{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1,
  "global_step": 100000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 4.7524,
      "step": 1000
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.5548,
      "step": 2000
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-06,
      "loss": 2.9636,
      "step": 3000
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.7618,
      "step": 4000
    },
    {
      "epoch": 0.01,
      "learning_rate": 1e-05,
      "loss": 2.6257,
      "step": 5000
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 2.5517,
      "step": 6000
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.4628,
      "step": 7000
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.4338,
      "step": 8000
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.8e-05,
      "loss": 2.3362,
      "step": 9000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 2.2746,
      "step": 10000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 2.1795,
      "step": 11000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4e-05,
      "loss": 2.2309,
      "step": 12000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.8605,
      "step": 13000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.7232,
      "step": 14000
    },
    {
      "epoch": 0.01,
      "learning_rate": 3e-05,
      "loss": 1.6872,
      "step": 15000
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.1581,
      "step": 16000
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 2.0653,
      "step": 17000
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.6e-05,
      "loss": 2.049,
      "step": 18000
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.8e-05,
      "loss": 2.0773,
      "step": 19000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 1.9397,
      "step": 20000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.2e-05,
      "loss": 1.8899,
      "step": 21000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.8474,
      "step": 22000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.8034,
      "step": 23000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8e-05,
      "loss": 1.7666,
      "step": 24000
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 1.7899,
      "step": 25000
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.4265,
      "step": 26000
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.3535,
      "step": 27000
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.1703,
      "step": 28000
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.8e-05,
      "loss": 1.129,
      "step": 29000
    },
    {
      "epoch": 0.03,
      "learning_rate": 6e-05,
      "loss": 1.2811,
      "step": 30000
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.2e-05,
      "loss": 1.2189,
      "step": 31000
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.4371,
      "step": 32000
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.6e-05,
      "loss": 1.3551,
      "step": 33000
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.3616,
      "step": 34000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7e-05,
      "loss": 1.2483,
      "step": 35000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.2e-05,
      "loss": 1.2174,
      "step": 36000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.4e-05,
      "loss": 1.1861,
      "step": 37000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.6e-05,
      "loss": 1.1465,
      "step": 38000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.800000000000001e-05,
      "loss": 1.1957,
      "step": 39000
    },
    {
      "epoch": 0.04,
      "learning_rate": 8e-05,
      "loss": 1.136,
      "step": 40000
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.2e-05,
      "loss": 1.1122,
      "step": 41000
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.4e-05,
      "loss": 1.0905,
      "step": 42000
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.6e-05,
      "loss": 1.0996,
      "step": 43000
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.0632,
      "step": 44000
    },
    {
      "epoch": 0.04,
      "learning_rate": 9e-05,
      "loss": 1.1387,
      "step": 45000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.2049,
      "step": 46000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.4e-05,
      "loss": 1.1783,
      "step": 47000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.6e-05,
      "loss": 1.1043,
      "step": 48000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.8e-05,
      "loss": 1.0633,
      "step": 49000
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 1.1331,
      "step": 50000
    },
    {
      "epoch": 0.05,
      "eval_loss": 0.753776490688324,
      "eval_runtime": 33.8225,
      "eval_samples_per_second": 147.83,
      "eval_steps_per_second": 2.336,
      "step": 50000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.999972660400536e-05,
      "loss": 0.9559,
      "step": 51000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.999890641901125e-05,
      "loss": 0.9156,
      "step": 52000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.999753945398704e-05,
      "loss": 0.9237,
      "step": 53000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.99956257238817e-05,
      "loss": 0.9444,
      "step": 54000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.9576,
      "step": 55000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.999015805811965e-05,
      "loss": 0.994,
      "step": 56000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.998660418225645e-05,
      "loss": 1.1439,
      "step": 57000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.998250366089848e-05,
      "loss": 1.0131,
      "step": 58000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.997785653888835e-05,
      "loss": 1.0879,
      "step": 59000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.925,
      "step": 60000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.996692270216947e-05,
      "loss": 0.9413,
      "step": 61000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.996063610703137e-05,
      "loss": 0.8956,
      "step": 62000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.995380315038119e-05,
      "loss": 0.8672,
      "step": 63000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.994642390694308e-05,
      "loss": 0.8875,
      "step": 64000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.9124,
      "step": 65000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.993002688846913e-05,
      "loss": 0.9428,
      "step": 66000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.992100929274846e-05,
      "loss": 0.9931,
      "step": 67000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.991144576886823e-05,
      "loss": 1.1243,
      "step": 68000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.990133642141359e-05,
      "loss": 0.9759,
      "step": 69000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.989068136093873e-05,
      "loss": 1.0443,
      "step": 70000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.987948070396571e-05,
      "loss": 0.9112,
      "step": 71000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.986773457298311e-05,
      "loss": 0.9212,
      "step": 72000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.985544309644475e-05,
      "loss": 0.8929,
      "step": 73000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.984260640876821e-05,
      "loss": 0.8609,
      "step": 74000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.8797,
      "step": 75000
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.981529796748134e-05,
      "loss": 0.9014,
      "step": 76000
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.980082651251175e-05,
      "loss": 0.9251,
      "step": 77000
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.97858104436822e-05,
      "loss": 0.988,
      "step": 78000
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.977024992520602e-05,
      "loss": 1.0805,
      "step": 79000
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.9457,
      "step": 80000
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.973749622593534e-05,
      "loss": 0.9887,
      "step": 81000
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.972030340333001e-05,
      "loss": 0.8866,
      "step": 82000
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.970256684745258e-05,
      "loss": 0.8843,
      "step": 83000
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.968428675226714e-05,
      "loss": 0.8685,
      "step": 84000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.8369,
      "step": 85000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.964609674954696e-05,
      "loss": 0.8639,
      "step": 86000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.962618725965196e-05,
      "loss": 0.881,
      "step": 87000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.8954,
      "step": 88000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.95847403914247e-05,
      "loss": 0.9711,
      "step": 89000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.956320346634876e-05,
      "loss": 1.0358,
      "step": 90000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.954112452602045e-05,
      "loss": 0.927,
      "step": 91000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.95185038118915e-05,
      "loss": 0.9126,
      "step": 92000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.949534157133844e-05,
      "loss": 0.8692,
      "step": 93000
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.94716380576598e-05,
      "loss": 0.8355,
      "step": 94000
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.8358,
      "step": 95000
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.942260825371358e-05,
      "loss": 0.8086,
      "step": 96000
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.939728249962807e-05,
      "loss": 0.8348,
      "step": 97000
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.937141654477528e-05,
      "loss": 0.8471,
      "step": 98000
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.934501067202117e-05,
      "loss": 0.8733,
      "step": 99000
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.9549,
      "step": 100000
    },
    {
      "epoch": 0.1,
      "eval_loss": 0.777112603187561,
      "eval_runtime": 32.3706,
      "eval_samples_per_second": 154.461,
      "eval_steps_per_second": 2.44,
      "step": 100000
    }
  ],
  "max_steps": 1000000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 5.9649898315776e+18,
  "trial_name": null,
  "trial_params": null
}