{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.106918238993711,
  "eval_steps": 25,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10062893081761007,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.10062893081761007,
      "eval_loss": NaN,
      "eval_runtime": 0.8789,
      "eval_samples_per_second": 152.457,
      "eval_steps_per_second": 19.342,
      "step": 1
    },
    {
      "epoch": 0.20125786163522014,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.3018867924528302,
      "grad_norm": NaN,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.4025157232704403,
      "grad_norm": NaN,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.5031446540880503,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.6037735849056604,
      "grad_norm": NaN,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.7044025157232704,
      "grad_norm": NaN,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.8050314465408805,
      "grad_norm": NaN,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.9056603773584906,
      "grad_norm": NaN,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 1.0534591194968554,
      "grad_norm": NaN,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 1.1540880503144655,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 11
    },
    {
      "epoch": 1.2547169811320755,
      "grad_norm": NaN,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 1.3553459119496856,
      "grad_norm": NaN,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0,
      "step": 13
    },
    {
      "epoch": 1.4559748427672956,
      "grad_norm": NaN,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0,
      "step": 14
    },
    {
      "epoch": 1.5566037735849056,
      "grad_norm": NaN,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 1.6572327044025157,
      "grad_norm": NaN,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0,
      "step": 16
    },
    {
      "epoch": 1.757861635220126,
      "grad_norm": NaN,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0,
      "step": 17
    },
    {
      "epoch": 1.858490566037736,
      "grad_norm": NaN,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 2.006289308176101,
      "grad_norm": NaN,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0,
      "step": 19
    },
    {
      "epoch": 2.106918238993711,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 20
    }
  ],
  "logging_steps": 1,
  "max_steps": 20,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 25,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.362407301152768e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}