{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.954653937947494,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0477326968973747,
      "grad_norm": 4.068389892578125,
      "learning_rate": 4.761904761904762e-05,
      "loss": 2.3107,
      "step": 100
    },
    {
      "epoch": 0.0954653937947494,
      "grad_norm": 2.991318464279175,
      "learning_rate": 9.523809523809524e-05,
      "loss": 1.8576,
      "step": 200
    },
    {
      "epoch": 0.1431980906921241,
      "grad_norm": 2.333883285522461,
      "learning_rate": 9.943858030057405e-05,
      "loss": 1.7539,
      "step": 300
    },
    {
      "epoch": 0.1909307875894988,
      "grad_norm": 2.2262773513793945,
      "learning_rate": 9.751405104519151e-05,
      "loss": 1.692,
      "step": 400
    },
    {
      "epoch": 0.2386634844868735,
      "grad_norm": 2.6444602012634277,
      "learning_rate": 9.42728012826605e-05,
      "loss": 1.6101,
      "step": 500
    },
    {
      "epoch": 0.2863961813842482,
      "grad_norm": 2.4133706092834473,
      "learning_rate": 8.980465328528219e-05,
      "loss": 1.6038,
      "step": 600
    },
    {
      "epoch": 0.3341288782816229,
      "grad_norm": 2.31902813911438,
      "learning_rate": 8.423342941649866e-05,
      "loss": 1.5127,
      "step": 700
    },
    {
      "epoch": 0.3818615751789976,
      "grad_norm": 2.5150299072265625,
      "learning_rate": 7.771352073656629e-05,
      "loss": 1.4941,
      "step": 800
    },
    {
      "epoch": 0.4295942720763723,
      "grad_norm": 2.1890738010406494,
      "learning_rate": 7.042560848134592e-05,
      "loss": 1.4806,
      "step": 900
    },
    {
      "epoch": 0.477326968973747,
      "grad_norm": 2.1867263317108154,
      "learning_rate": 6.257165698159149e-05,
      "loss": 1.4077,
      "step": 1000
    },
    {
      "epoch": 0.5250596658711217,
      "grad_norm": 2.231353521347046,
      "learning_rate": 5.4369316780129554e-05,
      "loss": 1.4155,
      "step": 1100
    },
    {
      "epoch": 0.5727923627684964,
      "grad_norm": 2.0291645526885986,
      "learning_rate": 4.604589304905754e-05,
      "loss": 1.3634,
      "step": 1200
    },
    {
      "epoch": 0.6205250596658711,
      "grad_norm": 2.1311423778533936,
      "learning_rate": 3.783204645559504e-05,
      "loss": 1.3241,
      "step": 1300
    },
    {
      "epoch": 0.6682577565632458,
      "grad_norm": 1.8706629276275635,
      "learning_rate": 2.995540103966864e-05,
      "loss": 1.2945,
      "step": 1400
    },
    {
      "epoch": 0.7159904534606205,
      "grad_norm": 1.8337299823760986,
      "learning_rate": 2.263423624322326e-05,
      "loss": 1.264,
      "step": 1500
    },
    {
      "epoch": 0.7637231503579952,
      "grad_norm": 1.8664114475250244,
      "learning_rate": 1.6071437899220688e-05,
      "loss": 1.2934,
      "step": 1600
    },
    {
      "epoch": 0.8114558472553699,
      "grad_norm": 2.2168829441070557,
      "learning_rate": 1.0448875811934417e-05,
      "loss": 1.2624,
      "step": 1700
    },
    {
      "epoch": 0.8591885441527446,
      "grad_norm": 2.4389848709106445,
      "learning_rate": 5.922363738351888e-06,
      "loss": 1.2715,
      "step": 1800
    },
    {
      "epoch": 0.9069212410501193,
      "grad_norm": 2.066229820251465,
      "learning_rate": 2.6173414408598827e-06,
      "loss": 1.2322,
      "step": 1900
    },
    {
      "epoch": 0.954653937947494,
      "grad_norm": 1.689720869064331,
      "learning_rate": 6.253984711796612e-07,
      "loss": 1.2093,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 2095,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.602614826159309e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}