{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "global_step": 6400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 1.5625e-06,
      "loss": 2.6055,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.125e-06,
      "loss": 2.6479,
      "step": 200
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.6875000000000004e-06,
      "loss": 2.6039,
      "step": 300
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.25e-06,
      "loss": 2.6115,
      "step": 400
    },
    {
      "epoch": 0.08,
      "learning_rate": 7.8125e-06,
      "loss": 2.5965,
      "step": 500
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.375000000000001e-06,
      "loss": 2.5992,
      "step": 600
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.09375e-05,
      "loss": 2.6191,
      "step": 700
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.25e-05,
      "loss": 2.5917,
      "step": 800
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.4062500000000001e-05,
      "loss": 2.5972,
      "step": 900
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.5625e-05,
      "loss": 2.5517,
      "step": 1000
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.71875e-05,
      "loss": 2.5635,
      "step": 1100
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 2.5634,
      "step": 1200
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.0312500000000002e-05,
      "loss": 2.554,
      "step": 1300
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.1875e-05,
      "loss": 2.559,
      "step": 1400
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.34375e-05,
      "loss": 2.5601,
      "step": 1500
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.5e-05,
      "loss": 2.5275,
      "step": 1600
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.6562500000000002e-05,
      "loss": 2.5367,
      "step": 1700
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.8125000000000003e-05,
      "loss": 2.5423,
      "step": 1800
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.96875e-05,
      "loss": 2.4997,
      "step": 1900
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.125e-05,
      "loss": 2.5041,
      "step": 2000
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.2812500000000005e-05,
      "loss": 2.5048,
      "step": 2100
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.4375e-05,
      "loss": 2.4889,
      "step": 2200
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.59375e-05,
      "loss": 2.507,
      "step": 2300
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 2.4832,
      "step": 2400
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.90625e-05,
      "loss": 2.4661,
      "step": 2500
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 2.4704,
      "step": 2600
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.21875e-05,
      "loss": 2.4762,
      "step": 2700
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.375e-05,
      "loss": 2.4511,
      "step": 2800
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.5312500000000004e-05,
      "loss": 2.4563,
      "step": 2900
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.6875e-05,
      "loss": 2.4755,
      "step": 3000
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.8437500000000005e-05,
      "loss": 2.483,
      "step": 3100
    },
    {
      "epoch": 0.5,
      "learning_rate": 5e-05,
      "loss": 2.4765,
      "step": 3200
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.15625e-05,
      "loss": 2.4527,
      "step": 3300
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.3125000000000004e-05,
      "loss": 2.467,
      "step": 3400
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.46875e-05,
      "loss": 2.4261,
      "step": 3500
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.6250000000000005e-05,
      "loss": 2.4484,
      "step": 3600
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.78125e-05,
      "loss": 2.428,
      "step": 3700
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.9375e-05,
      "loss": 2.4456,
      "step": 3800
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.0937500000000004e-05,
      "loss": 2.4489,
      "step": 3900
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.25e-05,
      "loss": 2.4524,
      "step": 4000
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.40625e-05,
      "loss": 2.4575,
      "step": 4100
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.562500000000001e-05,
      "loss": 2.434,
      "step": 4200
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.71875e-05,
      "loss": 2.4343,
      "step": 4300
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.875e-05,
      "loss": 2.4481,
      "step": 4400
    },
    {
      "epoch": 0.7,
      "learning_rate": 7.031250000000001e-05,
      "loss": 2.4392,
      "step": 4500
    },
    {
      "epoch": 0.72,
      "learning_rate": 7.1875e-05,
      "loss": 2.4047,
      "step": 4600
    },
    {
      "epoch": 0.73,
      "learning_rate": 7.34375e-05,
      "loss": 2.4314,
      "step": 4700
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.4137,
      "step": 4800
    },
    {
      "epoch": 0.77,
      "learning_rate": 7.65625e-05,
      "loss": 2.4424,
      "step": 4900
    },
    {
      "epoch": 0.78,
      "learning_rate": 7.8125e-05,
      "loss": 2.409,
      "step": 5000
    },
    {
      "epoch": 0.8,
      "learning_rate": 7.96875e-05,
      "loss": 2.4307,
      "step": 5100
    },
    {
      "epoch": 0.81,
      "learning_rate": 8.125000000000001e-05,
      "loss": 2.4222,
      "step": 5200
    },
    {
      "epoch": 0.83,
      "learning_rate": 8.28125e-05,
      "loss": 2.4247,
      "step": 5300
    },
    {
      "epoch": 0.84,
      "learning_rate": 8.4375e-05,
      "loss": 2.4073,
      "step": 5400
    },
    {
      "epoch": 0.86,
      "learning_rate": 8.593750000000001e-05,
      "loss": 2.4269,
      "step": 5500
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.75e-05,
      "loss": 2.4198,
      "step": 5600
    },
    {
      "epoch": 0.89,
      "learning_rate": 8.90625e-05,
      "loss": 2.436,
      "step": 5700
    },
    {
      "epoch": 0.91,
      "learning_rate": 9.062500000000001e-05,
      "loss": 2.4122,
      "step": 5800
    },
    {
      "epoch": 0.92,
      "learning_rate": 9.21875e-05,
      "loss": 2.4047,
      "step": 5900
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.375e-05,
      "loss": 2.4164,
      "step": 6000
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.53125e-05,
      "loss": 2.4175,
      "step": 6100
    },
    {
      "epoch": 0.97,
      "learning_rate": 9.687500000000001e-05,
      "loss": 2.3834,
      "step": 6200
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.84375e-05,
      "loss": 2.4239,
      "step": 6300
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001,
      "loss": 2.4192,
      "step": 6400
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5911958376190094,
      "eval_loss": 2.2528364658355713,
      "eval_runtime": 50783.1906,
      "eval_samples_per_second": 6.456,
      "eval_steps_per_second": 0.807,
      "step": 6400
    }
  ],
  "max_steps": 6400,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 2.707934115004416e+17,
  "trial_name": null,
  "trial_params": null
}