{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000996189574876099,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00019923791497521978,
      "grad_norm": 2.1565117835998535,
      "learning_rate": 1e-05,
      "loss": 16.6202,
      "step": 1
    },
    {
      "epoch": 0.00019923791497521978,
      "eval_loss": 1.1159639358520508,
      "eval_runtime": 416.2411,
      "eval_samples_per_second": 20.31,
      "eval_steps_per_second": 10.155,
      "step": 1
    },
    {
      "epoch": 0.00039847582995043956,
      "grad_norm": 2.2432003021240234,
      "learning_rate": 2e-05,
      "loss": 18.0401,
      "step": 2
    },
    {
      "epoch": 0.00039847582995043956,
      "eval_loss": 1.10923171043396,
      "eval_runtime": 330.4184,
      "eval_samples_per_second": 25.586,
      "eval_steps_per_second": 12.793,
      "step": 2
    },
    {
      "epoch": 0.0005977137449256594,
      "grad_norm": 2.570234775543213,
      "learning_rate": 3e-05,
      "loss": 19.1045,
      "step": 3
    },
    {
      "epoch": 0.0007969516599008791,
      "grad_norm": 2.083988904953003,
      "learning_rate": 4e-05,
      "loss": 16.9334,
      "step": 4
    },
    {
      "epoch": 0.0007969516599008791,
      "eval_loss": 1.1058850288391113,
      "eval_runtime": 682.2132,
      "eval_samples_per_second": 12.392,
      "eval_steps_per_second": 6.196,
      "step": 4
    },
    {
      "epoch": 0.000996189574876099,
      "grad_norm": 2.4700844287872314,
      "learning_rate": 5e-05,
      "loss": 19.0701,
      "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": 6569915433615360.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}