{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 205,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04884004884004884,
      "grad_norm": 2.951613426208496,
      "learning_rate": 6.545454545454546e-06,
      "loss": 1.6103919982910155,
      "step": 10
    },
    {
      "epoch": 0.09768009768009768,
      "grad_norm": 1.4161419868469238,
      "learning_rate": 7.9664804049057e-06,
      "loss": 1.1710912704467773,
      "step": 20
    },
    {
      "epoch": 0.14652014652014653,
      "grad_norm": 1.1890255212783813,
      "learning_rate": 7.831269296751948e-06,
      "loss": 1.0446645736694335,
      "step": 30
    },
    {
      "epoch": 0.19536019536019536,
      "grad_norm": 1.1855751276016235,
      "learning_rate": 7.595806964341581e-06,
      "loss": 0.9899624824523926,
      "step": 40
    },
    {
      "epoch": 0.2442002442002442,
      "grad_norm": 1.4533610343933105,
      "learning_rate": 7.266254652228843e-06,
      "loss": 0.9951982498168945,
      "step": 50
    },
    {
      "epoch": 0.29304029304029305,
      "grad_norm": 1.264499545097351,
      "learning_rate": 6.851235618187317e-06,
      "loss": 0.9782312393188477,
      "step": 60
    },
    {
      "epoch": 0.3418803418803419,
      "grad_norm": 1.3089553117752075,
      "learning_rate": 6.36160949202369e-06,
      "loss": 0.9667717933654785,
      "step": 70
    },
    {
      "epoch": 0.3907203907203907,
      "grad_norm": 1.0916252136230469,
      "learning_rate": 5.810188116178156e-06,
      "loss": 0.9572884559631347,
      "step": 80
    },
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 1.2539805173873901,
      "learning_rate": 5.211400303591802e-06,
      "loss": 0.9558270454406739,
      "step": 90
    },
    {
      "epoch": 0.4884004884004884,
      "grad_norm": 1.1267527341842651,
      "learning_rate": 4.580914284981961e-06,
      "loss": 0.9527605056762696,
      "step": 100
    },
    {
      "epoch": 0.5372405372405372,
      "grad_norm": 1.0940070152282715,
      "learning_rate": 3.935227724789994e-06,
      "loss": 0.9419396400451661,
      "step": 110
    },
    {
      "epoch": 0.5860805860805861,
      "grad_norm": 1.7783108949661255,
      "learning_rate": 3.2912360336831093e-06,
      "loss": 0.9319709777832031,
      "step": 120
    },
    {
      "epoch": 0.6349206349206349,
      "grad_norm": 1.1148947477340698,
      "learning_rate": 2.665790273396718e-06,
      "loss": 0.9522204399108887,
      "step": 130
    },
    {
      "epoch": 0.6837606837606838,
      "grad_norm": 1.0567108392715454,
      "learning_rate": 2.0752562220367795e-06,
      "loss": 0.9412946701049805,
      "step": 140
    },
    {
      "epoch": 0.7326007326007326,
      "grad_norm": 1.0418899059295654,
      "learning_rate": 1.5350861375962904e-06,
      "loss": 0.9191699981689453,
      "step": 150
    },
    {
      "epoch": 0.7814407814407814,
      "grad_norm": 0.9806021451950073,
      "learning_rate": 1.0594144251711994e-06,
      "loss": 0.9190822601318359,
      "step": 160
    },
    {
      "epoch": 0.8302808302808303,
      "grad_norm": 1.0123064517974854,
      "learning_rate": 6.606877878829161e-07,
      "loss": 0.9286371231079101,
      "step": 170
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 1.079588770866394,
      "learning_rate": 3.4933953919383984e-07,
      "loss": 0.9289794921875,
      "step": 180
    },
    {
      "epoch": 0.927960927960928,
      "grad_norm": 1.2275781631469727,
      "learning_rate": 1.3351659874955546e-07,
      "loss": 0.919953727722168,
      "step": 190
    },
    {
      "epoch": 0.9768009768009768,
      "grad_norm": 1.0596216917037964,
      "learning_rate": 1.8866315333544213e-08,
      "loss": 0.9213088989257813,
      "step": 200
    },
    {
      "epoch": 1.0,
      "step": 205,
      "total_flos": 2.640143661303595e+18,
      "train_loss": 0.9932206619076612,
      "train_runtime": 1797.9362,
      "train_samples_per_second": 7.286,
      "train_steps_per_second": 0.114
    }
  ],
  "logging_steps": 10,
  "max_steps": 205,
  "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": 2.640143661303595e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}