{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 21720,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04604051565377532,
      "grad_norm": 4.105458736419678,
      "learning_rate": 2.930939226519337e-05,
      "loss": 0.7338,
      "step": 500
    },
    {
      "epoch": 0.09208103130755065,
      "grad_norm": 6.632126331329346,
      "learning_rate": 2.861878453038674e-05,
      "loss": 0.6214,
      "step": 1000
    },
    {
      "epoch": 0.13812154696132597,
      "grad_norm": 5.542463302612305,
      "learning_rate": 2.7928176795580113e-05,
      "loss": 0.6065,
      "step": 1500
    },
    {
      "epoch": 0.1841620626151013,
      "grad_norm": 8.155370712280273,
      "learning_rate": 2.7237569060773482e-05,
      "loss": 0.5881,
      "step": 2000
    },
    {
      "epoch": 0.2302025782688766,
      "grad_norm": 3.674407720565796,
      "learning_rate": 2.6546961325966852e-05,
      "loss": 0.582,
      "step": 2500
    },
    {
      "epoch": 0.27624309392265195,
      "grad_norm": 3.3256947994232178,
      "learning_rate": 2.585635359116022e-05,
      "loss": 0.577,
      "step": 3000
    },
    {
      "epoch": 0.32228360957642727,
      "grad_norm": 4.420624732971191,
      "learning_rate": 2.516574585635359e-05,
      "loss": 0.5748,
      "step": 3500
    },
    {
      "epoch": 0.3683241252302026,
      "grad_norm": 5.609716892242432,
      "learning_rate": 2.4475138121546964e-05,
      "loss": 0.5532,
      "step": 4000
    },
    {
      "epoch": 0.4143646408839779,
      "grad_norm": 10.64582633972168,
      "learning_rate": 2.3784530386740334e-05,
      "loss": 0.5705,
      "step": 4500
    },
    {
      "epoch": 0.4604051565377532,
      "grad_norm": 4.55027437210083,
      "learning_rate": 2.3093922651933703e-05,
      "loss": 0.5542,
      "step": 5000
    },
    {
      "epoch": 0.5064456721915286,
      "grad_norm": 4.849785327911377,
      "learning_rate": 2.2403314917127073e-05,
      "loss": 0.5561,
      "step": 5500
    },
    {
      "epoch": 0.5524861878453039,
      "grad_norm": 7.6427154541015625,
      "learning_rate": 2.1712707182320442e-05,
      "loss": 0.5427,
      "step": 6000
    },
    {
      "epoch": 0.5985267034990792,
      "grad_norm": 4.943839073181152,
      "learning_rate": 2.1022099447513815e-05,
      "loss": 0.548,
      "step": 6500
    },
    {
      "epoch": 0.6445672191528545,
      "grad_norm": 3.1242663860321045,
      "learning_rate": 2.0331491712707185e-05,
      "loss": 0.5401,
      "step": 7000
    },
    {
      "epoch": 0.6906077348066298,
      "grad_norm": 4.478808403015137,
      "learning_rate": 1.9640883977900554e-05,
      "loss": 0.5444,
      "step": 7500
    },
    {
      "epoch": 0.7366482504604052,
      "grad_norm": 5.4113054275512695,
      "learning_rate": 1.8950276243093924e-05,
      "loss": 0.545,
      "step": 8000
    },
    {
      "epoch": 0.7826887661141805,
      "grad_norm": 3.117663860321045,
      "learning_rate": 1.825966850828729e-05,
      "loss": 0.5268,
      "step": 8500
    },
    {
      "epoch": 0.8287292817679558,
      "grad_norm": 4.178927421569824,
      "learning_rate": 1.7569060773480663e-05,
      "loss": 0.5441,
      "step": 9000
    },
    {
      "epoch": 0.8747697974217311,
      "grad_norm": 8.61349868774414,
      "learning_rate": 1.6878453038674033e-05,
      "loss": 0.5383,
      "step": 9500
    },
    {
      "epoch": 0.9208103130755064,
      "grad_norm": 5.246815204620361,
      "learning_rate": 1.6187845303867402e-05,
      "loss": 0.5386,
      "step": 10000
    },
    {
      "epoch": 0.9668508287292817,
      "grad_norm": 5.026543140411377,
      "learning_rate": 1.5497237569060772e-05,
      "loss": 0.5313,
      "step": 10500
    },
    {
      "epoch": 1.0128913443830572,
      "grad_norm": 3.600374937057495,
      "learning_rate": 1.4806629834254145e-05,
      "loss": 0.5252,
      "step": 11000
    },
    {
      "epoch": 1.0589318600368325,
      "grad_norm": 3.5238852500915527,
