{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3999563604625791,
  "eval_steps": 500,
  "global_step": 7332,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.027274710888064588,
      "grad_norm": 8.132363319396973,
      "learning_rate": 1.976e-05,
      "loss": 3.5991,
      "step": 500
    },
    {
      "epoch": 0.054549421776129176,
      "grad_norm": 7.099025249481201,
      "learning_rate": 1.9818702290076336e-05,
      "loss": 2.8754,
      "step": 1000
    },
    {
      "epoch": 0.08182413266419376,
      "grad_norm": 7.820577621459961,
      "learning_rate": 1.963520258367587e-05,
      "loss": 2.6895,
      "step": 1500
    },
    {
      "epoch": 0.10909884355225835,
      "grad_norm": 5.448477268218994,
      "learning_rate": 1.94517028772754e-05,
      "loss": 2.6494,
      "step": 2000
    },
    {
      "epoch": 0.13637355444032292,
      "grad_norm": 6.391147613525391,
      "learning_rate": 1.926820317087493e-05,
      "loss": 2.5544,
      "step": 2500
    },
    {
      "epoch": 0.16364826532838753,
      "grad_norm": 5.117228031158447,
      "learning_rate": 1.908470346447446e-05,
      "loss": 2.5431,
      "step": 3000
    },
    {
      "epoch": 0.1909229762164521,
      "grad_norm": 4.08992338180542,
      "learning_rate": 1.890120375807399e-05,
      "loss": 2.5359,
      "step": 3500
    },
    {
      "epoch": 0.2181976871045167,
      "grad_norm": 3.984097957611084,
      "learning_rate": 1.871770405167352e-05,
      "loss": 2.4834,
      "step": 4000
    },
    {
      "epoch": 0.24547239799258128,
      "grad_norm": 3.8590118885040283,
      "learning_rate": 1.853420434527305e-05,
      "loss": 2.4899,
      "step": 4500
    },
    {
      "epoch": 0.27274710888064585,
      "grad_norm": 4.541988372802734,
      "learning_rate": 1.835070463887258e-05,
      "loss": 2.4608,
      "step": 5000
    },
    {
      "epoch": 0.30002181976871045,
      "grad_norm": 4.910805702209473,
      "learning_rate": 1.816720493247211e-05,
      "loss": 2.402,
      "step": 5500
    },
    {
      "epoch": 0.32729653065677505,
      "grad_norm": 4.220065116882324,
      "learning_rate": 1.798370522607164e-05,
      "loss": 2.4483,
      "step": 6000
    },
    {
      "epoch": 0.3545712415448396,
      "grad_norm": 3.9413557052612305,
      "learning_rate": 1.780020551967117e-05,
      "loss": 2.4271,
      "step": 6500
    },
    {
      "epoch": 0.3818459524329042,
      "grad_norm": 2.890425443649292,
      "learning_rate": 1.76167058132707e-05,
      "loss": 2.3884,
      "step": 7000
    }
  ],
  "logging_steps": 500,
  "max_steps": 54996,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1833,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1915793178624000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}