{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0343,
  "global_step": 100000,
  "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": 4.9742,
      "step": 1000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 3.2028,
      "step": 2000
    },
    {
      "epoch": 0.01,
      "learning_rate": 3e-05,
      "loss": 2.7868,
      "step": 3000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 2.4373,
      "step": 4000
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 2.1736,
      "step": 5000
    },
    {
      "epoch": 0.03,
      "learning_rate": 6e-05,
      "loss": 1.505,
      "step": 6000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7e-05,
      "loss": 1.4261,
      "step": 7000
    },
    {
      "epoch": 0.04,
      "learning_rate": 8e-05,
      "loss": 1.3269,
      "step": 8000
    },
    {
      "epoch": 0.04,
      "learning_rate": 9e-05,
      "loss": 1.1804,
      "step": 9000
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 1.1062,
      "step": 10000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.999316524962345e-05,
      "loss": 1.0042,
      "step": 11000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.997266286704631e-05,
      "loss": 1.1207,
      "step": 12000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.993849845741524e-05,
      "loss": 1.1057,
      "step": 13000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.0074,
      "step": 14000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.9714,
      "step": 15000
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.9125,
      "step": 16000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.9794,
      "step": 17000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.0198,
      "step": 18000
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.9468,
      "step": 19000
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.9073,
      "step": 20000
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.917525374361912e-05,
      "loss": 0.8919,
      "step": 21000
    },
    {
      "epoch": 0.11,
      "learning_rate": 9.901899829374047e-05,
      "loss": 0.8664,
      "step": 22000
    },
    {
      "epoch": 0.12,
      "learning_rate": 9.884934153917997e-05,
      "loss": 0.9437,
      "step": 23000
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.86663298624003e-05,
      "loss": 0.8504,
      "step": 24000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.847001329696653e-05,
      "loss": 0.9226,
      "step": 25000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.826044551386744e-05,
      "loss": 0.9327,
      "step": 26000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.803768380684242e-05,
      "loss": 0.8735,
      "step": 27000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.780178907671789e-05,
      "loss": 0.8495,
      "step": 28000
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.7825,
      "step": 29000
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.729086208503174e-05,
      "loss": 0.8995,
      "step": 30000
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.701596950580806e-05,
      "loss": 0.9189,
      "step": 31000
    },
    {
      "epoch": 1.04,
      "learning_rate": 9.672822322997305e-05,
      "loss": 0.8422,
      "step": 32000
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.642770192448536e-05,
      "loss": 0.8293,
      "step": 33000
    },
    {
      "epoch": 1.05,
      "learning_rate": 9.611448774886924e-05,
      "loss": 0.7942,
      "step": 34000
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.578866633275288e-05,
      "loss": 0.8259,
      "step": 35000
    },
    {
      "epoch": 1.06,
      "learning_rate": 9.545032675245813e-05,
      "loss": 0.8857,
      "step": 36000
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.509956150664796e-05,
      "loss": 0.8452,
      "step": 37000
    },
    {
      "epoch": 1.07,
      "learning_rate": 9.473646649103818e-05,
      "loss": 0.8053,
      "step": 38000
