{
  "best_metric": null,
  "best_model_checkpoint": null,
<<<<<<< HEAD
  "epoch": 408.505875769446,
  "global_step": 730000,
=======
  "epoch": 111.9194180190263,
  "global_step": 200000,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
<<<<<<< HEAD
      "epoch": 5.6,
      "learning_rate": 2.3437499999999998e-07,
      "loss": 0.8947,
      "step": 10000
    },
    {
      "epoch": 5.6,
      "eval_loss": 0.7632947564125061,
      "eval_runtime": 76.0776,
      "eval_samples_per_second": 101.633,
      "eval_steps_per_second": 12.711,
      "step": 10000
    },
    {
      "epoch": 11.19,
      "learning_rate": 4.6874999999999996e-07,
      "loss": 0.7738,
      "step": 20000
    },
    {
      "epoch": 11.19,
      "eval_loss": 0.7603365182876587,
      "eval_runtime": 76.429,
      "eval_samples_per_second": 101.166,
      "eval_steps_per_second": 12.652,
      "step": 20000
    },
    {
      "epoch": 16.79,
      "learning_rate": 7.031249999999999e-07,
      "loss": 0.7725,
      "step": 30000
    },
    {
      "epoch": 16.79,
      "eval_loss": 0.7571617960929871,
      "eval_runtime": 76.146,
      "eval_samples_per_second": 101.542,
      "eval_steps_per_second": 12.699,
      "step": 30000
    },
    {
      "epoch": 22.38,
      "learning_rate": 9.374999999999999e-07,
      "loss": 0.7715,
      "step": 40000
    },
    {
      "epoch": 22.38,
      "eval_loss": 0.7568734884262085,
      "eval_runtime": 76.4339,
      "eval_samples_per_second": 101.159,
      "eval_steps_per_second": 12.651,
=======
      "epoch": 11.19,
      "learning_rate": 1.8749999999999998e-06,
      "loss": 0.8164,
      "step": 10000
    },
    {
      "epoch": 11.19,
      "eval_loss": 0.7568955421447754,
      "eval_runtime": 301.8174,
      "eval_samples_per_second": 25.618,
      "eval_steps_per_second": 1.604,
      "step": 10000
    },
    {
      "epoch": 22.37,
      "learning_rate": 3.7499999999999997e-06,
      "loss": 0.7702,
      "step": 20000
    },
    {
      "epoch": 22.37,
      "eval_loss": 0.7498099207878113,
      "eval_runtime": 249.204,
      "eval_samples_per_second": 31.027,
      "eval_steps_per_second": 1.942,
      "step": 20000
    },
    {
      "epoch": 33.56,
      "learning_rate": 5.6249999999999995e-06,
      "loss": 0.7668,
      "step": 30000
    },
    {
      "epoch": 33.56,
      "eval_loss": 0.7477062344551086,
      "eval_runtime": 189.0409,
      "eval_samples_per_second": 40.901,
      "eval_steps_per_second": 2.56,
      "step": 30000
    },
    {
      "epoch": 44.74,
      "learning_rate": 7.499999999999999e-06,
      "loss": 0.7655,
      "step": 40000
    },
    {
      "epoch": 44.74,
      "eval_loss": 0.7450574040412903,
      "eval_runtime": 66.2284,
      "eval_samples_per_second": 116.748,
      "eval_steps_per_second": 7.308,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 40000
    },
    {
      "epoch": 27.98,
<<<<<<< HEAD
      "learning_rate": 1.171875e-06,
      "loss": 0.7695,
=======
      "learning_rate": 9.375e-06,
      "loss": 0.7653,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 50000
    },
    {
      "epoch": 27.98,
<<<<<<< HEAD
      "eval_loss": 0.7500209212303162,
      "eval_runtime": 76.3619,
      "eval_samples_per_second": 101.255,
      "eval_steps_per_second": 12.663,
=======
      "eval_loss": 0.7478589415550232,
      "eval_runtime": 76.5001,
      "eval_samples_per_second": 101.072,
      "eval_steps_per_second": 12.641,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 50000
    },
    {
      "epoch": 33.58,
<<<<<<< HEAD
      "learning_rate": 1.4062499999999999e-06,
      "loss": 0.7688,
=======
      "learning_rate": 1.1249999999999999e-05,
      "loss": 0.7648,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 60000
    },
    {
      "epoch": 33.58,
<<<<<<< HEAD