      "learning_rate": 1.4116022099447514e-05,
      "loss": 0.4928,
      "step": 11500
    },
    {
      "epoch": 1.1049723756906078,
      "grad_norm": 4.74073600769043,
      "learning_rate": 1.3425414364640886e-05,
      "loss": 0.5087,
      "step": 12000
    },
    {
      "epoch": 1.1510128913443831,
      "grad_norm": 8.856585502624512,
      "learning_rate": 1.2734806629834255e-05,
      "loss": 0.4898,
      "step": 12500
    },
    {
      "epoch": 1.1970534069981584,
      "grad_norm": 8.898761749267578,
      "learning_rate": 1.2044198895027623e-05,
      "loss": 0.5066,
      "step": 13000
    },
    {
      "epoch": 1.2430939226519337,
      "grad_norm": 5.918560028076172,
      "learning_rate": 1.1353591160220994e-05,
      "loss": 0.5149,
      "step": 13500
    },
    {
      "epoch": 1.289134438305709,
      "grad_norm": 4.796153545379639,
      "learning_rate": 1.0662983425414364e-05,
      "loss": 0.5006,
      "step": 14000
    },
    {
      "epoch": 1.3351749539594844,
      "grad_norm": 5.584662914276123,
      "learning_rate": 9.972375690607735e-06,
      "loss": 0.5058,
      "step": 14500
    },
    {
      "epoch": 1.3812154696132597,
      "grad_norm": 9.456035614013672,
      "learning_rate": 9.281767955801105e-06,
      "loss": 0.4885,
      "step": 15000
    },
    {
      "epoch": 1.427255985267035,
      "grad_norm": 3.6488196849823,
      "learning_rate": 8.591160220994474e-06,
      "loss": 0.4914,
      "step": 15500
    },
    {
      "epoch": 1.4732965009208103,
      "grad_norm": 3.0951404571533203,
      "learning_rate": 7.900552486187846e-06,
      "loss": 0.5016,
      "step": 16000
    },
    {
      "epoch": 1.5193370165745856,
      "grad_norm": 5.87822151184082,
      "learning_rate": 7.209944751381215e-06,
      "loss": 0.5117,
      "step": 16500
    },
    {
      "epoch": 1.565377532228361,
      "grad_norm": 5.016966819763184,
      "learning_rate": 6.519337016574586e-06,
      "loss": 0.5134,
      "step": 17000
    },
    {
      "epoch": 1.6114180478821363,
      "grad_norm": 8.312193870544434,
      "learning_rate": 5.828729281767956e-06,
      "loss": 0.4934,
      "step": 17500
    },
    {
      "epoch": 1.6574585635359116,
      "grad_norm": 5.323014736175537,
      "learning_rate": 5.1381215469613265e-06,
      "loss": 0.5025,
      "step": 18000
    },
    {
      "epoch": 1.703499079189687,
      "grad_norm": 4.238588809967041,
      "learning_rate": 4.447513812154697e-06,
      "loss": 0.4948,
      "step": 18500
    },
    {
      "epoch": 1.7495395948434622,
      "grad_norm": 3.3375260829925537,
      "learning_rate": 3.756906077348067e-06,
      "loss": 0.5086,
      "step": 19000
    },
    {
      "epoch": 1.7955801104972375,
      "grad_norm": 6.620930194854736,
      "learning_rate": 3.0662983425414365e-06,
      "loss": 0.4931,
      "step": 19500
    },
    {
      "epoch": 1.8416206261510129,
      "grad_norm": 4.153687000274658,
      "learning_rate": 2.375690607734807e-06,
      "loss": 0.4853,
      "step": 20000
    },
    {
      "epoch": 1.8876611418047882,
      "grad_norm": 5.683996677398682,
      "learning_rate": 1.6850828729281769e-06,
      "loss": 0.492,
      "step": 20500
    },
    {
      "epoch": 1.9337016574585635,
      "grad_norm": 3.776688575744629,
      "learning_rate": 9.944751381215469e-07,
      "loss": 0.4876,
      "step": 21000
    },
    {
      "epoch": 1.979742173112339,
      "grad_norm": 2.931673526763916,
      "learning_rate": 3.0386740331491715e-07,
      "loss": 0.5069,
      "step": 21500
    },
    {
      "epoch": 2.0,
      "step": 21720,
      "total_flos": 2.645641233904435e+16,
      "train_loss": 0.5331895410246172,
      "train_runtime": 7144.6567,
      "train_samples_per_second": 36.48,
      "train_steps_per_second": 3.04
    }
  ],
  "logging_steps": 500,
  "max_steps": 21720,
  "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": 2.645641233904435e+16,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}