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.43611409721806e-05,
      "loss": 0.7982,
      "step": 39000
    },
    {
      "epoch": 1.08,
      "learning_rate": 9.397368756032445e-05,
      "loss": 0.7702,
      "step": 40000
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.357421218136386e-05,
      "loss": 0.8445,
      "step": 41000
    },
    {
      "epoch": 1.09,
      "learning_rate": 9.316282404787871e-05,
      "loss": 0.8462,
      "step": 42000
    },
    {
      "epoch": 1.1,
      "learning_rate": 9.273963562927695e-05,
      "loss": 0.7921,
      "step": 43000
    },
    {
      "epoch": 1.1,
      "learning_rate": 9.230476262104677e-05,
      "loss": 0.7774,
      "step": 44000
    },
    {
      "epoch": 1.11,
      "learning_rate": 9.185832391312644e-05,
      "loss": 0.7416,
      "step": 45000
    },
    {
      "epoch": 1.11,
      "learning_rate": 9.140044155740101e-05,
      "loss": 0.8354,
      "step": 46000
    },
    {
      "epoch": 2.0,
      "learning_rate": 9.093124073433463e-05,
      "loss": 0.7574,
      "step": 47000
    },
    {
      "epoch": 2.01,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.8271,
      "step": 48000
    },
    {
      "epoch": 2.01,
      "learning_rate": 8.995939984474624e-05,
      "loss": 0.8484,
      "step": 49000
    },
    {
      "epoch": 2.02,
      "learning_rate": 8.945702546981969e-05,
      "loss": 0.7902,
      "step": 50000
    },
    {
      "epoch": 2.02,
      "eval_loss": 0.6111912131309509,
      "eval_runtime": 16.8365,
      "eval_samples_per_second": 296.974,
      "eval_steps_per_second": 2.376,
      "step": 50000
    },
    {
      "epoch": 2.02,
      "learning_rate": 8.894386393810563e-05,
      "loss": 0.7754,
      "step": 51000
    },
    {
      "epoch": 2.03,
      "learning_rate": 8.842005554284296e-05,
      "loss": 0.7547,
      "step": 52000
    },
    {
      "epoch": 2.03,
      "learning_rate": 8.788574348801675e-05,
      "loss": 0.7562,
      "step": 53000
    },
    {
      "epoch": 2.04,
      "learning_rate": 8.73410738492077e-05,
      "loss": 0.8285,
      "step": 54000
    },
    {
      "epoch": 2.04,
      "learning_rate": 8.678619553365659e-05,
      "loss": 0.7984,
      "step": 55000
    },
    {
      "epoch": 2.05,
      "learning_rate": 8.622126023955446e-05,
      "loss": 0.7628,
      "step": 56000
    },
    {
      "epoch": 2.05,
      "learning_rate": 8.564642241456986e-05,
      "loss": 0.7491,
      "step": 57000
    },
    {
      "epoch": 2.06,
      "learning_rate": 8.506183921362443e-05,
      "loss": 0.7236,
      "step": 58000
    },
    {
      "epoch": 2.06,
      "learning_rate": 8.44676704559283e-05,
      "loss": 0.7943,
      "step": 59000
    },
    {
      "epoch": 2.07,
      "learning_rate": 8.386407858128706e-05,
      "loss": 0.8044,
      "step": 60000
    },
    {
      "epoch": 2.07,
      "learning_rate": 8.32512286056924e-05,
      "loss": 0.7512,
      "step": 61000
    },
    {
      "epoch": 2.08,
      "learning_rate": 8.262928807620843e-05,
      "loss": 0.7394,
      "step": 62000
    },
    {
      "epoch": 2.08,
      "learning_rate": 8.199842702516583e-05,
      "loss": 0.6992,
      "step": 63000
    },
    {
      "epoch": 2.09,
      "learning_rate": 8.135881792367686e-05,
      "loss": 0.7923,
      "step": 64000
    },
    {
      "epoch": 2.09,
      "learning_rate": 8.07106356344834e-05,
      "loss": 0.8017,
      "step": 65000
    },
    {
      "epoch": 2.1,
      "learning_rate": 8.005405736415126e-05,
      "loss": 0.7458,
      "step": 66000
    },
    {
      "epoch": 2.1,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.733,
      "step": 67000
    },
    {
      "epoch": 2.11,
      "learning_rate": 7.871643313414718e-05,
      "loss": 0.6762,
      "step": 68000
    },
    {
      "epoch": 2.11,
      "learning_rate": 7.803575286758364e-05,
      "loss": 0.7856,
      "step": 69000
    },
    {
      "epoch": 3.0,
      "learning_rate": 7.734740790612136e-05,
      "loss": 0.7869,
