{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 20.0,
  "eval_steps": 500,
  "global_step": 1240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 5.648942470550537,
      "learning_rate": 2.8814516129032256e-05,
      "loss": 0.6182,
      "step": 50
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 5.39515495300293,
      "learning_rate": 2.760483870967742e-05,
      "loss": 0.2539,
      "step": 100
    },
    {
      "epoch": 2.4193548387096775,
      "grad_norm": 4.596336364746094,
      "learning_rate": 2.6395161290322583e-05,
      "loss": 0.1844,
      "step": 150
    },
    {
      "epoch": 3.225806451612903,
      "grad_norm": 4.098703384399414,
      "learning_rate": 2.5185483870967742e-05,
      "loss": 0.1339,
      "step": 200
    },
    {
      "epoch": 4.032258064516129,
      "grad_norm": 6.071151256561279,
      "learning_rate": 2.3975806451612904e-05,
      "loss": 0.1029,
      "step": 250
    },
    {
      "epoch": 4.838709677419355,
      "grad_norm": 1.638786792755127,
      "learning_rate": 2.2766129032258065e-05,
      "loss": 0.0887,
      "step": 300
    },
    {
      "epoch": 5.645161290322581,
      "grad_norm": 13.432732582092285,
      "learning_rate": 2.1556451612903224e-05,
      "loss": 0.0582,
      "step": 350
    },
    {
      "epoch": 6.451612903225806,
      "grad_norm": 7.428147315979004,
      "learning_rate": 2.034677419354839e-05,
      "loss": 0.0472,
      "step": 400
    },
    {
      "epoch": 7.258064516129032,
      "grad_norm": 4.40520715713501,
      "learning_rate": 1.913709677419355e-05,
      "loss": 0.0383,
      "step": 450
    },
    {
      "epoch": 8.064516129032258,
      "grad_norm": 2.924527645111084,
      "learning_rate": 1.792741935483871e-05,
      "loss": 0.0334,
      "step": 500
    },
    {
      "epoch": 8.870967741935484,
      "grad_norm": 0.11616887152194977,
      "learning_rate": 1.671774193548387e-05,
      "loss": 0.0292,
      "step": 550
    },
    {
      "epoch": 9.67741935483871,
      "grad_norm": 0.6070950627326965,
      "learning_rate": 1.5508064516129033e-05,
      "loss": 0.0205,
      "step": 600
    },
    {
      "epoch": 10.483870967741936,
      "grad_norm": 0.7682154178619385,
      "learning_rate": 1.4298387096774195e-05,
      "loss": 0.0176,
      "step": 650
    },
    {
      "epoch": 11.290322580645162,
      "grad_norm": 6.306002140045166,
      "learning_rate": 1.3088709677419355e-05,
      "loss": 0.0137,
      "step": 700
    },
    {
      "epoch": 12.096774193548388,
      "grad_norm": 0.5101358890533447,
      "learning_rate": 1.1879032258064517e-05,
      "loss": 0.0104,
      "step": 750
    },
    {
      "epoch": 12.903225806451612,
      "grad_norm": 0.11972428858280182,
      "learning_rate": 1.0669354838709679e-05,
      "loss": 0.0072,
      "step": 800
    },
    {
      "epoch": 13.709677419354838,
      "grad_norm": 8.585674285888672,
      "learning_rate": 9.459677419354839e-06,
      "loss": 0.0064,
      "step": 850
    },
    {
      "epoch": 14.516129032258064,
      "grad_norm": 4.257481575012207,
      "learning_rate": 8.25e-06,
      "loss": 0.0067,
      "step": 900
    },
    {
      "epoch": 15.32258064516129,
      "grad_norm": 0.24766378104686737,
      "learning_rate": 7.040322580645162e-06,
      "loss": 0.0074,
      "step": 950
    },
    {
      "epoch": 16.129032258064516,
      "grad_norm": 0.2106390744447708,
      "learning_rate": 5.8306451612903235e-06,
      "loss": 0.008,
      "step": 1000
    },
    {
      "epoch": 16.93548387096774,
      "grad_norm": 0.015542744658887386,
      "learning_rate": 4.620967741935484e-06,
      "loss": 0.0026,
      "step": 1050
    },
    {
      "epoch": 17.741935483870968,
      "grad_norm": 0.039411235600709915,
      "learning_rate": 3.4112903225806454e-06,
      "loss": 0.004,
      "step": 1100
    },
    {
      "epoch": 18.548387096774192,
      "grad_norm": 11.331886291503906,
      "learning_rate": 2.2016129032258064e-06,
      "loss": 0.0027,
      "step": 1150
    },
    {
      "epoch": 19.35483870967742,
      "grad_norm": 0.09029797464609146,
      "learning_rate": 9.919354838709678e-07,
      "loss": 0.0019,
      "step": 1200
    }
  ],
  "logging_steps": 50,
  "max_steps": 1240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 20,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1455109469510400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}