{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.30627871362940273,
  "eval_steps": 100,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.015313935681470138,
      "grad_norm": 3.8326407564846536,
      "learning_rate": 6.134969325153375e-07,
      "loss": 1.3339,
      "step": 5
    },
    {
      "epoch": 0.030627871362940276,
      "grad_norm": 3.5496788557416803,
      "learning_rate": 1.226993865030675e-06,
      "loss": 1.3517,
      "step": 10
    },
    {
      "epoch": 0.045941807044410414,
      "grad_norm": 2.292172802820395,
      "learning_rate": 1.8404907975460124e-06,
      "loss": 1.3142,
      "step": 15
    },
    {
      "epoch": 0.06125574272588055,
      "grad_norm": 1.7775340318261912,
      "learning_rate": 2.45398773006135e-06,
      "loss": 1.2477,
      "step": 20
    },
    {
      "epoch": 0.07656967840735068,
      "grad_norm": 1.4368794370978828,
      "learning_rate": 3.0674846625766875e-06,
      "loss": 1.2037,
      "step": 25
    },
    {
      "epoch": 0.09188361408882083,
      "grad_norm": 1.061354555879628,
      "learning_rate": 3.680981595092025e-06,
      "loss": 1.1505,
      "step": 30
    },
    {
      "epoch": 0.10719754977029096,
      "grad_norm": 0.8377616484610274,
      "learning_rate": 4.294478527607362e-06,
      "loss": 1.1179,
      "step": 35
    },
    {
      "epoch": 0.1225114854517611,
      "grad_norm": 0.7884987790196414,
      "learning_rate": 4.9079754601227e-06,
      "loss": 1.0735,
      "step": 40
    },
    {
      "epoch": 0.13782542113323124,
      "grad_norm": 0.7279957151761491,
      "learning_rate": 5.521472392638038e-06,
      "loss": 1.0556,
      "step": 45
    },
    {
      "epoch": 0.15313935681470137,
      "grad_norm": 0.6692858930956382,
      "learning_rate": 6.134969325153375e-06,
      "loss": 1.0294,
      "step": 50
    },
    {
      "epoch": 0.16845329249617153,
      "grad_norm": 0.6401840707040195,
      "learning_rate": 6.748466257668712e-06,
      "loss": 1.0175,
      "step": 55
    },
    {
      "epoch": 0.18376722817764166,
      "grad_norm": 0.6584204446837412,
      "learning_rate": 7.36196319018405e-06,
      "loss": 1.0283,
      "step": 60
    },
    {
      "epoch": 0.1990811638591118,
      "grad_norm": 0.6647811794468166,
      "learning_rate": 7.975460122699386e-06,
      "loss": 0.9799,
      "step": 65
    },
    {
      "epoch": 0.21439509954058192,
      "grad_norm": 0.6774675226534475,
      "learning_rate": 8.588957055214725e-06,
      "loss": 0.969,
      "step": 70
    },
    {
      "epoch": 0.22970903522205208,
      "grad_norm": 0.6918496726012217,
      "learning_rate": 9.202453987730062e-06,
      "loss": 0.9787,
      "step": 75
    },
    {
      "epoch": 0.2450229709035222,
      "grad_norm": 0.6740082248654927,
      "learning_rate": 9.8159509202454e-06,
      "loss": 0.9596,
      "step": 80
    },
    {
      "epoch": 0.26033690658499237,
      "grad_norm": 0.6791518891702232,
      "learning_rate": 1.0429447852760737e-05,
      "loss": 0.9813,
      "step": 85
    },
    {
      "epoch": 0.27565084226646247,
      "grad_norm": 0.7029695620068616,
      "learning_rate": 1.1042944785276076e-05,
      "loss": 0.9703,
      "step": 90
    },
    {
      "epoch": 0.29096477794793263,
      "grad_norm": 0.6355433423695775,
      "learning_rate": 1.1656441717791411e-05,
      "loss": 0.9375,
      "step": 95
    },
    {
      "epoch": 0.30627871362940273,
      "grad_norm": 0.6551855479751819,
      "learning_rate": 1.226993865030675e-05,
      "loss": 0.952,
      "step": 100
    },
    {
      "epoch": 0.30627871362940273,
      "eval_loss": 0.964697003364563,
      "eval_runtime": 3.4019,
      "eval_samples_per_second": 36.45,
      "eval_steps_per_second": 2.352,
      "step": 100
    }
  ],
  "logging_steps": 5,
  "max_steps": 1630,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 10603468947456.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}