{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 100.0,
  "eval_steps": 100,
  "global_step": 10600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.94,
      "learning_rate": 1.3773584905660377e-06,
      "loss": 127.5473,
      "step": 100
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.2641509433962264e-06,
      "loss": 93.1935,
      "step": 200
    },
    {
      "epoch": 2.83,
      "learning_rate": 5.150943396226416e-06,
      "loss": 46.8948,
      "step": 300
    },
    {
      "epoch": 3.77,
      "learning_rate": 7.037735849056604e-06,
      "loss": 29.0448,
      "step": 400
    },
    {
      "epoch": 4.72,
      "learning_rate": 8.924528301886793e-06,
      "loss": 21.3695,
      "step": 500
    },
    {
      "epoch": 5.66,
      "learning_rate": 1.0811320754716984e-05,
      "loss": 16.0309,
      "step": 600
    },
    {
      "epoch": 6.6,
      "learning_rate": 1.2698113207547172e-05,
      "loss": 11.634,
      "step": 700
    },
    {
      "epoch": 7.55,
      "learning_rate": 1.458490566037736e-05,
      "loss": 8.507,
      "step": 800
    },
    {
      "epoch": 8.49,
      "learning_rate": 1.6471698113207547e-05,
      "loss": 6.5544,
      "step": 900
    },
    {
      "epoch": 9.43,
      "learning_rate": 1.8358490566037736e-05,
      "loss": 5.4801,
      "step": 1000
    },
    {
      "epoch": 10.38,
      "learning_rate": 1.9999908365494266e-05,
      "loss": 4.8409,
      "step": 1100
    },
    {
      "epoch": 11.32,
      "learning_rate": 1.999307723208382e-05,
      "loss": 4.5821,
      "step": 1200
    },
    {
      "epoch": 12.26,
      "learning_rate": 1.9975410248472147e-05,
      "loss": 4.4581,
      "step": 1300
    },
    {
      "epoch": 13.21,
      "learning_rate": 1.9946926571599945e-05,
      "loss": 4.4058,
      "step": 1400
    },
    {
      "epoch": 14.15,
      "learning_rate": 1.9907657087334364e-05,
      "loss": 4.3872,
      "step": 1500
    },
    {
      "epoch": 15.09,
      "learning_rate": 1.9857644376978347e-05,
      "loss": 4.3754,
      "step": 1600
    },
    {
      "epoch": 16.04,
      "learning_rate": 1.9796942671098212e-05,
      "loss": 4.3666,
      "step": 1700
    },
    {
      "epoch": 16.98,
      "learning_rate": 1.9725617790719523e-05,
      "loss": 4.3582,
      "step": 1800
    },
    {
      "epoch": 17.92,
      "learning_rate": 1.9643747075954974e-05,
      "loss": 4.3503,
      "step": 1900
    },
    {
      "epoch": 18.87,
      "learning_rate": 1.9551419302141784e-05,
      "loss": 4.3376,
      "step": 2000
    },
    {
      "epoch": 19.81,
      "learning_rate": 1.9448734583579404e-05,
      "loss": 4.3143,
      "step": 2100
    },
    {
      "epoch": 20.75,
      "learning_rate": 1.9335804264972018e-05,
      "loss": 4.3017,
      "step": 2200
    },
    {
      "epoch": 21.7,
      "learning_rate": 1.9212750800693506e-05,
      "loss": 4.2686,
      "step": 2300
    },
    {
      "epoch": 22.64,
      "learning_rate": 1.90797076220058e-05,
      "loss": 4.2361,
      "step": 2400
    },
    {
      "epoch": 23.58,
      "learning_rate": 1.8936818992374606e-05,
      "loss": 4.1892,
      "step": 2500
    },
    {
      "epoch": 24.53,
      "learning_rate": 1.8784239851039375e-05,
      "loss": 4.0793,
      "step": 2600
    },
    {
      "epoch": 25.47,
      "learning_rate": 1.8622135645007168e-05,
