{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.2526315789473683,
  "eval_steps": 25,
  "global_step": 18,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.16842105263157894,
      "grad_norm": 0.1560886651277542,
      "learning_rate": 9.924038765061042e-05,
      "loss": 11.5478,
      "step": 1
    },
    {
      "epoch": 0.16842105263157894,
      "eval_loss": 11.938690185546875,
      "eval_runtime": 0.5648,
      "eval_samples_per_second": 70.82,
      "eval_steps_per_second": 8.852,
      "step": 1
    },
    {
      "epoch": 0.3368421052631579,
      "grad_norm": 0.18378160893917084,
      "learning_rate": 9.698463103929542e-05,
      "loss": 11.4842,
      "step": 2
    },
    {
      "epoch": 0.5052631578947369,
      "grad_norm": 0.17300869524478912,
      "learning_rate": 9.330127018922194e-05,
      "loss": 11.4912,
      "step": 3
    },
    {
      "epoch": 0.6736842105263158,
      "grad_norm": 0.20356659591197968,
      "learning_rate": 8.83022221559489e-05,
      "loss": 11.4184,
      "step": 4
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 0.2707521915435791,
      "learning_rate": 8.213938048432697e-05,
      "loss": 11.2246,
      "step": 5
    },
    {
      "epoch": 1.0842105263157895,
      "grad_norm": 0.3075051009654999,
      "learning_rate": 7.500000000000001e-05,
      "loss": 20.2474,
      "step": 6
    },
    {
      "epoch": 1.2526315789473683,
      "grad_norm": 0.2343152016401291,
      "learning_rate": 6.710100716628344e-05,
      "loss": 10.0065,
      "step": 7
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 0.16806015372276306,
      "learning_rate": 5.868240888334653e-05,
      "loss": 6.9828,
      "step": 8
    },
    {
      "epoch": 1.5894736842105264,
      "grad_norm": 0.2095569521188736,
      "learning_rate": 5e-05,
      "loss": 11.861,
      "step": 9
    },
    {
      "epoch": 1.7578947368421054,
      "grad_norm": 0.3017806112766266,
      "learning_rate": 4.131759111665349e-05,
      "loss": 15.9188,
      "step": 10
    },
    {
      "epoch": 1.9263157894736842,
      "grad_norm": 0.2827466130256653,
      "learning_rate": 3.289899283371657e-05,
      "loss": 15.2822,
      "step": 11
    },
    {
      "epoch": 2.168421052631579,
      "grad_norm": 0.20033185184001923,
      "learning_rate": 2.500000000000001e-05,
      "loss": 11.4648,
      "step": 12
    },
    {
      "epoch": 2.336842105263158,
      "grad_norm": 0.18562130630016327,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 11.4451,
      "step": 13
    },
    {
      "epoch": 2.5052631578947366,
      "grad_norm": 0.21771396696567535,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 11.4589,
      "step": 14
    },
    {
      "epoch": 2.6736842105263157,
      "grad_norm": 0.18469057977199554,
      "learning_rate": 6.698729810778065e-06,
      "loss": 11.494,
      "step": 15
    },
    {
      "epoch": 2.8421052631578947,
      "grad_norm": 0.2434016913175583,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 11.1981,
      "step": 16
    },
    {
      "epoch": 3.0842105263157893,
      "grad_norm": 0.3651926815509796,
      "learning_rate": 7.596123493895991e-07,
      "loss": 20.4587,
      "step": 17
    },
    {
      "epoch": 3.2526315789473683,
      "grad_norm": 0.20429116487503052,
      "learning_rate": 0.0,
      "loss": 10.1188,
      "step": 18
    }
  ],
  "logging_steps": 1,
  "max_steps": 18,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 150384622436352.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}