      "eval_loss": 0.7491664886474609,
      "eval_runtime": 76.419,
      "eval_samples_per_second": 101.179,
      "eval_steps_per_second": 12.654,
=======
      "eval_loss": 0.7447686195373535,
      "eval_runtime": 76.3539,
      "eval_samples_per_second": 101.265,
      "eval_steps_per_second": 12.665,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 60000
    },
    {
      "epoch": 39.17,
<<<<<<< HEAD
      "learning_rate": 1.6406249999999999e-06,
      "loss": 0.768,
=======
      "learning_rate": 1.3124999999999999e-05,
      "loss": 0.7645,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 70000
    },
    {
      "epoch": 39.17,
<<<<<<< HEAD
      "eval_loss": 0.748078465461731,
      "eval_runtime": 76.5312,
      "eval_samples_per_second": 101.031,
      "eval_steps_per_second": 12.635,
=======
      "eval_loss": 0.7464274764060974,
      "eval_runtime": 76.7958,
      "eval_samples_per_second": 100.683,
      "eval_steps_per_second": 12.592,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 70000
    },
    {
      "epoch": 44.77,
<<<<<<< HEAD
      "learning_rate": 1.8749999999999998e-06,
      "loss": 0.7667,
=======
      "learning_rate": 1.4999999999999999e-05,
      "loss": 0.7642,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 80000
    },
    {
      "epoch": 44.77,
<<<<<<< HEAD
      "eval_loss": 0.7448051571846008,
      "eval_runtime": 76.5688,
      "eval_samples_per_second": 100.981,
      "eval_steps_per_second": 12.629,
=======
      "eval_loss": 0.7449608445167542,
      "eval_runtime": 122.9116,
      "eval_samples_per_second": 62.907,
      "eval_steps_per_second": 7.867,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 80000
    },
    {
      "epoch": 50.36,
<<<<<<< HEAD
      "learning_rate": 2.109375e-06,
      "loss": 0.7663,
=======
      "learning_rate": 1.6875e-05,
      "loss": 0.7636,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 90000
    },
    {
      "epoch": 50.36,
<<<<<<< HEAD
      "eval_loss": 0.7472007870674133,
      "eval_runtime": 76.5244,
      "eval_samples_per_second": 101.04,
      "eval_steps_per_second": 12.636,
=======
      "eval_loss": 0.7427342534065247,
      "eval_runtime": 76.4172,
      "eval_samples_per_second": 101.181,
      "eval_steps_per_second": 12.654,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 90000
    },
    {
      "epoch": 55.96,
<<<<<<< HEAD
      "learning_rate": 2.34375e-06,
      "loss": 0.766,
=======
      "learning_rate": 2e-05,
      "loss": 0.7602,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 100000
    },
    {
      "epoch": 55.96,
<<<<<<< HEAD
      "eval_loss": 0.7444973587989807,
      "eval_runtime": 76.6067,
      "eval_samples_per_second": 100.931,
      "eval_steps_per_second": 12.623,
=======
      "eval_loss": 0.726163387298584,
      "eval_runtime": 76.3938,
      "eval_samples_per_second": 101.212,
      "eval_steps_per_second": 12.658,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 100000
    },
    {
      "epoch": 61.56,
<<<<<<< HEAD
      "learning_rate": 2.578125e-06,
      "loss": 0.7656,
=======
      "learning_rate": 2e-05,
      "loss": 0.7279,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 110000
    },
    {
      "epoch": 61.56,
<<<<<<< HEAD
      "eval_loss": 0.7434288263320923,
      "eval_runtime": 76.5916,
      "eval_samples_per_second": 100.951,
      "eval_steps_per_second": 12.625,
=======
      "eval_loss": 0.6971690654754639,
      "eval_runtime": 76.7625,
      "eval_samples_per_second": 100.726,
      "eval_steps_per_second": 12.597,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 110000
    },
    {
      "epoch": 67.15,
<<<<<<< HEAD
      "learning_rate": 2.8124999999999998e-06,
      "loss": 0.7654,
=======
      "learning_rate": 2e-05,
