{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 814,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12298232129131437,
      "grad_norm": 6.340283393859863,
      "learning_rate": 4.9933489107396326e-05,
      "loss": 2.0775,
      "step": 100
    },
    {
      "epoch": 0.24596464258262873,
      "grad_norm": 5.597610950469971,
      "learning_rate": 4.6913866856909926e-05,
      "loss": 2.2188,
      "step": 200
    },
    {
      "epoch": 0.3689469638739431,
      "grad_norm": 5.629631519317627,
      "learning_rate": 3.991940046522724e-05,
      "loss": 2.2347,
      "step": 300
    },
    {
      "epoch": 0.49192928516525747,
      "grad_norm": 5.603486061096191,
      "learning_rate": 3.0218780389368545e-05,
      "loss": 2.2132,
      "step": 400
    },
    {
      "epoch": 0.6149116064565718,
      "grad_norm": 5.57080602645874,
      "learning_rate": 1.9571552451450542e-05,
      "loss": 2.1841,
      "step": 500
    },
    {
      "epoch": 0.7378939277478862,
      "grad_norm": 5.660244464874268,
      "learning_rate": 9.908962828396607e-06,
      "loss": 2.15,
      "step": 600
    },
    {
      "epoch": 0.8608762490392006,
      "grad_norm": 5.181326389312744,
      "learning_rate": 2.98365919315127e-06,
      "loss": 2.1234,
      "step": 700
    },
    {
      "epoch": 0.9838585703305149,
      "grad_norm": 5.189568519592285,
      "learning_rate": 5.178692436005883e-08,
      "loss": 2.0872,
      "step": 800
    },
    {
      "epoch": 1.0,
      "step": 814,
      "total_flos": 5454715103844864.0,
      "train_loss": 2.1604688349168484,
      "train_runtime": 2203.1408,
      "train_samples_per_second": 11.81,
      "train_steps_per_second": 0.369
    }
  ],
  "logging_steps": 100,
  "max_steps": 814,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5454715103844864.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}