{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1580436540016168,
  "global_step": 45840,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 8.9186,
      "step": 500
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 3.7382,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 3.0114,
      "step": 1500
    },
    {
      "epoch": 0.05,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 2.4521,
      "step": 2000
    },
    {
      "epoch": 0.06,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 1.9839,
      "step": 2500
    },
    {
      "epoch": 0.08,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 1.5945,
      "step": 3000
    },
    {
      "epoch": 0.09,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 1.2823,
      "step": 3500
    },
    {
      "epoch": 0.1,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 1.0479,
      "step": 4000
    },
    {
      "epoch": 0.11,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.8997,
      "step": 4500
    },
    {
      "epoch": 0.13,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.8052,
      "step": 5000
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.7506,
      "step": 5500
    },
    {
      "epoch": 0.15,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.7126,
      "step": 6000
    },
    {
      "epoch": 0.16,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.696,
      "step": 6500
    },
    {
      "epoch": 0.18,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6808,
      "step": 7000
    },
    {
      "epoch": 0.19,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6715,
      "step": 7500
    },
    {
      "epoch": 0.2,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6636,
      "step": 8000
    },
    {
      "epoch": 0.21,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6554,
      "step": 8500
    },
    {
      "epoch": 0.23,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6506,
      "step": 9000
    },
    {
      "epoch": 0.24,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.646,
      "step": 9500
    },
    {
      "epoch": 0.25,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6389,
      "step": 10000
    },
    {
      "epoch": 0.27,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6308,
      "step": 10500
    },
    {
      "epoch": 0.28,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6298,
      "step": 11000
    },
    {
      "epoch": 0.29,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6256,
      "step": 11500
    },
    {
      "epoch": 0.3,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6244,
      "step": 12000
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6201,
      "step": 12500
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6163,
      "step": 13000
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6152,
      "step": 13500
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6132,
      "step": 14000
    },
    {
      "epoch": 0.37,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6104,
      "step": 14500
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6037,
      "step": 15000
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6019,
      "step": 15500
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6027,
      "step": 16000
    },
    {
      "epoch": 0.42,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.6024,
      "step": 16500
    },
    {
      "epoch": 0.43,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5963,
      "step": 17000
    },
    {
      "epoch": 0.44,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5961,
      "step": 17500
    },
    {
      "epoch": 0.45,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.593,
      "step": 18000
    },
    {
      "epoch": 0.47,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5918,
      "step": 18500
    },
    {
      "epoch": 0.48,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5893,
      "step": 19000
    },
    {
      "epoch": 0.49,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5913,
      "step": 19500
    },
    {
      "epoch": 0.51,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5885,
      "step": 20000
    },
    {
      "epoch": 0.52,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5867,
      "step": 20500
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5836,
      "step": 21000
    },
    {
      "epoch": 0.54,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5849,
      "step": 21500
    },
    {
      "epoch": 0.56,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5826,
      "step": 22000
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5821,
      "step": 22500
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5781,
      "step": 23000
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5791,
      "step": 23500
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5805,
      "step": 24000
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.572,
      "step": 24500
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5704,
      "step": 25000
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5731,
      "step": 25500
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.568,
      "step": 26000
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5733,
      "step": 26500
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5692,
      "step": 27000
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5692,
      "step": 27500
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5684,
      "step": 28000
    },
    {
      "epoch": 0.72,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5685,
      "step": 28500
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5631,
      "step": 29000
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.564,
      "step": 29500
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5647,
      "step": 30000
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5615,
      "step": 30500
    },
    {
      "epoch": 0.78,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5608,
      "step": 31000
    },
    {
      "epoch": 0.8,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5616,
      "step": 31500
    },
    {
      "epoch": 0.81,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5602,
      "step": 32000
    },
    {
      "epoch": 0.82,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.56,
      "step": 32500
    },
    {
      "epoch": 0.83,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5596,
      "step": 33000
    },
    {
      "epoch": 0.85,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5558,
      "step": 33500
    },
    {
      "epoch": 0.86,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5565,
      "step": 34000
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.557,
      "step": 34500
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5531,
      "step": 35000
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5526,
      "step": 35500
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5533,
      "step": 36000
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5539,
      "step": 36500
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5494,
      "step": 37000
    },
    {
      "epoch": 0.95,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5505,
      "step": 37500
    },
    {
      "epoch": 0.96,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5483,
      "step": 38000
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.549,
      "step": 38500
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5465,
      "step": 39000
    },
    {
      "epoch": 1.0,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.547,
      "step": 39500
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.5191423892974854,
      "eval_runtime": 289.9374,
      "eval_samples_per_second": 86.226,
      "eval_steps_per_second": 7.188,
      "step": 39584
    },
    {
      "epoch": 1.01,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5462,
      "step": 40000
    },
    {
      "epoch": 1.02,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5449,
      "step": 40500
    },
    {
      "epoch": 1.04,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5452,
      "step": 41000
    },
    {
      "epoch": 1.05,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5442,
      "step": 41500
    },
    {
      "epoch": 1.06,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5437,
      "step": 42000
    },
    {
      "epoch": 1.07,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5396,
      "step": 42500
    },
    {
      "epoch": 1.09,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5384,
      "step": 43000
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5396,
      "step": 43500
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5382,
      "step": 44000
    },
    {
      "epoch": 1.12,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5357,
      "step": 44500
    },
    {
      "epoch": 1.14,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5376,
      "step": 45000
    },
    {
      "epoch": 1.15,
      "learning_rate": 3.0000000000000005e-06,
      "loss": 0.5343,
      "step": 45500
    }
  ],
  "max_steps": 197920,
  "num_train_epochs": 5,
  "total_flos": 2.435936360767488e+16,
  "trial_name": null,
  "trial_params": null
}