934,
      "grad_norm": 1.515625,
      "learning_rate": 1.8708230809261465e-05,
      "loss": 1.0324644088745116,
      "num_input_tokens_seen": 17471146880,
      "step": 61430,
      "train_runtime": 598418.3536,
      "train_tokens_per_second": 29195.54
    },
    {
      "epoch": 2.173867277596322,
      "grad_norm": 1.53125,
      "learning_rate": 1.8706921378450034e-05,
      "loss": 1.0243822097778321,
      "num_input_tokens_seen": 17473970816,
      "step": 61440,
      "train_runtime": 598519.1514,
      "train_tokens_per_second": 29195.341
    },
    {
      "epoch": 2.174221097860051,
      "grad_norm": 1.640625,
      "learning_rate": 1.870561222255007e-05,
      "loss": 1.0333621025085449,
      "num_input_tokens_seen": 17476795328,
      "step": 61450,
      "train_runtime": 598614.4838,
      "train_tokens_per_second": 29195.41
    },
    {
      "epoch": 2.1745749181237795,
      "grad_norm": 1.578125,
      "learning_rate": 1.8704303341465393e-05,
      "loss": 1.0324178695678712,
      "num_input_tokens_seen": 17479608960,
      "step": 61460,
      "train_runtime": 598709.3019,
      "train_tokens_per_second": 29195.486
    },
    {
      "epoch": 2.1749287383875084,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8702994735099868e-05,
      "loss": 1.041243839263916,
      "num_input_tokens_seen": 17482478592,
      "step": 61470,
      "train_runtime": 598805.0729,
      "train_tokens_per_second": 29195.609
    },
    {
      "epoch": 2.175282558651237,
      "grad_norm": 1.6875,
      "learning_rate": 1.8701686403357407e-05,
      "loss": 1.0407357215881348,
      "num_input_tokens_seen": 17485279424,
      "step": 61480,
      "train_runtime": 598901.8839,
      "train_tokens_per_second": 29195.566
    },
    {
      "epoch": 2.175636378914966,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8700378346141973e-05,
      "loss": 1.034457015991211,
      "num_input_tokens_seen": 17488142464,
      "step": 61490,
      "train_runtime": 599001.1563,
      "train_tokens_per_second": 29195.507
    },
    {
      "epoch": 2.1759901991786945,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8699070563357574e-05,
      "loss": 1.0467189788818358,
      "num_input_tokens_seen": 17490942848,
      "step": 61500,
      "train_runtime": 599095.9732,
      "train_tokens_per_second": 29195.561
    },
    {
      "epoch": 2.1763440194424235,
      "grad_norm": 1.671875,
      "learning_rate": 1.8697763054908255e-05,
      "loss": 1.0322153091430664,
      "num_input_tokens_seen": 17493765120,
      "step": 61510,
      "train_runtime": 599192.9038,
      "train_tokens_per_second": 29195.548
    },
    {
      "epoch": 2.1766978397061525,
      "grad_norm": 1.671875,
      "learning_rate": 1.8696455820698124e-05,
      "loss": 1.038115882873535,
      "num_input_tokens_seen": 17496527616,
      "step": 61520,
      "train_runtime": 599286.7481,
      "train_tokens_per_second": 29195.586
    },
    {
      "epoch": 2.177051659969881,
      "grad_norm": 1.546875,
      "learning_rate": 1.8695148860631327e-05,
      "loss": 1.0433521270751953,
      "num_input_tokens_seen": 17499360960,
      "step": 61530,
      "train_runtime": 599381.2159,
      "train_tokens_per_second": 29195.711
    },
    {
      "epoch": 2.17740548023361,
      "grad_norm": 1.5859375,
      "learning_rate": 1.869384217461206e-05,
      "loss": 1.0533103942871094,
      "num_input_tokens_seen": 17502238720,
      "step": 61540,
      "train_runtime": 599483.4199,
      "train_tokens_per_second": 29195.534
    },
    {
      "epoch": 2.1777593004973386,
      "grad_norm": 1.609375,
      "learning_rate": 1.8692535762544565e-05,
      "loss": 1.036928367614746,
      "num_input_tokens_seen": 17505065216,
      "step": 61550,
      "train_runtime": 599581.4842,
      "train_tokens_per_second": 29195.473
    },
    {
      "epoch": 2.1781131207610676,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8691229624333126e-05,
      "loss": 1.0354942321777343,
      "num_input_tokens_seen": 17507923456,
      "step": 61560,
      "train_runtime": 599680.642,
      "train_tokens_per_second": 29195.412
    },
    {
      "epoch": 2.178466941024796,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8689923759882078e-05,
      "loss": 1.025139617919922,
      "num_input_tokens_seen": 17510774400,
      "step": 61570,
      "train_runtime": 599775.8903,
      "train_tokens_per_second": 29195.529
    },
    {
      "epoch": 2.178820761288525,
      "grad_norm": 1.5703125,
      "learning_rate": 1.868861816909581e-05,
      "loss": 1.0326663970947265,
      "num_input_tokens_seen": 17513635840,
      "step": 61580,
      "train_runtime": 599871.6964,
      "train_tokens_per_second": 29195.636
    },
    {
      "epoch": 2.1791745815522536,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8687312851878747e-05,
      "loss": 1.043799877166748,
      "num_input_tokens_seen": 17516477248,
      "step": 61590,
      "train_runtime": 599967.5734,
      "train_tokens_per_second": 29195.707
    },
    {
      "epoch": 2.1795284018159826,
      "grad_norm": 1.5546875,
      "learning_rate": 1.868600780813536e-05,
      "loss": 1.0415350914001464,
      "num_input_tokens_seen": 17519313344,
      "step": 61600,
      "train_runtime": 600062.0917,
      "train_tokens_per_second": 29195.834
    },
    {
      "epoch": 2.179882222079711,
      "grad_norm": 1.515625,
      "learning_rate": 1.8684703037770177e-05,
      "loss": 1.0295090675354004,
      "num_input_tokens_seen": 17522141632,
      "step": 61610,
      "train_runtime": 600158.7309,
      "train_tokens_per_second": 29195.846
    },
    {
      "epoch": 2.18023604234344,
      "grad_norm": 1.609375,
      "learning_rate": 1.868339854068776e-05,
      "loss": 1.0311452865600585,
      "num_input_tokens_seen": 17525007360,
      "step": 61620,
      "train_runtime": 600257.9011,
      "train_tokens_per_second": 29195.796
    },
    {
      "epoch": 2.1805898626071687,
      "grad_norm": 1.5234375,
      "learning_rate": 1.8682094316792737e-05,
      "loss": 1.0359119415283202,
      "num_input_tokens_seen": 17527868992,
      "step": 61630,
      "train_runtime": 600355.6136,
      "train_tokens_per_second": 29195.811
    },
    {
      "epoch": 2.1809436828708977,
      "grad_norm": 1.59375,
      "learning_rate": 1.868079036598975e-05,
      "loss": 1.0254598617553712,
      "num_input_tokens_seen": 17530742272,
      "step": 61640,
      "train_runtime": 600456.5247,
      "train_tokens_per_second": 29195.69
    },
    {
      "epoch": 2.1812975031346262,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8679486688183527e-05,
      "loss": 1.0265083312988281,
      "num_input_tokens_seen": 17533594048,
      "step": 61650,
      "train_runtime": 600555.1642,
      "train_tokens_per_second": 29195.643
    },
    {
      "epoch": 2.181651323398355,
      "grad_norm": 1.578125,
      "learning_rate": 1.8678183283278816e-05,
      "loss": 1.027509880065918,
      "num_input_tokens_seen": 17536464256,
      "step": 61660,
      "train_runtime": 600653.1376,
      "train_tokens_per_second": 29195.659
    },
    {
      "epoch": 2.1820051436620838,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8676880151180415e-05,
      "loss": 1.017686367034912,
      "num_input_tokens_seen": 17539378816,
      "step": 61670,
      "train_runtime": 600753.2635,
      "train_tokens_per_second": 29195.645
    },
    {
      "epoch": 2.1823589639258127,
      "grad_norm": 1.609375,
      "learning_rate": 1.8675577291793172e-05,
      "loss": 1.0239133834838867,
      "num_input_tokens_seen": 17542225280,
      "step": 61680,
      "train_runtime": 600849.5313,
      "train_tokens_per_second": 29195.704
    },
    {
      "epoch": 2.1827127841895413,
      "grad_norm": 1.53125,
      "learning_rate": 1.867427470502199e-05,
      "loss": 1.0345226287841798,
      "num_input_tokens_seen": 17545053888,
      "step": 61690,
      "train_runtime": 600946.616,
      "train_tokens_per_second": 29195.695
    },
    {
      "epoch": 2.1830666044532703,
      "grad_norm": 1.5546875,
      "learning_rate": 1.86729723907718e-05,
      "loss": 1.0400017738342284,
      "num_input_tokens_seen": 17547918080,
      "step": 61700,
      "train_runtime": 601044.1407,
      "train_tokens_per_second": 29195.723
    },
    {
      "epoch": 2.1834204247169993,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8671670348947597e-05,
      "loss": 1.0336851119995116,
      "num_input_tokens_seen": 17550791040,
      "step": 61710,
      "train_runtime": 601142.5741,
      "train_tokens_per_second": 29195.721
    },
    {
      "epoch": 2.183774244980728,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8670368579454405e-05,
      "loss": 1.0389968872070312,
      "num_input_tokens_seen": 17553607104,
      "step": 61720,
      "train_runtime": 601239.8796,
      "train_tokens_per_second": 29195.68
    },
    {
      "epoch": 2.184128065244457,
      "grad_norm": 1.53125,
      "learning_rate": 1.8669067082197318e-05,
      "loss": 1.035944938659668,
      "num_input_tokens_seen": 17556536064,
      "step": 61730,
      "train_runtime": 601342.4339,
      "train_tokens_per_second": 29195.572
    },
    {
      "epoch": 2.1844818855081853,
      "grad_norm": 1.6875,
      "learning_rate": 1.866776585708145e-05,
      "loss": 1.0309480667114257,
      "num_input_tokens_seen": 17559385856,
      "step": 61740,
      "train_runtime": 601436.3512,
      "train_tokens_per_second": 29195.751
    },
    {
      "epoch": 2.1848357057719143,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8666464904011983e-05,
      "loss": 1.0252955436706543,
      "num_input_tokens_seen": 17562246080,
      "step": 61750,
      "train_runtime": 601536.2738,
      "train_tokens_per_second": 29195.656
    },
    {
      "epoch": 2.185189526035643,
      "grad_norm": 1.578125,
      "learning_rate": 1.8665164222894125e-05,
      "loss": 1.0456543922424317,
      "num_input_tokens_seen": 17565140800,
      "step": 61760,
      "train_runtime": 601635.3742,
      "train_tokens_per_second": 29195.658
    },
    {
      "epoch": 2.185543346299372,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8663863813633152e-05,
      "loss": 1.0315608978271484,
      "num_input_tokens_seen": 17567945856,
      "step": 61770,
      "train_runtime": 601729.0222,
      "train_tokens_per_second": 29195.776
    },
    {
      "epoch": 2.1858971665631004,
      "grad_norm": 1.640625,
      "learning_rate": 1.866256367613437e-05,
      "loss": 1.0364339828491211,
      "num_input_tokens_seen": 17570781184,
      "step": 61780,
      "train_runtime": 601826.378,
      "train_tokens_per_second": 29195.764
    },
    {
      "epoch": 2.1862509868268294,
      "grad_norm": 1.59375,
      "learning_rate": 1.8661263810303138e-05,
      "loss": 1.0412982940673827,
      "num_input_tokens_seen": 17573646208,
      "step": 61790,
      "train_runtime": 601923.8692,
      "train_tokens_per_second": 29195.796
    },
    {
      "epoch": 2.186604807090558,
      "grad_norm": 1.578125,
      "learning_rate": 1.8659964216044853e-05,
      "loss": 1.0393583297729492,
      "num_input_tokens_seen": 17576526592,
      "step": 61800,
      "train_runtime": 602023.2115,
      "train_tokens_per_second": 29195.762
    },
    {
      "epoch": 2.186958627354287,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8658664893264978e-05,
      "loss": 1.0269815444946289,
      "num_input_tokens_seen": 17579403136,
      "step": 61810,
      "train_runtime": 602125.2337,
      "train_tokens_per_second": 29195.593
    },
    {
      "epoch": 2.1873124476180155,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8657365841868997e-05,
      "loss": 1.0229013442993165,
      "num_input_tokens_seen": 17582272640,
      "step": 61820,
      "train_runtime": 602222.5742,
      "train_tokens_per_second": 29195.639
    },
    {
      "epoch": 2.1876662678817445,
      "grad_norm": 1.625,
      "learning_rate": 1.865606706176246e-05,
      "loss": 1.0298029899597168,
      "num_input_tokens_seen": 17585155648,
      "step": 61830,
      "train_runtime": 602321.7097,
      "train_tokens_per_second": 29195.62
    },
    {
      "epoch": 2.188020088145473,
      "grad_norm": 1.6640625,
      "learning_rate": 1.8654768552850943e-05,
      "loss": 1.0325407981872559,
      "num_input_tokens_seen": 17588005056,
      "step": 61840,
      "train_runtime": 602417.5787,
      "train_tokens_per_second": 29195.704
    },
    {
      "epoch": 2.188373908409202,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8653470315040096e-05,
      "loss": 1.0392494201660156,
      "num_input_tokens_seen": 17590807744,
      "step": 61850,
      "train_runtime": 602512.3576,
      "train_tokens_per_second": 29195.763
    },
    {
      "epoch": 2.188727728672931,
      "grad_norm": 1.609375,
      "learning_rate": 1.8652172348235588e-05,
      "loss": 1.0315486907958984,
      "num_input_tokens_seen": 17593702784,
      "step": 61860,
      "train_runtime": 602610.1775,
      "train_tokens_per_second": 29195.827
    },
    {
      "epoch": 2.1890815489366595,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8650874652343146e-05,
      "loss": 1.0366020202636719,
      "num_input_tokens_seen": 17596551360,
      "step": 61870,
      "train_runtime": 602706.6393,
      "train_tokens_per_second": 29195.881
    },
    {
      "epoch": 2.1894353692003885,
      "grad_norm": 1.6484375,
      "learning_rate": 1.864957722726855e-05,
      "loss": 1.0170689582824708,
      "num_input_tokens_seen": 17599421888,
      "step": 61880,
      "train_runtime": 602806.221,
      "train_tokens_per_second": 29195.82
    },
    {
      "epoch": 2.189789189464117,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8648280072917605e-05,
      "loss": 1.044498825073242,
      "num_input_tokens_seen": 17602278592,
      "step": 61890,
      "train_runtime": 602901.6762,
      "train_tokens_per_second": 29195.936
    },
    {
      "epoch": 2.190143009727846,
      "grad_norm": 1.546875,
      "learning_rate": 1.864698318919618e-05,
      "loss": 1.0406606674194336,
      "num_input_tokens_seen": 17605110528,
      "step": 61900,
      "train_runtime": 602997.1602,
      "train_tokens_per_second": 29196.009
    },
    {
      "epoch": 2.1904968299915746,
      "grad_norm": 1.546875,
      "learning_rate": 1.8645686576010185e-05,
      "loss": 1.0333731651306153,
      "num_input_tokens_seen": 17607923200,
      "step": 61910,
      "train_runtime": 603095.0599,
      "train_tokens_per_second": 29195.933
    },
    {
      "epoch": 2.1908506502553036,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8644390233265576e-05,
      "loss": 1.0354606628417968,
      "num_input_tokens_seen": 17610732992,
      "step": 61920,
      "train_runtime": 603190.1333,
      "train_tokens_per_second": 29195.99
    },
    {
      "epoch": 2.191204470519032,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8643094160868353e-05,
      "loss": 1.032284927368164,
      "num_input_tokens_seen": 17613603008,
      "step": 61930,
      "train_runtime": 603287.1595,
      "train_tokens_per_second": 29196.052
    },
    {
      "epoch": 2.191558290782761,
      "grad_norm": 1.59375,
      "learning_rate": 1.864179835872456e-05,
      "loss": 1.0242864608764648,
      "num_input_tokens_seen": 17616494016,
      "step": 61940,
      "train_runtime": 603387.9176,
      "train_tokens_per_second": 29195.967
    },
    {
      "epoch": 2.1919121110464896,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8640502826740292e-05,
      "loss": 1.0320741653442382,
      "num_input_tokens_seen": 17619335488,
      "step": 61950,
      "train_runtime": 603484.304,
      "train_tokens_per_second": 29196.013
    },
    {
      "epoch": 2.1922659313102186,
      "grad_norm": 1.53125,
      "learning_rate": 1.8639207564821686e-05,
      "loss": 1.0297990798950196,
      "num_input_tokens_seen": 17622172864,
      "step": 61960,
      "train_runtime": 603580.0926,
      "train_tokens_per_second": 29196.08
    },
    {
      "epoch": 2.192619751573947,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8637912572874924e-05,
      "loss": 1.0415176391601562,
      "num_input_tokens_seen": 17625011712,
      "step": 61970,
      "train_runtime": 603675.2437,
      "train_tokens_per_second": 29196.181
    },
    {
      "epoch": 2.192973571837676,
      "grad_norm": 1.6171875,
      "learning_rate": 1.863661785080624e-05,
      "loss": 1.0399425506591797,
      "num_input_tokens_seen": 17627814336,
      "step": 61980,
      "train_runtime": 603770.9954,
      "train_tokens_per_second": 29196.193
    },
    {
      "epoch": 2.1933273921014047,
      "grad_norm": 1.65625,
      "learning_rate": 1.86353233985219e-05,
      "loss": 1.0482044219970703,
      "num_input_tokens_seen": 17630649280,
      "step": 61990,
      "train_runtime": 603869.433,
      "train_tokens_per_second": 29196.128
    },
    {
      "epoch": 2.1936812123651337,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8634029215928235e-05,
      "loss": 1.0341508865356446,
      "num_input_tokens_seen": 17633497792,
      "step": 62000,
      "train_runtime": 603966.2359,
      "train_tokens_per_second": 29196.165
    },
    {
      "epoch": 2.1940350326288627,
      "grad_norm": 1.5625,
      "learning_rate": 1.8632735302931604e-05,
      "loss": 1.037165069580078,
      "num_input_tokens_seen": 17636320640,
      "step": 62010,
      "train_runtime": 604062.4466,
      "train_tokens_per_second": 29196.188
    },
    {
      "epoch": 2.1943888528925912,
      "grad_norm": 1.59375,
      "learning_rate": 1.8631441659438417e-05,
      "loss": 1.0354007720947265,
      "num_input_tokens_seen": 17639196672,
      "step": 62020,
      "train_runtime": 604159.2353,
      "train_tokens_per_second": 29196.271
    },
    {
      "epoch": 2.19474267315632,
      "grad_norm": 1.5703125,
      "learning_rate": 1.863014828535514e-05,
      "loss": 1.0331151008605957,
      "num_input_tokens_seen": 17642081216,
      "step": 62030,
      "train_runtime": 604257.669,
      "train_tokens_per_second": 29196.288
    },
    {
      "epoch": 2.1950964934200488,
      "grad_norm": 1.5625,
      "learning_rate": 1.8628855180588262e-05,
      "loss": 1.042378044128418,
      "num_input_tokens_seen": 17644976064,
      "step": 62040,
      "train_runtime": 604357.0187,
      "train_tokens_per_second": 29196.279
    },
    {
      "epoch": 2.1954503136837777,
      "grad_norm": 1.59375,
      "learning_rate": 1.862756234504434e-05,
      "loss": 1.0557915687561035,
      "num_input_tokens_seen": 17647833216,
      "step": 62050,
      "train_runtime": 604453.689,
      "train_tokens_per_second": 29196.336
    },
    {
      "epoch": 2.1958041339475063,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8626269778629965e-05,
      "loss": 1.0349488258361816,
      "num_input_tokens_seen": 17650638208,
      "step": 62060,
      "train_runtime": 604548.0874,
      "train_tokens_per_second": 29196.417
    },
    {
      "epoch": 2.1961579542112353,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8624977481251777e-05,
      "loss": 1.0277597427368164,
      "num_input_tokens_seen": 17653478400,
      "step": 62070,
      "train_runtime": 604645.2465,
      "train_tokens_per_second": 29196.423
    },
    {
      "epoch": 2.196511774474964,
      "grad_norm": 1.5390625,
      "learning_rate": 1.862368545281646e-05,
      "loss": 1.033428955078125,
      "num_input_tokens_seen": 17656320896,
      "step": 62080,
      "train_runtime": 604741.2959,
      "train_tokens_per_second": 29196.486
    },
    {
      "epoch": 2.196865594738693,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8622393693230738e-05,
      "loss": 1.0331455230712892,
      "num_input_tokens_seen": 17659203712,
      "step": 62090,
      "train_runtime": 604842.9192,
      "train_tokens_per_second": 29196.347
    },
    {
      "epoch": 2.1972194150024213,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8621102202401388e-05,
      "loss": 1.042647361755371,
      "num_input_tokens_seen": 17662076288,
      "step": 62100,
      "train_runtime": 604941.1555,
      "train_tokens_per_second": 29196.354
    },
    {
      "epoch": 2.1975732352661503,
      "grad_norm": 1.6484375,
      "learning_rate": 1.8619810980235236e-05,
      "loss": 1.0368070602416992,
      "num_input_tokens_seen": 17664887296,
      "step": 62110,
      "train_runtime": 605033.0511,
      "train_tokens_per_second": 29196.566
    },
    {
      "epoch": 2.197927055529879,
      "grad_norm": 1.578125,
      "learning_rate": 1.861852002663913e-05,
      "loss": 1.0344112396240235,
      "num_input_tokens_seen": 17667683200,
      "step": 62120,
      "train_runtime": 605126.9479,
      "train_tokens_per_second": 29196.656
    },
    {
      "epoch": 2.198280875793608,
      "grad_norm": 1.640625,
      "learning_rate": 1.8617229341520003e-05,
      "loss": 1.03271484375,
      "num_input_tokens_seen": 17670567744,
      "step": 62130,
      "train_runtime": 605223.5778,
      "train_tokens_per_second": 29196.76
    },
    {
      "epoch": 2.1986346960573364,
      "grad_norm": 1.6328125,
      "learning_rate": 1.861593892478479e-05,
      "loss": 1.0349559783935547,
      "num_input_tokens_seen": 17673351808,
      "step": 62140,
      "train_runtime": 605314.1736,
      "train_tokens_per_second": 29196.99
    },
    {
      "epoch": 2.1989885163210654,
      "grad_norm": 1.5546875,
      "learning_rate": 1.861464877634051e-05,
      "loss": 1.038050079345703,
      "num_input_tokens_seen": 17676174976,
      "step": 62150,
      "train_runtime": 605411.4305,
      "train_tokens_per_second": 29196.963
    },
    {
      "epoch": 2.199342336584794,
      "grad_norm": 1.5859375,
      "learning_rate": 1.861335889609419e-05,
      "loss": 1.0267320632934571,
      "num_input_tokens_seen": 17679012096,
      "step": 62160,
      "train_runtime": 605509.7641,
      "train_tokens_per_second": 29196.907
    },
    {
      "epoch": 2.199696156848523,
      "grad_norm": 1.5625,
      "learning_rate": 1.861206928395293e-05,
      "loss": 1.028369140625,
      "num_input_tokens_seen": 17681857024,
      "step": 62170,
      "train_runtime": 605608.6589,
      "train_tokens_per_second": 29196.837
    },
    {
      "epoch": 2.2000499771122515,
      "grad_norm": 1.59375,
      "learning_rate": 1.8610779939823866e-05,
      "loss": 1.0324415206909179,
      "num_input_tokens_seen": 17684691456,
      "step": 62180,
      "train_runtime": 605707.3917,
      "train_tokens_per_second": 29196.757
    },
    {
      "epoch": 2.2004037973759805,
      "grad_norm": 1.6484375,
      "learning_rate": 1.8609490863614178e-05,
      "loss": 1.0506168365478517,
      "num_input_tokens_seen": 17687516544,
      "step": 62190,
      "train_runtime": 605802.4534,
      "train_tokens_per_second": 29196.839
    },
    {
      "epoch": 2.2007576176397095,
      "grad_norm": 1.6484375,
      "learning_rate": 1.860820205523109e-05,
      "loss": 1.0250724792480468,
      "num_input_tokens_seen": 17690320320,
      "step": 62200,
      "train_runtime": 605897.4965,
      "train_tokens_per_second": 29196.886
    },
    {
      "epoch": 2.201111437903438,
      "grad_norm": 1.625,
      "learning_rate": 1.860691351458187e-05,
      "loss": 1.0261665344238282,
      "num_input_tokens_seen": 17693185216,
      "step": 62210,
      "train_runtime": 605997.5535,
      "train_tokens_per_second": 29196.793
    },
    {
      "epoch": 2.201465258167167,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8605625241573843e-05,
      "loss": 1.037122917175293,
      "num_input_tokens_seen": 17696017216,
      "step": 62220,
      "train_runtime": 606094.8899,
      "train_tokens_per_second": 29196.777
    },
    {
      "epoch": 2.2018190784308955,
      "grad_norm": 1.6328125,
      "learning_rate": 1.860433723611436e-05,
      "loss": 1.0384132385253906,
      "num_input_tokens_seen": 17698888960,
      "step": 62230,
      "train_runtime": 606191.9777,
      "train_tokens_per_second": 29196.838
    },
    {
      "epoch": 2.2021728986946245,
      "grad_norm": 1.640625,
      "learning_rate": 1.860304949811083e-05,
      "loss": 1.0161128997802735,
      "num_input_tokens_seen": 17701728960,
      "step": 62240,
      "train_runtime": 606292.5496,
      "train_tokens_per_second": 29196.679
    },
    {
      "epoch": 2.202526718958353,
      "grad_norm": 1.59375,
      "learning_rate": 1.8601762027470703e-05,
      "loss": 1.039572811126709,
      "num_input_tokens_seen": 17704541120,
      "step": 62250,
      "train_runtime": 606390.1043,
      "train_tokens_per_second": 29196.619
    },
    {
      "epoch": 2.202880539222082,
      "grad_norm": 1.578125,
      "learning_rate": 1.8600474824101473e-05,
      "loss": 1.035677719116211,
      "num_input_tokens_seen": 17707415232,
      "step": 62260,
      "train_runtime": 606488.8369,
      "train_tokens_per_second": 29196.605
    },
    {
      "epoch": 2.2032343594858106,
      "grad_norm": 1.625,
      "learning_rate": 1.8599187887910684e-05,
      "loss": 1.0380376815795898,
      "num_input_tokens_seen": 17710243136,
      "step": 62270,
      "train_runtime": 606586.9317,
      "train_tokens_per_second": 29196.546
    },
    {
      "epoch": 2.2035881797495396,
      "grad_norm": 1.5078125,
      "learning_rate": 1.8597901218805913e-05,
      "loss": 1.0464062690734863,
      "num_input_tokens_seen": 17713073152,
      "step": 62280,
      "train_runtime": 606683.0377,
      "train_tokens_per_second": 29196.585
    },
    {
      "epoch": 2.203942000013268,
      "grad_norm": 1.6484375,
      "learning_rate": 1.8596614816694798e-05,
      "loss": 1.0464081764221191,
      "num_input_tokens_seen": 17715918400,
      "step": 62290,
      "train_runtime": 606779.8825,
      "train_tokens_per_second": 29196.615
    },
    {
      "epoch": 2.204295820276997,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8595328681485004e-05,
      "loss": 1.0373023986816405,
      "num_input_tokens_seen": 17718743104,
      "step": 62300,
      "train_runtime": 606877.4962,
      "train_tokens_per_second": 29196.573
    },
    {
      "epoch": 2.2046496405407257,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8594042813084256e-05,
      "loss": 1.0293991088867187,
      "num_input_tokens_seen": 17721597248,
      "step": 62310,
      "train_runtime": 606977.2579,
      "train_tokens_per_second": 29196.477
    },
    {
      "epoch": 2.2050034608044546,
      "grad_norm": 1.640625,
      "learning_rate": 1.859275721140032e-05,
      "loss": 1.0247962951660157,
      "num_input_tokens_seen": 17724442304,
      "step": 62320,
      "train_runtime": 607074.4223,
      "train_tokens_per_second": 29196.49
    },
    {
      "epoch": 2.205357281068183,
      "grad_norm": 1.5625,
      "learning_rate": 1.8591471876341e-05,
      "loss": 1.0365991592407227,
      "num_input_tokens_seen": 17727305152,
      "step": 62330,
      "train_runtime": 607169.8118,
      "train_tokens_per_second": 29196.618
    },
    {
      "epoch": 2.205711101331912,
      "grad_norm": 1.4765625,
      "learning_rate": 1.859018680781414e-05,
      "loss": 1.0345233917236327,
      "num_input_tokens_seen": 17730153856,
      "step": 62340,
      "train_runtime": 607265.894,
      "train_tokens_per_second": 29196.69
    },
    {
      "epoch": 2.206064921595641,
      "grad_norm": 1.625,
      "learning_rate": 1.8588902005727657e-05,
      "loss": 1.0383614540100097,
      "num_input_tokens_seen": 17732989184,
      "step": 62350,
      "train_runtime": 607361.2008,
      "train_tokens_per_second": 29196.776
    },
    {
      "epoch": 2.2064187418593697,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8587617469989476e-05,
      "loss": 1.0330827713012696,
      "num_input_tokens_seen": 17735848512,
      "step": 62360,
      "train_runtime": 607461.3975,
      "train_tokens_per_second": 29196.668
    },
    {
      "epoch": 2.2067725621230987,
      "grad_norm": 1.609375,
      "learning_rate": 1.8586333200507588e-05,
      "loss": 1.0304414749145507,
      "num_input_tokens_seen": 17738637504,
      "step": 62370,
      "train_runtime": 607556.4466,
      "train_tokens_per_second": 29196.69
    },
    {
      "epoch": 2.2071263823868272,
      "grad_norm": 1.5703125,
      "learning_rate": 1.858504919719003e-05,
      "loss": 1.0402921676635741,
      "num_input_tokens_seen": 17741497344,
      "step": 62380,
      "train_runtime": 607654.663,
      "train_tokens_per_second": 29196.678
    },
    {
      "epoch": 2.2074802026505562,
      "grad_norm": 1.578125,
      "learning_rate": 1.858376545994487e-05,
      "loss": 1.0380632400512695,
      "num_input_tokens_seen": 17744365440,
      "step": 62390,
      "train_runtime": 607754.0307,
      "train_tokens_per_second": 29196.623
    },
    {
      "epoch": 2.2078340229142848,
      "grad_norm": 1.6484375,
      "learning_rate": 1.858248198868023e-05,
      "loss": 1.0395071029663085,
      "num_input_tokens_seen": 17747151168,
      "step": 62400,
      "train_runtime": 607848.7902,
      "train_tokens_per_second": 29196.655
    },
    {
      "epoch": 2.2081878431780138,
      "grad_norm": 1.609375,
      "learning_rate": 1.8581198783304274e-05,
      "loss": 1.0322110176086425,
      "num_input_tokens_seen": 17749970624,
      "step": 62410,
      "train_runtime": 607943.9537,
      "train_tokens_per_second": 29196.722
    },
    {
      "epoch": 2.2085416634417423,
      "grad_norm": 1.578125,
      "learning_rate": 1.8579915843725208e-05,
      "loss": 1.0338438987731933,
      "num_input_tokens_seen": 17752786432,
      "step": 62420,
      "train_runtime": 608042.1862,
      "train_tokens_per_second": 29196.636
    },
    {
      "epoch": 2.2088954837054713,
      "grad_norm": 1.5625,
      "learning_rate": 1.857863316985129e-05,
      "loss": 1.0273969650268555,
      "num_input_tokens_seen": 17755608000,
      "step": 62430,
      "train_runtime": 608135.6416,
      "train_tokens_per_second": 29196.789
    },
    {
      "epoch": 2.2092493039692,
      "grad_norm": 1.6015625,
      "learning_rate": 1.857735076159082e-05,
      "loss": 1.040304183959961,
      "num_input_tokens_seen": 17758458496,
      "step": 62440,
      "train_runtime": 608234.1207,
      "train_tokens_per_second": 29196.748
    },
    {
      "epoch": 2.209603124232929,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8576068618852123e-05,
      "loss": 1.032697868347168,
      "num_input_tokens_seen": 17761298176,
      "step": 62450,
      "train_runtime": 608332.7384,
      "train_tokens_per_second": 29196.683
    },
    {
      "epoch": 2.2099569444966574,
      "grad_norm": 1.5625,
      "learning_rate": 1.8574786741543605e-05,
      "loss": 1.0207687377929688,
      "num_input_tokens_seen": 17764157248,
      "step": 62460,
      "train_runtime": 608430.7057,
      "train_tokens_per_second": 29196.681
    },
    {
      "epoch": 2.2103107647603863,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8573505129573684e-05,
      "loss": 1.0311878204345704,
      "num_input_tokens_seen": 17766932928,
      "step": 62470,
      "train_runtime": 608523.1597,
      "train_tokens_per_second": 29196.806
    },
    {
      "epoch": 2.210664585024115,
      "grad_norm": 1.5703125,
      "learning_rate": 1.857222378285084e-05,
      "loss": 1.0336832046508788,
      "num_input_tokens_seen": 17769756160,
      "step": 62480,
      "train_runtime": 608618.1834,
      "train_tokens_per_second": 29196.887
    },
    {
      "epoch": 2.211018405287844,
      "grad_norm": 1.53125,
      "learning_rate": 1.8570942701283585e-05,
      "loss": 1.0314796447753907,
      "num_input_tokens_seen": 17772630336,
      "step": 62490,
      "train_runtime": 608716.356,
      "train_tokens_per_second": 29196.9
    },
    {
      "epoch": 2.2113722255515724,
      "grad_norm": 1.640625,
      "learning_rate": 1.8569661884780485e-05,
      "loss": 1.0482921600341797,
      "num_input_tokens_seen": 17775517248,
      "step": 62500,
      "train_runtime": 608816.6751,
      "train_tokens_per_second": 29196.83
    },
    {
      "epoch": 2.2117260458153014,
      "grad_norm": 1.59375,
      "learning_rate": 1.8568381333250152e-05,
      "loss": 1.0401954650878906,
      "num_input_tokens_seen": 17778377984,
      "step": 62510,
      "train_runtime": 608913.5105,
      "train_tokens_per_second": 29196.885
    },
    {
      "epoch": 2.21207986607903,
      "grad_norm": 1.6015625,
      "learning_rate": 1.856710104660123e-05,
      "loss": 1.0236482620239258,
      "num_input_tokens_seen": 17781199488,
      "step": 62520,
      "train_runtime": 609010.6037,
      "train_tokens_per_second": 29196.864
    },
    {
      "epoch": 2.212433686342759,
      "grad_norm": 1.578125,
      "learning_rate": 1.8565821024742414e-05,
      "loss": 1.0427706718444825,
      "num_input_tokens_seen": 17784016896,
      "step": 62530,
      "train_runtime": 609106.1358,
      "train_tokens_per_second": 29196.91
    },
    {
      "epoch": 2.212787506606488,
      "grad_norm": 1.5703125,
      "learning_rate": 1.856454126758245e-05,
      "loss": 1.0355745315551759,
      "num_input_tokens_seen": 17786886592,
      "step": 62540,
      "train_runtime": 609205.4588,
      "train_tokens_per_second": 29196.86
    },
    {
      "epoch": 2.2131413268702165,
      "grad_norm": 1.671875,
      "learning_rate": 1.8563261775030108e-05,
      "loss": 1.044036293029785,
      "num_input_tokens_seen": 17789750720,
      "step": 62550,
      "train_runtime": 609305.2359,
      "train_tokens_per_second": 29196.78
    },
    {
      "epoch": 2.2134951471339455,
      "grad_norm": 1.5390625,
      "learning_rate": 1.856198254699423e-05,
      "loss": 1.0357852935791017,
      "num_input_tokens_seen": 17792588096,
      "step": 62560,
      "train_runtime": 609404.0811,
      "train_tokens_per_second": 29196.7
    },
    {
      "epoch": 2.213848967397674,
      "grad_norm": 1.59375,
      "learning_rate": 1.8560703583383675e-05,
      "loss": 1.031400775909424,
      "num_input_tokens_seen": 17795441536,
      "step": 62570,
      "train_runtime": 609500.5288,
      "train_tokens_per_second": 29196.761
    },
    {
      "epoch": 2.214202787661403,
      "grad_norm": 1.578125,
      "learning_rate": 1.855942488410737e-05,
      "loss": 1.0412686347961426,
      "num_input_tokens_seen": 17798296512,
      "step": 62580,
      "train_runtime": 609598.9173,
      "train_tokens_per_second": 29196.732
    },
    {
      "epoch": 2.2145566079251315,
      "grad_norm": 1.6171875,
      "learning_rate": 1.855814644907426e-05,
      "loss": 1.0430171012878418,
      "num_input_tokens_seen": 17801200640,
      "step": 62590,
      "train_runtime": 609700.9613,
      "train_tokens_per_second": 29196.609
    },
    {
      "epoch": 2.2149104281888605,
      "grad_norm": 1.6171875,
      "learning_rate": 1.855686827819336e-05,
      "loss": 1.0205448150634766,
      "num_input_tokens_seen": 17804031872,
      "step": 62600,
      "train_runtime": 609797.9895,
      "train_tokens_per_second": 29196.606
    },
    {
      "epoch": 2.215264248452589,
      "grad_norm": 1.6171875,
      "learning_rate": 1.855559037137371e-05,
      "loss": 1.044449806213379,
      "num_input_tokens_seen": 17806885504,
      "step": 62610,
      "train_runtime": 609894.6313,
      "train_tokens_per_second": 29196.659
    },
    {
      "epoch": 2.215618068716318,
      "grad_norm": 1.6484375,
      "learning_rate": 1.85543127285244e-05,
      "loss": 1.0466630935668946,
      "num_input_tokens_seen": 17809684032,
      "step": 62620,
      "train_runtime": 609991.0518,
      "train_tokens_per_second": 29196.632
    },
    {
      "epoch": 2.2159718889800466,
      "grad_norm": 1.546875,
      "learning_rate": 1.8553035349554565e-05,
      "loss": 1.0315136909484863,
      "num_input_tokens_seen": 17812522176,
      "step": 62630,
      "train_runtime": 610086.6069,
      "train_tokens_per_second": 29196.711
    },
    {
      "epoch": 2.2163257092437756,
      "grad_norm": 1.5859375,
      "learning_rate": 1.855175823437339e-05,
      "loss": 1.0362170219421387,
      "num_input_tokens_seen": 17815373440,
      "step": 62640,
      "train_runtime": 610184.453,
      "train_tokens_per_second": 29196.702
    },
    {
      "epoch": 2.216679529507504,
      "grad_norm": 1.578125,
      "learning_rate": 1.8550481382890086e-05,
      "loss": 1.0235048294067384,
      "num_input_tokens_seen": 17818197824,
      "step": 62650,
      "train_runtime": 610279.0236,
      "train_tokens_per_second": 29196.805
    },
    {
      "epoch": 2.217033349771233,
      "grad_norm": 1.515625,
      "learning_rate": 1.8549204795013926e-05,
      "loss": 1.050114631652832,
      "num_input_tokens_seen": 17821069632,
      "step": 62660,
      "train_runtime": 610377.323,
      "train_tokens_per_second": 29196.808
    },
    {
      "epoch": 2.2173871700349617,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8547928470654215e-05,
      "loss": 1.031122589111328,
      "num_input_tokens_seen": 17823951168,
      "step": 62670,
      "train_runtime": 610478.6477,
      "train_tokens_per_second": 29196.682
    },
    {
      "epoch": 2.2177409902986907,
      "grad_norm": 1.609375,
      "learning_rate": 1.854665240972031e-05,
      "loss": 1.0282096862792969,
      "num_input_tokens_seen": 17826824576,
      "step": 62680,
      "train_runtime": 610577.3496,
      "train_tokens_per_second": 29196.669
    },
    {
      "epoch": 2.2180948105624196,
      "grad_norm": 1.640625,
      "learning_rate": 1.8545376612121605e-05,
      "loss": 1.0419161796569825,
      "num_input_tokens_seen": 17829648384,
      "step": 62690,
      "train_runtime": 610675.06,
      "train_tokens_per_second": 29196.621
    },
    {
      "epoch": 2.218448630826148,
      "grad_norm": 1.625,
      "learning_rate": 1.854410107776754e-05,
      "loss": 1.0522695541381837,
      "num_input_tokens_seen": 17832494912,
      "step": 62700,
      "train_runtime": 610772.1332,
      "train_tokens_per_second": 29196.641
    },
    {
      "epoch": 2.218802451089877,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8542825806567598e-05,
      "loss": 1.0436452865600585,
      "num_input_tokens_seen": 17835344064,
      "step": 62710,
      "train_runtime": 610867.9468,
      "train_tokens_per_second": 29196.726
    },
    {
      "epoch": 2.2191562713536057,
      "grad_norm": 1.640625,
      "learning_rate": 1.854155079843131e-05,
      "loss": 1.049454116821289,
      "num_input_tokens_seen": 17838160576,
      "step": 62720,
      "train_runtime": 610963.2025,
      "train_tokens_per_second": 29196.784
    },
    {
      "epoch": 2.2195100916173347,
      "grad_norm": 1.640625,
      "learning_rate": 1.8540276053268246e-05,
      "loss": 1.027310562133789,
      "num_input_tokens_seen": 17840954304,
      "step": 62730,
      "train_runtime": 611059.5239,
      "train_tokens_per_second": 29196.754
    },
    {
      "epoch": 2.2198639118810632,
      "grad_norm": 1.609375,
      "learning_rate": 1.8539001570988016e-05,
      "loss": 1.033111000061035,
      "num_input_tokens_seen": 17843745280,
      "step": 62740,
      "train_runtime": 611154.5073,
      "train_tokens_per_second": 29196.783
    },
    {
      "epoch": 2.2202177321447922,
      "grad_norm": 1.59375,
      "learning_rate": 1.8537727351500283e-05,
      "loss": 1.0474322319030762,
      "num_input_tokens_seen": 17846575936,
      "step": 62750,
      "train_runtime": 611251.3814,
      "train_tokens_per_second": 29196.786
    },
    {
      "epoch": 2.2205715524085208,
      "grad_norm": 1.65625,
      "learning_rate": 1.8536453394714744e-05,
      "loss": 1.042524814605713,
      "num_input_tokens_seen": 17849360512,
      "step": 62760,
      "train_runtime": 611344.7343,
      "train_tokens_per_second": 29196.883
    },
    {
      "epoch": 2.2209253726722498,
      "grad_norm": 1.65625,
      "learning_rate": 1.8535179700541148e-05,
      "loss": 1.04327392578125,
      "num_input_tokens_seen": 17852226816,
      "step": 62770,
      "train_runtime": 611443.9077,
      "train_tokens_per_second": 29196.835
    },
    {
      "epoch": 2.2212791929359783,
      "grad_norm": 1.53125,
      "learning_rate": 1.853390626888928e-05,
      "loss": 1.0360421180725097,
      "num_input_tokens_seen": 17855051712,
      "step": 62780,
      "train_runtime": 611542.45,
      "train_tokens_per_second": 29196.749
    },
    {
      "epoch": 2.2216330131997073,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8532633099668977e-05,
      "loss": 1.0402423858642578,
      "num_input_tokens_seen": 17857865280,
      "step": 62790,
      "train_runtime": 611638.22,
      "train_tokens_per_second": 29196.778
    },
    {
      "epoch": 2.221986833463436,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8531360192790107e-05,
      "loss": 1.0318503379821777,
      "num_input_tokens_seen": 17860658048,
      "step": 62800,
      "train_runtime": 611730.8922,
      "train_tokens_per_second": 29196.92
    },
    {
      "epoch": 2.222340653727165,
      "grad_norm": 1.6640625,
      "learning_rate": 1.853008754816259e-05,
      "loss": 1.0265142440795898,
      "num_input_tokens_seen": 17863485696,
      "step": 62810,
      "train_runtime": 611827.2516,
      "train_tokens_per_second": 29196.944
    },
    {
      "epoch": 2.2226944739908934,
      "grad_norm": 1.6484375,
      "learning_rate": 1.852881516569639e-05,
      "loss": 1.0433298110961915,
      "num_input_tokens_seen": 17866356800,
      "step": 62820,
      "train_runtime": 611929.0099,
      "train_tokens_per_second": 29196.78
    },
    {
      "epoch": 2.2230482942546224,
      "grad_norm": 1.609375,
      "learning_rate": 1.8527543045301513e-05,
      "loss": 1.0384368896484375,
      "num_input_tokens_seen": 17869209344,
      "step": 62830,
      "train_runtime": 612023.7695,
      "train_tokens_per_second": 29196.921
    },
    {
      "epoch": 2.223402114518351,
      "grad_norm": 1.5625,
      "learning_rate": 1.8526271186888e-05,
      "loss": 1.0359642028808593,
      "num_input_tokens_seen": 17872057152,
      "step": 62840,
      "train_runtime": 612121.434,
      "train_tokens_per_second": 29196.914
    },
    {
      "epoch": 2.22375593478208,
      "grad_norm": 1.6171875,
      "learning_rate": 1.852499959036595e-05,
      "loss": 1.022753620147705,
      "num_input_tokens_seen": 17874869568,
      "step": 62850,
      "train_runtime": 612214.594,
      "train_tokens_per_second": 29197.065
    },
    {
      "epoch": 2.2241097550458084,
      "grad_norm": 1.578125,
      "learning_rate": 1.8523728255645494e-05,
      "loss": 1.0331228256225586,
      "num_input_tokens_seen": 17877708864,
      "step": 62860,
      "train_runtime": 612311.5853,
      "train_tokens_per_second": 29197.078
    },
    {
      "epoch": 2.2244635753095374,
      "grad_norm": 1.5234375,
      "learning_rate": 1.8522457182636814e-05,
      "loss": 1.0438164710998534,
      "num_input_tokens_seen": 17880557632,
      "step": 62870,
      "train_runtime": 612409.9366,
      "train_tokens_per_second": 29197.04
    },
    {
      "epoch": 2.2248173955732664,
      "grad_norm": 1.5234375,
      "learning_rate": 1.8521186371250122e-05,
      "loss": 1.0419047355651856,
      "num_input_tokens_seen": 17883430784,
      "step": 62880,
      "train_runtime": 612504.618,
      "train_tokens_per_second": 29197.218
    },
    {
      "epoch": 2.225171215836995,
      "grad_norm": 1.578125,
      "learning_rate": 1.851991582139569e-05,
      "loss": 1.058720016479492,
      "num_input_tokens_seen": 17886279104,
      "step": 62890,
      "train_runtime": 612598.5522,
      "train_tokens_per_second": 29197.39
    },
    {
      "epoch": 2.225525036100724,
      "grad_norm": 1.546875,
      "learning_rate": 1.8518645532983816e-05,
      "loss": 1.035905647277832,
      "num_input_tokens_seen": 17889097344,
      "step": 62900,
      "train_runtime": 612694.7356,
      "train_tokens_per_second": 29197.407
    },
    {
      "epoch": 2.2258788563644525,
      "grad_norm": 1.59375,
      "learning_rate": 1.851737550592486e-05,
      "loss": 1.0216590881347656,
      "num_input_tokens_seen": 17891929792,
      "step": 62910,
      "train_runtime": 612791.0316,
      "train_tokens_per_second": 29197.441
    },
    {
      "epoch": 2.2262326766281815,
      "grad_norm": 1.5078125,
      "learning_rate": 1.8516105740129215e-05,
      "loss": 1.0440673828125,
      "num_input_tokens_seen": 17894842304,
      "step": 62920,
      "train_runtime": 612891.5579,
      "train_tokens_per_second": 29197.404
    },
    {
      "epoch": 2.22658649689191,
      "grad_norm": 1.59375,
      "learning_rate": 1.8514836235507305e-05,
      "loss": 1.057785701751709,
      "num_input_tokens_seen": 17897694336,
      "step": 62930,
      "train_runtime": 612988.9752,
      "train_tokens_per_second": 29197.416
    },
    {
      "epoch": 2.226940317155639,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8513566991969618e-05,
      "loss": 1.0113880157470703,
      "num_input_tokens_seen": 17900512064,
      "step": 62940,
      "train_runtime": 613084.3956,
      "train_tokens_per_second": 29197.468
    },
    {
      "epoch": 2.2272941374193675,
      "grad_norm": 1.65625,
      "learning_rate": 1.851229800942668e-05,
      "loss": 1.052680778503418,
      "num_input_tokens_seen": 17903365056,
      "step": 62950,
      "train_runtime": 613179.793,
      "train_tokens_per_second": 29197.578
    },
    {
      "epoch": 2.2276479576830965,
      "grad_norm": 1.6171875,
      "learning_rate": 1.851102928778905e-05,
      "loss": 1.0455453872680665,
      "num_input_tokens_seen": 17906207488,
      "step": 62960,
      "train_runtime": 613276.3994,
      "train_tokens_per_second": 29197.614
    },
    {
      "epoch": 2.228001777946825,
      "grad_norm": 1.703125,
      "learning_rate": 1.8509760826967337e-05,
      "loss": 1.0478303909301758,
      "num_input_tokens_seen": 17909064768,
      "step": 62970,
      "train_runtime": 613374.6259,
      "train_tokens_per_second": 29197.596
    },
    {
      "epoch": 2.228355598210554,
      "grad_norm": 1.6328125,
      "learning_rate": 1.850849262687219e-05,
      "loss": 1.0386860847473145,
      "num_input_tokens_seen": 17911911680,
      "step": 62980,
      "train_runtime": 613469.3414,
      "train_tokens_per_second": 29197.729
    },
    {
      "epoch": 2.2287094184742826,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8507224687414308e-05,
      "loss": 1.0417236328125,
      "num_input_tokens_seen": 17914744320,
      "step": 62990,
      "train_runtime": 613566.0129,
      "train_tokens_per_second": 29197.746
    },
    {
      "epoch": 2.2290632387380116,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8505957008504415e-05,
      "loss": 1.0322514533996583,
      "num_input_tokens_seen": 17917577600,
      "step": 63000,
      "train_runtime": 613660.418,
      "train_tokens_per_second": 29197.871
    },
    {
      "epoch": 2.22941705900174,
      "grad_norm": 1.546875,
      "learning_rate": 1.8504689590053308e-05,
      "loss": 1.038742733001709,
      "num_input_tokens_seen": 17920431744,
      "step": 63010,
      "train_runtime": 613760.1458,
      "train_tokens_per_second": 29197.777
    },
    {
      "epoch": 2.229770879265469,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8503422431971794e-05,
      "loss": 1.0285913467407226,
      "num_input_tokens_seen": 17923229248,
      "step": 63020,
      "train_runtime": 613857.141,
      "train_tokens_per_second": 29197.721
    },
    {
      "epoch": 2.230124699529198,
      "grad_norm": 1.515625,
      "learning_rate": 1.850215553417074e-05,
      "loss": 1.0401494026184082,
      "num_input_tokens_seen": 17926048128,
      "step": 63030,
      "train_runtime": 613951.9278,
      "train_tokens_per_second": 29197.804
    },
    {
      "epoch": 2.2304785197929267,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8500888896561066e-05,
      "loss": 1.0449932098388672,
      "num_input_tokens_seen": 17928859264,
      "step": 63040,
      "train_runtime": 614048.814,
      "train_tokens_per_second": 29197.775
    },
    {
      "epoch": 2.2308323400566556,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8499622519053708e-05,
      "loss": 1.0341005325317383,
      "num_input_tokens_seen": 17931673024,
      "step": 63050,
      "train_runtime": 614144.8377,
      "train_tokens_per_second": 29197.792
    },
    {
      "epoch": 2.231186160320384,
      "grad_norm": 1.59375,
      "learning_rate": 1.8498356401559667e-05,
      "loss": 1.0336530685424805,
      "num_input_tokens_seen": 17934523840,
      "step": 63060,
      "train_runtime": 614242.1178,
      "train_tokens_per_second": 29197.809
    },
    {
      "epoch": 2.231539980584113,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8497090543989972e-05,
      "loss": 1.0366477966308594,
      "num_input_tokens_seen": 17937379968,
      "step": 63070,
      "train_runtime": 614338.7863,
      "train_tokens_per_second": 29197.863
    },
    {
      "epoch": 2.2318938008478417,
      "grad_norm": 1.703125,
      "learning_rate": 1.8495824946255704e-05,
      "loss": 1.0416396141052247,
      "num_input_tokens_seen": 17940220032,
      "step": 63080,
      "train_runtime": 614435.3803,
      "train_tokens_per_second": 29197.896
    },
    {
      "epoch": 2.2322476211115707,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8494559608267985e-05,
      "loss": 1.0371956825256348,
      "num_input_tokens_seen": 17943035136,
      "step": 63090,
      "train_runtime": 614530.7638,
      "train_tokens_per_second": 29197.944
    },
    {
      "epoch": 2.2326014413752993,
      "grad_norm": 1.578125,
      "learning_rate": 1.8493294529937976e-05,
      "loss": 1.0345140457153321,
      "num_input_tokens_seen": 17945947456,
      "step": 63100,
      "train_runtime": 614633.3577,
      "train_tokens_per_second": 29197.809
    },
    {
      "epoch": 2.2329552616390282,
      "grad_norm": 1.59375,
      "learning_rate": 1.849202971117688e-05,
      "loss": 1.032081413269043,
      "num_input_tokens_seen": 17948796544,
      "step": 63110,
      "train_runtime": 614729.9876,
      "train_tokens_per_second": 29197.854
    },
    {
      "epoch": 2.233309081902757,
      "grad_norm": 1.59375,
      "learning_rate": 1.8490765151895952e-05,
      "loss": 1.0353840827941894,
      "num_input_tokens_seen": 17951693056,
      "step": 63120,
      "train_runtime": 614828.2723,
      "train_tokens_per_second": 29197.898
    },
    {
      "epoch": 2.2336629021664858,
      "grad_norm": 1.578125,
      "learning_rate": 1.8489500852006484e-05,
      "loss": 1.0363322257995606,
      "num_input_tokens_seen": 17954511552,
      "step": 63130,
      "train_runtime": 614925.0674,
      "train_tokens_per_second": 29197.885
    },
    {
      "epoch": 2.2340167224302143,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8488236811419795e-05,
      "loss": 1.0454951286315919,
      "num_input_tokens_seen": 17957332800,
      "step": 63140,
      "train_runtime": 615018.2598,
      "train_tokens_per_second": 29198.048
    },
    {
      "epoch": 2.2343705426939433,
      "grad_norm": 1.53125,
      "learning_rate": 1.8486973030047278e-05,
      "loss": 1.0266526222229004,
      "num_input_tokens_seen": 17960199232,
      "step": 63150,
      "train_runtime": 615116.8471,
      "train_tokens_per_second": 29198.028
    },
    {
      "epoch": 2.234724362957672,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8485709507800337e-05,
      "loss": 1.0463420867919921,
      "num_input_tokens_seen": 17963042176,
      "step": 63160,
      "train_runtime": 615215.1078,
      "train_tokens_per_second": 29197.986
    },
    {
      "epoch": 2.235078183221401,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8484446244590438e-05,
      "loss": 1.0274453163146973,
      "num_input_tokens_seen": 17965905216,
      "step": 63170,
      "train_runtime": 615317.5954,
      "train_tokens_per_second": 29197.776
    },
    {
      "epoch": 2.23543200348513,
      "grad_norm": 1.6171875,
      "learning_rate": 1.848318324032909e-05,
      "loss": 1.0283151626586915,
      "num_input_tokens_seen": 17968737600,
      "step": 63180,
      "train_runtime": 615415.1261,
      "train_tokens_per_second": 29197.751
    },
    {
      "epoch": 2.2357858237488584,
      "grad_norm": 1.6640625,
      "learning_rate": 1.8481920494927827e-05,
      "loss": 1.0407233238220215,
      "num_input_tokens_seen": 17971527744,
      "step": 63190,
      "train_runtime": 615510.1866,
      "train_tokens_per_second": 29197.775
    },
    {
      "epoch": 2.2361396440125874,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8480658008298242e-05,
      "loss": 1.0547028541564942,
      "num_input_tokens_seen": 17974361408,
      "step": 63200,
      "train_runtime": 615610.6637,
      "train_tokens_per_second": 29197.612
    },
    {
      "epoch": 2.236493464276316,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8479395780351963e-05,
      "loss": 1.0347110748291015,
      "num_input_tokens_seen": 17977231808,
      "step": 63210,
      "train_runtime": 615708.1187,
      "train_tokens_per_second": 29197.653
    },
    {
      "epoch": 2.236847284540045,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8478133811000662e-05,
      "loss": 1.0292227745056153,
      "num_input_tokens_seen": 17980107904,
      "step": 63220,
      "train_runtime": 615806.2609,
      "train_tokens_per_second": 29197.67
    },
    {
      "epoch": 2.2372011048037734,
      "grad_norm": 1.578125,
      "learning_rate": 1.8476872100156055e-05,
      "loss": 1.0385347366333009,
      "num_input_tokens_seen": 17982972992,
      "step": 63230,
      "train_runtime": 615902.8533,
      "train_tokens_per_second": 29197.743
    },
    {
      "epoch": 2.2375549250675024,
      "grad_norm": 1.59375,
      "learning_rate": 1.8475610647729893e-05,
      "loss": 1.0353388786315918,
      "num_input_tokens_seen": 17985832064,
      "step": 63240,
      "train_runtime": 616002.0782,
      "train_tokens_per_second": 29197.681
    },
    {
      "epoch": 2.237908745331231,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8474349453633978e-05,
      "loss": 1.0347203254699706,
      "num_input_tokens_seen": 17988681024,
      "step": 63250,
      "train_runtime": 616100.4836,
      "train_tokens_per_second": 29197.641
    },
    {
      "epoch": 2.23826256559496,
      "grad_norm": 1.578125,
      "learning_rate": 1.8473088517780156e-05,
      "loss": 1.0321243286132813,
      "num_input_tokens_seen": 17991489792,
      "step": 63260,
      "train_runtime": 616195.2093,
      "train_tokens_per_second": 29197.711
    },
    {
      "epoch": 2.2386163858586885,
      "grad_norm": 1.671875,
      "learning_rate": 1.84718278400803e-05,
      "loss": 1.0438150405883788,
      "num_input_tokens_seen": 17994283456,
      "step": 63270,
      "train_runtime": 616289.3249,
      "train_tokens_per_second": 29197.785
    },
    {
      "epoch": 2.2389702061224175,
      "grad_norm": 1.578125,
      "learning_rate": 1.847056742044634e-05,
      "loss": 1.023946475982666,
      "num_input_tokens_seen": 17997138560,
      "step": 63280,
      "train_runtime": 616387.5643,
      "train_tokens_per_second": 29197.764
    },
    {
      "epoch": 2.239324026386146,
      "grad_norm": 1.6484375,
      "learning_rate": 1.8469307258790238e-05,
      "loss": 1.038642978668213,
      "num_input_tokens_seen": 18000014592,
      "step": 63290,
      "train_runtime": 616489.217,
      "train_tokens_per_second": 29197.615
    },
    {
      "epoch": 2.239677846649875,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8468047355024013e-05,
      "loss": 1.0281539916992188,
      "num_input_tokens_seen": 18002834944,
      "step": 63300,
      "train_runtime": 616585.5937,
      "train_tokens_per_second": 29197.625
    },
    {
      "epoch": 2.2400316669136036,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8466787709059705e-05,
      "loss": 1.0520421981811523,
      "num_input_tokens_seen": 18005689024,
      "step": 63310,
      "train_runtime": 616684.292,
      "train_tokens_per_second": 29197.58
    },
    {
      "epoch": 2.2403854871773325,
      "grad_norm": 1.625,
      "learning_rate": 1.846552832080941e-05,
      "loss": 1.0466800689697267,
      "num_input_tokens_seen": 18008566912,
      "step": 63320,
      "train_runtime": 616785.8556,
      "train_tokens_per_second": 29197.438
    },
    {
      "epoch": 2.240739307441061,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8464269190185267e-05,
      "loss": 1.0350932121276855,
      "num_input_tokens_seen": 18011385536,
      "step": 63330,
      "train_runtime": 616881.4109,
      "train_tokens_per_second": 29197.485
    },
    {
      "epoch": 2.24109312770479,
      "grad_norm": 1.65625,
      "learning_rate": 1.8463010317099445e-05,
      "loss": 1.0414432525634765,
      "num_input_tokens_seen": 18014273600,
      "step": 63340,
      "train_runtime": 616980.6267,
      "train_tokens_per_second": 29197.47
    },
    {
      "epoch": 2.2414469479685186,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8461751701464168e-05,
      "loss": 1.0393269538879395,
      "num_input_tokens_seen": 18017111104,
      "step": 63350,
      "train_runtime": 617075.0436,
      "train_tokens_per_second": 29197.601
    },
    {
      "epoch": 2.2418007682322476,
      "grad_norm": 1.578125,
      "learning_rate": 1.8460493343191697e-05,
      "loss": 1.0393078804016114,
      "num_input_tokens_seen": 18019982592,
      "step": 63360,
      "train_runtime": 617174.3325,
      "train_tokens_per_second": 29197.557
    },
    {
      "epoch": 2.2421545884959766,
      "grad_norm": 1.578125,
      "learning_rate": 1.8459235242194336e-05,
      "loss": 1.052144718170166,
      "num_input_tokens_seen": 18022809728,
      "step": 63370,
      "train_runtime": 617271.1555,
      "train_tokens_per_second": 29197.557
    },
    {
      "epoch": 2.242508408759705,
      "grad_norm": 1.578125,
      "learning_rate": 1.8457977398384422e-05,
      "loss": 1.0257415771484375,
      "num_input_tokens_seen": 18025575296,
      "step": 63380,
      "train_runtime": 617366.1053,
      "train_tokens_per_second": 29197.546
    },
    {
      "epoch": 2.242862229023434,
      "grad_norm": 1.5,
      "learning_rate": 1.8456719811674344e-05,
      "loss": 1.0248476028442384,
      "num_input_tokens_seen": 18028389056,
      "step": 63390,
      "train_runtime": 617460.8339,
      "train_tokens_per_second": 29197.624
    },
    {
      "epoch": 2.2432160492871627,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8455462481976532e-05,
      "loss": 1.0307409286499023,
      "num_input_tokens_seen": 18031265984,
      "step": 63400,
      "train_runtime": 617558.3876,
      "train_tokens_per_second": 29197.67
    },
    {
      "epoch": 2.2435698695508917,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8454205409203457e-05,
      "loss": 1.0327302932739257,
      "num_input_tokens_seen": 18034121600,
      "step": 63410,
      "train_runtime": 617659.818,
      "train_tokens_per_second": 29197.498
    },
    {
      "epoch": 2.24392368981462,
      "grad_norm": 1.609375,
      "learning_rate": 1.8452948593267625e-05,
      "loss": 1.0383750915527343,
      "num_input_tokens_seen": 18037002880,
      "step": 63420,
      "train_runtime": 617760.0095,
      "train_tokens_per_second": 29197.427
    },
    {
      "epoch": 2.244277510078349,
      "grad_norm": 1.5078125,
      "learning_rate": 1.845169203408159e-05,
      "loss": 1.026041603088379,
      "num_input_tokens_seen": 18039850752,
      "step": 63430,
      "train_runtime": 617857.5266,
      "train_tokens_per_second": 29197.428
    },
    {
      "epoch": 2.2446313303420777,
      "grad_norm": 1.6015625,
      "learning_rate": 1.845043573155795e-05,
      "loss": 1.0251968383789063,
      "num_input_tokens_seen": 18042645056,
      "step": 63440,
      "train_runtime": 617954.821,
      "train_tokens_per_second": 29197.353
    },
    {
      "epoch": 2.2449851506058067,
      "grad_norm": 1.671875,
      "learning_rate": 1.8449179685609337e-05,
      "loss": 1.0266098022460937,
      "num_input_tokens_seen": 18045479104,
      "step": 63450,
      "train_runtime": 618049.4714,
      "train_tokens_per_second": 29197.467
    },
    {
      "epoch": 2.2453389708695353,
      "grad_norm": 1.5625,
      "learning_rate": 1.8447923896148434e-05,
      "loss": 1.0275009155273438,
      "num_input_tokens_seen": 18048314304,
      "step": 63460,
      "train_runtime": 618145.5556,
      "train_tokens_per_second": 29197.515
    },
    {
      "epoch": 2.2456927911332643,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8446668363087957e-05,
      "loss": 1.0360755920410156,
      "num_input_tokens_seen": 18051161152,
      "step": 63470,
      "train_runtime": 618245.0398,
      "train_tokens_per_second": 29197.422
    },
    {
      "epoch": 2.246046611396993,
      "grad_norm": 1.546875,
      "learning_rate": 1.8445413086340664e-05,
      "loss": 1.0508489608764648,
      "num_input_tokens_seen": 18054002368,
      "step": 63480,
      "train_runtime": 618341.8015,
      "train_tokens_per_second": 29197.448
    },
    {
      "epoch": 2.246400431660722,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8444158065819366e-05,
      "loss": 1.0261276245117188,
      "num_input_tokens_seen": 18056809152,
      "step": 63490,
      "train_runtime": 618438.0892,
      "train_tokens_per_second": 29197.44
    },
    {
      "epoch": 2.2467542519244503,
      "grad_norm": 1.546875,
      "learning_rate": 1.8442903301436902e-05,
      "loss": 1.0409505844116211,
      "num_input_tokens_seen": 18059634944,
      "step": 63500,
      "train_runtime": 618536.8982,
      "train_tokens_per_second": 29197.345
    },
    {
      "epoch": 2.2471080721881793,
      "grad_norm": 1.578125,
      "learning_rate": 1.844164879310616e-05,
      "loss": 1.0414392471313476,
      "num_input_tokens_seen": 18062452928,
      "step": 63510,
      "train_runtime": 618632.174,
      "train_tokens_per_second": 29197.403
    },
    {
      "epoch": 2.2474618924519083,
      "grad_norm": 1.5703125,
      "learning_rate": 1.844039454074006e-05,
      "loss": 1.0403059005737305,
      "num_input_tokens_seen": 18065313152,
      "step": 63520,
      "train_runtime": 618730.1091,
      "train_tokens_per_second": 29197.404
    },
    {
      "epoch": 2.247815712715637,
      "grad_norm": 1.6953125,
      "learning_rate": 1.8439140544251578e-05,
      "loss": 1.031533145904541,
      "num_input_tokens_seen": 18068128896,
      "step": 63530,
      "train_runtime": 618827.9646,
      "train_tokens_per_second": 29197.337
    },
    {
      "epoch": 2.248169532979366,
      "grad_norm": 1.59375,
      "learning_rate": 1.8437886803553726e-05,
      "loss": 1.0483896255493164,
      "num_input_tokens_seen": 18070927296,
      "step": 63540,
      "train_runtime": 618919.3138,
      "train_tokens_per_second": 29197.549
    },
    {
      "epoch": 2.2485233532430944,
      "grad_norm": 1.53125,
      "learning_rate": 1.843663331855955e-05,
      "loss": 1.0343040466308593,
      "num_input_tokens_seen": 18073789568,
      "step": 63550,
      "train_runtime": 619019.5699,
      "train_tokens_per_second": 29197.445
    },
    {
      "epoch": 2.2488771735068234,
      "grad_norm": 1.5625,
      "learning_rate": 1.8435380089182142e-05,
      "loss": 1.0425338745117188,
      "num_input_tokens_seen": 18076627072,
      "step": 63560,
      "train_runtime": 619117.8813,
      "train_tokens_per_second": 29197.391
    },
    {
      "epoch": 2.249230993770552,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8434127115334636e-05,
      "loss": 1.0201240539550782,
      "num_input_tokens_seen": 18079494784,
      "step": 63570,
      "train_runtime": 619216.5061,
      "train_tokens_per_second": 29197.372
    },
    {
      "epoch": 2.249584814034281,
      "grad_norm": 1.578125,
      "learning_rate": 1.843287439693021e-05,
      "loss": 1.0294544219970703,
      "num_input_tokens_seen": 18082270528,
      "step": 63580,
      "train_runtime": 619309.588,
      "train_tokens_per_second": 29197.466
    },
    {
      "epoch": 2.2499386342980094,
      "grad_norm": 1.625,
      "learning_rate": 1.8431621933882087e-05,
      "loss": 1.0418066024780273,
      "num_input_tokens_seen": 18085124736,
      "step": 63590,
      "train_runtime": 619407.9635,
      "train_tokens_per_second": 29197.437
    },
    {
      "epoch": 2.2502924545617384,
      "grad_norm": 1.65625,
      "learning_rate": 1.8430369726103514e-05,
      "loss": 1.0399689674377441,
      "num_input_tokens_seen": 18087948160,
      "step": 63600,
      "train_runtime": 619504.989,
      "train_tokens_per_second": 29197.421
    },
    {
      "epoch": 2.250646274825467,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8429117773507797e-05,
      "loss": 1.0339451789855958,
      "num_input_tokens_seen": 18090803840,
      "step": 63610,
      "train_runtime": 619602.3771,
      "train_tokens_per_second": 29197.441
    },
    {
      "epoch": 2.251000095089196,
      "grad_norm": 1.625,
      "learning_rate": 1.8427866076008265e-05,
      "loss": 1.0347336769104003,
      "num_input_tokens_seen": 18093636864,
      "step": 63620,
      "train_runtime": 619697.2606,
      "train_tokens_per_second": 29197.542
    },
    {
      "epoch": 2.2513539153529245,
      "grad_norm": 1.6640625,
      "learning_rate": 1.842661463351832e-05,
      "loss": 1.03631591796875,
      "num_input_tokens_seen": 18096458176,
      "step": 63630,
      "train_runtime": 619793.2649,
      "train_tokens_per_second": 29197.572
    },
    {
      "epoch": 2.2517077356166535,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8425363445951368e-05,
      "loss": 1.0282306671142578,
      "num_input_tokens_seen": 18099305088,
      "step": 63640,
      "train_runtime": 619891.7065,
      "train_tokens_per_second": 29197.527
    },
    {
      "epoch": 2.252061555880382,
      "grad_norm": 1.5546875,
      "learning_rate": 1.842411251322088e-05,
      "loss": 1.0304922103881835,
      "num_input_tokens_seen": 18102157248,
      "step": 63650,
      "train_runtime": 619991.0008,
      "train_tokens_per_second": 29197.452
    },
    {
      "epoch": 2.252415376144111,
      "grad_norm": 1.515625,
      "learning_rate": 1.8422861835240357e-05,
      "loss": 1.0515201568603516,
      "num_input_tokens_seen": 18105021696,
      "step": 63660,
      "train_runtime": 620087.9779,
      "train_tokens_per_second": 29197.505
    },
    {
      "epoch": 2.25276919640784,
      "grad_norm": 1.578125,
      "learning_rate": 1.842161141192335e-05,
      "loss": 1.0258378982543945,
      "num_input_tokens_seen": 18107910592,
      "step": 63670,
      "train_runtime": 620187.376,
      "train_tokens_per_second": 29197.483
    },
    {
      "epoch": 2.2531230166715686,
      "grad_norm": 1.625,
      "learning_rate": 1.8420361243183444e-05,
      "loss": 1.0289522171020509,
      "num_input_tokens_seen": 18110765696,
      "step": 63680,
      "train_runtime": 620283.2911,
      "train_tokens_per_second": 29197.571
    },
    {
      "epoch": 2.253476836935297,
      "grad_norm": 1.5234375,
      "learning_rate": 1.841911132893427e-05,
      "loss": 1.0291211128234863,
      "num_input_tokens_seen": 18113634752,
      "step": 63690,
      "train_runtime": 620382.598,
      "train_tokens_per_second": 29197.522
    },
    {
      "epoch": 2.253830657199026,
      "grad_norm": 1.6171875,
      "learning_rate": 1.841786166908949e-05,
      "loss": 1.0349963188171387,
      "num_input_tokens_seen": 18116427968,
      "step": 63700,
      "train_runtime": 620475.9732,
      "train_tokens_per_second": 29197.63
    },
    {
      "epoch": 2.254184477462755,
      "grad_norm": 1.609375,
      "learning_rate": 1.841661226356282e-05,
      "loss": 1.0285568237304688,
      "num_input_tokens_seen": 18119236352,
      "step": 63710,
      "train_runtime": 620571.5672,
      "train_tokens_per_second": 29197.658
    },
    {
      "epoch": 2.2545382977264836,
      "grad_norm": 1.5078125,
      "learning_rate": 1.8415363112268012e-05,
      "loss": 1.0465338706970215,
      "num_input_tokens_seen": 18122137728,
      "step": 63720,
      "train_runtime": 620672.4157,
      "train_tokens_per_second": 29197.588
    },
    {
      "epoch": 2.2548921179902126,
      "grad_norm": 1.5859375,
      "learning_rate": 1.841411421511886e-05,
      "loss": 1.0396684646606444,
      "num_input_tokens_seen": 18124975104,
      "step": 63730,
      "train_runtime": 620768.3078,
      "train_tokens_per_second": 29197.649
    },
    {
      "epoch": 2.255245938253941,
      "grad_norm": 1.546875,
      "learning_rate": 1.841286557202919e-05,
      "loss": 1.0462173461914062,
      "num_input_tokens_seen": 18127781952,
      "step": 63740,
      "train_runtime": 620863.985,
      "train_tokens_per_second": 29197.67
    },
    {
      "epoch": 2.25559975851767,
      "grad_norm": 1.5859375,
      "learning_rate": 1.841161718291288e-05,
      "loss": 1.0254095077514649,
      "num_input_tokens_seen": 18130655552,
      "step": 63750,
      "train_runtime": 620962.9387,
      "train_tokens_per_second": 29197.645
    },
    {
      "epoch": 2.2559535787813987,
      "grad_norm": 1.546875,
      "learning_rate": 1.8410369047683846e-05,
      "loss": 1.0365596771240235,
      "num_input_tokens_seen": 18133477952,
      "step": 63760,
      "train_runtime": 621059.6241,
      "train_tokens_per_second": 29197.644
    },
    {
      "epoch": 2.2563073990451277,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8409121166256037e-05,
      "loss": 1.0397085189819335,
      "num_input_tokens_seen": 18136394880,
      "step": 63770,
      "train_runtime": 621159.6448,
      "train_tokens_per_second": 29197.639
    },
    {
      "epoch": 2.256661219308856,
      "grad_norm": 1.65625,
      "learning_rate": 1.840787353854346e-05,
      "loss": 1.039761734008789,
      "num_input_tokens_seen": 18139277696,
      "step": 63780,
      "train_runtime": 621257.583,
      "train_tokens_per_second": 29197.676
    },
    {
      "epoch": 2.257015039572585,
      "grad_norm": 1.6171875,
      "learning_rate": 1.840662616446015e-05,
      "loss": 1.0228913307189942,
      "num_input_tokens_seen": 18142099264,
      "step": 63790,
      "train_runtime": 621351.5049,
      "train_tokens_per_second": 29197.804
    },
    {
      "epoch": 2.2573688598363137,
      "grad_norm": 1.578125,
      "learning_rate": 1.8405379043920177e-05,
      "loss": 1.0467246055603028,
      "num_input_tokens_seen": 18144960192,
      "step": 63800,
      "train_runtime": 621449.8475,
      "train_tokens_per_second": 29197.787
    },
    {
      "epoch": 2.2577226801000427,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8404132176837667e-05,
      "loss": 1.0339645385742187,
      "num_input_tokens_seen": 18147823744,
      "step": 63810,
      "train_runtime": 621546.1001,
      "train_tokens_per_second": 29197.872
    },
    {
      "epoch": 2.2580765003637713,
      "grad_norm": 1.578125,
      "learning_rate": 1.840288556312678e-05,
      "loss": 1.03076114654541,
      "num_input_tokens_seen": 18150667328,
      "step": 63820,
      "train_runtime": 621644.965,
      "train_tokens_per_second": 29197.803
    },
    {
      "epoch": 2.2584303206275003,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8401639202701713e-05,
      "loss": 1.0513643264770507,
      "num_input_tokens_seen": 18153507776,
      "step": 63830,
      "train_runtime": 621742.7308,
      "train_tokens_per_second": 29197.78
    },
    {
      "epoch": 2.258784140891229,
      "grad_norm": 1.625,
      "learning_rate": 1.8400393095476712e-05,
      "loss": 1.0398809432983398,
      "num_input_tokens_seen": 18156356992,
      "step": 63840,
      "train_runtime": 621839.3175,
      "train_tokens_per_second": 29197.827
    },
    {
      "epoch": 2.259137961154958,
      "grad_norm": 1.609375,
      "learning_rate": 1.8399147241366053e-05,
      "loss": 1.0168328285217285,
      "num_input_tokens_seen": 18159206912,
      "step": 63850,
      "train_runtime": 621937.5671,
      "train_tokens_per_second": 29197.797
    },
    {
      "epoch": 2.259491781418687,
      "grad_norm": 1.609375,
      "learning_rate": 1.8397901640284058e-05,
      "loss": 1.037716007232666,
      "num_input_tokens_seen": 18162015296,
      "step": 63860,
      "train_runtime": 622032.2623,
      "train_tokens_per_second": 29197.867
    },
    {
      "epoch": 2.2598456016824153,
      "grad_norm": 1.625,
      "learning_rate": 1.8396656292145095e-05,
      "loss": 1.0450238227844237,
      "num_input_tokens_seen": 18164865728,
      "step": 63870,
      "train_runtime": 622129.6627,
      "train_tokens_per_second": 29197.878
    },
    {
      "epoch": 2.2601994219461443,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8395411196863562e-05,
      "loss": 1.0361207962036132,
      "num_input_tokens_seen": 18167747456,
      "step": 63880,
      "train_runtime": 622229.7243,
      "train_tokens_per_second": 29197.814
    },
    {
      "epoch": 2.260553242209873,
      "grad_norm": 1.5546875,
      "learning_rate": 1.839416635435391e-05,
      "loss": 1.0308193206787108,
      "num_input_tokens_seen": 18170612736,
      "step": 63890,
      "train_runtime": 622328.2918,
      "train_tokens_per_second": 29197.793
    },
    {
      "epoch": 2.260907062473602,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8392921764530616e-05,
      "loss": 1.0465408325195313,
      "num_input_tokens_seen": 18173508032,
      "step": 63900,
      "train_runtime": 622426.328,
      "train_tokens_per_second": 29197.846
    },
    {
      "epoch": 2.2612608827373304,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8391677427308206e-05,
      "loss": 1.0435256958007812,
      "num_input_tokens_seen": 18176356672,
      "step": 63910,
      "train_runtime": 622523.5507,
      "train_tokens_per_second": 29197.862
    },
    {
      "epoch": 2.2616147030010594,
      "grad_norm": 1.578125,
      "learning_rate": 1.8390433342601252e-05,
      "loss": 1.028120994567871,
      "num_input_tokens_seen": 18179242432,
      "step": 63920,
      "train_runtime": 622622.3606,
      "train_tokens_per_second": 29197.863
    },
    {
      "epoch": 2.261968523264788,
      "grad_norm": 1.5625,
      "learning_rate": 1.838918951032435e-05,
      "loss": 1.0301898002624512,
      "num_input_tokens_seen": 18182086272,
      "step": 63930,
      "train_runtime": 622723.7012,
      "train_tokens_per_second": 29197.678
    },
    {
      "epoch": 2.262322343528517,
      "grad_norm": 1.625,
      "learning_rate": 1.8387945930392157e-05,
      "loss": 1.0318767547607421,
      "num_input_tokens_seen": 18184978560,
      "step": 63940,
      "train_runtime": 622824.8443,
      "train_tokens_per_second": 29197.581
    },
    {
      "epoch": 2.2626761637922455,
      "grad_norm": 1.7265625,
      "learning_rate": 1.838670260271935e-05,
      "loss": 1.028726577758789,
      "num_input_tokens_seen": 18187870912,
      "step": 63950,
      "train_runtime": 622924.2773,
      "train_tokens_per_second": 29197.563
    },
    {
      "epoch": 2.2630299840559744,
      "grad_norm": 1.625,
      "learning_rate": 1.8385459527220665e-05,
      "loss": 1.0095151901245116,
      "num_input_tokens_seen": 18190690944,
      "step": 63960,
      "train_runtime": 623022.849,
      "train_tokens_per_second": 29197.47
    },
    {
      "epoch": 2.263383804319703,
      "grad_norm": 1.65625,
      "learning_rate": 1.838421670381086e-05,
      "loss": 1.0391574859619142,
      "num_input_tokens_seen": 18193527552,
      "step": 63970,
      "train_runtime": 623118.6856,
      "train_tokens_per_second": 29197.532
    },
    {
      "epoch": 2.263737624583432,
      "grad_norm": 1.6015625,
      "learning_rate": 1.838297413240475e-05,
      "loss": 1.0406129837036133,
      "num_input_tokens_seen": 18196320960,
      "step": 63980,
      "train_runtime": 623214.4762,
      "train_tokens_per_second": 29197.526
    },
    {
      "epoch": 2.2640914448471605,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8381731812917183e-05,
      "loss": 1.0221141815185546,
      "num_input_tokens_seen": 18199177536,
      "step": 63990,
      "train_runtime": 623311.4231,
      "train_tokens_per_second": 29197.568
    },
    {
      "epoch": 2.2644452651108895,
      "grad_norm": 1.546875,
      "learning_rate": 1.8380489745263044e-05,
      "loss": 1.0434159278869628,
      "num_input_tokens_seen": 18202115584,
      "step": 64000,
      "train_runtime": 623415.0751,
      "train_tokens_per_second": 29197.426
    },
    {
      "epoch": 2.2647990853746185,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8379247929357262e-05,
      "loss": 1.046522331237793,
      "num_input_tokens_seen": 18204937984,
      "step": 64010,
      "train_runtime": 623511.2073,
      "train_tokens_per_second": 29197.451
    },
    {
      "epoch": 2.265152905638347,
      "grad_norm": 1.625,
      "learning_rate": 1.8378006365114808e-05,
      "loss": 1.020125675201416,
      "num_input_tokens_seen": 18207782784,
      "step": 64020,
      "train_runtime": 623610.175,
      "train_tokens_per_second": 29197.379
    },
    {
      "epoch": 2.2655067259020756,
      "grad_norm": 1.515625,
      "learning_rate": 1.8376765052450693e-05,
      "loss": 1.0354833602905273,
      "num_input_tokens_seen": 18210612032,
      "step": 64030,
      "train_runtime": 623706.0717,
      "train_tokens_per_second": 29197.426
    },
    {
      "epoch": 2.2658605461658046,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8375523991279958e-05,
      "loss": 1.0354298591613769,
      "num_input_tokens_seen": 18213459136,
      "step": 64040,
      "train_runtime": 623803.9096,
      "train_tokens_per_second": 29197.411
    },
    {
      "epoch": 2.2662143664295336,
      "grad_norm": 1.6640625,
      "learning_rate": 1.83742831815177e-05,
      "loss": 1.0357027053833008,
      "num_input_tokens_seen": 18216316096,
      "step": 64050,
      "train_runtime": 623901.6238,
      "train_tokens_per_second": 29197.417
    },
    {
      "epoch": 2.266568186693262,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8373042623079042e-05,
      "loss": 1.042828369140625,
      "num_input_tokens_seen": 18219144064,
      "step": 64060,
      "train_runtime": 623996.2964,
      "train_tokens_per_second": 29197.52
    },
    {
      "epoch": 2.266922006956991,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8371802315879157e-05,
      "loss": 1.0347795486450195,
      "num_input_tokens_seen": 18222026368,
      "step": 64070,
      "train_runtime": 624096.1725,
      "train_tokens_per_second": 29197.465
    },
    {
      "epoch": 2.2672758272207196,
      "grad_norm": 1.6015625,
      "learning_rate": 1.837056225983326e-05,
      "loss": 1.0481571197509765,
      "num_input_tokens_seen": 18224849856,
      "step": 64080,
      "train_runtime": 624192.9876,
      "train_tokens_per_second": 29197.46
    },
    {
      "epoch": 2.2676296474844486,
      "grad_norm": 1.59375,
      "learning_rate": 1.8369322454856595e-05,
      "loss": 1.0413642883300782,
      "num_input_tokens_seen": 18227699200,
      "step": 64090,
      "train_runtime": 624291.3457,
      "train_tokens_per_second": 29197.424
    },
    {
      "epoch": 2.267983467748177,
      "grad_norm": 1.625,
      "learning_rate": 1.8368082900864454e-05,
      "loss": 1.0392223358154298,
      "num_input_tokens_seen": 18230607296,
      "step": 64100,
      "train_runtime": 624391.8998,
      "train_tokens_per_second": 29197.38
    },
    {
      "epoch": 2.268337288011906,
      "grad_norm": 1.5625,
      "learning_rate": 1.8366843597772163e-05,
      "loss": 1.0338793754577638,
      "num_input_tokens_seen": 18233416512,
      "step": 64110,
      "train_runtime": 624486.4015,
      "train_tokens_per_second": 29197.46
    },
    {
      "epoch": 2.2686911082756347,
      "grad_norm": 1.5078125,
      "learning_rate": 1.8365604545495093e-05,
      "loss": 1.022924041748047,
      "num_input_tokens_seen": 18236270336,
      "step": 64120,
      "train_runtime": 624584.2321,
      "train_tokens_per_second": 29197.456
    },
    {
      "epoch": 2.2690449285393637,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8364365743948656e-05,
      "loss": 1.031276798248291,
      "num_input_tokens_seen": 18239149376,
      "step": 64130,
      "train_runtime": 624682.1929,
      "train_tokens_per_second": 29197.486
    },
    {
      "epoch": 2.2693987488030922,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8363127193048303e-05,
      "loss": 1.0460419654846191,
      "num_input_tokens_seen": 18241989056,
      "step": 64140,
      "train_runtime": 624779.7546,
      "train_tokens_per_second": 29197.471
    },
    {
      "epoch": 2.269752569066821,
      "grad_norm": 1.7265625,
      "learning_rate": 1.836188889270952e-05,
      "loss": 1.0462946891784668,
      "num_input_tokens_seen": 18244820672,
      "step": 64150,
      "train_runtime": 624878.6675,
      "train_tokens_per_second": 29197.381
    },
    {
      "epoch": 2.2701063893305498,
      "grad_norm": 1.6484375,
      "learning_rate": 1.8360650842847834e-05,
      "loss": 1.0404623031616211,
      "num_input_tokens_seen": 18247666816,
      "step": 64160,
      "train_runtime": 624978.3232,
      "train_tokens_per_second": 29197.28
    },
    {
      "epoch": 2.2704602095942787,
      "grad_norm": 1.578125,
      "learning_rate": 1.8359413043378822e-05,
      "loss": 1.0416048049926758,
      "num_input_tokens_seen": 18250471552,
      "step": 64170,
      "train_runtime": 625075.5277,
      "train_tokens_per_second": 29197.226
    },
    {
      "epoch": 2.2708140298580073,
      "grad_norm": 1.578125,
      "learning_rate": 1.8358175494218088e-05,
      "loss": 1.024864959716797,
      "num_input_tokens_seen": 18253279872,
      "step": 64180,
      "train_runtime": 625169.0613,
      "train_tokens_per_second": 29197.35
    },
    {
      "epoch": 2.2711678501217363,
      "grad_norm": 1.578125,
      "learning_rate": 1.8356938195281282e-05,
      "loss": 1.0446632385253907,
      "num_input_tokens_seen": 18256188672,
      "step": 64190,
      "train_runtime": 625271.8121,
      "train_tokens_per_second": 29197.204
    },
    {
      "epoch": 2.2715216703854653,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8355701146484093e-05,
      "loss": 1.03402099609375,
      "num_input_tokens_seen": 18258988480,
      "step": 64200,
      "train_runtime": 625367.3255,
      "train_tokens_per_second": 29197.222
    },
    {
      "epoch": 2.271875490649194,
      "grad_norm": 1.53125,
      "learning_rate": 1.835446434774225e-05,
      "loss": 1.0459038734436035,
      "num_input_tokens_seen": 18261761728,
      "step": 64210,
      "train_runtime": 625459.269,
      "train_tokens_per_second": 29197.364
    },
    {
      "epoch": 2.272229310912923,
      "grad_norm": 1.546875,
      "learning_rate": 1.835322779897152e-05,
      "loss": 1.0082343101501465,
      "num_input_tokens_seen": 18264589440,
      "step": 64220,
      "train_runtime": 625557.3095,
      "train_tokens_per_second": 29197.308
    },
    {
      "epoch": 2.2725831311766513,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8351991500087712e-05,
      "loss": 1.0329509735107423,
      "num_input_tokens_seen": 18267451840,
      "step": 64230,
      "train_runtime": 625653.8283,
      "train_tokens_per_second": 29197.379
    },
    {
      "epoch": 2.2729369514403803,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8350755451006675e-05,
      "loss": 1.0398679733276368,
      "num_input_tokens_seen": 18270272704,
      "step": 64240,
      "train_runtime": 625751.8161,
      "train_tokens_per_second": 29197.315
    },
    {
      "epoch": 2.273290771704109,
      "grad_norm": 1.546875,
      "learning_rate": 1.8349519651644293e-05,
      "loss": 1.0330918312072754,
      "num_input_tokens_seen": 18273148800,
      "step": 64250,
      "train_runtime": 625850.9974,
      "train_tokens_per_second": 29197.283
    },
    {
      "epoch": 2.273644591967838,
      "grad_norm": 1.609375,
      "learning_rate": 1.8348284101916496e-05,
      "loss": 1.0290111541748046,
      "num_input_tokens_seen": 18275962176,
      "step": 64260,
      "train_runtime": 625945.8427,
      "train_tokens_per_second": 29197.354
    },
    {
      "epoch": 2.2739984122315664,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8347048801739246e-05,
      "loss": 1.0446077346801759,
      "num_input_tokens_seen": 18278836416,
      "step": 64270,
      "train_runtime": 626042.0491,
      "train_tokens_per_second": 29197.458
    },
    {
      "epoch": 2.2743522324952954,
      "grad_norm": 1.625,
      "learning_rate": 1.8345813751028558e-05,
      "loss": 1.0254140853881837,
      "num_input_tokens_seen": 18281634432,
      "step": 64280,
      "train_runtime": 626135.5545,
      "train_tokens_per_second": 29197.566
    },
    {
      "epoch": 2.274706052759024,
      "grad_norm": 1.6328125,
      "learning_rate": 1.834457894970047e-05,
      "loss": 1.039866828918457,
      "num_input_tokens_seen": 18284517248,
      "step": 64290,
      "train_runtime": 626236.6148,
      "train_tokens_per_second": 29197.458
    },
    {
      "epoch": 2.275059873022753,
      "grad_norm": 1.609375,
      "learning_rate": 1.834334439767107e-05,
      "loss": 1.043266201019287,
      "num_input_tokens_seen": 18287369728,
      "step": 64300,
      "train_runtime": 626336.222,
      "train_tokens_per_second": 29197.369
    },
    {
      "epoch": 2.2754136932864815,
      "grad_norm": 1.59375,
      "learning_rate": 1.8342110094856478e-05,
      "loss": 1.0364429473876953,
      "num_input_tokens_seen": 18290188480,
      "step": 64310,
      "train_runtime": 626432.8932,
      "train_tokens_per_second": 29197.363
    },
    {
      "epoch": 2.2757675135502105,
      "grad_norm": 1.7109375,
      "learning_rate": 1.834087604117287e-05,
      "loss": 1.0412542343139648,
      "num_input_tokens_seen": 18293081152,
      "step": 64320,
      "train_runtime": 626532.2632,
      "train_tokens_per_second": 29197.349
    },
    {
      "epoch": 2.276121333813939,
      "grad_norm": 1.578125,
      "learning_rate": 1.833964223653644e-05,
      "loss": 1.0314523696899414,
      "num_input_tokens_seen": 18295940352,
      "step": 64330,
      "train_runtime": 626630.1005,
      "train_tokens_per_second": 29197.353
    },
    {
      "epoch": 2.276475154077668,
      "grad_norm": 1.609375,
      "learning_rate": 1.8338408680863432e-05,
      "loss": 1.0374682426452637,
      "num_input_tokens_seen": 18298808640,
      "step": 64340,
      "train_runtime": 626727.0085,
      "train_tokens_per_second": 29197.415
    },
    {
      "epoch": 2.276828974341397,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8337175374070135e-05,
      "loss": 1.0267463684082032,
      "num_input_tokens_seen": 18301680768,
      "step": 64350,
      "train_runtime": 626824.3356,