      "loss": 0.6981,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 120000
    },
    {
      "epoch": 67.15,
<<<<<<< HEAD
      "eval_loss": 0.7411925196647644,
      "eval_runtime": 76.517,
      "eval_samples_per_second": 101.049,
      "eval_steps_per_second": 12.638,
=======
      "eval_loss": 0.6809367537498474,
      "eval_runtime": 76.4831,
      "eval_samples_per_second": 101.094,
      "eval_steps_per_second": 12.643,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 120000
    },
    {
      "epoch": 72.75,
<<<<<<< HEAD
      "learning_rate": 3.046875e-06,
      "loss": 0.7652,
=======
      "learning_rate": 2e-05,
      "loss": 0.6781,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 130000
    },
    {
      "epoch": 72.75,
<<<<<<< HEAD
      "eval_loss": 0.7399063110351562,
      "eval_runtime": 76.4205,
      "eval_samples_per_second": 101.177,
      "eval_steps_per_second": 12.654,
=======
      "eval_loss": 0.6643149852752686,
      "eval_runtime": 76.5075,
      "eval_samples_per_second": 101.062,
      "eval_steps_per_second": 12.639,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 130000
    },
    {
      "epoch": 78.34,
<<<<<<< HEAD
      "learning_rate": 3.2812499999999997e-06,
      "loss": 0.7649,
=======
      "learning_rate": 2e-05,
      "loss": 0.6612,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 140000
    },
    {
      "epoch": 78.34,
<<<<<<< HEAD
      "eval_loss": 0.7432417869567871,
      "eval_runtime": 76.3896,
      "eval_samples_per_second": 101.218,
      "eval_steps_per_second": 12.659,
=======
      "eval_loss": 0.653438150882721,
      "eval_runtime": 76.7069,
      "eval_samples_per_second": 100.799,
      "eval_steps_per_second": 12.606,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 140000
    },
    {
      "epoch": 83.94,
<<<<<<< HEAD
      "learning_rate": 3.515625e-06,
      "loss": 0.7647,
=======
      "learning_rate": 2e-05,
      "loss": 0.6483,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 150000
    },
    {
      "epoch": 83.94,
<<<<<<< HEAD
      "eval_loss": 0.7411432862281799,
      "eval_runtime": 76.5523,
      "eval_samples_per_second": 101.003,
      "eval_steps_per_second": 12.632,
=======
      "eval_loss": 0.6426078081130981,
      "eval_runtime": 76.587,
      "eval_samples_per_second": 100.957,
      "eval_steps_per_second": 12.626,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 150000
    },
    {
      "epoch": 89.54,
<<<<<<< HEAD
      "learning_rate": 3.7499999999999997e-06,
      "loss": 0.7645,
=======
      "learning_rate": 2e-05,
      "loss": 0.6389,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 160000
    },
    {
      "epoch": 89.54,
<<<<<<< HEAD
      "eval_loss": 0.7415673136711121,
      "eval_runtime": 76.1013,
      "eval_samples_per_second": 101.601,
      "eval_steps_per_second": 12.707,
=======
      "eval_loss": 0.6356751918792725,
      "eval_runtime": 76.2962,
      "eval_samples_per_second": 101.342,
      "eval_steps_per_second": 12.674,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 160000
    },
    {
      "epoch": 95.13,
<<<<<<< HEAD
      "learning_rate": 3.9843749999999994e-06,
      "loss": 0.7642,
=======
      "learning_rate": 2e-05,
      "loss": 0.6318,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 170000
    },
    {
      "epoch": 95.13,
<<<<<<< HEAD
      "eval_loss": 0.742856502532959,
      "eval_runtime": 76.276,
      "eval_samples_per_second": 101.369,
      "eval_steps_per_second": 12.678,
=======
      "eval_loss": 0.6319578289985657,
      "eval_runtime": 134.8378,
      "eval_samples_per_second": 57.343,
      "eval_steps_per_second": 7.172,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 170000
    },
    {
      "epoch": 100.73,
<<<<<<< HEAD
      "learning_rate": 4.21875e-06,
      "loss": 0.764,
