{
  "best_metric": 0.20570282638072968,
  "best_model_checkpoint": "DistilBERT1/checkpoint-205",
  "epoch": 10.0,
  "global_step": 2050,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.921028466483012,
      "eval_loss": 0.20570282638072968,
      "eval_runtime": 6.0089,
      "eval_samples_per_second": 181.232,
      "eval_steps_per_second": 11.483,
      "step": 205
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9302112029384757,
      "eval_loss": 0.2391415685415268,
      "eval_runtime": 6.3171,
      "eval_samples_per_second": 172.388,
      "eval_steps_per_second": 10.923,
      "step": 410
    },
    {
      "epoch": 2.44,
      "learning_rate": 1.5121951219512196e-05,
      "loss": 0.2164,
      "step": 500
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9320477502295684,
      "eval_loss": 0.2756326496601105,
      "eval_runtime": 6.7274,
      "eval_samples_per_second": 161.875,
      "eval_steps_per_second": 10.257,
      "step": 615
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9274563820018366,
      "eval_loss": 0.322733998298645,
      "eval_runtime": 6.7541,
      "eval_samples_per_second": 161.235,
      "eval_steps_per_second": 10.216,
      "step": 820
    },
    {
      "epoch": 4.88,
      "learning_rate": 1.024390243902439e-05,
      "loss": 0.0376,
      "step": 1000
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9329660238751147,
      "eval_loss": 0.3475565016269684,
      "eval_runtime": 6.7958,
      "eval_samples_per_second": 160.245,
      "eval_steps_per_second": 10.153,
      "step": 1025
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9320477502295684,
      "eval_loss": 0.38214486837387085,
      "eval_runtime": 6.7413,
      "eval_samples_per_second": 161.542,
      "eval_steps_per_second": 10.235,
      "step": 1230
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9338842975206612,
      "eval_loss": 0.39508363604545593,
      "eval_runtime": 6.7438,
      "eval_samples_per_second": 161.481,
      "eval_steps_per_second": 10.232,
      "step": 1435
    },
    {
      "epoch": 7.32,
      "learning_rate": 5.365853658536586e-06,
      "loss": 0.0087,
      "step": 1500
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9357208448117539,
      "eval_loss": 0.412009596824646,
      "eval_runtime": 6.7147,
      "eval_samples_per_second": 162.181,
      "eval_steps_per_second": 10.276,
      "step": 1640
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9338842975206612,
      "eval_loss": 0.407277911901474,
      "eval_runtime": 5.9717,
      "eval_samples_per_second": 182.361,
      "eval_steps_per_second": 11.555,
      "step": 1845
    },
    {
      "epoch": 9.76,
      "learning_rate": 4.878048780487805e-07,
      "loss": 0.0017,
      "step": 2000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.9338842975206612,
      "eval_loss": 0.41211310029029846,
      "eval_runtime": 5.9224,
      "eval_samples_per_second": 183.878,
      "eval_steps_per_second": 11.651,
      "step": 2050
    }
  ],
  "max_steps": 2050,
  "num_train_epochs": 10,
  "total_flos": 1609911482519136.0,
  "trial_name": null,
  "trial_params": null
}