{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0286,
  "global_step": 50000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1e-05,
      "loss": 6.2934,
      "step": 1000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 4.5891,
      "step": 2000
    },
    {
      "epoch": 0.01,
      "learning_rate": 3e-05,
      "loss": 3.6889,
      "step": 3000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 3.5628,
      "step": 4000
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 3.0405,
      "step": 5000
    },
    {
      "epoch": 0.03,
      "learning_rate": 6e-05,
      "loss": 1.9283,
      "step": 6000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7e-05,
      "loss": 1.694,
      "step": 7000
    },
    {
      "epoch": 0.04,
      "learning_rate": 8e-05,
      "loss": 1.4026,
      "step": 8000
    },
    {
      "epoch": 0.04,
      "learning_rate": 9e-05,
      "loss": 1.4236,
      "step": 9000
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 1.3469,
      "step": 10000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.2046,
      "step": 11000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.2526,
      "step": 12000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.1314,
      "step": 13000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.1873,
      "step": 14000
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.98292246503335e-05,
      "loss": 1.109,
      "step": 15000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.975414512725057e-05,
      "loss": 1.1241,
      "step": 16000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.966546331768191e-05,
      "loss": 1.1475,
      "step": 17000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.0234,
      "step": 18000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.944739353007344e-05,
      "loss": 1.0963,
      "step": 19000
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.931806517013612e-05,
      "loss": 1.0489,
      "step": 20000
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.917525374361912e-05,
      "loss": 1.043,
      "step": 21000
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.901899829374047e-05,
      "loss": 1.0831,
      "step": 22000
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.9691,
      "step": 23000
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.86663298624003e-05,
      "loss": 1.0388,
      "step": 24000
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.847001329696653e-05,
      "loss": 1.0023,
      "step": 25000
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.9834,
      "step": 26000
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.803768380684242e-05,
      "loss": 1.0336,
      "step": 27000
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.9267,
      "step": 28000
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.001,
      "step": 29000
    },
    {
      "epoch": 2.0,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.9167,
      "step": 30000
    },
    {
      "epoch": 2.01,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.9919,
      "step": 31000
    },
    {
      "epoch": 2.01,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.9983,
      "step": 32000
    },
    {
      "epoch": 2.02,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.9105,
      "step": 33000
    },
    {
      "epoch": 2.02,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.9767,
      "step": 34000
    },
    {
      "epoch": 2.03,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8995,
      "step": 35000
    },
    {
      "epoch": 2.03,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.9651,
      "step": 36000
    },
    {
      "epoch": 2.04,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.9688,
      "step": 37000
    },
    {
      "epoch": 2.04,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8861,
      "step": 38000
    },
    {
      "epoch": 2.05,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.9505,
      "step": 39000
    },
    {
      "epoch": 2.05,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.883,
      "step": 40000
    },
    {
      "epoch": 2.06,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.9406,
      "step": 41000
    },
    {
      "epoch": 2.06,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.9528,
      "step": 42000
    },
    {
      "epoch": 2.07,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.8694,
      "step": 43000
    },
    {
      "epoch": 2.07,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.9334,
      "step": 44000
    },
    {
      "epoch": 3.0,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.859,
      "step": 45000
    },
    {
      "epoch": 3.01,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.9242,
      "step": 46000
    },
    {
      "epoch": 3.01,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.8941,
      "step": 47000
    },
    {
      "epoch": 3.02,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8876,
      "step": 48000
    },
    {
      "epoch": 3.02,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.9315,
      "step": 49000
    },
    {
      "epoch": 3.03,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.8365,
      "step": 50000
    },
    {
      "epoch": 3.03,
      "eval_loss": 0.6204128861427307,
      "eval_runtime": 16.9348,
      "eval_samples_per_second": 295.25,
      "eval_steps_per_second": 2.362,
      "step": 50000
    }
  ],
  "max_steps": 200000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 8.422825643401544e+17,
  "trial_name": null,
  "trial_params": null
}