=======
      "learning_rate": 2e-05,
      "loss": 0.6261,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 180000
    },
    {
      "epoch": 100.73,
<<<<<<< HEAD
      "eval_loss": 0.7411246299743652,
      "eval_runtime": 76.2112,
      "eval_samples_per_second": 101.455,
      "eval_steps_per_second": 12.688,
=======
      "eval_loss": 0.6279829740524292,
      "eval_runtime": 76.2996,
      "eval_samples_per_second": 101.337,
      "eval_steps_per_second": 12.674,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 180000
    },
    {
      "epoch": 106.32,
<<<<<<< HEAD
      "learning_rate": 4.453125e-06,
      "loss": 0.764,
=======
      "learning_rate": 2e-05,
      "loss": 0.6214,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 190000
    },
    {
      "epoch": 106.32,
<<<<<<< HEAD
      "eval_loss": 0.7412048578262329,
      "eval_runtime": 76.6531,
      "eval_samples_per_second": 100.87,
      "eval_steps_per_second": 12.615,
=======
      "eval_loss": 0.6199918389320374,
      "eval_runtime": 76.2832,
      "eval_samples_per_second": 101.359,
      "eval_steps_per_second": 12.676,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 190000
    },
    {
      "epoch": 111.92,
<<<<<<< HEAD
      "learning_rate": 1e-05,
      "loss": 0.7632,
=======
      "learning_rate": 2e-05,
      "loss": 0.6177,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
      "step": 200000
    },
    {
      "epoch": 111.92,
<<<<<<< HEAD
      "eval_loss": 0.7407946586608887,
      "eval_runtime": 76.5545,
      "eval_samples_per_second": 101.0,
      "eval_steps_per_second": 12.632,
      "step": 200000
    },
    {
      "epoch": 117.52,
      "learning_rate": 1e-05,
      "loss": 0.7575,
      "step": 210000
    },
    {
      "epoch": 117.52,
      "eval_loss": 0.7322171330451965,
      "eval_runtime": 76.7018,
      "eval_samples_per_second": 100.806,
      "eval_steps_per_second": 12.607,
      "step": 210000
    },
    {
      "epoch": 123.11,
      "learning_rate": 1e-05,
      "loss": 0.7422,
      "step": 220000
    },
    {
      "epoch": 123.11,
      "eval_loss": 0.7116619944572449,
      "eval_runtime": 76.7768,
      "eval_samples_per_second": 100.707,
      "eval_steps_per_second": 12.595,
      "step": 220000
    },
    {
      "epoch": 128.71,
      "learning_rate": 1e-05,
      "loss": 0.7142,
      "step": 230000
    },
    {
      "epoch": 128.71,
      "eval_loss": 0.6831667423248291,
      "eval_runtime": 76.4706,
      "eval_samples_per_second": 101.111,
      "eval_steps_per_second": 12.645,
      "step": 230000
    },
    {
      "epoch": 134.3,
      "learning_rate": 1e-05,
      "loss": 0.6903,
      "step": 240000
    },
    {
      "epoch": 134.3,
      "eval_loss": 0.6659817695617676,
      "eval_runtime": 76.4365,
      "eval_samples_per_second": 101.156,
      "eval_steps_per_second": 12.651,
      "step": 240000
    },
    {
      "epoch": 139.9,
      "learning_rate": 1e-05,
      "loss": 0.6732,
      "step": 250000
    },
    {
      "epoch": 139.9,
      "eval_loss": 0.6514819860458374,
      "eval_runtime": 76.6466,
      "eval_samples_per_second": 100.879,
      "eval_steps_per_second": 12.616,
      "step": 250000
    },
    {
      "epoch": 145.5,
      "learning_rate": 1e-05,
      "loss": 0.661,
      "step": 260000
    },
    {
      "epoch": 145.5,
      "eval_loss": 0.6453074812889099,
      "eval_runtime": 76.4842,
      "eval_samples_per_second": 101.093,
      "eval_steps_per_second": 12.643,
      "step": 260000
    },
    {
      "epoch": 151.09,
      "learning_rate": 1e-05,
      "loss": 0.652,
      "step": 270000
    },
    {
      "epoch": 151.09,
      "eval_loss": 0.637267529964447,
      "eval_runtime": 76.4521,
      "eval_samples_per_second": 101.135,
      "eval_steps_per_second": 12.648,
