{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 25.0,
  "eval_steps": 500,
  "global_step": 2475,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.0202020202020203,
      "grad_norm": 3.2150983810424805,
      "learning_rate": 4.595959595959596e-05,
      "loss": 1.8523,
      "step": 200
    },
    {
      "epoch": 4.040404040404041,
      "grad_norm": 1.2652349472045898,
      "learning_rate": 4.191919191919192e-05,
      "loss": 0.4357,
      "step": 400
    },
    {
      "epoch": 6.0606060606060606,
      "grad_norm": 1.2245885133743286,
      "learning_rate": 3.787878787878788e-05,
      "loss": 0.2712,
      "step": 600
    },
    {
      "epoch": 8.080808080808081,
      "grad_norm": 1.4887850284576416,
      "learning_rate": 3.3838383838383844e-05,
      "loss": 0.1956,
      "step": 800
    },
    {
      "epoch": 10.1010101010101,
      "grad_norm": 1.4152169227600098,
      "learning_rate": 2.9797979797979796e-05,
      "loss": 0.1566,
      "step": 1000
    },
    {
      "epoch": 12.121212121212121,
      "grad_norm": 0.9230123162269592,
      "learning_rate": 2.575757575757576e-05,
      "loss": 0.1279,
      "step": 1200
    },
    {
      "epoch": 14.141414141414142,
      "grad_norm": 0.9463744163513184,
      "learning_rate": 2.171717171717172e-05,
      "loss": 0.0987,
      "step": 1400
    },
    {
      "epoch": 16.161616161616163,
      "grad_norm": 1.6643699407577515,
      "learning_rate": 1.7676767676767676e-05,
      "loss": 0.0871,
      "step": 1600
    },
    {
      "epoch": 18.181818181818183,
      "grad_norm": 0.7526511549949646,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 0.076,
      "step": 1800
    },
    {
      "epoch": 20.2020202020202,
      "grad_norm": 0.8697160482406616,
      "learning_rate": 9.595959595959595e-06,
      "loss": 0.0647,
      "step": 2000
    },
    {
      "epoch": 22.22222222222222,
      "grad_norm": 0.369678258895874,
      "learning_rate": 5.555555555555556e-06,
      "loss": 0.0618,
      "step": 2200
    },
    {
      "epoch": 24.242424242424242,
      "grad_norm": 0.760077178478241,
      "learning_rate": 1.5151515151515152e-06,
      "loss": 0.0546,
      "step": 2400
    }
  ],
  "logging_steps": 200,
  "max_steps": 2475,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 25,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2995330351104000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}