{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.025175,
  "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": 5.5038,
      "step": 1000
    },
    {
      "epoch": 0.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.8672,
      "step": 2000
    },
    {
      "epoch": 0.0,
      "learning_rate": 6e-06,
      "loss": 3.2766,
      "step": 3000
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 3.0282,
      "step": 4000
    },
    {
      "epoch": 0.01,
      "learning_rate": 1e-05,
      "loss": 2.9102,
      "step": 5000
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.2e-05,
      "loss": 2.4652,
      "step": 6000
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.4442,
      "step": 7000
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.3615,
      "step": 8000
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.8e-05,
      "loss": 2.3086,
      "step": 9000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 1.9953,
      "step": 10000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 2.0225,
      "step": 11000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.4e-05,
      "loss": 1.9861,
      "step": 12000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.9702,
      "step": 13000
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.7159,
      "step": 14000
    },
    {
      "epoch": 0.01,
      "learning_rate": 3e-05,
      "loss": 1.7636,
      "step": 15000
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.7657,
      "step": 16000
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.7626,
      "step": 17000
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.6e-05,
      "loss": 1.5361,
      "step": 18000
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.8e-05,
      "loss": 1.5983,
      "step": 19000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4e-05,
      "loss": 1.6259,
      "step": 20000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.2e-05,
      "loss": 1.6412,
      "step": 21000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.4312,
      "step": 22000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.4999,
      "step": 23000
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.8e-05,
      "loss": 1.5345,
      "step": 24000
    },
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 1.5499,
      "step": 25000
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.1287,
      "step": 26000
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.0482,
      "step": 27000
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.1469,
      "step": 28000
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.8e-05,
      "loss": 1.1014,
      "step": 29000
    },
    {
      "epoch": 0.03,
      "learning_rate": 6e-05,
      "loss": 0.892,
      "step": 30000
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.2e-05,
      "loss": 0.9009,
      "step": 31000
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.0052,
      "step": 32000
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.6e-05,
      "loss": 0.9948,
      "step": 33000
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.800000000000001e-05,
      "loss": 0.8196,
      "step": 34000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7e-05,
      "loss": 0.8326,
      "step": 35000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.2e-05,
      "loss": 0.9323,
      "step": 36000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.4e-05,
      "loss": 0.9235,
      "step": 37000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.6e-05,
      "loss": 0.7571,
      "step": 38000
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.7897,
      "step": 39000
    },
    {
      "epoch": 0.04,
      "learning_rate": 8e-05,
      "loss": 0.8974,
      "step": 40000
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.2e-05,
      "loss": 0.8626,
      "step": 41000
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.4e-05,
      "loss": 0.7038,
      "step": 42000
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.6e-05,
      "loss": 0.8287,
      "step": 43000
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.8792,
      "step": 44000
    },
    {
      "epoch": 0.04,
      "learning_rate": 9e-05,
      "loss": 0.8538,
      "step": 45000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.6968,
      "step": 46000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.4e-05,
      "loss": 0.7232,
      "step": 47000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.6e-05,
      "loss": 0.8358,
      "step": 48000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.8e-05,
      "loss": 0.8355,
      "step": 49000
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 0.6348,
      "step": 50000
    },
    {
      "epoch": 0.05,
      "eval_loss": 0.5932290554046631,
      "eval_runtime": 30.1295,
      "eval_samples_per_second": 165.95,
      "eval_steps_per_second": 2.622,
      "step": 50000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.999972660400536e-05,
      "loss": 0.6375,
      "step": 51000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.999890641901125e-05,
      "loss": 0.7625,
      "step": 52000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.999753945398704e-05,
      "loss": 0.7111,
      "step": 53000
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.99956257238817e-05,
      "loss": 0.5652,
      "step": 54000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.999316524962345e-05,
      "loss": 0.5796,
      "step": 55000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.999015805811965e-05,
