{
  "best_metric": 0.23052819073200226,
  "best_model_checkpoint": "ontonotes_roberta-large/checkpoint-216276",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 216276,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 2.651404619216919,
      "learning_rate": 1.960019974477057e-05,
      "loss": 0.4522,
      "step": 36046
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.28564417362213135,
      "eval_runtime": 161.0463,
      "eval_samples_per_second": 165.884,
      "eval_steps_per_second": 20.739,
      "step": 36046
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.05408318713307381,
      "learning_rate": 1.920034400488265e-05,
      "loss": 0.2819,
      "step": 72092
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.25353872776031494,
      "eval_runtime": 159.5889,
      "eval_samples_per_second": 167.399,
      "eval_steps_per_second": 20.929,
      "step": 72092
    },
    {
      "epoch": 3.0,
      "grad_norm": 6.422146320343018,
      "learning_rate": 1.8800466071131334e-05,
      "loss": 0.2472,
      "step": 108138
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.25045502185821533,
      "eval_runtime": 160.8762,
      "eval_samples_per_second": 166.059,
      "eval_steps_per_second": 20.761,
      "step": 108138
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5866804122924805,
      "learning_rate": 1.8400621428175113e-05,
      "loss": 0.2243,
      "step": 144184
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.23909471929073334,
      "eval_runtime": 158.8568,
      "eval_samples_per_second": 168.17,
      "eval_steps_per_second": 21.025,
      "step": 144184
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.9897892475128174,
      "learning_rate": 1.800076568828719e-05,
      "loss": 0.2081,
      "step": 180230
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.2330855131149292,
      "eval_runtime": 158.6881,
      "eval_samples_per_second": 168.349,
      "eval_steps_per_second": 21.048,
      "step": 180230
    },
    {
      "epoch": 6.0,
      "grad_norm": 4.185283184051514,
      "learning_rate": 1.7600921045330967e-05,
      "loss": 0.1952,
      "step": 216276
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.23052819073200226,
      "eval_runtime": 160.5141,
      "eval_samples_per_second": 166.434,
      "eval_steps_per_second": 20.808,
      "step": 216276
    }
  ],
  "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": 2.0947896085132877e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}