      "train_tokens_per_second": 29197.464
    },
    {
      "epoch": 2.2771827946051255,
      "grad_norm": 1.5625,
      "learning_rate": 1.8335942316072865e-05,
      "loss": 1.0374742507934571,
      "num_input_tokens_seen": 18304524160,
      "step": 64360,
      "train_runtime": 626921.2791,
      "train_tokens_per_second": 29197.484
    },
    {
      "epoch": 2.277536614868854,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8334709506787985e-05,
      "loss": 1.031332778930664,
      "num_input_tokens_seen": 18307434048,
      "step": 64370,
      "train_runtime": 627022.7785,
      "train_tokens_per_second": 29197.399
    },
    {
      "epoch": 2.277890435132583,
      "grad_norm": 1.671875,
      "learning_rate": 1.8333476946131896e-05,
      "loss": 1.0254192352294922,
      "num_input_tokens_seen": 18310294400,
      "step": 64380,
      "train_runtime": 627121.6147,
      "train_tokens_per_second": 29197.358
    },
    {
      "epoch": 2.278244255396312,
      "grad_norm": 1.609375,
      "learning_rate": 1.833224463402104e-05,
      "loss": 1.0401155471801757,
      "num_input_tokens_seen": 18313157696,
      "step": 64390,
      "train_runtime": 627220.5511,
      "train_tokens_per_second": 29197.318
    },
    {
      "epoch": 2.2785980756600406,
      "grad_norm": 1.609375,
      "learning_rate": 1.8331012570371896e-05,
      "loss": 1.0457454681396485,
      "num_input_tokens_seen": 18316027776,
      "step": 64400,
      "train_runtime": 627317.5793,
      "train_tokens_per_second": 29197.377
    },
    {
      "epoch": 2.2789518959237696,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8329780755100982e-05,
      "loss": 1.0439123153686523,
      "num_input_tokens_seen": 18318848320,
      "step": 64410,
      "train_runtime": 627411.5672,
      "train_tokens_per_second": 29197.499
    },
    {
      "epoch": 2.279305716187498,
      "grad_norm": 1.65625,
      "learning_rate": 1.8328549188124855e-05,
      "loss": 1.043769073486328,
      "num_input_tokens_seen": 18321744320,
      "step": 64420,
      "train_runtime": 627513.8923,
      "train_tokens_per_second": 29197.353
    },
    {
      "epoch": 2.279659536451227,
      "grad_norm": 1.578125,
      "learning_rate": 1.8327317869360112e-05,
      "loss": 1.0141810417175292,
      "num_input_tokens_seen": 18324578176,
      "step": 64430,
      "train_runtime": 627610.8161,
      "train_tokens_per_second": 29197.359
    },
    {
      "epoch": 2.2800133567149556,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8326086798723394e-05,
      "loss": 1.0207132339477538,
      "num_input_tokens_seen": 18327486656,
      "step": 64440,
      "train_runtime": 627711.2992,
      "train_tokens_per_second": 29197.318
    },
    {
      "epoch": 2.2803671769786846,
      "grad_norm": 1.625,
      "learning_rate": 1.832485597613137e-05,
      "loss": 1.0384506225585937,
      "num_input_tokens_seen": 18330381120,
      "step": 64450,
      "train_runtime": 627811.6926,
      "train_tokens_per_second": 29197.26
    },
    {
      "epoch": 2.280720997242413,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8323625401500763e-05,
      "loss": 1.0421475410461425,
      "num_input_tokens_seen": 18333246272,
      "step": 64460,
      "train_runtime": 627910.4712,
      "train_tokens_per_second": 29197.23
    },
    {
      "epoch": 2.281074817506142,
      "grad_norm": 1.5859375,
      "learning_rate": 1.832239507474832e-05,
      "loss": 1.0280970573425292,
      "num_input_tokens_seen": 18336156800,
      "step": 64470,
      "train_runtime": 628012.4818,
      "train_tokens_per_second": 29197.122
    },
    {
      "epoch": 2.2814286377698707,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8321164995790837e-05,
      "loss": 1.0427358627319336,
      "num_input_tokens_seen": 18339035840,
      "step": 64480,
      "train_runtime": 628111.6357,
      "train_tokens_per_second": 29197.096
    },
    {
      "epoch": 2.2817824580335997,
      "grad_norm": 1.5234375,
      "learning_rate": 1.831993516454515e-05,
      "loss": 1.0380359649658204,
      "num_input_tokens_seen": 18341846016,
      "step": 64490,
      "train_runtime": 628208.5688,
      "train_tokens_per_second": 29197.064
    },
    {
      "epoch": 2.2821362782973287,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8318705580928116e-05,
      "loss": 1.0348947525024415,
      "num_input_tokens_seen": 18344666752,
      "step": 64500,
      "train_runtime": 628304.5724,
      "train_tokens_per_second": 29197.093
    },
    {
      "epoch": 2.2824900985610572,
      "grad_norm": 1.6484375,
      "learning_rate": 1.8317476244856666e-05,
      "loss": 1.033930778503418,
      "num_input_tokens_seen": 18347492224,
      "step": 64510,
      "train_runtime": 628400.0894,
      "train_tokens_per_second": 29197.151
    },
    {
      "epoch": 2.2828439188247858,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8316247156247734e-05,
      "loss": 1.0285585403442383,
      "num_input_tokens_seen": 18350386304,
      "step": 64520,
      "train_runtime": 628499.6995,
      "train_tokens_per_second": 29197.128
    },
    {
      "epoch": 2.2831977390885148,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8315018315018315e-05,
      "loss": 1.0467044830322265,
      "num_input_tokens_seen": 18353217600,
      "step": 64530,
      "train_runtime": 628597.5557,
      "train_tokens_per_second": 29197.087
    },
    {
      "epoch": 2.2835515593522437,
      "grad_norm": 1.5234375,
      "learning_rate": 1.8313789721085437e-05,
      "loss": 1.0134990692138672,
      "num_input_tokens_seen": 18356073664,
      "step": 64540,
      "train_runtime": 628694.4822,
      "train_tokens_per_second": 29197.129
    },
    {
      "epoch": 2.2839053796159723,
      "grad_norm": 1.6484375,
      "learning_rate": 1.8312561374366162e-05,
      "loss": 1.0387868881225586,
      "num_input_tokens_seen": 18358872704,
      "step": 64550,
      "train_runtime": 628788.6716,
      "train_tokens_per_second": 29197.207
    },
    {
      "epoch": 2.2842591998797013,
      "grad_norm": 1.65625,
      "learning_rate": 1.83113332747776e-05,
      "loss": 1.038320541381836,
      "num_input_tokens_seen": 18361735744,
      "step": 64560,
      "train_runtime": 628889.1265,
      "train_tokens_per_second": 29197.095
    },
    {
      "epoch": 2.28461302014343,
      "grad_norm": 1.6640625,
      "learning_rate": 1.8310105422236888e-05,
      "loss": 1.024345588684082,
      "num_input_tokens_seen": 18364562880,
      "step": 64570,
      "train_runtime": 628986.9309,
      "train_tokens_per_second": 29197.05
    },
    {
      "epoch": 2.284966840407159,
      "grad_norm": 1.5625,
      "learning_rate": 1.8308877816661216e-05,
      "loss": 1.0377293586730958,
      "num_input_tokens_seen": 18367401024,
      "step": 64580,
      "train_runtime": 629085.2566,
      "train_tokens_per_second": 29196.998
    },
    {
      "epoch": 2.2853206606708873,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8307650457967805e-05,
      "loss": 1.0366357803344726,
      "num_input_tokens_seen": 18370255744,
      "step": 64590,
      "train_runtime": 629185.8636,
      "train_tokens_per_second": 29196.867
    },
    {
      "epoch": 2.2856744809346163,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8306423346073912e-05,
      "loss": 1.0456771850585938,
      "num_input_tokens_seen": 18373099648,
      "step": 64600,
      "train_runtime": 629281.1296,
      "train_tokens_per_second": 29196.966
    },
    {
      "epoch": 2.286028301198345,
      "grad_norm": 1.609375,
      "learning_rate": 1.830519648089684e-05,
      "loss": 1.0351470947265624,
      "num_input_tokens_seen": 18375949440,
      "step": 64610,
      "train_runtime": 629375.1676,
      "train_tokens_per_second": 29197.131
    },
    {
      "epoch": 2.286382121462074,
      "grad_norm": 1.609375,
      "learning_rate": 1.8303969862353928e-05,
      "loss": 1.0320655822753906,
      "num_input_tokens_seen": 18378796160,
      "step": 64620,
      "train_runtime": 629470.9671,
      "train_tokens_per_second": 29197.21
    },
    {
      "epoch": 2.2867359417258024,
      "grad_norm": 1.6171875,
      "learning_rate": 1.830274349036255e-05,
      "loss": 1.0561960220336915,
      "num_input_tokens_seen": 18381682240,
      "step": 64630,
      "train_runtime": 629572.2057,
      "train_tokens_per_second": 29197.099
    },
    {
      "epoch": 2.2870897619895314,
      "grad_norm": 1.6328125,
      "learning_rate": 1.830151736484013e-05,
      "loss": 1.0282472610473632,
      "num_input_tokens_seen": 18384510848,
      "step": 64640,
      "train_runtime": 629670.9423,
      "train_tokens_per_second": 29197.013
    },
    {
      "epoch": 2.28744358225326,
      "grad_norm": 1.578125,
      "learning_rate": 1.830029148570411e-05,
      "loss": 1.0292570114135742,
      "num_input_tokens_seen": 18387382016,
      "step": 64650,
      "train_runtime": 629770.9928,
      "train_tokens_per_second": 29196.934
    },
    {
      "epoch": 2.287797402516989,
      "grad_norm": 1.5703125,
      "learning_rate": 1.829906585287199e-05,
      "loss": 1.044973659515381,
      "num_input_tokens_seen": 18390254336,
      "step": 64660,
      "train_runtime": 629868.8903,
      "train_tokens_per_second": 29196.956
    },
    {
      "epoch": 2.2881512227807175,
      "grad_norm": 1.625,
      "learning_rate": 1.8297840466261302e-05,
      "loss": 1.0455560684204102,
      "num_input_tokens_seen": 18393092352,
      "step": 64670,
      "train_runtime": 629967.6508,
      "train_tokens_per_second": 29196.884
    },
    {
      "epoch": 2.2885050430444465,
      "grad_norm": 1.59375,
      "learning_rate": 1.8296615325789615e-05,
      "loss": 1.048040771484375,
      "num_input_tokens_seen": 18395909632,
      "step": 64680,
      "train_runtime": 630061.2908,
      "train_tokens_per_second": 29197.016
    },
    {
      "epoch": 2.2888588633081755,
      "grad_norm": 1.5703125,
      "learning_rate": 1.829539043137454e-05,
      "loss": 1.0449575424194335,
      "num_input_tokens_seen": 18398797824,
      "step": 64690,
      "train_runtime": 630158.7639,
      "train_tokens_per_second": 29197.083
    },
    {
      "epoch": 2.289212683571904,
      "grad_norm": 1.59375,
      "learning_rate": 1.8294165782933725e-05,
      "loss": 1.029738998413086,
      "num_input_tokens_seen": 18401685376,
      "step": 64700,
      "train_runtime": 630259.9672,
      "train_tokens_per_second": 29196.976
    },
    {
      "epoch": 2.289566503835633,
      "grad_norm": 1.59375,
      "learning_rate": 1.8292941380384852e-05,
      "loss": 1.0258625030517579,
      "num_input_tokens_seen": 18404513216,
      "step": 64710,
      "train_runtime": 630356.6601,
      "train_tokens_per_second": 29196.984
    },
    {
      "epoch": 2.2899203240993615,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8291717223645656e-05,
      "loss": 1.033228302001953,
      "num_input_tokens_seen": 18407399104,
      "step": 64720,
      "train_runtime": 630456.828,
      "train_tokens_per_second": 29196.922
    },
    {
      "epoch": 2.2902741443630905,
      "grad_norm": 1.53125,
      "learning_rate": 1.8290493312633896e-05,
      "loss": 1.0421640396118164,
      "num_input_tokens_seen": 18410233344,
      "step": 64730,
      "train_runtime": 630553.2668,
      "train_tokens_per_second": 29196.952
    },
    {
      "epoch": 2.290627964626819,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8289269647267365e-05,
      "loss": 1.028494167327881,
      "num_input_tokens_seen": 18413004224,
      "step": 64740,
      "train_runtime": 630647.0612,
      "train_tokens_per_second": 29197.003
    },
    {
      "epoch": 2.290981784890548,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8288046227463916e-05,
      "loss": 1.0369249343872071,
      "num_input_tokens_seen": 18415917824,
      "step": 64750,
      "train_runtime": 630748.2963,
      "train_tokens_per_second": 29196.936
    },
    {
      "epoch": 2.2913356051542766,
      "grad_norm": 1.5703125,
      "learning_rate": 1.828682305314142e-05,
      "loss": 1.032666015625,
      "num_input_tokens_seen": 18418796032,
      "step": 64760,
      "train_runtime": 630846.0598,
      "train_tokens_per_second": 29196.974
    },
    {
      "epoch": 2.2916894254180056,
      "grad_norm": 1.5859375,
      "learning_rate": 1.82856001242178e-05,
      "loss": 1.0364411354064942,
      "num_input_tokens_seen": 18421703296,
      "step": 64770,
      "train_runtime": 630948.3843,
      "train_tokens_per_second": 29196.847
    },
    {
      "epoch": 2.292043245681734,
      "grad_norm": 1.609375,
      "learning_rate": 1.8284377440611006e-05,
      "loss": 1.0370383262634277,
      "num_input_tokens_seen": 18424564416,
      "step": 64780,
      "train_runtime": 631046.1282,
      "train_tokens_per_second": 29196.858
    },
    {
      "epoch": 2.292397065945463,
      "grad_norm": 1.5390625,
      "learning_rate": 1.828315500223904e-05,
      "loss": 1.0400867462158203,
      "num_input_tokens_seen": 18427471424,
      "step": 64790,
      "train_runtime": 631145.3279,
      "train_tokens_per_second": 29196.875
    },
    {
      "epoch": 2.2927508862091917,
      "grad_norm": 1.609375,
      "learning_rate": 1.8281932809019927e-05,
      "loss": 1.0253150939941407,
      "num_input_tokens_seen": 18430335168,
      "step": 64800,
      "train_runtime": 631240.1039,
      "train_tokens_per_second": 29197.028
    },
    {
      "epoch": 2.2931047064729206,
      "grad_norm": 1.6015625,
      "learning_rate": 1.828071086087174e-05,
      "loss": 1.0349834442138672,
      "num_input_tokens_seen": 18433147648,
      "step": 64810,
      "train_runtime": 631337.0844,
      "train_tokens_per_second": 29196.998
    },
    {
      "epoch": 2.293458526736649,
      "grad_norm": 1.5546875,
      "learning_rate": 1.827948915771259e-05,
      "loss": 1.0476248741149903,
      "num_input_tokens_seen": 18436049856,
      "step": 64820,
      "train_runtime": 631436.3839,
      "train_tokens_per_second": 29197.003
    },
    {
      "epoch": 2.293812347000378,
      "grad_norm": 1.578125,
      "learning_rate": 1.827826769946063e-05,
      "loss": 1.039565372467041,
      "num_input_tokens_seen": 18438903360,
      "step": 64830,
      "train_runtime": 631536.3526,
      "train_tokens_per_second": 29196.899
    },
    {
      "epoch": 2.294166167264107,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8277046486034035e-05,
      "loss": 1.0273591995239257,
      "num_input_tokens_seen": 18441781184,
      "step": 64840,
      "train_runtime": 631636.2799,
      "train_tokens_per_second": 29196.836
    },
    {
      "epoch": 2.2945199875278357,
      "grad_norm": 1.578125,
      "learning_rate": 1.8275825517351035e-05,
      "loss": 1.0401777267456054,
      "num_input_tokens_seen": 18444648704,
      "step": 64850,
      "train_runtime": 631735.1406,
      "train_tokens_per_second": 29196.807
    },
    {
      "epoch": 2.2948738077915642,
      "grad_norm": 1.5546875,
      "learning_rate": 1.827460479332989e-05,
      "loss": 1.0224387168884277,
      "num_input_tokens_seen": 18447546560,
      "step": 64860,
      "train_runtime": 631835.5094,
      "train_tokens_per_second": 29196.755
    },
    {
      "epoch": 2.2952276280552932,
      "grad_norm": 1.5859375,
      "learning_rate": 1.827338431388891e-05,
      "loss": 1.0415216445922852,
      "num_input_tokens_seen": 18450421440,
      "step": 64870,
      "train_runtime": 631938.0701,
      "train_tokens_per_second": 29196.566
    },
    {
      "epoch": 2.295581448319022,
      "grad_norm": 1.5625,
      "learning_rate": 1.8272164078946418e-05,
      "loss": 1.0378936767578124,
      "num_input_tokens_seen": 18453212928,
      "step": 64880,
      "train_runtime": 632029.8043,
      "train_tokens_per_second": 29196.745
    },
    {
      "epoch": 2.2959352685827508,
      "grad_norm": 1.640625,
      "learning_rate": 1.82709440884208e-05,
      "loss": 1.0377042770385743,
      "num_input_tokens_seen": 18456091264,
      "step": 64890,
      "train_runtime": 632128.9348,
      "train_tokens_per_second": 29196.72
    },
    {
      "epoch": 2.2962890888464798,
      "grad_norm": 1.5625,
      "learning_rate": 1.8269724342230474e-05,
      "loss": 1.0219600677490235,
      "num_input_tokens_seen": 18458993792,
      "step": 64900,
      "train_runtime": 632227.8367,
      "train_tokens_per_second": 29196.743
    },
    {
      "epoch": 2.2966429091102083,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8268504840293886e-05,
      "loss": 1.0450669288635255,
      "num_input_tokens_seen": 18461815168,
      "step": 64910,
      "train_runtime": 632322.2493,
      "train_tokens_per_second": 29196.846
    },
    {
      "epoch": 2.2969967293739373,
      "grad_norm": 1.5625,
      "learning_rate": 1.8267285582529535e-05,
      "loss": 1.0436393737792968,
      "num_input_tokens_seen": 18464662144,
      "step": 64920,
      "train_runtime": 632417.4905,
      "train_tokens_per_second": 29196.95
    },
    {
      "epoch": 2.297350549637666,
      "grad_norm": 1.6484375,
      "learning_rate": 1.826606656885594e-05,
      "loss": 1.0366973876953125,
      "num_input_tokens_seen": 18467464896,
      "step": 64930,
      "train_runtime": 632512.8779,
      "train_tokens_per_second": 29196.978
    },
    {
      "epoch": 2.297704369901395,
      "grad_norm": 1.6328125,
      "learning_rate": 1.826484779919168e-05,
      "loss": 1.0373764991760255,
      "num_input_tokens_seen": 18470356672,
      "step": 64940,
      "train_runtime": 632613.3148,
      "train_tokens_per_second": 29196.914
    },
    {
      "epoch": 2.2980581901651234,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8263629273455353e-05,
      "loss": 1.0451536178588867,
      "num_input_tokens_seen": 18473203840,
      "step": 64950,
      "train_runtime": 632713.4759,
      "train_tokens_per_second": 29196.792
    },
    {
      "epoch": 2.2984120104288523,
      "grad_norm": 1.53125,
      "learning_rate": 1.8262410991565605e-05,
      "loss": 1.0363346099853517,
      "num_input_tokens_seen": 18476093120,
      "step": 64960,
      "train_runtime": 632816.7672,
      "train_tokens_per_second": 29196.592
    },
    {
      "epoch": 2.298765830692581,
      "grad_norm": 1.578125,
      "learning_rate": 1.826119295344112e-05,
      "loss": 1.0332185745239257,
      "num_input_tokens_seen": 18478951936,
      "step": 64970,
      "train_runtime": 632915.7945,
      "train_tokens_per_second": 29196.541
    },
    {
      "epoch": 2.29911965095631,
      "grad_norm": 1.5625,
      "learning_rate": 1.8259975159000613e-05,
      "loss": 1.037625217437744,
      "num_input_tokens_seen": 18481807872,
      "step": 64980,
      "train_runtime": 633012.5718,
      "train_tokens_per_second": 29196.589
    },
    {
      "epoch": 2.2994734712200384,
      "grad_norm": 1.5625,
      "learning_rate": 1.825875760816284e-05,
      "loss": 1.0380874633789063,
      "num_input_tokens_seen": 18484662720,
      "step": 64990,
      "train_runtime": 633108.8602,
      "train_tokens_per_second": 29196.658
    },
    {
      "epoch": 2.2998272914837674,
      "grad_norm": 1.625,
      "learning_rate": 1.8257540300846603e-05,
      "loss": 1.030609703063965,
      "num_input_tokens_seen": 18487515328,
      "step": 65000,
      "train_runtime": 633209.3845,
      "train_tokens_per_second": 29196.528
    },
    {
      "epoch": 2.2998272914837674,
      "eval_loss": 1.0217957496643066,
      "eval_runtime": 8.4425,
      "eval_samples_per_second": 472.37,
      "eval_steps_per_second": 3.79,
      "num_input_tokens_seen": 18487515328,
      "step": 65000
    },
    {
      "epoch": 2.300181111747496,
      "grad_norm": 1.6484375,
      "learning_rate": 1.825632323697073e-05,
      "loss": 1.0229268074035645,
      "num_input_tokens_seen": 18490398528,
      "step": 65010,
      "train_runtime": 633337.7732,
      "train_tokens_per_second": 29195.161
    },
    {
      "epoch": 2.300534932011225,
      "grad_norm": 1.578125,
      "learning_rate": 1.8255106416454093e-05,
      "loss": 1.0366459846496583,
      "num_input_tokens_seen": 18493255488,
      "step": 65020,
      "train_runtime": 633435.1971,
      "train_tokens_per_second": 29195.181
    },
    {
      "epoch": 2.300888752274954,
      "grad_norm": 1.671875,
      "learning_rate": 1.82538898392156e-05,
      "loss": 1.0396026611328124,
      "num_input_tokens_seen": 18496091968,
      "step": 65030,
      "train_runtime": 633534.8279,
      "train_tokens_per_second": 29195.067
    },
    {
      "epoch": 2.3012425725386825,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8252673505174206e-05,
      "loss": 1.0393798828125,
      "num_input_tokens_seen": 18498931456,
      "step": 65040,
      "train_runtime": 633632.0104,
      "train_tokens_per_second": 29195.071
    },
    {
      "epoch": 2.3015963928024115,
      "grad_norm": 1.703125,
      "learning_rate": 1.825145741424888e-05,
      "loss": 1.0458796501159668,
      "num_input_tokens_seen": 18501787392,
      "step": 65050,
      "train_runtime": 633732.3105,
      "train_tokens_per_second": 29194.957
    },
    {
      "epoch": 2.30195021306614,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8250241566358662e-05,
      "loss": 1.0302570343017579,
      "num_input_tokens_seen": 18504658240,
      "step": 65060,
      "train_runtime": 633832.5729,
      "train_tokens_per_second": 29194.868
    },
    {
      "epoch": 2.302304033329869,
      "grad_norm": 1.59375,
      "learning_rate": 1.8249025961422598e-05,
      "loss": 1.0455583572387694,
      "num_input_tokens_seen": 18507565504,
      "step": 65070,
      "train_runtime": 633933.0913,
      "train_tokens_per_second": 29194.825
    },
    {
      "epoch": 2.3026578535935975,
      "grad_norm": 1.6875,
      "learning_rate": 1.824781059935979e-05,
      "loss": 1.0493395805358887,
      "num_input_tokens_seen": 18510434112,
      "step": 65080,
      "train_runtime": 634033.0666,
      "train_tokens_per_second": 29194.746
    },
    {
      "epoch": 2.3030116738573265,
      "grad_norm": 1.640625,
      "learning_rate": 1.8246595480089376e-05,
      "loss": 1.0372772216796875,
      "num_input_tokens_seen": 18513277376,
      "step": 65090,
      "train_runtime": 634129.9972,
      "train_tokens_per_second": 29194.767
    },
    {
      "epoch": 2.303365494121055,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8245380603530526e-05,
      "loss": 1.0383846282958984,
      "num_input_tokens_seen": 18516184256,
      "step": 65100,
      "train_runtime": 634229.5608,
      "train_tokens_per_second": 29194.767
    },
    {
      "epoch": 2.303719314384784,
      "grad_norm": 1.609375,
      "learning_rate": 1.8244165969602455e-05,
      "loss": 1.035775375366211,
      "num_input_tokens_seen": 18519012096,
      "step": 65110,
      "train_runtime": 634326.1239,
      "train_tokens_per_second": 29194.781
    },
    {
      "epoch": 2.3040731346485126,
      "grad_norm": 1.609375,
      "learning_rate": 1.824295157822441e-05,
      "loss": 1.051549243927002,
      "num_input_tokens_seen": 18521816896,
      "step": 65120,
      "train_runtime": 634420.2949,
      "train_tokens_per_second": 29194.868
    },
    {
      "epoch": 2.3044269549122416,
      "grad_norm": 1.625,
      "learning_rate": 1.8241737429315674e-05,
      "loss": 1.0504838943481445,
      "num_input_tokens_seen": 18524689920,
      "step": 65130,
      "train_runtime": 634520.368,
      "train_tokens_per_second": 29194.792
    },
    {
      "epoch": 2.30478077517597,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8240523522795575e-05,
      "loss": 1.0351264953613282,
      "num_input_tokens_seen": 18527584000,
      "step": 65140,
      "train_runtime": 634625.4872,
      "train_tokens_per_second": 29194.516
    },
    {
      "epoch": 2.305134595439699,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8239309858583466e-05,
      "loss": 1.0427067756652832,
      "num_input_tokens_seen": 18530475648,
      "step": 65150,
      "train_runtime": 634723.5119,
      "train_tokens_per_second": 29194.563
    },
    {
      "epoch": 2.3054884157034277,
      "grad_norm": 1.5234375,
      "learning_rate": 1.8238096436598755e-05,
      "loss": 1.0311473846435546,
      "num_input_tokens_seen": 18533333888,
      "step": 65160,
      "train_runtime": 634822.1385,
      "train_tokens_per_second": 29194.53
    },
    {
      "epoch": 2.3058422359671567,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8236883256760882e-05,
      "loss": 1.0339998245239257,
      "num_input_tokens_seen": 18536214272,
      "step": 65170,
      "train_runtime": 634922.3519,
      "train_tokens_per_second": 29194.459
    },
    {
      "epoch": 2.3061960562308856,
      "grad_norm": 1.6640625,
      "learning_rate": 1.8235670318989305e-05,
      "loss": 1.0396757125854492,
      "num_input_tokens_seen": 18539085120,
      "step": 65180,
      "train_runtime": 635020.2009,
      "train_tokens_per_second": 29194.481
    },
    {
      "epoch": 2.306549876494614,
      "grad_norm": 1.5625,
      "learning_rate": 1.8234457623203548e-05,
      "loss": 1.0299694061279296,
      "num_input_tokens_seen": 18541982144,
      "step": 65190,
      "train_runtime": 635118.3014,
      "train_tokens_per_second": 29194.533
    },
    {
      "epoch": 2.3069036967583427,
      "grad_norm": 1.78125,
      "learning_rate": 1.8233245169323163e-05,
      "loss": 1.0411277770996095,
      "num_input_tokens_seen": 18544886080,
      "step": 65200,
      "train_runtime": 635219.4226,
      "train_tokens_per_second": 29194.457
    },
    {
      "epoch": 2.3072575170220717,
      "grad_norm": 1.5078125,
      "learning_rate": 1.823203295726772e-05,
      "loss": 1.0397773742675782,
      "num_input_tokens_seen": 18547720512,
      "step": 65210,
      "train_runtime": 635314.1117,
      "train_tokens_per_second": 29194.567
    },
    {
      "epoch": 2.3076113372858007,
      "grad_norm": 1.5703125,
      "learning_rate": 1.823082098695686e-05,
      "loss": 1.042841911315918,
      "num_input_tokens_seen": 18550568192,
      "step": 65220,
      "train_runtime": 635413.6803,
      "train_tokens_per_second": 29194.474
    },
    {
      "epoch": 2.3079651575495292,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8229609258310233e-05,
      "loss": 1.0319224357604981,
      "num_input_tokens_seen": 18553420544,
      "step": 65230,
      "train_runtime": 635511.5974,
      "train_tokens_per_second": 29194.464
    },
    {
      "epoch": 2.3083189778132582,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8228397771247542e-05,
      "loss": 1.0429303169250488,
      "num_input_tokens_seen": 18556261376,
      "step": 65240,
      "train_runtime": 635609.77,
      "train_tokens_per_second": 29194.424
    },
    {
      "epoch": 2.3086727980769868,
      "grad_norm": 1.6171875,
      "learning_rate": 1.822718652568852e-05,
      "loss": 1.0485212326049804,
      "num_input_tokens_seen": 18559124864,
      "step": 65250,
      "train_runtime": 635704.6007,
      "train_tokens_per_second": 29194.574
    },
    {
      "epoch": 2.3090266183407158,
      "grad_norm": 1.546875,
      "learning_rate": 1.8225975521552944e-05,
      "loss": 1.0395598411560059,
      "num_input_tokens_seen": 18561957888,
      "step": 65260,
      "train_runtime": 635800.6228,
      "train_tokens_per_second": 29194.62
    },
    {
      "epoch": 2.3093804386044443,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8224764758760622e-05,
      "loss": 1.043720817565918,
      "num_input_tokens_seen": 18564790272,
      "step": 65270,
      "train_runtime": 635897.9345,
      "train_tokens_per_second": 29194.607
    },
    {
      "epoch": 2.3097342588681733,
      "grad_norm": 1.609375,
      "learning_rate": 1.8223554237231398e-05,
      "loss": 1.047821044921875,
      "num_input_tokens_seen": 18567663936,
      "step": 65280,
      "train_runtime": 635998.3623,
      "train_tokens_per_second": 29194.515
    },
    {
      "epoch": 2.310088079131902,
      "grad_norm": 1.5859375,
      "learning_rate": 1.822234395688517e-05,
      "loss": 1.0426538467407227,
      "num_input_tokens_seen": 18570522944,
      "step": 65290,
      "train_runtime": 636097.7239,
      "train_tokens_per_second": 29194.45
    },
    {
      "epoch": 2.310441899395631,
      "grad_norm": 1.578125,
      "learning_rate": 1.8221133917641845e-05,
      "loss": 1.021619701385498,
      "num_input_tokens_seen": 18573323968,
      "step": 65300,
      "train_runtime": 636190.3419,
      "train_tokens_per_second": 29194.602
    },
    {
      "epoch": 2.3107957196593594,
      "grad_norm": 1.6015625,
      "learning_rate": 1.821992411942139e-05,
      "loss": 1.041017723083496,
      "num_input_tokens_seen": 18576142400,
      "step": 65310,
      "train_runtime": 636286.5782,
      "train_tokens_per_second": 29194.616
    },
    {
      "epoch": 2.3111495399230884,
      "grad_norm": 1.53125,
      "learning_rate": 1.8218714562143804e-05,
      "loss": 1.0422449111938477,
      "num_input_tokens_seen": 18578974528,
      "step": 65320,
      "train_runtime": 636383.0338,
      "train_tokens_per_second": 29194.641
    },
    {
      "epoch": 2.3115033601868173,
      "grad_norm": 1.59375,
      "learning_rate": 1.8217505245729113e-05,
      "loss": 1.0307751655578614,
      "num_input_tokens_seen": 18581874560,
      "step": 65330,
      "train_runtime": 636483.2041,
      "train_tokens_per_second": 29194.603
    },
    {
      "epoch": 2.311857180450546,
      "grad_norm": 1.640625,
      "learning_rate": 1.8216296170097395e-05,
      "loss": 1.0481264114379882,
      "num_input_tokens_seen": 18584736768,
      "step": 65340,
      "train_runtime": 636584.5421,
      "train_tokens_per_second": 29194.452
    },
    {
      "epoch": 2.3122110007142744,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8215087335168758e-05,
      "loss": 1.0404241561889649,
      "num_input_tokens_seen": 18587584192,
      "step": 65350,
      "train_runtime": 636681.2033,
      "train_tokens_per_second": 29194.492
    },
    {
      "epoch": 2.3125648209780034,
      "grad_norm": 1.59375,
      "learning_rate": 1.8213878740863342e-05,
      "loss": 1.0382518768310547,
      "num_input_tokens_seen": 18590437696,
      "step": 65360,
      "train_runtime": 636779.251,
      "train_tokens_per_second": 29194.478
    },
    {
      "epoch": 2.3129186412417324,
      "grad_norm": 1.6171875,
      "learning_rate": 1.821267038710133e-05,
      "loss": 1.0545601844787598,
      "num_input_tokens_seen": 18593262144,
      "step": 65370,
      "train_runtime": 636872.9649,
      "train_tokens_per_second": 29194.617
    },
    {
      "epoch": 2.313272461505461,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8211462273802946e-05,
      "loss": 1.036918544769287,
      "num_input_tokens_seen": 18596127232,
      "step": 65380,
      "train_runtime": 636973.5019,
      "train_tokens_per_second": 29194.507
    },
    {
      "epoch": 2.31362628176919,
      "grad_norm": 1.59375,
      "learning_rate": 1.821025440088844e-05,
      "loss": 1.0232006072998048,
      "num_input_tokens_seen": 18598984320,
      "step": 65390,
      "train_runtime": 637072.4411,
      "train_tokens_per_second": 29194.458
    },
    {
      "epoch": 2.3139801020329185,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8209046768278115e-05,
      "loss": 1.0324426651000977,
      "num_input_tokens_seen": 18601814464,
      "step": 65400,
      "train_runtime": 637169.9669,
      "train_tokens_per_second": 29194.431
    },
    {
      "epoch": 2.3143339222966475,
      "grad_norm": 1.671875,
      "learning_rate": 1.8207839375892292e-05,
      "loss": 1.0417671203613281,
      "num_input_tokens_seen": 18604680256,
      "step": 65410,
      "train_runtime": 637269.6279,
      "train_tokens_per_second": 29194.362
    },
    {
      "epoch": 2.314687742560376,
      "grad_norm": 1.59375,
      "learning_rate": 1.8206632223651342e-05,
      "loss": 1.0272227287292481,
      "num_input_tokens_seen": 18607483072,
      "step": 65420,
      "train_runtime": 637363.0407,
      "train_tokens_per_second": 29194.481
    },
    {
      "epoch": 2.315041562824105,
      "grad_norm": 1.5625,
      "learning_rate": 1.8205425311475674e-05,
      "loss": 1.0361154556274415,
      "num_input_tokens_seen": 18610298048,
      "step": 65430,
      "train_runtime": 637457.704,
      "train_tokens_per_second": 29194.561
    },
    {
      "epoch": 2.3153953830878335,
      "grad_norm": 1.6328125,
      "learning_rate": 1.820421863928572e-05,
      "loss": 1.0453486442565918,
      "num_input_tokens_seen": 18613147456,
      "step": 65440,
      "train_runtime": 637558.0189,
      "train_tokens_per_second": 29194.437
    },
    {
      "epoch": 2.3157492033515625,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8203012207001965e-05,
      "loss": 1.0388654708862304,
      "num_input_tokens_seen": 18616037376,
      "step": 65450,
      "train_runtime": 637660.1718,
      "train_tokens_per_second": 29194.292
    },
    {
      "epoch": 2.316103023615291,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8201806014544923e-05,
      "loss": 1.0443506240844727,
      "num_input_tokens_seen": 18618861184,
      "step": 65460,
      "train_runtime": 637753.5988,
      "train_tokens_per_second": 29194.443
    },
    {
      "epoch": 2.31645684387902,
      "grad_norm": 1.578125,
      "learning_rate": 1.8200600061835143e-05,
      "loss": 1.0519091606140136,
      "num_input_tokens_seen": 18621689664,
      "step": 65470,
      "train_runtime": 637850.2664,
      "train_tokens_per_second": 29194.453
    },
    {
      "epoch": 2.3168106641427486,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8199394348793213e-05,
      "loss": 1.0428619384765625,
      "num_input_tokens_seen": 18624549248,
      "step": 65480,
      "train_runtime": 637947.7675,
      "train_tokens_per_second": 29194.474
    },
    {
      "epoch": 2.3171644844064776,
      "grad_norm": 1.59375,
      "learning_rate": 1.8198188875339767e-05,
      "loss": 1.0486169815063477,
      "num_input_tokens_seen": 18627419968,
      "step": 65490,
      "train_runtime": 638044.9453,
      "train_tokens_per_second": 29194.526
    },
    {
      "epoch": 2.317518304670206,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8196983641395458e-05,
      "loss": 1.0388744354248047,
      "num_input_tokens_seen": 18630259328,
      "step": 65500,
      "train_runtime": 638140.0148,
      "train_tokens_per_second": 29194.626
    },
    {
      "epoch": 2.317872124933935,
      "grad_norm": 1.625,
      "learning_rate": 1.819577864688099e-05,
      "loss": 1.0508481025695802,
      "num_input_tokens_seen": 18633127296,
      "step": 65510,
      "train_runtime": 638237.1523,
      "train_tokens_per_second": 29194.677
    },
    {
      "epoch": 2.318225945197664,
      "grad_norm": 1.4765625,
      "learning_rate": 1.8194573891717096e-05,
      "loss": 1.041521167755127,
      "num_input_tokens_seen": 18635986944,
      "step": 65520,
      "train_runtime": 638333.8506,
      "train_tokens_per_second": 29194.734
    },
    {
      "epoch": 2.3185797654613927,
      "grad_norm": 1.6171875,
      "learning_rate": 1.819336937582455e-05,
      "loss": 1.0501035690307616,
      "num_input_tokens_seen": 18638905088,
      "step": 65530,
      "train_runtime": 638436.7715,
      "train_tokens_per_second": 29194.598
    },
    {
      "epoch": 2.3189335857251216,
      "grad_norm": 1.609375,
      "learning_rate": 1.8192165099124165e-05,
      "loss": 1.0338028907775878,
      "num_input_tokens_seen": 18641765184,
      "step": 65540,
      "train_runtime": 638535.3494,
      "train_tokens_per_second": 29194.57
    },
    {
      "epoch": 2.31928740598885,
      "grad_norm": 1.6484375,
      "learning_rate": 1.8190961061536783e-05,
      "loss": 1.0423393249511719,
      "num_input_tokens_seen": 18644563072,
      "step": 65550,
      "train_runtime": 638629.7637,
      "train_tokens_per_second": 29194.635
    },
    {
      "epoch": 2.319641226252579,
      "grad_norm": 1.53125,
      "learning_rate": 1.8189757262983285e-05,
      "loss": 1.0432945251464845,
      "num_input_tokens_seen": 18647349824,
      "step": 65560,
      "train_runtime": 638722.5952,
      "train_tokens_per_second": 29194.755
    },
    {
      "epoch": 2.3199950465163077,
      "grad_norm": 1.625,
      "learning_rate": 1.818855370338459e-05,
      "loss": 1.0450042724609374,
      "num_input_tokens_seen": 18650167424,
      "step": 65570,
      "train_runtime": 638818.1839,
      "train_tokens_per_second": 29194.797
    },
    {
      "epoch": 2.3203488667800367,
      "grad_norm": 1.71875,
      "learning_rate": 1.8187350382661664e-05,
      "loss": 1.0318404197692872,
      "num_input_tokens_seen": 18653026496,
      "step": 65580,
      "train_runtime": 638915.5335,
      "train_tokens_per_second": 29194.824
    },
    {
      "epoch": 2.3207026870437653,
      "grad_norm": 1.6015625,
      "learning_rate": 1.818614730073549e-05,
      "loss": 1.0348509788513183,
      "num_input_tokens_seen": 18655831808,
      "step": 65590,
      "train_runtime": 639009.5781,
      "train_tokens_per_second": 29194.917
    },
    {
      "epoch": 2.3210565073074942,
      "grad_norm": 1.6171875,
      "learning_rate": 1.81849444575271e-05,
      "loss": 1.029323196411133,
      "num_input_tokens_seen": 18658701440,
      "step": 65600,
      "train_runtime": 639107.7652,
      "train_tokens_per_second": 29194.922
    },
    {
      "epoch": 2.321410327571223,
      "grad_norm": 1.578125,
      "learning_rate": 1.818374185295756e-05,
      "loss": 1.042348575592041,
      "num_input_tokens_seen": 18661548544,
      "step": 65610,
      "train_runtime": 639203.1483,
      "train_tokens_per_second": 29195.02
    },
    {
      "epoch": 2.3217641478349518,
      "grad_norm": 1.625,
      "learning_rate": 1.8182539486947967e-05,
      "loss": 1.0297676086425782,
      "num_input_tokens_seen": 18664386688,
      "step": 65620,
      "train_runtime": 639297.9584,
      "train_tokens_per_second": 29195.13
    },
    {
      "epoch": 2.3221179680986803,
      "grad_norm": 1.578125,
      "learning_rate": 1.8181337359419467e-05,
      "loss": 1.0351337432861327,
      "num_input_tokens_seen": 18667199936,
      "step": 65630,
      "train_runtime": 639392.7489,
      "train_tokens_per_second": 29195.201
    },
    {
      "epoch": 2.3224717883624093,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8180135470293233e-05,
      "loss": 1.0372797012329102,
      "num_input_tokens_seen": 18670070528,
      "step": 65640,
      "train_runtime": 639493.633,
      "train_tokens_per_second": 29195.084
    },
    {
      "epoch": 2.322825608626138,
      "grad_norm": 1.578125,
      "learning_rate": 1.817893381949048e-05,
      "loss": 1.021463394165039,
      "num_input_tokens_seen": 18672928768,
      "step": 65650,
      "train_runtime": 639590.9739,
      "train_tokens_per_second": 29195.11
    },
    {
      "epoch": 2.323179428889867,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8177732406932444e-05,
      "loss": 1.0444185256958007,
      "num_input_tokens_seen": 18675744448,
      "step": 65660,
      "train_runtime": 639683.8936,
      "train_tokens_per_second": 29195.271
    },
    {
      "epoch": 2.323533249153596,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8176531232540427e-05,
      "loss": 1.042653751373291,
      "num_input_tokens_seen": 18678559424,
      "step": 65670,
      "train_runtime": 639778.3116,
      "train_tokens_per_second": 29195.362
    },
    {
      "epoch": 2.3238870694173244,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8175330296235734e-05,
      "loss": 1.0215051651000977,
      "num_input_tokens_seen": 18681412992,
      "step": 65680,
      "train_runtime": 639876.2104,
      "train_tokens_per_second": 29195.355
    },
    {
      "epoch": 2.324240889681053,
      "grad_norm": 1.5625,
      "learning_rate": 1.8174129597939733e-05,
      "loss": 1.0381223678588867,
      "num_input_tokens_seen": 18684223744,
      "step": 65690,
      "train_runtime": 639971.9146,
      "train_tokens_per_second": 29195.381
    },
    {
      "epoch": 2.324594709944782,
      "grad_norm": 1.6796875,
      "learning_rate": 1.8172929137573813e-05,
      "loss": 1.0431167602539062,
      "num_input_tokens_seen": 18687058176,
      "step": 65700,
      "train_runtime": 640070.6064,
      "train_tokens_per_second": 29195.308
    },
    {
      "epoch": 2.324948530208511,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8171728915059404e-05,
      "loss": 1.0456758499145509,
      "num_input_tokens_seen": 18689947136,
      "step": 65710,
      "train_runtime": 640169.7904,
      "train_tokens_per_second": 29195.297
    },
    {
      "epoch": 2.3253023504722394,
      "grad_norm": 1.5859375,
      "learning_rate": 1.817052893031798e-05,
      "loss": 1.0348082542419434,
      "num_input_tokens_seen": 18692801856,
      "step": 65720,
      "train_runtime": 640265.5766,
      "train_tokens_per_second": 29195.388
    },
    {
      "epoch": 2.3256561707359684,
      "grad_norm": 1.5546875,
      "learning_rate": 1.816932918327103e-05,
      "loss": 1.0332138061523437,
      "num_input_tokens_seen": 18695612672,
      "step": 65730,
      "train_runtime": 640361.4709,
      "train_tokens_per_second": 29195.405
    },
    {
      "epoch": 2.326009990999697,
      "grad_norm": 1.609375,
      "learning_rate": 1.8168129673840103e-05,
      "loss": 1.0494257926940918,
      "num_input_tokens_seen": 18698471744,
      "step": 65740,
      "train_runtime": 640459.3339,
      "train_tokens_per_second": 29195.408
    },
    {
      "epoch": 2.326363811263426,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8166930401946775e-05,
      "loss": 1.0381599426269532,
      "num_input_tokens_seen": 18701272576,
      "step": 65750,
      "train_runtime": 640552.5318,
      "train_tokens_per_second": 29195.533
    },
    {
      "epoch": 2.3267176315271545,
      "grad_norm": 1.640625,
      "learning_rate": 1.816573136751265e-05,
      "loss": 1.038637065887451,
      "num_input_tokens_seen": 18704139328,
      "step": 65760,
      "train_runtime": 640648.7868,
      "train_tokens_per_second": 29195.621
    },
    {
      "epoch": 2.3270714517908835,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8164532570459383e-05,
      "loss": 1.0320422172546386,
      "num_input_tokens_seen": 18707006848,
      "step": 65770,
      "train_runtime": 640746.4757,
      "train_tokens_per_second": 29195.645
    },
    {
      "epoch": 2.327425272054612,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8163334010708654e-05,
      "loss": 1.0366893768310548,
      "num_input_tokens_seen": 18709892928,
      "step": 65780,
      "train_runtime": 640844.1234,
      "train_tokens_per_second": 29195.7
    },
    {
      "epoch": 2.327779092318341,
      "grad_norm": 1.6484375,
      "learning_rate": 1.8162135688182183e-05,
      "loss": 1.0350963592529296,
      "num_input_tokens_seen": 18712777408,
      "step": 65790,
      "train_runtime": 640942.7868,
      "train_tokens_per_second": 29195.706
    },
    {
      "epoch": 2.3281329125820696,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8160937602801726e-05,
      "loss": 1.020425796508789,
      "num_input_tokens_seen": 18715626432,
      "step": 65800,
      "train_runtime": 641041.0764,
      "train_tokens_per_second": 29195.674
    },
    {
      "epoch": 2.3284867328457985,
      "grad_norm": 1.59375,
      "learning_rate": 1.815973975448908e-05,
      "loss": 1.031758689880371,
      "num_input_tokens_seen": 18718445888,
      "step": 65810,
      "train_runtime": 641137.455,
      "train_tokens_per_second": 29195.683
    },
    {
      "epoch": 2.328840553109527,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8158542143166065e-05,
      "loss": 1.020189094543457,
      "num_input_tokens_seen": 18721253184,
      "step": 65820,
      "train_runtime": 641232.9577,
      "train_tokens_per_second": 29195.713
    },
    {
      "epoch": 2.329194373373256,
      "grad_norm": 1.59375,
      "learning_rate": 1.8157344768754553e-05,
      "loss": 1.040908432006836,
      "num_input_tokens_seen": 18724112320,
      "step": 65830,
      "train_runtime": 641330.5112,
      "train_tokens_per_second": 29195.73
    },
    {
      "epoch": 2.3295481936369846,
      "grad_norm": 1.625,
      "learning_rate": 1.8156147631176442e-05,
      "loss": 1.0478226661682128,
      "num_input_tokens_seen": 18726930880,
      "step": 65840,
      "train_runtime": 641424.883,
      "train_tokens_per_second": 29195.829
    },
    {
      "epoch": 2.3299020139007136,
      "grad_norm": 1.6171875,
      "learning_rate": 1.815495073035367e-05,
      "loss": 1.046358299255371,
      "num_input_tokens_seen": 18729769408,
      "step": 65850,
      "train_runtime": 641521.5589,
      "train_tokens_per_second": 29195.853
    },
    {
      "epoch": 2.3302558341644426,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8153754066208205e-05,
      "loss": 1.0229454040527344,
      "num_input_tokens_seen": 18732633152,
      "step": 65860,
      "train_runtime": 641618.6648,
      "train_tokens_per_second": 29195.898
    },
    {
      "epoch": 2.330609654428171,
      "grad_norm": 1.53125,
      "learning_rate": 1.815255763866206e-05,
      "loss": 1.0375890731811523,
      "num_input_tokens_seen": 18735486784,
      "step": 65870,
      "train_runtime": 641716.5318,
      "train_tokens_per_second": 29195.892
    },
    {
      "epoch": 2.3309634746919,
      "grad_norm": 1.5703125,
      "learning_rate": 1.815136144763728e-05,
      "loss": 1.028489112854004,
      "num_input_tokens_seen": 18738361472,
      "step": 65880,
      "train_runtime": 641816.0087,
      "train_tokens_per_second": 29195.846
    },
    {
      "epoch": 2.3313172949556287,
      "grad_norm": 1.6171875,
      "learning_rate": 1.815016549305594e-05,
      "loss": 1.0424678802490235,
      "num_input_tokens_seen": 18741237696,
      "step": 65890,
      "train_runtime": 641918.2448,
      "train_tokens_per_second": 29195.677
    },
    {
      "epoch": 2.3316711152193577,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8148969774840164e-05,
      "loss": 1.024123764038086,
      "num_input_tokens_seen": 18744061760,
      "step": 65900,
      "train_runtime": 642011.4367,
      "train_tokens_per_second": 29195.838
    },
    {
      "epoch": 2.332024935483086,
      "grad_norm": 1.6171875,
      "learning_rate": 1.81477742929121e-05,
      "loss": 1.0257047653198241,
      "num_input_tokens_seen": 18746900800,
      "step": 65910,
      "train_runtime": 642106.8929,
      "train_tokens_per_second": 29195.919
    },
    {
      "epoch": 2.332378755746815,
      "grad_norm": 1.703125,
      "learning_rate": 1.8146579047193934e-05,
      "loss": 1.0409255027770996,
      "num_input_tokens_seen": 18749736960,
      "step": 65920,
      "train_runtime": 642201.8331,
      "train_tokens_per_second": 29196.019
    },
    {
      "epoch": 2.3327325760105437,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8145384037607897e-05,
      "loss": 1.0407175064086913,
      "num_input_tokens_seen": 18752535488,
      "step": 65930,
      "train_runtime": 642296.1034,
      "train_tokens_per_second": 29196.091
    },
    {
      "epoch": 2.3330863962742727,
      "grad_norm": 1.625,
      "learning_rate": 1.814418926407624e-05,
      "loss": 1.0438365936279297,
      "num_input_tokens_seen": 18755344768,
      "step": 65940,
      "train_runtime": 642393.2608,
      "train_tokens_per_second": 29196.048
    },
    {
      "epoch": 2.3334402165380013,
      "grad_norm": 1.6640625,
      "learning_rate": 1.814299472652127e-05,
      "loss": 1.03980712890625,
      "num_input_tokens_seen": 18758153088,
      "step": 65950,
      "train_runtime": 642488.0,
      "train_tokens_per_second": 29196.114
    },
    {
      "epoch": 2.3337940368017303,
      "grad_norm": 1.59375,
      "learning_rate": 1.8141800424865312e-05,
      "loss": 1.035262680053711,
      "num_input_tokens_seen": 18761029760,
      "step": 65960,
      "train_runtime": 642590.1055,
      "train_tokens_per_second": 29195.952
    },
    {
      "epoch": 2.334147857065459,
      "grad_norm": 1.75,
      "learning_rate": 1.814060635903073e-05,
      "loss": 1.04500093460083,
      "num_input_tokens_seen": 18763859392,
      "step": 65970,
      "train_runtime": 642686.2129,
      "train_tokens_per_second": 29195.989
    },
    {
      "epoch": 2.334501677329188,
      "grad_norm": 1.5625,
      "learning_rate": 1.8139412528939936e-05,
      "loss": 1.049753761291504,
      "num_input_tokens_seen": 18766739456,
      "step": 65980,
      "train_runtime": 642783.3253,
      "train_tokens_per_second": 29196.058
    },
    {
      "epoch": 2.3348554975929163,
      "grad_norm": 1.59375,
      "learning_rate": 1.8138218934515365e-05,
      "loss": 1.0277958869934083,
      "num_input_tokens_seen": 18769582080,
      "step": 65990,
      "train_runtime": 642877.9403,
      "train_tokens_per_second": 29196.183
    },
    {
      "epoch": 2.3352093178566453,
      "grad_norm": 1.5625,
      "learning_rate": 1.8137025575679486e-05,
      "loss": 1.0216602325439452,
      "num_input_tokens_seen": 18772463872,
      "step": 66000,
      "train_runtime": 642979.1397,
      "train_tokens_per_second": 29196.07
    },
    {
      "epoch": 2.3355631381203743,
      "grad_norm": 1.578125,
      "learning_rate": 1.8135832452354816e-05,
      "loss": 1.0328174591064454,
      "num_input_tokens_seen": 18775306816,
      "step": 66010,
      "train_runtime": 643078.4375,
      "train_tokens_per_second": 29195.983
    },
    {
      "epoch": 2.335916958384103,
      "grad_norm": 1.53125,
      "learning_rate": 1.8134639564463902e-05,
      "loss": 1.040322494506836,
      "num_input_tokens_seen": 18778154816,
      "step": 66020,
      "train_runtime": 643173.499,
      "train_tokens_per_second": 29196.095
    },
    {
      "epoch": 2.3362707786478314,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8133446911929316e-05,
      "loss": 1.023731803894043,
      "num_input_tokens_seen": 18781012096,
      "step": 66030,
      "train_runtime": 643272.2242,
      "train_tokens_per_second": 29196.056
    },
    {
      "epoch": 2.3366245989115604,
      "grad_norm": 1.59375,
      "learning_rate": 1.813225449467369e-05,
      "loss": 1.0389450073242188,
      "num_input_tokens_seen": 18783775872,
      "step": 66040,
      "train_runtime": 643365.4979,
      "train_tokens_per_second": 29196.119
    },
    {
      "epoch": 2.3369784191752894,
      "grad_norm": 1.65625,
      "learning_rate": 1.8131062312619663e-05,
      "loss": 1.0501955032348633,
      "num_input_tokens_seen": 18786629696,
      "step": 66050,
      "train_runtime": 643464.5788,
      "train_tokens_per_second": 29196.059
    },
    {
      "epoch": 2.337332239439018,
      "grad_norm": 1.6640625,
      "learning_rate": 1.8129870365689933e-05,
      "loss": 1.0326604843139648,
      "num_input_tokens_seen": 18789471104,
      "step": 66060,
      "train_runtime": 643562.8102,
      "train_tokens_per_second": 29196.018
    },
    {
      "epoch": 2.337686059702747,
      "grad_norm": 1.609375,
      "learning_rate": 1.812867865380722e-05,
      "loss": 1.020165252685547,
      "num_input_tokens_seen": 18792219776,
      "step": 66070,
      "train_runtime": 643652.4786,
      "train_tokens_per_second": 29196.221
    },
    {
      "epoch": 2.3380398799664754,
      "grad_norm": 1.59375,
      "learning_rate": 1.8127487176894286e-05,
      "loss": 1.0396703720092773,
      "num_input_tokens_seen": 18795002688,
      "step": 66080,
      "train_runtime": 643747.0621,
      "train_tokens_per_second": 29196.254
    },
    {
      "epoch": 2.3383937002302044,
      "grad_norm": 1.578125,
      "learning_rate": 1.8126295934873926e-05,
      "loss": 1.035307025909424,
      "num_input_tokens_seen": 18797805056,
      "step": 66090,
      "train_runtime": 643841.9735,
      "train_tokens_per_second": 29196.303
    },
    {
      "epoch": 2.338747520493933,
      "grad_norm": 1.65625,
      "learning_rate": 1.8125104927668964e-05,
      "loss": 1.032102108001709,
      "num_input_tokens_seen": 18800643456,
      "step": 66100,
      "train_runtime": 643940.389,
      "train_tokens_per_second": 29196.248
    },
    {
      "epoch": 2.339101340757662,
      "grad_norm": 1.484375,
      "learning_rate": 1.8123914155202273e-05,
      "loss": 1.0147523880004883,
      "num_input_tokens_seen": 18803516992,
      "step": 66110,
      "train_runtime": 644040.1525,
      "train_tokens_per_second": 29196.187
    },
    {
      "epoch": 2.3394551610213905,
      "grad_norm": 1.578125,
      "learning_rate": 1.8122723617396757e-05,
      "loss": 1.0244878768920898,
      "num_input_tokens_seen": 18806350144,
      "step": 66120,
      "train_runtime": 644137.6248,
      "train_tokens_per_second": 29196.168
    },
    {
      "epoch": 2.3398089812851195,
      "grad_norm": 1.671875,
      "learning_rate": 1.8121533314175345e-05,
      "loss": 1.029740810394287,
      "num_input_tokens_seen": 18809254528,
      "step": 66130,
      "train_runtime": 644236.2757,
      "train_tokens_per_second": 29196.205
    },
    {
      "epoch": 2.340162801548848,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8120343245461015e-05,
      "loss": 1.043163776397705,
      "num_input_tokens_seen": 18812083584,
      "step": 66140,
      "train_runtime": 644331.3163,
      "train_tokens_per_second": 29196.289
    },
    {
      "epoch": 2.340516621812577,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8119153411176775e-05,
      "loss": 1.0486584663391114,
      "num_input_tokens_seen": 18814965056,
      "step": 66150,
      "train_runtime": 644429.8956,
      "train_tokens_per_second": 29196.295
    },
    {
      "epoch": 2.3408704420763056,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8117963811245663e-05,
      "loss": 1.0507564544677734,
      "num_input_tokens_seen": 18817774016,
      "step": 66160,
      "train_runtime": 644526.9889,
      "train_tokens_per_second": 29196.255
    },
    {
      "epoch": 2.3412242623400346,
      "grad_norm": 1.640625,
      "learning_rate": 1.8116774445590763e-05,
      "loss": 1.0382383346557618,
      "num_input_tokens_seen": 18820576064,
      "step": 66170,
      "train_runtime": 644621.1616,
      "train_tokens_per_second": 29196.336
    },
    {
      "epoch": 2.341578082603763,
      "grad_norm": 1.5078125,
      "learning_rate": 1.811558531413519e-05,
      "loss": 1.0310840606689453,
      "num_input_tokens_seen": 18823359872,
      "step": 66180,
      "train_runtime": 644716.0792,
      "train_tokens_per_second": 29196.356
    },
    {
      "epoch": 2.341931902867492,
      "grad_norm": 1.5625,
      "learning_rate": 1.8114396416802094e-05,
      "loss": 1.0374882698059082,
      "num_input_tokens_seen": 18826234368,
      "step": 66190,
      "train_runtime": 644815.258,
      "train_tokens_per_second": 29196.323
    },
    {
      "epoch": 2.342285723131221,
      "grad_norm": 1.59375,
      "learning_rate": 1.8113207753514652e-05,
      "loss": 1.0533061027526855,
      "num_input_tokens_seen": 18829086336,
      "step": 66200,
      "train_runtime": 644912.1594,
      "train_tokens_per_second": 29196.358
    },
    {
      "epoch": 2.3426395433949496,
      "grad_norm": 1.546875,
      "learning_rate": 1.8112019324196088e-05,
      "loss": 1.0432257652282715,
      "num_input_tokens_seen": 18831936704,
      "step": 66210,
      "train_runtime": 645008.9355,
      "train_tokens_per_second": 29196.397
    },
    {
      "epoch": 2.3429933636586786,
      "grad_norm": 1.5859375,
      "learning_rate": 1.811083112876966e-05,
      "loss": 1.0352489471435546,
      "num_input_tokens_seen": 18834722496,
      "step": 66220,
      "train_runtime": 645101.8027,
      "train_tokens_per_second": 29196.512
    },
    {
      "epoch": 2.343347183922407,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8109643167158653e-05,
      "loss": 1.0364683151245118,
      "num_input_tokens_seen": 18837561088,
      "step": 66230,
      "train_runtime": 645198.9444,
      "train_tokens_per_second": 29196.516
    },
    {
      "epoch": 2.343701004186136,
      "grad_norm": 1.59375,
      "learning_rate": 1.8108455439286402e-05,
      "loss": 1.0390121459960937,
      "num_input_tokens_seen": 18840350976,
      "step": 66240,
      "train_runtime": 645291.9406,
      "train_tokens_per_second": 29196.631
    },
    {
      "epoch": 2.3440548244498647,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8107267945076254e-05,
      "loss": 1.0240438461303711,
      "num_input_tokens_seen": 18843199936,
      "step": 66250,
      "train_runtime": 645389.6554,
      "train_tokens_per_second": 29196.625
    },
    {
      "epoch": 2.3444086447135937,
      "grad_norm": 1.5703125,
      "learning_rate": 1.810608068445162e-05,
      "loss": 1.040040874481201,
      "num_input_tokens_seen": 18846032704,
      "step": 66260,
      "train_runtime": 645483.8665,
      "train_tokens_per_second": 29196.753
    },
    {
      "epoch": 2.344762464977322,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8104893657335918e-05,
      "loss": 1.037527084350586,
      "num_input_tokens_seen": 18848898560,
      "step": 66270,
      "train_runtime": 645581.4065,
      "train_tokens_per_second": 29196.78
    },
    {
      "epoch": 2.345116285241051,
      "grad_norm": 1.5625,
      "learning_rate": 1.810370686365262e-05,
      "loss": 1.0184425354003905,
      "num_input_tokens_seen": 18851771072,
      "step": 66280,
      "train_runtime": 645681.6215,
      "train_tokens_per_second": 29196.698
    },
    {
      "epoch": 2.3454701055047797,
      "grad_norm": 1.546875,
      "learning_rate": 1.810252030332523e-05,
      "loss": 1.0474827766418457,
      "num_input_tokens_seen": 18854587648,
      "step": 66290,
      "train_runtime": 645778.3523,
      "train_tokens_per_second": 29196.686
    },
    {
      "epoch": 2.3458239257685087,
      "grad_norm": 1.609375,
      "learning_rate": 1.8101333976277282e-05,
      "loss": 1.029682731628418,
      "num_input_tokens_seen": 18857386176,
      "step": 66300,
      "train_runtime": 645874.1707,
      "train_tokens_per_second": 29196.687
    },
    {
      "epoch": 2.3461777460322373,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8100147882432346e-05,
      "loss": 1.029153537750244,
      "num_input_tokens_seen": 18860248448,
      "step": 66310,
      "train_runtime": 645973.1312,
      "train_tokens_per_second": 29196.645
    },
    {
      "epoch": 2.3465315662959663,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8098962021714032e-05,
      "loss": 1.0405263900756836,
      "num_input_tokens_seen": 18863064320,
      "step": 66320,
      "train_runtime": 646069.5021,
      "train_tokens_per_second": 29196.649
    },
    {
      "epoch": 2.346885386559695,
      "grad_norm": 1.578125,
      "learning_rate": 1.8097776394045977e-05,
      "loss": 1.0277963638305665,
      "num_input_tokens_seen": 18865859712,
      "step": 66330,
      "train_runtime": 646162.6569,
      "train_tokens_per_second": 29196.766
    },
    {
      "epoch": 2.347239206823424,
      "grad_norm": 1.59375,
      "learning_rate": 1.8096590999351865e-05,
      "loss": 1.0426666259765625,
      "num_input_tokens_seen": 18868693952,
      "step": 66340,
      "train_runtime": 646257.9765,
      "train_tokens_per_second": 29196.845
    },
    {
      "epoch": 2.347593027087153,
      "grad_norm": 1.6640625,
      "learning_rate": 1.8095405837555397e-05,
      "loss": 1.0357634544372558,
      "num_input_tokens_seen": 18871519552,
      "step": 66350,
      "train_runtime": 646356.8167,
      "train_tokens_per_second": 29196.752
    },
    {
      "epoch": 2.3479468473508813,
      "grad_norm": 1.578125,
      "learning_rate": 1.809422090858033e-05,
      "loss": 1.043788528442383,
      "num_input_tokens_seen": 18874326400,
      "step": 66360,
      "train_runtime": 646455.939,
      "train_tokens_per_second": 29196.617
    },
    {
      "epoch": 2.3483006676146103,
      "grad_norm": 1.625,
      "learning_rate": 1.809303621235044e-05,
      "loss": 1.0341991424560546,
      "num_input_tokens_seen": 18877182784,
      "step": 66370,
      "train_runtime": 646555.3948,
      "train_tokens_per_second": 29196.544
    },
    {
      "epoch": 2.348654487878339,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8091851748789548e-05,
      "loss": 1.0270216941833497,
      "num_input_tokens_seen": 18880003776,
      "step": 66380,
      "train_runtime": 646652.3715,
      "train_tokens_per_second": 29196.528
    },
    {
      "epoch": 2.349008308142068,
      "grad_norm": 1.6015625,
      "learning_rate": 1.80906675178215e-05,
      "loss": 1.0425743103027343,
      "num_input_tokens_seen": 18882870144,
      "step": 66390,
      "train_runtime": 646749.584,
      "train_tokens_per_second": 29196.571
    },
    {
      "epoch": 2.3493621284057964,
      "grad_norm": 1.59375,
      "learning_rate": 1.808948351937018e-05,
      "loss": 1.0361618041992187,
      "num_input_tokens_seen": 18885742848,
      "step": 66400,
      "train_runtime": 646849.9212,
      "train_tokens_per_second": 29196.483
    },
    {
      "epoch": 2.3497159486695254,
      "grad_norm": 1.5625,
      "learning_rate": 1.808829975335952e-05,
      "loss": 1.030990219116211,
      "num_input_tokens_seen": 18888581888,
      "step": 66410,
      "train_runtime": 646946.2284,
      "train_tokens_per_second": 29196.525
    },
    {
      "epoch": 2.350069768933254,
      "grad_norm": 1.6796875,
      "learning_rate": 1.8087116219713467e-05,
      "loss": 1.0359463691711426,
      "num_input_tokens_seen": 18891465728,
      "step": 66420,
      "train_runtime": 647048.0298,
      "train_tokens_per_second": 29196.389
    },
    {
      "epoch": 2.350423589196983,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8085932918356015e-05,
      "loss": 1.051318359375,
      "num_input_tokens_seen": 18894308736,
      "step": 66430,
      "train_runtime": 647144.238,
      "train_tokens_per_second": 29196.441
    },
    {
      "epoch": 2.3507774094607115,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8084749849211188e-05,
      "loss": 1.0455533981323242,
      "num_input_tokens_seen": 18897165888,
      "step": 66440,
      "train_runtime": 647239.3283,
      "train_tokens_per_second": 29196.566
    },
    {
      "epoch": 2.3511312297244404,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8083567012203052e-05,
      "loss": 1.0394617080688477,
      "num_input_tokens_seen": 18900017216,
      "step": 66450,
      "train_runtime": 647338.7275,
      "train_tokens_per_second": 29196.488
    },
    {
      "epoch": 2.351485049988169,
      "grad_norm": 1.59375,
      "learning_rate": 1.808238440725569e-05,
      "loss": 1.0177885055541993,
      "num_input_tokens_seen": 18902877056,
      "step": 66460,
      "train_runtime": 647435.7274,
      "train_tokens_per_second": 29196.531
    },
    {
      "epoch": 2.351838870251898,
      "grad_norm": 1.6640625,
      "learning_rate": 1.8081202034293245e-05,
      "loss": 1.0389205932617187,
      "num_input_tokens_seen": 18905723136,
      "step": 66470,
      "train_runtime": 647533.761,
      "train_tokens_per_second": 29196.506
    },
    {
      "epoch": 2.3521926905156265,
      "grad_norm": 1.6484375,
      "learning_rate": 1.808001989323987e-05,
      "loss": 1.0428040504455567,
      "num_input_tokens_seen": 18908575936,
      "step": 66480,
      "train_runtime": 647630.0863,
      "train_tokens_per_second": 29196.568
    },
    {
      "epoch": 2.3525465107793555,
      "grad_norm": 1.6484375,
      "learning_rate": 1.807883798401978e-05,
      "loss": 1.039106559753418,
      "num_input_tokens_seen": 18911356288,
      "step": 66490,
      "train_runtime": 647723.3112,
      "train_tokens_per_second": 29196.658
    },
    {
      "epoch": 2.3529003310430845,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8077656306557196e-05,
      "loss": 1.0409401893615722,
      "num_input_tokens_seen": 18914208448,
      "step": 66500,
      "train_runtime": 647822.2523,
      "train_tokens_per_second": 29196.602
    },
    {
      "epoch": 2.353254151306813,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8076474860776387e-05,
      "loss": 1.029317569732666,
      "num_input_tokens_seen": 18917053952,
      "step": 66510,
      "train_runtime": 647918.529,
      "train_tokens_per_second": 29196.655
    },
    {
      "epoch": 2.3536079715705416,
      "grad_norm": 1.640625,
      "learning_rate": 1.807529364660166e-05,
      "loss": 1.0431474685668944,
      "num_input_tokens_seen": 18919881536,
      "step": 66520,
      "train_runtime": 648016.9299,
      "train_tokens_per_second": 29196.585
    },
    {
      "epoch": 2.3539617918342706,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8074112663957353e-05,
      "loss": 1.0420499801635743,
      "num_input_tokens_seen": 18922675456,
      "step": 66530,
      "train_runtime": 648111.354,
      "train_tokens_per_second": 29196.642
    },
    {
      "epoch": 2.3543156120979996,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8072931912767843e-05,
      "loss": 1.0233688354492188,
      "num_input_tokens_seen": 18925517760,
      "step": 66540,
      "train_runtime": 648207.9246,
      "train_tokens_per_second": 29196.678
    },
    {
      "epoch": 2.354669432361728,
      "grad_norm": 1.5859375,
      "learning_rate": 1.807175139295753e-05,
      "loss": 1.0185602188110352,
      "num_input_tokens_seen": 18928376128,
      "step": 66550,
      "train_runtime": 648308.2607,
      "train_tokens_per_second": 29196.568
    },
    {
      "epoch": 2.355023252625457,
      "grad_norm": 1.5625,
      "learning_rate": 1.8070571104450855e-05,
      "loss": 1.0308652877807618,
      "num_input_tokens_seen": 18931240256,
      "step": 66560,
      "train_runtime": 648408.7066,
      "train_tokens_per_second": 29196.462
    },
    {
      "epoch": 2.3553770728891856,
      "grad_norm": 1.65625,
      "learning_rate": 1.8069391047172297e-05,
      "loss": 1.0437036514282227,
      "num_input_tokens_seen": 18934033152,
      "step": 66570,
      "train_runtime": 648503.4193,
      "train_tokens_per_second": 29196.505
    },
    {
      "epoch": 2.3557308931529146,
      "grad_norm": 1.640625,
      "learning_rate": 1.8068211221046367e-05,
      "loss": 1.0314538955688477,
      "num_input_tokens_seen": 18936829376,
      "step": 66580,
      "train_runtime": 648597.0876,
      "train_tokens_per_second": 29196.599
    },
    {
      "epoch": 2.356084713416643,
      "grad_norm": 1.578125,
      "learning_rate": 1.8067031625997616e-05,
      "loss": 1.0379018783569336,
      "num_input_tokens_seen": 18939639552,
      "step": 66590,
      "train_runtime": 648690.9219,
      "train_tokens_per_second": 29196.708
    },
    {
      "epoch": 2.356438533680372,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8065852261950612e-05,
      "loss": 1.0267288208007812,
      "num_input_tokens_seen": 18942461440,
      "step": 66600,
      "train_runtime": 648785.5521,
      "train_tokens_per_second": 29196.799
    },
    {
      "epoch": 2.3567923539441007,
      "grad_norm": 1.59375,
      "learning_rate": 1.8064673128829977e-05,
      "loss": 1.0454681396484375,
      "num_input_tokens_seen": 18945258304,
      "step": 66610,
      "train_runtime": 648879.3854,
      "train_tokens_per_second": 29196.887
    },
    {
      "epoch": 2.3571461742078297,
      "grad_norm": 1.5625,
      "learning_rate": 1.8063494226560355e-05,
      "loss": 1.0351696014404297,
      "num_input_tokens_seen": 18948082688,
      "step": 66620,
      "train_runtime": 648974.5438,
      "train_tokens_per_second": 29196.958
    },
    {
      "epoch": 2.3574999944715582,
      "grad_norm": 1.5078125,
      "learning_rate": 1.8062315555066432e-05,
      "loss": 1.039164161682129,
      "num_input_tokens_seen": 18950908864,
      "step": 66630,
      "train_runtime": 649069.6508,
      "train_tokens_per_second": 29197.034
    },
    {
      "epoch": 2.357853814735287,
      "grad_norm": 1.5625,
      "learning_rate": 1.8061137114272934e-05,
      "loss": 1.039458656311035,
      "num_input_tokens_seen": 18953769920,
      "step": 66640,
      "train_runtime": 649168.4708,
      "train_tokens_per_second": 29196.997
    },
    {
      "epoch": 2.3582076349990158,
      "grad_norm": 1.59375,
      "learning_rate": 1.8059958904104592e-05,
      "loss": 1.0271575927734375,
      "num_input_tokens_seen": 18956558976,
      "step": 66650,
      "train_runtime": 649260.235,
      "train_tokens_per_second": 29197.166
    },
    {
      "epoch": 2.3585614552627447,
      "grad_norm": 1.5625,
      "learning_rate": 1.8058780924486212e-05,
      "loss": 1.0409416198730468,
      "num_input_tokens_seen": 18959454272,
      "step": 66660,
      "train_runtime": 649361.4199,
      "train_tokens_per_second": 29197.075
    },
    {
      "epoch": 2.3589152755264733,
      "grad_norm": 1.5625,
      "learning_rate": 1.8057603175342603e-05,
      "loss": 1.02748384475708,
      "num_input_tokens_seen": 18962273984,
      "step": 66670,
      "train_runtime": 649456.9257,
      "train_tokens_per_second": 29197.123
    },
    {
      "epoch": 2.3592690957902023,
      "grad_norm": 1.5,
      "learning_rate": 1.8056425656598623e-05,
      "loss": 1.0309016227722168,
      "num_input_tokens_seen": 18965111808,
      "step": 66680,
      "train_runtime": 649551.811,
      "train_tokens_per_second": 29197.227
    },
    {
      "epoch": 2.3596229160539313,
      "grad_norm": 1.6875,
      "learning_rate": 1.805524836817916e-05,
      "loss": 1.045396900177002,
      "num_input_tokens_seen": 18967973248,
      "step": 66690,
      "train_runtime": 649651.3816,
      "train_tokens_per_second": 29197.157
    },
    {
      "epoch": 2.35997673631766,
      "grad_norm": 1.59375,
      "learning_rate": 1.8054071310009144e-05,
      "loss": 1.0322769165039063,
      "num_input_tokens_seen": 18970783296,
      "step": 66700,
      "train_runtime": 649748.2691,
      "train_tokens_per_second": 29197.128
    },
    {
      "epoch": 2.360330556581389,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8052894482013526e-05,
      "loss": 1.027587890625,
      "num_input_tokens_seen": 18973634560,
      "step": 66710,
      "train_runtime": 649847.2571,
      "train_tokens_per_second": 29197.068
    },
    {
      "epoch": 2.3606843768451173,
      "grad_norm": 1.65625,
      "learning_rate": 1.80517178841173e-05,
      "loss": 1.0380279541015625,
      "num_input_tokens_seen": 18976445888,
      "step": 66720,
      "train_runtime": 649942.126,
      "train_tokens_per_second": 29197.132
    },
    {
      "epoch": 2.3610381971088463,
      "grad_norm": 1.6015625,
      "learning_rate": 1.805054151624549e-05,
      "loss": 1.0326272010803224,
      "num_input_tokens_seen": 18979350976,
      "step": 66730,
      "train_runtime": 650042.8997,
      "train_tokens_per_second": 29197.075
    },
    {
      "epoch": 2.361392017372575,
      "grad_norm": 1.59375,
      "learning_rate": 1.8049365378323154e-05,
      "loss": 1.034350299835205,
      "num_input_tokens_seen": 18982182400,
      "step": 66740,
      "train_runtime": 650139.5881,
      "train_tokens_per_second": 29197.087
    },
    {
      "epoch": 2.361745837636304,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8048189470275397e-05,
      "loss": 1.0354164123535157,
      "num_input_tokens_seen": 18985068800,
      "step": 66750,
      "train_runtime": 650236.9692,
      "train_tokens_per_second": 29197.154
    },
    {
      "epoch": 2.3620996579000324,
      "grad_norm": 1.5859375,
      "learning_rate": 1.804701379202734e-05,
      "loss": 1.0331238746643066,
      "num_input_tokens_seen": 18987914560,
      "step": 66760,
      "train_runtime": 650334.6872,
      "train_tokens_per_second": 29197.143
    },
    {
      "epoch": 2.3624534781637614,
      "grad_norm": 1.5859375,
      "learning_rate": 1.8045838343504142e-05,
      "loss": 1.0215399742126465,
      "num_input_tokens_seen": 18990767360,
      "step": 66770,
      "train_runtime": 650432.3966,
      "train_tokens_per_second": 29197.142
    },
    {
      "epoch": 2.36280729842749,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8044663124631007e-05,
      "loss": 1.0403265953063965,
      "num_input_tokens_seen": 18993610112,
      "step": 66780,
      "train_runtime": 650532.5794,
      "train_tokens_per_second": 29197.016
    },
    {
      "epoch": 2.363161118691219,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8043488135333166e-05,
      "loss": 1.0225337982177733,
      "num_input_tokens_seen": 18996413312,
      "step": 66790,
      "train_runtime": 650627.8264,
      "train_tokens_per_second": 29197.05
    },
    {
      "epoch": 2.3635149389549475,
      "grad_norm": 1.59375,
      "learning_rate": 1.804231337553588e-05,
      "loss": 1.0296518325805664,
      "num_input_tokens_seen": 18999240960,
      "step": 66800,
      "train_runtime": 650723.9082,
      "train_tokens_per_second": 29197.085
    },
    {
      "epoch": 2.3638687592186765,
      "grad_norm": 1.5703125,
      "learning_rate": 1.804113884516445e-05,
      "loss": 1.0442829132080078,
      "num_input_tokens_seen": 19002115392,
      "step": 66810,
      "train_runtime": 650820.8181,
      "train_tokens_per_second": 29197.154
    },
    {
      "epoch": 2.364222579482405,
      "grad_norm": 1.5546875,
      "learning_rate": 1.803996454414421e-05,
      "loss": 1.0412076950073241,
      "num_input_tokens_seen": 19004939456,
      "step": 66820,
      "train_runtime": 650916.0735,
      "train_tokens_per_second": 29197.219
    },
    {
      "epoch": 2.364576399746134,
      "grad_norm": 1.578125,
      "learning_rate": 1.803879047240052e-05,
      "loss": 1.0318403244018555,
      "num_input_tokens_seen": 19007806976,
      "step": 66830,
      "train_runtime": 651015.3563,
      "train_tokens_per_second": 29197.171
    },
    {
      "epoch": 2.364930220009863,
      "grad_norm": 1.6171875,
      "learning_rate": 1.8037616629858794e-05,
      "loss": 1.0364686012268067,
      "num_input_tokens_seen": 19010648704,
      "step": 66840,
      "train_runtime": 651113.5774,
      "train_tokens_per_second": 29197.131
    },
    {
      "epoch": 2.3652840402735915,
      "grad_norm": 1.5859375,
      "learning_rate": 1.803644301644446e-05,
      "loss": 1.0440656661987304,
      "num_input_tokens_seen": 19013491520,
      "step": 66850,
      "train_runtime": 651206.6687,
      "train_tokens_per_second": 29197.323
    },
    {
      "epoch": 2.36563786053732,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8035269632082984e-05,
      "loss": 1.0359214782714843,
      "num_input_tokens_seen": 19016368320,
      "step": 66860,
      "train_runtime": 651306.7548,
      "train_tokens_per_second": 29197.253
    },
    {
      "epoch": 2.365991680801049,
      "grad_norm": 1.671875,
      "learning_rate": 1.8034096476699873e-05,
      "loss": 1.0434577941894532,
      "num_input_tokens_seen": 19019231680,
      "step": 66870,
      "train_runtime": 651406.2693,
      "train_tokens_per_second": 29197.189
    },
    {
      "epoch": 2.366345501064778,
      "grad_norm": 1.5390625,
      "learning_rate": 1.8032923550220667e-05,
      "loss": 1.01727294921875,
      "num_input_tokens_seen": 19022032128,
      "step": 66880,
      "train_runtime": 651502.5852,
      "train_tokens_per_second": 29197.171
    },
    {
      "epoch": 2.3666993213285066,
      "grad_norm": 1.6015625,
      "learning_rate": 1.803175085257093e-05,
      "loss": 1.0339614868164062,
      "num_input_tokens_seen": 19024924416,
      "step": 66890,
      "train_runtime": 651603.1515,
      "train_tokens_per_second": 29197.103
    },
    {
      "epoch": 2.3670531415922356,
      "grad_norm": 1.5546875,
      "learning_rate": 1.8030578383676272e-05,
      "loss": 1.0255003929138184,
      "num_input_tokens_seen": 19027770240,
      "step": 66900,
      "train_runtime": 651702.3915,
      "train_tokens_per_second": 29197.024
    },
    {
      "epoch": 2.367406961855964,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8029406143462326e-05,
      "loss": 1.0408638000488282,
      "num_input_tokens_seen": 19030609344,
      "step": 66910,
      "train_runtime": 651799.1937,
      "train_tokens_per_second": 29197.043
    },
    {
      "epoch": 2.367760782119693,
      "grad_norm": 1.5703125,
      "learning_rate": 1.8028234131854774e-05,
      "loss": 1.0262052536010742,
      "num_input_tokens_seen": 19033486464,
      "step": 66920,
      "train_runtime": 651896.7173,
      "train_tokens_per_second": 29197.089
    },
    {
      "epoch": 2.3681146023834216,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8027062348779313e-05,
      "loss": 1.0260032653808593,
      "num_input_tokens_seen": 19036277568,
      "step": 66930,
      "train_runtime": 651992.7925,
      "train_tokens_per_second": 29197.067
    },
    {
      "epoch": 2.3684684226471506,
      "grad_norm": 1.609375,
      "learning_rate": 1.802589079416168e-05,
      "loss": 1.034390640258789,
      "num_input_tokens_seen": 19039119552,
      "step": 66940,
      "train_runtime": 652086.3326,
      "train_tokens_per_second": 29197.238
    },
    {
      "epoch": 2.368822242910879,
      "grad_norm": 1.53125,
      "learning_rate": 1.8024719467927664e-05,
      "loss": 1.046706199645996,
      "num_input_tokens_seen": 19042012416,
      "step": 66950,
      "train_runtime": 652189.349,
      "train_tokens_per_second": 29197.061
    },
    {
      "epoch": 2.369176063174608,
      "grad_norm": 1.6328125,
      "learning_rate": 1.8023548370003062e-05,
      "loss": 1.0305341720581054,
      "num_input_tokens_seen": 19044805184,
      "step": 66960,
      "train_runtime": 652283.1316,
      "train_tokens_per_second": 29197.145
    },
    {
      "epoch": 2.3695298834383367,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8022377500313714e-05,
      "loss": 1.0341482162475586,
      "num_input_tokens_seen": 19047623872,
      "step": 66970,
      "train_runtime": 652377.8243,
      "train_tokens_per_second": 29197.228
    },
    {
      "epoch": 2.3698837037020657,
      "grad_norm": 1.609375,
      "learning_rate": 1.80212068587855e-05,
      "loss": 1.0355841636657714,
      "num_input_tokens_seen": 19050525824,
      "step": 66980,
      "train_runtime": 652478.1365,
      "train_tokens_per_second": 29197.186
    },
    {
      "epoch": 2.3702375239657942,
      "grad_norm": 1.53125,
      "learning_rate": 1.8020036445344325e-05,
      "loss": 1.0338769912719727,
      "num_input_tokens_seen": 19053351168,
      "step": 66990,
      "train_runtime": 652575.2165,
      "train_tokens_per_second": 29197.173
    },
    {
      "epoch": 2.3705913442295232,
      "grad_norm": 1.609375,
      "learning_rate": 1.8018866259916134e-05,
      "loss": 1.0486441612243653,
      "num_input_tokens_seen": 19056236480,
      "step": 67000,
      "train_runtime": 652673.154,
      "train_tokens_per_second": 29197.212
    },
    {
      "epoch": 2.3709451644932518,
      "grad_norm": 1.53125,
      "learning_rate": 1.8017696302426904e-05,
      "loss": 1.0326087951660157,
      "num_input_tokens_seen": 19059105792,
      "step": 67010,
      "train_runtime": 652770.8836,
      "train_tokens_per_second": 29197.236
    },
    {
      "epoch": 2.3712989847569808,
      "grad_norm": 1.6484375,
      "learning_rate": 1.801652657280264e-05,
      "loss": 1.0221431732177735,
      "num_input_tokens_seen": 19061936128,
      "step": 67020,
      "train_runtime": 652866.6296,
      "train_tokens_per_second": 29197.29
    },
    {
      "epoch": 2.3716528050207097,
      "grad_norm": 1.65625,
      "learning_rate": 1.8015357070969387e-05,
      "loss": 1.0389217376708983,
      "num_input_tokens_seen": 19064763584,
      "step": 67030,
      "train_runtime": 652962.8654,
      "train_tokens_per_second": 29197.317
    },
    {
      "epoch": 2.3720066252844383,
      "grad_norm": 1.59375,
      "learning_rate": 1.801418779685323e-05,
      "loss": 1.0314453125,
      "num_input_tokens_seen": 19067641472,
      "step": 67040,
      "train_runtime": 653060.3314,
      "train_tokens_per_second": 29197.366
    },
    {
      "epoch": 2.3723604455481673,
      "grad_norm": 1.65625,
      "learning_rate": 1.8013018750380265e-05,
      "loss": 1.0375774383544922,
      "num_input_tokens_seen": 19070533248,
      "step": 67050,
      "train_runtime": 653161.6294,
      "train_tokens_per_second": 29197.265
    },
    {
      "epoch": 2.372714265811896,
      "grad_norm": 1.625,
      "learning_rate": 1.8011849931476647e-05,
      "loss": 1.0497207641601562,
      "num_input_tokens_seen": 19073411136,
      "step": 67060,
      "train_runtime": 653262.0769,
      "train_tokens_per_second": 29197.181
    },
    {
      "epoch": 2.373068086075625,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8010681340068548e-05,
      "loss": 1.0245656013488769,
      "num_input_tokens_seen": 19076215360,
      "step": 67070,
      "train_runtime": 653360.5327,
      "train_tokens_per_second": 29197.073
    },
    {
      "epoch": 2.3734219063393533,
      "grad_norm": 1.5546875,
      "learning_rate": 1.800951297608218e-05,
      "loss": 1.0293115615844726,
      "num_input_tokens_seen": 19079047936,
      "step": 67080,
      "train_runtime": 653455.2711,
      "train_tokens_per_second": 29197.175
    },
    {
      "epoch": 2.3737757266030823,
      "grad_norm": 1.609375,
      "learning_rate": 1.8008344839443795e-05,
      "loss": 1.0224365234375,
      "num_input_tokens_seen": 19081876416,
      "step": 67090,
      "train_runtime": 653553.1131,
      "train_tokens_per_second": 29197.132
    },
    {
      "epoch": 2.374129546866811,
      "grad_norm": 1.578125,
      "learning_rate": 1.8007176930079663e-05,
      "loss": 1.0180472373962401,
      "num_input_tokens_seen": 19084723968,
      "step": 67100,
      "train_runtime": 653648.1577,
      "train_tokens_per_second": 29197.243
    },
    {
      "epoch": 2.37448336713054,
      "grad_norm": 1.5625,
      "learning_rate": 1.8006009247916096e-05,
      "loss": 1.0434990882873536,
      "num_input_tokens_seen": 19087596672,
      "step": 67110,
      "train_runtime": 653745.6756,
      "train_tokens_per_second": 29197.282
    },
    {
      "epoch": 2.3748371873942684,
      "grad_norm": 1.546875,
      "learning_rate": 1.800484179287944e-05,
      "loss": 1.0326407432556153,
      "num_input_tokens_seen": 19090493248,
      "step": 67120,
      "train_runtime": 653846.0876,
      "train_tokens_per_second": 29197.228
    },
    {
      "epoch": 2.3751910076579974,
      "grad_norm": 1.6015625,
      "learning_rate": 1.8003674564896075e-05,
      "loss": 1.0351058006286622,
      "num_input_tokens_seen": 19093306240,
      "step": 67130,
      "train_runtime": 653941.1002,
      "train_tokens_per_second": 29197.287
    },
    {
      "epoch": 2.375544827921726,
      "grad_norm": 1.625,
      "learning_rate": 1.8002507563892413e-05,
      "loss": 1.0301342010498047,
      "num_input_tokens_seen": 19096105600,
      "step": 67140,
      "train_runtime": 654035.0945,
      "train_tokens_per_second": 29197.371
    },
    {
      "epoch": 2.375898648185455,
      "grad_norm": 1.578125,
      "learning_rate": 1.8001340789794895e-05,
      "loss": 1.056152629852295,
      "num_input_tokens_seen": 19098944000,
      "step": 67150,
      "train_runtime": 654132.1336,
      "train_tokens_per_second": 29197.379
    },
    {
      "epoch": 2.3762524684491835,
      "grad_norm": 1.6171875,
      "learning_rate": 1.800017424253001e-05,
      "loss": 1.028088092803955,
      "num_input_tokens_seen": 19101779264,
      "step": 67160,
      "train_runtime": 654233.0662,
      "train_tokens_per_second": 29197.209
    },
    {
      "epoch": 2.3766062887129125,
      "grad_norm": 1.671875,
      "learning_rate": 1.7999007922024254e-05,
      "loss": 1.0408269882202148,
      "num_input_tokens_seen": 19104616576,
      "step": 67170,
      "train_runtime": 654328.5876,
      "train_tokens_per_second": 29197.282
    },
    {
      "epoch": 2.3769601089766415,
      "grad_norm": 1.578125,
      "learning_rate": 1.7997841828204185e-05,
      "loss": 1.0332897186279297,
      "num_input_tokens_seen": 19107457088,
      "step": 67180,
      "train_runtime": 654424.1293,
      "train_tokens_per_second": 29197.36
    },
    {
      "epoch": 2.37731392924037,
      "grad_norm": 1.640625,
      "learning_rate": 1.799667596099638e-05,
      "loss": 1.0439233779907227,
      "num_input_tokens_seen": 19110291264,
      "step": 67190,
      "train_runtime": 654519.0102,
      "train_tokens_per_second": 29197.458
    },
    {
      "epoch": 2.3776677495040985,
      "grad_norm": 1.625,
      "learning_rate": 1.7995510320327445e-05,
      "loss": 1.02845458984375,
      "num_input_tokens_seen": 19113143040,
      "step": 67200,
      "train_runtime": 654615.0857,
      "train_tokens_per_second": 29197.529
    },
    {
      "epoch": 2.3780215697678275,
      "grad_norm": 1.5234375,
      "learning_rate": 1.7994344906124028e-05,
      "loss": 1.0471319198608398,
      "num_input_tokens_seen": 19115954752,
      "step": 67210,
      "train_runtime": 654713.8126,
      "train_tokens_per_second": 29197.421
    },
    {
      "epoch": 2.3783753900315565,
      "grad_norm": 1.6796875,
      "learning_rate": 1.799317971831281e-05,
      "loss": 1.04210205078125,
      "num_input_tokens_seen": 19118786944,
      "step": 67220,
      "train_runtime": 654811.2055,
      "train_tokens_per_second": 29197.403
    },
    {
      "epoch": 2.378729210295285,
      "grad_norm": 1.6171875,
      "learning_rate": 1.79920147568205e-05,
      "loss": 1.0325956344604492,
      "num_input_tokens_seen": 19121651968,
      "step": 67230,
      "train_runtime": 654909.9473,
      "train_tokens_per_second": 29197.376
    },
    {
      "epoch": 2.379083030559014,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7990850021573845e-05,
      "loss": 1.0383377075195312,
      "num_input_tokens_seen": 19124483200,
      "step": 67240,
      "train_runtime": 655006.4261,
      "train_tokens_per_second": 29197.398
    },
    {
      "epoch": 2.3794368508227426,
      "grad_norm": 1.5625,
      "learning_rate": 1.798968551249962e-05,
      "loss": 1.0416743278503418,
      "num_input_tokens_seen": 19127322624,
      "step": 67250,
      "train_runtime": 655103.1187,
      "train_tokens_per_second": 29197.423
    },
    {
      "epoch": 2.3797906710864716,
      "grad_norm": 1.59375,
      "learning_rate": 1.7988521229524637e-05,
      "loss": 1.0380262374877929,
      "num_input_tokens_seen": 19130141760,
      "step": 67260,
      "train_runtime": 655196.8306,
      "train_tokens_per_second": 29197.549
    },
    {
      "epoch": 2.3801444913502,
      "grad_norm": 1.609375,
      "learning_rate": 1.7987357172575745e-05,
      "loss": 1.032976245880127,
      "num_input_tokens_seen": 19132988224,
