{
  "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": 7.1569,
      "step": 100
    },
    {
      "epoch": 0.03,
      "learning_rate": 3.125e-06,
      "loss": 6.4544,
      "step": 200
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.6875000000000004e-06,
      "loss": 6.0991,
      "step": 300
    },
    {
      "epoch": 0.06,
      "learning_rate": 6.25e-06,
      "loss": 5.9141,
      "step": 400
    },
    {
      "epoch": 0.08,
      "learning_rate": 7.8125e-06,
      "loss": 5.7949,
      "step": 500
    },
    {
      "epoch": 0.09,
      "learning_rate": 9.375000000000001e-06,
      "loss": 5.6929,
      "step": 600
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.09375e-05,
      "loss": 5.6492,
      "step": 700
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.25e-05,
      "loss": 5.5034,
      "step": 800
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.4062500000000001e-05,
      "loss": 5.3694,
      "step": 900
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.5625e-05,
      "loss": 5.2019,
      "step": 1000
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.71875e-05,
      "loss": 5.0093,
      "step": 1100
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.8750000000000002e-05,
      "loss": 4.7568,
      "step": 1200
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.0312500000000002e-05,
      "loss": 4.5082,
      "step": 1300
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.1875e-05,
      "loss": 4.2716,
      "step": 1400
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.34375e-05,
      "loss": 4.0387,
      "step": 1500
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.5e-05,
      "loss": 3.7807,
      "step": 1600
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.6562500000000002e-05,
      "loss": 3.5811,
      "step": 1700
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.8125000000000003e-05,
      "loss": 3.4261,
      "step": 1800
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.96875e-05,
      "loss": 3.2447,
      "step": 1900
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.125e-05,
      "loss": 3.1248,
      "step": 2000
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.2812500000000005e-05,
      "loss": 3.0083,
      "step": 2100
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.4375e-05,
      "loss": 2.9129,
      "step": 2200
    },
    {
      "epoch": 0.36,
      "learning_rate": 3.59375e-05,
      "loss": 2.8483,
      "step": 2300
    },
    {
      "epoch": 0.38,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 2.7705,
      "step": 2400
    },
    {
      "epoch": 0.39,
      "learning_rate": 3.90625e-05,
      "loss": 2.7036,
      "step": 2500
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 2.6582,
      "step": 2600
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.21875e-05,
      "loss": 2.6227,
      "step": 2700
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.375e-05,
      "loss": 2.5692,
      "step": 2800
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.5312500000000004e-05,
      "loss": 2.5436,
      "step": 2900
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.6875e-05,
      "loss": 2.5384,
      "step": 3000
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.8437500000000005e-05,
      "loss": 2.5215,
      "step": 3100
    },
    {
      "epoch": 0.5,
      "learning_rate": 5e-05,
      "loss": 2.4988,
      "step": 3200
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.15625e-05,
      "loss": 2.4609,
      "step": 3300
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.3125000000000004e-05,
      "loss": 2.4631,
      "step": 3400
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.46875e-05,
      "loss": 2.4115,
      "step": 3500
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.6250000000000005e-05,
      "loss": 2.4199,
      "step": 3600
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.78125e-05,
      "loss": 2.388,
      "step": 3700
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.9375e-05,
      "loss": 2.396,
      "step": 3800
    },
    {
      "epoch": 0.61,
      "learning_rate": 6.0937500000000004e-05,
      "loss": 2.3892,
      "step": 3900
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.25e-05,
      "loss": 2.3833,
      "step": 4000
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.40625e-05,
      "loss": 2.3809,
      "step": 4100
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.562500000000001e-05,
      "loss": 2.3514,
      "step": 4200
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.71875e-05,
      "loss": 2.3439,
      "step": 4300
    },
    {
      "epoch": 0.69,
      "learning_rate": 6.875e-05,
      "loss": 2.3401,
      "step": 4400
    },
    {
      "epoch": 0.7,
      "learning_rate": 7.031250000000001e-05,
      "loss": 2.3278,
      "step": 4500
    },
    {
      "epoch": 0.72,
      "learning_rate": 7.1875e-05,
      "loss": 2.2968,
      "step": 4600
    },
    {
      "epoch": 0.73,
      "learning_rate": 7.34375e-05,
      "loss": 2.3086,
      "step": 4700
    },
    {
      "epoch": 0.75,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.2847,
      "step": 4800
    },
    {
      "epoch": 0.77,
      "learning_rate": 7.65625e-05,
      "loss": 2.3077,
      "step": 4900
    },
    {
      "epoch": 0.78,
      "learning_rate": 7.8125e-05,
      "loss": 2.2695,
      "step": 5000
    },
    {
      "epoch": 0.8,
      "learning_rate": 7.96875e-05,
      "loss": 2.2833,
      "step": 5100
    },
    {
      "epoch": 0.81,
      "learning_rate": 8.125000000000001e-05,
      "loss": 2.2645,
      "step": 5200
    },
    {
      "epoch": 0.83,
      "learning_rate": 8.28125e-05,
      "loss": 2.2623,
      "step": 5300
    },
    {
      "epoch": 0.84,
      "learning_rate": 8.4375e-05,
      "loss": 2.2452,
      "step": 5400
    },
    {
      "epoch": 0.86,
      "learning_rate": 8.593750000000001e-05,
      "loss": 2.2568,
      "step": 5500
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.75e-05,
      "loss": 2.2473,
      "step": 5600
    },
    {
      "epoch": 0.89,
      "learning_rate": 8.90625e-05,
      "loss": 2.257,
      "step": 5700
    },
    {
      "epoch": 0.91,
      "learning_rate": 9.062500000000001e-05,
      "loss": 2.2266,
      "step": 5800
    },
    {
      "epoch": 0.92,
      "learning_rate": 9.21875e-05,
      "loss": 2.2209,
      "step": 5900
    },
    {
      "epoch": 0.94,
      "learning_rate": 9.375e-05,
      "loss": 2.2254,
      "step": 6000
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.53125e-05,
      "loss": 2.2169,
      "step": 6100
    },
    {
      "epoch": 0.97,
      "learning_rate": 9.687500000000001e-05,
      "loss": 2.1862,
      "step": 6200
    },
    {
      "epoch": 0.98,
      "learning_rate": 9.84375e-05,
      "loss": 2.2179,
      "step": 6300
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0001,
      "loss": 2.2154,
      "step": 6400
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.623776836543713,
      "eval_loss": 2.0203473567962646,
      "eval_runtime": 51421.4651,
      "eval_samples_per_second": 6.376,
      "eval_steps_per_second": 0.797,
      "step": 6400
    },
    {
      "epoch": 1.0,
      "step": 6400,
      "total_flos": 2.707934115004416e+17,
      "train_loss": 3.1972352838516236,
      "train_runtime": 98443.4988,
      "train_samples_per_second": 4.161,
      "train_steps_per_second": 0.065
    }
  ],
  "max_steps": 6400,
  "num_train_epochs": 9223372036854775807,
  "total_flos": 2.707934115004416e+17,
  "trial_name": null,
  "trial_params": null
}