      "loss": 3.8419,
      "step": 2700
    },
    {
      "epoch": 26.42,
      "learning_rate": 1.845068214965255e-05,
      "loss": 3.507,
      "step": 2800
    },
    {
      "epoch": 27.36,
      "learning_rate": 1.8270065278118092e-05,
      "loss": 3.0923,
      "step": 2900
    },
    {
      "epoch": 28.3,
      "learning_rate": 1.8080480879722103e-05,
      "loss": 2.5866,
      "step": 3000
    },
    {
      "epoch": 29.25,
      "learning_rate": 1.7882134527592244e-05,
      "loss": 2.2309,
      "step": 3100
    },
    {
      "epoch": 30.19,
      "learning_rate": 1.7677351806066863e-05,
      "loss": 1.9554,
      "step": 3200
    },
    {
      "epoch": 31.13,
      "learning_rate": 1.7466600884087986e-05,
      "loss": 1.7519,
      "step": 3300
    },
    {
      "epoch": 32.08,
      "learning_rate": 1.7243535137637227e-05,
      "loss": 1.5826,
      "step": 3400
    },
    {
      "epoch": 33.02,
      "learning_rate": 1.7012614967583424e-05,
      "loss": 1.4243,
      "step": 3500
    },
    {
      "epoch": 33.96,
      "learning_rate": 1.6774090768906323e-05,
      "loss": 1.3115,
      "step": 3600
    },
    {
      "epoch": 34.91,
      "learning_rate": 1.6528221181905217e-05,
      "loss": 1.2043,
      "step": 3700
    },
    {
      "epoch": 35.85,
      "learning_rate": 1.6275272811746063e-05,
      "loss": 1.131,
      "step": 3800
    },
    {
      "epoch": 36.79,
      "learning_rate": 1.6018150231520486e-05,
      "loss": 1.0536,
      "step": 3900
    },
    {
      "epoch": 37.74,
      "learning_rate": 1.575193832697346e-05,
      "loss": 0.9722,
      "step": 4000
    },
    {
      "epoch": 38.68,
      "learning_rate": 1.5479489390466186e-05,
      "loss": 0.932,
      "step": 4100
    },
    {
      "epoch": 39.62,
      "learning_rate": 1.520109884810164e-05,
      "loss": 0.8723,
      "step": 4200
    },
    {
      "epoch": 40.57,
      "learning_rate": 1.4917068568678037e-05,
      "loss": 0.8349,
      "step": 4300
    },
    {
      "epoch": 41.51,
      "learning_rate": 1.4627706536361717e-05,
      "loss": 0.8096,
      "step": 4400
    },
    {
      "epoch": 42.45,
      "learning_rate": 1.4333326516728909e-05,
      "loss": 0.8033,
      "step": 4500
    },
    {
      "epoch": 43.4,
      "learning_rate": 1.4034247716538545e-05,
      "loss": 0.757,
      "step": 4600
    },
    {
      "epoch": 44.34,
      "learning_rate": 1.373079443760497e-05,
      "loss": 0.7242,
      "step": 4700
    },
    {
      "epoch": 45.28,
      "learning_rate": 1.3423295725145908e-05,
      "loss": 0.6985,
      "step": 4800
    },
    {
      "epoch": 46.23,
      "learning_rate": 1.3115214387653711e-05,
      "loss": 0.6804,
      "step": 4900
    },
    {
      "epoch": 47.17,
      "learning_rate": 1.2800661191392916e-05,
      "loss": 0.6658,
      "step": 5000
    },
    {
      "epoch": 48.11,
      "learning_rate": 1.2483071138273168e-05,
      "loss": 0.6392,
      "step": 5100
    },
    {
      "epoch": 49.06,
      "learning_rate": 1.2162788602520851e-05,
      "loss": 0.6237,
      "step": 5200
    },
    {
      "epoch": 50.0,
      "learning_rate": 1.1840160877917335e-05,
      "loss": 0.5931,
      "step": 5300
    },
    {
      "epoch": 50.94,
      "learning_rate": 1.1515537801215944e-05,
      "loss": 0.5826,
      "step": 5400
    },
    {
      "epoch": 51.89,