      "step": 270000
    },
    {
      "epoch": 156.69,
      "learning_rate": 1e-05,
      "loss": 0.6446,
      "step": 280000
    },
    {
      "epoch": 156.69,
      "eval_loss": 0.6328049302101135,
      "eval_runtime": 76.4339,
      "eval_samples_per_second": 101.159,
      "eval_steps_per_second": 12.651,
      "step": 280000
    },
    {
      "epoch": 162.28,
      "learning_rate": 1e-05,
      "loss": 0.6384,
      "step": 290000
    },
    {
      "epoch": 162.28,
      "eval_loss": 0.6286044120788574,
      "eval_runtime": 76.4408,
      "eval_samples_per_second": 101.15,
      "eval_steps_per_second": 12.65,
      "step": 290000
    },
    {
      "epoch": 167.88,
      "learning_rate": 1e-05,
      "loss": 0.6313,
      "step": 300000
    },
    {
      "epoch": 167.88,
      "eval_loss": 0.627047598361969,
      "eval_runtime": 76.2029,
      "eval_samples_per_second": 101.466,
      "eval_steps_per_second": 12.69,
      "step": 300000
    },
    {
      "epoch": 173.48,
      "learning_rate": 1e-05,
      "loss": 0.6267,
      "step": 310000
    },
    {
      "epoch": 173.48,
      "eval_loss": 0.6226180195808411,
      "eval_runtime": 76.351,
      "eval_samples_per_second": 101.269,
      "eval_steps_per_second": 12.665,
      "step": 310000
    },
    {
      "epoch": 179.07,
      "learning_rate": 1e-05,
      "loss": 0.6225,
      "step": 320000
    },
    {
      "epoch": 179.07,
      "eval_loss": 0.6174684166908264,
      "eval_runtime": 77.0828,
      "eval_samples_per_second": 100.308,
      "eval_steps_per_second": 12.545,
      "step": 320000
    },
    {
      "epoch": 184.67,
      "learning_rate": 1e-05,
      "loss": 0.6195,
      "step": 330000
    },
    {
      "epoch": 184.67,
      "eval_loss": 0.6189109086990356,
      "eval_runtime": 76.6515,
      "eval_samples_per_second": 100.872,
      "eval_steps_per_second": 12.616,
      "step": 330000
    },
    {
      "epoch": 190.26,
      "learning_rate": 1e-05,
      "loss": 0.6166,
      "step": 340000
    },
    {
      "epoch": 190.26,
      "eval_loss": 0.6162586808204651,
      "eval_runtime": 76.6287,
      "eval_samples_per_second": 100.902,
      "eval_steps_per_second": 12.619,
      "step": 340000
    },
    {
      "epoch": 195.86,
      "learning_rate": 1e-05,
      "loss": 0.614,
      "step": 350000
    },
    {
      "epoch": 195.86,
      "eval_loss": 0.6159895658493042,
      "eval_runtime": 76.4934,
      "eval_samples_per_second": 101.081,
      "eval_steps_per_second": 12.642,
      "step": 350000
    },
    {
      "epoch": 201.45,
      "learning_rate": 1e-05,
      "loss": 0.6117,
      "step": 360000
    },
    {
      "epoch": 201.45,
      "eval_loss": 0.6115593910217285,
      "eval_runtime": 75.8517,
      "eval_samples_per_second": 101.936,
      "eval_steps_per_second": 12.749,
      "step": 360000
    },
    {
      "epoch": 207.05,
      "learning_rate": 1e-05,
      "loss": 0.6094,
      "step": 370000
    },
    {
      "epoch": 207.05,
      "eval_loss": 0.6114900708198547,
      "eval_runtime": 76.348,
      "eval_samples_per_second": 101.273,
      "eval_steps_per_second": 12.666,
      "step": 370000
    },
    {
      "epoch": 212.65,
      "learning_rate": 1e-05,
      "loss": 0.6071,
      "step": 380000
    },
    {
      "epoch": 212.65,
      "eval_loss": 0.6110843420028687,
      "eval_runtime": 76.4292,
      "eval_samples_per_second": 101.165,
      "eval_steps_per_second": 12.652,
      "step": 380000
    },
    {
      "epoch": 218.24,
      "learning_rate": 1e-05,
      "loss": 0.6048,
      "step": 390000
    },
    {
      "epoch": 218.24,
      "eval_loss": 0.6108397245407104,
      "eval_runtime": 76.2883,
      "eval_samples_per_second": 101.352,
      "eval_steps_per_second": 12.676,
      "step": 390000
    },
