{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 29,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034482758620689655,
      "grad_norm": 3.9996883869171143,
      "learning_rate": 3.333333333333333e-07,
      "loss": 1.4892,
      "mean_token_accuracy": 0.6603646278381348,
      "step": 1
    },
    {
      "epoch": 0.06896551724137931,
      "grad_norm": 4.237244606018066,
      "learning_rate": 6.666666666666666e-07,
      "loss": 1.4666,
      "mean_token_accuracy": 0.7045964002609253,
      "step": 2
    },
    {
      "epoch": 0.10344827586206896,
      "grad_norm": 4.874926567077637,
      "learning_rate": 1e-06,
      "loss": 1.7228,
      "mean_token_accuracy": 0.6302095651626587,
      "step": 3
    },
    {
      "epoch": 0.13793103448275862,
      "grad_norm": 4.235203266143799,
      "learning_rate": 9.963544370490268e-07,
      "loss": 1.4493,
      "mean_token_accuracy": 0.6814345717430115,
      "step": 4
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 7.380453109741211,
      "learning_rate": 9.85470908713026e-07,
      "loss": 2.0416,
      "mean_token_accuracy": 0.6577650904655457,
      "step": 5
    },
    {
      "epoch": 0.20689655172413793,
      "grad_norm": 3.541438341140747,
      "learning_rate": 9.675081213427074e-07,
      "loss": 1.2546,
      "mean_token_accuracy": 0.7483809590339661,
      "step": 6
    },
    {
      "epoch": 0.2413793103448276,
      "grad_norm": 3.448702812194824,
      "learning_rate": 9.427280128266049e-07,
      "loss": 1.3896,
      "mean_token_accuracy": 0.6593328714370728,
      "step": 7
    },
    {
      "epoch": 0.27586206896551724,
      "grad_norm": 3.706294298171997,
      "learning_rate": 9.114919329468282e-07,
      "loss": 1.4015,
      "mean_token_accuracy": 0.6922000646591187,
      "step": 8
    },
    {
      "epoch": 0.3103448275862069,
      "grad_norm": 4.539882659912109,
      "learning_rate": 8.742553740855505e-07,
      "loss": 1.7425,
      "mean_token_accuracy": 0.5878053307533264,
      "step": 9
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 3.8082709312438965,
      "learning_rate": 8.315613291203976e-07,
      "loss": 1.4157,
      "mean_token_accuracy": 0.6789916157722473,
      "step": 10
    },
    {
      "epoch": 0.3793103448275862,
      "grad_norm": 5.028677940368652,
      "learning_rate": 7.840323733655778e-07,
      "loss": 1.755,
      "mean_token_accuracy": 0.6366782188415527,
      "step": 11
    },
    {
      "epoch": 0.41379310344827586,
      "grad_norm": 5.152957439422607,
      "learning_rate": 7.323615860218842e-07,
      "loss": 1.7695,
      "mean_token_accuracy": 0.6314002275466919,
      "step": 12
    },
    {
      "epoch": 0.4482758620689655,
      "grad_norm": 3.268697738647461,
      "learning_rate": 6.773024435212677e-07,
      "loss": 1.4895,
      "mean_token_accuracy": 0.6149526834487915,
      "step": 13
    },
    {
      "epoch": 0.4827586206896552,
      "grad_norm": 3.3466408252716064,
      "learning_rate": 6.196578321437789e-07,
      "loss": 1.1299,
      "mean_token_accuracy": 0.7559174299240112,
      "step": 14
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 4.494246482849121,
      "learning_rate": 5.602683401276614e-07,
      "loss": 1.5723,
      "mean_token_accuracy": 0.6703522801399231,
      "step": 15
    },
    {
      "epoch": 0.5517241379310345,
      "grad_norm": 2.2075376510620117,
      "learning_rate": 5e-07,
      "loss": 1.0356,
      "mean_token_accuracy": 0.7093867063522339,
      "step": 16
    },
    {
      "epoch": 0.5862068965517241,
      "grad_norm": 2.7901251316070557,
      "learning_rate": 4.397316598723385e-07,
      "loss": 1.1132,
      "mean_token_accuracy": 0.7466140985488892,
      "step": 17
    },
    {
      "epoch": 0.6206896551724138,
      "grad_norm": 3.604022979736328,
      "learning_rate": 3.8034216785622125e-07,
      "loss": 1.3046,
      "mean_token_accuracy": 0.7072184681892395,
      "step": 18
    },
    {
      "epoch": 0.6551724137931034,
      "grad_norm": 3.637402057647705,
      "learning_rate": 3.2269755647873214e-07,
      "loss": 1.5471,
      "mean_token_accuracy": 0.6090646386146545,
      "step": 19
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 3.484041452407837,
      "learning_rate": 2.676384139781157e-07,
      "loss": 1.4808,
      "mean_token_accuracy": 0.6458947658538818,
      "step": 20
    },
    {
      "epoch": 0.7241379310344828,
      "grad_norm": 4.93519926071167,
      "learning_rate": 2.1596762663442213e-07,
      "loss": 1.853,
      "mean_token_accuracy": 0.6095913648605347,
      "step": 21
    },
    {
      "epoch": 0.7586206896551724,
      "grad_norm": 6.128385543823242,
      "learning_rate": 1.6843867087960251e-07,
      "loss": 1.552,
      "mean_token_accuracy": 0.6161980032920837,
      "step": 22
    },
    {
      "epoch": 0.7931034482758621,
      "grad_norm": 5.635701656341553,
      "learning_rate": 1.257446259144494e-07,
      "loss": 1.5498,
      "mean_token_accuracy": 0.7546396851539612,
      "step": 23
    },
    {
      "epoch": 0.8275862068965517,
      "grad_norm": 3.2936410903930664,
      "learning_rate": 8.850806705317182e-08,
      "loss": 1.542,
      "mean_token_accuracy": 0.5884397029876709,
      "step": 24
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 3.3056509494781494,
      "learning_rate": 5.72719871733951e-08,
      "loss": 1.4571,
      "mean_token_accuracy": 0.677709698677063,
      "step": 25
    },
    {
      "epoch": 0.896551724137931,
      "grad_norm": 3.8348419666290283,
      "learning_rate": 3.2491878657292635e-08,
      "loss": 1.5325,
      "mean_token_accuracy": 0.6370223760604858,
      "step": 26
    },
    {
      "epoch": 0.9310344827586207,
      "grad_norm": 3.4010775089263916,
      "learning_rate": 1.4529091286973993e-08,
      "loss": 1.3759,
      "mean_token_accuracy": 0.6779050230979919,
      "step": 27
    },
    {
      "epoch": 0.9655172413793104,
      "grad_norm": 3.990252733230591,
      "learning_rate": 3.6455629509730135e-09,
      "loss": 1.4335,
      "mean_token_accuracy": 0.688022255897522,
      "step": 28
    },
    {
      "epoch": 1.0,
      "grad_norm": 4.286991596221924,
      "learning_rate": 0.0,
      "loss": 1.5531,
      "mean_token_accuracy": 0.6274685859680176,
      "step": 29
    },
    {
      "epoch": 1.0,
      "step": 29,
      "total_flos": 978754951168.0,
      "train_loss": 1.4972400459749946,
      "train_runtime": 1197.8134,
      "train_samples_per_second": 0.095,
      "train_steps_per_second": 0.024
    }
  ],
  "logging_steps": 1,
  "max_steps": 29,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 978754951168.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}