      "learning_rate": 1.1189271372801474e-05,
      "loss": 0.5833,
      "step": 5500
    },
    {
      "epoch": 52.83,
      "learning_rate": 1.0861715375003623e-05,
      "loss": 0.5603,
      "step": 5600
    },
    {
      "epoch": 53.77,
      "learning_rate": 1.0533224988478176e-05,
      "loss": 0.564,
      "step": 5700
    },
    {
      "epoch": 54.72,
      "learning_rate": 1.0204156407071964e-05,
      "loss": 0.5516,
      "step": 5800
    },
    {
      "epoch": 55.66,
      "learning_rate": 9.874866451589151e-06,
      "loss": 0.5528,
      "step": 5900
    },
    {
      "epoch": 56.6,
      "learning_rate": 9.549001881675188e-06,
      "loss": 0.5396,
      "step": 6000
    },
    {
      "epoch": 57.55,
      "learning_rate": 9.22033352215851e-06,
      "loss": 0.5292,
      "step": 6100
    },
    {
      "epoch": 58.49,
      "learning_rate": 8.892510582822682e-06,
      "loss": 0.5093,
      "step": 6200
    },
    {
      "epoch": 59.43,
      "learning_rate": 8.565888533777731e-06,
      "loss": 0.5153,
      "step": 6300
    },
    {
      "epoch": 60.38,
      "learning_rate": 8.240821542965487e-06,
      "loss": 0.4972,
      "step": 6400
    },
    {
      "epoch": 61.32,
      "learning_rate": 7.917662092122658e-06,
      "loss": 0.4761,
      "step": 6500
    },
    {
      "epoch": 62.26,
      "learning_rate": 7.5967605945723e-06,
      "loss": 0.4784,
      "step": 6600
    },
    {
      "epoch": 63.21,
      "learning_rate": 7.278465015258145e-06,
      "loss": 0.4546,
      "step": 6700
    },
    {
      "epoch": 64.15,
      "learning_rate": 6.963120493433808e-06,
      "loss": 0.4692,
      "step": 6800
    },
    {
      "epoch": 65.09,
      "learning_rate": 6.65106896841597e-06,
      "loss": 0.4569,
      "step": 6900
    },
    {
      "epoch": 66.04,
      "learning_rate": 6.342648808807368e-06,
      "loss": 0.465,
      "step": 7000
    },
    {
      "epoch": 66.98,
      "learning_rate": 6.038194445591676e-06,
      "loss": 0.4592,
      "step": 7100
    },
    {
      "epoch": 67.92,
      "learning_rate": 5.738036009498027e-06,
      "loss": 0.4518,
      "step": 7200
    },
    {
      "epoch": 68.87,
      "learning_rate": 5.442498973028489e-06,
      "loss": 0.4557,
      "step": 7300
    },
    {
      "epoch": 69.81,
      "learning_rate": 5.151903797536631e-06,
      "loss": 0.4392,
      "step": 7400
    },
    {
      "epoch": 70.75,
      "learning_rate": 4.866565585739835e-06,
      "loss": 0.4348,
      "step": 7500
    },
    {
      "epoch": 71.7,
      "learning_rate": 4.586793740042181e-06,
      "loss": 0.4322,
      "step": 7600
    },
    {
      "epoch": 72.64,
      "learning_rate": 4.312891627038364e-06,
      "loss": 0.4285,
      "step": 7700
    },
    {
      "epoch": 73.58,
      "learning_rate": 4.047802118060723e-06,
      "loss": 0.4296,
      "step": 7800
    },
    {
      "epoch": 74.53,
      "learning_rate": 3.7864578043142407e-06,
      "loss": 0.4309,
      "step": 7900
    },
    {
      "epoch": 75.47,
      "learning_rate": 3.5318510560731366e-06,
      "loss": 0.4341,
      "step": 8000
    },
    {
      "epoch": 76.42,
      "learning_rate": 3.284257952519031e-06,
      "loss": 0.4252,
      "step": 8100
    },
    {
      "epoch": 77.36,
      "learning_rate": 3.0439469676883693e-06,
      "loss": 0.4232,