    {
      "epoch": 223.84,
      "learning_rate": 1e-05,
      "loss": 0.6025,
      "step": 400000
    },
    {
      "epoch": 223.84,
      "eval_loss": 0.6071902513504028,
      "eval_runtime": 76.1442,
      "eval_samples_per_second": 101.544,
      "eval_steps_per_second": 12.7,
      "step": 400000
    },
    {
      "epoch": 229.43,
      "learning_rate": 1e-05,
      "loss": 0.6006,
      "step": 410000
    },
    {
      "epoch": 229.43,
      "eval_loss": 0.6058005690574646,
      "eval_runtime": 76.1177,
      "eval_samples_per_second": 101.579,
      "eval_steps_per_second": 12.704,
      "step": 410000
    },
    {
      "epoch": 235.03,
      "learning_rate": 1e-05,
      "loss": 0.599,
      "step": 420000
    },
    {
      "epoch": 235.03,
      "eval_loss": 0.6018807888031006,
      "eval_runtime": 76.6301,
      "eval_samples_per_second": 100.9,
      "eval_steps_per_second": 12.619,
      "step": 420000
    },
    {
      "epoch": 240.63,
      "learning_rate": 1e-05,
      "loss": 0.5969,
      "step": 430000
    },
    {
      "epoch": 240.63,
      "eval_loss": 0.6019513010978699,
      "eval_runtime": 76.6382,
      "eval_samples_per_second": 100.89,
      "eval_steps_per_second": 12.618,
      "step": 430000
    },
    {
      "epoch": 246.22,
      "learning_rate": 1e-05,
      "loss": 0.5956,
      "step": 440000
    },
    {
      "epoch": 246.22,
      "eval_loss": 0.6009297370910645,
      "eval_runtime": 76.7463,
      "eval_samples_per_second": 100.747,
      "eval_steps_per_second": 12.6,
      "step": 440000
    },
    {
      "epoch": 251.82,
      "learning_rate": 1e-05,
      "loss": 0.5937,
      "step": 450000
    },
    {
      "epoch": 251.82,
      "eval_loss": 0.6020432114601135,
      "eval_runtime": 76.498,
      "eval_samples_per_second": 101.075,
      "eval_steps_per_second": 12.641,
      "step": 450000
    },
    {
      "epoch": 257.41,
      "learning_rate": 1e-05,
      "loss": 0.5923,
      "step": 460000
    },
    {
      "epoch": 257.41,
      "eval_loss": 0.5997503399848938,
      "eval_runtime": 76.4264,
      "eval_samples_per_second": 101.169,
      "eval_steps_per_second": 12.653,
      "step": 460000
    },
    {
      "epoch": 263.01,
      "learning_rate": 1e-05,
      "loss": 0.5907,
      "step": 470000
    },
    {
      "epoch": 263.01,
      "eval_loss": 0.6007161140441895,
      "eval_runtime": 76.517,
      "eval_samples_per_second": 101.049,
      "eval_steps_per_second": 12.638,
      "step": 470000
    },
    {
      "epoch": 268.61,
      "learning_rate": 1e-05,
      "loss": 0.5894,
      "step": 480000
    },
    {
      "epoch": 268.61,
      "eval_loss": 0.5984556674957275,
      "eval_runtime": 76.4528,
      "eval_samples_per_second": 101.134,
      "eval_steps_per_second": 12.648,
      "step": 480000
    },
    {
      "epoch": 274.2,
      "learning_rate": 1e-05,
      "loss": 0.5876,
      "step": 490000
    },
    {
      "epoch": 274.2,
      "eval_loss": 0.5970821976661682,
      "eval_runtime": 76.2171,
      "eval_samples_per_second": 101.447,
      "eval_steps_per_second": 12.687,
      "step": 490000
    },
    {
      "epoch": 279.8,
      "learning_rate": 1e-05,
      "loss": 0.5863,
      "step": 500000
    },
    {
      "epoch": 279.8,
      "eval_loss": 0.5982722640037537,
      "eval_runtime": 76.3256,
      "eval_samples_per_second": 101.303,
      "eval_steps_per_second": 12.669,
      "step": 500000
    },
    {
      "epoch": 285.39,
      "learning_rate": 1e-05,
      "loss": 0.585,
      "step": 510000
    },
    {
      "epoch": 285.39,
      "eval_loss": 0.5990148782730103,
      "eval_runtime": 76.2053,
      "eval_samples_per_second": 101.463,
      "eval_steps_per_second": 12.689,
      "step": 510000
    },
    {
      "epoch": 290.99,
