{
  "best_metric": 0.703125,
  "best_model_checkpoint": "/content/20epcoh1/checkpoint-300",
  "epoch": 4.0,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13,
      "learning_rate": 1.2e-05,
      "loss": 2.1242,
      "step": 10
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.5333333333333337e-05,
      "loss": 1.8392,
      "step": 20
    },
    {
      "epoch": 0.4,
      "learning_rate": 3.866666666666667e-05,
      "loss": 1.5371,
      "step": 30
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.3264,
      "step": 40
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.533333333333334e-05,
      "loss": 1.1148,
      "step": 50
    },
    {
      "epoch": 0.8,
      "learning_rate": 7.866666666666666e-05,
      "loss": 0.9979,
      "step": 60
    },
    {
      "epoch": 0.93,
      "learning_rate": 9.200000000000001e-05,
      "loss": 1.053,
      "step": 70
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6160714285714286,
      "eval_loss": 1.0581690073013306,
      "eval_runtime": 14.56,
      "eval_samples_per_second": 30.769,
      "eval_steps_per_second": 3.846,
      "step": 75
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00010533333333333332,
      "loss": 0.8613,
      "step": 80
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00011866666666666669,
      "loss": 0.9467,
      "step": 90
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.000132,
      "loss": 0.8097,
      "step": 100
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.00014533333333333333,
      "loss": 0.8538,
      "step": 110
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.00015866666666666668,
      "loss": 0.887,
      "step": 120
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.000172,
      "loss": 1.0396,
      "step": 130
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00018533333333333333,
      "loss": 0.8933,
      "step": 140
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00019866666666666668,
      "loss": 1.026,
      "step": 150
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6584821428571429,
      "eval_loss": 0.9405480623245239,
      "eval_runtime": 14.9426,
      "eval_samples_per_second": 29.981,
      "eval_steps_per_second": 3.748,
      "step": 150
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00019866666666666668,
      "loss": 0.78,
      "step": 160
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0001971851851851852,
      "loss": 0.6783,
      "step": 170
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.0001957037037037037,
      "loss": 0.7991,
      "step": 180
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00019422222222222223,
      "loss": 0.7667,
      "step": 190
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00019274074074074075,
      "loss": 0.7979,
      "step": 200
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00019125925925925926,
      "loss": 0.8502,
      "step": 210
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00018977777777777778,
      "loss": 0.7942,
      "step": 220
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6339285714285714,
      "eval_loss": 0.9822031855583191,
      "eval_runtime": 19.6852,
      "eval_samples_per_second": 22.758,
      "eval_steps_per_second": 2.845,
      "step": 225
    },
    {
      "epoch": 3.07,
      "learning_rate": 0.0001882962962962963,
      "loss": 0.5113,
      "step": 230
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0001868148148148148,
      "loss": 0.659,
      "step": 240
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.00018533333333333333,
      "loss": 0.5285,
      "step": 250
    },
    {
      "epoch": 3.47,
      "learning_rate": 0.00018385185185185185,
      "loss": 0.5316,
      "step": 260
    },
    {
      "epoch": 3.6,
      "learning_rate": 0.00018237037037037036,
      "loss": 0.5804,
      "step": 270
    },
    {
      "epoch": 3.73,
      "learning_rate": 0.0001808888888888889,
      "loss": 0.6496,
      "step": 280
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.00017940740740740742,
      "loss": 0.5075,
      "step": 290
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.00017792592592592594,
      "loss": 0.4856,
      "step": 300
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.703125,
      "eval_loss": 0.831343948841095,
      "eval_runtime": 16.0292,
      "eval_samples_per_second": 27.949,
      "eval_steps_per_second": 3.494,
      "step": 300
    }
  ],
  "max_steps": 1500,
  "num_train_epochs": 20,
  "total_flos": 1.962510888920408e+18,
  "trial_name": null,
  "trial_params": null
}