      "step": 67270,
      "train_runtime": 655294.388,
      "train_tokens_per_second": 29197.546
    },
    {
      "epoch": 2.380498311613929,
      "grad_norm": 1.65625,
      "learning_rate": 1.7986193341579814e-05,
      "loss": 1.0309293746948243,
      "num_input_tokens_seen": 19135846528,
      "step": 67280,
      "train_runtime": 655392.6776,
      "train_tokens_per_second": 29197.529
    },
    {
      "epoch": 2.3808521318776577,
      "grad_norm": 1.65625,
      "learning_rate": 1.7985029736463757e-05,
      "loss": 1.0364151000976562,
      "num_input_tokens_seen": 19138757312,
      "step": 67290,
      "train_runtime": 655497.2608,
      "train_tokens_per_second": 29197.311
    },
    {
      "epoch": 2.3812059521413866,
      "grad_norm": 1.625,
      "learning_rate": 1.798386635715452e-05,
      "loss": 1.0323609352111816,
      "num_input_tokens_seen": 19141531136,
      "step": 67300,
      "train_runtime": 655589.4322,
      "train_tokens_per_second": 29197.437
    },
    {
      "epoch": 2.381559772405115,
      "grad_norm": 1.6171875,
      "learning_rate": 1.798270320357908e-05,
      "loss": 1.0205324172973633,
      "num_input_tokens_seen": 19144349440,
      "step": 67310,
      "train_runtime": 655687.8085,
      "train_tokens_per_second": 29197.355
    },
    {
      "epoch": 2.381913592668844,
      "grad_norm": 1.546875,
      "learning_rate": 1.7981540275664447e-05,
      "loss": 1.030990982055664,
      "num_input_tokens_seen": 19147203008,
      "step": 67320,
      "train_runtime": 655784.5304,
      "train_tokens_per_second": 29197.4
    },
    {
      "epoch": 2.382267412932573,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7980377573337658e-05,
      "loss": 1.0355592727661134,
      "num_input_tokens_seen": 19150074432,
      "step": 67330,
      "train_runtime": 655882.3867,
      "train_tokens_per_second": 29197.421
    },
    {
      "epoch": 2.3826212331963017,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7979215096525794e-05,
      "loss": 1.042961597442627,
      "num_input_tokens_seen": 19152964736,
      "step": 67340,
      "train_runtime": 655981.2613,
      "train_tokens_per_second": 29197.427
    },
    {
      "epoch": 2.3829750534600302,
      "grad_norm": 1.5625,
      "learning_rate": 1.7978052845155965e-05,
      "loss": 1.0270118713378906,
      "num_input_tokens_seen": 19155801792,
      "step": 67350,
      "train_runtime": 656080.0164,
      "train_tokens_per_second": 29197.356
    },
    {
      "epoch": 2.3833288737237592,
      "grad_norm": 1.6640625,
      "learning_rate": 1.797689081915531e-05,
      "loss": 1.0278014183044433,
      "num_input_tokens_seen": 19158648192,
      "step": 67360,
      "train_runtime": 656177.656,
      "train_tokens_per_second": 29197.349
    },
    {
      "epoch": 2.383682693987488,
      "grad_norm": 1.59375,
      "learning_rate": 1.7975729018451004e-05,
      "loss": 1.0376891136169433,
      "num_input_tokens_seen": 19161527488,
      "step": 67370,
      "train_runtime": 656279.8353,
      "train_tokens_per_second": 29197.191
    },
    {
      "epoch": 2.3840365142512168,
      "grad_norm": 1.65625,
      "learning_rate": 1.7974567442970254e-05,
      "loss": 1.0438356399536133,
      "num_input_tokens_seen": 19164337920,
      "step": 67380,
      "train_runtime": 656374.2644,
      "train_tokens_per_second": 29197.272
    },
    {
      "epoch": 2.3843903345149458,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7973406092640308e-05,
      "loss": 1.0472169876098634,
      "num_input_tokens_seen": 19167200960,
      "step": 67390,
      "train_runtime": 656473.8766,
      "train_tokens_per_second": 29197.203
    },
    {
      "epoch": 2.3847441547786743,
      "grad_norm": 1.5625,
      "learning_rate": 1.797224496738843e-05,
      "loss": 1.030417251586914,
      "num_input_tokens_seen": 19170035712,
      "step": 67400,
      "train_runtime": 656572.4514,
      "train_tokens_per_second": 29197.137
    },
    {
      "epoch": 2.3850979750424033,
      "grad_norm": 1.609375,
      "learning_rate": 1.797108406714193e-05,
      "loss": 1.030099582672119,
      "num_input_tokens_seen": 19172876992,
      "step": 67410,
      "train_runtime": 656669.4133,
      "train_tokens_per_second": 29197.152
    },
    {
      "epoch": 2.385451795306132,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7969923391828146e-05,
      "loss": 1.0458013534545898,
      "num_input_tokens_seen": 19175719744,
      "step": 67420,
      "train_runtime": 656765.5594,
      "train_tokens_per_second": 29197.207
    },
    {
      "epoch": 2.385805615569861,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7968762941374456e-05,
      "loss": 1.0360552787780761,
      "num_input_tokens_seen": 19178526016,
      "step": 67430,
      "train_runtime": 656863.1307,
      "train_tokens_per_second": 29197.142
    },
    {
      "epoch": 2.3861594358335894,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7967602715708257e-05,
      "loss": 1.0375307083129883,
      "num_input_tokens_seen": 19181360832,
      "step": 67440,
      "train_runtime": 656959.0015,
      "train_tokens_per_second": 29197.196
    },
    {
      "epoch": 2.3865132560973183,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7966442714756992e-05,
      "loss": 1.0304872512817382,
      "num_input_tokens_seen": 19184188736,
      "step": 67450,
      "train_runtime": 657053.9462,
      "train_tokens_per_second": 29197.281
    },
    {
      "epoch": 2.386867076361047,
      "grad_norm": 1.640625,
      "learning_rate": 1.7965282938448134e-05,
      "loss": 1.0263973236083985,
      "num_input_tokens_seen": 19186973888,
      "step": 67460,
      "train_runtime": 657145.5575,
      "train_tokens_per_second": 29197.449
    },
    {
      "epoch": 2.387220896624776,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7964123386709175e-05,
      "loss": 1.035407829284668,
      "num_input_tokens_seen": 19189801984,
      "step": 67470,
      "train_runtime": 657241.2974,
      "train_tokens_per_second": 29197.499
    },
    {
      "epoch": 2.3875747168885044,
      "grad_norm": 1.640625,
      "learning_rate": 1.796296405946766e-05,
      "loss": 1.0412323951721192,
      "num_input_tokens_seen": 19192624448,
      "step": 67480,
      "train_runtime": 657335.597,
      "train_tokens_per_second": 29197.604
    },
    {
      "epoch": 2.3879285371522334,
      "grad_norm": 1.6015625,
      "learning_rate": 1.796180495665116e-05,
      "loss": 1.0300722122192383,
      "num_input_tokens_seen": 19195485120,
      "step": 67490,
      "train_runtime": 657433.3285,
      "train_tokens_per_second": 29197.615
    },
    {
      "epoch": 2.388282357415962,
      "grad_norm": 1.5859375,
      "learning_rate": 1.796064607818727e-05,
      "loss": 1.0262359619140624,
      "num_input_tokens_seen": 19198248000,
      "step": 67500,
      "train_runtime": 657528.5922,
      "train_tokens_per_second": 29197.587
    },
    {
      "epoch": 2.388636177679691,
      "grad_norm": 1.625,
      "learning_rate": 1.795948742400363e-05,
      "loss": 1.0323685646057128,
      "num_input_tokens_seen": 19201038656,
      "step": 67510,
      "train_runtime": 657621.6356,
      "train_tokens_per_second": 29197.699
    },
    {
      "epoch": 2.38898999794342,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7958328994027903e-05,
      "loss": 1.0443204879760741,
      "num_input_tokens_seen": 19203872192,
      "step": 67520,
      "train_runtime": 657715.2283,
      "train_tokens_per_second": 29197.852
    },
    {
      "epoch": 2.3893438182071485,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7957170788187792e-05,
      "loss": 1.0398640632629395,
      "num_input_tokens_seen": 19206691648,
      "step": 67530,
      "train_runtime": 657810.682,
      "train_tokens_per_second": 29197.902
    },
    {
      "epoch": 2.3896976384708775,
      "grad_norm": 1.6796875,
      "learning_rate": 1.7956012806411028e-05,
      "loss": 1.0244104385375976,
      "num_input_tokens_seen": 19209527552,
      "step": 67540,
      "train_runtime": 657912.4778,
      "train_tokens_per_second": 29197.695
    },
    {
      "epoch": 2.390051458734606,
      "grad_norm": 1.65625,
      "learning_rate": 1.795485504862537e-05,
      "loss": 1.0277759552001953,
      "num_input_tokens_seen": 19212346624,
      "step": 67550,
      "train_runtime": 658008.9791,
      "train_tokens_per_second": 29197.697
    },
    {
      "epoch": 2.390405278998335,
      "grad_norm": 1.5625,
      "learning_rate": 1.795369751475862e-05,
      "loss": 1.037470245361328,
      "num_input_tokens_seen": 19215182976,
      "step": 67560,
      "train_runtime": 658104.3592,
      "train_tokens_per_second": 29197.775
    },
    {
      "epoch": 2.3907590992620635,
      "grad_norm": 1.703125,
      "learning_rate": 1.795254020473861e-05,
      "loss": 1.042388343811035,
      "num_input_tokens_seen": 19218037120,
      "step": 67570,
      "train_runtime": 658203.5453,
      "train_tokens_per_second": 29197.711
    },
    {
      "epoch": 2.3911129195257925,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7951383118493203e-05,
      "loss": 1.0339637756347657,
      "num_input_tokens_seen": 19220905088,
      "step": 67580,
      "train_runtime": 658306.0829,
      "train_tokens_per_second": 29197.52
    },
    {
      "epoch": 2.391466739789521,
      "grad_norm": 1.6015625,
      "learning_rate": 1.795022625595029e-05,
      "loss": 1.025121021270752,
      "num_input_tokens_seen": 19223711296,
      "step": 67590,
      "train_runtime": 658401.0061,
      "train_tokens_per_second": 29197.573
    },
    {
      "epoch": 2.39182056005325,
      "grad_norm": 1.59375,
      "learning_rate": 1.79490696170378e-05,
      "loss": 1.0445737838745117,
      "num_input_tokens_seen": 19226493888,
      "step": 67600,
      "train_runtime": 658493.7162,
      "train_tokens_per_second": 29197.688
    },
    {
      "epoch": 2.3921743803169786,
      "grad_norm": 1.625,
      "learning_rate": 1.79479132016837e-05,
      "loss": 1.0409154891967773,
      "num_input_tokens_seen": 19229300800,
      "step": 67610,
      "train_runtime": 658587.2065,
      "train_tokens_per_second": 29197.805
    },
    {
      "epoch": 2.3925282005807076,
      "grad_norm": 1.625,
      "learning_rate": 1.794675700981597e-05,
      "loss": 1.0388486862182618,
      "num_input_tokens_seen": 19232120256,
      "step": 67620,
      "train_runtime": 658685.4374,
      "train_tokens_per_second": 29197.731
    },
    {
      "epoch": 2.392882020844436,
      "grad_norm": 1.6015625,
      "learning_rate": 1.794560104136264e-05,
      "loss": 1.040609645843506,
      "num_input_tokens_seen": 19234951936,
      "step": 67630,
      "train_runtime": 658780.1504,
      "train_tokens_per_second": 29197.832
    },
    {
      "epoch": 2.393235841108165,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7944445296251776e-05,
      "loss": 1.0288999557495118,
      "num_input_tokens_seen": 19237797504,
      "step": 67640,
      "train_runtime": 658878.1588,
      "train_tokens_per_second": 29197.807
    },
    {
      "epoch": 2.3935896613718937,
      "grad_norm": 1.578125,
      "learning_rate": 1.794328977441146e-05,
      "loss": 1.0368385314941406,
      "num_input_tokens_seen": 19240642304,
      "step": 67650,
      "train_runtime": 658973.43,
      "train_tokens_per_second": 29197.903
    },
    {
      "epoch": 2.3939434816356226,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7942134475769813e-05,
      "loss": 1.0347375869750977,
      "num_input_tokens_seen": 19243497152,
      "step": 67660,
      "train_runtime": 659074.1903,
      "train_tokens_per_second": 29197.771
    },
    {
      "epoch": 2.3942973018993516,
      "grad_norm": 1.6875,
      "learning_rate": 1.794097940025499e-05,
      "loss": 1.020726776123047,
      "num_input_tokens_seen": 19246382720,
      "step": 67670,
      "train_runtime": 659173.894,
      "train_tokens_per_second": 29197.732
    },
    {
      "epoch": 2.39465112216308,
      "grad_norm": 1.65625,
      "learning_rate": 1.7939824547795183e-05,
      "loss": 1.037057590484619,
      "num_input_tokens_seen": 19249216896,
      "step": 67680,
      "train_runtime": 659269.5959,
      "train_tokens_per_second": 29197.793
    },
    {
      "epoch": 2.3950049424268087,
      "grad_norm": 1.609375,
      "learning_rate": 1.793866991831861e-05,
      "loss": 1.0411869049072267,
      "num_input_tokens_seen": 19252052992,
      "step": 67690,
      "train_runtime": 659362.9019,
      "train_tokens_per_second": 29197.962
    },
    {
      "epoch": 2.3953587626905377,
      "grad_norm": 1.6484375,
      "learning_rate": 1.793751551175352e-05,
      "loss": 1.0219942092895509,
      "num_input_tokens_seen": 19254910272,
      "step": 67700,
      "train_runtime": 659458.9297,
      "train_tokens_per_second": 29198.043
    },
    {
      "epoch": 2.3957125829542667,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7936361328028196e-05,
      "loss": 1.026258659362793,
      "num_input_tokens_seen": 19257707904,
      "step": 67710,
      "train_runtime": 659551.3324,
      "train_tokens_per_second": 29198.194
    },
    {
      "epoch": 2.3960664032179952,
      "grad_norm": 1.5625,
      "learning_rate": 1.7935207367070964e-05,
      "loss": 1.0348807334899903,
      "num_input_tokens_seen": 19260580096,
      "step": 67720,
      "train_runtime": 659649.0679,
      "train_tokens_per_second": 29198.222
    },
    {
      "epoch": 2.3964202234817242,
      "grad_norm": 1.6015625,
      "learning_rate": 1.793405362881016e-05,
      "loss": 1.0370976448059082,
      "num_input_tokens_seen": 19263461888,
      "step": 67730,
      "train_runtime": 659748.9445,
      "train_tokens_per_second": 29198.17
    },
    {
      "epoch": 2.3967740437454528,
      "grad_norm": 1.5625,
      "learning_rate": 1.7932900113174182e-05,
      "loss": 1.0424583435058594,
      "num_input_tokens_seen": 19266301248,
      "step": 67740,
      "train_runtime": 659845.2618,
      "train_tokens_per_second": 29198.211
    },
    {
      "epoch": 2.3971278640091818,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7931746820091423e-05,
      "loss": 1.0405729293823243,
      "num_input_tokens_seen": 19269187200,
      "step": 67750,
      "train_runtime": 659946.6246,
      "train_tokens_per_second": 29198.099
    },
    {
      "epoch": 2.3974816842729103,
      "grad_norm": 1.609375,
      "learning_rate": 1.793059374949034e-05,
      "loss": 1.0329941749572753,
      "num_input_tokens_seen": 19272044224,
      "step": 67760,
      "train_runtime": 660043.9187,
      "train_tokens_per_second": 29198.124
    },
    {
      "epoch": 2.3978355045366393,
      "grad_norm": 1.546875,
      "learning_rate": 1.7929440901299405e-05,
      "loss": 1.0383519172668456,
      "num_input_tokens_seen": 19274895168,
      "step": 67770,
      "train_runtime": 660140.7281,
      "train_tokens_per_second": 29198.161
    },
    {
      "epoch": 2.398189324800368,
      "grad_norm": 1.59375,
      "learning_rate": 1.7928288275447135e-05,
      "loss": 1.0262335777282714,
      "num_input_tokens_seen": 19277718016,
      "step": 67780,
      "train_runtime": 660237.4754,
      "train_tokens_per_second": 29198.158
    },
    {
      "epoch": 2.398543145064097,
      "grad_norm": 1.578125,
      "learning_rate": 1.792713587186207e-05,
      "loss": 1.0466070175170898,
      "num_input_tokens_seen": 19280601024,
      "step": 67790,
      "train_runtime": 660337.81,
      "train_tokens_per_second": 29198.087
    },
    {
      "epoch": 2.3988969653278254,
      "grad_norm": 1.609375,
      "learning_rate": 1.7925983690472782e-05,
      "loss": 1.0523872375488281,
      "num_input_tokens_seen": 19283403200,
      "step": 67800,
      "train_runtime": 660432.2045,
      "train_tokens_per_second": 29198.157
    },
    {
      "epoch": 2.3992507855915544,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7924831731207873e-05,
      "loss": 1.0378917694091796,
      "num_input_tokens_seen": 19286276032,
      "step": 67810,
      "train_runtime": 660532.0786,
      "train_tokens_per_second": 29198.091
    },
    {
      "epoch": 2.399604605855283,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7923679993995988e-05,
      "loss": 1.0290794372558594,
      "num_input_tokens_seen": 19289053632,
      "step": 67820,
      "train_runtime": 660624.4159,
      "train_tokens_per_second": 29198.215
    },
    {
      "epoch": 2.399958426119012,
      "grad_norm": 1.65625,
      "learning_rate": 1.79225284787658e-05,
      "loss": 1.0453547477722167,
      "num_input_tokens_seen": 19291869760,
      "step": 67830,
      "train_runtime": 660719.7503,
      "train_tokens_per_second": 29198.264
    },
    {
      "epoch": 2.4003122463827404,
      "grad_norm": 1.65625,
      "learning_rate": 1.7921377185446003e-05,
      "loss": 1.0173507690429688,
      "num_input_tokens_seen": 19294748224,
      "step": 67840,
      "train_runtime": 660820.0753,
      "train_tokens_per_second": 29198.187
    },
    {
      "epoch": 2.4006660666464694,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7920226113965338e-05,
      "loss": 1.043630599975586,
      "num_input_tokens_seen": 19297604224,
      "step": 67850,
      "train_runtime": 660917.2079,
      "train_tokens_per_second": 29198.217
    },
    {
      "epoch": 2.4010198869101984,
      "grad_norm": 1.6171875,
      "learning_rate": 1.791907526425257e-05,
      "loss": 1.0321243286132813,
      "num_input_tokens_seen": 19300442624,
      "step": 67860,
      "train_runtime": 661014.7546,
      "train_tokens_per_second": 29198.202
    },
    {
      "epoch": 2.401373707173927,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7917924636236495e-05,
      "loss": 1.0487638473510743,
      "num_input_tokens_seen": 19303286912,
      "step": 67870,
      "train_runtime": 661111.9982,
      "train_tokens_per_second": 29198.21
    },
    {
      "epoch": 2.401727527437656,
      "grad_norm": 1.609375,
      "learning_rate": 1.7916774229845944e-05,
      "loss": 1.0420937538146973,
      "num_input_tokens_seen": 19306127872,
      "step": 67880,
      "train_runtime": 661209.6237,
      "train_tokens_per_second": 29198.196
    },
    {
      "epoch": 2.4020813477013845,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7915624045009787e-05,
      "loss": 1.0452825546264648,
      "num_input_tokens_seen": 19308988352,
      "step": 67890,
      "train_runtime": 661309.9748,
      "train_tokens_per_second": 29198.09
    },
    {
      "epoch": 2.4024351679651135,
      "grad_norm": 1.65625,
      "learning_rate": 1.791447408165691e-05,
      "loss": 1.044661521911621,
      "num_input_tokens_seen": 19311830400,
      "step": 67900,
      "train_runtime": 661406.7861,
      "train_tokens_per_second": 29198.113
    },
    {
      "epoch": 2.402788988228842,
      "grad_norm": 1.578125,
      "learning_rate": 1.7913324339716244e-05,
      "loss": 1.0360885620117188,
      "num_input_tokens_seen": 19314628096,
      "step": 67910,
      "train_runtime": 661504.7456,
      "train_tokens_per_second": 29198.019
    },
    {
      "epoch": 2.403142808492571,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7912174819116744e-05,
      "loss": 1.044959831237793,
      "num_input_tokens_seen": 19317486464,
      "step": 67920,
      "train_runtime": 661599.9006,
      "train_tokens_per_second": 29198.14
    },
    {
      "epoch": 2.4034966287562995,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7911025519787406e-05,
      "loss": 1.0345386505126952,
      "num_input_tokens_seen": 19320343936,
      "step": 67930,
      "train_runtime": 661698.5436,
      "train_tokens_per_second": 29198.106
    },
    {
      "epoch": 2.4038504490200285,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7909876441657247e-05,
      "loss": 1.0365507125854492,
      "num_input_tokens_seen": 19323255232,
      "step": 67940,
      "train_runtime": 661799.1738,
      "train_tokens_per_second": 29198.065
    },
    {
      "epoch": 2.404204269283757,
      "grad_norm": 1.609375,
      "learning_rate": 1.7908727584655324e-05,
      "loss": 1.0426183700561524,
      "num_input_tokens_seen": 19326011456,
      "step": 67950,
      "train_runtime": 661891.9453,
      "train_tokens_per_second": 29198.137
    },
    {
      "epoch": 2.404558089547486,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7907578948710722e-05,
      "loss": 1.0322011947631835,
      "num_input_tokens_seen": 19328812416,
      "step": 67960,
      "train_runtime": 661986.6681,
      "train_tokens_per_second": 29198.19
    },
    {
      "epoch": 2.4049119098112146,
      "grad_norm": 1.65625,
      "learning_rate": 1.790643053375256e-05,
      "loss": 1.038454818725586,
      "num_input_tokens_seen": 19331645056,
      "step": 67970,
      "train_runtime": 662081.8622,
      "train_tokens_per_second": 29198.27
    },
    {
      "epoch": 2.4052657300749436,
      "grad_norm": 1.5234375,
      "learning_rate": 1.7905282339709987e-05,
      "loss": 1.0464975357055664,
      "num_input_tokens_seen": 19334499904,
      "step": 67980,
      "train_runtime": 662178.4251,
      "train_tokens_per_second": 29198.324
    },
    {
      "epoch": 2.405619550338672,
      "grad_norm": 1.6875,
      "learning_rate": 1.7904134366512183e-05,
      "loss": 1.0257089614868165,
      "num_input_tokens_seen": 19337347840,
      "step": 67990,
      "train_runtime": 662274.4121,
      "train_tokens_per_second": 29198.392
    },
    {
      "epoch": 2.405973370602401,
      "grad_norm": 1.5625,
      "learning_rate": 1.790298661408836e-05,
      "loss": 1.0383018493652343,
      "num_input_tokens_seen": 19340199680,
      "step": 68000,
      "train_runtime": 662369.6484,
      "train_tokens_per_second": 29198.499
    },
    {
      "epoch": 2.40632719086613,
      "grad_norm": 1.578125,
      "learning_rate": 1.7901839082367766e-05,
      "loss": 1.027627944946289,
      "num_input_tokens_seen": 19343053632,
      "step": 68010,
      "train_runtime": 662467.1076,
      "train_tokens_per_second": 29198.512
    },
    {
      "epoch": 2.4066810111298587,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7900691771279682e-05,
      "loss": 1.0331575393676757,
      "num_input_tokens_seen": 19345908864,
      "step": 68020,
      "train_runtime": 662562.808,
      "train_tokens_per_second": 29198.604
    },
    {
      "epoch": 2.407034831393587,
      "grad_norm": 1.5625,
      "learning_rate": 1.7899544680753404e-05,
      "loss": 1.0392854690551758,
      "num_input_tokens_seen": 19348721856,
      "step": 68030,
      "train_runtime": 662659.0464,
      "train_tokens_per_second": 29198.608
    },
    {
      "epoch": 2.407388651657316,
      "grad_norm": 1.6875,
      "learning_rate": 1.7898397810718286e-05,
      "loss": 1.0480867385864259,
      "num_input_tokens_seen": 19351526976,
      "step": 68040,
      "train_runtime": 662756.6154,
      "train_tokens_per_second": 29198.542
    },
    {
      "epoch": 2.407742471921045,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7897251161103693e-05,
      "loss": 1.0350421905517577,
      "num_input_tokens_seen": 19354386368,
      "step": 68050,
      "train_runtime": 662853.7247,
      "train_tokens_per_second": 29198.578
    },
    {
      "epoch": 2.4080962921847737,
      "grad_norm": 1.59375,
      "learning_rate": 1.789610473183903e-05,
      "loss": 1.0397065162658692,
      "num_input_tokens_seen": 19357238848,
      "step": 68060,
      "train_runtime": 662948.7487,
      "train_tokens_per_second": 29198.696
    },
    {
      "epoch": 2.4084501124485027,
      "grad_norm": 1.703125,
      "learning_rate": 1.789495852285373e-05,
      "loss": 1.0351788520812988,
      "num_input_tokens_seen": 19360095936,
      "step": 68070,
      "train_runtime": 663046.6788,
      "train_tokens_per_second": 29198.692
    },
    {
      "epoch": 2.4088039327122313,
      "grad_norm": 1.6796875,
      "learning_rate": 1.789381253407726e-05,
      "loss": 1.0286617279052734,
      "num_input_tokens_seen": 19362983168,
      "step": 68080,
      "train_runtime": 663146.3837,
      "train_tokens_per_second": 29198.656
    },
    {
      "epoch": 2.4091577529759602,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7892666765439117e-05,
      "loss": 1.0390830039978027,
      "num_input_tokens_seen": 19365830400,
      "step": 68090,
      "train_runtime": 663242.114,
      "train_tokens_per_second": 29198.735
    },
    {
      "epoch": 2.409511573239689,
      "grad_norm": 1.53125,
      "learning_rate": 1.789152121686884e-05,
      "loss": 1.0402548789978028,
      "num_input_tokens_seen": 19368627456,
      "step": 68100,
      "train_runtime": 663334.294,
      "train_tokens_per_second": 29198.894
    },
    {
      "epoch": 2.4098653935034178,
      "grad_norm": 1.5703125,
      "learning_rate": 1.789037588829598e-05,
      "loss": 1.0401814460754395,
      "num_input_tokens_seen": 19371494976,
      "step": 68110,
      "train_runtime": 663433.1741,
      "train_tokens_per_second": 29198.864
    },
    {
      "epoch": 2.4102192137671463,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7889230779650135e-05,
      "loss": 1.0371888160705567,
      "num_input_tokens_seen": 19374391936,
      "step": 68120,
      "train_runtime": 663534.7294,
      "train_tokens_per_second": 29198.761
    },
    {
      "epoch": 2.4105730340308753,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7888085890860927e-05,
      "loss": 1.0203709602355957,
      "num_input_tokens_seen": 19377238656,
      "step": 68130,
      "train_runtime": 663631.0346,
      "train_tokens_per_second": 29198.813
    },
    {
      "epoch": 2.410926854294604,
      "grad_norm": 1.5625,
      "learning_rate": 1.7886941221858022e-05,
      "loss": 1.034256362915039,
      "num_input_tokens_seen": 19380071296,
      "step": 68140,
      "train_runtime": 663728.6403,
      "train_tokens_per_second": 29198.787
    },
    {
      "epoch": 2.411280674558333,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7885796772571094e-05,
      "loss": 1.0326120376586914,
      "num_input_tokens_seen": 19382972800,
      "step": 68150,
      "train_runtime": 663830.9672,
      "train_tokens_per_second": 29198.657
    },
    {
      "epoch": 2.411634494822062,
      "grad_norm": 1.71875,
      "learning_rate": 1.788465254292987e-05,
      "loss": 1.03338680267334,
      "num_input_tokens_seen": 19385770304,
      "step": 68160,
      "train_runtime": 663926.8457,
      "train_tokens_per_second": 29198.654
    },
    {
      "epoch": 2.4119883150857904,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7883508532864095e-05,
      "loss": 1.035634708404541,
      "num_input_tokens_seen": 19388657024,
      "step": 68170,
      "train_runtime": 664027.3181,
      "train_tokens_per_second": 29198.583
    },
    {
      "epoch": 2.412342135349519,
      "grad_norm": 1.5625,
      "learning_rate": 1.7882364742303563e-05,
      "loss": 1.0460302352905273,
      "num_input_tokens_seen": 19391486080,
      "step": 68180,
      "train_runtime": 664124.1337,
      "train_tokens_per_second": 29198.587
    },
    {
      "epoch": 2.412695955613248,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7881221171178072e-05,
      "loss": 1.0430177688598632,
      "num_input_tokens_seen": 19394326528,
      "step": 68190,
      "train_runtime": 664220.6156,
      "train_tokens_per_second": 29198.622
    },
    {
      "epoch": 2.413049775876977,
      "grad_norm": 1.609375,
      "learning_rate": 1.7880077819417483e-05,
      "loss": 1.0353623390197755,
      "num_input_tokens_seen": 19397190464,
      "step": 68200,
      "train_runtime": 664318.6907,
      "train_tokens_per_second": 29198.622
    },
    {
      "epoch": 2.4134035961407054,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7878934686951657e-05,
      "loss": 1.041202926635742,
      "num_input_tokens_seen": 19399980352,
      "step": 68210,
      "train_runtime": 664410.8341,
      "train_tokens_per_second": 29198.772
    },
    {
      "epoch": 2.4137574164044344,
      "grad_norm": 1.5390625,
      "learning_rate": 1.787779177371051e-05,
      "loss": 1.0399333000183106,
      "num_input_tokens_seen": 19402815616,
      "step": 68220,
      "train_runtime": 664509.0832,
      "train_tokens_per_second": 29198.721
    },
    {
      "epoch": 2.414111236668163,
      "grad_norm": 1.578125,
      "learning_rate": 1.7876649079623982e-05,
      "loss": 1.0327028274536132,
      "num_input_tokens_seen": 19405657088,
      "step": 68230,
      "train_runtime": 664606.2012,
      "train_tokens_per_second": 29198.73
    },
    {
      "epoch": 2.414465056931892,
      "grad_norm": 1.6640625,
      "learning_rate": 1.787550660462204e-05,
      "loss": 1.0403755187988282,
      "num_input_tokens_seen": 19408556928,
      "step": 68240,
      "train_runtime": 664708.5896,
      "train_tokens_per_second": 29198.595
    },
    {
      "epoch": 2.4148188771956205,
      "grad_norm": 1.59375,
      "learning_rate": 1.7874364348634686e-05,
      "loss": 1.0333271026611328,
      "num_input_tokens_seen": 19411388096,
      "step": 68250,
      "train_runtime": 664803.9917,
      "train_tokens_per_second": 29198.664
    },
    {
      "epoch": 2.4151726974593495,
      "grad_norm": 1.6796875,
      "learning_rate": 1.787322231159196e-05,
      "loss": 1.0401830673217773,
      "num_input_tokens_seen": 19414268544,
      "step": 68260,
      "train_runtime": 664903.1876,
      "train_tokens_per_second": 29198.64
    },
    {
      "epoch": 2.415526517723078,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7872080493423915e-05,
      "loss": 1.0143505096435548,
      "num_input_tokens_seen": 19417073856,
      "step": 68270,
      "train_runtime": 664999.6934,
      "train_tokens_per_second": 29198.621
    },
    {
      "epoch": 2.415880337986807,
      "grad_norm": 1.671875,
      "learning_rate": 1.7870938894060653e-05,
      "loss": 1.03094425201416,
      "num_input_tokens_seen": 19419968512,
      "step": 68280,
      "train_runtime": 665097.7039,
      "train_tokens_per_second": 29198.67
    },
    {
      "epoch": 2.4162341582505356,
      "grad_norm": 1.578125,
      "learning_rate": 1.7869797513432305e-05,
      "loss": 1.0439214706420898,
      "num_input_tokens_seen": 19422819328,
      "step": 68290,
      "train_runtime": 665194.9596,
      "train_tokens_per_second": 29198.687
    },
    {
      "epoch": 2.4165879785142645,
      "grad_norm": 1.5625,
      "learning_rate": 1.7868656351469017e-05,
      "loss": 1.02906494140625,
      "num_input_tokens_seen": 19425674496,
      "step": 68300,
      "train_runtime": 665294.0221,
      "train_tokens_per_second": 29198.631
    },
    {
      "epoch": 2.416941798777993,
      "grad_norm": 1.578125,
      "learning_rate": 1.786751540810099e-05,
      "loss": 1.0496397018432617,
      "num_input_tokens_seen": 19428499456,
      "step": 68310,
      "train_runtime": 665389.9725,
      "train_tokens_per_second": 29198.666
    },
    {
      "epoch": 2.417295619041722,
      "grad_norm": 1.59375,
      "learning_rate": 1.786637468325844e-05,
      "loss": 1.039009952545166,
      "num_input_tokens_seen": 19431315072,
      "step": 68320,
      "train_runtime": 665482.6345,
      "train_tokens_per_second": 29198.831
    },
    {
      "epoch": 2.4176494393054506,
      "grad_norm": 1.65625,
      "learning_rate": 1.786523417687162e-05,
      "loss": 1.0510046005249023,
      "num_input_tokens_seen": 19434190656,
      "step": 68330,
      "train_runtime": 665585.73,
      "train_tokens_per_second": 29198.629
    },
    {
      "epoch": 2.4180032595691796,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7864093888870813e-05,
      "loss": 1.0226861953735351,
      "num_input_tokens_seen": 19437104192,
      "step": 68340,
      "train_runtime": 665691.4448,
      "train_tokens_per_second": 29198.369
    },
    {
      "epoch": 2.4183570798329086,
      "grad_norm": 1.625,
      "learning_rate": 1.7862953819186332e-05,
      "loss": 1.0432785034179688,
      "num_input_tokens_seen": 19439931200,
      "step": 68350,
      "train_runtime": 665789.554,
      "train_tokens_per_second": 29198.312
    },
    {
      "epoch": 2.418710900096637,
      "grad_norm": 1.5625,
      "learning_rate": 1.786181396774852e-05,
      "loss": 1.0352023124694825,
      "num_input_tokens_seen": 19442805888,
      "step": 68360,
      "train_runtime": 665886.0249,
      "train_tokens_per_second": 29198.399
    },
    {
      "epoch": 2.419064720360366,
      "grad_norm": 1.671875,
      "learning_rate": 1.7860674334487757e-05,
      "loss": 1.0329362869262695,
      "num_input_tokens_seen": 19445669952,
      "step": 68370,
      "train_runtime": 665983.8492,
      "train_tokens_per_second": 29198.411
    },
    {
      "epoch": 2.4194185406240947,
      "grad_norm": 1.578125,
      "learning_rate": 1.7859534919334447e-05,
      "loss": 1.025977325439453,
      "num_input_tokens_seen": 19448465280,
      "step": 68380,
      "train_runtime": 666076.3627,
      "train_tokens_per_second": 29198.552
    },
    {
      "epoch": 2.4197723608878237,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7858395722219032e-05,
      "loss": 1.0505538940429688,
      "num_input_tokens_seen": 19451290176,
      "step": 68390,
      "train_runtime": 666172.8782,
      "train_tokens_per_second": 29198.562
    },
    {
      "epoch": 2.420126181151552,
      "grad_norm": 1.640625,
      "learning_rate": 1.7857256743071978e-05,
      "loss": 1.0248251914978028,
      "num_input_tokens_seen": 19454168704,
      "step": 68400,
      "train_runtime": 666273.511,
      "train_tokens_per_second": 29198.472
    },
    {
      "epoch": 2.420480001415281,
      "grad_norm": 1.6171875,
      "learning_rate": 1.785611798182379e-05,
      "loss": 1.0329280853271485,
      "num_input_tokens_seen": 19456994560,
      "step": 68410,
      "train_runtime": 666368.5625,
      "train_tokens_per_second": 29198.548
    },
    {
      "epoch": 2.4208338216790097,
      "grad_norm": 1.625,
      "learning_rate": 1.7854979438405e-05,
      "loss": 1.017113494873047,
      "num_input_tokens_seen": 19459841792,
      "step": 68420,
      "train_runtime": 666463.4686,
      "train_tokens_per_second": 29198.662
    },
    {
      "epoch": 2.4211876419427387,
      "grad_norm": 1.5078125,
      "learning_rate": 1.7853841112746157e-05,
      "loss": 1.0391107559204102,
      "num_input_tokens_seen": 19462673920,
      "step": 68430,
      "train_runtime": 666560.428,
      "train_tokens_per_second": 29198.664
    },
    {
      "epoch": 2.4215414622064673,
      "grad_norm": 1.59375,
      "learning_rate": 1.7852703004777873e-05,
      "loss": 1.0446707725524902,
      "num_input_tokens_seen": 19465500608,
      "step": 68440,
      "train_runtime": 666655.8567,
      "train_tokens_per_second": 29198.724
    },
    {
      "epoch": 2.4218952824701963,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7851565114430764e-05,
      "loss": 1.0335012435913087,
      "num_input_tokens_seen": 19468332288,
      "step": 68450,
      "train_runtime": 666754.5175,
      "train_tokens_per_second": 29198.651
    },
    {
      "epoch": 2.422249102733925,
      "grad_norm": 1.625,
      "learning_rate": 1.7850427441635482e-05,
      "loss": 1.0351312637329102,
      "num_input_tokens_seen": 19471153856,
      "step": 68460,
      "train_runtime": 666849.0598,
      "train_tokens_per_second": 29198.742
    },
    {
      "epoch": 2.422602922997654,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7849289986322723e-05,
      "loss": 1.045156192779541,
      "num_input_tokens_seen": 19473960384,
      "step": 68470,
      "train_runtime": 666943.3888,
      "train_tokens_per_second": 29198.821
    },
    {
      "epoch": 2.4229567432613823,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7848152748423196e-05,
      "loss": 1.0287800788879395,
      "num_input_tokens_seen": 19476810240,
      "step": 68480,
      "train_runtime": 667041.4239,
      "train_tokens_per_second": 29198.802
    },
    {
      "epoch": 2.4233105635251113,
      "grad_norm": 1.5703125,
      "learning_rate": 1.784701572786765e-05,
      "loss": 1.048683261871338,
      "num_input_tokens_seen": 19479679872,
      "step": 68490,
      "train_runtime": 667137.2271,
      "train_tokens_per_second": 29198.91
    },
    {
      "epoch": 2.4236643837888403,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7845878924586875e-05,
      "loss": 1.0333450317382813,
      "num_input_tokens_seen": 19482488192,
      "step": 68500,
      "train_runtime": 667231.9014,
      "train_tokens_per_second": 29198.976
    },
    {
      "epoch": 2.424018204052569,
      "grad_norm": 1.59375,
      "learning_rate": 1.7844742338511663e-05,
      "loss": 1.0348918914794922,
      "num_input_tokens_seen": 19485348736,
      "step": 68510,
      "train_runtime": 667331.2738,
      "train_tokens_per_second": 29198.914
    },
    {
      "epoch": 2.4243720243162974,
      "grad_norm": 1.609375,
      "learning_rate": 1.7843605969572865e-05,
      "loss": 1.0312030792236329,
      "num_input_tokens_seen": 19488182592,
      "step": 68520,
      "train_runtime": 667427.6793,
      "train_tokens_per_second": 29198.943
    },
    {
      "epoch": 2.4247258445800264,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7842469817701354e-05,
      "loss": 1.0313251495361329,
      "num_input_tokens_seen": 19491078592,
      "step": 68530,
      "train_runtime": 667526.9319,
      "train_tokens_per_second": 29198.94
    },
    {
      "epoch": 2.4250796648437554,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7841333882828033e-05,
      "loss": 1.0276253700256348,
      "num_input_tokens_seen": 19493887616,
      "step": 68540,
      "train_runtime": 667623.7942,
      "train_tokens_per_second": 29198.911
    },
    {
      "epoch": 2.425433485107484,
      "grad_norm": 1.6875,
      "learning_rate": 1.7840198164883827e-05,
      "loss": 1.035160732269287,
      "num_input_tokens_seen": 19496733952,
      "step": 68550,
      "train_runtime": 667719.3575,
      "train_tokens_per_second": 29198.995
    },
    {
      "epoch": 2.425787305371213,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7839062663799703e-05,
      "loss": 1.0562235832214355,
      "num_input_tokens_seen": 19499576576,
      "step": 68560,
      "train_runtime": 667817.7979,
      "train_tokens_per_second": 29198.947
    },
    {
      "epoch": 2.4261411256349414,
      "grad_norm": 1.65625,
      "learning_rate": 1.7837927379506662e-05,
      "loss": 1.0372554779052734,
      "num_input_tokens_seen": 19502451520,
      "step": 68570,
      "train_runtime": 667915.0204,
      "train_tokens_per_second": 29199.001
    },
    {
      "epoch": 2.4264949458986704,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7836792311935722e-05,
      "loss": 1.0365077018737794,
      "num_input_tokens_seen": 19505334848,
      "step": 68580,
      "train_runtime": 668015.5075,
      "train_tokens_per_second": 29198.925
    },
    {
      "epoch": 2.426848766162399,
      "grad_norm": 1.6875,
      "learning_rate": 1.7835657461017948e-05,
      "loss": 1.0361645698547364,
      "num_input_tokens_seen": 19508146112,
      "step": 68590,
      "train_runtime": 668112.6033,
      "train_tokens_per_second": 29198.89
    },
    {
      "epoch": 2.427202586426128,
      "grad_norm": 1.625,
      "learning_rate": 1.7834522826684414e-05,
      "loss": 1.0384063720703125,
      "num_input_tokens_seen": 19511018624,
      "step": 68600,
      "train_runtime": 668210.4127,
      "train_tokens_per_second": 29198.914
    },
    {
      "epoch": 2.4275564066898565,
      "grad_norm": 1.578125,
      "learning_rate": 1.783338840886625e-05,
      "loss": 1.0379545211791992,
      "num_input_tokens_seen": 19513878080,
      "step": 68610,
      "train_runtime": 668307.4512,
      "train_tokens_per_second": 29198.953
    },
    {
      "epoch": 2.4279102269535855,
      "grad_norm": 1.5625,
      "learning_rate": 1.7832254207494598e-05,
      "loss": 1.0298705101013184,
      "num_input_tokens_seen": 19516727616,
      "step": 68620,
      "train_runtime": 668408.8036,
      "train_tokens_per_second": 29198.789
    },
    {
      "epoch": 2.428264047217314,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7831120222500635e-05,
      "loss": 1.0583419799804688,
      "num_input_tokens_seen": 19519535680,
      "step": 68630,
      "train_runtime": 668505.0539,
      "train_tokens_per_second": 29198.786
    },
    {
      "epoch": 2.428617867481043,
      "grad_norm": 1.5234375,
      "learning_rate": 1.782998645381558e-05,
      "loss": 1.0343798637390136,
      "num_input_tokens_seen": 19522431680,
      "step": 68640,
      "train_runtime": 668604.4186,
      "train_tokens_per_second": 29198.778
    },
    {
      "epoch": 2.4289716877447716,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7828852901370663e-05,
      "loss": 1.0251478195190429,
      "num_input_tokens_seen": 19525270144,
      "step": 68650,
      "train_runtime": 668701.3058,
      "train_tokens_per_second": 29198.792
    },
    {
      "epoch": 2.4293255080085006,
      "grad_norm": 1.625,
      "learning_rate": 1.7827719565097157e-05,
      "loss": 1.026251220703125,
      "num_input_tokens_seen": 19528156928,
      "step": 68660,
      "train_runtime": 668801.4105,
      "train_tokens_per_second": 29198.738
    },
    {
      "epoch": 2.429679328272229,
      "grad_norm": 1.59375,
      "learning_rate": 1.7826586444926364e-05,
      "loss": 1.0340392112731933,
      "num_input_tokens_seen": 19531035392,
      "step": 68670,
      "train_runtime": 668899.449,
      "train_tokens_per_second": 29198.761
    },
    {
      "epoch": 2.430033148535958,
      "grad_norm": 1.640625,
      "learning_rate": 1.782545354078962e-05,
      "loss": 1.0374011993408203,
      "num_input_tokens_seen": 19533874624,
      "step": 68680,
      "train_runtime": 668996.418,
      "train_tokens_per_second": 29198.773
    },
    {
      "epoch": 2.430386968799687,
      "grad_norm": 1.59375,
      "learning_rate": 1.7824320852618285e-05,
      "loss": 1.0233301162719726,
      "num_input_tokens_seen": 19536690112,
      "step": 68690,
      "train_runtime": 669093.4902,
      "train_tokens_per_second": 29198.745
    },
    {
      "epoch": 2.4307407890634156,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7823188380343746e-05,
      "loss": 1.049265480041504,
      "num_input_tokens_seen": 19539581504,
      "step": 68700,
      "train_runtime": 669192.7962,
      "train_tokens_per_second": 29198.733
    },
    {
      "epoch": 2.4310946093271446,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7822056123897433e-05,
      "loss": 1.0305707931518555,
      "num_input_tokens_seen": 19542478080,
      "step": 68710,
      "train_runtime": 669294.2259,
      "train_tokens_per_second": 29198.635
    },
    {
      "epoch": 2.431448429590873,
      "grad_norm": 1.625,
      "learning_rate": 1.7820924083210802e-05,
      "loss": 1.0336406707763672,
      "num_input_tokens_seen": 19545280320,
      "step": 68720,
      "train_runtime": 669386.7181,
      "train_tokens_per_second": 29198.787
    },
    {
      "epoch": 2.431802249854602,
      "grad_norm": 1.5546875,
      "learning_rate": 1.781979225821533e-05,
      "loss": 1.0193326950073243,
      "num_input_tokens_seen": 19548097024,
      "step": 68730,
      "train_runtime": 669484.3212,
      "train_tokens_per_second": 29198.738
    },
    {
      "epoch": 2.4321560701183307,
      "grad_norm": 1.6875,
      "learning_rate": 1.781866064884254e-05,
      "loss": 1.0487627029418944,
      "num_input_tokens_seen": 19550942208,
      "step": 68740,
      "train_runtime": 669580.4688,
      "train_tokens_per_second": 29198.794
    },
    {
      "epoch": 2.4325098903820597,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7817529255023968e-05,
      "loss": 1.0418296813964845,
      "num_input_tokens_seen": 19553779264,
      "step": 68750,
      "train_runtime": 669675.26,
      "train_tokens_per_second": 29198.897
    },
    {
      "epoch": 2.432863710645788,
      "grad_norm": 1.6015625,
      "learning_rate": 1.78163980766912e-05,
      "loss": 1.0393393516540528,
      "num_input_tokens_seen": 19556599360,
      "step": 68760,
      "train_runtime": 669772.8133,
      "train_tokens_per_second": 29198.855
    },
    {
      "epoch": 2.433217530909517,
      "grad_norm": 1.4921875,
      "learning_rate": 1.7815267113775832e-05,
      "loss": 1.03318510055542,
      "num_input_tokens_seen": 19559495680,
      "step": 68770,
      "train_runtime": 669875.2808,
      "train_tokens_per_second": 29198.712
    },
    {
      "epoch": 2.4335713511732457,
      "grad_norm": 1.734375,
      "learning_rate": 1.781413636620951e-05,
      "loss": 1.0419466018676757,
      "num_input_tokens_seen": 19562304384,
      "step": 68780,
      "train_runtime": 669970.054,
      "train_tokens_per_second": 29198.774
    },
    {
      "epoch": 2.4339251714369747,
      "grad_norm": 1.5703125,
      "learning_rate": 1.781300583392389e-05,
      "loss": 1.0437986373901367,
      "num_input_tokens_seen": 19565156416,
      "step": 68790,
      "train_runtime": 670068.4442,
      "train_tokens_per_second": 29198.743
    },
    {
      "epoch": 2.4342789917007033,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7811875516850678e-05,
      "loss": 1.0376073837280273,
      "num_input_tokens_seen": 19568039168,
      "step": 68800,
      "train_runtime": 670168.266,
      "train_tokens_per_second": 29198.696
    },
    {
      "epoch": 2.4346328119644323,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7810745414921605e-05,
      "loss": 1.0499457359313964,
      "num_input_tokens_seen": 19570895680,
      "step": 68810,
      "train_runtime": 670266.2435,
      "train_tokens_per_second": 29198.689
    },
    {
      "epoch": 2.434986632228161,
      "grad_norm": 1.5234375,
      "learning_rate": 1.7809615528068414e-05,
      "loss": 1.027841281890869,
      "num_input_tokens_seen": 19573712576,
      "step": 68820,
      "train_runtime": 670361.6078,
      "train_tokens_per_second": 29198.737
    },
    {
      "epoch": 2.43534045249189,
      "grad_norm": 1.59375,
      "learning_rate": 1.7808485856222905e-05,
      "loss": 1.0338020324707031,
      "num_input_tokens_seen": 19576527808,
      "step": 68830,
      "train_runtime": 670456.9424,
      "train_tokens_per_second": 29198.785
    },
    {
      "epoch": 2.435694272755619,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7807356399316896e-05,
      "loss": 1.0221359252929687,
      "num_input_tokens_seen": 19579367232,
      "step": 68840,
      "train_runtime": 670554.5688,
      "train_tokens_per_second": 29198.768
    },
    {
      "epoch": 2.4360480930193473,
      "grad_norm": 1.59375,
      "learning_rate": 1.780622715728223e-05,
      "loss": 1.0493825912475585,
      "num_input_tokens_seen": 19582191040,
      "step": 68850,
      "train_runtime": 670650.0023,
      "train_tokens_per_second": 29198.823
    },
    {
      "epoch": 2.436401913283076,
      "grad_norm": 1.5234375,
      "learning_rate": 1.7805098130050797e-05,
      "loss": 1.0368536949157714,
      "num_input_tokens_seen": 19585090240,
      "step": 68860,
      "train_runtime": 670751.0452,
      "train_tokens_per_second": 29198.747
    },
    {
      "epoch": 2.436755733546805,
      "grad_norm": 1.6640625,
      "learning_rate": 1.780396931755449e-05,
      "loss": 1.0542387008666991,
      "num_input_tokens_seen": 19587910144,
      "step": 68870,
      "train_runtime": 670846.9476,
      "train_tokens_per_second": 29198.777
    },
    {
      "epoch": 2.437109553810534,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7802840719725262e-05,
      "loss": 1.0143828392028809,
      "num_input_tokens_seen": 19590721216,
      "step": 68880,
      "train_runtime": 670943.2607,
      "train_tokens_per_second": 29198.775
    },
    {
      "epoch": 2.4374633740742624,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7801712336495076e-05,
      "loss": 1.0203460693359374,
      "num_input_tokens_seen": 19593571584,
      "step": 68890,
      "train_runtime": 671042.8979,
      "train_tokens_per_second": 29198.687
    },
    {
      "epoch": 2.4378171943379914,
      "grad_norm": 1.65625,
      "learning_rate": 1.7800584167795936e-05,
      "loss": 1.037510585784912,
      "num_input_tokens_seen": 19596410624,
      "step": 68900,
      "train_runtime": 671140.6423,
      "train_tokens_per_second": 29198.665
    },
    {
      "epoch": 2.43817101460172,
      "grad_norm": 1.578125,
      "learning_rate": 1.7799456213559863e-05,
      "loss": 1.0304201126098633,
      "num_input_tokens_seen": 19599232384,
      "step": 68910,
      "train_runtime": 671237.6225,
      "train_tokens_per_second": 29198.65
    },
    {
      "epoch": 2.438524834865449,
      "grad_norm": 1.625,
      "learning_rate": 1.7798328473718933e-05,
      "loss": 1.037412452697754,
      "num_input_tokens_seen": 19602052352,
      "step": 68920,
      "train_runtime": 671334.0955,
      "train_tokens_per_second": 29198.655
    },
    {
      "epoch": 2.4388786551291775,
      "grad_norm": 1.671875,
      "learning_rate": 1.779720094820522e-05,
      "loss": 1.0413493156433105,
      "num_input_tokens_seen": 19604874368,
      "step": 68930,
      "train_runtime": 671427.9576,
      "train_tokens_per_second": 29198.776
    },
    {
      "epoch": 2.4392324753929064,
      "grad_norm": 1.578125,
      "learning_rate": 1.7796073636950857e-05,
      "loss": 1.033941650390625,
      "num_input_tokens_seen": 19607754176,
      "step": 68940,
      "train_runtime": 671527.2545,
      "train_tokens_per_second": 29198.747
    },
    {
      "epoch": 2.439586295656635,
      "grad_norm": 1.6796875,
      "learning_rate": 1.7794946539887983e-05,
      "loss": 1.0341178894042968,
      "num_input_tokens_seen": 19610550208,
      "step": 68950,
      "train_runtime": 671623.4503,
      "train_tokens_per_second": 29198.728
    },
    {
      "epoch": 2.439940115920364,
      "grad_norm": 1.578125,
      "learning_rate": 1.7793819656948787e-05,
      "loss": 1.0428680419921874,
      "num_input_tokens_seen": 19613431296,
      "step": 68960,
      "train_runtime": 671720.0044,
      "train_tokens_per_second": 29198.82
    },
    {
      "epoch": 2.4402939361840925,
      "grad_norm": 1.65625,
      "learning_rate": 1.7792692988065476e-05,
      "loss": 1.0438711166381835,
      "num_input_tokens_seen": 19616247744,
      "step": 68970,
      "train_runtime": 671816.564,
      "train_tokens_per_second": 29198.815
    },
    {
      "epoch": 2.4406477564478215,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7791566533170294e-05,
      "loss": 1.029484176635742,
      "num_input_tokens_seen": 19619128000,
      "step": 68980,
      "train_runtime": 671916.6921,
      "train_tokens_per_second": 29198.751
    },
    {
      "epoch": 2.44100157671155,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7790440292195505e-05,
      "loss": 1.0431220054626464,
      "num_input_tokens_seen": 19621999168,
      "step": 68990,
      "train_runtime": 672015.6473,
      "train_tokens_per_second": 29198.724
    },
    {
      "epoch": 2.441355396975279,
      "grad_norm": 1.6015625,
      "learning_rate": 1.778931426507342e-05,
      "loss": 1.0394121170043946,
      "num_input_tokens_seen": 19624835136,
      "step": 69000,
      "train_runtime": 672113.8285,
      "train_tokens_per_second": 29198.678
    },
    {
      "epoch": 2.4417092172390076,
      "grad_norm": 1.5390625,
      "learning_rate": 1.778818845173636e-05,
      "loss": 1.029822826385498,
      "num_input_tokens_seen": 19627691904,
      "step": 69010,
      "train_runtime": 672211.6646,
      "train_tokens_per_second": 29198.678
    },
    {
      "epoch": 2.4420630375027366,
      "grad_norm": 1.59375,
      "learning_rate": 1.7787062852116687e-05,
      "loss": 1.0254796028137207,
      "num_input_tokens_seen": 19630551680,
      "step": 69020,
      "train_runtime": 672309.3358,
      "train_tokens_per_second": 29198.69
    },
    {
      "epoch": 2.4424168577664656,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7785937466146795e-05,
      "loss": 1.0420955657958983,
      "num_input_tokens_seen": 19633376384,
      "step": 69030,
      "train_runtime": 672405.6075,
      "train_tokens_per_second": 29198.71
    },
    {
      "epoch": 2.442770678030194,
      "grad_norm": 1.5625,
      "learning_rate": 1.7784812293759106e-05,
      "loss": 1.0351673126220704,
      "num_input_tokens_seen": 19636211712,
      "step": 69040,
      "train_runtime": 672501.5609,
      "train_tokens_per_second": 29198.76
    },
    {
      "epoch": 2.443124498293923,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7783687334886065e-05,
      "loss": 1.030184555053711,
      "num_input_tokens_seen": 19639016256,
      "step": 69050,
      "train_runtime": 672596.3569,
      "train_tokens_per_second": 29198.814
    },
    {
      "epoch": 2.4434783185576516,
      "grad_norm": 1.578125,
      "learning_rate": 1.7782562589460156e-05,
      "loss": 1.027071475982666,
      "num_input_tokens_seen": 19641962752,
      "step": 69060,
      "train_runtime": 672700.2521,
      "train_tokens_per_second": 29198.685
    },
    {
      "epoch": 2.4438321388213806,
      "grad_norm": 1.546875,
      "learning_rate": 1.778143805741389e-05,
      "loss": 1.0340648651123048,
      "num_input_tokens_seen": 19644806592,
      "step": 69070,
      "train_runtime": 672799.7622,
      "train_tokens_per_second": 29198.593
    },
    {
      "epoch": 2.444185959085109,
      "grad_norm": 1.53125,
      "learning_rate": 1.7780313738679804e-05,
      "loss": 1.0302449226379395,
      "num_input_tokens_seen": 19647662272,
      "step": 69080,
      "train_runtime": 672894.9189,
      "train_tokens_per_second": 29198.708
    },
    {
      "epoch": 2.444539779348838,
      "grad_norm": 1.578125,
      "learning_rate": 1.777918963319047e-05,
      "loss": 1.0389592170715332,
      "num_input_tokens_seen": 19650563968,
      "step": 69090,
      "train_runtime": 672994.1607,
      "train_tokens_per_second": 29198.714
    },
    {
      "epoch": 2.4448935996125667,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7778065740878485e-05,
      "loss": 1.0505677223205567,
      "num_input_tokens_seen": 19653403136,
      "step": 69100,
      "train_runtime": 673093.1921,
      "train_tokens_per_second": 29198.636
    },
    {
      "epoch": 2.4452474198762957,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7776942061676485e-05,
      "loss": 1.0419110298156737,
      "num_input_tokens_seen": 19656230784,
      "step": 69110,
      "train_runtime": 673190.7915,
      "train_tokens_per_second": 29198.603
    },
    {
      "epoch": 2.4456012401400242,
      "grad_norm": 1.609375,
      "learning_rate": 1.7775818595517125e-05,
      "loss": 1.028173065185547,
      "num_input_tokens_seen": 19659065408,
      "step": 69120,
      "train_runtime": 673286.879,
      "train_tokens_per_second": 29198.646
    },
    {
      "epoch": 2.445955060403753,
      "grad_norm": 1.546875,
      "learning_rate": 1.7774695342333093e-05,
      "loss": 1.0467111587524414,
      "num_input_tokens_seen": 19661943488,
      "step": 69130,
      "train_runtime": 673384.4195,
      "train_tokens_per_second": 29198.691
    },
    {
      "epoch": 2.4463088806674818,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7773572302057108e-05,
      "loss": 1.0229506492614746,
      "num_input_tokens_seen": 19664729728,
      "step": 69140,
      "train_runtime": 673476.5201,
      "train_tokens_per_second": 29198.835
    },
    {
      "epoch": 2.4466627009312107,
      "grad_norm": 1.6796875,
      "learning_rate": 1.777244947462192e-05,
      "loss": 1.034883689880371,
      "num_input_tokens_seen": 19667571456,
      "step": 69150,
      "train_runtime": 673575.1176,
      "train_tokens_per_second": 29198.78
    },
    {
      "epoch": 2.4470165211949393,
      "grad_norm": 1.578125,
      "learning_rate": 1.777132685996031e-05,
      "loss": 1.0457597732543946,
      "num_input_tokens_seen": 19670420928,
      "step": 69160,
      "train_runtime": 673671.9366,
      "train_tokens_per_second": 29198.813
    },
    {
      "epoch": 2.4473703414586683,
      "grad_norm": 1.640625,
      "learning_rate": 1.7770204458005086e-05,
      "loss": 1.0310590744018555,
      "num_input_tokens_seen": 19673216000,
      "step": 69170,
      "train_runtime": 673765.9179,
      "train_tokens_per_second": 29198.889
    },
    {
      "epoch": 2.4477241617223973,
      "grad_norm": 1.546875,
      "learning_rate": 1.776908226868908e-05,
      "loss": 1.0549046516418457,
      "num_input_tokens_seen": 19676064512,
      "step": 69180,
      "train_runtime": 673864.3985,
      "train_tokens_per_second": 29198.849
    },
    {
      "epoch": 2.448077981986126,
      "grad_norm": 1.640625,
      "learning_rate": 1.776796029194517e-05,
      "loss": 1.0252192497253418,
      "num_input_tokens_seen": 19678938944,
      "step": 69190,
      "train_runtime": 673962.3185,
      "train_tokens_per_second": 29198.871
    },
    {
      "epoch": 2.448431802249855,
      "grad_norm": 1.59375,
      "learning_rate": 1.776683852770624e-05,
      "loss": 1.0427411079406739,
      "num_input_tokens_seen": 19681750464,
      "step": 69200,
      "train_runtime": 674058.4663,
      "train_tokens_per_second": 29198.877
    },
    {
      "epoch": 2.4487856225135833,
      "grad_norm": 1.640625,
      "learning_rate": 1.7765716975905224e-05,
      "loss": 1.0385528564453126,
      "num_input_tokens_seen": 19684566592,
      "step": 69210,
      "train_runtime": 674155.4192,
      "train_tokens_per_second": 29198.855
    },
    {
      "epoch": 2.4491394427773123,
      "grad_norm": 1.5625,
      "learning_rate": 1.776459563647508e-05,
      "loss": 1.0360111236572265,
      "num_input_tokens_seen": 19687365696,
      "step": 69220,
      "train_runtime": 674248.7865,
      "train_tokens_per_second": 29198.963
    },
    {
      "epoch": 2.449493263041041,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7763474509348795e-05,
      "loss": 1.0354524612426759,
      "num_input_tokens_seen": 19690192640,
      "step": 69230,
      "train_runtime": 674344.8043,
      "train_tokens_per_second": 29198.998
    },
    {
      "epoch": 2.44984708330477,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7762353594459377e-05,
      "loss": 1.0363286972045898,
      "num_input_tokens_seen": 19693018944,
      "step": 69240,
      "train_runtime": 674439.4662,
      "train_tokens_per_second": 29199.09
    },
    {
      "epoch": 2.4502009035684984,
      "grad_norm": 1.640625,
      "learning_rate": 1.7761232891739878e-05,
      "loss": 1.0454733848571778,
      "num_input_tokens_seen": 19695877760,
      "step": 69250,
      "train_runtime": 674539.5739,
      "train_tokens_per_second": 29198.995
    },
    {
      "epoch": 2.4505547238322274,
      "grad_norm": 1.609375,
      "learning_rate": 1.776011240112337e-05,
      "loss": 1.026791477203369,
      "num_input_tokens_seen": 19698677056,
      "step": 69260,
      "train_runtime": 674637.2276,
      "train_tokens_per_second": 29198.918
    },
    {
      "epoch": 2.450908544095956,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7758992122542966e-05,
      "loss": 1.0298766136169433,
      "num_input_tokens_seen": 19701504960,
      "step": 69270,
      "train_runtime": 674733.5474,
      "train_tokens_per_second": 29198.941
    },
    {
      "epoch": 2.451262364359685,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7757872055931786e-05,
      "loss": 1.0340000152587892,
      "num_input_tokens_seen": 19704340224,
      "step": 69280,
      "train_runtime": 674829.54,
      "train_tokens_per_second": 29198.989
    },
    {
      "epoch": 2.4516161846234135,
      "grad_norm": 1.625,
      "learning_rate": 1.7756752201223005e-05,
      "loss": 1.0470769882202149,
      "num_input_tokens_seen": 19707155328,
      "step": 69290,
      "train_runtime": 674923.8634,
      "train_tokens_per_second": 29199.079
    },
    {
      "epoch": 2.4519700048871425,
      "grad_norm": 1.6953125,
      "learning_rate": 1.7755632558349808e-05,
      "loss": 1.0521994590759278,
      "num_input_tokens_seen": 19710033664,
      "step": 69300,
      "train_runtime": 675023.1792,
      "train_tokens_per_second": 29199.047
    },
    {
      "epoch": 2.452323825150871,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7754513127245423e-05,
      "loss": 1.036869716644287,
      "num_input_tokens_seen": 19712820608,
      "step": 69310,
      "train_runtime": 675116.0672,
      "train_tokens_per_second": 29199.158
    },
    {
      "epoch": 2.4526776454146,
      "grad_norm": 1.5546875,
      "learning_rate": 1.77533939078431e-05,
      "loss": 1.0346519470214843,
      "num_input_tokens_seen": 19715692160,
      "step": 69320,
      "train_runtime": 675213.5053,
      "train_tokens_per_second": 29199.197
    },
    {
      "epoch": 2.453031465678329,
      "grad_norm": 1.65625,
      "learning_rate": 1.7752274900076117e-05,
      "loss": 1.0308061599731446,
      "num_input_tokens_seen": 19718515712,
      "step": 69330,
      "train_runtime": 675310.4293,
      "train_tokens_per_second": 29199.187
    },
    {
      "epoch": 2.4533852859420575,
      "grad_norm": 1.5703125,
      "learning_rate": 1.775115610387779e-05,
      "loss": 1.020094108581543,
      "num_input_tokens_seen": 19721335040,
      "step": 69340,
      "train_runtime": 675404.7546,
      "train_tokens_per_second": 29199.284
    },
    {
      "epoch": 2.453739106205786,
      "grad_norm": 1.5625,
      "learning_rate": 1.7750037519181458e-05,
      "loss": 1.0232133865356445,
      "num_input_tokens_seen": 19724223744,
      "step": 69350,
      "train_runtime": 675506.1573,
      "train_tokens_per_second": 29199.177
    },
    {
      "epoch": 2.454092926469515,
      "grad_norm": 1.6171875,
      "learning_rate": 1.774891914592049e-05,
      "loss": 1.033740520477295,
      "num_input_tokens_seen": 19727068800,
      "step": 69360,
      "train_runtime": 675603.9085,
      "train_tokens_per_second": 29199.163
    },
    {
      "epoch": 2.454446746733244,
      "grad_norm": 1.640625,
      "learning_rate": 1.7747800984028288e-05,
      "loss": 1.0410243034362794,
      "num_input_tokens_seen": 19729890368,
      "step": 69370,
      "train_runtime": 675700.9089,
      "train_tokens_per_second": 29199.147
    },
    {
      "epoch": 2.4548005669969726,
      "grad_norm": 1.484375,
      "learning_rate": 1.7746683033438273e-05,
      "loss": 1.0381586074829101,
      "num_input_tokens_seen": 19732693376,
      "step": 69380,
      "train_runtime": 675799.1686,
      "train_tokens_per_second": 29199.05
    },
    {
      "epoch": 2.4551543872607016,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7745565294083913e-05,
      "loss": 1.0432146072387696,
      "num_input_tokens_seen": 19735536192,
      "step": 69390,
      "train_runtime": 675897.432,
      "train_tokens_per_second": 29199.01
    },
    {
      "epoch": 2.45550820752443,
      "grad_norm": 35.5,
      "learning_rate": 1.7744447765898684e-05,
      "loss": 1.0501142501831056,
      "num_input_tokens_seen": 19738395840,
      "step": 69400,
      "train_runtime": 675994.7283,
      "train_tokens_per_second": 29199.038
    },
    {
      "epoch": 2.455862027788159,
      "grad_norm": 1.6640625,
      "learning_rate": 1.774333044881611e-05,
      "loss": 1.0364815711975097,
      "num_input_tokens_seen": 19741271552,
      "step": 69410,
      "train_runtime": 676092.9228,
      "train_tokens_per_second": 29199.051
    },
    {
      "epoch": 2.4562158480518876,
      "grad_norm": 1.609375,
      "learning_rate": 1.7742213342769734e-05,
      "loss": 1.0386528015136718,
      "num_input_tokens_seen": 19744131584,
      "step": 69420,
      "train_runtime": 676190.251,
      "train_tokens_per_second": 29199.078
    },
    {
      "epoch": 2.4565696683156166,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7741096447693133e-05,
      "loss": 1.027775764465332,
      "num_input_tokens_seen": 19747028800,
      "step": 69430,
      "train_runtime": 676291.3157,
      "train_tokens_per_second": 29198.998
    },
    {
      "epoch": 2.456923488579345,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7739979763519905e-05,
      "loss": 1.0348522186279296,
      "num_input_tokens_seen": 19749886016,
      "step": 69440,
      "train_runtime": 676386.6441,
      "train_tokens_per_second": 29199.107
    },
    {
      "epoch": 2.457277308843074,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7738863290183695e-05,
      "loss": 1.0279630661010741,
      "num_input_tokens_seen": 19752744512,
      "step": 69450,
      "train_runtime": 676486.1685,
      "train_tokens_per_second": 29199.037
    },
    {
      "epoch": 2.4576311291068027,
      "grad_norm": 1.5625,
      "learning_rate": 1.7737747027618156e-05,
      "loss": 1.0369864463806153,
      "num_input_tokens_seen": 19755592768,
      "step": 69460,
      "train_runtime": 676583.3278,
      "train_tokens_per_second": 29199.053
    },
    {
      "epoch": 2.4579849493705317,
      "grad_norm": 1.59375,
      "learning_rate": 1.7736630975756982e-05,
      "loss": 1.046706771850586,
      "num_input_tokens_seen": 19758432768,
      "step": 69470,
      "train_runtime": 676681.509,
      "train_tokens_per_second": 29199.014
    },
    {
      "epoch": 2.4583387696342602,
      "grad_norm": 1.59375,
      "learning_rate": 1.7735515134533902e-05,
      "loss": 1.0388235092163085,
      "num_input_tokens_seen": 19761284928,
      "step": 69480,
      "train_runtime": 676781.4224,
      "train_tokens_per_second": 29198.918
    },
    {
      "epoch": 2.4586925898979892,
      "grad_norm": 1.625,
      "learning_rate": 1.773439950388265e-05,
      "loss": 1.034647274017334,
      "num_input_tokens_seen": 19764132992,
      "step": 69490,
      "train_runtime": 676878.9903,
      "train_tokens_per_second": 29198.916
    },
    {
      "epoch": 2.4590464101617178,
      "grad_norm": 1.59375,
      "learning_rate": 1.773328408373702e-05,
      "loss": 1.0314868927001952,
      "num_input_tokens_seen": 19766993728,
      "step": 69500,
      "train_runtime": 676977.6439,
      "train_tokens_per_second": 29198.887
    },
    {
      "epoch": 2.4594002304254468,
      "grad_norm": 1.640625,
      "learning_rate": 1.7732168874030813e-05,
      "loss": 1.0230062484741211,
      "num_input_tokens_seen": 19769818432,
      "step": 69510,
      "train_runtime": 677072.6822,
      "train_tokens_per_second": 29198.96
    },
    {
      "epoch": 2.4597540506891757,
      "grad_norm": 1.65625,
      "learning_rate": 1.7731053874697875e-05,
      "loss": 1.0479019165039063,
      "num_input_tokens_seen": 19772655424,
      "step": 69520,
      "train_runtime": 677170.5569,
      "train_tokens_per_second": 29198.93
    },
    {
      "epoch": 2.4601078709529043,
      "grad_norm": 1.59375,
      "learning_rate": 1.7729939085672064e-05,
      "loss": 1.0357666015625,
      "num_input_tokens_seen": 19775456576,
      "step": 69530,
      "train_runtime": 677265.2946,
      "train_tokens_per_second": 29198.981
    },
    {
      "epoch": 2.4604616912166333,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7728824506887278e-05,
      "loss": 1.0381930351257325,
      "num_input_tokens_seen": 19778306176,
      "step": 69540,
      "train_runtime": 677362.398,
      "train_tokens_per_second": 29199.002
    },
    {
      "epoch": 2.460815511480362,
      "grad_norm": 1.625,
      "learning_rate": 1.7727710138277448e-05,
      "loss": 1.0315091133117675,
      "num_input_tokens_seen": 19781158528,
      "step": 69550,
      "train_runtime": 677459.3219,
      "train_tokens_per_second": 29199.035
    },
    {
      "epoch": 2.461169331744091,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7726595979776522e-05,
      "loss": 1.025179100036621,
      "num_input_tokens_seen": 19783951744,
      "step": 69560,
      "train_runtime": 677553.2443,
      "train_tokens_per_second": 29199.11
    },
    {
      "epoch": 2.4615231520078193,
      "grad_norm": 1.625,
      "learning_rate": 1.7725482031318487e-05,
      "loss": 1.047089195251465,
      "num_input_tokens_seen": 19786827456,
      "step": 69570,
      "train_runtime": 677655.5759,
      "train_tokens_per_second": 29198.944
    },
    {
      "epoch": 2.4618769722715483,
      "grad_norm": 1.546875,
      "learning_rate": 1.772436829283735e-05,
      "loss": 1.0311185836791992,
      "num_input_tokens_seen": 19789700992,
      "step": 69580,
      "train_runtime": 677754.876,
      "train_tokens_per_second": 29198.906
    },
    {
      "epoch": 2.462230792535277,
      "grad_norm": 1.59375,
      "learning_rate": 1.7723254764267157e-05,
      "loss": 1.0366227149963378,
      "num_input_tokens_seen": 19792513024,
      "step": 69590,
      "train_runtime": 677851.015,
      "train_tokens_per_second": 29198.913
    },
    {
      "epoch": 2.462584612799006,
      "grad_norm": 1.53125,
      "learning_rate": 1.772214144554198e-05,
      "loss": 1.039426326751709,
      "num_input_tokens_seen": 19795376896,
      "step": 69600,
      "train_runtime": 677948.5443,
      "train_tokens_per_second": 29198.937
    },
    {
      "epoch": 2.4629384330627344,
      "grad_norm": 1.5625,
      "learning_rate": 1.772102833659591e-05,
      "loss": 1.049594783782959,
      "num_input_tokens_seen": 19798204352,
      "step": 69610,
      "train_runtime": 678045.333,
      "train_tokens_per_second": 29198.939
    },
    {
      "epoch": 2.4632922533264634,
      "grad_norm": 1.5625,
      "learning_rate": 1.771991543736308e-05,
      "loss": 1.0267019271850586,
      "num_input_tokens_seen": 19801081152,
      "step": 69620,
      "train_runtime": 678143.0539,
      "train_tokens_per_second": 29198.974
    },
    {
      "epoch": 2.463646073590192,
      "grad_norm": 1.671875,
      "learning_rate": 1.7718802747777656e-05,
      "loss": 1.0491281509399415,
      "num_input_tokens_seen": 19803958720,
      "step": 69630,
      "train_runtime": 678243.7204,
      "train_tokens_per_second": 29198.883
    },
    {
      "epoch": 2.463999893853921,
      "grad_norm": 1.59375,
      "learning_rate": 1.771769026777381e-05,
      "loss": 1.0378268241882325,
      "num_input_tokens_seen": 19806807360,
      "step": 69640,
      "train_runtime": 678340.4732,
      "train_tokens_per_second": 29198.917
    },
    {
      "epoch": 2.4643537141176495,
      "grad_norm": 1.59375,
      "learning_rate": 1.7716577997285763e-05,
      "loss": 1.036257266998291,
      "num_input_tokens_seen": 19809599360,
      "step": 69650,
      "train_runtime": 678436.6671,
      "train_tokens_per_second": 29198.893
    },
    {
      "epoch": 2.4647075343813785,
      "grad_norm": 1.53125,
      "learning_rate": 1.771546593624776e-05,
      "loss": 1.045534324645996,
      "num_input_tokens_seen": 19812505984,
      "step": 69660,
      "train_runtime": 678534.8685,
      "train_tokens_per_second": 29198.95
    },
    {
      "epoch": 2.4650613546451074,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7714354084594077e-05,
      "loss": 1.031464195251465,
      "num_input_tokens_seen": 19815300608,
      "step": 69670,
      "train_runtime": 678627.9062,
      "train_tokens_per_second": 29199.065
    },
    {
      "epoch": 2.465415174908836,
      "grad_norm": 1.640625,
      "learning_rate": 1.7713242442259005e-05,
      "loss": 1.0380437850952149,
      "num_input_tokens_seen": 19818156096,
      "step": 69680,
      "train_runtime": 678725.6092,
      "train_tokens_per_second": 29199.069
    },
    {
      "epoch": 2.4657689951725645,
      "grad_norm": 1.6328125,
      "learning_rate": 1.771213100917688e-05,
      "loss": 1.0372909545898437,
      "num_input_tokens_seen": 19821056256,
      "step": 69690,
      "train_runtime": 678825.9105,
      "train_tokens_per_second": 29199.027
    },
    {
      "epoch": 2.4661228154362935,
      "grad_norm": 1.6484375,
      "learning_rate": 1.771101978528207e-05,
      "loss": 1.037991428375244,
      "num_input_tokens_seen": 19823867648,
      "step": 69700,
      "train_runtime": 678920.365,
      "train_tokens_per_second": 29199.106
    },
    {
      "epoch": 2.4664766357000225,
      "grad_norm": 1.6171875,
      "learning_rate": 1.770990877050895e-05,
      "loss": 1.0336776733398438,
      "num_input_tokens_seen": 19826690560,
      "step": 69710,
      "train_runtime": 679017.341,
      "train_tokens_per_second": 29199.093
    },
    {
      "epoch": 2.466830455963751,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7708797964791944e-05,
      "loss": 1.0350730895996094,
      "num_input_tokens_seen": 19829525056,
      "step": 69720,
      "train_runtime": 679113.693,
      "train_tokens_per_second": 29199.124
    },
    {
      "epoch": 2.46718427622748,
      "grad_norm": 1.65625,
      "learning_rate": 1.7707687368065497e-05,
      "loss": 1.0426039695739746,
      "num_input_tokens_seen": 19832363904,
      "step": 69730,
      "train_runtime": 679212.5046,
      "train_tokens_per_second": 29199.056
    },
    {
      "epoch": 2.4675380964912086,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7706576980264086e-05,
      "loss": 1.0232948303222655,
      "num_input_tokens_seen": 19835189952,
      "step": 69740,
      "train_runtime": 679307.8997,
      "train_tokens_per_second": 29199.116
    },
    {
      "epoch": 2.4678919167549376,
      "grad_norm": 1.6328125,
      "learning_rate": 1.770546680132221e-05,
      "loss": 1.0410656929016113,
      "num_input_tokens_seen": 19838050304,
      "step": 69750,
      "train_runtime": 679406.8258,
      "train_tokens_per_second": 29199.074
    },
    {
      "epoch": 2.468245737018666,
      "grad_norm": 1.5625,
      "learning_rate": 1.7704356831174402e-05,
      "loss": 1.0339242935180664,
      "num_input_tokens_seen": 19840935616,
      "step": 69760,
      "train_runtime": 679505.7306,
      "train_tokens_per_second": 29199.07
    },
    {
      "epoch": 2.468599557282395,
      "grad_norm": 1.59375,
      "learning_rate": 1.770324706975523e-05,
      "loss": 1.0415584564208984,
      "num_input_tokens_seen": 19843782208,
      "step": 69770,
      "train_runtime": 679601.2726,
      "train_tokens_per_second": 29199.154
    },
    {
      "epoch": 2.4689533775461237,
      "grad_norm": 1.5234375,
      "learning_rate": 1.7702137516999267e-05,
      "loss": 1.0258638381958007,
      "num_input_tokens_seen": 19846603840,
      "step": 69780,
      "train_runtime": 679696.7962,
      "train_tokens_per_second": 29199.202
    },
    {
      "epoch": 2.4693071978098526,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7701028172841147e-05,
      "loss": 1.036543846130371,
      "num_input_tokens_seen": 19849473472,
      "step": 69790,
      "train_runtime": 679798.006,
      "train_tokens_per_second": 29199.076
    },
    {
      "epoch": 2.469661018073581,
      "grad_norm": 1.703125,
      "learning_rate": 1.7699919037215512e-05,
      "loss": 1.0313720703125,
      "num_input_tokens_seen": 19852302208,
      "step": 69800,
      "train_runtime": 679893.2666,
      "train_tokens_per_second": 29199.145
    },
    {
      "epoch": 2.47001483833731,
      "grad_norm": 1.65625,
      "learning_rate": 1.7698810110057035e-05,
      "loss": 1.031489944458008,
      "num_input_tokens_seen": 19855086656,
      "step": 69810,
      "train_runtime": 679988.7572,
      "train_tokens_per_second": 29199.14
    },
    {
      "epoch": 2.4703686586010387,
      "grad_norm": 1.5859375,
      "learning_rate": 1.769770139130042e-05,
      "loss": 1.053888702392578,
      "num_input_tokens_seen": 19857882560,
      "step": 69820,
      "train_runtime": 680084.9221,
      "train_tokens_per_second": 29199.122
    },
    {
      "epoch": 2.4707224788647677,
      "grad_norm": 1.609375,
      "learning_rate": 1.7696592880880408e-05,
      "loss": 1.0403172492980957,
      "num_input_tokens_seen": 19860724608,
      "step": 69830,
      "train_runtime": 680183.1492,
      "train_tokens_per_second": 29199.084
    },
    {
      "epoch": 2.4710762991284962,
      "grad_norm": 1.671875,
      "learning_rate": 1.769548457873175e-05,
      "loss": 1.0328142166137695,
      "num_input_tokens_seen": 19863600896,
      "step": 69840,
      "train_runtime": 680282.8928,
      "train_tokens_per_second": 29199.03
    },
    {
      "epoch": 2.4714301193922252,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7694376484789247e-05,
      "loss": 1.0438216209411622,
      "num_input_tokens_seen": 19866412352,
      "step": 69850,
      "train_runtime": 680378.8865,
      "train_tokens_per_second": 29199.043
    },
    {
      "epoch": 2.471783939655954,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7693268598987705e-05,
      "loss": 1.027155303955078,
      "num_input_tokens_seen": 19869221248,
      "step": 69860,
      "train_runtime": 680476.9559,
      "train_tokens_per_second": 29198.963
    },
    {
      "epoch": 2.4721377599196828,
      "grad_norm": 1.609375,
      "learning_rate": 1.769216092126198e-05,
      "loss": 1.020984935760498,
      "num_input_tokens_seen": 19872089536,
      "step": 69870,
      "train_runtime": 680575.0149,
      "train_tokens_per_second": 29198.97
    },
    {
      "epoch": 2.4724915801834118,
      "grad_norm": 1.609375,
      "learning_rate": 1.7691053451546948e-05,
      "loss": 1.039038848876953,
      "num_input_tokens_seen": 19874967808,
      "step": 69880,
      "train_runtime": 680673.9498,
      "train_tokens_per_second": 29198.955
    },
    {
      "epoch": 2.4728454004471403,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7689946189777502e-05,
      "loss": 1.0243235588073731,
      "num_input_tokens_seen": 19877793088,
      "step": 69890,
      "train_runtime": 680767.8022,
      "train_tokens_per_second": 29199.079
    },
    {
      "epoch": 2.4731992207108693,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7688839135888594e-05,
      "loss": 1.0419851303100587,
      "num_input_tokens_seen": 19880589376,
      "step": 69900,
      "train_runtime": 680866.5707,
      "train_tokens_per_second": 29198.951
    },
    {
      "epoch": 2.473553040974598,
      "grad_norm": 1.5625,
      "learning_rate": 1.768773228981517e-05,
      "loss": 1.041335105895996,
      "num_input_tokens_seen": 19883474944,
      "step": 69910,
      "train_runtime": 680964.1077,
      "train_tokens_per_second": 29199.006
    },
    {
      "epoch": 2.473906861238327,
      "grad_norm": 1.625,
      "learning_rate": 1.7686625651492226e-05,
      "loss": 1.027377986907959,
      "num_input_tokens_seen": 19886367424,
      "step": 69920,
      "train_runtime": 681061.8519,
      "train_tokens_per_second": 29199.062
    },
    {
      "epoch": 2.4742606815020554,
      "grad_norm": 1.578125,
      "learning_rate": 1.7685519220854775e-05,
      "loss": 1.0351346969604491,
      "num_input_tokens_seen": 19889233600,
      "step": 69930,
      "train_runtime": 681163.1441,
      "train_tokens_per_second": 29198.928
    },
    {
      "epoch": 2.4746145017657843,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7684412997837872e-05,
      "loss": 1.0309329986572267,
      "num_input_tokens_seen": 19892081472,
      "step": 69940,
      "train_runtime": 681262.7337,
      "train_tokens_per_second": 29198.84
    },
    {
      "epoch": 2.474968322029513,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7683306982376585e-05,
      "loss": 1.023515796661377,
      "num_input_tokens_seen": 19894934656,
      "step": 69950,
      "train_runtime": 681361.5654,
      "train_tokens_per_second": 29198.792
    },
    {
      "epoch": 2.475322142293242,
      "grad_norm": 1.578125,
      "learning_rate": 1.7682201174406023e-05,
      "loss": 1.0204511642456056,
      "num_input_tokens_seen": 19897847616,
      "step": 69960,
      "train_runtime": 681462.9426,
      "train_tokens_per_second": 29198.723
    },
    {
      "epoch": 2.4756759625569704,
      "grad_norm": 1.640625,
      "learning_rate": 1.7681095573861314e-05,
      "loss": 1.0379213333129882,
      "num_input_tokens_seen": 19900666432,
      "step": 69970,
      "train_runtime": 681559.5715,
      "train_tokens_per_second": 29198.719
    },
    {
      "epoch": 2.4760297828206994,
      "grad_norm": 1.671875,
      "learning_rate": 1.7679990180677623e-05,
      "loss": 1.0398656845092773,
      "num_input_tokens_seen": 19903458944,
      "step": 69980,
      "train_runtime": 681653.2424,
      "train_tokens_per_second": 29198.803
    },
    {
      "epoch": 2.476383603084428,
      "grad_norm": 1.578125,
      "learning_rate": 1.767888499479013e-05,
      "loss": 1.0422216415405274,
      "num_input_tokens_seen": 19906279488,
      "step": 69990,
      "train_runtime": 681749.8171,
      "train_tokens_per_second": 29198.804
    },
    {
      "epoch": 2.476737423348157,
      "grad_norm": 1.5390625,
      "learning_rate": 1.767778001613406e-05,
      "loss": 1.0271638870239257,
      "num_input_tokens_seen": 19909106304,
      "step": 70000,
      "train_runtime": 681847.4155,
      "train_tokens_per_second": 29198.771
    },
    {
      "epoch": 2.476737423348157,
      "eval_loss": 1.0226019620895386,
      "eval_runtime": 8.438,
      "eval_samples_per_second": 472.624,
      "eval_steps_per_second": 3.792,
      "num_input_tokens_seen": 19909106304,
      "step": 70000
    },
    {
      "epoch": 2.477091243611886,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7676675244644658e-05,
      "loss": 1.043246078491211,
      "num_input_tokens_seen": 19911947520,
      "step": 70010,
      "train_runtime": 681973.0097,
      "train_tokens_per_second": 29197.559
    },
    {
      "epoch": 2.4774450638756145,
      "grad_norm": 1.6796875,
      "learning_rate": 1.7675570680257193e-05,
      "loss": 1.033086395263672,
      "num_input_tokens_seen": 19914752768,
      "step": 70020,
      "train_runtime": 682067.9238,
      "train_tokens_per_second": 29197.609
    },
    {
      "epoch": 2.477798884139343,
      "grad_norm": 1.671875,
      "learning_rate": 1.7674466322906973e-05,
      "loss": 1.032648468017578,
      "num_input_tokens_seen": 19917633088,
      "step": 70030,
      "train_runtime": 682167.6405,
      "train_tokens_per_second": 29197.564
    },
    {
      "epoch": 2.478152704403072,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7673362172529324e-05,
      "loss": 1.049037551879883,
      "num_input_tokens_seen": 19920416832,
      "step": 70040,
      "train_runtime": 682260.3028,
      "train_tokens_per_second": 29197.678
    },
    {
      "epoch": 2.478506524666801,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7672258229059605e-05,
      "loss": 1.0461451530456543,
      "num_input_tokens_seen": 19923288640,
      "step": 70050,
      "train_runtime": 682355.2529,
      "train_tokens_per_second": 29197.824
    },
    {
      "epoch": 2.4788603449305295,
      "grad_norm": 1.59375,
      "learning_rate": 1.76711544924332e-05,
      "loss": 1.0544964790344238,
      "num_input_tokens_seen": 19926118016,
      "step": 70060,
      "train_runtime": 682449.4575,
      "train_tokens_per_second": 29197.94
    },
    {
      "epoch": 2.4792141651942585,
      "grad_norm": 1.59375,
      "learning_rate": 1.7670050962585536e-05,
      "loss": 1.0319511413574218,
      "num_input_tokens_seen": 19928952320,
      "step": 70070,
      "train_runtime": 682546.6688,
      "train_tokens_per_second": 29197.934
    },
    {
      "epoch": 2.479567985457987,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7668947639452045e-05,
      "loss": 1.0358685493469237,
      "num_input_tokens_seen": 19931790464,
      "step": 70080,
      "train_runtime": 682644.3682,
      "train_tokens_per_second": 29197.912
    },
    {
      "epoch": 2.479921805721716,
      "grad_norm": 1.6015625,
      "learning_rate": 1.76678445229682e-05,
      "loss": 1.038547897338867,
      "num_input_tokens_seen": 19934580160,
      "step": 70090,
      "train_runtime": 682737.9695,
      "train_tokens_per_second": 29197.995
    },
    {
      "epoch": 2.4802756259854446,
      "grad_norm": 1.609375,
      "learning_rate": 1.7666741613069505e-05,
      "loss": 1.042399024963379,
      "num_input_tokens_seen": 19937440128,
      "step": 70100,
      "train_runtime": 682834.9493,
      "train_tokens_per_second": 29198.037
    },
    {
      "epoch": 2.4806294462491736,
      "grad_norm": 1.7109375,
      "learning_rate": 1.7665638909691484e-05,
      "loss": 1.0448123931884765,
      "num_input_tokens_seen": 19940313664,
      "step": 70110,
      "train_runtime": 682935.8255,
      "train_tokens_per_second": 29197.932
    },
    {
      "epoch": 2.480983266512902,
      "grad_norm": 1.59375,
      "learning_rate": 1.766453641276969e-05,
      "loss": 1.0446372985839845,
      "num_input_tokens_seen": 19943147776,
      "step": 70120,
      "train_runtime": 683034.3905,
      "train_tokens_per_second": 29197.868
    },
    {
      "epoch": 2.481337086776631,
      "grad_norm": 1.625,
      "learning_rate": 1.7663434122239723e-05,
      "loss": 1.0311466217041017,
      "num_input_tokens_seen": 19945951232,
      "step": 70130,
      "train_runtime": 683130.5559,
      "train_tokens_per_second": 29197.861
    },
    {
      "epoch": 2.4816909070403597,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7662332038037176e-05,
      "loss": 1.0424449920654297,
      "num_input_tokens_seen": 19948818112,
      "step": 70140,
      "train_runtime": 683230.3647,
      "train_tokens_per_second": 29197.792
    },
    {
      "epoch": 2.4820447273040886,
      "grad_norm": 1.59375,
      "learning_rate": 1.76612301600977e-05,
      "loss": 1.047245407104492,
      "num_input_tokens_seen": 19951633920,
      "step": 70150,
      "train_runtime": 683324.8136,
      "train_tokens_per_second": 29197.877
    },
    {
      "epoch": 2.4823985475678176,
      "grad_norm": 1.5625,
      "learning_rate": 1.7660128488356968e-05,
      "loss": 1.0316501617431642,
      "num_input_tokens_seen": 19954501632,
      "step": 70160,
      "train_runtime": 683423.1756,
      "train_tokens_per_second": 29197.871
    },
    {
      "epoch": 2.482752367831546,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7659027022750667e-05,
      "loss": 1.0387092590332032,
      "num_input_tokens_seen": 19957396288,
      "step": 70170,
      "train_runtime": 683522.8728,
      "train_tokens_per_second": 29197.847
    },
    {
      "epoch": 2.4831061880952747,
      "grad_norm": 1.6015625,
      "learning_rate": 1.765792576321452e-05,
      "loss": 1.0438535690307618,
      "num_input_tokens_seen": 19960188992,
      "step": 70180,
      "train_runtime": 683618.0569,
      "train_tokens_per_second": 29197.867
    },
    {
      "epoch": 2.4834600083590037,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7656824709684287e-05,
      "loss": 1.0361352920532227,
      "num_input_tokens_seen": 19963016256,
