{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 279,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03593890386343217,
      "grad_norm": 3.182513952255249,
      "learning_rate": 5.142857142857143e-06,
      "loss": 0.9999963760375976,
      "step": 10
    },
    {
      "epoch": 0.07187780772686433,
      "grad_norm": 1.173149585723877,
      "learning_rate": 7.992974927057286e-06,
      "loss": 0.5433789730072022,
      "step": 20
    },
    {
      "epoch": 0.1078167115902965,
      "grad_norm": 0.8281139731407166,
      "learning_rate": 7.936922311790387e-06,
      "loss": 0.4406783103942871,
      "step": 30
    },
    {
      "epoch": 0.14375561545372867,
      "grad_norm": 0.8478610515594482,
      "learning_rate": 7.825603937106089e-06,
      "loss": 0.4059865951538086,
      "step": 40
    },
    {
      "epoch": 0.17969451931716082,
      "grad_norm": 0.8095178604125977,
      "learning_rate": 7.660582468972073e-06,
      "loss": 0.38223881721496583,
      "step": 50
    },
    {
      "epoch": 0.215633423180593,
      "grad_norm": 0.7364096641540527,
      "learning_rate": 7.444174447069421e-06,
      "loss": 0.37668166160583494,
      "step": 60
    },
    {
      "epoch": 0.25157232704402516,
      "grad_norm": 0.7268216609954834,
      "learning_rate": 7.179417765653413e-06,
      "loss": 0.359727144241333,
      "step": 70
    },
    {
      "epoch": 0.28751123090745734,
      "grad_norm": 0.7387126684188843,
      "learning_rate": 6.870029028177324e-06,
      "loss": 0.35879950523376464,
      "step": 80
    },
    {
      "epoch": 0.32345013477088946,
      "grad_norm": 0.8118855953216553,
      "learning_rate": 6.520351374326845e-06,
      "loss": 0.350269079208374,
      "step": 90
    },
    {
      "epoch": 0.35938903863432164,
      "grad_norm": 0.7069733738899231,
      "learning_rate": 6.1352935118591635e-06,
      "loss": 0.35556807518005373,
      "step": 100
    },
    {
      "epoch": 0.3953279424977538,
      "grad_norm": 0.7542175650596619,
      "learning_rate": 5.720260809106082e-06,
      "loss": 0.3427577495574951,
      "step": 110
    },
    {
      "epoch": 0.431266846361186,
      "grad_norm": 0.8069055080413818,
      "learning_rate": 5.28107941545135e-06,
      "loss": 0.3359182596206665,
      "step": 120
    },
    {
      "epoch": 0.46720575022461813,
      "grad_norm": 0.8552827835083008,
      "learning_rate": 4.823914474964393e-06,
      "loss": 0.3400346040725708,
      "step": 130
    },
    {
      "epoch": 0.5031446540880503,
      "grad_norm": 0.7165119647979736,
      "learning_rate": 4.355183581291739e-06,
      "loss": 0.3393260478973389,
      "step": 140
    },
    {
      "epoch": 0.5390835579514824,
      "grad_norm": 0.7520389556884766,
      "learning_rate": 3.8814666887097606e-06,
      "loss": 0.33171849250793456,
      "step": 150
    },
    {
      "epoch": 0.5750224618149147,
      "grad_norm": 0.6773005723953247,
      "learning_rate": 3.4094137439900755e-06,
      "loss": 0.33351149559021,
      "step": 160
    },
    {
      "epoch": 0.6109613656783468,
      "grad_norm": 0.7068390846252441,
      "learning_rate": 2.94565133572373e-06,
      "loss": 0.32773785591125487,
      "step": 170
    },
    {
      "epoch": 0.6469002695417789,
      "grad_norm": 0.8255635499954224,
      "learning_rate": 2.496689671543048e-06,
      "loss": 0.32363770008087156,
      "step": 180
    },
    {
      "epoch": 0.6828391734052112,
      "grad_norm": 0.6686235070228577,
      "learning_rate": 2.068831189077021e-06,
      "loss": 0.33127546310424805,
      "step": 190
    },
    {
      "epoch": 0.7187780772686433,
      "grad_norm": 0.7526047229766846,
      "learning_rate": 1.6680820835421124e-06,
      "loss": 0.3253414392471313,
      "step": 200
    },
    {
      "epoch": 0.7547169811320755,
      "grad_norm": 0.6801684498786926,
      "learning_rate": 1.3000679939271586e-06,
      "loss": 0.32832999229431153,
      "step": 210
    },
    {
      "epoch": 0.7906558849955077,
      "grad_norm": 0.6622071266174316,
      "learning_rate": 9.699550313535194e-07,
      "loss": 0.33035430908203123,
      "step": 220
    },
    {
      "epoch": 0.8265947888589398,
      "grad_norm": 0.6161302924156189,
      "learning_rate": 6.823772581991929e-07,
      "loss": 0.31977477073669436,
      "step": 230
    },
    {
      "epoch": 0.862533692722372,
      "grad_norm": 0.6483022570610046,
      "learning_rate": 4.413716360210111e-07,
      "loss": 0.32599825859069825,
      "step": 240
    },
    {
      "epoch": 0.8984725965858041,
      "grad_norm": 0.6623414158821106,
      "learning_rate": 2.503213554635164e-07,
      "loss": 0.3147287845611572,
      "step": 250
    },
    {
      "epoch": 0.9344115004492363,
      "grad_norm": 0.6427763104438782,
      "learning_rate": 1.11908343678357e-07,
      "loss": 0.32068469524383547,
      "step": 260
    },
    {
      "epoch": 0.9703504043126685,
      "grad_norm": 0.6542255878448486,
      "learning_rate": 2.8075615945932328e-08,
      "loss": 0.3222502708435059,
      "step": 270
    },
    {
      "epoch": 1.0,
      "step": 279,
      "total_flos": 3.329238633864495e+18,
      "train_loss": 0.37422844500524594,
      "train_runtime": 1723.7802,
      "train_samples_per_second": 20.659,
      "train_steps_per_second": 0.162
    }
  ],
  "logging_steps": 10,
  "max_steps": 279,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3.329238633864495e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}