{
  "best_global_step": 34,
  "best_metric": 0.621012270450592,
  "best_model_checkpoint": "tiny_bert_km_20_v1_cola/checkpoint-34",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 204,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.6240780353546143,
      "learning_rate": 4.9e-05,
      "loss": 0.6189,
      "step": 34
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 0.621012270450592,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.349,
      "eval_samples_per_second": 2988.382,
      "eval_steps_per_second": 14.326,
      "step": 34
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9508184194564819,
      "learning_rate": 4.8e-05,
      "loss": 0.6054,
      "step": 68
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6912751793861389,
      "eval_loss": 0.6221826672554016,
      "eval_matthews_correlation": 0.0,
      "eval_runtime": 0.3272,
      "eval_samples_per_second": 3187.695,
      "eval_steps_per_second": 15.281,
      "step": 68
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.0832624435424805,
      "learning_rate": 4.7e-05,
      "loss": 0.5963,
      "step": 102
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6893576383590698,
      "eval_loss": 0.6258023977279663,
      "eval_matthews_correlation": -0.02929206145132745,
      "eval_runtime": 0.3266,
      "eval_samples_per_second": 3193.301,
      "eval_steps_per_second": 15.308,
      "step": 102
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.9972037076950073,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.5762,
      "step": 136
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6586769223213196,
      "eval_loss": 0.6420552134513855,
      "eval_matthews_correlation": 0.007101634138319549,
      "eval_runtime": 0.3708,
      "eval_samples_per_second": 2812.855,
      "eval_steps_per_second": 13.484,
      "step": 136
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.118736505508423,
      "learning_rate": 4.5e-05,
      "loss": 0.5409,
      "step": 170
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6807286739349365,
      "eval_loss": 0.6646057963371277,
      "eval_matthews_correlation": 0.057064889008809946,
      "eval_runtime": 0.3249,
      "eval_samples_per_second": 3210.474,
      "eval_steps_per_second": 15.391,
      "step": 170
    },
    {
      "epoch": 6.0,
      "grad_norm": 2.346623420715332,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.4934,
      "step": 204
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6452540755271912,
      "eval_loss": 0.7104889154434204,
      "eval_matthews_correlation": 0.038032706075893756,
      "eval_runtime": 0.3558,
      "eval_samples_per_second": 2931.596,
      "eval_steps_per_second": 14.054,
      "step": 204
    },
    {
      "epoch": 6.0,
      "step": 204,
      "total_flos": 1345426898614272.0,
      "train_loss": 0.5718443440456017,
      "train_runtime": 34.8494,
      "train_samples_per_second": 12268.486,
      "train_steps_per_second": 48.781
    }
  ],
  "logging_steps": 1,
  "max_steps": 1700,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1345426898614272.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}