      "step": 70190,
      "train_runtime": 683712.3143,
      "train_tokens_per_second": 29197.977
    },
    {
      "epoch": 2.4838138286227327,
      "grad_norm": 1.59375,
      "learning_rate": 1.765572386209575e-05,
      "loss": 1.0365182876586914,
      "num_input_tokens_seen": 19965854144,
      "step": 70200,
      "train_runtime": 683810.4899,
      "train_tokens_per_second": 29197.935
    },
    {
      "epoch": 2.4841676488864612,
      "grad_norm": 1.546875,
      "learning_rate": 1.7654623220384713e-05,
      "loss": 1.0543792724609375,
      "num_input_tokens_seen": 19968755072,
      "step": 70210,
      "train_runtime": 683910.2937,
      "train_tokens_per_second": 29197.916
    },
    {
      "epoch": 2.4845214691501902,
      "grad_norm": 1.5625,
      "learning_rate": 1.7653522784487014e-05,
      "loss": 1.0445202827453612,
      "num_input_tokens_seen": 19971626880,
      "step": 70220,
      "train_runtime": 684011.966,
      "train_tokens_per_second": 29197.774
    },
    {
      "epoch": 2.4848752894139188,
      "grad_norm": 1.6875,
      "learning_rate": 1.765242255433852e-05,
      "loss": 1.0328493118286133,
      "num_input_tokens_seen": 19974504704,
      "step": 70230,
      "train_runtime": 684110.0125,
      "train_tokens_per_second": 29197.796
    },
    {
      "epoch": 2.4852291096776478,
      "grad_norm": 1.640625,
      "learning_rate": 1.7651322529875126e-05,
      "loss": 1.048323631286621,
      "num_input_tokens_seen": 19977307968,
      "step": 70240,
      "train_runtime": 684205.2071,
      "train_tokens_per_second": 29197.831
    },
    {
      "epoch": 2.4855829299413763,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7650222711032744e-05,
      "loss": 1.030902099609375,
      "num_input_tokens_seen": 19980154560,
      "step": 70250,
      "train_runtime": 684302.3924,
      "train_tokens_per_second": 29197.844
    },
    {
      "epoch": 2.4859367502051053,
      "grad_norm": 1.6484375,
      "learning_rate": 1.764912309774733e-05,
      "loss": 1.0417071342468263,
      "num_input_tokens_seen": 19982925312,
      "step": 70260,
      "train_runtime": 684394.7065,
      "train_tokens_per_second": 29197.954
    },
    {
      "epoch": 2.486290570468834,
      "grad_norm": 1.65625,
      "learning_rate": 1.764802368995486e-05,
      "loss": 1.041130828857422,
      "num_input_tokens_seen": 19985811008,
      "step": 70270,
      "train_runtime": 684492.5197,
      "train_tokens_per_second": 29197.998
    },
    {
      "epoch": 2.486644390732563,
      "grad_norm": 1.5859375,
      "learning_rate": 1.764692448759134e-05,
      "loss": 1.0390267372131348,
      "num_input_tokens_seen": 19988728576,
      "step": 70280,
      "train_runtime": 684592.6906,
      "train_tokens_per_second": 29197.987
    },
    {
      "epoch": 2.4869982109962914,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7645825490592797e-05,
      "loss": 1.0377613067626954,
      "num_input_tokens_seen": 19991587584,
      "step": 70290,
      "train_runtime": 684693.9364,
      "train_tokens_per_second": 29197.845
    },
    {
      "epoch": 2.4873520312600204,
      "grad_norm": 1.609375,
      "learning_rate": 1.7644726698895296e-05,
      "loss": 1.0483118057250977,
      "num_input_tokens_seen": 19994424064,
      "step": 70300,
      "train_runtime": 684790.117,
      "train_tokens_per_second": 29197.886
    },
    {
      "epoch": 2.487705851523749,
      "grad_norm": 1.625,
      "learning_rate": 1.7643628112434918e-05,
      "loss": 1.0363382339477538,
      "num_input_tokens_seen": 19997281344,
      "step": 70310,
      "train_runtime": 684887.2003,
      "train_tokens_per_second": 29197.92
    },
    {
      "epoch": 2.488059671787478,
      "grad_norm": 1.5546875,
      "learning_rate": 1.764252973114779e-05,
      "loss": 1.0319355964660644,
      "num_input_tokens_seen": 20000128448,
      "step": 70320,
      "train_runtime": 684984.5186,
      "train_tokens_per_second": 29197.928
    },
    {
      "epoch": 2.4884134920512064,
      "grad_norm": 1.5703125,
      "learning_rate": 1.764143155497005e-05,
      "loss": 1.0354350090026856,
      "num_input_tokens_seen": 20002925120,
      "step": 70330,
      "train_runtime": 685079.2223,
      "train_tokens_per_second": 29197.974
    },
    {
      "epoch": 2.4887673123149354,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7640333583837874e-05,
      "loss": 1.0348269462585449,
      "num_input_tokens_seen": 20005764160,
      "step": 70340,
      "train_runtime": 685176.8558,
      "train_tokens_per_second": 29197.957
    },
    {
      "epoch": 2.4891211325786644,
      "grad_norm": 1.5625,
      "learning_rate": 1.7639235817687455e-05,
      "loss": 1.0241846084594726,
      "num_input_tokens_seen": 20008615616,
      "step": 70350,
      "train_runtime": 685275.074,
      "train_tokens_per_second": 29197.933
    },
    {
      "epoch": 2.489474952842393,
      "grad_norm": 1.546875,
      "learning_rate": 1.7638138256455024e-05,
      "loss": 1.0346773147583008,
      "num_input_tokens_seen": 20011465024,
      "step": 70360,
      "train_runtime": 685372.3395,
      "train_tokens_per_second": 29197.947
    },
    {
      "epoch": 2.489828773106122,
      "grad_norm": 1.578125,
      "learning_rate": 1.7637040900076837e-05,
      "loss": 1.0406438827514648,
      "num_input_tokens_seen": 20014335744,
      "step": 70370,
      "train_runtime": 685469.813,
      "train_tokens_per_second": 29197.983
    },
    {
      "epoch": 2.4901825933698505,
      "grad_norm": 1.625,
      "learning_rate": 1.7635943748489174e-05,
      "loss": 1.0471635818481446,
      "num_input_tokens_seen": 20017177792,
      "step": 70380,
      "train_runtime": 685568.3659,
      "train_tokens_per_second": 29197.931
    },
    {
      "epoch": 2.4905364136335795,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7634846801628348e-05,
      "loss": 1.021799087524414,
      "num_input_tokens_seen": 20020005760,
      "step": 70390,
      "train_runtime": 685664.1113,
      "train_tokens_per_second": 29197.978
    },
    {
      "epoch": 2.490890233897308,
      "grad_norm": 1.609375,
      "learning_rate": 1.7633750059430698e-05,
      "loss": 1.0402362823486329,
      "num_input_tokens_seen": 20022855936,
      "step": 70400,
      "train_runtime": 685761.1154,
      "train_tokens_per_second": 29198.004
    },
    {
      "epoch": 2.491244054161037,
      "grad_norm": 1.59375,
      "learning_rate": 1.763265352183259e-05,
      "loss": 1.044804573059082,
      "num_input_tokens_seen": 20025694464,
      "step": 70410,
      "train_runtime": 685855.2611,
      "train_tokens_per_second": 29198.135
    },
    {
      "epoch": 2.4915978744247655,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7631557188770415e-05,
      "loss": 1.030923080444336,
      "num_input_tokens_seen": 20028502272,
      "step": 70420,
      "train_runtime": 685949.4533,
      "train_tokens_per_second": 29198.219
    },
    {
      "epoch": 2.4919516946884945,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7630461060180593e-05,
      "loss": 1.0222898483276368,
      "num_input_tokens_seen": 20031350080,
      "step": 70430,
      "train_runtime": 686044.1223,
      "train_tokens_per_second": 29198.341
    },
    {
      "epoch": 2.492305514952223,
      "grad_norm": 1.5703125,
      "learning_rate": 1.762936513599958e-05,
      "loss": 1.033487606048584,
      "num_input_tokens_seen": 20034196416,
      "step": 70440,
      "train_runtime": 686143.2053,
      "train_tokens_per_second": 29198.273
    },
    {
      "epoch": 2.492659335215952,
      "grad_norm": 1.5234375,
      "learning_rate": 1.7628269416163852e-05,
      "loss": 1.0257003784179688,
      "num_input_tokens_seen": 20036979200,
      "step": 70450,
      "train_runtime": 686238.0707,
      "train_tokens_per_second": 29198.291
    },
    {
      "epoch": 2.4930131554796806,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7627173900609905e-05,
      "loss": 1.0411569595336914,
      "num_input_tokens_seen": 20039828608,
      "step": 70460,
      "train_runtime": 686337.47,
      "train_tokens_per_second": 29198.214
    },
    {
      "epoch": 2.4933669757434096,
      "grad_norm": 1.609375,
      "learning_rate": 1.762607858927428e-05,
      "loss": 1.0392009735107421,
      "num_input_tokens_seen": 20042683840,
      "step": 70470,
      "train_runtime": 686434.4994,
      "train_tokens_per_second": 29198.247
    },
    {
      "epoch": 2.493720796007138,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7624983482093533e-05,
      "loss": 1.0470592498779296,
      "num_input_tokens_seen": 20045562304,
      "step": 70480,
      "train_runtime": 686535.9857,
      "train_tokens_per_second": 29198.123
    },
    {
      "epoch": 2.494074616270867,
      "grad_norm": 1.6484375,
      "learning_rate": 1.762388857900425e-05,
      "loss": 1.0241777420043945,
      "num_input_tokens_seen": 20048406016,
      "step": 70490,
      "train_runtime": 686633.3673,
      "train_tokens_per_second": 29198.124
    },
    {
      "epoch": 2.494428436534596,
      "grad_norm": 1.6171875,
      "learning_rate": 1.762279387994305e-05,
      "loss": 1.0401315689086914,
      "num_input_tokens_seen": 20051217472,
      "step": 70500,
      "train_runtime": 686727.136,
      "train_tokens_per_second": 29198.231
    },
    {
      "epoch": 2.4947822567983247,
      "grad_norm": 1.65625,
      "learning_rate": 1.7621699384846572e-05,
      "loss": 1.0325753211975097,
      "num_input_tokens_seen": 20054047872,
      "step": 70510,
      "train_runtime": 686822.5113,
      "train_tokens_per_second": 29198.297
    },
    {
      "epoch": 2.495136077062053,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7620605093651485e-05,
      "loss": 1.041620635986328,
      "num_input_tokens_seen": 20056927616,
      "step": 70520,
      "train_runtime": 686924.4465,
      "train_tokens_per_second": 29198.157
    },
    {
      "epoch": 2.495489897325782,
      "grad_norm": 1.5546875,
      "learning_rate": 1.761951100629449e-05,
      "loss": 1.034763717651367,
      "num_input_tokens_seen": 20059779904,
      "step": 70530,
      "train_runtime": 687022.1922,
      "train_tokens_per_second": 29198.154
    },
    {
      "epoch": 2.495843717589511,
      "grad_norm": 1.65625,
      "learning_rate": 1.7618417122712306e-05,
      "loss": 1.0382463455200195,
      "num_input_tokens_seen": 20062643328,
      "step": 70540,
      "train_runtime": 687119.9065,
      "train_tokens_per_second": 29198.169
    },
    {
      "epoch": 2.4961975378532397,
      "grad_norm": 1.5625,
      "learning_rate": 1.7617323442841694e-05,
      "loss": 1.0441109657287597,
      "num_input_tokens_seen": 20065479360,
      "step": 70550,
      "train_runtime": 687216.7542,
      "train_tokens_per_second": 29198.181
    },
    {
      "epoch": 2.4965513581169687,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7616229966619426e-05,
      "loss": 1.0254087448120117,
      "num_input_tokens_seen": 20068353216,
      "step": 70560,
      "train_runtime": 687316.954,
      "train_tokens_per_second": 29198.106
    },
    {
      "epoch": 2.4969051783806973,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7615136693982312e-05,
      "loss": 1.0500760078430176,
      "num_input_tokens_seen": 20071205120,
      "step": 70570,
      "train_runtime": 687417.1253,
      "train_tokens_per_second": 29198.0
    },
    {
      "epoch": 2.4972589986444262,
      "grad_norm": 1.6015625,
      "learning_rate": 1.761404362486719e-05,
      "loss": 1.039862823486328,
      "num_input_tokens_seen": 20073973632,
      "step": 70580,
      "train_runtime": 687510.4001,
      "train_tokens_per_second": 29198.065
    },
    {
      "epoch": 2.497612818908155,
      "grad_norm": 1.5859375,
      "learning_rate": 1.761295075921092e-05,
      "loss": 1.0207703590393067,
      "num_input_tokens_seen": 20076802560,
      "step": 70590,
      "train_runtime": 687608.2284,
      "train_tokens_per_second": 29198.025
    },
    {
      "epoch": 2.4979666391718838,
      "grad_norm": 1.625,
      "learning_rate": 1.761185809695039e-05,
      "loss": 1.0327105522155762,
      "num_input_tokens_seen": 20079634944,
      "step": 70600,
      "train_runtime": 687710.321,
      "train_tokens_per_second": 29197.81
    },
    {
      "epoch": 2.4983204594356123,
      "grad_norm": 1.53125,
      "learning_rate": 1.7610765638022518e-05,
      "loss": 1.03543062210083,
      "num_input_tokens_seen": 20082539520,
      "step": 70610,
      "train_runtime": 687812.0971,
      "train_tokens_per_second": 29197.712
    },
    {
      "epoch": 2.4986742796993413,
      "grad_norm": 1.734375,
      "learning_rate": 1.760967338236425e-05,
      "loss": 1.0199213981628419,
      "num_input_tokens_seen": 20085392384,
      "step": 70620,
      "train_runtime": 687909.1177,
      "train_tokens_per_second": 29197.741
    },
    {
      "epoch": 2.49902809996307,
      "grad_norm": 1.65625,
      "learning_rate": 1.7608581329912554e-05,
      "loss": 1.0372910499572754,
      "num_input_tokens_seen": 20088244544,
      "step": 70630,
      "train_runtime": 688006.1822,
      "train_tokens_per_second": 29197.767
    },
    {
      "epoch": 2.499381920226799,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7607489480604435e-05,
      "loss": 1.0385788917541503,
      "num_input_tokens_seen": 20091088832,
      "step": 70640,
      "train_runtime": 688104.2388,
      "train_tokens_per_second": 29197.74
    },
    {
      "epoch": 2.4997357404905274,
      "grad_norm": 1.59375,
      "learning_rate": 1.760639783437692e-05,
      "loss": 1.037490463256836,
      "num_input_tokens_seen": 20093947968,
      "step": 70650,
      "train_runtime": 688203.229,
      "train_tokens_per_second": 29197.695
    },
    {
      "epoch": 2.5000895607542564,
      "grad_norm": 1.578125,
      "learning_rate": 1.7605306391167054e-05,
      "loss": 1.031712245941162,
      "num_input_tokens_seen": 20096796864,
      "step": 70660,
      "train_runtime": 688302.7,
      "train_tokens_per_second": 29197.614
    },
    {
      "epoch": 2.500443381017985,
      "grad_norm": 1.59375,
      "learning_rate": 1.7604215150911924e-05,
      "loss": 1.034970760345459,
      "num_input_tokens_seen": 20099653888,
      "step": 70670,
      "train_runtime": 688402.7513,
      "train_tokens_per_second": 29197.521
    },
    {
      "epoch": 2.500797201281714,
      "grad_norm": 1.671875,
      "learning_rate": 1.7603124113548636e-05,
      "loss": 1.0453186988830567,
      "num_input_tokens_seen": 20102535744,
      "step": 70680,
      "train_runtime": 688503.4902,
      "train_tokens_per_second": 29197.435
    },
    {
      "epoch": 2.501151021545443,
      "grad_norm": 1.578125,
      "learning_rate": 1.7602033279014336e-05,
      "loss": 1.0359989166259767,
      "num_input_tokens_seen": 20105282176,
      "step": 70690,
      "train_runtime": 688595.7878,
      "train_tokens_per_second": 29197.51
    },
    {
      "epoch": 2.5015048418091714,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7600942647246167e-05,
      "loss": 1.0444388389587402,
      "num_input_tokens_seen": 20108109184,
      "step": 70700,
      "train_runtime": 688693.2213,
      "train_tokens_per_second": 29197.484
    },
    {
      "epoch": 2.5018586620729,
      "grad_norm": 1.6171875,
      "learning_rate": 1.759985221818134e-05,
      "loss": 1.0374637603759767,
      "num_input_tokens_seen": 20110959168,
      "step": 70710,
      "train_runtime": 688788.0572,
      "train_tokens_per_second": 29197.601
    },
    {
      "epoch": 2.502212482336629,
      "grad_norm": 1.6796875,
      "learning_rate": 1.7598761991757063e-05,
      "loss": 1.0434428215026856,
      "num_input_tokens_seen": 20113792832,
      "step": 70720,
      "train_runtime": 688882.5548,
      "train_tokens_per_second": 29197.71
    },
    {
      "epoch": 2.502566302600358,
      "grad_norm": 1.59375,
      "learning_rate": 1.7597671967910576e-05,
      "loss": 1.018665885925293,
      "num_input_tokens_seen": 20116706048,
      "step": 70730,
      "train_runtime": 688984.1147,
      "train_tokens_per_second": 29197.634
    },
    {
      "epoch": 2.5029201228640865,
      "grad_norm": 1.5625,
      "learning_rate": 1.7596582146579158e-05,
      "loss": 1.0275723457336425,
      "num_input_tokens_seen": 20119553664,
      "step": 70740,
      "train_runtime": 689082.6994,
      "train_tokens_per_second": 29197.589
    },
    {
      "epoch": 2.5032739431278155,
      "grad_norm": 1.59375,
      "learning_rate": 1.7595492527700113e-05,
      "loss": 1.030484390258789,
      "num_input_tokens_seen": 20122383680,
      "step": 70750,
      "train_runtime": 689180.5165,
      "train_tokens_per_second": 29197.552
    },
    {
      "epoch": 2.503627763391544,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7594403111210754e-05,
      "loss": 1.041122817993164,
      "num_input_tokens_seen": 20125241664,
      "step": 70760,
      "train_runtime": 689277.4017,
      "train_tokens_per_second": 29197.594
    },
    {
      "epoch": 2.503981583655273,
      "grad_norm": 1.625,
      "learning_rate": 1.759331389704844e-05,
      "loss": 1.0335031509399415,
      "num_input_tokens_seen": 20128067520,
      "step": 70770,
      "train_runtime": 689372.5785,
      "train_tokens_per_second": 29197.662
    },
    {
      "epoch": 2.5043354039190016,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7592224885150554e-05,
      "loss": 1.03505859375,
      "num_input_tokens_seen": 20130945472,
      "step": 70780,
      "train_runtime": 689469.667,
      "train_tokens_per_second": 29197.725
    },
    {
      "epoch": 2.5046892241827305,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7591136075454505e-05,
      "loss": 1.038192367553711,
      "num_input_tokens_seen": 20133811840,
      "step": 70790,
      "train_runtime": 689568.1758,
      "train_tokens_per_second": 29197.71
    },
    {
      "epoch": 2.505043044446459,
      "grad_norm": 1.5390625,
      "learning_rate": 1.759004746789772e-05,
      "loss": 1.0300588607788086,
      "num_input_tokens_seen": 20136662016,
      "step": 70800,
      "train_runtime": 689665.4817,
      "train_tokens_per_second": 29197.723
    },
    {
      "epoch": 2.505396864710188,
      "grad_norm": 1.59375,
      "learning_rate": 1.7588959062417677e-05,
      "loss": 1.0384530067443847,
      "num_input_tokens_seen": 20139489600,
      "step": 70810,
      "train_runtime": 689761.3083,
      "train_tokens_per_second": 29197.766
    },
    {
      "epoch": 2.5057506849739166,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7587870858951845e-05,
      "loss": 1.0325246810913087,
      "num_input_tokens_seen": 20142356672,
      "step": 70820,
      "train_runtime": 689859.2127,
      "train_tokens_per_second": 29197.779
    },
    {
      "epoch": 2.5061045052376456,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7586782857437747e-05,
      "loss": 1.045950698852539,
      "num_input_tokens_seen": 20145186560,
      "step": 70830,
      "train_runtime": 689956.5574,
      "train_tokens_per_second": 29197.761
    },
    {
      "epoch": 2.5064583255013746,
      "grad_norm": 1.59375,
      "learning_rate": 1.7585695057812936e-05,
      "loss": 1.0364270210266113,
      "num_input_tokens_seen": 20148037056,
      "step": 70840,
      "train_runtime": 690056.3917,
      "train_tokens_per_second": 29197.667
    },
    {
      "epoch": 2.506812145765103,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7584607460014974e-05,
      "loss": 1.0485967636108398,
      "num_input_tokens_seen": 20150856640,
      "step": 70850,
      "train_runtime": 690154.6411,
      "train_tokens_per_second": 29197.596
    },
    {
      "epoch": 2.5071659660288317,
      "grad_norm": 1.59375,
      "learning_rate": 1.7583520063981454e-05,
      "loss": 1.046253490447998,
      "num_input_tokens_seen": 20153722560,
      "step": 70860,
      "train_runtime": 690251.6926,
      "train_tokens_per_second": 29197.643
    },
    {
      "epoch": 2.5075197862925607,
      "grad_norm": 1.609375,
      "learning_rate": 1.7582432869650005e-05,
      "loss": 1.0410200119018556,
      "num_input_tokens_seen": 20156559872,
      "step": 70870,
      "train_runtime": 690350.5954,
      "train_tokens_per_second": 29197.57
    },
    {
      "epoch": 2.5078736065562897,
      "grad_norm": 1.625,
      "learning_rate": 1.7581345876958283e-05,
      "loss": 1.048954391479492,
      "num_input_tokens_seen": 20159407296,
      "step": 70880,
      "train_runtime": 690448.3527,
      "train_tokens_per_second": 29197.56
    },
    {
      "epoch": 2.508227426820018,
      "grad_norm": 1.5703125,
      "learning_rate": 1.758025908584396e-05,
      "loss": 1.0226085662841797,
      "num_input_tokens_seen": 20162231168,
      "step": 70890,
      "train_runtime": 690546.054,
      "train_tokens_per_second": 29197.518
    },
    {
      "epoch": 2.508581247083747,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7579172496244738e-05,
      "loss": 1.0261170387268066,
      "num_input_tokens_seen": 20165083776,
      "step": 70900,
      "train_runtime": 690641.5897,
      "train_tokens_per_second": 29197.61
    },
    {
      "epoch": 2.5089350673474757,
      "grad_norm": 1.578125,
      "learning_rate": 1.7578086108098357e-05,
      "loss": 1.0440559387207031,
      "num_input_tokens_seen": 20167938752,
      "step": 70910,
      "train_runtime": 690736.6927,
      "train_tokens_per_second": 29197.723
    },
    {
      "epoch": 2.5092888876112047,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7576999921342574e-05,
      "loss": 1.0330398559570313,
      "num_input_tokens_seen": 20170824000,
      "step": 70920,
      "train_runtime": 690836.1298,
      "train_tokens_per_second": 29197.697
    },
    {
      "epoch": 2.5096427078749333,
      "grad_norm": 1.5703125,
      "learning_rate": 1.757591393591517e-05,
      "loss": 1.0293724060058593,
      "num_input_tokens_seen": 20173757184,
      "step": 70930,
      "train_runtime": 690940.234,
      "train_tokens_per_second": 29197.543
    },
    {
      "epoch": 2.5099965281386623,
      "grad_norm": 1.65625,
      "learning_rate": 1.757482815175397e-05,
      "loss": 1.0517236709594726,
      "num_input_tokens_seen": 20176624384,
      "step": 70940,
      "train_runtime": 691041.2118,
      "train_tokens_per_second": 29197.426
    },
    {
      "epoch": 2.510350348402391,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7573742568796796e-05,
      "loss": 1.0335943222045898,
      "num_input_tokens_seen": 20179397632,
      "step": 70950,
      "train_runtime": 691131.318,
      "train_tokens_per_second": 29197.632
    },
    {
      "epoch": 2.51070416866612,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7572657186981528e-05,
      "loss": 1.027177619934082,
      "num_input_tokens_seen": 20182239744,
      "step": 70960,
      "train_runtime": 691227.3914,
      "train_tokens_per_second": 29197.685
    },
    {
      "epoch": 2.5110579889298483,
      "grad_norm": 1.640625,
      "learning_rate": 1.7571572006246058e-05,
      "loss": 1.03250150680542,
      "num_input_tokens_seen": 20185052096,
      "step": 70970,
      "train_runtime": 691323.8023,
      "train_tokens_per_second": 29197.681
    },
    {
      "epoch": 2.5114118091935773,
      "grad_norm": 1.625,
      "learning_rate": 1.7570487026528298e-05,
      "loss": 1.0265772819519043,
      "num_input_tokens_seen": 20187876608,
      "step": 70980,
      "train_runtime": 691417.697,
      "train_tokens_per_second": 29197.801
    },
    {
      "epoch": 2.5117656294573063,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7569402247766204e-05,
      "loss": 1.0365100860595704,
      "num_input_tokens_seen": 20190655872,
      "step": 70990,
      "train_runtime": 691514.2284,
      "train_tokens_per_second": 29197.745
    },
    {
      "epoch": 2.512119449721035,
      "grad_norm": 1.6328125,
      "learning_rate": 1.756831766989775e-05,
      "loss": 1.0467074394226075,
      "num_input_tokens_seen": 20193493696,
      "step": 71000,
      "train_runtime": 691609.6931,
      "train_tokens_per_second": 29197.818
    },
    {
      "epoch": 2.5124732699847634,
      "grad_norm": 1.640625,
      "learning_rate": 1.7567233292860927e-05,
      "loss": 1.0239517211914062,
      "num_input_tokens_seen": 20196396096,
      "step": 71010,
      "train_runtime": 691709.8686,
      "train_tokens_per_second": 29197.785
    },
    {
      "epoch": 2.5128270902484924,
      "grad_norm": 1.65625,
      "learning_rate": 1.7566149116593772e-05,
      "loss": 1.050065040588379,
      "num_input_tokens_seen": 20199170688,
      "step": 71020,
      "train_runtime": 691801.7534,
      "train_tokens_per_second": 29197.918
    },
    {
      "epoch": 2.5131809105122214,
      "grad_norm": 1.59375,
      "learning_rate": 1.7565065141034336e-05,
      "loss": 1.0370341300964356,
      "num_input_tokens_seen": 20202050368,
      "step": 71030,
      "train_runtime": 691901.4207,
      "train_tokens_per_second": 29197.874
    },
    {
      "epoch": 2.51353473077595,
      "grad_norm": 1.59375,
      "learning_rate": 1.7563981366120702e-05,
      "loss": 1.0450572967529297,
      "num_input_tokens_seen": 20204947520,
      "step": 71040,
      "train_runtime": 692005.6867,
      "train_tokens_per_second": 29197.661
    },
    {
      "epoch": 2.5138885510396785,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7562897791790976e-05,
      "loss": 1.0492069244384765,
      "num_input_tokens_seen": 20207766720,
      "step": 71050,
      "train_runtime": 692101.2889,
      "train_tokens_per_second": 29197.701
    },
    {
      "epoch": 2.5142423713034074,
      "grad_norm": 1.6796875,
      "learning_rate": 1.7561814417983292e-05,
      "loss": 1.042871856689453,
      "num_input_tokens_seen": 20210606912,
      "step": 71060,
      "train_runtime": 692196.8092,
      "train_tokens_per_second": 29197.775
    },
    {
      "epoch": 2.5145961915671364,
      "grad_norm": 1.6015625,
      "learning_rate": 1.756073124463581e-05,
      "loss": 1.0326969146728515,
      "num_input_tokens_seen": 20213471168,
      "step": 71070,
      "train_runtime": 692296.938,
      "train_tokens_per_second": 29197.69
    },
    {
      "epoch": 2.514950011830865,
      "grad_norm": 1.65625,
      "learning_rate": 1.7559648271686728e-05,
      "loss": 1.037348747253418,
      "num_input_tokens_seen": 20216309632,
      "step": 71080,
      "train_runtime": 692392.5679,
      "train_tokens_per_second": 29197.757
    },
    {
      "epoch": 2.515303832094594,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7558565499074244e-05,
      "loss": 1.0345145225524903,
      "num_input_tokens_seen": 20219150528,
      "step": 71090,
      "train_runtime": 692489.3643,
      "train_tokens_per_second": 29197.778
    },
    {
      "epoch": 2.5156576523583225,
      "grad_norm": 1.609375,
      "learning_rate": 1.7557482926736613e-05,
      "loss": 1.0384387969970703,
      "num_input_tokens_seen": 20221969920,
      "step": 71100,
      "train_runtime": 692586.6985,
      "train_tokens_per_second": 29197.745
    },
    {
      "epoch": 2.5160114726220515,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7556400554612095e-05,
      "loss": 1.0301805496215821,
      "num_input_tokens_seen": 20224859456,
      "step": 71110,
      "train_runtime": 692685.5132,
      "train_tokens_per_second": 29197.751
    },
    {
      "epoch": 2.51636529288578,
      "grad_norm": 1.59375,
      "learning_rate": 1.755531838263899e-05,
      "loss": 1.036323070526123,
      "num_input_tokens_seen": 20227731328,
      "step": 71120,
      "train_runtime": 692783.2792,
      "train_tokens_per_second": 29197.776
    },
    {
      "epoch": 2.516719113149509,
      "grad_norm": 1.6953125,
      "learning_rate": 1.7554236410755618e-05,
      "loss": 1.0391746520996095,
      "num_input_tokens_seen": 20230561728,
      "step": 71130,
      "train_runtime": 692879.5892,
      "train_tokens_per_second": 29197.803
    },
    {
      "epoch": 2.517072933413238,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7553154638900324e-05,
      "loss": 1.0417469024658204,
      "num_input_tokens_seen": 20233369024,
      "step": 71140,
      "train_runtime": 692975.0718,
      "train_tokens_per_second": 29197.831
    },
    {
      "epoch": 2.5174267536769666,
      "grad_norm": 1.59375,
      "learning_rate": 1.755207306701148e-05,
      "loss": 1.048625373840332,
      "num_input_tokens_seen": 20236241920,
      "step": 71150,
      "train_runtime": 693074.1408,
      "train_tokens_per_second": 29197.803
    },
    {
      "epoch": 2.517780573940695,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7550991695027495e-05,
      "loss": 1.0389785766601562,
      "num_input_tokens_seen": 20239093888,
      "step": 71160,
      "train_runtime": 693170.0446,
      "train_tokens_per_second": 29197.877
    },
    {
      "epoch": 2.518134394204424,
      "grad_norm": 1.6015625,
      "learning_rate": 1.754991052288679e-05,
      "loss": 1.03898286819458,
      "num_input_tokens_seen": 20241943488,
      "step": 71170,
      "train_runtime": 693266.0725,
      "train_tokens_per_second": 29197.943
    },
    {
      "epoch": 2.518488214468153,
      "grad_norm": 1.59375,
      "learning_rate": 1.7548829550527827e-05,
      "loss": 1.031207275390625,
      "num_input_tokens_seen": 20244810752,
      "step": 71180,
      "train_runtime": 693362.913,
      "train_tokens_per_second": 29198.001
    },
    {
      "epoch": 2.5188420347318816,
      "grad_norm": 1.6875,
      "learning_rate": 1.7547748777889075e-05,
      "loss": 1.0265087127685546,
      "num_input_tokens_seen": 20247703104,
      "step": 71190,
      "train_runtime": 693463.2856,
      "train_tokens_per_second": 29197.945
    },
    {
      "epoch": 2.51919585499561,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7546668204909052e-05,
      "loss": 1.0409708976745606,
      "num_input_tokens_seen": 20250545472,
      "step": 71200,
      "train_runtime": 693561.4509,
      "train_tokens_per_second": 29197.911
    },
    {
      "epoch": 2.519549675259339,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7545587831526283e-05,
      "loss": 1.0401552200317383,
      "num_input_tokens_seen": 20253413440,
      "step": 71210,
      "train_runtime": 693660.6938,
      "train_tokens_per_second": 29197.868
    },
    {
      "epoch": 2.519903495523068,
      "grad_norm": 1.578125,
      "learning_rate": 1.7544507657679332e-05,
      "loss": 1.0350618362426758,
      "num_input_tokens_seen": 20256302592,
      "step": 71220,
      "train_runtime": 693760.1123,
      "train_tokens_per_second": 29197.848
    },
    {
      "epoch": 2.5202573157867967,
      "grad_norm": 1.59375,
      "learning_rate": 1.754342768330679e-05,
      "loss": 1.0174758911132813,
      "num_input_tokens_seen": 20259174336,
      "step": 71230,
      "train_runtime": 693858.6305,
      "train_tokens_per_second": 29197.842
    },
    {
      "epoch": 2.5206111360505257,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7542347908347262e-05,
      "loss": 1.0332990646362306,
      "num_input_tokens_seen": 20262036224,
      "step": 71240,
      "train_runtime": 693957.5386,
      "train_tokens_per_second": 29197.804
    },
    {
      "epoch": 2.520964956314254,
      "grad_norm": 1.609375,
      "learning_rate": 1.7541268332739394e-05,
      "loss": 1.0180647850036622,
      "num_input_tokens_seen": 20264869056,
      "step": 71250,
      "train_runtime": 694056.5769,
      "train_tokens_per_second": 29197.719
    },
    {
      "epoch": 2.521318776577983,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7540188956421847e-05,
      "loss": 1.0314628601074218,
      "num_input_tokens_seen": 20267714688,
      "step": 71260,
      "train_runtime": 694152.4908,
      "train_tokens_per_second": 29197.784
    },
    {
      "epoch": 2.5216725968417117,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7539109779333315e-05,
      "loss": 1.0321144104003905,
      "num_input_tokens_seen": 20270540288,
      "step": 71270,
      "train_runtime": 694249.3057,
      "train_tokens_per_second": 29197.783
    },
    {
      "epoch": 2.5220264171054407,
      "grad_norm": 1.5625,
      "learning_rate": 1.753803080141252e-05,
      "loss": 1.0246649742126466,
      "num_input_tokens_seen": 20273355968,
      "step": 71280,
      "train_runtime": 694343.0262,
      "train_tokens_per_second": 29197.897
    },
    {
      "epoch": 2.5223802373691693,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7536952022598202e-05,
      "loss": 1.0357545852661132,
      "num_input_tokens_seen": 20276167552,
      "step": 71290,
      "train_runtime": 694439.6762,
      "train_tokens_per_second": 29197.882
    },
    {
      "epoch": 2.5227340576328983,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7535873442829135e-05,
      "loss": 1.0417398452758788,
      "num_input_tokens_seen": 20278973056,
      "step": 71300,
      "train_runtime": 694534.2772,
      "train_tokens_per_second": 29197.944
    },
    {
      "epoch": 2.523087877896627,
      "grad_norm": 1.6171875,
      "learning_rate": 1.753479506204412e-05,
      "loss": 1.0368605613708497,
      "num_input_tokens_seen": 20281819072,
      "step": 71310,
      "train_runtime": 694629.4611,
      "train_tokens_per_second": 29198.04
    },
    {
      "epoch": 2.523441698160356,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7533716880181973e-05,
      "loss": 1.0197439193725586,
      "num_input_tokens_seen": 20284649920,
      "step": 71320,
      "train_runtime": 694724.8197,
      "train_tokens_per_second": 29198.107
    },
    {
      "epoch": 2.523795518424085,
      "grad_norm": 1.6640625,
      "learning_rate": 1.753263889718155e-05,
      "loss": 1.0345342636108399,
      "num_input_tokens_seen": 20287518336,
      "step": 71330,
      "train_runtime": 694825.9001,
      "train_tokens_per_second": 29197.988
    },
    {
      "epoch": 2.5241493386878133,
      "grad_norm": 1.6328125,
      "learning_rate": 1.753156111298173e-05,
      "loss": 1.0333967208862305,
      "num_input_tokens_seen": 20290399488,
      "step": 71340,
      "train_runtime": 694923.6986,
      "train_tokens_per_second": 29198.025
    },
    {
      "epoch": 2.524503158951542,
      "grad_norm": 1.5625,
      "learning_rate": 1.7530483527521414e-05,
      "loss": 1.0378395080566407,
      "num_input_tokens_seen": 20293213312,
      "step": 71350,
      "train_runtime": 695018.5855,
      "train_tokens_per_second": 29198.087
    },
    {
      "epoch": 2.524856979215271,
      "grad_norm": 1.6796875,
      "learning_rate": 1.752940614073953e-05,
      "loss": 1.040757942199707,
      "num_input_tokens_seen": 20295999424,
      "step": 71360,
      "train_runtime": 695114.8837,
      "train_tokens_per_second": 29198.05
    },
    {
      "epoch": 2.525210799479,
      "grad_norm": 1.6015625,
      "learning_rate": 1.752832895257503e-05,
      "loss": 1.0367169380187988,
      "num_input_tokens_seen": 20298866944,
      "step": 71370,
      "train_runtime": 695213.6236,
      "train_tokens_per_second": 29198.028
    },
    {
      "epoch": 2.5255646197427284,
      "grad_norm": 1.5703125,
      "learning_rate": 1.752725196296691e-05,
      "loss": 1.0465580940246582,
      "num_input_tokens_seen": 20301717888,
      "step": 71380,
      "train_runtime": 695309.5151,
      "train_tokens_per_second": 29198.102
    },
    {
      "epoch": 2.5259184400064574,
      "grad_norm": 1.609375,
      "learning_rate": 1.7526175171854162e-05,
      "loss": 1.0258728981018066,
      "num_input_tokens_seen": 20304618112,
      "step": 71390,
      "train_runtime": 695409.6758,
      "train_tokens_per_second": 29198.067
    },
    {
      "epoch": 2.526272260270186,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7525098579175827e-05,
      "loss": 1.041765022277832,
      "num_input_tokens_seen": 20307481920,
      "step": 71400,
      "train_runtime": 695511.0265,
      "train_tokens_per_second": 29197.93
    },
    {
      "epoch": 2.526626080533915,
      "grad_norm": 1.59375,
      "learning_rate": 1.752402218487097e-05,
      "loss": 1.028568649291992,
      "num_input_tokens_seen": 20310337024,
      "step": 71410,
      "train_runtime": 695607.5728,
      "train_tokens_per_second": 29197.981
    },
    {
      "epoch": 2.5269799007976435,
      "grad_norm": 1.546875,
      "learning_rate": 1.752294598887867e-05,
      "loss": 1.0274955749511718,
      "num_input_tokens_seen": 20313203264,
      "step": 71420,
      "train_runtime": 695703.2562,
      "train_tokens_per_second": 29198.086
    },
    {
      "epoch": 2.5273337210613724,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7521869991138047e-05,
      "loss": 1.0215212821960449,
      "num_input_tokens_seen": 20316021696,
      "step": 71430,
      "train_runtime": 695799.3673,
      "train_tokens_per_second": 29198.103
    },
    {
      "epoch": 2.527687541325101,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7520794191588235e-05,
      "loss": 1.0449066162109375,
      "num_input_tokens_seen": 20318850752,
      "step": 71440,
      "train_runtime": 695893.1669,
      "train_tokens_per_second": 29198.233
    },
    {
      "epoch": 2.52804136158883,
      "grad_norm": 1.578125,
      "learning_rate": 1.75197185901684e-05,
      "loss": 1.0238967895507813,
      "num_input_tokens_seen": 20321689920,
      "step": 71450,
      "train_runtime": 695989.4692,
      "train_tokens_per_second": 29198.272
    },
    {
      "epoch": 2.5283951818525585,
      "grad_norm": 1.65625,
      "learning_rate": 1.7518643186817734e-05,
      "loss": 1.0428394317626952,
      "num_input_tokens_seen": 20324493056,
      "step": 71460,
      "train_runtime": 696084.2421,
      "train_tokens_per_second": 29198.324
    },
    {
      "epoch": 2.5287490021162875,
      "grad_norm": 1.59375,
      "learning_rate": 1.751756798147546e-05,
      "loss": 1.0362817764282226,
      "num_input_tokens_seen": 20327357952,
      "step": 71470,
      "train_runtime": 696182.1634,
      "train_tokens_per_second": 29198.332
    },
    {
      "epoch": 2.5291028223800165,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7516492974080814e-05,
      "loss": 1.0162363052368164,
      "num_input_tokens_seen": 20330247104,
      "step": 71480,
      "train_runtime": 696282.0954,
      "train_tokens_per_second": 29198.291
    },
    {
      "epoch": 2.529456642643745,
      "grad_norm": 1.59375,
      "learning_rate": 1.7515418164573068e-05,
      "loss": 1.036035919189453,
      "num_input_tokens_seen": 20333112576,
      "step": 71490,
      "train_runtime": 696380.349,
      "train_tokens_per_second": 29198.286
    },
    {
      "epoch": 2.5298104629074736,
      "grad_norm": 1.640625,
      "learning_rate": 1.751434355289152e-05,
      "loss": 1.0453762054443358,
      "num_input_tokens_seen": 20335925760,
      "step": 71500,
      "train_runtime": 696473.5825,
      "train_tokens_per_second": 29198.417
    },
    {
      "epoch": 2.5301642831712026,
      "grad_norm": 1.6328125,
      "learning_rate": 1.751326913897549e-05,
      "loss": 1.032444667816162,
      "num_input_tokens_seen": 20338758848,
      "step": 71510,
      "train_runtime": 696570.6248,
      "train_tokens_per_second": 29198.416
    },
    {
      "epoch": 2.5305181034349316,
      "grad_norm": 1.625,
      "learning_rate": 1.751219492276433e-05,
      "loss": 1.0384626388549805,
      "num_input_tokens_seen": 20341625664,
      "step": 71520,
      "train_runtime": 696667.9121,
      "train_tokens_per_second": 29198.454
    },
    {
      "epoch": 2.53087192369866,
      "grad_norm": 1.640625,
      "learning_rate": 1.7511120904197406e-05,
      "loss": 1.0360041618347169,
      "num_input_tokens_seen": 20344459520,
      "step": 71530,
      "train_runtime": 696764.6947,
      "train_tokens_per_second": 29198.465
    },
    {
      "epoch": 2.5312257439623886,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7510047083214125e-05,
      "loss": 1.035093116760254,
      "num_input_tokens_seen": 20347315264,
      "step": 71540,
      "train_runtime": 696860.2285,
      "train_tokens_per_second": 29198.56
    },
    {
      "epoch": 2.5315795642261176,
      "grad_norm": 1.5703125,
      "learning_rate": 1.750897345975391e-05,
      "loss": 1.0355972290039062,
      "num_input_tokens_seen": 20350156416,
      "step": 71550,
      "train_runtime": 696958.1486,
      "train_tokens_per_second": 29198.534
    },
    {
      "epoch": 2.5319333844898466,
      "grad_norm": 1.625,
      "learning_rate": 1.7507900033756213e-05,
      "loss": 1.0303318977355957,
      "num_input_tokens_seen": 20352940096,
      "step": 71560,
      "train_runtime": 697051.7122,
      "train_tokens_per_second": 29198.609
    },
    {
      "epoch": 2.532287204753575,
      "grad_norm": 1.703125,
      "learning_rate": 1.750682680516052e-05,
      "loss": 1.0332200050354003,
      "num_input_tokens_seen": 20355880000,
      "step": 71570,
      "train_runtime": 697153.9754,
      "train_tokens_per_second": 29198.543
    },
    {
      "epoch": 2.532641025017304,
      "grad_norm": 1.6796875,
      "learning_rate": 1.7505753773906322e-05,
      "loss": 1.033493995666504,
      "num_input_tokens_seen": 20358729344,
      "step": 71580,
      "train_runtime": 697253.7571,
      "train_tokens_per_second": 29198.451
    },
    {
      "epoch": 2.5329948452810327,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7504680939933153e-05,
      "loss": 1.043874740600586,
      "num_input_tokens_seen": 20361543488,
      "step": 71590,
      "train_runtime": 697348.8601,
      "train_tokens_per_second": 29198.504
    },
    {
      "epoch": 2.5333486655447617,
      "grad_norm": 1.609375,
      "learning_rate": 1.7503608303180574e-05,
      "loss": 1.0362807273864747,
      "num_input_tokens_seen": 20364404352,
      "step": 71600,
      "train_runtime": 697448.279,
      "train_tokens_per_second": 29198.444
    },
    {
      "epoch": 2.5337024858084902,
      "grad_norm": 1.5625,
      "learning_rate": 1.7502535863588165e-05,
      "loss": 1.0355775833129883,
      "num_input_tokens_seen": 20367230016,
      "step": 71610,
      "train_runtime": 697543.862,
      "train_tokens_per_second": 29198.494
    },
    {
      "epoch": 2.534056306072219,
      "grad_norm": 1.578125,
      "learning_rate": 1.7501463621095532e-05,
      "loss": 1.0407910346984863,
      "num_input_tokens_seen": 20370069696,
      "step": 71620,
      "train_runtime": 697644.366,
      "train_tokens_per_second": 29198.358
    },
    {
      "epoch": 2.5344101263359478,
      "grad_norm": 1.65625,
      "learning_rate": 1.7500391575642305e-05,
      "loss": 1.0467127799987792,
      "num_input_tokens_seen": 20372935360,
      "step": 71630,
      "train_runtime": 697742.5803,
      "train_tokens_per_second": 29198.355
    },
    {
      "epoch": 2.5347639465996767,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7499319727168155e-05,
      "loss": 1.025866413116455,
      "num_input_tokens_seen": 20375760320,
      "step": 71640,
      "train_runtime": 697840.8651,
      "train_tokens_per_second": 29198.291
    },
    {
      "epoch": 2.5351177668634053,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7498248075612753e-05,
      "loss": 1.0277240753173829,
      "num_input_tokens_seen": 20378570176,
      "step": 71650,
      "train_runtime": 697935.5514,
      "train_tokens_per_second": 29198.355
    },
    {
      "epoch": 2.5354715871271343,
      "grad_norm": 1.6328125,
      "learning_rate": 1.749717662091582e-05,
      "loss": 1.0335241317749024,
      "num_input_tokens_seen": 20381461056,
      "step": 71660,
      "train_runtime": 698032.6602,
      "train_tokens_per_second": 29198.435
    },
    {
      "epoch": 2.5358254073908633,
      "grad_norm": 1.6015625,
      "learning_rate": 1.749610536301709e-05,
      "loss": 1.041363525390625,
      "num_input_tokens_seen": 20384278976,
      "step": 71670,
      "train_runtime": 698128.7666,
      "train_tokens_per_second": 29198.452
    },
    {
      "epoch": 2.536179227654592,
      "grad_norm": 1.625,
      "learning_rate": 1.749503430185633e-05,
      "loss": 1.0340948104858398,
      "num_input_tokens_seen": 20387070080,
      "step": 71680,
      "train_runtime": 698226.0531,
      "train_tokens_per_second": 29198.381
    },
    {
      "epoch": 2.5365330479183203,
      "grad_norm": 1.5546875,
      "learning_rate": 1.749396343737332e-05,
      "loss": 1.042078399658203,
      "num_input_tokens_seen": 20389926656,
      "step": 71690,
      "train_runtime": 698325.7759,
      "train_tokens_per_second": 29198.302
    },
    {
      "epoch": 2.5368868681820493,
      "grad_norm": 1.65625,
      "learning_rate": 1.7492892769507885e-05,
      "loss": 1.0463653564453126,
      "num_input_tokens_seen": 20392709184,
      "step": 71700,
      "train_runtime": 698419.739,
      "train_tokens_per_second": 29198.357
    },
    {
      "epoch": 2.5372406884457783,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7491822298199854e-05,
      "loss": 1.0376474380493164,
      "num_input_tokens_seen": 20395600960,
      "step": 71710,
      "train_runtime": 698520.7792,
      "train_tokens_per_second": 29198.274
    },
    {
      "epoch": 2.537594508709507,
      "grad_norm": 1.5859375,
      "learning_rate": 1.74907520233891e-05,
      "loss": 1.025615119934082,
      "num_input_tokens_seen": 20398470400,
      "step": 71720,
      "train_runtime": 698620.1,
      "train_tokens_per_second": 29198.23
    },
    {
      "epoch": 2.537948328973236,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7489681945015517e-05,
      "loss": 1.0429603576660156,
      "num_input_tokens_seen": 20401296832,
      "step": 71730,
      "train_runtime": 698715.3157,
      "train_tokens_per_second": 29198.296
    },
    {
      "epoch": 2.5383021492369644,
      "grad_norm": 1.609375,
      "learning_rate": 1.7488612063019018e-05,
      "loss": 1.0396735191345214,
      "num_input_tokens_seen": 20404107264,
      "step": 71740,
      "train_runtime": 698809.5712,
      "train_tokens_per_second": 29198.38
    },
    {
      "epoch": 2.5386559695006934,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7487542377339547e-05,
      "loss": 1.0324188232421876,
      "num_input_tokens_seen": 20406953792,
      "step": 71750,
      "train_runtime": 698905.7766,
      "train_tokens_per_second": 29198.433
    },
    {
      "epoch": 2.539009789764422,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7486472887917072e-05,
      "loss": 1.0397804260253907,
      "num_input_tokens_seen": 20409816768,
      "step": 71760,
      "train_runtime": 699003.6728,
      "train_tokens_per_second": 29198.44
    },
    {
      "epoch": 2.539363610028151,
      "grad_norm": 1.609375,
      "learning_rate": 1.7485403594691592e-05,
      "loss": 1.0357054710388183,
      "num_input_tokens_seen": 20412693888,
      "step": 71770,
      "train_runtime": 699103.5315,
      "train_tokens_per_second": 29198.385
    },
    {
      "epoch": 2.5397174302918795,
      "grad_norm": 1.640625,
      "learning_rate": 1.7484334497603126e-05,
      "loss": 1.0205920219421387,
      "num_input_tokens_seen": 20415487872,
      "step": 71780,
      "train_runtime": 699199.0802,
      "train_tokens_per_second": 29198.391
    },
    {
      "epoch": 2.5400712505556085,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7483265596591712e-05,
      "loss": 1.036037540435791,
      "num_input_tokens_seen": 20418321472,
      "step": 71790,
      "train_runtime": 699295.499,
      "train_tokens_per_second": 29198.417
    },
    {
      "epoch": 2.540425070819337,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7482196891597433e-05,
      "loss": 1.0330844879150392,
      "num_input_tokens_seen": 20421154816,
      "step": 71800,
      "train_runtime": 699391.5602,
      "train_tokens_per_second": 29198.458
    },
    {
      "epoch": 2.540778891083066,
      "grad_norm": 1.578125,
      "learning_rate": 1.7481128382560382e-05,
      "loss": 1.0288825035095215,
      "num_input_tokens_seen": 20423964608,
      "step": 71810,
      "train_runtime": 699490.3043,
      "train_tokens_per_second": 29198.353
    },
    {
      "epoch": 2.541132711346795,
      "grad_norm": 1.515625,
      "learning_rate": 1.748006006942068e-05,
      "loss": 1.0379628181457519,
      "num_input_tokens_seen": 20426861632,
      "step": 71820,
      "train_runtime": 699589.3987,
      "train_tokens_per_second": 29198.358
    },
    {
      "epoch": 2.5414865316105235,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7478991952118476e-05,
      "loss": 1.0244562149047851,
      "num_input_tokens_seen": 20429681792,
      "step": 71830,
      "train_runtime": 699685.192,
      "train_tokens_per_second": 29198.391
    },
    {
      "epoch": 2.541840351874252,
      "grad_norm": 1.703125,
      "learning_rate": 1.747792403059395e-05,
      "loss": 1.0292970657348632,
      "num_input_tokens_seen": 20432497280,
      "step": 71840,
      "train_runtime": 699779.7054,
      "train_tokens_per_second": 29198.471
    },
    {
      "epoch": 2.542194172137981,
      "grad_norm": 1.671875,
      "learning_rate": 1.747685630478729e-05,
      "loss": 1.0418409347534179,
      "num_input_tokens_seen": 20435354624,
      "step": 71850,
      "train_runtime": 699876.9002,
      "train_tokens_per_second": 29198.499
    },
    {
      "epoch": 2.54254799240171,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7475788774638732e-05,
      "loss": 1.030650806427002,
      "num_input_tokens_seen": 20438161600,
      "step": 71860,
      "train_runtime": 699969.9271,
      "train_tokens_per_second": 29198.628
    },
    {
      "epoch": 2.5429018126654386,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7474721440088522e-05,
      "loss": 1.0224766731262207,
      "num_input_tokens_seen": 20441053888,
      "step": 71870,
      "train_runtime": 700069.2104,
      "train_tokens_per_second": 29198.619
    },
    {
      "epoch": 2.543255632929167,
      "grad_norm": 1.578125,
      "learning_rate": 1.747365430107694e-05,
      "loss": 1.0329282760620118,
      "num_input_tokens_seen": 20443936192,
      "step": 71880,
      "train_runtime": 700167.8489,
      "train_tokens_per_second": 29198.622
    },
    {
      "epoch": 2.543609453192896,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7472587357544283e-05,
      "loss": 1.0190404891967773,
      "num_input_tokens_seen": 20446803712,
      "step": 71890,
      "train_runtime": 700263.945,
      "train_tokens_per_second": 29198.71
    },
    {
      "epoch": 2.543963273456625,
      "grad_norm": 1.65625,
      "learning_rate": 1.7471520609430883e-05,
      "loss": 1.0399824142456056,
      "num_input_tokens_seen": 20449636224,
      "step": 71900,
      "train_runtime": 700359.4857,
      "train_tokens_per_second": 29198.771
    },
    {
      "epoch": 2.5443170937203536,
      "grad_norm": 1.5625,
      "learning_rate": 1.747045405667709e-05,
      "loss": 1.0353170394897462,
      "num_input_tokens_seen": 20452428224,
      "step": 71910,
      "train_runtime": 700452.8783,
      "train_tokens_per_second": 29198.864
    },
    {
      "epoch": 2.5446709139840826,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7469387699223282e-05,
      "loss": 1.022813606262207,
      "num_input_tokens_seen": 20455261440,
      "step": 71920,
      "train_runtime": 700548.0605,
      "train_tokens_per_second": 29198.941
    },
    {
      "epoch": 2.545024734247811,
      "grad_norm": 1.671875,
      "learning_rate": 1.7468321537009867e-05,
      "loss": 1.0237547874450683,
      "num_input_tokens_seen": 20458134784,
      "step": 71930,
      "train_runtime": 700647.6666,
      "train_tokens_per_second": 29198.891
    },
    {
      "epoch": 2.54537855451154,
      "grad_norm": 1.5546875,
      "learning_rate": 1.746725556997727e-05,
      "loss": 1.0489091873168945,
      "num_input_tokens_seen": 20460955776,
      "step": 71940,
      "train_runtime": 700745.769,
      "train_tokens_per_second": 29198.829
    },
    {
      "epoch": 2.5457323747752687,
      "grad_norm": 1.640625,
      "learning_rate": 1.7466189798065948e-05,
      "loss": 1.044600486755371,
      "num_input_tokens_seen": 20463774080,
      "step": 71950,
      "train_runtime": 700843.2395,
      "train_tokens_per_second": 29198.789
    },
    {
      "epoch": 2.5460861950389977,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7465124221216382e-05,
      "loss": 1.0505943298339844,
      "num_input_tokens_seen": 20466610112,
      "step": 71960,
      "train_runtime": 700938.093,
      "train_tokens_per_second": 29198.884
    },
    {
      "epoch": 2.5464400153027267,
      "grad_norm": 1.640625,
      "learning_rate": 1.7464058839369074e-05,
      "loss": 1.0336755752563476,
      "num_input_tokens_seen": 20469394560,
      "step": 71970,
      "train_runtime": 701032.6918,
      "train_tokens_per_second": 29198.916
    },
    {
      "epoch": 2.546793835566455,
      "grad_norm": 1.5625,
      "learning_rate": 1.7462993652464556e-05,
      "loss": 1.0302765846252442,
      "num_input_tokens_seen": 20472254144,
      "step": 71980,
      "train_runtime": 701130.8187,
      "train_tokens_per_second": 29198.908
    },
    {
      "epoch": 2.5471476558301838,
      "grad_norm": 1.5546875,
      "learning_rate": 1.746192866044339e-05,
      "loss": 1.0410104751586915,
      "num_input_tokens_seen": 20475150016,
      "step": 71990,
      "train_runtime": 701231.5431,
      "train_tokens_per_second": 29198.843
    },
    {
      "epoch": 2.5475014760939128,
      "grad_norm": 1.578125,
      "learning_rate": 1.746086386324615e-05,
      "loss": 1.0391339302062987,
      "num_input_tokens_seen": 20477997248,
      "step": 72000,
      "train_runtime": 701328.5613,
      "train_tokens_per_second": 29198.864
    },
    {
      "epoch": 2.5478552963576417,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7459799260813448e-05,
      "loss": 1.0276718139648438,
      "num_input_tokens_seen": 20480808576,
      "step": 72010,
      "train_runtime": 701424.3063,
      "train_tokens_per_second": 29198.886
    },
    {
      "epoch": 2.5482091166213703,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7458734853085918e-05,
      "loss": 1.041015625,
      "num_input_tokens_seen": 20483689472,
      "step": 72020,
      "train_runtime": 701523.9275,
      "train_tokens_per_second": 29198.846
    },
    {
      "epoch": 2.548562936885099,
      "grad_norm": 1.546875,
      "learning_rate": 1.7457670640004212e-05,
      "loss": 1.0435802459716796,
      "num_input_tokens_seen": 20486498944,
      "step": 72030,
      "train_runtime": 701617.679,
      "train_tokens_per_second": 29198.949
    },
    {
      "epoch": 2.548916757148828,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7456606621509013e-05,
      "loss": 1.0313965797424316,
      "num_input_tokens_seen": 20489338176,
      "step": 72040,
      "train_runtime": 701716.0024,
      "train_tokens_per_second": 29198.904
    },
    {
      "epoch": 2.549270577412557,
      "grad_norm": 1.6640625,
      "learning_rate": 1.745554279754104e-05,
      "loss": 1.0269933700561524,
      "num_input_tokens_seen": 20492240576,
      "step": 72050,
      "train_runtime": 701817.6169,
      "train_tokens_per_second": 29198.812
    },
    {
      "epoch": 2.5496243976762853,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7454479168041013e-05,
      "loss": 1.0311915397644043,
      "num_input_tokens_seen": 20495117568,
      "step": 72060,
      "train_runtime": 701917.6645,
      "train_tokens_per_second": 29198.749
    },
    {
      "epoch": 2.5499782179400143,
      "grad_norm": 1.6171875,
      "learning_rate": 1.74534157329497e-05,
      "loss": 1.0363428115844726,
      "num_input_tokens_seen": 20497946432,
      "step": 72070,
      "train_runtime": 702012.9335,
      "train_tokens_per_second": 29198.816
    },
    {
      "epoch": 2.550332038203743,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7452352492207886e-05,
      "loss": 1.0437593460083008,
      "num_input_tokens_seen": 20500781440,
      "step": 72080,
      "train_runtime": 702107.8568,
      "train_tokens_per_second": 29198.906
    },
    {
      "epoch": 2.550685858467472,
      "grad_norm": 1.5625,
      "learning_rate": 1.7451289445756374e-05,
      "loss": 1.0296886444091797,
      "num_input_tokens_seen": 20503619904,
      "step": 72090,
      "train_runtime": 702205.8271,
      "train_tokens_per_second": 29198.875
    },
    {
      "epoch": 2.5510396787312004,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7450226593536005e-05,
      "loss": 1.035538101196289,
      "num_input_tokens_seen": 20506504192,
      "step": 72100,
      "train_runtime": 702304.1965,
      "train_tokens_per_second": 29198.892
    },
    {
      "epoch": 2.5513934989949294,
      "grad_norm": 1.5859375,
      "learning_rate": 1.744916393548763e-05,
      "loss": 1.022240161895752,
      "num_input_tokens_seen": 20509361536,
      "step": 72110,
      "train_runtime": 702404.1514,
      "train_tokens_per_second": 29198.805
    },
    {
      "epoch": 2.551747319258658,
      "grad_norm": 1.625,
      "learning_rate": 1.744810147155215e-05,
      "loss": 1.0434225082397461,
      "num_input_tokens_seen": 20512159936,
      "step": 72120,
      "train_runtime": 702502.6546,
      "train_tokens_per_second": 29198.694
    },
    {
      "epoch": 2.552101139522387,
      "grad_norm": 1.5625,
      "learning_rate": 1.7447039201670458e-05,
      "loss": 1.0254053115844726,
      "num_input_tokens_seen": 20515013056,
      "step": 72130,
      "train_runtime": 702600.2116,
      "train_tokens_per_second": 29198.7
    },
    {
      "epoch": 2.5524549597861155,
      "grad_norm": 1.625,
      "learning_rate": 1.7445977125783497e-05,
      "loss": 1.0449935913085937,
      "num_input_tokens_seen": 20517825984,
      "step": 72140,
      "train_runtime": 702697.6623,
      "train_tokens_per_second": 29198.654
    },
    {
      "epoch": 2.5528087800498445,
      "grad_norm": 1.671875,
      "learning_rate": 1.7444915243832234e-05,
      "loss": 1.046217155456543,
      "num_input_tokens_seen": 20520697984,
      "step": 72150,
      "train_runtime": 702798.6154,
      "train_tokens_per_second": 29198.546
    },
    {
      "epoch": 2.5531626003135734,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7443853555757645e-05,
      "loss": 1.0400374412536622,
      "num_input_tokens_seen": 20523585344,
      "step": 72160,
      "train_runtime": 702896.9358,
      "train_tokens_per_second": 29198.57
    },
    {
      "epoch": 2.553516420577302,
      "grad_norm": 1.6171875,
      "learning_rate": 1.744279206150074e-05,
      "loss": 1.0370914459228515,
      "num_input_tokens_seen": 20526424384,
      "step": 72170,
      "train_runtime": 702994.3148,
      "train_tokens_per_second": 29198.564
    },
    {
      "epoch": 2.5538702408410305,
      "grad_norm": 1.546875,
      "learning_rate": 1.7441730761002567e-05,
      "loss": 1.0510648727416991,
      "num_input_tokens_seen": 20529302208,
      "step": 72180,
      "train_runtime": 703094.4898,
      "train_tokens_per_second": 29198.497
    },
    {
      "epoch": 2.5542240611047595,
      "grad_norm": 1.625,
      "learning_rate": 1.7440669654204185e-05,
      "loss": 1.0239250183105468,
      "num_input_tokens_seen": 20532160512,
      "step": 72190,
      "train_runtime": 703193.1467,
      "train_tokens_per_second": 29198.465
    },
    {
      "epoch": 2.5545778813684885,
      "grad_norm": 1.59375,
      "learning_rate": 1.7439608741046666e-05,
      "loss": 1.0344970703125,
      "num_input_tokens_seen": 20535015680,
      "step": 72200,
      "train_runtime": 703291.9118,
      "train_tokens_per_second": 29198.424
    },
    {
      "epoch": 2.554931701632217,
      "grad_norm": 1.671875,
      "learning_rate": 1.7438548021471134e-05,
      "loss": 1.057102108001709,
      "num_input_tokens_seen": 20537910336,
      "step": 72210,
      "train_runtime": 703393.6672,
      "train_tokens_per_second": 29198.316
    },
    {
      "epoch": 2.555285521895946,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7437487495418724e-05,
      "loss": 1.0356021881103517,
      "num_input_tokens_seen": 20540782016,
      "step": 72220,
      "train_runtime": 703491.3387,
      "train_tokens_per_second": 29198.344
    },
    {
      "epoch": 2.5556393421596746,
      "grad_norm": 1.671875,
      "learning_rate": 1.7436427162830597e-05,
      "loss": 1.0510616302490234,
      "num_input_tokens_seen": 20543592128,
      "step": 72230,
      "train_runtime": 703588.8141,
      "train_tokens_per_second": 29198.293
    },
    {
      "epoch": 2.5559931624234036,
      "grad_norm": 1.6484375,
      "learning_rate": 1.743536702364794e-05,
      "loss": 1.0230504989624023,
      "num_input_tokens_seen": 20546470208,
      "step": 72240,
      "train_runtime": 703688.0779,
      "train_tokens_per_second": 29198.264
    },
    {
      "epoch": 2.556346982687132,
      "grad_norm": 1.5625,
      "learning_rate": 1.743430707781196e-05,
      "loss": 1.0468578338623047,
      "num_input_tokens_seen": 20549301952,
      "step": 72250,
      "train_runtime": 703787.7289,
      "train_tokens_per_second": 29198.153
    },
    {
      "epoch": 2.556700802950861,
      "grad_norm": 1.6015625,
      "learning_rate": 1.74332473252639e-05,
      "loss": 1.0369295120239257,
      "num_input_tokens_seen": 20552154176,
      "step": 72260,
      "train_runtime": 703885.3517,
      "train_tokens_per_second": 29198.156
    },
    {
      "epoch": 2.5570546232145897,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7432187765945016e-05,
      "loss": 1.0443584442138671,
      "num_input_tokens_seen": 20554992704,
      "step": 72270,
      "train_runtime": 703984.2374,
      "train_tokens_per_second": 29198.087
    },
    {
      "epoch": 2.5574084434783186,
      "grad_norm": 1.6640625,
      "learning_rate": 1.74311283997966e-05,
      "loss": 1.0297391891479493,
      "num_input_tokens_seen": 20557903744,
      "step": 72280,
      "train_runtime": 704084.2314,
      "train_tokens_per_second": 29198.074
    },
    {
      "epoch": 2.557762263742047,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7430069226759962e-05,
      "loss": 1.0356757164001464,
      "num_input_tokens_seen": 20560747520,
      "step": 72290,
      "train_runtime": 704179.3706,
      "train_tokens_per_second": 29198.168
    },
    {
      "epoch": 2.558116084005776,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7429010246776435e-05,
      "loss": 1.0354219436645509,
      "num_input_tokens_seen": 20563542208,
      "step": 72300,
      "train_runtime": 704272.1855,
      "train_tokens_per_second": 29198.288
    },
    {
      "epoch": 2.558469904269505,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7427951459787386e-05,
      "loss": 1.036043357849121,
      "num_input_tokens_seen": 20566405568,
      "step": 72310,
      "train_runtime": 704370.6759,
      "train_tokens_per_second": 29198.271
    },
    {
      "epoch": 2.5588237245332337,
      "grad_norm": 1.671875,
      "learning_rate": 1.7426892865734197e-05,
      "loss": 1.033118438720703,
      "num_input_tokens_seen": 20569259520,
      "step": 72320,
      "train_runtime": 704469.8845,
      "train_tokens_per_second": 29198.21
    },
    {
      "epoch": 2.5591775447969622,
      "grad_norm": 1.5625,
      "learning_rate": 1.742583446455828e-05,
      "loss": 1.0214186668395997,
      "num_input_tokens_seen": 20572132544,
      "step": 72330,
      "train_runtime": 704564.6872,
      "train_tokens_per_second": 29198.359
    },
    {
      "epoch": 2.5595313650606912,
      "grad_norm": 1.671875,
      "learning_rate": 1.7424776256201074e-05,
      "loss": 1.0500652313232421,
      "num_input_tokens_seen": 20574947520,
      "step": 72340,
      "train_runtime": 704659.804,
      "train_tokens_per_second": 29198.412
    },
    {
      "epoch": 2.55988518532442,
      "grad_norm": 1.6875,
      "learning_rate": 1.7423718240604035e-05,
      "loss": 1.0336706161499023,
      "num_input_tokens_seen": 20577857664,
      "step": 72350,
      "train_runtime": 704762.809,
      "train_tokens_per_second": 29198.274
    },
    {
      "epoch": 2.5602390055881488,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7422660417708656e-05,
      "loss": 1.024794578552246,
      "num_input_tokens_seen": 20580678912,
      "step": 72360,
      "train_runtime": 704859.9137,
      "train_tokens_per_second": 29198.254
    },
    {
      "epoch": 2.5605928258518773,
      "grad_norm": 1.53125,
      "learning_rate": 1.7421602787456446e-05,
      "loss": 1.0418370246887207,
      "num_input_tokens_seen": 20583452032,
      "step": 72370,
      "train_runtime": 704951.9186,
      "train_tokens_per_second": 29198.377
    },
    {
      "epoch": 2.5609466461156063,
      "grad_norm": 1.578125,
      "learning_rate": 1.7420545349788937e-05,
      "loss": 1.0303762435913086,
      "num_input_tokens_seen": 20586235200,
      "step": 72380,
      "train_runtime": 705046.6858,
      "train_tokens_per_second": 29198.4
    },
    {
      "epoch": 2.5613004663793353,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7419488104647694e-05,
      "loss": 1.028137493133545,
      "num_input_tokens_seen": 20589092928,
      "step": 72390,
      "train_runtime": 705147.0089,
      "train_tokens_per_second": 29198.299
    },
    {
      "epoch": 2.561654286643064,
      "grad_norm": 1.7109375,
      "learning_rate": 1.7418431051974298e-05,
      "loss": 1.0226737976074218,
      "num_input_tokens_seen": 20591972160,
      "step": 72400,
      "train_runtime": 705244.1237,
      "train_tokens_per_second": 29198.36
    },
    {
      "epoch": 2.562008106906793,
      "grad_norm": 1.5625,
      "learning_rate": 1.7417374191710362e-05,
      "loss": 1.0430026054382324,
      "num_input_tokens_seen": 20594829568,
      "step": 72410,
      "train_runtime": 705341.1678,
      "train_tokens_per_second": 29198.394
    },
    {
      "epoch": 2.5623619271705214,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7416317523797522e-05,
      "loss": 1.0357673645019532,
      "num_input_tokens_seen": 20597679360,
      "step": 72420,
      "train_runtime": 705435.7107,
      "train_tokens_per_second": 29198.521
    },
    {
      "epoch": 2.5627157474342503,
      "grad_norm": 1.5625,
      "learning_rate": 1.7415261048177434e-05,
      "loss": 1.0370598793029786,
      "num_input_tokens_seen": 20600511872,
      "step": 72430,
      "train_runtime": 705532.1114,
      "train_tokens_per_second": 29198.546
    },
    {
      "epoch": 2.563069567697979,
      "grad_norm": 1.671875,
      "learning_rate": 1.7414204764791785e-05,
      "loss": 1.027860736846924,
      "num_input_tokens_seen": 20603403456,
      "step": 72440,
      "train_runtime": 705631.3561,
      "train_tokens_per_second": 29198.537
    },
    {
      "epoch": 2.563423387961708,
      "grad_norm": 1.6328125,
      "learning_rate": 1.741314867358229e-05,
      "loss": 1.0518159866333008,
      "num_input_tokens_seen": 20606216256,
      "step": 72450,
      "train_runtime": 705725.9633,
      "train_tokens_per_second": 29198.609
    },
    {
      "epoch": 2.5637772082254364,
      "grad_norm": 1.5625,
      "learning_rate": 1.7412092774490668e-05,
      "loss": 1.0540843963623048,
      "num_input_tokens_seen": 20609104064,
      "step": 72460,
      "train_runtime": 705827.7581,
      "train_tokens_per_second": 29198.489
    },
    {
      "epoch": 2.5641310284891654,
      "grad_norm": 1.5703125,
      "learning_rate": 1.741103706745869e-05,
      "loss": 1.0275188446044923,
      "num_input_tokens_seen": 20611943552,
      "step": 72470,
      "train_runtime": 705928.9262,
      "train_tokens_per_second": 29198.327
    },
    {
      "epoch": 2.564484848752894,
      "grad_norm": 1.65625,
      "learning_rate": 1.740998155242814e-05,
      "loss": 1.0316118240356444,
      "num_input_tokens_seen": 20614718400,
      "step": 72480,
      "train_runtime": 706022.8671,
      "train_tokens_per_second": 29198.372
    },
    {
      "epoch": 2.564838669016623,
      "grad_norm": 1.625,
      "learning_rate": 1.740892622934082e-05,
      "loss": 1.0425684928894043,
      "num_input_tokens_seen": 20617540800,
      "step": 72490,
      "train_runtime": 706117.5801,
      "train_tokens_per_second": 29198.453
    },
    {
      "epoch": 2.565192489280352,
      "grad_norm": 1.6328125,
      "learning_rate": 1.740787109813857e-05,
      "loss": 1.027834415435791,
      "num_input_tokens_seen": 20620348352,
      "step": 72500,
      "train_runtime": 706212.3624,
      "train_tokens_per_second": 29198.509
    },
    {
      "epoch": 2.5655463095440805,
      "grad_norm": 1.578125,
      "learning_rate": 1.7406816158763242e-05,
      "loss": 1.041705322265625,
      "num_input_tokens_seen": 20623187264,
      "step": 72510,
      "train_runtime": 706310.0854,
      "train_tokens_per_second": 29198.489
    },
    {
      "epoch": 2.565900129807809,
      "grad_norm": 1.546875,
      "learning_rate": 1.7405761411156717e-05,
      "loss": 1.0276119232177734,
      "num_input_tokens_seen": 20626035456,
      "step": 72520,
      "train_runtime": 706406.698,
      "train_tokens_per_second": 29198.528
    },
    {
      "epoch": 2.566253950071538,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7404706855260906e-05,
      "loss": 1.034765625,
      "num_input_tokens_seen": 20628858880,
      "step": 72530,
      "train_runtime": 706503.4884,
      "train_tokens_per_second": 29198.524
    },
    {
      "epoch": 2.566607770335267,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7403652491017738e-05,
      "loss": 1.0468368530273438,
      "num_input_tokens_seen": 20631688512,
      "step": 72540,
      "train_runtime": 706599.7292,
      "train_tokens_per_second": 29198.551
    },
    {
      "epoch": 2.5669615905989955,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7402598318369174e-05,
      "loss": 1.0289791107177735,
      "num_input_tokens_seen": 20634507200,
      "step": 72550,
      "train_runtime": 706693.4328,
      "train_tokens_per_second": 29198.668
    },
    {
      "epoch": 2.5673154108627245,
      "grad_norm": 1.53125,
      "learning_rate": 1.7401544337257186e-05,
      "loss": 1.0413643836975097,
      "num_input_tokens_seen": 20637348352,
      "step": 72560,
      "train_runtime": 706791.2089,
      "train_tokens_per_second": 29198.649
    },
    {
      "epoch": 2.567669231126453,
      "grad_norm": 1.65625,
      "learning_rate": 1.740049054762379e-05,
      "loss": 1.0230756759643556,
      "num_input_tokens_seen": 20640215424,
      "step": 72570,
      "train_runtime": 706889.2226,
      "train_tokens_per_second": 29198.656
    },
    {
      "epoch": 2.568023051390182,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7399436949411007e-05,
      "loss": 1.0395191192626954,
      "num_input_tokens_seen": 20643027648,
      "step": 72580,
      "train_runtime": 706982.1028,
      "train_tokens_per_second": 29198.798
    },
    {
      "epoch": 2.5683768716539106,
      "grad_norm": 1.671875,
      "learning_rate": 1.7398383542560892e-05,
      "loss": 1.037757110595703,
      "num_input_tokens_seen": 20645891072,
      "step": 72590,
      "train_runtime": 707080.7439,
      "train_tokens_per_second": 29198.774
    },
    {
      "epoch": 2.5687306919176396,
      "grad_norm": 1.6328125,
      "learning_rate": 1.739733032701553e-05,
      "loss": 1.0374832153320312,
      "num_input_tokens_seen": 20648709120,
      "step": 72600,
      "train_runtime": 707176.2178,
      "train_tokens_per_second": 29198.817
    },
    {
      "epoch": 2.569084512181368,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7396277302717024e-05,
      "loss": 1.049748134613037,
      "num_input_tokens_seen": 20651559168,
      "step": 72610,
      "train_runtime": 707273.5348,
      "train_tokens_per_second": 29198.829
    },
    {
      "epoch": 2.569438332445097,
      "grad_norm": 1.578125,
      "learning_rate": 1.7395224469607495e-05,
      "loss": 1.049699592590332,
      "num_input_tokens_seen": 20654400000,
      "step": 72620,
      "train_runtime": 707371.9859,
      "train_tokens_per_second": 29198.781
    },
    {
      "epoch": 2.5697921527088257,
      "grad_norm": 1.6015625,
      "learning_rate": 1.73941718276291e-05,
      "loss": 1.0341974258422852,
      "num_input_tokens_seen": 20657272192,
      "step": 72630,
      "train_runtime": 707472.5033,
      "train_tokens_per_second": 29198.693
    },
    {
      "epoch": 2.5701459729725546,
      "grad_norm": 1.4921875,
      "learning_rate": 1.7393119376724022e-05,
      "loss": 1.043117141723633,
      "num_input_tokens_seen": 20660119040,
      "step": 72640,
      "train_runtime": 707568.2361,
      "train_tokens_per_second": 29198.766
    },
    {
      "epoch": 2.5704997932362836,
      "grad_norm": 1.5703125,
      "learning_rate": 1.739206711683445e-05,
      "loss": 1.0322357177734376,
      "num_input_tokens_seen": 20662932928,
      "step": 72650,
      "train_runtime": 707665.937,
      "train_tokens_per_second": 29198.711
    },
    {
      "epoch": 2.570853613500012,
      "grad_norm": 1.5,
      "learning_rate": 1.739101504790262e-05,
      "loss": 1.0297353744506836,
      "num_input_tokens_seen": 20665755456,
      "step": 72660,
      "train_runtime": 707761.3897,
      "train_tokens_per_second": 29198.761
    },
    {
      "epoch": 2.5712074337637407,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7389963169870784e-05,
      "loss": 1.0215118408203125,
      "num_input_tokens_seen": 20668651456,
      "step": 72670,
      "train_runtime": 707861.5672,
      "train_tokens_per_second": 29198.72
    },
    {
      "epoch": 2.5715612540274697,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7388911482681212e-05,
      "loss": 1.0224244117736816,
      "num_input_tokens_seen": 20671458752,
      "step": 72680,
      "train_runtime": 707956.7233,
      "train_tokens_per_second": 29198.76
    },
    {
      "epoch": 2.5719150742911987,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7387859986276197e-05,
      "loss": 1.044388771057129,
      "num_input_tokens_seen": 20674322048,
      "step": 72690,
      "train_runtime": 708055.9553,
      "train_tokens_per_second": 29198.712
    },
    {
      "epoch": 2.5722688945549272,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7386808680598078e-05,
      "loss": 1.0288274765014649,
      "num_input_tokens_seen": 20677222848,
      "step": 72700,
      "train_runtime": 708156.4744,
      "train_tokens_per_second": 29198.664
    },
    {
      "epoch": 2.572622714818656,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7385757565589192e-05,
      "loss": 1.0333978652954101,
      "num_input_tokens_seen": 20680008704,
      "step": 72710,
      "train_runtime": 708252.1373,
      "train_tokens_per_second": 29198.653
    },
    {
      "epoch": 2.5729765350823848,
      "grad_norm": 1.765625,
      "learning_rate": 1.7384706641191913e-05,
      "loss": 1.0302373886108398,
      "num_input_tokens_seen": 20682933632,
      "step": 72720,
      "train_runtime": 708355.9267,
      "train_tokens_per_second": 29198.504
    },
    {
      "epoch": 2.5733303553461138,
      "grad_norm": 1.578125,
      "learning_rate": 1.7383655907348643e-05,
      "loss": 1.036936378479004,
      "num_input_tokens_seen": 20685755072,
      "step": 72730,
      "train_runtime": 708452.5719,
      "train_tokens_per_second": 29198.504
    },
    {
      "epoch": 2.5736841756098423,
      "grad_norm": 1.59375,
      "learning_rate": 1.7382605364001803e-05,
      "loss": 1.0349697113037108,
      "num_input_tokens_seen": 20688576000,
      "step": 72740,
      "train_runtime": 708550.595,
      "train_tokens_per_second": 29198.446
    },
    {
      "epoch": 2.5740379958735713,
      "grad_norm": 1.59375,
      "learning_rate": 1.738155501109383e-05,
      "loss": 1.042165184020996,
      "num_input_tokens_seen": 20691433728,
      "step": 72750,
      "train_runtime": 708648.6997,
      "train_tokens_per_second": 29198.436
    },
    {
      "epoch": 2.5743918161373,
      "grad_norm": 1.59375,
      "learning_rate": 1.7380504848567207e-05,
      "loss": 1.0357250213623046,
      "num_input_tokens_seen": 20694294400,
      "step": 72760,
      "train_runtime": 708744.9915,
      "train_tokens_per_second": 29198.505
    },
    {
      "epoch": 2.574745636401029,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7379454876364413e-05,
      "loss": 1.0319669723510743,
      "num_input_tokens_seen": 20697143680,
      "step": 72770,
      "train_runtime": 708841.7411,
      "train_tokens_per_second": 29198.54
    },
    {
      "epoch": 2.5750994566647574,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7378405094427978e-05,
      "loss": 1.041044044494629,
      "num_input_tokens_seen": 20700026816,
      "step": 72780,
      "train_runtime": 708942.4451,
      "train_tokens_per_second": 29198.459
    },
    {
      "epoch": 2.5754532769284864,
      "grad_norm": 1.625,
      "learning_rate": 1.737735550270045e-05,
      "loss": 1.0463923454284667,
      "num_input_tokens_seen": 20702885952,
      "step": 72790,
      "train_runtime": 709040.7306,
      "train_tokens_per_second": 29198.444
    },
    {
      "epoch": 2.5758070971922153,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7376306101124385e-05,
      "loss": 1.0326871871948242,
      "num_input_tokens_seen": 20705759360,
      "step": 72800,
      "train_runtime": 709137.7127,
      "train_tokens_per_second": 29198.503
    },
    {
      "epoch": 2.576160917455944,
      "grad_norm": 1.609375,
      "learning_rate": 1.7375256889642376e-05,
      "loss": 1.0417254447937012,
      "num_input_tokens_seen": 20708582592,
      "step": 72810,
      "train_runtime": 709234.139,
      "train_tokens_per_second": 29198.514
    },
    {
      "epoch": 2.5765147377196724,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7374207868197044e-05,
      "loss": 1.0423618316650392,
      "num_input_tokens_seen": 20711415936,
      "step": 72820,
      "train_runtime": 709330.8314,
      "train_tokens_per_second": 29198.528
    },
    {
      "epoch": 2.5768685579834014,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7373159036731028e-05,
      "loss": 1.036679458618164,
      "num_input_tokens_seen": 20714234880,
      "step": 72830,
      "train_runtime": 709426.6846,
      "train_tokens_per_second": 29198.556
    },
    {
      "epoch": 2.5772223782471304,
      "grad_norm": 1.609375,
      "learning_rate": 1.737211039518699e-05,
      "loss": 1.0506651878356934,
      "num_input_tokens_seen": 20717062464,
      "step": 72840,
      "train_runtime": 709525.088,
      "train_tokens_per_second": 29198.492
    },
    {
      "epoch": 2.577576198510859,
      "grad_norm": 1.640625,
      "learning_rate": 1.7371061943507615e-05,
      "loss": 1.0361663818359375,
      "num_input_tokens_seen": 20719861312,
      "step": 72850,
      "train_runtime": 709618.3512,
      "train_tokens_per_second": 29198.598
    },
    {
      "epoch": 2.5779300187745875,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7370013681635626e-05,
      "loss": 1.0345247268676758,
      "num_input_tokens_seen": 20722699136,
      "step": 72860,
      "train_runtime": 709715.8532,
      "train_tokens_per_second": 29198.586
    },
    {
      "epoch": 2.5782838390383165,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7368965609513755e-05,
      "loss": 1.0188274383544922,
      "num_input_tokens_seen": 20725508736,
      "step": 72870,
      "train_runtime": 709814.6258,
      "train_tokens_per_second": 29198.481
    },
    {
      "epoch": 2.5786376593020455,
      "grad_norm": 1.65625,
      "learning_rate": 1.736791772708476e-05,
      "loss": 1.0423794746398927,
      "num_input_tokens_seen": 20728335552,
      "step": 72880,
      "train_runtime": 709910.842,
      "train_tokens_per_second": 29198.505
    },
    {
      "epoch": 2.578991479565774,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7366870034291427e-05,
      "loss": 1.0295652389526366,
      "num_input_tokens_seen": 20731187840,
      "step": 72890,
      "train_runtime": 710008.4624,
      "train_tokens_per_second": 29198.508
    },
    {
      "epoch": 2.579345299829503,
      "grad_norm": 1.6796875,
      "learning_rate": 1.736582253107657e-05,
      "loss": 1.0413851737976074,
      "num_input_tokens_seen": 20733978560,
      "step": 72900,
      "train_runtime": 710101.919,
      "train_tokens_per_second": 29198.595
    },
    {
      "epoch": 2.5796991200932315,
      "grad_norm": 1.625,
      "learning_rate": 1.736477521738302e-05,
      "loss": 1.0245348930358886,
      "num_input_tokens_seen": 20736831488,
      "step": 72910,
      "train_runtime": 710199.6798,
      "train_tokens_per_second": 29198.593
    },
    {
      "epoch": 2.5800529403569605,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7363728093153632e-05,
      "loss": 1.0384122848510742,
      "num_input_tokens_seen": 20739722624,
      "step": 72920,
      "train_runtime": 710301.1868,
      "train_tokens_per_second": 29198.491
    },
    {
      "epoch": 2.580406760620689,
      "grad_norm": 1.609375,
      "learning_rate": 1.7362681158331295e-05,
      "loss": 1.0458061218261718,
      "num_input_tokens_seen": 20742627072,
      "step": 72930,
      "train_runtime": 710400.706,
      "train_tokens_per_second": 29198.489
    },
    {
      "epoch": 2.580760580884418,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7361634412858908e-05,
      "loss": 1.0299225807189942,
      "num_input_tokens_seen": 20745470464,
      "step": 72940,
      "train_runtime": 710500.1152,
      "train_tokens_per_second": 29198.405
    },
    {
      "epoch": 2.5811144011481466,
      "grad_norm": 1.5625,
      "learning_rate": 1.7360587856679405e-05,
      "loss": 1.0393754959106445,
      "num_input_tokens_seen": 20748280128,
      "step": 72950,
      "train_runtime": 710595.5348,
      "train_tokens_per_second": 29198.439
    },
    {
      "epoch": 2.5814682214118756,
      "grad_norm": 1.640625,
      "learning_rate": 1.735954148973574e-05,
      "loss": 1.0427716255187989,
      "num_input_tokens_seen": 20751092480,
      "step": 72960,
      "train_runtime": 710691.2214,
      "train_tokens_per_second": 29198.465
    },
    {
      "epoch": 2.581822041675604,
      "grad_norm": 1.640625,
      "learning_rate": 1.7358495311970887e-05,
      "loss": 1.0366731643676759,
      "num_input_tokens_seen": 20753923712,
      "step": 72970,
      "train_runtime": 710785.1643,
      "train_tokens_per_second": 29198.589
    },
    {
      "epoch": 2.582175861939333,
      "grad_norm": 1.609375,
      "learning_rate": 1.7357449323327853e-05,
      "loss": 1.0247762680053711,
      "num_input_tokens_seen": 20756733696,
      "step": 72980,
      "train_runtime": 710881.9543,
      "train_tokens_per_second": 29198.566
    },
    {
      "epoch": 2.582529682203062,
      "grad_norm": 1.59375,
      "learning_rate": 1.7356403523749667e-05,
      "loss": 1.033622932434082,
      "num_input_tokens_seen": 20759522816,
      "step": 72990,
      "train_runtime": 710976.345,
      "train_tokens_per_second": 29198.613
    },
    {
      "epoch": 2.5828835024667907,
      "grad_norm": 1.5625,
      "learning_rate": 1.7355357913179375e-05,
      "loss": 1.031148338317871,
      "num_input_tokens_seen": 20762470848,
      "step": 73000,
      "train_runtime": 711078.1505,
      "train_tokens_per_second": 29198.578
    },
    {
      "epoch": 2.583237322730519,
      "grad_norm": 1.578125,
      "learning_rate": 1.7354312491560043e-05,
      "loss": 1.0321311950683594,
      "num_input_tokens_seen": 20765296640,
      "step": 73010,
      "train_runtime": 711172.6475,
      "train_tokens_per_second": 29198.672
    },
    {
      "epoch": 2.583591142994248,
      "grad_norm": 1.546875,
      "learning_rate": 1.7353267258834785e-05,
      "loss": 1.0340192794799805,
      "num_input_tokens_seen": 20768109120,
      "step": 73020,
      "train_runtime": 711268.4268,
      "train_tokens_per_second": 29198.694
    },
    {
      "epoch": 2.583944963257977,
      "grad_norm": 1.640625,
      "learning_rate": 1.7352222214946716e-05,
      "loss": 1.0239102363586425,
      "num_input_tokens_seen": 20770975936,
      "step": 73030,
      "train_runtime": 711368.5127,
      "train_tokens_per_second": 29198.616
    },
    {
      "epoch": 2.5842987835217057,
      "grad_norm": 1.6015625,
      "learning_rate": 1.735117735983898e-05,
      "loss": 1.0171987533569335,
      "num_input_tokens_seen": 20773825472,
      "step": 73040,
      "train_runtime": 711470.3829,
      "train_tokens_per_second": 29198.44
    },
    {
      "epoch": 2.5846526037854347,
      "grad_norm": 1.6015625,
      "learning_rate": 1.735013269345475e-05,
      "loss": 1.0353946685791016,
      "num_input_tokens_seen": 20776646144,
      "step": 73050,
      "train_runtime": 711567.0892,
      "train_tokens_per_second": 29198.436
    },
    {
      "epoch": 2.5850064240491633,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7349088215737225e-05,
      "loss": 1.0437808990478517,
      "num_input_tokens_seen": 20779489664,
      "step": 73060,
      "train_runtime": 711665.4993,
      "train_tokens_per_second": 29198.394
    },
    {
      "epoch": 2.5853602443128922,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7348043926629614e-05,
      "loss": 1.0264128684997558,
      "num_input_tokens_seen": 20782366720,
      "step": 73070,
      "train_runtime": 711763.2076,
      "train_tokens_per_second": 29198.428
    },
    {
      "epoch": 2.585714064576621,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7346999826075162e-05,
      "loss": 1.0286325454711913,
      "num_input_tokens_seen": 20785225088,
      "step": 73080,
      "train_runtime": 711862.0889,
      "train_tokens_per_second": 29198.387
    },
    {
      "epoch": 2.5860678848403498,
      "grad_norm": 1.5625,
      "learning_rate": 1.7345955914017143e-05,
      "loss": 1.0439311981201171,
      "num_input_tokens_seen": 20788115840,
      "step": 73090,
      "train_runtime": 711960.9867,
      "train_tokens_per_second": 29198.392
    },
    {
      "epoch": 2.5864217051040783,
      "grad_norm": 1.625,
      "learning_rate": 1.7344912190398834e-05,
      "loss": 1.032898235321045,
      "num_input_tokens_seen": 20790963584,
      "step": 73100,
      "train_runtime": 712058.5534,
      "train_tokens_per_second": 29198.39
    },
    {
      "epoch": 2.5867755253678073,
      "grad_norm": 1.6015625,
      "learning_rate": 1.734386865516356e-05,
      "loss": 1.0273544311523437,
      "num_input_tokens_seen": 20793819776,
      "step": 73110,
      "train_runtime": 712154.462,
      "train_tokens_per_second": 29198.469
    },
    {
      "epoch": 2.587129345631536,
      "grad_norm": 1.65625,
      "learning_rate": 1.734282530825465e-05,
      "loss": 1.043428611755371,
