{
  "best_metric": 0.3044949173927307,
  "best_model_checkpoint": "./esnli-label-predictor-bert-based/checkpoint-1000",
  "epoch": 2.952755905511811,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.49,
      "learning_rate": 4.1797900262467194e-05,
      "loss": 0.3644,
      "step": 250
    },
    {
      "epoch": 0.49,
      "eval_Accuracy": {
        "accuracy": 0.8712660028449503
      },
      "eval_loss": 0.33003470301628113,
      "eval_runtime": 5.1931,
      "eval_samples_per_second": 1895.21,
      "eval_steps_per_second": 3.851,
      "step": 250
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.3595800524934386e-05,
      "loss": 0.3495,
      "step": 500
    },
    {
      "epoch": 0.98,
      "eval_Accuracy": {
        "accuracy": 0.878988010566958
      },
      "eval_loss": 0.3118612766265869,
      "eval_runtime": 4.9109,
      "eval_samples_per_second": 2004.123,
      "eval_steps_per_second": 4.073,
      "step": 500
    },
    {
      "epoch": 1.48,
      "learning_rate": 2.5393700787401574e-05,
      "loss": 0.279,
      "step": 750
    },
    {
      "epoch": 1.48,
      "eval_Accuracy": {
        "accuracy": 0.8764478764478765
      },
      "eval_loss": 0.31501224637031555,
      "eval_runtime": 5.3058,
      "eval_samples_per_second": 1854.965,
      "eval_steps_per_second": 3.769,
      "step": 750
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.7191601049868766e-05,
      "loss": 0.2759,
      "step": 1000
    },
    {
      "epoch": 1.97,
      "eval_Accuracy": {
        "accuracy": 0.8818329607803292
      },
      "eval_loss": 0.3044949173927307,
      "eval_runtime": 5.291,
      "eval_samples_per_second": 1860.134,
      "eval_steps_per_second": 3.78,
      "step": 1000
    },
    {
      "epoch": 2.46,
      "learning_rate": 8.98950131233596e-06,
      "loss": 0.2318,
      "step": 1250
    },
    {
      "epoch": 2.46,
      "eval_Accuracy": {
        "accuracy": 0.8812233285917497
      },
      "eval_loss": 0.32354599237442017,
      "eval_runtime": 5.146,
      "eval_samples_per_second": 1912.55,
      "eval_steps_per_second": 3.887,
      "step": 1250
    },
    {
      "epoch": 2.95,
      "learning_rate": 7.874015748031496e-07,
      "loss": 0.2248,
      "step": 1500
    },
    {
      "epoch": 2.95,
      "eval_Accuracy": {
        "accuracy": 0.8807153017679333
      },
      "eval_loss": 0.3224857747554779,
      "eval_runtime": 4.9985,
      "eval_samples_per_second": 1968.987,
      "eval_steps_per_second": 4.001,
      "step": 1500
    }
  ],
  "max_steps": 1524,
  "num_train_epochs": 3,
  "total_flos": 3156563450188512.0,
  "trial_name": null,
  "trial_params": null
}