{
  "best_metric": 0.19775843620300293,
  "best_model_checkpoint": "ontonotes_roberta-large-v2/checkpoint-108138",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 108138,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.8596975803375244,
      "learning_rate": 1.960019974477057e-05,
      "loss": 0.3672,
      "step": 36046
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.23480436205863953,
      "eval_runtime": 162.404,
      "eval_samples_per_second": 164.497,
      "eval_steps_per_second": 20.566,
      "step": 36046
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.4112672805786133,
      "learning_rate": 1.9200332907950954e-05,
      "loss": 0.2279,
      "step": 72092
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.21355144679546356,
      "eval_runtime": 158.0799,
      "eval_samples_per_second": 168.997,
      "eval_steps_per_second": 21.129,
      "step": 72092
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.2005605697631836,
      "learning_rate": 1.880049936192643e-05,
      "loss": 0.2002,
      "step": 108138
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.19775843620300293,
      "eval_runtime": 159.9354,
      "eval_samples_per_second": 167.036,
      "eval_steps_per_second": 20.883,
      "step": 108138
    }
  ],
  "logging_steps": 500,
  "max_steps": 1802300,
  "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": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0393056782837677e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}