{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3333333333333333,
  "eval_steps": 500,
  "global_step": 135,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.24764642119407654,
      "learning_rate": 1.9984268150178167e-06,
      "loss": 0.4454,
      "step": 20
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.16292472183704376,
      "learning_rate": 1.976679926364567e-06,
      "loss": 0.4486,
      "step": 40
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.23981738090515137,
      "learning_rate": 1.9298944480495172e-06,
      "loss": 0.4176,
      "step": 60
    },
    {
      "epoch": 0.19753086419753085,
      "grad_norm": 0.25884947180747986,
      "learning_rate": 1.8592697928608701e-06,
      "loss": 0.4354,
      "step": 80
    },
    {
      "epoch": 0.24691358024691357,
      "grad_norm": 0.24895012378692627,
      "learning_rate": 1.7666165250516003e-06,
      "loss": 0.4689,
      "step": 100
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.2755189836025238,
      "learning_rate": 1.6543099439299843e-06,
      "loss": 0.4721,
      "step": 120
    }
  ],
  "logging_steps": 20,
  "max_steps": 405,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 135,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.9304910947680256e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}