      "num_input_tokens_seen": 20796683840,
      "step": 73120,
      "train_runtime": 712255.3479,
      "train_tokens_per_second": 29198.354
    },
    {
      "epoch": 2.587483165895265,
      "grad_norm": 1.578125,
      "learning_rate": 1.734178214961547e-05,
      "loss": 1.0394826889038087,
      "num_input_tokens_seen": 20799500928,
      "step": 73130,
      "train_runtime": 712349.9177,
      "train_tokens_per_second": 29198.432
    },
    {
      "epoch": 2.587836986158994,
      "grad_norm": 1.546875,
      "learning_rate": 1.7340739179189408e-05,
      "loss": 1.0423120498657226,
      "num_input_tokens_seen": 20802316864,
      "step": 73140,
      "train_runtime": 712445.3065,
      "train_tokens_per_second": 29198.476
    },
    {
      "epoch": 2.5881908064227224,
      "grad_norm": 1.5234375,
      "learning_rate": 1.7339696396919868e-05,
      "loss": 1.0517769813537599,
      "num_input_tokens_seen": 20805153536,
      "step": 73150,
      "train_runtime": 712544.0323,
      "train_tokens_per_second": 29198.411
    },
    {
      "epoch": 2.588544626686451,
      "grad_norm": 1.6796875,
      "learning_rate": 1.7338653802750284e-05,
      "loss": 1.0347846031188965,
      "num_input_tokens_seen": 20808015808,
      "step": 73160,
      "train_runtime": 712641.1927,
      "train_tokens_per_second": 29198.447
    },
    {
      "epoch": 2.58889844695018,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7337611396624114e-05,
      "loss": 1.0490592956542968,
      "num_input_tokens_seen": 20810881280,
      "step": 73170,
      "train_runtime": 712739.6703,
      "train_tokens_per_second": 29198.433
    },
    {
      "epoch": 2.589252267213909,
      "grad_norm": 1.625,
      "learning_rate": 1.733656917848484e-05,
      "loss": 1.0402219772338868,
      "num_input_tokens_seen": 20813741248,
      "step": 73180,
      "train_runtime": 712835.0628,
      "train_tokens_per_second": 29198.537
    },
    {
      "epoch": 2.5896060874776374,
      "grad_norm": 1.6171875,
      "learning_rate": 1.733552714827596e-05,
      "loss": 1.0287700653076173,
      "num_input_tokens_seen": 20816625088,
      "step": 73190,
      "train_runtime": 712937.0565,
      "train_tokens_per_second": 29198.405
    },
    {
      "epoch": 2.589959907741366,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7334485305941013e-05,
      "loss": 1.0370455741882325,
      "num_input_tokens_seen": 20819518080,
      "step": 73200,
      "train_runtime": 713039.2872,
      "train_tokens_per_second": 29198.276
    },
    {
      "epoch": 2.590313728005095,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7333443651423543e-05,
      "loss": 1.0338541984558105,
      "num_input_tokens_seen": 20822403584,
      "step": 73210,
      "train_runtime": 713139.2186,
      "train_tokens_per_second": 29198.231
    },
    {
      "epoch": 2.590667548268824,
      "grad_norm": 1.625,
      "learning_rate": 1.7332402184667127e-05,
      "loss": 1.0232536315917968,
      "num_input_tokens_seen": 20825248640,
      "step": 73220,
      "train_runtime": 713235.2681,
      "train_tokens_per_second": 29198.288
    },
    {
      "epoch": 2.5910213685325525,
      "grad_norm": 1.640625,
      "learning_rate": 1.7331360905615364e-05,
      "loss": 1.0454533576965332,
      "num_input_tokens_seen": 20828073856,
      "step": 73230,
      "train_runtime": 713332.246,
      "train_tokens_per_second": 29198.279
    },
    {
      "epoch": 2.5913751887962815,
      "grad_norm": 1.6484375,
      "learning_rate": 1.733031981421188e-05,
      "loss": 1.0475595474243165,
      "num_input_tokens_seen": 20830918720,
      "step": 73240,
      "train_runtime": 713431.3348,
      "train_tokens_per_second": 29198.211
    },
    {
      "epoch": 2.59172900906001,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7329278910400316e-05,
      "loss": 1.0433822631835938,
      "num_input_tokens_seen": 20833775936,
      "step": 73250,
      "train_runtime": 713528.0676,
      "train_tokens_per_second": 29198.257
    },
    {
      "epoch": 2.592082829323739,
      "grad_norm": 1.59375,
      "learning_rate": 1.7328238194124348e-05,
      "loss": 1.0364750862121581,
      "num_input_tokens_seen": 20836626816,
      "step": 73260,
      "train_runtime": 713626.1837,
      "train_tokens_per_second": 29198.238
    },
    {
      "epoch": 2.5924366495874676,
      "grad_norm": 1.625,
      "learning_rate": 1.7327197665327667e-05,
      "loss": 1.039337158203125,
      "num_input_tokens_seen": 20839408512,
      "step": 73270,
      "train_runtime": 713719.0802,
      "train_tokens_per_second": 29198.335
    },
    {
      "epoch": 2.5927904698511965,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7326157323953994e-05,
      "loss": 1.0355443954467773,
      "num_input_tokens_seen": 20842184896,
      "step": 73280,
      "train_runtime": 713810.2321,
      "train_tokens_per_second": 29198.496
    },
    {
      "epoch": 2.593144290114925,
      "grad_norm": 1.609375,
      "learning_rate": 1.732511716994707e-05,
      "loss": 1.0382380485534668,
      "num_input_tokens_seen": 20845055808,
      "step": 73290,
      "train_runtime": 713907.7317,
      "train_tokens_per_second": 29198.529
    },
    {
      "epoch": 2.593498110378654,
      "grad_norm": 1.625,
      "learning_rate": 1.7324077203250654e-05,
      "loss": 1.0443264961242675,
      "num_input_tokens_seen": 20847931264,
      "step": 73300,
      "train_runtime": 714006.0929,
      "train_tokens_per_second": 29198.534
    },
    {
      "epoch": 2.5938519306423826,
      "grad_norm": 1.5625,
      "learning_rate": 1.7323037423808545e-05,
      "loss": 1.0297700881958007,
      "num_input_tokens_seen": 20850769152,
      "step": 73310,
      "train_runtime": 714101.004,
      "train_tokens_per_second": 29198.627
    },
    {
      "epoch": 2.5942057509061116,
      "grad_norm": 1.609375,
      "learning_rate": 1.7321997831564546e-05,
      "loss": 1.0318084716796876,
      "num_input_tokens_seen": 20853610880,
      "step": 73320,
      "train_runtime": 714198.2506,
      "train_tokens_per_second": 29198.631
    },
    {
      "epoch": 2.5945595711698406,
      "grad_norm": 1.625,
      "learning_rate": 1.7320958426462496e-05,
      "loss": 1.0394277572631836,
      "num_input_tokens_seen": 20856452352,
      "step": 73330,
      "train_runtime": 714294.5115,
      "train_tokens_per_second": 29198.674
    },
    {
      "epoch": 2.594913391433569,
      "grad_norm": 1.5546875,
      "learning_rate": 1.731991920844626e-05,
      "loss": 1.0471017837524415,
      "num_input_tokens_seen": 20859311808,
      "step": 73340,
      "train_runtime": 714393.4686,
      "train_tokens_per_second": 29198.632
    },
    {
      "epoch": 2.5952672116972977,
      "grad_norm": 1.515625,
      "learning_rate": 1.7318880177459714e-05,
      "loss": 1.0351833343505858,
      "num_input_tokens_seen": 20862189568,
      "step": 73350,
      "train_runtime": 714493.1783,
      "train_tokens_per_second": 29198.585
    },
    {
      "epoch": 2.5956210319610267,
      "grad_norm": 1.5234375,
      "learning_rate": 1.7317841333446765e-05,
      "loss": 1.0270872116088867,
      "num_input_tokens_seen": 20865010560,
      "step": 73360,
      "train_runtime": 714588.7861,
      "train_tokens_per_second": 29198.626
    },
    {
      "epoch": 2.5959748522247557,
      "grad_norm": 1.6171875,
      "learning_rate": 1.731680267635135e-05,
      "loss": 1.0363285064697265,
      "num_input_tokens_seen": 20867867264,
      "step": 73370,
      "train_runtime": 714686.6109,
      "train_tokens_per_second": 29198.626
    },
    {
      "epoch": 2.596328672488484,
      "grad_norm": 1.625,
      "learning_rate": 1.7315764206117417e-05,
      "loss": 1.0529472351074218,
      "num_input_tokens_seen": 20870682048,
      "step": 73380,
      "train_runtime": 714782.1991,
      "train_tokens_per_second": 29198.659
    },
    {
      "epoch": 2.596682492752213,
      "grad_norm": 1.625,
      "learning_rate": 1.7314725922688945e-05,
      "loss": 1.0343170166015625,
      "num_input_tokens_seen": 20873590400,
      "step": 73390,
      "train_runtime": 714882.2334,
      "train_tokens_per_second": 29198.642
    },
    {
      "epoch": 2.5970363130159417,
      "grad_norm": 1.5859375,
      "learning_rate": 1.731368782600993e-05,
      "loss": 1.0487605094909669,
      "num_input_tokens_seen": 20876455424,
      "step": 73400,
      "train_runtime": 714979.0356,
      "train_tokens_per_second": 29198.696
    },
    {
      "epoch": 2.5973901332796707,
      "grad_norm": 1.625,
      "learning_rate": 1.7312649916024402e-05,
      "loss": 1.0372756958007812,
      "num_input_tokens_seen": 20879320896,
      "step": 73410,
      "train_runtime": 715076.205,
      "train_tokens_per_second": 29198.735
    },
    {
      "epoch": 2.5977439535433993,
      "grad_norm": 1.5703125,
      "learning_rate": 1.731161219267641e-05,
      "loss": 1.0378450393676757,
      "num_input_tokens_seen": 20882183040,
      "step": 73420,
      "train_runtime": 715173.7538,
      "train_tokens_per_second": 29198.755
    },
    {
      "epoch": 2.5980977738071283,
      "grad_norm": 1.65625,
      "learning_rate": 1.731057465591002e-05,
      "loss": 1.0260846138000488,
      "num_input_tokens_seen": 20885040192,
      "step": 73430,
      "train_runtime": 715275.6616,
      "train_tokens_per_second": 29198.589
    },
    {
      "epoch": 2.598451594070857,
      "grad_norm": 1.609375,
      "learning_rate": 1.7309537305669334e-05,
      "loss": 1.0425134658813477,
      "num_input_tokens_seen": 20887862656,
      "step": 73440,
      "train_runtime": 715369.1997,
      "train_tokens_per_second": 29198.717
    },
    {
      "epoch": 2.598805414334586,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7308500141898458e-05,
      "loss": 1.0399380683898927,
      "num_input_tokens_seen": 20890725696,
      "step": 73450,
      "train_runtime": 715464.0468,
      "train_tokens_per_second": 29198.848
    },
    {
      "epoch": 2.5991592345983143,
      "grad_norm": 1.671875,
      "learning_rate": 1.730746316454155e-05,
      "loss": 1.0241090774536132,
      "num_input_tokens_seen": 20893585792,
      "step": 73460,
      "train_runtime": 715564.3244,
      "train_tokens_per_second": 29198.753
    },
    {
      "epoch": 2.5995130548620433,
      "grad_norm": 1.5859375,
      "learning_rate": 1.730642637354276e-05,
      "loss": 1.0393680572509765,
      "num_input_tokens_seen": 20896413568,
      "step": 73470,
      "train_runtime": 715659.0887,
      "train_tokens_per_second": 29198.838
    },
    {
      "epoch": 2.5998668751257723,
      "grad_norm": 1.6796875,
      "learning_rate": 1.7305389768846286e-05,
      "loss": 1.0236593246459962,
      "num_input_tokens_seen": 20899254592,
      "step": 73480,
      "train_runtime": 715755.4581,
      "train_tokens_per_second": 29198.876
    },
    {
      "epoch": 2.600220695389501,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7304353350396332e-05,
      "loss": 1.024784469604492,
      "num_input_tokens_seen": 20902064384,
      "step": 73490,
      "train_runtime": 715850.4488,
      "train_tokens_per_second": 29198.926
    },
    {
      "epoch": 2.6005745156532294,
      "grad_norm": 1.640625,
      "learning_rate": 1.7303317118137143e-05,
      "loss": 1.03966064453125,
      "num_input_tokens_seen": 20904853440,
      "step": 73500,
      "train_runtime": 715944.4085,
      "train_tokens_per_second": 29198.99
    },
    {
      "epoch": 2.6009283359169584,
      "grad_norm": 1.625,
      "learning_rate": 1.7302281072012973e-05,
      "loss": 1.0359983444213867,
      "num_input_tokens_seen": 20907649664,
      "step": 73510,
      "train_runtime": 716037.3171,
      "train_tokens_per_second": 29199.106
    },
    {
      "epoch": 2.6012821561806874,
      "grad_norm": 1.640625,
      "learning_rate": 1.7301245211968094e-05,
      "loss": 1.0287960052490235,
      "num_input_tokens_seen": 20910440256,
      "step": 73520,
      "train_runtime": 716132.335,
      "train_tokens_per_second": 29199.129
    },
    {
      "epoch": 2.601635976444416,
      "grad_norm": 1.609375,
      "learning_rate": 1.7300209537946832e-05,
      "loss": 1.0358367919921876,
      "num_input_tokens_seen": 20913234880,
      "step": 73530,
      "train_runtime": 716225.5339,
      "train_tokens_per_second": 29199.231
    },
    {
      "epoch": 2.6019897967081445,
      "grad_norm": 1.65625,
      "learning_rate": 1.7299174049893497e-05,
      "loss": 1.0366092681884767,
      "num_input_tokens_seen": 20916057088,
      "step": 73540,
      "train_runtime": 716323.0109,
      "train_tokens_per_second": 29199.198
    },
    {
      "epoch": 2.6023436169718734,
      "grad_norm": 1.65625,
      "learning_rate": 1.7298138747752453e-05,
      "loss": 1.025697612762451,
      "num_input_tokens_seen": 20918907264,
      "step": 73550,
      "train_runtime": 716421.3321,
      "train_tokens_per_second": 29199.169
    },
    {
      "epoch": 2.6026974372356024,
      "grad_norm": 1.5859375,
      "learning_rate": 1.729710363146807e-05,
      "loss": 1.0462289810180665,
      "num_input_tokens_seen": 20921776704,
      "step": 73560,
      "train_runtime": 716521.0379,
      "train_tokens_per_second": 29199.11
    },
    {
      "epoch": 2.603051257499331,
      "grad_norm": 1.625,
      "learning_rate": 1.7296068700984743e-05,
      "loss": 1.0359846115112306,
      "num_input_tokens_seen": 20924649920,
      "step": 73570,
      "train_runtime": 716619.255,
      "train_tokens_per_second": 29199.118
    },
    {
      "epoch": 2.60340507776306,
      "grad_norm": 1.609375,
      "learning_rate": 1.7295033956246902e-05,
      "loss": 1.043634033203125,
      "num_input_tokens_seen": 20927540288,
      "step": 73580,
      "train_runtime": 716719.94,
      "train_tokens_per_second": 29199.048
    },
    {
      "epoch": 2.6037588980267885,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7293999397198985e-05,
      "loss": 1.0188390731811523,
      "num_input_tokens_seen": 20930353536,
      "step": 73590,
      "train_runtime": 716815.0286,
      "train_tokens_per_second": 29199.1
    },
    {
      "epoch": 2.6041127182905175,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7292965023785464e-05,
      "loss": 1.0415985107421875,
      "num_input_tokens_seen": 20933269120,
      "step": 73600,
      "train_runtime": 716915.3705,
      "train_tokens_per_second": 29199.08
    },
    {
      "epoch": 2.604466538554246,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7291930835950827e-05,
      "loss": 1.028214454650879,
      "num_input_tokens_seen": 20936127552,
      "step": 73610,
      "train_runtime": 717012.6937,
      "train_tokens_per_second": 29199.103
    },
    {
      "epoch": 2.604820358817975,
      "grad_norm": 1.640625,
      "learning_rate": 1.72908968336396e-05,
      "loss": 1.0446977615356445,
      "num_input_tokens_seen": 20938932160,
      "step": 73620,
      "train_runtime": 717111.8576,
      "train_tokens_per_second": 29198.976
    },
    {
      "epoch": 2.6051741790817036,
      "grad_norm": 1.640625,
      "learning_rate": 1.728986301679631e-05,
      "loss": 1.0375707626342774,
      "num_input_tokens_seen": 20941741568,
      "step": 73630,
      "train_runtime": 717206.7736,
      "train_tokens_per_second": 29199.029
    },
    {
      "epoch": 2.6055279993454326,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7288829385365522e-05,
      "loss": 1.0406131744384766,
      "num_input_tokens_seen": 20944624768,
      "step": 73640,
      "train_runtime": 717306.9878,
      "train_tokens_per_second": 29198.969
    },
    {
      "epoch": 2.605881819609161,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7287795939291814e-05,
      "loss": 1.042018508911133,
      "num_input_tokens_seen": 20947419776,
      "step": 73650,
      "train_runtime": 717402.871,
      "train_tokens_per_second": 29198.963
    },
    {
      "epoch": 2.60623563987289,
      "grad_norm": 1.59375,
      "learning_rate": 1.728676267851981e-05,
      "loss": 1.0453001022338868,
      "num_input_tokens_seen": 20950244352,
      "step": 73660,
      "train_runtime": 717499.9354,
      "train_tokens_per_second": 29198.949
    },
    {
      "epoch": 2.606589460136619,
      "grad_norm": 1.5703125,
      "learning_rate": 1.728572960299412e-05,
      "loss": 1.028050994873047,
      "num_input_tokens_seen": 20953037376,
      "step": 73670,
      "train_runtime": 717593.897,
      "train_tokens_per_second": 29199.018
    },
    {
      "epoch": 2.6069432804003476,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7284696712659413e-05,
      "loss": 1.0415597915649415,
      "num_input_tokens_seen": 20955934848,
      "step": 73680,
      "train_runtime": 717693.8117,
      "train_tokens_per_second": 29198.991
    },
    {
      "epoch": 2.607297100664076,
      "grad_norm": 1.5703125,
      "learning_rate": 1.728366400746036e-05,
      "loss": 1.0307459831237793,
      "num_input_tokens_seen": 20958793728,
      "step": 73690,
      "train_runtime": 717791.4721,
      "train_tokens_per_second": 29199.001
    },
    {
      "epoch": 2.607650920927805,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7282631487341668e-05,
      "loss": 1.0376344680786134,
      "num_input_tokens_seen": 20961629568,
      "step": 73700,
      "train_runtime": 717887.5523,
      "train_tokens_per_second": 29199.043
    },
    {
      "epoch": 2.608004741191534,
      "grad_norm": 1.6484375,
      "learning_rate": 1.728159915224805e-05,
      "loss": 1.049967098236084,
      "num_input_tokens_seen": 20964455104,
      "step": 73710,
      "train_runtime": 717983.9662,
      "train_tokens_per_second": 29199.057
    },
    {
      "epoch": 2.6083585614552627,
      "grad_norm": 1.5625,
      "learning_rate": 1.728056700212426e-05,
      "loss": 1.0371708869934082,
      "num_input_tokens_seen": 20967304832,
      "step": 73720,
      "train_runtime": 718080.292,
      "train_tokens_per_second": 29199.109
    },
    {
      "epoch": 2.6087123817189917,
      "grad_norm": 1.6796875,
      "learning_rate": 1.7279535036915067e-05,
      "loss": 1.0324953079223633,
      "num_input_tokens_seen": 20970106624,
      "step": 73730,
      "train_runtime": 718175.5644,
      "train_tokens_per_second": 29199.137
    },
    {
      "epoch": 2.60906620198272,
      "grad_norm": 1.6171875,
      "learning_rate": 1.727850325656526e-05,
      "loss": 1.0304928779602052,
      "num_input_tokens_seen": 20972956032,
      "step": 73740,
      "train_runtime": 718271.1502,
      "train_tokens_per_second": 29199.218
    },
    {
      "epoch": 2.609420022246449,
      "grad_norm": 1.609375,
      "learning_rate": 1.7277471661019656e-05,
      "loss": 1.036383056640625,
      "num_input_tokens_seen": 20975826112,
      "step": 73750,
      "train_runtime": 718370.2301,
      "train_tokens_per_second": 29199.186
    },
    {
      "epoch": 2.6097738425101777,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7276440250223096e-05,
      "loss": 1.0376932144165039,
      "num_input_tokens_seen": 20978662528,
      "step": 73760,
      "train_runtime": 718467.4619,
      "train_tokens_per_second": 29199.182
    },
    {
      "epoch": 2.6101276627739067,
      "grad_norm": 1.640625,
      "learning_rate": 1.727540902412044e-05,
      "loss": 1.0252016067504883,
      "num_input_tokens_seen": 20981486208,
      "step": 73770,
      "train_runtime": 718562.312,
      "train_tokens_per_second": 29199.258
    },
    {
      "epoch": 2.6104814830376353,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7274377982656575e-05,
      "loss": 1.0442005157470704,
      "num_input_tokens_seen": 20984376768,
      "step": 73780,
      "train_runtime": 718660.5852,
      "train_tokens_per_second": 29199.287
    },
    {
      "epoch": 2.6108353033013643,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7273347125776408e-05,
      "loss": 1.0230806350708008,
      "num_input_tokens_seen": 20987196416,
      "step": 73790,
      "train_runtime": 718758.1953,
      "train_tokens_per_second": 29199.245
    },
    {
      "epoch": 2.611189123565093,
      "grad_norm": 1.5390625,
      "learning_rate": 1.727231645342487e-05,
      "loss": 1.0253418922424316,
      "num_input_tokens_seen": 20990048384,
      "step": 73800,
      "train_runtime": 718856.626,
      "train_tokens_per_second": 29199.214
    },
    {
      "epoch": 2.611542943828822,
      "grad_norm": 1.59375,
      "learning_rate": 1.727128596554691e-05,
      "loss": 1.0244155883789063,
      "num_input_tokens_seen": 20992882624,
      "step": 73810,
      "train_runtime": 718954.6303,
      "train_tokens_per_second": 29199.176
    },
    {
      "epoch": 2.611896764092551,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7270255662087515e-05,
      "loss": 1.032984447479248,
      "num_input_tokens_seen": 20995766208,
      "step": 73820,
      "train_runtime": 719053.6397,
      "train_tokens_per_second": 29199.165
    },
    {
      "epoch": 2.6122505843562793,
      "grad_norm": 1.5078125,
      "learning_rate": 1.7269225542991676e-05,
      "loss": 1.0242673873901367,
      "num_input_tokens_seen": 20998585920,
      "step": 73830,
      "train_runtime": 719148.2073,
      "train_tokens_per_second": 29199.247
    },
    {
      "epoch": 2.612604404620008,
      "grad_norm": 1.578125,
      "learning_rate": 1.726819560820442e-05,
      "loss": 1.039299774169922,
      "num_input_tokens_seen": 21001371392,
      "step": 73840,
      "train_runtime": 719241.1253,
      "train_tokens_per_second": 29199.347
    },
    {
      "epoch": 2.612958224883737,
      "grad_norm": 1.625,
      "learning_rate": 1.7267165857670794e-05,
      "loss": 1.0338326454162599,
      "num_input_tokens_seen": 21004203648,
      "step": 73850,
      "train_runtime": 719340.1325,
      "train_tokens_per_second": 29199.266
    },
    {
      "epoch": 2.613312045147466,
      "grad_norm": 1.5625,
      "learning_rate": 1.7266136291335867e-05,
      "loss": 1.0424266815185548,
      "num_input_tokens_seen": 21007036032,
      "step": 73860,
      "train_runtime": 719435.1436,
      "train_tokens_per_second": 29199.346
    },
    {
      "epoch": 2.6136658654111944,
      "grad_norm": 1.6328125,
      "learning_rate": 1.726510690914472e-05,
      "loss": 1.0373186111450194,
      "num_input_tokens_seen": 21009850816,
      "step": 73870,
      "train_runtime": 719529.2785,
      "train_tokens_per_second": 29199.438
    },
    {
      "epoch": 2.614019685674923,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7264077711042482e-05,
      "loss": 1.0241134643554688,
      "num_input_tokens_seen": 21012699328,
      "step": 73880,
      "train_runtime": 719628.5507,
      "train_tokens_per_second": 29199.369
    },
    {
      "epoch": 2.614373505938652,
      "grad_norm": 1.640625,
      "learning_rate": 1.7263048696974286e-05,
      "loss": 1.0393528938293457,
      "num_input_tokens_seen": 21015604288,
      "step": 73890,
      "train_runtime": 719728.6768,
      "train_tokens_per_second": 29199.343
    },
    {
      "epoch": 2.614727326202381,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7262019866885286e-05,
      "loss": 1.04998836517334,
      "num_input_tokens_seen": 21018489536,
      "step": 73900,
      "train_runtime": 719826.7672,
      "train_tokens_per_second": 29199.372
    },
    {
      "epoch": 2.6150811464661095,
      "grad_norm": 1.59375,
      "learning_rate": 1.7260991220720677e-05,
      "loss": 1.0311408042907715,
      "num_input_tokens_seen": 21021335488,
      "step": 73910,
      "train_runtime": 719921.3844,
      "train_tokens_per_second": 29199.488
    },
    {
      "epoch": 2.6154349667298384,
      "grad_norm": 1.609375,
      "learning_rate": 1.7259962758425654e-05,
      "loss": 1.0251912117004394,
      "num_input_tokens_seen": 21024135552,
      "step": 73920,
      "train_runtime": 720014.3039,
      "train_tokens_per_second": 29199.608
    },
    {
      "epoch": 2.615788786993567,
      "grad_norm": 1.6484375,
      "learning_rate": 1.725893447994545e-05,
      "loss": 1.02861328125,
      "num_input_tokens_seen": 21026949824,
      "step": 73930,
      "train_runtime": 720108.6876,
      "train_tokens_per_second": 29199.689
    },
    {
      "epoch": 2.616142607257296,
      "grad_norm": 1.625,
      "learning_rate": 1.725790638522532e-05,
      "loss": 1.035659408569336,
      "num_input_tokens_seen": 21029835200,
      "step": 73940,
      "train_runtime": 720208.9361,
      "train_tokens_per_second": 29199.631
    },
    {
      "epoch": 2.6164964275210245,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7256878474210535e-05,
      "loss": 1.035560131072998,
      "num_input_tokens_seen": 21032660032,
      "step": 73950,
      "train_runtime": 720305.3489,
      "train_tokens_per_second": 29199.644
    },
    {
      "epoch": 2.6168502477847535,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7255850746846394e-05,
      "loss": 1.0434463500976563,
      "num_input_tokens_seen": 21035511104,
      "step": 73960,
      "train_runtime": 720404.1238,
      "train_tokens_per_second": 29199.598
    },
    {
      "epoch": 2.6172040680484825,
      "grad_norm": 1.59375,
      "learning_rate": 1.7254823203078215e-05,
      "loss": 1.0365983963012695,
      "num_input_tokens_seen": 21038345728,
      "step": 73970,
      "train_runtime": 720505.7835,
      "train_tokens_per_second": 29199.413
    },
    {
      "epoch": 2.617557888312211,
      "grad_norm": 1.6796875,
      "learning_rate": 1.7253795842851346e-05,
      "loss": 1.0441009521484375,
      "num_input_tokens_seen": 21041184256,
      "step": 73980,
      "train_runtime": 720601.0707,
      "train_tokens_per_second": 29199.491
    },
    {
      "epoch": 2.6179117085759396,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7252768666111146e-05,
      "loss": 1.0465215682983398,
      "num_input_tokens_seen": 21044001600,
      "step": 73990,
      "train_runtime": 720697.1523,
      "train_tokens_per_second": 29199.507
    },
    {
      "epoch": 2.6182655288396686,
      "grad_norm": 1.6484375,
      "learning_rate": 1.725174167280301e-05,
      "loss": 1.0304261207580567,
      "num_input_tokens_seen": 21046825920,
      "step": 74000,
      "train_runtime": 720794.0376,
      "train_tokens_per_second": 29199.501
    },
    {
      "epoch": 2.6186193491033976,
      "grad_norm": 1.578125,
      "learning_rate": 1.7250714862872344e-05,
      "loss": 1.044468307495117,
      "num_input_tokens_seen": 21049622976,
      "step": 74010,
      "train_runtime": 720885.9618,
      "train_tokens_per_second": 29199.657
    },
    {
      "epoch": 2.618973169367126,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7249688236264586e-05,
      "loss": 1.0491365432739257,
      "num_input_tokens_seen": 21052515648,
      "step": 74020,
      "train_runtime": 720982.4094,
      "train_tokens_per_second": 29199.763
    },
    {
      "epoch": 2.6193269896308546,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7248661792925187e-05,
      "loss": 1.0313045501708984,
      "num_input_tokens_seen": 21055384128,
      "step": 74030,
      "train_runtime": 721079.7161,
      "train_tokens_per_second": 29199.801
    },
    {
      "epoch": 2.6196808098945836,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7247635532799638e-05,
      "loss": 1.0591121673583985,
      "num_input_tokens_seen": 21058265024,
      "step": 74040,
      "train_runtime": 721180.0187,
      "train_tokens_per_second": 29199.734
    },
    {
      "epoch": 2.6200346301583126,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7246609455833433e-05,
      "loss": 1.0504627227783203,
      "num_input_tokens_seen": 21061118592,
      "step": 74050,
      "train_runtime": 721278.7323,
      "train_tokens_per_second": 29199.694
    },
    {
      "epoch": 2.620388450422041,
      "grad_norm": 1.5234375,
      "learning_rate": 1.7245583561972093e-05,
      "loss": 1.0431556701660156,
      "num_input_tokens_seen": 21063940864,
      "step": 74060,
      "train_runtime": 721373.6164,
      "train_tokens_per_second": 29199.766
    },
    {
      "epoch": 2.62074227068577,
      "grad_norm": 1.59375,
      "learning_rate": 1.724455785116118e-05,
      "loss": 1.0296178817749024,
      "num_input_tokens_seen": 21066691904,
      "step": 74070,
      "train_runtime": 721463.8437,
      "train_tokens_per_second": 29199.927
    },
    {
      "epoch": 2.6210960909494987,
      "grad_norm": 1.53125,
      "learning_rate": 1.7243532323346245e-05,
      "loss": 1.0335490226745605,
      "num_input_tokens_seen": 21069529344,
      "step": 74080,
      "train_runtime": 721562.0348,
      "train_tokens_per_second": 29199.886
    },
    {
      "epoch": 2.6214499112132277,
      "grad_norm": 1.609375,
      "learning_rate": 1.7242506978472894e-05,
      "loss": 1.035957145690918,
      "num_input_tokens_seen": 21072362368,
      "step": 74090,
      "train_runtime": 721660.9655,
      "train_tokens_per_second": 29199.809
    },
    {
      "epoch": 2.6218037314769562,
      "grad_norm": 1.625,
      "learning_rate": 1.724148181648674e-05,
      "loss": 1.031332015991211,
      "num_input_tokens_seen": 21075212032,
      "step": 74100,
      "train_runtime": 721759.466,
      "train_tokens_per_second": 29199.772
    },
    {
      "epoch": 2.622157551740685,
      "grad_norm": 1.65625,
      "learning_rate": 1.7240456837333422e-05,
      "loss": 1.0312532424926757,
      "num_input_tokens_seen": 21078059712,
      "step": 74110,
      "train_runtime": 721858.2957,
      "train_tokens_per_second": 29199.719
    },
    {
      "epoch": 2.6225113720044138,
      "grad_norm": 1.65625,
      "learning_rate": 1.72394320409586e-05,
      "loss": 1.026190185546875,
      "num_input_tokens_seen": 21080842944,
      "step": 74120,
      "train_runtime": 721951.8409,
      "train_tokens_per_second": 29199.791
    },
    {
      "epoch": 2.6228651922681427,
      "grad_norm": 1.59375,
      "learning_rate": 1.7238407427307952e-05,
      "loss": 1.048473834991455,
      "num_input_tokens_seen": 21083691840,
      "step": 74130,
      "train_runtime": 722049.6095,
      "train_tokens_per_second": 29199.783
    },
    {
      "epoch": 2.6232190125318713,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7237382996327196e-05,
      "loss": 1.0365747451782226,
      "num_input_tokens_seen": 21086498176,
      "step": 74140,
      "train_runtime": 722145.556,
      "train_tokens_per_second": 29199.789
    },
    {
      "epoch": 2.6235728327956003,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7236358747962054e-05,
      "loss": 1.034881591796875,
      "num_input_tokens_seen": 21089361856,
      "step": 74150,
      "train_runtime": 722245.9049,
      "train_tokens_per_second": 29199.697
    },
    {
      "epoch": 2.6239266530593293,
      "grad_norm": 1.6484375,
      "learning_rate": 1.723533468215827e-05,
      "loss": 1.0393529891967774,
      "num_input_tokens_seen": 21092201920,
      "step": 74160,
      "train_runtime": 722342.9705,
      "train_tokens_per_second": 29199.705
    },
    {
      "epoch": 2.624280473323058,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7234310798861627e-05,
      "loss": 1.0304763793945313,
      "num_input_tokens_seen": 21095045888,
      "step": 74170,
      "train_runtime": 722441.9564,
      "train_tokens_per_second": 29199.641
    },
    {
      "epoch": 2.6246342935867863,
      "grad_norm": 1.5703125,
      "learning_rate": 1.723328709801792e-05,
      "loss": 1.029227066040039,
      "num_input_tokens_seen": 21097907136,
      "step": 74180,
      "train_runtime": 722538.778,
      "train_tokens_per_second": 29199.688
    },
    {
      "epoch": 2.6249881138505153,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7232263579572966e-05,
      "loss": 1.0462636947631836,
      "num_input_tokens_seen": 21100776960,
      "step": 74190,
      "train_runtime": 722635.0065,
      "train_tokens_per_second": 29199.771
    },
    {
      "epoch": 2.6253419341142443,
      "grad_norm": 1.5625,
      "learning_rate": 1.723124024347261e-05,
      "loss": 1.0322845458984375,
      "num_input_tokens_seen": 21103612416,
      "step": 74200,
      "train_runtime": 722733.6798,
      "train_tokens_per_second": 29199.708
    },
    {
      "epoch": 2.625695754377973,
      "grad_norm": 1.6640625,
      "learning_rate": 1.723021708966271e-05,
      "loss": 1.0425363540649415,
      "num_input_tokens_seen": 21106506368,
      "step": 74210,
      "train_runtime": 722835.2299,
      "train_tokens_per_second": 29199.609
    },
    {
      "epoch": 2.626049574641702,
      "grad_norm": 1.65625,
      "learning_rate": 1.7229194118089154e-05,
      "loss": 1.0427579879760742,
      "num_input_tokens_seen": 21109353856,
      "step": 74220,
      "train_runtime": 722935.5759,
      "train_tokens_per_second": 29199.495
    },
    {
      "epoch": 2.6264033949054304,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7228171328697853e-05,
      "loss": 1.0292658805847168,
      "num_input_tokens_seen": 21112211456,
      "step": 74230,
      "train_runtime": 723033.1067,
      "train_tokens_per_second": 29199.509
    },
    {
      "epoch": 2.6267572151691594,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7227148721434737e-05,
      "loss": 1.0247881889343262,
      "num_input_tokens_seen": 21115057344,
      "step": 74240,
      "train_runtime": 723128.9698,
      "train_tokens_per_second": 29199.573
    },
    {
      "epoch": 2.627111035432888,
      "grad_norm": 1.59375,
      "learning_rate": 1.7226126296245764e-05,
      "loss": 1.0402429580688477,
      "num_input_tokens_seen": 21117978752,
      "step": 74250,
      "train_runtime": 723232.2662,
      "train_tokens_per_second": 29199.442
    },
    {
      "epoch": 2.627464855696617,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7225104053076904e-05,
      "loss": 1.0497488021850585,
      "num_input_tokens_seen": 21120835712,
      "step": 74260,
      "train_runtime": 723331.0984,
      "train_tokens_per_second": 29199.402
    },
    {
      "epoch": 2.6278186759603455,
      "grad_norm": 1.5625,
      "learning_rate": 1.722408199187416e-05,
      "loss": 1.0302837371826172,
      "num_input_tokens_seen": 21123661312,
      "step": 74270,
      "train_runtime": 723428.0854,
      "train_tokens_per_second": 29199.393
    },
    {
      "epoch": 2.6281724962240745,
      "grad_norm": 1.6171875,
      "learning_rate": 1.722306011258355e-05,
      "loss": 1.0460431098937988,
      "num_input_tokens_seen": 21126457792,
      "step": 74280,
      "train_runtime": 723523.2487,
      "train_tokens_per_second": 29199.418
    },
    {
      "epoch": 2.628526316487803,
      "grad_norm": 1.640625,
      "learning_rate": 1.7222038415151115e-05,
      "loss": 1.0201163291931152,
      "num_input_tokens_seen": 21129291136,
      "step": 74290,
      "train_runtime": 723620.8537,
      "train_tokens_per_second": 29199.395
    },
    {
      "epoch": 2.628880136751532,
      "grad_norm": 1.5625,
      "learning_rate": 1.7221016899522925e-05,
      "loss": 1.0347099304199219,
      "num_input_tokens_seen": 21132155264,
      "step": 74300,
      "train_runtime": 723718.9605,
      "train_tokens_per_second": 29199.394
    },
    {
      "epoch": 2.629233957015261,
      "grad_norm": 1.578125,
      "learning_rate": 1.7219995565645076e-05,
      "loss": 1.0411623001098633,
      "num_input_tokens_seen": 21135021504,
      "step": 74310,
      "train_runtime": 723816.8073,
      "train_tokens_per_second": 29199.407
    },
    {
      "epoch": 2.6295877772789895,
      "grad_norm": 1.5859375,
      "learning_rate": 1.721897441346366e-05,
      "loss": 1.030312728881836,
      "num_input_tokens_seen": 21137851712,
      "step": 74320,
      "train_runtime": 723911.1569,
      "train_tokens_per_second": 29199.511
    },
    {
      "epoch": 2.629941597542718,
      "grad_norm": 1.6171875,
      "learning_rate": 1.721795344292483e-05,
      "loss": 1.036593246459961,
      "num_input_tokens_seen": 21140660928,
      "step": 74330,
      "train_runtime": 724006.5529,
      "train_tokens_per_second": 29199.544
    },
    {
      "epoch": 2.630295417806447,
      "grad_norm": 1.609375,
      "learning_rate": 1.7216932653974727e-05,
      "loss": 1.0361680030822753,
      "num_input_tokens_seen": 21143533184,
      "step": 74340,
      "train_runtime": 724104.2379,
      "train_tokens_per_second": 29199.571
    },
    {
      "epoch": 2.630649238070176,
      "grad_norm": 1.59375,
      "learning_rate": 1.7215912046559533e-05,
      "loss": 1.0328497886657715,
      "num_input_tokens_seen": 21146320576,
      "step": 74350,
      "train_runtime": 724200.5488,
      "train_tokens_per_second": 29199.537
    },
    {
      "epoch": 2.6310030583339046,
      "grad_norm": 1.59375,
      "learning_rate": 1.7214891620625454e-05,
      "loss": 1.048986053466797,
      "num_input_tokens_seen": 21149176960,
      "step": 74360,
      "train_runtime": 724297.9381,
      "train_tokens_per_second": 29199.554
    },
    {
      "epoch": 2.631356878597633,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7213871376118704e-05,
      "loss": 1.041756820678711,
      "num_input_tokens_seen": 21152039488,
      "step": 74370,
      "train_runtime": 724393.7982,
      "train_tokens_per_second": 29199.642
    },
    {
      "epoch": 2.631710698861362,
      "grad_norm": 1.734375,
      "learning_rate": 1.721285131298553e-05,
      "loss": 1.050881576538086,
      "num_input_tokens_seen": 21154890176,
      "step": 74380,
      "train_runtime": 724490.4371,
      "train_tokens_per_second": 29199.682
    },
    {
      "epoch": 2.632064519125091,
      "grad_norm": 1.609375,
      "learning_rate": 1.72118314311722e-05,
      "loss": 1.0407476425170898,
      "num_input_tokens_seen": 21157692672,
      "step": 74390,
      "train_runtime": 724586.1303,
      "train_tokens_per_second": 29199.693
    },
    {
      "epoch": 2.6324183393888196,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7210811730625004e-05,
      "loss": 1.0424415588378906,
      "num_input_tokens_seen": 21160574016,
      "step": 74400,
      "train_runtime": 724685.8502,
      "train_tokens_per_second": 29199.651
    },
    {
      "epoch": 2.6327721596525486,
      "grad_norm": 1.609375,
      "learning_rate": 1.720979221129026e-05,
      "loss": 1.0314376831054688,
      "num_input_tokens_seen": 21163414784,
      "step": 74410,
      "train_runtime": 724781.8073,
      "train_tokens_per_second": 29199.705
    },
    {
      "epoch": 2.633125979916277,
      "grad_norm": 1.7265625,
      "learning_rate": 1.7208772873114285e-05,
      "loss": 1.0495695114135741,
      "num_input_tokens_seen": 21166249216,
      "step": 74420,
      "train_runtime": 724877.0093,
      "train_tokens_per_second": 29199.78
    },
    {
      "epoch": 2.633479800180006,
      "grad_norm": 1.5625,
      "learning_rate": 1.720775371604345e-05,
      "loss": 1.0367534637451172,
      "num_input_tokens_seen": 21169072000,
      "step": 74430,
      "train_runtime": 724972.4333,
      "train_tokens_per_second": 29199.83
    },
    {
      "epoch": 2.6338336204437347,
      "grad_norm": 1.59375,
      "learning_rate": 1.7206734740024123e-05,
      "loss": 1.0510353088378905,
      "num_input_tokens_seen": 21171826496,
      "step": 74440,
      "train_runtime": 725067.7745,
      "train_tokens_per_second": 29199.79
    },
    {
      "epoch": 2.6341874407074637,
      "grad_norm": 1.59375,
      "learning_rate": 1.7205715945002714e-05,
      "loss": 1.0388142585754394,
      "num_input_tokens_seen": 21174732928,
      "step": 74450,
      "train_runtime": 725168.8324,
      "train_tokens_per_second": 29199.728
    },
    {
      "epoch": 2.6345412609711922,
      "grad_norm": 1.6328125,
      "learning_rate": 1.720469733092564e-05,
      "loss": 1.0323932647705079,
      "num_input_tokens_seen": 21177572160,
      "step": 74460,
      "train_runtime": 725262.3191,
      "train_tokens_per_second": 29199.879
    },
    {
      "epoch": 2.634895081234921,
      "grad_norm": 1.578125,
      "learning_rate": 1.7203678897739344e-05,
      "loss": 1.0400453567504884,
      "num_input_tokens_seen": 21180421568,
      "step": 74470,
      "train_runtime": 725361.6561,
      "train_tokens_per_second": 29199.809
    },
    {
      "epoch": 2.6352489014986498,
      "grad_norm": 1.671875,
      "learning_rate": 1.72026606453903e-05,
      "loss": 1.0249276161193848,
      "num_input_tokens_seen": 21183226624,
      "step": 74480,
      "train_runtime": 725457.8868,
      "train_tokens_per_second": 29199.802
    },
    {
      "epoch": 2.6356027217623788,
      "grad_norm": 1.609375,
      "learning_rate": 1.7201642573824997e-05,
      "loss": 1.038792324066162,
      "num_input_tokens_seen": 21186133120,
      "step": 74490,
      "train_runtime": 725556.983,
      "train_tokens_per_second": 29199.82
    },
    {
      "epoch": 2.6359565420261077,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7200624682989938e-05,
      "loss": 1.026932430267334,
      "num_input_tokens_seen": 21188933696,
      "step": 74500,
      "train_runtime": 725653.0895,
      "train_tokens_per_second": 29199.812
    },
    {
      "epoch": 2.6363103622898363,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7199606972831665e-05,
      "loss": 1.0308568000793457,
      "num_input_tokens_seen": 21191812480,
      "step": 74510,
      "train_runtime": 725751.258,
      "train_tokens_per_second": 29199.829
    },
    {
      "epoch": 2.636664182553565,
      "grad_norm": 1.625,
      "learning_rate": 1.7198589443296727e-05,
      "loss": 1.0433834075927735,
      "num_input_tokens_seen": 21194666944,
      "step": 74520,
      "train_runtime": 725849.0859,
      "train_tokens_per_second": 29199.826
    },
    {
      "epoch": 2.637018002817294,
      "grad_norm": 1.625,
      "learning_rate": 1.7197572094331708e-05,
      "loss": 1.0306610107421874,
      "num_input_tokens_seen": 21197567488,
      "step": 74530,
      "train_runtime": 725950.0252,
      "train_tokens_per_second": 29199.761
    },
    {
      "epoch": 2.637371823081023,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7196554925883205e-05,
      "loss": 1.034794235229492,
      "num_input_tokens_seen": 21200438720,
      "step": 74540,
      "train_runtime": 726049.6604,
      "train_tokens_per_second": 29199.709
    },
    {
      "epoch": 2.6377256433447513,
      "grad_norm": 1.6328125,
      "learning_rate": 1.719553793789784e-05,
      "loss": 1.018881893157959,
      "num_input_tokens_seen": 21203302528,
      "step": 74550,
      "train_runtime": 726148.7516,
      "train_tokens_per_second": 29199.668
    },
    {
      "epoch": 2.6380794636084803,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7194521130322257e-05,
      "loss": 1.032090950012207,
      "num_input_tokens_seen": 21206112320,
      "step": 74560,
      "train_runtime": 726244.9481,
      "train_tokens_per_second": 29199.669
    },
    {
      "epoch": 2.638433283872209,
      "grad_norm": 1.6796875,
      "learning_rate": 1.719350450310313e-05,
      "loss": 1.0204669952392578,
      "num_input_tokens_seen": 21208951360,
      "step": 74570,
      "train_runtime": 726342.0291,
      "train_tokens_per_second": 29199.675
    },
    {
      "epoch": 2.638787104135938,
      "grad_norm": 1.6484375,
      "learning_rate": 1.719248805618713e-05,
      "loss": 1.0472336769104005,
      "num_input_tokens_seen": 21211793536,
      "step": 74580,
      "train_runtime": 726437.0486,
      "train_tokens_per_second": 29199.768
    },
    {
      "epoch": 2.6391409243996664,
      "grad_norm": 1.546875,
      "learning_rate": 1.7191471789520986e-05,
      "loss": 1.047210693359375,
      "num_input_tokens_seen": 21214634752,
      "step": 74590,
      "train_runtime": 726534.8444,
      "train_tokens_per_second": 29199.749
    },
    {
      "epoch": 2.6394947446633954,
      "grad_norm": 1.640625,
      "learning_rate": 1.7190455703051418e-05,
      "loss": 1.043419647216797,
      "num_input_tokens_seen": 21217478016,
      "step": 74600,
      "train_runtime": 726632.3109,
      "train_tokens_per_second": 29199.745
    },
    {
      "epoch": 2.639848564927124,
      "grad_norm": 1.5546875,
      "learning_rate": 1.718943979672519e-05,
      "loss": 1.0348834991455078,
      "num_input_tokens_seen": 21220320320,
      "step": 74610,
      "train_runtime": 726729.9157,
      "train_tokens_per_second": 29199.734
    },
    {
      "epoch": 2.640202385190853,
      "grad_norm": 1.625,
      "learning_rate": 1.7188424070489067e-05,
      "loss": 1.0420114517211914,
      "num_input_tokens_seen": 21223128576,
      "step": 74620,
      "train_runtime": 726826.1247,
      "train_tokens_per_second": 29199.733
    },
    {
      "epoch": 2.6405562054545815,
      "grad_norm": 1.640625,
      "learning_rate": 1.718740852428986e-05,
      "loss": 1.0460393905639649,
      "num_input_tokens_seen": 21226022720,
      "step": 74630,
      "train_runtime": 726924.6718,
      "train_tokens_per_second": 29199.756
    },
    {
      "epoch": 2.6409100257183105,
      "grad_norm": 1.640625,
      "learning_rate": 1.7186393158074376e-05,
      "loss": 1.0293766021728517,
      "num_input_tokens_seen": 21228902464,
      "step": 74640,
      "train_runtime": 727025.7648,
      "train_tokens_per_second": 29199.656
    },
    {
      "epoch": 2.6412638459820394,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7185377971789472e-05,
      "loss": 1.041979694366455,
      "num_input_tokens_seen": 21231730240,
      "step": 74650,
      "train_runtime": 727120.7565,
      "train_tokens_per_second": 29199.731
    },
    {
      "epoch": 2.641617666245768,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7184362965382004e-05,
      "loss": 1.031626319885254,
      "num_input_tokens_seen": 21234550016,
      "step": 74660,
      "train_runtime": 727214.8759,
      "train_tokens_per_second": 29199.829
    },
    {
      "epoch": 2.6419714865094965,
      "grad_norm": 1.609375,
      "learning_rate": 1.7183348138798857e-05,
      "loss": 1.0462791442871093,
      "num_input_tokens_seen": 21237429248,
      "step": 74670,
      "train_runtime": 727313.7568,
      "train_tokens_per_second": 29199.818
    },
    {
      "epoch": 2.6423253067732255,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7182333491986944e-05,
      "loss": 1.0363322257995606,
      "num_input_tokens_seen": 21240264064,
      "step": 74680,
      "train_runtime": 727411.2577,
      "train_tokens_per_second": 29199.801
    },
    {
      "epoch": 2.6426791270369545,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7181319024893197e-05,
      "loss": 1.0504075050354005,
      "num_input_tokens_seen": 21243128064,
      "step": 74690,
      "train_runtime": 727509.9125,
      "train_tokens_per_second": 29199.778
    },
    {
      "epoch": 2.643032947300683,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7180304737464563e-05,
      "loss": 1.026515579223633,
      "num_input_tokens_seen": 21245930688,
      "step": 74700,
      "train_runtime": 727606.6252,
      "train_tokens_per_second": 29199.749
    },
    {
      "epoch": 2.6433867675644116,
      "grad_norm": 1.578125,
      "learning_rate": 1.717929062964802e-05,
      "loss": 1.0485559463500977,
      "num_input_tokens_seen": 21248833792,
      "step": 74710,
      "train_runtime": 727708.4474,
      "train_tokens_per_second": 29199.653
    },
    {
      "epoch": 2.6437405878281406,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7178276701390557e-05,
      "loss": 1.0422436714172363,
      "num_input_tokens_seen": 21251690944,
      "step": 74720,
      "train_runtime": 727805.41,
      "train_tokens_per_second": 29199.688
    },
    {
      "epoch": 2.6440944080918696,
      "grad_norm": 1.59375,
      "learning_rate": 1.7177262952639204e-05,
      "loss": 1.0311418533325196,
      "num_input_tokens_seen": 21254541952,
      "step": 74730,
      "train_runtime": 727904.8917,
      "train_tokens_per_second": 29199.614
    },
    {
      "epoch": 2.644448228355598,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7176249383340994e-05,
      "loss": 1.0247024536132812,
      "num_input_tokens_seen": 21257403136,
      "step": 74740,
      "train_runtime": 728002.3932,
      "train_tokens_per_second": 29199.634
    },
    {
      "epoch": 2.644802048619327,
      "grad_norm": 1.59375,
      "learning_rate": 1.7175235993442985e-05,
      "loss": 1.0401777267456054,
      "num_input_tokens_seen": 21260179008,
      "step": 74750,
      "train_runtime": 728093.3756,
      "train_tokens_per_second": 29199.797
    },
    {
      "epoch": 2.6451558688830556,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7174222782892264e-05,
      "loss": 1.0415636062622071,
      "num_input_tokens_seen": 21262949312,
      "step": 74760,
      "train_runtime": 728188.3887,
      "train_tokens_per_second": 29199.792
    },
    {
      "epoch": 2.6455096891467846,
      "grad_norm": 1.5859375,
      "learning_rate": 1.717320975163594e-05,
      "loss": 1.0264537811279297,
      "num_input_tokens_seen": 21265767488,
      "step": 74770,
      "train_runtime": 728283.9994,
      "train_tokens_per_second": 29199.828
    },
    {
      "epoch": 2.645863509410513,
      "grad_norm": 1.5625,
      "learning_rate": 1.717219689962114e-05,
      "loss": 1.046554183959961,
      "num_input_tokens_seen": 21268573504,
      "step": 74780,
      "train_runtime": 728379.2885,
      "train_tokens_per_second": 29199.86
    },
    {
      "epoch": 2.646217329674242,
      "grad_norm": 1.625,
      "learning_rate": 1.717118422679501e-05,
      "loss": 1.0348100662231445,
      "num_input_tokens_seen": 21271434688,
      "step": 74790,
      "train_runtime": 728475.4318,
      "train_tokens_per_second": 29199.934
    },
    {
      "epoch": 2.646571149937971,
      "grad_norm": 1.609375,
      "learning_rate": 1.7170171733104716e-05,
      "loss": 1.0371975898742676,
      "num_input_tokens_seen": 21274258048,
      "step": 74800,
      "train_runtime": 728571.622,
      "train_tokens_per_second": 29199.954
    },
    {
      "epoch": 2.6469249702016997,
      "grad_norm": 1.578125,
      "learning_rate": 1.7169159418497464e-05,
      "loss": 1.036684799194336,
      "num_input_tokens_seen": 21277078912,
      "step": 74810,
      "train_runtime": 728668.3679,
      "train_tokens_per_second": 29199.949
    },
    {
      "epoch": 2.6472787904654282,
      "grad_norm": 1.609375,
      "learning_rate": 1.716814728292046e-05,
      "loss": 1.0544466018676757,
      "num_input_tokens_seen": 21279938368,
      "step": 74820,
      "train_runtime": 728764.7516,
      "train_tokens_per_second": 29200.01
    },
    {
      "epoch": 2.6476326107291572,
      "grad_norm": 1.578125,
      "learning_rate": 1.716713532632094e-05,
      "loss": 1.045415496826172,
      "num_input_tokens_seen": 21282810560,
      "step": 74830,
      "train_runtime": 728863.4154,
      "train_tokens_per_second": 29199.998
    },
    {
      "epoch": 2.647986430992886,
      "grad_norm": 1.53125,
      "learning_rate": 1.7166123548646162e-05,
      "loss": 1.0398288726806642,
      "num_input_tokens_seen": 21285690624,
      "step": 74840,
      "train_runtime": 728964.6349,
      "train_tokens_per_second": 29199.895
    },
    {
      "epoch": 2.6483402512566148,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7165111949843414e-05,
      "loss": 1.0555944442749023,
      "num_input_tokens_seen": 21288509504,
      "step": 74850,
      "train_runtime": 729062.868,
      "train_tokens_per_second": 29199.827
    },
    {
      "epoch": 2.6486940715203433,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7164100529859983e-05,
      "loss": 1.035882568359375,
      "num_input_tokens_seen": 21291339008,
      "step": 74860,
      "train_runtime": 729158.5095,
      "train_tokens_per_second": 29199.877
    },
    {
      "epoch": 2.6490478917840723,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7163089288643202e-05,
      "loss": 1.030413818359375,
      "num_input_tokens_seen": 21294160896,
      "step": 74870,
      "train_runtime": 729256.7594,
      "train_tokens_per_second": 29199.813
    },
    {
      "epoch": 2.6494017120478013,
      "grad_norm": 1.5390625,
      "learning_rate": 1.716207822614042e-05,
      "loss": 1.037015151977539,
      "num_input_tokens_seen": 21296970304,
      "step": 74880,
      "train_runtime": 729352.4204,
      "train_tokens_per_second": 29199.835
    },
    {
      "epoch": 2.64975553231153,
      "grad_norm": 1.640625,
      "learning_rate": 1.7161067342298994e-05,
      "loss": 1.0456188201904297,
      "num_input_tokens_seen": 21299887296,
      "step": 74890,
      "train_runtime": 729453.983,
      "train_tokens_per_second": 29199.768
    },
    {
      "epoch": 2.650109352575259,
      "grad_norm": 1.546875,
      "learning_rate": 1.716005663706632e-05,
      "loss": 1.0318016052246093,
      "num_input_tokens_seen": 21302715392,
      "step": 74900,
      "train_runtime": 729550.8831,
      "train_tokens_per_second": 29199.766
    },
    {
      "epoch": 2.6504631728389874,
      "grad_norm": 1.6171875,
      "learning_rate": 1.71590461103898e-05,
      "loss": 1.03843994140625,
      "num_input_tokens_seen": 21305607168,
      "step": 74910,
      "train_runtime": 729650.1633,
      "train_tokens_per_second": 29199.757
    },
    {
      "epoch": 2.6508169931027163,
      "grad_norm": 1.6953125,
      "learning_rate": 1.7158035762216875e-05,
      "loss": 1.0395072937011718,
      "num_input_tokens_seen": 21308404736,
      "step": 74920,
      "train_runtime": 729744.8729,
      "train_tokens_per_second": 29199.801
    },
    {
      "epoch": 2.651170813366445,
      "grad_norm": 1.515625,
      "learning_rate": 1.715702559249499e-05,
      "loss": 1.045435619354248,
      "num_input_tokens_seen": 21311278016,
      "step": 74930,
      "train_runtime": 729843.5751,
      "train_tokens_per_second": 29199.788
    },
    {
      "epoch": 2.651524633630174,
      "grad_norm": 1.6015625,
      "learning_rate": 1.715601560117163e-05,
      "loss": 1.020213508605957,
      "num_input_tokens_seen": 21314162560,
      "step": 74940,
      "train_runtime": 729945.6729,
      "train_tokens_per_second": 29199.656
    },
    {
      "epoch": 2.6518784538939024,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7155005788194283e-05,
      "loss": 1.0411531448364257,
      "num_input_tokens_seen": 21317031872,
      "step": 74950,
      "train_runtime": 730045.9934,
      "train_tokens_per_second": 29199.574
    },
    {
      "epoch": 2.6522322741576314,
      "grad_norm": 1.59375,
      "learning_rate": 1.7153996153510472e-05,
      "loss": 1.0370901107788086,
      "num_input_tokens_seen": 21319871040,
      "step": 74960,
      "train_runtime": 730144.5606,
      "train_tokens_per_second": 29199.52
    },
    {
      "epoch": 2.65258609442136,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7152986697067734e-05,
      "loss": 1.0224742889404297,
      "num_input_tokens_seen": 21322697536,
      "step": 74970,
      "train_runtime": 730242.7001,
      "train_tokens_per_second": 29199.467
    },
    {
      "epoch": 2.652939914685089,
      "grad_norm": 1.546875,
      "learning_rate": 1.7151977418813636e-05,
      "loss": 1.036501979827881,
      "num_input_tokens_seen": 21325580480,
      "step": 74980,
      "train_runtime": 730342.232,
      "train_tokens_per_second": 29199.435
    },
    {
      "epoch": 2.653293734948818,
      "grad_norm": 1.65625,
      "learning_rate": 1.7150968318695755e-05,
      "loss": 1.0359375,
      "num_input_tokens_seen": 21328386432,
      "step": 74990,
      "train_runtime": 730437.573,
      "train_tokens_per_second": 29199.465
    },
    {
      "epoch": 2.6536475552125465,
      "grad_norm": 1.5078125,
      "learning_rate": 1.7149959396661695e-05,
      "loss": 1.032864475250244,
      "num_input_tokens_seen": 21331230016,
      "step": 75000,
      "train_runtime": 730533.9359,
      "train_tokens_per_second": 29199.506
    },
    {
      "epoch": 2.6536475552125465,
      "eval_loss": 1.0215721130371094,
      "eval_runtime": 8.4404,
      "eval_samples_per_second": 472.491,
      "eval_steps_per_second": 3.791,
      "num_input_tokens_seen": 21331230016,
      "step": 75000
    },
    {
      "epoch": 2.654001375476275,
      "grad_norm": 1.6171875,
      "learning_rate": 1.714895065265909e-05,
      "loss": 1.0244102478027344,
      "num_input_tokens_seen": 21334045504,
      "step": 75010,
      "train_runtime": 730659.0807,
      "train_tokens_per_second": 29198.358
    },
    {
      "epoch": 2.654355195740004,
      "grad_norm": 1.609375,
      "learning_rate": 1.7147942086635584e-05,
      "loss": 1.0343477249145507,
      "num_input_tokens_seen": 21336892864,
      "step": 75020,
      "train_runtime": 730757.5976,
      "train_tokens_per_second": 29198.318
    },
    {
      "epoch": 2.654709016003733,
      "grad_norm": 1.609375,
      "learning_rate": 1.7146933698538846e-05,
      "loss": 1.0260223388671874,
      "num_input_tokens_seen": 21339728320,
      "step": 75030,
      "train_runtime": 730851.7002,
      "train_tokens_per_second": 29198.438
    },
    {
      "epoch": 2.6550628362674615,
      "grad_norm": 1.6328125,
      "learning_rate": 1.714592548831657e-05,
      "loss": 1.043216609954834,
      "num_input_tokens_seen": 21342609664,
      "step": 75040,
      "train_runtime": 730951.8551,
      "train_tokens_per_second": 29198.38
    },
    {
      "epoch": 2.6554166565311905,
      "grad_norm": 1.578125,
      "learning_rate": 1.7144917455916462e-05,
      "loss": 1.0269176483154296,
      "num_input_tokens_seen": 21345477696,
      "step": 75050,
      "train_runtime": 731050.7073,
      "train_tokens_per_second": 29198.354
    },
    {
      "epoch": 2.655770476794919,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7143909601286258e-05,
      "loss": 1.0375288009643555,
      "num_input_tokens_seen": 21348371520,
      "step": 75060,
      "train_runtime": 731151.7534,
      "train_tokens_per_second": 29198.277
    },
    {
      "epoch": 2.656124297058648,
      "grad_norm": 1.4921875,
      "learning_rate": 1.714290192437372e-05,
      "loss": 1.0346717834472656,
      "num_input_tokens_seen": 21351214976,
      "step": 75070,
      "train_runtime": 731251.7975,
      "train_tokens_per_second": 29198.171
    },
    {
      "epoch": 2.6564781173223766,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7141894425126622e-05,
      "loss": 1.0467147827148438,
      "num_input_tokens_seen": 21354111424,
      "step": 75080,
      "train_runtime": 731353.1498,
      "train_tokens_per_second": 29198.085
    },
    {
      "epoch": 2.6568319375861056,
      "grad_norm": 1.65625,
      "learning_rate": 1.714088710349276e-05,
      "loss": 1.0321643829345704,
      "num_input_tokens_seen": 21356917824,
      "step": 75090,
      "train_runtime": 731447.2206,
      "train_tokens_per_second": 29198.167
    },
    {
      "epoch": 2.657185757849834,
      "grad_norm": 1.546875,
      "learning_rate": 1.7139879959419956e-05,
      "loss": 1.0531591415405273,
      "num_input_tokens_seen": 21359767360,
      "step": 75100,
      "train_runtime": 731543.8536,
      "train_tokens_per_second": 29198.205
    },
    {
      "epoch": 2.657539578113563,
      "grad_norm": 1.5625,
      "learning_rate": 1.7138872992856052e-05,
      "loss": 1.031565284729004,
      "num_input_tokens_seen": 21362590848,
      "step": 75110,
      "train_runtime": 731640.5693,
      "train_tokens_per_second": 29198.204
    },
    {
      "epoch": 2.6578933983772917,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7137866203748908e-05,
      "loss": 1.0386063575744628,
      "num_input_tokens_seen": 21365424768,
      "step": 75120,
      "train_runtime": 731735.6473,
      "train_tokens_per_second": 29198.283
    },
    {
      "epoch": 2.6582472186410206,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7136859592046407e-05,
      "loss": 1.030996322631836,
      "num_input_tokens_seen": 21368230656,
      "step": 75130,
      "train_runtime": 731831.1075,
      "train_tokens_per_second": 29198.309
    },
    {
      "epoch": 2.6586010389047496,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7135853157696462e-05,
      "loss": 1.0491019248962403,
      "num_input_tokens_seen": 21371087424,
      "step": 75140,
      "train_runtime": 731931.5813,
      "train_tokens_per_second": 29198.204
    },
    {
      "epoch": 2.658954859168478,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7134846900647e-05,
      "loss": 1.0347311973571778,
      "num_input_tokens_seen": 21373933824,
      "step": 75150,
      "train_runtime": 732027.58,
      "train_tokens_per_second": 29198.263
    },
    {
      "epoch": 2.6593086794322067,
      "grad_norm": 1.5859375,
      "learning_rate": 1.713384082084596e-05,
      "loss": 1.0353900909423828,
      "num_input_tokens_seen": 21376792704,
      "step": 75160,
      "train_runtime": 732124.3031,
      "train_tokens_per_second": 29198.31
    },
    {
      "epoch": 2.6596624996959357,
      "grad_norm": 1.6015625,
      "learning_rate": 1.713283491824132e-05,
      "loss": 1.0560933113098145,
      "num_input_tokens_seen": 21379616256,
      "step": 75170,
      "train_runtime": 732217.4212,
      "train_tokens_per_second": 29198.453
    },
    {
      "epoch": 2.6600163199596647,
      "grad_norm": 1.625,
      "learning_rate": 1.713182919278107e-05,
      "loss": 1.0321111679077148,
      "num_input_tokens_seen": 21382498624,
      "step": 75180,
      "train_runtime": 732319.4378,
      "train_tokens_per_second": 29198.322
    },
    {
      "epoch": 2.6603701402233932,
      "grad_norm": 1.546875,
      "learning_rate": 1.7130823644413222e-05,
      "loss": 1.0435989379882813,
      "num_input_tokens_seen": 21385420160,
      "step": 75190,
      "train_runtime": 732419.9259,
      "train_tokens_per_second": 29198.305
    },
    {
      "epoch": 2.660723960487122,
      "grad_norm": 1.6328125,
      "learning_rate": 1.712981827308581e-05,
      "loss": 1.0277837753295898,
      "num_input_tokens_seen": 21388258624,
      "step": 75200,
      "train_runtime": 732516.6042,
      "train_tokens_per_second": 29198.326
    },
    {
      "epoch": 2.6610777807508508,
      "grad_norm": 1.65625,
      "learning_rate": 1.712881307874689e-05,
      "loss": 1.0300518035888673,
      "num_input_tokens_seen": 21391087168,
      "step": 75210,
      "train_runtime": 732615.1944,
      "train_tokens_per_second": 29198.258
    },
    {
      "epoch": 2.6614316010145798,
      "grad_norm": 1.6171875,
      "learning_rate": 1.712780806134454e-05,
      "loss": 1.031192684173584,
      "num_input_tokens_seen": 21393891648,
      "step": 75220,
      "train_runtime": 732709.0888,
      "train_tokens_per_second": 29198.343
    },
    {
      "epoch": 2.6617854212783083,
      "grad_norm": 1.640625,
      "learning_rate": 1.7126803220826854e-05,
      "loss": 1.0347548484802247,
      "num_input_tokens_seen": 21396704512,
      "step": 75230,
      "train_runtime": 732805.2466,
      "train_tokens_per_second": 29198.351
    },
    {
      "epoch": 2.6621392415420373,
      "grad_norm": 1.5625,
      "learning_rate": 1.7125798557141954e-05,
      "loss": 1.03814697265625,
      "num_input_tokens_seen": 21399525952,
      "step": 75240,
      "train_runtime": 732901.1809,
      "train_tokens_per_second": 29198.378
    },
    {
      "epoch": 2.662493061805766,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7124794070237987e-05,
      "loss": 1.0328025817871094,
      "num_input_tokens_seen": 21402350976,
      "step": 75250,
      "train_runtime": 732995.2922,
      "train_tokens_per_second": 29198.484
    },
    {
      "epoch": 2.662846882069495,
      "grad_norm": 1.609375,
      "learning_rate": 1.71237897600631e-05,
      "loss": 1.0326838493347168,
      "num_input_tokens_seen": 21405216576,
      "step": 75260,
      "train_runtime": 733093.2473,
      "train_tokens_per_second": 29198.491
    },
    {
      "epoch": 2.6632007023332234,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7122785626565498e-05,
      "loss": 1.0329131126403808,
      "num_input_tokens_seen": 21408015360,
      "step": 75270,
      "train_runtime": 733187.9017,
      "train_tokens_per_second": 29198.539
    },
    {
      "epoch": 2.6635545225969524,
      "grad_norm": 1.640625,
      "learning_rate": 1.7121781669693363e-05,
      "loss": 1.0332388877868652,
      "num_input_tokens_seen": 21410867392,
      "step": 75280,
      "train_runtime": 733286.7728,
      "train_tokens_per_second": 29198.491
    },
    {
      "epoch": 2.663908342860681,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7120777889394933e-05,
      "loss": 1.0310681343078614,
      "num_input_tokens_seen": 21413760192,
      "step": 75290,
      "train_runtime": 733385.29,
      "train_tokens_per_second": 29198.513
    },
    {
      "epoch": 2.66426216312441,
      "grad_norm": 1.6015625,
      "learning_rate": 1.711977428561845e-05,
      "loss": 1.039668655395508,
      "num_input_tokens_seen": 21416683264,
      "step": 75300,
      "train_runtime": 733487.7983,
      "train_tokens_per_second": 29198.418
    },
    {
      "epoch": 2.6646159833881384,
      "grad_norm": 1.578125,
      "learning_rate": 1.7118770858312188e-05,
      "loss": 1.0372652053833007,
      "num_input_tokens_seen": 21419519360,
      "step": 75310,
      "train_runtime": 733585.8413,
      "train_tokens_per_second": 29198.382
    },
    {
      "epoch": 2.6649698036518674,
      "grad_norm": 1.5625,
      "learning_rate": 1.7117767607424434e-05,
      "loss": 1.0280562400817872,
      "num_input_tokens_seen": 21422421760,
      "step": 75320,
      "train_runtime": 733685.1008,
      "train_tokens_per_second": 29198.387
    },
    {
      "epoch": 2.6653236239155964,
      "grad_norm": 1.5625,
      "learning_rate": 1.71167645329035e-05,
      "loss": 1.0272883415222167,
      "num_input_tokens_seen": 21425259456,
      "step": 75330,
      "train_runtime": 733779.1391,
      "train_tokens_per_second": 29198.513
    },
    {
      "epoch": 2.665677444179325,
      "grad_norm": 1.640625,
      "learning_rate": 1.7115761634697715e-05,
      "loss": 1.0500532150268556,
      "num_input_tokens_seen": 21428091328,
      "step": 75340,
      "train_runtime": 733876.3489,
      "train_tokens_per_second": 29198.504
    },
    {
      "epoch": 2.6660312644430535,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7114758912755432e-05,
      "loss": 1.025968360900879,
      "num_input_tokens_seen": 21430920960,
      "step": 75350,
      "train_runtime": 733975.8902,
      "train_tokens_per_second": 29198.399
    },
    {
      "epoch": 2.6663850847067825,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7113756367025033e-05,
      "loss": 1.0315526008605957,
      "num_input_tokens_seen": 21433734336,
      "step": 75360,
      "train_runtime": 734070.3819,
      "train_tokens_per_second": 29198.473
    },
    {
      "epoch": 2.6667389049705115,
      "grad_norm": 1.578125,
      "learning_rate": 1.71127539974549e-05,
      "loss": 1.043890380859375,
      "num_input_tokens_seen": 21436544064,
      "step": 75370,
      "train_runtime": 734165.0859,
      "train_tokens_per_second": 29198.534
    },
    {
      "epoch": 2.66709272523424,
      "grad_norm": 1.6484375,
      "learning_rate": 1.711175180399346e-05,
      "loss": 1.030762004852295,
      "num_input_tokens_seen": 21439364224,
      "step": 75380,
      "train_runtime": 734258.2684,
      "train_tokens_per_second": 29198.669
    },
    {
      "epoch": 2.667446545497969,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7110749786589146e-05,
      "loss": 1.043888473510742,
      "num_input_tokens_seen": 21442223744,
      "step": 75390,
      "train_runtime": 734358.6626,
      "train_tokens_per_second": 29198.571
    },
    {
      "epoch": 2.6678003657616975,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7109747945190424e-05,
      "loss": 1.0323155403137207,
      "num_input_tokens_seen": 21445103360,
      "step": 75400,
      "train_runtime": 734460.4135,
      "train_tokens_per_second": 29198.447
    },
    {
      "epoch": 2.6681541860254265,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7108746279745763e-05,
      "loss": 1.026235866546631,
      "num_input_tokens_seen": 21447920640,
      "step": 75410,
      "train_runtime": 734556.3555,
      "train_tokens_per_second": 29198.469
    },
    {
      "epoch": 2.668508006289155,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7107744790203676e-05,
      "loss": 1.0344736099243164,
      "num_input_tokens_seen": 21450836416,
      "step": 75420,
      "train_runtime": 734659.2517,
      "train_tokens_per_second": 29198.348
    },
    {
      "epoch": 2.668861826552884,
      "grad_norm": 1.640625,
      "learning_rate": 1.7106743476512673e-05,
      "loss": 1.0468305587768554,
      "num_input_tokens_seen": 21453674560,
      "step": 75430,
      "train_runtime": 734754.2177,
      "train_tokens_per_second": 29198.437
    },
    {
      "epoch": 2.6692156468166126,
      "grad_norm": 1.6796875,
      "learning_rate": 1.71057423386213e-05,
      "loss": 1.0296573638916016,
      "num_input_tokens_seen": 21456513792,
      "step": 75440,
      "train_runtime": 734848.1369,
      "train_tokens_per_second": 29198.569
    },
    {
      "epoch": 2.6695694670803416,
      "grad_norm": 1.546875,
      "learning_rate": 1.7104741376478137e-05,
      "loss": 1.0540922164916993,
      "num_input_tokens_seen": 21459358976,
      "step": 75450,
      "train_runtime": 734945.9334,
      "train_tokens_per_second": 29198.555
    },
    {
      "epoch": 2.66992328734407,
      "grad_norm": 1.6015625,
      "learning_rate": 1.710374059003175e-05,
      "loss": 1.037712287902832,
      "num_input_tokens_seen": 21462132352,
      "step": 75460,
      "train_runtime": 735039.7489,
      "train_tokens_per_second": 29198.601
    },
    {
      "epoch": 2.670277107607799,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7102739979230753e-05,
      "loss": 1.0446080207824706,
      "num_input_tokens_seen": 21464969152,
      "step": 75470,
      "train_runtime": 735138.5454,
      "train_tokens_per_second": 29198.536
    },
    {
      "epoch": 2.670630927871528,
      "grad_norm": 1.5390625,
      "learning_rate": 1.7101739544023772e-05,
      "loss": 1.0497421264648437,
      "num_input_tokens_seen": 21467774336,
      "step": 75480,
      "train_runtime": 735232.2639,
      "train_tokens_per_second": 29198.629
    },
    {
      "epoch": 2.6709847481352567,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7100739284359464e-05,
      "loss": 1.0534069061279296,
      "num_input_tokens_seen": 21470656000,
      "step": 75490,
      "train_runtime": 735330.9288,
      "train_tokens_per_second": 29198.63
    },
    {
      "epoch": 2.671338568398985,
      "grad_norm": 1.640625,
      "learning_rate": 1.7099739200186484e-05,
      "loss": 1.0326498031616211,
      "num_input_tokens_seen": 21473521728,
      "step": 75500,
      "train_runtime": 735426.9008,
      "train_tokens_per_second": 29198.717
    },
    {
      "epoch": 2.671692388662714,
      "grad_norm": 1.59375,
      "learning_rate": 1.7098739291453537e-05,
      "loss": 1.0296855926513673,
      "num_input_tokens_seen": 21476320704,
      "step": 75510,
      "train_runtime": 735521.555,
      "train_tokens_per_second": 29198.765
    },
    {
      "epoch": 2.672046208926443,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7097739558109325e-05,
      "loss": 1.0396528244018555,
      "num_input_tokens_seen": 21479090432,
      "step": 75520,
      "train_runtime": 735614.5323,
      "train_tokens_per_second": 29198.839
    },
    {
      "epoch": 2.6724000291901717,
      "grad_norm": 1.578125,
      "learning_rate": 1.709674000010258e-05,
      "loss": 1.0329484939575195,
      "num_input_tokens_seen": 21482007488,
      "step": 75530,
      "train_runtime": 735718.8601,
      "train_tokens_per_second": 29198.664
    },
    {
      "epoch": 2.6727538494539003,
      "grad_norm": 1.671875,
      "learning_rate": 1.7095740617382063e-05,
      "loss": 1.0410003662109375,
      "num_input_tokens_seen": 21484823488,
      "step": 75540,
      "train_runtime": 735812.6114,
      "train_tokens_per_second": 29198.77
    },
    {
      "epoch": 2.6731076697176293,
      "grad_norm": 1.671875,
      "learning_rate": 1.7094741409896546e-05,
      "loss": 1.0504890441894532,
      "num_input_tokens_seen": 21487602816,
      "step": 75550,
      "train_runtime": 735905.7696,
      "train_tokens_per_second": 29198.851
    },
    {
      "epoch": 2.6734614899813582,
      "grad_norm": 1.59375,
      "learning_rate": 1.709374237759482e-05,
      "loss": 1.0339191436767579,
      "num_input_tokens_seen": 21490430208,
      "step": 75560,
      "train_runtime": 736003.2658,
      "train_tokens_per_second": 29198.825
    },
    {
      "epoch": 2.673815310245087,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7092743520425707e-05,
      "loss": 1.023002815246582,
      "num_input_tokens_seen": 21493338944,
      "step": 75570,
      "train_runtime": 736105.3967,
      "train_tokens_per_second": 29198.725
    },
    {
      "epoch": 2.6741691305088158,
      "grad_norm": 1.5390625,
      "learning_rate": 1.709174483833804e-05,
      "loss": 1.0542022705078125,
      "num_input_tokens_seen": 21496185408,
      "step": 75580,
      "train_runtime": 736201.1582,
      "train_tokens_per_second": 29198.793
    },
    {
      "epoch": 2.6745229507725443,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7090746331280686e-05,
      "loss": 1.0258445739746094,
      "num_input_tokens_seen": 21499051008,
      "step": 75590,
      "train_runtime": 736298.8177,
      "train_tokens_per_second": 29198.812
    },
    {
      "epoch": 2.6748767710362733,
      "grad_norm": 1.609375,
      "learning_rate": 1.708974799920251e-05,
      "loss": 1.0424688339233399,
      "num_input_tokens_seen": 21501881216,
      "step": 75600,
      "train_runtime": 736396.0454,
      "train_tokens_per_second": 29198.8
    },
    {
      "epoch": 2.675230591300002,
      "grad_norm": 1.640625,
      "learning_rate": 1.7088749842052426e-05,
      "loss": 1.0431360244750976,
      "num_input_tokens_seen": 21504745920,
      "step": 75610,
      "train_runtime": 736495.8717,
      "train_tokens_per_second": 29198.732
    },
    {
      "epoch": 2.675584411563731,
      "grad_norm": 1.5546875,
      "learning_rate": 1.708775185977935e-05,
      "loss": 1.0325456619262696,
      "num_input_tokens_seen": 21507583360,
      "step": 75620,
      "train_runtime": 736592.5257,
      "train_tokens_per_second": 29198.753
    },
    {
      "epoch": 2.67593823182746,
      "grad_norm": 1.5625,
      "learning_rate": 1.7086754052332214e-05,
      "loss": 1.0330854415893556,
      "num_input_tokens_seen": 21510452928,
      "step": 75630,
      "train_runtime": 736690.9686,
      "train_tokens_per_second": 29198.747
    },
    {
      "epoch": 2.6762920520911884,
      "grad_norm": 1.671875,
      "learning_rate": 1.7085756419659995e-05,
      "loss": 1.0495521545410156,
      "num_input_tokens_seen": 21513343104,
      "step": 75640,
      "train_runtime": 736787.7777,
      "train_tokens_per_second": 29198.833
    },
    {
      "epoch": 2.676645872354917,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7084758961711672e-05,
      "loss": 1.0358688354492187,
      "num_input_tokens_seen": 21516211328,
      "step": 75650,
      "train_runtime": 736886.5456,
      "train_tokens_per_second": 29198.811
    },
    {
      "epoch": 2.676999692618646,
      "grad_norm": 1.6484375,
      "learning_rate": 1.708376167843625e-05,
      "loss": 1.0378828048706055,
      "num_input_tokens_seen": 21519057920,
      "step": 75660,
      "train_runtime": 736983.0284,
      "train_tokens_per_second": 29198.851
    },
    {
      "epoch": 2.677353512882375,
      "grad_norm": 1.59375,
      "learning_rate": 1.708276456978275e-05,
      "loss": 1.032766342163086,
      "num_input_tokens_seen": 21521913728,
      "step": 75670,
      "train_runtime": 737079.7494,
      "train_tokens_per_second": 29198.894
    },
    {
      "epoch": 2.6777073331461034,
      "grad_norm": 1.609375,
      "learning_rate": 1.7081767635700222e-05,
      "loss": 1.0293581008911132,
      "num_input_tokens_seen": 21524808512,
      "step": 75680,
      "train_runtime": 737179.1145,
      "train_tokens_per_second": 29198.885
    },
    {
      "epoch": 2.678061153409832,
      "grad_norm": 1.59375,
      "learning_rate": 1.7080770876137737e-05,
      "loss": 1.033340072631836,
      "num_input_tokens_seen": 21527647104,
      "step": 75690,
      "train_runtime": 737275.8589,
      "train_tokens_per_second": 29198.904
    },
    {
      "epoch": 2.678414973673561,
      "grad_norm": 1.625,
      "learning_rate": 1.707977429104437e-05,
      "loss": 1.0170310974121093,
      "num_input_tokens_seen": 21530510784,
      "step": 75700,
      "train_runtime": 737373.0219,
      "train_tokens_per_second": 29198.94
    },
    {
      "epoch": 2.67876879393729,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7078777880369244e-05,
      "loss": 1.0363851547241212,
      "num_input_tokens_seen": 21533340544,
      "step": 75710,
      "train_runtime": 737467.1289,
      "train_tokens_per_second": 29199.051
    },
    {
      "epoch": 2.6791226142010185,
      "grad_norm": 1.65625,
      "learning_rate": 1.7077781644061477e-05,
      "loss": 1.0364976882934571,
      "num_input_tokens_seen": 21536198336,
      "step": 75720,
      "train_runtime": 737563.0735,
      "train_tokens_per_second": 29199.128
    },
    {
      "epoch": 2.6794764344647475,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7076785582070228e-05,
      "loss": 1.0350483894348144,
      "num_input_tokens_seen": 21539043904,
      "step": 75730,
      "train_runtime": 737659.8744,
      "train_tokens_per_second": 29199.154
    },
    {
      "epoch": 2.679830254728476,
      "grad_norm": 1.578125,
      "learning_rate": 1.7075789694344664e-05,
      "loss": 1.0489768028259276,
      "num_input_tokens_seen": 21541908672,
      "step": 75740,
      "train_runtime": 737756.9898,
      "train_tokens_per_second": 29199.193
    },
    {
      "epoch": 2.680184074992205,
      "grad_norm": 1.625,
      "learning_rate": 1.7074793980833974e-05,
      "loss": 1.0458626747131348,
      "num_input_tokens_seen": 21544763392,
      "step": 75750,
      "train_runtime": 737856.175,
      "train_tokens_per_second": 29199.137
    },
    {
      "epoch": 2.6805378952559336,
      "grad_norm": 1.609375,
      "learning_rate": 1.7073798441487372e-05,
      "loss": 1.0405797958374023,
      "num_input_tokens_seen": 21547567424,
      "step": 75760,
      "train_runtime": 737949.8769,
      "train_tokens_per_second": 29199.229
    },
    {
      "epoch": 2.6808917155196625,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7072803076254092e-05,
      "loss": 1.0399297714233398,
      "num_input_tokens_seen": 21550345856,
      "step": 75770,
      "train_runtime": 738042.3357,
      "train_tokens_per_second": 29199.336
    },
    {
      "epoch": 2.681245535783391,
      "grad_norm": 1.6328125,
      "learning_rate": 1.707180788508339e-05,
      "loss": 1.0301517486572265,
      "num_input_tokens_seen": 21553202816,
      "step": 75780,
      "train_runtime": 738139.5367,
      "train_tokens_per_second": 29199.361
    },
    {
      "epoch": 2.68159935604712,
      "grad_norm": 1.6015625,
      "learning_rate": 1.707081286792454e-05,
      "loss": 1.0292243003845214,
      "num_input_tokens_seen": 21556086656,
      "step": 75790,
      "train_runtime": 738239.1521,
      "train_tokens_per_second": 29199.327
    },
    {
      "epoch": 2.6819531763108486,
      "grad_norm": 1.640625,
      "learning_rate": 1.7069818024726833e-05,
      "loss": 1.0302600860595703,
      "num_input_tokens_seen": 21558929152,
      "step": 75800,
      "train_runtime": 738337.2175,
      "train_tokens_per_second": 29199.299
    },
    {
      "epoch": 2.6823069965745776,
      "grad_norm": 1.671875,
      "learning_rate": 1.7068823355439583e-05,
      "loss": 1.0395679473876953,
      "num_input_tokens_seen": 21561794176,
      "step": 75810,
      "train_runtime": 738432.939,
      "train_tokens_per_second": 29199.394
    },
    {
      "epoch": 2.6826608168383066,
      "grad_norm": 1.609375,
      "learning_rate": 1.7067828860012138e-05,
      "loss": 1.0311152458190918,
      "num_input_tokens_seen": 21564658624,
      "step": 75820,
      "train_runtime": 738533.316,
      "train_tokens_per_second": 29199.304
    },
    {
      "epoch": 2.683014637102035,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7066834538393844e-05,
      "loss": 1.0284954071044923,
      "num_input_tokens_seen": 21567477376,
      "step": 75830,
      "train_runtime": 738630.334,
      "train_tokens_per_second": 29199.285
    },
    {
      "epoch": 2.6833684573657637,
      "grad_norm": 1.625,
      "learning_rate": 1.7065840390534083e-05,
      "loss": 1.035334300994873,
      "num_input_tokens_seen": 21570292608,
      "step": 75840,
      "train_runtime": 738726.7679,
      "train_tokens_per_second": 29199.284
    },
    {
      "epoch": 2.6837222776294927,
      "grad_norm": 1.6796875,
      "learning_rate": 1.7064846416382256e-05,
      "loss": 1.0461501121520995,
      "num_input_tokens_seen": 21573104320,
      "step": 75850,
      "train_runtime": 738822.0795,
      "train_tokens_per_second": 29199.323
    },
    {
      "epoch": 2.6840760978932217,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7063852615887773e-05,
      "loss": 1.0253961563110352,
      "num_input_tokens_seen": 21575921984,
      "step": 75860,
      "train_runtime": 738917.2108,
      "train_tokens_per_second": 29199.377
    },
    {
      "epoch": 2.68442991815695,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7062858989000085e-05,
      "loss": 1.052175521850586,
      "num_input_tokens_seen": 21578773568,
      "step": 75870,
      "train_runtime": 739015.2728,
      "train_tokens_per_second": 29199.361
    },
    {
      "epoch": 2.684783738420679,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7061865535668645e-05,
      "loss": 1.0315242767333985,
      "num_input_tokens_seen": 21581601600,
      "step": 75880,
      "train_runtime": 739109.9073,
      "train_tokens_per_second": 29199.448
    },
    {
      "epoch": 2.6851375586844077,
      "grad_norm": 1.5625,
      "learning_rate": 1.706087225584294e-05,
      "loss": 1.0265794754028321,
      "num_input_tokens_seen": 21584469952,
      "step": 75890,
      "train_runtime": 739209.3313,
      "train_tokens_per_second": 29199.401
    },
    {
      "epoch": 2.6854913789481367,
      "grad_norm": 1.609375,
      "learning_rate": 1.7059879149472464e-05,
      "loss": 1.0242912292480468,
      "num_input_tokens_seen": 21587296640,
      "step": 75900,
      "train_runtime": 739305.0129,
      "train_tokens_per_second": 29199.446
    },
    {
      "epoch": 2.6858451992118653,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7058886216506746e-05,
      "loss": 1.047739028930664,
      "num_input_tokens_seen": 21590111808,
      "step": 75910,
      "train_runtime": 739398.8002,
      "train_tokens_per_second": 29199.549
    },
    {
      "epoch": 2.6861990194755943,
      "grad_norm": 1.5625,
      "learning_rate": 1.705789345689532e-05,
      "loss": 1.0411389350891114,
      "num_input_tokens_seen": 21592972352,
      "step": 75920,
      "train_runtime": 739498.0828,
      "train_tokens_per_second": 29199.497
    },
    {
      "epoch": 2.686552839739323,
      "grad_norm": 1.6640625,
      "learning_rate": 1.705690087058776e-05,
      "loss": 1.0306855201721192,
      "num_input_tokens_seen": 21595827328,
      "step": 75930,
      "train_runtime": 739595.954,
      "train_tokens_per_second": 29199.494
    },
    {
      "epoch": 2.686906660003052,
      "grad_norm": 1.65625,
      "learning_rate": 1.7055908457533644e-05,
      "loss": 1.039632797241211,
      "num_input_tokens_seen": 21598685184,
      "step": 75940,
      "train_runtime": 739696.3524,
      "train_tokens_per_second": 29199.394
    },
    {
      "epoch": 2.6872604802667803,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7054916217682577e-05,
      "loss": 1.02457857131958,
      "num_input_tokens_seen": 21601495360,
      "step": 75950,
      "train_runtime": 739793.3806,
      "train_tokens_per_second": 29199.363
    },
    {
      "epoch": 2.6876143005305093,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7053924150984184e-05,
      "loss": 1.0355435371398927,
      "num_input_tokens_seen": 21604312000,
      "step": 75960,
      "train_runtime": 739890.285,
      "train_tokens_per_second": 29199.345
    },
    {
      "epoch": 2.6879681207942383,
      "grad_norm": 1.625,
      "learning_rate": 1.7052932257388107e-05,
      "loss": 1.0442063331604003,
      "num_input_tokens_seen": 21607158528,
      "step": 75970,
      "train_runtime": 739987.6315,
      "train_tokens_per_second": 29199.351
    },
    {
      "epoch": 2.688321941057967,
      "grad_norm": 1.6875,
      "learning_rate": 1.7051940536844015e-05,
      "loss": 1.0448694229125977,
      "num_input_tokens_seen": 21609980864,
      "step": 75980,
      "train_runtime": 740083.7625,
      "train_tokens_per_second": 29199.372
    },
    {
      "epoch": 2.6886757613216954,
      "grad_norm": 1.609375,
      "learning_rate": 1.7050948989301595e-05,
      "loss": 1.0301618576049805,
      "num_input_tokens_seen": 21612790976,
      "step": 75990,
      "train_runtime": 740180.6212,
      "train_tokens_per_second": 29199.347
    },
    {
      "epoch": 2.6890295815854244,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7049957614710553e-05,
      "loss": 1.0429344177246094,
      "num_input_tokens_seen": 21615594560,
      "step": 76000,
      "train_runtime": 740275.1678,
      "train_tokens_per_second": 29199.405
    },
    {
      "epoch": 2.6893834018491534,
      "grad_norm": 1.640625,
      "learning_rate": 1.7048966413020613e-05,
      "loss": 1.036581802368164,
      "num_input_tokens_seen": 21618415616,
      "step": 76010,
      "train_runtime": 740372.1947,
      "train_tokens_per_second": 29199.389
    },
    {
      "epoch": 2.689737222112882,
      "grad_norm": 1.6015625,
      "learning_rate": 1.704797538418153e-05,
      "loss": 1.0299457550048827,
      "num_input_tokens_seen": 21621306880,
      "step": 76020,
      "train_runtime": 740469.7776,
      "train_tokens_per_second": 29199.445
    },
    {
      "epoch": 2.6900910423766105,
      "grad_norm": 1.59375,
      "learning_rate": 1.7046984528143065e-05,
      "loss": 1.048173999786377,
      "num_input_tokens_seen": 21624121792,
      "step": 76030,
      "train_runtime": 740564.0418,
      "train_tokens_per_second": 29199.53
    },
    {
      "epoch": 2.6904448626403394,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7045993844855012e-05,
