{
  "best_metric": 1.367624282836914,
  "best_model_checkpoint": "./results/checkpoint-11635",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 11635,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.21486892995272883,
      "grad_norm": 1.7943241596221924,
      "learning_rate": 4.7851310700472715e-05,
      "loss": 1.815,
      "step": 500
    },
    {
      "epoch": 0.42973785990545765,
      "grad_norm": 1.5547664165496826,
      "learning_rate": 4.570262140094543e-05,
      "loss": 1.7137,
      "step": 1000
    },
    {
      "epoch": 0.6446067898581865,
      "grad_norm": 1.829068899154663,
      "learning_rate": 4.355393210141814e-05,
      "loss": 1.6652,
      "step": 1500
    },
    {
      "epoch": 0.8594757198109153,
      "grad_norm": 1.6881290674209595,
      "learning_rate": 4.140524280189085e-05,
      "loss": 1.6365,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.4293888807296753,
      "eval_runtime": 13.2899,
      "eval_samples_per_second": 352.072,
      "eval_steps_per_second": 2.784,
      "step": 2327
    },
    {
      "epoch": 1.0743446497636442,
      "grad_norm": 1.6054766178131104,
      "learning_rate": 3.9256553502363556e-05,
      "loss": 1.5857,
      "step": 2500
    },
    {
      "epoch": 1.289213579716373,
      "grad_norm": 1.550986647605896,
      "learning_rate": 3.7107864202836275e-05,
      "loss": 1.5097,
      "step": 3000
    },
    {
      "epoch": 1.504082509669102,
      "grad_norm": 1.5548337697982788,
      "learning_rate": 3.495917490330898e-05,
      "loss": 1.495,
      "step": 3500
    },
    {
      "epoch": 1.7189514396218306,
      "grad_norm": 1.5597646236419678,
      "learning_rate": 3.281048560378169e-05,
      "loss": 1.4887,
      "step": 4000
    },
    {
      "epoch": 1.9338203695745595,
      "grad_norm": 1.4021880626678467,
      "learning_rate": 3.066179630425441e-05,
      "loss": 1.4862,
      "step": 4500
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.390964150428772,
      "eval_runtime": 13.2972,
      "eval_samples_per_second": 351.878,
      "eval_steps_per_second": 2.783,
      "step": 4654
    },
    {
      "epoch": 2.1486892995272884,
      "grad_norm": 1.399411916732788,
      "learning_rate": 2.8513107004727117e-05,
      "loss": 1.4227,
      "step": 5000
    },
    {
      "epoch": 2.363558229480017,
      "grad_norm": 1.5368090867996216,
      "learning_rate": 2.636441770519983e-05,
      "loss": 1.3905,
      "step": 5500
    },
    {
      "epoch": 2.578427159432746,
      "grad_norm": 1.406023383140564,
      "learning_rate": 2.421572840567254e-05,
      "loss": 1.3967,
      "step": 6000
    },
    {
      "epoch": 2.793296089385475,
      "grad_norm": 1.437154769897461,
      "learning_rate": 2.206703910614525e-05,
      "loss": 1.4,
      "step": 6500
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.3757044076919556,
      "eval_runtime": 13.2522,
      "eval_samples_per_second": 353.074,
      "eval_steps_per_second": 2.792,
      "step": 6981
    },
    {
      "epoch": 3.008165019338204,
      "grad_norm": 1.37666916847229,
      "learning_rate": 1.9918349806617966e-05,
      "loss": 1.392,
      "step": 7000
    },
    {
      "epoch": 3.2230339492909326,
      "grad_norm": 1.4489548206329346,
      "learning_rate": 1.7769660507090678e-05,
      "loss": 1.3282,
      "step": 7500
    },
    {
      "epoch": 3.4379028792436612,
      "grad_norm": 1.3192425966262817,
      "learning_rate": 1.5620971207563386e-05,
      "loss": 1.333,
      "step": 8000
    },
    {
      "epoch": 3.6527718091963903,
      "grad_norm": 1.4072356224060059,
      "learning_rate": 1.34722819080361e-05,
      "loss": 1.3261,
      "step": 8500
    },
    {
      "epoch": 3.867640739149119,
      "grad_norm": 1.4121943712234497,
      "learning_rate": 1.1323592608508809e-05,
      "loss": 1.336,
      "step": 9000
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.368784785270691,
      "eval_runtime": 13.295,
      "eval_samples_per_second": 351.936,
      "eval_steps_per_second": 2.783,
      "step": 9308
    },
    {
      "epoch": 4.082509669101848,
      "grad_norm": 1.347611904144287,
      "learning_rate": 9.174903308981523e-06,
      "loss": 1.3144,
      "step": 9500
    },
    {
      "epoch": 4.297378599054577,
      "grad_norm": 1.3636679649353027,
      "learning_rate": 7.026214009454233e-06,
      "loss": 1.2937,
      "step": 10000
    },
    {
      "epoch": 4.512247529007306,
      "grad_norm": 1.3717917203903198,
      "learning_rate": 4.877524709926945e-06,
      "loss": 1.2912,
      "step": 10500
    },
    {
      "epoch": 4.727116458960034,
      "grad_norm": 1.5116732120513916,
      "learning_rate": 2.7288354103996563e-06,
      "loss": 1.2907,
      "step": 11000
    },
    {
      "epoch": 4.941985388912763,
      "grad_norm": 1.450828194618225,
      "learning_rate": 5.801461108723678e-07,
      "loss": 1.2871,
      "step": 11500
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.367624282836914,
      "eval_runtime": 13.3043,
      "eval_samples_per_second": 351.69,
      "eval_steps_per_second": 2.781,
      "step": 11635
    }
  ],
  "logging_steps": 500,
  "max_steps": 11635,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "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": 2.523724794298368e+16,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}