{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14566783848350068,
  "eval_steps": 500,
  "global_step": 15000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004855594616116689,
      "grad_norm": 3.0736300945281982,
      "learning_rate": 4.991907342306472e-05,
      "loss": 5.2731,
      "step": 500
    },
    {
      "epoch": 0.009711189232233379,
      "grad_norm": 10.307616233825684,
      "learning_rate": 4.983814684612945e-05,
      "loss": 5.2117,
      "step": 1000
    },
    {
      "epoch": 0.014566783848350069,
      "grad_norm": 15.462577819824219,
      "learning_rate": 4.9757220269194165e-05,
      "loss": 5.1878,
      "step": 1500
    },
    {
      "epoch": 0.019422378464466757,
      "grad_norm": 13.30544376373291,
      "learning_rate": 4.967629369225889e-05,
      "loss": 5.1723,
      "step": 2000
    },
    {
      "epoch": 0.024277973080583447,
      "grad_norm": 13.564447402954102,
      "learning_rate": 4.959536711532361e-05,
      "loss": 5.1663,
      "step": 2500
    },
    {
      "epoch": 0.029133567696700138,
      "grad_norm": 15.116345405578613,
      "learning_rate": 4.9514440538388335e-05,
      "loss": 5.1597,
      "step": 3000
    },
    {
      "epoch": 0.033989162312816824,
      "grad_norm": 9.680214881896973,
      "learning_rate": 4.9433513961453054e-05,
      "loss": 5.1509,
      "step": 3500
    },
    {
      "epoch": 0.038844756928933515,
      "grad_norm": 12.354632377624512,
      "learning_rate": 4.935258738451778e-05,
      "loss": 5.1455,
      "step": 4000
    },
    {
      "epoch": 0.043700351545050205,
      "grad_norm": 14.90212345123291,
      "learning_rate": 4.92716608075825e-05,
      "loss": 5.1417,
      "step": 4500
    },
    {
      "epoch": 0.048555946161166895,
      "grad_norm": 12.882039070129395,
      "learning_rate": 4.9190734230647223e-05,
      "loss": 5.1371,
      "step": 5000
    },
    {
      "epoch": 0.053411540777283585,
      "grad_norm": 15.77685546875,
      "learning_rate": 4.910980765371194e-05,
      "loss": 5.1317,
      "step": 5500
    },
    {
      "epoch": 0.058267135393400275,
      "grad_norm": 11.873464584350586,
      "learning_rate": 4.902888107677667e-05,
      "loss": 5.1265,
      "step": 6000
    },
    {
      "epoch": 0.06312273000951696,
      "grad_norm": 14.090598106384277,
      "learning_rate": 4.8947954499841386e-05,
      "loss": 5.1176,
      "step": 6500
    },
    {
      "epoch": 0.06797832462563365,
      "grad_norm": 13.959632873535156,
      "learning_rate": 4.8867027922906105e-05,
      "loss": 5.1135,
      "step": 7000
    },
    {
      "epoch": 0.07283391924175034,
      "grad_norm": 13.812936782836914,
      "learning_rate": 4.878610134597083e-05,
      "loss": 5.1067,
      "step": 7500
    },
    {
      "epoch": 0.07768951385786703,
      "grad_norm": 10.268146514892578,
      "learning_rate": 4.870517476903555e-05,
      "loss": 5.1056,
      "step": 8000
    },
    {
      "epoch": 0.08254510847398372,
      "grad_norm": 13.129918098449707,
      "learning_rate": 4.8624248192100275e-05,
      "loss": 5.0994,
      "step": 8500
    },
    {
      "epoch": 0.08740070309010041,
      "grad_norm": 15.821222305297852,
      "learning_rate": 4.8543321615164994e-05,
      "loss": 5.0889,
      "step": 9000
    },
    {
      "epoch": 0.0922562977062171,
      "grad_norm": 7.900857448577881,
      "learning_rate": 4.846239503822972e-05,
      "loss": 5.0827,
      "step": 9500
    },
    {
      "epoch": 0.09711189232233379,
      "grad_norm": 5.5381903648376465,
      "learning_rate": 4.838146846129444e-05,
      "loss": 5.1042,
      "step": 10000
    },
    {
      "epoch": 0.10196748693845048,
      "grad_norm": 4.201797008514404,
      "learning_rate": 4.830054188435916e-05,
      "loss": 5.0793,
      "step": 10500
    },
    {
      "epoch": 0.10682308155456717,
      "grad_norm": 8.572744369506836,
      "learning_rate": 4.821961530742388e-05,
      "loss": 5.0727,
      "step": 11000
    },
    {
      "epoch": 0.11167867617068386,
      "grad_norm": 10.609322547912598,
      "learning_rate": 4.813868873048861e-05,
      "loss": 5.0683,
      "step": 11500
    },
    {
      "epoch": 0.11653427078680055,
      "grad_norm": 9.953619003295898,
      "learning_rate": 4.8057762153553326e-05,
      "loss": 5.0632,
      "step": 12000
    },
    {
      "epoch": 0.12138986540291724,
      "grad_norm": 8.941683769226074,
      "learning_rate": 4.7976835576618045e-05,
      "loss": 5.0614,
      "step": 12500
    },
    {
      "epoch": 0.12624546001903392,
      "grad_norm": 9.56987190246582,
      "learning_rate": 4.789590899968277e-05,
      "loss": 5.0637,
      "step": 13000
    },
    {
      "epoch": 0.13110105463515062,
      "grad_norm": 7.185657978057861,
      "learning_rate": 4.781498242274749e-05,
      "loss": 5.0569,
      "step": 13500
    },
    {
      "epoch": 0.1359566492512673,
      "grad_norm": 16.51009178161621,
      "learning_rate": 4.7734055845812215e-05,
      "loss": 5.0581,
      "step": 14000
    },
    {
      "epoch": 0.140812243867384,
      "grad_norm": 10.030774116516113,
      "learning_rate": 4.7653129268876933e-05,
      "loss": 5.0552,
      "step": 14500
    },
    {
      "epoch": 0.14566783848350068,
      "grad_norm": 7.811285018920898,
      "learning_rate": 4.757220269194166e-05,
      "loss": 5.0521,
      "step": 15000
    }
  ],
  "logging_steps": 500,
  "max_steps": 308922,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.520669651145851e+17,
  "train_batch_size": 2048,
  "trial_name": null,
  "trial_params": null
}