{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 6.999476713762428,
  "eval_steps": 1000,
  "global_step": 8360,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 4.958123953098828e-05,
      "loss": 0.1445,
      "step": 100
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.916247906197655e-05,
      "loss": 0.1585,
      "step": 200
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.874371859296483e-05,
      "loss": 0.1654,
      "step": 300
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.83249581239531e-05,
      "loss": 0.1701,
      "step": 400
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.7906197654941376e-05,
      "loss": 0.1884,
      "step": 500
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.748743718592965e-05,
      "loss": 0.1868,
      "step": 600
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.7068676716917926e-05,
      "loss": 0.1872,
      "step": 700
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.66499162479062e-05,
      "loss": 0.2018,
      "step": 800
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.6231155778894475e-05,
      "loss": 0.1865,
      "step": 900
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.581239530988275e-05,
      "loss": 0.2002,
      "step": 1000
    },
    {
      "epoch": 0.84,
      "eval_loss": 2.548002243041992,
      "eval_runtime": 20.7773,
      "eval_samples_per_second": 57.466,
      "eval_steps_per_second": 14.391,
      "step": 1000
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.5393634840871025e-05,
      "loss": 0.1776,
      "step": 1100
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.49748743718593e-05,
      "loss": 0.2035,
      "step": 1200
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.4556113902847574e-05,
      "loss": 0.1199,
      "step": 1300
    },
    {
      "epoch": 1.17,
      "learning_rate": 4.413735343383585e-05,
      "loss": 0.1311,
      "step": 1400
    },
    {
      "epoch": 1.26,
      "learning_rate": 4.3718592964824124e-05,
      "loss": 0.1279,
      "step": 1500
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.32998324958124e-05,
      "loss": 0.1279,
      "step": 1600
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.288107202680067e-05,
      "loss": 0.1249,
      "step": 1700
    },
    {
      "epoch": 1.51,
      "learning_rate": 4.246231155778895e-05,
      "loss": 0.1354,
      "step": 1800
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.204355108877722e-05,
      "loss": 0.1407,
      "step": 1900
    },
    {
      "epoch": 1.67,
      "learning_rate": 4.16247906197655e-05,
      "loss": 0.1207,
      "step": 2000
    },
    {
      "epoch": 1.67,
      "eval_loss": 2.662675619125366,
      "eval_runtime": 20.7988,
      "eval_samples_per_second": 57.407,
      "eval_steps_per_second": 14.376,
      "step": 2000
    },
    {
      "epoch": 1.76,
      "learning_rate": 4.120603015075377e-05,
      "loss": 0.1439,
      "step": 2100
    },
    {
      "epoch": 1.84,
      "learning_rate": 4.078726968174205e-05,
      "loss": 0.1342,
      "step": 2200
    },
    {
      "epoch": 1.93,
      "learning_rate": 4.036850921273032e-05,
      "loss": 0.1251,
      "step": 2300
    },
    {
      "epoch": 2.01,
      "learning_rate": 3.9949748743718597e-05,
      "loss": 0.1242,
      "step": 2400
    },
    {
      "epoch": 2.09,
      "learning_rate": 3.953098827470687e-05,
      "loss": 0.0826,
      "step": 2500
    },
    {
      "epoch": 2.18,
      "learning_rate": 3.9112227805695146e-05,
      "loss": 0.0793,
      "step": 2600
    },
    {
      "epoch": 2.26,
      "learning_rate": 3.869346733668342e-05,
      "loss": 0.0874,
      "step": 2700
    },
    {
      "epoch": 2.34,
      "learning_rate": 3.8274706867671696e-05,
      "loss": 0.0992,
      "step": 2800
    },
    {
      "epoch": 2.43,
      "learning_rate": 3.785594639865997e-05,
      "loss": 0.088,
      "step": 2900
    },
    {
