{
  "best_metric": 0.0,
  "best_model_checkpoint": "cola-pixel-handwritten-mean-vatrpp-256-128-4-3e-5-15000-420/checkpoint-100",
  "epoch": 68.71641791044776,
  "global_step": 1100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.24,
      "learning_rate": 1.485e-05,
      "loss": 0.651,
      "step": 100
    },
    {
      "epoch": 6.24,
      "eval_loss": 0.6247654557228088,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 8.2894,
      "eval_samples_per_second": 125.824,
      "eval_steps_per_second": 15.803,
      "step": 100
    },
    {
      "epoch": 12.48,
      "learning_rate": 2.985e-05,
      "loss": 0.6339,
      "step": 200
    },
    {
      "epoch": 12.48,
      "eval_loss": 0.6229375600814819,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.7031,
      "eval_samples_per_second": 135.4,
      "eval_steps_per_second": 17.006,
      "step": 200
    },
    {
      "epoch": 18.72,
      "learning_rate": 2.9799324324324325e-05,
      "loss": 0.6347,
      "step": 300
    },
    {
      "epoch": 18.72,
      "eval_loss": 0.6187897324562073,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.7482,
      "eval_samples_per_second": 134.612,
      "eval_steps_per_second": 16.907,
      "step": 300
    },
    {
      "epoch": 24.96,
      "learning_rate": 2.959662162162162e-05,
      "loss": 0.6348,
      "step": 400
    },
    {
      "epoch": 24.96,
      "eval_loss": 0.6177605390548706,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.7262,
      "eval_samples_per_second": 134.996,
      "eval_steps_per_second": 16.955,
      "step": 400
    },
    {
      "epoch": 31.24,
      "learning_rate": 2.9393918918918918e-05,
      "loss": 0.6383,
      "step": 500
    },
    {
      "epoch": 31.24,
      "eval_loss": 0.6179342269897461,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.957,
      "eval_samples_per_second": 131.08,
      "eval_steps_per_second": 16.464,
      "step": 500
    },
    {
      "epoch": 37.48,
      "learning_rate": 2.919121621621622e-05,
      "loss": 0.633,
      "step": 600
    },
    {
      "epoch": 37.48,
      "eval_loss": 0.6183168888092041,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.762,
      "eval_samples_per_second": 134.373,
      "eval_steps_per_second": 16.877,
      "step": 600
    },
    {
      "epoch": 43.72,
      "learning_rate": 2.8988513513513515e-05,
      "loss": 0.633,
      "step": 700
    },
    {
      "epoch": 43.72,
      "eval_loss": 0.6158902645111084,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.7727,
      "eval_samples_per_second": 134.188,
      "eval_steps_per_second": 16.854,
      "step": 700
    },
    {
      "epoch": 49.96,
      "learning_rate": 2.8785810810810812e-05,
      "loss": 0.6333,
      "step": 800
    },
    {
      "epoch": 49.96,
      "eval_loss": 0.6180645823478699,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.8257,
      "eval_samples_per_second": 133.279,
      "eval_steps_per_second": 16.74,
      "step": 800
    },
    {
      "epoch": 56.24,
      "learning_rate": 2.858310810810811e-05,
      "loss": 0.6369,
      "step": 900
    },
    {
      "epoch": 56.24,
      "eval_loss": 0.6213133335113525,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.8016,
      "eval_samples_per_second": 133.69,
      "eval_steps_per_second": 16.791,
      "step": 900
    },
    {
      "epoch": 62.48,
      "learning_rate": 2.8380405405405405e-05,
      "loss": 0.6359,
      "step": 1000
    },
    {
      "epoch": 62.48,
      "eval_loss": 0.6190767288208008,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.866,
      "eval_samples_per_second": 132.595,
      "eval_steps_per_second": 16.654,
      "step": 1000
    },
    {
      "epoch": 68.72,
      "learning_rate": 2.8177702702702706e-05,
      "loss": 0.6348,
      "step": 1100
    },
    {
      "epoch": 68.72,
      "eval_loss": 0.6171795129776001,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 7.7581,
      "eval_samples_per_second": 134.44,
      "eval_steps_per_second": 16.886,
      "step": 1100
    },
    {
      "epoch": 68.72,
      "step": 1100,
      "total_flos": 1.5137619491114975e+19,
      "train_loss": 0.6363277019153942,
      "train_runtime": 6298.8329,
      "train_samples_per_second": 1219.273,
      "train_steps_per_second": 2.381
    }
  ],
  "max_steps": 15000,
  "num_train_epochs": 938,
  "total_flos": 1.5137619491114975e+19,
  "trial_name": null,
  "trial_params": null
}