{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03532008830022075,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00706401766004415,
      "grad_norm": 1.3894250392913818,
      "learning_rate": 1e-05,
      "loss": 2.641,
      "step": 1
    },
    {
      "epoch": 0.00706401766004415,
      "eval_loss": 2.8345160484313965,
      "eval_runtime": 159.1957,
      "eval_samples_per_second": 1.501,
      "eval_steps_per_second": 0.754,
      "step": 1
    },
    {
      "epoch": 0.0141280353200883,
      "grad_norm": 1.2751744985580444,
      "learning_rate": 2e-05,
      "loss": 2.5202,
      "step": 2
    },
    {
      "epoch": 0.0141280353200883,
      "eval_loss": 2.7751479148864746,
      "eval_runtime": 7.0882,
      "eval_samples_per_second": 33.718,
      "eval_steps_per_second": 16.929,
      "step": 2
    },
    {
      "epoch": 0.02119205298013245,
      "grad_norm": 1.4411779642105103,
      "learning_rate": 3e-05,
      "loss": 2.5638,
      "step": 3
    },
    {
      "epoch": 0.0282560706401766,
      "grad_norm": 1.4029831886291504,
      "learning_rate": 4e-05,
      "loss": 2.5586,
      "step": 4
    },
    {
      "epoch": 0.0282560706401766,
      "eval_loss": 2.693354368209839,
      "eval_runtime": 11.3248,
      "eval_samples_per_second": 21.104,
      "eval_steps_per_second": 10.596,
      "step": 4
    },
    {
      "epoch": 0.03532008830022075,
      "grad_norm": 1.6515071392059326,
      "learning_rate": 5e-05,
      "loss": 2.6961,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3877365202550784.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}