      "loss": 0.7634,
      "step": 56000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.998660418225645e-05,
      "loss": 0.7296,
      "step": 57000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.998250366089848e-05,
      "loss": 0.5758,
      "step": 58000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.997785653888835e-05,
      "loss": 0.6196,
      "step": 59000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.997266286704631e-05,
      "loss": 0.7018,
      "step": 60000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.996692270216947e-05,
      "loss": 0.6875,
      "step": 61000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.996063610703137e-05,
      "loss": 0.6113,
      "step": 62000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.995380315038119e-05,
      "loss": 0.7141,
      "step": 63000
    },
    {
      "epoch": 0.06,
      "learning_rate": 9.994642390694308e-05,
      "loss": 0.814,
      "step": 64000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.993849845741524e-05,
      "loss": 0.7573,
      "step": 65000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.993002688846913e-05,
      "loss": 0.6522,
      "step": 66000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.992100929274846e-05,
      "loss": 0.6774,
      "step": 67000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.991144576886823e-05,
      "loss": 0.7855,
      "step": 68000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.990133642141359e-05,
      "loss": 0.7461,
      "step": 69000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.989068136093873e-05,
      "loss": 0.634,
      "step": 70000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.987948070396571e-05,
      "loss": 0.6621,
      "step": 71000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.986773457298311e-05,
      "loss": 0.769,
      "step": 72000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.985544309644475e-05,
      "loss": 0.7128,
      "step": 73000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.984260640876821e-05,
      "loss": 0.6125,
      "step": 74000
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.98292246503335e-05,
      "loss": 0.6764,
      "step": 75000
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.981529796748134e-05,
      "loss": 0.7392,
      "step": 76000
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.980082651251175e-05,
      "loss": 0.6323,
      "step": 77000
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.97858104436822e-05,
      "loss": 0.6628,
      "step": 78000
    },
    {
      "epoch": 1.0,
      "learning_rate": 9.977024992520602e-05,
      "loss": 0.7715,
      "step": 79000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.975414512725057e-05,
      "loss": 0.7154,
      "step": 80000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.973749622593534e-05,
      "loss": 0.6102,
      "step": 81000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.972030340333001e-05,
      "loss": 0.6467,
      "step": 82000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.970256684745258e-05,
      "loss": 0.7534,
      "step": 83000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.968428675226714e-05,
      "loss": 0.704,
      "step": 84000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.966546331768191e-05,
      "loss": 0.6225,
      "step": 85000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.964609674954696e-05,
      "loss": 0.6437,
      "step": 86000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.962618725965196e-05,
      "loss": 0.754,
      "step": 87000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.96057350657239e-05,
      "loss": 0.6902,
      "step": 88000
    },
    {
      "epoch": 1.01,
      "learning_rate": 9.95847403914247e-05,
      "loss": 0.6096,
      "step": 89000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.956320346634876e-05,
      "loss": 0.6426,
      "step": 90000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.954112452602045e-05,
      "loss": 0.7444,
      "step": 91000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.95185038118915e-05,
      "loss": 0.6821,
      "step": 92000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.949534157133844e-05,
      "loss": 0.5948,
      "step": 93000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.94716380576598e-05,
      "loss": 0.6266,
      "step": 94000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.944739353007344e-05,
      "loss": 0.7387,
      "step": 95000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.942260825371358e-05,
      "loss": 0.6734,
      "step": 96000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.939728249962807e-05,
      "loss": 0.5943,
      "step": 97000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.937141654477528e-05,
      "loss": 0.6332,
      "step": 98000
    },
    {
      "epoch": 1.02,
      "learning_rate": 9.934501067202117e-05,
      "loss": 0.7306,
      "step": 99000
    },
    {
      "epoch": 1.03,
      "learning_rate": 9.931806517013612e-05,
      "loss": 0.6654,
      "step": 100000
    },
    {
      "epoch": 1.03,
      "eval_loss": 0.4750686585903168,
      "eval_runtime": 31.9311,
      "eval_samples_per_second": 156.587,
      "eval_steps_per_second": 2.474,
      "step": 100000
    }
  ],
  "max_steps": 1000000,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 5.965012200289468e+18,
  "trial_name": null,
  "trial_params": null
}