{
  "best_metric": 0.7702265372168284,
  "best_model_checkpoint": "amazon-xlnet-large-2/checkpoint-20000",
  "epoch": 1.0,
  "global_step": 20000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 9.75e-06,
      "loss": 0.7155,
      "step": 500
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.5e-06,
      "loss": 0.6416,
      "step": 1000
    },
    {
      "epoch": 0.07,
      "learning_rate": 9.250000000000001e-06,
      "loss": 0.6013,
      "step": 1500
    },
    {
      "epoch": 0.1,
      "learning_rate": 9e-06,
      "loss": 0.6026,
      "step": 2000
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.750000000000001e-06,
      "loss": 0.5762,
      "step": 2500
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.5e-06,
      "loss": 0.6114,
      "step": 3000
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.25e-06,
      "loss": 0.6004,
      "step": 3500
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.5701,
      "step": 4000
    },
    {
      "epoch": 0.23,
      "learning_rate": 7.75e-06,
      "loss": 0.6027,
      "step": 4500
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.568,
      "step": 5000
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.25e-06,
      "loss": 0.5704,
      "step": 5500
    },
    {
      "epoch": 0.3,
      "learning_rate": 7e-06,
      "loss": 0.5688,
      "step": 6000
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.750000000000001e-06,
      "loss": 0.5657,
      "step": 6500
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.5517,
      "step": 7000
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.25e-06,
      "loss": 0.577,
      "step": 7500
    },
    {
      "epoch": 0.4,
      "learning_rate": 6e-06,
      "loss": 0.5462,
      "step": 8000
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.75e-06,
      "loss": 0.576,
      "step": 8500
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.5602,
      "step": 9000
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.2500000000000006e-06,
      "loss": 0.5697,
      "step": 9500
    },
    {
      "epoch": 0.5,
      "learning_rate": 5e-06,
      "loss": 0.5501,
      "step": 10000
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.75e-06,
      "loss": 0.5489,
      "step": 10500
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.5e-06,
      "loss": 0.5818,
      "step": 11000
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.25e-06,
      "loss": 0.5433,
      "step": 11500
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.5318,
      "step": 12000
    },
    {
      "epoch": 0.62,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.5762,
      "step": 12500
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.5e-06,
      "loss": 0.5335,
      "step": 13000
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.2500000000000002e-06,
      "loss": 0.5483,
      "step": 13500
    },
    {
      "epoch": 0.7,
      "learning_rate": 3e-06,
      "loss": 0.537,
      "step": 14000
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.7500000000000004e-06,
      "loss": 0.5403,
      "step": 14500
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.5e-06,
      "loss": 0.5545,
      "step": 15000
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.25e-06,
      "loss": 0.526,
      "step": 15500
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.5623,
      "step": 16000
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.75e-06,
      "loss": 0.5331,
      "step": 16500
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.5e-06,
      "loss": 0.5757,
      "step": 17000
    },
    {
      "epoch": 0.88,
      "learning_rate": 1.25e-06,
      "loss": 0.568,
      "step": 17500
    },
    {
      "epoch": 0.9,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.5492,
      "step": 18000
    },
    {
      "epoch": 0.93,
      "learning_rate": 7.5e-07,
      "loss": 0.5629,
      "step": 18500
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.5445,
      "step": 19000
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.5000000000000004e-07,
      "loss": 0.5629,
      "step": 19500
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.5505,
      "step": 20000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.77635,
      "eval_f1": 0.7702265372168284,
      "eval_loss": 0.5627002716064453,
      "eval_runtime": 539.3763,
      "eval_samples_per_second": 37.08,
      "eval_steps_per_second": 9.27,
      "step": 20000
    }
  ],
  "max_steps": 20000,
  "num_train_epochs": 1,
  "total_flos": 2.62860464073984e+16,
  "trial_name": null,
  "trial_params": null
}