      "learning_rate": 1e-05,
      "loss": 0.583,
      "step": 520000
    },
    {
      "epoch": 290.99,
      "eval_loss": 0.5960124135017395,
      "eval_runtime": 76.218,
      "eval_samples_per_second": 101.446,
      "eval_steps_per_second": 12.687,
      "step": 520000
    },
    {
      "epoch": 296.59,
      "learning_rate": 1e-05,
      "loss": 0.5822,
      "step": 530000
    },
    {
      "epoch": 296.59,
      "eval_loss": 0.593532145023346,
      "eval_runtime": 76.3226,
      "eval_samples_per_second": 101.307,
      "eval_steps_per_second": 12.67,
      "step": 530000
    },
    {
      "epoch": 302.18,
      "learning_rate": 1e-05,
      "loss": 0.5808,
      "step": 540000
    },
    {
      "epoch": 302.18,
      "eval_loss": 0.596666693687439,
      "eval_runtime": 76.1588,
      "eval_samples_per_second": 101.525,
      "eval_steps_per_second": 12.697,
      "step": 540000
    },
    {
      "epoch": 307.78,
      "learning_rate": 1e-05,
      "loss": 0.5794,
      "step": 550000
    },
    {
      "epoch": 307.78,
      "eval_loss": 0.5946430563926697,
      "eval_runtime": 76.3226,
      "eval_samples_per_second": 101.307,
      "eval_steps_per_second": 12.67,
      "step": 550000
    },
    {
      "epoch": 313.37,
      "learning_rate": 1e-05,
      "loss": 0.578,
      "step": 560000
    },
    {
      "epoch": 313.37,
      "eval_loss": 0.5950666666030884,
      "eval_runtime": 76.243,
      "eval_samples_per_second": 101.413,
      "eval_steps_per_second": 12.683,
      "step": 560000
    },
    {
      "epoch": 318.97,
      "learning_rate": 1e-05,
      "loss": 0.5766,
      "step": 570000
    },
    {
      "epoch": 318.97,
      "eval_loss": 0.5932120680809021,
      "eval_runtime": 76.0598,
      "eval_samples_per_second": 101.657,
      "eval_steps_per_second": 12.714,
      "step": 570000
    },
    {
      "epoch": 324.57,
      "learning_rate": 1e-05,
      "loss": 0.5752,
      "step": 580000
    },
    {
      "epoch": 324.57,
      "eval_loss": 0.5916844606399536,
      "eval_runtime": 76.215,
      "eval_samples_per_second": 101.45,
      "eval_steps_per_second": 12.688,
      "step": 580000
    },
    {
      "epoch": 330.16,
      "learning_rate": 1e-05,
      "loss": 0.5739,
      "step": 590000
    },
    {
      "epoch": 330.16,
      "eval_loss": 0.592149019241333,
      "eval_runtime": 76.1575,
      "eval_samples_per_second": 101.526,
      "eval_steps_per_second": 12.697,
      "step": 590000
    },
    {
      "epoch": 335.76,
      "learning_rate": 1e-05,
      "loss": 0.5726,
      "step": 600000
    },
    {
      "epoch": 335.76,
      "eval_loss": 0.5907247066497803,
      "eval_runtime": 76.2114,
      "eval_samples_per_second": 101.455,
      "eval_steps_per_second": 12.688,
      "step": 600000
    },
    {
      "epoch": 341.35,
      "learning_rate": 1e-05,
      "loss": 0.5714,
      "step": 610000
    },
    {
      "epoch": 341.35,
      "eval_loss": 0.5907928347587585,
      "eval_runtime": 76.207,
      "eval_samples_per_second": 101.461,
      "eval_steps_per_second": 12.689,
      "step": 610000
    },
    {
      "epoch": 346.95,
      "learning_rate": 1e-05,
      "loss": 0.5702,
      "step": 620000
    },
    {
      "epoch": 346.95,
      "eval_loss": 0.5909689664840698,
      "eval_runtime": 76.3919,
      "eval_samples_per_second": 101.215,
      "eval_steps_per_second": 12.658,
      "step": 620000
    },
    {
      "epoch": 352.55,
      "learning_rate": 1e-05,
      "loss": 0.5686,
      "step": 630000
    },
    {
      "epoch": 352.55,
      "eval_loss": 0.5894390940666199,
      "eval_runtime": 76.3494,
      "eval_samples_per_second": 101.271,
      "eval_steps_per_second": 12.665,
      "step": 630000
    },
    {
      "epoch": 358.14,
      "learning_rate": 1e-05,
      "loss": 0.5674,