      "loss": 1.0444411277770995,
      "num_input_tokens_seen": 21626982592,
      "step": 76040,
      "train_runtime": 740660.0937,
      "train_tokens_per_second": 29199.606
    },
    {
      "epoch": 2.6907986829040684,
      "grad_norm": 1.5546875,
      "learning_rate": 1.7045003334267175e-05,
      "loss": 1.027272605895996,
      "num_input_tokens_seen": 21629820416,
      "step": 76050,
      "train_runtime": 740757.7846,
      "train_tokens_per_second": 29199.586
    },
    {
      "epoch": 2.691152503167797,
      "grad_norm": 1.6171875,
      "learning_rate": 1.704401299632939e-05,
      "loss": 1.0389467239379884,
      "num_input_tokens_seen": 21632654976,
      "step": 76060,
      "train_runtime": 740855.4655,
      "train_tokens_per_second": 29199.562
    },
    {
      "epoch": 2.691506323431526,
      "grad_norm": 1.65625,
      "learning_rate": 1.7043022830991498e-05,
      "loss": 1.0218398094177246,
      "num_input_tokens_seen": 21635567616,
      "step": 76070,
      "train_runtime": 740956.9148,
      "train_tokens_per_second": 29199.495
    },
    {
      "epoch": 2.6918601436952545,
      "grad_norm": 1.609375,
      "learning_rate": 1.7042032838203372e-05,
      "loss": 1.0409164428710938,
      "num_input_tokens_seen": 21638366592,
      "step": 76080,
      "train_runtime": 741052.5226,
      "train_tokens_per_second": 29199.505
    },
    {
      "epoch": 2.6922139639589835,
      "grad_norm": 1.5859375,
      "learning_rate": 1.7041043017914912e-05,
      "loss": 1.0369022369384766,
      "num_input_tokens_seen": 21641229952,
      "step": 76090,
      "train_runtime": 741151.0973,
      "train_tokens_per_second": 29199.484
    },
    {
      "epoch": 2.692567784222712,
      "grad_norm": 1.59375,
      "learning_rate": 1.7040053370076014e-05,
      "loss": 1.0342833518981933,
      "num_input_tokens_seen": 21644022464,
      "step": 76100,
      "train_runtime": 741246.833,
      "train_tokens_per_second": 29199.481
    },
    {
      "epoch": 2.692921604486441,
      "grad_norm": 1.6484375,
      "learning_rate": 1.703906389463662e-05,
      "loss": 1.0399560928344727,
      "num_input_tokens_seen": 21646869952,
      "step": 76110,
      "train_runtime": 741345.143,
      "train_tokens_per_second": 29199.449
    },
    {
      "epoch": 2.6932754247501696,
      "grad_norm": 1.5703125,
      "learning_rate": 1.703807459154668e-05,
      "loss": 1.0323552131652831,
      "num_input_tokens_seen": 21649738432,
      "step": 76120,
      "train_runtime": 741446.0438,
      "train_tokens_per_second": 29199.344
    },
    {
      "epoch": 2.6936292450138986,
      "grad_norm": 1.609375,
      "learning_rate": 1.703708546075616e-05,
      "loss": 1.0432754516601563,
      "num_input_tokens_seen": 21652608960,
      "step": 76130,
      "train_runtime": 741544.676,
      "train_tokens_per_second": 29199.332
    },
    {
      "epoch": 2.693983065277627,
      "grad_norm": 1.65625,
      "learning_rate": 1.7036096502215064e-05,
      "loss": 1.0469511032104493,
      "num_input_tokens_seen": 21655470272,
      "step": 76140,
      "train_runtime": 741641.0291,
      "train_tokens_per_second": 29199.396
    },
    {
      "epoch": 2.694336885541356,
      "grad_norm": 1.6484375,
      "learning_rate": 1.703510771587339e-05,
      "loss": 1.0536516189575196,
      "num_input_tokens_seen": 21658332672,
      "step": 76150,
      "train_runtime": 741736.7949,
      "train_tokens_per_second": 29199.485
    },
    {
      "epoch": 2.694690705805085,
      "grad_norm": 1.609375,
      "learning_rate": 1.703411910168118e-05,
      "loss": 1.0378475189208984,
      "num_input_tokens_seen": 21661167552,
      "step": 76160,
      "train_runtime": 741831.2548,
      "train_tokens_per_second": 29199.589
    },
    {
      "epoch": 2.6950445260688136,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7033130659588486e-05,
      "loss": 1.032486915588379,
      "num_input_tokens_seen": 21663979008,
      "step": 76170,
      "train_runtime": 741926.0764,
      "train_tokens_per_second": 29199.646
    },
    {
      "epoch": 2.695398346332542,
      "grad_norm": 1.578125,
      "learning_rate": 1.703214238954538e-05,
      "loss": 1.0255840301513672,
      "num_input_tokens_seen": 21666785984,
      "step": 76180,
      "train_runtime": 742019.6855,
      "train_tokens_per_second": 29199.746
    },
    {
      "epoch": 2.695752166596271,
      "grad_norm": 1.65625,
      "learning_rate": 1.7031154291501962e-05,
      "loss": 1.049422836303711,
      "num_input_tokens_seen": 21669590656,
      "step": 76190,
      "train_runtime": 742113.7143,
      "train_tokens_per_second": 29199.825
    },
    {
      "epoch": 2.69610598686,
      "grad_norm": 1.6328125,
      "learning_rate": 1.7030166365408335e-05,
      "loss": 1.0423591613769532,
      "num_input_tokens_seen": 21672408704,
      "step": 76200,
      "train_runtime": 742207.663,
      "train_tokens_per_second": 29199.926
    },
    {
      "epoch": 2.6964598071237287,
      "grad_norm": 1.59375,
      "learning_rate": 1.702917861121464e-05,
      "loss": 1.0369071960449219,
      "num_input_tokens_seen": 21675227200,
      "step": 76210,
      "train_runtime": 742301.0713,
      "train_tokens_per_second": 29200.048
    },
    {
      "epoch": 2.6968136273874577,
      "grad_norm": 1.625,
      "learning_rate": 1.7028191028871033e-05,
      "loss": 1.036498737335205,
      "num_input_tokens_seen": 21678019072,
      "step": 76220,
      "train_runtime": 742394.7442,
      "train_tokens_per_second": 29200.125
    },
    {
      "epoch": 2.697167447651186,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7027203618327685e-05,
      "loss": 1.0316251754760741,
      "num_input_tokens_seen": 21680876416,
      "step": 76230,
      "train_runtime": 742494.4591,
      "train_tokens_per_second": 29200.051
    },
    {
      "epoch": 2.697521267914915,
      "grad_norm": 1.6875,
      "learning_rate": 1.7026216379534793e-05,
      "loss": 1.033745002746582,
      "num_input_tokens_seen": 21683763584,
      "step": 76240,
      "train_runtime": 742595.8819,
      "train_tokens_per_second": 29199.951
    },
    {
      "epoch": 2.6978750881786437,
      "grad_norm": 1.59375,
      "learning_rate": 1.7025229312442577e-05,
      "loss": 1.0383378982543945,
      "num_input_tokens_seen": 21686638080,
      "step": 76250,
      "train_runtime": 742695.8467,
      "train_tokens_per_second": 29199.891
    },
    {
      "epoch": 2.6982289084423727,
      "grad_norm": 1.6640625,
      "learning_rate": 1.702424241700126e-05,
      "loss": 1.0436262130737304,
      "num_input_tokens_seen": 21689497024,
      "step": 76260,
      "train_runtime": 742793.8432,
      "train_tokens_per_second": 29199.888
    },
    {
      "epoch": 2.6985827287061013,
      "grad_norm": 1.5625,
      "learning_rate": 1.702325569316111e-05,
      "loss": 1.0276781082153321,
      "num_input_tokens_seen": 21692301504,
      "step": 76270,
      "train_runtime": 742889.0464,
      "train_tokens_per_second": 29199.921
    },
    {
      "epoch": 2.6989365489698303,
      "grad_norm": 1.640625,
      "learning_rate": 1.702226914087239e-05,
      "loss": 1.034851360321045,
      "num_input_tokens_seen": 21695201088,
      "step": 76280,
      "train_runtime": 742990.3155,
      "train_tokens_per_second": 29199.844
    },
    {
      "epoch": 2.699290369233559,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7021282760085415e-05,
      "loss": 1.032474899291992,
      "num_input_tokens_seen": 21698053248,
      "step": 76290,
      "train_runtime": 743092.2209,
      "train_tokens_per_second": 29199.678
    },
    {
      "epoch": 2.699644189497288,
      "grad_norm": 1.6640625,
      "learning_rate": 1.7020296550750485e-05,
      "loss": 1.0346038818359375,
      "num_input_tokens_seen": 21700865984,
      "step": 76300,
      "train_runtime": 743188.5437,
      "train_tokens_per_second": 29199.678
    },
    {
      "epoch": 2.699998009761017,
      "grad_norm": 1.609375,
      "learning_rate": 1.7019310512817936e-05,
      "loss": 1.0329483032226563,
      "num_input_tokens_seen": 21703666688,
      "step": 76310,
      "train_runtime": 743284.3757,
      "train_tokens_per_second": 29199.681
    },
    {
      "epoch": 2.7003518300247453,
      "grad_norm": 1.6484375,
      "learning_rate": 1.7018324646238134e-05,
      "loss": 1.028021240234375,
      "num_input_tokens_seen": 21706505600,
      "step": 76320,
      "train_runtime": 743382.1003,
      "train_tokens_per_second": 29199.661
    },
    {
      "epoch": 2.700705650288474,
      "grad_norm": 1.578125,
      "learning_rate": 1.7017338950961455e-05,
      "loss": 1.050076389312744,
      "num_input_tokens_seen": 21709358976,
      "step": 76330,
      "train_runtime": 743480.171,
      "train_tokens_per_second": 29199.648
    },
    {
      "epoch": 2.701059470552203,
      "grad_norm": 1.609375,
      "learning_rate": 1.7016353426938287e-05,
      "loss": 1.0373003005981445,
      "num_input_tokens_seen": 21712215616,
      "step": 76340,
      "train_runtime": 743579.3662,
      "train_tokens_per_second": 29199.594
    },
    {
      "epoch": 2.701413290815932,
      "grad_norm": 1.640625,
      "learning_rate": 1.701536807411905e-05,
      "loss": 1.0228207588195801,
      "num_input_tokens_seen": 21715044352,
      "step": 76350,
      "train_runtime": 743676.2157,
      "train_tokens_per_second": 29199.595
    },
    {
      "epoch": 2.7017671110796604,
      "grad_norm": 1.5625,
      "learning_rate": 1.7014382892454186e-05,
      "loss": 1.043057918548584,
      "num_input_tokens_seen": 21717864448,
      "step": 76360,
      "train_runtime": 743770.8085,
      "train_tokens_per_second": 29199.673
    },
    {
      "epoch": 2.702120931343389,
      "grad_norm": 1.5703125,
      "learning_rate": 1.7013397881894147e-05,
      "loss": 1.0498950004577636,
      "num_input_tokens_seen": 21720737600,
      "step": 76370,
      "train_runtime": 743870.2714,
      "train_tokens_per_second": 29199.631
    },
    {
      "epoch": 2.702474751607118,
      "grad_norm": 1.5625,
      "learning_rate": 1.701241304238941e-05,
      "loss": 1.0266778945922852,
      "num_input_tokens_seen": 21723578752,
      "step": 76380,
      "train_runtime": 743970.8812,
      "train_tokens_per_second": 29199.501
    },
    {
      "epoch": 2.702828571870847,
      "grad_norm": 1.6015625,
      "learning_rate": 1.7011428373890478e-05,
      "loss": 1.0336106300354004,
      "num_input_tokens_seen": 21726396992,
      "step": 76390,
      "train_runtime": 744066.9439,
      "train_tokens_per_second": 29199.519
    },
    {
      "epoch": 2.7031823921345755,
      "grad_norm": 1.6953125,
      "learning_rate": 1.7010443876347863e-05,
      "loss": 1.0420209884643554,
      "num_input_tokens_seen": 21729171008,
      "step": 76400,
      "train_runtime": 744160.6157,
      "train_tokens_per_second": 29199.571
    },
    {
      "epoch": 2.7035362123983044,
      "grad_norm": 1.6015625,
      "learning_rate": 1.70094595497121e-05,
      "loss": 1.0338743209838868,
      "num_input_tokens_seen": 21731987520,
      "step": 76410,
      "train_runtime": 744257.1997,
      "train_tokens_per_second": 29199.566
    },
    {
      "epoch": 2.703890032662033,
      "grad_norm": 1.578125,
      "learning_rate": 1.700847539393375e-05,
      "loss": 1.0431564331054688,
      "num_input_tokens_seen": 21734839360,
      "step": 76420,
      "train_runtime": 744357.5053,
      "train_tokens_per_second": 29199.463
    },
    {
      "epoch": 2.704243852925762,
      "grad_norm": 1.625,
      "learning_rate": 1.7007491408963392e-05,
      "loss": 1.0525484085083008,
      "num_input_tokens_seen": 21737673280,
      "step": 76430,
      "train_runtime": 744453.8354,
      "train_tokens_per_second": 29199.491
    },
    {
      "epoch": 2.7045976731894905,
      "grad_norm": 1.609375,
      "learning_rate": 1.7006507594751617e-05,
      "loss": 1.033160400390625,
      "num_input_tokens_seen": 21740469248,
      "step": 76440,
      "train_runtime": 744547.804,
      "train_tokens_per_second": 29199.561
    },
    {
      "epoch": 2.7049514934532195,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7005523951249047e-05,
      "loss": 1.0297947883605958,
      "num_input_tokens_seen": 21743335360,
      "step": 76450,
      "train_runtime": 744644.4561,
      "train_tokens_per_second": 29199.62
    },
    {
      "epoch": 2.705305313716948,
      "grad_norm": 1.578125,
      "learning_rate": 1.700454047840632e-05,
      "loss": 1.0360895156860352,
      "num_input_tokens_seen": 21746228608,
      "step": 76460,
      "train_runtime": 744747.2681,
      "train_tokens_per_second": 29199.474
    },
    {
      "epoch": 2.705659133980677,
      "grad_norm": 1.5703125,
      "learning_rate": 1.700355717617409e-05,
      "loss": 1.0420401573181153,
      "num_input_tokens_seen": 21749065088,
      "step": 76470,
      "train_runtime": 744845.0351,
      "train_tokens_per_second": 29199.45
    },
    {
      "epoch": 2.7060129542444056,
      "grad_norm": 1.609375,
      "learning_rate": 1.7002574044503038e-05,
      "loss": 1.0384427070617677,
      "num_input_tokens_seen": 21751911296,
      "step": 76480,
      "train_runtime": 744943.4958,
      "train_tokens_per_second": 29199.411
    },
    {
      "epoch": 2.7063667745081346,
      "grad_norm": 1.6171875,
      "learning_rate": 1.7001591083343853e-05,
      "loss": 1.0449153900146484,
      "num_input_tokens_seen": 21754742208,
      "step": 76490,
      "train_runtime": 745040.9336,
      "train_tokens_per_second": 29199.392
    },
    {
      "epoch": 2.7067205947718636,
      "grad_norm": 1.59375,
      "learning_rate": 1.700060829264726e-05,
      "loss": 1.0282995223999023,
      "num_input_tokens_seen": 21757582848,
      "step": 76500,
      "train_runtime": 745137.4794,
      "train_tokens_per_second": 29199.421
    },
    {
      "epoch": 2.707074415035592,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6999625672363997e-05,
      "loss": 1.0365151405334472,
      "num_input_tokens_seen": 21760409728,
      "step": 76510,
      "train_runtime": 745234.4034,
      "train_tokens_per_second": 29199.416
    },
    {
      "epoch": 2.7074282352993206,
      "grad_norm": 1.625,
      "learning_rate": 1.699864322244482e-05,
      "loss": 1.031969928741455,
      "num_input_tokens_seen": 21763204672,
      "step": 76520,
      "train_runtime": 745329.3794,
      "train_tokens_per_second": 29199.446
    },
    {
      "epoch": 2.7077820555630496,
      "grad_norm": 1.578125,
      "learning_rate": 1.6997660942840497e-05,
      "loss": 1.0243657112121582,
      "num_input_tokens_seen": 21766003712,
      "step": 76530,
      "train_runtime": 745422.0275,
      "train_tokens_per_second": 29199.571
    },
    {
      "epoch": 2.7081358758267786,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6996678833501832e-05,
      "loss": 1.035759162902832,
      "num_input_tokens_seen": 21768833600,
      "step": 76540,
      "train_runtime": 745518.855,
      "train_tokens_per_second": 29199.575
    },
    {
      "epoch": 2.708489696090507,
      "grad_norm": 1.6015625,
      "learning_rate": 1.699569689437965e-05,
      "loss": 1.0384992599487304,
      "num_input_tokens_seen": 21771657984,
      "step": 76550,
      "train_runtime": 745615.0364,
      "train_tokens_per_second": 29199.596
    },
    {
      "epoch": 2.708843516354236,
      "grad_norm": 1.5390625,
      "learning_rate": 1.699471512542477e-05,
      "loss": 1.0281932830810547,
      "num_input_tokens_seen": 21774478912,
      "step": 76560,
      "train_runtime": 745711.7168,
      "train_tokens_per_second": 29199.593
    },
    {
      "epoch": 2.7091973366179647,
      "grad_norm": 1.71875,
      "learning_rate": 1.6993733526588064e-05,
      "loss": 1.0381028175354003,
      "num_input_tokens_seen": 21777322304,
      "step": 76570,
      "train_runtime": 745809.2045,
      "train_tokens_per_second": 29199.589
    },
    {
      "epoch": 2.7095511568816937,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6992752097820396e-05,
      "loss": 1.0340736389160157,
      "num_input_tokens_seen": 21780193088,
      "step": 76580,
      "train_runtime": 745907.7903,
      "train_tokens_per_second": 29199.579
    },
    {
      "epoch": 2.7099049771454222,
      "grad_norm": 1.5546875,
      "learning_rate": 1.699177083907267e-05,
      "loss": 1.0392833709716798,
      "num_input_tokens_seen": 21783066048,
      "step": 76590,
      "train_runtime": 746005.4943,
      "train_tokens_per_second": 29199.605
    },
    {
      "epoch": 2.710258797409151,
      "grad_norm": 1.5625,
      "learning_rate": 1.6990789750295798e-05,
      "loss": 1.0290023803710937,
      "num_input_tokens_seen": 21785906688,
      "step": 76600,
      "train_runtime": 746101.7867,
      "train_tokens_per_second": 29199.644
    },
    {
      "epoch": 2.7106126176728798,
      "grad_norm": 1.671875,
      "learning_rate": 1.6989808831440724e-05,
      "loss": 1.0462963104248046,
      "num_input_tokens_seen": 21788675264,
      "step": 76610,
      "train_runtime": 746195.0022,
      "train_tokens_per_second": 29199.707
    },
    {
      "epoch": 2.7109664379366087,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6988828082458395e-05,
      "loss": 1.0390210151672363,
      "num_input_tokens_seen": 21791558400,
      "step": 76620,
      "train_runtime": 746293.3764,
      "train_tokens_per_second": 29199.721
    },
    {
      "epoch": 2.7113202582003373,
      "grad_norm": 1.59375,
      "learning_rate": 1.6987847503299786e-05,
      "loss": 1.048428440093994,
      "num_input_tokens_seen": 21794476480,
      "step": 76630,
      "train_runtime": 746394.6297,
      "train_tokens_per_second": 29199.669
    },
    {
      "epoch": 2.7116740784640663,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6986867093915897e-05,
      "loss": 1.0435577392578126,
      "num_input_tokens_seen": 21797305600,
      "step": 76640,
      "train_runtime": 746490.3257,
      "train_tokens_per_second": 29199.716
    },
    {
      "epoch": 2.7120278987277953,
      "grad_norm": 1.640625,
      "learning_rate": 1.6985886854257746e-05,
      "loss": 1.0305185317993164,
      "num_input_tokens_seen": 21800140032,
      "step": 76650,
      "train_runtime": 746587.301,
      "train_tokens_per_second": 29199.72
    },
    {
      "epoch": 2.712381718991524,
      "grad_norm": 1.6953125,
      "learning_rate": 1.6984906784276358e-05,
      "loss": 1.0359444618225098,
      "num_input_tokens_seen": 21802975936,
      "step": 76660,
      "train_runtime": 746683.4846,
      "train_tokens_per_second": 29199.757
    },
    {
      "epoch": 2.7127355392552523,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6983926883922794e-05,
      "loss": 1.030405616760254,
      "num_input_tokens_seen": 21805830272,
      "step": 76670,
      "train_runtime": 746779.1115,
      "train_tokens_per_second": 29199.84
    },
    {
      "epoch": 2.7130893595189813,
      "grad_norm": 1.5703125,
      "learning_rate": 1.698294715314813e-05,
      "loss": 1.046832275390625,
      "num_input_tokens_seen": 21808682048,
      "step": 76680,
      "train_runtime": 746878.5209,
      "train_tokens_per_second": 29199.771
    },
    {
      "epoch": 2.7134431797827103,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6981967591903456e-05,
      "loss": 1.0256492614746093,
      "num_input_tokens_seen": 21811552832,
      "step": 76690,
      "train_runtime": 746977.4839,
      "train_tokens_per_second": 29199.746
    },
    {
      "epoch": 2.713797000046439,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6980988200139892e-05,
      "loss": 1.0317070960998536,
      "num_input_tokens_seen": 21814358976,
      "step": 76700,
      "train_runtime": 747069.7583,
      "train_tokens_per_second": 29199.896
    },
    {
      "epoch": 2.7141508203101674,
      "grad_norm": 1.6015625,
      "learning_rate": 1.698000897780856e-05,
      "loss": 1.0546156883239746,
      "num_input_tokens_seen": 21817212736,
      "step": 76710,
      "train_runtime": 747167.6475,
      "train_tokens_per_second": 29199.889
    },
    {
      "epoch": 2.7145046405738964,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6979029924860625e-05,
      "loss": 1.0517955780029298,
      "num_input_tokens_seen": 21820037248,
      "step": 76720,
      "train_runtime": 747264.3065,
      "train_tokens_per_second": 29199.892
    },
    {
      "epoch": 2.7148584608376254,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6978051041247257e-05,
      "loss": 1.0421335220336914,
      "num_input_tokens_seen": 21822866944,
      "step": 76730,
      "train_runtime": 747359.304,
      "train_tokens_per_second": 29199.967
    },
    {
      "epoch": 2.715212281101354,
      "grad_norm": 1.609375,
      "learning_rate": 1.6977072326919648e-05,
      "loss": 1.0271671295166016,
      "num_input_tokens_seen": 21825739008,
      "step": 76740,
      "train_runtime": 747458.508,
      "train_tokens_per_second": 29199.934
    },
    {
      "epoch": 2.715566101365083,
      "grad_norm": 1.609375,
      "learning_rate": 1.6976093781829007e-05,
      "loss": 1.0535451889038085,
      "num_input_tokens_seen": 21828614784,
      "step": 76750,
      "train_runtime": 747558.4088,
      "train_tokens_per_second": 29199.879
    },
    {
      "epoch": 2.7159199216288115,
      "grad_norm": 1.6015625,
      "learning_rate": 1.697511540592657e-05,
      "loss": 1.0340782165527345,
      "num_input_tokens_seen": 21831440576,
      "step": 76760,
      "train_runtime": 747657.67,
      "train_tokens_per_second": 29199.781
    },
    {
      "epoch": 2.7162737418925404,
      "grad_norm": 1.65625,
      "learning_rate": 1.6974137199163594e-05,
      "loss": 1.0348898887634277,
      "num_input_tokens_seen": 21834287296,
      "step": 76770,
      "train_runtime": 747755.4973,
      "train_tokens_per_second": 29199.768
    },
    {
      "epoch": 2.716627562156269,
      "grad_norm": 1.609375,
      "learning_rate": 1.697315916149134e-05,
      "loss": 1.0303754806518555,
      "num_input_tokens_seen": 21837165440,
      "step": 76780,
      "train_runtime": 747857.2483,
      "train_tokens_per_second": 29199.644
    },
    {
      "epoch": 2.716981382419998,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6972181292861104e-05,
      "loss": 1.0183255195617675,
      "num_input_tokens_seen": 21839997568,
      "step": 76790,
      "train_runtime": 747953.6817,
      "train_tokens_per_second": 29199.666
    },
    {
      "epoch": 2.717335202683727,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6971203593224196e-05,
      "loss": 1.0293447494506835,
      "num_input_tokens_seen": 21842827200,
      "step": 76800,
      "train_runtime": 748049.2193,
      "train_tokens_per_second": 29199.719
    },
    {
      "epoch": 2.7176890229474555,
      "grad_norm": 1.59375,
      "learning_rate": 1.6970226062531953e-05,
      "loss": 1.0314170837402343,
      "num_input_tokens_seen": 21845663168,
      "step": 76810,
      "train_runtime": 748143.5435,
      "train_tokens_per_second": 29199.829
    },
    {
      "epoch": 2.718042843211184,
      "grad_norm": 1.578125,
      "learning_rate": 1.6969248700735715e-05,
      "loss": 1.0409141540527345,
      "num_input_tokens_seen": 21848520832,
      "step": 76820,
      "train_runtime": 748244.0763,
      "train_tokens_per_second": 29199.724
    },
    {
      "epoch": 2.718396663474913,
      "grad_norm": 1.59375,
      "learning_rate": 1.6968271507786855e-05,
      "loss": 1.037938690185547,
      "num_input_tokens_seen": 21851369344,
      "step": 76830,
      "train_runtime": 748343.4337,
      "train_tokens_per_second": 29199.654
    },
    {
      "epoch": 2.718750483738642,
      "grad_norm": 1.65625,
      "learning_rate": 1.696729448363677e-05,
      "loss": 1.0392114639282226,
      "num_input_tokens_seen": 21854241984,
      "step": 76840,
      "train_runtime": 748440.6308,
      "train_tokens_per_second": 29199.7
    },
    {
      "epoch": 2.7191043040023706,
      "grad_norm": 1.65625,
      "learning_rate": 1.6966317628236856e-05,
      "loss": 1.034537124633789,
      "num_input_tokens_seen": 21857128640,
      "step": 76850,
      "train_runtime": 748539.401,
      "train_tokens_per_second": 29199.704
    },
    {
      "epoch": 2.719458124266099,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6965340941538545e-05,
      "loss": 1.0269306182861329,
      "num_input_tokens_seen": 21860015104,
      "step": 76860,
      "train_runtime": 748638.9982,
      "train_tokens_per_second": 29199.675
    },
    {
      "epoch": 2.719811944529828,
      "grad_norm": 1.5234375,
      "learning_rate": 1.6964364423493297e-05,
      "loss": 1.0343852043151855,
      "num_input_tokens_seen": 21862857920,
      "step": 76870,
      "train_runtime": 748736.6903,
      "train_tokens_per_second": 29199.662
    },
    {
      "epoch": 2.720165764793557,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6963388074052565e-05,
      "loss": 1.0279793739318848,
      "num_input_tokens_seen": 21865689920,
      "step": 76880,
      "train_runtime": 748833.5042,
      "train_tokens_per_second": 29199.668
    },
    {
      "epoch": 2.7205195850572856,
      "grad_norm": 1.515625,
      "learning_rate": 1.696241189316784e-05,
      "loss": 1.0380186080932616,
      "num_input_tokens_seen": 21868568512,
      "step": 76890,
      "train_runtime": 748933.1054,
      "train_tokens_per_second": 29199.629
    },
    {
      "epoch": 2.7208734053210146,
      "grad_norm": 1.5859375,
      "learning_rate": 1.696143588079063e-05,
      "loss": 1.0345788955688477,
      "num_input_tokens_seen": 21871420864,
      "step": 76900,
      "train_runtime": 749033.0913,
      "train_tokens_per_second": 29199.539
    },
    {
      "epoch": 2.721227225584743,
      "grad_norm": 1.53125,
      "learning_rate": 1.6960460036872468e-05,
      "loss": 1.0365086555480958,
      "num_input_tokens_seen": 21874252096,
      "step": 76910,
      "train_runtime": 749127.2028,
      "train_tokens_per_second": 29199.65
    },
    {
      "epoch": 2.721581045848472,
      "grad_norm": 1.5234375,
      "learning_rate": 1.6959484361364888e-05,
      "loss": 1.0338808059692384,
      "num_input_tokens_seen": 21877093760,
      "step": 76920,
      "train_runtime": 749223.2137,
      "train_tokens_per_second": 29199.701
    },
    {
      "epoch": 2.7219348661122007,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6958508854219458e-05,
      "loss": 1.027717399597168,
      "num_input_tokens_seen": 21879918656,
      "step": 76930,
      "train_runtime": 749320.3583,
      "train_tokens_per_second": 29199.685
    },
    {
      "epoch": 2.7222886863759297,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6957533515387773e-05,
      "loss": 1.0405205726623534,
      "num_input_tokens_seen": 21882779904,
      "step": 76940,
      "train_runtime": 749417.939,
      "train_tokens_per_second": 29199.701
    },
    {
      "epoch": 2.7226425066396582,
      "grad_norm": 1.65625,
      "learning_rate": 1.6956558344821422e-05,
      "loss": 1.0352829933166503,
      "num_input_tokens_seen": 21885640960,
      "step": 76950,
      "train_runtime": 749516.3235,
      "train_tokens_per_second": 29199.686
    },
    {
      "epoch": 2.722996326903387,
      "grad_norm": 1.640625,
      "learning_rate": 1.695558334247204e-05,
      "loss": 1.035008430480957,
      "num_input_tokens_seen": 21888424064,
      "step": 76960,
      "train_runtime": 749609.7048,
      "train_tokens_per_second": 29199.761
    },
    {
      "epoch": 2.7233501471671158,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6954608508291262e-05,
      "loss": 1.033052349090576,
      "num_input_tokens_seen": 21891334464,
      "step": 76970,
      "train_runtime": 749712.8831,
      "train_tokens_per_second": 29199.624
    },
    {
      "epoch": 2.7237039674308448,
      "grad_norm": 1.578125,
      "learning_rate": 1.6953633842230755e-05,
      "loss": 1.0521023750305176,
      "num_input_tokens_seen": 21894168512,
      "step": 76980,
      "train_runtime": 749808.3577,
      "train_tokens_per_second": 29199.686
    },
    {
      "epoch": 2.7240577876945737,
      "grad_norm": 1.59375,
      "learning_rate": 1.6952659344242205e-05,
      "loss": 1.0476419448852539,
      "num_input_tokens_seen": 21896982784,
      "step": 76990,
      "train_runtime": 749905.9147,
      "train_tokens_per_second": 29199.64
    },
    {
      "epoch": 2.7244116079583023,
      "grad_norm": 1.609375,
      "learning_rate": 1.6951685014277307e-05,
      "loss": 1.0367165565490724,
      "num_input_tokens_seen": 21899842432,
      "step": 77000,
      "train_runtime": 750005.6231,
      "train_tokens_per_second": 29199.571
    },
    {
      "epoch": 2.724765428222031,
      "grad_norm": 1.578125,
      "learning_rate": 1.6950710852287785e-05,
      "loss": 1.0342987060546875,
      "num_input_tokens_seen": 21902723712,
      "step": 77010,
      "train_runtime": 750105.5536,
      "train_tokens_per_second": 29199.522
    },
    {
      "epoch": 2.72511924848576,
      "grad_norm": 1.59375,
      "learning_rate": 1.694973685822538e-05,
      "loss": 1.0449722290039063,
      "num_input_tokens_seen": 21905556736,
      "step": 77020,
      "train_runtime": 750206.037,
      "train_tokens_per_second": 29199.387
    },
    {
      "epoch": 2.725473068749489,
      "grad_norm": 1.609375,
      "learning_rate": 1.694876303204185e-05,
      "loss": 1.0455759048461915,
      "num_input_tokens_seen": 21908415424,
      "step": 77030,
      "train_runtime": 750303.0593,
      "train_tokens_per_second": 29199.422
    },
    {
      "epoch": 2.7258268890132173,
      "grad_norm": 1.5703125,
      "learning_rate": 1.694778937368897e-05,
      "loss": 1.0404438018798827,
      "num_input_tokens_seen": 21911277504,
      "step": 77040,
      "train_runtime": 750402.5725,
      "train_tokens_per_second": 29199.364
    },
    {
      "epoch": 2.7261807092769463,
      "grad_norm": 1.6015625,
      "learning_rate": 1.694681588311855e-05,
      "loss": 1.0524599075317382,
      "num_input_tokens_seen": 21914132480,
      "step": 77050,
      "train_runtime": 750500.4586,
      "train_tokens_per_second": 29199.359
    },
    {
      "epoch": 2.726534529540675,
      "grad_norm": 1.6328125,
      "learning_rate": 1.69458425602824e-05,
      "loss": 1.0411909103393555,
      "num_input_tokens_seen": 21917014848,
      "step": 77060,
      "train_runtime": 750599.8558,
      "train_tokens_per_second": 29199.333
    },
    {
      "epoch": 2.726888349804404,
      "grad_norm": 1.59375,
      "learning_rate": 1.6944869405132355e-05,
      "loss": 1.0255498886108398,
      "num_input_tokens_seen": 21919817088,
      "step": 77070,
      "train_runtime": 750695.1924,
      "train_tokens_per_second": 29199.357
    },
    {
      "epoch": 2.7272421700681324,
      "grad_norm": 1.625,
      "learning_rate": 1.6943896417620272e-05,
      "loss": 1.036949348449707,
      "num_input_tokens_seen": 21922673088,
      "step": 77080,
      "train_runtime": 750794.9938,
      "train_tokens_per_second": 29199.28
    },
    {
      "epoch": 2.7275959903318614,
      "grad_norm": 1.546875,
      "learning_rate": 1.6942923597698035e-05,
      "loss": 1.0369297027587892,
      "num_input_tokens_seen": 21925522880,
      "step": 77090,
      "train_runtime": 750891.3239,
      "train_tokens_per_second": 29199.329
    },
    {
      "epoch": 2.72794981059559,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6941950945317536e-05,
      "loss": 1.0427448272705078,
      "num_input_tokens_seen": 21928275456,
      "step": 77100,
      "train_runtime": 750981.753,
      "train_tokens_per_second": 29199.478
    },
    {
      "epoch": 2.728303630859319,
      "grad_norm": 1.640625,
      "learning_rate": 1.6940978460430684e-05,
      "loss": 1.0525982856750489,
      "num_input_tokens_seen": 21931067648,
      "step": 77110,
      "train_runtime": 751075.0683,
      "train_tokens_per_second": 29199.568
    },
    {
      "epoch": 2.7286574511230475,
      "grad_norm": 1.65625,
      "learning_rate": 1.694000614298942e-05,
      "loss": 1.0271966934204102,
      "num_input_tokens_seen": 21933895808,
      "step": 77120,
      "train_runtime": 751169.8166,
      "train_tokens_per_second": 29199.65
    },
    {
      "epoch": 2.7290112713867765,
      "grad_norm": 1.671875,
      "learning_rate": 1.6939033992945697e-05,
      "loss": 1.0243898391723634,
      "num_input_tokens_seen": 21936745856,
      "step": 77130,
      "train_runtime": 751266.719,
      "train_tokens_per_second": 29199.677
    },
    {
      "epoch": 2.7293650916505054,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6938062010251483e-05,
      "loss": 1.0478816032409668,
      "num_input_tokens_seen": 21939569088,
      "step": 77140,
      "train_runtime": 751362.6374,
      "train_tokens_per_second": 29199.707
    },
    {
      "epoch": 2.729718911914234,
      "grad_norm": 1.59375,
      "learning_rate": 1.693709019485877e-05,
      "loss": 1.028091812133789,
      "num_input_tokens_seen": 21942403072,
      "step": 77150,
      "train_runtime": 751457.8593,
      "train_tokens_per_second": 29199.779
    },
    {
      "epoch": 2.7300727321779625,
      "grad_norm": 1.703125,
      "learning_rate": 1.6936118546719572e-05,
      "loss": 1.0413694381713867,
      "num_input_tokens_seen": 21945177536,
      "step": 77160,
      "train_runtime": 751551.3482,
      "train_tokens_per_second": 29199.838
    },
    {
      "epoch": 2.7304265524416915,
      "grad_norm": 1.546875,
      "learning_rate": 1.6935147065785917e-05,
      "loss": 1.0388131141662598,
      "num_input_tokens_seen": 21948041216,
      "step": 77170,
      "train_runtime": 751648.6933,
      "train_tokens_per_second": 29199.866
    },
    {
      "epoch": 2.7307803727054205,
      "grad_norm": 1.71875,
      "learning_rate": 1.693417575200986e-05,
      "loss": 1.028806495666504,
      "num_input_tokens_seen": 21950913408,
      "step": 77180,
      "train_runtime": 751745.9489,
      "train_tokens_per_second": 29199.909
    },
    {
      "epoch": 2.731134192969149,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6933204605343466e-05,
      "loss": 1.0345026969909668,
      "num_input_tokens_seen": 21953740544,
      "step": 77190,
      "train_runtime": 751843.1826,
      "train_tokens_per_second": 29199.893
    },
    {
      "epoch": 2.7314880132328776,
      "grad_norm": 1.6015625,
      "learning_rate": 1.693223362573882e-05,
      "loss": 1.0410938262939453,
      "num_input_tokens_seen": 21956518336,
      "step": 77200,
      "train_runtime": 751935.6464,
      "train_tokens_per_second": 29199.997
    },
    {
      "epoch": 2.7318418334966066,
      "grad_norm": 1.671875,
      "learning_rate": 1.6931262813148036e-05,
      "loss": 1.040059471130371,
      "num_input_tokens_seen": 21959352768,
      "step": 77210,
      "train_runtime": 752033.9334,
      "train_tokens_per_second": 29199.949
    },
    {
      "epoch": 2.7321956537603356,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6930292167523236e-05,
      "loss": 1.0253015518188477,
      "num_input_tokens_seen": 21962230144,
      "step": 77220,
      "train_runtime": 752133.0698,
      "train_tokens_per_second": 29199.926
    },
    {
      "epoch": 2.732549474024064,
      "grad_norm": 1.625,
      "learning_rate": 1.6929321688816573e-05,
      "loss": 1.0230438232421875,
      "num_input_tokens_seen": 21965091328,
      "step": 77230,
      "train_runtime": 752227.0208,
      "train_tokens_per_second": 29200.083
    },
    {
      "epoch": 2.732903294287793,
      "grad_norm": 1.65625,
      "learning_rate": 1.6928351376980197e-05,
      "loss": 1.0273933410644531,
      "num_input_tokens_seen": 21967972992,
      "step": 77240,
      "train_runtime": 752325.1505,
      "train_tokens_per_second": 29200.104
    },
    {
      "epoch": 2.7332571145515216,
      "grad_norm": 1.578125,
      "learning_rate": 1.692738123196631e-05,
      "loss": 1.0298395156860352,
      "num_input_tokens_seen": 21970800576,
      "step": 77250,
      "train_runtime": 752422.2158,
      "train_tokens_per_second": 29200.096
    },
    {
      "epoch": 2.7336109348152506,
      "grad_norm": 1.59375,
      "learning_rate": 1.6926411253727104e-05,
      "loss": 1.0399215698242188,
      "num_input_tokens_seen": 21973649280,
      "step": 77260,
      "train_runtime": 752518.8628,
      "train_tokens_per_second": 29200.131
    },
    {
      "epoch": 2.733964755078979,
      "grad_norm": 1.609375,
      "learning_rate": 1.69254414422148e-05,
      "loss": 1.0352811813354492,
      "num_input_tokens_seen": 21976449216,
      "step": 77270,
      "train_runtime": 752612.7139,
      "train_tokens_per_second": 29200.21
    },
    {
      "epoch": 2.734318575342708,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6924471797381652e-05,
      "loss": 1.0239381790161133,
      "num_input_tokens_seen": 21979263296,
      "step": 77280,
      "train_runtime": 752708.4059,
      "train_tokens_per_second": 29200.236
    },
    {
      "epoch": 2.7346723956064367,
      "grad_norm": 1.6484375,
      "learning_rate": 1.692350231917991e-05,
      "loss": 1.0358606338500977,
      "num_input_tokens_seen": 21982126528,
      "step": 77290,
      "train_runtime": 752804.7602,
      "train_tokens_per_second": 29200.302
    },
    {
      "epoch": 2.7350262158701657,
      "grad_norm": 1.5625,
      "learning_rate": 1.692253300756186e-05,
      "loss": 1.033787727355957,
      "num_input_tokens_seen": 21985036480,
      "step": 77300,
      "train_runtime": 752905.6452,
      "train_tokens_per_second": 29200.255
    },
    {
      "epoch": 2.7353800361338942,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6921563862479795e-05,
      "loss": 1.0382116317749024,
      "num_input_tokens_seen": 21987895872,
      "step": 77310,
      "train_runtime": 753001.5138,
      "train_tokens_per_second": 29200.334
    },
    {
      "epoch": 2.7357338563976232,
      "grad_norm": 1.6953125,
      "learning_rate": 1.692059488388604e-05,
      "loss": 1.029775333404541,
      "num_input_tokens_seen": 21990741056,
      "step": 77320,
      "train_runtime": 753097.7873,
      "train_tokens_per_second": 29200.379
    },
    {
      "epoch": 2.736087676661352,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6919626071732924e-05,
      "loss": 1.0358288764953614,
      "num_input_tokens_seen": 21993612672,
      "step": 77330,
      "train_runtime": 753197.5032,
      "train_tokens_per_second": 29200.326
    },
    {
      "epoch": 2.7364414969250808,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6918657425972812e-05,
      "loss": 1.0407492637634277,
      "num_input_tokens_seen": 21996454272,
      "step": 77340,
      "train_runtime": 753295.5325,
      "train_tokens_per_second": 29200.298
    },
    {
      "epoch": 2.7367953171888093,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6917688946558078e-05,
      "loss": 1.037459373474121,
      "num_input_tokens_seen": 21999303488,
      "step": 77350,
      "train_runtime": 753393.1217,
      "train_tokens_per_second": 29200.298
    },
    {
      "epoch": 2.7371491374525383,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6916720633441113e-05,
      "loss": 1.0311447143554688,
      "num_input_tokens_seen": 22002172608,
      "step": 77360,
      "train_runtime": 753490.5321,
      "train_tokens_per_second": 29200.331
    },
    {
      "epoch": 2.7375029577162673,
      "grad_norm": 1.625,
      "learning_rate": 1.6915752486574336e-05,
      "loss": 1.0316404342651366,
      "num_input_tokens_seen": 22005088576,
      "step": 77370,
      "train_runtime": 753589.6505,
      "train_tokens_per_second": 29200.359
    },
    {
      "epoch": 2.737856777979996,
      "grad_norm": 1.578125,
      "learning_rate": 1.6914784505910173e-05,
      "loss": 1.029127311706543,
      "num_input_tokens_seen": 22007950400,
      "step": 77380,
      "train_runtime": 753683.7007,
      "train_tokens_per_second": 29200.513
    },
    {
      "epoch": 2.738210598243725,
      "grad_norm": 1.5625,
      "learning_rate": 1.6913816691401083e-05,
      "loss": 1.0060611724853517,
      "num_input_tokens_seen": 22010779520,
      "step": 77390,
      "train_runtime": 753779.1978,
      "train_tokens_per_second": 29200.566
    },
    {
      "epoch": 2.7385644185074534,
      "grad_norm": 1.59375,
      "learning_rate": 1.691284904299953e-05,
      "loss": 1.0296453475952148,
      "num_input_tokens_seen": 22013619264,
      "step": 77400,
      "train_runtime": 753874.045,
      "train_tokens_per_second": 29200.659
    },
    {
      "epoch": 2.7389182387711823,
      "grad_norm": 1.59375,
      "learning_rate": 1.6911881560658007e-05,
      "loss": 1.0385475158691406,
      "num_input_tokens_seen": 22016483264,
      "step": 77410,
      "train_runtime": 753972.0355,
      "train_tokens_per_second": 29200.663
    },
    {
      "epoch": 2.739272059034911,
      "grad_norm": 1.59375,
      "learning_rate": 1.6910914244329028e-05,
      "loss": 1.0315587043762207,
      "num_input_tokens_seen": 22019272000,
      "step": 77420,
      "train_runtime": 754066.5677,
      "train_tokens_per_second": 29200.7
    },
    {
      "epoch": 2.73962587929864,
      "grad_norm": 1.59375,
      "learning_rate": 1.690994709396511e-05,
      "loss": 1.0386127471923827,
      "num_input_tokens_seen": 22022173440,
      "step": 77430,
      "train_runtime": 754168.8651,
      "train_tokens_per_second": 29200.587
    },
    {
      "epoch": 2.7399796995623684,
      "grad_norm": 1.6171875,
      "learning_rate": 1.690898010951881e-05,
      "loss": 1.0369446754455567,
      "num_input_tokens_seen": 22024978752,
      "step": 77440,
      "train_runtime": 754264.465,
      "train_tokens_per_second": 29200.605
    },
    {
      "epoch": 2.7403335198260974,
      "grad_norm": 1.5546875,
      "learning_rate": 1.690801329094269e-05,
      "loss": 1.0497906684875489,
      "num_input_tokens_seen": 22027876416,
      "step": 77450,
      "train_runtime": 754362.9811,
      "train_tokens_per_second": 29200.633
    },
    {
      "epoch": 2.740687340089826,
      "grad_norm": 1.59375,
      "learning_rate": 1.6907046638189336e-05,
      "loss": 1.0211292266845704,
      "num_input_tokens_seen": 22030670016,
      "step": 77460,
      "train_runtime": 754457.5628,
      "train_tokens_per_second": 29200.675
    },
    {
      "epoch": 2.741041160353555,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6906080151211352e-05,
      "loss": 1.020215129852295,
      "num_input_tokens_seen": 22033492032,
      "step": 77470,
      "train_runtime": 754554.4364,
      "train_tokens_per_second": 29200.666
    },
    {
      "epoch": 2.741394980617284,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6905113829961355e-05,
      "loss": 1.0405159950256349,
      "num_input_tokens_seen": 22036393792,
      "step": 77480,
      "train_runtime": 754656.0236,
      "train_tokens_per_second": 29200.58
    },
    {
      "epoch": 2.7417488008810125,
      "grad_norm": 1.59375,
      "learning_rate": 1.6904147674391995e-05,
      "loss": 1.0426615715026855,
      "num_input_tokens_seen": 22039244224,
      "step": 77490,
      "train_runtime": 754753.2516,
      "train_tokens_per_second": 29200.595
    },
    {
      "epoch": 2.742102621144741,
      "grad_norm": 1.5703125,
      "learning_rate": 1.690318168445593e-05,
      "loss": 1.034453773498535,
      "num_input_tokens_seen": 22042118848,
      "step": 77500,
      "train_runtime": 754853.4032,
      "train_tokens_per_second": 29200.529
    },
    {
      "epoch": 2.74245644140847,
      "grad_norm": 1.625,
      "learning_rate": 1.6902215860105837e-05,
      "loss": 1.0449695587158203,
      "num_input_tokens_seen": 22044959296,
      "step": 77510,
      "train_runtime": 754947.9406,
      "train_tokens_per_second": 29200.635
    },
    {
      "epoch": 2.742810261672199,
      "grad_norm": 1.640625,
      "learning_rate": 1.6901250201294422e-05,
      "loss": 1.0425844192504883,
      "num_input_tokens_seen": 22047794688,
      "step": 77520,
      "train_runtime": 755045.6288,
      "train_tokens_per_second": 29200.612
    },
    {
      "epoch": 2.7431640819359275,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6900284707974394e-05,
      "loss": 1.0231382369995117,
      "num_input_tokens_seen": 22050627136,
      "step": 77530,
      "train_runtime": 755142.0406,
      "train_tokens_per_second": 29200.635
    },
    {
      "epoch": 2.743517902199656,
      "grad_norm": 1.6484375,
      "learning_rate": 1.689931938009849e-05,
      "loss": 1.0557575225830078,
      "num_input_tokens_seen": 22053482688,
      "step": 77540,
      "train_runtime": 755238.1041,
      "train_tokens_per_second": 29200.702
    },
    {
      "epoch": 2.743871722463385,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6898354217619476e-05,
      "loss": 1.0448843955993652,
      "num_input_tokens_seen": 22056334528,
      "step": 77550,
      "train_runtime": 755333.698,
      "train_tokens_per_second": 29200.782
    },
    {
      "epoch": 2.744225542727114,
      "grad_norm": 1.5625,
      "learning_rate": 1.689738922049011e-05,
      "loss": 1.035269069671631,
      "num_input_tokens_seen": 22059175488,
      "step": 77560,
      "train_runtime": 755432.3164,
      "train_tokens_per_second": 29200.731
    },
    {
      "epoch": 2.7445793629908426,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6896424388663198e-05,
      "loss": 1.0409799575805665,
      "num_input_tokens_seen": 22061974016,
      "step": 77570,
      "train_runtime": 755528.4558,
      "train_tokens_per_second": 29200.719
    },
    {
      "epoch": 2.7449331832545716,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6895459722091548e-05,
      "loss": 1.031081199645996,
      "num_input_tokens_seen": 22064835392,
      "step": 77580,
      "train_runtime": 755626.6601,
      "train_tokens_per_second": 29200.711
    },
    {
      "epoch": 2.7452870035183,
      "grad_norm": 1.5859375,
      "learning_rate": 1.689449522072799e-05,
      "loss": 1.0393082618713378,
      "num_input_tokens_seen": 22067711104,
      "step": 77590,
      "train_runtime": 755724.6048,
      "train_tokens_per_second": 29200.731
    },
    {
      "epoch": 2.745640823782029,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6893530884525372e-05,
      "loss": 1.0436410903930664,
      "num_input_tokens_seen": 22070538496,
      "step": 77600,
      "train_runtime": 755819.0623,
      "train_tokens_per_second": 29200.823
    },
    {
      "epoch": 2.7459946440457577,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6892566713436568e-05,
      "loss": 1.0397705078125,
      "num_input_tokens_seen": 22073471424,
      "step": 77610,
      "train_runtime": 755924.6126,
      "train_tokens_per_second": 29200.625
    },
    {
      "epoch": 2.7463484643094866,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6891602707414458e-05,
      "loss": 1.0292543411254882,
      "num_input_tokens_seen": 22076286656,
      "step": 77620,
      "train_runtime": 756019.7619,
      "train_tokens_per_second": 29200.674
    },
    {
      "epoch": 2.7467022845732156,
      "grad_norm": 1.5234375,
      "learning_rate": 1.6890638866411958e-05,
      "loss": 1.0453036308288575,
      "num_input_tokens_seen": 22079122304,
      "step": 77630,
      "train_runtime": 756117.4285,
      "train_tokens_per_second": 29200.653
    },
    {
      "epoch": 2.747056104836944,
      "grad_norm": 1.5625,
      "learning_rate": 1.6889675190381985e-05,
      "loss": 1.0436043739318848,
      "num_input_tokens_seen": 22081886336,
      "step": 77640,
      "train_runtime": 756209.8189,
      "train_tokens_per_second": 29200.74
    },
    {
      "epoch": 2.7474099251006727,
      "grad_norm": 1.5625,
      "learning_rate": 1.6888711679277482e-05,
      "loss": 1.0332523345947267,
      "num_input_tokens_seen": 22084674624,
      "step": 77650,
      "train_runtime": 756306.5111,
      "train_tokens_per_second": 29200.694
    },
    {
      "epoch": 2.7477637453644017,
      "grad_norm": 1.609375,
      "learning_rate": 1.688774833305142e-05,
      "loss": 1.031964111328125,
      "num_input_tokens_seen": 22087477760,
      "step": 77660,
      "train_runtime": 756400.9428,
      "train_tokens_per_second": 29200.754
    },
    {
      "epoch": 2.7481175656281307,
      "grad_norm": 1.59375,
      "learning_rate": 1.688678515165677e-05,
      "loss": 1.037259006500244,
      "num_input_tokens_seen": 22090309504,
      "step": 77670,
      "train_runtime": 756498.3948,
      "train_tokens_per_second": 29200.735
    },
    {
      "epoch": 2.7484713858918592,
      "grad_norm": 1.578125,
      "learning_rate": 1.6885822135046542e-05,
      "loss": 1.0400027275085448,
      "num_input_tokens_seen": 22093155520,
      "step": 77680,
      "train_runtime": 756597.9403,
      "train_tokens_per_second": 29200.655
    },
    {
      "epoch": 2.748825206155588,
      "grad_norm": 1.640625,
      "learning_rate": 1.6884859283173742e-05,
      "loss": 1.0416351318359376,
      "num_input_tokens_seen": 22095957504,
      "step": 77690,
      "train_runtime": 756690.9283,
      "train_tokens_per_second": 29200.77
    },
    {
      "epoch": 2.7491790264193168,
      "grad_norm": 1.6484375,
      "learning_rate": 1.688389659599142e-05,
      "loss": 1.0313817977905273,
      "num_input_tokens_seen": 22098825664,
      "step": 77700,
      "train_runtime": 756791.507,
      "train_tokens_per_second": 29200.679
    },
    {
      "epoch": 2.7495328466830458,
      "grad_norm": 1.6015625,
      "learning_rate": 1.688293407345263e-05,
      "loss": 1.0248108863830567,
      "num_input_tokens_seen": 22101652608,
      "step": 77710,
      "train_runtime": 756889.6945,
      "train_tokens_per_second": 29200.626
    },
    {
      "epoch": 2.7498866669467743,
      "grad_norm": 1.671875,
      "learning_rate": 1.688197171551044e-05,
      "loss": 1.0193477630615235,
      "num_input_tokens_seen": 22104494784,
      "step": 77720,
      "train_runtime": 756987.4765,
      "train_tokens_per_second": 29200.608
    },
    {
      "epoch": 2.7502404872105033,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6881009522117954e-05,
      "loss": 1.0322214126586915,
      "num_input_tokens_seen": 22107361344,
      "step": 77730,
      "train_runtime": 757088.8238,
      "train_tokens_per_second": 29200.486
    },
    {
      "epoch": 2.750594307474232,
      "grad_norm": 1.640625,
      "learning_rate": 1.688004749322828e-05,
      "loss": 1.0334153175354004,
      "num_input_tokens_seen": 22110234624,
      "step": 77740,
      "train_runtime": 757188.5594,
      "train_tokens_per_second": 29200.434
    },
    {
      "epoch": 2.750948127737961,
      "grad_norm": 1.65625,
      "learning_rate": 1.6879085628794544e-05,
      "loss": 1.0506589889526368,
      "num_input_tokens_seen": 22113058496,
      "step": 77750,
      "train_runtime": 757287.9966,
      "train_tokens_per_second": 29200.329
    },
    {
      "epoch": 2.7513019480016894,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6878123928769905e-05,
      "loss": 1.0295150756835938,
      "num_input_tokens_seen": 22115896384,
      "step": 77760,
      "train_runtime": 757384.8961,
      "train_tokens_per_second": 29200.34
    },
    {
      "epoch": 2.7516557682654184,
      "grad_norm": 1.609375,
      "learning_rate": 1.6877162393107524e-05,
      "loss": 1.0298801422119142,
      "num_input_tokens_seen": 22118697984,
      "step": 77770,
      "train_runtime": 757479.6418,
      "train_tokens_per_second": 29200.386
    },
    {
      "epoch": 2.752009588529147,
      "grad_norm": 1.625,
      "learning_rate": 1.687620102176059e-05,
      "loss": 1.024642562866211,
      "num_input_tokens_seen": 22121535360,
      "step": 77780,
      "train_runtime": 757577.1028,
      "train_tokens_per_second": 29200.375
    },
    {
      "epoch": 2.752363408792876,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6875239814682313e-05,
      "loss": 1.0370899200439454,
      "num_input_tokens_seen": 22124367936,
      "step": 77790,
      "train_runtime": 757675.1454,
      "train_tokens_per_second": 29200.335
    },
    {
      "epoch": 2.7527172290566044,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6874278771825917e-05,
      "loss": 1.0465311050415038,
      "num_input_tokens_seen": 22127225408,
      "step": 77800,
      "train_runtime": 757773.9767,
      "train_tokens_per_second": 29200.297
    },
    {
      "epoch": 2.7530710493203334,
      "grad_norm": 1.5625,
      "learning_rate": 1.6873317893144635e-05,
      "loss": 1.0439983367919923,
      "num_input_tokens_seen": 22130098176,
      "step": 77810,
      "train_runtime": 757875.564,
      "train_tokens_per_second": 29200.174
    },
    {
      "epoch": 2.7534248695840624,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6872357178591744e-05,
      "loss": 1.0354196548461914,
      "num_input_tokens_seen": 22132897664,
      "step": 77820,
      "train_runtime": 757968.2652,
      "train_tokens_per_second": 29200.296
    },
    {
      "epoch": 2.753778689847791,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6871396628120516e-05,
      "loss": 1.040496253967285,
      "num_input_tokens_seen": 22135731520,
      "step": 77830,
      "train_runtime": 758067.5578,
      "train_tokens_per_second": 29200.21
    },
    {
      "epoch": 2.7541325101115195,
      "grad_norm": 1.671875,
      "learning_rate": 1.6870436241684255e-05,
      "loss": 1.0316450119018554,
      "num_input_tokens_seen": 22138625280,
      "step": 77840,
      "train_runtime": 758167.172,
      "train_tokens_per_second": 29200.19
    },
    {
      "epoch": 2.7544863303752485,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6869476019236267e-05,
      "loss": 1.04425048828125,
      "num_input_tokens_seen": 22141391040,
      "step": 77850,
      "train_runtime": 758261.2229,
      "train_tokens_per_second": 29200.215
    },
    {
      "epoch": 2.7548401506389775,
      "grad_norm": 1.5234375,
      "learning_rate": 1.6868515960729903e-05,
      "loss": 1.0301612854003905,
      "num_input_tokens_seen": 22144226176,
      "step": 77860,
      "train_runtime": 758355.8439,
      "train_tokens_per_second": 29200.311
    },
    {
      "epoch": 2.755193970902706,
      "grad_norm": 1.5625,
      "learning_rate": 1.686755606611851e-05,
      "loss": 1.0335573196411132,
      "num_input_tokens_seen": 22147074304,
      "step": 77870,
      "train_runtime": 758450.6357,
      "train_tokens_per_second": 29200.416
    },
    {
      "epoch": 2.755547791166435,
      "grad_norm": 1.625,
      "learning_rate": 1.6866596335355463e-05,
      "loss": 1.0312722206115723,
      "num_input_tokens_seen": 22149905152,
      "step": 77880,
      "train_runtime": 758547.4021,
      "train_tokens_per_second": 29200.423
    },
    {
      "epoch": 2.7559016114301635,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6865636768394156e-05,
      "loss": 1.0460906028747559,
      "num_input_tokens_seen": 22152753536,
      "step": 77890,
      "train_runtime": 758645.2846,
      "train_tokens_per_second": 29200.41
    },
    {
      "epoch": 2.7562554316938925,
      "grad_norm": 1.640625,
      "learning_rate": 1.6864677365187998e-05,
      "loss": 1.0282997131347655,
      "num_input_tokens_seen": 22155593856,
      "step": 77900,
      "train_runtime": 758742.4448,
      "train_tokens_per_second": 29200.414
    },
    {
      "epoch": 2.756609251957621,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6863718125690418e-05,
      "loss": 1.040975284576416,
      "num_input_tokens_seen": 22158424960,
      "step": 77910,
      "train_runtime": 758837.833,
      "train_tokens_per_second": 29200.475
    },
    {
      "epoch": 2.75696307222135,
      "grad_norm": 1.671875,
      "learning_rate": 1.686275904985486e-05,
      "loss": 1.0217095375061036,
      "num_input_tokens_seen": 22161254208,
      "step": 77920,
      "train_runtime": 758935.1302,
      "train_tokens_per_second": 29200.459
    },
    {
      "epoch": 2.7573168924850786,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6861800137634795e-05,
      "loss": 1.0400981903076172,
      "num_input_tokens_seen": 22164182720,
      "step": 77930,
      "train_runtime": 759037.6816,
      "train_tokens_per_second": 29200.372
    },
    {
      "epoch": 2.7576707127488076,
      "grad_norm": 1.6796875,
      "learning_rate": 1.6860841388983708e-05,
      "loss": 1.0293962478637695,
      "num_input_tokens_seen": 22167008064,
      "step": 77940,
      "train_runtime": 759132.283,
      "train_tokens_per_second": 29200.455
    },
    {
      "epoch": 2.758024533012536,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6859882803855102e-05,
      "loss": 1.04813232421875,
      "num_input_tokens_seen": 22169825856,
      "step": 77950,
      "train_runtime": 759226.5107,
      "train_tokens_per_second": 29200.542
    },
    {
      "epoch": 2.758378353276265,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6858924382202497e-05,
      "loss": 1.0265396118164063,
      "num_input_tokens_seen": 22172692160,
      "step": 77960,
      "train_runtime": 759325.3136,
      "train_tokens_per_second": 29200.518
    },
    {
      "epoch": 2.758732173539994,
      "grad_norm": 1.609375,
      "learning_rate": 1.6857966123979434e-05,
      "loss": 1.0341054916381835,
      "num_input_tokens_seen": 22175520448,
      "step": 77970,
      "train_runtime": 759421.2432,
      "train_tokens_per_second": 29200.553
    },
    {
      "epoch": 2.7590859938037227,
      "grad_norm": 1.5703125,
      "learning_rate": 1.685700802913947e-05,
      "loss": 1.0466272354125976,
      "num_input_tokens_seen": 22178426944,
      "step": 77980,
      "train_runtime": 759520.4564,
      "train_tokens_per_second": 29200.566
    },
    {
      "epoch": 2.759439814067451,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6856050097636186e-05,
      "loss": 1.057492446899414,
      "num_input_tokens_seen": 22181314688,
      "step": 77990,
      "train_runtime": 759622.5106,
      "train_tokens_per_second": 29200.444
    },
    {
      "epoch": 2.75979363433118,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6855092329423174e-05,
      "loss": 1.0317235946655274,
      "num_input_tokens_seen": 22184108224,
      "step": 78000,
      "train_runtime": 759714.1784,
      "train_tokens_per_second": 29200.598
    },
    {
      "epoch": 2.760147454594909,
      "grad_norm": 1.578125,
      "learning_rate": 1.685413472445405e-05,
      "loss": 1.0371011734008788,
      "num_input_tokens_seen": 22186936768,
      "step": 78010,
      "train_runtime": 759810.803,
      "train_tokens_per_second": 29200.607
    },
    {
      "epoch": 2.7605012748586377,
      "grad_norm": 1.625,
      "learning_rate": 1.685317728268245e-05,
      "loss": 1.0319923400878905,
      "num_input_tokens_seen": 22189785280,
      "step": 78020,
      "train_runtime": 759911.5652,
      "train_tokens_per_second": 29200.484
    },
    {
      "epoch": 2.7608550951223663,
      "grad_norm": 1.6328125,
      "learning_rate": 1.685222000406202e-05,
      "loss": 1.0465873718261718,
      "num_input_tokens_seen": 22192593792,
      "step": 78030,
      "train_runtime": 760008.0103,
      "train_tokens_per_second": 29200.474
    },
    {
      "epoch": 2.7612089153860953,
      "grad_norm": 1.5078125,
      "learning_rate": 1.685126288854643e-05,
      "loss": 1.0314863204956055,
      "num_input_tokens_seen": 22195471872,
      "step": 78040,
      "train_runtime": 760106.9698,
      "train_tokens_per_second": 29200.458
    },
    {
      "epoch": 2.7615627356498242,
      "grad_norm": 1.59375,
      "learning_rate": 1.6850305936089365e-05,
      "loss": 1.0279099464416503,
      "num_input_tokens_seen": 22198294656,
      "step": 78050,
      "train_runtime": 760202.0147,
      "train_tokens_per_second": 29200.521
    },
    {
      "epoch": 2.761916555913553,
      "grad_norm": 1.578125,
      "learning_rate": 1.6849349146644543e-05,
      "loss": 1.0338947296142578,
      "num_input_tokens_seen": 22201098240,
      "step": 78060,
      "train_runtime": 760297.5686,
      "train_tokens_per_second": 29200.538
    },
    {
      "epoch": 2.7622703761772818,
      "grad_norm": 1.59375,
      "learning_rate": 1.6848392520165675e-05,
      "loss": 1.0385046005249023,
      "num_input_tokens_seen": 22203973952,
      "step": 78070,
      "train_runtime": 760395.7484,
      "train_tokens_per_second": 29200.55
    },
    {
      "epoch": 2.7626241964410103,
      "grad_norm": 1.5859375,
      "learning_rate": 1.684743605660651e-05,
      "loss": 1.0270936965942383,
      "num_input_tokens_seen": 22206807104,
      "step": 78080,
      "train_runtime": 760497.4225,
      "train_tokens_per_second": 29200.371
    },
    {
      "epoch": 2.7629780167047393,
      "grad_norm": 1.640625,
      "learning_rate": 1.684647975592081e-05,
      "loss": 1.0257631301879884,
      "num_input_tokens_seen": 22209710528,
      "step": 78090,
      "train_runtime": 760595.5912,
      "train_tokens_per_second": 29200.42
    },
    {
      "epoch": 2.763331836968468,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6845523618062353e-05,
      "loss": 1.0324773788452148,
      "num_input_tokens_seen": 22212573568,
      "step": 78100,
      "train_runtime": 760693.2745,
      "train_tokens_per_second": 29200.434
    },
    {
      "epoch": 2.763685657232197,
      "grad_norm": 1.609375,
      "learning_rate": 1.684456764298494e-05,
      "loss": 1.0421674728393555,
      "num_input_tokens_seen": 22215399360,
      "step": 78110,
      "train_runtime": 760790.0075,
      "train_tokens_per_second": 29200.435
    },
    {
      "epoch": 2.7640394774959254,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6843611830642385e-05,
      "loss": 1.025580596923828,
      "num_input_tokens_seen": 22218234368,
      "step": 78120,
      "train_runtime": 760887.0516,
      "train_tokens_per_second": 29200.437
    },
    {
      "epoch": 2.7643932977596544,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6842656180988522e-05,
      "loss": 1.0471729278564452,
      "num_input_tokens_seen": 22221042496,
      "step": 78130,
      "train_runtime": 760983.5764,
      "train_tokens_per_second": 29200.423
    },
    {
      "epoch": 2.764747118023383,
      "grad_norm": 1.609375,
      "learning_rate": 1.6841700693977213e-05,
      "loss": 1.0397962570190429,
      "num_input_tokens_seen": 22223843904,
      "step": 78140,
      "train_runtime": 761078.2509,
      "train_tokens_per_second": 29200.472
    },
    {
      "epoch": 2.765100938287112,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6840745369562314e-05,
      "loss": 1.0255697250366211,
      "num_input_tokens_seen": 22226673472,
      "step": 78150,
      "train_runtime": 761172.9123,
      "train_tokens_per_second": 29200.558
    },
    {
      "epoch": 2.765454758550841,
      "grad_norm": 1.609375,
      "learning_rate": 1.6839790207697727e-05,
      "loss": 1.0177677154541016,
      "num_input_tokens_seen": 22229570880,
      "step": 78160,
      "train_runtime": 761273.0832,
      "train_tokens_per_second": 29200.521
    },
    {
      "epoch": 2.7658085788145694,
      "grad_norm": 1.53125,
      "learning_rate": 1.6838835208337357e-05,
      "loss": 1.034083938598633,
      "num_input_tokens_seen": 22232420608,
      "step": 78170,
      "train_runtime": 761369.3756,
      "train_tokens_per_second": 29200.571
    },
    {
      "epoch": 2.766162399078298,
      "grad_norm": 1.640625,
      "learning_rate": 1.6837880371435127e-05,
      "loss": 1.0238880157470702,
      "num_input_tokens_seen": 22235267136,
      "step": 78180,
      "train_runtime": 761467.8782,
      "train_tokens_per_second": 29200.532
    },
    {
      "epoch": 2.766516219342027,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6836925696944987e-05,
      "loss": 1.0508018493652345,
      "num_input_tokens_seen": 22238079104,
      "step": 78190,
      "train_runtime": 761562.7354,
      "train_tokens_per_second": 29200.587
    },
    {
      "epoch": 2.766870039605756,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6835971184820895e-05,
      "loss": 1.0402687072753907,
      "num_input_tokens_seen": 22240920832,
      "step": 78200,
      "train_runtime": 761658.4597,
      "train_tokens_per_second": 29200.648
    },
    {
      "epoch": 2.7672238598694845,
      "grad_norm": 1.671875,
      "learning_rate": 1.6835016835016834e-05,
      "loss": 1.0383331298828125,
      "num_input_tokens_seen": 22243733824,
      "step": 78210,
      "train_runtime": 761753.8143,
      "train_tokens_per_second": 29200.686
    },
    {
      "epoch": 2.7675776801332135,
      "grad_norm": 1.5859375,
      "learning_rate": 1.683406264748681e-05,
      "loss": 1.028543186187744,
      "num_input_tokens_seen": 22246553728,
      "step": 78220,
      "train_runtime": 761848.1517,
      "train_tokens_per_second": 29200.771
    },
    {
      "epoch": 2.767931500396942,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6833108622184828e-05,
      "loss": 1.056753158569336,
      "num_input_tokens_seen": 22249420352,
      "step": 78230,
      "train_runtime": 761948.9455,
      "train_tokens_per_second": 29200.671
    },
    {
      "epoch": 2.768285320660671,
      "grad_norm": 1.625,
      "learning_rate": 1.6832154759064936e-05,
      "loss": 1.045571517944336,
      "num_input_tokens_seen": 22252240832,
      "step": 78240,
      "train_runtime": 762045.1599,
      "train_tokens_per_second": 29200.685
    },
    {
      "epoch": 2.7686391409243996,
      "grad_norm": 1.71875,
      "learning_rate": 1.6831201058081183e-05,
      "loss": 1.0426578521728516,
      "num_input_tokens_seen": 22255082176,
      "step": 78250,
      "train_runtime": 762140.944,
      "train_tokens_per_second": 29200.743
    },
    {
      "epoch": 2.7689929611881285,
      "grad_norm": 1.5625,
      "learning_rate": 1.6830247519187638e-05,
      "loss": 1.0339637756347657,
      "num_input_tokens_seen": 22257962304,
      "step": 78260,
      "train_runtime": 762239.9919,
      "train_tokens_per_second": 29200.728
    },
    {
      "epoch": 2.769346781451857,
      "grad_norm": 1.65625,
      "learning_rate": 1.68292941423384e-05,
      "loss": 1.0424501419067382,
      "num_input_tokens_seen": 22260806144,
      "step": 78270,
      "train_runtime": 762338.8324,
      "train_tokens_per_second": 29200.672
    },
    {
      "epoch": 2.769700601715586,
      "grad_norm": 1.6015625,
      "learning_rate": 1.682834092748757e-05,
      "loss": 1.0182760238647461,
      "num_input_tokens_seen": 22263636032,
      "step": 78280,
      "train_runtime": 762434.9717,
      "train_tokens_per_second": 29200.702
    },
    {
      "epoch": 2.7700544219793146,
      "grad_norm": 1.5703125,
      "learning_rate": 1.682738787458928e-05,
      "loss": 1.0279247283935546,
      "num_input_tokens_seen": 22266491520,
      "step": 78290,
      "train_runtime": 762531.8361,
      "train_tokens_per_second": 29200.737
    },
    {
      "epoch": 2.7704082422430436,
      "grad_norm": 1.609375,
      "learning_rate": 1.6826434983597672e-05,
      "loss": 1.0421895027160644,
      "num_input_tokens_seen": 22269292672,
      "step": 78300,
      "train_runtime": 762625.174,
      "train_tokens_per_second": 29200.836
    },
    {
      "epoch": 2.7707620625067726,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6825482254466916e-05,
      "loss": 1.0415054321289063,
      "num_input_tokens_seen": 22272114496,
      "step": 78310,
      "train_runtime": 762721.7945,
      "train_tokens_per_second": 29200.837
    },
    {
      "epoch": 2.771115882770501,
      "grad_norm": 1.609375,
      "learning_rate": 1.6824529687151183e-05,
      "loss": 1.0404348373413086,
      "num_input_tokens_seen": 22274962176,
      "step": 78320,
      "train_runtime": 762819.4189,
      "train_tokens_per_second": 29200.833
    },
    {
      "epoch": 2.7714697030342297,
      "grad_norm": 1.578125,
      "learning_rate": 1.682357728160468e-05,
      "loss": 1.0567041397094727,
      "num_input_tokens_seen": 22277834496,
      "step": 78330,
      "train_runtime": 762919.1317,
      "train_tokens_per_second": 29200.781
    },
    {
      "epoch": 2.7718235232979587,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6822625037781626e-05,
      "loss": 1.045063591003418,
      "num_input_tokens_seen": 22280728768,
      "step": 78340,
      "train_runtime": 763019.4845,
      "train_tokens_per_second": 29200.734
    },
    {
      "epoch": 2.7721773435616877,
      "grad_norm": 1.53125,
      "learning_rate": 1.6821672955636254e-05,
      "loss": 1.0316388130187988,
      "num_input_tokens_seen": 22283664064,
      "step": 78350,
      "train_runtime": 763123.7184,
      "train_tokens_per_second": 29200.592
    },
    {
      "epoch": 2.772531163825416,
      "grad_norm": 1.625,
      "learning_rate": 1.6820721035122815e-05,
      "loss": 1.0297891616821289,
      "num_input_tokens_seen": 22286453632,
      "step": 78360,
      "train_runtime": 763215.5521,
      "train_tokens_per_second": 29200.733
    },
    {
      "epoch": 2.7728849840891447,
      "grad_norm": 1.59375,
      "learning_rate": 1.6819769276195584e-05,
      "loss": 1.0312591552734376,
      "num_input_tokens_seen": 22289323072,
      "step": 78370,
      "train_runtime": 763313.5241,
      "train_tokens_per_second": 29200.744
    },
    {
      "epoch": 2.7732388043528737,
      "grad_norm": 1.578125,
      "learning_rate": 1.6818817678808855e-05,
      "loss": 1.0421823501586913,
      "num_input_tokens_seen": 22292172864,
      "step": 78380,
      "train_runtime": 763409.7858,
      "train_tokens_per_second": 29200.795
    },
    {
      "epoch": 2.7735926246166027,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6817866242916934e-05,
      "loss": 1.0434464454650878,
      "num_input_tokens_seen": 22295007808,
      "step": 78390,
      "train_runtime": 763507.0593,
      "train_tokens_per_second": 29200.788
    },
    {
      "epoch": 2.7739464448803313,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6816914968474148e-05,
      "loss": 1.03793306350708,
      "num_input_tokens_seen": 22297791168,
      "step": 78400,
      "train_runtime": 763599.8369,
      "train_tokens_per_second": 29200.885
    },
    {
      "epoch": 2.7743002651440603,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6815963855434838e-05,
      "loss": 1.0423437118530274,
      "num_input_tokens_seen": 22300622016,
      "step": 78410,
      "train_runtime": 763694.9987,
      "train_tokens_per_second": 29200.953
    },
    {
      "epoch": 2.774654085407789,
      "grad_norm": 1.6796875,
      "learning_rate": 1.681501290375337e-05,
      "loss": 1.0273399353027344,
      "num_input_tokens_seen": 22303400320,
      "step": 78420,
      "train_runtime": 763787.9508,
      "train_tokens_per_second": 29201.037
    },
    {
      "epoch": 2.775007905671518,
      "grad_norm": 1.546875,
      "learning_rate": 1.6814062113384127e-05,
      "loss": 1.0374479293823242,
      "num_input_tokens_seen": 22306210880,
      "step": 78430,
      "train_runtime": 763884.6273,
      "train_tokens_per_second": 29201.021
    },
    {
      "epoch": 2.7753617259352463,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6813111484281506e-05,
      "loss": 1.042191982269287,
      "num_input_tokens_seen": 22309084032,
      "step": 78440,
      "train_runtime": 763987.5244,
      "train_tokens_per_second": 29200.849
    },
    {
      "epoch": 2.7757155461989753,
      "grad_norm": 1.59375,
      "learning_rate": 1.6812161016399918e-05,
      "loss": 1.0244480133056642,
      "num_input_tokens_seen": 22311947648,
      "step": 78450,
      "train_runtime": 764087.5827,
      "train_tokens_per_second": 29200.772
    },
    {
      "epoch": 2.7760693664627043,
      "grad_norm": 1.6171875,
      "learning_rate": 1.681121070969381e-05,
      "loss": 1.0299898147583009,
      "num_input_tokens_seen": 22314863168,
      "step": 78460,
      "train_runtime": 764188.8169,
      "train_tokens_per_second": 29200.719
    },
    {
      "epoch": 2.776423186726433,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6810260564117625e-05,
      "loss": 1.0283088684082031,
      "num_input_tokens_seen": 22317715904,
      "step": 78470,
      "train_runtime": 764288.616,
      "train_tokens_per_second": 29200.639
    },
    {
      "epoch": 2.7767770069901614,
      "grad_norm": 1.6796875,
      "learning_rate": 1.6809310579625838e-05,
      "loss": 1.0412121772766114,
      "num_input_tokens_seen": 22320463168,
      "step": 78480,
      "train_runtime": 764380.9968,
      "train_tokens_per_second": 29200.704
    },
    {
      "epoch": 2.7771308272538904,
      "grad_norm": 1.5859375,
      "learning_rate": 1.680836075617293e-05,
      "loss": 1.0414365768432616,
      "num_input_tokens_seen": 22323344384,
      "step": 78490,
      "train_runtime": 764480.6657,
      "train_tokens_per_second": 29200.666
    },
    {
      "epoch": 2.7774846475176194,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6807411093713423e-05,
      "loss": 1.0258904457092286,
      "num_input_tokens_seen": 22326178176,
      "step": 78500,
      "train_runtime": 764579.5866,
      "train_tokens_per_second": 29200.594
    },
    {
      "epoch": 2.777838467781348,
      "grad_norm": 1.59375,
      "learning_rate": 1.6806461592201837e-05,
      "loss": 1.0158932685852051,
      "num_input_tokens_seen": 22329054592,
      "step": 78510,
      "train_runtime": 764680.0089,
      "train_tokens_per_second": 29200.521
    },
    {
      "epoch": 2.7781922880450765,
      "grad_norm": 1.671875,
      "learning_rate": 1.6805512251592702e-05,
      "loss": 1.0426855087280273,
      "num_input_tokens_seen": 22331912768,
      "step": 78520,
      "train_runtime": 764778.8492,
      "train_tokens_per_second": 29200.484
    },
    {
      "epoch": 2.7785461083088054,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6804563071840595e-05,
      "loss": 1.027762508392334,
      "num_input_tokens_seen": 22334710336,
      "step": 78530,
      "train_runtime": 764874.4049,
      "train_tokens_per_second": 29200.494
    },
    {
      "epoch": 2.7788999285725344,
      "grad_norm": 1.6484375,
      "learning_rate": 1.680361405290009e-05,
      "loss": 1.0424509048461914,
      "num_input_tokens_seen": 22337572160,
      "step": 78540,
      "train_runtime": 764972.9259,
      "train_tokens_per_second": 29200.474
    },
    {
      "epoch": 2.779253748836263,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6802665194725778e-05,
      "loss": 1.0509458541870118,
      "num_input_tokens_seen": 22340434496,
      "step": 78550,
      "train_runtime": 765069.7464,
      "train_tokens_per_second": 29200.52
    },
    {
      "epoch": 2.779607569099992,
      "grad_norm": 1.578125,
      "learning_rate": 1.6801716497272283e-05,
      "loss": 1.0310098648071289,
      "num_input_tokens_seen": 22343290432,
      "step": 78560,
      "train_runtime": 765166.1589,
      "train_tokens_per_second": 29200.573
    },
    {
      "epoch": 2.7799613893637205,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6800767960494234e-05,
      "loss": 1.0226579666137696,
      "num_input_tokens_seen": 22346138368,
      "step": 78570,
      "train_runtime": 765262.3869,
      "train_tokens_per_second": 29200.623
    },
    {
      "epoch": 2.7803152096274495,
      "grad_norm": 1.59375,
      "learning_rate": 1.6799819584346275e-05,
      "loss": 1.0368896484375,
      "num_input_tokens_seen": 22348997440,
      "step": 78580,
      "train_runtime": 765358.4431,
      "train_tokens_per_second": 29200.694
    },
    {
      "epoch": 2.780669029891178,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6798871368783085e-05,
      "loss": 1.032035732269287,
      "num_input_tokens_seen": 22351825024,
      "step": 78590,
      "train_runtime": 765453.1556,
      "train_tokens_per_second": 29200.775
    },
    {
      "epoch": 2.781022850154907,
      "grad_norm": 1.578125,
      "learning_rate": 1.6797923313759344e-05,
      "loss": 1.0324738502502442,
      "num_input_tokens_seen": 22354714048,
      "step": 78600,
      "train_runtime": 765552.4537,
      "train_tokens_per_second": 29200.761
    },
    {
      "epoch": 2.7813766704186356,
      "grad_norm": 1.5703125,
      "learning_rate": 1.679697541922976e-05,
      "loss": 1.0181628227233888,
      "num_input_tokens_seen": 22357579840,
      "step": 78610,
      "train_runtime": 765651.9125,
      "train_tokens_per_second": 29200.711
    },
    {
      "epoch": 2.7817304906823646,
      "grad_norm": 1.609375,
      "learning_rate": 1.679602768514905e-05,
      "loss": 1.0437126159667969,
      "num_input_tokens_seen": 22360363328,
      "step": 78620,
      "train_runtime": 765746.1006,
      "train_tokens_per_second": 29200.754
    },
    {
      "epoch": 2.782084310946093,
      "grad_norm": 1.59375,
      "learning_rate": 1.679508011147196e-05,
      "loss": 1.0406976699829102,
      "num_input_tokens_seen": 22363190912,
      "step": 78630,
      "train_runtime": 765842.049,
      "train_tokens_per_second": 29200.787
    },
    {
      "epoch": 2.782438131209822,
      "grad_norm": 1.59375,
      "learning_rate": 1.679413269815325e-05,
      "loss": 1.036379051208496,
      "num_input_tokens_seen": 22366037632,
      "step": 78640,
      "train_runtime": 765938.3899,
      "train_tokens_per_second": 29200.831
    },
    {
      "epoch": 2.782791951473551,
      "grad_norm": 1.546875,
      "learning_rate": 1.679318544514769e-05,
      "loss": 1.0345842361450195,
      "num_input_tokens_seen": 22368912640,
      "step": 78650,
      "train_runtime": 766037.6452,
      "train_tokens_per_second": 29200.801
    },
    {
      "epoch": 2.7831457717372796,
      "grad_norm": 1.6328125,
      "learning_rate": 1.679223835241007e-05,
      "loss": 1.041607666015625,
      "num_input_tokens_seen": 22371757440,
      "step": 78660,
      "train_runtime": 766134.6748,
      "train_tokens_per_second": 29200.816
    },
    {
      "epoch": 2.783499592001008,
      "grad_norm": 1.6328125,
      "learning_rate": 1.679129141989521e-05,
      "loss": 1.0324914932250977,
      "num_input_tokens_seen": 22374578816,
      "step": 78670,
      "train_runtime": 766230.004,
      "train_tokens_per_second": 29200.865
    },
    {
      "epoch": 2.783853412264737,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6790344647557936e-05,
      "loss": 1.024125862121582,
      "num_input_tokens_seen": 22377440960,
      "step": 78680,
      "train_runtime": 766329.6606,
      "train_tokens_per_second": 29200.802
    },
    {
      "epoch": 2.784207232528466,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6789398035353095e-05,
      "loss": 1.0376310348510742,
      "num_input_tokens_seen": 22380344832,
      "step": 78690,
      "train_runtime": 766429.6488,
      "train_tokens_per_second": 29200.782
    },
    {
      "epoch": 2.7845610527921947,
      "grad_norm": 1.578125,
      "learning_rate": 1.6788451583235557e-05,
      "loss": 1.0235712051391601,
      "num_input_tokens_seen": 22383213120,
      "step": 78700,
      "train_runtime": 766528.1996,
      "train_tokens_per_second": 29200.769
    },
    {
      "epoch": 2.7849148730559237,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6787505291160198e-05,
      "loss": 1.0341009140014648,
      "num_input_tokens_seen": 22386001152,
      "step": 78710,
      "train_runtime": 766619.0003,
      "train_tokens_per_second": 29200.947
    },
    {
      "epoch": 2.785268693319652,
      "grad_norm": 1.59375,
      "learning_rate": 1.6786559159081923e-05,
      "loss": 1.027538013458252,
      "num_input_tokens_seen": 22388851200,
      "step": 78720,
      "train_runtime": 766717.9988,
      "train_tokens_per_second": 29200.894
    },
    {
      "epoch": 2.785622513583381,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6785613186955645e-05,
      "loss": 1.0448867797851562,
      "num_input_tokens_seen": 22391718272,
      "step": 78730,
      "train_runtime": 766816.6326,
      "train_tokens_per_second": 29200.877
    },
    {
      "epoch": 2.7859763338471097,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6784667374736305e-05,
      "loss": 1.0274223327636718,
      "num_input_tokens_seen": 22394603136,
      "step": 78740,
      "train_runtime": 766916.8656,
      "train_tokens_per_second": 29200.822
    },
    {
      "epoch": 2.7863301541108387,
      "grad_norm": 1.5859375,
      "learning_rate": 1.678372172237886e-05,
      "loss": 1.040988826751709,
      "num_input_tokens_seen": 22397408832,
      "step": 78750,
      "train_runtime": 767013.0303,
      "train_tokens_per_second": 29200.819
    },
    {
      "epoch": 2.7866839743745673,
      "grad_norm": 1.7421875,
      "learning_rate": 1.678277622983827e-05,
      "loss": 1.0438885688781738,
      "num_input_tokens_seen": 22400283968,
      "step": 78760,
      "train_runtime": 767113.1525,
      "train_tokens_per_second": 29200.756
    },
    {
      "epoch": 2.7870377946382963,
      "grad_norm": 1.5625,
      "learning_rate": 1.678183089706954e-05,
      "loss": 1.038498306274414,
      "num_input_tokens_seen": 22403159552,
      "step": 78770,
      "train_runtime": 767211.7968,
      "train_tokens_per_second": 29200.75
    },
    {
      "epoch": 2.787391614902025,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6780885724027666e-05,
      "loss": 1.0388550758361816,
      "num_input_tokens_seen": 22405994944,
      "step": 78780,
      "train_runtime": 767310.2212,
      "train_tokens_per_second": 29200.699
    },
    {
      "epoch": 2.787745435165754,
      "grad_norm": 1.625,
      "learning_rate": 1.6779940710667678e-05,
      "loss": 1.0492558479309082,
      "num_input_tokens_seen": 22408906560,
      "step": 78790,
      "train_runtime": 767411.6266,
      "train_tokens_per_second": 29200.635
    },
    {
      "epoch": 2.788099255429483,
      "grad_norm": 1.609375,
      "learning_rate": 1.677899585694461e-05,
      "loss": 1.0364137649536134,
      "num_input_tokens_seen": 22411748224,
      "step": 78800,
      "train_runtime": 767507.7748,
      "train_tokens_per_second": 29200.679
    },
    {
      "epoch": 2.7884530756932113,
      "grad_norm": 1.5703125,
      "learning_rate": 1.677805116281354e-05,
      "loss": 1.034420108795166,
      "num_input_tokens_seen": 22414616128,
      "step": 78810,
      "train_runtime": 767607.7412,
      "train_tokens_per_second": 29200.612
    },
    {
      "epoch": 2.78880689595694,
      "grad_norm": 1.640625,
      "learning_rate": 1.6777106628229533e-05,
      "loss": 1.0425487518310548,
      "num_input_tokens_seen": 22417387840,
      "step": 78820,
      "train_runtime": 767702.0171,
      "train_tokens_per_second": 29200.637
    },
    {
      "epoch": 2.789160716220669,
      "grad_norm": 1.6015625,
      "learning_rate": 1.677616225314769e-05,
      "loss": 1.0390522003173828,
      "num_input_tokens_seen": 22420179392,
      "step": 78830,
      "train_runtime": 767795.9362,
      "train_tokens_per_second": 29200.701
    },
    {
      "epoch": 2.789514536484398,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6775218037523117e-05,
      "loss": 1.0310272216796874,
      "num_input_tokens_seen": 22423023808,
      "step": 78840,
      "train_runtime": 767892.4051,
      "train_tokens_per_second": 29200.737
    },
    {
      "epoch": 2.7898683567481264,
      "grad_norm": 1.625,
      "learning_rate": 1.6774273981310952e-05,
      "loss": 1.0331769943237306,
      "num_input_tokens_seen": 22425856768,
      "step": 78850,
      "train_runtime": 767990.0932,
      "train_tokens_per_second": 29200.711
    },
    {
      "epoch": 2.790222177011855,
      "grad_norm": 1.5625,
      "learning_rate": 1.6773330084466342e-05,
      "loss": 1.0359731674194337,
      "num_input_tokens_seen": 22428683712,
      "step": 78860,
      "train_runtime": 768088.123,
      "train_tokens_per_second": 29200.665
    },
    {
      "epoch": 2.790575997275584,
      "grad_norm": 1.625,
      "learning_rate": 1.6772386346944455e-05,
      "loss": 1.0385757446289063,
      "num_input_tokens_seen": 22431505600,
      "step": 78870,
      "train_runtime": 768183.1599,
      "train_tokens_per_second": 29200.726
    },
    {
      "epoch": 2.790929817539313,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6771442768700477e-05,
      "loss": 1.0342417716979981,
      "num_input_tokens_seen": 22434373568,
      "step": 78880,
      "train_runtime": 768279.8276,
      "train_tokens_per_second": 29200.784
    },
    {
      "epoch": 2.7912836378030415,
      "grad_norm": 1.640625,
      "learning_rate": 1.6770499349689606e-05,
      "loss": 1.0319907188415527,
      "num_input_tokens_seen": 22437308160,
      "step": 78890,
      "train_runtime": 768380.691,
      "train_tokens_per_second": 29200.77
    },
    {
      "epoch": 2.7916374580667704,
      "grad_norm": 1.625,
      "learning_rate": 1.676955608986706e-05,
      "loss": 1.025151538848877,
      "num_input_tokens_seen": 22440142976,
      "step": 78900,
      "train_runtime": 768475.9325,
      "train_tokens_per_second": 29200.84
    },
    {
      "epoch": 2.791991278330499,
      "grad_norm": 1.59375,
      "learning_rate": 1.676861298918808e-05,
      "loss": 1.0387285232543946,
      "num_input_tokens_seen": 22442945728,
      "step": 78910,
      "train_runtime": 768570.6319,
      "train_tokens_per_second": 29200.889
    },
    {
      "epoch": 2.792345098594228,
      "grad_norm": 1.546875,
      "learning_rate": 1.6767670047607924e-05,
      "loss": 1.0349979400634766,
      "num_input_tokens_seen": 22445788992,
      "step": 78920,
      "train_runtime": 768668.7382,
      "train_tokens_per_second": 29200.861
    },
    {
      "epoch": 2.7926989188579565,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6766727265081858e-05,
      "loss": 1.0273520469665527,
      "num_input_tokens_seen": 22448639232,
      "step": 78930,
      "train_runtime": 768767.3205,
      "train_tokens_per_second": 29200.824
    },
    {
      "epoch": 2.7930527391216855,
      "grad_norm": 1.625,
      "learning_rate": 1.676578464156517e-05,
      "loss": 1.0417093276977538,
      "num_input_tokens_seen": 22451453376,
      "step": 78940,
      "train_runtime": 768863.3193,
      "train_tokens_per_second": 29200.838
    },
    {
      "epoch": 2.793406559385414,
      "grad_norm": 1.625,
      "learning_rate": 1.6764842177013176e-05,
      "loss": 1.034782886505127,
      "num_input_tokens_seen": 22454338048,
      "step": 78950,
      "train_runtime": 768964.8239,
      "train_tokens_per_second": 29200.735
    },
    {
      "epoch": 2.793760379649143,
      "grad_norm": 1.5546875,
      "learning_rate": 1.67638998713812e-05,
      "loss": 1.0416025161743163,
      "num_input_tokens_seen": 22457192384,
      "step": 78960,
      "train_runtime": 769060.5437,
      "train_tokens_per_second": 29200.812
    },
    {