      "epoch": 2.51,
      "learning_rate": 3.7437185929648245e-05,
      "loss": 0.0768,
      "step": 3000
    },
    {
      "epoch": 2.51,
      "eval_loss": 2.742750406265259,
      "eval_runtime": 20.7709,
      "eval_samples_per_second": 57.484,
      "eval_steps_per_second": 14.395,
      "step": 3000
    },
    {
      "epoch": 2.6,
      "learning_rate": 3.701842546063652e-05,
      "loss": 0.0805,
      "step": 3100
    },
    {
      "epoch": 2.68,
      "learning_rate": 3.6599664991624795e-05,
      "loss": 0.0796,
      "step": 3200
    },
    {
      "epoch": 2.76,
      "learning_rate": 3.618090452261307e-05,
      "loss": 0.0819,
      "step": 3300
    },
    {
      "epoch": 2.85,
      "learning_rate": 3.5762144053601344e-05,
      "loss": 0.0844,
      "step": 3400
    },
    {
      "epoch": 2.93,
      "learning_rate": 3.534338358458962e-05,
      "loss": 0.081,
      "step": 3500
    },
    {
      "epoch": 3.01,
      "learning_rate": 3.4924623115577894e-05,
      "loss": 0.0796,
      "step": 3600
    },
    {
      "epoch": 3.1,
      "learning_rate": 3.450586264656617e-05,
      "loss": 0.0595,
      "step": 3700
    },
    {
      "epoch": 3.18,
      "learning_rate": 3.408710217755444e-05,
      "loss": 0.0481,
      "step": 3800
    },
    {
      "epoch": 3.27,
      "learning_rate": 3.366834170854272e-05,
      "loss": 0.0554,
      "step": 3900
    },
    {
      "epoch": 3.35,
      "learning_rate": 3.324958123953099e-05,
      "loss": 0.0566,
      "step": 4000
    },
    {
      "epoch": 3.35,
      "eval_loss": 2.823474407196045,
      "eval_runtime": 20.7588,
      "eval_samples_per_second": 57.518,
      "eval_steps_per_second": 14.404,
      "step": 4000
    },
    {
      "epoch": 3.43,
      "learning_rate": 3.283082077051927e-05,
      "loss": 0.0562,
      "step": 4100
    },
    {
      "epoch": 3.52,
      "learning_rate": 3.241206030150754e-05,
      "loss": 0.0584,
      "step": 4200
    },
    {
      "epoch": 3.6,
      "learning_rate": 3.199329983249582e-05,
      "loss": 0.0555,
      "step": 4300
    },
    {
      "epoch": 3.68,
      "learning_rate": 3.157453936348409e-05,
      "loss": 0.0446,
      "step": 4400
    },
    {
      "epoch": 3.77,
      "learning_rate": 3.1155778894472366e-05,
      "loss": 0.0559,
      "step": 4500
    },
    {
      "epoch": 3.85,
      "learning_rate": 3.073701842546064e-05,
      "loss": 0.0582,
      "step": 4600
    },
    {
      "epoch": 3.94,
      "learning_rate": 3.0318257956448916e-05,
      "loss": 0.0457,
      "step": 4700
    },
    {
      "epoch": 4.02,
      "learning_rate": 2.989949748743719e-05,
      "loss": 0.0486,
      "step": 4800
    },
    {
      "epoch": 4.1,
      "learning_rate": 2.9480737018425465e-05,
      "loss": 0.0292,
      "step": 4900
    },
    {
      "epoch": 4.19,
      "learning_rate": 2.906197654941374e-05,
      "loss": 0.0335,
      "step": 5000
    },
    {
      "epoch": 4.19,
      "eval_loss": 2.9011123180389404,
      "eval_runtime": 20.7527,
      "eval_samples_per_second": 57.535,
      "eval_steps_per_second": 14.408,
      "step": 5000
    },
    {
      "epoch": 4.27,
      "learning_rate": 2.8643216080402015e-05,
      "loss": 0.028,
      "step": 5100
    },
    {
      "epoch": 4.35,
      "learning_rate": 2.822445561139029e-05,
      "loss": 0.0317,
      "step": 5200
    },
    {
      "epoch": 4.44,
      "learning_rate": 2.7805695142378564e-05,
      "loss": 0.0392,
      "step": 5300
    },
    {
      "epoch": 4.52,
      "learning_rate": 2.738693467336684e-05,
      "loss": 0.035,
      "step": 5400
    },
    {
      "epoch": 4.6,
      "learning_rate": 2.696817420435511e-05,
      "loss": 0.0333,
      "step": 5500
    },
    {
      "epoch": 4.69,
      "learning_rate": 2.6549413735343385e-05,
      "loss": 0.0306,
      "step": 5600
    },
    {
      "epoch": 4.77,
      "learning_rate": 2.613065326633166e-05,
      "loss": 0.0427,
