{
  "best_metric": 0.6033268648340611,
  "best_model_checkpoint": "./nlu_finetuned_models/cola/bert-base-uncased_lr1e-05/checkpoint-3367",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 4810,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.4246382415294647,
      "eval_matthews_correlation": 0.5212265735601975,
      "eval_runtime": 0.4359,
      "eval_samples_per_second": 1963.789,
      "eval_steps_per_second": 123.884,
      "step": 481
    },
    {
      "epoch": 1.0395010395010396,
      "grad_norm": 22.556371688842773,
      "learning_rate": 9.533289095332891e-06,
      "loss": 0.524,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.4183749258518219,
      "eval_matthews_correlation": 0.5182707021157785,
      "eval_runtime": 0.4174,
      "eval_samples_per_second": 2050.804,
      "eval_steps_per_second": 129.373,
      "step": 962
    },
    {
      "epoch": 2.079002079002079,
      "grad_norm": 11.332476615905762,
      "learning_rate": 8.427339084273391e-06,
      "loss": 0.3607,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.4737670123577118,
      "eval_matthews_correlation": 0.5528480933747183,
      "eval_runtime": 0.4152,
      "eval_samples_per_second": 2061.677,
      "eval_steps_per_second": 130.059,
      "step": 1443
    },
    {
      "epoch": 3.1185031185031185,
      "grad_norm": 1.7414240837097168,
      "learning_rate": 7.3213890732138915e-06,
      "loss": 0.2474,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.604235053062439,
      "eval_matthews_correlation": 0.5775461143960999,
      "eval_runtime": 0.4144,
      "eval_samples_per_second": 2065.494,
      "eval_steps_per_second": 130.3,
      "step": 1924
    },
    {
      "epoch": 4.158004158004158,
      "grad_norm": 1.0630062818527222,
      "learning_rate": 6.2154390621543915e-06,
      "loss": 0.1789,
      "step": 2000
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.6851717233657837,
      "eval_matthews_correlation": 0.5868698844413494,
      "eval_runtime": 0.4073,
      "eval_samples_per_second": 2101.732,
      "eval_steps_per_second": 132.586,
      "step": 2405
    },
    {
      "epoch": 5.197505197505198,
      "grad_norm": 35.31257247924805,
      "learning_rate": 5.1094890510948916e-06,
      "loss": 0.152,
      "step": 2500
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.7323755025863647,
      "eval_matthews_correlation": 0.5776036075873803,
      "eval_runtime": 0.4074,
      "eval_samples_per_second": 2101.249,
      "eval_steps_per_second": 132.555,
      "step": 2886
    },
    {
      "epoch": 6.237006237006237,
      "grad_norm": 24.80868911743164,
      "learning_rate": 4.003539040035391e-06,
      "loss": 0.1163,
      "step": 3000
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.8122499585151672,
      "eval_matthews_correlation": 0.6033268648340611,
      "eval_runtime": 0.4037,
      "eval_samples_per_second": 2120.501,
      "eval_steps_per_second": 133.77,
      "step": 3367
    },
    {
      "epoch": 7.276507276507276,
      "grad_norm": 0.17492461204528809,
      "learning_rate": 2.897589028975891e-06,
      "loss": 0.085,
      "step": 3500
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.8224215507507324,
      "eval_matthews_correlation": 0.5901838943346132,
      "eval_runtime": 0.4068,
      "eval_samples_per_second": 2104.297,
      "eval_steps_per_second": 132.748,
      "step": 3848
    },
    {
      "epoch": 8.316008316008316,
      "grad_norm": 0.08201944828033447,
      "learning_rate": 1.7916390179163902e-06,
      "loss": 0.0786,
      "step": 4000
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.8545462489128113,
      "eval_matthews_correlation": 0.5823814386000223,
      "eval_runtime": 0.4115,
      "eval_samples_per_second": 2079.997,
      "eval_steps_per_second": 131.215,
      "step": 4329
    },
    {
      "epoch": 9.355509355509355,
      "grad_norm": 0.11403591185808182,
      "learning_rate": 6.856890068568902e-07,
      "loss": 0.0562,
      "step": 4500
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.8709535598754883,
      "eval_matthews_correlation": 0.5859609460754699,
      "eval_runtime": 0.4136,
      "eval_samples_per_second": 2069.416,
      "eval_steps_per_second": 130.547,
      "step": 4810
    },
    {
      "epoch": 10.0,
      "step": 4810,
      "total_flos": 816557451978060.0,
      "train_loss": 0.19049413486726566,
      "train_runtime": 286.7383,
      "train_samples_per_second": 268.363,
      "train_steps_per_second": 16.775
    }
  ],
  "logging_steps": 500,
  "max_steps": 4810,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 816557451978060.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}