      "epoch": 2.7941141999128716,
      "grad_norm": 1.609375,
      "learning_rate": 1.676295772462457e-05,
      "loss": 1.0250621795654298,
      "num_input_tokens_seen": 22460072896,
      "step": 78970,
      "train_runtime": 769162.2442,
      "train_tokens_per_second": 29200.696
    },
    {
      "epoch": 2.7944680201766006,
      "grad_norm": 1.609375,
      "learning_rate": 1.6762015736698667e-05,
      "loss": 1.0459904670715332,
      "num_input_tokens_seen": 22462947456,
      "step": 78980,
      "train_runtime": 769262.9762,
      "train_tokens_per_second": 29200.609
    },
    {
      "epoch": 2.7948218404403296,
      "grad_norm": 1.578125,
      "learning_rate": 1.676107390755886e-05,
      "loss": 1.0297903060913085,
      "num_input_tokens_seen": 22465819968,
      "step": 78990,
      "train_runtime": 769363.2508,
      "train_tokens_per_second": 29200.537
    },
    {
      "epoch": 2.795175660704058,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6760132237160538e-05,
      "loss": 1.0294001579284668,
      "num_input_tokens_seen": 22468670784,
      "step": 79000,
      "train_runtime": 769459.5651,
      "train_tokens_per_second": 29200.587
    },
    {
      "epoch": 2.7955294809677866,
      "grad_norm": 1.625,
      "learning_rate": 1.6759190725459125e-05,
      "loss": 1.0272762298583984,
      "num_input_tokens_seen": 22471500608,
      "step": 79010,
      "train_runtime": 769557.2681,
      "train_tokens_per_second": 29200.557
    },
    {
      "epoch": 2.7958833012315156,
      "grad_norm": 1.6796875,
      "learning_rate": 1.675824937241005e-05,
      "loss": 1.0256433486938477,
      "num_input_tokens_seen": 22474348096,
      "step": 79020,
      "train_runtime": 769655.3504,
      "train_tokens_per_second": 29200.535
    },
    {
      "epoch": 2.7962371214952446,
      "grad_norm": 1.59375,
      "learning_rate": 1.675730817796875e-05,
      "loss": 1.0421129226684571,
      "num_input_tokens_seen": 22477195520,
      "step": 79030,
      "train_runtime": 769751.528,
      "train_tokens_per_second": 29200.586
    },
    {
      "epoch": 2.796590941758973,
      "grad_norm": 1.5703125,
      "learning_rate": 1.67563671420907e-05,
      "loss": 1.0367191314697266,
      "num_input_tokens_seen": 22480027648,
      "step": 79040,
      "train_runtime": 769848.6608,
      "train_tokens_per_second": 29200.58
    },
    {
      "epoch": 2.796944762022702,
      "grad_norm": 1.59375,
      "learning_rate": 1.6755426264731383e-05,
      "loss": 1.0395885467529298,
      "num_input_tokens_seen": 22482931776,
      "step": 79050,
      "train_runtime": 769948.6356,
      "train_tokens_per_second": 29200.561
    },
    {
      "epoch": 2.7972985822864307,
      "grad_norm": 1.640625,
      "learning_rate": 1.6754485545846296e-05,
      "loss": 1.029010009765625,
      "num_input_tokens_seen": 22485762688,
      "step": 79060,
      "train_runtime": 770045.6867,
      "train_tokens_per_second": 29200.557
    },
    {
      "epoch": 2.7976524025501597,
      "grad_norm": 1.5625,
      "learning_rate": 1.675354498539096e-05,
      "loss": 1.033984661102295,
      "num_input_tokens_seen": 22488650496,
      "step": 79070,
      "train_runtime": 770143.8171,
      "train_tokens_per_second": 29200.586
    },
    {
      "epoch": 2.798006222813888,
      "grad_norm": 1.6796875,
      "learning_rate": 1.675260458332091e-05,
      "loss": 1.0408400535583495,
      "num_input_tokens_seen": 22491476864,
      "step": 79080,
      "train_runtime": 770242.4786,
      "train_tokens_per_second": 29200.515
    },
    {
      "epoch": 2.798360043077617,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6751664339591696e-05,
      "loss": 1.0310531616210938,
      "num_input_tokens_seen": 22494350720,
      "step": 79090,
      "train_runtime": 770343.8139,
      "train_tokens_per_second": 29200.404
    },
    {
      "epoch": 2.7987138633413458,
      "grad_norm": 1.578125,
      "learning_rate": 1.6750724254158888e-05,
      "loss": 1.031711483001709,
      "num_input_tokens_seen": 22497189248,
      "step": 79100,
      "train_runtime": 770441.4164,
      "train_tokens_per_second": 29200.389
    },
    {
      "epoch": 2.7990676836050747,
      "grad_norm": 1.5859375,
      "learning_rate": 1.674978432697808e-05,
      "loss": 1.0335887908935546,
      "num_input_tokens_seen": 22500000512,
      "step": 79110,
      "train_runtime": 770536.6314,
      "train_tokens_per_second": 29200.429
    },
    {
      "epoch": 2.7994215038688033,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6748844558004877e-05,
      "loss": 1.0389722824096679,
      "num_input_tokens_seen": 22502837696,
      "step": 79120,
      "train_runtime": 770632.8517,
      "train_tokens_per_second": 29200.465
    },
    {
      "epoch": 2.7997753241325323,
      "grad_norm": 1.625,
      "learning_rate": 1.6747904947194892e-05,
      "loss": 1.0459507942199706,
      "num_input_tokens_seen": 22505659008,
      "step": 79130,
      "train_runtime": 770730.5204,
      "train_tokens_per_second": 29200.425
    },
    {
      "epoch": 2.8001291443962613,
      "grad_norm": 1.65625,
      "learning_rate": 1.6746965494503776e-05,
      "loss": 1.0330518722534179,
      "num_input_tokens_seen": 22508518272,
      "step": 79140,
      "train_runtime": 770832.8795,
      "train_tokens_per_second": 29200.257
    },
    {
      "epoch": 2.80048296465999,
      "grad_norm": 1.640625,
      "learning_rate": 1.6746026199887178e-05,
      "loss": 1.021514320373535,
      "num_input_tokens_seen": 22511400896,
      "step": 79150,
      "train_runtime": 770932.6566,
      "train_tokens_per_second": 29200.217
    },
    {
      "epoch": 2.8008367849237183,
      "grad_norm": 1.6875,
      "learning_rate": 1.674508706330078e-05,
      "loss": 1.0297744750976563,
      "num_input_tokens_seen": 22514250368,
      "step": 79160,
      "train_runtime": 771030.0685,
      "train_tokens_per_second": 29200.224
    },
    {
      "epoch": 2.8011906051874473,
      "grad_norm": 1.6015625,
      "learning_rate": 1.674414808470027e-05,
      "loss": 1.0259479522705077,
      "num_input_tokens_seen": 22517091392,
      "step": 79170,
      "train_runtime": 771126.5486,
      "train_tokens_per_second": 29200.254
    },
    {
      "epoch": 2.8015444254511763,
      "grad_norm": 1.625,
      "learning_rate": 1.674320926404136e-05,
      "loss": 1.039177703857422,
      "num_input_tokens_seen": 22519973952,
      "step": 79180,
      "train_runtime": 771228.352,
      "train_tokens_per_second": 29200.138
    },
    {
      "epoch": 2.801898245714905,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6742270601279773e-05,
      "loss": 1.0355941772460937,
      "num_input_tokens_seen": 22522788032,
      "step": 79190,
      "train_runtime": 771323.59,
      "train_tokens_per_second": 29200.18
    },
    {
      "epoch": 2.8022520659786334,
      "grad_norm": 1.5859375,
      "learning_rate": 1.674133209637126e-05,
      "loss": 1.0276732444763184,
      "num_input_tokens_seen": 22525527232,
      "step": 79200,
      "train_runtime": 771416.1694,
      "train_tokens_per_second": 29200.227
    },
    {
      "epoch": 2.8026058862423624,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6740393749271583e-05,
      "loss": 1.0273798942565917,
      "num_input_tokens_seen": 22528348864,
      "step": 79210,
      "train_runtime": 771512.1975,
      "train_tokens_per_second": 29200.25
    },
    {
      "epoch": 2.8029597065060914,
      "grad_norm": 1.59375,
      "learning_rate": 1.6739455559936515e-05,
      "loss": 1.0279330253601073,
      "num_input_tokens_seen": 22531238848,
      "step": 79220,
      "train_runtime": 771613.9657,
      "train_tokens_per_second": 29200.144
    },
    {
      "epoch": 2.80331352676982,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6738517528321858e-05,
      "loss": 1.0308595657348634,
      "num_input_tokens_seen": 22534054976,
      "step": 79230,
      "train_runtime": 771708.0486,
      "train_tokens_per_second": 29200.233
    },
    {
      "epoch": 2.803667347033549,
      "grad_norm": 1.5390625,
      "learning_rate": 1.673757965438342e-05,
      "loss": 1.038060188293457,
      "num_input_tokens_seen": 22536885504,
      "step": 79240,
      "train_runtime": 771802.9332,
      "train_tokens_per_second": 29200.311
    },
    {
      "epoch": 2.8040211672972775,
      "grad_norm": 1.609375,
      "learning_rate": 1.6736641938077036e-05,
      "loss": 1.0232739448547363,
      "num_input_tokens_seen": 22539703424,
      "step": 79250,
      "train_runtime": 771899.7107,
      "train_tokens_per_second": 29200.3
    },
    {
      "epoch": 2.8043749875610064,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6735704379358556e-05,
      "loss": 1.0274675369262696,
      "num_input_tokens_seen": 22542576768,
      "step": 79260,
      "train_runtime": 771997.4157,
      "train_tokens_per_second": 29200.327
    },
    {
      "epoch": 2.804728807824735,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6734766978183844e-05,
      "loss": 1.0376950263977052,
      "num_input_tokens_seen": 22545414400,
      "step": 79270,
      "train_runtime": 772095.3964,
      "train_tokens_per_second": 29200.296
    },
    {
      "epoch": 2.805082628088464,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6733829734508786e-05,
      "loss": 1.0474204063415526,
      "num_input_tokens_seen": 22548244032,
      "step": 79280,
      "train_runtime": 772190.2691,
      "train_tokens_per_second": 29200.373
    },
    {
      "epoch": 2.8054364483521925,
      "grad_norm": 1.5625,
      "learning_rate": 1.6732892648289272e-05,
      "loss": 1.0465702056884765,
      "num_input_tokens_seen": 22551078080,
      "step": 79290,
      "train_runtime": 772286.5298,
      "train_tokens_per_second": 29200.403
    },
    {
      "epoch": 2.8057902686159215,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6731955719481236e-05,
      "loss": 1.0349903106689453,
      "num_input_tokens_seen": 22553890176,
      "step": 79300,
      "train_runtime": 772380.4965,
      "train_tokens_per_second": 29200.492
    },
    {
      "epoch": 2.80614408887965,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6731018948040602e-05,
      "loss": 1.0348207473754882,
      "num_input_tokens_seen": 22556735360,
      "step": 79310,
      "train_runtime": 772478.8663,
      "train_tokens_per_second": 29200.456
    },
    {
      "epoch": 2.806497909143379,
      "grad_norm": 1.609375,
      "learning_rate": 1.6730082333923324e-05,
      "loss": 1.0304140090942382,
      "num_input_tokens_seen": 22559638784,
      "step": 79320,
      "train_runtime": 772581.3229,
      "train_tokens_per_second": 29200.342
    },
    {
      "epoch": 2.806851729407108,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6729145877085377e-05,
      "loss": 1.029456615447998,
      "num_input_tokens_seen": 22562438080,
      "step": 79330,
      "train_runtime": 772675.1437,
      "train_tokens_per_second": 29200.419
    },
    {
      "epoch": 2.8072055496708366,
      "grad_norm": 1.625,
      "learning_rate": 1.6728209577482738e-05,
      "loss": 1.0435773849487304,
      "num_input_tokens_seen": 22565311872,
      "step": 79340,
      "train_runtime": 772772.4287,
      "train_tokens_per_second": 29200.462
    },
    {
      "epoch": 2.807559369934565,
      "grad_norm": 1.625,
      "learning_rate": 1.672727343507142e-05,
      "loss": 1.024774169921875,
      "num_input_tokens_seen": 22568143872,
      "step": 79350,
      "train_runtime": 772869.3907,
      "train_tokens_per_second": 29200.463
    },
    {
      "epoch": 2.807913190198294,
      "grad_norm": 1.6796875,
      "learning_rate": 1.6726337449807442e-05,
      "loss": 1.0179197311401367,
      "num_input_tokens_seen": 22570998912,
      "step": 79360,
      "train_runtime": 772966.1939,
      "train_tokens_per_second": 29200.499
    },
    {
      "epoch": 2.808267010462023,
      "grad_norm": 1.625,
      "learning_rate": 1.6725401621646838e-05,
      "loss": 1.037172222137451,
      "num_input_tokens_seen": 22573867392,
      "step": 79370,
      "train_runtime": 773064.7586,
      "train_tokens_per_second": 29200.487
    },
    {
      "epoch": 2.8086208307257516,
      "grad_norm": 1.625,
      "learning_rate": 1.672446595054567e-05,
      "loss": 1.037921142578125,
      "num_input_tokens_seen": 22576701120,
      "step": 79380,
      "train_runtime": 773161.2511,
      "train_tokens_per_second": 29200.508
    },
    {
      "epoch": 2.8089746509894806,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6723530436460007e-05,
      "loss": 1.0508163452148438,
      "num_input_tokens_seen": 22579582016,
      "step": 79390,
      "train_runtime": 773261.3043,
      "train_tokens_per_second": 29200.455
    },
    {
      "epoch": 2.809328471253209,
      "grad_norm": 1.5,
      "learning_rate": 1.6722595079345938e-05,
      "loss": 1.0305066108703613,
      "num_input_tokens_seen": 22582426944,
      "step": 79400,
      "train_runtime": 773357.5584,
      "train_tokens_per_second": 29200.499
    },
    {
      "epoch": 2.809682291516938,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6721659879159576e-05,
      "loss": 1.0415762901306151,
      "num_input_tokens_seen": 22585227584,
      "step": 79410,
      "train_runtime": 773451.1572,
      "train_tokens_per_second": 29200.587
    },
    {
      "epoch": 2.8100361117806667,
      "grad_norm": 1.6015625,
      "learning_rate": 1.672072483585704e-05,
      "loss": 1.0397422790527344,
      "num_input_tokens_seen": 22588139392,
      "step": 79420,
      "train_runtime": 773551.0842,
      "train_tokens_per_second": 29200.579
    },
    {
      "epoch": 2.8103899320443957,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6719789949394475e-05,
      "loss": 1.033463478088379,
      "num_input_tokens_seen": 22590980032,
      "step": 79430,
      "train_runtime": 773650.7954,
      "train_tokens_per_second": 29200.487
    },
    {
      "epoch": 2.8107437523081242,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6718855219728038e-05,
      "loss": 1.038078498840332,
      "num_input_tokens_seen": 22593824960,
      "step": 79440,
      "train_runtime": 773747.761,
      "train_tokens_per_second": 29200.504
    },
    {
      "epoch": 2.811097572571853,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6717920646813904e-05,
      "loss": 1.0373571395874024,
      "num_input_tokens_seen": 22596675008,
      "step": 79450,
      "train_runtime": 773844.1537,
      "train_tokens_per_second": 29200.55
    },
    {
      "epoch": 2.8114513928355818,
      "grad_norm": 1.640625,
      "learning_rate": 1.671698623060827e-05,
      "loss": 1.0321333885192872,
      "num_input_tokens_seen": 22599531776,
      "step": 79460,
      "train_runtime": 773943.1503,
      "train_tokens_per_second": 29200.506
    },
    {
      "epoch": 2.8118052130993108,
      "grad_norm": 1.671875,
      "learning_rate": 1.6716051971067343e-05,
      "loss": 1.0351702690124511,
      "num_input_tokens_seen": 22602311936,
      "step": 79470,
      "train_runtime": 774036.1573,
      "train_tokens_per_second": 29200.589
    },
    {
      "epoch": 2.8121590333630397,
      "grad_norm": 1.71875,
      "learning_rate": 1.671511786814735e-05,
      "loss": 1.0404480934143066,
      "num_input_tokens_seen": 22605161536,
      "step": 79480,
      "train_runtime": 774135.7743,
      "train_tokens_per_second": 29200.513
    },
    {
      "epoch": 2.8125128536267683,
      "grad_norm": 1.59375,
      "learning_rate": 1.671418392180454e-05,
      "loss": 1.0398025512695312,
      "num_input_tokens_seen": 22608042176,
      "step": 79490,
      "train_runtime": 774237.0329,
      "train_tokens_per_second": 29200.414
    },
    {
      "epoch": 2.812866673890497,
      "grad_norm": 1.6015625,
      "learning_rate": 1.671325013199517e-05,
      "loss": 1.0447395324707032,
      "num_input_tokens_seen": 22610894592,
      "step": 79500,
      "train_runtime": 774333.584,
      "train_tokens_per_second": 29200.457
    },
    {
      "epoch": 2.813220494154226,
      "grad_norm": 1.609375,
      "learning_rate": 1.671231649867552e-05,
      "loss": 1.0558664321899414,
      "num_input_tokens_seen": 22613708032,
      "step": 79510,
      "train_runtime": 774431.412,
      "train_tokens_per_second": 29200.401
    },
    {
      "epoch": 2.813574314417955,
      "grad_norm": 1.578125,
      "learning_rate": 1.671138302180189e-05,
      "loss": 1.0389620780944824,
      "num_input_tokens_seen": 22616538560,
      "step": 79520,
      "train_runtime": 774528.5864,
      "train_tokens_per_second": 29200.392
    },
    {
      "epoch": 2.8139281346816833,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6710449701330584e-05,
      "loss": 1.0267772674560547,
      "num_input_tokens_seen": 22619327744,
      "step": 79530,
      "train_runtime": 774620.4407,
      "train_tokens_per_second": 29200.53
    },
    {
      "epoch": 2.814281954945412,
      "grad_norm": 1.5859375,
      "learning_rate": 1.670951653721794e-05,
      "loss": 1.0322991371154786,
      "num_input_tokens_seen": 22622145408,
      "step": 79540,
      "train_runtime": 774715.6603,
      "train_tokens_per_second": 29200.578
    },
    {
      "epoch": 2.814635775209141,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6708583529420303e-05,
      "loss": 1.0457352638244628,
      "num_input_tokens_seen": 22624937088,
      "step": 79550,
      "train_runtime": 774809.5215,
      "train_tokens_per_second": 29200.644
    },
    {
      "epoch": 2.81498959547287,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6707650677894036e-05,
      "loss": 1.0355209350585937,
      "num_input_tokens_seen": 22627746688,
      "step": 79560,
      "train_runtime": 774903.8606,
      "train_tokens_per_second": 29200.715
    },
    {
      "epoch": 2.8153434157365984,
      "grad_norm": 1.59375,
      "learning_rate": 1.670671798259552e-05,
      "loss": 1.0329557418823243,
      "num_input_tokens_seen": 22630539840,
      "step": 79570,
      "train_runtime": 774998.982,
      "train_tokens_per_second": 29200.735
    },
    {
      "epoch": 2.8156972360003274,
      "grad_norm": 1.546875,
      "learning_rate": 1.6705785443481153e-05,
      "loss": 1.0242696762084962,
      "num_input_tokens_seen": 22633376000,
      "step": 79580,
      "train_runtime": 775092.7212,
      "train_tokens_per_second": 29200.863
    },
    {
      "epoch": 2.816051056264056,
      "grad_norm": 1.625,
      "learning_rate": 1.6704853060507353e-05,
      "loss": 1.0221620559692384,
      "num_input_tokens_seen": 22636252992,
      "step": 79590,
      "train_runtime": 775192.5933,
      "train_tokens_per_second": 29200.812
    },
    {
      "epoch": 2.816404876527785,
      "grad_norm": 1.640625,
      "learning_rate": 1.6703920833630547e-05,
      "loss": 1.013923454284668,
      "num_input_tokens_seen": 22639025728,
      "step": 79600,
      "train_runtime": 775285.6076,
      "train_tokens_per_second": 29200.885
    },
    {
      "epoch": 2.8167586967915135,
      "grad_norm": 1.6171875,
      "learning_rate": 1.670298876280719e-05,
      "loss": 1.0309035301208496,
      "num_input_tokens_seen": 22641890048,
      "step": 79610,
      "train_runtime": 775382.8945,
      "train_tokens_per_second": 29200.915
    },
    {
      "epoch": 2.8171125170552425,
      "grad_norm": 1.640625,
      "learning_rate": 1.6702056847993747e-05,
      "loss": 1.0482139587402344,
      "num_input_tokens_seen": 22644749760,
      "step": 79620,
      "train_runtime": 775479.897,
      "train_tokens_per_second": 29200.95
    },
    {
      "epoch": 2.8174663373189714,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6701125089146698e-05,
      "loss": 1.0564154624938964,
      "num_input_tokens_seen": 22647593088,
      "step": 79630,
      "train_runtime": 775577.0595,
      "train_tokens_per_second": 29200.958
    },
    {
      "epoch": 2.8178201575827,
      "grad_norm": 1.59375,
      "learning_rate": 1.6700193486222547e-05,
      "loss": 1.044890785217285,
      "num_input_tokens_seen": 22650394176,
      "step": 79640,
      "train_runtime": 775671.6789,
      "train_tokens_per_second": 29201.007
    },
    {
      "epoch": 2.8181739778464285,
      "grad_norm": 1.59375,
      "learning_rate": 1.669926203917781e-05,
      "loss": 1.0315406799316407,
      "num_input_tokens_seen": 22653288576,
      "step": 79650,
      "train_runtime": 775768.0544,
      "train_tokens_per_second": 29201.11
    },
    {
      "epoch": 2.8185277981101575,
      "grad_norm": 1.5859375,
      "learning_rate": 1.669833074796902e-05,
      "loss": 1.024192714691162,
      "num_input_tokens_seen": 22656080832,
      "step": 79660,
      "train_runtime": 775862.3975,
      "train_tokens_per_second": 29201.158
    },
    {
      "epoch": 2.8188816183738865,
      "grad_norm": 1.6328125,
      "learning_rate": 1.669739961255273e-05,
      "loss": 1.0299896240234374,
      "num_input_tokens_seen": 22658895168,
      "step": 79670,
      "train_runtime": 775959.1688,
      "train_tokens_per_second": 29201.144
    },
    {
      "epoch": 2.819235438637615,
      "grad_norm": 1.6328125,
      "learning_rate": 1.669646863288551e-05,
      "loss": 1.0404972076416015,
      "num_input_tokens_seen": 22661759104,
      "step": 79680,
      "train_runtime": 776055.6778,
      "train_tokens_per_second": 29201.203
    },
    {
      "epoch": 2.8195892589013436,
      "grad_norm": 1.6328125,
      "learning_rate": 1.669553780892394e-05,
      "loss": 1.0407751083374024,
      "num_input_tokens_seen": 22664598336,
      "step": 79690,
      "train_runtime": 776154.9702,
      "train_tokens_per_second": 29201.125
    },
    {
      "epoch": 2.8199430791650726,
      "grad_norm": 1.609375,
      "learning_rate": 1.6694607140624624e-05,
      "loss": 1.036793327331543,
      "num_input_tokens_seen": 22667450240,
      "step": 79700,
      "train_runtime": 776252.7726,
      "train_tokens_per_second": 29201.12
    },
    {
      "epoch": 2.8202968994288016,
      "grad_norm": 1.703125,
      "learning_rate": 1.6693676627944183e-05,
      "loss": 1.0411174774169922,
      "num_input_tokens_seen": 22670263360,
      "step": 79710,
      "train_runtime": 776349.2006,
      "train_tokens_per_second": 29201.116
    },
    {
      "epoch": 2.82065071969253,
      "grad_norm": 1.609375,
      "learning_rate": 1.6692746270839252e-05,
      "loss": 1.0489755630493165,
      "num_input_tokens_seen": 22673060800,
      "step": 79720,
      "train_runtime": 776445.0372,
      "train_tokens_per_second": 29201.115
    },
    {
      "epoch": 2.821004539956259,
      "grad_norm": 1.5625,
      "learning_rate": 1.6691816069266487e-05,
      "loss": 1.0361312866210937,
      "num_input_tokens_seen": 22675910144,
      "step": 79730,
      "train_runtime": 776542.7485,
      "train_tokens_per_second": 29201.11
    },
    {
      "epoch": 2.8213583602199876,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6690886023182548e-05,
      "loss": 1.0229256629943848,
      "num_input_tokens_seen": 22678804544,
      "step": 79740,
      "train_runtime": 776640.6078,
      "train_tokens_per_second": 29201.157
    },
    {
      "epoch": 2.8217121804837166,
      "grad_norm": 1.6796875,
      "learning_rate": 1.6689956132544133e-05,
      "loss": 1.0272525787353515,
      "num_input_tokens_seen": 22681628544,
      "step": 79750,
      "train_runtime": 776739.3221,
      "train_tokens_per_second": 29201.082
    },
    {
      "epoch": 2.822066000747445,
      "grad_norm": 1.53125,
      "learning_rate": 1.6689026397307936e-05,
      "loss": 1.0263747215270995,
      "num_input_tokens_seen": 22684480640,
      "step": 79760,
      "train_runtime": 776836.2433,
      "train_tokens_per_second": 29201.11
    },
    {
      "epoch": 2.822419821011174,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6688096817430687e-05,
      "loss": 1.0362535476684571,
      "num_input_tokens_seen": 22687366912,
      "step": 79770,
      "train_runtime": 776935.9583,
      "train_tokens_per_second": 29201.077
    },
    {
      "epoch": 2.8227736412749027,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6687167392869115e-05,
      "loss": 1.0204397201538087,
      "num_input_tokens_seen": 22690203008,
      "step": 79780,
      "train_runtime": 777032.7363,
      "train_tokens_per_second": 29201.09
    },
    {
      "epoch": 2.8231274615386317,
      "grad_norm": 1.59375,
      "learning_rate": 1.668623812357998e-05,
      "loss": 1.0296805381774903,
      "num_input_tokens_seen": 22693049152,
      "step": 79790,
      "train_runtime": 777127.9507,
      "train_tokens_per_second": 29201.175
    },
    {
      "epoch": 2.8234812818023602,
      "grad_norm": 1.609375,
      "learning_rate": 1.6685309009520046e-05,
      "loss": 1.0385083198547362,
      "num_input_tokens_seen": 22695839424,
      "step": 79800,
      "train_runtime": 777221.8049,
      "train_tokens_per_second": 29201.239
    },
    {
      "epoch": 2.8238351020660892,
      "grad_norm": 1.5703125,
      "learning_rate": 1.668438005064611e-05,
      "loss": 1.0321401596069335,
      "num_input_tokens_seen": 22698688832,
      "step": 79810,
      "train_runtime": 777322.6951,
      "train_tokens_per_second": 29201.114
    },
    {
      "epoch": 2.824188922329818,
      "grad_norm": 1.578125,
      "learning_rate": 1.6683451246914973e-05,
      "loss": 1.0327841758728027,
      "num_input_tokens_seen": 22701506496,
      "step": 79820,
      "train_runtime": 777418.2367,
      "train_tokens_per_second": 29201.15
    },
    {
      "epoch": 2.8245427425935468,
      "grad_norm": 1.625,
      "learning_rate": 1.6682522598283452e-05,
      "loss": 1.057236385345459,
      "num_input_tokens_seen": 22704423808,
      "step": 79830,
      "train_runtime": 777518.2537,
      "train_tokens_per_second": 29201.146
    },
    {
      "epoch": 2.8248965628572753,
      "grad_norm": 1.609375,
      "learning_rate": 1.6681594104708393e-05,
      "loss": 1.032967758178711,
      "num_input_tokens_seen": 22707222912,
      "step": 79840,
      "train_runtime": 777613.4443,
      "train_tokens_per_second": 29201.171
    },
    {
      "epoch": 2.8252503831210043,
      "grad_norm": 1.5625,
      "learning_rate": 1.6680665766146643e-05,
      "loss": 1.0514030456542969,
      "num_input_tokens_seen": 22710062464,
      "step": 79850,
      "train_runtime": 777710.9267,
      "train_tokens_per_second": 29201.162
    },
    {
      "epoch": 2.8256042033847333,
      "grad_norm": 1.6328125,
      "learning_rate": 1.667973758255508e-05,
      "loss": 1.032219123840332,
      "num_input_tokens_seen": 22712959424,
      "step": 79860,
      "train_runtime": 777810.5131,
      "train_tokens_per_second": 29201.147
    },
    {
      "epoch": 2.825958023648462,
      "grad_norm": 1.6171875,
      "learning_rate": 1.667880955389059e-05,
      "loss": 1.0339744567871094,
      "num_input_tokens_seen": 22715825792,
      "step": 79870,
      "train_runtime": 777909.651,
      "train_tokens_per_second": 29201.111
    },
    {
      "epoch": 2.826311843912191,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6677881680110082e-05,
      "loss": 1.041092300415039,
      "num_input_tokens_seen": 22718702272,
      "step": 79880,
      "train_runtime": 778008.7479,
      "train_tokens_per_second": 29201.088
    },
    {
      "epoch": 2.8266656641759194,
      "grad_norm": 1.59375,
      "learning_rate": 1.6676953961170472e-05,
      "loss": 1.0323168754577636,
      "num_input_tokens_seen": 22721534784,
      "step": 79890,
      "train_runtime": 778104.9894,
      "train_tokens_per_second": 29201.117
    },
    {
      "epoch": 2.8270194844396483,
      "grad_norm": 1.625,
      "learning_rate": 1.6676026397028705e-05,
      "loss": 1.035478401184082,
      "num_input_tokens_seen": 22724360256,
      "step": 79900,
      "train_runtime": 778201.2639,
      "train_tokens_per_second": 29201.135
    },
    {
      "epoch": 2.827373304703377,
      "grad_norm": 1.5625,
      "learning_rate": 1.6675098987641735e-05,
      "loss": 1.0395593643188477,
      "num_input_tokens_seen": 22727262016,
      "step": 79910,
      "train_runtime": 778305.5986,
      "train_tokens_per_second": 29200.949
    },
    {
      "epoch": 2.827727124967106,
      "grad_norm": 1.671875,
      "learning_rate": 1.6674171732966538e-05,
      "loss": 1.0355644226074219,
      "num_input_tokens_seen": 22730093376,
      "step": 79920,
      "train_runtime": 778401.9676,
      "train_tokens_per_second": 29200.971
    },
    {
      "epoch": 2.8280809452308344,
      "grad_norm": 1.609375,
      "learning_rate": 1.6673244632960093e-05,
      "loss": 1.0340763092041017,
      "num_input_tokens_seen": 22732973632,
      "step": 79930,
      "train_runtime": 778504.4297,
      "train_tokens_per_second": 29200.828
    },
    {
      "epoch": 2.8284347654945634,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6672317687579418e-05,
      "loss": 1.0296091079711913,
      "num_input_tokens_seen": 22735793600,
      "step": 79940,
      "train_runtime": 778599.6236,
      "train_tokens_per_second": 29200.879
    },
    {
      "epoch": 2.828788585758292,
      "grad_norm": 1.65625,
      "learning_rate": 1.6671390896781527e-05,
      "loss": 1.0396522521972655,
      "num_input_tokens_seen": 22738639808,
      "step": 79950,
      "train_runtime": 778696.342,
      "train_tokens_per_second": 29200.907
    },
    {
      "epoch": 2.829142406022021,
      "grad_norm": 1.59375,
      "learning_rate": 1.6670464260523466e-05,
      "loss": 1.0409607887268066,
      "num_input_tokens_seen": 22741458816,
      "step": 79960,
      "train_runtime": 778788.2541,
      "train_tokens_per_second": 29201.081
    },
    {
      "epoch": 2.82949622628575,
      "grad_norm": 1.5546875,
      "learning_rate": 1.666953777876229e-05,
      "loss": 1.034112548828125,
      "num_input_tokens_seen": 22744280000,
      "step": 79970,
      "train_runtime": 778882.6255,
      "train_tokens_per_second": 29201.165
    },
    {
      "epoch": 2.8298500465494785,
      "grad_norm": 1.578125,
      "learning_rate": 1.6668611451455068e-05,
      "loss": 1.025139045715332,
      "num_input_tokens_seen": 22747096128,
      "step": 79980,
      "train_runtime": 778978.8721,
      "train_tokens_per_second": 29201.172
    },
    {
      "epoch": 2.830203866813207,
      "grad_norm": 1.546875,
      "learning_rate": 1.6667685278558893e-05,
      "loss": 1.042760467529297,
      "num_input_tokens_seen": 22749936704,
      "step": 79990,
      "train_runtime": 779076.9504,
      "train_tokens_per_second": 29201.142
    },
    {
      "epoch": 2.830557687076936,
      "grad_norm": 1.6484375,
      "learning_rate": 1.666675926003087e-05,
      "loss": 1.0351173400878906,
      "num_input_tokens_seen": 22752762176,
      "step": 80000,
      "train_runtime": 779175.3398,
      "train_tokens_per_second": 29201.081
    },
    {
      "epoch": 2.830557687076936,
      "eval_loss": 1.0218605995178223,
      "eval_runtime": 8.4506,
      "eval_samples_per_second": 471.918,
      "eval_steps_per_second": 3.787,
      "num_input_tokens_seen": 22752762176,
      "step": 80000
    },
    {
      "epoch": 2.830911507340665,
      "grad_norm": 1.6796875,
      "learning_rate": 1.6665833395828124e-05,
      "loss": 1.0323559761047363,
      "num_input_tokens_seen": 22755631936,
      "step": 80010,
      "train_runtime": 779303.7064,
      "train_tokens_per_second": 29199.953
    },
    {
      "epoch": 2.8312653276043935,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6664907685907795e-05,
      "loss": 1.046002197265625,
      "num_input_tokens_seen": 22758462976,
      "step": 80020,
      "train_runtime": 779402.1696,
      "train_tokens_per_second": 29199.897
    },
    {
      "epoch": 2.831619147868122,
      "grad_norm": 1.6171875,
      "learning_rate": 1.666398213022704e-05,
      "loss": 1.0349205017089844,
      "num_input_tokens_seen": 22761258944,
      "step": 80030,
      "train_runtime": 779495.249,
      "train_tokens_per_second": 29199.997
    },
    {
      "epoch": 2.831972968131851,
      "grad_norm": 1.59375,
      "learning_rate": 1.6663056728743024e-05,
      "loss": 1.0328171730041504,
      "num_input_tokens_seen": 22764086592,
      "step": 80040,
      "train_runtime": 779592.0914,
      "train_tokens_per_second": 29199.997
    },
    {
      "epoch": 2.83232678839558,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6662131481412947e-05,
      "loss": 1.036666488647461,
      "num_input_tokens_seen": 22766929536,
      "step": 80050,
      "train_runtime": 779690.424,
      "train_tokens_per_second": 29199.96
    },
    {
      "epoch": 2.8326806086593086,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6661206388194006e-05,
      "loss": 1.023030662536621,
      "num_input_tokens_seen": 22769697472,
      "step": 80060,
      "train_runtime": 779785.5356,
      "train_tokens_per_second": 29199.948
    },
    {
      "epoch": 2.8330344289230376,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6660281449043436e-05,
      "loss": 1.0272648811340332,
      "num_input_tokens_seen": 22772522304,
      "step": 80070,
      "train_runtime": 779883.9537,
      "train_tokens_per_second": 29199.886
    },
    {
      "epoch": 2.833388249186766,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6659356663918466e-05,
      "loss": 1.0347506523132324,
      "num_input_tokens_seen": 22775296320,
      "step": 80080,
      "train_runtime": 779976.497,
      "train_tokens_per_second": 29199.978
    },
    {
      "epoch": 2.833742069450495,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6658432032776354e-05,
      "loss": 1.0472360610961915,
      "num_input_tokens_seen": 22778134208,
      "step": 80090,
      "train_runtime": 780072.8102,
      "train_tokens_per_second": 29200.01
    },
    {
      "epoch": 2.8340958897142237,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6657507555574375e-05,
      "loss": 1.0317363739013672,
      "num_input_tokens_seen": 22780978304,
      "step": 80100,
      "train_runtime": 780168.8945,
      "train_tokens_per_second": 29200.06
    },
    {
      "epoch": 2.8344497099779526,
      "grad_norm": 1.609375,
      "learning_rate": 1.6656583232269816e-05,
      "loss": 1.0367139816284179,
      "num_input_tokens_seen": 22783811328,
      "step": 80110,
      "train_runtime": 780262.8487,
      "train_tokens_per_second": 29200.174
    },
    {
      "epoch": 2.834803530241681,
      "grad_norm": 1.65625,
      "learning_rate": 1.665565906281999e-05,
      "loss": 1.0183178901672363,
      "num_input_tokens_seen": 22786625408,
      "step": 80120,
      "train_runtime": 780357.9983,
      "train_tokens_per_second": 29200.22
    },
    {
      "epoch": 2.83515735050541,
      "grad_norm": 1.59375,
      "learning_rate": 1.6654735047182213e-05,
      "loss": 1.0287519454956056,
      "num_input_tokens_seen": 22789406720,
      "step": 80130,
      "train_runtime": 780453.3894,
      "train_tokens_per_second": 29200.215
    },
    {
      "epoch": 2.8355111707691387,
      "grad_norm": 1.4921875,
      "learning_rate": 1.6653811185313824e-05,
      "loss": 1.0330543518066406,
      "num_input_tokens_seen": 22792252736,
      "step": 80140,
      "train_runtime": 780550.2869,
      "train_tokens_per_second": 29200.236
    },
    {
      "epoch": 2.8358649910328677,
      "grad_norm": 1.6015625,
      "learning_rate": 1.665288747717218e-05,
      "loss": 1.0447502136230469,
      "num_input_tokens_seen": 22795048704,
      "step": 80150,
      "train_runtime": 780643.5143,
      "train_tokens_per_second": 29200.331
    },
    {
      "epoch": 2.8362188112965967,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6651963922714655e-05,
      "loss": 1.036759376525879,
      "num_input_tokens_seen": 22797884928,
      "step": 80160,
      "train_runtime": 780741.412,
      "train_tokens_per_second": 29200.302
    },
    {
      "epoch": 2.8365726315603252,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6651040521898635e-05,
      "loss": 1.0344396591186524,
      "num_input_tokens_seen": 22800727424,
      "step": 80170,
      "train_runtime": 780836.8625,
      "train_tokens_per_second": 29200.373
    },
    {
      "epoch": 2.836926451824054,
      "grad_norm": 1.59375,
      "learning_rate": 1.6650117274681528e-05,
      "loss": 1.0404803276062011,
      "num_input_tokens_seen": 22803598144,
      "step": 80180,
      "train_runtime": 780933.4789,
      "train_tokens_per_second": 29200.436
    },
    {
      "epoch": 2.8372802720877828,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6649194181020756e-05,
      "loss": 1.0317547798156739,
      "num_input_tokens_seen": 22806523392,
      "step": 80190,
      "train_runtime": 781035.5054,
      "train_tokens_per_second": 29200.367
    },
    {
      "epoch": 2.8376340923515118,
      "grad_norm": 1.609375,
      "learning_rate": 1.6648271240873753e-05,
      "loss": 1.0424488067626954,
      "num_input_tokens_seen": 22809368256,
      "step": 80200,
      "train_runtime": 781133.8014,
      "train_tokens_per_second": 29200.334
    },
    {
      "epoch": 2.8379879126152403,
      "grad_norm": 1.59375,
      "learning_rate": 1.664734845419798e-05,
      "loss": 1.0092010498046875,
      "num_input_tokens_seen": 22812157952,
      "step": 80210,
      "train_runtime": 781225.6033,
      "train_tokens_per_second": 29200.474
    },
    {
      "epoch": 2.8383417328789693,
      "grad_norm": 1.6015625,
      "learning_rate": 1.66464258209509e-05,
      "loss": 1.048866367340088,
      "num_input_tokens_seen": 22815019264,
      "step": 80220,
      "train_runtime": 781324.8043,
      "train_tokens_per_second": 29200.429
    },
    {
      "epoch": 2.838695553142698,
      "grad_norm": 1.5703125,
      "learning_rate": 1.664550334109001e-05,
      "loss": 1.0418125152587892,
      "num_input_tokens_seen": 22817832448,
      "step": 80230,
      "train_runtime": 781420.9027,
      "train_tokens_per_second": 29200.438
    },
    {
      "epoch": 2.839049373406427,
      "grad_norm": 1.640625,
      "learning_rate": 1.664458101457281e-05,
      "loss": 1.0309842109680176,
      "num_input_tokens_seen": 22820726848,
      "step": 80240,
      "train_runtime": 781522.3056,
      "train_tokens_per_second": 29200.353
    },
    {
      "epoch": 2.8394031936701554,
      "grad_norm": 1.6171875,
      "learning_rate": 1.664365884135682e-05,
      "loss": 1.0547696113586427,
      "num_input_tokens_seen": 22823606464,
      "step": 80250,
      "train_runtime": 781620.4793,
      "train_tokens_per_second": 29200.369
    },
    {
      "epoch": 2.8397570139338844,
      "grad_norm": 1.59375,
      "learning_rate": 1.6642736821399583e-05,
      "loss": 1.048665428161621,
      "num_input_tokens_seen": 22826425216,
      "step": 80260,
      "train_runtime": 781715.8714,
      "train_tokens_per_second": 29200.412
    },
    {
      "epoch": 2.840110834197613,
      "grad_norm": 1.65625,
      "learning_rate": 1.6641814954658643e-05,
      "loss": 1.0321236610412599,
      "num_input_tokens_seen": 22829255552,
      "step": 80270,
      "train_runtime": 781811.4184,
      "train_tokens_per_second": 29200.463
    },
    {
      "epoch": 2.840464654461342,
      "grad_norm": 1.609375,
      "learning_rate": 1.664089324109158e-05,
      "loss": 1.0476900100708009,
      "num_input_tokens_seen": 22832113664,
      "step": 80280,
      "train_runtime": 781909.7553,
      "train_tokens_per_second": 29200.446
    },
    {
      "epoch": 2.8408184747250704,
      "grad_norm": 1.625,
      "learning_rate": 1.6639971680655975e-05,
      "loss": 1.043871021270752,
      "num_input_tokens_seen": 22834964416,
      "step": 80290,
      "train_runtime": 782006.6723,
      "train_tokens_per_second": 29200.473
    },
    {
      "epoch": 2.8411722949887994,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6639050273309432e-05,
      "loss": 1.0197729110717773,
      "num_input_tokens_seen": 22837856320,
      "step": 80300,
      "train_runtime": 782106.8313,
      "train_tokens_per_second": 29200.431
    },
    {
      "epoch": 2.8415261152525284,
      "grad_norm": 1.59375,
      "learning_rate": 1.6638129019009573e-05,
      "loss": 1.040507984161377,
      "num_input_tokens_seen": 22840750912,
      "step": 80310,
      "train_runtime": 782208.529,
      "train_tokens_per_second": 29200.335
    },
    {
      "epoch": 2.841879935516257,
      "grad_norm": 1.6171875,
      "learning_rate": 1.663720791771403e-05,
      "loss": 1.033221435546875,
      "num_input_tokens_seen": 22843562560,
      "step": 80320,
      "train_runtime": 782307.1684,
      "train_tokens_per_second": 29200.247
    },
    {
      "epoch": 2.8422337557799855,
      "grad_norm": 1.5859375,
      "learning_rate": 1.663628696938046e-05,
      "loss": 1.0516000747680665,
      "num_input_tokens_seen": 22846482752,
      "step": 80330,
      "train_runtime": 782409.4706,
      "train_tokens_per_second": 29200.161
    },
    {
      "epoch": 2.8425875760437145,
      "grad_norm": 1.578125,
      "learning_rate": 1.663536617396653e-05,
      "loss": 1.0329723358154297,
      "num_input_tokens_seen": 22849334080,
      "step": 80340,
      "train_runtime": 782510.8815,
      "train_tokens_per_second": 29200.021
    },
    {
      "epoch": 2.8429413963074435,
      "grad_norm": 1.65625,
      "learning_rate": 1.6634445531429922e-05,
      "loss": 1.0408260345458984,
      "num_input_tokens_seen": 22852179392,
      "step": 80350,
      "train_runtime": 782608.7549,
      "train_tokens_per_second": 29200.005
    },
    {
      "epoch": 2.843295216571172,
      "grad_norm": 1.6328125,
      "learning_rate": 1.663352504172834e-05,
      "loss": 1.0457895278930665,
      "num_input_tokens_seen": 22854962240,
      "step": 80360,
      "train_runtime": 782701.4196,
      "train_tokens_per_second": 29200.103
    },
    {
      "epoch": 2.8436490368349006,
      "grad_norm": 1.578125,
      "learning_rate": 1.663260470481951e-05,
      "loss": 1.0390413284301758,
      "num_input_tokens_seen": 22857796608,
      "step": 80370,
      "train_runtime": 782798.1697,
      "train_tokens_per_second": 29200.115
    },
    {
      "epoch": 2.8440028570986295,
      "grad_norm": 1.515625,
      "learning_rate": 1.663168452066115e-05,
      "loss": 1.0397710800170898,
      "num_input_tokens_seen": 22860663616,
      "step": 80380,
      "train_runtime": 782896.0498,
      "train_tokens_per_second": 29200.126
    },
    {
      "epoch": 2.8443566773623585,
      "grad_norm": 1.609375,
      "learning_rate": 1.663076448921102e-05,
      "loss": 1.0263717651367188,
      "num_input_tokens_seen": 22863503296,
      "step": 80390,
      "train_runtime": 782992.2633,
      "train_tokens_per_second": 29200.165
    },
    {
      "epoch": 2.844710497626087,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6629844610426892e-05,
      "loss": 1.043206024169922,
      "num_input_tokens_seen": 22866358464,
      "step": 80400,
      "train_runtime": 783091.698,
      "train_tokens_per_second": 29200.103
    },
    {
      "epoch": 2.845064317889816,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6628924884266542e-05,
      "loss": 1.048374080657959,
      "num_input_tokens_seen": 22869242816,
      "step": 80410,
      "train_runtime": 783190.8953,
      "train_tokens_per_second": 29200.088
    },
    {
      "epoch": 2.8454181381535446,
      "grad_norm": 1.578125,
      "learning_rate": 1.6628005310687773e-05,
      "loss": 1.0357446670532227,
      "num_input_tokens_seen": 22872063808,
      "step": 80420,
      "train_runtime": 783285.778,
      "train_tokens_per_second": 29200.152
    },
    {
      "epoch": 2.8457719584172736,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6627085889648396e-05,
      "loss": 1.042096996307373,
      "num_input_tokens_seen": 22874942272,
      "step": 80430,
      "train_runtime": 783381.8339,
      "train_tokens_per_second": 29200.246
    },
    {
      "epoch": 2.846125778681002,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6626166621106252e-05,
      "loss": 1.0323066711425781,
      "num_input_tokens_seen": 22877804864,
      "step": 80440,
      "train_runtime": 783479.3622,
      "train_tokens_per_second": 29200.265
    },
    {
      "epoch": 2.846479598944731,
      "grad_norm": 1.609375,
      "learning_rate": 1.6625247505019183e-05,
      "loss": 1.035548496246338,
      "num_input_tokens_seen": 22880627520,
      "step": 80450,
      "train_runtime": 783573.7371,
      "train_tokens_per_second": 29200.35
    },
    {
      "epoch": 2.84683341920846,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6624328541345054e-05,
      "loss": 1.035201644897461,
      "num_input_tokens_seen": 22883450304,
      "step": 80460,
      "train_runtime": 783668.9869,
      "train_tokens_per_second": 29200.403
    },
    {
      "epoch": 2.8471872394721887,
      "grad_norm": 1.625,
      "learning_rate": 1.662340973004175e-05,
      "loss": 1.0444052696228028,
      "num_input_tokens_seen": 22886343104,
      "step": 80470,
      "train_runtime": 783769.7832,
      "train_tokens_per_second": 29200.339
    },
    {
      "epoch": 2.847541059735917,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6622491071067173e-05,
      "loss": 1.0478404998779296,
      "num_input_tokens_seen": 22889160512,
      "step": 80480,
      "train_runtime": 783863.9402,
      "train_tokens_per_second": 29200.425
    },
    {
      "epoch": 2.847894879999646,
      "grad_norm": 1.640625,
      "learning_rate": 1.662157256437923e-05,
      "loss": 1.0283281326293945,
      "num_input_tokens_seen": 22892025600,
      "step": 80490,
      "train_runtime": 783962.2773,
      "train_tokens_per_second": 29200.417
    },
    {
      "epoch": 2.848248700263375,
      "grad_norm": 1.625,
      "learning_rate": 1.6620654209935848e-05,
      "loss": 1.040452003479004,
      "num_input_tokens_seen": 22894854976,
      "step": 80500,
      "train_runtime": 784059.227,
      "train_tokens_per_second": 29200.415
    },
    {
      "epoch": 2.8486025205271037,
      "grad_norm": 1.6796875,
      "learning_rate": 1.661973600769498e-05,
      "loss": 1.0361530303955078,
      "num_input_tokens_seen": 22897708736,
      "step": 80510,
      "train_runtime": 784158.4942,
      "train_tokens_per_second": 29200.358
    },
    {
      "epoch": 2.8489563407908323,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6618817957614587e-05,
      "loss": 1.043104362487793,
      "num_input_tokens_seen": 22900593600,
      "step": 80520,
      "train_runtime": 784258.0592,
      "train_tokens_per_second": 29200.329
    },
    {
      "epoch": 2.8493101610545613,
      "grad_norm": 1.6015625,
      "learning_rate": 1.661790005965265e-05,
      "loss": 1.0335250854492188,
      "num_input_tokens_seen": 22903405696,
      "step": 80530,
      "train_runtime": 784354.0986,
      "train_tokens_per_second": 29200.339
    },
    {
      "epoch": 2.8496639813182902,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6616982313767158e-05,
      "loss": 1.027759075164795,
      "num_input_tokens_seen": 22906273536,
      "step": 80540,
      "train_runtime": 784453.0012,
      "train_tokens_per_second": 29200.313
    },
    {
      "epoch": 2.850017801582019,
      "grad_norm": 1.640625,
      "learning_rate": 1.661606471991613e-05,
      "loss": 1.0343889236450194,
      "num_input_tokens_seen": 22909100416,
      "step": 80550,
      "train_runtime": 784547.9039,
      "train_tokens_per_second": 29200.384
    },
    {
      "epoch": 2.8503716218457478,
      "grad_norm": 1.6796875,
      "learning_rate": 1.661514727805759e-05,
      "loss": 1.0448912620544433,
      "num_input_tokens_seen": 22911954944,
      "step": 80560,
      "train_runtime": 784648.0056,
      "train_tokens_per_second": 29200.297
    },
    {
      "epoch": 2.8507254421094763,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6614229988149582e-05,
      "loss": 1.0320121765136718,
      "num_input_tokens_seen": 22914805888,
      "step": 80570,
      "train_runtime": 784745.0473,
      "train_tokens_per_second": 29200.319
    },
    {
      "epoch": 2.8510792623732053,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6613312850150166e-05,
      "loss": 1.043410587310791,
      "num_input_tokens_seen": 22917642432,
      "step": 80580,
      "train_runtime": 784840.6334,
      "train_tokens_per_second": 29200.377
    },
    {
      "epoch": 2.851433082636934,
      "grad_norm": 1.6015625,
      "learning_rate": 1.661239586401742e-05,
      "loss": 1.0322134971618653,
      "num_input_tokens_seen": 22920466432,
      "step": 80590,
      "train_runtime": 784938.3236,
      "train_tokens_per_second": 29200.341
    },
    {
      "epoch": 2.851786902900663,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6611479029709438e-05,
      "loss": 1.04379243850708,
      "num_input_tokens_seen": 22923306688,
      "step": 80600,
      "train_runtime": 785033.0714,
      "train_tokens_per_second": 29200.434
    },
    {
      "epoch": 2.8521407231643914,
      "grad_norm": 1.640625,
      "learning_rate": 1.6610562347184323e-05,
      "loss": 1.0454593658447267,
      "num_input_tokens_seen": 22926170240,
      "step": 80610,
      "train_runtime": 785129.6609,
      "train_tokens_per_second": 29200.489
    },
    {
      "epoch": 2.8524945434281204,
      "grad_norm": 1.578125,
      "learning_rate": 1.66096458164002e-05,
      "loss": 1.0244400024414062,
      "num_input_tokens_seen": 22928970432,
      "step": 80620,
      "train_runtime": 785226.168,
      "train_tokens_per_second": 29200.467
    },
    {
      "epoch": 2.852848363691849,
      "grad_norm": 1.640625,
      "learning_rate": 1.6608729437315218e-05,
      "loss": 1.0343225479125977,
      "num_input_tokens_seen": 22931792896,
      "step": 80630,
      "train_runtime": 785322.2037,
      "train_tokens_per_second": 29200.49
    },
    {
      "epoch": 2.853202183955578,
      "grad_norm": 1.625,
      "learning_rate": 1.660781320988753e-05,
      "loss": 1.0353330612182616,
      "num_input_tokens_seen": 22934705536,
      "step": 80640,
      "train_runtime": 785423.8471,
      "train_tokens_per_second": 29200.419
    },
    {
      "epoch": 2.853556004219307,
      "grad_norm": 1.6875,
      "learning_rate": 1.6606897134075307e-05,
      "loss": 1.0372068405151367,
      "num_input_tokens_seen": 22937512192,
      "step": 80650,
      "train_runtime": 785518.2264,
      "train_tokens_per_second": 29200.484
    },
    {
      "epoch": 2.8539098244830354,
      "grad_norm": 1.640625,
      "learning_rate": 1.660598120983674e-05,
      "loss": 1.0422983169555664,
      "num_input_tokens_seen": 22940352448,
      "step": 80660,
      "train_runtime": 785614.9788,
      "train_tokens_per_second": 29200.503
    },
    {
      "epoch": 2.854263644746764,
      "grad_norm": 1.59375,
      "learning_rate": 1.660506543713004e-05,
      "loss": 1.0379693984985352,
      "num_input_tokens_seen": 22943216320,
      "step": 80670,
      "train_runtime": 785713.9613,
      "train_tokens_per_second": 29200.469
    },
    {
      "epoch": 2.854617465010493,
      "grad_norm": 1.5859375,
      "learning_rate": 1.660414981591342e-05,
      "loss": 1.0329832077026366,
      "num_input_tokens_seen": 22946051328,
      "step": 80680,
      "train_runtime": 785811.5584,
      "train_tokens_per_second": 29200.45
    },
    {
      "epoch": 2.854971285274222,
      "grad_norm": 1.515625,
      "learning_rate": 1.6603234346145123e-05,
      "loss": 1.035323429107666,
      "num_input_tokens_seen": 22948868032,
      "step": 80690,
      "train_runtime": 785905.485,
      "train_tokens_per_second": 29200.544
    },
    {
      "epoch": 2.8553251055379505,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6602319027783403e-05,
      "loss": 1.0245865821838378,
      "num_input_tokens_seen": 22951708672,
      "step": 80700,
      "train_runtime": 786000.9355,
      "train_tokens_per_second": 29200.612
    },
    {
      "epoch": 2.8556789258016795,
      "grad_norm": 1.6796875,
      "learning_rate": 1.6601403860786528e-05,
      "loss": 1.035319709777832,
      "num_input_tokens_seen": 22954602496,
      "step": 80710,
      "train_runtime": 786099.8604,
      "train_tokens_per_second": 29200.619
    },
    {
      "epoch": 2.856032746065408,
      "grad_norm": 1.6328125,
      "learning_rate": 1.660048884511279e-05,
      "loss": 1.0315517425537108,
      "num_input_tokens_seen": 22957379648,
      "step": 80720,
      "train_runtime": 786193.8895,
      "train_tokens_per_second": 29200.659
    },
    {
      "epoch": 2.856386566329137,
      "grad_norm": 1.5234375,
      "learning_rate": 1.6599573980720478e-05,
      "loss": 1.043848419189453,
      "num_input_tokens_seen": 22960240256,
      "step": 80730,
      "train_runtime": 786289.6652,
      "train_tokens_per_second": 29200.74
    },
    {
      "epoch": 2.8567403865928656,
      "grad_norm": 1.59375,
      "learning_rate": 1.6598659267567925e-05,
      "loss": 1.0380939483642577,
      "num_input_tokens_seen": 22963055232,
      "step": 80740,
      "train_runtime": 786386.1779,
      "train_tokens_per_second": 29200.736
    },
    {
      "epoch": 2.8570942068565945,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6597744705613464e-05,
      "loss": 1.0320858001708983,
      "num_input_tokens_seen": 22965878144,
      "step": 80750,
      "train_runtime": 786484.0455,
      "train_tokens_per_second": 29200.692
    },
    {
      "epoch": 2.857448027120323,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6596830294815434e-05,
      "loss": 1.0376737594604493,
      "num_input_tokens_seen": 22968705728,
      "step": 80760,
      "train_runtime": 786581.0959,
      "train_tokens_per_second": 29200.684
    },
    {
      "epoch": 2.857801847384052,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6595916035132218e-05,
      "loss": 1.0475418090820312,
      "num_input_tokens_seen": 22971548928,
      "step": 80770,
      "train_runtime": 786680.9112,
      "train_tokens_per_second": 29200.593
    },
    {
      "epoch": 2.8581556676477806,
      "grad_norm": 1.578125,
      "learning_rate": 1.6595001926522184e-05,
      "loss": 1.0299690246582032,
      "num_input_tokens_seen": 22974430848,
      "step": 80780,
      "train_runtime": 786781.3615,
      "train_tokens_per_second": 29200.528
    },
    {
      "epoch": 2.8585094879115096,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6594087968943735e-05,
      "loss": 1.0284738540649414,
      "num_input_tokens_seen": 22977273280,
      "step": 80790,
      "train_runtime": 786877.5378,
      "train_tokens_per_second": 29200.571
    },
    {
      "epoch": 2.8588633081752386,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6593174162355295e-05,
      "loss": 1.0406036376953125,
      "num_input_tokens_seen": 22980155840,
      "step": 80800,
      "train_runtime": 786976.3388,
      "train_tokens_per_second": 29200.568
    },
    {
      "epoch": 2.859217128438967,
      "grad_norm": 1.625,
      "learning_rate": 1.6592260506715286e-05,
      "loss": 1.0246242523193358,
      "num_input_tokens_seen": 22983013056,
      "step": 80810,
      "train_runtime": 787074.1871,
      "train_tokens_per_second": 29200.568
    },
    {
      "epoch": 2.8595709487026957,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6591347001982155e-05,
      "loss": 1.0344379425048829,
      "num_input_tokens_seen": 22985856384,
      "step": 80820,
      "train_runtime": 787171.4994,
      "train_tokens_per_second": 29200.57
    },
    {
      "epoch": 2.8599247689664247,
      "grad_norm": 1.640625,
      "learning_rate": 1.659043364811436e-05,
      "loss": 1.0432378768920898,
      "num_input_tokens_seen": 22988643200,
      "step": 80830,
      "train_runtime": 787265.6984,
      "train_tokens_per_second": 29200.616
    },
    {
      "epoch": 2.8602785892301537,
      "grad_norm": 1.671875,
      "learning_rate": 1.6589520445070395e-05,
      "loss": 1.0230390548706054,
      "num_input_tokens_seen": 22991561792,
      "step": 80840,
      "train_runtime": 787363.4775,
      "train_tokens_per_second": 29200.696
    },
    {
      "epoch": 2.860632409493882,
      "grad_norm": 1.609375,
      "learning_rate": 1.6588607392808746e-05,
      "loss": 1.032874870300293,
      "num_input_tokens_seen": 22994382656,
      "step": 80850,
      "train_runtime": 787459.2108,
      "train_tokens_per_second": 29200.729
    },
    {
      "epoch": 2.8609862297576107,
      "grad_norm": 1.5390625,
      "learning_rate": 1.658769449128792e-05,
      "loss": 1.0213472366333007,
      "num_input_tokens_seen": 22997277952,
      "step": 80860,
      "train_runtime": 787561.7525,
      "train_tokens_per_second": 29200.603
    },
    {
      "epoch": 2.8613400500213397,
      "grad_norm": 1.7421875,
      "learning_rate": 1.6586781740466448e-05,
      "loss": 1.0343477249145507,
      "num_input_tokens_seen": 23000124160,
      "step": 80870,
      "train_runtime": 787659.1013,
      "train_tokens_per_second": 29200.607
    },
    {
      "epoch": 2.8616938702850687,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6585869140302875e-05,
      "loss": 1.0354864120483398,
      "num_input_tokens_seen": 23002947008,
      "step": 80880,
      "train_runtime": 787754.9394,
      "train_tokens_per_second": 29200.638
    },
    {
      "epoch": 2.8620476905487973,
      "grad_norm": 1.609375,
      "learning_rate": 1.6584956690755752e-05,
      "loss": 1.0454496383666991,
      "num_input_tokens_seen": 23005774592,
      "step": 80890,
      "train_runtime": 787852.7824,
      "train_tokens_per_second": 29200.601
    },
    {
      "epoch": 2.8624015108125263,
      "grad_norm": 1.6953125,
      "learning_rate": 1.658404439178366e-05,
      "loss": 1.0439382553100587,
      "num_input_tokens_seen": 23008555840,
      "step": 80900,
      "train_runtime": 787945.356,
      "train_tokens_per_second": 29200.7
    },
    {
      "epoch": 2.862755331076255,
      "grad_norm": 1.578125,
      "learning_rate": 1.6583132243345195e-05,
      "loss": 1.0365544319152833,
      "num_input_tokens_seen": 23011404608,
      "step": 80910,
      "train_runtime": 788041.4872,
      "train_tokens_per_second": 29200.753
    },
    {
      "epoch": 2.863109151339984,
      "grad_norm": 1.609375,
      "learning_rate": 1.6582220245398953e-05,
      "loss": 1.037847137451172,
      "num_input_tokens_seen": 23014274560,
      "step": 80920,
      "train_runtime": 788139.9323,
      "train_tokens_per_second": 29200.747
    },
    {
      "epoch": 2.8634629716037123,
      "grad_norm": 1.609375,
      "learning_rate": 1.658130839790356e-05,
      "loss": 1.0516275405883788,
      "num_input_tokens_seen": 23017134336,
      "step": 80930,
      "train_runtime": 788236.4337,
      "train_tokens_per_second": 29200.8
    },
    {
      "epoch": 2.8638167918674413,
      "grad_norm": 1.609375,
      "learning_rate": 1.658039670081766e-05,
      "loss": 1.0313149452209474,
      "num_input_tokens_seen": 23019984512,
      "step": 80940,
      "train_runtime": 788334.0255,
      "train_tokens_per_second": 29200.8
    },
    {
      "epoch": 2.86417061213117,
      "grad_norm": 1.5625,
      "learning_rate": 1.65794851540999e-05,
      "loss": 1.0307487487792968,
      "num_input_tokens_seen": 23022766400,
      "step": 80950,
      "train_runtime": 788427.0837,
      "train_tokens_per_second": 29200.882
    },
    {
      "epoch": 2.864524432394899,
      "grad_norm": 1.609375,
      "learning_rate": 1.6578573757708953e-05,
      "loss": 1.038377571105957,
      "num_input_tokens_seen": 23025656960,
      "step": 80960,
      "train_runtime": 788527.1977,
      "train_tokens_per_second": 29200.841
    },
    {
      "epoch": 2.8648782526586274,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6577662511603507e-05,
      "loss": 1.0301566123962402,
      "num_input_tokens_seen": 23028472640,
      "step": 80970,
      "train_runtime": 788622.5905,
      "train_tokens_per_second": 29200.879
    },
    {
      "epoch": 2.8652320729223564,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6576751415742262e-05,
      "loss": 1.0512137413024902,
      "num_input_tokens_seen": 23031304192,
      "step": 80980,
      "train_runtime": 788716.3925,
      "train_tokens_per_second": 29200.996
    },
    {
      "epoch": 2.8655858931860854,
      "grad_norm": 1.640625,
      "learning_rate": 1.6575840470083934e-05,
      "loss": 1.0471799850463868,
      "num_input_tokens_seen": 23034158272,
      "step": 80990,
      "train_runtime": 788813.18,
      "train_tokens_per_second": 29201.031
    },
    {
      "epoch": 2.865939713449814,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6574929674587263e-05,
      "loss": 1.0507784843444825,
      "num_input_tokens_seen": 23037005184,
      "step": 81000,
      "train_runtime": 788911.5043,
      "train_tokens_per_second": 29201.0
    },
    {
      "epoch": 2.8662935337135425,
      "grad_norm": 1.640625,
      "learning_rate": 1.6574019029210995e-05,
      "loss": 1.0329381942749023,
      "num_input_tokens_seen": 23039829248,
      "step": 81010,
      "train_runtime": 789007.4987,
      "train_tokens_per_second": 29201.027
    },
    {
      "epoch": 2.8666473539772714,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6573108533913894e-05,
      "loss": 1.0286808013916016,
      "num_input_tokens_seen": 23042716608,
      "step": 81020,
      "train_runtime": 789108.6973,
      "train_tokens_per_second": 29200.941
    },
    {
      "epoch": 2.8670011742410004,
      "grad_norm": 1.5546875,
      "learning_rate": 1.657219818865474e-05,
      "loss": 1.0306102752685546,
      "num_input_tokens_seen": 23045577920,
      "step": 81030,
      "train_runtime": 789206.6759,
      "train_tokens_per_second": 29200.941
    },
    {
      "epoch": 2.867354994504729,
      "grad_norm": 1.640625,
      "learning_rate": 1.6571287993392336e-05,
      "loss": 1.028251838684082,
      "num_input_tokens_seen": 23048399296,
      "step": 81040,
      "train_runtime": 789302.1543,
      "train_tokens_per_second": 29200.984
    },
    {
      "epoch": 2.867708814768458,
      "grad_norm": 1.71875,
      "learning_rate": 1.6570377948085496e-05,
      "loss": 1.0416295051574707,
      "num_input_tokens_seen": 23051287040,
      "step": 81050,
      "train_runtime": 789400.3118,
      "train_tokens_per_second": 29201.011
    },
    {
      "epoch": 2.8680626350321865,
      "grad_norm": 1.65625,
      "learning_rate": 1.6569468052693042e-05,
      "loss": 1.0420572280883789,
      "num_input_tokens_seen": 23054120704,
      "step": 81060,
      "train_runtime": 789498.0917,
      "train_tokens_per_second": 29200.983
    },
    {
      "epoch": 2.8684164552959155,
      "grad_norm": 1.578125,
      "learning_rate": 1.6568558307173823e-05,
      "loss": 1.0375555992126464,
      "num_input_tokens_seen": 23056946880,
      "step": 81070,
      "train_runtime": 789596.5174,
      "train_tokens_per_second": 29200.923
    },
    {
      "epoch": 2.868770275559644,
      "grad_norm": 1.5703125,
      "learning_rate": 1.65676487114867e-05,
      "loss": 1.0291165351867675,
      "num_input_tokens_seen": 23059841856,
      "step": 81080,
      "train_runtime": 789696.4538,
      "train_tokens_per_second": 29200.893
    },
    {
      "epoch": 2.869124095823373,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6566739265590547e-05,
      "loss": 1.037203598022461,
      "num_input_tokens_seen": 23062668928,
      "step": 81090,
      "train_runtime": 789793.195,
      "train_tokens_per_second": 29200.896
    },
    {
      "epoch": 2.8694779160871016,
      "grad_norm": 1.5703125,
      "learning_rate": 1.656582996944426e-05,
      "loss": 1.035593318939209,
      "num_input_tokens_seen": 23065522304,
      "step": 81100,
      "train_runtime": 789890.5214,
      "train_tokens_per_second": 29200.91
    },
    {
      "epoch": 2.8698317363508306,
      "grad_norm": 1.578125,
      "learning_rate": 1.6564920823006745e-05,
      "loss": 1.0275936126708984,
      "num_input_tokens_seen": 23068403328,
      "step": 81110,
      "train_runtime": 789989.2571,
      "train_tokens_per_second": 29200.908
    },
    {
      "epoch": 2.870185556614559,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6564011826236926e-05,
      "loss": 1.0375207901000976,
      "num_input_tokens_seen": 23071303168,
      "step": 81120,
      "train_runtime": 790090.44,
      "train_tokens_per_second": 29200.838
    },
    {
      "epoch": 2.870539376878288,
      "grad_norm": 1.640625,
      "learning_rate": 1.656310297909374e-05,
      "loss": 1.0457921028137207,
      "num_input_tokens_seen": 23074100224,
      "step": 81130,
      "train_runtime": 790186.1679,
      "train_tokens_per_second": 29200.84
    },
    {
      "epoch": 2.870893197142017,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6562194281536146e-05,
      "loss": 1.045921802520752,
      "num_input_tokens_seen": 23076961088,
      "step": 81140,
      "train_runtime": 790284.2285,
      "train_tokens_per_second": 29200.837
    },
    {
      "epoch": 2.8712470174057456,
      "grad_norm": 1.59375,
      "learning_rate": 1.6561285733523108e-05,
      "loss": 1.044546127319336,
      "num_input_tokens_seen": 23079791232,
      "step": 81150,
      "train_runtime": 790381.4225,
      "train_tokens_per_second": 29200.827
    },
    {
      "epoch": 2.871600837669474,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6560377335013625e-05,
      "loss": 1.027407169342041,
      "num_input_tokens_seen": 23082620160,
      "step": 81160,
      "train_runtime": 790475.9828,
      "train_tokens_per_second": 29200.913
    },
    {
      "epoch": 2.871954657933203,
      "grad_norm": 1.6484375,
      "learning_rate": 1.655946908596669e-05,
      "loss": 1.035403060913086,
      "num_input_tokens_seen": 23085475136,
      "step": 81170,
      "train_runtime": 790575.3234,
      "train_tokens_per_second": 29200.855
    },
    {
      "epoch": 2.872308478196932,
      "grad_norm": 1.7109375,
      "learning_rate": 1.6558560986341324e-05,
      "loss": 1.0394344329833984,
      "num_input_tokens_seen": 23088293056,
      "step": 81180,
      "train_runtime": 790670.5455,
      "train_tokens_per_second": 29200.902
    },
    {
      "epoch": 2.8726622984606607,
      "grad_norm": 1.6875,
      "learning_rate": 1.6557653036096564e-05,
      "loss": 1.0486452102661132,
      "num_input_tokens_seen": 23091135424,
      "step": 81190,
      "train_runtime": 790767.6096,
      "train_tokens_per_second": 29200.912
    },
    {
      "epoch": 2.8730161187243892,
      "grad_norm": 1.625,
      "learning_rate": 1.6556745235191454e-05,
      "loss": 1.0372606277465821,
      "num_input_tokens_seen": 23093985664,
      "step": 81200,
      "train_runtime": 790863.0951,
      "train_tokens_per_second": 29200.99
    },
    {
      "epoch": 2.873369938988118,
      "grad_norm": 1.640625,
      "learning_rate": 1.6555837583585066e-05,
      "loss": 1.0517115592956543,
      "num_input_tokens_seen": 23096877056,
      "step": 81210,
      "train_runtime": 790963.5844,
      "train_tokens_per_second": 29200.936
    },
    {
      "epoch": 2.873723759251847,
      "grad_norm": 1.65625,
      "learning_rate": 1.6554930081236475e-05,
      "loss": 1.0369503021240234,
      "num_input_tokens_seen": 23099723456,
      "step": 81220,
      "train_runtime": 791061.3631,
      "train_tokens_per_second": 29200.925
    },
    {
      "epoch": 2.8740775795155757,
      "grad_norm": 1.59375,
      "learning_rate": 1.6554022728104783e-05,
      "loss": 1.0300237655639648,
      "num_input_tokens_seen": 23102569664,
      "step": 81230,
      "train_runtime": 791159.071,
      "train_tokens_per_second": 29200.916
    },
    {
      "epoch": 2.8744313997793047,
      "grad_norm": 1.6328125,
      "learning_rate": 1.65531155241491e-05,
      "loss": 1.0319210052490235,
      "num_input_tokens_seen": 23105362432,
      "step": 81240,
      "train_runtime": 791252.7274,
      "train_tokens_per_second": 29200.989
    },
    {
      "epoch": 2.8747852200430333,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6552208469328555e-05,
      "loss": 1.0427913665771484,
      "num_input_tokens_seen": 23108133120,
      "step": 81250,
      "train_runtime": 791344.3315,
      "train_tokens_per_second": 29201.11
    },
    {
      "epoch": 2.8751390403067623,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6551301563602294e-05,
      "loss": 1.022377872467041,
      "num_input_tokens_seen": 23110986048,
      "step": 81260,
      "train_runtime": 791443.124,
      "train_tokens_per_second": 29201.07
    },
    {
      "epoch": 2.875492860570491,
      "grad_norm": 1.59375,
      "learning_rate": 1.655039480692947e-05,
      "loss": 1.0495617866516114,
      "num_input_tokens_seen": 23113758464,
      "step": 81270,
      "train_runtime": 791535.4646,
      "train_tokens_per_second": 29201.166
    },
    {
      "epoch": 2.87584668083422,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6549488199269263e-05,
      "loss": 1.0309659957885742,
      "num_input_tokens_seen": 23116559744,
      "step": 81280,
      "train_runtime": 791630.1226,
      "train_tokens_per_second": 29201.213
    },
    {
      "epoch": 2.876200501097949,
      "grad_norm": 1.5859375,
      "learning_rate": 1.654858174058087e-05,
      "loss": 1.0382278442382813,
      "num_input_tokens_seen": 23119414528,
      "step": 81290,
      "train_runtime": 791728.3983,
      "train_tokens_per_second": 29201.194
    },
    {
      "epoch": 2.8765543213616773,
      "grad_norm": 1.640625,
      "learning_rate": 1.6547675430823484e-05,
      "loss": 1.0466912269592286,
      "num_input_tokens_seen": 23122306944,
      "step": 81300,
      "train_runtime": 791827.8095,
      "train_tokens_per_second": 29201.181
    },
    {
      "epoch": 2.876908141625406,
      "grad_norm": 1.5625,
      "learning_rate": 1.6546769269956337e-05,
      "loss": 1.0330430030822755,
      "num_input_tokens_seen": 23125164416,
      "step": 81310,
      "train_runtime": 791927.183,
      "train_tokens_per_second": 29201.125
    },
    {
      "epoch": 2.877261961889135,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6545863257938662e-05,
      "loss": 1.0302630424499513,
      "num_input_tokens_seen": 23128015424,
      "step": 81320,
      "train_runtime": 792023.706,
      "train_tokens_per_second": 29201.166
    },
    {
      "epoch": 2.877615782152864,
      "grad_norm": 1.5859375,
      "learning_rate": 1.654495739472972e-05,
      "loss": 1.0363154411315918,
      "num_input_tokens_seen": 23130818240,
      "step": 81330,
      "train_runtime": 792120.2857,
      "train_tokens_per_second": 29201.144
    },
    {
      "epoch": 2.8779696024165924,
      "grad_norm": 1.59375,
      "learning_rate": 1.654405168028877e-05,
      "loss": 1.0354799270629882,
      "num_input_tokens_seen": 23133666240,
      "step": 81340,
      "train_runtime": 792218.7958,
      "train_tokens_per_second": 29201.108
    },
    {
      "epoch": 2.878323422680321,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6543146114575108e-05,
      "loss": 1.0285295486450194,
      "num_input_tokens_seen": 23136511360,
      "step": 81350,
      "train_runtime": 792315.3986,
      "train_tokens_per_second": 29201.138
    },
    {
      "epoch": 2.87867724294405,
      "grad_norm": 1.546875,
      "learning_rate": 1.6542240697548022e-05,
      "loss": 1.029501247406006,
      "num_input_tokens_seen": 23139309760,
      "step": 81360,
      "train_runtime": 792410.9168,
      "train_tokens_per_second": 29201.15
    },
    {
      "epoch": 2.879031063207779,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6541335429166833e-05,
      "loss": 1.0373859405517578,
      "num_input_tokens_seen": 23142062976,
      "step": 81370,
      "train_runtime": 792501.1835,
      "train_tokens_per_second": 29201.298
    },
    {
      "epoch": 2.8793848834715075,
      "grad_norm": 1.59375,
      "learning_rate": 1.6540430309390877e-05,
      "loss": 1.0180582046508788,
      "num_input_tokens_seen": 23144899776,
      "step": 81380,
      "train_runtime": 792598.5561,
      "train_tokens_per_second": 29201.289
    },
    {
      "epoch": 2.8797387037352364,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6539525338179495e-05,
      "loss": 1.0333572387695313,
      "num_input_tokens_seen": 23147722432,
      "step": 81390,
      "train_runtime": 792696.417,
      "train_tokens_per_second": 29201.245
    },
    {
      "epoch": 2.880092523998965,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6538620515492054e-05,
      "loss": 1.0398573875427246,
      "num_input_tokens_seen": 23150635136,
      "step": 81400,
      "train_runtime": 792800.9877,
      "train_tokens_per_second": 29201.067
    },
    {
      "epoch": 2.880446344262694,
      "grad_norm": 1.59375,
      "learning_rate": 1.6537715841287933e-05,
      "loss": 1.034147357940674,
      "num_input_tokens_seen": 23153445824,
      "step": 81410,
      "train_runtime": 792899.6815,
      "train_tokens_per_second": 29200.978
    },
    {
      "epoch": 2.8808001645264225,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6536811315526516e-05,
      "loss": 1.053011417388916,
      "num_input_tokens_seen": 23156338304,
      "step": 81420,
      "train_runtime": 792999.8637,
      "train_tokens_per_second": 29200.936
    },
    {
      "epoch": 2.8811539847901515,
      "grad_norm": 1.640625,
      "learning_rate": 1.6535906938167223e-05,
      "loss": 1.0440032958984375,
      "num_input_tokens_seen": 23159170432,
      "step": 81430,
      "train_runtime": 793096.9215,
      "train_tokens_per_second": 29200.933
    },
    {
      "epoch": 2.88150780505388,
      "grad_norm": 1.65625,
      "learning_rate": 1.6535002709169474e-05,
      "loss": 1.0418243408203125,
      "num_input_tokens_seen": 23162008640,
      "step": 81440,
      "train_runtime": 793190.4702,
      "train_tokens_per_second": 29201.068
    },
    {
      "epoch": 2.881861625317609,
      "grad_norm": 1.578125,
      "learning_rate": 1.653409862849271e-05,
      "loss": 1.0364418983459474,
      "num_input_tokens_seen": 23164825472,
      "step": 81450,
      "train_runtime": 793287.885,
      "train_tokens_per_second": 29201.033
    },
    {
      "epoch": 2.8822154455813376,
      "grad_norm": 1.578125,
      "learning_rate": 1.653319469609639e-05,
      "loss": 1.0379003524780273,
      "num_input_tokens_seen": 23167639168,
      "step": 81460,
      "train_runtime": 793382.9957,
      "train_tokens_per_second": 29201.079
    },
    {
      "epoch": 2.8825692658450666,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6532290911939978e-05,
      "loss": 1.0384090423583985,
      "num_input_tokens_seen": 23170475456,
      "step": 81470,
      "train_runtime": 793478.9905,
      "train_tokens_per_second": 29201.12
    },
    {
      "epoch": 2.8829230861087956,
      "grad_norm": 1.640625,
      "learning_rate": 1.6531387275982972e-05,
      "loss": 1.0368953704833985,
      "num_input_tokens_seen": 23173259136,
      "step": 81480,
      "train_runtime": 793574.4237,
      "train_tokens_per_second": 29201.116
    },
    {
      "epoch": 2.883276906372524,
      "grad_norm": 1.578125,
      "learning_rate": 1.6530483788184863e-05,
      "loss": 1.0396878242492675,
      "num_input_tokens_seen": 23176068160,
      "step": 81490,
      "train_runtime": 793668.808,
      "train_tokens_per_second": 29201.183
    },
    {
      "epoch": 2.8836307266362526,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6529580448505172e-05,
      "loss": 1.0473644256591796,
      "num_input_tokens_seen": 23178903680,
      "step": 81500,
      "train_runtime": 793764.146,
      "train_tokens_per_second": 29201.248
    },
    {
      "epoch": 2.8839845468999816,
      "grad_norm": 1.609375,
      "learning_rate": 1.6528677256903436e-05,
      "loss": 1.041646957397461,
      "num_input_tokens_seen": 23181723136,
      "step": 81510,
      "train_runtime": 793860.4713,
      "train_tokens_per_second": 29201.256
    },
    {
      "epoch": 2.8843383671637106,
      "grad_norm": 1.59375,
      "learning_rate": 1.6527774213339204e-05,
      "loss": 1.044781494140625,
      "num_input_tokens_seen": 23184502272,
      "step": 81520,
      "train_runtime": 793953.0985,
      "train_tokens_per_second": 29201.35
    },
    {
      "epoch": 2.884692187427439,
      "grad_norm": 1.609375,
      "learning_rate": 1.6526871317772037e-05,
      "loss": 1.0308469772338866,
      "num_input_tokens_seen": 23187387136,
      "step": 81530,
      "train_runtime": 794048.7404,
      "train_tokens_per_second": 29201.466
    },
    {
      "epoch": 2.885046007691168,
      "grad_norm": 1.65625,
      "learning_rate": 1.6525968570161512e-05,
      "loss": 1.0453777313232422,
      "num_input_tokens_seen": 23190172480,
      "step": 81540,
      "train_runtime": 794143.749,
      "train_tokens_per_second": 29201.48
    },
    {
      "epoch": 2.8853998279548967,
      "grad_norm": 1.625,
      "learning_rate": 1.6525065970467236e-05,
      "loss": 1.031926727294922,
      "num_input_tokens_seen": 23193086080,
      "step": 81550,
      "train_runtime": 794247.5797,
      "train_tokens_per_second": 29201.331
    },
    {
      "epoch": 2.8857536482186257,
      "grad_norm": 1.546875,
      "learning_rate": 1.6524163518648803e-05,
      "loss": 1.0329414367675782,
      "num_input_tokens_seen": 23195886528,
      "step": 81560,
      "train_runtime": 794343.0235,
      "train_tokens_per_second": 29201.347
    },
    {
      "epoch": 2.886107468482354,
      "grad_norm": 1.734375,
      "learning_rate": 1.6523261214665855e-05,
      "loss": 1.0284431457519532,
      "num_input_tokens_seen": 23198753536,
      "step": 81570,
      "train_runtime": 794441.2649,
      "train_tokens_per_second": 29201.345
    },
    {
      "epoch": 2.886461288746083,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6522359058478024e-05,
      "loss": 1.036871337890625,
      "num_input_tokens_seen": 23201578240,
      "step": 81580,
      "train_runtime": 794535.4176,
      "train_tokens_per_second": 29201.44
    },
    {
      "epoch": 2.8868151090098118,
      "grad_norm": 1.6171875,
      "learning_rate": 1.652145705004497e-05,
      "loss": 1.0340182304382324,
      "num_input_tokens_seen": 23204418304,
      "step": 81590,
      "train_runtime": 794631.2703,
      "train_tokens_per_second": 29201.492
    },
    {
      "epoch": 2.8871689292735407,
      "grad_norm": 1.6484375,
      "learning_rate": 1.652055518932636e-05,
      "loss": 1.031052589416504,
      "num_input_tokens_seen": 23207239872,
      "step": 81600,
      "train_runtime": 794726.7811,
      "train_tokens_per_second": 29201.532
    },
    {
      "epoch": 2.8875227495372693,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6519653476281895e-05,
      "loss": 1.0439897537231446,
      "num_input_tokens_seen": 23210166912,
      "step": 81610,
      "train_runtime": 794828.0784,
      "train_tokens_per_second": 29201.493
    },
    {
      "epoch": 2.8878765698009983,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6518751910871267e-05,
      "loss": 1.034339714050293,
      "num_input_tokens_seen": 23212979328,
      "step": 81620,
      "train_runtime": 794922.0886,
      "train_tokens_per_second": 29201.578
    },
    {
      "epoch": 2.8882303900647273,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6517850493054192e-05,
      "loss": 1.0341724395751952,
      "num_input_tokens_seen": 23215794752,
      "step": 81630,
      "train_runtime": 795014.5942,
      "train_tokens_per_second": 29201.721
    },
    {
      "epoch": 2.888584210328456,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6516949222790416e-05,
      "loss": 1.0343653678894043,
      "num_input_tokens_seen": 23218609280,
      "step": 81640,
      "train_runtime": 795112.066,
      "train_tokens_per_second": 29201.681
    },
    {
      "epoch": 2.8889380305921843,
      "grad_norm": 1.6796875,
      "learning_rate": 1.651604810003968e-05,
      "loss": 1.043610191345215,
      "num_input_tokens_seen": 23221403840,
      "step": 81650,
      "train_runtime": 795206.3468,
      "train_tokens_per_second": 29201.734
    },
    {
      "epoch": 2.8892918508559133,
      "grad_norm": 1.6875,
      "learning_rate": 1.6515147124761745e-05,
      "loss": 1.0444480895996093,
      "num_input_tokens_seen": 23224249472,
      "step": 81660,
      "train_runtime": 795302.5884,
      "train_tokens_per_second": 29201.778
    },
    {
      "epoch": 2.8896456711196423,
      "grad_norm": 1.59375,
      "learning_rate": 1.6514246296916406e-05,
      "loss": 1.0476489067077637,
      "num_input_tokens_seen": 23227105728,
      "step": 81670,
      "train_runtime": 795399.1364,
      "train_tokens_per_second": 29201.824
    },
    {
      "epoch": 2.889999491383371,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6513345616463443e-05,
      "loss": 1.0399064064025878,
      "num_input_tokens_seen": 23229927488,
      "step": 81680,
      "train_runtime": 795497.0329,
      "train_tokens_per_second": 29201.778
    },
    {
      "epoch": 2.8903533116470994,
      "grad_norm": 1.5859375,
      "learning_rate": 1.651244508336267e-05,
      "loss": 1.0377567291259766,
      "num_input_tokens_seen": 23232781248,
      "step": 81690,
      "train_runtime": 795592.6456,
      "train_tokens_per_second": 29201.855
    },
    {
      "epoch": 2.8907071319108284,
      "grad_norm": 1.5859375,
      "learning_rate": 1.651154469757392e-05,
      "loss": 1.0356073379516602,
      "num_input_tokens_seen": 23235630400,
      "step": 81700,
      "train_runtime": 795688.5258,
      "train_tokens_per_second": 29201.917
    },
    {
      "epoch": 2.8910609521745574,
      "grad_norm": 1.625,
      "learning_rate": 1.6510644459057032e-05,
      "loss": 1.0302897453308106,
      "num_input_tokens_seen": 23238496384,
      "step": 81710,
      "train_runtime": 795786.9858,
      "train_tokens_per_second": 29201.906
    },
    {
      "epoch": 2.891414772438286,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6509744367771856e-05,
      "loss": 1.0419872283935547,
      "num_input_tokens_seen": 23241361984,
      "step": 81720,
      "train_runtime": 795889.8943,
      "train_tokens_per_second": 29201.73
    },
    {
      "epoch": 2.891768592702015,
      "grad_norm": 1.609375,
      "learning_rate": 1.650884442367827e-05,
      "loss": 1.0418277740478517,
      "num_input_tokens_seen": 23244226048,
      "step": 81730,
      "train_runtime": 795987.1105,
      "train_tokens_per_second": 29201.762
    },
    {
      "epoch": 2.8921224129657435,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6507944626736166e-05,
      "loss": 1.0353635787963866,
      "num_input_tokens_seen": 23247043072,
      "step": 81740,
      "train_runtime": 796081.6736,
      "train_tokens_per_second": 29201.832
    },
    {
      "epoch": 2.8924762332294724,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6507044976905436e-05,
      "loss": 1.0370108604431152,
      "num_input_tokens_seen": 23249923328,
      "step": 81750,
      "train_runtime": 796180.8039,
      "train_tokens_per_second": 29201.813
    },
    {
      "epoch": 2.892830053493201,
      "grad_norm": 1.53125,
      "learning_rate": 1.6506145474146002e-05,
      "loss": 1.0417546272277831,
      "num_input_tokens_seen": 23252808448,
      "step": 81760,
      "train_runtime": 796281.1212,
      "train_tokens_per_second": 29201.758
    },
    {
      "epoch": 2.89318387375693,
      "grad_norm": 1.5625,
      "learning_rate": 1.6505246118417803e-05,
      "loss": 1.0345733642578125,
      "num_input_tokens_seen": 23255655424,
      "step": 81770,
      "train_runtime": 796376.6207,
      "train_tokens_per_second": 29201.831
    },
    {
      "epoch": 2.8935376940206585,
      "grad_norm": 1.6015625,
      "learning_rate": 1.650434690968078e-05,
      "loss": 1.0338716506958008,
      "num_input_tokens_seen": 23258495040,
      "step": 81780,
      "train_runtime": 796472.292,
      "train_tokens_per_second": 29201.888
    },
    {
      "epoch": 2.8938915142843875,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6503447847894902e-05,
      "loss": 1.0342218399047851,
      "num_input_tokens_seen": 23261335040,
      "step": 81790,
      "train_runtime": 796567.029,
      "train_tokens_per_second": 29201.981
    },
    {
      "epoch": 2.894245334548116,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6502548933020142e-05,
      "loss": 1.0327499389648438,
      "num_input_tokens_seen": 23264181824,
      "step": 81800,
      "train_runtime": 796664.8247,
      "train_tokens_per_second": 29201.969
    },
    {
      "epoch": 2.894599154811845,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6501650165016504e-05,
      "loss": 1.0299384117126464,
      "num_input_tokens_seen": 23267051008,
      "step": 81810,
      "train_runtime": 796766.7557,
      "train_tokens_per_second": 29201.835
    },
    {
      "epoch": 2.894952975075574,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6500751543843988e-05,
      "loss": 1.038261604309082,
      "num_input_tokens_seen": 23269968704,
      "step": 81820,
      "train_runtime": 796867.6779,
      "train_tokens_per_second": 29201.798
    },
    {
      "epoch": 2.8953067953393026,
      "grad_norm": 1.609375,
      "learning_rate": 1.6499853069462623e-05,
      "loss": 1.0340678215026855,
      "num_input_tokens_seen": 23272819136,
      "step": 81830,
      "train_runtime": 796966.5682,
      "train_tokens_per_second": 29201.751
    },
    {
      "epoch": 2.895660615603031,
      "grad_norm": 1.5078125,
      "learning_rate": 1.649895474183245e-05,
      "loss": 1.0278254508972169,
      "num_input_tokens_seen": 23275730752,
      "step": 81840,
      "train_runtime": 797064.8674,
      "train_tokens_per_second": 29201.802
    },
    {
      "epoch": 2.89601443586676,
      "grad_norm": 1.5859375,
      "learning_rate": 1.649805656091352e-05,
      "loss": 1.0536632537841797,
      "num_input_tokens_seen": 23278545536,
      "step": 81850,
      "train_runtime": 797160.7082,
      "train_tokens_per_second": 29201.823
    },
    {
      "epoch": 2.896368256130489,
      "grad_norm": 1.609375,
      "learning_rate": 1.649715852666591e-05,
      "loss": 1.0208560943603515,
      "num_input_tokens_seen": 23281337024,
      "step": 81860,
      "train_runtime": 797255.521,
      "train_tokens_per_second": 29201.851
    },
    {
      "epoch": 2.8967220763942176,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6496260639049703e-05,
      "loss": 1.034883403778076,
      "num_input_tokens_seen": 23284166976,
      "step": 81870,
      "train_runtime": 797352.6218,
      "train_tokens_per_second": 29201.844
    },
    {
      "epoch": 2.8970758966579466,
      "grad_norm": 1.65625,
      "learning_rate": 1.6495362898024995e-05,
      "loss": 1.0236222267150878,
      "num_input_tokens_seen": 23286988288,
      "step": 81880,
      "train_runtime": 797448.8015,
      "train_tokens_per_second": 29201.86
