{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.076923076923077,
  "eval_steps": 50,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 2.819514036178589,
      "learning_rate": 1e-05,
      "loss": 2.1194,
      "step": 1
    },
    {
      "epoch": 0.3076923076923077,
      "eval_loss": 3.018016815185547,
      "eval_runtime": 0.4302,
      "eval_samples_per_second": 13.946,
      "eval_steps_per_second": 4.649,
      "step": 1
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 2.598237991333008,
      "learning_rate": 2e-05,
      "loss": 2.2508,
      "step": 2
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 3.3801863193511963,
      "learning_rate": 3e-05,
      "loss": 2.3393,
      "step": 3
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 8.21949291229248,
      "learning_rate": 4e-05,
      "loss": 4.3959,
      "step": 4
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 2.318739891052246,
      "learning_rate": 5e-05,
      "loss": 1.9481,
      "step": 5
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 2.0345592498779297,
      "learning_rate": 6e-05,
      "loss": 2.0598,
      "step": 6
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 4.51873779296875,
      "learning_rate": 7e-05,
      "loss": 3.0184,
      "step": 7
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 1.5071061849594116,
      "learning_rate": 8e-05,
      "loss": 1.6382,
      "step": 8
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 1.303425669670105,
      "learning_rate": 9e-05,
      "loss": 1.4197,
      "step": 9
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 3.249138593673706,
      "learning_rate": 0.0001,
      "loss": 2.1184,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 50,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.35523765321728e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}