{
  "best_metric": 0.687774658203125,
  "best_model_checkpoint": "robertatest/checkpoint-6",
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5,
      "grad_norm": 5.72326135635376,
      "learning_rate": 1e-05,
      "loss": 0.7371,
      "step": 1
    },
    {
      "epoch": 1.0,
      "grad_norm": 5.217761993408203,
      "learning_rate": 2e-05,
      "loss": 0.6233,
      "step": 2
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5,
      "eval_auc": 0.5,
      "eval_f1": 0.0,
      "eval_loss": 0.7041667103767395,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.7626,
      "eval_samples_per_second": 5.245,
      "eval_steps_per_second": 1.311,
      "step": 2
    },
    {
      "epoch": 1.5,
      "grad_norm": 6.899262428283691,
      "learning_rate": 3e-05,
      "loss": 0.6912,
      "step": 3
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.985622406005859,
      "learning_rate": 4e-05,
      "loss": 0.6854,
      "step": 4
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5,
      "eval_auc": 0.75,
      "eval_f1": 0.0,
      "eval_loss": 0.6881411671638489,
      "eval_precision": 0.0,
      "eval_recall": 0.0,
      "eval_runtime": 0.6966,
      "eval_samples_per_second": 5.742,
      "eval_steps_per_second": 1.435,
      "step": 4
    },
    {
      "epoch": 2.5,
      "grad_norm": 3.8720149993896484,
      "learning_rate": 5e-05,
      "loss": 0.6425,
      "step": 5
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.4388933181762695,
      "learning_rate": 4.888888888888889e-05,
      "loss": 0.6463,
      "step": 6
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.5,
      "eval_auc": 1.0,
      "eval_f1": 0.5,
      "eval_loss": 0.687774658203125,
      "eval_precision": 0.5,
      "eval_recall": 0.5,
      "eval_runtime": 0.6946,
      "eval_samples_per_second": 5.759,
      "eval_steps_per_second": 1.44,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 25,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.01
      },
      "attributes": {
        "early_stopping_patience_counter": 1
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3157332664320.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}