{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9999800466907437,
  "global_step": 25058,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 4.900830074227792e-05,
      "loss": 3.3225,
      "step": 500
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.801061537233618e-05,
      "loss": 2.3912,
      "step": 1000
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.701293000239445e-05,
      "loss": 2.1243,
      "step": 1500
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.6015244632452715e-05,
      "loss": 1.989,
      "step": 2000
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.5017559262510976e-05,
      "loss": 1.889,
      "step": 2500
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.401987389256924e-05,
      "loss": 1.808,
      "step": 3000
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.3022188522627504e-05,
      "loss": 1.7416,
      "step": 3500
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.202649852342566e-05,
      "loss": 1.7027,
      "step": 4000
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.102881315348392e-05,
      "loss": 1.6679,
      "step": 4500
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.003112778354218e-05,
      "loss": 1.6188,
      "step": 5000
    },
    {
      "epoch": 0.22,
      "learning_rate": 3.903344241360045e-05,
      "loss": 1.5844,
      "step": 5500
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.8035757043658716e-05,
      "loss": 1.5613,
      "step": 6000
    },
    {
      "epoch": 0.26,
      "learning_rate": 3.7038071673716977e-05,
      "loss": 1.5266,
      "step": 6500
    },
    {
      "epoch": 0.28,
      "learning_rate": 3.6040386303775244e-05,
      "loss": 1.5123,
      "step": 7000
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.5042700933833505e-05,
      "loss": 1.472,
      "step": 7500
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.404501556389177e-05,
      "loss": 1.4397,
      "step": 8000
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.304733019395004e-05,
      "loss": 1.4177,
      "step": 8500
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.20496448240083e-05,
      "loss": 1.4125,
      "step": 9000
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.105195945406657e-05,
      "loss": 1.3836,
      "step": 9500
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.0054274084124832e-05,
      "loss": 1.368,
      "step": 10000
    },
    {
      "epoch": 0.42,
      "learning_rate": 2.9056588714183096e-05,
      "loss": 1.3567,
      "step": 10500
    },
    {
      "epoch": 0.44,
      "learning_rate": 2.805890334424136e-05,
      "loss": 1.3294,
      "step": 11000
    },
    {
      "epoch": 0.46,
      "learning_rate": 2.7063213345039512e-05,
      "loss": 1.3221,
      "step": 11500
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.6065527975097776e-05,
      "loss": 1.3013,
      "step": 12000
    },
    {
      "epoch": 0.5,
      "learning_rate": 2.5067842605156037e-05,
      "loss": 1.3042,
      "step": 12500
    },
    {
      "epoch": 0.52,
      "learning_rate": 2.4070157235214305e-05,
      "loss": 1.2593,
      "step": 13000
    },
    {
      "epoch": 0.54,
      "learning_rate": 2.307247186527257e-05,
      "loss": 1.2566,
      "step": 13500
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.2076781866070717e-05,
      "loss": 1.2441,
      "step": 14000
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.107909649612898e-05,
      "loss": 1.2255,
      "step": 14500
    },
    {
      "epoch": 0.6,
      "learning_rate": 2.0081411126187246e-05,
      "loss": 1.2176,
      "step": 15000
    },
    {
      "epoch": 0.62,
      "learning_rate": 1.908372575624551e-05,
      "loss": 1.212,
      "step": 15500
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.8086040386303777e-05,
      "loss": 1.1993,
      "step": 16000
    },
    {
      "epoch": 0.66,
      "learning_rate": 1.708835501636204e-05,
      "loss": 1.1604,
      "step": 16500
    },
    {
      "epoch": 0.68,
      "learning_rate": 1.609266501716019e-05,
      "loss": 1.201,
      "step": 17000
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.5094979647218454e-05,
      "loss": 1.1614,
      "step": 17500
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.4097294277276718e-05,
      "loss": 1.1584,
      "step": 18000
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.3099608907334984e-05,
      "loss": 1.1534,
      "step": 18500
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.2101923537393248e-05,
      "loss": 1.1386,
      "step": 19000
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.1104238167451512e-05,
      "loss": 1.1231,
      "step": 19500
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.0106552797509778e-05,
      "loss": 1.1396,
      "step": 20000
    },
    {
      "epoch": 0.82,
      "learning_rate": 9.108867427568042e-06,
      "loss": 1.1261,
      "step": 20500
    },
    {
      "epoch": 0.84,
      "learning_rate": 8.11317742836619e-06,
      "loss": 1.1098,
      "step": 21000
    },
    {
      "epoch": 0.86,
      "learning_rate": 7.1154920584244555e-06,
      "loss": 1.1006,
      "step": 21500
    },
    {
      "epoch": 0.88,
      "learning_rate": 6.1178066884827205e-06,
      "loss": 1.099,
      "step": 22000
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.1201213185409855e-06,
      "loss": 1.1121,
      "step": 22500
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.12243594859925e-06,
      "loss": 1.108,
      "step": 23000
    },
    {
      "epoch": 0.94,
      "learning_rate": 3.124750578657515e-06,
      "loss": 1.0903,
      "step": 23500
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.129060579455663e-06,
      "loss": 1.0892,
      "step": 24000
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.1313752095139278e-06,
      "loss": 1.0597,
      "step": 24500
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.3368983957219251e-07,
      "loss": 1.0854,
      "step": 25000
    },
    {
      "epoch": 1.0,
      "step": 25058,
      "total_flos": 7.377974265999974e+16,
      "train_loss": 1.4067512356623162,
      "train_runtime": 5393.9428,
      "train_samples_per_second": 148.66,
      "train_steps_per_second": 4.646
    }
  ],
  "max_steps": 25058,
  "num_train_epochs": 1,
  "total_flos": 7.377974265999974e+16,
  "trial_name": null,
  "trial_params": null
}