{
  "best_global_step": 102,
  "best_metric": 0.6168506741523743,
  "best_model_checkpoint": "bert_base_km_5_v1_cola/checkpoint-102",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 272,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.0184812545776367,
      "learning_rate": 4.9e-05,
      "loss": 0.6154,
      "step": 34
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6893576383590698,
      "eval_loss": 0.6183784604072571,
      "eval_matthews_correlation": -0.007887379670285008,
      "eval_runtime": 0.6744,
      "eval_samples_per_second": 1546.637,
      "eval_steps_per_second": 7.414,
      "step": 34
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.073906183242798,
      "learning_rate": 4.8e-05,
      "loss": 0.5959,
      "step": 68
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6740172505378723,
      "eval_loss": 0.6171430349349976,
      "eval_matthews_correlation": 0.005476740094736749,
      "eval_runtime": 0.7236,
      "eval_samples_per_second": 1441.409,
      "eval_steps_per_second": 6.91,
      "step": 68
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.9242302179336548,
      "learning_rate": 4.7e-05,
      "loss": 0.5583,
      "step": 102
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6874400973320007,
      "eval_loss": 0.6168506741523743,
      "eval_matthews_correlation": 0.04959298805408078,
      "eval_runtime": 0.6807,
      "eval_samples_per_second": 1532.323,
      "eval_steps_per_second": 7.346,
      "step": 102
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.0941638946533203,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.5145,
      "step": 136
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6634707450866699,
      "eval_loss": 0.6423744559288025,
      "eval_matthews_correlation": 0.09532212745017962,
      "eval_runtime": 0.6687,
      "eval_samples_per_second": 1559.856,
      "eval_steps_per_second": 7.478,
      "step": 136
    },
    {
      "epoch": 5.0,
      "grad_norm": 2.465773105621338,
      "learning_rate": 4.5e-05,
      "loss": 0.4591,
      "step": 170
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6490891575813293,
      "eval_loss": 0.6875084638595581,
      "eval_matthews_correlation": 0.09892672481640027,
      "eval_runtime": 0.6908,
      "eval_samples_per_second": 1509.867,
      "eval_steps_per_second": 7.238,
      "step": 170
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.0577287673950195,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.412,
      "step": 204
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6308724880218506,
      "eval_loss": 0.7450611591339111,
      "eval_matthews_correlation": 0.06511003868382283,
      "eval_runtime": 0.6768,
      "eval_samples_per_second": 1541.14,
      "eval_steps_per_second": 7.388,
      "step": 204
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.787646532058716,
      "learning_rate": 4.3e-05,
      "loss": 0.3633,
      "step": 238
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6203259825706482,
      "eval_loss": 0.7966165542602539,
      "eval_matthews_correlation": 0.10894429086010696,
      "eval_runtime": 0.6801,
      "eval_samples_per_second": 1533.561,
      "eval_steps_per_second": 7.352,
      "step": 238
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.5457634925842285,
      "learning_rate": 4.2e-05,
      "loss": 0.3189,
      "step": 272
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6462128758430481,
      "eval_loss": 0.8535791635513306,
      "eval_matthews_correlation": 0.10018630520281055,
      "eval_runtime": 0.7183,
      "eval_samples_per_second": 1452.028,
      "eval_steps_per_second": 6.961,
      "step": 272
    },
    {
      "epoch": 8.0,
      "step": 272,
      "total_flos": 8999450537533440.0,
      "train_loss": 0.47968793616575356,
      "train_runtime": 135.9284,
      "train_samples_per_second": 3145.406,
      "train_steps_per_second": 12.507
    }
  ],
  "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": 8999450537533440.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}