      "step": 70000
    },
    {
      "epoch": 3.01,
      "learning_rate": 7.66515864363997e-05,
      "loss": 0.7138,
      "step": 71000
    },
    {
      "epoch": 3.01,
      "learning_rate": 7.594847868906076e-05,
      "loss": 0.783,
      "step": 72000
    },
    {
      "epoch": 3.02,
      "learning_rate": 7.52382768867422e-05,
      "loss": 0.7764,
      "step": 73000
    },
    {
      "epoch": 3.02,
      "learning_rate": 7.452117519152542e-05,
      "loss": 0.734,
      "step": 74000
    },
    {
      "epoch": 3.03,
      "learning_rate": 7.379736965185368e-05,
      "loss": 0.7214,
      "step": 75000
    },
    {
      "epoch": 3.03,
      "learning_rate": 7.30670581489344e-05,
      "loss": 0.6889,
      "step": 76000
    },
    {
      "epoch": 3.04,
      "learning_rate": 7.233044034264034e-05,
      "loss": 0.7645,
      "step": 77000
    },
    {
      "epoch": 3.04,
      "learning_rate": 7.158771761692464e-05,
      "loss": 0.7769,
      "step": 78000
    },
    {
      "epoch": 3.05,
      "learning_rate": 7.083909302476453e-05,
      "loss": 0.7248,
      "step": 79000
    },
    {
      "epoch": 3.05,
      "learning_rate": 7.008477123264848e-05,
      "loss": 0.712,
      "step": 80000
    },
    {
      "epoch": 3.06,
      "learning_rate": 6.932495846462261e-05,
      "loss": 0.6695,
      "step": 81000
    },
    {
      "epoch": 3.06,
      "learning_rate": 6.855986244591104e-05,
      "loss": 0.7599,
      "step": 82000
    },
    {
      "epoch": 3.07,
      "learning_rate": 6.778969234612584e-05,
      "loss": 0.7775,
      "step": 83000
    },
    {
      "epoch": 3.07,
      "learning_rate": 6.701465872208216e-05,
      "loss": 0.721,
      "step": 84000
    },
    {
      "epoch": 3.08,
      "learning_rate": 6.623497346023418e-05,
      "loss": 0.7063,
      "step": 85000
    },
    {
      "epoch": 3.08,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.6491,
      "step": 86000
    },
    {
      "epoch": 3.09,
      "learning_rate": 6.466250186922325e-05,
      "loss": 0.7574,
      "step": 87000
    },
    {
      "epoch": 3.09,
      "learning_rate": 6.387014543809223e-05,
      "loss": 0.7797,
      "step": 88000
    },
    {
      "epoch": 3.1,
      "learning_rate": 6.307399704769099e-05,
      "loss": 0.7137,
      "step": 89000
    },
    {
      "epoch": 3.1,
      "learning_rate": 6.227427435703997e-05,
      "loss": 0.7049,
      "step": 90000
    },
    {
      "epoch": 3.11,
      "learning_rate": 6.147119600233758e-05,
      "loss": 0.6887,
      "step": 91000
    },
    {
      "epoch": 3.11,
      "learning_rate": 6.066498153718735e-05,
      "loss": 0.696,
      "step": 92000
    },
    {
      "epoch": 3.12,
      "learning_rate": 5.985585137257401e-05,
      "loss": 0.7601,
      "step": 93000
    },
    {
      "epoch": 4.0,
      "learning_rate": 5.90440267166055e-05,
      "loss": 0.6706,
      "step": 94000
    },
    {
      "epoch": 4.01,
      "learning_rate": 5.8229729514036705e-05,
      "loss": 0.7382,
      "step": 95000
    },
    {
      "epoch": 4.01,
      "learning_rate": 5.74131823855921e-05,
      "loss": 0.7557,
      "step": 96000
    },
    {
      "epoch": 4.02,
      "learning_rate": 5.6594608567103456e-05,
      "loss": 0.7053,
      "step": 97000
    },
    {
      "epoch": 4.02,
      "learning_rate": 5.577423184847932e-05,
      "loss": 0.6898,
      "step": 98000
    },
    {
      "epoch": 4.03,
      "learning_rate": 5.495227651252315e-05,
      "loss": 0.6446,
      "step": 99000
    },
    {
      "epoch": 4.03,
      "learning_rate": 5.4128967273616625e-05,
      "loss": 0.7387,
      "step": 100000
    },
    {
      "epoch": 4.03,
      "eval_loss": 0.534711480140686,
      "eval_runtime": 10.2682,
      "eval_samples_per_second": 486.942,
      "eval_steps_per_second": 3.896,
      "step": 100000
    }
  ],
  "max_steps": 200000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 1.6845398605824e+18,
  "trial_name": null,
  "trial_params": null
}