{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 222,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 6.1063642501831055,
      "learning_rate": 2.9998398686512352e-05,
      "loss": 2.083,
      "step": 10
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 5.588654518127441,
      "learning_rate": 2.9806654415389075e-05,
      "loss": 1.9956,
      "step": 20
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 6.115135192871094,
      "learning_rate": 2.929933201197811e-05,
      "loss": 1.7412,
      "step": 30
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 7.452136993408203,
      "learning_rate": 2.848724417252025e-05,
      "loss": 1.6624,
      "step": 40
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 5.455906867980957,
      "learning_rate": 2.7387699139407064e-05,
      "loss": 1.589,
      "step": 50
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 3.9575319290161133,
      "learning_rate": 2.6024131806044012e-05,
      "loss": 1.581,
      "step": 60
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 5.873230457305908,
      "learning_rate": 2.442560424278399e-05,
      "loss": 1.5157,
      "step": 70
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 4.3736677169799805,
      "learning_rate": 2.2626186289353917e-05,
      "loss": 1.3116,
      "step": 80
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 3.42568302154541,
      "learning_rate": 2.066422941537127e-05,
      "loss": 1.3391,
      "step": 90
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 5.2938923835754395,
      "learning_rate": 1.8581549325353126e-05,
      "loss": 1.2756,
      "step": 100
    },
    {
      "epoch": 1.4864864864864864,
      "grad_norm": 4.406149864196777,
      "learning_rate": 1.642253472957274e-05,
      "loss": 1.2829,
      "step": 110
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 4.457900524139404,
      "learning_rate": 1.4233201275765495e-05,
      "loss": 1.247,
      "step": 120
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 4.813417434692383,
      "learning_rate": 1.206021080548753e-05,
      "loss": 1.3003,
      "step": 130
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 5.256839275360107,
      "learning_rate": 9.949876837974945e-06,
      "loss": 1.1312,
      "step": 140
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 3.5331361293792725,
      "learning_rate": 7.947177477888473e-06,
      "loss": 1.1936,
      "step": 150
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 3.892634153366089,
      "learning_rate": 6.094796785101442e-06,
      "loss": 1.1134,
      "step": 160
    },
    {
      "epoch": 2.2972972972972974,
      "grad_norm": 4.420440196990967,
      "learning_rate": 4.432215038069449e-06,
      "loss": 1.1295,
      "step": 170
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 4.735657691955566,
      "learning_rate": 2.994867280238814e-06,
      "loss": 1.2112,
      "step": 180
    },
    {
      "epoch": 2.5675675675675675,
      "grad_norm": 3.50005841255188,
      "learning_rate": 1.8133880836160682e-06,
      "loss": 1.0869,
      "step": 190
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 3.905202627182007,
      "learning_rate": 9.129586260518635e-07,
      "loss": 0.9863,
      "step": 200
    },
    {
      "epoch": 2.8378378378378377,
      "grad_norm": 4.286425590515137,
      "learning_rate": 3.127699981533755e-07,
      "loss": 1.1179,
      "step": 210
    },
    {
      "epoch": 2.972972972972973,
      "grad_norm": 3.1638362407684326,
      "learning_rate": 2.5614178506644936e-08,
      "loss": 1.174,
      "step": 220
    },
    {
      "epoch": 3.0,
      "step": 222,
      "total_flos": 941914803142656.0,
      "train_loss": 1.3648135576162252,
      "train_runtime": 73.9321,
      "train_samples_per_second": 47.719,
      "train_steps_per_second": 3.003
    }
  ],
  "logging_steps": 10,
  "max_steps": 222,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 941914803142656.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}