      "step": 5700
    },
    {
      "epoch": 4.86,
      "learning_rate": 2.5711892797319935e-05,
      "loss": 0.0249,
      "step": 5800
    },
    {
      "epoch": 4.94,
      "learning_rate": 2.529313232830821e-05,
      "loss": 0.0391,
      "step": 5900
    },
    {
      "epoch": 5.02,
      "learning_rate": 2.4874371859296484e-05,
      "loss": 0.0281,
      "step": 6000
    },
    {
      "epoch": 5.02,
      "eval_loss": 2.8658268451690674,
      "eval_runtime": 20.7258,
      "eval_samples_per_second": 57.609,
      "eval_steps_per_second": 14.426,
      "step": 6000
    },
    {
      "epoch": 5.11,
      "learning_rate": 2.445561139028476e-05,
      "loss": 0.0213,
      "step": 6100
    },
    {
      "epoch": 5.19,
      "learning_rate": 2.4036850921273034e-05,
      "loss": 0.0163,
      "step": 6200
    },
    {
      "epoch": 5.27,
      "learning_rate": 2.361809045226131e-05,
      "loss": 0.0166,
      "step": 6300
    },
    {
      "epoch": 5.36,
      "learning_rate": 2.3199329983249583e-05,
      "loss": 0.0161,
      "step": 6400
    },
    {
      "epoch": 5.44,
      "learning_rate": 2.2780569514237858e-05,
      "loss": 0.0241,
      "step": 6500
    },
    {
      "epoch": 5.53,
      "learning_rate": 2.2361809045226133e-05,
      "loss": 0.0237,
      "step": 6600
    },
    {
      "epoch": 5.61,
      "learning_rate": 2.1943048576214408e-05,
      "loss": 0.0143,
      "step": 6700
    },
    {
      "epoch": 5.69,
      "learning_rate": 2.1524288107202682e-05,
      "loss": 0.017,
      "step": 6800
    },
    {
      "epoch": 5.78,
      "learning_rate": 2.1105527638190957e-05,
      "loss": 0.0198,
      "step": 6900
    },
    {
      "epoch": 5.86,
      "learning_rate": 2.0686767169179232e-05,
      "loss": 0.0215,
      "step": 7000
    },
    {
      "epoch": 5.86,
      "eval_loss": 2.8833489418029785,
      "eval_runtime": 20.7599,
      "eval_samples_per_second": 57.515,
      "eval_steps_per_second": 14.403,
      "step": 7000
    },
    {
      "epoch": 5.94,
      "learning_rate": 2.0268006700167507e-05,
      "loss": 0.0197,
      "step": 7100
    },
    {
      "epoch": 6.03,
      "learning_rate": 1.984924623115578e-05,
      "loss": 0.0173,
      "step": 7200
    },
    {
      "epoch": 6.11,
      "learning_rate": 1.9430485762144056e-05,
      "loss": 0.015,
      "step": 7300
    },
    {
      "epoch": 6.2,
      "learning_rate": 1.901172529313233e-05,
      "loss": 0.0139,
      "step": 7400
    },
    {
      "epoch": 6.28,
      "learning_rate": 1.8592964824120602e-05,
      "loss": 0.0116,
      "step": 7500
    },
    {
      "epoch": 6.36,
      "learning_rate": 1.8174204355108877e-05,
      "loss": 0.0048,
      "step": 7600
    },
    {
      "epoch": 6.45,
      "learning_rate": 1.7755443886097152e-05,
      "loss": 0.0117,
      "step": 7700
    },
    {
      "epoch": 6.53,
      "learning_rate": 1.7336683417085427e-05,
      "loss": 0.0079,
      "step": 7800
    },
    {
      "epoch": 6.61,
      "learning_rate": 1.69179229480737e-05,
      "loss": 0.0095,
      "step": 7900
    },
    {
      "epoch": 6.7,
      "learning_rate": 1.6499162479061976e-05,
      "loss": 0.0081,
      "step": 8000
    },
    {
      "epoch": 6.7,
      "eval_loss": 2.974073648452759,
      "eval_runtime": 20.7629,
      "eval_samples_per_second": 57.506,
      "eval_steps_per_second": 14.401,
      "step": 8000
    },
    {
      "epoch": 6.78,
      "learning_rate": 1.608040201005025e-05,
      "loss": 0.0086,
      "step": 8100
    },
    {
      "epoch": 6.87,
      "learning_rate": 1.5661641541038526e-05,
      "loss": 0.013,
      "step": 8200
    },
    {
      "epoch": 6.95,
      "learning_rate": 1.5242881072026802e-05,
      "loss": 0.0079,
      "step": 8300
    }
  ],
  "logging_steps": 100,
  "max_steps": 11940,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 1.919599695983693e+16,
  "trial_name": null,
  "trial_params": null
}