{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 14754,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06777822963264199,
      "grad_norm": 31.397275924682617,
      "learning_rate": 2.8983326555510372e-05,
      "loss": 2.7299,
      "step": 500
    },
    {
      "epoch": 0.13555645926528398,
      "grad_norm": 25.8492431640625,
      "learning_rate": 2.796665311102074e-05,
      "loss": 1.752,
      "step": 1000
    },
    {
      "epoch": 0.203334688897926,
      "grad_norm": 29.627431869506836,
      "learning_rate": 2.694997966653111e-05,
      "loss": 1.5588,
      "step": 1500
    },
    {
      "epoch": 0.27111291853056796,
      "grad_norm": 21.147193908691406,
      "learning_rate": 2.593330622204148e-05,
      "loss": 1.5014,
      "step": 2000
    },
    {
      "epoch": 0.33889114816321,
      "grad_norm": 17.81966781616211,
      "learning_rate": 2.491663277755185e-05,
      "loss": 1.4768,
      "step": 2500
    },
    {
      "epoch": 0.406669377795852,
      "grad_norm": 20.26822853088379,
      "learning_rate": 2.389995933306222e-05,
      "loss": 1.4064,
      "step": 3000
    },
    {
      "epoch": 0.47444760742849396,
      "grad_norm": 16.216028213500977,
      "learning_rate": 2.288328588857259e-05,
      "loss": 1.3502,
      "step": 3500
    },
    {
      "epoch": 0.5422258370611359,
      "grad_norm": 17.930505752563477,
      "learning_rate": 2.1866612444082963e-05,
      "loss": 1.3101,
      "step": 4000
    },
    {
      "epoch": 0.6100040666937779,
      "grad_norm": 26.499574661254883,
      "learning_rate": 2.084993899959333e-05,
      "loss": 1.2922,
      "step": 4500
    },
    {
      "epoch": 0.67778229632642,
      "grad_norm": 26.83368492126465,
      "learning_rate": 1.9833265555103702e-05,
      "loss": 1.3053,
      "step": 5000
    },
    {
      "epoch": 0.745560525959062,
      "grad_norm": 22.85872459411621,
      "learning_rate": 1.8816592110614073e-05,
      "loss": 1.2555,
      "step": 5500
    },
    {
      "epoch": 0.813338755591704,
      "grad_norm": 23.48080825805664,
      "learning_rate": 1.779991866612444e-05,
      "loss": 1.2068,
      "step": 6000
    },
    {
      "epoch": 0.8811169852243459,
      "grad_norm": 20.919252395629883,
      "learning_rate": 1.6783245221634812e-05,
      "loss": 1.1991,
      "step": 6500
    },
    {
      "epoch": 0.9488952148569879,
      "grad_norm": 23.9005126953125,
      "learning_rate": 1.576657177714518e-05,
      "loss": 1.2156,
      "step": 7000
    },
    {
      "epoch": 1.01667344448963,
      "grad_norm": 22.660743713378906,
      "learning_rate": 1.4749898332655551e-05,
      "loss": 1.0827,
      "step": 7500
    },
    {
      "epoch": 1.0844516741222718,
      "grad_norm": 25.28419303894043,
      "learning_rate": 1.373322488816592e-05,
      "loss": 0.8481,
      "step": 8000
    },
    {
      "epoch": 1.152229903754914,
      "grad_norm": 14.510698318481445,
      "learning_rate": 1.271655144367629e-05,
      "loss": 0.872,
      "step": 8500
    },
    {
      "epoch": 1.2200081333875559,
      "grad_norm": 29.12289810180664,
      "learning_rate": 1.1699877999186661e-05,
      "loss": 0.8375,
      "step": 9000
    },
    {
      "epoch": 1.287786363020198,
      "grad_norm": 19.038454055786133,
      "learning_rate": 1.0683204554697033e-05,
      "loss": 0.8464,
      "step": 9500
    },
    {
      "epoch": 1.35556459265284,
      "grad_norm": 21.09101676940918,
      "learning_rate": 9.666531110207402e-06,
      "loss": 0.8746,
      "step": 10000
    },
    {
      "epoch": 1.4233428222854818,
      "grad_norm": 20.79250144958496,
      "learning_rate": 8.649857665717772e-06,
      "loss": 0.8776,
      "step": 10500
    },
    {
      "epoch": 1.491121051918124,
      "grad_norm": 21.217571258544922,
      "learning_rate": 7.633184221228141e-06,
      "loss": 0.8523,
      "step": 11000
    },
    {
      "epoch": 1.5588992815507658,
      "grad_norm": 15.557079315185547,
      "learning_rate": 6.616510776738511e-06,
      "loss": 0.8387,
      "step": 11500
    },
    {
      "epoch": 1.626677511183408,
      "grad_norm": 14.53345012664795,
      "learning_rate": 5.5998373322488825e-06,
      "loss": 0.8377,
      "step": 12000
    },
    {
      "epoch": 1.6944557408160499,
      "grad_norm": 26.921611785888672,
      "learning_rate": 4.583163887759252e-06,
      "loss": 0.8449,
      "step": 12500
    },
    {
      "epoch": 1.7622339704486918,
      "grad_norm": 12.789366722106934,
      "learning_rate": 3.566490443269622e-06,
      "loss": 0.8547,
      "step": 13000
    },
    {
      "epoch": 1.830012200081334,
      "grad_norm": 37.19759750366211,
      "learning_rate": 2.549816998779992e-06,
      "loss": 0.818,
      "step": 13500
    },
    {
      "epoch": 1.8977904297139758,
      "grad_norm": 14.62682819366455,
      "learning_rate": 1.533143554290362e-06,
      "loss": 0.8128,
      "step": 14000
    },
    {
      "epoch": 1.965568659346618,
      "grad_norm": 21.051790237426758,
      "learning_rate": 5.164701098007319e-07,
      "loss": 0.8115,
      "step": 14500
    },
    {
      "epoch": 2.0,
      "step": 14754,
      "total_flos": 3.541929151120589e+16,
      "train_loss": 1.148573803161563,
      "train_runtime": 3245.3985,
      "train_samples_per_second": 54.554,
      "train_steps_per_second": 4.546
    }
  ],
  "logging_steps": 500,
  "max_steps": 14754,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 3.541929151120589e+16,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}