{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5617977528089888,
  "eval_steps": 500,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11235955056179775,
      "grad_norm": 1.256082565384994,
      "learning_rate": 0.00018333333333333334,
      "loss": 2.9875,
      "step": 10
    },
    {
      "epoch": 0.2247191011235955,
      "grad_norm": 0.6724869801987505,
      "learning_rate": 0.00014166666666666668,
      "loss": 1.8072,
      "step": 20
    },
    {
      "epoch": 0.33707865168539325,
      "grad_norm": 1.12869001911435,
      "learning_rate": 0.0001,
      "loss": 1.4428,
      "step": 30
    },
    {
      "epoch": 0.449438202247191,
      "grad_norm": 0.8159726100045944,
      "learning_rate": 5.833333333333334e-05,
      "loss": 1.2392,
      "step": 40
    },
    {
      "epoch": 0.5617977528089888,
      "grad_norm": 0.5492630453683175,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.1145,
      "step": 50
    },
    {
      "epoch": 0.5617977528089888,
      "step": 50,
      "total_flos": 33135697920.0,
      "train_loss": 1.7182426643371582,
      "train_runtime": 470.8396,
      "train_samples_per_second": 0.85,
      "train_steps_per_second": 0.106
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 33135697920.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}