{
  "best_global_step": 250,
  "best_metric": 0.903,
  "best_model_checkpoint": "./output/checkpoint-250",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "grad_norm": 4.507571697235107,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 3.6814801025390627,
      "step": 25
    },
    {
      "epoch": 0.2,
      "grad_norm": 5.898707389831543,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 3.506214599609375,
      "step": 50
    },
    {
      "epoch": 0.3,
      "grad_norm": 8.463967323303223,
      "learning_rate": 7.4e-06,
      "loss": 3.1335317993164065,
      "step": 75
    },
    {
      "epoch": 0.4,
      "grad_norm": 12.804802894592285,
      "learning_rate": 9.9e-06,
      "loss": 2.86414794921875,
      "step": 100
    },
    {
      "epoch": 0.5,
      "grad_norm": 17.248327255249023,
      "learning_rate": 1.2400000000000002e-05,
      "loss": 2.2183343505859376,
      "step": 125
    },
    {
      "epoch": 0.6,
      "grad_norm": 26.214523315429688,
      "learning_rate": 1.4900000000000001e-05,
      "loss": 1.6969413757324219,
      "step": 150
    },
    {
      "epoch": 0.7,
      "grad_norm": 25.541751861572266,
      "learning_rate": 1.7400000000000003e-05,
      "loss": 1.355454559326172,
      "step": 175
    },
    {
      "epoch": 0.8,
      "grad_norm": 29.073373794555664,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 1.1928968811035157,
      "step": 200
    },
    {
      "epoch": 0.9,
      "grad_norm": 20.221284866333008,
      "learning_rate": 1.94e-05,
      "loss": 0.8974443054199219,
      "step": 225
    },
    {
      "epoch": 1.0,
      "grad_norm": 16.163564682006836,
      "learning_rate": 1.8775000000000002e-05,
      "loss": 0.8238192749023437,
      "step": 250
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.903,
      "eval_loss": 0.5729588866233826,
      "eval_runtime": 6.6811,
      "eval_samples_per_second": 299.352,
      "eval_steps_per_second": 2.395,
      "step": 250
    }
  ],
  "logging_steps": 25,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "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": 1052482019328000.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}