      "step": 8200
    },
    {
      "epoch": 78.3,
      "learning_rate": 2.811178679356429e-06,
      "loss": 0.42,
      "step": 8300
    },
    {
      "epoch": 79.25,
      "learning_rate": 2.586205486483554e-06,
      "loss": 0.4056,
      "step": 8400
    },
    {
      "epoch": 80.19,
      "learning_rate": 2.369271335529936e-06,
      "loss": 0.41,
      "step": 8500
    },
    {
      "epoch": 81.13,
      "learning_rate": 2.160611455935786e-06,
      "loss": 0.419,
      "step": 8600
    },
    {
      "epoch": 82.08,
      "learning_rate": 1.9604521050536506e-06,
      "loss": 0.4078,
      "step": 8700
    },
    {
      "epoch": 83.02,
      "learning_rate": 1.7690103228094845e-06,
      "loss": 0.4194,
      "step": 8800
    },
    {
      "epoch": 83.96,
      "learning_rate": 1.5864936963585164e-06,
      "loss": 0.3995,
      "step": 8900
    },
    {
      "epoch": 84.91,
      "learning_rate": 1.413100134991111e-06,
      "loss": 0.4128,
      "step": 9000
    },
    {
      "epoch": 85.85,
      "learning_rate": 1.2490176555326306e-06,
      "loss": 0.4075,
      "step": 9100
    },
    {
      "epoch": 86.79,
      "learning_rate": 1.0944241784701025e-06,
      "loss": 0.4075,
      "step": 9200
    },
    {
      "epoch": 87.74,
      "learning_rate": 9.49487335026692e-07,
      "loss": 0.4012,
      "step": 9300
    },
    {
      "epoch": 88.68,
      "learning_rate": 8.143642853931688e-07,
      "loss": 0.4066,
      "step": 9400
    },
    {
      "epoch": 89.62,
      "learning_rate": 6.892015483135095e-07,
      "loss": 0.401,
      "step": 9500
    },
    {
      "epoch": 90.57,
      "learning_rate": 5.741348422094128e-07,
      "loss": 0.3933,
      "step": 9600
    },
    {
      "epoch": 91.51,
      "learning_rate": 4.69288938015946e-07,
      "loss": 0.4163,
      "step": 9700
    },
    {
      "epoch": 92.45,
      "learning_rate": 3.747775238879847e-07,
      "loss": 0.3918,
      "step": 9800
    },
    {
      "epoch": 93.4,
      "learning_rate": 2.907030819240908e-07,
      "loss": 0.409,
      "step": 9900
    },
    {
      "epoch": 94.34,
      "learning_rate": 2.1783985444653433e-07,
      "loss": 0.3987,
      "step": 10000
    },
    {
      "epoch": 95.28,
      "learning_rate": 1.5479499961417067e-07,
      "loss": 0.395,
      "step": 10100
    },
    {
      "epoch": 96.23,
      "learning_rate": 1.024256518460387e-07,
      "loss": 0.4019,
      "step": 10200
    },
    {
      "epoch": 97.17,
      "learning_rate": 6.078859709449215e-08,
      "loss": 0.3952,
      "step": 10300
    },
    {
      "epoch": 98.11,
      "learning_rate": 2.992898390362875e-08,
      "loss": 0.4062,
      "step": 10400
    },
    {
      "epoch": 99.06,
      "learning_rate": 9.88027445312123e-09,
      "loss": 0.3926,
      "step": 10500
    },
    {
      "epoch": 100.0,
      "learning_rate": 7.027047924512698e-10,
      "loss": 0.4021,
      "step": 10600
    },
    {
      "epoch": 100.0,
      "step": 10600,
      "total_flos": 6.516030907718042e+16,
      "train_loss": 4.689974609231049,
      "train_runtime": 6096.2204,
      "train_samples_per_second": 55.51,
      "train_steps_per_second": 1.739
    }
  ],
  "logging_steps": 100,
  "max_steps": 10600,
  "num_train_epochs": 100,
  "save_steps": 100,
  "total_flos": 6.516030907718042e+16,
  "trial_name": null,
  "trial_params": null
}