    },
    {
      "epoch": 2.897429716921675,
      "grad_norm": 1.59375,
      "learning_rate": 1.649446530355191e-05,
      "loss": 1.0408872604370116,
      "num_input_tokens_seen": 23289779840,
      "step": 81890,
      "train_runtime": 797545.2116,
      "train_tokens_per_second": 29201.83
    },
    {
      "epoch": 2.897783537185404,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6493567855590576e-05,
      "loss": 1.0385618209838867,
      "num_input_tokens_seen": 23292648000,
      "step": 81900,
      "train_runtime": 797640.409,
      "train_tokens_per_second": 29201.941
    },
    {
      "epoch": 2.8981373574491327,
      "grad_norm": 1.609375,
      "learning_rate": 1.649267055410114e-05,
      "loss": 1.0398298263549806,
      "num_input_tokens_seen": 23295458304,
      "step": 81910,
      "train_runtime": 797735.1371,
      "train_tokens_per_second": 29201.996
    },
    {
      "epoch": 2.8984911777128617,
      "grad_norm": 1.6015625,
      "learning_rate": 1.649177339904376e-05,
      "loss": 1.0287906646728515,
      "num_input_tokens_seen": 23298307712,
      "step": 81920,
      "train_runtime": 797831.0019,
      "train_tokens_per_second": 29202.059
    },
    {
      "epoch": 2.8988449979765902,
      "grad_norm": 1.6328125,
      "learning_rate": 1.649087639037862e-05,
      "loss": 1.0294256210327148,
      "num_input_tokens_seen": 23301108992,
      "step": 81930,
      "train_runtime": 797923.0489,
      "train_tokens_per_second": 29202.201
    },
    {
      "epoch": 2.899198818240319,
      "grad_norm": 1.625,
      "learning_rate": 1.6489979528065905e-05,
      "loss": 1.0255126953125,
      "num_input_tokens_seen": 23303952384,
      "step": 81940,
      "train_runtime": 798021.2765,
      "train_tokens_per_second": 29202.169
    },
    {
      "epoch": 2.8995526385040478,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6489082812065826e-05,
      "loss": 1.0414183616638184,
      "num_input_tokens_seen": 23306748480,
      "step": 81950,
      "train_runtime": 798117.8849,
      "train_tokens_per_second": 29202.138
    },
    {
      "epoch": 2.8999064587677768,
      "grad_norm": 1.578125,
      "learning_rate": 1.64881862423386e-05,
      "loss": 1.0533702850341797,
      "num_input_tokens_seen": 23309584064,
      "step": 81960,
      "train_runtime": 798213.0109,
      "train_tokens_per_second": 29202.21
    },
    {
      "epoch": 2.9002602790315057,
      "grad_norm": 1.578125,
      "learning_rate": 1.6487289818844477e-05,
      "loss": 1.0271595001220704,
      "num_input_tokens_seen": 23312365312,
      "step": 81970,
      "train_runtime": 798306.3229,
      "train_tokens_per_second": 29202.281
    },
    {
      "epoch": 2.9006140992952343,
      "grad_norm": 1.6796875,
      "learning_rate": 1.6486393541543697e-05,
      "loss": 1.0262845993041991,
      "num_input_tokens_seen": 23315219072,
      "step": 81980,
      "train_runtime": 798409.0664,
      "train_tokens_per_second": 29202.097
    },
    {
      "epoch": 2.900967919558963,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6485497410396535e-05,
      "loss": 1.0358407020568847,
      "num_input_tokens_seen": 23318028480,
      "step": 81990,
      "train_runtime": 798501.6696,
      "train_tokens_per_second": 29202.229
    },
    {
      "epoch": 2.901321739822692,
      "grad_norm": 1.671875,
      "learning_rate": 1.6484601425363267e-05,
      "loss": 1.0435805320739746,
      "num_input_tokens_seen": 23320873664,
      "step": 82000,
      "train_runtime": 798598.9142,
      "train_tokens_per_second": 29202.236
    },
    {
      "epoch": 2.901675560086421,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6483705586404196e-05,
      "loss": 1.034358596801758,
      "num_input_tokens_seen": 23323738368,
      "step": 82010,
      "train_runtime": 798695.2528,
      "train_tokens_per_second": 29202.3
    },
    {
      "epoch": 2.9020293803501493,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6482809893479635e-05,
      "loss": 1.027450942993164,
      "num_input_tokens_seen": 23326582464,
      "step": 82020,
      "train_runtime": 798793.654,
      "train_tokens_per_second": 29202.263
    },
    {
      "epoch": 2.902383200613878,
      "grad_norm": 1.6171875,
      "learning_rate": 1.648191434654991e-05,
      "loss": 1.0448732376098633,
      "num_input_tokens_seen": 23329444608,
      "step": 82030,
      "train_runtime": 798893.0439,
      "train_tokens_per_second": 29202.213
    },
    {
      "epoch": 2.902737020877607,
      "grad_norm": 1.578125,
      "learning_rate": 1.6481018945575367e-05,
      "loss": 1.0368382453918457,
      "num_input_tokens_seen": 23332333568,
      "step": 82040,
      "train_runtime": 798994.7451,
      "train_tokens_per_second": 29202.111
    },
    {
      "epoch": 2.903090841141336,
      "grad_norm": 1.5625,
      "learning_rate": 1.6480123690516364e-05,
      "loss": 1.036186981201172,
      "num_input_tokens_seen": 23335177600,
      "step": 82050,
      "train_runtime": 799093.2528,
      "train_tokens_per_second": 29202.071
    },
    {
      "epoch": 2.9034446614050644,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6479228581333274e-05,
      "loss": 1.0387323379516602,
      "num_input_tokens_seen": 23338055424,
      "step": 82060,
      "train_runtime": 799193.1876,
      "train_tokens_per_second": 29202.02
    },
    {
      "epoch": 2.9037984816687934,
      "grad_norm": 1.65625,
      "learning_rate": 1.647833361798648e-05,
      "loss": 1.0484508514404296,
      "num_input_tokens_seen": 23340829952,
      "step": 82070,
      "train_runtime": 799287.5113,
      "train_tokens_per_second": 29202.045
    },
    {
      "epoch": 2.904152301932522,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6477438800436394e-05,
      "loss": 1.0314799308776856,
      "num_input_tokens_seen": 23343640960,
      "step": 82080,
      "train_runtime": 799381.7614,
      "train_tokens_per_second": 29202.119
    },
    {
      "epoch": 2.904506122196251,
      "grad_norm": 1.625,
      "learning_rate": 1.6476544128643425e-05,
      "loss": 1.0453567504882812,
      "num_input_tokens_seen": 23346495808,
      "step": 82090,
      "train_runtime": 799480.5097,
      "train_tokens_per_second": 29202.083
    },
    {
      "epoch": 2.9048599424599795,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6475649602568016e-05,
      "loss": 1.0362819671630858,
      "num_input_tokens_seen": 23349385728,
      "step": 82100,
      "train_runtime": 799583.8589,
      "train_tokens_per_second": 29201.922
    },
    {
      "epoch": 2.9052137627237085,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6474755222170613e-05,
      "loss": 1.0411346435546875,
      "num_input_tokens_seen": 23352194688,
      "step": 82110,
      "train_runtime": 799679.6278,
      "train_tokens_per_second": 29201.938
    },
    {
      "epoch": 2.905567582987437,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6473860987411676e-05,
      "loss": 1.0373552322387696,
      "num_input_tokens_seen": 23355018176,
      "step": 82120,
      "train_runtime": 799775.453,
      "train_tokens_per_second": 29201.969
    },
    {
      "epoch": 2.905921403251166,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6472966898251688e-05,
      "loss": 1.0439065933227538,
      "num_input_tokens_seen": 23357856768,
      "step": 82130,
      "train_runtime": 799871.2319,
      "train_tokens_per_second": 29202.021
    },
    {
      "epoch": 2.9062752235148945,
      "grad_norm": 1.625,
      "learning_rate": 1.647207295465114e-05,
      "loss": 1.034780502319336,
      "num_input_tokens_seen": 23360679424,
      "step": 82140,
      "train_runtime": 799966.7541,
      "train_tokens_per_second": 29202.063
    },
    {
      "epoch": 2.9066290437786235,
      "grad_norm": 1.5390625,
      "learning_rate": 1.647117915657054e-05,
      "loss": 1.0428266525268555,
      "num_input_tokens_seen": 23363557888,
      "step": 82150,
      "train_runtime": 800064.5954,
      "train_tokens_per_second": 29202.089
    },
    {
      "epoch": 2.9069828640423525,
      "grad_norm": 1.5625,
      "learning_rate": 1.6470285503970414e-05,
      "loss": 1.049283790588379,
      "num_input_tokens_seen": 23366426304,
      "step": 82160,
      "train_runtime": 800166.0149,
      "train_tokens_per_second": 29201.973
    },
    {
      "epoch": 2.907336684306081,
      "grad_norm": 1.6171875,
      "learning_rate": 1.64693919968113e-05,
      "loss": 1.0376446723937989,
      "num_input_tokens_seen": 23369299520,
      "step": 82170,
      "train_runtime": 800266.476,
      "train_tokens_per_second": 29201.897
    },
    {
      "epoch": 2.9076905045698096,
      "grad_norm": 1.59375,
      "learning_rate": 1.646849863505375e-05,
      "loss": 1.0471147537231444,
      "num_input_tokens_seen": 23372104064,
      "step": 82180,
      "train_runtime": 800362.1654,
      "train_tokens_per_second": 29201.91
    },
    {
      "epoch": 2.9080443248335386,
      "grad_norm": 1.546875,
      "learning_rate": 1.646760541865834e-05,
      "loss": 1.038701629638672,
      "num_input_tokens_seen": 23374971840,
      "step": 82190,
      "train_runtime": 800459.4958,
      "train_tokens_per_second": 29201.942
    },
    {
      "epoch": 2.9083981450972676,
      "grad_norm": 1.59375,
      "learning_rate": 1.6466712347585644e-05,
      "loss": 1.0466977119445802,
      "num_input_tokens_seen": 23377801472,
      "step": 82200,
      "train_runtime": 800555.7725,
      "train_tokens_per_second": 29201.965
    },
    {
      "epoch": 2.908751965360996,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6465819421796264e-05,
      "loss": 1.0389780044555663,
      "num_input_tokens_seen": 23380662528,
      "step": 82210,
      "train_runtime": 800656.0313,
      "train_tokens_per_second": 29201.881
    },
    {
      "epoch": 2.909105785624725,
      "grad_norm": 1.5625,
      "learning_rate": 1.6464926641250812e-05,
      "loss": 1.0378755569458007,
      "num_input_tokens_seen": 23383518848,
      "step": 82220,
      "train_runtime": 800754.7439,
      "train_tokens_per_second": 29201.849
    },
    {
      "epoch": 2.9094596058884536,
      "grad_norm": 1.6171875,
      "learning_rate": 1.646403400590992e-05,
      "loss": 1.0260343551635742,
      "num_input_tokens_seen": 23386361024,
      "step": 82230,
      "train_runtime": 800850.959,
      "train_tokens_per_second": 29201.889
    },
    {
      "epoch": 2.9098134261521826,
      "grad_norm": 1.59375,
      "learning_rate": 1.6463141515734232e-05,
      "loss": 1.0451658248901368,
      "num_input_tokens_seen": 23389224576,
      "step": 82240,
      "train_runtime": 800951.0361,
      "train_tokens_per_second": 29201.816
    },
    {
      "epoch": 2.910167246415911,
      "grad_norm": 1.703125,
      "learning_rate": 1.6462249170684403e-05,
      "loss": 1.042930793762207,
      "num_input_tokens_seen": 23392087744,
      "step": 82250,
      "train_runtime": 801048.7298,
      "train_tokens_per_second": 29201.829
    },
    {
      "epoch": 2.91052106667964,
      "grad_norm": 1.6796875,
      "learning_rate": 1.6461356970721107e-05,
      "loss": 1.0268678665161133,
      "num_input_tokens_seen": 23394902336,
      "step": 82260,
      "train_runtime": 801143.1698,
      "train_tokens_per_second": 29201.9
    },
    {
      "epoch": 2.9108748869433687,
      "grad_norm": 1.6640625,
      "learning_rate": 1.646046491580503e-05,
      "loss": 1.0245210647583007,
      "num_input_tokens_seen": 23397752896,
      "step": 82270,
      "train_runtime": 801240.8077,
      "train_tokens_per_second": 29201.899
    },
    {
      "epoch": 2.9112287072070977,
      "grad_norm": 1.6640625,
      "learning_rate": 1.645957300589688e-05,
      "loss": 1.0315054893493651,
      "num_input_tokens_seen": 23400557440,
      "step": 82280,
      "train_runtime": 801338.2876,
      "train_tokens_per_second": 29201.846
    },
    {
      "epoch": 2.9115825274708262,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6458681240957374e-05,
      "loss": 1.0308526039123536,
      "num_input_tokens_seen": 23403410944,
      "step": 82290,
      "train_runtime": 801436.2181,
      "train_tokens_per_second": 29201.838
    },
    {
      "epoch": 2.9119363477345552,
      "grad_norm": 1.5859375,
      "learning_rate": 1.645778962094724e-05,
      "loss": 1.0425003051757813,
      "num_input_tokens_seen": 23406277184,
      "step": 82300,
      "train_runtime": 801535.2022,
      "train_tokens_per_second": 29201.808
    },
    {
      "epoch": 2.912290167998284,
      "grad_norm": 1.546875,
      "learning_rate": 1.645689814582723e-05,
      "loss": 1.0414790153503417,
      "num_input_tokens_seen": 23409114752,
      "step": 82310,
      "train_runtime": 801632.7168,
      "train_tokens_per_second": 29201.796
    },
    {
      "epoch": 2.9126439882620128,
      "grad_norm": 1.6328125,
      "learning_rate": 1.645600681555811e-05,
      "loss": 1.0364343643188476,
      "num_input_tokens_seen": 23411988544,
      "step": 82320,
      "train_runtime": 801733.3433,
      "train_tokens_per_second": 29201.715
    },
    {
      "epoch": 2.9129978085257413,
      "grad_norm": 1.5703125,
      "learning_rate": 1.645511563010065e-05,
      "loss": 1.0193931579589843,
      "num_input_tokens_seen": 23414833600,
      "step": 82330,
      "train_runtime": 801828.0123,
      "train_tokens_per_second": 29201.815
    },
    {
      "epoch": 2.9133516287894703,
      "grad_norm": 1.6796875,
      "learning_rate": 1.6454224589415647e-05,
      "loss": 1.0287192344665528,
      "num_input_tokens_seen": 23417700224,
      "step": 82340,
      "train_runtime": 801931.2084,
      "train_tokens_per_second": 29201.632
    },
    {
      "epoch": 2.9137054490531993,
      "grad_norm": 1.5625,
      "learning_rate": 1.6453333693463906e-05,
      "loss": 1.0384401321411132,
      "num_input_tokens_seen": 23420516672,
      "step": 82350,
      "train_runtime": 802026.9148,
      "train_tokens_per_second": 29201.659
    },
    {
      "epoch": 2.914059269316928,
      "grad_norm": 1.59375,
      "learning_rate": 1.645244294220625e-05,
      "loss": 1.0306867599487304,
      "num_input_tokens_seen": 23423308992,
      "step": 82360,
      "train_runtime": 802121.1385,
      "train_tokens_per_second": 29201.71
    },
    {
      "epoch": 2.914413089580657,
      "grad_norm": 1.6640625,
      "learning_rate": 1.645155233560352e-05,
      "loss": 1.0426767349243165,
      "num_input_tokens_seen": 23426087808,
      "step": 82370,
      "train_runtime": 802215.0333,
      "train_tokens_per_second": 29201.756
    },
    {
      "epoch": 2.9147669098443854,
      "grad_norm": 1.609375,
      "learning_rate": 1.645066187361656e-05,
      "loss": 1.0385237693786622,
      "num_input_tokens_seen": 23428857280,
      "step": 82380,
      "train_runtime": 802308.4974,
      "train_tokens_per_second": 29201.806
    },
    {
      "epoch": 2.9151207301081143,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6449771556206242e-05,
      "loss": 1.0501800537109376,
      "num_input_tokens_seen": 23431687424,
      "step": 82390,
      "train_runtime": 802407.3446,
      "train_tokens_per_second": 29201.736
    },
    {
      "epoch": 2.915474550371843,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6448881383333446e-05,
      "loss": 1.03688325881958,
      "num_input_tokens_seen": 23434521024,
      "step": 82400,
      "train_runtime": 802501.599,
      "train_tokens_per_second": 29201.837
    },
    {
      "epoch": 2.915828370635572,
      "grad_norm": 1.65625,
      "learning_rate": 1.644799135495907e-05,
      "loss": 1.037541389465332,
      "num_input_tokens_seen": 23437367872,
      "step": 82410,
      "train_runtime": 802600.4116,
      "train_tokens_per_second": 29201.789
    },
    {
      "epoch": 2.9161821908993004,
      "grad_norm": 1.5703125,
      "learning_rate": 1.644710147104402e-05,
      "loss": 1.0276203155517578,
      "num_input_tokens_seen": 23440213440,
      "step": 82420,
      "train_runtime": 802699.8237,
      "train_tokens_per_second": 29201.717
    },
    {
      "epoch": 2.9165360111630294,
      "grad_norm": 1.578125,
      "learning_rate": 1.644621173154923e-05,
      "loss": 1.0274230003356934,
      "num_input_tokens_seen": 23443040192,
      "step": 82430,
      "train_runtime": 802797.0822,
      "train_tokens_per_second": 29201.701
    },
    {
      "epoch": 2.916889831426758,
      "grad_norm": 1.5625,
      "learning_rate": 1.6445322136435636e-05,
      "loss": 1.027376365661621,
      "num_input_tokens_seen": 23445897728,
      "step": 82440,
      "train_runtime": 802894.815,
      "train_tokens_per_second": 29201.705
    },
    {
      "epoch": 2.917243651690487,
      "grad_norm": 1.5703125,
      "learning_rate": 1.644443268566419e-05,
      "loss": 1.0313352584838866,
      "num_input_tokens_seen": 23448717952,
      "step": 82450,
      "train_runtime": 802989.9098,
      "train_tokens_per_second": 29201.759
    },
    {
      "epoch": 2.917597471954216,
      "grad_norm": 1.59375,
      "learning_rate": 1.6443543379195868e-05,
      "loss": 1.0223358154296875,
      "num_input_tokens_seen": 23451563712,
      "step": 82460,
      "train_runtime": 803087.281,
      "train_tokens_per_second": 29201.762
    },
    {
      "epoch": 2.9179512922179445,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6442654216991655e-05,
      "loss": 1.0424938201904297,
      "num_input_tokens_seen": 23454397248,
      "step": 82470,
      "train_runtime": 803183.9498,
      "train_tokens_per_second": 29201.775
    },
    {
      "epoch": 2.918305112481673,
      "grad_norm": 1.59375,
      "learning_rate": 1.6441765199012542e-05,
      "loss": 1.0375866889953613,
      "num_input_tokens_seen": 23457219136,
      "step": 82480,
      "train_runtime": 803279.1174,
      "train_tokens_per_second": 29201.829
    },
    {
      "epoch": 2.918658932745402,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6440876325219555e-05,
      "loss": 1.0376762390136718,
      "num_input_tokens_seen": 23460053376,
      "step": 82490,
      "train_runtime": 803377.8722,
      "train_tokens_per_second": 29201.767
    },
    {
      "epoch": 2.919012753009131,
      "grad_norm": 1.671875,
      "learning_rate": 1.643998759557372e-05,
      "loss": 1.0407905578613281,
      "num_input_tokens_seen": 23462918400,
      "step": 82500,
      "train_runtime": 803478.4591,
      "train_tokens_per_second": 29201.677
    },
    {
      "epoch": 2.9193665732728595,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6439099010036077e-05,
      "loss": 1.0334360122680664,
      "num_input_tokens_seen": 23465773888,
      "step": 82510,
      "train_runtime": 803579.0367,
      "train_tokens_per_second": 29201.575
    },
    {
      "epoch": 2.919720393536588,
      "grad_norm": 1.6171875,
      "learning_rate": 1.643821056856769e-05,
      "loss": 1.043668556213379,
      "num_input_tokens_seen": 23468648320,
      "step": 82520,
      "train_runtime": 803677.4092,
      "train_tokens_per_second": 29201.578
    },
    {
      "epoch": 2.920074213800317,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6437322271129625e-05,
      "loss": 1.037771224975586,
      "num_input_tokens_seen": 23471500992,
      "step": 82530,
      "train_runtime": 803777.4924,
      "train_tokens_per_second": 29201.491
    },
    {
      "epoch": 2.920428034064046,
      "grad_norm": 1.578125,
      "learning_rate": 1.6436434117682977e-05,
      "loss": 1.0240306854248047,
      "num_input_tokens_seen": 23474317632,
      "step": 82540,
      "train_runtime": 803873.6207,
      "train_tokens_per_second": 29201.503
    },
    {
      "epoch": 2.9207818543277746,
      "grad_norm": 1.640625,
      "learning_rate": 1.643554610818885e-05,
      "loss": 1.0379066467285156,
      "num_input_tokens_seen": 23477154112,
      "step": 82550,
      "train_runtime": 803971.1754,
      "train_tokens_per_second": 29201.487
    },
    {
      "epoch": 2.9211356745915036,
      "grad_norm": 1.640625,
      "learning_rate": 1.6434658242608358e-05,
      "loss": 1.0424989700317382,
      "num_input_tokens_seen": 23479999040,
      "step": 82560,
      "train_runtime": 804069.373,
      "train_tokens_per_second": 29201.459
    },
    {
      "epoch": 2.921489494855232,
      "grad_norm": 1.609375,
      "learning_rate": 1.6433770520902633e-05,
      "loss": 1.0274450302124023,
      "num_input_tokens_seen": 23482883584,
      "step": 82570,
      "train_runtime": 804166.5287,
      "train_tokens_per_second": 29201.518
    },
    {
      "epoch": 2.921843315118961,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6432882943032823e-05,
      "loss": 1.0244965553283691,
      "num_input_tokens_seen": 23485719744,
      "step": 82580,
      "train_runtime": 804263.4444,
      "train_tokens_per_second": 29201.526
    },
    {
      "epoch": 2.9221971353826897,
      "grad_norm": 1.59375,
      "learning_rate": 1.643199550896009e-05,
      "loss": 1.0335446357727052,
      "num_input_tokens_seen": 23488491712,
      "step": 82590,
      "train_runtime": 804356.1855,
      "train_tokens_per_second": 29201.605
    },
    {
      "epoch": 2.9225509556464186,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6431108218645612e-05,
      "loss": 1.0197903633117675,
      "num_input_tokens_seen": 23491391424,
      "step": 82600,
      "train_runtime": 804457.2417,
      "train_tokens_per_second": 29201.541
    },
    {
      "epoch": 2.922904775910147,
      "grad_norm": 1.6171875,
      "learning_rate": 1.643022107205058e-05,
      "loss": 1.0353784561157227,
      "num_input_tokens_seen": 23494246912,
      "step": 82610,
      "train_runtime": 804557.2295,
      "train_tokens_per_second": 29201.461
    },
    {
      "epoch": 2.923258596173876,
      "grad_norm": 1.640625,
      "learning_rate": 1.6429334069136193e-05,
      "loss": 1.0300652503967285,
      "num_input_tokens_seen": 23497134400,
      "step": 82620,
      "train_runtime": 804656.2261,
      "train_tokens_per_second": 29201.457
    },
    {
      "epoch": 2.9236124164376047,
      "grad_norm": 1.5546875,
      "learning_rate": 1.642844720986368e-05,
      "loss": 1.0273927688598632,
      "num_input_tokens_seen": 23499930368,
      "step": 82630,
      "train_runtime": 804749.3238,
      "train_tokens_per_second": 29201.553
    },
    {
      "epoch": 2.9239662367013337,
      "grad_norm": 1.6015625,
      "learning_rate": 1.642756049419427e-05,
      "loss": 1.0347605705261231,
      "num_input_tokens_seen": 23502771072,
      "step": 82640,
      "train_runtime": 804845.6019,
      "train_tokens_per_second": 29201.59
    },
    {
      "epoch": 2.9243200569650627,
      "grad_norm": 1.65625,
      "learning_rate": 1.6426673922089217e-05,
      "loss": 1.04333553314209,
      "num_input_tokens_seen": 23505573696,
      "step": 82650,
      "train_runtime": 804939.8628,
      "train_tokens_per_second": 29201.652
    },
    {
      "epoch": 2.9246738772287912,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6425787493509783e-05,
      "loss": 1.028804874420166,
      "num_input_tokens_seen": 23508397952,
      "step": 82660,
      "train_runtime": 805036.7898,
      "train_tokens_per_second": 29201.644
    },
    {
      "epoch": 2.92502769749252,
      "grad_norm": 1.5859375,
      "learning_rate": 1.642490120841725e-05,
      "loss": 1.0479217529296876,
      "num_input_tokens_seen": 23511237120,
      "step": 82670,
      "train_runtime": 805134.0633,
      "train_tokens_per_second": 29201.643
    },
    {
      "epoch": 2.9253815177562488,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6424015066772907e-05,
      "loss": 1.0232019424438477,
      "num_input_tokens_seen": 23514068032,
      "step": 82680,
      "train_runtime": 805229.8037,
      "train_tokens_per_second": 29201.686
    },
    {
      "epoch": 2.9257353380199778,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6423129068538065e-05,
      "loss": 1.04473819732666,
      "num_input_tokens_seen": 23516875840,
      "step": 82690,
      "train_runtime": 805322.6391,
      "train_tokens_per_second": 29201.806
    },
    {
      "epoch": 2.9260891582837063,
      "grad_norm": 1.625,
      "learning_rate": 1.642224321367405e-05,
      "loss": 1.028672981262207,
      "num_input_tokens_seen": 23519660288,
      "step": 82700,
      "train_runtime": 805419.5846,
      "train_tokens_per_second": 29201.749
    },
    {
      "epoch": 2.9264429785474353,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6421357502142192e-05,
      "loss": 1.031590175628662,
      "num_input_tokens_seen": 23522507648,
      "step": 82710,
      "train_runtime": 805518.8437,
      "train_tokens_per_second": 29201.685
    },
    {
      "epoch": 2.926796798811164,
      "grad_norm": 1.65625,
      "learning_rate": 1.6420471933903847e-05,
      "loss": 1.0406122207641602,
      "num_input_tokens_seen": 23525359104,
      "step": 82720,
      "train_runtime": 805616.9574,
      "train_tokens_per_second": 29201.668
    },
    {
      "epoch": 2.927150619074893,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6419586508920383e-05,
      "loss": 1.0263463020324708,
      "num_input_tokens_seen": 23528215360,
      "step": 82730,
      "train_runtime": 805714.642,
      "train_tokens_per_second": 29201.673
    },
    {
      "epoch": 2.9275044393386214,
      "grad_norm": 1.59375,
      "learning_rate": 1.641870122715318e-05,
      "loss": 1.0184555053710938,
      "num_input_tokens_seen": 23531081984,
      "step": 82740,
      "train_runtime": 805813.8614,
      "train_tokens_per_second": 29201.635
    },
    {
      "epoch": 2.9278582596023504,
      "grad_norm": 1.7109375,
      "learning_rate": 1.641781608856363e-05,
      "loss": 1.038747787475586,
      "num_input_tokens_seen": 23533993408,
      "step": 82750,
      "train_runtime": 805918.4707,
      "train_tokens_per_second": 29201.457
    },
    {
      "epoch": 2.928212079866079,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6416931093113156e-05,
      "loss": 1.022183895111084,
      "num_input_tokens_seen": 23536830208,
      "step": 82760,
      "train_runtime": 806016.3323,
      "train_tokens_per_second": 29201.431
    },
    {
      "epoch": 2.928565900129808,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6416046240763165e-05,
      "loss": 1.0428789138793946,
      "num_input_tokens_seen": 23539626496,
      "step": 82770,
      "train_runtime": 806110.7673,
      "train_tokens_per_second": 29201.479
    },
    {
      "epoch": 2.9289197203935364,
      "grad_norm": 1.6953125,
      "learning_rate": 1.641516153147511e-05,
      "loss": 1.0486883163452148,
      "num_input_tokens_seen": 23542492032,
      "step": 82780,
      "train_runtime": 806209.4407,
      "train_tokens_per_second": 29201.459
    },
    {
      "epoch": 2.9292735406572654,
      "grad_norm": 1.625,
      "learning_rate": 1.6414276965210436e-05,
      "loss": 1.0230631828308105,
      "num_input_tokens_seen": 23545410752,
      "step": 82790,
      "train_runtime": 806308.9349,
      "train_tokens_per_second": 29201.476
    },
    {
      "epoch": 2.9296273609209944,
      "grad_norm": 1.59375,
      "learning_rate": 1.641339254193062e-05,
      "loss": 1.023196315765381,
      "num_input_tokens_seen": 23548268608,
      "step": 82800,
      "train_runtime": 806407.8321,
      "train_tokens_per_second": 29201.438
    },
    {
      "epoch": 2.929981181184723,
      "grad_norm": 1.609375,
      "learning_rate": 1.6412508261597135e-05,
      "loss": 1.0337226867675782,
      "num_input_tokens_seen": 23551140928,
      "step": 82810,
      "train_runtime": 806506.7116,
      "train_tokens_per_second": 29201.42
    },
    {
      "epoch": 2.9303350014484515,
      "grad_norm": 1.609375,
      "learning_rate": 1.641162412417149e-05,
      "loss": 1.0280645370483399,
      "num_input_tokens_seen": 23554037248,
      "step": 82820,
      "train_runtime": 806606.2958,
      "train_tokens_per_second": 29201.405
    },
    {
      "epoch": 2.9306888217121805,
      "grad_norm": 1.5390625,
      "learning_rate": 1.641074012961519e-05,
      "loss": 1.0302412986755372,
      "num_input_tokens_seen": 23556947584,
      "step": 82830,
      "train_runtime": 806708.2653,
      "train_tokens_per_second": 29201.322
    },
    {
      "epoch": 2.9310426419759095,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6409856277889765e-05,
      "loss": 1.0429987907409668,
      "num_input_tokens_seen": 23559806400,
      "step": 82840,
      "train_runtime": 806803.9229,
      "train_tokens_per_second": 29201.403
    },
    {
      "epoch": 2.931396462239638,
      "grad_norm": 1.7578125,
      "learning_rate": 1.6408972568956752e-05,
      "loss": 1.0425691604614258,
      "num_input_tokens_seen": 23562656192,
      "step": 82850,
      "train_runtime": 806902.3325,
      "train_tokens_per_second": 29201.373
    },
    {
      "epoch": 2.9317502825033666,
      "grad_norm": 1.625,
      "learning_rate": 1.640808900277771e-05,
      "loss": 1.0348703384399414,
      "num_input_tokens_seen": 23565470976,
      "step": 82860,
      "train_runtime": 806999.3286,
      "train_tokens_per_second": 29201.351
    },
    {
      "epoch": 2.9321041027670955,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6407205579314206e-05,
      "loss": 1.049706268310547,
      "num_input_tokens_seen": 23568335808,
      "step": 82870,
      "train_runtime": 807097.7969,
      "train_tokens_per_second": 29201.338
    },
    {
      "epoch": 2.9324579230308245,
      "grad_norm": 1.609375,
      "learning_rate": 1.640632229852783e-05,
      "loss": 1.0388547897338867,
      "num_input_tokens_seen": 23571196224,
      "step": 82880,
      "train_runtime": 807198.328,
      "train_tokens_per_second": 29201.245
    },
    {
      "epoch": 2.932811743294553,
      "grad_norm": 1.59375,
      "learning_rate": 1.6405439160380177e-05,
      "loss": 1.039502239227295,
      "num_input_tokens_seen": 23574055680,
      "step": 82890,
      "train_runtime": 807298.0631,
      "train_tokens_per_second": 29201.18
    },
    {
      "epoch": 2.933165563558282,
      "grad_norm": 1.6171875,
      "learning_rate": 1.640455616483286e-05,
      "loss": 1.0378055572509766,
      "num_input_tokens_seen": 23576903680,
      "step": 82900,
      "train_runtime": 807394.3625,
      "train_tokens_per_second": 29201.224
    },
    {
      "epoch": 2.9335193838220106,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6403673311847505e-05,
      "loss": 1.0379903793334961,
      "num_input_tokens_seen": 23579735552,
      "step": 82910,
      "train_runtime": 807488.9517,
      "train_tokens_per_second": 29201.31
    },
    {
      "epoch": 2.9338732040857396,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6402790601385763e-05,
      "loss": 1.0442813873291015,
      "num_input_tokens_seen": 23582601088,
      "step": 82920,
      "train_runtime": 807585.7718,
      "train_tokens_per_second": 29201.358
    },
    {
      "epoch": 2.934227024349468,
      "grad_norm": 1.65625,
      "learning_rate": 1.6401908033409285e-05,
      "loss": 1.0352426528930665,
      "num_input_tokens_seen": 23585431296,
      "step": 82930,
      "train_runtime": 807679.4303,
      "train_tokens_per_second": 29201.476
    },
    {
      "epoch": 2.934580844613197,
      "grad_norm": 1.6015625,
      "learning_rate": 1.640102560787974e-05,
      "loss": 1.0472219467163086,
      "num_input_tokens_seen": 23588249344,
      "step": 82940,
      "train_runtime": 807777.2876,
      "train_tokens_per_second": 29201.427
    },
    {
      "epoch": 2.9349346648769257,
      "grad_norm": 1.6484375,
      "learning_rate": 1.640014332475882e-05,
      "loss": 1.0261850357055664,
      "num_input_tokens_seen": 23591092352,
      "step": 82950,
      "train_runtime": 807873.5082,
      "train_tokens_per_second": 29201.468
    },
    {
      "epoch": 2.9352884851406547,
      "grad_norm": 1.5859375,
      "learning_rate": 1.639926118400822e-05,
      "loss": 1.0508545875549316,
      "num_input_tokens_seen": 23593946496,
      "step": 82960,
      "train_runtime": 807971.2623,
      "train_tokens_per_second": 29201.467
    },
    {
      "epoch": 2.935642305404383,
      "grad_norm": 1.59375,
      "learning_rate": 1.6398379185589653e-05,
      "loss": 1.0354289054870605,
      "num_input_tokens_seen": 23596771136,
      "step": 82970,
      "train_runtime": 808067.6675,
      "train_tokens_per_second": 29201.479
    },
    {
      "epoch": 2.935996125668112,
      "grad_norm": 1.640625,
      "learning_rate": 1.6397497329464858e-05,
      "loss": 1.0426487922668457,
      "num_input_tokens_seen": 23599582208,
      "step": 82980,
      "train_runtime": 808165.4333,
      "train_tokens_per_second": 29201.425
    },
    {
      "epoch": 2.936349945931841,
      "grad_norm": 1.6328125,
      "learning_rate": 1.639661561559557e-05,
      "loss": 1.039994716644287,
      "num_input_tokens_seen": 23602429056,
      "step": 82990,
      "train_runtime": 808266.1608,
      "train_tokens_per_second": 29201.308
    },
    {
      "epoch": 2.9367037661955697,
      "grad_norm": 1.5390625,
      "learning_rate": 1.639573404394355e-05,
      "loss": 1.0282909393310546,
      "num_input_tokens_seen": 23605236096,
      "step": 83000,
      "train_runtime": 808360.6589,
      "train_tokens_per_second": 29201.367
    },
    {
      "epoch": 2.9370575864592983,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6394852614470568e-05,
      "loss": 1.0318000793457032,
      "num_input_tokens_seen": 23608039360,
      "step": 83010,
      "train_runtime": 808455.231,
      "train_tokens_per_second": 29201.418
    },
    {
      "epoch": 2.9374114067230273,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6393971327138412e-05,
      "loss": 1.0403034210205078,
      "num_input_tokens_seen": 23610894848,
      "step": 83020,
      "train_runtime": 808553.1459,
      "train_tokens_per_second": 29201.414
    },
    {
      "epoch": 2.9377652269867562,
      "grad_norm": 1.5859375,
      "learning_rate": 1.639309018190888e-05,
      "loss": 1.0262086868286133,
      "num_input_tokens_seen": 23613715840,
      "step": 83030,
      "train_runtime": 808651.3124,
      "train_tokens_per_second": 29201.357
    },
    {
      "epoch": 2.938119047250485,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6392209178743793e-05,
      "loss": 1.0176182746887208,
      "num_input_tokens_seen": 23616599040,
      "step": 83040,
      "train_runtime": 808750.7229,
      "train_tokens_per_second": 29201.333
    },
    {
      "epoch": 2.9384728675142138,
      "grad_norm": 1.59375,
      "learning_rate": 1.639132831760497e-05,
      "loss": 1.050097370147705,
      "num_input_tokens_seen": 23619449024,
      "step": 83050,
      "train_runtime": 808847.4093,
      "train_tokens_per_second": 29201.366
    },
    {
      "epoch": 2.9388266877779423,
      "grad_norm": 1.546875,
      "learning_rate": 1.6390447598454276e-05,
      "loss": 1.041276741027832,
      "num_input_tokens_seen": 23622251072,
      "step": 83060,
      "train_runtime": 808939.7425,
      "train_tokens_per_second": 29201.497
    },
    {
      "epoch": 2.9391805080416713,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6389567021253547e-05,
      "loss": 1.0392881393432618,
      "num_input_tokens_seen": 23625106624,
      "step": 83070,
      "train_runtime": 809034.3986,
      "train_tokens_per_second": 29201.61
    },
    {
      "epoch": 2.9395343283054,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6388686585964667e-05,
      "loss": 1.0344202041625976,
      "num_input_tokens_seen": 23627990528,
      "step": 83080,
      "train_runtime": 809135.1449,
      "train_tokens_per_second": 29201.538
    },
    {
      "epoch": 2.939888148569129,
      "grad_norm": 1.640625,
      "learning_rate": 1.6387806292549522e-05,
      "loss": 1.0498573303222656,
      "num_input_tokens_seen": 23630893568,
      "step": 83090,
      "train_runtime": 809236.0622,
      "train_tokens_per_second": 29201.484
    },
    {
      "epoch": 2.9402419688328574,
      "grad_norm": 1.5234375,
      "learning_rate": 1.6386926140970015e-05,
      "loss": 1.0250654220581055,
      "num_input_tokens_seen": 23633754176,
      "step": 83100,
      "train_runtime": 809333.2534,
      "train_tokens_per_second": 29201.511
    },
    {
      "epoch": 2.9405957890965864,
      "grad_norm": 1.65625,
      "learning_rate": 1.6386046131188054e-05,
      "loss": 1.0363791465759278,
      "num_input_tokens_seen": 23636573824,
      "step": 83110,
      "train_runtime": 809428.2446,
      "train_tokens_per_second": 29201.568
    },
    {
      "epoch": 2.940949609360315,
      "grad_norm": 1.640625,
      "learning_rate": 1.638516626316558e-05,
      "loss": 1.032752227783203,
      "num_input_tokens_seen": 23639506816,
      "step": 83120,
      "train_runtime": 809531.7466,
      "train_tokens_per_second": 29201.457
    },
    {
      "epoch": 2.941303429624044,
      "grad_norm": 1.609375,
      "learning_rate": 1.6384286536864525e-05,
      "loss": 1.033646583557129,
      "num_input_tokens_seen": 23642375104,
      "step": 83130,
      "train_runtime": 809630.7281,
      "train_tokens_per_second": 29201.43
    },
    {
      "epoch": 2.941657249887773,
      "grad_norm": 1.6796875,
      "learning_rate": 1.6383406952246856e-05,
      "loss": 1.031043815612793,
      "num_input_tokens_seen": 23645265600,
      "step": 83140,
      "train_runtime": 809732.7498,
      "train_tokens_per_second": 29201.321
    },
    {
      "epoch": 2.9420110701515014,
      "grad_norm": 1.6015625,
      "learning_rate": 1.638252750927455e-05,
      "loss": 1.0491025924682618,
      "num_input_tokens_seen": 23648169152,
      "step": 83150,
      "train_runtime": 809836.1244,
      "train_tokens_per_second": 29201.178
    },
    {
      "epoch": 2.94236489041523,
      "grad_norm": 1.640625,
      "learning_rate": 1.6381648207909584e-05,
      "loss": 1.035498046875,
      "num_input_tokens_seen": 23651006656,
      "step": 83160,
      "train_runtime": 809934.6078,
      "train_tokens_per_second": 29201.131
    },
    {
      "epoch": 2.942718710678959,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6380769048113964e-05,
      "loss": 1.0369665145874023,
      "num_input_tokens_seen": 23653862656,
      "step": 83170,
      "train_runtime": 810033.1101,
      "train_tokens_per_second": 29201.106
    },
    {
      "epoch": 2.943072530942688,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6379890029849707e-05,
      "loss": 1.0251930236816407,
      "num_input_tokens_seen": 23656685696,
      "step": 83180,
      "train_runtime": 810127.5635,
      "train_tokens_per_second": 29201.186
    },
    {
      "epoch": 2.9434263512064165,
      "grad_norm": 1.546875,
      "learning_rate": 1.6379011153078844e-05,
      "loss": 1.0345199584960938,
      "num_input_tokens_seen": 23659521088,
      "step": 83190,
      "train_runtime": 810225.5275,
      "train_tokens_per_second": 29201.155
    },
    {
      "epoch": 2.943780171470145,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6378132417763415e-05,
      "loss": 1.0429896354675292,
      "num_input_tokens_seen": 23662329792,
      "step": 83200,
      "train_runtime": 810318.5551,
      "train_tokens_per_second": 29201.269
    },
    {
      "epoch": 2.944133991733874,
      "grad_norm": 1.640625,
      "learning_rate": 1.637725382386548e-05,
      "loss": 1.04199161529541,
      "num_input_tokens_seen": 23665161344,
      "step": 83210,
      "train_runtime": 810414.418,
      "train_tokens_per_second": 29201.308
    },
    {
      "epoch": 2.944487811997603,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6376375371347118e-05,
      "loss": 1.0399656295776367,
      "num_input_tokens_seen": 23668013440,
      "step": 83220,
      "train_runtime": 810511.2748,
      "train_tokens_per_second": 29201.338
    },
    {
      "epoch": 2.9448416322613316,
      "grad_norm": 1.6953125,
      "learning_rate": 1.6375497060170403e-05,
      "loss": 1.0407147407531738,
      "num_input_tokens_seen": 23670866432,
      "step": 83230,
      "train_runtime": 810609.4099,
      "train_tokens_per_second": 29201.322
    },
    {
      "epoch": 2.9451954525250605,
      "grad_norm": 1.6171875,
      "learning_rate": 1.637461889029745e-05,
      "loss": 1.0501070022583008,
      "num_input_tokens_seen": 23673660032,
      "step": 83240,
      "train_runtime": 810703.4842,
      "train_tokens_per_second": 29201.379
    },
    {
      "epoch": 2.945549272788789,
      "grad_norm": 1.671875,
      "learning_rate": 1.637374086169037e-05,
      "loss": 1.0400890350341796,
      "num_input_tokens_seen": 23676509120,
      "step": 83250,
      "train_runtime": 810802.8829,
      "train_tokens_per_second": 29201.313
    },
    {
      "epoch": 2.945903093052518,
      "grad_norm": 1.546875,
      "learning_rate": 1.6372862974311286e-05,
      "loss": 1.0551732063293457,
      "num_input_tokens_seen": 23679353472,
      "step": 83260,
      "train_runtime": 810900.3995,
      "train_tokens_per_second": 29201.309
    },
    {
      "epoch": 2.9462569133162466,
      "grad_norm": 1.6875,
      "learning_rate": 1.637198522812235e-05,
      "loss": 1.0175580978393555,
      "num_input_tokens_seen": 23682166592,
      "step": 83270,
      "train_runtime": 810995.2322,
      "train_tokens_per_second": 29201.364
    },
    {
      "epoch": 2.9466107335799756,
      "grad_norm": 1.6796875,
      "learning_rate": 1.6371107623085722e-05,
      "loss": 1.0290751457214355,
      "num_input_tokens_seen": 23684986752,
      "step": 83280,
      "train_runtime": 811088.9562,
      "train_tokens_per_second": 29201.466
    },
    {
      "epoch": 2.9469645538437046,
      "grad_norm": 1.671875,
      "learning_rate": 1.637023015916356e-05,
      "loss": 1.0330411911010742,
      "num_input_tokens_seen": 23687790464,
      "step": 83290,
      "train_runtime": 811184.4892,
      "train_tokens_per_second": 29201.483
    },
    {
      "epoch": 2.947318374107433,
      "grad_norm": 1.6328125,
      "learning_rate": 1.636935283631807e-05,
      "loss": 1.0419689178466798,
      "num_input_tokens_seen": 23690656576,
      "step": 83300,
      "train_runtime": 811283.966,
      "train_tokens_per_second": 29201.436
    },
    {
      "epoch": 2.9476721943711617,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6368475654511438e-05,
      "loss": 1.0391867637634278,
      "num_input_tokens_seen": 23693496896,
      "step": 83310,
      "train_runtime": 811382.3216,
      "train_tokens_per_second": 29201.397
    },
    {
      "epoch": 2.9480260146348907,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6367598613705887e-05,
      "loss": 1.0370962142944335,
      "num_input_tokens_seen": 23696350464,
      "step": 83320,
      "train_runtime": 811482.2133,
      "train_tokens_per_second": 29201.318
    },
    {
      "epoch": 2.9483798348986197,
      "grad_norm": 1.6328125,
      "learning_rate": 1.636672171386364e-05,
      "loss": 1.0474227905273437,
      "num_input_tokens_seen": 23699161920,
      "step": 83330,
      "train_runtime": 811576.3861,
      "train_tokens_per_second": 29201.394
    },
    {
      "epoch": 2.948733655162348,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6365844954946946e-05,
      "loss": 1.027945613861084,
      "num_input_tokens_seen": 23702015040,
      "step": 83340,
      "train_runtime": 811674.7638,
      "train_tokens_per_second": 29201.37
    },
    {
      "epoch": 2.9490874754260767,
      "grad_norm": 1.546875,
      "learning_rate": 1.6364968336918064e-05,
      "loss": 1.0290781021118165,
      "num_input_tokens_seen": 23704874816,
      "step": 83350,
      "train_runtime": 811772.1334,
      "train_tokens_per_second": 29201.39
    },
    {
      "epoch": 2.9494412956898057,
      "grad_norm": 1.5859375,
      "learning_rate": 1.636409185973925e-05,
      "loss": 1.0323095321655273,
      "num_input_tokens_seen": 23707676672,
      "step": 83360,
      "train_runtime": 811867.7582,
      "train_tokens_per_second": 29201.402
    },
    {
      "epoch": 2.9497951159535347,
      "grad_norm": 1.546875,
      "learning_rate": 1.6363215523372812e-05,
      "loss": 1.0296506881713867,
      "num_input_tokens_seen": 23710491712,
      "step": 83370,
      "train_runtime": 811962.9451,
      "train_tokens_per_second": 29201.446
    },
    {
      "epoch": 2.9501489362172633,
      "grad_norm": 1.625,
      "learning_rate": 1.6362339327781036e-05,
      "loss": 1.0371984481811523,
      "num_input_tokens_seen": 23713341312,
      "step": 83380,
      "train_runtime": 812060.5783,
      "train_tokens_per_second": 29201.444
    },
    {
      "epoch": 2.9505027564809923,
      "grad_norm": 1.625,
      "learning_rate": 1.6361463272926238e-05,
      "loss": 1.0407882690429688,
      "num_input_tokens_seen": 23716154880,
      "step": 83390,
      "train_runtime": 812156.77,
      "train_tokens_per_second": 29201.449
    },
    {
      "epoch": 2.950856576744721,
      "grad_norm": 1.578125,
      "learning_rate": 1.6360587358770747e-05,
      "loss": 1.040146255493164,
      "num_input_tokens_seen": 23719030144,
      "step": 83400,
      "train_runtime": 812255.7319,
      "train_tokens_per_second": 29201.432
    },
    {
      "epoch": 2.95121039700845,
      "grad_norm": 1.625,
      "learning_rate": 1.635971158527691e-05,
      "loss": 1.0358320236206056,
      "num_input_tokens_seen": 23721824896,
      "step": 83410,
      "train_runtime": 812350.3448,
      "train_tokens_per_second": 29201.471
    },
    {
      "epoch": 2.9515642172721783,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6358835952407074e-05,
      "loss": 1.047813606262207,
      "num_input_tokens_seen": 23724640000,
      "step": 83420,
      "train_runtime": 812446.3442,
      "train_tokens_per_second": 29201.485
    },
    {
      "epoch": 2.9519180375359073,
      "grad_norm": 1.515625,
      "learning_rate": 1.6357960460123614e-05,
      "loss": 1.0337163925170898,
      "num_input_tokens_seen": 23727508160,
      "step": 83430,
      "train_runtime": 812543.4344,
      "train_tokens_per_second": 29201.526
    },
    {
      "epoch": 2.952271857799636,
      "grad_norm": 1.609375,
      "learning_rate": 1.6357085108388913e-05,
      "loss": 1.0336053848266602,
      "num_input_tokens_seen": 23730346240,
      "step": 83440,
      "train_runtime": 812641.6113,
      "train_tokens_per_second": 29201.49
    },
    {
      "epoch": 2.952625678063365,
      "grad_norm": 1.671875,
      "learning_rate": 1.6356209897165374e-05,
      "loss": 1.0407537460327148,
      "num_input_tokens_seen": 23733172224,
      "step": 83450,
      "train_runtime": 812738.597,
      "train_tokens_per_second": 29201.483
    },
    {
      "epoch": 2.9529794983270934,
      "grad_norm": 1.5234375,
      "learning_rate": 1.635533482641541e-05,
      "loss": 1.0320850372314454,
      "num_input_tokens_seen": 23736043904,
      "step": 83460,
      "train_runtime": 812838.3508,
      "train_tokens_per_second": 29201.432
    },
    {
      "epoch": 2.9533333185908224,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6354459896101436e-05,
      "loss": 1.0169832229614257,
      "num_input_tokens_seen": 23738905920,
      "step": 83470,
      "train_runtime": 812939.6017,
      "train_tokens_per_second": 29201.316
    },
    {
      "epoch": 2.9536871388545514,
      "grad_norm": 1.640625,
      "learning_rate": 1.6353585106185908e-05,
      "loss": 1.031891441345215,
      "num_input_tokens_seen": 23741739648,
      "step": 83480,
      "train_runtime": 813037.6555,
      "train_tokens_per_second": 29201.279
    },
    {
      "epoch": 2.95404095911828,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6352710456631275e-05,
      "loss": 1.0437505722045899,
      "num_input_tokens_seen": 23744573248,
      "step": 83490,
      "train_runtime": 813132.5993,
      "train_tokens_per_second": 29201.354
    },
    {
      "epoch": 2.9543947793820085,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6351835947400003e-05,
      "loss": 1.0244093894958497,
      "num_input_tokens_seen": 23747442240,
      "step": 83500,
      "train_runtime": 813230.6265,
      "train_tokens_per_second": 29201.362
    },
    {
      "epoch": 2.9547485996457374,
      "grad_norm": 1.59375,
      "learning_rate": 1.6350961578454578e-05,
      "loss": 1.031100082397461,
      "num_input_tokens_seen": 23750253312,
      "step": 83510,
      "train_runtime": 813324.1048,
      "train_tokens_per_second": 29201.462
    },
    {
      "epoch": 2.9551024199094664,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6350087349757494e-05,
      "loss": 1.0316301345825196,
      "num_input_tokens_seen": 23752986560,
      "step": 83520,
      "train_runtime": 813416.2332,
      "train_tokens_per_second": 29201.515
    },
    {
      "epoch": 2.955456240173195,
      "grad_norm": 1.671875,
      "learning_rate": 1.6349213261271268e-05,
      "loss": 1.0535274505615235,
      "num_input_tokens_seen": 23755793728,
      "step": 83530,
      "train_runtime": 813510.0248,
      "train_tokens_per_second": 29201.599
    },
    {
      "epoch": 2.955810060436924,
      "grad_norm": 1.6484375,
      "learning_rate": 1.634833931295842e-05,
      "loss": 1.0426877975463866,
      "num_input_tokens_seen": 23758717696,
      "step": 83540,
      "train_runtime": 813612.8274,
      "train_tokens_per_second": 29201.503
    },
    {
      "epoch": 2.9561638807006525,
      "grad_norm": 1.65625,
      "learning_rate": 1.6347465504781485e-05,
      "loss": 1.0429293632507324,
      "num_input_tokens_seen": 23761537792,
      "step": 83550,
      "train_runtime": 813707.2172,
      "train_tokens_per_second": 29201.582
    },
    {
      "epoch": 2.9565177009643815,
      "grad_norm": 1.625,
      "learning_rate": 1.634659183670303e-05,
      "loss": 1.0380303382873535,
      "num_input_tokens_seen": 23764342720,
      "step": 83560,
      "train_runtime": 813802.0589,
      "train_tokens_per_second": 29201.625
    },
    {
      "epoch": 2.95687152122811,
      "grad_norm": 1.609375,
      "learning_rate": 1.634571830868561e-05,
      "loss": 1.0393528938293457,
      "num_input_tokens_seen": 23767170432,
      "step": 83570,
      "train_runtime": 813898.3201,
      "train_tokens_per_second": 29201.646
    },
    {
      "epoch": 2.957225341491839,
      "grad_norm": 1.6015625,
      "learning_rate": 1.634484492069181e-05,
      "loss": 1.0295408248901368,
      "num_input_tokens_seen": 23770029248,
      "step": 83580,
      "train_runtime": 813998.704,
      "train_tokens_per_second": 29201.557
    },
    {
      "epoch": 2.9575791617555676,
      "grad_norm": 1.59375,
      "learning_rate": 1.6343971672684228e-05,
      "loss": 1.0261205673217773,
      "num_input_tokens_seen": 23772902400,
      "step": 83590,
      "train_runtime": 814097.1023,
      "train_tokens_per_second": 29201.556
    },
    {
      "epoch": 2.9579329820192966,
      "grad_norm": 1.734375,
      "learning_rate": 1.634309856462547e-05,
      "loss": 1.0408454895019532,
      "num_input_tokens_seen": 23775763584,
      "step": 83600,
      "train_runtime": 814196.6963,
      "train_tokens_per_second": 29201.498
    },
    {
      "epoch": 2.958286802283025,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6342225596478154e-05,
      "loss": 1.0440988540649414,
      "num_input_tokens_seen": 23778612032,
      "step": 83610,
      "train_runtime": 814292.569,
      "train_tokens_per_second": 29201.558
    },
    {
      "epoch": 2.958640622546754,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6341352768204925e-05,
      "loss": 1.034379768371582,
      "num_input_tokens_seen": 23781454720,
      "step": 83620,
      "train_runtime": 814391.7196,
      "train_tokens_per_second": 29201.494
    },
    {
      "epoch": 2.958994442810483,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6340480079768432e-05,
      "loss": 1.0396920204162599,
      "num_input_tokens_seen": 23784243904,
      "step": 83630,
      "train_runtime": 814488.6613,
      "train_tokens_per_second": 29201.443
    },
    {
      "epoch": 2.9593482630742116,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6339607531131343e-05,
      "loss": 1.0407211303710937,
      "num_input_tokens_seen": 23787060416,
      "step": 83640,
      "train_runtime": 814586.1707,
      "train_tokens_per_second": 29201.405
    },
    {
      "epoch": 2.95970208333794,
      "grad_norm": 1.53125,
      "learning_rate": 1.633873512225633e-05,
      "loss": 1.0280614852905274,
      "num_input_tokens_seen": 23789838016,
      "step": 83650,
      "train_runtime": 814680.1885,
      "train_tokens_per_second": 29201.444
    },
    {
      "epoch": 2.960055903601669,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6337862853106086e-05,
      "loss": 1.0407819747924805,
      "num_input_tokens_seen": 23792624640,
      "step": 83660,
      "train_runtime": 814774.8348,
      "train_tokens_per_second": 29201.472
    },
    {
      "epoch": 2.960409723865398,
      "grad_norm": 1.6171875,
      "learning_rate": 1.633699072364333e-05,
      "loss": 1.0313257217407226,
      "num_input_tokens_seen": 23795411712,
      "step": 83670,
      "train_runtime": 814869.6431,
      "train_tokens_per_second": 29201.495
    },
    {
      "epoch": 2.9607635441291267,
      "grad_norm": 1.625,
      "learning_rate": 1.6336118733830765e-05,
      "loss": 1.0471054077148438,
      "num_input_tokens_seen": 23798338304,
      "step": 83680,
      "train_runtime": 814971.4828,
      "train_tokens_per_second": 29201.437
    },
    {
      "epoch": 2.9611173643928552,
      "grad_norm": 1.53125,
      "learning_rate": 1.633524688363114e-05,
      "loss": 1.0382051467895508,
      "num_input_tokens_seen": 23801185152,
      "step": 83690,
      "train_runtime": 815069.0282,
      "train_tokens_per_second": 29201.435
    },
    {
      "epoch": 2.961471184656584,
      "grad_norm": 1.546875,
      "learning_rate": 1.6334375173007193e-05,
      "loss": 1.020213508605957,
      "num_input_tokens_seen": 23804061376,
      "step": 83700,
      "train_runtime": 815167.6045,
      "train_tokens_per_second": 29201.432
    },
    {
      "epoch": 2.961825004920313,
      "grad_norm": 1.671875,
      "learning_rate": 1.6333503601921697e-05,
      "loss": 1.030905055999756,
      "num_input_tokens_seen": 23806873920,
      "step": 83710,
      "train_runtime": 815266.434,
      "train_tokens_per_second": 29201.342
    },
    {
      "epoch": 2.9621788251840417,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6332632170337422e-05,
      "loss": 1.0365280151367187,
      "num_input_tokens_seen": 23809774912,
      "step": 83720,
      "train_runtime": 815369.3529,
      "train_tokens_per_second": 29201.214
    },
    {
      "epoch": 2.9625326454477707,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6331760878217162e-05,
      "loss": 1.0395414352416992,
      "num_input_tokens_seen": 23812611520,
      "step": 83730,
      "train_runtime": 815463.3186,
      "train_tokens_per_second": 29201.328
    },
    {
      "epoch": 2.9628864657114993,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6330889725523713e-05,
      "loss": 1.033464241027832,
      "num_input_tokens_seen": 23815486784,
      "step": 83740,
      "train_runtime": 815563.8022,
      "train_tokens_per_second": 29201.255
    },
    {
      "epoch": 2.9632402859752283,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6330018712219902e-05,
      "loss": 1.037591552734375,
      "num_input_tokens_seen": 23818351040,
      "step": 83750,
      "train_runtime": 815660.8058,
      "train_tokens_per_second": 29201.294
    },
    {
      "epoch": 2.963594106238957,
      "grad_norm": 1.6171875,
      "learning_rate": 1.632914783826856e-05,
      "loss": 1.0326713562011718,
      "num_input_tokens_seen": 23821142784,
      "step": 83760,
      "train_runtime": 815754.1138,
      "train_tokens_per_second": 29201.376
    },
    {
      "epoch": 2.963947926502686,
      "grad_norm": 1.578125,
      "learning_rate": 1.632827710363253e-05,
      "loss": 1.0370306015014648,
      "num_input_tokens_seen": 23823973440,
      "step": 83770,
      "train_runtime": 815852.3666,
      "train_tokens_per_second": 29201.329
    },
    {
      "epoch": 2.9643017467664143,
      "grad_norm": 1.6796875,
      "learning_rate": 1.632740650827467e-05,
      "loss": 1.0479924201965332,
      "num_input_tokens_seen": 23826783360,
      "step": 83780,
      "train_runtime": 815947.1019,
      "train_tokens_per_second": 29201.382
    },
    {
      "epoch": 2.9646555670301433,
      "grad_norm": 1.6953125,
      "learning_rate": 1.632653605215786e-05,
      "loss": 1.023562240600586,
      "num_input_tokens_seen": 23829662080,
      "step": 83790,
      "train_runtime": 816048.3115,
      "train_tokens_per_second": 29201.288
    },
    {
      "epoch": 2.965009387293872,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6325665735244984e-05,
      "loss": 1.0211713790893555,
      "num_input_tokens_seen": 23832484480,
      "step": 83800,
      "train_runtime": 816145.0025,
      "train_tokens_per_second": 29201.287
    },
    {
      "epoch": 2.965363207557601,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6324795557498935e-05,
      "loss": 1.0427845954895019,
      "num_input_tokens_seen": 23835282624,
      "step": 83810,
      "train_runtime": 816239.0129,
      "train_tokens_per_second": 29201.352
    },
    {
      "epoch": 2.96571702782133,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6323925518882646e-05,
      "loss": 1.0471160888671875,
      "num_input_tokens_seen": 23838149952,
      "step": 83820,
      "train_runtime": 816338.1456,
      "train_tokens_per_second": 29201.318
    },
    {
      "epoch": 2.9660708480850584,
      "grad_norm": 1.625,
      "learning_rate": 1.632305561935903e-05,
      "loss": 1.0438769340515137,
      "num_input_tokens_seen": 23840988480,
      "step": 83830,
      "train_runtime": 816436.6775,
      "train_tokens_per_second": 29201.271
    },
    {
      "epoch": 2.966424668348787,
      "grad_norm": 1.65625,
      "learning_rate": 1.632218585889104e-05,
      "loss": 1.0327733993530273,
      "num_input_tokens_seen": 23843888640,
      "step": 83840,
      "train_runtime": 816536.7651,
      "train_tokens_per_second": 29201.243
    },
    {
      "epoch": 2.966778488612516,
      "grad_norm": 1.59375,
      "learning_rate": 1.6321316237441624e-05,
      "loss": 1.038883113861084,
      "num_input_tokens_seen": 23846769472,
      "step": 83850,
      "train_runtime": 816636.8666,
      "train_tokens_per_second": 29201.191
    },
    {
      "epoch": 2.967132308876245,
      "grad_norm": 1.6875,
      "learning_rate": 1.632044675497376e-05,
      "loss": 1.0322915077209474,
      "num_input_tokens_seen": 23849633408,
      "step": 83860,
      "train_runtime": 816734.2909,
      "train_tokens_per_second": 29201.215
    },
    {
      "epoch": 2.9674861291399734,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6319577411450427e-05,
      "loss": 1.0376972198486327,
      "num_input_tokens_seen": 23852474496,
      "step": 83870,
      "train_runtime": 816833.3151,
      "train_tokens_per_second": 29201.153
    },
    {
      "epoch": 2.9678399494037024,
      "grad_norm": 1.625,
      "learning_rate": 1.631870820683463e-05,
      "loss": 1.036899948120117,
      "num_input_tokens_seen": 23855295936,
      "step": 83880,
      "train_runtime": 816928.0384,
      "train_tokens_per_second": 29201.221
    },
    {
      "epoch": 2.968193769667431,
      "grad_norm": 1.65625,
      "learning_rate": 1.6317839141089375e-05,
      "loss": 1.0414960861206055,
      "num_input_tokens_seen": 23858154432,
      "step": 83890,
      "train_runtime": 817027.2403,
      "train_tokens_per_second": 29201.174
    },
    {
      "epoch": 2.96854758993116,
      "grad_norm": 1.609375,
      "learning_rate": 1.6316970214177686e-05,
      "loss": 1.0340216636657715,
      "num_input_tokens_seen": 23861043520,
      "step": 83900,
      "train_runtime": 817126.8337,
      "train_tokens_per_second": 29201.15
    },
    {
      "epoch": 2.9689014101948885,
      "grad_norm": 1.546875,
      "learning_rate": 1.6316101426062604e-05,
      "loss": 1.0428642272949218,
      "num_input_tokens_seen": 23863870976,
      "step": 83910,
      "train_runtime": 817225.9734,
      "train_tokens_per_second": 29201.068
    },
    {
      "epoch": 2.9692552304586175,
      "grad_norm": 1.6640625,
      "learning_rate": 1.6315232776707187e-05,
      "loss": 1.0439083099365234,
      "num_input_tokens_seen": 23866709632,
      "step": 83920,
      "train_runtime": 817321.2793,
      "train_tokens_per_second": 29201.136
    },
    {
      "epoch": 2.969609050722346,
      "grad_norm": 1.59375,
      "learning_rate": 1.63143642660745e-05,
      "loss": 1.0401698112487794,
      "num_input_tokens_seen": 23869575552,
      "step": 83930,
      "train_runtime": 817419.0257,
      "train_tokens_per_second": 29201.15
    },
    {
      "epoch": 2.969962870986075,
      "grad_norm": 1.6171875,
      "learning_rate": 1.631349589412762e-05,
      "loss": 1.0308097839355468,
      "num_input_tokens_seen": 23872414336,
      "step": 83940,
      "train_runtime": 817516.4469,
      "train_tokens_per_second": 29201.143
    },
    {
      "epoch": 2.9703166912498036,
      "grad_norm": 1.5703125,
      "learning_rate": 1.631262766082964e-05,
      "loss": 1.0370325088500976,
      "num_input_tokens_seen": 23875271040,
      "step": 83950,
      "train_runtime": 817613.9917,
      "train_tokens_per_second": 29201.153
    },
    {
      "epoch": 2.9706705115135326,
      "grad_norm": 1.71875,
      "learning_rate": 1.631175956614368e-05,
      "loss": 1.0424533843994142,
      "num_input_tokens_seen": 23878081408,
      "step": 83960,
      "train_runtime": 817710.6585,
      "train_tokens_per_second": 29201.138
    },
    {
      "epoch": 2.9710243317772616,
      "grad_norm": 1.671875,
      "learning_rate": 1.6310891610032843e-05,
      "loss": 1.0304970741271973,
      "num_input_tokens_seen": 23880967424,
      "step": 83970,
      "train_runtime": 817809.2136,
      "train_tokens_per_second": 29201.147
    },
    {
      "epoch": 2.97137815204099,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6310023792460282e-05,
      "loss": 1.035243034362793,
      "num_input_tokens_seen": 23883809984,
      "step": 83980,
      "train_runtime": 817903.8494,
      "train_tokens_per_second": 29201.244
    },
    {
      "epoch": 2.9717319723047186,
      "grad_norm": 1.5703125,
      "learning_rate": 1.630915611338914e-05,
      "loss": 1.0332615852355957,
      "num_input_tokens_seen": 23886686784,
      "step": 83990,
      "train_runtime": 818005.1137,
      "train_tokens_per_second": 29201.146
    },
    {
      "epoch": 2.9720857925684476,
      "grad_norm": 1.578125,
      "learning_rate": 1.6308288572782576e-05,
      "loss": 1.0409120559692382,
      "num_input_tokens_seen": 23889513152,
      "step": 84000,
      "train_runtime": 818103.0032,
      "train_tokens_per_second": 29201.107
    },
    {
      "epoch": 2.9724396128321766,
      "grad_norm": 1.53125,
      "learning_rate": 1.6307421170603776e-05,
      "loss": 1.0313928604125977,
      "num_input_tokens_seen": 23892358592,
      "step": 84010,
      "train_runtime": 818200.3783,
      "train_tokens_per_second": 29201.109
    },
    {
      "epoch": 2.972793433095905,
      "grad_norm": 1.65625,
      "learning_rate": 1.630655390681592e-05,
      "loss": 1.0481962203979491,
      "num_input_tokens_seen": 23895242368,
      "step": 84020,
      "train_runtime": 818298.8259,
      "train_tokens_per_second": 29201.12
    },
    {
      "epoch": 2.9731472533596337,
      "grad_norm": 1.609375,
      "learning_rate": 1.6305686781382223e-05,
      "loss": 1.0338308334350585,
      "num_input_tokens_seen": 23898074240,
      "step": 84030,
      "train_runtime": 818393.3536,
      "train_tokens_per_second": 29201.208
    },
    {
      "epoch": 2.9735010736233627,
      "grad_norm": 1.5625,
      "learning_rate": 1.6304819794265894e-05,
      "loss": 1.0428453445434571,
      "num_input_tokens_seen": 23900947776,
      "step": 84040,
      "train_runtime": 818493.7128,
      "train_tokens_per_second": 29201.138
    },
    {
      "epoch": 2.9738548938870917,
      "grad_norm": 1.5625,
      "learning_rate": 1.630395294543017e-05,
      "loss": 1.0501089096069336,
      "num_input_tokens_seen": 23903795648,
      "step": 84050,
      "train_runtime": 818591.6396,
      "train_tokens_per_second": 29201.124
    },
    {
      "epoch": 2.97420871415082,
      "grad_norm": 1.59375,
      "learning_rate": 1.6303086234838297e-05,
      "loss": 1.0355937004089355,
      "num_input_tokens_seen": 23906608384,
      "step": 84060,
      "train_runtime": 818688.7845,
      "train_tokens_per_second": 29201.094
    },
    {
      "epoch": 2.974562534414549,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6302219662453528e-05,
      "loss": 1.0426020622253418,
      "num_input_tokens_seen": 23909471936,
      "step": 84070,
      "train_runtime": 818786.2443,
      "train_tokens_per_second": 29201.116
    },
    {
      "epoch": 2.9749163546782778,
      "grad_norm": 1.671875,
      "learning_rate": 1.6301353228239137e-05,
      "loss": 1.0484376907348634,
      "num_input_tokens_seen": 23912263040,
      "step": 84080,
      "train_runtime": 818880.8979,
      "train_tokens_per_second": 29201.149
    },
    {
      "epoch": 2.9752701749420067,
      "grad_norm": 1.6484375,
      "learning_rate": 1.630048693215842e-05,
      "loss": 1.0321388244628906,
      "num_input_tokens_seen": 23915095168,
      "step": 84090,
      "train_runtime": 818979.1326,
      "train_tokens_per_second": 29201.104
    },
    {
      "epoch": 2.9756239952057353,
      "grad_norm": 1.578125,
      "learning_rate": 1.6299620774174663e-05,
      "loss": 1.0377731323242188,
      "num_input_tokens_seen": 23917917952,
      "step": 84100,
      "train_runtime": 819072.5947,
      "train_tokens_per_second": 29201.219
    },
    {
      "epoch": 2.9759778154694643,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6298754754251192e-05,
      "loss": 1.0273590087890625,
      "num_input_tokens_seen": 23920775040,
      "step": 84110,
      "train_runtime": 819172.6021,
      "train_tokens_per_second": 29201.141
    },
    {
      "epoch": 2.9763316357331933,
      "grad_norm": 1.671875,
      "learning_rate": 1.6297888872351324e-05,
      "loss": 1.0324262619018554,
      "num_input_tokens_seen": 23923597440,
      "step": 84120,
      "train_runtime": 819267.9632,
      "train_tokens_per_second": 29201.188
    },
    {
      "epoch": 2.976685455996922,
      "grad_norm": 1.640625,
      "learning_rate": 1.6297023128438407e-05,
      "loss": 1.0222408294677734,
      "num_input_tokens_seen": 23926424320,
      "step": 84130,
      "train_runtime": 819362.5536,
      "train_tokens_per_second": 29201.267
    },
    {
      "epoch": 2.9770392762606503,
      "grad_norm": 1.6484375,
      "learning_rate": 1.6296157522475794e-05,
      "loss": 1.0209815979003907,
      "num_input_tokens_seen": 23929324800,
      "step": 84140,
      "train_runtime": 819464.9014,
      "train_tokens_per_second": 29201.159
    },
    {
      "epoch": 2.9773930965243793,
      "grad_norm": 1.6875,
      "learning_rate": 1.629529205442685e-05,
      "loss": 1.0476024627685547,
      "num_input_tokens_seen": 23932135424,
      "step": 84150,
      "train_runtime": 819558.5141,
      "train_tokens_per_second": 29201.253
    },
    {
      "epoch": 2.9777469167881083,
      "grad_norm": 1.6484375,
      "learning_rate": 1.629442672425496e-05,
      "loss": 1.0290684700012207,
      "num_input_tokens_seen": 23934969664,
      "step": 84160,
      "train_runtime": 819656.7552,
      "train_tokens_per_second": 29201.211
    },
    {
      "epoch": 2.978100737051837,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6293561531923517e-05,
      "loss": 1.029268455505371,
      "num_input_tokens_seen": 23937865792,
      "step": 84170,
      "train_runtime": 819757.9142,
      "train_tokens_per_second": 29201.14
    },
    {
      "epoch": 2.9784545573155654,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6292696477395934e-05,
      "loss": 1.0444313049316407,
      "num_input_tokens_seen": 23940704256,
      "step": 84180,
      "train_runtime": 819852.2512,
      "train_tokens_per_second": 29201.242
    },
    {
      "epoch": 2.9788083775792944,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6291831560635628e-05,
      "loss": 1.0373075485229493,
      "num_input_tokens_seen": 23943607104,
      "step": 84190,
      "train_runtime": 819954.4493,
      "train_tokens_per_second": 29201.143
    },
    {
      "epoch": 2.9791621978430234,
      "grad_norm": 1.625,
      "learning_rate": 1.6290966781606043e-05,
      "loss": 1.040273952484131,
      "num_input_tokens_seen": 23946468992,
      "step": 84200,
      "train_runtime": 820054.3418,
      "train_tokens_per_second": 29201.076
    },
    {
      "epoch": 2.979516018106752,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6290102140270622e-05,
      "loss": 1.0225068092346192,
      "num_input_tokens_seen": 23949304768,
      "step": 84210,
      "train_runtime": 820152.2878,
      "train_tokens_per_second": 29201.046
    },
    {
      "epoch": 2.979869838370481,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6289237636592827e-05,
      "loss": 1.0325600624084472,
      "num_input_tokens_seen": 23952142016,
      "step": 84220,
      "train_runtime": 820250.9879,
      "train_tokens_per_second": 29200.991
    },
    {
      "epoch": 2.9802236586342095,
      "grad_norm": 1.6171875,
      "learning_rate": 1.628837327053614e-05,
      "loss": 1.0378568649291993,
      "num_input_tokens_seen": 23955013248,
      "step": 84230,
      "train_runtime": 820349.6948,
      "train_tokens_per_second": 29200.978
    },
    {
      "epoch": 2.9805774788979384,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6287509042064053e-05,
      "loss": 1.021855640411377,
      "num_input_tokens_seen": 23957892288,
      "step": 84240,
      "train_runtime": 820451.2877,
      "train_tokens_per_second": 29200.871
    },
    {
      "epoch": 2.980931299161667,
      "grad_norm": 1.640625,
      "learning_rate": 1.6286644951140067e-05,
      "loss": 1.036000633239746,
      "num_input_tokens_seen": 23960771200,
      "step": 84250,
      "train_runtime": 820549.8239,
      "train_tokens_per_second": 29200.873
    },
    {
      "epoch": 2.981285119425396,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6285780997727696e-05,
      "loss": 1.039645290374756,
      "num_input_tokens_seen": 23963668736,
      "step": 84260,
      "train_runtime": 820647.454,
      "train_tokens_per_second": 29200.93
    },
    {
      "epoch": 2.9816389396891245,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6284917181790476e-05,
      "loss": 1.037799072265625,
      "num_input_tokens_seen": 23966484160,
      "step": 84270,
      "train_runtime": 820742.6188,
      "train_tokens_per_second": 29200.974
    },
    {
      "epoch": 2.9819927599528535,
      "grad_norm": 1.5859375,
      "learning_rate": 1.628405350329195e-05,
      "loss": 1.0435062408447267,
      "num_input_tokens_seen": 23969362176,
      "step": 84280,
      "train_runtime": 820841.3804,
      "train_tokens_per_second": 29200.967
    },
    {
      "epoch": 2.982346580216582,
      "grad_norm": 1.625,
      "learning_rate": 1.628318996219568e-05,
      "loss": 1.0404690742492675,
      "num_input_tokens_seen": 23972235456,
      "step": 84290,
      "train_runtime": 820941.4159,
      "train_tokens_per_second": 29200.909
    },
    {
      "epoch": 2.982700400480311,
      "grad_norm": 1.6875,
      "learning_rate": 1.628232655846523e-05,
      "loss": 1.0426322937011718,
      "num_input_tokens_seen": 23975004352,
      "step": 84300,
      "train_runtime": 821037.4587,
      "train_tokens_per_second": 29200.865
    },
    {
      "epoch": 2.98305422074404,
      "grad_norm": 1.671875,
      "learning_rate": 1.6281463292064193e-05,
      "loss": 1.0507189750671386,
      "num_input_tokens_seen": 23977789120,
      "step": 84310,
      "train_runtime": 821132.1187,
      "train_tokens_per_second": 29200.891
    },
    {
      "epoch": 2.9834080410077686,
      "grad_norm": 1.578125,
      "learning_rate": 1.628060016295616e-05,
      "loss": 1.0124247550964356,
      "num_input_tokens_seen": 23980638016,
      "step": 84320,
      "train_runtime": 821233.089,
      "train_tokens_per_second": 29200.769
    },
    {
      "epoch": 2.983761861271497,
      "grad_norm": 1.59375,
      "learning_rate": 1.6279737171104752e-05,
      "loss": 1.0482660293579102,
      "num_input_tokens_seen": 23983545536,
      "step": 84330,
      "train_runtime": 821332.3071,
      "train_tokens_per_second": 29200.782
    },
    {
      "epoch": 2.984115681535226,
      "grad_norm": 1.65625,
      "learning_rate": 1.6278874316473593e-05,
      "loss": 1.0426139831542969,
      "num_input_tokens_seen": 23986342400,
      "step": 84340,
      "train_runtime": 821427.3751,
      "train_tokens_per_second": 29200.807
    },
    {
      "epoch": 2.984469501798955,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6278011599026314e-05,
      "loss": 1.037677001953125,
      "num_input_tokens_seen": 23989209536,
      "step": 84350,
      "train_runtime": 821526.6637,
      "train_tokens_per_second": 29200.768
    },
    {
      "epoch": 2.9848233220626836,
      "grad_norm": 1.6171875,
      "learning_rate": 1.627714901872657e-05,
      "loss": 1.0412812232971191,
      "num_input_tokens_seen": 23992052352,
      "step": 84360,
      "train_runtime": 821621.2517,
      "train_tokens_per_second": 29200.866
    },
    {
      "epoch": 2.9851771423264126,
      "grad_norm": 1.578125,
      "learning_rate": 1.627628657553804e-05,
      "loss": 1.0412015914916992,
      "num_input_tokens_seen": 23994967104,
      "step": 84370,
      "train_runtime": 821724.3638,
      "train_tokens_per_second": 29200.749
    },
    {
      "epoch": 2.985530962590141,
      "grad_norm": 1.5625,
      "learning_rate": 1.627542426942439e-05,
      "loss": 1.0342002868652345,
      "num_input_tokens_seen": 23997814592,
      "step": 84380,
      "train_runtime": 821819.8224,
      "train_tokens_per_second": 29200.822
    },
    {
      "epoch": 2.98588478285387,
      "grad_norm": 1.5859375,
      "learning_rate": 1.627456210034932e-05,
      "loss": 1.0339414596557617,
      "num_input_tokens_seen": 24000678208,
      "step": 84390,
      "train_runtime": 821918.0364,
      "train_tokens_per_second": 29200.817
    },
    {
      "epoch": 2.9862386031175987,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6273700068276534e-05,
      "loss": 1.0284908294677735,
      "num_input_tokens_seen": 24003519680,
      "step": 84400,
      "train_runtime": 822016.1954,
      "train_tokens_per_second": 29200.787
    },
    {
      "epoch": 2.9865924233813277,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6272838173169752e-05,
      "loss": 1.0417510986328125,
      "num_input_tokens_seen": 24006336896,
      "step": 84410,
      "train_runtime": 822107.1646,
      "train_tokens_per_second": 29200.982
    },
    {
      "epoch": 2.9869462436450562,
      "grad_norm": 1.59375,
      "learning_rate": 1.627197641499271e-05,
      "loss": 1.0412151336669921,
      "num_input_tokens_seen": 24009124224,
      "step": 84420,
      "train_runtime": 822201.7038,
      "train_tokens_per_second": 29201.015
    },
    {
      "epoch": 2.987300063908785,
      "grad_norm": 1.640625,
      "learning_rate": 1.6271114793709146e-05,
      "loss": 1.0387316703796388,
      "num_input_tokens_seen": 24011981888,
      "step": 84430,
      "train_runtime": 822297.6252,
      "train_tokens_per_second": 29201.084
    },
    {
      "epoch": 2.9876538841725138,
      "grad_norm": 1.6171875,
      "learning_rate": 1.6270253309282836e-05,
      "loss": 1.0334922790527343,
      "num_input_tokens_seen": 24014828672,
      "step": 84440,
      "train_runtime": 822395.2338,
      "train_tokens_per_second": 29201.08
    },
    {
      "epoch": 2.9880077044362428,
      "grad_norm": 1.578125,
      "learning_rate": 1.626939196167754e-05,
      "loss": 1.0276421546936034,
      "num_input_tokens_seen": 24017713280,
      "step": 84450,
      "train_runtime": 822494.0673,
      "train_tokens_per_second": 29201.078
    },
    {
      "epoch": 2.9883615246999717,
      "grad_norm": 1.796875,
      "learning_rate": 1.6268530750857053e-05,
      "loss": 1.0436725616455078,
      "num_input_tokens_seen": 24020520128,
      "step": 84460,
      "train_runtime": 822589.5058,
      "train_tokens_per_second": 29201.102
    },
    {
      "epoch": 2.9887153449637003,
      "grad_norm": 1.609375,
      "learning_rate": 1.6267669676785175e-05,
      "loss": 1.029702854156494,
      "num_input_tokens_seen": 24023329728,
      "step": 84470,
      "train_runtime": 822685.6995,
      "train_tokens_per_second": 29201.103
    },
    {
      "epoch": 2.989069165227429,
      "grad_norm": 1.625,
      "learning_rate": 1.6266808739425716e-05,
      "loss": 1.0219280242919921,
      "num_input_tokens_seen": 24026236160,
      "step": 84480,
      "train_runtime": 822788.4264,
      "train_tokens_per_second": 29200.989
    },
    {
      "epoch": 2.989422985491158,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6265947938742507e-05,
      "loss": 1.0317282676696777,
      "num_input_tokens_seen": 24029062336,
      "step": 84490,
      "train_runtime": 822886.7261,
      "train_tokens_per_second": 29200.936
    },
    {
      "epoch": 2.989776805754887,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6265087274699387e-05,
      "loss": 1.0504442214965821,
      "num_input_tokens_seen": 24031888384,
      "step": 84500,
      "train_runtime": 822986.9948,
      "train_tokens_per_second": 29200.812
    },
    {
      "epoch": 2.9901306260186153,
      "grad_norm": 1.625,
      "learning_rate": 1.626422674726021e-05,
      "loss": 1.033837890625,
      "num_input_tokens_seen": 24034728064,
      "step": 84510,
      "train_runtime": 823083.1907,
      "train_tokens_per_second": 29200.849
    },
    {
      "epoch": 2.990484446282344,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6263366356388846e-05,
      "loss": 1.0366727828979492,
      "num_input_tokens_seen": 24037534720,
      "step": 84520,
      "train_runtime": 823179.209,
      "train_tokens_per_second": 29200.853
    },
    {
      "epoch": 2.990838266546073,
      "grad_norm": 1.6484375,
      "learning_rate": 1.626250610204918e-05,
      "loss": 1.0387153625488281,
      "num_input_tokens_seen": 24040405760,
      "step": 84530,
      "train_runtime": 823279.2355,
      "train_tokens_per_second": 29200.792
    },
    {
      "epoch": 2.991192086809802,
      "grad_norm": 1.625,
      "learning_rate": 1.6261645984205095e-05,
      "loss": 1.033730697631836,
      "num_input_tokens_seen": 24043297024,
      "step": 84540,
      "train_runtime": 823382.027,
      "train_tokens_per_second": 29200.658
    },
    {
      "epoch": 2.9915459070735304,
      "grad_norm": 1.6328125,
      "learning_rate": 1.6260786002820508e-05,
      "loss": 1.0389947891235352,
      "num_input_tokens_seen": 24046108160,
      "step": 84550,
      "train_runtime": 823478.479,
      "train_tokens_per_second": 29200.652
    },
    {
      "epoch": 2.9918997273372594,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6259926157859336e-05,
      "loss": 1.0464378356933595,
      "num_input_tokens_seen": 24049044672,
      "step": 84560,
      "train_runtime": 823580.6675,
      "train_tokens_per_second": 29200.594
    },
    {
      "epoch": 2.992253547600988,
      "grad_norm": 1.6484375,
      "learning_rate": 1.625906644928552e-05,
      "loss": 1.0460453033447266,
      "num_input_tokens_seen": 24051938048,
      "step": 84570,
      "train_runtime": 823682.3684,
      "train_tokens_per_second": 29200.501
    },
    {
      "epoch": 2.992607367864717,
      "grad_norm": 1.5703125,
      "learning_rate": 1.6258206877062995e-05,
      "loss": 1.03430118560791,
      "num_input_tokens_seen": 24054786176,
      "step": 84580,
      "train_runtime": 823779.2201,
      "train_tokens_per_second": 29200.526
    },
    {
      "epoch": 2.9929611881284455,
      "grad_norm": 1.5859375,
      "learning_rate": 1.6257347441155738e-05,
      "loss": 1.046249008178711,
      "num_input_tokens_seen": 24057639360,
      "step": 84590,
      "train_runtime": 823876.2804,
      "train_tokens_per_second": 29200.549
    },
    {
      "epoch": 2.9933150083921745,
      "grad_norm": 1.6171875,
      "learning_rate": 1.625648814152771e-05,
      "loss": 1.031470489501953,
      "num_input_tokens_seen": 24060529600,
      "step": 84600,
      "train_runtime": 823977.1976,
      "train_tokens_per_second": 29200.48
    },
    {
      "epoch": 2.993668828655903,
      "grad_norm": 1.6953125,
      "learning_rate": 1.6255628978142908e-05,
      "loss": 1.0271507263183595,
      "num_input_tokens_seen": 24063329024,
      "step": 84610,
      "train_runtime": 824069.6227,
      "train_tokens_per_second": 29200.602
    },
    {
      "epoch": 2.994022648919632,
      "grad_norm": 1.734375,
      "learning_rate": 1.6254769950965327e-05,
      "loss": 1.0327853202819823,
      "num_input_tokens_seen": 24066189824,
      "step": 84620,
      "train_runtime": 824166.7065,
      "train_tokens_per_second": 29200.633
    },
    {
      "epoch": 2.9943764691833605,
      "grad_norm": 1.625,
      "learning_rate": 1.6253911059958986e-05,
      "loss": 1.0484712600708008,
      "num_input_tokens_seen": 24069068992,
      "step": 84630,
      "train_runtime": 824265.576,
      "train_tokens_per_second": 29200.624
    },
    {
      "epoch": 2.9947302894470895,
      "grad_norm": 1.578125,
      "learning_rate": 1.625305230508791e-05,
      "loss": 1.034200096130371,
      "num_input_tokens_seen": 24071887808,
      "step": 84640,
      "train_runtime": 824359.5993,
      "train_tokens_per_second": 29200.713
    },
    {
      "epoch": 2.9950841097108185,
      "grad_norm": 1.75,
      "learning_rate": 1.625219368631614e-05,
      "loss": 1.0386927604675293,
      "num_input_tokens_seen": 24074699776,
      "step": 84650,
      "train_runtime": 824454.4296,
      "train_tokens_per_second": 29200.765
    },
    {
      "epoch": 2.995437929974547,
      "grad_norm": 1.6015625,
      "learning_rate": 1.6251335203607734e-05,
      "loss": 1.0473630905151368,
      "num_input_tokens_seen": 24077558400,
      "step": 84660,
      "train_runtime": 824553.7407,
      "train_tokens_per_second": 29200.715
    },
    {
      "epoch": 2.9957917502382756,
      "grad_norm": 1.5390625,
      "learning_rate": 1.6250476856926757e-05,
      "loss": 1.0421865463256836,
      "num_input_tokens_seen": 24080440832,
      "step": 84670,
      "train_runtime": 824653.543,
      "train_tokens_per_second": 29200.676
    },
    {
      "epoch": 2.9961455705020046,
      "grad_norm": 1.65625,
      "learning_rate": 1.6249618646237292e-05,
      "loss": 1.0359792709350586,
      "num_input_tokens_seen": 24083276032,
      "step": 84680,
      "train_runtime": 824752.48,
      "train_tokens_per_second": 29200.611
    },
    {
      "epoch": 2.9964993907657336,
      "grad_norm": 1.6015625,
      "learning_rate": 1.624876057150343e-05,
      "loss": 1.0325206756591796,
      "num_input_tokens_seen": 24086081344,
      "step": 84690,
      "train_runtime": 824847.5024,
      "train_tokens_per_second": 29200.648
    },
    {
      "epoch": 2.996853211029462,
      "grad_norm": 1.65625,
      "learning_rate": 1.624790263268928e-05,
      "loss": 1.0359966278076171,
      "num_input_tokens_seen": 24088907200,
      "step": 84700,
      "train_runtime": 824942.1467,
      "train_tokens_per_second": 29200.723
    },
    {
      "epoch": 2.997207031293191,
      "grad_norm": 1.625,
      "learning_rate": 1.6247044829758963e-05,
      "loss": 1.027275276184082,
      "num_input_tokens_seen": 24091731584,
      "step": 84710,
      "train_runtime": 825038.2099,
      "train_tokens_per_second": 29200.746
    },
    {
      "epoch": 2.9975608515569196,
      "grad_norm": 1.609375,
      "learning_rate": 1.6246187162676616e-05,
      "loss": 1.0346318244934083,
      "num_input_tokens_seen": 24094547328,
      "step": 84720,
      "train_runtime": 825131.2872,
      "train_tokens_per_second": 29200.865
    },
    {
      "epoch": 2.9979146718206486,
      "grad_norm": 1.546875,
      "learning_rate": 1.624532963140638e-05,
      "loss": 1.0331748008728028,
      "num_input_tokens_seen": 24097437120,
      "step": 84730,
      "train_runtime": 825233.6004,
      "train_tokens_per_second": 29200.746
    },
    {
      "epoch": 2.998268492084377,
      "grad_norm": 1.5546875,
      "learning_rate": 1.6244472235912418e-05,
      "loss": 1.0209616661071776,
      "num_input_tokens_seen": 24100316032,
      "step": 84740,
      "train_runtime": 825332.9529,
      "train_tokens_per_second": 29200.719
    },
    {
      "epoch": 2.998622312348106,
      "grad_norm": 1.546875,
      "learning_rate": 1.624361497615891e-05,
      "loss": 1.0485048294067383,
      "num_input_tokens_seen": 24103207808,
      "step": 84750,
      "train_runtime": 825434.7476,
      "train_tokens_per_second": 29200.622
    },
    {
      "epoch": 2.9989761326118347,
      "grad_norm": 1.6171875,
      "learning_rate": 1.624275785211003e-05,
      "loss": 1.046034049987793,
      "num_input_tokens_seen": 24106077248,
      "step": 84760,
      "train_runtime": 825534.5905,
      "train_tokens_per_second": 29200.566
    },
    {
      "epoch": 2.9993299528755637,
      "grad_norm": 1.6484375,
      "learning_rate": 1.624190086372999e-05,
      "loss": 1.0432168960571289,
      "num_input_tokens_seen": 24108912320,
      "step": 84770,
      "train_runtime": 825630.5476,
      "train_tokens_per_second": 29200.606
    },
    {
      "epoch": 2.9996837731392922,
      "grad_norm": 1.59375,
      "learning_rate": 1.6241044010982998e-05,
      "loss": 1.0395265579223634,
      "num_input_tokens_seen": 24111758528,
      "step": 84780,
      "train_runtime": 825726.0656,
      "train_tokens_per_second": 29200.675
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.02244234085083,
      "eval_runtime": 8.4934,
      "eval_samples_per_second": 469.541,
      "eval_steps_per_second": 3.768,
      "num_input_tokens_seen": 24114289216,
      "step": 84789
    },
    {
      "epoch": 3.0,
      "num_input_tokens_seen": 24114289216,
      "step": 84789,
      "total_flos": 4.014701818973667e+20,
      "train_loss": 1.068974989199425,
      "train_runtime": 825845.889,
      "train_samples_per_second": 105.133,
      "train_steps_per_second": 0.103
    }
  ],
  "logging_steps": 10,
  "max_steps": 84789,
  "num_input_tokens_seen": 24114289216,
  "num_train_epochs": 3,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.014701818973667e+20,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}