      "step": 640000
    },
    {
      "epoch": 358.14,
      "eval_loss": 0.5915200114250183,
      "eval_runtime": 76.5727,
      "eval_samples_per_second": 100.976,
      "eval_steps_per_second": 12.629,
      "step": 640000
    },
    {
      "epoch": 363.74,
      "learning_rate": 1e-05,
      "loss": 0.5664,
      "step": 650000
    },
    {
      "epoch": 363.74,
      "eval_loss": 0.5875544548034668,
      "eval_runtime": 76.0536,
      "eval_samples_per_second": 101.665,
      "eval_steps_per_second": 12.715,
      "step": 650000
    },
    {
      "epoch": 369.33,
      "learning_rate": 1e-05,
      "loss": 0.565,
      "step": 660000
    },
    {
      "epoch": 369.33,
      "eval_loss": 0.5878584980964661,
      "eval_runtime": 76.1299,
      "eval_samples_per_second": 101.563,
      "eval_steps_per_second": 12.702,
      "step": 660000
    },
    {
      "epoch": 374.93,
      "learning_rate": 1e-05,
      "loss": 0.5636,
      "step": 670000
    },
    {
      "epoch": 374.93,
      "eval_loss": 0.5897438526153564,
      "eval_runtime": 76.3557,
      "eval_samples_per_second": 101.263,
      "eval_steps_per_second": 12.664,
      "step": 670000
    },
    {
      "epoch": 380.53,
      "learning_rate": 1e-05,
      "loss": 0.5625,
      "step": 680000
    },
    {
      "epoch": 380.53,
      "eval_loss": 0.5888833999633789,
      "eval_runtime": 76.7072,
      "eval_samples_per_second": 100.799,
      "eval_steps_per_second": 12.606,
      "step": 680000
    },
    {
      "epoch": 386.12,
      "learning_rate": 1e-05,
      "loss": 0.5609,
      "step": 690000
    },
    {
      "epoch": 386.12,
      "eval_loss": 0.5903308987617493,
      "eval_runtime": 76.5139,
      "eval_samples_per_second": 101.053,
      "eval_steps_per_second": 12.638,
      "step": 690000
    },
    {
      "epoch": 391.72,
      "learning_rate": 1e-05,
      "loss": 0.5594,
      "step": 700000
    },
    {
      "epoch": 391.72,
      "eval_loss": 0.5877216458320618,
      "eval_runtime": 76.4574,
      "eval_samples_per_second": 101.128,
      "eval_steps_per_second": 12.648,
      "step": 700000
    },
    {
      "epoch": 397.31,
      "learning_rate": 1e-05,
      "loss": 0.5584,
      "step": 710000
    },
    {
      "epoch": 397.31,
      "eval_loss": 0.5875140428543091,
      "eval_runtime": 76.1634,
      "eval_samples_per_second": 101.519,
      "eval_steps_per_second": 12.696,
      "step": 710000
    },
    {
      "epoch": 402.91,
      "learning_rate": 1e-05,
      "loss": 0.5573,
      "step": 720000
    },
    {
      "epoch": 402.91,
      "eval_loss": 0.5887530446052551,
      "eval_runtime": 76.2807,
      "eval_samples_per_second": 101.362,
      "eval_steps_per_second": 12.677,
      "step": 720000
    },
    {
      "epoch": 408.51,
      "learning_rate": 1e-05,
      "loss": 0.5561,
      "step": 730000
    },
    {
      "epoch": 408.51,
      "eval_loss": 0.5863147974014282,
      "eval_runtime": 76.2255,
      "eval_samples_per_second": 101.436,
      "eval_steps_per_second": 12.686,
      "step": 730000
    }
  ],
  "max_steps": 1000000,
  "num_train_epochs": 560,
  "total_flos": 3.197989282913906e+21,
=======
      "eval_loss": 0.6199995875358582,
      "eval_runtime": 76.4051,
      "eval_samples_per_second": 101.197,
      "eval_steps_per_second": 12.656,
      "step": 200000
    },
    {
      "epoch": 111.92,
      "step": 200000,
      "total_flos": 1.0512018951481177e+21,
      "train_loss": 0.5566074145507812,
      "train_runtime": 84698.4102,
      "train_samples_per_second": 37.781,
      "train_steps_per_second": 2.361
    }
  ],
  "max_steps": 200000,
  "num_train_epochs": 112,
  "total_flos": 1.0512018951481177e+21,
>>>>>>> f31c512c34f45b1f3e7b799ebda1f4af417ffe1b
  "trial_name": null,
  "trial_params": null
}